diff --git a/Documentation/ABI/testing/sysfs-bus-iio b/Documentation/ABI/testing/sysfs-bus-iio index df42bed09f25d8d3db72b2745e193457d8959a98..53f07fc41b966067682e956768acfe670ef39603 100644 --- a/Documentation/ABI/testing/sysfs-bus-iio +++ b/Documentation/ABI/testing/sysfs-bus-iio @@ -142,7 +142,7 @@ Description: Raw capacitance measurement from channel Y. Units after application of scale and offset are nanofarads. -What: /sys/.../iio:deviceX/in_capacitanceY-in_capacitanceZ_raw +What: /sys/.../iio:deviceX/in_capacitanceY-capacitanceZ_raw KernelVersion: 3.2 Contact: linux-iio@vger.kernel.org Description: diff --git a/Documentation/arm64/silicon-errata.rst b/Documentation/arm64/silicon-errata.rst index cd7b468f202109e4f33605b4d5714261d07fcdfe..0894bdff64c83f29199eb1f63bb908c3daf86d95 100644 --- a/Documentation/arm64/silicon-errata.rst +++ b/Documentation/arm64/silicon-errata.rst @@ -76,10 +76,14 @@ stable kernels. +----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A57 | #1319537 | ARM64_ERRATUM_1319367 | +----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-A57 | #1742098 | ARM64_ERRATUM_1742098 | ++----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A72 | #853709 | N/A | +----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A72 | #1319367 | ARM64_ERRATUM_1319367 | +----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-A72 | #1655431 | ARM64_ERRATUM_1742098 | ++----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A73 | #858921 | ARM64_ERRATUM_858921 | +----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A76 | #1188873,1418040| ARM64_ERRATUM_1418040 | diff --git a/Documentation/process/code-of-conduct-interpretation.rst b/Documentation/process/code-of-conduct-interpretation.rst index 4f8a06b00f6081541e7bf731d06ca7f692d94ea0..43da2cc2e3b9b6272151a7675122a3d62b0cb310 100644 --- a/Documentation/process/code-of-conduct-interpretation.rst +++ b/Documentation/process/code-of-conduct-interpretation.rst @@ -51,7 +51,7 @@ the Technical Advisory Board (TAB) or other maintainers if you're uncertain how to handle situations that come up. It will not be considered a violation report unless you want it to be. If you are uncertain about approaching the TAB or any other maintainers, please -reach out to our conflict mediator, Joanna Lee . +reach out to our conflict mediator, Joanna Lee . In the end, "be kind to each other" is really what the end goal is for everybody. We know everyone is human and we all fail at times, but the diff --git a/Documentation/trace/histogram.rst b/Documentation/trace/histogram.rst index 1ef750ee72ceeca6c4eadb1aa7bfde1989b5d3f2..03e3b3f4a5813e7b31a2feba1cdff49514fe43e3 100644 --- a/Documentation/trace/histogram.rst +++ b/Documentation/trace/histogram.rst @@ -39,7 +39,7 @@ Documentation written by Tom Zanussi will use the event's kernel stacktrace as the key. The keywords 'keys' or 'key' can be used to specify keys, and the keywords 'values', 'vals', or 'val' can be used to specify values. Compound - keys consisting of up to two fields can be specified by the 'keys' + keys consisting of up to three fields can be specified by the 'keys' keyword. Hashing a compound key produces a unique entry in the table for each unique combination of component keys, and can be useful for providing more fine-grained summaries of event data. diff --git a/Documentation/virt/kvm/devices/vm.rst b/Documentation/virt/kvm/devices/vm.rst index 0aa5b1cfd700c485bbbb4385ff63a94e231c3dcf..60acc39e0e937c52d5e98c160ccf5f8fb9825264 100644 --- a/Documentation/virt/kvm/devices/vm.rst +++ b/Documentation/virt/kvm/devices/vm.rst @@ -215,6 +215,7 @@ KVM_S390_VM_TOD_EXT). :Parameters: address of a buffer in user space to store the data (u8) to :Returns: -EFAULT if the given address is not accessible from kernel space; -EINVAL if setting the TOD clock extension to != 0 is not supported + -EOPNOTSUPP for a PV guest (TOD managed by the ultravisor) 3.2. ATTRIBUTE: KVM_S390_VM_TOD_LOW ----------------------------------- @@ -224,6 +225,7 @@ the POP (u64). :Parameters: address of a buffer in user space to store the data (u64) to :Returns: -EFAULT if the given address is not accessible from kernel space + -EOPNOTSUPP for a PV guest (TOD managed by the ultravisor) 3.3. ATTRIBUTE: KVM_S390_VM_TOD_EXT ----------------------------------- @@ -237,6 +239,7 @@ it, it is stored as 0 and not allowed to be set to a value != 0. (kvm_s390_vm_tod_clock) to :Returns: -EFAULT if the given address is not accessible from kernel space; -EINVAL if setting the TOD clock extension to != 0 is not supported + -EOPNOTSUPP for a PV guest (TOD managed by the ultravisor) 4. GROUP: KVM_S390_VM_CRYPTO ============================ diff --git a/Makefile b/Makefile index b726b4924df609213334305cdd3bad84cee0b70c..55d173dbbfa518560672462fcbab701736e9ea5d 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 5 PATCHLEVEL = 10 -SUBLEVEL = 149 +SUBLEVEL = 157 EXTRAVERSION = NAME = Dare mighty things @@ -480,6 +480,8 @@ LZ4 = lz4 XZ = xz ZSTD = zstd +PAHOLE_FLAGS = $(shell PAHOLE=$(PAHOLE) $(srctree)/scripts/pahole-flags.sh) + CHECKFLAGS := -D__linux__ -Dlinux -D__STDC__ -Dunix -D__unix__ \ -Wbitwise -Wno-return-void -Wno-unknown-attribute $(CF) NOSTDINC_FLAGS := @@ -534,6 +536,7 @@ export KBUILD_CFLAGS CFLAGS_KERNEL CFLAGS_MODULE export KBUILD_AFLAGS AFLAGS_KERNEL AFLAGS_MODULE export KBUILD_AFLAGS_MODULE KBUILD_CFLAGS_MODULE KBUILD_LDFLAGS_MODULE export KBUILD_AFLAGS_KERNEL KBUILD_CFLAGS_KERNEL +export PAHOLE_FLAGS # Files to ignore in find ... statements @@ -826,12 +829,12 @@ endif # Initialize all stack variables with a zero value. ifdef CONFIG_INIT_STACK_ALL_ZERO -# Future support for zero initialization is still being debated, see -# https://bugs.llvm.org/show_bug.cgi?id=45497. These flags are subject to being -# renamed or dropped. KBUILD_CFLAGS += -ftrivial-auto-var-init=zero +ifdef CONFIG_CC_HAS_AUTO_VAR_INIT_ZERO_ENABLER +# https://github.com/llvm/llvm-project/issues/44842 KBUILD_CFLAGS += -enable-trivial-auto-var-init-zero-knowing-it-will-be-removed-from-clang endif +endif DEBUG_CFLAGS := @@ -849,7 +852,9 @@ else DEBUG_CFLAGS += -g endif -ifndef CONFIG_AS_IS_LLVM +ifdef CONFIG_AS_IS_LLVM +KBUILD_AFLAGS += -g +else KBUILD_AFLAGS += -Wa,-gdwarf-2 endif @@ -1213,7 +1218,7 @@ endif $(Q)$(MAKE) $(hdr-inst)=$(hdr-prefix)arch/$(SRCARCH)/include/uapi ifeq ($(KBUILD_EXTMOD),) -core-y += kernel/ certs/ mm/ fs/ ipc/ security/ crypto/ block/ +core-y += kernel/ certs/ mm/ fs/ ipc/ security/ crypto/ block/ io_uring/ vmlinux-dirs := $(patsubst %/,%,$(filter %/, \ $(core-y) $(core-m) $(drivers-y) $(drivers-m) \ diff --git a/android/abi_gki_aarch64.xml b/android/abi_gki_aarch64.xml index 3861943bf0d18ac9602af194c2376112de15d546..90dddab87ba2c03f535007544b5bcb0da53642d8 100644 --- a/android/abi_gki_aarch64.xml +++ b/android/abi_gki_aarch64.xml @@ -1511,6 +1511,7 @@ + @@ -1663,6 +1664,7 @@ + @@ -4251,6 +4253,7 @@ + @@ -4937,7 +4940,7 @@ - + @@ -5248,21 +5251,21 @@ - + - + - + - + - + - + @@ -5441,7 +5444,7 @@ - + @@ -5476,7 +5479,7 @@ - + @@ -5911,7 +5914,7 @@ - + @@ -5943,7 +5946,7 @@ - + @@ -6468,7 +6471,7 @@ - + @@ -6729,15 +6732,15 @@ - + - + - + - + @@ -7540,7 +7543,7 @@ - + @@ -8210,7 +8213,7 @@ - + @@ -8359,12 +8362,12 @@ - + - + - + @@ -8959,7 +8962,7 @@ - + @@ -8999,7 +9002,7 @@ - + @@ -10243,7 +10246,7 @@ - + @@ -10457,9 +10460,9 @@ - + - + @@ -10798,7 +10801,7 @@ - + @@ -11061,7 +11064,7 @@ - + @@ -11473,18 +11476,18 @@ - + - + - + - + - + @@ -11604,7 +11607,7 @@ - + @@ -11616,7 +11619,7 @@ - + @@ -11643,10 +11646,10 @@ - + - + @@ -12492,7 +12495,7 @@ - + @@ -12532,7 +12535,7 @@ - + @@ -12979,32 +12982,7 @@ - - - - - - - - - - - - - - - - - - - - - - - - - - + @@ -13146,7 +13124,7 @@ - + @@ -13404,7 +13382,7 @@ - + @@ -13466,7 +13444,7 @@ - + @@ -13660,7 +13638,7 @@ - + @@ -14989,24 +14967,24 @@ - + - + - + - + - + - + - + @@ -15356,7 +15334,7 @@ - + @@ -16195,7 +16173,7 @@ - + @@ -16542,12 +16520,12 @@ - + - + - + @@ -16629,7 +16607,7 @@ - + @@ -16798,10 +16776,7 @@ - - - - + @@ -16868,45 +16843,45 @@ - + - + - + - + - + - + - + - + - + - + - + - + - + - + @@ -16930,7 +16905,7 @@ - + @@ -17109,42 +17084,42 @@ - + - + - + - + - + - + - + - + - + - + - + - + - + @@ -17554,24 +17529,24 @@ - + - + - + - + - + - + - + @@ -17654,7 +17629,7 @@ - + @@ -18107,7 +18082,7 @@ - + @@ -18542,7 +18517,7 @@ - + @@ -18584,7 +18559,7 @@ - + @@ -18690,7 +18665,7 @@ - + @@ -18801,7 +18776,7 @@ - + @@ -19170,7 +19145,7 @@ - + @@ -19965,7 +19940,7 @@ - + @@ -20047,7 +20022,7 @@ - + @@ -20594,7 +20569,7 @@ - + @@ -21655,7 +21630,7 @@ - + @@ -21796,10 +21771,10 @@ - + - + @@ -22867,7 +22842,7 @@ - + @@ -23563,7 +23538,7 @@ - + @@ -23588,66 +23563,66 @@ - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + @@ -23655,7 +23630,7 @@ - + @@ -23708,12 +23683,12 @@ - + - + - + @@ -24051,7 +24026,7 @@ - + @@ -24190,7 +24165,7 @@ - + @@ -26138,7 +26113,7 @@ - + @@ -26228,7 +26203,7 @@ - + @@ -26727,7 +26702,7 @@ - + @@ -28747,7 +28722,7 @@ - + @@ -29334,7 +29309,7 @@ - + @@ -29867,30 +29842,30 @@ - + - + - + - + - + - + - + - + - + @@ -30470,7 +30445,7 @@ - + @@ -30521,7 +30496,7 @@ - + @@ -30759,7 +30734,7 @@ - + @@ -30822,7 +30797,7 @@ - + @@ -31151,15 +31126,15 @@ - + - + - + - + @@ -31814,7 +31789,7 @@ - + @@ -31833,7 +31808,7 @@ - + @@ -32577,7 +32552,7 @@ - + @@ -32736,7 +32711,7 @@ - + @@ -33268,7 +33243,7 @@ - + @@ -34174,7 +34149,7 @@ - + @@ -34397,105 +34372,105 @@ - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + @@ -35691,38 +35666,6 @@ - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - @@ -35903,7 +35846,7 @@ - + @@ -36310,7 +36253,7 @@ - + @@ -36554,12 +36497,12 @@ - + - + - + @@ -36726,7 +36669,7 @@ - + @@ -36901,7 +36844,7 @@ - + @@ -37123,7 +37066,7 @@ - + @@ -38029,7 +37972,7 @@ - + @@ -38337,7 +38280,7 @@ - + @@ -38405,7 +38348,7 @@ - + @@ -38906,13 +38849,13 @@ - + - + - + @@ -38936,7 +38879,7 @@ - + @@ -38954,13 +38897,13 @@ - + - + @@ -38969,7 +38912,7 @@ - + @@ -38978,7 +38921,7 @@ - + @@ -39028,21 +38971,21 @@ - + - + - + - + - + - + @@ -39636,7 +39579,7 @@ - + @@ -39939,7 +39882,7 @@ - + @@ -40175,21 +40118,21 @@ - + - + - + - + - + - + @@ -41406,7 +41349,7 @@ - + @@ -41415,7 +41358,7 @@ - + @@ -42023,81 +41966,81 @@ - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + @@ -42168,7 +42111,7 @@ - + @@ -42756,7 +42699,7 @@ - + @@ -43491,7 +43434,7 @@ - + @@ -44092,21 +44035,21 @@ - + - + - + - + - + - + @@ -44134,7 +44077,7 @@ - + @@ -45407,7 +45350,7 @@ - + @@ -45677,7 +45620,7 @@ - + @@ -46652,7 +46595,7 @@ - + @@ -46870,76 +46813,76 @@ - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + @@ -47350,7 +47293,7 @@ - + @@ -48283,51 +48226,51 @@ - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + @@ -48883,21 +48826,21 @@ - + - + - + - + - + - + @@ -49659,7 +49602,7 @@ - + @@ -49808,7 +49751,7 @@ - + @@ -51440,13 +51383,13 @@ - + - + - + @@ -51455,24 +51398,24 @@ - + - + - + - + - + - + @@ -51493,7 +51436,7 @@ - + @@ -51531,15 +51474,15 @@ - + - + - + - + @@ -52113,27 +52056,27 @@ - + - + - + - + - + - + - + - + @@ -52845,7 +52788,7 @@ - + @@ -53735,30 +53678,30 @@ - + - + - + - + - + - + - + - + - + @@ -53877,7 +53820,7 @@ - + @@ -54315,114 +54258,114 @@ - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + @@ -54802,7 +54745,7 @@ - + @@ -56752,7 +56695,7 @@ - + @@ -56795,36 +56738,36 @@ - + - + - + - + - + - + - + - + - + - + - + @@ -57085,7 +57028,7 @@ - + @@ -57754,18 +57697,18 @@ - + - + - + - + - + @@ -58216,7 +58159,7 @@ - + @@ -58890,96 +58833,96 @@ - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + @@ -59008,7 +58951,7 @@ - + @@ -59041,10 +58984,10 @@ - + - + @@ -59238,7 +59181,7 @@ - + @@ -59583,7 +59526,7 @@ - + @@ -59813,7 +59756,7 @@ - + @@ -59821,15 +59764,15 @@ - + - + - + - + @@ -59904,7 +59847,7 @@ - + @@ -60197,7 +60140,6 @@ - @@ -60421,21 +60363,21 @@ - + - + - + - + - + - + @@ -60449,7 +60391,7 @@ - + @@ -60484,7 +60426,7 @@ - + @@ -61033,18 +60975,18 @@ - + - + - + - + - + @@ -61424,7 +61366,7 @@ - + @@ -61934,7 +61876,7 @@ - + @@ -61996,13 +61938,13 @@ - + - + @@ -62154,61 +62096,61 @@ - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + @@ -62448,7 +62390,7 @@ - + @@ -63625,10 +63567,10 @@ - + - + @@ -64125,45 +64067,45 @@ - + - + - + - + - + - + - + - + - + - + - + - + - + - + @@ -64321,7 +64263,7 @@ - + @@ -65049,7 +64991,7 @@ - + @@ -65477,7 +65419,7 @@ - + @@ -65513,27 +65455,27 @@ - + - + - + - + - + - + - + - + @@ -65897,30 +65839,30 @@ - + - + - + - + - + - + - + - + - + @@ -65946,7 +65888,7 @@ - + @@ -65997,18 +65939,18 @@ - + - + - + - + - + @@ -66037,7 +65979,7 @@ - + @@ -66152,7 +66094,7 @@ - + @@ -66167,7 +66109,7 @@ - + @@ -66435,7 +66377,7 @@ - + @@ -66613,18 +66555,18 @@ - + - + - + - + - + @@ -66707,25 +66649,25 @@ - + - + - + - + - + @@ -66984,7 +66926,7 @@ - + @@ -67645,7 +67587,7 @@ - + @@ -68944,7 +68886,7 @@ - + @@ -69753,18 +69695,18 @@ - + - + - + - + - + @@ -70187,7 +70129,7 @@ - + @@ -70205,7 +70147,7 @@ - + @@ -70232,7 +70174,7 @@ - + @@ -70484,16 +70426,16 @@ - + - + - + @@ -70625,18 +70567,18 @@ - + - + - + - + - + @@ -70918,7 +70860,7 @@ - + @@ -71103,15 +71045,15 @@ - + - + - + - + @@ -71703,7 +71645,7 @@ - + @@ -71737,7 +71679,7 @@ - + @@ -71868,30 +71810,30 @@ - + - + - + - + - + - + - + - + - + @@ -71908,25 +71850,25 @@ - + - + - + - + - + - + - + @@ -72307,7 +72249,7 @@ - + @@ -72903,7 +72845,7 @@ - + @@ -73110,7 +73052,7 @@ - + @@ -73175,18 +73117,18 @@ - + - + - + - + - + @@ -73885,7 +73827,7 @@ - + @@ -74034,7 +73976,7 @@ - + @@ -74191,7 +74133,7 @@ - + @@ -74377,7 +74319,7 @@ - + @@ -74668,74 +74610,85 @@ - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + + + + + + + + + + + + @@ -74743,7 +74696,7 @@ - + @@ -74751,7 +74704,7 @@ - + @@ -74759,7 +74712,7 @@ - + @@ -74767,7 +74720,7 @@ - + @@ -74775,7 +74728,7 @@ - + @@ -74783,7 +74736,7 @@ - + @@ -74791,7 +74744,7 @@ - + @@ -74799,7 +74752,7 @@ - + @@ -74831,7 +74784,7 @@ - + @@ -74839,7 +74792,7 @@ - + @@ -74847,7 +74800,7 @@ - + @@ -74855,7 +74808,7 @@ - + @@ -74863,7 +74816,7 @@ - + @@ -74880,7 +74833,7 @@ - + @@ -74888,7 +74841,7 @@ - + @@ -74896,7 +74849,7 @@ - + @@ -74904,7 +74857,7 @@ - + @@ -74912,15 +74865,15 @@ - + - + - + @@ -74937,7 +74890,7 @@ - + @@ -74945,7 +74898,7 @@ - + @@ -74953,7 +74906,7 @@ - + @@ -74964,7 +74917,7 @@ - + @@ -74972,7 +74925,7 @@ - + @@ -74989,7 +74942,7 @@ - + @@ -74997,7 +74950,7 @@ - + @@ -75008,12 +74961,12 @@ - + - + @@ -75021,7 +74974,7 @@ - + @@ -75029,7 +74982,7 @@ - + @@ -75037,7 +74990,7 @@ - + @@ -75045,7 +74998,7 @@ - + @@ -75062,7 +75015,7 @@ - + @@ -75079,7 +75032,7 @@ - + @@ -75093,7 +75046,7 @@ - + @@ -75104,7 +75057,7 @@ - + @@ -75112,12 +75065,12 @@ - + - + @@ -75125,7 +75078,7 @@ - + @@ -75136,7 +75089,7 @@ - + @@ -75147,7 +75100,7 @@ - + @@ -75158,12 +75111,12 @@ - + - + @@ -75177,7 +75130,7 @@ - + @@ -75185,7 +75138,7 @@ - + @@ -75193,7 +75146,7 @@ - + @@ -75201,7 +75154,7 @@ - + @@ -75209,7 +75162,7 @@ - + @@ -75220,7 +75173,7 @@ - + @@ -75234,7 +75187,7 @@ - + @@ -75242,123 +75195,123 @@ - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + @@ -75366,7 +75319,7 @@ - + @@ -75374,35 +75327,35 @@ - + - + - + - + - + - + - + - + - + - + - + @@ -75413,7 +75366,7 @@ - + @@ -75421,7 +75374,7 @@ - + @@ -75429,7 +75382,7 @@ - + @@ -75440,7 +75393,7 @@ - + @@ -75448,11 +75401,11 @@ - + - - + + @@ -75460,7 +75413,7 @@ - + @@ -75471,7 +75424,7 @@ - + @@ -75482,7 +75435,7 @@ - + @@ -75490,7 +75443,7 @@ - + @@ -75510,18 +75463,18 @@ - + - + - + - + - + @@ -75529,7 +75482,7 @@ - + @@ -75537,7 +75490,7 @@ - + @@ -75545,7 +75498,7 @@ - + @@ -75553,7 +75506,7 @@ - + @@ -75561,7 +75514,7 @@ - + @@ -75572,7 +75525,7 @@ - + @@ -75580,7 +75533,7 @@ - + @@ -75588,7 +75541,7 @@ - + @@ -75596,7 +75549,7 @@ - + @@ -75604,7 +75557,7 @@ - + @@ -75612,7 +75565,7 @@ - + @@ -75623,7 +75576,7 @@ - + @@ -75631,7 +75584,7 @@ - + @@ -75639,7 +75592,7 @@ - + @@ -75650,7 +75603,7 @@ - + @@ -75661,7 +75614,7 @@ - + @@ -75669,7 +75622,7 @@ - + @@ -75677,7 +75630,7 @@ - + @@ -75685,7 +75638,7 @@ - + @@ -75693,7 +75646,7 @@ - + @@ -75701,7 +75654,7 @@ - + @@ -75709,7 +75662,7 @@ - + @@ -75717,7 +75670,7 @@ - + @@ -75743,7 +75696,7 @@ - + @@ -75757,7 +75710,7 @@ - + @@ -75765,7 +75718,7 @@ - + @@ -75773,7 +75726,7 @@ - + @@ -75784,7 +75737,7 @@ - + @@ -75792,7 +75745,7 @@ - + @@ -75800,7 +75753,7 @@ - + @@ -75811,7 +75764,7 @@ - + @@ -75819,7 +75772,7 @@ - + @@ -75830,61 +75783,61 @@ - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + @@ -75892,7 +75845,7 @@ - + @@ -75903,7 +75856,7 @@ - + @@ -75911,7 +75864,7 @@ - + @@ -75919,7 +75872,7 @@ - + @@ -75927,7 +75880,7 @@ - + @@ -75938,7 +75891,7 @@ - + @@ -75946,7 +75899,7 @@ - + @@ -75954,7 +75907,7 @@ - + @@ -75962,37 +75915,37 @@ - + - + - + - + - + - + - + - + - + - + @@ -76000,7 +75953,7 @@ - + @@ -76008,7 +75961,18 @@ - + + + + + + + + + + + + @@ -76016,23 +75980,23 @@ - + - + - + - + - + @@ -76040,15 +76004,15 @@ - + - + - + @@ -76056,7 +76020,7 @@ - + @@ -76070,15 +76034,15 @@ - + - + - + - + @@ -76086,7 +76050,7 @@ - + @@ -76100,7 +76064,7 @@ - + @@ -76114,15 +76078,15 @@ - + - + - + @@ -76130,9 +76094,9 @@ - + - + @@ -76144,7 +76108,7 @@ - + @@ -76152,7 +76116,7 @@ - + @@ -76160,7 +76124,7 @@ - + @@ -76168,12 +76132,12 @@ - + - + - + @@ -76181,15 +76145,15 @@ - + - + - + @@ -76209,7 +76173,7 @@ - + @@ -76217,18 +76181,18 @@ - + - + - + - + - + @@ -76236,7 +76200,7 @@ - + @@ -76244,7 +76208,7 @@ - + @@ -76252,7 +76216,7 @@ - + @@ -76266,7 +76230,7 @@ - + @@ -76286,7 +76250,7 @@ - + @@ -76295,26 +76259,26 @@ - + - + - + - + - + - + @@ -76322,15 +76286,15 @@ - + - + - + @@ -76338,7 +76302,7 @@ - + @@ -76349,7 +76313,7 @@ - + @@ -76357,7 +76321,7 @@ - + @@ -76368,7 +76332,7 @@ - + @@ -76379,7 +76343,7 @@ - + @@ -76393,7 +76357,7 @@ - + @@ -76401,7 +76365,7 @@ - + @@ -76418,7 +76382,7 @@ - + @@ -76426,15 +76390,15 @@ - + - + - + @@ -76442,7 +76406,7 @@ - + @@ -76468,12 +76432,12 @@ - + - + @@ -76514,7 +76478,7 @@ - + @@ -76522,7 +76486,7 @@ - + @@ -76530,7 +76494,7 @@ - + @@ -76538,7 +76502,7 @@ - + @@ -76546,7 +76510,7 @@ - + @@ -76554,7 +76518,7 @@ - + @@ -76562,7 +76526,7 @@ - + @@ -76570,7 +76534,7 @@ - + @@ -76578,18 +76542,18 @@ - + - + - + - + @@ -76597,32 +76561,32 @@ - + - + - + - + - + - + - + - + - + - + @@ -76630,30 +76594,30 @@ - + - + - + - + - + - + - + - + @@ -76664,7 +76628,7 @@ - + @@ -76672,15 +76636,15 @@ - + - + - + @@ -76688,10 +76652,10 @@ - + - + @@ -76709,34 +76673,34 @@ - + - + - + - + - + - + - + - + - + - + @@ -76744,7 +76708,7 @@ - + @@ -76752,7 +76716,7 @@ - + @@ -76760,23 +76724,31 @@ - + - + + + + + + + + + - + - + - + - + @@ -76784,7 +76756,7 @@ - + @@ -76795,38 +76767,38 @@ - + - + - + - + - + - + - + - + - + - + - + - + @@ -76835,15 +76807,15 @@ - + - + - + @@ -76851,7 +76823,7 @@ - + @@ -76859,101 +76831,101 @@ - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + @@ -76961,38 +76933,38 @@ - + - + - + - + - + - + - + - + - + - + @@ -77000,7 +76972,7 @@ - + @@ -77008,7 +76980,7 @@ - + @@ -77016,7 +76988,7 @@ - + @@ -77024,7 +76996,7 @@ - + @@ -77032,7 +77004,7 @@ - + @@ -77040,7 +77012,7 @@ - + @@ -77051,7 +77023,7 @@ - + @@ -77059,7 +77031,7 @@ - + @@ -77109,7 +77081,7 @@ - + @@ -77499,30 +77471,30 @@ - + - + - + - + - + - + - + - + - + @@ -77662,234 +77634,234 @@ - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + @@ -78257,9 +78229,9 @@ - + - + @@ -78878,121 +78850,121 @@ - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + @@ -79031,21 +79003,21 @@ - + - + - + - + - + - + @@ -80008,7 +79980,7 @@ - + @@ -80186,7 +80158,7 @@ - + @@ -80431,7 +80403,7 @@ - + @@ -80544,7 +80516,7 @@ - + @@ -80942,7 +80914,7 @@ - + @@ -81406,18 +81378,18 @@ - + - + - + - + - + @@ -81627,7 +81599,7 @@ - + @@ -81811,7 +81783,7 @@ - + @@ -82387,73 +82359,73 @@ - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + @@ -83381,7 +83353,7 @@ - + @@ -83520,7 +83492,7 @@ - + @@ -83616,151 +83588,151 @@ - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + @@ -84286,7 +84258,7 @@ - + @@ -84361,31 +84333,31 @@ - + - + - + - + - + - + - + - + - + @@ -84985,7 +84957,7 @@ - + @@ -86303,7 +86275,7 @@ - + @@ -86757,6 +86729,7 @@ + @@ -86835,7 +86808,7 @@ - + @@ -86962,10 +86935,10 @@ - + - + @@ -87384,7 +87357,7 @@ - + @@ -87719,7 +87692,7 @@ - + @@ -87823,7 +87796,7 @@ - + @@ -88288,7 +88261,7 @@ - + @@ -90572,7 +90545,7 @@ - + @@ -90663,7 +90636,7 @@ - + @@ -91073,7 +91046,7 @@ - + @@ -91109,7 +91082,7 @@ - + @@ -91283,9 +91256,9 @@ - + - + @@ -91905,18 +91878,18 @@ - + - + - + - + - + @@ -92135,7 +92108,7 @@ - + @@ -92149,7 +92122,7 @@ - + @@ -92367,13 +92340,13 @@ - + - + - + @@ -92421,7 +92394,7 @@ - + @@ -92454,7 +92427,7 @@ - + @@ -92677,7 +92650,7 @@ - + @@ -92761,22 +92734,22 @@ - + - + - + - + - + - + @@ -93414,7 +93387,7 @@ - + @@ -93667,7 +93640,7 @@ - + @@ -93854,7 +93827,7 @@ - + @@ -93959,7 +93932,7 @@ - + @@ -94655,7 +94628,7 @@ - + @@ -94838,7 +94811,7 @@ - + @@ -94861,12 +94834,12 @@ - + - + - + @@ -95697,12 +95670,12 @@ - + - + - + @@ -95851,7 +95824,7 @@ - + @@ -95860,7 +95833,7 @@ - + @@ -97064,7 +97037,7 @@ - + @@ -97249,10 +97222,10 @@ - + - + @@ -98101,10 +98074,10 @@ - + - + @@ -98783,6 +98756,7 @@ + @@ -99039,7 +99013,7 @@ - + @@ -99140,7 +99114,7 @@ - + @@ -99590,42 +99564,42 @@ - + - + - + - + - + - + - + - + - + - + - + - + - + @@ -100801,7 +100775,7 @@ - + @@ -100966,33 +100940,33 @@ - + - + - + - + - + - + - + - + - + - + @@ -101156,7 +101130,7 @@ - + @@ -102159,199 +102133,199 @@ - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + @@ -103282,33 +103256,33 @@ - + - + - + - + - + - + - + - + - + - + @@ -103408,18 +103382,18 @@ - + - + - + - + - + @@ -103550,7 +103524,7 @@ - + @@ -104312,7 +104286,7 @@ - + @@ -104632,27 +104606,27 @@ - + - + - + - + - + - + - + - + - + @@ -104677,9 +104651,9 @@ - + - + @@ -104823,7 +104797,7 @@ - + @@ -104983,7 +104957,7 @@ - + @@ -104992,7 +104966,7 @@ - + @@ -105034,7 +105008,7 @@ - + @@ -105271,34 +105245,48 @@ - + - + - + - + - + - + - + - + - + - + - + + + + + + + + + + + + + + + @@ -105312,15 +105300,15 @@ - + - + - + - + @@ -105328,7 +105316,7 @@ - + @@ -105336,7 +105324,7 @@ - + @@ -105344,7 +105332,7 @@ - + @@ -105355,7 +105343,7 @@ - + @@ -105363,7 +105351,7 @@ - + @@ -105377,7 +105365,7 @@ - + @@ -105388,7 +105376,7 @@ - + @@ -105396,7 +105384,7 @@ - + @@ -105404,7 +105392,7 @@ - + @@ -105412,7 +105400,7 @@ - + @@ -105432,7 +105420,7 @@ - + @@ -105440,13 +105428,13 @@ - + - + @@ -105463,7 +105451,7 @@ - + @@ -105477,7 +105465,7 @@ - + @@ -105491,7 +105479,7 @@ - + @@ -105499,7 +105487,7 @@ - + @@ -105513,7 +105501,7 @@ - + @@ -105524,7 +105512,7 @@ - + @@ -105541,15 +105529,15 @@ - + - + - + @@ -105557,7 +105545,7 @@ - + @@ -105568,7 +105556,7 @@ - + @@ -105579,7 +105567,7 @@ - + @@ -105587,7 +105575,7 @@ - + @@ -105604,7 +105592,7 @@ - + @@ -105627,7 +105615,7 @@ - + @@ -105635,7 +105623,7 @@ - + @@ -105646,7 +105634,7 @@ - + @@ -105660,18 +105648,18 @@ - + - + - + - + @@ -105697,7 +105685,7 @@ - + @@ -105708,7 +105696,7 @@ - + @@ -105716,7 +105704,7 @@ - + @@ -105736,7 +105724,7 @@ - + @@ -105747,7 +105735,7 @@ - + @@ -105758,12 +105746,12 @@ - + - + @@ -105771,7 +105759,7 @@ - + @@ -105779,7 +105767,7 @@ - + @@ -105787,7 +105775,7 @@ - + @@ -105795,12 +105783,12 @@ - + - + @@ -105808,7 +105796,7 @@ - + @@ -105816,7 +105804,7 @@ - + @@ -105824,7 +105812,7 @@ - + @@ -105832,7 +105820,7 @@ - + @@ -105840,7 +105828,7 @@ - + @@ -105848,7 +105836,7 @@ - + @@ -105889,7 +105877,7 @@ - + @@ -105897,13 +105885,13 @@ - + - + @@ -105929,7 +105917,7 @@ - + @@ -105994,7 +105982,7 @@ - + @@ -106005,7 +105993,7 @@ - + @@ -106022,7 +106010,7 @@ - + @@ -106066,9 +106054,9 @@ - + - + @@ -106077,7 +106065,7 @@ - + @@ -106088,7 +106076,7 @@ - + @@ -106108,7 +106096,7 @@ - + @@ -106116,7 +106104,7 @@ - + @@ -106133,7 +106121,7 @@ - + @@ -106162,12 +106150,12 @@ - + - + @@ -106176,10 +106164,10 @@ - + - + @@ -106193,17 +106181,17 @@ - + - + - + @@ -106211,7 +106199,7 @@ - + @@ -106222,7 +106210,7 @@ - + @@ -106230,7 +106218,7 @@ - + @@ -106271,7 +106259,7 @@ - + @@ -106279,7 +106267,7 @@ - + @@ -106287,7 +106275,7 @@ - + @@ -106301,7 +106289,7 @@ - + @@ -106321,7 +106309,7 @@ - + @@ -106329,7 +106317,7 @@ - + @@ -106337,7 +106325,7 @@ - + @@ -106345,12 +106333,12 @@ - + - + @@ -106358,7 +106346,7 @@ - + @@ -106366,10 +106354,10 @@ - + - + @@ -106377,23 +106365,23 @@ - + - + - - + + - + @@ -106402,12 +106390,12 @@ - + - + @@ -106415,12 +106403,12 @@ - + - + @@ -106428,12 +106416,12 @@ - + - + @@ -106441,7 +106429,7 @@ - + @@ -106452,7 +106440,7 @@ - + @@ -106466,7 +106454,7 @@ - + @@ -106477,7 +106465,7 @@ - + @@ -106491,7 +106479,7 @@ - + @@ -106505,7 +106493,7 @@ - + @@ -106516,7 +106504,7 @@ - + @@ -106527,7 +106515,7 @@ - + @@ -106544,12 +106532,12 @@ - + - + @@ -106563,7 +106551,7 @@ - + @@ -106586,7 +106574,15 @@ - + + + + + + + + + @@ -106633,7 +106629,7 @@ - + @@ -106641,7 +106637,7 @@ - + @@ -106655,37 +106651,37 @@ - + - + - + - + - + - + - + - + - + - + - + - + @@ -106714,7 +106710,7 @@ - + @@ -106731,7 +106727,7 @@ - + @@ -106748,7 +106744,7 @@ - + @@ -106756,7 +106752,7 @@ - + @@ -106764,12 +106760,12 @@ - + - + @@ -106777,7 +106773,7 @@ - + @@ -106785,9 +106781,9 @@ - + - + @@ -106802,12 +106798,12 @@ - + - + @@ -106833,7 +106829,7 @@ - + @@ -106844,7 +106840,7 @@ - + @@ -106864,7 +106860,7 @@ - + @@ -106887,7 +106883,7 @@ - + @@ -106901,12 +106897,12 @@ - + - + @@ -106917,7 +106913,7 @@ - + @@ -106931,7 +106927,7 @@ - + @@ -106942,7 +106938,7 @@ - + @@ -106956,7 +106952,7 @@ - + @@ -106970,20 +106966,20 @@ - + - + - + - + @@ -106997,7 +106993,7 @@ - + @@ -107005,7 +107001,7 @@ - + @@ -107016,7 +107012,7 @@ - + @@ -107033,7 +107029,7 @@ - + @@ -107053,7 +107049,7 @@ - + @@ -107070,7 +107066,7 @@ - + @@ -107081,7 +107077,7 @@ - + @@ -107089,7 +107085,7 @@ - + @@ -107097,7 +107093,7 @@ - + @@ -107105,7 +107101,7 @@ - + @@ -107119,7 +107115,7 @@ - + @@ -107127,7 +107123,7 @@ - + @@ -107138,7 +107134,7 @@ - + @@ -107155,7 +107151,7 @@ - + @@ -107181,7 +107177,7 @@ - + @@ -107192,7 +107188,7 @@ - + @@ -107203,7 +107199,7 @@ - + @@ -107523,7 +107519,7 @@ - + @@ -107590,7 +107586,7 @@ - + @@ -109340,30 +109336,30 @@ - + - + - + - + - + - + - + - + - + @@ -109466,7 +109462,7 @@ - + @@ -109802,27 +109798,27 @@ - + - + - + - + - + - + - + - + @@ -109956,7 +109952,7 @@ - + @@ -110796,7 +110792,7 @@ - + @@ -111246,7 +111242,7 @@ - + @@ -111348,33 +111344,33 @@ - + - + - + - + - + - + - + - + - + - + @@ -111512,21 +111508,21 @@ - + - + - + - + - + - + @@ -111950,7 +111946,7 @@ - + @@ -112221,7 +112217,7 @@ - + @@ -112292,7 +112288,7 @@ - + @@ -112323,7 +112319,7 @@ - + @@ -112766,7 +112762,7 @@ - + @@ -113173,7 +113169,7 @@ - + @@ -113222,15 +113218,15 @@ - + - + - + - + @@ -113764,7 +113760,7 @@ - + @@ -114280,15 +114276,15 @@ - + - + - + - + @@ -114972,7 +114968,7 @@ - + @@ -115447,7 +115443,7 @@ - + @@ -115715,33 +115711,33 @@ - + - + - + - + - + - + - + - + - + - + @@ -115869,39 +115865,39 @@ - + - + - + - + - + - + - + - + - + - + - + - + @@ -116273,7 +116269,7 @@ - + @@ -116345,7 +116341,7 @@ - + @@ -116366,7 +116362,7 @@ - + @@ -116378,7 +116374,7 @@ - + @@ -116426,7 +116422,7 @@ - + @@ -116493,13 +116489,13 @@ - + - + @@ -116837,7 +116833,7 @@ - + @@ -117632,10 +117628,10 @@ - - - - + + + + @@ -117759,16 +117755,16 @@ - - - - + + + + - - - + + + @@ -117777,8 +117773,8 @@ - - + + @@ -118285,9 +118281,9 @@ - - - + + + @@ -118346,12 +118342,12 @@ - - - - - - + + + + + + @@ -118445,8 +118441,8 @@ - - + + @@ -118465,16 +118461,16 @@ - - - - + + + + - - - - + + + + @@ -120400,12 +120396,12 @@ - - - - - - + + + + + + @@ -120468,8 +120464,8 @@ - - + + @@ -121716,25 +121712,25 @@ - - - - - - - - - - - + + + + + + + + + + + - - - - - - + + + + + + @@ -121776,9 +121772,9 @@ - - - + + + @@ -121789,9 +121785,9 @@ - - - + + + @@ -121856,9 +121852,9 @@ - - - + + + @@ -122403,8 +122399,8 @@ - - + + @@ -122413,8 +122409,8 @@ - - + + @@ -122922,8 +122918,8 @@ - - + + @@ -123083,8 +123079,8 @@ - - + + @@ -124391,9 +124387,9 @@ - - - + + + @@ -124746,9 +124742,9 @@ - - - + + + @@ -124810,20 +124806,20 @@ - - + + - - + + - - + + - - + + @@ -125860,6 +125856,11 @@ + + + + + @@ -126640,6 +126641,11 @@ + + + + + @@ -126680,10 +126686,10 @@ - - - - + + + + @@ -127448,8 +127454,8 @@ - - + + @@ -127471,10 +127477,10 @@ - - - - + + + + @@ -127538,13 +127544,13 @@ - - + + - - - + + + @@ -127616,17 +127622,17 @@ - - + + - - + + - - - + + + @@ -127700,20 +127706,20 @@ - - - - - + + + + + - - - + + + - - + + @@ -127727,20 +127733,20 @@ - - - + + + - - - - + + + + - - - + + + @@ -127777,9 +127783,9 @@ - - - + + + @@ -127869,9 +127875,9 @@ - - - + + + @@ -127892,9 +127898,9 @@ - - - + + + @@ -127917,9 +127923,9 @@ - - - + + + @@ -127928,10 +127934,10 @@ - - - - + + + + @@ -128248,8 +128254,8 @@ - - + + @@ -128288,12 +128294,12 @@ - - + + - - + + @@ -128302,13 +128308,13 @@ - - - + + + - - + + @@ -128673,9 +128679,9 @@ - - - + + + @@ -129324,8 +129330,8 @@ - - + + @@ -129571,8 +129577,8 @@ - - + + @@ -129635,21 +129641,21 @@ - - - + + + - - + + - - + + - - + + @@ -129674,9 +129680,9 @@ - - - + + + @@ -129688,14 +129694,14 @@ - - - + + + - - - + + + @@ -130401,10 +130407,10 @@ - - - - + + + + @@ -130418,9 +130424,9 @@ - - - + + + @@ -130451,14 +130457,14 @@ - - - + + + - - - + + + @@ -130485,11 +130491,11 @@ - - - - - + + + + + @@ -130543,23 +130549,23 @@ - - - - + + + + - - - - - + + + + + - - - + + + @@ -130590,9 +130596,9 @@ - - - + + + @@ -130628,18 +130634,18 @@ - - + + - - - - + + + + - - + + @@ -131053,9 +131059,9 @@ - - - + + + @@ -131450,57 +131456,57 @@ - - + + - - - + + + - - - + + + - - - + + + - - - - - + + + + + - - - - + + + + - - - + + + - - - - + + + + - - - - + + + + - - + + @@ -131512,40 +131518,40 @@ - - - + + + - - + + - - - - + + + + - - + + - - + + - - + + - - - + + + @@ -131576,24 +131582,24 @@ - - + + - - + + - - + + - - + + @@ -131632,26 +131638,26 @@ - - + + - - - + + + - - - - - + + + + + - - - - + + + + @@ -131699,8 +131705,8 @@ - - + + @@ -131798,8 +131804,8 @@ - - + + @@ -131825,8 +131831,8 @@ - - + + @@ -132194,9 +132200,9 @@ - - - + + + @@ -133092,9 +133098,9 @@ - - - + + + @@ -134505,11 +134511,11 @@ - - - - - + + + + + @@ -134533,8 +134539,8 @@ - - + + @@ -134582,14 +134588,14 @@ - - - - + + + + - - + + @@ -134718,12 +134724,12 @@ - - + + - - + + @@ -134749,8 +134755,8 @@ - - + + @@ -134816,8 +134822,8 @@ - - + + @@ -134846,12 +134852,12 @@ - - + + - - + + @@ -135158,9 +135164,9 @@ - - - + + + @@ -135209,8 +135215,8 @@ - - + + @@ -135218,19 +135224,19 @@ - - - + + + - - - + + + - - - + + + @@ -135246,12 +135252,12 @@ - - - - - - + + + + + + @@ -135311,13 +135317,13 @@ - - - - - - - + + + + + + + @@ -135825,8 +135831,8 @@ - - + + @@ -136203,58 +136209,58 @@ - - - - + + + + - - - - - + + + + + - - - + + + - - - - + + + + - - - + + + - - + + - - + + - - + + - - - + + + @@ -136607,16 +136613,16 @@ - - - - - + + + + + - - - + + + @@ -136626,16 +136632,16 @@ - - - + + + - - - - - + + + + + @@ -136645,24 +136651,24 @@ - - - - - + + + + + - - - + + + - - + + - - + + @@ -136676,44 +136682,44 @@ - - - - + + + + - - - + + + - - - + + + - - - + + + - - - + + + - - + + - - - + + + - - - + + + @@ -136728,33 +136734,33 @@ - - - - - + + + + + - - - - - + + + + + - - - + + + - - - + + + - - - + + + @@ -137818,8 +137824,8 @@ - - + + @@ -137834,8 +137840,8 @@ - - + + @@ -137856,75 +137862,75 @@ - - + + - - + + - - + + - - + + - - - + + + - - + + - - + + - - + + - - + + - - - - - + + + + + - - + + - - - + + + - - - + + + - - + + - - - - - - + + + + + + @@ -138108,9 +138114,9 @@ - - - + + + @@ -138245,7 +138251,7 @@ - + @@ -138379,7 +138385,7 @@ - + @@ -138629,8 +138635,8 @@ - - + + @@ -138653,8 +138659,8 @@ - - + + @@ -138963,21 +138969,21 @@ - - - + + + - - - + + + - - - - - + + + + + @@ -138988,49 +138994,49 @@ - - - - - - + + + + + + - - + + - - - + + + - - - + + + - - - - - - - + + + + + + + - - - + + + - - - + + + - - + + @@ -139039,8 +139045,8 @@ - - + + @@ -139193,11 +139199,11 @@ - - - - - + + + + + @@ -139235,8 +139241,8 @@ - - + + @@ -139264,12 +139270,12 @@ - - + + - - + + @@ -139893,6 +139899,11 @@ + + + + + @@ -140234,11 +140245,11 @@ - - - - - + + + + + @@ -140293,12 +140304,12 @@ - - - - - - + + + + + + @@ -140444,11 +140455,11 @@ - - - - - + + + + + @@ -140465,11 +140476,11 @@ - - - - - + + + + + @@ -141067,22 +141078,22 @@ - - - - + + + + - - - - + + + + - - - - + + + + @@ -141133,23 +141144,23 @@ - - - - + + + + - - - - + + + + - - - - - + + + + + @@ -141351,9 +141362,9 @@ - - - + + + @@ -141528,9 +141539,9 @@ - - - + + + @@ -141541,9 +141552,9 @@ - - - + + + @@ -141561,14 +141572,14 @@ - - - + + + - - - + + + @@ -141589,9 +141600,9 @@ - - - + + + @@ -141599,14 +141610,13 @@ - - + + - diff --git a/android/abi_gki_aarch64_generic b/android/abi_gki_aarch64_generic index 2b619558903315717ecf1923b8b061feef0579e3..0f921e8e8e23d35025021c07ae209f25f91955c9 100644 --- a/android/abi_gki_aarch64_generic +++ b/android/abi_gki_aarch64_generic @@ -2603,6 +2603,7 @@ usb_role_switch_unregister usb_speed_string usb_string_id + usb_udc_vbus_handler usb_unregister_notify __usecs_to_jiffies usleep_range diff --git a/android/abi_gki_aarch64_rockchip b/android/abi_gki_aarch64_rockchip index c8d79bc24b463b531ac61caa5214028ab8a0b331..85bd8bc134cfdb9dfa8bac1aa8a4811d586c7cda 100644 --- a/android/abi_gki_aarch64_rockchip +++ b/android/abi_gki_aarch64_rockchip @@ -2397,6 +2397,7 @@ __drm_atomic_state_free drm_bridge_chain_mode_set drm_bridge_get_edid + drm_connector_attach_content_protection_property drm_connector_list_iter_begin drm_connector_list_iter_end drm_connector_list_iter_next @@ -2445,6 +2446,7 @@ drm_gem_unmap_dma_buf drm_get_format_info drm_get_format_name + drm_hdcp_update_content_protection drm_helper_mode_fill_fb_struct drm_kms_helper_poll_enable drm_kms_helper_poll_fini @@ -2470,6 +2472,7 @@ drm_mode_prune_invalid drm_mode_set_crtcinfo drm_modeset_lock_all + drm_modeset_unlock drm_modeset_unlock_all drm_mode_sort drm_mode_validate_size @@ -2483,6 +2486,7 @@ drm_plane_create_zpos_property drm_prime_get_contiguous_size __drm_printfn_seq_file + drm_property_blob_put drm_property_create drm_property_create_bitmask drm_property_create_bool @@ -2490,6 +2494,8 @@ drm_property_create_object drm_property_create_range drm_property_destroy + drm_property_lookup_blob + drm_property_replace_blob __drm_puts_seq_file drm_rect_calc_hscale drm_self_refresh_helper_cleanup diff --git a/arch/alpha/include/asm/thread_info.h b/arch/alpha/include/asm/thread_info.h index 807d7b9a18604d24ccf66784aee6164ce44f625e..0ce1eee0924b159d95b69dbf198eab4ac8cb2020 100644 --- a/arch/alpha/include/asm/thread_info.h +++ b/arch/alpha/include/asm/thread_info.h @@ -62,6 +62,7 @@ register struct thread_info *__current_thread_info __asm__("$8"); #define TIF_SIGPENDING 2 /* signal pending */ #define TIF_NEED_RESCHED 3 /* rescheduling necessary */ #define TIF_SYSCALL_AUDIT 4 /* syscall audit active */ +#define TIF_NOTIFY_SIGNAL 5 /* signal notifications exist */ #define TIF_DIE_IF_KERNEL 9 /* dik recursion lock */ #define TIF_MEMDIE 13 /* is terminating due to OOM killer */ #define TIF_POLLING_NRFLAG 14 /* idle is polling for TIF_NEED_RESCHED */ @@ -71,11 +72,12 @@ register struct thread_info *__current_thread_info __asm__("$8"); #define _TIF_NEED_RESCHED (1<pcb.ksp = (unsigned long) childstack; childti->pcb.flags = 1; /* set FEN, clear everything else */ - if (unlikely(p->flags & PF_KTHREAD)) { + if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { /* kernel thread */ memset(childstack, 0, sizeof(struct switch_stack) + sizeof(struct pt_regs)); diff --git a/arch/alpha/kernel/signal.c b/arch/alpha/kernel/signal.c index 3739efce1ec02821a43ea322b3e956d3433777bc..948b89789da82ace0ed16151ac8f94b747c4d625 100644 --- a/arch/alpha/kernel/signal.c +++ b/arch/alpha/kernel/signal.c @@ -527,7 +527,7 @@ do_work_pending(struct pt_regs *regs, unsigned long thread_flags, schedule(); } else { local_irq_enable(); - if (thread_flags & _TIF_SIGPENDING) { + if (thread_flags & (_TIF_SIGPENDING|_TIF_NOTIFY_SIGNAL)) { do_signal(regs, r0, r19); r0 = 0; } else { diff --git a/arch/arc/include/asm/io.h b/arch/arc/include/asm/io.h index 8f777d6441a5d002b63a2858de49317ebf7e39d7..80347382a38009931372861d4fee1060bca58fde 100644 --- a/arch/arc/include/asm/io.h +++ b/arch/arc/include/asm/io.h @@ -32,7 +32,7 @@ static inline void ioport_unmap(void __iomem *addr) { } -extern void iounmap(const void __iomem *addr); +extern void iounmap(const volatile void __iomem *addr); /* * io{read,write}{16,32}be() macros diff --git a/arch/arc/include/asm/thread_info.h b/arch/arc/include/asm/thread_info.h index f9eef0e8f0b770b16a88bd74a6aac592d9646276..c0942c24d4015f6f0ef946b350a7ecb7130927dd 100644 --- a/arch/arc/include/asm/thread_info.h +++ b/arch/arc/include/asm/thread_info.h @@ -79,6 +79,7 @@ static inline __attribute_const__ struct thread_info *current_thread_info(void) #define TIF_SIGPENDING 2 /* signal pending */ #define TIF_NEED_RESCHED 3 /* rescheduling necessary */ #define TIF_SYSCALL_AUDIT 4 /* syscall auditing active */ +#define TIF_NOTIFY_SIGNAL 5 /* signal notifications exist */ #define TIF_SYSCALL_TRACE 15 /* syscall trace active */ /* true if poll_idle() is polling TIF_NEED_RESCHED */ @@ -89,11 +90,12 @@ static inline __attribute_const__ struct thread_info *current_thread_info(void) #define _TIF_SIGPENDING (1<flags & PF_KTHREAD)) { + if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { memset(c_regs, 0, sizeof(struct pt_regs)); c_callee->r13 = kthread_arg; diff --git a/arch/arc/kernel/signal.c b/arch/arc/kernel/signal.c index 9d5996e014c01255ffd333a8341b51330a79c650..4868bdebf586ddc69f5b2424d7e82076841aba82 100644 --- a/arch/arc/kernel/signal.c +++ b/arch/arc/kernel/signal.c @@ -405,7 +405,7 @@ void do_signal(struct pt_regs *regs) restart_scall = in_syscall(regs) && syscall_restartable(regs); - if (get_signal(&ksig)) { + if (test_thread_flag(TIF_SIGPENDING) && get_signal(&ksig)) { if (restart_scall) { arc_restart_syscall(&ksig.ka, regs); syscall_wont_restart(regs); /* No more restarts */ diff --git a/arch/arc/mm/ioremap.c b/arch/arc/mm/ioremap.c index 95c649fbc95aff99f99a2f481b2f72d898d2f639..d3b1ea16e9cd3f6e66ad13de6a0b33033a52efd2 100644 --- a/arch/arc/mm/ioremap.c +++ b/arch/arc/mm/ioremap.c @@ -93,7 +93,7 @@ void __iomem *ioremap_prot(phys_addr_t paddr, unsigned long size, EXPORT_SYMBOL(ioremap_prot); -void iounmap(const void __iomem *addr) +void iounmap(const volatile void __iomem *addr) { /* weird double cast to handle phys_addr_t > 32 bits */ if (arc_uncached_addr_space((phys_addr_t)(u32)addr)) diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 3d61fcb8ba19ac33f45dbe6466614bd2ac2d6bf4..dcd055eb9eaf3d296eac1f9c53e25fc267c3e838 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -1792,7 +1792,6 @@ config CMDLINE choice prompt "Kernel command line type" if CMDLINE != "" default CMDLINE_FROM_BOOTLOADER - depends on ATAGS config CMDLINE_FROM_BOOTLOADER bool "Use bootloader kernel arguments if available" diff --git a/arch/arm/boot/dts/am335x-pcm-953.dtsi b/arch/arm/boot/dts/am335x-pcm-953.dtsi index 6c547c83e5ddf76b167144aa44e43b884e209177..fc465f0d7e18b603fc3f103a0d09a46b198742e7 100644 --- a/arch/arm/boot/dts/am335x-pcm-953.dtsi +++ b/arch/arm/boot/dts/am335x-pcm-953.dtsi @@ -12,22 +12,20 @@ compatible = "phytec,am335x-pcm-953", "phytec,am335x-phycore-som", "ti,am33xx"; /* Power */ - regulators { - vcc3v3: fixedregulator@1 { - compatible = "regulator-fixed"; - regulator-name = "vcc3v3"; - regulator-min-microvolt = <3300000>; - regulator-max-microvolt = <3300000>; - regulator-boot-on; - }; + vcc3v3: fixedregulator1 { + compatible = "regulator-fixed"; + regulator-name = "vcc3v3"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + regulator-boot-on; + }; - vcc1v8: fixedregulator@2 { - compatible = "regulator-fixed"; - regulator-name = "vcc1v8"; - regulator-min-microvolt = <1800000>; - regulator-max-microvolt = <1800000>; - regulator-boot-on; - }; + vcc1v8: fixedregulator2 { + compatible = "regulator-fixed"; + regulator-name = "vcc1v8"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-boot-on; }; /* User IO */ diff --git a/arch/arm/boot/dts/armada-385-turris-omnia.dts b/arch/arm/boot/dts/armada-385-turris-omnia.dts index fde4c302f08ec7bc88c304815420f39b5f6ffdb7..92e08486ec81fbdb8e9eefb5b874bc31e9a3d424 100644 --- a/arch/arm/boot/dts/armada-385-turris-omnia.dts +++ b/arch/arm/boot/dts/armada-385-turris-omnia.dts @@ -307,7 +307,7 @@ marvell,function = "spi0"; }; - spi0cs1_pins: spi0cs1-pins { + spi0cs2_pins: spi0cs2-pins { marvell,pins = "mpp26"; marvell,function = "spi0"; }; @@ -342,7 +342,7 @@ }; }; - /* MISO, MOSI, SCLK and CS1 are routed to pin header CN11 */ + /* MISO, MOSI, SCLK and CS2 are routed to pin header CN11 */ }; &uart0 { diff --git a/arch/arm/boot/dts/at91sam9g20ek_common.dtsi b/arch/arm/boot/dts/at91sam9g20ek_common.dtsi index ca03685f0f0867237d30d473d695ec46b6b687e7..4783e657b4cb64567b94416c8355fd14126ff27c 100644 --- a/arch/arm/boot/dts/at91sam9g20ek_common.dtsi +++ b/arch/arm/boot/dts/at91sam9g20ek_common.dtsi @@ -39,6 +39,13 @@ }; + usb1 { + pinctrl_usb1_vbus_gpio: usb1_vbus_gpio { + atmel,pins = + ; /* PC5 GPIO */ + }; + }; + mmc0_slot1 { pinctrl_board_mmc0_slot1: mmc0_slot1-board { atmel,pins = @@ -84,6 +91,8 @@ }; usb1: gadget@fffa4000 { + pinctrl-0 = <&pinctrl_usb1_vbus_gpio>; + pinctrl-names = "default"; atmel,vbus-gpio = <&pioC 5 GPIO_ACTIVE_HIGH>; status = "okay"; }; diff --git a/arch/arm/boot/dts/exynos4412-midas.dtsi b/arch/arm/boot/dts/exynos4412-midas.dtsi index 06450066b1787fbfc757eaf0cde6b3020a36afbf..255a13666edcdd223d894cac928b44055464e2cf 100644 --- a/arch/arm/boot/dts/exynos4412-midas.dtsi +++ b/arch/arm/boot/dts/exynos4412-midas.dtsi @@ -588,7 +588,7 @@ clocks = <&camera 1>; clock-names = "extclk"; samsung,camclk-out = <1>; - gpios = <&gpm1 6 GPIO_ACTIVE_HIGH>; + gpios = <&gpm1 6 GPIO_ACTIVE_LOW>; port { is_s5k6a3_ep: endpoint { diff --git a/arch/arm/boot/dts/exynos4412-origen.dts b/arch/arm/boot/dts/exynos4412-origen.dts index c2e793b69e7d9c5d590c044b3571419de53bf67f..e2d76ea4404e8ea0a9588f252e8f3d27d6706d25 100644 --- a/arch/arm/boot/dts/exynos4412-origen.dts +++ b/arch/arm/boot/dts/exynos4412-origen.dts @@ -95,7 +95,7 @@ }; &ehci { - samsung,vbus-gpio = <&gpx3 5 1>; + samsung,vbus-gpio = <&gpx3 5 GPIO_ACTIVE_HIGH>; status = "okay"; phys = <&exynos_usbphy 2>, <&exynos_usbphy 3>; phy-names = "hsic0", "hsic1"; diff --git a/arch/arm/boot/dts/imx6dl.dtsi b/arch/arm/boot/dts/imx6dl.dtsi index fdd81fdc3f35721395240c44a417f7c99ff43240..cd3183c36488a9d5dc60f0cd3c76e6653d1fe700 100644 --- a/arch/arm/boot/dts/imx6dl.dtsi +++ b/arch/arm/boot/dts/imx6dl.dtsi @@ -84,6 +84,9 @@ ocram: sram@900000 { compatible = "mmio-sram"; reg = <0x00900000 0x20000>; + ranges = <0 0x00900000 0x20000>; + #address-cells = <1>; + #size-cells = <1>; clocks = <&clks IMX6QDL_CLK_OCRAM>; }; diff --git a/arch/arm/boot/dts/imx6q-prti6q.dts b/arch/arm/boot/dts/imx6q-prti6q.dts index b4605edfd2ab807ec67153163860b23cc7d5d411..d8fa83effd63863f373cdf67697a1f780015d5e4 100644 --- a/arch/arm/boot/dts/imx6q-prti6q.dts +++ b/arch/arm/boot/dts/imx6q-prti6q.dts @@ -364,8 +364,8 @@ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_wifi>; interrupts-extended = <&gpio1 30 IRQ_TYPE_LEVEL_HIGH>; - ref-clock-frequency = "38400000"; - tcxo-clock-frequency = "19200000"; + ref-clock-frequency = <38400000>; + tcxo-clock-frequency = <19200000>; }; }; diff --git a/arch/arm/boot/dts/imx6q.dtsi b/arch/arm/boot/dts/imx6q.dtsi index 5277e390329126313549b2021fd1d1f447d995bc..afec1677e6baf92e85d42b1a5874fd5847e5b602 100644 --- a/arch/arm/boot/dts/imx6q.dtsi +++ b/arch/arm/boot/dts/imx6q.dtsi @@ -163,6 +163,9 @@ ocram: sram@900000 { compatible = "mmio-sram"; reg = <0x00900000 0x40000>; + ranges = <0 0x00900000 0x40000>; + #address-cells = <1>; + #size-cells = <1>; clocks = <&clks IMX6QDL_CLK_OCRAM>; }; diff --git a/arch/arm/boot/dts/imx6qdl-gw5910.dtsi b/arch/arm/boot/dts/imx6qdl-gw5910.dtsi index ed4e2225995941194983e532bc9e0847ef4b2a47..852601d5ab6b89afa8bc4bdad312ea58d9652185 100644 --- a/arch/arm/boot/dts/imx6qdl-gw5910.dtsi +++ b/arch/arm/boot/dts/imx6qdl-gw5910.dtsi @@ -31,7 +31,7 @@ user-pb { label = "user_pb"; - gpios = <&gsc_gpio 0 GPIO_ACTIVE_LOW>; + gpios = <&gsc_gpio 2 GPIO_ACTIVE_LOW>; linux,code = ; }; diff --git a/arch/arm/boot/dts/imx6qdl-gw5913.dtsi b/arch/arm/boot/dts/imx6qdl-gw5913.dtsi index 4cd7d290f5b28f6240411b3b690fa8ad33c988c7..7a2628fdd1424b7a4f88ae69eba04925253debe6 100644 --- a/arch/arm/boot/dts/imx6qdl-gw5913.dtsi +++ b/arch/arm/boot/dts/imx6qdl-gw5913.dtsi @@ -28,7 +28,7 @@ user-pb { label = "user_pb"; - gpios = <&gsc_gpio 0 GPIO_ACTIVE_LOW>; + gpios = <&gsc_gpio 2 GPIO_ACTIVE_LOW>; linux,code = ; }; diff --git a/arch/arm/boot/dts/imx6qp.dtsi b/arch/arm/boot/dts/imx6qp.dtsi index b310f13a53f22eb6c59ab2d3ca21b2803b5d7921..4d23c92aa8a6bf9fa16820f4a3706bed0c6aee23 100644 --- a/arch/arm/boot/dts/imx6qp.dtsi +++ b/arch/arm/boot/dts/imx6qp.dtsi @@ -9,12 +9,18 @@ ocram2: sram@940000 { compatible = "mmio-sram"; reg = <0x00940000 0x20000>; + ranges = <0 0x00940000 0x20000>; + #address-cells = <1>; + #size-cells = <1>; clocks = <&clks IMX6QDL_CLK_OCRAM>; }; ocram3: sram@960000 { compatible = "mmio-sram"; reg = <0x00960000 0x20000>; + ranges = <0 0x00960000 0x20000>; + #address-cells = <1>; + #size-cells = <1>; clocks = <&clks IMX6QDL_CLK_OCRAM>; }; diff --git a/arch/arm/boot/dts/imx6sl.dtsi b/arch/arm/boot/dts/imx6sl.dtsi index 91a8c54d5e113ba1b2fe385d448566d9d11a2584..c184a6d5bc4206e97c04eef6601a973d2560fa0b 100644 --- a/arch/arm/boot/dts/imx6sl.dtsi +++ b/arch/arm/boot/dts/imx6sl.dtsi @@ -114,6 +114,9 @@ ocram: sram@900000 { compatible = "mmio-sram"; reg = <0x00900000 0x20000>; + ranges = <0 0x00900000 0x20000>; + #address-cells = <1>; + #size-cells = <1>; clocks = <&clks IMX6SL_CLK_OCRAM>; }; diff --git a/arch/arm/boot/dts/imx6sll.dtsi b/arch/arm/boot/dts/imx6sll.dtsi index 0b622201a1f3d6c95d0fe2a54f4aa5c2b2725a01..bf5b262b91f9195247324d913e1dff0733487868 100644 --- a/arch/arm/boot/dts/imx6sll.dtsi +++ b/arch/arm/boot/dts/imx6sll.dtsi @@ -115,6 +115,9 @@ ocram: sram@900000 { compatible = "mmio-sram"; reg = <0x00900000 0x20000>; + ranges = <0 0x00900000 0x20000>; + #address-cells = <1>; + #size-cells = <1>; }; intc: interrupt-controller@a01000 { diff --git a/arch/arm/boot/dts/imx6sx.dtsi b/arch/arm/boot/dts/imx6sx.dtsi index dfdca1804f9f81ee7b1b4d5dd1363d64d3e17f45..c399919943c3488173b47aa26768407eee5b7c86 100644 --- a/arch/arm/boot/dts/imx6sx.dtsi +++ b/arch/arm/boot/dts/imx6sx.dtsi @@ -161,12 +161,18 @@ ocram_s: sram@8f8000 { compatible = "mmio-sram"; reg = <0x008f8000 0x4000>; + ranges = <0 0x008f8000 0x4000>; + #address-cells = <1>; + #size-cells = <1>; clocks = <&clks IMX6SX_CLK_OCRAM_S>; }; ocram: sram@900000 { compatible = "mmio-sram"; reg = <0x00900000 0x20000>; + ranges = <0 0x00900000 0x20000>; + #address-cells = <1>; + #size-cells = <1>; clocks = <&clks IMX6SX_CLK_OCRAM>; }; diff --git a/arch/arm/boot/dts/imx7d-sdb.dts b/arch/arm/boot/dts/imx7d-sdb.dts index 6823b9f1a2a32a960b1940d878f716af6bf857e8..6d562ebe902957cc02cd583e6bb6376ae0971369 100644 --- a/arch/arm/boot/dts/imx7d-sdb.dts +++ b/arch/arm/boot/dts/imx7d-sdb.dts @@ -199,12 +199,7 @@ interrupt-parent = <&gpio2>; interrupts = <29 0>; pendown-gpio = <&gpio2 29 GPIO_ACTIVE_HIGH>; - ti,x-min = /bits/ 16 <0>; - ti,x-max = /bits/ 16 <0>; - ti,y-min = /bits/ 16 <0>; - ti,y-max = /bits/ 16 <0>; - ti,pressure-max = /bits/ 16 <0>; - ti,x-plate-ohms = /bits/ 16 <400>; + touchscreen-max-pressure = <255>; wakeup-source; }; }; diff --git a/arch/arm/boot/dts/imx7s.dtsi b/arch/arm/boot/dts/imx7s.dtsi index 9e1b0af0aa43f28198ffe7e90f9879d686a5abc9..e4ff47110a9603ccd5e2326542cf6aad1f3513a5 100644 --- a/arch/arm/boot/dts/imx7s.dtsi +++ b/arch/arm/boot/dts/imx7s.dtsi @@ -1221,10 +1221,10 @@ clocks = <&clks IMX7D_NAND_USDHC_BUS_RAWNAND_CLK>; }; - gpmi: nand-controller@33002000{ + gpmi: nand-controller@33002000 { compatible = "fsl,imx7d-gpmi-nand"; #address-cells = <1>; - #size-cells = <1>; + #size-cells = <0>; reg = <0x33002000 0x2000>, <0x33004000 0x4000>; reg-names = "gpmi-nand", "bch"; interrupts = ; diff --git a/arch/arm/boot/dts/kirkwood-lsxl.dtsi b/arch/arm/boot/dts/kirkwood-lsxl.dtsi index 7b151acb99846f21e68404bab0bdc76d838475fd..88b70ba1c8feec67b670335c60235aa21342687e 100644 --- a/arch/arm/boot/dts/kirkwood-lsxl.dtsi +++ b/arch/arm/boot/dts/kirkwood-lsxl.dtsi @@ -10,6 +10,11 @@ ocp@f1000000 { pinctrl: pin-controller@10000 { + /* Non-default UART pins */ + pmx_uart0: pmx-uart0 { + marvell,pins = "mpp4", "mpp5"; + }; + pmx_power_hdd: pmx-power-hdd { marvell,pins = "mpp10"; marvell,function = "gpo"; @@ -213,22 +218,11 @@ &mdio { status = "okay"; - ethphy0: ethernet-phy@0 { - reg = <0>; - }; - ethphy1: ethernet-phy@8 { reg = <8>; }; }; -ð0 { - status = "okay"; - ethernet0-port@0 { - phy-handle = <ðphy0>; - }; -}; - ð1 { status = "okay"; ethernet1-port@0 { diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h index 536b6b979f634dd7d2ecc78336fa59e2ce87511e..eb7ce2747eb00e8549fe66194b1683386cb73b2e 100644 --- a/arch/arm/include/asm/thread_info.h +++ b/arch/arm/include/asm/thread_info.h @@ -126,6 +126,8 @@ extern int vfp_restore_user_hwstate(struct user_vfp *, * thread information flags: * TIF_USEDFPU - FPU was used by this task this quantum (SMP) * TIF_POLLING_NRFLAG - true if poll_idle() is polling TIF_NEED_RESCHED + * + * Any bit in the range of 0..15 will cause do_work_pending() to be invoked. */ #define TIF_SIGPENDING 0 /* signal pending */ #define TIF_NEED_RESCHED 1 /* rescheduling necessary */ @@ -135,6 +137,7 @@ extern int vfp_restore_user_hwstate(struct user_vfp *, #define TIF_SYSCALL_AUDIT 5 /* syscall auditing active */ #define TIF_SYSCALL_TRACEPOINT 6 /* syscall tracepoint instrumentation */ #define TIF_SECCOMP 7 /* seccomp syscall filtering active */ +#define TIF_NOTIFY_SIGNAL 8 /* signal notifications exist */ #define TIF_USING_IWMMXT 17 #define TIF_MEMDIE 18 /* is terminating due to OOM killer */ @@ -148,6 +151,7 @@ extern int vfp_restore_user_hwstate(struct user_vfp *, #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) #define _TIF_SYSCALL_TRACEPOINT (1 << TIF_SYSCALL_TRACEPOINT) #define _TIF_SECCOMP (1 << TIF_SECCOMP) +#define _TIF_NOTIFY_SIGNAL (1 << TIF_NOTIFY_SIGNAL) #define _TIF_USING_IWMMXT (1 << TIF_USING_IWMMXT) /* Checks for any syscall work in entry-common.S */ @@ -158,7 +162,8 @@ extern int vfp_restore_user_hwstate(struct user_vfp *, * Change these and you break ASM code in entry-common.S */ #define _TIF_WORK_MASK (_TIF_NEED_RESCHED | _TIF_SIGPENDING | \ - _TIF_NOTIFY_RESUME | _TIF_UPROBE) + _TIF_NOTIFY_RESUME | _TIF_UPROBE | \ + _TIF_NOTIFY_SIGNAL) #endif /* __KERNEL__ */ #endif /* __ASM_ARM_THREAD_INFO_H */ diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S index bd619da73c84ec6d6efe895df9abbe4ea908faeb..9b3c737575e9191f36871e9237918429d1012503 100644 --- a/arch/arm/kernel/entry-common.S +++ b/arch/arm/kernel/entry-common.S @@ -53,7 +53,7 @@ __ret_fast_syscall: cmp r2, #TASK_SIZE blne addr_limit_check_failed ldr r1, [tsk, #TI_FLAGS] @ re-check for syscall tracing - tst r1, #_TIF_SYSCALL_WORK | _TIF_WORK_MASK + movs r1, r1, lsl #16 bne fast_work_pending @@ -90,7 +90,7 @@ __ret_fast_syscall: cmp r2, #TASK_SIZE blne addr_limit_check_failed ldr r1, [tsk, #TI_FLAGS] @ re-check for syscall tracing - tst r1, #_TIF_SYSCALL_WORK | _TIF_WORK_MASK + movs r1, r1, lsl #16 beq no_work_pending UNWIND(.fnend ) ENDPROC(ret_fast_syscall) @@ -131,7 +131,7 @@ ENTRY(ret_to_user_from_irq) cmp r2, #TASK_SIZE blne addr_limit_check_failed ldr r1, [tsk, #TI_FLAGS] - tst r1, #_TIF_WORK_MASK + movs r1, r1, lsl #16 bne slow_work_pending no_work_pending: asm_trace_hardirqs_on save = 0 diff --git a/arch/arm/kernel/entry-v7m.S b/arch/arm/kernel/entry-v7m.S index de1f20624be152f232cb32bdda391249500a1199..d0e898608d3033ac72123e2caf9a61a3cf6a6a9b 100644 --- a/arch/arm/kernel/entry-v7m.S +++ b/arch/arm/kernel/entry-v7m.S @@ -59,7 +59,7 @@ __irq_entry: get_thread_info tsk ldr r2, [tsk, #TI_FLAGS] - tst r2, #_TIF_WORK_MASK + movs r2, r2, lsl #16 beq 2f @ no work pending mov r0, #V7M_SCB_ICSR_PENDSVSET str r0, [r1, V7M_SCB_ICSR] @ raise PendSV diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c index 9f199b1e838391a71f9018e1763867f597f5ad85..2647e48c537e618ec631b077538b5f43485017ed 100644 --- a/arch/arm/kernel/process.c +++ b/arch/arm/kernel/process.c @@ -243,7 +243,7 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start, thread->cpu_domain = get_domain(); #endif - if (likely(!(p->flags & PF_KTHREAD))) { + if (likely(!(p->flags & (PF_KTHREAD | PF_IO_WORKER)))) { *childregs = *current_pt_regs(); childregs->ARM_r0 = 0; if (stack_start) diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c index 2f81d3af5f9af3216d58103120f5f8c7621d1875..a3a38d0a4c853332102aefd01c02b0967e0ccc3f 100644 --- a/arch/arm/kernel/signal.c +++ b/arch/arm/kernel/signal.c @@ -655,7 +655,7 @@ do_work_pending(struct pt_regs *regs, unsigned int thread_flags, int syscall) if (unlikely(!user_mode(regs))) return 0; local_irq_enable(); - if (thread_flags & _TIF_SIGPENDING) { + if (thread_flags & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL)) { int restart = do_signal(regs, syscall); if (unlikely(restart)) { /* diff --git a/arch/arm/mach-mxs/mach-mxs.c b/arch/arm/mach-mxs/mach-mxs.c index c109f47e9cbca8d6eb685634a3d5e07f162339f0..a687e83ad604885d28303945c60bf4d7efe77d52 100644 --- a/arch/arm/mach-mxs/mach-mxs.c +++ b/arch/arm/mach-mxs/mach-mxs.c @@ -387,8 +387,10 @@ static void __init mxs_machine_init(void) root = of_find_node_by_path("/"); ret = of_property_read_string(root, "model", &soc_dev_attr->machine); - if (ret) + if (ret) { + kfree(soc_dev_attr); return; + } soc_dev_attr->family = "Freescale MXS Family"; soc_dev_attr->soc_id = mxs_get_soc_id(); diff --git a/arch/arm/mm/dump.c b/arch/arm/mm/dump.c index c18d23a5e5f1234828cfbb490d67915762fea16e..9b9023a92d464b94cd97c060931bef409179042b 100644 --- a/arch/arm/mm/dump.c +++ b/arch/arm/mm/dump.c @@ -342,7 +342,7 @@ static void walk_pmd(struct pg_state *st, pud_t *pud, unsigned long start) addr = start + i * PMD_SIZE; domain = get_domain_name(pmd); if (pmd_none(*pmd) || pmd_large(*pmd) || !pmd_present(*pmd)) - note_page(st, addr, 3, pmd_val(*pmd), domain); + note_page(st, addr, 4, pmd_val(*pmd), domain); else walk_pte(st, pmd, addr, domain); diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index 86f213f1b44b8c20b1dba442f29c56c563c17f7f..0d0c3bf2391433f7ea105c424694ef40967238d1 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -300,7 +300,11 @@ static struct mem_type mem_types[] __ro_after_init = { .prot_pte = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY | L_PTE_XN | L_PTE_RDONLY, .prot_l1 = PMD_TYPE_TABLE, +#ifdef CONFIG_ARM_LPAE + .prot_sect = PMD_TYPE_SECT | L_PMD_SECT_RDONLY | PMD_SECT_AP2, +#else .prot_sect = PMD_TYPE_SECT, +#endif .domain = DOMAIN_KERNEL, }, [MT_ROM] = { diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 5d812d656654860d4387ae8ade57c4c08646fe9c..177af975e84cf6458f137438865be0477e79ca5b 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -496,6 +496,22 @@ config ARM64_ERRATUM_834220 If unsure, say Y. +config ARM64_ERRATUM_1742098 + bool "Cortex-A57/A72: 1742098: ELR recorded incorrectly on interrupt taken between cryptographic instructions in a sequence" + depends on COMPAT + default y + help + This option removes the AES hwcap for aarch32 user-space to + workaround erratum 1742098 on Cortex-A57 and Cortex-A72. + + Affected parts may corrupt the AES state if an interrupt is + taken between a pair of AES instructions. These instructions + are only present if the cryptography extensions are present. + All software should have a fallback implementation for CPUs + that don't implement the cryptography extensions. + + If unsure, say Y. + config ARM64_ERRATUM_845719 bool "Cortex-A53: 845719: a load might read incorrect data" depends on COMPAT diff --git a/arch/arm64/boot/dts/arm/juno-base.dtsi b/arch/arm64/boot/dts/arm/juno-base.dtsi index 2c0161125ece457ac289f9979a0980dcc0a2d033..cb45a2f0537a90d0a859b106d3f0d4ecf6caf195 100644 --- a/arch/arm64/boot/dts/arm/juno-base.dtsi +++ b/arch/arm64/boot/dts/arm/juno-base.dtsi @@ -595,12 +595,26 @@ polling-delay = <1000>; polling-delay-passive = <100>; thermal-sensors = <&scpi_sensors0 0>; + trips { + pmic_crit0: trip0 { + temperature = <90000>; + hysteresis = <2000>; + type = "critical"; + }; + }; }; soc { polling-delay = <1000>; polling-delay-passive = <100>; thermal-sensors = <&scpi_sensors0 3>; + trips { + soc_crit0: trip0 { + temperature = <80000>; + hysteresis = <2000>; + type = "critical"; + }; + }; }; big_cluster_thermal_zone: big-cluster { diff --git a/arch/arm64/boot/dts/freescale/imx8mm.dtsi b/arch/arm64/boot/dts/freescale/imx8mm.dtsi index f4d7bb75707df286168bf0a1c5a004f7d15bf961..3490619a9ba96390cc7bd4fd6ed70a738ab92941 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm.dtsi @@ -939,10 +939,10 @@ clocks = <&clk IMX8MM_CLK_NAND_USDHC_BUS_RAWNAND_CLK>; }; - gpmi: nand-controller@33002000{ + gpmi: nand-controller@33002000 { compatible = "fsl,imx8mm-gpmi-nand", "fsl,imx7d-gpmi-nand"; #address-cells = <1>; - #size-cells = <1>; + #size-cells = <0>; reg = <0x33002000 0x2000>, <0x33004000 0x4000>; reg-names = "gpmi-nand", "bch"; interrupts = ; diff --git a/arch/arm64/boot/dts/freescale/imx8mn.dtsi b/arch/arm64/boot/dts/freescale/imx8mn.dtsi index aea723eb2ba3f42b72b0f49f22aa545d30f6b3ac..7dba83041264c505121bb26a0c732ff880a12688 100644 --- a/arch/arm64/boot/dts/freescale/imx8mn.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mn.dtsi @@ -809,7 +809,7 @@ gpmi: nand-controller@33002000 { compatible = "fsl,imx8mn-gpmi-nand", "fsl,imx7d-gpmi-nand"; #address-cells = <1>; - #size-cells = <1>; + #size-cells = <0>; reg = <0x33002000 0x2000>, <0x33004000 0x4000>; reg-names = "gpmi-nand", "bch"; interrupts = ; diff --git a/arch/arm64/boot/dts/freescale/imx8mq-librem5.dtsi b/arch/arm64/boot/dts/freescale/imx8mq-librem5.dtsi index e3c6d1272198f3f4106c460d3c8c4b8bb841b02d..325ea100969a8f17e20abbaa52f2dcbb2fbb6872 100644 --- a/arch/arm64/boot/dts/freescale/imx8mq-librem5.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mq-librem5.dtsi @@ -899,6 +899,7 @@ interrupts = <20 IRQ_TYPE_LEVEL_LOW>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_gauge>; + power-supplies = <&bq25895>; maxim,over-heat-temp = <700>; maxim,over-volt = <4500>; maxim,rsns-microohm = <5000>; diff --git a/arch/arm64/boot/dts/qcom/sc7180-trogdor-lte-sku.dtsi b/arch/arm64/boot/dts/qcom/sc7180-trogdor-lte-sku.dtsi index 44956e3165a16e383544b9eaafbaf447c3de3a45..469aad4e5948c20cb5fb3165b3805209e1dfabd5 100644 --- a/arch/arm64/boot/dts/qcom/sc7180-trogdor-lte-sku.dtsi +++ b/arch/arm64/boot/dts/qcom/sc7180-trogdor-lte-sku.dtsi @@ -9,6 +9,10 @@ label = "proximity-wifi-lte"; }; +&mpss_mem { + reg = <0x0 0x86000000 0x0 0x8c00000>; +}; + &remoteproc_mpss { firmware-name = "qcom/sc7180-trogdor/modem/mba.mbn", "qcom/sc7180-trogdor/modem/qdsp6sw.mbn"; diff --git a/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi b/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi index 5b2a616c6257b8a0a53d2568a0ffb72eb74b0ecf..cb2c47f13a8a436be2a0e5e7cc800972c24799d9 100644 --- a/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi +++ b/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi @@ -39,7 +39,7 @@ }; mpss_mem: memory@86000000 { - reg = <0x0 0x86000000 0x0 0x8c00000>; + reg = <0x0 0x86000000 0x0 0x2000000>; no-map; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-puma-haikou.dts b/arch/arm64/boot/dts/rockchip/rk3399-puma-haikou.dts index a8d363568fd62a082dc99b00a844dfd75aa8d136..3fc761c8d550aef448297b29c51edbeaa4732ffe 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-puma-haikou.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-puma-haikou.dts @@ -203,7 +203,7 @@ cap-sd-highspeed; cd-gpios = <&gpio0 RK_PA7 GPIO_ACTIVE_LOW>; disable-wp; - max-frequency = <150000000>; + max-frequency = <40000000>; pinctrl-names = "default"; pinctrl-0 = <&sdmmc_clk &sdmmc_cmd &sdmmc_cd &sdmmc_bus4>; vmmc-supply = <&vcc3v3_baseboard>; diff --git a/arch/arm64/configs/gki_defconfig b/arch/arm64/configs/gki_defconfig index 173eaa72041958fe569f275370efe185adf38d77..f39632dfeeb08c51b9c21e8dfc15b89fd36b0286 100644 --- a/arch/arm64/configs/gki_defconfig +++ b/arch/arm64/configs/gki_defconfig @@ -662,7 +662,6 @@ CONFIG_HARDENED_USERCOPY=y CONFIG_STATIC_USERMODEHELPER=y CONFIG_STATIC_USERMODEHELPER_PATH="" CONFIG_SECURITY_SELINUX=y -CONFIG_INIT_STACK_ALL_ZERO=y CONFIG_INIT_ON_ALLOC_DEFAULT_ON=y CONFIG_CRYPTO_CHACHA20POLY1305=y CONFIG_CRYPTO_ADIANTUM=y diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h index 280bd09768ac8659a5cc459065d6825fbd7fabde..b481c97fdec77926e8955a8af74ad9152eea2913 100644 --- a/arch/arm64/include/asm/cpucaps.h +++ b/arch/arm64/include/asm/cpucaps.h @@ -73,8 +73,9 @@ #define ARM64_MTE_ASYMM 62 #define ARM64_SPECTRE_BHB 63 #define ARM64_WORKAROUND_2457168 64 +#define ARM64_WORKAROUND_1742098 65 -/* kabi: reserve 65 - 76 for future cpu capabilities */ +/* kabi: reserve 66 - 76 for future cpu capabilities */ #define ARM64_NCAPS 76 #endif /* __ASM_CPUCAPS_H */ diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 39f5c1672f480a409edbca38067991f2552298d2..9cf5d9551e9917b8d0c19f752aff71f5bca369a6 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -41,7 +41,7 @@ (((midr) & MIDR_IMPLEMENTOR_MASK) >> MIDR_IMPLEMENTOR_SHIFT) #define MIDR_CPU_MODEL(imp, partnum) \ - (((imp) << MIDR_IMPLEMENTOR_SHIFT) | \ + ((_AT(u32, imp) << MIDR_IMPLEMENTOR_SHIFT) | \ (0xf << MIDR_ARCHITECTURE_SHIFT) | \ ((partnum) << MIDR_PARTNUM_SHIFT)) @@ -60,6 +60,7 @@ #define ARM_CPU_IMP_FUJITSU 0x46 #define ARM_CPU_IMP_HISI 0x48 #define ARM_CPU_IMP_APPLE 0x61 +#define ARM_CPU_IMP_AMPERE 0xC0 #define ARM_CPU_PART_AEM_V8 0xD0F #define ARM_CPU_PART_FOUNDATION 0xD00 @@ -112,6 +113,8 @@ #define APPLE_CPU_PART_M1_ICESTORM 0x022 #define APPLE_CPU_PART_M1_FIRESTORM 0x023 +#define AMPERE_CPU_PART_AMPERE1 0xAC3 + #define MIDR_CORTEX_A53 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53) #define MIDR_CORTEX_A57 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57) #define MIDR_CORTEX_A72 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A72) @@ -151,6 +154,7 @@ #define MIDR_HISI_TSV110 MIDR_CPU_MODEL(ARM_CPU_IMP_HISI, HISI_CPU_PART_TSV110) #define MIDR_APPLE_M1_ICESTORM MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_ICESTORM) #define MIDR_APPLE_M1_FIRESTORM MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM) +#define MIDR_AMPERE1 MIDR_CPU_MODEL(ARM_CPU_IMP_AMPERE, AMPERE_CPU_PART_AMPERE1) /* Fujitsu Erratum 010001 affects A64FX 1.0 and 1.1, (v0r0 and v1r0) */ #define MIDR_FUJITSU_ERRATUM_010001 MIDR_FUJITSU_A64FX diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h index 973b144152711ace4bc6ee85c44926cebd253274..16892f0d05ad635cd22ac0ac520e180b678ff648 100644 --- a/arch/arm64/include/asm/efi.h +++ b/arch/arm64/include/asm/efi.h @@ -25,6 +25,7 @@ int efi_set_mapping_permissions(struct mm_struct *mm, efi_memory_desc_t *md); ({ \ efi_virtmap_load(); \ __efi_fpsimd_begin(); \ + spin_lock(&efi_rt_lock); \ }) #define arch_efi_call_virt(p, f, args...) \ @@ -36,10 +37,12 @@ int efi_set_mapping_permissions(struct mm_struct *mm, efi_memory_desc_t *md); #define arch_efi_call_virt_teardown() \ ({ \ + spin_unlock(&efi_rt_lock); \ __efi_fpsimd_end(); \ efi_virtmap_unload(); \ }) +extern spinlock_t efi_rt_lock; efi_status_t __efi_rt_asm_wrapper(void *, const char *, ...); #define ARCH_EFI_IRQ_FLAGS_MASK (PSR_D_BIT | PSR_A_BIT | PSR_I_BIT | PSR_F_BIT) diff --git a/arch/arm64/include/asm/syscall_wrapper.h b/arch/arm64/include/asm/syscall_wrapper.h index b383b4802a7bdcf1b5851377529a03ef1b5bf536..d30217c21eff78f99fbefdb20a85e3c6bae06b14 100644 --- a/arch/arm64/include/asm/syscall_wrapper.h +++ b/arch/arm64/include/asm/syscall_wrapper.h @@ -8,7 +8,7 @@ #ifndef __ASM_SYSCALL_WRAPPER_H #define __ASM_SYSCALL_WRAPPER_H -struct pt_regs; +#include #define SC_ARM64_REGS_TO_ARGS(x, ...) \ __MAP(x,__SC_ARGS \ diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h index 1fbab854a51b0ee5872b9f23991c3f0ae72fb9b3..cdcf307764aada48973ed47d591b06c6a0bb621d 100644 --- a/arch/arm64/include/asm/thread_info.h +++ b/arch/arm64/include/asm/thread_info.h @@ -68,6 +68,7 @@ void arch_release_task_struct(struct task_struct *tsk); #define TIF_UPROBE 4 /* uprobe breakpoint or singlestep */ #define TIF_FSCHECK 5 /* Check FS is USER_DS on return */ #define TIF_MTE_ASYNC_FAULT 6 /* MTE Asynchronous Tag Check Fault */ +#define TIF_NOTIFY_SIGNAL 7 /* signal notifications exist */ #define TIF_SYSCALL_TRACE 8 /* syscall trace active */ #define TIF_SYSCALL_AUDIT 9 /* syscall auditing */ #define TIF_SYSCALL_TRACEPOINT 10 /* syscall tracepoint for ftrace */ @@ -98,10 +99,12 @@ void arch_release_task_struct(struct task_struct *tsk); #define _TIF_32BIT (1 << TIF_32BIT) #define _TIF_SVE (1 << TIF_SVE) #define _TIF_MTE_ASYNC_FAULT (1 << TIF_MTE_ASYNC_FAULT) +#define _TIF_NOTIFY_SIGNAL (1 << TIF_NOTIFY_SIGNAL) #define _TIF_WORK_MASK (_TIF_NEED_RESCHED | _TIF_SIGPENDING | \ _TIF_NOTIFY_RESUME | _TIF_FOREIGN_FPSTATE | \ - _TIF_UPROBE | _TIF_FSCHECK | _TIF_MTE_ASYNC_FAULT) + _TIF_UPROBE | _TIF_FSCHECK | _TIF_MTE_ASYNC_FAULT | \ + _TIF_NOTIFY_SIGNAL) #define _TIF_SYSCALL_WORK (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \ _TIF_SYSCALL_TRACEPOINT | _TIF_SECCOMP | \ diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 92158607ef27d05fb1f517a1b7a0224e9c027b5f..f0484c063dc917d7610b89a5551016107c2baa4d 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -358,6 +358,14 @@ static const struct midr_range tsb_flush_fail_cpus[] = { }; #endif /* CONFIG_ARM64_WORKAROUND_TSB_FLUSH_FAILURE */ +#ifdef CONFIG_ARM64_ERRATUM_1742098 +static struct midr_range broken_aarch32_aes[] = { + MIDR_RANGE(MIDR_CORTEX_A57, 0, 1, 0xf, 0xf), + MIDR_ALL_VERSIONS(MIDR_CORTEX_A72), + {}, +}; +#endif + const struct arm64_cpu_capabilities arm64_errata[] = { #ifdef CONFIG_ARM64_WORKAROUND_CLEAN_CACHE { @@ -566,6 +574,14 @@ const struct arm64_cpu_capabilities arm64_errata[] = { /* Cortex-A510 r0p0-r1p1 */ CAP_MIDR_RANGE(MIDR_CORTEX_A510, 0, 0, 1, 1) }, +#endif +#ifdef CONFIG_ARM64_ERRATUM_1742098 + { + .desc = "ARM erratum 1742098", + .capability = ARM64_WORKAROUND_1742098, + CAP_MIDR_RANGE_LIST(broken_aarch32_aes), + .type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM, + }, #endif { } diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 6cbaee8913d6b0ab8d8595b5af8a5752f875be16..a2ad318c34c87c83497cce3e67a7792e0e2c382d 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -78,6 +78,7 @@ #include #include #include +#include #include #include #include @@ -1880,6 +1881,14 @@ static void cpu_enable_mte(struct arm64_cpu_capabilities const *cap) } #endif /* CONFIG_ARM64_MTE */ +static void elf_hwcap_fixup(void) +{ +#ifdef CONFIG_ARM64_ERRATUM_1742098 + if (cpus_have_const_cap(ARM64_WORKAROUND_1742098)) + compat_elf_hwcap2 &= ~COMPAT_HWCAP2_AES; +#endif /* ARM64_ERRATUM_1742098 */ +} + #ifdef CONFIG_KVM static bool is_kvm_protected_mode(const struct arm64_cpu_capabilities *entry, int __unused) { @@ -2920,8 +2929,10 @@ void __init setup_cpu_features(void) setup_system_capabilities(); setup_elf_hwcaps(arm64_elf_hwcaps); - if (system_supports_32bit_el0()) + if (system_supports_32bit_el0()) { setup_elf_hwcaps(compat_elf_hwcaps); + elf_hwcap_fixup(); + } if (system_uses_ttbr0_pan()) pr_info("emulated: Privileged Access Never (PAN) using TTBR0_EL1 switching\n"); diff --git a/arch/arm64/kernel/efi-rt-wrapper.S b/arch/arm64/kernel/efi-rt-wrapper.S index 75691a2641c1c0f8ec05604ae6b47345fcb93e75..2d3c4b02393e4d60b6e45763a4050df4987dcaec 100644 --- a/arch/arm64/kernel/efi-rt-wrapper.S +++ b/arch/arm64/kernel/efi-rt-wrapper.S @@ -4,6 +4,7 @@ */ #include +#include SYM_FUNC_START(__efi_rt_asm_wrapper) stp x29, x30, [sp, #-32]! @@ -16,6 +17,12 @@ SYM_FUNC_START(__efi_rt_asm_wrapper) */ stp x1, x18, [sp, #16] + ldr_l x16, efi_rt_stack_top + mov sp, x16 +#ifdef CONFIG_SHADOW_CALL_STACK + str x18, [sp, #-16]! +#endif + /* * We are lucky enough that no EFI runtime services take more than * 5 arguments, so all are passed in registers rather than via the @@ -29,6 +36,7 @@ SYM_FUNC_START(__efi_rt_asm_wrapper) mov x4, x6 blr x8 + mov sp, x29 ldp x1, x2, [sp, #16] cmp x2, x18 ldp x29, x30, [sp], #32 @@ -42,6 +50,10 @@ SYM_FUNC_START(__efi_rt_asm_wrapper) * called with preemption disabled and a separate shadow stack is used * for interrupts. */ - mov x18, x2 +#ifdef CONFIG_SHADOW_CALL_STACK + ldr_l x18, efi_rt_stack_top + ldr x18, [x18, #-16] +#endif + b efi_handle_corrupted_x18 // tail call SYM_FUNC_END(__efi_rt_asm_wrapper) diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c index fa02efb28e88e7a05fe1884b9cc77b3a934c9815..72f432d23ec5cc9dc2dc385ac334bd6a33dbdeba 100644 --- a/arch/arm64/kernel/efi.c +++ b/arch/arm64/kernel/efi.c @@ -12,6 +12,14 @@ #include +static bool region_is_misaligned(const efi_memory_desc_t *md) +{ + if (PAGE_SIZE == EFI_PAGE_SIZE) + return false; + return !PAGE_ALIGNED(md->phys_addr) || + !PAGE_ALIGNED(md->num_pages << EFI_PAGE_SHIFT); +} + /* * Only regions of type EFI_RUNTIME_SERVICES_CODE need to be * executable, everything else can be mapped with the XN bits @@ -25,14 +33,22 @@ static __init pteval_t create_mapping_protection(efi_memory_desc_t *md) if (type == EFI_MEMORY_MAPPED_IO) return PROT_DEVICE_nGnRE; - if (WARN_ONCE(!PAGE_ALIGNED(md->phys_addr), - "UEFI Runtime regions are not aligned to 64 KB -- buggy firmware?")) + if (region_is_misaligned(md)) { + static bool __initdata code_is_misaligned; + /* - * If the region is not aligned to the page size of the OS, we - * can not use strict permissions, since that would also affect - * the mapping attributes of the adjacent regions. + * Regions that are not aligned to the OS page size cannot be + * mapped with strict permissions, as those might interfere + * with the permissions that are needed by the adjacent + * region's mapping. However, if we haven't encountered any + * misaligned runtime code regions so far, we can safely use + * non-executable permissions for non-code regions. */ - return pgprot_val(PAGE_KERNEL_EXEC); + code_is_misaligned |= (type == EFI_RUNTIME_SERVICES_CODE); + + return code_is_misaligned ? pgprot_val(PAGE_KERNEL_EXEC) + : pgprot_val(PAGE_KERNEL); + } /* R-- */ if ((attr & (EFI_MEMORY_XP | EFI_MEMORY_RO)) == @@ -62,19 +78,16 @@ int __init efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md) bool page_mappings_only = (md->type == EFI_RUNTIME_SERVICES_CODE || md->type == EFI_RUNTIME_SERVICES_DATA); - if (!PAGE_ALIGNED(md->phys_addr) || - !PAGE_ALIGNED(md->num_pages << EFI_PAGE_SHIFT)) { - /* - * If the end address of this region is not aligned to page - * size, the mapping is rounded up, and may end up sharing a - * page frame with the next UEFI memory region. If we create - * a block entry now, we may need to split it again when mapping - * the next region, and support for that is going to be removed - * from the MMU routines. So avoid block mappings altogether in - * that case. - */ + /* + * If this region is not aligned to the page size used by the OS, the + * mapping will be rounded outwards, and may end up sharing a page + * frame with an adjacent runtime memory region. Given that the page + * table descriptor covering the shared page will be rewritten when the + * adjacent region gets mapped, we must avoid block mappings here so we + * don't have to worry about splitting them when that happens. + */ + if (region_is_misaligned(md)) page_mappings_only = true; - } create_pgd_mapping(mm, md->phys_addr, md->virt_addr, md->num_pages << EFI_PAGE_SHIFT, @@ -101,6 +114,9 @@ int __init efi_set_mapping_permissions(struct mm_struct *mm, BUG_ON(md->type != EFI_RUNTIME_SERVICES_CODE && md->type != EFI_RUNTIME_SERVICES_DATA); + if (region_is_misaligned(md)) + return 0; + /* * Calling apply_to_page_range() is only safe on regions that are * guaranteed to be mapped down to pages. Since we are only called @@ -127,3 +143,30 @@ asmlinkage efi_status_t efi_handle_corrupted_x18(efi_status_t s, const char *f) pr_err_ratelimited(FW_BUG "register x18 corrupted by EFI %s\n", f); return s; } + +DEFINE_SPINLOCK(efi_rt_lock); + +asmlinkage u64 *efi_rt_stack_top __ro_after_init; + +/* EFI requires 8 KiB of stack space for runtime services */ +static_assert(THREAD_SIZE >= SZ_8K); + +static int __init arm64_efi_rt_init(void) +{ + void *p; + + if (!efi_enabled(EFI_RUNTIME_SERVICES)) + return 0; + + p = __vmalloc_node(THREAD_SIZE, THREAD_ALIGN, GFP_KERNEL, + NUMA_NO_NODE, &&l); +l: if (!p) { + pr_warn("Failed to allocate EFI runtime stack\n"); + clear_bit(EFI_RUNTIME_SERVICES, &efi.flags); + return -ENOMEM; + } + + efi_rt_stack_top = p + THREAD_SIZE; + return 0; +} +core_initcall(arm64_efi_rt_init); diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c index 3724bab278b283d41127d31cc594f771cdb022ec..402a24f845b9e5aec2d76e0ef491b28503be89be 100644 --- a/arch/arm64/kernel/ftrace.c +++ b/arch/arm64/kernel/ftrace.c @@ -216,11 +216,26 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, unsigned long pc = rec->ip; u32 old = 0, new; + new = aarch64_insn_gen_nop(); + + /* + * When using mcount, callsites in modules may have been initalized to + * call an arbitrary module PLT (which redirects to the _mcount stub) + * rather than the ftrace PLT we'll use at runtime (which redirects to + * the ftrace trampoline). We can ignore the old PLT when initializing + * the callsite. + * + * Note: 'mod' is only set at module load time. + */ + if (!IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS) && + IS_ENABLED(CONFIG_ARM64_MODULE_PLTS) && mod) { + return aarch64_insn_patch_text_nosync((void *)pc, new); + } + if (!ftrace_find_callable_addr(rec, mod, &addr)) return -EINVAL; old = aarch64_insn_gen_branch_imm(pc, addr, AARCH64_INSN_BRANCH_LINK); - new = aarch64_insn_gen_nop(); return ftrace_modify_code(pc, old, new, true); } diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index d98512af85f122af41cdb8e3de586d7a555989cb..3d523d9fc589dcf6d14ad8b93f1e5bf2763d189e 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -394,7 +394,7 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start, ptrauth_thread_init_kernel(p); - if (likely(!(p->flags & PF_KTHREAD))) { + if (likely(!(p->flags & (PF_KTHREAD | PF_IO_WORKER)))) { *childregs = *current_pt_regs(); childregs->regs[0] = 0; diff --git a/arch/arm64/kernel/proton-pack.c b/arch/arm64/kernel/proton-pack.c index 40be3a7c2c53154a17be367d56badf57b9e1c48a..428cfabd11c495dbf84117f97d0aa236047aae1d 100644 --- a/arch/arm64/kernel/proton-pack.c +++ b/arch/arm64/kernel/proton-pack.c @@ -868,6 +868,10 @@ u8 spectre_bhb_loop_affected(int scope) MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N1), {}, }; + static const struct midr_range spectre_bhb_k11_list[] = { + MIDR_ALL_VERSIONS(MIDR_AMPERE1), + {}, + }; static const struct midr_range spectre_bhb_k8_list[] = { MIDR_ALL_VERSIONS(MIDR_CORTEX_A72), MIDR_ALL_VERSIONS(MIDR_CORTEX_A57), @@ -878,6 +882,8 @@ u8 spectre_bhb_loop_affected(int scope) k = 32; else if (is_midr_in_range_list(read_cpuid_id(), spectre_bhb_k24_list)) k = 24; + else if (is_midr_in_range_list(read_cpuid_id(), spectre_bhb_k11_list)) + k = 11; else if (is_midr_in_range_list(read_cpuid_id(), spectre_bhb_k8_list)) k = 8; diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index 0dab5679a97d58ab746868c9dc8cdfdc9731fc73..b6fbbd527dd79b3dbfe756a81f65adc8d634bbdd 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -938,7 +938,7 @@ asmlinkage void do_notify_resume(struct pt_regs *regs, (void __user *)NULL, current); } - if (thread_flags & _TIF_SIGPENDING) + if (thread_flags & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL)) do_signal(regs); if (thread_flags & _TIF_NOTIFY_RESUME) { diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c index 543c67cae02ff7d4c96dc027e85ec3d2b075ecc9..f35af19b70555f9be60894973f3987dd70d3a14d 100644 --- a/arch/arm64/kernel/topology.c +++ b/arch/arm64/kernel/topology.c @@ -22,46 +22,6 @@ #include #include -void store_cpu_topology(unsigned int cpuid) -{ - struct cpu_topology *cpuid_topo = &cpu_topology[cpuid]; - u64 mpidr; - - if (cpuid_topo->package_id != -1) - goto topology_populated; - - mpidr = read_cpuid_mpidr(); - - /* Uniprocessor systems can rely on default topology values */ - if (mpidr & MPIDR_UP_BITMASK) - return; - - /* - * This would be the place to create cpu topology based on MPIDR. - * - * However, it cannot be trusted to depict the actual topology; some - * pieces of the architecture enforce an artificial cap on Aff0 values - * (e.g. GICv3's ICC_SGI1R_EL1 limits it to 15), leading to an - * artificial cycling of Aff1, Aff2 and Aff3 values. IOW, these end up - * having absolutely no relationship to the actual underlying system - * topology, and cannot be reasonably used as core / package ID. - * - * If the MT bit is set, Aff0 *could* be used to define a thread ID, but - * we still wouldn't be able to obtain a sane core ID. This means we - * need to entirely ignore MPIDR for any topology deduction. - */ - cpuid_topo->thread_id = -1; - cpuid_topo->core_id = cpuid; - cpuid_topo->package_id = cpu_to_node(cpuid); - - pr_debug("CPU%u: cluster %d core %d thread %d mpidr %#016llx\n", - cpuid, cpuid_topo->package_id, cpuid_topo->core_id, - cpuid_topo->thread_id, mpidr); - -topology_populated: - update_siblings_masks(cpuid); -} - #ifdef CONFIG_ACPI static bool __init acpi_cpu_is_threaded(int cpu) { @@ -158,7 +118,7 @@ static int validate_cpu_freq_invariance_counters(int cpu) } /* Convert maximum frequency from KHz to Hz and validate */ - max_freq_hz = cpufreq_get_hw_max_freq(cpu) * 1000; + max_freq_hz = cpufreq_get_hw_max_freq(cpu) * 1000ULL; if (unlikely(!max_freq_hz)) { pr_debug("CPU%d: invalid maximum frequency.\n", cpu); return -EINVAL; diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c index 089fc2ffcb43d1c6c1269036762edf669068ad24..238018e36b731b543e4ba9e50bebd0f999175b59 100644 --- a/arch/arm64/kvm/vgic/vgic-its.c +++ b/arch/arm64/kvm/vgic/vgic-its.c @@ -2096,7 +2096,7 @@ static int scan_its_table(struct vgic_its *its, gpa_t base, int size, u32 esz, memset(entry, 0, esz); - while (len > 0) { + while (true) { int next_offset; size_t byte_offset; @@ -2109,6 +2109,9 @@ static int scan_its_table(struct vgic_its *its, gpa_t base, int size, u32 esz, return next_offset; byte_offset = next_offset * esz; + if (byte_offset >= len) + break; + id += next_offset; gpa += byte_offset; len -= byte_offset; diff --git a/arch/c6x/include/asm/thread_info.h b/arch/c6x/include/asm/thread_info.h index f70382844b965bcfb04f893dc45226f9b7d1b27d..dd8913d57189dc6eb15855221a44d5cca364a8db 100644 --- a/arch/c6x/include/asm/thread_info.h +++ b/arch/c6x/include/asm/thread_info.h @@ -82,6 +82,7 @@ struct thread_info *current_thread_info(void) #define TIF_SIGPENDING 2 /* signal pending */ #define TIF_NEED_RESCHED 3 /* rescheduling necessary */ #define TIF_RESTORE_SIGMASK 4 /* restore signal mask in do_signal() */ +#define TIF_NOTIFY_SIGNAL 5 /* signal notifications exist */ #define TIF_MEMDIE 17 /* OOM killer killed process */ diff --git a/arch/c6x/kernel/asm-offsets.c b/arch/c6x/kernel/asm-offsets.c index 0f8fde494875edd371e36ad0315c6435ab3b3915..4a264ef87dcb8bb3a6dba5858bf90fc64b82ffee 100644 --- a/arch/c6x/kernel/asm-offsets.c +++ b/arch/c6x/kernel/asm-offsets.c @@ -116,6 +116,7 @@ void foo(void) DEFINE(_TIF_NOTIFY_RESUME, (1< #include +#include #include #include @@ -313,7 +314,7 @@ asmlinkage void do_notify_resume(struct pt_regs *regs, u32 thread_info_flags, int syscall) { /* deal with pending signal delivery */ - if (thread_info_flags & (1 << TIF_SIGPENDING)) + if (thread_info_flags & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL)) do_signal(regs, syscall); if (thread_info_flags & (1 << TIF_NOTIFY_RESUME)) diff --git a/arch/csky/include/asm/thread_info.h b/arch/csky/include/asm/thread_info.h index 68e7a1227170ce959c5cbb377f5bd584ad757b57..21456a3737c2afa7288b303e6d597d8c16f5ae62 100644 --- a/arch/csky/include/asm/thread_info.h +++ b/arch/csky/include/asm/thread_info.h @@ -64,6 +64,7 @@ static inline struct thread_info *current_thread_info(void) #define TIF_SYSCALL_TRACE 4 /* syscall trace active */ #define TIF_SYSCALL_TRACEPOINT 5 /* syscall tracepoint instrumentation */ #define TIF_SYSCALL_AUDIT 6 /* syscall auditing */ +#define TIF_NOTIFY_SIGNAL 7 /* signal notifications exist */ #define TIF_POLLING_NRFLAG 16 /* poll_idle() is TIF_NEED_RESCHED */ #define TIF_MEMDIE 18 /* is terminating due to OOM killer */ #define TIF_RESTORE_SIGMASK 20 /* restore signal mask in do_signal() */ @@ -75,6 +76,7 @@ static inline struct thread_info *current_thread_info(void) #define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE) #define _TIF_SYSCALL_TRACEPOINT (1 << TIF_SYSCALL_TRACEPOINT) #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) +#define _TIF_NOTIFY_SIGNAL (1 << TIF_NOTIFY_SIGNAL) #define _TIF_UPROBE (1 << TIF_UPROBE) #define _TIF_POLLING_NRFLAG (1 << TIF_POLLING_NRFLAG) #define _TIF_MEMDIE (1 << TIF_MEMDIE) @@ -82,7 +84,8 @@ static inline struct thread_info *current_thread_info(void) #define _TIF_SECCOMP (1 << TIF_SECCOMP) #define _TIF_WORK_MASK (_TIF_NEED_RESCHED | _TIF_SIGPENDING | \ - _TIF_NOTIFY_RESUME | _TIF_UPROBE) + _TIF_NOTIFY_RESUME | _TIF_UPROBE | \ + _TIF_NOTIFY_SIGNAL) #define _TIF_SYSCALL_WORK (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \ _TIF_SYSCALL_TRACEPOINT | _TIF_SECCOMP) diff --git a/arch/csky/kernel/process.c b/arch/csky/kernel/process.c index 69af6bc87e6473d2c0c868cf364893e3593f8adf..3d0ca22cd0e2e6075c4bcdcb5d69d6e55f5131f1 100644 --- a/arch/csky/kernel/process.c +++ b/arch/csky/kernel/process.c @@ -49,7 +49,7 @@ int copy_thread(unsigned long clone_flags, /* setup thread.sp for switch_to !!! */ p->thread.sp = (unsigned long)childstack; - if (unlikely(p->flags & PF_KTHREAD)) { + if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { memset(childregs, 0, sizeof(struct pt_regs)); childstack->r15 = (unsigned long) ret_from_kernel_thread; childstack->r10 = kthread_arg; diff --git a/arch/csky/kernel/signal.c b/arch/csky/kernel/signal.c index 243228b0aa075e4d9862905afeb88824f924f265..f7c1677e5971907d8d0bd8bc9cc45196d7098a1f 100644 --- a/arch/csky/kernel/signal.c +++ b/arch/csky/kernel/signal.c @@ -261,7 +261,7 @@ asmlinkage void do_notify_resume(struct pt_regs *regs, uprobe_notify_resume(regs); /* Handle pending signal delivery */ - if (thread_info_flags & _TIF_SIGPENDING) + if (thread_info_flags & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL)) do_signal(regs); if (thread_info_flags & _TIF_NOTIFY_RESUME) { diff --git a/arch/h8300/include/asm/thread_info.h b/arch/h8300/include/asm/thread_info.h index 0cdaa302d3d28239bc9295be4917e4239cc4c423..a518214d4ddd81f75e79a1d7fbb0fc106c681866 100644 --- a/arch/h8300/include/asm/thread_info.h +++ b/arch/h8300/include/asm/thread_info.h @@ -73,6 +73,7 @@ static inline struct thread_info *current_thread_info(void) #define TIF_SYSCALL_AUDIT 7 /* syscall auditing active */ #define TIF_SYSCALL_TRACEPOINT 8 /* for ftrace syscall instrumentation */ #define TIF_POLLING_NRFLAG 9 /* true if poll_idle() is polling TIF_NEED_RESCHED */ +#define TIF_NOTIFY_SIGNAL 10 /* signal notifications exist */ /* as above, but as bit values */ #define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE) @@ -83,6 +84,7 @@ static inline struct thread_info *current_thread_info(void) #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) #define _TIF_SYSCALL_TRACEPOINT (1 << TIF_SYSCALL_TRACEPOINT) #define _TIF_POLLING_NRFLAG (1 << TIF_POLLING_NRFLAG) +#define _TIF_NOTIFY_SIGNAL (1 << TIF_NOTIFY_SIGNAL) /* work to do in syscall trace */ #define _TIF_WORK_SYSCALL_MASK (_TIF_SYSCALL_TRACE | _TIF_SINGLESTEP | \ @@ -92,7 +94,7 @@ static inline struct thread_info *current_thread_info(void) #define _TIF_ALLWORK_MASK (_TIF_SYSCALL_TRACE | _TIF_SIGPENDING | \ _TIF_NEED_RESCHED | _TIF_SYSCALL_AUDIT | \ _TIF_SINGLESTEP | _TIF_NOTIFY_RESUME | \ - _TIF_SYSCALL_TRACEPOINT) + _TIF_SYSCALL_TRACEPOINT | _TIF_NOTIFY_SIGNAL) /* work to do on interrupt/exception return */ #define _TIF_WORK_MASK (_TIF_ALLWORK_MASK & ~(_TIF_SYSCALL_TRACE | \ diff --git a/arch/h8300/kernel/process.c b/arch/h8300/kernel/process.c index bc1364db58feb01e82c1fd407dea4ee0a8611944..46b1342ce515b3a33b63a9559786fbe55f2770ce 100644 --- a/arch/h8300/kernel/process.c +++ b/arch/h8300/kernel/process.c @@ -112,7 +112,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, childregs = (struct pt_regs *) (THREAD_SIZE + task_stack_page(p)) - 1; - if (unlikely(p->flags & PF_KTHREAD)) { + if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { memset(childregs, 0, sizeof(struct pt_regs)); childregs->retpc = (unsigned long) ret_from_kernel_thread; childregs->er4 = topstk; /* arg */ diff --git a/arch/h8300/kernel/signal.c b/arch/h8300/kernel/signal.c index 75d9b7e626b2faf7b3b92e444a0b47d0afe05a39..75a1c36b105a18b3d07347ea576a30b4cb89d2e3 100644 --- a/arch/h8300/kernel/signal.c +++ b/arch/h8300/kernel/signal.c @@ -279,7 +279,7 @@ static void do_signal(struct pt_regs *regs) asmlinkage void do_notify_resume(struct pt_regs *regs, u32 thread_info_flags) { - if (thread_info_flags & _TIF_SIGPENDING) + if (thread_info_flags & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL)) do_signal(regs); if (thread_info_flags & _TIF_NOTIFY_RESUME) diff --git a/arch/hexagon/include/asm/thread_info.h b/arch/hexagon/include/asm/thread_info.h index 563da198646455b2497da3a5f87f64b3023f3e4c..535976665bf0013ba067a4599b83cce87d72d9ca 100644 --- a/arch/hexagon/include/asm/thread_info.h +++ b/arch/hexagon/include/asm/thread_info.h @@ -95,6 +95,7 @@ register struct thread_info *__current_thread_info asm(QUOTED_THREADINFO_REG); #define TIF_NEED_RESCHED 3 /* rescheduling necessary */ #define TIF_SINGLESTEP 4 /* restore ss @ return to usr mode */ #define TIF_RESTORE_SIGMASK 6 /* restore sig mask in do_signal() */ +#define TIF_NOTIFY_SIGNAL 7 /* signal notifications exist */ /* true if poll_idle() is polling TIF_NEED_RESCHED */ #define TIF_MEMDIE 17 /* OOM killer killed process */ @@ -103,6 +104,7 @@ register struct thread_info *__current_thread_info asm(QUOTED_THREADINFO_REG); #define _TIF_SIGPENDING (1 << TIF_SIGPENDING) #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) #define _TIF_SINGLESTEP (1 << TIF_SINGLESTEP) +#define _TIF_NOTIFY_SIGNAL (1 << TIF_NOTIFY_SIGNAL) /* work to do on interrupt/exception return - All but TIF_SYSCALL_TRACE */ #define _TIF_WORK_MASK (0x0000FFFF & ~_TIF_SYSCALL_TRACE) diff --git a/arch/hexagon/kernel/process.c b/arch/hexagon/kernel/process.c index 67767c5ed98c3a14ab4813614416ca3f731fc96a..c61165c99ae0ba9d45c79e6f3ab9323ef72cebc4 100644 --- a/arch/hexagon/kernel/process.c +++ b/arch/hexagon/kernel/process.c @@ -73,7 +73,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long arg, sizeof(*ss)); ss->lr = (unsigned long)ret_from_fork; p->thread.switch_sp = ss; - if (unlikely(p->flags & PF_KTHREAD)) { + if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { memset(childregs, 0, sizeof(struct pt_regs)); /* r24 <- fn, r25 <- arg */ ss->r24 = usp; @@ -174,7 +174,7 @@ int do_work_pending(struct pt_regs *regs, u32 thread_info_flags) return 1; } - if (thread_info_flags & _TIF_SIGPENDING) { + if (thread_info_flags & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL)) { do_signal(regs); return 1; } diff --git a/arch/ia64/include/asm/thread_info.h b/arch/ia64/include/asm/thread_info.h index 64a1011f681210b445de33aaefc2e820bcad1b28..51d20cb3770622fdfa4bc0672957bd00c0a7c399 100644 --- a/arch/ia64/include/asm/thread_info.h +++ b/arch/ia64/include/asm/thread_info.h @@ -103,6 +103,7 @@ struct thread_info { #define TIF_SYSCALL_TRACE 2 /* syscall trace active */ #define TIF_SYSCALL_AUDIT 3 /* syscall auditing active */ #define TIF_SINGLESTEP 4 /* restore singlestep on return to user mode */ +#define TIF_NOTIFY_SIGNAL 5 /* signal notification exist */ #define TIF_NOTIFY_RESUME 6 /* resumption notification requested */ #define TIF_MEMDIE 17 /* is terminating due to OOM killer */ #define TIF_MCA_INIT 18 /* this task is processing MCA or INIT */ @@ -115,6 +116,7 @@ struct thread_info { #define _TIF_SINGLESTEP (1 << TIF_SINGLESTEP) #define _TIF_SYSCALL_TRACEAUDIT (_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SINGLESTEP) #define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME) +#define _TIF_NOTIFY_SIGNAL (1 << TIF_NOTIFY_SIGNAL) #define _TIF_SIGPENDING (1 << TIF_SIGPENDING) #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) #define _TIF_MCA_INIT (1 << TIF_MCA_INIT) @@ -124,7 +126,7 @@ struct thread_info { /* "work to do on user-return" bits */ #define TIF_ALLWORK_MASK (_TIF_SIGPENDING|_TIF_NOTIFY_RESUME|_TIF_SYSCALL_AUDIT|\ - _TIF_NEED_RESCHED|_TIF_SYSCALL_TRACE) + _TIF_NEED_RESCHED|_TIF_SYSCALL_TRACE|_TIF_NOTIFY_SIGNAL) /* like TIF_ALLWORK_BITS but sans TIF_SYSCALL_TRACE or TIF_SYSCALL_AUDIT */ #define TIF_WORK_MASK (TIF_ALLWORK_MASK&~(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT)) diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c index c9ff8796b5097e0498256482f10cb96b10b1d802..8159b7af5509f4e21818f76bf15ac2ee24289390 100644 --- a/arch/ia64/kernel/process.c +++ b/arch/ia64/kernel/process.c @@ -171,7 +171,8 @@ do_notify_resume_user(sigset_t *unused, struct sigscratch *scr, long in_syscall) } /* deal with pending signal delivery */ - if (test_thread_flag(TIF_SIGPENDING)) { + if (test_thread_flag(TIF_SIGPENDING) || + test_thread_flag(TIF_NOTIFY_SIGNAL)) { local_irq_enable(); /* force interrupt enable */ ia64_do_signal(scr, in_syscall); } @@ -337,7 +338,7 @@ copy_thread(unsigned long clone_flags, unsigned long user_stack_base, ia64_drop_fpu(p); /* don't pick up stale state from a CPU's fph */ - if (unlikely(p->flags & PF_KTHREAD)) { + if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { if (unlikely(!user_stack_base)) { /* fork_idle() called us */ return 0; diff --git a/arch/ia64/kernel/signal.c b/arch/ia64/kernel/signal.c index e67b22fc3c60b7dbe47494b836a5cf5ea583ee5e..c1b299760bf7a91082efc743c9876be81a3fe2c1 100644 --- a/arch/ia64/kernel/signal.c +++ b/arch/ia64/kernel/signal.c @@ -341,7 +341,8 @@ ia64_do_signal (struct sigscratch *scr, long in_syscall) * need to push through a forced SIGSEGV. */ while (1) { - get_signal(&ksig); + if (!get_signal(&ksig)) + break; /* * get_signal() may have run a debugger (via notify_parent()) diff --git a/arch/ia64/mm/numa.c b/arch/ia64/mm/numa.c index f34964271101a2f894d92733a52576b7457040ab..6cd002e8163db1cf0f270397eaf64719c34042ea 100644 --- a/arch/ia64/mm/numa.c +++ b/arch/ia64/mm/numa.c @@ -106,5 +106,6 @@ int memory_add_physaddr_to_nid(u64 addr) return 0; return nid; } +EXPORT_SYMBOL(memory_add_physaddr_to_nid); #endif #endif diff --git a/arch/m68k/include/asm/thread_info.h b/arch/m68k/include/asm/thread_info.h index 3689c6718c883d23a9599a28635f8dcf035a9bfc..15a757073fa58ffcab231b5b7f4190479b2d363b 100644 --- a/arch/m68k/include/asm/thread_info.h +++ b/arch/m68k/include/asm/thread_info.h @@ -60,6 +60,7 @@ static inline struct thread_info *current_thread_info(void) * bits 0-7 are tested at every exception exit * bits 8-15 are also tested at syscall exit */ +#define TIF_NOTIFY_SIGNAL 4 #define TIF_NOTIFY_RESUME 5 /* callback before returning to user */ #define TIF_SIGPENDING 6 /* signal pending */ #define TIF_NEED_RESCHED 7 /* rescheduling necessary */ diff --git a/arch/m68k/kernel/process.c b/arch/m68k/kernel/process.c index 08359a6e058f632294989db6800dcddd5626a0f2..da83cc83e79123b92654fb99f1dbbeb972593d09 100644 --- a/arch/m68k/kernel/process.c +++ b/arch/m68k/kernel/process.c @@ -157,7 +157,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long arg, */ p->thread.fs = get_fs().seg; - if (unlikely(p->flags & PF_KTHREAD)) { + if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { /* kernel thread */ memset(frame, 0, sizeof(struct fork_frame)); frame->regs.sr = PS_S; diff --git a/arch/m68k/kernel/signal.c b/arch/m68k/kernel/signal.c index fd916844a683f9393d4b601d79785451726d75cc..5d12736b4b28135135f36ec504455c9dfe970152 100644 --- a/arch/m68k/kernel/signal.c +++ b/arch/m68k/kernel/signal.c @@ -1129,7 +1129,8 @@ static void do_signal(struct pt_regs *regs) void do_notify_resume(struct pt_regs *regs) { - if (test_thread_flag(TIF_SIGPENDING)) + if (test_thread_flag(TIF_NOTIFY_SIGNAL) || + test_thread_flag(TIF_SIGPENDING)) do_signal(regs); if (test_thread_flag(TIF_NOTIFY_RESUME)) diff --git a/arch/microblaze/include/asm/thread_info.h b/arch/microblaze/include/asm/thread_info.h index ad8e8fcb90d3baea26ad95360ad422610f45210f..44f5ca33186259f4545fe13225e6d3f3eac6860c 100644 --- a/arch/microblaze/include/asm/thread_info.h +++ b/arch/microblaze/include/asm/thread_info.h @@ -107,6 +107,7 @@ static inline struct thread_info *current_thread_info(void) #define TIF_NEED_RESCHED 3 /* rescheduling necessary */ /* restore singlestep on return to user mode */ #define TIF_SINGLESTEP 4 +#define TIF_NOTIFY_SIGNAL 5 /* signal notifications exist */ #define TIF_MEMDIE 6 /* is terminating due to OOM killer */ #define TIF_SYSCALL_AUDIT 9 /* syscall auditing active */ #define TIF_SECCOMP 10 /* secure computing */ @@ -119,6 +120,7 @@ static inline struct thread_info *current_thread_info(void) #define _TIF_SIGPENDING (1 << TIF_SIGPENDING) #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) #define _TIF_SINGLESTEP (1 << TIF_SINGLESTEP) +#define _TIF_NOTIFY_SIGNAL (1 << TIF_NOTIFY_SIGNAL) #define _TIF_POLLING_NRFLAG (1 << TIF_POLLING_NRFLAG) #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) #define _TIF_SECCOMP (1 << TIF_SECCOMP) diff --git a/arch/microblaze/kernel/process.c b/arch/microblaze/kernel/process.c index f99860771ff4854f13b1c3832edb53f1fd61ac1c..ee000ae17e3956529f2d72933943518a11375c44 100644 --- a/arch/microblaze/kernel/process.c +++ b/arch/microblaze/kernel/process.c @@ -59,7 +59,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long arg, struct pt_regs *childregs = task_pt_regs(p); struct thread_info *ti = task_thread_info(p); - if (unlikely(p->flags & PF_KTHREAD)) { + if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { /* if we're creating a new kernel thread then just zeroing all * the registers. That's OK for a brand new thread.*/ memset(childregs, 0, sizeof(struct pt_regs)); diff --git a/arch/microblaze/kernel/signal.c b/arch/microblaze/kernel/signal.c index f11a0ccccabc47f155ee02e176eb1b47234e94a8..5a8d173d7b75c876bd3ea61890cb5322534060ab 100644 --- a/arch/microblaze/kernel/signal.c +++ b/arch/microblaze/kernel/signal.c @@ -313,7 +313,8 @@ static void do_signal(struct pt_regs *regs, int in_syscall) asmlinkage void do_notify_resume(struct pt_regs *regs, int in_syscall) { - if (test_thread_flag(TIF_SIGPENDING)) + if (test_thread_flag(TIF_SIGPENDING) || + test_thread_flag(TIF_NOTIFY_SIGNAL)) do_signal(regs, in_syscall); if (test_thread_flag(TIF_NOTIFY_RESUME)) diff --git a/arch/mips/bcm47xx/prom.c b/arch/mips/bcm47xx/prom.c index 3e2a8166377f5fd851d08b73c2835805096a9b99..22509b5fab74f0ecec2523221b0a7f790023ba62 100644 --- a/arch/mips/bcm47xx/prom.c +++ b/arch/mips/bcm47xx/prom.c @@ -86,7 +86,7 @@ static __init void prom_init_mem(void) pr_debug("Assume 128MB RAM\n"); break; } - if (!memcmp(prom_init, prom_init + mem, 32)) + if (!memcmp((void *)prom_init, (void *)prom_init + mem, 32)) break; } lowmem = mem; @@ -163,7 +163,7 @@ void __init bcm47xx_prom_highmem_init(void) off = EXTVBASE + __pa(off); for (extmem = 128 << 20; extmem < 512 << 20; extmem <<= 1) { - if (!memcmp(prom_init, (void *)(off + extmem), 16)) + if (!memcmp((void *)prom_init, (void *)(off + extmem), 16)) break; } extmem -= lowmem; diff --git a/arch/mips/include/asm/fw/fw.h b/arch/mips/include/asm/fw/fw.h index d0ef8b4892bbe6af327a0b351df93f948c413b37..d0494ce4b3373a751597d063c6b9bece9379b431 100644 --- a/arch/mips/include/asm/fw/fw.h +++ b/arch/mips/include/asm/fw/fw.h @@ -26,6 +26,6 @@ extern char *fw_getcmdline(void); extern void fw_meminit(void); extern char *fw_getenv(char *name); extern unsigned long fw_getenvl(char *name); -extern void fw_init_early_console(char port); +extern void fw_init_early_console(void); #endif /* __ASM_FW_H_ */ diff --git a/arch/mips/include/asm/thread_info.h b/arch/mips/include/asm/thread_info.h index ee26f9a4575dfc2b09568855015200043ca0ffbe..e2c352da3877ae85d570cd88a78e45916b428168 100644 --- a/arch/mips/include/asm/thread_info.h +++ b/arch/mips/include/asm/thread_info.h @@ -115,6 +115,7 @@ static inline struct thread_info *current_thread_info(void) #define TIF_SECCOMP 4 /* secure computing */ #define TIF_NOTIFY_RESUME 5 /* callback before returning to user */ #define TIF_UPROBE 6 /* breakpointed or singlestepping */ +#define TIF_NOTIFY_SIGNAL 7 /* signal notifications exist */ #define TIF_RESTORE_SIGMASK 9 /* restore signal mask in do_signal() */ #define TIF_USEDFPU 16 /* FPU was used by this task this quantum (SMP) */ #define TIF_MEMDIE 18 /* is terminating due to OOM killer */ @@ -139,6 +140,7 @@ static inline struct thread_info *current_thread_info(void) #define _TIF_SECCOMP (1<= BIT(25)) || + WARN_ON((offset >= (long)BIT(25)) || (offset < -(long)BIT(25))); insn.j_format.opcode = bc6_op; diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c index 75ebd8d7bd5d00bd0bdd29e9c80e0581a69bfbdf..98ecaf6f3edb0c1b8c0e82626292c2668c39cc60 100644 --- a/arch/mips/kernel/process.c +++ b/arch/mips/kernel/process.c @@ -135,7 +135,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, /* Put the stack after the struct pt_regs. */ childksp = (unsigned long) childregs; p->thread.cp0_status = (read_c0_status() & ~(ST0_CU2|ST0_CU1)) | ST0_KERNEL_CUMASK; - if (unlikely(p->flags & PF_KTHREAD)) { + if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { /* kernel thread */ unsigned long status = p->thread.cp0_status; memset(childregs, 0, sizeof(struct pt_regs)); diff --git a/arch/mips/kernel/signal.c b/arch/mips/kernel/signal.c index 50d0515bea21f486d1f7a3d51a6457f171300b29..f1e985109da013276857529bece31ed5bdbb8559 100644 --- a/arch/mips/kernel/signal.c +++ b/arch/mips/kernel/signal.c @@ -903,7 +903,7 @@ asmlinkage void do_notify_resume(struct pt_regs *regs, void *unused, uprobe_notify_resume(regs); /* deal with pending signal delivery */ - if (thread_info_flags & _TIF_SIGPENDING) + if (thread_info_flags & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL)) do_signal(regs); if (thread_info_flags & _TIF_NOTIFY_RESUME) { diff --git a/arch/mips/pic32/pic32mzda/early_console.c b/arch/mips/pic32/pic32mzda/early_console.c index 25372e62783b584456162362d6765aca7a73b829..3cd1b408fa1cb039f917f2d92e82fd00d8a44574 100644 --- a/arch/mips/pic32/pic32mzda/early_console.c +++ b/arch/mips/pic32/pic32mzda/early_console.c @@ -27,7 +27,7 @@ #define U_BRG(x) (UART_BASE(x) + 0x40) static void __iomem *uart_base; -static char console_port = -1; +static int console_port = -1; static int __init configure_uart_pins(int port) { @@ -47,7 +47,7 @@ static int __init configure_uart_pins(int port) return 0; } -static void __init configure_uart(char port, int baud) +static void __init configure_uart(int port, int baud) { u32 pbclk; @@ -60,7 +60,7 @@ static void __init configure_uart(char port, int baud) uart_base + PIC32_SET(U_STA(port))); } -static void __init setup_early_console(char port, int baud) +static void __init setup_early_console(int port, int baud) { if (configure_uart_pins(port)) return; @@ -130,16 +130,15 @@ _out: return baud; } -void __init fw_init_early_console(char port) +void __init fw_init_early_console(void) { char *arch_cmdline = pic32_getcmdline(); - int baud = -1; + int baud, port; uart_base = ioremap(PIC32_BASE_UART, 0xc00); baud = get_baud_from_cmdline(arch_cmdline); - if (port == -1) - port = get_port_from_cmdline(arch_cmdline); + port = get_port_from_cmdline(arch_cmdline); if (port == -1) port = EARLY_CONSOLE_PORT; diff --git a/arch/mips/pic32/pic32mzda/init.c b/arch/mips/pic32/pic32mzda/init.c index f232c77ff5265381908eef747eacca2f4316b4be..488c0bee7ebf59d49dd8f6b105bc031143cab5e8 100644 --- a/arch/mips/pic32/pic32mzda/init.c +++ b/arch/mips/pic32/pic32mzda/init.c @@ -60,7 +60,7 @@ void __init plat_mem_setup(void) strlcpy(arcs_cmdline, boot_command_line, COMMAND_LINE_SIZE); #ifdef CONFIG_EARLY_PRINTK - fw_init_early_console(-1); + fw_init_early_console(); #endif pic32_config_init(); } diff --git a/arch/mips/sgi-ip27/ip27-xtalk.c b/arch/mips/sgi-ip27/ip27-xtalk.c index 000ede156bdc040c8b998903bb523cf767ac612c..5143d1cf8984c5b2ec9139831bc1e07a1cbad94d 100644 --- a/arch/mips/sgi-ip27/ip27-xtalk.c +++ b/arch/mips/sgi-ip27/ip27-xtalk.c @@ -27,15 +27,18 @@ static void bridge_platform_create(nasid_t nasid, int widget, int masterwid) { struct xtalk_bridge_platform_data *bd; struct sgi_w1_platform_data *wd; - struct platform_device *pdev; + struct platform_device *pdev_wd; + struct platform_device *pdev_bd; struct resource w1_res; unsigned long offset; offset = NODE_OFFSET(nasid); wd = kzalloc(sizeof(*wd), GFP_KERNEL); - if (!wd) - goto no_mem; + if (!wd) { + pr_warn("xtalk:n%d/%x bridge create out of memory\n", nasid, widget); + return; + } snprintf(wd->dev_id, sizeof(wd->dev_id), "bridge-%012lx", offset + (widget << SWIN_SIZE_BITS)); @@ -46,22 +49,35 @@ static void bridge_platform_create(nasid_t nasid, int widget, int masterwid) w1_res.end = w1_res.start + 3; w1_res.flags = IORESOURCE_MEM; - pdev = platform_device_alloc("sgi_w1", PLATFORM_DEVID_AUTO); - if (!pdev) { - kfree(wd); - goto no_mem; + pdev_wd = platform_device_alloc("sgi_w1", PLATFORM_DEVID_AUTO); + if (!pdev_wd) { + pr_warn("xtalk:n%d/%x bridge create out of memory\n", nasid, widget); + goto err_kfree_wd; + } + if (platform_device_add_resources(pdev_wd, &w1_res, 1)) { + pr_warn("xtalk:n%d/%x bridge failed to add platform resources.\n", nasid, widget); + goto err_put_pdev_wd; + } + if (platform_device_add_data(pdev_wd, wd, sizeof(*wd))) { + pr_warn("xtalk:n%d/%x bridge failed to add platform data.\n", nasid, widget); + goto err_put_pdev_wd; + } + if (platform_device_add(pdev_wd)) { + pr_warn("xtalk:n%d/%x bridge failed to add platform device.\n", nasid, widget); + goto err_put_pdev_wd; } - platform_device_add_resources(pdev, &w1_res, 1); - platform_device_add_data(pdev, wd, sizeof(*wd)); - platform_device_add(pdev); + /* platform_device_add_data() duplicates the data */ + kfree(wd); bd = kzalloc(sizeof(*bd), GFP_KERNEL); - if (!bd) - goto no_mem; - pdev = platform_device_alloc("xtalk-bridge", PLATFORM_DEVID_AUTO); - if (!pdev) { - kfree(bd); - goto no_mem; + if (!bd) { + pr_warn("xtalk:n%d/%x bridge create out of memory\n", nasid, widget); + goto err_unregister_pdev_wd; + } + pdev_bd = platform_device_alloc("xtalk-bridge", PLATFORM_DEVID_AUTO); + if (!pdev_bd) { + pr_warn("xtalk:n%d/%x bridge create out of memory\n", nasid, widget); + goto err_kfree_bd; } @@ -82,13 +98,31 @@ static void bridge_platform_create(nasid_t nasid, int widget, int masterwid) bd->io.flags = IORESOURCE_IO; bd->io_offset = offset; - platform_device_add_data(pdev, bd, sizeof(*bd)); - platform_device_add(pdev); + if (platform_device_add_data(pdev_bd, bd, sizeof(*bd))) { + pr_warn("xtalk:n%d/%x bridge failed to add platform data.\n", nasid, widget); + goto err_put_pdev_bd; + } + if (platform_device_add(pdev_bd)) { + pr_warn("xtalk:n%d/%x bridge failed to add platform device.\n", nasid, widget); + goto err_put_pdev_bd; + } + /* platform_device_add_data() duplicates the data */ + kfree(bd); pr_info("xtalk:n%d/%x bridge widget\n", nasid, widget); return; -no_mem: - pr_warn("xtalk:n%d/%x bridge create out of memory\n", nasid, widget); +err_put_pdev_bd: + platform_device_put(pdev_bd); +err_kfree_bd: + kfree(bd); +err_unregister_pdev_wd: + platform_device_unregister(pdev_wd); + return; +err_put_pdev_wd: + platform_device_put(pdev_wd); +err_kfree_wd: + kfree(wd); + return; } static int probe_one_port(nasid_t nasid, int widget, int masterwid) diff --git a/arch/nds32/include/asm/thread_info.h b/arch/nds32/include/asm/thread_info.h index c135111ec44ebb1519c13b616edbda6d85f4f8d3..d3967ad184f03361599f357dd2510f7f92366a9f 100644 --- a/arch/nds32/include/asm/thread_info.h +++ b/arch/nds32/include/asm/thread_info.h @@ -48,6 +48,7 @@ struct thread_info { #define TIF_NEED_RESCHED 2 #define TIF_SINGLESTEP 3 #define TIF_NOTIFY_RESUME 4 /* callback before returning to user */ +#define TIF_NOTIFY_SIGNAL 5 /* signal notifications exist */ #define TIF_SYSCALL_TRACE 8 #define TIF_POLLING_NRFLAG 17 #define TIF_MEMDIE 18 @@ -57,6 +58,7 @@ struct thread_info { #define _TIF_SIGPENDING (1 << TIF_SIGPENDING) #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) #define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME) +#define _TIF_NOTIFY_SIGNAL (1 << TIF_NOTIFY_SIGNAL) #define _TIF_SINGLESTEP (1 << TIF_SINGLESTEP) #define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE) #define _TIF_POLLING_NRFLAG (1 << TIF_POLLING_NRFLAG) diff --git a/arch/nds32/kernel/ex-exit.S b/arch/nds32/kernel/ex-exit.S index 6a2966c2d8c8f4e2af2dad5ede211de8c8f046fd..b30699911b81ecf63aa26bf2b18a9ef3da03af79 100644 --- a/arch/nds32/kernel/ex-exit.S +++ b/arch/nds32/kernel/ex-exit.S @@ -120,7 +120,7 @@ work_pending: andi $p1, $r1, #_TIF_NEED_RESCHED bnez $p1, work_resched - andi $p1, $r1, #_TIF_SIGPENDING|#_TIF_NOTIFY_RESUME + andi $p1, $r1, #_TIF_SIGPENDING|#_TIF_NOTIFY_RESUME|#_TIF_NOTIFY_SIGNAL beqz $p1, no_work_pending move $r0, $sp ! 'regs' diff --git a/arch/nds32/kernel/process.c b/arch/nds32/kernel/process.c index e01ad5d1722450f2f4b54e16e615b4c9cf4dea40..c1327e552ec6c68a66ea708c127e7fc7e00d1df3 100644 --- a/arch/nds32/kernel/process.c +++ b/arch/nds32/kernel/process.c @@ -156,7 +156,7 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start, memset(&p->thread.cpu_context, 0, sizeof(struct cpu_context)); - if (unlikely(p->flags & PF_KTHREAD)) { + if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { memset(childregs, 0, sizeof(struct pt_regs)); /* kernel thread fn */ p->thread.cpu_context.r6 = stack_start; diff --git a/arch/nds32/kernel/signal.c b/arch/nds32/kernel/signal.c index 2acb94812af987882ead1c1ab72c9a99e87d4e75..7e3ca430a2233c7cd530fc7e7192a44f811f4770 100644 --- a/arch/nds32/kernel/signal.c +++ b/arch/nds32/kernel/signal.c @@ -376,7 +376,7 @@ static void do_signal(struct pt_regs *regs) asmlinkage void do_notify_resume(struct pt_regs *regs, unsigned int thread_flags) { - if (thread_flags & _TIF_SIGPENDING) + if (thread_flags & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL)) do_signal(regs); if (thread_flags & _TIF_NOTIFY_RESUME) diff --git a/arch/nios2/boot/Makefile b/arch/nios2/boot/Makefile index 37dfc7e584bce3d8080512e99e6e9062e9ebf9de..0b704c1f379f5377728b7b956c845ca5fd5ed194 100644 --- a/arch/nios2/boot/Makefile +++ b/arch/nios2/boot/Makefile @@ -20,7 +20,7 @@ $(obj)/vmlinux.bin: vmlinux FORCE $(obj)/vmlinux.gz: $(obj)/vmlinux.bin FORCE $(call if_changed,gzip) -$(obj)/vmImage: $(obj)/vmlinux.gz +$(obj)/vmImage: $(obj)/vmlinux.gz FORCE $(call if_changed,uimage) @$(kecho) 'Kernel: $@ is ready' diff --git a/arch/nios2/include/asm/thread_info.h b/arch/nios2/include/asm/thread_info.h index 7349a4fa635beafbaef4d0396f786908c00f5b75..272d2c72a7275bf1a0fe01789524e48cd00bf038 100644 --- a/arch/nios2/include/asm/thread_info.h +++ b/arch/nios2/include/asm/thread_info.h @@ -86,6 +86,7 @@ static inline struct thread_info *current_thread_info(void) #define TIF_MEMDIE 4 /* is terminating due to OOM killer */ #define TIF_SECCOMP 5 /* secure computing */ #define TIF_SYSCALL_AUDIT 6 /* syscall auditing active */ +#define TIF_NOTIFY_SIGNAL 7 /* signal notifications exist */ #define TIF_RESTORE_SIGMASK 9 /* restore signal mask in do_signal() */ #define TIF_POLLING_NRFLAG 16 /* true if poll_idle() is polling @@ -97,6 +98,7 @@ static inline struct thread_info *current_thread_info(void) #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) #define _TIF_SECCOMP (1 << TIF_SECCOMP) #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) +#define _TIF_NOTIFY_SIGNAL (1 << TIF_NOTIFY_SIGNAL) #define _TIF_RESTORE_SIGMASK (1 << TIF_RESTORE_SIGMASK) #define _TIF_POLLING_NRFLAG (1 << TIF_POLLING_NRFLAG) diff --git a/arch/nios2/kernel/process.c b/arch/nios2/kernel/process.c index 50b4eb19a6cc9962198ddbe12e1ba02bf2324d4b..c5f916ca6845f02876a9826a0b0fa9dcfa265715 100644 --- a/arch/nios2/kernel/process.c +++ b/arch/nios2/kernel/process.c @@ -109,7 +109,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long arg, struct switch_stack *childstack = ((struct switch_stack *)childregs) - 1; - if (unlikely(p->flags & PF_KTHREAD)) { + if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { memset(childstack, 0, sizeof(struct switch_stack) + sizeof(struct pt_regs)); diff --git a/arch/nios2/kernel/signal.c b/arch/nios2/kernel/signal.c index 916180e4a9978190c3399a2eb62d87262c00fb26..68d626c4f1ba7708863ea71a6dc553a9f0480f6e 100644 --- a/arch/nios2/kernel/signal.c +++ b/arch/nios2/kernel/signal.c @@ -309,7 +309,8 @@ asmlinkage int do_notify_resume(struct pt_regs *regs) if (!user_mode(regs)) return 0; - if (test_thread_flag(TIF_SIGPENDING)) { + if (test_thread_flag(TIF_SIGPENDING) || + test_thread_flag(TIF_NOTIFY_SIGNAL)) { int restart = do_signal(regs); if (unlikely(restart)) { diff --git a/arch/openrisc/include/asm/thread_info.h b/arch/openrisc/include/asm/thread_info.h index 9afe68bc423b36cbf9379bac567f0f9f5780772b..4f9d2a26145584da003193414d43bbbd59e19b48 100644 --- a/arch/openrisc/include/asm/thread_info.h +++ b/arch/openrisc/include/asm/thread_info.h @@ -98,6 +98,7 @@ register struct thread_info *current_thread_info_reg asm("r10"); #define TIF_SINGLESTEP 4 /* restore singlestep on return to user * mode */ +#define TIF_NOTIFY_SIGNAL 5 /* signal notifications exist */ #define TIF_SYSCALL_TRACEPOINT 8 /* for ftrace syscall instrumentation */ #define TIF_RESTORE_SIGMASK 9 #define TIF_POLLING_NRFLAG 16 /* true if poll_idle() is polling * TIF_NEED_RESCHED @@ -109,6 +110,7 @@ register struct thread_info *current_thread_info_reg asm("r10"); #define _TIF_SIGPENDING (1<flags & PF_KTHREAD)) { + if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { memset(kregs, 0, sizeof(struct pt_regs)); kregs->gpr[20] = usp; /* fn, kernel thread */ kregs->gpr[22] = arg; diff --git a/arch/openrisc/kernel/signal.c b/arch/openrisc/kernel/signal.c index af66f968dd4590b7e53b813e0379ed5f56f32553..1ebcff2710965f08a7a2056c2e09be72f986c849 100644 --- a/arch/openrisc/kernel/signal.c +++ b/arch/openrisc/kernel/signal.c @@ -299,7 +299,7 @@ do_work_pending(struct pt_regs *regs, unsigned int thread_flags, int syscall) if (unlikely(!user_mode(regs))) return 0; local_irq_enable(); - if (thread_flags & _TIF_SIGPENDING) { + if (thread_flags & (_TIF_SIGPENDING|_TIF_NOTIFY_SIGNAL)) { int restart = do_signal(regs, syscall); if (unlikely(restart)) { /* diff --git a/arch/parisc/include/asm/hardware.h b/arch/parisc/include/asm/hardware.h index 9d3d7737c58b1214f4844395678e0ad77360be3a..a005ebc547793eabf654ecc2afcf0f94f9239313 100644 --- a/arch/parisc/include/asm/hardware.h +++ b/arch/parisc/include/asm/hardware.h @@ -10,12 +10,12 @@ #define SVERSION_ANY_ID PA_SVERSION_ANY_ID struct hp_hardware { - unsigned short hw_type:5; /* HPHW_xxx */ - unsigned short hversion; - unsigned long sversion:28; - unsigned short opt; - const char name[80]; /* The hardware description */ -}; + unsigned int hw_type:8; /* HPHW_xxx */ + unsigned int hversion:12; + unsigned int sversion:12; + unsigned char opt; + unsigned char name[59]; /* The hardware description */ +} __packed; struct parisc_device; diff --git a/arch/parisc/include/asm/thread_info.h b/arch/parisc/include/asm/thread_info.h index 285757544cca230d5714bf72fb7679ef70096a48..0bd38a972ceab5fe577068c24f7412d9c2490535 100644 --- a/arch/parisc/include/asm/thread_info.h +++ b/arch/parisc/include/asm/thread_info.h @@ -52,6 +52,7 @@ struct thread_info { #define TIF_POLLING_NRFLAG 3 /* true if poll_idle() is polling TIF_NEED_RESCHED */ #define TIF_32BIT 4 /* 32 bit binary */ #define TIF_MEMDIE 5 /* is terminating due to OOM killer */ +#define TIF_NOTIFY_SIGNAL 6 /* signal notifications exist */ #define TIF_SYSCALL_AUDIT 7 /* syscall auditing active */ #define TIF_NOTIFY_RESUME 8 /* callback before returning to user */ #define TIF_SINGLESTEP 9 /* single stepping? */ @@ -61,6 +62,7 @@ struct thread_info { #define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE) #define _TIF_SIGPENDING (1 << TIF_SIGPENDING) +#define _TIF_NOTIFY_SIGNAL (1 << TIF_NOTIFY_SIGNAL) #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) #define _TIF_POLLING_NRFLAG (1 << TIF_POLLING_NRFLAG) #define _TIF_32BIT (1 << TIF_32BIT) @@ -72,7 +74,7 @@ struct thread_info { #define _TIF_SYSCALL_TRACEPOINT (1 << TIF_SYSCALL_TRACEPOINT) #define _TIF_USER_WORK_MASK (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | \ - _TIF_NEED_RESCHED) + _TIF_NEED_RESCHED | _TIF_NOTIFY_SIGNAL) #define _TIF_SYSCALL_TRACE_MASK (_TIF_SYSCALL_TRACE | _TIF_SINGLESTEP | \ _TIF_BLOCKSTEP | _TIF_SYSCALL_AUDIT | \ _TIF_SECCOMP | _TIF_SYSCALL_TRACEPOINT) diff --git a/arch/parisc/kernel/drivers.c b/arch/parisc/kernel/drivers.c index f5a25ed0930d2868ec78d301f957f8a60547ce47..d95157488832a05a868ae2fd51a4dc0d616175ee 100644 --- a/arch/parisc/kernel/drivers.c +++ b/arch/parisc/kernel/drivers.c @@ -883,15 +883,13 @@ void __init walk_central_bus(void) &root); } -static void print_parisc_device(struct parisc_device *dev) +static __init void print_parisc_device(struct parisc_device *dev) { - char hw_path[64]; - static int count; + static int count __initdata; - print_pa_hwpath(dev, hw_path); - pr_info("%d. %s at %pap [%s] { %d, 0x%x, 0x%.3x, 0x%.5x }", - ++count, dev->name, &(dev->hpa.start), hw_path, dev->id.hw_type, - dev->id.hversion_rev, dev->id.hversion, dev->id.sversion); + pr_info("%d. %s at %pap { type:%d, hv:%#x, sv:%#x, rev:%#x }", + ++count, dev->name, &(dev->hpa.start), dev->id.hw_type, + dev->id.hversion, dev->id.sversion, dev->id.hversion_rev); if (dev->num_addrs) { int k; @@ -1080,7 +1078,7 @@ static __init int qemu_print_iodc_data(struct device *lin_dev, void *data) -static int print_one_device(struct device * dev, void * data) +static __init int print_one_device(struct device * dev, void * data) { struct parisc_device * pdev = to_parisc_device(dev); diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c index a92a23d6acd931c2fb047a898b3c6eef9d488e20..5e4381280c97bfded073f549658a75dc456faf70 100644 --- a/arch/parisc/kernel/process.c +++ b/arch/parisc/kernel/process.c @@ -200,7 +200,7 @@ copy_thread(unsigned long clone_flags, unsigned long usp, extern void * const ret_from_kernel_thread; extern void * const child_return; - if (unlikely(p->flags & PF_KTHREAD)) { + if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { /* kernel thread */ memset(cregs, 0, sizeof(struct pt_regs)); if (!usp) /* idle thread */ diff --git a/arch/parisc/kernel/signal.c b/arch/parisc/kernel/signal.c index 8d6c9b88eb3f2cec74238089278015f4d08bbfac..db1a47cf424ddef417e6ab081123abc6872549e8 100644 --- a/arch/parisc/kernel/signal.c +++ b/arch/parisc/kernel/signal.c @@ -609,7 +609,8 @@ do_signal(struct pt_regs *regs, long in_syscall) void do_notify_resume(struct pt_regs *regs, long in_syscall) { - if (test_thread_flag(TIF_SIGPENDING)) + if (test_thread_flag(TIF_SIGPENDING) || + test_thread_flag(TIF_NOTIFY_SIGNAL)) do_signal(regs, in_syscall); if (test_thread_flag(TIF_NOTIFY_RESUME)) diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index 6d25bfd1a6f875eec170d541ec2006ee11f3917a..304029a895c542e284d2aa02dd9b8a77cecd3a40 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -153,7 +153,7 @@ CFLAGS-$(CONFIG_GENERIC_CPU) += -mcpu=power8 CFLAGS-$(CONFIG_GENERIC_CPU) += $(call cc-option,-mtune=power9,-mtune=power8) else CFLAGS-$(CONFIG_GENERIC_CPU) += $(call cc-option,-mtune=power7,$(call cc-option,-mtune=power5)) -CFLAGS-$(CONFIG_GENERIC_CPU) += $(call cc-option,-mcpu=power5,-mcpu=power4) +CFLAGS-$(CONFIG_GENERIC_CPU) += -mcpu=power4 endif else ifdef CONFIG_PPC_BOOK3E_64 CFLAGS-$(CONFIG_GENERIC_CPU) += -mcpu=powerpc64 diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile index e4b364b5da9e7a110400ac4d746c23108f2dfa26..8b78eba755f9a8d039622ed8b7c11497a4aa1336 100644 --- a/arch/powerpc/boot/Makefile +++ b/arch/powerpc/boot/Makefile @@ -30,6 +30,7 @@ endif BOOTCFLAGS := -Wall -Wundef -Wstrict-prototypes -Wno-trigraphs \ -fno-strict-aliasing -O2 -msoft-float -mno-altivec -mno-vsx \ + $(call cc-option,-mno-spe) $(call cc-option,-mspe=no) \ -pipe -fomit-frame-pointer -fno-builtin -fPIC -nostdinc \ $(LINUXINCLUDE) diff --git a/arch/powerpc/boot/dts/fsl/e500v1_power_isa.dtsi b/arch/powerpc/boot/dts/fsl/e500v1_power_isa.dtsi new file mode 100644 index 0000000000000000000000000000000000000000..7e2a90cde72e52c2ffdfa7375300c14219c2a006 --- /dev/null +++ b/arch/powerpc/boot/dts/fsl/e500v1_power_isa.dtsi @@ -0,0 +1,51 @@ +/* + * e500v1 Power ISA Device Tree Source (include) + * + * Copyright 2012 Freescale Semiconductor Inc. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * * Neither the name of Freescale Semiconductor nor the + * names of its contributors may be used to endorse or promote products + * derived from this software without specific prior written permission. + * + * + * ALTERNATIVELY, this software may be distributed under the terms of the + * GNU General Public License ("GPL") as published by the Free Software + * Foundation, either version 2 of that License or (at your option) any + * later version. + * + * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor "AS IS" AND ANY + * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED + * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY + * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES + * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; + * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND + * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +/ { + cpus { + power-isa-version = "2.03"; + power-isa-b; // Base + power-isa-e; // Embedded + power-isa-atb; // Alternate Time Base + power-isa-cs; // Cache Specification + power-isa-e.le; // Embedded.Little-Endian + power-isa-e.pm; // Embedded.Performance Monitor + power-isa-ecl; // Embedded Cache Locking + power-isa-mmc; // Memory Coherence + power-isa-sp; // Signal Processing Engine + power-isa-sp.fs; // SPE.Embedded Float Scalar Single + power-isa-sp.fv; // SPE.Embedded Float Vector + mmu-type = "power-embedded"; + }; +}; diff --git a/arch/powerpc/boot/dts/fsl/mpc8540ads.dts b/arch/powerpc/boot/dts/fsl/mpc8540ads.dts index 18a885130538a483d4ede5ac51549cebc0d63e12..e03ae130162baa407e03a0cda01311842301903d 100644 --- a/arch/powerpc/boot/dts/fsl/mpc8540ads.dts +++ b/arch/powerpc/boot/dts/fsl/mpc8540ads.dts @@ -7,7 +7,7 @@ /dts-v1/; -/include/ "e500v2_power_isa.dtsi" +/include/ "e500v1_power_isa.dtsi" / { model = "MPC8540ADS"; diff --git a/arch/powerpc/boot/dts/fsl/mpc8541cds.dts b/arch/powerpc/boot/dts/fsl/mpc8541cds.dts index ac381e7b1c60ece2b7f1a54ca7d34f5d26651488..a2a6c5cf852e971f7ce6928f572dd93b4c5699cb 100644 --- a/arch/powerpc/boot/dts/fsl/mpc8541cds.dts +++ b/arch/powerpc/boot/dts/fsl/mpc8541cds.dts @@ -7,7 +7,7 @@ /dts-v1/; -/include/ "e500v2_power_isa.dtsi" +/include/ "e500v1_power_isa.dtsi" / { model = "MPC8541CDS"; diff --git a/arch/powerpc/boot/dts/fsl/mpc8555cds.dts b/arch/powerpc/boot/dts/fsl/mpc8555cds.dts index 9f58db2a7e66165f5abad4ff5aac3ccbaf16f57f..901b6ff06dfbb4b7e4a8b3c81bc6ddb338879283 100644 --- a/arch/powerpc/boot/dts/fsl/mpc8555cds.dts +++ b/arch/powerpc/boot/dts/fsl/mpc8555cds.dts @@ -7,7 +7,7 @@ /dts-v1/; -/include/ "e500v2_power_isa.dtsi" +/include/ "e500v1_power_isa.dtsi" / { model = "MPC8555CDS"; diff --git a/arch/powerpc/boot/dts/fsl/mpc8560ads.dts b/arch/powerpc/boot/dts/fsl/mpc8560ads.dts index a24722ccaebf1cef5a6eb62bc2fe15a43ac9f6a3..c2f9aea78b29ff3b8e513ab60498292a2d1927bc 100644 --- a/arch/powerpc/boot/dts/fsl/mpc8560ads.dts +++ b/arch/powerpc/boot/dts/fsl/mpc8560ads.dts @@ -7,7 +7,7 @@ /dts-v1/; -/include/ "e500v2_power_isa.dtsi" +/include/ "e500v1_power_isa.dtsi" / { model = "MPC8560ADS"; diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h index 6de3517bea94e7fb7f761e1af0b559b249050951..ff31d2fa2140f34163c488f60da99cff894e0c39 100644 --- a/arch/powerpc/include/asm/thread_info.h +++ b/arch/powerpc/include/asm/thread_info.h @@ -96,6 +96,7 @@ void arch_setup_new_exec(void); #define TIF_SYSCALL_TRACE 0 /* syscall trace active */ #define TIF_SIGPENDING 1 /* signal pending */ #define TIF_NEED_RESCHED 2 /* rescheduling necessary */ +#define TIF_NOTIFY_SIGNAL 3 /* signal notifications exist */ #define TIF_SYSCALL_EMU 4 /* syscall emulation active */ #define TIF_RESTORE_TM 5 /* need to restore TM FP/VEC/VSX */ #define TIF_PATCH_PENDING 6 /* pending live patching update */ @@ -121,6 +122,7 @@ void arch_setup_new_exec(void); #define _TIF_SYSCALL_TRACE (1<list); parent = of_get_parent(dn); pdn->parent = parent ? PCI_DN(parent) : NULL; + of_node_put(parent); if (pdn->parent) list_add_tail(&pdn->list, &pdn->parent->child_list); diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index c43cc26bde5dbfef5039e1c8678f63dba636ce36..cf375d67eacbd9fe81e4bebcb993aabbf666ab2c 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1684,7 +1684,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, /* Copy registers */ sp -= sizeof(struct pt_regs); childregs = (struct pt_regs *) sp; - if (unlikely(p->flags & PF_KTHREAD)) { + if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { /* kernel thread */ memset(childregs, 0, sizeof(struct pt_regs)); childregs->gpr[1] = sp + sizeof(struct pt_regs); diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c index d2c356f370775dddb5191888cd414c0e33974cf6..a8bb0aca1d021ee675b0ba10d467be761db572ab 100644 --- a/arch/powerpc/kernel/signal.c +++ b/arch/powerpc/kernel/signal.c @@ -318,7 +318,7 @@ void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags) if (thread_info_flags & _TIF_PATCH_PENDING) klp_update_patch_state(current); - if (thread_info_flags & _TIF_SIGPENDING) { + if (thread_info_flags & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL)) { BUG_ON(regs != current->thread.regs); do_signal(current); } diff --git a/arch/powerpc/math-emu/math_efp.c b/arch/powerpc/math-emu/math_efp.c index 0a05e51964c1098e169f69412da07edec4d6363a..90111c9e7521f1a564dfd4c3c5c27e46b7a35f69 100644 --- a/arch/powerpc/math-emu/math_efp.c +++ b/arch/powerpc/math-emu/math_efp.c @@ -17,6 +17,7 @@ #include #include +#include #include #include diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c index c61c3b62c8c628c290c9bc1846b35378d480ccfd..1d05c168c8fb52ec2fcce47f4e9ef0ef8f28cf7b 100644 --- a/arch/powerpc/platforms/powernv/opal.c +++ b/arch/powerpc/platforms/powernv/opal.c @@ -892,6 +892,7 @@ static void opal_export_attrs(void) kobj = kobject_create_and_add("exports", opal_kobj); if (!kobj) { pr_warn("kobject_create_and_add() of exports failed\n"); + of_node_put(np); return; } diff --git a/arch/powerpc/sysdev/fsl_msi.c b/arch/powerpc/sysdev/fsl_msi.c index 808e7118abfc5b45655156866e967a5be72030d5..d276c5e964458689ad746ffb6362694a85d6c9a1 100644 --- a/arch/powerpc/sysdev/fsl_msi.c +++ b/arch/powerpc/sysdev/fsl_msi.c @@ -211,8 +211,10 @@ static int fsl_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) dev_err(&pdev->dev, "node %pOF has an invalid fsl,msi phandle %u\n", hose->dn, np->phandle); + of_node_put(np); return -EINVAL; } + of_node_put(np); } for_each_pci_msi_entry(entry, pdev) { diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 1b894c327578168a561669d70777fc71067b5bac..557c4a8c4087dd4518b109298137592f8eeefedc 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -35,7 +35,7 @@ config RISCV select CLINT_TIMER if !MMU select COMMON_CLK select EDAC_SUPPORT - select GENERIC_ARCH_TOPOLOGY if SMP + select GENERIC_ARCH_TOPOLOGY select GENERIC_ATOMIC64 if !64BIT select GENERIC_CLOCKEVENTS select GENERIC_EARLY_IOREMAP diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile index e7aedc634961764eac8a32ff54ccee945080c2c2..e0ecca5b61e18180f06c3580ba22bcd06b166c68 100644 --- a/arch/riscv/Makefile +++ b/arch/riscv/Makefile @@ -37,6 +37,7 @@ else endif ifeq ($(CONFIG_LD_IS_LLD),y) +ifeq ($(shell test $(CONFIG_LLD_VERSION) -lt 150000; echo $$?),0) KBUILD_CFLAGS += -mno-relax KBUILD_AFLAGS += -mno-relax ifndef CONFIG_AS_IS_LLVM @@ -44,6 +45,7 @@ ifndef CONFIG_AS_IS_LLVM KBUILD_AFLAGS += -Wa,-mno-relax endif endif +endif # ISA string setting riscv-march-$(CONFIG_ARCH_RV32I) := rv32ima diff --git a/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts b/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts index 60846e88ae4b1c3ef5a5c0a3bc3ba36be6f9985b..dddabfbbc7a909962664bf1dc21350cd3e74c3d9 100644 --- a/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts +++ b/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts @@ -3,6 +3,8 @@ #include "fu540-c000.dtsi" #include +#include +#include /* Clock frequency (in Hz) of the PCB crystal for rtcclk */ #define RTCCLK_FREQ 1000000 @@ -46,6 +48,42 @@ compatible = "gpio-restart"; gpios = <&gpio 10 GPIO_ACTIVE_LOW>; }; + + led-controller { + compatible = "pwm-leds"; + + led-d1 { + pwms = <&pwm0 0 7812500 PWM_POLARITY_INVERTED>; + active-low; + color = ; + max-brightness = <255>; + label = "d1"; + }; + + led-d2 { + pwms = <&pwm0 1 7812500 PWM_POLARITY_INVERTED>; + active-low; + color = ; + max-brightness = <255>; + label = "d2"; + }; + + led-d3 { + pwms = <&pwm0 2 7812500 PWM_POLARITY_INVERTED>; + active-low; + color = ; + max-brightness = <255>; + label = "d3"; + }; + + led-d4 { + pwms = <&pwm0 3 7812500 PWM_POLARITY_INVERTED>; + active-low; + color = ; + max-brightness = <255>; + label = "d4"; + }; + }; }; &uart0 { diff --git a/arch/riscv/include/asm/io.h b/arch/riscv/include/asm/io.h index c025a746a1486c1af7e3e860b355429610eeeb56..391dd869db64be57f5fc92c206ef3af50534dc86 100644 --- a/arch/riscv/include/asm/io.h +++ b/arch/riscv/include/asm/io.h @@ -114,9 +114,9 @@ __io_reads_ins(reads, u32, l, __io_br(), __io_ar(addr)) __io_reads_ins(ins, u8, b, __io_pbr(), __io_par(addr)) __io_reads_ins(ins, u16, w, __io_pbr(), __io_par(addr)) __io_reads_ins(ins, u32, l, __io_pbr(), __io_par(addr)) -#define insb(addr, buffer, count) __insb((void __iomem *)(long)addr, buffer, count) -#define insw(addr, buffer, count) __insw((void __iomem *)(long)addr, buffer, count) -#define insl(addr, buffer, count) __insl((void __iomem *)(long)addr, buffer, count) +#define insb(addr, buffer, count) __insb(PCI_IOBASE + (addr), buffer, count) +#define insw(addr, buffer, count) __insw(PCI_IOBASE + (addr), buffer, count) +#define insl(addr, buffer, count) __insl(PCI_IOBASE + (addr), buffer, count) __io_writes_outs(writes, u8, b, __io_bw(), __io_aw()) __io_writes_outs(writes, u16, w, __io_bw(), __io_aw()) @@ -128,22 +128,22 @@ __io_writes_outs(writes, u32, l, __io_bw(), __io_aw()) __io_writes_outs(outs, u8, b, __io_pbw(), __io_paw()) __io_writes_outs(outs, u16, w, __io_pbw(), __io_paw()) __io_writes_outs(outs, u32, l, __io_pbw(), __io_paw()) -#define outsb(addr, buffer, count) __outsb((void __iomem *)(long)addr, buffer, count) -#define outsw(addr, buffer, count) __outsw((void __iomem *)(long)addr, buffer, count) -#define outsl(addr, buffer, count) __outsl((void __iomem *)(long)addr, buffer, count) +#define outsb(addr, buffer, count) __outsb(PCI_IOBASE + (addr), buffer, count) +#define outsw(addr, buffer, count) __outsw(PCI_IOBASE + (addr), buffer, count) +#define outsl(addr, buffer, count) __outsl(PCI_IOBASE + (addr), buffer, count) #ifdef CONFIG_64BIT __io_reads_ins(reads, u64, q, __io_br(), __io_ar(addr)) #define readsq(addr, buffer, count) __readsq(addr, buffer, count) __io_reads_ins(ins, u64, q, __io_pbr(), __io_par(addr)) -#define insq(addr, buffer, count) __insq((void __iomem *)addr, buffer, count) +#define insq(addr, buffer, count) __insq(PCI_IOBASE + (addr), buffer, count) __io_writes_outs(writes, u64, q, __io_bw(), __io_aw()) #define writesq(addr, buffer, count) __writesq(addr, buffer, count) __io_writes_outs(outs, u64, q, __io_pbr(), __io_paw()) -#define outsq(addr, buffer, count) __outsq((void __iomem *)addr, buffer, count) +#define outsq(addr, buffer, count) __outsq(PCI_IOBASE + (addr), buffer, count) #endif #include diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 73e8b5e5bb6544e6c59684106f15146cf6b0fdac..b16304fdf44898fd6aa96cc1f7c012e21f544a69 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -470,6 +470,7 @@ extern void *dtb_early_va; extern uintptr_t dtb_early_pa; void setup_bootmem(void); void paging_init(void); +void misc_mem_init(void); #define FIRST_USER_ADDRESS 0 diff --git a/arch/riscv/include/asm/thread_info.h b/arch/riscv/include/asm/thread_info.h index d79ae9d98999f6b9dce68aaf00412fe08635e31b..c55e0a1f07a0fba0110ffeb67f67028b17a460aa 100644 --- a/arch/riscv/include/asm/thread_info.h +++ b/arch/riscv/include/asm/thread_info.h @@ -80,6 +80,7 @@ struct thread_info { #define TIF_SYSCALL_TRACEPOINT 6 /* syscall tracepoint instrumentation */ #define TIF_SYSCALL_AUDIT 7 /* syscall auditing */ #define TIF_SECCOMP 8 /* syscall secure computing */ +#define TIF_NOTIFY_SIGNAL 9 /* signal notifications exist */ #define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE) #define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME) @@ -88,9 +89,11 @@ struct thread_info { #define _TIF_SYSCALL_TRACEPOINT (1 << TIF_SYSCALL_TRACEPOINT) #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) #define _TIF_SECCOMP (1 << TIF_SECCOMP) +#define _TIF_NOTIFY_SIGNAL (1 << TIF_NOTIFY_SIGNAL) #define _TIF_WORK_MASK \ - (_TIF_NOTIFY_RESUME | _TIF_SIGPENDING | _TIF_NEED_RESCHED) + (_TIF_NOTIFY_RESUME | _TIF_SIGPENDING | _TIF_NEED_RESCHED | \ + _TIF_NOTIFY_SIGNAL) #define _TIF_SYSCALL_WORK \ (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_TRACEPOINT | _TIF_SYSCALL_AUDIT | \ diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c index dd5f985b1f40e0418f4bdac872819275a0766cd0..7868050ff426da5a270703d324d09bc55013ecc5 100644 --- a/arch/riscv/kernel/process.c +++ b/arch/riscv/kernel/process.c @@ -111,8 +111,10 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long arg, { struct pt_regs *childregs = task_pt_regs(p); + memset(&p->thread.s, 0, sizeof(p->thread.s)); + /* p->thread holds context to be restored by __switch_to() */ - if (unlikely(p->flags & PF_KTHREAD)) { + if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { /* Kernel thread */ memset(childregs, 0, sizeof(struct pt_regs)); childregs->gp = gp_in_global; diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index 117f3212a8e4b767ad0376f37c8a543b2c74a239..8e78a8ab6a345c429607a5029ce2801ed29915da 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -54,10 +54,17 @@ static DEFINE_PER_CPU(struct cpu, cpu_devices); static void __init parse_dtb(void) { /* Early scan of device tree from init memory */ - if (early_init_dt_scan(dtb_early_va)) - return; + if (early_init_dt_scan(dtb_early_va)) { + const char *name = of_flat_dt_get_machine_name(); + + if (name) { + pr_info("Machine model: %s\n", name); + dump_stack_set_arch_desc("%s (DT)", name); + } + } else { + pr_err("No DTB passed to the kernel\n"); + } - pr_err("No DTB passed to the kernel\n"); #ifdef CONFIG_CMDLINE_FORCE strlcpy(boot_command_line, CONFIG_CMDLINE, COMMAND_LINE_SIZE); pr_info("Forcing kernel command line to: %s\n", boot_command_line); @@ -89,6 +96,8 @@ void __init setup_arch(char **cmdline_p) else pr_err("No DTB found in kernel mappings\n"); #endif + early_init_fdt_scan_reserved_mem(); + misc_mem_init(); #ifdef CONFIG_SWIOTLB swiotlb_init(1); diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c index 529c123cf0a47689a47b595c4ea0f282266e7fff..50a8225c58bca4839a8bc6d4987dd95f15a44658 100644 --- a/arch/riscv/kernel/signal.c +++ b/arch/riscv/kernel/signal.c @@ -312,7 +312,7 @@ asmlinkage __visible void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags) { /* Handle pending signal delivery */ - if (thread_info_flags & _TIF_SIGPENDING) + if (thread_info_flags & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL)) do_signal(regs); if (thread_info_flags & _TIF_NOTIFY_RESUME) diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c index 0b04e0eae3ab5bfe0e9ff714e6ebef512b83dafd..0e0aed380e281b8fbc69c9ab1b9422d1baabb90c 100644 --- a/arch/riscv/kernel/smpboot.c +++ b/arch/riscv/kernel/smpboot.c @@ -46,6 +46,8 @@ void __init smp_prepare_cpus(unsigned int max_cpus) int cpuid; int ret; + store_cpu_topology(smp_processor_id()); + /* This covers non-smp usecase mandated by "nosmp" option */ if (max_cpus == 0) return; @@ -152,8 +154,8 @@ asmlinkage __visible void smp_callin(void) mmgrab(mm); current->active_mm = mm; + store_cpu_topology(curr_cpuid); notify_cpu_starting(curr_cpuid); - update_siblings_masks(curr_cpuid); set_cpu_online(curr_cpuid, 1); /* diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c index 8a7880b9c433eaeca415f77678ff63b115960d61..bb402685057a2693e10a085050832401aa65af94 100644 --- a/arch/riscv/kernel/sys_riscv.c +++ b/arch/riscv/kernel/sys_riscv.c @@ -18,9 +18,6 @@ static long riscv_sys_mmap(unsigned long addr, unsigned long len, if (unlikely(offset & (~PAGE_MASK >> page_shift_offset))) return -EINVAL; - if (unlikely((prot & PROT_WRITE) && !(prot & PROT_READ))) - return -EINVAL; - return ksys_mmap_pgoff(addr, len, prot, flags, fd, offset >> (PAGE_SHIFT - page_shift_offset)); } diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile index 24d936c147cdfbf1ee84526373793c133380e9c9..c92b55a0ec1cb12649266d08e255547393af52bf 100644 --- a/arch/riscv/kernel/vdso/Makefile +++ b/arch/riscv/kernel/vdso/Makefile @@ -28,9 +28,12 @@ obj-vdso := $(addprefix $(obj)/, $(obj-vdso)) obj-y += vdso.o vdso-syms.o CPPFLAGS_vdso.lds += -P -C -U$(ARCH) +ifneq ($(filter vgettimeofday, $(vdso-syms)),) +CPPFLAGS_vdso.lds += -DHAS_VGETTIMEOFDAY +endif # Disable -pg to prevent insert call site -CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) -Os +CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) # Disable profiling and instrumentation for VDSO code GCOV_PROFILE := n diff --git a/arch/riscv/kernel/vdso/vdso.lds.S b/arch/riscv/kernel/vdso/vdso.lds.S index e6f558bca71bb2128e6f1952b97e78a16cc09777..b3e58402c3426fd3283e97cd5d274b416abc806f 100644 --- a/arch/riscv/kernel/vdso/vdso.lds.S +++ b/arch/riscv/kernel/vdso/vdso.lds.S @@ -64,9 +64,11 @@ VERSION LINUX_4.15 { global: __vdso_rt_sigreturn; +#ifdef HAS_VGETTIMEOFDAY __vdso_gettimeofday; __vdso_clock_gettime; __vdso_clock_getres; +#endif __vdso_getcpu; __vdso_flush_icache; local: *; diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c index 3c8b9e433c673754e29444ffe2e75883c8ce0e99..8f84bbe0ac33e256f61fa59af676872e670deebf 100644 --- a/arch/riscv/mm/fault.c +++ b/arch/riscv/mm/fault.c @@ -167,7 +167,8 @@ static inline bool access_error(unsigned long cause, struct vm_area_struct *vma) } break; case EXC_LOAD_PAGE_FAULT: - if (!(vma->vm_flags & VM_READ)) { + /* Write implies read */ + if (!(vma->vm_flags & (VM_READ | VM_WRITE))) { return true; } break; diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index e8921e78a29260be1e4dace41b684e243831031f..6c2f38aac54432f4bdb7cf5ebaad2208caeb7523 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include @@ -41,13 +42,14 @@ struct pt_alloc_ops { #endif }; +static phys_addr_t dma32_phys_limit __ro_after_init; + static void __init zone_sizes_init(void) { unsigned long max_zone_pfns[MAX_NR_ZONES] = { 0, }; #ifdef CONFIG_ZONE_DMA32 - max_zone_pfns[ZONE_DMA32] = PFN_DOWN(min(4UL * SZ_1G, - (unsigned long) PFN_PHYS(max_low_pfn))); + max_zone_pfns[ZONE_DMA32] = PFN_DOWN(dma32_phys_limit); #endif max_zone_pfns[ZONE_NORMAL] = max_low_pfn; @@ -193,6 +195,7 @@ void __init setup_bootmem(void) max_pfn = PFN_DOWN(dram_end); max_low_pfn = max_pfn; + dma32_phys_limit = min(4UL * SZ_1G, (unsigned long)PFN_PHYS(max_low_pfn)); set_max_mapnr(max_low_pfn); #ifdef CONFIG_BLK_DEV_INITRD @@ -205,7 +208,7 @@ void __init setup_bootmem(void) */ memblock_reserve(dtb_early_pa, fdt_totalsize(dtb_early_va)); - early_init_fdt_scan_reserved_mem(); + dma_contiguous_reserve(dma32_phys_limit); memblock_allow_resize(); memblock_dump_all(); } @@ -665,8 +668,12 @@ static void __init resource_init(void) void __init paging_init(void) { setup_vm_final(); - sparse_init(); setup_zero_page(); +} + +void __init misc_mem_init(void) +{ + sparse_init(); zone_sizes_init(); resource_init(); } diff --git a/arch/s390/boot/compressed/vmlinux.lds.S b/arch/s390/boot/compressed/vmlinux.lds.S index 9427e2cd0c1542bf4adaab8edcbb789f8f84f26f..11bf3919610e40fe481ad0aea07be79719cdf797 100644 --- a/arch/s390/boot/compressed/vmlinux.lds.S +++ b/arch/s390/boot/compressed/vmlinux.lds.S @@ -91,8 +91,17 @@ SECTIONS _compressed_start = .; *(.vmlinux.bin.compressed) _compressed_end = .; - FILL(0xff); - . = ALIGN(4096); + } + +#define SB_TRAILER_SIZE 32 + /* Trailer needed for Secure Boot */ + . += SB_TRAILER_SIZE; /* make sure .sb.trailer does not overwrite the previous section */ + . = ALIGN(4096) - SB_TRAILER_SIZE; + .sb.trailer : { + QUAD(0) + QUAD(0) + QUAD(0) + QUAD(0x000000207a49504c) } _end = .; diff --git a/arch/s390/include/asm/futex.h b/arch/s390/include/asm/futex.h index 26f9144562c9ede4fbbd934ddcae7162ffba17bb..e1d0b2aaaddd3acedcdf1006441b99349caf28ac 100644 --- a/arch/s390/include/asm/futex.h +++ b/arch/s390/include/asm/futex.h @@ -16,7 +16,8 @@ "3: jl 1b\n" \ " lhi %0,0\n" \ "4: sacf 768\n" \ - EX_TABLE(0b,4b) EX_TABLE(2b,4b) EX_TABLE(3b,4b) \ + EX_TABLE(0b,4b) EX_TABLE(1b,4b) \ + EX_TABLE(2b,4b) EX_TABLE(3b,4b) \ : "=d" (ret), "=&d" (oldval), "=&d" (newval), \ "=m" (*uaddr) \ : "0" (-EFAULT), "d" (oparg), "a" (uaddr), \ diff --git a/arch/s390/include/asm/thread_info.h b/arch/s390/include/asm/thread_info.h index 13a04fcf77625618221ee68cb77d8a4715b213ba..0045341ade486490659160ad59f2f937e5a3df8f 100644 --- a/arch/s390/include/asm/thread_info.h +++ b/arch/s390/include/asm/thread_info.h @@ -65,6 +65,7 @@ void arch_setup_new_exec(void); #define TIF_GUARDED_STORAGE 4 /* load guarded storage control block */ #define TIF_PATCH_PENDING 5 /* pending live patching update */ #define TIF_PGSTE 6 /* New mm's will use 4K page tables */ +#define TIF_NOTIFY_SIGNAL 7 /* signal notifications exist */ #define TIF_ISOLATE_BP 8 /* Run process with isolated BP */ #define TIF_ISOLATE_BP_GUEST 9 /* Run KVM guests with isolated BP */ @@ -82,6 +83,7 @@ void arch_setup_new_exec(void); #define TIF_SYSCALL_TRACEPOINT 27 /* syscall tracepoint instrumentation */ #define _TIF_NOTIFY_RESUME BIT(TIF_NOTIFY_RESUME) +#define _TIF_NOTIFY_SIGNAL BIT(TIF_NOTIFY_SIGNAL) #define _TIF_SIGPENDING BIT(TIF_SIGPENDING) #define _TIF_NEED_RESCHED BIT(TIF_NEED_RESCHED) #define _TIF_UPROBE BIT(TIF_UPROBE) diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c index 76762dc67ca90134b67c244a212f9b25042188dc..f292c3e10671092b28fd0cc687e06b735a89e6c7 100644 --- a/arch/s390/kernel/crash_dump.c +++ b/arch/s390/kernel/crash_dump.c @@ -44,7 +44,7 @@ struct save_area { u64 fprs[16]; u32 fpc; u32 prefix; - u64 todpreg; + u32 todpreg; u64 timer; u64 todcmp; u64 vxrs_low[16]; diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 963e8cb936e2865b838f02865a9f6c4f11830274..88ecbcf097a369335801e9887f4d7efcf667410d 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -52,7 +52,8 @@ STACK_SIZE = 1 << STACK_SHIFT STACK_INIT = STACK_SIZE - STACK_FRAME_OVERHEAD - __PT_SIZE _TIF_WORK = (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | \ - _TIF_UPROBE | _TIF_GUARDED_STORAGE | _TIF_PATCH_PENDING) + _TIF_UPROBE | _TIF_GUARDED_STORAGE | _TIF_PATCH_PENDING | \ + _TIF_NOTIFY_SIGNAL) _TIF_TRACE = (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | \ _TIF_SYSCALL_TRACEPOINT) _CIF_WORK = (_CIF_ASCE_PRIMARY | _CIF_ASCE_SECONDARY | _CIF_FPU) @@ -481,8 +482,8 @@ ENTRY(system_call) #endif TSTMSK __PT_FLAGS(%r11),_PIF_SYSCALL_RESTART jo .Lsysc_syscall_restart - TSTMSK __TI_flags(%r12),_TIF_SIGPENDING - jo .Lsysc_sigpending + TSTMSK __TI_flags(%r12),(_TIF_SIGPENDING|_TIF_NOTIFY_SIGNAL) + jnz .Lsysc_sigpending TSTMSK __TI_flags(%r12),_TIF_NOTIFY_RESUME jo .Lsysc_notify_resume TSTMSK __LC_CPU_FLAGS,(_CIF_ASCE_PRIMARY|_CIF_ASCE_SECONDARY) @@ -863,8 +864,8 @@ ENTRY(io_int_handler) TSTMSK __TI_flags(%r12),_TIF_PATCH_PENDING jo .Lio_patch_pending #endif - TSTMSK __TI_flags(%r12),_TIF_SIGPENDING - jo .Lio_sigpending + TSTMSK __TI_flags(%r12),(_TIF_SIGPENDING|_TIF_NOTIFY_SIGNAL) + jnz .Lio_sigpending TSTMSK __TI_flags(%r12),_TIF_NOTIFY_RESUME jo .Lio_notify_resume TSTMSK __TI_flags(%r12),_TIF_GUARDED_STORAGE diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c index 137a170f47d4fb5e9dd2b752c9a250b4047bae3a..bd7da4049707cb72a9d9d52e69f499eaa9dd7bfe 100644 --- a/arch/s390/kernel/process.c +++ b/arch/s390/kernel/process.c @@ -127,7 +127,7 @@ int copy_thread(unsigned long clone_flags, unsigned long new_stackp, frame->sf.gprs[9] = (unsigned long) frame; /* Store access registers to kernel stack of new process. */ - if (unlikely(p->flags & PF_KTHREAD)) { + if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { /* kernel thread */ memset(&frame->childregs, 0, sizeof(struct pt_regs)); frame->childregs.psw.mask = PSW_KERNEL_BITS | PSW_MASK_DAT | diff --git a/arch/s390/kernel/signal.c b/arch/s390/kernel/signal.c index 9e900a8977bd2110f798439e1fc464c20a769e9b..b27b6c1f058d07e8175e85c640c243254e4efa84 100644 --- a/arch/s390/kernel/signal.c +++ b/arch/s390/kernel/signal.c @@ -472,7 +472,7 @@ void do_signal(struct pt_regs *regs) current->thread.system_call = test_pt_regs_flag(regs, PIF_SYSCALL) ? regs->int_code : 0; - if (get_signal(&ksig)) { + if (test_thread_flag(TIF_SIGPENDING) && get_signal(&ksig)) { /* Whee! Actually deliver the signal. */ if (current->thread.system_call) { regs->int_code = current->thread.system_call; diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index d8e9239c24ffc62c91a0f280fe5bddd89029a664..59db85fb63e1cb0015bfb9cfc4c728a76e617b36 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -1092,6 +1092,8 @@ static int kvm_s390_vm_get_migration(struct kvm *kvm, return 0; } +static void __kvm_s390_set_tod_clock(struct kvm *kvm, const struct kvm_s390_vm_tod_clock *gtod); + static int kvm_s390_set_tod_ext(struct kvm *kvm, struct kvm_device_attr *attr) { struct kvm_s390_vm_tod_clock gtod; @@ -1101,7 +1103,7 @@ static int kvm_s390_set_tod_ext(struct kvm *kvm, struct kvm_device_attr *attr) if (!test_kvm_facility(kvm, 139) && gtod.epoch_idx) return -EINVAL; - kvm_s390_set_tod_clock(kvm, >od); + __kvm_s390_set_tod_clock(kvm, >od); VM_EVENT(kvm, 3, "SET: TOD extension: 0x%x, TOD base: 0x%llx", gtod.epoch_idx, gtod.tod); @@ -1132,7 +1134,7 @@ static int kvm_s390_set_tod_low(struct kvm *kvm, struct kvm_device_attr *attr) sizeof(gtod.tod))) return -EFAULT; - kvm_s390_set_tod_clock(kvm, >od); + __kvm_s390_set_tod_clock(kvm, >od); VM_EVENT(kvm, 3, "SET: TOD base: 0x%llx", gtod.tod); return 0; } @@ -1144,6 +1146,16 @@ static int kvm_s390_set_tod(struct kvm *kvm, struct kvm_device_attr *attr) if (attr->flags) return -EINVAL; + mutex_lock(&kvm->lock); + /* + * For protected guests, the TOD is managed by the ultravisor, so trying + * to change it will never bring the expected results. + */ + if (kvm_s390_pv_is_protected(kvm)) { + ret = -EOPNOTSUPP; + goto out_unlock; + } + switch (attr->attr) { case KVM_S390_VM_TOD_EXT: ret = kvm_s390_set_tod_ext(kvm, attr); @@ -1158,6 +1170,9 @@ static int kvm_s390_set_tod(struct kvm *kvm, struct kvm_device_attr *attr) ret = -ENXIO; break; } + +out_unlock: + mutex_unlock(&kvm->lock); return ret; } @@ -3862,14 +3877,12 @@ retry: return 0; } -void kvm_s390_set_tod_clock(struct kvm *kvm, - const struct kvm_s390_vm_tod_clock *gtod) +static void __kvm_s390_set_tod_clock(struct kvm *kvm, const struct kvm_s390_vm_tod_clock *gtod) { struct kvm_vcpu *vcpu; struct kvm_s390_tod_clock_ext htod; int i; - mutex_lock(&kvm->lock); preempt_disable(); get_tod_clock_ext((char *)&htod); @@ -3890,7 +3903,15 @@ void kvm_s390_set_tod_clock(struct kvm *kvm, kvm_s390_vcpu_unblock_all(kvm); preempt_enable(); +} + +int kvm_s390_try_set_tod_clock(struct kvm *kvm, const struct kvm_s390_vm_tod_clock *gtod) +{ + if (!mutex_trylock(&kvm->lock)) + return 0; + __kvm_s390_set_tod_clock(kvm, gtod); mutex_unlock(&kvm->lock); + return 1; } /** diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index a3e9b71d426f9313ac3764c034c0e8aa85293480..b6ff64796af9d37e3db8a74984f3c7978831e937 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -326,8 +326,7 @@ int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu); int kvm_s390_handle_sigp_pei(struct kvm_vcpu *vcpu); /* implemented in kvm-s390.c */ -void kvm_s390_set_tod_clock(struct kvm *kvm, - const struct kvm_s390_vm_tod_clock *gtod); +int kvm_s390_try_set_tod_clock(struct kvm *kvm, const struct kvm_s390_vm_tod_clock *gtod); long kvm_arch_fault_in_page(struct kvm_vcpu *vcpu, gpa_t gpa, int writable); int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long addr); int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr); diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index 3b1a498e58d25d7273e515a8e09e0e1debbac3a5..e34d518dd3d395e899d35000ba840502d56cc769 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -102,7 +102,20 @@ static int handle_set_clock(struct kvm_vcpu *vcpu) return kvm_s390_inject_prog_cond(vcpu, rc); VCPU_EVENT(vcpu, 3, "SCK: setting guest TOD to 0x%llx", gtod.tod); - kvm_s390_set_tod_clock(vcpu->kvm, >od); + /* + * To set the TOD clock the kvm lock must be taken, but the vcpu lock + * is already held in handle_set_clock. The usual lock order is the + * opposite. As SCK is deprecated and should not be used in several + * cases, for example when the multiple epoch facility or TOD clock + * steering facility is installed (see Principles of Operation), a + * slow path can be used. If the lock can not be taken via try_lock, + * the instruction will be retried via -EAGAIN at a later point in + * time. + */ + if (!kvm_s390_try_set_tod_clock(vcpu->kvm, >od)) { + kvm_s390_retry_instr(vcpu); + return -EAGAIN; + } kvm_s390_set_psw_cc(vcpu, 0); return 0; diff --git a/arch/s390/pci/pci_mmio.c b/arch/s390/pci/pci_mmio.c index 37b1bbd1a27ccbbdfc01fe50ff4f13585ec1b5dc..1ec8076209cab37018dfcd7cd5972121376bcc97 100644 --- a/arch/s390/pci/pci_mmio.c +++ b/arch/s390/pci/pci_mmio.c @@ -64,7 +64,7 @@ static inline int __pcistg_mio_inuser( asm volatile ( " sacf 256\n" "0: llgc %[tmp],0(%[src])\n" - " sllg %[val],%[val],8\n" + "4: sllg %[val],%[val],8\n" " aghi %[src],1\n" " ogr %[val],%[tmp]\n" " brctg %[cnt],0b\n" @@ -72,7 +72,7 @@ static inline int __pcistg_mio_inuser( "2: ipm %[cc]\n" " srl %[cc],28\n" "3: sacf 768\n" - EX_TABLE(0b, 3b) EX_TABLE(1b, 3b) EX_TABLE(2b, 3b) + EX_TABLE(0b, 3b) EX_TABLE(4b, 3b) EX_TABLE(1b, 3b) EX_TABLE(2b, 3b) : [src] "+a" (src), [cnt] "+d" (cnt), [val] "+d" (val), [tmp] "=d" (tmp), @@ -222,10 +222,10 @@ static inline int __pcilg_mio_inuser( "2: ahi %[shift],-8\n" " srlg %[tmp],%[val],0(%[shift])\n" "3: stc %[tmp],0(%[dst])\n" - " aghi %[dst],1\n" + "5: aghi %[dst],1\n" " brctg %[cnt],2b\n" "4: sacf 768\n" - EX_TABLE(0b, 4b) EX_TABLE(1b, 4b) EX_TABLE(3b, 4b) + EX_TABLE(0b, 4b) EX_TABLE(1b, 4b) EX_TABLE(3b, 4b) EX_TABLE(5b, 4b) : [cc] "+d" (cc), [val] "=d" (val), [len] "+d" (len), [dst] "+a" (dst), [cnt] "+d" (cnt), [tmp] "=d" (tmp), diff --git a/arch/sh/include/asm/sections.h b/arch/sh/include/asm/sections.h index 8edb824049b9eeb4f7e8e6af14e8eeb4b45718a9..0cb0ca149ac34a62e4d5e8191a2597d6029dd5ec 100644 --- a/arch/sh/include/asm/sections.h +++ b/arch/sh/include/asm/sections.h @@ -4,7 +4,7 @@ #include -extern long __machvec_start, __machvec_end; +extern char __machvec_start[], __machvec_end[]; extern char __uncached_start, __uncached_end; extern char __start_eh_frame[], __stop_eh_frame[]; diff --git a/arch/sh/include/asm/thread_info.h b/arch/sh/include/asm/thread_info.h index 243ea5150aa00bdbdddbe6a7ffe6b869d1074565..598d0184ffeae3c0e713075d6096926d9e001fc0 100644 --- a/arch/sh/include/asm/thread_info.h +++ b/arch/sh/include/asm/thread_info.h @@ -105,6 +105,7 @@ extern void init_thread_xstate(void); #define TIF_SYSCALL_TRACE 0 /* syscall trace active */ #define TIF_SIGPENDING 1 /* signal pending */ #define TIF_NEED_RESCHED 2 /* rescheduling necessary */ +#define TIF_NOTIFY_SIGNAL 3 /* signal notifications exist */ #define TIF_SINGLESTEP 4 /* singlestepping active */ #define TIF_SYSCALL_AUDIT 5 /* syscall auditing active */ #define TIF_SECCOMP 6 /* secure computing */ @@ -116,6 +117,7 @@ extern void init_thread_xstate(void); #define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE) #define _TIF_SIGPENDING (1 << TIF_SIGPENDING) #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) +#define _TIF_NOTIFY_SIGNAL (1 << TIF_NOTIFY_SIGNAL) #define _TIF_SINGLESTEP (1 << TIF_SINGLESTEP) #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) #define _TIF_SECCOMP (1 << TIF_SECCOMP) @@ -132,7 +134,7 @@ extern void init_thread_xstate(void); #define _TIF_ALLWORK_MASK (_TIF_SYSCALL_TRACE | _TIF_SIGPENDING | \ _TIF_NEED_RESCHED | _TIF_SYSCALL_AUDIT | \ _TIF_SINGLESTEP | _TIF_NOTIFY_RESUME | \ - _TIF_SYSCALL_TRACEPOINT) + _TIF_SYSCALL_TRACEPOINT | _TIF_NOTIFY_SIGNAL) /* work to do on interrupt/exception return */ #define _TIF_WORK_MASK (_TIF_ALLWORK_MASK & ~(_TIF_SYSCALL_TRACE | \ diff --git a/arch/sh/kernel/machvec.c b/arch/sh/kernel/machvec.c index d606679a211e1bdb4095faf46523d0c562155cef..57efaf5b82ae07e4f744aaeded508143dd248ccf 100644 --- a/arch/sh/kernel/machvec.c +++ b/arch/sh/kernel/machvec.c @@ -20,8 +20,8 @@ #define MV_NAME_SIZE 32 #define for_each_mv(mv) \ - for ((mv) = (struct sh_machine_vector *)&__machvec_start; \ - (mv) && (unsigned long)(mv) < (unsigned long)&__machvec_end; \ + for ((mv) = (struct sh_machine_vector *)__machvec_start; \ + (mv) && (unsigned long)(mv) < (unsigned long)__machvec_end; \ (mv)++) static struct sh_machine_vector * __init get_mv_byname(const char *name) @@ -87,8 +87,8 @@ void __init sh_mv_setup(void) if (!machvec_selected) { unsigned long machvec_size; - machvec_size = ((unsigned long)&__machvec_end - - (unsigned long)&__machvec_start); + machvec_size = ((unsigned long)__machvec_end - + (unsigned long)__machvec_start); /* * Sanity check for machvec section alignment. Ensure @@ -102,7 +102,7 @@ void __init sh_mv_setup(void) * vector (usually the only one) from .machvec.init. */ if (machvec_size >= sizeof(struct sh_machine_vector)) - sh_mv = *(struct sh_machine_vector *)&__machvec_start; + sh_mv = *(struct sh_machine_vector *)__machvec_start; } pr_notice("Booting machvec: %s\n", get_system_type()); diff --git a/arch/sh/kernel/process_32.c b/arch/sh/kernel/process_32.c index 80a5d1c66a5175ffa4af49fe8ddd086d41eac978..1aa508eb0823ae3d0ffd70437d22227a585b21b9 100644 --- a/arch/sh/kernel/process_32.c +++ b/arch/sh/kernel/process_32.c @@ -114,7 +114,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long arg, childregs = task_pt_regs(p); p->thread.sp = (unsigned long) childregs; - if (unlikely(p->flags & PF_KTHREAD)) { + if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { memset(childregs, 0, sizeof(struct pt_regs)); p->thread.pc = (unsigned long) ret_from_kernel_thread; childregs->regs[4] = arg; diff --git a/arch/sh/kernel/signal_32.c b/arch/sh/kernel/signal_32.c index 1add47fd31f62d0e8e0eb3030e1d506415092fde..dd3092911efad74200882e1192aa89fd9fe97bdd 100644 --- a/arch/sh/kernel/signal_32.c +++ b/arch/sh/kernel/signal_32.c @@ -499,7 +499,7 @@ asmlinkage void do_notify_resume(struct pt_regs *regs, unsigned int save_r0, unsigned long thread_info_flags) { /* deal with pending signal delivery */ - if (thread_info_flags & _TIF_SIGPENDING) + if (thread_info_flags & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL)) do_signal(regs, save_r0); if (thread_info_flags & _TIF_NOTIFY_RESUME) diff --git a/arch/sparc/include/asm/thread_info_32.h b/arch/sparc/include/asm/thread_info_32.h index 548b366165dd19f7df59d5a76ca5104979608116..45b4955b253f25f7eec048aa1808b5cdec0b2ebf 100644 --- a/arch/sparc/include/asm/thread_info_32.h +++ b/arch/sparc/include/asm/thread_info_32.h @@ -104,6 +104,7 @@ register struct thread_info *current_thread_info_reg asm("g6"); #define TIF_SIGPENDING 2 /* signal pending */ #define TIF_NEED_RESCHED 3 /* rescheduling necessary */ #define TIF_RESTORE_SIGMASK 4 /* restore signal mask in do_signal() */ +#define TIF_NOTIFY_SIGNAL 5 /* signal notifications exist */ #define TIF_USEDFPU 8 /* FPU was used by this task * this quantum (SMP) */ #define TIF_POLLING_NRFLAG 9 /* true if poll_idle() is polling @@ -115,11 +116,12 @@ register struct thread_info *current_thread_info_reg asm("g6"); #define _TIF_NOTIFY_RESUME (1<ksp = (unsigned long) new_stack; p->thread.kregs = childregs; - if (unlikely(p->flags & PF_KTHREAD)) { + if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { extern int nwindows; unsigned long psr; memset(new_stack, 0, STACKFRAME_SZ + TRACEREG_SZ); diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c index 6f8c7822fc065d394c0e573aa5eae10851a34542..7afd0a859a78c8aa0389de0e6409df7defa7adc7 100644 --- a/arch/sparc/kernel/process_64.c +++ b/arch/sparc/kernel/process_64.c @@ -597,7 +597,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long arg, sizeof(struct sparc_stackf)); t->fpsaved[0] = 0; - if (unlikely(p->flags & PF_KTHREAD)) { + if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { memset(child_trap_frame, 0, child_stack_sz); __thread_flag_byte_ptr(t)[TI_FLAG_BYTE_CWP] = (current_pt_regs()->tstate + 1) & TSTATE_CWP; diff --git a/arch/sparc/kernel/signal_32.c b/arch/sparc/kernel/signal_32.c index 1da36dd34990b59b1d26ff18c01bbb046924802d..4d478510550c3b61eaf5a4ed288736c22f4af0d1 100644 --- a/arch/sparc/kernel/signal_32.c +++ b/arch/sparc/kernel/signal_32.c @@ -521,7 +521,7 @@ static void do_signal(struct pt_regs *regs, unsigned long orig_i0) void do_notify_resume(struct pt_regs *regs, unsigned long orig_i0, unsigned long thread_info_flags) { - if (thread_info_flags & _TIF_SIGPENDING) + if (thread_info_flags & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL)) do_signal(regs, orig_i0); if (thread_info_flags & _TIF_NOTIFY_RESUME) tracehook_notify_resume(regs); diff --git a/arch/sparc/kernel/signal_64.c b/arch/sparc/kernel/signal_64.c index f7ef7edcd5c1a53338b1e48275d197a82d9fc9c4..a0eec62c825df026ff0505201616257d3228a48c 100644 --- a/arch/sparc/kernel/signal_64.c +++ b/arch/sparc/kernel/signal_64.c @@ -549,7 +549,7 @@ void do_notify_resume(struct pt_regs *regs, unsigned long orig_i0, unsigned long user_exit(); if (thread_info_flags & _TIF_UPROBE) uprobe_notify_resume(regs); - if (thread_info_flags & _TIF_SIGPENDING) + if (thread_info_flags & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL)) do_signal(regs, orig_i0); if (thread_info_flags & _TIF_NOTIFY_RESUME) tracehook_notify_resume(regs); diff --git a/arch/um/include/asm/thread_info.h b/arch/um/include/asm/thread_info.h index 66ab6a07330b2de580a97d52d70082bce12328c9..e610e932cfe1e3fa4444b1bff8cf975ebdd7a300 100644 --- a/arch/um/include/asm/thread_info.h +++ b/arch/um/include/asm/thread_info.h @@ -57,6 +57,7 @@ static inline struct thread_info *current_thread_info(void) #define TIF_SYSCALL_TRACE 0 /* syscall trace active */ #define TIF_SIGPENDING 1 /* signal pending */ #define TIF_NEED_RESCHED 2 /* rescheduling necessary */ +#define TIF_NOTIFY_SIGNAL 3 /* signal notifications exist */ #define TIF_RESTART_BLOCK 4 #define TIF_MEMDIE 5 /* is terminating due to OOM killer */ #define TIF_SYSCALL_AUDIT 6 @@ -68,6 +69,7 @@ static inline struct thread_info *current_thread_info(void) #define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE) #define _TIF_SIGPENDING (1 << TIF_SIGPENDING) #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) +#define _TIF_NOTIFY_SIGNAL (1 << TIF_NOTIFY_SIGNAL) #define _TIF_MEMDIE (1 << TIF_MEMDIE) #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) #define _TIF_SECCOMP (1 << TIF_SECCOMP) diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c index 8eb8b736abc1862aa3120c004acbf9e610a11942..e6c9b11b20334169b0408dc0d77938dfccc8e53e 100644 --- a/arch/um/kernel/process.c +++ b/arch/um/kernel/process.c @@ -99,7 +99,8 @@ void interrupt_end(void) if (need_resched()) schedule(); - if (test_thread_flag(TIF_SIGPENDING)) + if (test_thread_flag(TIF_SIGPENDING) || + test_thread_flag(TIF_NOTIFY_SIGNAL)) do_signal(regs); if (test_thread_flag(TIF_NOTIFY_RESUME)) tracehook_notify_resume(regs); @@ -156,7 +157,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long arg, struct task_struct * p, unsigned long tls) { void (*handler)(void); - int kthread = current->flags & PF_KTHREAD; + int kthread = current->flags & (PF_KTHREAD | PF_IO_WORKER); int ret = 0; p->thread = (struct thread_struct) INIT_THREAD; diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c index 52e2e2a3e4aefae46b887ecbf374d23d9e472fd9..00c6dce14bd2b33d06480ef00f7cba7652ed5ec4 100644 --- a/arch/um/kernel/um_arch.c +++ b/arch/um/kernel/um_arch.c @@ -77,7 +77,7 @@ static int show_cpuinfo(struct seq_file *m, void *v) static void *c_start(struct seq_file *m, loff_t *pos) { - return *pos < NR_CPUS ? cpu_data + *pos : NULL; + return *pos < nr_cpu_ids ? cpu_data + *pos : NULL; } static void *c_next(struct seq_file *m, void *v, loff_t *pos) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 22aa1b0f8b61371f7eba4485ad8d2f140cb61c64..c16b6ed49f60191ee4b1f6ad62f3c2c09ca242ca 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1953,7 +1953,6 @@ config EFI config EFI_STUB bool "EFI stub support" depends on EFI && !X86_USE_3DNOW - depends on $(cc-option,-mabi=ms) || X86_32 select RELOCATABLE help This kernel feature allows a bzImage to be loaded directly diff --git a/arch/x86/configs/gki_defconfig b/arch/x86/configs/gki_defconfig index 2a72947a2edeac03b91460a6ab1c62c90bec2203..1801f6faee2d9a22c1c468251c67ff74bc71dfec 100644 --- a/arch/x86/configs/gki_defconfig +++ b/arch/x86/configs/gki_defconfig @@ -594,7 +594,6 @@ CONFIG_HARDENED_USERCOPY=y CONFIG_STATIC_USERMODEHELPER=y CONFIG_STATIC_USERMODEHELPER_PATH="" CONFIG_SECURITY_SELINUX=y -CONFIG_INIT_STACK_ALL_ZERO=y CONFIG_INIT_ON_ALLOC_DEFAULT_ON=y CONFIG_CRYPTO_CHACHA20POLY1305=y CONFIG_CRYPTO_ADIANTUM=y diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index f6eadf9320a1a360b13256ca5815239ae0eeae66..990d5543e3bf22ccd856d5605c2b6516b06a55d5 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -4412,6 +4412,7 @@ static const struct x86_cpu_desc isolation_ucodes[] = { INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X, 5, 0x00000000), INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X, 6, 0x00000000), INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X, 7, 0x00000000), + INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X, 11, 0x00000000), INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_L, 3, 0x0000007c), INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE, 3, 0x0000007c), INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE, 9, 0x0000004e), diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 945d470f62d0fcc09e4fd525fcf9f067e2bb745b..48f30ffef1f4b8ec444d6b373576469f8e056ce6 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -855,8 +855,13 @@ struct event_constraint intel_icl_pebs_event_constraints[] = { INTEL_FLAGS_UEVENT_CONSTRAINT(0x0400, 0x800000000ULL), /* SLOTS */ INTEL_PLD_CONSTRAINT(0x1cd, 0xff), /* MEM_TRANS_RETIRED.LOAD_LATENCY */ - INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x1d0, 0xf), /* MEM_INST_RETIRED.LOAD */ - INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x2d0, 0xf), /* MEM_INST_RETIRED.STORE */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x12d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_STORES */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x21d0, 0xf), /* MEM_INST_RETIRED.LOCK_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x41d0, 0xf), /* MEM_INST_RETIRED.SPLIT_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x42d0, 0xf), /* MEM_INST_RETIRED.SPLIT_STORES */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x81d0, 0xf), /* MEM_INST_RETIRED.ALL_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x82d0, 0xf), /* MEM_INST_RETIRED.ALL_STORES */ INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD_RANGE(0xd1, 0xd4, 0xf), /* MEM_LOAD_*_RETIRED.* */ diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index 42173a7be3bb42d2ce1490c3e3dcc7f24f4555ac..4b6c39c5facba17f7a6de72d1dc07f39a72a8828 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -1847,7 +1847,7 @@ void __init intel_pmu_arch_lbr_init(void) return; clear_arch_lbr: - clear_cpu_cap(&boot_cpu_data, X86_FEATURE_ARCH_LBR); + setup_clear_cpu_cap(X86_FEATURE_ARCH_LBR); } /** diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c index cc3b79c06685303983984ef191973f12ebe7ca90..d87421acddc397409b0550791ed22f312b797c38 100644 --- a/arch/x86/events/intel/pt.c +++ b/arch/x86/events/intel/pt.c @@ -13,6 +13,8 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include +#include +#include #include #include @@ -1245,6 +1247,15 @@ static int pt_buffer_try_single(struct pt_buffer *buf, int nr_pages) if (1 << order != nr_pages) goto out; + /* + * Some processors cannot always support single range for more than + * 4KB - refer errata TGL052, ADL037 and RPL017. Future processors might + * also be affected, so for now rather than trying to keep track of + * which ones, just disable it for all. + */ + if (nr_pages > 1) + goto out; + buf->single = true; buf->nr_pages = nr_pages; ret = 0; @@ -1348,10 +1359,36 @@ static void pt_addr_filters_fini(struct perf_event *event) event->hw.addr_filters = NULL; } -static inline bool valid_kernel_ip(unsigned long ip) +#ifdef CONFIG_X86_64 +static u64 canonical_address(u64 vaddr, u8 vaddr_bits) +{ + return ((s64)vaddr << (64 - vaddr_bits)) >> (64 - vaddr_bits); +} + +static u64 is_canonical_address(u64 vaddr, u8 vaddr_bits) +{ + return canonical_address(vaddr, vaddr_bits) == vaddr; +} + +/* Clamp to a canonical address greater-than-or-equal-to the address given */ +static u64 clamp_to_ge_canonical_addr(u64 vaddr, u8 vaddr_bits) +{ + return is_canonical_address(vaddr, vaddr_bits) ? + vaddr : + -BIT_ULL(vaddr_bits - 1); +} + +/* Clamp to a canonical address less-than-or-equal-to the address given */ +static u64 clamp_to_le_canonical_addr(u64 vaddr, u8 vaddr_bits) { - return virt_addr_valid(ip) && kernel_ip(ip); + return is_canonical_address(vaddr, vaddr_bits) ? + vaddr : + BIT_ULL(vaddr_bits - 1) - 1; } +#else +#define clamp_to_ge_canonical_addr(x, y) (x) +#define clamp_to_le_canonical_addr(x, y) (x) +#endif static int pt_event_addr_filters_validate(struct list_head *filters) { @@ -1367,14 +1404,6 @@ static int pt_event_addr_filters_validate(struct list_head *filters) filter->action == PERF_ADDR_FILTER_ACTION_START) return -EOPNOTSUPP; - if (!filter->path.dentry) { - if (!valid_kernel_ip(filter->offset)) - return -EINVAL; - - if (!valid_kernel_ip(filter->offset + filter->size)) - return -EINVAL; - } - if (++range > intel_pt_validate_hw_cap(PT_CAP_num_address_ranges)) return -EOPNOTSUPP; } @@ -1398,9 +1427,26 @@ static void pt_event_addr_filters_sync(struct perf_event *event) if (filter->path.dentry && !fr[range].start) { msr_a = msr_b = 0; } else { - /* apply the offset */ - msr_a = fr[range].start; - msr_b = msr_a + fr[range].size - 1; + unsigned long n = fr[range].size - 1; + unsigned long a = fr[range].start; + unsigned long b; + + if (a > ULONG_MAX - n) + b = ULONG_MAX; + else + b = a + n; + /* + * Apply the offset. 64-bit addresses written to the + * MSRs must be canonical, but the range can encompass + * non-canonical addresses. Since software cannot + * execute at non-canonical addresses, adjusting to + * canonical addresses does not affect the result of the + * address filter. + */ + msr_a = clamp_to_ge_canonical_addr(a, boot_cpu_data.x86_virt_bits); + msr_b = clamp_to_le_canonical_addr(b, boot_cpu_data.x86_virt_bits); + if (msr_b < msr_a) + msr_a = msr_b = 0; } filters->filter[range].msr_a = msr_a; diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h index 0ed20e8bba9e5bfba8f0490f43d5b08fd9a57948..ae7192b7513616a5833d5aecd4cbf8a1938ac622 100644 --- a/arch/x86/include/asm/hyperv-tlfs.h +++ b/arch/x86/include/asm/hyperv-tlfs.h @@ -474,7 +474,7 @@ struct hv_enlightened_vmcs { u64 guest_rip; u32 hv_clean_fields; - u32 hv_padding_32; + u32 padding32_1; u32 hv_synthetic_controls; struct { u32 nested_flush_hypercall:1; @@ -482,7 +482,7 @@ struct hv_enlightened_vmcs { u32 reserved:30; } __packed hv_enlightenments_control; u32 hv_vp_id; - + u32 padding32_2; u64 hv_vm_id; u64 partition_assist_page; u64 padding64_4[4]; diff --git a/arch/x86/include/asm/iommu.h b/arch/x86/include/asm/iommu.h index bf1ed2ddc74bd605408eaea6ffc9ab27b765bdfd..7a983119bc4032bea5894edaeb11ff08c3ccda07 100644 --- a/arch/x86/include/asm/iommu.h +++ b/arch/x86/include/asm/iommu.h @@ -17,8 +17,10 @@ arch_rmrr_sanity_check(struct acpi_dmar_reserved_memory *rmrr) { u64 start = rmrr->base_address; u64 end = rmrr->end_address + 1; + int entry_type; - if (e820__mapped_all(start, end, E820_TYPE_RESERVED)) + entry_type = e820__get_entry_type(start, end); + if (entry_type == E820_TYPE_RESERVED || entry_type == E820_TYPE_NVS) return 0; pr_err(FW_BUG "No firmware reserved region can cover this RMRR [%#018Lx-%#018Lx], contact BIOS vendor for fixes\n", diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h index 91a06cef50c1b85bd3628b93fe13ef54db06ff73..f73327397b898a3b0ec7cb801bd16070324b6894 100644 --- a/arch/x86/include/asm/microcode.h +++ b/arch/x86/include/asm/microcode.h @@ -9,6 +9,7 @@ struct ucode_patch { struct list_head plist; void *data; /* Intel uses only this one */ + unsigned int size; u32 patch_id; u16 equiv_cpu; }; diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 144dc164b7596a5c13e22f21b58665116ceb54eb..5a8ee3b83af2a8c375374e55cd0f456560a7d9f3 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -489,6 +489,11 @@ #define MSR_AMD64_CPUID_FN_1 0xc0011004 #define MSR_AMD64_LS_CFG 0xc0011020 #define MSR_AMD64_DC_CFG 0xc0011022 + +#define MSR_AMD64_DE_CFG 0xc0011029 +#define MSR_AMD64_DE_CFG_LFENCE_SERIALIZE_BIT 1 +#define MSR_AMD64_DE_CFG_LFENCE_SERIALIZE BIT_ULL(MSR_AMD64_DE_CFG_LFENCE_SERIALIZE_BIT) + #define MSR_AMD64_BU_CFG2 0xc001102a #define MSR_AMD64_IBSFETCHCTL 0xc0011030 #define MSR_AMD64_IBSFETCHLINAD 0xc0011031 @@ -565,9 +570,6 @@ #define FAM10H_MMIO_CONF_BASE_MASK 0xfffffffULL #define FAM10H_MMIO_CONF_BASE_SHIFT 20 #define MSR_FAM10H_NODE_ID 0xc001100c -#define MSR_F10H_DECFG 0xc0011029 -#define MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT 1 -#define MSR_F10H_DECFG_LFENCE_SERIALIZE BIT_ULL(MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT) /* K8 MSRs */ #define MSR_K8_TOP_MEM1 0xc001001a diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index e701f29b48817c022fdf6067cd59f3e51a0ecec7..012c8ee93b67f827ee34c18e30a17a43bb09cc36 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -93,6 +93,7 @@ struct thread_info { #define TIF_NOTSC 16 /* TSC is not accessible in userland */ #define TIF_IA32 17 /* IA32 compatibility process */ #define TIF_SLD 18 /* Restore split lock detection on context switch */ +#define TIF_NOTIFY_SIGNAL 19 /* signal notifications exist */ #define TIF_MEMDIE 20 /* is terminating due to OOM killer */ #define TIF_POLLING_NRFLAG 21 /* idle is polling for TIF_NEED_RESCHED */ #define TIF_IO_BITMAP 22 /* uses I/O bitmap */ @@ -121,6 +122,7 @@ struct thread_info { #define _TIF_NOCPUID (1 << TIF_NOCPUID) #define _TIF_NOTSC (1 << TIF_NOTSC) #define _TIF_IA32 (1 << TIF_IA32) +#define _TIF_NOTIFY_SIGNAL (1 << TIF_NOTIFY_SIGNAL) #define _TIF_SLD (1 << TIF_SLD) #define _TIF_POLLING_NRFLAG (1 << TIF_POLLING_NRFLAG) #define _TIF_IO_BITMAP (1 << TIF_IO_BITMAP) diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 8b9e3277a6ceb1a21d5ab506bf04d34e5ef520c8..ec3fa4dc9031847a0d10b212a91372e9cb268de8 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -822,8 +822,6 @@ static void init_amd_gh(struct cpuinfo_x86 *c) set_cpu_bug(c, X86_BUG_AMD_TLB_MMATCH); } -#define MSR_AMD64_DE_CFG 0xC0011029 - static void init_amd_ln(struct cpuinfo_x86 *c) { /* @@ -1018,8 +1016,8 @@ static void init_amd(struct cpuinfo_x86 *c) * msr_set_bit() uses the safe accessors, too, even if the MSR * is not present. */ - msr_set_bit(MSR_F10H_DECFG, - MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT); + msr_set_bit(MSR_AMD64_DE_CFG, + MSR_AMD64_DE_CFG_LFENCE_SERIALIZE_BIT); /* A serializing LFENCE stops RDTSC speculation */ set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC); diff --git a/arch/x86/kernel/cpu/feat_ctl.c b/arch/x86/kernel/cpu/feat_ctl.c index 29a3bedabd060f9668b41aacf6609cdecb166a52..d7541851288e36984b6cd5836224e9645aa5bd1d 100644 --- a/arch/x86/kernel/cpu/feat_ctl.c +++ b/arch/x86/kernel/cpu/feat_ctl.c @@ -1,11 +1,11 @@ // SPDX-License-Identifier: GPL-2.0 #include +#include #include #include #include #include -#include "cpu.h" #undef pr_fmt #define pr_fmt(fmt) "x86/cpu: " fmt diff --git a/arch/x86/kernel/cpu/hygon.c b/arch/x86/kernel/cpu/hygon.c index 774ca6bfda9f4c463d4368f0ba8063cab05c4193..205fa420ee7ca582ad50a7b9ae8184c65c8f1fbe 100644 --- a/arch/x86/kernel/cpu/hygon.c +++ b/arch/x86/kernel/cpu/hygon.c @@ -342,8 +342,8 @@ static void init_hygon(struct cpuinfo_x86 *c) * msr_set_bit() uses the safe accessors, too, even if the MSR * is not present. */ - msr_set_bit(MSR_F10H_DECFG, - MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT); + msr_set_bit(MSR_AMD64_DE_CFG, + MSR_AMD64_DE_CFG_LFENCE_SERIALIZE_BIT); /* A serializing LFENCE stops RDTSC speculation */ set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC); diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index 3f6b137ef4e6e564bff9fe4e8fd5ad2913d5de2a..234a96f25248dbb32dd3c68f133500dfd0d003c6 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -441,7 +441,13 @@ apply_microcode_early_amd(u32 cpuid_1_eax, void *ucode, size_t size, bool save_p return ret; native_rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy); - if (rev >= mc->hdr.patch_id) + + /* + * Allow application of the same revision to pick up SMT-specific + * changes even if the revision of the other SMT thread is already + * up-to-date. + */ + if (rev > mc->hdr.patch_id) return ret; if (!__apply_microcode_amd(mc)) { @@ -523,8 +529,12 @@ void load_ucode_amd_ap(unsigned int cpuid_1_eax) native_rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy); - /* Check whether we have saved a new patch already: */ - if (*new_rev && rev < mc->hdr.patch_id) { + /* + * Check whether a new patch has been saved already. Also, allow application of + * the same revision in order to pick up SMT-thread-specific configuration even + * if the sibling SMT thread already has an up-to-date revision. + */ + if (*new_rev && rev <= mc->hdr.patch_id) { if (!__apply_microcode_amd(mc)) { *new_rev = mc->hdr.patch_id; return; @@ -783,6 +793,7 @@ static int verify_and_add_patch(u8 family, u8 *fw, unsigned int leftover, kfree(patch); return -EINVAL; } + patch->size = *patch_size; mc_hdr = (struct microcode_header_amd *)(fw + SECTION_HDR_SIZE); proc_id = mc_hdr->processor_rev_id; @@ -864,7 +875,7 @@ load_microcode_amd(bool save, u8 family, const u8 *data, size_t size) return ret; memset(amd_ucode_patch, 0, PATCH_MAX_SIZE); - memcpy(amd_ucode_patch, p->data, min_t(u32, ksize(p->data), PATCH_MAX_SIZE)); + memcpy(amd_ucode_patch, p->data, min_t(u32, p->size, PATCH_MAX_SIZE)); return ret; } diff --git a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c index 0daf2f1cf7a867fe773aaf2e54cf83d672c492f9..465dce141bfc830abe0d7430abb2123b425f4f6f 100644 --- a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c +++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c @@ -416,6 +416,7 @@ static int pseudo_lock_fn(void *_rdtgrp) struct pseudo_lock_region *plr = rdtgrp->plr; u32 rmid_p, closid_p; unsigned long i; + u64 saved_msr; #ifdef CONFIG_KASAN /* * The registers used for local register variables are also used @@ -459,6 +460,7 @@ static int pseudo_lock_fn(void *_rdtgrp) * the buffer and evict pseudo-locked memory read earlier from the * cache. */ + saved_msr = __rdmsr(MSR_MISC_FEATURE_CONTROL); __wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0); closid_p = this_cpu_read(pqr_state.cur_closid); rmid_p = this_cpu_read(pqr_state.cur_rmid); @@ -510,7 +512,7 @@ static int pseudo_lock_fn(void *_rdtgrp) __wrmsr(IA32_PQR_ASSOC, rmid_p, closid_p); /* Re-enable the hardware prefetcher(s) */ - wrmsr(MSR_MISC_FEATURE_CONTROL, 0x0, 0x0); + wrmsrl(MSR_MISC_FEATURE_CONTROL, saved_msr); local_irq_enable(); plr->thread_done = 1; @@ -867,6 +869,7 @@ bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_domain *d) static int measure_cycles_lat_fn(void *_plr) { struct pseudo_lock_region *plr = _plr; + u32 saved_low, saved_high; unsigned long i; u64 start, end; void *mem_r; @@ -875,6 +878,7 @@ static int measure_cycles_lat_fn(void *_plr) /* * Disable hardware prefetchers. */ + rdmsr(MSR_MISC_FEATURE_CONTROL, saved_low, saved_high); wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0); mem_r = READ_ONCE(plr->kmem); /* @@ -891,7 +895,7 @@ static int measure_cycles_lat_fn(void *_plr) end = rdtsc_ordered(); trace_pseudo_lock_mem_latency((u32)(end - start)); } - wrmsr(MSR_MISC_FEATURE_CONTROL, 0x0, 0x0); + wrmsr(MSR_MISC_FEATURE_CONTROL, saved_low, saved_high); local_irq_enable(); plr->thread_done = 1; wake_up_interruptible(&plr->lock_thread_wq); @@ -936,6 +940,7 @@ static int measure_residency_fn(struct perf_event_attr *miss_attr, u64 hits_before = 0, hits_after = 0, miss_before = 0, miss_after = 0; struct perf_event *miss_event, *hit_event; int hit_pmcnum, miss_pmcnum; + u32 saved_low, saved_high; unsigned int line_size; unsigned int size; unsigned long i; @@ -969,6 +974,7 @@ static int measure_residency_fn(struct perf_event_attr *miss_attr, /* * Disable hardware prefetchers. */ + rdmsr(MSR_MISC_FEATURE_CONTROL, saved_low, saved_high); wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0); /* Initialize rest of local variables */ @@ -1027,7 +1033,7 @@ static int measure_residency_fn(struct perf_event_attr *miss_attr, */ rmb(); /* Re-enable hardware prefetchers */ - wrmsr(MSR_MISC_FEATURE_CONTROL, 0x0, 0x0); + wrmsr(MSR_MISC_FEATURE_CONTROL, saved_low, saved_high); local_irq_enable(); out_hit: perf_event_release_kernel(hit_event); diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c index 91288da29599516f1f5c068748afc7836ab2354e..37d48ab3d077cf0f073d285fa6a903d6117c77c6 100644 --- a/arch/x86/kernel/cpu/topology.c +++ b/arch/x86/kernel/cpu/topology.c @@ -96,6 +96,8 @@ int detect_extended_topology(struct cpuinfo_x86 *c) unsigned int ht_mask_width, core_plus_mask_width, die_plus_mask_width; unsigned int core_select_mask, core_level_siblings; unsigned int die_select_mask, die_level_siblings; + unsigned int pkg_mask_width; + bool die_level_present = false; int leaf; leaf = detect_extended_topology_leaf(c); @@ -110,10 +112,10 @@ int detect_extended_topology(struct cpuinfo_x86 *c) core_level_siblings = smp_num_siblings = LEVEL_MAX_SIBLINGS(ebx); core_plus_mask_width = ht_mask_width = BITS_SHIFT_NEXT_LEVEL(eax); die_level_siblings = LEVEL_MAX_SIBLINGS(ebx); - die_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax); + pkg_mask_width = die_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax); sub_index = 1; - do { + while (true) { cpuid_count(leaf, sub_index, &eax, &ebx, &ecx, &edx); /* @@ -126,23 +128,33 @@ int detect_extended_topology(struct cpuinfo_x86 *c) die_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax); } if (LEAFB_SUBTYPE(ecx) == DIE_TYPE) { + die_level_present = true; die_level_siblings = LEVEL_MAX_SIBLINGS(ebx); die_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax); } + if (LEAFB_SUBTYPE(ecx) != INVALID_TYPE) + pkg_mask_width = BITS_SHIFT_NEXT_LEVEL(eax); + else + break; + sub_index++; - } while (LEAFB_SUBTYPE(ecx) != INVALID_TYPE); + } - core_select_mask = (~(-1 << core_plus_mask_width)) >> ht_mask_width; + core_select_mask = (~(-1 << pkg_mask_width)) >> ht_mask_width; die_select_mask = (~(-1 << die_plus_mask_width)) >> core_plus_mask_width; c->cpu_core_id = apic->phys_pkg_id(c->initial_apicid, ht_mask_width) & core_select_mask; - c->cpu_die_id = apic->phys_pkg_id(c->initial_apicid, - core_plus_mask_width) & die_select_mask; + + if (die_level_present) { + c->cpu_die_id = apic->phys_pkg_id(c->initial_apicid, + core_plus_mask_width) & die_select_mask; + } + c->phys_proc_id = apic->phys_pkg_id(c->initial_apicid, - die_plus_mask_width); + pkg_mask_width); /* * Reinit the apicid, now that we have extended initial_apicid. */ diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 4505d845daba6eb31434954cb8832068c7fd4230..e12d7df5ec3a11f6e41d7d370914499cb2c831fd 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -178,6 +178,23 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long arg, task_user_gs(p) = get_user_gs(current_pt_regs()); #endif + if (unlikely(p->flags & PF_IO_WORKER)) { + /* + * An IO thread is a user space thread, but it doesn't + * return to ret_after_fork(). + * + * In order to indicate that to tools like gdb, + * we reset the stack and instruction pointers. + * + * It does the same kernel frame setup to return to a kernel + * function that a kernel thread does. + */ + childregs->sp = 0; + childregs->ip = 0; + kthread_frame_init(frame, sp, arg); + return 0; + } + /* Set a new TLS for the child thread? */ if (clone_flags & CLONE_SETTLS) ret = set_new_tls(p, tls); diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index b001ba811cabbe716c5d9ba46ca4e258acd0570a..9eff48171532049dcac77b440e643e49be8602ce 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -798,11 +798,11 @@ static inline unsigned long get_nr_restart_syscall(const struct pt_regs *regs) * want to handle. Thus you cannot kill init even with a SIGKILL even by * mistake. */ -void arch_do_signal(struct pt_regs *regs) +void arch_do_signal_or_restart(struct pt_regs *regs, bool has_signal) { struct ksignal ksig; - if (get_signal(&ksig)) { + if (has_signal && get_signal(&ksig)) { /* Whee! Actually deliver the signal. */ handle_signal(&ksig, regs); return; diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index cc071c4c65240b0192e3f323d7c6750d7557b2c0..d557a545f4bc5552dfb22ec7ed174c102c678f6e 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -697,7 +697,7 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task, /* Otherwise, skip ahead to the user-specified starting frame: */ while (!unwind_done(state) && (!on_stack(&state->stack_info, first_frame, sizeof(long)) || - state->sp < (unsigned long)first_frame)) + state->sp <= (unsigned long)first_frame)) unwind_next_frame(state); return; diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 6f44274aa949d84658d97b7fb0d1ebd05a474c75..06a776fdb90cfba85356d80dac668af7d89821d5 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -813,11 +813,13 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) entry->eax = min(entry->eax, 0x8000001f); break; case 0x80000001: + entry->ebx &= ~GENMASK(27, 16); cpuid_entry_override(entry, CPUID_8000_0001_EDX); cpuid_entry_override(entry, CPUID_8000_0001_ECX); break; case 0x80000006: - /* L2 cache and TLB: pass through host info. */ + /* Drop reserved bits, pass host L2 cache and TLB info. */ + entry->edx &= ~GENMASK(17, 16); break; case 0x80000007: /* Advanced power management */ /* invariant TSC is CPUID.80000007H:EDX[8] */ @@ -840,6 +842,7 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) g_phys_as = phys_as; entry->eax = g_phys_as | (virt_as << 8); + entry->ecx &= ~(GENMASK(31, 16) | GENMASK(11, 8)); entry->edx = 0; cpuid_entry_override(entry, CPUID_8000_0008_EBX); break; @@ -859,6 +862,9 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) entry->ecx = entry->edx = 0; break; case 0x8000001a: + entry->eax &= GENMASK(2, 0); + entry->ebx = entry->ecx = entry->edx = 0; + break; case 0x8000001e: break; /* Support memory encryption cpuid if host supports it */ diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 2aa41d682bb2c2427bc3a5d4ba8e2fa2c32f111d..63efccc8f4292792871678beba193a6622a68f5c 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -796,8 +796,7 @@ static int linearize(struct x86_emulate_ctxt *ctxt, ctxt->mode, linear); } -static inline int assign_eip(struct x86_emulate_ctxt *ctxt, ulong dst, - enum x86emul_mode mode) +static inline int assign_eip(struct x86_emulate_ctxt *ctxt, ulong dst) { ulong linear; int rc; @@ -807,41 +806,71 @@ static inline int assign_eip(struct x86_emulate_ctxt *ctxt, ulong dst, if (ctxt->op_bytes != sizeof(unsigned long)) addr.ea = dst & ((1UL << (ctxt->op_bytes << 3)) - 1); - rc = __linearize(ctxt, addr, &max_size, 1, false, true, mode, &linear); + rc = __linearize(ctxt, addr, &max_size, 1, false, true, ctxt->mode, &linear); if (rc == X86EMUL_CONTINUE) ctxt->_eip = addr.ea; return rc; } +static inline int emulator_recalc_and_set_mode(struct x86_emulate_ctxt *ctxt) +{ + u64 efer; + struct desc_struct cs; + u16 selector; + u32 base3; + + ctxt->ops->get_msr(ctxt, MSR_EFER, &efer); + + if (!(ctxt->ops->get_cr(ctxt, 0) & X86_CR0_PE)) { + /* Real mode. cpu must not have long mode active */ + if (efer & EFER_LMA) + return X86EMUL_UNHANDLEABLE; + ctxt->mode = X86EMUL_MODE_REAL; + return X86EMUL_CONTINUE; + } + + if (ctxt->eflags & X86_EFLAGS_VM) { + /* Protected/VM86 mode. cpu must not have long mode active */ + if (efer & EFER_LMA) + return X86EMUL_UNHANDLEABLE; + ctxt->mode = X86EMUL_MODE_VM86; + return X86EMUL_CONTINUE; + } + + if (!ctxt->ops->get_segment(ctxt, &selector, &cs, &base3, VCPU_SREG_CS)) + return X86EMUL_UNHANDLEABLE; + + if (efer & EFER_LMA) { + if (cs.l) { + /* Proper long mode */ + ctxt->mode = X86EMUL_MODE_PROT64; + } else if (cs.d) { + /* 32 bit compatibility mode*/ + ctxt->mode = X86EMUL_MODE_PROT32; + } else { + ctxt->mode = X86EMUL_MODE_PROT16; + } + } else { + /* Legacy 32 bit / 16 bit mode */ + ctxt->mode = cs.d ? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16; + } + + return X86EMUL_CONTINUE; +} + static inline int assign_eip_near(struct x86_emulate_ctxt *ctxt, ulong dst) { - return assign_eip(ctxt, dst, ctxt->mode); + return assign_eip(ctxt, dst); } -static int assign_eip_far(struct x86_emulate_ctxt *ctxt, ulong dst, - const struct desc_struct *cs_desc) +static int assign_eip_far(struct x86_emulate_ctxt *ctxt, ulong dst) { - enum x86emul_mode mode = ctxt->mode; - int rc; + int rc = emulator_recalc_and_set_mode(ctxt); -#ifdef CONFIG_X86_64 - if (ctxt->mode >= X86EMUL_MODE_PROT16) { - if (cs_desc->l) { - u64 efer = 0; + if (rc != X86EMUL_CONTINUE) + return rc; - ctxt->ops->get_msr(ctxt, MSR_EFER, &efer); - if (efer & EFER_LMA) - mode = X86EMUL_MODE_PROT64; - } else - mode = X86EMUL_MODE_PROT32; /* temporary value */ - } -#endif - if (mode == X86EMUL_MODE_PROT16 || mode == X86EMUL_MODE_PROT32) - mode = cs_desc->d ? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16; - rc = assign_eip(ctxt, dst, mode); - if (rc == X86EMUL_CONTINUE) - ctxt->mode = mode; - return rc; + return assign_eip(ctxt, dst); } static inline int jmp_rel(struct x86_emulate_ctxt *ctxt, int rel) @@ -2039,7 +2068,7 @@ static int em_pop_sreg(struct x86_emulate_ctxt *ctxt) if (rc != X86EMUL_CONTINUE) return rc; - if (ctxt->modrm_reg == VCPU_SREG_SS) + if (seg == VCPU_SREG_SS) ctxt->interruptibility = KVM_X86_SHADOW_INT_MOV_SS; if (ctxt->op_bytes > 2) rsp_increment(ctxt, ctxt->op_bytes - 2); @@ -2256,7 +2285,7 @@ static int em_jmp_far(struct x86_emulate_ctxt *ctxt) if (rc != X86EMUL_CONTINUE) return rc; - rc = assign_eip_far(ctxt, ctxt->src.val, &new_desc); + rc = assign_eip_far(ctxt, ctxt->src.val); /* Error handling is not implemented. */ if (rc != X86EMUL_CONTINUE) return X86EMUL_UNHANDLEABLE; @@ -2337,7 +2366,7 @@ static int em_ret_far(struct x86_emulate_ctxt *ctxt) &new_desc); if (rc != X86EMUL_CONTINUE) return rc; - rc = assign_eip_far(ctxt, eip, &new_desc); + rc = assign_eip_far(ctxt, eip); /* Error handling is not implemented. */ if (rc != X86EMUL_CONTINUE) return X86EMUL_UNHANDLEABLE; @@ -2957,6 +2986,7 @@ static int em_sysexit(struct x86_emulate_ctxt *ctxt) ops->set_segment(ctxt, ss_sel, &ss, 0, VCPU_SREG_SS); ctxt->_eip = rdx; + ctxt->mode = usermode; *reg_write(ctxt, VCPU_REGS_RSP) = rcx; return X86EMUL_CONTINUE; @@ -3553,7 +3583,7 @@ static int em_call_far(struct x86_emulate_ctxt *ctxt) if (rc != X86EMUL_CONTINUE) return rc; - rc = assign_eip_far(ctxt, ctxt->src.val, &new_desc); + rc = assign_eip_far(ctxt, ctxt->src.val); if (rc != X86EMUL_CONTINUE) goto fail; @@ -3695,11 +3725,25 @@ static int em_movbe(struct x86_emulate_ctxt *ctxt) static int em_cr_write(struct x86_emulate_ctxt *ctxt) { - if (ctxt->ops->set_cr(ctxt, ctxt->modrm_reg, ctxt->src.val)) + int cr_num = ctxt->modrm_reg; + int r; + + if (ctxt->ops->set_cr(ctxt, cr_num, ctxt->src.val)) return emulate_gp(ctxt, 0); /* Disable writeback. */ ctxt->dst.type = OP_NONE; + + if (cr_num == 0) { + /* + * CR0 write might have updated CR0.PE and/or CR0.PG + * which can affect the cpu's execution mode. + */ + r = emulator_recalc_and_set_mode(ctxt); + if (r != X86EMUL_CONTINUE) + return r; + } + return X86EMUL_CONTINUE; } diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index a0512a91760d2b8f43b8e72c006fa1af8aead290..c34ba034ca11111cb7830507d69bc8ce2c805338 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -305,12 +305,6 @@ int svm_set_efer(struct kvm_vcpu *vcpu, u64 efer) return 0; } -static int is_external_interrupt(u32 info) -{ - info &= SVM_EVTINJ_TYPE_MASK | SVM_EVTINJ_VALID; - return info == (SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_INTR); -} - static u32 svm_get_interrupt_shadow(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -1357,6 +1351,7 @@ static void svm_free_vcpu(struct kvm_vcpu *vcpu) */ svm_clear_current_vmcb(svm->vmcb); + svm_leave_nested(vcpu); svm_free_nested(svm); __free_page(pfn_to_page(__sme_clr(svm->vmcb_pa) >> PAGE_SHIFT)); @@ -2475,9 +2470,9 @@ static int svm_get_msr_feature(struct kvm_msr_entry *msr) msr->data = 0; switch (msr->index) { - case MSR_F10H_DECFG: - if (boot_cpu_has(X86_FEATURE_LFENCE_RDTSC)) - msr->data |= MSR_F10H_DECFG_LFENCE_SERIALIZE; + case MSR_AMD64_DE_CFG: + if (cpu_feature_enabled(X86_FEATURE_LFENCE_RDTSC)) + msr->data |= MSR_AMD64_DE_CFG_LFENCE_SERIALIZE; break; case MSR_IA32_PERF_CAPABILITIES: return 0; @@ -2584,7 +2579,7 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = 0x1E; } break; - case MSR_F10H_DECFG: + case MSR_AMD64_DE_CFG: msr_info->data = svm->msr_decfg; break; default: @@ -2764,7 +2759,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) case MSR_VM_IGNNE: vcpu_unimpl(vcpu, "unimplemented wrmsr: 0x%x data 0x%llx\n", ecx, data); break; - case MSR_F10H_DECFG: { + case MSR_AMD64_DE_CFG: { struct kvm_msr_entry msr_entry; msr_entry.index = msr->index; @@ -3115,15 +3110,6 @@ static int handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) return 0; } - if (is_external_interrupt(svm->vmcb->control.exit_int_info) && - exit_code != SVM_EXIT_EXCP_BASE + PF_VECTOR && - exit_code != SVM_EXIT_NPF && exit_code != SVM_EXIT_TASK_SWITCH && - exit_code != SVM_EXIT_INTR && exit_code != SVM_EXIT_NMI) - printk(KERN_ERR "%s: unexpected exit_int_info 0x%x " - "exit_code 0x%x\n", - __func__, svm->vmcb->control.exit_int_info, - exit_code); - if (exit_fastpath != EXIT_FASTPATH_NONE) return 1; diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index a2835d784f4be2ceb1186061d90ef70f7bfb80f1..3d4988ea8b572551b3178ffa4d7f9dfb60c73e50 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -304,25 +304,29 @@ TRACE_EVENT(kvm_inj_virq, * Tracepoint for kvm interrupt injection: */ TRACE_EVENT(kvm_inj_exception, - TP_PROTO(unsigned exception, bool has_error, unsigned error_code), - TP_ARGS(exception, has_error, error_code), + TP_PROTO(unsigned exception, bool has_error, unsigned error_code, + bool reinjected), + TP_ARGS(exception, has_error, error_code, reinjected), TP_STRUCT__entry( __field( u8, exception ) __field( u8, has_error ) __field( u32, error_code ) + __field( bool, reinjected ) ), TP_fast_assign( __entry->exception = exception; __entry->has_error = has_error; __entry->error_code = error_code; + __entry->reinjected = reinjected; ), - TP_printk("%s (0x%x)", + TP_printk("%s (0x%x)%s", __print_symbolic(__entry->exception, kvm_trace_sym_exc), /* FIXME: don't print error_code if not present */ - __entry->has_error ? __entry->error_code : 0) + __entry->has_error ? __entry->error_code : 0, + __entry->reinjected ? " [reinjected]" : "") ); /* diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 6c4277e99d586930df9d74d2a953a7eb6887fbac..498fed0dda98c80fb703726ab8e3214505fe713c 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -2232,7 +2232,8 @@ static void prepare_vmcs02_early_rare(struct vcpu_vmx *vmx, } } -static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) +static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct loaded_vmcs *vmcs01, + struct vmcs12 *vmcs12) { u32 exec_control, vmcs12_exec_ctrl; u64 guest_efer = nested_vmx_calc_efer(vmx, vmcs12); @@ -2243,7 +2244,7 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) /* * PIN CONTROLS */ - exec_control = vmx_pin_based_exec_ctrl(vmx); + exec_control = __pin_controls_get(vmcs01); exec_control |= (vmcs12->pin_based_vm_exec_control & ~PIN_BASED_VMX_PREEMPTION_TIMER); @@ -2258,7 +2259,7 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) /* * EXEC CONTROLS */ - exec_control = vmx_exec_control(vmx); /* L0's desires */ + exec_control = __exec_controls_get(vmcs01); /* L0's desires */ exec_control &= ~CPU_BASED_INTR_WINDOW_EXITING; exec_control &= ~CPU_BASED_NMI_WINDOW_EXITING; exec_control &= ~CPU_BASED_TPR_SHADOW; @@ -2295,17 +2296,20 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) * SECONDARY EXEC CONTROLS */ if (cpu_has_secondary_exec_ctrls()) { - exec_control = vmx->secondary_exec_control; + exec_control = __secondary_exec_controls_get(vmcs01); /* Take the following fields only from vmcs12 */ exec_control &= ~(SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | + SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | SECONDARY_EXEC_ENABLE_INVPCID | SECONDARY_EXEC_ENABLE_RDTSCP | SECONDARY_EXEC_XSAVES | SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE | SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY | SECONDARY_EXEC_APIC_REGISTER_VIRT | - SECONDARY_EXEC_ENABLE_VMFUNC); + SECONDARY_EXEC_ENABLE_VMFUNC | + SECONDARY_EXEC_DESC); + if (nested_cpu_has(vmcs12, CPU_BASED_ACTIVATE_SECONDARY_CONTROLS)) { vmcs12_exec_ctrl = vmcs12->secondary_vm_exec_control & @@ -2341,9 +2345,15 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) * are emulated by vmx_set_efer() in prepare_vmcs02(), but speculate * on the related bits (if supported by the CPU) in the hope that * we can avoid VMWrites during vmx_set_efer(). + * + * Similarly, take vmcs01's PERF_GLOBAL_CTRL in the hope that if KVM is + * loading PERF_GLOBAL_CTRL via the VMCS for L1, then KVM will want to + * do the same for L2. */ - exec_control = (vmcs12->vm_entry_controls | vmx_vmentry_ctrl()) & - ~VM_ENTRY_IA32E_MODE & ~VM_ENTRY_LOAD_IA32_EFER; + exec_control = __vm_entry_controls_get(vmcs01); + exec_control |= (vmcs12->vm_entry_controls & + ~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL); + exec_control &= ~(VM_ENTRY_IA32E_MODE | VM_ENTRY_LOAD_IA32_EFER); if (cpu_has_load_ia32_efer()) { if (guest_efer & EFER_LMA) exec_control |= VM_ENTRY_IA32E_MODE; @@ -2359,9 +2369,11 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) * we should use its exit controls. Note that VM_EXIT_LOAD_IA32_EFER * bits may be modified by vmx_set_efer() in prepare_vmcs02(). */ - exec_control = vmx_vmexit_ctrl(); + exec_control = __vm_exit_controls_get(vmcs01); if (cpu_has_load_ia32_efer() && guest_efer != host_efer) exec_control |= VM_EXIT_LOAD_IA32_EFER; + else + exec_control &= ~VM_EXIT_LOAD_IA32_EFER; vm_exit_controls_set(vmx, exec_control); /* @@ -3370,7 +3382,7 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, vmx_switch_vmcs(vcpu, &vmx->nested.vmcs02); - prepare_vmcs02_early(vmx, vmcs12); + prepare_vmcs02_early(vmx, &vmx->vmcs01, vmcs12); if (from_vmentry) { if (unlikely(!nested_get_vmcs12_pages(vcpu))) { @@ -3776,7 +3788,16 @@ static void nested_vmx_inject_exception_vmexit(struct kvm_vcpu *vcpu, u32 intr_info = nr | INTR_INFO_VALID_MASK; if (vcpu->arch.exception.has_error_code) { - vmcs12->vm_exit_intr_error_code = vcpu->arch.exception.error_code; + /* + * Intel CPUs do not generate error codes with bits 31:16 set, + * and more importantly VMX disallows setting bits 31:16 in the + * injected error code for VM-Entry. Drop the bits to mimic + * hardware and avoid inducing failure on nested VM-Entry if L1 + * chooses to inject the exception back to L2. AMD CPUs _do_ + * generate "full" 32-bit error codes, so KVM allows userspace + * to inject exception error codes with bits 31:16 set. + */ + vmcs12->vm_exit_intr_error_code = (u16)vcpu->arch.exception.error_code; intr_info |= INTR_INFO_DELIVER_CODE_MASK; } @@ -4183,14 +4204,6 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, nested_vmx_abort(vcpu, VMX_ABORT_SAVE_GUEST_MSR_FAIL); } - - /* - * Drop what we picked up for L2 via vmx_complete_interrupts. It is - * preserved above and would only end up incorrectly in L1. - */ - vcpu->arch.nmi_injected = false; - kvm_clear_exception_queue(vcpu); - kvm_clear_interrupt_queue(vcpu); } /* @@ -4530,6 +4543,17 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, WARN_ON_ONCE(nested_early_check); } + /* + * Drop events/exceptions that were queued for re-injection to L2 + * (picked up via vmx_complete_interrupts()), as well as exceptions + * that were pending for L2. Note, this must NOT be hoisted above + * prepare_vmcs12(), events/exceptions queued for re-injection need to + * be captured in vmcs12 (see vmcs12_save_pending_event()). + */ + vcpu->arch.nmi_injected = false; + kvm_clear_exception_queue(vcpu); + kvm_clear_interrupt_queue(vcpu); + vmx_switch_vmcs(vcpu, &vmx->vmcs01); /* Update any VMCS fields that might have changed while L2 ran */ diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index b33d0f283d4f84c0cb53b8dcea2f681bef9d4dee..af6742d11ca149790e92687872a7a5264e77acd7 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -1737,7 +1737,17 @@ static void vmx_queue_exception(struct kvm_vcpu *vcpu) kvm_deliver_exception_payload(vcpu); if (has_error_code) { - vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, error_code); + /* + * Despite the error code being architecturally defined as 32 + * bits, and the VMCS field being 32 bits, Intel CPUs and thus + * VMX don't actually supporting setting bits 31:16. Hardware + * will (should) never provide a bogus error code, but AMD CPUs + * do generate error codes with bits 31:16 set, and so KVM's + * ABI lets userspace shove in arbitrary 32-bit values. Drop + * the upper bits to avoid VM-Fail, losing information that + * does't really exist is preferable to killing the VM. + */ + vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, (u16)error_code); intr_info |= INTR_INFO_DELIVER_CODE_MASK; } diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 24903f05c204b7bcff0f6c52eb83656a0c03deb4..ed4b6da83aa87c1a75a95ab0ec2433d4befca86b 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -386,9 +386,13 @@ static inline void lname##_controls_set(struct vcpu_vmx *vmx, u32 val) \ vmx->loaded_vmcs->controls_shadow.lname = val; \ } \ } \ +static inline u32 __##lname##_controls_get(struct loaded_vmcs *vmcs) \ +{ \ + return vmcs->controls_shadow.lname; \ +} \ static inline u32 lname##_controls_get(struct vcpu_vmx *vmx) \ { \ - return vmx->loaded_vmcs->controls_shadow.lname; \ + return __##lname##_controls_get(vmx->loaded_vmcs); \ } \ static inline void lname##_controls_setbit(struct vcpu_vmx *vmx, u32 val) \ { \ diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index f3473418dcd5db3f7e07f7ef1aae06185636711a..23d7c563e012b358d661efb3e74415365718703b 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -459,6 +459,7 @@ static int exception_class(int vector) #define EXCPT_TRAP 1 #define EXCPT_ABORT 2 #define EXCPT_INTERRUPT 3 +#define EXCPT_DB 4 static int exception_type(int vector) { @@ -469,8 +470,14 @@ static int exception_type(int vector) mask = 1 << vector; - /* #DB is trap, as instruction watchpoints are handled elsewhere */ - if (mask & ((1 << DB_VECTOR) | (1 << BP_VECTOR) | (1 << OF_VECTOR))) + /* + * #DBs can be trap-like or fault-like, the caller must check other CPU + * state, e.g. DR6, to determine whether a #DB is a trap or fault. + */ + if (mask & (1 << DB_VECTOR)) + return EXCPT_DB; + + if (mask & ((1 << BP_VECTOR) | (1 << OF_VECTOR))) return EXCPT_TRAP; if (mask & ((1 << DF_VECTOR) | (1 << MC_VECTOR))) @@ -1355,7 +1362,7 @@ static const u32 msr_based_features_all[] = { MSR_IA32_VMX_EPT_VPID_CAP, MSR_IA32_VMX_VMFUNC, - MSR_F10H_DECFG, + MSR_AMD64_DE_CFG, MSR_IA32_UCODE_REV, MSR_IA32_ARCH_CAPABILITIES, MSR_IA32_PERF_CAPABILITIES, @@ -5353,6 +5360,11 @@ split_irqchip_unlock: r = 0; break; case KVM_CAP_X86_USER_SPACE_MSR: + r = -EINVAL; + if (cap->args[0] & ~(KVM_MSR_EXIT_REASON_INVAL | + KVM_MSR_EXIT_REASON_UNKNOWN | + KVM_MSR_EXIT_REASON_FILTER)) + break; kvm->arch.user_space_msr_mask = cap->args[0]; r = 0; break; @@ -5434,23 +5446,22 @@ err: return r; } -static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, void __user *argp) +static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, + struct kvm_msr_filter *filter) { - struct kvm_msr_filter __user *user_msr_filter = argp; struct kvm_x86_msr_filter *new_filter, *old_filter; - struct kvm_msr_filter filter; bool default_allow; bool empty = true; int r = 0; u32 i; - if (copy_from_user(&filter, user_msr_filter, sizeof(filter))) - return -EFAULT; + if (filter->flags & ~KVM_MSR_FILTER_DEFAULT_DENY) + return -EINVAL; - for (i = 0; i < ARRAY_SIZE(filter.ranges); i++) - empty &= !filter.ranges[i].nmsrs; + for (i = 0; i < ARRAY_SIZE(filter->ranges); i++) + empty &= !filter->ranges[i].nmsrs; - default_allow = !(filter.flags & KVM_MSR_FILTER_DEFAULT_DENY); + default_allow = !(filter->flags & KVM_MSR_FILTER_DEFAULT_DENY); if (empty && !default_allow) return -EINVAL; @@ -5458,8 +5469,8 @@ static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, void __user *argp) if (!new_filter) return -ENOMEM; - for (i = 0; i < ARRAY_SIZE(filter.ranges); i++) { - r = kvm_add_msr_filter(new_filter, &filter.ranges[i]); + for (i = 0; i < ARRAY_SIZE(filter->ranges); i++) { + r = kvm_add_msr_filter(new_filter, &filter->ranges[i]); if (r) { kvm_free_msr_filter(new_filter); return r; @@ -5482,6 +5493,62 @@ static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, void __user *argp) return 0; } +#ifdef CONFIG_KVM_COMPAT +/* for KVM_X86_SET_MSR_FILTER */ +struct kvm_msr_filter_range_compat { + __u32 flags; + __u32 nmsrs; + __u32 base; + __u32 bitmap; +}; + +struct kvm_msr_filter_compat { + __u32 flags; + struct kvm_msr_filter_range_compat ranges[KVM_MSR_FILTER_MAX_RANGES]; +}; + +#define KVM_X86_SET_MSR_FILTER_COMPAT _IOW(KVMIO, 0xc6, struct kvm_msr_filter_compat) + +long kvm_arch_vm_compat_ioctl(struct file *filp, unsigned int ioctl, + unsigned long arg) +{ + void __user *argp = (void __user *)arg; + struct kvm *kvm = filp->private_data; + long r = -ENOTTY; + + switch (ioctl) { + case KVM_X86_SET_MSR_FILTER_COMPAT: { + struct kvm_msr_filter __user *user_msr_filter = argp; + struct kvm_msr_filter_compat filter_compat; + struct kvm_msr_filter filter; + int i; + + if (copy_from_user(&filter_compat, user_msr_filter, + sizeof(filter_compat))) + return -EFAULT; + + filter.flags = filter_compat.flags; + for (i = 0; i < ARRAY_SIZE(filter.ranges); i++) { + struct kvm_msr_filter_range_compat *cr; + + cr = &filter_compat.ranges[i]; + filter.ranges[i] = (struct kvm_msr_filter_range) { + .flags = cr->flags, + .nmsrs = cr->nmsrs, + .base = cr->base, + .bitmap = (__u8 *)(ulong)cr->bitmap, + }; + } + + r = kvm_vm_ioctl_set_msr_filter(kvm, &filter); + break; + } + } + + return r; +} +#endif + long kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -5788,9 +5855,16 @@ set_pit2_out: case KVM_SET_PMU_EVENT_FILTER: r = kvm_vm_ioctl_set_pmu_event_filter(kvm, argp); break; - case KVM_X86_SET_MSR_FILTER: - r = kvm_vm_ioctl_set_msr_filter(kvm, argp); + case KVM_X86_SET_MSR_FILTER: { + struct kvm_msr_filter __user *user_msr_filter = argp; + struct kvm_msr_filter filter; + + if (copy_from_user(&filter, user_msr_filter, sizeof(filter))) + return -EFAULT; + + r = kvm_vm_ioctl_set_msr_filter(kvm, &filter); break; + } default: r = -ENOTTY; } @@ -7560,6 +7634,12 @@ restart: unsigned long rflags = kvm_x86_ops.get_rflags(vcpu); toggle_interruptibility(vcpu, ctxt->interruptibility); vcpu->arch.emulate_regs_need_sync_to_vcpu = false; + + /* + * Note, EXCPT_DB is assumed to be fault-like as the emulator + * only supports code breakpoints and general detect #DB, both + * of which are fault-like. + */ if (!ctxt->have_exception || exception_type(ctxt->exception.vector) == EXCPT_TRAP) { kvm_rip_write(vcpu, ctxt->eip); @@ -8347,6 +8427,11 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu) static void kvm_inject_exception(struct kvm_vcpu *vcpu) { + trace_kvm_inj_exception(vcpu->arch.exception.nr, + vcpu->arch.exception.has_error_code, + vcpu->arch.exception.error_code, + vcpu->arch.exception.injected); + if (vcpu->arch.exception.error_code && !is_protmode(vcpu)) vcpu->arch.exception.error_code = false; kvm_x86_ops.queue_exception(vcpu); @@ -8404,13 +8489,16 @@ static void inject_pending_event(struct kvm_vcpu *vcpu, bool *req_immediate_exit /* try to inject new event if pending */ if (vcpu->arch.exception.pending) { - trace_kvm_inj_exception(vcpu->arch.exception.nr, - vcpu->arch.exception.has_error_code, - vcpu->arch.exception.error_code); - - vcpu->arch.exception.pending = false; - vcpu->arch.exception.injected = true; - + /* + * Fault-class exceptions, except #DBs, set RF=1 in the RFLAGS + * value pushed on the stack. Trap-like exception and all #DBs + * leave RF as-is (KVM follows Intel's behavior in this regard; + * AMD states that code breakpoint #DBs excplitly clear RF=0). + * + * Note, most versions of Intel's SDM and AMD's APM incorrectly + * describe the behavior of General Detect #DBs, which are + * fault-like. They do _not_ set RF, a la code breakpoints. + */ if (exception_type(vcpu->arch.exception.nr) == EXCPT_FAULT) __kvm_set_rflags(vcpu, kvm_get_rflags(vcpu) | X86_EFLAGS_RF); @@ -8424,6 +8512,10 @@ static void inject_pending_event(struct kvm_vcpu *vcpu, bool *req_immediate_exit } kvm_inject_exception(vcpu); + + vcpu->arch.exception.pending = false; + vcpu->arch.exception.injected = true; + can_inject = false; } diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 91e61dbba3e0c571da67779b40cb9415e78093d9..88cb537ccdea1b76b454a3a0a18a2946d169f2d3 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -216,9 +216,15 @@ __ioremap_caller(resource_size_t phys_addr, unsigned long size, * Mappings have to be page-aligned */ offset = phys_addr & ~PAGE_MASK; - phys_addr &= PHYSICAL_PAGE_MASK; + phys_addr &= PAGE_MASK; size = PAGE_ALIGN(last_addr+1) - phys_addr; + /* + * Mask out any bits not part of the actual physical + * address, like memory encryption bits. + */ + phys_addr &= PHYSICAL_PAGE_MASK; + retval = memtype_reserve(phys_addr, (u64)phys_addr + size, pcm, &new_pcm); if (retval) { diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index f9f27e2b68e9b28b0f7c80afd257e2d0910a11e1..b64937593891a6893aa1b845d2589fb76d64c252 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -535,6 +535,7 @@ static void pm_save_spec_msr(void) MSR_TSX_FORCE_ABORT, MSR_IA32_MCU_OPT_CTRL, MSR_AMD64_LS_CFG, + MSR_AMD64_DE_CFG, }; msr_build_context(spec_msr_id, ARRAY_SIZE(spec_msr_id)); diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index 804c65d2b95f3c066f9040d5d5580e1b6256f0ce..815030b7f6fa8b48c58e9f3f0bee7aa5ee50aa1a 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -768,6 +768,7 @@ static void xen_load_idt(const struct desc_ptr *desc) { static DEFINE_SPINLOCK(lock); static struct trap_info traps[257]; + static const struct trap_info zero = { }; unsigned out; trace_xen_cpu_load_idt(desc); @@ -777,7 +778,7 @@ static void xen_load_idt(const struct desc_ptr *desc) memcpy(this_cpu_ptr(&idt_desc), desc, sizeof(idt_desc)); out = xen_convert_trap_info(desc, traps, false); - memset(&traps[out], 0, sizeof(traps[0])); + traps[out] = zero; xen_mc_flush(); if (HYPERVISOR_set_trap_table(traps)) diff --git a/arch/xtensa/include/asm/thread_info.h b/arch/xtensa/include/asm/thread_info.h index 6acbbe0d87d3d2319cf1e7db5210ac4332763dab..a312333a9addcbb1c864076e0dd71006fecb12f9 100644 --- a/arch/xtensa/include/asm/thread_info.h +++ b/arch/xtensa/include/asm/thread_info.h @@ -111,18 +111,21 @@ static inline struct thread_info *current_thread_info(void) #define TIF_NEED_RESCHED 2 /* rescheduling necessary */ #define TIF_SINGLESTEP 3 /* restore singlestep on return to user mode */ #define TIF_SYSCALL_TRACEPOINT 4 /* syscall tracepoint instrumentation */ -#define TIF_MEMDIE 5 /* is terminating due to OOM killer */ +#define TIF_NOTIFY_SIGNAL 5 /* signal notifications exist */ #define TIF_RESTORE_SIGMASK 6 /* restore signal mask in do_signal() */ #define TIF_NOTIFY_RESUME 7 /* callback before returning to user */ #define TIF_DB_DISABLED 8 /* debug trap disabled for syscall */ #define TIF_SYSCALL_AUDIT 9 /* syscall auditing active */ #define TIF_SECCOMP 10 /* secure computing */ +#define TIF_MEMDIE 11 /* is terminating due to OOM killer */ #define _TIF_SYSCALL_TRACE (1<thread.sp = (unsigned long)childregs; - if (!(p->flags & PF_KTHREAD)) { + if (!(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { struct pt_regs *regs = current_pt_regs(); unsigned long usp = usp_thread_fn ? usp_thread_fn : regs->areg[1]; diff --git a/arch/xtensa/kernel/signal.c b/arch/xtensa/kernel/signal.c index 1cb230fafdf2b5cc2ee26964ba60b1c3333bd53b..f2b00f43cf236ad2c4e8b1088ffdd23ac466dae7 100644 --- a/arch/xtensa/kernel/signal.c +++ b/arch/xtensa/kernel/signal.c @@ -498,7 +498,8 @@ static void do_signal(struct pt_regs *regs) void do_notify_resume(struct pt_regs *regs) { - if (test_thread_flag(TIF_SIGPENDING)) + if (test_thread_flag(TIF_SIGPENDING) || + test_thread_flag(TIF_NOTIFY_SIGNAL)) do_signal(regs); if (test_thread_flag(TIF_NOTIFY_RESUME)) diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c index be6733558b831246c77914e159e34886e66f1a26..badb90352bf33149c6e4494e8dfe5e9104282218 100644 --- a/block/bfq-cgroup.c +++ b/block/bfq-cgroup.c @@ -611,6 +611,10 @@ struct bfq_group *bfq_bio_bfqg(struct bfq_data *bfqd, struct bio *bio) struct bfq_group *bfqg; while (blkg) { + if (!blkg->online) { + blkg = blkg->parent; + continue; + } bfqg = blkg_to_bfqg(blkg); if (bfqg->online) { bio_associate_blkg_from_css(bio, &blkg->blkcg->css); diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index c65c37f9e33d020ec427144394b8cec1b65b8864..0e64aa558b95fc21483af77b67fccfda2dd736e3 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -421,6 +421,8 @@ static struct bfq_io_cq *bfq_bic_lookup(struct bfq_data *bfqd, */ void bfq_schedule_dispatch(struct bfq_data *bfqd) { + lockdep_assert_held(&bfqd->lock); + if (bfqd->queued != 0) { bfq_log(bfqd, "schedule dispatch"); blk_mq_run_hw_queues(bfqd->queue, true); @@ -6264,8 +6266,8 @@ bfq_idle_slice_timer_body(struct bfq_data *bfqd, struct bfq_queue *bfqq) bfq_bfqq_expire(bfqd, bfqq, true, reason); schedule_dispatch: - spin_unlock_irqrestore(&bfqd->lock, flags); bfq_schedule_dispatch(bfqd); + spin_unlock_irqrestore(&bfqd->lock, flags); } /* diff --git a/block/blk-throttle.c b/block/blk-throttle.c index c53a254171a29e0dac95596b5232230f32e48356..c526fdd0a7b909e13d6437c8fa72b7a0f09fb400 100644 --- a/block/blk-throttle.c +++ b/block/blk-throttle.c @@ -944,7 +944,7 @@ static bool tg_with_in_bps_limit(struct throtl_grp *tg, struct bio *bio, u64 bps_limit, unsigned long *wait) { bool rw = bio_data_dir(bio); - u64 bytes_allowed, extra_bytes, tmp; + u64 bytes_allowed, extra_bytes; unsigned long jiffy_elapsed, jiffy_wait, jiffy_elapsed_rnd; unsigned int bio_size = throtl_bio_data_size(bio); @@ -961,10 +961,8 @@ static bool tg_with_in_bps_limit(struct throtl_grp *tg, struct bio *bio, jiffy_elapsed_rnd = tg->td->throtl_slice; jiffy_elapsed_rnd = roundup(jiffy_elapsed_rnd, tg->td->throtl_slice); - - tmp = bps_limit * jiffy_elapsed_rnd; - do_div(tmp, HZ); - bytes_allowed = tmp; + bytes_allowed = mul_u64_u64_div_u64(bps_limit, (u64)jiffy_elapsed_rnd, + (u64)HZ); if (tg->bytes_disp[rw] + bio_size <= bytes_allowed) { if (wait) diff --git a/block/blk-wbt.c b/block/blk-wbt.c index 35d81b5deae1c821da2f8a937dcc4eb60bbec834..6f63920f073c6b1bda014ad22f1895e1d7f57578 100644 --- a/block/blk-wbt.c +++ b/block/blk-wbt.c @@ -838,9 +838,11 @@ int wbt_init(struct request_queue *q) rwb->last_comp = rwb->last_issue = jiffies; rwb->win_nsec = RWB_WINDOW_NSEC; rwb->enable_state = WBT_STATE_ON_DEFAULT; - rwb->wc = 1; + rwb->wc = test_bit(QUEUE_FLAG_WC, &q->queue_flags); rwb->rq_depth.default_depth = RWB_DEF_DEPTH; - wbt_update_limits(rwb); + rwb->min_lat_nsec = wbt_default_latency_nsec(q); + + wbt_queue_depth_changed(&rwb->rqos); /* * Assign rwb and add the stats callback. @@ -848,10 +850,5 @@ int wbt_init(struct request_queue *q) rq_qos_add(q, &rwb->rqos); blk_stat_add_callback(q, rwb->cb); - rwb->min_lat_nsec = wbt_default_latency_nsec(q); - - wbt_queue_depth_changed(&rwb->rqos); - wbt_set_write_cache(q, test_bit(QUEUE_FLAG_WC, &q->queue_flags)); - return 0; } diff --git a/block/sed-opal.c b/block/sed-opal.c index daafadbb88cae7d256d4bab708ec3ac4900ac821..0ac5a4f3f2261ccb07a1792775a422a908fb3092 100644 --- a/block/sed-opal.c +++ b/block/sed-opal.c @@ -88,8 +88,8 @@ struct opal_dev { u64 lowest_lba; size_t pos; - u8 cmd[IO_BUFFER_LENGTH]; - u8 resp[IO_BUFFER_LENGTH]; + u8 *cmd; + u8 *resp; struct parsed_resp parsed; size_t prev_d_len; @@ -2134,6 +2134,8 @@ void free_opal_dev(struct opal_dev *dev) return; clean_opal_dev(dev); + kfree(dev->resp); + kfree(dev->cmd); kfree(dev); } EXPORT_SYMBOL(free_opal_dev); @@ -2146,17 +2148,39 @@ struct opal_dev *init_opal_dev(void *data, sec_send_recv *send_recv) if (!dev) return NULL; + /* + * Presumably DMA-able buffers must be cache-aligned. Kmalloc makes + * sure the allocated buffer is DMA-safe in that regard. + */ + dev->cmd = kmalloc(IO_BUFFER_LENGTH, GFP_KERNEL); + if (!dev->cmd) + goto err_free_dev; + + dev->resp = kmalloc(IO_BUFFER_LENGTH, GFP_KERNEL); + if (!dev->resp) + goto err_free_cmd; + INIT_LIST_HEAD(&dev->unlk_lst); mutex_init(&dev->dev_lock); dev->data = data; dev->send_recv = send_recv; if (check_opal_support(dev) != 0) { pr_debug("Opal is not supported on this device\n"); - kfree(dev); - return NULL; + goto err_free_resp; } return dev; + +err_free_resp: + kfree(dev->resp); + +err_free_cmd: + kfree(dev->cmd); + +err_free_dev: + kfree(dev); + + return NULL; } EXPORT_SYMBOL(init_opal_dev); diff --git a/crypto/akcipher.c b/crypto/akcipher.c index f866085c8a4a38e83e94bb64efcaa80e5e7eff73..ab975a420e1e982c338010db3f1e3651b22cd9d0 100644 --- a/crypto/akcipher.c +++ b/crypto/akcipher.c @@ -120,6 +120,12 @@ static int akcipher_default_op(struct akcipher_request *req) return -ENOSYS; } +static int akcipher_default_set_key(struct crypto_akcipher *tfm, + const void *key, unsigned int keylen) +{ + return -ENOSYS; +} + int crypto_register_akcipher(struct akcipher_alg *alg) { struct crypto_alg *base = &alg->base; @@ -132,6 +138,8 @@ int crypto_register_akcipher(struct akcipher_alg *alg) alg->encrypt = akcipher_default_op; if (!alg->decrypt) alg->decrypt = akcipher_default_op; + if (!alg->set_priv_key) + alg->set_priv_key = akcipher_default_set_key; akcipher_prepare_alg(alg); return crypto_register_alg(base); diff --git a/drivers/accessibility/speakup/main.c b/drivers/accessibility/speakup/main.c index 48019660a0967922e5c14b8d60f384219ecf4297..63c5444f0f1aea7c5ae41e19fecd0eb3b1a6e5fe 100644 --- a/drivers/accessibility/speakup/main.c +++ b/drivers/accessibility/speakup/main.c @@ -1780,7 +1780,7 @@ static void speakup_con_update(struct vc_data *vc) { unsigned long flags; - if (!speakup_console[vc->vc_num] || spk_parked) + if (!speakup_console[vc->vc_num] || spk_parked || !synth) return; if (!spin_trylock_irqsave(&speakup_info.spinlock, flags)) /* Speakup output, discard */ diff --git a/drivers/acpi/acpi_extlog.c b/drivers/acpi/acpi_extlog.c index 72f1fb77abcd03b5a332d0d13d8803a2cb8035df..e648158368a7d8802f129e6da1509fa054f8af71 100644 --- a/drivers/acpi/acpi_extlog.c +++ b/drivers/acpi/acpi_extlog.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include @@ -138,8 +139,8 @@ static int extlog_print(struct notifier_block *nb, unsigned long val, int cpu = mce->extcpu; struct acpi_hest_generic_status *estatus, *tmp; struct acpi_hest_generic_data *gdata; - const guid_t *fru_id = &guid_null; - char *fru_text = ""; + const guid_t *fru_id; + char *fru_text; guid_t *sec_type; static u32 err_seq; @@ -160,17 +161,23 @@ static int extlog_print(struct notifier_block *nb, unsigned long val, /* log event via trace */ err_seq++; - gdata = (struct acpi_hest_generic_data *)(tmp + 1); - if (gdata->validation_bits & CPER_SEC_VALID_FRU_ID) - fru_id = (guid_t *)gdata->fru_id; - if (gdata->validation_bits & CPER_SEC_VALID_FRU_TEXT) - fru_text = gdata->fru_text; - sec_type = (guid_t *)gdata->section_type; - if (guid_equal(sec_type, &CPER_SEC_PLATFORM_MEM)) { - struct cper_sec_mem_err *mem = (void *)(gdata + 1); - if (gdata->error_data_length >= sizeof(*mem)) - trace_extlog_mem_event(mem, err_seq, fru_id, fru_text, - (u8)gdata->error_severity); + apei_estatus_for_each_section(tmp, gdata) { + if (gdata->validation_bits & CPER_SEC_VALID_FRU_ID) + fru_id = (guid_t *)gdata->fru_id; + else + fru_id = &guid_null; + if (gdata->validation_bits & CPER_SEC_VALID_FRU_TEXT) + fru_text = gdata->fru_text; + else + fru_text = ""; + sec_type = (guid_t *)gdata->section_type; + if (guid_equal(sec_type, &CPER_SEC_PLATFORM_MEM)) { + struct cper_sec_mem_err *mem = (void *)(gdata + 1); + + if (gdata->error_data_length >= sizeof(*mem)) + trace_extlog_mem_event(mem, err_seq, fru_id, fru_text, + (u8)gdata->error_severity); + } } out: diff --git a/drivers/acpi/acpi_video.c b/drivers/acpi/acpi_video.c index eb04b2f828eef470c4116dae8f41aba1473e35d7..cf6c9ffe04a2da23135d6bae40e86f4434565df7 100644 --- a/drivers/acpi/acpi_video.c +++ b/drivers/acpi/acpi_video.c @@ -498,6 +498,22 @@ static const struct dmi_system_id video_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "SATELLITE R830"), }, }, + { + .callback = video_disable_backlight_sysfs_if, + .ident = "Toshiba Satellite Z830", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"), + DMI_MATCH(DMI_PRODUCT_NAME, "SATELLITE Z830"), + }, + }, + { + .callback = video_disable_backlight_sysfs_if, + .ident = "Toshiba Portege Z830", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"), + DMI_MATCH(DMI_PRODUCT_NAME, "PORTEGE Z830"), + }, + }, /* * Some machine's _DOD IDs don't have bit 31(Device ID Scheme) set * but the IDs actually follow the Device ID Scheme. diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index 0c8330ed1ffd5c80c6774687b60970f07822e17f..9bdb5bd5fda63cb7295dcf9462cec57d7922ec4b 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -163,7 +163,7 @@ static void ghes_unmap(void __iomem *vaddr, enum fixed_addresses fixmap_idx) clear_fixmap(fixmap_idx); } -int ghes_estatus_pool_init(int num_ghes) +int ghes_estatus_pool_init(unsigned int num_ghes) { unsigned long addr, len; int rc; @@ -985,7 +985,7 @@ static void ghes_proc_in_irq(struct irq_work *irq_work) ghes_estatus_cache_add(generic, estatus); } - if (task_work_pending && current->mm != &init_mm) { + if (task_work_pending && current->mm) { estatus_node->task_work.func = ghes_kick_task_work; estatus_node->task_work_cpu = smp_processor_id(); ret = task_work_add(current, &estatus_node->task_work, diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c index e39d59ad64964e1899841967721f41d8177ed364..b13713199ad94aaa3a64e854c6c1a52ec401aa68 100644 --- a/drivers/acpi/video_detect.c +++ b/drivers/acpi/video_detect.c @@ -500,6 +500,70 @@ static const struct dmi_system_id video_detect_dmi_table[] = { DMI_MATCH(DMI_BOARD_NAME, "PF5LUXG"), }, }, + /* + * More Tongfang devices with the same issue as the Clevo NL5xRU and + * NL5xNU/TUXEDO Aura 15 Gen1 and Gen2. See the description above. + */ + { + .callback = video_detect_force_native, + .ident = "TongFang GKxNRxx", + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "GKxNRxx"), + }, + }, + { + .callback = video_detect_force_native, + .ident = "TongFang GKxNRxx", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "TUXEDO"), + DMI_MATCH(DMI_BOARD_NAME, "POLARIS1501A1650TI"), + }, + }, + { + .callback = video_detect_force_native, + .ident = "TongFang GKxNRxx", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "TUXEDO"), + DMI_MATCH(DMI_BOARD_NAME, "POLARIS1501A2060"), + }, + }, + { + .callback = video_detect_force_native, + .ident = "TongFang GKxNRxx", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "TUXEDO"), + DMI_MATCH(DMI_BOARD_NAME, "POLARIS1701A1650TI"), + }, + }, + { + .callback = video_detect_force_native, + .ident = "TongFang GKxNRxx", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "TUXEDO"), + DMI_MATCH(DMI_BOARD_NAME, "POLARIS1701A2060"), + }, + }, + { + .callback = video_detect_force_native, + .ident = "TongFang GMxNGxx", + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "GMxNGxx"), + }, + }, + { + .callback = video_detect_force_native, + .ident = "TongFang GMxZGxx", + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "GMxZGxx"), + }, + }, + { + .callback = video_detect_force_native, + .ident = "TongFang GMxRGxx", + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "GMxRGxx"), + }, + }, /* * Desktops which falsely report a backlight and which our heuristics * for this do not catch. diff --git a/drivers/android/binder.c b/drivers/android/binder.c index f0d8989a2130c19aff421b9e41883cea1ad8f78f..a73dcd2daedd4533c0f9a29901a1d64f4cc62cbd 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -2060,7 +2060,7 @@ static void binder_deferred_fd_close(int fd) if (!twcb) return; init_task_work(&twcb->twork, binder_do_fd_close); - __close_fd_get_file(fd, &twcb->file); + close_fd_get_file(fd, &twcb->file); if (twcb->file) { filp_close(twcb->file, current->files); task_work_add(current, &twcb->twork, TWA_RESUME); diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h index d1f284f0c83d98bb69ceec24c7e6560f7699f455..1ce89735699336fe237c089c4d959c8e8b7600fe 100644 --- a/drivers/ata/ahci.h +++ b/drivers/ata/ahci.h @@ -254,7 +254,7 @@ enum { PCS_7 = 0x94, /* 7+ port PCS (Denverton) */ /* em constants */ - EM_MAX_SLOTS = 8, + EM_MAX_SLOTS = SATA_PMP_MAX_PORTS, EM_MAX_RETRY = 5, /* em_ctl bits */ diff --git a/drivers/ata/ahci_imx.c b/drivers/ata/ahci_imx.c index 388baf528fa81cabf9b185944af32de80c3f6307..189f75d53741475cb67216568302335e3fbcf723 100644 --- a/drivers/ata/ahci_imx.c +++ b/drivers/ata/ahci_imx.c @@ -1230,4 +1230,4 @@ module_platform_driver(imx_ahci_driver); MODULE_DESCRIPTION("Freescale i.MX AHCI SATA platform driver"); MODULE_AUTHOR("Richard Zhu "); MODULE_LICENSE("GPL"); -MODULE_ALIAS("ahci:imx"); +MODULE_ALIAS("platform:" DRV_NAME); diff --git a/drivers/ata/libahci_platform.c b/drivers/ata/libahci_platform.c index 0910441321f729bc9ea449c326e83c776c3906df..64d6da0a53035e2093d645fc3bcabe204fbb2f7f 100644 --- a/drivers/ata/libahci_platform.c +++ b/drivers/ata/libahci_platform.c @@ -451,14 +451,24 @@ struct ahci_host_priv *ahci_platform_get_resources(struct platform_device *pdev, } } - hpriv->nports = child_nodes = of_get_child_count(dev->of_node); + /* + * Too many sub-nodes most likely means having something wrong with + * the firmware. + */ + child_nodes = of_get_child_count(dev->of_node); + if (child_nodes > AHCI_MAX_PORTS) { + rc = -EINVAL; + goto err_out; + } /* * If no sub-node was found, we still need to set nports to * one in order to be able to use the * ahci_platform_[en|dis]able_[phys|regulators] functions. */ - if (!child_nodes) + if (child_nodes) + hpriv->nports = child_nodes; + else hpriv->nports = 1; hpriv->phys = devm_kcalloc(dev, hpriv->nports, sizeof(*hpriv->phys), GFP_KERNEL); diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index a0e788b6482148aaf474d1a5950ebd95857bd45d..f1755efd30a255c21f03de5e933334356406d1ca 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -3303,6 +3303,7 @@ static unsigned int ata_scsiop_maint_in(struct ata_scsi_args *args, u8 *rbuf) case REPORT_LUNS: case REQUEST_SENSE: case SYNCHRONIZE_CACHE: + case SYNCHRONIZE_CACHE_16: case REZERO_UNIT: case SEEK_6: case SEEK_10: @@ -3969,6 +3970,7 @@ static inline ata_xlat_func_t ata_get_xlat_func(struct ata_device *dev, u8 cmd) return ata_scsi_write_same_xlat; case SYNCHRONIZE_CACHE: + case SYNCHRONIZE_CACHE_16: if (ata_try_flush_cache(dev)) return ata_scsi_flush_xlat; break; @@ -4030,44 +4032,51 @@ void ata_scsi_dump_cdb(struct ata_port *ap, struct scsi_cmnd *cmd) int __ata_scsi_queuecmd(struct scsi_cmnd *scmd, struct ata_device *dev) { + struct ata_port *ap = dev->link->ap; u8 scsi_op = scmd->cmnd[0]; ata_xlat_func_t xlat_func; - int rc = 0; + + /* + * scsi_queue_rq() will defer commands if scsi_host_in_recovery(). + * However, this check is done without holding the ap->lock (a libata + * specific lock), so we can have received an error irq since then, + * therefore we must check if EH is pending, while holding ap->lock. + */ + if (ap->pflags & (ATA_PFLAG_EH_PENDING | ATA_PFLAG_EH_IN_PROGRESS)) + return SCSI_MLQUEUE_DEVICE_BUSY; + + if (unlikely(!scmd->cmd_len)) + goto bad_cdb_len; if (dev->class == ATA_DEV_ATA || dev->class == ATA_DEV_ZAC) { - if (unlikely(!scmd->cmd_len || scmd->cmd_len > dev->cdb_len)) + if (unlikely(scmd->cmd_len > dev->cdb_len)) goto bad_cdb_len; xlat_func = ata_get_xlat_func(dev, scsi_op); - } else { - if (unlikely(!scmd->cmd_len)) - goto bad_cdb_len; + } else if (likely((scsi_op != ATA_16) || !atapi_passthru16)) { + /* relay SCSI command to ATAPI device */ + int len = COMMAND_SIZE(scsi_op); - xlat_func = NULL; - if (likely((scsi_op != ATA_16) || !atapi_passthru16)) { - /* relay SCSI command to ATAPI device */ - int len = COMMAND_SIZE(scsi_op); - if (unlikely(len > scmd->cmd_len || - len > dev->cdb_len || - scmd->cmd_len > ATAPI_CDB_LEN)) - goto bad_cdb_len; + if (unlikely(len > scmd->cmd_len || + len > dev->cdb_len || + scmd->cmd_len > ATAPI_CDB_LEN)) + goto bad_cdb_len; - xlat_func = atapi_xlat; - } else { - /* ATA_16 passthru, treat as an ATA command */ - if (unlikely(scmd->cmd_len > 16)) - goto bad_cdb_len; + xlat_func = atapi_xlat; + } else { + /* ATA_16 passthru, treat as an ATA command */ + if (unlikely(scmd->cmd_len > 16)) + goto bad_cdb_len; - xlat_func = ata_get_xlat_func(dev, scsi_op); - } + xlat_func = ata_get_xlat_func(dev, scsi_op); } if (xlat_func) - rc = ata_scsi_translate(dev, scmd, xlat_func); - else - ata_scsi_simulate(dev, scmd); + return ata_scsi_translate(dev, scmd, xlat_func); - return rc; + ata_scsi_simulate(dev, scmd); + + return 0; bad_cdb_len: DPRINTK("bad CDB len=%u, scsi_op=0x%02x, max=%u\n", @@ -4215,6 +4224,7 @@ void ata_scsi_simulate(struct ata_device *dev, struct scsi_cmnd *cmd) * turning this into a no-op. */ case SYNCHRONIZE_CACHE: + case SYNCHRONIZE_CACHE_16: fallthrough; /* no-op's, complete with success */ diff --git a/drivers/ata/libata-transport.c b/drivers/ata/libata-transport.c index b33772df9bc601d96275d916bffe11dadb058a64..31a66fc0c31dc36c85111797b94be903e2a089a6 100644 --- a/drivers/ata/libata-transport.c +++ b/drivers/ata/libata-transport.c @@ -301,7 +301,9 @@ int ata_tport_add(struct device *parent, pm_runtime_enable(dev); pm_runtime_forbid(dev); - transport_add_device(dev); + error = transport_add_device(dev); + if (error) + goto tport_transport_add_err; transport_configure_device(dev); error = ata_tlink_add(&ap->link); @@ -312,12 +314,12 @@ int ata_tport_add(struct device *parent, tport_link_err: transport_remove_device(dev); + tport_transport_add_err: device_del(dev); tport_err: transport_destroy_device(dev); put_device(dev); - ata_host_put(ap->host); return error; } @@ -426,7 +428,9 @@ int ata_tlink_add(struct ata_link *link) goto tlink_err; } - transport_add_device(dev); + error = transport_add_device(dev); + if (error) + goto tlink_transport_err; transport_configure_device(dev); ata_for_each_dev(ata_dev, link, ALL) { @@ -441,6 +445,7 @@ int ata_tlink_add(struct ata_link *link) ata_tdev_delete(ata_dev); } transport_remove_device(dev); + tlink_transport_err: device_del(dev); tlink_err: transport_destroy_device(dev); @@ -678,7 +683,13 @@ static int ata_tdev_add(struct ata_device *ata_dev) return error; } - transport_add_device(dev); + error = transport_add_device(dev); + if (error) { + device_del(dev); + ata_tdev_free(ata_dev); + return error; + } + transport_configure_device(dev); return 0; } diff --git a/drivers/ata/pata_legacy.c b/drivers/ata/pata_legacy.c index d91ba47f2fc44db4c23ba48d9cd3a00ae00269bc..4405d255e3aa2807b5e2560a04c6a1b7a76f4dca 100644 --- a/drivers/ata/pata_legacy.c +++ b/drivers/ata/pata_legacy.c @@ -278,9 +278,10 @@ static void pdc20230_set_piomode(struct ata_port *ap, struct ata_device *adev) outb(inb(0x1F4) & 0x07, 0x1F4); rt = inb(0x1F3); - rt &= 0x07 << (3 * adev->devno); + rt &= ~(0x07 << (3 * !adev->devno)); if (pio) - rt |= (1 + 3 * pio) << (3 * adev->devno); + rt |= (1 + 3 * pio) << (3 * !adev->devno); + outb(rt, 0x1F3); udelay(100); outb(inb(0x1F2) | 0x01, 0x1F2); diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c index 212e5d3a78a190f22d4689a7ed7e4f59da4a83aa..321cb3138d4e96c7bb23aadd81f6d7f46347fb55 100644 --- a/drivers/base/arch_topology.c +++ b/drivers/base/arch_topology.c @@ -607,4 +607,23 @@ void __init init_cpu_topology(void) else if (of_have_populated_dt() && parse_dt_topology()) reset_cpu_topology(); } + +void store_cpu_topology(unsigned int cpuid) +{ + struct cpu_topology *cpuid_topo = &cpu_topology[cpuid]; + + if (cpuid_topo->package_id != -1) + goto topology_populated; + + cpuid_topo->thread_id = -1; + cpuid_topo->core_id = cpuid; + cpuid_topo->package_id = cpu_to_node(cpuid); + + pr_debug("CPU%u: package %d core %d thread %d\n", + cpuid, cpuid_topo->package_id, cpuid_topo->core_id, + cpuid_topo->thread_id); + +topology_populated: + update_siblings_masks(cpuid); +} #endif diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c index b03cc51f1e5c7e1437605ef5faa9eb3620175585..c4e56e058599aa106af5e8f8e199b0ab289347b7 100644 --- a/drivers/base/power/domain.c +++ b/drivers/base/power/domain.c @@ -2861,6 +2861,10 @@ static int genpd_iterate_idle_states(struct device_node *dn, np = it.node; if (!of_match_node(idle_state_match, np)) continue; + + if (!of_device_is_available(np)) + continue; + if (states) { ret = genpd_parse_state(&states[i], np); if (ret) { diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c index 407527ff6b1f6ae518a9efb9650a47baf5b5ec49..51450f7c81afee4ad5f89ac4cd076a6a7c7a9f79 100644 --- a/drivers/block/drbd/drbd_main.c +++ b/drivers/block/drbd/drbd_main.c @@ -2720,7 +2720,7 @@ static int init_submitter(struct drbd_device *device) enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsigned int minor) { struct drbd_resource *resource = adm_ctx->resource; - struct drbd_connection *connection; + struct drbd_connection *connection, *n; struct drbd_device *device; struct drbd_peer_device *peer_device, *tmp_peer_device; struct gendisk *disk; @@ -2839,7 +2839,7 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig out_idr_remove_vol: idr_remove(&connection->peer_devices, vnr); out_idr_remove_from_resource: - for_each_connection(connection, resource) { + for_each_connection_safe(connection, n, resource) { peer_device = idr_remove(&connection->peer_devices, vnr); if (peer_device) kref_put(&connection->kref, drbd_destroy_connection); diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 4a6b82d434eef8afb561bf6a9a9cfba54c1450e9..b0d3dadeb9643199453b5915db90fce86d05478d 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -1342,10 +1342,12 @@ static int nbd_start_device_ioctl(struct nbd_device *nbd, struct block_device *b mutex_unlock(&nbd->config_lock); ret = wait_event_interruptible(config->recv_wq, atomic_read(&config->recv_threads) == 0); - if (ret) + if (ret) { sock_shutdown(nbd); - flush_workqueue(nbd->recv_workq); + nbd_clear_que(nbd); + } + flush_workqueue(nbd->recv_workq); mutex_lock(&nbd->config_lock); nbd_bdev_reset(bdev); /* user requested, ignore socket errors */ diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index a699e6166aefe11426bb0c5a49771876b8544403..6efd981979bd30f4e79c15842642052ab17e38e5 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -2816,6 +2816,7 @@ enum { enum { BTMTK_WMT_INVALID, BTMTK_WMT_PATCH_UNDONE, + BTMTK_WMT_PATCH_PROGRESS, BTMTK_WMT_PATCH_DONE, BTMTK_WMT_ON_UNDONE, BTMTK_WMT_ON_DONE, @@ -2831,7 +2832,7 @@ struct btmtk_wmt_hdr { struct btmtk_hci_wmt_cmd { struct btmtk_wmt_hdr hdr; - u8 data[256]; + u8 data[]; } __packed; struct btmtk_hci_wmt_evt { @@ -2934,7 +2935,7 @@ static void btusb_mtk_wmt_recv(struct urb *urb) * to generate the event. Otherwise, the WMT event cannot return from * the device successfully. */ - udelay(100); + udelay(500); usb_anchor_urb(urb, &data->ctrl_anchor); err = usb_submit_urb(urb, GFP_ATOMIC); @@ -3010,7 +3011,7 @@ static int btusb_mtk_hci_wmt_sync(struct hci_dev *hdev, struct btmtk_hci_wmt_evt_funcc *wmt_evt_funcc; u32 hlen, status = BTMTK_WMT_INVALID; struct btmtk_hci_wmt_evt *wmt_evt; - struct btmtk_hci_wmt_cmd wc; + struct btmtk_hci_wmt_cmd *wc; struct btmtk_wmt_hdr *hdr; int err; @@ -3019,24 +3020,42 @@ static int btusb_mtk_hci_wmt_sync(struct hci_dev *hdev, if (hlen > 255) return -EINVAL; - hdr = (struct btmtk_wmt_hdr *)&wc; + wc = kzalloc(hlen, GFP_KERNEL); + if (!wc) + return -ENOMEM; + + hdr = &wc->hdr; hdr->dir = 1; hdr->op = wmt_params->op; hdr->dlen = cpu_to_le16(wmt_params->dlen + 1); hdr->flag = wmt_params->flag; - memcpy(wc.data, wmt_params->data, wmt_params->dlen); + memcpy(wc->data, wmt_params->data, wmt_params->dlen); set_bit(BTUSB_TX_WAIT_VND_EVT, &data->flags); - err = __hci_cmd_send(hdev, 0xfc6f, hlen, &wc); + /* WMT cmd/event doesn't follow up the generic HCI cmd/event handling, + * it needs constantly polling control pipe until the host received the + * WMT event, thus, we should require to specifically acquire PM counter + * on the USB to prevent the interface from entering auto suspended + * while WMT cmd/event in progress. + */ + err = usb_autopm_get_interface(data->intf); + if (err < 0) + goto err_free_wc; + + err = __hci_cmd_send(hdev, 0xfc6f, hlen, wc); if (err < 0) { clear_bit(BTUSB_TX_WAIT_VND_EVT, &data->flags); - return err; + usb_autopm_put_interface(data->intf); + goto err_free_wc; } /* Submit control IN URB on demand to process the WMT event */ err = btusb_mtk_submit_wmt_recv_urb(hdev); + + usb_autopm_put_interface(data->intf); + if (err < 0) return err; @@ -3054,13 +3073,14 @@ static int btusb_mtk_hci_wmt_sync(struct hci_dev *hdev, if (err == -EINTR) { bt_dev_err(hdev, "Execution of wmt command interrupted"); clear_bit(BTUSB_TX_WAIT_VND_EVT, &data->flags); - return err; + goto err_free_wc; } if (err) { bt_dev_err(hdev, "Execution of wmt command timed out"); clear_bit(BTUSB_TX_WAIT_VND_EVT, &data->flags); - return -ETIMEDOUT; + err = -ETIMEDOUT; + goto err_free_wc; } /* Parse and handle the return WMT event */ @@ -3096,7 +3116,8 @@ static int btusb_mtk_hci_wmt_sync(struct hci_dev *hdev, err_free_skb: kfree_skb(data->evt_skb); data->evt_skb = NULL; - +err_free_wc: + kfree(wc); return err; } @@ -3238,9 +3259,9 @@ err_free_buf: return err; } -static int btusb_mtk_id_get(struct btusb_data *data, u32 *id) +static int btusb_mtk_id_get(struct btusb_data *data, u32 reg, u32 *id) { - return btusb_mtk_reg_read(data, 0x80000008, id); + return btusb_mtk_reg_read(data, reg, id); } static int btusb_mtk_setup(struct hci_dev *hdev) @@ -3258,7 +3279,7 @@ static int btusb_mtk_setup(struct hci_dev *hdev) calltime = ktime_get(); - err = btusb_mtk_id_get(data, &dev_id); + err = btusb_mtk_id_get(data, 0x80000008, &dev_id); if (err < 0) { bt_dev_err(hdev, "Failed to get device id (%d)", err); return err; diff --git a/drivers/bluetooth/hci_ldisc.c b/drivers/bluetooth/hci_ldisc.c index 637c5b8c2aa1a545c1b07a16df3b196489149144..726d5c83c550e5052023654bbbaed15968fdd5f9 100644 --- a/drivers/bluetooth/hci_ldisc.c +++ b/drivers/bluetooth/hci_ldisc.c @@ -490,6 +490,11 @@ static int hci_uart_tty_open(struct tty_struct *tty) BT_ERR("Can't allocate control structure"); return -ENFILE; } + if (percpu_init_rwsem(&hu->proto_lock)) { + BT_ERR("Can't allocate semaphore structure"); + kfree(hu); + return -ENOMEM; + } tty->disc_data = hu; hu->tty = tty; @@ -502,8 +507,6 @@ static int hci_uart_tty_open(struct tty_struct *tty) INIT_WORK(&hu->init_ready, hci_uart_init_work); INIT_WORK(&hu->write_work, hci_uart_write_work); - percpu_init_rwsem(&hu->proto_lock); - /* Flush any pending characters in the driver */ tty_driver_flush_buffer(tty); diff --git a/drivers/bluetooth/hci_serdev.c b/drivers/bluetooth/hci_serdev.c index e9a44ab3812df06e1714cb237eb15d4b72f3b5bd..f2e2e553d4de7abfe0254229b52b8c9dd4eb24c7 100644 --- a/drivers/bluetooth/hci_serdev.c +++ b/drivers/bluetooth/hci_serdev.c @@ -301,11 +301,12 @@ int hci_uart_register_device(struct hci_uart *hu, serdev_device_set_client_ops(hu->serdev, &hci_serdev_client_ops); + if (percpu_init_rwsem(&hu->proto_lock)) + return -ENOMEM; + err = serdev_device_open(hu->serdev); if (err) - return err; - - percpu_init_rwsem(&hu->proto_lock); + goto err_rwsem; err = p->open(hu); if (err) @@ -375,6 +376,8 @@ err_alloc: p->close(hu); err_open: serdev_device_close(hu->serdev); +err_rwsem: + percpu_free_rwsem(&hu->proto_lock); return err; } EXPORT_SYMBOL_GPL(hci_uart_register_device); @@ -396,5 +399,6 @@ void hci_uart_unregister_device(struct hci_uart *hu) clear_bit(HCI_UART_PROTO_READY, &hu->flags); serdev_device_close(hu->serdev); } + percpu_free_rwsem(&hu->proto_lock); } EXPORT_SYMBOL_GPL(hci_uart_unregister_device); diff --git a/drivers/bus/sunxi-rsb.c b/drivers/bus/sunxi-rsb.c index 9b1a5e62417cbcd11a6f6886fede7e1498d55d55..f8c29b888e6b4683170b27e7bf7cb76aa85cc1e9 100644 --- a/drivers/bus/sunxi-rsb.c +++ b/drivers/bus/sunxi-rsb.c @@ -268,6 +268,9 @@ EXPORT_SYMBOL_GPL(sunxi_rsb_driver_register); /* common code that starts a transfer */ static int _sunxi_rsb_run_xfer(struct sunxi_rsb *rsb) { + u32 int_mask, status; + bool timeout; + if (readl(rsb->regs + RSB_CTRL) & RSB_CTRL_START_TRANS) { dev_dbg(rsb->dev, "RSB transfer still in progress\n"); return -EBUSY; @@ -275,13 +278,23 @@ static int _sunxi_rsb_run_xfer(struct sunxi_rsb *rsb) reinit_completion(&rsb->complete); - writel(RSB_INTS_LOAD_BSY | RSB_INTS_TRANS_ERR | RSB_INTS_TRANS_OVER, - rsb->regs + RSB_INTE); + int_mask = RSB_INTS_LOAD_BSY | RSB_INTS_TRANS_ERR | RSB_INTS_TRANS_OVER; + writel(int_mask, rsb->regs + RSB_INTE); writel(RSB_CTRL_START_TRANS | RSB_CTRL_GLOBAL_INT_ENB, rsb->regs + RSB_CTRL); - if (!wait_for_completion_io_timeout(&rsb->complete, - msecs_to_jiffies(100))) { + if (irqs_disabled()) { + timeout = readl_poll_timeout_atomic(rsb->regs + RSB_INTS, + status, (status & int_mask), + 10, 100000); + writel(status, rsb->regs + RSB_INTS); + } else { + timeout = !wait_for_completion_io_timeout(&rsb->complete, + msecs_to_jiffies(100)); + status = rsb->status; + } + + if (timeout) { dev_dbg(rsb->dev, "RSB timeout\n"); /* abort the transfer */ @@ -293,18 +306,18 @@ static int _sunxi_rsb_run_xfer(struct sunxi_rsb *rsb) return -ETIMEDOUT; } - if (rsb->status & RSB_INTS_LOAD_BSY) { + if (status & RSB_INTS_LOAD_BSY) { dev_dbg(rsb->dev, "RSB busy\n"); return -EBUSY; } - if (rsb->status & RSB_INTS_TRANS_ERR) { - if (rsb->status & RSB_INTS_TRANS_ERR_ACK) { + if (status & RSB_INTS_TRANS_ERR) { + if (status & RSB_INTS_TRANS_ERR_ACK) { dev_dbg(rsb->dev, "RSB slave nack\n"); return -EINVAL; } - if (rsb->status & RSB_INTS_TRANS_ERR_DATA) { + if (status & RSB_INTS_TRANS_ERR_DATA) { dev_dbg(rsb->dev, "RSB transfer data error\n"); return -EIO; } diff --git a/drivers/char/hw_random/imx-rngc.c b/drivers/char/hw_random/imx-rngc.c index 61c844baf26e875661278114c3618a5e29867c14..9b182e5bfa87a7c2740deedf36a03ff2ed1942e8 100644 --- a/drivers/char/hw_random/imx-rngc.c +++ b/drivers/char/hw_random/imx-rngc.c @@ -272,13 +272,6 @@ static int imx_rngc_probe(struct platform_device *pdev) goto err; } - ret = devm_request_irq(&pdev->dev, - irq, imx_rngc_irq, 0, pdev->name, (void *)rngc); - if (ret) { - dev_err(rngc->dev, "Can't get interrupt working.\n"); - goto err; - } - init_completion(&rngc->rng_op_done); rngc->rng.name = pdev->name; @@ -292,6 +285,13 @@ static int imx_rngc_probe(struct platform_device *pdev) imx_rngc_irq_mask_clear(rngc); + ret = devm_request_irq(&pdev->dev, + irq, imx_rngc_irq, 0, pdev->name, (void *)rngc); + if (ret) { + dev_err(rngc->dev, "Can't get interrupt working.\n"); + return ret; + } + if (self_test) { ret = imx_rngc_self_test(rngc); if (ret) { diff --git a/drivers/clk/baikal-t1/ccu-div.c b/drivers/clk/baikal-t1/ccu-div.c index 4062092d67f905a601e1d8d0856175eaeee0240c..a6642f3d33d44dcded40ea9af615c0b7ef12eec5 100644 --- a/drivers/clk/baikal-t1/ccu-div.c +++ b/drivers/clk/baikal-t1/ccu-div.c @@ -34,6 +34,7 @@ #define CCU_DIV_CTL_CLKDIV_MASK(_width) \ GENMASK((_width) + CCU_DIV_CTL_CLKDIV_FLD - 1, CCU_DIV_CTL_CLKDIV_FLD) #define CCU_DIV_CTL_LOCK_SHIFTED BIT(27) +#define CCU_DIV_CTL_GATE_REF_BUF BIT(28) #define CCU_DIV_CTL_LOCK_NORMAL BIT(31) #define CCU_DIV_RST_DELAY_US 1 @@ -170,6 +171,40 @@ static int ccu_div_gate_is_enabled(struct clk_hw *hw) return !!(val & CCU_DIV_CTL_EN); } +static int ccu_div_buf_enable(struct clk_hw *hw) +{ + struct ccu_div *div = to_ccu_div(hw); + unsigned long flags; + + spin_lock_irqsave(&div->lock, flags); + regmap_update_bits(div->sys_regs, div->reg_ctl, + CCU_DIV_CTL_GATE_REF_BUF, 0); + spin_unlock_irqrestore(&div->lock, flags); + + return 0; +} + +static void ccu_div_buf_disable(struct clk_hw *hw) +{ + struct ccu_div *div = to_ccu_div(hw); + unsigned long flags; + + spin_lock_irqsave(&div->lock, flags); + regmap_update_bits(div->sys_regs, div->reg_ctl, + CCU_DIV_CTL_GATE_REF_BUF, CCU_DIV_CTL_GATE_REF_BUF); + spin_unlock_irqrestore(&div->lock, flags); +} + +static int ccu_div_buf_is_enabled(struct clk_hw *hw) +{ + struct ccu_div *div = to_ccu_div(hw); + u32 val = 0; + + regmap_read(div->sys_regs, div->reg_ctl, &val); + + return !(val & CCU_DIV_CTL_GATE_REF_BUF); +} + static unsigned long ccu_div_var_recalc_rate(struct clk_hw *hw, unsigned long parent_rate) { @@ -323,6 +358,7 @@ static const struct ccu_div_dbgfs_bit ccu_div_bits[] = { CCU_DIV_DBGFS_BIT_ATTR("div_en", CCU_DIV_CTL_EN), CCU_DIV_DBGFS_BIT_ATTR("div_rst", CCU_DIV_CTL_RST), CCU_DIV_DBGFS_BIT_ATTR("div_bypass", CCU_DIV_CTL_SET_CLKDIV), + CCU_DIV_DBGFS_BIT_ATTR("div_buf", CCU_DIV_CTL_GATE_REF_BUF), CCU_DIV_DBGFS_BIT_ATTR("div_lock", CCU_DIV_CTL_LOCK_NORMAL) }; @@ -441,6 +477,9 @@ static void ccu_div_var_debug_init(struct clk_hw *hw, struct dentry *dentry) continue; } + if (!strcmp("div_buf", name)) + continue; + bits[didx] = ccu_div_bits[bidx]; bits[didx].div = div; @@ -477,6 +516,21 @@ static void ccu_div_gate_debug_init(struct clk_hw *hw, struct dentry *dentry) &ccu_div_dbgfs_fixed_clkdiv_fops); } +static void ccu_div_buf_debug_init(struct clk_hw *hw, struct dentry *dentry) +{ + struct ccu_div *div = to_ccu_div(hw); + struct ccu_div_dbgfs_bit *bit; + + bit = kmalloc(sizeof(*bit), GFP_KERNEL); + if (!bit) + return; + + *bit = ccu_div_bits[3]; + bit->div = div; + debugfs_create_file_unsafe(bit->name, ccu_div_dbgfs_mode, dentry, bit, + &ccu_div_dbgfs_bit_fops); +} + static void ccu_div_fixed_debug_init(struct clk_hw *hw, struct dentry *dentry) { struct ccu_div *div = to_ccu_div(hw); @@ -489,6 +543,7 @@ static void ccu_div_fixed_debug_init(struct clk_hw *hw, struct dentry *dentry) #define ccu_div_var_debug_init NULL #define ccu_div_gate_debug_init NULL +#define ccu_div_buf_debug_init NULL #define ccu_div_fixed_debug_init NULL #endif /* !CONFIG_DEBUG_FS */ @@ -520,6 +575,13 @@ static const struct clk_ops ccu_div_gate_ops = { .debug_init = ccu_div_gate_debug_init }; +static const struct clk_ops ccu_div_buf_ops = { + .enable = ccu_div_buf_enable, + .disable = ccu_div_buf_disable, + .is_enabled = ccu_div_buf_is_enabled, + .debug_init = ccu_div_buf_debug_init +}; + static const struct clk_ops ccu_div_fixed_ops = { .recalc_rate = ccu_div_fixed_recalc_rate, .round_rate = ccu_div_fixed_round_rate, @@ -566,6 +628,8 @@ struct ccu_div *ccu_div_hw_register(const struct ccu_div_init_data *div_init) } else if (div_init->type == CCU_DIV_GATE) { hw_init.ops = &ccu_div_gate_ops; div->divider = div_init->divider; + } else if (div_init->type == CCU_DIV_BUF) { + hw_init.ops = &ccu_div_buf_ops; } else if (div_init->type == CCU_DIV_FIXED) { hw_init.ops = &ccu_div_fixed_ops; div->divider = div_init->divider; @@ -579,6 +643,7 @@ struct ccu_div *ccu_div_hw_register(const struct ccu_div_init_data *div_init) goto err_free_div; } parent_data.fw_name = div_init->parent_name; + parent_data.name = div_init->parent_name; hw_init.parent_data = &parent_data; hw_init.num_parents = 1; diff --git a/drivers/clk/baikal-t1/ccu-div.h b/drivers/clk/baikal-t1/ccu-div.h index 795665caefbdc9f3320de927f9340695f2be979f..4eb49ff4803c6e27502096fc874009b2d9995620 100644 --- a/drivers/clk/baikal-t1/ccu-div.h +++ b/drivers/clk/baikal-t1/ccu-div.h @@ -13,6 +13,14 @@ #include #include +/* + * CCU Divider private clock IDs + * @CCU_SYS_SATA_CLK: CCU SATA internal clock + * @CCU_SYS_XGMAC_CLK: CCU XGMAC internal clock + */ +#define CCU_SYS_SATA_CLK -1 +#define CCU_SYS_XGMAC_CLK -2 + /* * CCU Divider private flags * @CCU_DIV_SKIP_ONE: Due to some reason divider can't be set to 1. @@ -31,11 +39,13 @@ * enum ccu_div_type - CCU Divider types * @CCU_DIV_VAR: Clocks gate with variable divider. * @CCU_DIV_GATE: Clocks gate with fixed divider. + * @CCU_DIV_BUF: Clock gate with no divider. * @CCU_DIV_FIXED: Ungateable clock with fixed divider. */ enum ccu_div_type { CCU_DIV_VAR, CCU_DIV_GATE, + CCU_DIV_BUF, CCU_DIV_FIXED }; diff --git a/drivers/clk/baikal-t1/clk-ccu-div.c b/drivers/clk/baikal-t1/clk-ccu-div.c index f141fda12b09aa69d7361581efabccfafd9d238c..90f4fda406ee668b94c877dcb72c5ba62418d494 100644 --- a/drivers/clk/baikal-t1/clk-ccu-div.c +++ b/drivers/clk/baikal-t1/clk-ccu-div.c @@ -76,6 +76,16 @@ .divider = _divider \ } +#define CCU_DIV_BUF_INFO(_id, _name, _pname, _base, _flags) \ + { \ + .id = _id, \ + .name = _name, \ + .parent_name = _pname, \ + .base = _base, \ + .type = CCU_DIV_BUF, \ + .flags = _flags \ + } + #define CCU_DIV_FIXED_INFO(_id, _name, _pname, _divider) \ { \ .id = _id, \ @@ -188,11 +198,14 @@ static const struct ccu_div_rst_map axi_rst_map[] = { * for the SoC devices registers IO-operations. */ static const struct ccu_div_info sys_info[] = { - CCU_DIV_VAR_INFO(CCU_SYS_SATA_REF_CLK, "sys_sata_ref_clk", + CCU_DIV_VAR_INFO(CCU_SYS_SATA_CLK, "sys_sata_clk", "sata_clk", CCU_SYS_SATA_REF_BASE, 4, CLK_SET_RATE_GATE, CCU_DIV_SKIP_ONE | CCU_DIV_LOCK_SHIFTED | CCU_DIV_RESET_DOMAIN), + CCU_DIV_BUF_INFO(CCU_SYS_SATA_REF_CLK, "sys_sata_ref_clk", + "sys_sata_clk", CCU_SYS_SATA_REF_BASE, + CLK_SET_RATE_PARENT), CCU_DIV_VAR_INFO(CCU_SYS_APB_CLK, "sys_apb_clk", "pcie_clk", CCU_SYS_APB_BASE, 5, CLK_IS_CRITICAL, CCU_DIV_RESET_DOMAIN), @@ -204,10 +217,12 @@ static const struct ccu_div_info sys_info[] = { "eth_clk", CCU_SYS_GMAC1_BASE, 5), CCU_DIV_FIXED_INFO(CCU_SYS_GMAC1_PTP_CLK, "sys_gmac1_ptp_clk", "eth_clk", 10), - CCU_DIV_GATE_INFO(CCU_SYS_XGMAC_REF_CLK, "sys_xgmac_ref_clk", - "eth_clk", CCU_SYS_XGMAC_BASE, 8), + CCU_DIV_GATE_INFO(CCU_SYS_XGMAC_CLK, "sys_xgmac_clk", + "eth_clk", CCU_SYS_XGMAC_BASE, 1), + CCU_DIV_FIXED_INFO(CCU_SYS_XGMAC_REF_CLK, "sys_xgmac_ref_clk", + "sys_xgmac_clk", 8), CCU_DIV_FIXED_INFO(CCU_SYS_XGMAC_PTP_CLK, "sys_xgmac_ptp_clk", - "eth_clk", 10), + "sys_xgmac_clk", 8), CCU_DIV_GATE_INFO(CCU_SYS_USB_CLK, "sys_usb_clk", "eth_clk", CCU_SYS_USB_BASE, 10), CCU_DIV_VAR_INFO(CCU_SYS_PVT_CLK, "sys_pvt_clk", @@ -396,6 +411,9 @@ static int ccu_div_clk_register(struct ccu_div_data *data) init.base = info->base; init.sys_regs = data->sys_regs; init.divider = info->divider; + } else if (init.type == CCU_DIV_BUF) { + init.base = info->base; + init.sys_regs = data->sys_regs; } else { init.divider = info->divider; } diff --git a/drivers/clk/bcm/clk-bcm2835.c b/drivers/clk/bcm/clk-bcm2835.c index 178886823b90ca2a8449c3ae00f992607030c1f7..b7f89873fcf54e13b83d664d40508f342c179232 100644 --- a/drivers/clk/bcm/clk-bcm2835.c +++ b/drivers/clk/bcm/clk-bcm2835.c @@ -968,9 +968,9 @@ static u32 bcm2835_clock_choose_div(struct clk_hw *hw, return div; } -static long bcm2835_clock_rate_from_divisor(struct bcm2835_clock *clock, - unsigned long parent_rate, - u32 div) +static unsigned long bcm2835_clock_rate_from_divisor(struct bcm2835_clock *clock, + unsigned long parent_rate, + u32 div) { const struct bcm2835_clock_data *data = clock->data; u64 temp; @@ -1786,7 +1786,7 @@ static const struct bcm2835_clk_desc clk_desc_array[] = { .load_mask = CM_PLLC_LOADPER, .hold_mask = CM_PLLC_HOLDPER, .fixed_divider = 1, - .flags = CLK_SET_RATE_PARENT), + .flags = CLK_IS_CRITICAL | CLK_SET_RATE_PARENT), /* * PLLD is the display PLL, used to drive DSI display panels. diff --git a/drivers/clk/berlin/bg2.c b/drivers/clk/berlin/bg2.c index bccdfa00fd37394aa62538356783ccd3a9eef8e3..67a9edbba29c448bbd9f58e3e06f095788d1168e 100644 --- a/drivers/clk/berlin/bg2.c +++ b/drivers/clk/berlin/bg2.c @@ -500,12 +500,15 @@ static void __init berlin2_clock_setup(struct device_node *np) int n, ret; clk_data = kzalloc(struct_size(clk_data, hws, MAX_CLKS), GFP_KERNEL); - if (!clk_data) + if (!clk_data) { + of_node_put(parent_np); return; + } clk_data->num = MAX_CLKS; hws = clk_data->hws; gbase = of_iomap(parent_np, 0); + of_node_put(parent_np); if (!gbase) return; diff --git a/drivers/clk/berlin/bg2q.c b/drivers/clk/berlin/bg2q.c index e9518d35f262e171cb1233707579f8b8102a4023..dd2784bb75b649c2f5eb072759ff4fee6a4cc47a 100644 --- a/drivers/clk/berlin/bg2q.c +++ b/drivers/clk/berlin/bg2q.c @@ -286,19 +286,23 @@ static void __init berlin2q_clock_setup(struct device_node *np) int n, ret; clk_data = kzalloc(struct_size(clk_data, hws, MAX_CLKS), GFP_KERNEL); - if (!clk_data) + if (!clk_data) { + of_node_put(parent_np); return; + } clk_data->num = MAX_CLKS; hws = clk_data->hws; gbase = of_iomap(parent_np, 0); if (!gbase) { + of_node_put(parent_np); pr_err("%pOF: Unable to map global base\n", np); return; } /* BG2Q CPU PLL is not part of global registers */ cpupll_base = of_iomap(parent_np, 1); + of_node_put(parent_np); if (!cpupll_base) { pr_err("%pOF: Unable to map cpupll base\n", np); iounmap(gbase); diff --git a/drivers/clk/clk-ast2600.c b/drivers/clk/clk-ast2600.c index 24dab2312bc6faf572e7a7b63c187de602e6df18..9c3305bcb27ae0810a677ac9bb693bd04e53e6c4 100644 --- a/drivers/clk/clk-ast2600.c +++ b/drivers/clk/clk-ast2600.c @@ -622,7 +622,7 @@ static int aspeed_g6_clk_probe(struct platform_device *pdev) regmap_write(map, 0x308, 0x12000); /* 3x3 = 9 */ /* P-Bus (BCLK) clock divider */ - hw = clk_hw_register_divider_table(dev, "bclk", "hpll", 0, + hw = clk_hw_register_divider_table(dev, "bclk", "epll", 0, scu_g6_base + ASPEED_G6_CLK_SELECTION1, 20, 3, 0, ast2600_div_table, &aspeed_g6_clk_lock); diff --git a/drivers/clk/clk-oxnas.c b/drivers/clk/clk-oxnas.c index 78d5ea669fea7df4aba3dfa5b9c337b37b1ece81..2fe36f579ac5e83e996a2a5aa72f9600af3226d3 100644 --- a/drivers/clk/clk-oxnas.c +++ b/drivers/clk/clk-oxnas.c @@ -207,7 +207,7 @@ static const struct of_device_id oxnas_stdclk_dt_ids[] = { static int oxnas_stdclk_probe(struct platform_device *pdev) { - struct device_node *np = pdev->dev.of_node; + struct device_node *np = pdev->dev.of_node, *parent_np; const struct oxnas_stdclk_data *data; const struct of_device_id *id; struct regmap *regmap; @@ -219,7 +219,9 @@ static int oxnas_stdclk_probe(struct platform_device *pdev) return -ENODEV; data = id->data; - regmap = syscon_node_to_regmap(of_get_parent(np)); + parent_np = of_get_parent(np); + regmap = syscon_node_to_regmap(parent_np); + of_node_put(parent_np); if (IS_ERR(regmap)) { dev_err(&pdev->dev, "failed to have parent regmap\n"); return PTR_ERR(regmap); diff --git a/drivers/clk/clk-qoriq.c b/drivers/clk/clk-qoriq.c index 46101c6a20f261830e6195498d09ab2ef6359636..585b9ac11881804ffa974261f44dcee73f158f8b 100644 --- a/drivers/clk/clk-qoriq.c +++ b/drivers/clk/clk-qoriq.c @@ -1038,8 +1038,13 @@ static void __init _clockgen_init(struct device_node *np, bool legacy); */ static void __init legacy_init_clockgen(struct device_node *np) { - if (!clockgen.node) - _clockgen_init(of_get_parent(np), true); + if (!clockgen.node) { + struct device_node *parent_np; + + parent_np = of_get_parent(np); + _clockgen_init(parent_np, true); + of_node_put(parent_np); + } } /* Legacy node */ @@ -1134,6 +1139,7 @@ static struct clk * __init create_sysclk(const char *name) sysclk = of_get_child_by_name(clockgen.node, "sysclk"); if (sysclk) { clk = sysclk_from_fixed(sysclk, name); + of_node_put(sysclk); if (!IS_ERR(clk)) return clk; } diff --git a/drivers/clk/clk-versaclock5.c b/drivers/clk/clk-versaclock5.c index 4e741f94baf02adf3b379892364f04433bb038bf..eb597ea7bb87b63a4c4bd62a341b24ddec9ff1e7 100644 --- a/drivers/clk/clk-versaclock5.c +++ b/drivers/clk/clk-versaclock5.c @@ -1116,7 +1116,7 @@ static const struct vc5_chip_info idt_5p49v6901_info = { .model = IDT_VC6_5P49V6901, .clk_fod_cnt = 4, .clk_out_cnt = 5, - .flags = VC5_HAS_PFD_FREQ_DBL, + .flags = VC5_HAS_PFD_FREQ_DBL | VC5_HAS_BYPASS_SYNC_BIT, }; static const struct vc5_chip_info idt_5p49v6965_info = { diff --git a/drivers/clk/mediatek/clk-mt8183-mfgcfg.c b/drivers/clk/mediatek/clk-mt8183-mfgcfg.c index 37b4162c5882036da6e74afea176361f8a108258..3a33014eee7f7b90e173e74d3482102148c258f3 100644 --- a/drivers/clk/mediatek/clk-mt8183-mfgcfg.c +++ b/drivers/clk/mediatek/clk-mt8183-mfgcfg.c @@ -18,9 +18,9 @@ static const struct mtk_gate_regs mfg_cg_regs = { .sta_ofs = 0x0, }; -#define GATE_MFG(_id, _name, _parent, _shift) \ - GATE_MTK(_id, _name, _parent, &mfg_cg_regs, _shift, \ - &mtk_clk_gate_ops_setclr) +#define GATE_MFG(_id, _name, _parent, _shift) \ + GATE_MTK_FLAGS(_id, _name, _parent, &mfg_cg_regs, _shift, \ + &mtk_clk_gate_ops_setclr, CLK_SET_RATE_PARENT) static const struct mtk_gate mfg_clks[] = { GATE_MFG(CLK_MFG_BG3D, "mfg_bg3d", "mfg_sel", 0) diff --git a/drivers/clk/meson/meson-aoclk.c b/drivers/clk/meson/meson-aoclk.c index 27cd2c1f3f6123fceb5216bffccf159d3c0d318f..434cd8f9de8262d2ce33b66623e74061a6c6f590 100644 --- a/drivers/clk/meson/meson-aoclk.c +++ b/drivers/clk/meson/meson-aoclk.c @@ -38,6 +38,7 @@ int meson_aoclkc_probe(struct platform_device *pdev) struct meson_aoclk_reset_controller *rstc; struct meson_aoclk_data *data; struct device *dev = &pdev->dev; + struct device_node *np; struct regmap *regmap; int ret, clkid; @@ -49,7 +50,9 @@ int meson_aoclkc_probe(struct platform_device *pdev) if (!rstc) return -ENOMEM; - regmap = syscon_node_to_regmap(of_get_parent(dev->of_node)); + np = of_get_parent(dev->of_node); + regmap = syscon_node_to_regmap(np); + of_node_put(np); if (IS_ERR(regmap)) { dev_err(dev, "failed to get regmap\n"); return PTR_ERR(regmap); diff --git a/drivers/clk/meson/meson-eeclk.c b/drivers/clk/meson/meson-eeclk.c index 8d5a5dab955a85c5ef7042d887def12cda1de439..0e5e6b57eb20e37c1082fa23f25f9495c44f565f 100644 --- a/drivers/clk/meson/meson-eeclk.c +++ b/drivers/clk/meson/meson-eeclk.c @@ -18,6 +18,7 @@ int meson_eeclkc_probe(struct platform_device *pdev) { const struct meson_eeclkc_data *data; struct device *dev = &pdev->dev; + struct device_node *np; struct regmap *map; int ret, i; @@ -26,7 +27,9 @@ int meson_eeclkc_probe(struct platform_device *pdev) return -EINVAL; /* Get the hhi system controller node */ - map = syscon_node_to_regmap(of_get_parent(dev->of_node)); + np = of_get_parent(dev->of_node); + map = syscon_node_to_regmap(np); + of_node_put(np); if (IS_ERR(map)) { dev_err(dev, "failed to get HHI regmap\n"); diff --git a/drivers/clk/meson/meson8b.c b/drivers/clk/meson/meson8b.c index 862f0756b50f0c1f3ae5e1cc29ec9cf1daa470ec..1da9d212f8b77f55e25982138eefc5d185dd6f64 100644 --- a/drivers/clk/meson/meson8b.c +++ b/drivers/clk/meson/meson8b.c @@ -3735,13 +3735,16 @@ static void __init meson8b_clkc_init_common(struct device_node *np, struct clk_hw_onecell_data *clk_hw_onecell_data) { struct meson8b_clk_reset *rstc; + struct device_node *parent_np; const char *notifier_clk_name; struct clk *notifier_clk; void __iomem *clk_base; struct regmap *map; int i, ret; - map = syscon_node_to_regmap(of_get_parent(np)); + parent_np = of_get_parent(np); + map = syscon_node_to_regmap(parent_np); + of_node_put(parent_np); if (IS_ERR(map)) { pr_info("failed to get HHI regmap - Trying obsolete regs\n"); diff --git a/drivers/clk/qcom/apss-ipq6018.c b/drivers/clk/qcom/apss-ipq6018.c index d78ff2f310bfadc69e64bc3d3f8fbe17ace4fe86..b5d93657e1ee32fb295906b2b9a05f682adb497b 100644 --- a/drivers/clk/qcom/apss-ipq6018.c +++ b/drivers/clk/qcom/apss-ipq6018.c @@ -57,7 +57,7 @@ static struct clk_branch apcs_alias0_core_clk = { .parent_hws = (const struct clk_hw *[]){ &apcs_alias0_clk_src.clkr.hw }, .num_parents = 1, - .flags = CLK_SET_RATE_PARENT, + .flags = CLK_SET_RATE_PARENT | CLK_IS_CRITICAL, .ops = &clk_branch2_ops, }, }, diff --git a/drivers/clk/sprd/common.c b/drivers/clk/sprd/common.c index d620bbbcdfc88eeb77446b8f1ce267e75103a917..ce81e4087a8fce2e8d2239e6d706de7f33b24c7d 100644 --- a/drivers/clk/sprd/common.c +++ b/drivers/clk/sprd/common.c @@ -41,7 +41,7 @@ int sprd_clk_regmap_init(struct platform_device *pdev, { void __iomem *base; struct device *dev = &pdev->dev; - struct device_node *node = dev->of_node; + struct device_node *node = dev->of_node, *np; struct regmap *regmap; if (of_find_property(node, "sprd,syscon", NULL)) { @@ -50,9 +50,10 @@ int sprd_clk_regmap_init(struct platform_device *pdev, pr_err("%s: failed to get syscon regmap\n", __func__); return PTR_ERR(regmap); } - } else if (of_device_is_compatible(of_get_parent(dev->of_node), - "syscon")) { - regmap = device_node_to_regmap(of_get_parent(dev->of_node)); + } else if (of_device_is_compatible(np = of_get_parent(node), "syscon") || + (of_node_put(np), 0)) { + regmap = device_node_to_regmap(np); + of_node_put(np); if (IS_ERR(regmap)) { dev_err(dev, "failed to get regmap from its parent.\n"); return PTR_ERR(regmap); diff --git a/drivers/clk/tegra/clk-tegra114.c b/drivers/clk/tegra/clk-tegra114.c index bc9e47a4cb60ac02e4e2c22d1331aaa1bdd8bea1..4e2b26e3e573875b4ce9578a436914ddd51ebffb 100644 --- a/drivers/clk/tegra/clk-tegra114.c +++ b/drivers/clk/tegra/clk-tegra114.c @@ -1317,6 +1317,7 @@ static void __init tegra114_clock_init(struct device_node *np) } pmc_base = of_iomap(node, 0); + of_node_put(node); if (!pmc_base) { pr_err("Can't map pmc registers\n"); WARN_ON(1); diff --git a/drivers/clk/tegra/clk-tegra20.c b/drivers/clk/tegra/clk-tegra20.c index 3efc651b42e3acd4d4f009d187cbd9dfe421f6fe..d60ee6e318a55105b237fc6d8aeda58f025a9a40 100644 --- a/drivers/clk/tegra/clk-tegra20.c +++ b/drivers/clk/tegra/clk-tegra20.c @@ -1128,6 +1128,7 @@ static void __init tegra20_clock_init(struct device_node *np) } pmc_base = of_iomap(node, 0); + of_node_put(node); if (!pmc_base) { pr_err("Can't map pmc registers\n"); BUG(); diff --git a/drivers/clk/tegra/clk-tegra210.c b/drivers/clk/tegra/clk-tegra210.c index 68cbb98af567dd53e0429dbbbe91198d7f74c291..1a0016d07f88c2b4c0f1e34ea9885167c0809ccf 100644 --- a/drivers/clk/tegra/clk-tegra210.c +++ b/drivers/clk/tegra/clk-tegra210.c @@ -3697,6 +3697,7 @@ static void __init tegra210_clock_init(struct device_node *np) } pmc_base = of_iomap(node, 0); + of_node_put(node); if (!pmc_base) { pr_err("Can't map pmc registers\n"); WARN_ON(1); diff --git a/drivers/clk/ti/clk-dra7-atl.c b/drivers/clk/ti/clk-dra7-atl.c index 8d4c08b034bdde50e77b60bd15cacba7860698b2..e2e59d78c173f8c0b5690a5931ac420f6f8261a5 100644 --- a/drivers/clk/ti/clk-dra7-atl.c +++ b/drivers/clk/ti/clk-dra7-atl.c @@ -251,14 +251,16 @@ static int of_dra7_atl_clk_probe(struct platform_device *pdev) if (rc) { pr_err("%s: failed to lookup atl clock %d\n", __func__, i); - return -EINVAL; + ret = -EINVAL; + goto pm_put; } clk = of_clk_get_from_provider(&clkspec); if (IS_ERR(clk)) { pr_err("%s: failed to get atl clock %d from provider\n", __func__, i); - return PTR_ERR(clk); + ret = PTR_ERR(clk); + goto pm_put; } cdesc = to_atl_desc(__clk_get_hw(clk)); @@ -291,8 +293,9 @@ static int of_dra7_atl_clk_probe(struct platform_device *pdev) if (cdesc->enabled) atl_clk_enable(__clk_get_hw(clk)); } - pm_runtime_put_sync(cinfo->dev); +pm_put: + pm_runtime_put_sync(cinfo->dev); return ret; } diff --git a/drivers/clk/zynqmp/clkc.c b/drivers/clk/zynqmp/clkc.c index db8d0d7161ce2cf233925057f96e7013a38f8925..9c82ae240c407da78b4ae69a131f74012d48c288 100644 --- a/drivers/clk/zynqmp/clkc.c +++ b/drivers/clk/zynqmp/clkc.c @@ -687,6 +687,13 @@ static void zynqmp_get_clock_info(void) FIELD_PREP(CLK_ATTR_NODE_INDEX, i); zynqmp_pm_clock_get_name(clock[i].clk_id, &name); + + /* + * Terminate with NULL character in case name provided by firmware + * is longer and truncated due to size limit. + */ + name.name[sizeof(name.name) - 1] = '\0'; + if (!strcmp(name.name, RESERVED_CLK_NAME)) continue; strncpy(clock[i].clk_name, name.name, MAX_NAME_LEN); diff --git a/drivers/clk/zynqmp/pll.c b/drivers/clk/zynqmp/pll.c index abe6afbf3407b358bb4aab4777a3f042c7baa098..2ae7f9129b07abe268b4632f7045ebaef5cf3d6a 100644 --- a/drivers/clk/zynqmp/pll.c +++ b/drivers/clk/zynqmp/pll.c @@ -99,26 +99,25 @@ static long zynqmp_pll_round_rate(struct clk_hw *hw, unsigned long rate, unsigned long *prate) { u32 fbdiv; - long rate_div, f; + u32 mult, div; - /* Enable the fractional mode if needed */ - rate_div = (rate * FRAC_DIV) / *prate; - f = rate_div % FRAC_DIV; - if (f) { - if (rate > PS_PLL_VCO_MAX) { - fbdiv = rate / PS_PLL_VCO_MAX; - rate = rate / (fbdiv + 1); - } - if (rate < PS_PLL_VCO_MIN) { - fbdiv = DIV_ROUND_UP(PS_PLL_VCO_MIN, rate); - rate = rate * fbdiv; - } - return rate; + /* Let rate fall inside the range PS_PLL_VCO_MIN ~ PS_PLL_VCO_MAX */ + if (rate > PS_PLL_VCO_MAX) { + div = DIV_ROUND_UP(rate, PS_PLL_VCO_MAX); + rate = rate / div; + } + if (rate < PS_PLL_VCO_MIN) { + mult = DIV_ROUND_UP(PS_PLL_VCO_MIN, rate); + rate = rate * mult; } fbdiv = DIV_ROUND_CLOSEST(rate, *prate); - fbdiv = clamp_t(u32, fbdiv, PLL_FBDIV_MIN, PLL_FBDIV_MAX); - return *prate * fbdiv; + if (fbdiv < PLL_FBDIV_MIN || fbdiv > PLL_FBDIV_MAX) { + fbdiv = clamp_t(u32, fbdiv, PLL_FBDIV_MIN, PLL_FBDIV_MAX); + rate = *prate * fbdiv; + } + + return rate; } /** diff --git a/drivers/counter/microchip-tcb-capture.c b/drivers/counter/microchip-tcb-capture.c index 710acc0a37044c101efbff1aecd0eb78aecf08b7..85fbbac06d3142147d9cda7bbac6f85840b02221 100644 --- a/drivers/counter/microchip-tcb-capture.c +++ b/drivers/counter/microchip-tcb-capture.c @@ -29,7 +29,6 @@ struct mchp_tc_data { int qdec_mode; int num_channels; int channel[2]; - bool trig_inverted; }; enum mchp_tc_count_function { @@ -163,7 +162,7 @@ static int mchp_tc_count_signal_read(struct counter_device *counter, regmap_read(priv->regmap, ATMEL_TC_REG(priv->channel[0], SR), &sr); - if (priv->trig_inverted) + if (signal->id == 1) sigstatus = (sr & ATMEL_TC_MTIOB); else sigstatus = (sr & ATMEL_TC_MTIOA); @@ -181,6 +180,17 @@ static int mchp_tc_count_action_get(struct counter_device *counter, struct mchp_tc_data *const priv = counter->priv; u32 cmr; + if (priv->qdec_mode) { + *action = COUNTER_SYNAPSE_ACTION_BOTH_EDGES; + return 0; + } + + /* Only TIOA signal is evaluated in non-QDEC mode */ + if (synapse->signal->id != 0) { + *action = COUNTER_SYNAPSE_ACTION_NONE; + return 0; + } + regmap_read(priv->regmap, ATMEL_TC_REG(priv->channel[0], CMR), &cmr); switch (cmr & ATMEL_TC_ETRGEDG) { @@ -209,8 +219,8 @@ static int mchp_tc_count_action_set(struct counter_device *counter, struct mchp_tc_data *const priv = counter->priv; u32 edge = ATMEL_TC_ETRGEDG_NONE; - /* QDEC mode is rising edge only */ - if (priv->qdec_mode) + /* QDEC mode is rising edge only; only TIOA handled in non-QDEC mode */ + if (priv->qdec_mode || synapse->signal->id != 0) return -EINVAL; switch (action) { diff --git a/drivers/cpufreq/qcom-cpufreq-nvmem.c b/drivers/cpufreq/qcom-cpufreq-nvmem.c index 7fdd30e92e42973bfb549500f77a06a4638fe9b4..9b3d24721d7b2894bbfa1bb138201b7e8a3d04df 100644 --- a/drivers/cpufreq/qcom-cpufreq-nvmem.c +++ b/drivers/cpufreq/qcom-cpufreq-nvmem.c @@ -215,6 +215,7 @@ static int qcom_cpufreq_krait_name_version(struct device *cpu_dev, int speed = 0, pvs = 0, pvs_ver = 0; u8 *speedbin; size_t len; + int ret = 0; speedbin = nvmem_cell_read(speedbin_nvmem, &len); @@ -232,7 +233,8 @@ static int qcom_cpufreq_krait_name_version(struct device *cpu_dev, break; default: dev_err(cpu_dev, "Unable to read nvmem data. Defaulting to 0!\n"); - return -ENODEV; + ret = -ENODEV; + goto len_error; } snprintf(*pvs_name, sizeof("speedXX-pvsXX-vXX"), "speed%d-pvs%d-v%d", @@ -240,8 +242,9 @@ static int qcom_cpufreq_krait_name_version(struct device *cpu_dev, drv->versions = (1 << speed); +len_error: kfree(speedbin); - return 0; + return ret; } static const struct qcom_cpufreq_match_data match_data_kryo = { @@ -264,7 +267,8 @@ static int qcom_cpufreq_probe(struct platform_device *pdev) struct nvmem_cell *speedbin_nvmem; struct device_node *np; struct device *cpu_dev; - char *pvs_name = "speedXX-pvsXX-vXX"; + char pvs_name_buffer[] = "speedXX-pvsXX-vXX"; + char *pvs_name = pvs_name_buffer; unsigned cpu; const struct of_device_id *match; int ret; diff --git a/drivers/cpuidle/cpuidle-psci.c b/drivers/cpuidle/cpuidle-psci.c index efc063ffc683a13622bf861d07fe2bfb861b3870..95ec4a688aa7611f36c37c5f9b704a781b647f12 100644 --- a/drivers/cpuidle/cpuidle-psci.c +++ b/drivers/cpuidle/cpuidle-psci.c @@ -68,10 +68,12 @@ static int __psci_enter_domain_idle_state(struct cpuidle_device *dev, if (ret) return -1; - trace_android_vh_cpuidle_psci_enter(dev, s2idle); /* Do runtime PM to manage a hierarchical CPU toplogy. */ rcu_irq_enter_irqson(); + + trace_android_vh_cpuidle_psci_enter(dev, s2idle); + if (s2idle) dev_pm_genpd_suspend(pd_dev); else @@ -89,10 +91,11 @@ static int __psci_enter_domain_idle_state(struct cpuidle_device *dev, dev_pm_genpd_resume(pd_dev); else pm_runtime_get_sync(pd_dev); - rcu_irq_exit_irqson(); trace_android_vh_cpuidle_psci_exit(dev, s2idle); + rcu_irq_exit_irqson(); + cpu_pm_exit(); /* Clear the domain state to start fresh when back from idle. */ diff --git a/drivers/crypto/cavium/cpt/cptpf_main.c b/drivers/crypto/cavium/cpt/cptpf_main.c index 7819490274512635a9c0323fc3dc6229c3d39c72..d9362199423f2d0b77ef181d0a983c1532373c66 100644 --- a/drivers/crypto/cavium/cpt/cptpf_main.c +++ b/drivers/crypto/cavium/cpt/cptpf_main.c @@ -254,6 +254,7 @@ static int cpt_ucode_load_fw(struct cpt_device *cpt, const u8 *fw, bool is_ae) const struct firmware *fw_entry; struct device *dev = &cpt->pdev->dev; struct ucode_header *ucode; + unsigned int code_length; struct microcode *mcode; int j, ret = 0; @@ -264,11 +265,12 @@ static int cpt_ucode_load_fw(struct cpt_device *cpt, const u8 *fw, bool is_ae) ucode = (struct ucode_header *)fw_entry->data; mcode = &cpt->mcode[cpt->next_mc_idx]; memcpy(mcode->version, (u8 *)fw_entry->data, CPT_UCODE_VERSION_SZ); - mcode->code_size = ntohl(ucode->code_length) * 2; - if (!mcode->code_size) { + code_length = ntohl(ucode->code_length); + if (code_length == 0 || code_length >= INT_MAX / 2) { ret = -EINVAL; goto fw_release; } + mcode->code_size = code_length * 2; mcode->is_ae = is_ae; mcode->core_mask = 0ULL; diff --git a/drivers/crypto/ccp/ccp-dmaengine.c b/drivers/crypto/ccp/ccp-dmaengine.c index b3eea329f840fbc974aed0b93c2412c11efd9895..b9299defb431d5cf1a98e855c66c5ca02fc174b7 100644 --- a/drivers/crypto/ccp/ccp-dmaengine.c +++ b/drivers/crypto/ccp/ccp-dmaengine.c @@ -642,6 +642,10 @@ static void ccp_dma_release(struct ccp_device *ccp) for (i = 0; i < ccp->cmd_q_count; i++) { chan = ccp->ccp_dma_chan + i; dma_chan = &chan->dma_chan; + + if (dma_chan->client_count) + dma_release_channel(dma_chan); + tasklet_kill(&chan->cleanup_tasklet); list_del_rcu(&dma_chan->device_node); } @@ -767,8 +771,8 @@ void ccp_dmaengine_unregister(struct ccp_device *ccp) if (!dmaengine) return; - dma_async_device_unregister(dma_dev); ccp_dma_release(ccp); + dma_async_device_unregister(dma_dev); kmem_cache_destroy(ccp->dma_desc_cache); kmem_cache_destroy(ccp->dma_cmd_cache); diff --git a/drivers/crypto/hisilicon/zip/zip_crypto.c b/drivers/crypto/hisilicon/zip/zip_crypto.c index 08b4660b014c6f24b1689865956e55e32059ba62..5db7cdea994aeb4c2615eaba065153a7af477caa 100644 --- a/drivers/crypto/hisilicon/zip/zip_crypto.c +++ b/drivers/crypto/hisilicon/zip/zip_crypto.c @@ -107,12 +107,12 @@ static int sgl_sge_nr_set(const char *val, const struct kernel_param *kp) if (ret || n == 0 || n > HISI_ACC_SGL_SGE_NR_MAX) return -EINVAL; - return param_set_int(val, kp); + return param_set_ushort(val, kp); } static const struct kernel_param_ops sgl_sge_nr_ops = { .set = sgl_sge_nr_set, - .get = param_get_int, + .get = param_get_ushort, }; static u16 sgl_sge_nr = HZIP_SGL_SGE_NR; diff --git a/drivers/crypto/inside-secure/safexcel_hash.c b/drivers/crypto/inside-secure/safexcel_hash.c index b2d5f0aa4243efbd953163f35a3ebb42d2e69946..31515c63bcfe5578b2acc81e8de156088c521faa 100644 --- a/drivers/crypto/inside-secure/safexcel_hash.c +++ b/drivers/crypto/inside-secure/safexcel_hash.c @@ -382,7 +382,7 @@ static int safexcel_ahash_send_req(struct crypto_async_request *async, int ring, u32 x; x = ipad[i] ^ ipad[i + 4]; - cache[i] ^= swab(x); + cache[i] ^= swab32(x); } } cache_len = AES_BLOCK_SIZE; @@ -820,7 +820,7 @@ static int safexcel_ahash_final(struct ahash_request *areq) u32 *result = (void *)areq->result; /* K3 */ - result[i] = swab(ctx->base.ipad.word[i + 4]); + result[i] = swab32(ctx->base.ipad.word[i + 4]); } areq->result[0] ^= 0x80; // 10- padding crypto_cipher_encrypt_one(ctx->kaes, areq->result, areq->result); @@ -2105,7 +2105,7 @@ static int safexcel_xcbcmac_setkey(struct crypto_ahash *tfm, const u8 *key, crypto_cipher_encrypt_one(ctx->kaes, (u8 *)key_tmp + AES_BLOCK_SIZE, "\x3\x3\x3\x3\x3\x3\x3\x3\x3\x3\x3\x3\x3\x3\x3\x3"); for (i = 0; i < 3 * AES_BLOCK_SIZE / sizeof(u32); i++) - ctx->base.ipad.word[i] = swab(key_tmp[i]); + ctx->base.ipad.word[i] = swab32(key_tmp[i]); crypto_cipher_clear_flags(ctx->kaes, CRYPTO_TFM_REQ_MASK); crypto_cipher_set_flags(ctx->kaes, crypto_ahash_get_flags(tfm) & @@ -2188,7 +2188,7 @@ static int safexcel_cmac_setkey(struct crypto_ahash *tfm, const u8 *key, return ret; for (i = 0; i < len / sizeof(u32); i++) - ctx->base.ipad.word[i + 8] = swab(aes.key_enc[i]); + ctx->base.ipad.word[i + 8] = swab32(aes.key_enc[i]); /* precompute the CMAC key material */ crypto_cipher_clear_flags(ctx->kaes, CRYPTO_TFM_REQ_MASK); diff --git a/drivers/crypto/marvell/octeontx/otx_cptpf_ucode.c b/drivers/crypto/marvell/octeontx/otx_cptpf_ucode.c index 40b482198ebc566c73f19bcd1fdce00ea82ab6ba..a765eefb18c2fac7942ceca21d8aa10b9c4633e9 100644 --- a/drivers/crypto/marvell/octeontx/otx_cptpf_ucode.c +++ b/drivers/crypto/marvell/octeontx/otx_cptpf_ucode.c @@ -286,6 +286,7 @@ static int process_tar_file(struct device *dev, struct tar_ucode_info_t *tar_info; struct otx_cpt_ucode_hdr *ucode_hdr; int ucode_type, ucode_size; + unsigned int code_length; /* * If size is less than microcode header size then don't report @@ -303,7 +304,13 @@ static int process_tar_file(struct device *dev, if (get_ucode_type(ucode_hdr, &ucode_type)) return 0; - ucode_size = ntohl(ucode_hdr->code_length) * 2; + code_length = ntohl(ucode_hdr->code_length); + if (code_length >= INT_MAX / 2) { + dev_err(dev, "Invalid code_length %u\n", code_length); + return -EINVAL; + } + + ucode_size = code_length * 2; if (!ucode_size || (size < round_up(ucode_size, 16) + sizeof(struct otx_cpt_ucode_hdr) + OTX_CPT_UCODE_SIGN_LEN)) { dev_err(dev, "Ucode %s invalid size\n", filename); @@ -886,6 +893,7 @@ static int ucode_load(struct device *dev, struct otx_cpt_ucode *ucode, { struct otx_cpt_ucode_hdr *ucode_hdr; const struct firmware *fw; + unsigned int code_length; int ret; set_ucode_filename(ucode, ucode_filename); @@ -896,7 +904,13 @@ static int ucode_load(struct device *dev, struct otx_cpt_ucode *ucode, ucode_hdr = (struct otx_cpt_ucode_hdr *) fw->data; memcpy(ucode->ver_str, ucode_hdr->ver_str, OTX_CPT_UCODE_VER_STR_SZ); ucode->ver_num = ucode_hdr->ver_num; - ucode->size = ntohl(ucode_hdr->code_length) * 2; + code_length = ntohl(ucode_hdr->code_length); + if (code_length >= INT_MAX / 2) { + dev_err(dev, "Ucode invalid code_length %u\n", code_length); + ret = -EINVAL; + goto release_fw; + } + ucode->size = code_length * 2; if (!ucode->size || (fw->size < round_up(ucode->size, 16) + sizeof(struct otx_cpt_ucode_hdr) + OTX_CPT_UCODE_SIGN_LEN)) { dev_err(dev, "Ucode %s invalid size\n", ucode_filename); diff --git a/drivers/crypto/qat/qat_common/qat_algs.c b/drivers/crypto/qat/qat_common/qat_algs.c index b939f0099c12efde6b8af08115df001b38880cf1..9f6966648ca2d33216e74844162c577ed6d84c30 100644 --- a/drivers/crypto/qat/qat_common/qat_algs.c +++ b/drivers/crypto/qat/qat_common/qat_algs.c @@ -35,19 +35,6 @@ static DEFINE_MUTEX(algs_lock); static unsigned int active_devs; -struct qat_alg_buf { - u32 len; - u32 resrvd; - u64 addr; -} __packed; - -struct qat_alg_buf_list { - u64 resrvd; - u32 num_bufs; - u32 num_mapped_bufs; - struct qat_alg_buf bufers[]; -} __packed __aligned(64); - /* Common content descriptor */ struct qat_alg_cd { union { @@ -638,14 +625,20 @@ static void qat_alg_free_bufl(struct qat_crypto_instance *inst, dma_addr_t blpout = qat_req->buf.bloutp; size_t sz = qat_req->buf.sz; size_t sz_out = qat_req->buf.sz_out; + int bl_dma_dir; int i; + bl_dma_dir = blp != blpout ? DMA_TO_DEVICE : DMA_BIDIRECTIONAL; + for (i = 0; i < bl->num_bufs; i++) dma_unmap_single(dev, bl->bufers[i].addr, - bl->bufers[i].len, DMA_BIDIRECTIONAL); + bl->bufers[i].len, bl_dma_dir); dma_unmap_single(dev, blp, sz, DMA_TO_DEVICE); - kfree(bl); + + if (!qat_req->buf.sgl_src_valid) + kfree(bl); + if (blp != blpout) { /* If out of place operation dma unmap only data */ int bufless = blout->num_bufs - blout->num_mapped_bufs; @@ -653,10 +646,12 @@ static void qat_alg_free_bufl(struct qat_crypto_instance *inst, for (i = bufless; i < blout->num_bufs; i++) { dma_unmap_single(dev, blout->bufers[i].addr, blout->bufers[i].len, - DMA_BIDIRECTIONAL); + DMA_FROM_DEVICE); } dma_unmap_single(dev, blpout, sz_out, DMA_TO_DEVICE); - kfree(blout); + + if (!qat_req->buf.sgl_dst_valid) + kfree(blout); } } @@ -670,26 +665,34 @@ static int qat_alg_sgl_to_bufl(struct qat_crypto_instance *inst, int n = sg_nents(sgl); struct qat_alg_buf_list *bufl; struct qat_alg_buf_list *buflout = NULL; - dma_addr_t blp; - dma_addr_t bloutp; + dma_addr_t blp = DMA_MAPPING_ERROR; + dma_addr_t bloutp = DMA_MAPPING_ERROR; struct scatterlist *sg; - size_t sz_out, sz = struct_size(bufl, bufers, n + 1); + size_t sz_out, sz = struct_size(bufl, bufers, n); + int node = dev_to_node(&GET_DEV(inst->accel_dev)); + int bufl_dma_dir; if (unlikely(!n)) return -EINVAL; - bufl = kzalloc_node(sz, GFP_ATOMIC, - dev_to_node(&GET_DEV(inst->accel_dev))); - if (unlikely(!bufl)) - return -ENOMEM; + qat_req->buf.sgl_src_valid = false; + qat_req->buf.sgl_dst_valid = false; + + if (n > QAT_MAX_BUFF_DESC) { + bufl = kzalloc_node(sz, GFP_ATOMIC, node); + if (unlikely(!bufl)) + return -ENOMEM; + } else { + bufl = &qat_req->buf.sgl_src.sgl_hdr; + memset(bufl, 0, sizeof(struct qat_alg_buf_list)); + qat_req->buf.sgl_src_valid = true; + } + + bufl_dma_dir = sgl != sglout ? DMA_TO_DEVICE : DMA_BIDIRECTIONAL; for_each_sg(sgl, sg, n, i) bufl->bufers[i].addr = DMA_MAPPING_ERROR; - blp = dma_map_single(dev, bufl, sz, DMA_TO_DEVICE); - if (unlikely(dma_mapping_error(dev, blp))) - goto err_in; - for_each_sg(sgl, sg, n, i) { int y = sg_nctr; @@ -698,13 +701,16 @@ static int qat_alg_sgl_to_bufl(struct qat_crypto_instance *inst, bufl->bufers[y].addr = dma_map_single(dev, sg_virt(sg), sg->length, - DMA_BIDIRECTIONAL); + bufl_dma_dir); bufl->bufers[y].len = sg->length; if (unlikely(dma_mapping_error(dev, bufl->bufers[y].addr))) goto err_in; sg_nctr++; } bufl->num_bufs = sg_nctr; + blp = dma_map_single(dev, bufl, sz, DMA_TO_DEVICE); + if (unlikely(dma_mapping_error(dev, blp))) + goto err_in; qat_req->buf.bl = bufl; qat_req->buf.blp = blp; qat_req->buf.sz = sz; @@ -713,20 +719,23 @@ static int qat_alg_sgl_to_bufl(struct qat_crypto_instance *inst, struct qat_alg_buf *bufers; n = sg_nents(sglout); - sz_out = struct_size(buflout, bufers, n + 1); + sz_out = struct_size(buflout, bufers, n); sg_nctr = 0; - buflout = kzalloc_node(sz_out, GFP_ATOMIC, - dev_to_node(&GET_DEV(inst->accel_dev))); - if (unlikely(!buflout)) - goto err_in; + + if (n > QAT_MAX_BUFF_DESC) { + buflout = kzalloc_node(sz_out, GFP_ATOMIC, node); + if (unlikely(!buflout)) + goto err_in; + } else { + buflout = &qat_req->buf.sgl_dst.sgl_hdr; + memset(buflout, 0, sizeof(struct qat_alg_buf_list)); + qat_req->buf.sgl_dst_valid = true; + } bufers = buflout->bufers; for_each_sg(sglout, sg, n, i) bufers[i].addr = DMA_MAPPING_ERROR; - bloutp = dma_map_single(dev, buflout, sz_out, DMA_TO_DEVICE); - if (unlikely(dma_mapping_error(dev, bloutp))) - goto err_out; for_each_sg(sglout, sg, n, i) { int y = sg_nctr; @@ -735,7 +744,7 @@ static int qat_alg_sgl_to_bufl(struct qat_crypto_instance *inst, bufers[y].addr = dma_map_single(dev, sg_virt(sg), sg->length, - DMA_BIDIRECTIONAL); + DMA_FROM_DEVICE); if (unlikely(dma_mapping_error(dev, bufers[y].addr))) goto err_out; bufers[y].len = sg->length; @@ -743,6 +752,9 @@ static int qat_alg_sgl_to_bufl(struct qat_crypto_instance *inst, } buflout->num_bufs = sg_nctr; buflout->num_mapped_bufs = sg_nctr; + bloutp = dma_map_single(dev, buflout, sz_out, DMA_TO_DEVICE); + if (unlikely(dma_mapping_error(dev, bloutp))) + goto err_out; qat_req->buf.blout = buflout; qat_req->buf.bloutp = bloutp; qat_req->buf.sz_out = sz_out; @@ -754,27 +766,32 @@ static int qat_alg_sgl_to_bufl(struct qat_crypto_instance *inst, return 0; err_out: + if (!dma_mapping_error(dev, bloutp)) + dma_unmap_single(dev, bloutp, sz_out, DMA_TO_DEVICE); + n = sg_nents(sglout); for (i = 0; i < n; i++) if (!dma_mapping_error(dev, buflout->bufers[i].addr)) dma_unmap_single(dev, buflout->bufers[i].addr, buflout->bufers[i].len, - DMA_BIDIRECTIONAL); - if (!dma_mapping_error(dev, bloutp)) - dma_unmap_single(dev, bloutp, sz_out, DMA_TO_DEVICE); - kfree(buflout); + DMA_FROM_DEVICE); + + if (!qat_req->buf.sgl_dst_valid) + kfree(buflout); err_in: + if (!dma_mapping_error(dev, blp)) + dma_unmap_single(dev, blp, sz, DMA_TO_DEVICE); + n = sg_nents(sgl); for (i = 0; i < n; i++) if (!dma_mapping_error(dev, bufl->bufers[i].addr)) dma_unmap_single(dev, bufl->bufers[i].addr, bufl->bufers[i].len, - DMA_BIDIRECTIONAL); + bufl_dma_dir); - if (!dma_mapping_error(dev, blp)) - dma_unmap_single(dev, blp, sz, DMA_TO_DEVICE); - kfree(bufl); + if (!qat_req->buf.sgl_src_valid) + kfree(bufl); dev_err(dev, "Failed to map buf for dma\n"); return -ENOMEM; diff --git a/drivers/crypto/qat/qat_common/qat_crypto.h b/drivers/crypto/qat/qat_common/qat_crypto.h index 12682d1e9f5f3432db268e88617e0d147a402d72..5f9328201ba4695033057dee8c8543706ab1b6b5 100644 --- a/drivers/crypto/qat/qat_common/qat_crypto.h +++ b/drivers/crypto/qat/qat_common/qat_crypto.h @@ -20,6 +20,26 @@ struct qat_crypto_instance { atomic_t refctr; }; +#define QAT_MAX_BUFF_DESC 4 + +struct qat_alg_buf { + u32 len; + u32 resrvd; + u64 addr; +} __packed; + +struct qat_alg_buf_list { + u64 resrvd; + u32 num_bufs; + u32 num_mapped_bufs; + struct qat_alg_buf bufers[]; +} __packed; + +struct qat_alg_fixed_buf_list { + struct qat_alg_buf_list sgl_hdr; + struct qat_alg_buf descriptors[QAT_MAX_BUFF_DESC]; +} __packed __aligned(64); + struct qat_crypto_request_buffs { struct qat_alg_buf_list *bl; dma_addr_t blp; @@ -27,6 +47,10 @@ struct qat_crypto_request_buffs { dma_addr_t bloutp; size_t sz; size_t sz_out; + bool sgl_src_valid; + bool sgl_dst_valid; + struct qat_alg_fixed_buf_list sgl_src; + struct qat_alg_fixed_buf_list sgl_dst; }; struct qat_crypto_request; diff --git a/drivers/crypto/sahara.c b/drivers/crypto/sahara.c index d60679c79822469684c0a6f1d81ad631de253b37..2043dd061121715f08c0771ed5973d4fa91afc32 100644 --- a/drivers/crypto/sahara.c +++ b/drivers/crypto/sahara.c @@ -25,10 +25,10 @@ #include #include #include -#include #include #include #include +#include #define SHA_BUFFER_LEN PAGE_SIZE #define SAHARA_MAX_SHA_BLOCK_SIZE SHA256_BLOCK_SIZE @@ -195,7 +195,7 @@ struct sahara_dev { void __iomem *regs_base; struct clk *clk_ipg; struct clk *clk_ahb; - struct mutex queue_mutex; + spinlock_t queue_spinlock; struct task_struct *kthread; struct completion dma_completion; @@ -641,9 +641,9 @@ static int sahara_aes_crypt(struct skcipher_request *req, unsigned long mode) rctx->mode = mode; - mutex_lock(&dev->queue_mutex); + spin_lock_bh(&dev->queue_spinlock); err = crypto_enqueue_request(&dev->queue, &req->base); - mutex_unlock(&dev->queue_mutex); + spin_unlock_bh(&dev->queue_spinlock); wake_up_process(dev->kthread); @@ -1042,10 +1042,10 @@ static int sahara_queue_manage(void *data) do { __set_current_state(TASK_INTERRUPTIBLE); - mutex_lock(&dev->queue_mutex); + spin_lock_bh(&dev->queue_spinlock); backlog = crypto_get_backlog(&dev->queue); async_req = crypto_dequeue_request(&dev->queue); - mutex_unlock(&dev->queue_mutex); + spin_unlock_bh(&dev->queue_spinlock); if (backlog) backlog->complete(backlog, -EINPROGRESS); @@ -1091,9 +1091,9 @@ static int sahara_sha_enqueue(struct ahash_request *req, int last) rctx->first = 1; } - mutex_lock(&dev->queue_mutex); + spin_lock_bh(&dev->queue_spinlock); ret = crypto_enqueue_request(&dev->queue, &req->base); - mutex_unlock(&dev->queue_mutex); + spin_unlock_bh(&dev->queue_spinlock); wake_up_process(dev->kthread); @@ -1454,7 +1454,7 @@ static int sahara_probe(struct platform_device *pdev) crypto_init_queue(&dev->queue, SAHARA_QUEUE_LENGTH); - mutex_init(&dev->queue_mutex); + spin_lock_init(&dev->queue_spinlock); dev_ptr = dev; diff --git a/drivers/dma-buf/dma-heap.c b/drivers/dma-buf/dma-heap.c index 26d59b48f421cec0b206820f7fdde728a6c51436..53d8ee80a26d31699929cc34e251d2e177abc0e1 100644 --- a/drivers/dma-buf/dma-heap.c +++ b/drivers/dma-buf/dma-heap.c @@ -297,7 +297,7 @@ EXPORT_SYMBOL_GPL(dma_heap_get_name); struct dma_heap *dma_heap_add(const struct dma_heap_export_info *exp_info) { - struct dma_heap *heap, *err_ret; + struct dma_heap *heap, *h, *err_ret; unsigned int minor; int ret; @@ -311,15 +311,6 @@ struct dma_heap *dma_heap_add(const struct dma_heap_export_info *exp_info) return ERR_PTR(-EINVAL); } - /* check the name is unique */ - heap = dma_heap_find(exp_info->name); - if (heap) { - pr_err("dma_heap: Already registered heap named %s\n", - exp_info->name); - dma_heap_put(heap); - return ERR_PTR(-EINVAL); - } - heap = kzalloc(sizeof(*heap), GFP_KERNEL); if (!heap) return ERR_PTR(-ENOMEM); @@ -363,13 +354,27 @@ struct dma_heap *dma_heap_add(const struct dma_heap_export_info *exp_info) /* Make sure it doesn't disappear on us */ heap->heap_dev = get_device(heap->heap_dev); - /* Add heap to the list */ mutex_lock(&heap_list_lock); + /* check the name is unique */ + list_for_each_entry(h, &heap_list, list) { + if (!strcmp(h->name, exp_info->name)) { + mutex_unlock(&heap_list_lock); + pr_err("dma_heap: Already registered heap named %s\n", + exp_info->name); + err_ret = ERR_PTR(-EINVAL); + put_device(heap->heap_dev); + goto err3; + } + } + + /* Add heap to the list */ list_add(&heap->list, &heap_list); mutex_unlock(&heap_list_lock); return heap; +err3: + device_destroy(dma_heap_class, heap->heap_devt); err2: cdev_del(&heap->heap_cdev); err1: diff --git a/drivers/dma-buf/udmabuf.c b/drivers/dma-buf/udmabuf.c index b624f3d8f0e64091ee0ea57f4c4849714396ebac..e359c5c6c4df2572df6c70ed41ab44160ef1d300 100644 --- a/drivers/dma-buf/udmabuf.c +++ b/drivers/dma-buf/udmabuf.c @@ -118,17 +118,20 @@ static int begin_cpu_udmabuf(struct dma_buf *buf, { struct udmabuf *ubuf = buf->priv; struct device *dev = ubuf->device->this_device; + int ret = 0; if (!ubuf->sg) { ubuf->sg = get_sg_table(dev, buf, direction); - if (IS_ERR(ubuf->sg)) - return PTR_ERR(ubuf->sg); + if (IS_ERR(ubuf->sg)) { + ret = PTR_ERR(ubuf->sg); + ubuf->sg = NULL; + } } else { dma_sync_sg_for_cpu(dev, ubuf->sg->sgl, ubuf->sg->nents, direction); } - return 0; + return ret; } static int end_cpu_udmabuf(struct dma_buf *buf, diff --git a/drivers/dma/at_hdmac.c b/drivers/dma/at_hdmac.c index 7eaee5b705b1bf47bb7c78301550cd5751720ee2..6a4f9697b57425fad9b7aadf4c56140a55925ad2 100644 --- a/drivers/dma/at_hdmac.c +++ b/drivers/dma/at_hdmac.c @@ -237,6 +237,8 @@ static void atc_dostart(struct at_dma_chan *atchan, struct at_desc *first) ATC_SPIP_BOUNDARY(first->boundary)); channel_writel(atchan, DPIP, ATC_DPIP_HOLE(first->dst_hole) | ATC_DPIP_BOUNDARY(first->boundary)); + /* Don't allow CPU to reorder channel enable. */ + wmb(); dma_writel(atdma, CHER, atchan->mask); vdbg_dump_regs(atchan); @@ -297,7 +299,8 @@ static int atc_get_bytes_left(struct dma_chan *chan, dma_cookie_t cookie) struct at_desc *desc_first = atc_first_active(atchan); struct at_desc *desc; int ret; - u32 ctrla, dscr, trials; + u32 ctrla, dscr; + unsigned int i; /* * If the cookie doesn't match to the currently running transfer then @@ -367,7 +370,7 @@ static int atc_get_bytes_left(struct dma_chan *chan, dma_cookie_t cookie) dscr = channel_readl(atchan, DSCR); rmb(); /* ensure DSCR is read before CTRLA */ ctrla = channel_readl(atchan, CTRLA); - for (trials = 0; trials < ATC_MAX_DSCR_TRIALS; ++trials) { + for (i = 0; i < ATC_MAX_DSCR_TRIALS; ++i) { u32 new_dscr; rmb(); /* ensure DSCR is read after CTRLA */ @@ -393,7 +396,7 @@ static int atc_get_bytes_left(struct dma_chan *chan, dma_cookie_t cookie) rmb(); /* ensure DSCR is read before CTRLA */ ctrla = channel_readl(atchan, CTRLA); } - if (unlikely(trials >= ATC_MAX_DSCR_TRIALS)) + if (unlikely(i == ATC_MAX_DSCR_TRIALS)) return -ETIMEDOUT; /* for the first descriptor we can be more accurate */ @@ -443,18 +446,6 @@ atc_chain_complete(struct at_dma_chan *atchan, struct at_desc *desc) if (!atc_chan_is_cyclic(atchan)) dma_cookie_complete(txd); - /* If the transfer was a memset, free our temporary buffer */ - if (desc->memset_buffer) { - dma_pool_free(atdma->memset_pool, desc->memset_vaddr, - desc->memset_paddr); - desc->memset_buffer = false; - } - - /* move children to free_list */ - list_splice_init(&desc->tx_list, &atchan->free_list); - /* move myself to free_list */ - list_move(&desc->desc_node, &atchan->free_list); - spin_unlock_irqrestore(&atchan->lock, flags); dma_descriptor_unmap(txd); @@ -464,42 +455,20 @@ atc_chain_complete(struct at_dma_chan *atchan, struct at_desc *desc) dmaengine_desc_get_callback_invoke(txd, NULL); dma_run_dependencies(txd); -} - -/** - * atc_complete_all - finish work for all transactions - * @atchan: channel to complete transactions for - * - * Eventually submit queued descriptors if any - * - * Assume channel is idle while calling this function - * Called with atchan->lock held and bh disabled - */ -static void atc_complete_all(struct at_dma_chan *atchan) -{ - struct at_desc *desc, *_desc; - LIST_HEAD(list); - unsigned long flags; - - dev_vdbg(chan2dev(&atchan->chan_common), "complete all\n"); spin_lock_irqsave(&atchan->lock, flags); - - /* - * Submit queued descriptors ASAP, i.e. before we go through - * the completed ones. - */ - if (!list_empty(&atchan->queue)) - atc_dostart(atchan, atc_first_queued(atchan)); - /* empty active_list now it is completed */ - list_splice_init(&atchan->active_list, &list); - /* empty queue list by moving descriptors (if any) to active_list */ - list_splice_init(&atchan->queue, &atchan->active_list); - + /* move children to free_list */ + list_splice_init(&desc->tx_list, &atchan->free_list); + /* add myself to free_list */ + list_add(&desc->desc_node, &atchan->free_list); spin_unlock_irqrestore(&atchan->lock, flags); - list_for_each_entry_safe(desc, _desc, &list, desc_node) - atc_chain_complete(atchan, desc); + /* If the transfer was a memset, free our temporary buffer */ + if (desc->memset_buffer) { + dma_pool_free(atdma->memset_pool, desc->memset_vaddr, + desc->memset_paddr); + desc->memset_buffer = false; + } } /** @@ -508,26 +477,28 @@ static void atc_complete_all(struct at_dma_chan *atchan) */ static void atc_advance_work(struct at_dma_chan *atchan) { + struct at_desc *desc; unsigned long flags; - int ret; dev_vdbg(chan2dev(&atchan->chan_common), "advance_work\n"); spin_lock_irqsave(&atchan->lock, flags); - ret = atc_chan_is_enabled(atchan); - spin_unlock_irqrestore(&atchan->lock, flags); - if (ret) - return; - - if (list_empty(&atchan->active_list) || - list_is_singular(&atchan->active_list)) - return atc_complete_all(atchan); + if (atc_chan_is_enabled(atchan) || list_empty(&atchan->active_list)) + return spin_unlock_irqrestore(&atchan->lock, flags); - atc_chain_complete(atchan, atc_first_active(atchan)); + desc = atc_first_active(atchan); + /* Remove the transfer node from the active list. */ + list_del_init(&desc->desc_node); + spin_unlock_irqrestore(&atchan->lock, flags); + atc_chain_complete(atchan, desc); /* advance work */ spin_lock_irqsave(&atchan->lock, flags); - atc_dostart(atchan, atc_first_active(atchan)); + if (!list_empty(&atchan->active_list)) { + desc = atc_first_queued(atchan); + list_move_tail(&desc->desc_node, &atchan->active_list); + atc_dostart(atchan, desc); + } spin_unlock_irqrestore(&atchan->lock, flags); } @@ -539,6 +510,7 @@ static void atc_advance_work(struct at_dma_chan *atchan) static void atc_handle_error(struct at_dma_chan *atchan) { struct at_desc *bad_desc; + struct at_desc *desc; struct at_desc *child; unsigned long flags; @@ -551,13 +523,12 @@ static void atc_handle_error(struct at_dma_chan *atchan) bad_desc = atc_first_active(atchan); list_del_init(&bad_desc->desc_node); - /* As we are stopped, take advantage to push queued descriptors - * in active_list */ - list_splice_init(&atchan->queue, atchan->active_list.prev); - /* Try to restart the controller */ - if (!list_empty(&atchan->active_list)) - atc_dostart(atchan, atc_first_active(atchan)); + if (!list_empty(&atchan->active_list)) { + desc = atc_first_queued(atchan); + list_move_tail(&desc->desc_node, &atchan->active_list); + atc_dostart(atchan, desc); + } /* * KERN_CRITICAL may seem harsh, but since this only happens @@ -672,19 +643,11 @@ static dma_cookie_t atc_tx_submit(struct dma_async_tx_descriptor *tx) spin_lock_irqsave(&atchan->lock, flags); cookie = dma_cookie_assign(tx); - if (list_empty(&atchan->active_list)) { - dev_vdbg(chan2dev(tx->chan), "tx_submit: started %u\n", - desc->txd.cookie); - atc_dostart(atchan, desc); - list_add_tail(&desc->desc_node, &atchan->active_list); - } else { - dev_vdbg(chan2dev(tx->chan), "tx_submit: queued %u\n", - desc->txd.cookie); - list_add_tail(&desc->desc_node, &atchan->queue); - } - + list_add_tail(&desc->desc_node, &atchan->queue); spin_unlock_irqrestore(&atchan->lock, flags); + dev_vdbg(chan2dev(tx->chan), "tx_submit: queued %u\n", + desc->txd.cookie); return cookie; } @@ -1418,11 +1381,8 @@ static int atc_terminate_all(struct dma_chan *chan) struct at_dma_chan *atchan = to_at_dma_chan(chan); struct at_dma *atdma = to_at_dma(chan->device); int chan_id = atchan->chan_common.chan_id; - struct at_desc *desc, *_desc; unsigned long flags; - LIST_HEAD(list); - dev_vdbg(chan2dev(chan), "%s\n", __func__); /* @@ -1441,19 +1401,15 @@ static int atc_terminate_all(struct dma_chan *chan) cpu_relax(); /* active_list entries will end up before queued entries */ - list_splice_init(&atchan->queue, &list); - list_splice_init(&atchan->active_list, &list); - - spin_unlock_irqrestore(&atchan->lock, flags); - - /* Flush all pending and queued descriptors */ - list_for_each_entry_safe(desc, _desc, &list, desc_node) - atc_chain_complete(atchan, desc); + list_splice_tail_init(&atchan->queue, &atchan->free_list); + list_splice_tail_init(&atchan->active_list, &atchan->free_list); clear_bit(ATC_IS_PAUSED, &atchan->status); /* if channel dedicated to cyclic operations, free it */ clear_bit(ATC_IS_CYCLIC, &atchan->status); + spin_unlock_irqrestore(&atchan->lock, flags); + return 0; } @@ -1508,20 +1464,26 @@ atc_tx_status(struct dma_chan *chan, } /** - * atc_issue_pending - try to finish work + * atc_issue_pending - takes the first transaction descriptor in the pending + * queue and starts the transfer. * @chan: target DMA channel */ static void atc_issue_pending(struct dma_chan *chan) { - struct at_dma_chan *atchan = to_at_dma_chan(chan); + struct at_dma_chan *atchan = to_at_dma_chan(chan); + struct at_desc *desc; + unsigned long flags; dev_vdbg(chan2dev(chan), "issue_pending\n"); - /* Not needed for cyclic transfers */ - if (atc_chan_is_cyclic(atchan)) - return; + spin_lock_irqsave(&atchan->lock, flags); + if (atc_chan_is_enabled(atchan) || list_empty(&atchan->queue)) + return spin_unlock_irqrestore(&atchan->lock, flags); - atc_advance_work(atchan); + desc = atc_first_queued(atchan); + list_move_tail(&desc->desc_node, &atchan->active_list); + atc_dostart(atchan, desc); + spin_unlock_irqrestore(&atchan->lock, flags); } /** @@ -1939,7 +1901,11 @@ static int __init at_dma_probe(struct platform_device *pdev) dma_has_cap(DMA_SLAVE, atdma->dma_common.cap_mask) ? "slave " : "", plat_dat->nr_channels); - dma_async_device_register(&atdma->dma_common); + err = dma_async_device_register(&atdma->dma_common); + if (err) { + dev_err(&pdev->dev, "Unable to register: %d.\n", err); + goto err_dma_async_device_register; + } /* * Do not return an error if the dmac node is not present in order to @@ -1959,6 +1925,7 @@ static int __init at_dma_probe(struct platform_device *pdev) err_of_dma_controller_register: dma_async_device_unregister(&atdma->dma_common); +err_dma_async_device_register: dma_pool_destroy(atdma->memset_pool); err_memset_pool_create: dma_pool_destroy(atdma->dma_desc_pool); diff --git a/drivers/dma/at_hdmac_regs.h b/drivers/dma/at_hdmac_regs.h index 80fc2fe8c77ea9be26dc84a18beaaad2198e429c..8dc82c7b1dcf0d1831bab7bff83b337521cf29fe 100644 --- a/drivers/dma/at_hdmac_regs.h +++ b/drivers/dma/at_hdmac_regs.h @@ -164,13 +164,13 @@ /* LLI == Linked List Item; aka DMA buffer descriptor */ struct at_lli { /* values that are not changed by hardware */ - dma_addr_t saddr; - dma_addr_t daddr; + u32 saddr; + u32 daddr; /* value that may get written back: */ - u32 ctrla; + u32 ctrla; /* more values that are not changed by hardware */ - u32 ctrlb; - dma_addr_t dscr; /* chain to next lli */ + u32 ctrlb; + u32 dscr; /* chain to next lli */ }; /** diff --git a/drivers/dma/hisi_dma.c b/drivers/dma/hisi_dma.c index 3e83769615d1cb71d335093aa2b8aeae276b5e0e..8f1651367310037cad4177e4066533e06a29d091 100644 --- a/drivers/dma/hisi_dma.c +++ b/drivers/dma/hisi_dma.c @@ -185,7 +185,8 @@ static void hisi_dma_reset_qp_point(struct hisi_dma_dev *hdma_dev, u32 index) hisi_dma_chan_write(hdma_dev->base, HISI_DMA_CQ_HEAD_PTR, index, 0); } -static void hisi_dma_reset_hw_chan(struct hisi_dma_chan *chan) +static void hisi_dma_reset_or_disable_hw_chan(struct hisi_dma_chan *chan, + bool disable) { struct hisi_dma_dev *hdma_dev = chan->hdma_dev; u32 index = chan->qp_num, tmp; @@ -206,8 +207,11 @@ static void hisi_dma_reset_hw_chan(struct hisi_dma_chan *chan) hisi_dma_do_reset(hdma_dev, index); hisi_dma_reset_qp_point(hdma_dev, index); hisi_dma_pause_dma(hdma_dev, index, false); - hisi_dma_enable_dma(hdma_dev, index, true); - hisi_dma_unmask_irq(hdma_dev, index); + + if (!disable) { + hisi_dma_enable_dma(hdma_dev, index, true); + hisi_dma_unmask_irq(hdma_dev, index); + } ret = readl_relaxed_poll_timeout(hdma_dev->base + HISI_DMA_Q_FSM_STS + index * HISI_DMA_OFFSET, tmp, @@ -223,7 +227,7 @@ static void hisi_dma_free_chan_resources(struct dma_chan *c) struct hisi_dma_chan *chan = to_hisi_dma_chan(c); struct hisi_dma_dev *hdma_dev = chan->hdma_dev; - hisi_dma_reset_hw_chan(chan); + hisi_dma_reset_or_disable_hw_chan(chan, false); vchan_free_chan_resources(&chan->vc); memset(chan->sq, 0, sizeof(struct hisi_dma_sqe) * hdma_dev->chan_depth); @@ -272,7 +276,6 @@ static void hisi_dma_start_transfer(struct hisi_dma_chan *chan) vd = vchan_next_desc(&chan->vc); if (!vd) { - dev_err(&hdma_dev->pdev->dev, "no issued task!\n"); chan->desc = NULL; return; } @@ -304,7 +307,7 @@ static void hisi_dma_issue_pending(struct dma_chan *c) spin_lock_irqsave(&chan->vc.lock, flags); - if (vchan_issue_pending(&chan->vc)) + if (vchan_issue_pending(&chan->vc) && !chan->desc) hisi_dma_start_transfer(chan); spin_unlock_irqrestore(&chan->vc.lock, flags); @@ -399,7 +402,7 @@ static void hisi_dma_enable_qp(struct hisi_dma_dev *hdma_dev, u32 qp_index) static void hisi_dma_disable_qp(struct hisi_dma_dev *hdma_dev, u32 qp_index) { - hisi_dma_reset_hw_chan(&hdma_dev->chan[qp_index]); + hisi_dma_reset_or_disable_hw_chan(&hdma_dev->chan[qp_index], true); } static void hisi_dma_enable_qps(struct hisi_dma_dev *hdma_dev) @@ -438,18 +441,15 @@ static irqreturn_t hisi_dma_irq(int irq, void *data) desc = chan->desc; cqe = chan->cq + chan->cq_head; if (desc) { + chan->cq_head = (chan->cq_head + 1) % hdma_dev->chan_depth; + hisi_dma_chan_write(hdma_dev->base, HISI_DMA_CQ_HEAD_PTR, + chan->qp_num, chan->cq_head); if (FIELD_GET(STATUS_MASK, cqe->w0) == STATUS_SUCC) { - chan->cq_head = (chan->cq_head + 1) % - hdma_dev->chan_depth; - hisi_dma_chan_write(hdma_dev->base, - HISI_DMA_CQ_HEAD_PTR, chan->qp_num, - chan->cq_head); vchan_cookie_complete(&desc->vd); + hisi_dma_start_transfer(chan); } else { dev_err(&hdma_dev->pdev->dev, "task error!\n"); } - - chan->desc = NULL; } spin_unlock_irqrestore(&chan->vc.lock, flags); diff --git a/drivers/dma/ioat/dma.c b/drivers/dma/ioat/dma.c index 37ff4ec7db76fd77f46a7d40de7f0013e52206f3..e2070df6cad287bda75386961060339eb1b15d30 100644 --- a/drivers/dma/ioat/dma.c +++ b/drivers/dma/ioat/dma.c @@ -656,7 +656,7 @@ static void __cleanup(struct ioatdma_chan *ioat_chan, dma_addr_t phys_complete) if (active - i == 0) { dev_dbg(to_dev(ioat_chan), "%s: cancel completion timeout\n", __func__); - mod_timer(&ioat_chan->timer, jiffies + IDLE_TIMEOUT); + mod_timer_pending(&ioat_chan->timer, jiffies + IDLE_TIMEOUT); } /* microsecond delay by sysfs variable per pending descriptor */ @@ -682,7 +682,7 @@ static void ioat_cleanup(struct ioatdma_chan *ioat_chan) if (chanerr & (IOAT_CHANERR_HANDLE_MASK | IOAT_CHANERR_RECOVER_MASK)) { - mod_timer(&ioat_chan->timer, jiffies + IDLE_TIMEOUT); + mod_timer_pending(&ioat_chan->timer, jiffies + IDLE_TIMEOUT); ioat_eh(ioat_chan); } } @@ -879,7 +879,7 @@ static void check_active(struct ioatdma_chan *ioat_chan) } if (test_and_clear_bit(IOAT_CHAN_ACTIVE, &ioat_chan->state)) - mod_timer(&ioat_chan->timer, jiffies + IDLE_TIMEOUT); + mod_timer_pending(&ioat_chan->timer, jiffies + IDLE_TIMEOUT); } static void ioat_reboot_chan(struct ioatdma_chan *ioat_chan) diff --git a/drivers/dma/mv_xor_v2.c b/drivers/dma/mv_xor_v2.c index 9b0d463f89bbd478ca594476c8532241d6750d6d..4800c596433ad7f6fbd30eedc41108d31cefaad4 100644 --- a/drivers/dma/mv_xor_v2.c +++ b/drivers/dma/mv_xor_v2.c @@ -899,6 +899,7 @@ static int mv_xor_v2_remove(struct platform_device *pdev) tasklet_kill(&xor_dev->irq_tasklet); clk_disable_unprepare(xor_dev->clk); + clk_disable_unprepare(xor_dev->reg_clk); return 0; } diff --git a/drivers/dma/mxs-dma.c b/drivers/dma/mxs-dma.c index 65f816b40c32807e07c90c0418ed91e3a83dd9d5..dc147cc2436e9e35566fffba413ba539baa9e05f 100644 --- a/drivers/dma/mxs-dma.c +++ b/drivers/dma/mxs-dma.c @@ -167,29 +167,11 @@ static struct mxs_dma_type mxs_dma_types[] = { } }; -static const struct platform_device_id mxs_dma_ids[] = { - { - .name = "imx23-dma-apbh", - .driver_data = (kernel_ulong_t) &mxs_dma_types[0], - }, { - .name = "imx23-dma-apbx", - .driver_data = (kernel_ulong_t) &mxs_dma_types[1], - }, { - .name = "imx28-dma-apbh", - .driver_data = (kernel_ulong_t) &mxs_dma_types[2], - }, { - .name = "imx28-dma-apbx", - .driver_data = (kernel_ulong_t) &mxs_dma_types[3], - }, { - /* end of list */ - } -}; - static const struct of_device_id mxs_dma_dt_ids[] = { - { .compatible = "fsl,imx23-dma-apbh", .data = &mxs_dma_ids[0], }, - { .compatible = "fsl,imx23-dma-apbx", .data = &mxs_dma_ids[1], }, - { .compatible = "fsl,imx28-dma-apbh", .data = &mxs_dma_ids[2], }, - { .compatible = "fsl,imx28-dma-apbx", .data = &mxs_dma_ids[3], }, + { .compatible = "fsl,imx23-dma-apbh", .data = &mxs_dma_types[0], }, + { .compatible = "fsl,imx23-dma-apbx", .data = &mxs_dma_types[1], }, + { .compatible = "fsl,imx28-dma-apbh", .data = &mxs_dma_types[2], }, + { .compatible = "fsl,imx28-dma-apbx", .data = &mxs_dma_types[3], }, { /* sentinel */ } }; MODULE_DEVICE_TABLE(of, mxs_dma_dt_ids); @@ -688,7 +670,7 @@ static enum dma_status mxs_dma_tx_status(struct dma_chan *chan, return mxs_chan->status; } -static int __init mxs_dma_init(struct mxs_dma_engine *mxs_dma) +static int mxs_dma_init(struct mxs_dma_engine *mxs_dma) { int ret; @@ -759,11 +741,9 @@ static struct dma_chan *mxs_dma_xlate(struct of_phandle_args *dma_spec, ofdma->of_node); } -static int __init mxs_dma_probe(struct platform_device *pdev) +static int mxs_dma_probe(struct platform_device *pdev) { struct device_node *np = pdev->dev.of_node; - const struct platform_device_id *id_entry; - const struct of_device_id *of_id; const struct mxs_dma_type *dma_type; struct mxs_dma_engine *mxs_dma; struct resource *iores; @@ -779,13 +759,7 @@ static int __init mxs_dma_probe(struct platform_device *pdev) return ret; } - of_id = of_match_device(mxs_dma_dt_ids, &pdev->dev); - if (of_id) - id_entry = of_id->data; - else - id_entry = platform_get_device_id(pdev); - - dma_type = (struct mxs_dma_type *)id_entry->driver_data; + dma_type = (struct mxs_dma_type *)of_device_get_match_data(&pdev->dev); mxs_dma->type = dma_type->type; mxs_dma->dev_id = dma_type->id; @@ -865,11 +839,7 @@ static struct platform_driver mxs_dma_driver = { .name = "mxs-dma", .of_match_table = mxs_dma_dt_ids, }, - .id_table = mxs_dma_ids, + .probe = mxs_dma_probe, }; -static int __init mxs_dma_module_init(void) -{ - return platform_driver_probe(&mxs_dma_driver, mxs_dma_probe); -} -subsys_initcall(mxs_dma_module_init); +builtin_platform_driver(mxs_dma_driver); diff --git a/drivers/dma/pxa_dma.c b/drivers/dma/pxa_dma.c index b4ef4f19f7decb9c007a3ecfa369ba974fd1faca..68d9d60c051d9468563332005532d9eac1514b1c 100644 --- a/drivers/dma/pxa_dma.c +++ b/drivers/dma/pxa_dma.c @@ -1249,14 +1249,14 @@ static int pxad_init_phys(struct platform_device *op, return -ENOMEM; for (i = 0; i < nb_phy_chans; i++) - if (platform_get_irq(op, i) > 0) + if (platform_get_irq_optional(op, i) > 0) nr_irq++; for (i = 0; i < nb_phy_chans; i++) { phy = &pdev->phys[i]; phy->base = pdev->base; phy->idx = i; - irq = platform_get_irq(op, i); + irq = platform_get_irq_optional(op, i); if ((nr_irq > 1) && (irq > 0)) ret = devm_request_irq(&op->dev, irq, pxad_chan_handler, diff --git a/drivers/firmware/arm_scmi/driver.c b/drivers/firmware/arm_scmi/driver.c index e594d739f43701cb36b6fb149d48d6cba00b08f7..977a45dba55ae2dbafcff500fb10a03610f20d73 100644 --- a/drivers/firmware/arm_scmi/driver.c +++ b/drivers/firmware/arm_scmi/driver.c @@ -1126,8 +1126,12 @@ scmi_txrx_setup(struct scmi_info *info, struct device *dev, int prot_id) { int ret = scmi_chan_setup(info, dev, prot_id, true); - if (!ret) /* Rx is optional, hence no error check */ - scmi_chan_setup(info, dev, prot_id, false); + if (!ret) { + /* Rx is optional, report only memory errors */ + ret = scmi_chan_setup(info, dev, prot_id, false); + if (ret && ret != -ENOMEM) + ret = 0; + } return ret; } @@ -1595,6 +1599,7 @@ MODULE_DEVICE_TABLE(of, scmi_of_match); static struct platform_driver scmi_driver = { .driver = { .name = "arm-scmi", + .suppress_bind_attrs = true, .of_match_table = scmi_of_match, .dev_groups = versions_groups, }, diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index e3df82d5d37a83f2fe6958ab5ecfabe8581e286a..70be9c87fb673234899457bb7eda9fa09213e657 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -590,7 +590,7 @@ int __init efi_config_parse_tables(const efi_config_table_t *config_tables, seed = early_memremap(efi_rng_seed, sizeof(*seed)); if (seed != NULL) { - size = READ_ONCE(seed->size); + size = min(seed->size, EFI_RANDOM_SEED_SIZE); early_memunmap(seed, sizeof(*seed)); } else { pr_err("Could not map UEFI random seed!\n"); diff --git a/drivers/firmware/efi/libstub/fdt.c b/drivers/firmware/efi/libstub/fdt.c index 368cd60000eec18ec3affe2a199a64631ac81fe4..d48b0de05b62fdab81b9b0a7033766a1ceac0e75 100644 --- a/drivers/firmware/efi/libstub/fdt.c +++ b/drivers/firmware/efi/libstub/fdt.c @@ -281,14 +281,6 @@ efi_status_t allocate_new_fdt_and_exit_boot(void *handle, goto fail; } - /* - * Now that we have done our final memory allocation (and free) - * we can get the memory map key needed for exit_boot_services(). - */ - status = efi_get_memory_map(&map); - if (status != EFI_SUCCESS) - goto fail_free_new_fdt; - status = update_fdt((void *)fdt_addr, fdt_size, (void *)*new_fdt_addr, MAX_FDT_SIZE, cmdline_ptr, initrd_addr, initrd_size); diff --git a/drivers/firmware/efi/libstub/random.c b/drivers/firmware/efi/libstub/random.c index 24aa375353724abd5339f4d71179c92330bf3170..33ab567695951d6c3c9df4217d067fb53367a373 100644 --- a/drivers/firmware/efi/libstub/random.c +++ b/drivers/firmware/efi/libstub/random.c @@ -75,7 +75,12 @@ efi_status_t efi_random_get_seed(void) if (status != EFI_SUCCESS) return status; - status = efi_bs_call(allocate_pool, EFI_RUNTIME_SERVICES_DATA, + /* + * Use EFI_ACPI_RECLAIM_MEMORY here so that it is guaranteed that the + * allocation will survive a kexec reboot (although we refresh the seed + * beforehand) + */ + status = efi_bs_call(allocate_pool, EFI_ACPI_RECLAIM_MEMORY, sizeof(*seed) + EFI_RANDOM_SEED_SIZE, (void **)&seed); if (status != EFI_SUCCESS) diff --git a/drivers/firmware/efi/tpm.c b/drivers/firmware/efi/tpm.c index 8f665678e9e398760910bb54bfbdb544251a433b..e8d69bd548f3fe2a6f34eb9c3332f97076cd9722 100644 --- a/drivers/firmware/efi/tpm.c +++ b/drivers/firmware/efi/tpm.c @@ -97,7 +97,7 @@ int __init efi_tpm_eventlog_init(void) goto out_calc; } - memblock_reserve((unsigned long)final_tbl, + memblock_reserve(efi.tpm_final_log, tbl_size + sizeof(*final_tbl)); efi_tpm_final_log_size = tbl_size; diff --git a/drivers/firmware/google/coreboot_table.c b/drivers/firmware/google/coreboot_table.c index 0205987a4fd4f08614e386b294e0bb9330b33ffc..568074148f62b34482dd760fba4a22355596cae2 100644 --- a/drivers/firmware/google/coreboot_table.c +++ b/drivers/firmware/google/coreboot_table.c @@ -152,12 +152,8 @@ static int coreboot_table_probe(struct platform_device *pdev) if (!ptr) return -ENOMEM; - ret = bus_register(&coreboot_bus_type); - if (!ret) { - ret = coreboot_table_populate(dev, ptr); - if (ret) - bus_unregister(&coreboot_bus_type); - } + ret = coreboot_table_populate(dev, ptr); + memunmap(ptr); return ret; @@ -172,7 +168,6 @@ static int __cb_dev_unregister(struct device *dev, void *dummy) static int coreboot_table_remove(struct platform_device *pdev) { bus_for_each_dev(&coreboot_bus_type, NULL, NULL, __cb_dev_unregister); - bus_unregister(&coreboot_bus_type); return 0; } @@ -202,6 +197,32 @@ static struct platform_driver coreboot_table_driver = { .of_match_table = of_match_ptr(coreboot_of_match), }, }; -module_platform_driver(coreboot_table_driver); + +static int __init coreboot_table_driver_init(void) +{ + int ret; + + ret = bus_register(&coreboot_bus_type); + if (ret) + return ret; + + ret = platform_driver_register(&coreboot_table_driver); + if (ret) { + bus_unregister(&coreboot_bus_type); + return ret; + } + + return 0; +} + +static void __exit coreboot_table_driver_exit(void) +{ + platform_driver_unregister(&coreboot_table_driver); + bus_unregister(&coreboot_bus_type); +} + +module_init(coreboot_table_driver_init); +module_exit(coreboot_table_driver_exit); + MODULE_AUTHOR("Google, Inc."); MODULE_LICENSE("GPL"); diff --git a/drivers/firmware/google/gsmi.c b/drivers/firmware/google/gsmi.c index 7d9367b220107b95f9c18ec6d7cdf9f81d155beb..c1cd5ca875caae78fbec86d95cac09a65d4df1eb 100644 --- a/drivers/firmware/google/gsmi.c +++ b/drivers/firmware/google/gsmi.c @@ -680,6 +680,15 @@ static struct notifier_block gsmi_die_notifier = { static int gsmi_panic_callback(struct notifier_block *nb, unsigned long reason, void *arg) { + + /* + * Panic callbacks are executed with all other CPUs stopped, + * so we must not attempt to spin waiting for gsmi_dev.lock + * to be released. + */ + if (spin_is_locked(&gsmi_dev.lock)) + return NOTIFY_DONE; + gsmi_shutdown_reason(GSMI_SHUTDOWN_PANIC); return NOTIFY_DONE; } diff --git a/drivers/fpga/dfl.c b/drivers/fpga/dfl.c index b450870b75ed8d3076bea9d198e5a8a01fd047e1..eb8a6e329af9b95a312e2f6d06cd3b3988f9dcac 100644 --- a/drivers/fpga/dfl.c +++ b/drivers/fpga/dfl.c @@ -1857,7 +1857,7 @@ long dfl_feature_ioctl_set_irq(struct platform_device *pdev, return -EINVAL; fds = memdup_user((void __user *)(arg + sizeof(hdr)), - hdr.count * sizeof(s32)); + array_size(hdr.count, sizeof(s32))); if (IS_ERR(fds)) return PTR_ERR(fds); diff --git a/drivers/fsi/fsi-core.c b/drivers/fsi/fsi-core.c index 59ddc9fd5bca47cdf6f997c3ac72e08a7d215e6e..92e6eebd1851e577e606f6a440598f7f89eba1a8 100644 --- a/drivers/fsi/fsi-core.c +++ b/drivers/fsi/fsi-core.c @@ -1309,6 +1309,9 @@ int fsi_master_register(struct fsi_master *master) mutex_init(&master->scan_lock); master->idx = ida_simple_get(&master_ida, 0, INT_MAX, GFP_KERNEL); + if (master->idx < 0) + return master->idx; + dev_set_name(&master->dev, "fsi%d", master->idx); master->dev.class = &fsi_master_class; diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig index ca868271f4c43204a4129006954fe10cee0059a8..4e9b3a95fa7c7e6d88d9c367c30d6a2c7348c131 100644 --- a/drivers/gpu/drm/Kconfig +++ b/drivers/gpu/drm/Kconfig @@ -30,6 +30,7 @@ menuconfig DRM config DRM_MIPI_DBI tristate depends on DRM + select DRM_KMS_HELPER config DRM_MIPI_DSI bool diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c index df1f9b88a53f9fb04d5c20c5ad703a99a1208e45..98d3661336a46e3f8d9fa550a66690a4f205a36f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c @@ -1671,10 +1671,12 @@ amdgpu_connector_add(struct amdgpu_device *adev, adev->mode_info.dither_property, AMDGPU_FMT_DITHER_DISABLE); - if (amdgpu_audio != 0) + if (amdgpu_audio != 0) { drm_object_attach_property(&amdgpu_connector->base.base, adev->mode_info.audio_property, AMDGPU_AUDIO_AUTO); + amdgpu_connector->audio = AMDGPU_AUDIO_AUTO; + } subpixel_order = SubPixelHorizontalRGB; connector->interlace_allowed = true; @@ -1796,6 +1798,7 @@ amdgpu_connector_add(struct amdgpu_device *adev, drm_object_attach_property(&amdgpu_connector->base.base, adev->mode_info.audio_property, AMDGPU_AUDIO_AUTO); + amdgpu_connector->audio = AMDGPU_AUDIO_AUTO; } drm_object_attach_property(&amdgpu_connector->base.base, adev->mode_info.dither_property, @@ -1849,6 +1852,7 @@ amdgpu_connector_add(struct amdgpu_device *adev, drm_object_attach_property(&amdgpu_connector->base.base, adev->mode_info.audio_property, AMDGPU_AUDIO_AUTO); + amdgpu_connector->audio = AMDGPU_AUDIO_AUTO; } drm_object_attach_property(&amdgpu_connector->base.base, adev->mode_info.dither_property, @@ -1899,6 +1903,7 @@ amdgpu_connector_add(struct amdgpu_device *adev, drm_object_attach_property(&amdgpu_connector->base.base, adev->mode_info.audio_property, AMDGPU_AUDIO_AUTO); + amdgpu_connector->audio = AMDGPU_AUDIO_AUTO; } drm_object_attach_property(&amdgpu_connector->base.base, adev->mode_info.dither_property, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 881045e600af28e47c21a3a9418762cbcbd239d2..bde0496d2f153961c758d7cdf8e6d758e9ca892c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -2179,16 +2179,8 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev) } adev->ip_blocks[i].status.sw = true; - if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_COMMON) { - /* need to do common hw init early so everything is set up for gmc */ - r = adev->ip_blocks[i].version->funcs->hw_init((void *)adev); - if (r) { - DRM_ERROR("hw_init %d failed %d\n", i, r); - goto init_failed; - } - adev->ip_blocks[i].status.hw = true; - } else if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GMC) { - /* need to do gmc hw init early so we can allocate gpu mem */ + /* need to do gmc hw init early so we can allocate gpu mem */ + if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GMC) { /* Try to reserve bad pages early */ if (amdgpu_sriov_vf(adev)) amdgpu_virt_exchange_data(adev); @@ -2770,8 +2762,8 @@ static int amdgpu_device_ip_reinit_early_sriov(struct amdgpu_device *adev) int i, r; static enum amd_ip_block_type ip_order[] = { - AMD_IP_BLOCK_TYPE_COMMON, AMD_IP_BLOCK_TYPE_GMC, + AMD_IP_BLOCK_TYPE_COMMON, AMD_IP_BLOCK_TYPE_PSP, AMD_IP_BLOCK_TYPE_IH, }; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c index 947f50e402ba0abe9ae8dda33300f026e7322fb6..7cc7af2a6822e4795d1b096cf723011909dce9aa 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c @@ -35,7 +35,6 @@ #include #include #include -#include #include #include #include @@ -499,7 +498,6 @@ bool amdgpu_display_ddc_probe(struct amdgpu_connector *amdgpu_connector, static const struct drm_framebuffer_funcs amdgpu_fb_funcs = { .destroy = drm_gem_fb_destroy, .create_handle = drm_gem_fb_create_handle, - .dirty = drm_atomic_helper_dirtyfb, }; uint32_t amdgpu_display_supported_domains(struct amdgpu_device *adev, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c index e8c76bd8c501f1bfaea5a1e255123d4935a620d1..6aa9fd9cb83b4f6703a1c5257efdfe1aac1fe0af 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c @@ -341,11 +341,9 @@ int amdgpu_gem_userptr_ioctl(struct drm_device *dev, void *data, if (r) goto release_object; - if (args->flags & AMDGPU_GEM_USERPTR_REGISTER) { - r = amdgpu_mn_register(bo, args->addr); - if (r) - goto release_object; - } + r = amdgpu_mn_register(bo, args->addr); + if (r) + goto release_object; if (args->flags & AMDGPU_GEM_USERPTR_VALIDATE) { r = amdgpu_ttm_tt_get_user_pages(bo, bo->tbo.ttm->pages); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c index 16bfb36c27e415da3bffcbc49249ff3a4471ac58..d6f2951035959616b526f398c3f49a2f4fa1131f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c @@ -670,6 +670,12 @@ void amdgpu_detect_virtualization(struct amdgpu_device *adev) adev->virt.caps |= AMDGPU_PASSTHROUGH_MODE; } + if (amdgpu_sriov_vf(adev) && adev->asic_type == CHIP_SIENNA_CICHLID) + /* VF MMIO access (except mailbox range) from CPU + * will be blocked during sriov runtime + */ + adev->virt.caps |= AMDGPU_VF_MMIO_ACCESS_PROTECT; + /* we have the ability to check now */ if (amdgpu_sriov_vf(adev)) { switch (adev->asic_type) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h index 77b9d37bfa1b27a0689484d9861ca0232bacb76b..aea49bad914fa4ae6396854cb1c750c0c251a604 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h @@ -31,6 +31,7 @@ #define AMDGPU_SRIOV_CAPS_IS_VF (1 << 2) /* this GPU is a virtual function */ #define AMDGPU_PASSTHROUGH_MODE (1 << 3) /* thw whole GPU is pass through for VM */ #define AMDGPU_SRIOV_CAPS_RUNTIME (1 << 4) /* is out of full access mode */ +#define AMDGPU_VF_MMIO_ACCESS_PROTECT (1 << 5) /* MMIO write access is not allowed in sriov runtime */ /* all asic after AI use this offset */ #define mmRCC_IOV_FUNC_IDENTIFIER 0xDE5 @@ -241,6 +242,9 @@ struct amdgpu_virt { #define amdgpu_passthrough(adev) \ ((adev)->virt.caps & AMDGPU_PASSTHROUGH_MODE) +#define amdgpu_sriov_vf_mmio_access_protection(adev) \ +((adev)->virt.caps & AMDGPU_VF_MMIO_ACCESS_PROTECT) + static inline bool is_virtual_machine(void) { #ifdef CONFIG_X86 diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 635601d8b131052c50ed1f2bd7d5463c0348be18..45b1f00c5968081bb279d65f6083b09f857f7810 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -3200,7 +3200,11 @@ void amdgpu_vm_manager_init(struct amdgpu_device *adev) */ #ifdef CONFIG_X86_64 if (amdgpu_vm_update_mode == -1) { - if (amdgpu_gmc_vram_full_visible(&adev->gmc)) + /* For asic with VF MMIO access protection + * avoid using CPU for VM table updates + */ + if (amdgpu_gmc_vram_full_visible(&adev->gmc) && + !amdgpu_sriov_vf_mmio_access_protection(adev)) adev->vm_manager.vm_update_mode = AMDGPU_VM_USE_CPU_FOR_COMPUTE; else diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c index a1a8e026b9fa60787da29be341e9c4c7fa6cf72c..1f2e2460e121ee134a72d423baeea06184474750 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c @@ -1475,11 +1475,6 @@ static int sdma_v4_0_start(struct amdgpu_device *adev) WREG32_SDMA(i, mmSDMA0_CNTL, temp); if (!amdgpu_sriov_vf(adev)) { - ring = &adev->sdma.instance[i].ring; - adev->nbio.funcs->sdma_doorbell_range(adev, i, - ring->use_doorbell, ring->doorbell_index, - adev->doorbell_index.sdma_doorbell_range); - /* unhalt engine */ temp = RREG32_SDMA(i, mmSDMA0_F32_CNTL); temp = REG_SET_FIELD(temp, SDMA0_F32_CNTL, HALT, 0); diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c index abd649285a22d8f9bcde9a2047711901989b2d71..7212b9900e0abafdf8386235789ec6f25167384d 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc15.c +++ b/drivers/gpu/drm/amd/amdgpu/soc15.c @@ -1332,6 +1332,25 @@ static int soc15_common_sw_fini(void *handle) return 0; } +static void soc15_doorbell_range_init(struct amdgpu_device *adev) +{ + int i; + struct amdgpu_ring *ring; + + /* sdma/ih doorbell range are programed by hypervisor */ + if (!amdgpu_sriov_vf(adev)) { + for (i = 0; i < adev->sdma.num_instances; i++) { + ring = &adev->sdma.instance[i].ring; + adev->nbio.funcs->sdma_doorbell_range(adev, i, + ring->use_doorbell, ring->doorbell_index, + adev->doorbell_index.sdma_doorbell_range); + } + + adev->nbio.funcs->ih_doorbell_range(adev, adev->irq.ih.use_doorbell, + adev->irq.ih.doorbell_index); + } +} + static int soc15_common_hw_init(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; @@ -1351,6 +1370,12 @@ static int soc15_common_hw_init(void *handle) /* enable the doorbell aperture */ soc15_enable_doorbell_aperture(adev, true); + /* HW doorbell routing policy: doorbell writing not + * in SDMA/IH/MM/ACV range will be routed to CP. So + * we need to init SDMA/IH/MM/ACV doorbell range prior + * to CP ip block init and ring test. + */ + soc15_doorbell_range_init(adev); return 0; } diff --git a/drivers/gpu/drm/amd/display/dc/calcs/bw_fixed.c b/drivers/gpu/drm/amd/display/dc/calcs/bw_fixed.c index 6ca288fb5fb9e69ee8f154b23e5a393d8d44d374..2d46bc527b2187b873ccb768a6135fb024ef4b30 100644 --- a/drivers/gpu/drm/amd/display/dc/calcs/bw_fixed.c +++ b/drivers/gpu/drm/amd/display/dc/calcs/bw_fixed.c @@ -26,12 +26,12 @@ #include "bw_fixed.h" -#define MIN_I64 \ - (int64_t)(-(1LL << 63)) - #define MAX_I64 \ (int64_t)((1ULL << 63) - 1) +#define MIN_I64 \ + (-MAX_I64 - 1) + #define FRACTIONAL_PART_MASK \ ((1ULL << BW_FIXED_BITS_PER_FRACTIONAL_PART) - 1) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 93f5229c303e7bc484244f71bfd03edd5c6a51af..99887bcfada0430b3941521ee85e5d40c39cc558 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -2202,11 +2202,8 @@ static void copy_stream_update_to_stream(struct dc *dc, if (update->abm_level) stream->abm_level = *update->abm_level; - if (update->periodic_interrupt0) - stream->periodic_interrupt0 = *update->periodic_interrupt0; - - if (update->periodic_interrupt1) - stream->periodic_interrupt1 = *update->periodic_interrupt1; + if (update->periodic_interrupt) + stream->periodic_interrupt = *update->periodic_interrupt; if (update->gamut_remap) stream->gamut_remap_matrix = *update->gamut_remap; @@ -2288,13 +2285,8 @@ static void commit_planes_do_stream_update(struct dc *dc, if (!pipe_ctx->top_pipe && !pipe_ctx->prev_odm_pipe && pipe_ctx->stream == stream) { - if (stream_update->periodic_interrupt0 && - dc->hwss.setup_periodic_interrupt) - dc->hwss.setup_periodic_interrupt(dc, pipe_ctx, VLINE0); - - if (stream_update->periodic_interrupt1 && - dc->hwss.setup_periodic_interrupt) - dc->hwss.setup_periodic_interrupt(dc, pipe_ctx, VLINE1); + if (stream_update->periodic_interrupt && dc->hwss.setup_periodic_interrupt) + dc->hwss.setup_periodic_interrupt(dc, pipe_ctx); if ((stream_update->hdr_static_metadata && !stream->use_dynamic_meta) || stream_update->vrr_infopacket || diff --git a/drivers/gpu/drm/amd/display/dc/dc_stream.h b/drivers/gpu/drm/amd/display/dc/dc_stream.h index 205bedd1b19663694fd178fda439fb382144e7f7..0487c1b8957c06af1bc7f0653e63c75c284f0636 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_stream.h +++ b/drivers/gpu/drm/amd/display/dc/dc_stream.h @@ -179,8 +179,7 @@ struct dc_stream_state { /* DMCU info */ unsigned int abm_level; - struct periodic_interrupt_config periodic_interrupt0; - struct periodic_interrupt_config periodic_interrupt1; + struct periodic_interrupt_config periodic_interrupt; /* from core_stream struct */ struct dc_context *ctx; @@ -244,8 +243,7 @@ struct dc_stream_update { struct dc_info_packet *hdr_static_metadata; unsigned int *abm_level; - struct periodic_interrupt_config *periodic_interrupt0; - struct periodic_interrupt_config *periodic_interrupt1; + struct periodic_interrupt_config *periodic_interrupt; struct dc_info_packet *vrr_infopacket; struct dc_info_packet *vsc_infopacket; diff --git a/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c b/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c index 8f362e8c17870baebaaf31ca8a516ba53692505d..be6d43c9979c82afff271f498d7194cc833665bc 100644 --- a/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c @@ -361,7 +361,8 @@ static const struct dce_audio_registers audio_regs[] = { audio_regs(2), audio_regs(3), audio_regs(4), - audio_regs(5) + audio_regs(5), + audio_regs(6), }; #define DCE120_AUD_COMMON_MASK_SH_LIST(mask_sh)\ diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c index 31a13daf4289c44df5422caf2c3d78982cbb00ea..71a85c5306ed0c98f01190895d2e73431eba03bd 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c @@ -3611,7 +3611,7 @@ void dcn10_calc_vupdate_position( { const struct dc_crtc_timing *dc_crtc_timing = &pipe_ctx->stream->timing; int vline_int_offset_from_vupdate = - pipe_ctx->stream->periodic_interrupt0.lines_offset; + pipe_ctx->stream->periodic_interrupt.lines_offset; int vupdate_offset_from_vsync = dc->hwss.get_vupdate_offset_from_vsync(pipe_ctx); int start_position; @@ -3636,18 +3636,10 @@ void dcn10_calc_vupdate_position( static void dcn10_cal_vline_position( struct dc *dc, struct pipe_ctx *pipe_ctx, - enum vline_select vline, uint32_t *start_line, uint32_t *end_line) { - enum vertical_interrupt_ref_point ref_point = INVALID_POINT; - - if (vline == VLINE0) - ref_point = pipe_ctx->stream->periodic_interrupt0.ref_point; - else if (vline == VLINE1) - ref_point = pipe_ctx->stream->periodic_interrupt1.ref_point; - - switch (ref_point) { + switch (pipe_ctx->stream->periodic_interrupt.ref_point) { case START_V_UPDATE: dcn10_calc_vupdate_position( dc, @@ -3656,7 +3648,9 @@ static void dcn10_cal_vline_position( end_line); break; case START_V_SYNC: - // Suppose to do nothing because vsync is 0; + // vsync is line 0 so start_line is just the requested line offset + *start_line = pipe_ctx->stream->periodic_interrupt.lines_offset; + *end_line = *start_line + 2; break; default: ASSERT(0); @@ -3666,24 +3660,15 @@ static void dcn10_cal_vline_position( void dcn10_setup_periodic_interrupt( struct dc *dc, - struct pipe_ctx *pipe_ctx, - enum vline_select vline) + struct pipe_ctx *pipe_ctx) { struct timing_generator *tg = pipe_ctx->stream_res.tg; + uint32_t start_line = 0; + uint32_t end_line = 0; - if (vline == VLINE0) { - uint32_t start_line = 0; - uint32_t end_line = 0; + dcn10_cal_vline_position(dc, pipe_ctx, &start_line, &end_line); - dcn10_cal_vline_position(dc, pipe_ctx, vline, &start_line, &end_line); - - tg->funcs->setup_vertical_interrupt0(tg, start_line, end_line); - - } else if (vline == VLINE1) { - pipe_ctx->stream_res.tg->funcs->setup_vertical_interrupt1( - tg, - pipe_ctx->stream->periodic_interrupt1.lines_offset); - } + tg->funcs->setup_vertical_interrupt0(tg, start_line, end_line); } void dcn10_setup_vupdate_interrupt(struct dc *dc, struct pipe_ctx *pipe_ctx) diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.h index e5691e49902315f0165dc017ab68ff51b781c067..81b5057d5ff123b8921d5e706557b437082827b1 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.h +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.h @@ -174,8 +174,7 @@ void dcn10_set_cursor_attribute(struct pipe_ctx *pipe_ctx); void dcn10_set_cursor_sdr_white_level(struct pipe_ctx *pipe_ctx); void dcn10_setup_periodic_interrupt( struct dc *dc, - struct pipe_ctx *pipe_ctx, - enum vline_select vline); + struct pipe_ctx *pipe_ctx); enum dc_status dcn10_set_clock(struct dc *dc, enum dc_clock_type clock_type, uint32_t clk_khz, diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c index 8f66eef0c68370d300ebbee281a5d8a176cc1af3..c6c4888c666511b8ef80e8d90897bda0d86a1960 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c @@ -1746,7 +1746,7 @@ void dcn20_post_unlock_program_front_end( for (j = 0; j < TIMEOUT_FOR_PIPE_ENABLE_MS*1000 && hubp->funcs->hubp_is_flip_pending(hubp); j++) - mdelay(1); + udelay(1); } } diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h index 64c1be818b0e8e017f5dae7b4dbc326130d68310..3165a66c5362f0394bd0a2e32abfb58bfc42e0d5 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h @@ -32,11 +32,6 @@ #include "inc/hw/link_encoder.h" #include "core_status.h" -enum vline_select { - VLINE0, - VLINE1 -}; - struct pipe_ctx; struct dc_state; struct dc_stream_status; @@ -112,8 +107,7 @@ struct hw_sequencer_funcs { int group_index, int group_size, struct pipe_ctx *grouped_pipes[]); void (*setup_periodic_interrupt)(struct dc *dc, - struct pipe_ctx *pipe_ctx, - enum vline_select vline); + struct pipe_ctx *pipe_ctx); void (*set_drr)(struct pipe_ctx **pipe_ctx, int num_pipes, unsigned int vmin, unsigned int vmax, unsigned int vmid, unsigned int vmid_frame_number); diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c index 1c526cb239e035429a37792f195816b22bc83993..3a31058b029e31ff7023405b283298675ef7f945 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c @@ -379,16 +379,31 @@ static int arcturus_set_default_dpm_table(struct smu_context *smu) return 0; } -static int arcturus_check_powerplay_table(struct smu_context *smu) +static void arcturus_check_bxco_support(struct smu_context *smu) { struct smu_table_context *table_context = &smu->smu_table; struct smu_11_0_powerplay_table *powerplay_table = table_context->power_play_table; struct smu_baco_context *smu_baco = &smu->smu_baco; + struct amdgpu_device *adev = smu->adev; + uint32_t val; if (powerplay_table->platform_caps & SMU_11_0_PP_PLATFORM_CAP_BACO || - powerplay_table->platform_caps & SMU_11_0_PP_PLATFORM_CAP_MACO) - smu_baco->platform_support = true; + powerplay_table->platform_caps & SMU_11_0_PP_PLATFORM_CAP_MACO) { + val = RREG32_SOC15(NBIO, 0, mmRCC_BIF_STRAP0); + smu_baco->platform_support = + (val & RCC_BIF_STRAP0__STRAP_PX_CAPABLE_MASK) ? true : + false; + } +} + +static int arcturus_check_powerplay_table(struct smu_context *smu) +{ + struct smu_table_context *table_context = &smu->smu_table; + struct smu_11_0_powerplay_table *powerplay_table = + table_context->power_play_table; + + arcturus_check_bxco_support(smu); table_context->thermal_controller_type = powerplay_table->thermal_controller_type; @@ -2131,13 +2146,11 @@ static void arcturus_get_unique_id(struct smu_context *smu) static bool arcturus_is_baco_supported(struct smu_context *smu) { struct amdgpu_device *adev = smu->adev; - uint32_t val; if (!smu_v11_0_baco_is_support(smu) || amdgpu_sriov_vf(adev)) return false; - val = RREG32_SOC15(NBIO, 0, mmRCC_BIF_STRAP0); - return (val & RCC_BIF_STRAP0__STRAP_PX_CAPABLE_MASK) ? true : false; + return true; } static int arcturus_set_df_cstate(struct smu_context *smu, diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c index 2937784bc8249e9adce1824eb155f518959770f4..a7773b6453d539c12e39e19d38f2a8ea15106377 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c @@ -338,19 +338,34 @@ navi10_get_allowed_feature_mask(struct smu_context *smu, return 0; } -static int navi10_check_powerplay_table(struct smu_context *smu) +static void navi10_check_bxco_support(struct smu_context *smu) { struct smu_table_context *table_context = &smu->smu_table; struct smu_11_0_powerplay_table *powerplay_table = table_context->power_play_table; struct smu_baco_context *smu_baco = &smu->smu_baco; + struct amdgpu_device *adev = smu->adev; + uint32_t val; + + if (powerplay_table->platform_caps & SMU_11_0_PP_PLATFORM_CAP_BACO || + powerplay_table->platform_caps & SMU_11_0_PP_PLATFORM_CAP_MACO) { + val = RREG32_SOC15(NBIO, 0, mmRCC_BIF_STRAP0); + smu_baco->platform_support = + (val & RCC_BIF_STRAP0__STRAP_PX_CAPABLE_MASK) ? true : + false; + } +} + +static int navi10_check_powerplay_table(struct smu_context *smu) +{ + struct smu_table_context *table_context = &smu->smu_table; + struct smu_11_0_powerplay_table *powerplay_table = + table_context->power_play_table; if (powerplay_table->platform_caps & SMU_11_0_PP_PLATFORM_CAP_HARDWAREDC) smu->dc_controlled_by_gpio = true; - if (powerplay_table->platform_caps & SMU_11_0_PP_PLATFORM_CAP_BACO || - powerplay_table->platform_caps & SMU_11_0_PP_PLATFORM_CAP_MACO) - smu_baco->platform_support = true; + navi10_check_bxco_support(smu); table_context->thermal_controller_type = powerplay_table->thermal_controller_type; @@ -1948,13 +1963,11 @@ static int navi10_overdrive_get_gfx_clk_base_voltage(struct smu_context *smu, static bool navi10_is_baco_supported(struct smu_context *smu) { struct amdgpu_device *adev = smu->adev; - uint32_t val; if (amdgpu_sriov_vf(adev) || (!smu_v11_0_baco_is_support(smu))) return false; - val = RREG32_SOC15(NBIO, 0, mmRCC_BIF_STRAP0); - return (val & RCC_BIF_STRAP0__STRAP_PX_CAPABLE_MASK) ? true : false; + return true; } static int navi10_set_default_od_settings(struct smu_context *smu) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c index 49d7fa1d084274f514c0a982e3925d44a6af2446..45c8152622008cfd810c74795423409dcb81e197 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c @@ -294,16 +294,47 @@ sienna_cichlid_get_allowed_feature_mask(struct smu_context *smu, return 0; } -static int sienna_cichlid_check_powerplay_table(struct smu_context *smu) +static void sienna_cichlid_check_bxco_support(struct smu_context *smu) { struct smu_table_context *table_context = &smu->smu_table; struct smu_11_0_7_powerplay_table *powerplay_table = table_context->power_play_table; struct smu_baco_context *smu_baco = &smu->smu_baco; + struct amdgpu_device *adev = smu->adev; + uint32_t val; if (powerplay_table->platform_caps & SMU_11_0_7_PP_PLATFORM_CAP_BACO || - powerplay_table->platform_caps & SMU_11_0_7_PP_PLATFORM_CAP_MACO) - smu_baco->platform_support = true; + powerplay_table->platform_caps & SMU_11_0_7_PP_PLATFORM_CAP_MACO) { + val = RREG32_SOC15(NBIO, 0, mmRCC_BIF_STRAP0); + smu_baco->platform_support = + (val & RCC_BIF_STRAP0__STRAP_PX_CAPABLE_MASK) ? true : + false; + + /* + * Disable BACO entry/exit completely on below SKUs to + * avoid hardware intermittent failures. + */ + if (((adev->pdev->device == 0x73A1) && + (adev->pdev->revision == 0x00)) || + ((adev->pdev->device == 0x73BF) && + (adev->pdev->revision == 0xCF)) || + ((adev->pdev->device == 0x7422) && + (adev->pdev->revision == 0x00))) + smu_baco->platform_support = false; + + } +} + +static int sienna_cichlid_check_powerplay_table(struct smu_context *smu) +{ + struct smu_table_context *table_context = &smu->smu_table; + struct smu_11_0_7_powerplay_table *powerplay_table = + table_context->power_play_table; + + if (powerplay_table->platform_caps & SMU_11_0_7_PP_PLATFORM_CAP_HARDWAREDC) + smu->dc_controlled_by_gpio = true; + + sienna_cichlid_check_bxco_support(smu); table_context->thermal_controller_type = powerplay_table->thermal_controller_type; @@ -1736,13 +1767,11 @@ static int sienna_cichlid_run_btc(struct smu_context *smu) static bool sienna_cichlid_is_baco_supported(struct smu_context *smu) { struct amdgpu_device *adev = smu->adev; - uint32_t val; if (amdgpu_sriov_vf(adev) || (!smu_v11_0_baco_is_support(smu))) return false; - val = RREG32_SOC15(NBIO, 0, mmRCC_BIF_STRAP0); - return (val & RCC_BIF_STRAP0__STRAP_PX_CAPABLE_MASK) ? true : false; + return true; } static bool sienna_cichlid_is_mode1_reset_supported(struct smu_context *smu) @@ -2806,6 +2835,7 @@ static const struct pptable_funcs sienna_cichlid_ppt_funcs = { .get_dpm_ultimate_freq = sienna_cichlid_get_dpm_ultimate_freq, .set_soft_freq_limited_range = smu_v11_0_set_soft_freq_limited_range, .run_btc = sienna_cichlid_run_btc, + .set_power_source = smu_v11_0_set_power_source, .get_pp_feature_mask = smu_cmn_get_pp_feature_mask, .set_pp_feature_mask = smu_cmn_set_pp_feature_mask, .get_gpu_metrics = sienna_cichlid_get_gpu_metrics, diff --git a/drivers/gpu/drm/bridge/adv7511/adv7511.h b/drivers/gpu/drm/bridge/adv7511/adv7511.h index a0f6ee15c24859a48f39c7120ad36a48ca28eec0..711061bf3eb7e9d5d9709ac485af731a5241cd1a 100644 --- a/drivers/gpu/drm/bridge/adv7511/adv7511.h +++ b/drivers/gpu/drm/bridge/adv7511/adv7511.h @@ -386,10 +386,7 @@ void adv7511_cec_irq_process(struct adv7511 *adv7511, unsigned int irq1); #else static inline int adv7511_cec_init(struct device *dev, struct adv7511 *adv7511) { - unsigned int offset = adv7511->type == ADV7533 ? - ADV7533_REG_CEC_OFFSET : 0; - - regmap_write(adv7511->regmap, ADV7511_REG_CEC_CTRL + offset, + regmap_write(adv7511->regmap, ADV7511_REG_CEC_CTRL, ADV7511_CEC_CTRL_POWER_DOWN); return 0; } diff --git a/drivers/gpu/drm/bridge/adv7511/adv7511_cec.c b/drivers/gpu/drm/bridge/adv7511/adv7511_cec.c index a20a45c0b353f18eb9d2af13f2a5d707e7b1fc5c..ddd1305b82b2ca692ac47d99d60b1e869dcafab7 100644 --- a/drivers/gpu/drm/bridge/adv7511/adv7511_cec.c +++ b/drivers/gpu/drm/bridge/adv7511/adv7511_cec.c @@ -316,7 +316,7 @@ int adv7511_cec_init(struct device *dev, struct adv7511 *adv7511) goto err_cec_alloc; } - regmap_write(adv7511->regmap, ADV7511_REG_CEC_CTRL + offset, 0); + regmap_write(adv7511->regmap, ADV7511_REG_CEC_CTRL, 0); /* cec soft reset */ regmap_write(adv7511->regmap_cec, ADV7511_REG_CEC_SOFT_RESET + offset, 0x01); @@ -343,7 +343,7 @@ err_cec_alloc: dev_info(dev, "Initializing CEC failed with error %d, disabling CEC\n", ret); err_cec_parse_dt: - regmap_write(adv7511->regmap, ADV7511_REG_CEC_CTRL + offset, + regmap_write(adv7511->regmap, ADV7511_REG_CEC_CTRL, ADV7511_CEC_CTRL_POWER_DOWN); return ret == -EPROBE_DEFER ? ret : 0; } diff --git a/drivers/gpu/drm/bridge/lontium-lt9611.c b/drivers/gpu/drm/bridge/lontium-lt9611.c index 29b1ce2140abc441b86abbdf0701b9008a43c8a1..1dcc28a4d853793395a4696501e904445be79ec6 100644 --- a/drivers/gpu/drm/bridge/lontium-lt9611.c +++ b/drivers/gpu/drm/bridge/lontium-lt9611.c @@ -816,13 +816,14 @@ static int lt9611_connector_init(struct drm_bridge *bridge, struct lt9611 *lt961 drm_connector_helper_add(<9611->connector, <9611_bridge_connector_helper_funcs); - drm_connector_attach_encoder(<9611->connector, bridge->encoder); if (!bridge->encoder) { DRM_ERROR("Parent encoder object not found"); return -ENODEV; } + drm_connector_attach_encoder(<9611->connector, bridge->encoder); + return 0; } diff --git a/drivers/gpu/drm/bridge/megachips-stdpxxxx-ge-b850v3-fw.c b/drivers/gpu/drm/bridge/megachips-stdpxxxx-ge-b850v3-fw.c index cce98bf2a4e7324f85c1d4e113e44ae80abed7a7..72248a565579ecfad1940b6c1caca42ad826114b 100644 --- a/drivers/gpu/drm/bridge/megachips-stdpxxxx-ge-b850v3-fw.c +++ b/drivers/gpu/drm/bridge/megachips-stdpxxxx-ge-b850v3-fw.c @@ -296,7 +296,9 @@ static void ge_b850v3_lvds_remove(void) * This check is to avoid both the drivers * removing the bridge in their remove() function */ - if (!ge_b850v3_lvds_ptr) + if (!ge_b850v3_lvds_ptr || + !ge_b850v3_lvds_ptr->stdp2690_i2c || + !ge_b850v3_lvds_ptr->stdp4028_i2c) goto out; drm_bridge_remove(&ge_b850v3_lvds_ptr->bridge); diff --git a/drivers/gpu/drm/bridge/parade-ps8640.c b/drivers/gpu/drm/bridge/parade-ps8640.c index 7bd0affa057a59770df67ea86b46e4b2c411736d..9248510104005b7deed7ff5a99051aab41cae8ea 100644 --- a/drivers/gpu/drm/bridge/parade-ps8640.c +++ b/drivers/gpu/drm/bridge/parade-ps8640.c @@ -333,8 +333,8 @@ static int ps8640_probe(struct i2c_client *client) if (IS_ERR(ps_bridge->panel_bridge)) return PTR_ERR(ps_bridge->panel_bridge); - ps_bridge->supplies[0].supply = "vdd33"; - ps_bridge->supplies[1].supply = "vdd12"; + ps_bridge->supplies[0].supply = "vdd12"; + ps_bridge->supplies[1].supply = "vdd33"; ret = devm_regulator_bulk_get(dev, ARRAY_SIZE(ps_bridge->supplies), ps_bridge->supplies); if (ret) diff --git a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c index b10228b9e3a93bf4144ce6d6d3d818907edf9b92..356c7d0bd035fc0051b45a3cae4a64f0b166b1f0 100644 --- a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c +++ b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c @@ -2984,6 +2984,7 @@ static irqreturn_t dw_hdmi_irq(int irq, void *dev_id) { struct dw_hdmi *hdmi = dev_id; u8 intr_stat, phy_int_pol, phy_pol_mask, phy_stat; + enum drm_connector_status status = connector_status_unknown; intr_stat = hdmi_readb(hdmi, HDMI_IH_PHY_STAT0); phy_int_pol = hdmi_readb(hdmi, HDMI_PHY_POL0); @@ -3022,13 +3023,15 @@ static irqreturn_t dw_hdmi_irq(int irq, void *dev_id) cec_notifier_phys_addr_invalidate(hdmi->cec_notifier); mutex_unlock(&hdmi->cec_notifier_mutex); } - } - if (intr_stat & HDMI_IH_PHY_STAT0_HPD) { - enum drm_connector_status status = phy_int_pol & HDMI_PHY_HPD - ? connector_status_connected - : connector_status_disconnected; + if (phy_stat & HDMI_PHY_HPD) + status = connector_status_connected; + + if (!(phy_stat & (HDMI_PHY_HPD | HDMI_PHY_RX_SENSE))) + status = connector_status_disconnected; + } + if (status != connector_status_unknown) { dev_dbg(hdmi->dev, "EVENT=%s\n", status == connector_status_connected ? "plugin" : "plugout"); diff --git a/drivers/gpu/drm/drm_bridge.c b/drivers/gpu/drm/drm_bridge.c index 044acd07c15387a612946d821bec9701478b7196..d799ec14fd7f5c53a4f8b130a03959bbd3502cfd 100644 --- a/drivers/gpu/drm/drm_bridge.c +++ b/drivers/gpu/drm/drm_bridge.c @@ -753,8 +753,8 @@ static int select_bus_fmt_recursive(struct drm_bridge *first_bridge, struct drm_connector_state *conn_state, u32 out_bus_fmt) { + unsigned int i, num_in_bus_fmts = 0; struct drm_bridge_state *cur_state; - unsigned int num_in_bus_fmts, i; struct drm_bridge *prev_bridge; u32 *in_bus_fmts; int ret; @@ -875,7 +875,7 @@ drm_atomic_bridge_chain_select_bus_fmts(struct drm_bridge *bridge, struct drm_connector *conn = conn_state->connector; struct drm_encoder *encoder = bridge->encoder; struct drm_bridge_state *last_bridge_state; - unsigned int i, num_out_bus_fmts; + unsigned int i, num_out_bus_fmts = 0; struct drm_bridge *last_bridge; u32 *out_bus_fmts; int ret = 0; diff --git a/drivers/gpu/drm/drm_dp_dual_mode_helper.c b/drivers/gpu/drm/drm_dp_dual_mode_helper.c index 1c9ea9f7fdafed88daa7cf6eb3657eca1c0c0aea..f2ff0bfdf54d78cd2f8af7a7b6afb787d63be837 100644 --- a/drivers/gpu/drm/drm_dp_dual_mode_helper.c +++ b/drivers/gpu/drm/drm_dp_dual_mode_helper.c @@ -62,23 +62,45 @@ ssize_t drm_dp_dual_mode_read(struct i2c_adapter *adapter, u8 offset, void *buffer, size_t size) { + u8 zero = 0; + char *tmpbuf = NULL; + /* + * As sub-addressing is not supported by all adaptors, + * always explicitly read from the start and discard + * any bytes that come before the requested offset. + * This way, no matter whether the adaptor supports it + * or not, we'll end up reading the proper data. + */ struct i2c_msg msgs[] = { { .addr = DP_DUAL_MODE_SLAVE_ADDRESS, .flags = 0, .len = 1, - .buf = &offset, + .buf = &zero, }, { .addr = DP_DUAL_MODE_SLAVE_ADDRESS, .flags = I2C_M_RD, - .len = size, + .len = size + offset, .buf = buffer, }, }; int ret; + if (offset) { + tmpbuf = kmalloc(size + offset, GFP_KERNEL); + if (!tmpbuf) + return -ENOMEM; + + msgs[1].buf = tmpbuf; + } + ret = i2c_transfer(adapter, msgs, ARRAY_SIZE(msgs)); + if (tmpbuf) + memcpy(buffer, tmpbuf + offset, size); + + kfree(tmpbuf); + if (ret < 0) return ret; if (ret != ARRAY_SIZE(msgs)) @@ -205,18 +227,6 @@ enum drm_dp_dual_mode_type drm_dp_dual_mode_detect(struct i2c_adapter *adapter) if (ret) return DRM_DP_DUAL_MODE_UNKNOWN; - /* - * Sigh. Some (maybe all?) type 1 adaptors are broken and ack - * the offset but ignore it, and instead they just always return - * data from the start of the HDMI ID buffer. So for a broken - * type 1 HDMI adaptor a single byte read will always give us - * 0x44, and for a type 1 DVI adaptor it should give 0x00 - * (assuming it implements any registers). Fortunately neither - * of those values will match the type 2 signature of the - * DP_DUAL_MODE_ADAPTOR_ID register so we can proceed with - * the type 2 adaptor detection safely even in the presence - * of broken type 1 adaptors. - */ ret = drm_dp_dual_mode_read(adapter, DP_DUAL_MODE_ADAPTOR_ID, &adaptor_id, sizeof(adaptor_id)); DRM_DEBUG_KMS("DP dual mode adaptor ID: %02x (err %zd)\n", @@ -231,11 +241,10 @@ enum drm_dp_dual_mode_type drm_dp_dual_mode_detect(struct i2c_adapter *adapter) return DRM_DP_DUAL_MODE_TYPE2_DVI; } /* - * If neither a proper type 1 ID nor a broken type 1 adaptor - * as described above, assume type 1, but let the user know - * that we may have misdetected the type. + * If not a proper type 1 ID, still assume type 1, but let + * the user know that we may have misdetected the type. */ - if (!is_type1_adaptor(adaptor_id) && adaptor_id != hdmi_id[0]) + if (!is_type1_adaptor(adaptor_id)) DRM_ERROR("Unexpected DP dual mode adaptor ID %02x\n", adaptor_id); @@ -339,10 +348,8 @@ EXPORT_SYMBOL(drm_dp_dual_mode_get_tmds_output); * @enable: enable (as opposed to disable) the TMDS output buffers * * Set the state of the TMDS output buffers in the adaptor. For - * type2 this is set via the DP_DUAL_MODE_TMDS_OEN register. As - * some type 1 adaptors have problems with registers (see comments - * in drm_dp_dual_mode_detect()) we avoid touching the register, - * making this function a no-op on type 1 adaptors. + * type2 this is set via the DP_DUAL_MODE_TMDS_OEN register. + * Type1 adaptors do not support any register writes. * * Returns: * 0 on success, negative error code on failure diff --git a/drivers/gpu/drm/drm_dp_helper.c b/drivers/gpu/drm/drm_dp_helper.c index 3c55753bab161d80dbaf403cf4177ee52ed3a056..6ba16db7750031b9fd4d6d68e52081600033f2cb 100644 --- a/drivers/gpu/drm/drm_dp_helper.c +++ b/drivers/gpu/drm/drm_dp_helper.c @@ -2172,17 +2172,8 @@ int drm_dp_set_phy_test_pattern(struct drm_dp_aux *aux, struct drm_dp_phy_test_params *data, u8 dp_rev) { int err, i; - u8 link_config[2]; u8 test_pattern; - link_config[0] = drm_dp_link_rate_to_bw_code(data->link_rate); - link_config[1] = data->num_lanes; - if (data->enhanced_frame_cap) - link_config[1] |= DP_LANE_COUNT_ENHANCED_FRAME_EN; - err = drm_dp_dpcd_write(aux, DP_LINK_BW_SET, link_config, 2); - if (err < 0) - return err; - test_pattern = data->phy_pattern; if (dp_rev < 0x12) { test_pattern = (test_pattern << 2) & diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c index ab423b0413ee5f0a780b6e30aa9b8f984410f444..4272cd3622f8b56a3b09dde179bcc6afb0b67d7b 100644 --- a/drivers/gpu/drm/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/drm_dp_mst_topology.c @@ -4856,14 +4856,14 @@ void drm_dp_mst_dump_topology(struct seq_file *m, seq_printf(m, "dpcd: %*ph\n", DP_RECEIVER_CAP_SIZE, buf); ret = drm_dp_dpcd_read(mgr->aux, DP_FAUX_CAP, buf, 2); - if (ret) { + if (ret != 2) { seq_printf(m, "faux/mst read failed\n"); goto out; } seq_printf(m, "faux/mst: %*ph\n", 2, buf); ret = drm_dp_dpcd_read(mgr->aux, DP_MSTM_CTRL, buf, 1); - if (ret) { + if (ret != 1) { seq_printf(m, "mst ctrl read failed\n"); goto out; } @@ -4871,7 +4871,7 @@ void drm_dp_mst_dump_topology(struct seq_file *m, /* dump the standard OUI branch header */ ret = drm_dp_dpcd_read(mgr->aux, DP_BRANCH_OUI, buf, DP_BRANCH_OUI_HEADER_SIZE); - if (ret) { + if (ret != DP_BRANCH_OUI_HEADER_SIZE) { seq_printf(m, "branch oui read failed\n"); goto out; } diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c index 006e3b896caea7ed28a9c3df19bb5b134eef9ab9..4ca995ce19af6191a6495fc682c7e88f850b054b 100644 --- a/drivers/gpu/drm/drm_drv.c +++ b/drivers/gpu/drm/drm_drv.c @@ -610,7 +610,7 @@ static int drm_dev_init(struct drm_device *dev, mutex_init(&dev->clientlist_mutex); mutex_init(&dev->master_mutex); - ret = drmm_add_action(dev, drm_dev_init_release, NULL); + ret = drmm_add_action_or_reset(dev, drm_dev_init_release, NULL); if (ret) return ret; diff --git a/drivers/gpu/drm/drm_internal.h b/drivers/gpu/drm/drm_internal.h index f80e0f28087d17ee86a724a95aef46bd7501960d..41efe40bc70f6e9b0faf3278e38b23ed6caed123 100644 --- a/drivers/gpu/drm/drm_internal.h +++ b/drivers/gpu/drm/drm_internal.h @@ -116,7 +116,8 @@ static inline void drm_vblank_flush_worker(struct drm_vblank_crtc *vblank) static inline void drm_vblank_destroy_worker(struct drm_vblank_crtc *vblank) { - kthread_destroy_worker(vblank->worker); + if (vblank->worker) + kthread_destroy_worker(vblank->worker); } int drm_vblank_worker_init(struct drm_vblank_crtc *vblank); diff --git a/drivers/gpu/drm/drm_ioctl.c b/drivers/gpu/drm/drm_ioctl.c index 9aa3909fb6cd2fa558061bfc729e3233136317b4..ea22102a4b55aea20e24810be89a456caf099bb5 100644 --- a/drivers/gpu/drm/drm_ioctl.c +++ b/drivers/gpu/drm/drm_ioctl.c @@ -473,7 +473,13 @@ EXPORT_SYMBOL(drm_invalid_op); */ static int drm_copy_field(char __user *buf, size_t *buf_len, const char *value) { - int len; + size_t len; + + /* don't attempt to copy a NULL pointer */ + if (WARN_ONCE(!value, "BUG: the value to copy was not set!")) { + *buf_len = 0; + return 0; + } /* don't overflow userbuf */ len = strlen(value); diff --git a/drivers/gpu/drm/drm_mipi_dsi.c b/drivers/gpu/drm/drm_mipi_dsi.c index 946ae45f9664a7820539f50df3999442ce1c7c80..4c81d600a38df4948b951e465fb1c347e932a5d7 100644 --- a/drivers/gpu/drm/drm_mipi_dsi.c +++ b/drivers/gpu/drm/drm_mipi_dsi.c @@ -301,6 +301,7 @@ static int mipi_dsi_remove_device_fn(struct device *dev, void *priv) { struct mipi_dsi_device *dsi = to_mipi_dsi_device(dev); + mipi_dsi_detach(dsi); mipi_dsi_device_unregister(dsi); return 0; diff --git a/drivers/gpu/drm/drm_panel_orientation_quirks.c b/drivers/gpu/drm/drm_panel_orientation_quirks.c index f5ab891731d0b3821ed123c4e5548bace813cc9c..ca0fefeaab20b22504987bcd78c1ef9176976469 100644 --- a/drivers/gpu/drm/drm_panel_orientation_quirks.c +++ b/drivers/gpu/drm/drm_panel_orientation_quirks.c @@ -128,6 +128,18 @@ static const struct dmi_system_id orientation_data[] = { DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "One S1003"), }, .driver_data = (void *)&lcd800x1280_rightside_up, + }, { /* Acer Switch V 10 (SW5-017) */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "SW5-017"), + }, + .driver_data = (void *)&lcd800x1280_rightside_up, + }, { /* Anbernic Win600 */ + .matches = { + DMI_EXACT_MATCH(DMI_BOARD_VENDOR, "Anbernic"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "Win600"), + }, + .driver_data = (void *)&lcd720x1280_rightside_up, }, { /* Asus T100HA */ .matches = { DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), diff --git a/drivers/gpu/drm/i915/display/intel_sdvo.c b/drivers/gpu/drm/i915/display/intel_sdvo.c index 4eaa4aa86ecdf68518e688928d3ac3b44904dfc9..58f8fb7c8799c2bd85ae3a272185aec112fff655 100644 --- a/drivers/gpu/drm/i915/display/intel_sdvo.c +++ b/drivers/gpu/drm/i915/display/intel_sdvo.c @@ -2760,13 +2760,10 @@ intel_sdvo_dvi_init(struct intel_sdvo *intel_sdvo, int device) if (!intel_sdvo_connector) return false; - if (device == 0) { - intel_sdvo->controlled_output |= SDVO_OUTPUT_TMDS0; + if (device == 0) intel_sdvo_connector->output_flag = SDVO_OUTPUT_TMDS0; - } else if (device == 1) { - intel_sdvo->controlled_output |= SDVO_OUTPUT_TMDS1; + else if (device == 1) intel_sdvo_connector->output_flag = SDVO_OUTPUT_TMDS1; - } intel_connector = &intel_sdvo_connector->base; connector = &intel_connector->base; @@ -2821,7 +2818,6 @@ intel_sdvo_tv_init(struct intel_sdvo *intel_sdvo, int type) encoder->encoder_type = DRM_MODE_ENCODER_TVDAC; connector->connector_type = DRM_MODE_CONNECTOR_SVIDEO; - intel_sdvo->controlled_output |= type; intel_sdvo_connector->output_flag = type; if (intel_sdvo_connector_init(intel_sdvo_connector, intel_sdvo) < 0) { @@ -2862,13 +2858,10 @@ intel_sdvo_analog_init(struct intel_sdvo *intel_sdvo, int device) encoder->encoder_type = DRM_MODE_ENCODER_DAC; connector->connector_type = DRM_MODE_CONNECTOR_VGA; - if (device == 0) { - intel_sdvo->controlled_output |= SDVO_OUTPUT_RGB0; + if (device == 0) intel_sdvo_connector->output_flag = SDVO_OUTPUT_RGB0; - } else if (device == 1) { - intel_sdvo->controlled_output |= SDVO_OUTPUT_RGB1; + else if (device == 1) intel_sdvo_connector->output_flag = SDVO_OUTPUT_RGB1; - } if (intel_sdvo_connector_init(intel_sdvo_connector, intel_sdvo) < 0) { kfree(intel_sdvo_connector); @@ -2898,13 +2891,10 @@ intel_sdvo_lvds_init(struct intel_sdvo *intel_sdvo, int device) encoder->encoder_type = DRM_MODE_ENCODER_LVDS; connector->connector_type = DRM_MODE_CONNECTOR_LVDS; - if (device == 0) { - intel_sdvo->controlled_output |= SDVO_OUTPUT_LVDS0; + if (device == 0) intel_sdvo_connector->output_flag = SDVO_OUTPUT_LVDS0; - } else if (device == 1) { - intel_sdvo->controlled_output |= SDVO_OUTPUT_LVDS1; + else if (device == 1) intel_sdvo_connector->output_flag = SDVO_OUTPUT_LVDS1; - } if (intel_sdvo_connector_init(intel_sdvo_connector, intel_sdvo) < 0) { kfree(intel_sdvo_connector); @@ -2937,16 +2927,39 @@ err: return false; } +static u16 intel_sdvo_filter_output_flags(u16 flags) +{ + flags &= SDVO_OUTPUT_MASK; + + /* SDVO requires XXX1 function may not exist unless it has XXX0 function.*/ + if (!(flags & SDVO_OUTPUT_TMDS0)) + flags &= ~SDVO_OUTPUT_TMDS1; + + if (!(flags & SDVO_OUTPUT_RGB0)) + flags &= ~SDVO_OUTPUT_RGB1; + + if (!(flags & SDVO_OUTPUT_LVDS0)) + flags &= ~SDVO_OUTPUT_LVDS1; + + return flags; +} + static bool intel_sdvo_output_setup(struct intel_sdvo *intel_sdvo, u16 flags) { - /* SDVO requires XXX1 function may not exist unless it has XXX0 function.*/ + struct drm_i915_private *i915 = to_i915(intel_sdvo->base.base.dev); + + flags = intel_sdvo_filter_output_flags(flags); + + intel_sdvo->controlled_output = flags; + + intel_sdvo_select_ddc_bus(i915, intel_sdvo); if (flags & SDVO_OUTPUT_TMDS0) if (!intel_sdvo_dvi_init(intel_sdvo, 0)) return false; - if ((flags & SDVO_TMDS_MASK) == SDVO_TMDS_MASK) + if (flags & SDVO_OUTPUT_TMDS1) if (!intel_sdvo_dvi_init(intel_sdvo, 1)) return false; @@ -2967,7 +2980,7 @@ intel_sdvo_output_setup(struct intel_sdvo *intel_sdvo, u16 flags) if (!intel_sdvo_analog_init(intel_sdvo, 0)) return false; - if ((flags & SDVO_RGB_MASK) == SDVO_RGB_MASK) + if (flags & SDVO_OUTPUT_RGB1) if (!intel_sdvo_analog_init(intel_sdvo, 1)) return false; @@ -2975,14 +2988,13 @@ intel_sdvo_output_setup(struct intel_sdvo *intel_sdvo, u16 flags) if (!intel_sdvo_lvds_init(intel_sdvo, 0)) return false; - if ((flags & SDVO_LVDS_MASK) == SDVO_LVDS_MASK) + if (flags & SDVO_OUTPUT_LVDS1) if (!intel_sdvo_lvds_init(intel_sdvo, 1)) return false; - if ((flags & SDVO_OUTPUT_MASK) == 0) { + if (flags == 0) { unsigned char bytes[2]; - intel_sdvo->controlled_output = 0; memcpy(bytes, &intel_sdvo->caps.output_flags, 2); DRM_DEBUG_KMS("%s: Unknown SDVO output type (0x%02x%02x)\n", SDVO_NAME(intel_sdvo), @@ -3394,8 +3406,6 @@ bool intel_sdvo_init(struct drm_i915_private *dev_priv, */ intel_sdvo->base.cloneable = 0; - intel_sdvo_select_ddc_bus(dev_priv, intel_sdvo); - /* Set the input timing to the screen. Assume always input 0. */ if (!intel_sdvo_set_target_input(intel_sdvo)) goto err_output; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c index 8dd295dbe241689bf440ff17ea0b1b0fb0c801d2..dd35d3d7ad03d5b8dc6214c09b7b075f5aff8171 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c @@ -36,13 +36,13 @@ static struct sg_table *i915_gem_map_dma_buf(struct dma_buf_attachment *attachme goto err_unpin_pages; } - ret = sg_alloc_table(st, obj->mm.pages->nents, GFP_KERNEL); + ret = sg_alloc_table(st, obj->mm.pages->orig_nents, GFP_KERNEL); if (ret) goto err_free; src = obj->mm.pages->sgl; dst = st->sgl; - for (i = 0; i < obj->mm.pages->nents; i++) { + for (i = 0; i < obj->mm.pages->orig_nents; i++) { sg_set_page(dst, sg_page(src), src->length, 0); dst = sg_next(dst); src = sg_next(src); diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c index a33887f2464faf6cf5bab9593d511e845080ad87..5f86d9aacb8a31a320acb11dc70bdb4fd85674f9 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt.c +++ b/drivers/gpu/drm/i915/gt/intel_gt.c @@ -745,6 +745,10 @@ void intel_gt_invalidate_tlbs(struct intel_gt *gt) if (!i915_mmio_reg_offset(rb.reg)) continue; + if (INTEL_GEN(i915) == 12 && (engine->class == VIDEO_DECODE_CLASS || + engine->class == VIDEO_ENHANCEMENT_CLASS)) + rb.bit = _MASKED_BIT_ENABLE(rb.bit); + intel_uncore_write_fw(uncore, rb.reg, rb.bit); } diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 2f2dc029668bc7f85f5d787bb183621811e61897..1b5e8d3e45a98f8e41eb168bf5dbd410e7a55b72 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -5145,10 +5145,14 @@ skl_compute_wm_params(const struct intel_crtc_state *crtc_state, wp->y_tiled = modifier == I915_FORMAT_MOD_Y_TILED || modifier == I915_FORMAT_MOD_Yf_TILED || modifier == I915_FORMAT_MOD_Y_TILED_CCS || - modifier == I915_FORMAT_MOD_Yf_TILED_CCS; + modifier == I915_FORMAT_MOD_Yf_TILED_CCS || + modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS || + modifier == I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS; wp->x_tiled = modifier == I915_FORMAT_MOD_X_TILED; wp->rc_surface = modifier == I915_FORMAT_MOD_Y_TILED_CCS || - modifier == I915_FORMAT_MOD_Yf_TILED_CCS; + modifier == I915_FORMAT_MOD_Yf_TILED_CCS || + modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS || + modifier == I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS; wp->is_planar = intel_format_info_is_yuv_semiplanar(format, modifier); wp->width = width; diff --git a/drivers/gpu/drm/imx/imx-tve.c b/drivers/gpu/drm/imx/imx-tve.c index 2a8d2e32e7b42678850cf9758019653cc4957882..9fe6a47331067d78d426b0af499f2d879f03f6be 100644 --- a/drivers/gpu/drm/imx/imx-tve.c +++ b/drivers/gpu/drm/imx/imx-tve.c @@ -212,8 +212,9 @@ static int imx_tve_connector_get_modes(struct drm_connector *connector) return ret; } -static int imx_tve_connector_mode_valid(struct drm_connector *connector, - struct drm_display_mode *mode) +static enum drm_mode_status +imx_tve_connector_mode_valid(struct drm_connector *connector, + struct drm_display_mode *mode) { struct imx_tve *tve = con_to_tve(connector); unsigned long rate; diff --git a/drivers/gpu/drm/meson/meson_drv.c b/drivers/gpu/drm/meson/meson_drv.c index 2d022f3fb437ed93226f023e8fc817460f8c452c..b0bfe85f5f6a81f4f33e042391286faa7fbca0cb 100644 --- a/drivers/gpu/drm/meson/meson_drv.c +++ b/drivers/gpu/drm/meson/meson_drv.c @@ -528,6 +528,13 @@ static int meson_drv_probe(struct platform_device *pdev) return 0; }; +static int meson_drv_remove(struct platform_device *pdev) +{ + component_master_del(&pdev->dev, &meson_drv_master_ops); + + return 0; +} + static struct meson_drm_match_data meson_drm_gxbb_data = { .compat = VPU_COMPATIBLE_GXBB, }; @@ -565,6 +572,7 @@ static const struct dev_pm_ops meson_drv_pm_ops = { static struct platform_driver meson_drm_platform_driver = { .probe = meson_drv_probe, + .remove = meson_drv_remove, .shutdown = meson_drv_shutdown, .driver = { .name = "meson-drm", diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c index 7503f093f3b644f588273ea289bbe8dda4cbf365..b7841f7fc10a8c754323b5b22e07022e48bdb6ea 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c @@ -675,12 +675,10 @@ static void _dpu_kms_hw_destroy(struct dpu_kms *dpu_kms) _dpu_kms_mmu_destroy(dpu_kms); if (dpu_kms->catalog) { - for (i = 0; i < dpu_kms->catalog->vbif_count; i++) { - u32 vbif_idx = dpu_kms->catalog->vbif[i].id; - - if ((vbif_idx < VBIF_MAX) && dpu_kms->hw_vbif[vbif_idx]) { - dpu_hw_vbif_destroy(dpu_kms->hw_vbif[vbif_idx]); - dpu_kms->hw_vbif[vbif_idx] = NULL; + for (i = 0; i < ARRAY_SIZE(dpu_kms->hw_vbif); i++) { + if (dpu_kms->hw_vbif[i]) { + dpu_hw_vbif_destroy(dpu_kms->hw_vbif[i]); + dpu_kms->hw_vbif[i] = NULL; } } } @@ -987,7 +985,7 @@ static int dpu_kms_hw_init(struct msm_kms *kms) for (i = 0; i < dpu_kms->catalog->vbif_count; i++) { u32 vbif_idx = dpu_kms->catalog->vbif[i].id; - dpu_kms->hw_vbif[i] = dpu_hw_vbif_init(vbif_idx, + dpu_kms->hw_vbif[vbif_idx] = dpu_hw_vbif_init(vbif_idx, dpu_kms->vbif[vbif_idx], dpu_kms->catalog); if (IS_ERR_OR_NULL(dpu_kms->hw_vbif[vbif_idx])) { rc = PTR_ERR(dpu_kms->hw_vbif[vbif_idx]); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.c index 5e8c3f3e662563e759d8255174efb7cef1f93f78..fc86d34aec805004ffcd42d60abd55341287aab3 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.c @@ -11,6 +11,14 @@ #include "dpu_hw_vbif.h" #include "dpu_trace.h" +static struct dpu_hw_vbif *dpu_get_vbif(struct dpu_kms *dpu_kms, enum dpu_vbif vbif_idx) +{ + if (vbif_idx < ARRAY_SIZE(dpu_kms->hw_vbif)) + return dpu_kms->hw_vbif[vbif_idx]; + + return NULL; +} + /** * _dpu_vbif_wait_for_xin_halt - wait for the xin to halt * @vbif: Pointer to hardware vbif driver @@ -148,20 +156,15 @@ exit: void dpu_vbif_set_ot_limit(struct dpu_kms *dpu_kms, struct dpu_vbif_set_ot_params *params) { - struct dpu_hw_vbif *vbif = NULL; + struct dpu_hw_vbif *vbif; struct dpu_hw_mdp *mdp; bool forced_on = false; u32 ot_lim; - int ret, i; + int ret; mdp = dpu_kms->hw_mdp; - for (i = 0; i < ARRAY_SIZE(dpu_kms->hw_vbif); i++) { - if (dpu_kms->hw_vbif[i] && - dpu_kms->hw_vbif[i]->idx == params->vbif_idx) - vbif = dpu_kms->hw_vbif[i]; - } - + vbif = dpu_get_vbif(dpu_kms, params->vbif_idx); if (!vbif || !mdp) { DPU_DEBUG("invalid arguments vbif %d mdp %d\n", vbif != NULL, mdp != NULL); @@ -204,7 +207,7 @@ void dpu_vbif_set_ot_limit(struct dpu_kms *dpu_kms, void dpu_vbif_set_qos_remap(struct dpu_kms *dpu_kms, struct dpu_vbif_set_qos_params *params) { - struct dpu_hw_vbif *vbif = NULL; + struct dpu_hw_vbif *vbif; struct dpu_hw_mdp *mdp; bool forced_on = false; const struct dpu_vbif_qos_tbl *qos_tbl; @@ -216,13 +219,7 @@ void dpu_vbif_set_qos_remap(struct dpu_kms *dpu_kms, } mdp = dpu_kms->hw_mdp; - for (i = 0; i < ARRAY_SIZE(dpu_kms->hw_vbif); i++) { - if (dpu_kms->hw_vbif[i] && - dpu_kms->hw_vbif[i]->idx == params->vbif_idx) { - vbif = dpu_kms->hw_vbif[i]; - break; - } - } + vbif = dpu_get_vbif(dpu_kms, params->vbif_idx); if (!vbif || !vbif->cap) { DPU_ERROR("invalid vbif %d\n", params->vbif_idx); diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_connector.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_connector.c index 7288041dd86ad806e0843939c5c1036ff338d955..7444b75c4215794f544553d7dee552718dad947d 100644 --- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_connector.c +++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_connector.c @@ -56,8 +56,9 @@ static int mdp4_lvds_connector_get_modes(struct drm_connector *connector) return ret; } -static int mdp4_lvds_connector_mode_valid(struct drm_connector *connector, - struct drm_display_mode *mode) +static enum drm_mode_status +mdp4_lvds_connector_mode_valid(struct drm_connector *connector, + struct drm_display_mode *mode) { struct mdp4_lvds_connector *mdp4_lvds_connector = to_mdp4_lvds_connector(connector); diff --git a/drivers/gpu/drm/msm/dp/dp_catalog.c b/drivers/gpu/drm/msm/dp/dp_catalog.c index 2da6982efdbfc1a44b0fc74a522334da8bef8b66..613348b022fe82e34f2614cee0e47c9112c82f69 100644 --- a/drivers/gpu/drm/msm/dp/dp_catalog.c +++ b/drivers/gpu/drm/msm/dp/dp_catalog.c @@ -416,7 +416,7 @@ void dp_catalog_ctrl_config_msa(struct dp_catalog *dp_catalog, if (rate == link_rate_hbr3) pixel_div = 6; - else if (rate == 1620000 || rate == 270000) + else if (rate == 162000 || rate == 270000) pixel_div = 2; else if (rate == link_rate_hbr2) pixel_div = 4; diff --git a/drivers/gpu/drm/msm/dp/dp_display.c b/drivers/gpu/drm/msm/dp/dp_display.c index a3de1d0523ea083df106d30fcc89c0a26e4e28b2..5a152d505dfb9c5c6a01368ba2918b480c0179ce 100644 --- a/drivers/gpu/drm/msm/dp/dp_display.c +++ b/drivers/gpu/drm/msm/dp/dp_display.c @@ -1201,7 +1201,7 @@ int dp_display_request_irq(struct msm_dp *dp_display) return -EINVAL; } - rc = devm_request_irq(&dp->pdev->dev, dp->irq, + rc = devm_request_irq(dp_display->drm_dev->dev, dp->irq, dp_display_irq_handler, IRQF_TRIGGER_HIGH, "dp_display_isr", dp); if (rc < 0) { diff --git a/drivers/gpu/drm/msm/dsi/dsi.c b/drivers/gpu/drm/msm/dsi/dsi.c index f845333593daa7d1821f54536e8dbc41fb901786..7377596a13f4b2818c15da08df9be8df8a9c3ee6 100644 --- a/drivers/gpu/drm/msm/dsi/dsi.c +++ b/drivers/gpu/drm/msm/dsi/dsi.c @@ -205,6 +205,12 @@ int msm_dsi_modeset_init(struct msm_dsi *msm_dsi, struct drm_device *dev, return -EINVAL; priv = dev->dev_private; + + if (priv->num_bridges == ARRAY_SIZE(priv->bridges)) { + DRM_DEV_ERROR(dev->dev, "too many bridges\n"); + return -ENOSPC; + } + msm_dsi->dev = dev; ret = msm_dsi_host_modeset_init(msm_dsi->host, dev); diff --git a/drivers/gpu/drm/msm/hdmi/hdmi.c b/drivers/gpu/drm/msm/hdmi/hdmi.c index 28b33b35a30cec7a2b57cf6053cfab42153dd3b5..bd65dc9b889232c78d0f362f5e1a9a7b3357ee4c 100644 --- a/drivers/gpu/drm/msm/hdmi/hdmi.c +++ b/drivers/gpu/drm/msm/hdmi/hdmi.c @@ -293,6 +293,11 @@ int msm_hdmi_modeset_init(struct hdmi *hdmi, struct platform_device *pdev = hdmi->pdev; int ret; + if (priv->num_bridges == ARRAY_SIZE(priv->bridges)) { + DRM_DEV_ERROR(dev->dev, "too many bridges\n"); + return -ENOSPC; + } + hdmi->dev = dev; hdmi->encoder = encoder; @@ -321,8 +326,8 @@ int msm_hdmi_modeset_init(struct hdmi *hdmi, goto fail; } - ret = devm_request_irq(&pdev->dev, hdmi->irq, - msm_hdmi_irq, IRQF_TRIGGER_HIGH | IRQF_ONESHOT, + ret = devm_request_irq(dev->dev, hdmi->irq, + msm_hdmi_irq, IRQF_TRIGGER_HIGH, "hdmi_isr", hdmi); if (ret < 0) { DRM_DEV_ERROR(dev->dev, "failed to request IRQ%u: %d\n", diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c index 5679552cde32cb050a11c48fd17405259f590c9f..44fc23e5054a060791cd6e3e20ac3f08da6e953c 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.c +++ b/drivers/gpu/drm/nouveau/nouveau_bo.c @@ -279,8 +279,10 @@ nouveau_bo_alloc(struct nouveau_cli *cli, u64 *size, int *align, u32 domain, break; } - if (WARN_ON(pi < 0)) + if (WARN_ON(pi < 0)) { + kfree(nvbo); return ERR_PTR(-EINVAL); + } /* Disable compression if suitable settings couldn't be found. */ if (nvbo->comp && !vmm->page[pi].comp) { diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.c b/drivers/gpu/drm/nouveau/nouveau_connector.c index 4c992fd5bd68a9d8d5c33257d54c22a2f6951fb5..9542fc63e79685a52e5796954551e4500ad4a0bb 100644 --- a/drivers/gpu/drm/nouveau/nouveau_connector.c +++ b/drivers/gpu/drm/nouveau/nouveau_connector.c @@ -500,7 +500,8 @@ nouveau_connector_set_encoder(struct drm_connector *connector, connector->interlace_allowed = nv_encoder->caps.dp_interlace; else - connector->interlace_allowed = true; + connector->interlace_allowed = + drm->client.device.info.family < NV_DEVICE_INFO_V0_VOLTA; connector->doublescan_allowed = true; } else if (nv_encoder->dcb->type == DCB_OUTPUT_LVDS || diff --git a/drivers/gpu/drm/nouveau/nouveau_prime.c b/drivers/gpu/drm/nouveau/nouveau_prime.c index 5f5b87f99546832e53d4e678bb9faeb30d9cba3d..f08bda533bd943e0b08a1c53052099e410cb37dc 100644 --- a/drivers/gpu/drm/nouveau/nouveau_prime.c +++ b/drivers/gpu/drm/nouveau/nouveau_prime.c @@ -89,7 +89,6 @@ struct drm_gem_object *nouveau_gem_prime_import_sg_table(struct drm_device *dev, ret = nouveau_bo_init(nvbo, size, align, NOUVEAU_GEM_DOMAIN_GART, sg, robj); if (ret) { - nouveau_bo_ref(NULL, &nvbo); obj = ERR_PTR(ret); goto unlock; } diff --git a/drivers/gpu/drm/omapdrm/dss/dss.c b/drivers/gpu/drm/omapdrm/dss/dss.c index 6ccbc29c4ce4bbbdc8950e4041620e061166ffa1..d5b3123ed081e92fb6ccf2d594727a0027917f7c 100644 --- a/drivers/gpu/drm/omapdrm/dss/dss.c +++ b/drivers/gpu/drm/omapdrm/dss/dss.c @@ -1173,6 +1173,7 @@ static void __dss_uninit_ports(struct dss_device *dss, unsigned int num_ports) default: break; } + of_node_put(port); } } @@ -1205,11 +1206,13 @@ static int dss_init_ports(struct dss_device *dss) default: break; } + of_node_put(port); } return 0; error: + of_node_put(port); __dss_uninit_ports(dss, i); return r; } diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c index b7b37082a9d72c7b7d518dcc79a86ad5331664ed..1a87cc445b5e115936d88903355cec3f30fab1fc 100644 --- a/drivers/gpu/drm/panel/panel-simple.c +++ b/drivers/gpu/drm/panel/panel-simple.c @@ -2655,6 +2655,7 @@ static const struct display_timing logictechno_lt161010_2nh_timing = { static const struct panel_desc logictechno_lt161010_2nh = { .timings = &logictechno_lt161010_2nh_timing, .num_timings = 1, + .bpc = 6, .size = { .width = 154, .height = 86, @@ -2684,6 +2685,7 @@ static const struct display_timing logictechno_lt170410_2whc_timing = { static const struct panel_desc logictechno_lt170410_2whc = { .timings = &logictechno_lt170410_2whc_timing, .num_timings = 1, + .bpc = 8, .size = { .width = 217, .height = 136, diff --git a/drivers/gpu/drm/pl111/pl111_versatile.c b/drivers/gpu/drm/pl111/pl111_versatile.c index bdd883f4f0da520b18cfb9fbfb6995918b8cb639..963a5d5e6987a592e75c4dcbd8f92d63e54f1cf8 100644 --- a/drivers/gpu/drm/pl111/pl111_versatile.c +++ b/drivers/gpu/drm/pl111/pl111_versatile.c @@ -402,6 +402,7 @@ static int pl111_vexpress_clcd_init(struct device *dev, struct device_node *np, if (of_device_is_compatible(child, "arm,pl111")) { has_coretile_clcd = true; ct_clcd = child; + of_node_put(child); break; } if (of_device_is_compatible(child, "arm,hdlcd")) { diff --git a/drivers/gpu/drm/rockchip/dw-mipi-dsi-rockchip.c b/drivers/gpu/drm/rockchip/dw-mipi-dsi-rockchip.c index b0fb3c3cba5962a151263af9365677838737d23a..c51be1c9c20704dde6a93d27d5ac844a64a73f04 100644 --- a/drivers/gpu/drm/rockchip/dw-mipi-dsi-rockchip.c +++ b/drivers/gpu/drm/rockchip/dw-mipi-dsi-rockchip.c @@ -1286,5 +1286,11 @@ struct platform_driver dw_mipi_dsi_rockchip_driver = { .of_match_table = dw_mipi_dsi_rockchip_dt_ids, .pm = &dw_mipi_dsi_rockchip_pm_ops, .name = "dw-mipi-dsi-rockchip", + /* + * For dual-DSI display, one DSI pokes at the other DSI's + * drvdata in dw_mipi_dsi_rockchip_find_second(). This is not + * safe for asynchronous probe. + */ + .probe_type = PROBE_FORCE_SYNCHRONOUS, }, }; diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c index 2c6ebc328b24f6c88a713ad43d16a142191084a1..318692ad9680f40771836837bc7a87bd42a858ac 100644 --- a/drivers/gpu/drm/tegra/drm.c +++ b/drivers/gpu/drm/tegra/drm.c @@ -1042,6 +1042,10 @@ static bool host1x_drm_wants_iommu(struct host1x_device *dev) struct host1x *host1x = dev_get_drvdata(dev->dev.parent); struct iommu_domain *domain; + /* Our IOMMU usage policy doesn't currently play well with GART */ + if (of_machine_is_compatible("nvidia,tegra20")) + return false; + /* * If the Tegra DRM clients are backed by an IOMMU, push buffers are * likely to be allocated beyond the 32-bit boundary if sufficient diff --git a/drivers/gpu/drm/udl/udl_modeset.c b/drivers/gpu/drm/udl/udl_modeset.c index edcfd8c120c44c07cf2038fc0a4a658ee7c3851d..209b5ceba3e00ec639db47d3fa56610ce8a62c7a 100644 --- a/drivers/gpu/drm/udl/udl_modeset.c +++ b/drivers/gpu/drm/udl/udl_modeset.c @@ -400,9 +400,6 @@ udl_simple_display_pipe_enable(struct drm_simple_display_pipe *pipe, udl_handle_damage(fb, 0, 0, fb->width, fb->height); - if (!crtc_state->mode_changed) - return; - /* enable display */ udl_crtc_write_mode_to_hw(crtc); } diff --git a/drivers/gpu/drm/vc4/vc4_drv.c b/drivers/gpu/drm/vc4/vc4_drv.c index 52426bc8edb8bb282553b2dcd740ab33522df999..888aec1bbeee67cce34625af32c603c907ef3ea4 100644 --- a/drivers/gpu/drm/vc4/vc4_drv.c +++ b/drivers/gpu/drm/vc4/vc4_drv.c @@ -404,7 +404,12 @@ static int __init vc4_drm_register(void) if (ret) return ret; - return platform_driver_register(&vc4_platform_driver); + ret = platform_driver_register(&vc4_platform_driver); + if (ret) + platform_unregister_drivers(component_drivers, + ARRAY_SIZE(component_drivers)); + + return ret; } static void __exit vc4_drm_unregister(void) diff --git a/drivers/gpu/drm/vc4/vc4_vec.c b/drivers/gpu/drm/vc4/vc4_vec.c index bd5b8eb58b180696b217f914d550af1419a2978d..c6bd168a5898303a8706e73a5b4380f94f63cb87 100644 --- a/drivers/gpu/drm/vc4/vc4_vec.c +++ b/drivers/gpu/drm/vc4/vc4_vec.c @@ -257,7 +257,7 @@ static void vc4_vec_ntsc_j_mode_set(struct vc4_vec *vec) static const struct drm_display_mode ntsc_mode = { DRM_MODE("720x480", DRM_MODE_TYPE_DRIVER, 13500, 720, 720 + 14, 720 + 14 + 64, 720 + 14 + 64 + 60, 0, - 480, 480 + 3, 480 + 3 + 3, 480 + 3 + 3 + 16, 0, + 480, 480 + 7, 480 + 7 + 6, 525, 0, DRM_MODE_FLAG_INTERLACE) }; @@ -279,7 +279,7 @@ static void vc4_vec_pal_m_mode_set(struct vc4_vec *vec) static const struct drm_display_mode pal_mode = { DRM_MODE("720x576", DRM_MODE_TYPE_DRIVER, 13500, 720, 720 + 20, 720 + 20 + 64, 720 + 20 + 64 + 60, 0, - 576, 576 + 2, 576 + 2 + 3, 576 + 2 + 3 + 20, 0, + 576, 576 + 4, 576 + 4 + 6, 625, 0, DRM_MODE_FLAG_INTERLACE) }; diff --git a/drivers/gpu/drm/virtio/virtgpu_plane.c b/drivers/gpu/drm/virtio/virtgpu_plane.c index bc15db7e0f1485a81739cab99ce37a1a91f5be5e..9028ba669e493c74b0652d650ad8e411a9e76e96 100644 --- a/drivers/gpu/drm/virtio/virtgpu_plane.c +++ b/drivers/gpu/drm/virtio/virtgpu_plane.c @@ -259,14 +259,14 @@ static int virtio_gpu_cursor_prepare_fb(struct drm_plane *plane, } static void virtio_gpu_cursor_cleanup_fb(struct drm_plane *plane, - struct drm_plane_state *old_state) + struct drm_plane_state *state) { struct virtio_gpu_framebuffer *vgfb; - if (!plane->state->fb) + if (!state->fb) return; - vgfb = to_virtio_gpu_framebuffer(plane->state->fb); + vgfb = to_virtio_gpu_framebuffer(state->fb); if (vgfb->fence) { dma_fence_put(&vgfb->fence->f); vgfb->fence = NULL; diff --git a/drivers/gpu/drm/virtio/virtgpu_vq.c b/drivers/gpu/drm/virtio/virtgpu_vq.c index 5e40fa0f5e8f2dc8f439971a7e2a5dfc4903760f..e98a29d243c087063e39619dd10be4f70bc505ed 100644 --- a/drivers/gpu/drm/virtio/virtgpu_vq.c +++ b/drivers/gpu/drm/virtio/virtgpu_vq.c @@ -601,7 +601,7 @@ void virtio_gpu_cmd_transfer_to_host_2d(struct virtio_gpu_device *vgdev, bool use_dma_api = !virtio_has_dma_quirk(vgdev->vdev); struct virtio_gpu_object_shmem *shmem = to_virtio_gpu_shmem(bo); - if (use_dma_api) + if (virtio_gpu_is_shmem(bo) && use_dma_api) dma_sync_sgtable_for_device(vgdev->vdev->dev.parent, shmem->pages, DMA_TO_DEVICE); diff --git a/drivers/gpu/host1x/dev.c b/drivers/gpu/host1x/dev.c index 8659558b518d6afc3100c19631363c42e6fe1b43..9f674a8d5009dbdb4a561743c6aa9ff1a4d7db4a 100644 --- a/drivers/gpu/host1x/dev.c +++ b/drivers/gpu/host1x/dev.c @@ -198,6 +198,10 @@ static void host1x_setup_sid_table(struct host1x *host) static bool host1x_wants_iommu(struct host1x *host1x) { + /* Our IOMMU usage policy doesn't currently play well with GART */ + if (of_machine_is_compatible("nvidia,tegra20")) + return false; + /* * If we support addressing a maximum of 32 bits of physical memory * and if the host1x firewall is enabled, there's no need to enable diff --git a/drivers/hid/hid-hyperv.c b/drivers/hid/hid-hyperv.c index 978ee2aab2d4010e3bd96f0d3d8a7f9d86384c7e..b7704dd6809dc8786ed5e7db61cbaa0b9847ef07 100644 --- a/drivers/hid/hid-hyperv.c +++ b/drivers/hid/hid-hyperv.c @@ -498,7 +498,7 @@ static int mousevsc_probe(struct hv_device *device, ret = hid_add_device(hid_dev); if (ret) - goto probe_err1; + goto probe_err2; ret = hid_parse(hid_dev); diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 6be1658f7f8b56c7d77ef8ce550b29d2de1a71c0..f2efba89846710baa93ec151904d55a18f22527f 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -827,6 +827,7 @@ #define USB_DEVICE_ID_MADCATZ_BEATPAD 0x4540 #define USB_DEVICE_ID_MADCATZ_RAT5 0x1705 #define USB_DEVICE_ID_MADCATZ_RAT9 0x1709 +#define USB_DEVICE_ID_MADCATZ_MMO7 0x1713 #define USB_VENDOR_ID_MCC 0x09db #define USB_DEVICE_ID_MCC_PMD1024LS 0x0076 @@ -1152,7 +1153,9 @@ #define USB_DEVICE_ID_SYNAPTICS_DELL_K12A 0x2819 #define USB_DEVICE_ID_SYNAPTICS_ACER_SWITCH5_012 0x2968 #define USB_DEVICE_ID_SYNAPTICS_TP_V103 0x5710 +#define USB_DEVICE_ID_SYNAPTICS_ACER_ONE_S1002 0x73f4 #define USB_DEVICE_ID_SYNAPTICS_ACER_ONE_S1003 0x73f5 +#define USB_DEVICE_ID_SYNAPTICS_ACER_SWITCH5_017 0x73f6 #define USB_DEVICE_ID_SYNAPTICS_ACER_SWITCH5 0x81a7 #define USB_VENDOR_ID_TEXAS_INSTRUMENTS 0x2047 diff --git a/drivers/hid/hid-ite.c b/drivers/hid/hid-ite.c index 742c052b0110af4b2b1666d179dd27b6747b02f5..b8cce9c196d8c4d6603fcd2204480cae3e0ea94d 100644 --- a/drivers/hid/hid-ite.c +++ b/drivers/hid/hid-ite.c @@ -18,10 +18,21 @@ static __u8 *ite_report_fixup(struct hid_device *hdev, __u8 *rdesc, unsigned int unsigned long quirks = (unsigned long)hid_get_drvdata(hdev); if (quirks & QUIRK_TOUCHPAD_ON_OFF_REPORT) { + /* For Acer Aspire Switch 10 SW5-012 keyboard-dock */ if (*rsize == 188 && rdesc[162] == 0x81 && rdesc[163] == 0x02) { - hid_info(hdev, "Fixing up ITE keyboard report descriptor\n"); + hid_info(hdev, "Fixing up Acer Sw5-012 ITE keyboard report descriptor\n"); rdesc[163] = HID_MAIN_ITEM_RELATIVE; } + /* For Acer One S1002/S1003 keyboard-dock */ + if (*rsize == 188 && rdesc[185] == 0x81 && rdesc[186] == 0x02) { + hid_info(hdev, "Fixing up Acer S1002/S1003 ITE keyboard report descriptor\n"); + rdesc[186] = HID_MAIN_ITEM_RELATIVE; + } + /* For Acer Aspire Switch 10E (SW3-016) keyboard-dock */ + if (*rsize == 210 && rdesc[184] == 0x81 && rdesc[185] == 0x02) { + hid_info(hdev, "Fixing up Acer Aspire Switch 10E (SW3-016) ITE keyboard report descriptor\n"); + rdesc[185] = HID_MAIN_ITEM_RELATIVE; + } } return rdesc; @@ -103,7 +114,18 @@ static const struct hid_device_id ite_devices[] = { /* ITE8910 USB kbd ctlr, with Synaptics touchpad connected to it. */ { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, USB_VENDOR_ID_SYNAPTICS, - USB_DEVICE_ID_SYNAPTICS_ACER_ONE_S1003) }, + USB_DEVICE_ID_SYNAPTICS_ACER_ONE_S1002), + .driver_data = QUIRK_TOUCHPAD_ON_OFF_REPORT }, + /* ITE8910 USB kbd ctlr, with Synaptics touchpad connected to it. */ + { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, + USB_VENDOR_ID_SYNAPTICS, + USB_DEVICE_ID_SYNAPTICS_ACER_ONE_S1003), + .driver_data = QUIRK_TOUCHPAD_ON_OFF_REPORT }, + /* ITE8910 USB kbd ctlr, with Synaptics touchpad connected to it. */ + { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, + USB_VENDOR_ID_SYNAPTICS, + USB_DEVICE_ID_SYNAPTICS_ACER_SWITCH5_017), + .driver_data = QUIRK_TOUCHPAD_ON_OFF_REPORT }, { } }; MODULE_DEVICE_TABLE(hid, ite_devices); diff --git a/drivers/hid/hid-magicmouse.c b/drivers/hid/hid-magicmouse.c index fc4c07459753909b8c2c187a846bed17fd0fb9de..28158d2f2352306c7a40fe8c4e3980e795aff5ff 100644 --- a/drivers/hid/hid-magicmouse.c +++ b/drivers/hid/hid-magicmouse.c @@ -387,7 +387,7 @@ static int magicmouse_raw_event(struct hid_device *hdev, magicmouse_raw_event(hdev, report, data + 2, data[1]); magicmouse_raw_event(hdev, report, data + 2 + data[1], size - 2 - data[1]); - break; + return 0; default: return 0; } diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c index d686917cc3b1fcdffa19256a9a2af721496bf65e..a78ce16d4782d410aa8db27a12899ee548cbc37f 100644 --- a/drivers/hid/hid-multitouch.c +++ b/drivers/hid/hid-multitouch.c @@ -1155,7 +1155,7 @@ static void mt_touch_report(struct hid_device *hid, int contact_count = -1; /* sticky fingers release in progress, abort */ - if (test_and_set_bit(MT_IO_FLAGS_RUNNING, &td->mt_io_flags)) + if (test_and_set_bit_lock(MT_IO_FLAGS_RUNNING, &td->mt_io_flags)) return; scantime = *app->scantime; @@ -1236,7 +1236,7 @@ static void mt_touch_report(struct hid_device *hid, del_timer(&td->release_timer); } - clear_bit(MT_IO_FLAGS_RUNNING, &td->mt_io_flags); + clear_bit_unlock(MT_IO_FLAGS_RUNNING, &td->mt_io_flags); } static int mt_touch_input_configured(struct hid_device *hdev, @@ -1671,11 +1671,11 @@ static void mt_expired_timeout(struct timer_list *t) * An input report came in just before we release the sticky fingers, * it will take care of the sticky fingers. */ - if (test_and_set_bit(MT_IO_FLAGS_RUNNING, &td->mt_io_flags)) + if (test_and_set_bit_lock(MT_IO_FLAGS_RUNNING, &td->mt_io_flags)) return; if (test_bit(MT_IO_FLAGS_PENDING_SLOTS, &td->mt_io_flags)) mt_release_contacts(hdev); - clear_bit(MT_IO_FLAGS_RUNNING, &td->mt_io_flags); + clear_bit_unlock(MT_IO_FLAGS_RUNNING, &td->mt_io_flags); } static int mt_probe(struct hid_device *hdev, const struct hid_device_id *id) diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c index 2ab71d717bb03935688b2282bb1de4e28343f7f8..4a8014e9a511c515eba4bff9299aee6b9e9a9ace 100644 --- a/drivers/hid/hid-quirks.c +++ b/drivers/hid/hid-quirks.c @@ -609,6 +609,7 @@ static const struct hid_device_id hid_have_special_driver[] = { { HID_USB_DEVICE(USB_VENDOR_ID_SAITEK, USB_DEVICE_ID_SAITEK_MMO7) }, { HID_USB_DEVICE(USB_VENDOR_ID_MADCATZ, USB_DEVICE_ID_MADCATZ_RAT5) }, { HID_USB_DEVICE(USB_VENDOR_ID_MADCATZ, USB_DEVICE_ID_MADCATZ_RAT9) }, + { HID_USB_DEVICE(USB_VENDOR_ID_MADCATZ, USB_DEVICE_ID_MADCATZ_MMO7) }, #endif #if IS_ENABLED(CONFIG_HID_SAMSUNG) { HID_USB_DEVICE(USB_VENDOR_ID_SAMSUNG, USB_DEVICE_ID_SAMSUNG_IR_REMOTE) }, diff --git a/drivers/hid/hid-saitek.c b/drivers/hid/hid-saitek.c index c7bf14c0196057bf568a08053f4c76483cacf4c5..b84e975977c4278711959f7cb8fd2647d3c18032 100644 --- a/drivers/hid/hid-saitek.c +++ b/drivers/hid/hid-saitek.c @@ -187,6 +187,8 @@ static const struct hid_device_id saitek_devices[] = { .driver_data = SAITEK_RELEASE_MODE_RAT7 }, { HID_USB_DEVICE(USB_VENDOR_ID_SAITEK, USB_DEVICE_ID_SAITEK_MMO7), .driver_data = SAITEK_RELEASE_MODE_MMO7 }, + { HID_USB_DEVICE(USB_VENDOR_ID_MADCATZ, USB_DEVICE_ID_MADCATZ_MMO7), + .driver_data = SAITEK_RELEASE_MODE_MMO7 }, { } }; diff --git a/drivers/hid/hid-uclogic-core.c b/drivers/hid/hid-uclogic-core.c index 4edb241957040209672137bc513efa3abf13d970..e4811d37ca775a59e4537f808c6910cf43939534 100644 --- a/drivers/hid/hid-uclogic-core.c +++ b/drivers/hid/hid-uclogic-core.c @@ -172,6 +172,7 @@ static int uclogic_probe(struct hid_device *hdev, * than the pen, so use QUIRK_MULTI_INPUT for all tablets. */ hdev->quirks |= HID_QUIRK_MULTI_INPUT; + hdev->quirks |= HID_QUIRK_HIDINPUT_FORCE; /* Allocate and assign driver data */ drvdata = devm_kzalloc(&hdev->dev, sizeof(*drvdata), GFP_KERNEL); diff --git a/drivers/hsi/controllers/omap_ssi_core.c b/drivers/hsi/controllers/omap_ssi_core.c index 44a3f5660c1090e3eb64c21a8acdbceb641fecb8..eb982015831858b7725f85c26bce24f9c2f9c98f 100644 --- a/drivers/hsi/controllers/omap_ssi_core.c +++ b/drivers/hsi/controllers/omap_ssi_core.c @@ -524,6 +524,7 @@ static int ssi_probe(struct platform_device *pd) if (!childpdev) { err = -ENODEV; dev_err(&pd->dev, "failed to create ssi controller port\n"); + of_node_put(child); goto out3; } } diff --git a/drivers/hsi/controllers/omap_ssi_port.c b/drivers/hsi/controllers/omap_ssi_port.c index a0cb5be246e1cf2ca47f53c5bea5859128474768..b9495b720f1bd121970deaf4f151a517c27b33d4 100644 --- a/drivers/hsi/controllers/omap_ssi_port.c +++ b/drivers/hsi/controllers/omap_ssi_port.c @@ -230,10 +230,10 @@ static int ssi_start_dma(struct hsi_msg *msg, int lch) if (msg->ttype == HSI_MSG_READ) { err = dma_map_sg(&ssi->device, msg->sgt.sgl, msg->sgt.nents, DMA_FROM_DEVICE); - if (err < 0) { + if (!err) { dev_dbg(&ssi->device, "DMA map SG failed !\n"); pm_runtime_put_autosuspend(omap_port->pdev); - return err; + return -EIO; } csdp = SSI_DST_BURST_4x32_BIT | SSI_DST_MEMORY_PORT | SSI_SRC_SINGLE_ACCESS0 | SSI_SRC_PERIPHERAL_PORT | @@ -247,10 +247,10 @@ static int ssi_start_dma(struct hsi_msg *msg, int lch) } else { err = dma_map_sg(&ssi->device, msg->sgt.sgl, msg->sgt.nents, DMA_TO_DEVICE); - if (err < 0) { + if (!err) { dev_dbg(&ssi->device, "DMA map SG failed !\n"); pm_runtime_put_autosuspend(omap_port->pdev); - return err; + return -EIO; } csdp = SSI_SRC_BURST_4x32_BIT | SSI_SRC_MEMORY_PORT | SSI_DST_SINGLE_ACCESS0 | SSI_DST_PERIPHERAL_PORT | diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c index 10188b1a6a089120cc8f5669dc8628a0f8b159bb..5b902adb0d1bf9709dc71f13b99d0a9eab05f468 100644 --- a/drivers/hv/channel_mgmt.c +++ b/drivers/hv/channel_mgmt.c @@ -501,13 +501,17 @@ static void vmbus_add_channel_work(struct work_struct *work) * Add the new device to the bus. This will kick off device-driver * binding which eventually invokes the device driver's AddDevice() * method. + * + * If vmbus_device_register() fails, the 'device_obj' is freed in + * vmbus_device_release() as called by device_unregister() in the + * error path of vmbus_device_register(). In the outside error + * path, there's no need to free it. */ ret = vmbus_device_register(newchannel->device_obj); if (ret != 0) { pr_err("unable to add child device object (relid %d)\n", newchannel->offermsg.child_relid); - kfree(newchannel->device_obj); goto err_deq_chan; } diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index 514279dac7cb5262b8a353cbfb868f20a8799a25..e99400f3ae1d112ab8e94053203abd1e59376f01 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -2020,6 +2020,7 @@ int vmbus_device_register(struct hv_device *child_device_obj) ret = device_register(&child_device_obj->device); if (ret) { pr_err("Unable to register child device\n"); + put_device(&child_device_obj->device); return ret; } diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c index bb9211215a688f8eb06ae11b94a58ae68e368cc9..032129292957ec8cc73cd56ed1e89b9ea086356b 100644 --- a/drivers/hwmon/coretemp.c +++ b/drivers/hwmon/coretemp.c @@ -46,9 +46,6 @@ MODULE_PARM_DESC(tjmax, "TjMax value in degrees Celsius"); #define TOTAL_ATTRS (MAX_CORE_ATTRS + 1) #define MAX_CORE_DATA (NUM_REAL_CORES + BASE_SYSFS_ATTR_NO) -#define TO_CORE_ID(cpu) (cpu_data(cpu).cpu_core_id) -#define TO_ATTR_NO(cpu) (TO_CORE_ID(cpu) + BASE_SYSFS_ATTR_NO) - #ifdef CONFIG_SMP #define for_each_sibling(i, cpu) \ for_each_cpu(i, topology_sibling_cpumask(cpu)) @@ -91,6 +88,8 @@ struct temp_data { struct platform_data { struct device *hwmon_dev; u16 pkg_id; + u16 cpu_map[NUM_REAL_CORES]; + struct ida ida; struct cpumask cpumask; struct temp_data *core_data[MAX_CORE_DATA]; struct device_attribute name_attr; @@ -441,7 +440,7 @@ static struct temp_data *init_temp_data(unsigned int cpu, int pkg_flag) MSR_IA32_THERM_STATUS; tdata->is_pkg_data = pkg_flag; tdata->cpu = cpu; - tdata->cpu_core_id = TO_CORE_ID(cpu); + tdata->cpu_core_id = topology_core_id(cpu); tdata->attr_size = MAX_CORE_ATTRS; mutex_init(&tdata->update_lock); return tdata; @@ -454,7 +453,7 @@ static int create_core_data(struct platform_device *pdev, unsigned int cpu, struct platform_data *pdata = platform_get_drvdata(pdev); struct cpuinfo_x86 *c = &cpu_data(cpu); u32 eax, edx; - int err, attr_no; + int err, index, attr_no; /* * Find attr number for sysfs: @@ -462,14 +461,26 @@ static int create_core_data(struct platform_device *pdev, unsigned int cpu, * The attr number is always core id + 2 * The Pkgtemp will always show up as temp1_*, if available */ - attr_no = pkg_flag ? PKG_SYSFS_ATTR_NO : TO_ATTR_NO(cpu); + if (pkg_flag) { + attr_no = PKG_SYSFS_ATTR_NO; + } else { + index = ida_alloc(&pdata->ida, GFP_KERNEL); + if (index < 0) + return index; + pdata->cpu_map[index] = topology_core_id(cpu); + attr_no = index + BASE_SYSFS_ATTR_NO; + } - if (attr_no > MAX_CORE_DATA - 1) - return -ERANGE; + if (attr_no > MAX_CORE_DATA - 1) { + err = -ERANGE; + goto ida_free; + } tdata = init_temp_data(cpu, pkg_flag); - if (!tdata) - return -ENOMEM; + if (!tdata) { + err = -ENOMEM; + goto ida_free; + } /* Test if we can access the status register */ err = rdmsr_safe_on_cpu(cpu, tdata->status_reg, &eax, &edx); @@ -505,6 +516,9 @@ static int create_core_data(struct platform_device *pdev, unsigned int cpu, exit_free: pdata->core_data[attr_no] = NULL; kfree(tdata); +ida_free: + if (!pkg_flag) + ida_free(&pdata->ida, index); return err; } @@ -524,6 +538,9 @@ static void coretemp_remove_core(struct platform_data *pdata, int indx) kfree(pdata->core_data[indx]); pdata->core_data[indx] = NULL; + + if (indx >= BASE_SYSFS_ATTR_NO) + ida_free(&pdata->ida, indx - BASE_SYSFS_ATTR_NO); } static int coretemp_probe(struct platform_device *pdev) @@ -537,6 +554,7 @@ static int coretemp_probe(struct platform_device *pdev) return -ENOMEM; pdata->pkg_id = pdev->id; + ida_init(&pdata->ida); platform_set_drvdata(pdev, pdata); pdata->hwmon_dev = devm_hwmon_device_register_with_groups(dev, DRVNAME, @@ -553,6 +571,7 @@ static int coretemp_remove(struct platform_device *pdev) if (pdata->core_data[i]) coretemp_remove_core(pdata, i); + ida_destroy(&pdata->ida); return 0; } @@ -647,7 +666,7 @@ static int coretemp_cpu_offline(unsigned int cpu) struct platform_device *pdev = coretemp_get_pdev(cpu); struct platform_data *pd; struct temp_data *tdata; - int indx, target; + int i, indx = -1, target; /* * Don't execute this on suspend as the device remove locks @@ -660,12 +679,19 @@ static int coretemp_cpu_offline(unsigned int cpu) if (!pdev) return 0; - /* The core id is too big, just return */ - indx = TO_ATTR_NO(cpu); - if (indx > MAX_CORE_DATA - 1) + pd = platform_get_drvdata(pdev); + + for (i = 0; i < NUM_REAL_CORES; i++) { + if (pd->cpu_map[i] == topology_core_id(cpu)) { + indx = i + BASE_SYSFS_ATTR_NO; + break; + } + } + + /* Too many cores and this core is not populated, just return */ + if (indx < 0) return 0; - pd = platform_get_drvdata(pdev); tdata = pd->core_data[indx]; cpumask_clear_cpu(cpu, &pd->cpumask); diff --git a/drivers/hwmon/gsc-hwmon.c b/drivers/hwmon/gsc-hwmon.c index 1fe37418ff46c9f2a130c85bbc77aaac41956fdc..f29ce49294dafb92351d4ceb7924ef8c4df28066 100644 --- a/drivers/hwmon/gsc-hwmon.c +++ b/drivers/hwmon/gsc-hwmon.c @@ -267,6 +267,7 @@ gsc_hwmon_get_devtree_pdata(struct device *dev) pdata->nchannels = nchannels; /* fan controller base address */ + of_node_get(dev->parent->of_node); fan = of_find_compatible_node(dev->parent->of_node, NULL, "gw,gsc-fan"); if (fan && of_property_read_u32(fan, "reg", &pdata->fan_base)) { dev_err(dev, "fan node without base\n"); diff --git a/drivers/hwspinlock/qcom_hwspinlock.c b/drivers/hwspinlock/qcom_hwspinlock.c index 3647109666658c60a459e766e42bfbaf9db82881..e499146648639772eda4192d3981d046662fa6e2 100644 --- a/drivers/hwspinlock/qcom_hwspinlock.c +++ b/drivers/hwspinlock/qcom_hwspinlock.c @@ -105,7 +105,7 @@ static const struct regmap_config tcsr_mutex_config = { .reg_bits = 32, .reg_stride = 4, .val_bits = 32, - .max_register = 0x40000, + .max_register = 0x20000, .fast_io = true, }; diff --git a/drivers/hwtracing/coresight/coresight-cti-core.c b/drivers/hwtracing/coresight/coresight-cti-core.c index 8988b2ed2ea6f5d3f5fed1606d824d6bf6f1781f..dcd607a0c41a18a27bc5115cdd8b0a6f2e23195a 100644 --- a/drivers/hwtracing/coresight/coresight-cti-core.c +++ b/drivers/hwtracing/coresight/coresight-cti-core.c @@ -90,11 +90,9 @@ void cti_write_all_hw_regs(struct cti_drvdata *drvdata) static int cti_enable_hw(struct cti_drvdata *drvdata) { struct cti_config *config = &drvdata->config; - struct device *dev = &drvdata->csdev->dev; unsigned long flags; int rc = 0; - pm_runtime_get_sync(dev->parent); spin_lock_irqsave(&drvdata->spinlock, flags); /* no need to do anything if enabled or unpowered*/ @@ -119,7 +117,6 @@ cti_state_unchanged: /* cannot enable due to error */ cti_err_not_enabled: spin_unlock_irqrestore(&drvdata->spinlock, flags); - pm_runtime_put(dev->parent); return rc; } @@ -153,7 +150,6 @@ cti_hp_not_enabled: static int cti_disable_hw(struct cti_drvdata *drvdata) { struct cti_config *config = &drvdata->config; - struct device *dev = &drvdata->csdev->dev; struct coresight_device *csdev = drvdata->csdev; spin_lock(&drvdata->spinlock); @@ -175,7 +171,6 @@ static int cti_disable_hw(struct cti_drvdata *drvdata) coresight_disclaim_device_unlocked(csdev); CS_LOCK(drvdata->base); spin_unlock(&drvdata->spinlock); - pm_runtime_put(dev->parent); return 0; /* not disabled this call */ diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c index 5618c1ff34dc3a88c6e65fbdf179c435b7d9512f..45682d30d70567d3cb51e94d7ea5391f838df588 100644 --- a/drivers/i2c/busses/i2c-i801.c +++ b/drivers/i2c/busses/i2c-i801.c @@ -1275,6 +1275,7 @@ static const struct { */ { "Latitude 5480", 0x29 }, { "Vostro V131", 0x1d }, + { "Vostro 5568", 0x29 }, }; static void register_dell_lis3lv02d_i2c_device(struct i801_priv *priv) diff --git a/drivers/i2c/busses/i2c-mlxbf.c b/drivers/i2c/busses/i2c-mlxbf.c index bea82a787b4f305a30058195972aa3c52d6f1f03..90c488a606934da8109c0e3ae6a04c5ddb10ea97 100644 --- a/drivers/i2c/busses/i2c-mlxbf.c +++ b/drivers/i2c/busses/i2c-mlxbf.c @@ -312,6 +312,7 @@ static u64 mlxbf_i2c_corepll_frequency; * exact. */ #define MLXBF_I2C_SMBUS_TIMEOUT (300 * 1000) /* 300ms */ +#define MLXBF_I2C_SMBUS_LOCK_POLL_TIMEOUT (300 * 1000) /* 300ms */ /* Encapsulates timing parameters. */ struct mlxbf_i2c_timings { @@ -520,6 +521,25 @@ static bool mlxbf_smbus_master_wait_for_idle(struct mlxbf_i2c_priv *priv) return false; } +/* + * wait for the lock to be released before acquiring it. + */ +static bool mlxbf_i2c_smbus_master_lock(struct mlxbf_i2c_priv *priv) +{ + if (mlxbf_smbus_poll(priv->smbus->io, MLXBF_I2C_SMBUS_MASTER_GW, + MLXBF_I2C_MASTER_LOCK_BIT, true, + MLXBF_I2C_SMBUS_LOCK_POLL_TIMEOUT)) + return true; + + return false; +} + +static void mlxbf_i2c_smbus_master_unlock(struct mlxbf_i2c_priv *priv) +{ + /* Clear the gw to clear the lock */ + writel(0, priv->smbus->io + MLXBF_I2C_SMBUS_MASTER_GW); +} + static bool mlxbf_i2c_smbus_transaction_success(u32 master_status, u32 cause_status) { @@ -711,10 +731,19 @@ mlxbf_i2c_smbus_start_transaction(struct mlxbf_i2c_priv *priv, slave = request->slave & GENMASK(6, 0); addr = slave << 1; - /* First of all, check whether the HW is idle. */ - if (WARN_ON(!mlxbf_smbus_master_wait_for_idle(priv))) + /* + * Try to acquire the smbus gw lock before any reads of the GW register since + * a read sets the lock. + */ + if (WARN_ON(!mlxbf_i2c_smbus_master_lock(priv))) return -EBUSY; + /* Check whether the HW is idle */ + if (WARN_ON(!mlxbf_smbus_master_wait_for_idle(priv))) { + ret = -EBUSY; + goto out_unlock; + } + /* Set first byte. */ data_desc[data_idx++] = addr; @@ -738,8 +767,10 @@ mlxbf_i2c_smbus_start_transaction(struct mlxbf_i2c_priv *priv, write_en = 1; write_len += operation->length; if (data_idx + operation->length > - MLXBF_I2C_MASTER_DATA_DESC_SIZE) - return -ENOBUFS; + MLXBF_I2C_MASTER_DATA_DESC_SIZE) { + ret = -ENOBUFS; + goto out_unlock; + } memcpy(data_desc + data_idx, operation->buffer, operation->length); data_idx += operation->length; @@ -771,7 +802,7 @@ mlxbf_i2c_smbus_start_transaction(struct mlxbf_i2c_priv *priv, ret = mlxbf_i2c_smbus_enable(priv, slave, write_len, block_en, pec_en, 0); if (ret) - return ret; + goto out_unlock; } if (read_en) { @@ -798,6 +829,9 @@ mlxbf_i2c_smbus_start_transaction(struct mlxbf_i2c_priv *priv, priv->smbus->io + MLXBF_I2C_SMBUS_MASTER_FSM); } +out_unlock: + mlxbf_i2c_smbus_master_unlock(priv); + return ret; } diff --git a/drivers/i2c/busses/i2c-piix4.c b/drivers/i2c/busses/i2c-piix4.c index 8c1b31ed0c429a73240e4f5509dcf18d26efc467..aa1d3657ab4e6937252e218acb3cfe84f3393e3a 100644 --- a/drivers/i2c/busses/i2c-piix4.c +++ b/drivers/i2c/busses/i2c-piix4.c @@ -961,6 +961,7 @@ static int piix4_probe(struct pci_dev *dev, const struct pci_device_id *id) "", &piix4_main_adapters[0]); if (retval < 0) return retval; + piix4_adapter_count = 1; } /* Check for auxiliary SMBus on some AMD chipsets */ diff --git a/drivers/i2c/busses/i2c-qcom-cci.c b/drivers/i2c/busses/i2c-qcom-cci.c index 09e599069a81d2133127c1ebba763bd84b174a4c..06c87c79bae76e3cb69d082d8537467d6782b7f6 100644 --- a/drivers/i2c/busses/i2c-qcom-cci.c +++ b/drivers/i2c/busses/i2c-qcom-cci.c @@ -638,6 +638,11 @@ static int cci_probe(struct platform_device *pdev) if (ret < 0) goto error; + pm_runtime_set_autosuspend_delay(dev, MSEC_PER_SEC); + pm_runtime_use_autosuspend(dev); + pm_runtime_set_active(dev); + pm_runtime_enable(dev); + for (i = 0; i < cci->data->num_masters; i++) { if (!cci->master[i].cci) continue; @@ -649,14 +654,12 @@ static int cci_probe(struct platform_device *pdev) } } - pm_runtime_set_autosuspend_delay(dev, MSEC_PER_SEC); - pm_runtime_use_autosuspend(dev); - pm_runtime_set_active(dev); - pm_runtime_enable(dev); - return 0; error_i2c: + pm_runtime_disable(dev); + pm_runtime_dont_use_autosuspend(dev); + for (--i ; i >= 0; i--) { if (cci->master[i].cci) { i2c_del_adapter(&cci->master[i].adap); diff --git a/drivers/i2c/busses/i2c-tegra.c b/drivers/i2c/busses/i2c-tegra.c index 8b113ae32dc713f26d28726a934a30c9f3b55863..42f1db60ad6f80aa042ec61b5a302dfd93ade959 100644 --- a/drivers/i2c/busses/i2c-tegra.c +++ b/drivers/i2c/busses/i2c-tegra.c @@ -283,6 +283,7 @@ struct tegra_i2c_dev { struct dma_chan *tx_dma_chan; struct dma_chan *rx_dma_chan; unsigned int dma_buf_size; + struct device *dma_dev; dma_addr_t dma_phys; void *dma_buf; @@ -419,7 +420,7 @@ static int tegra_i2c_dma_submit(struct tegra_i2c_dev *i2c_dev, size_t len) static void tegra_i2c_release_dma(struct tegra_i2c_dev *i2c_dev) { if (i2c_dev->dma_buf) { - dma_free_coherent(i2c_dev->dev, i2c_dev->dma_buf_size, + dma_free_coherent(i2c_dev->dma_dev, i2c_dev->dma_buf_size, i2c_dev->dma_buf, i2c_dev->dma_phys); i2c_dev->dma_buf = NULL; } @@ -466,10 +467,13 @@ static int tegra_i2c_init_dma(struct tegra_i2c_dev *i2c_dev) i2c_dev->tx_dma_chan = chan; + WARN_ON(i2c_dev->tx_dma_chan->device != i2c_dev->rx_dma_chan->device); + i2c_dev->dma_dev = chan->device->dev; + i2c_dev->dma_buf_size = i2c_dev->hw->quirks->max_write_len + I2C_PACKET_HEADER_SIZE; - dma_buf = dma_alloc_coherent(i2c_dev->dev, i2c_dev->dma_buf_size, + dma_buf = dma_alloc_coherent(i2c_dev->dma_dev, i2c_dev->dma_buf_size, &dma_phys, GFP_KERNEL | __GFP_NOWARN); if (!dma_buf) { dev_err(i2c_dev->dev, "failed to allocate DMA buffer\n"); @@ -1255,7 +1259,7 @@ static int tegra_i2c_xfer_msg(struct tegra_i2c_dev *i2c_dev, if (i2c_dev->dma_mode) { if (i2c_dev->msg_read) { - dma_sync_single_for_device(i2c_dev->dev, + dma_sync_single_for_device(i2c_dev->dma_dev, i2c_dev->dma_phys, xfer_size, DMA_FROM_DEVICE); @@ -1263,7 +1267,7 @@ static int tegra_i2c_xfer_msg(struct tegra_i2c_dev *i2c_dev, if (err) return err; } else { - dma_sync_single_for_cpu(i2c_dev->dev, + dma_sync_single_for_cpu(i2c_dev->dma_dev, i2c_dev->dma_phys, xfer_size, DMA_TO_DEVICE); } @@ -1276,7 +1280,7 @@ static int tegra_i2c_xfer_msg(struct tegra_i2c_dev *i2c_dev, memcpy(i2c_dev->dma_buf + I2C_PACKET_HEADER_SIZE, msg->buf, msg->len); - dma_sync_single_for_device(i2c_dev->dev, + dma_sync_single_for_device(i2c_dev->dma_dev, i2c_dev->dma_phys, xfer_size, DMA_TO_DEVICE); @@ -1327,7 +1331,7 @@ static int tegra_i2c_xfer_msg(struct tegra_i2c_dev *i2c_dev, } if (i2c_dev->msg_read && i2c_dev->msg_err == I2C_ERR_NONE) { - dma_sync_single_for_cpu(i2c_dev->dev, + dma_sync_single_for_cpu(i2c_dev->dma_dev, i2c_dev->dma_phys, xfer_size, DMA_FROM_DEVICE); diff --git a/drivers/i2c/busses/i2c-xiic.c b/drivers/i2c/busses/i2c-xiic.c index 8dabb6ffb1a4f088adc2b507c2ea89ad411cdbbe..3b564e68130b5380ce0a89a4d025fca5bcdd5101 100644 --- a/drivers/i2c/busses/i2c-xiic.c +++ b/drivers/i2c/busses/i2c-xiic.c @@ -935,6 +935,7 @@ static struct platform_driver xiic_i2c_driver = { module_platform_driver(xiic_i2c_driver); +MODULE_ALIAS("platform:" DRIVER_NAME); MODULE_AUTHOR("info@mocean-labs.com"); MODULE_DESCRIPTION("Xilinx I2C bus driver"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/iio/adc/ad7923.c b/drivers/iio/adc/ad7923.c index 8c1e866f72e85971f79fad6771106801ce0bef91..96eeda433ad66a5b40ddb45b2b70e87cca484523 100644 --- a/drivers/iio/adc/ad7923.c +++ b/drivers/iio/adc/ad7923.c @@ -93,6 +93,7 @@ enum ad7923_id { .sign = 'u', \ .realbits = (bits), \ .storagebits = 16, \ + .shift = 12 - (bits), \ .endianness = IIO_BE, \ }, \ } @@ -274,7 +275,8 @@ static int ad7923_read_raw(struct iio_dev *indio_dev, return ret; if (chan->address == EXTRACT(ret, 12, 4)) - *val = EXTRACT(ret, 0, 12); + *val = EXTRACT(ret, chan->scan_type.shift, + chan->scan_type.realbits); else return -EIO; diff --git a/drivers/iio/adc/at91-sama5d2_adc.c b/drivers/iio/adc/at91-sama5d2_adc.c index 4ede7e766765e2f8a1cfa8af3efbcb67d0ca7646..250b78ee162519d7a13c53046e1400c451e4e31a 100644 --- a/drivers/iio/adc/at91-sama5d2_adc.c +++ b/drivers/iio/adc/at91-sama5d2_adc.c @@ -74,7 +74,7 @@ #define AT91_SAMA5D2_MR_ANACH BIT(23) /* Tracking Time */ #define AT91_SAMA5D2_MR_TRACKTIM(v) ((v) << 24) -#define AT91_SAMA5D2_MR_TRACKTIM_MAX 0xff +#define AT91_SAMA5D2_MR_TRACKTIM_MAX 0xf /* Transfer Time */ #define AT91_SAMA5D2_MR_TRANSFER(v) ((v) << 28) #define AT91_SAMA5D2_MR_TRANSFER_MAX 0x3 @@ -1353,10 +1353,12 @@ static int at91_adc_read_info_raw(struct iio_dev *indio_dev, ret = at91_adc_read_position(st, chan->channel, &tmp_val); *val = tmp_val; + if (ret > 0) + ret = at91_adc_adjust_val_osr(st, val); mutex_unlock(&st->lock); iio_device_release_direct_mode(indio_dev); - return at91_adc_adjust_val_osr(st, val); + return ret; } if (chan->type == IIO_PRESSURE) { ret = iio_device_claim_direct_mode(indio_dev); @@ -1367,10 +1369,12 @@ static int at91_adc_read_info_raw(struct iio_dev *indio_dev, ret = at91_adc_read_pressure(st, chan->channel, &tmp_val); *val = tmp_val; + if (ret > 0) + ret = at91_adc_adjust_val_osr(st, val); mutex_unlock(&st->lock); iio_device_release_direct_mode(indio_dev); - return at91_adc_adjust_val_osr(st, val); + return ret; } /* in this case we have a voltage channel */ @@ -1461,16 +1465,20 @@ static int at91_adc_write_raw(struct iio_dev *indio_dev, /* if no change, optimize out */ if (val == st->oversampling_ratio) return 0; + mutex_lock(&st->lock); st->oversampling_ratio = val; /* update ratio */ at91_adc_config_emr(st); + mutex_unlock(&st->lock); return 0; case IIO_CHAN_INFO_SAMP_FREQ: if (val < st->soc_info.min_sample_rate || val > st->soc_info.max_sample_rate) return -EINVAL; + mutex_lock(&st->lock); at91_adc_setup_samp_freq(indio_dev, val); + mutex_unlock(&st->lock); return 0; default: return -EINVAL; @@ -1899,6 +1907,9 @@ static __maybe_unused int at91_adc_suspend(struct device *dev) struct iio_dev *indio_dev = dev_get_drvdata(dev); struct at91_adc_state *st = iio_priv(indio_dev); + if (iio_buffer_enabled(indio_dev)) + at91_adc_buffer_postdisable(indio_dev); + /* * Do a sofware reset of the ADC before we go to suspend. * this will ensure that all pins are free from being muxed by the ADC @@ -1942,14 +1953,11 @@ static __maybe_unused int at91_adc_resume(struct device *dev) if (!iio_buffer_enabled(indio_dev)) return 0; - /* check if we are enabling triggered buffer or the touchscreen */ - if (at91_adc_current_chan_is_touch(indio_dev)) - return at91_adc_configure_touch(st, true); - else - return at91_adc_configure_trigger(st->trig, true); + ret = at91_adc_buffer_prepare(indio_dev); + if (ret) + goto vref_disable_resume; - /* not needed but more explicit */ - return 0; + return at91_adc_configure_trigger(st->trig, true); vref_disable_resume: regulator_disable(st->vref); diff --git a/drivers/iio/adc/at91_adc.c b/drivers/iio/adc/at91_adc.c index 0a793e7cd53ee114b93eeeab21b74ebbf6dc14d1..38d4a910bc525676ca698d9bf167b4a74d6d0a18 100644 --- a/drivers/iio/adc/at91_adc.c +++ b/drivers/iio/adc/at91_adc.c @@ -616,8 +616,10 @@ static struct iio_trigger *at91_adc_allocate_trigger(struct iio_dev *idev, trig->ops = &at91_adc_trigger_ops; ret = iio_trigger_register(trig); - if (ret) + if (ret) { + iio_trigger_free(trig); return NULL; + } return trig; } diff --git a/drivers/iio/adc/ltc2497.c b/drivers/iio/adc/ltc2497.c index 1adddf5a88a94b0a2ae4284e1cf4033ce11fdc2c..61f373fab9a114b46347c9757fa0a540f6c0866e 100644 --- a/drivers/iio/adc/ltc2497.c +++ b/drivers/iio/adc/ltc2497.c @@ -41,6 +41,19 @@ static int ltc2497_result_and_measure(struct ltc2497core_driverdata *ddata, } *val = (be32_to_cpu(st->buf) >> 14) - (1 << 17); + + /* + * The part started a new conversion at the end of the above i2c + * transfer, so if the address didn't change since the last call + * everything is fine and we can return early. + * If not (which should only happen when some sort of bulk + * conversion is implemented) we have to program the new + * address. Note that this probably fails as the conversion that + * was triggered above is like not complete yet and the two + * operations have to be done in a single transfer. + */ + if (ddata->addr_prev == address) + return 0; } ret = i2c_smbus_write_byte(st->client, diff --git a/drivers/iio/adc/mp2629_adc.c b/drivers/iio/adc/mp2629_adc.c index 331a9a7282170ad2a1735ec76f98a315104b25e4..acd9420c041626d00facda4902ede65c28c4083a 100644 --- a/drivers/iio/adc/mp2629_adc.c +++ b/drivers/iio/adc/mp2629_adc.c @@ -56,7 +56,8 @@ static struct iio_map mp2629_adc_maps[] = { MP2629_MAP(SYSTEM_VOLT, "system-volt"), MP2629_MAP(INPUT_VOLT, "input-volt"), MP2629_MAP(BATT_CURRENT, "batt-current"), - MP2629_MAP(INPUT_CURRENT, "input-current") + MP2629_MAP(INPUT_CURRENT, "input-current"), + { } }; static int mp2629_read_raw(struct iio_dev *indio_dev, @@ -73,7 +74,7 @@ static int mp2629_read_raw(struct iio_dev *indio_dev, if (ret) return ret; - if (chan->address == MP2629_INPUT_VOLT) + if (chan->channel == MP2629_INPUT_VOLT) rval &= GENMASK(6, 0); *val = rval; return IIO_VAL_INT; diff --git a/drivers/iio/dac/ad5593r.c b/drivers/iio/dac/ad5593r.c index 5b4df36fdc2ad9a5c559a06d279cdbb60202d230..4cc855c781218e18f19e80b6c406db2ea71feb9d 100644 --- a/drivers/iio/dac/ad5593r.c +++ b/drivers/iio/dac/ad5593r.c @@ -13,6 +13,8 @@ #include #include +#include + #define AD5593R_MODE_CONF (0 << 4) #define AD5593R_MODE_DAC_WRITE (1 << 4) #define AD5593R_MODE_ADC_READBACK (4 << 4) @@ -20,6 +22,24 @@ #define AD5593R_MODE_GPIO_READBACK (6 << 4) #define AD5593R_MODE_REG_READBACK (7 << 4) +static int ad5593r_read_word(struct i2c_client *i2c, u8 reg, u16 *value) +{ + int ret; + u8 buf[2]; + + ret = i2c_smbus_write_byte(i2c, reg); + if (ret < 0) + return ret; + + ret = i2c_master_recv(i2c, buf, sizeof(buf)); + if (ret < 0) + return ret; + + *value = get_unaligned_be16(buf); + + return 0; +} + static int ad5593r_write_dac(struct ad5592r_state *st, unsigned chan, u16 value) { struct i2c_client *i2c = to_i2c_client(st->dev); @@ -38,13 +58,7 @@ static int ad5593r_read_adc(struct ad5592r_state *st, unsigned chan, u16 *value) if (val < 0) return (int) val; - val = i2c_smbus_read_word_swapped(i2c, AD5593R_MODE_ADC_READBACK); - if (val < 0) - return (int) val; - - *value = (u16) val; - - return 0; + return ad5593r_read_word(i2c, AD5593R_MODE_ADC_READBACK, value); } static int ad5593r_reg_write(struct ad5592r_state *st, u8 reg, u16 value) @@ -58,25 +72,19 @@ static int ad5593r_reg_write(struct ad5592r_state *st, u8 reg, u16 value) static int ad5593r_reg_read(struct ad5592r_state *st, u8 reg, u16 *value) { struct i2c_client *i2c = to_i2c_client(st->dev); - s32 val; - - val = i2c_smbus_read_word_swapped(i2c, AD5593R_MODE_REG_READBACK | reg); - if (val < 0) - return (int) val; - *value = (u16) val; - - return 0; + return ad5593r_read_word(i2c, AD5593R_MODE_REG_READBACK | reg, value); } static int ad5593r_gpio_read(struct ad5592r_state *st, u8 *value) { struct i2c_client *i2c = to_i2c_client(st->dev); - s32 val; + u16 val; + int ret; - val = i2c_smbus_read_word_swapped(i2c, AD5593R_MODE_GPIO_READBACK); - if (val < 0) - return (int) val; + ret = ad5593r_read_word(i2c, AD5593R_MODE_GPIO_READBACK, &val); + if (ret) + return ret; *value = (u8) val; diff --git a/drivers/iio/industrialio-sw-trigger.c b/drivers/iio/industrialio-sw-trigger.c index 9ae793a70b8bffc08e9131b947cc44569dc055be..a7714d32a6418e5f0d802304a5ace71de0f9d41f 100644 --- a/drivers/iio/industrialio-sw-trigger.c +++ b/drivers/iio/industrialio-sw-trigger.c @@ -58,8 +58,12 @@ int iio_register_sw_trigger_type(struct iio_sw_trigger_type *t) t->group = configfs_register_default_group(iio_triggers_group, t->name, &iio_trigger_type_group_type); - if (IS_ERR(t->group)) + if (IS_ERR(t->group)) { + mutex_lock(&iio_trigger_types_lock); + list_del(&t->list); + mutex_unlock(&iio_trigger_types_lock); ret = PTR_ERR(t->group); + } return ret; } diff --git a/drivers/iio/inkern.c b/drivers/iio/inkern.c index 8c3faa7972842db38a55531c18cf626bfb4119fa..c32b2577dd9916bcbe21a8df17920b9eea4621a5 100644 --- a/drivers/iio/inkern.c +++ b/drivers/iio/inkern.c @@ -136,9 +136,10 @@ static int __of_iio_channel_get(struct iio_channel *channel, idev = bus_find_device(&iio_bus_type, NULL, iiospec.np, iio_dev_node_match); - of_node_put(iiospec.np); - if (idev == NULL) + if (idev == NULL) { + of_node_put(iiospec.np); return -EPROBE_DEFER; + } indio_dev = dev_to_iio_dev(idev); channel->indio_dev = indio_dev; @@ -146,6 +147,7 @@ static int __of_iio_channel_get(struct iio_channel *channel, index = indio_dev->info->of_xlate(indio_dev, &iiospec); else index = __of_iio_simple_xlate(indio_dev, &iiospec); + of_node_put(iiospec.np); if (index < 0) goto err_put; channel->channel = &indio_dev->channels[index]; diff --git a/drivers/iio/light/apds9960.c b/drivers/iio/light/apds9960.c index 9afb3fcc74e627edf4a8184a229f163bd05e90dd..4a7ccf268ebf4365eb73e080878cbf28d47a1d1d 100644 --- a/drivers/iio/light/apds9960.c +++ b/drivers/iio/light/apds9960.c @@ -53,9 +53,6 @@ #define APDS9960_REG_CONTROL_PGAIN_MASK_SHIFT 2 #define APDS9960_REG_CONFIG_2 0x90 -#define APDS9960_REG_CONFIG_2_GGAIN_MASK 0x60 -#define APDS9960_REG_CONFIG_2_GGAIN_MASK_SHIFT 5 - #define APDS9960_REG_ID 0x92 #define APDS9960_REG_STATUS 0x93 @@ -76,6 +73,9 @@ #define APDS9960_REG_GCONF_1_GFIFO_THRES_MASK_SHIFT 6 #define APDS9960_REG_GCONF_2 0xa3 +#define APDS9960_REG_GCONF_2_GGAIN_MASK 0x60 +#define APDS9960_REG_GCONF_2_GGAIN_MASK_SHIFT 5 + #define APDS9960_REG_GOFFSET_U 0xa4 #define APDS9960_REG_GOFFSET_D 0xa5 #define APDS9960_REG_GPULSE 0xa6 @@ -395,9 +395,9 @@ static int apds9960_set_pxs_gain(struct apds9960_data *data, int val) } ret = regmap_update_bits(data->regmap, - APDS9960_REG_CONFIG_2, - APDS9960_REG_CONFIG_2_GGAIN_MASK, - idx << APDS9960_REG_CONFIG_2_GGAIN_MASK_SHIFT); + APDS9960_REG_GCONF_2, + APDS9960_REG_GCONF_2_GGAIN_MASK, + idx << APDS9960_REG_GCONF_2_GGAIN_MASK_SHIFT); if (!ret) data->pxs_gain = idx; mutex_unlock(&data->lock); diff --git a/drivers/iio/light/tsl2583.c b/drivers/iio/light/tsl2583.c index 40b7dd266b3149e84d10a6fd2213dc116181f969..e39d512145a67871091616ad20d2ef8469bb529d 100644 --- a/drivers/iio/light/tsl2583.c +++ b/drivers/iio/light/tsl2583.c @@ -856,7 +856,7 @@ static int tsl2583_probe(struct i2c_client *clientp, TSL2583_POWER_OFF_DELAY_MS); pm_runtime_use_autosuspend(&clientp->dev); - ret = devm_iio_device_register(indio_dev->dev.parent, indio_dev); + ret = iio_device_register(indio_dev); if (ret) { dev_err(&clientp->dev, "%s: iio registration failed\n", __func__); diff --git a/drivers/iio/pressure/dps310.c b/drivers/iio/pressure/dps310.c index 0730380ceb692e92d8d109972ff2ccfc097b4adf..cf8b92fae1b3db663d51935f55aa10f962c2229f 100644 --- a/drivers/iio/pressure/dps310.c +++ b/drivers/iio/pressure/dps310.c @@ -89,6 +89,7 @@ struct dps310_data { s32 c00, c10, c20, c30, c01, c11, c21; s32 pressure_raw; s32 temp_raw; + bool timeout_recovery_failed; }; static const struct iio_chan_spec dps310_channels[] = { @@ -159,6 +160,102 @@ static int dps310_get_coefs(struct dps310_data *data) return 0; } +/* + * Some versions of the chip will read temperatures in the ~60C range when + * it's actually ~20C. This is the manufacturer recommended workaround + * to correct the issue. The registers used below are undocumented. + */ +static int dps310_temp_workaround(struct dps310_data *data) +{ + int rc; + int reg; + + rc = regmap_read(data->regmap, 0x32, ®); + if (rc) + return rc; + + /* + * If bit 1 is set then the device is okay, and the workaround does not + * need to be applied + */ + if (reg & BIT(1)) + return 0; + + rc = regmap_write(data->regmap, 0x0e, 0xA5); + if (rc) + return rc; + + rc = regmap_write(data->regmap, 0x0f, 0x96); + if (rc) + return rc; + + rc = regmap_write(data->regmap, 0x62, 0x02); + if (rc) + return rc; + + rc = regmap_write(data->regmap, 0x0e, 0x00); + if (rc) + return rc; + + return regmap_write(data->regmap, 0x0f, 0x00); +} + +static int dps310_startup(struct dps310_data *data) +{ + int rc; + int ready; + + /* + * Set up pressure sensor in single sample, one measurement per second + * mode + */ + rc = regmap_write(data->regmap, DPS310_PRS_CFG, 0); + if (rc) + return rc; + + /* + * Set up external (MEMS) temperature sensor in single sample, one + * measurement per second mode + */ + rc = regmap_write(data->regmap, DPS310_TMP_CFG, DPS310_TMP_EXT); + if (rc) + return rc; + + /* Temp and pressure shifts are disabled when PRC <= 8 */ + rc = regmap_write_bits(data->regmap, DPS310_CFG_REG, + DPS310_PRS_SHIFT_EN | DPS310_TMP_SHIFT_EN, 0); + if (rc) + return rc; + + /* MEAS_CFG doesn't update correctly unless first written with 0 */ + rc = regmap_write_bits(data->regmap, DPS310_MEAS_CFG, + DPS310_MEAS_CTRL_BITS, 0); + if (rc) + return rc; + + /* Turn on temperature and pressure measurement in the background */ + rc = regmap_write_bits(data->regmap, DPS310_MEAS_CFG, + DPS310_MEAS_CTRL_BITS, DPS310_PRS_EN | + DPS310_TEMP_EN | DPS310_BACKGROUND); + if (rc) + return rc; + + /* + * Calibration coefficients required for reporting temperature. + * They are available 40ms after the device has started + */ + rc = regmap_read_poll_timeout(data->regmap, DPS310_MEAS_CFG, ready, + ready & DPS310_COEF_RDY, 10000, 40000); + if (rc) + return rc; + + rc = dps310_get_coefs(data); + if (rc) + return rc; + + return dps310_temp_workaround(data); +} + static int dps310_get_pres_precision(struct dps310_data *data) { int rc; @@ -297,11 +394,69 @@ static int dps310_get_temp_k(struct dps310_data *data) return scale_factors[ilog2(rc)]; } +static int dps310_reset_wait(struct dps310_data *data) +{ + int rc; + + rc = regmap_write(data->regmap, DPS310_RESET, DPS310_RESET_MAGIC); + if (rc) + return rc; + + /* Wait for device chip access: 2.5ms in specification */ + usleep_range(2500, 12000); + return 0; +} + +static int dps310_reset_reinit(struct dps310_data *data) +{ + int rc; + + rc = dps310_reset_wait(data); + if (rc) + return rc; + + return dps310_startup(data); +} + +static int dps310_ready_status(struct dps310_data *data, int ready_bit, int timeout) +{ + int sleep = DPS310_POLL_SLEEP_US(timeout); + int ready; + + return regmap_read_poll_timeout(data->regmap, DPS310_MEAS_CFG, ready, ready & ready_bit, + sleep, timeout); +} + +static int dps310_ready(struct dps310_data *data, int ready_bit, int timeout) +{ + int rc; + + rc = dps310_ready_status(data, ready_bit, timeout); + if (rc) { + if (rc == -ETIMEDOUT && !data->timeout_recovery_failed) { + /* Reset and reinitialize the chip. */ + if (dps310_reset_reinit(data)) { + data->timeout_recovery_failed = true; + } else { + /* Try again to get sensor ready status. */ + if (dps310_ready_status(data, ready_bit, timeout)) + data->timeout_recovery_failed = true; + else + return 0; + } + } + + return rc; + } + + data->timeout_recovery_failed = false; + return 0; +} + static int dps310_read_pres_raw(struct dps310_data *data) { int rc; int rate; - int ready; int timeout; s32 raw; u8 val[3]; @@ -313,9 +468,7 @@ static int dps310_read_pres_raw(struct dps310_data *data) timeout = DPS310_POLL_TIMEOUT_US(rate); /* Poll for sensor readiness; base the timeout upon the sample rate. */ - rc = regmap_read_poll_timeout(data->regmap, DPS310_MEAS_CFG, ready, - ready & DPS310_PRS_RDY, - DPS310_POLL_SLEEP_US(timeout), timeout); + rc = dps310_ready(data, DPS310_PRS_RDY, timeout); if (rc) goto done; @@ -352,7 +505,6 @@ static int dps310_read_temp_raw(struct dps310_data *data) { int rc; int rate; - int ready; int timeout; if (mutex_lock_interruptible(&data->lock)) @@ -362,10 +514,8 @@ static int dps310_read_temp_raw(struct dps310_data *data) timeout = DPS310_POLL_TIMEOUT_US(rate); /* Poll for sensor readiness; base the timeout upon the sample rate. */ - rc = regmap_read_poll_timeout(data->regmap, DPS310_MEAS_CFG, ready, - ready & DPS310_TMP_RDY, - DPS310_POLL_SLEEP_US(timeout), timeout); - if (rc < 0) + rc = dps310_ready(data, DPS310_TMP_RDY, timeout); + if (rc) goto done; rc = dps310_read_temp_ready(data); @@ -660,7 +810,7 @@ static void dps310_reset(void *action_data) { struct dps310_data *data = action_data; - regmap_write(data->regmap, DPS310_RESET, DPS310_RESET_MAGIC); + dps310_reset_wait(data); } static const struct regmap_config dps310_regmap_config = { @@ -677,52 +827,12 @@ static const struct iio_info dps310_info = { .write_raw = dps310_write_raw, }; -/* - * Some verions of chip will read temperatures in the ~60C range when - * its actually ~20C. This is the manufacturer recommended workaround - * to correct the issue. The registers used below are undocumented. - */ -static int dps310_temp_workaround(struct dps310_data *data) -{ - int rc; - int reg; - - rc = regmap_read(data->regmap, 0x32, ®); - if (rc < 0) - return rc; - - /* - * If bit 1 is set then the device is okay, and the workaround does not - * need to be applied - */ - if (reg & BIT(1)) - return 0; - - rc = regmap_write(data->regmap, 0x0e, 0xA5); - if (rc < 0) - return rc; - - rc = regmap_write(data->regmap, 0x0f, 0x96); - if (rc < 0) - return rc; - - rc = regmap_write(data->regmap, 0x62, 0x02); - if (rc < 0) - return rc; - - rc = regmap_write(data->regmap, 0x0e, 0x00); - if (rc < 0) - return rc; - - return regmap_write(data->regmap, 0x0f, 0x00); -} - static int dps310_probe(struct i2c_client *client, const struct i2c_device_id *id) { struct dps310_data *data; struct iio_dev *iio; - int rc, ready; + int rc; iio = devm_iio_device_alloc(&client->dev, sizeof(*data)); if (!iio) @@ -747,54 +857,8 @@ static int dps310_probe(struct i2c_client *client, if (rc) return rc; - /* - * Set up pressure sensor in single sample, one measurement per second - * mode - */ - rc = regmap_write(data->regmap, DPS310_PRS_CFG, 0); - - /* - * Set up external (MEMS) temperature sensor in single sample, one - * measurement per second mode - */ - rc = regmap_write(data->regmap, DPS310_TMP_CFG, DPS310_TMP_EXT); - if (rc < 0) - return rc; - - /* Temp and pressure shifts are disabled when PRC <= 8 */ - rc = regmap_write_bits(data->regmap, DPS310_CFG_REG, - DPS310_PRS_SHIFT_EN | DPS310_TMP_SHIFT_EN, 0); - if (rc < 0) - return rc; - - /* MEAS_CFG doesn't update correctly unless first written with 0 */ - rc = regmap_write_bits(data->regmap, DPS310_MEAS_CFG, - DPS310_MEAS_CTRL_BITS, 0); - if (rc < 0) - return rc; - - /* Turn on temperature and pressure measurement in the background */ - rc = regmap_write_bits(data->regmap, DPS310_MEAS_CFG, - DPS310_MEAS_CTRL_BITS, DPS310_PRS_EN | - DPS310_TEMP_EN | DPS310_BACKGROUND); - if (rc < 0) - return rc; - - /* - * Calibration coefficients required for reporting temperature. - * They are available 40ms after the device has started - */ - rc = regmap_read_poll_timeout(data->regmap, DPS310_MEAS_CFG, ready, - ready & DPS310_COEF_RDY, 10000, 40000); - if (rc < 0) - return rc; - - rc = dps310_get_coefs(data); - if (rc < 0) - return rc; - - rc = dps310_temp_workaround(data); - if (rc < 0) + rc = dps310_startup(data); + if (rc) return rc; rc = devm_iio_device_register(&client->dev, iio); diff --git a/drivers/iio/pressure/ms5611.h b/drivers/iio/pressure/ms5611.h index bc06271fa38bc95f8b1f14e2fdb27041e24c6560..5e2d2d4d87b56437852851282567953ae7543d66 100644 --- a/drivers/iio/pressure/ms5611.h +++ b/drivers/iio/pressure/ms5611.h @@ -25,13 +25,6 @@ enum { MS5607, }; -struct ms5611_chip_info { - u16 prom[MS5611_PROM_WORDS_NB]; - - int (*temp_and_pressure_compensate)(struct ms5611_chip_info *chip_info, - s32 *temp, s32 *pressure); -}; - /* * OverSampling Rate descriptor. * Warning: cmd MUST be kept aligned on a word boundary (see @@ -50,12 +43,15 @@ struct ms5611_state { const struct ms5611_osr *pressure_osr; const struct ms5611_osr *temp_osr; - int (*reset)(struct device *dev); - int (*read_prom_word)(struct device *dev, int index, u16 *word); - int (*read_adc_temp_and_pressure)(struct device *dev, + u16 prom[MS5611_PROM_WORDS_NB]; + + int (*reset)(struct ms5611_state *st); + int (*read_prom_word)(struct ms5611_state *st, int index, u16 *word); + int (*read_adc_temp_and_pressure)(struct ms5611_state *st, s32 *temp, s32 *pressure); - struct ms5611_chip_info *chip_info; + int (*compensate_temp_and_pressure)(struct ms5611_state *st, s32 *temp, + s32 *pressure); struct regulator *vdd; }; diff --git a/drivers/iio/pressure/ms5611_core.c b/drivers/iio/pressure/ms5611_core.c index 214b0d25f59804ba499a679482e69e6ab3c91ce4..874a73b3ea9d60b5d0ea2e249e9651f246a32c78 100644 --- a/drivers/iio/pressure/ms5611_core.c +++ b/drivers/iio/pressure/ms5611_core.c @@ -85,8 +85,7 @@ static int ms5611_read_prom(struct iio_dev *indio_dev) struct ms5611_state *st = iio_priv(indio_dev); for (i = 0; i < MS5611_PROM_WORDS_NB; i++) { - ret = st->read_prom_word(&indio_dev->dev, - i, &st->chip_info->prom[i]); + ret = st->read_prom_word(st, i, &st->prom[i]); if (ret < 0) { dev_err(&indio_dev->dev, "failed to read prom at %d\n", i); @@ -94,7 +93,7 @@ static int ms5611_read_prom(struct iio_dev *indio_dev) } } - if (!ms5611_prom_is_valid(st->chip_info->prom, MS5611_PROM_WORDS_NB)) { + if (!ms5611_prom_is_valid(st->prom, MS5611_PROM_WORDS_NB)) { dev_err(&indio_dev->dev, "PROM integrity check failed\n"); return -ENODEV; } @@ -108,28 +107,27 @@ static int ms5611_read_temp_and_pressure(struct iio_dev *indio_dev, int ret; struct ms5611_state *st = iio_priv(indio_dev); - ret = st->read_adc_temp_and_pressure(&indio_dev->dev, temp, pressure); + ret = st->read_adc_temp_and_pressure(st, temp, pressure); if (ret < 0) { dev_err(&indio_dev->dev, "failed to read temperature and pressure\n"); return ret; } - return st->chip_info->temp_and_pressure_compensate(st->chip_info, - temp, pressure); + return st->compensate_temp_and_pressure(st, temp, pressure); } -static int ms5611_temp_and_pressure_compensate(struct ms5611_chip_info *chip_info, +static int ms5611_temp_and_pressure_compensate(struct ms5611_state *st, s32 *temp, s32 *pressure) { s32 t = *temp, p = *pressure; s64 off, sens, dt; - dt = t - (chip_info->prom[5] << 8); - off = ((s64)chip_info->prom[2] << 16) + ((chip_info->prom[4] * dt) >> 7); - sens = ((s64)chip_info->prom[1] << 15) + ((chip_info->prom[3] * dt) >> 8); + dt = t - (st->prom[5] << 8); + off = ((s64)st->prom[2] << 16) + ((st->prom[4] * dt) >> 7); + sens = ((s64)st->prom[1] << 15) + ((st->prom[3] * dt) >> 8); - t = 2000 + ((chip_info->prom[6] * dt) >> 23); + t = 2000 + ((st->prom[6] * dt) >> 23); if (t < 2000) { s64 off2, sens2, t2; @@ -155,17 +153,17 @@ static int ms5611_temp_and_pressure_compensate(struct ms5611_chip_info *chip_inf return 0; } -static int ms5607_temp_and_pressure_compensate(struct ms5611_chip_info *chip_info, +static int ms5607_temp_and_pressure_compensate(struct ms5611_state *st, s32 *temp, s32 *pressure) { s32 t = *temp, p = *pressure; s64 off, sens, dt; - dt = t - (chip_info->prom[5] << 8); - off = ((s64)chip_info->prom[2] << 17) + ((chip_info->prom[4] * dt) >> 6); - sens = ((s64)chip_info->prom[1] << 16) + ((chip_info->prom[3] * dt) >> 7); + dt = t - (st->prom[5] << 8); + off = ((s64)st->prom[2] << 17) + ((st->prom[4] * dt) >> 6); + sens = ((s64)st->prom[1] << 16) + ((st->prom[3] * dt) >> 7); - t = 2000 + ((chip_info->prom[6] * dt) >> 23); + t = 2000 + ((st->prom[6] * dt) >> 23); if (t < 2000) { s64 off2, sens2, t2, tmp; @@ -196,7 +194,7 @@ static int ms5611_reset(struct iio_dev *indio_dev) int ret; struct ms5611_state *st = iio_priv(indio_dev); - ret = st->reset(&indio_dev->dev); + ret = st->reset(st); if (ret < 0) { dev_err(&indio_dev->dev, "failed to reset device\n"); return ret; @@ -343,15 +341,6 @@ static int ms5611_write_raw(struct iio_dev *indio_dev, static const unsigned long ms5611_scan_masks[] = {0x3, 0}; -static struct ms5611_chip_info chip_info_tbl[] = { - [MS5611] = { - .temp_and_pressure_compensate = ms5611_temp_and_pressure_compensate, - }, - [MS5607] = { - .temp_and_pressure_compensate = ms5607_temp_and_pressure_compensate, - } -}; - static const struct iio_chan_spec ms5611_channels[] = { { .type = IIO_PRESSURE, @@ -434,7 +423,20 @@ int ms5611_probe(struct iio_dev *indio_dev, struct device *dev, struct ms5611_state *st = iio_priv(indio_dev); mutex_init(&st->lock); - st->chip_info = &chip_info_tbl[type]; + + switch (type) { + case MS5611: + st->compensate_temp_and_pressure = + ms5611_temp_and_pressure_compensate; + break; + case MS5607: + st->compensate_temp_and_pressure = + ms5607_temp_and_pressure_compensate; + break; + default: + return -EINVAL; + } + st->temp_osr = &ms5611_avail_temp_osr[ARRAY_SIZE(ms5611_avail_temp_osr) - 1]; st->pressure_osr = diff --git a/drivers/iio/pressure/ms5611_i2c.c b/drivers/iio/pressure/ms5611_i2c.c index 7c04f730430c7aa02c7cf02c13f328a735065285..cccc40f7df0b9f4284c87fd95fdb4be7d6b7f1c8 100644 --- a/drivers/iio/pressure/ms5611_i2c.c +++ b/drivers/iio/pressure/ms5611_i2c.c @@ -20,17 +20,15 @@ #include "ms5611.h" -static int ms5611_i2c_reset(struct device *dev) +static int ms5611_i2c_reset(struct ms5611_state *st) { - struct ms5611_state *st = iio_priv(dev_to_iio_dev(dev)); - return i2c_smbus_write_byte(st->client, MS5611_RESET); } -static int ms5611_i2c_read_prom_word(struct device *dev, int index, u16 *word) +static int ms5611_i2c_read_prom_word(struct ms5611_state *st, int index, + u16 *word) { int ret; - struct ms5611_state *st = iio_priv(dev_to_iio_dev(dev)); ret = i2c_smbus_read_word_swapped(st->client, MS5611_READ_PROM_WORD + (index << 1)); @@ -57,11 +55,10 @@ static int ms5611_i2c_read_adc(struct ms5611_state *st, s32 *val) return 0; } -static int ms5611_i2c_read_adc_temp_and_pressure(struct device *dev, +static int ms5611_i2c_read_adc_temp_and_pressure(struct ms5611_state *st, s32 *temp, s32 *pressure) { int ret; - struct ms5611_state *st = iio_priv(dev_to_iio_dev(dev)); const struct ms5611_osr *osr = st->temp_osr; ret = i2c_smbus_write_byte(st->client, osr->cmd); diff --git a/drivers/iio/pressure/ms5611_spi.c b/drivers/iio/pressure/ms5611_spi.c index 45d3a7d5be8e4e637b7acc9c563c1ede7b22e43f..3039fe8aa2a2d6e90b535cf214474273dc14e974 100644 --- a/drivers/iio/pressure/ms5611_spi.c +++ b/drivers/iio/pressure/ms5611_spi.c @@ -15,18 +15,17 @@ #include "ms5611.h" -static int ms5611_spi_reset(struct device *dev) +static int ms5611_spi_reset(struct ms5611_state *st) { u8 cmd = MS5611_RESET; - struct ms5611_state *st = iio_priv(dev_to_iio_dev(dev)); return spi_write_then_read(st->client, &cmd, 1, NULL, 0); } -static int ms5611_spi_read_prom_word(struct device *dev, int index, u16 *word) +static int ms5611_spi_read_prom_word(struct ms5611_state *st, int index, + u16 *word) { int ret; - struct ms5611_state *st = iio_priv(dev_to_iio_dev(dev)); ret = spi_w8r16be(st->client, MS5611_READ_PROM_WORD + (index << 1)); if (ret < 0) @@ -37,11 +36,10 @@ static int ms5611_spi_read_prom_word(struct device *dev, int index, u16 *word) return 0; } -static int ms5611_spi_read_adc(struct device *dev, s32 *val) +static int ms5611_spi_read_adc(struct ms5611_state *st, s32 *val) { int ret; u8 buf[3] = { MS5611_READ_ADC }; - struct ms5611_state *st = iio_priv(dev_to_iio_dev(dev)); ret = spi_write_then_read(st->client, buf, 1, buf, 3); if (ret < 0) @@ -52,11 +50,10 @@ static int ms5611_spi_read_adc(struct device *dev, s32 *val) return 0; } -static int ms5611_spi_read_adc_temp_and_pressure(struct device *dev, +static int ms5611_spi_read_adc_temp_and_pressure(struct ms5611_state *st, s32 *temp, s32 *pressure) { int ret; - struct ms5611_state *st = iio_priv(dev_to_iio_dev(dev)); const struct ms5611_osr *osr = st->temp_osr; /* @@ -68,7 +65,7 @@ static int ms5611_spi_read_adc_temp_and_pressure(struct device *dev, return ret; usleep_range(osr->conv_usec, osr->conv_usec + (osr->conv_usec / 10UL)); - ret = ms5611_spi_read_adc(dev, temp); + ret = ms5611_spi_read_adc(st, temp); if (ret < 0) return ret; @@ -78,7 +75,7 @@ static int ms5611_spi_read_adc_temp_and_pressure(struct device *dev, return ret; usleep_range(osr->conv_usec, osr->conv_usec + (osr->conv_usec / 10UL)); - return ms5611_spi_read_adc(dev, pressure); + return ms5611_spi_read_adc(st, pressure); } static int ms5611_spi_probe(struct spi_device *spi) @@ -94,7 +91,7 @@ static int ms5611_spi_probe(struct spi_device *spi) spi_set_drvdata(spi, indio_dev); spi->mode = SPI_MODE_0; - spi->max_speed_hz = 20000000; + spi->max_speed_hz = min(spi->max_speed_hz, 20000000U); spi->bits_per_word = 8; ret = spi_setup(spi); if (ret < 0) diff --git a/drivers/iio/temperature/ltc2983.c b/drivers/iio/temperature/ltc2983.c index 3b4a0e60e6059481b7e3ea3c4ea79908a48ed6d8..8306daa7790812e53602ca1cf6a75d0a97efabef 100644 --- a/drivers/iio/temperature/ltc2983.c +++ b/drivers/iio/temperature/ltc2983.c @@ -1376,13 +1376,6 @@ static int ltc2983_setup(struct ltc2983_data *st, bool assign_iio) return ret; } - st->iio_chan = devm_kzalloc(&st->spi->dev, - st->iio_channels * sizeof(*st->iio_chan), - GFP_KERNEL); - - if (!st->iio_chan) - return -ENOMEM; - ret = regmap_update_bits(st->regmap, LTC2983_GLOBAL_CONFIG_REG, LTC2983_NOTCH_FREQ_MASK, LTC2983_NOTCH_FREQ(st->filter_notch_freq)); @@ -1494,6 +1487,12 @@ static int ltc2983_probe(struct spi_device *spi) if (ret) return ret; + st->iio_chan = devm_kzalloc(&spi->dev, + st->iio_channels * sizeof(*st->iio_chan), + GFP_KERNEL); + if (!st->iio_chan) + return -ENOMEM; + ret = ltc2983_setup(st, true); if (ret) return ret; diff --git a/drivers/iio/trigger/iio-trig-sysfs.c b/drivers/iio/trigger/iio-trig-sysfs.c index 2277d6336ac065d6625662bd0dad032aa2e35214..9ed5b9405ade0a667d5e7c52f4977be47fb27f8a 100644 --- a/drivers/iio/trigger/iio-trig-sysfs.c +++ b/drivers/iio/trigger/iio-trig-sysfs.c @@ -209,9 +209,13 @@ static int iio_sysfs_trigger_remove(int id) static int __init iio_sysfs_trig_init(void) { + int ret; device_initialize(&iio_sysfs_trig_dev); dev_set_name(&iio_sysfs_trig_dev, "iio_sysfs_trigger"); - return device_add(&iio_sysfs_trig_dev); + ret = device_add(&iio_sysfs_trig_dev); + if (ret) + put_device(&iio_sysfs_trig_dev); + return ret; } module_init(iio_sysfs_trig_init); diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c index 3cc7a23fa69fee4d7b8bbc0c199eab871e2e4bfc..3133b6be6cab9c6b2674be59abf88f8627ad4d1e 100644 --- a/drivers/infiniband/core/cm.c +++ b/drivers/infiniband/core/cm.c @@ -1643,14 +1643,13 @@ static void cm_path_set_rec_type(struct ib_device *ib_device, u8 port_num, static void cm_format_path_lid_from_req(struct cm_req_msg *req_msg, struct sa_path_rec *primary_path, - struct sa_path_rec *alt_path) + struct sa_path_rec *alt_path, + struct ib_wc *wc) { u32 lid; if (primary_path->rec_type != SA_PATH_REC_TYPE_OPA) { - sa_path_set_dlid(primary_path, - IBA_GET(CM_REQ_PRIMARY_LOCAL_PORT_LID, - req_msg)); + sa_path_set_dlid(primary_path, wc->slid); sa_path_set_slid(primary_path, IBA_GET(CM_REQ_PRIMARY_REMOTE_PORT_LID, req_msg)); @@ -1687,7 +1686,8 @@ static void cm_format_path_lid_from_req(struct cm_req_msg *req_msg, static void cm_format_paths_from_req(struct cm_req_msg *req_msg, struct sa_path_rec *primary_path, - struct sa_path_rec *alt_path) + struct sa_path_rec *alt_path, + struct ib_wc *wc) { primary_path->dgid = *IBA_GET_MEM_PTR(CM_REQ_PRIMARY_LOCAL_PORT_GID, req_msg); @@ -1745,7 +1745,7 @@ static void cm_format_paths_from_req(struct cm_req_msg *req_msg, if (sa_path_is_roce(alt_path)) alt_path->roce.route_resolved = false; } - cm_format_path_lid_from_req(req_msg, primary_path, alt_path); + cm_format_path_lid_from_req(req_msg, primary_path, alt_path, wc); } static u16 cm_get_bth_pkey(struct cm_work *work) @@ -2163,7 +2163,7 @@ static int cm_req_handler(struct cm_work *work) if (cm_req_has_alt_path(req_msg)) work->path[1].rec_type = work->path[0].rec_type; cm_format_paths_from_req(req_msg, &work->path[0], - &work->path[1]); + &work->path[1], work->mad_recv_wc->wc); if (cm_id_priv->av.ah_attr.type == RDMA_AH_ATTR_TYPE_ROCE) sa_path_set_dmac(&work->path[0], cm_id_priv->av.ah_attr.roce.dmac); diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index b5fa19a033c0aa636207985d1ab05866e48127a8..9ed5de38e372f10f9da8040f229d35db5a351da9 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -1437,7 +1437,7 @@ static bool validate_ipv4_net_dev(struct net_device *net_dev, return false; memset(&fl4, 0, sizeof(fl4)); - fl4.flowi4_iif = net_dev->ifindex; + fl4.flowi4_oif = net_dev->ifindex; fl4.daddr = daddr; fl4.saddr = saddr; diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c index aa526c5ca0cf3789892cf82310e9708d810c1898..d91892ffe243625791a08972e4c980526c8b883c 100644 --- a/drivers/infiniband/core/device.c +++ b/drivers/infiniband/core/device.c @@ -2759,10 +2759,18 @@ static int __init ib_core_init(void) nldev_init(); rdma_nl_register(RDMA_NL_LS, ibnl_ls_cb_table); - roce_gid_mgmt_init(); + ret = roce_gid_mgmt_init(); + if (ret) { + pr_warn("Couldn't init RoCE GID management\n"); + goto err_parent; + } return 0; +err_parent: + rdma_nl_unregister(RDMA_NL_LS); + nldev_exit(); + unregister_pernet_device(&rdma_dev_net_ops); err_compat: unregister_blocking_lsm_notifier(&ibdev_lsm_nb); err_sa: diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c index 12d29d54a0812da5a778532ef0f1128f4ee10203..c90f6378d839609927722915c75c12dd014dcd26 100644 --- a/drivers/infiniband/core/nldev.c +++ b/drivers/infiniband/core/nldev.c @@ -2181,7 +2181,7 @@ void __init nldev_init(void) rdma_nl_register(RDMA_NL_NLDEV, nldev_cb_table); } -void __exit nldev_exit(void) +void nldev_exit(void) { rdma_nl_unregister(RDMA_NL_NLDEV); } diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c index 466026825dd7548192a9d4a0f44d1302a8986390..d7c90da9ce7f1d72830d314f3c4038206c2e13ee 100644 --- a/drivers/infiniband/core/uverbs_cmd.c +++ b/drivers/infiniband/core/uverbs_cmd.c @@ -749,6 +749,7 @@ static int ib_uverbs_reg_mr(struct uverbs_attr_bundle *attrs) mr->uobject = uobj; atomic_inc(&pd->usecnt); mr->iova = cmd.hca_va; + mr->length = cmd.length; rdma_restrack_new(&mr->res, RDMA_RESTRACK_MR); rdma_restrack_set_name(&mr->res, NULL); @@ -832,8 +833,10 @@ static int ib_uverbs_rereg_mr(struct uverbs_attr_bundle *attrs) atomic_dec(&old_pd->usecnt); } - if (cmd.flags & IB_MR_REREG_TRANS) + if (cmd.flags & IB_MR_REREG_TRANS) { mr->iova = cmd.hca_va; + mr->length = cmd.length; + } memset(&resp, 0, sizeof(resp)); resp.lkey = mr->lkey; diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c index 597e889ba83126ff337125782aeac8ea038ac8a4..5889639e90a1c246eaa75612cf4d13d2e4222bd7 100644 --- a/drivers/infiniband/core/verbs.c +++ b/drivers/infiniband/core/verbs.c @@ -2082,6 +2082,8 @@ struct ib_mr *ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length, mr->pd = pd; mr->dm = NULL; atomic_inc(&pd->usecnt); + mr->iova = virt_addr; + mr->length = length; rdma_restrack_new(&mr->res, RDMA_RESTRACK_MR); rdma_restrack_parent_name(&mr->res, &pd->res); diff --git a/drivers/infiniband/hw/hfi1/pio.c b/drivers/infiniband/hw/hfi1/pio.c index 1cd8f80f097a77408a97feed8d6858619ffa08fd..60eb3a64518f3ec4669fc2fae364353ce2c91631 100644 --- a/drivers/infiniband/hw/hfi1/pio.c +++ b/drivers/infiniband/hw/hfi1/pio.c @@ -955,8 +955,7 @@ void sc_disable(struct send_context *sc) spin_unlock(&sc->release_lock); write_seqlock(&sc->waitlock); - if (!list_empty(&sc->piowait)) - list_move(&sc->piowait, &wake_list); + list_splice_init(&sc->piowait, &wake_list); write_sequnlock(&sc->waitlock); while (!list_empty(&wake_list)) { struct iowait *wait; diff --git a/drivers/infiniband/hw/hns/hns_roce_mr.c b/drivers/infiniband/hw/hns/hns_roce_mr.c index 027ec8413ac25ccba513c4fc9cd6e25ff49e0abc..6d7cc724862fa8a3199e8c628a72b46c312613eb 100644 --- a/drivers/infiniband/hw/hns/hns_roce_mr.c +++ b/drivers/infiniband/hw/hns/hns_roce_mr.c @@ -286,7 +286,6 @@ struct ib_mr *hns_roce_reg_user_mr(struct ib_pd *pd, u64 start, u64 length, goto err_alloc_pbl; mr->ibmr.rkey = mr->ibmr.lkey = mr->key; - mr->ibmr.length = length; return &mr->ibmr; diff --git a/drivers/infiniband/hw/mlx4/mr.c b/drivers/infiniband/hw/mlx4/mr.c index 426fed005d538bd50a9deb3c9a9770337c595ec4..811b4bb345247d1bc42fa95bd3422743afa15290 100644 --- a/drivers/infiniband/hw/mlx4/mr.c +++ b/drivers/infiniband/hw/mlx4/mr.c @@ -439,7 +439,6 @@ struct ib_mr *mlx4_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length, goto err_mr; mr->ibmr.rkey = mr->ibmr.lkey = mr->mmr.key; - mr->ibmr.length = length; mr->ibmr.page_size = 1U << shift; return &mr->ibmr; diff --git a/drivers/infiniband/hw/qedr/main.c b/drivers/infiniband/hw/qedr/main.c index 967641662b24a75c37dd73e5a4dc2cdd891a91e3..d0bb61b7e419f2aeabeb7b7696e306baa13438d9 100644 --- a/drivers/infiniband/hw/qedr/main.c +++ b/drivers/infiniband/hw/qedr/main.c @@ -374,6 +374,10 @@ static int qedr_alloc_resources(struct qedr_dev *dev) if (IS_IWARP(dev)) { xa_init(&dev->qps); dev->iwarp_wq = create_singlethread_workqueue("qedr_iwarpq"); + if (!dev->iwarp_wq) { + rc = -ENOMEM; + goto err1; + } } /* Allocate Status blocks for CNQ */ @@ -381,7 +385,7 @@ static int qedr_alloc_resources(struct qedr_dev *dev) GFP_KERNEL); if (!dev->sb_array) { rc = -ENOMEM; - goto err1; + goto err_destroy_wq; } dev->cnq_array = kcalloc(dev->num_cnq, @@ -432,6 +436,9 @@ err3: kfree(dev->cnq_array); err2: kfree(dev->sb_array); +err_destroy_wq: + if (IS_IWARP(dev)) + destroy_workqueue(dev->iwarp_wq); err1: kfree(dev->sgid_tbl); return rc; diff --git a/drivers/infiniband/sw/rxe/rxe_qp.c b/drivers/infiniband/sw/rxe/rxe_qp.c index 2847ab4d9a5f045818a6e5b0f45a4b3f2818cc25..2e4b008f03870175b2fffb6141ca2461bc8bfdec 100644 --- a/drivers/infiniband/sw/rxe/rxe_qp.c +++ b/drivers/infiniband/sw/rxe/rxe_qp.c @@ -775,7 +775,9 @@ void rxe_qp_destroy(struct rxe_qp *qp) rxe_cleanup_task(&qp->comp.task); /* flush out any receive wr's or pending requests */ - __rxe_do_task(&qp->req.task); + if (qp->req.task.func) + __rxe_do_task(&qp->req.task); + if (qp->sq.queue) { __rxe_do_task(&qp->comp.task); __rxe_do_task(&qp->req.task); @@ -815,8 +817,10 @@ static void rxe_qp_do_cleanup(struct work_struct *work) free_rd_atomic_resources(qp); - kernel_sock_shutdown(qp->sk, SHUT_RDWR); - sock_release(qp->sk); + if (qp->sk) { + kernel_sock_shutdown(qp->sk, SHUT_RDWR); + sock_release(qp->sk); + } } /* called when the last reference to the qp is dropped */ diff --git a/drivers/infiniband/sw/siw/siw_qp_rx.c b/drivers/infiniband/sw/siw/siw_qp_rx.c index 875ea6f1b04a29034b6b41f8bfedaefc01af28c6..fd721cc19682eb2ca510315abb4e3ab60f2f8116 100644 --- a/drivers/infiniband/sw/siw/siw_qp_rx.c +++ b/drivers/infiniband/sw/siw/siw_qp_rx.c @@ -961,27 +961,28 @@ out: static int siw_get_trailer(struct siw_qp *qp, struct siw_rx_stream *srx) { struct sk_buff *skb = srx->skb; + int avail = min(srx->skb_new, srx->fpdu_part_rem); u8 *tbuf = (u8 *)&srx->trailer.crc - srx->pad; __wsum crc_in, crc_own = 0; siw_dbg_qp(qp, "expected %d, available %d, pad %u\n", srx->fpdu_part_rem, srx->skb_new, srx->pad); - if (srx->skb_new < srx->fpdu_part_rem) - return -EAGAIN; - - skb_copy_bits(skb, srx->skb_offset, tbuf, srx->fpdu_part_rem); + skb_copy_bits(skb, srx->skb_offset, tbuf, avail); - if (srx->mpa_crc_hd && srx->pad) - crypto_shash_update(srx->mpa_crc_hd, tbuf, srx->pad); + srx->skb_new -= avail; + srx->skb_offset += avail; + srx->skb_copied += avail; + srx->fpdu_part_rem -= avail; - srx->skb_new -= srx->fpdu_part_rem; - srx->skb_offset += srx->fpdu_part_rem; - srx->skb_copied += srx->fpdu_part_rem; + if (srx->fpdu_part_rem) + return -EAGAIN; if (!srx->mpa_crc_hd) return 0; + if (srx->pad) + crypto_shash_update(srx->mpa_crc_hd, tbuf, srx->pad); /* * CRC32 is computed, transmitted and received directly in NBO, * so there's never a reason to convert byte order. @@ -1083,10 +1084,9 @@ static int siw_get_hdr(struct siw_rx_stream *srx) * completely received. */ if (iwarp_pktinfo[opcode].hdr_len > sizeof(struct iwarp_ctrl_tagged)) { - bytes = iwarp_pktinfo[opcode].hdr_len - MIN_DDP_HDR; + int hdrlen = iwarp_pktinfo[opcode].hdr_len; - if (srx->skb_new < bytes) - return -EAGAIN; + bytes = min_t(int, hdrlen - MIN_DDP_HDR, srx->skb_new); skb_copy_bits(skb, srx->skb_offset, (char *)c_hdr + srx->fpdu_part_rcvd, bytes); @@ -1096,6 +1096,9 @@ static int siw_get_hdr(struct siw_rx_stream *srx) srx->skb_new -= bytes; srx->skb_offset += bytes; srx->skb_copied += bytes; + + if (srx->fpdu_part_rcvd < hdrlen) + return -EAGAIN; } /* diff --git a/drivers/input/joystick/iforce/iforce-main.c b/drivers/input/joystick/iforce/iforce-main.c index b86de1312512bd3a1b41ab795956bdbe317f5974..84b87526b7ba319d98494c53a06364e5369f4d23 100644 --- a/drivers/input/joystick/iforce/iforce-main.c +++ b/drivers/input/joystick/iforce/iforce-main.c @@ -273,22 +273,22 @@ int iforce_init_device(struct device *parent, u16 bustype, * Get device info. */ - if (!iforce_get_id_packet(iforce, 'M', buf, &len) || len < 3) + if (!iforce_get_id_packet(iforce, 'M', buf, &len) && len >= 3) input_dev->id.vendor = get_unaligned_le16(buf + 1); else dev_warn(&iforce->dev->dev, "Device does not respond to id packet M\n"); - if (!iforce_get_id_packet(iforce, 'P', buf, &len) || len < 3) + if (!iforce_get_id_packet(iforce, 'P', buf, &len) && len >= 3) input_dev->id.product = get_unaligned_le16(buf + 1); else dev_warn(&iforce->dev->dev, "Device does not respond to id packet P\n"); - if (!iforce_get_id_packet(iforce, 'B', buf, &len) || len < 3) + if (!iforce_get_id_packet(iforce, 'B', buf, &len) && len >= 3) iforce->device_memory.end = get_unaligned_le16(buf + 1); else dev_warn(&iforce->dev->dev, "Device does not respond to id packet B\n"); - if (!iforce_get_id_packet(iforce, 'N', buf, &len) || len < 2) + if (!iforce_get_id_packet(iforce, 'N', buf, &len) && len >= 2) ff_effects = buf[1]; else dev_warn(&iforce->dev->dev, "Device does not respond to id packet N\n"); diff --git a/drivers/input/misc/soc_button_array.c b/drivers/input/misc/soc_button_array.c index efffcf0ebd3b42ef1c3a1b203cc46995eada4cbf..31c02c2019c1c5da338e338766738561df6120aa 100644 --- a/drivers/input/misc/soc_button_array.c +++ b/drivers/input/misc/soc_button_array.c @@ -18,6 +18,10 @@ #include #include +static bool use_low_level_irq; +module_param(use_low_level_irq, bool, 0444); +MODULE_PARM_DESC(use_low_level_irq, "Use low-level triggered IRQ instead of edge triggered"); + struct soc_button_info { const char *name; int acpi_index; @@ -73,6 +77,13 @@ static const struct dmi_system_id dmi_use_low_level_irq[] = { DMI_MATCH(DMI_PRODUCT_NAME, "Aspire SW5-012"), }, }, + { + /* Acer Switch V 10 SW5-017, same issue as Acer Switch 10 SW5-012. */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "SW5-017"), + }, + }, { /* * Acer One S1003. _LID method messes with power-button GPIO @@ -164,7 +175,8 @@ soc_button_device_create(struct platform_device *pdev, } /* See dmi_use_low_level_irq[] comment */ - if (!autorepeat && dmi_check_system(dmi_use_low_level_irq)) { + if (!autorepeat && (use_low_level_irq || + dmi_check_system(dmi_use_low_level_irq))) { irq_set_irq_type(irq, IRQ_TYPE_LEVEL_LOW); gpio_keys[n_buttons].irq = irq; gpio_keys[n_buttons].gpio = -ENOENT; diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c index 82577095e175efd1969cdfbc40f9b2af8b6340f4..f1013b950d579047fb2e253408e7ccbae7a81137 100644 --- a/drivers/input/mouse/synaptics.c +++ b/drivers/input/mouse/synaptics.c @@ -191,6 +191,7 @@ static const char * const smbus_pnp_ids[] = { "SYN3221", /* HP 15-ay000 */ "SYN323d", /* HP Spectre X360 13-w013dx */ "SYN3257", /* HP Envy 13-ad105ng */ + "SYN3286", /* HP Laptop 15-da3001TU */ NULL }; diff --git a/drivers/input/serio/i8042.c b/drivers/input/serio/i8042.c index a9f68f535b727bc56ced6311a91a6144082e72fe..8648b4c46138b40d7318262079380424e7de10b4 100644 --- a/drivers/input/serio/i8042.c +++ b/drivers/input/serio/i8042.c @@ -1543,8 +1543,6 @@ static int i8042_probe(struct platform_device *dev) { int error; - i8042_platform_device = dev; - if (i8042_reset == I8042_RESET_ALWAYS) { error = i8042_controller_selftest(); if (error) @@ -1582,7 +1580,6 @@ static int i8042_probe(struct platform_device *dev) i8042_free_aux_ports(); /* in case KBD failed but AUX not */ i8042_free_irqs(); i8042_controller_reset(false); - i8042_platform_device = NULL; return error; } @@ -1592,7 +1589,6 @@ static int i8042_remove(struct platform_device *dev) i8042_unregister_ports(); i8042_free_irqs(); i8042_controller_reset(false); - i8042_platform_device = NULL; return 0; } diff --git a/drivers/input/touchscreen/goodix.c b/drivers/input/touchscreen/goodix.c index b23abde5d7db3be5c4020b2e48f427582deea95e..b7f87ad4b9a956800a55f1caa48f21f6eb29d136 100644 --- a/drivers/input/touchscreen/goodix.c +++ b/drivers/input/touchscreen/goodix.c @@ -1059,6 +1059,7 @@ static int goodix_configure_dev(struct goodix_ts_data *ts) input_set_abs_params(ts->input_dev, ABS_MT_WIDTH_MAJOR, 0, 255, 0, 0); input_set_abs_params(ts->input_dev, ABS_MT_TOUCH_MAJOR, 0, 255, 0, 0); +retry_read_config: /* Read configuration and apply touchscreen parameters */ goodix_read_config(ts); @@ -1066,6 +1067,16 @@ static int goodix_configure_dev(struct goodix_ts_data *ts) touchscreen_parse_properties(ts->input_dev, true, &ts->prop); if (!ts->prop.max_x || !ts->prop.max_y || !ts->max_touch_num) { + if (!ts->reset_controller_at_probe && + ts->irq_pin_access_method != IRQ_PIN_ACCESS_NONE) { + dev_info(&ts->client->dev, "Config not set, resetting controller\n"); + /* Retry after a controller reset */ + ts->reset_controller_at_probe = true; + error = goodix_reset(ts); + if (error) + return error; + goto retry_read_config; + } dev_err(&ts->client->dev, "Invalid config (%d, %d, %d), using defaults\n", ts->prop.max_x, ts->prop.max_y, ts->max_touch_num); diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 8f0af4a4b562a17be4a28b5de3396e0d58d3952f..03f81f1135495c2171856f0d88a76faca74e4932 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -2846,6 +2846,7 @@ static int __init si_domain_init(int hw) if (md_domain_init(si_domain, DEFAULT_DOMAIN_ADDRESS_WIDTH)) { domain_exit(si_domain); + si_domain = NULL; return -EFAULT; } @@ -3505,6 +3506,10 @@ free_iommu: disable_dmar_iommu(iommu); free_dmar_iommu(iommu); } + if (si_domain) { + domain_exit(si_domain); + si_domain = NULL; + } kfree(g_iommus); diff --git a/drivers/iommu/intel/pasid.c b/drivers/iommu/intel/pasid.c index fb911b6c418f2b3bc4ca4de18ac1f65f6e0ac35a..86fd49ae7f612d7c64d42a59fa16a7a0c670715b 100644 --- a/drivers/iommu/intel/pasid.c +++ b/drivers/iommu/intel/pasid.c @@ -669,7 +669,7 @@ int intel_pasid_setup_second_level(struct intel_iommu *iommu, * Since it is a second level only translation setup, we should * set SRE bit as well (addresses are expected to be GPAs). */ - if (pasid != PASID_RID2PASID) + if (pasid != PASID_RID2PASID && ecap_srs(iommu->ecap)) pasid_set_sre(pte); pasid_set_present(pte); pasid_flush_caches(iommu, pte, pasid, did); @@ -704,7 +704,8 @@ int intel_pasid_setup_pass_through(struct intel_iommu *iommu, * We should set SRE bit as well since the addresses are expected * to be GPAs. */ - pasid_set_sre(pte); + if (ecap_srs(iommu->ecap)) + pasid_set_sre(pte); pasid_set_present(pte); pasid_flush_caches(iommu, pte, pasid, did); diff --git a/drivers/iommu/omap-iommu-debug.c b/drivers/iommu/omap-iommu-debug.c index a99afb5d9011c5375905d54520e9851048bfbc5a..259f65291d909696ca91bbc70f50791a097969f0 100644 --- a/drivers/iommu/omap-iommu-debug.c +++ b/drivers/iommu/omap-iommu-debug.c @@ -32,12 +32,12 @@ static inline bool is_omap_iommu_detached(struct omap_iommu *obj) ssize_t bytes; \ const char *str = "%20s: %08x\n"; \ const int maxcol = 32; \ - bytes = snprintf(p, maxcol, str, __stringify(name), \ + if (len < maxcol) \ + goto out; \ + bytes = scnprintf(p, maxcol, str, __stringify(name), \ iommu_read_reg(obj, MMU_##name)); \ p += bytes; \ len -= bytes; \ - if (len < maxcol) \ - goto out; \ } while (0) static ssize_t diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 2c93c53fc6885734983c04b2257bff3680b7bf73..8e988615925e6090ffd409b9fd1b0d2accc18487 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -1622,7 +1622,7 @@ static int its_select_cpu(struct irq_data *d, cpu = cpumask_pick_least_loaded(d, tmpmask); } else { - cpumask_and(tmpmask, irq_data_get_affinity_mask(d), cpu_online_mask); + cpumask_copy(tmpmask, aff_mask); /* If we cannot cross sockets, limit the search to that node */ if ((its_dev->its->flags & ITS_FLAGS_WORKAROUND_CAVIUM_23144) && diff --git a/drivers/isdn/hardware/mISDN/netjet.c b/drivers/isdn/hardware/mISDN/netjet.c index a52f275f826348475b0f49a241ee73b2c6553fca..f8447135a90220bf24eef9403d13f725035ef43a 100644 --- a/drivers/isdn/hardware/mISDN/netjet.c +++ b/drivers/isdn/hardware/mISDN/netjet.c @@ -956,7 +956,7 @@ nj_release(struct tiger_hw *card) } if (card->irq > 0) free_irq(card->irq, card); - if (card->isac.dch.dev.dev.class) + if (device_is_registered(&card->isac.dch.dev.dev)) mISDN_unregister_device(&card->isac.dch.dev); for (i = 0; i < 2; i++) { diff --git a/drivers/isdn/mISDN/core.c b/drivers/isdn/mISDN/core.c index a41b4b264594121e45b338d151c59fd4937c16c4..90ee56d07a6e92f434619e15a90cd2c613093abf 100644 --- a/drivers/isdn/mISDN/core.c +++ b/drivers/isdn/mISDN/core.c @@ -222,7 +222,7 @@ mISDN_register_device(struct mISDNdevice *dev, err = get_free_devid(); if (err < 0) - goto error1; + return err; dev->id = err; device_initialize(&dev->dev); @@ -233,11 +233,12 @@ mISDN_register_device(struct mISDNdevice *dev, if (debug & DEBUG_CORE) printk(KERN_DEBUG "mISDN_register %s %d\n", dev_name(&dev->dev), dev->id); + dev->dev.class = &mISDN_class; + err = create_stack(dev); if (err) goto error1; - dev->dev.class = &mISDN_class; dev->dev.platform_data = dev; dev->dev.parent = parent; dev_set_drvdata(&dev->dev, dev); @@ -249,8 +250,8 @@ mISDN_register_device(struct mISDNdevice *dev, error3: delete_stack(dev); - return err; error1: + put_device(&dev->dev); return err; } diff --git a/drivers/isdn/mISDN/dsp_pipeline.c b/drivers/isdn/mISDN/dsp_pipeline.c index c3b2c99b5cd5ceaf12c9fc7dcd929840ec6b3870..cfbcd9e973c2e64f71dd82710f59b1a2dd78dfc8 100644 --- a/drivers/isdn/mISDN/dsp_pipeline.c +++ b/drivers/isdn/mISDN/dsp_pipeline.c @@ -77,6 +77,7 @@ int mISDN_dsp_element_register(struct mISDN_dsp_element *elem) if (!entry) return -ENOMEM; + INIT_LIST_HEAD(&entry->list); entry->elem = elem; entry->dev.class = elements_class; @@ -107,7 +108,7 @@ err2: device_unregister(&entry->dev); return ret; err1: - kfree(entry); + put_device(&entry->dev); return ret; } EXPORT_SYMBOL(mISDN_dsp_element_register); diff --git a/drivers/isdn/mISDN/l1oip.h b/drivers/isdn/mISDN/l1oip.h index 7ea10db20e3a6567d91b4d6d8b63daa99eadaa98..48133d022812071543fb4e0fee48af6968619f2d 100644 --- a/drivers/isdn/mISDN/l1oip.h +++ b/drivers/isdn/mISDN/l1oip.h @@ -59,6 +59,7 @@ struct l1oip { int bundle; /* bundle channels in one frm */ int codec; /* codec to use for transmis. */ int limit; /* limit number of bchannels */ + bool shutdown; /* if card is released */ /* timer */ struct timer_list keep_tl; diff --git a/drivers/isdn/mISDN/l1oip_core.c b/drivers/isdn/mISDN/l1oip_core.c index b57dcb834594de13eb1b90492a38b69a479f1b50..aec4f2a69c3bddbd45a66f5e8d81bdb8abefb4d2 100644 --- a/drivers/isdn/mISDN/l1oip_core.c +++ b/drivers/isdn/mISDN/l1oip_core.c @@ -275,7 +275,7 @@ l1oip_socket_send(struct l1oip *hc, u8 localcodec, u8 channel, u32 chanmask, p = frame; /* restart timer */ - if (time_before(hc->keep_tl.expires, jiffies + 5 * HZ)) + if (time_before(hc->keep_tl.expires, jiffies + 5 * HZ) && !hc->shutdown) mod_timer(&hc->keep_tl, jiffies + L1OIP_KEEPALIVE * HZ); else hc->keep_tl.expires = jiffies + L1OIP_KEEPALIVE * HZ; @@ -601,7 +601,9 @@ multiframe: goto multiframe; /* restart timer */ - if (time_before(hc->timeout_tl.expires, jiffies + 5 * HZ) || !hc->timeout_on) { + if ((time_before(hc->timeout_tl.expires, jiffies + 5 * HZ) || + !hc->timeout_on) && + !hc->shutdown) { hc->timeout_on = 1; mod_timer(&hc->timeout_tl, jiffies + L1OIP_TIMEOUT * HZ); } else /* only adjust timer */ @@ -1232,11 +1234,10 @@ release_card(struct l1oip *hc) { int ch; - if (timer_pending(&hc->keep_tl)) - del_timer(&hc->keep_tl); + hc->shutdown = true; - if (timer_pending(&hc->timeout_tl)) - del_timer(&hc->timeout_tl); + del_timer_sync(&hc->keep_tl); + del_timer_sync(&hc->timeout_tl); cancel_work_sync(&hc->workq); diff --git a/drivers/leds/leds-lm3601x.c b/drivers/leds/leds-lm3601x.c index d0e1d4814042e52c5896df61c923e197181c63e3..3d127274820173667a9648de4a2af2ca821cbf3e 100644 --- a/drivers/leds/leds-lm3601x.c +++ b/drivers/leds/leds-lm3601x.c @@ -444,8 +444,6 @@ static int lm3601x_remove(struct i2c_client *client) { struct lm3601x_led *led = i2c_get_clientdata(client); - mutex_destroy(&led->lock); - return regmap_update_bits(led->regmap, LM3601X_ENABLE_REG, LM3601X_ENABLE_MASK, LM3601X_MODE_STANDBY); diff --git a/drivers/mailbox/bcm-flexrm-mailbox.c b/drivers/mailbox/bcm-flexrm-mailbox.c index bee33abb530849de1aa6f5b8593c004e53d4af3d..e913ed1e34c63d597abb9b459fd03a4d97bec480 100644 --- a/drivers/mailbox/bcm-flexrm-mailbox.c +++ b/drivers/mailbox/bcm-flexrm-mailbox.c @@ -632,15 +632,15 @@ static int flexrm_spu_dma_map(struct device *dev, struct brcm_message *msg) rc = dma_map_sg(dev, msg->spu.src, sg_nents(msg->spu.src), DMA_TO_DEVICE); - if (rc < 0) - return rc; + if (!rc) + return -EIO; rc = dma_map_sg(dev, msg->spu.dst, sg_nents(msg->spu.dst), DMA_FROM_DEVICE); - if (rc < 0) { + if (!rc) { dma_unmap_sg(dev, msg->spu.src, sg_nents(msg->spu.src), DMA_TO_DEVICE); - return rc; + return -EIO; } return 0; diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c index a878b959fbcdd80e6fac0a98fcdbf93c84be190d..3aa73da2c67bdf2edf5cd1e455ff58ef6fac0f2b 100644 --- a/drivers/md/bcache/writeback.c +++ b/drivers/md/bcache/writeback.c @@ -119,6 +119,53 @@ static void __update_writeback_rate(struct cached_dev *dc) dc->writeback_rate_target = target; } +static bool idle_counter_exceeded(struct cache_set *c) +{ + int counter, dev_nr; + + /* + * If c->idle_counter is overflow (idel for really long time), + * reset as 0 and not set maximum rate this time for code + * simplicity. + */ + counter = atomic_inc_return(&c->idle_counter); + if (counter <= 0) { + atomic_set(&c->idle_counter, 0); + return false; + } + + dev_nr = atomic_read(&c->attached_dev_nr); + if (dev_nr == 0) + return false; + + /* + * c->idle_counter is increased by writeback thread of all + * attached backing devices, in order to represent a rough + * time period, counter should be divided by dev_nr. + * Otherwise the idle time cannot be larger with more backing + * device attached. + * The following calculation equals to checking + * (counter / dev_nr) < (dev_nr * 6) + */ + if (counter < (dev_nr * dev_nr * 6)) + return false; + + return true; +} + +/* + * Idle_counter is increased every time when update_writeback_rate() is + * called. If all backing devices attached to the same cache set have + * identical dc->writeback_rate_update_seconds values, it is about 6 + * rounds of update_writeback_rate() on each backing device before + * c->at_max_writeback_rate is set to 1, and then max wrteback rate set + * to each dc->writeback_rate.rate. + * In order to avoid extra locking cost for counting exact dirty cached + * devices number, c->attached_dev_nr is used to calculate the idle + * throushold. It might be bigger if not all cached device are in write- + * back mode, but it still works well with limited extra rounds of + * update_writeback_rate(). + */ static bool set_at_max_writeback_rate(struct cache_set *c, struct cached_dev *dc) { @@ -129,21 +176,8 @@ static bool set_at_max_writeback_rate(struct cache_set *c, /* Don't set max writeback rate if gc is running */ if (!c->gc_mark_valid) return false; - /* - * Idle_counter is increased everytime when update_writeback_rate() is - * called. If all backing devices attached to the same cache set have - * identical dc->writeback_rate_update_seconds values, it is about 6 - * rounds of update_writeback_rate() on each backing device before - * c->at_max_writeback_rate is set to 1, and then max wrteback rate set - * to each dc->writeback_rate.rate. - * In order to avoid extra locking cost for counting exact dirty cached - * devices number, c->attached_dev_nr is used to calculate the idle - * throushold. It might be bigger if not all cached device are in write- - * back mode, but it still works well with limited extra rounds of - * update_writeback_rate(). - */ - if (atomic_inc_return(&c->idle_counter) < - atomic_read(&c->attached_dev_nr) * 6) + + if (!idle_counter_exceeded(c)) return false; if (atomic_read(&c->at_max_writeback_rate) != 1) @@ -157,13 +191,10 @@ static bool set_at_max_writeback_rate(struct cache_set *c, dc->writeback_rate_change = 0; /* - * Check c->idle_counter and c->at_max_writeback_rate agagain in case - * new I/O arrives during before set_at_max_writeback_rate() returns. - * Then the writeback rate is set to 1, and its new value should be - * decided via __update_writeback_rate(). + * In case new I/O arrives during before + * set_at_max_writeback_rate() returns. */ - if ((atomic_read(&c->idle_counter) < - atomic_read(&c->attached_dev_nr) * 6) || + if (!idle_counter_exceeded(c) || !atomic_read(&c->at_max_writeback_rate)) return false; diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c index 835b1f3464d068339fdd1881cf9fbdb1b33805a4..2156a2d5ac70e7b43f592f9b9c51f78dd9c32cfe 100644 --- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -254,6 +254,7 @@ struct dm_integrity_c { struct completion crypto_backoff; + bool wrote_to_journal; bool journal_uptodate; bool just_formatted; bool recalculate_flag; @@ -2256,6 +2257,8 @@ static void integrity_commit(struct work_struct *w) if (!commit_sections) goto release_flush_bios; + ic->wrote_to_journal = true; + i = commit_start; for (n = 0; n < commit_sections; n++) { for (j = 0; j < ic->journal_section_entries; j++) { @@ -2470,10 +2473,6 @@ static void integrity_writer(struct work_struct *w) unsigned prev_free_sectors; - /* the following test is not needed, but it tests the replay code */ - if (unlikely(dm_post_suspending(ic->ti)) && !ic->meta_dev) - return; - spin_lock_irq(&ic->endio_wait.lock); write_start = ic->committed_section; write_sections = ic->n_committed_sections; @@ -2980,10 +2979,17 @@ static void dm_integrity_postsuspend(struct dm_target *ti) drain_workqueue(ic->commit_wq); if (ic->mode == 'J') { - if (ic->meta_dev) - queue_work(ic->writer_wq, &ic->writer_work); + queue_work(ic->writer_wq, &ic->writer_work); drain_workqueue(ic->writer_wq); dm_integrity_flush_buffers(ic, true); + if (ic->wrote_to_journal) { + init_journal(ic, ic->free_section, + ic->journal_sections - ic->free_section, ic->commit_seq); + if (ic->free_section) { + init_journal(ic, 0, ic->free_section, + next_commit_seq(ic->commit_seq)); + } + } } if (ic->mode == 'B') { @@ -3011,6 +3017,8 @@ static void dm_integrity_resume(struct dm_target *ti) DEBUG_print("resume\n"); + ic->wrote_to_journal = false; + if (ic->provided_data_sectors != old_provided_data_sectors) { if (ic->provided_data_sectors > old_provided_data_sectors && ic->mode == 'B' && diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c index b839705654d4ed1fc14e2c7ae44ccc690780eec7..20171c9d8952ebfc02e142c8a2dcee783cdb9294 100644 --- a/drivers/md/dm-ioctl.c +++ b/drivers/md/dm-ioctl.c @@ -573,7 +573,7 @@ static void list_version_get_needed(struct target_type *tt, void *needed_param) size_t *needed = needed_param; *needed += sizeof(struct dm_target_versions); - *needed += strlen(tt->name); + *needed += strlen(tt->name) + 1; *needed += ALIGN_MASK; } @@ -638,7 +638,7 @@ static int __list_versions(struct dm_ioctl *param, size_t param_size, const char iter_info.old_vers = NULL; iter_info.vers = vers; iter_info.flags = 0; - iter_info.end = (char *)vers+len; + iter_info.end = (char *)vers + needed; /* * Now loop through filling out the names & versions. diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index a4c0cafa6010a8eaeb50451dc9b32a9ad81a0bb6..a20332e755e816f38ca212b84fea60855d0f603a 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -48,7 +48,7 @@ static void dump_zones(struct mddev *mddev) int len = 0; for (k = 0; k < conf->strip_zone[j].nb_dev; k++) - len += snprintf(line+len, 200-len, "%s%s", k?"/":"", + len += scnprintf(line+len, 200-len, "%s%s", k?"/":"", bdevname(conf->devlist[j*raid_disks + k]->bdev, b)); pr_debug("md: zone%d=[%s]\n", j, line); diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 01c7edf329367efb33d02ecdc901b10c2de10839..9f114b9d8dc6bb17a603bc564ca0316eb917d2c3 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -36,6 +36,7 @@ */ #include +#include #include #include #include @@ -3936,7 +3937,7 @@ static void handle_stripe_fill(struct stripe_head *sh, * back cache (prexor with orig_page, and then xor with * page) in the read path */ - if (s->injournal && s->failed) { + if (s->to_read && s->injournal && s->failed) { if (test_bit(STRIPE_R5C_CACHING, &sh->state)) r5c_make_stripe_write_out(sh); goto out; @@ -6519,7 +6520,18 @@ static void raid5d(struct md_thread *thread) spin_unlock_irq(&conf->device_lock); md_check_recovery(mddev); spin_lock_irq(&conf->device_lock); + + /* + * Waiting on MD_SB_CHANGE_PENDING below may deadlock + * seeing md_check_recovery() is needed to clear + * the flag when using mdmon. + */ + continue; } + + wait_event_lock_irq(mddev->sb_wait, + !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags), + conf->device_lock); } pr_debug("%d stripes handled\n", handled); diff --git a/drivers/media/cec/platform/cros-ec/cros-ec-cec.c b/drivers/media/cec/platform/cros-ec/cros-ec-cec.c index 2d95e16cd248934bfd8f27da9343f80864b7bba6..f66699d5dc66ee847782db67a9ee623c0e7e3809 100644 --- a/drivers/media/cec/platform/cros-ec/cros-ec-cec.c +++ b/drivers/media/cec/platform/cros-ec/cros-ec-cec.c @@ -44,6 +44,8 @@ static void handle_cec_message(struct cros_ec_cec *cros_ec_cec) uint8_t *cec_message = cros_ec->event_data.data.cec_message; unsigned int len = cros_ec->event_size; + if (len > CEC_MAX_MSG_SIZE) + len = CEC_MAX_MSG_SIZE; cros_ec_cec->rx_msg.len = len; memcpy(cros_ec_cec->rx_msg.msg, cec_message, len); diff --git a/drivers/media/cec/platform/s5p/s5p_cec.c b/drivers/media/cec/platform/s5p/s5p_cec.c index 028a09a7531efd986cba2bbdb63d724cca1917a1..102f1af01000a120486db5f606f18394f93936b5 100644 --- a/drivers/media/cec/platform/s5p/s5p_cec.c +++ b/drivers/media/cec/platform/s5p/s5p_cec.c @@ -115,6 +115,8 @@ static irqreturn_t s5p_cec_irq_handler(int irq, void *priv) dev_dbg(cec->dev, "Buffer overrun (worker did not process previous message)\n"); cec->rx = STATE_BUSY; cec->msg.len = status >> 24; + if (cec->msg.len > CEC_MAX_MSG_SIZE) + cec->msg.len = CEC_MAX_MSG_SIZE; cec->msg.rx_status = CEC_RX_STATUS_OK; s5p_cec_get_rx_buf(cec, cec->msg.len, cec->msg.msg); diff --git a/drivers/media/dvb-core/dmxdev.c b/drivers/media/dvb-core/dmxdev.c index e58cb8434dafeea3323ea892028be6ffde3ca155..12b7f698f562303a56d6948c33fbcfb86256624f 100644 --- a/drivers/media/dvb-core/dmxdev.c +++ b/drivers/media/dvb-core/dmxdev.c @@ -800,6 +800,11 @@ static int dvb_demux_open(struct inode *inode, struct file *file) if (mutex_lock_interruptible(&dmxdev->mutex)) return -ERESTARTSYS; + if (dmxdev->exit) { + mutex_unlock(&dmxdev->mutex); + return -ENODEV; + } + for (i = 0; i < dmxdev->filternum; i++) if (dmxdev->filter[i].state == DMXDEV_STATE_FREE) break; @@ -1458,7 +1463,10 @@ EXPORT_SYMBOL(dvb_dmxdev_init); void dvb_dmxdev_release(struct dmxdev *dmxdev) { + mutex_lock(&dmxdev->mutex); dmxdev->exit = 1; + mutex_unlock(&dmxdev->mutex); + if (dmxdev->dvbdev->users > 1) { wait_event(dmxdev->dvbdev->wait_queue, dmxdev->dvbdev->users == 1); diff --git a/drivers/media/dvb-frontends/drxk_hard.c b/drivers/media/dvb-frontends/drxk_hard.c index a57470bf71bf3a944d98acec7b61b864b591b799..2134e25096aac877d865c2047afb0aa06e52bb81 100644 --- a/drivers/media/dvb-frontends/drxk_hard.c +++ b/drivers/media/dvb-frontends/drxk_hard.c @@ -6672,7 +6672,7 @@ static int drxk_read_snr(struct dvb_frontend *fe, u16 *snr) static int drxk_read_ucblocks(struct dvb_frontend *fe, u32 *ucblocks) { struct drxk_state *state = fe->demodulator_priv; - u16 err; + u16 err = 0; dprintk(1, "\n"); diff --git a/drivers/media/pci/cx88/cx88-vbi.c b/drivers/media/pci/cx88/cx88-vbi.c index 58489ea0c1da1ab3d4c867227f460583eca21b9c..7cf2271866d05e8e86a368356a9b6aebb62bb65a 100644 --- a/drivers/media/pci/cx88/cx88-vbi.c +++ b/drivers/media/pci/cx88/cx88-vbi.c @@ -144,11 +144,10 @@ static int buffer_prepare(struct vb2_buffer *vb) return -EINVAL; vb2_set_plane_payload(vb, 0, size); - cx88_risc_buffer(dev->pci, &buf->risc, sgt->sgl, - 0, VBI_LINE_LENGTH * lines, - VBI_LINE_LENGTH, 0, - lines); - return 0; + return cx88_risc_buffer(dev->pci, &buf->risc, sgt->sgl, + 0, VBI_LINE_LENGTH * lines, + VBI_LINE_LENGTH, 0, + lines); } static void buffer_finish(struct vb2_buffer *vb) diff --git a/drivers/media/pci/cx88/cx88-video.c b/drivers/media/pci/cx88/cx88-video.c index 8cffdacf600792ee4fa301cdea4a7c79de6026b5..e5adffa3a99a849028a4e3b65e7ac503b9ae5b1f 100644 --- a/drivers/media/pci/cx88/cx88-video.c +++ b/drivers/media/pci/cx88/cx88-video.c @@ -431,6 +431,7 @@ static int queue_setup(struct vb2_queue *q, static int buffer_prepare(struct vb2_buffer *vb) { + int ret; struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb); struct cx8800_dev *dev = vb->vb2_queue->drv_priv; struct cx88_core *core = dev->core; @@ -445,35 +446,35 @@ static int buffer_prepare(struct vb2_buffer *vb) switch (core->field) { case V4L2_FIELD_TOP: - cx88_risc_buffer(dev->pci, &buf->risc, - sgt->sgl, 0, UNSET, - buf->bpl, 0, core->height); + ret = cx88_risc_buffer(dev->pci, &buf->risc, + sgt->sgl, 0, UNSET, + buf->bpl, 0, core->height); break; case V4L2_FIELD_BOTTOM: - cx88_risc_buffer(dev->pci, &buf->risc, - sgt->sgl, UNSET, 0, - buf->bpl, 0, core->height); + ret = cx88_risc_buffer(dev->pci, &buf->risc, + sgt->sgl, UNSET, 0, + buf->bpl, 0, core->height); break; case V4L2_FIELD_SEQ_TB: - cx88_risc_buffer(dev->pci, &buf->risc, - sgt->sgl, - 0, buf->bpl * (core->height >> 1), - buf->bpl, 0, - core->height >> 1); + ret = cx88_risc_buffer(dev->pci, &buf->risc, + sgt->sgl, + 0, buf->bpl * (core->height >> 1), + buf->bpl, 0, + core->height >> 1); break; case V4L2_FIELD_SEQ_BT: - cx88_risc_buffer(dev->pci, &buf->risc, - sgt->sgl, - buf->bpl * (core->height >> 1), 0, - buf->bpl, 0, - core->height >> 1); + ret = cx88_risc_buffer(dev->pci, &buf->risc, + sgt->sgl, + buf->bpl * (core->height >> 1), 0, + buf->bpl, 0, + core->height >> 1); break; case V4L2_FIELD_INTERLACED: default: - cx88_risc_buffer(dev->pci, &buf->risc, - sgt->sgl, 0, buf->bpl, - buf->bpl, buf->bpl, - core->height >> 1); + ret = cx88_risc_buffer(dev->pci, &buf->risc, + sgt->sgl, 0, buf->bpl, + buf->bpl, buf->bpl, + core->height >> 1); break; } dprintk(2, @@ -481,7 +482,7 @@ static int buffer_prepare(struct vb2_buffer *vb) buf, buf->vb.vb2_buf.index, __func__, core->width, core->height, dev->fmt->depth, dev->fmt->fourcc, (unsigned long)buf->risc.dma); - return 0; + return ret; } static void buffer_finish(struct vb2_buffer *vb) diff --git a/drivers/media/platform/exynos4-is/fimc-is.c b/drivers/media/platform/exynos4-is/fimc-is.c index dc2a144cd29b6a1129e8ecfccc26d6f14c3b8f46..b52d2203eac57c605516cd6d8721b7dd0dced184 100644 --- a/drivers/media/platform/exynos4-is/fimc-is.c +++ b/drivers/media/platform/exynos4-is/fimc-is.c @@ -213,6 +213,7 @@ static int fimc_is_register_subdevs(struct fimc_is *is) if (ret < 0 || index >= FIMC_IS_SENSORS_NUM) { of_node_put(child); + of_node_put(i2c_bus); return ret; } index++; diff --git a/drivers/media/platform/qcom/venus/vdec.c b/drivers/media/platform/qcom/venus/vdec.c index ea13170a6a2cf8c322d4160bf701e26eb8c49704..de34a87d1130e6b5eea2d33974b3f94c1962d00f 100644 --- a/drivers/media/platform/qcom/venus/vdec.c +++ b/drivers/media/platform/qcom/venus/vdec.c @@ -158,6 +158,8 @@ vdec_try_fmt_common(struct venus_inst *inst, struct v4l2_format *f) else return NULL; fmt = find_format(inst, pixmp->pixelformat, f->type); + if (!fmt) + return NULL; } pixmp->width = clamp(pixmp->width, frame_width_min(inst), diff --git a/drivers/media/platform/xilinx/xilinx-vipp.c b/drivers/media/platform/xilinx/xilinx-vipp.c index cc2856efea5947cfd91f02f6cb18b9e9e01e15a7..f2b0c490187cdeb9fa0c87a999f60583a30c0d4e 100644 --- a/drivers/media/platform/xilinx/xilinx-vipp.c +++ b/drivers/media/platform/xilinx/xilinx-vipp.c @@ -472,7 +472,7 @@ static int xvip_graph_dma_init(struct xvip_composite_device *xdev) { struct device_node *ports; struct device_node *port; - int ret; + int ret = 0; ports = of_get_child_by_name(xdev->dev->of_node, "ports"); if (ports == NULL) { @@ -482,13 +482,14 @@ static int xvip_graph_dma_init(struct xvip_composite_device *xdev) for_each_child_of_node(ports, port) { ret = xvip_graph_dma_init_one(xdev, port); - if (ret < 0) { + if (ret) { of_node_put(port); - return ret; + break; } } - return 0; + of_node_put(ports); + return ret; } static void xvip_graph_cleanup(struct xvip_composite_device *xdev) diff --git a/drivers/media/rc/mceusb.c b/drivers/media/rc/mceusb.c index de4cf6eb5258b51b3a4dafb5835f2d3a7c4b9ffa..142319c48405d8163daede661d5cd819078c007f 100644 --- a/drivers/media/rc/mceusb.c +++ b/drivers/media/rc/mceusb.c @@ -1077,7 +1077,7 @@ static int mceusb_set_timeout(struct rc_dev *dev, unsigned int timeout) struct mceusb_dev *ir = dev->priv; unsigned int units; - units = DIV_ROUND_CLOSEST(timeout, MCE_TIME_UNIT); + units = DIV_ROUND_UP(timeout, MCE_TIME_UNIT); cmdbuf[2] = units >> 8; cmdbuf[3] = units; diff --git a/drivers/media/test-drivers/vivid/vivid-core.c b/drivers/media/test-drivers/vivid/vivid-core.c index 1e356dc65d3184483362eb3c24c7a317fbe68506..761d2abd40067ab7d7d3589a6e4bcda50ff816c8 100644 --- a/drivers/media/test-drivers/vivid/vivid-core.c +++ b/drivers/media/test-drivers/vivid/vivid-core.c @@ -330,6 +330,28 @@ static int vidioc_g_fbuf(struct file *file, void *fh, struct v4l2_framebuffer *a return vivid_vid_out_g_fbuf(file, fh, a); } +/* + * Only support the framebuffer of one of the vivid instances. + * Anything else is rejected. + */ +bool vivid_validate_fb(const struct v4l2_framebuffer *a) +{ + struct vivid_dev *dev; + int i; + + for (i = 0; i < n_devs; i++) { + dev = vivid_devs[i]; + if (!dev || !dev->video_pbase) + continue; + if ((unsigned long)a->base == dev->video_pbase && + a->fmt.width <= dev->display_width && + a->fmt.height <= dev->display_height && + a->fmt.bytesperline <= dev->display_byte_stride) + return true; + } + return false; +} + static int vidioc_s_fbuf(struct file *file, void *fh, const struct v4l2_framebuffer *a) { struct video_device *vdev = video_devdata(file); @@ -850,8 +872,12 @@ static int vivid_detect_feature_set(struct vivid_dev *dev, int inst, /* how many inputs do we have and of what type? */ dev->num_inputs = num_inputs[inst]; - if (dev->num_inputs < 1) - dev->num_inputs = 1; + if (node_type & 0x20007) { + if (dev->num_inputs < 1) + dev->num_inputs = 1; + } else { + dev->num_inputs = 0; + } if (dev->num_inputs >= MAX_INPUTS) dev->num_inputs = MAX_INPUTS; for (i = 0; i < dev->num_inputs; i++) { @@ -868,8 +894,12 @@ static int vivid_detect_feature_set(struct vivid_dev *dev, int inst, /* how many outputs do we have and of what type? */ dev->num_outputs = num_outputs[inst]; - if (dev->num_outputs < 1) - dev->num_outputs = 1; + if (node_type & 0x40300) { + if (dev->num_outputs < 1) + dev->num_outputs = 1; + } else { + dev->num_outputs = 0; + } if (dev->num_outputs >= MAX_OUTPUTS) dev->num_outputs = MAX_OUTPUTS; for (i = 0; i < dev->num_outputs; i++) { diff --git a/drivers/media/test-drivers/vivid/vivid-core.h b/drivers/media/test-drivers/vivid/vivid-core.h index 99e69b8f770f00570369048b26ccff303a9f9799..6aa32c8e6fb5cd401de1133750219aaa569097eb 100644 --- a/drivers/media/test-drivers/vivid/vivid-core.h +++ b/drivers/media/test-drivers/vivid/vivid-core.h @@ -609,4 +609,6 @@ static inline bool vivid_is_hdmi_out(const struct vivid_dev *dev) return dev->output_type[dev->output] == HDMI; } +bool vivid_validate_fb(const struct v4l2_framebuffer *a); + #endif diff --git a/drivers/media/test-drivers/vivid/vivid-vid-cap.c b/drivers/media/test-drivers/vivid/vivid-vid-cap.c index eadf28ab1e393d77da83684a637fd460c93adce2..d493bd17481b0dca009cbefd987d5331dd1381ea 100644 --- a/drivers/media/test-drivers/vivid/vivid-vid-cap.c +++ b/drivers/media/test-drivers/vivid/vivid-vid-cap.c @@ -452,6 +452,12 @@ void vivid_update_format_cap(struct vivid_dev *dev, bool keep_controls) tpg_reset_source(&dev->tpg, dev->src_rect.width, dev->src_rect.height, dev->field_cap); dev->crop_cap = dev->src_rect; dev->crop_bounds_cap = dev->src_rect; + if (dev->bitmap_cap && + (dev->compose_cap.width != dev->crop_cap.width || + dev->compose_cap.height != dev->crop_cap.height)) { + vfree(dev->bitmap_cap); + dev->bitmap_cap = NULL; + } dev->compose_cap = dev->crop_cap; if (V4L2_FIELD_HAS_T_OR_B(dev->field_cap)) dev->compose_cap.height /= 2; @@ -909,6 +915,8 @@ int vivid_vid_cap_s_selection(struct file *file, void *fh, struct v4l2_selection struct vivid_dev *dev = video_drvdata(file); struct v4l2_rect *crop = &dev->crop_cap; struct v4l2_rect *compose = &dev->compose_cap; + unsigned orig_compose_w = compose->width; + unsigned orig_compose_h = compose->height; unsigned factor = V4L2_FIELD_HAS_T_OR_B(dev->field_cap) ? 2 : 1; int ret; @@ -1025,17 +1033,17 @@ int vivid_vid_cap_s_selection(struct file *file, void *fh, struct v4l2_selection s->r.height /= factor; } v4l2_rect_map_inside(&s->r, &dev->fmt_cap_rect); - if (dev->bitmap_cap && (compose->width != s->r.width || - compose->height != s->r.height)) { - vfree(dev->bitmap_cap); - dev->bitmap_cap = NULL; - } *compose = s->r; break; default: return -EINVAL; } + if (dev->bitmap_cap && (compose->width != orig_compose_w || + compose->height != orig_compose_h)) { + vfree(dev->bitmap_cap); + dev->bitmap_cap = NULL; + } tpg_s_crop_compose(&dev->tpg, crop, compose); return 0; } @@ -1276,7 +1284,14 @@ int vivid_vid_cap_s_fbuf(struct file *file, void *fh, return -EINVAL; if (a->fmt.bytesperline < (a->fmt.width * fmt->bit_depth[0]) / 8) return -EINVAL; - if (a->fmt.height * a->fmt.bytesperline < a->fmt.sizeimage) + if (a->fmt.bytesperline > a->fmt.sizeimage / a->fmt.height) + return -EINVAL; + + /* + * Only support the framebuffer of one of the vivid instances. + * Anything else is rejected. + */ + if (!vivid_validate_fb(a)) return -EINVAL; dev->fb_vbase_cap = phys_to_virt((unsigned long)a->base); diff --git a/drivers/media/v4l2-core/v4l2-dv-timings.c b/drivers/media/v4l2-core/v4l2-dv-timings.c index af48705c704f8bc1a8bcdb2248dab0787043f5f8..003c32fed3f7546f58bd651d6c408505b0b4fd1f 100644 --- a/drivers/media/v4l2-core/v4l2-dv-timings.c +++ b/drivers/media/v4l2-core/v4l2-dv-timings.c @@ -161,6 +161,20 @@ bool v4l2_valid_dv_timings(const struct v4l2_dv_timings *t, (bt->interlaced && !(caps & V4L2_DV_BT_CAP_INTERLACED)) || (!bt->interlaced && !(caps & V4L2_DV_BT_CAP_PROGRESSIVE))) return false; + + /* sanity checks for the blanking timings */ + if (!bt->interlaced && + (bt->il_vbackporch || bt->il_vsync || bt->il_vfrontporch)) + return false; + if (bt->hfrontporch > 2 * bt->width || + bt->hsync > 1024 || bt->hbackporch > 1024) + return false; + if (bt->vfrontporch > 4096 || + bt->vsync > 128 || bt->vbackporch > 4096) + return false; + if (bt->interlaced && (bt->il_vfrontporch > 4096 || + bt->il_vsync > 128 || bt->il_vbackporch > 4096)) + return false; return fnc == NULL || fnc(t, fnc_handle); } EXPORT_SYMBOL_GPL(v4l2_valid_dv_timings); diff --git a/drivers/memory/of_memory.c b/drivers/memory/of_memory.c index d9f5437d3bce09e8124e16fa664539dc4b6948ed..1791614f324b7dca6668f89a1d4e751afb9fee82 100644 --- a/drivers/memory/of_memory.c +++ b/drivers/memory/of_memory.c @@ -134,6 +134,7 @@ const struct lpddr2_timings *of_get_ddr_timings(struct device_node *np_ddr, for_each_child_of_node(np_ddr, np_tim) { if (of_device_is_compatible(np_tim, tim_compat)) { if (of_do_get_timings(np_tim, &timings[i])) { + of_node_put(np_tim); devm_kfree(dev, timings); goto default_timings; } @@ -282,6 +283,7 @@ const struct lpddr3_timings if (of_device_is_compatible(np_tim, tim_compat)) { if (of_lpddr3_do_get_timings(np_tim, &timings[i])) { devm_kfree(dev, timings); + of_node_put(np_tim); goto default_timings; } i++; diff --git a/drivers/memory/pl353-smc.c b/drivers/memory/pl353-smc.c index b0b251bb207f3a68d8a8f1969567ac1275f0ce0e..1a6964f1ba6a7147c4808bf48ea75f631545ae18 100644 --- a/drivers/memory/pl353-smc.c +++ b/drivers/memory/pl353-smc.c @@ -416,6 +416,7 @@ static int pl353_smc_probe(struct amba_device *adev, const struct amba_id *id) if (init) init(adev, child); of_platform_device_create(child, NULL, &adev->dev); + of_node_put(child); return 0; diff --git a/drivers/mfd/fsl-imx25-tsadc.c b/drivers/mfd/fsl-imx25-tsadc.c index a016b39fe9b0e54eaf0b3c97811c133cce9bfed4..5f1f6f3a0696addd1e45a9e8ab40b6fc9a8cfb1a 100644 --- a/drivers/mfd/fsl-imx25-tsadc.c +++ b/drivers/mfd/fsl-imx25-tsadc.c @@ -69,7 +69,7 @@ static int mx25_tsadc_setup_irq(struct platform_device *pdev, int irq; irq = platform_get_irq(pdev, 0); - if (irq <= 0) + if (irq < 0) return irq; tsadc->domain = irq_domain_add_simple(np, 2, 0, &mx25_tsadc_domain_ops, @@ -84,6 +84,19 @@ static int mx25_tsadc_setup_irq(struct platform_device *pdev, return 0; } +static int mx25_tsadc_unset_irq(struct platform_device *pdev) +{ + struct mx25_tsadc *tsadc = platform_get_drvdata(pdev); + int irq = platform_get_irq(pdev, 0); + + if (irq >= 0) { + irq_set_chained_handler_and_data(irq, NULL, NULL); + irq_domain_remove(tsadc->domain); + } + + return 0; +} + static void mx25_tsadc_setup_clk(struct platform_device *pdev, struct mx25_tsadc *tsadc) { @@ -171,18 +184,21 @@ static int mx25_tsadc_probe(struct platform_device *pdev) platform_set_drvdata(pdev, tsadc); - return devm_of_platform_populate(dev); + ret = devm_of_platform_populate(dev); + if (ret) + goto err_irq; + + return 0; + +err_irq: + mx25_tsadc_unset_irq(pdev); + + return ret; } static int mx25_tsadc_remove(struct platform_device *pdev) { - struct mx25_tsadc *tsadc = platform_get_drvdata(pdev); - int irq = platform_get_irq(pdev, 0); - - if (irq) { - irq_set_chained_handler_and_data(irq, NULL, NULL); - irq_domain_remove(tsadc->domain); - } + mx25_tsadc_unset_irq(pdev); return 0; } diff --git a/drivers/mfd/intel_soc_pmic_core.c b/drivers/mfd/intel_soc_pmic_core.c index ddd64f9e3341e74018b5a875da49e9f3caf77519..926653e1f6033b00a73a864efaaee9bbc4cfa12f 100644 --- a/drivers/mfd/intel_soc_pmic_core.c +++ b/drivers/mfd/intel_soc_pmic_core.c @@ -95,6 +95,7 @@ static int intel_soc_pmic_i2c_probe(struct i2c_client *i2c, return 0; err_del_irq_chip: + pwm_remove_table(crc_pwm_lookup, ARRAY_SIZE(crc_pwm_lookup)); regmap_del_irq_chip(pmic->irq, pmic->irq_chip_data); return ret; } diff --git a/drivers/mfd/lp8788-irq.c b/drivers/mfd/lp8788-irq.c index 348439a3fbbd45f56b9abb53124ab2b64c0030f2..39006297f3d2703ac852f2ffef33abf1cb13132a 100644 --- a/drivers/mfd/lp8788-irq.c +++ b/drivers/mfd/lp8788-irq.c @@ -175,6 +175,7 @@ int lp8788_irq_init(struct lp8788 *lp, int irq) IRQF_TRIGGER_FALLING | IRQF_ONESHOT, "lp8788-irq", irqd); if (ret) { + irq_domain_remove(lp->irqdm); dev_err(lp->dev, "failed to create a thread for IRQ_N\n"); return ret; } @@ -188,4 +189,6 @@ void lp8788_irq_exit(struct lp8788 *lp) { if (lp->irq) free_irq(lp->irq, lp->irqdm); + if (lp->irqdm) + irq_domain_remove(lp->irqdm); } diff --git a/drivers/mfd/lp8788.c b/drivers/mfd/lp8788.c index 768d556b3fe98090c76e21c1dca06efd3a3ad458..5c3d642c8e3a3e3cfb1d9a6de1b18bcb785e5584 100644 --- a/drivers/mfd/lp8788.c +++ b/drivers/mfd/lp8788.c @@ -195,8 +195,16 @@ static int lp8788_probe(struct i2c_client *cl, const struct i2c_device_id *id) if (ret) return ret; - return mfd_add_devices(lp->dev, -1, lp8788_devs, - ARRAY_SIZE(lp8788_devs), NULL, 0, NULL); + ret = mfd_add_devices(lp->dev, -1, lp8788_devs, + ARRAY_SIZE(lp8788_devs), NULL, 0, NULL); + if (ret) + goto err_exit_irq; + + return 0; + +err_exit_irq: + lp8788_irq_exit(lp); + return ret; } static int lp8788_remove(struct i2c_client *cl) diff --git a/drivers/mfd/lpc_ich.c b/drivers/mfd/lpc_ich.c index 3bbb29a7e7a57c023317ae1b3aa22aa576ce3617..2411b7a2e6f472a73e549daccff96a611e6bc4f8 100644 --- a/drivers/mfd/lpc_ich.c +++ b/drivers/mfd/lpc_ich.c @@ -63,6 +63,8 @@ #define SPIBASE_BYT 0x54 #define SPIBASE_BYT_SZ 512 #define SPIBASE_BYT_EN BIT(1) +#define BYT_BCR 0xfc +#define BYT_BCR_WPD BIT(0) #define SPIBASE_LPT 0x3800 #define SPIBASE_LPT_SZ 512 @@ -1083,12 +1085,57 @@ wdt_done: return ret; } +static bool lpc_ich_byt_set_writeable(void __iomem *base, void *data) +{ + u32 val; + + val = readl(base + BYT_BCR); + if (!(val & BYT_BCR_WPD)) { + val |= BYT_BCR_WPD; + writel(val, base + BYT_BCR); + val = readl(base + BYT_BCR); + } + + return val & BYT_BCR_WPD; +} + +static bool lpc_ich_lpt_set_writeable(void __iomem *base, void *data) +{ + struct pci_dev *pdev = data; + u32 bcr; + + pci_read_config_dword(pdev, BCR, &bcr); + if (!(bcr & BCR_WPD)) { + bcr |= BCR_WPD; + pci_write_config_dword(pdev, BCR, bcr); + pci_read_config_dword(pdev, BCR, &bcr); + } + + return bcr & BCR_WPD; +} + +static bool lpc_ich_bxt_set_writeable(void __iomem *base, void *data) +{ + unsigned int spi = PCI_DEVFN(13, 2); + struct pci_bus *bus = data; + u32 bcr; + + pci_bus_read_config_dword(bus, spi, BCR, &bcr); + if (!(bcr & BCR_WPD)) { + bcr |= BCR_WPD; + pci_bus_write_config_dword(bus, spi, BCR, bcr); + pci_bus_read_config_dword(bus, spi, BCR, &bcr); + } + + return bcr & BCR_WPD; +} + static int lpc_ich_init_spi(struct pci_dev *dev) { struct lpc_ich_priv *priv = pci_get_drvdata(dev); struct resource *res = &intel_spi_res[0]; struct intel_spi_boardinfo *info; - u32 spi_base, rcba, bcr; + u32 spi_base, rcba; info = devm_kzalloc(&dev->dev, sizeof(*info), GFP_KERNEL); if (!info) @@ -1102,6 +1149,8 @@ static int lpc_ich_init_spi(struct pci_dev *dev) if (spi_base & SPIBASE_BYT_EN) { res->start = spi_base & ~(SPIBASE_BYT_SZ - 1); res->end = res->start + SPIBASE_BYT_SZ - 1; + + info->set_writeable = lpc_ich_byt_set_writeable; } break; @@ -1112,8 +1161,8 @@ static int lpc_ich_init_spi(struct pci_dev *dev) res->start = spi_base + SPIBASE_LPT; res->end = res->start + SPIBASE_LPT_SZ - 1; - pci_read_config_dword(dev, BCR, &bcr); - info->writeable = !!(bcr & BCR_WPD); + info->set_writeable = lpc_ich_lpt_set_writeable; + info->data = dev; } break; @@ -1134,8 +1183,8 @@ static int lpc_ich_init_spi(struct pci_dev *dev) res->start = spi_base & 0xfffffff0; res->end = res->start + SPIBASE_APL_SZ - 1; - pci_bus_read_config_dword(bus, spi, BCR, &bcr); - info->writeable = !!(bcr & BCR_WPD); + info->set_writeable = lpc_ich_bxt_set_writeable; + info->data = bus; } pci_bus_write_config_byte(bus, p2sb, 0xe1, 0x1); diff --git a/drivers/mfd/sm501.c b/drivers/mfd/sm501.c index 6d2f4a0a901dc0853c39f872dd1f1c18c7b17603..37ad72d8cde2ae2f2c04819e12cdfbb5c85fdad5 100644 --- a/drivers/mfd/sm501.c +++ b/drivers/mfd/sm501.c @@ -1720,7 +1720,12 @@ static struct platform_driver sm501_plat_driver = { static int __init sm501_base_init(void) { - platform_driver_register(&sm501_plat_driver); + int ret; + + ret = platform_driver_register(&sm501_plat_driver); + if (ret < 0) + return ret; + return pci_register_driver(&sm501_pci_driver); } diff --git a/drivers/misc/ocxl/file.c b/drivers/misc/ocxl/file.c index c742ab02ae1862e4f0d3c8dcf9308e8af2015003..e094809b54ff5ab2814d6d0fc0568c56b3d2d445 100644 --- a/drivers/misc/ocxl/file.c +++ b/drivers/misc/ocxl/file.c @@ -259,6 +259,8 @@ static long afu_ioctl(struct file *file, unsigned int cmd, if (IS_ERR(ev_ctx)) return PTR_ERR(ev_ctx); rc = ocxl_irq_set_handler(ctx, irq_id, irq_handler, irq_free, ev_ctx); + if (rc) + eventfd_ctx_put(ev_ctx); break; case OCXL_IOCTL_GET_METADATA: diff --git a/drivers/misc/vmw_vmci/vmci_queue_pair.c b/drivers/misc/vmw_vmci/vmci_queue_pair.c index a49782dd903cd4ddf88c85439b555fa9035204a1..d4d388f021ccd82b1a1c24669306f9721a4d3e7e 100644 --- a/drivers/misc/vmw_vmci/vmci_queue_pair.c +++ b/drivers/misc/vmw_vmci/vmci_queue_pair.c @@ -852,6 +852,7 @@ static int qp_notify_peer_local(bool attach, struct vmci_handle handle) u32 context_id = vmci_get_context_id(); struct vmci_event_qp ev; + memset(&ev, 0, sizeof(ev)); ev.msg.hdr.dst = vmci_make_handle(context_id, VMCI_EVENT_HANDLER); ev.msg.hdr.src = vmci_make_handle(VMCI_HYPERVISOR_CONTEXT_ID, VMCI_CONTEXT_RESOURCE_ID); @@ -1465,6 +1466,7 @@ static int qp_notify_peer(bool attach, * kernel. */ + memset(&ev, 0, sizeof(ev)); ev.msg.hdr.dst = vmci_make_handle(peer_id, VMCI_EVENT_HANDLER); ev.msg.hdr.src = vmci_make_handle(VMCI_HYPERVISOR_CONTEXT_ID, VMCI_CONTEXT_RESOURCE_ID); diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index dbf4b1159d3b353964c2eea2b0bcbc96b9332991..1d98faa5fe0dd3e336fd286f08a02400c81d0475 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -1077,6 +1077,11 @@ static void mmc_blk_issue_discard_rq(struct mmc_queue *mq, struct request *req) nr = blk_rq_sectors(req); do { + unsigned int erase_arg = card->erase_arg; + + if (mmc_card_broken_sd_discard(card)) + erase_arg = SD_ERASE_ARG; + err = 0; if (card->quirks & MMC_QUIRK_INAND_CMD38) { err = mmc_switch(card, EXT_CSD_CMD_SET_NORMAL, @@ -1087,7 +1092,7 @@ static void mmc_blk_issue_discard_rq(struct mmc_queue *mq, struct request *req) card->ext_csd.generic_cmd6_time); } if (!err) - err = mmc_erase(card, from, nr, card->erase_arg); + err = mmc_erase(card, from, nr, erase_arg); } while (err == -EIO && !mmc_blk_reset(md, card->host, type)); if (err) status = BLK_STS_IOERR; diff --git a/drivers/mmc/core/card.h b/drivers/mmc/core/card.h index 7bd392d55cfa5fa0ba1e1c3f04117354c8e8bd7a..5c6986131faff3719c3b4e40a0df2ebb63b23c28 100644 --- a/drivers/mmc/core/card.h +++ b/drivers/mmc/core/card.h @@ -70,6 +70,7 @@ struct mmc_fixup { #define EXT_CSD_REV_ANY (-1u) #define CID_MANFID_SANDISK 0x2 +#define CID_MANFID_SANDISK_SD 0x3 #define CID_MANFID_ATP 0x9 #define CID_MANFID_TOSHIBA 0x11 #define CID_MANFID_MICRON 0x13 @@ -222,4 +223,9 @@ static inline int mmc_card_broken_hpi(const struct mmc_card *c) return c->quirks & MMC_QUIRK_BROKEN_HPI; } +static inline int mmc_card_broken_sd_discard(const struct mmc_card *c) +{ + return c->quirks & MMC_QUIRK_BROKEN_SD_DISCARD; +} + #endif diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c index 9c09d0254470fc719c4deeaed9fd05db9704da9e..f13eb6f19aedc8a733e875c9324a0264a3cc1849 100644 --- a/drivers/mmc/core/core.c +++ b/drivers/mmc/core/core.c @@ -1131,7 +1131,13 @@ u32 mmc_select_voltage(struct mmc_host *host, u32 ocr) mmc_power_cycle(host, ocr); } else { bit = fls(ocr) - 1; - ocr &= 3 << bit; + /* + * The bit variable represents the highest voltage bit set in + * the OCR register. + * To keep a range of 2 values (e.g. 3.2V/3.3V and 3.3V/3.4V), + * we must shift the mask '3' with (bit - 1). + */ + ocr &= 3 << (bit - 1); if (bit != host->ios.vdd) dev_warn(mmc_dev(host), "exceeding card's volts\n"); } diff --git a/drivers/mmc/core/quirks.h b/drivers/mmc/core/quirks.h index d68e6e513a4f426c1ef5eb543dd6ff62c7444b80..c8c0f50a2076de540b07158995b0167858403b80 100644 --- a/drivers/mmc/core/quirks.h +++ b/drivers/mmc/core/quirks.h @@ -99,6 +99,12 @@ static const struct mmc_fixup __maybe_unused mmc_blk_fixups[] = { MMC_FIXUP("V10016", CID_MANFID_KINGSTON, CID_OEMID_ANY, add_quirk_mmc, MMC_QUIRK_TRIM_BROKEN), + /* + * Some SD cards reports discard support while they don't + */ + MMC_FIXUP(CID_NAME_ANY, CID_MANFID_SANDISK_SD, 0x5344, add_quirk_sd, + MMC_QUIRK_BROKEN_SD_DISCARD), + END_FIXUP }; diff --git a/drivers/mmc/core/sdio_bus.c b/drivers/mmc/core/sdio_bus.c index 3d709029e07ce17679eb4de055d314caecd2bae8..a448535c1265d6385878f21de341330d4d23e402 100644 --- a/drivers/mmc/core/sdio_bus.c +++ b/drivers/mmc/core/sdio_bus.c @@ -292,7 +292,8 @@ static void sdio_release_func(struct device *dev) { struct sdio_func *func = dev_to_sdio_func(dev); - sdio_free_func_cis(func); + if (!(func->card->quirks & MMC_QUIRK_NONSTD_SDIO)) + sdio_free_func_cis(func); kfree(func->info); kfree(func->tmpbuf); diff --git a/drivers/mmc/host/Kconfig b/drivers/mmc/host/Kconfig index 9daef0237382adb4357ccc2c3689b2287047c2b7..c732381819f98a52719f44f58b60563ef5f63d2a 100644 --- a/drivers/mmc/host/Kconfig +++ b/drivers/mmc/host/Kconfig @@ -1080,9 +1080,10 @@ config MMC_SDHCI_OMAP config MMC_SDHCI_AM654 tristate "Support for the SDHCI Controller in TI's AM654 SOCs" - depends on MMC_SDHCI_PLTFM && OF && REGMAP_MMIO + depends on MMC_SDHCI_PLTFM && OF select MMC_SDHCI_IO_ACCESSORS select MMC_CQHCI + select REGMAP_MMIO help This selects the Secure Digital Host Controller Interface (SDHCI) support present in TI's AM654 SOCs. The controller supports diff --git a/drivers/mmc/host/au1xmmc.c b/drivers/mmc/host/au1xmmc.c index bd00515fbaba21eb14957b8d2b2a44b382e2204a..56a3bf51d446d2ca02117dd266bc22e13e79d792 100644 --- a/drivers/mmc/host/au1xmmc.c +++ b/drivers/mmc/host/au1xmmc.c @@ -1097,8 +1097,9 @@ out5: if (host->platdata && host->platdata->cd_setup && !(mmc->caps & MMC_CAP_NEEDS_POLL)) host->platdata->cd_setup(mmc, 0); -out_clk: + clk_disable_unprepare(host->clk); +out_clk: clk_put(host->clk); out_irq: free_irq(host->irq, host); diff --git a/drivers/mmc/host/sdhci-brcmstb.c b/drivers/mmc/host/sdhci-brcmstb.c index f24623aac2dbecbad15920242e2417771d4e187c..4d42b1810acea5bd37df228b7a867b48d72cfe6f 100644 --- a/drivers/mmc/host/sdhci-brcmstb.c +++ b/drivers/mmc/host/sdhci-brcmstb.c @@ -12,28 +12,55 @@ #include #include +#include "sdhci-cqhci.h" #include "sdhci-pltfm.h" #include "cqhci.h" #define SDHCI_VENDOR 0x78 #define SDHCI_VENDOR_ENHANCED_STRB 0x1 +#define SDHCI_VENDOR_GATE_SDCLK_EN 0x2 -#define BRCMSTB_PRIV_FLAGS_NO_64BIT BIT(0) -#define BRCMSTB_PRIV_FLAGS_BROKEN_TIMEOUT BIT(1) +#define BRCMSTB_MATCH_FLAGS_NO_64BIT BIT(0) +#define BRCMSTB_MATCH_FLAGS_BROKEN_TIMEOUT BIT(1) +#define BRCMSTB_MATCH_FLAGS_HAS_CLOCK_GATE BIT(2) + +#define BRCMSTB_PRIV_FLAGS_HAS_CQE BIT(0) +#define BRCMSTB_PRIV_FLAGS_GATE_CLOCK BIT(1) #define SDHCI_ARASAN_CQE_BASE_ADDR 0x200 struct sdhci_brcmstb_priv { void __iomem *cfg_regs; - bool has_cqe; + unsigned int flags; }; struct brcmstb_match_priv { void (*hs400es)(struct mmc_host *mmc, struct mmc_ios *ios); struct sdhci_ops *ops; - unsigned int flags; + const unsigned int flags; }; +static inline void enable_clock_gating(struct sdhci_host *host) +{ + u32 reg; + + reg = sdhci_readl(host, SDHCI_VENDOR); + reg |= SDHCI_VENDOR_GATE_SDCLK_EN; + sdhci_writel(host, reg, SDHCI_VENDOR); +} + +void brcmstb_reset(struct sdhci_host *host, u8 mask) +{ + struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host); + struct sdhci_brcmstb_priv *priv = sdhci_pltfm_priv(pltfm_host); + + sdhci_and_cqhci_reset(host, mask); + + /* Reset will clear this, so re-enable it */ + if (priv->flags & BRCMSTB_PRIV_FLAGS_GATE_CLOCK) + enable_clock_gating(host); +} + static void sdhci_brcmstb_hs400es(struct mmc_host *mmc, struct mmc_ios *ios) { struct sdhci_host *host = mmc_priv(mmc); @@ -129,22 +156,23 @@ static struct sdhci_ops sdhci_brcmstb_ops = { static struct sdhci_ops sdhci_brcmstb_ops_7216 = { .set_clock = sdhci_brcmstb_set_clock, .set_bus_width = sdhci_set_bus_width, - .reset = sdhci_reset, + .reset = brcmstb_reset, .set_uhs_signaling = sdhci_brcmstb_set_uhs_signaling, }; static struct brcmstb_match_priv match_priv_7425 = { - .flags = BRCMSTB_PRIV_FLAGS_NO_64BIT | - BRCMSTB_PRIV_FLAGS_BROKEN_TIMEOUT, + .flags = BRCMSTB_MATCH_FLAGS_NO_64BIT | + BRCMSTB_MATCH_FLAGS_BROKEN_TIMEOUT, .ops = &sdhci_brcmstb_ops, }; static struct brcmstb_match_priv match_priv_7445 = { - .flags = BRCMSTB_PRIV_FLAGS_BROKEN_TIMEOUT, + .flags = BRCMSTB_MATCH_FLAGS_BROKEN_TIMEOUT, .ops = &sdhci_brcmstb_ops, }; static const struct brcmstb_match_priv match_priv_7216 = { + .flags = BRCMSTB_MATCH_FLAGS_HAS_CLOCK_GATE, .hs400es = sdhci_brcmstb_hs400es, .ops = &sdhci_brcmstb_ops_7216, }; @@ -176,7 +204,7 @@ static int sdhci_brcmstb_add_host(struct sdhci_host *host, bool dma64; int ret; - if (!priv->has_cqe) + if ((priv->flags & BRCMSTB_PRIV_FLAGS_HAS_CQE) == 0) return sdhci_add_host(host); dev_dbg(mmc_dev(host->mmc), "CQE is enabled\n"); @@ -225,7 +253,6 @@ static int sdhci_brcmstb_probe(struct platform_device *pdev) struct sdhci_brcmstb_priv *priv; struct sdhci_host *host; struct resource *iomem; - bool has_cqe = false; struct clk *clk; int res; @@ -244,10 +271,6 @@ static int sdhci_brcmstb_probe(struct platform_device *pdev) return res; memset(&brcmstb_pdata, 0, sizeof(brcmstb_pdata)); - if (device_property_read_bool(&pdev->dev, "supports-cqe")) { - has_cqe = true; - match_priv->ops->irq = sdhci_brcmstb_cqhci_irq; - } brcmstb_pdata.ops = match_priv->ops; host = sdhci_pltfm_init(pdev, &brcmstb_pdata, sizeof(struct sdhci_brcmstb_priv)); @@ -258,7 +281,10 @@ static int sdhci_brcmstb_probe(struct platform_device *pdev) pltfm_host = sdhci_priv(host); priv = sdhci_pltfm_priv(pltfm_host); - priv->has_cqe = has_cqe; + if (device_property_read_bool(&pdev->dev, "supports-cqe")) { + priv->flags |= BRCMSTB_PRIV_FLAGS_HAS_CQE; + match_priv->ops->irq = sdhci_brcmstb_cqhci_irq; + } /* Map in the non-standard CFG registers */ iomem = platform_get_resource(pdev, IORESOURCE_MEM, 1); @@ -273,6 +299,14 @@ static int sdhci_brcmstb_probe(struct platform_device *pdev) if (res) goto err; + /* + * Automatic clock gating does not work for SD cards that may + * voltage switch so only enable it for non-removable devices. + */ + if ((match_priv->flags & BRCMSTB_MATCH_FLAGS_HAS_CLOCK_GATE) && + (host->mmc->caps & MMC_CAP_NONREMOVABLE)) + priv->flags |= BRCMSTB_PRIV_FLAGS_GATE_CLOCK; + /* * If the chip has enhanced strobe and it's enabled, add * callback @@ -287,14 +321,14 @@ static int sdhci_brcmstb_probe(struct platform_device *pdev) * properties through mmc_of_parse(). */ host->caps = sdhci_readl(host, SDHCI_CAPABILITIES); - if (match_priv->flags & BRCMSTB_PRIV_FLAGS_NO_64BIT) + if (match_priv->flags & BRCMSTB_MATCH_FLAGS_NO_64BIT) host->caps &= ~SDHCI_CAN_64BIT; host->caps1 = sdhci_readl(host, SDHCI_CAPABILITIES_1); host->caps1 &= ~(SDHCI_SUPPORT_SDR50 | SDHCI_SUPPORT_SDR104 | SDHCI_SUPPORT_DDR50); host->quirks |= SDHCI_QUIRK_MISSING_CAPS; - if (match_priv->flags & BRCMSTB_PRIV_FLAGS_BROKEN_TIMEOUT) + if (match_priv->flags & BRCMSTB_MATCH_FLAGS_BROKEN_TIMEOUT) host->quirks |= SDHCI_QUIRK_BROKEN_TIMEOUT_VAL; res = sdhci_brcmstb_add_host(host, priv); diff --git a/drivers/mmc/host/sdhci-cqhci.h b/drivers/mmc/host/sdhci-cqhci.h new file mode 100644 index 0000000000000000000000000000000000000000..cf8e7ba71bbd7b932191c3e9fca02e4095a12676 --- /dev/null +++ b/drivers/mmc/host/sdhci-cqhci.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright 2022 The Chromium OS Authors + * + * Support that applies to the combination of SDHCI and CQHCI, while not + * expressing a dependency between the two modules. + */ + +#ifndef __MMC_HOST_SDHCI_CQHCI_H__ +#define __MMC_HOST_SDHCI_CQHCI_H__ + +#include "cqhci.h" +#include "sdhci.h" + +static inline void sdhci_and_cqhci_reset(struct sdhci_host *host, u8 mask) +{ + if ((host->mmc->caps2 & MMC_CAP2_CQE) && (mask & SDHCI_RESET_ALL) && + host->mmc->cqe_private) + cqhci_deactivate(host->mmc); + + sdhci_reset(host, mask); +} + +#endif /* __MMC_HOST_SDHCI_CQHCI_H__ */ diff --git a/drivers/mmc/host/sdhci-esdhc-imx.c b/drivers/mmc/host/sdhci-esdhc-imx.c index a4bd85b200a3edf710da0138dd145d4ae5da5223..1f1bdd34dd5543d45f48ccb2dc3187b390c9dbff 100644 --- a/drivers/mmc/host/sdhci-esdhc-imx.c +++ b/drivers/mmc/host/sdhci-esdhc-imx.c @@ -26,6 +26,7 @@ #include #include #include +#include "sdhci-cqhci.h" #include "sdhci-pltfm.h" #include "sdhci-esdhc.h" #include "cqhci.h" @@ -294,22 +295,6 @@ struct pltfm_imx_data { struct pm_qos_request pm_qos_req; }; -static const struct platform_device_id imx_esdhc_devtype[] = { - { - .name = "sdhci-esdhc-imx25", - .driver_data = (kernel_ulong_t) &esdhc_imx25_data, - }, { - .name = "sdhci-esdhc-imx35", - .driver_data = (kernel_ulong_t) &esdhc_imx35_data, - }, { - .name = "sdhci-esdhc-imx51", - .driver_data = (kernel_ulong_t) &esdhc_imx51_data, - }, { - /* sentinel */ - } -}; -MODULE_DEVICE_TABLE(platform, imx_esdhc_devtype); - static const struct of_device_id imx_esdhc_dt_ids[] = { { .compatible = "fsl,imx25-esdhc", .data = &esdhc_imx25_data, }, { .compatible = "fsl,imx35-esdhc", .data = &esdhc_imx35_data, }, @@ -1243,7 +1228,7 @@ static void esdhc_set_uhs_signaling(struct sdhci_host *host, unsigned timing) static void esdhc_reset(struct sdhci_host *host, u8 mask) { - sdhci_reset(host, mask); + sdhci_and_cqhci_reset(host, mask); sdhci_writel(host, host->ier, SDHCI_INT_ENABLE); sdhci_writel(host, host->ier, SDHCI_SIGNAL_ENABLE); @@ -1545,72 +1530,6 @@ sdhci_esdhc_imx_probe_dt(struct platform_device *pdev, } #endif -static int sdhci_esdhc_imx_probe_nondt(struct platform_device *pdev, - struct sdhci_host *host, - struct pltfm_imx_data *imx_data) -{ - struct esdhc_platform_data *boarddata = &imx_data->boarddata; - int err; - - if (!host->mmc->parent->platform_data) { - dev_err(mmc_dev(host->mmc), "no board data!\n"); - return -EINVAL; - } - - imx_data->boarddata = *((struct esdhc_platform_data *) - host->mmc->parent->platform_data); - /* write_protect */ - if (boarddata->wp_type == ESDHC_WP_GPIO) { - host->mmc->caps2 |= MMC_CAP2_RO_ACTIVE_HIGH; - - err = mmc_gpiod_request_ro(host->mmc, "wp", 0, 0); - if (err) { - dev_err(mmc_dev(host->mmc), - "failed to request write-protect gpio!\n"); - return err; - } - } - - /* card_detect */ - switch (boarddata->cd_type) { - case ESDHC_CD_GPIO: - err = mmc_gpiod_request_cd(host->mmc, "cd", 0, false, 0); - if (err) { - dev_err(mmc_dev(host->mmc), - "failed to request card-detect gpio!\n"); - return err; - } - fallthrough; - - case ESDHC_CD_CONTROLLER: - /* we have a working card_detect back */ - host->quirks &= ~SDHCI_QUIRK_BROKEN_CARD_DETECTION; - break; - - case ESDHC_CD_PERMANENT: - host->mmc->caps |= MMC_CAP_NONREMOVABLE; - break; - - case ESDHC_CD_NONE: - break; - } - - switch (boarddata->max_bus_width) { - case 8: - host->mmc->caps |= MMC_CAP_8_BIT_DATA | MMC_CAP_4_BIT_DATA; - break; - case 4: - host->mmc->caps |= MMC_CAP_4_BIT_DATA; - break; - case 1: - default: - host->quirks |= SDHCI_QUIRK_FORCE_1_BIT_DATA; - break; - } - - return 0; -} - static int sdhci_esdhc_imx_probe(struct platform_device *pdev) { const struct of_device_id *of_id = @@ -1630,8 +1549,7 @@ static int sdhci_esdhc_imx_probe(struct platform_device *pdev) imx_data = sdhci_pltfm_priv(pltfm_host); - imx_data->socdata = of_id ? of_id->data : (struct esdhc_soc_data *) - pdev->id_entry->driver_data; + imx_data->socdata = of_id->data; if (imx_data->socdata->flags & ESDHC_FLAG_PMQOS) cpu_latency_qos_add_request(&imx_data->pm_qos_req, 0); @@ -1692,6 +1610,10 @@ static int sdhci_esdhc_imx_probe(struct platform_device *pdev) host->mmc_host_ops.execute_tuning = usdhc_execute_tuning; } + err = sdhci_esdhc_imx_probe_dt(pdev, host, imx_data); + if (err) + goto disable_ahb_clk; + if (imx_data->socdata->flags & ESDHC_FLAG_MAN_TUNING) sdhci_esdhc_ops.platform_execute_tuning = esdhc_executing_tuning; @@ -1699,13 +1621,15 @@ static int sdhci_esdhc_imx_probe(struct platform_device *pdev) if (imx_data->socdata->flags & ESDHC_FLAG_ERR004536) host->quirks |= SDHCI_QUIRK_BROKEN_ADMA; - if (imx_data->socdata->flags & ESDHC_FLAG_HS400) + if (host->mmc->caps & MMC_CAP_8_BIT_DATA && + imx_data->socdata->flags & ESDHC_FLAG_HS400) host->quirks2 |= SDHCI_QUIRK2_CAPS_BIT63_FOR_HS400; if (imx_data->socdata->flags & ESDHC_FLAG_BROKEN_AUTO_CMD23) host->quirks2 |= SDHCI_QUIRK2_ACMD23_BROKEN; - if (imx_data->socdata->flags & ESDHC_FLAG_HS400_ES) { + if (host->mmc->caps & MMC_CAP_8_BIT_DATA && + imx_data->socdata->flags & ESDHC_FLAG_HS400_ES) { host->mmc->caps2 |= MMC_CAP2_HS400_ES; host->mmc_host_ops.hs400_enhanced_strobe = esdhc_hs400_enhanced_strobe; @@ -1727,13 +1651,6 @@ static int sdhci_esdhc_imx_probe(struct platform_device *pdev) goto disable_ahb_clk; } - if (of_id) - err = sdhci_esdhc_imx_probe_dt(pdev, host, imx_data); - else - err = sdhci_esdhc_imx_probe_nondt(pdev, host, imx_data); - if (err) - goto disable_ahb_clk; - sdhci_esdhc_imx_hwinit(host); err = sdhci_add_host(host); @@ -1944,7 +1861,6 @@ static struct platform_driver sdhci_esdhc_imx_driver = { .of_match_table = imx_esdhc_dt_ids, .pm = &sdhci_esdhc_pmops, }, - .id_table = imx_esdhc_devtype, .probe = sdhci_esdhc_imx_probe, .remove = sdhci_esdhc_imx_remove, }; diff --git a/drivers/mmc/host/sdhci-msm.c b/drivers/mmc/host/sdhci-msm.c index b7d9a39f6bb992ee1336b2fa67a78f3aef17bee9..559795530c7048552c288efc0094c16878457b68 100644 --- a/drivers/mmc/host/sdhci-msm.c +++ b/drivers/mmc/host/sdhci-msm.c @@ -2442,6 +2442,7 @@ static const struct sdhci_msm_variant_info sm8250_sdhci_var = { static const struct of_device_id sdhci_msm_dt_match[] = { {.compatible = "qcom,sdhci-msm-v4", .data = &sdhci_msm_mci_var}, {.compatible = "qcom,sdhci-msm-v5", .data = &sdhci_msm_v5_var}, + {.compatible = "qcom,sdm670-sdhci", .data = &sdm845_sdhci_var}, {.compatible = "qcom,sdm845-sdhci", .data = &sdm845_sdhci_var}, {.compatible = "qcom,sm8250-sdhci", .data = &sm8250_sdhci_var}, {.compatible = "qcom,sc7180-sdhci", .data = &sdm845_sdhci_var}, diff --git a/drivers/mmc/host/sdhci-of-arasan.c b/drivers/mmc/host/sdhci-of-arasan.c index fc38db64a6b48ae4954cb47fe4e20c99b51fcc14..9da49dc152489a1c40e363ff81b32e8a20066efb 100644 --- a/drivers/mmc/host/sdhci-of-arasan.c +++ b/drivers/mmc/host/sdhci-of-arasan.c @@ -25,6 +25,7 @@ #include #include "cqhci.h" +#include "sdhci-cqhci.h" #include "sdhci-pltfm.h" #define SDHCI_ARASAN_VENDOR_REGISTER 0x78 @@ -359,7 +360,7 @@ static void sdhci_arasan_reset(struct sdhci_host *host, u8 mask) struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host); struct sdhci_arasan_data *sdhci_arasan = sdhci_pltfm_priv(pltfm_host); - sdhci_reset(host, mask); + sdhci_and_cqhci_reset(host, mask); if (sdhci_arasan->quirks & SDHCI_ARASAN_QUIRK_FORCE_CDTEST) { ctrl = sdhci_readb(host, SDHCI_HOST_CONTROL); diff --git a/drivers/mmc/host/sdhci-pci-core.c b/drivers/mmc/host/sdhci-pci-core.c index a78b060ce847158505ae2cc2c4c3151feee69478..8b02fe3916d127dea270e74ea4a8935f7934ca2d 100644 --- a/drivers/mmc/host/sdhci-pci-core.c +++ b/drivers/mmc/host/sdhci-pci-core.c @@ -967,6 +967,12 @@ static bool glk_broken_cqhci(struct sdhci_pci_slot *slot) dmi_match(DMI_SYS_VENDOR, "IRBIS")); } +static bool jsl_broken_hs400es(struct sdhci_pci_slot *slot) +{ + return slot->chip->pdev->device == PCI_DEVICE_ID_INTEL_JSL_EMMC && + dmi_match(DMI_BIOS_VENDOR, "ASUSTeK COMPUTER INC."); +} + static int glk_emmc_probe_slot(struct sdhci_pci_slot *slot) { int ret = byt_emmc_probe_slot(slot); @@ -975,9 +981,11 @@ static int glk_emmc_probe_slot(struct sdhci_pci_slot *slot) slot->host->mmc->caps2 |= MMC_CAP2_CQE; if (slot->chip->pdev->device != PCI_DEVICE_ID_INTEL_GLK_EMMC) { - slot->host->mmc->caps2 |= MMC_CAP2_HS400_ES, - slot->host->mmc_host_ops.hs400_enhanced_strobe = - intel_hs400_enhanced_strobe; + if (!jsl_broken_hs400es(slot)) { + slot->host->mmc->caps2 |= MMC_CAP2_HS400_ES; + slot->host->mmc_host_ops.hs400_enhanced_strobe = + intel_hs400_enhanced_strobe; + } slot->host->mmc->caps2 |= MMC_CAP2_CQE_DCMD; } @@ -1791,6 +1799,8 @@ static int amd_probe(struct sdhci_pci_chip *chip) } } + pci_dev_put(smbus_dev); + if (gen == AMD_CHIPSET_BEFORE_ML || gen == AMD_CHIPSET_CZ) chip->quirks2 |= SDHCI_QUIRK2_CLEAR_TRANSFERMODE_REG_BEFORE_CMD; diff --git a/drivers/mmc/host/sdhci-pci-o2micro.c b/drivers/mmc/host/sdhci-pci-o2micro.c index 8c357e3b78d7cc01d34ea65e92705da4f4106443..72234790a310b673008d1446756648f7f850c006 100644 --- a/drivers/mmc/host/sdhci-pci-o2micro.c +++ b/drivers/mmc/host/sdhci-pci-o2micro.c @@ -31,6 +31,7 @@ #define O2_SD_CAPS 0xE0 #define O2_SD_ADMA1 0xE2 #define O2_SD_ADMA2 0xE7 +#define O2_SD_MISC_CTRL2 0xF0 #define O2_SD_INF_MOD 0xF1 #define O2_SD_MISC_CTRL4 0xFC #define O2_SD_MISC_CTRL 0x1C0 @@ -822,6 +823,12 @@ static int sdhci_pci_o2_probe(struct sdhci_pci_chip *chip) /* Set Tuning Windows to 5 */ pci_write_config_byte(chip->pdev, O2_SD_TUNING_CTRL, 0x55); + //Adjust 1st and 2nd CD debounce time + pci_read_config_dword(chip->pdev, O2_SD_MISC_CTRL2, &scratch_32); + scratch_32 &= 0xFFE7FFFF; + scratch_32 |= 0x00180000; + pci_write_config_dword(chip->pdev, O2_SD_MISC_CTRL2, scratch_32); + pci_write_config_dword(chip->pdev, O2_SD_DETECT_SETTING, 1); /* Lock WP */ ret = pci_read_config_byte(chip->pdev, O2_SD_LOCK_WP, &scratch); diff --git a/drivers/mmc/host/sdhci-sprd.c b/drivers/mmc/host/sdhci-sprd.c index 9cd8862e6cbd04f32f39c6f7fda680f9b75e6702..8575f4537e57b26e713a2a63a6a607f397d3072d 100644 --- a/drivers/mmc/host/sdhci-sprd.c +++ b/drivers/mmc/host/sdhci-sprd.c @@ -296,7 +296,7 @@ static unsigned int sdhci_sprd_get_max_clock(struct sdhci_host *host) static unsigned int sdhci_sprd_get_min_clock(struct sdhci_host *host) { - return 400000; + return 100000; } static void sdhci_sprd_set_uhs_signaling(struct sdhci_host *host, diff --git a/drivers/mmc/host/sdhci-tegra.c b/drivers/mmc/host/sdhci-tegra.c index d50b691f6c44e5f5053c031056be527572b14ff3..d8fd2b5efd3877dabf6eb9147e6f2bb6c2fb2e6c 100644 --- a/drivers/mmc/host/sdhci-tegra.c +++ b/drivers/mmc/host/sdhci-tegra.c @@ -24,6 +24,7 @@ #include #include +#include "sdhci-cqhci.h" #include "sdhci-pltfm.h" #include "cqhci.h" @@ -361,7 +362,7 @@ static void tegra_sdhci_reset(struct sdhci_host *host, u8 mask) const struct sdhci_tegra_soc_data *soc_data = tegra_host->soc_data; u32 misc_ctrl, clk_ctrl, pad_ctrl; - sdhci_reset(host, mask); + sdhci_and_cqhci_reset(host, mask); if (!(mask & SDHCI_RESET_ALL)) return; @@ -760,7 +761,7 @@ static void tegra_sdhci_set_clock(struct sdhci_host *host, unsigned int clock) */ host_clk = tegra_host->ddr_signaling ? clock * 2 : clock; clk_set_rate(pltfm_host->clk, host_clk); - tegra_host->curr_clk_rate = host_clk; + tegra_host->curr_clk_rate = clk_get_rate(pltfm_host->clk); if (tegra_host->ddr_signaling) host->max_clk = host_clk; else diff --git a/drivers/mmc/host/sdhci_am654.c b/drivers/mmc/host/sdhci_am654.c index 7cab9d831afb31decf22845c2874aa72a0aa6458..24cd6d3dc647785935df9d0dbb82187ecffa0e93 100644 --- a/drivers/mmc/host/sdhci_am654.c +++ b/drivers/mmc/host/sdhci_am654.c @@ -15,6 +15,7 @@ #include #include "cqhci.h" +#include "sdhci-cqhci.h" #include "sdhci-pltfm.h" /* CTL_CFG Registers */ @@ -378,7 +379,7 @@ static void sdhci_am654_reset(struct sdhci_host *host, u8 mask) struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host); struct sdhci_am654_data *sdhci_am654 = sdhci_pltfm_priv(pltfm_host); - sdhci_reset(host, mask); + sdhci_and_cqhci_reset(host, mask); if (sdhci_am654->quirks & SDHCI_AM654_QUIRK_FORCE_CDTEST) { ctrl = sdhci_readb(host, SDHCI_HOST_CONTROL); @@ -464,7 +465,7 @@ static struct sdhci_ops sdhci_am654_ops = { .set_clock = sdhci_am654_set_clock, .write_b = sdhci_am654_write_b, .irq = sdhci_am654_cqhci_irq, - .reset = sdhci_reset, + .reset = sdhci_and_cqhci_reset, }; static const struct sdhci_pltfm_data sdhci_am654_pdata = { @@ -494,7 +495,7 @@ static struct sdhci_ops sdhci_j721e_8bit_ops = { .set_clock = sdhci_am654_set_clock, .write_b = sdhci_am654_write_b, .irq = sdhci_am654_cqhci_irq, - .reset = sdhci_reset, + .reset = sdhci_and_cqhci_reset, }; static const struct sdhci_pltfm_data sdhci_j721e_8bit_pdata = { diff --git a/drivers/mmc/host/wmt-sdmmc.c b/drivers/mmc/host/wmt-sdmmc.c index cf10949fb0acc929c5ecbe487c0ac23252ffa6cd..8df722ec57edc94e0ae8a45c49eacea36cbfdd8f 100644 --- a/drivers/mmc/host/wmt-sdmmc.c +++ b/drivers/mmc/host/wmt-sdmmc.c @@ -849,7 +849,7 @@ static int wmt_mci_probe(struct platform_device *pdev) if (IS_ERR(priv->clk_sdmmc)) { dev_err(&pdev->dev, "Error getting clock\n"); ret = PTR_ERR(priv->clk_sdmmc); - goto fail5; + goto fail5_and_a_half; } ret = clk_prepare_enable(priv->clk_sdmmc); @@ -866,6 +866,9 @@ static int wmt_mci_probe(struct platform_device *pdev) return 0; fail6: clk_put(priv->clk_sdmmc); +fail5_and_a_half: + dma_free_coherent(&pdev->dev, mmc->max_blk_count * 16, + priv->dma_desc_buffer, priv->dma_desc_device_addr); fail5: free_irq(dma_irq, priv); fail4: diff --git a/drivers/mtd/devices/docg3.c b/drivers/mtd/devices/docg3.c index a030792115bc2e9bfd14ac48ab76b76e997b3de7..fa42473d04c1bf875c1535e24164e4fbcf7547f6 100644 --- a/drivers/mtd/devices/docg3.c +++ b/drivers/mtd/devices/docg3.c @@ -1975,9 +1975,14 @@ static int __init docg3_probe(struct platform_device *pdev) dev_err(dev, "No I/O memory resource defined\n"); return ret; } - base = devm_ioremap(dev, ress->start, DOC_IOSPACE_SIZE); ret = -ENOMEM; + base = devm_ioremap(dev, ress->start, DOC_IOSPACE_SIZE); + if (!base) { + dev_err(dev, "devm_ioremap dev failed\n"); + return ret; + } + cascade = devm_kcalloc(dev, DOC_MAX_NBFLOORS, sizeof(*cascade), GFP_KERNEL); if (!cascade) diff --git a/drivers/mtd/nand/raw/atmel/nand-controller.c b/drivers/mtd/nand/raw/atmel/nand-controller.c index 2228c34f3deabd7cf4103f13850f9ad0f0937db4..0d84f8156d8e49d547e998be6b8b8cfcdf1adc6e 100644 --- a/drivers/mtd/nand/raw/atmel/nand-controller.c +++ b/drivers/mtd/nand/raw/atmel/nand-controller.c @@ -405,6 +405,7 @@ static int atmel_nand_dma_transfer(struct atmel_nand_controller *nc, dma_async_issue_pending(nc->dmac); wait_for_completion(&finished); + dma_unmap_single(nc->dev, buf_dma, len, dir); return 0; diff --git a/drivers/mtd/nand/raw/fsl_elbc_nand.c b/drivers/mtd/nand/raw/fsl_elbc_nand.c index b2af7f81fdf8f1360f5d8686aba707bd4c104db7..c174b6dc3c6bae069ba9ef7a481d4d072415a9a2 100644 --- a/drivers/mtd/nand/raw/fsl_elbc_nand.c +++ b/drivers/mtd/nand/raw/fsl_elbc_nand.c @@ -727,36 +727,40 @@ static int fsl_elbc_attach_chip(struct nand_chip *chip) struct fsl_lbc_regs __iomem *lbc = ctrl->regs; unsigned int al; - switch (chip->ecc.engine_type) { /* * if ECC was not chosen in DT, decide whether to use HW or SW ECC from * CS Base Register */ - case NAND_ECC_ENGINE_TYPE_NONE: + if (chip->ecc.engine_type == NAND_ECC_ENGINE_TYPE_INVALID) { /* If CS Base Register selects full hardware ECC then use it */ if ((in_be32(&lbc->bank[priv->bank].br) & BR_DECC) == BR_DECC_CHK_GEN) { - chip->ecc.read_page = fsl_elbc_read_page; - chip->ecc.write_page = fsl_elbc_write_page; - chip->ecc.write_subpage = fsl_elbc_write_subpage; - chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST; - mtd_set_ooblayout(mtd, &fsl_elbc_ooblayout_ops); - chip->ecc.size = 512; - chip->ecc.bytes = 3; - chip->ecc.strength = 1; } else { /* otherwise fall back to default software ECC */ chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; chip->ecc.algo = NAND_ECC_ALGO_HAMMING; } + } + + switch (chip->ecc.engine_type) { + /* if HW ECC was chosen, setup ecc and oob layout */ + case NAND_ECC_ENGINE_TYPE_ON_HOST: + chip->ecc.read_page = fsl_elbc_read_page; + chip->ecc.write_page = fsl_elbc_write_page; + chip->ecc.write_subpage = fsl_elbc_write_subpage; + mtd_set_ooblayout(mtd, &fsl_elbc_ooblayout_ops); + chip->ecc.size = 512; + chip->ecc.bytes = 3; + chip->ecc.strength = 1; break; - /* if SW ECC was chosen in DT, we do not need to set anything here */ + /* if none or SW ECC was chosen, we do not need to set anything here */ + case NAND_ECC_ENGINE_TYPE_NONE: case NAND_ECC_ENGINE_TYPE_SOFT: + case NAND_ECC_ENGINE_TYPE_ON_DIE: break; - /* should we also implement *_ECC_ENGINE_CONTROLLER to do as above? */ default: return -EINVAL; } diff --git a/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c b/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c index 92e8ca56f56653761a502b383fe8a8a86150a952..200d3ab343b006f820b6da8a5de8435d5f8cbe18 100644 --- a/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c +++ b/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c @@ -653,8 +653,9 @@ static void gpmi_nfc_compute_timings(struct gpmi_nand_data *this, unsigned int tRP_ps; bool use_half_period; int sample_delay_ps, sample_delay_factor; - u16 busy_timeout_cycles; + unsigned int busy_timeout_cycles; u8 wrn_dly_sel; + u64 busy_timeout_ps; if (sdr->tRC_min >= 30000) { /* ONFI non-EDO modes [0-3] */ @@ -678,7 +679,8 @@ static void gpmi_nfc_compute_timings(struct gpmi_nand_data *this, addr_setup_cycles = TO_CYCLES(sdr->tALS_min, period_ps); data_setup_cycles = TO_CYCLES(sdr->tDS_min, period_ps); data_hold_cycles = TO_CYCLES(sdr->tDH_min, period_ps); - busy_timeout_cycles = TO_CYCLES(sdr->tWB_max + sdr->tR_max, period_ps); + busy_timeout_ps = max(sdr->tBERS_max, sdr->tPROG_max); + busy_timeout_cycles = TO_CYCLES(busy_timeout_ps, period_ps); hw->timing0 = BF_GPMI_TIMING0_ADDRESS_SETUP(addr_setup_cycles) | BF_GPMI_TIMING0_DATA_HOLD(data_hold_cycles) | diff --git a/drivers/mtd/nand/raw/marvell_nand.c b/drivers/mtd/nand/raw/marvell_nand.c index d00c916f133bd59a00c674b3aa199b1e8fad761b..dce35f81e0a55d0dcb313e035ffa854e6bb1c3b0 100644 --- a/drivers/mtd/nand/raw/marvell_nand.c +++ b/drivers/mtd/nand/raw/marvell_nand.c @@ -2672,7 +2672,7 @@ static int marvell_nand_chip_init(struct device *dev, struct marvell_nfc *nfc, chip->controller = &nfc->controller; nand_set_flash_node(chip, np); - if (!of_property_read_bool(np, "marvell,nand-keep-config")) + if (of_property_read_bool(np, "marvell,nand-keep-config")) chip->options |= NAND_KEEP_TIMINGS; mtd = nand_to_mtd(chip); diff --git a/drivers/mtd/nand/raw/meson_nand.c b/drivers/mtd/nand/raw/meson_nand.c index 327a2257ec26da52ed2ec92e3f47dab247cf0462..38f490088d764b1d0ed0c2e0293f586717f93898 100644 --- a/drivers/mtd/nand/raw/meson_nand.c +++ b/drivers/mtd/nand/raw/meson_nand.c @@ -454,7 +454,7 @@ static int meson_nfc_ecc_correct(struct nand_chip *nand, u32 *bitflips, if (ECC_ERR_CNT(*info) != ECC_UNCORRECTABLE) { mtd->ecc_stats.corrected += ECC_ERR_CNT(*info); *bitflips = max_t(u32, *bitflips, ECC_ERR_CNT(*info)); - *correct_bitmap |= 1 >> i; + *correct_bitmap |= BIT_ULL(i); continue; } if ((nand->options & NAND_NEED_SCRAMBLING) && @@ -800,7 +800,7 @@ static int meson_nfc_read_page_hwecc(struct nand_chip *nand, u8 *buf, u8 *data = buf + i * ecc->size; u8 *oob = nand->oob_poi + i * (ecc->bytes + 2); - if (correct_bitmap & (1 << i)) + if (correct_bitmap & BIT_ULL(i)) continue; ret = nand_check_erased_ecc_chunk(data, ecc->size, oob, ecc->bytes + 2, diff --git a/drivers/mtd/parsers/bcm47xxpart.c b/drivers/mtd/parsers/bcm47xxpart.c index 6012a10f10c83aef7aa26a1542f83559ed0e3833..13daf9bffd081912a1f6036833e1a4d87a0662de 100644 --- a/drivers/mtd/parsers/bcm47xxpart.c +++ b/drivers/mtd/parsers/bcm47xxpart.c @@ -233,11 +233,11 @@ static int bcm47xxpart_parse(struct mtd_info *master, } /* Read middle of the block */ - err = mtd_read(master, offset + 0x8000, 0x4, &bytes_read, + err = mtd_read(master, offset + (blocksize / 2), 0x4, &bytes_read, (uint8_t *)buf); if (err && !mtd_is_bitflip(err)) { pr_err("mtd_read error while parsing (offset: 0x%X): %d\n", - offset, err); + offset + (blocksize / 2), err); continue; } diff --git a/drivers/mtd/spi-nor/controllers/intel-spi-pci.c b/drivers/mtd/spi-nor/controllers/intel-spi-pci.c index 555fe55d14aee8731363a97bc6023a6a53712146..8a3c1f3c2d2e8e9648f076df757d708cc35eed31 100644 --- a/drivers/mtd/spi-nor/controllers/intel-spi-pci.c +++ b/drivers/mtd/spi-nor/controllers/intel-spi-pci.c @@ -16,12 +16,30 @@ #define BCR 0xdc #define BCR_WPD BIT(0) +static bool intel_spi_pci_set_writeable(void __iomem *base, void *data) +{ + struct pci_dev *pdev = data; + u32 bcr; + + /* Try to make the chip read/write */ + pci_read_config_dword(pdev, BCR, &bcr); + if (!(bcr & BCR_WPD)) { + bcr |= BCR_WPD; + pci_write_config_dword(pdev, BCR, bcr); + pci_read_config_dword(pdev, BCR, &bcr); + } + + return bcr & BCR_WPD; +} + static const struct intel_spi_boardinfo bxt_info = { .type = INTEL_SPI_BXT, + .set_writeable = intel_spi_pci_set_writeable, }; static const struct intel_spi_boardinfo cnl_info = { .type = INTEL_SPI_CNL, + .set_writeable = intel_spi_pci_set_writeable, }; static int intel_spi_pci_probe(struct pci_dev *pdev, @@ -29,7 +47,6 @@ static int intel_spi_pci_probe(struct pci_dev *pdev, { struct intel_spi_boardinfo *info; struct intel_spi *ispi; - u32 bcr; int ret; ret = pcim_enable_device(pdev); @@ -41,15 +58,7 @@ static int intel_spi_pci_probe(struct pci_dev *pdev, if (!info) return -ENOMEM; - /* Try to make the chip read/write */ - pci_read_config_dword(pdev, BCR, &bcr); - if (!(bcr & BCR_WPD)) { - bcr |= BCR_WPD; - pci_write_config_dword(pdev, BCR, bcr); - pci_read_config_dword(pdev, BCR, &bcr); - } - info->writeable = !!(bcr & BCR_WPD); - + info->data = pdev; ispi = intel_spi_probe(&pdev->dev, &pdev->resource[0], info); if (IS_ERR(ispi)) return PTR_ERR(ispi); diff --git a/drivers/mtd/spi-nor/controllers/intel-spi.c b/drivers/mtd/spi-nor/controllers/intel-spi.c index b54a56a68100e2ac7e298b978ddf60c6fc314045..6c802db6b4af0664830e66bd25514970d7fa8d6d 100644 --- a/drivers/mtd/spi-nor/controllers/intel-spi.c +++ b/drivers/mtd/spi-nor/controllers/intel-spi.c @@ -53,17 +53,17 @@ #define FRACC 0x50 #define FREG(n) (0x54 + ((n) * 4)) -#define FREG_BASE_MASK 0x3fff +#define FREG_BASE_MASK GENMASK(14, 0) #define FREG_LIMIT_SHIFT 16 -#define FREG_LIMIT_MASK (0x03fff << FREG_LIMIT_SHIFT) +#define FREG_LIMIT_MASK GENMASK(30, 16) /* Offset is from @ispi->pregs */ #define PR(n) ((n) * 4) #define PR_WPE BIT(31) #define PR_LIMIT_SHIFT 16 -#define PR_LIMIT_MASK (0x3fff << PR_LIMIT_SHIFT) +#define PR_LIMIT_MASK GENMASK(30, 16) #define PR_RPE BIT(15) -#define PR_BASE_MASK 0x3fff +#define PR_BASE_MASK GENMASK(14, 0) /* Offsets are from @ispi->sregs */ #define SSFSTS_CTL 0x00 @@ -117,7 +117,7 @@ #define ERASE_OPCODE_SHIFT 8 #define ERASE_OPCODE_MASK (0xff << ERASE_OPCODE_SHIFT) #define ERASE_64K_OPCODE_SHIFT 16 -#define ERASE_64K_OPCODE_MASK (0xff << ERASE_OPCODE_SHIFT) +#define ERASE_64K_OPCODE_MASK (0xff << ERASE_64K_OPCODE_SHIFT) #define INTEL_SPI_TIMEOUT 5000 /* ms */ #define INTEL_SPI_FIFO_SZ 64 @@ -132,7 +132,6 @@ * @sregs: Start of software sequencer registers * @nregions: Maximum number of regions * @pr_num: Maximum number of protected range registers - * @writeable: Is the chip writeable * @locked: Is SPI setting locked * @swseq_reg: Use SW sequencer in register reads/writes * @swseq_erase: Use SW sequencer in erase operation @@ -150,7 +149,6 @@ struct intel_spi { void __iomem *sregs; size_t nregions; size_t pr_num; - bool writeable; bool locked; bool swseq_reg; bool swseq_erase; @@ -305,6 +303,14 @@ static int intel_spi_wait_sw_busy(struct intel_spi *ispi) INTEL_SPI_TIMEOUT * 1000); } +static bool intel_spi_set_writeable(struct intel_spi *ispi) +{ + if (!ispi->info->set_writeable) + return false; + + return ispi->info->set_writeable(ispi->base, ispi->info->data); +} + static int intel_spi_init(struct intel_spi *ispi) { u32 opmenu0, opmenu1, lvscc, uvscc, val; @@ -317,19 +323,6 @@ static int intel_spi_init(struct intel_spi *ispi) ispi->nregions = BYT_FREG_NUM; ispi->pr_num = BYT_PR_NUM; ispi->swseq_reg = true; - - if (writeable) { - /* Disable write protection */ - val = readl(ispi->base + BYT_BCR); - if (!(val & BYT_BCR_WPD)) { - val |= BYT_BCR_WPD; - writel(val, ispi->base + BYT_BCR); - val = readl(ispi->base + BYT_BCR); - } - - ispi->writeable = !!(val & BYT_BCR_WPD); - } - break; case INTEL_SPI_LPT: @@ -359,6 +352,12 @@ static int intel_spi_init(struct intel_spi *ispi) return -EINVAL; } + /* Try to disable write protection if user asked to do so */ + if (writeable && !intel_spi_set_writeable(ispi)) { + dev_warn(ispi->dev, "can't disable chip write protection\n"); + writeable = false; + } + /* Disable #SMI generation from HW sequencer */ val = readl(ispi->base + HSFSTS_CTL); val &= ~HSFSTS_CTL_FSMIE; @@ -885,9 +884,12 @@ static void intel_spi_fill_partition(struct intel_spi *ispi, /* * If any of the regions have protection bits set, make the * whole partition read-only to be on the safe side. + * + * Also if the user did not ask the chip to be writeable + * mask the bit too. */ - if (intel_spi_is_protected(ispi, base, limit)) - ispi->writeable = false; + if (!writeable || intel_spi_is_protected(ispi, base, limit)) + part->mask_flags |= MTD_WRITEABLE; end = (limit << 12) + 4096; if (end > part->size) @@ -928,7 +930,6 @@ struct intel_spi *intel_spi_probe(struct device *dev, ispi->dev = dev; ispi->info = info; - ispi->writeable = info->writeable; ret = intel_spi_init(ispi); if (ret) @@ -946,10 +947,6 @@ struct intel_spi *intel_spi_probe(struct device *dev, intel_spi_fill_partition(ispi, &part); - /* Prevent writes if not explicitly enabled */ - if (!ispi->writeable || !writeable) - ispi->nor.mtd.flags &= ~MTD_WRITEABLE; - ret = mtd_device_register(&ispi->nor.mtd, &part, 1); if (ret) return ERR_PTR(ret); diff --git a/drivers/net/arcnet/arc-rimi.c b/drivers/net/arcnet/arc-rimi.c index 98df38fe553ced05b714767d4ad628dcba45819a..12d085405bd052c3621280d97bd3b92575466379 100644 --- a/drivers/net/arcnet/arc-rimi.c +++ b/drivers/net/arcnet/arc-rimi.c @@ -332,7 +332,7 @@ static int __init arc_rimi_init(void) dev->irq = 9; if (arcrimi_probe(dev)) { - free_netdev(dev); + free_arcdev(dev); return -EIO; } @@ -349,7 +349,7 @@ static void __exit arc_rimi_exit(void) iounmap(lp->mem_start); release_mem_region(dev->mem_start, dev->mem_end - dev->mem_start + 1); free_irq(dev->irq, dev); - free_netdev(dev); + free_arcdev(dev); } #ifndef MODULE diff --git a/drivers/net/arcnet/arcdevice.h b/drivers/net/arcnet/arcdevice.h index 22a49c6d7ae6ef590b3b0e2d8b6bcf2a10f8b0b7..5d4a4c7efbbff3763193844e2052ca32dcb27490 100644 --- a/drivers/net/arcnet/arcdevice.h +++ b/drivers/net/arcnet/arcdevice.h @@ -298,6 +298,10 @@ struct arcnet_local { int excnak_pending; /* We just got an excesive nak interrupt */ + /* RESET flag handling */ + int reset_in_progress; + struct work_struct reset_work; + struct { uint16_t sequence; /* sequence number (incs with each packet) */ __be16 aborted_seq; @@ -350,7 +354,9 @@ void arcnet_dump_skb(struct net_device *dev, struct sk_buff *skb, char *desc) void arcnet_unregister_proto(struct ArcProto *proto); irqreturn_t arcnet_interrupt(int irq, void *dev_id); + struct net_device *alloc_arcdev(const char *name); +void free_arcdev(struct net_device *dev); int arcnet_open(struct net_device *dev); int arcnet_close(struct net_device *dev); diff --git a/drivers/net/arcnet/arcnet.c b/drivers/net/arcnet/arcnet.c index e04efc0a5c977ee8b33a0ff77fe15c85ee322119..d76dd7d14299e198f305f4effed8611a8c9b480f 100644 --- a/drivers/net/arcnet/arcnet.c +++ b/drivers/net/arcnet/arcnet.c @@ -387,10 +387,44 @@ static void arcnet_timer(struct timer_list *t) struct arcnet_local *lp = from_timer(lp, t, timer); struct net_device *dev = lp->dev; - if (!netif_carrier_ok(dev)) { + spin_lock_irq(&lp->lock); + + if (!lp->reset_in_progress && !netif_carrier_ok(dev)) { netif_carrier_on(dev); netdev_info(dev, "link up\n"); } + + spin_unlock_irq(&lp->lock); +} + +static void reset_device_work(struct work_struct *work) +{ + struct arcnet_local *lp; + struct net_device *dev; + + lp = container_of(work, struct arcnet_local, reset_work); + dev = lp->dev; + + /* Do not bring the network interface back up if an ifdown + * was already done. + */ + if (!netif_running(dev) || !lp->reset_in_progress) + return; + + rtnl_lock(); + + /* Do another check, in case of an ifdown that was triggered in + * the small race window between the exit condition above and + * acquiring RTNL. + */ + if (!netif_running(dev) || !lp->reset_in_progress) + goto out; + + dev_close(dev); + dev_open(dev, NULL); + +out: + rtnl_unlock(); } static void arcnet_reply_tasklet(unsigned long data) @@ -452,12 +486,25 @@ struct net_device *alloc_arcdev(const char *name) lp->dev = dev; spin_lock_init(&lp->lock); timer_setup(&lp->timer, arcnet_timer, 0); + INIT_WORK(&lp->reset_work, reset_device_work); } return dev; } EXPORT_SYMBOL(alloc_arcdev); +void free_arcdev(struct net_device *dev) +{ + struct arcnet_local *lp = netdev_priv(dev); + + /* Do not cancel this at ->ndo_close(), as the workqueue itself + * indirectly calls the ifdown path through dev_close(). + */ + cancel_work_sync(&lp->reset_work); + free_netdev(dev); +} +EXPORT_SYMBOL(free_arcdev); + /* Open/initialize the board. This is called sometime after booting when * the 'ifconfig' program is run. * @@ -587,6 +634,10 @@ int arcnet_close(struct net_device *dev) /* shut down the card */ lp->hw.close(dev); + + /* reset counters */ + lp->reset_in_progress = 0; + module_put(lp->hw.owner); return 0; } @@ -820,6 +871,9 @@ irqreturn_t arcnet_interrupt(int irq, void *dev_id) spin_lock_irqsave(&lp->lock, flags); + if (lp->reset_in_progress) + goto out; + /* RESET flag was enabled - if device is not running, we must * clear it right away (but nothing else). */ @@ -852,11 +906,14 @@ irqreturn_t arcnet_interrupt(int irq, void *dev_id) if (status & RESETflag) { arc_printk(D_NORMAL, dev, "spurious reset (status=%Xh)\n", status); - arcnet_close(dev); - arcnet_open(dev); + + lp->reset_in_progress = 1; + netif_stop_queue(dev); + netif_carrier_off(dev); + schedule_work(&lp->reset_work); /* get out of the interrupt handler! */ - break; + goto out; } /* RX is inhibited - we must have received something. * Prepare to receive into the next buffer. @@ -1052,6 +1109,7 @@ irqreturn_t arcnet_interrupt(int irq, void *dev_id) udelay(1); lp->hw.intmask(dev, lp->intmask); +out: spin_unlock_irqrestore(&lp->lock, flags); return retval; } diff --git a/drivers/net/arcnet/com20020-isa.c b/drivers/net/arcnet/com20020-isa.c index f983c4ce6b07f186fd2b6cc136df9eabfa7c8df4..be618e4b9ed5e0aa20f949ea23abf416ce5239b6 100644 --- a/drivers/net/arcnet/com20020-isa.c +++ b/drivers/net/arcnet/com20020-isa.c @@ -169,7 +169,7 @@ static int __init com20020_init(void) dev->irq = 9; if (com20020isa_probe(dev)) { - free_netdev(dev); + free_arcdev(dev); return -EIO; } @@ -182,7 +182,7 @@ static void __exit com20020_exit(void) unregister_netdev(my_dev); free_irq(my_dev->irq, my_dev); release_region(my_dev->base_addr, ARCNET_TOTAL_SIZE); - free_netdev(my_dev); + free_arcdev(my_dev); } #ifndef MODULE diff --git a/drivers/net/arcnet/com20020-pci.c b/drivers/net/arcnet/com20020-pci.c index 9f44e2e458df17e08b2ab9238d5dca39c52110bb..b4f8798d8c5093ff87be29d3f8e31665a6a0d851 100644 --- a/drivers/net/arcnet/com20020-pci.c +++ b/drivers/net/arcnet/com20020-pci.c @@ -294,7 +294,7 @@ static void com20020pci_remove(struct pci_dev *pdev) unregister_netdev(dev); free_irq(dev->irq, dev); - free_netdev(dev); + free_arcdev(dev); } } diff --git a/drivers/net/arcnet/com20020_cs.c b/drivers/net/arcnet/com20020_cs.c index cf607ffcf358e95eab6a63c3c7bb63382cd57c49..e0c7720bd5da95065ba74d61a680fa23e29f58f1 100644 --- a/drivers/net/arcnet/com20020_cs.c +++ b/drivers/net/arcnet/com20020_cs.c @@ -113,6 +113,7 @@ static int com20020_probe(struct pcmcia_device *p_dev) struct com20020_dev *info; struct net_device *dev; struct arcnet_local *lp; + int ret = -ENOMEM; dev_dbg(&p_dev->dev, "com20020_attach()\n"); @@ -142,12 +143,18 @@ static int com20020_probe(struct pcmcia_device *p_dev) info->dev = dev; p_dev->priv = info; - return com20020_config(p_dev); + ret = com20020_config(p_dev); + if (ret) + goto fail_config; + + return 0; +fail_config: + free_arcdev(dev); fail_alloc_dev: kfree(info); fail_alloc_info: - return -ENOMEM; + return ret; } /* com20020_attach */ static void com20020_detach(struct pcmcia_device *link) @@ -177,7 +184,7 @@ static void com20020_detach(struct pcmcia_device *link) dev = info->dev; if (dev) { dev_dbg(&link->dev, "kfree...\n"); - free_netdev(dev); + free_arcdev(dev); } dev_dbg(&link->dev, "kfree2...\n"); kfree(info); diff --git a/drivers/net/arcnet/com90io.c b/drivers/net/arcnet/com90io.c index cf214b7306715487b84cd2301fca4de1bada6f48..3856b447d38ed27ca5ef98a1d0b4191f92152d31 100644 --- a/drivers/net/arcnet/com90io.c +++ b/drivers/net/arcnet/com90io.c @@ -396,7 +396,7 @@ static int __init com90io_init(void) err = com90io_probe(dev); if (err) { - free_netdev(dev); + free_arcdev(dev); return err; } @@ -419,7 +419,7 @@ static void __exit com90io_exit(void) free_irq(dev->irq, dev); release_region(dev->base_addr, ARCNET_TOTAL_SIZE); - free_netdev(dev); + free_arcdev(dev); } module_init(com90io_init) diff --git a/drivers/net/arcnet/com90xx.c b/drivers/net/arcnet/com90xx.c index 3dc3d533cb19a258e72f57d46443b9b52d1b8df7..d8dfb9ea0de89bf9929ee334d9f332c9156cef18 100644 --- a/drivers/net/arcnet/com90xx.c +++ b/drivers/net/arcnet/com90xx.c @@ -554,7 +554,7 @@ err_free_irq: err_release_mem: release_mem_region(dev->mem_start, dev->mem_end - dev->mem_start + 1); err_free_dev: - free_netdev(dev); + free_arcdev(dev); return -EIO; } @@ -672,7 +672,7 @@ static void __exit com90xx_exit(void) release_region(dev->base_addr, ARCNET_TOTAL_SIZE); release_mem_region(dev->mem_start, dev->mem_end - dev->mem_start + 1); - free_netdev(dev); + free_arcdev(dev); } } diff --git a/drivers/net/can/mscan/mpc5xxx_can.c b/drivers/net/can/mscan/mpc5xxx_can.c index e254e04ae257f9de1c012360977c42b495ea9b21..ef649764f9b4ecebd8838fbdbdaefb43ddc52cb4 100644 --- a/drivers/net/can/mscan/mpc5xxx_can.c +++ b/drivers/net/can/mscan/mpc5xxx_can.c @@ -325,14 +325,14 @@ static int mpc5xxx_can_probe(struct platform_device *ofdev) &mscan_clksrc); if (!priv->can.clock.freq) { dev_err(&ofdev->dev, "couldn't get MSCAN clock properties\n"); - goto exit_free_mscan; + goto exit_put_clock; } err = register_mscandev(dev, mscan_clksrc); if (err) { dev_err(&ofdev->dev, "registering %s failed (err=%d)\n", DRV_NAME, err); - goto exit_free_mscan; + goto exit_put_clock; } dev_info(&ofdev->dev, "MSCAN at 0x%p, irq %d, clock %d Hz\n", @@ -340,7 +340,9 @@ static int mpc5xxx_can_probe(struct platform_device *ofdev) return 0; -exit_free_mscan: +exit_put_clock: + if (data->put_clock) + data->put_clock(ofdev); free_candev(dev); exit_dispose_irq: irq_dispose_mapping(irq); diff --git a/drivers/net/can/rcar/rcar_canfd.c b/drivers/net/can/rcar/rcar_canfd.c index 67f0f14e2bf4e1eadcd9409aa80d0a4ac6ece0dd..c61534a2a2d3a3fca47e28433fee9d56378a7221 100644 --- a/drivers/net/can/rcar/rcar_canfd.c +++ b/drivers/net/can/rcar/rcar_canfd.c @@ -1075,7 +1075,7 @@ static irqreturn_t rcar_canfd_global_interrupt(int irq, void *dev_id) struct rcar_canfd_global *gpriv = dev_id; struct net_device *ndev; struct rcar_canfd_channel *priv; - u32 sts, gerfl; + u32 sts, cc, gerfl; u32 ch, ridx; /* Global error interrupts still indicate a condition specific @@ -1093,7 +1093,9 @@ static irqreturn_t rcar_canfd_global_interrupt(int irq, void *dev_id) /* Handle Rx interrupts */ sts = rcar_canfd_read(priv->base, RCANFD_RFSTS(ridx)); - if (likely(sts & RCANFD_RFSTS_RFIF)) { + cc = rcar_canfd_read(priv->base, RCANFD_RFCC(ridx)); + if (likely(sts & RCANFD_RFSTS_RFIF && + cc & RCANFD_RFCC_RFIE)) { if (napi_schedule_prep(&priv->napi)) { /* Disable Rx FIFO interrupts */ rcar_canfd_clear_bit(priv->base, diff --git a/drivers/net/can/spi/mcp251x.c b/drivers/net/can/spi/mcp251x.c index 5dde3c42d241bdf0572a517c9232a838c86b966d..ffcb04aac9729ece57edce656e526f5613a34f45 100644 --- a/drivers/net/can/spi/mcp251x.c +++ b/drivers/net/can/spi/mcp251x.c @@ -1419,11 +1419,14 @@ static int mcp251x_can_probe(struct spi_device *spi) ret = mcp251x_gpio_setup(priv); if (ret) - goto error_probe; + goto out_unregister_candev; netdev_info(net, "MCP%x successfully initialized.\n", priv->model); return 0; +out_unregister_candev: + unregister_candev(net); + error_probe: destroy_workqueue(priv->wq); priv->wq = NULL; diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb.h b/drivers/net/can/usb/kvaser_usb/kvaser_usb.h index 61e67986b625e9a556147ce1c7a6b84e4d87670e..62958f04a2f20ea613b2d0754937b7b3718be6de 100644 --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb.h +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb.h @@ -178,6 +178,8 @@ struct kvaser_usb_dev_cfg { extern const struct kvaser_usb_dev_ops kvaser_usb_hydra_dev_ops; extern const struct kvaser_usb_dev_ops kvaser_usb_leaf_dev_ops; +void kvaser_usb_unlink_tx_urbs(struct kvaser_usb_net_priv *priv); + int kvaser_usb_recv_cmd(const struct kvaser_usb *dev, void *cmd, int len, int *actual_len); diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c index 416763fd1f11c8cd3205b20781f3e8560ec0ac0d..7491f85e85b304bcd8904b974fbd8ce899f714bb 100644 --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c @@ -453,7 +453,7 @@ static void kvaser_usb_reset_tx_urb_contexts(struct kvaser_usb_net_priv *priv) /* This method might sleep. Do not call it in the atomic context * of URB completions. */ -static void kvaser_usb_unlink_tx_urbs(struct kvaser_usb_net_priv *priv) +void kvaser_usb_unlink_tx_urbs(struct kvaser_usb_net_priv *priv) { usb_kill_anchored_urbs(&priv->tx_submitted); kvaser_usb_reset_tx_urb_contexts(priv); @@ -690,6 +690,7 @@ static int kvaser_usb_init_one(struct kvaser_usb *dev, int channel) init_usb_anchor(&priv->tx_submitted); init_completion(&priv->start_comp); init_completion(&priv->stop_comp); + init_completion(&priv->flush_comp); priv->can.ctrlmode_supported = 0; priv->dev = dev; diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c index 01d4a731b579c1071b956d38a0653d8f8f299f19..45d27872488395c09b78bae8e05a0227ce7957a9 100644 --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c @@ -1845,7 +1845,7 @@ static int kvaser_usb_hydra_start_chip(struct kvaser_usb_net_priv *priv) { int err; - init_completion(&priv->start_comp); + reinit_completion(&priv->start_comp); err = kvaser_usb_hydra_send_simple_cmd(priv->dev, CMD_START_CHIP_REQ, priv->channel); @@ -1863,7 +1863,7 @@ static int kvaser_usb_hydra_stop_chip(struct kvaser_usb_net_priv *priv) { int err; - init_completion(&priv->stop_comp); + reinit_completion(&priv->stop_comp); /* Make sure we do not report invalid BUS_OFF from CMD_CHIP_STATE_EVENT * see comment in kvaser_usb_hydra_update_state() @@ -1886,7 +1886,7 @@ static int kvaser_usb_hydra_flush_queue(struct kvaser_usb_net_priv *priv) { int err; - init_completion(&priv->flush_comp); + reinit_completion(&priv->flush_comp); err = kvaser_usb_hydra_send_simple_cmd(priv->dev, CMD_FLUSH_QUEUE, priv->channel); diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c index 5e281249ad5feba3cb40e6fd521a1db8131bcb6e..15380cc08ee69ad72317b7d1fb0d3f350b473d40 100644 --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c @@ -309,6 +309,38 @@ struct kvaser_cmd { } u; } __packed; +#define CMD_SIZE_ANY 0xff +#define kvaser_fsize(field) sizeof_field(struct kvaser_cmd, field) + +static const u8 kvaser_usb_leaf_cmd_sizes_leaf[] = { + [CMD_START_CHIP_REPLY] = kvaser_fsize(u.simple), + [CMD_STOP_CHIP_REPLY] = kvaser_fsize(u.simple), + [CMD_GET_CARD_INFO_REPLY] = kvaser_fsize(u.cardinfo), + [CMD_TX_ACKNOWLEDGE] = kvaser_fsize(u.tx_acknowledge_header), + [CMD_GET_SOFTWARE_INFO_REPLY] = kvaser_fsize(u.leaf.softinfo), + [CMD_RX_STD_MESSAGE] = kvaser_fsize(u.leaf.rx_can), + [CMD_RX_EXT_MESSAGE] = kvaser_fsize(u.leaf.rx_can), + [CMD_LEAF_LOG_MESSAGE] = kvaser_fsize(u.leaf.log_message), + [CMD_CHIP_STATE_EVENT] = kvaser_fsize(u.leaf.chip_state_event), + [CMD_CAN_ERROR_EVENT] = kvaser_fsize(u.leaf.error_event), + /* ignored events: */ + [CMD_FLUSH_QUEUE_REPLY] = CMD_SIZE_ANY, +}; + +static const u8 kvaser_usb_leaf_cmd_sizes_usbcan[] = { + [CMD_START_CHIP_REPLY] = kvaser_fsize(u.simple), + [CMD_STOP_CHIP_REPLY] = kvaser_fsize(u.simple), + [CMD_GET_CARD_INFO_REPLY] = kvaser_fsize(u.cardinfo), + [CMD_TX_ACKNOWLEDGE] = kvaser_fsize(u.tx_acknowledge_header), + [CMD_GET_SOFTWARE_INFO_REPLY] = kvaser_fsize(u.usbcan.softinfo), + [CMD_RX_STD_MESSAGE] = kvaser_fsize(u.usbcan.rx_can), + [CMD_RX_EXT_MESSAGE] = kvaser_fsize(u.usbcan.rx_can), + [CMD_CHIP_STATE_EVENT] = kvaser_fsize(u.usbcan.chip_state_event), + [CMD_CAN_ERROR_EVENT] = kvaser_fsize(u.usbcan.error_event), + /* ignored events: */ + [CMD_USBCAN_CLOCK_OVERFLOW_EVENT] = CMD_SIZE_ANY, +}; + /* Summary of a kvaser error event, for a unified Leaf/Usbcan error * handling. Some discrepancies between the two families exist: * @@ -396,6 +428,43 @@ static const struct kvaser_usb_dev_cfg kvaser_usb_leaf_imx_dev_cfg_32mhz = { .bittiming_const = &kvaser_usb_flexc_bittiming_const, }; +static int kvaser_usb_leaf_verify_size(const struct kvaser_usb *dev, + const struct kvaser_cmd *cmd) +{ + /* buffer size >= cmd->len ensured by caller */ + u8 min_size = 0; + + switch (dev->driver_info->family) { + case KVASER_LEAF: + if (cmd->id < ARRAY_SIZE(kvaser_usb_leaf_cmd_sizes_leaf)) + min_size = kvaser_usb_leaf_cmd_sizes_leaf[cmd->id]; + break; + case KVASER_USBCAN: + if (cmd->id < ARRAY_SIZE(kvaser_usb_leaf_cmd_sizes_usbcan)) + min_size = kvaser_usb_leaf_cmd_sizes_usbcan[cmd->id]; + break; + } + + if (min_size == CMD_SIZE_ANY) + return 0; + + if (min_size) { + min_size += CMD_HEADER_LEN; + if (cmd->len >= min_size) + return 0; + + dev_err_ratelimited(&dev->intf->dev, + "Received command %u too short (size %u, needed %u)", + cmd->id, cmd->len, min_size); + return -EIO; + } + + dev_warn_ratelimited(&dev->intf->dev, + "Unhandled command (%d, size %d)\n", + cmd->id, cmd->len); + return -EINVAL; +} + static void * kvaser_usb_leaf_frame_to_cmd(const struct kvaser_usb_net_priv *priv, const struct sk_buff *skb, int *frame_len, @@ -503,6 +572,9 @@ static int kvaser_usb_leaf_wait_cmd(const struct kvaser_usb *dev, u8 id, end: kfree(buf); + if (err == 0) + err = kvaser_usb_leaf_verify_size(dev, cmd); + return err; } @@ -1137,6 +1209,9 @@ static void kvaser_usb_leaf_stop_chip_reply(const struct kvaser_usb *dev, static void kvaser_usb_leaf_handle_command(const struct kvaser_usb *dev, const struct kvaser_cmd *cmd) { + if (kvaser_usb_leaf_verify_size(dev, cmd) < 0) + return; + switch (cmd->id) { case CMD_START_CHIP_REPLY: kvaser_usb_leaf_start_chip_reply(dev, cmd); @@ -1249,7 +1324,7 @@ static int kvaser_usb_leaf_start_chip(struct kvaser_usb_net_priv *priv) { int err; - init_completion(&priv->start_comp); + reinit_completion(&priv->start_comp); err = kvaser_usb_leaf_send_simple_cmd(priv->dev, CMD_START_CHIP, priv->channel); @@ -1267,7 +1342,7 @@ static int kvaser_usb_leaf_stop_chip(struct kvaser_usb_net_priv *priv) { int err; - init_completion(&priv->stop_comp); + reinit_completion(&priv->stop_comp); err = kvaser_usb_leaf_send_simple_cmd(priv->dev, CMD_STOP_CHIP, priv->channel); @@ -1355,9 +1430,13 @@ static int kvaser_usb_leaf_set_mode(struct net_device *netdev, switch (mode) { case CAN_MODE_START: + kvaser_usb_unlink_tx_urbs(priv); + err = kvaser_usb_leaf_simple_cmd_async(priv, CMD_START_CHIP); if (err) return err; + + priv->can.state = CAN_STATE_ERROR_ACTIVE; break; default: return -EOPNOTSUPP; diff --git a/drivers/net/dsa/dsa_loop.c b/drivers/net/dsa/dsa_loop.c index e38906ae8f235d24b47f676eb9a0e7b060fbc22f..fbeb99ab9e4ddde3cc5052926a717369477f46fd 100644 --- a/drivers/net/dsa/dsa_loop.c +++ b/drivers/net/dsa/dsa_loop.c @@ -376,6 +376,17 @@ static struct mdio_driver dsa_loop_drv = { #define NUM_FIXED_PHYS (DSA_LOOP_NUM_PORTS - 2) +static void dsa_loop_phydevs_unregister(void) +{ + unsigned int i; + + for (i = 0; i < NUM_FIXED_PHYS; i++) + if (!IS_ERR(phydevs[i])) { + fixed_phy_unregister(phydevs[i]); + phy_device_free(phydevs[i]); + } +} + static int __init dsa_loop_init(void) { struct fixed_phy_status status = { @@ -383,23 +394,23 @@ static int __init dsa_loop_init(void) .speed = SPEED_100, .duplex = DUPLEX_FULL, }; - unsigned int i; + unsigned int i, ret; for (i = 0; i < NUM_FIXED_PHYS; i++) phydevs[i] = fixed_phy_register(PHY_POLL, &status, NULL); - return mdio_driver_register(&dsa_loop_drv); + ret = mdio_driver_register(&dsa_loop_drv); + if (ret) + dsa_loop_phydevs_unregister(); + + return ret; } module_init(dsa_loop_init); static void __exit dsa_loop_exit(void) { - unsigned int i; - mdio_driver_unregister(&dsa_loop_drv); - for (i = 0; i < NUM_FIXED_PHYS; i++) - if (!IS_ERR(phydevs[i])) - fixed_phy_unregister(phydevs[i]); + dsa_loop_phydevs_unregister(); } module_exit(dsa_loop_exit); diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index 52414ac2c901abc5482c311261500674efdbbbb2..1722d4091ea3f45b2c8ae264e90cdec45cb7935b 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -4488,13 +4488,19 @@ static struct pci_driver ena_pci_driver = { static int __init ena_init(void) { + int ret; + ena_wq = create_singlethread_workqueue(DRV_MODULE_NAME); if (!ena_wq) { pr_err("Failed to create workqueue\n"); return -ENOMEM; } - return pci_register_driver(&ena_pci_driver); + ret = pci_register_driver(&ena_pci_driver); + if (ret) + destroy_workqueue(ena_wq); + + return ret; } static void __exit ena_cleanup(void) diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c index 213769054391c1f7236aad579ade7defcedb9a82..a7166cd1179f2ccd362ac3d57b77a2ee50689f38 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c @@ -239,6 +239,7 @@ enum xgbe_sfp_speed { #define XGBE_SFP_BASE_BR_1GBE_MAX 0x0d #define XGBE_SFP_BASE_BR_10GBE_MIN 0x64 #define XGBE_SFP_BASE_BR_10GBE_MAX 0x68 +#define XGBE_MOLEX_SFP_BASE_BR_10GBE_MAX 0x78 #define XGBE_SFP_BASE_CU_CABLE_LEN 18 @@ -284,6 +285,8 @@ struct xgbe_sfp_eeprom { #define XGBE_BEL_FUSE_VENDOR "BEL-FUSE " #define XGBE_BEL_FUSE_PARTNO "1GBT-SFP06 " +#define XGBE_MOLEX_VENDOR "Molex Inc. " + struct xgbe_sfp_ascii { union { char vendor[XGBE_SFP_BASE_VENDOR_NAME_LEN + 1]; @@ -834,7 +837,11 @@ static bool xgbe_phy_sfp_bit_rate(struct xgbe_sfp_eeprom *sfp_eeprom, break; case XGBE_SFP_SPEED_10000: min = XGBE_SFP_BASE_BR_10GBE_MIN; - max = XGBE_SFP_BASE_BR_10GBE_MAX; + if (memcmp(&sfp_eeprom->base[XGBE_SFP_BASE_VENDOR_NAME], + XGBE_MOLEX_VENDOR, XGBE_SFP_BASE_VENDOR_NAME_LEN) == 0) + max = XGBE_MOLEX_SFP_BASE_BR_10GBE_MAX; + else + max = XGBE_SFP_BASE_BR_10GBE_MAX; break; default: return false; @@ -1151,7 +1158,10 @@ static void xgbe_phy_sfp_parse_eeprom(struct xgbe_prv_data *pdata) } /* Determine the type of SFP */ - if (sfp_base[XGBE_SFP_BASE_10GBE_CC] & XGBE_SFP_BASE_10GBE_CC_SR) + if (phy_data->sfp_cable == XGBE_SFP_CABLE_PASSIVE && + xgbe_phy_sfp_bit_rate(sfp_eeprom, XGBE_SFP_SPEED_10000)) + phy_data->sfp_base = XGBE_SFP_BASE_10000_CR; + else if (sfp_base[XGBE_SFP_BASE_10GBE_CC] & XGBE_SFP_BASE_10GBE_CC_SR) phy_data->sfp_base = XGBE_SFP_BASE_10000_SR; else if (sfp_base[XGBE_SFP_BASE_10GBE_CC] & XGBE_SFP_BASE_10GBE_CC_LR) phy_data->sfp_base = XGBE_SFP_BASE_10000_LR; @@ -1167,9 +1177,6 @@ static void xgbe_phy_sfp_parse_eeprom(struct xgbe_prv_data *pdata) phy_data->sfp_base = XGBE_SFP_BASE_1000_CX; else if (sfp_base[XGBE_SFP_BASE_1GBE_CC] & XGBE_SFP_BASE_1GBE_CC_T) phy_data->sfp_base = XGBE_SFP_BASE_1000_T; - else if ((phy_data->sfp_cable == XGBE_SFP_CABLE_PASSIVE) && - xgbe_phy_sfp_bit_rate(sfp_eeprom, XGBE_SFP_SPEED_10000)) - phy_data->sfp_base = XGBE_SFP_BASE_10000_CR; switch (phy_data->sfp_base) { case XGBE_SFP_BASE_1000_T: diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c index 78c7cbc372b0559c1aaf2a95bb9ac84c9dba860a..71151f675a49858de69b550a8267024b2947147f 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c @@ -1004,8 +1004,10 @@ static int xgene_enet_open(struct net_device *ndev) xgene_enet_napi_enable(pdata); ret = xgene_enet_register_irq(ndev); - if (ret) + if (ret) { + xgene_enet_napi_disable(pdata); return ret; + } if (ndev->phydev) { phy_start(ndev->phydev); diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_macsec.c b/drivers/net/ethernet/aquantia/atlantic/aq_macsec.c index 4a6dfac857ca962575ad0e8810c083313016e73a..ee823a18294cd72a29e25ab5e1d27a35b98c4e56 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_macsec.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_macsec.c @@ -585,6 +585,7 @@ static int aq_update_txsa(struct aq_nic_s *nic, const unsigned int sc_idx, ret = aq_mss_set_egress_sakey_record(hw, &key_rec, sa_idx); + memzero_explicit(&key_rec, sizeof(key_rec)); return ret; } @@ -932,6 +933,7 @@ static int aq_update_rxsa(struct aq_nic_s *nic, const unsigned int sc_idx, ret = aq_mss_set_ingress_sakey_record(hw, &sa_key_record, sa_idx); + memzero_explicit(&sa_key_record, sizeof(sa_key_record)); return ret; } @@ -1451,26 +1453,57 @@ static void aq_check_txsa_expiration(struct aq_nic_s *nic) egress_sa_threshold_expired); } +#define AQ_LOCKED_MDO_DEF(mdo) \ +static int aq_locked_mdo_##mdo(struct macsec_context *ctx) \ +{ \ + struct aq_nic_s *nic = netdev_priv(ctx->netdev); \ + int ret; \ + mutex_lock(&nic->macsec_mutex); \ + ret = aq_mdo_##mdo(ctx); \ + mutex_unlock(&nic->macsec_mutex); \ + return ret; \ +} + +AQ_LOCKED_MDO_DEF(dev_open) +AQ_LOCKED_MDO_DEF(dev_stop) +AQ_LOCKED_MDO_DEF(add_secy) +AQ_LOCKED_MDO_DEF(upd_secy) +AQ_LOCKED_MDO_DEF(del_secy) +AQ_LOCKED_MDO_DEF(add_rxsc) +AQ_LOCKED_MDO_DEF(upd_rxsc) +AQ_LOCKED_MDO_DEF(del_rxsc) +AQ_LOCKED_MDO_DEF(add_rxsa) +AQ_LOCKED_MDO_DEF(upd_rxsa) +AQ_LOCKED_MDO_DEF(del_rxsa) +AQ_LOCKED_MDO_DEF(add_txsa) +AQ_LOCKED_MDO_DEF(upd_txsa) +AQ_LOCKED_MDO_DEF(del_txsa) +AQ_LOCKED_MDO_DEF(get_dev_stats) +AQ_LOCKED_MDO_DEF(get_tx_sc_stats) +AQ_LOCKED_MDO_DEF(get_tx_sa_stats) +AQ_LOCKED_MDO_DEF(get_rx_sc_stats) +AQ_LOCKED_MDO_DEF(get_rx_sa_stats) + const struct macsec_ops aq_macsec_ops = { - .mdo_dev_open = aq_mdo_dev_open, - .mdo_dev_stop = aq_mdo_dev_stop, - .mdo_add_secy = aq_mdo_add_secy, - .mdo_upd_secy = aq_mdo_upd_secy, - .mdo_del_secy = aq_mdo_del_secy, - .mdo_add_rxsc = aq_mdo_add_rxsc, - .mdo_upd_rxsc = aq_mdo_upd_rxsc, - .mdo_del_rxsc = aq_mdo_del_rxsc, - .mdo_add_rxsa = aq_mdo_add_rxsa, - .mdo_upd_rxsa = aq_mdo_upd_rxsa, - .mdo_del_rxsa = aq_mdo_del_rxsa, - .mdo_add_txsa = aq_mdo_add_txsa, - .mdo_upd_txsa = aq_mdo_upd_txsa, - .mdo_del_txsa = aq_mdo_del_txsa, - .mdo_get_dev_stats = aq_mdo_get_dev_stats, - .mdo_get_tx_sc_stats = aq_mdo_get_tx_sc_stats, - .mdo_get_tx_sa_stats = aq_mdo_get_tx_sa_stats, - .mdo_get_rx_sc_stats = aq_mdo_get_rx_sc_stats, - .mdo_get_rx_sa_stats = aq_mdo_get_rx_sa_stats, + .mdo_dev_open = aq_locked_mdo_dev_open, + .mdo_dev_stop = aq_locked_mdo_dev_stop, + .mdo_add_secy = aq_locked_mdo_add_secy, + .mdo_upd_secy = aq_locked_mdo_upd_secy, + .mdo_del_secy = aq_locked_mdo_del_secy, + .mdo_add_rxsc = aq_locked_mdo_add_rxsc, + .mdo_upd_rxsc = aq_locked_mdo_upd_rxsc, + .mdo_del_rxsc = aq_locked_mdo_del_rxsc, + .mdo_add_rxsa = aq_locked_mdo_add_rxsa, + .mdo_upd_rxsa = aq_locked_mdo_upd_rxsa, + .mdo_del_rxsa = aq_locked_mdo_del_rxsa, + .mdo_add_txsa = aq_locked_mdo_add_txsa, + .mdo_upd_txsa = aq_locked_mdo_upd_txsa, + .mdo_del_txsa = aq_locked_mdo_del_txsa, + .mdo_get_dev_stats = aq_locked_mdo_get_dev_stats, + .mdo_get_tx_sc_stats = aq_locked_mdo_get_tx_sc_stats, + .mdo_get_tx_sa_stats = aq_locked_mdo_get_tx_sa_stats, + .mdo_get_rx_sc_stats = aq_locked_mdo_get_rx_sc_stats, + .mdo_get_rx_sa_stats = aq_locked_mdo_get_rx_sa_stats, }; int aq_macsec_init(struct aq_nic_s *nic) @@ -1492,6 +1525,7 @@ int aq_macsec_init(struct aq_nic_s *nic) nic->ndev->features |= NETIF_F_HW_MACSEC; nic->ndev->macsec_ops = &aq_macsec_ops; + mutex_init(&nic->macsec_mutex); return 0; } @@ -1515,7 +1549,7 @@ int aq_macsec_enable(struct aq_nic_s *nic) if (!nic->macsec_cfg) return 0; - rtnl_lock(); + mutex_lock(&nic->macsec_mutex); if (nic->aq_fw_ops->send_macsec_req) { struct macsec_cfg_request cfg = { 0 }; @@ -1564,7 +1598,7 @@ int aq_macsec_enable(struct aq_nic_s *nic) ret = aq_apply_macsec_cfg(nic); unlock: - rtnl_unlock(); + mutex_unlock(&nic->macsec_mutex); return ret; } @@ -1576,9 +1610,9 @@ void aq_macsec_work(struct aq_nic_s *nic) if (!netif_carrier_ok(nic->ndev)) return; - rtnl_lock(); + mutex_lock(&nic->macsec_mutex); aq_check_txsa_expiration(nic); - rtnl_unlock(); + mutex_unlock(&nic->macsec_mutex); } int aq_macsec_rx_sa_cnt(struct aq_nic_s *nic) @@ -1589,21 +1623,30 @@ int aq_macsec_rx_sa_cnt(struct aq_nic_s *nic) if (!cfg) return 0; + mutex_lock(&nic->macsec_mutex); + for (i = 0; i < AQ_MACSEC_MAX_SC; i++) { if (!test_bit(i, &cfg->rxsc_idx_busy)) continue; cnt += hweight_long(cfg->aq_rxsc[i].rx_sa_idx_busy); } + mutex_unlock(&nic->macsec_mutex); return cnt; } int aq_macsec_tx_sc_cnt(struct aq_nic_s *nic) { + int cnt; + if (!nic->macsec_cfg) return 0; - return hweight_long(nic->macsec_cfg->txsc_idx_busy); + mutex_lock(&nic->macsec_mutex); + cnt = hweight_long(nic->macsec_cfg->txsc_idx_busy); + mutex_unlock(&nic->macsec_mutex); + + return cnt; } int aq_macsec_tx_sa_cnt(struct aq_nic_s *nic) @@ -1614,12 +1657,15 @@ int aq_macsec_tx_sa_cnt(struct aq_nic_s *nic) if (!cfg) return 0; + mutex_lock(&nic->macsec_mutex); + for (i = 0; i < AQ_MACSEC_MAX_SC; i++) { if (!test_bit(i, &cfg->txsc_idx_busy)) continue; cnt += hweight_long(cfg->aq_txsc[i].tx_sa_idx_busy); } + mutex_unlock(&nic->macsec_mutex); return cnt; } @@ -1691,6 +1737,8 @@ u64 *aq_macsec_get_stats(struct aq_nic_s *nic, u64 *data) if (!cfg) return data; + mutex_lock(&nic->macsec_mutex); + aq_macsec_update_stats(nic); common_stats = &cfg->stats; @@ -1773,5 +1821,7 @@ u64 *aq_macsec_get_stats(struct aq_nic_s *nic, u64 *data) data += i; + mutex_unlock(&nic->macsec_mutex); + return data; } diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h index 926cca9a0c837ce31685f4e52f6880e4e5ba6005..6da3efa289a3fe91716ffcb6a2982f2df3a2922d 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h @@ -152,6 +152,8 @@ struct aq_nic_s { struct mutex fwreq_mutex; #if IS_ENABLED(CONFIG_MACSEC) struct aq_macsec_cfg *macsec_cfg; + /* mutex to protect data in macsec_cfg */ + struct mutex macsec_mutex; #endif /* PTP support */ struct aq_ptp_s *aq_ptp; diff --git a/drivers/net/ethernet/aquantia/atlantic/macsec/macsec_api.c b/drivers/net/ethernet/aquantia/atlantic/macsec/macsec_api.c index 36c7cf05630a1ea4711cde2d1a88d7a0050ed0d0..4319249595207c0a7cca9c479a9465bc7f2548a2 100644 --- a/drivers/net/ethernet/aquantia/atlantic/macsec/macsec_api.c +++ b/drivers/net/ethernet/aquantia/atlantic/macsec/macsec_api.c @@ -757,6 +757,7 @@ set_ingress_sakey_record(struct aq_hw_s *hw, u16 table_index) { u16 packed_record[18]; + int ret; if (table_index >= NUMROWS_INGRESSSAKEYRECORD) return -EINVAL; @@ -789,9 +790,12 @@ set_ingress_sakey_record(struct aq_hw_s *hw, packed_record[16] = rec->key_len & 0x3; - return set_raw_ingress_record(hw, packed_record, 18, 2, - ROWOFFSET_INGRESSSAKEYRECORD + - table_index); + ret = set_raw_ingress_record(hw, packed_record, 18, 2, + ROWOFFSET_INGRESSSAKEYRECORD + + table_index); + + memzero_explicit(packed_record, sizeof(packed_record)); + return ret; } int aq_mss_set_ingress_sakey_record(struct aq_hw_s *hw, @@ -1739,14 +1743,14 @@ static int set_egress_sakey_record(struct aq_hw_s *hw, ret = set_raw_egress_record(hw, packed_record, 8, 2, ROWOFFSET_EGRESSSAKEYRECORD + table_index); if (unlikely(ret)) - return ret; + goto clear_key; ret = set_raw_egress_record(hw, packed_record + 8, 8, 2, ROWOFFSET_EGRESSSAKEYRECORD + table_index - 32); - if (unlikely(ret)) - return ret; - return 0; +clear_key: + memzero_explicit(packed_record, sizeof(packed_record)); + return ret; } int aq_mss_set_egress_sakey_record(struct aq_hw_s *hw, diff --git a/drivers/net/ethernet/atheros/ag71xx.c b/drivers/net/ethernet/atheros/ag71xx.c index c26c9b0c00d8fb7babd827ceb036bc10e8acb3c0..fe3ca3af431a4e055bc337d2e452dc72eb6aefde 100644 --- a/drivers/net/ethernet/atheros/ag71xx.c +++ b/drivers/net/ethernet/atheros/ag71xx.c @@ -1468,7 +1468,7 @@ static int ag71xx_open(struct net_device *ndev) if (ret) { netif_err(ag, link, ndev, "phylink_of_phy_connect filed with err: %i\n", ret); - goto err; + return ret; } max_frame_len = ag71xx_max_frame_len(ndev->mtu); @@ -1489,6 +1489,7 @@ static int ag71xx_open(struct net_device *ndev) err: ag71xx_rings_cleanup(ag); + phylink_disconnect_phy(ag->phylink); return ret; } diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c index 6290d8bedc92e8bee3ffcba8ab5fbd956edae76b..9960127f612eaf54f79ca06c8f6ac2901b2871ea 100644 --- a/drivers/net/ethernet/broadcom/bgmac.c +++ b/drivers/net/ethernet/broadcom/bgmac.c @@ -1568,7 +1568,6 @@ void bgmac_enet_remove(struct bgmac *bgmac) phy_disconnect(bgmac->net_dev->phydev); netif_napi_del(&bgmac->napi); bgmac_dma_free(bgmac); - free_netdev(bgmac->net_dev); } EXPORT_SYMBOL_GPL(bgmac_enet_remove); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index 198e041d841091d5d6bcbe76b0a858f6de715de0..4f669e7c75587803ec8b488b6bcd9532704a6d47 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -788,6 +788,7 @@ static void bnx2x_tpa_stop(struct bnx2x *bp, struct bnx2x_fastpath *fp, BNX2X_ERR("skb_put is about to fail... pad %d len %d rx_buf_size %d\n", pad, len, fp->rx_buf_size); bnx2x_panic(); + bnx2x_frag_free(fp, new_data); return; } #endif diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c index 08437eaacbb966cf3909fd21d14ae2fe15e11a5e..ac327839eed9031320a9ba4517520681b33ab79d 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c @@ -795,16 +795,20 @@ static void bnx2x_vf_enable_traffic(struct bnx2x *bp, struct bnx2x_virtf *vf) static u8 bnx2x_vf_is_pcie_pending(struct bnx2x *bp, u8 abs_vfid) { - struct pci_dev *dev; struct bnx2x_virtf *vf = bnx2x_vf_by_abs_fid(bp, abs_vfid); + struct pci_dev *dev; + bool pending; if (!vf) return false; dev = pci_get_domain_bus_and_slot(vf->domain, vf->bus, vf->devfn); - if (dev) - return bnx2x_is_pcie_pending(dev); - return false; + if (!dev) + return false; + pending = bnx2x_is_pcie_pending(dev); + pci_dev_put(dev); + + return pending; } int bnx2x_vf_flr_clnup_epilog(struct bnx2x *bp, u8 abs_vfid) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index b818d5f342d53be1468547873908b1fb981482c8..92f54e333395834ef13a0e82790f35df53133682 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -12008,8 +12008,8 @@ static int bnxt_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb, rcu_read_lock(); hlist_for_each_entry_rcu(fltr, head, hash) { if (bnxt_fltr_match(fltr, new_fltr)) { + rc = fltr->sw_id; rcu_read_unlock(); - rc = 0; goto err_free; } } @@ -13111,8 +13111,16 @@ static struct pci_driver bnxt_pci_driver = { static int __init bnxt_init(void) { + int err; + bnxt_debug_init(); - return pci_register_driver(&bnxt_pci_driver); + err = pci_register_driver(&bnxt_pci_driver); + if (err) { + bnxt_debug_exit(); + return err; + } + + return 0; } static void __exit bnxt_exit(void) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index f8f7756195205c3550576f83b32d405f9618136b..81b63d1c2391f6112a5addfb0db72fd74f2d9e8a 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -125,7 +125,7 @@ static int bnxt_set_coalesce(struct net_device *dev, } reset_coalesce: - if (netif_running(dev)) { + if (test_bit(BNXT_STATE_OPEN, &bp->state)) { if (update_stats) { rc = bnxt_close_nic(bp, true, false); if (!rc) diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c index e0d18e91710804c3276f7f43bf788e39210fb981..eefb25bcf57ff24d51d9edb429c9bcaf474b3f84 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c @@ -1798,13 +1798,10 @@ static int liquidio_open(struct net_device *netdev) ifstate_set(lio, LIO_IFSTATE_RUNNING); - if (OCTEON_CN23XX_PF(oct)) { - if (!oct->msix_on) - if (setup_tx_poll_fn(netdev)) - return -1; - } else { - if (setup_tx_poll_fn(netdev)) - return -1; + if (!OCTEON_CN23XX_PF(oct) || !oct->msix_on) { + ret = setup_tx_poll_fn(netdev); + if (ret) + goto err_poll; } netif_tx_start_all_queues(netdev); @@ -1817,7 +1814,7 @@ static int liquidio_open(struct net_device *netdev) /* tell Octeon to start forwarding packets to host */ ret = send_rx_ctrl_cmd(lio, 1); if (ret) - return ret; + goto err_rx_ctrl; /* start periodical statistics fetch */ INIT_DELAYED_WORK(&lio->stats_wk.work, lio_fetch_stats); @@ -1828,6 +1825,27 @@ static int liquidio_open(struct net_device *netdev) dev_info(&oct->pci_dev->dev, "%s interface is opened\n", netdev->name); + return 0; + +err_rx_ctrl: + if (!OCTEON_CN23XX_PF(oct) || !oct->msix_on) + cleanup_tx_poll_fn(netdev); +err_poll: + if (lio->ptp_clock) { + ptp_clock_unregister(lio->ptp_clock); + lio->ptp_clock = NULL; + } + + if (oct->props[lio->ifidx].napi_enabled == 1) { + list_for_each_entry_safe(napi, n, &netdev->napi_list, dev_list) + napi_disable(napi); + + oct->props[lio->ifidx].napi_enabled = 0; + + if (OCTEON_CN23XX_PF(oct)) + oct->droq[0]->ops.poll_mode = 0; + } + return ret; } diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c index 8ff28ed04b7fcd0616760f91d727898d98f01f3e..f0e48b9373d6dc01126c8246d08fe93a63ba054b 100644 --- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c +++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c @@ -1438,8 +1438,10 @@ static acpi_status bgx_acpi_match_id(acpi_handle handle, u32 lvl, return AE_OK; } - if (strncmp(string.pointer, bgx_sel, 4)) + if (strncmp(string.pointer, bgx_sel, 4)) { + kfree(string.pointer); return AE_OK; + } acpi_walk_namespace(ACPI_TYPE_DEVICE, handle, 1, bgx_acpi_register_phy, NULL, bgx, NULL); diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c index 84ad7261e243a9a61b864818357c16ab98d3cb21..8a167eea288c39e8ec18f44057c19d376cafdef6 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c +++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c @@ -1302,6 +1302,7 @@ static int cxgb_up(struct adapter *adap) if (ret < 0) { CH_ERR(adap, "failed to bind qsets, err %d\n", ret); t3_intr_disable(adap); + quiesce_rx(adap); free_irq_resources(adap); err = ret; goto out; diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c index 2820a0bb971bffbff848fd2b9de5ce467bc7c289..5e1e46425014c50210f3a35696d723ce6c1636f5 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c @@ -858,7 +858,7 @@ static int cxgb4vf_open(struct net_device *dev) */ err = t4vf_update_port_info(pi); if (err < 0) - return err; + goto err_unwind; /* * Note that this interface is up and start everything up ... diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index 4af25382595763de99fc095af97c022b45d915aa..975762ccb66fd0edf4561feeeb7f47d7f35f1b91 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -1212,7 +1212,7 @@ static void enetc_setup_txbdr(struct enetc_hw *hw, struct enetc_bdr *tx_ring) /* enable Tx ints by setting pkt thr to 1 */ enetc_txbdr_wr(hw, idx, ENETC_TBICR0, ENETC_TBICR0_ICEN | 0x1); - tbmr = ENETC_TBMR_EN; + tbmr = ENETC_TBMR_EN | ENETC_TBMR_SET_PRIO(tx_ring->prio); if (tx_ring->ndev->features & NETIF_F_HW_VLAN_CTAG_TX) tbmr |= ENETC_TBMR_VIH; @@ -1241,7 +1241,12 @@ static void enetc_setup_rxbdr(struct enetc_hw *hw, struct enetc_bdr *rx_ring) enetc_rxbdr_wr(hw, idx, ENETC_RBBSR, ENETC_RXB_DMA_SIZE); + /* Also prepare the consumer index in case page allocation never + * succeeds. In that case, hardware will never advance producer index + * to match consumer index, and will drop all frames. + */ enetc_rxbdr_wr(hw, idx, ENETC_RBPIR, 0); + enetc_rxbdr_wr(hw, idx, ENETC_RBCIR, 1); /* enable Rx ints by setting pkt thr to 1 */ enetc_rxbdr_wr(hw, idx, ENETC_RBICR0, ENETC_RBICR0_ICEN | 0x1); @@ -1267,13 +1272,14 @@ static void enetc_setup_rxbdr(struct enetc_hw *hw, struct enetc_bdr *rx_ring) static void enetc_setup_bdrs(struct enetc_ndev_priv *priv) { + struct enetc_hw *hw = &priv->si->hw; int i; for (i = 0; i < priv->num_tx_rings; i++) - enetc_setup_txbdr(&priv->si->hw, priv->tx_ring[i]); + enetc_setup_txbdr(hw, priv->tx_ring[i]); for (i = 0; i < priv->num_rx_rings; i++) - enetc_setup_rxbdr(&priv->si->hw, priv->rx_ring[i]); + enetc_setup_rxbdr(hw, priv->rx_ring[i]); } static void enetc_clear_rxbdr(struct enetc_hw *hw, struct enetc_bdr *rx_ring) @@ -1306,13 +1312,14 @@ static void enetc_clear_txbdr(struct enetc_hw *hw, struct enetc_bdr *tx_ring) static void enetc_clear_bdrs(struct enetc_ndev_priv *priv) { + struct enetc_hw *hw = &priv->si->hw; int i; for (i = 0; i < priv->num_tx_rings; i++) - enetc_clear_txbdr(&priv->si->hw, priv->tx_ring[i]); + enetc_clear_txbdr(hw, priv->tx_ring[i]); for (i = 0; i < priv->num_rx_rings; i++) - enetc_clear_rxbdr(&priv->si->hw, priv->rx_ring[i]); + enetc_clear_rxbdr(hw, priv->rx_ring[i]); udelay(1); } @@ -1320,13 +1327,13 @@ static void enetc_clear_bdrs(struct enetc_ndev_priv *priv) static int enetc_setup_irqs(struct enetc_ndev_priv *priv) { struct pci_dev *pdev = priv->si->pdev; + struct enetc_hw *hw = &priv->si->hw; int i, j, err; for (i = 0; i < priv->bdr_int_num; i++) { int irq = pci_irq_vector(pdev, ENETC_BDR_INT_BASE_IDX + i); struct enetc_int_vector *v = priv->int_vector[i]; int entry = ENETC_BDR_INT_BASE_IDX + i; - struct enetc_hw *hw = &priv->si->hw; snprintf(v->name, sizeof(v->name), "%s-rxtx%d", priv->ndev->name, i); @@ -1414,13 +1421,14 @@ static void enetc_setup_interrupts(struct enetc_ndev_priv *priv) static void enetc_clear_interrupts(struct enetc_ndev_priv *priv) { + struct enetc_hw *hw = &priv->si->hw; int i; for (i = 0; i < priv->num_tx_rings; i++) - enetc_txbdr_wr(&priv->si->hw, i, ENETC_TBIER, 0); + enetc_txbdr_wr(hw, i, ENETC_TBIER, 0); for (i = 0; i < priv->num_rx_rings; i++) - enetc_rxbdr_wr(&priv->si->hw, i, ENETC_RBIER, 0); + enetc_rxbdr_wr(hw, i, ENETC_RBIER, 0); } static int enetc_phylink_connect(struct net_device *ndev) @@ -1560,6 +1568,7 @@ static int enetc_setup_tc_mqprio(struct net_device *ndev, void *type_data) { struct enetc_ndev_priv *priv = netdev_priv(ndev); struct tc_mqprio_qopt *mqprio = type_data; + struct enetc_hw *hw = &priv->si->hw; struct enetc_bdr *tx_ring; u8 num_tc; int i; @@ -1574,7 +1583,8 @@ static int enetc_setup_tc_mqprio(struct net_device *ndev, void *type_data) /* Reset all ring priorities to 0 */ for (i = 0; i < priv->num_tx_rings; i++) { tx_ring = priv->tx_ring[i]; - enetc_set_bdr_prio(&priv->si->hw, tx_ring->index, 0); + tx_ring->prio = 0; + enetc_set_bdr_prio(hw, tx_ring->index, tx_ring->prio); } return 0; @@ -1593,7 +1603,8 @@ static int enetc_setup_tc_mqprio(struct net_device *ndev, void *type_data) */ for (i = 0; i < num_tc; i++) { tx_ring = priv->tx_ring[i]; - enetc_set_bdr_prio(&priv->si->hw, tx_ring->index, i); + tx_ring->prio = i; + enetc_set_bdr_prio(hw, tx_ring->index, tx_ring->prio); } /* Reset the number of netdev queues based on the TC count */ @@ -1674,19 +1685,21 @@ static int enetc_set_rss(struct net_device *ndev, int en) static void enetc_enable_rxvlan(struct net_device *ndev, bool en) { struct enetc_ndev_priv *priv = netdev_priv(ndev); + struct enetc_hw *hw = &priv->si->hw; int i; for (i = 0; i < priv->num_rx_rings; i++) - enetc_bdr_enable_rxvlan(&priv->si->hw, i, en); + enetc_bdr_enable_rxvlan(hw, i, en); } static void enetc_enable_txvlan(struct net_device *ndev, bool en) { struct enetc_ndev_priv *priv = netdev_priv(ndev); + struct enetc_hw *hw = &priv->si->hw; int i; for (i = 0; i < priv->num_tx_rings; i++) - enetc_bdr_enable_txvlan(&priv->si->hw, i, en); + enetc_bdr_enable_txvlan(hw, i, en); } void enetc_set_features(struct net_device *ndev, netdev_features_t features) diff --git a/drivers/net/ethernet/freescale/enetc/enetc.h b/drivers/net/ethernet/freescale/enetc/enetc.h index 00386c5d3cde93e41c1c723f29f0b092f4ee7d0e..725c3d1cbb1982cbac50d7b7b920f998f3446e82 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.h +++ b/drivers/net/ethernet/freescale/enetc/enetc.h @@ -58,6 +58,7 @@ struct enetc_bdr { void __iomem *rcir; }; u16 index; + u16 prio; int bd_count; /* # of BDs */ int next_to_use; int next_to_clean; @@ -338,19 +339,20 @@ int enetc_set_psfp(struct net_device *ndev, bool en); static inline void enetc_get_max_cap(struct enetc_ndev_priv *priv) { + struct enetc_hw *hw = &priv->si->hw; u32 reg; - reg = enetc_port_rd(&priv->si->hw, ENETC_PSIDCAPR); + reg = enetc_port_rd(hw, ENETC_PSIDCAPR); priv->psfp_cap.max_streamid = reg & ENETC_PSIDCAPR_MSK; /* Port stream filter capability */ - reg = enetc_port_rd(&priv->si->hw, ENETC_PSFCAPR); + reg = enetc_port_rd(hw, ENETC_PSFCAPR); priv->psfp_cap.max_psfp_filter = reg & ENETC_PSFCAPR_MSK; /* Port stream gate capability */ - reg = enetc_port_rd(&priv->si->hw, ENETC_PSGCAPR); + reg = enetc_port_rd(hw, ENETC_PSGCAPR); priv->psfp_cap.max_psfp_gate = (reg & ENETC_PSGCAPR_SGIT_MSK); priv->psfp_cap.max_psfp_gatelist = (reg & ENETC_PSGCAPR_GCL_MSK) >> 16; /* Port flow meter capability */ - reg = enetc_port_rd(&priv->si->hw, ENETC_PFMCAPR); + reg = enetc_port_rd(hw, ENETC_PFMCAPR); priv->psfp_cap.max_psfp_meter = reg & ENETC_PFMCAPR_MSK; } diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c index 6904e10dd46b32076d4a4a14b3bcad27251961a1..515db7e6e6497fe64a00ee4d8a724ab8b59ba1ca 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c @@ -748,9 +748,6 @@ static void enetc_pf_netdev_setup(struct enetc_si *si, struct net_device *ndev, ndev->priv_flags |= IFF_UNICAST_FLT; - if (si->hw_features & ENETC_SI_F_QBV) - priv->active_offloads |= ENETC_F_QBV; - if (si->hw_features & ENETC_SI_F_PSFP && !enetc_psfp_enable(priv)) { priv->active_offloads |= ENETC_F_QCI; ndev->features |= NETIF_F_HW_TC; @@ -996,7 +993,8 @@ static void enetc_pl_mac_link_up(struct phylink_config *config, struct enetc_ndev_priv *priv; priv = netdev_priv(pf->si->ndev); - if (priv->active_offloads & ENETC_F_QBV) + + if (pf->si->hw_features & ENETC_SI_F_QBV) enetc_sched_speed_set(priv, speed); if (!phylink_autoneg_inband(mode) && diff --git a/drivers/net/ethernet/freescale/enetc/enetc_qos.c b/drivers/net/ethernet/freescale/enetc/enetc_qos.c index 62efe1aebf86a48c7c2f81cde4ad7288382dec99..5841721c8119086f900f9a64bde71e76c451b3f7 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_qos.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_qos.c @@ -17,8 +17,9 @@ static u16 enetc_get_max_gcl_len(struct enetc_hw *hw) void enetc_sched_speed_set(struct enetc_ndev_priv *priv, int speed) { + struct enetc_hw *hw = &priv->si->hw; u32 old_speed = priv->speed; - u32 pspeed; + u32 pspeed, tmp; if (speed == old_speed) return; @@ -39,16 +40,15 @@ void enetc_sched_speed_set(struct enetc_ndev_priv *priv, int speed) } priv->speed = speed; - enetc_port_wr(&priv->si->hw, ENETC_PMR, - (enetc_port_rd(&priv->si->hw, ENETC_PMR) - & (~ENETC_PMR_PSPEED_MASK)) - | pspeed); + tmp = enetc_port_rd(hw, ENETC_PMR); + enetc_port_wr(hw, ENETC_PMR, (tmp & ~ENETC_PMR_PSPEED_MASK) | pspeed); } static int enetc_setup_taprio(struct net_device *ndev, struct tc_taprio_qopt_offload *admin_conf) { struct enetc_ndev_priv *priv = netdev_priv(ndev); + struct enetc_hw *hw = &priv->si->hw; struct enetc_cbd cbd = {.cmd = 0}; struct tgs_gcl_conf *gcl_config; struct tgs_gcl_data *gcl_data; @@ -60,15 +60,16 @@ static int enetc_setup_taprio(struct net_device *ndev, int err; int i; - if (admin_conf->num_entries > enetc_get_max_gcl_len(&priv->si->hw)) + if (admin_conf->num_entries > enetc_get_max_gcl_len(hw)) return -EINVAL; gcl_len = admin_conf->num_entries; - tge = enetc_rd(&priv->si->hw, ENETC_QBV_PTGCR_OFFSET); + tge = enetc_rd(hw, ENETC_QBV_PTGCR_OFFSET); if (!admin_conf->enable) { - enetc_wr(&priv->si->hw, - ENETC_QBV_PTGCR_OFFSET, - tge & (~ENETC_QBV_TGE)); + enetc_wr(hw, ENETC_QBV_PTGCR_OFFSET, tge & ~ENETC_QBV_TGE); + + priv->active_offloads &= ~ENETC_F_QBV; + return 0; } @@ -123,18 +124,18 @@ static int enetc_setup_taprio(struct net_device *ndev, cbd.cls = BDCR_CMD_PORT_GCL; cbd.status_flags = 0; - enetc_wr(&priv->si->hw, ENETC_QBV_PTGCR_OFFSET, - tge | ENETC_QBV_TGE); + enetc_wr(hw, ENETC_QBV_PTGCR_OFFSET, tge | ENETC_QBV_TGE); err = enetc_send_cmd(priv->si, &cbd); if (err) - enetc_wr(&priv->si->hw, - ENETC_QBV_PTGCR_OFFSET, - tge & (~ENETC_QBV_TGE)); + enetc_wr(hw, ENETC_QBV_PTGCR_OFFSET, tge & ~ENETC_QBV_TGE); dma_unmap_single(&priv->si->pdev->dev, dma, data_size, DMA_TO_DEVICE); kfree(gcl_data); + if (!err) + priv->active_offloads |= ENETC_F_QBV; + return err; } @@ -142,6 +143,8 @@ int enetc_setup_tc_taprio(struct net_device *ndev, void *type_data) { struct tc_taprio_qopt_offload *taprio = type_data; struct enetc_ndev_priv *priv = netdev_priv(ndev); + struct enetc_hw *hw = &priv->si->hw; + struct enetc_bdr *tx_ring; int err; int i; @@ -150,18 +153,20 @@ int enetc_setup_tc_taprio(struct net_device *ndev, void *type_data) if (priv->tx_ring[i]->tsd_enable) return -EBUSY; - for (i = 0; i < priv->num_tx_rings; i++) - enetc_set_bdr_prio(&priv->si->hw, - priv->tx_ring[i]->index, - taprio->enable ? i : 0); + for (i = 0; i < priv->num_tx_rings; i++) { + tx_ring = priv->tx_ring[i]; + tx_ring->prio = taprio->enable ? i : 0; + enetc_set_bdr_prio(hw, tx_ring->index, tx_ring->prio); + } err = enetc_setup_taprio(ndev, taprio); - - if (err) - for (i = 0; i < priv->num_tx_rings; i++) - enetc_set_bdr_prio(&priv->si->hw, - priv->tx_ring[i]->index, - taprio->enable ? 0 : i); + if (err) { + for (i = 0; i < priv->num_tx_rings; i++) { + tx_ring = priv->tx_ring[i]; + tx_ring->prio = taprio->enable ? 0 : i; + enetc_set_bdr_prio(hw, tx_ring->index, tx_ring->prio); + } + } return err; } @@ -182,7 +187,7 @@ int enetc_setup_tc_cbs(struct net_device *ndev, void *type_data) struct tc_cbs_qopt_offload *cbs = type_data; u32 port_transmit_rate = priv->speed; u8 tc_nums = netdev_get_num_tc(ndev); - struct enetc_si *si = priv->si; + struct enetc_hw *hw = &priv->si->hw; u32 hi_credit_bit, hi_credit_reg; u32 max_interference_size; u32 port_frame_max_size; @@ -203,15 +208,15 @@ int enetc_setup_tc_cbs(struct net_device *ndev, void *type_data) * lower than this TC have been disabled. */ if (tc == prio_top && - enetc_get_cbs_enable(&si->hw, prio_next)) { + enetc_get_cbs_enable(hw, prio_next)) { dev_err(&ndev->dev, "Disable TC%d before disable TC%d\n", prio_next, tc); return -EINVAL; } - enetc_port_wr(&si->hw, ENETC_PTCCBSR1(tc), 0); - enetc_port_wr(&si->hw, ENETC_PTCCBSR0(tc), 0); + enetc_port_wr(hw, ENETC_PTCCBSR1(tc), 0); + enetc_port_wr(hw, ENETC_PTCCBSR0(tc), 0); return 0; } @@ -228,13 +233,13 @@ int enetc_setup_tc_cbs(struct net_device *ndev, void *type_data) * higher than this TC have been enabled. */ if (tc == prio_next) { - if (!enetc_get_cbs_enable(&si->hw, prio_top)) { + if (!enetc_get_cbs_enable(hw, prio_top)) { dev_err(&ndev->dev, "Enable TC%d first before enable TC%d\n", prio_top, prio_next); return -EINVAL; } - bw_sum += enetc_get_cbs_bw(&si->hw, prio_top); + bw_sum += enetc_get_cbs_bw(hw, prio_top); } if (bw_sum + bw >= 100) { @@ -243,7 +248,7 @@ int enetc_setup_tc_cbs(struct net_device *ndev, void *type_data) return -EINVAL; } - enetc_port_rd(&si->hw, ENETC_PTCMSDUR(tc)); + enetc_port_rd(hw, ENETC_PTCMSDUR(tc)); /* For top prio TC, the max_interfrence_size is maxSizedFrame. * @@ -263,8 +268,8 @@ int enetc_setup_tc_cbs(struct net_device *ndev, void *type_data) u32 m0, ma, r0, ra; m0 = port_frame_max_size * 8; - ma = enetc_port_rd(&si->hw, ENETC_PTCMSDUR(prio_top)) * 8; - ra = enetc_get_cbs_bw(&si->hw, prio_top) * + ma = enetc_port_rd(hw, ENETC_PTCMSDUR(prio_top)) * 8; + ra = enetc_get_cbs_bw(hw, prio_top) * port_transmit_rate * 10000ULL; r0 = port_transmit_rate * 1000000ULL; max_interference_size = m0 + ma + @@ -284,10 +289,10 @@ int enetc_setup_tc_cbs(struct net_device *ndev, void *type_data) hi_credit_reg = (u32)div_u64((ENETC_CLK * 100ULL) * hi_credit_bit, port_transmit_rate * 1000000ULL); - enetc_port_wr(&si->hw, ENETC_PTCCBSR1(tc), hi_credit_reg); + enetc_port_wr(hw, ENETC_PTCCBSR1(tc), hi_credit_reg); /* Set bw register and enable this traffic class */ - enetc_port_wr(&si->hw, ENETC_PTCCBSR0(tc), bw | ENETC_CBSE); + enetc_port_wr(hw, ENETC_PTCCBSR0(tc), bw | ENETC_CBSE); return 0; } @@ -297,6 +302,7 @@ int enetc_setup_tc_txtime(struct net_device *ndev, void *type_data) struct enetc_ndev_priv *priv = netdev_priv(ndev); struct tc_etf_qopt_offload *qopt = type_data; u8 tc_nums = netdev_get_num_tc(ndev); + struct enetc_hw *hw = &priv->si->hw; int tc; if (!tc_nums) @@ -312,12 +318,11 @@ int enetc_setup_tc_txtime(struct net_device *ndev, void *type_data) return -EBUSY; /* TSD and Qbv are mutually exclusive in hardware */ - if (enetc_rd(&priv->si->hw, ENETC_QBV_PTGCR_OFFSET) & ENETC_QBV_TGE) + if (enetc_rd(hw, ENETC_QBV_PTGCR_OFFSET) & ENETC_QBV_TGE) return -EBUSY; priv->tx_ring[tc]->tsd_enable = qopt->enable; - enetc_port_wr(&priv->si->hw, ENETC_PTCTSDR(tc), - qopt->enable ? ENETC_TSDE : 0); + enetc_port_wr(hw, ENETC_PTCTSDR(tc), qopt->enable ? ENETC_TSDE : 0); return 0; } diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index d8bdaf2e5365ca7d9c614b6ea9a08327c14aa2ed..686bb873125ccad7d41cd6ab4a2dea76539fc31a 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -623,7 +623,7 @@ fec_enet_txq_put_data_tso(struct fec_enet_priv_tx_q *txq, struct sk_buff *skb, dev_kfree_skb_any(skb); if (net_ratelimit()) netdev_err(ndev, "Tx DMA memory map failed\n"); - return NETDEV_TX_BUSY; + return NETDEV_TX_OK; } bdp->cbd_datlen = cpu_to_fec16(size); @@ -685,7 +685,7 @@ fec_enet_txq_put_hdr_tso(struct fec_enet_priv_tx_q *txq, dev_kfree_skb_any(skb); if (net_ratelimit()) netdev_err(ndev, "Tx DMA memory map failed\n"); - return NETDEV_TX_BUSY; + return NETDEV_TX_OK; } } @@ -2251,6 +2251,31 @@ static u32 fec_enet_register_offset[] = { IEEE_R_DROP, IEEE_R_FRAME_OK, IEEE_R_CRC, IEEE_R_ALIGN, IEEE_R_MACERR, IEEE_R_FDXFC, IEEE_R_OCTETS_OK }; +/* for i.MX6ul */ +static u32 fec_enet_register_offset_6ul[] = { + FEC_IEVENT, FEC_IMASK, FEC_R_DES_ACTIVE_0, FEC_X_DES_ACTIVE_0, + FEC_ECNTRL, FEC_MII_DATA, FEC_MII_SPEED, FEC_MIB_CTRLSTAT, FEC_R_CNTRL, + FEC_X_CNTRL, FEC_ADDR_LOW, FEC_ADDR_HIGH, FEC_OPD, FEC_TXIC0, FEC_RXIC0, + FEC_HASH_TABLE_HIGH, FEC_HASH_TABLE_LOW, FEC_GRP_HASH_TABLE_HIGH, + FEC_GRP_HASH_TABLE_LOW, FEC_X_WMRK, FEC_R_DES_START_0, + FEC_X_DES_START_0, FEC_R_BUFF_SIZE_0, FEC_R_FIFO_RSFL, FEC_R_FIFO_RSEM, + FEC_R_FIFO_RAEM, FEC_R_FIFO_RAFL, FEC_RACC, + RMON_T_DROP, RMON_T_PACKETS, RMON_T_BC_PKT, RMON_T_MC_PKT, + RMON_T_CRC_ALIGN, RMON_T_UNDERSIZE, RMON_T_OVERSIZE, RMON_T_FRAG, + RMON_T_JAB, RMON_T_COL, RMON_T_P64, RMON_T_P65TO127, RMON_T_P128TO255, + RMON_T_P256TO511, RMON_T_P512TO1023, RMON_T_P1024TO2047, + RMON_T_P_GTE2048, RMON_T_OCTETS, + IEEE_T_DROP, IEEE_T_FRAME_OK, IEEE_T_1COL, IEEE_T_MCOL, IEEE_T_DEF, + IEEE_T_LCOL, IEEE_T_EXCOL, IEEE_T_MACERR, IEEE_T_CSERR, IEEE_T_SQE, + IEEE_T_FDXFC, IEEE_T_OCTETS_OK, + RMON_R_PACKETS, RMON_R_BC_PKT, RMON_R_MC_PKT, RMON_R_CRC_ALIGN, + RMON_R_UNDERSIZE, RMON_R_OVERSIZE, RMON_R_FRAG, RMON_R_JAB, + RMON_R_RESVD_O, RMON_R_P64, RMON_R_P65TO127, RMON_R_P128TO255, + RMON_R_P256TO511, RMON_R_P512TO1023, RMON_R_P1024TO2047, + RMON_R_P_GTE2048, RMON_R_OCTETS, + IEEE_R_DROP, IEEE_R_FRAME_OK, IEEE_R_CRC, IEEE_R_ALIGN, IEEE_R_MACERR, + IEEE_R_FDXFC, IEEE_R_OCTETS_OK +}; #else static __u32 fec_enet_register_version = 1; static u32 fec_enet_register_offset[] = { @@ -2275,7 +2300,24 @@ static void fec_enet_get_regs(struct net_device *ndev, u32 *buf = (u32 *)regbuf; u32 i, off; int ret; +#if defined(CONFIG_M523x) || defined(CONFIG_M527x) || defined(CONFIG_M528x) || \ + defined(CONFIG_M520x) || defined(CONFIG_M532x) || defined(CONFIG_ARM) || \ + defined(CONFIG_ARM64) || defined(CONFIG_COMPILE_TEST) + u32 *reg_list; + u32 reg_cnt; + if (!of_machine_is_compatible("fsl,imx6ul")) { + reg_list = fec_enet_register_offset; + reg_cnt = ARRAY_SIZE(fec_enet_register_offset); + } else { + reg_list = fec_enet_register_offset_6ul; + reg_cnt = ARRAY_SIZE(fec_enet_register_offset_6ul); + } +#else + /* coldfire */ + static u32 *reg_list = fec_enet_register_offset; + static const u32 reg_cnt = ARRAY_SIZE(fec_enet_register_offset); +#endif ret = pm_runtime_resume_and_get(dev); if (ret < 0) return; @@ -2284,8 +2326,8 @@ static void fec_enet_get_regs(struct net_device *ndev, memset(buf, 0, regs->len); - for (i = 0; i < ARRAY_SIZE(fec_enet_register_offset); i++) { - off = fec_enet_register_offset[i]; + for (i = 0; i < reg_cnt; i++) { + off = reg_list[i]; if ((off == FEC_R_BOUND || off == FEC_R_FSTART) && !(fep->quirks & FEC_QUIRK_HAS_FRREG)) diff --git a/drivers/net/ethernet/freescale/fman/mac.c b/drivers/net/ethernet/freescale/fman/mac.c index 6eeccc11b76efc4381aa38b83461e5410ff957c9..3312dc4083a08e4a05b6ccf1f536a8b8973e69b8 100644 --- a/drivers/net/ethernet/freescale/fman/mac.c +++ b/drivers/net/ethernet/freescale/fman/mac.c @@ -884,12 +884,21 @@ _return: return err; } +static int mac_remove(struct platform_device *pdev) +{ + struct mac_device *mac_dev = platform_get_drvdata(pdev); + + platform_device_unregister(mac_dev->priv->eth_dev); + return 0; +} + static struct platform_driver mac_driver = { .driver = { .name = KBUILD_MODNAME, .of_match_table = mac_match, }, .probe = mac_probe, + .remove = mac_remove, }; builtin_platform_driver(mac_driver); diff --git a/drivers/net/ethernet/freescale/fs_enet/mac-fec.c b/drivers/net/ethernet/freescale/fs_enet/mac-fec.c index 99fe2c210d0f6a52f5a549c256872ee6e4c4d52c..61f4b6e50d29b2ef9f43679c19dab447b4e4dec3 100644 --- a/drivers/net/ethernet/freescale/fs_enet/mac-fec.c +++ b/drivers/net/ethernet/freescale/fs_enet/mac-fec.c @@ -98,7 +98,7 @@ static int do_pd_setup(struct fs_enet_private *fep) return -EINVAL; fep->fec.fecp = of_iomap(ofdev->dev.of_node, 0); - if (!fep->fcc.fccp) + if (!fep->fec.fecp) return -EINVAL; return 0; diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.c b/drivers/net/ethernet/hisilicon/hns/hnae.c index 00fafc0f85121566e33cc7791ded1d9440b629c7..430eccea8e5e96ae0009ddfe927b744ac2e10ba5 100644 --- a/drivers/net/ethernet/hisilicon/hns/hnae.c +++ b/drivers/net/ethernet/hisilicon/hns/hnae.c @@ -419,8 +419,10 @@ int hnae_ae_register(struct hnae_ae_dev *hdev, struct module *owner) hdev->cls_dev.release = hnae_release; (void)dev_set_name(&hdev->cls_dev, "hnae%d", hdev->id); ret = device_register(&hdev->cls_dev); - if (ret) + if (ret) { + put_device(&hdev->cls_dev); return ret; + } __module_get(THIS_MODULE); diff --git a/drivers/net/ethernet/huawei/hinic/hinic_debugfs.c b/drivers/net/ethernet/huawei/hinic/hinic_debugfs.c index 19eb839177ec2fe67643d676b2a3d9b14f448031..061952c6c21a497d57173db42dfb391d63dbf776 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_debugfs.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_debugfs.c @@ -85,6 +85,7 @@ static int hinic_dbg_get_func_table(struct hinic_dev *nic_dev, int idx) struct tag_sml_funcfg_tbl *funcfg_table_elem; struct hinic_cmd_lt_rd *read_data; u16 out_size = sizeof(*read_data); + int ret = ~0; int err; read_data = kzalloc(sizeof(*read_data), GFP_KERNEL); @@ -111,20 +112,25 @@ static int hinic_dbg_get_func_table(struct hinic_dev *nic_dev, int idx) switch (idx) { case VALID: - return funcfg_table_elem->dw0.bs.valid; + ret = funcfg_table_elem->dw0.bs.valid; + break; case RX_MODE: - return funcfg_table_elem->dw0.bs.nic_rx_mode; + ret = funcfg_table_elem->dw0.bs.nic_rx_mode; + break; case MTU: - return funcfg_table_elem->dw1.bs.mtu; + ret = funcfg_table_elem->dw1.bs.mtu; + break; case RQ_DEPTH: - return funcfg_table_elem->dw13.bs.cfg_rq_depth; + ret = funcfg_table_elem->dw13.bs.cfg_rq_depth; + break; case QUEUE_NUM: - return funcfg_table_elem->dw13.bs.cfg_q_num; + ret = funcfg_table_elem->dw13.bs.cfg_q_num; + break; } kfree(read_data); - return ~0; + return ret; } static ssize_t hinic_dbg_cmd_read(struct file *filp, char __user *buffer, size_t count, diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.c index 21b8235952d333b6d412ca783024c24603233c73..dff979f5d08b5d11855eebd930f7b72c1256c35b 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.c @@ -929,7 +929,7 @@ int hinic_init_cmdqs(struct hinic_cmdqs *cmdqs, struct hinic_hwif *hwif, err_set_cmdq_depth: hinic_ceq_unregister_cb(&func_to_io->ceqs, HINIC_CEQ_CMDQ); - + free_cmdq(&cmdqs->cmdq[HINIC_CMDQ_SYNC]); err_cmdq_ctxt: hinic_wqs_cmdq_free(&cmdqs->cmdq_pages, cmdqs->saved_wqs, HINIC_MAX_CMDQ_TYPES); diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c index 799b85c88eff876112527aab95ef72f82e1edb77..bcf2476512a5a2d87e02d0eee0e1dbded8ce050f 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c @@ -892,7 +892,7 @@ int hinic_set_interrupt_cfg(struct hinic_hwdev *hwdev, if (err) return -EINVAL; - interrupt_info->lli_credit_cnt = temp_info.lli_timer_cnt; + interrupt_info->lli_credit_cnt = temp_info.lli_credit_cnt; interrupt_info->lli_timer_cnt = temp_info.lli_timer_cnt; err = hinic_msg_to_mgmt(&pfhwdev->pf_to_mgmt, HINIC_MOD_COMM, diff --git a/drivers/net/ethernet/huawei/hinic/hinic_main.c b/drivers/net/ethernet/huawei/hinic/hinic_main.c index 4f1d585485d7ac74370438d5c925d49ac2a37a01..6ec042d48cd1f35a2fa34c179e757a707be640c2 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_main.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_main.c @@ -1502,8 +1502,15 @@ static struct pci_driver hinic_driver = { static int __init hinic_module_init(void) { + int ret; + hinic_dbg_register_debugfs(HINIC_DRV_NAME); - return pci_register_driver(&hinic_driver); + + ret = pci_register_driver(&hinic_driver); + if (ret) + hinic_dbg_unregister_debugfs(); + + return ret; } static void __exit hinic_module_exit(void) diff --git a/drivers/net/ethernet/huawei/hinic/hinic_sriov.c b/drivers/net/ethernet/huawei/hinic/hinic_sriov.c index f8a26459ff653c528216f922d0e1a58f68cdfc4e..4d82ebfe27f934c2b3b05c335d7aba9d346680b1 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_sriov.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_sriov.c @@ -1178,7 +1178,6 @@ int hinic_vf_func_init(struct hinic_hwdev *hwdev) dev_err(&hwdev->hwif->pdev->dev, "Failed to register VF, err: %d, status: 0x%x, out size: 0x%x\n", err, register_info.status, out_size); - hinic_unregister_vf_mbox_cb(hwdev, HINIC_MOD_L2NIC); return -EIO; } } else { diff --git a/drivers/net/ethernet/ibm/ehea/ehea_main.c b/drivers/net/ethernet/ibm/ehea/ehea_main.c index f6306673642531625c0da663d9976312e1b29627..28a5f8d73a61476deba2970be31d638da4798ba6 100644 --- a/drivers/net/ethernet/ibm/ehea/ehea_main.c +++ b/drivers/net/ethernet/ibm/ehea/ehea_main.c @@ -2897,6 +2897,7 @@ static struct device *ehea_register_port(struct ehea_port *port, ret = of_device_register(&port->ofdev); if (ret) { pr_err("failed to register device. ret=%d\n", ret); + put_device(&port->ofdev.dev); goto out; } diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index 63054061966e653bdea853943f480a0d12fd49b3..144c4824b5e8017bfc7c4628097121d998f21f51 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -2081,9 +2081,6 @@ static int i40e_set_ringparam(struct net_device *netdev, */ rx_rings[i].tail = hw->hw_addr + I40E_PRTGEN_STATUS; err = i40e_setup_rx_descriptors(&rx_rings[i]); - if (err) - goto rx_unwind; - err = i40e_alloc_rx_bi(&rx_rings[i]); if (err) goto rx_unwind; @@ -3086,10 +3083,17 @@ static int i40e_get_rss_hash_opts(struct i40e_pf *pf, struct ethtool_rxnfc *cmd) if (cmd->flow_type == TCP_V4_FLOW || cmd->flow_type == UDP_V4_FLOW) { - if (i_set & I40E_L3_SRC_MASK) - cmd->data |= RXH_IP_SRC; - if (i_set & I40E_L3_DST_MASK) - cmd->data |= RXH_IP_DST; + if (hw->mac.type == I40E_MAC_X722) { + if (i_set & I40E_X722_L3_SRC_MASK) + cmd->data |= RXH_IP_SRC; + if (i_set & I40E_X722_L3_DST_MASK) + cmd->data |= RXH_IP_DST; + } else { + if (i_set & I40E_L3_SRC_MASK) + cmd->data |= RXH_IP_SRC; + if (i_set & I40E_L3_DST_MASK) + cmd->data |= RXH_IP_DST; + } } else if (cmd->flow_type == TCP_V6_FLOW || cmd->flow_type == UDP_V6_FLOW) { if (i_set & I40E_L3_V6_SRC_MASK) @@ -3396,12 +3400,15 @@ static int i40e_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd, /** * i40e_get_rss_hash_bits - Read RSS Hash bits from register + * @hw: hw structure * @nfc: pointer to user request * @i_setc: bits currently set * * Returns value of bits to be set per user request **/ -static u64 i40e_get_rss_hash_bits(struct ethtool_rxnfc *nfc, u64 i_setc) +static u64 i40e_get_rss_hash_bits(struct i40e_hw *hw, + struct ethtool_rxnfc *nfc, + u64 i_setc) { u64 i_set = i_setc; u64 src_l3 = 0, dst_l3 = 0; @@ -3420,8 +3427,13 @@ static u64 i40e_get_rss_hash_bits(struct ethtool_rxnfc *nfc, u64 i_setc) dst_l3 = I40E_L3_V6_DST_MASK; } else if (nfc->flow_type == TCP_V4_FLOW || nfc->flow_type == UDP_V4_FLOW) { - src_l3 = I40E_L3_SRC_MASK; - dst_l3 = I40E_L3_DST_MASK; + if (hw->mac.type == I40E_MAC_X722) { + src_l3 = I40E_X722_L3_SRC_MASK; + dst_l3 = I40E_X722_L3_DST_MASK; + } else { + src_l3 = I40E_L3_SRC_MASK; + dst_l3 = I40E_L3_DST_MASK; + } } else { /* Any other flow type are not supported here */ return i_set; @@ -3439,6 +3451,7 @@ static u64 i40e_get_rss_hash_bits(struct ethtool_rxnfc *nfc, u64 i_setc) return i_set; } +#define FLOW_PCTYPES_SIZE 64 /** * i40e_set_rss_hash_opt - Enable/Disable flow types for RSS hash * @pf: pointer to the physical function struct @@ -3451,9 +3464,11 @@ static int i40e_set_rss_hash_opt(struct i40e_pf *pf, struct ethtool_rxnfc *nfc) struct i40e_hw *hw = &pf->hw; u64 hena = (u64)i40e_read_rx_ctl(hw, I40E_PFQF_HENA(0)) | ((u64)i40e_read_rx_ctl(hw, I40E_PFQF_HENA(1)) << 32); - u8 flow_pctype = 0; + DECLARE_BITMAP(flow_pctypes, FLOW_PCTYPES_SIZE); u64 i_set, i_setc; + bitmap_zero(flow_pctypes, FLOW_PCTYPES_SIZE); + if (pf->flags & I40E_FLAG_MFP_ENABLED) { dev_err(&pf->pdev->dev, "Change of RSS hash input set is not supported when MFP mode is enabled\n"); @@ -3469,36 +3484,35 @@ static int i40e_set_rss_hash_opt(struct i40e_pf *pf, struct ethtool_rxnfc *nfc) switch (nfc->flow_type) { case TCP_V4_FLOW: - flow_pctype = I40E_FILTER_PCTYPE_NONF_IPV4_TCP; + set_bit(I40E_FILTER_PCTYPE_NONF_IPV4_TCP, flow_pctypes); if (pf->hw_features & I40E_HW_MULTIPLE_TCP_UDP_RSS_PCTYPE) - hena |= - BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_TCP_SYN_NO_ACK); + set_bit(I40E_FILTER_PCTYPE_NONF_IPV4_TCP_SYN_NO_ACK, + flow_pctypes); break; case TCP_V6_FLOW: - flow_pctype = I40E_FILTER_PCTYPE_NONF_IPV6_TCP; - if (pf->hw_features & I40E_HW_MULTIPLE_TCP_UDP_RSS_PCTYPE) - hena |= - BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_TCP_SYN_NO_ACK); + set_bit(I40E_FILTER_PCTYPE_NONF_IPV6_TCP, flow_pctypes); if (pf->hw_features & I40E_HW_MULTIPLE_TCP_UDP_RSS_PCTYPE) - hena |= - BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_TCP_SYN_NO_ACK); + set_bit(I40E_FILTER_PCTYPE_NONF_IPV6_TCP_SYN_NO_ACK, + flow_pctypes); break; case UDP_V4_FLOW: - flow_pctype = I40E_FILTER_PCTYPE_NONF_IPV4_UDP; - if (pf->hw_features & I40E_HW_MULTIPLE_TCP_UDP_RSS_PCTYPE) - hena |= - BIT_ULL(I40E_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP) | - BIT_ULL(I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP); - + set_bit(I40E_FILTER_PCTYPE_NONF_IPV4_UDP, flow_pctypes); + if (pf->hw_features & I40E_HW_MULTIPLE_TCP_UDP_RSS_PCTYPE) { + set_bit(I40E_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP, + flow_pctypes); + set_bit(I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP, + flow_pctypes); + } hena |= BIT_ULL(I40E_FILTER_PCTYPE_FRAG_IPV4); break; case UDP_V6_FLOW: - flow_pctype = I40E_FILTER_PCTYPE_NONF_IPV6_UDP; - if (pf->hw_features & I40E_HW_MULTIPLE_TCP_UDP_RSS_PCTYPE) - hena |= - BIT_ULL(I40E_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP) | - BIT_ULL(I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP); - + set_bit(I40E_FILTER_PCTYPE_NONF_IPV6_UDP, flow_pctypes); + if (pf->hw_features & I40E_HW_MULTIPLE_TCP_UDP_RSS_PCTYPE) { + set_bit(I40E_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP, + flow_pctypes); + set_bit(I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP, + flow_pctypes); + } hena |= BIT_ULL(I40E_FILTER_PCTYPE_FRAG_IPV6); break; case AH_ESP_V4_FLOW: @@ -3531,17 +3545,20 @@ static int i40e_set_rss_hash_opt(struct i40e_pf *pf, struct ethtool_rxnfc *nfc) return -EINVAL; } - if (flow_pctype) { - i_setc = (u64)i40e_read_rx_ctl(hw, I40E_GLQF_HASH_INSET(0, - flow_pctype)) | - ((u64)i40e_read_rx_ctl(hw, I40E_GLQF_HASH_INSET(1, - flow_pctype)) << 32); - i_set = i40e_get_rss_hash_bits(nfc, i_setc); - i40e_write_rx_ctl(hw, I40E_GLQF_HASH_INSET(0, flow_pctype), - (u32)i_set); - i40e_write_rx_ctl(hw, I40E_GLQF_HASH_INSET(1, flow_pctype), - (u32)(i_set >> 32)); - hena |= BIT_ULL(flow_pctype); + if (bitmap_weight(flow_pctypes, FLOW_PCTYPES_SIZE)) { + u8 flow_id; + + for_each_set_bit(flow_id, flow_pctypes, FLOW_PCTYPES_SIZE) { + i_setc = (u64)i40e_read_rx_ctl(hw, I40E_GLQF_HASH_INSET(0, flow_id)) | + ((u64)i40e_read_rx_ctl(hw, I40E_GLQF_HASH_INSET(1, flow_id)) << 32); + i_set = i40e_get_rss_hash_bits(&pf->hw, nfc, i_setc); + + i40e_write_rx_ctl(hw, I40E_GLQF_HASH_INSET(0, flow_id), + (u32)i_set); + i40e_write_rx_ctl(hw, I40E_GLQF_HASH_INSET(1, flow_id), + (u32)(i_set >> 32)); + hena |= BIT_ULL(flow_id); + } } i40e_write_rx_ctl(hw, I40E_PFQF_HENA(0), (u32)hena); diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index c7f243ddbcf72fc6280706e1cbc4ef96adab456d..ea6a984c6d12b811101970fec92f681631fdea6c 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -3409,12 +3409,8 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring) if (ring->vsi->type == I40E_VSI_MAIN) xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq); - kfree(ring->rx_bi); ring->xsk_pool = i40e_xsk_pool(ring); if (ring->xsk_pool) { - ret = i40e_alloc_rx_bi_zc(ring); - if (ret) - return ret; ring->rx_buf_len = xsk_pool_get_rx_frame_size(ring->xsk_pool); /* For AF_XDP ZC, we disallow packets to span on @@ -3432,9 +3428,6 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring) ring->queue_index); } else { - ret = i40e_alloc_rx_bi(ring); - if (ret) - return ret; ring->rx_buf_len = vsi->rx_buf_len; if (ring->vsi->type == I40E_VSI_MAIN) { ret = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, @@ -12684,6 +12677,14 @@ static int i40e_xdp_setup(struct i40e_vsi *vsi, i40e_reset_and_rebuild(pf, true, true); } + if (!i40e_enabled_xdp_vsi(vsi) && prog) { + if (i40e_realloc_rx_bi_zc(vsi, true)) + return -ENOMEM; + } else if (i40e_enabled_xdp_vsi(vsi) && !prog) { + if (i40e_realloc_rx_bi_zc(vsi, false)) + return -ENOMEM; + } + for (i = 0; i < vsi->num_queue_pairs; i++) WRITE_ONCE(vsi->rx_rings[i]->xdp_prog, vsi->xdp_prog); @@ -12916,6 +12917,7 @@ int i40e_queue_pair_disable(struct i40e_vsi *vsi, int queue_pair) i40e_queue_pair_disable_irq(vsi, queue_pair); err = i40e_queue_pair_toggle_rings(vsi, queue_pair, false /* off */); + i40e_clean_rx_ring(vsi->rx_rings[queue_pair]); i40e_queue_pair_toggle_napi(vsi, queue_pair, false /* off */); i40e_queue_pair_clean_rings(vsi, queue_pair); i40e_queue_pair_reset_stats(vsi, queue_pair); diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 5ad28129fab2a0c07f219200b9fed88ccf91c634..43be33d87e3914ec92287efbe92130102f3d3035 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -1305,14 +1305,6 @@ err: return -ENOMEM; } -int i40e_alloc_rx_bi(struct i40e_ring *rx_ring) -{ - unsigned long sz = sizeof(*rx_ring->rx_bi) * rx_ring->count; - - rx_ring->rx_bi = kzalloc(sz, GFP_KERNEL); - return rx_ring->rx_bi ? 0 : -ENOMEM; -} - static void i40e_clear_rx_bi(struct i40e_ring *rx_ring) { memset(rx_ring->rx_bi, 0, sizeof(*rx_ring->rx_bi) * rx_ring->count); @@ -1443,6 +1435,11 @@ int i40e_setup_rx_descriptors(struct i40e_ring *rx_ring) rx_ring->xdp_prog = rx_ring->vsi->xdp_prog; + rx_ring->rx_bi = + kcalloc(rx_ring->count, sizeof(*rx_ring->rx_bi), GFP_KERNEL); + if (!rx_ring->rx_bi) + return -ENOMEM; + return 0; } diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h index 93ac201f68b8e0677d1c33acb7fe806d9b8a9956..af843e8169f7d10937019051fbb37d999b7950a5 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h @@ -465,7 +465,6 @@ int __i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size); bool __i40e_chk_linearize(struct sk_buff *skb); int i40e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, u32 flags); -int i40e_alloc_rx_bi(struct i40e_ring *rx_ring); /** * i40e_get_head - Retrieve head from head writeback diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h index 446672a7e39fb2b2a373b595a69fb6b67def9342..0872448c0e8045023f3243ce8f07992087bab5b8 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_type.h +++ b/drivers/net/ethernet/intel/i40e/i40e_type.h @@ -1404,6 +1404,10 @@ struct i40e_lldp_variables { #define I40E_PFQF_CTL_0_HASHLUTSIZE_512 0x00010000 /* INPUT SET MASK for RSS, flow director, and flexible payload */ +#define I40E_X722_L3_SRC_SHIFT 49 +#define I40E_X722_L3_SRC_MASK (0x3ULL << I40E_X722_L3_SRC_SHIFT) +#define I40E_X722_L3_DST_SHIFT 41 +#define I40E_X722_L3_DST_MASK (0x3ULL << I40E_X722_L3_DST_SHIFT) #define I40E_L3_SRC_SHIFT 47 #define I40E_L3_SRC_MASK (0x3ULL << I40E_L3_SRC_SHIFT) #define I40E_L3_V6_SRC_SHIFT 43 diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index ffff7de801af7ffec80515b4682afd5692edfece..381b28a087467a5b6e4c9d4352124501815d38fa 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -1483,10 +1483,12 @@ bool i40e_reset_vf(struct i40e_vf *vf, bool flr) if (test_bit(__I40E_VF_RESETS_DISABLED, pf->state)) return true; - /* If the VFs have been disabled, this means something else is - * resetting the VF, so we shouldn't continue. - */ - if (test_and_set_bit(__I40E_VF_DISABLE, pf->state)) + /* Bail out if VFs are disabled. */ + if (test_bit(__I40E_VF_DISABLE, pf->state)) + return true; + + /* If VF is being reset already we don't need to continue. */ + if (test_and_set_bit(I40E_VF_STATE_RESETTING, &vf->vf_states)) return true; i40e_trigger_vf_reset(vf, flr); @@ -1523,7 +1525,7 @@ bool i40e_reset_vf(struct i40e_vf *vf, bool flr) i40e_cleanup_reset_vf(vf); i40e_flush(hw); - clear_bit(__I40E_VF_DISABLE, pf->state); + clear_bit(I40E_VF_STATE_RESETTING, &vf->vf_states); return true; } @@ -1556,8 +1558,12 @@ bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr) return false; /* Begin reset on all VFs at once */ - for (v = 0; v < pf->num_alloc_vfs; v++) - i40e_trigger_vf_reset(&pf->vf[v], flr); + for (v = 0; v < pf->num_alloc_vfs; v++) { + vf = &pf->vf[v]; + /* If VF is being reset no need to trigger reset again */ + if (!test_bit(I40E_VF_STATE_RESETTING, &vf->vf_states)) + i40e_trigger_vf_reset(&pf->vf[v], flr); + } /* HW requires some time to make sure it can flush the FIFO for a VF * when it resets it. Poll the VPGEN_VFRSTAT register for each VF in @@ -1573,9 +1579,11 @@ bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr) */ while (v < pf->num_alloc_vfs) { vf = &pf->vf[v]; - reg = rd32(hw, I40E_VPGEN_VFRSTAT(vf->vf_id)); - if (!(reg & I40E_VPGEN_VFRSTAT_VFRD_MASK)) - break; + if (!test_bit(I40E_VF_STATE_RESETTING, &vf->vf_states)) { + reg = rd32(hw, I40E_VPGEN_VFRSTAT(vf->vf_id)); + if (!(reg & I40E_VPGEN_VFRSTAT_VFRD_MASK)) + break; + } /* If the current VF has finished resetting, move on * to the next VF in sequence. @@ -1603,6 +1611,10 @@ bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr) if (pf->vf[v].lan_vsi_idx == 0) continue; + /* If VF is reset in another thread just continue */ + if (test_bit(I40E_VF_STATE_RESETTING, &vf->vf_states)) + continue; + i40e_vsi_stop_rings_no_wait(pf->vsi[pf->vf[v].lan_vsi_idx]); } @@ -1614,6 +1626,10 @@ bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr) if (pf->vf[v].lan_vsi_idx == 0) continue; + /* If VF is reset in another thread just continue */ + if (test_bit(I40E_VF_STATE_RESETTING, &vf->vf_states)) + continue; + i40e_vsi_wait_queues_disabled(pf->vsi[pf->vf[v].lan_vsi_idx]); } @@ -1623,8 +1639,13 @@ bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr) mdelay(50); /* Finish the reset on each VF */ - for (v = 0; v < pf->num_alloc_vfs; v++) + for (v = 0; v < pf->num_alloc_vfs; v++) { + /* If VF is reset in another thread just continue */ + if (test_bit(I40E_VF_STATE_RESETTING, &vf->vf_states)) + continue; + i40e_cleanup_reset_vf(&pf->vf[v]); + } i40e_flush(hw); clear_bit(__I40E_VF_DISABLE, pf->state); diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h index a554d0a0b09bd56fb9904defd0a390df877cfa89..358bbdb5879511a581c2cebb54b74ff4f83a37a8 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h @@ -39,6 +39,7 @@ enum i40e_vf_states { I40E_VF_STATE_MC_PROMISC, I40E_VF_STATE_UC_PROMISC, I40E_VF_STATE_PRE_ENABLE, + I40E_VF_STATE_RESETTING }; /* VF capabilities */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c index 75e4a698c3db20b71140cb694cba11e031697f0d..7f12261236293a83bab4d97795039c424814d0e4 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c @@ -9,14 +9,6 @@ #include "i40e_txrx_common.h" #include "i40e_xsk.h" -int i40e_alloc_rx_bi_zc(struct i40e_ring *rx_ring) -{ - unsigned long sz = sizeof(*rx_ring->rx_bi_zc) * rx_ring->count; - - rx_ring->rx_bi_zc = kzalloc(sz, GFP_KERNEL); - return rx_ring->rx_bi_zc ? 0 : -ENOMEM; -} - void i40e_clear_rx_bi_zc(struct i40e_ring *rx_ring) { memset(rx_ring->rx_bi_zc, 0, @@ -28,6 +20,58 @@ static struct xdp_buff **i40e_rx_bi(struct i40e_ring *rx_ring, u32 idx) return &rx_ring->rx_bi_zc[idx]; } +/** + * i40e_realloc_rx_xdp_bi - reallocate SW ring for either XSK or normal buffer + * @rx_ring: Current rx ring + * @pool_present: is pool for XSK present + * + * Try allocating memory and return ENOMEM, if failed to allocate. + * If allocation was successful, substitute buffer with allocated one. + * Returns 0 on success, negative on failure + */ +static int i40e_realloc_rx_xdp_bi(struct i40e_ring *rx_ring, bool pool_present) +{ + size_t elem_size = pool_present ? sizeof(*rx_ring->rx_bi_zc) : + sizeof(*rx_ring->rx_bi); + void *sw_ring = kcalloc(rx_ring->count, elem_size, GFP_KERNEL); + + if (!sw_ring) + return -ENOMEM; + + if (pool_present) { + kfree(rx_ring->rx_bi); + rx_ring->rx_bi = NULL; + rx_ring->rx_bi_zc = sw_ring; + } else { + kfree(rx_ring->rx_bi_zc); + rx_ring->rx_bi_zc = NULL; + rx_ring->rx_bi = sw_ring; + } + return 0; +} + +/** + * i40e_realloc_rx_bi_zc - reallocate rx SW rings + * @vsi: Current VSI + * @zc: is zero copy set + * + * Reallocate buffer for rx_rings that might be used by XSK. + * XDP requires more memory, than rx_buf provides. + * Returns 0 on success, negative on failure + */ +int i40e_realloc_rx_bi_zc(struct i40e_vsi *vsi, bool zc) +{ + struct i40e_ring *rx_ring; + unsigned long q; + + for_each_set_bit(q, vsi->af_xdp_zc_qps, vsi->alloc_queue_pairs) { + rx_ring = vsi->rx_rings[q]; + if (i40e_realloc_rx_xdp_bi(rx_ring, zc)) + return -ENOMEM; + } + return 0; +} + /** * i40e_xsk_pool_enable - Enable/associate an AF_XDP buffer pool to a * certain ring/qid @@ -68,6 +112,10 @@ static int i40e_xsk_pool_enable(struct i40e_vsi *vsi, if (err) return err; + err = i40e_realloc_rx_xdp_bi(vsi->rx_rings[qid], true); + if (err) + return err; + err = i40e_queue_pair_enable(vsi, qid); if (err) return err; @@ -112,6 +160,9 @@ static int i40e_xsk_pool_disable(struct i40e_vsi *vsi, u16 qid) xsk_pool_dma_unmap(pool, I40E_RX_DMA_ATTR); if (if_running) { + err = i40e_realloc_rx_xdp_bi(vsi->rx_rings[qid], false); + if (err) + return err; err = i40e_queue_pair_enable(vsi, qid); if (err) return err; diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.h b/drivers/net/ethernet/intel/i40e/i40e_xsk.h index 7adfd8539247ccbb2aa01ae0754933e7b09b19c9..36f5b6d2060103c71a42ea01783bc4d133ba8f0f 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.h +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.h @@ -17,7 +17,7 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget); bool i40e_clean_xdp_tx_irq(struct i40e_vsi *vsi, struct i40e_ring *tx_ring); int i40e_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags); -int i40e_alloc_rx_bi_zc(struct i40e_ring *rx_ring); +int i40e_realloc_rx_bi_zc(struct i40e_vsi *vsi, bool zc); void i40e_clear_rx_bi_zc(struct i40e_ring *rx_ring); #endif /* _I40E_XSK_H_ */ diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 327196d15a6aef59d5c0fc8b8c99f579552db8a1..f24f1a8ec2fbc142fa809eefbfd1e855894afbbe 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -7416,7 +7416,7 @@ static void igb_vf_reset_msg(struct igb_adapter *adapter, u32 vf) { struct e1000_hw *hw = &adapter->hw; unsigned char *vf_mac = adapter->vf_data[vf].vf_mac_addresses; - u32 reg, msgbuf[3]; + u32 reg, msgbuf[3] = {}; u8 *addr = (u8 *)(&msgbuf[1]); /* process all the same items cleared in a function level reset */ diff --git a/drivers/net/ethernet/lantiq_etop.c b/drivers/net/ethernet/lantiq_etop.c index 2d0c52f7106bc028d9c7e594a54a6f133680b11c..5ea626b1e5783cfb733dbfa5dbc14d6f2a63f806 100644 --- a/drivers/net/ethernet/lantiq_etop.c +++ b/drivers/net/ethernet/lantiq_etop.c @@ -466,7 +466,6 @@ ltq_etop_tx(struct sk_buff *skb, struct net_device *dev) len = skb->len < ETH_ZLEN ? ETH_ZLEN : skb->len; if ((desc->ctl & (LTQ_DMA_OWN | LTQ_DMA_C)) || ch->skb[ch->dma.desc]) { - dev_kfree_skb_any(skb); netdev_err(dev, "tx ring full\n"); netif_tx_stop_queue(txq); return NETDEV_TX_BUSY; diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c index 90e6111ce534dba7f16de983549ade748890124c..735b76effc49220e61d8c7e6ac58ab9f796c366e 100644 --- a/drivers/net/ethernet/marvell/mv643xx_eth.c +++ b/drivers/net/ethernet/marvell/mv643xx_eth.c @@ -2471,6 +2471,7 @@ out_free: for (i = 0; i < mp->rxq_count; i++) rxq_deinit(mp->rxq + i); out: + napi_disable(&mp->napi); free_irq(dev->irq, dev); return err; diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h index d825eb021b22ef6154ee5f1960156cad078b17a7..e999ac2de34e8995da60cdb471e603f909560853 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h @@ -1434,6 +1434,7 @@ u32 mvpp2_read(struct mvpp2 *priv, u32 offset); void mvpp2_dbgfs_init(struct mvpp2 *priv, const char *name); void mvpp2_dbgfs_cleanup(struct mvpp2 *priv); +void mvpp2_dbgfs_exit(void); #ifdef CONFIG_MVPP2_PTP int mvpp22_tai_probe(struct device *dev, struct mvpp2 *priv); diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c index 4a3baa7e0142416d7ca15d9677362c9c29e5b986..75e83ea2a926e9ab57cd52aeb5f13da06ed87fd0 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c @@ -691,6 +691,13 @@ static int mvpp2_dbgfs_port_init(struct dentry *parent, return 0; } +static struct dentry *mvpp2_root; + +void mvpp2_dbgfs_exit(void) +{ + debugfs_remove(mvpp2_root); +} + void mvpp2_dbgfs_cleanup(struct mvpp2 *priv) { debugfs_remove_recursive(priv->dbgfs_dir); @@ -700,10 +707,9 @@ void mvpp2_dbgfs_cleanup(struct mvpp2 *priv) void mvpp2_dbgfs_init(struct mvpp2 *priv, const char *name) { - struct dentry *mvpp2_dir, *mvpp2_root; + struct dentry *mvpp2_dir; int ret, i; - mvpp2_root = debugfs_lookup(MVPP2_DRIVER_NAME, NULL); if (!mvpp2_root) mvpp2_root = debugfs_create_dir(MVPP2_DRIVER_NAME, NULL); diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index 542cd6f2c9bd45c0f46e4477bf087556a8bfa259..68c5ed8716c84a46504f6f0c4388629778ebed4d 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -7155,7 +7155,18 @@ static struct platform_driver mvpp2_driver = { }, }; -module_platform_driver(mvpp2_driver); +static int __init mvpp2_driver_init(void) +{ + return platform_driver_register(&mvpp2_driver); +} +module_init(mvpp2_driver_init); + +static void __exit mvpp2_driver_exit(void) +{ + platform_driver_unregister(&mvpp2_driver); + mvpp2_dbgfs_exit(); +} +module_exit(mvpp2_driver_exit); MODULE_DESCRIPTION("Marvell PPv2 Ethernet Driver - www.marvell.com"); MODULE_AUTHOR("Marcin Wojtas "); diff --git a/drivers/net/ethernet/marvell/prestera/prestera_rxtx.c b/drivers/net/ethernet/marvell/prestera/prestera_rxtx.c index 2a13c318048cc6ddc5292bb303ad84997686aa7a..59a3ea02b8add3c1df5b8558a2716392b50afe0f 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_rxtx.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_rxtx.c @@ -771,6 +771,7 @@ tx_done: int prestera_rxtx_switch_init(struct prestera_switch *sw) { struct prestera_rxtx *rxtx; + int err; rxtx = kzalloc(sizeof(*rxtx), GFP_KERNEL); if (!rxtx) @@ -778,7 +779,11 @@ int prestera_rxtx_switch_init(struct prestera_switch *sw) sw->rxtx = rxtx; - return prestera_sdma_switch_init(sw); + err = prestera_sdma_switch_init(sw); + if (err) + kfree(rxtx); + + return err; } void prestera_rxtx_switch_fini(struct prestera_switch *sw) diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index c7aff89141e175d615ff5ec7fb61bef332e34f75..217dc67c48fa247192b24f3de609fcf684bcff39 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -2299,7 +2299,10 @@ static int mtk_open(struct net_device *dev) int err = mtk_start_dma(eth); if (err) + if (err) { + phylink_disconnect_phy(mac->phylink); return err; + } mtk_gdm_config(eth, MTK_GDMA_TO_PDMA); diff --git a/drivers/net/ethernet/mellanox/mlx4/qp.c b/drivers/net/ethernet/mellanox/mlx4/qp.c index 427e7a31862c2a000bc51d068c7254e8e72a9e6a..d7f2890c254fe7c0a15fb160ae91d7d34b8d09be 100644 --- a/drivers/net/ethernet/mellanox/mlx4/qp.c +++ b/drivers/net/ethernet/mellanox/mlx4/qp.c @@ -697,7 +697,8 @@ static int mlx4_create_zones(struct mlx4_dev *dev, err = mlx4_bitmap_init(*bitmap + k, 1, MLX4_QP_TABLE_RAW_ETH_SIZE - 1, 0, 0); - mlx4_bitmap_alloc_range(*bitmap + k, 1, 1, 0); + if (!err) + mlx4_bitmap_alloc_range(*bitmap + k, 1, 1, 0); } if (err) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 94426d29025eb4e8a3bf2d6ea3b73d8445768453..c838d8698eab44dcb5d94e1ffa5fe01465b988ea 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -959,6 +959,7 @@ static void cmd_work_handler(struct work_struct *work) cmd_ent_get(ent); set_bit(MLX5_CMD_ENT_STATE_PENDING_COMP, &ent->state); + cmd_ent_get(ent); /* for the _real_ FW event on completion */ /* Skip sending command to fw if internal error */ if (mlx5_cmd_is_down(dev) || !opcode_allowed(&dev->cmd, ent->op)) { u8 status = 0; @@ -972,7 +973,6 @@ static void cmd_work_handler(struct work_struct *work) return; } - cmd_ent_get(ent); /* for the _real_ FW event on completion */ /* ring doorbell after the descriptor is valid */ mlx5_core_dbg(dev, "writing 0x%x to command doorbell\n", 1 << ent->idx); wmb(); @@ -1586,8 +1586,8 @@ static void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool force cmd_ent_put(ent); /* timeout work was canceled */ if (!forced || /* Real FW completion */ - pci_channel_offline(dev->pdev) || /* FW is inaccessible */ - dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) + mlx5_cmd_is_down(dev) || /* No real FW completion is expected */ + !opcode_allowed(cmd, ent->op)) cmd_ent_put(ent); ent->ts2 = ktime_get_ns(); @@ -1687,12 +1687,17 @@ void mlx5_cmd_flush(struct mlx5_core_dev *dev) struct mlx5_cmd *cmd = &dev->cmd; int i; - for (i = 0; i < cmd->max_reg_cmds; i++) - while (down_trylock(&cmd->sem)) + for (i = 0; i < cmd->max_reg_cmds; i++) { + while (down_trylock(&cmd->sem)) { mlx5_cmd_trigger_completions(dev); + cond_resched(); + } + } - while (down_trylock(&cmd->pages_sem)) + while (down_trylock(&cmd->pages_sem)) { mlx5_cmd_trigger_completions(dev); + cond_resched(); + } /* Unlock cmdif */ up(&cmd->pages_sem); @@ -1853,7 +1858,7 @@ void mlx5_cmd_init_async_ctx(struct mlx5_core_dev *dev, ctx->dev = dev; /* Starts at 1 to avoid doing wake_up if we are not cleaning up */ atomic_set(&ctx->num_inflight, 1); - init_waitqueue_head(&ctx->wait); + init_completion(&ctx->inflight_done); } EXPORT_SYMBOL(mlx5_cmd_init_async_ctx); @@ -1867,8 +1872,8 @@ EXPORT_SYMBOL(mlx5_cmd_init_async_ctx); */ void mlx5_cmd_cleanup_async_ctx(struct mlx5_async_ctx *ctx) { - atomic_dec(&ctx->num_inflight); - wait_event(ctx->wait, atomic_read(&ctx->num_inflight) == 0); + if (!atomic_dec_and_test(&ctx->num_inflight)) + wait_for_completion(&ctx->inflight_done); } EXPORT_SYMBOL(mlx5_cmd_cleanup_async_ctx); @@ -1879,7 +1884,7 @@ static void mlx5_cmd_exec_cb_handler(int status, void *_work) work->user_callback(status, work); if (atomic_dec_and_test(&ctx->num_inflight)) - wake_up(&ctx->wait); + complete(&ctx->inflight_done); } int mlx5_cmd_exec_cb(struct mlx5_async_ctx *ctx, void *in, int in_size, @@ -1895,7 +1900,7 @@ int mlx5_cmd_exec_cb(struct mlx5_async_ctx *ctx, void *in, int in_size, ret = cmd_exec(ctx->dev, in, in_size, out, out_size, mlx5_cmd_exec_cb_handler, work, false); if (ret && atomic_dec_and_test(&ctx->num_inflight)) - wake_up(&ctx->wait); + complete(&ctx->inflight_done); return ret; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c index e8a4adccd2b26f7c99d38eb6716ab24f9fd75f9f..f800e1ca5ba6263e21d9f9ab4743ee550e458bae 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c @@ -638,7 +638,7 @@ static void mlx5_tracer_handle_timestamp_trace(struct mlx5_fw_tracer *tracer, trace_timestamp = (timestamp_event.timestamp & MASK_52_7) | (str_frmt->timestamp & MASK_6_0); else - trace_timestamp = ((timestamp_event.timestamp & MASK_52_7) - 1) | + trace_timestamp = ((timestamp_event.timestamp - 1) & MASK_52_7) | (str_frmt->timestamp & MASK_6_0); mlx5_tracer_print_trace(str_frmt, dev, trace_timestamp); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c index 26f7fab109d9753f64ec12b51b8117a784b20d90..d08bd22dc5698ab0b94e9d9bd846f030207fbce1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c @@ -113,7 +113,6 @@ static bool mlx5e_ipsec_update_esn_state(struct mlx5e_ipsec_sa_entry *sa_entry) struct xfrm_replay_state_esn *replay_esn; u32 seq_bottom = 0; u8 overlap; - u32 *esn; if (!(sa_entry->x->props.flags & XFRM_STATE_ESN)) { sa_entry->esn_state.trigger = 0; @@ -128,11 +127,9 @@ static bool mlx5e_ipsec_update_esn_state(struct mlx5e_ipsec_sa_entry *sa_entry) sa_entry->esn_state.esn = xfrm_replay_seqhi(sa_entry->x, htonl(seq_bottom)); - esn = &sa_entry->esn_state.esn; sa_entry->esn_state.trigger = 1; if (unlikely(overlap && seq_bottom < MLX5E_IPSEC_ESN_SCOPE_MID)) { - ++(*esn); sa_entry->esn_state.overlap = 0; return true; } else if (unlikely(!overlap && diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c index 1cbb330b9f42b5fbcdf7ab2c6e7c28fbf62e4077..6c865cb7f445d7667f31102ff1235e89cfb3575d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c @@ -30,9 +30,9 @@ mlx5_eswitch_termtbl_hash(struct mlx5_flow_act *flow_act, sizeof(dest->vport.num), hash); hash = jhash((const void *)&dest->vport.vhca_id, sizeof(dest->vport.num), hash); - if (dest->vport.pkt_reformat) - hash = jhash(dest->vport.pkt_reformat, - sizeof(*dest->vport.pkt_reformat), + if (flow_act->pkt_reformat) + hash = jhash(flow_act->pkt_reformat, + sizeof(*flow_act->pkt_reformat), hash); return hash; } @@ -53,9 +53,11 @@ mlx5_eswitch_termtbl_cmp(struct mlx5_flow_act *flow_act1, if (ret) return ret; - return dest1->vport.pkt_reformat && dest2->vport.pkt_reformat ? - memcmp(dest1->vport.pkt_reformat, dest2->vport.pkt_reformat, - sizeof(*dest1->vport.pkt_reformat)) : 0; + if (flow_act1->pkt_reformat && flow_act2->pkt_reformat) + return memcmp(flow_act1->pkt_reformat, flow_act2->pkt_reformat, + sizeof(*flow_act1->pkt_reformat)); + + return !(flow_act1->pkt_reformat == flow_act2->pkt_reformat); } static int diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c index 839a01da110f34390a00f3e542d26ae8fd0a50c7..8ff16318e32dc922fa318712016deed2cb6e4900 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c @@ -122,7 +122,7 @@ void mlx5_mpfs_cleanup(struct mlx5_core_dev *dev) { struct mlx5_mpfs *mpfs = dev->priv.mpfs; - if (!MLX5_ESWITCH_MANAGER(dev)) + if (!mpfs) return; WARN_ON(!hlist_empty(mpfs->hash)); @@ -137,7 +137,7 @@ int mlx5_mpfs_add_mac(struct mlx5_core_dev *dev, u8 *mac) int err = 0; u32 index; - if (!MLX5_ESWITCH_MANAGER(dev)) + if (!mpfs) return 0; mutex_lock(&mpfs->lock); @@ -185,7 +185,7 @@ int mlx5_mpfs_del_mac(struct mlx5_core_dev *dev, u8 *mac) int err = 0; u32 index; - if (!MLX5_ESWITCH_MANAGER(dev)) + if (!mpfs) return 0; mutex_lock(&mpfs->lock); diff --git a/drivers/net/ethernet/micrel/ksz884x.c b/drivers/net/ethernet/micrel/ksz884x.c index 9ed264ed7070539d7c0c204999eaabf579ffd486..1fa16064142d9d659d4d05e5f0f194ba9a9e2237 100644 --- a/drivers/net/ethernet/micrel/ksz884x.c +++ b/drivers/net/ethernet/micrel/ksz884x.c @@ -6923,7 +6923,7 @@ static int pcidev_init(struct pci_dev *pdev, const struct pci_device_id *id) char banner[sizeof(version)]; struct ksz_switch *sw = NULL; - result = pci_enable_device(pdev); + result = pcim_enable_device(pdev); if (result) return result; diff --git a/drivers/net/ethernet/neterion/s2io.c b/drivers/net/ethernet/neterion/s2io.c index 3cae8449fadb7a6fe2753a791b6115e9056655b4..8a30be698f9924c0f8cf05edd012092b34883ad6 100644 --- a/drivers/net/ethernet/neterion/s2io.c +++ b/drivers/net/ethernet/neterion/s2io.c @@ -7114,9 +7114,8 @@ static int s2io_card_up(struct s2io_nic *sp) if (ret) { DBG_PRINT(ERR_DBG, "%s: Out of memory in Open\n", dev->name); - s2io_reset(sp); - free_rx_buffers(sp); - return -ENOMEM; + ret = -ENOMEM; + goto err_fill_buff; } DBG_PRINT(INFO_DBG, "Buf in ring:%d is %d:\n", i, ring->rx_bufs_left); @@ -7154,18 +7153,16 @@ static int s2io_card_up(struct s2io_nic *sp) /* Enable Rx Traffic and interrupts on the NIC */ if (start_nic(sp)) { DBG_PRINT(ERR_DBG, "%s: Starting NIC failed\n", dev->name); - s2io_reset(sp); - free_rx_buffers(sp); - return -ENODEV; + ret = -ENODEV; + goto err_out; } /* Add interrupt service routine */ if (s2io_add_isr(sp) != 0) { if (sp->config.intr_type == MSI_X) s2io_rem_isr(sp); - s2io_reset(sp); - free_rx_buffers(sp); - return -ENODEV; + ret = -ENODEV; + goto err_out; } timer_setup(&sp->alarm_timer, s2io_alarm_handle, 0); @@ -7185,6 +7182,20 @@ static int s2io_card_up(struct s2io_nic *sp) } return 0; + +err_out: + if (config->napi) { + if (config->intr_type == MSI_X) { + for (i = 0; i < sp->config.rx_ring_num; i++) + napi_disable(&sp->mac_control.rings[i].napi); + } else { + napi_disable(&sp->napi); + } + } +err_fill_buff: + s2io_reset(sp); + free_rx_buffers(sp); + return ret; } /** diff --git a/drivers/net/ethernet/netronome/nfp/nfp_devlink.c b/drivers/net/ethernet/netronome/nfp/nfp_devlink.c index 7a8187458724dbbd3addb5b38e3735b3dd60adfe..24578c48f075b35cfcd3c11caed703f4bf963dca 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_devlink.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_devlink.c @@ -363,7 +363,7 @@ int nfp_devlink_port_register(struct nfp_app *app, struct nfp_port *port) return ret; attrs.split = eth_port.is_split; - attrs.splittable = !attrs.split; + attrs.splittable = eth_port.port_lanes > 1 && !attrs.split; attrs.lanes = eth_port.port_lanes; attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL; attrs.phys.port_number = eth_port.label_port; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c index 3977aa2f59bd1681558e456ec31738c8cc837aa5..311873ff57e33117dd379d92a89b7362aa572d2b 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c @@ -1225,6 +1225,9 @@ nfp_port_get_module_info(struct net_device *netdev, u8 data; port = nfp_port_from_netdev(netdev); + if (!port) + return -EOPNOTSUPP; + /* update port state to get latest interface */ set_bit(NFP_PORT_CHANGED, &port->flags); eth_port = nfp_port_get_eth_port(port); diff --git a/drivers/net/ethernet/ni/nixge.c b/drivers/net/ethernet/ni/nixge.c index a6861df9904f9a2ea9034855fa71e2197c47032f..9c48fd85c418ac80c6f5bd36e2714d359bfadd1d 100644 --- a/drivers/net/ethernet/ni/nixge.c +++ b/drivers/net/ethernet/ni/nixge.c @@ -899,6 +899,7 @@ static int nixge_open(struct net_device *ndev) err_rx_irq: free_irq(priv->tx_irq, ndev); err_tx_irq: + napi_disable(&priv->napi); phy_stop(phy); phy_disconnect(phy); tasklet_kill(&priv->dma_err_tasklet); diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c index 2942102efd4884609a70218118f120e0883972dd..bde32f0845ca51b07fbe1f3b405232403d894552 100644 --- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c +++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c @@ -1166,6 +1166,7 @@ static void pch_gbe_tx_queue(struct pch_gbe_adapter *adapter, buffer_info->dma = 0; buffer_info->time_stamp = 0; tx_ring->next_to_use = ring_num; + dev_kfree_skb_any(skb); return; } buffer_info->mapped = true; @@ -2481,6 +2482,7 @@ static void pch_gbe_remove(struct pci_dev *pdev) unregister_netdev(netdev); pch_gbe_phy_hw_reset(&adapter->hw); + pci_dev_put(adapter->ptp_pdev); free_netdev(netdev); } @@ -2562,7 +2564,7 @@ static int pch_gbe_probe(struct pci_dev *pdev, /* setup the private structure */ ret = pch_gbe_sw_init(adapter); if (ret) - goto err_free_netdev; + goto err_put_dev; /* Initialize PHY */ ret = pch_gbe_init_phy(adapter); @@ -2620,6 +2622,8 @@ static int pch_gbe_probe(struct pci_dev *pdev, err_free_adapter: pch_gbe_phy_hw_reset(&adapter->hw); +err_put_dev: + pci_dev_put(adapter->ptp_pdev); err_free_netdev: free_netdev(netdev); return ret; diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index e42520f909fe23c6ae4734ed43e54b927482d72d..cb12d0171517e8a154ed1e488fff9a850cb23ee8 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -2383,11 +2383,15 @@ err_out: * than the full array, but leave the qcq shells in place */ for (i = lif->nxqs; i < lif->ionic->ntxqs_per_lif; i++) { - lif->txqcqs[i]->flags &= ~IONIC_QCQ_F_INTR; - ionic_qcq_free(lif, lif->txqcqs[i]); + if (lif->txqcqs && lif->txqcqs[i]) { + lif->txqcqs[i]->flags &= ~IONIC_QCQ_F_INTR; + ionic_qcq_free(lif, lif->txqcqs[i]); + } - lif->rxqcqs[i]->flags &= ~IONIC_QCQ_F_INTR; - ionic_qcq_free(lif, lif->rxqcqs[i]); + if (lif->rxqcqs && lif->rxqcqs[i]) { + lif->rxqcqs[i]->flags &= ~IONIC_QCQ_F_INTR; + ionic_qcq_free(lif, lif->rxqcqs[i]); + } } return err; diff --git a/drivers/net/ethernet/pensando/ionic/ionic_main.c b/drivers/net/ethernet/pensando/ionic/ionic_main.c index f60ffef33e0ce093167f5715b3cdbe8a3a38780d..00b6985edea0497bfc7b56fc37c6e5a4623ad725 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_main.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_main.c @@ -569,8 +569,14 @@ int ionic_port_reset(struct ionic *ionic) static int __init ionic_init_module(void) { + int ret; + ionic_debugfs_create(); - return ionic_bus_register_driver(); + ret = ionic_bus_register_driver(); + if (ret) + ionic_debugfs_destroy(); + + return ret; } static void __exit ionic_cleanup_module(void) diff --git a/drivers/net/ethernet/qlogic/qla3xxx.c b/drivers/net/ethernet/qlogic/qla3xxx.c index 2219e4c59ae602f7e9736f16d280c3eb6460df2a..99fd35a8ca750c67f8a5e467996aa0497f1de22c 100644 --- a/drivers/net/ethernet/qlogic/qla3xxx.c +++ b/drivers/net/ethernet/qlogic/qla3xxx.c @@ -2475,6 +2475,7 @@ static netdev_tx_t ql3xxx_send(struct sk_buff *skb, skb_shinfo(skb)->nr_frags); if (tx_cb->seg_count == -1) { netdev_err(ndev, "%s: invalid segment count!\n", __func__); + dev_kfree_skb_any(skb); return NETDEV_TX_OK; } diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c index 5b7413305be6330f1ff4f579af3fd4a816016474..eb1be73020822ddbb41b8202e55dac97e0b9f06f 100644 --- a/drivers/net/ethernet/sfc/ef10.c +++ b/drivers/net/ethernet/sfc/ef10.c @@ -3255,6 +3255,30 @@ static int efx_ef10_set_mac_address(struct efx_nic *efx) bool was_enabled = efx->port_enabled; int rc; +#ifdef CONFIG_SFC_SRIOV + /* If this function is a VF and we have access to the parent PF, + * then use the PF control path to attempt to change the VF MAC address. + */ + if (efx->pci_dev->is_virtfn && efx->pci_dev->physfn) { + struct efx_nic *efx_pf = pci_get_drvdata(efx->pci_dev->physfn); + struct efx_ef10_nic_data *nic_data = efx->nic_data; + u8 mac[ETH_ALEN]; + + /* net_dev->dev_addr can be zeroed by efx_net_stop in + * efx_ef10_sriov_set_vf_mac, so pass in a copy. + */ + ether_addr_copy(mac, efx->net_dev->dev_addr); + + rc = efx_ef10_sriov_set_vf_mac(efx_pf, nic_data->vf_index, mac); + if (!rc) + return 0; + + netif_dbg(efx, drv, efx->net_dev, + "Updating VF mac via PF failed (%d), setting directly\n", + rc); + } +#endif + efx_device_detach_sync(efx); efx_net_stop(efx->net_dev); @@ -3277,40 +3301,6 @@ static int efx_ef10_set_mac_address(struct efx_nic *efx) efx_net_open(efx->net_dev); efx_device_attach_if_not_resetting(efx); -#ifdef CONFIG_SFC_SRIOV - if (efx->pci_dev->is_virtfn && efx->pci_dev->physfn) { - struct efx_ef10_nic_data *nic_data = efx->nic_data; - struct pci_dev *pci_dev_pf = efx->pci_dev->physfn; - - if (rc == -EPERM) { - struct efx_nic *efx_pf; - - /* Switch to PF and change MAC address on vport */ - efx_pf = pci_get_drvdata(pci_dev_pf); - - rc = efx_ef10_sriov_set_vf_mac(efx_pf, - nic_data->vf_index, - efx->net_dev->dev_addr); - } else if (!rc) { - struct efx_nic *efx_pf = pci_get_drvdata(pci_dev_pf); - struct efx_ef10_nic_data *nic_data = efx_pf->nic_data; - unsigned int i; - - /* MAC address successfully changed by VF (with MAC - * spoofing) so update the parent PF if possible. - */ - for (i = 0; i < efx_pf->vf_count; ++i) { - struct ef10_vf *vf = nic_data->vf + i; - - if (vf->efx == efx) { - ether_addr_copy(vf->mac, - efx->net_dev->dev_addr); - return 0; - } - } - } - } else -#endif if (rc == -EPERM) { netif_err(efx, drv, efx->net_dev, "Cannot change MAC address; use sfboot to enable" diff --git a/drivers/net/ethernet/sfc/ef100_netdev.c b/drivers/net/ethernet/sfc/ef100_netdev.c index 67fe44db6b6124438291cf20b2f828d8d559035c..63a44ee763be7994e5a477cdcfd29fc9928c2b1c 100644 --- a/drivers/net/ethernet/sfc/ef100_netdev.c +++ b/drivers/net/ethernet/sfc/ef100_netdev.c @@ -200,6 +200,7 @@ static netdev_tx_t ef100_hard_start_xmit(struct sk_buff *skb, skb->len, skb->data_len, channel->channel); if (!efx->n_channels || !efx->n_tx_channels || !channel) { netif_stop_queue(net_dev); + dev_kfree_skb_any(skb); goto err; } diff --git a/drivers/net/ethernet/sfc/filter.h b/drivers/net/ethernet/sfc/filter.h index 40b2af8bfb81c69ff4f1d55f45e147adb5f66aed..2ac3c8f1b04b5f0aff0d5930872663b2a30792ae 100644 --- a/drivers/net/ethernet/sfc/filter.h +++ b/drivers/net/ethernet/sfc/filter.h @@ -157,7 +157,8 @@ struct efx_filter_spec { u32 flags:6; u32 dmaq_id:12; u32 rss_context; - __be16 outer_vid __aligned(4); /* allow jhash2() of match values */ + u32 vport_id; + __be16 outer_vid; __be16 inner_vid; u8 loc_mac[ETH_ALEN]; u8 rem_mac[ETH_ALEN]; diff --git a/drivers/net/ethernet/sfc/rx_common.c b/drivers/net/ethernet/sfc/rx_common.c index 2c09afac5beb45e8f15475e536c3b03180786930..36b46ddb671078639b62fb4cb07a74112ae9d299 100644 --- a/drivers/net/ethernet/sfc/rx_common.c +++ b/drivers/net/ethernet/sfc/rx_common.c @@ -676,17 +676,17 @@ bool efx_filter_spec_equal(const struct efx_filter_spec *left, (EFX_FILTER_FLAG_RX | EFX_FILTER_FLAG_TX))) return false; - return memcmp(&left->outer_vid, &right->outer_vid, + return memcmp(&left->vport_id, &right->vport_id, sizeof(struct efx_filter_spec) - - offsetof(struct efx_filter_spec, outer_vid)) == 0; + offsetof(struct efx_filter_spec, vport_id)) == 0; } u32 efx_filter_spec_hash(const struct efx_filter_spec *spec) { - BUILD_BUG_ON(offsetof(struct efx_filter_spec, outer_vid) & 3); - return jhash2((const u32 *)&spec->outer_vid, + BUILD_BUG_ON(offsetof(struct efx_filter_spec, vport_id) & 3); + return jhash2((const u32 *)&spec->vport_id, (sizeof(struct efx_filter_spec) - - offsetof(struct efx_filter_spec, outer_vid)) / 4, + offsetof(struct efx_filter_spec, vport_id)) / 4, 0); } diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c index ef3634d1b9f7fa25ff3f8fd3e5323b29e94c5b41..b9acee214bb6acb95fe40ba20f4796e0b25f4427 100644 --- a/drivers/net/ethernet/socionext/netsec.c +++ b/drivers/net/ethernet/socionext/netsec.c @@ -1958,11 +1958,13 @@ static int netsec_register_mdio(struct netsec_priv *priv, u32 phy_addr) ret = PTR_ERR(priv->phydev); dev_err(priv->dev, "get_phy_device err(%d)\n", ret); priv->phydev = NULL; + mdiobus_unregister(bus); return -ENODEV; } ret = phy_device_register(priv->phydev); if (ret) { + phy_device_free(priv->phydev); mdiobus_unregister(bus); dev_err(priv->dev, "phy_device_register err(%d)\n", ret); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c index 752658ec7beebc9c2a4b9ba46c52d7828c624e4a..50ef68497bce9e6ea8d0991f0f699df60b9ec751 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c @@ -261,11 +261,9 @@ static int meson8b_devm_clk_prepare_enable(struct meson8b_dwmac *dwmac, if (ret) return ret; - devm_add_action_or_reset(dwmac->dev, - (void(*)(void *))clk_disable_unprepare, - dwmac->rgmii_tx_clk); - - return 0; + return devm_add_action_or_reset(dwmac->dev, + (void(*)(void *))clk_disable_unprepare, + clk); } static int meson8b_init_prg_eth(struct meson8b_dwmac *dwmac) diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index b0f00b4edd9491b1d0cb37df8a7c6be6818b32ef..5af0f9f8c09754df686731822e08d17d48fc0768 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -864,6 +864,8 @@ static int cpsw_ndo_open(struct net_device *ndev) err_cleanup: if (!cpsw->usage_count) { + napi_disable(&cpsw->napi_rx); + napi_disable(&cpsw->napi_tx); cpdma_ctlr_stop(cpsw->dma); cpsw_destroy_xdp_rxqs(cpsw); } diff --git a/drivers/net/ethernet/tundra/tsi108_eth.c b/drivers/net/ethernet/tundra/tsi108_eth.c index c62f474b6d08eb74c159811c9ea32549845072e9..fcebd2418dbd3b3e2b8942ce211e699d146ef7c4 100644 --- a/drivers/net/ethernet/tundra/tsi108_eth.c +++ b/drivers/net/ethernet/tundra/tsi108_eth.c @@ -1302,12 +1302,15 @@ static int tsi108_open(struct net_device *dev) data->rxring = dma_alloc_coherent(&data->pdev->dev, rxring_size, &data->rxdma, GFP_KERNEL); - if (!data->rxring) + if (!data->rxring) { + free_irq(data->irq_num, dev); return -ENOMEM; + } data->txring = dma_alloc_coherent(&data->pdev->dev, txring_size, &data->txdma, GFP_KERNEL); if (!data->txring) { + free_irq(data->irq_num, dev); dma_free_coherent(&data->pdev->dev, rxring_size, data->rxring, data->rxdma); return -ENOMEM; diff --git a/drivers/net/hamradio/bpqether.c b/drivers/net/hamradio/bpqether.c index 1ad6085994b1cd74a851c2dca47375d896768553..5c17c92add8ab861cf1c9c5533feaa610535eb3b 100644 --- a/drivers/net/hamradio/bpqether.c +++ b/drivers/net/hamradio/bpqether.c @@ -533,7 +533,7 @@ static int bpq_device_event(struct notifier_block *this, if (!net_eq(dev_net(dev), &init_net)) return NOTIFY_DONE; - if (!dev_is_ethdev(dev)) + if (!dev_is_ethdev(dev) && !bpq_get_ax25_dev(dev)) return NOTIFY_DONE; switch (event) { diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h index a0f338cf14247a13651d1fca873cf4423dad795f..367878493e704227c09a9153e46812ba7d4afb42 100644 --- a/drivers/net/hyperv/hyperv_net.h +++ b/drivers/net/hyperv/hyperv_net.h @@ -977,7 +977,8 @@ struct net_device_context { u32 vf_alloc; /* Serial number of the VF to team with */ u32 vf_serial; - + /* completion variable to confirm vf association */ + struct completion vf_add; /* Is the current data path through the VF NIC? */ bool data_path_is_vf; diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index 6a7ab930ef70d8bca496bfad20c36d9e86a77813..d15da8287df3266a0a4a0349b40aeefdcd11d8b2 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -1327,6 +1327,10 @@ static void netvsc_send_vf(struct net_device *ndev, net_device_ctx->vf_alloc = nvmsg->msg.v4_msg.vf_assoc.allocated; net_device_ctx->vf_serial = nvmsg->msg.v4_msg.vf_assoc.serial; + + if (net_device_ctx->vf_alloc) + complete(&net_device_ctx->vf_add); + netdev_info(ndev, "VF slot %u %s\n", net_device_ctx->vf_serial, net_device_ctx->vf_alloc ? "added" : "removed"); diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 18484370da0d4dde48bd3dfb70d0510215229de6..f2020be43cfea2869df93524084e5fcb3982d2a5 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -2290,6 +2290,7 @@ static struct net_device *get_netvsc_byslot(const struct net_device *vf_netdev) { struct device *parent = vf_netdev->dev.parent; struct net_device_context *ndev_ctx; + struct net_device *ndev; struct pci_dev *pdev; u32 serial; @@ -2316,6 +2317,18 @@ static struct net_device *get_netvsc_byslot(const struct net_device *vf_netdev) return hv_get_drvdata(ndev_ctx->device_ctx); } + /* Fallback path to check synthetic vf with + * help of mac addr + */ + list_for_each_entry(ndev_ctx, &netvsc_dev_list, list) { + ndev = hv_get_drvdata(ndev_ctx->device_ctx); + if (ether_addr_equal(vf_netdev->perm_addr, ndev->perm_addr)) { + netdev_notice(vf_netdev, + "falling back to mac addr based matching\n"); + return ndev; + } + } + netdev_notice(vf_netdev, "no netdev found for vf serial:%u\n", serial); return NULL; @@ -2406,6 +2419,11 @@ static int netvsc_vf_changed(struct net_device *vf_netdev) return NOTIFY_OK; net_device_ctx->data_path_is_vf = vf_is_up; + if (vf_is_up && !net_device_ctx->vf_alloc) { + netdev_info(ndev, "Waiting for the VF association from host\n"); + wait_for_completion(&net_device_ctx->vf_add); + } + netvsc_switch_datapath(ndev, vf_is_up); netdev_info(ndev, "Data path switched %s VF: %s\n", vf_is_up ? "to" : "from", vf_netdev->name); @@ -2429,6 +2447,7 @@ static int netvsc_unregister_vf(struct net_device *vf_netdev) netvsc_vf_setxdp(vf_netdev, NULL); + reinit_completion(&net_device_ctx->vf_add); netdev_rx_handler_unregister(vf_netdev); netdev_upper_dev_unlink(vf_netdev, ndev); RCU_INIT_POINTER(net_device_ctx->vf_netdev, NULL); @@ -2466,6 +2485,7 @@ static int netvsc_probe(struct hv_device *dev, INIT_DELAYED_WORK(&net_device_ctx->dwork, netvsc_link_change); + init_completion(&net_device_ctx->vf_add); spin_lock_init(&net_device_ctx->lock); INIT_LIST_HEAD(&net_device_ctx->reconfig_events); INIT_DELAYED_WORK(&net_device_ctx->vf_takeover, netvsc_vf_setup); diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c index a1c77cc0041657de79b562c84408acabf9e8b99b..498e5c8013efb39db0cb861a7f119e68ce6b8715 100644 --- a/drivers/net/loopback.c +++ b/drivers/net/loopback.c @@ -208,7 +208,7 @@ static __net_init int loopback_net_init(struct net *net) int err; err = -ENOMEM; - dev = alloc_netdev(0, "lo", NET_NAME_UNKNOWN, loopback_setup); + dev = alloc_netdev(0, "lo", NET_NAME_PREDICTABLE, loopback_setup); if (!dev) goto out; diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 70c5905a916b98fa213b854b0c7a75c8d72116be..3e564158c401b7748503adbe913f4b2238f3e887 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -1390,7 +1390,8 @@ static struct macsec_rx_sc *del_rx_sc(struct macsec_secy *secy, sci_t sci) return NULL; } -static struct macsec_rx_sc *create_rx_sc(struct net_device *dev, sci_t sci) +static struct macsec_rx_sc *create_rx_sc(struct net_device *dev, sci_t sci, + bool active) { struct macsec_rx_sc *rx_sc; struct macsec_dev *macsec; @@ -1414,7 +1415,7 @@ static struct macsec_rx_sc *create_rx_sc(struct net_device *dev, sci_t sci) } rx_sc->sci = sci; - rx_sc->active = true; + rx_sc->active = active; refcount_set(&rx_sc->refcnt, 1); secy = &macsec_priv(dev)->secy; @@ -1823,6 +1824,7 @@ static int macsec_add_rxsa(struct sk_buff *skb, struct genl_info *info) secy->key_len); err = macsec_offload(ops->mdo_add_rxsa, &ctx); + memzero_explicit(ctx.sa.key, secy->key_len); if (err) goto cleanup; } @@ -1867,7 +1869,7 @@ static int macsec_add_rxsc(struct sk_buff *skb, struct genl_info *info) struct macsec_rx_sc *rx_sc; struct nlattr *tb_rxsc[MACSEC_RXSC_ATTR_MAX + 1]; struct macsec_secy *secy; - bool was_active; + bool active = true; int ret; if (!attrs[MACSEC_ATTR_IFINDEX]) @@ -1889,16 +1891,15 @@ static int macsec_add_rxsc(struct sk_buff *skb, struct genl_info *info) secy = &macsec_priv(dev)->secy; sci = nla_get_sci(tb_rxsc[MACSEC_RXSC_ATTR_SCI]); - rx_sc = create_rx_sc(dev, sci); + if (tb_rxsc[MACSEC_RXSC_ATTR_ACTIVE]) + active = nla_get_u8(tb_rxsc[MACSEC_RXSC_ATTR_ACTIVE]); + + rx_sc = create_rx_sc(dev, sci, active); if (IS_ERR(rx_sc)) { rtnl_unlock(); return PTR_ERR(rx_sc); } - was_active = rx_sc->active; - if (tb_rxsc[MACSEC_RXSC_ATTR_ACTIVE]) - rx_sc->active = !!nla_get_u8(tb_rxsc[MACSEC_RXSC_ATTR_ACTIVE]); - if (macsec_is_offloaded(netdev_priv(dev))) { const struct macsec_ops *ops; struct macsec_context ctx; @@ -1922,7 +1923,8 @@ static int macsec_add_rxsc(struct sk_buff *skb, struct genl_info *info) return 0; cleanup: - rx_sc->active = was_active; + del_rx_sc(secy, sci); + free_rx_sc(rx_sc); rtnl_unlock(); return ret; } @@ -2065,6 +2067,7 @@ static int macsec_add_txsa(struct sk_buff *skb, struct genl_info *info) secy->key_len); err = macsec_offload(ops->mdo_add_txsa, &ctx); + memzero_explicit(ctx.sa.key, secy->key_len); if (err) goto cleanup; } @@ -2561,7 +2564,7 @@ static bool macsec_is_configured(struct macsec_dev *macsec) struct macsec_tx_sc *tx_sc = &secy->tx_sc; int i; - if (secy->n_rx_sc > 0) + if (secy->rx_sc) return true; for (i = 0; i < MACSEC_NUM_AN; i++) @@ -2645,11 +2648,6 @@ static int macsec_upd_offload(struct sk_buff *skb, struct genl_info *info) if (ret) goto rollback; - /* Force features update, since they are different for SW MACSec and - * HW offloading cases. - */ - netdev_update_features(dev); - rtnl_unlock(); return 0; @@ -3417,16 +3415,9 @@ static netdev_tx_t macsec_start_xmit(struct sk_buff *skb, return ret; } -#define SW_MACSEC_FEATURES \ +#define MACSEC_FEATURES \ (NETIF_F_SG | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST) -/* If h/w offloading is enabled, use real device features save for - * VLAN_FEATURES - they require additional ops - * HW_MACSEC - no reason to report it - */ -#define REAL_DEV_FEATURES(dev) \ - ((dev)->features & ~(NETIF_F_VLAN_FEATURES | NETIF_F_HW_MACSEC)) - static int macsec_dev_init(struct net_device *dev) { struct macsec_dev *macsec = macsec_priv(dev); @@ -3443,12 +3434,8 @@ static int macsec_dev_init(struct net_device *dev) return err; } - if (macsec_is_offloaded(macsec)) { - dev->features = REAL_DEV_FEATURES(real_dev); - } else { - dev->features = real_dev->features & SW_MACSEC_FEATURES; - dev->features |= NETIF_F_LLTX | NETIF_F_GSO_SOFTWARE; - } + dev->features = real_dev->features & MACSEC_FEATURES; + dev->features |= NETIF_F_LLTX | NETIF_F_GSO_SOFTWARE; dev->needed_headroom = real_dev->needed_headroom + MACSEC_NEEDED_HEADROOM; @@ -3477,10 +3464,7 @@ static netdev_features_t macsec_fix_features(struct net_device *dev, struct macsec_dev *macsec = macsec_priv(dev); struct net_device *real_dev = macsec->real_dev; - if (macsec_is_offloaded(macsec)) - return REAL_DEV_FEATURES(real_dev); - - features &= (real_dev->features & SW_MACSEC_FEATURES) | + features &= (real_dev->features & MACSEC_FEATURES) | NETIF_F_GSO_SOFTWARE | NETIF_F_SOFT_FEATURES; features |= NETIF_F_LLTX; @@ -3829,7 +3813,6 @@ static int macsec_changelink(struct net_device *dev, struct nlattr *tb[], if (macsec_is_offloaded(macsec)) { const struct macsec_ops *ops; struct macsec_context ctx; - int ret; ops = macsec_get_ops(netdev_priv(dev), &ctx); if (!ops) { diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index c8d803d3616c90a74c05674a72c283b8062f4067..5869bc2c3aa798a53f526c48f2d3bb269f3d0a9e 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -139,7 +139,7 @@ static struct macvlan_source_entry *macvlan_hash_lookup_source( u32 idx = macvlan_eth_hash(addr); struct hlist_head *h = &vlan->port->vlan_source_hash[idx]; - hlist_for_each_entry_rcu(entry, h, hlist) { + hlist_for_each_entry_rcu(entry, h, hlist, lockdep_rtnl_is_held()) { if (ether_addr_equal_64bits(entry->addr, addr) && entry->vlan == vlan) return entry; @@ -1176,7 +1176,7 @@ void macvlan_common_setup(struct net_device *dev) { ether_setup(dev); - dev->min_mtu = 0; + /* ether_setup() has set dev->min_mtu to ETH_MIN_MTU. */ dev->max_mtu = ETH_MAX_MTU; dev->priv_flags &= ~IFF_TX_SKB_SHARING; netif_keep_dst(dev); @@ -1509,8 +1509,10 @@ destroy_macvlan_port: /* the macvlan port may be freed by macvlan_uninit when fail to register. * so we destroy the macvlan port only when it's valid. */ - if (create && macvlan_port_get_rtnl(lowerdev)) + if (create && macvlan_port_get_rtnl(lowerdev)) { + macvlan_flush_sources(port, vlan); macvlan_port_destroy(port->dev); + } return err; } EXPORT_SYMBOL_GPL(macvlan_common_newlink); @@ -1612,7 +1614,7 @@ static int macvlan_fill_info_macaddr(struct sk_buff *skb, struct hlist_head *h = &vlan->port->vlan_source_hash[i]; struct macvlan_source_entry *entry; - hlist_for_each_entry_rcu(entry, h, hlist) { + hlist_for_each_entry_rcu(entry, h, hlist, lockdep_rtnl_is_held()) { if (entry->vlan != vlan) continue; if (nla_put(skb, IFLA_MACVLAN_MACADDR, ETH_ALEN, entry->addr)) diff --git a/drivers/net/phy/dp83822.c b/drivers/net/phy/dp83822.c index 3a8849716459a7b0c71d4659f2714c7190f77271..db651649e0b80665d9fdbf40e06e5639af21633c 100644 --- a/drivers/net/phy/dp83822.c +++ b/drivers/net/phy/dp83822.c @@ -268,8 +268,7 @@ static int dp83822_config_intr(struct phy_device *phydev) DP83822_EEE_ERROR_CHANGE_INT_EN); if (!dp83822->fx_enabled) - misr_status |= DP83822_MDI_XOVER_INT_EN | - DP83822_ANEG_ERR_INT_EN | + misr_status |= DP83822_ANEG_ERR_INT_EN | DP83822_WOL_PKT_INT_EN; err = phy_write(phydev, MII_DP83822_MISR2, misr_status); diff --git a/drivers/net/phy/dp83867.c b/drivers/net/phy/dp83867.c index f86acad0aad44ec949912788960be6d6e715e102..c8031e297faf4bc3d99ba99048e4f0a47346ec25 100644 --- a/drivers/net/phy/dp83867.c +++ b/drivers/net/phy/dp83867.c @@ -757,6 +757,14 @@ static int dp83867_config_init(struct phy_device *phydev) else val &= ~DP83867_SGMII_TYPE; phy_write_mmd(phydev, DP83867_DEVADDR, DP83867_SGMIICTL, val); + + /* This is a SW workaround for link instability if RX_CTRL is + * not strapped to mode 3 or 4 in HW. This is required for SGMII + * in addition to clearing bit 7, handled above. + */ + if (dp83867->rxctrl_strap_quirk) + phy_set_bits_mmd(phydev, DP83867_DEVADDR, DP83867_CFG4, + BIT(8)); } val = phy_read(phydev, DP83867_CFG3); diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c index c1cbdac4b376f05bea70831f0d3d64064bcc1846..77ba6c3c7a0904714a3e261412804066f57e9b3b 100644 --- a/drivers/net/phy/mdio_bus.c +++ b/drivers/net/phy/mdio_bus.c @@ -574,7 +574,7 @@ int __mdiobus_register(struct mii_bus *bus, struct module *owner) } for (i = 0; i < PHY_MAX_ADDR; i++) { - if ((bus->phy_mask & (1 << i)) == 0) { + if ((bus->phy_mask & BIT(i)) == 0) { struct phy_device *phydev; phydev = mdiobus_scan(bus, i); diff --git a/drivers/net/phy/mscc/mscc_macsec.c b/drivers/net/phy/mscc/mscc_macsec.c index b7b2521c73fb629b341ea89a48dc43fb6458d930..c00eef457b8500041e0397b8b4333323a6a3b993 100644 --- a/drivers/net/phy/mscc/mscc_macsec.c +++ b/drivers/net/phy/mscc/mscc_macsec.c @@ -632,6 +632,7 @@ static void vsc8584_macsec_free_flow(struct vsc8531_private *priv, list_del(&flow->list); clear_bit(flow->index, bitmap); + memzero_explicit(flow->key, sizeof(flow->key)); kfree(flow); } diff --git a/drivers/net/thunderbolt.c b/drivers/net/thunderbolt.c index 3160443ef3b9e51a2ef2c769c329ef3c7c1456a4..5d96dc1b00b36e2c956412656ebc9bf43765ee0e 100644 --- a/drivers/net/thunderbolt.c +++ b/drivers/net/thunderbolt.c @@ -1343,12 +1343,21 @@ static int __init tbnet_init(void) TBNET_MATCH_FRAGS_ID); ret = tb_register_property_dir("network", tbnet_dir); - if (ret) { - tb_property_free_dir(tbnet_dir); - return ret; - } + if (ret) + goto err_free_dir; + + ret = tb_register_service_driver(&tbnet_driver); + if (ret) + goto err_unregister; - return tb_register_service_driver(&tbnet_driver); + return 0; + +err_unregister: + tb_unregister_property_dir("network", tbnet_dir); +err_free_dir: + tb_property_free_dir(tbnet_dir); + + return ret; } module_init(tbnet_init); diff --git a/drivers/net/tun.c b/drivers/net/tun.c index a643b2f2f4de99b81f75b3c06d6ad6fc557d0a2c..cb42fdbfeb3261badf5e0242d1a15adc299ceff6 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1475,7 +1475,8 @@ static struct sk_buff *tun_napi_alloc_frags(struct tun_file *tfile, int err; int i; - if (it->nr_segs > MAX_SKB_FRAGS + 1) + if (it->nr_segs > MAX_SKB_FRAGS + 1 || + len > (ETH_MAX_MTU - NET_SKB_PAD - NET_IP_ALIGN)) return ERR_PTR(-EMSGSIZE); local_bh_disable(); @@ -1985,17 +1986,25 @@ drop: skb_headlen(skb)); if (unlikely(headlen > skb_headlen(skb))) { + WARN_ON_ONCE(1); + err = -ENOMEM; this_cpu_inc(tun->pcpu_stats->rx_dropped); +napi_busy: napi_free_frags(&tfile->napi); rcu_read_unlock(); mutex_unlock(&tfile->napi_mutex); - WARN_ON(1); - return -ENOMEM; + return err; } - local_bh_disable(); - napi_gro_frags(&tfile->napi); - local_bh_enable(); + if (likely(napi_schedule_prep(&tfile->napi))) { + local_bh_disable(); + napi_gro_frags(&tfile->napi); + napi_complete(&tfile->napi); + local_bh_enable(); + } else { + err = -EBUSY; + goto napi_busy; + } mutex_unlock(&tfile->napi_mutex); } else if (tfile->napi_enabled) { struct sk_buff_head *queue = &tfile->sk.sk_write_queue; diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c index 43ddbe61dc58e140015e43317efcd7893fdb1693..935cd296887f27db12eb34146a090a6c71f5d079 100644 --- a/drivers/net/usb/cdc_ether.c +++ b/drivers/net/usb/cdc_ether.c @@ -763,6 +763,13 @@ static const struct usb_device_id products[] = { }, #endif +/* Lenovo ThinkPad OneLink+ Dock (based on Realtek RTL8153) */ +{ + USB_DEVICE_AND_INTERFACE_INFO(LENOVO_VENDOR_ID, 0x3054, USB_CLASS_COMM, + USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE), + .driver_info = 0, +}, + /* ThinkPad USB-C Dock (based on Realtek RTL8153) */ { USB_DEVICE_AND_INTERFACE_INFO(LENOVO_VENDOR_ID, 0x3062, USB_CLASS_COMM, diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index a1c9233e264d9e93519c226c088bfc713a5b65c2..7313e6e03c12579315b04f8e9d461b5289f86228 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1292,6 +1292,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x2357, 0x0201, 4)}, /* TP-LINK HSUPA Modem MA180 */ {QMI_FIXED_INTF(0x2357, 0x9000, 4)}, /* TP-LINK MA260 */ {QMI_QUIRK_SET_DTR(0x1bc7, 0x1031, 3)}, /* Telit LE910C1-EUX */ + {QMI_QUIRK_SET_DTR(0x1bc7, 0x103a, 0)}, /* Telit LE910C4-WWX */ {QMI_QUIRK_SET_DTR(0x1bc7, 0x1040, 2)}, /* Telit LE922A */ {QMI_QUIRK_SET_DTR(0x1bc7, 0x1050, 2)}, /* Telit FN980 */ {QMI_QUIRK_SET_DTR(0x1bc7, 0x1060, 2)}, /* Telit LN920 */ diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 0bb5b1c78654699167bdf227975c93a1000fb882..f9a79d67d6d4ffc17fa37751ffb4daf3a2148725 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -1689,7 +1689,9 @@ static void intr_callback(struct urb *urb) "Stop submitting intr, status %d\n", status); return; case -EOVERFLOW: - netif_info(tp, intr, tp->netdev, "intr status -EOVERFLOW\n"); + if (net_ratelimit()) + netif_info(tp, intr, tp->netdev, + "intr status -EOVERFLOW\n"); goto resubmit; /* -EPIPE: should clear the halt */ default: @@ -6868,6 +6870,7 @@ static const struct usb_device_id rtl8152_table[] = { {REALTEK_USB_DEVICE(VENDOR_ID_MICROSOFT, 0x0927)}, {REALTEK_USB_DEVICE(VENDOR_ID_SAMSUNG, 0xa101)}, {REALTEK_USB_DEVICE(VENDOR_ID_LENOVO, 0x304f)}, + {REALTEK_USB_DEVICE(VENDOR_ID_LENOVO, 0x3054)}, {REALTEK_USB_DEVICE(VENDOR_ID_LENOVO, 0x3062)}, {REALTEK_USB_DEVICE(VENDOR_ID_LENOVO, 0x3069)}, {REALTEK_USB_DEVICE(VENDOR_ID_LENOVO, 0x3082)}, diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c index 65d42f5d42a3c8f75963ab4d960c9aff9c167983..e1cd4c2de2d30c201f00b9f33fcfa73cb72d59bd 100644 --- a/drivers/net/usb/smsc95xx.c +++ b/drivers/net/usb/smsc95xx.c @@ -61,6 +61,7 @@ struct smsc95xx_priv { u8 suspend_flags; struct mii_bus *mdiobus; struct phy_device *phydev; + struct task_struct *pm_task; }; static bool turbo_mode = true; @@ -70,13 +71,14 @@ MODULE_PARM_DESC(turbo_mode, "Enable multiple frames per Rx transaction"); static int __must_check __smsc95xx_read_reg(struct usbnet *dev, u32 index, u32 *data, int in_pm) { + struct smsc95xx_priv *pdata = dev->driver_priv; u32 buf; int ret; int (*fn)(struct usbnet *, u8, u8, u16, u16, void *, u16); BUG_ON(!dev); - if (!in_pm) + if (current != pdata->pm_task) fn = usbnet_read_cmd; else fn = usbnet_read_cmd_nopm; @@ -100,13 +102,14 @@ static int __must_check __smsc95xx_read_reg(struct usbnet *dev, u32 index, static int __must_check __smsc95xx_write_reg(struct usbnet *dev, u32 index, u32 data, int in_pm) { + struct smsc95xx_priv *pdata = dev->driver_priv; u32 buf; int ret; int (*fn)(struct usbnet *, u8, u8, u16, u16, const void *, u16); BUG_ON(!dev); - if (!in_pm) + if (current != pdata->pm_task) fn = usbnet_write_cmd; else fn = usbnet_write_cmd_nopm; @@ -1468,9 +1471,12 @@ static int smsc95xx_suspend(struct usb_interface *intf, pm_message_t message) u32 val, link_up; int ret; + pdata->pm_task = current; + ret = usbnet_suspend(intf, message); if (ret < 0) { netdev_warn(dev->net, "usbnet_suspend error\n"); + pdata->pm_task = NULL; return ret; } @@ -1717,6 +1723,7 @@ done: if (ret && PMSG_IS_AUTO(message)) usbnet_resume(intf); + pdata->pm_task = NULL; return ret; } @@ -1737,29 +1744,31 @@ static int smsc95xx_resume(struct usb_interface *intf) /* do this first to ensure it's cleared even in error case */ pdata->suspend_flags = 0; + pdata->pm_task = current; + if (suspend_flags & SUSPEND_ALLMODES) { /* clear wake-up sources */ ret = smsc95xx_read_reg_nopm(dev, WUCSR, &val); if (ret < 0) - return ret; + goto done; val &= ~(WUCSR_WAKE_EN_ | WUCSR_MPEN_); ret = smsc95xx_write_reg_nopm(dev, WUCSR, val); if (ret < 0) - return ret; + goto done; /* clear wake-up status */ ret = smsc95xx_read_reg_nopm(dev, PM_CTRL, &val); if (ret < 0) - return ret; + goto done; val &= ~PM_CTL_WOL_EN_; val |= PM_CTL_WUPS_; ret = smsc95xx_write_reg_nopm(dev, PM_CTRL, val); if (ret < 0) - return ret; + goto done; } ret = usbnet_resume(intf); @@ -1767,15 +1776,21 @@ static int smsc95xx_resume(struct usb_interface *intf) netdev_warn(dev->net, "usbnet_resume error\n"); phy_init_hw(pdata->phydev); + +done: + pdata->pm_task = NULL; return ret; } static int smsc95xx_reset_resume(struct usb_interface *intf) { struct usbnet *dev = usb_get_intfdata(intf); + struct smsc95xx_priv *pdata = dev->driver_priv; int ret; + pdata->pm_task = current; ret = smsc95xx_reset(dev); + pdata->pm_task = NULL; if (ret < 0) return ret; diff --git a/drivers/net/wan/lapbether.c b/drivers/net/wan/lapbether.c index f6562a343cb4e960276868902597444620d28099..b965eb6a4bb17fc56ed09ca7dbb330e28e5ccc8f 100644 --- a/drivers/net/wan/lapbether.c +++ b/drivers/net/wan/lapbether.c @@ -403,7 +403,7 @@ static int lapbeth_device_event(struct notifier_block *this, if (dev_net(dev) != &init_net) return NOTIFY_DONE; - if (!dev_is_ethdev(dev)) + if (!dev_is_ethdev(dev) && !lapbeth_get_x25_dev(dev)) return NOTIFY_DONE; switch (event) { diff --git a/drivers/net/wireguard/queueing.h b/drivers/net/wireguard/queueing.h index e2388107f7fdc9c040841adfc164459e0c777d7d..1a7aaa2680412f110742bae1d45cbedd8baf248b 100644 --- a/drivers/net/wireguard/queueing.h +++ b/drivers/net/wireguard/queueing.h @@ -82,6 +82,17 @@ static inline void wg_reset_packet(struct sk_buff *skb, bool encapsulating) memset(&skb->headers_start, 0, offsetof(struct sk_buff, headers_end) - offsetof(struct sk_buff, headers_start)); + + /* ANDROID: + * Due to attempts to keep the ABI stable for struct sk_buff, the new + * fields were incorrectly added _AFTER_ the headers_end field, which + * requires that we manually copy the fields here from the old to the + * new one. + * Be sure to add any new field that is added in the + * ANDROID_KABI_REPLACE() macros below here as well. + */ + skb->scm_io_uring = 0; + if (encapsulating) { skb->l4_hash = l4_hash; skb->sw_hash = sw_hash; diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c index b61cd275fbda2723736179026726a3f462533ad5..15f02bf23e9bd917551f291cdd88c517d333c17d 100644 --- a/drivers/net/wireless/ath/ath10k/mac.c +++ b/drivers/net/wireless/ath/ath10k/mac.c @@ -853,11 +853,36 @@ static int ath10k_peer_delete(struct ath10k *ar, u32 vdev_id, const u8 *addr) return 0; } +static void ath10k_peer_map_cleanup(struct ath10k *ar, struct ath10k_peer *peer) +{ + int peer_id, i; + + lockdep_assert_held(&ar->conf_mutex); + + for_each_set_bit(peer_id, peer->peer_ids, + ATH10K_MAX_NUM_PEER_IDS) { + ar->peer_map[peer_id] = NULL; + } + + /* Double check that peer is properly un-referenced from + * the peer_map + */ + for (i = 0; i < ARRAY_SIZE(ar->peer_map); i++) { + if (ar->peer_map[i] == peer) { + ath10k_warn(ar, "removing stale peer_map entry for %pM (ptr %pK idx %d)\n", + peer->addr, peer, i); + ar->peer_map[i] = NULL; + } + } + + list_del(&peer->list); + kfree(peer); + ar->num_peers--; +} + static void ath10k_peer_cleanup(struct ath10k *ar, u32 vdev_id) { struct ath10k_peer *peer, *tmp; - int peer_id; - int i; lockdep_assert_held(&ar->conf_mutex); @@ -869,25 +894,7 @@ static void ath10k_peer_cleanup(struct ath10k *ar, u32 vdev_id) ath10k_warn(ar, "removing stale peer %pM from vdev_id %d\n", peer->addr, vdev_id); - for_each_set_bit(peer_id, peer->peer_ids, - ATH10K_MAX_NUM_PEER_IDS) { - ar->peer_map[peer_id] = NULL; - } - - /* Double check that peer is properly un-referenced from - * the peer_map - */ - for (i = 0; i < ARRAY_SIZE(ar->peer_map); i++) { - if (ar->peer_map[i] == peer) { - ath10k_warn(ar, "removing stale peer_map entry for %pM (ptr %pK idx %d)\n", - peer->addr, peer, i); - ar->peer_map[i] = NULL; - } - } - - list_del(&peer->list); - kfree(peer); - ar->num_peers--; + ath10k_peer_map_cleanup(ar, peer); } spin_unlock_bh(&ar->data_lock); } @@ -7470,10 +7477,7 @@ static int ath10k_sta_state(struct ieee80211_hw *hw, /* Clean up the peer object as well since we * must have failed to do this above. */ - list_del(&peer->list); - ar->peer_map[i] = NULL; - kfree(peer); - ar->num_peers--; + ath10k_peer_map_cleanup(ar, peer); } } spin_unlock_bh(&ar->data_lock); diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c index 44282aec069d3fc62d5edcb2902b4d20aef50b43..67faf62999dede4c50eb661dbe047ba43e3ebac8 100644 --- a/drivers/net/wireless/ath/ath11k/mac.c +++ b/drivers/net/wireless/ath/ath11k/mac.c @@ -3419,6 +3419,8 @@ static int ath11k_mac_set_txbf_conf(struct ath11k_vif *arvif) if (vht_cap & (IEEE80211_VHT_CAP_SU_BEAMFORMEE_CAPABLE)) { nsts = vht_cap & IEEE80211_VHT_CAP_BEAMFORMEE_STS_MASK; nsts >>= IEEE80211_VHT_CAP_BEAMFORMEE_STS_SHIFT; + if (nsts > (ar->num_rx_chains - 1)) + nsts = ar->num_rx_chains - 1; value |= SM(nsts, WMI_TXBF_STS_CAP_OFFSET); } @@ -3459,7 +3461,7 @@ static int ath11k_mac_set_txbf_conf(struct ath11k_vif *arvif) static void ath11k_set_vht_txbf_cap(struct ath11k *ar, u32 *vht_cap) { bool subfer, subfee; - int sound_dim = 0; + int sound_dim = 0, nsts = 0; subfer = !!(*vht_cap & (IEEE80211_VHT_CAP_SU_BEAMFORMER_CAPABLE)); subfee = !!(*vht_cap & (IEEE80211_VHT_CAP_SU_BEAMFORMEE_CAPABLE)); @@ -3469,6 +3471,11 @@ static void ath11k_set_vht_txbf_cap(struct ath11k *ar, u32 *vht_cap) subfer = false; } + if (ar->num_rx_chains < 2) { + *vht_cap &= ~(IEEE80211_VHT_CAP_SU_BEAMFORMEE_CAPABLE); + subfee = false; + } + /* If SU Beaformer is not set, then disable MU Beamformer Capability */ if (!subfer) *vht_cap &= ~(IEEE80211_VHT_CAP_MU_BEAMFORMER_CAPABLE); @@ -3481,7 +3488,9 @@ static void ath11k_set_vht_txbf_cap(struct ath11k *ar, u32 *vht_cap) sound_dim >>= IEEE80211_VHT_CAP_SOUNDING_DIMENSIONS_SHIFT; *vht_cap &= ~IEEE80211_VHT_CAP_SOUNDING_DIMENSIONS_MASK; - /* TODO: Need to check invalid STS and Sound_dim values set by FW? */ + nsts = (*vht_cap & IEEE80211_VHT_CAP_BEAMFORMEE_STS_MASK); + nsts >>= IEEE80211_VHT_CAP_BEAMFORMEE_STS_SHIFT; + *vht_cap &= ~IEEE80211_VHT_CAP_BEAMFORMEE_STS_MASK; /* Enable Sounding Dimension Field only if SU BF is enabled */ if (subfer) { @@ -3493,9 +3502,15 @@ static void ath11k_set_vht_txbf_cap(struct ath11k *ar, u32 *vht_cap) *vht_cap |= sound_dim; } - /* Use the STS advertised by FW unless SU Beamformee is not supported*/ - if (!subfee) - *vht_cap &= ~(IEEE80211_VHT_CAP_BEAMFORMEE_STS_MASK); + /* Enable Beamformee STS Field only if SU BF is enabled */ + if (subfee) { + if (nsts > (ar->num_rx_chains - 1)) + nsts = ar->num_rx_chains - 1; + + nsts <<= IEEE80211_VHT_CAP_BEAMFORMEE_STS_SHIFT; + nsts &= IEEE80211_VHT_CAP_BEAMFORMEE_STS_MASK; + *vht_cap |= nsts; + } } static struct ieee80211_sta_vht_cap diff --git a/drivers/net/wireless/ath/ath9k/htc_hst.c b/drivers/net/wireless/ath/ath9k/htc_hst.c index 994ec48b2f669588dbfe46c69611aad47aaebfbe..ca05b07a45e67c714e58ac5f9c708acfb1b8f1c8 100644 --- a/drivers/net/wireless/ath/ath9k/htc_hst.c +++ b/drivers/net/wireless/ath/ath9k/htc_hst.c @@ -364,33 +364,27 @@ ret: } static void ath9k_htc_fw_panic_report(struct htc_target *htc_handle, - struct sk_buff *skb) + struct sk_buff *skb, u32 len) { uint32_t *pattern = (uint32_t *)skb->data; - switch (*pattern) { - case 0x33221199: - { + if (*pattern == 0x33221199 && len >= sizeof(struct htc_panic_bad_vaddr)) { struct htc_panic_bad_vaddr *htc_panic; htc_panic = (struct htc_panic_bad_vaddr *) skb->data; dev_err(htc_handle->dev, "ath: firmware panic! " "exccause: 0x%08x; pc: 0x%08x; badvaddr: 0x%08x.\n", htc_panic->exccause, htc_panic->pc, htc_panic->badvaddr); - break; - } - case 0x33221299: - { + return; + } + if (*pattern == 0x33221299) { struct htc_panic_bad_epid *htc_panic; htc_panic = (struct htc_panic_bad_epid *) skb->data; dev_err(htc_handle->dev, "ath: firmware panic! " "bad epid: 0x%08x\n", htc_panic->epid); - break; - } - default: - dev_err(htc_handle->dev, "ath: unknown panic pattern!\n"); - break; + return; } + dev_err(htc_handle->dev, "ath: unknown panic pattern!\n"); } /* @@ -411,16 +405,26 @@ void ath9k_htc_rx_msg(struct htc_target *htc_handle, if (!htc_handle || !skb) return; + /* A valid message requires len >= 8. + * + * sizeof(struct htc_frame_hdr) == 8 + * sizeof(struct htc_ready_msg) == 8 + * sizeof(struct htc_panic_bad_vaddr) == 16 + * sizeof(struct htc_panic_bad_epid) == 8 + */ + if (unlikely(len < sizeof(struct htc_frame_hdr))) + goto invalid; htc_hdr = (struct htc_frame_hdr *) skb->data; epid = htc_hdr->endpoint_id; if (epid == 0x99) { - ath9k_htc_fw_panic_report(htc_handle, skb); + ath9k_htc_fw_panic_report(htc_handle, skb, len); kfree_skb(skb); return; } if (epid < 0 || epid >= ENDPOINT_MAX) { +invalid: if (pipe_id != USB_REG_IN_PIPE) dev_kfree_skb_any(skb); else @@ -432,21 +436,30 @@ void ath9k_htc_rx_msg(struct htc_target *htc_handle, /* Handle trailer */ if (htc_hdr->flags & HTC_FLAGS_RECV_TRAILER) { - if (be32_to_cpu(*(__be32 *) skb->data) == 0x00C60000) + if (be32_to_cpu(*(__be32 *) skb->data) == 0x00C60000) { /* Move past the Watchdog pattern */ htc_hdr = (struct htc_frame_hdr *)(skb->data + 4); + len -= 4; + } } /* Get the message ID */ + if (unlikely(len < sizeof(struct htc_frame_hdr) + sizeof(__be16))) + goto invalid; msg_id = (__be16 *) ((void *) htc_hdr + sizeof(struct htc_frame_hdr)); /* Now process HTC messages */ switch (be16_to_cpu(*msg_id)) { case HTC_MSG_READY_ID: + if (unlikely(len < sizeof(struct htc_ready_msg))) + goto invalid; htc_process_target_rdy(htc_handle, htc_hdr); break; case HTC_MSG_CONNECT_SERVICE_RESPONSE_ID: + if (unlikely(len < sizeof(struct htc_frame_hdr) + + sizeof(struct htc_conn_svc_rspmsg))) + goto invalid; htc_process_conn_rsp(htc_handle, htc_hdr); break; default: diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c index 61039538a15bc6fdf297ad0a05124b73074a2e50..c8e1d505f7b5dddfb04d0c5d39f3091ee4ac4828 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c @@ -290,6 +290,7 @@ static netdev_tx_t brcmf_netdev_start_xmit(struct sk_buff *skb, struct brcmf_pub *drvr = ifp->drvr; struct ethhdr *eh; int head_delta; + unsigned int tx_bytes = skb->len; brcmf_dbg(DATA, "Enter, bsscfgidx=%d\n", ifp->bsscfgidx); @@ -364,7 +365,7 @@ done: ndev->stats.tx_dropped++; } else { ndev->stats.tx_packets++; - ndev->stats.tx_bytes += skb->len; + ndev->stats.tx_bytes += tx_bytes; } /* Return ok: we always eat the packet */ diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.c index 430d2cca98b336919bd75a77356489996c539f76..1285d3685c4f51d15e2dfabe9e3700c5b5cb57c0 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.c @@ -228,6 +228,10 @@ static void brcmf_fweh_event_worker(struct work_struct *work) brcmf_fweh_event_name(event->code), event->code, event->emsg.ifidx, event->emsg.bsscfgidx, event->emsg.addr); + if (event->emsg.bsscfgidx >= BRCMF_MAX_IFS) { + bphy_err(drvr, "invalid bsscfg index: %u\n", event->emsg.bsscfgidx); + goto event_free; + } /* convert event message */ emsg_be = &event->emsg; diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pno.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pno.c index fabfbb0b40b0ca09aafd74433bc42efedc516e85..d0a7465be586dc899bfa581163825c836fd10d50 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pno.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pno.c @@ -158,12 +158,12 @@ static int brcmf_pno_set_random(struct brcmf_if *ifp, struct brcmf_pno_info *pi) struct brcmf_pno_macaddr_le pfn_mac; u8 *mac_addr = NULL; u8 *mac_mask = NULL; - int err, i; + int err, i, ri; - for (i = 0; i < pi->n_reqs; i++) - if (pi->reqs[i]->flags & NL80211_SCAN_FLAG_RANDOM_ADDR) { - mac_addr = pi->reqs[i]->mac_addr; - mac_mask = pi->reqs[i]->mac_addr_mask; + for (ri = 0; ri < pi->n_reqs; ri++) + if (pi->reqs[ri]->flags & NL80211_SCAN_FLAG_RANDOM_ADDR) { + mac_addr = pi->reqs[ri]->mac_addr; + mac_mask = pi->reqs[ri]->mac_addr_mask; break; } @@ -185,7 +185,7 @@ static int brcmf_pno_set_random(struct brcmf_if *ifp, struct brcmf_pno_info *pi) pfn_mac.mac[0] |= 0x02; brcmf_dbg(SCAN, "enabling random mac: reqid=%llu mac=%pM\n", - pi->reqs[i]->reqid, pfn_mac.mac); + pi->reqs[ri]->reqid, pfn_mac.mac); err = brcmf_fil_iovar_data_set(ifp, "pfn_macaddr", &pfn_mac, sizeof(pfn_mac)); if (err) diff --git a/drivers/net/wireless/cisco/airo.c b/drivers/net/wireless/cisco/airo.c index 0569f37e9ed59a7ab7d11408d3e45718552c478e..8c9c6bfbaeee7e5ec053d8cc2825be505e18531f 100644 --- a/drivers/net/wireless/cisco/airo.c +++ b/drivers/net/wireless/cisco/airo.c @@ -5236,7 +5236,7 @@ static int get_wep_tx_idx(struct airo_info *ai) return -1; } -static int set_wep_key(struct airo_info *ai, u16 index, const char *key, +static int set_wep_key(struct airo_info *ai, u16 index, const u8 *key, u16 keylen, int perm, int lock) { static const unsigned char macaddr[ETH_ALEN] = { 0x01, 0, 0, 0, 0, 0 }; @@ -5287,7 +5287,7 @@ static void proc_wepkey_on_close(struct inode *inode, struct file *file) struct net_device *dev = PDE_DATA(inode); struct airo_info *ai = dev->ml_priv; int i, rc; - char key[16]; + u8 key[16]; u16 index = 0; int j = 0; @@ -5315,12 +5315,22 @@ static void proc_wepkey_on_close(struct inode *inode, struct file *file) } for (i = 0; i < 16*3 && data->wbuffer[i+j]; i++) { + int val; + + if (i % 3 == 2) + continue; + + val = hex_to_bin(data->wbuffer[i+j]); + if (val < 0) { + airo_print_err(ai->dev->name, "WebKey passed invalid key hex"); + return; + } switch(i%3) { case 0: - key[i/3] = hex_to_bin(data->wbuffer[i+j])<<4; + key[i/3] = (u8)val << 4; break; case 1: - key[i/3] |= hex_to_bin(data->wbuffer[i+j]); + key[i/3] |= (u8)val; break; } } diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 40e2110970e9923adb25cef7f81dcd27a1204984..3da8ff71ffccb322c11cd30375f8ed297c093ba0 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -779,6 +779,7 @@ static void hwsim_send_nullfunc(struct mac80211_hwsim_data *data, u8 *mac, struct hwsim_vif_priv *vp = (void *)vif->drv_priv; struct sk_buff *skb; struct ieee80211_hdr *hdr; + struct ieee80211_tx_info *cb; if (!vp->assoc) return; @@ -800,6 +801,10 @@ static void hwsim_send_nullfunc(struct mac80211_hwsim_data *data, u8 *mac, memcpy(hdr->addr2, mac, ETH_ALEN); memcpy(hdr->addr3, vp->bssid, ETH_ALEN); + cb = IEEE80211_SKB_CB(skb); + cb->control.rates[0].count = 1; + cb->control.rates[1].idx = -1; + rcu_read_lock(); mac80211_hwsim_tx_frame(data->hw, skb, rcu_dereference(vif->chanctx_conf)->def.chan); diff --git a/drivers/net/wireless/microchip/wilc1000/cfg80211.c b/drivers/net/wireless/microchip/wilc1000/cfg80211.c index 6be5ac8ba518d84e70e6c66a63fc13769846097e..dd26f2086180732ebd62fdf3f1ed7797f89e543f 100644 --- a/drivers/net/wireless/microchip/wilc1000/cfg80211.c +++ b/drivers/net/wireless/microchip/wilc1000/cfg80211.c @@ -939,30 +939,52 @@ static inline void wilc_wfi_cfg_parse_ch_attr(u8 *buf, u32 len, u8 sta_ch) return; while (index + sizeof(*e) <= len) { + u16 attr_size; + e = (struct wilc_attr_entry *)&buf[index]; - if (e->attr_type == IEEE80211_P2P_ATTR_CHANNEL_LIST) + attr_size = le16_to_cpu(e->attr_len); + + if (index + sizeof(*e) + attr_size > len) + return; + + if (e->attr_type == IEEE80211_P2P_ATTR_CHANNEL_LIST && + attr_size >= (sizeof(struct wilc_attr_ch_list) - sizeof(*e))) ch_list_idx = index; - else if (e->attr_type == IEEE80211_P2P_ATTR_OPER_CHANNEL) + else if (e->attr_type == IEEE80211_P2P_ATTR_OPER_CHANNEL && + attr_size == (sizeof(struct wilc_attr_oper_ch) - sizeof(*e))) op_ch_idx = index; + if (ch_list_idx && op_ch_idx) break; - index += le16_to_cpu(e->attr_len) + sizeof(*e); + + index += sizeof(*e) + attr_size; } if (ch_list_idx) { - u16 attr_size; - struct wilc_ch_list_elem *e; - int i; + unsigned int i; + u16 elem_size; ch_list = (struct wilc_attr_ch_list *)&buf[ch_list_idx]; - attr_size = le16_to_cpu(ch_list->attr_len); - for (i = 0; i < attr_size;) { + /* the number of bytes following the final 'elem' member */ + elem_size = le16_to_cpu(ch_list->attr_len) - + (sizeof(*ch_list) - sizeof(struct wilc_attr_entry)); + for (i = 0; i < elem_size;) { + struct wilc_ch_list_elem *e; + e = (struct wilc_ch_list_elem *)(ch_list->elem + i); + + i += sizeof(*e); + if (i > elem_size) + break; + + i += e->no_of_channels; + if (i > elem_size) + break; + if (e->op_class == WILC_WLAN_OPERATING_CLASS_2_4GHZ) { memset(e->ch_list, sta_ch, e->no_of_channels); break; } - i += e->no_of_channels; } } diff --git a/drivers/net/wireless/microchip/wilc1000/hif.c b/drivers/net/wireless/microchip/wilc1000/hif.c index d025a30930157ae694b97a2db276dc97a13adddf..b25847799138babc6d7822b91bbc0e4542c71773 100644 --- a/drivers/net/wireless/microchip/wilc1000/hif.c +++ b/drivers/net/wireless/microchip/wilc1000/hif.c @@ -467,14 +467,25 @@ void *wilc_parse_join_bss_param(struct cfg80211_bss *bss, rsn_ie = cfg80211_find_ie(WLAN_EID_RSN, ies->data, ies->len); if (rsn_ie) { + int rsn_ie_len = sizeof(struct element) + rsn_ie[1]; int offset = 8; - param->mode_802_11i = 2; - param->rsn_found = true; /* extract RSN capabilities */ - offset += (rsn_ie[offset] * 4) + 2; - offset += (rsn_ie[offset] * 4) + 2; - memcpy(param->rsn_cap, &rsn_ie[offset], 2); + if (offset < rsn_ie_len) { + /* skip over pairwise suites */ + offset += (rsn_ie[offset] * 4) + 2; + + if (offset < rsn_ie_len) { + /* skip over authentication suites */ + offset += (rsn_ie[offset] * 4) + 2; + + if (offset + 1 < rsn_ie_len) { + param->mode_802_11i = 2; + param->rsn_found = true; + memcpy(param->rsn_cap, &rsn_ie[offset], 2); + } + } + } } if (param->rsn_found) { diff --git a/drivers/net/wireless/ralink/rt2x00/rt2800lib.c b/drivers/net/wireless/ralink/rt2x00/rt2800lib.c index fed6d21cd6ce19c8d728902a9925f5b782196e28..4bdd3a95f2d2153eba99231b34ace016c1e6545e 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2800lib.c +++ b/drivers/net/wireless/ralink/rt2x00/rt2800lib.c @@ -4151,7 +4151,10 @@ static void rt2800_config_channel(struct rt2x00_dev *rt2x00dev, rt2800_bbp_write(rt2x00dev, 62, 0x37 - rt2x00dev->lna_gain); rt2800_bbp_write(rt2x00dev, 63, 0x37 - rt2x00dev->lna_gain); rt2800_bbp_write(rt2x00dev, 64, 0x37 - rt2x00dev->lna_gain); - rt2800_bbp_write(rt2x00dev, 86, 0); + if (rt2x00_rt(rt2x00dev, RT6352)) + rt2800_bbp_write(rt2x00dev, 86, 0x38); + else + rt2800_bbp_write(rt2x00dev, 86, 0); } if (rf->channel <= 14) { @@ -4352,7 +4355,8 @@ static void rt2800_config_channel(struct rt2x00_dev *rt2x00dev, reg = (rf->channel <= 14 ? 0x1c : 0x24) + 2*rt2x00dev->lna_gain; rt2800_bbp_write_with_rx_chain(rt2x00dev, 66, reg); - rt2800_iq_calibrate(rt2x00dev, rf->channel); + if (rt2x00_rt(rt2x00dev, RT5592)) + rt2800_iq_calibrate(rt2x00dev, rf->channel); } bbp = rt2800_bbp_read(rt2x00dev, 4); @@ -5625,7 +5629,8 @@ static inline void rt2800_set_vgc(struct rt2x00_dev *rt2x00dev, if (qual->vgc_level != vgc_level) { if (rt2x00_rt(rt2x00dev, RT3572) || rt2x00_rt(rt2x00dev, RT3593) || - rt2x00_rt(rt2x00dev, RT3883)) { + rt2x00_rt(rt2x00dev, RT3883) || + rt2x00_rt(rt2x00dev, RT6352)) { rt2800_bbp_write_with_rx_chain(rt2x00dev, 66, vgc_level); } else if (rt2x00_rt(rt2x00dev, RT5592)) { @@ -5848,7 +5853,7 @@ static int rt2800_init_registers(struct rt2x00_dev *rt2x00dev) rt2800_register_write(rt2x00dev, TX_SW_CFG0, 0x00000404); } else if (rt2x00_rt(rt2x00dev, RT6352)) { rt2800_register_write(rt2x00dev, TX_SW_CFG0, 0x00000401); - rt2800_register_write(rt2x00dev, TX_SW_CFG1, 0x000C0000); + rt2800_register_write(rt2x00dev, TX_SW_CFG1, 0x000C0001); rt2800_register_write(rt2x00dev, TX_SW_CFG2, 0x00000000); rt2800_register_write(rt2x00dev, TX_ALC_VGA3, 0x00000000); rt2800_register_write(rt2x00dev, TX0_BB_GAIN_ATTEN, 0x0); @@ -6110,6 +6115,27 @@ static int rt2800_init_registers(struct rt2x00_dev *rt2x00dev) reg = rt2800_register_read(rt2x00dev, US_CYC_CNT); rt2x00_set_field32(®, US_CYC_CNT_CLOCK_CYCLE, 125); rt2800_register_write(rt2x00dev, US_CYC_CNT, reg); + } else if (rt2x00_is_soc(rt2x00dev)) { + struct clk *clk = clk_get_sys("bus", NULL); + int rate; + + if (IS_ERR(clk)) { + clk = clk_get_sys("cpu", NULL); + + if (IS_ERR(clk)) { + rate = 125; + } else { + rate = clk_get_rate(clk) / 3000000; + clk_put(clk); + } + } else { + rate = clk_get_rate(clk) / 1000000; + clk_put(clk); + } + + reg = rt2800_register_read(rt2x00dev, US_CYC_CNT); + rt2x00_set_field32(®, US_CYC_CNT_CLOCK_CYCLE, rate); + rt2800_register_write(rt2x00dev, US_CYC_CNT, reg); } reg = rt2800_register_read(rt2x00dev, HT_FBK_CFG0); diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c index 0d374a29484060944cd73666b79646ea22004a46..e34cd6fed7e885e84d08bc531a640f308aa5a4d3 100644 --- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c +++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c @@ -1874,13 +1874,6 @@ static int rtl8xxxu_read_efuse(struct rtl8xxxu_priv *priv) /* We have 8 bits to indicate validity */ map_addr = offset * 8; - if (map_addr >= EFUSE_MAP_LEN) { - dev_warn(dev, "%s: Illegal map_addr (%04x), " - "efuse corrupt!\n", - __func__, map_addr); - ret = -EINVAL; - goto exit; - } for (i = 0; i < EFUSE_MAX_WORD_UNIT; i++) { /* Check word enable condition in the section */ if (word_mask & BIT(i)) { @@ -1891,6 +1884,13 @@ static int rtl8xxxu_read_efuse(struct rtl8xxxu_priv *priv) ret = rtl8xxxu_read_efuse8(priv, efuse_addr++, &val8); if (ret) goto exit; + if (map_addr >= EFUSE_MAP_LEN - 1) { + dev_warn(dev, "%s: Illegal map_addr (%04x), " + "efuse corrupt!\n", + __func__, map_addr); + ret = -EINVAL; + goto exit; + } priv->efuse_wifi.raw[map_addr++] = val8; ret = rtl8xxxu_read_efuse8(priv, efuse_addr++, &val8); @@ -2925,12 +2925,12 @@ bool rtl8xxxu_gen2_simularity_compare(struct rtl8xxxu_priv *priv, } if (!(simubitmap & 0x30) && priv->tx_paths > 1) { - /* path B RX OK */ + /* path B TX OK */ for (i = 4; i < 6; i++) result[3][i] = result[c1][i]; } - if (!(simubitmap & 0x30) && priv->tx_paths > 1) { + if (!(simubitmap & 0xc0) && priv->tx_paths > 1) { /* path B RX OK */ for (i = 6; i < 8; i++) result[3][i] = result[c1][i]; @@ -4338,15 +4338,14 @@ void rtl8xxxu_gen2_update_rate_mask(struct rtl8xxxu_priv *priv, h2c.b_macid_cfg.ramask2 = (ramask >> 16) & 0xff; h2c.b_macid_cfg.ramask3 = (ramask >> 24) & 0xff; - h2c.ramask.arg = 0x80; h2c.b_macid_cfg.data1 = rateid; if (sgi) h2c.b_macid_cfg.data1 |= BIT(7); h2c.b_macid_cfg.data2 = bw; - dev_dbg(&priv->udev->dev, "%s: rate mask %08x, arg %02x, size %zi\n", - __func__, ramask, h2c.ramask.arg, sizeof(h2c.b_macid_cfg)); + dev_dbg(&priv->udev->dev, "%s: rate mask %08x, rateid %02x, sgi %d, size %zi\n", + __func__, ramask, rateid, sgi, sizeof(h2c.b_macid_cfg)); rtl8xxxu_gen2_h2c_cmd(priv, &h2c, sizeof(h2c.b_macid_cfg)); } @@ -4508,6 +4507,53 @@ rtl8xxxu_wireless_mode(struct ieee80211_hw *hw, struct ieee80211_sta *sta) return network_type; } +static void rtl8xxxu_set_aifs(struct rtl8xxxu_priv *priv, u8 slot_time) +{ + u32 reg_edca_param[IEEE80211_NUM_ACS] = { + [IEEE80211_AC_VO] = REG_EDCA_VO_PARAM, + [IEEE80211_AC_VI] = REG_EDCA_VI_PARAM, + [IEEE80211_AC_BE] = REG_EDCA_BE_PARAM, + [IEEE80211_AC_BK] = REG_EDCA_BK_PARAM, + }; + u32 val32; + u16 wireless_mode = 0; + u8 aifs, aifsn, sifs; + int i; + + if (priv->vif) { + struct ieee80211_sta *sta; + + rcu_read_lock(); + sta = ieee80211_find_sta(priv->vif, priv->vif->bss_conf.bssid); + if (sta) + wireless_mode = rtl8xxxu_wireless_mode(priv->hw, sta); + rcu_read_unlock(); + } + + if (priv->hw->conf.chandef.chan->band == NL80211_BAND_5GHZ || + (wireless_mode & WIRELESS_MODE_N_24G)) + sifs = 16; + else + sifs = 10; + + for (i = 0; i < IEEE80211_NUM_ACS; i++) { + val32 = rtl8xxxu_read32(priv, reg_edca_param[i]); + + /* It was set in conf_tx. */ + aifsn = val32 & 0xff; + + /* aifsn not set yet or already fixed */ + if (aifsn < 2 || aifsn > 15) + continue; + + aifs = aifsn * slot_time + sifs; + + val32 &= ~0xff; + val32 |= aifs; + rtl8xxxu_write32(priv, reg_edca_param[i], val32); + } +} + static void rtl8xxxu_bss_info_changed(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_bss_conf *bss_conf, u32 changed) @@ -4593,6 +4639,8 @@ rtl8xxxu_bss_info_changed(struct ieee80211_hw *hw, struct ieee80211_vif *vif, else val8 = 20; rtl8xxxu_write8(priv, REG_SLOT, val8); + + rtl8xxxu_set_aifs(priv, val8); } if (changed & BSS_CHANGED_BSSID) { @@ -4984,6 +5032,8 @@ static void rtl8xxxu_tx(struct ieee80211_hw *hw, if (control && control->sta) sta = control->sta; + queue = rtl8xxxu_queue_select(hw, skb); + tx_desc = skb_push(skb, tx_desc_size); memset(tx_desc, 0, tx_desc_size); @@ -4996,7 +5046,6 @@ static void rtl8xxxu_tx(struct ieee80211_hw *hw, is_broadcast_ether_addr(ieee80211_get_DA(hdr))) tx_desc->txdw0 |= TXDESC_BROADMULTICAST; - queue = rtl8xxxu_queue_select(hw, skb); tx_desc->txdw1 = cpu_to_le32(queue << TXDESC_QUEUE_SHIFT); if (tx_info->control.hw_key) { diff --git a/drivers/nfc/fdp/fdp.c b/drivers/nfc/fdp/fdp.c index 4dc7bd7e02b6b79cda90f79c4bfcc8c3c3e4ed48..90bea6a1db6921de0534b594ac1939c105a4d251 100644 --- a/drivers/nfc/fdp/fdp.c +++ b/drivers/nfc/fdp/fdp.c @@ -238,9 +238,6 @@ static int fdp_nci_open(struct nci_dev *ndev) { int r; struct fdp_nci_info *info = nci_get_drvdata(ndev); - struct device *dev = &info->phy->i2c_dev->dev; - - dev_dbg(dev, "%s\n", __func__); r = info->phy_ops->enable(info->phy); @@ -249,35 +246,26 @@ static int fdp_nci_open(struct nci_dev *ndev) static int fdp_nci_close(struct nci_dev *ndev) { - struct fdp_nci_info *info = nci_get_drvdata(ndev); - struct device *dev = &info->phy->i2c_dev->dev; - - dev_dbg(dev, "%s\n", __func__); return 0; } static int fdp_nci_send(struct nci_dev *ndev, struct sk_buff *skb) { struct fdp_nci_info *info = nci_get_drvdata(ndev); - struct device *dev = &info->phy->i2c_dev->dev; - - dev_dbg(dev, "%s\n", __func__); + int ret; if (atomic_dec_and_test(&info->data_pkt_counter)) info->data_pkt_counter_cb(ndev); - return info->phy_ops->write(info->phy, skb); -} - -int fdp_nci_recv_frame(struct nci_dev *ndev, struct sk_buff *skb) -{ - struct fdp_nci_info *info = nci_get_drvdata(ndev); - struct device *dev = &info->phy->i2c_dev->dev; + ret = info->phy_ops->write(info->phy, skb); + if (ret < 0) { + kfree_skb(skb); + return ret; + } - dev_dbg(dev, "%s\n", __func__); - return nci_recv_frame(ndev, skb); + consume_skb(skb); + return 0; } -EXPORT_SYMBOL(fdp_nci_recv_frame); static int fdp_nci_request_firmware(struct nci_dev *ndev) { @@ -489,8 +477,6 @@ static int fdp_nci_setup(struct nci_dev *ndev) int r; u8 patched = 0; - dev_dbg(dev, "%s\n", __func__); - r = nci_core_init(ndev); if (r) goto error; @@ -598,9 +584,7 @@ static int fdp_nci_core_reset_ntf_packet(struct nci_dev *ndev, struct sk_buff *skb) { struct fdp_nci_info *info = nci_get_drvdata(ndev); - struct device *dev = &info->phy->i2c_dev->dev; - dev_dbg(dev, "%s\n", __func__); info->setup_reset_ntf = 1; wake_up(&info->setup_wq); @@ -611,9 +595,7 @@ static int fdp_nci_prop_patch_ntf_packet(struct nci_dev *ndev, struct sk_buff *skb) { struct fdp_nci_info *info = nci_get_drvdata(ndev); - struct device *dev = &info->phy->i2c_dev->dev; - dev_dbg(dev, "%s\n", __func__); info->setup_patch_ntf = 1; info->setup_patch_status = skb->data[0]; wake_up(&info->setup_wq); @@ -786,11 +768,6 @@ EXPORT_SYMBOL(fdp_nci_probe); void fdp_nci_remove(struct nci_dev *ndev) { - struct fdp_nci_info *info = nci_get_drvdata(ndev); - struct device *dev = &info->phy->i2c_dev->dev; - - dev_dbg(dev, "%s\n", __func__); - nci_unregister_device(ndev); nci_free_device(ndev); } diff --git a/drivers/nfc/fdp/fdp.h b/drivers/nfc/fdp/fdp.h index 9bd1f3f23e2d1ff20a1938280d2883b2108c7c77..ead3b21ccae68eb8e2f0509b070c22f15c0c119e 100644 --- a/drivers/nfc/fdp/fdp.h +++ b/drivers/nfc/fdp/fdp.h @@ -25,6 +25,5 @@ int fdp_nci_probe(struct fdp_i2c_phy *phy, struct nfc_phy_ops *phy_ops, struct nci_dev **ndev, int tx_headroom, int tx_tailroom, u8 clock_type, u32 clock_freq, u8 *fw_vsc_cfg); void fdp_nci_remove(struct nci_dev *ndev); -int fdp_nci_recv_frame(struct nci_dev *ndev, struct sk_buff *skb); #endif /* __LOCAL_FDP_H_ */ diff --git a/drivers/nfc/fdp/i2c.c b/drivers/nfc/fdp/i2c.c index ad0abb1f0bae9b76135d9f41ed2763d36c95ebac..5e300788be52555d46868a8d73b8ab67d0ceb21f 100644 --- a/drivers/nfc/fdp/i2c.c +++ b/drivers/nfc/fdp/i2c.c @@ -49,7 +49,6 @@ static int fdp_nci_i2c_enable(void *phy_id) { struct fdp_i2c_phy *phy = phy_id; - dev_dbg(&phy->i2c_dev->dev, "%s\n", __func__); fdp_nci_i2c_reset(phy); return 0; @@ -59,7 +58,6 @@ static void fdp_nci_i2c_disable(void *phy_id) { struct fdp_i2c_phy *phy = phy_id; - dev_dbg(&phy->i2c_dev->dev, "%s\n", __func__); fdp_nci_i2c_reset(phy); } @@ -197,7 +195,6 @@ flush: static irqreturn_t fdp_nci_i2c_irq_thread_fn(int irq, void *phy_id) { struct fdp_i2c_phy *phy = phy_id; - struct i2c_client *client; struct sk_buff *skb; int r; @@ -206,9 +203,6 @@ static irqreturn_t fdp_nci_i2c_irq_thread_fn(int irq, void *phy_id) return IRQ_NONE; } - client = phy->i2c_dev; - dev_dbg(&client->dev, "%s\n", __func__); - r = fdp_nci_i2c_read(phy, &skb); if (r == -EREMOTEIO) @@ -217,7 +211,7 @@ static irqreturn_t fdp_nci_i2c_irq_thread_fn(int irq, void *phy_id) return IRQ_HANDLED; if (skb != NULL) - fdp_nci_recv_frame(phy->ndev, skb); + nci_recv_frame(phy->ndev, skb); return IRQ_HANDLED; } @@ -288,8 +282,6 @@ static int fdp_nci_i2c_probe(struct i2c_client *client) u32 clock_freq; int r = 0; - dev_dbg(dev, "%s\n", __func__); - if (!i2c_check_functionality(client->adapter, I2C_FUNC_I2C)) { nfc_err(dev, "No I2C_FUNC_I2C support\n"); return -ENODEV; @@ -351,8 +343,6 @@ static int fdp_nci_i2c_remove(struct i2c_client *client) { struct fdp_i2c_phy *phy = i2c_get_clientdata(client); - dev_dbg(&client->dev, "%s\n", __func__); - fdp_nci_remove(phy->ndev); fdp_nci_i2c_disable(phy); diff --git a/drivers/nfc/nfcmrvl/i2c.c b/drivers/nfc/nfcmrvl/i2c.c index f81f1cae932439656fe49dac6d924606aa71f400..41f27e1cac20a8ea1fa558047f85b088e6e19981 100644 --- a/drivers/nfc/nfcmrvl/i2c.c +++ b/drivers/nfc/nfcmrvl/i2c.c @@ -151,10 +151,15 @@ static int nfcmrvl_i2c_nci_send(struct nfcmrvl_private *priv, ret = -EREMOTEIO; } else ret = 0; + } + + if (ret) { kfree_skb(skb); + return ret; } - return ret; + consume_skb(skb); + return 0; } static void nfcmrvl_i2c_nci_update_config(struct nfcmrvl_private *priv, diff --git a/drivers/nfc/nxp-nci/core.c b/drivers/nfc/nxp-nci/core.c index a0ce95a287c545d5b1dbe76dca6f4dd6220db1e7..b68b315689c3afee55e5c8b298539e42b17ceb56 100644 --- a/drivers/nfc/nxp-nci/core.c +++ b/drivers/nfc/nxp-nci/core.c @@ -70,22 +70,20 @@ static int nxp_nci_send(struct nci_dev *ndev, struct sk_buff *skb) struct nxp_nci_info *info = nci_get_drvdata(ndev); int r; - if (!info->phy_ops->write) { - r = -ENOTSUPP; - goto send_exit; - } + if (!info->phy_ops->write) + return -EOPNOTSUPP; - if (info->mode != NXP_NCI_MODE_NCI) { - r = -EINVAL; - goto send_exit; - } + if (info->mode != NXP_NCI_MODE_NCI) + return -EINVAL; r = info->phy_ops->write(info->phy_id, skb); - if (r < 0) + if (r < 0) { kfree_skb(skb); + return r; + } -send_exit: - return r; + consume_skb(skb); + return 0; } static struct nci_ops nxp_nci_ops = { @@ -104,10 +102,8 @@ int nxp_nci_probe(void *phy_id, struct device *pdev, int r; info = devm_kzalloc(pdev, sizeof(struct nxp_nci_info), GFP_KERNEL); - if (!info) { - r = -ENOMEM; - goto probe_exit; - } + if (!info) + return -ENOMEM; info->phy_id = phy_id; info->pdev = pdev; @@ -120,31 +116,25 @@ int nxp_nci_probe(void *phy_id, struct device *pdev, if (info->phy_ops->set_mode) { r = info->phy_ops->set_mode(info->phy_id, NXP_NCI_MODE_COLD); if (r < 0) - goto probe_exit; + return r; } info->mode = NXP_NCI_MODE_COLD; info->ndev = nci_allocate_device(&nxp_nci_ops, NXP_NCI_NFC_PROTOCOLS, NXP_NCI_HDR_LEN, 0); - if (!info->ndev) { - r = -ENOMEM; - goto probe_exit; - } + if (!info->ndev) + return -ENOMEM; nci_set_parent_dev(info->ndev, pdev); nci_set_drvdata(info->ndev, info); r = nci_register_device(info->ndev); - if (r < 0) - goto probe_exit_free_nci; + if (r < 0) { + nci_free_device(info->ndev); + return r; + } *ndev = info->ndev; - - goto probe_exit; - -probe_exit_free_nci: - nci_free_device(info->ndev); -probe_exit: return r; } EXPORT_SYMBOL(nxp_nci_probe); diff --git a/drivers/nfc/s3fwrn5/core.c b/drivers/nfc/s3fwrn5/core.c index ba6c486d64659720431977b28e6d44a43659ca5e..9b43cd3a45afc894eec92b6678ba134580a7692e 100644 --- a/drivers/nfc/s3fwrn5/core.c +++ b/drivers/nfc/s3fwrn5/core.c @@ -97,11 +97,15 @@ static int s3fwrn5_nci_send(struct nci_dev *ndev, struct sk_buff *skb) } ret = s3fwrn5_write(info, skb); - if (ret < 0) + if (ret < 0) { kfree_skb(skb); + mutex_unlock(&info->mutex); + return ret; + } + consume_skb(skb); mutex_unlock(&info->mutex); - return ret; + return 0; } static int s3fwrn5_nci_post_setup(struct nci_dev *ndev) diff --git a/drivers/nfc/st-nci/se.c b/drivers/nfc/st-nci/se.c index 807eae04c1e34d68f1f9dd893d98393095afd006..37d397aae9b9d0b53df99830f5992677278ca304 100644 --- a/drivers/nfc/st-nci/se.c +++ b/drivers/nfc/st-nci/se.c @@ -327,7 +327,7 @@ static int st_nci_hci_connectivity_event_received(struct nci_dev *ndev, * AID 81 5 to 16 * PARAMETERS 82 0 to 255 */ - if (skb->len < NFC_MIN_AID_LENGTH + 2 && + if (skb->len < NFC_MIN_AID_LENGTH + 2 || skb->data[0] != NFC_EVT_TRANSACTION_AID_TAG) return -EPROTO; @@ -340,8 +340,10 @@ static int st_nci_hci_connectivity_event_received(struct nci_dev *ndev, /* Check next byte is PARAMETERS tag (82) */ if (skb->data[transaction->aid_len + 2] != - NFC_EVT_TRANSACTION_PARAMS_TAG) + NFC_EVT_TRANSACTION_PARAMS_TAG) { + devm_kfree(dev, transaction); return -EPROTO; + } transaction->params_len = skb->data[transaction->aid_len + 3]; memcpy(transaction->params, skb->data + diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 265d9199b657f915a258761ffbd73ecffed3ddc4..d9c78fe85cb38d942bf10d4cc654a92d1264c02c 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -2949,7 +2949,6 @@ static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id) nvme_init_subnqn(subsys, ctrl, id); memcpy(subsys->serial, id->sn, sizeof(subsys->serial)); memcpy(subsys->model, id->mn, sizeof(subsys->model)); - memcpy(subsys->firmware_rev, id->fr, sizeof(subsys->firmware_rev)); subsys->vendor_id = le16_to_cpu(id->vid); subsys->cmic = id->cmic; subsys->awupf = le16_to_cpu(id->awupf); @@ -3110,6 +3109,8 @@ int nvme_init_identify(struct nvme_ctrl *ctrl) ctrl->quirks |= core_quirks[i].quirks; } } + memcpy(ctrl->subsys->firmware_rev, id->fr, + sizeof(ctrl->subsys->firmware_rev)); if (force_apst && (ctrl->quirks & NVME_QUIRK_NO_DEEPEST_PS)) { dev_warn(ctrl->device, "forcibly allowing all power states due to nvme_core.force_apst -- use at your own risk\n"); @@ -3231,8 +3232,12 @@ int nvme_init_identify(struct nvme_ctrl *ctrl) return ret; if (!ctrl->identified && !nvme_discovery_ctrl(ctrl)) { + /* + * Do not return errors unless we are in a controller reset, + * the controller works perfectly fine without hwmon. + */ ret = nvme_hwmon_init(ctrl); - if (ret < 0) + if (ret == -EINTR) return ret; } @@ -3325,11 +3330,17 @@ static long nvme_dev_ioctl(struct file *file, unsigned int cmd, case NVME_IOCTL_IO_CMD: return nvme_dev_user_cmd(ctrl, argp); case NVME_IOCTL_RESET: + if (!capable(CAP_SYS_ADMIN)) + return -EACCES; dev_warn(ctrl->device, "resetting controller\n"); return nvme_reset_ctrl_sync(ctrl); case NVME_IOCTL_SUBSYS_RESET: + if (!capable(CAP_SYS_ADMIN)) + return -EACCES; return nvme_reset_subsystem(ctrl); case NVME_IOCTL_RESCAN: + if (!capable(CAP_SYS_ADMIN)) + return -EACCES; nvme_queue_scan(ctrl); return 0; default: @@ -4484,6 +4495,7 @@ EXPORT_SYMBOL_GPL(nvme_start_ctrl); void nvme_uninit_ctrl(struct nvme_ctrl *ctrl) { + nvme_hwmon_exit(ctrl); nvme_fault_inject_fini(&ctrl->fault_inject); dev_pm_qos_hide_latency_tolerance(ctrl->device); cdev_device_del(&ctrl->cdev, ctrl->device); diff --git a/drivers/nvme/host/hwmon.c b/drivers/nvme/host/hwmon.c index 552dbc04567bcbf5a2ca26b935d0f771187e8506..9e6e56c20ec993bfca3ee2eb18d2e371d7225230 100644 --- a/drivers/nvme/host/hwmon.c +++ b/drivers/nvme/host/hwmon.c @@ -12,7 +12,7 @@ struct nvme_hwmon_data { struct nvme_ctrl *ctrl; - struct nvme_smart_log log; + struct nvme_smart_log *log; struct mutex read_lock; }; @@ -60,14 +60,14 @@ static int nvme_set_temp_thresh(struct nvme_ctrl *ctrl, int sensor, bool under, static int nvme_hwmon_get_smart_log(struct nvme_hwmon_data *data) { return nvme_get_log(data->ctrl, NVME_NSID_ALL, NVME_LOG_SMART, 0, - NVME_CSI_NVM, &data->log, sizeof(data->log), 0); + NVME_CSI_NVM, data->log, sizeof(*data->log), 0); } static int nvme_hwmon_read(struct device *dev, enum hwmon_sensor_types type, u32 attr, int channel, long *val) { struct nvme_hwmon_data *data = dev_get_drvdata(dev); - struct nvme_smart_log *log = &data->log; + struct nvme_smart_log *log = data->log; int temp; int err; @@ -163,7 +163,7 @@ static umode_t nvme_hwmon_is_visible(const void *_data, case hwmon_temp_max: case hwmon_temp_min: if ((!channel && data->ctrl->wctemp) || - (channel && data->log.temp_sensor[channel - 1])) { + (channel && data->log->temp_sensor[channel - 1])) { if (data->ctrl->quirks & NVME_QUIRK_NO_TEMP_THRESH_CHANGE) return 0444; @@ -176,7 +176,7 @@ static umode_t nvme_hwmon_is_visible(const void *_data, break; case hwmon_temp_input: case hwmon_temp_label: - if (!channel || data->log.temp_sensor[channel - 1]) + if (!channel || data->log->temp_sensor[channel - 1]) return 0444; break; default: @@ -223,33 +223,57 @@ static const struct hwmon_chip_info nvme_hwmon_chip_info = { int nvme_hwmon_init(struct nvme_ctrl *ctrl) { - struct device *dev = ctrl->dev; + struct device *dev = ctrl->device; struct nvme_hwmon_data *data; struct device *hwmon; int err; - data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL); + data = kzalloc(sizeof(*data), GFP_KERNEL); if (!data) - return 0; + return -ENOMEM; + + data->log = kzalloc(sizeof(*data->log), GFP_KERNEL); + if (!data->log) { + err = -ENOMEM; + goto err_free_data; + } data->ctrl = ctrl; mutex_init(&data->read_lock); err = nvme_hwmon_get_smart_log(data); if (err) { - dev_warn(ctrl->device, - "Failed to read smart log (error %d)\n", err); - devm_kfree(dev, data); - return err; + dev_warn(dev, "Failed to read smart log (error %d)\n", err); + goto err_free_log; } - hwmon = devm_hwmon_device_register_with_info(dev, "nvme", data, - &nvme_hwmon_chip_info, - NULL); + hwmon = hwmon_device_register_with_info(dev, "nvme", + data, &nvme_hwmon_chip_info, + NULL); if (IS_ERR(hwmon)) { dev_warn(dev, "Failed to instantiate hwmon device\n"); - devm_kfree(dev, data); + err = PTR_ERR(hwmon); + goto err_free_log; } - + ctrl->hwmon_device = hwmon; return 0; + +err_free_log: + kfree(data->log); +err_free_data: + kfree(data); + return err; +} + +void nvme_hwmon_exit(struct nvme_ctrl *ctrl) +{ + if (ctrl->hwmon_device) { + struct nvme_hwmon_data *data = + dev_get_drvdata(ctrl->hwmon_device); + + hwmon_device_unregister(ctrl->hwmon_device); + ctrl->hwmon_device = NULL; + kfree(data->log); + kfree(data); + } } diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 58cf9e39d613e0a078c5add5d1c77e278d26ee32..86336496c65ce6782187721ace862c0090de9553 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -257,6 +257,9 @@ struct nvme_ctrl { struct rw_semaphore namespaces_rwsem; struct device ctrl_device; struct device *device; /* char device */ +#ifdef CONFIG_NVME_HWMON + struct device *hwmon_device; +#endif struct cdev cdev; struct work_struct reset_work; struct work_struct delete_work; @@ -541,11 +544,23 @@ static inline void nvme_fault_inject_fini(struct nvme_fault_inject *fault_inj) static inline void nvme_should_fail(struct request *req) {} #endif +bool nvme_wait_reset(struct nvme_ctrl *ctrl); +int nvme_try_sched_reset(struct nvme_ctrl *ctrl); + static inline int nvme_reset_subsystem(struct nvme_ctrl *ctrl) { + int ret; + if (!ctrl->subsystem) return -ENOTTY; - return ctrl->ops->reg_write32(ctrl, NVME_REG_NSSR, 0x4E564D65); + if (!nvme_wait_reset(ctrl)) + return -EBUSY; + + ret = ctrl->ops->reg_write32(ctrl, NVME_REG_NSSR, 0x4E564D65); + if (ret) + return ret; + + return nvme_try_sched_reset(ctrl); } /* @@ -632,7 +647,6 @@ void nvme_cancel_tagset(struct nvme_ctrl *ctrl); void nvme_cancel_admin_tagset(struct nvme_ctrl *ctrl); bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl, enum nvme_ctrl_state new_state); -bool nvme_wait_reset(struct nvme_ctrl *ctrl); int nvme_disable_ctrl(struct nvme_ctrl *ctrl); int nvme_enable_ctrl(struct nvme_ctrl *ctrl); int nvme_shutdown_ctrl(struct nvme_ctrl *ctrl); @@ -685,7 +699,6 @@ int nvme_set_queue_count(struct nvme_ctrl *ctrl, int *count); void nvme_stop_keep_alive(struct nvme_ctrl *ctrl); int nvme_reset_ctrl(struct nvme_ctrl *ctrl); int nvme_reset_ctrl_sync(struct nvme_ctrl *ctrl); -int nvme_try_sched_reset(struct nvme_ctrl *ctrl); int nvme_delete_ctrl(struct nvme_ctrl *ctrl); int nvme_get_log(struct nvme_ctrl *ctrl, u32 nsid, u8 log_page, u8 lsp, u8 csi, @@ -876,11 +889,16 @@ static inline struct nvme_ns *nvme_get_ns_from_dev(struct device *dev) #ifdef CONFIG_NVME_HWMON int nvme_hwmon_init(struct nvme_ctrl *ctrl); +void nvme_hwmon_exit(struct nvme_ctrl *ctrl); #else static inline int nvme_hwmon_init(struct nvme_ctrl *ctrl) { return 0; } + +static inline void nvme_hwmon_exit(struct nvme_ctrl *ctrl) +{ +} #endif u32 nvme_command_effects(struct nvme_ctrl *ctrl, struct nvme_ns *ns, diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index ce129655ef0a3d65bb5495083446b8a50ec3ffef..089f3910358486d8da5181c69a5260a5ba21fd95 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -2624,6 +2624,8 @@ static void nvme_reset_work(struct work_struct *work) if (result) goto out_unlock; + dma_set_min_align_mask(dev->dev, NVME_CTRL_PAGE_SIZE - 1); + /* * Limit the max command size to prevent iod->sg allocations going * over a single page. @@ -2636,7 +2638,6 @@ static void nvme_reset_work(struct work_struct *work) * Don't limit the IOMMU merged segment size. */ dma_set_max_seg_size(dev->dev, 0xffffffff); - dma_set_min_align_mask(dev->dev, NVME_CTRL_PAGE_SIZE - 1); mutex_unlock(&dev->shutdown_lock); @@ -3251,6 +3252,10 @@ static const struct pci_device_id nvme_id_table[] = { { PCI_DEVICE(0x1cc1, 0x8201), /* ADATA SX8200PNP 512GB */ .driver_data = NVME_QUIRK_NO_DEEPEST_PS | NVME_QUIRK_IGNORE_DEV_SUBNQN, }, + { PCI_DEVICE(0x1344, 0x5407), /* Micron Technology Inc NVMe SSD */ + .driver_data = NVME_QUIRK_IGNORE_DEV_SUBNQN }, + { PCI_DEVICE(0x1344, 0x6001), /* Micron Nitro NVMe */ + .driver_data = NVME_QUIRK_BOGUS_NID, }, { PCI_DEVICE(0x1c5c, 0x1504), /* SK Hynix PC400 */ .driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, }, { PCI_DEVICE(0x15b7, 0x2001), /* Sandisk Skyhawk */ diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c index e3e35b9bd684602fecdad05dea39f3585100df97..2ddbd4f4f62811c0715ff4f9c35db1150cb80460 100644 --- a/drivers/nvme/target/tcp.c +++ b/drivers/nvme/target/tcp.c @@ -922,10 +922,17 @@ static int nvmet_tcp_handle_h2c_data_pdu(struct nvmet_tcp_queue *queue) struct nvme_tcp_data_pdu *data = &queue->pdu.data; struct nvmet_tcp_cmd *cmd; - if (likely(queue->nr_cmds)) + if (likely(queue->nr_cmds)) { + if (unlikely(data->ttag >= queue->nr_cmds)) { + pr_err("queue %d: received out of bound ttag %u, nr_cmds %u\n", + queue->idx, data->ttag, queue->nr_cmds); + nvmet_tcp_fatal_error(queue); + return -EPROTO; + } cmd = &queue->cmds[data->ttag]; - else + } else { cmd = &queue->connect; + } if (le32_to_cpu(data->data_offset) != cmd->rbytes_done) { pr_err("ttag %u unexpected data offset %u (expected %u)\n", diff --git a/drivers/parisc/iosapic.c b/drivers/parisc/iosapic.c index 8a3b0c3a1e92bdcfc50c664a7caea0f7818cd8d6..fd99735dca3e6f5031d64f2aaf59d7c77ab9a98f 100644 --- a/drivers/parisc/iosapic.c +++ b/drivers/parisc/iosapic.c @@ -875,6 +875,7 @@ int iosapic_serial_irq(struct parisc_device *dev) return vi->txn_irq; } +EXPORT_SYMBOL(iosapic_serial_irq); #endif diff --git a/drivers/parport/parport_pc.c b/drivers/parport/parport_pc.c index eda4ded4d5e52a11f357e249a6826d893d227ceb..925be41eeebec7c91ec024dd4073f4bd037c4e0c 100644 --- a/drivers/parport/parport_pc.c +++ b/drivers/parport/parport_pc.c @@ -468,7 +468,7 @@ static size_t parport_pc_fifo_write_block_pio(struct parport *port, const unsigned char *bufp = buf; size_t left = length; unsigned long expire = jiffies + port->physport->cad->timeout; - const int fifo = FIFO(port); + const unsigned long fifo = FIFO(port); int poll_for = 8; /* 80 usecs */ const struct parport_pc_private *priv = port->physport->private_data; const int fifo_depth = priv->fifo_depth; diff --git a/drivers/pci/controller/dwc/pcie-designware-host.c b/drivers/pci/controller/dwc/pcie-designware-host.c index acea970df067ab6544ccaf80d3c467be9ce658b4..9f0bfdbfb0b0c54143d9088a1ae837e33b8f7ebb 100644 --- a/drivers/pci/controller/dwc/pcie-designware-host.c +++ b/drivers/pci/controller/dwc/pcie-designware-host.c @@ -466,9 +466,7 @@ static void __iomem *dw_pcie_other_conf_map_bus(struct pci_bus *bus, type = PCIE_ATU_TYPE_CFG1; - dw_pcie_prog_outbound_atu(pci, PCIE_ATU_REGION_INDEX1, - type, pp->cfg0_base, - busdev, pp->cfg0_size); + dw_pcie_prog_outbound_atu(pci, 0, type, pp->cfg0_base, busdev, pp->cfg0_size); return pp->va_cfg0_base + where; } @@ -482,9 +480,9 @@ static int dw_pcie_rd_other_conf(struct pci_bus *bus, unsigned int devfn, ret = pci_generic_config_read(bus, devfn, where, size, val); - if (!ret && pci->num_viewport <= 2) - dw_pcie_prog_outbound_atu(pci, PCIE_ATU_REGION_INDEX1, - PCIE_ATU_TYPE_IO, pp->io_base, + if (!ret && ((pci->num_viewport <= 2) || + (pci->iatu_unroll_enabled & DWC_IATU_IOCFG_SHARED))) + dw_pcie_prog_outbound_atu(pci, 0, PCIE_ATU_TYPE_IO, pp->io_base, pp->io_bus_addr, pp->io_size); return ret; @@ -499,9 +497,9 @@ static int dw_pcie_wr_other_conf(struct pci_bus *bus, unsigned int devfn, ret = pci_generic_config_write(bus, devfn, where, size, val); - if (!ret && pci->num_viewport <= 2) - dw_pcie_prog_outbound_atu(pci, PCIE_ATU_REGION_INDEX1, - PCIE_ATU_TYPE_IO, pp->io_base, + if (!ret && ((pci->num_viewport <= 2) || + (pci->iatu_unroll_enabled & DWC_IATU_IOCFG_SHARED))) + dw_pcie_prog_outbound_atu(pci, 0, PCIE_ATU_TYPE_IO, pp->io_base, pp->io_bus_addr, pp->io_size); return ret; @@ -588,21 +586,33 @@ void dw_pcie_setup_rc(struct pcie_port *pp) * ATU, so we should not program the ATU here. */ if (pp->bridge->child_ops == &dw_child_pcie_ops) { - struct resource_entry *tmp, *entry = NULL; + int atu_idx = 0; + struct resource_entry *entry; /* Get last memory resource entry */ - resource_list_for_each_entry(tmp, &pp->bridge->windows) - if (resource_type(tmp->res) == IORESOURCE_MEM) - entry = tmp; - - dw_pcie_prog_outbound_atu(pci, PCIE_ATU_REGION_INDEX0, - PCIE_ATU_TYPE_MEM, entry->res->start, - entry->res->start - entry->offset, - resource_size(entry->res)); - if (pci->num_viewport > 2) - dw_pcie_prog_outbound_atu(pci, PCIE_ATU_REGION_INDEX2, - PCIE_ATU_TYPE_IO, pp->io_base, - pp->io_bus_addr, pp->io_size); + resource_list_for_each_entry(entry, &pp->bridge->windows) { + if (resource_type(entry->res) != IORESOURCE_MEM) + continue; + + if (pci->num_viewport <= ++atu_idx) + break; + + dw_pcie_prog_outbound_atu(pci, atu_idx, + PCIE_ATU_TYPE_MEM, entry->res->start, + entry->res->start - entry->offset, + resource_size(entry->res)); + } + + if (pp->io_size) { + if (pci->num_viewport > ++atu_idx) + dw_pcie_prog_outbound_atu(pci, atu_idx, + PCIE_ATU_TYPE_IO, pp->io_base, + pp->io_bus_addr, pp->io_size); + } + + if (pci->num_viewport <= atu_idx) + dev_warn(pci->dev, "Resources exceed number of ATU entries (%d)", + pci->num_viewport); } dw_pcie_writel_dbi(pci, PCI_BASE_ADDRESS_0, 0); diff --git a/drivers/pci/controller/dwc/pcie-designware.c b/drivers/pci/controller/dwc/pcie-designware.c index db8911024073751056947df1bd30e4441a88b6c6..02b369eb683e3aefb08f4e7196f01d87386a8019 100644 --- a/drivers/pci/controller/dwc/pcie-designware.c +++ b/drivers/pci/controller/dwc/pcie-designware.c @@ -274,7 +274,7 @@ static void __dw_pcie_prog_outbound_atu(struct dw_pcie *pci, u8 func_no, if (pci->ops->cpu_addr_fixup) cpu_addr = pci->ops->cpu_addr_fixup(pci, cpu_addr); - if (pci->iatu_unroll_enabled) { + if (pci->iatu_unroll_enabled & DWC_IATU_UNROLL_EN) { dw_pcie_prog_outbound_atu_unroll(pci, func_no, index, type, cpu_addr, pci_addr, size); return; @@ -394,7 +394,7 @@ int dw_pcie_prog_inbound_atu(struct dw_pcie *pci, u8 func_no, int index, int type; u32 retries, val; - if (pci->iatu_unroll_enabled) + if (pci->iatu_unroll_enabled & DWC_IATU_UNROLL_EN) return dw_pcie_prog_inbound_atu_unroll(pci, func_no, index, bar, cpu_addr, as_type); @@ -452,7 +452,7 @@ void dw_pcie_disable_atu(struct dw_pcie *pci, int index, return; } - if (pci->iatu_unroll_enabled) { + if (pci->iatu_unroll_enabled & DWC_IATU_UNROLL_EN) { if (region == PCIE_ATU_REGION_INBOUND) { dw_pcie_writel_ib_unroll(pci, index, PCIE_ATU_UNR_REGION_CTRL2, ~(u32)PCIE_ATU_ENABLE); @@ -564,14 +564,15 @@ void dw_pcie_setup(struct dw_pcie *pci) if (pci->version >= 0x480A || (!pci->version && dw_pcie_iatu_unroll_enabled(pci))) { - pci->iatu_unroll_enabled = true; + pci->iatu_unroll_enabled |= DWC_IATU_UNROLL_EN; if (!pci->atu_base) pci->atu_base = devm_platform_ioremap_resource_byname(pdev, "atu"); if (IS_ERR(pci->atu_base)) pci->atu_base = pci->dbi_base + DEFAULT_DBI_ATU_OFFSET; } - dev_dbg(pci->dev, "iATU unroll: %s\n", pci->iatu_unroll_enabled ? + dev_dbg(pci->dev, "iATU unroll: %s\n", + pci->iatu_unroll_enabled & DWC_IATU_UNROLL_EN ? "enabled" : "disabled"); if (pci->link_gen > 0) diff --git a/drivers/pci/controller/dwc/pcie-designware.h b/drivers/pci/controller/dwc/pcie-designware.h index 9d2f511f13fafad6f4c852f7866176c4da392f71..98084e8489eca8be566c07ffdf7699c35f6371b4 100644 --- a/drivers/pci/controller/dwc/pcie-designware.h +++ b/drivers/pci/controller/dwc/pcie-designware.h @@ -80,9 +80,6 @@ #define PCIE_ATU_VIEWPORT 0x900 #define PCIE_ATU_REGION_INBOUND BIT(31) #define PCIE_ATU_REGION_OUTBOUND 0 -#define PCIE_ATU_REGION_INDEX2 0x2 -#define PCIE_ATU_REGION_INDEX1 0x1 -#define PCIE_ATU_REGION_INDEX0 0x0 #define PCIE_ATU_CR1 0x904 #define PCIE_ATU_TYPE_MEM 0x0 #define PCIE_ATU_TYPE_IO 0x2 @@ -259,6 +256,8 @@ struct dw_pcie_ops { void (*stop_link)(struct dw_pcie *pcie); }; +#define DWC_IATU_UNROLL_EN BIT(0) +#define DWC_IATU_IOCFG_SHARED BIT(1) struct dw_pcie { struct device *dev; void __iomem *dbi_base; diff --git a/drivers/pci/setup-res.c b/drivers/pci/setup-res.c index 7f1acb3918d0c3c8e5304a6848a22ffd02886257..875d50c16f19d0565c6970e8e38f7a7f63dd1070 100644 --- a/drivers/pci/setup-res.c +++ b/drivers/pci/setup-res.c @@ -210,6 +210,17 @@ static int pci_revert_fw_address(struct resource *res, struct pci_dev *dev, root = pci_find_parent_resource(dev, res); if (!root) { + /* + * If dev is behind a bridge, accesses will only reach it + * if res is inside the relevant bridge window. + */ + if (pci_upstream_bridge(dev)) + return -ENXIO; + + /* + * On the root bus, assume the host bridge will forward + * everything. + */ if (res->flags & IORESOURCE_IO) root = &ioport_resource; else diff --git a/drivers/phy/qualcomm/phy-qcom-usb-hsic.c b/drivers/phy/qualcomm/phy-qcom-usb-hsic.c index 04d18d52f700d93e4d22a8f47bbae0f936788394..d4741c2dbbb565ad98ec143388eb15e9f6578e04 100644 --- a/drivers/phy/qualcomm/phy-qcom-usb-hsic.c +++ b/drivers/phy/qualcomm/phy-qcom-usb-hsic.c @@ -54,8 +54,10 @@ static int qcom_usb_hsic_phy_power_on(struct phy *phy) /* Configure pins for HSIC functionality */ pins_default = pinctrl_lookup_state(uphy->pctl, PINCTRL_STATE_DEFAULT); - if (IS_ERR(pins_default)) - return PTR_ERR(pins_default); + if (IS_ERR(pins_default)) { + ret = PTR_ERR(pins_default); + goto err_ulpi; + } ret = pinctrl_select_state(uphy->pctl, pins_default); if (ret) diff --git a/drivers/phy/st/phy-stm32-usbphyc.c b/drivers/phy/st/phy-stm32-usbphyc.c index 2b3639cba51aa77bce3b30c6757ca44fc6cfb344..03fc567e9f188a81295793a9dfcfb92ca1b64e77 100644 --- a/drivers/phy/st/phy-stm32-usbphyc.c +++ b/drivers/phy/st/phy-stm32-usbphyc.c @@ -393,6 +393,8 @@ static int stm32_usbphyc_probe(struct platform_device *pdev) ret = of_property_read_u32(child, "reg", &index); if (ret || index > usbphyc->nphys) { dev_err(&phy->dev, "invalid reg property: %d\n", ret); + if (!ret) + ret = -EINVAL; goto put_child; } diff --git a/drivers/pinctrl/devicetree.c b/drivers/pinctrl/devicetree.c index 3fb2387147189d5d286751fa4c8c6d5b8a602f9d..eac55fee5281c4e247ff5f975a3de1d29662c5cf 100644 --- a/drivers/pinctrl/devicetree.c +++ b/drivers/pinctrl/devicetree.c @@ -220,6 +220,8 @@ int pinctrl_dt_to_map(struct pinctrl *p, struct pinctrl_dev *pctldev) for (state = 0; ; state++) { /* Retrieve the pinctrl-* property */ propname = kasprintf(GFP_KERNEL, "pinctrl-%d", state); + if (!propname) + return -ENOMEM; prop = of_find_property(np, propname, &size); kfree(propname); if (!prop) { diff --git a/drivers/platform/chrome/chromeos_laptop.c b/drivers/platform/chrome/chromeos_laptop.c index 472a03daa8693bccdf404a92fddda488ae7c6213..109c191d35cfc76d5a67ff296d6cb3da81370a27 100644 --- a/drivers/platform/chrome/chromeos_laptop.c +++ b/drivers/platform/chrome/chromeos_laptop.c @@ -718,6 +718,7 @@ static int __init chromeos_laptop_prepare_i2c_peripherals(struct chromeos_laptop *cros_laptop, const struct chromeos_laptop *src) { + struct i2c_peripheral *i2c_peripherals; struct i2c_peripheral *i2c_dev; struct i2c_board_info *info; int i; @@ -726,17 +727,15 @@ chromeos_laptop_prepare_i2c_peripherals(struct chromeos_laptop *cros_laptop, if (!src->num_i2c_peripherals) return 0; - cros_laptop->i2c_peripherals = kmemdup(src->i2c_peripherals, - src->num_i2c_peripherals * - sizeof(*src->i2c_peripherals), - GFP_KERNEL); - if (!cros_laptop->i2c_peripherals) + i2c_peripherals = kmemdup(src->i2c_peripherals, + src->num_i2c_peripherals * + sizeof(*src->i2c_peripherals), + GFP_KERNEL); + if (!i2c_peripherals) return -ENOMEM; - cros_laptop->num_i2c_peripherals = src->num_i2c_peripherals; - - for (i = 0; i < cros_laptop->num_i2c_peripherals; i++) { - i2c_dev = &cros_laptop->i2c_peripherals[i]; + for (i = 0; i < src->num_i2c_peripherals; i++) { + i2c_dev = &i2c_peripherals[i]; info = &i2c_dev->board_info; error = chromeos_laptop_setup_irq(i2c_dev); @@ -754,16 +753,19 @@ chromeos_laptop_prepare_i2c_peripherals(struct chromeos_laptop *cros_laptop, } } + cros_laptop->i2c_peripherals = i2c_peripherals; + cros_laptop->num_i2c_peripherals = src->num_i2c_peripherals; + return 0; err_out: while (--i >= 0) { - i2c_dev = &cros_laptop->i2c_peripherals[i]; + i2c_dev = &i2c_peripherals[i]; info = &i2c_dev->board_info; if (info->properties) property_entries_free(info->properties); } - kfree(cros_laptop->i2c_peripherals); + kfree(i2c_peripherals); return error; } diff --git a/drivers/platform/chrome/cros_ec.c b/drivers/platform/chrome/cros_ec.c index c4de8c4db19307d16c0bb8060ee2c4d34e6d39b8..5a622666a07552714cebba5ce1e6879b8a066b98 100644 --- a/drivers/platform/chrome/cros_ec.c +++ b/drivers/platform/chrome/cros_ec.c @@ -332,10 +332,16 @@ EXPORT_SYMBOL(cros_ec_suspend); static void cros_ec_report_events_during_suspend(struct cros_ec_device *ec_dev) { + bool wake_event; + while (ec_dev->mkbp_event_supported && - cros_ec_get_next_event(ec_dev, NULL, NULL) > 0) + cros_ec_get_next_event(ec_dev, &wake_event, NULL) > 0) { blocking_notifier_call_chain(&ec_dev->event_notifier, 1, ec_dev); + + if (wake_event && device_may_wakeup(ec_dev->dev)) + pm_wakeup_event(ec_dev->dev, 0); + } } /** diff --git a/drivers/platform/chrome/cros_ec_chardev.c b/drivers/platform/chrome/cros_ec_chardev.c index fd33de546aee0bb5ccea837e6fa2214cffa90014..0de7c255254e0ba7f4e33c4da8a7b7573e815bb5 100644 --- a/drivers/platform/chrome/cros_ec_chardev.c +++ b/drivers/platform/chrome/cros_ec_chardev.c @@ -327,6 +327,9 @@ static long cros_ec_chardev_ioctl_readmem(struct cros_ec_dev *ec, if (copy_from_user(&s_mem, arg, sizeof(s_mem))) return -EFAULT; + if (s_mem.bytes > sizeof(s_mem.buffer)) + return -EINVAL; + num = ec_dev->cmd_readmem(ec_dev, s_mem.offset, s_mem.bytes, s_mem.buffer); if (num <= 0) diff --git a/drivers/platform/chrome/cros_ec_proto.c b/drivers/platform/chrome/cros_ec_proto.c index 3a2a78ff33304aef1026b7be7fbe9ffb02ddb712..8ffbf92ec1e07196171b5425fe7f200951005b75 100644 --- a/drivers/platform/chrome/cros_ec_proto.c +++ b/drivers/platform/chrome/cros_ec_proto.c @@ -748,6 +748,7 @@ int cros_ec_get_next_event(struct cros_ec_device *ec_dev, u8 event_type; u32 host_event; int ret; + u32 ver_mask; /* * Default value for wake_event. @@ -769,6 +770,37 @@ int cros_ec_get_next_event(struct cros_ec_device *ec_dev, return get_keyboard_state_event(ec_dev); ret = get_next_event(ec_dev); + /* + * -ENOPROTOOPT is returned when EC returns EC_RES_INVALID_VERSION. + * This can occur when EC based device (e.g. Fingerprint MCU) jumps to + * the RO image which doesn't support newer version of the command. In + * this case we will attempt to update maximum supported version of the + * EC_CMD_GET_NEXT_EVENT. + */ + if (ret == -ENOPROTOOPT) { + dev_dbg(ec_dev->dev, + "GET_NEXT_EVENT returned invalid version error.\n"); + ret = cros_ec_get_host_command_version_mask(ec_dev, + EC_CMD_GET_NEXT_EVENT, + &ver_mask); + if (ret < 0 || ver_mask == 0) + /* + * Do not change the MKBP supported version if we can't + * obtain supported version correctly. Please note that + * calling EC_CMD_GET_NEXT_EVENT returned + * EC_RES_INVALID_VERSION which means that the command + * is present. + */ + return -ENOPROTOOPT; + + ec_dev->mkbp_event_supported = fls(ver_mask); + dev_dbg(ec_dev->dev, "MKBP support version changed to %u\n", + ec_dev->mkbp_event_supported - 1); + + /* Try to get next event with new MKBP support version set. */ + ret = get_next_event(ec_dev); + } + if (ret <= 0) return ret; diff --git a/drivers/platform/x86/acer-wmi.c b/drivers/platform/x86/acer-wmi.c index 8e696262215fce110dc0a3ede77ad462da4a2b80..ebec49957ed09791f22ca489de779a9acb3c2b50 100644 --- a/drivers/platform/x86/acer-wmi.c +++ b/drivers/platform/x86/acer-wmi.c @@ -536,6 +536,15 @@ static const struct dmi_system_id acer_quirks[] __initconst = { }, .driver_data = (void *)ACER_CAP_KBD_DOCK, }, + { + .callback = set_force_caps, + .ident = "Acer Aspire Switch V 10 SW5-017", + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "SW5-017"), + }, + .driver_data = (void *)ACER_CAP_KBD_DOCK, + }, { .callback = set_force_caps, .ident = "Acer One 10 (S1003)", diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c index 39e1a6396e08dba658223550af35e3aae363a0e7..db369cf26111927db1008e81d023670d7f6ce12b 100644 --- a/drivers/platform/x86/asus-wmi.c +++ b/drivers/platform/x86/asus-wmi.c @@ -1212,6 +1212,8 @@ static void asus_wmi_set_xusb2pr(struct asus_wmi *asus) pci_write_config_dword(xhci_pdev, USB_INTEL_XUSB2PR, cpu_to_le32(ports_available)); + pci_dev_put(xhci_pdev); + pr_info("set USB_INTEL_XUSB2PR old: 0x%04x, new: 0x%04x\n", orig_ports_available, ports_available); } diff --git a/drivers/platform/x86/hp-wmi.c b/drivers/platform/x86/hp-wmi.c index 012639f6d3354cc504d31ed93f5d4d770241aca3..6642d09b17b55d1a43f4e07accd0aa7106785e0a 100644 --- a/drivers/platform/x86/hp-wmi.c +++ b/drivers/platform/x86/hp-wmi.c @@ -63,6 +63,7 @@ enum hp_wmi_event_ids { HPWMI_PEAKSHIFT_PERIOD = 0x0F, HPWMI_BATTERY_CHARGE_PERIOD = 0x10, HPWMI_SANITIZATION_MODE = 0x17, + HPWMI_SMART_EXPERIENCE_APP = 0x21, }; struct bios_args { @@ -632,6 +633,8 @@ static void hp_wmi_notify(u32 value, void *context) break; case HPWMI_SANITIZATION_MODE: break; + case HPWMI_SMART_EXPERIENCE_APP: + break; default: pr_info("Unknown event_id - %d - 0x%x\n", event_id, event_data); break; @@ -900,8 +903,16 @@ static int __init hp_wmi_bios_setup(struct platform_device *device) wwan_rfkill = NULL; rfkill2_count = 0; - if (hp_wmi_rfkill_setup(device)) - hp_wmi_rfkill2_setup(device); + /* + * In pre-2009 BIOS, command 1Bh return 0x4 to indicate that + * BIOS no longer controls the power for the wireless + * devices. All features supported by this command will no + * longer be supported. + */ + if (!hp_wmi_bios_2009_later()) { + if (hp_wmi_rfkill_setup(device)) + hp_wmi_rfkill2_setup(device); + } thermal_policy_setup(device); diff --git a/drivers/platform/x86/intel_pmc_core_pltdrv.c b/drivers/platform/x86/intel_pmc_core_pltdrv.c index 15ca8afdd973de2a2b0c7060e8b26b4beb2951bf..ddfba38c210444f70612cd707ec22db5931f9724 100644 --- a/drivers/platform/x86/intel_pmc_core_pltdrv.c +++ b/drivers/platform/x86/intel_pmc_core_pltdrv.c @@ -18,6 +18,8 @@ #include #include +#include + static void intel_pmc_core_release(struct device *dev) { kfree(dev); @@ -53,6 +55,13 @@ static int __init pmc_core_platform_init(void) if (acpi_dev_present("INT33A1", NULL, -1)) return -ENODEV; + /* + * Skip forcefully attaching the device for VMs. Make an exception for + * Xen dom0, which does have full hardware access. + */ + if (cpu_feature_enabled(X86_FEATURE_HYPERVISOR) && !xen_initial_domain()) + return -ENODEV; + if (!x86_match_cpu(intel_pmc_core_platform_ids)) return -ENODEV; diff --git a/drivers/platform/x86/msi-laptop.c b/drivers/platform/x86/msi-laptop.c index 24ffc8e2d2d1eb2d8bcad2bffb28569edf75a1a4..0e804b6c2d242af401753a5466f9d6aecd016c1c 100644 --- a/drivers/platform/x86/msi-laptop.c +++ b/drivers/platform/x86/msi-laptop.c @@ -596,11 +596,10 @@ static const struct dmi_system_id msi_dmi_table[] __initconst = { { .ident = "MSI S270", .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "MICRO-STAR INT'L CO.,LTD"), + DMI_MATCH(DMI_SYS_VENDOR, "MICRO-STAR INT"), DMI_MATCH(DMI_PRODUCT_NAME, "MS-1013"), DMI_MATCH(DMI_PRODUCT_VERSION, "0131"), - DMI_MATCH(DMI_CHASSIS_VENDOR, - "MICRO-STAR INT'L CO.,LTD") + DMI_MATCH(DMI_CHASSIS_VENDOR, "MICRO-STAR INT") }, .driver_data = &quirk_old_ec_model, .callback = dmi_check_cb @@ -633,8 +632,7 @@ static const struct dmi_system_id msi_dmi_table[] __initconst = { DMI_MATCH(DMI_SYS_VENDOR, "NOTEBOOK"), DMI_MATCH(DMI_PRODUCT_NAME, "SAM2000"), DMI_MATCH(DMI_PRODUCT_VERSION, "0131"), - DMI_MATCH(DMI_CHASSIS_VENDOR, - "MICRO-STAR INT'L CO.,LTD") + DMI_MATCH(DMI_CHASSIS_VENDOR, "MICRO-STAR INT") }, .driver_data = &quirk_old_ec_model, .callback = dmi_check_cb @@ -1048,8 +1046,7 @@ static int __init msi_init(void) return -EINVAL; /* Register backlight stuff */ - - if (quirks->old_ec_model || + if (quirks->old_ec_model && acpi_video_get_backlight_type() == acpi_backlight_vendor) { struct backlight_properties props; memset(&props, 0, sizeof(struct backlight_properties)); @@ -1117,6 +1114,8 @@ fail_create_attr: fail_create_group: if (quirks->load_scm_model) { i8042_remove_filter(msi_laptop_i8042_filter); + cancel_delayed_work_sync(&msi_touchpad_dwork); + input_unregister_device(msi_laptop_input_dev); cancel_delayed_work_sync(&msi_rfkill_dwork); cancel_work_sync(&msi_rfkill_work); rfkill_cleanup(); @@ -1137,6 +1136,7 @@ static void __exit msi_cleanup(void) { if (quirks->load_scm_model) { i8042_remove_filter(msi_laptop_i8042_filter); + cancel_delayed_work_sync(&msi_touchpad_dwork); input_unregister_device(msi_laptop_input_dev); cancel_delayed_work_sync(&msi_rfkill_dwork); cancel_work_sync(&msi_rfkill_work); diff --git a/drivers/platform/x86/touchscreen_dmi.c b/drivers/platform/x86/touchscreen_dmi.c index ab6a9369649dba450c19fd14324f45b68838b3b3..110ff1e6ef81f968325eeab0d2ccf2d661527c2c 100644 --- a/drivers/platform/x86/touchscreen_dmi.c +++ b/drivers/platform/x86/touchscreen_dmi.c @@ -756,6 +756,22 @@ static const struct ts_dmi_data predia_basic_data = { .properties = predia_basic_props, }; +static const struct property_entry rca_cambio_w101_v2_props[] = { + PROPERTY_ENTRY_U32("touchscreen-min-x", 4), + PROPERTY_ENTRY_U32("touchscreen-min-y", 20), + PROPERTY_ENTRY_U32("touchscreen-size-x", 1644), + PROPERTY_ENTRY_U32("touchscreen-size-y", 874), + PROPERTY_ENTRY_BOOL("touchscreen-swapped-x-y"), + PROPERTY_ENTRY_STRING("firmware-name", "gsl1680-rca-cambio-w101-v2.fw"), + PROPERTY_ENTRY_U32("silead,max-fingers", 10), + { } +}; + +static const struct ts_dmi_data rca_cambio_w101_v2_data = { + .acpi_name = "MSSL1680:00", + .properties = rca_cambio_w101_v2_props, +}; + static const struct property_entry rwc_nanote_p8_props[] = { PROPERTY_ENTRY_U32("touchscreen-min-y", 46), PROPERTY_ENTRY_U32("touchscreen-size-x", 1728), @@ -1341,6 +1357,15 @@ const struct dmi_system_id touchscreen_dmi_table[] = { DMI_EXACT_MATCH(DMI_BOARD_NAME, "0E57"), }, }, + { + /* RCA Cambio W101 v2 */ + /* https://github.com/onitake/gsl-firmware/discussions/193 */ + .driver_data = (void *)&rca_cambio_w101_v2_data, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "RCA"), + DMI_MATCH(DMI_PRODUCT_NAME, "W101SA23T1"), + }, + }, { /* RWC NANOTE P8 */ .driver_data = (void *)&rwc_nanote_p8_data, diff --git a/drivers/power/supply/adp5061.c b/drivers/power/supply/adp5061.c index 003557043ab3afa5a35ee4babf3f797476af2e6c..daee1161c3059cf2bfb9c30639d5b64dd119b09c 100644 --- a/drivers/power/supply/adp5061.c +++ b/drivers/power/supply/adp5061.c @@ -427,11 +427,11 @@ static int adp5061_get_chg_type(struct adp5061_state *st, if (ret < 0) return ret; - chg_type = adp5061_chg_type[ADP5061_CHG_STATUS_1_CHG_STATUS(status1)]; - if (chg_type > ADP5061_CHG_FAST_CV) + chg_type = ADP5061_CHG_STATUS_1_CHG_STATUS(status1); + if (chg_type >= ARRAY_SIZE(adp5061_chg_type)) val->intval = POWER_SUPPLY_STATUS_UNKNOWN; else - val->intval = chg_type; + val->intval = adp5061_chg_type[chg_type]; return ret; } diff --git a/drivers/powercap/intel_rapl_common.c b/drivers/powercap/intel_rapl_common.c index 70d6d52bc1e2175b38397f79ee3c58a552ab1b97..285420c1eb7c3ecfb88590896729e28bdb4a997b 100644 --- a/drivers/powercap/intel_rapl_common.c +++ b/drivers/powercap/intel_rapl_common.c @@ -938,6 +938,9 @@ static u64 rapl_compute_time_window_core(struct rapl_package *rp, u64 value, y = value & 0x1f; value = (1 << y) * (4 + f) * rp->time_unit / 4; } else { + if (value < rp->time_unit) + return 0; + do_div(value, rp->time_unit); y = ilog2(value); f = div64_u64(4 * (value - (1 << y)), 1 << y); @@ -979,7 +982,6 @@ static const struct rapl_defaults rapl_defaults_spr_server = { .check_unit = rapl_check_unit_core, .set_floor_freq = set_floor_freq_default, .compute_time_window = rapl_compute_time_window_core, - .dram_domain_energy_unit = 15300, .psys_domain_energy_unit = 1000000000, }; diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index 317d701487ecd5ef64125eb81fb84f67020813f8..eb083b26ab4f6a3942498eedc0bd2aa6bbc6c613 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -2544,7 +2544,7 @@ static int _regulator_do_enable(struct regulator_dev *rdev) * expired, return -ETIMEDOUT. */ if (rdev->desc->poll_enabled_time) { - unsigned int time_remaining = delay; + int time_remaining = delay; while (time_remaining > 0) { _regulator_enable_delay(rdev->desc->poll_enabled_time); @@ -4928,6 +4928,7 @@ static void regulator_dev_release(struct device *dev) { struct regulator_dev *rdev = dev_get_drvdata(dev); + debugfs_remove_recursive(rdev->debugfs); kfree(rdev->constraints); of_node_put(rdev->dev.of_node); kfree(rdev); @@ -5401,11 +5402,15 @@ wash: mutex_lock(®ulator_list_mutex); regulator_ena_gpio_free(rdev); mutex_unlock(®ulator_list_mutex); + put_device(&rdev->dev); + rdev = NULL; clean: if (dangling_of_gpiod) gpiod_put(config->ena_gpiod); + if (rdev && rdev->dev.of_node) + of_node_put(rdev->dev.of_node); + kfree(rdev); kfree(config); - put_device(&rdev->dev); rinse: if (dangling_cfg_gpiod) gpiod_put(cfg->ena_gpiod); @@ -5434,7 +5439,6 @@ void regulator_unregister(struct regulator_dev *rdev) mutex_lock(®ulator_list_mutex); - debugfs_remove_recursive(rdev->debugfs); WARN_ON(rdev->open_count); regulator_remove_coupling(rdev); unset_regulator_supplies(rdev); diff --git a/drivers/regulator/qcom_rpm-regulator.c b/drivers/regulator/qcom_rpm-regulator.c index 7f9d66ac37ff8a4bf5c6e57e9574aae5c17f8f84..3c41b71a1f5298004ea7bceeb82d99ed2310ed23 100644 --- a/drivers/regulator/qcom_rpm-regulator.c +++ b/drivers/regulator/qcom_rpm-regulator.c @@ -802,6 +802,12 @@ static const struct rpm_regulator_data rpm_pm8018_regulators[] = { }; static const struct rpm_regulator_data rpm_pm8058_regulators[] = { + { "s0", QCOM_RPM_PM8058_SMPS0, &pm8058_smps, "vdd_s0" }, + { "s1", QCOM_RPM_PM8058_SMPS1, &pm8058_smps, "vdd_s1" }, + { "s2", QCOM_RPM_PM8058_SMPS2, &pm8058_smps, "vdd_s2" }, + { "s3", QCOM_RPM_PM8058_SMPS3, &pm8058_smps, "vdd_s3" }, + { "s4", QCOM_RPM_PM8058_SMPS4, &pm8058_smps, "vdd_s4" }, + { "l0", QCOM_RPM_PM8058_LDO0, &pm8058_nldo, "vdd_l0_l1_lvs" }, { "l1", QCOM_RPM_PM8058_LDO1, &pm8058_nldo, "vdd_l0_l1_lvs" }, { "l2", QCOM_RPM_PM8058_LDO2, &pm8058_pldo, "vdd_l2_l11_l12" }, @@ -829,12 +835,6 @@ static const struct rpm_regulator_data rpm_pm8058_regulators[] = { { "l24", QCOM_RPM_PM8058_LDO24, &pm8058_nldo, "vdd_l23_l24_l25" }, { "l25", QCOM_RPM_PM8058_LDO25, &pm8058_nldo, "vdd_l23_l24_l25" }, - { "s0", QCOM_RPM_PM8058_SMPS0, &pm8058_smps, "vdd_s0" }, - { "s1", QCOM_RPM_PM8058_SMPS1, &pm8058_smps, "vdd_s1" }, - { "s2", QCOM_RPM_PM8058_SMPS2, &pm8058_smps, "vdd_s2" }, - { "s3", QCOM_RPM_PM8058_SMPS3, &pm8058_smps, "vdd_s3" }, - { "s4", QCOM_RPM_PM8058_SMPS4, &pm8058_smps, "vdd_s4" }, - { "lvs0", QCOM_RPM_PM8058_LVS0, &pm8058_switch, "vdd_l0_l1_lvs" }, { "lvs1", QCOM_RPM_PM8058_LVS1, &pm8058_switch, "vdd_l0_l1_lvs" }, @@ -843,6 +843,12 @@ static const struct rpm_regulator_data rpm_pm8058_regulators[] = { }; static const struct rpm_regulator_data rpm_pm8901_regulators[] = { + { "s0", QCOM_RPM_PM8901_SMPS0, &pm8901_ftsmps, "vdd_s0" }, + { "s1", QCOM_RPM_PM8901_SMPS1, &pm8901_ftsmps, "vdd_s1" }, + { "s2", QCOM_RPM_PM8901_SMPS2, &pm8901_ftsmps, "vdd_s2" }, + { "s3", QCOM_RPM_PM8901_SMPS3, &pm8901_ftsmps, "vdd_s3" }, + { "s4", QCOM_RPM_PM8901_SMPS4, &pm8901_ftsmps, "vdd_s4" }, + { "l0", QCOM_RPM_PM8901_LDO0, &pm8901_nldo, "vdd_l0" }, { "l1", QCOM_RPM_PM8901_LDO1, &pm8901_pldo, "vdd_l1" }, { "l2", QCOM_RPM_PM8901_LDO2, &pm8901_pldo, "vdd_l2" }, @@ -851,12 +857,6 @@ static const struct rpm_regulator_data rpm_pm8901_regulators[] = { { "l5", QCOM_RPM_PM8901_LDO5, &pm8901_pldo, "vdd_l5" }, { "l6", QCOM_RPM_PM8901_LDO6, &pm8901_pldo, "vdd_l6" }, - { "s0", QCOM_RPM_PM8901_SMPS0, &pm8901_ftsmps, "vdd_s0" }, - { "s1", QCOM_RPM_PM8901_SMPS1, &pm8901_ftsmps, "vdd_s1" }, - { "s2", QCOM_RPM_PM8901_SMPS2, &pm8901_ftsmps, "vdd_s2" }, - { "s3", QCOM_RPM_PM8901_SMPS3, &pm8901_ftsmps, "vdd_s3" }, - { "s4", QCOM_RPM_PM8901_SMPS4, &pm8901_ftsmps, "vdd_s4" }, - { "lvs0", QCOM_RPM_PM8901_LVS0, &pm8901_switch, "lvs0_in" }, { "lvs1", QCOM_RPM_PM8901_LVS1, &pm8901_switch, "lvs1_in" }, { "lvs2", QCOM_RPM_PM8901_LVS2, &pm8901_switch, "lvs2_in" }, diff --git a/drivers/regulator/twl6030-regulator.c b/drivers/regulator/twl6030-regulator.c index 430265c404d65846733898e2f118739ca46ecdb7..7c7e3648ea4bf90deaec5f74ebcec842d7024fe6 100644 --- a/drivers/regulator/twl6030-regulator.c +++ b/drivers/regulator/twl6030-regulator.c @@ -530,6 +530,7 @@ static const struct twlreg_info TWL6030_INFO_##label = { \ #define TWL6032_ADJUSTABLE_LDO(label, offset) \ static const struct twlreg_info TWL6032_INFO_##label = { \ .base = offset, \ + .features = TWL6032_SUBCLASS, \ .desc = { \ .name = #label, \ .id = TWL6032_REG_##label, \ @@ -562,6 +563,7 @@ static const struct twlreg_info TWLFIXED_INFO_##label = { \ #define TWL6032_ADJUSTABLE_SMPS(label, offset) \ static const struct twlreg_info TWLSMPS_INFO_##label = { \ .base = offset, \ + .features = TWL6032_SUBCLASS, \ .desc = { \ .name = #label, \ .id = TWL6032_REG_##label, \ diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c index 7749deb614d75007d2a41169a03bcb52b120236a..53d22975a32fdb62198b57350a1244308ccaa2c0 100644 --- a/drivers/s390/block/dasd_eckd.c +++ b/drivers/s390/block/dasd_eckd.c @@ -4627,7 +4627,6 @@ static struct dasd_ccw_req *dasd_eckd_build_cp_raw(struct dasd_device *startdev, struct dasd_device *basedev; struct req_iterator iter; struct dasd_ccw_req *cqr; - unsigned int first_offs; unsigned int trkcount; unsigned long *idaws; unsigned int size; @@ -4661,7 +4660,6 @@ static struct dasd_ccw_req *dasd_eckd_build_cp_raw(struct dasd_device *startdev, last_trk = (blk_rq_pos(req) + blk_rq_sectors(req) - 1) / DASD_RAW_SECTORS_PER_TRACK; trkcount = last_trk - first_trk + 1; - first_offs = 0; if (rq_data_dir(req) == READ) cmd = DASD_ECKD_CCW_READ_TRACK; @@ -4705,13 +4703,13 @@ static struct dasd_ccw_req *dasd_eckd_build_cp_raw(struct dasd_device *startdev, if (use_prefix) { prefix_LRE(ccw++, data, first_trk, last_trk, cmd, basedev, - startdev, 1, first_offs + 1, trkcount, 0, 0); + startdev, 1, 0, trkcount, 0, 0); } else { define_extent(ccw++, data, first_trk, last_trk, cmd, basedev, 0); ccw[-1].flags |= CCW_FLAG_CC; data += sizeof(struct DE_eckd_data); - locate_record_ext(ccw++, data, first_trk, first_offs + 1, + locate_record_ext(ccw++, data, first_trk, 0, trkcount, cmd, basedev, 0, 0); } diff --git a/drivers/s390/scsi/zfcp_fsf.c b/drivers/s390/scsi/zfcp_fsf.c index 8401c42db54191f5dd6157107a1462fa235f8b15..524947bf21b97b9ccbd2ff020066d80c7398984f 100644 --- a/drivers/s390/scsi/zfcp_fsf.c +++ b/drivers/s390/scsi/zfcp_fsf.c @@ -866,7 +866,7 @@ static int zfcp_fsf_req_send(struct zfcp_fsf_req *req) const bool is_srb = zfcp_fsf_req_is_status_read_buffer(req); struct zfcp_adapter *adapter = req->adapter; struct zfcp_qdio *qdio = adapter->qdio; - int req_id = req->req_id; + unsigned long req_id = req->req_id; zfcp_reqlist_add(adapter->req_list, req); diff --git a/drivers/scsi/3w-9xxx.c b/drivers/scsi/3w-9xxx.c index 3337b1e80412b045b3609eb794e6d22da784c271..f6f92033132a8e16915012b87beb07bd7dccbb2b 100644 --- a/drivers/scsi/3w-9xxx.c +++ b/drivers/scsi/3w-9xxx.c @@ -2014,7 +2014,7 @@ static int twa_probe(struct pci_dev *pdev, const struct pci_device_id *dev_id) retval = pci_enable_device(pdev); if (retval) { TW_PRINTK(host, TW_DRIVER, 0x34, "Failed to enable pci device"); - goto out_disable_device; + return -ENODEV; } pci_set_master(pdev); diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c index f6d6539c657f0455262ded5a636e3ae0ec750f89..b793e342ab7c6e3a900d2cce24f902f711435865 100644 --- a/drivers/scsi/ibmvscsi/ibmvfc.c +++ b/drivers/scsi/ibmvscsi/ibmvfc.c @@ -635,8 +635,13 @@ static void ibmvfc_init_host(struct ibmvfc_host *vhost) memset(vhost->async_crq.msgs, 0, PAGE_SIZE); vhost->async_crq.cur = 0; - list_for_each_entry(tgt, &vhost->targets, queue) - ibmvfc_del_tgt(tgt); + list_for_each_entry(tgt, &vhost->targets, queue) { + if (vhost->client_migrated) + tgt->need_login = 1; + else + ibmvfc_del_tgt(tgt); + } + scsi_block_requests(vhost->host); ibmvfc_set_host_action(vhost, IBMVFC_HOST_ACTION_INIT); vhost->job_step = ibmvfc_npiv_login; @@ -2822,9 +2827,12 @@ static void ibmvfc_handle_crq(struct ibmvfc_crq *crq, struct ibmvfc_host *vhost) /* We need to re-setup the interpartition connection */ dev_info(vhost->dev, "Partition migrated, Re-enabling adapter\n"); vhost->client_migrated = 1; + + scsi_block_requests(vhost->host); ibmvfc_purge_requests(vhost, DID_REQUEUE); - ibmvfc_link_down(vhost, IBMVFC_LINK_DOWN); + ibmvfc_set_host_state(vhost, IBMVFC_LINK_DOWN); ibmvfc_set_host_action(vhost, IBMVFC_HOST_ACTION_REENABLE); + wake_up(&vhost->work_wait_q); } else if (crq->format == IBMVFC_PARTNER_FAILED || crq->format == IBMVFC_PARTNER_DEREGISTER) { dev_err(vhost->dev, "Host partner adapter deregistered or failed (rc=%d)\n", crq->format); ibmvfc_purge_requests(vhost, DID_ERROR); diff --git a/drivers/scsi/iscsi_tcp.c b/drivers/scsi/iscsi_tcp.c index df47557a02a3c0c3a49305861588697fef28b3d0..6485c1aa9e7412c9a93a5e80dfeeaeb68fa86204 100644 --- a/drivers/scsi/iscsi_tcp.c +++ b/drivers/scsi/iscsi_tcp.c @@ -558,6 +558,8 @@ iscsi_sw_tcp_conn_create(struct iscsi_cls_session *cls_session, tcp_conn = conn->dd_data; tcp_sw_conn = tcp_conn->dd_data; + mutex_init(&tcp_sw_conn->sock_lock); + tfm = crypto_alloc_ahash("crc32c", 0, CRYPTO_ALG_ASYNC); if (IS_ERR(tfm)) goto free_conn; @@ -592,11 +594,15 @@ free_conn: static void iscsi_sw_tcp_release_conn(struct iscsi_conn *conn) { - struct iscsi_session *session = conn->session; struct iscsi_tcp_conn *tcp_conn = conn->dd_data; struct iscsi_sw_tcp_conn *tcp_sw_conn = tcp_conn->dd_data; struct socket *sock = tcp_sw_conn->sock; + /* + * The iscsi transport class will make sure we are not called in + * parallel with start, stop, bind and destroys. However, this can be + * called twice if userspace does a stop then a destroy. + */ if (!sock) return; @@ -604,9 +610,9 @@ static void iscsi_sw_tcp_release_conn(struct iscsi_conn *conn) iscsi_sw_tcp_conn_restore_callbacks(conn); sock_put(sock->sk); - spin_lock_bh(&session->frwd_lock); + mutex_lock(&tcp_sw_conn->sock_lock); tcp_sw_conn->sock = NULL; - spin_unlock_bh(&session->frwd_lock); + mutex_unlock(&tcp_sw_conn->sock_lock); sockfd_put(sock); } @@ -658,7 +664,6 @@ iscsi_sw_tcp_conn_bind(struct iscsi_cls_session *cls_session, struct iscsi_cls_conn *cls_conn, uint64_t transport_eph, int is_leading) { - struct iscsi_session *session = cls_session->dd_data; struct iscsi_conn *conn = cls_conn->dd_data; struct iscsi_tcp_conn *tcp_conn = conn->dd_data; struct iscsi_sw_tcp_conn *tcp_sw_conn = tcp_conn->dd_data; @@ -678,10 +683,10 @@ iscsi_sw_tcp_conn_bind(struct iscsi_cls_session *cls_session, if (err) goto free_socket; - spin_lock_bh(&session->frwd_lock); + mutex_lock(&tcp_sw_conn->sock_lock); /* bind iSCSI connection and socket */ tcp_sw_conn->sock = sock; - spin_unlock_bh(&session->frwd_lock); + mutex_unlock(&tcp_sw_conn->sock_lock); /* setup Socket parameters */ sk = sock->sk; @@ -717,8 +722,15 @@ static int iscsi_sw_tcp_conn_set_param(struct iscsi_cls_conn *cls_conn, break; case ISCSI_PARAM_DATADGST_EN: iscsi_set_param(cls_conn, param, buf, buflen); + + mutex_lock(&tcp_sw_conn->sock_lock); + if (!tcp_sw_conn->sock) { + mutex_unlock(&tcp_sw_conn->sock_lock); + return -ENOTCONN; + } tcp_sw_conn->sendpage = conn->datadgst_en ? sock_no_sendpage : tcp_sw_conn->sock->ops->sendpage; + mutex_unlock(&tcp_sw_conn->sock_lock); break; case ISCSI_PARAM_MAX_R2T: return iscsi_tcp_set_max_r2t(conn, buf); @@ -733,8 +745,8 @@ static int iscsi_sw_tcp_conn_get_param(struct iscsi_cls_conn *cls_conn, enum iscsi_param param, char *buf) { struct iscsi_conn *conn = cls_conn->dd_data; - struct iscsi_tcp_conn *tcp_conn = conn->dd_data; - struct iscsi_sw_tcp_conn *tcp_sw_conn = tcp_conn->dd_data; + struct iscsi_sw_tcp_conn *tcp_sw_conn; + struct iscsi_tcp_conn *tcp_conn; struct sockaddr_in6 addr; struct socket *sock; int rc; @@ -744,21 +756,36 @@ static int iscsi_sw_tcp_conn_get_param(struct iscsi_cls_conn *cls_conn, case ISCSI_PARAM_CONN_ADDRESS: case ISCSI_PARAM_LOCAL_PORT: spin_lock_bh(&conn->session->frwd_lock); - if (!tcp_sw_conn || !tcp_sw_conn->sock) { + if (!conn->session->leadconn) { spin_unlock_bh(&conn->session->frwd_lock); return -ENOTCONN; } - sock = tcp_sw_conn->sock; - sock_hold(sock->sk); + /* + * The conn has been setup and bound, so just grab a ref + * incase a destroy runs while we are in the net layer. + */ + iscsi_get_conn(conn->cls_conn); spin_unlock_bh(&conn->session->frwd_lock); + tcp_conn = conn->dd_data; + tcp_sw_conn = tcp_conn->dd_data; + + mutex_lock(&tcp_sw_conn->sock_lock); + sock = tcp_sw_conn->sock; + if (!sock) { + rc = -ENOTCONN; + goto sock_unlock; + } + if (param == ISCSI_PARAM_LOCAL_PORT) rc = kernel_getsockname(sock, (struct sockaddr *)&addr); else rc = kernel_getpeername(sock, (struct sockaddr *)&addr); - sock_put(sock->sk); +sock_unlock: + mutex_unlock(&tcp_sw_conn->sock_lock); + iscsi_put_conn(conn->cls_conn); if (rc < 0) return rc; @@ -796,17 +823,21 @@ static int iscsi_sw_tcp_host_get_param(struct Scsi_Host *shost, } tcp_conn = conn->dd_data; tcp_sw_conn = tcp_conn->dd_data; - sock = tcp_sw_conn->sock; - if (!sock) { - spin_unlock_bh(&session->frwd_lock); - return -ENOTCONN; - } - sock_hold(sock->sk); + /* + * The conn has been setup and bound, so just grab a ref + * incase a destroy runs while we are in the net layer. + */ + iscsi_get_conn(conn->cls_conn); spin_unlock_bh(&session->frwd_lock); - rc = kernel_getsockname(sock, - (struct sockaddr *)&addr); - sock_put(sock->sk); + mutex_lock(&tcp_sw_conn->sock_lock); + sock = tcp_sw_conn->sock; + if (!sock) + rc = -ENOTCONN; + else + rc = kernel_getsockname(sock, (struct sockaddr *)&addr); + mutex_unlock(&tcp_sw_conn->sock_lock); + iscsi_put_conn(conn->cls_conn); if (rc < 0) return rc; diff --git a/drivers/scsi/iscsi_tcp.h b/drivers/scsi/iscsi_tcp.h index 791453195099c0f67a4299d5e4ec0596e5df8a0a..1731956326e2bf9a8c80e8b31705f0f7d643744b 100644 --- a/drivers/scsi/iscsi_tcp.h +++ b/drivers/scsi/iscsi_tcp.h @@ -28,6 +28,8 @@ struct iscsi_sw_tcp_send { struct iscsi_sw_tcp_conn { struct socket *sock; + /* Taken when accessing the sock from the netlink/sysfs interface */ + struct mutex sock_lock; struct iscsi_sw_tcp_send out; /* old values for socket callbacks */ diff --git a/drivers/scsi/libsas/sas_expander.c b/drivers/scsi/libsas/sas_expander.c index 8d6bcc19359ffda33c6e4dcf181532553408ad2c..51485d0251f2d96a1f9ac1a64a70eec698e7c779 100644 --- a/drivers/scsi/libsas/sas_expander.c +++ b/drivers/scsi/libsas/sas_expander.c @@ -85,7 +85,7 @@ static int smp_execute_task_sg(struct domain_device *dev, res = i->dft->lldd_execute_task(task, GFP_KERNEL); if (res) { - del_timer(&task->slow_task->timer); + del_timer_sync(&task->slow_task->timer); pr_notice("executing SMP task failed:%d\n", res); break; } diff --git a/drivers/scsi/qedf/qedf_main.c b/drivers/scsi/qedf/qedf_main.c index de5b6453827c08e483b650d67720a62f4e00d27e..f48ef47546f4dffab91df5ad108e5a0e50a2d035 100644 --- a/drivers/scsi/qedf/qedf_main.c +++ b/drivers/scsi/qedf/qedf_main.c @@ -1917,6 +1917,27 @@ static int qedf_vport_create(struct fc_vport *vport, bool disabled) fc_vport_setlink(vn_port); } + /* Set symbolic node name */ + if (base_qedf->pdev->device == QL45xxx) + snprintf(fc_host_symbolic_name(vn_port->host), 256, + "Marvell FastLinQ 45xxx FCoE v%s", QEDF_VERSION); + + if (base_qedf->pdev->device == QL41xxx) + snprintf(fc_host_symbolic_name(vn_port->host), 256, + "Marvell FastLinQ 41xxx FCoE v%s", QEDF_VERSION); + + /* Set supported speed */ + fc_host_supported_speeds(vn_port->host) = n_port->link_supported_speeds; + + /* Set speed */ + vn_port->link_speed = n_port->link_speed; + + /* Set port type */ + fc_host_port_type(vn_port->host) = FC_PORTTYPE_NPIV; + + /* Set maxframe size */ + fc_host_maxframe_size(vn_port->host) = n_port->mfs; + QEDF_INFO(&(base_qedf->dbg_ctx), QEDF_LOG_NPIV, "vn_port=%p.\n", vn_port); diff --git a/drivers/scsi/qla2xxx/qla_attr.c b/drivers/scsi/qla2xxx/qla_attr.c index d0407f44de78da687d67b87922cf77eaab2070e3..61b9dc511d9049f8f4fe2f6e3dc1397b3db85eee 100644 --- a/drivers/scsi/qla2xxx/qla_attr.c +++ b/drivers/scsi/qla2xxx/qla_attr.c @@ -3262,11 +3262,34 @@ struct fc_function_template qla2xxx_transport_vport_functions = { .bsg_timeout = qla24xx_bsg_timeout, }; +static uint +qla2x00_get_host_supported_speeds(scsi_qla_host_t *vha, uint speeds) +{ + uint supported_speeds = FC_PORTSPEED_UNKNOWN; + + if (speeds & FDMI_PORT_SPEED_64GB) + supported_speeds |= FC_PORTSPEED_64GBIT; + if (speeds & FDMI_PORT_SPEED_32GB) + supported_speeds |= FC_PORTSPEED_32GBIT; + if (speeds & FDMI_PORT_SPEED_16GB) + supported_speeds |= FC_PORTSPEED_16GBIT; + if (speeds & FDMI_PORT_SPEED_8GB) + supported_speeds |= FC_PORTSPEED_8GBIT; + if (speeds & FDMI_PORT_SPEED_4GB) + supported_speeds |= FC_PORTSPEED_4GBIT; + if (speeds & FDMI_PORT_SPEED_2GB) + supported_speeds |= FC_PORTSPEED_2GBIT; + if (speeds & FDMI_PORT_SPEED_1GB) + supported_speeds |= FC_PORTSPEED_1GBIT; + + return supported_speeds; +} + void qla2x00_init_host_attr(scsi_qla_host_t *vha) { struct qla_hw_data *ha = vha->hw; - u32 speeds = FC_PORTSPEED_UNKNOWN; + u32 speeds = 0, fdmi_speed = 0; fc_host_dev_loss_tmo(vha->host) = ha->port_down_retry_count; fc_host_node_name(vha->host) = wwn_to_u64(vha->node_name); @@ -3276,7 +3299,8 @@ qla2x00_init_host_attr(scsi_qla_host_t *vha) fc_host_max_npiv_vports(vha->host) = ha->max_npiv_vports; fc_host_npiv_vports_inuse(vha->host) = ha->cur_vport_count; - speeds = qla25xx_fdmi_port_speed_capability(ha); + fdmi_speed = qla25xx_fdmi_port_speed_capability(ha); + speeds = qla2x00_get_host_supported_speeds(vha, fdmi_speed); fc_host_supported_speeds(vha->host) = speeds; } diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c index 5eb959b5f7010f6d6b977a5726f1a7be32a311c2..cc20621bb49da1f28c5b38b772f665d8494e0532 100644 --- a/drivers/scsi/scsi_debug.c +++ b/drivers/scsi/scsi_debug.c @@ -1878,6 +1878,13 @@ static int resp_readcap16(struct scsi_cmnd *scp, arr[14] |= 0x40; } + /* + * Since the scsi_debug READ CAPACITY implementation always reports the + * total disk capacity, set RC BASIS = 1 for host-managed ZBC devices. + */ + if (devip->zmodel == BLK_ZONED_HM) + arr[12] |= 1 << 4; + arr[15] = sdebug_lowest_aligned & 0xff; if (have_dif_prot) { @@ -7079,8 +7086,12 @@ static int sdebug_add_host_helper(int per_host_idx) dev_set_name(&sdbg_host->dev, "adapter%d", sdebug_num_hosts); error = device_register(&sdbg_host->dev); - if (error) + if (error) { + spin_lock(&sdebug_host_list_lock); + list_del(&sdbg_host->host_list); + spin_unlock(&sdebug_host_list_lock); goto clean; + } ++sdebug_num_hosts; return 0; diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c index 29db4db76b39370059013dce013e59a8588f33a7..dcddd054de26631b3a1d6f3f1951b66af3c041c6 100644 --- a/drivers/scsi/scsi_sysfs.c +++ b/drivers/scsi/scsi_sysfs.c @@ -815,6 +815,14 @@ store_state_field(struct device *dev, struct device_attribute *attr, } mutex_lock(&sdev->state_mutex); + switch (sdev->sdev_state) { + case SDEV_RUNNING: + case SDEV_OFFLINE: + break; + default: + mutex_unlock(&sdev->state_mutex); + return -EINVAL; + } if (sdev->sdev_state == SDEV_RUNNING && state == SDEV_RUNNING) { ret = 0; } else { diff --git a/drivers/scsi/scsi_transport_sas.c b/drivers/scsi/scsi_transport_sas.c index 4a96fb05731d2f26f1677c6d429fc4ee16990cb8..c6256fdc24b10c9af5bca05d132385c0cbe4499c 100644 --- a/drivers/scsi/scsi_transport_sas.c +++ b/drivers/scsi/scsi_transport_sas.c @@ -716,12 +716,17 @@ int sas_phy_add(struct sas_phy *phy) int error; error = device_add(&phy->dev); - if (!error) { - transport_add_device(&phy->dev); - transport_configure_device(&phy->dev); + if (error) + return error; + + error = transport_add_device(&phy->dev); + if (error) { + device_del(&phy->dev); + return error; } + transport_configure_device(&phy->dev); - return error; + return 0; } EXPORT_SYMBOL(sas_phy_add); diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index e7101d0473a56a3b81e59da3c8c4806809f538dd..8fff9ee080fbfa1e6250f8bc81f8383176ffae3b 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -1074,6 +1074,7 @@ static blk_status_t sd_setup_write_same_cmnd(struct scsi_cmnd *cmd) struct bio *bio = rq->bio; u64 lba = sectors_to_logical(sdp, blk_rq_pos(rq)); u32 nr_blocks = sectors_to_logical(sdp, blk_rq_sectors(rq)); + unsigned int nr_bytes = blk_rq_bytes(rq); blk_status_t ret; if (sdkp->device->no_write_same) @@ -1110,7 +1111,7 @@ static blk_status_t sd_setup_write_same_cmnd(struct scsi_cmnd *cmd) */ rq->__data_len = sdp->sector_size; ret = scsi_alloc_sgtables(cmd); - rq->__data_len = blk_rq_bytes(rq); + rq->__data_len = nr_bytes; return ret; } diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index 7ac1090d4379c099a4ec04b80a2b97eb255e6ce5..3fa8a0c94bdc13309129be399e8f75be7b6e8409 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -356,16 +356,21 @@ enum storvsc_request_type { }; /* - * SRB status codes and masks; a subset of the codes used here. + * SRB status codes and masks. In the 8-bit field, the two high order bits + * are flags, while the remaining 6 bits are an integer status code. The + * definitions here include only the subset of the integer status codes that + * are tested for in this driver. */ - #define SRB_STATUS_AUTOSENSE_VALID 0x80 #define SRB_STATUS_QUEUE_FROZEN 0x40 -#define SRB_STATUS_INVALID_LUN 0x20 -#define SRB_STATUS_SUCCESS 0x01 -#define SRB_STATUS_ABORTED 0x02 -#define SRB_STATUS_ERROR 0x04 -#define SRB_STATUS_DATA_OVERRUN 0x12 + +/* SRB status integer codes */ +#define SRB_STATUS_SUCCESS 0x01 +#define SRB_STATUS_ABORTED 0x02 +#define SRB_STATUS_ERROR 0x04 +#define SRB_STATUS_INVALID_REQUEST 0x06 +#define SRB_STATUS_DATA_OVERRUN 0x12 +#define SRB_STATUS_INVALID_LUN 0x20 #define SRB_STATUS(status) \ (status & ~(SRB_STATUS_AUTOSENSE_VALID | SRB_STATUS_QUEUE_FROZEN)) @@ -995,38 +1000,25 @@ static void storvsc_handle_error(struct vmscsi_request *vm_srb, void (*process_err_fn)(struct work_struct *work); struct hv_host_device *host_dev = shost_priv(host); - /* - * In some situations, Hyper-V sets multiple bits in the - * srb_status, such as ABORTED and ERROR. So process them - * individually, with the most specific bits first. - */ - - if (vm_srb->srb_status & SRB_STATUS_INVALID_LUN) { - set_host_byte(scmnd, DID_NO_CONNECT); - process_err_fn = storvsc_remove_lun; - goto do_work; - } + switch (SRB_STATUS(vm_srb->srb_status)) { + case SRB_STATUS_ERROR: + case SRB_STATUS_ABORTED: + case SRB_STATUS_INVALID_REQUEST: + if (vm_srb->srb_status & SRB_STATUS_AUTOSENSE_VALID) { + /* Check for capacity change */ + if ((asc == 0x2a) && (ascq == 0x9)) { + process_err_fn = storvsc_device_scan; + /* Retry the I/O that triggered this. */ + set_host_byte(scmnd, DID_REQUEUE); + goto do_work; + } - if (vm_srb->srb_status & SRB_STATUS_ABORTED) { - if (vm_srb->srb_status & SRB_STATUS_AUTOSENSE_VALID && - /* Capacity data has changed */ - (asc == 0x2a) && (ascq == 0x9)) { - process_err_fn = storvsc_device_scan; /* - * Retry the I/O that triggered this. + * Otherwise, let upper layer deal with the + * error when sense message is present */ - set_host_byte(scmnd, DID_REQUEUE); - goto do_work; - } - } - - if (vm_srb->srb_status & SRB_STATUS_ERROR) { - /* - * Let upper layer deal with error when - * sense message is present. - */ - if (vm_srb->srb_status & SRB_STATUS_AUTOSENSE_VALID) return; + } /* * If there is an error; offline the device since all @@ -1049,6 +1041,13 @@ static void storvsc_handle_error(struct vmscsi_request *vm_srb, default: set_host_byte(scmnd, DID_ERROR); } + return; + + case SRB_STATUS_INVALID_LUN: + set_host_byte(scmnd, DID_NO_CONNECT); + process_err_fn = storvsc_remove_lun; + goto do_work; + } return; diff --git a/drivers/siox/siox-core.c b/drivers/siox/siox-core.c index f8c08fb9891d7495fbfcf9705413727d554c3733..e0ffef6e93865665edccaf292ebe798879a6dd3e 100644 --- a/drivers/siox/siox-core.c +++ b/drivers/siox/siox-core.c @@ -835,6 +835,8 @@ static struct siox_device *siox_device_add(struct siox_master *smaster, err_device_register: /* don't care to make the buffer smaller again */ + put_device(&sdevice->dev); + sdevice = NULL; err_buf_alloc: siox_master_unlock(smaster); diff --git a/drivers/slimbus/stream.c b/drivers/slimbus/stream.c index 75f87b3d8b9538a2f5293deb4270aae350d04721..73a2aa362957206c29d0c2afa50fe71275ebca61 100644 --- a/drivers/slimbus/stream.c +++ b/drivers/slimbus/stream.c @@ -67,10 +67,10 @@ static const int slim_presence_rate_table[] = { 384000, 768000, 0, /* Reserved */ - 110250, - 220500, - 441000, - 882000, + 11025, + 22050, + 44100, + 88200, 176400, 352800, 705600, diff --git a/drivers/soc/qcom/smem_state.c b/drivers/soc/qcom/smem_state.c index d2b558438deb7dc062f82a3e48de046832cd7b55..41e929407196011d2a2ea4c9d890b61285c7ad94 100644 --- a/drivers/soc/qcom/smem_state.c +++ b/drivers/soc/qcom/smem_state.c @@ -136,6 +136,7 @@ static void qcom_smem_state_release(struct kref *ref) struct qcom_smem_state *state = container_of(ref, struct qcom_smem_state, refcount); list_del(&state->list); + of_node_put(state->of_node); kfree(state); } @@ -169,7 +170,7 @@ struct qcom_smem_state *qcom_smem_state_register(struct device_node *of_node, kref_init(&state->refcount); - state->of_node = of_node; + state->of_node = of_node_get(of_node); state->ops = *ops; state->priv = priv; diff --git a/drivers/soc/qcom/smsm.c b/drivers/soc/qcom/smsm.c index 6564f15c531900359dfc05ed242d1ce0b97b67b0..acba67dfbc8597d50780954f9addf217108ebe21 100644 --- a/drivers/soc/qcom/smsm.c +++ b/drivers/soc/qcom/smsm.c @@ -511,7 +511,7 @@ static int qcom_smsm_probe(struct platform_device *pdev) for (id = 0; id < smsm->num_hosts; id++) { ret = smsm_parse_ipc(smsm, id); if (ret < 0) - return ret; + goto out_put; } /* Acquire the main SMSM state vector */ @@ -519,13 +519,14 @@ static int qcom_smsm_probe(struct platform_device *pdev) smsm->num_entries * sizeof(u32)); if (ret < 0 && ret != -EEXIST) { dev_err(&pdev->dev, "unable to allocate shared state entry\n"); - return ret; + goto out_put; } states = qcom_smem_get(QCOM_SMEM_HOST_ANY, SMEM_SMSM_SHARED_STATE, NULL); if (IS_ERR(states)) { dev_err(&pdev->dev, "Unable to acquire shared state entry\n"); - return PTR_ERR(states); + ret = PTR_ERR(states); + goto out_put; } /* Acquire the list of interrupt mask vectors */ @@ -533,13 +534,14 @@ static int qcom_smsm_probe(struct platform_device *pdev) ret = qcom_smem_alloc(QCOM_SMEM_HOST_ANY, SMEM_SMSM_CPU_INTR_MASK, size); if (ret < 0 && ret != -EEXIST) { dev_err(&pdev->dev, "unable to allocate smsm interrupt mask\n"); - return ret; + goto out_put; } intr_mask = qcom_smem_get(QCOM_SMEM_HOST_ANY, SMEM_SMSM_CPU_INTR_MASK, NULL); if (IS_ERR(intr_mask)) { dev_err(&pdev->dev, "unable to acquire shared memory interrupt mask\n"); - return PTR_ERR(intr_mask); + ret = PTR_ERR(intr_mask); + goto out_put; } /* Setup the reference to the local state bits */ @@ -550,7 +552,8 @@ static int qcom_smsm_probe(struct platform_device *pdev) smsm->state = qcom_smem_state_register(local_node, &smsm_state_ops, smsm); if (IS_ERR(smsm->state)) { dev_err(smsm->dev, "failed to register qcom_smem_state\n"); - return PTR_ERR(smsm->state); + ret = PTR_ERR(smsm->state); + goto out_put; } /* Register handlers for remote processor entries of interest. */ @@ -580,16 +583,19 @@ static int qcom_smsm_probe(struct platform_device *pdev) } platform_set_drvdata(pdev, smsm); + of_node_put(local_node); return 0; unwind_interfaces: + of_node_put(node); for (id = 0; id < smsm->num_entries; id++) if (smsm->entries[id].domain) irq_domain_remove(smsm->entries[id].domain); qcom_smem_state_unregister(smsm->state); - +out_put: + of_node_put(local_node); return ret; } diff --git a/drivers/soc/tegra/Kconfig b/drivers/soc/tegra/Kconfig index 976dee0364700e9f13dec6b52d7d620631a44724..676807c5a215425f9aa1d17d6929c8855759af99 100644 --- a/drivers/soc/tegra/Kconfig +++ b/drivers/soc/tegra/Kconfig @@ -136,7 +136,6 @@ config SOC_TEGRA_FUSE def_bool y depends on ARCH_TEGRA select SOC_BUS - select TEGRA20_APB_DMA if ARCH_TEGRA_2x_SOC config SOC_TEGRA_FLOWCTRL bool diff --git a/drivers/soundwire/cadence_master.c b/drivers/soundwire/cadence_master.c index c6d421a4b91b665c8c366fbc2f8a51a3c6eb3b5d..a3247692ddc077508f8547a1c3c1584dea045ebd 100644 --- a/drivers/soundwire/cadence_master.c +++ b/drivers/soundwire/cadence_master.c @@ -501,9 +501,12 @@ cdns_fill_msg_resp(struct sdw_cdns *cdns, return SDW_CMD_IGNORED; } - /* fill response */ - for (i = 0; i < count; i++) - msg->buf[i + offset] = FIELD_GET(CDNS_MCP_RESP_RDATA, cdns->response_buf[i]); + if (msg->flags == SDW_MSG_FLAG_READ) { + /* fill response */ + for (i = 0; i < count; i++) + msg->buf[i + offset] = FIELD_GET(CDNS_MCP_RESP_RDATA, + cdns->response_buf[i]); + } return SDW_CMD_OK; } diff --git a/drivers/soundwire/intel.c b/drivers/soundwire/intel.c index 824d9f900aca74e41e4b62a04420e7a0c8c951ec..942d2fe132181fbdc8b3347eeb31de07246c6b81 100644 --- a/drivers/soundwire/intel.c +++ b/drivers/soundwire/intel.c @@ -1470,7 +1470,6 @@ int intel_master_startup(struct platform_device *pdev) ret = intel_register_dai(sdw); if (ret) { dev_err(dev, "DAI registration failed: %d\n", ret); - snd_soc_unregister_component(dev); goto err_interrupt; } diff --git a/drivers/spi/spi-dw-bt1.c b/drivers/spi/spi-dw-bt1.c index bc9d5eab3c589ccb723b730c189d412720cd8b37..8f6a1af1445621f5a99477eb73dbe32f1579b793 100644 --- a/drivers/spi/spi-dw-bt1.c +++ b/drivers/spi/spi-dw-bt1.c @@ -293,8 +293,10 @@ static int dw_spi_bt1_probe(struct platform_device *pdev) pm_runtime_enable(&pdev->dev); ret = dw_spi_add_host(&pdev->dev, dws); - if (ret) + if (ret) { + pm_runtime_disable(&pdev->dev); goto err_disable_clk; + } platform_set_drvdata(pdev, dwsbt1); diff --git a/drivers/spi/spi-dw-dma.c b/drivers/spi/spi-dw-dma.c index a09831c62192a0cebc9cf0327af02e8a2b041d4a..32ac8f9068e874b84ab06e0b55733e7548990b46 100644 --- a/drivers/spi/spi-dw-dma.c +++ b/drivers/spi/spi-dw-dma.c @@ -127,12 +127,15 @@ static int dw_spi_dma_init_mfld(struct device *dev, struct dw_spi *dws) dw_spi_dma_sg_burst_init(dws); + pci_dev_put(dma_dev); + return 0; free_rxchan: dma_release_channel(dws->rxchan); dws->rxchan = NULL; err_exit: + pci_dev_put(dma_dev); return -EBUSY; } diff --git a/drivers/spi/spi-meson-spicc.c b/drivers/spi/spi-meson-spicc.c index e4cb52e1fe2619d7699413d05d5dacc1cbf32a0e..6974a1c947aad6488708dfe02330d12ed0c34b40 100644 --- a/drivers/spi/spi-meson-spicc.c +++ b/drivers/spi/spi-meson-spicc.c @@ -537,7 +537,7 @@ static unsigned long meson_spicc_pow2_recalc_rate(struct clk_hw *hw, struct clk_divider *divider = to_clk_divider(hw); struct meson_spicc_device *spicc = pow2_clk_to_spicc(divider); - if (!spicc->master->cur_msg || !spicc->master->busy) + if (!spicc->master->cur_msg) return 0; return clk_divider_ops.recalc_rate(hw, parent_rate); @@ -549,7 +549,7 @@ static int meson_spicc_pow2_determine_rate(struct clk_hw *hw, struct clk_divider *divider = to_clk_divider(hw); struct meson_spicc_device *spicc = pow2_clk_to_spicc(divider); - if (!spicc->master->cur_msg || !spicc->master->busy) + if (!spicc->master->cur_msg) return -EINVAL; return clk_divider_ops.determine_rate(hw, req); @@ -561,7 +561,7 @@ static int meson_spicc_pow2_set_rate(struct clk_hw *hw, unsigned long rate, struct clk_divider *divider = to_clk_divider(hw); struct meson_spicc_device *spicc = pow2_clk_to_spicc(divider); - if (!spicc->master->cur_msg || !spicc->master->busy) + if (!spicc->master->cur_msg) return -EINVAL; return clk_divider_ops.set_rate(hw, rate, parent_rate); diff --git a/drivers/spi/spi-mt7621.c b/drivers/spi/spi-mt7621.c index b4b9b7309b5e949faf09aa129368a4c03da7aac2..351b0ef52bbc8d72cbaecce743d0ab3a2ff82f4a 100644 --- a/drivers/spi/spi-mt7621.c +++ b/drivers/spi/spi-mt7621.c @@ -340,11 +340,9 @@ static int mt7621_spi_probe(struct platform_device *pdev) return PTR_ERR(base); clk = devm_clk_get(&pdev->dev, NULL); - if (IS_ERR(clk)) { - dev_err(&pdev->dev, "unable to get SYS clock, err=%d\n", - status); - return PTR_ERR(clk); - } + if (IS_ERR(clk)) + return dev_err_probe(&pdev->dev, PTR_ERR(clk), + "unable to get SYS clock\n"); status = clk_prepare_enable(clk); if (status) diff --git a/drivers/spi/spi-omap-100k.c b/drivers/spi/spi-omap-100k.c index 0d0cd061d3563f5aed7c8ab1d3837a650b3c9e88..7c992d1f4abd9b368b9efa21a35edd957bc1094a 100644 --- a/drivers/spi/spi-omap-100k.c +++ b/drivers/spi/spi-omap-100k.c @@ -414,6 +414,7 @@ static int omap1_spi100k_probe(struct platform_device *pdev) return status; err_fck: + pm_runtime_disable(&pdev->dev); clk_disable_unprepare(spi100k->fck); err_ick: clk_disable_unprepare(spi100k->ick); diff --git a/drivers/spi/spi-qup.c b/drivers/spi/spi-qup.c index d39dec6d1c91e8e68fc46e48c464ad8a0ac1edc6..f3877eeb3da65427c36e0538e0ae8559a56ef3ef 100644 --- a/drivers/spi/spi-qup.c +++ b/drivers/spi/spi-qup.c @@ -1199,8 +1199,10 @@ static int spi_qup_pm_resume_runtime(struct device *device) return ret; ret = clk_prepare_enable(controller->cclk); - if (ret) + if (ret) { + clk_disable_unprepare(controller->iclk); return ret; + } /* Disable clocks auto gaiting */ config = readl_relaxed(controller->base + QUP_CONFIG); @@ -1246,14 +1248,25 @@ static int spi_qup_resume(struct device *device) return ret; ret = clk_prepare_enable(controller->cclk); - if (ret) + if (ret) { + clk_disable_unprepare(controller->iclk); return ret; + } ret = spi_qup_set_state(controller, QUP_STATE_RESET); if (ret) - return ret; + goto disable_clk; - return spi_master_resume(master); + ret = spi_master_resume(master); + if (ret) + goto disable_clk; + + return 0; + +disable_clk: + clk_disable_unprepare(controller->cclk); + clk_disable_unprepare(controller->iclk); + return ret; } #endif /* CONFIG_PM_SLEEP */ diff --git a/drivers/spi/spi-s3c64xx.c b/drivers/spi/spi-s3c64xx.c index dfa7c91e13aa5849e9ff3b965a056e9e61241f6e..d435df1b715bba364e951de69f42d08359898c4c 100644 --- a/drivers/spi/spi-s3c64xx.c +++ b/drivers/spi/spi-s3c64xx.c @@ -84,6 +84,7 @@ #define S3C64XX_SPI_ST_TX_FIFORDY (1<<0) #define S3C64XX_SPI_PACKET_CNT_EN (1<<16) +#define S3C64XX_SPI_PACKET_CNT_MASK GENMASK(15, 0) #define S3C64XX_SPI_PND_TX_UNDERRUN_CLR (1<<4) #define S3C64XX_SPI_PND_TX_OVERRUN_CLR (1<<3) @@ -660,6 +661,13 @@ static int s3c64xx_spi_prepare_message(struct spi_master *master, return 0; } +static size_t s3c64xx_spi_max_transfer_size(struct spi_device *spi) +{ + struct spi_controller *ctlr = spi->controller; + + return ctlr->can_dma ? S3C64XX_SPI_PACKET_CNT_MASK : SIZE_MAX; +} + static int s3c64xx_spi_transfer_one(struct spi_master *master, struct spi_device *spi, struct spi_transfer *xfer) @@ -1135,6 +1143,7 @@ static int s3c64xx_spi_probe(struct platform_device *pdev) master->prepare_transfer_hardware = s3c64xx_spi_prepare_transfer; master->prepare_message = s3c64xx_spi_prepare_message; master->transfer_one = s3c64xx_spi_transfer_one; + master->max_transfer_size = s3c64xx_spi_max_transfer_size; master->num_chipselect = sci->num_cs; master->dma_alignment = 8; master->bits_per_word_mask = SPI_BPW_MASK(32) | SPI_BPW_MASK(16) | diff --git a/drivers/spi/spi-stm32.c b/drivers/spi/spi-stm32.c index a6dfc8fef20cd09303d4d8fc951146243eae1dfa..9ec37cf10c010ed0fbf253e98fc0b818c84126fe 100644 --- a/drivers/spi/spi-stm32.c +++ b/drivers/spi/spi-stm32.c @@ -443,7 +443,7 @@ static int stm32_spi_prepare_mbr(struct stm32_spi *spi, u32 speed_hz, u32 div, mbrdiv; /* Ensure spi->clk_rate is even */ - div = DIV_ROUND_UP(spi->clk_rate & ~0x1, speed_hz); + div = DIV_ROUND_CLOSEST(spi->clk_rate & ~0x1, speed_hz); /* * SPI framework set xfer->speed_hz to master->max_speed_hz if @@ -941,6 +941,7 @@ static irqreturn_t stm32h7_spi_irq_thread(int irq, void *dev_id) static DEFINE_RATELIMIT_STATE(rs, DEFAULT_RATELIMIT_INTERVAL * 10, 1); + ratelimit_set_flags(&rs, RATELIMIT_MSG_ON_RELEASE); if (__ratelimit(&rs)) dev_dbg_ratelimited(spi->dev, "Communication suspended\n"); if (!spi->cur_usedma && (spi->rx_buf && (spi->rx_len > 0))) diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index 2ff27f33210451dbb63ad52a49ce98e554f85f47..b1a638d91b2b5b59e31975c976b1172741fecfbf 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -946,6 +946,8 @@ void spi_unmap_buf(struct spi_controller *ctlr, struct device *dev, if (sgt->orig_nents) { dma_unmap_sg(dev, sgt->sgl, sgt->orig_nents, dir); sg_free_table(sgt); + sgt->orig_nents = 0; + sgt->nents = 0; } } diff --git a/drivers/spmi/spmi-pmic-arb.c b/drivers/spmi/spmi-pmic-arb.c index bbbd311eda030577775f6eca33964801a2534989..e6de2aeece8d3883949749110f285b7a0a941ec5 100644 --- a/drivers/spmi/spmi-pmic-arb.c +++ b/drivers/spmi/spmi-pmic-arb.c @@ -887,7 +887,8 @@ static int pmic_arb_read_apid_map_v5(struct spmi_pmic_arb *pmic_arb) * version 5, there is more than one APID mapped to each PPID. * The owner field for each of these mappings specifies the EE which is * allowed to write to the APID. The owner of the last (highest) APID - * for a given PPID will receive interrupts from the PPID. + * which has the IRQ owner bit set for a given PPID will receive + * interrupts from the PPID. */ for (i = 0; ; i++, apidd++) { offset = pmic_arb->ver_ops->apid_map_offset(i); @@ -910,16 +911,16 @@ static int pmic_arb_read_apid_map_v5(struct spmi_pmic_arb *pmic_arb) apid = pmic_arb->ppid_to_apid[ppid] & ~PMIC_ARB_APID_VALID; prev_apidd = &pmic_arb->apid_data[apid]; - if (valid && is_irq_ee && - prev_apidd->write_ee == pmic_arb->ee) { + if (!valid || apidd->write_ee == pmic_arb->ee) { + /* First PPID mapping or one for this EE */ + pmic_arb->ppid_to_apid[ppid] = i | PMIC_ARB_APID_VALID; + } else if (valid && is_irq_ee && + prev_apidd->write_ee == pmic_arb->ee) { /* * Duplicate PPID mapping after the one for this EE; * override the irq owner */ prev_apidd->irq_ee = apidd->irq_ee; - } else if (!valid || is_irq_ee) { - /* First PPID mapping or duplicate for another EE */ - pmic_arb->ppid_to_apid[ppid] = i | PMIC_ARB_APID_VALID; } apidd->ppid = ppid; diff --git a/drivers/staging/greybus/audio_helper.c b/drivers/staging/greybus/audio_helper.c index a9576f92efaa46150ac18b8b64ddbef172be7efa..08443f4aa045d2c4d0eadd56dda3ff058bad742c 100644 --- a/drivers/staging/greybus/audio_helper.c +++ b/drivers/staging/greybus/audio_helper.c @@ -3,7 +3,6 @@ * Greybus Audio Sound SoC helper APIs */ -#include #include #include #include @@ -116,10 +115,6 @@ int gbaudio_dapm_free_controls(struct snd_soc_dapm_context *dapm, { int i; struct snd_soc_dapm_widget *w, *next_w; -#ifdef CONFIG_DEBUG_FS - struct dentry *parent = dapm->debugfs_dapm; - struct dentry *debugfs_w = NULL; -#endif mutex_lock(&dapm->card->dapm_mutex); for (i = 0; i < num; i++) { @@ -139,12 +134,6 @@ int gbaudio_dapm_free_controls(struct snd_soc_dapm_context *dapm, continue; } widget++; -#ifdef CONFIG_DEBUG_FS - if (!parent) - debugfs_w = debugfs_lookup(w->name, parent); - debugfs_remove(debugfs_w); - debugfs_w = NULL; -#endif gbaudio_dapm_free_widget(w); } mutex_unlock(&dapm->card->dapm_mutex); diff --git a/drivers/staging/media/meson/vdec/vdec.c b/drivers/staging/media/meson/vdec/vdec.c index 5ccb3846c8797deb518e70e1b49c2fd18a906017..7a818ca15b37d8fd5b0e77d0d17016463d69c056 100644 --- a/drivers/staging/media/meson/vdec/vdec.c +++ b/drivers/staging/media/meson/vdec/vdec.c @@ -1109,6 +1109,7 @@ static int vdec_probe(struct platform_device *pdev) err_vdev_release: video_device_release(vdev); + v4l2_device_unregister(&core->v4l2_dev); return ret; } @@ -1117,6 +1118,7 @@ static int vdec_remove(struct platform_device *pdev) struct amvdec_core *core = platform_get_drvdata(pdev); video_unregister_device(core->vdev_dec); + v4l2_device_unregister(&core->v4l2_dev); return 0; } diff --git a/drivers/staging/media/meson/vdec/vdec_hevc.c b/drivers/staging/media/meson/vdec/vdec_hevc.c index 9530e580e57a20e25bfc043cba4abc5c79907a43..afced435c9070240885970a82c40280b4c6fc6f5 100644 --- a/drivers/staging/media/meson/vdec/vdec_hevc.c +++ b/drivers/staging/media/meson/vdec/vdec_hevc.c @@ -167,8 +167,12 @@ static int vdec_hevc_start(struct amvdec_session *sess) clk_set_rate(core->vdec_hevc_clk, 666666666); ret = clk_prepare_enable(core->vdec_hevc_clk); - if (ret) + if (ret) { + if (core->platform->revision == VDEC_REVISION_G12A || + core->platform->revision == VDEC_REVISION_SM1) + clk_disable_unprepare(core->vdec_hevcf_clk); return ret; + } if (core->platform->revision == VDEC_REVISION_SM1) regmap_update_bits(core->regmap_ao, AO_RTI_GEN_PWR_SLEEP0, diff --git a/drivers/staging/media/rkisp1/rkisp1-capture.c b/drivers/staging/media/rkisp1/rkisp1-capture.c index 0c934ca5adaa3546f767eec768b270151bb7d098..8936f5a81680c89e445b560eb7f0a03708d0bc3b 100644 --- a/drivers/staging/media/rkisp1/rkisp1-capture.c +++ b/drivers/staging/media/rkisp1/rkisp1-capture.c @@ -1258,11 +1258,12 @@ static int rkisp1_capture_link_validate(struct media_link *link) struct rkisp1_capture *cap = video_get_drvdata(vdev); const struct rkisp1_capture_fmt_cfg *fmt = rkisp1_find_fmt_cfg(cap, cap->pix.fmt.pixelformat); - struct v4l2_subdev_format sd_fmt; + struct v4l2_subdev_format sd_fmt = { + .which = V4L2_SUBDEV_FORMAT_ACTIVE, + .pad = link->source->index, + }; int ret; - sd_fmt.which = V4L2_SUBDEV_FORMAT_ACTIVE; - sd_fmt.pad = link->source->index; ret = v4l2_subdev_call(sd, pad, get_fmt, NULL, &sd_fmt); if (ret) return ret; diff --git a/drivers/staging/media/rkisp1/rkisp1-resizer.c b/drivers/staging/media/rkisp1/rkisp1-resizer.c index 4dcc342ac2b27daf0b614ea14a7bc1559c8f19c3..76f17dd7670f70f5b9d9b078607170a13702f43a 100644 --- a/drivers/staging/media/rkisp1/rkisp1-resizer.c +++ b/drivers/staging/media/rkisp1/rkisp1-resizer.c @@ -500,6 +500,10 @@ static int rkisp1_rsz_init_config(struct v4l2_subdev *sd, sink_fmt->height = RKISP1_DEFAULT_HEIGHT; sink_fmt->field = V4L2_FIELD_NONE; sink_fmt->code = RKISP1_DEF_FMT; + sink_fmt->colorspace = V4L2_COLORSPACE_SRGB; + sink_fmt->xfer_func = V4L2_XFER_FUNC_SRGB; + sink_fmt->ycbcr_enc = V4L2_YCBCR_ENC_601; + sink_fmt->quantization = V4L2_QUANTIZATION_LIM_RANGE; sink_crop = v4l2_subdev_get_try_crop(sd, cfg, RKISP1_RSZ_PAD_SINK); sink_crop->width = RKISP1_DEFAULT_WIDTH; diff --git a/drivers/staging/media/sunxi/cedrus/cedrus.c b/drivers/staging/media/sunxi/cedrus/cedrus.c index 1dd833757c4eeb19b426f9772b3d2a1129f3a9fb..28de90edf4cc5962a88f845c361a1d6e8a5b788a 100644 --- a/drivers/staging/media/sunxi/cedrus/cedrus.c +++ b/drivers/staging/media/sunxi/cedrus/cedrus.c @@ -399,6 +399,8 @@ static int cedrus_probe(struct platform_device *pdev) if (!dev) return -ENOMEM; + platform_set_drvdata(pdev, dev); + dev->vfd = cedrus_video_device; dev->dev = &pdev->dev; dev->pdev = pdev; @@ -469,8 +471,6 @@ static int cedrus_probe(struct platform_device *pdev) goto err_m2m_mc; } - platform_set_drvdata(pdev, dev); - return 0; err_m2m_mc: diff --git a/drivers/staging/rtl8723bs/core/rtw_cmd.c b/drivers/staging/rtl8723bs/core/rtw_cmd.c index 2abe205e3453568efff10e59465f4894e15e2149..cee05385f872798fb4ca6fe4d58c6d1899ff356b 100644 --- a/drivers/staging/rtl8723bs/core/rtw_cmd.c +++ b/drivers/staging/rtl8723bs/core/rtw_cmd.c @@ -165,8 +165,6 @@ No irqsave is necessary. int rtw_init_cmd_priv(struct cmd_priv *pcmdpriv) { - int res = 0; - init_completion(&pcmdpriv->cmd_queue_comp); init_completion(&pcmdpriv->terminate_cmdthread_comp); @@ -178,18 +176,16 @@ int rtw_init_cmd_priv(struct cmd_priv *pcmdpriv) pcmdpriv->cmd_allocated_buf = rtw_zmalloc(MAX_CMDSZ + CMDBUFF_ALIGN_SZ); - if (!pcmdpriv->cmd_allocated_buf) { - res = -ENOMEM; - goto exit; - } + if (!pcmdpriv->cmd_allocated_buf) + return -ENOMEM; pcmdpriv->cmd_buf = pcmdpriv->cmd_allocated_buf + CMDBUFF_ALIGN_SZ - ((SIZE_PTR)(pcmdpriv->cmd_allocated_buf) & (CMDBUFF_ALIGN_SZ-1)); pcmdpriv->rsp_allocated_buf = rtw_zmalloc(MAX_RSPSZ + 4); if (!pcmdpriv->rsp_allocated_buf) { - res = -ENOMEM; - goto exit; + kfree(pcmdpriv->cmd_allocated_buf); + return -ENOMEM; } pcmdpriv->rsp_buf = pcmdpriv->rsp_allocated_buf + 4 - ((SIZE_PTR)(pcmdpriv->rsp_allocated_buf) & 3); @@ -199,8 +195,8 @@ int rtw_init_cmd_priv(struct cmd_priv *pcmdpriv) pcmdpriv->rsp_cnt = 0; mutex_init(&pcmdpriv->sctx_mutex); -exit: - return res; + + return 0; } static void c2h_wk_callback(_workitem * work); diff --git a/drivers/staging/vt6655/device_main.c b/drivers/staging/vt6655/device_main.c index 09ab6d6f2429b64fbea282c6323a8f33a3546c14..343f0de031546eeac5094ea6a6b21f6aef179b11 100644 --- a/drivers/staging/vt6655/device_main.c +++ b/drivers/staging/vt6655/device_main.c @@ -564,7 +564,7 @@ err_free_rd: kfree(desc->rd_info); err_free_desc: - while (--i) { + while (i--) { desc = &priv->aRD0Ring[i]; device_free_rx_buf(priv, desc); kfree(desc->rd_info); @@ -610,7 +610,7 @@ err_free_rd: kfree(desc->rd_info); err_free_desc: - while (--i) { + while (i--) { desc = &priv->aRD1Ring[i]; device_free_rx_buf(priv, desc); kfree(desc->rd_info); @@ -675,7 +675,7 @@ static int device_init_td0_ring(struct vnt_private *priv) return 0; err_free_desc: - while (--i) { + while (i--) { desc = &priv->apTD0Rings[i]; kfree(desc->td_info); } @@ -715,7 +715,7 @@ static int device_init_td1_ring(struct vnt_private *priv) return 0; err_free_desc: - while (--i) { + while (i--) { desc = &priv->apTD1Rings[i]; kfree(desc->td_info); } diff --git a/drivers/target/loopback/tcm_loop.c b/drivers/target/loopback/tcm_loop.c index 16d5a4e117a273bee3db4ac17db80938c2186932..5ae5d94c5b931cba9b66b49058a7c014142f3a51 100644 --- a/drivers/target/loopback/tcm_loop.c +++ b/drivers/target/loopback/tcm_loop.c @@ -394,6 +394,7 @@ static int tcm_loop_setup_hba_bus(struct tcm_loop_hba *tl_hba, int tcm_loop_host ret = device_register(&tl_hba->dev); if (ret) { pr_err("device_register() failed for tl_hba->dev: %d\n", ret); + put_device(&tl_hba->dev); return -ENODEV; } @@ -1072,7 +1073,7 @@ check_len: */ ret = tcm_loop_setup_hba_bus(tl_hba, tcm_loop_hba_no_cnt); if (ret) - goto out; + return ERR_PTR(ret); sh = tl_hba->sh; tcm_loop_hba_no_cnt++; diff --git a/drivers/tee/optee/device.c b/drivers/tee/optee/device.c index 031806468af48c1635ea5f316fcf01e335a20ed5..60ffc54da00333e7e3ce828c41a09f0915746e78 100644 --- a/drivers/tee/optee/device.c +++ b/drivers/tee/optee/device.c @@ -80,7 +80,7 @@ static int optee_register_device(const uuid_t *device_uuid) rc = device_register(&optee_device->dev); if (rc) { pr_err("device registration failed, err: %d\n", rc); - kfree(optee_device); + put_device(&optee_device->dev); } return rc; diff --git a/drivers/thermal/intel/intel_powerclamp.c b/drivers/thermal/intel/intel_powerclamp.c index b0eb5ece9243b2007002ed6beb5e76888348e049..fb04470d7d4bbb2b77b3655ee880839e7de45d98 100644 --- a/drivers/thermal/intel/intel_powerclamp.c +++ b/drivers/thermal/intel/intel_powerclamp.c @@ -531,9 +531,7 @@ static int start_power_clamp(void) get_online_cpus(); /* prefer BSP */ - control_cpu = 0; - if (!cpu_online(control_cpu)) - control_cpu = smp_processor_id(); + control_cpu = cpumask_first(cpu_online_mask); clamping = true; schedule_delayed_work(&poll_pkg_cstate_work, 0); diff --git a/drivers/thermal/qcom/tsens-v0_1.c b/drivers/thermal/qcom/tsens-v0_1.c index 4ffa2e2c0145777d0f1d65f0f4f0c9ad99486f56..9b8ba429a30498db55d83064cb19ba27f6de1426 100644 --- a/drivers/thermal/qcom/tsens-v0_1.c +++ b/drivers/thermal/qcom/tsens-v0_1.c @@ -522,7 +522,7 @@ static const struct tsens_ops ops_8939 = { struct tsens_plat_data data_8939 = { .num_sensors = 10, .ops = &ops_8939, - .hw_ids = (unsigned int []){ 0, 1, 2, 4, 5, 6, 7, 8, 9, 10 }, + .hw_ids = (unsigned int []){ 0, 1, 2, 3, 5, 6, 7, 8, 9, 10 }, .feat = &tsens_v0_1_feat, .fields = tsens_v0_1_regfields, diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c index 65f99d744654fc1578e65a3d42ab64e8ddc4eb4f..e881b72833dcf1681d8bc1e779461e38bbe72df1 100644 --- a/drivers/thunderbolt/switch.c +++ b/drivers/thunderbolt/switch.c @@ -2413,6 +2413,26 @@ void tb_switch_unconfigure_link(struct tb_switch *sw) tb_lc_unconfigure_port(down); } +static int tb_switch_port_hotplug_enable(struct tb_switch *sw) +{ + struct tb_port *port; + + if (tb_switch_is_icm(sw)) + return 0; + + tb_switch_for_each_port(sw, port) { + int res; + + if (!port->cap_usb4) + continue; + + res = usb4_port_hotplug_enable(port); + if (res) + return res; + } + return 0; +} + /** * tb_switch_add() - Add a switch to the domain * @sw: Switch to add @@ -2480,6 +2500,10 @@ int tb_switch_add(struct tb_switch *sw) return ret; } + ret = tb_switch_port_hotplug_enable(sw); + if (ret) + return ret; + ret = device_add(&sw->dev); if (ret) { dev_err(&sw->dev, "failed to add device: %d\n", ret); diff --git a/drivers/thunderbolt/tb.h b/drivers/thunderbolt/tb.h index 8ea360b0ff7736581a44aa9b8be82462c59205e4..266f3bf8ff5c66b2e405bd2dfee0f0d0abfcbcf4 100644 --- a/drivers/thunderbolt/tb.h +++ b/drivers/thunderbolt/tb.h @@ -979,6 +979,7 @@ struct tb_port *usb4_switch_map_usb3_down(struct tb_switch *sw, const struct tb_port *port); int usb4_port_unlock(struct tb_port *port); +int usb4_port_hotplug_enable(struct tb_port *port); int usb4_port_configure(struct tb_port *port); void usb4_port_unconfigure(struct tb_port *port); int usb4_port_configure_xdomain(struct tb_port *port); diff --git a/drivers/thunderbolt/tb_regs.h b/drivers/thunderbolt/tb_regs.h index e7d9529822fab3f920a0c444687b3b899c0d8ca3..26868e2f9d0bd1609770e5544203dee8e6452339 100644 --- a/drivers/thunderbolt/tb_regs.h +++ b/drivers/thunderbolt/tb_regs.h @@ -285,6 +285,7 @@ struct tb_regs_port_header { #define ADP_CS_5 0x05 #define ADP_CS_5_LCA_MASK GENMASK(28, 22) #define ADP_CS_5_LCA_SHIFT 22 +#define ADP_CS_5_DHP BIT(31) /* TMU adapter registers */ #define TMU_ADP_CS_3 0x03 diff --git a/drivers/thunderbolt/usb4.c b/drivers/thunderbolt/usb4.c index c05ec6fad77f6df8b7cf63fa29304b04e8b343e9..0b3a77ade04d9b8a3a789710fbf0e1db1d4f25ae 100644 --- a/drivers/thunderbolt/usb4.c +++ b/drivers/thunderbolt/usb4.c @@ -854,6 +854,26 @@ int usb4_port_unlock(struct tb_port *port) return tb_port_write(port, &val, TB_CFG_PORT, ADP_CS_4, 1); } +/** + * usb4_port_hotplug_enable() - Enables hotplug for a port + * @port: USB4 port to operate on + * + * Enables hot plug events on a given port. This is only intended + * to be used on lane, DP-IN, and DP-OUT adapters. + */ +int usb4_port_hotplug_enable(struct tb_port *port) +{ + int ret; + u32 val; + + ret = tb_port_read(port, &val, TB_CFG_PORT, ADP_CS_5, 1); + if (ret) + return ret; + + val &= ~ADP_CS_5_DHP; + return tb_port_write(port, &val, TB_CFG_PORT, ADP_CS_5, 1); +} + static int usb4_port_set_configured(struct tb_port *port, bool configured) { int ret; diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c index c91a3004931f1a67b3df92c95207ced470774c15..e8528282597357229ece7e08b01c3a93d68cd764 100644 --- a/drivers/tty/n_gsm.c +++ b/drivers/tty/n_gsm.c @@ -1416,7 +1416,7 @@ static struct gsm_control *gsm_control_send(struct gsm_mux *gsm, unsigned int command, u8 *data, int clen) { struct gsm_control *ctrl = kzalloc(sizeof(struct gsm_control), - GFP_KERNEL); + GFP_ATOMIC); unsigned long flags; if (ctrl == NULL) return NULL; diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c index 98ce484f1089dd7667f3d272bc0fc7f465cb970f..aae9d26ce4f40a956ab3c2df4c499cceae1521fb 100644 --- a/drivers/tty/serial/8250/8250_core.c +++ b/drivers/tty/serial/8250/8250_core.c @@ -332,9 +332,9 @@ static int univ8250_setup_irq(struct uart_8250_port *up) * hardware interrupt, we use a timer-based system. The original * driver used to do this with IRQ0. */ - if (!port->irq) { + if (!port->irq) mod_timer(&up->timer, jiffies + uart_poll_timeout(port)); - } else + else retval = serial_link_irq_chain(up); return retval; @@ -766,6 +766,7 @@ void serial8250_suspend_port(int line) if (!console_suspend_enabled && uart_console(port) && port->type != PORT_8250) { unsigned char canary = 0xa5; + serial_out(up, UART_SCR, canary); if (serial_in(up, UART_SCR) == canary) up->canary = canary; diff --git a/drivers/tty/serial/8250/8250_lpss.c b/drivers/tty/serial/8250/8250_lpss.c index dfb730b7ea2ae7b20ab0e42ff49d4ff78cb302b8..1349c161c19221d22e3b6466be3883bc4df8d48c 100644 --- a/drivers/tty/serial/8250/8250_lpss.c +++ b/drivers/tty/serial/8250/8250_lpss.c @@ -268,8 +268,13 @@ static int lpss8250_dma_setup(struct lpss8250 *lpss, struct uart_8250_port *port struct dw_dma_slave *rx_param, *tx_param; struct device *dev = port->port.dev; - if (!lpss->dma_param.dma_dev) + if (!lpss->dma_param.dma_dev) { + dma = port->dma; + if (dma) + goto out_configuration_only; + return 0; + } rx_param = devm_kzalloc(dev, sizeof(*rx_param), GFP_KERNEL); if (!rx_param) @@ -280,16 +285,18 @@ static int lpss8250_dma_setup(struct lpss8250 *lpss, struct uart_8250_port *port return -ENOMEM; *rx_param = lpss->dma_param; - dma->rxconf.src_maxburst = lpss->dma_maxburst; - *tx_param = lpss->dma_param; - dma->txconf.dst_maxburst = lpss->dma_maxburst; dma->fn = lpss8250_dma_filter; dma->rx_param = rx_param; dma->tx_param = tx_param; port->dma = dma; + +out_configuration_only: + dma->rxconf.src_maxburst = lpss->dma_maxburst; + dma->txconf.dst_maxburst = lpss->dma_maxburst; + return 0; } diff --git a/drivers/tty/serial/8250/8250_omap.c b/drivers/tty/serial/8250/8250_omap.c index 537bee8d2258abe60c312608d0b2eadd93a39e22..483fff3a95c9eca323e212dfda04a41584f54748 100644 --- a/drivers/tty/serial/8250/8250_omap.c +++ b/drivers/tty/serial/8250/8250_omap.c @@ -157,7 +157,11 @@ static u32 uart_read(struct uart_8250_port *up, u32 reg) return readl(up->port.membase + (reg << up->port.regshift)); } -static void omap8250_set_mctrl(struct uart_port *port, unsigned int mctrl) +/* + * Called on runtime PM resume path from omap8250_restore_regs(), and + * omap8250_set_mctrl(). + */ +static void __omap8250_set_mctrl(struct uart_port *port, unsigned int mctrl) { struct uart_8250_port *up = up_to_u8250p(port); struct omap8250_priv *priv = up->port.private_data; @@ -181,6 +185,20 @@ static void omap8250_set_mctrl(struct uart_port *port, unsigned int mctrl) } } +static void omap8250_set_mctrl(struct uart_port *port, unsigned int mctrl) +{ + int err; + + err = pm_runtime_resume_and_get(port->dev); + if (err) + return; + + __omap8250_set_mctrl(port, mctrl); + + pm_runtime_mark_last_busy(port->dev); + pm_runtime_put_autosuspend(port->dev); +} + /* * Work Around for Errata i202 (2430, 3430, 3630, 4430 and 4460) * The access to uart register after MDR1 Access @@ -193,27 +211,10 @@ static void omap8250_set_mctrl(struct uart_port *port, unsigned int mctrl) static void omap_8250_mdr1_errataset(struct uart_8250_port *up, struct omap8250_priv *priv) { - u8 timeout = 255; - serial_out(up, UART_OMAP_MDR1, priv->mdr1); udelay(2); serial_out(up, UART_FCR, up->fcr | UART_FCR_CLEAR_XMIT | UART_FCR_CLEAR_RCVR); - /* - * Wait for FIFO to empty: when empty, RX_FIFO_E bit is 0 and - * TX_FIFO_E bit is 1. - */ - while (UART_LSR_THRE != (serial_in(up, UART_LSR) & - (UART_LSR_THRE | UART_LSR_DR))) { - timeout--; - if (!timeout) { - /* Should *never* happen. we warn and carry on */ - dev_crit(up->port.dev, "Errata i202: timedout %x\n", - serial_in(up, UART_LSR)); - break; - } - udelay(1); - } } static void omap_8250_get_divisor(struct uart_port *port, unsigned int baud, @@ -292,6 +293,7 @@ static void omap8250_restore_regs(struct uart_8250_port *up) { struct omap8250_priv *priv = up->port.private_data; struct uart_8250_dma *dma = up->dma; + u8 mcr = serial8250_in_MCR(up); if (dma && dma->tx_running) { /* @@ -308,7 +310,7 @@ static void omap8250_restore_regs(struct uart_8250_port *up) serial_out(up, UART_EFR, UART_EFR_ECB); serial_out(up, UART_LCR, UART_LCR_CONF_MODE_A); - serial8250_out_MCR(up, UART_MCR_TCRTLR); + serial8250_out_MCR(up, mcr | UART_MCR_TCRTLR); serial_out(up, UART_FCR, up->fcr); omap8250_update_scr(up, priv); @@ -324,7 +326,8 @@ static void omap8250_restore_regs(struct uart_8250_port *up) serial_out(up, UART_LCR, 0); /* drop TCR + TLR access, we setup XON/XOFF later */ - serial8250_out_MCR(up, up->mcr); + serial8250_out_MCR(up, mcr); + serial_out(up, UART_IER, up->ier); serial_out(up, UART_LCR, UART_LCR_CONF_MODE_B); @@ -341,7 +344,10 @@ static void omap8250_restore_regs(struct uart_8250_port *up) omap8250_update_mdr1(up, priv); - up->port.ops->set_mctrl(&up->port, up->port.mctrl); + __omap8250_set_mctrl(&up->port, up->port.mctrl); + + if (up->port.rs485.flags & SER_RS485_ENABLED) + serial8250_em485_stop_tx(up); } /* @@ -680,7 +686,6 @@ static int omap_8250_startup(struct uart_port *port) pm_runtime_get_sync(port->dev); - up->mcr = 0; serial_out(up, UART_FCR, UART_FCR_CLEAR_RCVR | UART_FCR_CLEAR_XMIT); serial_out(up, UART_LCR, UART_LCR_WLEN8); @@ -1471,9 +1476,15 @@ err: static int omap8250_remove(struct platform_device *pdev) { struct omap8250_priv *priv = platform_get_drvdata(pdev); + int err; + + err = pm_runtime_resume_and_get(&pdev->dev); + if (err) + return err; pm_runtime_dont_use_autosuspend(&pdev->dev); pm_runtime_put_sync(&pdev->dev); + flush_work(&priv->qos_work); pm_runtime_disable(&pdev->dev); serial8250_unregister_port(priv->line); cpu_latency_qos_remove_request(&priv->pm_qos_request); diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c index df10cc606582b121a7cf436d63126b120c5ed756..b6656898699d10f5dd01e86e60cf341f9f3a9a8f 100644 --- a/drivers/tty/serial/8250/8250_pci.c +++ b/drivers/tty/serial/8250/8250_pci.c @@ -1531,7 +1531,6 @@ static int pci_fintek_init(struct pci_dev *dev) resource_size_t bar_data[3]; u8 config_base; struct serial_private *priv = pci_get_drvdata(dev); - struct uart_8250_port *port; if (!(pci_resource_flags(dev, 5) & IORESOURCE_IO) || !(pci_resource_flags(dev, 4) & IORESOURCE_IO) || @@ -1578,13 +1577,7 @@ static int pci_fintek_init(struct pci_dev *dev) pci_write_config_byte(dev, config_base + 0x06, dev->irq); - if (priv) { - /* re-apply RS232/485 mode when - * pciserial_resume_ports() - */ - port = serial8250_get_port(priv->line[i]); - pci_fintek_rs485_config(&port->port, NULL); - } else { + if (!priv) { /* First init without port data * force init to RS232 Mode */ diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index 9d60418e4adb1c27b7bcc905d9e5dd75ebeffb0d..70aaea8409183f766030bc7e9aaf736e80077189 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -592,7 +592,7 @@ EXPORT_SYMBOL_GPL(serial8250_rpm_put); static int serial8250_em485_init(struct uart_8250_port *p) { if (p->em485) - return 0; + goto deassert_rts; p->em485 = kmalloc(sizeof(struct uart_8250_em485), GFP_ATOMIC); if (!p->em485) @@ -608,7 +608,9 @@ static int serial8250_em485_init(struct uart_8250_port *p) p->em485->active_timer = NULL; p->em485->tx_stopped = true; - p->rs485_stop_tx(p); +deassert_rts: + if (p->em485->tx_stopped) + p->rs485_stop_tx(p); return 0; } @@ -659,13 +661,6 @@ int serial8250_em485_config(struct uart_port *port, struct serial_rs485 *rs485) rs485->flags &= ~SER_RS485_RTS_AFTER_SEND; } - /* clamp the delays to [0, 100ms] */ - rs485->delay_rts_before_send = min(rs485->delay_rts_before_send, 100U); - rs485->delay_rts_after_send = min(rs485->delay_rts_after_send, 100U); - - memset(rs485->padding, 0, sizeof(rs485->padding)); - port->rs485 = *rs485; - gpiod_set_value(port->rs485_term_gpio, rs485->flags & SER_RS485_TERMINATE_BUS); @@ -673,15 +668,8 @@ int serial8250_em485_config(struct uart_port *port, struct serial_rs485 *rs485) * Both serial8250_em485_init() and serial8250_em485_destroy() * are idempotent. */ - if (rs485->flags & SER_RS485_ENABLED) { - int ret = serial8250_em485_init(up); - - if (ret) { - rs485->flags &= ~SER_RS485_ENABLED; - port->rs485.flags &= ~SER_RS485_ENABLED; - } - return ret; - } + if (rs485->flags & SER_RS485_ENABLED) + return serial8250_em485_init(up); serial8250_em485_destroy(up); return 0; @@ -1880,10 +1868,13 @@ EXPORT_SYMBOL_GPL(serial8250_modem_status); static bool handle_rx_dma(struct uart_8250_port *up, unsigned int iir) { switch (iir & 0x3f) { - case UART_IIR_RX_TIMEOUT: - serial8250_rx_dma_flush(up); + case UART_IIR_RDI: + if (!up->dma->rx_running) + break; fallthrough; case UART_IIR_RLSI: + case UART_IIR_RX_TIMEOUT: + serial8250_rx_dma_flush(up); return true; } return up->dma->rx_dma(up); @@ -2030,6 +2021,9 @@ EXPORT_SYMBOL_GPL(serial8250_do_set_mctrl); static void serial8250_set_mctrl(struct uart_port *port, unsigned int mctrl) { + if (port->rs485.flags & SER_RS485_ENABLED) + return; + if (port->set_mctrl) port->set_mctrl(port, mctrl); else @@ -3159,9 +3153,6 @@ static void serial8250_config_port(struct uart_port *port, int flags) if (flags & UART_CONFIG_TYPE) autoconfig(up); - if (port->rs485.flags & SER_RS485_ENABLED) - port->rs485_config(port, &port->rs485); - /* if access method is AU, it is a 16550 with a quirk */ if (port->type == PORT_16550A && port->iotype == UPIO_AU) up->bugs |= UART_BUG_NOMSR; @@ -3286,8 +3277,13 @@ static void serial8250_console_restore(struct uart_8250_port *up) unsigned int baud, quot, frac = 0; termios.c_cflag = port->cons->cflag; - if (port->state->port.tty && termios.c_cflag == 0) + termios.c_ispeed = port->cons->ispeed; + termios.c_ospeed = port->cons->ospeed; + if (port->state->port.tty && termios.c_cflag == 0) { termios.c_cflag = port->state->port.tty->termios.c_cflag; + termios.c_ispeed = port->state->port.tty->termios.c_ispeed; + termios.c_ospeed = port->state->port.tty->termios.c_ospeed; + } baud = serial8250_get_baud_rate(port, &termios, NULL); quot = serial8250_get_divisor(port, baud, &frac); diff --git a/drivers/tty/serial/8250/Kconfig b/drivers/tty/serial/8250/Kconfig index 603137da47363bda89a2778badeb38b84be81374..136f2b1460f919ea25c4ffb4c142419fa922788c 100644 --- a/drivers/tty/serial/8250/Kconfig +++ b/drivers/tty/serial/8250/Kconfig @@ -119,7 +119,7 @@ config SERIAL_8250_CONSOLE config SERIAL_8250_GSC tristate - depends on SERIAL_8250 && GSC + depends on SERIAL_8250 && PARISC default SERIAL_8250 config SERIAL_8250_DMA diff --git a/drivers/tty/serial/ar933x_uart.c b/drivers/tty/serial/ar933x_uart.c index c2be7cf91399295b6be57734253d9a67b0c092da..fcbaff8941930a7700c00adf18412294956fad5e 100644 --- a/drivers/tty/serial/ar933x_uart.c +++ b/drivers/tty/serial/ar933x_uart.c @@ -593,6 +593,11 @@ static int ar933x_config_rs485(struct uart_port *port, dev_err(port->dev, "RS485 needs rts-gpio\n"); return 1; } + + if (rs485conf->flags & SER_RS485_ENABLED) + gpiod_set_value(up->rts_gpiod, + !!(rs485conf->flags & SER_RS485_RTS_AFTER_SEND)); + port->rs485 = *rs485conf; return 0; } diff --git a/drivers/tty/serial/fsl_lpuart.c b/drivers/tty/serial/fsl_lpuart.c index a2c4eab0b47031cb7b7c891f5929d95c79c11b55..43aca5a2ef0f2b54780a1281e8eca9f3be013269 100644 --- a/drivers/tty/serial/fsl_lpuart.c +++ b/drivers/tty/serial/fsl_lpuart.c @@ -1725,6 +1725,7 @@ static void lpuart_dma_shutdown(struct lpuart_port *sport) if (sport->lpuart_dma_rx_use) { del_timer_sync(&sport->lpuart_timer); lpuart_dma_rx_free(&sport->port); + sport->lpuart_dma_rx_use = false; } if (sport->lpuart_dma_tx_use) { @@ -1733,6 +1734,7 @@ static void lpuart_dma_shutdown(struct lpuart_port *sport) sport->dma_tx_in_progress = false; dmaengine_terminate_all(sport->dma_tx_chan); } + sport->lpuart_dma_tx_use = false; } if (sport->dma_tx_chan) @@ -2667,10 +2669,6 @@ static int lpuart_probe(struct platform_device *pdev) if (ret) goto failed_irq_request; - ret = uart_add_one_port(&lpuart_reg, &sport->port); - if (ret) - goto failed_attach_port; - ret = uart_get_rs485_mode(&sport->port); if (ret) goto failed_get_rs485; @@ -2682,7 +2680,9 @@ static int lpuart_probe(struct platform_device *pdev) sport->port.rs485.delay_rts_after_send) dev_err(&pdev->dev, "driver doesn't support RTS delays\n"); - sport->port.rs485_config(&sport->port, &sport->port.rs485); + ret = uart_add_one_port(&lpuart_reg, &sport->port); + if (ret) + goto failed_attach_port; return 0; diff --git a/drivers/tty/serial/imx.c b/drivers/tty/serial/imx.c index bfbca711bbf9bf4ce99e249a3fca751eb4c7d730..164597e2e00443de7207c0fffb1ce446398c71c9 100644 --- a/drivers/tty/serial/imx.c +++ b/drivers/tty/serial/imx.c @@ -398,8 +398,7 @@ static void imx_uart_rts_active(struct imx_port *sport, u32 *ucr2) { *ucr2 &= ~(UCR2_CTSC | UCR2_CTS); - sport->port.mctrl |= TIOCM_RTS; - mctrl_gpio_set(sport->gpios, sport->port.mctrl); + mctrl_gpio_set(sport->gpios, sport->port.mctrl | TIOCM_RTS); } /* called with port.lock taken and irqs caller dependent */ @@ -408,8 +407,7 @@ static void imx_uart_rts_inactive(struct imx_port *sport, u32 *ucr2) *ucr2 &= ~UCR2_CTSC; *ucr2 |= UCR2_CTS; - sport->port.mctrl &= ~TIOCM_RTS; - mctrl_gpio_set(sport->gpios, sport->port.mctrl); + mctrl_gpio_set(sport->gpios, sport->port.mctrl & ~TIOCM_RTS); } static void start_hrtimer_ms(struct hrtimer *hrt, unsigned long msec) @@ -2381,8 +2379,6 @@ static int imx_uart_probe(struct platform_device *pdev) dev_err(&pdev->dev, "low-active RTS not possible when receiver is off, enabling receiver\n"); - imx_uart_rs485_config(&sport->port, &sport->port.rs485); - /* Disable interrupts before requesting them */ ucr1 = imx_uart_readl(sport, UCR1); ucr1 &= ~(UCR1_ADEN | UCR1_TRDYEN | UCR1_IDEN | UCR1_RRDYEN | UCR1_RTSDEN); @@ -2630,6 +2626,7 @@ static const struct dev_pm_ops imx_uart_pm_ops = { .suspend_noirq = imx_uart_suspend_noirq, .resume_noirq = imx_uart_resume_noirq, .freeze_noirq = imx_uart_suspend_noirq, + .thaw_noirq = imx_uart_resume_noirq, .restore_noirq = imx_uart_resume_noirq, .suspend = imx_uart_suspend, .resume = imx_uart_resume, diff --git a/drivers/tty/serial/jsm/jsm_driver.c b/drivers/tty/serial/jsm/jsm_driver.c index cd30da0ef08344a2bb0342f6c705c4e3f6438c3f..b5b61e598b5339561107ca0bd09b970728129bfe 100644 --- a/drivers/tty/serial/jsm/jsm_driver.c +++ b/drivers/tty/serial/jsm/jsm_driver.c @@ -212,7 +212,8 @@ static int jsm_probe_one(struct pci_dev *pdev, const struct pci_device_id *ent) break; default: - return -ENXIO; + rc = -ENXIO; + goto out_kfree_brd; } rc = request_irq(brd->irq, brd->bd_ops->intr, IRQF_SHARED, "JSM", brd); diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index b578f7090b6377f2d797490ec3684159114e896d..605f928f0636a774fb00d80202bf0090b512dcef 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -42,6 +42,11 @@ static struct lock_class_key port_lock_key; #define HIGH_BITS_OFFSET ((sizeof(long)-sizeof(int))*8) +/* + * Max time with active RTS before/after data is sent. + */ +#define RS485_MAX_RTS_DELAY 100 /* msecs */ + static void uart_change_speed(struct tty_struct *tty, struct uart_state *state, struct ktermios *old_termios); static void uart_wait_until_sent(struct tty_struct *tty, int timeout); @@ -144,15 +149,10 @@ uart_update_mctrl(struct uart_port *port, unsigned int set, unsigned int clear) unsigned long flags; unsigned int old; - if (port->rs485.flags & SER_RS485_ENABLED) { - set &= ~TIOCM_RTS; - clear &= ~TIOCM_RTS; - } - spin_lock_irqsave(&port->lock, flags); old = port->mctrl; port->mctrl = (old & ~clear) | set; - if (old != port->mctrl) + if (old != port->mctrl && !(port->rs485.flags & SER_RS485_ENABLED)) port->ops->set_mctrl(port, port->mctrl); spin_unlock_irqrestore(&port->lock, flags); } @@ -1326,8 +1326,41 @@ static int uart_set_rs485_config(struct uart_port *port, if (copy_from_user(&rs485, rs485_user, sizeof(*rs485_user))) return -EFAULT; + /* pick sane settings if the user hasn't */ + if (!(rs485.flags & SER_RS485_RTS_ON_SEND) == + !(rs485.flags & SER_RS485_RTS_AFTER_SEND)) { + dev_warn_ratelimited(port->dev, + "%s (%d): invalid RTS setting, using RTS_ON_SEND instead\n", + port->name, port->line); + rs485.flags |= SER_RS485_RTS_ON_SEND; + rs485.flags &= ~SER_RS485_RTS_AFTER_SEND; + } + + if (rs485.delay_rts_before_send > RS485_MAX_RTS_DELAY) { + rs485.delay_rts_before_send = RS485_MAX_RTS_DELAY; + dev_warn_ratelimited(port->dev, + "%s (%d): RTS delay before sending clamped to %u ms\n", + port->name, port->line, rs485.delay_rts_before_send); + } + + if (rs485.delay_rts_after_send > RS485_MAX_RTS_DELAY) { + rs485.delay_rts_after_send = RS485_MAX_RTS_DELAY; + dev_warn_ratelimited(port->dev, + "%s (%d): RTS delay after sending clamped to %u ms\n", + port->name, port->line, rs485.delay_rts_after_send); + } + /* Return clean padding area to userspace */ + memset(rs485.padding, 0, sizeof(rs485.padding)); + spin_lock_irqsave(&port->lock, flags); ret = port->rs485_config(port, &rs485); + if (!ret) { + port->rs485 = rs485; + + /* Reset RTS and other mctrl lines when disabling RS485 */ + if (!(rs485.flags & SER_RS485_ENABLED)) + port->ops->set_mctrl(port, port->mctrl); + } spin_unlock_irqrestore(&port->lock, flags); if (ret) return ret; @@ -2302,7 +2335,8 @@ int uart_resume_port(struct uart_driver *drv, struct uart_port *uport) uart_change_pm(state, UART_PM_STATE_ON); spin_lock_irq(&uport->lock); - ops->set_mctrl(uport, 0); + if (!(uport->rs485.flags & SER_RS485_ENABLED)) + ops->set_mctrl(uport, 0); spin_unlock_irq(&uport->lock); if (console_suspend_enabled || !uart_console(uport)) { /* Protected by port mutex for now */ @@ -2313,7 +2347,10 @@ int uart_resume_port(struct uart_driver *drv, struct uart_port *uport) if (tty) uart_change_speed(tty, state, NULL); spin_lock_irq(&uport->lock); - ops->set_mctrl(uport, uport->mctrl); + if (!(uport->rs485.flags & SER_RS485_ENABLED)) + ops->set_mctrl(uport, uport->mctrl); + else + uport->rs485_config(uport, &uport->rs485); ops->start_tx(uport); spin_unlock_irq(&uport->lock); tty_port_set_initialized(port, 1); @@ -2411,10 +2448,10 @@ uart_configure_port(struct uart_driver *drv, struct uart_state *state, */ spin_lock_irqsave(&port->lock, flags); port->mctrl &= TIOCM_DTR; - if (port->rs485.flags & SER_RS485_ENABLED && - !(port->rs485.flags & SER_RS485_RTS_AFTER_SEND)) - port->mctrl |= TIOCM_RTS; - port->ops->set_mctrl(port, port->mctrl); + if (!(port->rs485.flags & SER_RS485_ENABLED)) + port->ops->set_mctrl(port, port->mctrl); + else + port->rs485_config(port, &port->rs485); spin_unlock_irqrestore(&port->lock, flags); /* diff --git a/drivers/tty/serial/xilinx_uartps.c b/drivers/tty/serial/xilinx_uartps.c index b5a8afbc452ba6d4b4b3313684c780ba21d95d81..f7dfa123907ab660e4ff871985f1dd1a49ee202e 100644 --- a/drivers/tty/serial/xilinx_uartps.c +++ b/drivers/tty/serial/xilinx_uartps.c @@ -375,6 +375,8 @@ static irqreturn_t cdns_uart_isr(int irq, void *dev_id) isrstatus &= ~CDNS_UART_IXR_TXEMPTY; } + isrstatus &= port->read_status_mask; + isrstatus &= ~port->ignore_status_mask; /* * Skip RX processing if RX is disabled as RXEMPTY will never be set * as read bytes will not be removed from the FIFO. diff --git a/drivers/usb/cdns3/core.c b/drivers/usb/cdns3/core.c index 6eeb7ed8e91f364d027ccce62a902dc1bde401c4..8fe7420de033dfc5f18503505983a03f8b1ee718 100644 --- a/drivers/usb/cdns3/core.c +++ b/drivers/usb/cdns3/core.c @@ -97,13 +97,23 @@ static int cdns3_core_init_role(struct cdns3 *cdns) * can be restricted later depending on strap pin configuration. */ if (dr_mode == USB_DR_MODE_UNKNOWN) { - if (IS_ENABLED(CONFIG_USB_CDNS3_HOST) && - IS_ENABLED(CONFIG_USB_CDNS3_GADGET)) - dr_mode = USB_DR_MODE_OTG; - else if (IS_ENABLED(CONFIG_USB_CDNS3_HOST)) - dr_mode = USB_DR_MODE_HOST; - else if (IS_ENABLED(CONFIG_USB_CDNS3_GADGET)) - dr_mode = USB_DR_MODE_PERIPHERAL; + if (cdns->version == CDNSP_CONTROLLER_V2) { + if (IS_ENABLED(CONFIG_USB_CDNSP_HOST) && + IS_ENABLED(CONFIG_USB_CDNSP_GADGET)) + dr_mode = USB_DR_MODE_OTG; + else if (IS_ENABLED(CONFIG_USB_CDNSP_HOST)) + dr_mode = USB_DR_MODE_HOST; + else if (IS_ENABLED(CONFIG_USB_CDNSP_GADGET)) + dr_mode = USB_DR_MODE_PERIPHERAL; + } else { + if (IS_ENABLED(CONFIG_USB_CDNS3_HOST) && + IS_ENABLED(CONFIG_USB_CDNS3_GADGET)) + dr_mode = USB_DR_MODE_OTG; + else if (IS_ENABLED(CONFIG_USB_CDNS3_HOST)) + dr_mode = USB_DR_MODE_HOST; + else if (IS_ENABLED(CONFIG_USB_CDNS3_GADGET)) + dr_mode = USB_DR_MODE_PERIPHERAL; + } } /* diff --git a/drivers/usb/cdns3/core.h b/drivers/usb/cdns3/core.h index 3176f924293a188b922be6271435627478d8f603..0d87871499eaa2f7ed0ca6fece2a80e3ba6d4ce6 100644 --- a/drivers/usb/cdns3/core.h +++ b/drivers/usb/cdns3/core.h @@ -55,7 +55,9 @@ struct cdns3_platform_data { * @otg_res: the resource for otg * @otg_v0_regs: pointer to base of v0 otg registers * @otg_v1_regs: pointer to base of v1 otg registers + * @otg_cdnsp_regs: pointer to base of CDNSP otg registers * @otg_regs: pointer to base of otg registers + * @otg_irq_regs: pointer to interrupt registers * @otg_irq: irq number for otg controller * @dev_irq: irq number for device controller * @wakeup_irq: irq number for wakeup event, it is optional @@ -86,9 +88,12 @@ struct cdns3 { struct resource otg_res; struct cdns3_otg_legacy_regs *otg_v0_regs; struct cdns3_otg_regs *otg_v1_regs; + struct cdnsp_otg_regs *otg_cdnsp_regs; struct cdns3_otg_common_regs *otg_regs; + struct cdns3_otg_irq_regs *otg_irq_regs; #define CDNS3_CONTROLLER_V0 0 #define CDNS3_CONTROLLER_V1 1 +#define CDNSP_CONTROLLER_V2 2 u32 version; bool phyrst_a_enable; diff --git a/drivers/usb/cdns3/drd.c b/drivers/usb/cdns3/drd.c index 38ccd29e4cdef1e0dda34fc13cb4bb774d9642ca..95863d44e3e09eef840ac427d495045a8a9dfad8 100644 --- a/drivers/usb/cdns3/drd.c +++ b/drivers/usb/cdns3/drd.c @@ -2,13 +2,12 @@ /* * Cadence USBSS DRD Driver. * - * Copyright (C) 2018-2019 Cadence. + * Copyright (C) 2018-2020 Cadence. * Copyright (C) 2019 Texas Instruments * * Author: Pawel Laszczak * Roger Quadros * - * */ #include #include @@ -28,8 +27,9 @@ * * Returns 0 on success otherwise negative errno */ -int cdns3_set_mode(struct cdns3 *cdns, enum usb_dr_mode mode) +static int cdns3_set_mode(struct cdns3 *cdns, enum usb_dr_mode mode) { + u32 __iomem *override_reg; u32 reg; switch (mode) { @@ -39,11 +39,24 @@ int cdns3_set_mode(struct cdns3 *cdns, enum usb_dr_mode mode) break; case USB_DR_MODE_OTG: dev_dbg(cdns->dev, "Set controller to OTG mode\n"); - if (cdns->version == CDNS3_CONTROLLER_V1) { - reg = readl(&cdns->otg_v1_regs->override); + + if (cdns->version == CDNSP_CONTROLLER_V2) + override_reg = &cdns->otg_cdnsp_regs->override; + else if (cdns->version == CDNS3_CONTROLLER_V1) + override_reg = &cdns->otg_v1_regs->override; + else + override_reg = &cdns->otg_v0_regs->ctrl1; + + reg = readl(override_reg); + + if (cdns->version != CDNS3_CONTROLLER_V0) reg |= OVERRIDE_IDPULLUP; - writel(reg, &cdns->otg_v1_regs->override); + else + reg |= OVERRIDE_IDPULLUP_V0; + writel(reg, override_reg); + + if (cdns->version == CDNS3_CONTROLLER_V1) { /* * Enable work around feature built into the * controller to address issue with RX Sensitivity @@ -55,10 +68,6 @@ int cdns3_set_mode(struct cdns3 *cdns, enum usb_dr_mode mode) reg |= PHYRST_CFG_PHYRST_A_ENABLE; writel(reg, &cdns->otg_v1_regs->phyrst_cfg); } - } else { - reg = readl(&cdns->otg_v0_regs->ctrl1); - reg |= OVERRIDE_IDPULLUP_V0; - writel(reg, &cdns->otg_v0_regs->ctrl1); } /* @@ -123,7 +132,7 @@ bool cdns3_is_device(struct cdns3 *cdns) */ static void cdns3_otg_disable_irq(struct cdns3 *cdns) { - writel(0, &cdns->otg_regs->ien); + writel(0, &cdns->otg_irq_regs->ien); } /** @@ -133,7 +142,7 @@ static void cdns3_otg_disable_irq(struct cdns3 *cdns) static void cdns3_otg_enable_irq(struct cdns3 *cdns) { writel(OTGIEN_ID_CHANGE_INT | OTGIEN_VBUSVALID_RISE_INT | - OTGIEN_VBUSVALID_FALL_INT, &cdns->otg_regs->ien); + OTGIEN_VBUSVALID_FALL_INT, &cdns->otg_irq_regs->ien); } /** @@ -144,16 +153,21 @@ static void cdns3_otg_enable_irq(struct cdns3 *cdns) */ int cdns3_drd_host_on(struct cdns3 *cdns) { - u32 val; + u32 val, ready_bit; int ret; /* Enable host mode. */ writel(OTGCMD_HOST_BUS_REQ | OTGCMD_OTG_DIS, &cdns->otg_regs->cmd); + if (cdns->version == CDNSP_CONTROLLER_V2) + ready_bit = OTGSTS_CDNSP_XHCI_READY; + else + ready_bit = OTGSTS_CDNS3_XHCI_READY; + dev_dbg(cdns->dev, "Waiting till Host mode is turned on\n"); ret = readl_poll_timeout_atomic(&cdns->otg_regs->sts, val, - val & OTGSTS_XHCI_READY, 1, 100000); + val & ready_bit, 1, 100000); if (ret) dev_err(cdns->dev, "timeout waiting for xhci_ready\n"); @@ -189,17 +203,22 @@ void cdns3_drd_host_off(struct cdns3 *cdns) */ int cdns3_drd_gadget_on(struct cdns3 *cdns) { - int ret, val; u32 reg = OTGCMD_OTG_DIS; + u32 ready_bit; + int ret, val; /* switch OTG core */ writel(OTGCMD_DEV_BUS_REQ | reg, &cdns->otg_regs->cmd); dev_dbg(cdns->dev, "Waiting till Device mode is turned on\n"); + if (cdns->version == CDNSP_CONTROLLER_V2) + ready_bit = OTGSTS_CDNSP_DEV_READY; + else + ready_bit = OTGSTS_CDNS3_DEV_READY; + ret = readl_poll_timeout_atomic(&cdns->otg_regs->sts, val, - val & OTGSTS_DEV_READY, - 1, 100000); + val & ready_bit, 1, 100000); if (ret) { dev_err(cdns->dev, "timeout waiting for dev_ready\n"); return ret; @@ -244,7 +263,7 @@ static int cdns3_init_otg_mode(struct cdns3 *cdns) cdns3_otg_disable_irq(cdns); /* clear all interrupts */ - writel(~0, &cdns->otg_regs->ivect); + writel(~0, &cdns->otg_irq_regs->ivect); ret = cdns3_set_mode(cdns, USB_DR_MODE_OTG); if (ret) @@ -313,7 +332,7 @@ static irqreturn_t cdns3_drd_irq(int irq, void *data) if (cdns->in_lpm) return ret; - reg = readl(&cdns->otg_regs->ivect); + reg = readl(&cdns->otg_irq_regs->ivect); if (!reg) return IRQ_NONE; @@ -332,7 +351,7 @@ static irqreturn_t cdns3_drd_irq(int irq, void *data) ret = IRQ_WAKE_THREAD; } - writel(~0, &cdns->otg_regs->ivect); + writel(~0, &cdns->otg_irq_regs->ivect); return ret; } @@ -347,28 +366,43 @@ int cdns3_drd_init(struct cdns3 *cdns) return PTR_ERR(regs); /* Detection of DRD version. Controller has been released - * in two versions. Both are similar, but they have same changes - * in register maps. - * The first register in old version is command register and it's read - * only, so driver should read 0 from it. On the other hand, in v1 - * the first register contains device ID number which is not set to 0. - * Driver uses this fact to detect the proper version of + * in three versions. All are very similar and are software compatible, + * but they have same changes in register maps. + * The first register in oldest version is command register and it's + * read only. Driver should read 0 from it. On the other hand, in v1 + * and v2 the first register contains device ID number which is not + * set to 0. Driver uses this fact to detect the proper version of * controller. */ cdns->otg_v0_regs = regs; if (!readl(&cdns->otg_v0_regs->cmd)) { cdns->version = CDNS3_CONTROLLER_V0; cdns->otg_v1_regs = NULL; + cdns->otg_cdnsp_regs = NULL; cdns->otg_regs = regs; + cdns->otg_irq_regs = (struct cdns3_otg_irq_regs *) + &cdns->otg_v0_regs->ien; writel(1, &cdns->otg_v0_regs->simulate); dev_dbg(cdns->dev, "DRD version v0 (%08x)\n", readl(&cdns->otg_v0_regs->version)); } else { cdns->otg_v0_regs = NULL; cdns->otg_v1_regs = regs; + cdns->otg_cdnsp_regs = regs; + cdns->otg_regs = (void *)&cdns->otg_v1_regs->cmd; - cdns->version = CDNS3_CONTROLLER_V1; - writel(1, &cdns->otg_v1_regs->simulate); + + if (cdns->otg_cdnsp_regs->did == OTG_CDNSP_DID) { + cdns->otg_irq_regs = (struct cdns3_otg_irq_regs *) + &cdns->otg_cdnsp_regs->ien; + cdns->version = CDNSP_CONTROLLER_V2; + } else { + cdns->otg_irq_regs = (struct cdns3_otg_irq_regs *) + &cdns->otg_v1_regs->ien; + writel(1, &cdns->otg_v1_regs->simulate); + cdns->version = CDNS3_CONTROLLER_V1; + } + dev_dbg(cdns->dev, "DRD version v1 (ID: %08x, rev: %08x)\n", readl(&cdns->otg_v1_regs->did), readl(&cdns->otg_v1_regs->rid)); @@ -378,10 +412,17 @@ int cdns3_drd_init(struct cdns3 *cdns) /* Update dr_mode according to STRAP configuration. */ cdns->dr_mode = USB_DR_MODE_OTG; - if (state == OTGSTS_STRAP_HOST) { + + if ((cdns->version == CDNSP_CONTROLLER_V2 && + state == OTGSTS_CDNSP_STRAP_HOST) || + (cdns->version != CDNSP_CONTROLLER_V2 && + state == OTGSTS_STRAP_HOST)) { dev_dbg(cdns->dev, "Controller strapped to HOST\n"); cdns->dr_mode = USB_DR_MODE_HOST; - } else if (state == OTGSTS_STRAP_GADGET) { + } else if ((cdns->version == CDNSP_CONTROLLER_V2 && + state == OTGSTS_CDNSP_STRAP_GADGET) || + (cdns->version != CDNSP_CONTROLLER_V2 && + state == OTGSTS_STRAP_GADGET)) { dev_dbg(cdns->dev, "Controller strapped to PERIPHERAL\n"); cdns->dr_mode = USB_DR_MODE_PERIPHERAL; } diff --git a/drivers/usb/cdns3/drd.h b/drivers/usb/cdns3/drd.h index f1ccae285a16dbd40e03ec3a4607b4140025dde5..a767b6893938c33b793640555b7a0a63ee2caff9 100644 --- a/drivers/usb/cdns3/drd.h +++ b/drivers/usb/cdns3/drd.h @@ -1,8 +1,8 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* - * Cadence USB3 DRD header file. + * Cadence USB3 and USBSSP DRD header file. * - * Copyright (C) 2018-2019 Cadence. + * Copyright (C) 2018-2020 Cadence. * * Author: Pawel Laszczak */ @@ -13,7 +13,7 @@ #include #include "core.h" -/* DRD register interface for version v1. */ +/* DRD register interface for version v1 of cdns3 driver. */ struct cdns3_otg_regs { __le32 did; __le32 rid; @@ -38,7 +38,7 @@ struct cdns3_otg_regs { __le32 ctrl2; }; -/* DRD register interface for version v0. */ +/* DRD register interface for version v0 of cdns3 driver. */ struct cdns3_otg_legacy_regs { __le32 cmd; __le32 sts; @@ -57,14 +57,45 @@ struct cdns3_otg_legacy_regs { __le32 ctrl1; }; +/* DRD register interface for cdnsp driver */ +struct cdnsp_otg_regs { + __le32 did; + __le32 rid; + __le32 cfgs1; + __le32 cfgs2; + __le32 cmd; + __le32 sts; + __le32 state; + __le32 ien; + __le32 ivect; + __le32 tmr; + __le32 simulate; + __le32 adpbc_sts; + __le32 adp_ramp_time; + __le32 adpbc_ctrl1; + __le32 adpbc_ctrl2; + __le32 override; + __le32 vbusvalid_dbnc_cfg; + __le32 sessvalid_dbnc_cfg; + __le32 susp_timing_ctrl; +}; + +#define OTG_CDNSP_DID 0x0004034E + /* - * Common registers interface for both version of DRD. + * Common registers interface for both CDNS3 and CDNSP version of DRD. */ struct cdns3_otg_common_regs { __le32 cmd; __le32 sts; __le32 state; - __le32 different1; +}; + +/* + * Interrupt related registers. This registers are mapped in different + * location for CDNSP controller. + */ +struct cdns3_otg_irq_regs { __le32 ien; __le32 ivect; }; @@ -92,9 +123,9 @@ struct cdns3_otg_common_regs { #define OTGCMD_DEV_BUS_DROP BIT(8) /* Drop the bus for Host mode*/ #define OTGCMD_HOST_BUS_DROP BIT(9) -/* Power Down USBSS-DEV. */ +/* Power Down USBSS-DEV - only for CDNS3.*/ #define OTGCMD_DEV_POWER_OFF BIT(11) -/* Power Down CDNSXHCI. */ +/* Power Down CDNSXHCI - only for CDNS3. */ #define OTGCMD_HOST_POWER_OFF BIT(12) /* OTGIEN - bitmasks */ @@ -123,20 +154,31 @@ struct cdns3_otg_common_regs { #define OTGSTS_OTG_NRDY_MASK BIT(11) #define OTGSTS_OTG_NRDY(p) ((p) & OTGSTS_OTG_NRDY_MASK) /* - * Value of the strap pins. + * Value of the strap pins for: + * CDNS3: * 000 - no default configuration * 010 - Controller initiall configured as Host * 100 - Controller initially configured as Device + * CDNSP: + * 000 - No default configuration. + * 010 - Controller initiall configured as Host. + * 100 - Controller initially configured as Device. */ #define OTGSTS_STRAP(p) (((p) & GENMASK(14, 12)) >> 12) #define OTGSTS_STRAP_NO_DEFAULT_CFG 0x00 #define OTGSTS_STRAP_HOST_OTG 0x01 #define OTGSTS_STRAP_HOST 0x02 #define OTGSTS_STRAP_GADGET 0x04 +#define OTGSTS_CDNSP_STRAP_HOST 0x01 +#define OTGSTS_CDNSP_STRAP_GADGET 0x02 + /* Host mode is turned on. */ -#define OTGSTS_XHCI_READY BIT(26) +#define OTGSTS_CDNS3_XHCI_READY BIT(26) +#define OTGSTS_CDNSP_XHCI_READY BIT(27) + /* "Device mode is turned on .*/ -#define OTGSTS_DEV_READY BIT(27) +#define OTGSTS_CDNS3_DEV_READY BIT(27) +#define OTGSTS_CDNSP_DEV_READY BIT(26) /* OTGSTATE- bitmasks */ #define OTGSTATE_DEV_STATE_MASK GENMASK(2, 0) @@ -152,6 +194,8 @@ struct cdns3_otg_common_regs { #define OVERRIDE_IDPULLUP BIT(0) /* Only for CDNS3_CONTROLLER_V0 version */ #define OVERRIDE_IDPULLUP_V0 BIT(24) +/* Vbusvalid/Sesvalid override select. */ +#define OVERRIDE_SESS_VLD_SEL BIT(10) /* PHYRST_CFG - bitmasks */ #define PHYRST_CFG_PHYRST_A_ENABLE BIT(0) @@ -170,6 +214,5 @@ int cdns3_drd_gadget_on(struct cdns3 *cdns); void cdns3_drd_gadget_off(struct cdns3 *cdns); int cdns3_drd_host_on(struct cdns3 *cdns); void cdns3_drd_host_off(struct cdns3 *cdns); -int cdns3_set_mode(struct cdns3 *cdns, enum usb_dr_mode mode); #endif /* __LINUX_CDNS3_DRD */ diff --git a/drivers/usb/chipidea/otg_fsm.c b/drivers/usb/chipidea/otg_fsm.c index 6ed4b00dba961d7e63c70da520a9922344be206a..7a2a9559693fb49eea923f19f2faf8106c345510 100644 --- a/drivers/usb/chipidea/otg_fsm.c +++ b/drivers/usb/chipidea/otg_fsm.c @@ -256,8 +256,10 @@ static void ci_otg_del_timer(struct ci_hdrc *ci, enum otg_fsm_timer t) ci->enabled_otg_timer_bits &= ~(1 << t); if (ci->next_otg_timer == t) { if (ci->enabled_otg_timer_bits == 0) { + spin_unlock_irqrestore(&ci->lock, flags); /* No enabled timers after delete it */ hrtimer_cancel(&ci->otg_fsm_hrtimer); + spin_lock_irqsave(&ci->lock, flags); ci->next_otg_timer = NUM_OTG_FSM_TIMERS; } else { /* Find the next timer */ diff --git a/drivers/usb/common/debug.c b/drivers/usb/common/debug.c index a76a086b9c548e4295b1eddf96fef4c73d0ee656..f0c0e8db70388054d92342eba83c1a483dcd72e4 100644 --- a/drivers/usb/common/debug.c +++ b/drivers/usb/common/debug.c @@ -207,30 +207,28 @@ static void usb_decode_set_isoch_delay(__u8 wValue, char *str, size_t size) snprintf(str, size, "Set Isochronous Delay(Delay = %d ns)", wValue); } -/** - * usb_decode_ctrl - Returns human readable representation of control request. - * @str: buffer to return a human-readable representation of control request. - * This buffer should have about 200 bytes. - * @size: size of str buffer. - * @bRequestType: matches the USB bmRequestType field - * @bRequest: matches the USB bRequest field - * @wValue: matches the USB wValue field (CPU byte order) - * @wIndex: matches the USB wIndex field (CPU byte order) - * @wLength: matches the USB wLength field (CPU byte order) - * - * Function returns decoded, formatted and human-readable description of - * control request packet. - * - * The usage scenario for this is for tracepoints, so function as a return - * use the same value as in parameters. This approach allows to use this - * function in TP_printk - * - * Important: wValue, wIndex, wLength parameters before invoking this function - * should be processed by le16_to_cpu macro. - */ -const char *usb_decode_ctrl(char *str, size_t size, __u8 bRequestType, - __u8 bRequest, __u16 wValue, __u16 wIndex, - __u16 wLength) +static void usb_decode_ctrl_generic(char *str, size_t size, __u8 bRequestType, + __u8 bRequest, __u16 wValue, __u16 wIndex, + __u16 wLength) +{ + u8 recip = bRequestType & USB_RECIP_MASK; + u8 type = bRequestType & USB_TYPE_MASK; + + snprintf(str, size, + "Type=%s Recipient=%s Dir=%s bRequest=%u wValue=%u wIndex=%u wLength=%u", + (type == USB_TYPE_STANDARD) ? "Standard" : + (type == USB_TYPE_VENDOR) ? "Vendor" : + (type == USB_TYPE_CLASS) ? "Class" : "Unknown", + (recip == USB_RECIP_DEVICE) ? "Device" : + (recip == USB_RECIP_INTERFACE) ? "Interface" : + (recip == USB_RECIP_ENDPOINT) ? "Endpoint" : "Unknown", + (bRequestType & USB_DIR_IN) ? "IN" : "OUT", + bRequest, wValue, wIndex, wLength); +} + +static void usb_decode_ctrl_standard(char *str, size_t size, __u8 bRequestType, + __u8 bRequest, __u16 wValue, __u16 wIndex, + __u16 wLength) { switch (bRequest) { case USB_REQ_GET_STATUS: @@ -271,14 +269,48 @@ const char *usb_decode_ctrl(char *str, size_t size, __u8 bRequestType, usb_decode_set_isoch_delay(wValue, str, size); break; default: - snprintf(str, size, "%02x %02x %02x %02x %02x %02x %02x %02x", - bRequestType, bRequest, - (u8)(cpu_to_le16(wValue) & 0xff), - (u8)(cpu_to_le16(wValue) >> 8), - (u8)(cpu_to_le16(wIndex) & 0xff), - (u8)(cpu_to_le16(wIndex) >> 8), - (u8)(cpu_to_le16(wLength) & 0xff), - (u8)(cpu_to_le16(wLength) >> 8)); + usb_decode_ctrl_generic(str, size, bRequestType, bRequest, + wValue, wIndex, wLength); + break; + } +} + +/** + * usb_decode_ctrl - Returns human readable representation of control request. + * @str: buffer to return a human-readable representation of control request. + * This buffer should have about 200 bytes. + * @size: size of str buffer. + * @bRequestType: matches the USB bmRequestType field + * @bRequest: matches the USB bRequest field + * @wValue: matches the USB wValue field (CPU byte order) + * @wIndex: matches the USB wIndex field (CPU byte order) + * @wLength: matches the USB wLength field (CPU byte order) + * + * Function returns decoded, formatted and human-readable description of + * control request packet. + * + * The usage scenario for this is for tracepoints, so function as a return + * use the same value as in parameters. This approach allows to use this + * function in TP_printk + * + * Important: wValue, wIndex, wLength parameters before invoking this function + * should be processed by le16_to_cpu macro. + */ +const char *usb_decode_ctrl(char *str, size_t size, __u8 bRequestType, + __u8 bRequest, __u16 wValue, __u16 wIndex, + __u16 wLength) +{ + switch (bRequestType & USB_TYPE_MASK) { + case USB_TYPE_STANDARD: + usb_decode_ctrl_standard(str, size, bRequestType, bRequest, + wValue, wIndex, wLength); + break; + case USB_TYPE_VENDOR: + case USB_TYPE_CLASS: + default: + usb_decode_ctrl_generic(str, size, bRequestType, bRequest, + wValue, wIndex, wLength); + break; } return str; diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c index f03ee889ecc7056d50978cdf03804adf83853e21..6d24d138cc77e8567013cf4b4b91bf7f04444610 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -362,6 +362,9 @@ static const struct usb_device_id usb_quirk_list[] = { { USB_DEVICE(0x0781, 0x5583), .driver_info = USB_QUIRK_NO_LPM }, { USB_DEVICE(0x0781, 0x5591), .driver_info = USB_QUIRK_NO_LPM }, + /* Realforce 87U Keyboard */ + { USB_DEVICE(0x0853, 0x011b), .driver_info = USB_QUIRK_NO_LPM }, + /* M-Systems Flash Disk Pioneers */ { USB_DEVICE(0x08ec, 0x1000), .driver_info = USB_QUIRK_RESET_RESUME }, @@ -388,6 +391,15 @@ static const struct usb_device_id usb_quirk_list[] = { /* Kingston DataTraveler 3.0 */ { USB_DEVICE(0x0951, 0x1666), .driver_info = USB_QUIRK_NO_LPM }, + /* NVIDIA Jetson devices in Force Recovery mode */ + { USB_DEVICE(0x0955, 0x7018), .driver_info = USB_QUIRK_RESET_RESUME }, + { USB_DEVICE(0x0955, 0x7019), .driver_info = USB_QUIRK_RESET_RESUME }, + { USB_DEVICE(0x0955, 0x7418), .driver_info = USB_QUIRK_RESET_RESUME }, + { USB_DEVICE(0x0955, 0x7721), .driver_info = USB_QUIRK_RESET_RESUME }, + { USB_DEVICE(0x0955, 0x7c18), .driver_info = USB_QUIRK_RESET_RESUME }, + { USB_DEVICE(0x0955, 0x7e19), .driver_info = USB_QUIRK_RESET_RESUME }, + { USB_DEVICE(0x0955, 0x7f21), .driver_info = USB_QUIRK_RESET_RESUME }, + /* X-Rite/Gretag-Macbeth Eye-One Pro display colorimeter */ { USB_DEVICE(0x0971, 0x2000), .driver_info = USB_QUIRK_NO_SET_INTF }, @@ -438,6 +450,10 @@ static const struct usb_device_id usb_quirk_list[] = { { USB_DEVICE(0x1532, 0x0116), .driver_info = USB_QUIRK_LINEAR_UFRAME_INTR_BINTERVAL }, + /* Lenovo ThinkPad OneLink+ Dock twin hub controllers (VIA Labs VL812) */ + { USB_DEVICE(0x17ef, 0x1018), .driver_info = USB_QUIRK_RESET_RESUME }, + { USB_DEVICE(0x17ef, 0x1019), .driver_info = USB_QUIRK_RESET_RESUME }, + /* Lenovo USB-C to Ethernet Adapter RTL8153-04 */ { USB_DEVICE(0x17ef, 0x720c), .driver_info = USB_QUIRK_NO_LPM }, diff --git a/drivers/usb/dwc3/dwc3-exynos.c b/drivers/usb/dwc3/dwc3-exynos.c index 90bb022737da8ef4e540ee1a713ed3ac3acdd8e2..ee7b71827216c6ce5f39389e6c458736c7304ddb 100644 --- a/drivers/usb/dwc3/dwc3-exynos.c +++ b/drivers/usb/dwc3/dwc3-exynos.c @@ -37,15 +37,6 @@ struct dwc3_exynos { struct regulator *vdd10; }; -static int dwc3_exynos_remove_child(struct device *dev, void *unused) -{ - struct platform_device *pdev = to_platform_device(dev); - - platform_device_unregister(pdev); - - return 0; -} - static int dwc3_exynos_probe(struct platform_device *pdev) { struct dwc3_exynos *exynos; @@ -142,7 +133,7 @@ static int dwc3_exynos_remove(struct platform_device *pdev) struct dwc3_exynos *exynos = platform_get_drvdata(pdev); int i; - device_for_each_child(&pdev->dev, NULL, dwc3_exynos_remove_child); + of_platform_depopulate(&pdev->dev); for (i = exynos->num_clks - 1; i >= 0; i--) clk_disable_unprepare(exynos->clks[i]); diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 77a5a0a3760de4989a649d67f4f55f046b909ba5..1cd5ed0cdde34fd8cc582434c306e85d50353014 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -949,7 +949,7 @@ out: return 0; } -static void dwc3_remove_requests(struct dwc3 *dwc, struct dwc3_ep *dep) +static void dwc3_remove_requests(struct dwc3 *dwc, struct dwc3_ep *dep, int status) { struct dwc3_request *req; @@ -959,19 +959,19 @@ static void dwc3_remove_requests(struct dwc3 *dwc, struct dwc3_ep *dep) while (!list_empty(&dep->started_list)) { req = next_request(&dep->started_list); - dwc3_gadget_giveback(dep, req, -ESHUTDOWN); + dwc3_gadget_giveback(dep, req, status); } while (!list_empty(&dep->pending_list)) { req = next_request(&dep->pending_list); - dwc3_gadget_giveback(dep, req, -ESHUTDOWN); + dwc3_gadget_giveback(dep, req, status); } while (!list_empty(&dep->cancelled_list)) { req = next_request(&dep->cancelled_list); - dwc3_gadget_giveback(dep, req, -ESHUTDOWN); + dwc3_gadget_giveback(dep, req, status); } } @@ -1000,18 +1000,18 @@ static int __dwc3_gadget_ep_disable(struct dwc3_ep *dep) reg &= ~DWC3_DALEPENA_EP(dep->number); dwc3_writel(dwc->regs, DWC3_DALEPENA, reg); + dwc3_remove_requests(dwc, dep, -ESHUTDOWN); + + dep->stream_capable = false; + dep->type = 0; + dep->flags &= DWC3_EP_TXFIFO_RESIZED; + /* Clear out the ep descriptors for non-ep0 */ if (dep->number > 1) { dep->endpoint.comp_desc = NULL; dep->endpoint.desc = NULL; } - dwc3_remove_requests(dwc, dep); - - dep->stream_capable = false; - dep->type = 0; - dep->flags &= DWC3_EP_TXFIFO_RESIZED; - return 0; } @@ -1261,8 +1261,8 @@ static void dwc3_prepare_one_trb(struct dwc3_ep *dep, trb->ctrl = DWC3_TRBCTL_ISOCHRONOUS; } - /* always enable Interrupt on Missed ISOC */ - trb->ctrl |= DWC3_TRB_CTRL_ISP_IMI; + if (!no_interrupt && !chain) + trb->ctrl |= DWC3_TRB_CTRL_ISP_IMI; break; case USB_ENDPOINT_XFER_BULK: @@ -2276,7 +2276,7 @@ static void dwc3_stop_active_transfers(struct dwc3 *dwc) if (!dep) continue; - dwc3_remove_requests(dwc, dep); + dwc3_remove_requests(dwc, dep, -ESHUTDOWN); } } @@ -3151,6 +3151,10 @@ static int dwc3_gadget_ep_reclaim_completed_trb(struct dwc3_ep *dep, if (event->status & DEPEVT_STATUS_SHORT && !chain) return 1; + if ((trb->ctrl & DWC3_TRB_CTRL_ISP_IMI) && + DWC3_TRB_SIZE_TRBSTS(trb->size) == DWC3_TRBSTS_MISSED_ISOC) + return 1; + if ((trb->ctrl & DWC3_TRB_CTRL_IOC) || (trb->ctrl & DWC3_TRB_CTRL_LST)) return 1; diff --git a/drivers/usb/dwc3/host.c b/drivers/usb/dwc3/host.c index 86bc2bec9038d9c9280e4ad9c10a135223548f5d..b06ab85f8187ef152c5e49ad6508175096439290 100644 --- a/drivers/usb/dwc3/host.c +++ b/drivers/usb/dwc3/host.c @@ -10,13 +10,8 @@ #include #include -#include "../host/xhci-plat.h" #include "core.h" -static const struct xhci_plat_priv dwc3_xhci_plat_priv = { - .quirks = XHCI_SKIP_PHY_INIT, -}; - static int dwc3_host_get_irq(struct dwc3 *dwc) { struct platform_device *dwc3_pdev = to_platform_device(dwc->dev); @@ -92,11 +87,6 @@ int dwc3_host_init(struct dwc3 *dwc) goto err; } - ret = platform_device_add_data(xhci, &dwc3_xhci_plat_priv, - sizeof(dwc3_xhci_plat_priv)); - if (ret) - goto err; - memset(props, 0, sizeof(struct property_entry) * ARRAY_SIZE(props)); if (dwc->usb3_lpm_capable) diff --git a/drivers/usb/gadget/function/f_printer.c b/drivers/usb/gadget/function/f_printer.c index 61bbf27b5203740b62fbf3aa96cb6a42c462dbb1..939f174a956c2b85e0731b2918b2bac0ffe271d4 100644 --- a/drivers/usb/gadget/function/f_printer.c +++ b/drivers/usb/gadget/function/f_printer.c @@ -89,7 +89,7 @@ struct printer_dev { u8 printer_cdev_open; wait_queue_head_t wait; unsigned q_len; - char *pnp_string; /* We don't own memory! */ + char **pnp_string; /* We don't own memory! */ struct usb_function function; }; @@ -1001,16 +1001,16 @@ static int printer_func_setup(struct usb_function *f, if ((wIndex>>8) != dev->interface) break; - if (!dev->pnp_string) { + if (!*dev->pnp_string) { value = 0; break; } - value = strlen(dev->pnp_string); + value = strlen(*dev->pnp_string); buf[0] = (value >> 8) & 0xFF; buf[1] = value & 0xFF; - memcpy(buf + 2, dev->pnp_string, value); + memcpy(buf + 2, *dev->pnp_string, value); DBG(dev, "1284 PNP String: %x %s\n", value, - dev->pnp_string); + *dev->pnp_string); break; case GET_PORT_STATUS: /* Get Port Status */ @@ -1476,7 +1476,7 @@ static struct usb_function *gprinter_alloc(struct usb_function_instance *fi) kref_init(&dev->kref); ++opts->refcnt; dev->minor = opts->minor; - dev->pnp_string = opts->pnp_string; + dev->pnp_string = &opts->pnp_string; dev->q_len = opts->q_len; mutex_unlock(&opts->lock); diff --git a/drivers/usb/gadget/udc/bdc/bdc_udc.c b/drivers/usb/gadget/udc/bdc/bdc_udc.c index 248426a3e88a7447a9f8eb605f543f92dbd1ef58..5f0b3fd9363196d1518de101f400d681b43f4b28 100644 --- a/drivers/usb/gadget/udc/bdc/bdc_udc.c +++ b/drivers/usb/gadget/udc/bdc/bdc_udc.c @@ -151,6 +151,7 @@ static void bdc_uspc_disconnected(struct bdc *bdc, bool reinit) bdc->delayed_status = false; bdc->reinit = reinit; bdc->test_mode = false; + usb_gadget_set_state(&bdc->gadget, USB_STATE_NOTATTACHED); } /* TNotify wkaeup timer */ diff --git a/drivers/usb/host/bcma-hcd.c b/drivers/usb/host/bcma-hcd.c index 2df52f75f6b3c7e0b947025660a051cda475ae48..7558cc4d90cc66bd23f9c17997b6cc5d3ca9bad9 100644 --- a/drivers/usb/host/bcma-hcd.c +++ b/drivers/usb/host/bcma-hcd.c @@ -285,7 +285,7 @@ static void bcma_hci_platform_power_gpio(struct bcma_device *dev, bool val) { struct bcma_hcd_device *usb_dev = bcma_get_drvdata(dev); - if (IS_ERR_OR_NULL(usb_dev->gpio_desc)) + if (!usb_dev->gpio_desc) return; gpiod_set_value(usb_dev->gpio_desc, val); @@ -406,9 +406,11 @@ static int bcma_hcd_probe(struct bcma_device *core) return -ENOMEM; usb_dev->core = core; - if (core->dev.of_node) - usb_dev->gpio_desc = devm_gpiod_get(&core->dev, "vcc", - GPIOD_OUT_HIGH); + usb_dev->gpio_desc = devm_gpiod_get_optional(&core->dev, "vcc", + GPIOD_OUT_HIGH); + if (IS_ERR(usb_dev->gpio_desc)) + return dev_err_probe(&core->dev, PTR_ERR(usb_dev->gpio_desc), + "error obtaining VCC GPIO"); switch (core->id.id) { case BCMA_CORE_USB20_HOST: diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c index 2a7ccc0035a5e772d1c49019f956276c01fcb5a7..313ff8451448c0082433ce3a70c775cc9c4f3dc8 100644 --- a/drivers/usb/host/xhci-mem.c +++ b/drivers/usb/host/xhci-mem.c @@ -714,7 +714,7 @@ struct xhci_stream_info *xhci_alloc_stream_info(struct xhci_hcd *xhci, num_stream_ctxs, &stream_info->ctx_array_dma, mem_flags); if (!stream_info->stream_ctx_array) - goto cleanup_ctx; + goto cleanup_ring_array; memset(stream_info->stream_ctx_array, 0, sizeof(struct xhci_stream_ctx)*num_stream_ctxs); @@ -775,6 +775,11 @@ cleanup_rings: } xhci_free_command(xhci, stream_info->free_streams_command); cleanup_ctx: + xhci_free_stream_ctx(xhci, + stream_info->num_stream_ctxs, + stream_info->stream_ctx_array, + stream_info->ctx_array_dma); +cleanup_ring_array: kfree(stream_info->stream_rings); cleanup_info: kfree(stream_info); @@ -965,15 +970,19 @@ void xhci_free_virt_device(struct xhci_hcd *xhci, int slot_id) if (dev->eps[i].stream_info) xhci_free_stream_info(xhci, dev->eps[i].stream_info); - /* Endpoints on the TT/root port lists should have been removed - * when usb_disable_device() was called for the device. - * We can't drop them anyway, because the udev might have gone - * away by this point, and we can't tell what speed it was. + /* + * Endpoints are normally deleted from the bandwidth list when + * endpoints are dropped, before device is freed. + * If host is dying or being removed then endpoints aren't + * dropped cleanly, so delete the endpoint from list here. + * Only applicable for hosts with software bandwidth checking. */ - if (!list_empty(&dev->eps[i].bw_endpoint_list)) - xhci_warn(xhci, "Slot %u endpoint %u " - "not removed from BW list!\n", - slot_id, i); + + if (!list_empty(&dev->eps[i].bw_endpoint_list)) { + list_del_init(&dev->eps[i].bw_endpoint_list); + xhci_dbg(xhci, "Slot %u endpoint %u not removed from BW list!\n", + slot_id, i); + } } /* If this is a hub, free the TT(s) from the TT list */ xhci_free_tt_info(xhci, dev, slot_id); diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index 8952492d43be633d18bfb7f22f106828c80738df..9168b492c02b7356d6d09bad56b8e205aae36c61 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -58,24 +58,13 @@ #define PCI_DEVICE_ID_INTEL_CML_XHCI 0xa3af #define PCI_DEVICE_ID_INTEL_TIGER_LAKE_XHCI 0x9a13 #define PCI_DEVICE_ID_INTEL_MAPLE_RIDGE_XHCI 0x1138 -#define PCI_DEVICE_ID_INTEL_ALDER_LAKE_XHCI 0x461e -#define PCI_DEVICE_ID_INTEL_ALDER_LAKE_N_XHCI 0x464e -#define PCI_DEVICE_ID_INTEL_ALDER_LAKE_PCH_XHCI 0x51ed -#define PCI_DEVICE_ID_INTEL_RAPTOR_LAKE_XHCI 0xa71e -#define PCI_DEVICE_ID_INTEL_METEOR_LAKE_XHCI 0x7ec0 +#define PCI_DEVICE_ID_INTEL_ALDER_LAKE_PCH_XHCI 0x51ed +#define PCI_DEVICE_ID_INTEL_ALDER_LAKE_N_PCH_XHCI 0x54ed #define PCI_DEVICE_ID_AMD_PROMONTORYA_4 0x43b9 #define PCI_DEVICE_ID_AMD_PROMONTORYA_3 0x43ba #define PCI_DEVICE_ID_AMD_PROMONTORYA_2 0x43bb #define PCI_DEVICE_ID_AMD_PROMONTORYA_1 0x43bc -#define PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_1 0x161a -#define PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_2 0x161b -#define PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_3 0x161d -#define PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_4 0x161e -#define PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_5 0x15d6 -#define PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_6 0x15d7 -#define PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_7 0x161c -#define PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_8 0x161f #define PCI_DEVICE_ID_ASMEDIA_1042_XHCI 0x1042 #define PCI_DEVICE_ID_ASMEDIA_1042A_XHCI 0x1142 @@ -253,6 +242,11 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) pdev->device == PCI_DEVICE_ID_INTEL_DNV_XHCI)) xhci->quirks |= XHCI_MISSING_CAS; + if (pdev->vendor == PCI_VENDOR_ID_INTEL && + (pdev->device == PCI_DEVICE_ID_INTEL_ALDER_LAKE_PCH_XHCI || + pdev->device == PCI_DEVICE_ID_INTEL_ALDER_LAKE_N_PCH_XHCI)) + xhci->quirks |= XHCI_RESET_TO_DEFAULT; + if (pdev->vendor == PCI_VENDOR_ID_INTEL && (pdev->device == PCI_DEVICE_ID_INTEL_ALPINE_RIDGE_2C_XHCI || pdev->device == PCI_DEVICE_ID_INTEL_ALPINE_RIDGE_4C_XHCI || @@ -264,12 +258,7 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) pdev->device == PCI_DEVICE_ID_INTEL_TITAN_RIDGE_DD_XHCI || pdev->device == PCI_DEVICE_ID_INTEL_ICE_LAKE_XHCI || pdev->device == PCI_DEVICE_ID_INTEL_TIGER_LAKE_XHCI || - pdev->device == PCI_DEVICE_ID_INTEL_MAPLE_RIDGE_XHCI || - pdev->device == PCI_DEVICE_ID_INTEL_ALDER_LAKE_XHCI || - pdev->device == PCI_DEVICE_ID_INTEL_ALDER_LAKE_N_XHCI || - pdev->device == PCI_DEVICE_ID_INTEL_ALDER_LAKE_PCH_XHCI || - pdev->device == PCI_DEVICE_ID_INTEL_RAPTOR_LAKE_XHCI || - pdev->device == PCI_DEVICE_ID_INTEL_METEOR_LAKE_XHCI)) + pdev->device == PCI_DEVICE_ID_INTEL_MAPLE_RIDGE_XHCI)) xhci->quirks |= XHCI_DEFAULT_PM_RUNTIME_ALLOW; if (pdev->vendor == PCI_VENDOR_ID_ETRON && @@ -302,8 +291,14 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) } if (pdev->vendor == PCI_VENDOR_ID_ASMEDIA && - pdev->device == PCI_DEVICE_ID_ASMEDIA_1042_XHCI) + pdev->device == PCI_DEVICE_ID_ASMEDIA_1042_XHCI) { + /* + * try to tame the ASMedia 1042 controller which reports 0.96 + * but appears to behave more like 1.0 + */ + xhci->quirks |= XHCI_SPURIOUS_SUCCESS; xhci->quirks |= XHCI_BROKEN_STREAMS; + } if (pdev->vendor == PCI_VENDOR_ID_ASMEDIA && pdev->device == PCI_DEVICE_ID_ASMEDIA_1042A_XHCI) { xhci->quirks |= XHCI_TRUST_TX_LENGTH; @@ -332,15 +327,8 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) pdev->device == PCI_DEVICE_ID_AMD_PROMONTORYA_4)) xhci->quirks |= XHCI_NO_SOFT_RETRY; - if (pdev->vendor == PCI_VENDOR_ID_AMD && - (pdev->device == PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_1 || - pdev->device == PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_2 || - pdev->device == PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_3 || - pdev->device == PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_4 || - pdev->device == PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_5 || - pdev->device == PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_6 || - pdev->device == PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_7 || - pdev->device == PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_8)) + /* xHC spec requires PCI devices to support D3hot and D3cold */ + if (xhci->hci_version >= 0x120) xhci->quirks |= XHCI_DEFAULT_PM_RUNTIME_ALLOW; if (xhci->quirks & XHCI_RESET_ON_RESUME) diff --git a/drivers/usb/host/xhci-plat.c b/drivers/usb/host/xhci-plat.c index 01dcfd77494f948069e115c89c7850b6e092a80a..045383d384700636c836eed7995c81e42b69709d 100644 --- a/drivers/usb/host/xhci-plat.c +++ b/drivers/usb/host/xhci-plat.c @@ -134,7 +134,7 @@ static const struct xhci_plat_priv xhci_plat_renesas_rcar_gen3 = { }; static const struct xhci_plat_priv xhci_plat_brcm = { - .quirks = XHCI_RESET_ON_RESUME, + .quirks = XHCI_RESET_ON_RESUME | XHCI_SUSPEND_RESUME_CLKS, }; static const struct of_device_id usb_xhci_of_match[] = { @@ -488,7 +488,16 @@ static int __maybe_unused xhci_plat_suspend(struct device *dev) * xhci_suspend() needs `do_wakeup` to know whether host is allowed * to do wakeup during suspend. */ - return xhci_suspend(xhci, device_may_wakeup(dev)); + ret = xhci_suspend(xhci, device_may_wakeup(dev)); + if (ret) + return ret; + + if (!device_may_wakeup(dev) && (xhci->quirks & XHCI_SUSPEND_RESUME_CLKS)) { + clk_disable_unprepare(xhci->clk); + clk_disable_unprepare(xhci->reg_clk); + } + + return 0; } static int __maybe_unused xhci_plat_resume(struct device *dev) @@ -497,6 +506,11 @@ static int __maybe_unused xhci_plat_resume(struct device *dev) struct xhci_hcd *xhci = hcd_to_xhci(hcd); int ret; + if (!device_may_wakeup(dev) && (xhci->quirks & XHCI_SUSPEND_RESUME_CLKS)) { + clk_prepare_enable(xhci->clk); + clk_prepare_enable(xhci->reg_clk); + } + ret = xhci_priv_resume_quirk(hcd); if (ret) return ret; diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index 6f5e131a097f562bd71021da5f09c7664f56dfa0..b1f472f23a8825232acd73a6591e295b2d43ad14 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -791,9 +791,15 @@ void xhci_shutdown(struct usb_hcd *hcd) spin_lock_irq(&xhci->lock); xhci_halt(xhci); - /* Workaround for spurious wakeups at shutdown with HSW */ - if (xhci->quirks & XHCI_SPURIOUS_WAKEUP) + + /* + * Workaround for spurious wakeps at shutdown with HSW, and for boot + * firmware delay in ADL-P PCH if port are left in U3 at shutdown + */ + if (xhci->quirks & XHCI_SPURIOUS_WAKEUP || + xhci->quirks & XHCI_RESET_TO_DEFAULT) xhci_reset(xhci, XHCI_RESET_SHORT_USEC); + spin_unlock_irq(&xhci->lock); xhci_cleanup_msix(xhci); @@ -1160,7 +1166,8 @@ int xhci_resume(struct xhci_hcd *xhci, bool hibernated) /* re-initialize the HC on Restore Error, or Host Controller Error */ if (temp & (STS_SRE | STS_HCE)) { reinit_xhc = true; - xhci_warn(xhci, "xHC error in resume, USBSTS 0x%x, Reinit\n", temp); + if (!xhci->broken_suspend) + xhci_warn(xhci, "xHC error in resume, USBSTS 0x%x, Reinit\n", temp); } if (reinit_xhc) { diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index 373752e8f10f5e6267fcc183e8492894cdf14577..782cee6d5e7e9f30db79cbfd8c06db27e7527de2 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -1906,6 +1906,8 @@ struct xhci_hcd { #define XHCI_SG_TRB_CACHE_SIZE_QUIRK BIT_ULL(39) #define XHCI_NO_SOFT_RETRY BIT_ULL(40) #define XHCI_EP_CTX_BROKEN_DCS BIT_ULL(42) +#define XHCI_SUSPEND_RESUME_CLKS BIT_ULL(43) +#define XHCI_RESET_TO_DEFAULT BIT_ULL(44) unsigned int num_active_eps; unsigned int limit_active_eps; diff --git a/drivers/usb/misc/idmouse.c b/drivers/usb/misc/idmouse.c index e9437a176518a5f137a4df32d393b483e6d3b23c..ea39243efee396ea4ebb62c69f4bb1fabe9dad72 100644 --- a/drivers/usb/misc/idmouse.c +++ b/drivers/usb/misc/idmouse.c @@ -177,10 +177,6 @@ static int idmouse_create_image(struct usb_idmouse *dev) bytes_read += bulk_read; } - /* reset the device */ -reset: - ftip_command(dev, FTIP_RELEASE, 0, 0); - /* check for valid image */ /* right border should be black (0x00) */ for (bytes_read = sizeof(HEADER)-1 + WIDTH-1; bytes_read < IMGSIZE; bytes_read += WIDTH) @@ -192,6 +188,10 @@ reset: if (dev->bulk_in_buffer[bytes_read] != 0xFF) return -EAGAIN; + /* reset the device */ +reset: + ftip_command(dev, FTIP_RELEASE, 0, 0); + /* should be IMGSIZE == 65040 */ dev_dbg(&dev->interface->dev, "read %d bytes fingerprint data\n", bytes_read); diff --git a/drivers/usb/musb/musb_gadget.c b/drivers/usb/musb/musb_gadget.c index fb806b33178a03c5020bb3c026686f739103cf5e..c273eee35aaa71a16fcd43594558477946e0820f 100644 --- a/drivers/usb/musb/musb_gadget.c +++ b/drivers/usb/musb/musb_gadget.c @@ -760,6 +760,9 @@ static void rxstate(struct musb *musb, struct musb_request *req) musb_writew(epio, MUSB_RXCSR, csr); buffer_aint_mapped: + fifo_count = min_t(unsigned int, + request->length - request->actual, + (unsigned int)fifo_count); musb_read_fifo(musb_ep->hw_ep, fifo_count, (u8 *) (request->buf + request->actual)); request->actual += fifo_count; diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c index 6b5ba6180c307e9f72ff6e2d45808394da917ea2..8a4a0d4dbc139eb3a324f9a1d594ed16bd118d16 100644 --- a/drivers/usb/serial/cp210x.c +++ b/drivers/usb/serial/cp210x.c @@ -199,6 +199,8 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x16DC, 0x0015) }, /* W-IE-NE-R Plein & Baus GmbH CML Control, Monitoring and Data Logger */ { USB_DEVICE(0x17A8, 0x0001) }, /* Kamstrup Optical Eye/3-wire */ { USB_DEVICE(0x17A8, 0x0005) }, /* Kamstrup M-Bus Master MultiPort 250D */ + { USB_DEVICE(0x17A8, 0x0011) }, /* Kamstrup 444 MHz RF sniffer */ + { USB_DEVICE(0x17A8, 0x0013) }, /* Kamstrup 870 MHz RF sniffer */ { USB_DEVICE(0x17A8, 0x0101) }, /* Kamstrup 868 MHz wM-Bus C-Mode Meter Reader (Int Ant) */ { USB_DEVICE(0x17A8, 0x0102) }, /* Kamstrup 868 MHz wM-Bus C-Mode Meter Reader (Ext Ant) */ { USB_DEVICE(0x17F4, 0xAAAA) }, /* Wavesense Jazz blood glucose meter */ diff --git a/drivers/usb/serial/f81232.c b/drivers/usb/serial/f81232.c index 0c7eacc630e0ec6da40c8e6c83296007cda125d0..11fe49543f26afa99e2e9c3e492bb75045bd21ef 100644 --- a/drivers/usb/serial/f81232.c +++ b/drivers/usb/serial/f81232.c @@ -130,9 +130,6 @@ static u8 const clock_table[] = { F81232_CLK_1_846_MHZ, F81232_CLK_14_77_MHZ, static int calc_baud_divisor(speed_t baudrate, speed_t clockrate) { - if (!baudrate) - return 0; - return DIV_ROUND_CLOSEST(clockrate, baudrate); } @@ -523,9 +520,14 @@ static void f81232_set_baudrate(struct tty_struct *tty, speed_t baud_list[] = { baudrate, old_baudrate, F81232_DEF_BAUDRATE }; for (i = 0; i < ARRAY_SIZE(baud_list); ++i) { - idx = f81232_find_clk(baud_list[i]); + baudrate = baud_list[i]; + if (baudrate == 0) { + tty_encode_baud_rate(tty, 0, 0); + return; + } + + idx = f81232_find_clk(baudrate); if (idx >= 0) { - baudrate = baud_list[i]; tty_encode_baud_rate(tty, baudrate, baudrate); break; } diff --git a/drivers/usb/serial/f81534.c b/drivers/usb/serial/f81534.c index 5661fd03e5456aea43c8fc80e441b910a6b51a7c..e952be683c63ab86efc81f9561087ee04fea580f 100644 --- a/drivers/usb/serial/f81534.c +++ b/drivers/usb/serial/f81534.c @@ -538,9 +538,6 @@ static int f81534_submit_writer(struct usb_serial_port *port, gfp_t mem_flags) static u32 f81534_calc_baud_divisor(u32 baudrate, u32 clockrate) { - if (!baudrate) - return 0; - /* Round to nearest divisor */ return DIV_ROUND_CLOSEST(clockrate, baudrate); } @@ -570,9 +567,14 @@ static int f81534_set_port_config(struct usb_serial_port *port, u32 baud_list[] = {baudrate, old_baudrate, F81534_DEFAULT_BAUD_RATE}; for (i = 0; i < ARRAY_SIZE(baud_list); ++i) { - idx = f81534_find_clk(baud_list[i]); + baudrate = baud_list[i]; + if (baudrate == 0) { + tty_encode_baud_rate(tty, 0, 0); + return 0; + } + + idx = f81534_find_clk(baudrate); if (idx >= 0) { - baudrate = baud_list[i]; tty_encode_baud_rate(tty, baudrate, baudrate); break; } diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index eea3dd18a044c38338ea3206435573e0e405d4b0..5636b8f52216760a065ceb286ea1bafddd9cffaf 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -162,6 +162,8 @@ static void option_instat_callback(struct urb *urb); #define NOVATELWIRELESS_PRODUCT_G2 0xA010 #define NOVATELWIRELESS_PRODUCT_MC551 0xB001 +#define UBLOX_VENDOR_ID 0x1546 + /* AMOI PRODUCTS */ #define AMOI_VENDOR_ID 0x1614 #define AMOI_PRODUCT_H01 0x0800 @@ -240,7 +242,6 @@ static void option_instat_callback(struct urb *urb); #define QUECTEL_PRODUCT_UC15 0x9090 /* These u-blox products use Qualcomm's vendor ID */ #define UBLOX_PRODUCT_R410M 0x90b2 -#define UBLOX_PRODUCT_R6XX 0x90fa /* These Yuga products use Qualcomm's vendor ID */ #define YUGA_PRODUCT_CLM920_NC5 0x9625 @@ -254,6 +255,7 @@ static void option_instat_callback(struct urb *urb); #define QUECTEL_PRODUCT_EP06 0x0306 #define QUECTEL_PRODUCT_EM05G 0x030a #define QUECTEL_PRODUCT_EM060K 0x030b +#define QUECTEL_PRODUCT_EM05G_SG 0x0311 #define QUECTEL_PRODUCT_EM12 0x0512 #define QUECTEL_PRODUCT_RM500Q 0x0800 #define QUECTEL_PRODUCT_RM520N 0x0801 @@ -581,6 +583,9 @@ static void option_instat_callback(struct urb *urb); #define OPPO_VENDOR_ID 0x22d9 #define OPPO_PRODUCT_R11 0x276c +/* Sierra Wireless products */ +#define SIERRA_VENDOR_ID 0x1199 +#define SIERRA_PRODUCT_EM9191 0x90d3 /* Device flags */ @@ -1124,8 +1129,16 @@ static const struct usb_device_id option_ids[] = { /* u-blox products using Qualcomm vendor ID */ { USB_DEVICE(QUALCOMM_VENDOR_ID, UBLOX_PRODUCT_R410M), .driver_info = RSVD(1) | RSVD(3) }, - { USB_DEVICE(QUALCOMM_VENDOR_ID, UBLOX_PRODUCT_R6XX), + { USB_DEVICE(QUALCOMM_VENDOR_ID, 0x908b), /* u-blox LARA-R6 00B */ + .driver_info = RSVD(4) }, + { USB_DEVICE(QUALCOMM_VENDOR_ID, 0x90fa), .driver_info = RSVD(3) }, + /* u-blox products */ + { USB_DEVICE(UBLOX_VENDOR_ID, 0x1341) }, /* u-blox LARA-L6 */ + { USB_DEVICE(UBLOX_VENDOR_ID, 0x1342), /* u-blox LARA-L6 (RMNET) */ + .driver_info = RSVD(4) }, + { USB_DEVICE(UBLOX_VENDOR_ID, 0x1343), /* u-blox LARA-L6 (ECM) */ + .driver_info = RSVD(4) }, /* Quectel products using Quectel vendor ID */ { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC21, 0xff, 0xff, 0xff), .driver_info = NUMEP2 }, @@ -1148,6 +1161,8 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EP06, 0xff, 0, 0) }, { USB_DEVICE_INTERFACE_CLASS(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM05G, 0xff), .driver_info = RSVD(6) | ZLP }, + { USB_DEVICE_INTERFACE_CLASS(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM05G_SG, 0xff), + .driver_info = RSVD(6) | ZLP }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K, 0xff, 0x00, 0x40) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K, 0xff, 0xff, 0x30) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K, 0xff, 0xff, 0x40) }, @@ -2167,6 +2182,7 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x010a, 0xff) }, /* Fibocom MA510 (ECM mode) */ { USB_DEVICE_AND_INTERFACE_INFO(0x2cb7, 0x010b, 0xff, 0xff, 0x30) }, /* Fibocom FG150 Diag */ { USB_DEVICE_AND_INTERFACE_INFO(0x2cb7, 0x010b, 0xff, 0, 0) }, /* Fibocom FG150 AT */ + { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x0111, 0xff) }, /* Fibocom FM160 (MBIM mode) */ { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x01a0, 0xff) }, /* Fibocom NL668-AM/NL652-EU (laptop MBIM) */ { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x01a2, 0xff) }, /* Fibocom FM101-GL (laptop MBIM) */ { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x01a4, 0xff), /* Fibocom FM101-GL (laptop MBIM) */ @@ -2176,6 +2192,8 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_INTERFACE_CLASS(0x305a, 0x1405, 0xff) }, /* GosunCn GM500 MBIM */ { USB_DEVICE_INTERFACE_CLASS(0x305a, 0x1406, 0xff) }, /* GosunCn GM500 ECM/NCM */ { USB_DEVICE_AND_INTERFACE_INFO(OPPO_VENDOR_ID, OPPO_PRODUCT_R11, 0xff, 0xff, 0x30) }, + { USB_DEVICE_AND_INTERFACE_INFO(SIERRA_VENDOR_ID, SIERRA_PRODUCT_EM9191, 0xff, 0xff, 0x30) }, + { USB_DEVICE_AND_INTERFACE_INFO(SIERRA_VENDOR_ID, SIERRA_PRODUCT_EM9191, 0xff, 0, 0) }, { } /* Terminating entry */ }; MODULE_DEVICE_TABLE(usb, option_ids); diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h index 4993227ab29301ddf2fc03aec3aadf0a9baeec5a..20dcbccb290b36b9200a33c61a5fe2e35b0fe151 100644 --- a/drivers/usb/storage/unusual_devs.h +++ b/drivers/usb/storage/unusual_devs.h @@ -1275,12 +1275,6 @@ UNUSUAL_DEV( 0x090a, 0x1200, 0x0000, 0x9999, USB_SC_RBC, USB_PR_BULK, NULL, 0 ), -UNUSUAL_DEV(0x090c, 0x1000, 0x1100, 0x1100, - "Samsung", - "Flash Drive FIT", - USB_SC_DEVICE, USB_PR_DEVICE, NULL, - US_FL_MAX_SECTORS_64), - /* aeb */ UNUSUAL_DEV( 0x090c, 0x1132, 0x0000, 0xffff, "Feiya", diff --git a/drivers/usb/typec/mux/intel_pmc_mux.c b/drivers/usb/typec/mux/intel_pmc_mux.c index bcee2a366035c0f77f4c4e1a02a6015baaaa0c0f..271e2740992fdfae2834d088bc65b3af8f521565 100644 --- a/drivers/usb/typec/mux/intel_pmc_mux.c +++ b/drivers/usb/typec/mux/intel_pmc_mux.c @@ -352,13 +352,24 @@ pmc_usb_mux_usb4(struct pmc_usb_port *port, struct typec_mux_state *state) return pmc_usb_command(port, (void *)&req, sizeof(req)); } -static int pmc_usb_mux_safe_state(struct pmc_usb_port *port) +static int pmc_usb_mux_safe_state(struct pmc_usb_port *port, + struct typec_mux_state *state) { u8 msg; if (IOM_PORT_ACTIVITY_IS(port->iom_status, SAFE_MODE)) return 0; + if ((IOM_PORT_ACTIVITY_IS(port->iom_status, DP) || + IOM_PORT_ACTIVITY_IS(port->iom_status, DP_MFD)) && + state->alt && state->alt->svid == USB_TYPEC_DP_SID) + return 0; + + if ((IOM_PORT_ACTIVITY_IS(port->iom_status, TBT) || + IOM_PORT_ACTIVITY_IS(port->iom_status, ALT_MODE_TBT_USB)) && + state->alt && state->alt->svid == USB_TYPEC_TBT_SID) + return 0; + msg = PMC_USB_SAFE_MODE; msg |= port->usb3_port << PMC_USB_MSG_USB3_PORT_SHIFT; @@ -426,7 +437,7 @@ pmc_usb_mux_set(struct typec_mux *mux, struct typec_mux_state *state) return 0; if (state->mode == TYPEC_STATE_SAFE) - return pmc_usb_mux_safe_state(port); + return pmc_usb_mux_safe_state(port, state); if (state->mode == TYPEC_STATE_USB) return pmc_usb_connect(port, port->role); diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c index a3544875d92217cf05e81dc500e6daedbb1ae59b..0b855f373c6407d3df9af69b291bfd64b6aaa297 100644 --- a/drivers/vhost/vsock.c +++ b/drivers/vhost/vsock.c @@ -359,7 +359,7 @@ vhost_vsock_alloc_pkt(struct vhost_virtqueue *vq, return NULL; } - pkt->buf = kmalloc(pkt->len, GFP_KERNEL); + pkt->buf = kvmalloc(pkt->len, GFP_KERNEL); if (!pkt->buf) { kfree(pkt); return NULL; diff --git a/drivers/video/fbdev/smscufx.c b/drivers/video/fbdev/smscufx.c index 28768c272b73d3e57ff4212dfe44f9c81d4af56a..5fa3f1e5dfe886af77a81bb758358a55420e204c 100644 --- a/drivers/video/fbdev/smscufx.c +++ b/drivers/video/fbdev/smscufx.c @@ -97,7 +97,6 @@ struct ufx_data { struct kref kref; int fb_count; bool virtualized; /* true when physical usb device not present */ - struct delayed_work free_framebuffer_work; atomic_t usb_active; /* 0 = update virtual buffer, but no usb traffic */ atomic_t lost_pixels; /* 1 = a render op failed. Need screen refresh */ u8 *edid; /* null until we read edid from hw or get from sysfs */ @@ -137,6 +136,8 @@ static int ufx_submit_urb(struct ufx_data *dev, struct urb * urb, size_t len); static int ufx_alloc_urb_list(struct ufx_data *dev, int count, size_t size); static void ufx_free_urb_list(struct ufx_data *dev); +static DEFINE_MUTEX(disconnect_mutex); + /* reads a control register */ static int ufx_reg_read(struct ufx_data *dev, u32 index, u32 *data) { @@ -1070,9 +1071,13 @@ static int ufx_ops_open(struct fb_info *info, int user) if (user == 0 && !console) return -EBUSY; + mutex_lock(&disconnect_mutex); + /* If the USB device is gone, we don't accept new opens */ - if (dev->virtualized) + if (dev->virtualized) { + mutex_unlock(&disconnect_mutex); return -ENODEV; + } dev->fb_count++; @@ -1096,6 +1101,8 @@ static int ufx_ops_open(struct fb_info *info, int user) pr_debug("open /dev/fb%d user=%d fb_info=%p count=%d", info->node, user, info, dev->fb_count); + mutex_unlock(&disconnect_mutex); + return 0; } @@ -1108,15 +1115,24 @@ static void ufx_free(struct kref *kref) { struct ufx_data *dev = container_of(kref, struct ufx_data, kref); - /* this function will wait for all in-flight urbs to complete */ - if (dev->urbs.count > 0) - ufx_free_urb_list(dev); + kfree(dev); +} - pr_debug("freeing ufx_data %p", dev); +static void ufx_ops_destory(struct fb_info *info) +{ + struct ufx_data *dev = info->par; + int node = info->node; - kfree(dev); + /* Assume info structure is freed after this point */ + framebuffer_release(info); + + pr_debug("fb_info for /dev/fb%d has been freed", node); + + /* release reference taken by kref_init in probe() */ + kref_put(&dev->kref, ufx_free); } + static void ufx_release_urb_work(struct work_struct *work) { struct urb_node *unode = container_of(work, struct urb_node, @@ -1125,14 +1141,9 @@ static void ufx_release_urb_work(struct work_struct *work) up(&unode->dev->urbs.limit_sem); } -static void ufx_free_framebuffer_work(struct work_struct *work) +static void ufx_free_framebuffer(struct ufx_data *dev) { - struct ufx_data *dev = container_of(work, struct ufx_data, - free_framebuffer_work.work); struct fb_info *info = dev->info; - int node = info->node; - - unregister_framebuffer(info); if (info->cmap.len != 0) fb_dealloc_cmap(&info->cmap); @@ -1144,11 +1155,6 @@ static void ufx_free_framebuffer_work(struct work_struct *work) dev->info = NULL; - /* Assume info structure is freed after this point */ - framebuffer_release(info); - - pr_debug("fb_info for /dev/fb%d has been freed", node); - /* ref taken in probe() as part of registering framebfufer */ kref_put(&dev->kref, ufx_free); } @@ -1160,11 +1166,13 @@ static int ufx_ops_release(struct fb_info *info, int user) { struct ufx_data *dev = info->par; + mutex_lock(&disconnect_mutex); + dev->fb_count--; /* We can't free fb_info here - fbmem will touch it when we return */ if (dev->virtualized && (dev->fb_count == 0)) - schedule_delayed_work(&dev->free_framebuffer_work, HZ); + ufx_free_framebuffer(dev); if ((dev->fb_count == 0) && (info->fbdefio)) { fb_deferred_io_cleanup(info); @@ -1177,6 +1185,8 @@ static int ufx_ops_release(struct fb_info *info, int user) kref_put(&dev->kref, ufx_free); + mutex_unlock(&disconnect_mutex); + return 0; } @@ -1283,6 +1293,7 @@ static const struct fb_ops ufx_ops = { .fb_blank = ufx_ops_blank, .fb_check_var = ufx_ops_check_var, .fb_set_par = ufx_ops_set_par, + .fb_destroy = ufx_ops_destory, }; /* Assumes &info->lock held by caller @@ -1664,9 +1675,6 @@ static int ufx_usb_probe(struct usb_interface *interface, goto destroy_modedb; } - INIT_DELAYED_WORK(&dev->free_framebuffer_work, - ufx_free_framebuffer_work); - retval = ufx_reg_read(dev, 0x3000, &id_rev); check_warn_goto_error(retval, "error %d reading 0x3000 register from device", retval); dev_dbg(dev->gdev, "ID_REV register value 0x%08x", id_rev); @@ -1739,8 +1747,12 @@ e_nomem: static void ufx_usb_disconnect(struct usb_interface *interface) { struct ufx_data *dev; + struct fb_info *info; + + mutex_lock(&disconnect_mutex); dev = usb_get_intfdata(interface); + info = dev->info; pr_debug("USB disconnect starting\n"); @@ -1754,12 +1766,17 @@ static void ufx_usb_disconnect(struct usb_interface *interface) /* if clients still have us open, will be freed on last close */ if (dev->fb_count == 0) - schedule_delayed_work(&dev->free_framebuffer_work, 0); + ufx_free_framebuffer(dev); - /* release reference taken by kref_init in probe() */ - kref_put(&dev->kref, ufx_free); + /* this function will wait for all in-flight urbs to complete */ + if (dev->urbs.count > 0) + ufx_free_urb_list(dev); + + pr_debug("freeing ufx_data %p", dev); + + unregister_framebuffer(info); - /* consider ufx_data freed */ + mutex_unlock(&disconnect_mutex); } static struct usb_driver ufx_driver = { diff --git a/drivers/video/fbdev/stifb.c b/drivers/video/fbdev/stifb.c index 002f265d8db58e6162feac4b8598971f0a115386..3feb6e40d56d8c8db1ba4699dde09465050e1ec8 100644 --- a/drivers/video/fbdev/stifb.c +++ b/drivers/video/fbdev/stifb.c @@ -1041,6 +1041,48 @@ stifb_copyarea(struct fb_info *info, const struct fb_copyarea *area) SETUP_FB(fb); } +#define ARTIST_VRAM_SIZE 0x000804 +#define ARTIST_VRAM_SRC 0x000808 +#define ARTIST_VRAM_SIZE_TRIGGER_WINFILL 0x000a04 +#define ARTIST_VRAM_DEST_TRIGGER_BLOCKMOVE 0x000b00 +#define ARTIST_SRC_BM_ACCESS 0x018008 +#define ARTIST_FGCOLOR 0x018010 +#define ARTIST_BGCOLOR 0x018014 +#define ARTIST_BITMAP_OP 0x01801c + +static void +stifb_fillrect(struct fb_info *info, const struct fb_fillrect *rect) +{ + struct stifb_info *fb = container_of(info, struct stifb_info, info); + + if (rect->rop != ROP_COPY || + (fb->id == S9000_ID_HCRX && fb->info.var.bits_per_pixel == 32)) + return cfb_fillrect(info, rect); + + SETUP_HW(fb); + + if (fb->info.var.bits_per_pixel == 32) { + WRITE_WORD(0xBBA0A000, fb, REG_10); + + NGLE_REALLY_SET_IMAGE_PLANEMASK(fb, 0xffffffff); + } else { + WRITE_WORD(fb->id == S9000_ID_HCRX ? 0x13a02000 : 0x13a01000, fb, REG_10); + + NGLE_REALLY_SET_IMAGE_PLANEMASK(fb, 0xff); + } + + WRITE_WORD(0x03000300, fb, ARTIST_BITMAP_OP); + WRITE_WORD(0x2ea01000, fb, ARTIST_SRC_BM_ACCESS); + NGLE_QUICK_SET_DST_BM_ACCESS(fb, 0x2ea01000); + NGLE_REALLY_SET_IMAGE_FG_COLOR(fb, rect->color); + WRITE_WORD(0, fb, ARTIST_BGCOLOR); + + NGLE_SET_DSTXY(fb, (rect->dx << 16) | (rect->dy)); + SET_LENXY_START_RECFILL(fb, (rect->width << 16) | (rect->height)); + + SETUP_FB(fb); +} + static void __init stifb_init_display(struct stifb_info *fb) { @@ -1105,7 +1147,7 @@ static const struct fb_ops stifb_ops = { .owner = THIS_MODULE, .fb_setcolreg = stifb_setcolreg, .fb_blank = stifb_blank, - .fb_fillrect = cfb_fillrect, + .fb_fillrect = stifb_fillrect, .fb_copyarea = stifb_copyarea, .fb_imageblit = cfb_imageblit, }; @@ -1257,7 +1299,7 @@ static int __init stifb_init_fb(struct sti_struct *sti, int bpp_pref) /* limit fbsize to max visible screen size */ if (fix->smem_len > yres*fix->line_length) - fix->smem_len = yres*fix->line_length; + fix->smem_len = ALIGN(yres*fix->line_length, 4*1024*1024); fix->accel = FB_ACCEL_NONE; @@ -1297,7 +1339,7 @@ static int __init stifb_init_fb(struct sti_struct *sti, int bpp_pref) goto out_err0; } info->screen_size = fix->smem_len; - info->flags = FBINFO_DEFAULT | FBINFO_HWACCEL_COPYAREA; + info->flags = FBINFO_HWACCEL_COPYAREA | FBINFO_HWACCEL_FILLRECT; info->pseudo_palette = &fb->pseudo_palette; /* This has to be done !!! */ diff --git a/drivers/xen/gntdev-common.h b/drivers/xen/gntdev-common.h index 40ef379c28ab01a3a11008cb0f85a1b3fde134ca..9c286b2a19001616ae0e9986be13905891b5f5ff 100644 --- a/drivers/xen/gntdev-common.h +++ b/drivers/xen/gntdev-common.h @@ -44,9 +44,10 @@ struct gntdev_unmap_notify { }; struct gntdev_grant_map { + atomic_t in_use; struct mmu_interval_notifier notifier; + bool notifier_init; struct list_head next; - struct vm_area_struct *vma; int index; int count; int flags; diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c index 54fee4087bf1078803c230ad2081aafa8415cf53..16acddaff9aeadf80fb265a4eaf96a75dd63430d 100644 --- a/drivers/xen/gntdev.c +++ b/drivers/xen/gntdev.c @@ -276,6 +276,9 @@ void gntdev_put_map(struct gntdev_priv *priv, struct gntdev_grant_map *map) */ } + if (use_ptemod && map->notifier_init) + mmu_interval_notifier_remove(&map->notifier); + if (map->notify.flags & UNMAP_NOTIFY_SEND_EVENT) { notify_remote_via_evtchn(map->notify.event); evtchn_put(map->notify.event); @@ -288,21 +291,14 @@ void gntdev_put_map(struct gntdev_priv *priv, struct gntdev_grant_map *map) static int find_grant_ptes(pte_t *pte, unsigned long addr, void *data) { struct gntdev_grant_map *map = data; - unsigned int pgnr = (addr - map->vma->vm_start) >> PAGE_SHIFT; - int flags = map->flags | GNTMAP_application_map | GNTMAP_contains_pte; + unsigned int pgnr = (addr - map->pages_vm_start) >> PAGE_SHIFT; + int flags = map->flags | GNTMAP_application_map | GNTMAP_contains_pte | + (1 << _GNTMAP_guest_avail0); u64 pte_maddr; BUG_ON(pgnr >= map->count); pte_maddr = arbitrary_virt_to_machine(pte).maddr; - /* - * Set the PTE as special to force get_user_pages_fast() fall - * back to the slow path. If this is not supported as part of - * the grant map, it will be done afterwards. - */ - if (xen_feature(XENFEAT_gnttab_map_avail_bits)) - flags |= (1 << _GNTMAP_guest_avail0); - gnttab_set_map_op(&map->map_ops[pgnr], pte_maddr, flags, map->grants[pgnr].ref, map->grants[pgnr].domid); @@ -311,14 +307,6 @@ static int find_grant_ptes(pte_t *pte, unsigned long addr, void *data) return 0; } -#ifdef CONFIG_X86 -static int set_grant_ptes_as_special(pte_t *pte, unsigned long addr, void *data) -{ - set_pte_at(current->mm, addr, pte, pte_mkspecial(*pte)); - return 0; -} -#endif - int gntdev_map_grant_pages(struct gntdev_grant_map *map) { size_t alloced = 0; @@ -372,8 +360,7 @@ int gntdev_map_grant_pages(struct gntdev_grant_map *map) for (i = 0; i < map->count; i++) { if (map->map_ops[i].status == GNTST_okay) { map->unmap_ops[i].handle = map->map_ops[i].handle; - if (!use_ptemod) - alloced++; + alloced++; } else if (!err) err = -EINVAL; @@ -382,8 +369,7 @@ int gntdev_map_grant_pages(struct gntdev_grant_map *map) if (use_ptemod) { if (map->kmap_ops[i].status == GNTST_okay) { - if (map->map_ops[i].status == GNTST_okay) - alloced++; + alloced++; map->kunmap_ops[i].handle = map->kmap_ops[i].handle; } else if (!err) err = -EINVAL; @@ -399,20 +385,42 @@ static void __unmap_grant_pages_done(int result, unsigned int i; struct gntdev_grant_map *map = data->data; unsigned int offset = data->unmap_ops - map->unmap_ops; + int successful_unmaps = 0; + int live_grants; for (i = 0; i < data->count; i++) { + if (map->unmap_ops[offset + i].status == GNTST_okay && + map->unmap_ops[offset + i].handle != -1) + successful_unmaps++; + WARN_ON(map->unmap_ops[offset+i].status && map->unmap_ops[offset+i].handle != -1); pr_debug("unmap handle=%d st=%d\n", map->unmap_ops[offset+i].handle, map->unmap_ops[offset+i].status); map->unmap_ops[offset+i].handle = -1; + if (use_ptemod) { + if (map->kunmap_ops[offset + i].status == GNTST_okay && + map->kunmap_ops[offset + i].handle != -1) + successful_unmaps++; + + WARN_ON(map->kunmap_ops[offset+i].status && + map->kunmap_ops[offset+i].handle != -1); + pr_debug("kunmap handle=%u st=%d\n", + map->kunmap_ops[offset+i].handle, + map->kunmap_ops[offset+i].status); + map->kunmap_ops[offset+i].handle = -1; + } } + /* * Decrease the live-grant counter. This must happen after the loop to * prevent premature reuse of the grants by gnttab_mmap(). */ - atomic_sub(data->count, &map->live_grants); + live_grants = atomic_sub_return(successful_unmaps, &map->live_grants); + if (WARN_ON(live_grants < 0)) + pr_err("%s: live_grants became negative (%d) after unmapping %d pages!\n", + __func__, live_grants, successful_unmaps); /* Release reference taken by __unmap_grant_pages */ gntdev_put_map(NULL, map); @@ -493,11 +501,7 @@ static void gntdev_vma_close(struct vm_area_struct *vma) struct gntdev_priv *priv = file->private_data; pr_debug("gntdev_vma_close %p\n", vma); - if (use_ptemod) { - WARN_ON(map->vma != vma); - mmu_interval_notifier_remove(&map->notifier); - map->vma = NULL; - } + vma->vm_private_data = NULL; gntdev_put_map(priv, map); } @@ -525,29 +529,30 @@ static bool gntdev_invalidate(struct mmu_interval_notifier *mn, struct gntdev_grant_map *map = container_of(mn, struct gntdev_grant_map, notifier); unsigned long mstart, mend; + unsigned long map_start, map_end; if (!mmu_notifier_range_blockable(range)) return false; + map_start = map->pages_vm_start; + map_end = map->pages_vm_start + (map->count << PAGE_SHIFT); + /* * If the VMA is split or otherwise changed the notifier is not * updated, but we don't want to process VA's outside the modified * VMA. FIXME: It would be much more understandable to just prevent * modifying the VMA in the first place. */ - if (map->vma->vm_start >= range->end || - map->vma->vm_end <= range->start) + if (map_start >= range->end || map_end <= range->start) return true; - mstart = max(range->start, map->vma->vm_start); - mend = min(range->end, map->vma->vm_end); + mstart = max(range->start, map_start); + mend = min(range->end, map_end); pr_debug("map %d+%d (%lx %lx), range %lx %lx, mrange %lx %lx\n", - map->index, map->count, - map->vma->vm_start, map->vma->vm_end, - range->start, range->end, mstart, mend); - unmap_grant_pages(map, - (mstart - map->vma->vm_start) >> PAGE_SHIFT, - (mend - mstart) >> PAGE_SHIFT); + map->index, map->count, map_start, map_end, + range->start, range->end, mstart, mend); + unmap_grant_pages(map, (mstart - map_start) >> PAGE_SHIFT, + (mend - mstart) >> PAGE_SHIFT); return true; } @@ -1027,18 +1032,15 @@ static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma) return -EINVAL; pr_debug("map %d+%d at %lx (pgoff %lx)\n", - index, count, vma->vm_start, vma->vm_pgoff); + index, count, vma->vm_start, vma->vm_pgoff); mutex_lock(&priv->lock); map = gntdev_find_map_index(priv, index, count); if (!map) goto unlock_out; - if (use_ptemod && map->vma) - goto unlock_out; - if (atomic_read(&map->live_grants)) { - err = -EAGAIN; + if (!atomic_add_unless(&map->in_use, 1, 1)) goto unlock_out; - } + refcount_inc(&map->users); vma->vm_ops = &gntdev_vmops; @@ -1059,15 +1061,16 @@ static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma) map->flags |= GNTMAP_readonly; } + map->pages_vm_start = vma->vm_start; + if (use_ptemod) { - map->vma = vma; err = mmu_interval_notifier_insert_locked( &map->notifier, vma->vm_mm, vma->vm_start, vma->vm_end - vma->vm_start, &gntdev_mmu_ops); - if (err) { - map->vma = NULL; + if (err) goto out_unlock_put; - } + + map->notifier_init = true; } mutex_unlock(&priv->lock); @@ -1084,7 +1087,6 @@ static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma) */ mmu_interval_read_begin(&map->notifier); - map->pages_vm_start = vma->vm_start; err = apply_to_page_range(vma->vm_mm, vma->vm_start, vma->vm_end - vma->vm_start, find_grant_ptes, map); @@ -1102,23 +1104,6 @@ static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma) err = vm_map_pages_zero(vma, map->pages, map->count); if (err) goto out_put_map; - } else { -#ifdef CONFIG_X86 - /* - * If the PTEs were not made special by the grant map - * hypercall, do so here. - * - * This is racy since the mapping is already visible - * to userspace but userspace should be well-behaved - * enough to not touch it until the mmap() call - * returns. - */ - if (!xen_feature(XENFEAT_gnttab_map_avail_bits)) { - apply_to_page_range(vma->vm_mm, vma->vm_start, - vma->vm_end - vma->vm_start, - set_grant_ptes_as_special, NULL); - } -#endif } return 0; @@ -1130,13 +1115,8 @@ unlock_out: out_unlock_put: mutex_unlock(&priv->lock); out_put_map: - if (use_ptemod) { + if (use_ptemod) unmap_grant_pages(map, 0, map->count); - if (map->vma) { - mmu_interval_notifier_remove(&map->notifier); - map->vma = NULL; - } - } gntdev_put_map(priv, map); return err; } diff --git a/drivers/xen/pcpu.c b/drivers/xen/pcpu.c index cdc6daa7a9f66f9a534e619af244bc8843bcccef..9cf7085a260b4e48b0dfb81d1f8493b801293898 100644 --- a/drivers/xen/pcpu.c +++ b/drivers/xen/pcpu.c @@ -228,7 +228,7 @@ static int register_pcpu(struct pcpu *pcpu) err = device_register(dev); if (err) { - pcpu_release(dev); + put_device(dev); return err; } diff --git a/drivers/xen/platform-pci.c b/drivers/xen/platform-pci.c index 9db557b76511b235a17416fc7b881cf3ff496f90..804d8f4d0e73d261fefd187caf70727b7fb0bc33 100644 --- a/drivers/xen/platform-pci.c +++ b/drivers/xen/platform-pci.c @@ -137,7 +137,7 @@ static int platform_pci_probe(struct pci_dev *pdev, if (ret) { dev_warn(&pdev->dev, "Unable to set the evtchn callback " "err=%d\n", ret); - goto out; + goto irq_out; } } @@ -145,13 +145,16 @@ static int platform_pci_probe(struct pci_dev *pdev, grant_frames = alloc_xen_mmio(PAGE_SIZE * max_nr_gframes); ret = gnttab_setup_auto_xlat_frames(grant_frames); if (ret) - goto out; + goto irq_out; ret = gnttab_init(); if (ret) goto grant_out; return 0; grant_out: gnttab_free_auto_xlat_frames(); +irq_out: + if (!xen_have_vector_callback) + free_irq(pdev->irq, pdev); out: pci_release_region(pdev, 0); mem_out: diff --git a/drivers/xen/xen-pciback/conf_space_capability.c b/drivers/xen/xen-pciback/conf_space_capability.c index 5e53b4817f16796bec96c67a4af63b97bc9c97cc..097316a741268b6da10d2024303ac7b4ceae8490 100644 --- a/drivers/xen/xen-pciback/conf_space_capability.c +++ b/drivers/xen/xen-pciback/conf_space_capability.c @@ -190,13 +190,16 @@ static const struct config_field caplist_pm[] = { }; static struct msi_msix_field_config { - u16 enable_bit; /* bit for enabling MSI/MSI-X */ - unsigned int int_type; /* interrupt type for exclusiveness check */ + u16 enable_bit; /* bit for enabling MSI/MSI-X */ + u16 allowed_bits; /* bits allowed to be changed */ + unsigned int int_type; /* interrupt type for exclusiveness check */ } msi_field_config = { .enable_bit = PCI_MSI_FLAGS_ENABLE, + .allowed_bits = PCI_MSI_FLAGS_ENABLE, .int_type = INTERRUPT_TYPE_MSI, }, msix_field_config = { .enable_bit = PCI_MSIX_FLAGS_ENABLE, + .allowed_bits = PCI_MSIX_FLAGS_ENABLE | PCI_MSIX_FLAGS_MASKALL, .int_type = INTERRUPT_TYPE_MSIX, }; @@ -229,7 +232,7 @@ static int msi_msix_flags_write(struct pci_dev *dev, int offset, u16 new_value, return 0; if (!dev_data->allow_interrupt_control || - (new_value ^ old_value) & ~field_config->enable_bit) + (new_value ^ old_value) & ~field_config->allowed_bits) return PCIBIOS_SET_FAILED; if (new_value & field_config->enable_bit) { diff --git a/fs/Makefile b/fs/Makefile index 359c63fefa1b88011bb610f24d53e46a2e7156ea..c7851875b668b1fd378b8806f935d523535883b7 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -34,8 +34,6 @@ obj-$(CONFIG_TIMERFD) += timerfd.o obj-$(CONFIG_EVENTFD) += eventfd.o obj-$(CONFIG_USERFAULTFD) += userfaultfd.o obj-$(CONFIG_AIO) += aio.o -obj-$(CONFIG_IO_URING) += io_uring.o -obj-$(CONFIG_IO_WQ) += io-wq.o obj-$(CONFIG_FS_DAX) += dax.o obj-$(CONFIG_FS_ENCRYPTION) += crypto/ obj-$(CONFIG_FS_VERITY) += verity/ diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 7d6f2f791fe975e33f43b169aa8fe7c0360fb839..dfb6409f7a81d63933a2c9e7ddb1f2bea6d37f96 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -907,7 +907,7 @@ static int load_elf_binary(struct linux_binprm *bprm) interp_elf_ex = kmalloc(sizeof(*interp_elf_ex), GFP_KERNEL); if (!interp_elf_ex) { retval = -ENOMEM; - goto out_free_ph; + goto out_free_file; } /* Get the exec headers */ @@ -1328,6 +1328,7 @@ out: out_free_dentry: kfree(interp_elf_ex); kfree(interp_elf_phdata); +out_free_file: allow_write_access(interpreter); if (interpreter) fput(interpreter); diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index baff31a147e7dfa802c6a8823dce91837443daf5..6942707f8b034b6f380ddeb07a97407e9701f962 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -137,6 +137,7 @@ struct share_check { u64 root_objectid; u64 inum; int share_count; + bool have_delayed_delete_refs; }; static inline int extent_is_shared(struct share_check *sc) @@ -287,8 +288,10 @@ static void prelim_release(struct preftree *preftree) struct prelim_ref *ref, *next_ref; rbtree_postorder_for_each_entry_safe(ref, next_ref, - &preftree->root.rb_root, rbnode) + &preftree->root.rb_root, rbnode) { + free_inode_elem_list(ref->inode_list); free_pref(ref); + } preftree->root = RB_ROOT_CACHED; preftree->count = 0; @@ -646,6 +649,18 @@ unode_aux_to_inode_list(struct ulist_node *node) return (struct extent_inode_elem *)(uintptr_t)node->aux; } +static void free_leaf_list(struct ulist *ulist) +{ + struct ulist_node *node; + struct ulist_iterator uiter; + + ULIST_ITER_INIT(&uiter); + while ((node = ulist_next(ulist, &uiter))) + free_inode_elem_list(unode_aux_to_inode_list(node)); + + ulist_free(ulist); +} + /* * We maintain three separate rbtrees: one for direct refs, one for * indirect refs which have a key, and one for indirect refs which do not @@ -760,7 +775,11 @@ static int resolve_indirect_refs(struct btrfs_fs_info *fs_info, cond_resched(); } out: - ulist_free(parents); + /* + * We may have inode lists attached to refs in the parents ulist, so we + * must free them before freeing the ulist and its refs. + */ + free_leaf_list(parents); return ret; } @@ -817,16 +836,11 @@ static int add_delayed_refs(const struct btrfs_fs_info *fs_info, struct preftrees *preftrees, struct share_check *sc) { struct btrfs_delayed_ref_node *node; - struct btrfs_delayed_extent_op *extent_op = head->extent_op; struct btrfs_key key; - struct btrfs_key tmp_op_key; struct rb_node *n; int count; int ret = 0; - if (extent_op && extent_op->update_key) - btrfs_disk_key_to_cpu(&tmp_op_key, &extent_op->key); - spin_lock(&head->lock); for (n = rb_first_cached(&head->ref_tree); n; n = rb_next(n)) { node = rb_entry(n, struct btrfs_delayed_ref_node, @@ -852,10 +866,16 @@ static int add_delayed_refs(const struct btrfs_fs_info *fs_info, case BTRFS_TREE_BLOCK_REF_KEY: { /* NORMAL INDIRECT METADATA backref */ struct btrfs_delayed_tree_ref *ref; + struct btrfs_key *key_ptr = NULL; + + if (head->extent_op && head->extent_op->update_key) { + btrfs_disk_key_to_cpu(&key, &head->extent_op->key); + key_ptr = &key; + } ref = btrfs_delayed_node_to_tree_ref(node); ret = add_indirect_ref(fs_info, preftrees, ref->root, - &tmp_op_key, ref->level + 1, + key_ptr, ref->level + 1, node->bytenr, count, sc, GFP_ATOMIC); break; @@ -881,13 +901,22 @@ static int add_delayed_refs(const struct btrfs_fs_info *fs_info, key.offset = ref->offset; /* - * Found a inum that doesn't match our known inum, we - * know it's shared. + * If we have a share check context and a reference for + * another inode, we can't exit immediately. This is + * because even if this is a BTRFS_ADD_DELAYED_REF + * reference we may find next a BTRFS_DROP_DELAYED_REF + * which cancels out this ADD reference. + * + * If this is a DROP reference and there was no previous + * ADD reference, then we need to signal that when we + * process references from the extent tree (through + * add_inline_refs() and add_keyed_refs()), we should + * not exit early if we find a reference for another + * inode, because one of the delayed DROP references + * may cancel that reference in the extent tree. */ - if (sc && sc->inum && ref->objectid != sc->inum) { - ret = BACKREF_FOUND_SHARED; - goto out; - } + if (sc && count < 0) + sc->have_delayed_delete_refs = true; ret = add_indirect_ref(fs_info, preftrees, ref->root, &key, 0, node->bytenr, count, sc, @@ -917,7 +946,7 @@ static int add_delayed_refs(const struct btrfs_fs_info *fs_info, } if (!ret) ret = extent_is_shared(sc); -out: + spin_unlock(&head->lock); return ret; } @@ -1020,7 +1049,8 @@ static int add_inline_refs(const struct btrfs_fs_info *fs_info, key.type = BTRFS_EXTENT_DATA_KEY; key.offset = btrfs_extent_data_ref_offset(leaf, dref); - if (sc && sc->inum && key.objectid != sc->inum) { + if (sc && sc->inum && key.objectid != sc->inum && + !sc->have_delayed_delete_refs) { ret = BACKREF_FOUND_SHARED; break; } @@ -1030,6 +1060,7 @@ static int add_inline_refs(const struct btrfs_fs_info *fs_info, ret = add_indirect_ref(fs_info, preftrees, root, &key, 0, bytenr, count, sc, GFP_NOFS); + break; } default: @@ -1119,7 +1150,8 @@ static int add_keyed_refs(struct btrfs_fs_info *fs_info, key.type = BTRFS_EXTENT_DATA_KEY; key.offset = btrfs_extent_data_ref_offset(leaf, dref); - if (sc && sc->inum && key.objectid != sc->inum) { + if (sc && sc->inum && key.objectid != sc->inum && + !sc->have_delayed_delete_refs) { ret = BACKREF_FOUND_SHARED; break; } @@ -1358,6 +1390,12 @@ again: if (ret < 0) goto out; ref->inode_list = eie; + /* + * We transferred the list ownership to the ref, + * so set to NULL to avoid a double free in case + * an error happens after this. + */ + eie = NULL; } ret = ulist_add_merge_ptr(refs, ref->parent, ref->inode_list, @@ -1383,6 +1421,14 @@ again: eie->next = ref->inode_list; } eie = NULL; + /* + * We have transferred the inode list ownership from + * this ref to the ref we added to the 'refs' ulist. + * So set this ref's inode list to NULL to avoid + * use-after-free when our caller uses it or double + * frees in case an error happens before we return. + */ + ref->inode_list = NULL; } cond_resched(); } @@ -1399,24 +1445,6 @@ out: return ret; } -static void free_leaf_list(struct ulist *blocks) -{ - struct ulist_node *node = NULL; - struct extent_inode_elem *eie; - struct ulist_iterator uiter; - - ULIST_ITER_INIT(&uiter); - while ((node = ulist_next(blocks, &uiter))) { - if (!node->aux) - continue; - eie = unode_aux_to_inode_list(node); - free_inode_elem_list(eie); - node->aux = 0; - } - - ulist_free(blocks); -} - /* * Finds all leafs with a reference to the specified combination of bytenr and * offset. key_list_head will point to a list of corresponding keys (caller must @@ -1542,6 +1570,7 @@ int btrfs_check_shared(struct btrfs_root *root, u64 inum, u64 bytenr, .root_objectid = root->root_key.objectid, .inum = inum, .share_count = 0, + .have_delayed_delete_refs = false, }; ulist_init(roots); @@ -1576,6 +1605,7 @@ int btrfs_check_shared(struct btrfs_root *root, u64 inum, u64 bytenr, break; bytenr = node->val; shared.share_count = 0; + shared.have_delayed_delete_refs = false; cond_resched(); } diff --git a/fs/btrfs/export.c b/fs/btrfs/export.c index 1a8d419d9e1f4707c2d0fe2177896fd096164559..bfa2bf44529c25cb951cb546183084000119b4a3 100644 --- a/fs/btrfs/export.c +++ b/fs/btrfs/export.c @@ -58,7 +58,7 @@ static int btrfs_encode_fh(struct inode *inode, u32 *fh, int *max_len, } struct dentry *btrfs_get_dentry(struct super_block *sb, u64 objectid, - u64 root_objectid, u32 generation, + u64 root_objectid, u64 generation, int check_generation) { struct btrfs_fs_info *fs_info = btrfs_sb(sb); diff --git a/fs/btrfs/export.h b/fs/btrfs/export.h index f32f4113c976a95a072a65e558810ebc561a2a51..5afb7ca428289da24296b8e207ed67613fa691b0 100644 --- a/fs/btrfs/export.h +++ b/fs/btrfs/export.h @@ -19,7 +19,7 @@ struct btrfs_fid { } __attribute__ ((packed)); struct dentry *btrfs_get_dentry(struct super_block *sb, u64 objectid, - u64 root_objectid, u32 generation, + u64 root_objectid, u64 generation, int check_generation); struct dentry *btrfs_get_parent(struct dentry *child); diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index b5e9bfe884c4b7eec01517fdb708eb2fa13636b7..d0c31651ec80db695fbd7ca846bc078a5e4f95f3 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -2811,6 +2811,8 @@ static int btrfs_ioctl_get_subvol_info(struct file *file, void __user *argp) } } + btrfs_free_path(path); + path = NULL; if (copy_to_user(argp, subvol_info, sizeof(*subvol_info))) ret = -EFAULT; @@ -2903,6 +2905,8 @@ static int btrfs_ioctl_get_subvol_rootref(struct file *file, void __user *argp) } out: + btrfs_free_path(path); + if (!ret || ret == -EOVERFLOW) { rootrefs->num_items = found; /* update min_treeid for next search */ @@ -2914,7 +2918,6 @@ out: } kfree(rootrefs); - btrfs_free_path(path); return ret; } @@ -3878,6 +3881,8 @@ static long btrfs_ioctl_ino_to_path(struct btrfs_root *root, void __user *arg) ipath->fspath->val[i] = rel_ptr; } + btrfs_free_path(path); + path = NULL; ret = copy_to_user((void __user *)(unsigned long)ipa->fspath, ipath->fspath, size); if (ret) { diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index a02e38fb696c17f62d81a9ef0358bf376d411c48..36da775340768a617e6784775858c887f67efe98 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -1158,6 +1158,21 @@ out_add_root: fs_info->qgroup_rescan_running = true; btrfs_queue_work(fs_info->qgroup_rescan_workers, &fs_info->qgroup_rescan_work); + } else { + /* + * We have set both BTRFS_FS_QUOTA_ENABLED and + * BTRFS_QGROUP_STATUS_FLAG_ON, so we can only fail with + * -EINPROGRESS. That can happen because someone started the + * rescan worker by calling quota rescan ioctl before we + * attempted to initialize the rescan worker. Failure due to + * quotas disabled in the meanwhile is not possible, because + * we are holding a write lock on fs_info->subvol_sem, which + * is also acquired when disabling quotas. + * Ignore such error, and any other error would need to undo + * everything we did in the transaction we just committed. + */ + ASSERT(ret == -EINPROGRESS); + ret = 0; } out_free_path: diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index 0392c556af60126d72f660454bb1c99555121df9..88b9a5394561e3f919efbfed7f65c3f2f78d4ac6 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -3811,6 +3811,7 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start, int ret; struct btrfs_device *dev; unsigned int nofs_flag; + bool need_commit = false; if (btrfs_fs_closing(fs_info)) return -EAGAIN; @@ -3924,6 +3925,12 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start, */ nofs_flag = memalloc_nofs_save(); if (!is_dev_replace) { + u64 old_super_errors; + + spin_lock(&sctx->stat_lock); + old_super_errors = sctx->stat.super_errors; + spin_unlock(&sctx->stat_lock); + btrfs_info(fs_info, "scrub: started on devid %llu", devid); /* * by holding device list mutex, we can @@ -3932,6 +3939,16 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start, mutex_lock(&fs_info->fs_devices->device_list_mutex); ret = scrub_supers(sctx, dev); mutex_unlock(&fs_info->fs_devices->device_list_mutex); + + spin_lock(&sctx->stat_lock); + /* + * Super block errors found, but we can not commit transaction + * at current context, since btrfs_commit_transaction() needs + * to pause the current running scrub (hold by ourselves). + */ + if (sctx->stat.super_errors > old_super_errors && !sctx->readonly) + need_commit = true; + spin_unlock(&sctx->stat_lock); } if (!ret) @@ -3958,6 +3975,25 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start, scrub_workers_put(fs_info); scrub_put_ctx(sctx); + /* + * We found some super block errors before, now try to force a + * transaction commit, as scrub has finished. + */ + if (need_commit) { + struct btrfs_trans_handle *trans; + + trans = btrfs_start_transaction(fs_info->tree_root, 0); + if (IS_ERR(trans)) { + ret = PTR_ERR(trans); + btrfs_err(fs_info, + "scrub: failed to start transaction to fix super block errors: %d", ret); + return ret; + } + ret = btrfs_commit_transaction(trans); + if (ret < 0) + btrfs_err(fs_info, + "scrub: failed to commit transaction to fix super block errors: %d", ret); + } return ret; out: scrub_workers_put(fs_info); diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c index 3bb6b688ece522b9351383a1fa4d2db71b149ecc..ecf190286377caaa5db05d2b33d0277d6f7e1880 100644 --- a/fs/btrfs/sysfs.c +++ b/fs/btrfs/sysfs.c @@ -1767,8 +1767,11 @@ int __init btrfs_init_sysfs(void) #ifdef CONFIG_BTRFS_DEBUG ret = sysfs_create_group(&btrfs_kset->kobj, &btrfs_debug_feature_attr_group); - if (ret) - goto out2; + if (ret) { + sysfs_unmerge_group(&btrfs_kset->kobj, + &btrfs_static_feature_attr_group); + goto out_remove_group; + } #endif return 0; diff --git a/fs/btrfs/tests/btrfs-tests.c b/fs/btrfs/tests/btrfs-tests.c index 999c14e5d0bdd939c672076e963df4c87a1614f8..0599566c66b06b2c286da3189edb39696c2c658b 100644 --- a/fs/btrfs/tests/btrfs-tests.c +++ b/fs/btrfs/tests/btrfs-tests.c @@ -192,7 +192,7 @@ void btrfs_free_dummy_fs_info(struct btrfs_fs_info *fs_info) void btrfs_free_dummy_root(struct btrfs_root *root) { - if (!root) + if (IS_ERR_OR_NULL(root)) return; /* Will be freed by btrfs_free_fs_roots */ if (WARN_ON(test_bit(BTRFS_ROOT_IN_RADIX, &root->state))) diff --git a/fs/btrfs/tests/qgroup-tests.c b/fs/btrfs/tests/qgroup-tests.c index ce1ca8e73c2d1a8801e149fac57c8d771763ed1b..289366c98f5b8f49d7fc2f89e9ca1a2442d749f6 100644 --- a/fs/btrfs/tests/qgroup-tests.c +++ b/fs/btrfs/tests/qgroup-tests.c @@ -230,21 +230,21 @@ static int test_no_shared_qgroup(struct btrfs_root *root, ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &old_roots, false); if (ret) { - ulist_free(old_roots); test_err("couldn't find old roots: %d", ret); return ret; } ret = insert_normal_tree_ref(root, nodesize, nodesize, 0, BTRFS_FS_TREE_OBJECTID); - if (ret) + if (ret) { + ulist_free(old_roots); return ret; + } ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &new_roots, false); if (ret) { ulist_free(old_roots); - ulist_free(new_roots); test_err("couldn't find old roots: %d", ret); return ret; } @@ -256,31 +256,33 @@ static int test_no_shared_qgroup(struct btrfs_root *root, return ret; } + /* btrfs_qgroup_account_extent() always frees the ulists passed to it. */ + old_roots = NULL; + new_roots = NULL; + if (btrfs_verify_qgroup_counts(fs_info, BTRFS_FS_TREE_OBJECTID, nodesize, nodesize)) { test_err("qgroup counts didn't match expected values"); return -EINVAL; } - old_roots = NULL; - new_roots = NULL; ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &old_roots, false); if (ret) { - ulist_free(old_roots); test_err("couldn't find old roots: %d", ret); return ret; } ret = remove_extent_item(root, nodesize, nodesize); - if (ret) + if (ret) { + ulist_free(old_roots); return -EINVAL; + } ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &new_roots, false); if (ret) { ulist_free(old_roots); - ulist_free(new_roots); test_err("couldn't find old roots: %d", ret); return ret; } @@ -331,21 +333,21 @@ static int test_multiple_refs(struct btrfs_root *root, ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &old_roots, false); if (ret) { - ulist_free(old_roots); test_err("couldn't find old roots: %d", ret); return ret; } ret = insert_normal_tree_ref(root, nodesize, nodesize, 0, BTRFS_FS_TREE_OBJECTID); - if (ret) + if (ret) { + ulist_free(old_roots); return ret; + } ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &new_roots, false); if (ret) { ulist_free(old_roots); - ulist_free(new_roots); test_err("couldn't find old roots: %d", ret); return ret; } @@ -366,21 +368,21 @@ static int test_multiple_refs(struct btrfs_root *root, ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &old_roots, false); if (ret) { - ulist_free(old_roots); test_err("couldn't find old roots: %d", ret); return ret; } ret = add_tree_ref(root, nodesize, nodesize, 0, BTRFS_FIRST_FREE_OBJECTID); - if (ret) + if (ret) { + ulist_free(old_roots); return ret; + } ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &new_roots, false); if (ret) { ulist_free(old_roots); - ulist_free(new_roots); test_err("couldn't find old roots: %d", ret); return ret; } @@ -407,21 +409,21 @@ static int test_multiple_refs(struct btrfs_root *root, ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &old_roots, false); if (ret) { - ulist_free(old_roots); test_err("couldn't find old roots: %d", ret); return ret; } ret = remove_extent_ref(root, nodesize, nodesize, 0, BTRFS_FIRST_FREE_OBJECTID); - if (ret) + if (ret) { + ulist_free(old_roots); return ret; + } ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &new_roots, false); if (ret) { ulist_free(old_roots); - ulist_free(new_roots); test_err("couldn't find old roots: %d", ret); return ret; } diff --git a/fs/buffer.c b/fs/buffer.c index 029e806a85bd228308d46ede89dfc2b037f9090c..323dd9a0cbf4958ab1aee3b05d2357698331b9c3 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -2381,7 +2381,7 @@ int generic_cont_expand_simple(struct inode *inode, loff_t size) { struct address_space *mapping = inode->i_mapping; struct page *page; - void *fsdata; + void *fsdata = NULL; int err; err = inode_newsize_ok(inode, size); @@ -2407,7 +2407,7 @@ static int cont_expand_zero(struct file *file, struct address_space *mapping, struct inode *inode = mapping->host; unsigned int blocksize = i_blocksize(inode); struct page *page; - void *fsdata; + void *fsdata = NULL; pgoff_t index, curidx; loff_t curpos; unsigned zerofrom, offset, len; diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 76e43a487bc63230dc388c5385a863311396e9ad..51562d36fa83dde0905178a7cc3465dda4425dea 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -2294,6 +2294,7 @@ static int caps_are_flushed(struct inode *inode, u64 flush_tid) */ static int unsafe_request_wait(struct inode *inode) { + struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc; struct ceph_inode_info *ci = ceph_inode(inode); struct ceph_mds_request *req1 = NULL, *req2 = NULL; int ret, err = 0; @@ -2313,6 +2314,76 @@ static int unsafe_request_wait(struct inode *inode) } spin_unlock(&ci->i_unsafe_lock); + /* + * Trigger to flush the journal logs in all the relevant MDSes + * manually, or in the worst case we must wait at most 5 seconds + * to wait the journal logs to be flushed by the MDSes periodically. + */ + if (req1 || req2) { + struct ceph_mds_request *req; + struct ceph_mds_session **sessions; + struct ceph_mds_session *s; + unsigned int max_sessions; + int i; + + mutex_lock(&mdsc->mutex); + max_sessions = mdsc->max_sessions; + + sessions = kcalloc(max_sessions, sizeof(s), GFP_KERNEL); + if (!sessions) { + mutex_unlock(&mdsc->mutex); + err = -ENOMEM; + goto out; + } + + spin_lock(&ci->i_unsafe_lock); + if (req1) { + list_for_each_entry(req, &ci->i_unsafe_dirops, + r_unsafe_dir_item) { + s = req->r_session; + if (!s) + continue; + if (!sessions[s->s_mds]) { + s = ceph_get_mds_session(s); + sessions[s->s_mds] = s; + } + } + } + if (req2) { + list_for_each_entry(req, &ci->i_unsafe_iops, + r_unsafe_target_item) { + s = req->r_session; + if (!s) + continue; + if (!sessions[s->s_mds]) { + s = ceph_get_mds_session(s); + sessions[s->s_mds] = s; + } + } + } + spin_unlock(&ci->i_unsafe_lock); + + /* the auth MDS */ + spin_lock(&ci->i_ceph_lock); + if (ci->i_auth_cap) { + s = ci->i_auth_cap->session; + if (!sessions[s->s_mds]) + sessions[s->s_mds] = ceph_get_mds_session(s); + } + spin_unlock(&ci->i_ceph_lock); + mutex_unlock(&mdsc->mutex); + + /* send flush mdlog request to MDSes */ + for (i = 0; i < max_sessions; i++) { + s = sessions[i]; + if (s) { + send_flush_mdlog(s); + ceph_put_mds_session(s); + } + } + kfree(sessions); + } + dout("unsafe_request_wait %p wait on tid %llu %llu\n", inode, req1 ? req1->r_tid : 0ULL, req2 ? req2->r_tid : 0ULL); if (req1) { @@ -2320,15 +2391,19 @@ static int unsafe_request_wait(struct inode *inode) ceph_timeout_jiffies(req1->r_timeout)); if (ret) err = -EIO; - ceph_mdsc_put_request(req1); } if (req2) { ret = !wait_for_completion_timeout(&req2->r_safe_completion, ceph_timeout_jiffies(req2->r_timeout)); if (ret) err = -EIO; - ceph_mdsc_put_request(req2); } + +out: + if (req1) + ceph_mdsc_put_request(req1); + if (req2) + ceph_mdsc_put_request(req2); return err; } @@ -4310,33 +4385,9 @@ static void flush_dirty_session_caps(struct ceph_mds_session *s) dout("flush_dirty_caps done\n"); } -static void iterate_sessions(struct ceph_mds_client *mdsc, - void (*cb)(struct ceph_mds_session *)) -{ - int mds; - - mutex_lock(&mdsc->mutex); - for (mds = 0; mds < mdsc->max_sessions; ++mds) { - struct ceph_mds_session *s; - - if (!mdsc->sessions[mds]) - continue; - - s = ceph_get_mds_session(mdsc->sessions[mds]); - if (!s) - continue; - - mutex_unlock(&mdsc->mutex); - cb(s); - ceph_put_mds_session(s); - mutex_lock(&mdsc->mutex); - } - mutex_unlock(&mdsc->mutex); -} - void ceph_flush_dirty_caps(struct ceph_mds_client *mdsc) { - iterate_sessions(mdsc, flush_dirty_session_caps); + ceph_mdsc_iterate_sessions(mdsc, flush_dirty_session_caps, true); } void __ceph_touch_fmode(struct ceph_inode_info *ci, diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 6859967df2b192cdb4864e058add3e38cda9dabe..fa51872ff850482b19d291984ef51079e2141ffd 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -809,6 +809,33 @@ static void put_request_session(struct ceph_mds_request *req) } } +void ceph_mdsc_iterate_sessions(struct ceph_mds_client *mdsc, + void (*cb)(struct ceph_mds_session *), + bool check_state) +{ + int mds; + + mutex_lock(&mdsc->mutex); + for (mds = 0; mds < mdsc->max_sessions; ++mds) { + struct ceph_mds_session *s; + + s = __ceph_lookup_mds_session(mdsc, mds); + if (!s) + continue; + + if (check_state && !check_session_state(s)) { + ceph_put_mds_session(s); + continue; + } + + mutex_unlock(&mdsc->mutex); + cb(s); + ceph_put_mds_session(s); + mutex_lock(&mdsc->mutex); + } + mutex_unlock(&mdsc->mutex); +} + void ceph_mdsc_release_request(struct kref *kref) { struct ceph_mds_request *req = container_of(kref, @@ -1157,7 +1184,7 @@ random: /* * session messages */ -static struct ceph_msg *create_session_msg(u32 op, u64 seq) +struct ceph_msg *ceph_create_session_msg(u32 op, u64 seq) { struct ceph_msg *msg; struct ceph_mds_session_head *h; @@ -1165,7 +1192,8 @@ static struct ceph_msg *create_session_msg(u32 op, u64 seq) msg = ceph_msg_new(CEPH_MSG_CLIENT_SESSION, sizeof(*h), GFP_NOFS, false); if (!msg) { - pr_err("create_session_msg ENOMEM creating msg\n"); + pr_err("ENOMEM creating session %s msg\n", + ceph_session_op_name(op)); return NULL; } h = msg->front.iov_base; @@ -1299,7 +1327,7 @@ static struct ceph_msg *create_session_open_msg(struct ceph_mds_client *mdsc, u6 msg = ceph_msg_new(CEPH_MSG_CLIENT_SESSION, sizeof(*h) + extra_bytes, GFP_NOFS, false); if (!msg) { - pr_err("create_session_msg ENOMEM creating msg\n"); + pr_err("ENOMEM creating session open msg\n"); return ERR_PTR(-ENOMEM); } p = msg->front.iov_base; @@ -1833,8 +1861,8 @@ static int send_renew_caps(struct ceph_mds_client *mdsc, dout("send_renew_caps to mds%d (%s)\n", session->s_mds, ceph_mds_state_name(state)); - msg = create_session_msg(CEPH_SESSION_REQUEST_RENEWCAPS, - ++session->s_renew_seq); + msg = ceph_create_session_msg(CEPH_SESSION_REQUEST_RENEWCAPS, + ++session->s_renew_seq); if (!msg) return -ENOMEM; ceph_con_send(&session->s_con, msg); @@ -1848,7 +1876,7 @@ static int send_flushmsg_ack(struct ceph_mds_client *mdsc, dout("send_flushmsg_ack to mds%d (%s)s seq %lld\n", session->s_mds, ceph_session_state_name(session->s_state), seq); - msg = create_session_msg(CEPH_SESSION_FLUSHMSG_ACK, seq); + msg = ceph_create_session_msg(CEPH_SESSION_FLUSHMSG_ACK, seq); if (!msg) return -ENOMEM; ceph_con_send(&session->s_con, msg); @@ -1900,7 +1928,8 @@ static int request_close_session(struct ceph_mds_session *session) dout("request_close_session mds%d state %s seq %lld\n", session->s_mds, ceph_session_state_name(session->s_state), session->s_seq); - msg = create_session_msg(CEPH_SESSION_REQUEST_CLOSE, session->s_seq); + msg = ceph_create_session_msg(CEPH_SESSION_REQUEST_CLOSE, + session->s_seq); if (!msg) return -ENOMEM; ceph_con_send(&session->s_con, msg); @@ -4375,24 +4404,12 @@ void ceph_mdsc_lease_send_msg(struct ceph_mds_session *session, } /* - * lock unlock sessions, to wait ongoing session activities + * lock unlock the session, to wait ongoing session activities */ -static void lock_unlock_sessions(struct ceph_mds_client *mdsc) +static void lock_unlock_session(struct ceph_mds_session *s) { - int i; - - mutex_lock(&mdsc->mutex); - for (i = 0; i < mdsc->max_sessions; i++) { - struct ceph_mds_session *s = __ceph_lookup_mds_session(mdsc, i); - if (!s) - continue; - mutex_unlock(&mdsc->mutex); - mutex_lock(&s->s_mutex); - mutex_unlock(&s->s_mutex); - ceph_put_mds_session(s); - mutex_lock(&mdsc->mutex); - } - mutex_unlock(&mdsc->mutex); + mutex_lock(&s->s_mutex); + mutex_unlock(&s->s_mutex); } static void maybe_recover_session(struct ceph_mds_client *mdsc) @@ -4647,6 +4664,30 @@ static void wait_requests(struct ceph_mds_client *mdsc) dout("wait_requests done\n"); } +void send_flush_mdlog(struct ceph_mds_session *s) +{ + struct ceph_msg *msg; + + /* + * Pre-luminous MDS crashes when it sees an unknown session request + */ + if (!CEPH_HAVE_FEATURE(s->s_con.peer_features, SERVER_LUMINOUS)) + return; + + mutex_lock(&s->s_mutex); + dout("request mdlog flush to mds%d (%s)s seq %lld\n", s->s_mds, + ceph_session_state_name(s->s_state), s->s_seq); + msg = ceph_create_session_msg(CEPH_SESSION_REQUEST_FLUSH_MDLOG, + s->s_seq); + if (!msg) { + pr_err("failed to request mdlog flush to mds%d (%s) seq %lld\n", + s->s_mds, ceph_session_state_name(s->s_state), s->s_seq); + } else { + ceph_con_send(&s->s_con, msg); + } + mutex_unlock(&s->s_mutex); +} + /* * called before mount is ro, and before dentries are torn down. * (hmm, does this still race with new lookups?) @@ -4656,7 +4697,8 @@ void ceph_mdsc_pre_umount(struct ceph_mds_client *mdsc) dout("pre_umount\n"); mdsc->stopping = 1; - lock_unlock_sessions(mdsc); + ceph_mdsc_iterate_sessions(mdsc, send_flush_mdlog, true); + ceph_mdsc_iterate_sessions(mdsc, lock_unlock_session, false); ceph_flush_dirty_caps(mdsc); wait_requests(mdsc); diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index acf33d7192bb6e61267063fa54d7d8c4cb9219e1..a92e42e8a9f82f6194f940c2342522acaba29e7b 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -518,6 +518,11 @@ static inline void ceph_mdsc_put_request(struct ceph_mds_request *req) kref_put(&req->r_kref, ceph_mdsc_release_request); } +extern void send_flush_mdlog(struct ceph_mds_session *s); +extern void ceph_mdsc_iterate_sessions(struct ceph_mds_client *mdsc, + void (*cb)(struct ceph_mds_session *), + bool check_state); +extern struct ceph_msg *ceph_create_session_msg(u32 op, u64 seq); extern void __ceph_queue_cap_release(struct ceph_mds_session *session, struct ceph_cap *cap); extern void ceph_flush_cap_releases(struct ceph_mds_client *mdsc, diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c index 0369f672a76fb713996065ca9395e2078f5fb06e..734873be56a74f51b2cfc9f83f5194214d0d1037 100644 --- a/fs/ceph/snap.c +++ b/fs/ceph/snap.c @@ -697,9 +697,10 @@ int ceph_update_snap_trace(struct ceph_mds_client *mdsc, struct ceph_mds_snap_realm *ri; /* encoded */ __le64 *snaps; /* encoded */ __le64 *prior_parent_snaps; /* encoded */ - struct ceph_snap_realm *realm = NULL; + struct ceph_snap_realm *realm; struct ceph_snap_realm *first_realm = NULL; - int invalidate = 0; + struct ceph_snap_realm *realm_to_rebuild = NULL; + int rebuild_snapcs; int err = -ENOMEM; LIST_HEAD(dirty_realms); @@ -707,6 +708,8 @@ int ceph_update_snap_trace(struct ceph_mds_client *mdsc, dout("update_snap_trace deletion=%d\n", deletion); more: + realm = NULL; + rebuild_snapcs = 0; ceph_decode_need(&p, e, sizeof(*ri), bad); ri = p; p += sizeof(*ri); @@ -730,7 +733,7 @@ more: err = adjust_snap_realm_parent(mdsc, realm, le64_to_cpu(ri->parent)); if (err < 0) goto fail; - invalidate += err; + rebuild_snapcs += err; if (le64_to_cpu(ri->seq) > realm->seq) { dout("update_snap_trace updating %llx %p %lld -> %lld\n", @@ -755,22 +758,30 @@ more: if (realm->seq > mdsc->last_snap_seq) mdsc->last_snap_seq = realm->seq; - invalidate = 1; + rebuild_snapcs = 1; } else if (!realm->cached_context) { dout("update_snap_trace %llx %p seq %lld new\n", realm->ino, realm, realm->seq); - invalidate = 1; + rebuild_snapcs = 1; } else { dout("update_snap_trace %llx %p seq %lld unchanged\n", realm->ino, realm, realm->seq); } - dout("done with %llx %p, invalidated=%d, %p %p\n", realm->ino, - realm, invalidate, p, e); + dout("done with %llx %p, rebuild_snapcs=%d, %p %p\n", realm->ino, + realm, rebuild_snapcs, p, e); + + /* + * this will always track the uppest parent realm from which + * we need to rebuild the snapshot contexts _downward_ in + * hierarchy. + */ + if (rebuild_snapcs) + realm_to_rebuild = realm; - /* invalidate when we reach the _end_ (root) of the trace */ - if (invalidate && p >= e) - rebuild_snap_realms(realm, &dirty_realms); + /* rebuild_snapcs when we reach the _end_ (root) of the trace */ + if (realm_to_rebuild && p >= e) + rebuild_snap_realms(realm_to_rebuild, &dirty_realms); if (!first_realm) first_realm = realm; diff --git a/fs/ceph/strings.c b/fs/ceph/strings.c index 4a79f3632260e83a9f3169aea4c11da0119f8117..573bb9556fb56cbf16802d7770fcf22305bc5469 100644 --- a/fs/ceph/strings.c +++ b/fs/ceph/strings.c @@ -46,6 +46,7 @@ const char *ceph_session_op_name(int op) case CEPH_SESSION_FLUSHMSG_ACK: return "flushmsg_ack"; case CEPH_SESSION_FORCE_RO: return "force_ro"; case CEPH_SESSION_REJECT: return "reject"; + case CEPH_SESSION_REQUEST_FLUSH_MDLOG: return "flush_mdlog"; } return "???"; } diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 5a02c7adef090b491d5267c13135381ec9195bdd..b582dbf919e4e958fed2d022d64343f363637d2d 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -1221,8 +1221,11 @@ static ssize_t cifs_copy_file_range(struct file *src_file, loff_t off, ssize_t rc; struct cifsFileInfo *cfile = dst_file->private_data; - if (cfile->swapfile) - return -EOPNOTSUPP; + if (cfile->swapfile) { + rc = -EOPNOTSUPP; + free_xid(xid); + return rc; + } rc = cifs_file_copychunk_range(xid, src_file, off, dst_file, destoff, len, flags); diff --git a/fs/cifs/file.c b/fs/cifs/file.c index fafb69d338c26f8cd77ca6f9649da7ba4ab07781..144064dc0d38a892f1f209437fed85bba800dd38 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -1735,11 +1735,13 @@ int cifs_flock(struct file *file, int cmd, struct file_lock *fl) struct cifsFileInfo *cfile; __u32 type; - rc = -EACCES; xid = get_xid(); - if (!(fl->fl_flags & FL_FLOCK)) - return -ENOLCK; + if (!(fl->fl_flags & FL_FLOCK)) { + rc = -ENOLCK; + free_xid(xid); + return rc; + } cfile = (struct cifsFileInfo *)file->private_data; tcon = tlink_tcon(cfile->tlink); @@ -1758,8 +1760,9 @@ int cifs_flock(struct file *file, int cmd, struct file_lock *fl) * if no lock or unlock then nothing to do since we do not * know what it is */ + rc = -EOPNOTSUPP; free_xid(xid); - return -EOPNOTSUPP; + return rc; } rc = cifs_setlk(file, fl, type, wait_flag, posix_lck, lock, unlock, @@ -3936,6 +3939,15 @@ static ssize_t __cifs_readv( len = ctx->len; } + if (direct) { + rc = filemap_write_and_wait_range(file->f_inode->i_mapping, + offset, offset + len - 1); + if (rc) { + kref_put(&ctx->refcount, cifs_aio_ctx_release); + return -EAGAIN; + } + } + /* grab a lock here due to read response handlers can access ctx */ mutex_lock(&ctx->aio_mutex); diff --git a/fs/cifs/ioctl.c b/fs/cifs/ioctl.c index dcde44ff6cf9f3192e1fbb6fc63ecca8d142b5ef..e45598b6224277c7779e4625f0567b218ef63914 100644 --- a/fs/cifs/ioctl.c +++ b/fs/cifs/ioctl.c @@ -193,7 +193,7 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg) rc = put_user(ExtAttrBits & FS_FL_USER_VISIBLE, (int __user *)arg); - if (rc != EOPNOTSUPP) + if (rc != -EOPNOTSUPP) break; } #endif /* CONFIG_CIFS_POSIX */ @@ -222,7 +222,7 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg) * pSMBFile->fid.netfid, * extAttrBits, * &ExtAttrMask); - * if (rc != EOPNOTSUPP) + * if (rc != -EOPNOTSUPP) * break; */ diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c index d58c5ffeca0d97e51ac3611a354f913524613e67..cf6fd138d8d5c8f66b25017a0e0f6fb042615ddb 100644 --- a/fs/cifs/sess.c +++ b/fs/cifs/sess.c @@ -306,6 +306,7 @@ out: cifs_put_tcp_session(chan->server, 0); unload_nls(vol.local_nls); + free_xid(xid); return rc; } diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 11efd5289ec4338cd21f613a1e2ed65d8a3ebc43..72368b656b33ca67fe85f04321ebb03ecbfa5f3a 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -1256,6 +1256,8 @@ smb2_set_ea(const unsigned int xid, struct cifs_tcon *tcon, COMPOUND_FID, current->tgid, FILE_FULL_EA_INFORMATION, SMB2_O_INFO_FILE, 0, data, size); + if (rc) + goto sea_exit; smb2_set_next_command(tcon, &rqst[1]); smb2_set_related(&rqst[1]); @@ -1266,6 +1268,8 @@ smb2_set_ea(const unsigned int xid, struct cifs_tcon *tcon, rqst[2].rq_nvec = 1; rc = SMB2_close_init(tcon, server, &rqst[2], COMPOUND_FID, COMPOUND_FID, false); + if (rc) + goto sea_exit; smb2_set_related(&rqst[2]); rc = compound_send_recv(xid, ses, server, diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 7ee8abd1f79bed3676d4760208a4da08c524fa15..0c4a2474e75be92cf828217ec2712956fdcbca1d 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -1075,9 +1075,9 @@ int smb3_validate_negotiate(const unsigned int xid, struct cifs_tcon *tcon) pneg_inbuf->Dialects[0] = cpu_to_le16(server->vals->protocol_id); pneg_inbuf->DialectCount = cpu_to_le16(1); - /* structure is big enough for 3 dialects, sending only 1 */ + /* structure is big enough for 4 dialects, sending only 1 */ inbuflen = sizeof(*pneg_inbuf) - - sizeof(pneg_inbuf->Dialects[0]) * 2; + sizeof(pneg_inbuf->Dialects[0]) * 3; } rc = SMB2_ioctl(xid, tcon, NO_FILE_ID, NO_FILE_ID, @@ -2294,7 +2294,7 @@ create_sd_buf(umode_t mode, bool set_owner, unsigned int *len) unsigned int acelen, acl_size, ace_count; unsigned int owner_offset = 0; unsigned int group_offset = 0; - struct smb3_acl acl; + struct smb3_acl acl = {}; *len = roundup(sizeof(struct crt_sd_ctxt) + (sizeof(struct cifs_ace) * 4), 8); @@ -2367,6 +2367,7 @@ create_sd_buf(umode_t mode, bool set_owner, unsigned int *len) acl.AclRevision = ACL_REVISION; /* See 2.4.4.1 of MS-DTYP */ acl.AclSize = cpu_to_le16(acl_size); acl.AceCount = cpu_to_le16(ace_count); + /* acl.Sbz1 and Sbz2 MBZ so are not set here, but initialized above */ memcpy(aclptr, &acl, sizeof(struct smb3_acl)); buf->ccontext.DataLength = cpu_to_le32(ptr - (__u8 *)&buf->sd); diff --git a/fs/coredump.c b/fs/coredump.c index dc6c6271a0e6781804f3b0a246e215f2496b7be3..c2a2e050be3f290d8901dafa67afdf02076cb97c 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -520,7 +520,7 @@ static bool dump_interrupted(void) * but then we need to teach dump_write() to restart and clear * TIF_SIGPENDING. */ - return signal_pending(current); + return fatal_signal_pending(current) || freezing(current); } static void wait_for_dump_helpers(struct file *file) diff --git a/fs/crypto/fscrypt_private.h b/fs/crypto/fscrypt_private.h index bf75ecda9459f9b9c43ac7992c711b45ce7259b4..862e847c8ac52ebac3b7cdbc0196497c91640637 100644 --- a/fs/crypto/fscrypt_private.h +++ b/fs/crypto/fscrypt_private.h @@ -227,7 +227,7 @@ struct fscrypt_info { * will be NULL if the master key was found in a process-subscribed * keyring rather than in the filesystem-level keyring. */ - struct key *ci_master_key; + struct fscrypt_master_key *ci_master_key; /* * Link in list of inodes that were unlocked with the master key. @@ -470,6 +470,40 @@ struct fscrypt_master_key_secret { */ struct fscrypt_master_key { + /* + * Back-pointer to the super_block of the filesystem to which this + * master key has been added. Only valid if ->mk_active_refs > 0. + */ + struct super_block *mk_sb; + + /* + * Link in ->mk_sb->s_master_keys->key_hashtable. + * Only valid if ->mk_active_refs > 0. + */ + struct hlist_node mk_node; + + /* Semaphore that protects ->mk_secret and ->mk_users */ + struct rw_semaphore mk_sem; + + /* + * Active and structural reference counts. An active ref guarantees + * that the struct continues to exist, continues to be in the keyring + * ->mk_sb->s_master_keys, and that any embedded subkeys (e.g. + * ->mk_direct_keys) that have been prepared continue to exist. + * A structural ref only guarantees that the struct continues to exist. + * + * There is one active ref associated with ->mk_secret being present, + * and one active ref for each inode in ->mk_decrypted_inodes. + * + * There is one structural ref associated with the active refcount being + * nonzero. Finding a key in the keyring also takes a structural ref, + * which is then held temporarily while the key is operated on. + */ + refcount_t mk_active_refs; + refcount_t mk_struct_refs; + + struct rcu_head mk_rcu_head; + /* * The secret key material. After FS_IOC_REMOVE_ENCRYPTION_KEY is * executed, this is wiped and no new inodes can be unlocked with this @@ -478,7 +512,10 @@ struct fscrypt_master_key { * FS_IOC_REMOVE_ENCRYPTION_KEY can be retried, or * FS_IOC_ADD_ENCRYPTION_KEY can add the secret again. * - * Locking: protected by this master key's key->sem. + * While ->mk_secret is present, one ref in ->mk_active_refs is held. + * + * Locking: protected by ->mk_sem. The manipulation of ->mk_active_refs + * associated with this field is protected by ->mk_sem as well. */ struct fscrypt_master_key_secret mk_secret; @@ -499,22 +536,12 @@ struct fscrypt_master_key { * * This is NULL for v1 policy keys; those can only be added by root. * - * Locking: in addition to this keyring's own semaphore, this is - * protected by this master key's key->sem, so we can do atomic - * search+insert. It can also be searched without taking any locks, but - * in that case the returned key may have already been removed. + * Locking: protected by ->mk_sem. (We don't just rely on the keyrings + * subsystem semaphore ->mk_users->sem, as we need support for atomic + * search+insert along with proper synchronization with ->mk_secret.) */ struct key *mk_users; - /* - * Length of ->mk_decrypted_inodes, plus one if mk_secret is present. - * Once this goes to 0, the master key is removed from ->s_master_keys. - * The 'struct fscrypt_master_key' will continue to live as long as the - * 'struct key' whose payload it is, but we won't let this reference - * count rise again. - */ - refcount_t mk_refcount; - /* * List of inodes that were unlocked using this key. This allows the * inodes to be evicted efficiently if the key is removed. @@ -540,10 +567,10 @@ static inline bool is_master_key_secret_present(const struct fscrypt_master_key_secret *secret) { /* - * The READ_ONCE() is only necessary for fscrypt_drop_inode() and - * fscrypt_key_describe(). These run in atomic context, so they can't - * take the key semaphore and thus 'secret' can change concurrently - * which would be a data race. But they only need to know whether the + * The READ_ONCE() is only necessary for fscrypt_drop_inode(). + * fscrypt_drop_inode() runs in atomic context, so it can't take the key + * semaphore and thus 'secret' can change concurrently which would be a + * data race. But fscrypt_drop_inode() only need to know whether the * secret *was* present at the time of check, so READ_ONCE() suffices. */ return READ_ONCE(secret->size) != 0; @@ -572,7 +599,11 @@ static inline int master_key_spec_len(const struct fscrypt_key_specifier *spec) return 0; } -struct key * +void fscrypt_put_master_key(struct fscrypt_master_key *mk); + +void fscrypt_put_master_key_activeref(struct fscrypt_master_key *mk); + +struct fscrypt_master_key * fscrypt_find_master_key(struct super_block *sb, const struct fscrypt_key_specifier *mk_spec); diff --git a/fs/crypto/hooks.c b/fs/crypto/hooks.c index af74599ae1cf0677111a228d4438174c2c595569..be5c650e49573a7cfb950ce6970a926c0f9e1a96 100644 --- a/fs/crypto/hooks.c +++ b/fs/crypto/hooks.c @@ -5,8 +5,6 @@ * Encryption hooks for higher-level filesystem operations. */ -#include - #include "fscrypt_private.h" /** @@ -142,7 +140,6 @@ int fscrypt_prepare_setflags(struct inode *inode, unsigned int oldflags, unsigned int flags) { struct fscrypt_info *ci; - struct key *key; struct fscrypt_master_key *mk; int err; @@ -158,14 +155,13 @@ int fscrypt_prepare_setflags(struct inode *inode, ci = inode->i_crypt_info; if (ci->ci_policy.version != FSCRYPT_POLICY_V2) return -EINVAL; - key = ci->ci_master_key; - mk = key->payload.data[0]; - down_read(&key->sem); + mk = ci->ci_master_key; + down_read(&mk->mk_sem); if (is_master_key_secret_present(&mk->mk_secret)) err = fscrypt_derive_dirhash_key(ci, mk); else err = -ENOKEY; - up_read(&key->sem); + up_read(&mk->mk_sem); return err; } return 0; diff --git a/fs/crypto/keyring.c b/fs/crypto/keyring.c index c492deaed9d642c1b306a4bcd68bb04d7a9609e9..eb7b9040d267180c921b3fffe2ab3daf9ca8835f 100644 --- a/fs/crypto/keyring.c +++ b/fs/crypto/keyring.c @@ -18,6 +18,7 @@ * information about these ioctls. */ +#include #include #include #include @@ -25,6 +26,18 @@ #include "fscrypt_private.h" +/* The master encryption keys for a filesystem (->s_master_keys) */ +struct fscrypt_keyring { + /* + * Lock that protects ->key_hashtable. It does *not* protect the + * fscrypt_master_key structs themselves. + */ + spinlock_t lock; + + /* Hash table that maps fscrypt_key_specifier to fscrypt_master_key */ + struct hlist_head key_hashtable[128]; +}; + static void wipe_master_key_secret(struct fscrypt_master_key_secret *secret) { fscrypt_destroy_hkdf(&secret->hkdf); @@ -38,20 +51,70 @@ static void move_master_key_secret(struct fscrypt_master_key_secret *dst, memzero_explicit(src, sizeof(*src)); } -static void free_master_key(struct fscrypt_master_key *mk) +static void fscrypt_free_master_key(struct rcu_head *head) +{ + struct fscrypt_master_key *mk = + container_of(head, struct fscrypt_master_key, mk_rcu_head); + /* + * The master key secret and any embedded subkeys should have already + * been wiped when the last active reference to the fscrypt_master_key + * struct was dropped; doing it here would be unnecessarily late. + * Nevertheless, use kfree_sensitive() in case anything was missed. + */ + kfree_sensitive(mk); +} + +void fscrypt_put_master_key(struct fscrypt_master_key *mk) +{ + if (!refcount_dec_and_test(&mk->mk_struct_refs)) + return; + /* + * No structural references left, so free ->mk_users, and also free the + * fscrypt_master_key struct itself after an RCU grace period ensures + * that concurrent keyring lookups can no longer find it. + */ + WARN_ON(refcount_read(&mk->mk_active_refs) != 0); + key_put(mk->mk_users); + mk->mk_users = NULL; + call_rcu(&mk->mk_rcu_head, fscrypt_free_master_key); +} + +void fscrypt_put_master_key_activeref(struct fscrypt_master_key *mk) { + struct super_block *sb = mk->mk_sb; + struct fscrypt_keyring *keyring = sb->s_master_keys; size_t i; - wipe_master_key_secret(&mk->mk_secret); + if (!refcount_dec_and_test(&mk->mk_active_refs)) + return; + /* + * No active references left, so complete the full removal of this + * fscrypt_master_key struct by removing it from the keyring and + * destroying any subkeys embedded in it. + */ + + spin_lock(&keyring->lock); + hlist_del_rcu(&mk->mk_node); + spin_unlock(&keyring->lock); + + /* + * ->mk_active_refs == 0 implies that ->mk_secret is not present and + * that ->mk_decrypted_inodes is empty. + */ + WARN_ON(is_master_key_secret_present(&mk->mk_secret)); + WARN_ON(!list_empty(&mk->mk_decrypted_inodes)); for (i = 0; i <= FSCRYPT_MODE_MAX; i++) { fscrypt_destroy_prepared_key(&mk->mk_direct_keys[i]); fscrypt_destroy_prepared_key(&mk->mk_iv_ino_lblk_64_keys[i]); fscrypt_destroy_prepared_key(&mk->mk_iv_ino_lblk_32_keys[i]); } + memzero_explicit(&mk->mk_ino_hash_key, + sizeof(mk->mk_ino_hash_key)); + mk->mk_ino_hash_key_initialized = false; - key_put(mk->mk_users); - kfree_sensitive(mk); + /* Drop the structural ref associated with the active refs. */ + fscrypt_put_master_key(mk); } static inline bool valid_key_spec(const struct fscrypt_key_specifier *spec) @@ -61,44 +124,6 @@ static inline bool valid_key_spec(const struct fscrypt_key_specifier *spec) return master_key_spec_len(spec) != 0; } -static int fscrypt_key_instantiate(struct key *key, - struct key_preparsed_payload *prep) -{ - key->payload.data[0] = (struct fscrypt_master_key *)prep->data; - return 0; -} - -static void fscrypt_key_destroy(struct key *key) -{ - free_master_key(key->payload.data[0]); -} - -static void fscrypt_key_describe(const struct key *key, struct seq_file *m) -{ - seq_puts(m, key->description); - - if (key_is_positive(key)) { - const struct fscrypt_master_key *mk = key->payload.data[0]; - - if (!is_master_key_secret_present(&mk->mk_secret)) - seq_puts(m, ": secret removed"); - } -} - -/* - * Type of key in ->s_master_keys. Each key of this type represents a master - * key which has been added to the filesystem. Its payload is a - * 'struct fscrypt_master_key'. The "." prefix in the key type name prevents - * users from adding keys of this type via the keyrings syscalls rather than via - * the intended method of FS_IOC_ADD_ENCRYPTION_KEY. - */ -static struct key_type key_type_fscrypt = { - .name = "._fscrypt", - .instantiate = fscrypt_key_instantiate, - .destroy = fscrypt_key_destroy, - .describe = fscrypt_key_describe, -}; - static int fscrypt_user_key_instantiate(struct key *key, struct key_preparsed_payload *prep) { @@ -131,32 +156,6 @@ static struct key_type key_type_fscrypt_user = { .describe = fscrypt_user_key_describe, }; -/* Search ->s_master_keys or ->mk_users */ -static struct key *search_fscrypt_keyring(struct key *keyring, - struct key_type *type, - const char *description) -{ - /* - * We need to mark the keyring reference as "possessed" so that we - * acquire permission to search it, via the KEY_POS_SEARCH permission. - */ - key_ref_t keyref = make_key_ref(keyring, true /* possessed */); - - keyref = keyring_search(keyref, type, description, false); - if (IS_ERR(keyref)) { - if (PTR_ERR(keyref) == -EAGAIN || /* not found */ - PTR_ERR(keyref) == -EKEYREVOKED) /* recently invalidated */ - keyref = ERR_PTR(-ENOKEY); - return ERR_CAST(keyref); - } - return key_ref_to_ptr(keyref); -} - -#define FSCRYPT_FS_KEYRING_DESCRIPTION_SIZE \ - (CONST_STRLEN("fscrypt-") + sizeof_field(struct super_block, s_id)) - -#define FSCRYPT_MK_DESCRIPTION_SIZE (2 * FSCRYPT_KEY_IDENTIFIER_SIZE + 1) - #define FSCRYPT_MK_USERS_DESCRIPTION_SIZE \ (CONST_STRLEN("fscrypt-") + 2 * FSCRYPT_KEY_IDENTIFIER_SIZE + \ CONST_STRLEN("-users") + 1) @@ -164,21 +163,6 @@ static struct key *search_fscrypt_keyring(struct key *keyring, #define FSCRYPT_MK_USER_DESCRIPTION_SIZE \ (2 * FSCRYPT_KEY_IDENTIFIER_SIZE + CONST_STRLEN(".uid.") + 10 + 1) -static void format_fs_keyring_description( - char description[FSCRYPT_FS_KEYRING_DESCRIPTION_SIZE], - const struct super_block *sb) -{ - sprintf(description, "fscrypt-%s", sb->s_id); -} - -static void format_mk_description( - char description[FSCRYPT_MK_DESCRIPTION_SIZE], - const struct fscrypt_key_specifier *mk_spec) -{ - sprintf(description, "%*phN", - master_key_spec_len(mk_spec), (u8 *)&mk_spec->u); -} - static void format_mk_users_keyring_description( char description[FSCRYPT_MK_USERS_DESCRIPTION_SIZE], const u8 mk_identifier[FSCRYPT_KEY_IDENTIFIER_SIZE]) @@ -199,20 +183,15 @@ static void format_mk_user_description( /* Create ->s_master_keys if needed. Synchronized by fscrypt_add_key_mutex. */ static int allocate_filesystem_keyring(struct super_block *sb) { - char description[FSCRYPT_FS_KEYRING_DESCRIPTION_SIZE]; - struct key *keyring; + struct fscrypt_keyring *keyring; if (sb->s_master_keys) return 0; - format_fs_keyring_description(description, sb); - keyring = keyring_alloc(description, GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, - current_cred(), KEY_POS_SEARCH | - KEY_USR_SEARCH | KEY_USR_READ | KEY_USR_VIEW, - KEY_ALLOC_NOT_IN_QUOTA, NULL, NULL); - if (IS_ERR(keyring)) - return PTR_ERR(keyring); - + keyring = kzalloc(sizeof(*keyring), GFP_KERNEL); + if (!keyring) + return -ENOMEM; + spin_lock_init(&keyring->lock); /* * Pairs with the smp_load_acquire() in fscrypt_find_master_key(). * I.e., here we publish ->s_master_keys with a RELEASE barrier so that @@ -222,21 +201,80 @@ static int allocate_filesystem_keyring(struct super_block *sb) return 0; } -void fscrypt_sb_free(struct super_block *sb) +/* + * Release all encryption keys that have been added to the filesystem, along + * with the keyring that contains them. + * + * This is called at unmount time. The filesystem's underlying block device(s) + * are still available at this time; this is important because after user file + * accesses have been allowed, this function may need to evict keys from the + * keyslots of an inline crypto engine, which requires the block device(s). + * + * This is also called when the super_block is being freed. This is needed to + * avoid a memory leak if mounting fails after the "test_dummy_encryption" + * option was processed, as in that case the unmount-time call isn't made. + */ +void fscrypt_destroy_keyring(struct super_block *sb) { - key_put(sb->s_master_keys); + struct fscrypt_keyring *keyring = sb->s_master_keys; + size_t i; + + if (!keyring) + return; + + for (i = 0; i < ARRAY_SIZE(keyring->key_hashtable); i++) { + struct hlist_head *bucket = &keyring->key_hashtable[i]; + struct fscrypt_master_key *mk; + struct hlist_node *tmp; + + hlist_for_each_entry_safe(mk, tmp, bucket, mk_node) { + /* + * Since all inodes were already evicted, every key + * remaining in the keyring should have an empty inode + * list, and should only still be in the keyring due to + * the single active ref associated with ->mk_secret. + * There should be no structural refs beyond the one + * associated with the active ref. + */ + WARN_ON(refcount_read(&mk->mk_active_refs) != 1); + WARN_ON(refcount_read(&mk->mk_struct_refs) != 1); + WARN_ON(!is_master_key_secret_present(&mk->mk_secret)); + wipe_master_key_secret(&mk->mk_secret); + fscrypt_put_master_key_activeref(mk); + } + } + kfree_sensitive(keyring); sb->s_master_keys = NULL; } +static struct hlist_head * +fscrypt_mk_hash_bucket(struct fscrypt_keyring *keyring, + const struct fscrypt_key_specifier *mk_spec) +{ + /* + * Since key specifiers should be "random" values, it is sufficient to + * use a trivial hash function that just takes the first several bits of + * the key specifier. + */ + unsigned long i = get_unaligned((unsigned long *)&mk_spec->u); + + return &keyring->key_hashtable[i % ARRAY_SIZE(keyring->key_hashtable)]; +} + /* - * Find the specified master key in ->s_master_keys. - * Returns ERR_PTR(-ENOKEY) if not found. + * Find the specified master key struct in ->s_master_keys and take a structural + * ref to it. The structural ref guarantees that the key struct continues to + * exist, but it does *not* guarantee that ->s_master_keys continues to contain + * the key struct. The structural ref needs to be dropped by + * fscrypt_put_master_key(). Returns NULL if the key struct is not found. */ -struct key *fscrypt_find_master_key(struct super_block *sb, - const struct fscrypt_key_specifier *mk_spec) +struct fscrypt_master_key * +fscrypt_find_master_key(struct super_block *sb, + const struct fscrypt_key_specifier *mk_spec) { - struct key *keyring; - char description[FSCRYPT_MK_DESCRIPTION_SIZE]; + struct fscrypt_keyring *keyring; + struct hlist_head *bucket; + struct fscrypt_master_key *mk; /* * Pairs with the smp_store_release() in allocate_filesystem_keyring(). @@ -246,10 +284,38 @@ struct key *fscrypt_find_master_key(struct super_block *sb, */ keyring = smp_load_acquire(&sb->s_master_keys); if (keyring == NULL) - return ERR_PTR(-ENOKEY); /* No keyring yet, so no keys yet. */ - - format_mk_description(description, mk_spec); - return search_fscrypt_keyring(keyring, &key_type_fscrypt, description); + return NULL; /* No keyring yet, so no keys yet. */ + + bucket = fscrypt_mk_hash_bucket(keyring, mk_spec); + rcu_read_lock(); + switch (mk_spec->type) { + case FSCRYPT_KEY_SPEC_TYPE_DESCRIPTOR: + hlist_for_each_entry_rcu(mk, bucket, mk_node) { + if (mk->mk_spec.type == + FSCRYPT_KEY_SPEC_TYPE_DESCRIPTOR && + memcmp(mk->mk_spec.u.descriptor, + mk_spec->u.descriptor, + FSCRYPT_KEY_DESCRIPTOR_SIZE) == 0 && + refcount_inc_not_zero(&mk->mk_struct_refs)) + goto out; + } + break; + case FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER: + hlist_for_each_entry_rcu(mk, bucket, mk_node) { + if (mk->mk_spec.type == + FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER && + memcmp(mk->mk_spec.u.identifier, + mk_spec->u.identifier, + FSCRYPT_KEY_IDENTIFIER_SIZE) == 0 && + refcount_inc_not_zero(&mk->mk_struct_refs)) + goto out; + } + break; + } + mk = NULL; +out: + rcu_read_unlock(); + return mk; } static int allocate_master_key_users_keyring(struct fscrypt_master_key *mk) @@ -277,17 +343,30 @@ static int allocate_master_key_users_keyring(struct fscrypt_master_key *mk) static struct key *find_master_key_user(struct fscrypt_master_key *mk) { char description[FSCRYPT_MK_USER_DESCRIPTION_SIZE]; + key_ref_t keyref; format_mk_user_description(description, mk->mk_spec.u.identifier); - return search_fscrypt_keyring(mk->mk_users, &key_type_fscrypt_user, - description); + + /* + * We need to mark the keyring reference as "possessed" so that we + * acquire permission to search it, via the KEY_POS_SEARCH permission. + */ + keyref = keyring_search(make_key_ref(mk->mk_users, true /*possessed*/), + &key_type_fscrypt_user, description, false); + if (IS_ERR(keyref)) { + if (PTR_ERR(keyref) == -EAGAIN || /* not found */ + PTR_ERR(keyref) == -EKEYREVOKED) /* recently invalidated */ + keyref = ERR_PTR(-ENOKEY); + return ERR_CAST(keyref); + } + return key_ref_to_ptr(keyref); } /* * Give the current user a "key" in ->mk_users. This charges the user's quota * and marks the master key as added by the current user, so that it cannot be - * removed by another user with the key. Either the master key's key->sem must - * be held for write, or the master key must be still undergoing initialization. + * removed by another user with the key. Either ->mk_sem must be held for + * write, or the master key must be still undergoing initialization. */ static int add_master_key_user(struct fscrypt_master_key *mk) { @@ -309,7 +388,7 @@ static int add_master_key_user(struct fscrypt_master_key *mk) /* * Remove the current user's "key" from ->mk_users. - * The master key's key->sem must be held for write. + * ->mk_sem must be held for write. * * Returns 0 if removed, -ENOKEY if not found, or another -errno code. */ @@ -327,63 +406,49 @@ static int remove_master_key_user(struct fscrypt_master_key *mk) } /* - * Allocate a new fscrypt_master_key which contains the given secret, set it as - * the payload of a new 'struct key' of type fscrypt, and link the 'struct key' - * into the given keyring. Synchronized by fscrypt_add_key_mutex. + * Allocate a new fscrypt_master_key, transfer the given secret over to it, and + * insert it into sb->s_master_keys. */ -static int add_new_master_key(struct fscrypt_master_key_secret *secret, - const struct fscrypt_key_specifier *mk_spec, - struct key *keyring) +static int add_new_master_key(struct super_block *sb, + struct fscrypt_master_key_secret *secret, + const struct fscrypt_key_specifier *mk_spec) { + struct fscrypt_keyring *keyring = sb->s_master_keys; struct fscrypt_master_key *mk; - char description[FSCRYPT_MK_DESCRIPTION_SIZE]; - struct key *key; int err; mk = kzalloc(sizeof(*mk), GFP_KERNEL); if (!mk) return -ENOMEM; + mk->mk_sb = sb; + init_rwsem(&mk->mk_sem); + refcount_set(&mk->mk_struct_refs, 1); mk->mk_spec = *mk_spec; - move_master_key_secret(&mk->mk_secret, secret); - - refcount_set(&mk->mk_refcount, 1); /* secret is present */ INIT_LIST_HEAD(&mk->mk_decrypted_inodes); spin_lock_init(&mk->mk_decrypted_inodes_lock); if (mk_spec->type == FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER) { err = allocate_master_key_users_keyring(mk); if (err) - goto out_free_mk; + goto out_put; err = add_master_key_user(mk); if (err) - goto out_free_mk; + goto out_put; } - /* - * Note that we don't charge this key to anyone's quota, since when - * ->mk_users is in use those keys are charged instead, and otherwise - * (when ->mk_users isn't in use) only root can add these keys. - */ - format_mk_description(description, mk_spec); - key = key_alloc(&key_type_fscrypt, description, - GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, current_cred(), - KEY_POS_SEARCH | KEY_USR_SEARCH | KEY_USR_VIEW, - KEY_ALLOC_NOT_IN_QUOTA, NULL); - if (IS_ERR(key)) { - err = PTR_ERR(key); - goto out_free_mk; - } - err = key_instantiate_and_link(key, mk, sizeof(*mk), keyring, NULL); - key_put(key); - if (err) - goto out_free_mk; + move_master_key_secret(&mk->mk_secret, secret); + refcount_set(&mk->mk_active_refs, 1); /* ->mk_secret is present */ + spin_lock(&keyring->lock); + hlist_add_head_rcu(&mk->mk_node, + fscrypt_mk_hash_bucket(keyring, mk_spec)); + spin_unlock(&keyring->lock); return 0; -out_free_mk: - free_master_key(mk); +out_put: + fscrypt_put_master_key(mk); return err; } @@ -392,42 +457,34 @@ out_free_mk: static int add_existing_master_key(struct fscrypt_master_key *mk, struct fscrypt_master_key_secret *secret) { - struct key *mk_user; - bool rekey; int err; /* * If the current user is already in ->mk_users, then there's nothing to - * do. (Not applicable for v1 policy keys, which have NULL ->mk_users.) + * do. Otherwise, we need to add the user to ->mk_users. (Neither is + * applicable for v1 policy keys, which have NULL ->mk_users.) */ if (mk->mk_users) { - mk_user = find_master_key_user(mk); + struct key *mk_user = find_master_key_user(mk); + if (mk_user != ERR_PTR(-ENOKEY)) { if (IS_ERR(mk_user)) return PTR_ERR(mk_user); key_put(mk_user); return 0; } - } - - /* If we'll be re-adding ->mk_secret, try to take the reference. */ - rekey = !is_master_key_secret_present(&mk->mk_secret); - if (rekey && !refcount_inc_not_zero(&mk->mk_refcount)) - return KEY_DEAD; - - /* Add the current user to ->mk_users, if applicable. */ - if (mk->mk_users) { err = add_master_key_user(mk); - if (err) { - if (rekey && refcount_dec_and_test(&mk->mk_refcount)) - return KEY_DEAD; + if (err) return err; - } } /* Re-add the secret if needed. */ - if (rekey) + if (!is_master_key_secret_present(&mk->mk_secret)) { + if (!refcount_inc_not_zero(&mk->mk_active_refs)) + return KEY_DEAD; move_master_key_secret(&mk->mk_secret, secret); + } + return 0; } @@ -436,38 +493,36 @@ static int do_add_master_key(struct super_block *sb, const struct fscrypt_key_specifier *mk_spec) { static DEFINE_MUTEX(fscrypt_add_key_mutex); - struct key *key; + struct fscrypt_master_key *mk; int err; mutex_lock(&fscrypt_add_key_mutex); /* serialize find + link */ -retry: - key = fscrypt_find_master_key(sb, mk_spec); - if (IS_ERR(key)) { - err = PTR_ERR(key); - if (err != -ENOKEY) - goto out_unlock; + + mk = fscrypt_find_master_key(sb, mk_spec); + if (!mk) { /* Didn't find the key in ->s_master_keys. Add it. */ err = allocate_filesystem_keyring(sb); - if (err) - goto out_unlock; - err = add_new_master_key(secret, mk_spec, sb->s_master_keys); + if (!err) + err = add_new_master_key(sb, secret, mk_spec); } else { /* * Found the key in ->s_master_keys. Re-add the secret if * needed, and add the user to ->mk_users if needed. */ - down_write(&key->sem); - err = add_existing_master_key(key->payload.data[0], secret); - up_write(&key->sem); + down_write(&mk->mk_sem); + err = add_existing_master_key(mk, secret); + up_write(&mk->mk_sem); if (err == KEY_DEAD) { - /* Key being removed or needs to be removed */ - key_invalidate(key); - key_put(key); - goto retry; + /* + * We found a key struct, but it's already been fully + * removed. Ignore the old struct and add a new one. + * fscrypt_add_key_mutex means we don't need to worry + * about concurrent adds. + */ + err = add_new_master_key(sb, secret, mk_spec); } - key_put(key); + fscrypt_put_master_key(mk); } -out_unlock: mutex_unlock(&fscrypt_add_key_mutex); return err; } @@ -761,19 +816,19 @@ int fscrypt_verify_key_added(struct super_block *sb, const u8 identifier[FSCRYPT_KEY_IDENTIFIER_SIZE]) { struct fscrypt_key_specifier mk_spec; - struct key *key, *mk_user; struct fscrypt_master_key *mk; + struct key *mk_user; int err; mk_spec.type = FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER; memcpy(mk_spec.u.identifier, identifier, FSCRYPT_KEY_IDENTIFIER_SIZE); - key = fscrypt_find_master_key(sb, &mk_spec); - if (IS_ERR(key)) { - err = PTR_ERR(key); + mk = fscrypt_find_master_key(sb, &mk_spec); + if (!mk) { + err = -ENOKEY; goto out; } - mk = key->payload.data[0]; + down_read(&mk->mk_sem); mk_user = find_master_key_user(mk); if (IS_ERR(mk_user)) { err = PTR_ERR(mk_user); @@ -781,7 +836,8 @@ int fscrypt_verify_key_added(struct super_block *sb, key_put(mk_user); err = 0; } - key_put(key); + up_read(&mk->mk_sem); + fscrypt_put_master_key(mk); out: if (err == -ENOKEY && capable(CAP_FOWNER)) err = 0; @@ -943,11 +999,10 @@ static int do_remove_key(struct file *filp, void __user *_uarg, bool all_users) struct super_block *sb = file_inode(filp)->i_sb; struct fscrypt_remove_key_arg __user *uarg = _uarg; struct fscrypt_remove_key_arg arg; - struct key *key; struct fscrypt_master_key *mk; u32 status_flags = 0; int err; - bool dead; + bool inodes_remain; if (copy_from_user(&arg, uarg, sizeof(arg))) return -EFAULT; @@ -967,12 +1022,10 @@ static int do_remove_key(struct file *filp, void __user *_uarg, bool all_users) return -EACCES; /* Find the key being removed. */ - key = fscrypt_find_master_key(sb, &arg.key_spec); - if (IS_ERR(key)) - return PTR_ERR(key); - mk = key->payload.data[0]; - - down_write(&key->sem); + mk = fscrypt_find_master_key(sb, &arg.key_spec); + if (!mk) + return -ENOKEY; + down_write(&mk->mk_sem); /* If relevant, remove current user's (or all users) claim to the key */ if (mk->mk_users && mk->mk_users->keys.nr_leaves_on_tree != 0) { @@ -981,7 +1034,7 @@ static int do_remove_key(struct file *filp, void __user *_uarg, bool all_users) else err = remove_master_key_user(mk); if (err) { - up_write(&key->sem); + up_write(&mk->mk_sem); goto out_put_key; } if (mk->mk_users->keys.nr_leaves_on_tree != 0) { @@ -993,26 +1046,22 @@ static int do_remove_key(struct file *filp, void __user *_uarg, bool all_users) status_flags |= FSCRYPT_KEY_REMOVAL_STATUS_FLAG_OTHER_USERS; err = 0; - up_write(&key->sem); + up_write(&mk->mk_sem); goto out_put_key; } } /* No user claims remaining. Go ahead and wipe the secret. */ - dead = false; + err = -ENOKEY; if (is_master_key_secret_present(&mk->mk_secret)) { wipe_master_key_secret(&mk->mk_secret); - dead = refcount_dec_and_test(&mk->mk_refcount); - } - up_write(&key->sem); - if (dead) { - /* - * No inodes reference the key, and we wiped the secret, so the - * key object is free to be removed from the keyring. - */ - key_invalidate(key); + fscrypt_put_master_key_activeref(mk); err = 0; - } else { + } + inodes_remain = refcount_read(&mk->mk_active_refs) > 0; + up_write(&mk->mk_sem); + + if (inodes_remain) { /* Some inodes still reference this key; try to evict them. */ err = try_to_lock_encrypted_files(sb, mk); if (err == -EBUSY) { @@ -1028,7 +1077,7 @@ static int do_remove_key(struct file *filp, void __user *_uarg, bool all_users) * has been fully removed including all files locked. */ out_put_key: - key_put(key); + fscrypt_put_master_key(mk); if (err == 0) err = put_user(status_flags, &uarg->removal_status_flags); return err; @@ -1075,7 +1124,6 @@ int fscrypt_ioctl_get_key_status(struct file *filp, void __user *uarg) { struct super_block *sb = file_inode(filp)->i_sb; struct fscrypt_get_key_status_arg arg; - struct key *key; struct fscrypt_master_key *mk; int err; @@ -1092,19 +1140,18 @@ int fscrypt_ioctl_get_key_status(struct file *filp, void __user *uarg) arg.user_count = 0; memset(arg.__out_reserved, 0, sizeof(arg.__out_reserved)); - key = fscrypt_find_master_key(sb, &arg.key_spec); - if (IS_ERR(key)) { - if (key != ERR_PTR(-ENOKEY)) - return PTR_ERR(key); + mk = fscrypt_find_master_key(sb, &arg.key_spec); + if (!mk) { arg.status = FSCRYPT_KEY_STATUS_ABSENT; err = 0; goto out; } - mk = key->payload.data[0]; - down_read(&key->sem); + down_read(&mk->mk_sem); if (!is_master_key_secret_present(&mk->mk_secret)) { - arg.status = FSCRYPT_KEY_STATUS_INCOMPLETELY_REMOVED; + arg.status = refcount_read(&mk->mk_active_refs) > 0 ? + FSCRYPT_KEY_STATUS_INCOMPLETELY_REMOVED : + FSCRYPT_KEY_STATUS_ABSENT /* raced with full removal */; err = 0; goto out_release_key; } @@ -1126,8 +1173,8 @@ int fscrypt_ioctl_get_key_status(struct file *filp, void __user *uarg) } err = 0; out_release_key: - up_read(&key->sem); - key_put(key); + up_read(&mk->mk_sem); + fscrypt_put_master_key(mk); out: if (!err && copy_to_user(uarg, &arg, sizeof(arg))) err = -EFAULT; @@ -1139,13 +1186,9 @@ int __init fscrypt_init_keyring(void) { int err; - err = register_key_type(&key_type_fscrypt); - if (err) - return err; - err = register_key_type(&key_type_fscrypt_user); if (err) - goto err_unregister_fscrypt; + return err; err = register_key_type(&key_type_fscrypt_provisioning); if (err) @@ -1155,7 +1198,5 @@ int __init fscrypt_init_keyring(void) err_unregister_fscrypt_user: unregister_key_type(&key_type_fscrypt_user); -err_unregister_fscrypt: - unregister_key_type(&key_type_fscrypt); return err; } diff --git a/fs/crypto/keysetup.c b/fs/crypto/keysetup.c index bec2915effe587a3d0583fd5ba737b8aec7b1e60..516cd9f141467eeabb320973b16f41c3c56027eb 100644 --- a/fs/crypto/keysetup.c +++ b/fs/crypto/keysetup.c @@ -9,7 +9,6 @@ */ #include -#include #include #include "fscrypt_private.h" @@ -157,6 +156,7 @@ void fscrypt_destroy_prepared_key(struct fscrypt_prepared_key *prep_key) { crypto_free_skcipher(prep_key->tfm); fscrypt_destroy_inline_crypt_key(prep_key); + memzero_explicit(prep_key, sizeof(*prep_key)); } /* Given a per-file encryption key, set up the file's crypto transform object */ @@ -444,20 +444,18 @@ static bool fscrypt_valid_master_key_size(const struct fscrypt_master_key *mk, /* * Find the master key, then set up the inode's actual encryption key. * - * If the master key is found in the filesystem-level keyring, then the - * corresponding 'struct key' is returned in *master_key_ret with its semaphore - * read-locked. This is needed to ensure that only one task links the - * fscrypt_info into ->mk_decrypted_inodes (as multiple tasks may race to create - * an fscrypt_info for the same inode), and to synchronize the master key being - * removed with a new inode starting to use it. + * If the master key is found in the filesystem-level keyring, then it is + * returned in *mk_ret with its semaphore read-locked. This is needed to ensure + * that only one task links the fscrypt_info into ->mk_decrypted_inodes (as + * multiple tasks may race to create an fscrypt_info for the same inode), and to + * synchronize the master key being removed with a new inode starting to use it. */ static int setup_file_encryption_key(struct fscrypt_info *ci, bool need_dirhash_key, - struct key **master_key_ret) + struct fscrypt_master_key **mk_ret) { - struct key *key; - struct fscrypt_master_key *mk = NULL; struct fscrypt_key_specifier mk_spec; + struct fscrypt_master_key *mk; int err; switch (ci->ci_policy.version) { @@ -478,11 +476,10 @@ static int setup_file_encryption_key(struct fscrypt_info *ci, return -EINVAL; } - key = fscrypt_find_master_key(ci->ci_inode->i_sb, &mk_spec); - if (IS_ERR(key)) { - if (key != ERR_PTR(-ENOKEY) || - ci->ci_policy.version != FSCRYPT_POLICY_V1) - return PTR_ERR(key); + mk = fscrypt_find_master_key(ci->ci_inode->i_sb, &mk_spec); + if (!mk) { + if (ci->ci_policy.version != FSCRYPT_POLICY_V1) + return -ENOKEY; err = fscrypt_select_encryption_impl(ci, false); if (err) @@ -496,9 +493,7 @@ static int setup_file_encryption_key(struct fscrypt_info *ci, */ return fscrypt_setup_v1_file_key_via_subscribed_keyrings(ci); } - - mk = key->payload.data[0]; - down_read(&key->sem); + down_read(&mk->mk_sem); /* Has the secret been removed (via FS_IOC_REMOVE_ENCRYPTION_KEY)? */ if (!is_master_key_secret_present(&mk->mk_secret)) { @@ -530,18 +525,18 @@ static int setup_file_encryption_key(struct fscrypt_info *ci, if (err) goto out_release_key; - *master_key_ret = key; + *mk_ret = mk; return 0; out_release_key: - up_read(&key->sem); - key_put(key); + up_read(&mk->mk_sem); + fscrypt_put_master_key(mk); return err; } static void put_crypt_info(struct fscrypt_info *ci) { - struct key *key; + struct fscrypt_master_key *mk; if (!ci) return; @@ -551,24 +546,18 @@ static void put_crypt_info(struct fscrypt_info *ci) else if (ci->ci_owns_key) fscrypt_destroy_prepared_key(&ci->ci_enc_key); - key = ci->ci_master_key; - if (key) { - struct fscrypt_master_key *mk = key->payload.data[0]; - + mk = ci->ci_master_key; + if (mk) { /* * Remove this inode from the list of inodes that were unlocked - * with the master key. - * - * In addition, if we're removing the last inode from a key that - * already had its secret removed, invalidate the key so that it - * gets removed from ->s_master_keys. + * with the master key. In addition, if we're removing the last + * inode from a master key struct that already had its secret + * removed, then complete the full removal of the struct. */ spin_lock(&mk->mk_decrypted_inodes_lock); list_del(&ci->ci_master_key_link); spin_unlock(&mk->mk_decrypted_inodes_lock); - if (refcount_dec_and_test(&mk->mk_refcount)) - key_invalidate(key); - key_put(key); + fscrypt_put_master_key_activeref(mk); } memzero_explicit(ci, sizeof(*ci)); kmem_cache_free(fscrypt_info_cachep, ci); @@ -582,7 +571,7 @@ fscrypt_setup_encryption_info(struct inode *inode, { struct fscrypt_info *crypt_info; struct fscrypt_mode *mode; - struct key *master_key = NULL; + struct fscrypt_master_key *mk = NULL; int res; res = fscrypt_initialize(inode->i_sb->s_cop->flags); @@ -605,8 +594,7 @@ fscrypt_setup_encryption_info(struct inode *inode, WARN_ON(mode->ivsize > FSCRYPT_MAX_IV_SIZE); crypt_info->ci_mode = mode; - res = setup_file_encryption_key(crypt_info, need_dirhash_key, - &master_key); + res = setup_file_encryption_key(crypt_info, need_dirhash_key, &mk); if (res) goto out; @@ -621,12 +609,9 @@ fscrypt_setup_encryption_info(struct inode *inode, * We won the race and set ->i_crypt_info to our crypt_info. * Now link it into the master key's inode list. */ - if (master_key) { - struct fscrypt_master_key *mk = - master_key->payload.data[0]; - - refcount_inc(&mk->mk_refcount); - crypt_info->ci_master_key = key_get(master_key); + if (mk) { + crypt_info->ci_master_key = mk; + refcount_inc(&mk->mk_active_refs); spin_lock(&mk->mk_decrypted_inodes_lock); list_add(&crypt_info->ci_master_key_link, &mk->mk_decrypted_inodes); @@ -636,9 +621,9 @@ fscrypt_setup_encryption_info(struct inode *inode, } res = 0; out: - if (master_key) { - up_read(&master_key->sem); - key_put(master_key); + if (mk) { + up_read(&mk->mk_sem); + fscrypt_put_master_key(mk); } put_crypt_info(crypt_info); return res; @@ -803,7 +788,6 @@ EXPORT_SYMBOL(fscrypt_free_inode); int fscrypt_drop_inode(struct inode *inode) { const struct fscrypt_info *ci = fscrypt_get_info(inode); - const struct fscrypt_master_key *mk; /* * If ci is NULL, then the inode doesn't have an encryption key set up @@ -813,7 +797,6 @@ int fscrypt_drop_inode(struct inode *inode) */ if (!ci || !ci->ci_master_key) return 0; - mk = ci->ci_master_key->payload.data[0]; /* * With proper, non-racy use of FS_IOC_REMOVE_ENCRYPTION_KEY, all inodes @@ -832,6 +815,6 @@ int fscrypt_drop_inode(struct inode *inode) * then the thread removing the key will either evict the inode itself * or will correctly detect that it wasn't evicted due to the race. */ - return !is_master_key_secret_present(&mk->mk_secret); + return !is_master_key_secret_present(&ci->ci_master_key->mk_secret); } EXPORT_SYMBOL_GPL(fscrypt_drop_inode); diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c index a51cef6bd27ff48a3073ca3ced74696a40b2ba53..41bd3e70fd20f9076747c363b98673d3d061c6d3 100644 --- a/fs/crypto/policy.c +++ b/fs/crypto/policy.c @@ -692,12 +692,8 @@ int fscrypt_set_context(struct inode *inode, void *fs_data) * delayed key setup that requires the inode number. */ if (ci->ci_policy.version == FSCRYPT_POLICY_V2 && - (ci->ci_policy.v2.flags & FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32)) { - const struct fscrypt_master_key *mk = - ci->ci_master_key->payload.data[0]; - - fscrypt_hash_inode_number(ci, mk); - } + (ci->ci_policy.v2.flags & FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32)) + fscrypt_hash_inode_number(ci, ci->ci_master_key); return inode->i_sb->s_cop->set_context(inode, &ctx, ctxsize, fs_data); } diff --git a/fs/dlm/ast.c b/fs/dlm/ast.c index 283c7b94eddadeb7b88e7c84ff6c09a9db5c3e0a..ca06069e95c8c9e24d3e9b4635436ff40a7aef41 100644 --- a/fs/dlm/ast.c +++ b/fs/dlm/ast.c @@ -198,13 +198,13 @@ void dlm_add_cb(struct dlm_lkb *lkb, uint32_t flags, int mode, int status, if (!prev_seq) { kref_get(&lkb->lkb_ref); + mutex_lock(&ls->ls_cb_mutex); if (test_bit(LSFL_CB_DELAY, &ls->ls_flags)) { - mutex_lock(&ls->ls_cb_mutex); list_add(&lkb->lkb_cb_list, &ls->ls_cb_delay); - mutex_unlock(&ls->ls_cb_mutex); } else { queue_work(ls->ls_callback_wq, &lkb->lkb_cb_work); } + mutex_unlock(&ls->ls_cb_mutex); } out: mutex_unlock(&lkb->lkb_cb_mutex); @@ -284,7 +284,9 @@ void dlm_callback_stop(struct dlm_ls *ls) void dlm_callback_suspend(struct dlm_ls *ls) { + mutex_lock(&ls->ls_cb_mutex); set_bit(LSFL_CB_DELAY, &ls->ls_flags); + mutex_unlock(&ls->ls_cb_mutex); if (ls->ls_callback_wq) flush_workqueue(ls->ls_callback_wq); diff --git a/fs/dlm/lock.c b/fs/dlm/lock.c index eaa28d654e9f0dc7604a871cd4b7f459442ff43d..dde9afb6747bac4407fb28f29297276a1720a07c 100644 --- a/fs/dlm/lock.c +++ b/fs/dlm/lock.c @@ -2888,24 +2888,24 @@ static int set_unlock_args(uint32_t flags, void *astarg, struct dlm_args *args) static int validate_lock_args(struct dlm_ls *ls, struct dlm_lkb *lkb, struct dlm_args *args) { - int rv = -EINVAL; + int rv = -EBUSY; if (args->flags & DLM_LKF_CONVERT) { - if (lkb->lkb_flags & DLM_IFL_MSTCPY) + if (lkb->lkb_status != DLM_LKSTS_GRANTED) goto out; - if (args->flags & DLM_LKF_QUECVT && - !__quecvt_compat_matrix[lkb->lkb_grmode+1][args->mode+1]) + if (lkb->lkb_wait_type) goto out; - rv = -EBUSY; - if (lkb->lkb_status != DLM_LKSTS_GRANTED) + if (is_overlap(lkb)) goto out; - if (lkb->lkb_wait_type) + rv = -EINVAL; + if (lkb->lkb_flags & DLM_IFL_MSTCPY) goto out; - if (is_overlap(lkb)) + if (args->flags & DLM_LKF_QUECVT && + !__quecvt_compat_matrix[lkb->lkb_grmode+1][args->mode+1]) goto out; } diff --git a/fs/eventfd.c b/fs/eventfd.c index df466ef81dddfa05c6e6b3f90eaf0a8a352b53a7..4a14295cffe0d57c81f8f76980bf8da14181b084 100644 --- a/fs/eventfd.c +++ b/fs/eventfd.c @@ -45,21 +45,7 @@ struct eventfd_ctx { int id; }; -/** - * eventfd_signal - Adds @n to the eventfd counter. - * @ctx: [in] Pointer to the eventfd context. - * @n: [in] Value of the counter to be added to the eventfd internal counter. - * The value cannot be negative. - * - * This function is supposed to be called by the kernel in paths that do not - * allow sleeping. In this function we allow the counter to reach the ULLONG_MAX - * value, and we signal this as overflow condition by returning a EPOLLERR - * to poll(2). - * - * Returns the amount by which the counter was incremented. This will be less - * than @n if the counter has overflowed. - */ -__u64 eventfd_signal(struct eventfd_ctx *ctx, __u64 n) +__u64 eventfd_signal_mask(struct eventfd_ctx *ctx, __u64 n, unsigned mask) { unsigned long flags; @@ -80,12 +66,31 @@ __u64 eventfd_signal(struct eventfd_ctx *ctx, __u64 n) n = ULLONG_MAX - ctx->count; ctx->count += n; if (waitqueue_active(&ctx->wqh)) - wake_up_locked_poll(&ctx->wqh, EPOLLIN); + wake_up_locked_poll(&ctx->wqh, EPOLLIN | mask); this_cpu_dec(eventfd_wake_count); spin_unlock_irqrestore(&ctx->wqh.lock, flags); return n; } + +/** + * eventfd_signal - Adds @n to the eventfd counter. + * @ctx: [in] Pointer to the eventfd context. + * @n: [in] Value of the counter to be added to the eventfd internal counter. + * The value cannot be negative. + * + * This function is supposed to be called by the kernel in paths that do not + * allow sleeping. In this function we allow the counter to reach the ULLONG_MAX + * value, and we signal this as overflow condition by returning a EPOLLERR + * to poll(2). + * + * Returns the amount by which the counter was incremented. This will be less + * than @n if the counter has overflowed. + */ +__u64 eventfd_signal(struct eventfd_ctx *ctx, __u64 n) +{ + return eventfd_signal_mask(ctx, n, 0); +} EXPORT_SYMBOL_GPL(eventfd_signal); static void eventfd_free_ctx(struct eventfd_ctx *ctx) diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 0ceb8285bf6631473595d83f273849b491652e26..2c67c59814e17b30fa5c60019b52a4e7d3516546 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -551,7 +551,8 @@ out_unlock: */ #ifdef CONFIG_DEBUG_LOCK_ALLOC -static void ep_poll_safewake(struct eventpoll *ep, struct epitem *epi) +static void ep_poll_safewake(struct eventpoll *ep, struct epitem *epi, + unsigned pollflags) { struct eventpoll *ep_src; unsigned long flags; @@ -582,16 +583,17 @@ static void ep_poll_safewake(struct eventpoll *ep, struct epitem *epi) } spin_lock_irqsave_nested(&ep->poll_wait.lock, flags, nests); ep->nests = nests + 1; - wake_up_locked_poll(&ep->poll_wait, EPOLLIN); + wake_up_locked_poll(&ep->poll_wait, EPOLLIN | pollflags); ep->nests = 0; spin_unlock_irqrestore(&ep->poll_wait.lock, flags); } #else -static void ep_poll_safewake(struct eventpoll *ep, struct epitem *epi) +static void ep_poll_safewake(struct eventpoll *ep, struct epitem *epi, + unsigned pollflags) { - wake_up_poll(&ep->poll_wait, EPOLLIN); + wake_up_poll(&ep->poll_wait, EPOLLIN | pollflags); } #endif @@ -818,7 +820,7 @@ static void ep_free(struct eventpoll *ep) /* We need to release all tasks waiting for these file */ if (waitqueue_active(&ep->poll_wait)) - ep_poll_safewake(ep, NULL); + ep_poll_safewake(ep, NULL, 0); /* * We need to lock this because we could be hit by @@ -1287,7 +1289,7 @@ out_unlock: /* We have to call this outside the lock */ if (pwake) - ep_poll_safewake(ep, epi); + ep_poll_safewake(ep, epi, pollflags & EPOLL_URING_WAKE); if (!(epi->event.events & EPOLLEXCLUSIVE)) ewake = 1; @@ -1597,7 +1599,7 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event, /* We have to call this outside the lock */ if (pwake) - ep_poll_safewake(ep, NULL); + ep_poll_safewake(ep, NULL, 0); return 0; @@ -1700,7 +1702,7 @@ static int ep_modify(struct eventpoll *ep, struct epitem *epi, /* We have to call this outside the lock */ if (pwake) - ep_poll_safewake(ep, NULL); + ep_poll_safewake(ep, NULL, 0); return 0; } diff --git a/fs/exec.c b/fs/exec.c index bc503539257d8075e2d88dbd734ddfa4ea7bbe5e..6e1f8628ab9cc7eba33cbad6b8667836d5f717b5 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1203,11 +1203,11 @@ static int unshare_sighand(struct task_struct *me) return -ENOMEM; refcount_set(&newsighand->count, 1); - memcpy(newsighand->action, oldsighand->action, - sizeof(newsighand->action)); write_lock_irq(&tasklist_lock); spin_lock(&oldsighand->siglock); + memcpy(newsighand->action, oldsighand->action, + sizeof(newsighand->action)); rcu_assign_pointer(me->sighand, newsighand); spin_unlock(&oldsighand->siglock); write_unlock_irq(&tasklist_lock); diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 30add5a3df3df06a8b0fa5e7458fccfd90f9df9d..54750b7c162d26a8696afd85c9e1060439a454d8 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -5182,6 +5182,7 @@ ext4_ext_shift_extents(struct inode *inode, handle_t *handle, * and it is decreased till we reach start. */ again: + ret = 0; if (SHIFT == SHIFT_LEFT) iterator = &start; else @@ -5225,14 +5226,21 @@ again: ext4_ext_get_actual_len(extent); } else { extent = EXT_FIRST_EXTENT(path[depth].p_hdr); - if (le32_to_cpu(extent->ee_block) > 0) + if (le32_to_cpu(extent->ee_block) > start) *iterator = le32_to_cpu(extent->ee_block) - 1; - else - /* Beginning is reached, end of the loop */ + else if (le32_to_cpu(extent->ee_block) == start) iterator = NULL; - /* Update path extent in case we need to stop */ - while (le32_to_cpu(extent->ee_block) < start) + else { + extent = EXT_LAST_EXTENT(path[depth].p_hdr); + while (le32_to_cpu(extent->ee_block) >= start) + extent--; + + if (extent == EXT_LAST_EXTENT(path[depth].p_hdr)) + break; + extent++; + iterator = NULL; + } path[depth].p_ext = extent; } ret = ext4_ext_shift_path_extents(path, shift, inode, diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c index 501e60713010e57a0f84ad3b4335b9a43d23d497..41dcf21558c4edba55321d837c025b72f6f05433 100644 --- a/fs/ext4/fast_commit.c +++ b/fs/ext4/fast_commit.c @@ -766,22 +766,25 @@ static int ext4_fc_write_inode(struct inode *inode, u32 *crc) tl.fc_tag = cpu_to_le16(EXT4_FC_TAG_INODE); tl.fc_len = cpu_to_le16(inode_len + sizeof(fc_inode.fc_ino)); + ret = -ECANCELED; dst = ext4_fc_reserve_space(inode->i_sb, sizeof(tl) + inode_len + sizeof(fc_inode.fc_ino), crc); if (!dst) - return -ECANCELED; + goto err; if (!ext4_fc_memcpy(inode->i_sb, dst, &tl, sizeof(tl), crc)) - return -ECANCELED; + goto err; dst += sizeof(tl); if (!ext4_fc_memcpy(inode->i_sb, dst, &fc_inode, sizeof(fc_inode), crc)) - return -ECANCELED; + goto err; dst += sizeof(fc_inode); if (!ext4_fc_memcpy(inode->i_sb, dst, (u8 *)ext4_raw_inode(&iloc), inode_len, crc)) - return -ECANCELED; - - return 0; + goto err; + ret = 0; +err: + brelse(iloc.bh); + return ret; } /* @@ -1388,13 +1391,15 @@ static int ext4_fc_record_modified_inode(struct super_block *sb, int ino) if (state->fc_modified_inodes[i] == ino) return 0; if (state->fc_modified_inodes_used == state->fc_modified_inodes_size) { - state->fc_modified_inodes = krealloc( - state->fc_modified_inodes, + int *fc_modified_inodes; + + fc_modified_inodes = krealloc(state->fc_modified_inodes, sizeof(int) * (state->fc_modified_inodes_size + EXT4_FC_REPLAY_REALLOC_INCREMENT), GFP_KERNEL); - if (!state->fc_modified_inodes) + if (!fc_modified_inodes) return -ENOMEM; + state->fc_modified_inodes = fc_modified_inodes; state->fc_modified_inodes_size += EXT4_FC_REPLAY_REALLOC_INCREMENT; } @@ -1579,15 +1584,18 @@ int ext4_fc_record_regions(struct super_block *sb, int ino, if (replay && state->fc_regions_used != state->fc_regions_valid) state->fc_regions_used = state->fc_regions_valid; if (state->fc_regions_used == state->fc_regions_size) { + struct ext4_fc_alloc_region *fc_regions; + + fc_regions = krealloc(state->fc_regions, + sizeof(struct ext4_fc_alloc_region) * + (state->fc_regions_size + + EXT4_FC_REPLAY_REALLOC_INCREMENT), + GFP_KERNEL); + if (!fc_regions) + return -ENOMEM; state->fc_regions_size += EXT4_FC_REPLAY_REALLOC_INCREMENT; - state->fc_regions = krealloc( - state->fc_regions, - state->fc_regions_size * - sizeof(struct ext4_fc_alloc_region), - GFP_KERNEL); - if (!state->fc_regions) - return -ENOMEM; + state->fc_regions = fc_regions; } region = &state->fc_regions[state->fc_regions_used++]; region->ino = ino; diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 98c13bf3228e7f91528f1c3bf50f442a83307842..b41472c9697a83f8a22694433a8a2abbeafe0802 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -531,6 +531,12 @@ static ssize_t ext4_dio_write_iter(struct kiocb *iocb, struct iov_iter *from) ret = -EAGAIN; goto out; } + /* + * Make sure inline data cannot be created anymore since we are going + * to allocate blocks for DIO. We know the inode does not have any + * inline data now because ext4_dio_supported() checked for that. + */ + ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); offset = iocb->ki_pos; count = ret; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 6cc3fd2abcaf0e3f404aeb25581d2c1531312c06..8150fb0ff80077284f69e6287d9fbb67a1351194 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1186,6 +1186,13 @@ retry_grab: page = grab_cache_page_write_begin(mapping, index, flags); if (!page) return -ENOMEM; + /* + * The same as page allocation, we prealloc buffer heads before + * starting the handle. + */ + if (!page_has_buffers(page)) + create_empty_buffers(page, inode->i_sb->s_blocksize, 0); + unlock_page(page); retry_journal: @@ -5800,7 +5807,12 @@ int ext4_mark_iloc_dirty(handle_t *handle, } ext4_fc_track_inode(handle, inode); - if (IS_I_VERSION(inode)) + /* + * ea_inodes are using i_version for storing reference count, don't + * mess with it + */ + if (IS_I_VERSION(inode) && + !(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)) inode_inc_iversion(inode); /* the do_update_inode consumes one bh->b_count */ diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c index 04320715d61f1bbfad7f41c0fc5161f0cb975a86..4bfe2252d9a4e7971910525d6fb2eec733ac67e9 100644 --- a/fs/ext4/migrate.c +++ b/fs/ext4/migrate.c @@ -425,7 +425,8 @@ int ext4_ext_migrate(struct inode *inode) * already is extent-based, error out. */ if (!ext4_has_feature_extents(inode->i_sb) || - (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) + ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) || + ext4_has_inline_data(inode)) return -EINVAL; if (S_ISLNK(inode->i_mode) && inode->i_blocks == 0) diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 2b99badff05bada8ea5962870ac68ce626011931..2509d8de89eea589e0e6a5bde447c6d5c96a99fb 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -125,7 +125,7 @@ static struct buffer_head *__ext4_read_dirblock(struct inode *inode, struct ext4_dir_entry *dirent; int is_dx_block = 0; - if (block >= inode->i_size) { + if (block >= inode->i_size >> inode->i_blkbits) { ext4_error_inode(inode, func, line, block, "Attempting to read directory block (%u) that is past i_size (%llu)", block, inode->i_size); @@ -2236,8 +2236,16 @@ static int make_indexed_dir(handle_t *handle, struct ext4_filename *fname, memcpy(data2, de, len); de = (struct ext4_dir_entry_2 *) data2; top = data2 + len; - while ((char *)(de2 = ext4_next_entry(de, blocksize)) < top) + while ((char *)(de2 = ext4_next_entry(de, blocksize)) < top) { + if (ext4_check_dir_entry(dir, NULL, de, bh2, data2, len, + (data2 + (blocksize - csum_size) - + (char *) de))) { + brelse(bh2); + brelse(bh); + return -EFSCORRUPTED; + } de = de2; + } de->rec_len = ext4_rec_len_to_disk(data2 + (blocksize - csum_size) - (char *) de, blocksize); diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index f6409ddfd1172b42faffc32af0efc408539cdfbe..c55ba0390021e4f15ab145c3334b10d495ebd4f8 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -2068,7 +2068,7 @@ retry: goto out; } - if (ext4_blocks_count(es) == n_blocks_count) + if (ext4_blocks_count(es) == n_blocks_count && n_blocks_count_retry == 0) goto out; err = ext4_alloc_flex_bg_array(sb, n_group + 1); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 54a9d2195cccd4c4b67ac0534676d22fb7bac5a2..2792d4a40e9b2000ae66b14e2375c0607d9c99a0 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -188,19 +188,12 @@ int ext4_read_bh(struct buffer_head *bh, int op_flags, bh_end_io_t *end_io) int ext4_read_bh_lock(struct buffer_head *bh, int op_flags, bool wait) { - if (trylock_buffer(bh)) { - if (wait) - return ext4_read_bh(bh, op_flags, NULL); + lock_buffer(bh); + if (!wait) { ext4_read_bh_nowait(bh, op_flags, NULL); return 0; } - if (wait) { - wait_on_buffer(bh); - if (buffer_uptodate(bh)) - return 0; - return -EIO; - } - return 0; + return ext4_read_bh(bh, op_flags, NULL); } /* @@ -247,7 +240,8 @@ void ext4_sb_breadahead_unmovable(struct super_block *sb, sector_t block) struct buffer_head *bh = sb_getblk_gfp(sb, block, 0); if (likely(bh)) { - ext4_read_bh_lock(bh, REQ_RAHEAD, false); + if (trylock_buffer(bh)) + ext4_read_bh_nowait(bh, REQ_RAHEAD, NULL); brelse(bh); } } @@ -3549,6 +3543,7 @@ static int ext4_lazyinit_thread(void *arg) unsigned long next_wakeup, cur; BUG_ON(NULL == eli); + set_freezable(); cont_thread: while (true) { @@ -6261,7 +6256,7 @@ static int ext4_write_info(struct super_block *sb, int type) handle_t *handle; /* Data block + inode block */ - handle = ext4_journal_start(d_inode(sb->s_root), EXT4_HT_QUOTA, 2); + handle = ext4_journal_start_sb(sb, EXT4_HT_QUOTA, 2); if (IS_ERR(handle)) return PTR_ERR(handle); ret = dquot_commit_info(sb, type); diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index a5a2ab38f709d629c9dd5623c5eda99c19bc0593..e621560635af3c4c56d67a96967059fde0ecc14e 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -144,7 +144,7 @@ static bool __is_bitmap_valid(struct f2fs_sb_info *sbi, block_t blkaddr, unsigned int segno, offset; bool exist; - if (type != DATA_GENERIC_ENHANCE && type != DATA_GENERIC_ENHANCE_READ) + if (type == DATA_GENERIC) return true; segno = GET_SEGNO(sbi, blkaddr); @@ -152,6 +152,13 @@ static bool __is_bitmap_valid(struct f2fs_sb_info *sbi, block_t blkaddr, se = get_seg_entry(sbi, segno); exist = f2fs_test_bit(offset, se->cur_valid_map); + if (exist && type == DATA_GENERIC_ENHANCE_UPDATE) { + f2fs_err(sbi, "Inconsistent error blkaddr:%u, sit bitmap:%d", + blkaddr, exist); + set_sbi_flag(sbi, SBI_NEED_FSCK); + return exist; + } + if (!exist && type == DATA_GENERIC_ENHANCE) { f2fs_err(sbi, "Inconsistent error blkaddr:%u, sit bitmap:%d", blkaddr, exist); @@ -189,6 +196,7 @@ bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi, case DATA_GENERIC: case DATA_GENERIC_ENHANCE: case DATA_GENERIC_ENHANCE_READ: + case DATA_GENERIC_ENHANCE_UPDATE: if (unlikely(blkaddr >= MAX_BLKADDR(sbi) || blkaddr < MAIN_BLKADDR(sbi))) { f2fs_warn(sbi, "access invalid blkaddr:%u", @@ -1060,7 +1068,8 @@ void f2fs_remove_dirty_inode(struct inode *inode) spin_unlock(&sbi->inode_lock[type]); } -int f2fs_sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type) +int f2fs_sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type, + bool from_cp) { struct list_head *head; struct inode *inode; @@ -1095,11 +1104,15 @@ retry: if (inode) { unsigned long cur_ino = inode->i_ino; - F2FS_I(inode)->cp_task = current; + if (from_cp) + F2FS_I(inode)->cp_task = current; + F2FS_I(inode)->wb_task = current; filemap_fdatawrite(inode->i_mapping); - F2FS_I(inode)->cp_task = NULL; + F2FS_I(inode)->wb_task = NULL; + if (from_cp) + F2FS_I(inode)->cp_task = NULL; iput(inode); /* We need to give cpu to another writers. */ @@ -1228,7 +1241,7 @@ retry_flush_dents: /* write all the dirty dentry pages */ if (get_pages(sbi, F2FS_DIRTY_DENTS)) { f2fs_unlock_all(sbi); - err = f2fs_sync_dirty_inodes(sbi, DIR_INODE); + err = f2fs_sync_dirty_inodes(sbi, DIR_INODE, true); if (err) return err; cond_resched(); diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 0b2196e997b8c2aca6dbc42c6b1e1df415c2398e..c71c3e70833cea1736491a42ef66dba17a519d98 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -2862,7 +2862,7 @@ out: } unlock_page(page); if (!S_ISDIR(inode->i_mode) && !IS_NOQUOTA(inode) && - !F2FS_I(inode)->cp_task && allow_balance) + !F2FS_I(inode)->wb_task && allow_balance) f2fs_balance_fs(sbi, need_balance_fs); if (unlikely(f2fs_cp_error(sbi))) { @@ -3160,7 +3160,7 @@ static inline bool __should_serialize_io(struct inode *inode, struct writeback_control *wbc) { /* to avoid deadlock in path of data flush */ - if (F2FS_I(inode)->cp_task) + if (F2FS_I(inode)->wb_task) return false; if (!S_ISREG(inode->i_mode)) diff --git a/fs/f2fs/extent_cache.c b/fs/f2fs/extent_cache.c index 866e72b29bd5ac507bbad6cbf098b2030971d94d..761fd42c93f234a092f1de50acaac1db36fc8034 100644 --- a/fs/f2fs/extent_cache.c +++ b/fs/f2fs/extent_cache.c @@ -804,9 +804,8 @@ void f2fs_drop_extent_tree(struct inode *inode) if (!f2fs_may_extent_tree(inode)) return; - set_inode_flag(inode, FI_NO_EXTENT); - write_lock(&et->lock); + set_inode_flag(inode, FI_NO_EXTENT); __free_extent_tree(sbi, et); if (et->largest.len) { et->largest.len = 0; diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 592f2cde7b4caefbc089eb1f9a60c501e17b3012..d9e038d42548b05ecc5a3874a213d6ce1ab5bfdd 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -265,6 +265,10 @@ enum { * condition of read on truncated area * by extent_cache */ + DATA_GENERIC_ENHANCE_UPDATE, /* + * strong check on range and segment + * bitmap for update case + */ META_GENERIC, }; @@ -782,6 +786,7 @@ struct f2fs_inode_info { unsigned int clevel; /* maximum level of given file name */ struct task_struct *task; /* lookup and create consistency */ struct task_struct *cp_task; /* separate cp/wb IO stats*/ + struct task_struct *wb_task; /* indicate inode is in context of writeback */ nid_t i_xattr_nid; /* node id that contains xattrs */ loff_t last_disk_size; /* lastly written file size */ spinlock_t i_size_lock; /* protect last_disk_size */ @@ -3719,7 +3724,8 @@ int f2fs_recover_orphan_inodes(struct f2fs_sb_info *sbi); int f2fs_get_valid_checkpoint(struct f2fs_sb_info *sbi); void f2fs_update_dirty_page(struct inode *inode, struct page *page); void f2fs_remove_dirty_inode(struct inode *inode); -int f2fs_sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type); +int f2fs_sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type, + bool from_cp); void f2fs_wait_on_all_pages(struct f2fs_sb_info *sbi, int type); u64 f2fs_get_sectors_written(struct f2fs_sb_info *sbi); int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc); diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index 4921483705a6d43ae9b00a80a770de3f7ff28750..8577589fe54384b15d94fd3f9603eb77fbdfa8d7 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -1017,7 +1017,7 @@ static bool is_alive(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, { struct page *node_page; nid_t nid; - unsigned int ofs_in_node; + unsigned int ofs_in_node, max_addrs; block_t source_blkaddr; nid = le32_to_cpu(sum->nid); @@ -1043,6 +1043,14 @@ static bool is_alive(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, return false; } + max_addrs = IS_INODE(node_page) ? DEF_ADDRS_PER_INODE : + DEF_ADDRS_PER_BLOCK; + if (ofs_in_node >= max_addrs) { + f2fs_err(sbi, "Inconsistent ofs_in_node:%u in summary, ino:%u, nid:%u, max:%u", + ofs_in_node, dni->ino, dni->nid, max_addrs); + return false; + } + *nofs = ofs_of_node(node_page); source_blkaddr = data_blkaddr(NULL, node_page, ofs_in_node); f2fs_put_page(node_page, 1); diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index 829d767a77bfa065cee4123602397096494d5409..e7e90585aaead5da775e28faf83f085e97f28b7a 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -690,18 +690,19 @@ void f2fs_update_inode_page(struct inode *inode) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct page *node_page; + int count = 0; retry: node_page = f2fs_get_node_page(sbi, inode->i_ino); if (IS_ERR(node_page)) { int err = PTR_ERR(node_page); - if (err == -ENOMEM) { - cond_resched(); + /* The node block was truncated. */ + if (err == -ENOENT) + return; + + if (err == -ENOMEM || ++count <= DEFAULT_RETRY_IO_COUNT) goto retry; - } else if (err != -ENOENT) { - f2fs_stop_checkpoint(sbi, false, - STOP_CP_REASON_UPDATE_INODE); - } + f2fs_stop_checkpoint(sbi, false, STOP_CP_REASON_UPDATE_INODE); return; } f2fs_update_inode(inode, node_page); diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c index 329ae992ee0eb8b3a08ee071358e3b007ac356f5..30fc972406b3e290a1d8e94a687d18e4740c9b87 100644 --- a/fs/f2fs/recovery.c +++ b/fs/f2fs/recovery.c @@ -473,7 +473,7 @@ static int check_index_in_prev_nodes(struct f2fs_sb_info *sbi, struct dnode_of_data tdn = *dn; nid_t ino, nid; struct inode *inode; - unsigned int offset; + unsigned int offset, ofs_in_node, max_addrs; block_t bidx; int i; @@ -500,15 +500,24 @@ static int check_index_in_prev_nodes(struct f2fs_sb_info *sbi, got_it: /* Use the locked dnode page and inode */ nid = le32_to_cpu(sum.nid); + ofs_in_node = le16_to_cpu(sum.ofs_in_node); + + max_addrs = ADDRS_PER_PAGE(dn->node_page, dn->inode); + if (ofs_in_node >= max_addrs) { + f2fs_err(sbi, "Inconsistent ofs_in_node:%u in summary, ino:%lu, nid:%u, max:%u", + ofs_in_node, dn->inode->i_ino, nid, max_addrs); + return -EFSCORRUPTED; + } + if (dn->inode->i_ino == nid) { tdn.nid = nid; if (!dn->inode_page_locked) lock_page(dn->inode_page); tdn.node_page = dn->inode_page; - tdn.ofs_in_node = le16_to_cpu(sum.ofs_in_node); + tdn.ofs_in_node = ofs_in_node; goto truncate_out; } else if (dn->nid == nid) { - tdn.ofs_in_node = le16_to_cpu(sum.ofs_in_node); + tdn.ofs_in_node = ofs_in_node; goto truncate_out; } @@ -698,6 +707,14 @@ retry_prev: goto err; } + if (f2fs_is_valid_blkaddr(sbi, dest, + DATA_GENERIC_ENHANCE_UPDATE)) { + f2fs_err(sbi, "Inconsistent dest blkaddr:%u, ino:%lu, ofs:%u", + dest, inode->i_ino, dn.ofs_in_node); + err = -EFSCORRUPTED; + goto err; + } + /* write dummy data page */ f2fs_replace_block(sbi, &dn, src, dest, ni.version, false, false); diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index c0fcf37c7d3ba7ed799a4eea5ddcf998691042f0..7ff666f2d239fbf27e7fad342ae3b62d5f524894 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -594,7 +594,7 @@ do_sync: mutex_lock(&sbi->flush_lock); blk_start_plug(&plug); - f2fs_sync_dirty_inodes(sbi, FILE_INODE); + f2fs_sync_dirty_inodes(sbi, FILE_INODE, false); blk_finish_plug(&plug); mutex_unlock(&sbi->flush_lock); @@ -2148,8 +2148,10 @@ int f2fs_start_discard_thread(struct f2fs_sb_info *sbi) dcc->f2fs_issue_discard = kthread_run(issue_discard_thread, sbi, "f2fs_discard-%u:%u", MAJOR(dev), MINOR(dev)); - if (IS_ERR(dcc->f2fs_issue_discard)) + if (IS_ERR(dcc->f2fs_issue_discard)) { err = PTR_ERR(dcc->f2fs_issue_discard); + dcc->f2fs_issue_discard = NULL; + } return err; } diff --git a/fs/fcntl.c b/fs/fcntl.c index 71b43538fa44cf2eb46f3168336f54caa1f7cc50..fcf34f83bf6a831a48d274c9b9ca8362e2d8dea9 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -148,12 +148,17 @@ void f_delown(struct file *filp) pid_t f_getown(struct file *filp) { - pid_t pid; - read_lock(&filp->f_owner.lock); - pid = pid_vnr(filp->f_owner.pid); - if (filp->f_owner.pid_type == PIDTYPE_PGID) - pid = -pid; - read_unlock(&filp->f_owner.lock); + pid_t pid = 0; + + read_lock_irq(&filp->f_owner.lock); + rcu_read_lock(); + if (pid_task(filp->f_owner.pid, filp->f_owner.pid_type)) { + pid = pid_vnr(filp->f_owner.pid); + if (filp->f_owner.pid_type == PIDTYPE_PGID) + pid = -pid; + } + rcu_read_unlock(); + read_unlock_irq(&filp->f_owner.lock); return pid; } @@ -200,11 +205,14 @@ static int f_setown_ex(struct file *filp, unsigned long arg) static int f_getown_ex(struct file *filp, unsigned long arg) { struct f_owner_ex __user *owner_p = (void __user *)arg; - struct f_owner_ex owner; + struct f_owner_ex owner = {}; int ret = 0; - read_lock(&filp->f_owner.lock); - owner.pid = pid_vnr(filp->f_owner.pid); + read_lock_irq(&filp->f_owner.lock); + rcu_read_lock(); + if (pid_task(filp->f_owner.pid, filp->f_owner.pid_type)) + owner.pid = pid_vnr(filp->f_owner.pid); + rcu_read_unlock(); switch (filp->f_owner.pid_type) { case PIDTYPE_PID: owner.type = F_OWNER_TID; @@ -223,7 +231,7 @@ static int f_getown_ex(struct file *filp, unsigned long arg) ret = -EINVAL; break; } - read_unlock(&filp->f_owner.lock); + read_unlock_irq(&filp->f_owner.lock); if (!ret) { ret = copy_to_user(owner_p, &owner, sizeof(owner)); @@ -241,10 +249,10 @@ static int f_getowner_uids(struct file *filp, unsigned long arg) uid_t src[2]; int err; - read_lock(&filp->f_owner.lock); + read_lock_irq(&filp->f_owner.lock); src[0] = from_kuid(user_ns, filp->f_owner.uid); src[1] = from_kuid(user_ns, filp->f_owner.euid); - read_unlock(&filp->f_owner.lock); + read_unlock_irq(&filp->f_owner.lock); err = put_user(src[0], &dst[0]); err |= put_user(src[1], &dst[1]); diff --git a/fs/file.c b/fs/file.c index ef6ab9dd5f7a30b9d2f8e06b94e3a307121087b9..7b59ca9b94880b16f3526984ec8fc82a62297058 100644 --- a/fs/file.c +++ b/fs/file.c @@ -22,6 +22,8 @@ #include #include +#include "internal.h" + unsigned int sysctl_nr_open __read_mostly = 1024*1024; unsigned int sysctl_nr_open_min = BITS_PER_LONG; /* our min() is unusable in constant expressions ;-/ */ @@ -819,9 +821,8 @@ int __close_range(unsigned fd, unsigned max_fd, unsigned int flags) } /* - * variant of __close_fd that gets a ref on the file for later fput. - * The caller must ensure that filp_close() called on the file, and then - * an fput(). + * See close_fd_get_file() below, this variant assumes current->files->file_lock + * is held. */ int __close_fd_get_file(unsigned int fd, struct file **res) { @@ -829,26 +830,39 @@ int __close_fd_get_file(unsigned int fd, struct file **res) struct file *file; struct fdtable *fdt; - spin_lock(&files->file_lock); fdt = files_fdtable(files); if (fd >= fdt->max_fds) - goto out_unlock; + goto out_err; file = fdt->fd[fd]; if (!file) - goto out_unlock; + goto out_err; rcu_assign_pointer(fdt->fd[fd], NULL); __put_unused_fd(files, fd); - spin_unlock(&files->file_lock); get_file(file); *res = file; return 0; - -out_unlock: - spin_unlock(&files->file_lock); +out_err: *res = NULL; return -ENOENT; } +/* + * variant of close_fd that gets a ref on the file for later fput. + * The caller must ensure that filp_close() called on the file, and then + * an fput(). + */ +int close_fd_get_file(unsigned int fd, struct file **res) +{ + struct files_struct *files = current->files; + int ret; + + spin_lock(&files->file_lock); + ret = __close_fd_get_file(fd, res); + spin_unlock(&files->file_lock); + + return ret; +} + void do_close_on_exec(struct files_struct *files) { unsigned i; diff --git a/fs/fuse/file.c b/fs/fuse/file.c index d492898b33f52454fbaed380200c45ce29572ab0..6f0e1a7993497193073e9dee75a6efe1f0186e83 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -3393,10 +3393,9 @@ static long fuse_file_fallocate(struct file *file, int mode, loff_t offset, .mode = mode }; int err; - bool lock_inode = !(mode & FALLOC_FL_KEEP_SIZE) || - (mode & FALLOC_FL_PUNCH_HOLE); - - bool block_faults = FUSE_IS_DAX(inode) && lock_inode; + bool block_faults = FUSE_IS_DAX(inode) && + (!(mode & FALLOC_FL_KEEP_SIZE) || + (mode & FALLOC_FL_PUNCH_HOLE)); #ifdef CONFIG_FUSE_BPF struct fuse_err_ret fer; @@ -3416,22 +3415,20 @@ static long fuse_file_fallocate(struct file *file, int mode, loff_t offset, if (fm->fc->no_fallocate) return -EOPNOTSUPP; - if (lock_inode) { - inode_lock(inode); - if (block_faults) { - down_write(&fi->i_mmap_sem); - err = fuse_dax_break_layouts(inode, 0, 0); - if (err) - goto out; - } + inode_lock(inode); + if (block_faults) { + down_write(&fi->i_mmap_sem); + err = fuse_dax_break_layouts(inode, 0, 0); + if (err) + goto out; + } - if (mode & FALLOC_FL_PUNCH_HOLE) { - loff_t endbyte = offset + length - 1; + if (mode & FALLOC_FL_PUNCH_HOLE) { + loff_t endbyte = offset + length - 1; - err = fuse_writeback_range(inode, offset, endbyte); - if (err) - goto out; - } + err = fuse_writeback_range(inode, offset, endbyte); + if (err) + goto out; } if (!(mode & FALLOC_FL_KEEP_SIZE) && @@ -3441,6 +3438,10 @@ static long fuse_file_fallocate(struct file *file, int mode, loff_t offset, goto out; } + err = file_modified(file); + if (err) + goto out; + if (!(mode & FALLOC_FL_KEEP_SIZE)) set_bit(FUSE_I_SIZE_UNSTABLE, &fi->state); @@ -3477,8 +3478,7 @@ out: if (block_faults) up_write(&fi->i_mmap_sem); - if (lock_inode) - inode_unlock(inode); + inode_unlock(inode); fuse_flush_time_update(inode); diff --git a/fs/fuse/readdir.c b/fs/fuse/readdir.c index 5b31233162387cf7da582d2377c7a6a02e2da540..05166864e1c2c4de63d3530e316b2db1b7128551 100644 --- a/fs/fuse/readdir.c +++ b/fs/fuse/readdir.c @@ -79,8 +79,10 @@ static void fuse_add_dirent_to_cache(struct file *file, goto unlock; addr = kmap_atomic(page); - if (!offset) + if (!offset) { clear_page(addr); + SetPageUptodate(page); + } memcpy(addr + offset, dirent, reclen); kunmap_atomic(addr); fi->rdc.size = (index << PAGE_SHIFT) + offset + reclen; @@ -518,6 +520,12 @@ retry_locked: page = find_get_page_flags(file->f_mapping, index, FGP_ACCESSED | FGP_LOCK); + /* Page gone missing, then re-added to cache, but not initialized? */ + if (page && !PageUptodate(page)) { + unlock_page(page); + put_page(page); + page = NULL; + } spin_lock(&fi->rdc.lock); if (!page) { /* diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index b9ed6a6dbcf519250ea39d61e61b3edc6449f141..648f7336043f6a7ec5239d005153d426c64390dd 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -182,7 +182,10 @@ static int gfs2_check_sb(struct gfs2_sbd *sdp, int silent) pr_warn("Invalid superblock size\n"); return -EINVAL; } - + if (sb->sb_bsize_shift != ffs(sb->sb_bsize) - 1) { + pr_warn("Invalid block size shift\n"); + return -EINVAL; + } return 0; } @@ -381,8 +384,10 @@ static int init_names(struct gfs2_sbd *sdp, int silent) if (!table[0]) table = sdp->sd_vfs->s_id; - strlcpy(sdp->sd_proto_name, proto, GFS2_FSNAME_LEN); - strlcpy(sdp->sd_table_name, table, GFS2_FSNAME_LEN); + BUILD_BUG_ON(GFS2_LOCKNAME_LEN > GFS2_FSNAME_LEN); + + strscpy(sdp->sd_proto_name, proto, GFS2_LOCKNAME_LEN); + strscpy(sdp->sd_table_name, table, GFS2_LOCKNAME_LEN); table = sdp->sd_table_name; while ((table = strchr(table, '/'))) @@ -1414,13 +1419,13 @@ static int gfs2_parse_param(struct fs_context *fc, struct fs_parameter *param) switch (o) { case Opt_lockproto: - strlcpy(args->ar_lockproto, param->string, GFS2_LOCKNAME_LEN); + strscpy(args->ar_lockproto, param->string, GFS2_LOCKNAME_LEN); break; case Opt_locktable: - strlcpy(args->ar_locktable, param->string, GFS2_LOCKNAME_LEN); + strscpy(args->ar_locktable, param->string, GFS2_LOCKNAME_LEN); break; case Opt_hostdata: - strlcpy(args->ar_hostdata, param->string, GFS2_LOCKNAME_LEN); + strscpy(args->ar_hostdata, param->string, GFS2_LOCKNAME_LEN); break; case Opt_spectator: args->ar_spectator = 1; diff --git a/fs/internal.h b/fs/internal.h index 5155f6ce95c79498be285643bae25019cd5cd8d9..06d313b9beecbb16d9a3ea37050433c7d4c6203b 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -77,6 +77,8 @@ extern int vfs_path_lookup(struct dentry *, struct vfsmount *, long do_rmdir(int dfd, struct filename *name); long do_unlinkat(int dfd, struct filename *name); int may_linkat(struct path *link); +int do_renameat2(int olddfd, struct filename *oldname, int newdfd, + struct filename *newname, unsigned int flags); /* * namespace.c @@ -132,6 +134,7 @@ extern struct file *do_file_open_root(struct dentry *, struct vfsmount *, const char *, const struct open_flags *); extern struct open_how build_open_how(int flags, umode_t mode); extern int build_open_flags(const struct open_how *how, struct open_flags *op); +extern int __close_fd_get_file(unsigned int fd, struct file **res); long do_sys_ftruncate(unsigned int fd, loff_t length, int small); int chmod_common(const struct path *path, umode_t mode); diff --git a/fs/io-wq.c b/fs/io-wq.c deleted file mode 100644 index 3d5fc76b92d0143f121fc91b43dc8fbefeca92df..0000000000000000000000000000000000000000 --- a/fs/io-wq.c +++ /dev/null @@ -1,1242 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Basic worker thread pool for io_uring - * - * Copyright (C) 2019 Jens Axboe - * - */ -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include "../kernel/sched/sched.h" -#include "io-wq.h" - -#define WORKER_IDLE_TIMEOUT (5 * HZ) - -enum { - IO_WORKER_F_UP = 1, /* up and active */ - IO_WORKER_F_RUNNING = 2, /* account as running */ - IO_WORKER_F_FREE = 4, /* worker on free list */ - IO_WORKER_F_FIXED = 8, /* static idle worker */ - IO_WORKER_F_BOUND = 16, /* is doing bounded work */ -}; - -enum { - IO_WQ_BIT_EXIT = 0, /* wq exiting */ - IO_WQ_BIT_CANCEL = 1, /* cancel work on list */ - IO_WQ_BIT_ERROR = 2, /* error on setup */ -}; - -enum { - IO_WQE_FLAG_STALLED = 1, /* stalled on hash */ -}; - -/* - * One for each thread in a wqe pool - */ -struct io_worker { - refcount_t ref; - unsigned flags; - struct hlist_nulls_node nulls_node; - struct list_head all_list; - struct task_struct *task; - struct io_wqe *wqe; - - struct io_wq_work *cur_work; - spinlock_t lock; - - struct rcu_head rcu; - struct mm_struct *mm; -#ifdef CONFIG_BLK_CGROUP - struct cgroup_subsys_state *blkcg_css; -#endif - const struct cred *cur_creds; - const struct cred *saved_creds; - struct files_struct *restore_files; - struct nsproxy *restore_nsproxy; - struct fs_struct *restore_fs; -}; - -#if BITS_PER_LONG == 64 -#define IO_WQ_HASH_ORDER 6 -#else -#define IO_WQ_HASH_ORDER 5 -#endif - -#define IO_WQ_NR_HASH_BUCKETS (1u << IO_WQ_HASH_ORDER) - -struct io_wqe_acct { - unsigned nr_workers; - unsigned max_workers; - atomic_t nr_running; -}; - -enum { - IO_WQ_ACCT_BOUND, - IO_WQ_ACCT_UNBOUND, -}; - -/* - * Per-node worker thread pool - */ -struct io_wqe { - struct { - raw_spinlock_t lock; - struct io_wq_work_list work_list; - unsigned long hash_map; - unsigned flags; - } ____cacheline_aligned_in_smp; - - int node; - struct io_wqe_acct acct[2]; - - struct hlist_nulls_head free_list; - struct list_head all_list; - - struct io_wq *wq; - struct io_wq_work *hash_tail[IO_WQ_NR_HASH_BUCKETS]; -}; - -/* - * Per io_wq state - */ -struct io_wq { - struct io_wqe **wqes; - unsigned long state; - - free_work_fn *free_work; - io_wq_work_fn *do_work; - - struct task_struct *manager; - struct user_struct *user; - refcount_t refs; - struct completion done; - - struct hlist_node cpuhp_node; - - refcount_t use_refs; -}; - -static enum cpuhp_state io_wq_online; - -static bool io_worker_get(struct io_worker *worker) -{ - return refcount_inc_not_zero(&worker->ref); -} - -static void io_worker_release(struct io_worker *worker) -{ - if (refcount_dec_and_test(&worker->ref)) - wake_up_process(worker->task); -} - -/* - * Note: drops the wqe->lock if returning true! The caller must re-acquire - * the lock in that case. Some callers need to restart handling if this - * happens, so we can't just re-acquire the lock on behalf of the caller. - */ -static bool __io_worker_unuse(struct io_wqe *wqe, struct io_worker *worker) -{ - bool dropped_lock = false; - - if (worker->saved_creds) { - revert_creds(worker->saved_creds); - worker->cur_creds = worker->saved_creds = NULL; - } - - if (current->files != worker->restore_files) { - __acquire(&wqe->lock); - raw_spin_unlock_irq(&wqe->lock); - dropped_lock = true; - - task_lock(current); - current->files = worker->restore_files; - current->nsproxy = worker->restore_nsproxy; - task_unlock(current); - } - - if (current->fs != worker->restore_fs) - current->fs = worker->restore_fs; - - /* - * If we have an active mm, we need to drop the wq lock before unusing - * it. If we do, return true and let the caller retry the idle loop. - */ - if (worker->mm) { - if (!dropped_lock) { - __acquire(&wqe->lock); - raw_spin_unlock_irq(&wqe->lock); - dropped_lock = true; - } - __set_current_state(TASK_RUNNING); - kthread_unuse_mm(worker->mm); - mmput(worker->mm); - worker->mm = NULL; - } - -#ifdef CONFIG_BLK_CGROUP - if (worker->blkcg_css) { - kthread_associate_blkcg(NULL); - worker->blkcg_css = NULL; - } -#endif - if (current->signal->rlim[RLIMIT_FSIZE].rlim_cur != RLIM_INFINITY) - current->signal->rlim[RLIMIT_FSIZE].rlim_cur = RLIM_INFINITY; - return dropped_lock; -} - -static inline struct io_wqe_acct *io_work_get_acct(struct io_wqe *wqe, - struct io_wq_work *work) -{ - if (work->flags & IO_WQ_WORK_UNBOUND) - return &wqe->acct[IO_WQ_ACCT_UNBOUND]; - - return &wqe->acct[IO_WQ_ACCT_BOUND]; -} - -static inline struct io_wqe_acct *io_wqe_get_acct(struct io_wqe *wqe, - struct io_worker *worker) -{ - if (worker->flags & IO_WORKER_F_BOUND) - return &wqe->acct[IO_WQ_ACCT_BOUND]; - - return &wqe->acct[IO_WQ_ACCT_UNBOUND]; -} - -static void io_worker_exit(struct io_worker *worker) -{ - struct io_wqe *wqe = worker->wqe; - struct io_wqe_acct *acct = io_wqe_get_acct(wqe, worker); - - /* - * If we're not at zero, someone else is holding a brief reference - * to the worker. Wait for that to go away. - */ - set_current_state(TASK_INTERRUPTIBLE); - if (!refcount_dec_and_test(&worker->ref)) - schedule(); - __set_current_state(TASK_RUNNING); - - preempt_disable(); - current->flags &= ~PF_IO_WORKER; - if (worker->flags & IO_WORKER_F_RUNNING) - atomic_dec(&acct->nr_running); - if (!(worker->flags & IO_WORKER_F_BOUND)) - atomic_dec(&wqe->wq->user->processes); - worker->flags = 0; - preempt_enable(); - - raw_spin_lock_irq(&wqe->lock); - hlist_nulls_del_rcu(&worker->nulls_node); - list_del_rcu(&worker->all_list); - if (__io_worker_unuse(wqe, worker)) { - __release(&wqe->lock); - raw_spin_lock_irq(&wqe->lock); - } - acct->nr_workers--; - raw_spin_unlock_irq(&wqe->lock); - - kfree_rcu(worker, rcu); - if (refcount_dec_and_test(&wqe->wq->refs)) - complete(&wqe->wq->done); -} - -static inline bool io_wqe_run_queue(struct io_wqe *wqe) - __must_hold(wqe->lock) -{ - if (!wq_list_empty(&wqe->work_list) && - !(wqe->flags & IO_WQE_FLAG_STALLED)) - return true; - return false; -} - -/* - * Check head of free list for an available worker. If one isn't available, - * caller must wake up the wq manager to create one. - */ -static bool io_wqe_activate_free_worker(struct io_wqe *wqe) - __must_hold(RCU) -{ - struct hlist_nulls_node *n; - struct io_worker *worker; - - n = rcu_dereference(hlist_nulls_first_rcu(&wqe->free_list)); - if (is_a_nulls(n)) - return false; - - worker = hlist_nulls_entry(n, struct io_worker, nulls_node); - if (io_worker_get(worker)) { - wake_up_process(worker->task); - io_worker_release(worker); - return true; - } - - return false; -} - -/* - * We need a worker. If we find a free one, we're good. If not, and we're - * below the max number of workers, wake up the manager to create one. - */ -static void io_wqe_wake_worker(struct io_wqe *wqe, struct io_wqe_acct *acct) -{ - bool ret; - - /* - * Most likely an attempt to queue unbounded work on an io_wq that - * wasn't setup with any unbounded workers. - */ - if (unlikely(!acct->max_workers)) - pr_warn_once("io-wq is not configured for unbound workers"); - - rcu_read_lock(); - ret = io_wqe_activate_free_worker(wqe); - rcu_read_unlock(); - - if (!ret && acct->nr_workers < acct->max_workers) - wake_up_process(wqe->wq->manager); -} - -static void io_wqe_inc_running(struct io_wqe *wqe, struct io_worker *worker) -{ - struct io_wqe_acct *acct = io_wqe_get_acct(wqe, worker); - - atomic_inc(&acct->nr_running); -} - -static void io_wqe_dec_running(struct io_wqe *wqe, struct io_worker *worker) - __must_hold(wqe->lock) -{ - struct io_wqe_acct *acct = io_wqe_get_acct(wqe, worker); - - if (atomic_dec_and_test(&acct->nr_running) && io_wqe_run_queue(wqe)) - io_wqe_wake_worker(wqe, acct); -} - -static void io_worker_start(struct io_wqe *wqe, struct io_worker *worker) -{ - allow_kernel_signal(SIGINT); - - current->flags |= PF_IO_WORKER; - - worker->flags |= (IO_WORKER_F_UP | IO_WORKER_F_RUNNING); - worker->restore_files = current->files; - worker->restore_nsproxy = current->nsproxy; - worker->restore_fs = current->fs; - io_wqe_inc_running(wqe, worker); -} - -/* - * Worker will start processing some work. Move it to the busy list, if - * it's currently on the freelist - */ -static void __io_worker_busy(struct io_wqe *wqe, struct io_worker *worker, - struct io_wq_work *work) - __must_hold(wqe->lock) -{ - bool worker_bound, work_bound; - - if (worker->flags & IO_WORKER_F_FREE) { - worker->flags &= ~IO_WORKER_F_FREE; - hlist_nulls_del_init_rcu(&worker->nulls_node); - } - - /* - * If worker is moving from bound to unbound (or vice versa), then - * ensure we update the running accounting. - */ - worker_bound = (worker->flags & IO_WORKER_F_BOUND) != 0; - work_bound = (work->flags & IO_WQ_WORK_UNBOUND) == 0; - if (worker_bound != work_bound) { - io_wqe_dec_running(wqe, worker); - if (work_bound) { - worker->flags |= IO_WORKER_F_BOUND; - wqe->acct[IO_WQ_ACCT_UNBOUND].nr_workers--; - wqe->acct[IO_WQ_ACCT_BOUND].nr_workers++; - atomic_dec(&wqe->wq->user->processes); - } else { - worker->flags &= ~IO_WORKER_F_BOUND; - wqe->acct[IO_WQ_ACCT_UNBOUND].nr_workers++; - wqe->acct[IO_WQ_ACCT_BOUND].nr_workers--; - atomic_inc(&wqe->wq->user->processes); - } - io_wqe_inc_running(wqe, worker); - } -} - -/* - * No work, worker going to sleep. Move to freelist, and unuse mm if we - * have one attached. Dropping the mm may potentially sleep, so we drop - * the lock in that case and return success. Since the caller has to - * retry the loop in that case (we changed task state), we don't regrab - * the lock if we return success. - */ -static bool __io_worker_idle(struct io_wqe *wqe, struct io_worker *worker) - __must_hold(wqe->lock) -{ - if (!(worker->flags & IO_WORKER_F_FREE)) { - worker->flags |= IO_WORKER_F_FREE; - hlist_nulls_add_head_rcu(&worker->nulls_node, &wqe->free_list); - } - - return __io_worker_unuse(wqe, worker); -} - -static inline unsigned int io_get_work_hash(struct io_wq_work *work) -{ - return work->flags >> IO_WQ_HASH_SHIFT; -} - -static struct io_wq_work *io_get_next_work(struct io_wqe *wqe) - __must_hold(wqe->lock) -{ - struct io_wq_work_node *node, *prev; - struct io_wq_work *work, *tail; - unsigned int hash; - - wq_list_for_each(node, prev, &wqe->work_list) { - work = container_of(node, struct io_wq_work, list); - - /* not hashed, can run anytime */ - if (!io_wq_is_hashed(work)) { - wq_list_del(&wqe->work_list, node, prev); - return work; - } - - /* hashed, can run if not already running */ - hash = io_get_work_hash(work); - if (!(wqe->hash_map & BIT(hash))) { - wqe->hash_map |= BIT(hash); - /* all items with this hash lie in [work, tail] */ - tail = wqe->hash_tail[hash]; - wqe->hash_tail[hash] = NULL; - wq_list_cut(&wqe->work_list, &tail->list, prev); - return work; - } - } - - return NULL; -} - -static void io_wq_switch_mm(struct io_worker *worker, struct io_wq_work *work) -{ - if (worker->mm) { - kthread_unuse_mm(worker->mm); - mmput(worker->mm); - worker->mm = NULL; - } - - if (mmget_not_zero(work->identity->mm)) { - kthread_use_mm(work->identity->mm); - worker->mm = work->identity->mm; - return; - } - - /* failed grabbing mm, ensure work gets cancelled */ - work->flags |= IO_WQ_WORK_CANCEL; -} - -static inline void io_wq_switch_blkcg(struct io_worker *worker, - struct io_wq_work *work) -{ -#ifdef CONFIG_BLK_CGROUP - if (!(work->flags & IO_WQ_WORK_BLKCG)) - return; - if (work->identity->blkcg_css != worker->blkcg_css) { - kthread_associate_blkcg(work->identity->blkcg_css); - worker->blkcg_css = work->identity->blkcg_css; - } -#endif -} - -static void io_wq_switch_creds(struct io_worker *worker, - struct io_wq_work *work) -{ - const struct cred *old_creds = override_creds(work->identity->creds); - - worker->cur_creds = work->identity->creds; - if (worker->saved_creds) - put_cred(old_creds); /* creds set by previous switch */ - else - worker->saved_creds = old_creds; -} - -static void io_impersonate_work(struct io_worker *worker, - struct io_wq_work *work) -{ - if ((work->flags & IO_WQ_WORK_FILES) && - current->files != work->identity->files) { - task_lock(current); - current->files = work->identity->files; - current->nsproxy = work->identity->nsproxy; - task_unlock(current); - if (!work->identity->files) { - /* failed grabbing files, ensure work gets cancelled */ - work->flags |= IO_WQ_WORK_CANCEL; - } - } - if ((work->flags & IO_WQ_WORK_FS) && current->fs != work->identity->fs) - current->fs = work->identity->fs; - if ((work->flags & IO_WQ_WORK_MM) && work->identity->mm != worker->mm) - io_wq_switch_mm(worker, work); - if ((work->flags & IO_WQ_WORK_CREDS) && - worker->cur_creds != work->identity->creds) - io_wq_switch_creds(worker, work); - if (work->flags & IO_WQ_WORK_FSIZE) - current->signal->rlim[RLIMIT_FSIZE].rlim_cur = work->identity->fsize; - else if (current->signal->rlim[RLIMIT_FSIZE].rlim_cur != RLIM_INFINITY) - current->signal->rlim[RLIMIT_FSIZE].rlim_cur = RLIM_INFINITY; - io_wq_switch_blkcg(worker, work); -#ifdef CONFIG_AUDIT - current->loginuid = work->identity->loginuid; - current->sessionid = work->identity->sessionid; -#endif -} - -static void io_assign_current_work(struct io_worker *worker, - struct io_wq_work *work) -{ - if (work) { - /* flush pending signals before assigning new work */ - if (signal_pending(current)) - flush_signals(current); - cond_resched(); - } - -#ifdef CONFIG_AUDIT - current->loginuid = KUIDT_INIT(AUDIT_UID_UNSET); - current->sessionid = AUDIT_SID_UNSET; -#endif - - spin_lock_irq(&worker->lock); - worker->cur_work = work; - spin_unlock_irq(&worker->lock); -} - -static void io_wqe_enqueue(struct io_wqe *wqe, struct io_wq_work *work); - -static void io_worker_handle_work(struct io_worker *worker) - __releases(wqe->lock) -{ - struct io_wqe *wqe = worker->wqe; - struct io_wq *wq = wqe->wq; - - do { - struct io_wq_work *work; -get_next: - /* - * If we got some work, mark us as busy. If we didn't, but - * the list isn't empty, it means we stalled on hashed work. - * Mark us stalled so we don't keep looking for work when we - * can't make progress, any work completion or insertion will - * clear the stalled flag. - */ - work = io_get_next_work(wqe); - if (work) - __io_worker_busy(wqe, worker, work); - else if (!wq_list_empty(&wqe->work_list)) - wqe->flags |= IO_WQE_FLAG_STALLED; - - raw_spin_unlock_irq(&wqe->lock); - if (!work) - break; - io_assign_current_work(worker, work); - - /* handle a whole dependent link */ - do { - struct io_wq_work *old_work, *next_hashed, *linked; - unsigned int hash = io_get_work_hash(work); - - next_hashed = wq_next_work(work); - io_impersonate_work(worker, work); - /* - * OK to set IO_WQ_WORK_CANCEL even for uncancellable - * work, the worker function will do the right thing. - */ - if (test_bit(IO_WQ_BIT_CANCEL, &wq->state)) - work->flags |= IO_WQ_WORK_CANCEL; - - old_work = work; - linked = wq->do_work(work); - - work = next_hashed; - if (!work && linked && !io_wq_is_hashed(linked)) { - work = linked; - linked = NULL; - } - io_assign_current_work(worker, work); - wq->free_work(old_work); - - if (linked) - io_wqe_enqueue(wqe, linked); - - if (hash != -1U && !next_hashed) { - raw_spin_lock_irq(&wqe->lock); - wqe->hash_map &= ~BIT_ULL(hash); - wqe->flags &= ~IO_WQE_FLAG_STALLED; - /* skip unnecessary unlock-lock wqe->lock */ - if (!work) - goto get_next; - raw_spin_unlock_irq(&wqe->lock); - } - } while (work); - - raw_spin_lock_irq(&wqe->lock); - } while (1); -} - -static int io_wqe_worker(void *data) -{ - struct io_worker *worker = data; - struct io_wqe *wqe = worker->wqe; - struct io_wq *wq = wqe->wq; - - io_worker_start(wqe, worker); - - while (!test_bit(IO_WQ_BIT_EXIT, &wq->state)) { - set_current_state(TASK_INTERRUPTIBLE); -loop: - raw_spin_lock_irq(&wqe->lock); - if (io_wqe_run_queue(wqe)) { - __set_current_state(TASK_RUNNING); - io_worker_handle_work(worker); - goto loop; - } - /* drops the lock on success, retry */ - if (__io_worker_idle(wqe, worker)) { - __release(&wqe->lock); - goto loop; - } - raw_spin_unlock_irq(&wqe->lock); - if (signal_pending(current)) - flush_signals(current); - if (schedule_timeout(WORKER_IDLE_TIMEOUT)) - continue; - /* timed out, exit unless we're the fixed worker */ - if (test_bit(IO_WQ_BIT_EXIT, &wq->state) || - !(worker->flags & IO_WORKER_F_FIXED)) - break; - } - - if (test_bit(IO_WQ_BIT_EXIT, &wq->state)) { - raw_spin_lock_irq(&wqe->lock); - if (!wq_list_empty(&wqe->work_list)) - io_worker_handle_work(worker); - else - raw_spin_unlock_irq(&wqe->lock); - } - - io_worker_exit(worker); - return 0; -} - -/* - * Called when a worker is scheduled in. Mark us as currently running. - */ -void io_wq_worker_running(struct task_struct *tsk) -{ - struct io_worker *worker = kthread_data(tsk); - struct io_wqe *wqe = worker->wqe; - - if (!(worker->flags & IO_WORKER_F_UP)) - return; - if (worker->flags & IO_WORKER_F_RUNNING) - return; - worker->flags |= IO_WORKER_F_RUNNING; - io_wqe_inc_running(wqe, worker); -} - -/* - * Called when worker is going to sleep. If there are no workers currently - * running and we have work pending, wake up a free one or have the manager - * set one up. - */ -void io_wq_worker_sleeping(struct task_struct *tsk) -{ - struct io_worker *worker = kthread_data(tsk); - struct io_wqe *wqe = worker->wqe; - - if (!(worker->flags & IO_WORKER_F_UP)) - return; - if (!(worker->flags & IO_WORKER_F_RUNNING)) - return; - - worker->flags &= ~IO_WORKER_F_RUNNING; - - raw_spin_lock_irq(&wqe->lock); - io_wqe_dec_running(wqe, worker); - raw_spin_unlock_irq(&wqe->lock); -} - -static bool create_io_worker(struct io_wq *wq, struct io_wqe *wqe, int index) -{ - struct io_wqe_acct *acct = &wqe->acct[index]; - struct io_worker *worker; - - worker = kzalloc_node(sizeof(*worker), GFP_KERNEL, wqe->node); - if (!worker) - return false; - - refcount_set(&worker->ref, 1); - worker->nulls_node.pprev = NULL; - worker->wqe = wqe; - spin_lock_init(&worker->lock); - - worker->task = kthread_create_on_node(io_wqe_worker, worker, wqe->node, - "io_wqe_worker-%d/%d", index, wqe->node); - if (IS_ERR(worker->task)) { - kfree(worker); - return false; - } - kthread_bind_mask(worker->task, cpumask_of_node(wqe->node)); - - raw_spin_lock_irq(&wqe->lock); - hlist_nulls_add_head_rcu(&worker->nulls_node, &wqe->free_list); - list_add_tail_rcu(&worker->all_list, &wqe->all_list); - worker->flags |= IO_WORKER_F_FREE; - if (index == IO_WQ_ACCT_BOUND) - worker->flags |= IO_WORKER_F_BOUND; - if (!acct->nr_workers && (worker->flags & IO_WORKER_F_BOUND)) - worker->flags |= IO_WORKER_F_FIXED; - acct->nr_workers++; - raw_spin_unlock_irq(&wqe->lock); - - if (index == IO_WQ_ACCT_UNBOUND) - atomic_inc(&wq->user->processes); - - refcount_inc(&wq->refs); - wake_up_process(worker->task); - return true; -} - -static inline bool io_wqe_need_worker(struct io_wqe *wqe, int index) - __must_hold(wqe->lock) -{ - struct io_wqe_acct *acct = &wqe->acct[index]; - - /* if we have available workers or no work, no need */ - if (!hlist_nulls_empty(&wqe->free_list) || !io_wqe_run_queue(wqe)) - return false; - return acct->nr_workers < acct->max_workers; -} - -static bool io_wqe_worker_send_sig(struct io_worker *worker, void *data) -{ - send_sig(SIGINT, worker->task, 1); - return false; -} - -/* - * Iterate the passed in list and call the specific function for each - * worker that isn't exiting - */ -static bool io_wq_for_each_worker(struct io_wqe *wqe, - bool (*func)(struct io_worker *, void *), - void *data) -{ - struct io_worker *worker; - bool ret = false; - - list_for_each_entry_rcu(worker, &wqe->all_list, all_list) { - if (io_worker_get(worker)) { - /* no task if node is/was offline */ - if (worker->task) - ret = func(worker, data); - io_worker_release(worker); - if (ret) - break; - } - } - - return ret; -} - -static bool io_wq_worker_wake(struct io_worker *worker, void *data) -{ - wake_up_process(worker->task); - return false; -} - -/* - * Manager thread. Tasked with creating new workers, if we need them. - */ -static int io_wq_manager(void *data) -{ - struct io_wq *wq = data; - int node; - - /* create fixed workers */ - refcount_set(&wq->refs, 1); - for_each_node(node) { - if (!node_online(node)) - continue; - if (create_io_worker(wq, wq->wqes[node], IO_WQ_ACCT_BOUND)) - continue; - set_bit(IO_WQ_BIT_ERROR, &wq->state); - set_bit(IO_WQ_BIT_EXIT, &wq->state); - goto out; - } - - complete(&wq->done); - - while (!kthread_should_stop()) { - if (current->task_works) - task_work_run(); - - for_each_node(node) { - struct io_wqe *wqe = wq->wqes[node]; - bool fork_worker[2] = { false, false }; - - if (!node_online(node)) - continue; - - raw_spin_lock_irq(&wqe->lock); - if (io_wqe_need_worker(wqe, IO_WQ_ACCT_BOUND)) - fork_worker[IO_WQ_ACCT_BOUND] = true; - if (io_wqe_need_worker(wqe, IO_WQ_ACCT_UNBOUND)) - fork_worker[IO_WQ_ACCT_UNBOUND] = true; - raw_spin_unlock_irq(&wqe->lock); - if (fork_worker[IO_WQ_ACCT_BOUND]) - create_io_worker(wq, wqe, IO_WQ_ACCT_BOUND); - if (fork_worker[IO_WQ_ACCT_UNBOUND]) - create_io_worker(wq, wqe, IO_WQ_ACCT_UNBOUND); - } - set_current_state(TASK_INTERRUPTIBLE); - schedule_timeout(HZ); - } - - if (current->task_works) - task_work_run(); - -out: - if (refcount_dec_and_test(&wq->refs)) { - complete(&wq->done); - return 0; - } - /* if ERROR is set and we get here, we have workers to wake */ - if (test_bit(IO_WQ_BIT_ERROR, &wq->state)) { - rcu_read_lock(); - for_each_node(node) - io_wq_for_each_worker(wq->wqes[node], io_wq_worker_wake, NULL); - rcu_read_unlock(); - } - return 0; -} - -static bool io_wq_can_queue(struct io_wqe *wqe, struct io_wqe_acct *acct, - struct io_wq_work *work) -{ - bool free_worker; - - if (!(work->flags & IO_WQ_WORK_UNBOUND)) - return true; - if (atomic_read(&acct->nr_running)) - return true; - - rcu_read_lock(); - free_worker = !hlist_nulls_empty(&wqe->free_list); - rcu_read_unlock(); - if (free_worker) - return true; - - if (atomic_read(&wqe->wq->user->processes) >= acct->max_workers && - !(capable(CAP_SYS_RESOURCE) || capable(CAP_SYS_ADMIN))) - return false; - - return true; -} - -static void io_run_cancel(struct io_wq_work *work, struct io_wqe *wqe) -{ - struct io_wq *wq = wqe->wq; - - do { - struct io_wq_work *old_work = work; - - work->flags |= IO_WQ_WORK_CANCEL; - work = wq->do_work(work); - wq->free_work(old_work); - } while (work); -} - -static void io_wqe_insert_work(struct io_wqe *wqe, struct io_wq_work *work) -{ - unsigned int hash; - struct io_wq_work *tail; - - if (!io_wq_is_hashed(work)) { -append: - wq_list_add_tail(&work->list, &wqe->work_list); - return; - } - - hash = io_get_work_hash(work); - tail = wqe->hash_tail[hash]; - wqe->hash_tail[hash] = work; - if (!tail) - goto append; - - wq_list_add_after(&work->list, &tail->list, &wqe->work_list); -} - -static void io_wqe_enqueue(struct io_wqe *wqe, struct io_wq_work *work) -{ - struct io_wqe_acct *acct = io_work_get_acct(wqe, work); - bool do_wake; - unsigned long flags; - - /* - * Do early check to see if we need a new unbound worker, and if we do, - * if we're allowed to do so. This isn't 100% accurate as there's a - * gap between this check and incrementing the value, but that's OK. - * It's close enough to not be an issue, fork() has the same delay. - */ - if (unlikely(!io_wq_can_queue(wqe, acct, work))) { - io_run_cancel(work, wqe); - return; - } - - raw_spin_lock_irqsave(&wqe->lock, flags); - io_wqe_insert_work(wqe, work); - wqe->flags &= ~IO_WQE_FLAG_STALLED; - do_wake = (work->flags & IO_WQ_WORK_CONCURRENT) || - !atomic_read(&acct->nr_running); - raw_spin_unlock_irqrestore(&wqe->lock, flags); - - if (do_wake) - io_wqe_wake_worker(wqe, acct); -} - -void io_wq_enqueue(struct io_wq *wq, struct io_wq_work *work) -{ - struct io_wqe *wqe = wq->wqes[numa_node_id()]; - - io_wqe_enqueue(wqe, work); -} - -/* - * Work items that hash to the same value will not be done in parallel. - * Used to limit concurrent writes, generally hashed by inode. - */ -void io_wq_hash_work(struct io_wq_work *work, void *val) -{ - unsigned int bit; - - bit = hash_ptr(val, IO_WQ_HASH_ORDER); - work->flags |= (IO_WQ_WORK_HASHED | (bit << IO_WQ_HASH_SHIFT)); -} - -void io_wq_cancel_all(struct io_wq *wq) -{ - int node; - - set_bit(IO_WQ_BIT_CANCEL, &wq->state); - - rcu_read_lock(); - for_each_node(node) { - struct io_wqe *wqe = wq->wqes[node]; - - io_wq_for_each_worker(wqe, io_wqe_worker_send_sig, NULL); - } - rcu_read_unlock(); -} - -struct io_cb_cancel_data { - work_cancel_fn *fn; - void *data; - int nr_running; - int nr_pending; - bool cancel_all; -}; - -static bool io_wq_worker_cancel(struct io_worker *worker, void *data) -{ - struct io_cb_cancel_data *match = data; - unsigned long flags; - - /* - * Hold the lock to avoid ->cur_work going out of scope, caller - * may dereference the passed in work. - */ - spin_lock_irqsave(&worker->lock, flags); - if (worker->cur_work && - !(worker->cur_work->flags & IO_WQ_WORK_NO_CANCEL) && - match->fn(worker->cur_work, match->data)) { - send_sig(SIGINT, worker->task, 1); - match->nr_running++; - } - spin_unlock_irqrestore(&worker->lock, flags); - - return match->nr_running && !match->cancel_all; -} - -static inline void io_wqe_remove_pending(struct io_wqe *wqe, - struct io_wq_work *work, - struct io_wq_work_node *prev) -{ - unsigned int hash = io_get_work_hash(work); - struct io_wq_work *prev_work = NULL; - - if (io_wq_is_hashed(work) && work == wqe->hash_tail[hash]) { - if (prev) - prev_work = container_of(prev, struct io_wq_work, list); - if (prev_work && io_get_work_hash(prev_work) == hash) - wqe->hash_tail[hash] = prev_work; - else - wqe->hash_tail[hash] = NULL; - } - wq_list_del(&wqe->work_list, &work->list, prev); -} - -static void io_wqe_cancel_pending_work(struct io_wqe *wqe, - struct io_cb_cancel_data *match) -{ - struct io_wq_work_node *node, *prev; - struct io_wq_work *work; - unsigned long flags; - -retry: - raw_spin_lock_irqsave(&wqe->lock, flags); - wq_list_for_each(node, prev, &wqe->work_list) { - work = container_of(node, struct io_wq_work, list); - if (!match->fn(work, match->data)) - continue; - io_wqe_remove_pending(wqe, work, prev); - raw_spin_unlock_irqrestore(&wqe->lock, flags); - io_run_cancel(work, wqe); - match->nr_pending++; - if (!match->cancel_all) - return; - - /* not safe to continue after unlock */ - goto retry; - } - raw_spin_unlock_irqrestore(&wqe->lock, flags); -} - -static void io_wqe_cancel_running_work(struct io_wqe *wqe, - struct io_cb_cancel_data *match) -{ - rcu_read_lock(); - io_wq_for_each_worker(wqe, io_wq_worker_cancel, match); - rcu_read_unlock(); -} - -enum io_wq_cancel io_wq_cancel_cb(struct io_wq *wq, work_cancel_fn *cancel, - void *data, bool cancel_all) -{ - struct io_cb_cancel_data match = { - .fn = cancel, - .data = data, - .cancel_all = cancel_all, - }; - int node; - - /* - * First check pending list, if we're lucky we can just remove it - * from there. CANCEL_OK means that the work is returned as-new, - * no completion will be posted for it. - */ - for_each_node(node) { - struct io_wqe *wqe = wq->wqes[node]; - - io_wqe_cancel_pending_work(wqe, &match); - if (match.nr_pending && !match.cancel_all) - return IO_WQ_CANCEL_OK; - } - - /* - * Now check if a free (going busy) or busy worker has the work - * currently running. If we find it there, we'll return CANCEL_RUNNING - * as an indication that we attempt to signal cancellation. The - * completion will run normally in this case. - */ - for_each_node(node) { - struct io_wqe *wqe = wq->wqes[node]; - - io_wqe_cancel_running_work(wqe, &match); - if (match.nr_running && !match.cancel_all) - return IO_WQ_CANCEL_RUNNING; - } - - if (match.nr_running) - return IO_WQ_CANCEL_RUNNING; - if (match.nr_pending) - return IO_WQ_CANCEL_OK; - return IO_WQ_CANCEL_NOTFOUND; -} - -struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data) -{ - int ret = -ENOMEM, node; - struct io_wq *wq; - - if (WARN_ON_ONCE(!data->free_work || !data->do_work)) - return ERR_PTR(-EINVAL); - if (WARN_ON_ONCE(!bounded)) - return ERR_PTR(-EINVAL); - - wq = kzalloc(sizeof(*wq), GFP_KERNEL); - if (!wq) - return ERR_PTR(-ENOMEM); - - wq->wqes = kcalloc(nr_node_ids, sizeof(struct io_wqe *), GFP_KERNEL); - if (!wq->wqes) - goto err_wq; - - ret = cpuhp_state_add_instance_nocalls(io_wq_online, &wq->cpuhp_node); - if (ret) - goto err_wqes; - - wq->free_work = data->free_work; - wq->do_work = data->do_work; - - /* caller must already hold a reference to this */ - wq->user = data->user; - - ret = -ENOMEM; - for_each_node(node) { - struct io_wqe *wqe; - int alloc_node = node; - - if (!node_online(alloc_node)) - alloc_node = NUMA_NO_NODE; - wqe = kzalloc_node(sizeof(struct io_wqe), GFP_KERNEL, alloc_node); - if (!wqe) - goto err; - wq->wqes[node] = wqe; - wqe->node = alloc_node; - wqe->acct[IO_WQ_ACCT_BOUND].max_workers = bounded; - atomic_set(&wqe->acct[IO_WQ_ACCT_BOUND].nr_running, 0); - if (wq->user) { - wqe->acct[IO_WQ_ACCT_UNBOUND].max_workers = - task_rlimit(current, RLIMIT_NPROC); - } - atomic_set(&wqe->acct[IO_WQ_ACCT_UNBOUND].nr_running, 0); - wqe->wq = wq; - raw_spin_lock_init(&wqe->lock); - INIT_WQ_LIST(&wqe->work_list); - INIT_HLIST_NULLS_HEAD(&wqe->free_list, 0); - INIT_LIST_HEAD(&wqe->all_list); - } - - init_completion(&wq->done); - - wq->manager = kthread_create(io_wq_manager, wq, "io_wq_manager"); - if (!IS_ERR(wq->manager)) { - wake_up_process(wq->manager); - wait_for_completion(&wq->done); - if (test_bit(IO_WQ_BIT_ERROR, &wq->state)) { - ret = -ENOMEM; - goto err; - } - refcount_set(&wq->use_refs, 1); - reinit_completion(&wq->done); - return wq; - } - - ret = PTR_ERR(wq->manager); - complete(&wq->done); -err: - cpuhp_state_remove_instance_nocalls(io_wq_online, &wq->cpuhp_node); - for_each_node(node) - kfree(wq->wqes[node]); -err_wqes: - kfree(wq->wqes); -err_wq: - kfree(wq); - return ERR_PTR(ret); -} - -bool io_wq_get(struct io_wq *wq, struct io_wq_data *data) -{ - if (data->free_work != wq->free_work || data->do_work != wq->do_work) - return false; - - return refcount_inc_not_zero(&wq->use_refs); -} - -static void __io_wq_destroy(struct io_wq *wq) -{ - int node; - - cpuhp_state_remove_instance_nocalls(io_wq_online, &wq->cpuhp_node); - - set_bit(IO_WQ_BIT_EXIT, &wq->state); - if (wq->manager) - kthread_stop(wq->manager); - - rcu_read_lock(); - for_each_node(node) - io_wq_for_each_worker(wq->wqes[node], io_wq_worker_wake, NULL); - rcu_read_unlock(); - - wait_for_completion(&wq->done); - - for_each_node(node) - kfree(wq->wqes[node]); - kfree(wq->wqes); - kfree(wq); -} - -void io_wq_destroy(struct io_wq *wq) -{ - if (refcount_dec_and_test(&wq->use_refs)) - __io_wq_destroy(wq); -} - -struct task_struct *io_wq_get_task(struct io_wq *wq) -{ - return wq->manager; -} - -static bool io_wq_worker_affinity(struct io_worker *worker, void *data) -{ - struct task_struct *task = worker->task; - struct rq_flags rf; - struct rq *rq; - - rq = task_rq_lock(task, &rf); - do_set_cpus_allowed(task, cpumask_of_node(worker->wqe->node)); - task->flags |= PF_NO_SETAFFINITY; - task_rq_unlock(rq, task, &rf); - return false; -} - -static int io_wq_cpu_online(unsigned int cpu, struct hlist_node *node) -{ - struct io_wq *wq = hlist_entry_safe(node, struct io_wq, cpuhp_node); - int i; - - rcu_read_lock(); - for_each_node(i) - io_wq_for_each_worker(wq->wqes[i], io_wq_worker_affinity, NULL); - rcu_read_unlock(); - return 0; -} - -static __init int io_wq_init(void) -{ - int ret; - - ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN, "io-wq/online", - io_wq_cpu_online, NULL); - if (ret < 0) - return ret; - io_wq_online = ret; - return 0; -} -subsys_initcall(io_wq_init); diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index 98cfa73cb165bc512987bfb9ede08ad447f082c8..fa24b407a9dcb0ae62900a4cf19f544e997ce617 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -581,7 +581,7 @@ void jbd2_journal_commit_transaction(journal_t *journal) journal->j_running_transaction = NULL; start_time = ktime_get(); commit_transaction->t_log_start = journal->j_head; - wake_up(&journal->j_wait_transaction_locked); + wake_up_all(&journal->j_wait_transaction_locked); write_unlock(&journal->j_state_lock); jbd_debug(3, "JBD2: commit phase 2a\n"); diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 099e4319851d8067cf27c0de2a8bb40b268fc2b2..a076213214650058f889621970379ff7e2e8a835 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -924,10 +924,16 @@ int jbd2_fc_wait_bufs(journal_t *journal, int num_blks) for (i = j_fc_off - 1; i >= j_fc_off - num_blks; i--) { bh = journal->j_fc_wbuf[i]; wait_on_buffer(bh); + /* + * Update j_fc_off so jbd2_fc_release_bufs can release remain + * buffer head. + */ + if (unlikely(!buffer_uptodate(bh))) { + journal->j_fc_off = i + 1; + return -EIO; + } put_bh(bh); journal->j_fc_wbuf[i] = NULL; - if (unlikely(!buffer_uptodate(bh))) - return -EIO; } return 0; diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c index 1e07dfac4d8117bc1d941a329b56494b1f84ff58..1ae1697fe99bdf7227c31a2456979834ec2f2824 100644 --- a/fs/jbd2/recovery.c +++ b/fs/jbd2/recovery.c @@ -256,6 +256,7 @@ static int fc_do_one_pass(journal_t *journal, err = journal->j_fc_replay_callback(journal, bh, pass, next_fc_block - journal->j_fc_first, expected_commit_id); + brelse(bh); next_fc_block++; if (err < 0 || err == JBD2_FC_REPLAY_STOP) break; diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 0f1cef90fa7d67ba3240f6399427a5138955f40f..86472212cce17971f5f2dc1074cb2f29456c1a07 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -173,7 +173,7 @@ static void wait_transaction_locked(journal_t *journal) int need_to_start; tid_t tid = journal->j_running_transaction->t_tid; - prepare_to_wait(&journal->j_wait_transaction_locked, &wait, + prepare_to_wait_exclusive(&journal->j_wait_transaction_locked, &wait, TASK_UNINTERRUPTIBLE); need_to_start = !tid_geq(journal->j_commit_request, tid); read_unlock(&journal->j_state_lock); @@ -199,7 +199,7 @@ static void wait_transaction_switching(journal_t *journal) read_unlock(&journal->j_state_lock); return; } - prepare_to_wait(&journal->j_wait_transaction_locked, &wait, + prepare_to_wait_exclusive(&journal->j_wait_transaction_locked, &wait, TASK_UNINTERRUPTIBLE); read_unlock(&journal->j_state_lock); /* @@ -894,7 +894,7 @@ void jbd2_journal_unlock_updates (journal_t *journal) write_lock(&journal->j_state_lock); --journal->j_barrier_count; write_unlock(&journal->j_state_lock); - wake_up(&journal->j_wait_transaction_locked); + wake_up_all(&journal->j_wait_transaction_locked); } static void warn_dirty_buffer(struct buffer_head *bh) diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index afb39e1bbe3bf9cafb6a296a1d6d56a1cffe3583..8b3c86a502daa4cbedddb0276b3eb62d4bf8bf50 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -1519,8 +1519,11 @@ int kernfs_remove_by_name_ns(struct kernfs_node *parent, const char *name, mutex_lock(&kernfs_mutex); kn = kernfs_find_ns(parent, name, ns); - if (kn) + if (kn) { + kernfs_get(kn); __kernfs_remove(kn); + kernfs_put(kn); + } mutex_unlock(&kernfs_mutex); diff --git a/fs/namei.c b/fs/namei.c index 0719b0065afb31b6c2579f484d15d6d7fe6920d6..ce367432416341a0fee2dfc469d87d3bd1949a19 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -532,6 +532,8 @@ static void set_nameidata(struct nameidata *p, int dfd, struct filename *name) p->stack = p->internal; p->dfd = dfd; p->name = name; + p->path.mnt = NULL; + p->path.dentry = NULL; p->total_link_count = old ? old->total_link_count : 0; p->saved = old; current->nameidata = p; @@ -605,6 +607,8 @@ static void terminate_walk(struct nameidata *nd) rcu_read_unlock(); } nd->depth = 0; + nd->path.mnt = NULL; + nd->path.dentry = NULL; } /* path_put is needed afterwards regardless of success or failure */ @@ -633,6 +637,11 @@ static inline bool legitimize_path(struct nameidata *nd, static bool legitimize_links(struct nameidata *nd) { int i; + if (unlikely(nd->flags & LOOKUP_CACHED)) { + drop_links(nd); + nd->depth = 0; + return false; + } for (i = 0; i < nd->depth; i++) { struct saved *last = nd->stack + i; if (unlikely(!legitimize_path(nd, &last->link, last->seq))) { @@ -708,19 +717,19 @@ out: } /** - * unlazy_child - try to switch to ref-walk mode. + * try_to_unlazy_next - try to switch to ref-walk mode. * @nd: nameidata pathwalk data - * @dentry: child of nd->path.dentry - * @seq: seq number to check dentry against - * Returns: 0 on success, -ECHILD on failure + * @dentry: next dentry to step into + * @seq: seq number to check @dentry against + * Returns: true on success, false on failure * - * unlazy_child attempts to legitimize the current nd->path, nd->root and dentry - * for ref-walk mode. @dentry must be a path found by a do_lookup call on - * @nd. Must be called from rcu-walk context. - * Nothing should touch nameidata between unlazy_child() failure and + * Similar to to try_to_unlazy(), but here we have the next dentry already + * picked by rcu-walk and want to legitimize that in addition to the current + * nd->path and nd->root for ref-walk mode. Must be called from rcu-walk context. + * Nothing should touch nameidata between try_to_unlazy_next() failure and * terminate_walk(). */ -static int unlazy_child(struct nameidata *nd, struct dentry *dentry, unsigned seq) +static bool try_to_unlazy_next(struct nameidata *nd, struct dentry *dentry, unsigned seq) { BUG_ON(!(nd->flags & LOOKUP_RCU)); @@ -750,7 +759,7 @@ static int unlazy_child(struct nameidata *nd, struct dentry *dentry, unsigned se if (unlikely(!legitimize_root(nd))) goto out_dput; rcu_read_unlock(); - return 0; + return true; out2: nd->path.mnt = NULL; @@ -758,11 +767,11 @@ out1: nd->path.dentry = NULL; out: rcu_read_unlock(); - return -ECHILD; + return false; out_dput: rcu_read_unlock(); dput(dentry); - return -ECHILD; + return false; } static inline int d_revalidate(struct dentry *dentry, unsigned int flags) @@ -870,6 +879,7 @@ static int complete_walk(struct nameidata *nd) */ if (!(nd->flags & (LOOKUP_ROOT | LOOKUP_IS_SCOPED))) nd->root.mnt = NULL; + nd->flags &= ~LOOKUP_CACHED; if (!try_to_unlazy(nd)) return -ECHILD; } @@ -1458,7 +1468,7 @@ static inline int handle_mounts(struct nameidata *nd, struct dentry *dentry, return -ENOENT; if (likely(__follow_mount_rcu(nd, path, inode, seqp))) return 0; - if (unlazy_child(nd, dentry, seq)) + if (!try_to_unlazy_next(nd, dentry, seq)) return -ECHILD; // *path might've been clobbered by __follow_mount_rcu() path->mnt = nd->path.mnt; @@ -1579,7 +1589,7 @@ static struct dentry *lookup_fast(struct nameidata *nd, status = d_revalidate(dentry, nd->flags); if (likely(status > 0)) return dentry; - if (unlazy_child(nd, dentry, seq)) + if (!try_to_unlazy_next(nd, dentry, seq)) return ERR_PTR(-ECHILD); if (unlikely(status == -ECHILD)) /* we'd been told to redo it in non-rcu mode */ @@ -2288,6 +2298,10 @@ static const char *path_init(struct nameidata *nd, unsigned flags) int error; const char *s = nd->name->name; + /* LOOKUP_CACHED requires RCU, ask caller to retry */ + if ((flags & (LOOKUP_RCU | LOOKUP_CACHED)) == LOOKUP_CACHED) + return ERR_PTR(-EAGAIN); + if (!*s) flags &= ~LOOKUP_RCU; if (flags & LOOKUP_RCU) @@ -2317,8 +2331,6 @@ static const char *path_init(struct nameidata *nd, unsigned flags) } nd->root.mnt = NULL; - nd->path.mnt = NULL; - nd->path.dentry = NULL; /* Absolute pathname -- fetch the root (LOOKUP_IN_ROOT uses nd->dfd). */ if (*s == '/' && !(flags & LOOKUP_IN_ROOT)) { @@ -4425,8 +4437,8 @@ out: } EXPORT_SYMBOL_NS(vfs_rename, ANDROID_GKI_VFS_EXPORT_ONLY); -static int do_renameat2(int olddfd, const char __user *oldname, int newdfd, - const char __user *newname, unsigned int flags) +int do_renameat2(int olddfd, struct filename *from, int newdfd, + struct filename *to, unsigned int flags) { struct dentry *old_dentry, *new_dentry; struct dentry *trap; @@ -4434,32 +4446,30 @@ static int do_renameat2(int olddfd, const char __user *oldname, int newdfd, struct qstr old_last, new_last; int old_type, new_type; struct inode *delegated_inode = NULL; - struct filename *from; - struct filename *to; unsigned int lookup_flags = 0, target_flags = LOOKUP_RENAME_TARGET; bool should_retry = false; - int error; + int error = -EINVAL; if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE | RENAME_WHITEOUT)) - return -EINVAL; + goto put_both; if ((flags & (RENAME_NOREPLACE | RENAME_WHITEOUT)) && (flags & RENAME_EXCHANGE)) - return -EINVAL; + goto put_both; if (flags & RENAME_EXCHANGE) target_flags = 0; retry: - from = filename_parentat(olddfd, getname(oldname), lookup_flags, - &old_path, &old_last, &old_type); + from = filename_parentat(olddfd, from, lookup_flags, &old_path, + &old_last, &old_type); if (IS_ERR(from)) { error = PTR_ERR(from); - goto exit; + goto put_new; } - to = filename_parentat(newdfd, getname(newname), lookup_flags, - &new_path, &new_last, &new_type); + to = filename_parentat(newdfd, to, lookup_flags, &new_path, &new_last, + &new_type); if (IS_ERR(to)) { error = PTR_ERR(to); goto exit1; @@ -4552,34 +4562,40 @@ exit2: if (retry_estale(error, lookup_flags)) should_retry = true; path_put(&new_path); - putname(to); exit1: path_put(&old_path); - putname(from); if (should_retry) { should_retry = false; lookup_flags |= LOOKUP_REVAL; goto retry; } -exit: +put_both: + if (!IS_ERR(from)) + putname(from); +put_new: + if (!IS_ERR(to)) + putname(to); return error; } SYSCALL_DEFINE5(renameat2, int, olddfd, const char __user *, oldname, int, newdfd, const char __user *, newname, unsigned int, flags) { - return do_renameat2(olddfd, oldname, newdfd, newname, flags); + return do_renameat2(olddfd, getname(oldname), newdfd, getname(newname), + flags); } SYSCALL_DEFINE4(renameat, int, olddfd, const char __user *, oldname, int, newdfd, const char __user *, newname) { - return do_renameat2(olddfd, oldname, newdfd, newname, 0); + return do_renameat2(olddfd, getname(oldname), newdfd, getname(newname), + 0); } SYSCALL_DEFINE2(rename, const char __user *, oldname, const char __user *, newname) { - return do_renameat2(AT_FDCWD, oldname, AT_FDCWD, newname, 0); + return do_renameat2(AT_FDCWD, getname(oldname), AT_FDCWD, + getname(newname), 0); } int readlink_copy(char __user *buffer, int buflen, const char *link) @@ -4717,7 +4733,7 @@ int __page_symlink(struct inode *inode, const char *symname, int len, int nofs) { struct address_space *mapping = inode->i_mapping; struct page *page; - void *fsdata; + void *fsdata = NULL; int err; unsigned int flags = 0; if (nofs) diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index d6ac2c4f88b6b42bb81c1010c9430c82dcf47018..1eb6c7a142ff0036d48b1984fff022b8b2e11cd0 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -228,8 +228,7 @@ again: * */ void nfs_inode_reclaim_delegation(struct inode *inode, const struct cred *cred, - fmode_t type, - const nfs4_stateid *stateid, + fmode_t type, const nfs4_stateid *stateid, unsigned long pagemod_limit) { struct nfs_delegation *delegation; @@ -239,25 +238,24 @@ void nfs_inode_reclaim_delegation(struct inode *inode, const struct cred *cred, delegation = rcu_dereference(NFS_I(inode)->delegation); if (delegation != NULL) { spin_lock(&delegation->lock); - if (nfs4_is_valid_delegation(delegation, 0)) { - nfs4_stateid_copy(&delegation->stateid, stateid); - delegation->type = type; - delegation->pagemod_limit = pagemod_limit; - oldcred = delegation->cred; - delegation->cred = get_cred(cred); - clear_bit(NFS_DELEGATION_NEED_RECLAIM, - &delegation->flags); - spin_unlock(&delegation->lock); - rcu_read_unlock(); - put_cred(oldcred); - trace_nfs4_reclaim_delegation(inode, type); - return; - } - /* We appear to have raced with a delegation return. */ + nfs4_stateid_copy(&delegation->stateid, stateid); + delegation->type = type; + delegation->pagemod_limit = pagemod_limit; + oldcred = delegation->cred; + delegation->cred = get_cred(cred); + clear_bit(NFS_DELEGATION_NEED_RECLAIM, &delegation->flags); + if (test_and_clear_bit(NFS_DELEGATION_REVOKED, + &delegation->flags)) + atomic_long_inc(&nfs_active_delegations); spin_unlock(&delegation->lock); + rcu_read_unlock(); + put_cred(oldcred); + trace_nfs4_reclaim_delegation(inode, type); + } else { + rcu_read_unlock(); + nfs_inode_set_delegation(inode, cred, type, stateid, + pagemod_limit); } - rcu_read_unlock(); - nfs_inode_set_delegation(inode, cred, type, stateid, pagemod_limit); } static int nfs_do_return_delegation(struct inode *inode, struct nfs_delegation *delegation, int issync) diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index 0e6437b08a3a502bdb3bbbb792294d59fb051b2a..252c99c76a42d381ed8d26587121ab39a2b4dc74 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -346,6 +346,7 @@ int nfs40_init_client(struct nfs_client *clp) ret = nfs4_setup_slot_table(tbl, NFS4_MAX_SLOT_TABLE, "NFSv4.0 transport Slot table"); if (ret) { + nfs4_shutdown_slot_table(tbl); kfree(tbl); return ret; } diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index d9f14d6e8fd87765a02b2a20fb809aafaae756a9..a576b0e287117faa8f43bfa17e1d89b0c6bc9ef3 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -7014,6 +7014,7 @@ static void nfs4_lock_done(struct rpc_task *task, void *calldata) { struct nfs4_lockdata *data = calldata; struct nfs4_lock_state *lsp = data->lsp; + struct nfs_server *server = NFS_SERVER(d_inode(data->ctx->dentry)); dprintk("%s: begin!\n", __func__); @@ -7023,8 +7024,7 @@ static void nfs4_lock_done(struct rpc_task *task, void *calldata) data->rpc_status = task->tk_status; switch (task->tk_status) { case 0: - renew_lease(NFS_SERVER(d_inode(data->ctx->dentry)), - data->timestamp); + renew_lease(server, data->timestamp); if (data->arg.new_lock && !data->cancelled) { data->fl.fl_flags &= ~(FL_SLEEP | FL_ACCESS); if (locks_lock_inode_wait(lsp->ls_state->inode, &data->fl) < 0) @@ -7045,6 +7045,8 @@ static void nfs4_lock_done(struct rpc_task *task, void *calldata) if (!nfs4_stateid_match(&data->arg.open_stateid, &lsp->ls_state->open_stateid)) goto out_restart; + else if (nfs4_async_handle_error(task, server, lsp->ls_state, NULL) == -EAGAIN) + goto out_restart; } else if (!nfs4_stateid_match(&data->arg.lock_stateid, &lsp->ls_stateid)) goto out_restart; diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index a8fe8f84c5ae00dcc0387617314cff2d9fa6a676..a77a3d8c0b3f4932cab4ae79811e487a29d6482e 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1777,6 +1777,7 @@ static void nfs4_state_mark_reclaim_helper(struct nfs_client *clp, static void nfs4_state_start_reclaim_reboot(struct nfs_client *clp) { + set_bit(NFS4CLNT_RECLAIM_REBOOT, &clp->cl_state); /* Mark all delegations for reclaim */ nfs_delegation_mark_reclaim(clp); nfs4_state_mark_reclaim_helper(clp, nfs4_state_mark_reclaim_reboot); @@ -2642,6 +2643,7 @@ static void nfs4_state_manager(struct nfs_client *clp) if (status < 0) goto out_error; nfs4_state_end_reclaim_reboot(clp); + continue; } /* Detect expired delegations... */ diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c index f9b730c43192db468f802480786a80d68ccefde2..83c4e68839537917a1d83be5aa4f3afa585c72c0 100644 --- a/fs/nfsd/nfs4recover.c +++ b/fs/nfsd/nfs4recover.c @@ -815,8 +815,10 @@ __cld_pipe_inprogress_downcall(const struct cld_msg_v2 __user *cmsg, princhash.data = memdup_user( &ci->cc_princhash.cp_data, princhashlen); - if (IS_ERR_OR_NULL(princhash.data)) + if (IS_ERR_OR_NULL(princhash.data)) { + kfree(name.data); return -EFAULT; + } princhash.len = princhashlen; } else princhash.len = 0; diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index f1b503bec222131f26c92919101e594b67bf17f8..665d0eaeb8dbfccd0bb6fb82c8cc206425c881d2 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -843,6 +843,7 @@ static struct nfs4_ol_stateid * nfs4_alloc_open_stateid(struct nfs4_client *clp) static void nfs4_free_deleg(struct nfs4_stid *stid) { + WARN_ON(!list_empty(&stid->sc_cp_list)); kmem_cache_free(deleg_slab, stid); atomic_long_dec(&num_delegations); } @@ -1358,6 +1359,7 @@ static void nfs4_free_ol_stateid(struct nfs4_stid *stid) release_all_access(stp); if (stp->st_stateowner) nfs4_put_stateowner(stp->st_stateowner); + WARN_ON(!list_empty(&stid->sc_cp_list)); kmem_cache_free(stateid_slab, stid); } @@ -6207,6 +6209,7 @@ static void nfsd4_close_open_stateid(struct nfs4_ol_stateid *s) struct nfs4_client *clp = s->st_stid.sc_client; bool unhashed; LIST_HEAD(reaplist); + struct nfs4_ol_stateid *stp; spin_lock(&clp->cl_lock); unhashed = unhash_open_stateid(s, &reaplist); @@ -6215,6 +6218,8 @@ static void nfsd4_close_open_stateid(struct nfs4_ol_stateid *s) if (unhashed) put_ol_stateid_locked(s, &reaplist); spin_unlock(&clp->cl_lock); + list_for_each_entry(stp, &reaplist, st_locks) + nfs4_free_cpntf_statelist(clp->net, &stp->st_stid); free_ol_stateid_reaplist(&reaplist); } else { spin_unlock(&clp->cl_lock); diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 46f825cf53f4f271a0d1fcb8d31b98cbbf15c1ee..cc605ee0b2fae7b23c6635a0112fca081f5cb97e 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -3871,7 +3871,7 @@ nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr, if (resp->xdr.buf->page_len && test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags)) { WARN_ON_ONCE(1); - return nfserr_resource; + return nfserr_serverfault; } xdr_commit_encode(xdr); diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index 545f764d70b12345c62c906865f8643e3066b617..5ee4973525f0155a21fe094e139f2e0928f8c4bb 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -322,7 +322,7 @@ void nilfs_relax_pressure_in_lock(struct super_block *sb) struct the_nilfs *nilfs = sb->s_fs_info; struct nilfs_sc_info *sci = nilfs->ns_writer; - if (!sci || !sci->sc_flush_request) + if (sb_rdonly(sb) || unlikely(!sci) || !sci->sc_flush_request) return; set_bit(NILFS_SC_PRIOR_FLUSH, &sci->sc_flags); @@ -2248,7 +2248,7 @@ int nilfs_construct_segment(struct super_block *sb) struct nilfs_transaction_info *ti; int err; - if (!sci) + if (sb_rdonly(sb) || unlikely(!sci)) return -EROFS; /* A call inside transactions causes a deadlock. */ @@ -2287,7 +2287,7 @@ int nilfs_construct_dsync_segment(struct super_block *sb, struct inode *inode, struct nilfs_transaction_info ti; int err = 0; - if (!sci) + if (sb_rdonly(sb) || unlikely(!sci)) return -EROFS; nilfs_transaction_lock(sb, &ti, 0); @@ -2783,11 +2783,12 @@ int nilfs_attach_log_writer(struct super_block *sb, struct nilfs_root *root) if (nilfs->ns_writer) { /* - * This happens if the filesystem was remounted - * read/write after nilfs_error degenerated it into a - * read-only mount. + * This happens if the filesystem is made read-only by + * __nilfs_error or nilfs_remount and then remounted + * read/write. In these cases, reuse the existing + * writer. */ - nilfs_detach_log_writer(sb); + return 0; } nilfs->ns_writer = nilfs_segctor_new(sb, root); diff --git a/fs/nilfs2/sufile.c b/fs/nilfs2/sufile.c index 63722475e17e1db313cda588482d4ae102dba1d9..51f4cb060231f01773583fc705b736d4e563d541 100644 --- a/fs/nilfs2/sufile.c +++ b/fs/nilfs2/sufile.c @@ -495,14 +495,22 @@ void nilfs_sufile_do_free(struct inode *sufile, __u64 segnum, int nilfs_sufile_mark_dirty(struct inode *sufile, __u64 segnum) { struct buffer_head *bh; + void *kaddr; + struct nilfs_segment_usage *su; int ret; + down_write(&NILFS_MDT(sufile)->mi_sem); ret = nilfs_sufile_get_segment_usage_block(sufile, segnum, 0, &bh); if (!ret) { mark_buffer_dirty(bh); nilfs_mdt_mark_dirty(sufile); + kaddr = kmap_atomic(bh->b_page); + su = nilfs_sufile_block_get_segment_usage(sufile, segnum, bh, kaddr); + nilfs_segment_usage_set_dirty(su); + kunmap_atomic(kaddr); brelse(bh); } + up_write(&NILFS_MDT(sufile)->mi_sem); return ret; } diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c index 010037d38973f767c00265cbed409058e0519270..b3c094c59254ba5e7aae32a03127cfcc48c3a481 100644 --- a/fs/nilfs2/super.c +++ b/fs/nilfs2/super.c @@ -1134,8 +1134,6 @@ static int nilfs_remount(struct super_block *sb, int *flags, char *data) if ((bool)(*flags & SB_RDONLY) == sb_rdonly(sb)) goto out; if (*flags & SB_RDONLY) { - /* Shutting down log writer */ - nilfs_detach_log_writer(sb); sb->s_flags |= SB_RDONLY; /* diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c index c20ebecd7bc24cb9b0f7498e097a3225905e7f04..ce103dd39b8997a0702b9bb519a9cf1a73fd8ffc 100644 --- a/fs/nilfs2/the_nilfs.c +++ b/fs/nilfs2/the_nilfs.c @@ -690,9 +690,7 @@ int nilfs_count_free_blocks(struct the_nilfs *nilfs, sector_t *nblocks) { unsigned long ncleansegs; - down_read(&NILFS_MDT(nilfs->ns_dat)->mi_sem); ncleansegs = nilfs_sufile_get_ncleansegs(nilfs->ns_sufile); - up_read(&NILFS_MDT(nilfs->ns_dat)->mi_sem); *nblocks = (sector_t)ncleansegs * nilfs->ns_blocks_per_segment; return 0; } diff --git a/fs/ntfs/attrib.c b/fs/ntfs/attrib.c index 914e9917313000634397fb939b1a5c3045731660..c0881d39d36a9c02674d1d4b6c1ca8bced0877e7 100644 --- a/fs/ntfs/attrib.c +++ b/fs/ntfs/attrib.c @@ -594,17 +594,37 @@ static int ntfs_attr_find(const ATTR_TYPE type, const ntfschar *name, for (;; a = (ATTR_RECORD*)((u8*)a + le32_to_cpu(a->length))) { u8 *mrec_end = (u8 *)ctx->mrec + le32_to_cpu(ctx->mrec->bytes_allocated); - u8 *name_end = (u8 *)a + le16_to_cpu(a->name_offset) + - a->name_length * sizeof(ntfschar); - if ((u8*)a < (u8*)ctx->mrec || (u8*)a > mrec_end || - name_end > mrec_end) + u8 *name_end; + + /* check whether ATTR_RECORD wrap */ + if ((u8 *)a < (u8 *)ctx->mrec) + break; + + /* check whether Attribute Record Header is within bounds */ + if ((u8 *)a > mrec_end || + (u8 *)a + sizeof(ATTR_RECORD) > mrec_end) + break; + + /* check whether ATTR_RECORD's name is within bounds */ + name_end = (u8 *)a + le16_to_cpu(a->name_offset) + + a->name_length * sizeof(ntfschar); + if (name_end > mrec_end) break; + ctx->attr = a; if (unlikely(le32_to_cpu(a->type) > le32_to_cpu(type) || a->type == AT_END)) return -ENOENT; if (unlikely(!a->length)) break; + + /* check whether ATTR_RECORD's length wrap */ + if ((u8 *)a + le32_to_cpu(a->length) < (u8 *)a) + break; + /* check whether ATTR_RECORD's length is within bounds */ + if ((u8 *)a + le32_to_cpu(a->length) > mrec_end) + break; + if (a->type != type) continue; /* diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c index cf222c9225d6d5816b7928d26a1c0eecda00f0c4..645c4b1b23de1930746f63bc93ad0aab95675230 100644 --- a/fs/ntfs/inode.c +++ b/fs/ntfs/inode.c @@ -1829,6 +1829,13 @@ int ntfs_read_inode_mount(struct inode *vi) goto err_out; } + /* Sanity check offset to the first attribute */ + if (le16_to_cpu(m->attrs_offset) >= le32_to_cpu(m->bytes_allocated)) { + ntfs_error(sb, "Incorrect mft offset to the first attribute %u in superblock.", + le16_to_cpu(m->attrs_offset)); + goto err_out; + } + /* Need this to sanity check attribute list references to $MFT. */ vi->i_generation = ni->seq_no = le16_to_cpu(m->sequence_number); diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index c46bf7f581a14b117c72d7873ac3d95232b80515..856474b0a1ae7e1b7a2cc14c6fbebf37156b104c 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -231,6 +231,7 @@ static int ocfs2_mknod(struct inode *dir, handle_t *handle = NULL; struct ocfs2_super *osb; struct ocfs2_dinode *dirfe; + struct ocfs2_dinode *fe = NULL; struct buffer_head *new_fe_bh = NULL; struct inode *inode = NULL; struct ocfs2_alloc_context *inode_ac = NULL; @@ -381,6 +382,7 @@ static int ocfs2_mknod(struct inode *dir, goto leave; } + fe = (struct ocfs2_dinode *) new_fe_bh->b_data; if (S_ISDIR(mode)) { status = ocfs2_fill_new_dir(osb, handle, dir, inode, new_fe_bh, data_ac, meta_ac); @@ -453,8 +455,11 @@ roll_back: leave: if (status < 0 && did_quota_inode) dquot_free_inode(inode); - if (handle) + if (handle) { + if (status < 0 && fe) + ocfs2_set_links_count(fe, 0); ocfs2_commit_trans(osb, handle); + } ocfs2_inode_unlock(dir, 1); if (did_block_signals) @@ -631,18 +636,9 @@ static int ocfs2_mknod_locked(struct ocfs2_super *osb, return status; } - status = __ocfs2_mknod_locked(dir, inode, dev, new_fe_bh, + return __ocfs2_mknod_locked(dir, inode, dev, new_fe_bh, parent_fe_bh, handle, inode_ac, fe_blkno, suballoc_loc, suballoc_bit); - if (status < 0) { - u64 bg_blkno = ocfs2_which_suballoc_group(fe_blkno, suballoc_bit); - int tmp = ocfs2_free_suballoc_bits(handle, inode_ac->ac_inode, - inode_ac->ac_bh, suballoc_bit, bg_blkno, 1); - if (tmp) - mlog_errno(tmp); - } - - return status; } static int ocfs2_mkdir(struct inode *dir, @@ -2023,8 +2019,11 @@ bail: ocfs2_clusters_to_bytes(osb->sb, 1)); if (status < 0 && did_quota_inode) dquot_free_inode(inode); - if (handle) + if (handle) { + if (status < 0 && fe) + ocfs2_set_links_count(fe, 0); ocfs2_commit_trans(osb, handle); + } ocfs2_inode_unlock(dir, 1); if (did_block_signals) diff --git a/fs/open.c b/fs/open.c index b9d55ca3763b652a227e6a9bc406b8352629f674..93e85572b16529a35d8055b12b6632f7b4d5beea 100644 --- a/fs/open.c +++ b/fs/open.c @@ -1110,6 +1110,12 @@ inline int build_open_flags(const struct open_how *how, struct open_flags *op) lookup_flags |= LOOKUP_BENEATH; if (how->resolve & RESOLVE_IN_ROOT) lookup_flags |= LOOKUP_IN_ROOT; + if (how->resolve & RESOLVE_CACHED) { + /* Don't bother even trying for create/truncate/tmpfile open */ + if (flags & (O_TRUNC | O_CREAT | O_TMPFILE)) + return -EAGAIN; + lookup_flags |= LOOKUP_CACHED; + } op->lookup_flags = lookup_flags; return 0; diff --git a/fs/proc/self.c b/fs/proc/self.c index a4012154e1096bd240c1d97255807843bc932516..72cd69bcaf4ad977ab7c3b134d91cfaaeee34026 100644 --- a/fs/proc/self.c +++ b/fs/proc/self.c @@ -16,13 +16,6 @@ static const char *proc_self_get_link(struct dentry *dentry, pid_t tgid = task_tgid_nr_ns(current, ns); char *name; - /* - * Not currently supported. Once we can inherit all of struct pid, - * we can allow this. - */ - if (current->flags & PF_IO_WORKER) - return ERR_PTR(-EOPNOTSUPP); - if (!tgid) return ERR_PTR(-ENOENT); /* max length of unsigned int in decimal + NULL term */ diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 5e7ee2ab7df666f94cc3dc7f1795baab257ca649..b1929c8af90777eca01708f708bfa1ab1b483b2b 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -965,7 +965,7 @@ static int show_smaps_rollup(struct seq_file *m, void *v) vma = vma->vm_next; } - show_vma_header_prefix(m, priv->mm->mmap->vm_start, + show_vma_header_prefix(m, priv->mm->mmap ? priv->mm->mmap->vm_start : 0, last_vma_end, 0, 0, 0, 0); seq_pad(m, ' '); seq_puts(m, "[rollup]\n"); diff --git a/fs/proc/thread_self.c b/fs/proc/thread_self.c index d56681d86d28a28517df9730dfe1e9bfed597387..a553273fbd41758df711b85c9647134b9eb1c631 100644 --- a/fs/proc/thread_self.c +++ b/fs/proc/thread_self.c @@ -17,13 +17,6 @@ static const char *proc_thread_self_get_link(struct dentry *dentry, pid_t pid = task_pid_nr_ns(current, ns); char *name; - /* - * Not currently supported. Once we can inherit all of struct pid, - * we can allow this. - */ - if (current->flags & PF_IO_WORKER) - return ERR_PTR(-EOPNOTSUPP); - if (!pid) return ERR_PTR(-ENOENT); name = kmalloc(10 + 6 + 10 + 1, dentry ? GFP_KERNEL : GFP_ATOMIC); diff --git a/fs/quota/quota_tree.c b/fs/quota/quota_tree.c index 1a188fbdf34e5cff916063ea6071d0f74ed0a088..07948f6ac84ef93b6a43229adb08f16c4c15eaed 100644 --- a/fs/quota/quota_tree.c +++ b/fs/quota/quota_tree.c @@ -80,6 +80,35 @@ static ssize_t write_blk(struct qtree_mem_dqinfo *info, uint blk, char *buf) return ret; } +static inline int do_check_range(struct super_block *sb, const char *val_name, + uint val, uint min_val, uint max_val) +{ + if (val < min_val || val > max_val) { + quota_error(sb, "Getting %s %u out of range %u-%u", + val_name, val, min_val, max_val); + return -EUCLEAN; + } + + return 0; +} + +static int check_dquot_block_header(struct qtree_mem_dqinfo *info, + struct qt_disk_dqdbheader *dh) +{ + int err = 0; + + err = do_check_range(info->dqi_sb, "dqdh_next_free", + le32_to_cpu(dh->dqdh_next_free), 0, + info->dqi_blocks - 1); + if (err) + return err; + err = do_check_range(info->dqi_sb, "dqdh_prev_free", + le32_to_cpu(dh->dqdh_prev_free), 0, + info->dqi_blocks - 1); + + return err; +} + /* Remove empty block from list and return it */ static int get_free_dqblk(struct qtree_mem_dqinfo *info) { @@ -94,6 +123,9 @@ static int get_free_dqblk(struct qtree_mem_dqinfo *info) ret = read_blk(info, blk, buf); if (ret < 0) goto out_buf; + ret = check_dquot_block_header(info, dh); + if (ret) + goto out_buf; info->dqi_free_blk = le32_to_cpu(dh->dqdh_next_free); } else { @@ -241,6 +273,9 @@ static uint find_free_dqentry(struct qtree_mem_dqinfo *info, *err = read_blk(info, blk, buf); if (*err < 0) goto out_buf; + *err = check_dquot_block_header(info, dh); + if (*err) + goto out_buf; } else { blk = get_free_dqblk(info); if ((int)blk < 0) { @@ -433,6 +468,9 @@ static int free_dqentry(struct qtree_mem_dqinfo *info, struct dquot *dquot, goto out_buf; } dh = (struct qt_disk_dqdbheader *)buf; + ret = check_dquot_block_header(info, dh); + if (ret) + goto out_buf; le16_add_cpu(&dh->dqdh_entries, -1); if (!le16_to_cpu(dh->dqdh_entries)) { /* Block got free? */ ret = remove_free_dqentry(info, buf, blk); diff --git a/fs/super.c b/fs/super.c index ae2b97dabe312c9804bd6bb143167a84643cb961..602d02c50c4217f7ed438120e16917f251a9d301 100644 --- a/fs/super.c +++ b/fs/super.c @@ -293,7 +293,7 @@ static void __put_super(struct super_block *s) WARN_ON(s->s_inode_lru.node); WARN_ON(!list_empty(&s->s_mounts)); security_sb_free(s); - fscrypt_sb_free(s); + fscrypt_destroy_keyring(s); put_user_ns(s->s_user_ns); kfree(s->s_subtype); call_rcu(&s->rcu, destroy_super_rcu); @@ -454,6 +454,7 @@ void generic_shutdown_super(struct super_block *sb) evict_inodes(sb); /* only nonzero refcount inodes can have marks */ fsnotify_sb_delete(sb); + fscrypt_destroy_keyring(sb); if (sb->s_dio_done_wq) { destroy_workqueue(sb->s_dio_done_wq); diff --git a/fs/udf/namei.c b/fs/udf/namei.c index 9f3aced46c68fdf0ec34c8b458756c5316fe4539..aff5ca32e4f64b9ce4c3b93e0298544a9c30262d 100644 --- a/fs/udf/namei.c +++ b/fs/udf/namei.c @@ -241,7 +241,7 @@ static struct fileIdentDesc *udf_find_entry(struct inode *dir, poffset - lfi); else { if (!copy_name) { - copy_name = kmalloc(UDF_NAME_LEN, + copy_name = kmalloc(UDF_NAME_LEN_CS0, GFP_NOFS); if (!copy_name) { fi = ERR_PTR(-ENOMEM); diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index da8c8409528dc82dfe5dcffcd14b432f71f5503e..20892669308c74aaaae59e3cde9abf916ab580b0 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -987,7 +987,7 @@ static int resolve_userfault_fork(struct userfaultfd_ctx *new, int fd; fd = anon_inode_getfd_secure("[userfaultfd]", &userfaultfd_fops, new, - O_RDWR | (new->flags & UFFD_SHARED_FCNTL_FLAGS), inode); + O_RDONLY | (new->flags & UFFD_SHARED_FCNTL_FLAGS), inode); if (fd < 0) return fd; @@ -2100,7 +2100,7 @@ SYSCALL_DEFINE1(userfaultfd, int, flags) mmgrab(ctx->mm); fd = anon_inode_getfd_secure("[userfaultfd]", &userfaultfd_fops, ctx, - O_RDWR | (flags & UFFD_SHARED_FCNTL_FLAGS), NULL); + O_RDONLY | (flags & UFFD_SHARED_FCNTL_FLAGS), NULL); if (fd < 0) { mmdrop(ctx->mm); kmem_cache_free(userfaultfd_ctx_cachep, ctx); diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c index 6b87aeaa71792b136ea0b299e9fd0bc05f27de33..57ab34b1a9d4eabcdd220455c186b795729b247e 100644 --- a/fs/zonefs/super.c +++ b/fs/zonefs/super.c @@ -440,14 +440,22 @@ static void __zonefs_io_error(struct inode *inode, bool write) struct super_block *sb = inode->i_sb; struct zonefs_sb_info *sbi = ZONEFS_SB(sb); unsigned int noio_flag; - unsigned int nr_zones = - zi->i_zone_size >> (sbi->s_zone_sectors_shift + SECTOR_SHIFT); + unsigned int nr_zones = 1; struct zonefs_ioerr_data err = { .inode = inode, .write = write, }; int ret; + /* + * The only files that have more than one zone are conventional zone + * files with aggregated conventional zones, for which the inode zone + * size is always larger than the device zone size. + */ + if (zi->i_zone_size > bdev_zone_sectors(sb->s_bdev)) + nr_zones = zi->i_zone_size >> + (sbi->s_zone_sectors_shift + SECTOR_SHIFT); + /* * Memory allocations in blkdev_report_zones() can trigger a memory * reclaim which may in turn cause a recursion into zonefs as well as @@ -1364,6 +1372,14 @@ static int zonefs_init_file_inode(struct inode *inode, struct blk_zone *zone, zi->i_ztype = type; zi->i_zsector = zone->start; zi->i_zone_size = zone->len << SECTOR_SHIFT; + if (zi->i_zone_size > bdev_zone_sectors(sb->s_bdev) << SECTOR_SHIFT && + !(sbi->s_features & ZONEFS_F_AGGRCNV)) { + zonefs_err(sb, + "zone size %llu doesn't match device's zone sectors %llu\n", + zi->i_zone_size, + bdev_zone_sectors(sb->s_bdev) << SECTOR_SHIFT); + return -EINVAL; + } zi->i_max_size = min_t(loff_t, MAX_LFS_FILESIZE, zone->capacity << SECTOR_SHIFT); @@ -1406,11 +1422,11 @@ static struct dentry *zonefs_create_inode(struct dentry *parent, struct inode *dir = d_inode(parent); struct dentry *dentry; struct inode *inode; - int ret; + int ret = -ENOMEM; dentry = d_alloc_name(parent, name); if (!dentry) - return NULL; + return ERR_PTR(ret); inode = new_inode(parent->d_sb); if (!inode) @@ -1435,7 +1451,7 @@ static struct dentry *zonefs_create_inode(struct dentry *parent, dput: dput(dentry); - return NULL; + return ERR_PTR(ret); } struct zonefs_zone_data { @@ -1455,7 +1471,7 @@ static int zonefs_create_zgroup(struct zonefs_zone_data *zd, struct blk_zone *zone, *next, *end; const char *zgroup_name; char *file_name; - struct dentry *dir; + struct dentry *dir, *dent; unsigned int n = 0; int ret; @@ -1473,8 +1489,8 @@ static int zonefs_create_zgroup(struct zonefs_zone_data *zd, zgroup_name = "seq"; dir = zonefs_create_inode(sb->s_root, zgroup_name, NULL, type); - if (!dir) { - ret = -ENOMEM; + if (IS_ERR(dir)) { + ret = PTR_ERR(dir); goto free; } @@ -1520,8 +1536,9 @@ static int zonefs_create_zgroup(struct zonefs_zone_data *zd, * Use the file number within its group as file name. */ snprintf(file_name, ZONEFS_NAME_MAX - 1, "%u", n); - if (!zonefs_create_inode(dir, file_name, zone, type)) { - ret = -ENOMEM; + dent = zonefs_create_inode(dir, file_name, zone, type); + if (IS_ERR(dent)) { + ret = PTR_ERR(dent); goto free; } diff --git a/include/acpi/ghes.h b/include/acpi/ghes.h index 34fb3431a8f3646c8e45c34183bb43dbfc45540d..292a5c40bd0c62fc65a4d0ed2d3fd5855efca1d3 100644 --- a/include/acpi/ghes.h +++ b/include/acpi/ghes.h @@ -71,7 +71,7 @@ int ghes_register_vendor_record_notifier(struct notifier_block *nb); void ghes_unregister_vendor_record_notifier(struct notifier_block *nb); #endif -int ghes_estatus_pool_init(int num_ghes); +int ghes_estatus_pool_init(unsigned int num_ghes); /* From drivers/edac/ghes_edac.c */ diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 398f5e228b2e0980f5266ed119c7887367393e49..8a79995abea55a662b7229b3c7ea75deeac44eec 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -341,6 +341,7 @@ #define DATA_DATA \ *(.xiptext) \ *(DATA_MAIN) \ + *(.data..decrypted) \ *(.ref.data) \ *(.data..shared_aligned) /* percpu related */ \ MEM_KEEP(init.data*) \ @@ -1013,7 +1014,6 @@ #ifdef CONFIG_AMD_MEM_ENCRYPT #define PERCPU_DECRYPTED_SECTION \ . = ALIGN(PAGE_SIZE); \ - *(.data..decrypted) \ *(.data..percpu..decrypted) \ . = ALIGN(PAGE_SIZE); #else diff --git a/include/linux/ata.h b/include/linux/ata.h index 6e67aded28f8ceb461480e46cfffc7f07e32ff0d..6d2d31b03b4de3e18176133e61ec408dc4ad8709 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -565,6 +565,18 @@ struct ata_bmdma_prd { ((((id)[ATA_ID_SATA_CAPABILITY] != 0x0000) && \ ((id)[ATA_ID_SATA_CAPABILITY] != 0xffff)) && \ ((id)[ATA_ID_FEATURE_SUPP] & (1 << 2))) +#define ata_id_has_devslp(id) \ + ((((id)[ATA_ID_SATA_CAPABILITY] != 0x0000) && \ + ((id)[ATA_ID_SATA_CAPABILITY] != 0xffff)) && \ + ((id)[ATA_ID_FEATURE_SUPP] & (1 << 8))) +#define ata_id_has_ncq_autosense(id) \ + ((((id)[ATA_ID_SATA_CAPABILITY] != 0x0000) && \ + ((id)[ATA_ID_SATA_CAPABILITY] != 0xffff)) && \ + ((id)[ATA_ID_FEATURE_SUPP] & (1 << 7))) +#define ata_id_has_dipm(id) \ + ((((id)[ATA_ID_SATA_CAPABILITY] != 0x0000) && \ + ((id)[ATA_ID_SATA_CAPABILITY] != 0xffff)) && \ + ((id)[ATA_ID_FEATURE_SUPP] & (1 << 3))) #define ata_id_iordy_disable(id) ((id)[ATA_ID_CAPABILITY] & (1 << 10)) #define ata_id_has_iordy(id) ((id)[ATA_ID_CAPABILITY] & (1 << 11)) #define ata_id_u32(id,n) \ @@ -577,9 +589,6 @@ struct ata_bmdma_prd { #define ata_id_cdb_intr(id) (((id)[ATA_ID_CONFIG] & 0x60) == 0x20) #define ata_id_has_da(id) ((id)[ATA_ID_SATA_CAPABILITY_2] & (1 << 4)) -#define ata_id_has_devslp(id) ((id)[ATA_ID_FEATURE_SUPP] & (1 << 8)) -#define ata_id_has_ncq_autosense(id) \ - ((id)[ATA_ID_FEATURE_SUPP] & (1 << 7)) static inline bool ata_id_has_hipm(const u16 *id) { @@ -591,17 +600,6 @@ static inline bool ata_id_has_hipm(const u16 *id) return val & (1 << 9); } -static inline bool ata_id_has_dipm(const u16 *id) -{ - u16 val = id[ATA_ID_FEATURE_SUPP]; - - if (val == 0 || val == 0xffff) - return false; - - return val & (1 << 3); -} - - static inline bool ata_id_has_fua(const u16 *id) { if ((id[ATA_ID_CFSSE] & 0xC000) != 0x4000) @@ -770,16 +768,21 @@ static inline bool ata_id_has_read_log_dma_ext(const u16 *id) static inline bool ata_id_has_sense_reporting(const u16 *id) { - if (!(id[ATA_ID_CFS_ENABLE_2] & (1 << 15))) + if (!(id[ATA_ID_CFS_ENABLE_2] & BIT(15))) + return false; + if ((id[ATA_ID_COMMAND_SET_3] & (BIT(15) | BIT(14))) != BIT(14)) return false; - return id[ATA_ID_COMMAND_SET_3] & (1 << 6); + return id[ATA_ID_COMMAND_SET_3] & BIT(6); } static inline bool ata_id_sense_reporting_enabled(const u16 *id) { - if (!(id[ATA_ID_CFS_ENABLE_2] & (1 << 15))) + if (!ata_id_has_sense_reporting(id)) + return false; + /* ata_id_has_sense_reporting() == true, word 86 must have bit 15 set */ + if ((id[ATA_ID_COMMAND_SET_4] & (BIT(15) | BIT(14))) != BIT(14)) return false; - return id[ATA_ID_COMMAND_SET_4] & (1 << 6); + return id[ATA_ID_COMMAND_SET_4] & BIT(6); } /** diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index e20362ae573e0ba13aebe62344cd2689e71854d8..f09a5bbc9b8b091131b222312576becf932a4c35 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -46,7 +46,7 @@ struct bpf_reg_state { enum bpf_reg_type type; union { /* valid when type == PTR_TO_PACKET */ - u16 range; + int range; /* valid when type == CONST_PTR_TO_MAP | PTR_TO_MAP_VALUE | * PTR_TO_MAP_VALUE_OR_NULL @@ -291,6 +291,27 @@ struct bpf_verifier_state { iter < frame->allocated_stack / BPF_REG_SIZE; \ iter++, reg = bpf_get_spilled_reg(iter, frame)) +/* Invoke __expr over regsiters in __vst, setting __state and __reg */ +#define bpf_for_each_reg_in_vstate(__vst, __state, __reg, __expr) \ + ({ \ + struct bpf_verifier_state *___vstate = __vst; \ + int ___i, ___j; \ + for (___i = 0; ___i <= ___vstate->curframe; ___i++) { \ + struct bpf_reg_state *___regs; \ + __state = ___vstate->frame[___i]; \ + ___regs = __state->regs; \ + for (___j = 0; ___j < MAX_BPF_REG; ___j++) { \ + __reg = &___regs[___j]; \ + (void)(__expr); \ + } \ + bpf_for_each_spilled_reg(___j, __state, __reg) { \ + if (!__reg) \ + continue; \ + (void)(__expr); \ + } \ + } \ + }) + /* linked list of verifier states used to prune search */ struct bpf_verifier_state_list { struct bpf_verifier_state state; diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h index 455e9b9e2adf538d53ba1efcfccde2c96671f010..8287382d3d1dbe118c5454d0a2d00254232ad056 100644 --- a/include/linux/ceph/ceph_fs.h +++ b/include/linux/ceph/ceph_fs.h @@ -288,6 +288,7 @@ enum { CEPH_SESSION_FLUSHMSG_ACK, CEPH_SESSION_FORCE_RO, CEPH_SESSION_REJECT, + CEPH_SESSION_REQUEST_FLUSH_MDLOG, }; extern const char *ceph_session_op_name(int op); diff --git a/include/linux/dynamic_debug.h b/include/linux/dynamic_debug.h index a57ee75342cf801e5d50b5d44702aa6c052a1be4..c0c6ea9ea7e3624a7cc0ab6053d94d3adc50015e 100644 --- a/include/linux/dynamic_debug.h +++ b/include/linux/dynamic_debug.h @@ -50,9 +50,6 @@ struct _ddebug { #if defined(CONFIG_DYNAMIC_DEBUG_CORE) -/* exported for module authors to exercise >control */ -int dynamic_debug_exec_queries(const char *query, const char *modname); - int ddebug_add_module(struct _ddebug *tab, unsigned int n, const char *modname); extern int ddebug_remove_module(const char *mod_name); @@ -196,7 +193,7 @@ static inline int ddebug_remove_module(const char *mod) static inline int ddebug_dyndbg_module_param_cb(char *param, char *val, const char *modname) { - if (strstr(param, "dyndbg")) { + if (!strcmp(param, "dyndbg")) { /* avoid pr_warn(), which wants pr_fmt() fully defined */ printk(KERN_WARNING "dyndbg param is supported only in " "CONFIG_DYNAMIC_DEBUG builds\n"); @@ -216,12 +213,6 @@ static inline int ddebug_dyndbg_module_param_cb(char *param, char *val, rowsize, groupsize, buf, len, ascii); \ } while (0) -static inline int dynamic_debug_exec_queries(const char *query, const char *modname) -{ - pr_warn("kernel not built with CONFIG_DYNAMIC_DEBUG_CORE\n"); - return 0; -} - #endif /* !CONFIG_DYNAMIC_DEBUG_CORE */ #endif diff --git a/include/linux/efi.h b/include/linux/efi.h index 3bac68fb7ff1c67db25f66a29908b0c09a9370f6..7feb70d32d95570dd808b990ae78110b646e0c3e 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1161,7 +1161,7 @@ void efi_retrieve_tpm2_eventlog(void); arch_efi_call_virt_teardown(); \ }) -#define EFI_RANDOM_SEED_SIZE 64U +#define EFI_RANDOM_SEED_SIZE 32U // BLAKE2S_HASH_SIZE struct linux_efi_random_seed { u32 size; diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h index 7dff07713a073dc5aedf9bf66cc61885464a6153..46c42479f950121a8b56ae49c819a03ce435f70b 100644 --- a/include/linux/entry-common.h +++ b/include/linux/entry-common.h @@ -69,7 +69,7 @@ #define EXIT_TO_USER_MODE_WORK \ (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_UPROBE | \ - _TIF_NEED_RESCHED | _TIF_PATCH_PENDING | \ + _TIF_NEED_RESCHED | _TIF_PATCH_PENDING | _TIF_NOTIFY_SIGNAL | \ ARCH_EXIT_TO_USER_MODE_WORK) /** @@ -259,12 +259,13 @@ static __always_inline void arch_exit_to_user_mode(void) { } #endif /** - * arch_do_signal - Architecture specific signal delivery function + * arch_do_signal_or_restart - Architecture specific signal delivery function * @regs: Pointer to currents pt_regs + * @has_signal: actual signal to handle * * Invoked from exit_to_user_mode_loop(). */ -void arch_do_signal(struct pt_regs *regs); +void arch_do_signal_or_restart(struct pt_regs *regs, bool has_signal); /** * arch_syscall_exit_tracehook - Wrapper around tracehook_report_syscall_exit() diff --git a/include/linux/entry-kvm.h b/include/linux/entry-kvm.h index 0cef17afb41a66db373bf03fb0ec1ffdea2fe1ad..9b93f8584ff7d3f9988ad5556cdcd073b3f0a881 100644 --- a/include/linux/entry-kvm.h +++ b/include/linux/entry-kvm.h @@ -11,8 +11,8 @@ # define ARCH_XFER_TO_GUEST_MODE_WORK (0) #endif -#define XFER_TO_GUEST_MODE_WORK \ - (_TIF_NEED_RESCHED | _TIF_SIGPENDING | \ +#define XFER_TO_GUEST_MODE_WORK \ + (_TIF_NEED_RESCHED | _TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL | \ _TIF_NOTIFY_RESUME | ARCH_XFER_TO_GUEST_MODE_WORK) struct kvm_vcpu; diff --git a/include/linux/eventfd.h b/include/linux/eventfd.h index dc4fd8a6644dd62da4837ebc7e9d20a24716e59a..ce1cf42740bf4c349ad46cc07456dc7b87155533 100644 --- a/include/linux/eventfd.h +++ b/include/linux/eventfd.h @@ -39,6 +39,7 @@ struct file *eventfd_fget(int fd); struct eventfd_ctx *eventfd_ctx_fdget(int fd); struct eventfd_ctx *eventfd_ctx_fileget(struct file *file); __u64 eventfd_signal(struct eventfd_ctx *ctx, __u64 n); +__u64 eventfd_signal_mask(struct eventfd_ctx *ctx, __u64 n, unsigned mask); int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, wait_queue_entry_t *wait, __u64 *cnt); @@ -66,6 +67,12 @@ static inline int eventfd_signal(struct eventfd_ctx *ctx, int n) return -ENOSYS; } +static inline int eventfd_signal_mask(struct eventfd_ctx *ctx, __u64 n, + unsigned mask) +{ + return -ENOSYS; +} + static inline void eventfd_ctx_put(struct eventfd_ctx *ctx) { diff --git a/include/linux/fcntl.h b/include/linux/fcntl.h index 921e750843e660c2909c678b73eb052955712203..766fcd973bebac518cfd57eaa0c7c7bbf224e8ca 100644 --- a/include/linux/fcntl.h +++ b/include/linux/fcntl.h @@ -19,7 +19,7 @@ /* List of all valid flags for the how->resolve argument: */ #define VALID_RESOLVE_FLAGS \ (RESOLVE_NO_XDEV | RESOLVE_NO_MAGICLINKS | RESOLVE_NO_SYMLINKS | \ - RESOLVE_BENEATH | RESOLVE_IN_ROOT) + RESOLVE_BENEATH | RESOLVE_IN_ROOT | RESOLVE_CACHED) /* List of all open_how "versions". */ #define OPEN_HOW_SIZE_VER0 24 /* sizeof first published struct */ diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h index a32bf47c593e7a04492f90d8eb84469164bfcd7d..f1a99d3e5570712f4a48b3984e9b178208a460de 100644 --- a/include/linux/fdtable.h +++ b/include/linux/fdtable.h @@ -123,7 +123,7 @@ extern void __fd_install(struct files_struct *files, extern int __close_fd(struct files_struct *files, unsigned int fd); extern int __close_range(unsigned int fd, unsigned int max_fd, unsigned int flags); -extern int __close_fd_get_file(unsigned int fd, struct file **res); +extern int close_fd_get_file(unsigned int fd, struct file **res); extern int unshare_fd(unsigned long unshare_flags, unsigned int max_fds, struct files_struct **new_fdp); diff --git a/include/linux/fs.h b/include/linux/fs.h index 8cf258fc9162230755c491704ac303f8e717e63f..79f9fa17f7f8a235707bf8bbadc6533d0fcd1a50 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1471,7 +1471,16 @@ struct super_block { const struct xattr_handler **s_xattr; #ifdef CONFIG_FS_ENCRYPTION const struct fscrypt_operations *s_cop; +#ifdef __GENKSYMS__ + /* + * Android ABI CRC preservation due to commit 391cceee6d43 ("fscrypt: + * stop using keyrings subsystem for fscrypt_master_key") changing this + * type. Size is the same, this is a private field. + */ struct key *s_master_keys; /* master crypto keys in use */ +#else + struct fscrypt_keyring *s_master_keys; /* master crypto keys in use */ +#endif #endif #ifdef CONFIG_FS_VERITY const struct fsverity_operations *s_vop; diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index e05cb512897a2a27392138bb9806d50eb3a27a4e..380eb98243f9b61719a4d65b9b9841dd8fb26e47 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -298,7 +298,7 @@ fscrypt_free_dummy_policy(struct fscrypt_dummy_policy *dummy_policy) } /* keyring.c */ -void fscrypt_sb_free(struct super_block *sb); +void fscrypt_destroy_keyring(struct super_block *sb); int fscrypt_ioctl_add_key(struct file *filp, void __user *arg); int fscrypt_ioctl_remove_key(struct file *filp, void __user *arg); int fscrypt_ioctl_remove_key_all_users(struct file *filp, void __user *arg); @@ -486,7 +486,7 @@ fscrypt_free_dummy_policy(struct fscrypt_dummy_policy *dummy_policy) } /* keyring.c */ -static inline void fscrypt_sb_free(struct super_block *sb) +static inline void fscrypt_destroy_keyring(struct super_block *sb) { } diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h index 35b2d845704d9175466d979138d413d85423664b..5ae871af45de6b137ddabdd9c012ab5bb76fbf61 100644 --- a/include/linux/io_uring.h +++ b/include/linux/io_uring.h @@ -5,6 +5,37 @@ #include #include +#ifdef __GENKSYMS__ +/* + * ANDROID ABI HACK + * + * In the 5.10.162 release, the io_uring code was synced with the version + * that is in the 5.15.y kernel tree in order to resolve a huge number of + * potential, and known, problems with the codebase. This makes for a more + * secure and easier-to-update-and-maintain 5.10.y kernel tree, so this is + * a great thing, however this caused some issues when it comes to the + * Android KABI preservation and checking tools. + * + * A number of the io_uring structures get used in other core kernel + * structures, only as "opaque" pointers, so there is not any real ABI + * breakage. But, due to the visibility of the structures going away, the + * CRC values of many scheduler variables and functions were changed. + * + * In order to preserve the CRC values, to prevent all device kernels to be + * forced to rebuild for no reason whatsoever from a functional point of + * view, we need to keep around the "old" io_uring structures for the CRC + * calculation only. This is done by the following definitions of struct + * io_identity and struct io_uring_task which will only be visible when the + * CRC calculation build happens, not in any functional kernel build. + * + * Yes, this all is a horrible hack, and these really are not the true + * structures that any code uses, but so life is in the world of stable + * apis... + * The real structures are in io_uring/io_uring.c, see the ones there if + * you need to touch or do anything with it. + * + * NEVER touch these structure definitions, they are fake and not valid code. + */ struct io_identity { struct files_struct *files; struct mm_struct *mm; @@ -33,22 +64,23 @@ struct io_uring_task { atomic_t in_idle; bool sqpoll; }; +#endif /* ANDROID ABI HACK */ + #if defined(CONFIG_IO_URING) struct sock *io_uring_get_socket(struct file *file); -void __io_uring_task_cancel(void); -void __io_uring_files_cancel(struct files_struct *files); +void __io_uring_cancel(bool cancel_all); void __io_uring_free(struct task_struct *tsk); -static inline void io_uring_task_cancel(void) +static inline void io_uring_files_cancel(void) { - if (current->io_uring && !xa_empty(¤t->io_uring->xa)) - __io_uring_task_cancel(); + if (current->io_uring) + __io_uring_cancel(false); } -static inline void io_uring_files_cancel(struct files_struct *files) +static inline void io_uring_task_cancel(void) { - if (current->io_uring && !xa_empty(¤t->io_uring->xa)) - __io_uring_files_cancel(files); + if (current->io_uring) + __io_uring_cancel(true); } static inline void io_uring_free(struct task_struct *tsk) { @@ -63,7 +95,7 @@ static inline struct sock *io_uring_get_socket(struct file *file) static inline void io_uring_task_cancel(void) { } -static inline void io_uring_files_cancel(struct files_struct *files) +static inline void io_uring_files_cancel(void) { } static inline void io_uring_free(struct task_struct *tsk) diff --git a/include/linux/iova.h b/include/linux/iova.h index 5b4e75fe626aff4c2cb30ce3523f309e3a0845a8..0394d44f726eb3b125d04cea3d8fd6c298dfc218 100644 --- a/include/linux/iova.h +++ b/include/linux/iova.h @@ -133,7 +133,7 @@ static inline unsigned long iova_pfn(struct iova_domain *iovad, dma_addr_t iova) return iova >> iova_shift(iovad); } -#if IS_ENABLED(CONFIG_IOMMU_IOVA) +#if IS_REACHABLE(CONFIG_IOMMU_IOVA) int iova_cache_get(void); void iova_cache_put(void); diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 314ee5dcc92529cdf1990ad3d37eb6b5c48e1ee8..ac6915a0e3f3b58cc12a9d3d79a0ae647235aaaf 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -910,6 +910,8 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap); long kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg); +long kvm_arch_vm_compat_ioctl(struct file *filp, unsigned int ioctl, + unsigned long arg); int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu); int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu); diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 41fbb4793394d0c2f200e82b2a1fdd4eae95fdd7..ae88362216a4e1a32078dbddaf9a1410e4c0072d 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -899,7 +899,7 @@ void mlx5_cmd_allowed_opcode(struct mlx5_core_dev *dev, u16 opcode); struct mlx5_async_ctx { struct mlx5_core_dev *dev; atomic_t num_inflight; - struct wait_queue_head wait; + struct completion inflight_done; }; struct mlx5_async_work; diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index bb62eae4d88a3e6ed3fb9c78e06e85822bff1bbb..71e585990fe9fd14215044eb47da7b5a1d698a8e 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -273,6 +273,7 @@ struct mmc_card { #define MMC_QUIRK_BROKEN_IRQ_POLLING (1<<11) /* Polling SDIO_CCCR_INTx could create a fake interrupt */ #define MMC_QUIRK_TRIM_BROKEN (1<<12) /* Skip trim */ #define MMC_QUIRK_BROKEN_HPI (1<<13) /* Disable broken HPI support */ +#define MMC_QUIRK_BROKEN_SD_DISCARD (1<<14) /* Disable broken SD discard support */ bool reenable_cmdq; /* Re-enable Command Queue */ diff --git a/include/linux/namei.h b/include/linux/namei.h index a4bb992623c411e95266ecfd5e9aac5a54275f1b..b9605b2b46e7141f4a6366e787f70b7c19839909 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -46,6 +46,7 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT}; #define LOOKUP_NO_XDEV 0x040000 /* No mountpoint crossing. */ #define LOOKUP_BENEATH 0x080000 /* No escaping from starting point. */ #define LOOKUP_IN_ROOT 0x100000 /* Treat dirfd as fs root. */ +#define LOOKUP_CACHED 0x200000 /* Only do cached lookup */ /* LOOKUP_* flags which do scope-related checks based on the dirfd. */ #define LOOKUP_IS_SCOPED (LOOKUP_BENEATH | LOOKUP_IN_ROOT) diff --git a/include/linux/net.h b/include/linux/net.h index f5569faf930b1e766440cd8b35ceb9dfefe82494..e201a7fbf3bc26ab04fd8acc2ada2db8100764ba 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -43,8 +43,6 @@ struct net; #define SOCK_PASSCRED 3 #define SOCK_PASSSEC 4 -#define PROTO_CMSG_DATA_ONLY 0x0001 - #ifndef ARCH_HAS_SOCKET_TYPES /** * enum sock_type - Socket types @@ -139,7 +137,8 @@ typedef int (*sk_read_actor_t)(read_descriptor_t *, struct sk_buff *, struct proto_ops { int family; - unsigned int flags; + unsigned int flags; // ANDROID - removed in 5.10.162, but remains to + // preserve ABI. It is not used anywhere. struct module *owner; int (*release) (struct socket *sock); int (*bind) (struct socket *sock, diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index 5206d09910221c8b03638f5cda57839536236290..773943bc9228a78d366945a156c22c9eadc47838 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -201,6 +201,9 @@ struct ip_set_region { u32 elements; /* Number of elements vs timeout */ }; +/* Max range where every element is added/deleted in one step */ +#define IPSET_MAX_RANGE (1<<20) + /* The core set type structure */ struct ip_set_type { struct list_head list; diff --git a/include/linux/once.h b/include/linux/once.h index ae6f4eb41cbe7f61cb02f19620a2dbb2a1406089..bb58e1c3aa034f508be0b5372dbce5c6d7276a2f 100644 --- a/include/linux/once.h +++ b/include/linux/once.h @@ -5,10 +5,18 @@ #include #include +/* Helpers used from arbitrary contexts. + * Hard irqs are blocked, be cautious. + */ bool __do_once_start(bool *done, unsigned long *flags); void __do_once_done(bool *done, struct static_key_true *once_key, unsigned long *flags, struct module *mod); +/* Variant for process contexts only. */ +bool __do_once_slow_start(bool *done); +void __do_once_slow_done(bool *done, struct static_key_true *once_key, + struct module *mod); + /* Call a function exactly once. The idea of DO_ONCE() is to perform * a function call such as initialization of random seeds, etc, only * once, where DO_ONCE() can live in the fast-path. After @func has @@ -52,9 +60,29 @@ void __do_once_done(bool *done, struct static_key_true *once_key, ___ret; \ }) +/* Variant of DO_ONCE() for process/sleepable contexts. */ +#define DO_ONCE_SLOW(func, ...) \ + ({ \ + bool ___ret = false; \ + static bool __section(".data.once") ___done = false; \ + static DEFINE_STATIC_KEY_TRUE(___once_key); \ + if (static_branch_unlikely(&___once_key)) { \ + ___ret = __do_once_slow_start(&___done); \ + if (unlikely(___ret)) { \ + func(__VA_ARGS__); \ + __do_once_slow_done(&___done, &___once_key, \ + THIS_MODULE); \ + } \ + } \ + ___ret; \ + }) + #define get_random_once(buf, nbytes) \ DO_ONCE(get_random_bytes, (buf), (nbytes)) #define get_random_once_wait(buf, nbytes) \ DO_ONCE(get_random_bytes_wait, (buf), (nbytes)) \ +#define get_random_slow_once(buf, nbytes) \ + DO_ONCE_SLOW(get_random_bytes, (buf), (nbytes)) + #endif /* _LINUX_ONCE_H */ diff --git a/include/linux/platform_data/intel-spi.h b/include/linux/platform_data/intel-spi.h index 7f53a5c6f35e88a704116a0b30577e8633c194b6..7dda3f6904654ee3a04005c333a264ce3627af55 100644 --- a/include/linux/platform_data/intel-spi.h +++ b/include/linux/platform_data/intel-spi.h @@ -19,11 +19,13 @@ enum intel_spi_type { /** * struct intel_spi_boardinfo - Board specific data for Intel SPI driver * @type: Type which this controller is compatible with - * @writeable: The chip is writeable + * @set_writeable: Try to make the chip writeable (optional) + * @data: Data to be passed to @set_writeable can be %NULL */ struct intel_spi_boardinfo { enum intel_spi_type type; - bool writeable; + bool (*set_writeable)(void __iomem *base, void *data); + void *data; }; #endif /* INTEL_SPI_PDATA_H */ diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index 136ea0997e6df6c6d7e7910d02d2c54799ca85d8..7d5a78f49d43dd570e8eecef2a6402b25fb566a9 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -99,8 +99,8 @@ __ring_buffer_alloc(unsigned long size, unsigned flags, struct lock_class_key *k int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full); __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu, - struct file *filp, poll_table *poll_table); - + struct file *filp, poll_table *poll_table, int full); +void ring_buffer_wake_waiters(struct trace_buffer *buffer, int cpu); #define RING_BUFFER_ALL_CPUS -1 diff --git a/include/linux/sched.h b/include/linux/sched.h index 20d2cc49fd79beaf4970f14bae02ee4aca6e8218..78ef93e9590872d8efd230f71ba0b37469d81fdb 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1380,7 +1380,9 @@ struct task_struct { ANDROID_VENDOR_DATA_ARRAY(1, 64); ANDROID_OEM_DATA_ARRAY(1, 32); - ANDROID_KABI_RESERVE(1); + /* PF_IO_WORKER */ + ANDROID_KABI_USE(1, void *pf_io_worker); + ANDROID_KABI_RESERVE(2); ANDROID_KABI_RESERVE(3); ANDROID_KABI_RESERVE(4); diff --git a/include/linux/sched/jobctl.h b/include/linux/sched/jobctl.h index d2b4204ba4d34984b344ae4b302de77bc9603c74..fa067de9f1a94843f7402f2fd258d8b6339b59f0 100644 --- a/include/linux/sched/jobctl.h +++ b/include/linux/sched/jobctl.h @@ -19,7 +19,6 @@ struct task_struct; #define JOBCTL_TRAPPING_BIT 21 /* switching to TRACED */ #define JOBCTL_LISTENING_BIT 22 /* ptracer is listening for events */ #define JOBCTL_TRAP_FREEZE_BIT 23 /* trap for cgroup freezer */ -#define JOBCTL_TASK_WORK_BIT 24 /* set by TWA_SIGNAL */ #define JOBCTL_STOP_DEQUEUED (1UL << JOBCTL_STOP_DEQUEUED_BIT) #define JOBCTL_STOP_PENDING (1UL << JOBCTL_STOP_PENDING_BIT) @@ -29,10 +28,9 @@ struct task_struct; #define JOBCTL_TRAPPING (1UL << JOBCTL_TRAPPING_BIT) #define JOBCTL_LISTENING (1UL << JOBCTL_LISTENING_BIT) #define JOBCTL_TRAP_FREEZE (1UL << JOBCTL_TRAP_FREEZE_BIT) -#define JOBCTL_TASK_WORK (1UL << JOBCTL_TASK_WORK_BIT) #define JOBCTL_TRAP_MASK (JOBCTL_TRAP_STOP | JOBCTL_TRAP_NOTIFY) -#define JOBCTL_PENDING_MASK (JOBCTL_STOP_PENDING | JOBCTL_TRAP_MASK | JOBCTL_TASK_WORK) +#define JOBCTL_PENDING_MASK (JOBCTL_STOP_PENDING | JOBCTL_TRAP_MASK) extern bool task_set_jobctl_pending(struct task_struct *task, unsigned long mask); extern void task_clear_jobctl_trapping(struct task_struct *task); diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 02d53c6b574c6aa4955d6e35f8a50e2f1b1b2ad5..fb0b3899a86f4b7b3d7df7ce28d93ae4681a6255 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -360,11 +360,23 @@ static inline int restart_syscall(void) return -ERESTARTNOINTR; } -static inline int signal_pending(struct task_struct *p) +static inline int task_sigpending(struct task_struct *p) { return unlikely(test_tsk_thread_flag(p,TIF_SIGPENDING)); } +static inline int signal_pending(struct task_struct *p) +{ + /* + * TIF_NOTIFY_SIGNAL isn't really a signal, but it requires the same + * behavior in terms of ensuring that we break out of wait loops + * so that notify signal callbacks can be processed. + */ + if (unlikely(test_tsk_thread_flag(p, TIF_NOTIFY_SIGNAL))) + return 1; + return task_sigpending(p); +} + static inline int __fatal_signal_pending(struct task_struct *p) { return unlikely(sigismember(&p->pending.signal, SIGKILL)); @@ -372,7 +384,7 @@ static inline int __fatal_signal_pending(struct task_struct *p) static inline int fatal_signal_pending(struct task_struct *p) { - return signal_pending(p) && __fatal_signal_pending(p); + return task_sigpending(p) && __fatal_signal_pending(p); } static inline int signal_pending_state(long state, struct task_struct *p) @@ -509,7 +521,7 @@ extern int set_user_sigmask(const sigset_t __user *umask, size_t sigsetsize); static inline void restore_saved_sigmask_unless(bool interrupted) { if (interrupted) - WARN_ON(!test_thread_flag(TIF_SIGPENDING)); + WARN_ON(!signal_pending(current)); else restore_saved_sigmask(); } diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index df9505faed27991eb3ffd1e27ce954d041e6fc1b..5629761d979060ef04f5f3977bbc6f58b324a2ea 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -31,6 +31,7 @@ struct kernel_clone_args { /* Number of elements in *set_tid */ size_t set_tid_size; int cgroup; + int io_thread; struct cgroup *cgrp; struct css_set *cset; }; @@ -85,6 +86,7 @@ extern void exit_files(struct task_struct *); extern void exit_itimers(struct task_struct *); extern pid_t kernel_clone(struct kernel_clone_args *kargs); +struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node); struct task_struct *fork_idle(int); struct mm_struct *copy_init_mm(void); extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags); diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index dc30f62672d9a189c1027ea891994b87ad87f57a..bb1e05763c593c30893ec02ede4da3843ddf9750 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -685,6 +685,7 @@ typedef unsigned char *sk_buff_data_t; * @csum_level: indicates the number of consecutive checksums found in * the packet minus one that have been verified as * CHECKSUM_UNNECESSARY (max 3) + * @scm_io_uring: SKB holds io_uring registered files * @dst_pending_confirm: need to confirm neighbour * @decrypted: Decrypted SKB * @napi_id: id of the NAPI struct this skb came from @@ -912,7 +913,25 @@ struct sk_buff { __u32 headers_end[0]; /* public: */ - ANDROID_KABI_RESERVE(1); + /* Android KABI preservation. + * + * "open coded" version of ANDROID_KABI_USE() to pack more + * fields/variables into the space that we have. + * + * scm_io_uring is from 04df9719df18 ("io_uring/af_unix: defer + * registered files gc to io_uring release") + */ + /* NOTE: due to these fields ending up after headers_end, we have to + * manually copy them in the __copy_skb_header() call in skbuf.c. Be + * very aware of that if you change these fields. + */ + _ANDROID_KABI_REPLACE(_ANDROID_KABI_RESERVE(1), + struct { + __u8 scm_io_uring:1; + __u8 android_kabi_reserved1_padding1; + __u16 android_kabi_reserved1_padding2; + __u32 android_kabi_reserved1_padding3; + }); ANDROID_KABI_RESERVE(2); /* These elements must be at the end, see alloc_skb() for details. */ diff --git a/include/linux/socket.h b/include/linux/socket.h index 9aa530d497da8f738e2f2fd6f2d1b94bfd65c29c..c3b35d18bcd301035dd2794889b95450878e9cf8 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -421,6 +421,9 @@ extern int __sys_accept4_file(struct file *file, unsigned file_flags, struct sockaddr __user *upeer_sockaddr, int __user *upeer_addrlen, int flags, unsigned long nofile); +extern struct file *do_accept(struct file *file, unsigned file_flags, + struct sockaddr __user *upeer_sockaddr, + int __user *upeer_addrlen, int flags); extern int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr, int __user *upeer_addrlen, int flags); extern int __sys_socket(int family, int type, int protocol); @@ -436,5 +439,6 @@ extern int __sys_getpeername(int fd, struct sockaddr __user *usockaddr, int __user *usockaddr_len); extern int __sys_socketpair(int family, int type, int protocol, int __user *usockvec); +extern int __sys_shutdown_sock(struct socket *sock, int how); extern int __sys_shutdown(int fd, int how); #endif /* _LINUX_SOCKET_H */ diff --git a/include/linux/stddef.h b/include/linux/stddef.h index 998a4ba28eba40c966f7e4a6aaa68f46f6b3466b..938216f8ab7e7c85d6d54f595a70023cead69b23 100644 --- a/include/linux/stddef.h +++ b/include/linux/stddef.h @@ -36,4 +36,52 @@ enum { #define offsetofend(TYPE, MEMBER) \ (offsetof(TYPE, MEMBER) + sizeof_field(TYPE, MEMBER)) +/** + * struct_group() - Wrap a set of declarations in a mirrored struct + * + * @NAME: The identifier name of the mirrored sub-struct + * @MEMBERS: The member declarations for the mirrored structs + * + * Used to create an anonymous union of two structs with identical + * layout and size: one anonymous and one named. The former can be + * used normally without sub-struct naming, and the latter can be + * used to reason about the start, end, and size of the group of + * struct members. + */ +#define struct_group(NAME, MEMBERS...) \ + __struct_group(/* no tag */, NAME, /* no attrs */, MEMBERS) + +/** + * struct_group_attr() - Create a struct_group() with trailing attributes + * + * @NAME: The identifier name of the mirrored sub-struct + * @ATTRS: Any struct attributes to apply + * @MEMBERS: The member declarations for the mirrored structs + * + * Used to create an anonymous union of two structs with identical + * layout and size: one anonymous and one named. The former can be + * used normally without sub-struct naming, and the latter can be + * used to reason about the start, end, and size of the group of + * struct members. Includes structure attributes argument. + */ +#define struct_group_attr(NAME, ATTRS, MEMBERS...) \ + __struct_group(/* no tag */, NAME, ATTRS, MEMBERS) + +/** + * struct_group_tagged() - Create a struct_group with a reusable tag + * + * @TAG: The tag name for the named sub-struct + * @NAME: The identifier name of the mirrored sub-struct + * @MEMBERS: The member declarations for the mirrored structs + * + * Used to create an anonymous union of two structs with identical + * layout and size: one anonymous and one named. The former can be + * used normally without sub-struct naming, and the latter can be + * used to reason about the start, end, and size of the group of + * struct members. Includes struct tag argument for the named copy, + * so the specified layout can be reused later. + */ +#define struct_group_tagged(TAG, NAME, MEMBERS...) \ + __struct_group(TAG, NAME, /* no attrs */, MEMBERS) + #endif diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 112ff24ea927b3b8b488d5a58bb70f634496d183..1c170be3f7465a84149515f4d2463643ab9b327b 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -341,7 +341,7 @@ asmlinkage long sys_io_uring_setup(u32 entries, struct io_uring_params __user *p); asmlinkage long sys_io_uring_enter(unsigned int fd, u32 to_submit, u32 min_complete, u32 flags, - const sigset_t __user *sig, size_t sigsz); + const void __user *argp, size_t argsz); asmlinkage long sys_io_uring_register(unsigned int fd, unsigned int op, void __user *arg, unsigned int nr_args); diff --git a/include/linux/task_work.h b/include/linux/task_work.h index 0d848a1e9e62f18840ebd33a4e355b50d1526629..5b8a93f288bb4d924dcead4cb79b3754e0fecad4 100644 --- a/include/linux/task_work.h +++ b/include/linux/task_work.h @@ -22,6 +22,8 @@ enum task_work_notify_mode { int task_work_add(struct task_struct *task, struct callback_head *twork, enum task_work_notify_mode mode); +struct callback_head *task_work_cancel_match(struct task_struct *task, + bool (*match)(struct callback_head *, void *data), void *data); struct callback_head *task_work_cancel(struct task_struct *, task_work_func_t); void task_work_run(void); diff --git a/include/linux/tcp.h b/include/linux/tcp.h index b163dbd6875c0aaa42a612d007d57a55e9384f3b..5d728224a7613a34585bdf7020ee92d60ab3649f 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -266,7 +266,12 @@ struct tcp_sock { u32 packets_out; /* Packets which are "in flight" */ u32 retrans_out; /* Retransmitted packets out */ u32 max_packets_out; /* max packets_out in last window */ - u32 max_packets_seq; /* right edge of max_packets_out flight */ + /* ANDROID: + * max_packets_seq is really cwnd_usage_seq upstream, old name kept + * to preserve ABI due to changes in commit 49d429760df7 ("tcp: fix + * tcp_cwnd_validate() to not forget is_cwnd_limited") + */ + u32 max_packets_seq; /* right edge of cwnd usage tracking flight */ u16 urg_data; /* Saved octet of OOB data and control flags */ u8 ecn_flags; /* ECN status bits. */ diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index b480e1a07ed85198e4d43dde761ae9420734dc95..ee9ab7dbc8c3508606da402f10338e1df31cd528 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -198,4 +198,27 @@ static inline void tracehook_notify_resume(struct pt_regs *regs) blkcg_maybe_throttle_current(); } +/* + * called by exit_to_user_mode_loop() if ti_work & _TIF_NOTIFY_SIGNAL. This + * is currently used by TWA_SIGNAL based task_work, which requires breaking + * wait loops to ensure that task_work is noticed and run. + */ +static inline void tracehook_notify_signal(void) +{ + clear_thread_flag(TIF_NOTIFY_SIGNAL); + smp_mb__after_atomic(); + if (current->task_works) + task_work_run(); +} + +/* + * Called when we have work to process from exit_to_user_mode_loop() + */ +static inline void set_notify_signal(struct task_struct *task) +{ + if (!test_and_set_tsk_thread_flag(task, TIF_NOTIFY_SIGNAL) && + !wake_up_state(task, TASK_INTERRUPTIBLE)) + kick_process(task); +} + #endif /* */ diff --git a/include/linux/uio.h b/include/linux/uio.h index 27ff8eb786dc34817ac875f780b478c2b93a758f..cedb68e49e4f9830173dbb983f16c0f6bd3ca4a9 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -26,6 +26,12 @@ enum iter_type { ITER_DISCARD = 64, }; +struct iov_iter_state { + size_t iov_offset; + size_t count; + unsigned long nr_segs; +}; + struct iov_iter { /* * Bit 0 is the read/write bit, set if we're writing. @@ -55,6 +61,14 @@ static inline enum iter_type iov_iter_type(const struct iov_iter *i) return i->type & ~(READ | WRITE); } +static inline void iov_iter_save_state(struct iov_iter *iter, + struct iov_iter_state *state) +{ + state->iov_offset = iter->iov_offset; + state->count = iter->count; + state->nr_segs = iter->nr_segs; +} + static inline bool iter_is_iovec(const struct iov_iter *i) { return iov_iter_type(i) == ITER_IOVEC; @@ -226,6 +240,7 @@ ssize_t iov_iter_get_pages(struct iov_iter *i, struct page **pages, ssize_t iov_iter_get_pages_alloc(struct iov_iter *i, struct page ***pages, size_t maxsize, size_t *start); int iov_iter_npages(const struct iov_iter *i, int maxpages); +void iov_iter_restore(struct iov_iter *i, struct iov_iter_state *state); const void *dup_iter(struct iov_iter *new, struct iov_iter *old, gfp_t flags); diff --git a/include/media/v4l2-common.h b/include/media/v4l2-common.h index df4ad81251195e14f06088eda2a1674094afa144..40cd995491132cb2f7ae852e730ea688b5787f9d 100644 --- a/include/media/v4l2-common.h +++ b/include/media/v4l2-common.h @@ -175,7 +175,8 @@ struct v4l2_subdev *v4l2_i2c_new_subdev_board(struct v4l2_device *v4l2_dev, * * @sd: pointer to &struct v4l2_subdev * @client: pointer to struct i2c_client - * @devname: the name of the device; if NULL, the I²C device's name will be used + * @devname: the name of the device; if NULL, the I²C device drivers's name + * will be used * @postfix: sub-device specific string to put right after the I²C device name; * may be NULL */ diff --git a/include/net/ieee802154_netdev.h b/include/net/ieee802154_netdev.h index a8994f307fc3896a85aeecc5007dcadd1166118c..03b64bf876a4654f0466744fac5fb4b0fb52f4cf 100644 --- a/include/net/ieee802154_netdev.h +++ b/include/net/ieee802154_netdev.h @@ -185,21 +185,27 @@ static inline int ieee802154_sockaddr_check_size(struct sockaddr_ieee802154 *daddr, int len) { struct ieee802154_addr_sa *sa; + int ret = 0; sa = &daddr->addr; if (len < IEEE802154_MIN_NAMELEN) return -EINVAL; switch (sa->addr_type) { + case IEEE802154_ADDR_NONE: + break; case IEEE802154_ADDR_SHORT: if (len < IEEE802154_NAMELEN_SHORT) - return -EINVAL; + ret = -EINVAL; break; case IEEE802154_ADDR_LONG: if (len < IEEE802154_NAMELEN_LONG) - return -EINVAL; + ret = -EINVAL; + break; + default: + ret = -EINVAL; break; } - return 0; + return ret; } static inline void ieee802154_addr_from_sa(struct ieee802154_addr *a, diff --git a/include/net/ip.h b/include/net/ip.h index 57bdaac124694409a2e66d78938375200fcd411b..9a79511743b4011fa2d1bc035d246fe4fc13a6bd 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -556,7 +556,7 @@ static inline void iph_to_flow_copy_v4addrs(struct flow_keys *flow, BUILD_BUG_ON(offsetof(typeof(flow->addrs), v4addrs.dst) != offsetof(typeof(flow->addrs), v4addrs.src) + sizeof(flow->addrs.v4addrs.src)); - memcpy(&flow->addrs.v4addrs, &iph->saddr, sizeof(flow->addrs.v4addrs)); + memcpy(&flow->addrs.v4addrs, &iph->addrs, sizeof(flow->addrs.v4addrs)); flow->control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; } diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 60601896d4747ff5800786b7421873135d47a857..89ce8a50f2363ddaa670c32de63db90affe294e8 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -842,7 +842,7 @@ static inline void iph_to_flow_copy_v6addrs(struct flow_keys *flow, BUILD_BUG_ON(offsetof(typeof(flow->addrs), v6addrs.dst) != offsetof(typeof(flow->addrs), v6addrs.src) + sizeof(flow->addrs.v6addrs.src)); - memcpy(&flow->addrs.v6addrs, &iph->saddr, sizeof(flow->addrs.v6addrs)); + memcpy(&flow->addrs.v6addrs, &iph->addrs, sizeof(flow->addrs.v6addrs)); flow->control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; } diff --git a/include/net/protocol.h b/include/net/protocol.h index 2b778e1d2d8f1365c969952b9aed939e28cb80d7..0fd2df844fc71ff81cdf5bf13f9d010a1bbe828d 100644 --- a/include/net/protocol.h +++ b/include/net/protocol.h @@ -35,8 +35,6 @@ /* This is used to register protocols. */ struct net_protocol { - int (*early_demux)(struct sk_buff *skb); - int (*early_demux_handler)(struct sk_buff *skb); int (*handler)(struct sk_buff *skb); /* This returns an error if we weren't able to handle the error. */ @@ -53,8 +51,6 @@ struct net_protocol { #if IS_ENABLED(CONFIG_IPV6) struct inet6_protocol { - void (*early_demux)(struct sk_buff *skb); - void (*early_demux_handler)(struct sk_buff *skb); int (*handler)(struct sk_buff *skb); /* This returns an error if we weren't able to handle the error. */ diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 4b8c400658361945320e343d1cea435251f0a187..bd0cb93fae4e34fa26d79c65152c137afabd1f99 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -1185,7 +1185,6 @@ static inline void __qdisc_reset_queue(struct qdisc_skb_head *qh) static inline void qdisc_reset_queue(struct Qdisc *sch) { __qdisc_reset_queue(&sch->q); - sch->qstats.backlog = 0; } static inline struct Qdisc *qdisc_replace(struct Qdisc *sch, struct Qdisc *new, diff --git a/include/net/sock.h b/include/net/sock.h index d389a28015539aad6615c9956f8ff7a59826acef..d41488eec84d59682ac9bb70ad4250212055d2b6 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -423,7 +423,7 @@ struct sock { #ifdef CONFIG_XFRM struct xfrm_policy __rcu *sk_policy[2]; #endif - struct dst_entry *sk_rx_dst; + struct dst_entry __rcu *sk_rx_dst; struct dst_entry __rcu *sk_dst_cache; atomic_t sk_omem_alloc; int sk_sndbuf; diff --git a/include/net/sock_reuseport.h b/include/net/sock_reuseport.h index 505f1e18e9bf96ceb3a660729ef6e5b01bb41c2a..3eac185ae2e8afc3ff2028f8cc4a38bba4fe0db8 100644 --- a/include/net/sock_reuseport.h +++ b/include/net/sock_reuseport.h @@ -38,21 +38,20 @@ extern struct sock *reuseport_select_sock(struct sock *sk, extern int reuseport_attach_prog(struct sock *sk, struct bpf_prog *prog); extern int reuseport_detach_prog(struct sock *sk); -static inline bool reuseport_has_conns(struct sock *sk, bool set) +static inline bool reuseport_has_conns(struct sock *sk) { struct sock_reuseport *reuse; bool ret = false; rcu_read_lock(); reuse = rcu_dereference(sk->sk_reuseport_cb); - if (reuse) { - if (set) - reuse->has_conns = 1; - ret = reuse->has_conns; - } + if (reuse && reuse->has_conns) + ret = true; rcu_read_unlock(); return ret; } +void reuseport_has_conns_set(struct sock *sk); + #endif /* _SOCK_REUSEPORT_H */ diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 8528015590e44fdab27d6200eef46fd0ff838e50..afdf8bd1b4fe52f4be39a0a15d1b36e08a9d90fe 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -38,6 +38,7 @@ enum switchdev_attr_id { SWITCHDEV_ATTR_ID_PORT_MROUTER, SWITCHDEV_ATTR_ID_BRIDGE_AGEING_TIME, SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING, + SWITCHDEV_ATTR_ID_BRIDGE_VLAN_PROTOCOL, SWITCHDEV_ATTR_ID_BRIDGE_MC_DISABLED, SWITCHDEV_ATTR_ID_BRIDGE_MROUTER, #if IS_ENABLED(CONFIG_BRIDGE_MRP) @@ -57,6 +58,7 @@ struct switchdev_attr { bool mrouter; /* PORT_MROUTER */ clock_t ageing_time; /* BRIDGE_AGEING_TIME */ bool vlan_filtering; /* BRIDGE_VLAN_FILTERING */ + u16 vlan_protocol; /* BRIDGE_VLAN_PROTOCOL */ bool mc_disabled; /* MC_DISABLED */ #if IS_ENABLED(CONFIG_BRIDGE_MRP) u8 mrp_port_role; /* MRP_PORT_ROLE */ diff --git a/include/net/tcp.h b/include/net/tcp.h index 7a589fb027f50f8e62d496b3e0d7f55ce3e3f127..dc9f2247839528f1713278f7a1716f9ab5b7caeb 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -934,7 +934,7 @@ extern const struct inet_connection_sock_af_ops ipv6_specific; INDIRECT_CALLABLE_DECLARE(void tcp_v6_send_check(struct sock *sk, struct sk_buff *skb)); INDIRECT_CALLABLE_DECLARE(int tcp_v6_rcv(struct sk_buff *skb)); -INDIRECT_CALLABLE_DECLARE(void tcp_v6_early_demux(struct sk_buff *skb)); +void tcp_v6_early_demux(struct sk_buff *skb); #endif @@ -1265,11 +1265,14 @@ static inline bool tcp_is_cwnd_limited(const struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); + if (tp->is_cwnd_limited) + return true; + /* If in slow start, ensure cwnd grows to twice what was ACKed. */ if (tcp_in_slow_start(tp)) return tp->snd_cwnd < 2 * tp->max_packets_out; - return tp->is_cwnd_limited; + return false; } /* BBR congestion control needs pacing. diff --git a/include/net/udp.h b/include/net/udp.h index 010bc324f860b33dd19aa84fd387a552cffd935f..388e68c7bca050b3782201a80a424575a5f793bc 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -176,6 +176,7 @@ INDIRECT_CALLABLE_DECLARE(int udp6_gro_complete(struct sk_buff *, int)); struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb, struct udphdr *uh, struct sock *sk); int udp_gro_complete(struct sk_buff *skb, int nhoff, udp_lookup_t lookup); +void udp_v6_early_demux(struct sk_buff *skb); struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, netdev_features_t features, bool is_ipv6); diff --git a/include/trace/events/io_uring.h b/include/trace/events/io_uring.h index 9f0d3b7d56b0f31351e0d498be643524b3e895dc..0dd30de00e5b44ce0c0d8090299fc1ac8a22fa15 100644 --- a/include/trace/events/io_uring.h +++ b/include/trace/events/io_uring.h @@ -12,11 +12,11 @@ struct io_wq_work; /** * io_uring_create - called after a new io_uring context was prepared * - * @fd: corresponding file descriptor - * @ctx: pointer to a ring context structure + * @fd: corresponding file descriptor + * @ctx: pointer to a ring context structure * @sq_entries: actual SQ size * @cq_entries: actual CQ size - * @flags: SQ ring flags, provided to io_uring_setup(2) + * @flags: SQ ring flags, provided to io_uring_setup(2) * * Allows to trace io_uring creation and provide pointer to a context, that can * be used later to find correlated events. @@ -49,15 +49,15 @@ TRACE_EVENT(io_uring_create, ); /** - * io_uring_register - called after a buffer/file/eventfd was succesfully + * io_uring_register - called after a buffer/file/eventfd was successfully * registered for a ring * - * @ctx: pointer to a ring context structure - * @opcode: describes which operation to perform + * @ctx: pointer to a ring context structure + * @opcode: describes which operation to perform * @nr_user_files: number of registered files * @nr_user_bufs: number of registered buffers * @cq_ev_fd: whether eventfs registered or not - * @ret: return code + * @ret: return code * * Allows to trace fixed files/buffers/eventfds, that could be registered to * avoid an overhead of getting references to them for every operation. This @@ -142,16 +142,16 @@ TRACE_EVENT(io_uring_queue_async_work, TP_ARGS(ctx, rw, req, work, flags), TP_STRUCT__entry ( - __field( void *, ctx ) - __field( int, rw ) - __field( void *, req ) + __field( void *, ctx ) + __field( int, rw ) + __field( void *, req ) __field( struct io_wq_work *, work ) __field( unsigned int, flags ) ), TP_fast_assign( __entry->ctx = ctx; - __entry->rw = rw; + __entry->rw = rw; __entry->req = req; __entry->work = work; __entry->flags = flags; @@ -196,10 +196,10 @@ TRACE_EVENT(io_uring_defer, /** * io_uring_link - called before the io_uring request added into link_list of - * another request + * another request * - * @ctx: pointer to a ring context structure - * @req: pointer to a linked request + * @ctx: pointer to a ring context structure + * @req: pointer to a linked request * @target_req: pointer to a previous request, that would contain @req * * Allows to track linked requests, to understand dependencies between requests @@ -212,8 +212,8 @@ TRACE_EVENT(io_uring_link, TP_ARGS(ctx, req, target_req), TP_STRUCT__entry ( - __field( void *, ctx ) - __field( void *, req ) + __field( void *, ctx ) + __field( void *, req ) __field( void *, target_req ) ), @@ -244,7 +244,7 @@ TRACE_EVENT(io_uring_cqring_wait, TP_ARGS(ctx, min_events), TP_STRUCT__entry ( - __field( void *, ctx ) + __field( void *, ctx ) __field( int, min_events ) ), @@ -272,7 +272,7 @@ TRACE_EVENT(io_uring_fail_link, TP_ARGS(req, link), TP_STRUCT__entry ( - __field( void *, req ) + __field( void *, req ) __field( void *, link ) ), @@ -290,38 +290,42 @@ TRACE_EVENT(io_uring_fail_link, * @ctx: pointer to a ring context structure * @user_data: user data associated with the request * @res: result of the request + * @cflags: completion flags * */ TRACE_EVENT(io_uring_complete, - TP_PROTO(void *ctx, u64 user_data, long res), + TP_PROTO(void *ctx, u64 user_data, int res, unsigned cflags), - TP_ARGS(ctx, user_data, res), + TP_ARGS(ctx, user_data, res, cflags), TP_STRUCT__entry ( __field( void *, ctx ) __field( u64, user_data ) - __field( long, res ) + __field( int, res ) + __field( unsigned, cflags ) ), TP_fast_assign( __entry->ctx = ctx; __entry->user_data = user_data; __entry->res = res; + __entry->cflags = cflags; ), - TP_printk("ring %p, user_data 0x%llx, result %ld", + TP_printk("ring %p, user_data 0x%llx, result %d, cflags %x", __entry->ctx, (unsigned long long)__entry->user_data, - __entry->res) + __entry->res, __entry->cflags) ); - /** * io_uring_submit_sqe - called before submitting one SQE * * @ctx: pointer to a ring context structure + * @req: pointer to a submitted request * @opcode: opcode of request * @user_data: user data associated with the request + * @flags request flags * @force_nonblock: whether a context blocking or not * @sq_thread: true if sq_thread has submitted this SQE * @@ -330,41 +334,60 @@ TRACE_EVENT(io_uring_complete, */ TRACE_EVENT(io_uring_submit_sqe, - TP_PROTO(void *ctx, u8 opcode, u64 user_data, bool force_nonblock, - bool sq_thread), + TP_PROTO(void *ctx, void *req, u8 opcode, u64 user_data, u32 flags, + bool force_nonblock, bool sq_thread), - TP_ARGS(ctx, opcode, user_data, force_nonblock, sq_thread), + TP_ARGS(ctx, req, opcode, user_data, flags, force_nonblock, sq_thread), TP_STRUCT__entry ( __field( void *, ctx ) + __field( void *, req ) __field( u8, opcode ) __field( u64, user_data ) + __field( u32, flags ) __field( bool, force_nonblock ) __field( bool, sq_thread ) ), TP_fast_assign( __entry->ctx = ctx; + __entry->req = req; __entry->opcode = opcode; __entry->user_data = user_data; + __entry->flags = flags; __entry->force_nonblock = force_nonblock; __entry->sq_thread = sq_thread; ), - TP_printk("ring %p, op %d, data 0x%llx, non block %d, sq_thread %d", - __entry->ctx, __entry->opcode, - (unsigned long long) __entry->user_data, - __entry->force_nonblock, __entry->sq_thread) + TP_printk("ring %p, req %p, op %d, data 0x%llx, flags %u, " + "non block %d, sq_thread %d", __entry->ctx, __entry->req, + __entry->opcode, (unsigned long long)__entry->user_data, + __entry->flags, __entry->force_nonblock, __entry->sq_thread) ); +/* + * io_uring_poll_arm - called after arming a poll wait if successful + * + * @ctx: pointer to a ring context structure + * @req: pointer to the armed request + * @opcode: opcode of request + * @user_data: user data associated with the request + * @mask: request poll events mask + * @events: registered events of interest + * + * Allows to track which fds are waiting for and what are the events of + * interest. + */ TRACE_EVENT(io_uring_poll_arm, - TP_PROTO(void *ctx, u8 opcode, u64 user_data, int mask, int events), + TP_PROTO(void *ctx, void *req, u8 opcode, u64 user_data, + int mask, int events), - TP_ARGS(ctx, opcode, user_data, mask, events), + TP_ARGS(ctx, req, opcode, user_data, mask, events), TP_STRUCT__entry ( __field( void *, ctx ) + __field( void *, req ) __field( u8, opcode ) __field( u64, user_data ) __field( int, mask ) @@ -373,16 +396,17 @@ TRACE_EVENT(io_uring_poll_arm, TP_fast_assign( __entry->ctx = ctx; + __entry->req = req; __entry->opcode = opcode; __entry->user_data = user_data; __entry->mask = mask; __entry->events = events; ), - TP_printk("ring %p, op %d, data 0x%llx, mask 0x%x, events 0x%x", - __entry->ctx, __entry->opcode, - (unsigned long long) __entry->user_data, - __entry->mask, __entry->events) + TP_printk("ring %p, req %p, op %d, data 0x%llx, mask 0x%x, events 0x%x", + __entry->ctx, __entry->req, __entry->opcode, + (unsigned long long) __entry->user_data, + __entry->mask, __entry->events) ); TRACE_EVENT(io_uring_poll_wake, @@ -437,27 +461,40 @@ TRACE_EVENT(io_uring_task_add, __entry->mask) ); +/* + * io_uring_task_run - called when task_work_run() executes the poll events + * notification callbacks + * + * @ctx: pointer to a ring context structure + * @req: pointer to the armed request + * @opcode: opcode of request + * @user_data: user data associated with the request + * + * Allows to track when notified poll events are processed + */ TRACE_EVENT(io_uring_task_run, - TP_PROTO(void *ctx, u8 opcode, u64 user_data), + TP_PROTO(void *ctx, void *req, u8 opcode, u64 user_data), - TP_ARGS(ctx, opcode, user_data), + TP_ARGS(ctx, req, opcode, user_data), TP_STRUCT__entry ( __field( void *, ctx ) + __field( void *, req ) __field( u8, opcode ) __field( u64, user_data ) ), TP_fast_assign( __entry->ctx = ctx; + __entry->req = req; __entry->opcode = opcode; __entry->user_data = user_data; ), - TP_printk("ring %p, op %d, data 0x%llx", - __entry->ctx, __entry->opcode, - (unsigned long long) __entry->user_data) + TP_printk("ring %p, req %p, op %d, data 0x%llx", + __entry->ctx, __entry->req, __entry->opcode, + (unsigned long long) __entry->user_data) ); #endif /* _TRACE_IO_URING_H */ diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 1c714336b8635c665b02e015c5074248dc584b3e..221856f2d295c44ecee99ce709d2fda2391e30c6 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -583,7 +583,7 @@ TRACE_EVENT(rxrpc_client, TP_fast_assign( __entry->conn = conn ? conn->debug_id : 0; __entry->channel = channel; - __entry->usage = conn ? atomic_read(&conn->usage) : -2; + __entry->usage = conn ? refcount_read(&conn->ref) : -2; __entry->op = op; __entry->cid = conn ? conn->proto.cid : 0; ), diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h index cd2d8279a5e44714dc32bae06c1471b62ef59a7a..cb4e8e6e86a90b7c10a749740ee11cef0005e5d3 100644 --- a/include/uapi/linux/audit.h +++ b/include/uapi/linux/audit.h @@ -182,7 +182,7 @@ #define AUDIT_MAX_KEY_LEN 256 #define AUDIT_BITMASK_SIZE 64 #define AUDIT_WORD(nr) ((__u32)((nr)/32)) -#define AUDIT_BIT(nr) (1 << ((nr) - AUDIT_WORD(nr)*32)) +#define AUDIT_BIT(nr) (1U << ((nr) - AUDIT_WORD(nr)*32)) #define AUDIT_SYSCALL_CLASSES 16 #define AUDIT_CLASS_DIR_WRITE 0 diff --git a/include/uapi/linux/capability.h b/include/uapi/linux/capability.h index 741985d12f7dd6a69bb37ca35fc5f732c0e4e8e6..9ae1b3aecb1006ea7c5bfec2900a8ec19f546fd6 100644 --- a/include/uapi/linux/capability.h +++ b/include/uapi/linux/capability.h @@ -425,7 +425,7 @@ struct vfs_ns_cap_data { */ #define CAP_TO_INDEX(x) ((x) >> 5) /* 1 << 5 == bits in __u32 */ -#define CAP_TO_MASK(x) (1 << ((x) & 31)) /* mask for indexed __u32 */ +#define CAP_TO_MASK(x) (1U << ((x) & 31)) /* mask for indexed __u32 */ #endif /* _UAPI_LINUX_CAPABILITY_H */ diff --git a/include/uapi/linux/eventpoll.h b/include/uapi/linux/eventpoll.h index 8a3432d0f0dcb69bf1d0caaf75a363bad02468fa..e687658843b1c7eb840da95bd6fe1d64783af3a6 100644 --- a/include/uapi/linux/eventpoll.h +++ b/include/uapi/linux/eventpoll.h @@ -41,6 +41,12 @@ #define EPOLLMSG (__force __poll_t)0x00000400 #define EPOLLRDHUP (__force __poll_t)0x00002000 +/* + * Internal flag - wakeup generated by io_uring, used to detect recursion back + * into the io_uring poll handler. + */ +#define EPOLL_URING_WAKE ((__force __poll_t)(1U << 27)) + /* Set exclusive wakeup mode for the target file descriptor */ #define EPOLLEXCLUSIVE ((__force __poll_t)(1U << 28)) diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 98d8e06dea220cfa799569ccefb58c075000f50f..6481db93700287afd050a1cac3b4d0058956cba7 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -42,23 +42,25 @@ struct io_uring_sqe { __u32 statx_flags; __u32 fadvise_advice; __u32 splice_flags; + __u32 rename_flags; + __u32 unlink_flags; + __u32 hardlink_flags; }; __u64 user_data; /* data to be passed back at completion time */ + /* pack this to avoid bogus arm OABI complaints */ union { - struct { - /* pack this to avoid bogus arm OABI complaints */ - union { - /* index into fixed buffers, if used */ - __u16 buf_index; - /* for grouped buffer selection */ - __u16 buf_group; - } __attribute__((packed)); - /* personality to use, if used */ - __u16 personality; - __s32 splice_fd_in; - }; - __u64 __pad2[3]; + /* index into fixed buffers, if used */ + __u16 buf_index; + /* for grouped buffer selection */ + __u16 buf_group; + } __attribute__((packed)); + /* personality to use, if used */ + __u16 personality; + union { + __s32 splice_fd_in; + __u32 file_index; }; + __u64 __pad2[2]; }; enum { @@ -132,6 +134,9 @@ enum { IORING_OP_PROVIDE_BUFFERS, IORING_OP_REMOVE_BUFFERS, IORING_OP_TEE, + IORING_OP_SHUTDOWN, + IORING_OP_RENAMEAT, + IORING_OP_UNLINKAT, /* this goes last, obviously */ IORING_OP_LAST, @@ -145,14 +150,34 @@ enum { /* * sqe->timeout_flags */ -#define IORING_TIMEOUT_ABS (1U << 0) - +#define IORING_TIMEOUT_ABS (1U << 0) +#define IORING_TIMEOUT_UPDATE (1U << 1) +#define IORING_TIMEOUT_BOOTTIME (1U << 2) +#define IORING_TIMEOUT_REALTIME (1U << 3) +#define IORING_LINK_TIMEOUT_UPDATE (1U << 4) +#define IORING_TIMEOUT_CLOCK_MASK (IORING_TIMEOUT_BOOTTIME | IORING_TIMEOUT_REALTIME) +#define IORING_TIMEOUT_UPDATE_MASK (IORING_TIMEOUT_UPDATE | IORING_LINK_TIMEOUT_UPDATE) /* * sqe->splice_flags * extends splice(2) flags */ #define SPLICE_F_FD_IN_FIXED (1U << 31) /* the last bit of __u32 */ +/* + * POLL_ADD flags. Note that since sqe->poll_events is the flag space, the + * command flags for POLL_ADD are stored in sqe->len. + * + * IORING_POLL_ADD_MULTI Multishot poll. Sets IORING_CQE_F_MORE if + * the poll handler will continue to report + * CQEs on behalf of the same SQE. + * + * IORING_POLL_UPDATE Update existing poll request, matching + * sqe->addr as the old user_data field. + */ +#define IORING_POLL_ADD_MULTI (1U << 0) +#define IORING_POLL_UPDATE_EVENTS (1U << 1) +#define IORING_POLL_UPDATE_USER_DATA (1U << 2) + /* * IO completion data structure (Completion Queue Entry) */ @@ -166,8 +191,10 @@ struct io_uring_cqe { * cqe->flags * * IORING_CQE_F_BUFFER If set, the upper 16 bits are the buffer ID + * IORING_CQE_F_MORE If set, parent SQE will generate more CQE entries */ #define IORING_CQE_F_BUFFER (1U << 0) +#define IORING_CQE_F_MORE (1U << 1) enum { IORING_CQE_BUFFER_SHIFT = 16, @@ -226,6 +253,7 @@ struct io_cqring_offsets { #define IORING_ENTER_GETEVENTS (1U << 0) #define IORING_ENTER_SQ_WAKEUP (1U << 1) #define IORING_ENTER_SQ_WAIT (1U << 2) +#define IORING_ENTER_EXT_ARG (1U << 3) /* * Passed in for io_uring_setup(2). Copied back with updated info on success @@ -253,6 +281,10 @@ struct io_uring_params { #define IORING_FEAT_CUR_PERSONALITY (1U << 4) #define IORING_FEAT_FAST_POLL (1U << 5) #define IORING_FEAT_POLL_32BITS (1U << 6) +#define IORING_FEAT_SQPOLL_NONFIXED (1U << 7) +#define IORING_FEAT_EXT_ARG (1U << 8) +#define IORING_FEAT_NATIVE_WORKERS (1U << 9) +#define IORING_FEAT_RSRC_TAGS (1U << 10) /* * io_uring_register(2) opcodes and arguments @@ -272,16 +304,62 @@ enum { IORING_REGISTER_RESTRICTIONS = 11, IORING_REGISTER_ENABLE_RINGS = 12, + /* extended with tagging */ + IORING_REGISTER_FILES2 = 13, + IORING_REGISTER_FILES_UPDATE2 = 14, + IORING_REGISTER_BUFFERS2 = 15, + IORING_REGISTER_BUFFERS_UPDATE = 16, + + /* set/clear io-wq thread affinities */ + IORING_REGISTER_IOWQ_AFF = 17, + IORING_UNREGISTER_IOWQ_AFF = 18, + + /* set/get max number of io-wq workers */ + IORING_REGISTER_IOWQ_MAX_WORKERS = 19, + /* this goes last */ IORING_REGISTER_LAST }; +/* io-wq worker categories */ +enum { + IO_WQ_BOUND, + IO_WQ_UNBOUND, +}; + +/* deprecated, see struct io_uring_rsrc_update */ struct io_uring_files_update { __u32 offset; __u32 resv; __aligned_u64 /* __s32 * */ fds; }; +struct io_uring_rsrc_register { + __u32 nr; + __u32 resv; + __u64 resv2; + __aligned_u64 data; + __aligned_u64 tags; +}; + +struct io_uring_rsrc_update { + __u32 offset; + __u32 resv; + __aligned_u64 data; +}; + +struct io_uring_rsrc_update2 { + __u32 offset; + __u32 resv; + __aligned_u64 data; + __aligned_u64 tags; + __u32 nr; + __u32 resv2; +}; + +/* Skip updating fd indexes set to this value in the fd table */ +#define IORING_REGISTER_FILES_SKIP (-2) + #define IO_URING_OP_SUPPORTED (1U << 0) struct io_uring_probe_op { @@ -329,4 +407,11 @@ enum { IORING_RESTRICTION_LAST }; +struct io_uring_getevents_arg { + __u64 sigmask; + __u32 sigmask_sz; + __u32 pad; + __u64 ts; +}; + #endif diff --git a/include/uapi/linux/ip.h b/include/uapi/linux/ip.h index e42d13b55cf3acafd90f0ec6d13ebd685ad3f684..64beb32a2102680f963bca769ee87b2fc8c216e3 100644 --- a/include/uapi/linux/ip.h +++ b/include/uapi/linux/ip.h @@ -100,8 +100,14 @@ struct iphdr { __u8 ttl; __u8 protocol; __sum16 check; - __be32 saddr; - __be32 daddr; +#ifndef __GENKSYMS__ + __struct_group(/* no tag */, addrs, /* no attrs */, +#endif + __be32 saddr; + __be32 daddr; +#ifndef __GENKSYMS__ + ); +#endif /*The options start here. */ }; diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h index 13e8751bf24a0373fedb61b7b56d56c488477817..bfe9542953af5adfcc68b49f6496b0c7e1f8e245 100644 --- a/include/uapi/linux/ipv6.h +++ b/include/uapi/linux/ipv6.h @@ -130,8 +130,14 @@ struct ipv6hdr { __u8 nexthdr; __u8 hop_limit; - struct in6_addr saddr; - struct in6_addr daddr; +#ifndef __GENKSYMS__ + __struct_group(/* no tag */, addrs, /* no attrs */, +#endif + struct in6_addr saddr; + struct in6_addr daddr; +#ifndef __GENKSYMS__ + ); +#endif }; diff --git a/include/uapi/linux/openat2.h b/include/uapi/linux/openat2.h index 58b1eb71136007727e8535eaeb19e2ea4a00fb9a..a5feb7604948791c7a34ec0876c24a97eb5a375b 100644 --- a/include/uapi/linux/openat2.h +++ b/include/uapi/linux/openat2.h @@ -35,5 +35,9 @@ struct open_how { #define RESOLVE_IN_ROOT 0x10 /* Make all jumps to "/" and ".." be scoped inside the dirfd (similar to chroot(2)). */ +#define RESOLVE_CACHED 0x20 /* Only complete if resolution can be + completed through cached lookup. May + return -EAGAIN if that's not + possible. */ #endif /* _UAPI_LINUX_OPENAT2_H */ diff --git a/include/uapi/linux/stddef.h b/include/uapi/linux/stddef.h index ee8220f8dcf5f5e16662580cc5c35ac66c322048..c3725b4922632346ee99666d5f280fe4a85b7c61 100644 --- a/include/uapi/linux/stddef.h +++ b/include/uapi/linux/stddef.h @@ -1,6 +1,31 @@ /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI_LINUX_STDDEF_H +#define _UAPI_LINUX_STDDEF_H + #include #ifndef __always_inline #define __always_inline inline #endif + +/** + * __struct_group() - Create a mirrored named and anonyomous struct + * + * @TAG: The tag name for the named sub-struct (usually empty) + * @NAME: The identifier name of the mirrored sub-struct + * @ATTRS: Any struct attributes (usually empty) + * @MEMBERS: The member declarations for the mirrored structs + * + * Used to create an anonymous union of two structs with identical layout + * and size: one anonymous and one named. The former's members can be used + * normally without sub-struct naming, and the latter can be used to + * reason about the start, end, and size of the group of struct members. + * The named struct can also be explicitly tagged for layer reuse, as well + * as both having struct attributes appended. + */ +#define __struct_group(TAG, NAME, ATTRS, MEMBERS...) \ + union { \ + struct { MEMBERS } ATTRS; \ + struct TAG { MEMBERS } ATTRS NAME; \ + } +#endif diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 72b94b4bafe4a570c19b96a355e3c9223f90085c..069241b0a2fec97c4ce0e81db0a0716ead609f51 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -1555,7 +1555,8 @@ struct v4l2_bt_timings { ((bt)->width + V4L2_DV_BT_BLANKING_WIDTH(bt)) #define V4L2_DV_BT_BLANKING_HEIGHT(bt) \ ((bt)->vfrontporch + (bt)->vsync + (bt)->vbackporch + \ - (bt)->il_vfrontporch + (bt)->il_vsync + (bt)->il_vbackporch) + ((bt)->interlaced ? \ + ((bt)->il_vfrontporch + (bt)->il_vsync + (bt)->il_vbackporch) : 0)) #define V4L2_DV_BT_FRAME_HEIGHT(bt) \ ((bt)->height + V4L2_DV_BT_BLANKING_HEIGHT(bt)) diff --git a/init/Kconfig b/init/Kconfig index 4cab92837d52b226e4f95c6629b6b78ebea18b55..11810a255d497f67e099979d0d31290c91fb6d42 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -89,7 +89,7 @@ config CC_HAS_ASM_GOTO_OUTPUT config CC_HAS_ASM_GOTO_TIED_OUTPUT depends on CC_HAS_ASM_GOTO_OUTPUT # Detect buggy gcc and clang, fixed in gcc-11 clang-14. - def_bool $(success,echo 'int foo(int *x) { asm goto (".long (%l[bar]) - .\n": "+m"(*x) ::: bar); return *x; bar: return 0; }' | $CC -x c - -c -o /dev/null) + def_bool $(success,echo 'int foo(int *x) { asm goto (".long (%l[bar]) - .": "+m"(*x) ::: bar); return *x; bar: return 0; }' | $CC -x c - -c -o /dev/null) config TOOLS_SUPPORT_RELR def_bool $(success,env "CC=$(CC)" "LD=$(LD)" "NM=$(NM)" "OBJCOPY=$(OBJCOPY)" $(srctree)/scripts/tools-support-relr.sh) diff --git a/io_uring/Makefile b/io_uring/Makefile new file mode 100644 index 0000000000000000000000000000000000000000..3680425df9478bbe645003aaca8ae8dae2c9ad36 --- /dev/null +++ b/io_uring/Makefile @@ -0,0 +1,6 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Makefile for io_uring + +obj-$(CONFIG_IO_URING) += io_uring.o +obj-$(CONFIG_IO_WQ) += io-wq.o diff --git a/io_uring/io-wq.c b/io_uring/io-wq.c new file mode 100644 index 0000000000000000000000000000000000000000..6031fb319d8780b4c51cbaa45aa17a0c9b6942e2 --- /dev/null +++ b/io_uring/io-wq.c @@ -0,0 +1,1398 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Basic worker thread pool for io_uring + * + * Copyright (C) 2019 Jens Axboe + * + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "io-wq.h" + +#define WORKER_IDLE_TIMEOUT (5 * HZ) + +enum { + IO_WORKER_F_UP = 1, /* up and active */ + IO_WORKER_F_RUNNING = 2, /* account as running */ + IO_WORKER_F_FREE = 4, /* worker on free list */ + IO_WORKER_F_BOUND = 8, /* is doing bounded work */ +}; + +enum { + IO_WQ_BIT_EXIT = 0, /* wq exiting */ +}; + +enum { + IO_ACCT_STALLED_BIT = 0, /* stalled on hash */ +}; + +/* + * One for each thread in a wqe pool + */ +struct io_worker { + refcount_t ref; + unsigned flags; + struct hlist_nulls_node nulls_node; + struct list_head all_list; + struct task_struct *task; + struct io_wqe *wqe; + + struct io_wq_work *cur_work; + spinlock_t lock; + + struct completion ref_done; + + unsigned long create_state; + struct callback_head create_work; + int create_index; + + union { + struct rcu_head rcu; + struct work_struct work; + }; +}; + +#if BITS_PER_LONG == 64 +#define IO_WQ_HASH_ORDER 6 +#else +#define IO_WQ_HASH_ORDER 5 +#endif + +#define IO_WQ_NR_HASH_BUCKETS (1u << IO_WQ_HASH_ORDER) + +struct io_wqe_acct { + unsigned nr_workers; + unsigned max_workers; + int index; + atomic_t nr_running; + struct io_wq_work_list work_list; + unsigned long flags; +}; + +enum { + IO_WQ_ACCT_BOUND, + IO_WQ_ACCT_UNBOUND, + IO_WQ_ACCT_NR, +}; + +/* + * Per-node worker thread pool + */ +struct io_wqe { + raw_spinlock_t lock; + struct io_wqe_acct acct[2]; + + int node; + + struct hlist_nulls_head free_list; + struct list_head all_list; + + struct wait_queue_entry wait; + + struct io_wq *wq; + struct io_wq_work *hash_tail[IO_WQ_NR_HASH_BUCKETS]; + + cpumask_var_t cpu_mask; +}; + +/* + * Per io_wq state + */ +struct io_wq { + unsigned long state; + + free_work_fn *free_work; + io_wq_work_fn *do_work; + + struct io_wq_hash *hash; + + atomic_t worker_refs; + struct completion worker_done; + + struct hlist_node cpuhp_node; + + struct task_struct *task; + + struct io_wqe *wqes[]; +}; + +static enum cpuhp_state io_wq_online; + +struct io_cb_cancel_data { + work_cancel_fn *fn; + void *data; + int nr_running; + int nr_pending; + bool cancel_all; +}; + +static bool create_io_worker(struct io_wq *wq, struct io_wqe *wqe, int index); +static void io_wqe_dec_running(struct io_worker *worker); +static bool io_acct_cancel_pending_work(struct io_wqe *wqe, + struct io_wqe_acct *acct, + struct io_cb_cancel_data *match); +static void create_worker_cb(struct callback_head *cb); +static void io_wq_cancel_tw_create(struct io_wq *wq); + +static bool io_worker_get(struct io_worker *worker) +{ + return refcount_inc_not_zero(&worker->ref); +} + +static void io_worker_release(struct io_worker *worker) +{ + if (refcount_dec_and_test(&worker->ref)) + complete(&worker->ref_done); +} + +static inline struct io_wqe_acct *io_get_acct(struct io_wqe *wqe, bool bound) +{ + return &wqe->acct[bound ? IO_WQ_ACCT_BOUND : IO_WQ_ACCT_UNBOUND]; +} + +static inline struct io_wqe_acct *io_work_get_acct(struct io_wqe *wqe, + struct io_wq_work *work) +{ + return io_get_acct(wqe, !(work->flags & IO_WQ_WORK_UNBOUND)); +} + +static inline struct io_wqe_acct *io_wqe_get_acct(struct io_worker *worker) +{ + return io_get_acct(worker->wqe, worker->flags & IO_WORKER_F_BOUND); +} + +static void io_worker_ref_put(struct io_wq *wq) +{ + if (atomic_dec_and_test(&wq->worker_refs)) + complete(&wq->worker_done); +} + +static void io_worker_cancel_cb(struct io_worker *worker) +{ + struct io_wqe_acct *acct = io_wqe_get_acct(worker); + struct io_wqe *wqe = worker->wqe; + struct io_wq *wq = wqe->wq; + + atomic_dec(&acct->nr_running); + raw_spin_lock(&worker->wqe->lock); + acct->nr_workers--; + raw_spin_unlock(&worker->wqe->lock); + io_worker_ref_put(wq); + clear_bit_unlock(0, &worker->create_state); + io_worker_release(worker); +} + +static bool io_task_worker_match(struct callback_head *cb, void *data) +{ + struct io_worker *worker; + + if (cb->func != create_worker_cb) + return false; + worker = container_of(cb, struct io_worker, create_work); + return worker == data; +} + +static void io_worker_exit(struct io_worker *worker) +{ + struct io_wqe *wqe = worker->wqe; + struct io_wq *wq = wqe->wq; + + while (1) { + struct callback_head *cb = task_work_cancel_match(wq->task, + io_task_worker_match, worker); + + if (!cb) + break; + io_worker_cancel_cb(worker); + } + + if (refcount_dec_and_test(&worker->ref)) + complete(&worker->ref_done); + wait_for_completion(&worker->ref_done); + + raw_spin_lock(&wqe->lock); + if (worker->flags & IO_WORKER_F_FREE) + hlist_nulls_del_rcu(&worker->nulls_node); + list_del_rcu(&worker->all_list); + preempt_disable(); + io_wqe_dec_running(worker); + worker->flags = 0; + current->flags &= ~PF_IO_WORKER; + preempt_enable(); + raw_spin_unlock(&wqe->lock); + + kfree_rcu(worker, rcu); + io_worker_ref_put(wqe->wq); + do_exit(0); +} + +static inline bool io_acct_run_queue(struct io_wqe_acct *acct) +{ + if (!wq_list_empty(&acct->work_list) && + !test_bit(IO_ACCT_STALLED_BIT, &acct->flags)) + return true; + return false; +} + +/* + * Check head of free list for an available worker. If one isn't available, + * caller must create one. + */ +static bool io_wqe_activate_free_worker(struct io_wqe *wqe, + struct io_wqe_acct *acct) + __must_hold(RCU) +{ + struct hlist_nulls_node *n; + struct io_worker *worker; + + /* + * Iterate free_list and see if we can find an idle worker to + * activate. If a given worker is on the free_list but in the process + * of exiting, keep trying. + */ + hlist_nulls_for_each_entry_rcu(worker, n, &wqe->free_list, nulls_node) { + if (!io_worker_get(worker)) + continue; + if (io_wqe_get_acct(worker) != acct) { + io_worker_release(worker); + continue; + } + if (wake_up_process(worker->task)) { + io_worker_release(worker); + return true; + } + io_worker_release(worker); + } + + return false; +} + +/* + * We need a worker. If we find a free one, we're good. If not, and we're + * below the max number of workers, create one. + */ +static bool io_wqe_create_worker(struct io_wqe *wqe, struct io_wqe_acct *acct) +{ + /* + * Most likely an attempt to queue unbounded work on an io_wq that + * wasn't setup with any unbounded workers. + */ + if (unlikely(!acct->max_workers)) + pr_warn_once("io-wq is not configured for unbound workers"); + + raw_spin_lock(&wqe->lock); + if (acct->nr_workers >= acct->max_workers) { + raw_spin_unlock(&wqe->lock); + return true; + } + acct->nr_workers++; + raw_spin_unlock(&wqe->lock); + atomic_inc(&acct->nr_running); + atomic_inc(&wqe->wq->worker_refs); + return create_io_worker(wqe->wq, wqe, acct->index); +} + +static void io_wqe_inc_running(struct io_worker *worker) +{ + struct io_wqe_acct *acct = io_wqe_get_acct(worker); + + atomic_inc(&acct->nr_running); +} + +static void create_worker_cb(struct callback_head *cb) +{ + struct io_worker *worker; + struct io_wq *wq; + struct io_wqe *wqe; + struct io_wqe_acct *acct; + bool do_create = false; + + worker = container_of(cb, struct io_worker, create_work); + wqe = worker->wqe; + wq = wqe->wq; + acct = &wqe->acct[worker->create_index]; + raw_spin_lock(&wqe->lock); + if (acct->nr_workers < acct->max_workers) { + acct->nr_workers++; + do_create = true; + } + raw_spin_unlock(&wqe->lock); + if (do_create) { + create_io_worker(wq, wqe, worker->create_index); + } else { + atomic_dec(&acct->nr_running); + io_worker_ref_put(wq); + } + clear_bit_unlock(0, &worker->create_state); + io_worker_release(worker); +} + +static bool io_queue_worker_create(struct io_worker *worker, + struct io_wqe_acct *acct, + task_work_func_t func) +{ + struct io_wqe *wqe = worker->wqe; + struct io_wq *wq = wqe->wq; + + /* raced with exit, just ignore create call */ + if (test_bit(IO_WQ_BIT_EXIT, &wq->state)) + goto fail; + if (!io_worker_get(worker)) + goto fail; + /* + * create_state manages ownership of create_work/index. We should + * only need one entry per worker, as the worker going to sleep + * will trigger the condition, and waking will clear it once it + * runs the task_work. + */ + if (test_bit(0, &worker->create_state) || + test_and_set_bit_lock(0, &worker->create_state)) + goto fail_release; + + atomic_inc(&wq->worker_refs); + init_task_work(&worker->create_work, func); + worker->create_index = acct->index; + if (!task_work_add(wq->task, &worker->create_work, TWA_SIGNAL)) { + /* + * EXIT may have been set after checking it above, check after + * adding the task_work and remove any creation item if it is + * now set. wq exit does that too, but we can have added this + * work item after we canceled in io_wq_exit_workers(). + */ + if (test_bit(IO_WQ_BIT_EXIT, &wq->state)) + io_wq_cancel_tw_create(wq); + io_worker_ref_put(wq); + return true; + } + io_worker_ref_put(wq); + clear_bit_unlock(0, &worker->create_state); +fail_release: + io_worker_release(worker); +fail: + atomic_dec(&acct->nr_running); + io_worker_ref_put(wq); + return false; +} + +static void io_wqe_dec_running(struct io_worker *worker) + __must_hold(wqe->lock) +{ + struct io_wqe_acct *acct = io_wqe_get_acct(worker); + struct io_wqe *wqe = worker->wqe; + + if (!(worker->flags & IO_WORKER_F_UP)) + return; + + if (atomic_dec_and_test(&acct->nr_running) && io_acct_run_queue(acct)) { + atomic_inc(&acct->nr_running); + atomic_inc(&wqe->wq->worker_refs); + raw_spin_unlock(&wqe->lock); + io_queue_worker_create(worker, acct, create_worker_cb); + raw_spin_lock(&wqe->lock); + } +} + +/* + * Worker will start processing some work. Move it to the busy list, if + * it's currently on the freelist + */ +static void __io_worker_busy(struct io_wqe *wqe, struct io_worker *worker, + struct io_wq_work *work) + __must_hold(wqe->lock) +{ + if (worker->flags & IO_WORKER_F_FREE) { + worker->flags &= ~IO_WORKER_F_FREE; + hlist_nulls_del_init_rcu(&worker->nulls_node); + } +} + +/* + * No work, worker going to sleep. Move to freelist, and unuse mm if we + * have one attached. Dropping the mm may potentially sleep, so we drop + * the lock in that case and return success. Since the caller has to + * retry the loop in that case (we changed task state), we don't regrab + * the lock if we return success. + */ +static void __io_worker_idle(struct io_wqe *wqe, struct io_worker *worker) + __must_hold(wqe->lock) +{ + if (!(worker->flags & IO_WORKER_F_FREE)) { + worker->flags |= IO_WORKER_F_FREE; + hlist_nulls_add_head_rcu(&worker->nulls_node, &wqe->free_list); + } +} + +static inline unsigned int io_get_work_hash(struct io_wq_work *work) +{ + return work->flags >> IO_WQ_HASH_SHIFT; +} + +static bool io_wait_on_hash(struct io_wqe *wqe, unsigned int hash) +{ + struct io_wq *wq = wqe->wq; + bool ret = false; + + spin_lock_irq(&wq->hash->wait.lock); + if (list_empty(&wqe->wait.entry)) { + __add_wait_queue(&wq->hash->wait, &wqe->wait); + if (!test_bit(hash, &wq->hash->map)) { + __set_current_state(TASK_RUNNING); + list_del_init(&wqe->wait.entry); + ret = true; + } + } + spin_unlock_irq(&wq->hash->wait.lock); + return ret; +} + +static struct io_wq_work *io_get_next_work(struct io_wqe_acct *acct, + struct io_worker *worker) + __must_hold(wqe->lock) +{ + struct io_wq_work_node *node, *prev; + struct io_wq_work *work, *tail; + unsigned int stall_hash = -1U; + struct io_wqe *wqe = worker->wqe; + + wq_list_for_each(node, prev, &acct->work_list) { + unsigned int hash; + + work = container_of(node, struct io_wq_work, list); + + /* not hashed, can run anytime */ + if (!io_wq_is_hashed(work)) { + wq_list_del(&acct->work_list, node, prev); + return work; + } + + hash = io_get_work_hash(work); + /* all items with this hash lie in [work, tail] */ + tail = wqe->hash_tail[hash]; + + /* hashed, can run if not already running */ + if (!test_and_set_bit(hash, &wqe->wq->hash->map)) { + wqe->hash_tail[hash] = NULL; + wq_list_cut(&acct->work_list, &tail->list, prev); + return work; + } + if (stall_hash == -1U) + stall_hash = hash; + /* fast forward to a next hash, for-each will fix up @prev */ + node = &tail->list; + } + + if (stall_hash != -1U) { + bool unstalled; + + /* + * Set this before dropping the lock to avoid racing with new + * work being added and clearing the stalled bit. + */ + set_bit(IO_ACCT_STALLED_BIT, &acct->flags); + raw_spin_unlock(&wqe->lock); + unstalled = io_wait_on_hash(wqe, stall_hash); + raw_spin_lock(&wqe->lock); + if (unstalled) { + clear_bit(IO_ACCT_STALLED_BIT, &acct->flags); + if (wq_has_sleeper(&wqe->wq->hash->wait)) + wake_up(&wqe->wq->hash->wait); + } + } + + return NULL; +} + +static bool io_flush_signals(void) +{ + if (unlikely(test_thread_flag(TIF_NOTIFY_SIGNAL))) { + __set_current_state(TASK_RUNNING); + tracehook_notify_signal(); + return true; + } + return false; +} + +static void io_assign_current_work(struct io_worker *worker, + struct io_wq_work *work) +{ + if (work) { + io_flush_signals(); + cond_resched(); + } + + spin_lock(&worker->lock); + worker->cur_work = work; + spin_unlock(&worker->lock); +} + +static void io_wqe_enqueue(struct io_wqe *wqe, struct io_wq_work *work); + +static void io_worker_handle_work(struct io_worker *worker) + __releases(wqe->lock) +{ + struct io_wqe_acct *acct = io_wqe_get_acct(worker); + struct io_wqe *wqe = worker->wqe; + struct io_wq *wq = wqe->wq; + bool do_kill = test_bit(IO_WQ_BIT_EXIT, &wq->state); + + do { + struct io_wq_work *work; +get_next: + /* + * If we got some work, mark us as busy. If we didn't, but + * the list isn't empty, it means we stalled on hashed work. + * Mark us stalled so we don't keep looking for work when we + * can't make progress, any work completion or insertion will + * clear the stalled flag. + */ + work = io_get_next_work(acct, worker); + if (work) + __io_worker_busy(wqe, worker, work); + + raw_spin_unlock(&wqe->lock); + if (!work) + break; + io_assign_current_work(worker, work); + __set_current_state(TASK_RUNNING); + + /* handle a whole dependent link */ + do { + struct io_wq_work *next_hashed, *linked; + unsigned int hash = io_get_work_hash(work); + + next_hashed = wq_next_work(work); + + if (unlikely(do_kill) && (work->flags & IO_WQ_WORK_UNBOUND)) + work->flags |= IO_WQ_WORK_CANCEL; + wq->do_work(work); + io_assign_current_work(worker, NULL); + + linked = wq->free_work(work); + work = next_hashed; + if (!work && linked && !io_wq_is_hashed(linked)) { + work = linked; + linked = NULL; + } + io_assign_current_work(worker, work); + if (linked) + io_wqe_enqueue(wqe, linked); + + if (hash != -1U && !next_hashed) { + /* serialize hash clear with wake_up() */ + spin_lock_irq(&wq->hash->wait.lock); + clear_bit(hash, &wq->hash->map); + clear_bit(IO_ACCT_STALLED_BIT, &acct->flags); + spin_unlock_irq(&wq->hash->wait.lock); + if (wq_has_sleeper(&wq->hash->wait)) + wake_up(&wq->hash->wait); + raw_spin_lock(&wqe->lock); + /* skip unnecessary unlock-lock wqe->lock */ + if (!work) + goto get_next; + raw_spin_unlock(&wqe->lock); + } + } while (work); + + raw_spin_lock(&wqe->lock); + } while (1); +} + +static int io_wqe_worker(void *data) +{ + struct io_worker *worker = data; + struct io_wqe_acct *acct = io_wqe_get_acct(worker); + struct io_wqe *wqe = worker->wqe; + struct io_wq *wq = wqe->wq; + bool last_timeout = false; + char buf[TASK_COMM_LEN]; + + worker->flags |= (IO_WORKER_F_UP | IO_WORKER_F_RUNNING); + + snprintf(buf, sizeof(buf), "iou-wrk-%d", wq->task->pid); + set_task_comm(current, buf); + + while (!test_bit(IO_WQ_BIT_EXIT, &wq->state)) { + long ret; + + set_current_state(TASK_INTERRUPTIBLE); +loop: + raw_spin_lock(&wqe->lock); + if (io_acct_run_queue(acct)) { + io_worker_handle_work(worker); + goto loop; + } + /* timed out, exit unless we're the last worker */ + if (last_timeout && acct->nr_workers > 1) { + acct->nr_workers--; + raw_spin_unlock(&wqe->lock); + __set_current_state(TASK_RUNNING); + break; + } + last_timeout = false; + __io_worker_idle(wqe, worker); + raw_spin_unlock(&wqe->lock); + if (io_flush_signals()) + continue; + ret = schedule_timeout(WORKER_IDLE_TIMEOUT); + if (signal_pending(current)) { + struct ksignal ksig; + + if (!get_signal(&ksig)) + continue; + break; + } + last_timeout = !ret; + } + + if (test_bit(IO_WQ_BIT_EXIT, &wq->state)) { + raw_spin_lock(&wqe->lock); + io_worker_handle_work(worker); + } + + io_worker_exit(worker); + return 0; +} + +/* + * Called when a worker is scheduled in. Mark us as currently running. + */ +void io_wq_worker_running(struct task_struct *tsk) +{ + struct io_worker *worker = tsk->pf_io_worker; + + if (!worker) + return; + if (!(worker->flags & IO_WORKER_F_UP)) + return; + if (worker->flags & IO_WORKER_F_RUNNING) + return; + worker->flags |= IO_WORKER_F_RUNNING; + io_wqe_inc_running(worker); +} + +/* + * Called when worker is going to sleep. If there are no workers currently + * running and we have work pending, wake up a free one or create a new one. + */ +void io_wq_worker_sleeping(struct task_struct *tsk) +{ + struct io_worker *worker = tsk->pf_io_worker; + + if (!worker) + return; + if (!(worker->flags & IO_WORKER_F_UP)) + return; + if (!(worker->flags & IO_WORKER_F_RUNNING)) + return; + + worker->flags &= ~IO_WORKER_F_RUNNING; + + raw_spin_lock(&worker->wqe->lock); + io_wqe_dec_running(worker); + raw_spin_unlock(&worker->wqe->lock); +} + +static void io_init_new_worker(struct io_wqe *wqe, struct io_worker *worker, + struct task_struct *tsk) +{ + tsk->pf_io_worker = worker; + worker->task = tsk; + set_cpus_allowed_ptr(tsk, wqe->cpu_mask); + tsk->flags |= PF_NO_SETAFFINITY; + + raw_spin_lock(&wqe->lock); + hlist_nulls_add_head_rcu(&worker->nulls_node, &wqe->free_list); + list_add_tail_rcu(&worker->all_list, &wqe->all_list); + worker->flags |= IO_WORKER_F_FREE; + raw_spin_unlock(&wqe->lock); + wake_up_new_task(tsk); +} + +static bool io_wq_work_match_all(struct io_wq_work *work, void *data) +{ + return true; +} + +static inline bool io_should_retry_thread(long err) +{ + /* + * Prevent perpetual task_work retry, if the task (or its group) is + * exiting. + */ + if (fatal_signal_pending(current)) + return false; + + switch (err) { + case -EAGAIN: + case -ERESTARTSYS: + case -ERESTARTNOINTR: + case -ERESTARTNOHAND: + return true; + default: + return false; + } +} + +static void create_worker_cont(struct callback_head *cb) +{ + struct io_worker *worker; + struct task_struct *tsk; + struct io_wqe *wqe; + + worker = container_of(cb, struct io_worker, create_work); + clear_bit_unlock(0, &worker->create_state); + wqe = worker->wqe; + tsk = create_io_thread(io_wqe_worker, worker, wqe->node); + if (!IS_ERR(tsk)) { + io_init_new_worker(wqe, worker, tsk); + io_worker_release(worker); + return; + } else if (!io_should_retry_thread(PTR_ERR(tsk))) { + struct io_wqe_acct *acct = io_wqe_get_acct(worker); + + atomic_dec(&acct->nr_running); + raw_spin_lock(&wqe->lock); + acct->nr_workers--; + if (!acct->nr_workers) { + struct io_cb_cancel_data match = { + .fn = io_wq_work_match_all, + .cancel_all = true, + }; + + while (io_acct_cancel_pending_work(wqe, acct, &match)) + raw_spin_lock(&wqe->lock); + } + raw_spin_unlock(&wqe->lock); + io_worker_ref_put(wqe->wq); + kfree(worker); + return; + } + + /* re-create attempts grab a new worker ref, drop the existing one */ + io_worker_release(worker); + schedule_work(&worker->work); +} + +static void io_workqueue_create(struct work_struct *work) +{ + struct io_worker *worker = container_of(work, struct io_worker, work); + struct io_wqe_acct *acct = io_wqe_get_acct(worker); + + if (!io_queue_worker_create(worker, acct, create_worker_cont)) + kfree(worker); +} + +static bool create_io_worker(struct io_wq *wq, struct io_wqe *wqe, int index) +{ + struct io_wqe_acct *acct = &wqe->acct[index]; + struct io_worker *worker; + struct task_struct *tsk; + + __set_current_state(TASK_RUNNING); + + worker = kzalloc_node(sizeof(*worker), GFP_KERNEL, wqe->node); + if (!worker) { +fail: + atomic_dec(&acct->nr_running); + raw_spin_lock(&wqe->lock); + acct->nr_workers--; + raw_spin_unlock(&wqe->lock); + io_worker_ref_put(wq); + return false; + } + + refcount_set(&worker->ref, 1); + worker->wqe = wqe; + spin_lock_init(&worker->lock); + init_completion(&worker->ref_done); + + if (index == IO_WQ_ACCT_BOUND) + worker->flags |= IO_WORKER_F_BOUND; + + tsk = create_io_thread(io_wqe_worker, worker, wqe->node); + if (!IS_ERR(tsk)) { + io_init_new_worker(wqe, worker, tsk); + } else if (!io_should_retry_thread(PTR_ERR(tsk))) { + kfree(worker); + goto fail; + } else { + INIT_WORK(&worker->work, io_workqueue_create); + schedule_work(&worker->work); + } + + return true; +} + +/* + * Iterate the passed in list and call the specific function for each + * worker that isn't exiting + */ +static bool io_wq_for_each_worker(struct io_wqe *wqe, + bool (*func)(struct io_worker *, void *), + void *data) +{ + struct io_worker *worker; + bool ret = false; + + list_for_each_entry_rcu(worker, &wqe->all_list, all_list) { + if (io_worker_get(worker)) { + /* no task if node is/was offline */ + if (worker->task) + ret = func(worker, data); + io_worker_release(worker); + if (ret) + break; + } + } + + return ret; +} + +static bool io_wq_worker_wake(struct io_worker *worker, void *data) +{ + set_notify_signal(worker->task); + wake_up_process(worker->task); + return false; +} + +static void io_run_cancel(struct io_wq_work *work, struct io_wqe *wqe) +{ + struct io_wq *wq = wqe->wq; + + do { + work->flags |= IO_WQ_WORK_CANCEL; + wq->do_work(work); + work = wq->free_work(work); + } while (work); +} + +static void io_wqe_insert_work(struct io_wqe *wqe, struct io_wq_work *work) +{ + struct io_wqe_acct *acct = io_work_get_acct(wqe, work); + unsigned int hash; + struct io_wq_work *tail; + + if (!io_wq_is_hashed(work)) { +append: + wq_list_add_tail(&work->list, &acct->work_list); + return; + } + + hash = io_get_work_hash(work); + tail = wqe->hash_tail[hash]; + wqe->hash_tail[hash] = work; + if (!tail) + goto append; + + wq_list_add_after(&work->list, &tail->list, &acct->work_list); +} + +static bool io_wq_work_match_item(struct io_wq_work *work, void *data) +{ + return work == data; +} + +static void io_wqe_enqueue(struct io_wqe *wqe, struct io_wq_work *work) +{ + struct io_wqe_acct *acct = io_work_get_acct(wqe, work); + unsigned work_flags = work->flags; + bool do_create; + + /* + * If io-wq is exiting for this task, or if the request has explicitly + * been marked as one that should not get executed, cancel it here. + */ + if (test_bit(IO_WQ_BIT_EXIT, &wqe->wq->state) || + (work->flags & IO_WQ_WORK_CANCEL)) { + io_run_cancel(work, wqe); + return; + } + + raw_spin_lock(&wqe->lock); + io_wqe_insert_work(wqe, work); + clear_bit(IO_ACCT_STALLED_BIT, &acct->flags); + + rcu_read_lock(); + do_create = !io_wqe_activate_free_worker(wqe, acct); + rcu_read_unlock(); + + raw_spin_unlock(&wqe->lock); + + if (do_create && ((work_flags & IO_WQ_WORK_CONCURRENT) || + !atomic_read(&acct->nr_running))) { + bool did_create; + + did_create = io_wqe_create_worker(wqe, acct); + if (likely(did_create)) + return; + + raw_spin_lock(&wqe->lock); + /* fatal condition, failed to create the first worker */ + if (!acct->nr_workers) { + struct io_cb_cancel_data match = { + .fn = io_wq_work_match_item, + .data = work, + .cancel_all = false, + }; + + if (io_acct_cancel_pending_work(wqe, acct, &match)) + raw_spin_lock(&wqe->lock); + } + raw_spin_unlock(&wqe->lock); + } +} + +void io_wq_enqueue(struct io_wq *wq, struct io_wq_work *work) +{ + struct io_wqe *wqe = wq->wqes[numa_node_id()]; + + io_wqe_enqueue(wqe, work); +} + +/* + * Work items that hash to the same value will not be done in parallel. + * Used to limit concurrent writes, generally hashed by inode. + */ +void io_wq_hash_work(struct io_wq_work *work, void *val) +{ + unsigned int bit; + + bit = hash_ptr(val, IO_WQ_HASH_ORDER); + work->flags |= (IO_WQ_WORK_HASHED | (bit << IO_WQ_HASH_SHIFT)); +} + +static bool io_wq_worker_cancel(struct io_worker *worker, void *data) +{ + struct io_cb_cancel_data *match = data; + + /* + * Hold the lock to avoid ->cur_work going out of scope, caller + * may dereference the passed in work. + */ + spin_lock(&worker->lock); + if (worker->cur_work && + match->fn(worker->cur_work, match->data)) { + set_notify_signal(worker->task); + match->nr_running++; + } + spin_unlock(&worker->lock); + + return match->nr_running && !match->cancel_all; +} + +static inline void io_wqe_remove_pending(struct io_wqe *wqe, + struct io_wq_work *work, + struct io_wq_work_node *prev) +{ + struct io_wqe_acct *acct = io_work_get_acct(wqe, work); + unsigned int hash = io_get_work_hash(work); + struct io_wq_work *prev_work = NULL; + + if (io_wq_is_hashed(work) && work == wqe->hash_tail[hash]) { + if (prev) + prev_work = container_of(prev, struct io_wq_work, list); + if (prev_work && io_get_work_hash(prev_work) == hash) + wqe->hash_tail[hash] = prev_work; + else + wqe->hash_tail[hash] = NULL; + } + wq_list_del(&acct->work_list, &work->list, prev); +} + +static bool io_acct_cancel_pending_work(struct io_wqe *wqe, + struct io_wqe_acct *acct, + struct io_cb_cancel_data *match) + __releases(wqe->lock) +{ + struct io_wq_work_node *node, *prev; + struct io_wq_work *work; + + wq_list_for_each(node, prev, &acct->work_list) { + work = container_of(node, struct io_wq_work, list); + if (!match->fn(work, match->data)) + continue; + io_wqe_remove_pending(wqe, work, prev); + raw_spin_unlock(&wqe->lock); + io_run_cancel(work, wqe); + match->nr_pending++; + /* not safe to continue after unlock */ + return true; + } + + return false; +} + +static void io_wqe_cancel_pending_work(struct io_wqe *wqe, + struct io_cb_cancel_data *match) +{ + int i; +retry: + raw_spin_lock(&wqe->lock); + for (i = 0; i < IO_WQ_ACCT_NR; i++) { + struct io_wqe_acct *acct = io_get_acct(wqe, i == 0); + + if (io_acct_cancel_pending_work(wqe, acct, match)) { + if (match->cancel_all) + goto retry; + return; + } + } + raw_spin_unlock(&wqe->lock); +} + +static void io_wqe_cancel_running_work(struct io_wqe *wqe, + struct io_cb_cancel_data *match) +{ + rcu_read_lock(); + io_wq_for_each_worker(wqe, io_wq_worker_cancel, match); + rcu_read_unlock(); +} + +enum io_wq_cancel io_wq_cancel_cb(struct io_wq *wq, work_cancel_fn *cancel, + void *data, bool cancel_all) +{ + struct io_cb_cancel_data match = { + .fn = cancel, + .data = data, + .cancel_all = cancel_all, + }; + int node; + + /* + * First check pending list, if we're lucky we can just remove it + * from there. CANCEL_OK means that the work is returned as-new, + * no completion will be posted for it. + */ + for_each_node(node) { + struct io_wqe *wqe = wq->wqes[node]; + + io_wqe_cancel_pending_work(wqe, &match); + if (match.nr_pending && !match.cancel_all) + return IO_WQ_CANCEL_OK; + } + + /* + * Now check if a free (going busy) or busy worker has the work + * currently running. If we find it there, we'll return CANCEL_RUNNING + * as an indication that we attempt to signal cancellation. The + * completion will run normally in this case. + */ + for_each_node(node) { + struct io_wqe *wqe = wq->wqes[node]; + + io_wqe_cancel_running_work(wqe, &match); + if (match.nr_running && !match.cancel_all) + return IO_WQ_CANCEL_RUNNING; + } + + if (match.nr_running) + return IO_WQ_CANCEL_RUNNING; + if (match.nr_pending) + return IO_WQ_CANCEL_OK; + return IO_WQ_CANCEL_NOTFOUND; +} + +static int io_wqe_hash_wake(struct wait_queue_entry *wait, unsigned mode, + int sync, void *key) +{ + struct io_wqe *wqe = container_of(wait, struct io_wqe, wait); + int i; + + list_del_init(&wait->entry); + + rcu_read_lock(); + for (i = 0; i < IO_WQ_ACCT_NR; i++) { + struct io_wqe_acct *acct = &wqe->acct[i]; + + if (test_and_clear_bit(IO_ACCT_STALLED_BIT, &acct->flags)) + io_wqe_activate_free_worker(wqe, acct); + } + rcu_read_unlock(); + return 1; +} + +struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data) +{ + int ret, node, i; + struct io_wq *wq; + + if (WARN_ON_ONCE(!data->free_work || !data->do_work)) + return ERR_PTR(-EINVAL); + if (WARN_ON_ONCE(!bounded)) + return ERR_PTR(-EINVAL); + + wq = kzalloc(struct_size(wq, wqes, nr_node_ids), GFP_KERNEL); + if (!wq) + return ERR_PTR(-ENOMEM); + ret = cpuhp_state_add_instance_nocalls(io_wq_online, &wq->cpuhp_node); + if (ret) + goto err_wq; + + refcount_inc(&data->hash->refs); + wq->hash = data->hash; + wq->free_work = data->free_work; + wq->do_work = data->do_work; + + ret = -ENOMEM; + for_each_node(node) { + struct io_wqe *wqe; + int alloc_node = node; + + if (!node_online(alloc_node)) + alloc_node = NUMA_NO_NODE; + wqe = kzalloc_node(sizeof(struct io_wqe), GFP_KERNEL, alloc_node); + if (!wqe) + goto err; + wq->wqes[node] = wqe; + if (!alloc_cpumask_var(&wqe->cpu_mask, GFP_KERNEL)) + goto err; + cpumask_copy(wqe->cpu_mask, cpumask_of_node(node)); + wqe->node = alloc_node; + wqe->acct[IO_WQ_ACCT_BOUND].max_workers = bounded; + wqe->acct[IO_WQ_ACCT_UNBOUND].max_workers = + task_rlimit(current, RLIMIT_NPROC); + INIT_LIST_HEAD(&wqe->wait.entry); + wqe->wait.func = io_wqe_hash_wake; + for (i = 0; i < IO_WQ_ACCT_NR; i++) { + struct io_wqe_acct *acct = &wqe->acct[i]; + + acct->index = i; + atomic_set(&acct->nr_running, 0); + INIT_WQ_LIST(&acct->work_list); + } + wqe->wq = wq; + raw_spin_lock_init(&wqe->lock); + INIT_HLIST_NULLS_HEAD(&wqe->free_list, 0); + INIT_LIST_HEAD(&wqe->all_list); + } + + wq->task = get_task_struct(data->task); + atomic_set(&wq->worker_refs, 1); + init_completion(&wq->worker_done); + return wq; +err: + io_wq_put_hash(data->hash); + cpuhp_state_remove_instance_nocalls(io_wq_online, &wq->cpuhp_node); + for_each_node(node) { + if (!wq->wqes[node]) + continue; + free_cpumask_var(wq->wqes[node]->cpu_mask); + kfree(wq->wqes[node]); + } +err_wq: + kfree(wq); + return ERR_PTR(ret); +} + +static bool io_task_work_match(struct callback_head *cb, void *data) +{ + struct io_worker *worker; + + if (cb->func != create_worker_cb && cb->func != create_worker_cont) + return false; + worker = container_of(cb, struct io_worker, create_work); + return worker->wqe->wq == data; +} + +void io_wq_exit_start(struct io_wq *wq) +{ + set_bit(IO_WQ_BIT_EXIT, &wq->state); +} + +static void io_wq_cancel_tw_create(struct io_wq *wq) +{ + struct callback_head *cb; + + while ((cb = task_work_cancel_match(wq->task, io_task_work_match, wq)) != NULL) { + struct io_worker *worker; + + worker = container_of(cb, struct io_worker, create_work); + io_worker_cancel_cb(worker); + } +} + +static void io_wq_exit_workers(struct io_wq *wq) +{ + int node; + + if (!wq->task) + return; + + io_wq_cancel_tw_create(wq); + + rcu_read_lock(); + for_each_node(node) { + struct io_wqe *wqe = wq->wqes[node]; + + io_wq_for_each_worker(wqe, io_wq_worker_wake, NULL); + } + rcu_read_unlock(); + io_worker_ref_put(wq); + wait_for_completion(&wq->worker_done); + + for_each_node(node) { + spin_lock_irq(&wq->hash->wait.lock); + list_del_init(&wq->wqes[node]->wait.entry); + spin_unlock_irq(&wq->hash->wait.lock); + } + put_task_struct(wq->task); + wq->task = NULL; +} + +static void io_wq_destroy(struct io_wq *wq) +{ + int node; + + cpuhp_state_remove_instance_nocalls(io_wq_online, &wq->cpuhp_node); + + for_each_node(node) { + struct io_wqe *wqe = wq->wqes[node]; + struct io_cb_cancel_data match = { + .fn = io_wq_work_match_all, + .cancel_all = true, + }; + io_wqe_cancel_pending_work(wqe, &match); + free_cpumask_var(wqe->cpu_mask); + kfree(wqe); + } + io_wq_put_hash(wq->hash); + kfree(wq); +} + +void io_wq_put_and_exit(struct io_wq *wq) +{ + WARN_ON_ONCE(!test_bit(IO_WQ_BIT_EXIT, &wq->state)); + + io_wq_exit_workers(wq); + io_wq_destroy(wq); +} + +struct online_data { + unsigned int cpu; + bool online; +}; + +static bool io_wq_worker_affinity(struct io_worker *worker, void *data) +{ + struct online_data *od = data; + + if (od->online) + cpumask_set_cpu(od->cpu, worker->wqe->cpu_mask); + else + cpumask_clear_cpu(od->cpu, worker->wqe->cpu_mask); + return false; +} + +static int __io_wq_cpu_online(struct io_wq *wq, unsigned int cpu, bool online) +{ + struct online_data od = { + .cpu = cpu, + .online = online + }; + int i; + + rcu_read_lock(); + for_each_node(i) + io_wq_for_each_worker(wq->wqes[i], io_wq_worker_affinity, &od); + rcu_read_unlock(); + return 0; +} + +static int io_wq_cpu_online(unsigned int cpu, struct hlist_node *node) +{ + struct io_wq *wq = hlist_entry_safe(node, struct io_wq, cpuhp_node); + + return __io_wq_cpu_online(wq, cpu, true); +} + +static int io_wq_cpu_offline(unsigned int cpu, struct hlist_node *node) +{ + struct io_wq *wq = hlist_entry_safe(node, struct io_wq, cpuhp_node); + + return __io_wq_cpu_online(wq, cpu, false); +} + +int io_wq_cpu_affinity(struct io_wq *wq, cpumask_var_t mask) +{ + int i; + + rcu_read_lock(); + for_each_node(i) { + struct io_wqe *wqe = wq->wqes[i]; + + if (mask) + cpumask_copy(wqe->cpu_mask, mask); + else + cpumask_copy(wqe->cpu_mask, cpumask_of_node(i)); + } + rcu_read_unlock(); + return 0; +} + +/* + * Set max number of unbounded workers, returns old value. If new_count is 0, + * then just return the old value. + */ +int io_wq_max_workers(struct io_wq *wq, int *new_count) +{ + int prev[IO_WQ_ACCT_NR]; + bool first_node = true; + int i, node; + + BUILD_BUG_ON((int) IO_WQ_ACCT_BOUND != (int) IO_WQ_BOUND); + BUILD_BUG_ON((int) IO_WQ_ACCT_UNBOUND != (int) IO_WQ_UNBOUND); + BUILD_BUG_ON((int) IO_WQ_ACCT_NR != 2); + + for (i = 0; i < 2; i++) { + if (new_count[i] > task_rlimit(current, RLIMIT_NPROC)) + new_count[i] = task_rlimit(current, RLIMIT_NPROC); + } + + for (i = 0; i < IO_WQ_ACCT_NR; i++) + prev[i] = 0; + + rcu_read_lock(); + for_each_node(node) { + struct io_wqe *wqe = wq->wqes[node]; + struct io_wqe_acct *acct; + + raw_spin_lock(&wqe->lock); + for (i = 0; i < IO_WQ_ACCT_NR; i++) { + acct = &wqe->acct[i]; + if (first_node) + prev[i] = max_t(int, acct->max_workers, prev[i]); + if (new_count[i]) + acct->max_workers = new_count[i]; + } + raw_spin_unlock(&wqe->lock); + first_node = false; + } + rcu_read_unlock(); + + for (i = 0; i < IO_WQ_ACCT_NR; i++) + new_count[i] = prev[i]; + + return 0; +} + +static __init int io_wq_init(void) +{ + int ret; + + ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN, "io-wq/online", + io_wq_cpu_online, io_wq_cpu_offline); + if (ret < 0) + return ret; + io_wq_online = ret; + return 0; +} +subsys_initcall(io_wq_init); diff --git a/fs/io-wq.h b/io_uring/io-wq.h similarity index 76% rename from fs/io-wq.h rename to io_uring/io-wq.h index 75113bcd5889f41d9fe891aaa033db1d6154e0f1..300a695d191dfaf45a19fb4ff360515ddd12d994 100644 --- a/fs/io-wq.h +++ b/io_uring/io-wq.h @@ -1,7 +1,18 @@ #ifndef INTERNAL_IO_WQ_H #define INTERNAL_IO_WQ_H +#ifdef __GENKSYMS__ +/* + * ANDROID ABI HACK + * + * See the big comment in the linux/io_uring.h file for details. This + * include is not needed for any real functionality, but must be here to + * preserve the CRC of a number of variables and functions. + */ #include +#endif + +#include struct io_wq; @@ -9,16 +20,8 @@ enum { IO_WQ_WORK_CANCEL = 1, IO_WQ_WORK_HASHED = 2, IO_WQ_WORK_UNBOUND = 4, - IO_WQ_WORK_NO_CANCEL = 8, IO_WQ_WORK_CONCURRENT = 16, - IO_WQ_WORK_FILES = 32, - IO_WQ_WORK_FS = 64, - IO_WQ_WORK_MM = 128, - IO_WQ_WORK_CREDS = 256, - IO_WQ_WORK_BLKCG = 512, - IO_WQ_WORK_FSIZE = 1024, - IO_WQ_HASH_SHIFT = 24, /* upper 8 bits are used for hash key */ }; @@ -52,6 +55,7 @@ static inline void wq_list_add_after(struct io_wq_work_node *node, static inline void wq_list_add_tail(struct io_wq_work_node *node, struct io_wq_work_list *list) { + node->next = NULL; if (!list->first) { list->last = node; WRITE_ONCE(list->first, node); @@ -59,7 +63,6 @@ static inline void wq_list_add_tail(struct io_wq_work_node *node, list->last->next = node; list->last = node; } - node->next = NULL; } static inline void wq_list_cut(struct io_wq_work_list *list, @@ -95,7 +98,6 @@ static inline void wq_list_del(struct io_wq_work_list *list, struct io_wq_work { struct io_wq_work_node list; - struct io_identity *identity; unsigned flags; }; @@ -107,37 +109,48 @@ static inline struct io_wq_work *wq_next_work(struct io_wq_work *work) return container_of(work->list.next, struct io_wq_work, list); } -typedef void (free_work_fn)(struct io_wq_work *); -typedef struct io_wq_work *(io_wq_work_fn)(struct io_wq_work *); +typedef struct io_wq_work *(free_work_fn)(struct io_wq_work *); +typedef void (io_wq_work_fn)(struct io_wq_work *); -struct io_wq_data { - struct user_struct *user; +struct io_wq_hash { + refcount_t refs; + unsigned long map; + struct wait_queue_head wait; +}; +static inline void io_wq_put_hash(struct io_wq_hash *hash) +{ + if (refcount_dec_and_test(&hash->refs)) + kfree(hash); +} + +struct io_wq_data { + struct io_wq_hash *hash; + struct task_struct *task; io_wq_work_fn *do_work; free_work_fn *free_work; }; struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data); -bool io_wq_get(struct io_wq *wq, struct io_wq_data *data); -void io_wq_destroy(struct io_wq *wq); +void io_wq_exit_start(struct io_wq *wq); +void io_wq_put_and_exit(struct io_wq *wq); void io_wq_enqueue(struct io_wq *wq, struct io_wq_work *work); void io_wq_hash_work(struct io_wq_work *work, void *val); +int io_wq_cpu_affinity(struct io_wq *wq, cpumask_var_t mask); +int io_wq_max_workers(struct io_wq *wq, int *new_count); + static inline bool io_wq_is_hashed(struct io_wq_work *work) { return work->flags & IO_WQ_WORK_HASHED; } -void io_wq_cancel_all(struct io_wq *wq); - typedef bool (work_cancel_fn)(struct io_wq_work *, void *); enum io_wq_cancel io_wq_cancel_cb(struct io_wq *wq, work_cancel_fn *cancel, void *data, bool cancel_all); -struct task_struct *io_wq_get_task(struct io_wq *wq); - #if defined(CONFIG_IO_WQ) extern void io_wq_worker_sleeping(struct task_struct *); extern void io_wq_worker_running(struct task_struct *); @@ -152,6 +165,7 @@ static inline void io_wq_worker_running(struct task_struct *tsk) static inline bool io_wq_current_is_worker(void) { - return in_task() && (current->flags & PF_IO_WORKER); + return in_task() && (current->flags & PF_IO_WORKER) && + current->pf_io_worker; } #endif diff --git a/fs/io_uring.c b/io_uring/io_uring.c similarity index 51% rename from fs/io_uring.c rename to io_uring/io_uring.c index 7baab885c6f25080fe1d8d00d702ecb9bad92a86..35a9bcd5648bc7ff261dc3733f87d756783ed116 100644 --- a/fs/io_uring.c +++ b/io_uring/io_uring.c @@ -11,7 +11,7 @@ * before writing the tail (using smp_load_acquire to read the tail will * do). It also needs a smp_mb() before updating CQ head (ordering the * entry load(s) with the head store), pairing with an implicit barrier - * through a control-dependency in io_get_cqring (smp_store_release to + * through a control-dependency in io_get_cqe (smp_store_release to * store head will do). Failure to do so could lead to reading invalid * CQ entries. * @@ -57,7 +57,6 @@ #include #include #include -#include #include #include #include @@ -75,35 +74,43 @@ #include #include #include -#include #include #include #include #include -#include -#include +#include #define CREATE_TRACE_POINTS #include #include -#include "internal.h" +#include "../fs/internal.h" #include "io-wq.h" #define IORING_MAX_ENTRIES 32768 #define IORING_MAX_CQ_ENTRIES (2 * IORING_MAX_ENTRIES) +#define IORING_SQPOLL_CAP_ENTRIES_VALUE 8 -/* - * Shift of 9 is 512 entries, or exactly one page on 64-bit archs - */ -#define IORING_FILE_TABLE_SHIFT 9 -#define IORING_MAX_FILES_TABLE (1U << IORING_FILE_TABLE_SHIFT) -#define IORING_FILE_TABLE_MASK (IORING_MAX_FILES_TABLE - 1) -#define IORING_MAX_FIXED_FILES (64 * IORING_MAX_FILES_TABLE) +/* only define max */ +#define IORING_MAX_FIXED_FILES (1U << 15) #define IORING_MAX_RESTRICTIONS (IORING_RESTRICTION_LAST + \ IORING_REGISTER_LAST + IORING_OP_LAST) +#define IO_RSRC_TAG_TABLE_SHIFT (PAGE_SHIFT - 3) +#define IO_RSRC_TAG_TABLE_MAX (1U << IO_RSRC_TAG_TABLE_SHIFT) +#define IO_RSRC_TAG_TABLE_MASK (IO_RSRC_TAG_TABLE_MAX - 1) + +#define IORING_MAX_REG_BUFFERS (1U << 14) + +#define SQE_VALID_FLAGS (IOSQE_FIXED_FILE|IOSQE_IO_DRAIN|IOSQE_IO_LINK| \ + IOSQE_IO_HARDLINK | IOSQE_ASYNC | \ + IOSQE_BUFFER_SELECT) +#define IO_REQ_CLEAN_FLAGS (REQ_F_BUFFER_SELECTED | REQ_F_NEED_CLEANUP | \ + REQ_F_POLLED | REQ_F_INFLIGHT | REQ_F_CREDS) + +#define IO_TCTX_REFS_CACHE_NR (1U << 10) + struct io_uring { u32 head ____cacheline_aligned_in_smp; u32 tail ____cacheline_aligned_in_smp; @@ -162,7 +169,7 @@ struct io_rings { * Written by the application, shouldn't be modified by the * kernel. */ - u32 cq_flags; + u32 cq_flags; /* * Number of completion events lost because the queue was full; * this should be avoided by the application by making sure @@ -187,36 +194,65 @@ struct io_rings { struct io_uring_cqe cqes[] ____cacheline_aligned_in_smp; }; +enum io_uring_cmd_flags { + IO_URING_F_NONBLOCK = 1, + IO_URING_F_COMPLETE_DEFER = 2, +}; + struct io_mapped_ubuf { u64 ubuf; - size_t len; - struct bio_vec *bvec; + u64 ubuf_end; unsigned int nr_bvecs; unsigned long acct_pages; + struct bio_vec bvec[]; +}; + +struct io_ring_ctx; + +struct io_overflow_cqe { + struct io_uring_cqe cqe; + struct list_head list; +}; + +struct io_fixed_file { + /* file * with additional FFS_* flags */ + unsigned long file_ptr; +}; + +struct io_rsrc_put { + struct list_head list; + u64 tag; + union { + void *rsrc; + struct file *file; + struct io_mapped_ubuf *buf; + }; }; -struct fixed_file_table { - struct file **files; +struct io_file_table { + struct io_fixed_file *files; }; -struct fixed_file_ref_node { +struct io_rsrc_node { struct percpu_ref refs; struct list_head node; - struct list_head file_list; - struct fixed_file_data *file_data; + struct list_head rsrc_list; + struct io_rsrc_data *rsrc_data; struct llist_node llist; bool done; }; -struct fixed_file_data { - struct fixed_file_table *table; +typedef void (rsrc_put_fn)(struct io_ring_ctx *ctx, struct io_rsrc_put *prsrc); + +struct io_rsrc_data { struct io_ring_ctx *ctx; - struct fixed_file_ref_node *node; - struct percpu_ref refs; + u64 **tags; + unsigned int nr; + rsrc_put_fn *do_put; + atomic_t refs; struct completion done; - struct list_head ref_list; - spinlock_t lock; + bool quiesce; }; struct io_buffer { @@ -234,33 +270,81 @@ struct io_restriction { bool registered; }; +enum { + IO_SQ_THREAD_SHOULD_STOP = 0, + IO_SQ_THREAD_SHOULD_PARK, +}; + struct io_sq_data { refcount_t refs; + atomic_t park_pending; struct mutex lock; /* ctx's that are using this sqd */ struct list_head ctx_list; - struct list_head ctx_new_list; - struct mutex ctx_lock; struct task_struct *thread; struct wait_queue_head wait; + + unsigned sq_thread_idle; + int sq_cpu; + pid_t task_pid; + pid_t task_tgid; + + unsigned long state; + struct completion exited; +}; + +#define IO_COMPL_BATCH 32 +#define IO_REQ_CACHE_SIZE 32 +#define IO_REQ_ALLOC_BATCH 8 + +struct io_submit_link { + struct io_kiocb *head; + struct io_kiocb *last; +}; + +struct io_submit_state { + struct blk_plug plug; + struct io_submit_link link; + + /* + * io_kiocb alloc cache + */ + void *reqs[IO_REQ_CACHE_SIZE]; + unsigned int free_reqs; + + bool plug_started; + + /* + * Batch completion logic + */ + struct io_kiocb *compl_reqs[IO_COMPL_BATCH]; + unsigned int compl_nr; + /* inline/task_work completion list, under ->uring_lock */ + struct list_head free_list; + + unsigned int ios_left; }; struct io_ring_ctx { + /* const or read-mostly hot data */ struct { struct percpu_ref refs; - } ____cacheline_aligned_in_smp; - struct { + struct io_rings *rings; unsigned int flags; unsigned int compat: 1; - unsigned int limit_mem: 1; - unsigned int cq_overflow_flushed: 1; unsigned int drain_next: 1; unsigned int eventfd_async: 1; unsigned int restricted: 1; - unsigned int sqo_dead: 1; + unsigned int off_timeout_used: 1; + unsigned int drain_active: 1; + } ____cacheline_aligned_in_smp; + + /* submission data */ + struct { + struct mutex uring_lock; /* * Ring buffer of indices into array of io_uring_sqe, which is @@ -274,101 +358,59 @@ struct io_ring_ctx { * array. */ u32 *sq_array; + struct io_uring_sqe *sq_sqes; unsigned cached_sq_head; unsigned sq_entries; - unsigned sq_mask; - unsigned sq_thread_idle; - unsigned cached_sq_dropped; - unsigned cached_cq_overflow; - unsigned long sq_check_overflow; - struct list_head defer_list; + + /* + * Fixed resources fast path, should be accessed only under + * uring_lock, and updated through io_uring_register(2) + */ + struct io_rsrc_node *rsrc_node; + struct io_file_table file_table; + unsigned nr_user_files; + unsigned nr_user_bufs; + struct io_mapped_ubuf **user_bufs; + + struct io_submit_state submit_state; struct list_head timeout_list; + struct list_head ltimeout_list; struct list_head cq_overflow_list; - - struct io_uring_sqe *sq_sqes; + struct xarray io_buffers; + struct xarray personalities; + u32 pers_next; + unsigned sq_thread_idle; } ____cacheline_aligned_in_smp; - struct io_rings *rings; - - /* IO offload */ - struct io_wq *io_wq; - - /* - * For SQPOLL usage - we hold a reference to the parent task, so we - * have access to the ->files - */ - struct task_struct *sqo_task; - - /* Only used for accounting purposes */ - struct mm_struct *mm_account; - -#ifdef CONFIG_BLK_CGROUP - struct cgroup_subsys_state *sqo_blkcg_css; -#endif + /* IRQ completion list, under ->completion_lock */ + struct list_head locked_free_list; + unsigned int locked_free_nr; + const struct cred *sq_creds; /* cred used for __io_sq_thread() */ struct io_sq_data *sq_data; /* if using sq thread polling */ struct wait_queue_head sqo_sq_wait; - struct wait_queue_entry sqo_wait_entry; struct list_head sqd_list; - /* - * If used, fixed file set. Writers must ensure that ->refs is dead, - * readers must ensure that ->refs is alive as long as the file* is - * used. Only updated through io_uring_register(2). - */ - struct fixed_file_data *file_data; - unsigned nr_user_files; - - /* if used, fixed mapped user buffers */ - unsigned nr_user_bufs; - struct io_mapped_ubuf *user_bufs; - - struct user_struct *user; - - const struct cred *creds; - -#ifdef CONFIG_AUDIT - kuid_t loginuid; - unsigned int sessionid; -#endif - - struct completion ref_comp; - struct completion sq_thread_comp; - - /* if all else fails... */ - struct io_kiocb *fallback_req; - -#if defined(CONFIG_UNIX) - struct socket *ring_sock; -#endif - - struct xarray io_buffers; - - struct xarray personalities; - u32 pers_next; + unsigned long check_cq_overflow; struct { unsigned cached_cq_tail; unsigned cq_entries; - unsigned cq_mask; + struct eventfd_ctx *cq_ev_fd; + struct wait_queue_head poll_wait; + struct wait_queue_head cq_wait; + unsigned cq_extra; atomic_t cq_timeouts; unsigned cq_last_tm_flush; - unsigned long cq_check_overflow; - struct wait_queue_head cq_wait; - struct fasync_struct *cq_fasync; - struct eventfd_ctx *cq_ev_fd; - } ____cacheline_aligned_in_smp; - - struct { - struct mutex uring_lock; - wait_queue_head_t wait; } ____cacheline_aligned_in_smp; struct { spinlock_t completion_lock; + spinlock_t timeout_lock; + /* * ->iopoll_list is protected by the ctx->uring_lock for * io_uring instances that don't use IORING_SETUP_SQPOLL. @@ -378,39 +420,98 @@ struct io_ring_ctx { struct list_head iopoll_list; struct hlist_head *cancel_hash; unsigned cancel_hash_bits; - bool poll_multi_file; - - spinlock_t inflight_lock; - struct list_head inflight_list; + bool poll_multi_queue; } ____cacheline_aligned_in_smp; - struct delayed_work file_put_work; - struct llist_head file_put_llist; - - struct work_struct exit_work; struct io_restriction restrictions; + + /* slow path rsrc auxilary data, used by update/register */ + struct { + struct io_rsrc_node *rsrc_backup_node; + struct io_mapped_ubuf *dummy_ubuf; + struct io_rsrc_data *file_data; + struct io_rsrc_data *buf_data; + + struct delayed_work rsrc_put_work; + struct llist_head rsrc_put_llist; + struct list_head rsrc_ref_list; + spinlock_t rsrc_ref_lock; + }; + + /* Keep this last, we don't need it for the fast path */ + struct { + #if defined(CONFIG_UNIX) + struct socket *ring_sock; + #endif + /* hashed buffered write serialization */ + struct io_wq_hash *hash_map; + + /* Only used for accounting purposes */ + struct user_struct *user; + struct mm_struct *mm_account; + + /* ctx exit and cancelation */ + struct llist_head fallback_llist; + struct delayed_work fallback_work; + struct work_struct exit_work; + struct list_head tctx_list; + struct completion ref_comp; + u32 iowq_limits[2]; + bool iowq_limits_set; + }; }; +#ifndef __GENKSYMS__ +/* + * ANDROID ABI HACK + * + * See the big comment in the linux/io_uring.h file for details. This + * structure definition should NOT be used if __GENKSYMS__ is enabled, + * as a "fake" structure definition has already been read in the + * linux/io_uring.h file in order to preserve the Android kernel ABI. + */ +struct io_uring_task { + /* submission side */ + int cached_refs; + struct xarray xa; + struct wait_queue_head wait; + const struct io_ring_ctx *last; + struct io_wq *io_wq; + struct percpu_counter inflight; + atomic_t inflight_tracked; + atomic_t in_idle; + + spinlock_t task_lock; + struct io_wq_work_list task_list; + struct callback_head task_work; + bool task_running; +}; +#endif + /* * First field must be the file pointer in all the * iocb unions! See also 'struct kiocb' in */ struct io_poll_iocb { struct file *file; - union { - struct wait_queue_head *head; - u64 addr; - }; + struct wait_queue_head *head; __poll_t events; - bool done; - bool canceled; struct wait_queue_entry wait; }; +struct io_poll_update { + struct file *file; + u64 old_user_data; + u64 new_user_data; + __poll_t events; + bool update_events; + bool update_user_data; +}; + struct io_close { struct file *file; - struct file *put_file; int fd; + u32 file_slot; }; struct io_timeout_data { @@ -418,6 +519,7 @@ struct io_timeout_data { struct hrtimer timer; struct timespec64 ts; enum hrtimer_mode mode; + u32 flags; }; struct io_accept { @@ -425,6 +527,7 @@ struct io_accept { struct sockaddr __user *addr; int __user *addr_len; int flags; + u32 file_slot; unsigned long nofile; }; @@ -446,11 +549,20 @@ struct io_timeout { u32 off; u32 target_seq; struct list_head list; + /* head of the link, used by linked timeouts only */ + struct io_kiocb *head; + /* for linked completions */ + struct io_kiocb *prev; }; struct io_timeout_rem { struct file *file; u64 addr; + + /* timeout update */ + struct timespec64 ts; + u32 flags; + bool ltimeout; }; struct io_rw { @@ -469,8 +581,9 @@ struct io_connect { struct io_sr_msg { struct file *file; union { - struct user_msghdr __user *umsg; - void __user *buf; + struct compat_msghdr __user *umsg_compat; + struct user_msghdr __user *umsg; + void __user *buf; }; int msg_flags; int bgid; @@ -481,13 +594,13 @@ struct io_sr_msg { struct io_open { struct file *file; int dfd; - bool ignore_nonblock; + u32 file_slot; struct filename *filename; struct open_how how; unsigned long nofile; }; -struct io_files_update { +struct io_rsrc_update { struct file *file; u64 arg; u32 nr_args; @@ -518,10 +631,10 @@ struct io_epoll { struct io_splice { struct file *file_out; - struct file *file_in; loff_t off_out; loff_t off_in; u64 len; + int splice_fd_in; unsigned int flags; }; @@ -543,9 +656,52 @@ struct io_statx { struct statx __user *buffer; }; +struct io_shutdown { + struct file *file; + int how; +}; + +struct io_rename { + struct file *file; + int old_dfd; + int new_dfd; + struct filename *oldpath; + struct filename *newpath; + int flags; +}; + +struct io_unlink { + struct file *file; + int dfd; + int flags; + struct filename *filename; +}; + +struct io_mkdir { + struct file *file; + int dfd; + umode_t mode; + struct filename *filename; +}; + +struct io_symlink { + struct file *file; + int new_dfd; + struct filename *oldpath; + struct filename *newpath; +}; + +struct io_hardlink { + struct file *file; + int old_dfd; + int new_dfd; + struct filename *oldpath; + struct filename *newpath; + int flags; +}; + struct io_completion { struct file *file; - struct list_head list; u32 cflags; }; @@ -555,7 +711,8 @@ struct io_async_connect { struct io_async_msghdr { struct iovec fast_iov[UIO_FASTIOV]; - struct iovec *iov; + /* points to an allocated iov, if NULL we use fast_iov instead */ + struct iovec *free_iov; struct sockaddr __user *uaddr; struct msghdr msg; struct sockaddr_storage addr; @@ -565,6 +722,7 @@ struct io_async_rw { struct iovec fast_iov[UIO_FASTIOV]; const struct iovec *free_iovec; struct iov_iter iter; + struct iov_iter_state iter_state; size_t bytes_done; struct wait_page_queue wpq; }; @@ -577,19 +735,24 @@ enum { REQ_F_FORCE_ASYNC_BIT = IOSQE_ASYNC_BIT, REQ_F_BUFFER_SELECT_BIT = IOSQE_BUFFER_SELECT_BIT, - REQ_F_LINK_HEAD_BIT, - REQ_F_FAIL_LINK_BIT, + /* first byte is taken by user flags, shift it to not overlap */ + REQ_F_FAIL_BIT = 8, REQ_F_INFLIGHT_BIT, REQ_F_CUR_POS_BIT, REQ_F_NOWAIT_BIT, REQ_F_LINK_TIMEOUT_BIT, - REQ_F_ISREG_BIT, REQ_F_NEED_CLEANUP_BIT, REQ_F_POLLED_BIT, REQ_F_BUFFER_SELECTED_BIT, - REQ_F_NO_FILE_TABLE_BIT, - REQ_F_WORK_INITIALIZED_BIT, - REQ_F_LTIMEOUT_ACTIVE_BIT, + REQ_F_COMPLETE_INLINE_BIT, + REQ_F_REISSUE_BIT, + REQ_F_CREDS_BIT, + REQ_F_REFCOUNT_BIT, + REQ_F_ARM_LTIMEOUT_BIT, + /* keep async read/write and isreg together and in order */ + REQ_F_NOWAIT_READ_BIT, + REQ_F_NOWAIT_WRITE_BIT, + REQ_F_ISREG_BIT, /* not a real bit, just to check we're not overflowing the space */ __REQ_F_LAST_BIT, @@ -609,11 +772,9 @@ enum { /* IOSQE_BUFFER_SELECT */ REQ_F_BUFFER_SELECT = BIT(REQ_F_BUFFER_SELECT_BIT), - /* head of a link */ - REQ_F_LINK_HEAD = BIT(REQ_F_LINK_HEAD_BIT), /* fail rest of links */ - REQ_F_FAIL_LINK = BIT(REQ_F_FAIL_LINK_BIT), - /* on inflight list */ + REQ_F_FAIL = BIT(REQ_F_FAIL_BIT), + /* on inflight list, should be cancelled and waited on exit reliably */ REQ_F_INFLIGHT = BIT(REQ_F_INFLIGHT_BIT), /* read/write uses file position */ REQ_F_CUR_POS = BIT(REQ_F_CUR_POS_BIT), @@ -621,20 +782,28 @@ enum { REQ_F_NOWAIT = BIT(REQ_F_NOWAIT_BIT), /* has or had linked timeout */ REQ_F_LINK_TIMEOUT = BIT(REQ_F_LINK_TIMEOUT_BIT), - /* regular file */ - REQ_F_ISREG = BIT(REQ_F_ISREG_BIT), /* needs cleanup */ REQ_F_NEED_CLEANUP = BIT(REQ_F_NEED_CLEANUP_BIT), /* already went through poll handler */ REQ_F_POLLED = BIT(REQ_F_POLLED_BIT), /* buffer already selected */ REQ_F_BUFFER_SELECTED = BIT(REQ_F_BUFFER_SELECTED_BIT), - /* doesn't need file table for this request */ - REQ_F_NO_FILE_TABLE = BIT(REQ_F_NO_FILE_TABLE_BIT), - /* io_wq_work is initialized */ - REQ_F_WORK_INITIALIZED = BIT(REQ_F_WORK_INITIALIZED_BIT), - /* linked timeout is active, i.e. prepared by link's head */ - REQ_F_LTIMEOUT_ACTIVE = BIT(REQ_F_LTIMEOUT_ACTIVE_BIT), + /* completion is deferred through io_comp_state */ + REQ_F_COMPLETE_INLINE = BIT(REQ_F_COMPLETE_INLINE_BIT), + /* caller should reissue async */ + REQ_F_REISSUE = BIT(REQ_F_REISSUE_BIT), + /* supports async reads */ + REQ_F_NOWAIT_READ = BIT(REQ_F_NOWAIT_READ_BIT), + /* supports async writes */ + REQ_F_NOWAIT_WRITE = BIT(REQ_F_NOWAIT_WRITE_BIT), + /* regular file */ + REQ_F_ISREG = BIT(REQ_F_ISREG_BIT), + /* has creds assigned */ + REQ_F_CREDS = BIT(REQ_F_CREDS_BIT), + /* skip refcounting if not set */ + REQ_F_REFCOUNT = BIT(REQ_F_REFCOUNT_BIT), + /* there is a linked timeout that has to be armed */ + REQ_F_ARM_LTIMEOUT = BIT(REQ_F_ARM_LTIMEOUT_BIT), }; struct async_poll { @@ -642,6 +811,21 @@ struct async_poll { struct io_poll_iocb *double_poll; }; +typedef void (*io_req_tw_func_t)(struct io_kiocb *req, bool *locked); + +struct io_task_work { + union { + struct io_wq_work_node node; + struct llist_node fallback_node; + }; + io_req_tw_func_t func; +}; + +enum { + IORING_RSRC_FILE = 0, + IORING_RSRC_BUFFER = 1, +}; + /* * NOTE! Each of the iocb union members has the file pointer * as the first entry in their struct definition. So you can @@ -653,6 +837,7 @@ struct io_kiocb { struct file *file; struct io_rw rw; struct io_poll_iocb poll; + struct io_poll_update poll_update; struct io_accept accept; struct io_sync sync; struct io_cancel cancel; @@ -662,13 +847,19 @@ struct io_kiocb { struct io_sr_msg sr_msg; struct io_open open; struct io_close close; - struct io_files_update files_update; + struct io_rsrc_update rsrc_update; struct io_fadvise fadvise; struct io_madvise madvise; struct io_epoll epoll; struct io_splice splice; struct io_provide_buf pbuf; struct io_statx statx; + struct io_shutdown shutdown; + struct io_rename rename; + struct io_unlink unlink; + struct io_mkdir mkdir; + struct io_symlink symlink; + struct io_hardlink hardlink; /* use only after cleaning per-op data, see io_clean_op() */ struct io_completion compl; }; @@ -684,70 +875,44 @@ struct io_kiocb { struct io_ring_ctx *ctx; unsigned int flags; - refcount_t refs; + atomic_t refs; struct task_struct *task; u64 user_data; - struct list_head link_list; + struct io_kiocb *link; + struct percpu_ref *fixed_rsrc_refs; - /* - * 1. used with ctx->iopoll_list with reads/writes - * 2. to track reqs with ->files (see io_op_def::file_table) - */ + /* used with ctx->iopoll_list with reads/writes */ struct list_head inflight_entry; - - struct list_head iopoll_entry; - - struct percpu_ref *fixed_file_refs; - struct callback_head task_work; + struct io_task_work io_task_work; /* for polled requests, i.e. IORING_OP_POLL_ADD and async armed poll */ struct hlist_node hash_node; struct async_poll *apoll; struct io_wq_work work; -}; + const struct cred *creds; -struct io_defer_entry { - struct list_head list; - struct io_kiocb *req; - u32 seq; + /* store used ubuf, so we can prevent reloading */ + struct io_mapped_ubuf *imu; + /* stores selected buf, valid IFF REQ_F_BUFFER_SELECTED is set */ + struct io_buffer *kbuf; + atomic_t poll_refs; }; -#define IO_IOPOLL_BATCH 8 - -struct io_comp_state { - unsigned int nr; - struct list_head list; +struct io_tctx_node { + struct list_head ctx_node; + struct task_struct *task; struct io_ring_ctx *ctx; }; -struct io_submit_state { - struct blk_plug plug; - - /* - * io_kiocb alloc cache - */ - void *reqs[IO_IOPOLL_BATCH]; - unsigned int free_reqs; - - /* - * Batch completion logic - */ - struct io_comp_state comp; - - /* - * File reference cache - */ - struct file *file; - unsigned int fd; - unsigned int has_refs; - unsigned int ios_left; +struct io_defer_entry { + struct list_head list; + struct io_kiocb *req; + u32 seq; }; struct io_op_def { /* needs req->file assigned */ unsigned needs_file : 1; - /* don't fail if file grab fails */ - unsigned needs_file_no_error : 1; /* hash wq insertion if file is a regular file */ unsigned hash_reg_file : 1; /* unbound wq insertion if file is a non-regular file */ @@ -759,11 +924,12 @@ struct io_op_def { unsigned pollout : 1; /* op supports buffer selection */ unsigned buffer_select : 1; - /* must always have async data allocated */ - unsigned needs_async_data : 1; + /* do prep async if is going to be punted */ + unsigned needs_async_setup : 1; + /* should block plug */ + unsigned plug : 1; /* size of async data needed, if any */ unsigned short async_size; - unsigned work_flags; }; static const struct io_op_def io_op_defs[] = { @@ -773,41 +939,36 @@ static const struct io_op_def io_op_defs[] = { .unbound_nonreg_file = 1, .pollin = 1, .buffer_select = 1, - .needs_async_data = 1, + .needs_async_setup = 1, + .plug = 1, .async_size = sizeof(struct io_async_rw), - .work_flags = IO_WQ_WORK_MM | IO_WQ_WORK_BLKCG | - IO_WQ_WORK_FILES, }, [IORING_OP_WRITEV] = { .needs_file = 1, .hash_reg_file = 1, .unbound_nonreg_file = 1, .pollout = 1, - .needs_async_data = 1, + .needs_async_setup = 1, + .plug = 1, .async_size = sizeof(struct io_async_rw), - .work_flags = IO_WQ_WORK_MM | IO_WQ_WORK_BLKCG | - IO_WQ_WORK_FSIZE | IO_WQ_WORK_FILES, }, [IORING_OP_FSYNC] = { .needs_file = 1, - .work_flags = IO_WQ_WORK_BLKCG, }, [IORING_OP_READ_FIXED] = { .needs_file = 1, .unbound_nonreg_file = 1, .pollin = 1, + .plug = 1, .async_size = sizeof(struct io_async_rw), - .work_flags = IO_WQ_WORK_BLKCG | IO_WQ_WORK_MM | - IO_WQ_WORK_FILES, }, [IORING_OP_WRITE_FIXED] = { .needs_file = 1, .hash_reg_file = 1, .unbound_nonreg_file = 1, .pollout = 1, + .plug = 1, .async_size = sizeof(struct io_async_rw), - .work_flags = IO_WQ_WORK_BLKCG | IO_WQ_WORK_FSIZE | - IO_WQ_WORK_MM | IO_WQ_WORK_FILES, }, [IORING_OP_POLL_ADD] = { .needs_file = 1, @@ -816,126 +977,91 @@ static const struct io_op_def io_op_defs[] = { [IORING_OP_POLL_REMOVE] = {}, [IORING_OP_SYNC_FILE_RANGE] = { .needs_file = 1, - .work_flags = IO_WQ_WORK_BLKCG, }, [IORING_OP_SENDMSG] = { .needs_file = 1, .unbound_nonreg_file = 1, .pollout = 1, - .needs_async_data = 1, + .needs_async_setup = 1, .async_size = sizeof(struct io_async_msghdr), - .work_flags = IO_WQ_WORK_MM | IO_WQ_WORK_BLKCG | - IO_WQ_WORK_FS, }, [IORING_OP_RECVMSG] = { .needs_file = 1, .unbound_nonreg_file = 1, .pollin = 1, .buffer_select = 1, - .needs_async_data = 1, + .needs_async_setup = 1, .async_size = sizeof(struct io_async_msghdr), - .work_flags = IO_WQ_WORK_MM | IO_WQ_WORK_BLKCG | - IO_WQ_WORK_FS, }, [IORING_OP_TIMEOUT] = { - .needs_async_data = 1, .async_size = sizeof(struct io_timeout_data), - .work_flags = IO_WQ_WORK_MM, }, - [IORING_OP_TIMEOUT_REMOVE] = {}, + [IORING_OP_TIMEOUT_REMOVE] = { + /* used by timeout updates' prep() */ + }, [IORING_OP_ACCEPT] = { .needs_file = 1, .unbound_nonreg_file = 1, .pollin = 1, - .work_flags = IO_WQ_WORK_MM | IO_WQ_WORK_FILES, }, [IORING_OP_ASYNC_CANCEL] = {}, [IORING_OP_LINK_TIMEOUT] = { - .needs_async_data = 1, .async_size = sizeof(struct io_timeout_data), - .work_flags = IO_WQ_WORK_MM, }, [IORING_OP_CONNECT] = { .needs_file = 1, .unbound_nonreg_file = 1, .pollout = 1, - .needs_async_data = 1, + .needs_async_setup = 1, .async_size = sizeof(struct io_async_connect), - .work_flags = IO_WQ_WORK_MM | IO_WQ_WORK_FS, }, [IORING_OP_FALLOCATE] = { .needs_file = 1, - .work_flags = IO_WQ_WORK_BLKCG | IO_WQ_WORK_FSIZE, - }, - [IORING_OP_OPENAT] = { - .work_flags = IO_WQ_WORK_FILES | IO_WQ_WORK_BLKCG | - IO_WQ_WORK_FS, - }, - [IORING_OP_CLOSE] = { - .needs_file = 1, - .needs_file_no_error = 1, - .work_flags = IO_WQ_WORK_FILES | IO_WQ_WORK_BLKCG, - }, - [IORING_OP_FILES_UPDATE] = { - .work_flags = IO_WQ_WORK_FILES | IO_WQ_WORK_MM, - }, - [IORING_OP_STATX] = { - .work_flags = IO_WQ_WORK_FILES | IO_WQ_WORK_MM | - IO_WQ_WORK_FS | IO_WQ_WORK_BLKCG, }, + [IORING_OP_OPENAT] = {}, + [IORING_OP_CLOSE] = {}, + [IORING_OP_FILES_UPDATE] = {}, + [IORING_OP_STATX] = {}, [IORING_OP_READ] = { .needs_file = 1, .unbound_nonreg_file = 1, .pollin = 1, .buffer_select = 1, + .plug = 1, .async_size = sizeof(struct io_async_rw), - .work_flags = IO_WQ_WORK_MM | IO_WQ_WORK_BLKCG | - IO_WQ_WORK_FILES, }, [IORING_OP_WRITE] = { .needs_file = 1, .hash_reg_file = 1, .unbound_nonreg_file = 1, .pollout = 1, + .plug = 1, .async_size = sizeof(struct io_async_rw), - .work_flags = IO_WQ_WORK_MM | IO_WQ_WORK_BLKCG | - IO_WQ_WORK_FSIZE | IO_WQ_WORK_FILES, }, [IORING_OP_FADVISE] = { .needs_file = 1, - .work_flags = IO_WQ_WORK_BLKCG, - }, - [IORING_OP_MADVISE] = { - .work_flags = IO_WQ_WORK_MM | IO_WQ_WORK_BLKCG, }, + [IORING_OP_MADVISE] = {}, [IORING_OP_SEND] = { .needs_file = 1, .unbound_nonreg_file = 1, .pollout = 1, - .work_flags = IO_WQ_WORK_MM | IO_WQ_WORK_BLKCG | - IO_WQ_WORK_FS, }, [IORING_OP_RECV] = { .needs_file = 1, .unbound_nonreg_file = 1, .pollin = 1, .buffer_select = 1, - .work_flags = IO_WQ_WORK_MM | IO_WQ_WORK_BLKCG | - IO_WQ_WORK_FS, }, [IORING_OP_OPENAT2] = { - .work_flags = IO_WQ_WORK_FILES | IO_WQ_WORK_FS | - IO_WQ_WORK_BLKCG, }, [IORING_OP_EPOLL_CTL] = { .unbound_nonreg_file = 1, - .work_flags = IO_WQ_WORK_FILES, }, [IORING_OP_SPLICE] = { .needs_file = 1, .hash_reg_file = 1, .unbound_nonreg_file = 1, - .work_flags = IO_WQ_WORK_BLKCG | IO_WQ_WORK_FILES, }, [IORING_OP_PROVIDE_BUFFERS] = {}, [IORING_OP_REMOVE_BUFFERS] = {}, @@ -944,43 +1070,47 @@ static const struct io_op_def io_op_defs[] = { .hash_reg_file = 1, .unbound_nonreg_file = 1, }, + [IORING_OP_SHUTDOWN] = { + .needs_file = 1, + }, + [IORING_OP_RENAMEAT] = {}, + [IORING_OP_UNLINKAT] = {}, }; -enum io_mem_account { - ACCT_LOCKED, - ACCT_PINNED, -}; +/* requests with any of those set should undergo io_disarm_next() */ +#define IO_DISARM_MASK (REQ_F_ARM_LTIMEOUT | REQ_F_LINK_TIMEOUT | REQ_F_FAIL) -static void destroy_fixed_file_ref_node(struct fixed_file_ref_node *ref_node); -static struct fixed_file_ref_node *alloc_fixed_file_ref_node( - struct io_ring_ctx *ctx); +static bool io_disarm_next(struct io_kiocb *req); +static void io_uring_del_tctx_node(unsigned long index); +static void io_uring_try_cancel_requests(struct io_ring_ctx *ctx, + struct task_struct *task, + bool cancel_all); +static void io_uring_cancel_generic(bool cancel_all, struct io_sq_data *sqd); + +static void io_fill_cqe_req(struct io_kiocb *req, s32 res, u32 cflags); -static void __io_complete_rw(struct io_kiocb *req, long res, long res2, - struct io_comp_state *cs); -static void io_cqring_fill_event(struct io_kiocb *req, long res); static void io_put_req(struct io_kiocb *req); -static void io_put_req_deferred(struct io_kiocb *req, int nr); -static void io_double_put_req(struct io_kiocb *req); -static struct io_kiocb *io_prep_linked_timeout(struct io_kiocb *req); -static void __io_queue_linked_timeout(struct io_kiocb *req); +static void io_put_req_deferred(struct io_kiocb *req); +static void io_dismantle_req(struct io_kiocb *req); static void io_queue_linked_timeout(struct io_kiocb *req); -static int __io_sqe_files_update(struct io_ring_ctx *ctx, - struct io_uring_files_update *ip, - unsigned nr_args); -static void __io_clean_op(struct io_kiocb *req); -static struct file *io_file_get(struct io_submit_state *state, +static int __io_register_rsrc_update(struct io_ring_ctx *ctx, unsigned type, + struct io_uring_rsrc_update2 *up, + unsigned nr_args); +static void io_clean_op(struct io_kiocb *req); +static struct file *io_file_get(struct io_ring_ctx *ctx, struct io_kiocb *req, int fd, bool fixed); -static void __io_queue_sqe(struct io_kiocb *req, struct io_comp_state *cs); -static void io_file_put_work(struct work_struct *work); +static void __io_queue_sqe(struct io_kiocb *req); +static void io_rsrc_put_work(struct work_struct *work); -static ssize_t io_import_iovec(int rw, struct io_kiocb *req, - struct iovec **iovec, struct iov_iter *iter, - bool needs_lock); -static int io_setup_async_rw(struct io_kiocb *req, const struct iovec *iovec, - const struct iovec *fast_iov, - struct iov_iter *iter, bool force); -static void io_req_drop_files(struct io_kiocb *req); static void io_req_task_queue(struct io_kiocb *req); +static void io_submit_flush_completions(struct io_ring_ctx *ctx); +static int io_req_prep_async(struct io_kiocb *req); + +static int io_install_fixed_file(struct io_kiocb *req, struct file *file, + unsigned int issue_flags, u32 slot_index); +static int io_close_fixed(struct io_kiocb *req, unsigned int issue_flags); + +static enum hrtimer_restart io_link_timeout_fn(struct hrtimer *timer); static struct kmem_cache *req_cachep; @@ -999,21 +1129,67 @@ struct sock *io_uring_get_socket(struct file *file) } EXPORT_SYMBOL(io_uring_get_socket); -static inline void io_clean_op(struct io_kiocb *req) +static inline void io_tw_lock(struct io_ring_ctx *ctx, bool *locked) +{ + if (!*locked) { + mutex_lock(&ctx->uring_lock); + *locked = true; + } +} + +#define io_for_each_link(pos, head) \ + for (pos = (head); pos; pos = pos->link) + +/* + * Shamelessly stolen from the mm implementation of page reference checking, + * see commit f958d7b528b1 for details. + */ +#define req_ref_zero_or_close_to_overflow(req) \ + ((unsigned int) atomic_read(&(req->refs)) + 127u <= 127u) + +static inline bool req_ref_inc_not_zero(struct io_kiocb *req) { - if (req->flags & (REQ_F_NEED_CLEANUP | REQ_F_BUFFER_SELECTED)) - __io_clean_op(req); + WARN_ON_ONCE(!(req->flags & REQ_F_REFCOUNT)); + return atomic_inc_not_zero(&req->refs); } -static inline bool __io_match_files(struct io_kiocb *req, - struct files_struct *files) +static inline bool req_ref_put_and_test(struct io_kiocb *req) { - if (req->file && req->file->f_op == &io_uring_fops) + if (likely(!(req->flags & REQ_F_REFCOUNT))) return true; - return ((req->flags & REQ_F_WORK_INITIALIZED) && - (req->work.flags & IO_WQ_WORK_FILES)) && - req->work.identity->files == files; + WARN_ON_ONCE(req_ref_zero_or_close_to_overflow(req)); + return atomic_dec_and_test(&req->refs); +} + +static inline void req_ref_get(struct io_kiocb *req) +{ + WARN_ON_ONCE(!(req->flags & REQ_F_REFCOUNT)); + WARN_ON_ONCE(req_ref_zero_or_close_to_overflow(req)); + atomic_inc(&req->refs); +} + +static inline void __io_req_set_refcount(struct io_kiocb *req, int nr) +{ + if (!(req->flags & REQ_F_REFCOUNT)) { + req->flags |= REQ_F_REFCOUNT; + atomic_set(&req->refs, nr); + } +} + +static inline void io_req_set_refcount(struct io_kiocb *req) +{ + __io_req_set_refcount(req, 1); +} + +static inline void io_req_set_rsrc_node(struct io_kiocb *req) +{ + struct io_ring_ctx *ctx = req->ctx; + + if (!req->fixed_rsrc_refs) { + req->fixed_rsrc_refs = &ctx->rsrc_node->refs; + percpu_ref_get(req->fixed_rsrc_refs); + } } static void io_refs_resurrect(struct percpu_ref *ref, struct completion *compl) @@ -1028,169 +1204,104 @@ static void io_refs_resurrect(struct percpu_ref *ref, struct completion *compl) percpu_ref_put(ref); } -static bool io_match_task(struct io_kiocb *head, - struct task_struct *task, - struct files_struct *files) +static bool io_match_task(struct io_kiocb *head, struct task_struct *task, + bool cancel_all) + __must_hold(&req->ctx->timeout_lock) { - struct io_kiocb *link; + struct io_kiocb *req; - if (task && head->task != task) { - /* in terms of cancelation, always match if req task is dead */ - if (head->task->flags & PF_EXITING) - return true; + if (task && head->task != task) return false; - } - if (!files) - return true; - if (__io_match_files(head, files)) + if (cancel_all) return true; - if (head->flags & REQ_F_LINK_HEAD) { - list_for_each_entry(link, &head->link_list, link_list) { - if (__io_match_files(link, files)) - return true; - } + + io_for_each_link(req, head) { + if (req->flags & REQ_F_INFLIGHT) + return true; } return false; } - -static void io_sq_thread_drop_mm(void) +static bool io_match_linked(struct io_kiocb *head) { - struct mm_struct *mm = current->mm; + struct io_kiocb *req; - if (mm) { - kthread_unuse_mm(mm); - mmput(mm); - current->mm = NULL; + io_for_each_link(req, head) { + if (req->flags & REQ_F_INFLIGHT) + return true; } + return false; } -static int __io_sq_thread_acquire_mm(struct io_ring_ctx *ctx) +/* + * As io_match_task() but protected against racing with linked timeouts. + * User must not hold timeout_lock. + */ +static bool io_match_task_safe(struct io_kiocb *head, struct task_struct *task, + bool cancel_all) { - struct mm_struct *mm; - - if (current->flags & PF_EXITING) - return -EFAULT; - if (current->mm) - return 0; + bool matched; - /* Should never happen */ - if (unlikely(!(ctx->flags & IORING_SETUP_SQPOLL))) - return -EFAULT; + if (task && head->task != task) + return false; + if (cancel_all) + return true; - task_lock(ctx->sqo_task); - mm = ctx->sqo_task->mm; - if (unlikely(!mm || !mmget_not_zero(mm))) - mm = NULL; - task_unlock(ctx->sqo_task); + if (head->flags & REQ_F_LINK_TIMEOUT) { + struct io_ring_ctx *ctx = head->ctx; - if (mm) { - kthread_use_mm(mm); - return 0; - } - - return -EFAULT; -} - -static int io_sq_thread_acquire_mm(struct io_ring_ctx *ctx, - struct io_kiocb *req) -{ - if (!(io_op_defs[req->opcode].work_flags & IO_WQ_WORK_MM)) - return 0; - return __io_sq_thread_acquire_mm(ctx); -} - -static void io_sq_thread_associate_blkcg(struct io_ring_ctx *ctx, - struct cgroup_subsys_state **cur_css) - -{ -#ifdef CONFIG_BLK_CGROUP - /* puts the old one when swapping */ - if (*cur_css != ctx->sqo_blkcg_css) { - kthread_associate_blkcg(ctx->sqo_blkcg_css); - *cur_css = ctx->sqo_blkcg_css; + /* protect against races with linked timeouts */ + spin_lock_irq(&ctx->timeout_lock); + matched = io_match_linked(head); + spin_unlock_irq(&ctx->timeout_lock); + } else { + matched = io_match_linked(head); } -#endif + return matched; } -static void io_sq_thread_unassociate_blkcg(void) +static inline void req_set_fail(struct io_kiocb *req) { -#ifdef CONFIG_BLK_CGROUP - kthread_associate_blkcg(NULL); -#endif + req->flags |= REQ_F_FAIL; } -static inline void req_set_fail_links(struct io_kiocb *req) +static inline void req_fail_link_node(struct io_kiocb *req, int res) { - if ((req->flags & (REQ_F_LINK | REQ_F_HARDLINK)) == REQ_F_LINK) - req->flags |= REQ_F_FAIL_LINK; + req_set_fail(req); + req->result = res; } -/* - * None of these are dereferenced, they are simply used to check if any of - * them have changed. If we're under current and check they are still the - * same, we're fine to grab references to them for actual out-of-line use. - */ -static void io_init_identity(struct io_identity *id) +static void io_ring_ctx_ref_free(struct percpu_ref *ref) { - id->files = current->files; - id->mm = current->mm; -#ifdef CONFIG_BLK_CGROUP - rcu_read_lock(); - id->blkcg_css = blkcg_css(); - rcu_read_unlock(); -#endif - id->creds = current_cred(); - id->nsproxy = current->nsproxy; - id->fs = current->fs; - id->fsize = rlimit(RLIMIT_FSIZE); -#ifdef CONFIG_AUDIT - id->loginuid = current->loginuid; - id->sessionid = current->sessionid; -#endif - refcount_set(&id->count, 1); -} + struct io_ring_ctx *ctx = container_of(ref, struct io_ring_ctx, refs); -static inline void __io_req_init_async(struct io_kiocb *req) -{ - memset(&req->work, 0, sizeof(req->work)); - req->flags |= REQ_F_WORK_INITIALIZED; + complete(&ctx->ref_comp); } -/* - * Note: must call io_req_init_async() for the first time you - * touch any members of io_wq_work. - */ -static inline void io_req_init_async(struct io_kiocb *req) +static inline bool io_is_timeout_noseq(struct io_kiocb *req) { - struct io_uring_task *tctx = req->task->io_uring; - - if (req->flags & REQ_F_WORK_INITIALIZED) - return; - - __io_req_init_async(req); - - /* Grab a ref if this isn't our static identity */ - req->work.identity = tctx->identity; - if (tctx->identity != &tctx->__identity) - refcount_inc(&req->work.identity->count); + return !req->timeout.off; } -static inline bool io_async_submit(struct io_ring_ctx *ctx) +static void io_fallback_req_func(struct work_struct *work) { - return ctx->flags & IORING_SETUP_SQPOLL; -} + struct io_ring_ctx *ctx = container_of(work, struct io_ring_ctx, + fallback_work.work); + struct llist_node *node = llist_del_all(&ctx->fallback_llist); + struct io_kiocb *req, *tmp; + bool locked = false; -static void io_ring_ctx_ref_free(struct percpu_ref *ref) -{ - struct io_ring_ctx *ctx = container_of(ref, struct io_ring_ctx, refs); + percpu_ref_get(&ctx->refs); + llist_for_each_entry_safe(req, tmp, node, io_task_work.fallback_node) + req->io_task_work.func(req, &locked); - complete(&ctx->ref_comp); -} + if (locked) { + if (ctx->submit_state.compl_nr) + io_submit_flush_completions(ctx); + mutex_unlock(&ctx->uring_lock); + } + percpu_ref_put(&ctx->refs); -static inline bool io_is_timeout_noseq(struct io_kiocb *req) -{ - return !req->timeout.off; } static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) @@ -1202,10 +1313,6 @@ static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) if (!ctx) return NULL; - ctx->fallback_req = kmem_cache_alloc(req_cachep, GFP_KERNEL); - if (!ctx->fallback_req) - goto err; - /* * Use 5 bits less than the max cq entries, that should give us around * 32 entries per hash list if totally full and uniformly spread. @@ -1221,6 +1328,12 @@ static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) goto err; __hash_init(ctx->cancel_hash, 1U << hash_bits); + ctx->dummy_ubuf = kzalloc(sizeof(*ctx->dummy_ubuf), GFP_KERNEL); + if (!ctx->dummy_ubuf) + goto err; + /* set invalid range, so io_import_fixed() fails meeting it */ + ctx->dummy_ubuf->ubuf = -1UL; + if (percpu_ref_init(&ctx->refs, io_ring_ctx_ref_free, PERCPU_REF_ALLOW_REINIT, GFP_KERNEL)) goto err; @@ -1228,232 +1341,109 @@ static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) ctx->flags = p->flags; init_waitqueue_head(&ctx->sqo_sq_wait); INIT_LIST_HEAD(&ctx->sqd_list); - init_waitqueue_head(&ctx->cq_wait); + init_waitqueue_head(&ctx->poll_wait); INIT_LIST_HEAD(&ctx->cq_overflow_list); init_completion(&ctx->ref_comp); - init_completion(&ctx->sq_thread_comp); xa_init_flags(&ctx->io_buffers, XA_FLAGS_ALLOC1); xa_init_flags(&ctx->personalities, XA_FLAGS_ALLOC1); mutex_init(&ctx->uring_lock); - init_waitqueue_head(&ctx->wait); + init_waitqueue_head(&ctx->cq_wait); spin_lock_init(&ctx->completion_lock); + spin_lock_init(&ctx->timeout_lock); INIT_LIST_HEAD(&ctx->iopoll_list); INIT_LIST_HEAD(&ctx->defer_list); INIT_LIST_HEAD(&ctx->timeout_list); - spin_lock_init(&ctx->inflight_lock); - INIT_LIST_HEAD(&ctx->inflight_list); - INIT_DELAYED_WORK(&ctx->file_put_work, io_file_put_work); - init_llist_head(&ctx->file_put_llist); + INIT_LIST_HEAD(&ctx->ltimeout_list); + spin_lock_init(&ctx->rsrc_ref_lock); + INIT_LIST_HEAD(&ctx->rsrc_ref_list); + INIT_DELAYED_WORK(&ctx->rsrc_put_work, io_rsrc_put_work); + init_llist_head(&ctx->rsrc_put_llist); + INIT_LIST_HEAD(&ctx->tctx_list); + INIT_LIST_HEAD(&ctx->submit_state.free_list); + INIT_LIST_HEAD(&ctx->locked_free_list); + INIT_DELAYED_WORK(&ctx->fallback_work, io_fallback_req_func); return ctx; err: - if (ctx->fallback_req) - kmem_cache_free(req_cachep, ctx->fallback_req); + kfree(ctx->dummy_ubuf); kfree(ctx->cancel_hash); kfree(ctx); return NULL; } +static void io_account_cq_overflow(struct io_ring_ctx *ctx) +{ + struct io_rings *r = ctx->rings; + + WRITE_ONCE(r->cq_overflow, READ_ONCE(r->cq_overflow) + 1); + ctx->cq_extra--; +} + static bool req_need_defer(struct io_kiocb *req, u32 seq) { if (unlikely(req->flags & REQ_F_IO_DRAIN)) { struct io_ring_ctx *ctx = req->ctx; - return seq != ctx->cached_cq_tail - + READ_ONCE(ctx->cached_cq_overflow); + return seq + READ_ONCE(ctx->cq_extra) != ctx->cached_cq_tail; } return false; } -static void __io_commit_cqring(struct io_ring_ctx *ctx) -{ - struct io_rings *rings = ctx->rings; - - /* order cqe stores with ring update */ - smp_store_release(&rings->cq.tail, ctx->cached_cq_tail); -} +#define FFS_ASYNC_READ 0x1UL +#define FFS_ASYNC_WRITE 0x2UL +#ifdef CONFIG_64BIT +#define FFS_ISREG 0x4UL +#else +#define FFS_ISREG 0x0UL +#endif +#define FFS_MASK ~(FFS_ASYNC_READ|FFS_ASYNC_WRITE|FFS_ISREG) -static void io_put_identity(struct io_uring_task *tctx, struct io_kiocb *req) +static inline bool io_req_ffs_set(struct io_kiocb *req) { - if (req->work.identity == &tctx->__identity) - return; - if (refcount_dec_and_test(&req->work.identity->count)) - kfree(req->work.identity); + return IS_ENABLED(CONFIG_64BIT) && (req->flags & REQ_F_FIXED_FILE); } -static void io_req_clean_work(struct io_kiocb *req) +static void io_req_track_inflight(struct io_kiocb *req) { - if (!(req->flags & REQ_F_WORK_INITIALIZED)) - return; - - req->flags &= ~REQ_F_WORK_INITIALIZED; - - if (req->work.flags & IO_WQ_WORK_MM) { - mmdrop(req->work.identity->mm); - req->work.flags &= ~IO_WQ_WORK_MM; - } -#ifdef CONFIG_BLK_CGROUP - if (req->work.flags & IO_WQ_WORK_BLKCG) { - css_put(req->work.identity->blkcg_css); - req->work.flags &= ~IO_WQ_WORK_BLKCG; - } -#endif - if (req->work.flags & IO_WQ_WORK_CREDS) { - put_cred(req->work.identity->creds); - req->work.flags &= ~IO_WQ_WORK_CREDS; - } - if (req->work.flags & IO_WQ_WORK_FS) { - struct fs_struct *fs = req->work.identity->fs; - - spin_lock(&req->work.identity->fs->lock); - if (--fs->users) - fs = NULL; - spin_unlock(&req->work.identity->fs->lock); - if (fs) - free_fs_struct(fs); - req->work.flags &= ~IO_WQ_WORK_FS; + if (!(req->flags & REQ_F_INFLIGHT)) { + req->flags |= REQ_F_INFLIGHT; + atomic_inc(&req->task->io_uring->inflight_tracked); } - if (req->flags & REQ_F_INFLIGHT) - io_req_drop_files(req); - - io_put_identity(req->task->io_uring, req); } -/* - * Create a private copy of io_identity, since some fields don't match - * the current context. - */ -static bool io_identity_cow(struct io_kiocb *req) +static struct io_kiocb *__io_prep_linked_timeout(struct io_kiocb *req) { - struct io_uring_task *tctx = req->task->io_uring; - const struct cred *creds = NULL; - struct io_identity *id; - - if (req->work.flags & IO_WQ_WORK_CREDS) - creds = req->work.identity->creds; - - id = kmemdup(req->work.identity, sizeof(*id), GFP_KERNEL); - if (unlikely(!id)) { - req->work.flags |= IO_WQ_WORK_CANCEL; - return false; - } - - /* - * We can safely just re-init the creds we copied Either the field - * matches the current one, or we haven't grabbed it yet. The only - * exception is ->creds, through registered personalities, so handle - * that one separately. - */ - io_init_identity(id); - if (creds) - id->creds = creds; - - /* add one for this request */ - refcount_inc(&id->count); + if (WARN_ON_ONCE(!req->link)) + return NULL; - /* drop tctx and req identity references, if needed */ - if (tctx->identity != &tctx->__identity && - refcount_dec_and_test(&tctx->identity->count)) - kfree(tctx->identity); - if (req->work.identity != &tctx->__identity && - refcount_dec_and_test(&req->work.identity->count)) - kfree(req->work.identity); + req->flags &= ~REQ_F_ARM_LTIMEOUT; + req->flags |= REQ_F_LINK_TIMEOUT; - req->work.identity = id; - tctx->identity = id; - return true; + /* linked timeouts should have two refs once prep'ed */ + io_req_set_refcount(req); + __io_req_set_refcount(req->link, 2); + return req->link; } -static bool io_grab_identity(struct io_kiocb *req) +static inline struct io_kiocb *io_prep_linked_timeout(struct io_kiocb *req) { - const struct io_op_def *def = &io_op_defs[req->opcode]; - struct io_identity *id = req->work.identity; - struct io_ring_ctx *ctx = req->ctx; - - if (def->work_flags & IO_WQ_WORK_FSIZE) { - if (id->fsize != rlimit(RLIMIT_FSIZE)) - return false; - req->work.flags |= IO_WQ_WORK_FSIZE; - } -#ifdef CONFIG_BLK_CGROUP - if (!(req->work.flags & IO_WQ_WORK_BLKCG) && - (def->work_flags & IO_WQ_WORK_BLKCG)) { - rcu_read_lock(); - if (id->blkcg_css != blkcg_css()) { - rcu_read_unlock(); - return false; - } - /* - * This should be rare, either the cgroup is dying or the task - * is moving cgroups. Just punt to root for the handful of ios. - */ - if (css_tryget_online(id->blkcg_css)) - req->work.flags |= IO_WQ_WORK_BLKCG; - rcu_read_unlock(); - } -#endif - if (!(req->work.flags & IO_WQ_WORK_CREDS)) { - if (id->creds != current_cred()) - return false; - get_cred(id->creds); - req->work.flags |= IO_WQ_WORK_CREDS; - } -#ifdef CONFIG_AUDIT - if (!uid_eq(current->loginuid, id->loginuid) || - current->sessionid != id->sessionid) - return false; -#endif - if (!(req->work.flags & IO_WQ_WORK_FS) && - (def->work_flags & IO_WQ_WORK_FS)) { - if (current->fs != id->fs) - return false; - spin_lock(&id->fs->lock); - if (!id->fs->in_exec) { - id->fs->users++; - req->work.flags |= IO_WQ_WORK_FS; - } else { - req->work.flags |= IO_WQ_WORK_CANCEL; - } - spin_unlock(¤t->fs->lock); - } - if (!(req->work.flags & IO_WQ_WORK_FILES) && - (def->work_flags & IO_WQ_WORK_FILES) && - !(req->flags & REQ_F_NO_FILE_TABLE)) { - if (id->files != current->files || - id->nsproxy != current->nsproxy) - return false; - atomic_inc(&id->files->count); - get_nsproxy(id->nsproxy); - - if (!(req->flags & REQ_F_INFLIGHT)) { - req->flags |= REQ_F_INFLIGHT; - - spin_lock_irq(&ctx->inflight_lock); - list_add(&req->inflight_entry, &ctx->inflight_list); - spin_unlock_irq(&ctx->inflight_lock); - } - req->work.flags |= IO_WQ_WORK_FILES; - } - if (!(req->work.flags & IO_WQ_WORK_MM) && - (def->work_flags & IO_WQ_WORK_MM)) { - if (id->mm != current->mm) - return false; - mmgrab(id->mm); - req->work.flags |= IO_WQ_WORK_MM; - } - - return true; + if (likely(!(req->flags & REQ_F_ARM_LTIMEOUT))) + return NULL; + return __io_prep_linked_timeout(req); } static void io_prep_async_work(struct io_kiocb *req) { const struct io_op_def *def = &io_op_defs[req->opcode]; struct io_ring_ctx *ctx = req->ctx; - struct io_identity *id; - io_req_init_async(req); - id = req->work.identity; + if (!(req->flags & REQ_F_CREDS)) { + req->flags |= REQ_F_CREDS; + req->creds = get_current_cred(); + } + req->work.list.next = NULL; + req->work.flags = 0; if (req->flags & REQ_F_FORCE_ASYNC) req->work.flags |= IO_WQ_WORK_CONCURRENT; @@ -1464,92 +1454,77 @@ static void io_prep_async_work(struct io_kiocb *req) if (def->unbound_nonreg_file) req->work.flags |= IO_WQ_WORK_UNBOUND; } - - /* if we fail grabbing identity, we must COW, regrab, and retry */ - if (io_grab_identity(req)) - return; - - if (!io_identity_cow(req)) - return; - - /* can't fail at this point */ - if (!io_grab_identity(req)) - WARN_ON(1); } static void io_prep_async_link(struct io_kiocb *req) { struct io_kiocb *cur; - io_prep_async_work(req); - if (req->flags & REQ_F_LINK_HEAD) - list_for_each_entry(cur, &req->link_list, link_list) + if (req->flags & REQ_F_LINK_TIMEOUT) { + struct io_ring_ctx *ctx = req->ctx; + + spin_lock_irq(&ctx->timeout_lock); + io_for_each_link(cur, req) + io_prep_async_work(cur); + spin_unlock_irq(&ctx->timeout_lock); + } else { + io_for_each_link(cur, req) io_prep_async_work(cur); + } } -static struct io_kiocb *__io_queue_async_work(struct io_kiocb *req) +static void io_queue_async_work(struct io_kiocb *req, bool *locked) { struct io_ring_ctx *ctx = req->ctx; struct io_kiocb *link = io_prep_linked_timeout(req); + struct io_uring_task *tctx = req->task->io_uring; - trace_io_uring_queue_async_work(ctx, io_wq_is_hashed(&req->work), req, - &req->work, req->flags); - io_wq_enqueue(ctx->io_wq, &req->work); - return link; -} + /* must not take the lock, NULL it as a precaution */ + locked = NULL; -static void io_queue_async_work(struct io_kiocb *req) -{ - struct io_kiocb *link; + BUG_ON(!tctx); + BUG_ON(!tctx->io_wq); /* init ->work of the whole link before punting */ io_prep_async_link(req); - link = __io_queue_async_work(req); + /* + * Not expected to happen, but if we do have a bug where this _can_ + * happen, catch it here and ensure the request is marked as + * canceled. That will make io-wq go through the usual work cancel + * procedure rather than attempt to run this request (or create a new + * worker for it). + */ + if (WARN_ON_ONCE(!same_thread_group(req->task, current))) + req->work.flags |= IO_WQ_WORK_CANCEL; + + trace_io_uring_queue_async_work(ctx, io_wq_is_hashed(&req->work), req, + &req->work, req->flags); + io_wq_enqueue(tctx->io_wq, &req->work); if (link) io_queue_linked_timeout(link); } static void io_kill_timeout(struct io_kiocb *req, int status) + __must_hold(&req->ctx->completion_lock) + __must_hold(&req->ctx->timeout_lock) { struct io_timeout_data *io = req->async_data; - int ret; - ret = hrtimer_try_to_cancel(&io->timer); - if (ret != -1) { + if (hrtimer_try_to_cancel(&io->timer) != -1) { if (status) - req_set_fail_links(req); + req_set_fail(req); atomic_set(&req->ctx->cq_timeouts, atomic_read(&req->ctx->cq_timeouts) + 1); list_del_init(&req->timeout.list); - io_cqring_fill_event(req, status); - io_put_req_deferred(req, 1); - } -} - -/* - * Returns true if we found and killed one or more timeouts - */ -static bool io_kill_timeouts(struct io_ring_ctx *ctx, struct task_struct *tsk, - struct files_struct *files) -{ - struct io_kiocb *req, *tmp; - int canceled = 0; - - spin_lock_irq(&ctx->completion_lock); - list_for_each_entry_safe(req, tmp, &ctx->timeout_list, timeout.list) { - if (io_match_task(req, tsk, files)) { - io_kill_timeout(req, -ECANCELED); - canceled++; - } + io_fill_cqe_req(req, status, 0); + io_put_req_deferred(req); } - spin_unlock_irq(&ctx->completion_lock); - return canceled != 0; } -static void __io_queue_deferred(struct io_ring_ctx *ctx) +static void io_queue_deferred(struct io_ring_ctx *ctx) { - do { + while (!list_empty(&ctx->defer_list)) { struct io_defer_entry *de = list_first_entry(&ctx->defer_list, struct io_defer_entry, list); @@ -1558,19 +1533,16 @@ static void __io_queue_deferred(struct io_ring_ctx *ctx) list_del_init(&de->list); io_req_task_queue(de->req); kfree(de); - } while (!list_empty(&ctx->defer_list)); + } } static void io_flush_timeouts(struct io_ring_ctx *ctx) + __must_hold(&ctx->completion_lock) { + u32 seq = ctx->cached_cq_tail - atomic_read(&ctx->cq_timeouts); struct io_kiocb *req, *tmp; - u32 seq; - - if (list_empty(&ctx->timeout_list)) - return; - - seq = ctx->cached_cq_tail - atomic_read(&ctx->cq_timeouts); + spin_lock_irq(&ctx->timeout_lock); list_for_each_entry_safe(req, tmp, &ctx->timeout_list, timeout.list) { u32 events_needed, events_got; @@ -1591,441 +1563,568 @@ static void io_flush_timeouts(struct io_ring_ctx *ctx) io_kill_timeout(req, 0); } - ctx->cq_last_tm_flush = seq; + spin_unlock_irq(&ctx->timeout_lock); } -static void io_commit_cqring(struct io_ring_ctx *ctx) +static void __io_commit_cqring_flush(struct io_ring_ctx *ctx) { - io_flush_timeouts(ctx); - __io_commit_cqring(ctx); + if (ctx->off_timeout_used) + io_flush_timeouts(ctx); + if (ctx->drain_active) + io_queue_deferred(ctx); +} - if (unlikely(!list_empty(&ctx->defer_list))) - __io_queue_deferred(ctx); +static inline void io_commit_cqring(struct io_ring_ctx *ctx) +{ + if (unlikely(ctx->off_timeout_used || ctx->drain_active)) + __io_commit_cqring_flush(ctx); + /* order cqe stores with ring update */ + smp_store_release(&ctx->rings->cq.tail, ctx->cached_cq_tail); } static inline bool io_sqring_full(struct io_ring_ctx *ctx) { struct io_rings *r = ctx->rings; - return READ_ONCE(r->sq.tail) - ctx->cached_sq_head == r->sq_ring_entries; + return READ_ONCE(r->sq.tail) - ctx->cached_sq_head == ctx->sq_entries; +} + +static inline unsigned int __io_cqring_events(struct io_ring_ctx *ctx) +{ + return ctx->cached_cq_tail - READ_ONCE(ctx->rings->cq.head); } -static struct io_uring_cqe *io_get_cqring(struct io_ring_ctx *ctx) +static inline struct io_uring_cqe *io_get_cqe(struct io_ring_ctx *ctx) { struct io_rings *rings = ctx->rings; - unsigned tail; + unsigned tail, mask = ctx->cq_entries - 1; - tail = ctx->cached_cq_tail; /* * writes to the cq entry need to come after reading head; the * control dependency is enough as we're using WRITE_ONCE to * fill the cq entry */ - if (tail - READ_ONCE(rings->cq.head) == rings->cq_ring_entries) + if (__io_cqring_events(ctx) == ctx->cq_entries) return NULL; - ctx->cached_cq_tail++; - return &rings->cqes[tail & ctx->cq_mask]; + tail = ctx->cached_cq_tail++; + return &rings->cqes[tail & mask]; } static inline bool io_should_trigger_evfd(struct io_ring_ctx *ctx) { - if (!ctx->cq_ev_fd) + if (likely(!ctx->cq_ev_fd)) return false; if (READ_ONCE(ctx->rings->cq_flags) & IORING_CQ_EVENTFD_DISABLED) return false; - if (!ctx->eventfd_async) - return true; - return io_wq_current_is_worker(); + return !ctx->eventfd_async || io_wq_current_is_worker(); } +/* + * This should only get called when at least one event has been posted. + * Some applications rely on the eventfd notification count only changing + * IFF a new CQE has been added to the CQ ring. There's no depedency on + * 1:1 relationship between how many times this function is called (and + * hence the eventfd count) and number of CQEs posted to the CQ ring. + */ static void io_cqring_ev_posted(struct io_ring_ctx *ctx) { - if (wq_has_sleeper(&ctx->cq_wait)) { - wake_up_interruptible(&ctx->cq_wait); - kill_fasync(&ctx->cq_fasync, SIGIO, POLL_IN); - } - if (waitqueue_active(&ctx->wait)) - wake_up(&ctx->wait); + /* + * wake_up_all() may seem excessive, but io_wake_function() and + * io_should_wake() handle the termination of the loop and only + * wake as many waiters as we need to. + */ + if (wq_has_sleeper(&ctx->cq_wait)) + __wake_up(&ctx->cq_wait, TASK_NORMAL, 0, + poll_to_key(EPOLL_URING_WAKE | EPOLLIN)); if (ctx->sq_data && waitqueue_active(&ctx->sq_data->wait)) wake_up(&ctx->sq_data->wait); if (io_should_trigger_evfd(ctx)) - eventfd_signal(ctx->cq_ev_fd, 1); + eventfd_signal_mask(ctx->cq_ev_fd, 1, EPOLL_URING_WAKE); + if (waitqueue_active(&ctx->poll_wait)) + __wake_up(&ctx->poll_wait, TASK_INTERRUPTIBLE, 0, + poll_to_key(EPOLL_URING_WAKE | EPOLLIN)); } -static void io_cqring_mark_overflow(struct io_ring_ctx *ctx) +static void io_cqring_ev_posted_iopoll(struct io_ring_ctx *ctx) { - if (list_empty(&ctx->cq_overflow_list)) { - clear_bit(0, &ctx->sq_check_overflow); - clear_bit(0, &ctx->cq_check_overflow); - ctx->rings->sq_flags &= ~IORING_SQ_CQ_OVERFLOW; + /* see waitqueue_active() comment */ + smp_mb(); + + if (ctx->flags & IORING_SETUP_SQPOLL) { + if (waitqueue_active(&ctx->cq_wait)) + __wake_up(&ctx->cq_wait, TASK_NORMAL, 0, + poll_to_key(EPOLL_URING_WAKE | EPOLLIN)); } + if (io_should_trigger_evfd(ctx)) + eventfd_signal_mask(ctx->cq_ev_fd, 1, EPOLL_URING_WAKE); + if (waitqueue_active(&ctx->poll_wait)) + __wake_up(&ctx->poll_wait, TASK_INTERRUPTIBLE, 0, + poll_to_key(EPOLL_URING_WAKE | EPOLLIN)); } /* Returns true if there are no backlogged entries after the flush */ -static bool __io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force, - struct task_struct *tsk, - struct files_struct *files) +static bool __io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force) { - struct io_rings *rings = ctx->rings; - struct io_kiocb *req, *tmp; - struct io_uring_cqe *cqe; - unsigned long flags; - LIST_HEAD(list); + bool all_flushed, posted; - if (!force) { - if ((ctx->cached_cq_tail - READ_ONCE(rings->cq.head) == - rings->cq_ring_entries)) - return false; - } - - spin_lock_irqsave(&ctx->completion_lock, flags); + if (!force && __io_cqring_events(ctx) == ctx->cq_entries) + return false; - cqe = NULL; - list_for_each_entry_safe(req, tmp, &ctx->cq_overflow_list, compl.list) { - if (!io_match_task(req, tsk, files)) - continue; + posted = false; + spin_lock(&ctx->completion_lock); + while (!list_empty(&ctx->cq_overflow_list)) { + struct io_uring_cqe *cqe = io_get_cqe(ctx); + struct io_overflow_cqe *ocqe; - cqe = io_get_cqring(ctx); if (!cqe && !force) break; + ocqe = list_first_entry(&ctx->cq_overflow_list, + struct io_overflow_cqe, list); + if (cqe) + memcpy(cqe, &ocqe->cqe, sizeof(*cqe)); + else + io_account_cq_overflow(ctx); - list_move(&req->compl.list, &list); - if (cqe) { - WRITE_ONCE(cqe->user_data, req->user_data); - WRITE_ONCE(cqe->res, req->result); - WRITE_ONCE(cqe->flags, req->compl.cflags); - } else { - ctx->cached_cq_overflow++; - WRITE_ONCE(ctx->rings->cq_overflow, - ctx->cached_cq_overflow); - } + posted = true; + list_del(&ocqe->list); + kfree(ocqe); } - io_commit_cqring(ctx); - io_cqring_mark_overflow(ctx); - - spin_unlock_irqrestore(&ctx->completion_lock, flags); - io_cqring_ev_posted(ctx); - - while (!list_empty(&list)) { - req = list_first_entry(&list, struct io_kiocb, compl.list); - list_del(&req->compl.list); - io_put_req(req); + all_flushed = list_empty(&ctx->cq_overflow_list); + if (all_flushed) { + clear_bit(0, &ctx->check_cq_overflow); + WRITE_ONCE(ctx->rings->sq_flags, + ctx->rings->sq_flags & ~IORING_SQ_CQ_OVERFLOW); } - return cqe != NULL; + if (posted) + io_commit_cqring(ctx); + spin_unlock(&ctx->completion_lock); + if (posted) + io_cqring_ev_posted(ctx); + return all_flushed; } -static void io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force, - struct task_struct *tsk, - struct files_struct *files) +static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx) { - if (test_bit(0, &ctx->cq_check_overflow)) { + bool ret = true; + + if (test_bit(0, &ctx->check_cq_overflow)) { /* iopoll syncs against uring_lock, not completion_lock */ if (ctx->flags & IORING_SETUP_IOPOLL) mutex_lock(&ctx->uring_lock); - __io_cqring_overflow_flush(ctx, force, tsk, files); + ret = __io_cqring_overflow_flush(ctx, false); if (ctx->flags & IORING_SETUP_IOPOLL) mutex_unlock(&ctx->uring_lock); } + + return ret; } -static void __io_cqring_fill_event(struct io_kiocb *req, long res, - unsigned int cflags) +/* must to be called somewhat shortly after putting a request */ +static inline void io_put_task(struct task_struct *task, int nr) { - struct io_ring_ctx *ctx = req->ctx; - struct io_uring_cqe *cqe; + struct io_uring_task *tctx = task->io_uring; - trace_io_uring_complete(ctx, req->user_data, res); - - /* - * If we can't get a cq entry, userspace overflowed the - * submission (by quite a lot). Increment the overflow count in - * the ring. - */ - cqe = io_get_cqring(ctx); - if (likely(cqe)) { - WRITE_ONCE(cqe->user_data, req->user_data); - WRITE_ONCE(cqe->res, res); - WRITE_ONCE(cqe->flags, cflags); - } else if (ctx->cq_overflow_flushed || - atomic_read(&req->task->io_uring->in_idle)) { - /* - * If we're in ring overflow flush mode, or in task cancel mode, - * then we cannot store the request for later flushing, we need - * to drop it on the floor. - */ - ctx->cached_cq_overflow++; - WRITE_ONCE(ctx->rings->cq_overflow, ctx->cached_cq_overflow); + if (likely(task == current)) { + tctx->cached_refs += nr; } else { - if (list_empty(&ctx->cq_overflow_list)) { - set_bit(0, &ctx->sq_check_overflow); - set_bit(0, &ctx->cq_check_overflow); - ctx->rings->sq_flags |= IORING_SQ_CQ_OVERFLOW; - } - io_clean_op(req); - req->result = res; - req->compl.cflags = cflags; - refcount_inc(&req->refs); - list_add_tail(&req->compl.list, &ctx->cq_overflow_list); + percpu_counter_sub(&tctx->inflight, nr); + if (unlikely(atomic_read(&tctx->in_idle))) + wake_up(&tctx->wait); + put_task_struct_many(task, nr); } } -static void io_cqring_fill_event(struct io_kiocb *req, long res) +static void io_task_refs_refill(struct io_uring_task *tctx) { - __io_cqring_fill_event(req, res, 0); + unsigned int refill = -tctx->cached_refs + IO_TCTX_REFS_CACHE_NR; + + percpu_counter_add(&tctx->inflight, refill); + refcount_add(refill, ¤t->usage); + tctx->cached_refs += refill; } -static void io_cqring_add_event(struct io_kiocb *req, long res, long cflags) +static inline void io_get_task_refs(int nr) { - struct io_ring_ctx *ctx = req->ctx; - unsigned long flags; - - spin_lock_irqsave(&ctx->completion_lock, flags); - __io_cqring_fill_event(req, res, cflags); - io_commit_cqring(ctx); - spin_unlock_irqrestore(&ctx->completion_lock, flags); + struct io_uring_task *tctx = current->io_uring; - io_cqring_ev_posted(ctx); + tctx->cached_refs -= nr; + if (unlikely(tctx->cached_refs < 0)) + io_task_refs_refill(tctx); } -static void io_submit_flush_completions(struct io_comp_state *cs) +static __cold void io_uring_drop_tctx_refs(struct task_struct *task) { - struct io_ring_ctx *ctx = cs->ctx; + struct io_uring_task *tctx = task->io_uring; + unsigned int refs = tctx->cached_refs; - spin_lock_irq(&ctx->completion_lock); - while (!list_empty(&cs->list)) { - struct io_kiocb *req; + if (refs) { + tctx->cached_refs = 0; + percpu_counter_sub(&tctx->inflight, refs); + put_task_struct_many(task, refs); + } +} - req = list_first_entry(&cs->list, struct io_kiocb, compl.list); - list_del(&req->compl.list); - __io_cqring_fill_event(req, req->result, req->compl.cflags); +static bool io_cqring_event_overflow(struct io_ring_ctx *ctx, u64 user_data, + s32 res, u32 cflags) +{ + struct io_overflow_cqe *ocqe; + ocqe = kmalloc(sizeof(*ocqe), GFP_ATOMIC | __GFP_ACCOUNT); + if (!ocqe) { /* - * io_free_req() doesn't care about completion_lock unless one - * of these flags is set. REQ_F_WORK_INITIALIZED is in the list - * because of a potential deadlock with req->work.fs->lock + * If we're in ring overflow flush mode, or in task cancel mode, + * or cannot allocate an overflow entry, then we need to drop it + * on the floor. */ - if (req->flags & (REQ_F_FAIL_LINK|REQ_F_LINK_TIMEOUT - |REQ_F_WORK_INITIALIZED)) { - spin_unlock_irq(&ctx->completion_lock); - io_put_req(req); - spin_lock_irq(&ctx->completion_lock); - } else { - io_put_req(req); - } + io_account_cq_overflow(ctx); + return false; } - io_commit_cqring(ctx); - spin_unlock_irq(&ctx->completion_lock); + if (list_empty(&ctx->cq_overflow_list)) { + set_bit(0, &ctx->check_cq_overflow); + WRITE_ONCE(ctx->rings->sq_flags, + ctx->rings->sq_flags | IORING_SQ_CQ_OVERFLOW); - io_cqring_ev_posted(ctx); - cs->nr = 0; + } + ocqe->cqe.user_data = user_data; + ocqe->cqe.res = res; + ocqe->cqe.flags = cflags; + list_add_tail(&ocqe->list, &ctx->cq_overflow_list); + return true; } -static void __io_req_complete(struct io_kiocb *req, long res, unsigned cflags, - struct io_comp_state *cs) +static inline bool __io_fill_cqe(struct io_ring_ctx *ctx, u64 user_data, + s32 res, u32 cflags) { - if (!cs) { - io_cqring_add_event(req, res, cflags); - io_put_req(req); - } else { - io_clean_op(req); - req->result = res; - req->compl.cflags = cflags; - list_add_tail(&req->compl.list, &cs->list); - if (++cs->nr >= 32) - io_submit_flush_completions(cs); + struct io_uring_cqe *cqe; + + trace_io_uring_complete(ctx, user_data, res, cflags); + + /* + * If we can't get a cq entry, userspace overflowed the + * submission (by quite a lot). Increment the overflow count in + * the ring. + */ + cqe = io_get_cqe(ctx); + if (likely(cqe)) { + WRITE_ONCE(cqe->user_data, user_data); + WRITE_ONCE(cqe->res, res); + WRITE_ONCE(cqe->flags, cflags); + return true; } + return io_cqring_event_overflow(ctx, user_data, res, cflags); } -static void io_req_complete(struct io_kiocb *req, long res) +static noinline void io_fill_cqe_req(struct io_kiocb *req, s32 res, u32 cflags) { - __io_req_complete(req, res, 0, NULL); + __io_fill_cqe(req->ctx, req->user_data, res, cflags); } -static inline bool io_is_fallback_req(struct io_kiocb *req) +static noinline bool io_fill_cqe_aux(struct io_ring_ctx *ctx, u64 user_data, + s32 res, u32 cflags) { - return req == (struct io_kiocb *) - ((unsigned long) req->ctx->fallback_req & ~1UL); + ctx->cq_extra++; + return __io_fill_cqe(ctx, user_data, res, cflags); } -static struct io_kiocb *io_get_fallback_req(struct io_ring_ctx *ctx) +static void io_req_complete_post(struct io_kiocb *req, s32 res, + u32 cflags) { - struct io_kiocb *req; - - req = ctx->fallback_req; - if (!test_and_set_bit_lock(0, (unsigned long *) &ctx->fallback_req)) - return req; + struct io_ring_ctx *ctx = req->ctx; - return NULL; + spin_lock(&ctx->completion_lock); + __io_fill_cqe(ctx, req->user_data, res, cflags); + /* + * If we're the last reference to this request, add to our locked + * free_list cache. + */ + if (req_ref_put_and_test(req)) { + if (req->flags & (REQ_F_LINK | REQ_F_HARDLINK)) { + if (req->flags & IO_DISARM_MASK) + io_disarm_next(req); + if (req->link) { + io_req_task_queue(req->link); + req->link = NULL; + } + } + io_dismantle_req(req); + io_put_task(req->task, 1); + list_add(&req->inflight_entry, &ctx->locked_free_list); + ctx->locked_free_nr++; + } else { + if (!percpu_ref_tryget(&ctx->refs)) + req = NULL; + } + io_commit_cqring(ctx); + spin_unlock(&ctx->completion_lock); + + if (req) { + io_cqring_ev_posted(ctx); + percpu_ref_put(&ctx->refs); + } } -static struct io_kiocb *io_alloc_req(struct io_ring_ctx *ctx, - struct io_submit_state *state) +static inline bool io_req_needs_clean(struct io_kiocb *req) { - if (!state->free_reqs) { - gfp_t gfp = GFP_KERNEL | __GFP_NOWARN; - size_t sz; - int ret; + return req->flags & IO_REQ_CLEAN_FLAGS; +} + +static inline void io_req_complete_state(struct io_kiocb *req, s32 res, + u32 cflags) +{ + if (io_req_needs_clean(req)) + io_clean_op(req); + req->result = res; + req->compl.cflags = cflags; + req->flags |= REQ_F_COMPLETE_INLINE; +} - sz = min_t(size_t, state->ios_left, ARRAY_SIZE(state->reqs)); - ret = kmem_cache_alloc_bulk(req_cachep, gfp, sz, state->reqs); +static inline void __io_req_complete(struct io_kiocb *req, unsigned issue_flags, + s32 res, u32 cflags) +{ + if (issue_flags & IO_URING_F_COMPLETE_DEFER) + io_req_complete_state(req, res, cflags); + else + io_req_complete_post(req, res, cflags); +} - /* - * Bulk alloc is all-or-nothing. If we fail to get a batch, - * retry single alloc to be on the safe side. - */ - if (unlikely(ret <= 0)) { - state->reqs[0] = kmem_cache_alloc(req_cachep, gfp); - if (!state->reqs[0]) - goto fallback; - ret = 1; - } - state->free_reqs = ret; +static inline void io_req_complete(struct io_kiocb *req, s32 res) +{ + __io_req_complete(req, 0, res, 0); +} + +static void io_req_complete_failed(struct io_kiocb *req, s32 res) +{ + req_set_fail(req); + io_req_complete_post(req, res, 0); +} + +static void io_req_complete_fail_submit(struct io_kiocb *req) +{ + /* + * We don't submit, fail them all, for that replace hardlinks with + * normal links. Extra REQ_F_LINK is tolerated. + */ + req->flags &= ~REQ_F_HARDLINK; + req->flags |= REQ_F_LINK; + io_req_complete_failed(req, req->result); +} + +/* + * Don't initialise the fields below on every allocation, but do that in + * advance and keep them valid across allocations. + */ +static void io_preinit_req(struct io_kiocb *req, struct io_ring_ctx *ctx) +{ + req->ctx = ctx; + req->link = NULL; + req->async_data = NULL; + /* not necessary, but safer to zero */ + req->result = 0; +} + +static void io_flush_cached_locked_reqs(struct io_ring_ctx *ctx, + struct io_submit_state *state) +{ + spin_lock(&ctx->completion_lock); + list_splice_init(&ctx->locked_free_list, &state->free_list); + ctx->locked_free_nr = 0; + spin_unlock(&ctx->completion_lock); +} + +/* Returns true IFF there are requests in the cache */ +static bool io_flush_cached_reqs(struct io_ring_ctx *ctx) +{ + struct io_submit_state *state = &ctx->submit_state; + int nr; + + /* + * If we have more than a batch's worth of requests in our IRQ side + * locked cache, grab the lock and move them over to our submission + * side cache. + */ + if (READ_ONCE(ctx->locked_free_nr) > IO_COMPL_BATCH) + io_flush_cached_locked_reqs(ctx, state); + + nr = state->free_reqs; + while (!list_empty(&state->free_list)) { + struct io_kiocb *req = list_first_entry(&state->free_list, + struct io_kiocb, inflight_entry); + + list_del(&req->inflight_entry); + state->reqs[nr++] = req; + if (nr == ARRAY_SIZE(state->reqs)) + break; + } + + state->free_reqs = nr; + return nr != 0; +} + +/* + * A request might get retired back into the request caches even before opcode + * handlers and io_issue_sqe() are done with it, e.g. inline completion path. + * Because of that, io_alloc_req() should be called only under ->uring_lock + * and with extra caution to not get a request that is still worked on. + */ +static struct io_kiocb *io_alloc_req(struct io_ring_ctx *ctx) + __must_hold(&ctx->uring_lock) +{ + struct io_submit_state *state = &ctx->submit_state; + gfp_t gfp = GFP_KERNEL | __GFP_NOWARN; + int ret, i; + + BUILD_BUG_ON(ARRAY_SIZE(state->reqs) < IO_REQ_ALLOC_BATCH); + + if (likely(state->free_reqs || io_flush_cached_reqs(ctx))) + goto got_req; + + ret = kmem_cache_alloc_bulk(req_cachep, gfp, IO_REQ_ALLOC_BATCH, + state->reqs); + + /* + * Bulk alloc is all-or-nothing. If we fail to get a batch, + * retry single alloc to be on the safe side. + */ + if (unlikely(ret <= 0)) { + state->reqs[0] = kmem_cache_alloc(req_cachep, gfp); + if (!state->reqs[0]) + return NULL; + ret = 1; } + for (i = 0; i < ret; i++) + io_preinit_req(state->reqs[i], ctx); + state->free_reqs = ret; +got_req: state->free_reqs--; return state->reqs[state->free_reqs]; -fallback: - return io_get_fallback_req(ctx); } -static inline void io_put_file(struct io_kiocb *req, struct file *file, - bool fixed) +static inline void io_put_file(struct file *file) { - if (fixed) - percpu_ref_put(req->fixed_file_refs); - else + if (file) fput(file); } static void io_dismantle_req(struct io_kiocb *req) { - io_clean_op(req); + unsigned int flags = req->flags; - if (req->async_data) + if (io_req_needs_clean(req)) + io_clean_op(req); + if (!(flags & REQ_F_FIXED_FILE)) + io_put_file(req->file); + if (req->fixed_rsrc_refs) + percpu_ref_put(req->fixed_rsrc_refs); + if (req->async_data) { kfree(req->async_data); - if (req->file) - io_put_file(req, req->file, (req->flags & REQ_F_FIXED_FILE)); - - io_req_clean_work(req); + req->async_data = NULL; + } } static void __io_free_req(struct io_kiocb *req) { - struct io_uring_task *tctx = req->task->io_uring; struct io_ring_ctx *ctx = req->ctx; io_dismantle_req(req); + io_put_task(req->task, 1); - percpu_counter_dec(&tctx->inflight); - if (atomic_read(&tctx->in_idle)) - wake_up(&tctx->wait); - put_task_struct(req->task); + spin_lock(&ctx->completion_lock); + list_add(&req->inflight_entry, &ctx->locked_free_list); + ctx->locked_free_nr++; + spin_unlock(&ctx->completion_lock); - if (likely(!io_is_fallback_req(req))) - kmem_cache_free(req_cachep, req); - else - clear_bit_unlock(0, (unsigned long *) &ctx->fallback_req); percpu_ref_put(&ctx->refs); } -static void io_kill_linked_timeout(struct io_kiocb *req) +static inline void io_remove_next_linked(struct io_kiocb *req) { - struct io_ring_ctx *ctx = req->ctx; - struct io_kiocb *link; - bool cancelled = false; - unsigned long flags; - - spin_lock_irqsave(&ctx->completion_lock, flags); - link = list_first_entry_or_null(&req->link_list, struct io_kiocb, - link_list); - /* - * Can happen if a linked timeout fired and link had been like - * req -> link t-out -> link t-out [-> ...] - */ - if (link && (link->flags & REQ_F_LTIMEOUT_ACTIVE)) { - struct io_timeout_data *io = link->async_data; - int ret; - - list_del_init(&link->link_list); - ret = hrtimer_try_to_cancel(&io->timer); - if (ret != -1) { - io_cqring_fill_event(link, -ECANCELED); - io_commit_cqring(ctx); - cancelled = true; - } - } - req->flags &= ~REQ_F_LINK_TIMEOUT; - spin_unlock_irqrestore(&ctx->completion_lock, flags); + struct io_kiocb *nxt = req->link; - if (cancelled) { - io_cqring_ev_posted(ctx); - io_put_req(link); - } + req->link = nxt->link; + nxt->link = NULL; } -static struct io_kiocb *io_req_link_next(struct io_kiocb *req) +static bool io_kill_linked_timeout(struct io_kiocb *req) + __must_hold(&req->ctx->completion_lock) + __must_hold(&req->ctx->timeout_lock) { - struct io_kiocb *nxt; + struct io_kiocb *link = req->link; - /* - * The list should never be empty when we are called here. But could - * potentially happen if the chain is messed up, check to be on the - * safe side. - */ - if (unlikely(list_empty(&req->link_list))) - return NULL; + if (link && link->opcode == IORING_OP_LINK_TIMEOUT) { + struct io_timeout_data *io = link->async_data; - nxt = list_first_entry(&req->link_list, struct io_kiocb, link_list); - list_del_init(&req->link_list); - if (!list_empty(&nxt->link_list)) - nxt->flags |= REQ_F_LINK_HEAD; - return nxt; + io_remove_next_linked(req); + link->timeout.head = NULL; + if (hrtimer_try_to_cancel(&io->timer) != -1) { + list_del(&link->timeout.list); + io_fill_cqe_req(link, -ECANCELED, 0); + io_put_req_deferred(link); + return true; + } + } + return false; } -/* - * Called if REQ_F_LINK_HEAD is set, and we fail the head request - */ static void io_fail_links(struct io_kiocb *req) + __must_hold(&req->ctx->completion_lock) { - struct io_ring_ctx *ctx = req->ctx; - unsigned long flags; + struct io_kiocb *nxt, *link = req->link; - spin_lock_irqsave(&ctx->completion_lock, flags); - while (!list_empty(&req->link_list)) { - struct io_kiocb *link = list_first_entry(&req->link_list, - struct io_kiocb, link_list); + req->link = NULL; + while (link) { + long res = -ECANCELED; - list_del_init(&link->link_list); - trace_io_uring_fail_link(req, link); + if (link->flags & REQ_F_FAIL) + res = link->result; - io_cqring_fill_event(link, -ECANCELED); + nxt = link->link; + link->link = NULL; - /* - * It's ok to free under spinlock as they're not linked anymore, - * but avoid REQ_F_WORK_INITIALIZED because it may deadlock on - * work.fs->lock. - */ - if (link->flags & REQ_F_WORK_INITIALIZED) - io_put_req_deferred(link, 2); - else - io_double_put_req(link); + trace_io_uring_fail_link(req, link); + io_fill_cqe_req(link, res, 0); + io_put_req_deferred(link); + link = nxt; } +} - io_commit_cqring(ctx); - spin_unlock_irqrestore(&ctx->completion_lock, flags); +static bool io_disarm_next(struct io_kiocb *req) + __must_hold(&req->ctx->completion_lock) +{ + bool posted = false; - io_cqring_ev_posted(ctx); + if (req->flags & REQ_F_ARM_LTIMEOUT) { + struct io_kiocb *link = req->link; + + req->flags &= ~REQ_F_ARM_LTIMEOUT; + if (link && link->opcode == IORING_OP_LINK_TIMEOUT) { + io_remove_next_linked(req); + io_fill_cqe_req(link, -ECANCELED, 0); + io_put_req_deferred(link); + posted = true; + } + } else if (req->flags & REQ_F_LINK_TIMEOUT) { + struct io_ring_ctx *ctx = req->ctx; + + spin_lock_irq(&ctx->timeout_lock); + posted = io_kill_linked_timeout(req); + spin_unlock_irq(&ctx->timeout_lock); + } + if (unlikely((req->flags & REQ_F_FAIL) && + !(req->flags & REQ_F_HARDLINK))) { + posted |= (req->link != NULL); + io_fail_links(req); + } + return posted; } static struct io_kiocb *__io_req_find_next(struct io_kiocb *req) { - req->flags &= ~REQ_F_LINK_HEAD; - if (req->flags & REQ_F_LINK_TIMEOUT) - io_kill_linked_timeout(req); + struct io_kiocb *nxt; /* * If LINK is set, we have dependent requests in this chain. If we @@ -2033,28 +2132,112 @@ static struct io_kiocb *__io_req_find_next(struct io_kiocb *req) * dependencies to the next request. In case of failure, fail the rest * of the chain. */ - if (likely(!(req->flags & REQ_F_FAIL_LINK))) - return io_req_link_next(req); - io_fail_links(req); - return NULL; + if (req->flags & IO_DISARM_MASK) { + struct io_ring_ctx *ctx = req->ctx; + bool posted; + + spin_lock(&ctx->completion_lock); + posted = io_disarm_next(req); + if (posted) + io_commit_cqring(req->ctx); + spin_unlock(&ctx->completion_lock); + if (posted) + io_cqring_ev_posted(ctx); + } + nxt = req->link; + req->link = NULL; + return nxt; } -static struct io_kiocb *io_req_find_next(struct io_kiocb *req) +static inline struct io_kiocb *io_req_find_next(struct io_kiocb *req) { - if (likely(!(req->flags & REQ_F_LINK_HEAD))) + if (likely(!(req->flags & (REQ_F_LINK|REQ_F_HARDLINK)))) return NULL; return __io_req_find_next(req); } -static int io_req_task_work_add(struct io_kiocb *req, bool twa_signal_ok) +static void ctx_flush_and_put(struct io_ring_ctx *ctx, bool *locked) +{ + if (!ctx) + return; + if (*locked) { + if (ctx->submit_state.compl_nr) + io_submit_flush_completions(ctx); + mutex_unlock(&ctx->uring_lock); + *locked = false; + } + percpu_ref_put(&ctx->refs); +} + +static void tctx_task_work(struct callback_head *cb) +{ + bool locked = false; + struct io_ring_ctx *ctx = NULL; + struct io_uring_task *tctx = container_of(cb, struct io_uring_task, + task_work); + + while (1) { + struct io_wq_work_node *node; + + if (!tctx->task_list.first && locked && ctx->submit_state.compl_nr) + io_submit_flush_completions(ctx); + + spin_lock_irq(&tctx->task_lock); + node = tctx->task_list.first; + INIT_WQ_LIST(&tctx->task_list); + if (!node) + tctx->task_running = false; + spin_unlock_irq(&tctx->task_lock); + if (!node) + break; + + do { + struct io_wq_work_node *next = node->next; + struct io_kiocb *req = container_of(node, struct io_kiocb, + io_task_work.node); + + if (req->ctx != ctx) { + ctx_flush_and_put(ctx, &locked); + ctx = req->ctx; + /* if not contended, grab and improve batching */ + locked = mutex_trylock(&ctx->uring_lock); + percpu_ref_get(&ctx->refs); + } + req->io_task_work.func(req, &locked); + node = next; + } while (node); + + cond_resched(); + } + + ctx_flush_and_put(ctx, &locked); + + /* relaxed read is enough as only the task itself sets ->in_idle */ + if (unlikely(atomic_read(&tctx->in_idle))) + io_uring_drop_tctx_refs(current); +} + +static void io_req_task_work_add(struct io_kiocb *req) { struct task_struct *tsk = req->task; - struct io_ring_ctx *ctx = req->ctx; + struct io_uring_task *tctx = tsk->io_uring; enum task_work_notify_mode notify; - int ret; + struct io_wq_work_node *node; + unsigned long flags; + bool running; + + WARN_ON_ONCE(!tctx); - if (tsk->flags & PF_EXITING) - return -ESRCH; + spin_lock_irqsave(&tctx->task_lock, flags); + wq_list_add_tail(&req->io_task_work.node, &tctx->task_list); + running = tctx->task_running; + if (!running) + tctx->task_running = true; + spin_unlock_irqrestore(&tctx->task_lock, flags); + + /* task_work already pending, we're done */ + if (running) + return; /* * SQPOLL kernel thread doesn't need notification, just a wakeup. For @@ -2062,85 +2245,68 @@ static int io_req_task_work_add(struct io_kiocb *req, bool twa_signal_ok) * processing task_work. There's no reliable way to tell if TWA_RESUME * will do the job. */ - notify = TWA_NONE; - if (!(ctx->flags & IORING_SETUP_SQPOLL) && twa_signal_ok) - notify = TWA_SIGNAL; - - ret = task_work_add(tsk, &req->task_work, notify); - if (!ret) + notify = (req->ctx->flags & IORING_SETUP_SQPOLL) ? TWA_NONE : TWA_SIGNAL; + if (!task_work_add(tsk, &tctx->task_work, notify)) { wake_up_process(tsk); + return; + } - return ret; -} - -static void __io_req_task_cancel(struct io_kiocb *req, int error) -{ - struct io_ring_ctx *ctx = req->ctx; - - spin_lock_irq(&ctx->completion_lock); - io_cqring_fill_event(req, error); - io_commit_cqring(ctx); - spin_unlock_irq(&ctx->completion_lock); + spin_lock_irqsave(&tctx->task_lock, flags); + tctx->task_running = false; + node = tctx->task_list.first; + INIT_WQ_LIST(&tctx->task_list); + spin_unlock_irqrestore(&tctx->task_lock, flags); - io_cqring_ev_posted(ctx); - req_set_fail_links(req); - io_double_put_req(req); + while (node) { + req = container_of(node, struct io_kiocb, io_task_work.node); + node = node->next; + if (llist_add(&req->io_task_work.fallback_node, + &req->ctx->fallback_llist)) + schedule_delayed_work(&req->ctx->fallback_work, 1); + } } -static void io_req_task_cancel(struct callback_head *cb) +static void io_req_task_cancel(struct io_kiocb *req, bool *locked) { - struct io_kiocb *req = container_of(cb, struct io_kiocb, task_work); struct io_ring_ctx *ctx = req->ctx; - mutex_lock(&ctx->uring_lock); - __io_req_task_cancel(req, -ECANCELED); - mutex_unlock(&ctx->uring_lock); - percpu_ref_put(&ctx->refs); + /* not needed for normal modes, but SQPOLL depends on it */ + io_tw_lock(ctx, locked); + io_req_complete_failed(req, req->result); } -static void __io_req_task_submit(struct io_kiocb *req) +static void io_req_task_submit(struct io_kiocb *req, bool *locked) { struct io_ring_ctx *ctx = req->ctx; - mutex_lock(&ctx->uring_lock); - if (!ctx->sqo_dead && !__io_sq_thread_acquire_mm(ctx)) - __io_queue_sqe(req, NULL); + io_tw_lock(ctx, locked); + /* req->task == current here, checking PF_EXITING is safe */ + if (likely(!(req->task->flags & PF_EXITING))) + __io_queue_sqe(req); else - __io_req_task_cancel(req, -EFAULT); - mutex_unlock(&ctx->uring_lock); - - if (ctx->flags & IORING_SETUP_SQPOLL) - io_sq_thread_drop_mm(); + io_req_complete_failed(req, -EFAULT); } -static void io_req_task_submit(struct callback_head *cb) +static void io_req_task_queue_fail(struct io_kiocb *req, int ret) { - struct io_kiocb *req = container_of(cb, struct io_kiocb, task_work); - struct io_ring_ctx *ctx = req->ctx; - - __io_req_task_submit(req); - percpu_ref_put(&ctx->refs); + req->result = ret; + req->io_task_work.func = io_req_task_cancel; + io_req_task_work_add(req); } static void io_req_task_queue(struct io_kiocb *req) { - int ret; - - init_task_work(&req->task_work, io_req_task_submit); - percpu_ref_get(&req->ctx->refs); - - ret = io_req_task_work_add(req, true); - if (unlikely(ret)) { - struct task_struct *tsk; + req->io_task_work.func = io_req_task_submit; + io_req_task_work_add(req); +} - init_task_work(&req->task_work, io_req_task_cancel); - tsk = io_wq_get_task(req->ctx->io_wq); - task_work_add(tsk, &req->task_work, TWA_NONE); - wake_up_process(tsk); - } +static void io_req_task_queue_reissue(struct io_kiocb *req) +{ + req->io_task_work.func = io_queue_async_work; + io_req_task_work_add(req); } -static void io_queue_next(struct io_kiocb *req) +static inline void io_queue_next(struct io_kiocb *req) { struct io_kiocb *nxt = io_req_find_next(req); @@ -2154,153 +2320,118 @@ static void io_free_req(struct io_kiocb *req) __io_free_req(req); } -struct req_batch { - void *reqs[IO_IOPOLL_BATCH]; - int to_free; +static void io_free_req_work(struct io_kiocb *req, bool *locked) +{ + io_free_req(req); +} +struct req_batch { struct task_struct *task; int task_refs; + int ctx_refs; }; static inline void io_init_req_batch(struct req_batch *rb) { - rb->to_free = 0; rb->task_refs = 0; + rb->ctx_refs = 0; rb->task = NULL; } -static void __io_req_free_batch_flush(struct io_ring_ctx *ctx, - struct req_batch *rb) +static void io_req_free_batch_finish(struct io_ring_ctx *ctx, + struct req_batch *rb) { - kmem_cache_free_bulk(req_cachep, rb->to_free, rb->reqs); - percpu_ref_put_many(&ctx->refs, rb->to_free); - rb->to_free = 0; + if (rb->ctx_refs) + percpu_ref_put_many(&ctx->refs, rb->ctx_refs); + if (rb->task) + io_put_task(rb->task, rb->task_refs); } -static void io_req_free_batch_finish(struct io_ring_ctx *ctx, - struct req_batch *rb) +static void io_req_free_batch(struct req_batch *rb, struct io_kiocb *req, + struct io_submit_state *state) { - if (rb->to_free) - __io_req_free_batch_flush(ctx, rb); - if (rb->task) { - struct io_uring_task *tctx = rb->task->io_uring; + io_queue_next(req); + io_dismantle_req(req); - percpu_counter_sub(&tctx->inflight, rb->task_refs); - if (atomic_read(&tctx->in_idle)) - wake_up(&tctx->wait); - put_task_struct_many(rb->task, rb->task_refs); - rb->task = NULL; + if (req->task != rb->task) { + if (rb->task) + io_put_task(rb->task, rb->task_refs); + rb->task = req->task; + rb->task_refs = 0; } + rb->task_refs++; + rb->ctx_refs++; + + if (state->free_reqs != ARRAY_SIZE(state->reqs)) + state->reqs[state->free_reqs++] = req; + else + list_add(&req->inflight_entry, &state->free_list); } -static void io_req_free_batch(struct req_batch *rb, struct io_kiocb *req) +static void io_submit_flush_completions(struct io_ring_ctx *ctx) + __must_hold(&ctx->uring_lock) { - if (unlikely(io_is_fallback_req(req))) { - io_free_req(req); - return; + struct io_submit_state *state = &ctx->submit_state; + int i, nr = state->compl_nr; + struct req_batch rb; + + spin_lock(&ctx->completion_lock); + for (i = 0; i < nr; i++) { + struct io_kiocb *req = state->compl_reqs[i]; + + __io_fill_cqe(ctx, req->user_data, req->result, + req->compl.cflags); } - if (req->flags & REQ_F_LINK_HEAD) - io_queue_next(req); + io_commit_cqring(ctx); + spin_unlock(&ctx->completion_lock); + io_cqring_ev_posted(ctx); - if (req->task != rb->task) { - if (rb->task) { - struct io_uring_task *tctx = rb->task->io_uring; + io_init_req_batch(&rb); + for (i = 0; i < nr; i++) { + struct io_kiocb *req = state->compl_reqs[i]; - percpu_counter_sub(&tctx->inflight, rb->task_refs); - if (atomic_read(&tctx->in_idle)) - wake_up(&tctx->wait); - put_task_struct_many(rb->task, rb->task_refs); - } - rb->task = req->task; - rb->task_refs = 0; + if (req_ref_put_and_test(req)) + io_req_free_batch(&rb, req, &ctx->submit_state); } - rb->task_refs++; - io_dismantle_req(req); - rb->reqs[rb->to_free++] = req; - if (unlikely(rb->to_free == ARRAY_SIZE(rb->reqs))) - __io_req_free_batch_flush(req->ctx, rb); + io_req_free_batch_finish(ctx, &rb); + state->compl_nr = 0; } /* * Drop reference to request, return next in chain (if there is one) if this * was the last reference to this request. */ -static struct io_kiocb *io_put_req_find_next(struct io_kiocb *req) +static inline struct io_kiocb *io_put_req_find_next(struct io_kiocb *req) { struct io_kiocb *nxt = NULL; - if (refcount_dec_and_test(&req->refs)) { + if (req_ref_put_and_test(req)) { nxt = io_req_find_next(req); __io_free_req(req); } return nxt; } -static void io_put_req(struct io_kiocb *req) +static inline void io_put_req(struct io_kiocb *req) { - if (refcount_dec_and_test(&req->refs)) + if (req_ref_put_and_test(req)) io_free_req(req); } -static void io_put_req_deferred_cb(struct callback_head *cb) -{ - struct io_kiocb *req = container_of(cb, struct io_kiocb, task_work); - - io_free_req(req); -} - -static void io_free_req_deferred(struct io_kiocb *req) +static inline void io_put_req_deferred(struct io_kiocb *req) { - int ret; - - init_task_work(&req->task_work, io_put_req_deferred_cb); - ret = io_req_task_work_add(req, true); - if (unlikely(ret)) { - struct task_struct *tsk; - - tsk = io_wq_get_task(req->ctx->io_wq); - task_work_add(tsk, &req->task_work, TWA_NONE); - wake_up_process(tsk); + if (req_ref_put_and_test(req)) { + req->io_task_work.func = io_free_req_work; + io_req_task_work_add(req); } } -static inline void io_put_req_deferred(struct io_kiocb *req, int refs) -{ - if (refcount_sub_and_test(refs, &req->refs)) - io_free_req_deferred(req); -} - -static struct io_wq_work *io_steal_work(struct io_kiocb *req) -{ - struct io_kiocb *nxt; - - /* - * A ref is owned by io-wq in which context we're. So, if that's the - * last one, it's safe to steal next work. False negatives are Ok, - * it just will be re-punted async in io_put_work() - */ - if (refcount_read(&req->refs) != 1) - return NULL; - - nxt = io_req_find_next(req); - return nxt ? &nxt->work : NULL; -} - -static void io_double_put_req(struct io_kiocb *req) -{ - /* drop both submit and complete references */ - if (refcount_sub_and_test(2, &req->refs)) - io_free_req(req); -} - static unsigned io_cqring_events(struct io_ring_ctx *ctx) { - struct io_rings *rings = ctx->rings; - /* See comment at the top of this file */ smp_rmb(); - return ctx->cached_cq_tail - READ_ONCE(rings->cq.head); + return __io_cqring_events(ctx); } static inline unsigned int io_sqring_entries(struct io_ring_ctx *ctx) @@ -2326,38 +2457,23 @@ static inline unsigned int io_put_rw_kbuf(struct io_kiocb *req) { struct io_buffer *kbuf; + if (likely(!(req->flags & REQ_F_BUFFER_SELECTED))) + return 0; kbuf = (struct io_buffer *) (unsigned long) req->rw.addr; return io_put_kbuf(req, kbuf); } static inline bool io_run_task_work(void) { - /* - * Not safe to run on exiting task, and the task_work handling will - * not add work to such a task. - */ - if (unlikely(current->flags & PF_EXITING)) - return false; - if (current->task_works) { + if (test_thread_flag(TIF_NOTIFY_SIGNAL) || current->task_works) { __set_current_state(TASK_RUNNING); - task_work_run(); + tracehook_notify_signal(); return true; } return false; } -static void io_iopoll_queue(struct list_head *again) -{ - struct io_kiocb *req; - - do { - req = list_first_entry(again, struct io_kiocb, iopoll_entry); - list_del(&req->iopoll_entry); - __io_complete_rw(req, -EAGAIN, 0, NULL); - } while (!list_empty(again)); -} - /* * Find and free completed poll iocbs */ @@ -2366,41 +2482,25 @@ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events, { struct req_batch rb; struct io_kiocb *req; - LIST_HEAD(again); /* order with ->result store in io_complete_rw_iopoll() */ smp_rmb(); io_init_req_batch(&rb); while (!list_empty(done)) { - int cflags = 0; - - req = list_first_entry(done, struct io_kiocb, iopoll_entry); - if (READ_ONCE(req->result) == -EAGAIN) { - req->result = 0; - req->iopoll_completed = 0; - list_move_tail(&req->iopoll_entry, &again); - continue; - } - list_del(&req->iopoll_entry); + req = list_first_entry(done, struct io_kiocb, inflight_entry); + list_del(&req->inflight_entry); - if (req->flags & REQ_F_BUFFER_SELECTED) - cflags = io_put_rw_kbuf(req); - - __io_cqring_fill_event(req, req->result, cflags); + io_fill_cqe_req(req, req->result, io_put_rw_kbuf(req)); (*nr_events)++; - if (refcount_dec_and_test(&req->refs)) - io_req_free_batch(&rb, req); + if (req_ref_put_and_test(req)) + io_req_free_batch(&rb, req, &ctx->submit_state); } io_commit_cqring(ctx); - if (ctx->flags & IORING_SETUP_SQPOLL) - io_cqring_ev_posted(ctx); + io_cqring_ev_posted_iopoll(ctx); io_req_free_batch_finish(ctx, &rb); - - if (!list_empty(&again)) - io_iopoll_queue(&again); } static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events, @@ -2409,17 +2509,16 @@ static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events, struct io_kiocb *req, *tmp; LIST_HEAD(done); bool spin; - int ret; /* * Only spin for completions if we don't have multiple devices hanging * off our complete list, and we're under the requested amount. */ - spin = !ctx->poll_multi_file && *nr_events < min; + spin = !ctx->poll_multi_queue && *nr_events < min; - ret = 0; - list_for_each_entry_safe(req, tmp, &ctx->iopoll_list, iopoll_entry) { + list_for_each_entry_safe(req, tmp, &ctx->iopoll_list, inflight_entry) { struct kiocb *kiocb = &req->rw.kiocb; + int ret; /* * Move completed and retryable entries to our local lists. @@ -2427,50 +2526,27 @@ static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events, * and complete those lists first, if we have entries there. */ if (READ_ONCE(req->iopoll_completed)) { - list_move_tail(&req->iopoll_entry, &done); + list_move_tail(&req->inflight_entry, &done); continue; } if (!list_empty(&done)) break; ret = kiocb->ki_filp->f_op->iopoll(kiocb, spin); - if (ret < 0) - break; + if (unlikely(ret < 0)) + return ret; + else if (ret) + spin = false; /* iopoll may have completed current req */ if (READ_ONCE(req->iopoll_completed)) - list_move_tail(&req->iopoll_entry, &done); - - if (ret && spin) - spin = false; - ret = 0; + list_move_tail(&req->inflight_entry, &done); } if (!list_empty(&done)) io_iopoll_complete(ctx, nr_events, &done); - return ret; -} - -/* - * Poll for a minimum of 'min' events. Note that if min == 0 we consider that a - * non-spinning poll check - we'll still enter the driver poll loop, but only - * as a non-spinning completion check. - */ -static int io_iopoll_getevents(struct io_ring_ctx *ctx, unsigned int *nr_events, - long min) -{ - while (!list_empty(&ctx->iopoll_list) && !need_resched()) { - int ret; - - ret = io_do_iopoll(ctx, nr_events, min); - if (ret < 0) - return ret; - if (*nr_events >= min) - return 0; - } - - return 1; + return 0; } /* @@ -2508,7 +2584,7 @@ static void io_iopoll_try_reap_events(struct io_ring_ctx *ctx) static int io_iopoll_check(struct io_ring_ctx *ctx, long min) { unsigned int nr_events = 0; - int iters = 0, ret = 0; + int ret = 0; /* * We disallow the app entering submit/complete with polling, but we @@ -2516,17 +2592,16 @@ static int io_iopoll_check(struct io_ring_ctx *ctx, long min) * that got punted to a workqueue. */ mutex_lock(&ctx->uring_lock); + /* + * Don't enter poll loop if we already have events pending. + * If we do, we can potentially be spinning for commands that + * already triggered a CQE (eg in error). + */ + if (test_bit(0, &ctx->check_cq_overflow)) + __io_cqring_overflow_flush(ctx, false); + if (io_cqring_events(ctx)) + goto out; do { - /* - * Don't enter poll loop if we already have events pending. - * If we do, we can potentially be spinning for commands that - * already triggered a CQE (eg in error). - */ - if (test_bit(0, &ctx->cq_check_overflow)) - __io_cqring_overflow_flush(ctx, false, NULL, NULL); - if (io_cqring_events(ctx)) - break; - /* * If a submit got punted to a workqueue, we can have the * application entering polling for a command before it gets @@ -2537,18 +2612,21 @@ static int io_iopoll_check(struct io_ring_ctx *ctx, long min) * forever, while the workqueue is stuck trying to acquire the * very same mutex. */ - if (!(++iters & 7)) { + if (list_empty(&ctx->iopoll_list)) { + u32 tail = ctx->cached_cq_tail; + mutex_unlock(&ctx->uring_lock); io_run_task_work(); mutex_lock(&ctx->uring_lock); - } - - ret = io_iopoll_getevents(ctx, &nr_events, min); - if (ret <= 0) - break; - ret = 0; - } while (min && !nr_events && !need_resched()); + /* some requests don't go through iopoll_list */ + if (tail != ctx->cached_cq_tail || + list_empty(&ctx->iopoll_list)) + break; + } + ret = io_do_iopoll(ctx, &nr_events, min); + } while (!ret && nr_events < min && !need_resched()); +out: mutex_unlock(&ctx->uring_lock); return ret; } @@ -2560,79 +2638,129 @@ static void kiocb_end_write(struct io_kiocb *req) * thread. */ if (req->flags & REQ_F_ISREG) { - struct inode *inode = file_inode(req->file); + struct super_block *sb = file_inode(req->file)->i_sb; - __sb_writers_acquired(inode->i_sb, SB_FREEZE_WRITE); + __sb_writers_acquired(sb, SB_FREEZE_WRITE); + sb_end_write(sb); } - file_end_write(req->file); -} - -static void io_complete_rw_common(struct kiocb *kiocb, long res, - struct io_comp_state *cs) -{ - struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw.kiocb); - int cflags = 0; - - if (kiocb->ki_flags & IOCB_WRITE) - kiocb_end_write(req); - - if (res != req->result) - req_set_fail_links(req); - if (req->flags & REQ_F_BUFFER_SELECTED) - cflags = io_put_rw_kbuf(req); - __io_req_complete(req, res, cflags, cs); } #ifdef CONFIG_BLOCK -static bool io_resubmit_prep(struct io_kiocb *req, int error) +static bool io_resubmit_prep(struct io_kiocb *req) { - req_set_fail_links(req); - return false; + struct io_async_rw *rw = req->async_data; + + if (!rw) + return !io_req_prep_async(req); + iov_iter_restore(&rw->iter, &rw->iter_state); + return true; } -#endif -static bool io_rw_reissue(struct io_kiocb *req, long res) +static bool io_rw_should_reissue(struct io_kiocb *req) { -#ifdef CONFIG_BLOCK umode_t mode = file_inode(req->file)->i_mode; - int ret; + struct io_ring_ctx *ctx = req->ctx; if (!S_ISBLK(mode) && !S_ISREG(mode)) return false; - if ((res != -EAGAIN && res != -EOPNOTSUPP) || io_wq_current_is_worker()) + if ((req->flags & REQ_F_NOWAIT) || (io_wq_current_is_worker() && + !(ctx->flags & IORING_SETUP_IOPOLL))) return false; /* * If ref is dying, we might be running poll reap from the exit work. * Don't attempt to reissue from that path, just let it fail with * -EAGAIN. */ - if (percpu_ref_is_dying(&req->ctx->refs)) + if (percpu_ref_is_dying(&ctx->refs)) + return false; + /* + * Play it safe and assume not safe to re-import and reissue if we're + * not in the original thread group (or in task context). + */ + if (!same_thread_group(req->task, current) || !in_task()) return false; + return true; +} +#else +static bool io_resubmit_prep(struct io_kiocb *req) +{ + return false; +} +static bool io_rw_should_reissue(struct io_kiocb *req) +{ + return false; +} +#endif + +static bool __io_complete_rw_common(struct io_kiocb *req, long res) +{ + if (req->rw.kiocb.ki_flags & IOCB_WRITE) { + kiocb_end_write(req); + fsnotify_modify(req->file); + } else { + fsnotify_access(req->file); + } + if (res != req->result) { + if ((res == -EAGAIN || res == -EOPNOTSUPP) && + io_rw_should_reissue(req)) { + req->flags |= REQ_F_REISSUE; + return true; + } + req_set_fail(req); + req->result = res; + } + return false; +} - ret = io_sq_thread_acquire_mm(req->ctx, req); +static inline int io_fixup_rw_res(struct io_kiocb *req, unsigned res) +{ + struct io_async_rw *io = req->async_data; - if (io_resubmit_prep(req, ret)) { - refcount_inc(&req->refs); - io_queue_async_work(req); - return true; + /* add previously done IO, if any */ + if (io && io->bytes_done > 0) { + if (res < 0) + res = io->bytes_done; + else + res += io->bytes_done; } + return res; +} -#endif - return false; +static void io_req_task_complete(struct io_kiocb *req, bool *locked) +{ + unsigned int cflags = io_put_rw_kbuf(req); + int res = req->result; + + if (*locked) { + struct io_ring_ctx *ctx = req->ctx; + struct io_submit_state *state = &ctx->submit_state; + + io_req_complete_state(req, res, cflags); + state->compl_reqs[state->compl_nr++] = req; + if (state->compl_nr == ARRAY_SIZE(state->compl_reqs)) + io_submit_flush_completions(ctx); + } else { + io_req_complete_post(req, res, cflags); + } } static void __io_complete_rw(struct io_kiocb *req, long res, long res2, - struct io_comp_state *cs) + unsigned int issue_flags) { - if (!io_rw_reissue(req, res)) - io_complete_rw_common(&req->rw.kiocb, res, cs); + if (__io_complete_rw_common(req, res)) + return; + __io_req_complete(req, issue_flags, io_fixup_rw_res(req, res), io_put_rw_kbuf(req)); } static void io_complete_rw(struct kiocb *kiocb, long res, long res2) { struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw.kiocb); - __io_complete_rw(req, res, res2, NULL); + if (__io_complete_rw_common(req, res)) + return; + req->result = io_fixup_rw_res(req, res); + req->io_task_work.func = io_req_task_complete; + io_req_task_work_add(req); } static void io_complete_rw_iopoll(struct kiocb *kiocb, long res, long res2) @@ -2641,12 +2769,15 @@ static void io_complete_rw_iopoll(struct kiocb *kiocb, long res, long res2) if (kiocb->ki_flags & IOCB_WRITE) kiocb_end_write(req); - - if (res != -EAGAIN && res != req->result) - req_set_fail_links(req); + if (unlikely(res != req->result)) { + if (res == -EAGAIN && io_rw_should_reissue(req)) { + req->flags |= REQ_F_REISSUE; + return; + } + } WRITE_ONCE(req->result, res); - /* order with io_poll_complete() checking ->result */ + /* order with io_iopoll_complete() checking ->result */ smp_wmb(); WRITE_ONCE(req->iopoll_completed, 1); } @@ -2654,12 +2785,17 @@ static void io_complete_rw_iopoll(struct kiocb *kiocb, long res, long res2) /* * After the iocb has been issued, it's safe to be found on the poll list. * Adding the kiocb to the list AFTER submission ensures that we don't - * find it from a io_iopoll_getevents() thread before the issuer is done + * find it from a io_do_iopoll() thread before the issuer is done * accessing the kiocb cookie. */ static void io_iopoll_req_issued(struct io_kiocb *req) { struct io_ring_ctx *ctx = req->ctx; + const bool in_async = io_wq_current_is_worker(); + + /* workqueue context doesn't hold uring_lock, grab it now */ + if (unlikely(in_async)) + mutex_lock(&ctx->uring_lock); /* * Track whether we have multiple files in our lists. This will impact @@ -2667,14 +2803,22 @@ static void io_iopoll_req_issued(struct io_kiocb *req) * different devices. */ if (list_empty(&ctx->iopoll_list)) { - ctx->poll_multi_file = false; - } else if (!ctx->poll_multi_file) { + ctx->poll_multi_queue = false; + } else if (!ctx->poll_multi_queue) { struct io_kiocb *list_req; + unsigned int queue_num0, queue_num1; list_req = list_first_entry(&ctx->iopoll_list, struct io_kiocb, - iopoll_entry); - if (list_req->file != req->file) - ctx->poll_multi_file = true; + inflight_entry); + + if (list_req->file != req->file) { + ctx->poll_multi_queue = true; + } else { + queue_num0 = blk_qc_t_to_queue_num(list_req->rw.kiocb.ki_cookie); + queue_num1 = blk_qc_t_to_queue_num(req->rw.kiocb.ki_cookie); + if (queue_num0 != queue_num1) + ctx->poll_multi_queue = true; + } } /* @@ -2682,61 +2826,28 @@ static void io_iopoll_req_issued(struct io_kiocb *req) * it to the front so we find it first. */ if (READ_ONCE(req->iopoll_completed)) - list_add(&req->iopoll_entry, &ctx->iopoll_list); + list_add(&req->inflight_entry, &ctx->iopoll_list); else - list_add_tail(&req->iopoll_entry, &ctx->iopoll_list); - - if ((ctx->flags & IORING_SETUP_SQPOLL) && - wq_has_sleeper(&ctx->sq_data->wait)) - wake_up(&ctx->sq_data->wait); -} - -static void __io_state_file_put(struct io_submit_state *state) -{ - if (state->has_refs) - fput_many(state->file, state->has_refs); - state->file = NULL; -} + list_add_tail(&req->inflight_entry, &ctx->iopoll_list); -static inline void io_state_file_put(struct io_submit_state *state) -{ - if (state->file) - __io_state_file_put(state); -} - -/* - * Get as many references to a file as we have IOs left in this submission, - * assuming most submissions are for one file, or at least that each file - * has more than one submission. - */ -static struct file *__io_file_get(struct io_submit_state *state, int fd) -{ - if (!state) - return fget(fd); + if (unlikely(in_async)) { + /* + * If IORING_SETUP_SQPOLL is enabled, sqes are either handle + * in sq thread task context or in io worker task context. If + * current task context is sq thread, we don't need to check + * whether should wake up sq thread. + */ + if ((ctx->flags & IORING_SETUP_SQPOLL) && + wq_has_sleeper(&ctx->sq_data->wait)) + wake_up(&ctx->sq_data->wait); - if (state->file) { - if (state->fd == fd) { - state->has_refs--; - return state->file; - } - __io_state_file_put(state); + mutex_unlock(&ctx->uring_lock); } - state->file = fget_many(fd, state->ios_left); - if (!state->file) - return NULL; - - state->fd = fd; - state->has_refs = state->ios_left - 1; - return state->file; } static bool io_bdev_nowait(struct block_device *bdev) { -#ifdef CONFIG_BLOCK return !bdev || blk_queue_nowait(bdev_get_queue(bdev)); -#else - return true; -#endif } /* @@ -2744,19 +2855,21 @@ static bool io_bdev_nowait(struct block_device *bdev) * any file. For now, just ensure that anything potentially problematic is done * inline. */ -static bool io_file_supports_async(struct file *file, int rw) +static bool __io_file_supports_nowait(struct file *file, int rw) { umode_t mode = file_inode(file)->i_mode; if (S_ISBLK(mode)) { - if (io_bdev_nowait(file->f_inode->i_bdev)) + if (IS_ENABLED(CONFIG_BLOCK) && + io_bdev_nowait(I_BDEV(file->f_mapping->host))) return true; return false; } if (S_ISSOCK(mode)) return true; if (S_ISREG(mode)) { - if (io_bdev_nowait(file->f_inode->i_sb->s_bdev) && + if (IS_ENABLED(CONFIG_BLOCK) && + io_bdev_nowait(file->f_inode->i_sb->s_bdev) && file->f_op != &io_uring_fops) return true; return false; @@ -2775,20 +2888,36 @@ static bool io_file_supports_async(struct file *file, int rw) return file->f_op->write_iter != NULL; } -static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe) +static bool io_file_supports_nowait(struct io_kiocb *req, int rw) +{ + if (rw == READ && (req->flags & REQ_F_NOWAIT_READ)) + return true; + else if (rw == WRITE && (req->flags & REQ_F_NOWAIT_WRITE)) + return true; + + return __io_file_supports_nowait(req->file, rw); +} + +static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe, + int rw) { struct io_ring_ctx *ctx = req->ctx; struct kiocb *kiocb = &req->rw.kiocb; + struct file *file = req->file; unsigned ioprio; int ret; - if (S_ISREG(file_inode(req->file)->i_mode)) + if (!io_req_ffs_set(req) && S_ISREG(file_inode(file)->i_mode)) req->flags |= REQ_F_ISREG; kiocb->ki_pos = READ_ONCE(sqe->off); - if (kiocb->ki_pos == -1 && !(req->file->f_mode & FMODE_STREAM)) { - req->flags |= REQ_F_CUR_POS; - kiocb->ki_pos = req->file->f_pos; + if (kiocb->ki_pos == -1) { + if (!(file->f_mode & FMODE_STREAM)) { + req->flags |= REQ_F_CUR_POS; + kiocb->ki_pos = file->f_pos; + } else { + kiocb->ki_pos = 0; + } } kiocb->ki_hint = ki_hint_validate(file_write_hint(kiocb->ki_filp)); kiocb->ki_flags = iocb_flags(kiocb->ki_filp); @@ -2796,6 +2925,15 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe) if (unlikely(ret)) return ret; + /* + * If the file is marked O_NONBLOCK, still allow retry for it if it + * supports async. Otherwise it's impossible to use O_NONBLOCK files + * reliably. If not, or it IOCB_NOWAIT is set, don't retry. + */ + if ((kiocb->ki_flags & IOCB_NOWAIT) || + ((file->f_flags & O_NONBLOCK) && !io_file_supports_nowait(req, rw))) + req->flags |= REQ_F_NOWAIT; + ioprio = READ_ONCE(sqe->ioprio); if (ioprio) { ret = ioprio_check_cap(ioprio); @@ -2806,10 +2944,6 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe) } else kiocb->ki_ioprio = get_current_ioprio(); - /* don't allow async punt if RWF_NOWAIT was requested */ - if (kiocb->ki_flags & IOCB_NOWAIT) - req->flags |= REQ_F_NOWAIT; - if (ctx->flags & IORING_SETUP_IOPOLL) { if (!(kiocb->ki_flags & IOCB_DIRECT) || !kiocb->ki_filp->f_op->iopoll) @@ -2824,9 +2958,24 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe) kiocb->ki_complete = io_complete_rw; } + /* used for fixed read/write too - just read unconditionally */ + req->buf_index = READ_ONCE(sqe->buf_index); + req->imu = NULL; + + if (req->opcode == IORING_OP_READ_FIXED || + req->opcode == IORING_OP_WRITE_FIXED) { + struct io_ring_ctx *ctx = req->ctx; + u16 index; + + if (unlikely(req->buf_index >= ctx->nr_user_bufs)) + return -EFAULT; + index = array_index_nospec(req->buf_index, ctx->nr_user_bufs); + req->imu = ctx->user_bufs[index]; + io_req_set_rsrc_node(req); + } + req->rw.addr = READ_ONCE(sqe->addr); req->rw.len = READ_ONCE(sqe->len); - req->buf_index = READ_ONCE(sqe->buf_index); return 0; } @@ -2852,48 +3001,49 @@ static inline void io_rw_done(struct kiocb *kiocb, ssize_t ret) } static void kiocb_done(struct kiocb *kiocb, ssize_t ret, - struct io_comp_state *cs) + unsigned int issue_flags) { struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw.kiocb); - struct io_async_rw *io = req->async_data; - - /* add previously done IO, if any */ - if (io && io->bytes_done > 0) { - if (ret < 0) - ret = io->bytes_done; - else - ret += io->bytes_done; - } if (req->flags & REQ_F_CUR_POS) req->file->f_pos = kiocb->ki_pos; - if (ret >= 0 && kiocb->ki_complete == io_complete_rw) - __io_complete_rw(req, ret, 0, cs); + if (ret >= 0 && (kiocb->ki_complete == io_complete_rw)) + __io_complete_rw(req, ret, 0, issue_flags); else io_rw_done(kiocb, ret); + + if (req->flags & REQ_F_REISSUE) { + req->flags &= ~REQ_F_REISSUE; + if (io_resubmit_prep(req)) { + io_req_task_queue_reissue(req); + } else { + unsigned int cflags = io_put_rw_kbuf(req); + struct io_ring_ctx *ctx = req->ctx; + + ret = io_fixup_rw_res(req, ret); + req_set_fail(req); + if (!(issue_flags & IO_URING_F_NONBLOCK)) { + mutex_lock(&ctx->uring_lock); + __io_req_complete(req, issue_flags, ret, cflags); + mutex_unlock(&ctx->uring_lock); + } else { + __io_req_complete(req, issue_flags, ret, cflags); + } + } + } } -static ssize_t io_import_fixed(struct io_kiocb *req, int rw, - struct iov_iter *iter) +static int __io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter, + struct io_mapped_ubuf *imu) { - struct io_ring_ctx *ctx = req->ctx; size_t len = req->rw.len; - struct io_mapped_ubuf *imu; - u16 index, buf_index = req->buf_index; + u64 buf_end, buf_addr = req->rw.addr; size_t offset; - u64 buf_addr; - - if (unlikely(buf_index >= ctx->nr_user_bufs)) - return -EFAULT; - index = array_index_nospec(buf_index, ctx->nr_user_bufs); - imu = &ctx->user_bufs[index]; - buf_addr = req->rw.addr; - /* overflow */ - if (buf_addr + len < buf_addr) + if (unlikely(check_add_overflow(buf_addr, (u64)len, &buf_end))) return -EFAULT; /* not inside the mapped region */ - if (buf_addr < imu->ubuf || buf_addr + len > imu->ubuf + imu->len) + if (unlikely(buf_addr < imu->ubuf || buf_end > imu->ubuf_end)) return -EFAULT; /* @@ -2938,7 +3088,14 @@ static ssize_t io_import_fixed(struct io_kiocb *req, int rw, } } - return len; + return 0; +} + +static int io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter) +{ + if (WARN_ON_ONCE(!req->imu)) + return -EFAULT; + return __io_import_fixed(req, rw, iter, req->imu); } static void io_ring_submit_unlock(struct io_ring_ctx *ctx, bool needs_lock) @@ -3079,16 +3236,14 @@ static ssize_t io_iov_buffer_select(struct io_kiocb *req, struct iovec *iov, return __io_iov_buffer_select(req, iov, needs_lock); } -static ssize_t __io_import_iovec(int rw, struct io_kiocb *req, - struct iovec **iovec, struct iov_iter *iter, - bool needs_lock) +static int io_import_iovec(int rw, struct io_kiocb *req, struct iovec **iovec, + struct iov_iter *iter, bool needs_lock) { void __user *buf = u64_to_user_ptr(req->rw.addr); size_t sqe_len = req->rw.len; + u8 opcode = req->opcode; ssize_t ret; - u8 opcode; - opcode = req->opcode; if (opcode == IORING_OP_READ_FIXED || opcode == IORING_OP_WRITE_FIXED) { *iovec = NULL; return io_import_fixed(req, rw, iter); @@ -3113,10 +3268,8 @@ static ssize_t __io_import_iovec(int rw, struct io_kiocb *req, if (req->flags & REQ_F_BUFFER_SELECT) { ret = io_iov_buffer_select(req, *iovec, needs_lock); - if (!ret) { - ret = (*iovec)->iov_len; - iov_iter_init(iter, rw, *iovec, 1, ret); - } + if (!ret) + iov_iter_init(iter, rw, *iovec, 1, (*iovec)->iov_len); *iovec = NULL; return ret; } @@ -3125,18 +3278,6 @@ static ssize_t __io_import_iovec(int rw, struct io_kiocb *req, req->ctx->compat); } -static ssize_t io_import_iovec(int rw, struct io_kiocb *req, - struct iovec **iovec, struct iov_iter *iter, - bool needs_lock) -{ - struct io_async_rw *iorw = req->async_data; - - if (!iorw) - return __io_import_iovec(rw, req, iovec, iter, needs_lock); - *iovec = NULL; - return 0; -} - static inline loff_t *io_kiocb_ppos(struct kiocb *kiocb) { return (kiocb->ki_filp->f_mode & FMODE_STREAM) ? NULL : &kiocb->ki_pos; @@ -3229,32 +3370,31 @@ static void io_req_map_rw(struct io_kiocb *req, const struct iovec *iovec, } } -static inline int __io_alloc_async_data(struct io_kiocb *req) +static inline int io_alloc_async_data(struct io_kiocb *req) { WARN_ON_ONCE(!io_op_defs[req->opcode].async_size); req->async_data = kmalloc(io_op_defs[req->opcode].async_size, GFP_KERNEL); return req->async_data == NULL; } -static int io_alloc_async_data(struct io_kiocb *req) -{ - if (!io_op_defs[req->opcode].needs_async_data) - return 0; - - return __io_alloc_async_data(req); -} - static int io_setup_async_rw(struct io_kiocb *req, const struct iovec *iovec, const struct iovec *fast_iov, struct iov_iter *iter, bool force) { - if (!force && !io_op_defs[req->opcode].needs_async_data) + if (!force && !io_op_defs[req->opcode].needs_async_setup) return 0; if (!req->async_data) { - if (__io_alloc_async_data(req)) + struct io_async_rw *iorw; + + if (io_alloc_async_data(req)) { + kfree(iovec); return -ENOMEM; + } io_req_map_rw(req, iovec, fast_iov, iter); + iorw = req->async_data; + /* we've copied and mapped the iter, ensure state is saved */ + iov_iter_save_state(&iorw->iter, &iorw->iter_state); } return 0; } @@ -3263,9 +3403,9 @@ static inline int io_rw_prep_async(struct io_kiocb *req, int rw) { struct io_async_rw *iorw = req->async_data; struct iovec *iov = iorw->fast_iov; - ssize_t ret; + int ret; - ret = __io_import_iovec(rw, req, &iov, &iorw->iter, false); + ret = io_import_iovec(rw, req, &iov, &iorw->iter, false); if (unlikely(ret < 0)) return ret; @@ -3273,24 +3413,15 @@ static inline int io_rw_prep_async(struct io_kiocb *req, int rw) iorw->free_iovec = iov; if (iov) req->flags |= REQ_F_NEED_CLEANUP; + iov_iter_save_state(&iorw->iter, &iorw->iter_state); return 0; } static int io_read_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { - ssize_t ret; - - ret = io_prep_rw(req, sqe); - if (ret) - return ret; - if (unlikely(!(req->file->f_mode & FMODE_READ))) return -EBADF; - - /* either don't need iovec imported or already have it */ - if (!req->async_data) - return 0; - return io_rw_prep_async(req, READ); + return io_prep_rw(req, sqe, READ); } /* @@ -3309,7 +3440,6 @@ static int io_async_buf_func(struct wait_queue_entry *wait, unsigned mode, struct wait_page_queue *wpq; struct io_kiocb *req = wait->private; struct wait_page_key *key = arg; - int ret; wpq = container_of(wait, struct wait_page_queue, wait); @@ -3318,22 +3448,7 @@ static int io_async_buf_func(struct wait_queue_entry *wait, unsigned mode, req->rw.kiocb.ki_flags &= ~IOCB_WAITQ; list_del_init(&wait->entry); - - init_task_work(&req->task_work, io_req_task_submit); - percpu_ref_get(&req->ctx->refs); - - /* submit ref gets dropped, acquire a new one */ - refcount_inc(&req->refs); - ret = io_req_task_work_add(req, true); - if (unlikely(ret)) { - struct task_struct *tsk; - - /* queue just for cancelation */ - init_task_work(&req->task_work, io_req_task_cancel); - tsk = io_wq_get_task(req->ctx->io_wq); - task_work_add(tsk, &req->task_work, TWA_NONE); - wake_up_process(tsk); - } + io_req_task_queue(req); return 1; } @@ -3380,7 +3495,7 @@ static bool io_rw_should_retry(struct io_kiocb *req) return true; } -static int io_iter_do_read(struct io_kiocb *req, struct iov_iter *iter) +static inline int io_iter_do_read(struct io_kiocb *req, struct iov_iter *iter) { if (req->file->f_op->read_iter) return call_read_iter(req->file, &req->rw.kiocb, iter); @@ -3390,27 +3505,40 @@ static int io_iter_do_read(struct io_kiocb *req, struct iov_iter *iter) return -EINVAL; } -static int io_read(struct io_kiocb *req, bool force_nonblock, - struct io_comp_state *cs) +static bool need_read_all(struct io_kiocb *req) +{ + return req->flags & REQ_F_ISREG || + S_ISBLK(file_inode(req->file)->i_mode); +} + +static int io_read(struct io_kiocb *req, unsigned int issue_flags) { struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs; struct kiocb *kiocb = &req->rw.kiocb; struct iov_iter __iter, *iter = &__iter; - struct iov_iter iter_cp; struct io_async_rw *rw = req->async_data; - ssize_t io_size, ret, ret2; - bool no_async; + bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; + struct iov_iter_state __state, *state; + ssize_t ret, ret2; - if (rw) + if (rw) { iter = &rw->iter; - - ret = io_import_iovec(READ, req, &iovec, iter, !force_nonblock); - if (ret < 0) - return ret; - iter_cp = *iter; - io_size = iov_iter_count(iter); - req->result = io_size; - ret = 0; + state = &rw->iter_state; + /* + * We come here from an earlier attempt, restore our state to + * match in case it doesn't. It's cheap enough that we don't + * need to make this conditional. + */ + iov_iter_restore(iter, state); + iovec = NULL; + } else { + ret = io_import_iovec(READ, req, &iovec, iter, !force_nonblock); + if (ret < 0) + return ret; + state = &__state; + iov_iter_save_state(iter, state); + } + req->result = iov_iter_count(iter); /* Ensure we clear previously set non-block flag */ if (!force_nonblock) @@ -3418,127 +3546,130 @@ static int io_read(struct io_kiocb *req, bool force_nonblock, else kiocb->ki_flags |= IOCB_NOWAIT; - /* If the file doesn't support async, just async punt */ - no_async = force_nonblock && !io_file_supports_async(req->file, READ); - if (no_async) - goto copy_iov; + if (force_nonblock && !io_file_supports_nowait(req, READ)) { + ret = io_setup_async_rw(req, iovec, inline_vecs, iter, true); + return ret ?: -EAGAIN; + } - ret = rw_verify_area(READ, req->file, io_kiocb_ppos(kiocb), io_size); - if (unlikely(ret)) - goto out_free; + ret = rw_verify_area(READ, req->file, io_kiocb_ppos(kiocb), req->result); + if (unlikely(ret)) { + kfree(iovec); + return ret; + } ret = io_iter_do_read(req, iter); - if (!ret) { - goto done; - } else if (ret == -EIOCBQUEUED) { - ret = 0; - goto out_free; - } else if (ret == -EAGAIN) { + if (ret == -EAGAIN || (req->flags & REQ_F_REISSUE)) { + req->flags &= ~REQ_F_REISSUE; /* IOPOLL retry should happen for io-wq threads */ if (!force_nonblock && !(req->ctx->flags & IORING_SETUP_IOPOLL)) goto done; - /* no retry on NONBLOCK marked file */ - if (req->file->f_flags & O_NONBLOCK) + /* no retry on NONBLOCK nor RWF_NOWAIT */ + if (req->flags & REQ_F_NOWAIT) goto done; - /* some cases will consume bytes even on error returns */ - *iter = iter_cp; ret = 0; - goto copy_iov; - } else if (ret < 0) { - /* make sure -ERESTARTSYS -> -EINTR is done */ + } else if (ret == -EIOCBQUEUED) { + goto out_free; + } else if (ret <= 0 || ret == req->result || !force_nonblock || + (req->flags & REQ_F_NOWAIT) || !need_read_all(req)) { + /* read all, failed, already did sync or don't want to retry */ goto done; } - /* read it all, or we did blocking attempt. no retry. */ - if (!iov_iter_count(iter) || !force_nonblock || - (req->file->f_flags & O_NONBLOCK) || !(req->flags & REQ_F_ISREG)) - goto done; + /* + * Don't depend on the iter state matching what was consumed, or being + * untouched in case of error. Restore it and we'll advance it + * manually if we need to. + */ + iov_iter_restore(iter, state); - io_size -= ret; -copy_iov: ret2 = io_setup_async_rw(req, iovec, inline_vecs, iter, true); - if (ret2) { - ret = ret2; - goto out_free; - } - if (no_async) - return -EAGAIN; - rw = req->async_data; - /* it's copied and will be cleaned with ->io */ - iovec = NULL; - /* now use our persistent iterator, if we aren't already */ - iter = &rw->iter; -retry: - rw->bytes_done += ret; - /* if we can retry, do so with the callbacks armed */ - if (!io_rw_should_retry(req)) { - kiocb->ki_flags &= ~IOCB_WAITQ; - return -EAGAIN; - } + if (ret2) + return ret2; + iovec = NULL; + rw = req->async_data; /* - * Now retry read with the IOCB_WAITQ parts set in the iocb. If we - * get -EIOCBQUEUED, then we'll get a notification when the desired - * page gets unlocked. We can also get a partial read here, and if we - * do, then just retry at the new offset. + * Now use our persistent iterator and state, if we aren't already. + * We've restored and mapped the iter to match. */ - ret = io_iter_do_read(req, iter); - if (ret == -EIOCBQUEUED) { - ret = 0; - goto out_free; - } else if (ret > 0 && ret < io_size) { + if (iter != &rw->iter) { + iter = &rw->iter; + state = &rw->iter_state; + } + + do { + /* + * We end up here because of a partial read, either from + * above or inside this loop. Advance the iter by the bytes + * that were consumed. + */ + iov_iter_advance(iter, ret); + if (!iov_iter_count(iter)) + break; + rw->bytes_done += ret; + iov_iter_save_state(iter, state); + + /* if we can retry, do so with the callbacks armed */ + if (!io_rw_should_retry(req)) { + kiocb->ki_flags &= ~IOCB_WAITQ; + return -EAGAIN; + } + + req->result = iov_iter_count(iter); + /* + * Now retry read with the IOCB_WAITQ parts set in the iocb. If + * we get -EIOCBQUEUED, then we'll get a notification when the + * desired page gets unlocked. We can also get a partial read + * here, and if we do, then just retry at the new offset. + */ + ret = io_iter_do_read(req, iter); + if (ret == -EIOCBQUEUED) + return 0; /* we got some bytes, but not all. retry. */ kiocb->ki_flags &= ~IOCB_WAITQ; - goto retry; - } + iov_iter_restore(iter, state); + } while (ret > 0); done: - kiocb_done(kiocb, ret, cs); - ret = 0; + kiocb_done(kiocb, ret, issue_flags); out_free: - /* it's reportedly faster than delegating the null check to kfree() */ + /* it's faster to check here then delegate to kfree */ if (iovec) kfree(iovec); - return ret; + return 0; } static int io_write_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { - ssize_t ret; - - ret = io_prep_rw(req, sqe); - if (ret) - return ret; - if (unlikely(!(req->file->f_mode & FMODE_WRITE))) return -EBADF; - - /* either don't need iovec imported or already have it */ - if (!req->async_data) - return 0; - return io_rw_prep_async(req, WRITE); + return io_prep_rw(req, sqe, WRITE); } -static int io_write(struct io_kiocb *req, bool force_nonblock, - struct io_comp_state *cs) +static int io_write(struct io_kiocb *req, unsigned int issue_flags) { struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs; struct kiocb *kiocb = &req->rw.kiocb; struct iov_iter __iter, *iter = &__iter; - struct iov_iter iter_cp; struct io_async_rw *rw = req->async_data; - ssize_t ret, ret2, io_size; + bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; + struct iov_iter_state __state, *state; + ssize_t ret, ret2; - if (rw) + if (rw) { iter = &rw->iter; - - ret = io_import_iovec(WRITE, req, &iovec, iter, !force_nonblock); - if (ret < 0) - return ret; - iter_cp = *iter; - io_size = iov_iter_count(iter); - req->result = io_size; + state = &rw->iter_state; + iov_iter_restore(iter, state); + iovec = NULL; + } else { + ret = io_import_iovec(WRITE, req, &iovec, iter, !force_nonblock); + if (ret < 0) + return ret; + state = &__state; + iov_iter_save_state(iter, state); + } + req->result = iov_iter_count(iter); /* Ensure we clear previously set non-block flag */ if (!force_nonblock) @@ -3547,7 +3678,7 @@ static int io_write(struct io_kiocb *req, bool force_nonblock, kiocb->ki_flags |= IOCB_NOWAIT; /* If the file doesn't support async, just async punt */ - if (force_nonblock && !io_file_supports_async(req->file, WRITE)) + if (force_nonblock && !io_file_supports_nowait(req, WRITE)) goto copy_iov; /* file path doesn't support NOWAIT for non-direct_IO */ @@ -3555,7 +3686,7 @@ static int io_write(struct io_kiocb *req, bool force_nonblock, (req->flags & REQ_F_ISREG)) goto copy_iov; - ret = rw_verify_area(WRITE, req->file, io_kiocb_ppos(kiocb), io_size); + ret = rw_verify_area(WRITE, req->file, io_kiocb_ppos(kiocb), req->result); if (unlikely(ret)) goto out_free; @@ -3580,28 +3711,36 @@ static int io_write(struct io_kiocb *req, bool force_nonblock, else ret2 = -EINVAL; + if (req->flags & REQ_F_REISSUE) { + req->flags &= ~REQ_F_REISSUE; + ret2 = -EAGAIN; + } + /* * Raw bdev writes will return -EOPNOTSUPP for IOCB_NOWAIT. Just * retry them without IOCB_NOWAIT. */ if (ret2 == -EOPNOTSUPP && (kiocb->ki_flags & IOCB_NOWAIT)) ret2 = -EAGAIN; - /* no retry on NONBLOCK marked file */ - if (ret2 == -EAGAIN && (req->file->f_flags & O_NONBLOCK)) + /* no retry on NONBLOCK nor RWF_NOWAIT */ + if (ret2 == -EAGAIN && (req->flags & REQ_F_NOWAIT)) goto done; if (!force_nonblock || ret2 != -EAGAIN) { /* IOPOLL retry should happen for io-wq threads */ if ((req->ctx->flags & IORING_SETUP_IOPOLL) && ret2 == -EAGAIN) goto copy_iov; done: - kiocb_done(kiocb, ret2, cs); + kiocb_done(kiocb, ret2, issue_flags); } else { copy_iov: - /* some cases will consume bytes even on error returns */ - *iter = iter_cp; + iov_iter_restore(iter, state); ret = io_setup_async_rw(req, iovec, inline_vecs, iter, false); - if (!ret) + if (!ret) { + if (kiocb->ki_flags & IOCB_WRITE) + kiocb_end_write(req); return -EAGAIN; + } + return ret; } out_free: /* it's reportedly faster than delegating the null check to kfree() */ @@ -3610,37 +3749,160 @@ out_free: return ret; } -static int __io_splice_prep(struct io_kiocb *req, +static int io_renameat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { - struct io_splice* sp = &req->splice; - unsigned int valid_flags = SPLICE_F_FD_IN_FIXED | SPLICE_F_ALL; + struct io_rename *ren = &req->rename; + const char __user *oldf, *newf; if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; + if (sqe->ioprio || sqe->buf_index || sqe->splice_fd_in) + return -EINVAL; + if (unlikely(req->flags & REQ_F_FIXED_FILE)) + return -EBADF; - sp->file_in = NULL; - sp->len = READ_ONCE(sqe->len); - sp->flags = READ_ONCE(sqe->splice_flags); + ren->old_dfd = READ_ONCE(sqe->fd); + oldf = u64_to_user_ptr(READ_ONCE(sqe->addr)); + newf = u64_to_user_ptr(READ_ONCE(sqe->addr2)); + ren->new_dfd = READ_ONCE(sqe->len); + ren->flags = READ_ONCE(sqe->rename_flags); - if (unlikely(sp->flags & ~valid_flags)) - return -EINVAL; + ren->oldpath = getname(oldf); + if (IS_ERR(ren->oldpath)) + return PTR_ERR(ren->oldpath); - sp->file_in = io_file_get(NULL, req, READ_ONCE(sqe->splice_fd_in), - (sp->flags & SPLICE_F_FD_IN_FIXED)); - if (!sp->file_in) + ren->newpath = getname(newf); + if (IS_ERR(ren->newpath)) { + putname(ren->oldpath); + return PTR_ERR(ren->newpath); + } + + req->flags |= REQ_F_NEED_CLEANUP; + return 0; +} + +static int io_renameat(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_rename *ren = &req->rename; + int ret; + + if (issue_flags & IO_URING_F_NONBLOCK) + return -EAGAIN; + + ret = do_renameat2(ren->old_dfd, ren->oldpath, ren->new_dfd, + ren->newpath, ren->flags); + + req->flags &= ~REQ_F_NEED_CLEANUP; + if (ret < 0) + req_set_fail(req); + io_req_complete(req, ret); + return 0; +} + +static int io_unlinkat_prep(struct io_kiocb *req, + const struct io_uring_sqe *sqe) +{ + struct io_unlink *un = &req->unlink; + const char __user *fname; + + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; + if (sqe->ioprio || sqe->off || sqe->len || sqe->buf_index || + sqe->splice_fd_in) + return -EINVAL; + if (unlikely(req->flags & REQ_F_FIXED_FILE)) return -EBADF; + + un->dfd = READ_ONCE(sqe->fd); + + un->flags = READ_ONCE(sqe->unlink_flags); + if (un->flags & ~AT_REMOVEDIR) + return -EINVAL; + + fname = u64_to_user_ptr(READ_ONCE(sqe->addr)); + un->filename = getname(fname); + if (IS_ERR(un->filename)) + return PTR_ERR(un->filename); + req->flags |= REQ_F_NEED_CLEANUP; + return 0; +} - if (!S_ISREG(file_inode(sp->file_in)->i_mode)) { - /* - * Splice operation will be punted aync, and here need to - * modify io_wq_work.flags, so initialize io_wq_work firstly. - */ - io_req_init_async(req); - req->work.flags |= IO_WQ_WORK_UNBOUND; - } +static int io_unlinkat(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_unlink *un = &req->unlink; + int ret; + + if (issue_flags & IO_URING_F_NONBLOCK) + return -EAGAIN; + + if (un->flags & AT_REMOVEDIR) + ret = do_rmdir(un->dfd, un->filename); + else + ret = do_unlinkat(un->dfd, un->filename); + + req->flags &= ~REQ_F_NEED_CLEANUP; + if (ret < 0) + req_set_fail(req); + io_req_complete(req, ret); + return 0; +} + +static int io_shutdown_prep(struct io_kiocb *req, + const struct io_uring_sqe *sqe) +{ +#if defined(CONFIG_NET) + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; + if (unlikely(sqe->ioprio || sqe->off || sqe->addr || sqe->rw_flags || + sqe->buf_index || sqe->splice_fd_in)) + return -EINVAL; + + req->shutdown.how = READ_ONCE(sqe->len); + return 0; +#else + return -EOPNOTSUPP; +#endif +} + +static int io_shutdown(struct io_kiocb *req, unsigned int issue_flags) +{ +#if defined(CONFIG_NET) + struct socket *sock; + int ret; + + if (issue_flags & IO_URING_F_NONBLOCK) + return -EAGAIN; + + sock = sock_from_file(req->file, &ret); + if (unlikely(!sock)) + return ret; + + ret = __sys_shutdown_sock(sock, req->shutdown.how); + if (ret < 0) + req_set_fail(req); + io_req_complete(req, ret); + return 0; +#else + return -EOPNOTSUPP; +#endif +} + +static int __io_splice_prep(struct io_kiocb *req, + const struct io_uring_sqe *sqe) +{ + struct io_splice *sp = &req->splice; + unsigned int valid_flags = SPLICE_F_FD_IN_FIXED | SPLICE_F_ALL; + + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; + sp->len = READ_ONCE(sqe->len); + sp->flags = READ_ONCE(sqe->splice_flags); + if (unlikely(sp->flags & ~valid_flags)) + return -EINVAL; + sp->splice_fd_in = READ_ONCE(sqe->splice_fd_in); return 0; } @@ -3652,60 +3914,75 @@ static int io_tee_prep(struct io_kiocb *req, return __io_splice_prep(req, sqe); } -static int io_tee(struct io_kiocb *req, bool force_nonblock) +static int io_tee(struct io_kiocb *req, unsigned int issue_flags) { struct io_splice *sp = &req->splice; - struct file *in = sp->file_in; struct file *out = sp->file_out; unsigned int flags = sp->flags & ~SPLICE_F_FD_IN_FIXED; + struct file *in; long ret = 0; - if (force_nonblock) + if (issue_flags & IO_URING_F_NONBLOCK) return -EAGAIN; + + in = io_file_get(req->ctx, req, sp->splice_fd_in, + (sp->flags & SPLICE_F_FD_IN_FIXED)); + if (!in) { + ret = -EBADF; + goto done; + } + if (sp->len) ret = do_tee(in, out, sp->len, flags); - io_put_file(req, in, (sp->flags & SPLICE_F_FD_IN_FIXED)); - req->flags &= ~REQ_F_NEED_CLEANUP; - + if (!(sp->flags & SPLICE_F_FD_IN_FIXED)) + io_put_file(in); +done: if (ret != sp->len) - req_set_fail_links(req); + req_set_fail(req); io_req_complete(req, ret); return 0; } static int io_splice_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { - struct io_splice* sp = &req->splice; + struct io_splice *sp = &req->splice; sp->off_in = READ_ONCE(sqe->splice_off_in); sp->off_out = READ_ONCE(sqe->off); return __io_splice_prep(req, sqe); } -static int io_splice(struct io_kiocb *req, bool force_nonblock) +static int io_splice(struct io_kiocb *req, unsigned int issue_flags) { struct io_splice *sp = &req->splice; - struct file *in = sp->file_in; struct file *out = sp->file_out; unsigned int flags = sp->flags & ~SPLICE_F_FD_IN_FIXED; loff_t *poff_in, *poff_out; + struct file *in; long ret = 0; - if (force_nonblock) + if (issue_flags & IO_URING_F_NONBLOCK) return -EAGAIN; + in = io_file_get(req->ctx, req, sp->splice_fd_in, + (sp->flags & SPLICE_F_FD_IN_FIXED)); + if (!in) { + ret = -EBADF; + goto done; + } + poff_in = (sp->off_in == -1) ? NULL : &sp->off_in; poff_out = (sp->off_out == -1) ? NULL : &sp->off_out; if (sp->len) ret = do_splice(in, poff_in, out, poff_out, sp->len, flags); - io_put_file(req, in, (sp->flags & SPLICE_F_FD_IN_FIXED)); - req->flags &= ~REQ_F_NEED_CLEANUP; - + if (!(sp->flags & SPLICE_F_FD_IN_FIXED)) + io_put_file(in); +done: if (ret != sp->len) - req_set_fail_links(req); + req_set_fail(req); io_req_complete(req, ret); return 0; } @@ -3713,24 +3990,21 @@ static int io_splice(struct io_kiocb *req, bool force_nonblock) /* * IORING_OP_NOP just posts a completion event, nothing else. */ -static int io_nop(struct io_kiocb *req, struct io_comp_state *cs) +static int io_nop(struct io_kiocb *req, unsigned int issue_flags) { struct io_ring_ctx *ctx = req->ctx; if (unlikely(ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; - __io_req_complete(req, 0, 0, cs); + __io_req_complete(req, issue_flags, 0, 0); return 0; } -static int io_prep_fsync(struct io_kiocb *req, const struct io_uring_sqe *sqe) +static int io_fsync_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_ring_ctx *ctx = req->ctx; - if (!req->file) - return -EBADF; - if (unlikely(ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; if (unlikely(sqe->addr || sqe->ioprio || sqe->buf_index || @@ -3746,20 +4020,20 @@ static int io_prep_fsync(struct io_kiocb *req, const struct io_uring_sqe *sqe) return 0; } -static int io_fsync(struct io_kiocb *req, bool force_nonblock) +static int io_fsync(struct io_kiocb *req, unsigned int issue_flags) { loff_t end = req->sync.off + req->sync.len; int ret; /* fsync always requires a blocking context */ - if (force_nonblock) + if (issue_flags & IO_URING_F_NONBLOCK) return -EAGAIN; ret = vfs_fsync_range(req->file, req->sync.off, end > 0 ? end : LLONG_MAX, req->sync.flags & IORING_FSYNC_DATASYNC); if (ret < 0) - req_set_fail_links(req); + req_set_fail(req); io_req_complete(req, ret); return 0; } @@ -3779,17 +4053,19 @@ static int io_fallocate_prep(struct io_kiocb *req, return 0; } -static int io_fallocate(struct io_kiocb *req, bool force_nonblock) +static int io_fallocate(struct io_kiocb *req, unsigned int issue_flags) { int ret; /* fallocate always requiring blocking context */ - if (force_nonblock) + if (issue_flags & IO_URING_F_NONBLOCK) return -EAGAIN; ret = vfs_fallocate(req->file, req->sync.mode, req->sync.off, req->sync.len); if (ret < 0) - req_set_fail_links(req); + req_set_fail(req); + else + fsnotify_modify(req->file); io_req_complete(req, ret); return 0; } @@ -3799,7 +4075,9 @@ static int __io_openat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe const char __user *fname; int ret; - if (unlikely(sqe->ioprio || sqe->buf_index || sqe->splice_fd_in)) + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; + if (unlikely(sqe->ioprio || sqe->buf_index)) return -EINVAL; if (unlikely(req->flags & REQ_F_FIXED_FILE)) return -EBADF; @@ -3816,20 +4094,21 @@ static int __io_openat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe req->open.filename = NULL; return ret; } + + req->open.file_slot = READ_ONCE(sqe->file_index); + if (req->open.file_slot && (req->open.how.flags & O_CLOEXEC)) + return -EINVAL; + req->open.nofile = rlimit(RLIMIT_NOFILE); - req->open.ignore_nonblock = false; req->flags |= REQ_F_NEED_CLEANUP; return 0; } static int io_openat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { - u64 flags, mode; + u64 mode = READ_ONCE(sqe->len); + u64 flags = READ_ONCE(sqe->open_flags); - if (unlikely(req->ctx->flags & (IORING_SETUP_IOPOLL|IORING_SETUP_SQPOLL))) - return -EINVAL; - mode = READ_ONCE(sqe->len); - flags = READ_ONCE(sqe->open_flags); req->open.how = build_open_how(flags, mode); return __io_openat_prep(req, sqe); } @@ -3840,8 +4119,6 @@ static int io_openat2_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) size_t len; int ret; - if (unlikely(req->ctx->flags & (IORING_SETUP_IOPOLL|IORING_SETUP_SQPOLL))) - return -EINVAL; how = u64_to_user_ptr(READ_ONCE(sqe->addr2)); len = READ_ONCE(sqe->len); if (len < OPEN_HOW_SIZE_VER0) @@ -3855,58 +4132,75 @@ static int io_openat2_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) return __io_openat_prep(req, sqe); } -static int io_openat2(struct io_kiocb *req, bool force_nonblock) +static int io_openat2(struct io_kiocb *req, unsigned int issue_flags) { struct open_flags op; struct file *file; + bool resolve_nonblock, nonblock_set; + bool fixed = !!req->open.file_slot; int ret; - if (force_nonblock && !req->open.ignore_nonblock) - return -EAGAIN; - ret = build_open_flags(&req->open.how, &op); if (ret) goto err; + nonblock_set = op.open_flag & O_NONBLOCK; + resolve_nonblock = req->open.how.resolve & RESOLVE_CACHED; + if (issue_flags & IO_URING_F_NONBLOCK) { + /* + * Don't bother trying for O_TRUNC, O_CREAT, or O_TMPFILE open, + * it'll always -EAGAIN + */ + if (req->open.how.flags & (O_TRUNC | O_CREAT | O_TMPFILE)) + return -EAGAIN; + op.lookup_flags |= LOOKUP_CACHED; + op.open_flag |= O_NONBLOCK; + } - ret = __get_unused_fd_flags(req->open.how.flags, req->open.nofile); - if (ret < 0) - goto err; + if (!fixed) { + ret = __get_unused_fd_flags(req->open.how.flags, req->open.nofile); + if (ret < 0) + goto err; + } file = do_filp_open(req->open.dfd, req->open.filename, &op); if (IS_ERR(file)) { - put_unused_fd(ret); - ret = PTR_ERR(file); /* - * A work-around to ensure that /proc/self works that way - * that it should - if we get -EOPNOTSUPP back, then assume - * that proc_self_get_link() failed us because we're in async - * context. We should be safe to retry this from the task - * itself with force_nonblock == false set, as it should not - * block on lookup. Would be nice to know this upfront and - * avoid the async dance, but doesn't seem feasible. + * We could hang on to this 'fd' on retrying, but seems like + * marginal gain for something that is now known to be a slower + * path. So just put it, and we'll get a new one when we retry. */ - if (ret == -EOPNOTSUPP && io_wq_current_is_worker()) { - req->open.ignore_nonblock = true; - refcount_inc(&req->refs); - io_req_task_queue(req); - return 0; - } - } else { - fsnotify_open(file); - fd_install(ret, file); + if (!fixed) + put_unused_fd(ret); + + ret = PTR_ERR(file); + /* only retry if RESOLVE_CACHED wasn't already set by application */ + if (ret == -EAGAIN && + (!resolve_nonblock && (issue_flags & IO_URING_F_NONBLOCK))) + return -EAGAIN; + goto err; } + + if ((issue_flags & IO_URING_F_NONBLOCK) && !nonblock_set) + file->f_flags &= ~O_NONBLOCK; + fsnotify_open(file); + + if (!fixed) + fd_install(ret, file); + else + ret = io_install_fixed_file(req, file, issue_flags, + req->open.file_slot - 1); err: putname(req->open.filename); req->flags &= ~REQ_F_NEED_CLEANUP; if (ret < 0) - req_set_fail_links(req); - io_req_complete(req, ret); + req_set_fail(req); + __io_req_complete(req, issue_flags, ret, 0); return 0; } -static int io_openat(struct io_kiocb *req, bool force_nonblock) +static int io_openat(struct io_kiocb *req, unsigned int issue_flags) { - return io_openat2(req, force_nonblock); + return io_openat2(req, issue_flags); } static int io_remove_buffers_prep(struct io_kiocb *req, @@ -3947,6 +4241,7 @@ static int __io_remove_buffers(struct io_ring_ctx *ctx, struct io_buffer *buf, kfree(nxt); if (++i == nbufs) return i; + cond_resched(); } i++; kfree(buf); @@ -3955,13 +4250,13 @@ static int __io_remove_buffers(struct io_ring_ctx *ctx, struct io_buffer *buf, return i; } -static int io_remove_buffers(struct io_kiocb *req, bool force_nonblock, - struct io_comp_state *cs) +static int io_remove_buffers(struct io_kiocb *req, unsigned int issue_flags) { struct io_provide_buf *p = &req->pbuf; struct io_ring_ctx *ctx = req->ctx; struct io_buffer *head; int ret = 0; + bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; io_ring_submit_lock(ctx, !force_nonblock); @@ -3972,16 +4267,11 @@ static int io_remove_buffers(struct io_kiocb *req, bool force_nonblock, if (head) ret = __io_remove_buffers(ctx, head, p->bgid, p->nbufs); if (ret < 0) - req_set_fail_links(req); + req_set_fail(req); - /* need to hold the lock to complete IOPOLL requests */ - if (ctx->flags & IORING_SETUP_IOPOLL) { - __io_req_complete(req, ret, 0, cs); - io_ring_submit_unlock(ctx, !force_nonblock); - } else { - io_ring_submit_unlock(ctx, !force_nonblock); - __io_req_complete(req, ret, 0, cs); - } + /* complete before unlock, IOPOLL may need the lock */ + __io_req_complete(req, issue_flags, ret, 0); + io_ring_submit_unlock(ctx, !force_nonblock); return 0; } @@ -4048,13 +4338,13 @@ static int io_add_buffers(struct io_provide_buf *pbuf, struct io_buffer **head) return i ? i : -ENOMEM; } -static int io_provide_buffers(struct io_kiocb *req, bool force_nonblock, - struct io_comp_state *cs) +static int io_provide_buffers(struct io_kiocb *req, unsigned int issue_flags) { struct io_provide_buf *p = &req->pbuf; struct io_ring_ctx *ctx = req->ctx; struct io_buffer *head, *list; int ret = 0; + bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; io_ring_submit_lock(ctx, !force_nonblock); @@ -4064,21 +4354,16 @@ static int io_provide_buffers(struct io_kiocb *req, bool force_nonblock, ret = io_add_buffers(p, &head); if (ret >= 0 && !list) { - ret = xa_insert(&ctx->io_buffers, p->bgid, head, GFP_KERNEL); + ret = xa_insert(&ctx->io_buffers, p->bgid, head, + GFP_KERNEL_ACCOUNT); if (ret < 0) __io_remove_buffers(ctx, head, p->bgid, -1U); } if (ret < 0) - req_set_fail_links(req); - - /* need to hold the lock to complete IOPOLL requests */ - if (ctx->flags & IORING_SETUP_IOPOLL) { - __io_req_complete(req, ret, 0, cs); - io_ring_submit_unlock(ctx, !force_nonblock); - } else { - io_ring_submit_unlock(ctx, !force_nonblock); - __io_req_complete(req, ret, 0, cs); - } + req_set_fail(req); + /* complete before unlock, IOPOLL may need the lock */ + __io_req_complete(req, issue_flags, ret, 0); + io_ring_submit_unlock(ctx, !force_nonblock); return 0; } @@ -4088,7 +4373,7 @@ static int io_epoll_ctl_prep(struct io_kiocb *req, #if defined(CONFIG_EPOLL) if (sqe->ioprio || sqe->buf_index || sqe->splice_fd_in) return -EINVAL; - if (unlikely(req->ctx->flags & (IORING_SETUP_IOPOLL | IORING_SETUP_SQPOLL))) + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; req->epoll.epfd = READ_ONCE(sqe->fd); @@ -4109,20 +4394,20 @@ static int io_epoll_ctl_prep(struct io_kiocb *req, #endif } -static int io_epoll_ctl(struct io_kiocb *req, bool force_nonblock, - struct io_comp_state *cs) +static int io_epoll_ctl(struct io_kiocb *req, unsigned int issue_flags) { #if defined(CONFIG_EPOLL) struct io_epoll *ie = &req->epoll; int ret; + bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; ret = do_epoll_ctl(ie->epfd, ie->op, ie->fd, &ie->event, force_nonblock); if (force_nonblock && ret == -EAGAIN) return -EAGAIN; if (ret < 0) - req_set_fail_links(req); - __io_req_complete(req, ret, 0, cs); + req_set_fail(req); + __io_req_complete(req, issue_flags, ret, 0); return 0; #else return -EOPNOTSUPP; @@ -4146,18 +4431,18 @@ static int io_madvise_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) #endif } -static int io_madvise(struct io_kiocb *req, bool force_nonblock) +static int io_madvise(struct io_kiocb *req, unsigned int issue_flags) { #if defined(CONFIG_ADVISE_SYSCALLS) && defined(CONFIG_MMU) struct io_madvise *ma = &req->madvise; int ret; - if (force_nonblock) + if (issue_flags & IO_URING_F_NONBLOCK) return -EAGAIN; ret = do_madvise(current->mm, ma->addr, ma->len, ma->advice); if (ret < 0) - req_set_fail_links(req); + req_set_fail(req); io_req_complete(req, ret); return 0; #else @@ -4178,12 +4463,12 @@ static int io_fadvise_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) return 0; } -static int io_fadvise(struct io_kiocb *req, bool force_nonblock) +static int io_fadvise(struct io_kiocb *req, unsigned int issue_flags) { struct io_fadvise *fa = &req->fadvise; int ret; - if (force_nonblock) { + if (issue_flags & IO_URING_F_NONBLOCK) { switch (fa->advice) { case POSIX_FADV_NORMAL: case POSIX_FADV_RANDOM: @@ -4196,14 +4481,14 @@ static int io_fadvise(struct io_kiocb *req, bool force_nonblock) ret = vfs_fadvise(req->file, fa->offset, fa->len, fa->advice); if (ret < 0) - req_set_fail_links(req); - io_req_complete(req, ret); + req_set_fail(req); + __io_req_complete(req, issue_flags, ret, 0); return 0; } static int io_statx_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { - if (unlikely(req->ctx->flags & (IORING_SETUP_IOPOLL | IORING_SETUP_SQPOLL))) + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; if (sqe->ioprio || sqe->buf_index || sqe->splice_fd_in) return -EINVAL; @@ -4219,89 +4504,96 @@ static int io_statx_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) return 0; } -static int io_statx(struct io_kiocb *req, bool force_nonblock) +static int io_statx(struct io_kiocb *req, unsigned int issue_flags) { struct io_statx *ctx = &req->statx; int ret; - if (force_nonblock) + if (issue_flags & IO_URING_F_NONBLOCK) return -EAGAIN; ret = do_statx(ctx->dfd, ctx->filename, ctx->flags, ctx->mask, ctx->buffer); if (ret < 0) - req_set_fail_links(req); + req_set_fail(req); io_req_complete(req, ret); return 0; } static int io_close_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { - /* - * If we queue this for async, it must not be cancellable. That would - * leave the 'file' in an undeterminate state, and here need to modify - * io_wq_work.flags, so initialize io_wq_work firstly. - */ - io_req_init_async(req); - - if (unlikely(req->ctx->flags & (IORING_SETUP_IOPOLL|IORING_SETUP_SQPOLL))) + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; if (sqe->ioprio || sqe->off || sqe->addr || sqe->len || - sqe->rw_flags || sqe->buf_index || sqe->splice_fd_in) + sqe->rw_flags || sqe->buf_index) return -EINVAL; if (req->flags & REQ_F_FIXED_FILE) return -EBADF; req->close.fd = READ_ONCE(sqe->fd); - if ((req->file && req->file->f_op == &io_uring_fops)) - return -EBADF; + req->close.file_slot = READ_ONCE(sqe->file_index); + if (req->close.file_slot && req->close.fd) + return -EINVAL; - req->close.put_file = NULL; return 0; } -static int io_close(struct io_kiocb *req, bool force_nonblock, - struct io_comp_state *cs) +static int io_close(struct io_kiocb *req, unsigned int issue_flags) { + struct files_struct *files = current->files; struct io_close *close = &req->close; - int ret; + struct fdtable *fdt; + struct file *file = NULL; + int ret = -EBADF; - /* might be already done during nonblock submission */ - if (!close->put_file) { - ret = __close_fd_get_file(close->fd, &close->put_file); - if (ret < 0) - return (ret == -ENOENT) ? -EBADF : ret; + if (req->close.file_slot) { + ret = io_close_fixed(req, issue_flags); + goto err; + } + + spin_lock(&files->file_lock); + fdt = files_fdtable(files); + if (close->fd >= fdt->max_fds) { + spin_unlock(&files->file_lock); + goto err; + } + file = fdt->fd[close->fd]; + if (!file || file->f_op == &io_uring_fops) { + spin_unlock(&files->file_lock); + file = NULL; + goto err; } /* if the file has a flush method, be safe and punt to async */ - if (close->put_file->f_op->flush && force_nonblock) { - /* not safe to cancel at this point */ - req->work.flags |= IO_WQ_WORK_NO_CANCEL; - /* was never set, but play safe */ - req->flags &= ~REQ_F_NOWAIT; - /* avoid grabbing files - we don't need the files */ - req->flags |= REQ_F_NO_FILE_TABLE; + if (file->f_op->flush && (issue_flags & IO_URING_F_NONBLOCK)) { + spin_unlock(&files->file_lock); return -EAGAIN; } + ret = __close_fd_get_file(close->fd, &file); + spin_unlock(&files->file_lock); + if (ret < 0) { + if (ret == -ENOENT) + ret = -EBADF; + goto err; + } + /* No ->flush() or already async, safely close from here */ - ret = filp_close(close->put_file, req->work.identity->files); + ret = filp_close(file, current->files); +err: if (ret < 0) - req_set_fail_links(req); - fput(close->put_file); - close->put_file = NULL; - __io_req_complete(req, ret, 0, cs); + req_set_fail(req); + if (file) + fput(file); + __io_req_complete(req, issue_flags, ret, 0); return 0; } -static int io_prep_sfr(struct io_kiocb *req, const struct io_uring_sqe *sqe) +static int io_sfr_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_ring_ctx *ctx = req->ctx; - if (!req->file) - return -EBADF; - if (unlikely(ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; if (unlikely(sqe->addr || sqe->ioprio || sqe->buf_index || @@ -4314,18 +4606,18 @@ static int io_prep_sfr(struct io_kiocb *req, const struct io_uring_sqe *sqe) return 0; } -static int io_sync_file_range(struct io_kiocb *req, bool force_nonblock) +static int io_sync_file_range(struct io_kiocb *req, unsigned int issue_flags) { int ret; /* sync_file_range always requires a blocking context */ - if (force_nonblock) + if (issue_flags & IO_URING_F_NONBLOCK) return -EAGAIN; ret = sync_file_range(req->file, req->sync.off, req->sync.len, req->sync.flags); if (ret < 0) - req_set_fail_links(req); + req_set_fail(req); io_req_complete(req, ret); return 0; } @@ -4339,55 +4631,65 @@ static int io_setup_async_msg(struct io_kiocb *req, if (async_msg) return -EAGAIN; if (io_alloc_async_data(req)) { - if (kmsg->iov != kmsg->fast_iov) - kfree(kmsg->iov); + kfree(kmsg->free_iov); return -ENOMEM; } async_msg = req->async_data; req->flags |= REQ_F_NEED_CLEANUP; memcpy(async_msg, kmsg, sizeof(*kmsg)); + if (async_msg->msg.msg_name) + async_msg->msg.msg_name = &async_msg->addr; + /* if were using fast_iov, set it to the new one */ + if (!async_msg->free_iov) + async_msg->msg.msg_iter.iov = async_msg->fast_iov; + return -EAGAIN; } static int io_sendmsg_copy_hdr(struct io_kiocb *req, struct io_async_msghdr *iomsg) { - iomsg->iov = iomsg->fast_iov; iomsg->msg.msg_name = &iomsg->addr; + iomsg->free_iov = iomsg->fast_iov; return sendmsg_copy_msghdr(&iomsg->msg, req->sr_msg.umsg, - req->sr_msg.msg_flags, &iomsg->iov); + req->sr_msg.msg_flags, &iomsg->free_iov); } -static int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +static int io_sendmsg_prep_async(struct io_kiocb *req) { - struct io_async_msghdr *async_msg = req->async_data; - struct io_sr_msg *sr = &req->sr_msg; int ret; + ret = io_sendmsg_copy_hdr(req, req->async_data); + if (!ret) + req->flags |= REQ_F_NEED_CLEANUP; + return ret; +} + +static int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_sr_msg *sr = &req->sr_msg; + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; - if (unlikely(sqe->addr2 || sqe->splice_fd_in || sqe->ioprio)) + if (unlikely(sqe->addr2 || sqe->file_index)) + return -EINVAL; + if (unlikely(sqe->addr2 || sqe->file_index || sqe->ioprio)) return -EINVAL; - sr->msg_flags = READ_ONCE(sqe->msg_flags); sr->umsg = u64_to_user_ptr(READ_ONCE(sqe->addr)); sr->len = READ_ONCE(sqe->len); + sr->msg_flags = READ_ONCE(sqe->msg_flags) | MSG_NOSIGNAL; + if (sr->msg_flags & MSG_DONTWAIT) + req->flags |= REQ_F_NOWAIT; #ifdef CONFIG_COMPAT if (req->ctx->compat) sr->msg_flags |= MSG_CMSG_COMPAT; #endif - - if (!async_msg || !io_op_defs[req->opcode].needs_async_data) - return 0; - ret = io_sendmsg_copy_hdr(req, async_msg); - if (!ret) - req->flags |= REQ_F_NEED_CLEANUP; - return ret; + return 0; } -static int io_sendmsg(struct io_kiocb *req, bool force_nonblock, - struct io_comp_state *cs) +static int io_sendmsg(struct io_kiocb *req, unsigned int issue_flags) { struct io_async_msghdr iomsg, *kmsg; struct socket *sock; @@ -4399,46 +4701,37 @@ static int io_sendmsg(struct io_kiocb *req, bool force_nonblock, if (unlikely(!sock)) return ret; - if (req->async_data) { - kmsg = req->async_data; - kmsg->msg.msg_name = &kmsg->addr; - /* if iov is set, it's allocated already */ - if (!kmsg->iov) - kmsg->iov = kmsg->fast_iov; - kmsg->msg.msg_iter.iov = kmsg->iov; - } else { + kmsg = req->async_data; + if (!kmsg) { ret = io_sendmsg_copy_hdr(req, &iomsg); if (ret) return ret; kmsg = &iomsg; } - flags = req->sr_msg.msg_flags | MSG_NOSIGNAL; - if (flags & MSG_DONTWAIT) - req->flags |= REQ_F_NOWAIT; - else if (force_nonblock) + flags = req->sr_msg.msg_flags; + if (issue_flags & IO_URING_F_NONBLOCK) flags |= MSG_DONTWAIT; - if (flags & MSG_WAITALL) min_ret = iov_iter_count(&kmsg->msg.msg_iter); ret = __sys_sendmsg_sock(sock, &kmsg->msg, flags); - if (force_nonblock && ret == -EAGAIN) + if ((issue_flags & IO_URING_F_NONBLOCK) && ret == -EAGAIN) return io_setup_async_msg(req, kmsg); if (ret == -ERESTARTSYS) ret = -EINTR; - if (kmsg->iov != kmsg->fast_iov) - kfree(kmsg->iov); + /* fast path, check for non-NULL to avoid function call */ + if (kmsg->free_iov) + kfree(kmsg->free_iov); req->flags &= ~REQ_F_NEED_CLEANUP; if (ret < min_ret) - req_set_fail_links(req); - __io_req_complete(req, ret, 0, cs); + req_set_fail(req); + __io_req_complete(req, issue_flags, ret, 0); return 0; } -static int io_send(struct io_kiocb *req, bool force_nonblock, - struct io_comp_state *cs) +static int io_send(struct io_kiocb *req, unsigned int issue_flags) { struct io_sr_msg *sr = &req->sr_msg; struct msghdr msg; @@ -4461,25 +4754,22 @@ static int io_send(struct io_kiocb *req, bool force_nonblock, msg.msg_controllen = 0; msg.msg_namelen = 0; - flags = req->sr_msg.msg_flags | MSG_NOSIGNAL; - if (flags & MSG_DONTWAIT) - req->flags |= REQ_F_NOWAIT; - else if (force_nonblock) + flags = req->sr_msg.msg_flags; + if (issue_flags & IO_URING_F_NONBLOCK) flags |= MSG_DONTWAIT; - if (flags & MSG_WAITALL) min_ret = iov_iter_count(&msg.msg_iter); msg.msg_flags = flags; ret = sock_sendmsg(sock, &msg); - if (force_nonblock && ret == -EAGAIN) + if ((issue_flags & IO_URING_F_NONBLOCK) && ret == -EAGAIN) return -EAGAIN; if (ret == -ERESTARTSYS) ret = -EINTR; if (ret < min_ret) - req_set_fail_links(req); - __io_req_complete(req, ret, 0, cs); + req_set_fail(req); + __io_req_complete(req, issue_flags, ret, 0); return 0; } @@ -4499,15 +4789,14 @@ static int __io_recvmsg_copy_hdr(struct io_kiocb *req, if (req->flags & REQ_F_BUFFER_SELECT) { if (iov_len > 1) return -EINVAL; - if (copy_from_user(iomsg->iov, uiov, sizeof(*uiov))) + if (copy_from_user(iomsg->fast_iov, uiov, sizeof(*uiov))) return -EFAULT; - sr->len = iomsg->iov[0].iov_len; - iov_iter_init(&iomsg->msg.msg_iter, READ, iomsg->iov, 1, - sr->len); - iomsg->iov = NULL; + sr->len = iomsg->fast_iov[0].iov_len; + iomsg->free_iov = NULL; } else { + iomsg->free_iov = iomsg->fast_iov; ret = __import_iovec(READ, uiov, iov_len, UIO_FASTIOV, - &iomsg->iov, &iomsg->msg.msg_iter, + &iomsg->free_iov, &iomsg->msg.msg_iter, false); if (ret > 0) ret = 0; @@ -4520,16 +4809,14 @@ static int __io_recvmsg_copy_hdr(struct io_kiocb *req, static int __io_compat_recvmsg_copy_hdr(struct io_kiocb *req, struct io_async_msghdr *iomsg) { - struct compat_msghdr __user *msg_compat; struct io_sr_msg *sr = &req->sr_msg; struct compat_iovec __user *uiov; compat_uptr_t ptr; compat_size_t len; int ret; - msg_compat = (struct compat_msghdr __user *) sr->umsg; - ret = __get_compat_msghdr(&iomsg->msg, msg_compat, &iomsg->uaddr, - &ptr, &len); + ret = __get_compat_msghdr(&iomsg->msg, sr->umsg_compat, &iomsg->uaddr, + &ptr, &len); if (ret) return ret; @@ -4546,11 +4833,11 @@ static int __io_compat_recvmsg_copy_hdr(struct io_kiocb *req, if (clen < 0) return -EINVAL; sr->len = clen; - iomsg->iov[0].iov_len = clen; - iomsg->iov = NULL; + iomsg->free_iov = NULL; } else { + iomsg->free_iov = iomsg->fast_iov; ret = __import_iovec(READ, (struct iovec __user *)uiov, len, - UIO_FASTIOV, &iomsg->iov, + UIO_FASTIOV, &iomsg->free_iov, &iomsg->msg.msg_iter, true); if (ret < 0) return ret; @@ -4564,7 +4851,6 @@ static int io_recvmsg_copy_hdr(struct io_kiocb *req, struct io_async_msghdr *iomsg) { iomsg->msg.msg_name = &iomsg->addr; - iomsg->iov = iomsg->fast_iov; #ifdef CONFIG_COMPAT if (req->ctx->compat) @@ -4594,38 +4880,42 @@ static inline unsigned int io_put_recv_kbuf(struct io_kiocb *req) return io_put_kbuf(req, req->sr_msg.kbuf); } -static int io_recvmsg_prep(struct io_kiocb *req, - const struct io_uring_sqe *sqe) +static int io_recvmsg_prep_async(struct io_kiocb *req) { - struct io_async_msghdr *async_msg = req->async_data; - struct io_sr_msg *sr = &req->sr_msg; int ret; + ret = io_recvmsg_copy_hdr(req, req->async_data); + if (!ret) + req->flags |= REQ_F_NEED_CLEANUP; + return ret; +} + +static int io_recvmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_sr_msg *sr = &req->sr_msg; + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; - if (unlikely(sqe->addr2 || sqe->splice_fd_in || sqe->ioprio)) + if (unlikely(sqe->addr2 || sqe->file_index)) + return -EINVAL; + if (unlikely(sqe->addr2 || sqe->file_index || sqe->ioprio)) return -EINVAL; - sr->msg_flags = READ_ONCE(sqe->msg_flags); sr->umsg = u64_to_user_ptr(READ_ONCE(sqe->addr)); sr->len = READ_ONCE(sqe->len); sr->bgid = READ_ONCE(sqe->buf_group); + sr->msg_flags = READ_ONCE(sqe->msg_flags) | MSG_NOSIGNAL; + if (sr->msg_flags & MSG_DONTWAIT) + req->flags |= REQ_F_NOWAIT; #ifdef CONFIG_COMPAT if (req->ctx->compat) sr->msg_flags |= MSG_CMSG_COMPAT; #endif - - if (!async_msg || !io_op_defs[req->opcode].needs_async_data) - return 0; - ret = io_recvmsg_copy_hdr(req, async_msg); - if (!ret) - req->flags |= REQ_F_NEED_CLEANUP; - return ret; + return 0; } -static int io_recvmsg(struct io_kiocb *req, bool force_nonblock, - struct io_comp_state *cs) +static int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) { struct io_async_msghdr iomsg, *kmsg; struct socket *sock; @@ -4633,19 +4923,14 @@ static int io_recvmsg(struct io_kiocb *req, bool force_nonblock, unsigned flags; int min_ret = 0; int ret, cflags = 0; + bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; sock = sock_from_file(req->file, &ret); if (unlikely(!sock)) return ret; - if (req->async_data) { - kmsg = req->async_data; - kmsg->msg.msg_name = &kmsg->addr; - /* if iov is set, it's allocated already */ - if (!kmsg->iov) - kmsg->iov = kmsg->fast_iov; - kmsg->msg.msg_iter.iov = kmsg->iov; - } else { + kmsg = req->async_data; + if (!kmsg) { ret = io_recvmsg_copy_hdr(req, &iomsg); if (ret) return ret; @@ -4657,16 +4942,14 @@ static int io_recvmsg(struct io_kiocb *req, bool force_nonblock, if (IS_ERR(kbuf)) return PTR_ERR(kbuf); kmsg->fast_iov[0].iov_base = u64_to_user_ptr(kbuf->addr); - iov_iter_init(&kmsg->msg.msg_iter, READ, kmsg->iov, + kmsg->fast_iov[0].iov_len = req->sr_msg.len; + iov_iter_init(&kmsg->msg.msg_iter, READ, kmsg->fast_iov, 1, req->sr_msg.len); } - flags = req->sr_msg.msg_flags | MSG_NOSIGNAL; - if (flags & MSG_DONTWAIT) - req->flags |= REQ_F_NOWAIT; - else if (force_nonblock) + flags = req->sr_msg.msg_flags; + if (force_nonblock) flags |= MSG_DONTWAIT; - if (flags & MSG_WAITALL) min_ret = iov_iter_count(&kmsg->msg.msg_iter); @@ -4679,17 +4962,17 @@ static int io_recvmsg(struct io_kiocb *req, bool force_nonblock, if (req->flags & REQ_F_BUFFER_SELECTED) cflags = io_put_recv_kbuf(req); - if (kmsg->iov != kmsg->fast_iov) - kfree(kmsg->iov); + /* fast path, check for non-NULL to avoid function call */ + if (kmsg->free_iov) + kfree(kmsg->free_iov); req->flags &= ~REQ_F_NEED_CLEANUP; if (ret < min_ret || ((flags & MSG_WAITALL) && (kmsg->msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC)))) - req_set_fail_links(req); - __io_req_complete(req, ret, cflags, cs); + req_set_fail(req); + __io_req_complete(req, issue_flags, ret, cflags); return 0; } -static int io_recv(struct io_kiocb *req, bool force_nonblock, - struct io_comp_state *cs) +static int io_recv(struct io_kiocb *req, unsigned int issue_flags) { struct io_buffer *kbuf; struct io_sr_msg *sr = &req->sr_msg; @@ -4700,6 +4983,7 @@ static int io_recv(struct io_kiocb *req, bool force_nonblock, unsigned flags; int min_ret = 0; int ret, cflags = 0; + bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; sock = sock_from_file(req->file, &ret); if (unlikely(!sock)) @@ -4723,12 +5007,9 @@ static int io_recv(struct io_kiocb *req, bool force_nonblock, msg.msg_iocb = NULL; msg.msg_flags = 0; - flags = req->sr_msg.msg_flags | MSG_NOSIGNAL; - if (flags & MSG_DONTWAIT) - req->flags |= REQ_F_NOWAIT; - else if (force_nonblock) + flags = req->sr_msg.msg_flags; + if (force_nonblock) flags |= MSG_DONTWAIT; - if (flags & MSG_WAITALL) min_ret = iov_iter_count(&msg.msg_iter); @@ -4741,8 +5022,8 @@ out_free: if (req->flags & REQ_F_BUFFER_SELECTED) cflags = io_put_recv_kbuf(req); if (ret < min_ret || ((flags & MSG_WAITALL) && (msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC)))) - req_set_fail_links(req); - __io_req_complete(req, ret, cflags, cs); + req_set_fail(req); + __io_req_complete(req, issue_flags, ret, cflags); return 0; } @@ -4750,48 +5031,79 @@ static int io_accept_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_accept *accept = &req->accept; - if (unlikely(req->ctx->flags & (IORING_SETUP_IOPOLL|IORING_SETUP_SQPOLL))) + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; - if (sqe->ioprio || sqe->len || sqe->buf_index || sqe->splice_fd_in) + if (sqe->ioprio || sqe->len || sqe->buf_index) return -EINVAL; accept->addr = u64_to_user_ptr(READ_ONCE(sqe->addr)); accept->addr_len = u64_to_user_ptr(READ_ONCE(sqe->addr2)); accept->flags = READ_ONCE(sqe->accept_flags); accept->nofile = rlimit(RLIMIT_NOFILE); + + accept->file_slot = READ_ONCE(sqe->file_index); + if (accept->file_slot && (accept->flags & SOCK_CLOEXEC)) + return -EINVAL; + if (accept->flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK)) + return -EINVAL; + if (SOCK_NONBLOCK != O_NONBLOCK && (accept->flags & SOCK_NONBLOCK)) + accept->flags = (accept->flags & ~SOCK_NONBLOCK) | O_NONBLOCK; return 0; } -static int io_accept(struct io_kiocb *req, bool force_nonblock, - struct io_comp_state *cs) +static int io_accept(struct io_kiocb *req, unsigned int issue_flags) { struct io_accept *accept = &req->accept; + bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; unsigned int file_flags = force_nonblock ? O_NONBLOCK : 0; - int ret; + bool fixed = !!accept->file_slot; + struct file *file; + int ret, fd; if (req->file->f_flags & O_NONBLOCK) req->flags |= REQ_F_NOWAIT; - ret = __sys_accept4_file(req->file, file_flags, accept->addr, - accept->addr_len, accept->flags, - accept->nofile); - if (ret == -EAGAIN && force_nonblock) - return -EAGAIN; - if (ret < 0) { + if (!fixed) { + fd = __get_unused_fd_flags(accept->flags, accept->nofile); + if (unlikely(fd < 0)) + return fd; + } + file = do_accept(req->file, file_flags, accept->addr, accept->addr_len, + accept->flags); + + if (IS_ERR(file)) { + if (!fixed) + put_unused_fd(fd); + ret = PTR_ERR(file); + if (ret == -EAGAIN && force_nonblock) + return -EAGAIN; if (ret == -ERESTARTSYS) ret = -EINTR; - req_set_fail_links(req); + req_set_fail(req); + } else if (!fixed) { + fd_install(fd, file); + ret = fd; + } else { + ret = io_install_fixed_file(req, file, issue_flags, + accept->file_slot - 1); } - __io_req_complete(req, ret, 0, cs); + __io_req_complete(req, issue_flags, ret, 0); return 0; } +static int io_connect_prep_async(struct io_kiocb *req) +{ + struct io_async_connect *io = req->async_data; + struct io_connect *conn = &req->connect; + + return move_addr_to_kernel(conn->addr, conn->addr_len, &io->address); +} + static int io_connect_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_connect *conn = &req->connect; - struct io_async_connect *io = req->async_data; - if (unlikely(req->ctx->flags & (IORING_SETUP_IOPOLL|IORING_SETUP_SQPOLL))) + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; if (sqe->ioprio || sqe->len || sqe->buf_index || sqe->rw_flags || sqe->splice_fd_in) @@ -4799,20 +5111,15 @@ static int io_connect_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) conn->addr = u64_to_user_ptr(READ_ONCE(sqe->addr)); conn->addr_len = READ_ONCE(sqe->addr2); - - if (!io) - return 0; - - return move_addr_to_kernel(conn->addr, conn->addr_len, - &io->address); + return 0; } -static int io_connect(struct io_kiocb *req, bool force_nonblock, - struct io_comp_state *cs) +static int io_connect(struct io_kiocb *req, unsigned int issue_flags) { struct io_async_connect __io, *io; unsigned file_flags; int ret; + bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; if (req->async_data) { io = req->async_data; @@ -4836,7 +5143,6 @@ static int io_connect(struct io_kiocb *req, bool force_nonblock, ret = -ENOMEM; goto out; } - io = req->async_data; memcpy(req->async_data, &__io, sizeof(__io)); return -EAGAIN; } @@ -4844,248 +5150,361 @@ static int io_connect(struct io_kiocb *req, bool force_nonblock, ret = -EINTR; out: if (ret < 0) - req_set_fail_links(req); - __io_req_complete(req, ret, 0, cs); + req_set_fail(req); + __io_req_complete(req, issue_flags, ret, 0); return 0; } #else /* !CONFIG_NET */ -static int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +#define IO_NETOP_FN(op) \ +static int io_##op(struct io_kiocb *req, unsigned int issue_flags) \ +{ \ + return -EOPNOTSUPP; \ +} + +#define IO_NETOP_PREP(op) \ +IO_NETOP_FN(op) \ +static int io_##op##_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) \ +{ \ + return -EOPNOTSUPP; \ +} \ + +#define IO_NETOP_PREP_ASYNC(op) \ +IO_NETOP_PREP(op) \ +static int io_##op##_prep_async(struct io_kiocb *req) \ +{ \ + return -EOPNOTSUPP; \ +} + +IO_NETOP_PREP_ASYNC(sendmsg); +IO_NETOP_PREP_ASYNC(recvmsg); +IO_NETOP_PREP_ASYNC(connect); +IO_NETOP_PREP(accept); +IO_NETOP_FN(send); +IO_NETOP_FN(recv); +#endif /* CONFIG_NET */ + +struct io_poll_table { + struct poll_table_struct pt; + struct io_kiocb *req; + int nr_entries; + int error; +}; + +#define IO_POLL_CANCEL_FLAG BIT(31) +#define IO_POLL_RETRY_FLAG BIT(30) +#define IO_POLL_REF_MASK GENMASK(29, 0) + +/* + * We usually have 1-2 refs taken, 128 is more than enough and we want to + * maximise the margin between this amount and the moment when it overflows. + */ +#define IO_POLL_REF_BIAS 128 + +static bool io_poll_get_ownership_slowpath(struct io_kiocb *req) { - return -EOPNOTSUPP; + int v; + + /* + * poll_refs are already elevated and we don't have much hope for + * grabbing the ownership. Instead of incrementing set a retry flag + * to notify the loop that there might have been some change. + */ + v = atomic_fetch_or(IO_POLL_RETRY_FLAG, &req->poll_refs); + if (v & IO_POLL_REF_MASK) + return false; + return !(atomic_fetch_inc(&req->poll_refs) & IO_POLL_REF_MASK); } -static int io_sendmsg(struct io_kiocb *req, bool force_nonblock, - struct io_comp_state *cs) +/* + * If refs part of ->poll_refs (see IO_POLL_REF_MASK) is 0, it's free. We can + * bump it and acquire ownership. It's disallowed to modify requests while not + * owning it, that prevents from races for enqueueing task_work's and b/w + * arming poll and wakeups. + */ +static inline bool io_poll_get_ownership(struct io_kiocb *req) { - return -EOPNOTSUPP; + if (unlikely(atomic_read(&req->poll_refs) >= IO_POLL_REF_BIAS)) + return io_poll_get_ownership_slowpath(req); + return !(atomic_fetch_inc(&req->poll_refs) & IO_POLL_REF_MASK); } -static int io_send(struct io_kiocb *req, bool force_nonblock, - struct io_comp_state *cs) +static void io_poll_mark_cancelled(struct io_kiocb *req) { - return -EOPNOTSUPP; + atomic_or(IO_POLL_CANCEL_FLAG, &req->poll_refs); } -static int io_recvmsg_prep(struct io_kiocb *req, - const struct io_uring_sqe *sqe) +static struct io_poll_iocb *io_poll_get_double(struct io_kiocb *req) { - return -EOPNOTSUPP; + /* pure poll stashes this in ->async_data, poll driven retry elsewhere */ + if (req->opcode == IORING_OP_POLL_ADD) + return req->async_data; + return req->apoll->double_poll; } -static int io_recvmsg(struct io_kiocb *req, bool force_nonblock, - struct io_comp_state *cs) +static struct io_poll_iocb *io_poll_get_single(struct io_kiocb *req) { - return -EOPNOTSUPP; + if (req->opcode == IORING_OP_POLL_ADD) + return &req->poll; + return &req->apoll->poll; } -static int io_recv(struct io_kiocb *req, bool force_nonblock, - struct io_comp_state *cs) +static void io_poll_req_insert(struct io_kiocb *req) { - return -EOPNOTSUPP; + struct io_ring_ctx *ctx = req->ctx; + struct hlist_head *list; + + list = &ctx->cancel_hash[hash_long(req->user_data, ctx->cancel_hash_bits)]; + hlist_add_head(&req->hash_node, list); } -static int io_accept_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +static void io_init_poll_iocb(struct io_poll_iocb *poll, __poll_t events, + wait_queue_func_t wake_func) { - return -EOPNOTSUPP; + poll->head = NULL; +#define IO_POLL_UNMASK (EPOLLERR|EPOLLHUP|EPOLLNVAL|EPOLLRDHUP) + /* mask in events that we always want/need */ + poll->events = events | IO_POLL_UNMASK; + INIT_LIST_HEAD(&poll->wait.entry); + init_waitqueue_func_entry(&poll->wait, wake_func); } -static int io_accept(struct io_kiocb *req, bool force_nonblock, - struct io_comp_state *cs) +static inline void io_poll_remove_entry(struct io_poll_iocb *poll) { - return -EOPNOTSUPP; + struct wait_queue_head *head = smp_load_acquire(&poll->head); + + if (head) { + spin_lock_irq(&head->lock); + list_del_init(&poll->wait.entry); + poll->head = NULL; + spin_unlock_irq(&head->lock); + } } -static int io_connect_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +static void io_poll_remove_entries(struct io_kiocb *req) { - return -EOPNOTSUPP; + struct io_poll_iocb *poll = io_poll_get_single(req); + struct io_poll_iocb *poll_double = io_poll_get_double(req); + + /* + * While we hold the waitqueue lock and the waitqueue is nonempty, + * wake_up_pollfree() will wait for us. However, taking the waitqueue + * lock in the first place can race with the waitqueue being freed. + * + * We solve this as eventpoll does: by taking advantage of the fact that + * all users of wake_up_pollfree() will RCU-delay the actual free. If + * we enter rcu_read_lock() and see that the pointer to the queue is + * non-NULL, we can then lock it without the memory being freed out from + * under us. + * + * Keep holding rcu_read_lock() as long as we hold the queue lock, in + * case the caller deletes the entry from the queue, leaving it empty. + * In that case, only RCU prevents the queue memory from being freed. + */ + rcu_read_lock(); + io_poll_remove_entry(poll); + if (poll_double) + io_poll_remove_entry(poll_double); + rcu_read_unlock(); } -static int io_connect(struct io_kiocb *req, bool force_nonblock, - struct io_comp_state *cs) +/* + * All poll tw should go through this. Checks for poll events, manages + * references, does rewait, etc. + * + * Returns a negative error on failure. >0 when no action require, which is + * either spurious wakeup or multishot CQE is served. 0 when it's done with + * the request, then the mask is stored in req->result. + */ +static int io_poll_check_events(struct io_kiocb *req) { - return -EOPNOTSUPP; -} -#endif /* CONFIG_NET */ + struct io_ring_ctx *ctx = req->ctx; + struct io_poll_iocb *poll = io_poll_get_single(req); + int v; -struct io_poll_table { - struct poll_table_struct pt; - struct io_kiocb *req; - int nr_entries; - int error; -}; + /* req->task == current here, checking PF_EXITING is safe */ + if (unlikely(req->task->flags & PF_EXITING)) + io_poll_mark_cancelled(req); -static int __io_async_wake(struct io_kiocb *req, struct io_poll_iocb *poll, - __poll_t mask, task_work_func_t func) -{ - bool twa_signal_ok; - int ret; + do { + v = atomic_read(&req->poll_refs); - /* for instances that support it check for an event match first: */ - if (mask && !(mask & poll->events)) - return 0; + /* tw handler should be the owner, and so have some references */ + if (WARN_ON_ONCE(!(v & IO_POLL_REF_MASK))) + return 0; + if (v & IO_POLL_CANCEL_FLAG) + return -ECANCELED; + /* + * cqe.res contains only events of the first wake up + * and all others are be lost. Redo vfs_poll() to get + * up to date state. + */ + if ((v & IO_POLL_REF_MASK) != 1) + req->result = 0; + if (v & IO_POLL_RETRY_FLAG) { + req->result = 0; + /* + * We won't find new events that came in between + * vfs_poll and the ref put unless we clear the + * flag in advance. + */ + atomic_andnot(IO_POLL_RETRY_FLAG, &req->poll_refs); + v &= ~IO_POLL_RETRY_FLAG; + } - trace_io_uring_task_add(req->ctx, req->opcode, req->user_data, mask); + if (!req->result) { + struct poll_table_struct pt = { ._key = poll->events }; - list_del_init(&poll->wait.entry); + req->result = vfs_poll(req->file, &pt) & poll->events; + } - req->result = mask; - init_task_work(&req->task_work, func); - percpu_ref_get(&req->ctx->refs); + /* multishot, just fill an CQE and proceed */ + if (req->result && !(poll->events & EPOLLONESHOT)) { + __poll_t mask = mangle_poll(req->result & poll->events); + bool filled; - /* - * If we using the signalfd wait_queue_head for this wakeup, then - * it's not safe to use TWA_SIGNAL as we could be recursing on the - * tsk->sighand->siglock on doing the wakeup. Should not be needed - * either, as the normal wakeup will suffice. - */ - twa_signal_ok = (poll->head != &req->task->sighand->signalfd_wqh); + spin_lock(&ctx->completion_lock); + filled = io_fill_cqe_aux(ctx, req->user_data, mask, + IORING_CQE_F_MORE); + io_commit_cqring(ctx); + spin_unlock(&ctx->completion_lock); + if (unlikely(!filled)) + return -ECANCELED; + io_cqring_ev_posted(ctx); + } else if (req->result) { + return 0; + } - /* - * If this fails, then the task is exiting. When a task exits, the - * work gets canceled, so just cancel this request as well instead - * of executing it. We can't safely execute it anyway, as we may not - * have the needed state needed for it anyway. - */ - ret = io_req_task_work_add(req, twa_signal_ok); - if (unlikely(ret)) { - struct task_struct *tsk; + /* force the next iteration to vfs_poll() */ + req->result = 0; + + /* + * Release all references, retry if someone tried to restart + * task_work while we were executing it. + */ + } while (atomic_sub_return(v & IO_POLL_REF_MASK, &req->poll_refs) & + IO_POLL_REF_MASK); - WRITE_ONCE(poll->canceled, true); - tsk = io_wq_get_task(req->ctx->io_wq); - task_work_add(tsk, &req->task_work, TWA_NONE); - wake_up_process(tsk); - } return 1; } -static bool io_poll_rewait(struct io_kiocb *req, struct io_poll_iocb *poll) - __acquires(&req->ctx->completion_lock) +static void io_poll_task_func(struct io_kiocb *req, bool *locked) { struct io_ring_ctx *ctx = req->ctx; + int ret; - if (!req->result && !READ_ONCE(poll->canceled)) { - struct poll_table_struct pt = { ._key = poll->events }; - - req->result = vfs_poll(req->file, &pt) & poll->events; - } + ret = io_poll_check_events(req); + if (ret > 0) + return; - spin_lock_irq(&ctx->completion_lock); - if (!req->result && !READ_ONCE(poll->canceled)) { - add_wait_queue(poll->head, &poll->wait); - return true; + if (!ret) { + req->result = mangle_poll(req->result & req->poll.events); + } else { + req->result = ret; + req_set_fail(req); } - return false; -} - -static struct io_poll_iocb *io_poll_get_double(struct io_kiocb *req) -{ - /* pure poll stashes this in ->async_data, poll driven retry elsewhere */ - if (req->opcode == IORING_OP_POLL_ADD) - return req->async_data; - return req->apoll->double_poll; -} - -static struct io_poll_iocb *io_poll_get_single(struct io_kiocb *req) -{ - if (req->opcode == IORING_OP_POLL_ADD) - return &req->poll; - return &req->apoll->poll; + io_poll_remove_entries(req); + spin_lock(&ctx->completion_lock); + hash_del(&req->hash_node); + spin_unlock(&ctx->completion_lock); + io_req_complete_post(req, req->result, 0); } -static void io_poll_remove_double(struct io_kiocb *req) +static void io_apoll_task_func(struct io_kiocb *req, bool *locked) { - struct io_poll_iocb *poll = io_poll_get_double(req); + struct io_ring_ctx *ctx = req->ctx; + int ret; - lockdep_assert_held(&req->ctx->completion_lock); + ret = io_poll_check_events(req); + if (ret > 0) + return; - if (poll && poll->head) { - struct wait_queue_head *head = poll->head; + io_poll_remove_entries(req); + spin_lock(&ctx->completion_lock); + hash_del(&req->hash_node); + spin_unlock(&ctx->completion_lock); - spin_lock(&head->lock); - list_del_init(&poll->wait.entry); - if (poll->wait.private) - refcount_dec(&req->refs); - poll->head = NULL; - spin_unlock(&head->lock); - } + if (!ret) + io_req_task_submit(req, locked); + else + io_req_complete_failed(req, ret); } -static void io_poll_complete(struct io_kiocb *req, __poll_t mask, int error) +static void __io_poll_execute(struct io_kiocb *req, int mask) { - struct io_ring_ctx *ctx = req->ctx; + req->result = mask; + if (req->opcode == IORING_OP_POLL_ADD) + req->io_task_work.func = io_poll_task_func; + else + req->io_task_work.func = io_apoll_task_func; - io_poll_remove_double(req); - req->poll.done = true; - io_cqring_fill_event(req, error ? error : mangle_poll(mask)); - io_commit_cqring(ctx); + trace_io_uring_task_add(req->ctx, req->opcode, req->user_data, mask); + io_req_task_work_add(req); } -static void io_poll_task_func(struct callback_head *cb) +static inline void io_poll_execute(struct io_kiocb *req, int res) { - struct io_kiocb *req = container_of(cb, struct io_kiocb, task_work); - struct io_ring_ctx *ctx = req->ctx; - struct io_kiocb *nxt; - - if (io_poll_rewait(req, &req->poll)) { - spin_unlock_irq(&ctx->completion_lock); - } else { - hash_del(&req->hash_node); - io_poll_complete(req, req->result, 0); - spin_unlock_irq(&ctx->completion_lock); - - nxt = io_put_req_find_next(req); - io_cqring_ev_posted(ctx); - if (nxt) - __io_req_task_submit(nxt); - } + if (io_poll_get_ownership(req)) + __io_poll_execute(req, res); +} - percpu_ref_put(&ctx->refs); +static void io_poll_cancel_req(struct io_kiocb *req) +{ + io_poll_mark_cancelled(req); + /* kick tw, which should complete the request */ + io_poll_execute(req, 0); } -static int io_poll_double_wake(struct wait_queue_entry *wait, unsigned mode, - int sync, void *key) +static int io_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync, + void *key) { struct io_kiocb *req = wait->private; - struct io_poll_iocb *poll = io_poll_get_single(req); + struct io_poll_iocb *poll = container_of(wait, struct io_poll_iocb, + wait); __poll_t mask = key_to_poll(key); - /* for instances that support it check for an event match first: */ + if (unlikely(mask & POLLFREE)) { + io_poll_mark_cancelled(req); + /* we have to kick tw in case it's not already */ + io_poll_execute(req, 0); + + /* + * If the waitqueue is being freed early but someone is already + * holds ownership over it, we have to tear down the request as + * best we can. That means immediately removing the request from + * its waitqueue and preventing all further accesses to the + * waitqueue via the request. + */ + list_del_init(&poll->wait.entry); + + /* + * Careful: this *must* be the last step, since as soon + * as req->head is NULL'ed out, the request can be + * completed and freed, since aio_poll_complete_work() + * will no longer need to take the waitqueue lock. + */ + smp_store_release(&poll->head, NULL); + return 1; + } + + /* for instances that support it check for an event match first */ if (mask && !(mask & poll->events)) return 0; - list_del_init(&wait->entry); + if (io_poll_get_ownership(req)) { + /* + * If we trigger a multishot poll off our own wakeup path, + * disable multishot as there is a circular dependency between + * CQ posting and triggering the event. + */ + if (mask & EPOLL_URING_WAKE) + poll->events |= EPOLLONESHOT; - if (poll && poll->head) { - bool done; - - spin_lock(&poll->head->lock); - done = list_empty(&poll->wait.entry); - if (!done) - list_del_init(&poll->wait.entry); - /* make sure double remove sees this as being gone */ - wait->private = NULL; - spin_unlock(&poll->head->lock); - if (!done) { - /* use wait func handler, so it matches the rq type */ - poll->wait.func(&poll->wait, mode, sync, key); - } + __io_poll_execute(req, mask); } - refcount_dec(&req->refs); return 1; } -static void io_init_poll_iocb(struct io_poll_iocb *poll, __poll_t events, - wait_queue_func_t wake_func) -{ - poll->head = NULL; - poll->done = false; - poll->canceled = false; - poll->events = events; - INIT_LIST_HEAD(&poll->wait.entry); - init_waitqueue_func_entry(&poll->wait, wake_func); -} - static void __io_queue_proc(struct io_poll_iocb *poll, struct io_poll_table *pt, struct wait_queue_head *head, struct io_poll_iocb **poll_ptr) @@ -5098,29 +5517,31 @@ static void __io_queue_proc(struct io_poll_iocb *poll, struct io_poll_table *pt, * if this happens. */ if (unlikely(pt->nr_entries)) { - struct io_poll_iocb *poll_one = poll; + struct io_poll_iocb *first = poll; + /* double add on the same waitqueue head, ignore */ + if (first->head == head) + return; /* already have a 2nd entry, fail a third attempt */ if (*poll_ptr) { + if ((*poll_ptr)->head == head) + return; pt->error = -EINVAL; return; } - /* double add on the same waitqueue head, ignore */ - if (poll->head == head) - return; + poll = kmalloc(sizeof(*poll), GFP_ATOMIC); if (!poll) { pt->error = -ENOMEM; return; } - io_init_poll_iocb(poll, poll_one->events, io_poll_double_wake); - refcount_inc(&req->refs); - poll->wait.private = req; + io_init_poll_iocb(poll, first->events, first->wait.func); *poll_ptr = poll; } pt->nr_entries++; poll->head = head; + poll->wait.private = req; if (poll->events & EPOLLEXCLUSIVE) add_wait_queue_exclusive(head, &poll->wait); @@ -5128,78 +5549,23 @@ static void __io_queue_proc(struct io_poll_iocb *poll, struct io_poll_table *pt, add_wait_queue(head, &poll->wait); } -static void io_async_queue_proc(struct file *file, struct wait_queue_head *head, +static void io_poll_queue_proc(struct file *file, struct wait_queue_head *head, struct poll_table_struct *p) { struct io_poll_table *pt = container_of(p, struct io_poll_table, pt); - struct async_poll *apoll = pt->req->apoll; - - __io_queue_proc(&apoll->poll, pt, head, &apoll->double_poll); -} - -static void io_async_task_func(struct callback_head *cb) -{ - struct io_kiocb *req = container_of(cb, struct io_kiocb, task_work); - struct async_poll *apoll = req->apoll; - struct io_ring_ctx *ctx = req->ctx; - - trace_io_uring_task_run(req->ctx, req->opcode, req->user_data); - - if (io_poll_rewait(req, &apoll->poll)) { - spin_unlock_irq(&ctx->completion_lock); - percpu_ref_put(&ctx->refs); - return; - } - - /* If req is still hashed, it cannot have been canceled. Don't check. */ - if (hash_hashed(&req->hash_node)) - hash_del(&req->hash_node); - - io_poll_remove_double(req); - spin_unlock_irq(&ctx->completion_lock); - - if (!READ_ONCE(apoll->poll.canceled)) - __io_req_task_submit(req); - else - __io_req_task_cancel(req, -ECANCELED); - - percpu_ref_put(&ctx->refs); - kfree(apoll->double_poll); - kfree(apoll); -} - -static int io_async_wake(struct wait_queue_entry *wait, unsigned mode, int sync, - void *key) -{ - struct io_kiocb *req = wait->private; - struct io_poll_iocb *poll = &req->apoll->poll; - - trace_io_uring_poll_wake(req->ctx, req->opcode, req->user_data, - key_to_poll(key)); - - return __io_async_wake(req, poll, key_to_poll(key), io_async_task_func); -} - -static void io_poll_req_insert(struct io_kiocb *req) -{ - struct io_ring_ctx *ctx = req->ctx; - struct hlist_head *list; - list = &ctx->cancel_hash[hash_long(req->user_data, ctx->cancel_hash_bits)]; - hlist_add_head(&req->hash_node, list); + __io_queue_proc(&pt->req->poll, pt, head, + (struct io_poll_iocb **) &pt->req->async_data); } -static __poll_t __io_arm_poll_handler(struct io_kiocb *req, - struct io_poll_iocb *poll, - struct io_poll_table *ipt, __poll_t mask, - wait_queue_func_t wake_func) - __acquires(&ctx->completion_lock) +static int __io_arm_poll_handler(struct io_kiocb *req, + struct io_poll_iocb *poll, + struct io_poll_table *ipt, __poll_t mask) { struct io_ring_ctx *ctx = req->ctx; - bool cancel = false; INIT_HLIST_NODE(&req->hash_node); - io_init_poll_iocb(poll, mask, wake_func); + io_init_poll_iocb(poll, mask, io_poll_wake); poll->file = req->file; poll->wait.private = req; @@ -5208,169 +5574,138 @@ static __poll_t __io_arm_poll_handler(struct io_kiocb *req, ipt->error = 0; ipt->nr_entries = 0; + /* + * Take the ownership to delay any tw execution up until we're done + * with poll arming. see io_poll_get_ownership(). + */ + atomic_set(&req->poll_refs, 1); mask = vfs_poll(req->file, &ipt->pt) & poll->events; - if (unlikely(!ipt->nr_entries) && !ipt->error) - ipt->error = -EINVAL; - - spin_lock_irq(&ctx->completion_lock); - if (ipt->error) - io_poll_remove_double(req); - if (likely(poll->head)) { - spin_lock(&poll->head->lock); - if (unlikely(list_empty(&poll->wait.entry))) { - if (ipt->error) - cancel = true; + + if (mask && (poll->events & EPOLLONESHOT)) { + io_poll_remove_entries(req); + /* no one else has access to the req, forget about the ref */ + return mask; + } + if (!mask && unlikely(ipt->error || !ipt->nr_entries)) { + io_poll_remove_entries(req); + if (!ipt->error) + ipt->error = -EINVAL; + return 0; + } + + spin_lock(&ctx->completion_lock); + io_poll_req_insert(req); + spin_unlock(&ctx->completion_lock); + + if (mask) { + /* can't multishot if failed, just queue the event we've got */ + if (unlikely(ipt->error || !ipt->nr_entries)) { + poll->events |= EPOLLONESHOT; ipt->error = 0; - mask = 0; } - if (mask || ipt->error) - list_del_init(&poll->wait.entry); - else if (cancel) - WRITE_ONCE(poll->canceled, true); - else if (!poll->done) /* actually waiting for an event */ - io_poll_req_insert(req); - spin_unlock(&poll->head->lock); + __io_poll_execute(req, mask); + return 0; } - return mask; + /* + * Try to release ownership. If we see a change of state, e.g. + * poll was waken up, queue up a tw, it'll deal with it. + */ + if (atomic_cmpxchg(&req->poll_refs, 1, 0) != 1) + __io_poll_execute(req, 0); + return 0; +} + +static void io_async_queue_proc(struct file *file, struct wait_queue_head *head, + struct poll_table_struct *p) +{ + struct io_poll_table *pt = container_of(p, struct io_poll_table, pt); + struct async_poll *apoll = pt->req->apoll; + + __io_queue_proc(&apoll->poll, pt, head, &apoll->double_poll); } -static bool io_arm_poll_handler(struct io_kiocb *req) +enum { + IO_APOLL_OK, + IO_APOLL_ABORTED, + IO_APOLL_READY +}; + +static int io_arm_poll_handler(struct io_kiocb *req) { const struct io_op_def *def = &io_op_defs[req->opcode]; struct io_ring_ctx *ctx = req->ctx; struct async_poll *apoll; struct io_poll_table ipt; - __poll_t mask, ret; - int rw; + __poll_t mask = EPOLLONESHOT | POLLERR | POLLPRI; + int ret; if (!req->file || !file_can_poll(req->file)) - return false; + return IO_APOLL_ABORTED; if (req->flags & REQ_F_POLLED) - return false; - if (def->pollin) - rw = READ; - else if (def->pollout) - rw = WRITE; - else - return false; - /* if we can't nonblock try, then no point in arming a poll handler */ - if (!io_file_supports_async(req->file, rw)) - return false; + return IO_APOLL_ABORTED; + if (!def->pollin && !def->pollout) + return IO_APOLL_ABORTED; + + if (def->pollin) { + mask |= POLLIN | POLLRDNORM; + + /* If reading from MSG_ERRQUEUE using recvmsg, ignore POLLIN */ + if ((req->opcode == IORING_OP_RECVMSG) && + (req->sr_msg.msg_flags & MSG_ERRQUEUE)) + mask &= ~POLLIN; + } else { + mask |= POLLOUT | POLLWRNORM; + } apoll = kmalloc(sizeof(*apoll), GFP_ATOMIC); if (unlikely(!apoll)) - return false; + return IO_APOLL_ABORTED; apoll->double_poll = NULL; - - req->flags |= REQ_F_POLLED; req->apoll = apoll; - - mask = 0; - if (def->pollin) - mask |= POLLIN | POLLRDNORM; - if (def->pollout) - mask |= POLLOUT | POLLWRNORM; - - /* If reading from MSG_ERRQUEUE using recvmsg, ignore POLLIN */ - if ((req->opcode == IORING_OP_RECVMSG) && - (req->sr_msg.msg_flags & MSG_ERRQUEUE)) - mask &= ~POLLIN; - - mask |= POLLERR | POLLPRI; - + req->flags |= REQ_F_POLLED; ipt.pt._qproc = io_async_queue_proc; - ret = __io_arm_poll_handler(req, &apoll->poll, &ipt, mask, - io_async_wake); - if (ret || ipt.error) { - io_poll_remove_double(req); - spin_unlock_irq(&ctx->completion_lock); - kfree(apoll->double_poll); - kfree(apoll); - return false; - } - spin_unlock_irq(&ctx->completion_lock); - trace_io_uring_poll_arm(ctx, req->opcode, req->user_data, mask, - apoll->poll.events); - return true; -} - -static bool __io_poll_remove_one(struct io_kiocb *req, - struct io_poll_iocb *poll) -{ - bool do_complete = false; - - spin_lock(&poll->head->lock); - WRITE_ONCE(poll->canceled, true); - if (!list_empty(&poll->wait.entry)) { - list_del_init(&poll->wait.entry); - do_complete = true; - } - spin_unlock(&poll->head->lock); - hash_del(&req->hash_node); - return do_complete; -} - -static bool io_poll_remove_one(struct io_kiocb *req) -{ - bool do_complete; - - io_poll_remove_double(req); - - if (req->opcode == IORING_OP_POLL_ADD) { - do_complete = __io_poll_remove_one(req, &req->poll); - } else { - struct async_poll *apoll = req->apoll; - - /* non-poll requests have submit ref still */ - do_complete = __io_poll_remove_one(req, &apoll->poll); - if (do_complete) { - io_put_req(req); - kfree(apoll->double_poll); - kfree(apoll); - } - } - - if (do_complete) { - io_cqring_fill_event(req, -ECANCELED); - io_commit_cqring(req->ctx); - req_set_fail_links(req); - io_put_req_deferred(req, 1); - } + ret = __io_arm_poll_handler(req, &apoll->poll, &ipt, mask); + if (ret || ipt.error) + return ret ? IO_APOLL_READY : IO_APOLL_ABORTED; - return do_complete; + trace_io_uring_poll_arm(ctx, req, req->opcode, req->user_data, + mask, apoll->poll.events); + return IO_APOLL_OK; } /* * Returns true if we found and killed one or more poll requests */ static bool io_poll_remove_all(struct io_ring_ctx *ctx, struct task_struct *tsk, - struct files_struct *files) + bool cancel_all) { struct hlist_node *tmp; struct io_kiocb *req; - int posted = 0, i; + bool found = false; + int i; - spin_lock_irq(&ctx->completion_lock); + spin_lock(&ctx->completion_lock); for (i = 0; i < (1U << ctx->cancel_hash_bits); i++) { struct hlist_head *list; list = &ctx->cancel_hash[i]; hlist_for_each_entry_safe(req, tmp, list, hash_node) { - if (io_match_task(req, tsk, files)) - posted += io_poll_remove_one(req); + if (io_match_task_safe(req, tsk, cancel_all)) { + hlist_del_init(&req->hash_node); + io_poll_cancel_req(req); + found = true; + } } } - spin_unlock_irq(&ctx->completion_lock); - - if (posted) - io_cqring_ev_posted(ctx); - - return posted != 0; + spin_unlock(&ctx->completion_lock); + return found; } -static int io_poll_cancel(struct io_ring_ctx *ctx, __u64 sqe_addr) +static struct io_kiocb *io_poll_find(struct io_ring_ctx *ctx, __u64 sqe_addr, + bool poll_only) + __must_hold(&ctx->completion_lock) { struct hlist_head *list; struct io_kiocb *req; @@ -5379,107 +5714,161 @@ static int io_poll_cancel(struct io_ring_ctx *ctx, __u64 sqe_addr) hlist_for_each_entry(req, list, hash_node) { if (sqe_addr != req->user_data) continue; - if (io_poll_remove_one(req)) - return 0; - return -EALREADY; + if (poll_only && req->opcode != IORING_OP_POLL_ADD) + continue; + return req; } - - return -ENOENT; + return NULL; } -static int io_poll_remove_prep(struct io_kiocb *req, - const struct io_uring_sqe *sqe) +static bool io_poll_disarm(struct io_kiocb *req) + __must_hold(&ctx->completion_lock) { - if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) - return -EINVAL; - if (sqe->ioprio || sqe->off || sqe->len || sqe->buf_index || - sqe->poll_events) - return -EINVAL; - - req->poll.addr = READ_ONCE(sqe->addr); - return 0; + if (!io_poll_get_ownership(req)) + return false; + io_poll_remove_entries(req); + hash_del(&req->hash_node); + return true; } -/* - * Find a running poll command that matches one specified in sqe->addr, - * and remove it if found. - */ -static int io_poll_remove(struct io_kiocb *req) +static int io_poll_cancel(struct io_ring_ctx *ctx, __u64 sqe_addr, + bool poll_only) + __must_hold(&ctx->completion_lock) { - struct io_ring_ctx *ctx = req->ctx; - u64 addr; - int ret; + struct io_kiocb *req = io_poll_find(ctx, sqe_addr, poll_only); - addr = req->poll.addr; - spin_lock_irq(&ctx->completion_lock); - ret = io_poll_cancel(ctx, addr); - spin_unlock_irq(&ctx->completion_lock); - - if (ret < 0) - req_set_fail_links(req); - io_req_complete(req, ret); + if (!req) + return -ENOENT; + io_poll_cancel_req(req); return 0; } -static int io_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync, - void *key) +static __poll_t io_poll_parse_events(const struct io_uring_sqe *sqe, + unsigned int flags) { - struct io_kiocb *req = wait->private; - struct io_poll_iocb *poll = &req->poll; + u32 events; - return __io_async_wake(req, poll, key_to_poll(key), io_poll_task_func); + events = READ_ONCE(sqe->poll32_events); +#ifdef __BIG_ENDIAN + events = swahw32(events); +#endif + if (!(flags & IORING_POLL_ADD_MULTI)) + events |= EPOLLONESHOT; + return demangle_poll(events) | (events & (EPOLLEXCLUSIVE|EPOLLONESHOT)); } -static void io_poll_queue_proc(struct file *file, struct wait_queue_head *head, - struct poll_table_struct *p) +static int io_poll_update_prep(struct io_kiocb *req, + const struct io_uring_sqe *sqe) { - struct io_poll_table *pt = container_of(p, struct io_poll_table, pt); + struct io_poll_update *upd = &req->poll_update; + u32 flags; + + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; + if (sqe->ioprio || sqe->buf_index || sqe->splice_fd_in) + return -EINVAL; + flags = READ_ONCE(sqe->len); + if (flags & ~(IORING_POLL_UPDATE_EVENTS | IORING_POLL_UPDATE_USER_DATA | + IORING_POLL_ADD_MULTI)) + return -EINVAL; + /* meaningless without update */ + if (flags == IORING_POLL_ADD_MULTI) + return -EINVAL; + + upd->old_user_data = READ_ONCE(sqe->addr); + upd->update_events = flags & IORING_POLL_UPDATE_EVENTS; + upd->update_user_data = flags & IORING_POLL_UPDATE_USER_DATA; + + upd->new_user_data = READ_ONCE(sqe->off); + if (!upd->update_user_data && upd->new_user_data) + return -EINVAL; + if (upd->update_events) + upd->events = io_poll_parse_events(sqe, flags); + else if (sqe->poll32_events) + return -EINVAL; - __io_queue_proc(&pt->req->poll, pt, head, (struct io_poll_iocb **) &pt->req->async_data); + return 0; } static int io_poll_add_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_poll_iocb *poll = &req->poll; - u32 events; + u32 flags; if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; - if (sqe->addr || sqe->ioprio || sqe->off || sqe->len || sqe->buf_index) + if (sqe->ioprio || sqe->buf_index || sqe->off || sqe->addr) + return -EINVAL; + flags = READ_ONCE(sqe->len); + if (flags & ~IORING_POLL_ADD_MULTI) return -EINVAL; - events = READ_ONCE(sqe->poll32_events); -#ifdef __BIG_ENDIAN - events = swahw32(events); -#endif - poll->events = demangle_poll(events) | EPOLLERR | EPOLLHUP | - (events & EPOLLEXCLUSIVE); + io_req_set_refcount(req); + poll->events = io_poll_parse_events(sqe, flags); return 0; } -static int io_poll_add(struct io_kiocb *req) +static int io_poll_add(struct io_kiocb *req, unsigned int issue_flags) { struct io_poll_iocb *poll = &req->poll; - struct io_ring_ctx *ctx = req->ctx; struct io_poll_table ipt; - __poll_t mask; + int ret; ipt.pt._qproc = io_poll_queue_proc; - mask = __io_arm_poll_handler(req, &req->poll, &ipt, poll->events, - io_poll_wake); + ret = __io_arm_poll_handler(req, &req->poll, &ipt, poll->events); + if (!ret && ipt.error) + req_set_fail(req); + ret = ret ?: ipt.error; + if (ret) + __io_req_complete(req, issue_flags, ret, 0); + return 0; +} - if (mask) { /* no async, we'd stolen it */ - ipt.error = 0; - io_poll_complete(req, mask, 0); +static int io_poll_update(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_ring_ctx *ctx = req->ctx; + struct io_kiocb *preq; + int ret2, ret = 0; + + spin_lock(&ctx->completion_lock); + preq = io_poll_find(ctx, req->poll_update.old_user_data, true); + if (!preq || !io_poll_disarm(preq)) { + spin_unlock(&ctx->completion_lock); + ret = preq ? -EALREADY : -ENOENT; + goto out; } - spin_unlock_irq(&ctx->completion_lock); + spin_unlock(&ctx->completion_lock); - if (mask) { - io_cqring_ev_posted(ctx); - io_put_req(req); + if (req->poll_update.update_events || req->poll_update.update_user_data) { + /* only mask one event flags, keep behavior flags */ + if (req->poll_update.update_events) { + preq->poll.events &= ~0xffff; + preq->poll.events |= req->poll_update.events & 0xffff; + preq->poll.events |= IO_POLL_UNMASK; + } + if (req->poll_update.update_user_data) + preq->user_data = req->poll_update.new_user_data; + + ret2 = io_poll_add(preq, issue_flags); + /* successfully updated, don't complete poll request */ + if (!ret2) + goto out; } - return ipt.error; + req_set_fail(preq); + io_req_complete(preq, -ECANCELED); +out: + if (ret < 0) + req_set_fail(req); + /* complete update request, we're done with it */ + io_req_complete(req, ret); + return 0; +} + +static void io_req_task_timeout(struct io_kiocb *req, bool *locked) +{ + req_set_fail(req); + io_req_complete_post(req, -ETIME, 0); } static enum hrtimer_restart io_timeout_fn(struct hrtimer *timer) @@ -5490,88 +5879,182 @@ static enum hrtimer_restart io_timeout_fn(struct hrtimer *timer) struct io_ring_ctx *ctx = req->ctx; unsigned long flags; - spin_lock_irqsave(&ctx->completion_lock, flags); + spin_lock_irqsave(&ctx->timeout_lock, flags); list_del_init(&req->timeout.list); atomic_set(&req->ctx->cq_timeouts, atomic_read(&req->ctx->cq_timeouts) + 1); + spin_unlock_irqrestore(&ctx->timeout_lock, flags); - io_cqring_fill_event(req, -ETIME); - io_commit_cqring(ctx); - spin_unlock_irqrestore(&ctx->completion_lock, flags); - - io_cqring_ev_posted(ctx); - req_set_fail_links(req); - io_put_req(req); + req->io_task_work.func = io_req_task_timeout; + io_req_task_work_add(req); return HRTIMER_NORESTART; } -static int __io_timeout_cancel(struct io_kiocb *req) +static struct io_kiocb *io_timeout_extract(struct io_ring_ctx *ctx, + __u64 user_data) + __must_hold(&ctx->timeout_lock) { - struct io_timeout_data *io = req->async_data; - int ret; + struct io_timeout_data *io; + struct io_kiocb *req; + bool found = false; - ret = hrtimer_try_to_cancel(&io->timer); - if (ret == -1) - return -EALREADY; + list_for_each_entry(req, &ctx->timeout_list, timeout.list) { + found = user_data == req->user_data; + if (found) + break; + } + if (!found) + return ERR_PTR(-ENOENT); + + io = req->async_data; + if (hrtimer_try_to_cancel(&io->timer) == -1) + return ERR_PTR(-EALREADY); list_del_init(&req->timeout.list); + return req; +} + +static int io_timeout_cancel(struct io_ring_ctx *ctx, __u64 user_data) + __must_hold(&ctx->completion_lock) + __must_hold(&ctx->timeout_lock) +{ + struct io_kiocb *req = io_timeout_extract(ctx, user_data); - req_set_fail_links(req); - io_cqring_fill_event(req, -ECANCELED); - io_put_req_deferred(req, 1); + if (IS_ERR(req)) + return PTR_ERR(req); + + req_set_fail(req); + io_fill_cqe_req(req, -ECANCELED, 0); + io_put_req_deferred(req); return 0; } -static int io_timeout_cancel(struct io_ring_ctx *ctx, __u64 user_data) +static clockid_t io_timeout_get_clock(struct io_timeout_data *data) +{ + switch (data->flags & IORING_TIMEOUT_CLOCK_MASK) { + case IORING_TIMEOUT_BOOTTIME: + return CLOCK_BOOTTIME; + case IORING_TIMEOUT_REALTIME: + return CLOCK_REALTIME; + default: + /* can't happen, vetted at prep time */ + WARN_ON_ONCE(1); + fallthrough; + case 0: + return CLOCK_MONOTONIC; + } +} + +static int io_linked_timeout_update(struct io_ring_ctx *ctx, __u64 user_data, + struct timespec64 *ts, enum hrtimer_mode mode) + __must_hold(&ctx->timeout_lock) { + struct io_timeout_data *io; struct io_kiocb *req; - int ret = -ENOENT; + bool found = false; - list_for_each_entry(req, &ctx->timeout_list, timeout.list) { - if (user_data == req->user_data) { - ret = 0; + list_for_each_entry(req, &ctx->ltimeout_list, timeout.list) { + found = user_data == req->user_data; + if (found) break; - } } + if (!found) + return -ENOENT; - if (ret == -ENOENT) - return ret; + io = req->async_data; + if (hrtimer_try_to_cancel(&io->timer) == -1) + return -EALREADY; + hrtimer_init(&io->timer, io_timeout_get_clock(io), mode); + io->timer.function = io_link_timeout_fn; + hrtimer_start(&io->timer, timespec64_to_ktime(*ts), mode); + return 0; +} + +static int io_timeout_update(struct io_ring_ctx *ctx, __u64 user_data, + struct timespec64 *ts, enum hrtimer_mode mode) + __must_hold(&ctx->timeout_lock) +{ + struct io_kiocb *req = io_timeout_extract(ctx, user_data); + struct io_timeout_data *data; + + if (IS_ERR(req)) + return PTR_ERR(req); - return __io_timeout_cancel(req); + req->timeout.off = 0; /* noseq */ + data = req->async_data; + list_add_tail(&req->timeout.list, &ctx->timeout_list); + hrtimer_init(&data->timer, io_timeout_get_clock(data), mode); + data->timer.function = io_timeout_fn; + hrtimer_start(&data->timer, timespec64_to_ktime(*ts), mode); + return 0; } static int io_timeout_remove_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { + struct io_timeout_rem *tr = &req->timeout_rem; + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; if (unlikely(req->flags & (REQ_F_FIXED_FILE | REQ_F_BUFFER_SELECT))) return -EINVAL; - if (sqe->ioprio || sqe->buf_index || sqe->len || sqe->timeout_flags || - sqe->splice_fd_in) + if (sqe->ioprio || sqe->buf_index || sqe->len || sqe->splice_fd_in) + return -EINVAL; + + tr->ltimeout = false; + tr->addr = READ_ONCE(sqe->addr); + tr->flags = READ_ONCE(sqe->timeout_flags); + if (tr->flags & IORING_TIMEOUT_UPDATE_MASK) { + if (hweight32(tr->flags & IORING_TIMEOUT_CLOCK_MASK) > 1) + return -EINVAL; + if (tr->flags & IORING_LINK_TIMEOUT_UPDATE) + tr->ltimeout = true; + if (tr->flags & ~(IORING_TIMEOUT_UPDATE_MASK|IORING_TIMEOUT_ABS)) + return -EINVAL; + if (get_timespec64(&tr->ts, u64_to_user_ptr(sqe->addr2))) + return -EFAULT; + } else if (tr->flags) { + /* timeout removal doesn't support flags */ return -EINVAL; + } - req->timeout_rem.addr = READ_ONCE(sqe->addr); return 0; } +static inline enum hrtimer_mode io_translate_timeout_mode(unsigned int flags) +{ + return (flags & IORING_TIMEOUT_ABS) ? HRTIMER_MODE_ABS + : HRTIMER_MODE_REL; +} + /* * Remove or update an existing timeout command */ -static int io_timeout_remove(struct io_kiocb *req) +static int io_timeout_remove(struct io_kiocb *req, unsigned int issue_flags) { + struct io_timeout_rem *tr = &req->timeout_rem; struct io_ring_ctx *ctx = req->ctx; int ret; - spin_lock_irq(&ctx->completion_lock); - ret = io_timeout_cancel(ctx, req->timeout_rem.addr); + if (!(req->timeout_rem.flags & IORING_TIMEOUT_UPDATE)) { + spin_lock(&ctx->completion_lock); + spin_lock_irq(&ctx->timeout_lock); + ret = io_timeout_cancel(ctx, tr->addr); + spin_unlock_irq(&ctx->timeout_lock); + spin_unlock(&ctx->completion_lock); + } else { + enum hrtimer_mode mode = io_translate_timeout_mode(tr->flags); + + spin_lock_irq(&ctx->timeout_lock); + if (tr->ltimeout) + ret = io_linked_timeout_update(ctx, tr->addr, &tr->ts, mode); + else + ret = io_timeout_update(ctx, tr->addr, &tr->ts, mode); + spin_unlock_irq(&ctx->timeout_lock); + } - io_cqring_fill_event(req, ret); - io_commit_cqring(ctx); - spin_unlock_irq(&ctx->completion_lock); - io_cqring_ev_posted(ctx); if (ret < 0) - req_set_fail_links(req); - io_put_req(req); + req_set_fail(req); + io_req_complete_post(req, ret, 0); return 0; } @@ -5590,38 +6073,52 @@ static int io_timeout_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe, if (off && is_timeout_link) return -EINVAL; flags = READ_ONCE(sqe->timeout_flags); - if (flags & ~IORING_TIMEOUT_ABS) + if (flags & ~(IORING_TIMEOUT_ABS | IORING_TIMEOUT_CLOCK_MASK)) + return -EINVAL; + /* more than one clock specified is invalid, obviously */ + if (hweight32(flags & IORING_TIMEOUT_CLOCK_MASK) > 1) return -EINVAL; + INIT_LIST_HEAD(&req->timeout.list); req->timeout.off = off; + if (unlikely(off && !req->ctx->off_timeout_used)) + req->ctx->off_timeout_used = true; if (!req->async_data && io_alloc_async_data(req)) return -ENOMEM; data = req->async_data; data->req = req; + data->flags = flags; if (get_timespec64(&data->ts, u64_to_user_ptr(sqe->addr))) return -EFAULT; - if (flags & IORING_TIMEOUT_ABS) - data->mode = HRTIMER_MODE_ABS; - else - data->mode = HRTIMER_MODE_REL; - INIT_LIST_HEAD(&req->timeout.list); - hrtimer_init(&data->timer, CLOCK_MONOTONIC, data->mode); + data->mode = io_translate_timeout_mode(flags); + hrtimer_init(&data->timer, io_timeout_get_clock(data), data->mode); + + if (is_timeout_link) { + struct io_submit_link *link = &req->ctx->submit_state.link; + + if (!link->head) + return -EINVAL; + if (link->last->opcode == IORING_OP_LINK_TIMEOUT) + return -EINVAL; + req->timeout.head = link->last; + link->last->flags |= REQ_F_ARM_LTIMEOUT; + } return 0; } -static int io_timeout(struct io_kiocb *req) +static int io_timeout(struct io_kiocb *req, unsigned int issue_flags) { struct io_ring_ctx *ctx = req->ctx; struct io_timeout_data *data = req->async_data; struct list_head *entry; u32 tail, off = req->timeout.off; - spin_lock_irq(&ctx->completion_lock); + spin_lock_irq(&ctx->timeout_lock); /* * sqe->off holds how many events that need to occur for this @@ -5660,23 +6157,34 @@ add: list_add(&req->timeout.list, entry); data->timer.function = io_timeout_fn; hrtimer_start(&data->timer, timespec64_to_ktime(data->ts), data->mode); - spin_unlock_irq(&ctx->completion_lock); + spin_unlock_irq(&ctx->timeout_lock); return 0; } +struct io_cancel_data { + struct io_ring_ctx *ctx; + u64 user_data; +}; + static bool io_cancel_cb(struct io_wq_work *work, void *data) { struct io_kiocb *req = container_of(work, struct io_kiocb, work); + struct io_cancel_data *cd = data; - return req->user_data == (unsigned long) data; + return req->ctx == cd->ctx && req->user_data == cd->user_data; } -static int io_async_cancel_one(struct io_ring_ctx *ctx, void *sqe_addr) +static int io_async_cancel_one(struct io_uring_task *tctx, u64 user_data, + struct io_ring_ctx *ctx) { + struct io_cancel_data data = { .ctx = ctx, .user_data = user_data, }; enum io_wq_cancel cancel_ret; int ret = 0; - cancel_ret = io_wq_cancel_cb(ctx->io_wq, io_cancel_cb, sqe_addr, false); + if (!tctx || !tctx->io_wq) + return -ENOENT; + + cancel_ret = io_wq_cancel_cb(tctx->io_wq, io_cancel_cb, &data, false); switch (cancel_ret) { case IO_WQ_CANCEL_OK: ret = 0; @@ -5692,35 +6200,27 @@ static int io_async_cancel_one(struct io_ring_ctx *ctx, void *sqe_addr) return ret; } -static void io_async_find_and_cancel(struct io_ring_ctx *ctx, - struct io_kiocb *req, __u64 sqe_addr, - int success_ret) +static int io_try_cancel_userdata(struct io_kiocb *req, u64 sqe_addr) { - unsigned long flags; + struct io_ring_ctx *ctx = req->ctx; int ret; - ret = io_async_cancel_one(ctx, (void *) (unsigned long) sqe_addr); - if (ret != -ENOENT) { - spin_lock_irqsave(&ctx->completion_lock, flags); - goto done; - } + WARN_ON_ONCE(!io_wq_current_is_worker() && req->task != current); - spin_lock_irqsave(&ctx->completion_lock, flags); - ret = io_timeout_cancel(ctx, sqe_addr); + ret = io_async_cancel_one(req->task->io_uring, sqe_addr, ctx); if (ret != -ENOENT) - goto done; - ret = io_poll_cancel(ctx, sqe_addr); -done: - if (!ret) - ret = success_ret; - io_cqring_fill_event(req, ret); - io_commit_cqring(ctx); - spin_unlock_irqrestore(&ctx->completion_lock, flags); - io_cqring_ev_posted(ctx); + return ret; - if (ret < 0) - req_set_fail_links(req); - io_put_req(req); + spin_lock(&ctx->completion_lock); + spin_lock_irq(&ctx->timeout_lock); + ret = io_timeout_cancel(ctx, sqe_addr); + spin_unlock_irq(&ctx->timeout_lock); + if (ret != -ENOENT) + goto out; + ret = io_poll_cancel(ctx, sqe_addr, false); +out: + spin_unlock(&ctx->completion_lock); + return ret; } static int io_async_cancel_prep(struct io_kiocb *req, @@ -5738,52 +6238,72 @@ static int io_async_cancel_prep(struct io_kiocb *req, return 0; } -static int io_async_cancel(struct io_kiocb *req) +static int io_async_cancel(struct io_kiocb *req, unsigned int issue_flags) { struct io_ring_ctx *ctx = req->ctx; + u64 sqe_addr = req->cancel.addr; + struct io_tctx_node *node; + int ret; + + ret = io_try_cancel_userdata(req, sqe_addr); + if (ret != -ENOENT) + goto done; - io_async_find_and_cancel(ctx, req, req->cancel.addr, 0); + /* slow path, try all io-wq's */ + io_ring_submit_lock(ctx, !(issue_flags & IO_URING_F_NONBLOCK)); + ret = -ENOENT; + list_for_each_entry(node, &ctx->tctx_list, ctx_node) { + struct io_uring_task *tctx = node->task->io_uring; + + ret = io_async_cancel_one(tctx, req->cancel.addr, ctx); + if (ret != -ENOENT) + break; + } + io_ring_submit_unlock(ctx, !(issue_flags & IO_URING_F_NONBLOCK)); +done: + if (ret < 0) + req_set_fail(req); + io_req_complete_post(req, ret, 0); return 0; } -static int io_files_update_prep(struct io_kiocb *req, +static int io_rsrc_update_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { - if (unlikely(req->ctx->flags & IORING_SETUP_SQPOLL)) - return -EINVAL; if (unlikely(req->flags & (REQ_F_FIXED_FILE | REQ_F_BUFFER_SELECT))) return -EINVAL; - if (sqe->ioprio || sqe->rw_flags) + if (sqe->ioprio || sqe->rw_flags || sqe->splice_fd_in) return -EINVAL; - req->files_update.offset = READ_ONCE(sqe->off); - req->files_update.nr_args = READ_ONCE(sqe->len); - if (!req->files_update.nr_args) + req->rsrc_update.offset = READ_ONCE(sqe->off); + req->rsrc_update.nr_args = READ_ONCE(sqe->len); + if (!req->rsrc_update.nr_args) return -EINVAL; - req->files_update.arg = READ_ONCE(sqe->addr); + req->rsrc_update.arg = READ_ONCE(sqe->addr); return 0; } -static int io_files_update(struct io_kiocb *req, bool force_nonblock, - struct io_comp_state *cs) +static int io_files_update(struct io_kiocb *req, unsigned int issue_flags) { struct io_ring_ctx *ctx = req->ctx; - struct io_uring_files_update up; + struct io_uring_rsrc_update2 up; int ret; - if (force_nonblock) - return -EAGAIN; + up.offset = req->rsrc_update.offset; + up.data = req->rsrc_update.arg; + up.nr = 0; + up.tags = 0; + up.resv = 0; + up.resv2 = 0; - up.offset = req->files_update.offset; - up.fds = req->files_update.arg; - - mutex_lock(&ctx->uring_lock); - ret = __io_sqe_files_update(ctx, &up, req->files_update.nr_args); - mutex_unlock(&ctx->uring_lock); + io_ring_submit_lock(ctx, !(issue_flags & IO_URING_F_NONBLOCK)); + ret = __io_register_rsrc_update(ctx, IORING_RSRC_FILE, + &up, req->rsrc_update.nr_args); + io_ring_submit_unlock(ctx, !(issue_flags & IO_URING_F_NONBLOCK)); if (ret < 0) - req_set_fail_links(req); - __io_req_complete(req, ret, 0, cs); + req_set_fail(req); + __io_req_complete(req, issue_flags, ret, 0); return 0; } @@ -5803,11 +6323,11 @@ static int io_req_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) case IORING_OP_POLL_ADD: return io_poll_add_prep(req, sqe); case IORING_OP_POLL_REMOVE: - return io_poll_remove_prep(req, sqe); + return io_poll_update_prep(req, sqe); case IORING_OP_FSYNC: - return io_prep_fsync(req, sqe); + return io_fsync_prep(req, sqe); case IORING_OP_SYNC_FILE_RANGE: - return io_prep_sfr(req, sqe); + return io_sfr_prep(req, sqe); case IORING_OP_SENDMSG: case IORING_OP_SEND: return io_sendmsg_prep(req, sqe); @@ -5833,7 +6353,7 @@ static int io_req_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) case IORING_OP_CLOSE: return io_close_prep(req, sqe); case IORING_OP_FILES_UPDATE: - return io_files_update_prep(req, sqe); + return io_rsrc_update_prep(req, sqe); case IORING_OP_STATX: return io_statx_prep(req, sqe); case IORING_OP_FADVISE: @@ -5852,100 +6372,131 @@ static int io_req_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) return io_remove_buffers_prep(req, sqe); case IORING_OP_TEE: return io_tee_prep(req, sqe); + case IORING_OP_SHUTDOWN: + return io_shutdown_prep(req, sqe); + case IORING_OP_RENAMEAT: + return io_renameat_prep(req, sqe); + case IORING_OP_UNLINKAT: + return io_unlinkat_prep(req, sqe); } printk_once(KERN_WARNING "io_uring: unhandled opcode %d\n", req->opcode); - return-EINVAL; + return -EINVAL; } -static int io_req_defer_prep(struct io_kiocb *req, - const struct io_uring_sqe *sqe) +static int io_req_prep_async(struct io_kiocb *req) { - if (!sqe) + if (!io_op_defs[req->opcode].needs_async_setup) return 0; + if (WARN_ON_ONCE(req->async_data)) + return -EFAULT; if (io_alloc_async_data(req)) return -EAGAIN; - return io_req_prep(req, sqe); + + switch (req->opcode) { + case IORING_OP_READV: + return io_rw_prep_async(req, READ); + case IORING_OP_WRITEV: + return io_rw_prep_async(req, WRITE); + case IORING_OP_SENDMSG: + return io_sendmsg_prep_async(req); + case IORING_OP_RECVMSG: + return io_recvmsg_prep_async(req); + case IORING_OP_CONNECT: + return io_connect_prep_async(req); + } + printk_once(KERN_WARNING "io_uring: prep_async() bad opcode %d\n", + req->opcode); + return -EFAULT; } static u32 io_get_sequence(struct io_kiocb *req) { - struct io_kiocb *pos; - struct io_ring_ctx *ctx = req->ctx; - u32 total_submitted, nr_reqs = 1; - - if (req->flags & REQ_F_LINK_HEAD) - list_for_each_entry(pos, &req->link_list, link_list) - nr_reqs++; + u32 seq = req->ctx->cached_sq_head; - total_submitted = ctx->cached_sq_head - ctx->cached_sq_dropped; - return total_submitted - nr_reqs; + /* need original cached_sq_head, but it was increased for each req */ + io_for_each_link(req, req) + seq--; + return seq; } -static int io_req_defer(struct io_kiocb *req, const struct io_uring_sqe *sqe) +static bool io_drain_req(struct io_kiocb *req) { + struct io_kiocb *pos; struct io_ring_ctx *ctx = req->ctx; struct io_defer_entry *de; int ret; u32 seq; + if (req->flags & REQ_F_FAIL) { + io_req_complete_fail_submit(req); + return true; + } + + /* + * If we need to drain a request in the middle of a link, drain the + * head request and the next request/link after the current link. + * Considering sequential execution of links, IOSQE_IO_DRAIN will be + * maintained for every request of our link. + */ + if (ctx->drain_next) { + req->flags |= REQ_F_IO_DRAIN; + ctx->drain_next = false; + } + /* not interested in head, start from the first linked */ + io_for_each_link(pos, req->link) { + if (pos->flags & REQ_F_IO_DRAIN) { + ctx->drain_next = true; + req->flags |= REQ_F_IO_DRAIN; + break; + } + } + /* Still need defer if there is pending req in defer list. */ + spin_lock(&ctx->completion_lock); if (likely(list_empty_careful(&ctx->defer_list) && - !(req->flags & REQ_F_IO_DRAIN))) - return 0; + !(req->flags & REQ_F_IO_DRAIN))) { + spin_unlock(&ctx->completion_lock); + ctx->drain_active = false; + return false; + } + spin_unlock(&ctx->completion_lock); seq = io_get_sequence(req); /* Still a chance to pass the sequence check */ if (!req_need_defer(req, seq) && list_empty_careful(&ctx->defer_list)) - return 0; + return false; - if (!req->async_data) { - ret = io_req_defer_prep(req, sqe); - if (ret) - return ret; - } + ret = io_req_prep_async(req); + if (ret) + goto fail; io_prep_async_link(req); de = kmalloc(sizeof(*de), GFP_KERNEL); - if (!de) - return -ENOMEM; + if (!de) { + ret = -ENOMEM; +fail: + io_req_complete_failed(req, ret); + return true; + } - spin_lock_irq(&ctx->completion_lock); + spin_lock(&ctx->completion_lock); if (!req_need_defer(req, seq) && list_empty(&ctx->defer_list)) { - spin_unlock_irq(&ctx->completion_lock); + spin_unlock(&ctx->completion_lock); kfree(de); - io_queue_async_work(req); - return -EIOCBQUEUED; + io_queue_async_work(req, NULL); + return true; } trace_io_uring_defer(ctx, req, req->user_data); de->req = req; de->seq = seq; list_add_tail(&de->list, &ctx->defer_list); - spin_unlock_irq(&ctx->completion_lock); - return -EIOCBQUEUED; -} - -static void io_req_drop_files(struct io_kiocb *req) -{ - struct io_ring_ctx *ctx = req->ctx; - struct io_uring_task *tctx = req->task->io_uring; - unsigned long flags; - - if (req->work.flags & IO_WQ_WORK_FILES) { - put_files_struct(req->work.identity->files); - put_nsproxy(req->work.identity->nsproxy); - } - spin_lock_irqsave(&ctx->inflight_lock, flags); - list_del(&req->inflight_entry); - spin_unlock_irqrestore(&ctx->inflight_lock, flags); - req->flags &= ~REQ_F_INFLIGHT; - req->work.flags &= ~IO_WQ_WORK_FILES; - if (atomic_read(&tctx->in_idle)) - wake_up(&tctx->wait); + spin_unlock(&ctx->completion_lock); + return true; } -static void __io_clean_op(struct io_kiocb *req) +static void io_clean_op(struct io_kiocb *req) { if (req->flags & REQ_F_BUFFER_SELECTED) { switch (req->opcode) { @@ -5959,7 +6510,6 @@ static void __io_clean_op(struct io_kiocb *req) kfree(req->sr_msg.kbuf); break; } - req->flags &= ~REQ_F_BUFFER_SELECTED; } if (req->flags & REQ_F_NEED_CLEANUP) { @@ -5971,508 +6521,589 @@ static void __io_clean_op(struct io_kiocb *req) case IORING_OP_WRITE_FIXED: case IORING_OP_WRITE: { struct io_async_rw *io = req->async_data; - if (io->free_iovec) - kfree(io->free_iovec); + + kfree(io->free_iovec); break; } case IORING_OP_RECVMSG: case IORING_OP_SENDMSG: { struct io_async_msghdr *io = req->async_data; - if (io->iov != io->fast_iov) - kfree(io->iov); + + kfree(io->free_iov); break; } - case IORING_OP_SPLICE: - case IORING_OP_TEE: - io_put_file(req, req->splice.file_in, - (req->splice.flags & SPLICE_F_FD_IN_FIXED)); - break; case IORING_OP_OPENAT: case IORING_OP_OPENAT2: if (req->open.filename) putname(req->open.filename); break; + case IORING_OP_RENAMEAT: + putname(req->rename.oldpath); + putname(req->rename.newpath); + break; + case IORING_OP_UNLINKAT: + putname(req->unlink.filename); + break; } - req->flags &= ~REQ_F_NEED_CLEANUP; } + if ((req->flags & REQ_F_POLLED) && req->apoll) { + kfree(req->apoll->double_poll); + kfree(req->apoll); + req->apoll = NULL; + } + if (req->flags & REQ_F_INFLIGHT) { + struct io_uring_task *tctx = req->task->io_uring; + + atomic_dec(&tctx->inflight_tracked); + } + if (req->flags & REQ_F_CREDS) + put_cred(req->creds); + + req->flags &= ~IO_REQ_CLEAN_FLAGS; } -static int io_issue_sqe(struct io_kiocb *req, bool force_nonblock, - struct io_comp_state *cs) +static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags) { struct io_ring_ctx *ctx = req->ctx; + const struct cred *creds = NULL; int ret; + if ((req->flags & REQ_F_CREDS) && req->creds != current_cred()) + creds = override_creds(req->creds); + switch (req->opcode) { case IORING_OP_NOP: - ret = io_nop(req, cs); + ret = io_nop(req, issue_flags); break; case IORING_OP_READV: case IORING_OP_READ_FIXED: case IORING_OP_READ: - ret = io_read(req, force_nonblock, cs); + ret = io_read(req, issue_flags); break; case IORING_OP_WRITEV: case IORING_OP_WRITE_FIXED: case IORING_OP_WRITE: - ret = io_write(req, force_nonblock, cs); + ret = io_write(req, issue_flags); break; case IORING_OP_FSYNC: - ret = io_fsync(req, force_nonblock); + ret = io_fsync(req, issue_flags); break; case IORING_OP_POLL_ADD: - ret = io_poll_add(req); + ret = io_poll_add(req, issue_flags); break; case IORING_OP_POLL_REMOVE: - ret = io_poll_remove(req); + ret = io_poll_update(req, issue_flags); break; case IORING_OP_SYNC_FILE_RANGE: - ret = io_sync_file_range(req, force_nonblock); + ret = io_sync_file_range(req, issue_flags); break; case IORING_OP_SENDMSG: - ret = io_sendmsg(req, force_nonblock, cs); + ret = io_sendmsg(req, issue_flags); break; case IORING_OP_SEND: - ret = io_send(req, force_nonblock, cs); + ret = io_send(req, issue_flags); break; case IORING_OP_RECVMSG: - ret = io_recvmsg(req, force_nonblock, cs); + ret = io_recvmsg(req, issue_flags); break; case IORING_OP_RECV: - ret = io_recv(req, force_nonblock, cs); + ret = io_recv(req, issue_flags); break; case IORING_OP_TIMEOUT: - ret = io_timeout(req); + ret = io_timeout(req, issue_flags); break; case IORING_OP_TIMEOUT_REMOVE: - ret = io_timeout_remove(req); + ret = io_timeout_remove(req, issue_flags); break; case IORING_OP_ACCEPT: - ret = io_accept(req, force_nonblock, cs); + ret = io_accept(req, issue_flags); break; case IORING_OP_CONNECT: - ret = io_connect(req, force_nonblock, cs); + ret = io_connect(req, issue_flags); break; case IORING_OP_ASYNC_CANCEL: - ret = io_async_cancel(req); + ret = io_async_cancel(req, issue_flags); break; case IORING_OP_FALLOCATE: - ret = io_fallocate(req, force_nonblock); + ret = io_fallocate(req, issue_flags); break; case IORING_OP_OPENAT: - ret = io_openat(req, force_nonblock); + ret = io_openat(req, issue_flags); break; case IORING_OP_CLOSE: - ret = io_close(req, force_nonblock, cs); + ret = io_close(req, issue_flags); break; case IORING_OP_FILES_UPDATE: - ret = io_files_update(req, force_nonblock, cs); + ret = io_files_update(req, issue_flags); break; case IORING_OP_STATX: - ret = io_statx(req, force_nonblock); + ret = io_statx(req, issue_flags); break; case IORING_OP_FADVISE: - ret = io_fadvise(req, force_nonblock); + ret = io_fadvise(req, issue_flags); break; case IORING_OP_MADVISE: - ret = io_madvise(req, force_nonblock); + ret = io_madvise(req, issue_flags); break; case IORING_OP_OPENAT2: - ret = io_openat2(req, force_nonblock); + ret = io_openat2(req, issue_flags); break; case IORING_OP_EPOLL_CTL: - ret = io_epoll_ctl(req, force_nonblock, cs); + ret = io_epoll_ctl(req, issue_flags); break; case IORING_OP_SPLICE: - ret = io_splice(req, force_nonblock); + ret = io_splice(req, issue_flags); break; case IORING_OP_PROVIDE_BUFFERS: - ret = io_provide_buffers(req, force_nonblock, cs); + ret = io_provide_buffers(req, issue_flags); break; case IORING_OP_REMOVE_BUFFERS: - ret = io_remove_buffers(req, force_nonblock, cs); + ret = io_remove_buffers(req, issue_flags); break; case IORING_OP_TEE: - ret = io_tee(req, force_nonblock); + ret = io_tee(req, issue_flags); + break; + case IORING_OP_SHUTDOWN: + ret = io_shutdown(req, issue_flags); + break; + case IORING_OP_RENAMEAT: + ret = io_renameat(req, issue_flags); + break; + case IORING_OP_UNLINKAT: + ret = io_unlinkat(req, issue_flags); break; default: ret = -EINVAL; break; } + if (creds) + revert_creds(creds); if (ret) return ret; - /* If the op doesn't have a file, we're not polling for it */ - if ((ctx->flags & IORING_SETUP_IOPOLL) && req->file) { - const bool in_async = io_wq_current_is_worker(); - - /* workqueue context doesn't hold uring_lock, grab it now */ - if (in_async) - mutex_lock(&ctx->uring_lock); - + if ((ctx->flags & IORING_SETUP_IOPOLL) && req->file) io_iopoll_req_issued(req); - if (in_async) - mutex_unlock(&ctx->uring_lock); - } - return 0; } -static struct io_wq_work *io_wq_submit_work(struct io_wq_work *work) +static struct io_wq_work *io_wq_free_work(struct io_wq_work *work) +{ + struct io_kiocb *req = container_of(work, struct io_kiocb, work); + + req = io_put_req_find_next(req); + return req ? &req->work : NULL; +} + +static void io_wq_submit_work(struct io_wq_work *work) { struct io_kiocb *req = container_of(work, struct io_kiocb, work); struct io_kiocb *timeout; int ret = 0; + /* one will be dropped by ->io_free_work() after returning to io-wq */ + if (!(req->flags & REQ_F_REFCOUNT)) + __io_req_set_refcount(req, 2); + else + req_ref_get(req); + timeout = io_prep_linked_timeout(req); if (timeout) io_queue_linked_timeout(timeout); - /* if NO_CANCEL is set, we must still run the work */ - if ((work->flags & (IO_WQ_WORK_CANCEL|IO_WQ_WORK_NO_CANCEL)) == - IO_WQ_WORK_CANCEL) { + /* either cancelled or io-wq is dying, so don't touch tctx->iowq */ + if (work->flags & IO_WQ_WORK_CANCEL) ret = -ECANCELED; - } if (!ret) { do { - ret = io_issue_sqe(req, false, NULL); + ret = io_issue_sqe(req, 0); /* * We can get EAGAIN for polled IO even though we're * forcing a sync submission from here, since we can't * wait for request slots on the block side. */ - if (ret != -EAGAIN) + if (ret != -EAGAIN || !(req->ctx->flags & IORING_SETUP_IOPOLL)) break; cond_resched(); } while (1); } - if (ret) { - struct io_ring_ctx *lock_ctx = NULL; - - if (req->ctx->flags & IORING_SETUP_IOPOLL) - lock_ctx = req->ctx; - - /* - * io_iopoll_complete() does not hold completion_lock to - * complete polled io, so here for polled io, we can not call - * io_req_complete() directly, otherwise there maybe concurrent - * access to cqring, defer_list, etc, which is not safe. Given - * that io_iopoll_complete() is always called under uring_lock, - * so here for polled io, we also get uring_lock to complete - * it. - */ - if (lock_ctx) - mutex_lock(&lock_ctx->uring_lock); - - req_set_fail_links(req); - io_req_complete(req, ret); - - if (lock_ctx) - mutex_unlock(&lock_ctx->uring_lock); - } + /* avoid locking problems by failing it from a clean context */ + if (ret) + io_req_task_queue_fail(req, ret); +} - return io_steal_work(req); +static inline struct io_fixed_file *io_fixed_file_slot(struct io_file_table *table, + unsigned i) +{ + return &table->files[i]; } static inline struct file *io_file_from_index(struct io_ring_ctx *ctx, int index) { - struct fixed_file_table *table; + struct io_fixed_file *slot = io_fixed_file_slot(&ctx->file_table, index); - table = &ctx->file_data->table[index >> IORING_FILE_TABLE_SHIFT]; - return table->files[index & IORING_FILE_TABLE_MASK]; + return (struct file *) (slot->file_ptr & FFS_MASK); } -static struct file *io_file_get(struct io_submit_state *state, - struct io_kiocb *req, int fd, bool fixed) +static void io_fixed_file_set(struct io_fixed_file *file_slot, struct file *file) +{ + unsigned long file_ptr = (unsigned long) file; + + if (__io_file_supports_nowait(file, READ)) + file_ptr |= FFS_ASYNC_READ; + if (__io_file_supports_nowait(file, WRITE)) + file_ptr |= FFS_ASYNC_WRITE; + if (S_ISREG(file_inode(file)->i_mode)) + file_ptr |= FFS_ISREG; + file_slot->file_ptr = file_ptr; +} + +static inline struct file *io_file_get_fixed(struct io_ring_ctx *ctx, + struct io_kiocb *req, int fd) { - struct io_ring_ctx *ctx = req->ctx; struct file *file; + unsigned long file_ptr; - if (fixed) { - if (unlikely((unsigned int)fd >= ctx->nr_user_files)) - return NULL; - fd = array_index_nospec(fd, ctx->nr_user_files); - file = io_file_from_index(ctx, fd); - if (file) { - req->fixed_file_refs = &ctx->file_data->node->refs; - percpu_ref_get(req->fixed_file_refs); - } - } else { - trace_io_uring_file_get(ctx, fd); - file = __io_file_get(state, fd); - } + if (unlikely((unsigned int)fd >= ctx->nr_user_files)) + return NULL; + fd = array_index_nospec(fd, ctx->nr_user_files); + file_ptr = io_fixed_file_slot(&ctx->file_table, fd)->file_ptr; + file = (struct file *) (file_ptr & FFS_MASK); + file_ptr &= ~FFS_MASK; + /* mask in overlapping REQ_F and FFS bits */ + req->flags |= (file_ptr << REQ_F_NOWAIT_READ_BIT); + io_req_set_rsrc_node(req); + return file; +} - if (file && file->f_op == &io_uring_fops && - !(req->flags & REQ_F_INFLIGHT)) { - io_req_init_async(req); - req->flags |= REQ_F_INFLIGHT; +static struct file *io_file_get_normal(struct io_ring_ctx *ctx, + struct io_kiocb *req, int fd) +{ + struct file *file = fget(fd); - spin_lock_irq(&ctx->inflight_lock); - list_add(&req->inflight_entry, &ctx->inflight_list); - spin_unlock_irq(&ctx->inflight_lock); - } + trace_io_uring_file_get(ctx, fd); + /* we don't allow fixed io_uring files */ + if (file && unlikely(file->f_op == &io_uring_fops)) + io_req_track_inflight(req); return file; } -static int io_req_set_file(struct io_submit_state *state, struct io_kiocb *req, - int fd) +static inline struct file *io_file_get(struct io_ring_ctx *ctx, + struct io_kiocb *req, int fd, bool fixed) { - bool fixed; + if (fixed) + return io_file_get_fixed(ctx, req, fd); + else + return io_file_get_normal(ctx, req, fd); +} - fixed = (req->flags & REQ_F_FIXED_FILE) != 0; - if (unlikely(!fixed && io_async_submit(req->ctx))) - return -EBADF; +static void io_req_task_link_timeout(struct io_kiocb *req, bool *locked) +{ + struct io_kiocb *prev = req->timeout.prev; + int ret = -ENOENT; - req->file = io_file_get(state, req, fd, fixed); - if (req->file || io_op_defs[req->opcode].needs_file_no_error) - return 0; - return -EBADF; + if (prev) { + if (!(req->task->flags & PF_EXITING)) + ret = io_try_cancel_userdata(req, prev->user_data); + io_req_complete_post(req, ret ?: -ETIME, 0); + io_put_req(prev); + } else { + io_req_complete_post(req, -ETIME, 0); + } } static enum hrtimer_restart io_link_timeout_fn(struct hrtimer *timer) { struct io_timeout_data *data = container_of(timer, struct io_timeout_data, timer); - struct io_kiocb *req = data->req; + struct io_kiocb *prev, *req = data->req; struct io_ring_ctx *ctx = req->ctx; - struct io_kiocb *prev = NULL; unsigned long flags; - spin_lock_irqsave(&ctx->completion_lock, flags); + spin_lock_irqsave(&ctx->timeout_lock, flags); + prev = req->timeout.head; + req->timeout.head = NULL; /* * We don't expect the list to be empty, that will only happen if we * race with the completion of the linked work. */ - if (!list_empty(&req->link_list)) { - prev = list_entry(req->link_list.prev, struct io_kiocb, - link_list); - list_del_init(&req->link_list); - if (!refcount_inc_not_zero(&prev->refs)) + if (prev) { + io_remove_next_linked(prev); + if (!req_ref_inc_not_zero(prev)) prev = NULL; } - list_del(&req->timeout.list); - spin_unlock_irqrestore(&ctx->completion_lock, flags); + req->timeout.prev = prev; + spin_unlock_irqrestore(&ctx->timeout_lock, flags); - if (prev) { - io_async_find_and_cancel(ctx, req, prev->user_data, -ETIME); - io_put_req_deferred(prev, 1); - } else { - io_cqring_add_event(req, -ETIME, 0); - io_put_req_deferred(req, 1); - } + req->io_task_work.func = io_req_task_link_timeout; + io_req_task_work_add(req); return HRTIMER_NORESTART; } -static void __io_queue_linked_timeout(struct io_kiocb *req) +static void io_queue_linked_timeout(struct io_kiocb *req) { + struct io_ring_ctx *ctx = req->ctx; + + spin_lock_irq(&ctx->timeout_lock); /* - * If the list is now empty, then our linked request finished before - * we got a chance to setup the timer + * If the back reference is NULL, then our linked request finished + * before we got a chance to setup the timer */ - if (!list_empty(&req->link_list)) { + if (req->timeout.head) { struct io_timeout_data *data = req->async_data; data->timer.function = io_link_timeout_fn; hrtimer_start(&data->timer, timespec64_to_ktime(data->ts), data->mode); + list_add_tail(&req->timeout.list, &ctx->ltimeout_list); } -} - -static void io_queue_linked_timeout(struct io_kiocb *req) -{ - struct io_ring_ctx *ctx = req->ctx; - - spin_lock_irq(&ctx->completion_lock); - __io_queue_linked_timeout(req); - spin_unlock_irq(&ctx->completion_lock); - + spin_unlock_irq(&ctx->timeout_lock); /* drop submission reference */ io_put_req(req); } -static struct io_kiocb *io_prep_linked_timeout(struct io_kiocb *req) -{ - struct io_kiocb *nxt; - - if (!(req->flags & REQ_F_LINK_HEAD)) - return NULL; - if (req->flags & REQ_F_LINK_TIMEOUT) - return NULL; - - nxt = list_first_entry_or_null(&req->link_list, struct io_kiocb, - link_list); - if (!nxt || nxt->opcode != IORING_OP_LINK_TIMEOUT) - return NULL; - - nxt->flags |= REQ_F_LTIMEOUT_ACTIVE; - req->flags |= REQ_F_LINK_TIMEOUT; - return nxt; -} - -static void __io_queue_sqe(struct io_kiocb *req, struct io_comp_state *cs) +static void __io_queue_sqe(struct io_kiocb *req) + __must_hold(&req->ctx->uring_lock) { struct io_kiocb *linked_timeout; - const struct cred *old_creds = NULL; int ret; -again: - linked_timeout = io_prep_linked_timeout(req); - - if ((req->flags & REQ_F_WORK_INITIALIZED) && - (req->work.flags & IO_WQ_WORK_CREDS) && - req->work.identity->creds != current_cred()) { - if (old_creds) - revert_creds(old_creds); - if (old_creds == req->work.identity->creds) - old_creds = NULL; /* restored original creds */ - else - old_creds = override_creds(req->work.identity->creds); - } - - ret = io_issue_sqe(req, true, cs); +issue_sqe: + ret = io_issue_sqe(req, IO_URING_F_NONBLOCK|IO_URING_F_COMPLETE_DEFER); /* * We async punt it if the file wasn't marked NOWAIT, or if the file * doesn't support non-blocking read/write attempts */ - if (ret == -EAGAIN && !(req->flags & REQ_F_NOWAIT)) { - if (!io_arm_poll_handler(req)) { + if (likely(!ret)) { + if (req->flags & REQ_F_COMPLETE_INLINE) { + struct io_ring_ctx *ctx = req->ctx; + struct io_submit_state *state = &ctx->submit_state; + + state->compl_reqs[state->compl_nr++] = req; + if (state->compl_nr == ARRAY_SIZE(state->compl_reqs)) + io_submit_flush_completions(ctx); + return; + } + + linked_timeout = io_prep_linked_timeout(req); + if (linked_timeout) + io_queue_linked_timeout(linked_timeout); + } else if (ret == -EAGAIN && !(req->flags & REQ_F_NOWAIT)) { + linked_timeout = io_prep_linked_timeout(req); + + switch (io_arm_poll_handler(req)) { + case IO_APOLL_READY: + if (linked_timeout) + io_queue_linked_timeout(linked_timeout); + goto issue_sqe; + case IO_APOLL_ABORTED: /* * Queued up for async execution, worker will release * submit reference when the iocb is actually submitted. */ - io_queue_async_work(req); + io_queue_async_work(req, NULL); + break; } if (linked_timeout) io_queue_linked_timeout(linked_timeout); - } else if (likely(!ret)) { - /* drop submission reference */ - req = io_put_req_find_next(req); - if (linked_timeout) - io_queue_linked_timeout(linked_timeout); - - if (req) { - if (!(req->flags & REQ_F_FORCE_ASYNC)) - goto again; - io_queue_async_work(req); - } } else { - /* un-prep timeout, so it'll be killed as any other linked */ - req->flags &= ~REQ_F_LINK_TIMEOUT; - req_set_fail_links(req); - io_put_req(req); - io_req_complete(req, ret); + io_req_complete_failed(req, ret); } - - if (old_creds) - revert_creds(old_creds); } -static void io_queue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe, - struct io_comp_state *cs) +static inline void io_queue_sqe(struct io_kiocb *req) + __must_hold(&req->ctx->uring_lock) { - int ret; + if (unlikely(req->ctx->drain_active) && io_drain_req(req)) + return; - ret = io_req_defer(req, sqe); - if (ret) { - if (ret != -EIOCBQUEUED) { -fail_req: - req_set_fail_links(req); - io_put_req(req); - io_req_complete(req, ret); - } - } else if (req->flags & REQ_F_FORCE_ASYNC) { - if (!req->async_data) { - ret = io_req_defer_prep(req, sqe); - if (unlikely(ret)) - goto fail_req; - } - io_queue_async_work(req); + if (likely(!(req->flags & (REQ_F_FORCE_ASYNC | REQ_F_FAIL)))) { + __io_queue_sqe(req); + } else if (req->flags & REQ_F_FAIL) { + io_req_complete_fail_submit(req); } else { - if (sqe) { - ret = io_req_prep(req, sqe); - if (unlikely(ret)) - goto fail_req; - } - __io_queue_sqe(req, cs); + int ret = io_req_prep_async(req); + + if (unlikely(ret)) + io_req_complete_failed(req, ret); + else + io_queue_async_work(req, NULL); } } -static inline void io_queue_link_head(struct io_kiocb *req, - struct io_comp_state *cs) +/* + * Check SQE restrictions (opcode and flags). + * + * Returns 'true' if SQE is allowed, 'false' otherwise. + */ +static inline bool io_check_restriction(struct io_ring_ctx *ctx, + struct io_kiocb *req, + unsigned int sqe_flags) { - if (unlikely(req->flags & REQ_F_FAIL_LINK)) { - io_put_req(req); - io_req_complete(req, -ECANCELED); - } else - io_queue_sqe(req, NULL, cs); + if (likely(!ctx->restricted)) + return true; + + if (!test_bit(req->opcode, ctx->restrictions.sqe_op)) + return false; + + if ((sqe_flags & ctx->restrictions.sqe_flags_required) != + ctx->restrictions.sqe_flags_required) + return false; + + if (sqe_flags & ~(ctx->restrictions.sqe_flags_allowed | + ctx->restrictions.sqe_flags_required)) + return false; + + return true; } -static int io_submit_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe, - struct io_kiocb **link, struct io_comp_state *cs) +static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, + const struct io_uring_sqe *sqe) + __must_hold(&ctx->uring_lock) { - struct io_ring_ctx *ctx = req->ctx; - int ret; + struct io_submit_state *state; + unsigned int sqe_flags; + int personality, ret = 0; - /* - * If we already have a head request, queue this one for async - * submittal once the head completes. If we don't have a head but - * IOSQE_IO_LINK is set in the sqe, start a new head. This one will be - * submitted sync once the chain is complete. If none of those - * conditions are true (normal request), then just queue it. - */ - if (*link) { - struct io_kiocb *head = *link; + /* req is partially pre-initialised, see io_preinit_req() */ + req->opcode = READ_ONCE(sqe->opcode); + /* same numerical values with corresponding REQ_F_*, safe to copy */ + req->flags = sqe_flags = READ_ONCE(sqe->flags); + req->user_data = READ_ONCE(sqe->user_data); + req->file = NULL; + req->fixed_rsrc_refs = NULL; + req->task = current; - /* - * Taking sequential execution of a link, draining both sides - * of the link also fullfils IOSQE_IO_DRAIN semantics for all - * requests in the link. So, it drains the head and the - * next after the link request. The last one is done via - * drain_next flag to persist the effect across calls. - */ - if (req->flags & REQ_F_IO_DRAIN) { - head->flags |= REQ_F_IO_DRAIN; - ctx->drain_next = 1; - } - ret = io_req_defer_prep(req, sqe); - if (unlikely(ret)) { - /* fail even hard links since we don't submit */ - head->flags |= REQ_F_FAIL_LINK; + /* enforce forwards compatibility on users */ + if (unlikely(sqe_flags & ~SQE_VALID_FLAGS)) + return -EINVAL; + if (unlikely(req->opcode >= IORING_OP_LAST)) + return -EINVAL; + if (!io_check_restriction(ctx, req, sqe_flags)) + return -EACCES; + + if ((sqe_flags & IOSQE_BUFFER_SELECT) && + !io_op_defs[req->opcode].buffer_select) + return -EOPNOTSUPP; + if (unlikely(sqe_flags & IOSQE_IO_DRAIN)) + ctx->drain_active = true; + + personality = READ_ONCE(sqe->personality); + if (personality) { + req->creds = xa_load(&ctx->personalities, personality); + if (!req->creds) + return -EINVAL; + get_cred(req->creds); + req->flags |= REQ_F_CREDS; + } + state = &ctx->submit_state; + + /* + * Plug now if we have more than 1 IO left after this, and the target + * is potentially a read/write to block based storage. + */ + if (!state->plug_started && state->ios_left > 1 && + io_op_defs[req->opcode].plug) { + blk_start_plug(&state->plug); + state->plug_started = true; + } + + if (io_op_defs[req->opcode].needs_file) { + req->file = io_file_get(ctx, req, READ_ONCE(sqe->fd), + (sqe_flags & IOSQE_FIXED_FILE)); + if (unlikely(!req->file)) + ret = -EBADF; + } + + state->ios_left--; + return ret; +} + +static int io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req, + const struct io_uring_sqe *sqe) + __must_hold(&ctx->uring_lock) +{ + struct io_submit_link *link = &ctx->submit_state.link; + int ret; + + ret = io_init_req(ctx, req, sqe); + if (unlikely(ret)) { +fail_req: + /* fail even hard links since we don't submit */ + if (link->head) { + /* + * we can judge a link req is failed or cancelled by if + * REQ_F_FAIL is set, but the head is an exception since + * it may be set REQ_F_FAIL because of other req's failure + * so let's leverage req->result to distinguish if a head + * is set REQ_F_FAIL because of its failure or other req's + * failure so that we can set the correct ret code for it. + * init result here to avoid affecting the normal path. + */ + if (!(link->head->flags & REQ_F_FAIL)) + req_fail_link_node(link->head, -ECANCELED); + } else if (!(req->flags & (REQ_F_LINK | REQ_F_HARDLINK))) { + /* + * the current req is a normal req, we should return + * error and thus break the submittion loop. + */ + io_req_complete_failed(req, ret); return ret; } + req_fail_link_node(req, ret); + } else { + ret = io_req_prep(req, sqe); + if (unlikely(ret)) + goto fail_req; + } + + /* don't need @sqe from now on */ + trace_io_uring_submit_sqe(ctx, req, req->opcode, req->user_data, + req->flags, true, + ctx->flags & IORING_SETUP_SQPOLL); + + /* + * If we already have a head request, queue this one for async + * submittal once the head completes. If we don't have a head but + * IOSQE_IO_LINK is set in the sqe, start a new head. This one will be + * submitted sync once the chain is complete. If none of those + * conditions are true (normal request), then just queue it. + */ + if (link->head) { + struct io_kiocb *head = link->head; + + if (!(req->flags & REQ_F_FAIL)) { + ret = io_req_prep_async(req); + if (unlikely(ret)) { + req_fail_link_node(req, ret); + if (!(head->flags & REQ_F_FAIL)) + req_fail_link_node(head, -ECANCELED); + } + } trace_io_uring_link(ctx, req, head); - list_add_tail(&req->link_list, &head->link_list); + link->last->link = req; + link->last = req; /* last request of a link, enqueue the link */ if (!(req->flags & (REQ_F_LINK | REQ_F_HARDLINK))) { - io_queue_link_head(head, cs); - *link = NULL; + link->head = NULL; + io_queue_sqe(head); } } else { - if (unlikely(ctx->drain_next)) { - req->flags |= REQ_F_IO_DRAIN; - ctx->drain_next = 0; - } if (req->flags & (REQ_F_LINK | REQ_F_HARDLINK)) { - req->flags |= REQ_F_LINK_HEAD; - INIT_LIST_HEAD(&req->link_list); - - ret = io_req_defer_prep(req, sqe); - if (unlikely(ret)) - req->flags |= REQ_F_FAIL_LINK; - *link = req; + link->head = req; + link->last = req; } else { - io_queue_sqe(req, sqe, cs); + io_queue_sqe(req); } } @@ -6482,29 +7113,27 @@ static int io_submit_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe, /* * Batched submission is done, ensure local IO is flushed out. */ -static void io_submit_state_end(struct io_submit_state *state) +static void io_submit_state_end(struct io_submit_state *state, + struct io_ring_ctx *ctx) { - if (!list_empty(&state->comp.list)) - io_submit_flush_completions(&state->comp); - blk_finish_plug(&state->plug); - io_state_file_put(state); - if (state->free_reqs) - kmem_cache_free_bulk(req_cachep, state->free_reqs, state->reqs); + if (state->link.head) + io_queue_sqe(state->link.head); + if (state->compl_nr) + io_submit_flush_completions(ctx); + if (state->plug_started) + blk_finish_plug(&state->plug); } /* * Start submission side cache. */ static void io_submit_state_start(struct io_submit_state *state, - struct io_ring_ctx *ctx, unsigned int max_ios) -{ - blk_start_plug(&state->plug); - state->comp.nr = 0; - INIT_LIST_HEAD(&state->comp.list); - state->comp.ctx = ctx; - state->free_reqs = 0; - state->file = NULL; + unsigned int max_ios) +{ + state->plug_started = false; state->ios_left = max_ios; + /* set only head, no need to init link_last in advance */ + state->link.head = NULL; } static void io_commit_sqring(struct io_ring_ctx *ctx) @@ -6520,7 +7149,7 @@ static void io_commit_sqring(struct io_ring_ctx *ctx) } /* - * Fetch an sqe, if one is available. Note that sqe_ptr will point to memory + * Fetch an sqe, if one is available. Note this returns a pointer to memory * that is mapped by userspace. This means that care needs to be taken to * ensure that reads are stable, as we cannot rely on userspace always * being a good citizen. If members of the sqe are validated and then later @@ -6529,8 +7158,8 @@ static void io_commit_sqring(struct io_ring_ctx *ctx) */ static const struct io_uring_sqe *io_get_sqe(struct io_ring_ctx *ctx) { - u32 *sq_array = ctx->sq_array; - unsigned head; + unsigned head, mask = ctx->sq_entries - 1; + unsigned sq_idx = ctx->cached_sq_head++ & mask; /* * The cached sq head (or cq tail) serves two purposes: @@ -6540,423 +7169,256 @@ static const struct io_uring_sqe *io_get_sqe(struct io_ring_ctx *ctx) * 2) allows the kernel side to track the head on its own, even * though the application is the one updating it. */ - head = READ_ONCE(sq_array[ctx->cached_sq_head & ctx->sq_mask]); + head = READ_ONCE(ctx->sq_array[sq_idx]); if (likely(head < ctx->sq_entries)) return &ctx->sq_sqes[head]; /* drop invalid entries */ - ctx->cached_sq_dropped++; - WRITE_ONCE(ctx->rings->sq_dropped, ctx->cached_sq_dropped); + ctx->cq_extra--; + WRITE_ONCE(ctx->rings->sq_dropped, + READ_ONCE(ctx->rings->sq_dropped) + 1); return NULL; } -static inline void io_consume_sqe(struct io_ring_ctx *ctx) -{ - ctx->cached_sq_head++; -} - -/* - * Check SQE restrictions (opcode and flags). - * - * Returns 'true' if SQE is allowed, 'false' otherwise. - */ -static inline bool io_check_restriction(struct io_ring_ctx *ctx, - struct io_kiocb *req, - unsigned int sqe_flags) -{ - if (!ctx->restricted) - return true; - - if (!test_bit(req->opcode, ctx->restrictions.sqe_op)) - return false; - - if ((sqe_flags & ctx->restrictions.sqe_flags_required) != - ctx->restrictions.sqe_flags_required) - return false; - - if (sqe_flags & ~(ctx->restrictions.sqe_flags_allowed | - ctx->restrictions.sqe_flags_required)) - return false; - - return true; -} - -#define SQE_VALID_FLAGS (IOSQE_FIXED_FILE|IOSQE_IO_DRAIN|IOSQE_IO_LINK| \ - IOSQE_IO_HARDLINK | IOSQE_ASYNC | \ - IOSQE_BUFFER_SELECT) - -static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, - const struct io_uring_sqe *sqe, - struct io_submit_state *state) -{ - unsigned int sqe_flags; - int id, ret; - - req->opcode = READ_ONCE(sqe->opcode); - req->user_data = READ_ONCE(sqe->user_data); - req->async_data = NULL; - req->file = NULL; - req->ctx = ctx; - req->flags = 0; - /* one is dropped after submission, the other at completion */ - refcount_set(&req->refs, 2); - req->task = current; - req->result = 0; - - if (unlikely(req->opcode >= IORING_OP_LAST)) - return -EINVAL; - - if (unlikely(io_sq_thread_acquire_mm(ctx, req))) - return -EFAULT; - - sqe_flags = READ_ONCE(sqe->flags); - /* enforce forwards compatibility on users */ - if (unlikely(sqe_flags & ~SQE_VALID_FLAGS)) - return -EINVAL; - - if (unlikely(!io_check_restriction(ctx, req, sqe_flags))) - return -EACCES; - - if ((sqe_flags & IOSQE_BUFFER_SELECT) && - !io_op_defs[req->opcode].buffer_select) - return -EOPNOTSUPP; - - id = READ_ONCE(sqe->personality); - if (id) { - struct io_identity *iod; - - iod = xa_load(&ctx->personalities, id); - if (unlikely(!iod)) - return -EINVAL; - refcount_inc(&iod->count); - - __io_req_init_async(req); - get_cred(iod->creds); - req->work.identity = iod; - req->work.flags |= IO_WQ_WORK_CREDS; - } - - /* same numerical values with corresponding REQ_F_*, safe to copy */ - req->flags |= sqe_flags; - - if (!io_op_defs[req->opcode].needs_file) - return 0; - - ret = io_req_set_file(state, req, READ_ONCE(sqe->fd)); - state->ios_left--; - return ret; -} - static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr) + __must_hold(&ctx->uring_lock) { - struct io_submit_state state; - struct io_kiocb *link = NULL; - int i, submitted = 0; - - /* if we have a backlog and couldn't flush it all, return BUSY */ - if (test_bit(0, &ctx->sq_check_overflow)) { - if (!__io_cqring_overflow_flush(ctx, false, NULL, NULL)) - return -EBUSY; - } + int submitted = 0; /* make sure SQ entry isn't read before tail */ nr = min3(nr, ctx->sq_entries, io_sqring_entries(ctx)); - if (!percpu_ref_tryget_many(&ctx->refs, nr)) return -EAGAIN; + io_get_task_refs(nr); - percpu_counter_add(¤t->io_uring->inflight, nr); - refcount_add(nr, ¤t->usage); - - io_submit_state_start(&state, ctx, nr); - - for (i = 0; i < nr; i++) { + io_submit_state_start(&ctx->submit_state, nr); + while (submitted < nr) { const struct io_uring_sqe *sqe; struct io_kiocb *req; - int err; - sqe = io_get_sqe(ctx); - if (unlikely(!sqe)) { - io_consume_sqe(ctx); - break; - } - req = io_alloc_req(ctx, &state); + req = io_alloc_req(ctx); if (unlikely(!req)) { if (!submitted) submitted = -EAGAIN; break; } - io_consume_sqe(ctx); + sqe = io_get_sqe(ctx); + if (unlikely(!sqe)) { + list_add(&req->inflight_entry, &ctx->submit_state.free_list); + break; + } /* will complete beyond this point, count as submitted */ submitted++; - - err = io_init_req(ctx, req, sqe, &state); - if (unlikely(err)) { -fail_req: - io_put_req(req); - io_req_complete(req, err); + if (io_submit_sqe(ctx, req, sqe)) break; - } - - trace_io_uring_submit_sqe(ctx, req->opcode, req->user_data, - true, io_async_submit(ctx)); - err = io_submit_sqe(req, sqe, &link, &state.comp); - if (err) - goto fail_req; } if (unlikely(submitted != nr)) { int ref_used = (submitted == -EAGAIN) ? 0 : submitted; - struct io_uring_task *tctx = current->io_uring; int unused = nr - ref_used; + current->io_uring->cached_refs += unused; percpu_ref_put_many(&ctx->refs, unused); - percpu_counter_sub(&tctx->inflight, unused); - put_task_struct_many(current, unused); } - if (link) - io_queue_link_head(link, &state.comp); - io_submit_state_end(&state); + io_submit_state_end(&ctx->submit_state, ctx); /* Commit SQ ring head once we've consumed and submitted all SQEs */ io_commit_sqring(ctx); return submitted; } -static inline void io_ring_set_wakeup_flag(struct io_ring_ctx *ctx) +static inline bool io_sqd_events_pending(struct io_sq_data *sqd) { - /* Tell userspace we may need a wakeup call */ - spin_lock_irq(&ctx->completion_lock); - ctx->rings->sq_flags |= IORING_SQ_NEED_WAKEUP; - spin_unlock_irq(&ctx->completion_lock); + return READ_ONCE(sqd->state); } -static inline void io_ring_clear_wakeup_flag(struct io_ring_ctx *ctx) +static inline void io_ring_set_wakeup_flag(struct io_ring_ctx *ctx) { - spin_lock_irq(&ctx->completion_lock); - ctx->rings->sq_flags &= ~IORING_SQ_NEED_WAKEUP; - spin_unlock_irq(&ctx->completion_lock); + /* Tell userspace we may need a wakeup call */ + spin_lock(&ctx->completion_lock); + WRITE_ONCE(ctx->rings->sq_flags, + ctx->rings->sq_flags | IORING_SQ_NEED_WAKEUP); + spin_unlock(&ctx->completion_lock); } -static int io_sq_wake_function(struct wait_queue_entry *wqe, unsigned mode, - int sync, void *key) +static inline void io_ring_clear_wakeup_flag(struct io_ring_ctx *ctx) { - struct io_ring_ctx *ctx = container_of(wqe, struct io_ring_ctx, sqo_wait_entry); - int ret; - - ret = autoremove_wake_function(wqe, mode, sync, key); - if (ret) { - unsigned long flags; - - spin_lock_irqsave(&ctx->completion_lock, flags); - ctx->rings->sq_flags &= ~IORING_SQ_NEED_WAKEUP; - spin_unlock_irqrestore(&ctx->completion_lock, flags); - } - return ret; + spin_lock(&ctx->completion_lock); + WRITE_ONCE(ctx->rings->sq_flags, + ctx->rings->sq_flags & ~IORING_SQ_NEED_WAKEUP); + spin_unlock(&ctx->completion_lock); } -enum sq_ret { - SQT_IDLE = 1, - SQT_SPIN = 2, - SQT_DID_WORK = 4, -}; - -static enum sq_ret __io_sq_thread(struct io_ring_ctx *ctx, - unsigned long start_jiffies, bool cap_entries) +static int __io_sq_thread(struct io_ring_ctx *ctx, bool cap_entries) { - unsigned long timeout = start_jiffies + ctx->sq_thread_idle; - struct io_sq_data *sqd = ctx->sq_data; unsigned int to_submit; int ret = 0; -again: - if (!list_empty(&ctx->iopoll_list)) { - unsigned nr_events = 0; - - mutex_lock(&ctx->uring_lock); - if (!list_empty(&ctx->iopoll_list) && !need_resched()) - io_do_iopoll(ctx, &nr_events, 0); - mutex_unlock(&ctx->uring_lock); - } - to_submit = io_sqring_entries(ctx); + /* if we're handling multiple rings, cap submit size for fairness */ + if (cap_entries && to_submit > IORING_SQPOLL_CAP_ENTRIES_VALUE) + to_submit = IORING_SQPOLL_CAP_ENTRIES_VALUE; - /* - * If submit got -EBUSY, flag us as needing the application - * to enter the kernel to reap and flush events. - */ - if (!to_submit || ret == -EBUSY || need_resched()) { - /* - * Drop cur_mm before scheduling, we can't hold it for - * long periods (or over schedule()). Do this before - * adding ourselves to the waitqueue, as the unuse/drop - * may sleep. - */ - io_sq_thread_drop_mm(); + if (!list_empty(&ctx->iopoll_list) || to_submit) { + unsigned nr_events = 0; + const struct cred *creds = NULL; - /* - * We're polling. If we're within the defined idle - * period, then let us spin without work before going - * to sleep. The exception is if we got EBUSY doing - * more IO, we should wait for the application to - * reap events and wake us up. - */ - if (!list_empty(&ctx->iopoll_list) || need_resched() || - (!time_after(jiffies, timeout) && ret != -EBUSY && - !percpu_ref_is_dying(&ctx->refs))) - return SQT_SPIN; + if (ctx->sq_creds != current_cred()) + creds = override_creds(ctx->sq_creds); - prepare_to_wait(&sqd->wait, &ctx->sqo_wait_entry, - TASK_INTERRUPTIBLE); + mutex_lock(&ctx->uring_lock); + if (!list_empty(&ctx->iopoll_list)) + io_do_iopoll(ctx, &nr_events, 0); /* - * While doing polled IO, before going to sleep, we need - * to check if there are new reqs added to iopoll_list, - * it is because reqs may have been punted to io worker - * and will be added to iopoll_list later, hence check - * the iopoll_list again. + * Don't submit if refs are dying, good for io_uring_register(), + * but also it is relied upon by io_ring_exit_work() */ - if ((ctx->flags & IORING_SETUP_IOPOLL) && - !list_empty_careful(&ctx->iopoll_list)) { - finish_wait(&sqd->wait, &ctx->sqo_wait_entry); - goto again; - } + if (to_submit && likely(!percpu_ref_is_dying(&ctx->refs)) && + !(ctx->flags & IORING_SETUP_R_DISABLED)) + ret = io_submit_sqes(ctx, to_submit); + mutex_unlock(&ctx->uring_lock); - to_submit = io_sqring_entries(ctx); - if (!to_submit || ret == -EBUSY) - return SQT_IDLE; + if (to_submit && wq_has_sleeper(&ctx->sqo_sq_wait)) + wake_up(&ctx->sqo_sq_wait); + if (creds) + revert_creds(creds); } - finish_wait(&sqd->wait, &ctx->sqo_wait_entry); - io_ring_clear_wakeup_flag(ctx); - - /* if we're handling multiple rings, cap submit size for fairness */ - if (cap_entries && to_submit > 8) - to_submit = 8; - - mutex_lock(&ctx->uring_lock); - if (likely(!percpu_ref_is_dying(&ctx->refs) && !ctx->sqo_dead)) - ret = io_submit_sqes(ctx, to_submit); - mutex_unlock(&ctx->uring_lock); + return ret; +} - if (!io_sqring_full(ctx) && wq_has_sleeper(&ctx->sqo_sq_wait)) - wake_up(&ctx->sqo_sq_wait); +static void io_sqd_update_thread_idle(struct io_sq_data *sqd) +{ + struct io_ring_ctx *ctx; + unsigned sq_thread_idle = 0; - return SQT_DID_WORK; + list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) + sq_thread_idle = max(sq_thread_idle, ctx->sq_thread_idle); + sqd->sq_thread_idle = sq_thread_idle; } -static void io_sqd_init_new(struct io_sq_data *sqd) +static bool io_sqd_handle_event(struct io_sq_data *sqd) { - struct io_ring_ctx *ctx; + bool did_sig = false; + struct ksignal ksig; - while (!list_empty(&sqd->ctx_new_list)) { - ctx = list_first_entry(&sqd->ctx_new_list, struct io_ring_ctx, sqd_list); - init_wait(&ctx->sqo_wait_entry); - ctx->sqo_wait_entry.func = io_sq_wake_function; - list_move_tail(&ctx->sqd_list, &sqd->ctx_list); - complete(&ctx->sq_thread_comp); + if (test_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state) || + signal_pending(current)) { + mutex_unlock(&sqd->lock); + if (signal_pending(current)) + did_sig = get_signal(&ksig); + cond_resched(); + mutex_lock(&sqd->lock); } + return did_sig || test_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state); } static int io_sq_thread(void *data) { - struct cgroup_subsys_state *cur_css = NULL; - const struct cred *old_cred = NULL; struct io_sq_data *sqd = data; struct io_ring_ctx *ctx; - unsigned long start_jiffies; + unsigned long timeout = 0; + char buf[TASK_COMM_LEN]; + DEFINE_WAIT(wait); - start_jiffies = jiffies; - while (!kthread_should_stop()) { - enum sq_ret ret = 0; - bool cap_entries; + snprintf(buf, sizeof(buf), "iou-sqp-%d", sqd->task_pid); + set_task_comm(current, buf); - /* - * Any changes to the sqd lists are synchronized through the - * kthread parking. This synchronizes the thread vs users, - * the users are synchronized on the sqd->ctx_lock. - */ - if (kthread_should_park()) { - kthread_parkme(); - /* - * When sq thread is unparked, in case the previous park operation - * comes from io_put_sq_data(), which means that sq thread is going - * to be stopped, so here needs to have a check. - */ - if (kthread_should_stop()) + if (sqd->sq_cpu != -1) + set_cpus_allowed_ptr(current, cpumask_of(sqd->sq_cpu)); + else + set_cpus_allowed_ptr(current, cpu_online_mask); + current->flags |= PF_NO_SETAFFINITY; + + mutex_lock(&sqd->lock); + while (1) { + bool cap_entries, sqt_spin = false; + + if (io_sqd_events_pending(sqd) || signal_pending(current)) { + if (io_sqd_handle_event(sqd)) break; + timeout = jiffies + sqd->sq_thread_idle; } - if (unlikely(!list_empty(&sqd->ctx_new_list))) - io_sqd_init_new(sqd); - cap_entries = !list_is_singular(&sqd->ctx_list); - list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) { - if (current->cred != ctx->creds) { - if (old_cred) - revert_creds(old_cred); - old_cred = override_creds(ctx->creds); - } - io_sq_thread_associate_blkcg(ctx, &cur_css); -#ifdef CONFIG_AUDIT - current->loginuid = ctx->loginuid; - current->sessionid = ctx->sessionid; -#endif - - ret |= __io_sq_thread(ctx, start_jiffies, cap_entries); + int ret = __io_sq_thread(ctx, cap_entries); - io_sq_thread_drop_mm(); + if (!sqt_spin && (ret > 0 || !list_empty(&ctx->iopoll_list))) + sqt_spin = true; } + if (io_run_task_work()) + sqt_spin = true; - if (ret & SQT_SPIN) { - io_run_task_work(); - io_sq_thread_drop_mm(); + if (sqt_spin || !time_after(jiffies, timeout)) { cond_resched(); - } else if (ret == SQT_IDLE) { - if (kthread_should_park()) - continue; - list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) + if (sqt_spin) + timeout = jiffies + sqd->sq_thread_idle; + continue; + } + + prepare_to_wait(&sqd->wait, &wait, TASK_INTERRUPTIBLE); + if (!io_sqd_events_pending(sqd) && !current->task_works) { + bool needs_sched = true; + + list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) { io_ring_set_wakeup_flag(ctx); - schedule(); - start_jiffies = jiffies; + + if ((ctx->flags & IORING_SETUP_IOPOLL) && + !list_empty_careful(&ctx->iopoll_list)) { + needs_sched = false; + break; + } + if (io_sqring_entries(ctx)) { + needs_sched = false; + break; + } + } + + if (needs_sched) { + mutex_unlock(&sqd->lock); + schedule(); + mutex_lock(&sqd->lock); + } list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) io_ring_clear_wakeup_flag(ctx); } + + finish_wait(&sqd->wait, &wait); + timeout = jiffies + sqd->sq_thread_idle; } + io_uring_cancel_generic(true, sqd); + sqd->thread = NULL; + list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) + io_ring_set_wakeup_flag(ctx); io_run_task_work(); - io_sq_thread_drop_mm(); - - if (cur_css) - io_sq_thread_unassociate_blkcg(); - if (old_cred) - revert_creds(old_cred); - - kthread_parkme(); + mutex_unlock(&sqd->lock); - return 0; + complete(&sqd->exited); + do_exit(0); } struct io_wait_queue { struct wait_queue_entry wq; struct io_ring_ctx *ctx; - unsigned to_wait; + unsigned cq_tail; unsigned nr_timeouts; }; static inline bool io_should_wake(struct io_wait_queue *iowq) { struct io_ring_ctx *ctx = iowq->ctx; + int dist = ctx->cached_cq_tail - (int) iowq->cq_tail; /* * Wake up if we have enough events, or if a timeout occurred since we * started waiting. For timeouts, we always want to return to userspace, * regardless of event count. */ - return io_cqring_events(ctx) >= iowq->to_wait || - atomic_read(&ctx->cq_timeouts) != iowq->nr_timeouts; + return dist >= 0 || atomic_read(&ctx->cq_timeouts) != iowq->nr_timeouts; } static int io_wake_function(struct wait_queue_entry *curr, unsigned int mode, @@ -6969,7 +7431,7 @@ static int io_wake_function(struct wait_queue_entry *curr, unsigned int mode, * Cannot safely flush overflowed CQEs from here, ensure we wake up * the task, and the next invocation will do it. */ - if (io_should_wake(iowq) || test_bit(0, &iowq->ctx->cq_check_overflow)) + if (io_should_wake(iowq) || test_bit(0, &iowq->ctx->check_cq_overflow)) return autoremove_wake_function(curr, mode, wake_flags, key); return -1; } @@ -6980,43 +7442,60 @@ static int io_run_task_work_sig(void) return 1; if (!signal_pending(current)) return 0; - if (current->jobctl & JOBCTL_TASK_WORK) { - spin_lock_irq(¤t->sighand->siglock); - current->jobctl &= ~JOBCTL_TASK_WORK; - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); - return 1; - } + if (test_thread_flag(TIF_NOTIFY_SIGNAL)) + return -ERESTARTSYS; return -EINTR; } +/* when returns >0, the caller should retry */ +static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx, + struct io_wait_queue *iowq, + ktime_t timeout) +{ + int ret; + + /* make sure we run task_work before checking for signals */ + ret = io_run_task_work_sig(); + if (ret || io_should_wake(iowq)) + return ret; + /* let the caller flush overflows, retry */ + if (test_bit(0, &ctx->check_cq_overflow)) + return 1; + + if (!schedule_hrtimeout(&timeout, HRTIMER_MODE_ABS)) + return -ETIME; + return 1; +} + /* * Wait until events become available, if we don't already have some. The * application must reap them itself, as they reside on the shared cq ring. */ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, - const sigset_t __user *sig, size_t sigsz) -{ - struct io_wait_queue iowq = { - .wq = { - .private = current, - .func = io_wake_function, - .entry = LIST_HEAD_INIT(iowq.wq.entry), - }, - .ctx = ctx, - .to_wait = min_events, - }; + const sigset_t __user *sig, size_t sigsz, + struct __kernel_timespec __user *uts) +{ + struct io_wait_queue iowq; struct io_rings *rings = ctx->rings; - int ret = 0; + ktime_t timeout = KTIME_MAX; + int ret; do { - io_cqring_overflow_flush(ctx, false, NULL, NULL); + io_cqring_overflow_flush(ctx); if (io_cqring_events(ctx) >= min_events) return 0; if (!io_run_task_work()) break; } while (1); + if (uts) { + struct timespec64 ts; + + if (get_timespec64(&ts, uts)) + return -EFAULT; + timeout = ktime_add_ns(timespec64_to_ktime(ts), ktime_get_ns()); + } + if (sig) { #ifdef CONFIG_COMPAT if (in_compat_syscall()) @@ -7026,37 +7505,271 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, #endif ret = set_user_sigmask(sig, sigsz); - if (ret) - return ret; + if (ret) + return ret; + } + + init_waitqueue_func_entry(&iowq.wq, io_wake_function); + iowq.wq.private = current; + INIT_LIST_HEAD(&iowq.wq.entry); + iowq.ctx = ctx; + iowq.nr_timeouts = atomic_read(&ctx->cq_timeouts); + iowq.cq_tail = READ_ONCE(ctx->rings->cq.head) + min_events; + + trace_io_uring_cqring_wait(ctx, min_events); + do { + /* if we can't even flush overflow, don't wait for more */ + if (!io_cqring_overflow_flush(ctx)) { + ret = -EBUSY; + break; + } + prepare_to_wait_exclusive(&ctx->cq_wait, &iowq.wq, + TASK_INTERRUPTIBLE); + ret = io_cqring_wait_schedule(ctx, &iowq, timeout); + finish_wait(&ctx->cq_wait, &iowq.wq); + cond_resched(); + } while (ret > 0); + + restore_saved_sigmask_unless(ret == -EINTR); + + return READ_ONCE(rings->cq.head) == READ_ONCE(rings->cq.tail) ? ret : 0; +} + +static void io_free_page_table(void **table, size_t size) +{ + unsigned i, nr_tables = DIV_ROUND_UP(size, PAGE_SIZE); + + for (i = 0; i < nr_tables; i++) + kfree(table[i]); + kfree(table); +} + +static void **io_alloc_page_table(size_t size) +{ + unsigned i, nr_tables = DIV_ROUND_UP(size, PAGE_SIZE); + size_t init_size = size; + void **table; + + table = kcalloc(nr_tables, sizeof(*table), GFP_KERNEL_ACCOUNT); + if (!table) + return NULL; + + for (i = 0; i < nr_tables; i++) { + unsigned int this_size = min_t(size_t, size, PAGE_SIZE); + + table[i] = kzalloc(this_size, GFP_KERNEL_ACCOUNT); + if (!table[i]) { + io_free_page_table(table, init_size); + return NULL; + } + size -= this_size; + } + return table; +} + +static void io_rsrc_node_destroy(struct io_rsrc_node *ref_node) +{ + percpu_ref_exit(&ref_node->refs); + kfree(ref_node); +} + +static void io_rsrc_node_ref_zero(struct percpu_ref *ref) +{ + struct io_rsrc_node *node = container_of(ref, struct io_rsrc_node, refs); + struct io_ring_ctx *ctx = node->rsrc_data->ctx; + unsigned long flags; + bool first_add = false; + unsigned long delay = HZ; + + spin_lock_irqsave(&ctx->rsrc_ref_lock, flags); + node->done = true; + + /* if we are mid-quiesce then do not delay */ + if (node->rsrc_data->quiesce) + delay = 0; + + while (!list_empty(&ctx->rsrc_ref_list)) { + node = list_first_entry(&ctx->rsrc_ref_list, + struct io_rsrc_node, node); + /* recycle ref nodes in order */ + if (!node->done) + break; + list_del(&node->node); + first_add |= llist_add(&node->llist, &ctx->rsrc_put_llist); + } + spin_unlock_irqrestore(&ctx->rsrc_ref_lock, flags); + + if (first_add) + mod_delayed_work(system_wq, &ctx->rsrc_put_work, delay); +} + +static struct io_rsrc_node *io_rsrc_node_alloc(struct io_ring_ctx *ctx) +{ + struct io_rsrc_node *ref_node; + + ref_node = kzalloc(sizeof(*ref_node), GFP_KERNEL); + if (!ref_node) + return NULL; + + if (percpu_ref_init(&ref_node->refs, io_rsrc_node_ref_zero, + 0, GFP_KERNEL)) { + kfree(ref_node); + return NULL; + } + INIT_LIST_HEAD(&ref_node->node); + INIT_LIST_HEAD(&ref_node->rsrc_list); + ref_node->done = false; + return ref_node; +} + +static void io_rsrc_node_switch(struct io_ring_ctx *ctx, + struct io_rsrc_data *data_to_kill) +{ + WARN_ON_ONCE(!ctx->rsrc_backup_node); + WARN_ON_ONCE(data_to_kill && !ctx->rsrc_node); + + if (data_to_kill) { + struct io_rsrc_node *rsrc_node = ctx->rsrc_node; + + rsrc_node->rsrc_data = data_to_kill; + spin_lock_irq(&ctx->rsrc_ref_lock); + list_add_tail(&rsrc_node->node, &ctx->rsrc_ref_list); + spin_unlock_irq(&ctx->rsrc_ref_lock); + + atomic_inc(&data_to_kill->refs); + percpu_ref_kill(&rsrc_node->refs); + ctx->rsrc_node = NULL; + } + + if (!ctx->rsrc_node) { + ctx->rsrc_node = ctx->rsrc_backup_node; + ctx->rsrc_backup_node = NULL; + } +} + +static int io_rsrc_node_switch_start(struct io_ring_ctx *ctx) +{ + if (ctx->rsrc_backup_node) + return 0; + ctx->rsrc_backup_node = io_rsrc_node_alloc(ctx); + return ctx->rsrc_backup_node ? 0 : -ENOMEM; +} + +static int io_rsrc_ref_quiesce(struct io_rsrc_data *data, struct io_ring_ctx *ctx) +{ + int ret; + + /* As we may drop ->uring_lock, other task may have started quiesce */ + if (data->quiesce) + return -ENXIO; + + data->quiesce = true; + do { + ret = io_rsrc_node_switch_start(ctx); + if (ret) + break; + io_rsrc_node_switch(ctx, data); + + /* kill initial ref, already quiesced if zero */ + if (atomic_dec_and_test(&data->refs)) + break; + mutex_unlock(&ctx->uring_lock); + flush_delayed_work(&ctx->rsrc_put_work); + ret = wait_for_completion_interruptible(&data->done); + if (!ret) { + mutex_lock(&ctx->uring_lock); + if (atomic_read(&data->refs) > 0) { + /* + * it has been revived by another thread while + * we were unlocked + */ + mutex_unlock(&ctx->uring_lock); + } else { + break; + } + } + + atomic_inc(&data->refs); + /* wait for all works potentially completing data->done */ + flush_delayed_work(&ctx->rsrc_put_work); + reinit_completion(&data->done); + + ret = io_run_task_work_sig(); + mutex_lock(&ctx->uring_lock); + } while (ret >= 0); + data->quiesce = false; + + return ret; +} + +static u64 *io_get_tag_slot(struct io_rsrc_data *data, unsigned int idx) +{ + unsigned int off = idx & IO_RSRC_TAG_TABLE_MASK; + unsigned int table_idx = idx >> IO_RSRC_TAG_TABLE_SHIFT; + + return &data->tags[table_idx][off]; +} + +static void io_rsrc_data_free(struct io_rsrc_data *data) +{ + size_t size = data->nr * sizeof(data->tags[0][0]); + + if (data->tags) + io_free_page_table((void **)data->tags, size); + kfree(data); +} + +static int io_rsrc_data_alloc(struct io_ring_ctx *ctx, rsrc_put_fn *do_put, + u64 __user *utags, unsigned nr, + struct io_rsrc_data **pdata) +{ + struct io_rsrc_data *data; + int ret = -ENOMEM; + unsigned i; + + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; + data->tags = (u64 **)io_alloc_page_table(nr * sizeof(data->tags[0][0])); + if (!data->tags) { + kfree(data); + return -ENOMEM; } - iowq.nr_timeouts = atomic_read(&ctx->cq_timeouts); - trace_io_uring_cqring_wait(ctx, min_events); - do { - io_cqring_overflow_flush(ctx, false, NULL, NULL); - prepare_to_wait_exclusive(&ctx->wait, &iowq.wq, - TASK_INTERRUPTIBLE); - /* make sure we run task_work before checking for signals */ - ret = io_run_task_work_sig(); - if (ret > 0) { - finish_wait(&ctx->wait, &iowq.wq); - continue; - } - else if (ret < 0) - break; - if (io_should_wake(&iowq)) - break; - if (test_bit(0, &ctx->cq_check_overflow)) { - finish_wait(&ctx->wait, &iowq.wq); - continue; + data->nr = nr; + data->ctx = ctx; + data->do_put = do_put; + if (utags) { + ret = -EFAULT; + for (i = 0; i < nr; i++) { + u64 *tag_slot = io_get_tag_slot(data, i); + + if (copy_from_user(tag_slot, &utags[i], + sizeof(*tag_slot))) + goto fail; } - schedule(); - } while (1); - finish_wait(&ctx->wait, &iowq.wq); + } - restore_saved_sigmask_unless(ret == -EINTR); + atomic_set(&data->refs, 1); + init_completion(&data->done); + *pdata = data; + return 0; +fail: + io_rsrc_data_free(data); + return ret; +} - return READ_ONCE(rings->cq.head) == READ_ONCE(rings->cq.tail) ? ret : 0; +static bool io_alloc_file_tables(struct io_file_table *table, unsigned nr_files) +{ + table->files = kvcalloc(nr_files, sizeof(table->files[0]), + GFP_KERNEL_ACCOUNT); + return !!table->files; +} + +static void io_free_file_tables(struct io_file_table *table) +{ + kvfree(table->files); + table->files = NULL; } static void __io_sqe_files_unregister(struct io_ring_ctx *ctx) @@ -7080,92 +7793,97 @@ static void __io_sqe_files_unregister(struct io_ring_ctx *ctx) fput(file); } #endif + io_free_file_tables(&ctx->file_table); + io_rsrc_data_free(ctx->file_data); + ctx->file_data = NULL; + ctx->nr_user_files = 0; } -static void io_file_ref_kill(struct percpu_ref *ref) +static int io_sqe_files_unregister(struct io_ring_ctx *ctx) { - struct fixed_file_data *data; + unsigned nr = ctx->nr_user_files; + int ret; - data = container_of(ref, struct fixed_file_data, refs); - complete(&data->done); -} + if (!ctx->file_data) + return -ENXIO; -static void io_sqe_files_set_node(struct fixed_file_data *file_data, - struct fixed_file_ref_node *ref_node) -{ - spin_lock_bh(&file_data->lock); - file_data->node = ref_node; - list_add_tail(&ref_node->node, &file_data->ref_list); - spin_unlock_bh(&file_data->lock); - percpu_ref_get(&file_data->refs); + /* + * Quiesce may unlock ->uring_lock, and while it's not held + * prevent new requests using the table. + */ + ctx->nr_user_files = 0; + ret = io_rsrc_ref_quiesce(ctx->file_data, ctx); + ctx->nr_user_files = nr; + if (!ret) + __io_sqe_files_unregister(ctx); + return ret; } -static int io_sqe_files_unregister(struct io_ring_ctx *ctx) +static void io_sq_thread_unpark(struct io_sq_data *sqd) + __releases(&sqd->lock) { - struct fixed_file_data *data = ctx->file_data; - struct fixed_file_ref_node *backup_node, *ref_node = NULL; - unsigned nr_tables, i; - int ret; + WARN_ON_ONCE(sqd->thread == current); - if (!data) - return -ENXIO; - backup_node = alloc_fixed_file_ref_node(ctx); - if (!backup_node) - return -ENOMEM; + /* + * Do the dance but not conditional clear_bit() because it'd race with + * other threads incrementing park_pending and setting the bit. + */ + clear_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state); + if (atomic_dec_return(&sqd->park_pending)) + set_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state); + mutex_unlock(&sqd->lock); +} - spin_lock_bh(&data->lock); - ref_node = data->node; - spin_unlock_bh(&data->lock); - if (ref_node) - percpu_ref_kill(&ref_node->refs); +static void io_sq_thread_park(struct io_sq_data *sqd) + __acquires(&sqd->lock) +{ + WARN_ON_ONCE(sqd->thread == current); - percpu_ref_kill(&data->refs); + atomic_inc(&sqd->park_pending); + set_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state); + mutex_lock(&sqd->lock); + if (sqd->thread) + wake_up_process(sqd->thread); +} - /* wait for all refs nodes to complete */ - flush_delayed_work(&ctx->file_put_work); - do { - ret = wait_for_completion_interruptible(&data->done); - if (!ret) - break; - ret = io_run_task_work_sig(); - if (ret < 0) { - percpu_ref_resurrect(&data->refs); - reinit_completion(&data->done); - io_sqe_files_set_node(data, backup_node); - return ret; - } - } while (1); +static void io_sq_thread_stop(struct io_sq_data *sqd) +{ + WARN_ON_ONCE(sqd->thread == current); + WARN_ON_ONCE(test_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state)); - __io_sqe_files_unregister(ctx); - nr_tables = DIV_ROUND_UP(ctx->nr_user_files, IORING_MAX_FILES_TABLE); - for (i = 0; i < nr_tables; i++) - kfree(data->table[i].files); - kfree(data->table); - percpu_ref_exit(&data->refs); - kfree(data); - ctx->file_data = NULL; - ctx->nr_user_files = 0; - destroy_fixed_file_ref_node(backup_node); - return 0; + set_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state); + mutex_lock(&sqd->lock); + if (sqd->thread) + wake_up_process(sqd->thread); + mutex_unlock(&sqd->lock); + wait_for_completion(&sqd->exited); } static void io_put_sq_data(struct io_sq_data *sqd) { if (refcount_dec_and_test(&sqd->refs)) { - /* - * The park is a bit of a work-around, without it we get - * warning spews on shutdown with SQPOLL set and affinity - * set to a single CPU. - */ - if (sqd->thread) { - kthread_park(sqd->thread); - kthread_stop(sqd->thread); - } + WARN_ON_ONCE(atomic_read(&sqd->park_pending)); + io_sq_thread_stop(sqd); kfree(sqd); } } +static void io_sq_thread_finish(struct io_ring_ctx *ctx) +{ + struct io_sq_data *sqd = ctx->sq_data; + + if (sqd) { + io_sq_thread_park(sqd); + list_del_init(&ctx->sqd_list); + io_sqd_update_thread_idle(sqd); + io_sq_thread_unpark(sqd); + + io_put_sq_data(sqd); + ctx->sq_data = NULL; + } +} + static struct io_sq_data *io_attach_sq_data(struct io_uring_params *p) { struct io_ring_ctx *ctx_attach; @@ -7186,92 +7904,46 @@ static struct io_sq_data *io_attach_sq_data(struct io_uring_params *p) fdput(f); return ERR_PTR(-EINVAL); } + if (sqd->task_tgid != current->tgid) { + fdput(f); + return ERR_PTR(-EPERM); + } refcount_inc(&sqd->refs); fdput(f); return sqd; } -static struct io_sq_data *io_get_sq_data(struct io_uring_params *p) +static struct io_sq_data *io_get_sq_data(struct io_uring_params *p, + bool *attached) { struct io_sq_data *sqd; - if (p->flags & IORING_SETUP_ATTACH_WQ) - return io_attach_sq_data(p); + *attached = false; + if (p->flags & IORING_SETUP_ATTACH_WQ) { + sqd = io_attach_sq_data(p); + if (!IS_ERR(sqd)) { + *attached = true; + return sqd; + } + /* fall through for EPERM case, setup new sqd/task */ + if (PTR_ERR(sqd) != -EPERM) + return sqd; + } sqd = kzalloc(sizeof(*sqd), GFP_KERNEL); if (!sqd) return ERR_PTR(-ENOMEM); + atomic_set(&sqd->park_pending, 0); refcount_set(&sqd->refs, 1); INIT_LIST_HEAD(&sqd->ctx_list); - INIT_LIST_HEAD(&sqd->ctx_new_list); - mutex_init(&sqd->ctx_lock); mutex_init(&sqd->lock); init_waitqueue_head(&sqd->wait); + init_completion(&sqd->exited); return sqd; } -static void io_sq_thread_unpark(struct io_sq_data *sqd) - __releases(&sqd->lock) -{ - if (!sqd->thread) - return; - kthread_unpark(sqd->thread); - mutex_unlock(&sqd->lock); -} - -static void io_sq_thread_park(struct io_sq_data *sqd) - __acquires(&sqd->lock) -{ - if (!sqd->thread) - return; - mutex_lock(&sqd->lock); - kthread_park(sqd->thread); -} - -static void io_sq_thread_stop(struct io_ring_ctx *ctx) -{ - struct io_sq_data *sqd = ctx->sq_data; - - if (sqd) { - if (sqd->thread) { - /* - * We may arrive here from the error branch in - * io_sq_offload_create() where the kthread is created - * without being waked up, thus wake it up now to make - * sure the wait will complete. - */ - wake_up_process(sqd->thread); - wait_for_completion(&ctx->sq_thread_comp); - - io_sq_thread_park(sqd); - } - - mutex_lock(&sqd->ctx_lock); - list_del(&ctx->sqd_list); - mutex_unlock(&sqd->ctx_lock); - - if (sqd->thread) { - finish_wait(&sqd->wait, &ctx->sqo_wait_entry); - io_sq_thread_unpark(sqd); - } - - io_put_sq_data(sqd); - ctx->sq_data = NULL; - } -} - -static void io_finish_async(struct io_ring_ctx *ctx) -{ - io_sq_thread_stop(ctx); - - if (ctx->io_wq) { - io_wq_destroy(ctx->io_wq); - ctx->io_wq = NULL; - } -} - #if defined(CONFIG_UNIX) /* * Ensure the UNIX gc is aware of our file set, so we are certain that @@ -7296,9 +7968,10 @@ static int __io_sqe_files_scm(struct io_ring_ctx *ctx, int nr, int offset) } skb->sk = sk; + skb->scm_io_uring = 1; nr_files = 0; - fpl->user = get_uid(ctx->user); + fpl->user = get_uid(current_user()); for (i = 0; i < nr; i++) { struct file *file = io_file_from_index(ctx, i + offset); @@ -7374,35 +8047,9 @@ static int io_sqe_files_scm(struct io_ring_ctx *ctx) } #endif -static int io_sqe_alloc_file_tables(struct fixed_file_data *file_data, - unsigned nr_tables, unsigned nr_files) -{ - int i; - - for (i = 0; i < nr_tables; i++) { - struct fixed_file_table *table = &file_data->table[i]; - unsigned this_files; - - this_files = min(nr_files, IORING_MAX_FILES_TABLE); - table->files = kcalloc(this_files, sizeof(struct file *), - GFP_KERNEL_ACCOUNT); - if (!table->files) - break; - nr_files -= this_files; - } - - if (i == nr_tables) - return 0; - - for (i = 0; i < nr_tables; i++) { - struct fixed_file_table *table = &file_data->table[i]; - kfree(table->files); - } - return 1; -} - -static void io_ring_file_put(struct io_ring_ctx *ctx, struct file *file) +static void io_rsrc_file_put(struct io_ring_ctx *ctx, struct io_rsrc_put *prsrc) { + struct file *file = prsrc->file; #if defined(CONFIG_UNIX) struct sock *sock = ctx->ring_sock->sk; struct sk_buff_head list, *head = &sock->sk_receive_queue; @@ -7463,117 +8110,61 @@ static void io_ring_file_put(struct io_ring_ctx *ctx, struct file *file) #endif } -struct io_file_put { - struct list_head list; - struct file *file; -}; - -static void __io_file_put_work(struct fixed_file_ref_node *ref_node) +static void __io_rsrc_put_work(struct io_rsrc_node *ref_node) { - struct fixed_file_data *file_data = ref_node->file_data; - struct io_ring_ctx *ctx = file_data->ctx; - struct io_file_put *pfile, *tmp; + struct io_rsrc_data *rsrc_data = ref_node->rsrc_data; + struct io_ring_ctx *ctx = rsrc_data->ctx; + struct io_rsrc_put *prsrc, *tmp; + + list_for_each_entry_safe(prsrc, tmp, &ref_node->rsrc_list, list) { + list_del(&prsrc->list); + + if (prsrc->tag) { + bool lock_ring = ctx->flags & IORING_SETUP_IOPOLL; + + io_ring_submit_lock(ctx, lock_ring); + spin_lock(&ctx->completion_lock); + io_fill_cqe_aux(ctx, prsrc->tag, 0, 0); + io_commit_cqring(ctx); + spin_unlock(&ctx->completion_lock); + io_cqring_ev_posted(ctx); + io_ring_submit_unlock(ctx, lock_ring); + } - list_for_each_entry_safe(pfile, tmp, &ref_node->file_list, list) { - list_del(&pfile->list); - io_ring_file_put(ctx, pfile->file); - kfree(pfile); + rsrc_data->do_put(ctx, prsrc); + kfree(prsrc); } - percpu_ref_exit(&ref_node->refs); - kfree(ref_node); - percpu_ref_put(&file_data->refs); + io_rsrc_node_destroy(ref_node); + if (atomic_dec_and_test(&rsrc_data->refs)) + complete(&rsrc_data->done); } -static void io_file_put_work(struct work_struct *work) +static void io_rsrc_put_work(struct work_struct *work) { struct io_ring_ctx *ctx; struct llist_node *node; - ctx = container_of(work, struct io_ring_ctx, file_put_work.work); - node = llist_del_all(&ctx->file_put_llist); + ctx = container_of(work, struct io_ring_ctx, rsrc_put_work.work); + node = llist_del_all(&ctx->rsrc_put_llist); while (node) { - struct fixed_file_ref_node *ref_node; + struct io_rsrc_node *ref_node; struct llist_node *next = node->next; - ref_node = llist_entry(node, struct fixed_file_ref_node, llist); - __io_file_put_work(ref_node); + ref_node = llist_entry(node, struct io_rsrc_node, llist); + __io_rsrc_put_work(ref_node); node = next; } } -static void io_file_data_ref_zero(struct percpu_ref *ref) -{ - struct fixed_file_ref_node *ref_node; - struct fixed_file_data *data; - struct io_ring_ctx *ctx; - bool first_add = false; - int delay = HZ; - - ref_node = container_of(ref, struct fixed_file_ref_node, refs); - data = ref_node->file_data; - ctx = data->ctx; - - spin_lock_bh(&data->lock); - ref_node->done = true; - - while (!list_empty(&data->ref_list)) { - ref_node = list_first_entry(&data->ref_list, - struct fixed_file_ref_node, node); - /* recycle ref nodes in order */ - if (!ref_node->done) - break; - list_del(&ref_node->node); - first_add |= llist_add(&ref_node->llist, &ctx->file_put_llist); - } - spin_unlock_bh(&data->lock); - - if (percpu_ref_is_dying(&data->refs)) - delay = 0; - - if (!delay) - mod_delayed_work(system_wq, &ctx->file_put_work, 0); - else if (first_add) - queue_delayed_work(system_wq, &ctx->file_put_work, delay); -} - -static struct fixed_file_ref_node *alloc_fixed_file_ref_node( - struct io_ring_ctx *ctx) -{ - struct fixed_file_ref_node *ref_node; - - ref_node = kzalloc(sizeof(*ref_node), GFP_KERNEL); - if (!ref_node) - return NULL; - - if (percpu_ref_init(&ref_node->refs, io_file_data_ref_zero, - 0, GFP_KERNEL)) { - kfree(ref_node); - return NULL; - } - INIT_LIST_HEAD(&ref_node->node); - INIT_LIST_HEAD(&ref_node->file_list); - ref_node->file_data = ctx->file_data; - ref_node->done = false; - return ref_node; -} - -static void destroy_fixed_file_ref_node(struct fixed_file_ref_node *ref_node) -{ - percpu_ref_exit(&ref_node->refs); - kfree(ref_node); -} - static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, - unsigned nr_args) + unsigned nr_args, u64 __user *tags) { __s32 __user *fds = (__s32 __user *) arg; - unsigned nr_tables, i; struct file *file; - int fd, ret = -ENOMEM; - struct fixed_file_ref_node *ref_node; - struct fixed_file_data *file_data; + int fd, ret; + unsigned i; if (ctx->file_data) return -EBUSY; @@ -7583,44 +8174,34 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, return -EMFILE; if (nr_args > rlimit(RLIMIT_NOFILE)) return -EMFILE; + ret = io_rsrc_node_switch_start(ctx); + if (ret) + return ret; + ret = io_rsrc_data_alloc(ctx, io_rsrc_file_put, tags, nr_args, + &ctx->file_data); + if (ret) + return ret; - file_data = kzalloc(sizeof(*ctx->file_data), GFP_KERNEL_ACCOUNT); - if (!file_data) - return -ENOMEM; - file_data->ctx = ctx; - init_completion(&file_data->done); - INIT_LIST_HEAD(&file_data->ref_list); - spin_lock_init(&file_data->lock); - - nr_tables = DIV_ROUND_UP(nr_args, IORING_MAX_FILES_TABLE); - file_data->table = kcalloc(nr_tables, sizeof(*file_data->table), - GFP_KERNEL_ACCOUNT); - if (!file_data->table) - goto out_free; - - if (percpu_ref_init(&file_data->refs, io_file_ref_kill, - PERCPU_REF_ALLOW_REINIT, GFP_KERNEL)) + ret = -ENOMEM; + if (!io_alloc_file_tables(&ctx->file_table, nr_args)) goto out_free; - if (io_sqe_alloc_file_tables(file_data, nr_tables, nr_args)) - goto out_ref; - ctx->file_data = file_data; - for (i = 0; i < nr_args; i++, ctx->nr_user_files++) { - struct fixed_file_table *table; - unsigned index; - if (copy_from_user(&fd, &fds[i], sizeof(fd))) { ret = -EFAULT; goto out_fput; } /* allow sparse sets */ - if (fd == -1) + if (fd == -1) { + ret = -EINVAL; + if (unlikely(*io_get_tag_slot(ctx->file_data, i))) + goto out_fput; continue; + } file = fget(fd); ret = -EBADF; - if (!file) + if (unlikely(!file)) goto out_fput; /* @@ -7634,24 +8215,16 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, fput(file); goto out_fput; } - table = &file_data->table[i >> IORING_FILE_TABLE_SHIFT]; - index = i & IORING_FILE_TABLE_MASK; - table->files[index] = file; + io_fixed_file_set(io_fixed_file_slot(&ctx->file_table, i), file); } ret = io_sqe_files_scm(ctx); if (ret) { - io_sqe_files_unregister(ctx); + __io_sqe_files_unregister(ctx); return ret; } - ref_node = alloc_fixed_file_ref_node(ctx); - if (!ref_node) { - io_sqe_files_unregister(ctx); - return -ENOMEM; - } - - io_sqe_files_set_node(file_data, ref_node); + io_rsrc_node_switch(ctx, NULL); return ret; out_fput: for (i = 0; i < ctx->nr_user_files; i++) { @@ -7659,14 +8232,10 @@ out_fput: if (file) fput(file); } - for (i = 0; i < nr_tables; i++) - kfree(file_data->table[i].files); + io_free_file_tables(&ctx->file_table); ctx->nr_user_files = 0; -out_ref: - percpu_ref_exit(&file_data->refs); out_free: - kfree(file_data->table); - kfree(file_data); + io_rsrc_data_free(ctx->file_data); ctx->file_data = NULL; return ret; } @@ -7714,63 +8283,159 @@ static int io_sqe_file_register(struct io_ring_ctx *ctx, struct file *file, #endif } -static int io_queue_file_removal(struct fixed_file_data *data, - struct file *file) +static int io_queue_rsrc_removal(struct io_rsrc_data *data, unsigned idx, + struct io_rsrc_node *node, void *rsrc) +{ + u64 *tag_slot = io_get_tag_slot(data, idx); + struct io_rsrc_put *prsrc; + + prsrc = kzalloc(sizeof(*prsrc), GFP_KERNEL); + if (!prsrc) + return -ENOMEM; + + prsrc->tag = *tag_slot; + *tag_slot = 0; + prsrc->rsrc = rsrc; + list_add(&prsrc->list, &node->rsrc_list); + return 0; +} + +static int io_install_fixed_file(struct io_kiocb *req, struct file *file, + unsigned int issue_flags, u32 slot_index) +{ + struct io_ring_ctx *ctx = req->ctx; + bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; + bool needs_switch = false; + struct io_fixed_file *file_slot; + int ret = -EBADF; + + io_ring_submit_lock(ctx, !force_nonblock); + if (file->f_op == &io_uring_fops) + goto err; + ret = -ENXIO; + if (!ctx->file_data) + goto err; + ret = -EINVAL; + if (slot_index >= ctx->nr_user_files) + goto err; + + slot_index = array_index_nospec(slot_index, ctx->nr_user_files); + file_slot = io_fixed_file_slot(&ctx->file_table, slot_index); + + if (file_slot->file_ptr) { + struct file *old_file; + + ret = io_rsrc_node_switch_start(ctx); + if (ret) + goto err; + + old_file = (struct file *)(file_slot->file_ptr & FFS_MASK); + ret = io_queue_rsrc_removal(ctx->file_data, slot_index, + ctx->rsrc_node, old_file); + if (ret) + goto err; + file_slot->file_ptr = 0; + needs_switch = true; + } + + *io_get_tag_slot(ctx->file_data, slot_index) = 0; + io_fixed_file_set(file_slot, file); + ret = io_sqe_file_register(ctx, file, slot_index); + if (ret) { + file_slot->file_ptr = 0; + goto err; + } + + ret = 0; +err: + if (needs_switch) + io_rsrc_node_switch(ctx, ctx->file_data); + io_ring_submit_unlock(ctx, !force_nonblock); + if (ret) + fput(file); + return ret; +} + +static int io_close_fixed(struct io_kiocb *req, unsigned int issue_flags) { - struct io_file_put *pfile; - struct fixed_file_ref_node *ref_node = data->node; + unsigned int offset = req->close.file_slot - 1; + struct io_ring_ctx *ctx = req->ctx; + struct io_fixed_file *file_slot; + struct file *file; + int ret; - pfile = kzalloc(sizeof(*pfile), GFP_KERNEL); - if (!pfile) - return -ENOMEM; + io_ring_submit_lock(ctx, !(issue_flags & IO_URING_F_NONBLOCK)); + ret = -ENXIO; + if (unlikely(!ctx->file_data)) + goto out; + ret = -EINVAL; + if (offset >= ctx->nr_user_files) + goto out; + ret = io_rsrc_node_switch_start(ctx); + if (ret) + goto out; - pfile->file = file; - list_add(&pfile->list, &ref_node->file_list); + offset = array_index_nospec(offset, ctx->nr_user_files); + file_slot = io_fixed_file_slot(&ctx->file_table, offset); + ret = -EBADF; + if (!file_slot->file_ptr) + goto out; - return 0; + file = (struct file *)(file_slot->file_ptr & FFS_MASK); + ret = io_queue_rsrc_removal(ctx->file_data, offset, ctx->rsrc_node, file); + if (ret) + goto out; + + file_slot->file_ptr = 0; + io_rsrc_node_switch(ctx, ctx->file_data); + ret = 0; +out: + io_ring_submit_unlock(ctx, !(issue_flags & IO_URING_F_NONBLOCK)); + return ret; } static int __io_sqe_files_update(struct io_ring_ctx *ctx, - struct io_uring_files_update *up, + struct io_uring_rsrc_update2 *up, unsigned nr_args) { - struct fixed_file_data *data = ctx->file_data; - struct fixed_file_ref_node *ref_node; + u64 __user *tags = u64_to_user_ptr(up->tags); + __s32 __user *fds = u64_to_user_ptr(up->data); + struct io_rsrc_data *data = ctx->file_data; + struct io_fixed_file *file_slot; struct file *file; - __s32 __user *fds; - int fd, i, err; - __u32 done; + int fd, i, err = 0; + unsigned int done; bool needs_switch = false; - if (check_add_overflow(up->offset, nr_args, &done)) - return -EOVERFLOW; - if (done > ctx->nr_user_files) + if (!ctx->file_data) + return -ENXIO; + if (up->offset + nr_args > ctx->nr_user_files) return -EINVAL; - ref_node = alloc_fixed_file_ref_node(ctx); - if (!ref_node) - return -ENOMEM; + for (done = 0; done < nr_args; done++) { + u64 tag = 0; - done = 0; - fds = u64_to_user_ptr(up->fds); - while (nr_args) { - struct fixed_file_table *table; - unsigned index; - - err = 0; - if (copy_from_user(&fd, &fds[done], sizeof(fd))) { + if ((tags && copy_from_user(&tag, &tags[done], sizeof(tag))) || + copy_from_user(&fd, &fds[done], sizeof(fd))) { err = -EFAULT; break; } - i = array_index_nospec(up->offset, ctx->nr_user_files); - table = &ctx->file_data->table[i >> IORING_FILE_TABLE_SHIFT]; - index = i & IORING_FILE_TABLE_MASK; - if (table->files[index]) { - file = table->files[index]; - err = io_queue_file_removal(data, file); + if ((fd == IORING_REGISTER_FILES_SKIP || fd == -1) && tag) { + err = -EINVAL; + break; + } + if (fd == IORING_REGISTER_FILES_SKIP) + continue; + + i = array_index_nospec(up->offset + done, ctx->nr_user_files); + file_slot = io_fixed_file_slot(&ctx->file_table, i); + + if (file_slot->file_ptr) { + file = (struct file *)(file_slot->file_ptr & FFS_MASK); + err = io_queue_rsrc_removal(data, i, ctx->rsrc_node, file); if (err) break; - table->files[index] = NULL; + file_slot->file_ptr = 0; needs_switch = true; } if (fd != -1) { @@ -7792,106 +8457,61 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx, err = -EBADF; break; } - table->files[index] = file; + *io_get_tag_slot(data, i) = tag; + io_fixed_file_set(file_slot, file); err = io_sqe_file_register(ctx, file, i); if (err) { - table->files[index] = NULL; + file_slot->file_ptr = 0; fput(file); break; } } - nr_args--; - done++; - up->offset++; } - if (needs_switch) { - percpu_ref_kill(&data->node->refs); - io_sqe_files_set_node(data, ref_node); - } else - destroy_fixed_file_ref_node(ref_node); - + if (needs_switch) + io_rsrc_node_switch(ctx, data); return done ? done : err; } -static int io_sqe_files_update(struct io_ring_ctx *ctx, void __user *arg, - unsigned nr_args) -{ - struct io_uring_files_update up; - - if (!ctx->file_data) - return -ENXIO; - if (!nr_args) - return -EINVAL; - if (copy_from_user(&up, arg, sizeof(up))) - return -EFAULT; - if (up.resv) - return -EINVAL; - - return __io_sqe_files_update(ctx, &up, nr_args); -} - -static void io_free_work(struct io_wq_work *work) -{ - struct io_kiocb *req = container_of(work, struct io_kiocb, work); - - /* Consider that io_steal_work() relies on this ref */ - io_put_req(req); -} - -static int io_init_wq_offload(struct io_ring_ctx *ctx, - struct io_uring_params *p) +static struct io_wq *io_init_wq_offload(struct io_ring_ctx *ctx, + struct task_struct *task) { + struct io_wq_hash *hash; struct io_wq_data data; - struct fd f; - struct io_ring_ctx *ctx_attach; unsigned int concurrency; - int ret = 0; - - data.user = ctx->user; - data.free_work = io_free_work; - data.do_work = io_wq_submit_work; - - if (!(p->flags & IORING_SETUP_ATTACH_WQ)) { - /* Do QD, or 4 * CPUS, whatever is smallest */ - concurrency = min(ctx->sq_entries, 4 * num_online_cpus()); - ctx->io_wq = io_wq_create(concurrency, &data); - if (IS_ERR(ctx->io_wq)) { - ret = PTR_ERR(ctx->io_wq); - ctx->io_wq = NULL; + mutex_lock(&ctx->uring_lock); + hash = ctx->hash_map; + if (!hash) { + hash = kzalloc(sizeof(*hash), GFP_KERNEL); + if (!hash) { + mutex_unlock(&ctx->uring_lock); + return ERR_PTR(-ENOMEM); } - return ret; + refcount_set(&hash->refs, 1); + init_waitqueue_head(&hash->wait); + ctx->hash_map = hash; } + mutex_unlock(&ctx->uring_lock); - f = fdget(p->wq_fd); - if (!f.file) - return -EBADF; - - if (f.file->f_op != &io_uring_fops) { - ret = -EINVAL; - goto out_fput; - } + data.hash = hash; + data.task = task; + data.free_work = io_wq_free_work; + data.do_work = io_wq_submit_work; - ctx_attach = f.file->private_data; - /* @io_wq is protected by holding the fd */ - if (!io_wq_get(ctx_attach->io_wq, &data)) { - ret = -EINVAL; - goto out_fput; - } + /* Do QD, or 4 * CPUS, whatever is smallest */ + concurrency = min(ctx->sq_entries, 4 * num_online_cpus()); - ctx->io_wq = ctx_attach->io_wq; -out_fput: - fdput(f); - return ret; + return io_wq_create(concurrency, &data); } -static int io_uring_alloc_task_context(struct task_struct *task) +static int io_uring_alloc_task_context(struct task_struct *task, + struct io_ring_ctx *ctx) { struct io_uring_task *tctx; int ret; - tctx = kmalloc(sizeof(*tctx), GFP_KERNEL); + tctx = kzalloc(sizeof(*tctx), GFP_KERNEL); if (unlikely(!tctx)) return -ENOMEM; @@ -7901,14 +8521,22 @@ static int io_uring_alloc_task_context(struct task_struct *task) return ret; } + tctx->io_wq = io_init_wq_offload(ctx, task); + if (IS_ERR(tctx->io_wq)) { + ret = PTR_ERR(tctx->io_wq); + percpu_counter_destroy(&tctx->inflight); + kfree(tctx); + return ret; + } + xa_init(&tctx->xa); init_waitqueue_head(&tctx->wait); - tctx->last = NULL; atomic_set(&tctx->in_idle, 0); - tctx->sqpoll = false; - io_init_identity(&tctx->__identity); - tctx->identity = &tctx->__identity; + atomic_set(&tctx->inflight_tracked, 0); task->io_uring = tctx; + spin_lock_init(&tctx->task_lock); + INIT_WQ_LIST(&tctx->task_list); + init_task_work(&tctx->task_work, tctx_task_work); return 0; } @@ -7917,9 +8545,9 @@ void __io_uring_free(struct task_struct *tsk) struct io_uring_task *tctx = tsk->io_uring; WARN_ON_ONCE(!xa_empty(&tctx->xa)); - WARN_ON_ONCE(refcount_read(&tctx->identity->count) != 1); - if (tctx->identity != &tctx->__identity) - kfree(tctx->identity); + WARN_ON_ONCE(tctx->io_wq); + WARN_ON_ONCE(tctx->cached_refs); + percpu_counter_destroy(&tctx->inflight); kfree(tctx); tsk->io_uring = NULL; @@ -7930,54 +8558,71 @@ static int io_sq_offload_create(struct io_ring_ctx *ctx, { int ret; + /* Retain compatibility with failing for an invalid attach attempt */ + if ((ctx->flags & (IORING_SETUP_ATTACH_WQ | IORING_SETUP_SQPOLL)) == + IORING_SETUP_ATTACH_WQ) { + struct fd f; + + f = fdget(p->wq_fd); + if (!f.file) + return -ENXIO; + if (f.file->f_op != &io_uring_fops) { + fdput(f); + return -EINVAL; + } + fdput(f); + } if (ctx->flags & IORING_SETUP_SQPOLL) { + struct task_struct *tsk; struct io_sq_data *sqd; + bool attached; - ret = -EPERM; - if (!capable(CAP_SYS_ADMIN)) - goto err; - - sqd = io_get_sq_data(p); + sqd = io_get_sq_data(p, &attached); if (IS_ERR(sqd)) { ret = PTR_ERR(sqd); goto err; } + ctx->sq_creds = get_current_cred(); ctx->sq_data = sqd; - io_sq_thread_park(sqd); - mutex_lock(&sqd->ctx_lock); - list_add(&ctx->sqd_list, &sqd->ctx_new_list); - mutex_unlock(&sqd->ctx_lock); - io_sq_thread_unpark(sqd); - ctx->sq_thread_idle = msecs_to_jiffies(p->sq_thread_idle); if (!ctx->sq_thread_idle) ctx->sq_thread_idle = HZ; - if (sqd->thread) - goto done; + io_sq_thread_park(sqd); + list_add(&ctx->sqd_list, &sqd->ctx_list); + io_sqd_update_thread_idle(sqd); + /* don't attach to a dying SQPOLL thread, would be racy */ + ret = (attached && !sqd->thread) ? -ENXIO : 0; + io_sq_thread_unpark(sqd); + + if (ret < 0) + goto err; + if (attached) + return 0; if (p->flags & IORING_SETUP_SQ_AFF) { int cpu = p->sq_thread_cpu; ret = -EINVAL; - if (cpu >= nr_cpu_ids) - goto err; - if (!cpu_online(cpu)) - goto err; - - sqd->thread = kthread_create_on_cpu(io_sq_thread, sqd, - cpu, "io_uring-sq"); + if (cpu >= nr_cpu_ids || !cpu_online(cpu)) + goto err_sqpoll; + sqd->sq_cpu = cpu; } else { - sqd->thread = kthread_create(io_sq_thread, sqd, - "io_uring-sq"); + sqd->sq_cpu = -1; } - if (IS_ERR(sqd->thread)) { - ret = PTR_ERR(sqd->thread); - sqd->thread = NULL; - goto err; + + sqd->task_pid = current->pid; + sqd->task_tgid = current->tgid; + tsk = create_io_thread(io_sq_thread, sqd, NUMA_NO_NODE); + if (IS_ERR(tsk)) { + ret = PTR_ERR(tsk); + goto err_sqpoll; } - ret = io_uring_alloc_task_context(sqd->thread); + + sqd->thread = tsk; + ret = io_uring_alloc_task_context(tsk, ctx); + wake_up_new_task(tsk); if (ret) goto err; } else if (p->flags & IORING_SETUP_SQ_AFF) { @@ -7986,26 +8631,14 @@ static int io_sq_offload_create(struct io_ring_ctx *ctx, goto err; } -done: - ret = io_init_wq_offload(ctx, p); - if (ret) - goto err; - return 0; +err_sqpoll: + complete(&ctx->sq_data->exited); err: - io_finish_async(ctx); + io_sq_thread_finish(ctx); return ret; } -static void io_sq_offload_start(struct io_ring_ctx *ctx) -{ - struct io_sq_data *sqd = ctx->sq_data; - - ctx->flags &= ~IORING_SETUP_R_DISABLED; - if ((ctx->flags & IORING_SETUP_SQPOLL) && sqd && sqd->thread) - wake_up_process(sqd->thread); -} - static inline void __io_unaccount_mem(struct user_struct *user, unsigned long nr_pages) { @@ -8031,37 +8664,27 @@ static inline int __io_account_mem(struct user_struct *user, return 0; } -static void io_unaccount_mem(struct io_ring_ctx *ctx, unsigned long nr_pages, - enum io_mem_account acct) +static void io_unaccount_mem(struct io_ring_ctx *ctx, unsigned long nr_pages) { - if (ctx->limit_mem) + if (ctx->user) __io_unaccount_mem(ctx->user, nr_pages); - if (ctx->mm_account) { - if (acct == ACCT_LOCKED) - ctx->mm_account->locked_vm -= nr_pages; - else if (acct == ACCT_PINNED) - atomic64_sub(nr_pages, &ctx->mm_account->pinned_vm); - } + if (ctx->mm_account) + atomic64_sub(nr_pages, &ctx->mm_account->pinned_vm); } -static int io_account_mem(struct io_ring_ctx *ctx, unsigned long nr_pages, - enum io_mem_account acct) +static int io_account_mem(struct io_ring_ctx *ctx, unsigned long nr_pages) { int ret; - if (ctx->limit_mem) { + if (ctx->user) { ret = __io_account_mem(ctx->user, nr_pages); if (ret) return ret; } - if (ctx->mm_account) { - if (acct == ACCT_LOCKED) - ctx->mm_account->locked_vm += nr_pages; - else if (acct == ACCT_PINNED) - atomic64_add(nr_pages, &ctx->mm_account->pinned_vm); - } + if (ctx->mm_account) + atomic64_add(nr_pages, &ctx->mm_account->pinned_vm); return 0; } @@ -8080,10 +8703,9 @@ static void io_mem_free(void *ptr) static void *io_mem_alloc(size_t size) { - gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO | __GFP_NOWARN | __GFP_COMP | - __GFP_NORETRY; + gfp_t gfp = GFP_KERNEL_ACCOUNT | __GFP_ZERO | __GFP_NOWARN | __GFP_COMP; - return (void *) __get_free_pages(gfp_flags, get_order(size)); + return (void *) __get_free_pages(gfp, get_order(size)); } static unsigned long rings_size(unsigned sq_entries, unsigned cq_entries, @@ -8115,41 +8737,58 @@ static unsigned long rings_size(unsigned sq_entries, unsigned cq_entries, return off; } -static unsigned long ring_pages(unsigned sq_entries, unsigned cq_entries) +static void io_buffer_unmap(struct io_ring_ctx *ctx, struct io_mapped_ubuf **slot) { - size_t pages; + struct io_mapped_ubuf *imu = *slot; + unsigned int i; - pages = (size_t)1 << get_order( - rings_size(sq_entries, cq_entries, NULL)); - pages += (size_t)1 << get_order( - array_size(sizeof(struct io_uring_sqe), sq_entries)); - - return pages; + if (imu != ctx->dummy_ubuf) { + for (i = 0; i < imu->nr_bvecs; i++) + unpin_user_page(imu->bvec[i].bv_page); + if (imu->acct_pages) + io_unaccount_mem(ctx, imu->acct_pages); + kvfree(imu); + } + *slot = NULL; } -static int io_sqe_buffer_unregister(struct io_ring_ctx *ctx) +static void io_rsrc_buf_put(struct io_ring_ctx *ctx, struct io_rsrc_put *prsrc) { - int i, j; + io_buffer_unmap(ctx, &prsrc->buf); + prsrc->buf = NULL; +} - if (!ctx->user_bufs) - return -ENXIO; +static void __io_sqe_buffers_unregister(struct io_ring_ctx *ctx) +{ + unsigned int i; - for (i = 0; i < ctx->nr_user_bufs; i++) { - struct io_mapped_ubuf *imu = &ctx->user_bufs[i]; + for (i = 0; i < ctx->nr_user_bufs; i++) + io_buffer_unmap(ctx, &ctx->user_bufs[i]); + kfree(ctx->user_bufs); + io_rsrc_data_free(ctx->buf_data); + ctx->user_bufs = NULL; + ctx->buf_data = NULL; + ctx->nr_user_bufs = 0; +} - for (j = 0; j < imu->nr_bvecs; j++) - unpin_user_page(imu->bvec[j].bv_page); +static int io_sqe_buffers_unregister(struct io_ring_ctx *ctx) +{ + unsigned nr = ctx->nr_user_bufs; + int ret; - if (imu->acct_pages) - io_unaccount_mem(ctx, imu->acct_pages, ACCT_PINNED); - kvfree(imu->bvec); - imu->nr_bvecs = 0; - } + if (!ctx->buf_data) + return -ENXIO; - kfree(ctx->user_bufs); - ctx->user_bufs = NULL; + /* + * Quiesce may unlock ->uring_lock, and while it's not held + * prevent new requests using the table. + */ ctx->nr_user_bufs = 0; - return 0; + ret = io_rsrc_ref_quiesce(ctx->buf_data, ctx); + ctx->nr_user_bufs = nr; + if (!ret) + __io_sqe_buffers_unregister(ctx); + return ret; } static int io_copy_iov(struct io_ring_ctx *ctx, struct iovec *dst, @@ -8201,7 +8840,7 @@ static bool headpage_already_acct(struct io_ring_ctx *ctx, struct page **pages, /* check previously registered pages */ for (i = 0; i < ctx->nr_user_bufs; i++) { - struct io_mapped_ubuf *imu = &ctx->user_bufs[i]; + struct io_mapped_ubuf *imu = ctx->user_bufs[i]; for (j = 0; j < imu->nr_bvecs; j++) { if (!PageCompound(imu->bvec[j].bv_page)) @@ -8220,6 +8859,7 @@ static int io_buffer_account_pin(struct io_ring_ctx *ctx, struct page **pages, { int i, ret; + imu->acct_pages = 0; for (i = 0; i < nr_pages; i++) { if (!PageCompound(pages[i])) { imu->acct_pages++; @@ -8239,147 +8879,252 @@ static int io_buffer_account_pin(struct io_ring_ctx *ctx, struct page **pages, if (!imu->acct_pages) return 0; - ret = io_account_mem(ctx, imu->acct_pages, ACCT_PINNED); + ret = io_account_mem(ctx, imu->acct_pages); if (ret) imu->acct_pages = 0; return ret; } -static int io_sqe_buffer_register(struct io_ring_ctx *ctx, void __user *arg, - unsigned nr_args) +static int io_sqe_buffer_register(struct io_ring_ctx *ctx, struct iovec *iov, + struct io_mapped_ubuf **pimu, + struct page **last_hpage) { + struct io_mapped_ubuf *imu = NULL; struct vm_area_struct **vmas = NULL; struct page **pages = NULL; - struct page *last_hpage = NULL; - int i, j, got_pages = 0; - int ret = -EINVAL; + unsigned long off, start, end, ubuf; + size_t size; + int ret, pret, nr_pages, i; - if (ctx->user_bufs) - return -EBUSY; - if (!nr_args || nr_args > UIO_MAXIOV) - return -EINVAL; + if (!iov->iov_base) { + *pimu = ctx->dummy_ubuf; + return 0; + } - ctx->user_bufs = kcalloc(nr_args, sizeof(struct io_mapped_ubuf), - GFP_KERNEL); - if (!ctx->user_bufs) - return -ENOMEM; + ubuf = (unsigned long) iov->iov_base; + end = (ubuf + iov->iov_len + PAGE_SIZE - 1) >> PAGE_SHIFT; + start = ubuf >> PAGE_SHIFT; + nr_pages = end - start; - for (i = 0; i < nr_args; i++) { - struct io_mapped_ubuf *imu = &ctx->user_bufs[i]; - unsigned long off, start, end, ubuf; - int pret, nr_pages; - struct iovec iov; - size_t size; + *pimu = NULL; + ret = -ENOMEM; - ret = io_copy_iov(ctx, &iov, arg, i); - if (ret) - goto err; + pages = kvmalloc_array(nr_pages, sizeof(struct page *), GFP_KERNEL); + if (!pages) + goto done; + + vmas = kvmalloc_array(nr_pages, sizeof(struct vm_area_struct *), + GFP_KERNEL); + if (!vmas) + goto done; + imu = kvmalloc(struct_size(imu, bvec, nr_pages), GFP_KERNEL); + if (!imu) + goto done; + + ret = 0; + mmap_read_lock(current->mm); + pret = pin_user_pages(ubuf, nr_pages, FOLL_WRITE | FOLL_LONGTERM, + pages, vmas); + if (pret == nr_pages) { + /* don't support file backed memory */ + for (i = 0; i < nr_pages; i++) { + struct vm_area_struct *vma = vmas[i]; + + if (vma_is_shmem(vma)) + continue; + if (vma->vm_file && + !is_file_hugepages(vma->vm_file)) { + ret = -EOPNOTSUPP; + break; + } + } + } else { + ret = pret < 0 ? pret : -EFAULT; + } + mmap_read_unlock(current->mm); + if (ret) { /* - * Don't impose further limits on the size and buffer - * constraints here, we'll -EINVAL later when IO is - * submitted if they are wrong. + * if we did partial map, or found file backed vmas, + * release any pages we did get */ - ret = -EFAULT; - if (!iov.iov_base || !iov.iov_len) - goto err; + if (pret > 0) + unpin_user_pages(pages, pret); + goto done; + } - /* arbitrary limit, but we need something */ - if (iov.iov_len > SZ_1G) - goto err; + ret = io_buffer_account_pin(ctx, pages, pret, imu, last_hpage); + if (ret) { + unpin_user_pages(pages, pret); + goto done; + } - ubuf = (unsigned long) iov.iov_base; - end = (ubuf + iov.iov_len + PAGE_SIZE - 1) >> PAGE_SHIFT; - start = ubuf >> PAGE_SHIFT; - nr_pages = end - start; + off = ubuf & ~PAGE_MASK; + size = iov->iov_len; + for (i = 0; i < nr_pages; i++) { + size_t vec_len; + + vec_len = min_t(size_t, size, PAGE_SIZE - off); + imu->bvec[i].bv_page = pages[i]; + imu->bvec[i].bv_len = vec_len; + imu->bvec[i].bv_offset = off; + off = 0; + size -= vec_len; + } + /* store original address for later verification */ + imu->ubuf = ubuf; + imu->ubuf_end = ubuf + iov->iov_len; + imu->nr_bvecs = nr_pages; + *pimu = imu; + ret = 0; +done: + if (ret) + kvfree(imu); + kvfree(pages); + kvfree(vmas); + return ret; +} - ret = 0; - if (!pages || nr_pages > got_pages) { - kvfree(vmas); - kvfree(pages); - pages = kvmalloc_array(nr_pages, sizeof(struct page *), - GFP_KERNEL); - vmas = kvmalloc_array(nr_pages, - sizeof(struct vm_area_struct *), - GFP_KERNEL); - if (!pages || !vmas) { - ret = -ENOMEM; - goto err; - } - got_pages = nr_pages; - } +static int io_buffers_map_alloc(struct io_ring_ctx *ctx, unsigned int nr_args) +{ + ctx->user_bufs = kcalloc(nr_args, sizeof(*ctx->user_bufs), GFP_KERNEL); + return ctx->user_bufs ? 0 : -ENOMEM; +} - imu->bvec = kvmalloc_array(nr_pages, sizeof(struct bio_vec), - GFP_KERNEL); - ret = -ENOMEM; - if (!imu->bvec) - goto err; +static int io_buffer_validate(struct iovec *iov) +{ + unsigned long tmp, acct_len = iov->iov_len + (PAGE_SIZE - 1); - ret = 0; - mmap_read_lock(current->mm); - pret = pin_user_pages(ubuf, nr_pages, - FOLL_WRITE | FOLL_LONGTERM, - pages, vmas); - if (pret == nr_pages) { - /* don't support file backed memory */ - for (j = 0; j < nr_pages; j++) { - struct vm_area_struct *vma = vmas[j]; - - if (vma->vm_file && - !is_file_hugepages(vma->vm_file)) { - ret = -EOPNOTSUPP; - break; - } - } - } else { - ret = pret < 0 ? pret : -EFAULT; - } - mmap_read_unlock(current->mm); - if (ret) { - /* - * if we did partial map, or found file backed vmas, - * release any pages we did get - */ - if (pret > 0) - unpin_user_pages(pages, pret); - kvfree(imu->bvec); - goto err; + /* + * Don't impose further limits on the size and buffer + * constraints here, we'll -EINVAL later when IO is + * submitted if they are wrong. + */ + if (!iov->iov_base) + return iov->iov_len ? -EFAULT : 0; + if (!iov->iov_len) + return -EFAULT; + + /* arbitrary limit, but we need something */ + if (iov->iov_len > SZ_1G) + return -EFAULT; + + if (check_add_overflow((unsigned long)iov->iov_base, acct_len, &tmp)) + return -EOVERFLOW; + + return 0; +} + +static int io_sqe_buffers_register(struct io_ring_ctx *ctx, void __user *arg, + unsigned int nr_args, u64 __user *tags) +{ + struct page *last_hpage = NULL; + struct io_rsrc_data *data; + int i, ret; + struct iovec iov; + + if (ctx->user_bufs) + return -EBUSY; + if (!nr_args || nr_args > IORING_MAX_REG_BUFFERS) + return -EINVAL; + ret = io_rsrc_node_switch_start(ctx); + if (ret) + return ret; + ret = io_rsrc_data_alloc(ctx, io_rsrc_buf_put, tags, nr_args, &data); + if (ret) + return ret; + ret = io_buffers_map_alloc(ctx, nr_args); + if (ret) { + io_rsrc_data_free(data); + return ret; + } + + for (i = 0; i < nr_args; i++, ctx->nr_user_bufs++) { + ret = io_copy_iov(ctx, &iov, arg, i); + if (ret) + break; + ret = io_buffer_validate(&iov); + if (ret) + break; + if (!iov.iov_base && *io_get_tag_slot(data, i)) { + ret = -EINVAL; + break; } - ret = io_buffer_account_pin(ctx, pages, pret, imu, &last_hpage); - if (ret) { - unpin_user_pages(pages, pret); - kvfree(imu->bvec); - goto err; + ret = io_sqe_buffer_register(ctx, &iov, &ctx->user_bufs[i], + &last_hpage); + if (ret) + break; + } + + WARN_ON_ONCE(ctx->buf_data); + + ctx->buf_data = data; + if (ret) + __io_sqe_buffers_unregister(ctx); + else + io_rsrc_node_switch(ctx, NULL); + return ret; +} + +static int __io_sqe_buffers_update(struct io_ring_ctx *ctx, + struct io_uring_rsrc_update2 *up, + unsigned int nr_args) +{ + u64 __user *tags = u64_to_user_ptr(up->tags); + struct iovec iov, __user *iovs = u64_to_user_ptr(up->data); + struct page *last_hpage = NULL; + bool needs_switch = false; + __u32 done; + int i, err; + + if (!ctx->buf_data) + return -ENXIO; + if (up->offset + nr_args > ctx->nr_user_bufs) + return -EINVAL; + + for (done = 0; done < nr_args; done++) { + struct io_mapped_ubuf *imu; + int offset = up->offset + done; + u64 tag = 0; + + err = io_copy_iov(ctx, &iov, iovs, done); + if (err) + break; + if (tags && copy_from_user(&tag, &tags[done], sizeof(tag))) { + err = -EFAULT; + break; + } + err = io_buffer_validate(&iov); + if (err) + break; + if (!iov.iov_base && tag) { + err = -EINVAL; + break; } + err = io_sqe_buffer_register(ctx, &iov, &imu, &last_hpage); + if (err) + break; - off = ubuf & ~PAGE_MASK; - size = iov.iov_len; - for (j = 0; j < nr_pages; j++) { - size_t vec_len; - - vec_len = min_t(size_t, size, PAGE_SIZE - off); - imu->bvec[j].bv_page = pages[j]; - imu->bvec[j].bv_len = vec_len; - imu->bvec[j].bv_offset = off; - off = 0; - size -= vec_len; + i = array_index_nospec(offset, ctx->nr_user_bufs); + if (ctx->user_bufs[i] != ctx->dummy_ubuf) { + err = io_queue_rsrc_removal(ctx->buf_data, i, + ctx->rsrc_node, ctx->user_bufs[i]); + if (unlikely(err)) { + io_buffer_unmap(ctx, &imu); + break; + } + ctx->user_bufs[i] = NULL; + needs_switch = true; } - /* store original address for later verification */ - imu->ubuf = ubuf; - imu->len = iov.iov_len; - imu->nr_bvecs = nr_pages; - ctx->nr_user_bufs++; + ctx->user_bufs[i] = imu; + *io_get_tag_slot(ctx->buf_data, offset) = tag; } - kvfree(pages); - kvfree(vmas); - return 0; -err: - kvfree(pages); - kvfree(vmas); - io_sqe_buffer_unregister(ctx); - return ret; + + if (needs_switch) + io_rsrc_node_switch(ctx, ctx->buf_data); + return done ? done : err; } static int io_eventfd_register(struct io_ring_ctx *ctx, void __user *arg) @@ -8396,6 +9141,7 @@ static int io_eventfd_register(struct io_ring_ctx *ctx, void __user *arg) ctx->cq_ev_fd = eventfd_ctx_fdget(fd); if (IS_ERR(ctx->cq_ev_fd)) { int ret = PTR_ERR(ctx->cq_ev_fd); + ctx->cq_ev_fd = NULL; return ret; } @@ -8423,26 +9169,68 @@ static void io_destroy_buffers(struct io_ring_ctx *ctx) __io_remove_buffers(ctx, buf, index, -1U); } -static void io_ring_ctx_free(struct io_ring_ctx *ctx) +static void io_req_cache_free(struct list_head *list) { - io_finish_async(ctx); - io_sqe_buffer_unregister(ctx); + struct io_kiocb *req, *nxt; - if (ctx->sqo_task) { - put_task_struct(ctx->sqo_task); - ctx->sqo_task = NULL; - mmdrop(ctx->mm_account); - ctx->mm_account = NULL; + list_for_each_entry_safe(req, nxt, list, inflight_entry) { + list_del(&req->inflight_entry); + kmem_cache_free(req_cachep, req); } +} -#ifdef CONFIG_BLK_CGROUP - if (ctx->sqo_blkcg_css) - css_put(ctx->sqo_blkcg_css); -#endif +static void io_req_caches_free(struct io_ring_ctx *ctx) +{ + struct io_submit_state *state = &ctx->submit_state; + + mutex_lock(&ctx->uring_lock); + + if (state->free_reqs) { + kmem_cache_free_bulk(req_cachep, state->free_reqs, state->reqs); + state->free_reqs = 0; + } + + io_flush_cached_locked_reqs(ctx, state); + io_req_cache_free(&state->free_list); + mutex_unlock(&ctx->uring_lock); +} + +static void io_wait_rsrc_data(struct io_rsrc_data *data) +{ + if (data && !atomic_dec_and_test(&data->refs)) + wait_for_completion(&data->done); +} + +static void io_ring_ctx_free(struct io_ring_ctx *ctx) +{ + io_sq_thread_finish(ctx); - io_sqe_files_unregister(ctx); + /* __io_rsrc_put_work() may need uring_lock to progress, wait w/o it */ + io_wait_rsrc_data(ctx->buf_data); + io_wait_rsrc_data(ctx->file_data); + + mutex_lock(&ctx->uring_lock); + if (ctx->buf_data) + __io_sqe_buffers_unregister(ctx); + if (ctx->file_data) + __io_sqe_files_unregister(ctx); + if (ctx->rings) + __io_cqring_overflow_flush(ctx, true); + mutex_unlock(&ctx->uring_lock); io_eventfd_unregister(ctx); io_destroy_buffers(ctx); + if (ctx->sq_creds) + put_cred(ctx->sq_creds); + + /* there are no registered resources left, nobody uses it */ + if (ctx->rsrc_node) + io_rsrc_node_destroy(ctx->rsrc_node); + if (ctx->rsrc_backup_node) + io_rsrc_node_destroy(ctx->rsrc_backup_node); + flush_delayed_work(&ctx->rsrc_put_work); + + WARN_ON_ONCE(!list_empty(&ctx->rsrc_ref_list)); + WARN_ON_ONCE(!llist_empty(&ctx->rsrc_put_llist)); #if defined(CONFIG_UNIX) if (ctx->ring_sock) { @@ -8450,15 +9238,23 @@ static void io_ring_ctx_free(struct io_ring_ctx *ctx) sock_release(ctx->ring_sock); } #endif + WARN_ON_ONCE(!list_empty(&ctx->ltimeout_list)); + + if (ctx->mm_account) { + mmdrop(ctx->mm_account); + ctx->mm_account = NULL; + } io_mem_free(ctx->rings); io_mem_free(ctx->sq_sqes); percpu_ref_exit(&ctx->refs); free_uid(ctx->user); - put_cred(ctx->creds); + io_req_caches_free(ctx); + if (ctx->hash_map) + io_wq_put_hash(ctx->hash_map); kfree(ctx->cancel_hash); - kmem_cache_free(req_cachep, ctx->fallback_req); + kfree(ctx->dummy_ubuf); kfree(ctx); } @@ -8467,7 +9263,7 @@ static __poll_t io_uring_poll(struct file *file, poll_table *wait) struct io_ring_ctx *ctx = file->private_data; __poll_t mask = 0; - poll_wait(file, &ctx->cq_wait, wait); + poll_wait(file, &ctx->poll_wait, wait); /* * synchronizes with barrier from wq_has_sleeper call in * io_commit_cqring @@ -8489,38 +9285,63 @@ static __poll_t io_uring_poll(struct file *file, poll_table *wait) * Users may get EPOLLIN meanwhile seeing nothing in cqring, this * pushs them to do the flush. */ - if (io_cqring_events(ctx) || test_bit(0, &ctx->cq_check_overflow)) + if (io_cqring_events(ctx) || test_bit(0, &ctx->check_cq_overflow)) mask |= EPOLLIN | EPOLLRDNORM; return mask; } -static int io_uring_fasync(int fd, struct file *file, int on) -{ - struct io_ring_ctx *ctx = file->private_data; - - return fasync_helper(fd, file, on, &ctx->cq_fasync); -} - static int io_unregister_personality(struct io_ring_ctx *ctx, unsigned id) { - struct io_identity *iod; + const struct cred *creds; - iod = xa_erase(&ctx->personalities, id); - if (iod) { - put_cred(iod->creds); - if (refcount_dec_and_test(&iod->count)) - kfree(iod); + creds = xa_erase(&ctx->personalities, id); + if (creds) { + put_cred(creds); return 0; } return -EINVAL; } +struct io_tctx_exit { + struct callback_head task_work; + struct completion completion; + struct io_ring_ctx *ctx; +}; + +static void io_tctx_exit_cb(struct callback_head *cb) +{ + struct io_uring_task *tctx = current->io_uring; + struct io_tctx_exit *work; + + work = container_of(cb, struct io_tctx_exit, task_work); + /* + * When @in_idle, we're in cancellation and it's racy to remove the + * node. It'll be removed by the end of cancellation, just ignore it. + * tctx can be NULL if the queueing of this task_work raced with + * work cancelation off the exec path. + */ + if (tctx && !atomic_read(&tctx->in_idle)) + io_uring_del_tctx_node((unsigned long)work->ctx); + complete(&work->completion); +} + +static bool io_cancel_ctx_cb(struct io_wq_work *work, void *data) +{ + struct io_kiocb *req = container_of(work, struct io_kiocb, work); + + return req->ctx == data; +} + static void io_ring_exit_work(struct work_struct *work) { - struct io_ring_ctx *ctx = container_of(work, struct io_ring_ctx, - exit_work); + struct io_ring_ctx *ctx = container_of(work, struct io_ring_ctx, exit_work); + unsigned long timeout = jiffies + HZ * 60 * 5; + unsigned long interval = HZ / 20; + struct io_tctx_exit exit; + struct io_tctx_node *node; + int ret; /* * If we're doing polled IO and end up having requests being @@ -8529,53 +9350,100 @@ static void io_ring_exit_work(struct work_struct *work) * as nobody else will be looking for them. */ do { - io_iopoll_try_reap_events(ctx); - } while (!wait_for_completion_timeout(&ctx->ref_comp, HZ/20)); + io_uring_try_cancel_requests(ctx, NULL, true); + if (ctx->sq_data) { + struct io_sq_data *sqd = ctx->sq_data; + struct task_struct *tsk; + + io_sq_thread_park(sqd); + tsk = sqd->thread; + if (tsk && tsk->io_uring && tsk->io_uring->io_wq) + io_wq_cancel_cb(tsk->io_uring->io_wq, + io_cancel_ctx_cb, ctx, true); + io_sq_thread_unpark(sqd); + } + + if (WARN_ON_ONCE(time_after(jiffies, timeout))) { + /* there is little hope left, don't run it too often */ + interval = HZ * 60; + } + } while (!wait_for_completion_timeout(&ctx->ref_comp, interval)); + + init_completion(&exit.completion); + init_task_work(&exit.task_work, io_tctx_exit_cb); + exit.ctx = ctx; + /* + * Some may use context even when all refs and requests have been put, + * and they are free to do so while still holding uring_lock or + * completion_lock, see io_req_task_submit(). Apart from other work, + * this lock/unlock section also waits them to finish. + */ + mutex_lock(&ctx->uring_lock); + while (!list_empty(&ctx->tctx_list)) { + WARN_ON_ONCE(time_after(jiffies, timeout)); + + node = list_first_entry(&ctx->tctx_list, struct io_tctx_node, + ctx_node); + /* don't spin on a single task if cancellation failed */ + list_rotate_left(&ctx->tctx_list); + ret = task_work_add(node->task, &exit.task_work, TWA_SIGNAL); + if (WARN_ON_ONCE(ret)) + continue; + wake_up_process(node->task); + + mutex_unlock(&ctx->uring_lock); + wait_for_completion(&exit.completion); + mutex_lock(&ctx->uring_lock); + } + mutex_unlock(&ctx->uring_lock); + spin_lock(&ctx->completion_lock); + spin_unlock(&ctx->completion_lock); + io_ring_ctx_free(ctx); } -static bool io_cancel_ctx_cb(struct io_wq_work *work, void *data) +/* Returns true if we found and killed one or more timeouts */ +static bool io_kill_timeouts(struct io_ring_ctx *ctx, struct task_struct *tsk, + bool cancel_all) { - struct io_kiocb *req = container_of(work, struct io_kiocb, work); + struct io_kiocb *req, *tmp; + int canceled = 0; - return req->ctx == data; + spin_lock(&ctx->completion_lock); + spin_lock_irq(&ctx->timeout_lock); + list_for_each_entry_safe(req, tmp, &ctx->timeout_list, timeout.list) { + if (io_match_task(req, tsk, cancel_all)) { + io_kill_timeout(req, -ECANCELED); + canceled++; + } + } + spin_unlock_irq(&ctx->timeout_lock); + if (canceled != 0) + io_commit_cqring(ctx); + spin_unlock(&ctx->completion_lock); + if (canceled != 0) + io_cqring_ev_posted(ctx); + return canceled != 0; } static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx) { unsigned long index; - struct io_identify *iod; + struct creds *creds; mutex_lock(&ctx->uring_lock); percpu_ref_kill(&ctx->refs); - /* if force is set, the ring is going away. always drop after that */ - - if (WARN_ON_ONCE((ctx->flags & IORING_SETUP_SQPOLL) && !ctx->sqo_dead)) - ctx->sqo_dead = 1; - - ctx->cq_overflow_flushed = 1; if (ctx->rings) - __io_cqring_overflow_flush(ctx, true, NULL, NULL); + __io_cqring_overflow_flush(ctx, true); + xa_for_each(&ctx->personalities, index, creds) + io_unregister_personality(ctx, index); mutex_unlock(&ctx->uring_lock); - io_kill_timeouts(ctx, NULL, NULL); - io_poll_remove_all(ctx, NULL, NULL); - - if (ctx->io_wq) - io_wq_cancel_cb(ctx->io_wq, io_cancel_ctx_cb, ctx, true); + io_kill_timeouts(ctx, NULL, true); + io_poll_remove_all(ctx, NULL, true); /* if we failed setting up the ctx, we might not have any rings */ io_iopoll_try_reap_events(ctx); - xa_for_each(&ctx->personalities, index, iod) - io_unregister_personality(ctx, index); - - /* - * Do this upfront, so we won't have a grace period where the ring - * is closed but resources aren't reaped yet. This can cause - * spurious failure in setting up a new ring. - */ - io_unaccount_mem(ctx, ring_pages(ctx->sq_entries, ctx->cq_entries), - ACCT_LOCKED); INIT_WORK(&ctx->exit_work, io_ring_exit_work); /* @@ -8598,352 +9466,290 @@ static int io_uring_release(struct inode *inode, struct file *file) struct io_task_cancel { struct task_struct *task; - struct files_struct *files; + bool all; }; static bool io_cancel_task_cb(struct io_wq_work *work, void *data) { struct io_kiocb *req = container_of(work, struct io_kiocb, work); struct io_task_cancel *cancel = data; - bool ret; - - if (cancel->files && (req->flags & REQ_F_LINK_TIMEOUT)) { - unsigned long flags; - struct io_ring_ctx *ctx = req->ctx; - /* protect against races with linked timeouts */ - spin_lock_irqsave(&ctx->completion_lock, flags); - ret = io_match_task(req, cancel->task, cancel->files); - spin_unlock_irqrestore(&ctx->completion_lock, flags); - } else { - ret = io_match_task(req, cancel->task, cancel->files); - } - return ret; + return io_match_task_safe(req, cancel->task, cancel->all); } -static void io_cancel_defer_files(struct io_ring_ctx *ctx, - struct task_struct *task, - struct files_struct *files) +static bool io_cancel_defer_files(struct io_ring_ctx *ctx, + struct task_struct *task, bool cancel_all) { - struct io_defer_entry *de = NULL; + struct io_defer_entry *de; LIST_HEAD(list); - spin_lock_irq(&ctx->completion_lock); + spin_lock(&ctx->completion_lock); list_for_each_entry_reverse(de, &ctx->defer_list, list) { - if (io_match_task(de->req, task, files)) { + if (io_match_task_safe(de->req, task, cancel_all)) { list_cut_position(&list, &ctx->defer_list, &de->list); break; } } - spin_unlock_irq(&ctx->completion_lock); + spin_unlock(&ctx->completion_lock); + if (list_empty(&list)) + return false; while (!list_empty(&list)) { de = list_first_entry(&list, struct io_defer_entry, list); list_del_init(&de->list); - req_set_fail_links(de->req); - io_put_req(de->req); - io_req_complete(de->req, -ECANCELED); + io_req_complete_failed(de->req, -ECANCELED); kfree(de); } + return true; } -static int io_uring_count_inflight(struct io_ring_ctx *ctx, - struct task_struct *task, - struct files_struct *files) -{ - struct io_kiocb *req; - int cnt = 0; - - spin_lock_irq(&ctx->inflight_lock); - list_for_each_entry(req, &ctx->inflight_list, inflight_entry) - cnt += io_match_task(req, task, files); - spin_unlock_irq(&ctx->inflight_lock); - return cnt; -} - -static void io_uring_cancel_files(struct io_ring_ctx *ctx, - struct task_struct *task, - struct files_struct *files) +static bool io_uring_try_cancel_iowq(struct io_ring_ctx *ctx) { - while (!list_empty_careful(&ctx->inflight_list)) { - struct io_task_cancel cancel = { .task = task, .files = files }; - DEFINE_WAIT(wait); - int inflight; - - inflight = io_uring_count_inflight(ctx, task, files); - if (!inflight) - break; + struct io_tctx_node *node; + enum io_wq_cancel cret; + bool ret = false; - io_wq_cancel_cb(ctx->io_wq, io_cancel_task_cb, &cancel, true); - io_poll_remove_all(ctx, task, files); - io_kill_timeouts(ctx, task, files); - /* cancellations _may_ trigger task work */ - io_run_task_work(); + mutex_lock(&ctx->uring_lock); + list_for_each_entry(node, &ctx->tctx_list, ctx_node) { + struct io_uring_task *tctx = node->task->io_uring; - prepare_to_wait(&task->io_uring->wait, &wait, - TASK_UNINTERRUPTIBLE); - if (inflight == io_uring_count_inflight(ctx, task, files)) - schedule(); - finish_wait(&task->io_uring->wait, &wait); + /* + * io_wq will stay alive while we hold uring_lock, because it's + * killed after ctx nodes, which requires to take the lock. + */ + if (!tctx || !tctx->io_wq) + continue; + cret = io_wq_cancel_cb(tctx->io_wq, io_cancel_ctx_cb, ctx, true); + ret |= (cret != IO_WQ_CANCEL_NOTFOUND); } + mutex_unlock(&ctx->uring_lock); + + return ret; } -static void __io_uring_cancel_task_requests(struct io_ring_ctx *ctx, - struct task_struct *task) +static void io_uring_try_cancel_requests(struct io_ring_ctx *ctx, + struct task_struct *task, + bool cancel_all) { + struct io_task_cancel cancel = { .task = task, .all = cancel_all, }; + struct io_uring_task *tctx = task ? task->io_uring : NULL; + while (1) { - struct io_task_cancel cancel = { .task = task, .files = NULL, }; enum io_wq_cancel cret; bool ret = false; - cret = io_wq_cancel_cb(ctx->io_wq, io_cancel_task_cb, &cancel, true); - if (cret != IO_WQ_CANCEL_NOTFOUND) - ret = true; + if (!task) { + ret |= io_uring_try_cancel_iowq(ctx); + } else if (tctx && tctx->io_wq) { + /* + * Cancels requests of all rings, not only @ctx, but + * it's fine as the task is in exit/exec. + */ + cret = io_wq_cancel_cb(tctx->io_wq, io_cancel_task_cb, + &cancel, true); + ret |= (cret != IO_WQ_CANCEL_NOTFOUND); + } /* SQPOLL thread does its own polling */ - if (!(ctx->flags & IORING_SETUP_SQPOLL)) { + if ((!(ctx->flags & IORING_SETUP_SQPOLL) && cancel_all) || + (ctx->sq_data && ctx->sq_data->thread == current)) { while (!list_empty_careful(&ctx->iopoll_list)) { io_iopoll_try_reap_events(ctx); ret = true; } } - ret |= io_poll_remove_all(ctx, task, NULL); - ret |= io_kill_timeouts(ctx, task, NULL); + ret |= io_cancel_defer_files(ctx, task, cancel_all); + ret |= io_poll_remove_all(ctx, task, cancel_all); + ret |= io_kill_timeouts(ctx, task, cancel_all); + if (task) + ret |= io_run_task_work(); if (!ret) break; - io_run_task_work(); cond_resched(); } } -static void io_disable_sqo_submit(struct io_ring_ctx *ctx) -{ - mutex_lock(&ctx->uring_lock); - ctx->sqo_dead = 1; - if (ctx->flags & IORING_SETUP_R_DISABLED) - io_sq_offload_start(ctx); - mutex_unlock(&ctx->uring_lock); - - /* make sure callers enter the ring to get error */ - if (ctx->rings) - io_ring_set_wakeup_flag(ctx); -} - -/* - * We need to iteratively cancel requests, in case a request has dependent - * hard links. These persist even for failure of cancelations, hence keep - * looping until none are found. - */ -static void io_uring_cancel_task_requests(struct io_ring_ctx *ctx, - struct files_struct *files) -{ - struct task_struct *task = current; - - if ((ctx->flags & IORING_SETUP_SQPOLL) && ctx->sq_data) { - io_disable_sqo_submit(ctx); - task = ctx->sq_data->thread; - atomic_inc(&task->io_uring->in_idle); - io_sq_thread_park(ctx->sq_data); - } - - io_cancel_defer_files(ctx, task, files); - io_cqring_overflow_flush(ctx, true, task, files); - - if (!files) - __io_uring_cancel_task_requests(ctx, task); - else - io_uring_cancel_files(ctx, task, files); - - if ((ctx->flags & IORING_SETUP_SQPOLL) && ctx->sq_data) { - atomic_dec(&task->io_uring->in_idle); - io_sq_thread_unpark(ctx->sq_data); - } -} - -/* - * Note that this task has used io_uring. We use it for cancelation purposes. - */ -static int io_uring_add_task_file(struct io_ring_ctx *ctx, struct file *file) +static int __io_uring_add_tctx_node(struct io_ring_ctx *ctx) { struct io_uring_task *tctx = current->io_uring; + struct io_tctx_node *node; int ret; if (unlikely(!tctx)) { - ret = io_uring_alloc_task_context(current); + ret = io_uring_alloc_task_context(current, ctx); if (unlikely(ret)) return ret; + tctx = current->io_uring; - } - if (tctx->last != file) { - void *old = xa_load(&tctx->xa, (unsigned long)file); + if (ctx->iowq_limits_set) { + unsigned int limits[2] = { ctx->iowq_limits[0], + ctx->iowq_limits[1], }; - if (!old) { - get_file(file); - ret = xa_err(xa_store(&tctx->xa, (unsigned long)file, - file, GFP_KERNEL)); - if (ret) { - fput(file); + ret = io_wq_max_workers(tctx->io_wq, limits); + if (ret) return ret; - } } - tctx->last = file; } + if (!xa_load(&tctx->xa, (unsigned long)ctx)) { + node = kmalloc(sizeof(*node), GFP_KERNEL); + if (!node) + return -ENOMEM; + node->ctx = ctx; + node->task = current; - /* - * This is race safe in that the task itself is doing this, hence it - * cannot be going through the exit/cancel paths at the same time. - * This cannot be modified while exit/cancel is running. - */ - if (!tctx->sqpoll && (ctx->flags & IORING_SETUP_SQPOLL)) - tctx->sqpoll = true; + ret = xa_err(xa_store(&tctx->xa, (unsigned long)ctx, + node, GFP_KERNEL)); + if (ret) { + kfree(node); + return ret; + } + mutex_lock(&ctx->uring_lock); + list_add(&node->ctx_node, &ctx->tctx_list); + mutex_unlock(&ctx->uring_lock); + } + tctx->last = ctx; return 0; } /* - * Remove this io_uring_file -> task mapping. + * Note that this task has used io_uring. We use it for cancelation purposes. */ -static void io_uring_del_task_file(struct file *file) +static inline int io_uring_add_tctx_node(struct io_ring_ctx *ctx) { struct io_uring_task *tctx = current->io_uring; - if (tctx->last == file) - tctx->last = NULL; - file = xa_erase(&tctx->xa, (unsigned long)file); - if (file) - fput(file); + if (likely(tctx && tctx->last == ctx)) + return 0; + return __io_uring_add_tctx_node(ctx); } -static void io_uring_remove_task_files(struct io_uring_task *tctx) +/* + * Remove this io_uring_file -> task mapping. + */ +static void io_uring_del_tctx_node(unsigned long index) { - struct file *file; - unsigned long index; + struct io_uring_task *tctx = current->io_uring; + struct io_tctx_node *node; - xa_for_each(&tctx->xa, index, file) - io_uring_del_task_file(file); -} + if (!tctx) + return; + node = xa_erase(&tctx->xa, index); + if (!node) + return; -void __io_uring_files_cancel(struct files_struct *files) -{ - struct io_uring_task *tctx = current->io_uring; - struct file *file; - unsigned long index; + WARN_ON_ONCE(current != node->task); + WARN_ON_ONCE(list_empty(&node->ctx_node)); - /* make sure overflow events are dropped */ - atomic_inc(&tctx->in_idle); - xa_for_each(&tctx->xa, index, file) - io_uring_cancel_task_requests(file->private_data, files); - atomic_dec(&tctx->in_idle); + mutex_lock(&node->ctx->uring_lock); + list_del(&node->ctx_node); + mutex_unlock(&node->ctx->uring_lock); - if (files) - io_uring_remove_task_files(tctx); + if (tctx->last == node->ctx) + tctx->last = NULL; + kfree(node); } -static s64 tctx_inflight(struct io_uring_task *tctx) +static void io_uring_clean_tctx(struct io_uring_task *tctx) { + struct io_wq *wq = tctx->io_wq; + struct io_tctx_node *node; unsigned long index; - struct file *file; - s64 inflight; - - inflight = percpu_counter_sum(&tctx->inflight); - if (!tctx->sqpoll) - return inflight; - /* - * If we have SQPOLL rings, then we need to iterate and find them, and - * add the pending count for those. - */ - xa_for_each(&tctx->xa, index, file) { - struct io_ring_ctx *ctx = file->private_data; - - if (ctx->flags & IORING_SETUP_SQPOLL) { - struct io_uring_task *__tctx = ctx->sqo_task->io_uring; - - inflight += percpu_counter_sum(&__tctx->inflight); - } + xa_for_each(&tctx->xa, index, node) { + io_uring_del_tctx_node(index); + cond_resched(); + } + if (wq) { + /* + * Must be after io_uring_del_task_file() (removes nodes under + * uring_lock) to avoid race with io_uring_try_cancel_iowq(). + */ + io_wq_put_and_exit(wq); + tctx->io_wq = NULL; } +} - return inflight; +static s64 tctx_inflight(struct io_uring_task *tctx, bool tracked) +{ + if (tracked) + return atomic_read(&tctx->inflight_tracked); + return percpu_counter_sum(&tctx->inflight); } /* - * Find any io_uring fd that this task has registered or done IO on, and cancel - * requests. + * Find any io_uring ctx that this task has registered or done IO on, and cancel + * requests. @sqd should be not-null IFF it's an SQPOLL thread cancellation. */ -void __io_uring_task_cancel(void) +static void io_uring_cancel_generic(bool cancel_all, struct io_sq_data *sqd) { struct io_uring_task *tctx = current->io_uring; - DEFINE_WAIT(wait); + struct io_ring_ctx *ctx; s64 inflight; + DEFINE_WAIT(wait); - /* make sure overflow events are dropped */ - atomic_inc(&tctx->in_idle); + WARN_ON_ONCE(sqd && sqd->thread != current); - /* trigger io_disable_sqo_submit() */ - if (tctx->sqpoll) - __io_uring_files_cancel(NULL); + if (!current->io_uring) + return; + if (tctx->io_wq) + io_wq_exit_start(tctx->io_wq); + atomic_inc(&tctx->in_idle); do { + io_uring_drop_tctx_refs(current); /* read completions before cancelations */ - inflight = tctx_inflight(tctx); + inflight = tctx_inflight(tctx, !cancel_all); if (!inflight) break; - __io_uring_files_cancel(NULL); - - prepare_to_wait(&tctx->wait, &wait, TASK_UNINTERRUPTIBLE); - - /* - * If we've seen completions, retry without waiting. This - * avoids a race where a completion comes in before we did - * prepare_to_wait(). - */ - if (inflight == tctx_inflight(tctx)) - schedule(); - finish_wait(&tctx->wait, &wait); - } while (1); - - atomic_dec(&tctx->in_idle); - - io_uring_remove_task_files(tctx); -} - -static int io_uring_flush(struct file *file, void *data) -{ - struct io_uring_task *tctx = current->io_uring; - struct io_ring_ctx *ctx = file->private_data; - - if (fatal_signal_pending(current) || (current->flags & PF_EXITING)) - io_uring_cancel_task_requests(ctx, NULL); - if (!tctx) - return 0; + if (!sqd) { + struct io_tctx_node *node; + unsigned long index; - /* we should have cancelled and erased it before PF_EXITING */ - WARN_ON_ONCE((current->flags & PF_EXITING) && - xa_load(&tctx->xa, (unsigned long)file)); + xa_for_each(&tctx->xa, index, node) { + /* sqpoll task will cancel all its requests */ + if (node->ctx->sq_data) + continue; + io_uring_try_cancel_requests(node->ctx, current, + cancel_all); + } + } else { + list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) + io_uring_try_cancel_requests(ctx, current, + cancel_all); + } - /* - * fput() is pending, will be 2 if the only other ref is our potential - * task file note. If the task is exiting, drop regardless of count. - */ - if (atomic_long_read(&file->f_count) != 2) - return 0; + prepare_to_wait(&tctx->wait, &wait, TASK_INTERRUPTIBLE); + io_run_task_work(); + io_uring_drop_tctx_refs(current); - if (ctx->flags & IORING_SETUP_SQPOLL) { - /* there is only one file note, which is owned by sqo_task */ - WARN_ON_ONCE(ctx->sqo_task != current && - xa_load(&tctx->xa, (unsigned long)file)); - /* sqo_dead check is for when this happens after cancellation */ - WARN_ON_ONCE(ctx->sqo_task == current && !ctx->sqo_dead && - !xa_load(&tctx->xa, (unsigned long)file)); + /* + * If we've seen completions, retry without waiting. This + * avoids a race where a completion comes in before we did + * prepare_to_wait(). + */ + if (inflight == tctx_inflight(tctx, !cancel_all)) + schedule(); + finish_wait(&tctx->wait, &wait); + } while (1); - io_disable_sqo_submit(ctx); + io_uring_clean_tctx(tctx); + if (cancel_all) { + /* + * We shouldn't run task_works after cancel, so just leave + * ->in_idle set for normal exit. + */ + atomic_dec(&tctx->in_idle); + /* for exec all current's requests should be gone, kill tctx */ + __io_uring_free(current); } +} - if (!(ctx->flags & IORING_SETUP_SQPOLL) || ctx->sqo_task == current) - io_uring_del_task_file(file); - return 0; +void __io_uring_cancel(bool cancel_all) +{ + io_uring_cancel_generic(cancel_all, NULL); } static void *io_uring_validate_mmap_request(struct file *file, @@ -9018,60 +9824,84 @@ static unsigned long io_uring_nommu_get_unmapped_area(struct file *file, static int io_sqpoll_wait_sq(struct io_ring_ctx *ctx) { - int ret = 0; DEFINE_WAIT(wait); do { if (!io_sqring_full(ctx)) break; - prepare_to_wait(&ctx->sqo_sq_wait, &wait, TASK_INTERRUPTIBLE); - if (unlikely(ctx->sqo_dead)) { - ret = -EOWNERDEAD; - break; - } - if (!io_sqring_full(ctx)) break; - schedule(); } while (!signal_pending(current)); finish_wait(&ctx->sqo_sq_wait, &wait); - return ret; + return 0; +} + +static int io_get_ext_arg(unsigned flags, const void __user *argp, size_t *argsz, + struct __kernel_timespec __user **ts, + const sigset_t __user **sig) +{ + struct io_uring_getevents_arg arg; + + /* + * If EXT_ARG isn't set, then we have no timespec and the argp pointer + * is just a pointer to the sigset_t. + */ + if (!(flags & IORING_ENTER_EXT_ARG)) { + *sig = (const sigset_t __user *) argp; + *ts = NULL; + return 0; + } + + /* + * EXT_ARG is set - ensure we agree on the size of it and copy in our + * timespec and sigset_t pointers if good. + */ + if (*argsz != sizeof(arg)) + return -EINVAL; + if (copy_from_user(&arg, argp, sizeof(arg))) + return -EFAULT; + if (arg.pad) + return -EINVAL; + *sig = u64_to_user_ptr(arg.sigmask); + *argsz = arg.sigmask_sz; + *ts = u64_to_user_ptr(arg.ts); + return 0; } SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit, - u32, min_complete, u32, flags, const sigset_t __user *, sig, - size_t, sigsz) + u32, min_complete, u32, flags, const void __user *, argp, + size_t, argsz) { struct io_ring_ctx *ctx; - long ret = -EBADF; int submitted = 0; struct fd f; + long ret; io_run_task_work(); - if (flags & ~(IORING_ENTER_GETEVENTS | IORING_ENTER_SQ_WAKEUP | - IORING_ENTER_SQ_WAIT)) + if (unlikely(flags & ~(IORING_ENTER_GETEVENTS | IORING_ENTER_SQ_WAKEUP | + IORING_ENTER_SQ_WAIT | IORING_ENTER_EXT_ARG))) return -EINVAL; f = fdget(fd); - if (!f.file) + if (unlikely(!f.file)) return -EBADF; ret = -EOPNOTSUPP; - if (f.file->f_op != &io_uring_fops) + if (unlikely(f.file->f_op != &io_uring_fops)) goto out_fput; ret = -ENXIO; ctx = f.file->private_data; - if (!percpu_ref_tryget(&ctx->refs)) + if (unlikely(!percpu_ref_tryget(&ctx->refs))) goto out_fput; ret = -EBADFD; - if (ctx->flags & IORING_SETUP_R_DISABLED) + if (unlikely(ctx->flags & IORING_SETUP_R_DISABLED)) goto out; /* @@ -9081,9 +9911,9 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit, */ ret = 0; if (ctx->flags & IORING_SETUP_SQPOLL) { - io_cqring_overflow_flush(ctx, false, NULL, NULL); + io_cqring_overflow_flush(ctx); - if (unlikely(ctx->sqo_dead)) { + if (unlikely(ctx->sq_data->thread == NULL)) { ret = -EOWNERDEAD; goto out; } @@ -9096,7 +9926,7 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit, } submitted = to_submit; } else if (to_submit) { - ret = io_uring_add_task_file(ctx, f.file); + ret = io_uring_add_tctx_node(ctx); if (unlikely(ret)) goto out; mutex_lock(&ctx->uring_lock); @@ -9107,6 +9937,13 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit, goto out; } if (flags & IORING_ENTER_GETEVENTS) { + const sigset_t __user *sig; + struct __kernel_timespec __user *ts; + + ret = io_get_ext_arg(flags, argp, &argsz, &ts, &sig); + if (unlikely(ret)) + goto out; + min_complete = min(min_complete, ctx->cq_entries); /* @@ -9119,7 +9956,7 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit, !(ctx->flags & IORING_SETUP_SQPOLL)) { ret = io_iopoll_check(ctx, min_complete); } else { - ret = io_cqring_wait(ctx, min_complete, sig, sigsz); + ret = io_cqring_wait(ctx, min_complete, sig, argsz, ts); } } @@ -9132,9 +9969,8 @@ out_fput: #ifdef CONFIG_PROC_FS static int io_uring_show_cred(struct seq_file *m, unsigned int id, - const struct io_identity *iod) + const struct cred *cred) { - const struct cred *cred = iod->creds; struct user_namespace *uns = seq_user_ns(m); struct group_info *gi; kernel_cap_t cap; @@ -9178,18 +10014,18 @@ static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m) */ has_lock = mutex_trylock(&ctx->uring_lock); - if (has_lock && (ctx->flags & IORING_SETUP_SQPOLL)) + if (has_lock && (ctx->flags & IORING_SETUP_SQPOLL)) { sq = ctx->sq_data; + if (!sq->thread) + sq = NULL; + } seq_printf(m, "SqThread:\t%d\n", sq ? task_pid_nr(sq->thread) : -1); seq_printf(m, "SqThreadCpu:\t%d\n", sq ? task_cpu(sq->thread) : -1); seq_printf(m, "UserFiles:\t%u\n", ctx->nr_user_files); for (i = 0; has_lock && i < ctx->nr_user_files; i++) { - struct fixed_file_table *table; - struct file *f; + struct file *f = io_file_from_index(ctx, i); - table = &ctx->file_data->table[i >> IORING_FILE_TABLE_SHIFT]; - f = table->files[i & IORING_FILE_TABLE_MASK]; if (f) seq_printf(m, "%5u: %s\n", i, file_dentry(f)->d_iname); else @@ -9197,21 +10033,21 @@ static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m) } seq_printf(m, "UserBufs:\t%u\n", ctx->nr_user_bufs); for (i = 0; has_lock && i < ctx->nr_user_bufs; i++) { - struct io_mapped_ubuf *buf = &ctx->user_bufs[i]; + struct io_mapped_ubuf *buf = ctx->user_bufs[i]; + unsigned int len = buf->ubuf_end - buf->ubuf; - seq_printf(m, "%5u: 0x%llx/%u\n", i, buf->ubuf, - (unsigned int) buf->len); + seq_printf(m, "%5u: 0x%llx/%u\n", i, buf->ubuf, len); } if (has_lock && !xa_empty(&ctx->personalities)) { unsigned long index; - const struct io_identity *iod; + const struct cred *cred; seq_printf(m, "Personalities:\n"); - xa_for_each(&ctx->personalities, index, iod) - io_uring_show_cred(m, index, iod); + xa_for_each(&ctx->personalities, index, cred) + io_uring_show_cred(m, index, cred); } seq_printf(m, "PollList:\n"); - spin_lock_irq(&ctx->completion_lock); + spin_lock(&ctx->completion_lock); for (i = 0; i < (1U << ctx->cancel_hash_bits); i++) { struct hlist_head *list = &ctx->cancel_hash[i]; struct io_kiocb *req; @@ -9220,7 +10056,7 @@ static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m) seq_printf(m, " op=%d, task_works=%d\n", req->opcode, req->task->task_works != NULL); } - spin_unlock_irq(&ctx->completion_lock); + spin_unlock(&ctx->completion_lock); if (has_lock) mutex_unlock(&ctx->uring_lock); } @@ -9238,14 +10074,12 @@ static void io_uring_show_fdinfo(struct seq_file *m, struct file *f) static const struct file_operations io_uring_fops = { .release = io_uring_release, - .flush = io_uring_flush, .mmap = io_uring_mmap, #ifndef CONFIG_MMU .get_unmapped_area = io_uring_nommu_get_unmapped_area, .mmap_capabilities = io_uring_nommu_mmap_capabilities, #endif .poll = io_uring_poll, - .fasync = io_uring_fasync, #ifdef CONFIG_PROC_FS .show_fdinfo = io_uring_show_fdinfo, #endif @@ -9275,8 +10109,6 @@ static int io_allocate_scq_urings(struct io_ring_ctx *ctx, rings->cq_ring_mask = p->cq_entries - 1; rings->sq_ring_entries = p->sq_entries; rings->cq_ring_entries = p->cq_entries; - ctx->sq_mask = rings->sq_ring_mask; - ctx->cq_mask = rings->cq_ring_mask; size = array_size(sizeof(struct io_uring_sqe), p->sq_entries); if (size == SIZE_MAX) { @@ -9303,7 +10135,7 @@ static int io_uring_install_fd(struct io_ring_ctx *ctx, struct file *file) if (fd < 0) return fd; - ret = io_uring_add_task_file(ctx, file); + ret = io_uring_add_tctx_node(ctx); if (ret) { put_unused_fd(fd); return ret; @@ -9346,10 +10178,8 @@ static struct file *io_uring_get_file(struct io_ring_ctx *ctx) static int io_uring_create(unsigned entries, struct io_uring_params *p, struct io_uring_params __user *params) { - struct user_struct *user = NULL; struct io_ring_ctx *ctx; struct file *file; - bool limit_mem; int ret; if (!entries) @@ -9389,34 +10219,12 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p, p->cq_entries = 2 * p->sq_entries; } - user = get_uid(current_user()); - limit_mem = !capable(CAP_IPC_LOCK); - - if (limit_mem) { - ret = __io_account_mem(user, - ring_pages(p->sq_entries, p->cq_entries)); - if (ret) { - free_uid(user); - return ret; - } - } - ctx = io_ring_ctx_alloc(p); - if (!ctx) { - if (limit_mem) - __io_unaccount_mem(user, ring_pages(p->sq_entries, - p->cq_entries)); - free_uid(user); + if (!ctx) return -ENOMEM; - } ctx->compat = in_compat_syscall(); - ctx->user = user; - ctx->creds = get_current_cred(); -#ifdef CONFIG_AUDIT - ctx->loginuid = current->loginuid; - ctx->sessionid = current->sessionid; -#endif - ctx->sqo_task = get_task_struct(current); + if (!capable(CAP_IPC_LOCK)) + ctx->user = get_uid(current_user()); /* * This is just grabbed for accounting purposes. When a process exits, @@ -9427,35 +10235,6 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p, mmgrab(current->mm); ctx->mm_account = current->mm; -#ifdef CONFIG_BLK_CGROUP - /* - * The sq thread will belong to the original cgroup it was inited in. - * If the cgroup goes offline (e.g. disabling the io controller), then - * issued bios will be associated with the closest cgroup later in the - * block layer. - */ - rcu_read_lock(); - ctx->sqo_blkcg_css = blkcg_css(); - ret = css_tryget_online(ctx->sqo_blkcg_css); - rcu_read_unlock(); - if (!ret) { - /* don't init against a dying cgroup, have the user try again */ - ctx->sqo_blkcg_css = NULL; - ret = -ENODEV; - goto err; - } -#endif - - /* - * Account memory _before_ installing the file descriptor. Once - * the descriptor is installed, it can get closed at any time. Also - * do this before hitting the general error path, as ring freeing - * will un-account as well. - */ - io_account_mem(ctx, ring_pages(p->sq_entries, p->cq_entries), - ACCT_LOCKED); - ctx->limit_mem = limit_mem; - ret = io_allocate_scq_urings(ctx, p); if (ret) goto err; @@ -9463,9 +10242,11 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p, ret = io_sq_offload_create(ctx, p); if (ret) goto err; - - if (!(p->flags & IORING_SETUP_R_DISABLED)) - io_sq_offload_start(ctx); + /* always set a rsrc node */ + ret = io_rsrc_node_switch_start(ctx); + if (ret) + goto err; + io_rsrc_node_switch(ctx, NULL); memset(&p->sq_off, 0, sizeof(p->sq_off)); p->sq_off.head = offsetof(struct io_rings, sq.head); @@ -9488,7 +10269,9 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p, p->features = IORING_FEAT_SINGLE_MMAP | IORING_FEAT_NODROP | IORING_FEAT_SUBMIT_STABLE | IORING_FEAT_RW_CUR_POS | IORING_FEAT_CUR_PERSONALITY | IORING_FEAT_FAST_POLL | - IORING_FEAT_POLL_32BITS; + IORING_FEAT_POLL_32BITS | IORING_FEAT_SQPOLL_NONFIXED | + IORING_FEAT_EXT_ARG | IORING_FEAT_NATIVE_WORKERS | + IORING_FEAT_RSRC_TAGS; if (copy_to_user(params, p, sizeof(*p))) { ret = -EFAULT; @@ -9507,7 +10290,6 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p, */ ret = io_uring_install_fd(ctx, file); if (ret < 0) { - io_disable_sqo_submit(ctx); /* fput will clean it up */ fput(file); return ret; @@ -9516,7 +10298,6 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p, trace_io_uring_create(ret, ctx, p->sq_entries, p->cq_entries, p->flags); return ret; err: - io_disable_sqo_submit(ctx); io_ring_ctx_wait_and_kill(ctx); return ret; } @@ -9594,22 +10375,16 @@ out: static int io_register_personality(struct io_ring_ctx *ctx) { - struct io_identity *iod; + const struct cred *creds; u32 id; int ret; - iod = kmalloc(sizeof(*iod), GFP_KERNEL); - if (unlikely(!iod)) - return -ENOMEM; - - io_init_identity(iod); - iod->creds = get_current_cred(); + creds = get_current_cred(); - ret = xa_alloc_cyclic(&ctx->personalities, &id, (void *)iod, + ret = xa_alloc_cyclic(&ctx->personalities, &id, (void *)creds, XA_LIMIT(0, USHRT_MAX), &ctx->pers_next, GFP_KERNEL); if (ret < 0) { - put_cred(iod->creds); - kfree(iod); + put_cred(creds); return ret; } return id; @@ -9693,24 +10468,273 @@ static int io_register_enable_rings(struct io_ring_ctx *ctx) if (ctx->restrictions.registered) ctx->restricted = 1; - io_sq_offload_start(ctx); + ctx->flags &= ~IORING_SETUP_R_DISABLED; + if (ctx->sq_data && wq_has_sleeper(&ctx->sq_data->wait)) + wake_up(&ctx->sq_data->wait); + return 0; +} + +static int __io_register_rsrc_update(struct io_ring_ctx *ctx, unsigned type, + struct io_uring_rsrc_update2 *up, + unsigned nr_args) +{ + __u32 tmp; + int err; + + if (check_add_overflow(up->offset, nr_args, &tmp)) + return -EOVERFLOW; + err = io_rsrc_node_switch_start(ctx); + if (err) + return err; + + switch (type) { + case IORING_RSRC_FILE: + return __io_sqe_files_update(ctx, up, nr_args); + case IORING_RSRC_BUFFER: + return __io_sqe_buffers_update(ctx, up, nr_args); + } + return -EINVAL; +} + +static int io_register_files_update(struct io_ring_ctx *ctx, void __user *arg, + unsigned nr_args) +{ + struct io_uring_rsrc_update2 up; + + if (!nr_args) + return -EINVAL; + memset(&up, 0, sizeof(up)); + if (copy_from_user(&up, arg, sizeof(struct io_uring_rsrc_update))) + return -EFAULT; + if (up.resv || up.resv2) + return -EINVAL; + return __io_register_rsrc_update(ctx, IORING_RSRC_FILE, &up, nr_args); +} + +static int io_register_rsrc_update(struct io_ring_ctx *ctx, void __user *arg, + unsigned size, unsigned type) +{ + struct io_uring_rsrc_update2 up; + + if (size != sizeof(up)) + return -EINVAL; + if (copy_from_user(&up, arg, sizeof(up))) + return -EFAULT; + if (!up.nr || up.resv || up.resv2) + return -EINVAL; + return __io_register_rsrc_update(ctx, type, &up, up.nr); +} + +static int io_register_rsrc(struct io_ring_ctx *ctx, void __user *arg, + unsigned int size, unsigned int type) +{ + struct io_uring_rsrc_register rr; + + /* keep it extendible */ + if (size != sizeof(rr)) + return -EINVAL; + + memset(&rr, 0, sizeof(rr)); + if (copy_from_user(&rr, arg, size)) + return -EFAULT; + if (!rr.nr || rr.resv || rr.resv2) + return -EINVAL; + + switch (type) { + case IORING_RSRC_FILE: + return io_sqe_files_register(ctx, u64_to_user_ptr(rr.data), + rr.nr, u64_to_user_ptr(rr.tags)); + case IORING_RSRC_BUFFER: + return io_sqe_buffers_register(ctx, u64_to_user_ptr(rr.data), + rr.nr, u64_to_user_ptr(rr.tags)); + } + return -EINVAL; +} + +static int io_register_iowq_aff(struct io_ring_ctx *ctx, void __user *arg, + unsigned len) +{ + struct io_uring_task *tctx = current->io_uring; + cpumask_var_t new_mask; + int ret; + + if (!tctx || !tctx->io_wq) + return -EINVAL; + + if (!alloc_cpumask_var(&new_mask, GFP_KERNEL)) + return -ENOMEM; + + cpumask_clear(new_mask); + if (len > cpumask_size()) + len = cpumask_size(); + +#ifdef CONFIG_COMPAT + if (in_compat_syscall()) { + ret = compat_get_bitmap(cpumask_bits(new_mask), + (const compat_ulong_t __user *)arg, + len * 8 /* CHAR_BIT */); + } else { + ret = copy_from_user(new_mask, arg, len); + } +#else + ret = copy_from_user(new_mask, arg, len); +#endif + + if (ret) { + free_cpumask_var(new_mask); + return -EFAULT; + } + + ret = io_wq_cpu_affinity(tctx->io_wq, new_mask); + free_cpumask_var(new_mask); + return ret; +} + +static int io_unregister_iowq_aff(struct io_ring_ctx *ctx) +{ + struct io_uring_task *tctx = current->io_uring; + + if (!tctx || !tctx->io_wq) + return -EINVAL; + + return io_wq_cpu_affinity(tctx->io_wq, NULL); +} + +static int io_register_iowq_max_workers(struct io_ring_ctx *ctx, + void __user *arg) + __must_hold(&ctx->uring_lock) +{ + struct io_tctx_node *node; + struct io_uring_task *tctx = NULL; + struct io_sq_data *sqd = NULL; + __u32 new_count[2]; + int i, ret; + + if (copy_from_user(new_count, arg, sizeof(new_count))) + return -EFAULT; + for (i = 0; i < ARRAY_SIZE(new_count); i++) + if (new_count[i] > INT_MAX) + return -EINVAL; + + if (ctx->flags & IORING_SETUP_SQPOLL) { + sqd = ctx->sq_data; + if (sqd) { + /* + * Observe the correct sqd->lock -> ctx->uring_lock + * ordering. Fine to drop uring_lock here, we hold + * a ref to the ctx. + */ + refcount_inc(&sqd->refs); + mutex_unlock(&ctx->uring_lock); + mutex_lock(&sqd->lock); + mutex_lock(&ctx->uring_lock); + if (sqd->thread) + tctx = sqd->thread->io_uring; + } + } else { + tctx = current->io_uring; + } + + BUILD_BUG_ON(sizeof(new_count) != sizeof(ctx->iowq_limits)); + + for (i = 0; i < ARRAY_SIZE(new_count); i++) + if (new_count[i]) + ctx->iowq_limits[i] = new_count[i]; + ctx->iowq_limits_set = true; + + ret = -EINVAL; + if (tctx && tctx->io_wq) { + ret = io_wq_max_workers(tctx->io_wq, new_count); + if (ret) + goto err; + } else { + memset(new_count, 0, sizeof(new_count)); + } + + if (sqd) { + mutex_unlock(&sqd->lock); + io_put_sq_data(sqd); + } + + if (copy_to_user(arg, new_count, sizeof(new_count))) + return -EFAULT; + + /* that's it for SQPOLL, only the SQPOLL task creates requests */ + if (sqd) + return 0; + + /* now propagate the restriction to all registered users */ + list_for_each_entry(node, &ctx->tctx_list, ctx_node) { + struct io_uring_task *tctx = node->task->io_uring; + + if (WARN_ON_ONCE(!tctx->io_wq)) + continue; + + for (i = 0; i < ARRAY_SIZE(new_count); i++) + new_count[i] = ctx->iowq_limits[i]; + /* ignore errors, it always returns zero anyway */ + (void)io_wq_max_workers(tctx->io_wq, new_count); + } return 0; +err: + if (sqd) { + mutex_unlock(&sqd->lock); + io_put_sq_data(sqd); + } + return ret; } static bool io_register_op_must_quiesce(int op) { switch (op) { + case IORING_REGISTER_BUFFERS: + case IORING_UNREGISTER_BUFFERS: + case IORING_REGISTER_FILES: case IORING_UNREGISTER_FILES: case IORING_REGISTER_FILES_UPDATE: case IORING_REGISTER_PROBE: case IORING_REGISTER_PERSONALITY: case IORING_UNREGISTER_PERSONALITY: + case IORING_REGISTER_FILES2: + case IORING_REGISTER_FILES_UPDATE2: + case IORING_REGISTER_BUFFERS2: + case IORING_REGISTER_BUFFERS_UPDATE: + case IORING_REGISTER_IOWQ_AFF: + case IORING_UNREGISTER_IOWQ_AFF: + case IORING_REGISTER_IOWQ_MAX_WORKERS: return false; default: return true; } } +static int io_ctx_quiesce(struct io_ring_ctx *ctx) +{ + long ret; + + percpu_ref_kill(&ctx->refs); + + /* + * Drop uring mutex before waiting for references to exit. If another + * thread is currently inside io_uring_enter() it might need to grab the + * uring_lock to make progress. If we hold it here across the drain + * wait, then we can deadlock. It's safe to drop the mutex here, since + * no new references will come in after we've killed the percpu ref. + */ + mutex_unlock(&ctx->uring_lock); + do { + ret = wait_for_completion_interruptible(&ctx->ref_comp); + if (!ret) + break; + ret = io_run_task_work_sig(); + } while (ret >= 0); + mutex_lock(&ctx->uring_lock); + + if (ret) + io_refs_resurrect(&ctx->refs, &ctx->ref_comp); + return ret; +} + static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, void __user *arg, unsigned nr_args) __releases(ctx->uring_lock) @@ -9726,58 +10750,32 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, if (percpu_ref_is_dying(&ctx->refs)) return -ENXIO; - if (io_register_op_must_quiesce(opcode)) { - percpu_ref_kill(&ctx->refs); - - /* - * Drop uring mutex before waiting for references to exit. If - * another thread is currently inside io_uring_enter() it might - * need to grab the uring_lock to make progress. If we hold it - * here across the drain wait, then we can deadlock. It's safe - * to drop the mutex here, since no new references will come in - * after we've killed the percpu ref. - */ - mutex_unlock(&ctx->uring_lock); - do { - ret = wait_for_completion_interruptible(&ctx->ref_comp); - if (!ret) - break; - ret = io_run_task_work_sig(); - if (ret < 0) - break; - } while (1); - mutex_lock(&ctx->uring_lock); - - if (ret) { - io_refs_resurrect(&ctx->refs, &ctx->ref_comp); - return ret; - } - } - if (ctx->restricted) { - if (opcode >= IORING_REGISTER_LAST) { - ret = -EINVAL; - goto out; - } + if (opcode >= IORING_REGISTER_LAST) + return -EINVAL; + opcode = array_index_nospec(opcode, IORING_REGISTER_LAST); + if (!test_bit(opcode, ctx->restrictions.register_op)) + return -EACCES; + } - if (!test_bit(opcode, ctx->restrictions.register_op)) { - ret = -EACCES; - goto out; - } + if (io_register_op_must_quiesce(opcode)) { + ret = io_ctx_quiesce(ctx); + if (ret) + return ret; } switch (opcode) { case IORING_REGISTER_BUFFERS: - ret = io_sqe_buffer_register(ctx, arg, nr_args); + ret = io_sqe_buffers_register(ctx, arg, nr_args, NULL); break; case IORING_UNREGISTER_BUFFERS: ret = -EINVAL; if (arg || nr_args) break; - ret = io_sqe_buffer_unregister(ctx); + ret = io_sqe_buffers_unregister(ctx); break; case IORING_REGISTER_FILES: - ret = io_sqe_files_register(ctx, arg, nr_args); + ret = io_sqe_files_register(ctx, arg, nr_args, NULL); break; case IORING_UNREGISTER_FILES: ret = -EINVAL; @@ -9786,7 +10784,7 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, ret = io_sqe_files_unregister(ctx); break; case IORING_REGISTER_FILES_UPDATE: - ret = io_sqe_files_update(ctx, arg, nr_args); + ret = io_register_files_update(ctx, arg, nr_args); break; case IORING_REGISTER_EVENTFD: case IORING_REGISTER_EVENTFD_ASYNC: @@ -9834,12 +10832,43 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, case IORING_REGISTER_RESTRICTIONS: ret = io_register_restrictions(ctx, arg, nr_args); break; + case IORING_REGISTER_FILES2: + ret = io_register_rsrc(ctx, arg, nr_args, IORING_RSRC_FILE); + break; + case IORING_REGISTER_FILES_UPDATE2: + ret = io_register_rsrc_update(ctx, arg, nr_args, + IORING_RSRC_FILE); + break; + case IORING_REGISTER_BUFFERS2: + ret = io_register_rsrc(ctx, arg, nr_args, IORING_RSRC_BUFFER); + break; + case IORING_REGISTER_BUFFERS_UPDATE: + ret = io_register_rsrc_update(ctx, arg, nr_args, + IORING_RSRC_BUFFER); + break; + case IORING_REGISTER_IOWQ_AFF: + ret = -EINVAL; + if (!arg || !nr_args) + break; + ret = io_register_iowq_aff(ctx, arg, nr_args); + break; + case IORING_UNREGISTER_IOWQ_AFF: + ret = -EINVAL; + if (arg || nr_args) + break; + ret = io_unregister_iowq_aff(ctx); + break; + case IORING_REGISTER_IOWQ_MAX_WORKERS: + ret = -EINVAL; + if (!arg || nr_args != 2) + break; + ret = io_register_iowq_max_workers(ctx, arg); + break; default: ret = -EINVAL; break; } -out: if (io_register_op_must_quiesce(opcode)) { /* bring the ctx back to life */ percpu_ref_reinit(&ctx->refs); @@ -9865,6 +10894,8 @@ SYSCALL_DEFINE4(io_uring_register, unsigned int, fd, unsigned int, opcode, ctx = f.file->private_data; + io_run_task_work(); + mutex_lock(&ctx->uring_lock); ret = __io_uring_register(ctx, opcode, arg, nr_args); mutex_unlock(&ctx->uring_lock); @@ -9911,12 +10942,27 @@ static int __init io_uring_init(void) BUILD_BUG_SQE_ELEM(28, __u32, splice_flags); BUILD_BUG_SQE_ELEM(32, __u64, user_data); BUILD_BUG_SQE_ELEM(40, __u16, buf_index); + BUILD_BUG_SQE_ELEM(40, __u16, buf_group); BUILD_BUG_SQE_ELEM(42, __u16, personality); BUILD_BUG_SQE_ELEM(44, __s32, splice_fd_in); + BUILD_BUG_SQE_ELEM(44, __u32, file_index); + + BUILD_BUG_ON(sizeof(struct io_uring_files_update) != + sizeof(struct io_uring_rsrc_update)); + BUILD_BUG_ON(sizeof(struct io_uring_rsrc_update) > + sizeof(struct io_uring_rsrc_update2)); + + /* ->buf_index is u16 */ + BUILD_BUG_ON(IORING_MAX_REG_BUFFERS >= (1u << 16)); + + /* should fit into one byte */ + BUILD_BUG_ON(SQE_VALID_FLAGS >= (1 << 8)); BUILD_BUG_ON(ARRAY_SIZE(io_op_defs) != IORING_OP_LAST); - BUILD_BUG_ON(__REQ_F_LAST_BIT >= 8 * sizeof(int)); - req_cachep = KMEM_CACHE(io_kiocb, SLAB_HWCACHE_ALIGN | SLAB_PANIC); + BUILD_BUG_ON(__REQ_F_LAST_BIT > 8 * sizeof(int)); + + req_cachep = KMEM_CACHE(io_kiocb, SLAB_HWCACHE_ALIGN | SLAB_PANIC | + SLAB_ACCOUNT); return 0; }; __initcall(io_uring_init); diff --git a/ipc/msg.c b/ipc/msg.c index 6e6c8e0c9380e346efed7dbe7b88aad215560201..8ded6b8f10a2c5887a72d3dac8b13ccd819ed7af 100644 --- a/ipc/msg.c +++ b/ipc/msg.c @@ -147,7 +147,7 @@ static int newque(struct ipc_namespace *ns, struct ipc_params *params) key_t key = params->key; int msgflg = params->flg; - msq = kvmalloc(sizeof(*msq), GFP_KERNEL); + msq = kvmalloc(sizeof(*msq), GFP_KERNEL_ACCOUNT); if (unlikely(!msq)) return -ENOMEM; diff --git a/ipc/sem.c b/ipc/sem.c index 7d9c06b0ad6e24d3aee0cfdcc37c774f0b3fa82e..2cb6515ef1dd1b10a186cc61f013a94c5f0f29ef 100644 --- a/ipc/sem.c +++ b/ipc/sem.c @@ -511,7 +511,7 @@ static struct sem_array *sem_alloc(size_t nsems) if (nsems > (INT_MAX - sizeof(*sma)) / sizeof(sma->sems[0])) return NULL; - sma = kvzalloc(struct_size(sma, sems, nsems), GFP_KERNEL); + sma = kvzalloc(struct_size(sma, sems, nsems), GFP_KERNEL_ACCOUNT); if (unlikely(!sma)) return NULL; @@ -1852,7 +1852,7 @@ static inline int get_undo_list(struct sem_undo_list **undo_listp) undo_list = current->sysvsem.undo_list; if (!undo_list) { - undo_list = kzalloc(sizeof(*undo_list), GFP_KERNEL); + undo_list = kzalloc(sizeof(*undo_list), GFP_KERNEL_ACCOUNT); if (undo_list == NULL) return -ENOMEM; spin_lock_init(&undo_list->lock); @@ -1937,7 +1937,7 @@ static struct sem_undo *find_alloc_undo(struct ipc_namespace *ns, int semid) rcu_read_unlock(); /* step 2: allocate new undo structure */ - new = kzalloc(sizeof(struct sem_undo) + sizeof(short)*nsems, GFP_KERNEL); + new = kzalloc(sizeof(struct sem_undo) + sizeof(short)*nsems, GFP_KERNEL_ACCOUNT); if (!new) { ipc_rcu_putref(&sma->sem_perm, sem_rcu_free); return ERR_PTR(-ENOMEM); diff --git a/ipc/shm.c b/ipc/shm.c index 471ac3e7498d5359f151dd43f76d471924b76949..b418731d66e88e52f1825ddf0f4032b62c1afc9e 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -711,7 +711,7 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params) ns->shm_tot + numpages > ns->shm_ctlall) return -ENOSPC; - shp = kvmalloc(sizeof(*shp), GFP_KERNEL); + shp = kvmalloc(sizeof(*shp), GFP_KERNEL_ACCOUNT); if (unlikely(!shp)) return -ENOMEM; diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 6161973fffdd5ce05488007bb752fa792fd3eb30..351bb6c84f8b19424799097ce3fd9a90cf24b454 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -2914,7 +2914,7 @@ static int btf_struct_resolve(struct btf_verifier_env *env, if (v->next_member) { const struct btf_type *last_member_type; const struct btf_member *last_member; - u16 last_member_type_id; + u32 last_member_type_id; last_member = btf_type_member(v->t) + v->next_member - 1; last_member_type_id = last_member->type; diff --git a/kernel/bpf/percpu_freelist.c b/kernel/bpf/percpu_freelist.c index 3d897de8906121cfa95a1c34a0b8170f02fba4f8..bbab8bb4b2fdabde2725fa0676343a29255b9a79 100644 --- a/kernel/bpf/percpu_freelist.c +++ b/kernel/bpf/percpu_freelist.c @@ -102,22 +102,21 @@ void pcpu_freelist_populate(struct pcpu_freelist *s, void *buf, u32 elem_size, u32 nr_elems) { struct pcpu_freelist_head *head; - int i, cpu, pcpu_entries; + unsigned int cpu, cpu_idx, i, j, n, m; - pcpu_entries = nr_elems / num_possible_cpus() + 1; - i = 0; + n = nr_elems / num_possible_cpus(); + m = nr_elems % num_possible_cpus(); + cpu_idx = 0; for_each_possible_cpu(cpu) { -again: head = per_cpu_ptr(s->freelist, cpu); - /* No locking required as this is not visible yet. */ - pcpu_freelist_push_node(head, buf); - i++; - buf += elem_size; - if (i == nr_elems) - break; - if (i % pcpu_entries) - goto again; + j = n + (cpu_idx < m ? 1 : 0); + for (i = 0; i < j; i++) { + /* No locking required as this is not visible yet. */ + pcpu_freelist_push_node(head, buf); + buf += elem_size; + } + cpu_idx++; } } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index e4dcc23b52c014ba61a05c741712da5da0eeb712..50364031eb4d162204f3121b6eec59a29593c05b 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2978,7 +2978,9 @@ static int check_packet_access(struct bpf_verifier_env *env, u32 regno, int off, regno); return -EACCES; } - err = __check_mem_access(env, regno, off, size, reg->range, + + err = reg->range < 0 ? -EINVAL : + __check_mem_access(env, regno, off, size, reg->range, zero_size_allowed); if (err) { verbose(env, "R%d offset is outside of the packet\n", regno); @@ -4991,50 +4993,41 @@ static int check_func_proto(const struct bpf_func_proto *fn, int func_id) /* Packet data might have moved, any old PTR_TO_PACKET[_META,_END] * are now invalid, so turn them into unknown SCALAR_VALUE. */ -static void __clear_all_pkt_pointers(struct bpf_verifier_env *env, - struct bpf_func_state *state) +static void clear_all_pkt_pointers(struct bpf_verifier_env *env) { - struct bpf_reg_state *regs = state->regs, *reg; - int i; - - for (i = 0; i < MAX_BPF_REG; i++) - if (reg_is_pkt_pointer_any(®s[i])) - mark_reg_unknown(env, regs, i); + struct bpf_func_state *state; + struct bpf_reg_state *reg; - bpf_for_each_spilled_reg(i, state, reg) { - if (!reg) - continue; + bpf_for_each_reg_in_vstate(env->cur_state, state, reg, ({ if (reg_is_pkt_pointer_any(reg)) __mark_reg_unknown(env, reg); - } + })); } -static void clear_all_pkt_pointers(struct bpf_verifier_env *env) -{ - struct bpf_verifier_state *vstate = env->cur_state; - int i; - - for (i = 0; i <= vstate->curframe; i++) - __clear_all_pkt_pointers(env, vstate->frame[i]); -} +enum { + AT_PKT_END = -1, + BEYOND_PKT_END = -2, +}; -static void release_reg_references(struct bpf_verifier_env *env, - struct bpf_func_state *state, - int ref_obj_id) +static void mark_pkt_end(struct bpf_verifier_state *vstate, int regn, bool range_open) { - struct bpf_reg_state *regs = state->regs, *reg; - int i; + struct bpf_func_state *state = vstate->frame[vstate->curframe]; + struct bpf_reg_state *reg = &state->regs[regn]; - for (i = 0; i < MAX_BPF_REG; i++) - if (regs[i].ref_obj_id == ref_obj_id) - mark_reg_unknown(env, regs, i); + if (reg->type != PTR_TO_PACKET) + /* PTR_TO_PACKET_META is not supported yet */ + return; - bpf_for_each_spilled_reg(i, state, reg) { - if (!reg) - continue; - if (reg->ref_obj_id == ref_obj_id) - __mark_reg_unknown(env, reg); - } + /* The 'reg' is pkt > pkt_end or pkt >= pkt_end. + * How far beyond pkt_end it goes is unknown. + * if (!range_open) it's the case of pkt >= pkt_end + * if (range_open) it's the case of pkt > pkt_end + * hence this pointer is at least 1 byte bigger than pkt_end + */ + if (range_open) + reg->range = BEYOND_PKT_END; + else + reg->range = AT_PKT_END; } /* The pointer with the specified id has released its reference to kernel @@ -5043,16 +5036,22 @@ static void release_reg_references(struct bpf_verifier_env *env, static int release_reference(struct bpf_verifier_env *env, int ref_obj_id) { - struct bpf_verifier_state *vstate = env->cur_state; + struct bpf_func_state *state; + struct bpf_reg_state *reg; int err; - int i; err = release_reference_state(cur_func(env), ref_obj_id); if (err) return err; - for (i = 0; i <= vstate->curframe; i++) - release_reg_references(env, vstate->frame[i], ref_obj_id); + bpf_for_each_reg_in_vstate(env->cur_state, state, reg, ({ + if (reg->ref_obj_id == ref_obj_id) { + if (!env->allow_ptr_leaks) + __mark_reg_not_init(env, reg); + else + __mark_reg_unknown(env, reg); + } + })); return 0; } @@ -7191,35 +7190,14 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) return 0; } -static void __find_good_pkt_pointers(struct bpf_func_state *state, - struct bpf_reg_state *dst_reg, - enum bpf_reg_type type, u16 new_range) -{ - struct bpf_reg_state *reg; - int i; - - for (i = 0; i < MAX_BPF_REG; i++) { - reg = &state->regs[i]; - if (reg->type == type && reg->id == dst_reg->id) - /* keep the maximum range already checked */ - reg->range = max(reg->range, new_range); - } - - bpf_for_each_spilled_reg(i, state, reg) { - if (!reg) - continue; - if (reg->type == type && reg->id == dst_reg->id) - reg->range = max(reg->range, new_range); - } -} - static void find_good_pkt_pointers(struct bpf_verifier_state *vstate, struct bpf_reg_state *dst_reg, enum bpf_reg_type type, bool range_right_open) { - u16 new_range; - int i; + struct bpf_func_state *state; + struct bpf_reg_state *reg; + int new_range; if (dst_reg->off < 0 || (dst_reg->off == 0 && range_right_open)) @@ -7284,9 +7262,11 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *vstate, * the range won't allow anything. * dst_reg->off is known < MAX_PACKET_OFF, therefore it fits in a u16. */ - for (i = 0; i <= vstate->curframe; i++) - __find_good_pkt_pointers(vstate->frame[i], dst_reg, type, - new_range); + bpf_for_each_reg_in_vstate(vstate, state, reg, ({ + if (reg->type == type && reg->id == dst_reg->id) + /* keep the maximum range already checked */ + reg->range = max(reg->range, new_range); + })); } static int is_branch32_taken(struct bpf_reg_state *reg, u32 val, u8 opcode) @@ -7470,6 +7450,67 @@ static int is_branch_taken(struct bpf_reg_state *reg, u64 val, u8 opcode, return is_branch64_taken(reg, val, opcode); } +static int flip_opcode(u32 opcode) +{ + /* How can we transform "a b" into "b a"? */ + static const u8 opcode_flip[16] = { + /* these stay the same */ + [BPF_JEQ >> 4] = BPF_JEQ, + [BPF_JNE >> 4] = BPF_JNE, + [BPF_JSET >> 4] = BPF_JSET, + /* these swap "lesser" and "greater" (L and G in the opcodes) */ + [BPF_JGE >> 4] = BPF_JLE, + [BPF_JGT >> 4] = BPF_JLT, + [BPF_JLE >> 4] = BPF_JGE, + [BPF_JLT >> 4] = BPF_JGT, + [BPF_JSGE >> 4] = BPF_JSLE, + [BPF_JSGT >> 4] = BPF_JSLT, + [BPF_JSLE >> 4] = BPF_JSGE, + [BPF_JSLT >> 4] = BPF_JSGT + }; + return opcode_flip[opcode >> 4]; +} + +static int is_pkt_ptr_branch_taken(struct bpf_reg_state *dst_reg, + struct bpf_reg_state *src_reg, + u8 opcode) +{ + struct bpf_reg_state *pkt; + + if (src_reg->type == PTR_TO_PACKET_END) { + pkt = dst_reg; + } else if (dst_reg->type == PTR_TO_PACKET_END) { + pkt = src_reg; + opcode = flip_opcode(opcode); + } else { + return -1; + } + + if (pkt->range >= 0) + return -1; + + switch (opcode) { + case BPF_JLE: + /* pkt <= pkt_end */ + fallthrough; + case BPF_JGT: + /* pkt > pkt_end */ + if (pkt->range == BEYOND_PKT_END) + /* pkt has at last one extra byte beyond pkt_end */ + return opcode == BPF_JGT; + break; + case BPF_JLT: + /* pkt < pkt_end */ + fallthrough; + case BPF_JGE: + /* pkt >= pkt_end */ + if (pkt->range == BEYOND_PKT_END || pkt->range == AT_PKT_END) + return opcode == BPF_JGE; + break; + } + return -1; +} + /* Adjusts the register min/max values in the case that the dst_reg is the * variable register that we are working on, and src_reg is a constant or we're * simply doing a BPF_K check. @@ -7640,23 +7681,7 @@ static void reg_set_min_max_inv(struct bpf_reg_state *true_reg, u64 val, u32 val32, u8 opcode, bool is_jmp32) { - /* How can we transform "a b" into "b a"? */ - static const u8 opcode_flip[16] = { - /* these stay the same */ - [BPF_JEQ >> 4] = BPF_JEQ, - [BPF_JNE >> 4] = BPF_JNE, - [BPF_JSET >> 4] = BPF_JSET, - /* these swap "lesser" and "greater" (L and G in the opcodes) */ - [BPF_JGE >> 4] = BPF_JLE, - [BPF_JGT >> 4] = BPF_JLT, - [BPF_JLE >> 4] = BPF_JGE, - [BPF_JLT >> 4] = BPF_JGT, - [BPF_JSGE >> 4] = BPF_JSLE, - [BPF_JSGT >> 4] = BPF_JSLT, - [BPF_JSLE >> 4] = BPF_JSGE, - [BPF_JSLT >> 4] = BPF_JSGT - }; - opcode = opcode_flip[opcode >> 4]; + opcode = flip_opcode(opcode); /* This uses zero as "not present in table"; luckily the zero opcode, * BPF_JA, can't get here. */ @@ -7754,7 +7779,7 @@ static void mark_ptr_or_null_reg(struct bpf_func_state *state, reg->ref_obj_id = 0; } else if (!reg_may_point_to_spin_lock(reg)) { /* For not-NULL ptr, reg->ref_obj_id will be reset - * in release_reg_references(). + * in release_reference(). * * reg->id is still used by spin_lock ptr. Other * than spin_lock ptr type, reg->id can be reset. @@ -7764,22 +7789,6 @@ static void mark_ptr_or_null_reg(struct bpf_func_state *state, } } -static void __mark_ptr_or_null_regs(struct bpf_func_state *state, u32 id, - bool is_null) -{ - struct bpf_reg_state *reg; - int i; - - for (i = 0; i < MAX_BPF_REG; i++) - mark_ptr_or_null_reg(state, &state->regs[i], id, is_null); - - bpf_for_each_spilled_reg(i, state, reg) { - if (!reg) - continue; - mark_ptr_or_null_reg(state, reg, id, is_null); - } -} - /* The logic is similar to find_good_pkt_pointers(), both could eventually * be folded together at some point. */ @@ -7787,10 +7796,9 @@ static void mark_ptr_or_null_regs(struct bpf_verifier_state *vstate, u32 regno, bool is_null) { struct bpf_func_state *state = vstate->frame[vstate->curframe]; - struct bpf_reg_state *regs = state->regs; + struct bpf_reg_state *regs = state->regs, *reg; u32 ref_obj_id = regs[regno].ref_obj_id; u32 id = regs[regno].id; - int i; if (ref_obj_id && ref_obj_id == id && is_null) /* regs[regno] is in the " == NULL" branch. @@ -7799,8 +7807,9 @@ static void mark_ptr_or_null_regs(struct bpf_verifier_state *vstate, u32 regno, */ WARN_ON_ONCE(release_reference_state(state, id)); - for (i = 0; i <= vstate->curframe; i++) - __mark_ptr_or_null_regs(vstate->frame[i], id, is_null); + bpf_for_each_reg_in_vstate(vstate, state, reg, ({ + mark_ptr_or_null_reg(state, reg, id, is_null); + })); } static bool try_match_pkt_pointers(const struct bpf_insn *insn, @@ -7825,6 +7834,7 @@ static bool try_match_pkt_pointers(const struct bpf_insn *insn, /* pkt_data' > pkt_end, pkt_meta' > pkt_data */ find_good_pkt_pointers(this_branch, dst_reg, dst_reg->type, false); + mark_pkt_end(other_branch, insn->dst_reg, true); } else if ((dst_reg->type == PTR_TO_PACKET_END && src_reg->type == PTR_TO_PACKET) || (reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) && @@ -7832,6 +7842,7 @@ static bool try_match_pkt_pointers(const struct bpf_insn *insn, /* pkt_end > pkt_data', pkt_data > pkt_meta' */ find_good_pkt_pointers(other_branch, src_reg, src_reg->type, true); + mark_pkt_end(this_branch, insn->src_reg, false); } else { return false; } @@ -7844,6 +7855,7 @@ static bool try_match_pkt_pointers(const struct bpf_insn *insn, /* pkt_data' < pkt_end, pkt_meta' < pkt_data */ find_good_pkt_pointers(other_branch, dst_reg, dst_reg->type, true); + mark_pkt_end(this_branch, insn->dst_reg, false); } else if ((dst_reg->type == PTR_TO_PACKET_END && src_reg->type == PTR_TO_PACKET) || (reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) && @@ -7851,6 +7863,7 @@ static bool try_match_pkt_pointers(const struct bpf_insn *insn, /* pkt_end < pkt_data', pkt_data > pkt_meta' */ find_good_pkt_pointers(this_branch, src_reg, src_reg->type, false); + mark_pkt_end(other_branch, insn->src_reg, true); } else { return false; } @@ -7863,6 +7876,7 @@ static bool try_match_pkt_pointers(const struct bpf_insn *insn, /* pkt_data' >= pkt_end, pkt_meta' >= pkt_data */ find_good_pkt_pointers(this_branch, dst_reg, dst_reg->type, true); + mark_pkt_end(other_branch, insn->dst_reg, false); } else if ((dst_reg->type == PTR_TO_PACKET_END && src_reg->type == PTR_TO_PACKET) || (reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) && @@ -7870,6 +7884,7 @@ static bool try_match_pkt_pointers(const struct bpf_insn *insn, /* pkt_end >= pkt_data', pkt_data >= pkt_meta' */ find_good_pkt_pointers(other_branch, src_reg, src_reg->type, false); + mark_pkt_end(this_branch, insn->src_reg, true); } else { return false; } @@ -7882,6 +7897,7 @@ static bool try_match_pkt_pointers(const struct bpf_insn *insn, /* pkt_data' <= pkt_end, pkt_meta' <= pkt_data */ find_good_pkt_pointers(other_branch, dst_reg, dst_reg->type, false); + mark_pkt_end(this_branch, insn->dst_reg, true); } else if ((dst_reg->type == PTR_TO_PACKET_END && src_reg->type == PTR_TO_PACKET) || (reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) && @@ -7889,6 +7905,7 @@ static bool try_match_pkt_pointers(const struct bpf_insn *insn, /* pkt_end <= pkt_data', pkt_data <= pkt_meta' */ find_good_pkt_pointers(this_branch, src_reg, src_reg->type, true); + mark_pkt_end(other_branch, insn->src_reg, false); } else { return false; } @@ -7905,23 +7922,11 @@ static void find_equal_scalars(struct bpf_verifier_state *vstate, { struct bpf_func_state *state; struct bpf_reg_state *reg; - int i, j; - - for (i = 0; i <= vstate->curframe; i++) { - state = vstate->frame[i]; - for (j = 0; j < MAX_BPF_REG; j++) { - reg = &state->regs[j]; - if (reg->type == SCALAR_VALUE && reg->id == known_reg->id) - *reg = *known_reg; - } - bpf_for_each_spilled_reg(j, state, reg) { - if (!reg) - continue; - if (reg->type == SCALAR_VALUE && reg->id == known_reg->id) - *reg = *known_reg; - } - } + bpf_for_each_reg_in_vstate(vstate, state, reg, ({ + if (reg->type == SCALAR_VALUE && reg->id == known_reg->id) + *reg = *known_reg; + })); } static int check_cond_jmp_op(struct bpf_verifier_env *env, @@ -7988,6 +7993,10 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, src_reg->var_off.value, opcode, is_jmp32); + } else if (reg_is_pkt_pointer_any(dst_reg) && + reg_is_pkt_pointer_any(src_reg) && + !is_jmp32) { + pred = is_pkt_ptr_branch_taken(dst_reg, src_reg, opcode); } if (pred >= 0) { @@ -7996,7 +8005,8 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, */ if (!__is_pointer_value(false, dst_reg)) err = mark_chain_precision(env, insn->dst_reg); - if (BPF_SRC(insn->code) == BPF_X && !err) + if (BPF_SRC(insn->code) == BPF_X && !err && + !__is_pointer_value(false, src_reg)) err = mark_chain_precision(env, insn->src_reg); if (err) return err; diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 40dabc1d93beb3a2097f0edc7657ca885883283e..a0af4c99cae9fe8374ca55a2f74c3d45916278df 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -33,6 +33,7 @@ #include #include #include +#include #include #include #include @@ -1089,10 +1090,18 @@ static void update_tasks_cpumask(struct cpuset *cs) { struct css_task_iter it; struct task_struct *task; + bool top_cs = cs == &top_cpuset; css_task_iter_start(&cs->css, 0, &it); - while ((task = css_task_iter_next(&it))) + while ((task = css_task_iter_next(&it))) { + /* + * Percpu kthreads in top_cpuset are ignored + */ + if (top_cs && (task->flags & PF_KTHREAD) && + kthread_is_per_cpu(task)) + continue; update_cpus_allowed(cs, task, cs->effective_cpus); + } css_task_iter_end(&it); } @@ -2048,12 +2057,7 @@ static int update_prstate(struct cpuset *cs, int new_prs) update_flag(CS_CPU_EXCLUSIVE, cs, 0); } - /* - * Update cpumask of parent's tasks except when it is the top - * cpuset as some system daemons cannot be mapped to other CPUs. - */ - if (parent != &top_cpuset) - update_tasks_cpumask(parent); + update_tasks_cpumask(parent); if (parent->child_ecpus_count) update_sibling_cpumasks(parent, cs, &tmpmask); diff --git a/kernel/cpu.c b/kernel/cpu.c index 01866de556790ccd65f7c99f37b60642a241c6a4..92b350b272f445ae678be2f95ad6388ffc7761bf 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -1161,7 +1161,7 @@ int remove_cpu(unsigned int cpu) } EXPORT_SYMBOL_GPL(remove_cpu); -extern bool dl_cpu_busy(unsigned int cpu); +extern int dl_cpu_busy(int cpu, struct task_struct *p); int __pause_drain_rq(struct cpumask *cpus) { @@ -1210,7 +1210,7 @@ int pause_cpus(struct cpumask *cpus) cpumask_and(cpus, cpus, cpu_active_mask); for_each_cpu(cpu, cpus) { - if (!cpu_online(cpu) || dl_cpu_busy(cpu) || + if (!cpu_online(cpu) || dl_cpu_busy(cpu, NULL) || get_cpu_device(cpu)->offline_disabled == true) { err = -EBUSY; goto err_cpu_maps_update; diff --git a/kernel/entry/common.c b/kernel/entry/common.c index e289e6773292649c4e684087fb3113cd60ffed40..09f58853f6927b54f0231dc36b7e6df71df766d4 100644 --- a/kernel/entry/common.c +++ b/kernel/entry/common.c @@ -135,7 +135,15 @@ static __always_inline void exit_to_user_mode(void) } /* Workaround to allow gradual conversion of architecture code */ -void __weak arch_do_signal(struct pt_regs *regs) { } +void __weak arch_do_signal_or_restart(struct pt_regs *regs, bool has_signal) { } + +static void handle_signal_work(struct pt_regs *regs, unsigned long ti_work) +{ + if (ti_work & _TIF_NOTIFY_SIGNAL) + tracehook_notify_signal(); + + arch_do_signal_or_restart(regs, ti_work & _TIF_SIGPENDING); +} static unsigned long exit_to_user_mode_loop(struct pt_regs *regs, unsigned long ti_work) @@ -157,8 +165,8 @@ static unsigned long exit_to_user_mode_loop(struct pt_regs *regs, if (ti_work & _TIF_PATCH_PENDING) klp_update_patch_state(current); - if (ti_work & _TIF_SIGPENDING) - arch_do_signal(regs); + if (ti_work & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL)) + handle_signal_work(regs, ti_work); if (ti_work & _TIF_NOTIFY_RESUME) { tracehook_notify_resume(regs); diff --git a/kernel/entry/kvm.c b/kernel/entry/kvm.c index 2a3139dab109e7ef1546a104dfa3bd9ce4b18686..7b946847be7839af639f9aba6d8d264fb7df7c48 100644 --- a/kernel/entry/kvm.c +++ b/kernel/entry/kvm.c @@ -8,7 +8,7 @@ static int xfer_to_guest_mode_work(struct kvm_vcpu *vcpu, unsigned long ti_work) do { int ret; - if (ti_work & _TIF_SIGPENDING) { + if (ti_work & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL)) { kvm_handle_signal_exit(vcpu); return -EINTR; } diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index e1bbb3b92921d8eb084d2844cd2ae85ebaf5e14f..826a2355da1ed13cee9a14433c83c79afb13b6cb 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -1973,7 +1973,7 @@ bool uprobe_deny_signal(void) WARN_ON_ONCE(utask->state != UTASK_SSTEP); - if (signal_pending(t)) { + if (task_sigpending(t)) { spin_lock_irq(&t->sighand->siglock); clear_tsk_thread_flag(t, TIF_SIGPENDING); spin_unlock_irq(&t->sighand->siglock); diff --git a/kernel/exit.c b/kernel/exit.c index a821bb14d8d835b02b772efffcedfed2092ec1e8..318a27b42e4310a396846360edc3bd8716ad5d0e 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -766,7 +766,7 @@ void __noreturn do_exit(long code) schedule(); } - io_uring_files_cancel(tsk->files); + io_uring_files_cancel(); exit_signals(tsk); /* sets PF_EXITING */ /* sync mm's RSS info before statistics gathering */ diff --git a/kernel/fork.c b/kernel/fork.c index 26ee6f8c26175e6d451c467a1895bf6dc8421cd5..0e22f899124cab292c3b9ca43714ec04bdacb34b 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -967,6 +967,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node) tsk->splice_pipe = NULL; tsk->task_frag.page = NULL; tsk->wake_q.next = NULL; + tsk->pf_io_worker = NULL; account_kernel_stack(tsk, 1); @@ -1997,13 +1998,21 @@ static __latent_entropy struct task_struct *copy_process( recalc_sigpending(); spin_unlock_irq(¤t->sighand->siglock); retval = -ERESTARTNOINTR; - if (signal_pending(current)) + if (task_sigpending(current)) goto fork_out; retval = -ENOMEM; p = dup_task_struct(current, node); if (!p) goto fork_out; + if (args->io_thread) { + /* + * Mark us an IO worker, and block any signal that isn't + * fatal or STOP + */ + p->flags |= PF_IO_WORKER; + siginitsetinv(&p->blocked, sigmask(SIGKILL)|sigmask(SIGSTOP)); + } cpufreq_task_times_init(p); @@ -2483,6 +2492,28 @@ struct mm_struct *copy_init_mm(void) return dup_mm(NULL, &init_mm); } +/* + * This is like kernel_clone(), but shaved down and tailored to just + * creating io_uring workers. It returns a created task, or an error pointer. + * The returned task is inactive, and the caller must fire it up through + * wake_up_new_task(p). All signals are blocked in the created task. + */ +struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node) +{ + unsigned long flags = CLONE_FS|CLONE_FILES|CLONE_SIGHAND|CLONE_THREAD| + CLONE_IO; + struct kernel_clone_args args = { + .flags = ((lower_32_bits(flags) | CLONE_VM | + CLONE_UNTRACED) & ~CSIGNAL), + .exit_signal = (lower_32_bits(flags) & CSIGNAL), + .stack = (unsigned long)fn, + .stack_size = (unsigned long)arg, + .io_thread = 1, + }; + + return copy_process(NULL, 0, node, &args); +} + /* * Ok, this is the main fork-routine. * diff --git a/kernel/gcov/clang.c b/kernel/gcov/clang.c index c466c7fbdece557de01f448b4584bd563fa2ee09..ea6b45d0fa0d636d337e662d6833fd81e296b81d 100644 --- a/kernel/gcov/clang.c +++ b/kernel/gcov/clang.c @@ -327,6 +327,8 @@ void gcov_info_add(struct gcov_info *dst, struct gcov_info *src) for (i = 0; i < sfn_ptr->num_counters; i++) dfn_ptr->counters[i] += sfn_ptr->counters[i]; + + sfn_ptr = list_next_entry(sfn_ptr, head); } } diff --git a/kernel/gcov/gcc_4_7.c b/kernel/gcov/gcc_4_7.c index 53c67c87f141bb483e1baa7a20546dac9c997263..c699feda21ac0c213cdeb86c59aa898dbd12d591 100644 --- a/kernel/gcov/gcc_4_7.c +++ b/kernel/gcov/gcc_4_7.c @@ -33,6 +33,13 @@ #define GCOV_TAG_FUNCTION_LENGTH 3 +/* Since GCC 12.1 sizes are in BYTES and not in WORDS (4B). */ +#if (__GNUC__ >= 12) +#define GCOV_UNIT_SIZE 4 +#else +#define GCOV_UNIT_SIZE 1 +#endif + static struct gcov_info *gcov_info_head; /** @@ -451,12 +458,18 @@ static size_t convert_to_gcda(char *buffer, struct gcov_info *info) pos += store_gcov_u32(buffer, pos, info->version); pos += store_gcov_u32(buffer, pos, info->stamp); +#if (__GNUC__ >= 12) + /* Use zero as checksum of the compilation unit. */ + pos += store_gcov_u32(buffer, pos, 0); +#endif + for (fi_idx = 0; fi_idx < info->n_functions; fi_idx++) { fi_ptr = info->functions[fi_idx]; /* Function record. */ pos += store_gcov_u32(buffer, pos, GCOV_TAG_FUNCTION); - pos += store_gcov_u32(buffer, pos, GCOV_TAG_FUNCTION_LENGTH); + pos += store_gcov_u32(buffer, pos, + GCOV_TAG_FUNCTION_LENGTH * GCOV_UNIT_SIZE); pos += store_gcov_u32(buffer, pos, fi_ptr->ident); pos += store_gcov_u32(buffer, pos, fi_ptr->lineno_checksum); pos += store_gcov_u32(buffer, pos, fi_ptr->cfg_checksum); @@ -470,7 +483,8 @@ static size_t convert_to_gcda(char *buffer, struct gcov_info *info) /* Counter record. */ pos += store_gcov_u32(buffer, pos, GCOV_TAG_FOR_COUNTER(ct_idx)); - pos += store_gcov_u32(buffer, pos, ci_ptr->num * 2); + pos += store_gcov_u32(buffer, pos, + ci_ptr->num * 2 * GCOV_UNIT_SIZE); for (cv_idx = 0; cv_idx < ci_ptr->num; cv_idx++) { pos += store_gcov_u64(buffer, pos, diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 0440741201b6a241b395605e44ea5cabed53e505..d2eb3b6ec7cdad95eb87ba8f2badf73b9054cd3f 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -223,11 +223,16 @@ int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask, { struct irq_desc *desc = irq_data_to_desc(data); struct irq_chip *chip = irq_data_get_irq_chip(data); + const struct cpumask *prog_mask; int ret; + static DEFINE_RAW_SPINLOCK(tmp_mask_lock); + static struct cpumask tmp_mask; + if (!chip || !chip->irq_set_affinity) return -EINVAL; + raw_spin_lock(&tmp_mask_lock); /* * If this is a managed interrupt and housekeeping is enabled on * it check whether the requested affinity mask intersects with @@ -249,24 +254,34 @@ int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask, */ if (irqd_affinity_is_managed(data) && housekeeping_enabled(HK_FLAG_MANAGED_IRQ)) { - const struct cpumask *hk_mask, *prog_mask; - - static DEFINE_RAW_SPINLOCK(tmp_mask_lock); - static struct cpumask tmp_mask; + const struct cpumask *hk_mask; hk_mask = housekeeping_cpumask(HK_FLAG_MANAGED_IRQ); - raw_spin_lock(&tmp_mask_lock); cpumask_and(&tmp_mask, mask, hk_mask); if (!cpumask_intersects(&tmp_mask, cpu_online_mask)) prog_mask = mask; else prog_mask = &tmp_mask; - ret = chip->irq_set_affinity(data, prog_mask, force); - raw_spin_unlock(&tmp_mask_lock); } else { - ret = chip->irq_set_affinity(data, mask, force); + prog_mask = mask; } + + /* + * Make sure we only provide online CPUs to the irqchip, + * unless we are being asked to force the affinity (in which + * case we do as we are told). + */ + cpumask_and(&tmp_mask, prog_mask, cpu_online_mask); + if (!force && !cpumask_empty(&tmp_mask)) + ret = chip->irq_set_affinity(data, &tmp_mask, force); + else if (force) + ret = chip->irq_set_affinity(data, mask, force); + else + ret = -EINVAL; + + raw_spin_unlock(&tmp_mask_lock); + switch (ret) { case IRQ_SET_MASK_OK: case IRQ_SET_MASK_OK_DONE: diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index d217acc9f71b6a615e5add7d1dbaa876eb180371..b47d95b68ac1a460a562bdc523c1c0417d30a82f 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -456,6 +456,13 @@ int __msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, irqd_clr_can_reserve(irq_data); if (domain->flags & IRQ_DOMAIN_MSI_NOMASK_QUIRK) irqd_set_msi_nomask_quirk(irq_data); + if ((info->flags & MSI_FLAG_ACTIVATE_EARLY) && + irqd_affinity_is_managed(irq_data) && + !cpumask_intersects(irq_data_get_affinity_mask(irq_data), + cpu_online_mask)) { + irqd_set_managed_shutdown(irq_data); + continue; + } } ret = irq_domain_activate_irq(irq_data, can_reserve); if (ret) diff --git a/kernel/kprobes.c b/kernel/kprobes.c index dac82a0e7c0b0383ccd8d8d42b0fbd07e94bec27..75150e75551809c24d8734e1e606c82cf0b9ab32 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1841,7 +1841,13 @@ static int __unregister_kprobe_top(struct kprobe *p) if ((list_p != p) && (list_p->post_handler)) goto noclean; } - ap->post_handler = NULL; + /* + * For the kprobe-on-ftrace case, we keep the + * post_handler setting to identify this aggrprobe + * armed with kprobe_ipmodify_ops. + */ + if (!kprobe_ftrace(ap)) + ap->post_handler = NULL; } noclean: /* @@ -2335,8 +2341,11 @@ int enable_kprobe(struct kprobe *kp) if (!kprobes_all_disarmed && kprobe_disabled(p)) { p->flags &= ~KPROBE_FLAG_DISABLED; ret = arm_kprobe(p); - if (ret) + if (ret) { p->flags |= KPROBE_FLAG_DISABLED; + if (p != kp) + kp->flags |= KPROBE_FLAG_DISABLED; + } } out: mutex_unlock(&kprobe_mutex); diff --git a/kernel/livepatch/transition.c b/kernel/livepatch/transition.c index f6310f848f3426833a277db469e0d05957450c86..b04b87a4e0a7b6e441db4c49ef15c0821f6b7eb6 100644 --- a/kernel/livepatch/transition.c +++ b/kernel/livepatch/transition.c @@ -611,9 +611,23 @@ void klp_reverse_transition(void) /* Called from copy_process() during fork */ void klp_copy_process(struct task_struct *child) { - child->patch_state = current->patch_state; - /* TIF_PATCH_PENDING gets copied in setup_thread_stack() */ + /* + * The parent process may have gone through a KLP transition since + * the thread flag was copied in setup_thread_stack earlier. Bring + * the task flag up to date with the parent here. + * + * The operation is serialized against all klp_*_transition() + * operations by the tasklist_lock. The only exception is + * klp_update_patch_state(current), but we cannot race with + * that because we are current. + */ + if (test_tsk_thread_flag(current, TIF_PATCH_PENDING)) + set_tsk_thread_flag(child, TIF_PATCH_PENDING); + else + clear_tsk_thread_flag(child, TIF_PATCH_PENDING); + + child->patch_state = current->patch_state; } /* diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index 731aca37637dc3949308e47dcc9d817e89b88583..b6875ebd184d86a6039ae2acf63537987640c129 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -637,7 +637,7 @@ static void power_down(void) int error; if (hibernation_mode == HIBERNATION_SUSPEND) { - error = suspend_devices_and_enter(PM_SUSPEND_MEM); + error = suspend_devices_and_enter(mem_sleep_current); if (error) { hibernation_mode = hibernation_ops ? HIBERNATION_PLATFORM : diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h index 14af29fe137704f92c62230473745cf22549b6c9..8b51e6a5b3869dcd63860d4b61e54267b21febae 100644 --- a/kernel/rcu/tasks.h +++ b/kernel/rcu/tasks.h @@ -171,7 +171,7 @@ static void call_rcu_tasks_generic(struct rcu_head *rhp, rcu_callback_t func, static void synchronize_rcu_tasks_generic(struct rcu_tasks *rtp) { /* Complain if the scheduler has not started. */ - RCU_LOCKDEP_WARN(rcu_scheduler_active == RCU_SCHEDULER_INACTIVE, + WARN_ONCE(rcu_scheduler_active == RCU_SCHEDULER_INACTIVE, "synchronize_rcu_tasks called too soon"); /* Wait for the grace period. */ diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 0daec314b941ba9563af456a43c5c78c3db02871..6df3c15555d7cf65572bd03f13a6cd36a442b4a9 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -3393,15 +3393,16 @@ static void fill_page_cache_func(struct work_struct *work) bnode = (struct kvfree_rcu_bulk_data *) __get_free_page(GFP_KERNEL | __GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN); - if (bnode) { - raw_spin_lock_irqsave(&krcp->lock, flags); - pushed = put_cached_bnode(krcp, bnode); - raw_spin_unlock_irqrestore(&krcp->lock, flags); + if (!bnode) + break; - if (!pushed) { - free_page((unsigned long) bnode); - break; - } + raw_spin_lock_irqsave(&krcp->lock, flags); + pushed = put_cached_bnode(krcp, bnode); + raw_spin_unlock_irqrestore(&krcp->lock, flags); + + if (!pushed) { + free_page((unsigned long) bnode); + break; } } diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 0f1c19a38cb32235915201ac39b7d868362f3b33..e9cb8f0470b781e95d92cb6ec05510d095a124e4 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -21,7 +21,7 @@ #include #include "../workqueue_internal.h" -#include "../../fs/io-wq.h" +#include "../../io_uring/io-wq.h" #include "../smpboot.h" #include "pelt.h" diff --git a/kernel/signal.c b/kernel/signal.c index 17c8e49c1116a38fb8b7a6671eba44f8195e2f79..bf5717acf11cc26aee506458358a5bf60d3e5eec 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -987,7 +987,7 @@ static inline bool wants_signal(int sig, struct task_struct *p) if (task_is_stopped_or_traced(p)) return false; - return task_curr(p) || !signal_pending(p); + return task_curr(p) || !task_sigpending(p); } static void complete_signal(int sig, struct task_struct *p, enum pid_type type) @@ -2551,6 +2551,21 @@ bool get_signal(struct ksignal *ksig) struct signal_struct *signal = current->signal; int signr; + if (unlikely(current->task_works)) + task_work_run(); + + /* + * For non-generic architectures, check for TIF_NOTIFY_SIGNAL so + * that the arch handlers don't all have to do it. If we get here + * without TIF_SIGPENDING, just exit after running signal work. + */ + if (!IS_ENABLED(CONFIG_GENERIC_ENTRY)) { + if (test_thread_flag(TIF_NOTIFY_SIGNAL)) + tracehook_notify_signal(); + if (!task_sigpending(current)) + return false; + } + if (unlikely(uprobe_deny_signal())) return false; @@ -2563,26 +2578,6 @@ bool get_signal(struct ksignal *ksig) relock: spin_lock_irq(&sighand->siglock); - /* - * Make sure we can safely read ->jobctl() in task_work add. As Oleg - * states: - * - * It pairs with mb (implied by cmpxchg) before READ_ONCE. So we - * roughly have - * - * task_work_add: get_signal: - * STORE(task->task_works, new_work); STORE(task->jobctl); - * mb(); mb(); - * LOAD(task->jobctl); LOAD(task->task_works); - * - * and we can rely on STORE-MB-LOAD [ in task_work_add]. - */ - smp_store_mb(current->jobctl, current->jobctl & ~JOBCTL_TASK_WORK); - if (unlikely(current->task_works)) { - spin_unlock_irq(&sighand->siglock); - task_work_run(); - goto relock; - } /* * Every stopped thread goes here after wakeup. Check to see if @@ -2773,6 +2768,14 @@ relock: do_coredump(&ksig->info); } + /* + * PF_IO_WORKER threads will catch and exit on fatal signals + * themselves. They have cleanup that must be performed, so + * we cannot call do_exit() on their behalf. + */ + if (current->flags & PF_IO_WORKER) + goto out; + /* * Death signals, no core dump. */ @@ -2780,7 +2783,7 @@ relock: /* NOTREACHED */ } spin_unlock_irq(&sighand->siglock); - +out: ksig->sig = signr; if (!(ksig->ka.sa.sa_flags & SA_EXPOSE_TAGBITS)) @@ -2848,7 +2851,7 @@ static void retarget_shared_pending(struct task_struct *tsk, sigset_t *which) /* Remove the signals this thread can handle. */ sigandsets(&retarget, &retarget, &t->blocked); - if (!signal_pending(t)) + if (!task_sigpending(t)) signal_wake_up(t, 0); if (sigisemptyset(&retarget)) @@ -2882,7 +2885,7 @@ void exit_signals(struct task_struct *tsk) cgroup_threadgroup_change_end(tsk); - if (!signal_pending(tsk)) + if (!task_sigpending(tsk)) goto out; unblocked = tsk->blocked; @@ -2926,7 +2929,7 @@ long do_no_restart_syscall(struct restart_block *param) static void __set_task_blocked(struct task_struct *tsk, const sigset_t *newset) { - if (signal_pending(tsk) && !thread_group_empty(tsk)) { + if (task_sigpending(tsk) && !thread_group_empty(tsk)) { sigset_t newblocked; /* A set of now blocked but previously unblocked signals. */ sigandnsets(&newblocked, newset, ¤t->blocked); diff --git a/kernel/task_work.c b/kernel/task_work.c index e3a8e5c66ae53117a78caebceea1ce36837ccfb1..1698fbe6f0e134ac2a2ab3e9357b44af99c71f83 100644 --- a/kernel/task_work.c +++ b/kernel/task_work.c @@ -33,7 +33,6 @@ int task_work_add(struct task_struct *task, struct callback_head *work, enum task_work_notify_mode notify) { struct callback_head *head; - unsigned long flags; /* record the work call stack in order to print it in KASAN reports */ kasan_record_aux_stack(work); @@ -52,17 +51,7 @@ int task_work_add(struct task_struct *task, struct callback_head *work, set_notify_resume(task); break; case TWA_SIGNAL: - /* - * Only grab the sighand lock if we don't already have some - * task_work pending. This pairs with the smp_store_mb() - * in get_signal(), see comment there. - */ - if (!(READ_ONCE(task->jobctl) & JOBCTL_TASK_WORK) && - lock_task_sighand(task, &flags)) { - task->jobctl |= JOBCTL_TASK_WORK; - signal_wake_up(task, 0); - unlock_task_sighand(task, &flags); - } + set_notify_signal(task); break; default: WARN_ON_ONCE(1); @@ -73,18 +62,17 @@ int task_work_add(struct task_struct *task, struct callback_head *work, } /** - * task_work_cancel - cancel a pending work added by task_work_add() + * task_work_cancel_match - cancel a pending work added by task_work_add() * @task: the task which should execute the work - * @func: identifies the work to remove - * - * Find the last queued pending work with ->func == @func and remove - * it from queue. + * @match: match function to call * * RETURNS: * The found work or NULL if not found. */ struct callback_head * -task_work_cancel(struct task_struct *task, task_work_func_t func) +task_work_cancel_match(struct task_struct *task, + bool (*match)(struct callback_head *, void *data), + void *data) { struct callback_head **pprev = &task->task_works; struct callback_head *work; @@ -100,7 +88,7 @@ task_work_cancel(struct task_struct *task, task_work_func_t func) */ raw_spin_lock_irqsave(&task->pi_lock, flags); while ((work = READ_ONCE(*pprev))) { - if (work->func != func) + if (!match(work, data)) pprev = &work->next; else if (cmpxchg(pprev, work, work->next) == work) break; @@ -110,6 +98,28 @@ task_work_cancel(struct task_struct *task, task_work_func_t func) return work; } +static bool task_work_func_match(struct callback_head *cb, void *data) +{ + return cb->func == data; +} + +/** + * task_work_cancel - cancel a pending work added by task_work_add() + * @task: the task which should execute the work + * @func: identifies the work to remove + * + * Find the last queued pending work with ->func == @func and remove + * it from queue. + * + * RETURNS: + * The found work or NULL if not found. + */ +struct callback_head * +task_work_cancel(struct task_struct *task, task_work_func_t func) +{ + return task_work_cancel_match(task, task_work_func_match, func); +} + /** * task_work_run - execute the works added by task_work_add() * diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index d868df6f13c863d69cfeb5f7ccff60989e364544..d97c189695cbbe7436faca32a9e8ff919af704a6 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1295,6 +1295,7 @@ static int ftrace_add_mod(struct trace_array *tr, if (!ftrace_mod) return -ENOMEM; + INIT_LIST_HEAD(&ftrace_mod->list); ftrace_mod->func = kstrdup(func, GFP_KERNEL); ftrace_mod->module = kstrdup(module, GFP_KERNEL); ftrace_mod->enable = enable; @@ -2946,18 +2947,8 @@ int ftrace_shutdown(struct ftrace_ops *ops, int command) command |= FTRACE_UPDATE_TRACE_FUNC; } - if (!command || !ftrace_enabled) { - /* - * If these are dynamic or per_cpu ops, they still - * need their data freed. Since, function tracing is - * not currently active, we can just free them - * without synchronizing all CPUs. - */ - if (ops->flags & FTRACE_OPS_FL_DYNAMIC) - goto free_ops; - - return 0; - } + if (!command || !ftrace_enabled) + goto out; /* * If the ops uses a trampoline, then it needs to be @@ -2994,6 +2985,7 @@ int ftrace_shutdown(struct ftrace_ops *ops, int command) removed_ops = NULL; ops->flags &= ~FTRACE_OPS_FL_REMOVING; +out: /* * Dynamic ops may be freed, we must make sure that all * callers are done before leaving this function. @@ -3021,7 +3013,6 @@ int ftrace_shutdown(struct ftrace_ops *ops, int command) if (IS_ENABLED(CONFIG_PREEMPTION)) synchronize_rcu_tasks(); - free_ops: ftrace_trampoline_free(ops); } @@ -3188,7 +3179,7 @@ static int ftrace_allocate_records(struct ftrace_page *pg, int count) /* if we can't allocate this size, try something smaller */ if (!order) return -ENOMEM; - order >>= 1; + order--; goto again; } @@ -5662,8 +5653,12 @@ int ftrace_regex_release(struct inode *inode, struct file *file) if (filter_hash) { orig_hash = &iter->ops->func_hash->filter_hash; - if (iter->tr && !list_empty(&iter->tr->mod_trace)) - iter->hash->flags |= FTRACE_HASH_FL_MOD; + if (iter->tr) { + if (list_empty(&iter->tr->mod_trace)) + iter->hash->flags &= ~FTRACE_HASH_FL_MOD; + else + iter->hash->flags |= FTRACE_HASH_FL_MOD; + } } else orig_hash = &iter->ops->func_hash->notrace_hash; @@ -6883,7 +6878,7 @@ void __init ftrace_init(void) } pr_info("ftrace: allocating %ld entries in %ld pages\n", - count, count / ENTRIES_PER_PAGE + 1); + count, DIV_ROUND_UP(count, ENTRIES_PER_PAGE)); last_ftrace_enabled = ftrace_enabled = 1; diff --git a/kernel/trace/kprobe_event_gen_test.c b/kernel/trace/kprobe_event_gen_test.c index 18b0f1cbb947f05fc3add1744c25737970a215b3..c736487fc0e48ab40ef4113185a071ef7b167f6d 100644 --- a/kernel/trace/kprobe_event_gen_test.c +++ b/kernel/trace/kprobe_event_gen_test.c @@ -35,6 +35,49 @@ static struct trace_event_file *gen_kprobe_test; static struct trace_event_file *gen_kretprobe_test; +#define KPROBE_GEN_TEST_FUNC "do_sys_open" + +/* X86 */ +#if defined(CONFIG_X86_64) || defined(CONFIG_X86_32) +#define KPROBE_GEN_TEST_ARG0 "dfd=%ax" +#define KPROBE_GEN_TEST_ARG1 "filename=%dx" +#define KPROBE_GEN_TEST_ARG2 "flags=%cx" +#define KPROBE_GEN_TEST_ARG3 "mode=+4($stack)" + +/* ARM64 */ +#elif defined(CONFIG_ARM64) +#define KPROBE_GEN_TEST_ARG0 "dfd=%x0" +#define KPROBE_GEN_TEST_ARG1 "filename=%x1" +#define KPROBE_GEN_TEST_ARG2 "flags=%x2" +#define KPROBE_GEN_TEST_ARG3 "mode=%x3" + +/* ARM */ +#elif defined(CONFIG_ARM) +#define KPROBE_GEN_TEST_ARG0 "dfd=%r0" +#define KPROBE_GEN_TEST_ARG1 "filename=%r1" +#define KPROBE_GEN_TEST_ARG2 "flags=%r2" +#define KPROBE_GEN_TEST_ARG3 "mode=%r3" + +/* RISCV */ +#elif defined(CONFIG_RISCV) +#define KPROBE_GEN_TEST_ARG0 "dfd=%a0" +#define KPROBE_GEN_TEST_ARG1 "filename=%a1" +#define KPROBE_GEN_TEST_ARG2 "flags=%a2" +#define KPROBE_GEN_TEST_ARG3 "mode=%a3" + +/* others */ +#else +#define KPROBE_GEN_TEST_ARG0 NULL +#define KPROBE_GEN_TEST_ARG1 NULL +#define KPROBE_GEN_TEST_ARG2 NULL +#define KPROBE_GEN_TEST_ARG3 NULL +#endif + +static bool trace_event_file_is_valid(struct trace_event_file *input) +{ + return input && !IS_ERR(input); +} + /* * Test to make sure we can create a kprobe event, then add more * fields. @@ -58,23 +101,23 @@ static int __init test_gen_kprobe_cmd(void) * fields. */ ret = kprobe_event_gen_cmd_start(&cmd, "gen_kprobe_test", - "do_sys_open", - "dfd=%ax", "filename=%dx"); + KPROBE_GEN_TEST_FUNC, + KPROBE_GEN_TEST_ARG0, KPROBE_GEN_TEST_ARG1); if (ret) - goto free; + goto out; /* Use kprobe_event_add_fields to add the rest of the fields */ - ret = kprobe_event_add_fields(&cmd, "flags=%cx", "mode=+4($stack)"); + ret = kprobe_event_add_fields(&cmd, KPROBE_GEN_TEST_ARG2, KPROBE_GEN_TEST_ARG3); if (ret) - goto free; + goto out; /* * This actually creates the event. */ ret = kprobe_event_gen_cmd_end(&cmd); if (ret) - goto free; + goto out; /* * Now get the gen_kprobe_test event file. We need to prevent @@ -97,13 +140,13 @@ static int __init test_gen_kprobe_cmd(void) goto delete; } out: + kfree(buf); return ret; delete: + if (trace_event_file_is_valid(gen_kprobe_test)) + gen_kprobe_test = NULL; /* We got an error after creating the event, delete it */ ret = kprobe_event_delete("gen_kprobe_test"); - free: - kfree(buf); - goto out; } @@ -128,17 +171,17 @@ static int __init test_gen_kretprobe_cmd(void) * Define the kretprobe event. */ ret = kretprobe_event_gen_cmd_start(&cmd, "gen_kretprobe_test", - "do_sys_open", + KPROBE_GEN_TEST_FUNC, "$retval"); if (ret) - goto free; + goto out; /* * This actually creates the event. */ ret = kretprobe_event_gen_cmd_end(&cmd); if (ret) - goto free; + goto out; /* * Now get the gen_kretprobe_test event file. We need to @@ -162,13 +205,13 @@ static int __init test_gen_kretprobe_cmd(void) goto delete; } out: + kfree(buf); return ret; delete: + if (trace_event_file_is_valid(gen_kretprobe_test)) + gen_kretprobe_test = NULL; /* We got an error after creating the event, delete it */ ret = kprobe_event_delete("gen_kretprobe_test"); - free: - kfree(buf); - goto out; } @@ -182,10 +225,12 @@ static int __init kprobe_event_gen_test_init(void) ret = test_gen_kretprobe_cmd(); if (ret) { - WARN_ON(trace_array_set_clr_event(gen_kretprobe_test->tr, - "kprobes", - "gen_kretprobe_test", false)); - trace_put_event_file(gen_kretprobe_test); + if (trace_event_file_is_valid(gen_kretprobe_test)) { + WARN_ON(trace_array_set_clr_event(gen_kretprobe_test->tr, + "kprobes", + "gen_kretprobe_test", false)); + trace_put_event_file(gen_kretprobe_test); + } WARN_ON(kprobe_event_delete("gen_kretprobe_test")); } @@ -194,24 +239,30 @@ static int __init kprobe_event_gen_test_init(void) static void __exit kprobe_event_gen_test_exit(void) { - /* Disable the event or you can't remove it */ - WARN_ON(trace_array_set_clr_event(gen_kprobe_test->tr, - "kprobes", - "gen_kprobe_test", false)); + if (trace_event_file_is_valid(gen_kprobe_test)) { + /* Disable the event or you can't remove it */ + WARN_ON(trace_array_set_clr_event(gen_kprobe_test->tr, + "kprobes", + "gen_kprobe_test", false)); + + /* Now give the file and instance back */ + trace_put_event_file(gen_kprobe_test); + } - /* Now give the file and instance back */ - trace_put_event_file(gen_kprobe_test); /* Now unregister and free the event */ WARN_ON(kprobe_event_delete("gen_kprobe_test")); - /* Disable the event or you can't remove it */ - WARN_ON(trace_array_set_clr_event(gen_kprobe_test->tr, - "kprobes", - "gen_kretprobe_test", false)); + if (trace_event_file_is_valid(gen_kretprobe_test)) { + /* Disable the event or you can't remove it */ + WARN_ON(trace_array_set_clr_event(gen_kretprobe_test->tr, + "kprobes", + "gen_kretprobe_test", false)); + + /* Now give the file and instance back */ + trace_put_event_file(gen_kretprobe_test); + } - /* Now give the file and instance back */ - trace_put_event_file(gen_kretprobe_test); /* Now unregister and free the event */ WARN_ON(kprobe_event_delete("gen_kretprobe_test")); diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 6deac666ba3e4dab5efdd750d052edcf8b2bfbaa..49ebb8c6626828d8d3fd91f7124b9ea06d9821ff 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -414,6 +414,7 @@ struct rb_irq_work { struct irq_work work; wait_queue_head_t waiters; wait_queue_head_t full_waiters; + long wait_index; bool waiters_pending; bool full_waiters_pending; bool wakeup_full; @@ -516,6 +517,7 @@ struct ring_buffer_per_cpu { local_t committing; local_t commits; local_t pages_touched; + local_t pages_lost; local_t pages_read; long last_pages_touch; size_t shortest_full; @@ -770,10 +772,18 @@ size_t ring_buffer_nr_pages(struct trace_buffer *buffer, int cpu) size_t ring_buffer_nr_dirty_pages(struct trace_buffer *buffer, int cpu) { size_t read; + size_t lost; size_t cnt; read = local_read(&buffer->buffers[cpu]->pages_read); + lost = local_read(&buffer->buffers[cpu]->pages_lost); cnt = local_read(&buffer->buffers[cpu]->pages_touched); + + if (WARN_ON_ONCE(cnt < lost)) + return 0; + + cnt -= lost; + /* The reader can read an empty page, but not more than that */ if (cnt < read) { WARN_ON_ONCE(read > cnt + 1); @@ -783,6 +793,21 @@ size_t ring_buffer_nr_dirty_pages(struct trace_buffer *buffer, int cpu) return cnt - read; } +static __always_inline bool full_hit(struct trace_buffer *buffer, int cpu, int full) +{ + struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu]; + size_t nr_pages; + size_t dirty; + + nr_pages = cpu_buffer->nr_pages; + if (!nr_pages || !full) + return true; + + dirty = ring_buffer_nr_dirty_pages(buffer, cpu); + + return (dirty * 100) > (full * nr_pages); +} + /* * rb_wake_up_waiters - wake up tasks waiting for ring buffer input * @@ -794,12 +819,44 @@ static void rb_wake_up_waiters(struct irq_work *work) struct rb_irq_work *rbwork = container_of(work, struct rb_irq_work, work); wake_up_all(&rbwork->waiters); - if (rbwork->wakeup_full) { + if (rbwork->full_waiters_pending || rbwork->wakeup_full) { rbwork->wakeup_full = false; + rbwork->full_waiters_pending = false; wake_up_all(&rbwork->full_waiters); } } +/** + * ring_buffer_wake_waiters - wake up any waiters on this ring buffer + * @buffer: The ring buffer to wake waiters on + * + * In the case of a file that represents a ring buffer is closing, + * it is prudent to wake up any waiters that are on this. + */ +void ring_buffer_wake_waiters(struct trace_buffer *buffer, int cpu) +{ + struct ring_buffer_per_cpu *cpu_buffer; + struct rb_irq_work *rbwork; + + if (cpu == RING_BUFFER_ALL_CPUS) { + + /* Wake up individual ones too. One level recursion */ + for_each_buffer_cpu(buffer, cpu) + ring_buffer_wake_waiters(buffer, cpu); + + rbwork = &buffer->irq_work; + } else { + cpu_buffer = buffer->buffers[cpu]; + rbwork = &cpu_buffer->irq_work; + } + + rbwork->wait_index++; + /* make sure the waiters see the new index */ + smp_wmb(); + + rb_wake_up_waiters(&rbwork->work); +} + /** * ring_buffer_wait - wait for input to the ring buffer * @buffer: buffer to wait on @@ -815,6 +872,7 @@ int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full) struct ring_buffer_per_cpu *cpu_buffer; DEFINE_WAIT(wait); struct rb_irq_work *work; + long wait_index; int ret = 0; /* @@ -833,6 +891,7 @@ int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full) work = &cpu_buffer->irq_work; } + wait_index = READ_ONCE(work->wait_index); while (true) { if (full) @@ -877,26 +936,29 @@ int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full) !ring_buffer_empty_cpu(buffer, cpu)) { unsigned long flags; bool pagebusy; - size_t nr_pages; - size_t dirty; + bool done; if (!full) break; raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); pagebusy = cpu_buffer->reader_page == cpu_buffer->commit_page; - nr_pages = cpu_buffer->nr_pages; - dirty = ring_buffer_nr_dirty_pages(buffer, cpu); + done = !pagebusy && full_hit(buffer, cpu, full); + if (!cpu_buffer->shortest_full || - cpu_buffer->shortest_full < full) + cpu_buffer->shortest_full > full) cpu_buffer->shortest_full = full; raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); - if (!pagebusy && - (!nr_pages || (dirty * 100) > full * nr_pages)) + if (done) break; } schedule(); + + /* Make sure to see the new wait index */ + smp_rmb(); + if (wait_index != work->wait_index) + break; } if (full) @@ -913,6 +975,7 @@ int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full) * @cpu: the cpu buffer to wait on * @filp: the file descriptor * @poll_table: The poll descriptor + * @full: wait until the percentage of pages are available, if @cpu != RING_BUFFER_ALL_CPUS * * If @cpu == RING_BUFFER_ALL_CPUS then the task will wake up as soon * as data is added to any of the @buffer's cpu buffers. Otherwise @@ -922,14 +985,15 @@ int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full) * zero otherwise. */ __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu, - struct file *filp, poll_table *poll_table) + struct file *filp, poll_table *poll_table, int full) { struct ring_buffer_per_cpu *cpu_buffer; struct rb_irq_work *work; - if (cpu == RING_BUFFER_ALL_CPUS) + if (cpu == RING_BUFFER_ALL_CPUS) { work = &buffer->irq_work; - else { + full = 0; + } else { if (!cpumask_test_cpu(cpu, buffer->cpumask)) return -EINVAL; @@ -937,8 +1001,14 @@ __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu, work = &cpu_buffer->irq_work; } - poll_wait(filp, &work->waiters, poll_table); - work->waiters_pending = true; + if (full) { + poll_wait(filp, &work->full_waiters, poll_table); + work->full_waiters_pending = true; + } else { + poll_wait(filp, &work->waiters, poll_table); + work->waiters_pending = true; + } + /* * There's a tight race between setting the waiters_pending and * checking if the ring buffer is empty. Once the waiters_pending bit @@ -954,6 +1024,9 @@ __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu, */ smp_mb(); + if (full) + return full_hit(buffer, cpu, full) ? EPOLLIN | EPOLLRDNORM : 0; + if ((cpu == RING_BUFFER_ALL_CPUS && !ring_buffer_empty(buffer)) || (cpu != RING_BUFFER_ALL_CPUS && !ring_buffer_empty_cpu(buffer, cpu))) return EPOLLIN | EPOLLRDNORM; @@ -1595,9 +1668,9 @@ static void rb_free_cpu_buffer(struct ring_buffer_per_cpu *cpu_buffer) free_buffer_page(cpu_buffer->reader_page); - rb_head_page_deactivate(cpu_buffer); - if (head) { + rb_head_page_deactivate(cpu_buffer); + list_for_each_entry_safe(bpage, tmp, head, list) { list_del_init(&bpage->list); free_buffer_page(bpage); @@ -1833,6 +1906,7 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned long nr_pages) */ local_add(page_entries, &cpu_buffer->overrun); local_sub(BUF_PAGE_SIZE, &cpu_buffer->entries_bytes); + local_inc(&cpu_buffer->pages_lost); } /* @@ -2323,6 +2397,7 @@ rb_handle_head_page(struct ring_buffer_per_cpu *cpu_buffer, */ local_add(entries, &cpu_buffer->overrun); local_sub(BUF_PAGE_SIZE, &cpu_buffer->entries_bytes); + local_inc(&cpu_buffer->pages_lost); /* * The entries will be zeroed out when we move the @@ -2491,6 +2566,9 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer, /* Mark the rest of the page with padding */ rb_event_set_padding(event); + /* Make sure the padding is visible before the write update */ + smp_wmb(); + /* Set the write back to the previous setting */ local_sub(length, &tail_page->write); return; @@ -2502,6 +2580,9 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer, /* time delta must be non zero */ event->time_delta = 1; + /* Make sure the padding is visible before the tail_page->write update */ + smp_wmb(); + /* Set write to end of buffer */ length = (tail + length) - BUF_PAGE_SIZE; local_sub(length, &tail_page->write); @@ -2987,10 +3068,6 @@ static void rb_commit(struct ring_buffer_per_cpu *cpu_buffer, static __always_inline void rb_wakeups(struct trace_buffer *buffer, struct ring_buffer_per_cpu *cpu_buffer) { - size_t nr_pages; - size_t dirty; - size_t full; - if (buffer->irq_work.waiters_pending) { buffer->irq_work.waiters_pending = false; /* irq_work_queue() supplies it's own memory barriers */ @@ -3014,10 +3091,7 @@ rb_wakeups(struct trace_buffer *buffer, struct ring_buffer_per_cpu *cpu_buffer) cpu_buffer->last_pages_touch = local_read(&cpu_buffer->pages_touched); - full = cpu_buffer->shortest_full; - nr_pages = cpu_buffer->nr_pages; - dirty = ring_buffer_nr_dirty_pages(buffer, cpu_buffer->cpu); - if (full && nr_pages && (dirty * 100) <= full * nr_pages) + if (!full_hit(buffer, cpu_buffer->cpu, cpu_buffer->shortest_full)) return; cpu_buffer->irq_work.wakeup_full = true; @@ -4316,6 +4390,33 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer) arch_spin_unlock(&cpu_buffer->lock); local_irq_restore(flags); + /* + * The writer has preempt disable, wait for it. But not forever + * Although, 1 second is pretty much "forever" + */ +#define USECS_WAIT 1000000 + for (nr_loops = 0; nr_loops < USECS_WAIT; nr_loops++) { + /* If the write is past the end of page, a writer is still updating it */ + if (likely(!reader || rb_page_write(reader) <= BUF_PAGE_SIZE)) + break; + + udelay(1); + + /* Get the latest version of the reader write value */ + smp_rmb(); + } + + /* The writer is not moving forward? Something is wrong */ + if (RB_WARN_ON(cpu_buffer, nr_loops == USECS_WAIT)) + reader = NULL; + + /* + * Make sure we see any padding after the write update + * (see rb_reset_tail()) + */ + smp_rmb(); + + return reader; } @@ -4891,6 +4992,7 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer) local_set(&cpu_buffer->committing, 0); local_set(&cpu_buffer->commits, 0); local_set(&cpu_buffer->pages_touched, 0); + local_set(&cpu_buffer->pages_lost, 0); local_set(&cpu_buffer->pages_read, 0); cpu_buffer->last_pages_touch = 0; cpu_buffer->shortest_full = 0; @@ -5341,7 +5443,15 @@ int ring_buffer_read_page(struct trace_buffer *buffer, unsigned int pos = 0; unsigned int size; - if (full) + /* + * If a full page is expected, this can still be returned + * if there's been a previous partial read and the + * rest of the page can be read and the commit page is off + * the reader page. + */ + if (full && + (!read || (len < (commit - read)) || + cpu_buffer->reader_page == cpu_buffer->commit_page)) goto out_unlock; if (len > (commit - read)) diff --git a/kernel/trace/synth_event_gen_test.c b/kernel/trace/synth_event_gen_test.c index edd912cd14aaf8ba41b656f5fcf4fa472e5dcec9..a6a2813afb87f1f8937028723f3a961b4e4387fc 100644 --- a/kernel/trace/synth_event_gen_test.c +++ b/kernel/trace/synth_event_gen_test.c @@ -120,15 +120,13 @@ static int __init test_gen_synth_cmd(void) /* Now generate a gen_synth_test event */ ret = synth_event_trace_array(gen_synth_test, vals, ARRAY_SIZE(vals)); - out: + free: + kfree(buf); return ret; delete: /* We got an error after creating the event, delete it */ synth_event_delete("gen_synth_test"); - free: - kfree(buf); - - goto out; + goto free; } /* @@ -227,15 +225,13 @@ static int __init test_empty_synth_event(void) /* Now trace an empty_synth_test event */ ret = synth_event_trace_array(empty_synth_test, vals, ARRAY_SIZE(vals)); - out: + free: + kfree(buf); return ret; delete: /* We got an error after creating the event, delete it */ synth_event_delete("empty_synth_test"); - free: - kfree(buf); - - goto out; + goto free; } static struct synth_field_desc create_synth_test_fields[] = { diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 4344e95ee7ab9c1281de050e5365bd411bbbdaca..1ce8caf9d292fcf3ece8977afdeab7d8b2ba04ea 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1198,12 +1198,14 @@ void *tracing_cond_snapshot_data(struct trace_array *tr) { void *cond_data = NULL; + local_irq_disable(); arch_spin_lock(&tr->max_lock); if (tr->cond_snapshot) cond_data = tr->cond_snapshot->cond_data; arch_spin_unlock(&tr->max_lock); + local_irq_enable(); return cond_data; } @@ -1339,9 +1341,11 @@ int tracing_snapshot_cond_enable(struct trace_array *tr, void *cond_data, goto fail_unlock; } + local_irq_disable(); arch_spin_lock(&tr->max_lock); tr->cond_snapshot = cond_snapshot; arch_spin_unlock(&tr->max_lock); + local_irq_enable(); mutex_unlock(&trace_types_lock); @@ -1368,6 +1372,7 @@ int tracing_snapshot_cond_disable(struct trace_array *tr) { int ret = 0; + local_irq_disable(); arch_spin_lock(&tr->max_lock); if (!tr->cond_snapshot) @@ -1378,6 +1383,7 @@ int tracing_snapshot_cond_disable(struct trace_array *tr) } arch_spin_unlock(&tr->max_lock); + local_irq_enable(); return ret; } @@ -2199,6 +2205,11 @@ static size_t tgid_map_max; #define SAVED_CMDLINES_DEFAULT 128 #define NO_CMDLINE_MAP UINT_MAX +/* + * Preemption must be disabled before acquiring trace_cmdline_lock. + * The various trace_arrays' max_lock must be acquired in a context + * where interrupt is disabled. + */ static arch_spinlock_t trace_cmdline_lock = __ARCH_SPIN_LOCK_UNLOCKED; struct saved_cmdlines_buffer { unsigned map_pid_to_cmdline[PID_MAX_DEFAULT+1]; @@ -2411,7 +2422,11 @@ static int trace_save_cmdline(struct task_struct *tsk) * the lock, but we also don't want to spin * nor do we want to disable interrupts, * so if we miss here, then better luck next time. + * + * This is called within the scheduler and wake up, so interrupts + * had better been disabled and run queue lock been held. */ + lockdep_assert_preemption_disabled(); if (!arch_spin_trylock(&trace_cmdline_lock)) return 0; @@ -5482,9 +5497,11 @@ tracing_saved_cmdlines_size_read(struct file *filp, char __user *ubuf, char buf[64]; int r; + preempt_disable(); arch_spin_lock(&trace_cmdline_lock); r = scnprintf(buf, sizeof(buf), "%u\n", savedcmd->cmdline_num); arch_spin_unlock(&trace_cmdline_lock); + preempt_enable(); return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); } @@ -5509,10 +5526,12 @@ static int tracing_resize_saved_cmdlines(unsigned int val) return -ENOMEM; } + preempt_disable(); arch_spin_lock(&trace_cmdline_lock); savedcmd_temp = savedcmd; savedcmd = s; arch_spin_unlock(&trace_cmdline_lock); + preempt_enable(); free_saved_cmdlines_buffer(savedcmd_temp); return 0; @@ -5965,10 +5984,12 @@ int tracing_set_tracer(struct trace_array *tr, const char *buf) #ifdef CONFIG_TRACER_SNAPSHOT if (t->use_max_tr) { + local_irq_disable(); arch_spin_lock(&tr->max_lock); if (tr->cond_snapshot) ret = -EBUSY; arch_spin_unlock(&tr->max_lock); + local_irq_enable(); if (ret) goto out; } @@ -5999,12 +6020,12 @@ int tracing_set_tracer(struct trace_array *tr, const char *buf) if (tr->current_trace->reset) tr->current_trace->reset(tr); +#ifdef CONFIG_TRACER_MAX_TRACE + had_max_tr = tr->current_trace->use_max_tr; + /* Current trace needs to be nop_trace before synchronize_rcu */ tr->current_trace = &nop_trace; -#ifdef CONFIG_TRACER_MAX_TRACE - had_max_tr = tr->allocated_snapshot; - if (had_max_tr && !t->use_max_tr) { /* * We need to make sure that the update_max_tr sees that @@ -6016,14 +6037,14 @@ int tracing_set_tracer(struct trace_array *tr, const char *buf) synchronize_rcu(); free_snapshot(tr); } -#endif -#ifdef CONFIG_TRACER_MAX_TRACE - if (t->use_max_tr && !had_max_tr) { + if (t->use_max_tr && !tr->allocated_snapshot) { ret = tracing_alloc_snapshot_instance(tr); if (ret < 0) goto out; } +#else + tr->current_trace = &nop_trace; #endif if (t->init) { @@ -6254,7 +6275,7 @@ trace_poll(struct trace_iterator *iter, struct file *filp, poll_table *poll_tabl return EPOLLIN | EPOLLRDNORM; else return ring_buffer_poll_wait(iter->array_buffer->buffer, iter->cpu_file, - filp, poll_table); + filp, poll_table, iter->tr->buffer_percent); } static __poll_t @@ -7042,10 +7063,12 @@ tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt, goto out; } + local_irq_disable(); arch_spin_lock(&tr->max_lock); if (tr->cond_snapshot) ret = -EBUSY; arch_spin_unlock(&tr->max_lock); + local_irq_enable(); if (ret) goto out; diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c index 881df991742ab18c3f38fbf86886e4ef5a6fec62..18291ab35657031af567f96af84af8d6fb770335 100644 --- a/kernel/trace/trace_events_synth.c +++ b/kernel/trace/trace_events_synth.c @@ -791,10 +791,9 @@ static int register_synth_event(struct synth_event *event) } ret = set_synth_event_print_fmt(call); - if (ret < 0) { + /* unregister_trace_event() will be called inside */ + if (ret < 0) trace_remove_event_call(call); - goto err; - } out: return ret; err: diff --git a/lib/dynamic_debug.c b/lib/dynamic_debug.c index 921d0a654243ce7c58d5288f25a78fd3ba781cf7..10a50c03074ee14b7ed73b7bb8612c340a51d942 100644 --- a/lib/dynamic_debug.c +++ b/lib/dynamic_debug.c @@ -207,10 +207,11 @@ static int ddebug_change(const struct ddebug_query *query, continue; #ifdef CONFIG_JUMP_LABEL if (dp->flags & _DPRINTK_FLAGS_PRINT) { - if (!(modifiers->flags & _DPRINTK_FLAGS_PRINT)) + if (!(newflags & _DPRINTK_FLAGS_PRINT)) static_branch_disable(&dp->key.dd_key_true); - } else if (modifiers->flags & _DPRINTK_FLAGS_PRINT) + } else if (newflags & _DPRINTK_FLAGS_PRINT) { static_branch_enable(&dp->key.dd_key_true); + } #endif dp->flags = newflags; v2pr_info("changed %s:%d [%s]%s =%s\n", @@ -379,10 +380,6 @@ static int ddebug_parse_query(char *words[], int nwords, return -EINVAL; } - if (modname) - /* support $modname.dyndbg= */ - query->module = modname; - for (i = 0; i < nwords; i += 2) { char *keyword = words[i]; char *arg = words[i+1]; @@ -423,6 +420,13 @@ static int ddebug_parse_query(char *words[], int nwords, if (rc) return rc; } + if (!query->module && modname) + /* + * support $modname.dyndbg=, when + * not given in the query itself + */ + query->module = modname; + vpr_info_dq(query, "parsed"); return 0; } @@ -548,35 +552,6 @@ static int ddebug_exec_queries(char *query, const char *modname) return nfound; } -/** - * dynamic_debug_exec_queries - select and change dynamic-debug prints - * @query: query-string described in admin-guide/dynamic-debug-howto - * @modname: string containing module name, usually &module.mod_name - * - * This uses the >/proc/dynamic_debug/control reader, allowing module - * authors to modify their dynamic-debug callsites. The modname is - * canonically struct module.mod_name, but can also be null or a - * module-wildcard, for example: "drm*". - */ -int dynamic_debug_exec_queries(const char *query, const char *modname) -{ - int rc; - char *qry; /* writable copy of query */ - - if (!query) { - pr_err("non-null query/command string expected\n"); - return -EINVAL; - } - qry = kstrndup(query, PAGE_SIZE, GFP_KERNEL); - if (!qry) - return -ENOMEM; - - rc = ddebug_exec_queries(qry, modname); - kfree(qry); - return rc; -} -EXPORT_SYMBOL_GPL(dynamic_debug_exec_queries); - #define PREFIX_SIZE 64 static int remaining(int wrote) diff --git a/lib/iov_iter.c b/lib/iov_iter.c index 1b0a349fbcd926b4e49e48728c545395e0ae6bf5..650554964f181cc87260fab256e030f988bbf7e3 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -1836,24 +1836,38 @@ int import_single_range(int rw, void __user *buf, size_t len, } EXPORT_SYMBOL(import_single_range); -int iov_iter_for_each_range(struct iov_iter *i, size_t bytes, - int (*f)(struct kvec *vec, void *context), - void *context) +/** + * iov_iter_restore() - Restore a &struct iov_iter to the same state as when + * iov_iter_save_state() was called. + * + * @i: &struct iov_iter to restore + * @state: state to restore from + * + * Used after iov_iter_save_state() to bring restore @i, if operations may + * have advanced it. + * + * Note: only works on ITER_IOVEC, ITER_BVEC, and ITER_KVEC + */ +void iov_iter_restore(struct iov_iter *i, struct iov_iter_state *state) { - struct kvec w; - int err = -EINVAL; - if (!bytes) - return 0; - - iterate_all_kinds(i, bytes, v, -EINVAL, ({ - w.iov_base = kmap(v.bv_page) + v.bv_offset; - w.iov_len = v.bv_len; - err = f(&w, context); - kunmap(v.bv_page); - err;}), ({ - w = v; - err = f(&w, context);}) - ) - return err; + if (WARN_ON_ONCE(!iov_iter_is_bvec(i) && !iter_is_iovec(i)) && + !iov_iter_is_kvec(i)) + return; + i->iov_offset = state->iov_offset; + i->count = state->count; + /* + * For the *vec iters, nr_segs + iov is constant - if we increment + * the vec, then we also decrement the nr_segs count. Hence we don't + * need to track both of these, just one is enough and we can deduct + * the other from that. ITER_KVEC and ITER_IOVEC are the same struct + * size, so we can just increment the iov pointer as they are unionzed. + * ITER_BVEC _may_ be the same size on some archs, but on others it is + * not. Be safe and handle it separately. + */ + BUILD_BUG_ON(sizeof(struct iovec) != sizeof(struct kvec)); + if (iov_iter_is_bvec(i)) + i->bvec -= state->nr_segs - i->nr_segs; + else + i->iov -= state->nr_segs - i->nr_segs; + i->nr_segs = state->nr_segs; } -EXPORT_SYMBOL(iov_iter_for_each_range); diff --git a/lib/once.c b/lib/once.c index 59149bf3bfb4a97e4fa7febee737155d700bae48..351f66aad310a47f17d0636da0ed5b2b4460522d 100644 --- a/lib/once.c +++ b/lib/once.c @@ -66,3 +66,33 @@ void __do_once_done(bool *done, struct static_key_true *once_key, once_disable_jump(once_key, mod); } EXPORT_SYMBOL(__do_once_done); + +static DEFINE_MUTEX(once_mutex); + +bool __do_once_slow_start(bool *done) + __acquires(once_mutex) +{ + mutex_lock(&once_mutex); + if (*done) { + mutex_unlock(&once_mutex); + /* Keep sparse happy by restoring an even lock count on + * this mutex. In case we return here, we don't call into + * __do_once_done but return early in the DO_ONCE_SLOW() macro. + */ + __acquire(once_mutex); + return false; + } + + return true; +} +EXPORT_SYMBOL(__do_once_slow_start); + +void __do_once_slow_done(bool *done, struct static_key_true *once_key, + struct module *mod) + __releases(once_mutex) +{ + *done = true; + mutex_unlock(&once_mutex); + once_disable_jump(once_key, mod); +} +EXPORT_SYMBOL(__do_once_slow_done); diff --git a/lib/vdso/Makefile b/lib/vdso/Makefile index c415a685d61bb16ae92d196fb035ca7e3f397c6d..e814061d6aa010e90ab11a75e8a8171dc4cf8755 100644 --- a/lib/vdso/Makefile +++ b/lib/vdso/Makefile @@ -17,6 +17,6 @@ $(error ARCH_REL_TYPE_ABS is not set) endif quiet_cmd_vdso_check = VDSOCHK $@ - cmd_vdso_check = if $(OBJDUMP) -R $@ | egrep -h "$(ARCH_REL_TYPE_ABS)"; \ + cmd_vdso_check = if $(OBJDUMP) -R $@ | grep -E -h "$(ARCH_REL_TYPE_ABS)"; \ then (echo >&2 "$@: dynamic relocations are not supported"; \ rm -f $@; /bin/false); fi diff --git a/mm/filemap.c b/mm/filemap.c index 9a42edafb5fb9c56b32166dcbac1df9d6cb3cb25..aeb45f36aba18c0f4c472c0bbb04b1730a8d78b0 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -3471,7 +3471,7 @@ ssize_t generic_perform_write(struct file *file, unsigned long offset; /* Offset into pagecache page */ unsigned long bytes; /* Bytes to write to page */ size_t copied; /* Bytes copied from user */ - void *fsdata; + void *fsdata = NULL; offset = (pos & (PAGE_SIZE - 1)); bytes = min_t(unsigned long, PAGE_SIZE - offset, diff --git a/mm/hugetlb.c b/mm/hugetlb.c index e1c7c9c189f96d6fe6f19f5ddad2c3d86565792d..cc0e5ec63a0a33aae9e6e4988d8741ea213008f5 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2388,11 +2388,11 @@ struct page *alloc_huge_page(struct vm_area_struct *vma, page = alloc_buddy_huge_page_with_mpol(h, vma, addr); if (!page) goto out_uncharge_cgroup; + spin_lock(&hugetlb_lock); if (!avoid_reserve && vma_has_reserves(vma, gbl_chg)) { SetPagePrivate(page); h->resv_huge_pages--; } - spin_lock(&hugetlb_lock); list_add(&page->lru, &h->hugepage_activelist); /* Fall through */ } @@ -4331,15 +4331,11 @@ static inline vm_fault_t hugetlb_handle_userfault(struct vm_area_struct *vma, unsigned long haddr, unsigned long reason) { - vm_fault_t ret; - u32 hash; + u32 hash = hugetlb_fault_mutex_hash(mapping, idx); struct vm_fault vmf = { .vma = vma, .address = haddr, .flags = flags, - .vma_flags = vma->vm_flags, - .vma_page_prot = vma->vm_page_prot, - /* * Hard to debug if it ends up being * used by a callee that assumes @@ -4350,18 +4346,14 @@ static inline vm_fault_t hugetlb_handle_userfault(struct vm_area_struct *vma, }; /* - * hugetlb_fault_mutex and i_mmap_rwsem must be - * dropped before handling userfault. Reacquire - * after handling fault to make calling code simpler. + * vma_lock and hugetlb_fault_mutex must be dropped + * before handling userfault. Also mmap_lock will + * be dropped during handling userfault, any vma + * operation should be careful from here. */ - hash = hugetlb_fault_mutex_hash(mapping, idx); mutex_unlock(&hugetlb_fault_mutex_table[hash]); i_mmap_unlock_read(mapping); - ret = handle_userfault(&vmf, reason); - i_mmap_lock_read(mapping); - mutex_lock(&hugetlb_fault_mutex_table[hash]); - - return ret; + return handle_userfault(&vmf, VM_UFFD_MISSING); } static vm_fault_t hugetlb_no_page(struct mm_struct *mm, @@ -4378,6 +4370,7 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm, spinlock_t *ptl; unsigned long haddr = address & huge_page_mask(h); bool new_page = false; + u32 hash = hugetlb_fault_mutex_hash(mapping, idx); /* * Currently, we are forced to kill the process in the event the @@ -4387,7 +4380,7 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm, if (is_vma_resv_set(vma, HPAGE_RESV_UNMAPPED)) { pr_warn_ratelimited("PID %d killed due to inadequate hugepage pool\n", current->pid); - return ret; + goto out; } /* @@ -4524,6 +4517,8 @@ retry: unlock_page(page); out: + mutex_unlock(&hugetlb_fault_mutex_table[hash]); + i_mmap_unlock_read(mapping); return ret; backout: @@ -4619,10 +4614,12 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, mutex_lock(&hugetlb_fault_mutex_table[hash]); entry = huge_ptep_get(ptep); - if (huge_pte_none(entry)) { - ret = hugetlb_no_page(mm, vma, mapping, idx, address, ptep, flags); - goto out_mutex; - } + if (huge_pte_none(entry)) + /* + * hugetlb_no_page will drop vma lock and hugetlb fault + * mutex internally, which make us return immediately. + */ + return hugetlb_no_page(mm, vma, mapping, idx, address, ptep, flags); ret = 0; diff --git a/mm/maccess.c b/mm/maccess.c index 3bd70405f2d848d15ee90897e7e267eb3de2ebda..f6ea117a69eb55cde01746c40d69cbf9c54a45ca 100644 --- a/mm/maccess.c +++ b/mm/maccess.c @@ -83,7 +83,7 @@ long strncpy_from_kernel_nofault(char *dst, const void *unsafe_addr, long count) return src - unsafe_addr; Efault: pagefault_enable(); - dst[-1] = '\0'; + dst[0] = '\0'; return -EFAULT; } #else /* HAVE_GET_KERNEL_NOFAULT */ diff --git a/mm/memory.c b/mm/memory.c index 486f1eef20d9cca8f9dec13c238a1eb0d08fd862..6680d7a1e9791f59b9b74bdc465878d9702c6ca8 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -837,6 +837,17 @@ copy_present_page(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma if (likely(!page_maybe_dma_pinned(page))) return 1; + /* + * The vma->anon_vma of the child process may be NULL + * because the entire vma does not contain anonymous pages. + * A BUG will occur when the copy_present_page() passes + * a copy of a non-anonymous page of that vma to the + * page_add_new_anon_rmap() to set up new anonymous rmap. + * Return 1 if the page is not an anonymous page. + */ + if (!PageAnon(page)) + return 1; + new_page = *prealloc; if (!new_page) return -EAGAIN; diff --git a/mm/memremap.c b/mm/memremap.c index 2455bac895066d4458ae4a4c261b955dad531817..299aad0d26e56a68ffe724014d6ec28ec96e9aae 100644 --- a/mm/memremap.c +++ b/mm/memremap.c @@ -348,6 +348,7 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid) WARN(1, "File system DAX not supported\n"); return ERR_PTR(-EINVAL); } + params.pgprot = pgprot_decrypted(params.pgprot); break; case MEMORY_DEVICE_GENERIC: break; diff --git a/mm/mmap.c b/mm/mmap.c index 69c096503774370e21a3e0ae40c8b1095af11920..1e5e81ee661af45c9c0815ec8f49de4ba5178943 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1920,7 +1920,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr, if (!arch_validate_flags(vma->vm_flags)) { error = -EINVAL; if (file) - goto unmap_and_free_vma; + goto close_and_free_vma; else goto free_vma; } @@ -1967,6 +1967,9 @@ out: return addr; +close_and_free_vma: + if (vma->vm_ops && vma->vm_ops->close) + vma->vm_ops->close(vma); unmap_and_free_vma: vma->vm_file = NULL; fput(file); diff --git a/mm/vmscan.c b/mm/vmscan.c index bb80ecfa28717c5d473d7777ceef220bba42d6da..b2b60e5846e48afa862d67025453c1e50325f885 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -5394,9 +5394,9 @@ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) enum lru_list lru; unsigned long nr_reclaimed = 0; unsigned long nr_to_reclaim = sc->nr_to_reclaim; + bool proportional_reclaim; struct blk_plug plug; bool do_plug = true; - bool scan_adjusted; if (lru_gen_enabled()) { lru_gen_shrink_lruvec(lruvec, sc); @@ -5419,8 +5419,8 @@ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) * abort proportional reclaim if either the file or anon lru has already * dropped to zero at the first pass. */ - scan_adjusted = (!cgroup_reclaim(sc) && !current_is_kswapd() && - sc->priority == DEF_PRIORITY); + proportional_reclaim = (!cgroup_reclaim(sc) && !current_is_kswapd() && + sc->priority == DEF_PRIORITY); trace_android_vh_shrink_lruvec_blk_plug(&do_plug); if (do_plug) @@ -5442,7 +5442,7 @@ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) cond_resched(); - if (nr_reclaimed < nr_to_reclaim || scan_adjusted) + if (nr_reclaimed < nr_to_reclaim || proportional_reclaim) continue; /* @@ -5493,8 +5493,6 @@ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) nr_scanned = targets[lru] - nr[lru]; nr[lru] = targets[lru] * (100 - percentage) / 100; nr[lru] -= min(nr[lru], nr_scanned); - - scan_adjusted = true; } if (do_plug) blk_finish_plug(&plug); diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c index 8f528e783a6c533f604371228b7e31c28ea87577..400219801e63b587c74d053ca67b8110b8bb05ac 100644 --- a/net/9p/trans_fd.c +++ b/net/9p/trans_fd.c @@ -200,11 +200,15 @@ static void p9_conn_cancel(struct p9_conn *m, int err) list_for_each_entry_safe(req, rtmp, &m->req_list, req_list) { list_move(&req->req_list, &cancel_list); + req->status = REQ_STATUS_ERROR; } list_for_each_entry_safe(req, rtmp, &m->unsent_req_list, req_list) { list_move(&req->req_list, &cancel_list); + req->status = REQ_STATUS_ERROR; } + spin_unlock(&m->client->lock); + list_for_each_entry_safe(req, rtmp, &cancel_list, req_list) { p9_debug(P9_DEBUG_ERROR, "call back req %p\n", req); list_del(&req->req_list); @@ -212,7 +216,6 @@ static void p9_conn_cancel(struct p9_conn *m, int err) req->t_err = err; p9_client_cb(m->client, req, REQ_STATUS_ERROR); } - spin_unlock(&m->client->lock); } static __poll_t @@ -820,11 +823,14 @@ static int p9_fd_open(struct p9_client *client, int rfd, int wfd) goto out_free_ts; if (!(ts->rd->f_mode & FMODE_READ)) goto out_put_rd; + /* prevent workers from hanging on IO when fd is a pipe */ + ts->rd->f_flags |= O_NONBLOCK; ts->wr = fget(wfd); if (!ts->wr) goto out_put_rd; if (!(ts->wr->f_mode & FMODE_WRITE)) goto out_put_wr; + ts->wr->f_flags |= O_NONBLOCK; client->trans = ts; client->status = Connected; diff --git a/net/atm/mpoa_proc.c b/net/atm/mpoa_proc.c index 829db9eba0cb95ac9cfe775e8eaad712943a8dbe..aaf64b953915070be8501d8a7a7a40d9def67234 100644 --- a/net/atm/mpoa_proc.c +++ b/net/atm/mpoa_proc.c @@ -219,11 +219,12 @@ static ssize_t proc_mpc_write(struct file *file, const char __user *buff, if (!page) return -ENOMEM; - for (p = page, len = 0; len < nbytes; p++, len++) { + for (p = page, len = 0; len < nbytes; p++) { if (get_user(*p, buff++)) { free_page((unsigned long)page); return -EFAULT; } + len += 1; if (*p == '\0' || *p == '\n') break; } diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index c331b4176de7362908a4d2baa7c3c2608b291c47..99ef44b25cc0ec3f9ea7171c3435c15f51d1923f 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -4479,15 +4479,27 @@ static inline int __get_blocks(struct hci_dev *hdev, struct sk_buff *skb) return DIV_ROUND_UP(skb->len - HCI_ACL_HDR_SIZE, hdev->block_len); } -static void __check_timeout(struct hci_dev *hdev, unsigned int cnt) +static void __check_timeout(struct hci_dev *hdev, unsigned int cnt, u8 type) { - if (!hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) { - /* ACL tx timeout must be longer than maximum - * link supervision timeout (40.9 seconds) */ - if (!cnt && time_after(jiffies, hdev->acl_last_tx + - HCI_ACL_TX_TIMEOUT)) - hci_link_tx_to(hdev, ACL_LINK); + unsigned long last_tx; + + if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) + return; + + switch (type) { + case LE_LINK: + last_tx = hdev->le_last_tx; + break; + default: + last_tx = hdev->acl_last_tx; + break; } + + /* tx timeout must be longer than maximum link supervision timeout + * (40.9 seconds) + */ + if (!cnt && time_after(jiffies, last_tx + HCI_ACL_TX_TIMEOUT)) + hci_link_tx_to(hdev, type); } /* Schedule SCO */ @@ -4545,7 +4557,7 @@ static void hci_sched_acl_pkt(struct hci_dev *hdev) struct sk_buff *skb; int quote; - __check_timeout(hdev, cnt); + __check_timeout(hdev, cnt, ACL_LINK); while (hdev->acl_cnt && (chan = hci_chan_sent(hdev, ACL_LINK, "e))) { @@ -4588,8 +4600,6 @@ static void hci_sched_acl_blk(struct hci_dev *hdev) int quote; u8 type; - __check_timeout(hdev, cnt); - BT_DBG("%s", hdev->name); if (hdev->dev_type == HCI_AMP) @@ -4597,6 +4607,8 @@ static void hci_sched_acl_blk(struct hci_dev *hdev) else type = ACL_LINK; + __check_timeout(hdev, cnt, type); + while (hdev->block_cnt > 0 && (chan = hci_chan_sent(hdev, type, "e))) { u32 priority = (skb_peek(&chan->data_q))->priority; @@ -4670,7 +4682,7 @@ static void hci_sched_le(struct hci_dev *hdev) cnt = hdev->le_pkts ? hdev->le_cnt : hdev->acl_cnt; - __check_timeout(hdev, cnt); + __check_timeout(hdev, cnt, LE_LINK); tmp = cnt; while (cnt && (chan = hci_chan_sent(hdev, LE_LINK, "e))) { diff --git a/net/bluetooth/hci_sysfs.c b/net/bluetooth/hci_sysfs.c index b69d88b88d2e4f25dc725b147bcb373a2eee8404..ccd2c377bf83c8788d5a97a1783779a00c42dcb6 100644 --- a/net/bluetooth/hci_sysfs.c +++ b/net/bluetooth/hci_sysfs.c @@ -48,6 +48,9 @@ void hci_conn_add_sysfs(struct hci_conn *conn) BT_DBG("conn %p", conn); + if (device_is_registered(&conn->dev)) + return; + dev_set_name(&conn->dev, "%s:%d", hdev->name, conn->handle); if (device_add(&conn->dev) < 0) { diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 8692cbbe096266ab5be5bc923630073dcc855bd8..e851f8047f74b57abcce6a571cbb0fd3f38cb145 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -61,6 +61,9 @@ static void l2cap_send_disconn_req(struct l2cap_chan *chan, int err); static void l2cap_tx(struct l2cap_chan *chan, struct l2cap_ctrl *control, struct sk_buff_head *skbs, u8 event); +static void l2cap_retrans_timeout(struct work_struct *work); +static void l2cap_monitor_timeout(struct work_struct *work); +static void l2cap_ack_timeout(struct work_struct *work); static inline u8 bdaddr_type(u8 link_type, u8 bdaddr_type) { @@ -476,6 +479,9 @@ struct l2cap_chan *l2cap_chan_create(void) write_unlock(&chan_list_lock); INIT_DELAYED_WORK(&chan->chan_timer, l2cap_chan_timeout); + INIT_DELAYED_WORK(&chan->retrans_timer, l2cap_retrans_timeout); + INIT_DELAYED_WORK(&chan->monitor_timer, l2cap_monitor_timeout); + INIT_DELAYED_WORK(&chan->ack_timer, l2cap_ack_timeout); chan->state = BT_OPEN; @@ -1980,7 +1986,7 @@ static struct l2cap_chan *l2cap_global_chan_by_psm(int state, __le16 psm, if (link_type == LE_LINK && c->src_type == BDADDR_BREDR) continue; - if (c->psm == psm) { + if (c->chan_type != L2CAP_CHAN_FIXED && c->psm == psm) { int src_match, dst_match; int src_any, dst_any; @@ -3316,10 +3322,6 @@ int l2cap_ertm_init(struct l2cap_chan *chan) chan->rx_state = L2CAP_RX_STATE_RECV; chan->tx_state = L2CAP_TX_STATE_XMIT; - INIT_DELAYED_WORK(&chan->retrans_timer, l2cap_retrans_timeout); - INIT_DELAYED_WORK(&chan->monitor_timer, l2cap_monitor_timeout); - INIT_DELAYED_WORK(&chan->ack_timer, l2cap_ack_timeout); - skb_queue_head_init(&chan->srej_q); err = l2cap_seq_list_init(&chan->srej_list, chan->tx_win); @@ -3758,7 +3760,8 @@ done: l2cap_add_conf_opt(&ptr, L2CAP_CONF_RFC, sizeof(rfc), (unsigned long) &rfc, endptr - ptr); - if (test_bit(FLAG_EFS_ENABLE, &chan->flags)) { + if (remote_efs && + test_bit(FLAG_EFS_ENABLE, &chan->flags)) { chan->remote_id = efs.id; chan->remote_stype = efs.stype; chan->remote_msdu = le16_to_cpu(efs.msdu); @@ -4303,6 +4306,12 @@ static int l2cap_connect_create_rsp(struct l2cap_conn *conn, } } + chan = l2cap_chan_hold_unless_zero(chan); + if (!chan) { + err = -EBADSLT; + goto unlock; + } + err = 0; l2cap_chan_lock(chan); @@ -4332,6 +4341,7 @@ static int l2cap_connect_create_rsp(struct l2cap_conn *conn, } l2cap_chan_unlock(chan); + l2cap_chan_put(chan); unlock: mutex_unlock(&conn->chan_lock); @@ -4439,7 +4449,8 @@ static inline int l2cap_config_req(struct l2cap_conn *conn, chan->ident = cmd->ident; l2cap_send_cmd(conn, cmd->ident, L2CAP_CONF_RSP, len, rsp); - chan->num_conf_rsp++; + if (chan->num_conf_rsp < L2CAP_CONF_MAX_CONF_RSP) + chan->num_conf_rsp++; /* Reset config buffer. */ chan->conf_len = 0; @@ -5799,6 +5810,19 @@ static int l2cap_le_connect_req(struct l2cap_conn *conn, BT_DBG("psm 0x%2.2x scid 0x%4.4x mtu %u mps %u", __le16_to_cpu(psm), scid, mtu, mps); + /* BLUETOOTH CORE SPECIFICATION Version 5.3 | Vol 3, Part A + * page 1059: + * + * Valid range: 0x0001-0x00ff + * + * Table 4.15: L2CAP_LE_CREDIT_BASED_CONNECTION_REQ SPSM ranges + */ + if (!psm || __le16_to_cpu(psm) > L2CAP_PSM_LE_DYN_END) { + result = L2CAP_CR_LE_BAD_PSM; + chan = NULL; + goto response; + } + /* Check if we have socket listening on psm */ pchan = l2cap_global_chan_by_psm(BT_LISTEN, psm, &conn->hcon->src, &conn->hcon->dst, LE_LINK); @@ -5979,6 +6003,18 @@ static inline int l2cap_ecred_conn_req(struct l2cap_conn *conn, psm = req->psm; + /* BLUETOOTH CORE SPECIFICATION Version 5.3 | Vol 3, Part A + * page 1059: + * + * Valid range: 0x0001-0x00ff + * + * Table 4.15: L2CAP_LE_CREDIT_BASED_CONNECTION_REQ SPSM ranges + */ + if (!psm || __le16_to_cpu(psm) > L2CAP_PSM_LE_DYN_END) { + result = L2CAP_CR_LE_BAD_PSM; + goto response; + } + BT_DBG("psm 0x%2.2x mtu %u mps %u", __le16_to_cpu(psm), mtu, mps); memset(&pdu, 0, sizeof(pdu)); @@ -6865,6 +6901,7 @@ static int l2cap_rx_state_recv(struct l2cap_chan *chan, struct l2cap_ctrl *control, struct sk_buff *skb, u8 event) { + struct l2cap_ctrl local_control; int err = 0; bool skb_in_use = false; @@ -6889,15 +6926,32 @@ static int l2cap_rx_state_recv(struct l2cap_chan *chan, chan->buffer_seq = chan->expected_tx_seq; skb_in_use = true; + /* l2cap_reassemble_sdu may free skb, hence invalidate + * control, so make a copy in advance to use it after + * l2cap_reassemble_sdu returns and to avoid the race + * condition, for example: + * + * The current thread calls: + * l2cap_reassemble_sdu + * chan->ops->recv == l2cap_sock_recv_cb + * __sock_queue_rcv_skb + * Another thread calls: + * bt_sock_recvmsg + * skb_recv_datagram + * skb_free_datagram + * Then the current thread tries to access control, but + * it was freed by skb_free_datagram. + */ + local_control = *control; err = l2cap_reassemble_sdu(chan, skb, control); if (err) break; - if (control->final) { + if (local_control.final) { if (!test_and_clear_bit(CONN_REJ_ACT, &chan->conn_state)) { - control->final = 0; - l2cap_retransmit_all(chan, control); + local_control.final = 0; + l2cap_retransmit_all(chan, &local_control); l2cap_ertm_send(chan); } } @@ -7277,11 +7331,27 @@ static int l2cap_rx(struct l2cap_chan *chan, struct l2cap_ctrl *control, static int l2cap_stream_rx(struct l2cap_chan *chan, struct l2cap_ctrl *control, struct sk_buff *skb) { + /* l2cap_reassemble_sdu may free skb, hence invalidate control, so store + * the txseq field in advance to use it after l2cap_reassemble_sdu + * returns and to avoid the race condition, for example: + * + * The current thread calls: + * l2cap_reassemble_sdu + * chan->ops->recv == l2cap_sock_recv_cb + * __sock_queue_rcv_skb + * Another thread calls: + * bt_sock_recvmsg + * skb_recv_datagram + * skb_free_datagram + * Then the current thread tries to access control, but it was freed by + * skb_free_datagram. + */ + u16 txseq = control->txseq; + BT_DBG("chan %p, control %p, skb %p, state %d", chan, control, skb, chan->rx_state); - if (l2cap_classify_txseq(chan, control->txseq) == - L2CAP_TXSEQ_EXPECTED) { + if (l2cap_classify_txseq(chan, txseq) == L2CAP_TXSEQ_EXPECTED) { l2cap_pass_to_tx(chan, control); BT_DBG("buffer_seq %d->%d", chan->buffer_seq, @@ -7304,8 +7374,8 @@ static int l2cap_stream_rx(struct l2cap_chan *chan, struct l2cap_ctrl *control, } } - chan->last_acked_seq = control->txseq; - chan->expected_tx_seq = __next_seq(chan, control->txseq); + chan->last_acked_seq = txseq; + chan->expected_tx_seq = __next_seq(chan, txseq); return 0; } @@ -7561,6 +7631,7 @@ static void l2cap_data_channel(struct l2cap_conn *conn, u16 cid, return; } + l2cap_chan_hold(chan); l2cap_chan_lock(chan); } else { BT_DBG("unknown cid 0x%4.4x", cid); diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 2983e926fe3cceed63c3a29b53ac5d6658153a06..717b01ff9b2ba451e668c697aa5e225b3b70422c 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -231,6 +231,7 @@ static void *bpf_test_init(const union bpf_attr *kattr, u32 size, if (user_size > size) return ERR_PTR(-EMSGSIZE); + size = SKB_DATA_ALIGN(size); data = kzalloc(size + headroom + tailroom, GFP_USER); if (!data) return ERR_PTR(-ENOMEM); diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index 852f4b54e8811a275ca3df6d261c5a9c481b6db9..1dc5db07650c9ad387705f8ed06eb9b57111a554 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -855,26 +855,37 @@ EXPORT_SYMBOL_GPL(br_vlan_get_proto); int __br_vlan_set_proto(struct net_bridge *br, __be16 proto) { + struct switchdev_attr attr = { + .orig_dev = br->dev, + .id = SWITCHDEV_ATTR_ID_BRIDGE_VLAN_PROTOCOL, + .flags = SWITCHDEV_F_SKIP_EOPNOTSUPP, + .u.vlan_protocol = ntohs(proto), + }; int err = 0; struct net_bridge_port *p; struct net_bridge_vlan *vlan; struct net_bridge_vlan_group *vg; - __be16 oldproto; + __be16 oldproto = br->vlan_proto; if (br->vlan_proto == proto) return 0; + err = switchdev_port_attr_set(br->dev, &attr); + if (err && err != -EOPNOTSUPP) + return err; + /* Add VLANs for the new proto to the device filter. */ list_for_each_entry(p, &br->port_list, list) { vg = nbp_vlan_group(p); list_for_each_entry(vlan, &vg->vlan_list, vlist) { + if (vlan->priv_flags & BR_VLFLAG_ADDED_BY_SWITCHDEV) + continue; err = vlan_vid_add(p->dev, proto, vlan->vid); if (err) goto err_filt; } } - oldproto = br->vlan_proto; br->vlan_proto = proto; recalculate_group_addr(br); @@ -883,20 +894,32 @@ int __br_vlan_set_proto(struct net_bridge *br, __be16 proto) /* Delete VLANs for the old proto from the device filter. */ list_for_each_entry(p, &br->port_list, list) { vg = nbp_vlan_group(p); - list_for_each_entry(vlan, &vg->vlan_list, vlist) + list_for_each_entry(vlan, &vg->vlan_list, vlist) { + if (vlan->priv_flags & BR_VLFLAG_ADDED_BY_SWITCHDEV) + continue; vlan_vid_del(p->dev, oldproto, vlan->vid); + } } return 0; err_filt: - list_for_each_entry_continue_reverse(vlan, &vg->vlan_list, vlist) + attr.u.vlan_protocol = ntohs(oldproto); + switchdev_port_attr_set(br->dev, &attr); + + list_for_each_entry_continue_reverse(vlan, &vg->vlan_list, vlist) { + if (vlan->priv_flags & BR_VLFLAG_ADDED_BY_SWITCHDEV) + continue; vlan_vid_del(p->dev, proto, vlan->vid); + } list_for_each_entry_continue_reverse(p, &br->port_list, list) { vg = nbp_vlan_group(p); - list_for_each_entry(vlan, &vg->vlan_list, vlist) + list_for_each_entry(vlan, &vg->vlan_list, vlist) { + if (vlan->priv_flags & BR_VLFLAG_ADDED_BY_SWITCHDEV) + continue; vlan_vid_del(p->dev, proto, vlan->vid); + } } return err; diff --git a/net/caif/chnl_net.c b/net/caif/chnl_net.c index 42dc080a4dbbcbfd8b072f5c15684a37bb42ca37..806fb4d84fd3e375beefafc06a616a49cb7835db 100644 --- a/net/caif/chnl_net.c +++ b/net/caif/chnl_net.c @@ -315,9 +315,6 @@ static int chnl_net_open(struct net_device *dev) if (result == 0) { pr_debug("connect timeout\n"); - caif_disconnect_client(dev_net(dev), &priv->chnl); - priv->state = CAIF_DISCONNECTED; - pr_debug("state disconnected\n"); result = -ETIMEDOUT; goto error; } diff --git a/net/can/af_can.c b/net/can/af_can.c index 1c95ede2c9a6e4101f6840ae914bff156c9a1d1e..cf554e8555214fbb67b3187fe42e65e0f89aec55 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -451,7 +451,7 @@ int can_rx_register(struct net *net, struct net_device *dev, canid_t can_id, /* insert new receiver (dev,canid,mask) -> (func,data) */ - if (dev && dev->type != ARPHRD_CAN) + if (dev && (dev->type != ARPHRD_CAN || !can_get_ml_priv(dev))) return -ENODEV; if (dev && !net_eq(net, dev_net(dev))) diff --git a/net/can/bcm.c b/net/can/bcm.c index e918a0f3cda28ac190ff311c90c74caf6801aced..afa82adaf6cd5a8f79c1588b87ad18d30d09f240 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -274,6 +274,7 @@ static void bcm_can_tx(struct bcm_op *op) struct sk_buff *skb; struct net_device *dev; struct canfd_frame *cf = op->frames + op->cfsiz * op->currframe; + int err; /* no target device? => exit */ if (!op->ifindex) @@ -298,11 +299,11 @@ static void bcm_can_tx(struct bcm_op *op) /* send with loopback */ skb->dev = dev; can_skb_set_owner(skb, op->sk); - can_send(skb, 1); + err = can_send(skb, 1); + if (!err) + op->frames_abs++; - /* update statistics */ op->currframe++; - op->frames_abs++; /* reached last frame? */ if (op->currframe >= op->nframes) diff --git a/net/can/j1939/main.c b/net/can/j1939/main.c index ca75d1b8f415c070b9789605dcbbdee63cc1ddea..9da8fbc81c04a2692f5ada40e4b62937755fc483 100644 --- a/net/can/j1939/main.c +++ b/net/can/j1939/main.c @@ -332,6 +332,9 @@ int j1939_send_one(struct j1939_priv *priv, struct sk_buff *skb) /* re-claim the CAN_HDR from the SKB */ cf = skb_push(skb, J1939_CAN_HDR); + /* initialize header structure */ + memset(cf, 0, J1939_CAN_HDR); + /* make it a full can frame again */ skb_put(skb, J1939_CAN_FTR + (8 - dlc)); diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c index 2830a12a4dd1b4e39fea70838d0d3f9e8af9e66a..78f6a91106994fbb77fdbd76259d79c799f177bd 100644 --- a/net/can/j1939/transport.c +++ b/net/can/j1939/transport.c @@ -338,10 +338,12 @@ static void j1939_session_skb_drop_old(struct j1939_session *session) __skb_unlink(do_skb, &session->skb_queue); /* drop ref taken in j1939_session_skb_queue() */ skb_unref(do_skb); + spin_unlock_irqrestore(&session->skb_queue.lock, flags); kfree_skb(do_skb); + } else { + spin_unlock_irqrestore(&session->skb_queue.lock, flags); } - spin_unlock_irqrestore(&session->skb_queue.lock, flags); } void j1939_session_skb_queue(struct j1939_session *session, diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index ed120828c7e21f6681894020a8df689c059df2e8..b8d082f557183a6223526f29099efcc114d5b8a7 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -263,7 +263,7 @@ skb_flow_dissect_ct(const struct sk_buff *skb, key->ct_zone = ct->zone.id; #endif #if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) - key->ct_mark = ct->mark; + key->ct_mark = READ_ONCE(ct->mark); #endif cl = nf_ct_labels_find(ct); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 434c5aab83ea2780c511116a5df5f269ddd83f84..f6f580e9d282004a27b65b6b990ad5e7877d42f4 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -373,7 +373,7 @@ static int __neigh_ifdown(struct neigh_table *tbl, struct net_device *dev, write_lock_bh(&tbl->lock); neigh_flush_dev(tbl, dev, skip_perm); pneigh_ifdown_and_unlock(tbl, dev); - pneigh_queue_purge(&tbl->proxy_queue, dev_net(dev)); + pneigh_queue_purge(&tbl->proxy_queue, dev ? dev_net(dev) : NULL); if (skb_queue_empty_lockless(&tbl->proxy_queue)) del_timer_sync(&tbl->proxy_timer); return 0; diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index cbff7d94b993ec941197c99af3118350e7c95445..a3b7d965e9c019897ebfee816d9e8f1e5acb1b12 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -135,6 +135,7 @@ static int net_assign_generic(struct net *net, unsigned int id, void *data) static int ops_init(const struct pernet_operations *ops, struct net *net) { + struct net_generic *ng; int err = -ENOMEM; void *data = NULL; @@ -153,7 +154,13 @@ static int ops_init(const struct pernet_operations *ops, struct net *net) if (!err) return 0; + if (ops->id && ops->size) { cleanup: + ng = rcu_dereference_protected(net->gen, + lockdep_is_held(&pernet_ops_rwsem)); + ng->ptr[*ops->id] = NULL; + } + kfree(data); out: diff --git a/net/core/skbuff.c b/net/core/skbuff.c index da1f9f4fe3b9fbd76fc453c56254c70bcc5ec83f..11f49e2f749cfbc5efa8616a0ee9de684f736271 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -982,7 +982,15 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old) #ifdef CONFIG_NET_SCHED CHECK_SKB_FIELD(tc_index); #endif - + /* ANDROID: + * Due to attempts to keep the ABI stable for struct sk_buff, the new + * fields were incorrectly added _AFTER_ the headers_end field, which + * requires that we manually copy the fields here from the old to the + * new one. + * Be sure to add any new field that is added in the + * ANDROID_KABI_REPLACE() macros below here as well. + */ + new->scm_io_uring = old->scm_io_uring; } /* @@ -3832,23 +3840,25 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb, int i = 0; int pos; - if (list_skb && !list_skb->head_frag && skb_headlen(list_skb) && - (skb_shinfo(head_skb)->gso_type & SKB_GSO_DODGY)) { - /* gso_size is untrusted, and we have a frag_list with a linear - * non head_frag head. - * - * (we assume checking the first list_skb member suffices; - * i.e if either of the list_skb members have non head_frag - * head, then the first one has too). - * - * If head_skb's headlen does not fit requested gso_size, it - * means that the frag_list members do NOT terminate on exact - * gso_size boundaries. Hence we cannot perform skb_frag_t page - * sharing. Therefore we must fallback to copying the frag_list - * skbs; we do so by disabling SG. - */ - if (mss != GSO_BY_FRAGS && mss != skb_headlen(head_skb)) - features &= ~NETIF_F_SG; + if ((skb_shinfo(head_skb)->gso_type & SKB_GSO_DODGY) && + mss != GSO_BY_FRAGS && mss != skb_headlen(head_skb)) { + struct sk_buff *check_skb; + + for (check_skb = list_skb; check_skb; check_skb = check_skb->next) { + if (skb_headlen(check_skb) && !check_skb->head_frag) { + /* gso_size is untrusted, and we have a frag_list with + * a linear non head_frag item. + * + * If head_skb's headlen does not fit requested gso_size, + * it means that the frag_list members do NOT terminate + * on exact gso_size boundaries. Hence we cannot perform + * skb_frag_t page sharing. Therefore we must fallback to + * copying the frag_list skbs; we do so by disabling SG. + */ + features &= ~NETIF_F_SG; + break; + } + } } __skb_push(head_skb, doffset); diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c index b065f0a103ed06e40105967b9926679d5840d00a..49f9c2c4ffd5a5676082afae3aece4b7253c8e86 100644 --- a/net/core/sock_reuseport.c +++ b/net/core/sock_reuseport.c @@ -18,6 +18,22 @@ DEFINE_SPINLOCK(reuseport_lock); static DEFINE_IDA(reuseport_ida); +void reuseport_has_conns_set(struct sock *sk) +{ + struct sock_reuseport *reuse; + + if (!rcu_access_pointer(sk->sk_reuseport_cb)) + return; + + spin_lock_bh(&reuseport_lock); + reuse = rcu_dereference_protected(sk->sk_reuseport_cb, + lockdep_is_held(&reuseport_lock)); + if (likely(reuse)) + reuse->has_conns = 1; + spin_unlock_bh(&reuseport_lock); +} +EXPORT_SYMBOL(reuseport_has_conns_set); + static struct sock_reuseport *__reuseport_alloc(unsigned int max_socks) { unsigned int size = sizeof(struct sock_reuseport) + diff --git a/net/core/stream.c b/net/core/stream.c index a166a32b411fa6d9c37f5aed5da9b85b912a8086..a61130504827a7f4121c154dbb5f3e8e7cf6564f 100644 --- a/net/core/stream.c +++ b/net/core/stream.c @@ -159,7 +159,8 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p) *timeo_p = current_timeo; } out: - remove_wait_queue(sk_sleep(sk), &wait); + if (!sock_flag(sk, SOCK_DEAD)) + remove_wait_queue(sk_sleep(sk), &wait); return err; do_error: diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 2455b0c0e4866f30895ce3297c2652d5623b0430..a2a8b952b3c55bf9e79253102d26591f34155cc9 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -130,6 +130,8 @@ failure: * This unhashes the socket and releases the local port, if necessary. */ dccp_set_state(sk, DCCP_CLOSED); + if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) + inet_reset_saddr(sk); ip_rt_put(rt); sk->sk_route_caps = 0; inet->inet_dport = 0; diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 2be5c69824f94423e2f90b97938dd623a4fea9c7..21c61a9c3b1523d061b0bee8007003c9a9513373 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -957,6 +957,8 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, late_failure: dccp_set_state(sk, DCCP_CLOSED); + if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) + inet_reset_saddr(sk); __sk_dst_reset(sk); failure: inet->inet_dport = 0; diff --git a/net/hsr/hsr_forward.c b/net/hsr/hsr_forward.c index baf4765be6d78653732dc50c0ac36344b2af1045..908324b46328f311d6337f6115f8f202ebd19d2f 100644 --- a/net/hsr/hsr_forward.c +++ b/net/hsr/hsr_forward.c @@ -108,15 +108,15 @@ struct sk_buff *hsr_get_untagged_frame(struct hsr_frame_info *frame, struct hsr_port *port) { if (!frame->skb_std) { - if (frame->skb_hsr) { + if (frame->skb_hsr) frame->skb_std = create_stripped_skb_hsr(frame->skb_hsr, frame); - } else { - /* Unexpected */ - WARN_ONCE(1, "%s:%d: Unexpected frame received (port_src %s)\n", - __FILE__, __LINE__, port->dev->name); + else + netdev_warn_once(port->dev, + "Unexpected frame received in hsr_get_untagged_frame()\n"); + + if (!frame->skb_std) return NULL; - } } return skb_clone(frame->skb_std, GFP_ATOMIC); diff --git a/net/ieee802154/socket.c b/net/ieee802154/socket.c index 7edec210780a39e534657b295fc78eb0f8e07761..d4c275e56d8254bc0ad2e82decc683539bcbd761 100644 --- a/net/ieee802154/socket.c +++ b/net/ieee802154/socket.c @@ -273,6 +273,10 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) err = -EMSGSIZE; goto out_dev; } + if (!size) { + err = 0; + goto out_dev; + } hlen = LL_RESERVED_SPACE(dev); tlen = dev->needed_tailroom; @@ -499,8 +503,10 @@ static int dgram_bind(struct sock *sk, struct sockaddr *uaddr, int len) if (err < 0) goto out; - if (addr->family != AF_IEEE802154) + if (addr->family != AF_IEEE802154) { + err = -EINVAL; goto out; + } ieee802154_addr_from_sa(&haddr, &addr->addr); dev = ieee802154_get_dev(sock_net(sk), &haddr); diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index 87983e70f03f320fffae872a13f6befb34467204..23b06063e1a512b69d437f3e9ae74ff37e03664b 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -403,6 +403,16 @@ config INET_IPCOMP If unsure, say Y. +config INET_TABLE_PERTURB_ORDER + int "INET: Source port perturbation table size (as power of 2)" if EXPERT + default 16 + help + Source port perturbation table size (as power of 2) for + RFC 6056 3.3.4. Algorithm 4: Double-Hash Port Selection Algorithm. + + The default is almost always what you want. + Only change this if you know what you are doing. + config INET_XFRM_TUNNEL tristate select INET_TUNNEL diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 0494caae8d59834e7ca7735565060b7e75a4fb9a..b9f4fe8c14b8ae88acb959554e7d58947618d6f8 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -158,7 +158,7 @@ void inet_sock_destruct(struct sock *sk) kfree(rcu_dereference_protected(inet->inet_opt, 1)); dst_release(rcu_dereference_protected(sk->sk_dst_cache, 1)); - dst_release(sk->sk_rx_dst); + dst_release(rcu_dereference_protected(sk->sk_rx_dst, 1)); sk_refcnt_debug_dec(sk); } EXPORT_SYMBOL(inet_sock_destruct); @@ -1021,7 +1021,6 @@ static int inet_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned lon const struct proto_ops inet_stream_ops = { .family = PF_INET, - .flags = PROTO_CMSG_DATA_ONLY, .owner = THIS_MODULE, .release = inet_release, .bind = inet_bind, @@ -1730,12 +1729,7 @@ static const struct net_protocol igmp_protocol = { }; #endif -/* thinking of making this const? Don't. - * early_demux can change based on sysctl. - */ -static struct net_protocol tcp_protocol = { - .early_demux = tcp_v4_early_demux, - .early_demux_handler = tcp_v4_early_demux, +static const struct net_protocol tcp_protocol = { .handler = tcp_v4_rcv, .err_handler = tcp_v4_err, .no_policy = 1, @@ -1743,12 +1737,7 @@ static struct net_protocol tcp_protocol = { .icmp_strict_tag_validation = 1, }; -/* thinking of making this const? Don't. - * early_demux can change based on sysctl. - */ -static struct net_protocol udp_protocol = { - .early_demux = udp_v4_early_demux, - .early_demux_handler = udp_v4_early_demux, +static const struct net_protocol udp_protocol = { .handler = udp_rcv, .err_handler = udp_err, .no_policy = 1, diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c index 4a8550c49202db13b17d5cf4ed1e44dd8852c212..112c6e892d305025dcc25e67bf0f621669c5af44 100644 --- a/net/ipv4/datagram.c +++ b/net/ipv4/datagram.c @@ -70,7 +70,7 @@ int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len } inet->inet_daddr = fl4->daddr; inet->inet_dport = usin->sin_port; - reuseport_has_conns(sk, true); + reuseport_has_conns_set(sk); sk->sk_state = TCP_ESTABLISHED; sk_set_txhash(sk); inet->inet_id = prandom_u32(); diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c index 3450c9ba2728c7a1f5ac021fa88db37ff0cd977b..84257678160a3af951d43e89a25352444f39f383 100644 --- a/net/ipv4/esp4_offload.c +++ b/net/ipv4/esp4_offload.c @@ -312,6 +312,9 @@ static int esp_xmit(struct xfrm_state *x, struct sk_buff *skb, netdev_features_ xo->seq.low += skb_shinfo(skb)->gso_segs; } + if (xo->seq.low < seq) + xo->seq.hi++; + esp.seqno = cpu_to_be64(seq + ((u64)xo->seq.hi << 32)); ip_hdr(skb)->tot_len = htons(skb->len); diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index a28f525e2c47458c58768038566cb7785ae0069f..d11fb16234a6af17aa65349a58ae79acbaf49d7a 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1331,8 +1331,10 @@ int fib_table_insert(struct net *net, struct fib_table *tb, /* The alias was already inserted, so the node must exist. */ l = l ? l : fib_find_node(t, &tp, key); - if (WARN_ON_ONCE(!l)) + if (WARN_ON_ONCE(!l)) { + err = -ENOENT; goto out_free_new_fa; + } if (fib_find_alias(&l->leaf, new_fa->fa_slen, 0, 0, tb->tb_id, true) == new_fa) { diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index feb7f072f2b26f25fa373dfdb27ad00f721c2849..c68a1dae25ca3b46f75c85b850548bebe468d34f 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -721,13 +721,13 @@ EXPORT_SYMBOL_GPL(inet_unhash); * Note that we use 32bit integers (vs RFC 'short integers') * because 2^16 is not a multiple of num_ephemeral and this * property might be used by clever attacker. + * * RFC claims using TABLE_LENGTH=10 buckets gives an improvement, though - * attacks were since demonstrated, thus we use 65536 instead to really - * give more isolation and privacy, at the expense of 256kB of kernel - * memory. + * attacks were since demonstrated, thus we use 65536 by default instead + * to really give more isolation and privacy, at the expense of 256kB + * of kernel memory. */ -#define INET_TABLE_PERTURB_SHIFT 16 -#define INET_TABLE_PERTURB_SIZE (1 << INET_TABLE_PERTURB_SHIFT) +#define INET_TABLE_PERTURB_SIZE (1 << CONFIG_INET_TABLE_PERTURB_ORDER) static u32 *table_perturb; int __inet_hash_connect(struct inet_timewait_death_row *death_row, @@ -771,8 +771,8 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, if (likely(remaining > 1)) remaining &= ~1U; - net_get_random_once(table_perturb, - INET_TABLE_PERTURB_SIZE * sizeof(*table_perturb)); + get_random_slow_once(table_perturb, + INET_TABLE_PERTURB_SIZE * sizeof(*table_perturb)); index = port_offset & (INET_TABLE_PERTURB_SIZE - 1); offset = READ_ONCE(table_perturb[index]) + (port_offset >> 32); diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index b0c244af1e4d587322b4e3490ad3d878805be670..f6b3237e88cab18f55e21313477e84609d525c85 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -309,14 +309,13 @@ static bool ip_can_use_hint(const struct sk_buff *skb, const struct iphdr *iph, ip_hdr(hint)->tos == iph->tos; } -INDIRECT_CALLABLE_DECLARE(int udp_v4_early_demux(struct sk_buff *)); -INDIRECT_CALLABLE_DECLARE(int tcp_v4_early_demux(struct sk_buff *)); +int tcp_v4_early_demux(struct sk_buff *skb); +int udp_v4_early_demux(struct sk_buff *skb); static int ip_rcv_finish_core(struct net *net, struct sock *sk, struct sk_buff *skb, struct net_device *dev, const struct sk_buff *hint) { const struct iphdr *iph = ip_hdr(skb); - int (*edemux)(struct sk_buff *skb); struct rtable *rt; int err; @@ -327,21 +326,29 @@ static int ip_rcv_finish_core(struct net *net, struct sock *sk, goto drop_error; } - if (net->ipv4.sysctl_ip_early_demux && + if (READ_ONCE(net->ipv4.sysctl_ip_early_demux) && !skb_dst(skb) && !skb->sk && !ip_is_fragment(iph)) { - const struct net_protocol *ipprot; - int protocol = iph->protocol; - - ipprot = rcu_dereference(inet_protos[protocol]); - if (ipprot && (edemux = READ_ONCE(ipprot->early_demux))) { - err = INDIRECT_CALL_2(edemux, tcp_v4_early_demux, - udp_v4_early_demux, skb); - if (unlikely(err)) - goto drop_error; - /* must reload iph, skb->head might have changed */ - iph = ip_hdr(skb); + switch (iph->protocol) { + case IPPROTO_TCP: + if (READ_ONCE(net->ipv4.sysctl_tcp_early_demux)) { + tcp_v4_early_demux(skb); + + /* must reload iph, skb->head might have changed */ + iph = ip_hdr(skb); + } + break; + case IPPROTO_UDP: + if (READ_ONCE(net->ipv4.sysctl_udp_early_demux)) { + err = udp_v4_early_demux(skb); + if (unlikely(err)) + goto drop_error; + + /* must reload iph, skb->head might have changed */ + iph = ip_hdr(skb); + } + break; } } diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index 1088564d4dbcb2490f25008a7872e9c7a378222e..77e3b67e8790bb32dddd85b1b8596f6890c550ec 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -424,7 +424,7 @@ clusterip_tg(struct sk_buff *skb, const struct xt_action_param *par) switch (ctinfo) { case IP_CT_NEW: - ct->mark = hash; + WRITE_ONCE(ct->mark, hash); break; case IP_CT_RELATED: case IP_CT_RELATED_REPLY: @@ -441,7 +441,7 @@ clusterip_tg(struct sk_buff *skb, const struct xt_action_param *par) #ifdef DEBUG nf_ct_dump_tuple_ip(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); #endif - pr_debug("hash=%u ct_hash=%u ", hash, ct->mark); + pr_debug("hash=%u ct_hash=%u ", hash, READ_ONCE(ct->mark)); if (!clusterip_responsible(cipinfo->config, hash)) { pr_debug("not responsible\n"); return NF_DROP; diff --git a/net/ipv4/netfilter/nft_fib_ipv4.c b/net/ipv4/netfilter/nft_fib_ipv4.c index 03df986217b7b70a63b17000399d6e7a8beba9e9..9e6f0f1275e2cb3817a731b400bcd3621fdfe47d 100644 --- a/net/ipv4/netfilter/nft_fib_ipv4.c +++ b/net/ipv4/netfilter/nft_fib_ipv4.c @@ -83,6 +83,9 @@ void nft_fib4_eval(const struct nft_expr *expr, struct nft_regs *regs, else oif = NULL; + if (priv->flags & NFTA_FIB_F_IIF) + fl4.flowi4_oif = l3mdev_master_ifindex_rcu(oif); + if (nft_hook(pkt) == NF_INET_PRE_ROUTING && nft_fib_is_loopback(pkt->skb, nft_in(pkt))) { nft_fib_store_result(dest, priv, nft_in(pkt)); diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index 2a17dc9413ae95e8310371d2ba3b26d102220c89..7a0102a4b1de7eba58086c8564b41c24b4c318d3 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -1346,7 +1346,7 @@ static int nh_create_ipv4(struct net *net, struct nexthop *nh, if (!err) { nh->nh_flags = fib_nh->fib_nh_flags; fib_info_update_nhc_saddr(net, &fib_nh->nh_common, - fib_nh->fib_nh_scope); + !fib_nh->fib_nh_scope ? 0 : fib_nh->fib_nh_scope - 1); } else { fib_nh_release(net, fib_nh); } diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index c089723489f2a5ac0c4ff1df856794c21740fb69..070fd0670d0011e1e8222a1238d4f5fc02ee0d9a 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -361,61 +361,6 @@ bad_key: return ret; } -static void proc_configure_early_demux(int enabled, int protocol) -{ - struct net_protocol *ipprot; -#if IS_ENABLED(CONFIG_IPV6) - struct inet6_protocol *ip6prot; -#endif - - rcu_read_lock(); - - ipprot = rcu_dereference(inet_protos[protocol]); - if (ipprot) - ipprot->early_demux = enabled ? ipprot->early_demux_handler : - NULL; - -#if IS_ENABLED(CONFIG_IPV6) - ip6prot = rcu_dereference(inet6_protos[protocol]); - if (ip6prot) - ip6prot->early_demux = enabled ? ip6prot->early_demux_handler : - NULL; -#endif - rcu_read_unlock(); -} - -static int proc_tcp_early_demux(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos) -{ - int ret = 0; - - ret = proc_dointvec(table, write, buffer, lenp, ppos); - - if (write && !ret) { - int enabled = init_net.ipv4.sysctl_tcp_early_demux; - - proc_configure_early_demux(enabled, IPPROTO_TCP); - } - - return ret; -} - -static int proc_udp_early_demux(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos) -{ - int ret = 0; - - ret = proc_dointvec(table, write, buffer, lenp, ppos); - - if (write && !ret) { - int enabled = init_net.ipv4.sysctl_udp_early_demux; - - proc_configure_early_demux(enabled, IPPROTO_UDP); - } - - return ret; -} - static int proc_tfo_blackhole_detect_timeout(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) @@ -685,14 +630,14 @@ static struct ctl_table ipv4_net_table[] = { .data = &init_net.ipv4.sysctl_udp_early_demux, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_udp_early_demux + .proc_handler = proc_douintvec_minmax, }, { .procname = "tcp_early_demux", .data = &init_net.ipv4.sysctl_tcp_early_demux, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_tcp_early_demux + .proc_handler = proc_douintvec_minmax, }, { .procname = "nexthop_compat_mode", diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index bfeb05f62b94fbeab51153a35dc56cab24ab30ae..cc588bc2b11d72f38339aa4b23168689e00ba586 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2796,6 +2796,8 @@ int tcp_disconnect(struct sock *sk, int flags) tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; tp->snd_cwnd = TCP_INIT_CWND; tp->snd_cwnd_cnt = 0; + tp->is_cwnd_limited = 0; + tp->max_packets_out = 0; tp->window_clamp = 0; tp->delivered = 0; tp->delivered_ce = 0; @@ -2814,8 +2816,7 @@ int tcp_disconnect(struct sock *sk, int flags) icsk->icsk_ack.rcv_mss = TCP_MIN_MSS; memset(&tp->rx_opt, 0, sizeof(tp->rx_opt)); __sk_dst_reset(sk); - dst_release(sk->sk_rx_dst); - sk->sk_rx_dst = NULL; + dst_release(xchg((__force struct dst_entry **)&sk->sk_rx_dst, NULL)); tcp_saved_syn_free(tp); tp->compressed_ack = 0; tp->segs_in = 0; @@ -3290,7 +3291,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, int optname, case TCP_REPAIR_OPTIONS: if (!tp->repair) err = -EINVAL; - else if (sk->sk_state == TCP_ESTABLISHED) + else if (sk->sk_state == TCP_ESTABLISHED && !tp->bytes_sent) err = tcp_repair_options_est(sk, optval, optlen); else err = -EPERM; @@ -4041,12 +4042,16 @@ static void __tcp_alloc_md5sig_pool(void) * to memory. See smp_rmb() in tcp_get_md5sig_pool() */ smp_wmb(); - tcp_md5sig_pool_populated = true; + /* Paired with READ_ONCE() from tcp_alloc_md5sig_pool() + * and tcp_get_md5sig_pool(). + */ + WRITE_ONCE(tcp_md5sig_pool_populated, true); } bool tcp_alloc_md5sig_pool(void) { - if (unlikely(!tcp_md5sig_pool_populated)) { + /* Paired with WRITE_ONCE() from __tcp_alloc_md5sig_pool() */ + if (unlikely(!READ_ONCE(tcp_md5sig_pool_populated))) { mutex_lock(&tcp_md5sig_mutex); if (!tcp_md5sig_pool_populated) { @@ -4057,7 +4062,8 @@ bool tcp_alloc_md5sig_pool(void) mutex_unlock(&tcp_md5sig_mutex); } - return tcp_md5sig_pool_populated; + /* Paired with WRITE_ONCE() from __tcp_alloc_md5sig_pool() */ + return READ_ONCE(tcp_md5sig_pool_populated); } EXPORT_SYMBOL(tcp_alloc_md5sig_pool); @@ -4073,7 +4079,8 @@ struct tcp_md5sig_pool *tcp_get_md5sig_pool(void) { local_bh_disable(); - if (tcp_md5sig_pool_populated) { + /* Paired with WRITE_ONCE() from __tcp_alloc_md5sig_pool() */ + if (READ_ONCE(tcp_md5sig_pool_populated)) { /* coupled with smp_wmb() in __tcp_alloc_md5sig_pool() */ smp_rmb(); return this_cpu_ptr(&tcp_md5sig_pool); diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index eaf2308c355a6ed9f9ecafc660f296fbbd1ea698..809ee0f32d598a91a4c7c8354fcef111a62e5188 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -315,7 +315,7 @@ static int tcp_bpf_send_verdict(struct sock *sk, struct sk_psock *psock, { bool cork = false, enospc = sk_msg_full(msg); struct sock *sk_redir; - u32 tosend, delta = 0; + u32 tosend, origsize, sent, delta = 0; u32 eval = __SK_NONE; int ret; @@ -370,10 +370,12 @@ more_data: cork = true; psock->cork = NULL; } - sk_msg_return(sk, msg, msg->sg.size); + sk_msg_return(sk, msg, tosend); release_sock(sk); + origsize = msg->sg.size; ret = tcp_bpf_sendmsg_redir(sk_redir, msg, tosend, flags); + sent = origsize - msg->sg.size; if (eval == __SK_REDIRECT) sock_put(sk_redir); @@ -412,7 +414,7 @@ more_data: msg->sg.data[msg->sg.start].page_link && msg->sg.data[msg->sg.start].length) { if (eval == __SK_REDIRECT) - sk_mem_charge(sk, msg->sg.size); + sk_mem_charge(sk, tosend - sent); goto more_data; } } diff --git a/net/ipv4/tcp_cdg.c b/net/ipv4/tcp_cdg.c index 709d23801823935b4eb2d3121b6e7ca1bdb08972..56dede4b59d95d19c973a090f27d5e15364ad7fc 100644 --- a/net/ipv4/tcp_cdg.c +++ b/net/ipv4/tcp_cdg.c @@ -375,6 +375,7 @@ static void tcp_cdg_init(struct sock *sk) struct cdg *ca = inet_csk_ca(sk); struct tcp_sock *tp = tcp_sk(sk); + ca->gradients = NULL; /* We silently fall back to window = 1 if allocation fails. */ if (window > 1) ca->gradients = kcalloc(window, sizeof(ca->gradients[0]), @@ -388,6 +389,7 @@ static void tcp_cdg_release(struct sock *sk) struct cdg *ca = inet_csk_ca(sk); kfree(ca->gradients); + ca->gradients = NULL; } static struct tcp_congestion_ops tcp_cdg __read_mostly = { diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 5db6a3e313d2ed8086f54fe20cb6a5216a3c368e..4a3926cae468e7dc24f41d5ae3d25f15fdae1f13 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2176,7 +2176,8 @@ void tcp_enter_loss(struct sock *sk) */ static bool tcp_check_sack_reneging(struct sock *sk, int flag) { - if (flag & FLAG_SACK_RENEGING) { + if (flag & FLAG_SACK_RENEGING && + flag & FLAG_SND_UNA_ADVANCED) { struct tcp_sock *tp = tcp_sk(sk); unsigned long delay = max(usecs_to_jiffies(tp->srtt_us >> 4), msecs_to_jiffies(10)); @@ -5779,7 +5780,7 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb) trace_tcp_probe(sk, skb); tcp_mstamp_refresh(tp); - if (unlikely(!sk->sk_rx_dst)) + if (unlikely(!rcu_access_pointer(sk->sk_rx_dst))) inet_csk(sk)->icsk_af_ops->sk_rx_dst_set(sk, skb); /* * Header prediction. diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 0d165ce2d80a75c40de306256a94a16dc3b0e43b..8bd7b1ec3b6a36af98d82f36404d5951910ddeee 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -322,6 +322,8 @@ failure: * if necessary. */ tcp_set_state(sk, TCP_CLOSE); + if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) + inet_reset_saddr(sk); ip_rt_put(rt); sk->sk_route_caps = 0; inet->inet_dport = 0; @@ -1670,15 +1672,18 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb) struct sock *rsk; if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */ - struct dst_entry *dst = sk->sk_rx_dst; + struct dst_entry *dst; + + dst = rcu_dereference_protected(sk->sk_rx_dst, + lockdep_sock_is_held(sk)); sock_rps_save_rxhash(sk, skb); sk_mark_napi_id(sk, skb); if (dst) { if (inet_sk(sk)->rx_dst_ifindex != skb->skb_iif || !dst->ops->check(dst, 0)) { + RCU_INIT_POINTER(sk->sk_rx_dst, NULL); dst_release(dst); - sk->sk_rx_dst = NULL; } } tcp_rcv_established(sk, skb); @@ -1753,7 +1758,7 @@ int tcp_v4_early_demux(struct sk_buff *skb) skb->sk = sk; skb->destructor = sock_edemux; if (sk_fullsock(sk)) { - struct dst_entry *dst = READ_ONCE(sk->sk_rx_dst); + struct dst_entry *dst = rcu_dereference(sk->sk_rx_dst); if (dst) dst = dst_check(dst, 0); @@ -1767,8 +1772,7 @@ int tcp_v4_early_demux(struct sk_buff *skb) bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb) { - u32 limit = READ_ONCE(sk->sk_rcvbuf) + READ_ONCE(sk->sk_sndbuf); - u32 tail_gso_size, tail_gso_segs; + u32 limit, tail_gso_size, tail_gso_segs; struct skb_shared_info *shinfo; const struct tcphdr *th; struct tcphdr *thtail; @@ -1871,11 +1875,13 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb) __skb_push(skb, hdrlen); no_coalesce: + limit = (u32)READ_ONCE(sk->sk_rcvbuf) + (u32)(READ_ONCE(sk->sk_sndbuf) >> 1); + /* Only socket owner can try to collapse/prune rx queues * to reduce memory overhead, so add a little headroom here. * Few sockets backlog are possibly concurrently non empty. */ - limit += 64*1024; + limit += 64 * 1024; if (unlikely(sk_add_backlog(sk, skb, limit))) { bh_unlock_sock(sk); @@ -2162,7 +2168,7 @@ void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb) struct dst_entry *dst = skb_dst(skb); if (dst && dst_hold_safe(dst)) { - sk->sk_rx_dst = dst; + rcu_assign_pointer(sk->sk_rx_dst, dst); inet_sk(sk)->rx_dst_ifindex = skb->skb_iif; } } diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 521aad1f731e12ad794ca34b3bcc0c77087ccd21..7c944ad5cfa19795826419ddb1714743afe470c5 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1876,15 +1876,20 @@ static void tcp_cwnd_validate(struct sock *sk, bool is_cwnd_limited) const struct tcp_congestion_ops *ca_ops = inet_csk(sk)->icsk_ca_ops; struct tcp_sock *tp = tcp_sk(sk); - /* Track the maximum number of outstanding packets in each - * window, and remember whether we were cwnd-limited then. + /* Track the strongest available signal of the degree to which the cwnd + * is fully utilized. If cwnd-limited then remember that fact for the + * current window. If not cwnd-limited then track the maximum number of + * outstanding packets in the current window. (If cwnd-limited then we + * chose to not update tp->max_packets_out to avoid an extra else + * clause with no functional impact.) */ if (!before(tp->snd_una, tp->max_packets_seq) || - tp->packets_out > tp->max_packets_out || - is_cwnd_limited) { - tp->max_packets_out = tp->packets_out; - tp->max_packets_seq = tp->snd_nxt; + is_cwnd_limited || + (!tp->is_cwnd_limited && + tp->packets_out > tp->max_packets_out)) { tp->is_cwnd_limited = is_cwnd_limited; + tp->max_packets_out = tp->packets_out; + tp->max_packets_seq= tp->snd_nxt; } if (tcp_is_cwnd_limited(sk)) { diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index e498c7666ec623ce5bf9979c70da81e17a3a9aff..b093daaa3deb93dbc28bbd7f2aadf46a9aa0eae6 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -446,7 +446,7 @@ static struct sock *udp4_lib_lookup2(struct net *net, result = lookup_reuseport(net, sk, skb, saddr, sport, daddr, hnum); /* Fall back to scoring if group has connections */ - if (result && !reuseport_has_conns(sk, false)) + if (result && !reuseport_has_conns(sk)) return result; result = result ? : sk; @@ -2193,7 +2193,7 @@ bool udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst) struct dst_entry *old; if (dst_hold_safe(dst)) { - old = xchg(&sk->sk_rx_dst, dst); + old = xchg((__force struct dst_entry **)&sk->sk_rx_dst, dst); dst_release(old); return old != dst; } @@ -2383,7 +2383,7 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, struct dst_entry *dst = skb_dst(skb); int ret; - if (unlikely(sk->sk_rx_dst != dst)) + if (unlikely(rcu_dereference(sk->sk_rx_dst) != dst)) udp_sk_rx_dst_set(sk, dst); ret = udp_unicast_rcv_skb(sk, skb, uh); @@ -2541,7 +2541,7 @@ int udp_v4_early_demux(struct sk_buff *skb) skb->sk = sk; skb->destructor = sock_efree; - dst = READ_ONCE(sk->sk_rx_dst); + dst = rcu_dereference(sk->sk_rx_dst); if (dst) dst = dst_check(dst, 0); diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c index 8a22486cf27020c93f94670ebb1ec1aa93c8fb19..17ac45aa7194ce9c148ed95e14dd575d17feeb98 100644 --- a/net/ipv6/addrlabel.c +++ b/net/ipv6/addrlabel.c @@ -437,6 +437,7 @@ static void ip6addrlbl_putmsg(struct nlmsghdr *nlh, { struct ifaddrlblmsg *ifal = nlmsg_data(nlh); ifal->ifal_family = AF_INET6; + ifal->__ifal_reserved = 0; ifal->ifal_prefixlen = prefixlen; ifal->ifal_flags = 0; ifal->ifal_index = ifindex; diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index fcb0c767a5a7f33714caf54850505a083755d64d..8df81060709630490faede580df74f21fcd73e39 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -663,7 +663,6 @@ int inet6_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, const struct proto_ops inet6_stream_ops = { .family = PF_INET6, - .flags = PROTO_CMSG_DATA_ONLY, .owner = THIS_MODULE, .release = inet6_release, .bind = inet6_bind, diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 206f66310a88d1d4e792dadc8e11553781fb6564..f4559e5bc84bfcced68cce819ff01ad1bb6156f8 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -256,7 +256,7 @@ ipv4_connected: goto out; } - reuseport_has_conns(sk, true); + reuseport_has_conns_set(sk); sk->sk_state = TCP_ESTABLISHED; sk_set_txhash(sk); out: diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c index 1c3f02d05d2bfdaad4e915a1dca29c9d71b310bf..7608be04d0f58e3553e1e83d6e788cc0cd12377b 100644 --- a/net/ipv6/esp6_offload.c +++ b/net/ipv6/esp6_offload.c @@ -343,6 +343,9 @@ static int esp6_xmit(struct xfrm_state *x, struct sk_buff *skb, netdev_features xo->seq.low += skb_shinfo(skb)->gso_segs; } + if (xo->seq.low < seq) + xo->seq.hi++; + esp.seqno = cpu_to_be64(xo->seq.low + ((u64)xo->seq.hi << 32)); len = skb->len - sizeof(struct ipv6hdr); diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 9e0890738d93f6171c5cfc58744c89d4c9e60361..0010f9e54f13b74a0e9be27862848abd1d93df47 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1153,14 +1153,16 @@ static void ip6gre_tnl_link_config_route(struct ip6_tnl *t, int set_mtu, dev->needed_headroom = dst_len; if (set_mtu) { - dev->mtu = rt->dst.dev->mtu - t_hlen; + int mtu = rt->dst.dev->mtu - t_hlen; + if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) - dev->mtu -= 8; + mtu -= 8; if (dev->type == ARPHRD_ETHER) - dev->mtu -= ETH_HLEN; + mtu -= ETH_HLEN; - if (dev->mtu < IPV6_MIN_MTU) - dev->mtu = IPV6_MIN_MTU; + if (mtu < IPV6_MIN_MTU) + mtu = IPV6_MIN_MTU; + WRITE_ONCE(dev->mtu, mtu); } } ip6_rt_put(rt); diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index 15ea3d082534d2e6616e3eaecc6623f2b453c12a..4eb9fbfdce332c763c44dddc222cea7a5cb38acc 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -44,21 +44,25 @@ #include #include -INDIRECT_CALLABLE_DECLARE(void udp_v6_early_demux(struct sk_buff *)); -INDIRECT_CALLABLE_DECLARE(void tcp_v6_early_demux(struct sk_buff *)); +void udp_v6_early_demux(struct sk_buff *); +void tcp_v6_early_demux(struct sk_buff *); static void ip6_rcv_finish_core(struct net *net, struct sock *sk, struct sk_buff *skb) { - void (*edemux)(struct sk_buff *skb); - - if (net->ipv4.sysctl_ip_early_demux && !skb_dst(skb) && skb->sk == NULL) { - const struct inet6_protocol *ipprot; - - ipprot = rcu_dereference(inet6_protos[ipv6_hdr(skb)->nexthdr]); - if (ipprot && (edemux = READ_ONCE(ipprot->early_demux))) - INDIRECT_CALL_2(edemux, tcp_v6_early_demux, - udp_v6_early_demux, skb); + if (READ_ONCE(net->ipv4.sysctl_ip_early_demux) && + !skb_dst(skb) && !skb->sk) { + switch (ipv6_hdr(skb)->nexthdr) { + case IPPROTO_TCP: + if (READ_ONCE(net->ipv4.sysctl_tcp_early_demux)) + tcp_v6_early_demux(skb); + break; + case IPPROTO_UDP: + if (READ_ONCE(net->ipv4.sysctl_udp_early_demux)) + udp_v6_early_demux(skb); + break; + } } + if (!skb_valid_dst(skb)) ip6_route_input(skb); } diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 3a2741569b84764797021a975345db6a687e1fc7..0d4cab94c5dd2c3ecb828e44ef5be7ce70669685 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1476,8 +1476,8 @@ static void ip6_tnl_link_config(struct ip6_tnl *t) struct net_device *tdev = NULL; struct __ip6_tnl_parm *p = &t->parms; struct flowi6 *fl6 = &t->fl.u.ip6; - unsigned int mtu; int t_hlen; + int mtu; memcpy(dev->dev_addr, &p->laddr, sizeof(struct in6_addr)); memcpy(dev->broadcast, &p->raddr, sizeof(struct in6_addr)); @@ -1524,12 +1524,13 @@ static void ip6_tnl_link_config(struct ip6_tnl *t) dev->hard_header_len = tdev->hard_header_len + t_hlen; mtu = min_t(unsigned int, tdev->mtu, IP6_MAX_MTU); - dev->mtu = mtu - t_hlen; + mtu = mtu - t_hlen; if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) - dev->mtu -= 8; + mtu -= 8; - if (dev->mtu < IPV6_MIN_MTU) - dev->mtu = IPV6_MIN_MTU; + if (mtu < IPV6_MIN_MTU) + mtu = IPV6_MIN_MTU; + WRITE_ONCE(dev->mtu, mtu); } } } diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 6fa118bf40cdde1f852c6213b4b260e07c360180..2017257cb278495e97befc9f0a30ee5a600c732e 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -417,6 +417,12 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, rtnl_lock(); lock_sock(sk); + /* Another thread has converted the socket into IPv4 with + * IPV6_ADDRFORM concurrently. + */ + if (unlikely(sk->sk_family != AF_INET6)) + goto unlock; + switch (optname) { case IPV6_ADDRFORM: @@ -976,6 +982,7 @@ done: break; } +unlock: release_sock(sk); if (needs_rtnl) rtnl_unlock(); diff --git a/net/ipv6/netfilter/nft_fib_ipv6.c b/net/ipv6/netfilter/nft_fib_ipv6.c index 92f3235fa2874016e90b575a0d0110e0d10100f9..602743f6dcee023b17e2df265fb4ed38faf70731 100644 --- a/net/ipv6/netfilter/nft_fib_ipv6.c +++ b/net/ipv6/netfilter/nft_fib_ipv6.c @@ -37,6 +37,9 @@ static int nft_fib6_flowi_init(struct flowi6 *fl6, const struct nft_fib *priv, if (ipv6_addr_type(&fl6->daddr) & IPV6_ADDR_LINKLOCAL) { lookup_flags |= RT6_LOOKUP_F_IFACE; fl6->flowi6_oif = get_ifindex(dev ? dev : pkt->skb->dev); + } else if ((priv->flags & NFTA_FIB_F_IIF) && + (netif_is_l3_master(dev) || netif_is_l3_slave(dev))) { + fl6->flowi6_oif = dev->ifindex; } if (ipv6_addr_type(&fl6->saddr) & IPV6_ADDR_UNICAST) @@ -193,7 +196,8 @@ void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs, if (rt->rt6i_flags & (RTF_REJECT | RTF_ANYCAST | RTF_LOCAL)) goto put_rt_err; - if (oif && oif != rt->rt6i_idev->dev) + if (oif && oif != rt->rt6i_idev->dev && + l3mdev_master_ifindex_rcu(rt->rt6i_idev->dev) != oif->ifindex) goto put_rt_err; nft_fib_store_result(dest, priv, rt->rt6i_idev->dev); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 955d53194e00356b650b17e292ef75e59cf572c9..5ee0eb2e47813abb963534ac68b94ffd00efb0fc 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -6381,10 +6381,16 @@ static void __net_exit ip6_route_net_exit(struct net *net) static int __net_init ip6_route_net_init_late(struct net *net) { #ifdef CONFIG_PROC_FS - proc_create_net("ipv6_route", 0, net->proc_net, &ipv6_route_seq_ops, - sizeof(struct ipv6_route_iter)); - proc_create_net_single("rt6_stats", 0444, net->proc_net, - rt6_stats_seq_show, NULL); + if (!proc_create_net("ipv6_route", 0, net->proc_net, + &ipv6_route_seq_ops, + sizeof(struct ipv6_route_iter))) + return -ENOMEM; + + if (!proc_create_net_single("rt6_stats", 0444, net->proc_net, + rt6_stats_seq_show, NULL)) { + remove_proc_entry("ipv6_route", net->proc_net); + return -ENOMEM; + } #endif return 0; } diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 3c92e8cacbbab8bc7e95e6815a55cd36eaf86d2c..1ce486a9bc07625869c66f713e8895a5294f88a4 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -1123,10 +1123,12 @@ static void ipip6_tunnel_bind_dev(struct net_device *dev) if (tdev && !netif_is_l3_master(tdev)) { int t_hlen = tunnel->hlen + sizeof(struct iphdr); + int mtu; - dev->mtu = tdev->mtu - t_hlen; - if (dev->mtu < IPV6_MIN_MTU) - dev->mtu = IPV6_MIN_MTU; + mtu = tdev->mtu - t_hlen; + if (mtu < IPV6_MIN_MTU) + mtu = IPV6_MIN_MTU; + WRITE_ONCE(dev->mtu, mtu); } } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 8d91f36cb11bc4a92ba28c36d5b1acd29039b47c..c599e14be414dedc31af758f0022a933ac64bd0b 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -107,7 +107,7 @@ static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb) if (dst && dst_hold_safe(dst)) { const struct rt6_info *rt = (const struct rt6_info *)dst; - sk->sk_rx_dst = dst; + rcu_assign_pointer(sk->sk_rx_dst, dst); inet_sk(sk)->rx_dst_ifindex = skb->skb_iif; tcp_inet6_sk(sk)->rx_dst_cookie = rt6_get_cookie(rt); } @@ -339,6 +339,8 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, late_failure: tcp_set_state(sk, TCP_CLOSE); + if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) + inet_reset_saddr(sk); failure: inet->inet_dport = 0; sk->sk_route_caps = 0; @@ -1482,15 +1484,18 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) opt_skb = skb_clone(skb, sk_gfp_mask(sk, GFP_ATOMIC)); if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */ - struct dst_entry *dst = sk->sk_rx_dst; + struct dst_entry *dst; + + dst = rcu_dereference_protected(sk->sk_rx_dst, + lockdep_sock_is_held(sk)); sock_rps_save_rxhash(sk, skb); sk_mark_napi_id(sk, skb); if (dst) { if (inet_sk(sk)->rx_dst_ifindex != skb->skb_iif || dst->ops->check(dst, np->rx_dst_cookie) == NULL) { + RCU_INIT_POINTER(sk->sk_rx_dst, NULL); dst_release(dst); - sk->sk_rx_dst = NULL; } } @@ -1815,7 +1820,7 @@ do_time_wait: goto discard_it; } -INDIRECT_CALLABLE_SCOPE void tcp_v6_early_demux(struct sk_buff *skb) +void tcp_v6_early_demux(struct sk_buff *skb) { const struct ipv6hdr *hdr; const struct tcphdr *th; @@ -1842,7 +1847,7 @@ INDIRECT_CALLABLE_SCOPE void tcp_v6_early_demux(struct sk_buff *skb) skb->sk = sk; skb->destructor = sock_edemux; if (sk_fullsock(sk)) { - struct dst_entry *dst = READ_ONCE(sk->sk_rx_dst); + struct dst_entry *dst = rcu_dereference(sk->sk_rx_dst); if (dst) dst = dst_check(dst, tcp_inet6_sk(sk)->rx_dst_cookie); @@ -2166,12 +2171,7 @@ struct proto tcpv6_prot = { }; EXPORT_SYMBOL_GPL(tcpv6_prot); -/* thinking of making this const? Don't. - * early_demux can change based on sysctl. - */ -static struct inet6_protocol tcpv6_protocol = { - .early_demux = tcp_v6_early_demux, - .early_demux_handler = tcp_v6_early_demux, +static const struct inet6_protocol tcpv6_protocol = { .handler = tcp_v6_rcv, .err_handler = tcp_v6_err, .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 4e90e5a529455e22da261a99085ea38d91c4c4de..1805cc5f7418b6269d4b1e52fc3f1443ac34cb6f 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -179,7 +179,7 @@ static struct sock *udp6_lib_lookup2(struct net *net, result = lookup_reuseport(net, sk, skb, saddr, sport, daddr, hnum); /* Fall back to scoring if group has connections */ - if (result && !reuseport_has_conns(sk, false)) + if (result && !reuseport_has_conns(sk)) return result; result = result ? : sk; @@ -941,7 +941,7 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, struct dst_entry *dst = skb_dst(skb); int ret; - if (unlikely(sk->sk_rx_dst != dst)) + if (unlikely(rcu_dereference(sk->sk_rx_dst) != dst)) udp6_sk_rx_dst_set(sk, dst); if (!uh->check && !udp_sk(sk)->no_check6_rx) { @@ -1027,7 +1027,7 @@ static struct sock *__udp6_lib_demux_lookup(struct net *net, return NULL; } -INDIRECT_CALLABLE_SCOPE void udp_v6_early_demux(struct sk_buff *skb) +void udp_v6_early_demux(struct sk_buff *skb) { struct net *net = dev_net(skb->dev); const struct udphdr *uh; @@ -1055,7 +1055,7 @@ INDIRECT_CALLABLE_SCOPE void udp_v6_early_demux(struct sk_buff *skb) skb->sk = sk; skb->destructor = sock_efree; - dst = READ_ONCE(sk->sk_rx_dst); + dst = rcu_dereference(sk->sk_rx_dst); if (dst) dst = dst_check(dst, inet6_sk(sk)->rx_dst_cookie); @@ -1640,12 +1640,7 @@ int udpv6_getsockopt(struct sock *sk, int level, int optname, return ipv6_getsockopt(sk, level, optname, optval, optlen); } -/* thinking of making this const? Don't. - * early_demux can change based on sysctl. - */ -static struct inet6_protocol udpv6_protocol = { - .early_demux = udp_v6_early_demux, - .early_demux_handler = udp_v6_early_demux, +static const struct inet6_protocol udpv6_protocol = { .handler = udpv6_rcv, .err_handler = udpv6_err, .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index af7a4b8b1e9c4a46a0b0cf4245a981efa24b9152..247296e3294bdd05ab3f4fe2733f4213435113e8 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -289,9 +289,13 @@ int __init xfrm6_init(void) if (ret) goto out_state; - register_pernet_subsys(&xfrm6_net_ops); + ret = register_pernet_subsys(&xfrm6_net_ops); + if (ret) + goto out_protocol; out: return ret; +out_protocol: + xfrm6_protocol_fini(); out_state: xfrm6_state_fini(); out_policy: diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index 18469f1f707e5dad8dd6c71463621cbe05dcad3b..32b516ab9c47561b1952b2dca0a860c457d1a2b1 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -161,7 +161,8 @@ static void kcm_rcv_ready(struct kcm_sock *kcm) /* Buffer limit is okay now, add to ready list */ list_add_tail(&kcm->wait_rx_list, &kcm->mux->kcm_rx_waiters); - kcm->rx_wait = true; + /* paired with lockless reads in kcm_rfree() */ + WRITE_ONCE(kcm->rx_wait, true); } static void kcm_rfree(struct sk_buff *skb) @@ -177,7 +178,7 @@ static void kcm_rfree(struct sk_buff *skb) /* For reading rx_wait and rx_psock without holding lock */ smp_mb__after_atomic(); - if (!kcm->rx_wait && !kcm->rx_psock && + if (!READ_ONCE(kcm->rx_wait) && !READ_ONCE(kcm->rx_psock) && sk_rmem_alloc_get(sk) < sk->sk_rcvlowat) { spin_lock_bh(&mux->rx_lock); kcm_rcv_ready(kcm); @@ -220,7 +221,7 @@ static void requeue_rx_msgs(struct kcm_mux *mux, struct sk_buff_head *head) struct sk_buff *skb; struct kcm_sock *kcm; - while ((skb = __skb_dequeue(head))) { + while ((skb = skb_dequeue(head))) { /* Reset destructor to avoid calling kcm_rcv_ready */ skb->destructor = sock_rfree; skb_orphan(skb); @@ -236,7 +237,8 @@ try_again: if (kcm_queue_rcv_skb(&kcm->sk, skb)) { /* Should mean socket buffer full */ list_del(&kcm->wait_rx_list); - kcm->rx_wait = false; + /* paired with lockless reads in kcm_rfree() */ + WRITE_ONCE(kcm->rx_wait, false); /* Commit rx_wait to read in kcm_free */ smp_wmb(); @@ -279,10 +281,12 @@ static struct kcm_sock *reserve_rx_kcm(struct kcm_psock *psock, kcm = list_first_entry(&mux->kcm_rx_waiters, struct kcm_sock, wait_rx_list); list_del(&kcm->wait_rx_list); - kcm->rx_wait = false; + /* paired with lockless reads in kcm_rfree() */ + WRITE_ONCE(kcm->rx_wait, false); psock->rx_kcm = kcm; - kcm->rx_psock = psock; + /* paired with lockless reads in kcm_rfree() */ + WRITE_ONCE(kcm->rx_psock, psock); spin_unlock_bh(&mux->rx_lock); @@ -309,7 +313,8 @@ static void unreserve_rx_kcm(struct kcm_psock *psock, spin_lock_bh(&mux->rx_lock); psock->rx_kcm = NULL; - kcm->rx_psock = NULL; + /* paired with lockless reads in kcm_rfree() */ + WRITE_ONCE(kcm->rx_psock, NULL); /* Commit kcm->rx_psock before sk_rmem_alloc_get to sync with * kcm_rfree @@ -1079,53 +1084,18 @@ out_error: return err; } -static struct sk_buff *kcm_wait_data(struct sock *sk, int flags, - long timeo, int *err) -{ - struct sk_buff *skb; - - while (!(skb = skb_peek(&sk->sk_receive_queue))) { - if (sk->sk_err) { - *err = sock_error(sk); - return NULL; - } - - if (sock_flag(sk, SOCK_DONE)) - return NULL; - - if ((flags & MSG_DONTWAIT) || !timeo) { - *err = -EAGAIN; - return NULL; - } - - sk_wait_data(sk, &timeo, NULL); - - /* Handle signals */ - if (signal_pending(current)) { - *err = sock_intr_errno(timeo); - return NULL; - } - } - - return skb; -} - static int kcm_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { + int noblock = flags & MSG_DONTWAIT; struct sock *sk = sock->sk; struct kcm_sock *kcm = kcm_sk(sk); int err = 0; - long timeo; struct strp_msg *stm; int copied = 0; struct sk_buff *skb; - timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); - - lock_sock(sk); - - skb = kcm_wait_data(sk, flags, timeo, &err); + skb = skb_recv_datagram(sk, flags, noblock, &err); if (!skb) goto out; @@ -1156,14 +1126,11 @@ msg_finished: /* Finished with message */ msg->msg_flags |= MSG_EOR; KCM_STATS_INCR(kcm->stats.rx_msgs); - skb_unlink(skb, &sk->sk_receive_queue); - kfree_skb(skb); } } out: - release_sock(sk); - + skb_free_datagram(sk, skb); return copied ? : err; } @@ -1171,9 +1138,9 @@ static ssize_t kcm_splice_read(struct socket *sock, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags) { + int noblock = flags & MSG_DONTWAIT; struct sock *sk = sock->sk; struct kcm_sock *kcm = kcm_sk(sk); - long timeo; struct strp_msg *stm; int err = 0; ssize_t copied; @@ -1181,11 +1148,7 @@ static ssize_t kcm_splice_read(struct socket *sock, loff_t *ppos, /* Only support splice for SOCKSEQPACKET */ - timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); - - lock_sock(sk); - - skb = kcm_wait_data(sk, flags, timeo, &err); + skb = skb_recv_datagram(sk, flags, noblock, &err); if (!skb) goto err_out; @@ -1213,13 +1176,11 @@ static ssize_t kcm_splice_read(struct socket *sock, loff_t *ppos, * finish reading the message. */ - release_sock(sk); - + skb_free_datagram(sk, skb); return copied; err_out: - release_sock(sk); - + skb_free_datagram(sk, skb); return err; } @@ -1239,7 +1200,8 @@ static void kcm_recv_disable(struct kcm_sock *kcm) if (!kcm->rx_psock) { if (kcm->rx_wait) { list_del(&kcm->wait_rx_list); - kcm->rx_wait = false; + /* paired with lockless reads in kcm_rfree() */ + WRITE_ONCE(kcm->rx_wait, false); } requeue_rx_msgs(mux, &kcm->sk.sk_receive_queue); @@ -1792,7 +1754,8 @@ static void kcm_done(struct kcm_sock *kcm) if (kcm->rx_wait) { list_del(&kcm->wait_rx_list); - kcm->rx_wait = false; + /* paired with lockless reads in kcm_rfree() */ + WRITE_ONCE(kcm->rx_wait, false); } /* Move any pending receive messages to other kcm sockets */ requeue_rx_msgs(mux, &sk->sk_receive_queue); @@ -1837,10 +1800,10 @@ static int kcm_release(struct socket *sock) kcm = kcm_sk(sk); mux = kcm->mux; + lock_sock(sk); sock_orphan(sk); kfree_skb(kcm->seq_skb); - lock_sock(sk); /* Purge queue under lock to avoid race condition with tx_work trying * to act when queue is nonempty. If tx_work runs after this point * it will just return. diff --git a/net/key/af_key.c b/net/key/af_key.c index 05e271098888303390444cdc6dbaf368cca3b33d..8bc7d399987b27c8ac27293691dde69f860219c0 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -2909,7 +2909,7 @@ static int count_ah_combs(const struct xfrm_tmpl *t) break; if (!aalg->pfkey_supported) continue; - if (aalg_tmpl_set(t, aalg) && aalg->available) + if (aalg_tmpl_set(t, aalg)) sz += sizeof(struct sadb_comb); } return sz + sizeof(struct sadb_prop); @@ -2927,7 +2927,7 @@ static int count_esp_combs(const struct xfrm_tmpl *t) if (!ealg->pfkey_supported) continue; - if (!(ealg_tmpl_set(t, ealg) && ealg->available)) + if (!(ealg_tmpl_set(t, ealg))) continue; for (k = 1; ; k++) { @@ -2938,16 +2938,17 @@ static int count_esp_combs(const struct xfrm_tmpl *t) if (!aalg->pfkey_supported) continue; - if (aalg_tmpl_set(t, aalg) && aalg->available) + if (aalg_tmpl_set(t, aalg)) sz += sizeof(struct sadb_comb); } } return sz + sizeof(struct sadb_prop); } -static void dump_ah_combs(struct sk_buff *skb, const struct xfrm_tmpl *t) +static int dump_ah_combs(struct sk_buff *skb, const struct xfrm_tmpl *t) { struct sadb_prop *p; + int sz = 0; int i; p = skb_put(skb, sizeof(struct sadb_prop)); @@ -2975,13 +2976,17 @@ static void dump_ah_combs(struct sk_buff *skb, const struct xfrm_tmpl *t) c->sadb_comb_soft_addtime = 20*60*60; c->sadb_comb_hard_usetime = 8*60*60; c->sadb_comb_soft_usetime = 7*60*60; + sz += sizeof(*c); } } + + return sz + sizeof(*p); } -static void dump_esp_combs(struct sk_buff *skb, const struct xfrm_tmpl *t) +static int dump_esp_combs(struct sk_buff *skb, const struct xfrm_tmpl *t) { struct sadb_prop *p; + int sz = 0; int i, k; p = skb_put(skb, sizeof(struct sadb_prop)); @@ -3023,8 +3028,11 @@ static void dump_esp_combs(struct sk_buff *skb, const struct xfrm_tmpl *t) c->sadb_comb_soft_addtime = 20*60*60; c->sadb_comb_hard_usetime = 8*60*60; c->sadb_comb_soft_usetime = 7*60*60; + sz += sizeof(*c); } } + + return sz + sizeof(*p); } static int key_notify_policy_expire(struct xfrm_policy *xp, const struct km_event *c) @@ -3154,6 +3162,7 @@ static int pfkey_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *t, struct struct sadb_x_sec_ctx *sec_ctx; struct xfrm_sec_ctx *xfrm_ctx; int ctx_size = 0; + int alg_size = 0; sockaddr_size = pfkey_sockaddr_size(x->props.family); if (!sockaddr_size) @@ -3165,16 +3174,16 @@ static int pfkey_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *t, struct sizeof(struct sadb_x_policy); if (x->id.proto == IPPROTO_AH) - size += count_ah_combs(t); + alg_size = count_ah_combs(t); else if (x->id.proto == IPPROTO_ESP) - size += count_esp_combs(t); + alg_size = count_esp_combs(t); if ((xfrm_ctx = x->security)) { ctx_size = PFKEY_ALIGN8(xfrm_ctx->ctx_len); size += sizeof(struct sadb_x_sec_ctx) + ctx_size; } - skb = alloc_skb(size + 16, GFP_ATOMIC); + skb = alloc_skb(size + alg_size + 16, GFP_ATOMIC); if (skb == NULL) return -ENOMEM; @@ -3228,10 +3237,13 @@ static int pfkey_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *t, struct pol->sadb_x_policy_priority = xp->priority; /* Set sadb_comb's. */ + alg_size = 0; if (x->id.proto == IPPROTO_AH) - dump_ah_combs(skb, t); + alg_size = dump_ah_combs(skb, t); else if (x->id.proto == IPPROTO_ESP) - dump_esp_combs(skb, t); + alg_size = dump_esp_combs(skb, t); + + hdr->sadb_msg_len += alg_size / 8; /* security context */ if (xfrm_ctx) { diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 561b6d67ab8b933628d38f5309e2b1482787937b..dc8987ed08adbf7f81e1131069a43d088df27001 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -1480,11 +1480,15 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net, tunnel->l2tp_net = net; pn = l2tp_pernet(net); + sk = sock->sk; + sock_hold(sk); + tunnel->sock = sk; + spin_lock_bh(&pn->l2tp_tunnel_list_lock); list_for_each_entry(tunnel_walk, &pn->l2tp_tunnel_list, list) { if (tunnel_walk->tunnel_id == tunnel->tunnel_id) { spin_unlock_bh(&pn->l2tp_tunnel_list_lock); - + sock_put(sk); ret = -EEXIST; goto err_sock; } @@ -1492,10 +1496,6 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net, list_add_rcu(&tunnel->list, &pn->l2tp_tunnel_list); spin_unlock_bh(&pn->l2tp_tunnel_list_lock); - sk = sock->sk; - sock_hold(sk); - tunnel->sock = sk; - if (tunnel->encap == L2TP_ENCAPTYPE_UDP) { struct udp_tunnel_sock_cfg udp_cfg = { .sk_user_data = tunnel, diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 8010967a68741447924990329b686f7e853a6ec7..c6a7f1c99abc59252e6af21051dc09357a4bb0fc 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -3357,9 +3357,6 @@ static int ieee80211_set_csa_beacon(struct ieee80211_sub_if_data *sdata, case NL80211_IFTYPE_MESH_POINT: { struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; - if (params->chandef.width != sdata->vif.bss_conf.chandef.width) - return -EINVAL; - /* changes into another band are not supported */ if (sdata->vif.bss_conf.chandef.chan->band != params->chandef.chan->band) diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 73893025922fd361ebc738cce0ea9c64856b3b80..ae90ac3be59aadcba9f30d53b081b94e92116772 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -1349,8 +1349,10 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) ieee80211_led_exit(local); destroy_workqueue(local->workqueue); fail_workqueue: - if (local->wiphy_ciphers_allocated) + if (local->wiphy_ciphers_allocated) { kfree(local->hw.wiphy->cipher_suites); + local->wiphy_ciphers_allocated = false; + } kfree(local->int_scan_req); return result; } @@ -1420,8 +1422,10 @@ void ieee80211_free_hw(struct ieee80211_hw *hw) mutex_destroy(&local->iflist_mtx); mutex_destroy(&local->mtx); - if (local->wiphy_ciphers_allocated) + if (local->wiphy_ciphers_allocated) { kfree(local->hw.wiphy->cipher_suites); + local->wiphy_ciphers_allocated = false; + } idr_for_each(&local->ack_status_frames, ieee80211_free_ack_frame, NULL); diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c index 870c8eafef92910d9ebc8e5e555c322250ba5b6a..c2b051e0610ab726592ac2bb503e83165f67e5b6 100644 --- a/net/mac80211/mesh_pathtbl.c +++ b/net/mac80211/mesh_pathtbl.c @@ -718,7 +718,7 @@ int mesh_path_send_to_gates(struct mesh_path *mpath) void mesh_path_discard_frame(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb) { - kfree_skb(skb); + ieee80211_free_txskb(&sdata->local->hw, skb); sdata->u.mesh.mshstats.dropped_frames_no_route++; } diff --git a/net/mac802154/rx.c b/net/mac802154/rx.c index c439125ef2b91353eee3e978bea337bdebbd6394..726b47a4611b582bef8fa970869939add2d32d85 100644 --- a/net/mac802154/rx.c +++ b/net/mac802154/rx.c @@ -132,7 +132,7 @@ static int ieee802154_parse_frame_start(struct sk_buff *skb, struct ieee802154_hdr *hdr) { int hlen; - struct ieee802154_mac_cb *cb = mac_cb_init(skb); + struct ieee802154_mac_cb *cb = mac_cb(skb); skb_reset_mac_header(skb); @@ -294,8 +294,9 @@ void ieee802154_rx_irqsafe(struct ieee802154_hw *hw, struct sk_buff *skb, u8 lqi) { struct ieee802154_local *local = hw_to_local(hw); + struct ieee802154_mac_cb *cb = mac_cb_init(skb); - mac_cb(skb)->lqi = lqi; + cb->lqi = lqi; skb->pkt_type = IEEE802154_RX_MSG; skb_queue_tail(&local->skb_queue, skb); tasklet_schedule(&local->tasklet); diff --git a/net/netfilter/ipset/ip_set_hash_ip.c b/net/netfilter/ipset/ip_set_hash_ip.c index 5d6d68eaf6a9c70a28a9252dbd781f013f51da69..d7a81b2250e71bb95942b69aa0ba4675463daab2 100644 --- a/net/netfilter/ipset/ip_set_hash_ip.c +++ b/net/netfilter/ipset/ip_set_hash_ip.c @@ -131,8 +131,11 @@ hash_ip4_uadt(struct ip_set *set, struct nlattr *tb[], ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP_TO], &ip_to); if (ret) return ret; - if (ip > ip_to) + if (ip > ip_to) { + if (ip_to == 0) + return -IPSET_ERR_HASH_ELEM; swap(ip, ip_to); + } } else if (tb[IPSET_ATTR_CIDR]) { u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); @@ -143,18 +146,20 @@ hash_ip4_uadt(struct ip_set *set, struct nlattr *tb[], hosts = h->netmask == 32 ? 1 : 2 << (32 - h->netmask - 1); - if (retried) { + /* 64bit division is not allowed on 32bit */ + if (((u64)ip_to - ip + 1) >> (32 - h->netmask) > IPSET_MAX_RANGE) + return -ERANGE; + + if (retried) ip = ntohl(h->next.ip); - e.ip = htonl(ip); - } for (; ip <= ip_to;) { + e.ip = htonl(ip); ret = adtfn(set, &e, &ext, &ext, flags); if (ret && !ip_set_eexist(ret, flags)) return ret; ip += hosts; - e.ip = htonl(ip); - if (e.ip == 0) + if (ip == 0) return 0; ret = 0; diff --git a/net/netfilter/ipset/ip_set_hash_ipmark.c b/net/netfilter/ipset/ip_set_hash_ipmark.c index aba1df617d6e6e3f692329906d37b54a550f99ec..eefce34a34f08384ce96200c19fb52db67565bb9 100644 --- a/net/netfilter/ipset/ip_set_hash_ipmark.c +++ b/net/netfilter/ipset/ip_set_hash_ipmark.c @@ -120,6 +120,8 @@ hash_ipmark4_uadt(struct ip_set *set, struct nlattr *tb[], e.mark = ntohl(nla_get_be32(tb[IPSET_ATTR_MARK])); e.mark &= h->markmask; + if (e.mark == 0 && e.ip == 0) + return -IPSET_ERR_HASH_ELEM; if (adt == IPSET_TEST || !(tb[IPSET_ATTR_IP_TO] || tb[IPSET_ATTR_CIDR])) { @@ -132,8 +134,11 @@ hash_ipmark4_uadt(struct ip_set *set, struct nlattr *tb[], ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP_TO], &ip_to); if (ret) return ret; - if (ip > ip_to) + if (ip > ip_to) { + if (e.mark == 0 && ip_to == 0) + return -IPSET_ERR_HASH_ELEM; swap(ip, ip_to); + } } else if (tb[IPSET_ATTR_CIDR]) { u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); @@ -142,6 +147,9 @@ hash_ipmark4_uadt(struct ip_set *set, struct nlattr *tb[], ip_set_mask_from_to(ip, ip_to, cidr); } + if (((u64)ip_to - ip + 1) > IPSET_MAX_RANGE) + return -ERANGE; + if (retried) ip = ntohl(h->next.ip); for (; ip <= ip_to; ip++) { diff --git a/net/netfilter/ipset/ip_set_hash_ipport.c b/net/netfilter/ipset/ip_set_hash_ipport.c index 1ff228717e2989239f384f83f046a3ad21578dc1..4a54e9e8ae59f0560a34261dd02361a426d5de4a 100644 --- a/net/netfilter/ipset/ip_set_hash_ipport.c +++ b/net/netfilter/ipset/ip_set_hash_ipport.c @@ -172,6 +172,9 @@ hash_ipport4_uadt(struct ip_set *set, struct nlattr *tb[], swap(port, port_to); } + if (((u64)ip_to - ip + 1)*(port_to - port + 1) > IPSET_MAX_RANGE) + return -ERANGE; + if (retried) ip = ntohl(h->next.ip); for (; ip <= ip_to; ip++) { diff --git a/net/netfilter/ipset/ip_set_hash_ipportip.c b/net/netfilter/ipset/ip_set_hash_ipportip.c index fa88afd812fa6067fae9c7d89584d9324fb89102..09737de5ecc34cb0ae9af44c22e22d0723056ed2 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportip.c +++ b/net/netfilter/ipset/ip_set_hash_ipportip.c @@ -179,6 +179,9 @@ hash_ipportip4_uadt(struct ip_set *set, struct nlattr *tb[], swap(port, port_to); } + if (((u64)ip_to - ip + 1)*(port_to - port + 1) > IPSET_MAX_RANGE) + return -ERANGE; + if (retried) ip = ntohl(h->next.ip); for (; ip <= ip_to; ip++) { diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c index eef6ecfcb40990da4012da2bf3dee53bd415980e..02685371a68289c09f752bfdfdc5bd0858841303 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportnet.c +++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c @@ -252,6 +252,9 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[], swap(port, port_to); } + if (((u64)ip_to - ip + 1)*(port_to - port + 1) > IPSET_MAX_RANGE) + return -ERANGE; + ip2_to = ip2_from; if (tb[IPSET_ATTR_IP2_TO]) { ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP2_TO], &ip2_to); diff --git a/net/netfilter/ipset/ip_set_hash_net.c b/net/netfilter/ipset/ip_set_hash_net.c index 136cf0781d3a4beff4bf7692d156f0f30e627c15..9d1beaacb9730c24e3d4ae493a15b45d2c881eea 100644 --- a/net/netfilter/ipset/ip_set_hash_net.c +++ b/net/netfilter/ipset/ip_set_hash_net.c @@ -139,7 +139,7 @@ hash_net4_uadt(struct ip_set *set, struct nlattr *tb[], ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_net4_elem e = { .cidr = HOST_MASK }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); - u32 ip = 0, ip_to = 0; + u32 ip = 0, ip_to = 0, ipn, n = 0; int ret; if (tb[IPSET_ATTR_LINENO]) @@ -187,6 +187,15 @@ hash_net4_uadt(struct ip_set *set, struct nlattr *tb[], if (ip + UINT_MAX == ip_to) return -IPSET_ERR_HASH_RANGE; } + ipn = ip; + do { + ipn = ip_set_range_to_cidr(ipn, ip_to, &e.cidr); + n++; + } while (ipn++ < ip_to); + + if (n > IPSET_MAX_RANGE) + return -ERANGE; + if (retried) ip = ntohl(h->next.ip); do { diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c index be5e95a0d8762fb3381650aba7831bdc69eae934..c3ada9c63fa3873e4badb459a59119dd1140fb3d 100644 --- a/net/netfilter/ipset/ip_set_hash_netiface.c +++ b/net/netfilter/ipset/ip_set_hash_netiface.c @@ -201,7 +201,7 @@ hash_netiface4_uadt(struct ip_set *set, struct nlattr *tb[], ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netiface4_elem e = { .cidr = HOST_MASK, .elem = 1 }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); - u32 ip = 0, ip_to = 0; + u32 ip = 0, ip_to = 0, ipn, n = 0; int ret; if (tb[IPSET_ATTR_LINENO]) @@ -255,6 +255,14 @@ hash_netiface4_uadt(struct ip_set *set, struct nlattr *tb[], } else { ip_set_mask_from_to(ip, ip_to, e.cidr); } + ipn = ip; + do { + ipn = ip_set_range_to_cidr(ipn, ip_to, &e.cidr); + n++; + } while (ipn++ < ip_to); + + if (n > IPSET_MAX_RANGE) + return -ERANGE; if (retried) ip = ntohl(h->next.ip); diff --git a/net/netfilter/ipset/ip_set_hash_netnet.c b/net/netfilter/ipset/ip_set_hash_netnet.c index da4ef910b12d10c6ef74f3a1d9cdcb9a72ba8fa7..b1411bc91a404b82d12f51a1b3cf5cddc0ff1d07 100644 --- a/net/netfilter/ipset/ip_set_hash_netnet.c +++ b/net/netfilter/ipset/ip_set_hash_netnet.c @@ -167,7 +167,8 @@ hash_netnet4_uadt(struct ip_set *set, struct nlattr *tb[], struct hash_netnet4_elem e = { }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); u32 ip = 0, ip_to = 0; - u32 ip2 = 0, ip2_from = 0, ip2_to = 0; + u32 ip2 = 0, ip2_from = 0, ip2_to = 0, ipn; + u64 n = 0, m = 0; int ret; if (tb[IPSET_ATTR_LINENO]) @@ -243,6 +244,19 @@ hash_netnet4_uadt(struct ip_set *set, struct nlattr *tb[], } else { ip_set_mask_from_to(ip2_from, ip2_to, e.cidr[1]); } + ipn = ip; + do { + ipn = ip_set_range_to_cidr(ipn, ip_to, &e.cidr[0]); + n++; + } while (ipn++ < ip_to); + ipn = ip2_from; + do { + ipn = ip_set_range_to_cidr(ipn, ip2_to, &e.cidr[1]); + m++; + } while (ipn++ < ip2_to); + + if (n*m > IPSET_MAX_RANGE) + return -ERANGE; if (retried) { ip = ntohl(h->next.ip[0]); diff --git a/net/netfilter/ipset/ip_set_hash_netport.c b/net/netfilter/ipset/ip_set_hash_netport.c index 34448df80fb98a3134e3acb972eabb29774582af..d26d13528fe8bc9ff3ecdac02b553171f8d4e552 100644 --- a/net/netfilter/ipset/ip_set_hash_netport.c +++ b/net/netfilter/ipset/ip_set_hash_netport.c @@ -157,7 +157,8 @@ hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[], ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netport4_elem e = { .cidr = HOST_MASK - 1 }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); - u32 port, port_to, p = 0, ip = 0, ip_to = 0; + u32 port, port_to, p = 0, ip = 0, ip_to = 0, ipn; + u64 n = 0; bool with_ports = false; u8 cidr; int ret; @@ -234,6 +235,14 @@ hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[], } else { ip_set_mask_from_to(ip, ip_to, e.cidr + 1); } + ipn = ip; + do { + ipn = ip_set_range_to_cidr(ipn, ip_to, &cidr); + n++; + } while (ipn++ < ip_to); + + if (n*(port_to - port + 1) > IPSET_MAX_RANGE) + return -ERANGE; if (retried) { ip = ntohl(h->next.ip); diff --git a/net/netfilter/ipset/ip_set_hash_netportnet.c b/net/netfilter/ipset/ip_set_hash_netportnet.c index 934c1712cba853716694ce60846f1d700a4696de..6446f4fccc72983539b1d50b2f7e92b67f33102f 100644 --- a/net/netfilter/ipset/ip_set_hash_netportnet.c +++ b/net/netfilter/ipset/ip_set_hash_netportnet.c @@ -181,7 +181,8 @@ hash_netportnet4_uadt(struct ip_set *set, struct nlattr *tb[], struct hash_netportnet4_elem e = { }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); u32 ip = 0, ip_to = 0, p = 0, port, port_to; - u32 ip2_from = 0, ip2_to = 0, ip2; + u32 ip2_from = 0, ip2_to = 0, ip2, ipn; + u64 n = 0, m = 0; bool with_ports = false; int ret; @@ -283,6 +284,19 @@ hash_netportnet4_uadt(struct ip_set *set, struct nlattr *tb[], } else { ip_set_mask_from_to(ip2_from, ip2_to, e.cidr[1]); } + ipn = ip; + do { + ipn = ip_set_range_to_cidr(ipn, ip_to, &e.cidr[0]); + n++; + } while (ipn++ < ip_to); + ipn = ip2_from; + do { + ipn = ip_set_range_to_cidr(ipn, ip2_to, &e.cidr[1]); + m++; + } while (ipn++ < ip2_to); + + if (n*m*(port_to - port + 1) > IPSET_MAX_RANGE) + return -ERANGE; if (retried) { ip = ntohl(h->next.ip[0]); diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c index f9b16f2b221918f1be0ae6bd8da118b2046670a2..fdacbc3c15bef972cbc8237add6567d3123d3354 100644 --- a/net/netfilter/ipvs/ip_vs_app.c +++ b/net/netfilter/ipvs/ip_vs_app.c @@ -599,13 +599,19 @@ static const struct seq_operations ip_vs_app_seq_ops = { int __net_init ip_vs_app_net_init(struct netns_ipvs *ipvs) { INIT_LIST_HEAD(&ipvs->app_list); - proc_create_net("ip_vs_app", 0, ipvs->net->proc_net, &ip_vs_app_seq_ops, - sizeof(struct seq_net_private)); +#ifdef CONFIG_PROC_FS + if (!proc_create_net("ip_vs_app", 0, ipvs->net->proc_net, + &ip_vs_app_seq_ops, + sizeof(struct seq_net_private))) + return -ENOMEM; +#endif return 0; } void __net_exit ip_vs_app_net_cleanup(struct netns_ipvs *ipvs) { unregister_ip_vs_app(ipvs, NULL /* all */); +#ifdef CONFIG_PROC_FS remove_proc_entry("ip_vs_app", ipvs->net->proc_net); +#endif } diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index fb67f1ca2495b3e5e157d72608d0b6916a49bc61..cb6d68220c26534c0f6f0f1ca488b71e0b221746 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -1265,8 +1265,8 @@ static inline int todrop_entry(struct ip_vs_conn *cp) * The drop rate array needs tuning for real environments. * Called from timer bh only => no locking */ - static const char todrop_rate[9] = {0, 1, 2, 3, 4, 5, 6, 7, 8}; - static char todrop_counter[9] = {0}; + static const signed char todrop_rate[9] = {0, 1, 2, 3, 4, 5, 6, 7, 8}; + static signed char todrop_counter[9] = {0}; int i; /* if the conn entry hasn't lasted for 60 seconds, don't drop it. @@ -1447,20 +1447,36 @@ int __net_init ip_vs_conn_net_init(struct netns_ipvs *ipvs) { atomic_set(&ipvs->conn_count, 0); - proc_create_net("ip_vs_conn", 0, ipvs->net->proc_net, - &ip_vs_conn_seq_ops, sizeof(struct ip_vs_iter_state)); - proc_create_net("ip_vs_conn_sync", 0, ipvs->net->proc_net, - &ip_vs_conn_sync_seq_ops, - sizeof(struct ip_vs_iter_state)); +#ifdef CONFIG_PROC_FS + if (!proc_create_net("ip_vs_conn", 0, ipvs->net->proc_net, + &ip_vs_conn_seq_ops, + sizeof(struct ip_vs_iter_state))) + goto err_conn; + + if (!proc_create_net("ip_vs_conn_sync", 0, ipvs->net->proc_net, + &ip_vs_conn_sync_seq_ops, + sizeof(struct ip_vs_iter_state))) + goto err_conn_sync; +#endif + return 0; + +#ifdef CONFIG_PROC_FS +err_conn_sync: + remove_proc_entry("ip_vs_conn", ipvs->net->proc_net); +err_conn: + return -ENOMEM; +#endif } void __net_exit ip_vs_conn_net_cleanup(struct netns_ipvs *ipvs) { /* flush all the connection entries first */ ip_vs_conn_flush(ipvs); +#ifdef CONFIG_PROC_FS remove_proc_entry("ip_vs_conn", ipvs->net->proc_net); remove_proc_entry("ip_vs_conn_sync", ipvs->net->proc_net); +#endif } int __init ip_vs_conn_init(void) diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 9b88e4c04af1e904ae3fcb4fee61db71ae88778d..8d27c7ac271ff907f88af82fff3ce4f955a2b1d9 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1602,7 +1602,7 @@ init_conntrack(struct net *net, struct nf_conn *tmpl, } #ifdef CONFIG_NF_CONNTRACK_MARK - ct->mark = exp->master->mark; + ct->mark = READ_ONCE(exp->master->mark); #endif #ifdef CONFIG_NF_CONNTRACK_SECMARK ct->secmark = exp->master->secmark; diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 9e6898164199bd55c34686eaf3975c814953407d..c402283e7545bb0f45f40f8b0cae17d468518de2 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -317,9 +317,9 @@ nla_put_failure: } #ifdef CONFIG_NF_CONNTRACK_MARK -static int ctnetlink_dump_mark(struct sk_buff *skb, const struct nf_conn *ct) +static int ctnetlink_dump_mark(struct sk_buff *skb, u32 mark) { - if (nla_put_be32(skb, CTA_MARK, htonl(ct->mark))) + if (nla_put_be32(skb, CTA_MARK, htonl(mark))) goto nla_put_failure; return 0; @@ -532,7 +532,7 @@ static int ctnetlink_dump_extinfo(struct sk_buff *skb, static int ctnetlink_dump_info(struct sk_buff *skb, struct nf_conn *ct) { if (ctnetlink_dump_status(skb, ct) < 0 || - ctnetlink_dump_mark(skb, ct) < 0 || + ctnetlink_dump_mark(skb, READ_ONCE(ct->mark)) < 0 || ctnetlink_dump_secctx(skb, ct) < 0 || ctnetlink_dump_id(skb, ct) < 0 || ctnetlink_dump_use(skb, ct) < 0 || @@ -711,6 +711,7 @@ ctnetlink_conntrack_event(unsigned int events, struct nf_ct_event *item) struct sk_buff *skb; unsigned int type; unsigned int flags = 0, group; + u32 mark; int err; if (events & (1 << IPCT_DESTROY)) { @@ -811,8 +812,9 @@ ctnetlink_conntrack_event(unsigned int events, struct nf_ct_event *item) } #ifdef CONFIG_NF_CONNTRACK_MARK - if ((events & (1 << IPCT_MARK) || ct->mark) - && ctnetlink_dump_mark(skb, ct) < 0) + mark = READ_ONCE(ct->mark); + if ((events & (1 << IPCT_MARK) || mark) && + ctnetlink_dump_mark(skb, mark) < 0) goto nla_put_failure; #endif nlmsg_end(skb, nlh); @@ -1099,7 +1101,7 @@ static int ctnetlink_filter_match(struct nf_conn *ct, void *data) } #ifdef CONFIG_NF_CONNTRACK_MARK - if ((ct->mark & filter->mark.mask) != filter->mark.val) + if ((READ_ONCE(ct->mark) & filter->mark.mask) != filter->mark.val) goto ignore_entry; #endif @@ -1979,9 +1981,9 @@ static void ctnetlink_change_mark(struct nf_conn *ct, mask = ~ntohl(nla_get_be32(cda[CTA_MARK_MASK])); mark = ntohl(nla_get_be32(cda[CTA_MARK])); - newmark = (ct->mark & mask) ^ mark; - if (newmark != ct->mark) - ct->mark = newmark; + newmark = (READ_ONCE(ct->mark) & mask) ^ mark; + if (newmark != READ_ONCE(ct->mark)) + WRITE_ONCE(ct->mark, newmark); } #endif @@ -2669,6 +2671,7 @@ static int __ctnetlink_glue_build(struct sk_buff *skb, struct nf_conn *ct) { const struct nf_conntrack_zone *zone; struct nlattr *nest_parms; + u32 mark; zone = nf_ct_zone(ct); @@ -2726,7 +2729,8 @@ static int __ctnetlink_glue_build(struct sk_buff *skb, struct nf_conn *ct) goto nla_put_failure; #ifdef CONFIG_NF_CONNTRACK_MARK - if (ct->mark && ctnetlink_dump_mark(skb, ct) < 0) + mark = READ_ONCE(ct->mark); + if (mark && ctnetlink_dump_mark(skb, mark) < 0) goto nla_put_failure; #endif if (ctnetlink_dump_labels(skb, ct) < 0) diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 313d1c8ff066adb3b45f25321b5c89d9a06558d0..a7f88cdf3f87c487a3a2d1adb093e070ca0a4727 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -360,7 +360,7 @@ static int ct_seq_show(struct seq_file *s, void *v) goto release; #if defined(CONFIG_NF_CONNTRACK_MARK) - seq_printf(s, "mark=%u ", ct->mark); + seq_printf(s, "mark=%u ", READ_ONCE(ct->mark)); #endif ct_show_secctx(s, ct); diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c index d1862782be450307f5a392e7d22d688393031a0d..28306cb667190b9e9a833e9ca5bffd9912600f7b 100644 --- a/net/netfilter/nf_flow_table_offload.c +++ b/net/netfilter/nf_flow_table_offload.c @@ -910,6 +910,7 @@ static int nf_flow_table_block_setup(struct nf_flowtable *flowtable, struct flow_block_cb *block_cb, *next; int err = 0; + down_write(&flowtable->flow_block_lock); switch (cmd) { case FLOW_BLOCK_BIND: list_splice(&bo->cb_list, &flowtable->flow_block.cb_list); @@ -924,6 +925,7 @@ static int nf_flow_table_block_setup(struct nf_flowtable *flowtable, WARN_ON_ONCE(1); err = -EOPNOTSUPP; } + up_write(&flowtable->flow_block_lock); return err; } @@ -980,7 +982,9 @@ static int nf_flow_table_offload_cmd(struct flow_block_offload *bo, nf_flow_table_block_offload_init(bo, dev_net(dev), cmd, flowtable, extack); + down_write(&flowtable->flow_block_lock); err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_FT, bo); + up_write(&flowtable->flow_block_lock); if (err < 0) return err; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 810995d712ac7ee2083e2c3e495d24b72c21b682..2143edafba772aeeb23f47265b0653bdfab7dab1 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -7527,9 +7527,6 @@ static void nft_commit_release(struct nft_trans *trans) nf_tables_chain_destroy(&trans->ctx); break; case NFT_MSG_DELRULE: - if (trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD) - nft_flow_rule_destroy(nft_trans_flow_rule(trans)); - nf_tables_rule_destroy(&trans->ctx, nft_trans_rule(trans)); break; case NFT_MSG_DELSET: @@ -7973,6 +7970,9 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nft_rule_expr_deactivate(&trans->ctx, nft_trans_rule(trans), NFT_TRANS_COMMIT); + + if (trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD) + nft_flow_rule_destroy(nft_trans_flow_rule(trans)); break; case NFT_MSG_NEWSET: nft_clear(net, nft_trans_set(trans)); diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index 781118465d466583140692d492b8200a18640590..14093d86e6823264c68372d387e1a84275740266 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -97,7 +97,7 @@ static void nft_ct_get_eval(const struct nft_expr *expr, return; #ifdef CONFIG_NF_CONNTRACK_MARK case NFT_CT_MARK: - *dest = ct->mark; + *dest = READ_ONCE(ct->mark); return; #endif #ifdef CONFIG_NF_CONNTRACK_SECMARK @@ -294,8 +294,8 @@ static void nft_ct_set_eval(const struct nft_expr *expr, switch (priv->key) { #ifdef CONFIG_NF_CONNTRACK_MARK case NFT_CT_MARK: - if (ct->mark != value) { - ct->mark = value; + if (READ_ONCE(ct->mark) != value) { + WRITE_ONCE(ct->mark, value); nf_conntrack_event_cache(IPCT_MARK, ct); } break; diff --git a/net/netfilter/xt_connmark.c b/net/netfilter/xt_connmark.c index e5ebc0810675a98c54a0ae0f2b961d3ab35d2055..ad3c033db64e70dd642a63e9b48914fc0ac12cb9 100644 --- a/net/netfilter/xt_connmark.c +++ b/net/netfilter/xt_connmark.c @@ -30,6 +30,7 @@ connmark_tg_shift(struct sk_buff *skb, const struct xt_connmark_tginfo2 *info) u_int32_t new_targetmark; struct nf_conn *ct; u_int32_t newmark; + u_int32_t oldmark; ct = nf_ct_get(skb, &ctinfo); if (ct == NULL) @@ -37,14 +38,15 @@ connmark_tg_shift(struct sk_buff *skb, const struct xt_connmark_tginfo2 *info) switch (info->mode) { case XT_CONNMARK_SET: - newmark = (ct->mark & ~info->ctmask) ^ info->ctmark; + oldmark = READ_ONCE(ct->mark); + newmark = (oldmark & ~info->ctmask) ^ info->ctmark; if (info->shift_dir == D_SHIFT_RIGHT) newmark >>= info->shift_bits; else newmark <<= info->shift_bits; - if (ct->mark != newmark) { - ct->mark = newmark; + if (READ_ONCE(ct->mark) != newmark) { + WRITE_ONCE(ct->mark, newmark); nf_conntrack_event_cache(IPCT_MARK, ct); } break; @@ -55,15 +57,15 @@ connmark_tg_shift(struct sk_buff *skb, const struct xt_connmark_tginfo2 *info) else new_targetmark <<= info->shift_bits; - newmark = (ct->mark & ~info->ctmask) ^ + newmark = (READ_ONCE(ct->mark) & ~info->ctmask) ^ new_targetmark; - if (ct->mark != newmark) { - ct->mark = newmark; + if (READ_ONCE(ct->mark) != newmark) { + WRITE_ONCE(ct->mark, newmark); nf_conntrack_event_cache(IPCT_MARK, ct); } break; case XT_CONNMARK_RESTORE: - new_targetmark = (ct->mark & info->ctmask); + new_targetmark = (READ_ONCE(ct->mark) & info->ctmask); if (info->shift_dir == D_SHIFT_RIGHT) new_targetmark >>= info->shift_bits; else @@ -126,7 +128,7 @@ connmark_mt(const struct sk_buff *skb, struct xt_action_param *par) if (ct == NULL) return false; - return ((ct->mark & info->mask) == info->mark) ^ info->invert; + return ((READ_ONCE(ct->mark) & info->mask) == info->mark) ^ info->invert; } static int connmark_mt_check(const struct xt_mtchk_param *par) diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c index 2cfff70f70e062db8be50df2542bc8f3596c93e8..ed9019d807c789d61554d78372bdcee6813e1afe 100644 --- a/net/nfc/nci/core.c +++ b/net/nfc/nci/core.c @@ -530,7 +530,7 @@ static int nci_open_device(struct nci_dev *ndev) skb_queue_purge(&ndev->tx_q); ndev->ops->close(ndev); - ndev->flags = 0; + ndev->flags &= BIT(NCI_UNREG); } done: diff --git a/net/nfc/nci/data.c b/net/nfc/nci/data.c index b002e18f38c81f55dfbccf0585e75ff909c6b66b..b4548d8874899c3819c3f11ef9eb78c6ea50def3 100644 --- a/net/nfc/nci/data.c +++ b/net/nfc/nci/data.c @@ -279,8 +279,10 @@ void nci_rx_data_packet(struct nci_dev *ndev, struct sk_buff *skb) nci_plen(skb->data)); conn_info = nci_get_conn_info_by_conn_id(ndev, nci_conn_id(skb->data)); - if (!conn_info) + if (!conn_info) { + kfree_skb(skb); return; + } /* strip the nci data header */ skb_pull(skb, NCI_DATA_HDR_SIZE); diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 41f248895a871cf3ac74c1c340b3d43e32c62866..0f0f380e81a406b3cba1edc26a4b8ed98c6e238d 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -150,7 +150,7 @@ static u8 ovs_ct_get_state(enum ip_conntrack_info ctinfo) static u32 ovs_ct_get_mark(const struct nf_conn *ct) { #if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) - return ct ? ct->mark : 0; + return ct ? READ_ONCE(ct->mark) : 0; #else return 0; #endif @@ -336,9 +336,9 @@ static int ovs_ct_set_mark(struct nf_conn *ct, struct sw_flow_key *key, #if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) u32 new_mark; - new_mark = ct_mark | (ct->mark & ~(mask)); - if (ct->mark != new_mark) { - ct->mark = new_mark; + new_mark = ct_mark | (READ_ONCE(ct->mark) & ~(mask)); + if (READ_ONCE(ct->mark) != new_mark) { + WRITE_ONCE(ct->mark, new_mark); if (nf_ct_is_confirmed(ct)) nf_conntrack_event_cache(IPCT_MARK, ct); key->ct.mark = new_mark; diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 9d6ef6cb9b26334fa1dc9036d336e44d07946370..7ed97dc0b5617ee3256f610a419a1c235bcab728 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -241,10 +241,17 @@ void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key) upcall.portid = ovs_vport_find_upcall_portid(p, skb); upcall.mru = OVS_CB(skb)->mru; error = ovs_dp_upcall(dp, skb, key, &upcall, 0); - if (unlikely(error)) - kfree_skb(skb); - else + switch (error) { + case 0: + case -EAGAIN: + case -ERESTARTSYS: + case -EINTR: consume_skb(skb); + break; + default: + kfree_skb(skb); + break; + } stats_counter = &stats->n_missed; goto out; } @@ -537,8 +544,9 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb, out: if (err) skb_tx_error(skb); - kfree_skb(user_skb); - kfree_skb(nskb); + consume_skb(user_skb); + consume_skb(nskb); + return err; } @@ -1584,7 +1592,8 @@ static void ovs_dp_reset_user_features(struct sk_buff *skb, if (IS_ERR(dp)) return; - WARN(dp->user_features, "Dropping previously announced user features\n"); + pr_warn("%s: Dropping previously announced user features\n", + ovs_dp_name(dp)); dp->user_features = 0; } diff --git a/net/rds/tcp.c b/net/rds/tcp.c index 5327d130c4b5691e788bbbcb990a349d714ad8d4..b560d06e6d96d43b3a60ac8ee59ab13a0a383a44 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -166,10 +166,10 @@ void rds_tcp_reset_callbacks(struct socket *sock, */ atomic_set(&cp->cp_state, RDS_CONN_RESETTING); wait_event(cp->cp_waitq, !test_bit(RDS_IN_XMIT, &cp->cp_flags)); - lock_sock(osock->sk); /* reset receive side state for rds_tcp_data_recv() for osock */ cancel_delayed_work_sync(&cp->cp_send_w); cancel_delayed_work_sync(&cp->cp_recv_w); + lock_sock(osock->sk); if (tc->t_tinc) { rds_inc_put(&tc->t_tinc->ti_inc); tc->t_tinc = NULL; diff --git a/net/rose/rose_link.c b/net/rose/rose_link.c index f6102e6f51617f2a01b7e5ec04b58b16cfa7e599..730d2205f1976a1e0e69e1a89c6db512c195e2c4 100644 --- a/net/rose/rose_link.c +++ b/net/rose/rose_link.c @@ -236,6 +236,9 @@ void rose_transmit_clear_request(struct rose_neigh *neigh, unsigned int lci, uns unsigned char *dptr; int len; + if (!neigh->dev) + return; + len = AX25_BPQ_HEADER_LEN + AX25_MAX_HEADER_LEN + ROSE_MIN_LEN + 3; if ((skb = alloc_skb(len, GFP_ATOMIC)) == NULL) diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index 41671af6b33f91e9f77af4dc0c9d8f813247e4f3..0354f90dc93aa4d523a169b6934df532972e736c 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -351,7 +351,7 @@ static void rxrpc_dummy_notify_rx(struct sock *sk, struct rxrpc_call *rxcall, */ void rxrpc_kernel_end_call(struct socket *sock, struct rxrpc_call *call) { - _enter("%d{%d}", call->debug_id, atomic_read(&call->usage)); + _enter("%d{%d}", call->debug_id, refcount_read(&call->ref)); mutex_lock(&call->user_mutex); rxrpc_release_call(rxrpc_sk(sock->sk), call); diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index ccb65412b6704b38f88fe3f398d9529143e711a6..d86894a1c35d3a60f199d0a733bef11a56ef479e 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -14,14 +14,6 @@ #include #include "protocol.h" -#if 0 -#define CHECK_SLAB_OKAY(X) \ - BUG_ON(atomic_read((X)) >> (sizeof(atomic_t) - 2) == \ - (POISON_FREE << 8 | POISON_FREE)) -#else -#define CHECK_SLAB_OKAY(X) do {} while (0) -#endif - #define FCRYPT_BSIZE 8 struct rxrpc_crypt { union { @@ -86,7 +78,7 @@ struct rxrpc_net { struct work_struct client_conn_reaper; struct timer_list client_conn_reap_timer; - struct list_head local_endpoints; + struct hlist_head local_endpoints; struct mutex local_mutex; /* Lock for ->local_endpoints */ DECLARE_HASHTABLE (peer_hash, 10); @@ -264,9 +256,9 @@ struct rxrpc_security { struct rxrpc_local { struct rcu_head rcu; atomic_t active_users; /* Number of users of the local endpoint */ - atomic_t usage; /* Number of references to the structure */ + refcount_t ref; /* Number of references to the structure */ struct rxrpc_net *rxnet; /* The network ns in which this resides */ - struct list_head link; + struct hlist_node link; struct socket *socket; /* my UDP socket */ struct work_struct processor; struct rxrpc_sock __rcu *service; /* Service(s) listening on this endpoint */ @@ -289,7 +281,7 @@ struct rxrpc_local { */ struct rxrpc_peer { struct rcu_head rcu; /* This must be first */ - atomic_t usage; + refcount_t ref; unsigned long hash_key; struct hlist_node hash_link; struct rxrpc_local *local; @@ -391,7 +383,8 @@ enum rxrpc_conn_proto_state { */ struct rxrpc_bundle { struct rxrpc_conn_parameters params; - atomic_t usage; + refcount_t ref; + atomic_t active; /* Number of active users */ unsigned int debug_id; bool try_upgrade; /* True if the bundle is attempting upgrade */ bool alloc_conn; /* True if someone's getting a conn */ @@ -412,7 +405,7 @@ struct rxrpc_connection { struct rxrpc_conn_proto proto; struct rxrpc_conn_parameters params; - atomic_t usage; + refcount_t ref; struct rcu_head rcu; struct list_head cache_link; @@ -592,7 +585,7 @@ struct rxrpc_call { int error; /* Local error incurred */ enum rxrpc_call_state state; /* current state of call */ enum rxrpc_call_completion completion; /* Call completion condition */ - atomic_t usage; + refcount_t ref; u16 service_id; /* service ID */ u8 security_ix; /* Security type */ enum rxrpc_interruptibility interruptibility; /* At what point call may be interrupted */ @@ -1001,6 +994,7 @@ void rxrpc_put_peer_locked(struct rxrpc_peer *); extern const struct seq_operations rxrpc_call_seq_ops; extern const struct seq_operations rxrpc_connection_seq_ops; extern const struct seq_operations rxrpc_peer_seq_ops; +extern const struct seq_operations rxrpc_local_seq_ops; /* * recvmsg.c diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index a0b033954ceacc029a28d6dac086369b8ab76b78..2a14d69b171f3bfdc83fd6c2d77e4ece4738b046 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -91,7 +91,7 @@ static int rxrpc_service_prealloc_one(struct rxrpc_sock *rx, (head + 1) & (size - 1)); trace_rxrpc_conn(conn->debug_id, rxrpc_conn_new_service, - atomic_read(&conn->usage), here); + refcount_read(&conn->ref), here); } /* Now it gets complicated, because calls get registered with the @@ -104,7 +104,7 @@ static int rxrpc_service_prealloc_one(struct rxrpc_sock *rx, call->state = RXRPC_CALL_SERVER_PREALLOC; trace_rxrpc_call(call->debug_id, rxrpc_call_new_service, - atomic_read(&call->usage), + refcount_read(&call->ref), here, (const void *)user_call_ID); write_lock(&rx->call_lock); diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 150cd7b2154c8b2c19eb54c413d2ab18f92a2902..10dad2834d5b6e2df09de187e5e574f4ac6a261f 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -112,7 +112,7 @@ struct rxrpc_call *rxrpc_find_call_by_user_ID(struct rxrpc_sock *rx, found_extant_call: rxrpc_get_call(call, rxrpc_call_got); read_unlock(&rx->call_lock); - _leave(" = %p [%d]", call, atomic_read(&call->usage)); + _leave(" = %p [%d]", call, refcount_read(&call->ref)); return call; } @@ -160,7 +160,7 @@ struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp, spin_lock_init(&call->notify_lock); spin_lock_init(&call->input_lock); rwlock_init(&call->state_lock); - atomic_set(&call->usage, 1); + refcount_set(&call->ref, 1); call->debug_id = debug_id; call->tx_total_len = -1; call->next_rx_timo = 20 * HZ; @@ -301,7 +301,7 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, call->interruptibility = p->interruptibility; call->tx_total_len = p->tx_total_len; trace_rxrpc_call(call->debug_id, rxrpc_call_new_client, - atomic_read(&call->usage), + refcount_read(&call->ref), here, (const void *)p->user_call_ID); if (p->kernel) __set_bit(RXRPC_CALL_KERNEL, &call->flags); @@ -354,7 +354,7 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, goto error_attached_to_socket; trace_rxrpc_call(call->debug_id, rxrpc_call_connected, - atomic_read(&call->usage), here, NULL); + refcount_read(&call->ref), here, NULL); rxrpc_start_call_timer(call); @@ -374,7 +374,7 @@ error_dup_user_ID: __rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, RX_CALL_DEAD, -EEXIST); trace_rxrpc_call(call->debug_id, rxrpc_call_error, - atomic_read(&call->usage), here, ERR_PTR(-EEXIST)); + refcount_read(&call->ref), here, ERR_PTR(-EEXIST)); rxrpc_release_call(rx, call); mutex_unlock(&call->user_mutex); rxrpc_put_call(call, rxrpc_call_put); @@ -388,7 +388,7 @@ error_dup_user_ID: */ error_attached_to_socket: trace_rxrpc_call(call->debug_id, rxrpc_call_error, - atomic_read(&call->usage), here, ERR_PTR(ret)); + refcount_read(&call->ref), here, ERR_PTR(ret)); set_bit(RXRPC_CALL_DISCONNECTED, &call->flags); __rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, RX_CALL_DEAD, ret); @@ -444,8 +444,9 @@ void rxrpc_incoming_call(struct rxrpc_sock *rx, bool rxrpc_queue_call(struct rxrpc_call *call) { const void *here = __builtin_return_address(0); - int n = atomic_fetch_add_unless(&call->usage, 1, 0); - if (n == 0) + int n; + + if (!__refcount_inc_not_zero(&call->ref, &n)) return false; if (rxrpc_queue_work(&call->processor)) trace_rxrpc_call(call->debug_id, rxrpc_call_queued, n + 1, @@ -461,7 +462,7 @@ bool rxrpc_queue_call(struct rxrpc_call *call) bool __rxrpc_queue_call(struct rxrpc_call *call) { const void *here = __builtin_return_address(0); - int n = atomic_read(&call->usage); + int n = refcount_read(&call->ref); ASSERTCMP(n, >=, 1); if (rxrpc_queue_work(&call->processor)) trace_rxrpc_call(call->debug_id, rxrpc_call_queued_ref, n, @@ -478,7 +479,7 @@ void rxrpc_see_call(struct rxrpc_call *call) { const void *here = __builtin_return_address(0); if (call) { - int n = atomic_read(&call->usage); + int n = refcount_read(&call->ref); trace_rxrpc_call(call->debug_id, rxrpc_call_seen, n, here, NULL); @@ -488,11 +489,11 @@ void rxrpc_see_call(struct rxrpc_call *call) bool rxrpc_try_get_call(struct rxrpc_call *call, enum rxrpc_call_trace op) { const void *here = __builtin_return_address(0); - int n = atomic_fetch_add_unless(&call->usage, 1, 0); + int n; - if (n == 0) + if (!__refcount_inc_not_zero(&call->ref, &n)) return false; - trace_rxrpc_call(call->debug_id, op, n, here, NULL); + trace_rxrpc_call(call->debug_id, op, n + 1, here, NULL); return true; } @@ -502,9 +503,10 @@ bool rxrpc_try_get_call(struct rxrpc_call *call, enum rxrpc_call_trace op) void rxrpc_get_call(struct rxrpc_call *call, enum rxrpc_call_trace op) { const void *here = __builtin_return_address(0); - int n = atomic_inc_return(&call->usage); + int n; - trace_rxrpc_call(call->debug_id, op, n, here, NULL); + __refcount_inc(&call->ref, &n); + trace_rxrpc_call(call->debug_id, op, n + 1, here, NULL); } /* @@ -529,10 +531,10 @@ void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call) struct rxrpc_connection *conn = call->conn; bool put = false; - _enter("{%d,%d}", call->debug_id, atomic_read(&call->usage)); + _enter("{%d,%d}", call->debug_id, refcount_read(&call->ref)); trace_rxrpc_call(call->debug_id, rxrpc_call_release, - atomic_read(&call->usage), + refcount_read(&call->ref), here, (const void *)call->flags); ASSERTCMP(call->state, ==, RXRPC_CALL_COMPLETE); @@ -621,14 +623,14 @@ void rxrpc_put_call(struct rxrpc_call *call, enum rxrpc_call_trace op) struct rxrpc_net *rxnet = call->rxnet; const void *here = __builtin_return_address(0); unsigned int debug_id = call->debug_id; + bool dead; int n; ASSERT(call != NULL); - n = atomic_dec_return(&call->usage); + dead = __refcount_dec_and_test(&call->ref, &n); trace_rxrpc_call(debug_id, op, n, here, NULL); - ASSERTCMP(n, >=, 0); - if (n == 0) { + if (dead) { _debug("call %d dead", call->debug_id); ASSERTCMP(call->state, ==, RXRPC_CALL_COMPLETE); @@ -718,7 +720,7 @@ void rxrpc_destroy_all_calls(struct rxrpc_net *rxnet) list_del_init(&call->link); pr_err("Call %p still in use (%d,%s,%lx,%lx)!\n", - call, atomic_read(&call->usage), + call, refcount_read(&call->ref), rxrpc_call_states[call->state], call->flags, call->events); diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c index f5fb223aba82ab3684cc2880bd51c1b8a1c04481..f5fa5f3083bddf5f45fdd68735a36cf3fe236123 100644 --- a/net/rxrpc/conn_client.c +++ b/net/rxrpc/conn_client.c @@ -40,6 +40,8 @@ __read_mostly unsigned long rxrpc_conn_idle_client_fast_expiry = 2 * HZ; DEFINE_IDR(rxrpc_client_conn_ids); static DEFINE_SPINLOCK(rxrpc_conn_id_lock); +static void rxrpc_deactivate_bundle(struct rxrpc_bundle *bundle); + /* * Get a connection ID and epoch for a client connection from the global pool. * The connection struct pointer is then recorded in the idr radix tree. The @@ -102,7 +104,7 @@ void rxrpc_destroy_client_conn_ids(void) if (!idr_is_empty(&rxrpc_client_conn_ids)) { idr_for_each_entry(&rxrpc_client_conn_ids, conn, id) { pr_err("AF_RXRPC: Leaked client conn %p {%d}\n", - conn, atomic_read(&conn->usage)); + conn, refcount_read(&conn->ref)); } BUG(); } @@ -122,7 +124,8 @@ static struct rxrpc_bundle *rxrpc_alloc_bundle(struct rxrpc_conn_parameters *cp, if (bundle) { bundle->params = *cp; rxrpc_get_peer(bundle->params.peer); - atomic_set(&bundle->usage, 1); + refcount_set(&bundle->ref, 1); + atomic_set(&bundle->active, 1); spin_lock_init(&bundle->channel_lock); INIT_LIST_HEAD(&bundle->waiting_calls); } @@ -131,7 +134,7 @@ static struct rxrpc_bundle *rxrpc_alloc_bundle(struct rxrpc_conn_parameters *cp, struct rxrpc_bundle *rxrpc_get_bundle(struct rxrpc_bundle *bundle) { - atomic_inc(&bundle->usage); + refcount_inc(&bundle->ref); return bundle; } @@ -144,10 +147,13 @@ static void rxrpc_free_bundle(struct rxrpc_bundle *bundle) void rxrpc_put_bundle(struct rxrpc_bundle *bundle) { unsigned int d = bundle->debug_id; - unsigned int u = atomic_dec_return(&bundle->usage); + bool dead; + int r; + + dead = __refcount_dec_and_test(&bundle->ref, &r); - _debug("PUT B=%x %u", d, u); - if (u == 0) + _debug("PUT B=%x %d", d, r - 1); + if (dead) rxrpc_free_bundle(bundle); } @@ -169,7 +175,7 @@ rxrpc_alloc_client_connection(struct rxrpc_bundle *bundle, gfp_t gfp) return ERR_PTR(-ENOMEM); } - atomic_set(&conn->usage, 1); + refcount_set(&conn->ref, 1); conn->bundle = bundle; conn->params = bundle->params; conn->out_clientflag = RXRPC_CLIENT_INITIATED; @@ -199,7 +205,7 @@ rxrpc_alloc_client_connection(struct rxrpc_bundle *bundle, gfp_t gfp) key_get(conn->params.key); trace_rxrpc_conn(conn->debug_id, rxrpc_conn_new_client, - atomic_read(&conn->usage), + refcount_read(&conn->ref), __builtin_return_address(0)); atomic_inc(&rxnet->nr_client_conns); @@ -341,6 +347,7 @@ found_bundle_free: rxrpc_free_bundle(candidate); found_bundle: rxrpc_get_bundle(bundle); + atomic_inc(&bundle->active); spin_unlock(&local->client_bundles_lock); _leave(" = %u [found]", bundle->debug_id); return bundle; @@ -438,6 +445,7 @@ static void rxrpc_add_conn_to_bundle(struct rxrpc_bundle *bundle, gfp_t gfp) if (old) trace_rxrpc_client(old, -1, rxrpc_client_replace); candidate->bundle_shift = shift; + atomic_inc(&bundle->active); bundle->conns[i] = candidate; for (j = 0; j < RXRPC_MAXCALLS; j++) set_bit(shift + j, &bundle->avail_chans); @@ -728,6 +736,7 @@ granted_channel: smp_rmb(); out_put_bundle: + rxrpc_deactivate_bundle(bundle); rxrpc_put_bundle(bundle); out: _leave(" = %d", ret); @@ -903,9 +912,8 @@ out: static void rxrpc_unbundle_conn(struct rxrpc_connection *conn) { struct rxrpc_bundle *bundle = conn->bundle; - struct rxrpc_local *local = bundle->params.local; unsigned int bindex; - bool need_drop = false, need_put = false; + bool need_drop = false; int i; _enter("C=%x", conn->debug_id); @@ -924,15 +932,22 @@ static void rxrpc_unbundle_conn(struct rxrpc_connection *conn) } spin_unlock(&bundle->channel_lock); - /* If there are no more connections, remove the bundle */ - if (!bundle->avail_chans) { - _debug("maybe unbundle"); - spin_lock(&local->client_bundles_lock); + if (need_drop) { + rxrpc_deactivate_bundle(bundle); + rxrpc_put_connection(conn); + } +} - for (i = 0; i < ARRAY_SIZE(bundle->conns); i++) - if (bundle->conns[i]) - break; - if (i == ARRAY_SIZE(bundle->conns) && !bundle->params.exclusive) { +/* + * Drop the active count on a bundle. + */ +static void rxrpc_deactivate_bundle(struct rxrpc_bundle *bundle) +{ + struct rxrpc_local *local = bundle->params.local; + bool need_put = false; + + if (atomic_dec_and_lock(&bundle->active, &local->client_bundles_lock)) { + if (!bundle->params.exclusive) { _debug("erase bundle"); rb_erase(&bundle->local_node, &local->client_bundles); need_put = true; @@ -942,10 +957,6 @@ static void rxrpc_unbundle_conn(struct rxrpc_connection *conn) if (need_put) rxrpc_put_bundle(bundle); } - - if (need_drop) - rxrpc_put_connection(conn); - _leave(""); } /* @@ -972,14 +983,13 @@ void rxrpc_put_client_conn(struct rxrpc_connection *conn) { const void *here = __builtin_return_address(0); unsigned int debug_id = conn->debug_id; - int n; + bool dead; + int r; - n = atomic_dec_return(&conn->usage); - trace_rxrpc_conn(debug_id, rxrpc_conn_put_client, n, here); - if (n <= 0) { - ASSERTCMP(n, >=, 0); + dead = __refcount_dec_and_test(&conn->ref, &r); + trace_rxrpc_conn(debug_id, rxrpc_conn_put_client, r - 1, here); + if (dead) rxrpc_kill_client_conn(conn); - } } /* diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c index 3ef05a0e90ad07666a47202d754c82cfadb4cd0e..d829b97550cc2a25c0b7b8683e985c67dce7418b 100644 --- a/net/rxrpc/conn_object.c +++ b/net/rxrpc/conn_object.c @@ -105,7 +105,7 @@ struct rxrpc_connection *rxrpc_find_connection_rcu(struct rxrpc_local *local, goto not_found; *_peer = peer; conn = rxrpc_find_service_conn_rcu(peer, skb); - if (!conn || atomic_read(&conn->usage) == 0) + if (!conn || refcount_read(&conn->ref) == 0) goto not_found; _leave(" = %p", conn); return conn; @@ -115,7 +115,7 @@ struct rxrpc_connection *rxrpc_find_connection_rcu(struct rxrpc_local *local, */ conn = idr_find(&rxrpc_client_conn_ids, sp->hdr.cid >> RXRPC_CIDSHIFT); - if (!conn || atomic_read(&conn->usage) == 0) { + if (!conn || refcount_read(&conn->ref) == 0) { _debug("no conn"); goto not_found; } @@ -264,11 +264,12 @@ void rxrpc_kill_connection(struct rxrpc_connection *conn) bool rxrpc_queue_conn(struct rxrpc_connection *conn) { const void *here = __builtin_return_address(0); - int n = atomic_fetch_add_unless(&conn->usage, 1, 0); - if (n == 0) + int r; + + if (!__refcount_inc_not_zero(&conn->ref, &r)) return false; if (rxrpc_queue_work(&conn->processor)) - trace_rxrpc_conn(conn->debug_id, rxrpc_conn_queued, n + 1, here); + trace_rxrpc_conn(conn->debug_id, rxrpc_conn_queued, r + 1, here); else rxrpc_put_connection(conn); return true; @@ -281,7 +282,7 @@ void rxrpc_see_connection(struct rxrpc_connection *conn) { const void *here = __builtin_return_address(0); if (conn) { - int n = atomic_read(&conn->usage); + int n = refcount_read(&conn->ref); trace_rxrpc_conn(conn->debug_id, rxrpc_conn_seen, n, here); } @@ -293,9 +294,10 @@ void rxrpc_see_connection(struct rxrpc_connection *conn) struct rxrpc_connection *rxrpc_get_connection(struct rxrpc_connection *conn) { const void *here = __builtin_return_address(0); - int n = atomic_inc_return(&conn->usage); + int r; - trace_rxrpc_conn(conn->debug_id, rxrpc_conn_got, n, here); + __refcount_inc(&conn->ref, &r); + trace_rxrpc_conn(conn->debug_id, rxrpc_conn_got, r, here); return conn; } @@ -306,11 +308,11 @@ struct rxrpc_connection * rxrpc_get_connection_maybe(struct rxrpc_connection *conn) { const void *here = __builtin_return_address(0); + int r; if (conn) { - int n = atomic_fetch_add_unless(&conn->usage, 1, 0); - if (n > 0) - trace_rxrpc_conn(conn->debug_id, rxrpc_conn_got, n + 1, here); + if (__refcount_inc_not_zero(&conn->ref, &r)) + trace_rxrpc_conn(conn->debug_id, rxrpc_conn_got, r + 1, here); else conn = NULL; } @@ -334,12 +336,11 @@ void rxrpc_put_service_conn(struct rxrpc_connection *conn) { const void *here = __builtin_return_address(0); unsigned int debug_id = conn->debug_id; - int n; + int r; - n = atomic_dec_return(&conn->usage); - trace_rxrpc_conn(debug_id, rxrpc_conn_put_service, n, here); - ASSERTCMP(n, >=, 0); - if (n == 1) + __refcount_dec(&conn->ref, &r); + trace_rxrpc_conn(debug_id, rxrpc_conn_put_service, r - 1, here); + if (r - 1 == 1) rxrpc_set_service_reap_timer(conn->params.local->rxnet, jiffies + rxrpc_connection_expiry); } @@ -352,9 +353,9 @@ static void rxrpc_destroy_connection(struct rcu_head *rcu) struct rxrpc_connection *conn = container_of(rcu, struct rxrpc_connection, rcu); - _enter("{%d,u=%d}", conn->debug_id, atomic_read(&conn->usage)); + _enter("{%d,u=%d}", conn->debug_id, refcount_read(&conn->ref)); - ASSERTCMP(atomic_read(&conn->usage), ==, 0); + ASSERTCMP(refcount_read(&conn->ref), ==, 0); _net("DESTROY CONN %d", conn->debug_id); @@ -394,8 +395,8 @@ void rxrpc_service_connection_reaper(struct work_struct *work) write_lock(&rxnet->conn_lock); list_for_each_entry_safe(conn, _p, &rxnet->service_conns, link) { - ASSERTCMP(atomic_read(&conn->usage), >, 0); - if (likely(atomic_read(&conn->usage) > 1)) + ASSERTCMP(refcount_read(&conn->ref), >, 0); + if (likely(refcount_read(&conn->ref) > 1)) continue; if (conn->state == RXRPC_CONN_SERVICE_PREALLOC) continue; @@ -407,7 +408,7 @@ void rxrpc_service_connection_reaper(struct work_struct *work) expire_at = idle_timestamp + rxrpc_closed_conn_expiry * HZ; _debug("reap CONN %d { u=%d,t=%ld }", - conn->debug_id, atomic_read(&conn->usage), + conn->debug_id, refcount_read(&conn->ref), (long)expire_at - (long)now); if (time_before(now, expire_at)) { @@ -420,7 +421,7 @@ void rxrpc_service_connection_reaper(struct work_struct *work) /* The usage count sits at 1 whilst the object is unused on the * list; we reduce that to 0 to make the object unavailable. */ - if (atomic_cmpxchg(&conn->usage, 1, 0) != 1) + if (!refcount_dec_if_one(&conn->ref)) continue; trace_rxrpc_conn(conn->debug_id, rxrpc_conn_reap_service, 0, NULL); @@ -444,7 +445,7 @@ void rxrpc_service_connection_reaper(struct work_struct *work) link); list_del_init(&conn->link); - ASSERTCMP(atomic_read(&conn->usage), ==, 0); + ASSERTCMP(refcount_read(&conn->ref), ==, 0); rxrpc_kill_connection(conn); } @@ -472,7 +473,7 @@ void rxrpc_destroy_all_connections(struct rxrpc_net *rxnet) write_lock(&rxnet->conn_lock); list_for_each_entry_safe(conn, _p, &rxnet->service_conns, link) { pr_err("AF_RXRPC: Leaked conn %p {%d}\n", - conn, atomic_read(&conn->usage)); + conn, refcount_read(&conn->ref)); leak = true; } write_unlock(&rxnet->conn_lock); diff --git a/net/rxrpc/conn_service.c b/net/rxrpc/conn_service.c index 6c847720494fae5b268619cbb8230a618de676b3..68508166bbc0b5c5b71a87e9af92a2fa13b6e6c5 100644 --- a/net/rxrpc/conn_service.c +++ b/net/rxrpc/conn_service.c @@ -9,7 +9,7 @@ #include "ar-internal.h" static struct rxrpc_bundle rxrpc_service_dummy_bundle = { - .usage = ATOMIC_INIT(1), + .ref = REFCOUNT_INIT(1), .debug_id = UINT_MAX, .channel_lock = __SPIN_LOCK_UNLOCKED(&rxrpc_service_dummy_bundle.channel_lock), }; @@ -99,7 +99,7 @@ conn_published: return; found_extant_conn: - if (atomic_read(&cursor->usage) == 0) + if (refcount_read(&cursor->ref) == 0) goto replace_old_connection; write_sequnlock_bh(&peer->service_conn_lock); /* We should not be able to get here. rxrpc_incoming_connection() is @@ -132,7 +132,7 @@ struct rxrpc_connection *rxrpc_prealloc_service_connection(struct rxrpc_net *rxn * the rxrpc_connections list. */ conn->state = RXRPC_CONN_SERVICE_PREALLOC; - atomic_set(&conn->usage, 2); + refcount_set(&conn->ref, 2); conn->bundle = rxrpc_get_bundle(&rxrpc_service_dummy_bundle); atomic_inc(&rxnet->nr_conns); @@ -142,7 +142,7 @@ struct rxrpc_connection *rxrpc_prealloc_service_connection(struct rxrpc_net *rxn write_unlock(&rxnet->conn_lock); trace_rxrpc_conn(conn->debug_id, rxrpc_conn_new_service, - atomic_read(&conn->usage), + refcount_read(&conn->ref), __builtin_return_address(0)); } diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 1145cb14d86f863efe877ceaf73f90466398d785..e9178115a74495421ba5e3dc14763de15102a23e 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -1163,8 +1163,6 @@ static void rxrpc_post_packet_to_local(struct rxrpc_local *local, */ static void rxrpc_reject_packet(struct rxrpc_local *local, struct sk_buff *skb) { - CHECK_SLAB_OKAY(&local->usage); - if (rxrpc_get_local_maybe(local)) { skb_queue_tail(&local->reject_queue, skb); rxrpc_queue_local(local); @@ -1422,7 +1420,7 @@ int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb) } } - if (!call || atomic_read(&call->usage) == 0) { + if (!call || refcount_read(&call->ref) == 0) { if (rxrpc_to_client(sp) || sp->hdr.type != RXRPC_PACKET_TYPE_DATA) goto bad_message; diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c index ebbf1b03b62cf5bb1a15e64bda95be6cd3968292..2c66ee981f395b5348ff8663164b8c9852325add 100644 --- a/net/rxrpc/local_object.c +++ b/net/rxrpc/local_object.c @@ -78,10 +78,10 @@ static struct rxrpc_local *rxrpc_alloc_local(struct rxrpc_net *rxnet, local = kzalloc(sizeof(struct rxrpc_local), GFP_KERNEL); if (local) { - atomic_set(&local->usage, 1); + refcount_set(&local->ref, 1); atomic_set(&local->active_users, 1); local->rxnet = rxnet; - INIT_LIST_HEAD(&local->link); + INIT_HLIST_NODE(&local->link); INIT_WORK(&local->processor, rxrpc_local_processor); init_rwsem(&local->defrag_sem); skb_queue_head_init(&local->reject_queue); @@ -199,7 +199,7 @@ struct rxrpc_local *rxrpc_lookup_local(struct net *net, { struct rxrpc_local *local; struct rxrpc_net *rxnet = rxrpc_net(net); - struct list_head *cursor; + struct hlist_node *cursor; const char *age; long diff; int ret; @@ -209,16 +209,12 @@ struct rxrpc_local *rxrpc_lookup_local(struct net *net, mutex_lock(&rxnet->local_mutex); - for (cursor = rxnet->local_endpoints.next; - cursor != &rxnet->local_endpoints; - cursor = cursor->next) { - local = list_entry(cursor, struct rxrpc_local, link); + hlist_for_each(cursor, &rxnet->local_endpoints) { + local = hlist_entry(cursor, struct rxrpc_local, link); diff = rxrpc_local_cmp_key(local, srx); - if (diff < 0) + if (diff != 0) continue; - if (diff > 0) - break; /* Services aren't allowed to share transport sockets, so * reject that here. It is possible that the object is dying - @@ -230,9 +226,10 @@ struct rxrpc_local *rxrpc_lookup_local(struct net *net, goto addr_in_use; } - /* Found a match. We replace a dying object. Attempting to - * bind the transport socket may still fail if we're attempting - * to use a local address that the dying object is still using. + /* Found a match. We want to replace a dying object. + * Attempting to bind the transport socket may still fail if + * we're attempting to use a local address that the dying + * object is still using. */ if (!rxrpc_use_local(local)) break; @@ -249,10 +246,12 @@ struct rxrpc_local *rxrpc_lookup_local(struct net *net, if (ret < 0) goto sock_error; - if (cursor != &rxnet->local_endpoints) - list_replace_init(cursor, &local->link); - else - list_add_tail(&local->link, cursor); + if (cursor) { + hlist_replace_rcu(cursor, &local->link); + cursor->pprev = NULL; + } else { + hlist_add_head_rcu(&local->link, &rxnet->local_endpoints); + } age = "new"; found: @@ -285,10 +284,10 @@ addr_in_use: struct rxrpc_local *rxrpc_get_local(struct rxrpc_local *local) { const void *here = __builtin_return_address(0); - int n; + int r; - n = atomic_inc_return(&local->usage); - trace_rxrpc_local(local->debug_id, rxrpc_local_got, n, here); + __refcount_inc(&local->ref, &r); + trace_rxrpc_local(local->debug_id, rxrpc_local_got, r + 1, here); return local; } @@ -298,12 +297,12 @@ struct rxrpc_local *rxrpc_get_local(struct rxrpc_local *local) struct rxrpc_local *rxrpc_get_local_maybe(struct rxrpc_local *local) { const void *here = __builtin_return_address(0); + int r; if (local) { - int n = atomic_fetch_add_unless(&local->usage, 1, 0); - if (n > 0) + if (__refcount_inc_not_zero(&local->ref, &r)) trace_rxrpc_local(local->debug_id, rxrpc_local_got, - n + 1, here); + r + 1, here); else local = NULL; } @@ -317,10 +316,10 @@ void rxrpc_queue_local(struct rxrpc_local *local) { const void *here = __builtin_return_address(0); unsigned int debug_id = local->debug_id; - int n = atomic_read(&local->usage); + int r = refcount_read(&local->ref); if (rxrpc_queue_work(&local->processor)) - trace_rxrpc_local(debug_id, rxrpc_local_queued, n, here); + trace_rxrpc_local(debug_id, rxrpc_local_queued, r + 1, here); else rxrpc_put_local(local); } @@ -332,15 +331,16 @@ void rxrpc_put_local(struct rxrpc_local *local) { const void *here = __builtin_return_address(0); unsigned int debug_id; - int n; + bool dead; + int r; if (local) { debug_id = local->debug_id; - n = atomic_dec_return(&local->usage); - trace_rxrpc_local(debug_id, rxrpc_local_put, n, here); + dead = __refcount_dec_and_test(&local->ref, &r); + trace_rxrpc_local(debug_id, rxrpc_local_put, r, here); - if (n == 0) + if (dead) call_rcu(&local->rcu, rxrpc_local_rcu); } } @@ -393,7 +393,7 @@ static void rxrpc_local_destroyer(struct rxrpc_local *local) local->dead = true; mutex_lock(&rxnet->local_mutex); - list_del_init(&local->link); + hlist_del_init_rcu(&local->link); mutex_unlock(&rxnet->local_mutex); rxrpc_clean_up_local_conns(local); @@ -428,7 +428,7 @@ static void rxrpc_local_processor(struct work_struct *work) return; trace_rxrpc_local(local->debug_id, rxrpc_local_processing, - atomic_read(&local->usage), NULL); + refcount_read(&local->ref), NULL); do { again = false; @@ -480,11 +480,11 @@ void rxrpc_destroy_all_locals(struct rxrpc_net *rxnet) flush_workqueue(rxrpc_workqueue); - if (!list_empty(&rxnet->local_endpoints)) { + if (!hlist_empty(&rxnet->local_endpoints)) { mutex_lock(&rxnet->local_mutex); - list_for_each_entry(local, &rxnet->local_endpoints, link) { + hlist_for_each_entry(local, &rxnet->local_endpoints, link) { pr_err("AF_RXRPC: Leaked local %p {%d}\n", - local, atomic_read(&local->usage)); + local, refcount_read(&local->ref)); } mutex_unlock(&rxnet->local_mutex); BUG(); diff --git a/net/rxrpc/net_ns.c b/net/rxrpc/net_ns.c index cc7e30733feb0d3f381269dfc4b9bcd5532b42ec..34f389975a7d004b3b58345c26d1988c89599834 100644 --- a/net/rxrpc/net_ns.c +++ b/net/rxrpc/net_ns.c @@ -72,7 +72,7 @@ static __net_init int rxrpc_init_net(struct net *net) timer_setup(&rxnet->client_conn_reap_timer, rxrpc_client_conn_reap_timeout, 0); - INIT_LIST_HEAD(&rxnet->local_endpoints); + INIT_HLIST_HEAD(&rxnet->local_endpoints); mutex_init(&rxnet->local_mutex); hash_init(rxnet->peer_hash); @@ -98,6 +98,9 @@ static __net_init int rxrpc_init_net(struct net *net) proc_create_net("peers", 0444, rxnet->proc_net, &rxrpc_peer_seq_ops, sizeof(struct seq_net_private)); + proc_create_net("locals", 0444, rxnet->proc_net, + &rxrpc_local_seq_ops, + sizeof(struct seq_net_private)); return 0; err_proc: diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c index 0298fe2ad6d323b377b46d5dc70c8d472d899966..26d2ae9baaf2c5c3ce22d2336c21c90738a377a5 100644 --- a/net/rxrpc/peer_object.c +++ b/net/rxrpc/peer_object.c @@ -121,7 +121,7 @@ static struct rxrpc_peer *__rxrpc_lookup_peer_rcu( hash_for_each_possible_rcu(rxnet->peer_hash, peer, hash_link, hash_key) { if (rxrpc_peer_cmp_key(peer, local, srx, hash_key) == 0 && - atomic_read(&peer->usage) > 0) + refcount_read(&peer->ref) > 0) return peer; } @@ -140,7 +140,7 @@ struct rxrpc_peer *rxrpc_lookup_peer_rcu(struct rxrpc_local *local, peer = __rxrpc_lookup_peer_rcu(local, srx, hash_key); if (peer) { _net("PEER %d {%pISp}", peer->debug_id, &peer->srx.transport); - _leave(" = %p {u=%d}", peer, atomic_read(&peer->usage)); + _leave(" = %p {u=%d}", peer, refcount_read(&peer->ref)); } return peer; } @@ -216,7 +216,7 @@ struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *local, gfp_t gfp) peer = kzalloc(sizeof(struct rxrpc_peer), gfp); if (peer) { - atomic_set(&peer->usage, 1); + refcount_set(&peer->ref, 1); peer->local = rxrpc_get_local(local); INIT_HLIST_HEAD(&peer->error_targets); peer->service_conns = RB_ROOT; @@ -378,7 +378,7 @@ struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_sock *rx, _net("PEER %d {%pISp}", peer->debug_id, &peer->srx.transport); - _leave(" = %p {u=%d}", peer, atomic_read(&peer->usage)); + _leave(" = %p {u=%d}", peer, refcount_read(&peer->ref)); return peer; } @@ -388,10 +388,10 @@ struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_sock *rx, struct rxrpc_peer *rxrpc_get_peer(struct rxrpc_peer *peer) { const void *here = __builtin_return_address(0); - int n; + int r; - n = atomic_inc_return(&peer->usage); - trace_rxrpc_peer(peer->debug_id, rxrpc_peer_got, n, here); + __refcount_inc(&peer->ref, &r); + trace_rxrpc_peer(peer->debug_id, rxrpc_peer_got, r + 1, here); return peer; } @@ -401,11 +401,11 @@ struct rxrpc_peer *rxrpc_get_peer(struct rxrpc_peer *peer) struct rxrpc_peer *rxrpc_get_peer_maybe(struct rxrpc_peer *peer) { const void *here = __builtin_return_address(0); + int r; if (peer) { - int n = atomic_fetch_add_unless(&peer->usage, 1, 0); - if (n > 0) - trace_rxrpc_peer(peer->debug_id, rxrpc_peer_got, n + 1, here); + if (__refcount_inc_not_zero(&peer->ref, &r)) + trace_rxrpc_peer(peer->debug_id, rxrpc_peer_got, r + 1, here); else peer = NULL; } @@ -436,13 +436,14 @@ void rxrpc_put_peer(struct rxrpc_peer *peer) { const void *here = __builtin_return_address(0); unsigned int debug_id; - int n; + bool dead; + int r; if (peer) { debug_id = peer->debug_id; - n = atomic_dec_return(&peer->usage); - trace_rxrpc_peer(debug_id, rxrpc_peer_put, n, here); - if (n == 0) + dead = __refcount_dec_and_test(&peer->ref, &r); + trace_rxrpc_peer(debug_id, rxrpc_peer_put, r - 1, here); + if (dead) __rxrpc_put_peer(peer); } } @@ -455,11 +456,12 @@ void rxrpc_put_peer_locked(struct rxrpc_peer *peer) { const void *here = __builtin_return_address(0); unsigned int debug_id = peer->debug_id; - int n; + bool dead; + int r; - n = atomic_dec_return(&peer->usage); - trace_rxrpc_peer(debug_id, rxrpc_peer_put, n, here); - if (n == 0) { + dead = __refcount_dec_and_test(&peer->ref, &r); + trace_rxrpc_peer(debug_id, rxrpc_peer_put, r - 1, here); + if (dead) { hash_del_rcu(&peer->hash_link); list_del_init(&peer->keepalive_link); rxrpc_free_peer(peer); @@ -481,7 +483,7 @@ void rxrpc_destroy_all_peers(struct rxrpc_net *rxnet) hlist_for_each_entry(peer, &rxnet->peer_hash[i], hash_link) { pr_err("Leaked peer %u {%u} %pISp\n", peer->debug_id, - atomic_read(&peer->usage), + refcount_read(&peer->ref), &peer->srx.transport); } } diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c index e2f990754f8820216856820652988aec360e2868..8967201fd8e54eb35fb6d0d46f287d5393fd4841 100644 --- a/net/rxrpc/proc.c +++ b/net/rxrpc/proc.c @@ -107,7 +107,7 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v) call->cid, call->call_id, rxrpc_is_service_call(call) ? "Svc" : "Clt", - atomic_read(&call->usage), + refcount_read(&call->ref), rxrpc_call_states[call->state], call->abort_code, call->debug_id, @@ -189,7 +189,7 @@ print: conn->service_id, conn->proto.cid, rxrpc_conn_is_service(conn) ? "Svc" : "Clt", - atomic_read(&conn->usage), + refcount_read(&conn->ref), rxrpc_conn_states[conn->state], key_serial(conn->params.key), atomic_read(&conn->serial), @@ -239,7 +239,7 @@ static int rxrpc_peer_seq_show(struct seq_file *seq, void *v) " %3u %5u %6llus %8u %8u\n", lbuff, rbuff, - atomic_read(&peer->usage), + refcount_read(&peer->ref), peer->cong_cwnd, peer->mtu, now - peer->last_tx_at, @@ -334,3 +334,72 @@ const struct seq_operations rxrpc_peer_seq_ops = { .stop = rxrpc_peer_seq_stop, .show = rxrpc_peer_seq_show, }; + +/* + * Generate a list of extant virtual local endpoints in /proc/net/rxrpc/locals + */ +static int rxrpc_local_seq_show(struct seq_file *seq, void *v) +{ + struct rxrpc_local *local; + char lbuff[50]; + + if (v == SEQ_START_TOKEN) { + seq_puts(seq, + "Proto Local " + " Use Act\n"); + return 0; + } + + local = hlist_entry(v, struct rxrpc_local, link); + + sprintf(lbuff, "%pISpc", &local->srx.transport); + + seq_printf(seq, + "UDP %-47.47s %3u %3u\n", + lbuff, + refcount_read(&local->ref), + atomic_read(&local->active_users)); + + return 0; +} + +static void *rxrpc_local_seq_start(struct seq_file *seq, loff_t *_pos) + __acquires(rcu) +{ + struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq)); + unsigned int n; + + rcu_read_lock(); + + if (*_pos >= UINT_MAX) + return NULL; + + n = *_pos; + if (n == 0) + return SEQ_START_TOKEN; + + return seq_hlist_start_rcu(&rxnet->local_endpoints, n - 1); +} + +static void *rxrpc_local_seq_next(struct seq_file *seq, void *v, loff_t *_pos) +{ + struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq)); + + if (*_pos >= UINT_MAX) + return NULL; + + return seq_hlist_next_rcu(v, &rxnet->local_endpoints, _pos); +} + +static void rxrpc_local_seq_stop(struct seq_file *seq, void *v) + __releases(rcu) +{ + rcu_read_unlock(); +} + +const struct seq_operations rxrpc_local_seq_ops = { + .start = rxrpc_local_seq_start, + .next = rxrpc_local_seq_next, + .stop = rxrpc_local_seq_stop, + .show = rxrpc_local_seq_show, +}; diff --git a/net/rxrpc/skbuff.c b/net/rxrpc/skbuff.c index 0348d2bf6f7d8e85ea075c992a5b5368ca0362a0..580a5acffee71667e2e39b1820c401c85cc1b06f 100644 --- a/net/rxrpc/skbuff.c +++ b/net/rxrpc/skbuff.c @@ -71,7 +71,6 @@ void rxrpc_free_skb(struct sk_buff *skb, enum rxrpc_skb_trace op) const void *here = __builtin_return_address(0); if (skb) { int n; - CHECK_SLAB_OKAY(&skb->users); n = atomic_dec_return(select_skb_count(skb)); trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, rxrpc_skb(skb)->rx_flags, here); diff --git a/net/sched/Kconfig b/net/sched/Kconfig index d762e89ab74f7ec4390c64975608de26385e34ea..bc4e5da76fa6f70e49413b1ae8a768c257c92621 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -976,7 +976,7 @@ config NET_ACT_TUNNEL_KEY config NET_ACT_CT tristate "connection tracking tc action" - depends on NET_CLS_ACT && NF_CONNTRACK && NF_NAT && NF_FLOW_TABLE + depends on NET_CLS_ACT && NF_CONNTRACK && (!NF_NAT || NF_NAT) && NF_FLOW_TABLE help Say Y here to allow sending the packets to conntrack module. diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c index e19885d7fe2cba90b83a3345e201c0dc2b21c53b..31d268eedf3f90a0312c8650d53185a0c061fbd8 100644 --- a/net/sched/act_connmark.c +++ b/net/sched/act_connmark.c @@ -62,7 +62,7 @@ static int tcf_connmark_act(struct sk_buff *skb, const struct tc_action *a, c = nf_ct_get(skb, &ctinfo); if (c) { - skb->mark = c->mark; + skb->mark = READ_ONCE(c->mark); /* using overlimits stats to count how many packets marked */ ca->tcf_qstats.overlimits++; goto out; @@ -82,7 +82,7 @@ static int tcf_connmark_act(struct sk_buff *skb, const struct tc_action *a, c = nf_ct_tuplehash_to_ctrack(thash); /* using overlimits stats to count how many packets marked */ ca->tcf_qstats.overlimits++; - skb->mark = c->mark; + skb->mark = READ_ONCE(c->mark); nf_ct_put(c); out: diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index f7e88d7466c30b85acd5654ec5d307f3cd9acda8..2d41d866de3e3b31d4da95392404de331f8c634a 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -177,7 +177,7 @@ static void tcf_ct_flow_table_add_action_meta(struct nf_conn *ct, entry = tcf_ct_flow_table_flow_action_get_next(action); entry->id = FLOW_ACTION_CT_METADATA; #if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) - entry->ct_metadata.mark = ct->mark; + entry->ct_metadata.mark = READ_ONCE(ct->mark); #endif ctinfo = dir == IP_CT_DIR_ORIGINAL ? IP_CT_ESTABLISHED : IP_CT_ESTABLISHED_REPLY; @@ -843,9 +843,9 @@ static void tcf_ct_act_set_mark(struct nf_conn *ct, u32 mark, u32 mask) if (!mask) return; - new_mark = mark | (ct->mark & ~(mask)); - if (ct->mark != new_mark) { - ct->mark = new_mark; + new_mark = mark | (READ_ONCE(ct->mark) & ~(mask)); + if (READ_ONCE(ct->mark) != new_mark) { + WRITE_ONCE(ct->mark, new_mark); if (nf_ct_is_confirmed(ct)) nf_conntrack_event_cache(IPCT_MARK, ct); } diff --git a/net/sched/act_ctinfo.c b/net/sched/act_ctinfo.c index b20c8ce59905b38024f7fc19cebf39a1dc2ee918..06c74f22ab98b76bb3a43d69bcfb59c75eaeaa7c 100644 --- a/net/sched/act_ctinfo.c +++ b/net/sched/act_ctinfo.c @@ -33,7 +33,7 @@ static void tcf_ctinfo_dscp_set(struct nf_conn *ct, struct tcf_ctinfo *ca, { u8 dscp, newdscp; - newdscp = (((ct->mark & cp->dscpmask) >> cp->dscpmaskshift) << 2) & + newdscp = (((READ_ONCE(ct->mark) & cp->dscpmask) >> cp->dscpmaskshift) << 2) & ~INET_ECN_MASK; switch (proto) { @@ -73,7 +73,7 @@ static void tcf_ctinfo_cpmark_set(struct nf_conn *ct, struct tcf_ctinfo *ca, struct sk_buff *skb) { ca->stats_cpmark_set++; - skb->mark = ct->mark & cp->cpmarkmask; + skb->mark = READ_ONCE(ct->mark) & cp->cpmarkmask; } static int tcf_ctinfo_act(struct sk_buff *skb, const struct tc_action *a, @@ -131,7 +131,7 @@ static int tcf_ctinfo_act(struct sk_buff *skb, const struct tc_action *a, } if (cp->mode & CTINFO_MODE_DSCP) - if (!cp->dscpstatemask || (ct->mark & cp->dscpstatemask)) + if (!cp->dscpstatemask || (READ_ONCE(ct->mark) & cp->dscpstatemask)) tcf_ctinfo_dscp_set(ct, ca, cp, skb, wlen, proto); if (cp->mode & CTINFO_MODE_CPMARK) diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 6e18aa41778285e7fa97e606f46cfc67e0f03236..d8ffe41143856215825f5768253ef91f0df444ee 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1081,12 +1081,13 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent, skip: if (!ingress) { - notify_and_destroy(net, skb, n, classid, - rtnl_dereference(dev->qdisc), new); + old = rtnl_dereference(dev->qdisc); if (new && !new->ops->attach) qdisc_refcount_inc(new); rcu_assign_pointer(dev->qdisc, new ? : &noop_qdisc); + notify_and_destroy(net, skb, n, classid, old, new); + if (new && new->ops->attach) new->ops->attach(new); } else { diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c index 1c281cc81f57789b787c77622cc2c026414f9c9d..794c7377cd7e908eba4cb41c4c184ae2c64526a5 100644 --- a/net/sched/sch_atm.c +++ b/net/sched/sch_atm.c @@ -575,7 +575,6 @@ static void atm_tc_reset(struct Qdisc *sch) pr_debug("atm_tc_reset(sch %p,[qdisc %p])\n", sch, p); list_for_each_entry(flow, &p->flows, list) qdisc_reset(flow->q); - sch->q.qlen = 0; } static void atm_tc_destroy(struct Qdisc *sch) diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index c580139fcedecc0958b23abe32d6aede34effdf1..5dc7a3c310c9d335bf76f58f6d01fcbdb25b8730 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -2224,8 +2224,12 @@ retry: static void cake_reset(struct Qdisc *sch) { + struct cake_sched_data *q = qdisc_priv(sch); u32 c; + if (!q->tins) + return; + for (c = 0; c < CAKE_MAX_TINS; c++) cake_clear_tin(sch, c); } diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index 4a78fcf5d4f989a78f2ced9301e9bcd15232d7e2..9a3dff02b7a2bac9fc475ee4ff828ab739c79086 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -1053,7 +1053,6 @@ cbq_reset(struct Qdisc *sch) cl->cpriority = cl->priority; } } - sch->q.qlen = 0; } diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c index 2adbd945bf15aee182bc1505ec54b9695d104d52..25d2daaa81227478f3f91c57c26ea8185c686462 100644 --- a/net/sched/sch_choke.c +++ b/net/sched/sch_choke.c @@ -315,8 +315,6 @@ static void choke_reset(struct Qdisc *sch) rtnl_qdisc_drop(skb, sch); } - sch->q.qlen = 0; - sch->qstats.backlog = 0; if (q->tab) memset(q->tab, 0, (q->tab_mask + 1) * sizeof(struct sk_buff *)); q->head = q->tail = 0; diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c index dde564670ad8ca17128e45401b369144df9231a3..08424aac6da82eee4258b51d2a4686b5f007b536 100644 --- a/net/sched/sch_drr.c +++ b/net/sched/sch_drr.c @@ -443,8 +443,6 @@ static void drr_reset_qdisc(struct Qdisc *sch) qdisc_reset(cl->qdisc); } } - sch->qstats.backlog = 0; - sch->q.qlen = 0; } static void drr_destroy_qdisc(struct Qdisc *sch) diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c index 76ed1a05ded27cfc2f5f5af8581737f0abcb8498..a75bc7f80cd7e26e24646d76aa569fab455702b3 100644 --- a/net/sched/sch_dsmark.c +++ b/net/sched/sch_dsmark.c @@ -408,8 +408,6 @@ static void dsmark_reset(struct Qdisc *sch) pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p); if (p->q) qdisc_reset(p->q); - sch->qstats.backlog = 0; - sch->q.qlen = 0; } static void dsmark_destroy(struct Qdisc *sch) diff --git a/net/sched/sch_etf.c b/net/sched/sch_etf.c index c48f91075b5c60ee4fe9e10186c913baf5894a69..d96103b0e2bf516bb668aa4037cbf85a7c8f9e30 100644 --- a/net/sched/sch_etf.c +++ b/net/sched/sch_etf.c @@ -445,9 +445,6 @@ static void etf_reset(struct Qdisc *sch) timesortedlist_clear(sch); __qdisc_reset_queue(&sch->q); - sch->qstats.backlog = 0; - sch->q.qlen = 0; - q->last = 0; } diff --git a/net/sched/sch_ets.c b/net/sched/sch_ets.c index 9c224872ef0355e2b4d128c1924cb242106e31c0..05817c55692f0a2db4d027b6d6510ca6dc8edd18 100644 --- a/net/sched/sch_ets.c +++ b/net/sched/sch_ets.c @@ -722,8 +722,6 @@ static void ets_qdisc_reset(struct Qdisc *sch) } for (band = 0; band < q->nbands; band++) qdisc_reset(q->classes[band].qdisc); - sch->qstats.backlog = 0; - sch->q.qlen = 0; } static void ets_qdisc_destroy(struct Qdisc *sch) diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index 99e8db2621984903af8104ca0082d262e5f372b7..01d6eea5b0ce9695706b5f3b1164bd951db704af 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -347,8 +347,6 @@ static void fq_codel_reset(struct Qdisc *sch) codel_vars_init(&flow->cvars); } memset(q->backlogs, 0, q->flows_cnt * sizeof(u32)); - sch->q.qlen = 0; - sch->qstats.backlog = 0; q->memory_usage = 0; } diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c index c70802785518f4b33cbee68bbde563af60226f8c..cf04f70e96bf1fd38471d06321b97b74aef1628f 100644 --- a/net/sched/sch_fq_pie.c +++ b/net/sched/sch_fq_pie.c @@ -521,9 +521,6 @@ static void fq_pie_reset(struct Qdisc *sch) INIT_LIST_HEAD(&flow->flowchain); pie_vars_init(&flow->vars); } - - sch->q.qlen = 0; - sch->qstats.backlog = 0; } static void fq_pie_destroy(struct Qdisc *sch) diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index d1902fca98447f0073e98947ae0cc7f969728022..cdc43a06aa9bccee969adc31a1bad4dbbeb7ff05 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -1484,8 +1484,6 @@ hfsc_reset_qdisc(struct Qdisc *sch) } q->eligible = RB_ROOT; qdisc_watchdog_cancel(&q->watchdog); - sch->qstats.backlog = 0; - sch->q.qlen = 0; } static void diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index cd70dbcbd72fdddcda75d98d918f70554af60214..c3ba018fd083ea61eaebb46b782d3756e0878795 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -966,8 +966,6 @@ static void htb_reset(struct Qdisc *sch) } qdisc_watchdog_cancel(&q->watchdog); __qdisc_reset_queue(&q->direct_queue); - sch->q.qlen = 0; - sch->qstats.backlog = 0; memset(q->hlevel, 0, sizeof(q->hlevel)); memset(q->row_mask, 0, sizeof(q->row_mask)); } diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c index 5c27b4270b90894dcfdd5c9621a0db8cf13582c3..1c6dbcfa89b877aeb2aae586b3d429439524ba14 100644 --- a/net/sched/sch_multiq.c +++ b/net/sched/sch_multiq.c @@ -152,7 +152,6 @@ multiq_reset(struct Qdisc *sch) for (band = 0; band < q->bands; band++) qdisc_reset(q->queues[band]); - sch->q.qlen = 0; q->curband = 0; } diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c index 3eabb871a1d522ad72b903ad43666ce801220c2d..1c805fe05b82a674d665711fde1f8f63d5ab11cf 100644 --- a/net/sched/sch_prio.c +++ b/net/sched/sch_prio.c @@ -135,8 +135,6 @@ prio_reset(struct Qdisc *sch) for (prio = 0; prio < q->bands; prio++) qdisc_reset(q->queues[prio]); - sch->qstats.backlog = 0; - sch->q.qlen = 0; } static int prio_offload(struct Qdisc *sch, struct tc_prio_qopt *qopt) diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index af8c63a9ec18c53cdca0ac0bee6ff97af58996ec..1d1d81aeb389f495f1cae1c91284db881cd79d6f 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -1458,8 +1458,6 @@ static void qfq_reset_qdisc(struct Qdisc *sch) qdisc_reset(cl->qdisc); } } - sch->qstats.backlog = 0; - sch->q.qlen = 0; } static void qfq_destroy_qdisc(struct Qdisc *sch) diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index 40adf1f07a82dfdb8f704eecfa9a14f000213a91..935d90874b1b7d2e823d710bfabe402426a9e12c 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -72,6 +72,7 @@ static int red_enqueue(struct sk_buff *skb, struct Qdisc *sch, { struct red_sched_data *q = qdisc_priv(sch); struct Qdisc *child = q->qdisc; + unsigned int len; int ret; q->vars.qavg = red_calc_qavg(&q->parms, @@ -126,9 +127,10 @@ static int red_enqueue(struct sk_buff *skb, struct Qdisc *sch, break; } + len = qdisc_pkt_len(skb); ret = qdisc_enqueue(skb, child, to_free); if (likely(ret == NET_XMIT_SUCCESS)) { - qdisc_qstats_backlog_inc(sch, skb); + sch->qstats.backlog += len; sch->q.qlen++; } else if (net_xmit_drop_count(ret)) { q->stats.pdrop++; @@ -176,8 +178,6 @@ static void red_reset(struct Qdisc *sch) struct red_sched_data *q = qdisc_priv(sch); qdisc_reset(q->qdisc); - sch->qstats.backlog = 0; - sch->q.qlen = 0; red_restart(&q->vars); } diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c index b2724057629f696f4f89032e12be07ece13549a8..9ded56228ea10b8255778e3827292faf83cb4aaa 100644 --- a/net/sched/sch_sfb.c +++ b/net/sched/sch_sfb.c @@ -455,9 +455,8 @@ static void sfb_reset(struct Qdisc *sch) { struct sfb_sched_data *q = qdisc_priv(sch); - qdisc_reset(q->qdisc); - sch->qstats.backlog = 0; - sch->q.qlen = 0; + if (likely(q->qdisc)) + qdisc_reset(q->qdisc); q->slot = 0; q->double_buffering = false; sfb_zero_all_buckets(q); diff --git a/net/sched/sch_skbprio.c b/net/sched/sch_skbprio.c index 7a5e4c454715617cb57c6db7de7fdaa9e6886d40..df72fb83d9c7d88bb93d08c9a7453abe8a055eb0 100644 --- a/net/sched/sch_skbprio.c +++ b/net/sched/sch_skbprio.c @@ -213,9 +213,6 @@ static void skbprio_reset(struct Qdisc *sch) struct skbprio_sched_data *q = qdisc_priv(sch); int prio; - sch->qstats.backlog = 0; - sch->q.qlen = 0; - for (prio = 0; prio < SKBPRIO_MAX_PRIORITY; prio++) __skb_queue_purge(&q->qdiscs[prio]); diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index ab8835a72cee6d3c8ad66dd7859ed054448a27ca..7f33b31c7b8bde4ffae185c8b9230e3b158e9189 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -1626,8 +1626,6 @@ static void taprio_reset(struct Qdisc *sch) if (q->qdiscs[i]) qdisc_reset(q->qdiscs[i]); } - sch->qstats.backlog = 0; - sch->q.qlen = 0; } static void taprio_destroy(struct Qdisc *sch) diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c index 6eb17004a9e44c616b7ad94df832b9487380d3a6..7461e5c67d50a70164ac49e7beb458b0b77121bf 100644 --- a/net/sched/sch_tbf.c +++ b/net/sched/sch_tbf.c @@ -316,8 +316,6 @@ static void tbf_reset(struct Qdisc *sch) struct tbf_sched_data *q = qdisc_priv(sch); qdisc_reset(q->qdisc); - sch->qstats.backlog = 0; - sch->q.qlen = 0; q->t_c = ktime_get_ns(); q->tokens = q->buffer; q->ptokens = q->mtu; diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c index 6af6b95bdb6723a3d600c1defae08fd897c7a308..79aaab51cbf5c8357f282d6d4d9ba464e83e7f30 100644 --- a/net/sched/sch_teql.c +++ b/net/sched/sch_teql.c @@ -124,7 +124,6 @@ teql_reset(struct Qdisc *sch) struct teql_sched_data *dat = qdisc_priv(sch); skb_queue_purge(&dat->q); - sch->q.qlen = 0; } static void diff --git a/net/sctp/auth.c b/net/sctp/auth.c index db6b7373d16c374f1dba808070e95309d71c90d7..34964145514e6d8c284b5a2687ac19ef1e8b4cf0 100644 --- a/net/sctp/auth.c +++ b/net/sctp/auth.c @@ -863,12 +863,17 @@ int sctp_auth_set_key(struct sctp_endpoint *ep, } list_del_init(&shkey->key_list); - sctp_auth_shkey_release(shkey); list_add(&cur_key->key_list, sh_keys); - if (asoc && asoc->active_key_id == auth_key->sca_keynumber) - sctp_auth_asoc_init_active_key(asoc, GFP_KERNEL); + if (asoc && asoc->active_key_id == auth_key->sca_keynumber && + sctp_auth_asoc_init_active_key(asoc, GFP_KERNEL)) { + list_del_init(&cur_key->key_list); + sctp_auth_shkey_release(cur_key); + list_add(&shkey->key_list, sh_keys); + return -ENOMEM; + } + sctp_auth_shkey_release(shkey); return 0; } @@ -902,8 +907,13 @@ int sctp_auth_set_active_key(struct sctp_endpoint *ep, return -EINVAL; if (asoc) { + __u16 active_key_id = asoc->active_key_id; + asoc->active_key_id = key_id; - sctp_auth_asoc_init_active_key(asoc, GFP_KERNEL); + if (sctp_auth_asoc_init_active_key(asoc, GFP_KERNEL)) { + asoc->active_key_id = active_key_id; + return -ENOMEM; + } } else ep->active_key_id = key_id; diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index 3fd06a27105ddbfdaf9fc288558d57e471572341..83a89dcf75ed053b5179f27815671eb1354cef8f 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -384,6 +384,7 @@ static int sctp_prsctp_prune_unsent(struct sctp_association *asoc, { struct sctp_outq *q = &asoc->outqueue; struct sctp_chunk *chk, *temp; + struct sctp_stream_out *sout; q->sched->unsched_all(&asoc->stream); @@ -398,12 +399,14 @@ static int sctp_prsctp_prune_unsent(struct sctp_association *asoc, sctp_sched_dequeue_common(q, chk); asoc->sent_cnt_removable--; asoc->abandoned_unsent[SCTP_PR_INDEX(PRIO)]++; - if (chk->sinfo.sinfo_stream < asoc->stream.outcnt) { - struct sctp_stream_out *streamout = - SCTP_SO(&asoc->stream, chk->sinfo.sinfo_stream); - streamout->ext->abandoned_unsent[SCTP_PR_INDEX(PRIO)]++; - } + sout = SCTP_SO(&asoc->stream, chk->sinfo.sinfo_stream); + sout->ext->abandoned_unsent[SCTP_PR_INDEX(PRIO)]++; + + /* clear out_curr if all frag chunks are pruned */ + if (asoc->stream.out_curr == sout && + list_is_last(&chk->frag_list, &chk->msg->chunks)) + asoc->stream.out_curr = NULL; msg_len -= chk->skb->truesize + sizeof(struct sctp_chunk); sctp_chunk_free(chk); diff --git a/net/socket.c b/net/socket.c index abca62588f2192b5770d02753391dc2ff68af618..938ab3a89707549b5d394058fba48a5eb8ab4e76 100644 --- a/net/socket.c +++ b/net/socket.c @@ -1689,30 +1689,22 @@ SYSCALL_DEFINE2(listen, int, fd, int, backlog) return __sys_listen(fd, backlog); } -int __sys_accept4_file(struct file *file, unsigned file_flags, +struct file *do_accept(struct file *file, unsigned file_flags, struct sockaddr __user *upeer_sockaddr, - int __user *upeer_addrlen, int flags, - unsigned long nofile) + int __user *upeer_addrlen, int flags) { struct socket *sock, *newsock; struct file *newfile; - int err, len, newfd; + int err, len; struct sockaddr_storage address; - if (flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK)) - return -EINVAL; - - if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK)) - flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK; - sock = sock_from_file(file, &err); if (!sock) - goto out; + return ERR_PTR(err); - err = -ENFILE; newsock = sock_alloc(); if (!newsock) - goto out; + return ERR_PTR(-ENFILE); newsock->type = sock->type; newsock->ops = sock->ops; @@ -1723,18 +1715,9 @@ int __sys_accept4_file(struct file *file, unsigned file_flags, */ __module_get(newsock->ops->owner); - newfd = __get_unused_fd_flags(flags, nofile); - if (unlikely(newfd < 0)) { - err = newfd; - sock_release(newsock); - goto out; - } newfile = sock_alloc_file(newsock, flags, sock->sk->sk_prot_creator->name); - if (IS_ERR(newfile)) { - err = PTR_ERR(newfile); - put_unused_fd(newfd); - goto out; - } + if (IS_ERR(newfile)) + return newfile; err = security_socket_accept(sock, newsock); if (err) @@ -1759,16 +1742,38 @@ int __sys_accept4_file(struct file *file, unsigned file_flags, } /* File flags are not inherited via accept() unlike another OSes. */ - - fd_install(newfd, newfile); - err = newfd; -out: - return err; + return newfile; out_fd: fput(newfile); - put_unused_fd(newfd); - goto out; + return ERR_PTR(err); +} +int __sys_accept4_file(struct file *file, unsigned file_flags, + struct sockaddr __user *upeer_sockaddr, + int __user *upeer_addrlen, int flags, + unsigned long nofile) +{ + struct file *newfile; + int newfd; + + if (flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK)) + return -EINVAL; + + if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK)) + flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK; + + newfd = __get_unused_fd_flags(flags, nofile); + if (unlikely(newfd < 0)) + return newfd; + + newfile = do_accept(file, file_flags, upeer_sockaddr, upeer_addrlen, + flags); + if (IS_ERR(newfile)) { + put_unused_fd(newfd); + return PTR_ERR(newfile); + } + fd_install(newfd, newfile); + return newfd; } /* @@ -2182,6 +2187,17 @@ SYSCALL_DEFINE5(getsockopt, int, fd, int, level, int, optname, * Shutdown a socket. */ +int __sys_shutdown_sock(struct socket *sock, int how) +{ + int err; + + err = security_socket_shutdown(sock, how); + if (!err) + err = sock->ops->shutdown(sock, how); + + return err; +} + int __sys_shutdown(int fd, int how) { int err, fput_needed; @@ -2189,9 +2205,7 @@ int __sys_shutdown(int fd, int how) sock = sockfd_lookup_light(fd, &err, &fput_needed); if (sock != NULL) { - err = security_socket_shutdown(sock, how); - if (!err) - err = sock->ops->shutdown(sock, how); + err = __sys_shutdown_sock(sock, how); fput_light(sock->file, fput_needed); } return err; @@ -2406,10 +2420,6 @@ static int ___sys_sendmsg(struct socket *sock, struct user_msghdr __user *msg, long __sys_sendmsg_sock(struct socket *sock, struct msghdr *msg, unsigned int flags) { - /* disallow ancillary data requests from this path */ - if (msg->msg_control || msg->msg_controllen) - return -EINVAL; - return ____sys_sendmsg(sock, msg, flags, NULL, 0); } @@ -2618,12 +2628,6 @@ long __sys_recvmsg_sock(struct socket *sock, struct msghdr *msg, struct user_msghdr __user *umsg, struct sockaddr __user *uaddr, unsigned int flags) { - if (msg->msg_control || msg->msg_controllen) { - /* disallow ancillary data reqs unless cmsg is plain data */ - if (!(sock->ops->flags & PROTO_CMSG_DATA_ONLY)) - return -EINVAL; - } - return ____sys_recvmsg(sock, msg, umsg, uaddr, flags, 0); } diff --git a/net/tipc/discover.c b/net/tipc/discover.c index 14bc20604051d79bf69f31d1e1734fb7f6bfe588..2730310249e3cab7a818489b7728ec2ad547fbd9 100644 --- a/net/tipc/discover.c +++ b/net/tipc/discover.c @@ -147,8 +147,8 @@ static bool tipc_disc_addr_trial_msg(struct tipc_discoverer *d, { struct net *net = d->net; struct tipc_net *tn = tipc_net(net); - bool trial = time_before(jiffies, tn->addr_trial_end); u32 self = tipc_own_addr(net); + bool trial = time_before(jiffies, tn->addr_trial_end) && !self; if (mtyp == DSC_TRIAL_FAIL_MSG) { if (!trial) @@ -210,7 +210,10 @@ void tipc_disc_rcv(struct net *net, struct sk_buff *skb, u32 self; int err; - skb_linearize(skb); + if (skb_linearize(skb)) { + kfree_skb(skb); + return; + } hdr = buf_msg(skb); if (caps & TIPC_NODE_ID128) diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c index 49e89331365263050769e340387bfe77c88de303..2d62932b59878c68e3c966cff4e69bca4c3423c0 100644 --- a/net/tipc/netlink_compat.c +++ b/net/tipc/netlink_compat.c @@ -877,7 +877,7 @@ static int tipc_nl_compat_name_table_dump_header(struct tipc_nl_compat_msg *msg) }; ntq = (struct tipc_name_table_query *)TLV_DATA(msg->req); - if (TLV_GET_DATA_LEN(msg->req) < sizeof(struct tipc_name_table_query)) + if (TLV_GET_DATA_LEN(msg->req) < (int)sizeof(struct tipc_name_table_query)) return -EINVAL; depth = ntohl(ntq->depth); diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c index 13f3143609f9ef8e358010f5e9d0564c13a4e87f..89d8a2bd30cd0e8ebaed2f0d3d4de1f1422cf57b 100644 --- a/net/tipc/topsrv.c +++ b/net/tipc/topsrv.c @@ -176,7 +176,7 @@ static void tipc_conn_close(struct tipc_conn *con) conn_put(con); } -static struct tipc_conn *tipc_conn_alloc(struct tipc_topsrv *s) +static struct tipc_conn *tipc_conn_alloc(struct tipc_topsrv *s, struct socket *sock) { struct tipc_conn *con; int ret; @@ -202,10 +202,12 @@ static struct tipc_conn *tipc_conn_alloc(struct tipc_topsrv *s) } con->conid = ret; s->idr_in_use++; - spin_unlock_bh(&s->idr_lock); set_bit(CF_CONNECTED, &con->flags); con->server = s; + con->sock = sock; + conn_get(con); + spin_unlock_bh(&s->idr_lock); return con; } @@ -450,17 +452,24 @@ static void tipc_conn_data_ready(struct sock *sk) static void tipc_topsrv_accept(struct work_struct *work) { struct tipc_topsrv *srv = container_of(work, struct tipc_topsrv, awork); - struct socket *lsock = srv->listener; - struct socket *newsock; + struct socket *newsock, *lsock; struct tipc_conn *con; struct sock *newsk; int ret; + spin_lock_bh(&srv->idr_lock); + if (!srv->listener) { + spin_unlock_bh(&srv->idr_lock); + return; + } + lsock = srv->listener; + spin_unlock_bh(&srv->idr_lock); + while (1) { ret = kernel_accept(lsock, &newsock, O_NONBLOCK); if (ret < 0) return; - con = tipc_conn_alloc(srv); + con = tipc_conn_alloc(srv, newsock); if (IS_ERR(con)) { ret = PTR_ERR(con); sock_release(newsock); @@ -472,11 +481,11 @@ static void tipc_topsrv_accept(struct work_struct *work) newsk->sk_data_ready = tipc_conn_data_ready; newsk->sk_write_space = tipc_conn_write_space; newsk->sk_user_data = con; - con->sock = newsock; write_unlock_bh(&newsk->sk_callback_lock); /* Wake up receive process in case of 'SYN+' message */ newsk->sk_data_ready(newsk); + conn_put(con); } } @@ -489,7 +498,7 @@ static void tipc_topsrv_listener_data_ready(struct sock *sk) read_lock_bh(&sk->sk_callback_lock); srv = sk->sk_user_data; - if (srv->listener) + if (srv) queue_work(srv->rcv_wq, &srv->awork); read_unlock_bh(&sk->sk_callback_lock); } @@ -568,19 +577,19 @@ bool tipc_topsrv_kern_subscr(struct net *net, u32 port, u32 type, u32 lower, sub.seq.upper = upper; sub.timeout = TIPC_WAIT_FOREVER; sub.filter = filter; - *(u32 *)&sub.usr_handle = port; + *(u64 *)&sub.usr_handle = (u64)port; - con = tipc_conn_alloc(tipc_topsrv(net)); + con = tipc_conn_alloc(tipc_topsrv(net), NULL); if (IS_ERR(con)) return false; *conid = con->conid; - con->sock = NULL; rc = tipc_conn_rcv_sub(tipc_topsrv(net), con, &sub); - if (rc >= 0) - return true; + if (rc) + conn_put(con); + conn_put(con); - return false; + return !rc; } void tipc_topsrv_kern_unsubscr(struct net *net, int conid) @@ -699,8 +708,9 @@ static void tipc_topsrv_stop(struct net *net) __module_get(lsock->sk->sk_prot_creator->owner); srv->listener = NULL; spin_unlock_bh(&srv->idr_lock); - sock_release(lsock); + tipc_topsrv_work_stop(srv); + sock_release(lsock); idr_destroy(&srv->conn_idr); kfree(srv); } diff --git a/net/unix/garbage.c b/net/unix/garbage.c index d45d5366115a769b21bfc1db5a67f7d53c3fa9b8..dc27635403932154f3dec069c2e10d2ae365d8cb 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -204,6 +204,7 @@ void wait_for_unix_gc(void) /* The external entry point: unix_gc() */ void unix_gc(void) { + struct sk_buff *next_skb, *skb; struct unix_sock *u; struct unix_sock *next; struct sk_buff_head hitlist; @@ -297,11 +298,30 @@ void unix_gc(void) spin_unlock(&unix_gc_lock); + /* We need io_uring to clean its registered files, ignore all io_uring + * originated skbs. It's fine as io_uring doesn't keep references to + * other io_uring instances and so killing all other files in the cycle + * will put all io_uring references forcing it to go through normal + * release.path eventually putting registered files. + */ + skb_queue_walk_safe(&hitlist, skb, next_skb) { + if (skb->scm_io_uring) { + __skb_unlink(skb, &hitlist); + skb_queue_tail(&skb->sk->sk_receive_queue, skb); + } + } + /* Here we are. Hitlist is filled. Die. */ __skb_queue_purge(&hitlist); spin_lock(&unix_gc_lock); + /* There could be io_uring registered files, just push them back to + * the inflight list + */ + list_for_each_entry_safe(u, next, &gc_candidates, link) + list_move_tail(&u->link, &gc_inflight_list); + /* All candidates should have been detached by now. */ BUG_ON(!list_empty(&gc_candidates)); diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 5c0439c3bcfa4f767e96eb43dc1e817183252ed6..3a5bf3f42274a44e4aa87c9198692ef10c1b229b 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -1200,7 +1200,7 @@ EXPORT_SYMBOL_GPL(virtio_transport_recv_pkt); void virtio_transport_free_pkt(struct virtio_vsock_pkt *pkt) { - kfree(pkt->buf); + kvfree(pkt->buf); kfree(pkt); } EXPORT_SYMBOL_GPL(virtio_transport_free_pkt); diff --git a/net/wireless/reg.c b/net/wireless/reg.c index fd848609e656a5689624c27ab9b20c4c3a363e24..a1e64d967bd386011b229434c29c521ad4c750f4 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -1064,6 +1064,8 @@ MODULE_FIRMWARE("regulatory.db"); static int query_regdb_file(const char *alpha2) { + int err; + ASSERT_RTNL(); if (regdb) @@ -1073,9 +1075,13 @@ static int query_regdb_file(const char *alpha2) if (!alpha2) return -ENOMEM; - return request_firmware_nowait(THIS_MODULE, true, "regulatory.db", - ®_pdev->dev, GFP_KERNEL, - (void *)alpha2, regdb_fw_cb); + err = request_firmware_nowait(THIS_MODULE, true, "regulatory.db", + ®_pdev->dev, GFP_KERNEL, + (void *)alpha2, regdb_fw_cb); + if (err) + kfree(alpha2); + + return err; } int reg_reload_regdb(void) diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 22d169923261fc08f94947118ca16e5d26387566..15119c49c0934245cfd99424969557e1110fa193 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -1669,7 +1669,9 @@ cfg80211_update_known_bss(struct cfg80211_registered_device *rdev, if (old == rcu_access_pointer(known->pub.ies)) rcu_assign_pointer(known->pub.ies, new->pub.beacon_ies); - cfg80211_update_hidden_bsses(known, new->pub.beacon_ies, old); + cfg80211_update_hidden_bsses(known, + rcu_access_pointer(new->pub.beacon_ies), + old); if (old) kfree_rcu((struct cfg80211_bss_ies *)old, rcu_head); diff --git a/net/x25/x25_dev.c b/net/x25/x25_dev.c index 25bf72ee6cad070804f26ab353b5192a8ebbf923..226397add422a29bea21783c79e54abd7aa391bd 100644 --- a/net/x25/x25_dev.c +++ b/net/x25/x25_dev.c @@ -117,7 +117,7 @@ int x25_lapb_receive_frame(struct sk_buff *skb, struct net_device *dev, if (!pskb_may_pull(skb, 1)) { x25_neigh_put(nb); - return 0; + goto drop; } switch (skb->data[0]) { diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index c255aac6b816b4911b435ae76cd3377b88f2d9dd..8b8e957a69c36eb76ccea71e213427078c4323fd 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -97,6 +97,18 @@ static void xfrm_outer_mode_prep(struct xfrm_state *x, struct sk_buff *skb) } } +static inline bool xmit_xfrm_check_overflow(struct sk_buff *skb) +{ + struct xfrm_offload *xo = xfrm_offload(skb); + __u32 seq = xo->seq.low; + + seq += skb_shinfo(skb)->gso_segs; + if (unlikely(seq < xo->seq.low)) + return true; + + return false; +} + struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t features, bool *again) { int err; @@ -134,7 +146,8 @@ struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t featur return skb; } - if (skb_is_gso(skb) && unlikely(x->xso.dev != dev)) { + if (skb_is_gso(skb) && (unlikely(x->xso.dev != dev) || + unlikely(xmit_xfrm_check_overflow(skb)))) { struct sk_buff *segs; /* Packet got rerouted, fixup features and segment it. */ diff --git a/net/xfrm/xfrm_ipcomp.c b/net/xfrm/xfrm_ipcomp.c index 0814320472f188a34cde9e3d42490a5155518f8c..24ac6805275e9c2554eebfb2a906c1b7a2474b92 100644 --- a/net/xfrm/xfrm_ipcomp.c +++ b/net/xfrm/xfrm_ipcomp.c @@ -212,6 +212,7 @@ static void ipcomp_free_scratches(void) vfree(*per_cpu_ptr(scratches, i)); free_percpu(scratches); + ipcomp_scratches = NULL; } static void * __percpu *ipcomp_alloc_scratches(void) diff --git a/net/xfrm/xfrm_replay.c b/net/xfrm/xfrm_replay.c index c6a4338a0d08e82ee145e057012d61416f3b451f..65d009e3b6bbe4036cb5a0568f4fec939fc05946 100644 --- a/net/xfrm/xfrm_replay.c +++ b/net/xfrm/xfrm_replay.c @@ -657,7 +657,7 @@ static int xfrm_replay_overflow_offload_esn(struct xfrm_state *x, struct sk_buff oseq += skb_shinfo(skb)->gso_segs; } - if (unlikely(oseq < replay_esn->oseq)) { + if (unlikely(xo->seq.low < replay_esn->oseq)) { XFRM_SKB_CB(skb)->seq.output.hi = ++oseq_hi; xo->seq.hi = oseq_hi; replay_esn->oseq_hi = oseq_hi; diff --git a/scripts/Kbuild.include b/scripts/Kbuild.include index f247e691562d438816eed3e1f3eb52e75408b568..ba2a47576dbfcaa992c7430886f28d37ffcb8d05 100644 --- a/scripts/Kbuild.include +++ b/scripts/Kbuild.include @@ -95,8 +95,29 @@ echo-cmd = $(if $($(quiet)cmd_$(1)),\ quiet_redirect := silent_redirect := exec >/dev/null; +# Delete the target on interruption +# +# GNU Make automatically deletes the target if it has already been changed by +# the interrupted recipe. So, you can safely stop the build by Ctrl-C (Make +# will delete incomplete targets), and resume it later. +# +# However, this does not work when the stderr is piped to another program, like +# $ make >&2 | tee log +# Make dies with SIGPIPE before cleaning the targets. +# +# To address it, we clean the target in signal traps. +# +# Make deletes the target when it catches SIGHUP, SIGINT, SIGQUIT, SIGTERM. +# So, we cover them, and also SIGPIPE just in case. +# +# Of course, this is unneeded for phony targets. +delete-on-interrupt = \ + $(if $(filter-out $(PHONY), $@), \ + $(foreach sig, HUP INT QUIT TERM PIPE, \ + trap 'rm -f $@; trap - $(sig); kill -s $(sig) $$$$' $(sig);)) + # printing commands -cmd = @set -e; $(echo-cmd) $($(quiet)redirect) $(cmd_$(1)) +cmd = @set -e; $(echo-cmd) $($(quiet)redirect) $(delete-on-interrupt) $(cmd_$(1)) ### # if_changed - execute command if any prerequisite is newer than diff --git a/scripts/extract-cert.c b/scripts/extract-cert.c index 3034d991ba55279df22fb9ec20ddf0f06f3d9dc5..71b2980230226219e1bf03114d148e0851a703a3 100644 --- a/scripts/extract-cert.c +++ b/scripts/extract-cert.c @@ -23,6 +23,13 @@ #include #include +/* + * OpenSSL 3.0 deprecates the OpenSSL's ENGINE API. + * + * Remove this if/when that API is no longer used + */ +#pragma GCC diagnostic ignored "-Wdeprecated-declarations" + #define PKEY_ID_PKCS7 2 static __attribute__((noreturn)) diff --git a/scripts/kernel-doc b/scripts/kernel-doc index 6325bec3f66f855a4f35bc7577ad25502431ee95..19af6dd160e6b7e8ae2ad6c0bbe7360e8a558443 100755 --- a/scripts/kernel-doc +++ b/scripts/kernel-doc @@ -1215,6 +1215,13 @@ sub dump_struct($$) { $members =~ s/\s*CRYPTO_MINALIGN_ATTR/ /gos; $members =~ s/\s*____cacheline_aligned_in_smp/ /gos; $members =~ s/\s*____cacheline_aligned/ /gos; + # unwrap struct_group(): + # - first eat non-declaration parameters and rewrite for final match + # - then remove macro, outer parens, and trailing semicolon + $members =~ s/\bstruct_group\s*\(([^,]*,)/STRUCT_GROUP(/gos; + $members =~ s/\bstruct_group_(attr|tagged)\s*\(([^,]*,){2}/STRUCT_GROUP(/gos; + $members =~ s/\b__struct_group\s*\(([^,]*,){3}/STRUCT_GROUP(/gos; + $members =~ s/\bSTRUCT_GROUP(\(((?:(?>[^)(]+)|(?1))*)\))[^;]*;/$2/gos; # replace DECLARE_BITMAP $members =~ s/__ETHTOOL_DECLARE_LINK_MODE_MASK\s*\(([^\)]+)\)/DECLARE_BITMAP($1, __ETHTOOL_LINK_MODE_MASK_NBITS)/gos; diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh index f6e395dcf77f669b00269c74255fa934edccde7f..2631ab4ce9fde236c261270ca286b7761bc6b62c 100755 --- a/scripts/link-vmlinux.sh +++ b/scripts/link-vmlinux.sh @@ -234,7 +234,7 @@ gen_btf() vmlinux_link ${1} info "BTF" ${2} - LLVM_OBJCOPY=${OBJCOPY} ${PAHOLE} -J ${1} + LLVM_OBJCOPY="${OBJCOPY}" ${PAHOLE} -J ${PAHOLE_FLAGS} ${1} # Create ${2} which contains just .BTF section but no symbols. Add # SHF_ALLOC because .BTF will be part of the vmlinux image. --strip-all diff --git a/scripts/package/mkspec b/scripts/package/mkspec index 7c477ca7dc9826a0d4bd63e332b4d5959894836a..951cc60e5a903766f987f8c77738a383e85db114 100755 --- a/scripts/package/mkspec +++ b/scripts/package/mkspec @@ -85,10 +85,10 @@ $S mkdir -p %{buildroot}/boot %ifarch ia64 mkdir -p %{buildroot}/boot/efi - cp \$($MAKE image_name) %{buildroot}/boot/efi/vmlinuz-$KERNELRELEASE + cp \$($MAKE -s image_name) %{buildroot}/boot/efi/vmlinuz-$KERNELRELEASE ln -s efi/vmlinuz-$KERNELRELEASE %{buildroot}/boot/ %else - cp \$($MAKE image_name) %{buildroot}/boot/vmlinuz-$KERNELRELEASE + cp \$($MAKE -s image_name) %{buildroot}/boot/vmlinuz-$KERNELRELEASE %endif $M $MAKE %{?_smp_mflags} INSTALL_MOD_PATH=%{buildroot} modules_install $MAKE %{?_smp_mflags} INSTALL_HDR_PATH=%{buildroot}/usr headers_install diff --git a/scripts/pahole-flags.sh b/scripts/pahole-flags.sh new file mode 100755 index 0000000000000000000000000000000000000000..8c82173e42e523dc9b98c1ada893b2d672b4c172 --- /dev/null +++ b/scripts/pahole-flags.sh @@ -0,0 +1,21 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 + +extra_paholeopt= + +if ! [ -x "$(command -v ${PAHOLE})" ]; then + exit 0 +fi + +pahole_ver=$(${PAHOLE} --version | sed -E 's/v([0-9]+)\.([0-9]+)/\1\2/') + +if [ "${pahole_ver}" -ge "118" ] && [ "${pahole_ver}" -le "121" ]; then + # pahole 1.18 through 1.21 can't handle zero-sized per-CPU vars + extra_paholeopt="${extra_paholeopt} --skip_encoding_btf_vars" +fi + +if [ "${pahole_ver}" -ge "124" ]; then + extra_paholeopt="${extra_paholeopt} --skip_encoding_btf_enum64" +fi + +echo ${extra_paholeopt} diff --git a/scripts/selinux/install_policy.sh b/scripts/selinux/install_policy.sh index 2dccf141241d76e1620c68b2c32149f025c9f218..20af56ce245c568ad9be63bc33d7f9133a07315c 100755 --- a/scripts/selinux/install_policy.sh +++ b/scripts/selinux/install_policy.sh @@ -78,7 +78,7 @@ cd /etc/selinux/dummy/contexts/files $SF -F file_contexts / mounts=`cat /proc/$$/mounts | \ - egrep "ext[234]|jfs|xfs|reiserfs|jffs2|gfs2|btrfs|f2fs|ocfs2" | \ + grep -E "ext[234]|jfs|xfs|reiserfs|jffs2|gfs2|btrfs|f2fs|ocfs2" | \ awk '{ print $2 '}` $SF -F file_contexts $mounts diff --git a/scripts/sign-file.c b/scripts/sign-file.c index 8f06328d1cd1116e0045f587beb7d6ccf72d162b..513367e634bee0145cc588b29e8e1ab3f339d607 100644 --- a/scripts/sign-file.c +++ b/scripts/sign-file.c @@ -29,6 +29,13 @@ #include #include +/* + * OpenSSL 3.0 deprecates the OpenSSL's ENGINE API. + * + * Remove this if/when that API is no longer used + */ +#pragma GCC diagnostic ignored "-Wdeprecated-declarations" + /* * Use CMS if we have openssl-1.0.0 or newer available - otherwise we have to * assume that it's not available and its header file is missing and that we diff --git a/security/Kconfig.hardening b/security/Kconfig.hardening index a56c36470cb195c30f57faedb8701ef252722dae..a69055b32caceb04f6e6a1a0708daf0b8136b6f4 100644 --- a/security/Kconfig.hardening +++ b/security/Kconfig.hardening @@ -22,13 +22,23 @@ menu "Memory initialization" config CC_HAS_AUTO_VAR_INIT_PATTERN def_bool $(cc-option,-ftrivial-auto-var-init=pattern) -config CC_HAS_AUTO_VAR_INIT_ZERO +config CC_HAS_AUTO_VAR_INIT_ZERO_BARE + def_bool $(cc-option,-ftrivial-auto-var-init=zero) + +config CC_HAS_AUTO_VAR_INIT_ZERO_ENABLER + # Clang 16 and later warn about using the -enable flag, but it + # is required before then. def_bool $(cc-option,-ftrivial-auto-var-init=zero -enable-trivial-auto-var-init-zero-knowing-it-will-be-removed-from-clang) + depends on !CC_HAS_AUTO_VAR_INIT_ZERO_BARE + +config CC_HAS_AUTO_VAR_INIT_ZERO + def_bool CC_HAS_AUTO_VAR_INIT_ZERO_BARE || CC_HAS_AUTO_VAR_INIT_ZERO_ENABLER choice prompt "Initialize kernel stack variables at function entry" default GCC_PLUGIN_STRUCTLEAK_BYREF_ALL if COMPILE_TEST && GCC_PLUGINS default INIT_STACK_ALL_PATTERN if COMPILE_TEST && CC_HAS_AUTO_VAR_INIT_PATTERN + default INIT_STACK_ALL_ZERO if CC_HAS_AUTO_VAR_INIT_ZERO default INIT_STACK_NONE help This option enables initialization of stack variables at @@ -39,11 +49,11 @@ choice syscalls. This chooses the level of coverage over classes of potentially - uninitialized variables. The selected class will be + uninitialized variables. The selected class of variable will be initialized before use in a function. config INIT_STACK_NONE - bool "no automatic initialization (weakest)" + bool "no automatic stack variable initialization (weakest)" help Disable automatic stack variable initialization. This leaves the kernel vulnerable to the standard @@ -80,7 +90,7 @@ choice and is disallowed. config GCC_PLUGIN_STRUCTLEAK_BYREF_ALL - bool "zero-init anything passed by reference (very strong)" + bool "zero-init everything passed by reference (very strong)" depends on GCC_PLUGINS depends on !(KASAN && KASAN_STACK) select GCC_PLUGIN_STRUCTLEAK @@ -91,33 +101,44 @@ choice of uninitialized stack variable exploits and information exposures. + As a side-effect, this keeps a lot of variables on the + stack that can otherwise be optimized out, so combining + this with CONFIG_KASAN_STACK can lead to a stack overflow + and is disallowed. + config INIT_STACK_ALL_PATTERN - bool "0xAA-init everything on the stack (strongest)" + bool "pattern-init everything (strongest)" depends on CC_HAS_AUTO_VAR_INIT_PATTERN help - Initializes everything on the stack with a 0xAA - pattern. This is intended to eliminate all classes - of uninitialized stack variable exploits and information - exposures, even variables that were warned to have been - left uninitialized. + Initializes everything on the stack (including padding) + with a specific debug value. This is intended to eliminate + all classes of uninitialized stack variable exploits and + information exposures, even variables that were warned about + having been left uninitialized. Pattern initialization is known to provoke many existing bugs related to uninitialized locals, e.g. pointers receive - non-NULL values, buffer sizes and indices are very big. + non-NULL values, buffer sizes and indices are very big. The + pattern is situation-specific; Clang on 64-bit uses 0xAA + repeating for all types and padding except float and double + which use 0xFF repeating (-NaN). Clang on 32-bit uses 0xFF + repeating for all types and padding. config INIT_STACK_ALL_ZERO - bool "zero-init everything on the stack (strongest and safest)" + bool "zero-init everything (strongest and safest)" depends on CC_HAS_AUTO_VAR_INIT_ZERO help - Initializes everything on the stack with a zero - value. This is intended to eliminate all classes - of uninitialized stack variable exploits and information - exposures, even variables that were warned to have been - left uninitialized. - - Zero initialization provides safe defaults for strings, - pointers, indices and sizes, and is therefore - more suitable as a security mitigation measure. + Initializes everything on the stack (including padding) + with a zero value. This is intended to eliminate all + classes of uninitialized stack variable exploits and + information exposures, even variables that were warned + about having been left uninitialized. + + Zero initialization provides safe defaults for strings + (immediately NUL-terminated), pointers (NULL), indices + (index 0), and sizes (0 length), so it is therefore more + suitable as a production security mitigation than pattern + initialization. endchoice diff --git a/security/commoncap.c b/security/commoncap.c index 4bdb44c9e698e229d28728964b10790004d7511f..09b402c88f46f3e1585bf4566b4b5b9b6b3eb3dd 100644 --- a/security/commoncap.c +++ b/security/commoncap.c @@ -392,8 +392,10 @@ int cap_inode_getsecurity(struct inode *inode, const char *name, void **buffer, &tmpbuf, size, GFP_NOFS); dput(dentry); - if (ret < 0 || !tmpbuf) - return ret; + if (ret < 0 || !tmpbuf) { + size = ret; + goto out_free; + } fs_ns = inode->i_sb->s_user_ns; cap = (struct vfs_cap_data *) tmpbuf; diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c index 5df46e23824497d06863362790d4cfa14cef07d0..3d63372e6dac561792eae13a304abec3c45123db 100644 --- a/security/selinux/ss/services.c +++ b/security/selinux/ss/services.c @@ -2013,7 +2013,8 @@ static inline int convert_context_handle_invalid_context( * in `newc'. Verify that the context is valid * under the new policy. */ -static int convert_context(struct context *oldc, struct context *newc, void *p) +static int convert_context(struct context *oldc, struct context *newc, void *p, + gfp_t gfp_flags) { struct convert_context_args *args; struct ocontext *oc; @@ -2027,7 +2028,7 @@ static int convert_context(struct context *oldc, struct context *newc, void *p) args = p; if (oldc->str) { - s = kstrdup(oldc->str, GFP_KERNEL); + s = kstrdup(oldc->str, gfp_flags); if (!s) return -ENOMEM; diff --git a/security/selinux/ss/sidtab.c b/security/selinux/ss/sidtab.c index 656d50b09f7629bc22b884bf4b1fea1039ca243c..1981c5af13e0aff9d247523da6cbfdc3da948557 100644 --- a/security/selinux/ss/sidtab.c +++ b/security/selinux/ss/sidtab.c @@ -325,7 +325,7 @@ int sidtab_context_to_sid(struct sidtab *s, struct context *context, } rc = convert->func(context, &dst_convert->context, - convert->args); + convert->args, GFP_ATOMIC); if (rc) { context_destroy(&dst->context); goto out_unlock; @@ -404,7 +404,7 @@ static int sidtab_convert_tree(union sidtab_entry_inner *edst, while (i < SIDTAB_LEAF_ENTRIES && *pos < count) { rc = convert->func(&esrc->ptr_leaf->entries[i].context, &edst->ptr_leaf->entries[i].context, - convert->args); + convert->args, GFP_KERNEL); if (rc) return rc; (*pos)++; diff --git a/security/selinux/ss/sidtab.h b/security/selinux/ss/sidtab.h index 4eff0e49dcb22e490e2a880fd72099b4274e6ec5..9fce0d553fe2c92c84c59e2c045dabda1f0f5b1f 100644 --- a/security/selinux/ss/sidtab.h +++ b/security/selinux/ss/sidtab.h @@ -65,7 +65,7 @@ struct sidtab_isid_entry { }; struct sidtab_convert_params { - int (*func)(struct context *oldc, struct context *newc, void *args); + int (*func)(struct context *oldc, struct context *newc, void *args, gfp_t gfp_flags); void *args; struct sidtab *target; }; diff --git a/sound/aoa/soundbus/i2sbus/core.c b/sound/aoa/soundbus/i2sbus/core.c index faf6b03131ee41147907879fc2ac5f87d83b89e5..51ed2f34b276de1317862165ca1485e05aab64ef 100644 --- a/sound/aoa/soundbus/i2sbus/core.c +++ b/sound/aoa/soundbus/i2sbus/core.c @@ -147,6 +147,7 @@ static int i2sbus_get_and_fixup_rsrc(struct device_node *np, int index, return rc; } +/* Returns 1 if added, 0 for otherwise; don't return a negative value! */ /* FIXME: look at device node refcounting */ static int i2sbus_add_dev(struct macio_dev *macio, struct i2sbus_control *control, @@ -213,7 +214,7 @@ static int i2sbus_add_dev(struct macio_dev *macio, * either as the second one in that case is just a modem. */ if (!ok) { kfree(dev); - return -ENODEV; + return 0; } mutex_init(&dev->lock); @@ -302,6 +303,10 @@ static int i2sbus_add_dev(struct macio_dev *macio, if (soundbus_add_one(&dev->sound)) { printk(KERN_DEBUG "i2sbus: device registration error!\n"); + if (dev->sound.ofdev.dev.kobj.state_initialized) { + soundbus_dev_put(&dev->sound); + return 0; + } goto err; } diff --git a/sound/core/pcm_dmaengine.c b/sound/core/pcm_dmaengine.c index 1fc2fa07757445948afc98c7e9a3fee891f0acba..0fe93b423c4edf5372749a62ad81e1005197a5d1 100644 --- a/sound/core/pcm_dmaengine.c +++ b/sound/core/pcm_dmaengine.c @@ -132,12 +132,14 @@ EXPORT_SYMBOL_GPL(snd_dmaengine_pcm_set_config_from_dai_data); static void dmaengine_pcm_dma_complete(void *arg) { + unsigned int new_pos; struct snd_pcm_substream *substream = arg; struct dmaengine_pcm_runtime_data *prtd = substream_to_prtd(substream); - prtd->pos += snd_pcm_lib_period_bytes(substream); - if (prtd->pos >= snd_pcm_lib_buffer_bytes(substream)) - prtd->pos = 0; + new_pos = prtd->pos + snd_pcm_lib_period_bytes(substream); + if (new_pos >= snd_pcm_lib_buffer_bytes(substream)) + new_pos = 0; + prtd->pos = new_pos; snd_pcm_period_elapsed(substream); } diff --git a/sound/core/rawmidi.c b/sound/core/rawmidi.c index 257ad5206240fd0cff47545f505a38a2dca8c81b..0d91143eb4647f33c44c2b74afc6c556c7a5ea5a 100644 --- a/sound/core/rawmidi.c +++ b/sound/core/rawmidi.c @@ -1736,10 +1736,8 @@ static int snd_rawmidi_free(struct snd_rawmidi *rmidi) snd_info_free_entry(rmidi->proc_entry); rmidi->proc_entry = NULL; - mutex_lock(®ister_mutex); if (rmidi->ops && rmidi->ops->dev_unregister) rmidi->ops->dev_unregister(rmidi); - mutex_unlock(®ister_mutex); snd_rawmidi_free_substreams(&rmidi->streams[SNDRV_RAWMIDI_STREAM_INPUT]); snd_rawmidi_free_substreams(&rmidi->streams[SNDRV_RAWMIDI_STREAM_OUTPUT]); diff --git a/sound/core/sound_oss.c b/sound/core/sound_oss.c index 610f317bea9d1791196f2dc93006b06ee317f43a..99874e80b6829f14a700d59a83a5cd8af49a2679 100644 --- a/sound/core/sound_oss.c +++ b/sound/core/sound_oss.c @@ -162,7 +162,6 @@ int snd_unregister_oss_device(int type, struct snd_card *card, int dev) mutex_unlock(&sound_oss_mutex); return -ENOENT; } - unregister_sound_special(minor); switch (SNDRV_MINOR_OSS_DEVICE(minor)) { case SNDRV_MINOR_OSS_PCM: track2 = SNDRV_MINOR_OSS(cidx, SNDRV_MINOR_OSS_AUDIO); @@ -174,12 +173,18 @@ int snd_unregister_oss_device(int type, struct snd_card *card, int dev) track2 = SNDRV_MINOR_OSS(cidx, SNDRV_MINOR_OSS_DMMIDI1); break; } - if (track2 >= 0) { - unregister_sound_special(track2); + if (track2 >= 0) snd_oss_minors[track2] = NULL; - } snd_oss_minors[minor] = NULL; mutex_unlock(&sound_oss_mutex); + + /* call unregister_sound_special() outside sound_oss_mutex; + * otherwise may deadlock, as it can trigger the release of a card + */ + unregister_sound_special(minor); + if (track2 >= 0) + unregister_sound_special(track2); + kfree(mptr); return 0; } diff --git a/sound/hda/hdac_sysfs.c b/sound/hda/hdac_sysfs.c index e56e8332590310f8de65efd3701553544d0e1b0b..bcf302f5115ac9fd414ac00316a4098e19ee9c06 100644 --- a/sound/hda/hdac_sysfs.c +++ b/sound/hda/hdac_sysfs.c @@ -346,8 +346,10 @@ static int add_widget_node(struct kobject *parent, hda_nid_t nid, return -ENOMEM; kobject_init(kobj, &widget_ktype); err = kobject_add(kobj, parent, "%02x", nid); - if (err < 0) + if (err < 0) { + kobject_put(kobj); return err; + } err = sysfs_create_group(kobj, group); if (err < 0) { kobject_put(kobj); diff --git a/sound/pci/ac97/ac97_codec.c b/sound/pci/ac97/ac97_codec.c index 963731cf0d8c880f6c5ba5c9235dad01ca040ac5..cd66632bf1c37000b3a208f2cd541e1e4503c0f4 100644 --- a/sound/pci/ac97/ac97_codec.c +++ b/sound/pci/ac97/ac97_codec.c @@ -1946,6 +1946,7 @@ static int snd_ac97_dev_register(struct snd_device *device) snd_ac97_get_short_name(ac97)); if ((err = device_register(&ac97->dev)) < 0) { ac97_err(ac97, "Can't register ac97 bus\n"); + put_device(&ac97->dev); ac97->dev.bus = NULL; return err; } diff --git a/sound/pci/au88x0/au88x0.h b/sound/pci/au88x0/au88x0.h index 0aa7af049b1b98f690d4cf288b39154b840eb829..6cbb2bc4a0483a952ca8866589f92b5be962c220 100644 --- a/sound/pci/au88x0/au88x0.h +++ b/sound/pci/au88x0/au88x0.h @@ -141,7 +141,7 @@ struct snd_vortex { #ifndef CHIP_AU8810 stream_t dma_wt[NR_WT]; wt_voice_t wt_voice[NR_WT]; /* WT register cache. */ - char mixwt[(NR_WT / NR_WTPB) * 6]; /* WT mixin objects */ + s8 mixwt[(NR_WT / NR_WTPB) * 6]; /* WT mixin objects */ #endif /* Global resources */ @@ -235,8 +235,8 @@ static int vortex_alsafmt_aspfmt(snd_pcm_format_t alsafmt, vortex_t *v); static void vortex_connect_default(vortex_t * vortex, int en); static int vortex_adb_allocroute(vortex_t * vortex, int dma, int nr_ch, int dir, int type, int subdev); -static char vortex_adb_checkinout(vortex_t * vortex, int resmap[], int out, - int restype); +static int vortex_adb_checkinout(vortex_t * vortex, int resmap[], int out, + int restype); #ifndef CHIP_AU8810 static int vortex_wt_allocroute(vortex_t * vortex, int dma, int nr_ch); static void vortex_wt_connect(vortex_t * vortex, int en); diff --git a/sound/pci/au88x0/au88x0_core.c b/sound/pci/au88x0/au88x0_core.c index 5180f1bd1326c32b699d0c6ab4b3d4e2b24ea575..0b04436ac017e657642a2e8757ff4fa7c088269e 100644 --- a/sound/pci/au88x0/au88x0_core.c +++ b/sound/pci/au88x0/au88x0_core.c @@ -1998,7 +1998,7 @@ static const int resnum[VORTEX_RESOURCE_LAST] = out: Mean checkout if != 0. Else mean Checkin resource. restype: Indicates type of resource to be checked in or out. */ -static char +static int vortex_adb_checkinout(vortex_t * vortex, int resmap[], int out, int restype) { int i, qty = resnum[restype], resinuse = 0; diff --git a/sound/pci/hda/hda_beep.c b/sound/pci/hda/hda_beep.c index 53a2b89f8983ce4f1e2733d62836f68f09668429..e63621bcb21427b6ecc1e5516f37ca38ac1cef2f 100644 --- a/sound/pci/hda/hda_beep.c +++ b/sound/pci/hda/hda_beep.c @@ -118,6 +118,12 @@ static int snd_hda_beep_event(struct input_dev *dev, unsigned int type, return 0; } +static void turn_on_beep(struct hda_beep *beep) +{ + if (beep->keep_power_at_enable) + snd_hda_power_up_pm(beep->codec); +} + static void turn_off_beep(struct hda_beep *beep) { cancel_work_sync(&beep->beep_work); @@ -125,6 +131,8 @@ static void turn_off_beep(struct hda_beep *beep) /* turn off beep */ generate_tone(beep, 0); } + if (beep->keep_power_at_enable) + snd_hda_power_down_pm(beep->codec); } /** @@ -140,7 +148,9 @@ int snd_hda_enable_beep_device(struct hda_codec *codec, int enable) enable = !!enable; if (beep->enabled != enable) { beep->enabled = enable; - if (!enable) + if (enable) + turn_on_beep(beep); + else turn_off_beep(beep); return 1; } @@ -167,7 +177,8 @@ static int beep_dev_disconnect(struct snd_device *device) input_unregister_device(beep->dev); else input_free_device(beep->dev); - turn_off_beep(beep); + if (beep->enabled) + turn_off_beep(beep); return 0; } diff --git a/sound/pci/hda/hda_beep.h b/sound/pci/hda/hda_beep.h index a25358a4807abfbc581e352b8ce63811da4f172b..db76e3ddba65445bc8e47257436d6f6cb51df142 100644 --- a/sound/pci/hda/hda_beep.h +++ b/sound/pci/hda/hda_beep.h @@ -25,6 +25,7 @@ struct hda_beep { unsigned int enabled:1; unsigned int linear_tone:1; /* linear tone for IDT/STAC codec */ unsigned int playing:1; + unsigned int keep_power_at_enable:1; /* set by driver */ struct work_struct beep_work; /* scheduled task for beep event */ struct mutex mutex; void (*power_hook)(struct hda_beep *beep, bool on); diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 26dfa8558792f29d57ed3419f183d5ba99f928d7..494bfd2135a9ef0fdc48120998c5b3931ce58968 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -2749,6 +2749,9 @@ static const struct pci_device_id azx_ids[] = { { PCI_DEVICE(0x1002, 0xab28), .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS | AZX_DCAPS_PM_RUNTIME }, + { PCI_DEVICE(0x1002, 0xab30), + .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS | + AZX_DCAPS_PM_RUNTIME }, { PCI_DEVICE(0x1002, 0xab38), .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS | AZX_DCAPS_PM_RUNTIME }, diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c index f774b2ac9720c75cdd9d0cdecae1a6062f0cf0aa..82f14c3f642bdb9b9f2cefd133f56ae08456f0e5 100644 --- a/sound/pci/hda/patch_ca0132.c +++ b/sound/pci/hda/patch_ca0132.c @@ -1272,6 +1272,7 @@ static const struct snd_pci_quirk ca0132_quirks[] = { SND_PCI_QUIRK(0x1458, 0xA026, "Gigabyte G1.Sniper Z97", QUIRK_R3DI), SND_PCI_QUIRK(0x1458, 0xA036, "Gigabyte GA-Z170X-Gaming 7", QUIRK_R3DI), SND_PCI_QUIRK(0x3842, 0x1038, "EVGA X99 Classified", QUIRK_R3DI), + SND_PCI_QUIRK(0x3842, 0x1055, "EVGA Z390 DARK", QUIRK_R3DI), SND_PCI_QUIRK(0x1102, 0x0013, "Recon3D", QUIRK_R3D), SND_PCI_QUIRK(0x1102, 0x0018, "Recon3D", QUIRK_R3D), SND_PCI_QUIRK(0x1102, 0x0051, "Sound Blaster AE-5", QUIRK_AE5), diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index c3fcf478037f93190bb3fa93c5d9e3ff2f91eb2c..b1c57c65f6cd5f4515f17beefb8f167f5b963c97 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -2684,9 +2684,6 @@ static void generic_acomp_pin_eld_notify(void *audio_ptr, int port, int dev_id) */ if (codec->core.dev.power.power_state.event == PM_EVENT_SUSPEND) return; - /* ditto during suspend/resume process itself */ - if (snd_hdac_is_in_pm(&codec->core)) - return; check_presence_and_report(codec, pin_nid, dev_id); } @@ -2870,9 +2867,6 @@ static void intel_pin_eld_notify(void *audio_ptr, int port, int pipe) */ if (codec->core.dev.power.power_state.event == PM_EVENT_SUSPEND) return; - /* ditto during suspend/resume process itself */ - if (snd_hdac_is_in_pm(&codec->core)) - return; snd_hdac_i915_set_bclk(&codec->bus->core); check_presence_and_report(codec, pin_nid, dev_id); diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 574fe798d5125383a2af8c2db23da506d5f30910..8011b451902a85628bf7d1d310865cc06b6551a7 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -6883,6 +6883,7 @@ enum { ALC256_FIXUP_MIC_NO_PRESENCE_AND_RESUME, ALC285_FIXUP_LEGION_Y9000X_SPEAKERS, ALC285_FIXUP_LEGION_Y9000X_AUTOMUTE, + ALC285_FIXUP_HP_SPEAKERS_MICMUTE_LED, }; /* A special fixup for Lenovo C940 and Yoga Duet 7; @@ -8164,11 +8165,13 @@ static const struct hda_fixup alc269_fixups[] = { [ALC285_FIXUP_ASUS_G533Z_PINS] = { .type = HDA_FIXUP_PINS, .v.pins = (const struct hda_pintbl[]) { - { 0x14, 0x90170120 }, + { 0x14, 0x90170152 }, /* Speaker Surround Playback Switch */ + { 0x19, 0x03a19020 }, /* Mic Boost Volume */ + { 0x1a, 0x03a11c30 }, /* Mic Boost Volume */ + { 0x1e, 0x90170151 }, /* Rear jack, IN OUT EAPD Detect */ + { 0x21, 0x03211420 }, { } }, - .chained = true, - .chain_id = ALC294_FIXUP_ASUS_G513_PINS, }, [ALC294_FIXUP_ASUS_COEF_1B] = { .type = HDA_FIXUP_VERBS, @@ -8691,6 +8694,16 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC269_FIXUP_HEADSET_MODE_NO_HP_MIC }, + [ALC285_FIXUP_HP_SPEAKERS_MICMUTE_LED] = { + .type = HDA_FIXUP_VERBS, + .v.verbs = (const struct hda_verb[]) { + { 0x20, AC_VERB_SET_COEF_INDEX, 0x19 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x8e11 }, + { } + }, + .chained = true, + .chain_id = ALC285_FIXUP_HP_MUTE_LED, + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -8774,7 +8787,6 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1028, 0x0871, "Dell Precision 3630", ALC255_FIXUP_DELL_HEADSET_MIC), SND_PCI_QUIRK(0x1028, 0x0872, "Dell Precision 3630", ALC255_FIXUP_DELL_HEADSET_MIC), SND_PCI_QUIRK(0x1028, 0x0873, "Dell Precision 3930", ALC255_FIXUP_DUMMY_LINEOUT_VERB), - SND_PCI_QUIRK(0x1028, 0x087d, "Dell Precision 5530", ALC289_FIXUP_DUAL_SPK), SND_PCI_QUIRK(0x1028, 0x08ad, "Dell WYSE AIO", ALC225_FIXUP_DELL_WYSE_AIO_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x08ae, "Dell WYSE NB", ALC225_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x0935, "Dell", ALC274_FIXUP_DELL_AIO_LINEOUT_VERB), @@ -8914,6 +8926,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8870, "HP ZBook Fury 15.6 Inch G8 Mobile Workstation PC", ALC285_FIXUP_HP_GPIO_AMP_INIT), SND_PCI_QUIRK(0x103c, 0x8873, "HP ZBook Studio 15.6 Inch G8 Mobile Workstation PC", ALC285_FIXUP_HP_GPIO_AMP_INIT), SND_PCI_QUIRK(0x103c, 0x888d, "HP ZBook Power 15.6 inch G8 Mobile Workstation PC", ALC236_FIXUP_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8895, "HP EliteBook 855 G8 Notebook PC", ALC285_FIXUP_HP_SPEAKERS_MICMUTE_LED), SND_PCI_QUIRK(0x103c, 0x8896, "HP EliteBook 855 G8 Notebook PC", ALC285_FIXUP_HP_MUTE_LED), SND_PCI_QUIRK(0x103c, 0x89aa, "HP EliteBook 630 G9", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x1043, 0x103e, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC), @@ -8963,6 +8976,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x1e8e, "ASUS Zephyrus G15", ALC289_FIXUP_ASUS_GA401), SND_PCI_QUIRK(0x1043, 0x1c52, "ASUS Zephyrus G15 2022", ALC289_FIXUP_ASUS_GA401), SND_PCI_QUIRK(0x1043, 0x1f11, "ASUS Zephyrus G14", ALC289_FIXUP_ASUS_GA401), + SND_PCI_QUIRK(0x1043, 0x1f92, "ASUS ROG Flow X16", ALC289_FIXUP_ASUS_GA401), SND_PCI_QUIRK(0x1043, 0x3030, "ASUS ZN270IE", ALC256_FIXUP_ASUS_AIO_GPIO2), SND_PCI_QUIRK(0x1043, 0x831a, "ASUS P901", ALC269_FIXUP_STEREO_DMIC), SND_PCI_QUIRK(0x1043, 0x834a, "ASUS S101", ALC269_FIXUP_STEREO_DMIC), @@ -8984,6 +8998,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x10ec, 0x10f2, "Intel Reference board", ALC700_FIXUP_INTEL_REFERENCE), SND_PCI_QUIRK(0x10ec, 0x118c, "Medion EE4254 MD62100", ALC256_FIXUP_MEDION_HEADSET_NO_PRESENCE), SND_PCI_QUIRK(0x10ec, 0x1230, "Intel Reference board", ALC295_FIXUP_CHROME_BOOK), + SND_PCI_QUIRK(0x10ec, 0x124c, "Intel Reference board", ALC295_FIXUP_CHROME_BOOK), SND_PCI_QUIRK(0x10ec, 0x1252, "Intel Reference board", ALC295_FIXUP_CHROME_BOOK), SND_PCI_QUIRK(0x10ec, 0x1254, "Intel Reference board", ALC295_FIXUP_CHROME_BOOK), SND_PCI_QUIRK(0x10f7, 0x8338, "Panasonic CF-SZ6", ALC269_FIXUP_HEADSET_MODE), @@ -8992,6 +9007,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x144d, 0xc176, "Samsung Notebook 9 Pro (NP930MBE-K04US)", ALC298_FIXUP_SAMSUNG_AMP), SND_PCI_QUIRK(0x144d, 0xc189, "Samsung Galaxy Flex Book (NT950QCG-X716)", ALC298_FIXUP_SAMSUNG_AMP), SND_PCI_QUIRK(0x144d, 0xc18a, "Samsung Galaxy Book Ion (NP930XCJ-K01US)", ALC298_FIXUP_SAMSUNG_AMP), + SND_PCI_QUIRK(0x144d, 0xc1a3, "Samsung Galaxy Book Pro (NP935XDB-KC1SE)", ALC298_FIXUP_SAMSUNG_AMP), + SND_PCI_QUIRK(0x144d, 0xc1a6, "Samsung Galaxy Book Pro 360 (NP930QBD)", ALC298_FIXUP_SAMSUNG_AMP), SND_PCI_QUIRK(0x144d, 0xc740, "Samsung Ativ book 8 (NP870Z5G)", ALC269_FIXUP_ATIV_BOOK_8), SND_PCI_QUIRK(0x144d, 0xc812, "Samsung Notebook Pen S (NT950SBE-X58)", ALC298_FIXUP_SAMSUNG_AMP), SND_PCI_QUIRK(0x144d, 0xc830, "Samsung Galaxy Book Ion (NT950XCJ-X716A)", ALC298_FIXUP_SAMSUNG_AMP), @@ -9158,6 +9175,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x511f, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), SND_PCI_QUIRK(0x17aa, 0x9e54, "LENOVO NB", ALC269_FIXUP_LENOVO_EAPD), SND_PCI_QUIRK(0x1849, 0x1233, "ASRock NUC Box 1100", ALC233_FIXUP_NO_AUDIO_JACK), + SND_PCI_QUIRK(0x1849, 0xa233, "Positivo Master C6300", ALC269_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x19e5, 0x3204, "Huawei MACH-WX9", ALC256_FIXUP_HUAWEI_MACH_WX9_PINS), SND_PCI_QUIRK(0x19e5, 0x320f, "Huawei WRT-WX9 ", ALC256_FIXUP_ASUS_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1b35, 0x1235, "CZC B20", ALC269_FIXUP_CZC_B20), diff --git a/sound/pci/hda/patch_sigmatel.c b/sound/pci/hda/patch_sigmatel.c index b848e435b93fd6273801ace9109a3cb2af562b14..6fc0c4e77cd1ebcc2f5e5f6b9825651af4bba353 100644 --- a/sound/pci/hda/patch_sigmatel.c +++ b/sound/pci/hda/patch_sigmatel.c @@ -4308,6 +4308,8 @@ static int stac_parse_auto_config(struct hda_codec *codec) if (codec->beep) { /* IDT/STAC codecs have linear beep tone parameter */ codec->beep->linear_tone = spec->linear_tone_beep; + /* keep power up while beep is enabled */ + codec->beep->keep_power_at_enable = 1; /* if no beep switch is available, make its own one */ caps = query_amp_caps(codec, nid, HDA_OUTPUT); if (!(caps & AC_AMPCAP_MUTE)) { @@ -4448,28 +4450,6 @@ static int stac_suspend(struct hda_codec *codec) stac_shutup(codec); return 0; } - -static int stac_check_power_status(struct hda_codec *codec, hda_nid_t nid) -{ -#ifdef CONFIG_SND_HDA_INPUT_BEEP - struct sigmatel_spec *spec = codec->spec; -#endif - int ret = snd_hda_gen_check_power_status(codec, nid); - -#ifdef CONFIG_SND_HDA_INPUT_BEEP - if (nid == spec->gen.beep_nid && codec->beep) { - if (codec->beep->enabled != spec->beep_power_on) { - spec->beep_power_on = codec->beep->enabled; - if (spec->beep_power_on) - snd_hda_power_up_pm(codec); - else - snd_hda_power_down_pm(codec); - } - ret |= spec->beep_power_on; - } -#endif - return ret; -} #else #define stac_suspend NULL #endif /* CONFIG_PM */ @@ -4482,7 +4462,6 @@ static const struct hda_codec_ops stac_patch_ops = { .unsol_event = snd_hda_jack_unsol_event, #ifdef CONFIG_PM .suspend = stac_suspend, - .check_power_status = stac_check_power_status, #endif .reboot_notify = stac_shutup, }; diff --git a/sound/pci/rme9652/hdsp.c b/sound/pci/rme9652/hdsp.c index 4aee30db034dd3e0c448b2e02da735f3eb9aa4f8..95434742450044a43a54d02fa81ab5a1fbdbfb87 100644 --- a/sound/pci/rme9652/hdsp.c +++ b/sound/pci/rme9652/hdsp.c @@ -436,7 +436,7 @@ struct hdsp_midi { struct snd_rawmidi *rmidi; struct snd_rawmidi_substream *input; struct snd_rawmidi_substream *output; - char istimer; /* timer in use */ + signed char istimer; /* timer in use */ struct timer_list timer; spinlock_t lock; int pending; @@ -479,7 +479,7 @@ struct hdsp { pid_t playback_pid; int running; int system_sample_rate; - const char *channel_map; + const signed char *channel_map; int dev; int irq; unsigned long port; @@ -501,7 +501,7 @@ struct hdsp { where the data for that channel can be read/written from/to. */ -static const char channel_map_df_ss[HDSP_MAX_CHANNELS] = { +static const signed char channel_map_df_ss[HDSP_MAX_CHANNELS] = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25 }; @@ -516,7 +516,7 @@ static const char channel_map_mf_ss[HDSP_MAX_CHANNELS] = { /* Multiface */ -1, -1, -1, -1, -1, -1, -1, -1 }; -static const char channel_map_ds[HDSP_MAX_CHANNELS] = { +static const signed char channel_map_ds[HDSP_MAX_CHANNELS] = { /* ADAT channels are remapped */ 1, 3, 5, 7, 9, 11, 13, 15, 17, 19, 21, 23, /* channels 12 and 13 are S/PDIF */ @@ -525,7 +525,7 @@ static const char channel_map_ds[HDSP_MAX_CHANNELS] = { -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1 }; -static const char channel_map_H9632_ss[HDSP_MAX_CHANNELS] = { +static const signed char channel_map_H9632_ss[HDSP_MAX_CHANNELS] = { /* ADAT channels */ 0, 1, 2, 3, 4, 5, 6, 7, /* SPDIF */ @@ -539,7 +539,7 @@ static const char channel_map_H9632_ss[HDSP_MAX_CHANNELS] = { -1, -1 }; -static const char channel_map_H9632_ds[HDSP_MAX_CHANNELS] = { +static const signed char channel_map_H9632_ds[HDSP_MAX_CHANNELS] = { /* ADAT */ 1, 3, 5, 7, /* SPDIF */ @@ -553,7 +553,7 @@ static const char channel_map_H9632_ds[HDSP_MAX_CHANNELS] = { -1, -1, -1, -1, -1, -1 }; -static const char channel_map_H9632_qs[HDSP_MAX_CHANNELS] = { +static const signed char channel_map_H9632_qs[HDSP_MAX_CHANNELS] = { /* ADAT is disabled in this mode */ /* SPDIF */ 8, 9, @@ -3869,7 +3869,7 @@ static snd_pcm_uframes_t snd_hdsp_hw_pointer(struct snd_pcm_substream *substream return hdsp_hw_pointer(hdsp); } -static char *hdsp_channel_buffer_location(struct hdsp *hdsp, +static signed char *hdsp_channel_buffer_location(struct hdsp *hdsp, int stream, int channel) @@ -3893,7 +3893,7 @@ static int snd_hdsp_playback_copy(struct snd_pcm_substream *substream, void __user *src, unsigned long count) { struct hdsp *hdsp = snd_pcm_substream_chip(substream); - char *channel_buf; + signed char *channel_buf; if (snd_BUG_ON(pos + count > HDSP_CHANNEL_BUFFER_BYTES)) return -EINVAL; @@ -3911,7 +3911,7 @@ static int snd_hdsp_playback_copy_kernel(struct snd_pcm_substream *substream, void *src, unsigned long count) { struct hdsp *hdsp = snd_pcm_substream_chip(substream); - char *channel_buf; + signed char *channel_buf; channel_buf = hdsp_channel_buffer_location(hdsp, substream->pstr->stream, channel); if (snd_BUG_ON(!channel_buf)) @@ -3925,7 +3925,7 @@ static int snd_hdsp_capture_copy(struct snd_pcm_substream *substream, void __user *dst, unsigned long count) { struct hdsp *hdsp = snd_pcm_substream_chip(substream); - char *channel_buf; + signed char *channel_buf; if (snd_BUG_ON(pos + count > HDSP_CHANNEL_BUFFER_BYTES)) return -EINVAL; @@ -3943,7 +3943,7 @@ static int snd_hdsp_capture_copy_kernel(struct snd_pcm_substream *substream, void *dst, unsigned long count) { struct hdsp *hdsp = snd_pcm_substream_chip(substream); - char *channel_buf; + signed char *channel_buf; channel_buf = hdsp_channel_buffer_location(hdsp, substream->pstr->stream, channel); if (snd_BUG_ON(!channel_buf)) @@ -3957,7 +3957,7 @@ static int snd_hdsp_hw_silence(struct snd_pcm_substream *substream, unsigned long count) { struct hdsp *hdsp = snd_pcm_substream_chip(substream); - char *channel_buf; + signed char *channel_buf; channel_buf = hdsp_channel_buffer_location (hdsp, substream->pstr->stream, channel); if (snd_BUG_ON(!channel_buf)) diff --git a/sound/pci/rme9652/rme9652.c b/sound/pci/rme9652/rme9652.c index 8def24673f35f729706536fa883a70b1e4d21e10..459696844b8cef8eaa68f2a1acb5f3c68bcd60f6 100644 --- a/sound/pci/rme9652/rme9652.c +++ b/sound/pci/rme9652/rme9652.c @@ -229,7 +229,7 @@ struct snd_rme9652 { int last_spdif_sample_rate; /* so that we can catch externally ... */ int last_adat_sample_rate; /* ... induced rate changes */ - const char *channel_map; + const signed char *channel_map; struct snd_card *card; struct snd_pcm *pcm; @@ -246,12 +246,12 @@ struct snd_rme9652 { where the data for that channel can be read/written from/to. */ -static const char channel_map_9652_ss[26] = { +static const signed char channel_map_9652_ss[26] = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25 }; -static const char channel_map_9636_ss[26] = { +static const signed char channel_map_9636_ss[26] = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, /* channels 16 and 17 are S/PDIF */ 24, 25, @@ -259,7 +259,7 @@ static const char channel_map_9636_ss[26] = { -1, -1, -1, -1, -1, -1, -1, -1 }; -static const char channel_map_9652_ds[26] = { +static const signed char channel_map_9652_ds[26] = { /* ADAT channels are remapped */ 1, 3, 5, 7, 9, 11, 13, 15, 17, 19, 21, 23, /* channels 12 and 13 are S/PDIF */ @@ -268,7 +268,7 @@ static const char channel_map_9652_ds[26] = { -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1 }; -static const char channel_map_9636_ds[26] = { +static const signed char channel_map_9636_ds[26] = { /* ADAT channels are remapped */ 1, 3, 5, 7, 9, 11, 13, 15, /* channels 8 and 9 are S/PDIF */ @@ -1841,7 +1841,7 @@ static snd_pcm_uframes_t snd_rme9652_hw_pointer(struct snd_pcm_substream *substr return rme9652_hw_pointer(rme9652); } -static char *rme9652_channel_buffer_location(struct snd_rme9652 *rme9652, +static signed char *rme9652_channel_buffer_location(struct snd_rme9652 *rme9652, int stream, int channel) @@ -1869,7 +1869,7 @@ static int snd_rme9652_playback_copy(struct snd_pcm_substream *substream, void __user *src, unsigned long count) { struct snd_rme9652 *rme9652 = snd_pcm_substream_chip(substream); - char *channel_buf; + signed char *channel_buf; if (snd_BUG_ON(pos + count > RME9652_CHANNEL_BUFFER_BYTES)) return -EINVAL; @@ -1889,7 +1889,7 @@ static int snd_rme9652_playback_copy_kernel(struct snd_pcm_substream *substream, void *src, unsigned long count) { struct snd_rme9652 *rme9652 = snd_pcm_substream_chip(substream); - char *channel_buf; + signed char *channel_buf; channel_buf = rme9652_channel_buffer_location(rme9652, substream->pstr->stream, @@ -1905,7 +1905,7 @@ static int snd_rme9652_capture_copy(struct snd_pcm_substream *substream, void __user *dst, unsigned long count) { struct snd_rme9652 *rme9652 = snd_pcm_substream_chip(substream); - char *channel_buf; + signed char *channel_buf; if (snd_BUG_ON(pos + count > RME9652_CHANNEL_BUFFER_BYTES)) return -EINVAL; @@ -1925,7 +1925,7 @@ static int snd_rme9652_capture_copy_kernel(struct snd_pcm_substream *substream, void *dst, unsigned long count) { struct snd_rme9652 *rme9652 = snd_pcm_substream_chip(substream); - char *channel_buf; + signed char *channel_buf; channel_buf = rme9652_channel_buffer_location(rme9652, substream->pstr->stream, @@ -1941,7 +1941,7 @@ static int snd_rme9652_hw_silence(struct snd_pcm_substream *substream, unsigned long count) { struct snd_rme9652 *rme9652 = snd_pcm_substream_chip(substream); - char *channel_buf; + signed char *channel_buf; channel_buf = rme9652_channel_buffer_location (rme9652, substream->pstr->stream, diff --git a/sound/soc/codecs/da7219.c b/sound/soc/codecs/da7219.c index 5f8c96dea094a81121f92a4db5a0015e473233a7..f9e58d6509a8301c3fbdee440628dd859ef9c91f 100644 --- a/sound/soc/codecs/da7219.c +++ b/sound/soc/codecs/da7219.c @@ -2194,6 +2194,7 @@ static int da7219_register_dai_clks(struct snd_soc_component *component) dai_clk_lookup = clkdev_hw_create(dai_clk_hw, init.name, "%s", dev_name(dev)); if (!dai_clk_lookup) { + clk_hw_unregister(dai_clk_hw); ret = -ENOMEM; goto err; } else { @@ -2215,12 +2216,12 @@ static int da7219_register_dai_clks(struct snd_soc_component *component) return 0; err: - do { + while (--i >= 0) { if (da7219->dai_clks_lookup[i]) clkdev_drop(da7219->dai_clks_lookup[i]); clk_hw_unregister(&da7219->dai_clks_hw[i]); - } while (i-- > 0); + } if (np) kfree(da7219->clk_hw_data); diff --git a/sound/soc/codecs/hdac_hda.h b/sound/soc/codecs/hdac_hda.h index d0efc5e254ae9db2da7887e50a3733aa3f9163df..da0ed74758b05e8d268924430b10542d581c3a80 100644 --- a/sound/soc/codecs/hdac_hda.h +++ b/sound/soc/codecs/hdac_hda.h @@ -14,7 +14,7 @@ enum { HDAC_HDMI_1_DAI_ID, HDAC_HDMI_2_DAI_ID, HDAC_HDMI_3_DAI_ID, - HDAC_LAST_DAI_ID = HDAC_HDMI_3_DAI_ID, + HDAC_DAI_ID_NUM }; struct hdac_hda_pcm { @@ -24,7 +24,7 @@ struct hdac_hda_pcm { struct hdac_hda_priv { struct hda_codec codec; - struct hdac_hda_pcm pcm[HDAC_LAST_DAI_ID]; + struct hdac_hda_pcm pcm[HDAC_DAI_ID_NUM]; bool need_display_power; }; diff --git a/sound/soc/codecs/jz4725b.c b/sound/soc/codecs/jz4725b.c index e49374c72e70a148c7e36b99fd6aad8aeab94b9f..8a830d0ad9500cd1335632527589714562a4df33 100644 --- a/sound/soc/codecs/jz4725b.c +++ b/sound/soc/codecs/jz4725b.c @@ -136,14 +136,17 @@ enum { #define REG_CGR3_GO1L_OFFSET 0 #define REG_CGR3_GO1L_MASK (0x1f << REG_CGR3_GO1L_OFFSET) +#define REG_CGR10_GIL_OFFSET 0 +#define REG_CGR10_GIR_OFFSET 4 + struct jz_icdc { struct regmap *regmap; void __iomem *base; struct clk *clk; }; -static const SNDRV_CTL_TLVD_DECLARE_DB_LINEAR(jz4725b_dac_tlv, -2250, 0); -static const SNDRV_CTL_TLVD_DECLARE_DB_LINEAR(jz4725b_line_tlv, -1500, 600); +static const SNDRV_CTL_TLVD_DECLARE_DB_SCALE(jz4725b_adc_tlv, 0, 150, 0); +static const SNDRV_CTL_TLVD_DECLARE_DB_SCALE(jz4725b_dac_tlv, -2250, 150, 0); static const struct snd_kcontrol_new jz4725b_codec_controls[] = { SOC_DOUBLE_TLV("Master Playback Volume", @@ -151,11 +154,11 @@ static const struct snd_kcontrol_new jz4725b_codec_controls[] = { REG_CGR1_GODL_OFFSET, REG_CGR1_GODR_OFFSET, 0xf, 1, jz4725b_dac_tlv), - SOC_DOUBLE_R_TLV("Master Capture Volume", - JZ4725B_CODEC_REG_CGR3, - JZ4725B_CODEC_REG_CGR2, - REG_CGR2_GO1R_OFFSET, - 0x1f, 1, jz4725b_line_tlv), + SOC_DOUBLE_TLV("Master Capture Volume", + JZ4725B_CODEC_REG_CGR10, + REG_CGR10_GIL_OFFSET, + REG_CGR10_GIR_OFFSET, + 0xf, 0, jz4725b_adc_tlv), SOC_SINGLE("Master Playback Switch", JZ4725B_CODEC_REG_CR1, REG_CR1_DAC_MUTE_OFFSET, 1, 1), @@ -180,7 +183,7 @@ static SOC_VALUE_ENUM_SINGLE_DECL(jz4725b_codec_adc_src_enum, jz4725b_codec_adc_src_texts, jz4725b_codec_adc_src_values); static const struct snd_kcontrol_new jz4725b_codec_adc_src_ctrl = - SOC_DAPM_ENUM("Route", jz4725b_codec_adc_src_enum); + SOC_DAPM_ENUM("ADC Source Capture Route", jz4725b_codec_adc_src_enum); static const struct snd_kcontrol_new jz4725b_codec_mixer_controls[] = { SOC_DAPM_SINGLE("Line In Bypass", JZ4725B_CODEC_REG_CR1, @@ -225,7 +228,7 @@ static const struct snd_soc_dapm_widget jz4725b_codec_dapm_widgets[] = { SND_SOC_DAPM_ADC("ADC", "Capture", JZ4725B_CODEC_REG_PMR1, REG_PMR1_SB_ADC_OFFSET, 1), - SND_SOC_DAPM_MUX("ADC Source", SND_SOC_NOPM, 0, 0, + SND_SOC_DAPM_MUX("ADC Source Capture Route", SND_SOC_NOPM, 0, 0, &jz4725b_codec_adc_src_ctrl), /* Mixer */ @@ -236,7 +239,8 @@ static const struct snd_soc_dapm_widget jz4725b_codec_dapm_widgets[] = { SND_SOC_DAPM_MIXER("DAC to Mixer", JZ4725B_CODEC_REG_CR1, REG_CR1_DACSEL_OFFSET, 0, NULL, 0), - SND_SOC_DAPM_MIXER("Line In", SND_SOC_NOPM, 0, 0, NULL, 0), + SND_SOC_DAPM_MIXER("Line In", JZ4725B_CODEC_REG_PMR1, + REG_PMR1_SB_LIN_OFFSET, 1, NULL, 0), SND_SOC_DAPM_MIXER("HP Out", JZ4725B_CODEC_REG_CR1, REG_CR1_HP_DIS_OFFSET, 1, NULL, 0), @@ -283,11 +287,11 @@ static const struct snd_soc_dapm_route jz4725b_codec_dapm_routes[] = { {"Mixer", NULL, "DAC to Mixer"}, {"Mixer to ADC", NULL, "Mixer"}, - {"ADC Source", "Mixer", "Mixer to ADC"}, - {"ADC Source", "Line In", "Line In"}, - {"ADC Source", "Mic 1", "Mic 1"}, - {"ADC Source", "Mic 2", "Mic 2"}, - {"ADC", NULL, "ADC Source"}, + {"ADC Source Capture Route", "Mixer", "Mixer to ADC"}, + {"ADC Source Capture Route", "Line In", "Line In"}, + {"ADC Source Capture Route", "Mic 1", "Mic 1"}, + {"ADC Source Capture Route", "Mic 2", "Mic 2"}, + {"ADC", NULL, "ADC Source Capture Route"}, {"Out Stage", NULL, "Mixer"}, {"HP Out", NULL, "Out Stage"}, diff --git a/sound/soc/codecs/mt6660.c b/sound/soc/codecs/mt6660.c index d1797003c83dda96c60342da78473984816b8954..3cee2ea4b85de55a76e51c57acddfdea5214a84f 100644 --- a/sound/soc/codecs/mt6660.c +++ b/sound/soc/codecs/mt6660.c @@ -510,7 +510,11 @@ static int mt6660_i2c_probe(struct i2c_client *client, ret = devm_snd_soc_register_component(chip->dev, &mt6660_component_driver, &mt6660_codec_dai, 1); + if (ret) + pm_runtime_disable(chip->dev); + return ret; + probe_fail: _mt6660_chip_power_on(chip, 0); mutex_destroy(&chip->io_lock); diff --git a/sound/soc/codecs/rt1308-sdw.h b/sound/soc/codecs/rt1308-sdw.h index c5ce75666dcc869162943a409b05554f747ec6ec..98293d73ebabcd7d5a4e9004d628b5df28a4cd72 100644 --- a/sound/soc/codecs/rt1308-sdw.h +++ b/sound/soc/codecs/rt1308-sdw.h @@ -139,9 +139,11 @@ static const struct reg_default rt1308_reg_defaults[] = { { 0x3005, 0x23 }, { 0x3008, 0x02 }, { 0x300a, 0x00 }, + { 0xc000 | (RT1308_DATA_PATH << 4), 0x00 }, { 0xc003 | (RT1308_DAC_SET << 4), 0x00 }, { 0xc001 | (RT1308_POWER << 4), 0x00 }, { 0xc002 | (RT1308_POWER << 4), 0x00 }, + { 0xc000 | (RT1308_POWER_STATUS << 4), 0x00 }, }; #define RT1308_SDW_OFFSET 0xc000 diff --git a/sound/soc/codecs/sgtl5000.c b/sound/soc/codecs/sgtl5000.c index f066e016a874a30fb3846ef87aeae267bed0b643..edde0323799aaabccc8bb647a0188bd939a08217 100644 --- a/sound/soc/codecs/sgtl5000.c +++ b/sound/soc/codecs/sgtl5000.c @@ -1797,6 +1797,7 @@ static int sgtl5000_i2c_remove(struct i2c_client *client) { struct sgtl5000_priv *sgtl5000 = i2c_get_clientdata(client); + regmap_write(sgtl5000->regmap, SGTL5000_CHIP_CLK_CTRL, SGTL5000_CHIP_CLK_CTRL_DEFAULT); regmap_write(sgtl5000->regmap, SGTL5000_CHIP_DIG_POWER, SGTL5000_DIG_POWER_DEFAULT); regmap_write(sgtl5000->regmap, SGTL5000_CHIP_ANA_POWER, SGTL5000_ANA_POWER_DEFAULT); diff --git a/sound/soc/codecs/tas2764.c b/sound/soc/codecs/tas2764.c index 37588804a6b5f37e077c0ec4ad809358385dda3a..c8f6f5122cacb77e6ca6aa1baef21ef9027f2bb5 100644 --- a/sound/soc/codecs/tas2764.c +++ b/sound/soc/codecs/tas2764.c @@ -34,6 +34,9 @@ struct tas2764_priv { int v_sense_slot; int i_sense_slot; + + bool dac_powered; + bool unmuted; }; static void tas2764_reset(struct tas2764_priv *tas2764) @@ -50,34 +53,22 @@ static void tas2764_reset(struct tas2764_priv *tas2764) usleep_range(1000, 2000); } -static int tas2764_set_bias_level(struct snd_soc_component *component, - enum snd_soc_bias_level level) +static int tas2764_update_pwr_ctrl(struct tas2764_priv *tas2764) { - struct tas2764_priv *tas2764 = snd_soc_component_get_drvdata(component); + struct snd_soc_component *component = tas2764->component; + unsigned int val; + int ret; - switch (level) { - case SND_SOC_BIAS_ON: - snd_soc_component_update_bits(component, TAS2764_PWR_CTRL, - TAS2764_PWR_CTRL_MASK, - TAS2764_PWR_CTRL_ACTIVE); - break; - case SND_SOC_BIAS_STANDBY: - case SND_SOC_BIAS_PREPARE: - snd_soc_component_update_bits(component, TAS2764_PWR_CTRL, - TAS2764_PWR_CTRL_MASK, - TAS2764_PWR_CTRL_MUTE); - break; - case SND_SOC_BIAS_OFF: - snd_soc_component_update_bits(component, TAS2764_PWR_CTRL, - TAS2764_PWR_CTRL_MASK, - TAS2764_PWR_CTRL_SHUTDOWN); - break; + if (tas2764->dac_powered) + val = tas2764->unmuted ? + TAS2764_PWR_CTRL_ACTIVE : TAS2764_PWR_CTRL_MUTE; + else + val = TAS2764_PWR_CTRL_SHUTDOWN; - default: - dev_err(tas2764->dev, - "wrong power level setting %d\n", level); - return -EINVAL; - } + ret = snd_soc_component_update_bits(component, TAS2764_PWR_CTRL, + TAS2764_PWR_CTRL_MASK, val); + if (ret < 0) + return ret; return 0; } @@ -114,9 +105,7 @@ static int tas2764_codec_resume(struct snd_soc_component *component) usleep_range(1000, 2000); } - ret = snd_soc_component_update_bits(component, TAS2764_PWR_CTRL, - TAS2764_PWR_CTRL_MASK, - TAS2764_PWR_CTRL_ACTIVE); + ret = tas2764_update_pwr_ctrl(tas2764); if (ret < 0) return ret; @@ -150,14 +139,12 @@ static int tas2764_dac_event(struct snd_soc_dapm_widget *w, switch (event) { case SND_SOC_DAPM_POST_PMU: - ret = snd_soc_component_update_bits(component, TAS2764_PWR_CTRL, - TAS2764_PWR_CTRL_MASK, - TAS2764_PWR_CTRL_MUTE); + tas2764->dac_powered = true; + ret = tas2764_update_pwr_ctrl(tas2764); break; case SND_SOC_DAPM_PRE_PMD: - ret = snd_soc_component_update_bits(component, TAS2764_PWR_CTRL, - TAS2764_PWR_CTRL_MASK, - TAS2764_PWR_CTRL_SHUTDOWN); + tas2764->dac_powered = false; + ret = tas2764_update_pwr_ctrl(tas2764); break; default: dev_err(tas2764->dev, "Unsupported event\n"); @@ -202,17 +189,11 @@ static const struct snd_soc_dapm_route tas2764_audio_map[] = { static int tas2764_mute(struct snd_soc_dai *dai, int mute, int direction) { - struct snd_soc_component *component = dai->component; - int ret; - - ret = snd_soc_component_update_bits(component, TAS2764_PWR_CTRL, - TAS2764_PWR_CTRL_MASK, - mute ? TAS2764_PWR_CTRL_MUTE : 0); - - if (ret < 0) - return ret; + struct tas2764_priv *tas2764 = + snd_soc_component_get_drvdata(dai->component); - return 0; + tas2764->unmuted = !mute; + return tas2764_update_pwr_ctrl(tas2764); } static int tas2764_set_bitwidth(struct tas2764_priv *tas2764, int bitwidth) @@ -405,20 +386,13 @@ static int tas2764_set_dai_tdm_slot(struct snd_soc_dai *dai, if (tx_mask == 0 || rx_mask != 0) return -EINVAL; - if (slots == 1) { - if (tx_mask != 1) - return -EINVAL; - left_slot = 0; - right_slot = 0; + left_slot = __ffs(tx_mask); + tx_mask &= ~(1 << left_slot); + if (tx_mask == 0) { + right_slot = left_slot; } else { - left_slot = __ffs(tx_mask); - tx_mask &= ~(1 << left_slot); - if (tx_mask == 0) { - right_slot = left_slot; - } else { - right_slot = __ffs(tx_mask); - tx_mask &= ~(1 << right_slot); - } + right_slot = __ffs(tx_mask); + tx_mask &= ~(1 << right_slot); } if (tx_mask != 0 || left_slot >= slots || right_slot >= slots) @@ -485,7 +459,7 @@ static struct snd_soc_dai_driver tas2764_dai_driver[] = { .id = 0, .playback = { .stream_name = "ASI1 Playback", - .channels_min = 2, + .channels_min = 1, .channels_max = 2, .rates = TAS2764_RATES, .formats = TAS2764_FORMATS, @@ -526,12 +500,6 @@ static int tas2764_codec_probe(struct snd_soc_component *component) if (ret < 0) return ret; - ret = snd_soc_component_update_bits(component, TAS2764_PWR_CTRL, - TAS2764_PWR_CTRL_MASK, - TAS2764_PWR_CTRL_MUTE); - if (ret < 0) - return ret; - return 0; } @@ -549,7 +517,6 @@ static const struct snd_soc_component_driver soc_component_driver_tas2764 = { .probe = tas2764_codec_probe, .suspend = tas2764_codec_suspend, .resume = tas2764_codec_resume, - .set_bias_level = tas2764_set_bias_level, .controls = tas2764_snd_controls, .num_controls = ARRAY_SIZE(tas2764_snd_controls), .dapm_widgets = tas2764_dapm_widgets, diff --git a/sound/soc/codecs/tas2770.c b/sound/soc/codecs/tas2770.c index 171bbcc919d5580e587c8408a196ae5ce07fd741..c213c8096142b3fde31163de822d4125c3b5c560 100644 --- a/sound/soc/codecs/tas2770.c +++ b/sound/soc/codecs/tas2770.c @@ -395,21 +395,13 @@ static int tas2770_set_dai_tdm_slot(struct snd_soc_dai *dai, if (tx_mask == 0 || rx_mask != 0) return -EINVAL; - if (slots == 1) { - if (tx_mask != 1) - return -EINVAL; - - left_slot = 0; - right_slot = 0; + left_slot = __ffs(tx_mask); + tx_mask &= ~(1 << left_slot); + if (tx_mask == 0) { + right_slot = left_slot; } else { - left_slot = __ffs(tx_mask); - tx_mask &= ~(1 << left_slot); - if (tx_mask == 0) { - right_slot = left_slot; - } else { - right_slot = __ffs(tx_mask); - tx_mask &= ~(1 << right_slot); - } + right_slot = __ffs(tx_mask); + tx_mask &= ~(1 << right_slot); } if (tx_mask != 0 || left_slot >= slots || right_slot >= slots) diff --git a/sound/soc/codecs/wcd9335.c b/sound/soc/codecs/wcd9335.c index 8f4ed39c49de2f12a64526b7107b2021550c84c5..33c29a1f52d0085f4aa7d7a8b60d3562e1aa42e5 100644 --- a/sound/soc/codecs/wcd9335.c +++ b/sound/soc/codecs/wcd9335.c @@ -1971,8 +1971,8 @@ static int wcd9335_trigger(struct snd_pcm_substream *substream, int cmd, case SNDRV_PCM_TRIGGER_STOP: case SNDRV_PCM_TRIGGER_SUSPEND: case SNDRV_PCM_TRIGGER_PAUSE_PUSH: - slim_stream_unprepare(dai_data->sruntime); slim_stream_disable(dai_data->sruntime); + slim_stream_unprepare(dai_data->sruntime); break; default: break; diff --git a/sound/soc/codecs/wcd934x.c b/sound/soc/codecs/wcd934x.c index fd704df9b1758395afd5833ccff7abdf3adaedc1..104751ac6cd14a405352ec6e1a34417fc046b1ef 100644 --- a/sound/soc/codecs/wcd934x.c +++ b/sound/soc/codecs/wcd934x.c @@ -1829,8 +1829,8 @@ static int wcd934x_trigger(struct snd_pcm_substream *substream, int cmd, case SNDRV_PCM_TRIGGER_STOP: case SNDRV_PCM_TRIGGER_SUSPEND: case SNDRV_PCM_TRIGGER_PAUSE_PUSH: - slim_stream_unprepare(dai_data->sruntime); slim_stream_disable(dai_data->sruntime); + slim_stream_unprepare(dai_data->sruntime); break; default: break; diff --git a/sound/soc/codecs/wm8962.c b/sound/soc/codecs/wm8962.c index 38651022e3d5fffeb665d5e792612741d5328e51..21574447650cd0174dcdf6b87721c83704f3777c 100644 --- a/sound/soc/codecs/wm8962.c +++ b/sound/soc/codecs/wm8962.c @@ -1840,6 +1840,49 @@ SOC_SINGLE_TLV("SPKOUTR Mixer DACR Volume", WM8962_SPEAKER_MIXER_5, 4, 1, 0, inmix_tlv), }; +static int tp_event(struct snd_soc_dapm_widget *w, + struct snd_kcontrol *kcontrol, int event) +{ + int ret, reg, val, mask; + struct snd_soc_component *component = snd_soc_dapm_to_component(w->dapm); + + ret = pm_runtime_resume_and_get(component->dev); + if (ret < 0) { + dev_err(component->dev, "Failed to resume device: %d\n", ret); + return ret; + } + + reg = WM8962_ADDITIONAL_CONTROL_4; + + if (!strcmp(w->name, "TEMP_HP")) { + mask = WM8962_TEMP_ENA_HP_MASK; + val = WM8962_TEMP_ENA_HP; + } else if (!strcmp(w->name, "TEMP_SPK")) { + mask = WM8962_TEMP_ENA_SPK_MASK; + val = WM8962_TEMP_ENA_SPK; + } else { + pm_runtime_put(component->dev); + return -EINVAL; + } + + switch (event) { + case SND_SOC_DAPM_POST_PMD: + val = 0; + fallthrough; + case SND_SOC_DAPM_POST_PMU: + ret = snd_soc_component_update_bits(component, reg, mask, val); + break; + default: + WARN(1, "Invalid event %d\n", event); + pm_runtime_put(component->dev); + return -EINVAL; + } + + pm_runtime_put(component->dev); + + return 0; +} + static int cp_event(struct snd_soc_dapm_widget *w, struct snd_kcontrol *kcontrol, int event) { @@ -2133,8 +2176,10 @@ SND_SOC_DAPM_SUPPLY("TOCLK", WM8962_ADDITIONAL_CONTROL_1, 0, 0, NULL, 0), SND_SOC_DAPM_SUPPLY_S("DSP2", 1, WM8962_DSP2_POWER_MANAGEMENT, WM8962_DSP2_ENA_SHIFT, 0, dsp2_event, SND_SOC_DAPM_POST_PMU | SND_SOC_DAPM_PRE_PMD), -SND_SOC_DAPM_SUPPLY("TEMP_HP", WM8962_ADDITIONAL_CONTROL_4, 2, 0, NULL, 0), -SND_SOC_DAPM_SUPPLY("TEMP_SPK", WM8962_ADDITIONAL_CONTROL_4, 1, 0, NULL, 0), +SND_SOC_DAPM_SUPPLY("TEMP_HP", SND_SOC_NOPM, 0, 0, tp_event, + SND_SOC_DAPM_POST_PMU|SND_SOC_DAPM_POST_PMD), +SND_SOC_DAPM_SUPPLY("TEMP_SPK", SND_SOC_NOPM, 0, 0, tp_event, + SND_SOC_DAPM_POST_PMU|SND_SOC_DAPM_POST_PMD), SND_SOC_DAPM_MIXER("INPGAL", WM8962_LEFT_INPUT_PGA_CONTROL, 4, 0, inpgal, ARRAY_SIZE(inpgal)), @@ -3760,6 +3805,11 @@ static int wm8962_i2c_probe(struct i2c_client *i2c, if (ret < 0) goto err_pm_runtime; + regmap_update_bits(wm8962->regmap, WM8962_ADDITIONAL_CONTROL_4, + WM8962_TEMP_ENA_HP_MASK, 0); + regmap_update_bits(wm8962->regmap, WM8962_ADDITIONAL_CONTROL_4, + WM8962_TEMP_ENA_SPK_MASK, 0); + regcache_cache_only(wm8962->regmap, true); /* The drivers should power up as needed */ diff --git a/sound/soc/fsl/eukrea-tlv320.c b/sound/soc/fsl/eukrea-tlv320.c index e13271ea84ded1cf0706eda953b73c00dc111365..29cf9234984d9317650924a57801aece74e5cf15 100644 --- a/sound/soc/fsl/eukrea-tlv320.c +++ b/sound/soc/fsl/eukrea-tlv320.c @@ -86,7 +86,7 @@ static int eukrea_tlv320_probe(struct platform_device *pdev) int ret; int int_port = 0, ext_port; struct device_node *np = pdev->dev.of_node; - struct device_node *ssi_np = NULL, *codec_np = NULL; + struct device_node *ssi_np = NULL, *codec_np = NULL, *tmp_np = NULL; eukrea_tlv320.dev = &pdev->dev; if (np) { @@ -143,7 +143,7 @@ static int eukrea_tlv320_probe(struct platform_device *pdev) } if (machine_is_eukrea_cpuimx27() || - of_find_compatible_node(NULL, NULL, "fsl,imx21-audmux")) { + (tmp_np = of_find_compatible_node(NULL, NULL, "fsl,imx21-audmux"))) { imx_audmux_v1_configure_port(MX27_AUDMUX_HPCR1_SSI0, IMX_AUDMUX_V1_PCR_SYN | IMX_AUDMUX_V1_PCR_TFSDIR | @@ -158,10 +158,11 @@ static int eukrea_tlv320_probe(struct platform_device *pdev) IMX_AUDMUX_V1_PCR_SYN | IMX_AUDMUX_V1_PCR_RXDSEL(MX27_AUDMUX_HPCR1_SSI0) ); + of_node_put(tmp_np); } else if (machine_is_eukrea_cpuimx25sd() || machine_is_eukrea_cpuimx35sd() || machine_is_eukrea_cpuimx51sd() || - of_find_compatible_node(NULL, NULL, "fsl,imx31-audmux")) { + (tmp_np = of_find_compatible_node(NULL, NULL, "fsl,imx31-audmux"))) { if (!np) ext_port = machine_is_eukrea_cpuimx25sd() ? 4 : 3; @@ -178,6 +179,7 @@ static int eukrea_tlv320_probe(struct platform_device *pdev) IMX_AUDMUX_V2_PTCR_SYN, IMX_AUDMUX_V2_PDCR_RXDSEL(int_port) ); + of_node_put(tmp_np); } else { if (np) { /* The eukrea,asoc-tlv320 driver was explicitly diff --git a/sound/soc/intel/boards/bytcht_es8316.c b/sound/soc/intel/boards/bytcht_es8316.c index 7ed869bf1a926db4d9ec3398d27454174598d4a6..81269ed5a2aaa2abaf8d7035bfa0f19aa9d658a4 100644 --- a/sound/soc/intel/boards/bytcht_es8316.c +++ b/sound/soc/intel/boards/bytcht_es8316.c @@ -450,6 +450,13 @@ static const struct dmi_system_id byt_cht_es8316_quirk_table[] = { | BYT_CHT_ES8316_INTMIC_IN2_MAP | BYT_CHT_ES8316_JD_INVERTED), }, + { /* Nanote UMPC-01 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "RWC CO.,LTD"), + DMI_MATCH(DMI_PRODUCT_NAME, "UMPC-01"), + }, + .driver_data = (void *)BYT_CHT_ES8316_INTMIC_IN1_MAP, + }, { /* Teclast X98 Plus II */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "TECLAST"), diff --git a/sound/soc/qcom/lpass-cpu.c b/sound/soc/qcom/lpass-cpu.c index 03abb3d719d08366bf889ac03ea6cec47a16ac4a..ecd6c049ace24f09a3a47512e7925e35cc4c2881 100644 --- a/sound/soc/qcom/lpass-cpu.c +++ b/sound/soc/qcom/lpass-cpu.c @@ -745,10 +745,20 @@ static bool lpass_hdmi_regmap_volatile(struct device *dev, unsigned int reg) return true; if (reg == LPASS_HDMI_TX_LEGACY_ADDR(v)) return true; + if (reg == LPASS_HDMI_TX_VBIT_CTL_ADDR(v)) + return true; + if (reg == LPASS_HDMI_TX_PARITY_ADDR(v)) + return true; for (i = 0; i < v->hdmi_rdma_channels; ++i) { if (reg == LPAIF_HDMI_RDMACURR_REG(v, i)) return true; + if (reg == LPASS_HDMI_TX_DMA_ADDR(v, i)) + return true; + if (reg == LPASS_HDMI_TX_CH_LSB_ADDR(v, i)) + return true; + if (reg == LPASS_HDMI_TX_CH_MSB_ADDR(v, i)) + return true; } return false; } diff --git a/sound/soc/sh/rcar/ctu.c b/sound/soc/sh/rcar/ctu.c index 7647b3d4c0baa13d3108d05e88c643029e81297f..25a8cfc274335947190f4cb3f76cc10a49cd41b8 100644 --- a/sound/soc/sh/rcar/ctu.c +++ b/sound/soc/sh/rcar/ctu.c @@ -171,7 +171,11 @@ static int rsnd_ctu_init(struct rsnd_mod *mod, struct rsnd_dai_stream *io, struct rsnd_priv *priv) { - rsnd_mod_power_on(mod); + int ret; + + ret = rsnd_mod_power_on(mod); + if (ret < 0) + return ret; rsnd_ctu_activation(mod); diff --git a/sound/soc/sh/rcar/dvc.c b/sound/soc/sh/rcar/dvc.c index 8d91c0eb0880f17eb627bb946934b158fa3fd033..53b2ad01222b5605da0b144eb95c8a9a1209124c 100644 --- a/sound/soc/sh/rcar/dvc.c +++ b/sound/soc/sh/rcar/dvc.c @@ -186,7 +186,11 @@ static int rsnd_dvc_init(struct rsnd_mod *mod, struct rsnd_dai_stream *io, struct rsnd_priv *priv) { - rsnd_mod_power_on(mod); + int ret; + + ret = rsnd_mod_power_on(mod); + if (ret < 0) + return ret; rsnd_dvc_activation(mod); diff --git a/sound/soc/sh/rcar/mix.c b/sound/soc/sh/rcar/mix.c index a3e0370f5704a7a3318da26061eb24307e45612e..c6fe2595c373a214a3336ee044a88af78262c99c 100644 --- a/sound/soc/sh/rcar/mix.c +++ b/sound/soc/sh/rcar/mix.c @@ -146,7 +146,11 @@ static int rsnd_mix_init(struct rsnd_mod *mod, struct rsnd_dai_stream *io, struct rsnd_priv *priv) { - rsnd_mod_power_on(mod); + int ret; + + ret = rsnd_mod_power_on(mod); + if (ret < 0) + return ret; rsnd_mix_activation(mod); diff --git a/sound/soc/sh/rcar/src.c b/sound/soc/sh/rcar/src.c index 585ffba0244b9f568685ed52323d31f7f9fcb3b4..fd52e26a3808bfbef45c9199bc5bee4cd0522947 100644 --- a/sound/soc/sh/rcar/src.c +++ b/sound/soc/sh/rcar/src.c @@ -454,11 +454,14 @@ static int rsnd_src_init(struct rsnd_mod *mod, struct rsnd_priv *priv) { struct rsnd_src *src = rsnd_mod_to_src(mod); + int ret; /* reset sync convert_rate */ src->sync.val = 0; - rsnd_mod_power_on(mod); + ret = rsnd_mod_power_on(mod); + if (ret < 0) + return ret; rsnd_src_activation(mod); diff --git a/sound/soc/sh/rcar/ssi.c b/sound/soc/sh/rcar/ssi.c index 042207c116514de41de6a5a21cadaab2c9be9605..2ead44779d46d164e1ba95f072f40fcc6914f36b 100644 --- a/sound/soc/sh/rcar/ssi.c +++ b/sound/soc/sh/rcar/ssi.c @@ -518,7 +518,9 @@ static int rsnd_ssi_init(struct rsnd_mod *mod, ssi->usrcnt++; - rsnd_mod_power_on(mod); + ret = rsnd_mod_power_on(mod); + if (ret < 0) + return ret; rsnd_ssi_config_init(mod, io); diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c index ea145eedcb68d93b7d2e82fd83823b6fcaeeecca..88bbd96ed8a2de0647c3ac6b59083626136b97b5 100644 --- a/sound/soc/soc-core.c +++ b/sound/soc/soc-core.c @@ -3211,10 +3211,23 @@ EXPORT_SYMBOL_GPL(snd_soc_of_get_dai_link_codecs); static int __init snd_soc_init(void) { + int ret; + snd_soc_debugfs_init(); - snd_soc_util_init(); + ret = snd_soc_util_init(); + if (ret) + goto err_util_init; - return platform_driver_register(&soc_driver); + ret = platform_driver_register(&soc_driver); + if (ret) + goto err_register; + return 0; + +err_register: + snd_soc_util_exit(); +err_util_init: + snd_soc_debugfs_exit(); + return ret; } module_init(snd_soc_init); diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c index e81e927459b71869917d265ec64f5b390288d132..39b95ebd4215682d542831184da08a1b94a7aa19 100644 --- a/sound/soc/soc-pcm.c +++ b/sound/soc/soc-pcm.c @@ -723,11 +723,6 @@ static int soc_pcm_open(struct snd_pcm_substream *substream) ret = snd_soc_dai_startup(dai, substream); if (ret < 0) goto err; - - if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) - dai->tx_mask = 0; - else - dai->rx_mask = 0; } /* Dynamic PCM DAI links compat checks use dynamic capabilities */ diff --git a/sound/soc/soc-utils.c b/sound/soc/soc-utils.c index f27f94ca064bca45c28e3077d630e3e9f6558d63..6b398ffabb02e8a192a17b873bea77572daf5ef3 100644 --- a/sound/soc/soc-utils.c +++ b/sound/soc/soc-utils.c @@ -171,7 +171,7 @@ int __init snd_soc_util_init(void) return ret; } -void __exit snd_soc_util_exit(void) +void snd_soc_util_exit(void) { platform_driver_unregister(&soc_dummy_driver); platform_device_unregister(soc_dummy_dev); diff --git a/sound/soc/sof/sof-pci-dev.c b/sound/soc/sof/sof-pci-dev.c index 75657a25dbc059dbabc6b23598d9c3127c09ac63..fe9feaab6a0ac63edb82f5a7fe518ca5122f7017 100644 --- a/sound/soc/sof/sof-pci-dev.c +++ b/sound/soc/sof/sof-pci-dev.c @@ -75,7 +75,7 @@ static const struct dmi_system_id community_key_platforms[] = { { .ident = "Google Chromebooks", .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Google"), + DMI_MATCH(DMI_PRODUCT_FAMILY, "Google"), } }, {}, diff --git a/sound/synth/emux/emux.c b/sound/synth/emux/emux.c index 6695530bba9b38c7ceda4fe40688fefdb55fea71..c60ff81390a4412f218c9f08d6d920e7e3baa770 100644 --- a/sound/synth/emux/emux.c +++ b/sound/synth/emux/emux.c @@ -125,15 +125,10 @@ EXPORT_SYMBOL(snd_emux_register); */ int snd_emux_free(struct snd_emux *emu) { - unsigned long flags; - if (! emu) return -EINVAL; - spin_lock_irqsave(&emu->voice_lock, flags); - if (emu->timer_active) - del_timer(&emu->tlist); - spin_unlock_irqrestore(&emu->voice_lock, flags); + del_timer_sync(&emu->tlist); snd_emux_proc_free(emu); snd_emux_delete_virmidi(emu); diff --git a/sound/usb/endpoint.c b/sound/usb/endpoint.c index 8527267725bb718280c4252a5094ed93b2716ecf..80dcac5abe0c4fdb3dd72b290b9ead678a958bde 100644 --- a/sound/usb/endpoint.c +++ b/sound/usb/endpoint.c @@ -73,12 +73,13 @@ static inline unsigned get_usb_high_speed_rate(unsigned int rate) */ static void release_urb_ctx(struct snd_urb_ctx *u) { - if (u->buffer_size) + if (u->urb && u->buffer_size) usb_free_coherent(u->ep->chip->dev, u->buffer_size, u->urb->transfer_buffer, u->urb->transfer_dma); usb_free_urb(u->urb); u->urb = NULL; + u->buffer_size = 0; } static const char *usb_error_string(int err) @@ -998,6 +999,7 @@ static int sync_ep_set_params(struct snd_usb_endpoint *ep) if (!ep->syncbuf) return -ENOMEM; + ep->nurbs = SYNC_URBS; for (i = 0; i < SYNC_URBS; i++) { struct snd_urb_ctx *u = &ep->urb[i]; u->index = i; @@ -1017,8 +1019,6 @@ static int sync_ep_set_params(struct snd_usb_endpoint *ep) u->urb->complete = snd_complete_urb; } - ep->nurbs = SYNC_URBS; - return 0; out_of_memory: diff --git a/sound/usb/midi.c b/sound/usb/midi.c index 93fee6e365a6ed8edd82180235280fb5a88c51c4..b02e1a33304f04a9e0760e2be513bb0c682aec66 100644 --- a/sound/usb/midi.c +++ b/sound/usb/midi.c @@ -1149,10 +1149,8 @@ static int snd_usbmidi_output_open(struct snd_rawmidi_substream *substream) port = &umidi->endpoints[i].out->ports[j]; break; } - if (!port) { - snd_BUG(); + if (!port) return -ENXIO; - } substream->runtime->private_data = port; port->state = STATE_UNKNOWN; diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h index 1ac91c46da3cf9f88128daa2a3e661d7bdd1f81a..6a78813b63f5392a714e804d48f751208274e258 100644 --- a/sound/usb/quirks-table.h +++ b/sound/usb/quirks-table.h @@ -2028,6 +2028,10 @@ YAMAHA_DEVICE(0x7010, "UB99"), } } }, +{ + /* M-Audio Micro */ + USB_DEVICE_VENDOR_SPEC(0x0763, 0x201a), +}, { USB_DEVICE_VENDOR_SPEC(0x0763, 0x2030), .driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) { @@ -3656,6 +3660,58 @@ AU0828_DEVICE(0x2040, 0x7270, "Hauppauge", "HVR-950Q"), } }, +/* + * MacroSilicon MS2100/MS2106 based AV capture cards + * + * These claim 96kHz 1ch in the descriptors, but are actually 48kHz 2ch. + * They also need QUIRK_AUDIO_ALIGN_TRANSFER, which makes one wonder if + * they pretend to be 96kHz mono as a workaround for stereo being broken + * by that... + * + * They also have an issue with initial stream alignment that causes the + * channels to be swapped and out of phase, which is dealt with in quirks.c. + */ +{ + USB_AUDIO_DEVICE(0x534d, 0x0021), + .driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) { + .vendor_name = "MacroSilicon", + .product_name = "MS210x", + .ifnum = QUIRK_ANY_INTERFACE, + .type = QUIRK_COMPOSITE, + .data = &(const struct snd_usb_audio_quirk[]) { + { + .ifnum = 2, + .type = QUIRK_AUDIO_ALIGN_TRANSFER, + }, + { + .ifnum = 2, + .type = QUIRK_AUDIO_STANDARD_MIXER, + }, + { + .ifnum = 3, + .type = QUIRK_AUDIO_FIXED_ENDPOINT, + .data = &(const struct audioformat) { + .formats = SNDRV_PCM_FMTBIT_S16_LE, + .channels = 2, + .iface = 3, + .altsetting = 1, + .altset_idx = 1, + .attributes = 0, + .endpoint = 0x82, + .ep_attr = USB_ENDPOINT_XFER_ISOC | + USB_ENDPOINT_SYNC_ASYNC, + .rates = SNDRV_PCM_RATE_CONTINUOUS, + .rate_min = 48000, + .rate_max = 48000, + } + }, + { + .ifnum = -1 + } + } + } +}, + /* * MacroSilicon MS2109 based HDMI capture cards * diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index 41f5d8242478fdcdf68f60f0f941264c92b2954a..752422147fb3804e94fdc692fd8f2468d34e56a5 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1508,6 +1508,7 @@ void snd_usb_set_format_quirk(struct snd_usb_substream *subs, case USB_ID(0x2b73, 0x0017): /* Pioneer DJ DJM-250MK2 */ pioneer_djm_set_format_quirk(subs); break; + case USB_ID(0x534d, 0x0021): /* MacroSilicon MS2100/MS2106 */ case USB_ID(0x534d, 0x2109): /* MacroSilicon MS2109 */ subs->stream_offset_adj = 2; break; @@ -1743,6 +1744,7 @@ u64 snd_usb_interface_dsd_format_quirks(struct snd_usb_audio *chip, /* XMOS based USB DACs */ switch (chip->usb_id) { case USB_ID(0x1511, 0x0037): /* AURALiC VEGA */ + case USB_ID(0x21ed, 0xd75a): /* Accuphase DAC-60 option card */ case USB_ID(0x2522, 0x0012): /* LH Labs VI DAC Infinity */ case USB_ID(0x2772, 0x0230): /* Pro-Ject Pre Box S2 Digital */ if (fp->altsetting == 2) diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index 144dc164b7596a5c13e22f21b58665116ceb54eb..8fb9256768134d3f4be5a0946f644c7424c9bbb3 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -489,6 +489,11 @@ #define MSR_AMD64_CPUID_FN_1 0xc0011004 #define MSR_AMD64_LS_CFG 0xc0011020 #define MSR_AMD64_DC_CFG 0xc0011022 + +#define MSR_AMD64_DE_CFG 0xc0011029 +#define MSR_AMD64_DE_CFG_LFENCE_SERIALIZE_BIT 1 +#define MSR_AMD64_DE_CFG_LFENCE_SERIALIZE BIT_ULL(MSR_AMD64_DE_CFG_LFENCE_SERIALIZE_BIT) + #define MSR_AMD64_BU_CFG2 0xc001102a #define MSR_AMD64_IBSFETCHCTL 0xc0011030 #define MSR_AMD64_IBSFETCHLINAD 0xc0011031 @@ -565,9 +570,6 @@ #define FAM10H_MMIO_CONF_BASE_MASK 0xfffffffULL #define FAM10H_MMIO_CONF_BASE_SHIFT 20 #define MSR_FAM10H_NODE_ID 0xc001100c -#define MSR_F10H_DECFG 0xc0011029 -#define MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT 1 -#define MSR_F10H_DECFG_LFENCE_SERIALIZE BIT_ULL(MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT) /* K8 MSRs */ #define MSR_K8_TOP_MEM1 0xc001001a diff --git a/tools/bpf/bpftool/btf_dumper.c b/tools/bpf/bpftool/btf_dumper.c index 0e9310727281af3f0f8b58d1f6e76f2866548047..13be487631992ddf50249b445165a877934d50ca 100644 --- a/tools/bpf/bpftool/btf_dumper.c +++ b/tools/bpf/bpftool/btf_dumper.c @@ -416,7 +416,7 @@ static int btf_dumper_int(const struct btf_type *t, __u8 bit_offset, *(char *)data); break; case BTF_INT_BOOL: - jsonw_bool(jw, *(int *)data); + jsonw_bool(jw, *(bool *)data); break; default: /* shouldn't happen */ diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c index 6ebf2b215ef49698fc4601339099260380e1b126..eefa2b34e641ab85294e8576f44f881cac8ed865 100644 --- a/tools/bpf/bpftool/common.c +++ b/tools/bpf/bpftool/common.c @@ -271,6 +271,9 @@ int do_pin_any(int argc, char **argv, int (*get_fd)(int *, char ***)) int err; int fd; + if (!REQ_ARGS(3)) + return -EINVAL; + fd = get_fd(&argc, &argv); if (fd < 0) return fd; diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c index 1854d6b978604013b2decac6b983d7468dfe345c..4fd4e3462ebce5b86e5b37eb8e824218e589c3c4 100644 --- a/tools/bpf/bpftool/main.c +++ b/tools/bpf/bpftool/main.c @@ -398,6 +398,16 @@ int main(int argc, char **argv) setlinebuf(stdout); +#ifdef USE_LIBCAP + /* Libcap < 2.63 hooks before main() to compute the number of + * capabilities of the running kernel, and doing so it calls prctl() + * which may fail and set errno to non-zero. + * Let's reset errno to make sure this does not interfere with the + * batch mode. + */ + errno = 0; +#endif + last_do_help = do_help; pretty_output = false; json_output = false; diff --git a/tools/iio/iio_utils.c b/tools/iio/iio_utils.c index 7399eb7f13786f9d2e45d4fb9eef5e6123285ca4..d66b18c54606ab005e5fb8fc3662dc484b8a6381 100644 --- a/tools/iio/iio_utils.c +++ b/tools/iio/iio_utils.c @@ -543,6 +543,10 @@ static int calc_digits(int num) { int count = 0; + /* It takes a digit to represent zero */ + if (!num) + return 1; + while (num != 0) { num /= 10; count++; diff --git a/tools/include/nolibc/nolibc.h b/tools/include/nolibc/nolibc.h index b8cecb66d28b7f236a1afc3436f8ce315c27500b..c20d2fe7cebaa5354bc35fb9e2795cc914177f53 100644 --- a/tools/include/nolibc/nolibc.h +++ b/tools/include/nolibc/nolibc.h @@ -2318,9 +2318,9 @@ static __attribute__((unused)) int memcmp(const void *s1, const void *s2, size_t n) { size_t ofs = 0; - char c1 = 0; + int c1 = 0; - while (ofs < n && !(c1 = ((char *)s1)[ofs] - ((char *)s2)[ofs])) { + while (ofs < n && !(c1 = ((unsigned char *)s1)[ofs] - ((unsigned char *)s2)[ofs])) { ofs++; } return c1; diff --git a/tools/include/uapi/linux/openat2.h b/tools/include/uapi/linux/openat2.h index 58b1eb71136007727e8535eaeb19e2ea4a00fb9a..a5feb7604948791c7a34ec0876c24a97eb5a375b 100644 --- a/tools/include/uapi/linux/openat2.h +++ b/tools/include/uapi/linux/openat2.h @@ -35,5 +35,9 @@ struct open_how { #define RESOLVE_IN_ROOT 0x10 /* Make all jumps to "/" and ".." be scoped inside the dirfd (similar to chroot(2)). */ +#define RESOLVE_CACHED 0x20 /* Only complete if resolution can be + completed through cached lookup. May + return -EAGAIN if that's not + possible. */ #endif /* _UAPI_LINUX_OPENAT2_H */ diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c index e8745f646371fe3ceae58a414c69a0e9921970b2..fa1f8faf7dfe917635fbcffbdda3ea7587860302 100644 --- a/tools/lib/bpf/xsk.c +++ b/tools/lib/bpf/xsk.c @@ -930,13 +930,13 @@ void xsk_socket__delete(struct xsk_socket *xsk) ctx = xsk->ctx; umem = ctx->umem; - xsk_put_ctx(ctx, true); - - if (!ctx->refcount) { + if (ctx->refcount == 1) { xsk_delete_bpf_maps(xsk); close(ctx->prog_fd); } + xsk_put_ctx(ctx, true); + err = xsk_get_mmap_offsets(xsk->fd, &off); if (!err) { if (xsk->rx) { diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c index 5aa3b4e76479e9082e9c5abf226a16749c86f673..a2ea3931e01d570b661a590bf0ef0f5934b9de85 100644 --- a/tools/objtool/elf.c +++ b/tools/objtool/elf.c @@ -578,6 +578,11 @@ static int elf_update_symbol(struct elf *elf, struct section *symtab, Elf64_Xword entsize = symtab->sh.sh_entsize; int max_idx, idx = sym->idx; Elf_Scn *s, *t = NULL; + bool is_special_shndx = sym->sym.st_shndx >= SHN_LORESERVE && + sym->sym.st_shndx != SHN_XINDEX; + + if (is_special_shndx) + shndx = sym->sym.st_shndx; s = elf_getscn(elf->elf, symtab->idx); if (!s) { @@ -663,7 +668,7 @@ static int elf_update_symbol(struct elf *elf, struct section *symtab, } /* setup extended section index magic and write the symbol */ - if (shndx >= SHN_UNDEF && shndx < SHN_LORESERVE) { + if ((shndx >= SHN_UNDEF && shndx < SHN_LORESERVE) || is_special_shndx) { sym->sym.st_shndx = shndx; if (!shndx_data) shndx = 0; diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c index d3c15b53495d6b71e5ddbb952afd3ca60299776e..d96e86ddd2c53f6ac934f69ad40f38f6560d8404 100644 --- a/tools/perf/util/auxtrace.c +++ b/tools/perf/util/auxtrace.c @@ -2164,11 +2164,19 @@ struct sym_args { bool near; }; +static bool kern_sym_name_match(const char *kname, const char *name) +{ + size_t n = strlen(name); + + return !strcmp(kname, name) || + (!strncmp(kname, name, n) && kname[n] == '\t'); +} + static bool kern_sym_match(struct sym_args *args, const char *name, char type) { /* A function with the same name, and global or the n'th found or any */ return kallsyms__is_function(type) && - !strcmp(name, args->name) && + kern_sym_name_match(name, args->name) && ((args->global && isupper(type)) || (args->selected && ++(args->cnt) == args->idx) || (!args->global && !args->selected)); diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index 5163d2ffea70da39bc5890a3d826a59013ffe4e0..453773ce6f4552a14ec4068f75b1361dedd9fd92 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -3279,6 +3279,7 @@ static const char * const intel_pt_info_fmts[] = { [INTEL_PT_SNAPSHOT_MODE] = " Snapshot mode %"PRId64"\n", [INTEL_PT_PER_CPU_MMAPS] = " Per-cpu maps %"PRId64"\n", [INTEL_PT_MTC_BIT] = " MTC bit %#"PRIx64"\n", + [INTEL_PT_MTC_FREQ_BITS] = " MTC freq bits %#"PRIx64"\n", [INTEL_PT_TSC_CTC_N] = " TSC:CTC numerator %"PRIu64"\n", [INTEL_PT_TSC_CTC_D] = " TSC:CTC denominator %"PRIu64"\n", [INTEL_PT_CYC_BIT] = " CYC bit %#"PRIx64"\n", @@ -3293,8 +3294,12 @@ static void intel_pt_print_info(__u64 *arr, int start, int finish) if (!dump_trace) return; - for (i = start; i <= finish; i++) - fprintf(stdout, intel_pt_info_fmts[i], arr[i]); + for (i = start; i <= finish; i++) { + const char *fmt = intel_pt_info_fmts[i]; + + if (fmt) + fprintf(stdout, fmt, arr[i]); + } } static void intel_pt_print_info_str(const char *name, const char *str) diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 3a0a7930cd10ae52558786d0aa3c03eefc00d4f6..c56a4d9c3be9420608deb7ab96fb82499a7524e1 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -356,6 +356,12 @@ __add_event(struct list_head *list, int *idx, struct perf_cpu_map *cpus = pmu ? perf_cpu_map__get(pmu->cpus) : cpu_list ? perf_cpu_map__new(cpu_list) : NULL; + if (pmu) + perf_pmu__warn_invalid_formats(pmu); + + if (pmu && attr->type == PERF_TYPE_RAW) + perf_pmu__warn_invalid_config(pmu, attr->config, name); + if (init_attr) event_attr_init(attr); diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index d41caeb35cf6cb198f7f09ab648cb2ba057a45e4..ac45da0302a73c42ce7e202bc6c03fb1946aa77c 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -862,6 +862,23 @@ static struct perf_pmu *pmu_lookup(const char *name) return pmu; } +void perf_pmu__warn_invalid_formats(struct perf_pmu *pmu) +{ + struct perf_pmu_format *format; + + /* fake pmu doesn't have format list */ + if (pmu == &perf_pmu__fake) + return; + + list_for_each_entry(format, &pmu->format, list) + if (format->value >= PERF_PMU_FORMAT_VALUE_CONFIG_END) { + pr_warning("WARNING: '%s' format '%s' requires 'perf_event_attr::config%d'" + "which is not supported by this version of perf!\n", + pmu->name, format->name, format->value); + return; + } +} + static struct perf_pmu *pmu_find(const char *name) { struct perf_pmu *pmu; @@ -1716,3 +1733,36 @@ int perf_pmu__caps_parse(struct perf_pmu *pmu) return nr_caps; } + +void perf_pmu__warn_invalid_config(struct perf_pmu *pmu, __u64 config, + char *name) +{ + struct perf_pmu_format *format; + __u64 masks = 0, bits; + char buf[100]; + unsigned int i; + + list_for_each_entry(format, &pmu->format, list) { + if (format->value != PERF_PMU_FORMAT_VALUE_CONFIG) + continue; + + for_each_set_bit(i, format->bits, PERF_PMU_FORMAT_BITS) + masks |= 1ULL << i; + } + + /* + * Kernel doesn't export any valid format bits. + */ + if (masks == 0) + return; + + bits = config & ~masks; + if (bits == 0) + return; + + bitmap_scnprintf((unsigned long *)&bits, sizeof(bits) * 8, buf, sizeof(buf)); + + pr_warning("WARNING: event '%s' not valid (bits %s of config " + "'%llx' not supported by kernel)!\n", + name ?: "N/A", buf, config); +} diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h index a64e9c9ce731a1fb9a88392dcd750ffcff1dccd3..7d208b850769527723e760ff73ddf71a74fae7d1 100644 --- a/tools/perf/util/pmu.h +++ b/tools/perf/util/pmu.h @@ -15,6 +15,7 @@ enum { PERF_PMU_FORMAT_VALUE_CONFIG, PERF_PMU_FORMAT_VALUE_CONFIG1, PERF_PMU_FORMAT_VALUE_CONFIG2, + PERF_PMU_FORMAT_VALUE_CONFIG_END, }; #define PERF_PMU_FORMAT_BITS 64 @@ -120,4 +121,8 @@ int perf_pmu__convert_scale(const char *scale, char **end, double *sval); int perf_pmu__caps_parse(struct perf_pmu *pmu); +void perf_pmu__warn_invalid_config(struct perf_pmu *pmu, __u64 config, + char *name); +void perf_pmu__warn_invalid_formats(struct perf_pmu *pmu); + #endif /* __PMU_H */ diff --git a/tools/perf/util/pmu.l b/tools/perf/util/pmu.l index a15d9fbd7c0ed99512b0163ffe26bdb8eaf313bf..58b4926cfaca906dab6f6f85bd7f359c943f166d 100644 --- a/tools/perf/util/pmu.l +++ b/tools/perf/util/pmu.l @@ -27,8 +27,6 @@ num_dec [0-9]+ {num_dec} { return value(10); } config { return PP_CONFIG; } -config1 { return PP_CONFIG1; } -config2 { return PP_CONFIG2; } - { return '-'; } : { return ':'; } , { return ','; } diff --git a/tools/perf/util/pmu.y b/tools/perf/util/pmu.y index bfd7e8509869b64b53fbcbcddafe89a4a73b93b3..283efe059819d81ddb12c35c7147a20d8300ff0b 100644 --- a/tools/perf/util/pmu.y +++ b/tools/perf/util/pmu.y @@ -20,7 +20,7 @@ do { \ %} -%token PP_CONFIG PP_CONFIG1 PP_CONFIG2 +%token PP_CONFIG %token PP_VALUE PP_ERROR %type PP_VALUE %type bit_term @@ -47,18 +47,11 @@ PP_CONFIG ':' bits $3)); } | -PP_CONFIG1 ':' bits +PP_CONFIG PP_VALUE ':' bits { ABORT_ON(perf_pmu__new_format(format, name, - PERF_PMU_FORMAT_VALUE_CONFIG1, - $3)); -} -| -PP_CONFIG2 ':' bits -{ - ABORT_ON(perf_pmu__new_format(format, name, - PERF_PMU_FORMAT_VALUE_CONFIG2, - $3)); + $2, + $4)); } bits: diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index 96fe9c1af33644b71393dffb16d1c5c86a0a5342..4688e39de52afd4efdeb5a2782e52e0be300431b 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -203,7 +203,7 @@ static void new_line_csv(struct perf_stat_config *config, void *ctx) fputc('\n', os->fh); if (os->prefix) - fprintf(os->fh, "%s%s", os->prefix, config->csv_sep); + fprintf(os->fh, "%s", os->prefix); aggr_printout(config, os->evsel, os->id, os->nr); for (i = 0; i < os->nfields; i++) fputs(config->csv_sep, os->fh); diff --git a/tools/testing/selftests/arm64/signal/testcases/testcases.c b/tools/testing/selftests/arm64/signal/testcases/testcases.c index 61ebcdf638311e18858c0edfe106f32b963051f0..a3ac5c2d8aac73eaf8f7e6dcd0ce36feaf463708 100644 --- a/tools/testing/selftests/arm64/signal/testcases/testcases.c +++ b/tools/testing/selftests/arm64/signal/testcases/testcases.c @@ -33,7 +33,7 @@ bool validate_extra_context(struct extra_context *extra, char **err) return false; fprintf(stderr, "Validating EXTRA...\n"); - term = GET_RESV_NEXT_HEAD(extra); + term = GET_RESV_NEXT_HEAD(&extra->head); if (!term || term->magic || term->size) { *err = "Missing terminator after EXTRA context"; return false; diff --git a/tools/testing/selftests/bpf/verifier/ref_tracking.c b/tools/testing/selftests/bpf/verifier/ref_tracking.c index 006b5bd99c089321658d6039acec2dbe24069787..525d810b10b8161e896ebad00e4479eacbebcd82 100644 --- a/tools/testing/selftests/bpf/verifier/ref_tracking.c +++ b/tools/testing/selftests/bpf/verifier/ref_tracking.c @@ -901,3 +901,39 @@ .result_unpriv = REJECT, .errstr_unpriv = "unknown func", }, +{ + "reference tracking: try to leak released ptr reg", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -4), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_9, BPF_REG_0), + + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_MOV64_IMM(BPF_REG_2, 8), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_EMIT_CALL(BPF_FUNC_ringbuf_reserve), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_8, BPF_REG_0), + + BPF_MOV64_REG(BPF_REG_1, BPF_REG_8), + BPF_MOV64_IMM(BPF_REG_2, 0), + BPF_EMIT_CALL(BPF_FUNC_ringbuf_discard), + BPF_MOV64_IMM(BPF_REG_0, 0), + + BPF_STX_MEM(BPF_DW, BPF_REG_9, BPF_REG_8, 0), + BPF_EXIT_INSN() + }, + .fixup_map_array_48b = { 4 }, + .fixup_map_ringbuf = { 11 }, + .result = ACCEPT, + .result_unpriv = REJECT, + .errstr_unpriv = "R8 !read_ok" +}, diff --git a/tools/testing/selftests/futex/functional/Makefile b/tools/testing/selftests/futex/functional/Makefile index 23207829ec752b52a56577a679f5baf3f3f51a46..6a0ed2e7881eb31703c672a3fea26260192a97b9 100644 --- a/tools/testing/selftests/futex/functional/Makefile +++ b/tools/testing/selftests/futex/functional/Makefile @@ -3,11 +3,11 @@ INCLUDES := -I../include -I../../ CFLAGS := $(CFLAGS) -g -O2 -Wall -D_GNU_SOURCE -pthread $(INCLUDES) LDLIBS := -lpthread -lrt -HEADERS := \ +LOCAL_HDRS := \ ../include/futextest.h \ ../include/atomic.h \ ../include/logging.h -TEST_GEN_FILES := \ +TEST_GEN_PROGS := \ futex_wait_timeout \ futex_wait_wouldblock \ futex_requeue_pi \ @@ -21,5 +21,3 @@ TEST_PROGS := run.sh top_srcdir = ../../../../.. KSFT_KHDR_INSTALL := 1 include ../../lib.mk - -$(TEST_GEN_FILES): $(HEADERS) diff --git a/tools/testing/selftests/intel_pstate/Makefile b/tools/testing/selftests/intel_pstate/Makefile index 39f0fa2a8fd63ff51bfeb062831d6e95aaea4b0e..05d66ef50c9771d0b605547331474858069b1630 100644 --- a/tools/testing/selftests/intel_pstate/Makefile +++ b/tools/testing/selftests/intel_pstate/Makefile @@ -2,10 +2,10 @@ CFLAGS := $(CFLAGS) -Wall -D_GNU_SOURCE LDLIBS += -lm -uname_M := $(shell uname -m 2>/dev/null || echo not) -ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/x86/ -e s/x86_64/x86/) +ARCH ?= $(shell uname -m 2>/dev/null || echo not) +ARCH_PROCESSED := $(shell echo $(ARCH) | sed -e s/i.86/x86/ -e s/x86_64/x86/) -ifeq (x86,$(ARCH)) +ifeq (x86,$(ARCH_PROCESSED)) TEST_GEN_FILES := msr aperf endif diff --git a/tools/testing/selftests/tpm2/tpm2.py b/tools/testing/selftests/tpm2/tpm2.py index f34486cd7342d51a9cfddab193ca01243fb0b2e4..3e67fdb518ec32f31e4a49a5dde70902ace20fe3 100644 --- a/tools/testing/selftests/tpm2/tpm2.py +++ b/tools/testing/selftests/tpm2/tpm2.py @@ -370,6 +370,10 @@ class Client: fcntl.fcntl(self.tpm, fcntl.F_SETFL, flags) self.tpm_poll = select.poll() + def __del__(self): + if self.tpm: + self.tpm.close() + def close(self): self.tpm.close() diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index b5a1018b01576f75bcc0de4129f92b17c422c7f5..ebfe24ac0d13b4a9a4fc98acf5d23a9b5e2642c3 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -3949,6 +3949,12 @@ struct compat_kvm_clear_dirty_log { }; }; +long __weak kvm_arch_vm_compat_ioctl(struct file *filp, unsigned int ioctl, + unsigned long arg) +{ + return -ENOTTY; +} + static long kvm_vm_compat_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -3957,6 +3963,11 @@ static long kvm_vm_compat_ioctl(struct file *filp, if (kvm->mm != current->mm || kvm->vm_bugged) return -EIO; + + r = kvm_arch_vm_compat_ioctl(filp, ioctl, arg); + if (r != -ENOTTY) + return r; + switch (ioctl) { #ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT case KVM_CLEAR_DIRTY_LOG: {