diff --git a/Documentation/ABI/testing/sysfs-driver-panthor-profiling b/Documentation/ABI/testing/sysfs-driver-panthor-profiling new file mode 100644 index 0000000000000000000000000000000000000000..af05fccedc15f93f25f1c8485b0326521d2ee2fd --- /dev/null +++ b/Documentation/ABI/testing/sysfs-driver-panthor-profiling @@ -0,0 +1,10 @@ +What: /sys/bus/platform/drivers/panthor/.../profiling +Date: September 2024 +KernelVersion: 6.11.0 +Contact: Adrian Larumbe +Description: + Bitmask to enable drm fdinfo's job profiling measurements. + Valid values are: + 0: Don't enable fdinfo job profiling sources. + 1: Enable GPU cycle measurements for running jobs. + 2: Enable GPU timestamp sampling for running jobs. diff --git a/Documentation/accel/qaic/aic080.rst b/Documentation/accel/qaic/aic080.rst new file mode 100644 index 0000000000000000000000000000000000000000..d563771ea6ce4877f34d5f7e31ab502dbb09b29b --- /dev/null +++ b/Documentation/accel/qaic/aic080.rst @@ -0,0 +1,14 @@ +.. SPDX-License-Identifier: GPL-2.0-only + +=============================== + Qualcomm Cloud AI 80 (AIC080) +=============================== + +Overview +======== + +The Qualcomm Cloud AI 80/AIC080 family of products are a derivative of AIC100. +The number of NSPs and clock rates are reduced to fit within resource +constrained solutions. The PCIe Product ID is 0xa080. + +As a derivative product, all AIC100 documentation applies. diff --git a/Documentation/accel/qaic/aic100.rst b/Documentation/accel/qaic/aic100.rst index 590dae77ea124fe4794648178ae1fe8b4d3852e8..273da6192fb34662045e4300cafb1bbac7692c78 100644 --- a/Documentation/accel/qaic/aic100.rst +++ b/Documentation/accel/qaic/aic100.rst @@ -229,6 +229,8 @@ of the defined channels, and their uses. | _PERIODIC | | | timestamps in the device side logs with| | | | | the host time source. | +----------------+---------+----------+----------------------------------------+ +| IPCR | 24 & 25 | AMSS | AF_QIPCRTR clients and servers. | ++----------------+---------+----------+----------------------------------------+ DMA Bridge ========== diff --git a/Documentation/accel/qaic/index.rst b/Documentation/accel/qaic/index.rst index ad19b88d1a669eab10d949de947996d6d0f20d19..967b9dd8baceac0988400ee42694621ae4110a44 100644 --- a/Documentation/accel/qaic/index.rst +++ b/Documentation/accel/qaic/index.rst @@ -10,4 +10,5 @@ accelerator cards. .. toctree:: qaic + aic080 aic100 diff --git a/Documentation/arch/arm/mem_alignment.rst b/Documentation/arch/arm/mem_alignment.rst index aa22893b62bc342eb47e9a7e8caacc3e51c09112..64bd779593003b07b7a6fa94558049a9d7f5e2b4 100644 --- a/Documentation/arch/arm/mem_alignment.rst +++ b/Documentation/arch/arm/mem_alignment.rst @@ -12,7 +12,7 @@ ones. Of course this is a bad idea to rely on the alignment trap to perform unaligned memory access in general. If those access are predictable, you -are better to use the macros provided by include/asm/unaligned.h. The +are better to use the macros provided by include/linux/unaligned.h. The alignment trap can fixup misaligned access for the exception cases, but at a high performance cost. It better be rare. diff --git a/Documentation/arch/arm64/silicon-errata.rst b/Documentation/arch/arm64/silicon-errata.rst index 9eb5e70b488840ed570e786f5d530ff88ab98609..65bfab1b1861467358d201619018b1a327de4ad8 100644 --- a/Documentation/arch/arm64/silicon-errata.rst +++ b/Documentation/arch/arm64/silicon-errata.rst @@ -146,6 +146,8 @@ stable kernels. +----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A715 | #2645198 | ARM64_ERRATUM_2645198 | +----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-A715 | #3456084 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A720 | #3456091 | ARM64_ERRATUM_3194386 | +----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A725 | #3456106 | ARM64_ERRATUM_3194386 | @@ -186,6 +188,8 @@ stable kernels. +----------------+-----------------+-----------------+-----------------------------+ | ARM | Neoverse-N2 | #3324339 | ARM64_ERRATUM_3194386 | +----------------+-----------------+-----------------+-----------------------------+ +| ARM | Neoverse-N3 | #3456111 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ | ARM | Neoverse-V1 | #1619801 | N/A | +----------------+-----------------+-----------------+-----------------------------+ | ARM | Neoverse-V1 | #3324341 | ARM64_ERRATUM_3194386 | @@ -289,3 +293,5 @@ stable kernels. +----------------+-----------------+-----------------+-----------------------------+ | Microsoft | Azure Cobalt 100| #2253138 | ARM64_ERRATUM_2253138 | +----------------+-----------------+-----------------+-----------------------------+ +| Microsoft | Azure Cobalt 100| #3324339 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ diff --git a/Documentation/core-api/folio_queue.rst b/Documentation/core-api/folio_queue.rst new file mode 100644 index 0000000000000000000000000000000000000000..1fe7a9bc4b8dbe648ed339835e07157ceb909f3c --- /dev/null +++ b/Documentation/core-api/folio_queue.rst @@ -0,0 +1,212 @@ +.. SPDX-License-Identifier: GPL-2.0+ + +=========== +Folio Queue +=========== + +:Author: David Howells + +.. Contents: + + * Overview + * Initialisation + * Adding and removing folios + * Querying information about a folio + * Querying information about a folio_queue + * Folio queue iteration + * Folio marks + * Lockless simultaneous production/consumption issues + + +Overview +======== + +The folio_queue struct forms a single segment in a segmented list of folios +that can be used to form an I/O buffer. As such, the list can be iterated over +using the ITER_FOLIOQ iov_iter type. + +The publicly accessible members of the structure are:: + + struct folio_queue { + struct folio_queue *next; + struct folio_queue *prev; + ... + }; + +A pair of pointers are provided, ``next`` and ``prev``, that point to the +segments on either side of the segment being accessed. Whilst this is a +doubly-linked list, it is intentionally not a circular list; the outward +sibling pointers in terminal segments should be NULL. + +Each segment in the list also stores: + + * an ordered sequence of folio pointers, + * the size of each folio and + * three 1-bit marks per folio, + +but hese should not be accessed directly as the underlying data structure may +change, but rather the access functions outlined below should be used. + +The facility can be made accessible by:: + + #include + +and to use the iterator:: + + #include + + +Initialisation +============== + +A segment should be initialised by calling:: + + void folioq_init(struct folio_queue *folioq); + +with a pointer to the segment to be initialised. Note that this will not +necessarily initialise all the folio pointers, so care must be taken to check +the number of folios added. + + +Adding and removing folios +========================== + +Folios can be set in the next unused slot in a segment struct by calling one +of:: + + unsigned int folioq_append(struct folio_queue *folioq, + struct folio *folio); + + unsigned int folioq_append_mark(struct folio_queue *folioq, + struct folio *folio); + +Both functions update the stored folio count, store the folio and note its +size. The second function also sets the first mark for the folio added. Both +functions return the number of the slot used. [!] Note that no attempt is made +to check that the capacity wasn't overrun and the list will not be extended +automatically. + +A folio can be excised by calling:: + + void folioq_clear(struct folio_queue *folioq, unsigned int slot); + +This clears the slot in the array and also clears all the marks for that folio, +but doesn't change the folio count - so future accesses of that slot must check +if the slot is occupied. + + +Querying information about a folio +================================== + +Information about the folio in a particular slot may be queried by the +following function:: + + struct folio *folioq_folio(const struct folio_queue *folioq, + unsigned int slot); + +If a folio has not yet been set in that slot, this may yield an undefined +pointer. The size of the folio in a slot may be queried with either of:: + + unsigned int folioq_folio_order(const struct folio_queue *folioq, + unsigned int slot); + + size_t folioq_folio_size(const struct folio_queue *folioq, + unsigned int slot); + +The first function returns the size as an order and the second as a number of +bytes. + + +Querying information about a folio_queue +======================================== + +Information may be retrieved about a particular segment with the following +functions:: + + unsigned int folioq_nr_slots(const struct folio_queue *folioq); + + unsigned int folioq_count(struct folio_queue *folioq); + + bool folioq_full(struct folio_queue *folioq); + +The first function returns the maximum capacity of a segment. It must not be +assumed that this won't vary between segments. The second returns the number +of folios added to a segments and the third is a shorthand to indicate if the +segment has been filled to capacity. + +Not that the count and fullness are not affected by clearing folios from the +segment. These are more about indicating how many slots in the array have been +initialised, and it assumed that slots won't get reused, but rather the segment +will get discarded as the queue is consumed. + + +Folio marks +=========== + +Folios within a queue can also have marks assigned to them. These marks can be +used to note information such as if a folio needs folio_put() calling upon it. +There are three marks available to be set for each folio. + +The marks can be set by:: + + void folioq_mark(struct folio_queue *folioq, unsigned int slot); + void folioq_mark2(struct folio_queue *folioq, unsigned int slot); + void folioq_mark3(struct folio_queue *folioq, unsigned int slot); + +Cleared by:: + + void folioq_unmark(struct folio_queue *folioq, unsigned int slot); + void folioq_unmark2(struct folio_queue *folioq, unsigned int slot); + void folioq_unmark3(struct folio_queue *folioq, unsigned int slot); + +And the marks can be queried by:: + + bool folioq_is_marked(const struct folio_queue *folioq, unsigned int slot); + bool folioq_is_marked2(const struct folio_queue *folioq, unsigned int slot); + bool folioq_is_marked3(const struct folio_queue *folioq, unsigned int slot); + +The marks can be used for any purpose and are not interpreted by this API. + + +Folio queue iteration +===================== + +A list of segments may be iterated over using the I/O iterator facility using +an ``iov_iter`` iterator of ``ITER_FOLIOQ`` type. The iterator may be +initialised with:: + + void iov_iter_folio_queue(struct iov_iter *i, unsigned int direction, + const struct folio_queue *folioq, + unsigned int first_slot, unsigned int offset, + size_t count); + +This may be told to start at a particular segment, slot and offset within a +queue. The iov iterator functions will follow the next pointers when advancing +and prev pointers when reverting when needed. + + +Lockless simultaneous production/consumption issues +=================================================== + +If properly managed, the list can be extended by the producer at the head end +and shortened by the consumer at the tail end simultaneously without the need +to take locks. The ITER_FOLIOQ iterator inserts appropriate barriers to aid +with this. + +Care must be taken when simultaneously producing and consuming a list. If the +last segment is reached and the folios it refers to are entirely consumed by +the IOV iterators, an iov_iter struct will be left pointing to the last segment +with a slot number equal to the capacity of that segment. The iterator will +try to continue on from this if there's another segment available when it is +used again, but care must be taken lest the segment got removed and freed by +the consumer before the iterator was advanced. + +It is recommended that the queue always contain at least one segment, even if +that segment has never been filled or is entirely spent. This prevents the +head and tail pointers from collapsing. + + +API Function Reference +====================== + +.. kernel-doc:: include/linux/folio_queue.h diff --git a/Documentation/core-api/index.rst b/Documentation/core-api/index.rst index a331d2c814f57d65313ef42897c21204b995e816..6a875743dd4b7f1d0198c7b2bb0e7365ed3d3eaa 100644 --- a/Documentation/core-api/index.rst +++ b/Documentation/core-api/index.rst @@ -37,6 +37,7 @@ Library functionality that is used throughout the kernel. kref cleanup assoc_array + folio_queue xarray maple_tree idr diff --git a/Documentation/core-api/unaligned-memory-access.rst b/Documentation/core-api/unaligned-memory-access.rst index 1ee82419d8aa66929a5a52fac89a62c7f54d0644..5ceeb80eb539cf3aedf617bf75d85c4dc2af87b9 100644 --- a/Documentation/core-api/unaligned-memory-access.rst +++ b/Documentation/core-api/unaligned-memory-access.rst @@ -203,7 +203,7 @@ Avoiding unaligned accesses =========================== The easiest way to avoid unaligned access is to use the get_unaligned() and -put_unaligned() macros provided by the header file. +put_unaligned() macros provided by the header file. Going back to an earlier example of code that potentially causes unaligned access:: diff --git a/Documentation/devicetree/bindings/display/bridge/sil,sii9022.yaml b/Documentation/devicetree/bindings/display/bridge/sil,sii9022.yaml index 5a69547ad3d7966767a8be9f840345019101c53d..1509c4535e53c667a58c65ccee49810aa690c393 100644 --- a/Documentation/devicetree/bindings/display/bridge/sil,sii9022.yaml +++ b/Documentation/devicetree/bindings/display/bridge/sil,sii9022.yaml @@ -81,9 +81,22 @@ properties: properties: port@0: - $ref: /schemas/graph.yaml#/properties/port + unevaluatedProperties: false + $ref: /schemas/graph.yaml#/$defs/port-base description: Parallel RGB input port + properties: + endpoint: + $ref: /schemas/graph.yaml#/$defs/endpoint-base + unevaluatedProperties: false + + properties: + bus-width: + description: + Endpoint bus width. + enum: [ 16, 18, 24 ] + default: 24 + port@1: $ref: /schemas/graph.yaml#/properties/port description: HDMI output port diff --git a/Documentation/devicetree/bindings/display/bridge/ti,tdp158.yaml b/Documentation/devicetree/bindings/display/bridge/ti,tdp158.yaml new file mode 100644 index 0000000000000000000000000000000000000000..1c522f72c4bae3313930b5c76dd04dde1aef5151 --- /dev/null +++ b/Documentation/devicetree/bindings/display/bridge/ti,tdp158.yaml @@ -0,0 +1,57 @@ +# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/display/bridge/ti,tdp158.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: TI TDP158 HDMI to TMDS Redriver + +maintainers: + - Arnaud Vrac + - Pierre-Hugues Husson + +properties: + compatible: + const: ti,tdp158 + +# The reg property is required if and only if the device is connected +# to an I2C bus. In pin strap mode, reg must not be specified. + reg: + description: I2C address of the device + +# Pin 36 = Operation Enable / Reset Pin +# OE = L: Power Down Mode +# OE = H: Normal Operation +# Internal weak pullup - device resets on H to L transitions + enable-gpios: + description: GPIO controlling bridge enable + + vcc-supply: + description: Power supply 3.3V + + vdd-supply: + description: Power supply 1.1V + + ports: + $ref: /schemas/graph.yaml#/properties/ports + + properties: + port@0: + $ref: /schemas/graph.yaml#/properties/port + description: Bridge input + + port@1: + $ref: /schemas/graph.yaml#/properties/port + description: Bridge output + + required: + - port@0 + - port@1 + +required: + - compatible + - vcc-supply + - vdd-supply + - ports + +additionalProperties: false diff --git a/Documentation/devicetree/bindings/display/bridge/toshiba,tc358768.yaml b/Documentation/devicetree/bindings/display/bridge/toshiba,tc358768.yaml index 779d8c57f854db8663f18473edf78c85ce08251f..bb5d3b5438003c01dcf9bd987f81399ae79711f6 100644 --- a/Documentation/devicetree/bindings/display/bridge/toshiba,tc358768.yaml +++ b/Documentation/devicetree/bindings/display/bridge/toshiba,tc358768.yaml @@ -60,6 +60,10 @@ properties: data-lines: $ref: /schemas/types.yaml#/definitions/uint32 enum: [ 16, 18, 24 ] + deprecated: true + + bus-width: + enum: [ 16, 18, 24 ] port@1: $ref: /schemas/graph.yaml#/properties/port diff --git a/Documentation/devicetree/bindings/display/imx/fsl-imx-drm.txt b/Documentation/devicetree/bindings/display/imx/fsl-imx-drm.txt index 3c35338a2867cfdeb16f0ad279544a6d940e5301..269b1ae2fca99852f138c92b87d24d8c2d2850d3 100644 --- a/Documentation/devicetree/bindings/display/imx/fsl-imx-drm.txt +++ b/Documentation/devicetree/bindings/display/imx/fsl-imx-drm.txt @@ -119,7 +119,6 @@ Optional properties: - interface-pix-fmt: How this display is connected to the display interface. Currently supported types: "rgb24", "rgb565", "bgr666" and "lvds666". -- edid: verbatim EDID data block describing attached display. - ddc: phandle describing the i2c bus handling the display data channel - port@[0-1]: Port nodes with endpoint definitions as defined in @@ -131,7 +130,6 @@ example: disp0 { compatible = "fsl,imx-parallel-display"; - edid = [edid-data]; interface-pix-fmt = "rgb24"; port@0 { diff --git a/Documentation/devicetree/bindings/display/imx/ldb.txt b/Documentation/devicetree/bindings/display/imx/ldb.txt index 8e6e7d797943ff4635dd8260e346a8bc109819b7..03653a291b549b913a28bf34185e4b44def0fa19 100644 --- a/Documentation/devicetree/bindings/display/imx/ldb.txt +++ b/Documentation/devicetree/bindings/display/imx/ldb.txt @@ -62,7 +62,6 @@ Required properties: display-timings are used instead. Optional properties (required if display-timings are used): - - ddc-i2c-bus: phandle of an I2C controller used for DDC EDID probing - display-timings : A node that describes the display timings as defined in Documentation/devicetree/bindings/display/panel/display-timing.txt. - fsl,data-mapping : should be "spwg" or "jeida" diff --git a/Documentation/devicetree/bindings/display/panel/panel-lvds.yaml b/Documentation/devicetree/bindings/display/panel/panel-lvds.yaml index 155d8ffa8f6ef1be098f574854ea9b95dc806e66..5af2d69300751a2bd9448efc0fe88e72304fe449 100644 --- a/Documentation/devicetree/bindings/display/panel/panel-lvds.yaml +++ b/Documentation/devicetree/bindings/display/panel/panel-lvds.yaml @@ -50,6 +50,8 @@ properties: - hannstar,hsd101pww2 # Hydis Technologies 7" WXGA (800x1280) TFT LCD LVDS panel - hydis,hv070wx2-1e0 + # Jenson Display BL-JT60050-01A 7" WSVGA (1024x600) color TFT LCD LVDS panel + - jenson,bl-jt60050-01a - tbs,a711-panel - const: panel-lvds diff --git a/Documentation/devicetree/bindings/display/panel/panel-simple.yaml b/Documentation/devicetree/bindings/display/panel/panel-simple.yaml index b89e3979057911ab9e669e97e71c16578d9e0150..18b63f356bb4bbf6d2c8e58b13ebb14c5f4004ad 100644 --- a/Documentation/devicetree/bindings/display/panel/panel-simple.yaml +++ b/Documentation/devicetree/bindings/display/panel/panel-simple.yaml @@ -200,6 +200,8 @@ properties: - logictechno,lttd800480070-l2rt # Logic Technologies LTTD800480070-L6WH-RT 7” 800x480 TFT Resistive Touch Module - logictechno,lttd800480070-l6wh-rt + # Microchip AC69T88A 5" 800X480 LVDS interface TFT LCD Panel + - microchip,ac69t88a # Mitsubishi "AA070MC01 7.0" WVGA TFT LCD panel - mitsubishi,aa070mc01-ca1 # Mitsubishi AA084XE01 8.4" XGA TFT LCD panel diff --git a/Documentation/devicetree/bindings/display/panel/samsung,ams581vf01.yaml b/Documentation/devicetree/bindings/display/panel/samsung,ams581vf01.yaml new file mode 100644 index 0000000000000000000000000000000000000000..70dff9c0ef2beca88020f4b22d00652684e0c387 --- /dev/null +++ b/Documentation/devicetree/bindings/display/panel/samsung,ams581vf01.yaml @@ -0,0 +1,79 @@ +# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/display/panel/samsung,ams581vf01.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Samsung AMS581VF01 SOFEF01-based 5.81" 1080x2340 MIPI-DSI Panel + +maintainers: + - Danila Tikhonov + +description: + The Samsung AMS581VF01 is a 5.81 inch 1080x2340 MIPI-DSI CMD mode OLED panel. + +allOf: + - $ref: panel-common.yaml# + +properties: + compatible: + const: samsung,ams581vf01 + + reg: + maxItems: 1 + + vdd3p3-supply: + description: 3.3V source voltage rail + + vddio-supply: + description: I/O source voltage rail + + vsn-supply: + description: Negative source voltage rail + + vsp-supply: + description: Positive source voltage rail + + reset-gpios: true + port: true + +required: + - compatible + - reg + - vdd3p3-supply + - vddio-supply + - vsn-supply + - vsp-supply + - reset-gpios + - port + +additionalProperties: false + +examples: + - | + #include + + dsi { + #address-cells = <1>; + #size-cells = <0>; + + panel@0 { + compatible = "samsung,ams581vf01"; + reg = <0>; + + vdd3p3-supply = <&vreg_l7c_3p0>; + vddio-supply = <&vreg_l13a_1p8>; + vsn-supply = <&vreg_ibb>; + vsp-supply = <&vreg_lab>; + + reset-gpios = <&pm6150l_gpios 9 GPIO_ACTIVE_LOW>; + + port { + panel_in: endpoint { + remote-endpoint = <&mdss_dsi0_out>; + }; + }; + }; + }; + +... diff --git a/Documentation/devicetree/bindings/display/panel/samsung,ams639rq08.yaml b/Documentation/devicetree/bindings/display/panel/samsung,ams639rq08.yaml new file mode 100644 index 0000000000000000000000000000000000000000..f5b6ecb96f994fca2c6bff9c796ca8bea35b78dd --- /dev/null +++ b/Documentation/devicetree/bindings/display/panel/samsung,ams639rq08.yaml @@ -0,0 +1,80 @@ +# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/display/panel/samsung,ams639rq08.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Samsung AMS639RQ08 EA8076-based 6.39" 1080x2340 MIPI-DSI Panel + +maintainers: + - Danila Tikhonov + - Jens Reidel + +description: + The Samsung AMS639RQ08 is a 6.39 inch 1080x2340 MIPI-DSI CMD mode AMOLED panel. + +allOf: + - $ref: panel-common.yaml# + +properties: + compatible: + const: samsung,ams639rq08 + + reg: + maxItems: 1 + + vdd3p3-supply: + description: 3.3V source voltage rail + + vddio-supply: + description: I/O source voltage rail + + vsn-supply: + description: Negative source voltage rail + + vsp-supply: + description: Positive source voltage rail + + reset-gpios: true + port: true + +required: + - compatible + - reg + - vdd3p3-supply + - vddio-supply + - vsn-supply + - vsp-supply + - reset-gpios + - port + +additionalProperties: false + +examples: + - | + #include + + dsi { + #address-cells = <1>; + #size-cells = <0>; + + panel@0 { + compatible = "samsung,ams639rq08"; + reg = <0>; + + vdd3p3-supply = <&vreg_l18a_2p8>; + vddio-supply = <&vreg_l13a_1p8>; + vsn-supply = <&vreg_ibb>; + vsp-supply = <&vreg_lab>; + + reset-gpios = <&pm6150l_gpios 9 GPIO_ACTIVE_LOW>; + + port { + panel_in: endpoint { + remote-endpoint = <&mdss_dsi0_out>; + }; + }; + }; + }; + +... diff --git a/Documentation/devicetree/bindings/display/panel/samsung,s6e3ha8.yaml b/Documentation/devicetree/bindings/display/panel/samsung,s6e3ha8.yaml new file mode 100644 index 0000000000000000000000000000000000000000..05a78429aaead80ed06d196482032ae20517fa41 --- /dev/null +++ b/Documentation/devicetree/bindings/display/panel/samsung,s6e3ha8.yaml @@ -0,0 +1,75 @@ +# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/display/panel/samsung,s6e3ha8.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Samsung s6e3ha8 AMOLED DSI panel + +description: The s6e3ha8 is a 1440x2960 DPI display panel from Samsung Mobile + Displays (SMD). + +maintainers: + - Dzmitry Sankouski + +allOf: + - $ref: panel-common.yaml# + +properties: + compatible: + const: samsung,s6e3ha8 + + reg: + maxItems: 1 + + reset-gpios: true + + port: true + + vdd3-supply: + description: VDD regulator + + vci-supply: + description: VCI regulator + + vddr-supply: + description: VDDR regulator + +required: + - compatible + - reset-gpios + - vdd3-supply + - vci-supply + - vddr-supply + +unevaluatedProperties: false + +examples: + - | + #include + + dsi { + #address-cells = <1>; + #size-cells = <0>; + + panel@0 { + compatible = "samsung,s6e3ha8"; + reg = <0>; + vci-supply = <&s2dos05_ldo4>; + vddr-supply = <&s2dos05_buck1>; + vdd3-supply = <&s2dos05_ldo1>; + te-gpios = <&tlmm 10 GPIO_ACTIVE_HIGH>; + reset-gpios = <&tlmm 6 GPIO_ACTIVE_HIGH>; + pinctrl-0 = <&sde_dsi_active &sde_te_active_sleep>; + pinctrl-1 = <&sde_dsi_suspend &sde_te_active_sleep>; + pinctrl-names = "default", "sleep"; + + port { + panel_in: endpoint { + remote-endpoint = <&mdss_dsi0_out>; + }; + }; + }; + }; + +... diff --git a/Documentation/devicetree/bindings/display/rockchip/rockchip,rk3588-dw-hdmi-qp.yaml b/Documentation/devicetree/bindings/display/rockchip/rockchip,rk3588-dw-hdmi-qp.yaml new file mode 100644 index 0000000000000000000000000000000000000000..d8e761865f27e284d168d08c7599e4cd31a4c015 --- /dev/null +++ b/Documentation/devicetree/bindings/display/rockchip/rockchip,rk3588-dw-hdmi-qp.yaml @@ -0,0 +1,188 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/display/rockchip/rockchip,rk3588-dw-hdmi-qp.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Rockchip DW HDMI QP TX Encoder + +maintainers: + - Cristian Ciocaltea + +description: | + Rockchip RK3588 SoC integrates the Synopsys DesignWare HDMI QP TX controller + IP and a HDMI/eDP TX Combo PHY based on a Samsung IP block, providing the + following features, among others: + + * Fixed Rate Link (FRL) + * Display Stream Compression (DSC) + * 4K@120Hz and 8K@60Hz video modes + * Variable Refresh Rate (VRR) including Quick Media Switching (QMS) + * Fast Vactive (FVA) + * SCDC I2C DDC access + * Multi-stream audio + * Enhanced Audio Return Channel (EARC) + +allOf: + - $ref: /schemas/sound/dai-common.yaml# + +properties: + compatible: + enum: + - rockchip,rk3588-dw-hdmi-qp + + reg: + maxItems: 1 + + clocks: + items: + - description: Peripheral/APB bus clock + - description: EARC RX biphase clock + - description: Reference clock + - description: Audio interface clock + - description: TMDS/FRL link clock + - description: Video datapath clock + + clock-names: + items: + - const: pclk + - const: earc + - const: ref + - const: aud + - const: hdp + - const: hclk_vo1 + + interrupts: + items: + - description: AVP Unit interrupt + - description: CEC interrupt + - description: eARC RX interrupt + - description: Main Unit interrupt + - description: HPD interrupt + + interrupt-names: + items: + - const: avp + - const: cec + - const: earc + - const: main + - const: hpd + + phys: + maxItems: 1 + description: The HDMI/eDP PHY + + ports: + $ref: /schemas/graph.yaml#/properties/ports + + properties: + port@0: + $ref: /schemas/graph.yaml#/properties/port + description: Video port for RGB/YUV input. + + port@1: + $ref: /schemas/graph.yaml#/properties/port + description: Video port for HDMI/eDP output. + + required: + - port@0 + - port@1 + + power-domains: + maxItems: 1 + + resets: + maxItems: 2 + + reset-names: + items: + - const: ref + - const: hdp + + "#sound-dai-cells": + const: 0 + + rockchip,grf: + $ref: /schemas/types.yaml#/definitions/phandle + description: + Some HDMI QP related data is accessed through SYS GRF regs. + + rockchip,vo-grf: + $ref: /schemas/types.yaml#/definitions/phandle + description: + Additional HDMI QP related data is accessed through VO GRF regs. + +required: + - compatible + - reg + - clocks + - clock-names + - interrupts + - interrupt-names + - phys + - ports + - resets + - reset-names + - rockchip,grf + - rockchip,vo-grf + +unevaluatedProperties: false + +examples: + - | + #include + #include + #include + #include + #include + + soc { + #address-cells = <2>; + #size-cells = <2>; + + hdmi@fde80000 { + compatible = "rockchip,rk3588-dw-hdmi-qp"; + reg = <0x0 0xfde80000 0x0 0x20000>; + clocks = <&cru PCLK_HDMITX0>, + <&cru CLK_HDMITX0_EARC>, + <&cru CLK_HDMITX0_REF>, + <&cru MCLK_I2S5_8CH_TX>, + <&cru CLK_HDMIHDP0>, + <&cru HCLK_VO1>; + clock-names = "pclk", "earc", "ref", "aud", "hdp", "hclk_vo1"; + interrupts = , + , + , + , + ; + interrupt-names = "avp", "cec", "earc", "main", "hpd"; + phys = <&hdptxphy_hdmi0>; + power-domains = <&power RK3588_PD_VO1>; + resets = <&cru SRST_HDMITX0_REF>, <&cru SRST_HDMIHDP0>; + reset-names = "ref", "hdp"; + rockchip,grf = <&sys_grf>; + rockchip,vo-grf = <&vo1_grf>; + #sound-dai-cells = <0>; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + + hdmi0_in_vp0: endpoint { + remote-endpoint = <&vp0_out_hdmi0>; + }; + }; + + port@1 { + reg = <1>; + + hdmi0_out_con0: endpoint { + remote-endpoint = <&hdmi_con0_in>; + }; + }; + }; + }; + }; diff --git a/Documentation/devicetree/bindings/display/sharp,ls010b7dh04.yaml b/Documentation/devicetree/bindings/display/sharp,ls010b7dh04.yaml new file mode 100644 index 0000000000000000000000000000000000000000..8097f091c2a55f5488318b4c6926b02e05d3ee9f --- /dev/null +++ b/Documentation/devicetree/bindings/display/sharp,ls010b7dh04.yaml @@ -0,0 +1,92 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/display/sharp,ls010b7dh04.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Sharp Memory LCD panels + +maintainers: + - Alex Lanzano + +description: + Sharp Memory LCDs are a series of monochrome displays that operate over + a SPI bus. The displays require a signal (VCOM) to be generated to prevent + DC bias build up resulting in pixels being unable to change. Three modes + can be used to provide the VCOM signal ("software", "external", "pwm"). + +properties: + compatible: + enum: + - sharp,ls010b7dh04 + - sharp,ls011b7dh03 + - sharp,ls012b7dd01 + - sharp,ls013b7dh03 + - sharp,ls013b7dh05 + - sharp,ls018b7dh02 + - sharp,ls027b7dh01 + - sharp,ls027b7dh01a + - sharp,ls032b7dd02 + - sharp,ls044q7dh01 + + reg: + maxItems: 1 + + spi-max-frequency: + maximum: 2000000 + + sharp,vcom-mode: + $ref: /schemas/types.yaml#/definitions/string + description: | + software - This mode relies on a software operation to send a + "maintain display" message to the display, toggling the vcom + bit on and off with each message + + external - This mode relies on an external clock to generate + the signal on the EXTCOMM pin + + pwm - This mode relies on a pwm device to generate the signal + on the EXTCOMM pin + + enum: [software, external, pwm] + + enable-gpios: true + + pwms: + maxItems: 1 + description: External VCOM signal + +required: + - compatible + - reg + - sharp,vcom-mode + +allOf: + - $ref: panel/panel-common.yaml# + - $ref: /schemas/spi/spi-peripheral-props.yaml# + + - if: + properties: + sharp,vcom-mode: + const: pwm + then: + required: + - pwms + +unevaluatedProperties: false + +examples: + - | + spi { + #address-cells = <1>; + #size-cells = <0>; + + display@0 { + compatible = "sharp,ls013b7dh03"; + reg = <0>; + spi-cs-high; + spi-max-frequency = <1000000>; + sharp,vcom-mode = "software"; + }; + }; +... diff --git a/Documentation/devicetree/bindings/gpu/arm,mali-bifrost.yaml b/Documentation/devicetree/bindings/gpu/arm,mali-bifrost.yaml index 278399adc5506973dcb399807ba96a9a061b0c16..735c7f06c24e632ab738d062f15378f754c8adaf 100644 --- a/Documentation/devicetree/bindings/gpu/arm,mali-bifrost.yaml +++ b/Documentation/devicetree/bindings/gpu/arm,mali-bifrost.yaml @@ -26,6 +26,7 @@ properties: - renesas,r9a07g054-mali - rockchip,px30-mali - rockchip,rk3568-mali + - rockchip,rk3576-mali - const: arm,mali-bifrost # Mali Bifrost GPU model/revision is fully discoverable - items: - enum: diff --git a/Documentation/devicetree/bindings/net/xlnx,axi-ethernet.yaml b/Documentation/devicetree/bindings/net/xlnx,axi-ethernet.yaml index bbe89ea9590ceb53df4a0f589787c9990aec0219..e95c216282818e66e6b26bf763954b061a2d5e93 100644 --- a/Documentation/devicetree/bindings/net/xlnx,axi-ethernet.yaml +++ b/Documentation/devicetree/bindings/net/xlnx,axi-ethernet.yaml @@ -34,6 +34,7 @@ properties: and length of the AXI DMA controller IO space, unless axistream-connected is specified, in which case the reg attribute of the node referenced by it is used. + minItems: 1 maxItems: 2 interrupts: @@ -181,7 +182,7 @@ examples: clock-names = "s_axi_lite_clk", "axis_clk", "ref_clk", "mgt_clk"; clocks = <&axi_clk>, <&axi_clk>, <&pl_enet_ref_clk>, <&mgt_clk>; phy-mode = "mii"; - reg = <0x00 0x40000000 0x00 0x40000>; + reg = <0x40000000 0x40000>; xlnx,rxcsum = <0x2>; xlnx,rxmem = <0x800>; xlnx,txcsum = <0x2>; diff --git a/Documentation/devicetree/bindings/sound/davinci-mcasp-audio.yaml b/Documentation/devicetree/bindings/sound/davinci-mcasp-audio.yaml index 7735e08d35ba147e3a4a815ada8d31081c6338e8..ab3206ffa4af882b8643fd20613fbeff9394697c 100644 --- a/Documentation/devicetree/bindings/sound/davinci-mcasp-audio.yaml +++ b/Documentation/devicetree/bindings/sound/davinci-mcasp-audio.yaml @@ -102,7 +102,7 @@ properties: default: 2 interrupts: - anyOf: + oneOf: - minItems: 1 items: - description: TX interrupt diff --git a/Documentation/devicetree/bindings/sound/qcom,sm8250.yaml b/Documentation/devicetree/bindings/sound/qcom,sm8250.yaml index 1d3acdc0c7339b54b68040de2a7e53503555a574..2e2e01493a5f4f5048aaa894a95ebfc7fd033e4f 100644 --- a/Documentation/devicetree/bindings/sound/qcom,sm8250.yaml +++ b/Documentation/devicetree/bindings/sound/qcom,sm8250.yaml @@ -30,6 +30,7 @@ properties: - qcom,apq8096-sndcard - qcom,qcm6490-idp-sndcard - qcom,qcs6490-rb3gen2-sndcard + - qcom,qrb4210-rb2-sndcard - qcom,qrb5165-rb5-sndcard - qcom,sc7180-qdsp6-sndcard - qcom,sc8280xp-sndcard diff --git a/Documentation/devicetree/bindings/sound/renesas,rsnd.yaml b/Documentation/devicetree/bindings/sound/renesas,rsnd.yaml index 3bc93c59535e9abeb48584917b13ab83d2ae7854..6d0d1514cd4211b90aa4ead776694fcea63562f1 100644 --- a/Documentation/devicetree/bindings/sound/renesas,rsnd.yaml +++ b/Documentation/devicetree/bindings/sound/renesas,rsnd.yaml @@ -302,7 +302,7 @@ allOf: reg-names: items: enum: - - scu + - sru - ssi - adg # for Gen2/Gen3 diff --git a/Documentation/devicetree/bindings/vendor-prefixes.yaml b/Documentation/devicetree/bindings/vendor-prefixes.yaml index b320a39de7fe40ce4d97ed3ea264a5971a3428dd..46901c8d7eb0074b61839a21025d84a942101f83 100644 --- a/Documentation/devicetree/bindings/vendor-prefixes.yaml +++ b/Documentation/devicetree/bindings/vendor-prefixes.yaml @@ -752,6 +752,8 @@ patternProperties: description: Japan Display Inc. "^jedec,.*": description: JEDEC Solid State Technology Association + "^jenson,.*": + description: Jenson Display Co. Ltd. "^jesurun,.*": description: Shenzhen Jesurun Electronics Business Dept. "^jethome,.*": diff --git a/Documentation/driver-api/wmi.rst b/Documentation/driver-api/wmi.rst index 6ca58c8249e5482550c234784aa09463b708d546..4e8dbdb1fc6780090f6bd428ce02fcbfed4fde84 100644 --- a/Documentation/driver-api/wmi.rst +++ b/Documentation/driver-api/wmi.rst @@ -7,12 +7,11 @@ WMI Driver API The WMI driver core supports a more modern bus-based interface for interacting with WMI devices, and an older GUID-based interface. The latter interface is considered to be deprecated, so new WMI drivers should generally avoid it since -it has some issues with multiple WMI devices and events sharing the same GUIDs -and/or notification IDs. The modern bus-based interface instead maps each -WMI device to a :c:type:`struct wmi_device `, so it supports -WMI devices sharing GUIDs and/or notification IDs. Drivers can then register -a :c:type:`struct wmi_driver `, which will be bound to compatible -WMI devices by the driver core. +it has some issues with multiple WMI devices sharing the same GUID. +The modern bus-based interface instead maps each WMI device to a +:c:type:`struct wmi_device `, so it supports WMI devices sharing the +same GUID. Drivers can then register a :c:type:`struct wmi_driver ` +which will be bound to compatible WMI devices by the driver core. .. kernel-doc:: include/linux/wmi.h :internal: diff --git a/Documentation/gpu/automated_testing.rst b/Documentation/gpu/automated_testing.rst index 2d5a28866afe7e78f5604534d28e0951bf32ec07..6d7c6086034d33af7aeb5d91c394bd1ffa5c9fbc 100644 --- a/Documentation/gpu/automated_testing.rst +++ b/Documentation/gpu/automated_testing.rst @@ -68,19 +68,25 @@ known to behave unreliably. These tests won't cause a job to fail regardless of the result. They will still be run. Each new flake entry must be associated with a link to the email reporting the -bug to the author of the affected driver, the board name or Device Tree name of -the board, the first kernel version affected, the IGT version used for tests, -and an approximation of the failure rate. +bug to the author of the affected driver or the relevant GitLab issue. The entry +must also include the board name or Device Tree name, the first kernel version +affected, the IGT version used for tests, and an approximation of the failure rate. They should be provided under the following format:: - # Bug Report: $LORE_OR_PATCHWORK_URL + # Bug Report: $LORE_URL_OR_GITLAB_ISSUE # Board Name: broken-board.dtb # Linux Version: 6.6-rc1 # IGT Version: 1.28-gd2af13d9f # Failure Rate: 100 flaky-test +Use the appropriate link below to create a GitLab issue: +amdgpu driver: https://gitlab.freedesktop.org/drm/amd/-/issues +i915 driver: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues +msm driver: https://gitlab.freedesktop.org/drm/msm/-/issues +xe driver: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues + drivers/gpu/drm/ci/${DRIVER_NAME}-${HW_REVISION}-skips.txt ----------------------------------------------------------- diff --git a/Documentation/gpu/drivers.rst b/Documentation/gpu/drivers.rst index b899cbc5c2b488b982bcb73b85dbc17c8daba239..1f17ad0790d755512e857789d3327658293594a9 100644 --- a/Documentation/gpu/drivers.rst +++ b/Documentation/gpu/drivers.rst @@ -22,6 +22,8 @@ GPU Driver Documentation afbc komeda-kms panfrost + panthor + zynqmp .. only:: subproject and html diff --git a/Documentation/gpu/drm-client.rst b/Documentation/gpu/drm-client.rst index 58b5a1d1219d11fdef8e8f081329725a84bbc4f5..cbcfe30de777fb04170422ba76f8a0c4ad890c9b 100644 --- a/Documentation/gpu/drm-client.rst +++ b/Documentation/gpu/drm-client.rst @@ -13,3 +13,6 @@ Kernel clients .. kernel-doc:: drivers/gpu/drm/drm_client_modeset.c :export: + +.. kernel-doc:: drivers/gpu/drm/drm_client_event.c + :export: diff --git a/Documentation/gpu/drm-internals.rst b/Documentation/gpu/drm-internals.rst index 11d9a5730fb22f75c3aa1ae9d0c5b02813a2729b..cb9ae282771c8ade7148a5e777da27a95ddbb108 100644 --- a/Documentation/gpu/drm-internals.rst +++ b/Documentation/gpu/drm-internals.rst @@ -75,18 +75,6 @@ Module Initialization .. kernel-doc:: include/drm/drm_module.h :doc: overview -Managing Ownership of the Framebuffer Aperture ----------------------------------------------- - -.. kernel-doc:: drivers/gpu/drm/drm_aperture.c - :doc: overview - -.. kernel-doc:: include/drm/drm_aperture.h - :internal: - -.. kernel-doc:: drivers/gpu/drm/drm_aperture.c - :export: - Device Instance and Driver Handling ----------------------------------- diff --git a/Documentation/gpu/drm-kms-helpers.rst b/Documentation/gpu/drm-kms-helpers.rst index 8435e8621cc0872b5b8e29d89f156ee28106308f..8cf2f041af4704875910ce8228ae04615d0f21bd 100644 --- a/Documentation/gpu/drm-kms-helpers.rst +++ b/Documentation/gpu/drm-kms-helpers.rst @@ -110,15 +110,6 @@ fbdev Helper Functions Reference .. kernel-doc:: drivers/gpu/drm/drm_fb_helper.c :doc: fbdev helpers -.. kernel-doc:: drivers/gpu/drm/drm_fbdev_dma.c - :export: - -.. kernel-doc:: drivers/gpu/drm/drm_fbdev_shmem.c - :export: - -.. kernel-doc:: drivers/gpu/drm/drm_fbdev_ttm.c - :export: - .. kernel-doc:: include/drm/drm_fb_helper.h :internal: @@ -181,7 +172,7 @@ Bridge Operations Bridge Connector Helper ----------------------- -.. kernel-doc:: drivers/gpu/drm/drm_bridge_connector.c +.. kernel-doc:: drivers/gpu/drm/display/drm_bridge_connector.c :doc: overview @@ -204,7 +195,7 @@ MIPI-DSI bridge operation Bridge Connector Helper Reference --------------------------------- -.. kernel-doc:: drivers/gpu/drm/drm_bridge_connector.c +.. kernel-doc:: drivers/gpu/drm/display/drm_bridge_connector.c :export: Panel-Bridge Helper Reference diff --git a/Documentation/gpu/drm-uapi.rst b/Documentation/gpu/drm-uapi.rst index 370d820be24819de57a1b4b2e3ab3ace1c256deb..b75cc9a70d1f9871b601f93e8487a25cbda837bb 100644 --- a/Documentation/gpu/drm-uapi.rst +++ b/Documentation/gpu/drm-uapi.rst @@ -305,13 +305,26 @@ Kernel Mode Driver ------------------ The KMD is responsible for checking if the device needs a reset, and to perform -it as needed. Usually a hang is detected when a job gets stuck executing. KMD -should keep track of resets, because userspace can query any time about the -reset status for a specific context. This is needed to propagate to the rest of -the stack that a reset has happened. Currently, this is implemented by each -driver separately, with no common DRM interface. Ideally this should be properly -integrated at DRM scheduler to provide a common ground for all drivers. After a -reset, KMD should reject new command submissions for affected contexts. +it as needed. Usually a hang is detected when a job gets stuck executing. + +Propagation of errors to userspace has proven to be tricky since it goes in +the opposite direction of the usual flow of commands. Because of this vendor +independent error handling was added to the &dma_fence object, this way drivers +can add an error code to their fences before signaling them. See function +dma_fence_set_error() on how to do this and for examples of error codes to use. + +The DRM scheduler also allows setting error codes on all pending fences when +hardware submissions are restarted after an reset. Error codes are also +forwarded from the hardware fence to the scheduler fence to bubble up errors +to the higher levels of the stack and eventually userspace. + +Fence errors can be queried by userspace through the generic SYNC_IOC_FILE_INFO +IOCTL as well as through driver specific interfaces. + +Additional to setting fence errors drivers should also keep track of resets per +context, the DRM scheduler provides the drm_sched_entity_error() function as +helper for this use case. After a reset, KMD should reject new command +submissions for affected contexts. User Mode Driver ---------------- diff --git a/Documentation/gpu/drm-usage-stats.rst b/Documentation/gpu/drm-usage-stats.rst index a80f95ca1b2f4951b5c0c3e836551283229bd10b..cfdd1a05fceda8e31776ad02202f1810296673b4 100644 --- a/Documentation/gpu/drm-usage-stats.rst +++ b/Documentation/gpu/drm-usage-stats.rst @@ -73,6 +73,11 @@ scope of each device, in which case `drm-pdev` shall be present as well. Userspace should make sure to not double account any usage statistics by using the above described criteria in order to associate data to individual clients. +- drm-client-name: + +String optionally set by userspace using DRM_IOCTL_SET_CLIENT_NAME. + + Utilization ^^^^^^^^^^^ @@ -186,4 +191,5 @@ Driver specific implementations * :ref:`i915-usage-stats` * :ref:`panfrost-usage-stats` +* :ref:`panthor-usage-stats` * :ref:`xe-usage-stats` diff --git a/Documentation/gpu/panthor.rst b/Documentation/gpu/panthor.rst new file mode 100644 index 0000000000000000000000000000000000000000..3f8979fa2b86edf5ca0dfd179482697c5355169c --- /dev/null +++ b/Documentation/gpu/panthor.rst @@ -0,0 +1,46 @@ +.. SPDX-License-Identifier: GPL-2.0+ + +========================= + drm/Panthor CSF driver +========================= + +.. _panthor-usage-stats: + +Panthor DRM client usage stats implementation +============================================== + +The drm/Panthor driver implements the DRM client usage stats specification as +documented in :ref:`drm-client-usage-stats`. + +Example of the output showing the implemented key value pairs and entirety of +the currently possible format options: + +:: + pos: 0 + flags: 02400002 + mnt_id: 29 + ino: 491 + drm-driver: panthor + drm-client-id: 10 + drm-engine-panthor: 111110952750 ns + drm-cycles-panthor: 94439687187 + drm-maxfreq-panthor: 1000000000 Hz + drm-curfreq-panthor: 1000000000 Hz + drm-total-memory: 16480 KiB + drm-shared-memory: 0 + drm-active-memory: 16200 KiB + drm-resident-memory: 16480 KiB + drm-purgeable-memory: 0 + +Possible `drm-engine-` key names are: `panthor`. +`drm-curfreq-` values convey the current operating frequency for that engine. + +Users must bear in mind that engine and cycle sampling are disabled by default, +because of power saving concerns. `fdinfo` users and benchmark applications which +query the fdinfo file must make sure to toggle the job profiling status of the +driver by writing into the appropriate sysfs node:: + + echo > /sys/bus/platform/drivers/panthor/[a-f0-9]*.gpu/profiling + +Where `N` is a bit mask where cycle and timestamp sampling are respectively +enabled by the first and second bits. diff --git a/Documentation/gpu/todo.rst b/Documentation/gpu/todo.rst index 2b281e3c75a4b2273866057932a7323238c0aa75..256d0d1cb2164bd94f9b610a751b907834d96a21 100644 --- a/Documentation/gpu/todo.rst +++ b/Documentation/gpu/todo.rst @@ -834,6 +834,22 @@ Contact: Javier Martinez Canillas Level: Advanced +Querying errors from drm_syncobj +================================ + +The drm_syncobj container can be used by driver independent code to signal +complection of submission. + +One minor feature still missing is a generic DRM IOCTL to query the error +status of binary and timeline drm_syncobj. + +This should probably be improved by implementing the necessary kernel interface +and adding support for that in the userspace stack. + +Contact: Christian König + +Level: Starter + Outside DRM =========== diff --git a/Documentation/gpu/zynqmp.rst b/Documentation/gpu/zynqmp.rst new file mode 100644 index 0000000000000000000000000000000000000000..f57bfa0ad6ece88ee4a22be1f5df0ae6e257adb9 --- /dev/null +++ b/Documentation/gpu/zynqmp.rst @@ -0,0 +1,149 @@ +.. SPDX-License-Identifier: GPL-2.0+ + +=============================================== +Xilinx ZynqMP Ultrascale+ DisplayPort Subsystem +=============================================== + +This subsystem handles DisplayPort video and audio output on the ZynqMP. It +supports in-memory framebuffers with the DisplayPort DMA controller +(xilinx-dpdma), as well as "live" video and audio from the programmable logic +(PL). This subsystem can perform several transformations, including color space +conversion, alpha blending, and audio mixing, although not all features are +currently supported. + +debugfs +------- + +To support debugging and compliance testing, several test modes can be enabled +though debugfs. The following files in /sys/kernel/debug/dri/X/DP-1/test/ +control the DisplayPort test modes: + +active: + Writing a 1 to this file will activate test mode, and writing a 0 will + deactivate test mode. Writing a 1 or 0 when the test mode is already + active/inactive will re-activate/re-deactivate test mode. When test + mode is inactive, changes made to other files will have no (immediate) + effect, although the settings will be saved for when test mode is + activated. When test mode is active, changes made to other files will + apply immediately. + +custom: + Custom test pattern value + +downspread: + Enable/disable clock downspreading (spread-spectrum clocking) by + writing 1/0 + +enhanced: + Enable/disable enhanced framing + +ignore_aux_errors: + Ignore AUX errors when set to 1. Writes to this file take effect + immediately (regardless of whether test mode is active) and affect all + AUX transfers. + +ignore_hpd: + Ignore hotplug events (such as cable removals or monitor link + retraining requests) when set to 1. Writes to this file take effect + immediately (regardless of whether test mode is active). + +laneX_preemphasis: + Preemphasis from 0 (lowest) to 2 (highest) for lane X + +laneX_swing: + Voltage swing from 0 (lowest) to 3 (highest) for lane X + +lanes: + Number of lanes to use (1, 2, or 4) + +pattern: + Test pattern. May be one of: + + video + Use regular video input + + symbol-error + Symbol error measurement pattern + + prbs7 + Output of the PRBS7 (x^7 + x^6 + 1) polynomial + + 80bit-custom + A custom 80-bit pattern + + cp2520 + HBR2 compliance eye pattern + + tps1 + Link training symbol pattern TPS1 (/D10.2/) + + tps2 + Link training symbol pattern TPS2 + + tps3 + Link training symbol pattern TPS3 (for HBR2) + +rate: + Rate in hertz. One of + + * 5400000000 (HBR2) + * 2700000000 (HBR) + * 1620000000 (RBR) + +You can dump the displayport test settings with the following command:: + + for prop in /sys/kernel/debug/dri/1/DP-1/test/*; do + printf '%-17s ' ${prop##*/} + if [ ${prop##*/} = custom ]; then + hexdump -C $prop | head -1 + else + cat $prop + fi + done + +The output could look something like:: + + active 1 + custom 00000000 00 00 00 00 00 00 00 00 00 00 |..........| + downspread 0 + enhanced 1 + ignore_aux_errors 1 + ignore_hpd 1 + lane0_preemphasis 0 + lane0_swing 3 + lane1_preemphasis 0 + lane1_swing 3 + lanes 2 + pattern prbs7 + rate 1620000000 + +The recommended test procedure is to connect the board to a monitor, +configure test mode, activate test mode, and then disconnect the cable +and connect it to your test equipment of choice. For example, one +sequence of commands could be:: + + echo 1 > /sys/kernel/debug/dri/1/DP-1/test/enhanced + echo tps1 > /sys/kernel/debug/dri/1/DP-1/test/pattern + echo 1620000000 > /sys/kernel/debug/dri/1/DP-1/test/rate + echo 1 > /sys/kernel/debug/dri/1/DP-1/test/ignore_aux_errors + echo 1 > /sys/kernel/debug/dri/1/DP-1/test/ignore_hpd + echo 1 > /sys/kernel/debug/dri/1/DP-1/test/active + +at which point the cable could be disconnected from the monitor. + +Internals +--------- + +.. kernel-doc:: drivers/gpu/drm/xlnx/zynqmp_disp.h + +.. kernel-doc:: drivers/gpu/drm/xlnx/zynqmp_dpsub.h + +.. kernel-doc:: drivers/gpu/drm/xlnx/zynqmp_kms.h + +.. kernel-doc:: drivers/gpu/drm/xlnx/zynqmp_disp.c + +.. kernel-doc:: drivers/gpu/drm/xlnx/zynqmp_dp.c + +.. kernel-doc:: drivers/gpu/drm/xlnx/zynqmp_dpsub.c + +.. kernel-doc:: drivers/gpu/drm/xlnx/zynqmp_kms.c diff --git a/Documentation/networking/napi.rst b/Documentation/networking/napi.rst index 7bf7b95c4f7af346c7291ac2ea43f29e2626142a..dfa5d549be9c03f863669f6396bf28fb6424a9a0 100644 --- a/Documentation/networking/napi.rst +++ b/Documentation/networking/napi.rst @@ -144,9 +144,8 @@ IRQ should only be unmasked after a successful call to napi_complete_done(): napi_schedule_irqoff() is a variant of napi_schedule() which takes advantage of guarantees given by being invoked in IRQ context (no need to -mask interrupts). Note that PREEMPT_RT forces all interrupts -to be threaded so the interrupt may need to be marked ``IRQF_NO_THREAD`` -to avoid issues on real-time kernel configurations. +mask interrupts). napi_schedule_irqoff() will fall back to napi_schedule() if +IRQs are threaded (such as if ``PREEMPT_RT`` is enabled). Instance to queue mapping ------------------------- diff --git a/Documentation/translations/zh_CN/core-api/unaligned-memory-access.rst b/Documentation/translations/zh_CN/core-api/unaligned-memory-access.rst index 29c33e7e0855968a757e5546dc591228c19c6068..fbe0989a8ce57fa0385587087faa484978fce025 100644 --- a/Documentation/translations/zh_CN/core-api/unaligned-memory-access.rst +++ b/Documentation/translations/zh_CN/core-api/unaligned-memory-access.rst @@ -175,7 +175,7 @@ field2会导致非对齐访问，这并不是不合理的。你会期望field2 避免非对齐访问 ============== -避免非对齐访问的最简单方法是使用头文件提供的get_unaligned()和 +避免非对齐访问的最简单方法是使用头文件提供的get_unaligned()和 put_unaligned()宏。 回到前面的一个可能导致非对齐访问的代码例子:: diff --git a/Documentation/wmi/devices/dell-wmi-ddv.rst b/Documentation/wmi/devices/dell-wmi-ddv.rst index 2fcdfcf0332708264f6ce5c7165b801657915a5f..e0c20af309481a35fbc54e7c9d1c19d4c91f4633 100644 --- a/Documentation/wmi/devices/dell-wmi-ddv.rst +++ b/Documentation/wmi/devices/dell-wmi-ddv.rst @@ -8,7 +8,7 @@ Introduction ============ Many Dell notebooks made after ~2020 support a WMI-based interface for -retrieving various system data like battery temperature, ePPID, diagostic data +retrieving various system data like battery temperature, ePPID, diagnostic data and fan/thermal sensor data. This interface is likely used by the `Dell Data Vault` software on Windows, @@ -277,7 +277,7 @@ Reverse-Engineering the DDV WMI interface 4. Try to deduce the meaning of a certain WMI method by comparing the control flow with other ACPI methods (_BIX or _BIF for battery related methods for example). -5. Use the built-in UEFI diagostics to view sensor types/values for fan/thermal +5. Use the built-in UEFI diagnostics to view sensor types/values for fan/thermal related methods (sometimes overwriting static ACPI data fields can be used to test different sensor type values, since on some machines this data is not reinitialized upon a warm reset). diff --git a/MAINTAINERS b/MAINTAINERS index c27f3190737f8b85779bde5489639c8b899f4fd8..a3c87aab42d9785f15e45e7c005bbd8f474bbd2e 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -860,7 +860,7 @@ F: drivers/crypto/allwinner/ ALLWINNER DMIC DRIVERS M: Ban Tao -L: alsa-devel@alsa-project.org (moderated for non-subscribers) +L: linux-sound@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/sound/allwinner,sun50i-h6-dmic.yaml F: sound/soc/sunxi/sun50i-dmic.c @@ -1517,7 +1517,7 @@ F: drivers/iio/gyro/adxrs290.c ANALOG DEVICES INC ASOC CODEC DRIVERS M: Lars-Peter Clausen M: Nuno Sá -L: alsa-devel@alsa-project.org (moderated for non-subscribers) +L: linux-sound@vger.kernel.org S: Supported W: http://wiki.analog.com/ W: https://ez.analog.com/linux-software-drivers @@ -1594,7 +1594,7 @@ F: drivers/rtc/rtc-goldfish.c AOA (Apple Onboard Audio) ALSA DRIVER M: Johannes Berg L: linuxppc-dev@lists.ozlabs.org -L: alsa-devel@alsa-project.org (moderated for non-subscribers) +L: linux-sound@vger.kernel.org S: Maintained F: sound/aoa/ @@ -2091,7 +2091,7 @@ F: drivers/crypto/amlogic/ ARM/Amlogic Meson SoC Sound Drivers M: Jerome Brunet -L: alsa-devel@alsa-project.org (moderated for non-subscribers) +L: linux-sound@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/sound/amlogic* F: sound/soc/meson/ @@ -2129,7 +2129,7 @@ F: drivers/*/*alpine* ARM/APPLE MACHINE SOUND DRIVERS M: Martin Povišer L: asahi@lists.linux.dev -L: alsa-devel@alsa-project.org (moderated for non-subscribers) +L: linux-sound@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/sound/adi,ssm3515.yaml F: Documentation/devicetree/bindings/sound/apple,* @@ -3732,7 +3732,7 @@ F: arch/arm/boot/dts/microchip/at91-tse850-3.dts AXENTIA ASOC DRIVERS M: Peter Rosin -L: alsa-devel@alsa-project.org (moderated for non-subscribers) +L: linux-sound@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/sound/axentia,* F: sound/soc/atmel/tse850-pcm5142.c @@ -4851,7 +4851,7 @@ F: include/uapi/linux/bsg.h BT87X AUDIO DRIVER M: Clemens Ladisch -L: alsa-devel@alsa-project.org (moderated for non-subscribers) +L: linux-sound@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/tiwai/sound.git F: Documentation/sound/cards/bt87x.rst @@ -4913,7 +4913,7 @@ F: drivers/net/can/bxcan.c C-MEDIA CMI8788 DRIVER M: Clemens Ladisch -L: alsa-devel@alsa-project.org (moderated for non-subscribers) +L: linux-sound@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/tiwai/sound.git F: sound/pci/oxygen/ @@ -7097,12 +7097,10 @@ M: Javier Martinez Canillas L: dri-devel@lists.freedesktop.org S: Maintained T: git https://gitlab.freedesktop.org/drm/misc/kernel.git -F: drivers/gpu/drm/drm_aperture.c F: drivers/gpu/drm/tiny/ofdrm.c F: drivers/gpu/drm/tiny/simpledrm.c F: drivers/video/aperture.c F: drivers/video/nomodeset.c -F: include/drm/drm_aperture.h F: include/linux/aperture.h F: include/video/nomodeset.h @@ -7383,6 +7381,18 @@ S: Maintained F: Documentation/devicetree/bindings/display/panel/samsung,s6d7aa0.yaml F: drivers/gpu/drm/panel/panel-samsung-s6d7aa0.c +DRM DRIVER FOR SAMSUNG S6E3HA8 PANELS +M: Dzmitry Sankouski +S: Maintained +F: Documentation/devicetree/bindings/display/panel/samsung,s6e3ha8.yaml +F: drivers/gpu/drm/panel/panel-samsung-s6e3ha8.c + +DRM DRIVER FOR SHARP MEMORY LCD +M: Alex Lanzano +S: Maintained +F: Documentation/devicetree/bindings/display/sharp,ls010b7dh04.yaml +F: drivers/gpu/drm/tiny/sharp-memory.c + DRM DRIVER FOR SITRONIX ST7586 PANELS M: David Lechner S: Maintained @@ -7460,8 +7470,8 @@ T: git https://gitlab.freedesktop.org/drm/misc/kernel.git F: drivers/gpu/drm/udl/ DRM DRIVER FOR VIRTUAL KERNEL MODESETTING (VKMS) -M: Rodrigo Siqueira M: Maíra Canal +M: Louis Chauvet R: Haneen Mohammed R: Simona Vetter R: Melissa Wen @@ -7793,6 +7803,7 @@ F: include/uapi/drm/v3d_drm.h DRM DRIVERS FOR VC4 M: Maxime Ripard M: Dave Stevenson +R: Maíra Canal R: Raspberry Pi Kernel Maintenance S: Supported T: git https://gitlab.freedesktop.org/drm/misc/kernel.git @@ -7827,11 +7838,14 @@ L: dri-devel@lists.freedesktop.org S: Maintained T: git https://gitlab.freedesktop.org/drm/misc/kernel.git F: Documentation/devicetree/bindings/display/xlnx/ +F: Documentation/gpu/zynqmp.rst F: drivers/gpu/drm/xlnx/ DRM GPU SCHEDULER M: Luben Tuikov M: Matthew Brost +M: Danilo Krummrich +M: Philipp Stanner L: dri-devel@lists.freedesktop.org S: Maintained T: git https://gitlab.freedesktop.org/drm/misc/kernel.git @@ -8252,7 +8266,7 @@ F: drivers/edac/ti_edac.c EDIROL UA-101/UA-1000 DRIVER M: Clemens Ladisch -L: alsa-devel@alsa-project.org (moderated for non-subscribers) +L: linux-sound@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/tiwai/sound.git F: sound/usb/misc/ua101.c @@ -8814,7 +8828,7 @@ F: drivers/net/can/usb/f81604.c FIREWIRE AUDIO DRIVERS and IEC 61883-1/6 PACKET STREAMING ENGINE M: Clemens Ladisch M: Takashi Sakamoto -L: alsa-devel@alsa-project.org (moderated for non-subscribers) +L: linux-sound@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/tiwai/sound.git F: include/uapi/sound/firewire.h @@ -8888,7 +8902,7 @@ F: drivers/input/joystick/fsia6b.c FOCUSRITE SCARLETT2 MIXER DRIVER (Scarlett Gen 2+ and Clarett) M: Geoffrey D. Bennett -L: alsa-devel@alsa-project.org (moderated for non-subscribers) +L: linux-sound@vger.kernel.org S: Maintained W: https://github.com/geoffreybennett/scarlett-gen2 B: https://github.com/geoffreybennett/scarlett-gen2/issues @@ -8912,6 +8926,7 @@ F: include/linux/fortify-string.h F: lib/fortify_kunit.c F: lib/memcpy_kunit.c F: lib/test_fortify/* +K: \bunsafe_memcpy\b K: \b__NO_FORTIFY\b FPGA DFL DRIVERS @@ -9209,7 +9224,7 @@ M: Shengjiu Wang M: Xiubo Li R: Fabio Estevam R: Nicolin Chen -L: alsa-devel@alsa-project.org (moderated for non-subscribers) +L: linux-sound@vger.kernel.org L: linuxppc-dev@lists.ozlabs.org S: Maintained F: sound/soc/fsl/fsl* @@ -9219,7 +9234,7 @@ FREESCALE SOC LPC32XX SOUND DRIVERS M: J.M.B. Downing M: Piotr Wojtaszczyk R: Vladimir Zapolskiy -L: alsa-devel@alsa-project.org (moderated for non-subscribers) +L: linux-sound@vger.kernel.org L: linuxppc-dev@lists.ozlabs.org S: Maintained F: Documentation/devicetree/bindings/sound/nxp,lpc3220-i2s.yaml @@ -9227,7 +9242,7 @@ F: sound/soc/fsl/lpc3xxx-* FREESCALE SOC SOUND QMC DRIVER M: Herve Codina -L: alsa-devel@alsa-project.org (moderated for non-subscribers) +L: linux-sound@vger.kernel.org L: linuxppc-dev@lists.ozlabs.org S: Maintained F: Documentation/devicetree/bindings/sound/fsl,qmc-audio.yaml @@ -11154,7 +11169,7 @@ F: drivers/iio/pressure/dps310.c INFINEON PEB2466 ASoC CODEC M: Herve Codina -L: alsa-devel@alsa-project.org (moderated for non-subscribers) +L: linux-sound@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/sound/infineon,peb2466.yaml F: sound/soc/codecs/peb2466.c @@ -11317,7 +11332,7 @@ M: Bard Liao M: Ranjani Sridharan M: Kai Vehmanen R: Pierre-Louis Bossart -L: alsa-devel@alsa-project.org (moderated for non-subscribers) +L: linux-sound@vger.kernel.org S: Supported F: sound/soc/intel/ @@ -11496,7 +11511,7 @@ F: include/uapi/linux/idxd.h INTEL IN FIELD SCAN (IFS) DEVICE M: Jithu Joseph -R: Ashok Raj +R: Ashok Raj R: Tony Luck S: Maintained F: drivers/platform/x86/intel/ifs @@ -12001,7 +12016,7 @@ F: drivers/tty/ipwireless/ IRON DEVICE AUDIO CODEC DRIVERS M: Kiseok Jo -L: alsa-devel@alsa-project.org (moderated for non-subscribers) +L: linux-sound@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/sound/irondevice,* F: sound/soc/codecs/sma* @@ -12343,6 +12358,7 @@ F: include/linux/randomize_kstack.h F: kernel/configs/hardening.config F: lib/usercopy_kunit.c F: mm/usercopy.c +F: security/Kconfig.hardening K: \b(add|choose)_random_kstack_offset\b K: \b__check_(object_size|heap_object)\b K: \b__counted_by\b @@ -12459,7 +12475,7 @@ F: virt/kvm/* KERNEL VIRTUAL MACHINE FOR ARM64 (KVM/arm64) M: Marc Zyngier M: Oliver Upton -R: James Morse +R: Joey Gouly R: Suzuki K Poulose R: Zenghui Yu L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) @@ -13952,7 +13968,7 @@ F: drivers/media/i2c/max96717.c MAX9860 MONO AUDIO VOICE CODEC DRIVER M: Peter Rosin -L: alsa-devel@alsa-project.org (moderated for non-subscribers) +L: linux-sound@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/sound/max9860.txt F: sound/soc/codecs/max9860.* @@ -15085,7 +15101,7 @@ F: drivers/spi/spi-at91-usart.c MICROCHIP AUDIO ASOC DRIVERS M: Claudiu Beznea -L: alsa-devel@alsa-project.org (moderated for non-subscribers) +L: linux-sound@vger.kernel.org S: Supported F: Documentation/devicetree/bindings/sound/atmel* F: Documentation/devicetree/bindings/sound/axentia,tse850-pcm5142.txt @@ -15957,7 +15973,7 @@ F: include/linux/mtd/*nand*.h NATIVE INSTRUMENTS USB SOUND INTERFACE DRIVER M: Daniel Mack -L: alsa-devel@alsa-project.org (moderated for non-subscribers) +L: linux-sound@vger.kernel.org S: Maintained W: http://www.native-instruments.com F: sound/usb/caiaq/ @@ -16728,7 +16744,7 @@ F: drivers/extcon/extcon-ptn5150.c NXP SGTL5000 DRIVER M: Fabio Estevam -L: alsa-devel@alsa-project.org (moderated for non-subscribers) +L: linux-sound@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/sound/fsl,sgtl5000.yaml F: sound/soc/codecs/sgtl5000* @@ -16752,7 +16768,7 @@ K: "nxp,tda998x" NXP TFA9879 DRIVER M: Peter Rosin -L: alsa-devel@alsa-project.org (moderated for non-subscribers) +L: linux-sound@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/sound/nxp,tfa9879.yaml F: sound/soc/codecs/tfa9879* @@ -16764,7 +16780,7 @@ F: drivers/nfc/nxp-nci NXP/Goodix TFA989X (TFA1) DRIVER M: Stephan Gerhold -L: alsa-devel@alsa-project.org (moderated for non-subscribers) +L: linux-sound@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/sound/nxp,tfa989x.yaml F: sound/soc/codecs/tfa989x.c @@ -16850,7 +16866,7 @@ F: include/uapi/misc/ocxl.h OMAP AUDIO SUPPORT M: Peter Ujfalusi M: Jarkko Nikula -L: alsa-devel@alsa-project.org (moderated for non-subscribers) +L: linux-sound@vger.kernel.org L: linux-omap@vger.kernel.org S: Maintained F: sound/soc/ti/n810.c @@ -17407,7 +17423,7 @@ F: include/linux/pm_opp.h OPL4 DRIVER M: Clemens Ladisch -L: alsa-devel@alsa-project.org (moderated for non-subscribers) +L: linux-sound@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/tiwai/sound.git F: sound/drivers/opl4/ @@ -18790,7 +18806,7 @@ F: drivers/crypto/intel/qat/ QCOM AUDIO (ASoC) DRIVERS M: Srinivas Kandagatla -L: alsa-devel@alsa-project.org (moderated for non-subscribers) +L: linux-sound@vger.kernel.org L: linux-arm-msm@vger.kernel.org S: Supported F: Documentation/devicetree/bindings/soc/qcom/qcom,apr* @@ -19652,7 +19668,7 @@ F: drivers/net/ethernet/renesas/rtsn.* RENESAS IDT821034 ASoC CODEC M: Herve Codina -L: alsa-devel@alsa-project.org (moderated for non-subscribers) +L: linux-sound@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/sound/renesas,idt821034.yaml F: sound/soc/codecs/idt821034.c @@ -20403,7 +20419,7 @@ F: security/safesetid/ SAMSUNG AUDIO (ASoC) DRIVERS M: Sylwester Nawrocki -L: alsa-devel@alsa-project.org (moderated for non-subscribers) +L: linux-sound@vger.kernel.org S: Maintained B: mailto:linux-samsung-soc@vger.kernel.org F: Documentation/devicetree/bindings/sound/samsung* @@ -20939,7 +20955,7 @@ F: drivers/media/rc/serial_ir.c SERIAL LOW-POWER INTER-CHIP MEDIA BUS (SLIMbus) M: Srinivas Kandagatla -L: alsa-devel@alsa-project.org (moderated for non-subscribers) +L: linux-sound@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/slimbus/ F: drivers/slimbus/ @@ -21373,7 +21389,7 @@ F: Documentation/devicetree/bindings/i2c/socionext,synquacer-i2c.yaml F: drivers/i2c/busses/i2c-synquacer.c SOCIONEXT UNIPHIER SOUND DRIVER -L: alsa-devel@alsa-project.org (moderated for non-subscribers) +L: linux-sound@vger.kernel.org S: Orphan F: sound/soc/uniphier/ @@ -21632,7 +21648,7 @@ F: tools/testing/selftests/alsa SOUND - COMPRESSED AUDIO M: Vinod Koul -L: alsa-devel@alsa-project.org (moderated for non-subscribers) +L: linux-sound@vger.kernel.org S: Supported T: git git://git.kernel.org/pub/scm/linux/kernel/git/tiwai/sound.git F: Documentation/sound/designs/compress-offload.rst @@ -21695,7 +21711,7 @@ M: Vinod Koul M: Bard Liao R: Pierre-Louis Bossart R: Sanyog Kale -L: alsa-devel@alsa-project.org (moderated for non-subscribers) +L: linux-sound@vger.kernel.org S: Supported T: git git://git.kernel.org/pub/scm/linux/kernel/git/vkoul/soundwire.git F: Documentation/driver-api/soundwire/ @@ -22168,7 +22184,7 @@ F: kernel/static_call.c STI AUDIO (ASoC) DRIVERS M: Arnaud Pouliquen -L: alsa-devel@alsa-project.org (moderated for non-subscribers) +L: linux-sound@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/sound/st,sti-asoc-card.txt F: sound/soc/sti/ @@ -22189,7 +22205,7 @@ F: drivers/media/usb/stk1160/ STM32 AUDIO (ASoC) DRIVERS M: Olivier Moysan M: Arnaud Pouliquen -L: alsa-devel@alsa-project.org (moderated for non-subscribers) +L: linux-sound@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/iio/adc/st,stm32-dfsdm-adc.yaml F: Documentation/devicetree/bindings/sound/st,stm32-*.yaml @@ -22892,7 +22908,7 @@ F: drivers/irqchip/irq-xtensa-* TEXAS INSTRUMENTS ASoC DRIVERS M: Peter Ujfalusi -L: alsa-devel@alsa-project.org (moderated for non-subscribers) +L: linux-sound@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/sound/davinci-mcasp-audio.yaml F: sound/soc/ti/ @@ -22901,7 +22917,7 @@ TEXAS INSTRUMENTS AUDIO (ASoC/HDA) DRIVERS M: Shenghao Ding M: Kevin Lu M: Baojun Xu -L: alsa-devel@alsa-project.org (moderated for non-subscribers) +L: linux-sound@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/sound/tas2552.txt F: Documentation/devicetree/bindings/sound/ti,tas2562.yaml @@ -23269,7 +23285,7 @@ F: drivers/soc/ti/* TI LM49xxx FAMILY ASoC CODEC DRIVERS M: M R Swami Reddy M: Vishwas A Deshpande -L: alsa-devel@alsa-project.org (moderated for non-subscribers) +L: linux-sound@vger.kernel.org S: Maintained F: sound/soc/codecs/isabelle* F: sound/soc/codecs/lm49453* @@ -23284,14 +23300,14 @@ F: drivers/iio/adc/ti-lmp92064.c TI PCM3060 ASoC CODEC DRIVER M: Kirill Marinushkin -L: alsa-devel@alsa-project.org (moderated for non-subscribers) +L: linux-sound@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/sound/pcm3060.txt F: sound/soc/codecs/pcm3060* TI TAS571X FAMILY ASoC CODEC DRIVER M: Kevin Cernekee -L: alsa-devel@alsa-project.org (moderated for non-subscribers) +L: linux-sound@vger.kernel.org S: Odd Fixes F: sound/soc/codecs/tas571x* @@ -23319,7 +23335,7 @@ F: drivers/iio/adc/ti-tsc2046.c TI TWL4030 SERIES SOC CODEC DRIVER M: Peter Ujfalusi -L: alsa-devel@alsa-project.org (moderated for non-subscribers) +L: linux-sound@vger.kernel.org S: Maintained F: sound/soc/codecs/twl4030* @@ -23995,7 +24011,7 @@ F: drivers/usb/storage/ USB MIDI DRIVER M: Clemens Ladisch -L: alsa-devel@alsa-project.org (moderated for non-subscribers) +L: linux-sound@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/tiwai/sound.git F: sound/usb/midi.* @@ -24201,6 +24217,7 @@ F: lib/iov_iter.c USERSPACE DMA BUFFER DRIVER M: Gerd Hoffmann +M: Vivek Kasireddy L: dri-devel@lists.freedesktop.org S: Maintained T: git https://gitlab.freedesktop.org/drm/misc/kernel.git @@ -24655,7 +24672,7 @@ VIRTIO SOUND DRIVER M: Anton Yakovlev M: "Michael S. Tsirkin" L: virtualization@lists.linux.dev -L: alsa-devel@alsa-project.org (moderated for non-subscribers) +L: linux-sound@vger.kernel.org S: Maintained F: include/uapi/linux/virtio_snd.h F: sound/virtio/* @@ -25384,7 +25401,7 @@ F: include/xen/interface/io/usbif.h XEN SOUND FRONTEND DRIVER M: Oleksandr Andrushchenko L: xen-devel@lists.xenproject.org (moderated for non-subscribers) -L: alsa-devel@alsa-project.org (moderated for non-subscribers) +L: linux-sound@vger.kernel.org S: Supported F: sound/xen/* diff --git a/Makefile b/Makefile index 187a4ce2728e9a31d41ce86d6c7d4f037d8270a3..c5493c0c0ca128442b1ba925d874fcb6694eee10 100644 --- a/Makefile +++ b/Makefile @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 12 SUBLEVEL = 0 -EXTRAVERSION = -rc1 +EXTRAVERSION = -rc2 NAME = Baby Opossum Posse # *DOCUMENTATION* @@ -1645,7 +1645,7 @@ help: echo '* dtbs - Build device tree blobs for enabled boards'; \ echo ' dtbs_install - Install dtbs to $(INSTALL_DTBS_PATH)'; \ echo ' dt_binding_check - Validate device tree binding documents and examples'; \ - echo ' dt_binding_schema - Build processed device tree binding schemas'; \ + echo ' dt_binding_schemas - Build processed device tree binding schemas'; \ echo ' dtbs_check - Validate device tree source files';\ echo '') diff --git a/arch/Kconfig b/arch/Kconfig index 98157b38f5cf85e039941e31c164a9f80bf3d3b9..8af374ea1adc245b3aa341314a1dcb51865d03d1 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -838,7 +838,7 @@ config CFI_CLANG config CFI_ICALL_NORMALIZE_INTEGERS bool "Normalize CFI tags for integers" depends on CFI_CLANG - depends on $(cc-option,-fsanitize=kcfi -fsanitize-cfi-icall-experimental-normalize-integers) + depends on HAVE_CFI_ICALL_NORMALIZE_INTEGERS help This option normalizes the CFI tags for integer types so that all integer types of the same size and signedness receive the same CFI @@ -851,6 +851,22 @@ config CFI_ICALL_NORMALIZE_INTEGERS This option is necessary for using CFI with Rust. If unsure, say N. +config HAVE_CFI_ICALL_NORMALIZE_INTEGERS + def_bool !GCOV_KERNEL && !KASAN + depends on CFI_CLANG + depends on $(cc-option,-fsanitize=kcfi -fsanitize-cfi-icall-experimental-normalize-integers) + help + Is CFI_ICALL_NORMALIZE_INTEGERS supported with the set of compilers + currently in use? + + This option defaults to false if GCOV or KASAN is enabled, as there is + an LLVM bug that makes normalized integers tags incompatible with + KASAN and GCOV. Kconfig currently does not have the infrastructure to + detect whether your rustc compiler contains the fix for this bug, so + it is assumed that it doesn't. If your compiler has the fix, you can + explicitly enable this option in your config file. The Kconfig logic + needed to detect this will be added in a future kernel release. + config CFI_PERMISSIVE bool "Use CFI in permissive mode" depends on CFI_CLANG diff --git a/arch/alpha/kernel/traps.c b/arch/alpha/kernel/traps.c index 6afae65e9a8b32c8a7da57c0f2a0a320b6ea60fa..a9a38c80c4a7af92c5504cdfa6f9110b0c34f0a9 100644 --- a/arch/alpha/kernel/traps.c +++ b/arch/alpha/kernel/traps.c @@ -22,7 +22,7 @@ #include #include -#include +#include #include #include #include diff --git a/arch/arc/include/asm/io.h b/arch/arc/include/asm/io.h index 4fdb7350636c32720f394976deecef7e37c71901..f57cb5a6b624038cc371d18f1f228553844e6981 100644 --- a/arch/arc/include/asm/io.h +++ b/arch/arc/include/asm/io.h @@ -9,7 +9,7 @@ #include #include #include -#include +#include #ifdef CONFIG_ISA_ARCV2 #include diff --git a/arch/arc/include/asm/mmu.h b/arch/arc/include/asm/mmu.h index 9febf5bc3de6d0617b3e4b2c0a985231e908963c..4ae2db59d494cb7932f129a349aff16ca967dc3d 100644 --- a/arch/arc/include/asm/mmu.h +++ b/arch/arc/include/asm/mmu.h @@ -14,6 +14,7 @@ typedef struct { unsigned long asid[NR_CPUS]; /* 8 bit MMU PID + Generation cycle */ } mm_context_t; +struct pt_regs; extern void do_tlb_overlap_fault(unsigned long, unsigned long, struct pt_regs *); #endif diff --git a/arch/arc/include/asm/unaligned.h b/arch/arc/include/asm/unaligned.h deleted file mode 100644 index cf5a02382e0e09b135fb04a9b46c21a7c733a40e..0000000000000000000000000000000000000000 --- a/arch/arc/include/asm/unaligned.h +++ /dev/null @@ -1,27 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com) - */ - -#ifndef _ASM_ARC_UNALIGNED_H -#define _ASM_ARC_UNALIGNED_H - -/* ARC700 can't handle unaligned Data accesses. */ - -#include -#include - -#ifdef CONFIG_ARC_EMUL_UNALIGNED -int misaligned_fixup(unsigned long address, struct pt_regs *regs, - struct callee_regs *cregs); -#else -static inline int -misaligned_fixup(unsigned long address, struct pt_regs *regs, - struct callee_regs *cregs) -{ - /* Not fixed */ - return 1; -} -#endif - -#endif /* _ASM_ARC_UNALIGNED_H */ diff --git a/arch/arc/kernel/traps.c b/arch/arc/kernel/traps.c index a19751e824fb4c272e5cfa21ab3349210d30bfa7..8d2ea2cbd98b0f65d688e2dd150af7d2779d7176 100644 --- a/arch/arc/kernel/traps.c +++ b/arch/arc/kernel/traps.c @@ -18,8 +18,9 @@ #include #include #include -#include +#include #include +#include "unaligned.h" void die(const char *str, struct pt_regs *regs, unsigned long address) { diff --git a/arch/arc/kernel/unaligned.c b/arch/arc/kernel/unaligned.c index 99a9b92ed98d629e75783f71eef34f72d84800fd..d2f5ceaaed1b4a3c0ce4fced0aa3f59ffa97b451 100644 --- a/arch/arc/kernel/unaligned.c +++ b/arch/arc/kernel/unaligned.c @@ -12,6 +12,7 @@ #include #include #include +#include "unaligned.h" #ifdef CONFIG_CPU_BIG_ENDIAN #define BE 1 diff --git a/arch/arc/kernel/unaligned.h b/arch/arc/kernel/unaligned.h new file mode 100644 index 0000000000000000000000000000000000000000..5244453bb85f7f1d296b6d75a4ebedfc898cc631 --- /dev/null +++ b/arch/arc/kernel/unaligned.h @@ -0,0 +1,16 @@ +struct pt_regs; +struct callee_regs; + +#ifdef CONFIG_ARC_EMUL_UNALIGNED +int misaligned_fixup(unsigned long address, struct pt_regs *regs, + struct callee_regs *cregs); +#else +static inline int +misaligned_fixup(unsigned long address, struct pt_regs *regs, + struct callee_regs *cregs) +{ + /* Not fixed */ + return 1; +} +#endif + diff --git a/arch/arc/kernel/unwind.c b/arch/arc/kernel/unwind.c index 9270d0a713c31626e8787026472b0a0498545b47..d8969dab12d42d515a3bf53d763d268ca1a16134 100644 --- a/arch/arc/kernel/unwind.c +++ b/arch/arc/kernel/unwind.c @@ -19,7 +19,7 @@ #include #include #include -#include +#include #include extern char __start_unwind[], __end_unwind[]; diff --git a/arch/arm/crypto/aes-ce-glue.c b/arch/arm/crypto/aes-ce-glue.c index f5b66f4cf45d96eac9b2f3658ce8efced7f68008..21df5e7f51f9c96ef66c271c31cc5d1bd9192923 100644 --- a/arch/arm/crypto/aes-ce-glue.c +++ b/arch/arm/crypto/aes-ce-glue.c @@ -8,7 +8,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/arm/crypto/crc32-ce-glue.c b/arch/arm/crypto/crc32-ce-glue.c index 4ff18044af070bf7380b2d4c91b1bd8b650fa2fd..20b4dff13e3a66a6516410322361e68770fae8f5 100644 --- a/arch/arm/crypto/crc32-ce-glue.c +++ b/arch/arm/crypto/crc32-ce-glue.c @@ -18,7 +18,7 @@ #include #include #include -#include +#include #define PMULL_MIN_LEN 64L /* minimum size of buffer * for crc32_pmull_le_16 */ diff --git a/arch/arm/crypto/ghash-ce-glue.c b/arch/arm/crypto/ghash-ce-glue.c index 3ddf05b4234d8e5c6540edf087906507769ac242..3af9970825340d93f9fea29e5cc5783ae7119c8d 100644 --- a/arch/arm/crypto/ghash-ce-glue.c +++ b/arch/arm/crypto/ghash-ce-glue.c @@ -9,7 +9,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/arm/crypto/poly1305-glue.c b/arch/arm/crypto/poly1305-glue.c index 8482e302c45a441e31ed1ea8c47d8f42bd32c24d..4464ffbf8fd168428abd052b3a39f9a77c9595ba 100644 --- a/arch/arm/crypto/poly1305-glue.c +++ b/arch/arm/crypto/poly1305-glue.c @@ -8,7 +8,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/arm/crypto/sha2-ce-glue.c b/arch/arm/crypto/sha2-ce-glue.c index c62ce89dd3e0d886f0aef109790502035256f346..aeac45bfbf9f1f624174dba8fd20c9f8a1b5a8e1 100644 --- a/arch/arm/crypto/sha2-ce-glue.c +++ b/arch/arm/crypto/sha2-ce-glue.c @@ -16,7 +16,7 @@ #include #include #include -#include +#include #include "sha256_glue.h" diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h index 6c9c16d767cfd5df81e5d45c2df23b1454070673..f90be312418e87b53ab99d6059617c121b85825e 100644 --- a/arch/arm/include/asm/uaccess.h +++ b/arch/arm/include/asm/uaccess.h @@ -12,7 +12,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c index f8dd0b3cc8e040cb7cb737e10ae465c11882c913..3c6ddb1afdc463b393447969bfadb77eb99d3483 100644 --- a/arch/arm/mm/alignment.c +++ b/arch/arm/mm/alignment.c @@ -22,7 +22,7 @@ #include #include -#include +#include #include #include "fault.h" diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 3e29b44d2d7bd693c6209383a67b8d0d14345406..fd9df6dcc5937208fe158ac8da9c4ede131d0fc7 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -200,7 +200,8 @@ config ARM64 select HAVE_DMA_CONTIGUOUS select HAVE_DYNAMIC_FTRACE select HAVE_DYNAMIC_FTRACE_WITH_ARGS \ - if $(cc-option,-fpatchable-function-entry=2) + if (GCC_SUPPORTS_DYNAMIC_FTRACE_WITH_ARGS || \ + CLANG_SUPPORTS_DYNAMIC_FTRACE_WITH_ARGS) select HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS \ if DYNAMIC_FTRACE_WITH_ARGS && DYNAMIC_FTRACE_WITH_CALL_OPS select HAVE_DYNAMIC_FTRACE_WITH_CALL_OPS \ @@ -286,12 +287,10 @@ config CLANG_SUPPORTS_DYNAMIC_FTRACE_WITH_ARGS def_bool CC_IS_CLANG # https://github.com/ClangBuiltLinux/linux/issues/1507 depends on AS_IS_GNU || (AS_IS_LLVM && (LD_IS_LLD || LD_VERSION >= 23600)) - select HAVE_DYNAMIC_FTRACE_WITH_ARGS config GCC_SUPPORTS_DYNAMIC_FTRACE_WITH_ARGS def_bool CC_IS_GCC depends on $(cc-option,-fpatchable-function-entry=2) - select HAVE_DYNAMIC_FTRACE_WITH_ARGS config 64BIT def_bool y @@ -1097,6 +1096,7 @@ config ARM64_ERRATUM_3194386 * ARM Cortex-A78C erratum 3324346 * ARM Cortex-A78C erratum 3324347 * ARM Cortex-A710 erratam 3324338 + * ARM Cortex-A715 errartum 3456084 * ARM Cortex-A720 erratum 3456091 * ARM Cortex-A725 erratum 3456106 * ARM Cortex-X1 erratum 3324344 @@ -1107,6 +1107,7 @@ config ARM64_ERRATUM_3194386 * ARM Cortex-X925 erratum 3324334 * ARM Neoverse-N1 erratum 3324349 * ARM Neoverse N2 erratum 3324339 + * ARM Neoverse-N3 erratum 3456111 * ARM Neoverse-V1 erratum 3324341 * ARM Neoverse V2 erratum 3324336 * ARM Neoverse-V3 erratum 3312417 diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index b058c4803efb1c6d97d3e3ae1942abeef26cf330..9efd3f37c2fd9de155019f69cee1a0bb09e9a6dd 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -10,7 +10,7 @@ # # Copyright (C) 1995-2001 by Russell King -LDFLAGS_vmlinux :=--no-undefined -X +LDFLAGS_vmlinux :=--no-undefined -X --pic-veneer ifeq ($(CONFIG_RELOCATABLE), y) # Pass --no-apply-dynamic-relocs to restore pre-binutils-2.27 behaviour diff --git a/arch/arm64/crypto/aes-ce-ccm-glue.c b/arch/arm64/crypto/aes-ce-ccm-glue.c index ce9b28e3c7d63462c02827b177dc22633edb5474..a523b519700f518ef7b7887e4f94be3dcb729e07 100644 --- a/arch/arm64/crypto/aes-ce-ccm-glue.c +++ b/arch/arm64/crypto/aes-ce-ccm-glue.c @@ -9,7 +9,7 @@ */ #include -#include +#include #include #include #include diff --git a/arch/arm64/crypto/aes-ce-glue.c b/arch/arm64/crypto/aes-ce-glue.c index e921823ca103a4e4081282f88a68fb9dfd09b72d..00b8749013c5bf1a08985482597d5768b62eb012 100644 --- a/arch/arm64/crypto/aes-ce-glue.c +++ b/arch/arm64/crypto/aes-ce-glue.c @@ -7,7 +7,7 @@ #include #include -#include +#include #include #include #include diff --git a/arch/arm64/crypto/ghash-ce-glue.c b/arch/arm64/crypto/ghash-ce-glue.c index 97331b454ea8619304d85287d2ea70b9247acc0b..da7b7ec1a664e128bd46b26589a032a32653224b 100644 --- a/arch/arm64/crypto/ghash-ce-glue.c +++ b/arch/arm64/crypto/ghash-ce-glue.c @@ -7,7 +7,7 @@ #include #include -#include +#include #include #include #include diff --git a/arch/arm64/crypto/poly1305-glue.c b/arch/arm64/crypto/poly1305-glue.c index 9c4bfd62e789dc9d6e16ccf09c65e445b0244a7e..18883ea438f3c1ae66dd20dd9f2f661d52c90e54 100644 --- a/arch/arm64/crypto/poly1305-glue.c +++ b/arch/arm64/crypto/poly1305-glue.c @@ -8,7 +8,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/arm64/crypto/sha1-ce-glue.c b/arch/arm64/crypto/sha1-ce-glue.c index 1dd93e1fcb39a276a7be635878986c907d63afaf..cbd14f208f8301a627b36813cace10662f5162f7 100644 --- a/arch/arm64/crypto/sha1-ce-glue.c +++ b/arch/arm64/crypto/sha1-ce-glue.c @@ -7,7 +7,7 @@ #include #include -#include +#include #include #include #include diff --git a/arch/arm64/crypto/sha2-ce-glue.c b/arch/arm64/crypto/sha2-ce-glue.c index 0a44d2e7ee1f7b1d5da894b6229a75c3a3c7bde4..6b4866a88ded1c3701882b40a5a0bf8c1e332013 100644 --- a/arch/arm64/crypto/sha2-ce-glue.c +++ b/arch/arm64/crypto/sha2-ce-glue.c @@ -7,7 +7,7 @@ #include #include -#include +#include #include #include #include diff --git a/arch/arm64/crypto/sha3-ce-glue.c b/arch/arm64/crypto/sha3-ce-glue.c index 250e1377c481b35f76b0ea092348536347af7648..5662c3ac49e91ccdbba250bc7a0835a84621c36e 100644 --- a/arch/arm64/crypto/sha3-ce-glue.c +++ b/arch/arm64/crypto/sha3-ce-glue.c @@ -12,7 +12,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/arm64/crypto/sha512-ce-glue.c b/arch/arm64/crypto/sha512-ce-glue.c index f3431fc6231540724b82b5f0eb8441f4f53b4c61..071f6429322702581176d54bb6dd1f001eb80199 100644 --- a/arch/arm64/crypto/sha512-ce-glue.c +++ b/arch/arm64/crypto/sha512-ce-glue.c @@ -11,7 +11,7 @@ #include #include -#include +#include #include #include #include diff --git a/arch/arm64/crypto/sm3-ce-glue.c b/arch/arm64/crypto/sm3-ce-glue.c index 54bf6ebcfffb1567562af61f188c9bf6ccade166..1a71788c4cda5f35fae85c7da13d133f55912258 100644 --- a/arch/arm64/crypto/sm3-ce-glue.c +++ b/arch/arm64/crypto/sm3-ce-glue.c @@ -7,7 +7,7 @@ #include #include -#include +#include #include #include #include diff --git a/arch/arm64/crypto/sm3-neon-glue.c b/arch/arm64/crypto/sm3-neon-glue.c index 7182ee683f14ace6ea8c23ec9af0ab40fd3db97c..8dd71ce79b69bb937a096496dec66eb8b2b557ec 100644 --- a/arch/arm64/crypto/sm3-neon-glue.c +++ b/arch/arm64/crypto/sm3-neon-glue.c @@ -7,7 +7,7 @@ #include #include -#include +#include #include #include #include diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 5a7dfeb8e8eb55da537605fd841cc50992009509..488f8e75134959f5263a61230dbde5192e8d4a58 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -94,6 +94,7 @@ #define ARM_CPU_PART_NEOVERSE_V3 0xD84 #define ARM_CPU_PART_CORTEX_X925 0xD85 #define ARM_CPU_PART_CORTEX_A725 0xD87 +#define ARM_CPU_PART_NEOVERSE_N3 0xD8E #define APM_CPU_PART_XGENE 0x000 #define APM_CPU_VAR_POTENZA 0x00 @@ -176,6 +177,7 @@ #define MIDR_NEOVERSE_V3 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V3) #define MIDR_CORTEX_X925 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X925) #define MIDR_CORTEX_A725 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A725) +#define MIDR_NEOVERSE_N3 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_N3) #define MIDR_THUNDERX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX) #define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX) #define MIDR_THUNDERX_83XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_83XX) diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 329619c6fa9611b474dc4823fccf01a3b9dd61a8..94cff508874bf238cbc64f65801f3b0169def897 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -1441,11 +1441,6 @@ void kvm_set_vm_id_reg(struct kvm *kvm, u32 reg, u64 val); sign_extend64(__val, id##_##fld##_WIDTH - 1); \ }) -#define expand_field_sign(id, fld, val) \ - (id##_##fld##_SIGNED ? \ - __expand_field_sign_signed(id, fld, val) : \ - __expand_field_sign_unsigned(id, fld, val)) - #define get_idreg_field_unsigned(kvm, id, fld) \ ({ \ u64 __val = kvm_read_vm_id_reg((kvm), SYS_##id); \ @@ -1461,20 +1456,26 @@ void kvm_set_vm_id_reg(struct kvm *kvm, u32 reg, u64 val); #define get_idreg_field_enum(kvm, id, fld) \ get_idreg_field_unsigned(kvm, id, fld) -#define get_idreg_field(kvm, id, fld) \ +#define kvm_cmp_feat_signed(kvm, id, fld, op, limit) \ + (get_idreg_field_signed((kvm), id, fld) op __expand_field_sign_signed(id, fld, limit)) + +#define kvm_cmp_feat_unsigned(kvm, id, fld, op, limit) \ + (get_idreg_field_unsigned((kvm), id, fld) op __expand_field_sign_unsigned(id, fld, limit)) + +#define kvm_cmp_feat(kvm, id, fld, op, limit) \ (id##_##fld##_SIGNED ? \ - get_idreg_field_signed(kvm, id, fld) : \ - get_idreg_field_unsigned(kvm, id, fld)) + kvm_cmp_feat_signed(kvm, id, fld, op, limit) : \ + kvm_cmp_feat_unsigned(kvm, id, fld, op, limit)) #define kvm_has_feat(kvm, id, fld, limit) \ - (get_idreg_field((kvm), id, fld) >= expand_field_sign(id, fld, limit)) + kvm_cmp_feat(kvm, id, fld, >=, limit) #define kvm_has_feat_enum(kvm, id, fld, val) \ - (get_idreg_field_unsigned((kvm), id, fld) == __expand_field_sign_unsigned(id, fld, val)) + kvm_cmp_feat_unsigned(kvm, id, fld, ==, val) #define kvm_has_feat_range(kvm, id, fld, min, max) \ - (get_idreg_field((kvm), id, fld) >= expand_field_sign(id, fld, min) && \ - get_idreg_field((kvm), id, fld) <= expand_field_sign(id, fld, max)) + (kvm_cmp_feat(kvm, id, fld, >=, min) && \ + kvm_cmp_feat(kvm, id, fld, <=, max)) /* Check for a given level of PAuth support */ #define kvm_has_pauth(k, l) \ diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index dfefbdf4073a6a22ced7d89e5a10f56f1bc61b89..a78f247029aec3be4e7dfdc31f9a0d3c4346f49f 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -439,6 +439,7 @@ static const struct midr_range erratum_spec_ssbs_list[] = { MIDR_ALL_VERSIONS(MIDR_CORTEX_A78), MIDR_ALL_VERSIONS(MIDR_CORTEX_A78C), MIDR_ALL_VERSIONS(MIDR_CORTEX_A710), + MIDR_ALL_VERSIONS(MIDR_CORTEX_A715), MIDR_ALL_VERSIONS(MIDR_CORTEX_A720), MIDR_ALL_VERSIONS(MIDR_CORTEX_A725), MIDR_ALL_VERSIONS(MIDR_CORTEX_X1), @@ -447,8 +448,10 @@ static const struct midr_range erratum_spec_ssbs_list[] = { MIDR_ALL_VERSIONS(MIDR_CORTEX_X3), MIDR_ALL_VERSIONS(MIDR_CORTEX_X4), MIDR_ALL_VERSIONS(MIDR_CORTEX_X925), + MIDR_ALL_VERSIONS(MIDR_MICROSOFT_AZURE_COBALT_100), MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N1), MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2), + MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N3), MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V1), MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V2), MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V3), diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index 46d52e8a3df3a3917e33976e0c34f597f8936a6e..5310fe1da6165bcdedfb5ce61bce353e4c9dd58b 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -338,7 +338,7 @@ static inline void __hyp_sve_save_host(void) struct cpu_sve_state *sve_state = *host_data_ptr(sve_state); sve_state->zcr_el1 = read_sysreg_el1(SYS_ZCR); - write_sysreg_s(ZCR_ELx_LEN_MASK, SYS_ZCR_EL2); + write_sysreg_s(sve_vq_from_vl(kvm_host_sve_max_vl) - 1, SYS_ZCR_EL2); __sve_save_state(sve_state->sve_regs + sve_ffr_offset(kvm_host_sve_max_vl), &sve_state->fpsr, true); diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c index 87692b566d90d1e5bcd97b6ebb627f632df57cb7..fefc89209f9e41c95478f6770881eb314a38b4c2 100644 --- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c +++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c @@ -33,7 +33,7 @@ static void __hyp_sve_save_guest(struct kvm_vcpu *vcpu) */ sve_cond_update_zcr_vq(vcpu_sve_max_vq(vcpu) - 1, SYS_ZCR_EL2); __sve_save_state(vcpu_sve_pffr(vcpu), &vcpu->arch.ctxt.fp_regs.fpsr, true); - write_sysreg_s(ZCR_ELx_LEN_MASK, SYS_ZCR_EL2); + write_sysreg_s(sve_vq_from_vl(kvm_host_sve_max_vl) - 1, SYS_ZCR_EL2); } static void __hyp_sve_restore_host(void) @@ -45,10 +45,11 @@ static void __hyp_sve_restore_host(void) * the host. The layout of the data when saving the sve state depends * on the VL, so use a consistent (i.e., the maximum) host VL. * - * Setting ZCR_EL2 to ZCR_ELx_LEN_MASK sets the effective length - * supported by the system (or limited at EL3). + * Note that this constrains the PE to the maximum shared VL + * that was discovered, if we wish to use larger VLs this will + * need to be revisited. */ - write_sysreg_s(ZCR_ELx_LEN_MASK, SYS_ZCR_EL2); + write_sysreg_s(sve_vq_from_vl(kvm_host_sve_max_vl) - 1, SYS_ZCR_EL2); __sve_restore_state(sve_state->sve_regs + sve_ffr_offset(kvm_host_sve_max_vl), &sve_state->fpsr, true); @@ -488,7 +489,8 @@ void handle_trap(struct kvm_cpu_context *host_ctxt) case ESR_ELx_EC_SVE: cpacr_clear_set(0, CPACR_ELx_ZEN); isb(); - sve_cond_update_zcr_vq(ZCR_ELx_LEN_MASK, SYS_ZCR_EL2); + sve_cond_update_zcr_vq(sve_vq_from_vl(kvm_host_sve_max_vl) - 1, + SYS_ZCR_EL2); break; case ESR_ELx_EC_IABT_LOW: case ESR_ELx_EC_DABT_LOW: diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c index 187a5f4d56c0c61c5f46afa39383c5c6a3557e07..077d4098548d2c87abdd3931285d87798d63adb3 100644 --- a/arch/arm64/kvm/hyp/nvhe/pkvm.c +++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c @@ -574,12 +574,14 @@ int __pkvm_init_vcpu(pkvm_handle_t handle, struct kvm_vcpu *host_vcpu, unlock: hyp_spin_unlock(&vm_table_lock); - if (ret) + if (ret) { unmap_donated_memory(hyp_vcpu, sizeof(*hyp_vcpu)); + return ret; + } hyp_vcpu->vcpu.arch.cptr_el2 = kvm_get_reset_cptr_el2(&hyp_vcpu->vcpu); - return ret; + return 0; } static void diff --git a/arch/loongarch/crypto/crc32-loongarch.c b/arch/loongarch/crypto/crc32-loongarch.c index 3eebea3a7b478d0b2e78ac02ac5d2005a3b1a171..b7d9782827f55e543e858b18df3f73222a2f1aa9 100644 --- a/arch/loongarch/crypto/crc32-loongarch.c +++ b/arch/loongarch/crypto/crc32-loongarch.c @@ -13,7 +13,7 @@ #include #include -#include +#include #define _CRC32(crc, value, size, type) \ do { \ diff --git a/arch/microblaze/include/asm/flat.h b/arch/microblaze/include/asm/flat.h index 79a749f4ad04ee4073b336ab0e640a7c3aea72ea..edff4306fa7093f1e0137115b92d74461860115e 100644 --- a/arch/microblaze/include/asm/flat.h +++ b/arch/microblaze/include/asm/flat.h @@ -8,7 +8,7 @@ #ifndef _ASM_MICROBLAZE_FLAT_H #define _ASM_MICROBLAZE_FLAT_H -#include +#include /* * Microblaze works a little differently from other arches, because diff --git a/arch/mips/boot/compressed/decompress.c b/arch/mips/boot/compressed/decompress.c index adb6d5b0e6ebc05f5cb7212d85c6e697cc757ea3..90021c6a8cab5c4c291b0f9596ab99018bbaf20b 100644 --- a/arch/mips/boot/compressed/decompress.c +++ b/arch/mips/boot/compressed/decompress.c @@ -16,7 +16,7 @@ #include #include -#include +#include #include #include "decompress.h" diff --git a/arch/mips/crypto/crc32-mips.c b/arch/mips/crypto/crc32-mips.c index 2a59b85f88aacea20d11e6e8ddcb2b6c8006ebe4..a7a1d43a1b2ca5eb8a582681b22c7949da21ec06 100644 --- a/arch/mips/crypto/crc32-mips.c +++ b/arch/mips/crypto/crc32-mips.c @@ -14,7 +14,7 @@ #include #include #include -#include +#include #include diff --git a/arch/mips/crypto/poly1305-glue.c b/arch/mips/crypto/poly1305-glue.c index 867728ee535af450ef8f260aff10049cf0f60767..c03ad0bbe69cdc5016b0ce7e07631beb048dc393 100644 --- a/arch/mips/crypto/poly1305-glue.c +++ b/arch/mips/crypto/poly1305-glue.c @@ -5,7 +5,7 @@ * Copyright (C) 2019 Linaro Ltd. */ -#include +#include #include #include #include diff --git a/arch/nios2/kernel/misaligned.c b/arch/nios2/kernel/misaligned.c index 23e0544e117cef65f8b771fdd2917ed8995c50e8..2f2862eab3c6d54ccf1a7c62c0d1c3e8d132bd9f 100644 --- a/arch/nios2/kernel/misaligned.c +++ b/arch/nios2/kernel/misaligned.c @@ -23,7 +23,7 @@ #include #include -#include +#include /* instructions we emulate */ #define INST_LDHU 0x0b diff --git a/arch/parisc/boot/compressed/misc.c b/arch/parisc/boot/compressed/misc.c index d389359e22ac6c168538b02a3c55fb04cfa59760..9c83bd06ef1542437d0ac1d416ba67c3b707433a 100644 --- a/arch/parisc/boot/compressed/misc.c +++ b/arch/parisc/boot/compressed/misc.c @@ -6,7 +6,7 @@ #include #include -#include +#include #include #include "sizes.h" diff --git a/arch/parisc/include/asm/unaligned.h b/arch/parisc/include/asm/unaligned.h deleted file mode 100644 index c0621295100d5c1187b91183c854a145c9da1345..0000000000000000000000000000000000000000 --- a/arch/parisc/include/asm/unaligned.h +++ /dev/null @@ -1,11 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ASM_PARISC_UNALIGNED_H -#define _ASM_PARISC_UNALIGNED_H - -#include - -struct pt_regs; -void handle_unaligned(struct pt_regs *regs); -int check_unaligned(struct pt_regs *regs); - -#endif /* _ASM_PARISC_UNALIGNED_H */ diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c index 294b0e026c9a5baed1815d3ff477acb81fd64885..b9b3d527bc9065c659da306049182247f0d338ef 100644 --- a/arch/parisc/kernel/traps.c +++ b/arch/parisc/kernel/traps.c @@ -36,7 +36,7 @@ #include #include #include -#include +#include #include #include #include @@ -47,6 +47,8 @@ #include #include +#include "unaligned.h" + #if defined(CONFIG_LIGHTWEIGHT_SPINLOCK_CHECK) #include #endif diff --git a/arch/parisc/kernel/unaligned.c b/arch/parisc/kernel/unaligned.c index 3e79e40e361d5246a8e9c37337c3df44f6c6c4e6..f4626943633adc33efec55ccd2ac035c9a56e988 100644 --- a/arch/parisc/kernel/unaligned.c +++ b/arch/parisc/kernel/unaligned.c @@ -12,9 +12,10 @@ #include #include #include -#include +#include #include #include +#include "unaligned.h" /* #define DEBUG_UNALIGNED 1 */ diff --git a/arch/parisc/kernel/unaligned.h b/arch/parisc/kernel/unaligned.h new file mode 100644 index 0000000000000000000000000000000000000000..c1aa4b12e284f95862ce771bd4de18932ee2bdaf --- /dev/null +++ b/arch/parisc/kernel/unaligned.h @@ -0,0 +1,3 @@ +struct pt_regs; +void handle_unaligned(struct pt_regs *regs); +int check_unaligned(struct pt_regs *regs); diff --git a/arch/powerpc/crypto/aes-gcm-p10-glue.c b/arch/powerpc/crypto/aes-gcm-p10-glue.c index f62ee54076c06dc738f275da8690a4579d0f0fab..f66ad56e765f041be55571aecfef515c91a09d6b 100644 --- a/arch/powerpc/crypto/aes-gcm-p10-glue.c +++ b/arch/powerpc/crypto/aes-gcm-p10-glue.c @@ -5,7 +5,7 @@ * Copyright 2022- IBM Inc. All rights reserved */ -#include +#include #include #include #include diff --git a/arch/powerpc/crypto/poly1305-p10-glue.c b/arch/powerpc/crypto/poly1305-p10-glue.c index 95dd708573ee4d97574fe3becf7bad307df2e302..369686e9370b445d109596c1d599ac7a1908ff29 100644 --- a/arch/powerpc/crypto/poly1305-p10-glue.c +++ b/arch/powerpc/crypto/poly1305-p10-glue.c @@ -14,7 +14,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/powerpc/kernel/vdso/Makefile b/arch/powerpc/kernel/vdso/Makefile index 56fb1633529a728799e45c3152026cab7c100f4c..31ca5a5470047e7ac0a0f8194fd59c6a3b453b4d 100644 --- a/arch/powerpc/kernel/vdso/Makefile +++ b/arch/powerpc/kernel/vdso/Makefile @@ -22,7 +22,7 @@ endif ifneq ($(c-getrandom-y),) CFLAGS_vgetrandom-32.o += -include $(c-getrandom-y) - CFLAGS_vgetrandom-64.o += -include $(c-getrandom-y) $(call cc-option, -ffixed-r30) + CFLAGS_vgetrandom-64.o += -include $(c-getrandom-y) endif # Build rules diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c index d95e03b3d3e3f358a3c0c0e31b76c4694d5881d6..9e297f88adc5d97d4dc7b267b0bfebd58e5cf193 100644 --- a/arch/powerpc/platforms/pseries/papr_scm.c +++ b/arch/powerpc/platforms/pseries/papr_scm.c @@ -19,7 +19,7 @@ #include #include #include -#include +#include #include #define BIND_ANY_ADDR (~0ul) diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 22dc5ea4196ce19c7f2282c4160f92a02b69a2c7..62545946ecf432df5b41e235ba66438cd3743c06 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -777,8 +777,7 @@ config IRQ_STACKS config THREAD_SIZE_ORDER int "Kernel stack size (in power-of-two numbers of page size)" if VMAP_STACK && EXPERT range 0 4 - default 1 if 32BIT && !KASAN - default 3 if 64BIT && KASAN + default 1 if 32BIT default 2 help Specify the Pages of thread stack size (from 4KB to 64KB), which also diff --git a/arch/riscv/include/asm/thread_info.h b/arch/riscv/include/asm/thread_info.h index ebe52f96da348746159f3a630b82c49a8e45c5df..9c10fb180f43899042bf4b293aa72b630599df09 100644 --- a/arch/riscv/include/asm/thread_info.h +++ b/arch/riscv/include/asm/thread_info.h @@ -13,7 +13,12 @@ #include /* thread information allocation */ -#define THREAD_SIZE_ORDER CONFIG_THREAD_SIZE_ORDER +#ifdef CONFIG_KASAN +#define KASAN_STACK_ORDER 1 +#else +#define KASAN_STACK_ORDER 0 +#endif +#define THREAD_SIZE_ORDER (CONFIG_THREAD_SIZE_ORDER + KASAN_STACK_ORDER) #define THREAD_SIZE (PAGE_SIZE << THREAD_SIZE_ORDER) /* diff --git a/arch/sh/include/asm/flat.h b/arch/sh/include/asm/flat.h index fee4f25555cb53e90463c7cd4e1fbf19a2e383b9..70752c7bc55f2f170562a7e0827b4b269917b945 100644 --- a/arch/sh/include/asm/flat.h +++ b/arch/sh/include/asm/flat.h @@ -9,7 +9,7 @@ #ifndef __ASM_SH_FLAT_H #define __ASM_SH_FLAT_H -#include +#include static inline int flat_get_addr_from_rp(u32 __user *rp, u32 relval, u32 flags, u32 *addr) diff --git a/arch/sh/kernel/dwarf.c b/arch/sh/kernel/dwarf.c index 45c8ae20d10957db4b35c84f27d9ecc4a216f27a..a1b54bedc92935753e624794bca9ab205d0a3402 100644 --- a/arch/sh/kernel/dwarf.c +++ b/arch/sh/kernel/dwarf.c @@ -24,7 +24,7 @@ #include #include #include -#include +#include #include /* Reserve enough memory for two stack frames */ diff --git a/arch/sh/kernel/module.c b/arch/sh/kernel/module.c index b9cee98a754e5129eb067bb9660ea900bd0a969c..a469a80840d3deeda67d4f6c73c1f03793d9828d 100644 --- a/arch/sh/kernel/module.c +++ b/arch/sh/kernel/module.c @@ -18,7 +18,7 @@ #include #include #include -#include +#include #include int apply_relocate_add(Elf32_Shdr *sechdrs, diff --git a/arch/sparc/crypto/crc32c_glue.c b/arch/sparc/crypto/crc32c_glue.c index 688db0dcb97d92d746c3c51c194760bb804bd493..913b9a09e885de313b6afbc68c81f8e0b17e231a 100644 --- a/arch/sparc/crypto/crc32c_glue.c +++ b/arch/sparc/crypto/crc32c_glue.c @@ -20,7 +20,7 @@ #include #include -#include +#include #include "opcodes.h" diff --git a/arch/um/drivers/virt-pci.c b/arch/um/drivers/virt-pci.c index 6100819681b5cb6cbc7deb0509c7b01280035f14..744e7f31e8ef1774c8d6dd24d68e6ee39d7acd6b 100644 --- a/arch/um/drivers/virt-pci.c +++ b/arch/um/drivers/virt-pci.c @@ -14,7 +14,7 @@ #include #include #include -#include +#include #include #define MAX_DEVICES 8 diff --git a/arch/um/include/asm/uaccess.h b/arch/um/include/asm/uaccess.h index 7d9d60e41e4e3977ac87a320c22298f86ffc0a02..1d4b6bbc1b65ceb2a32154cdac20e5efc42fe42f 100644 --- a/arch/um/include/asm/uaccess.h +++ b/arch/um/include/asm/uaccess.h @@ -8,7 +8,7 @@ #define __UM_UACCESS_H #include -#include +#include #define __under_task_size(addr, size) \ (((unsigned long) (addr) < TASK_SIZE) && \ diff --git a/arch/x86/crypto/camellia_glue.c b/arch/x86/crypto/camellia_glue.c index d45e9c0c42acf7b072f08a8d823f194c8a4a8756..f110708c8038c78ebd5a69a4c3de4535ec35f118 100644 --- a/arch/x86/crypto/camellia_glue.c +++ b/arch/x86/crypto/camellia_glue.c @@ -8,7 +8,7 @@ * Copyright (C) 2006 NTT (Nippon Telegraph and Telephone Corporation) */ -#include +#include #include #include #include diff --git a/arch/x86/crypto/ghash-clmulni-intel_glue.c b/arch/x86/crypto/ghash-clmulni-intel_glue.c index 700ecaee9a08aabfdfa6a659db09a471b0f5e119..41bc02e489160cfb99eba0edc10f51794841f32a 100644 --- a/arch/x86/crypto/ghash-clmulni-intel_glue.c +++ b/arch/x86/crypto/ghash-clmulni-intel_glue.c @@ -19,7 +19,7 @@ #include #include #include -#include +#include #define GHASH_BLOCK_SIZE 16 #define GHASH_DIGEST_SIZE 16 diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h index 0152a81d9b4a2e295fe758475aa2f1b7954a6a6c..b4d719de2c845924efc47cebe5536c2f2bbd16c6 100644 --- a/arch/x86/include/asm/ftrace.h +++ b/arch/x86/include/asm/ftrace.h @@ -2,6 +2,8 @@ #ifndef _ASM_X86_FTRACE_H #define _ASM_X86_FTRACE_H +#include + #ifdef CONFIG_FUNCTION_TRACER #ifndef CC_USING_FENTRY # error Compiler does not support fentry? diff --git a/arch/x86/include/asm/reboot.h b/arch/x86/include/asm/reboot.h index c02183d3cdd7e8d5c712fb2d04b3b080ea653f80..ecd58ea9a837b194b62fcba3946e7557c007c996 100644 --- a/arch/x86/include/asm/reboot.h +++ b/arch/x86/include/asm/reboot.h @@ -26,7 +26,7 @@ void __noreturn machine_real_restart(unsigned int type); #define MRR_APM 1 typedef void (cpu_emergency_virt_cb)(void); -#if IS_ENABLED(CONFIG_KVM_INTEL) || IS_ENABLED(CONFIG_KVM_AMD) +#if IS_ENABLED(CONFIG_KVM_X86) void cpu_emergency_register_virt_callback(cpu_emergency_virt_cb *callback); void cpu_emergency_unregister_virt_callback(cpu_emergency_virt_cb *callback); void cpu_emergency_disable_virtualization(void); @@ -34,7 +34,7 @@ void cpu_emergency_disable_virtualization(void); static inline void cpu_emergency_register_virt_callback(cpu_emergency_virt_cb *callback) {} static inline void cpu_emergency_unregister_virt_callback(cpu_emergency_virt_cb *callback) {} static inline void cpu_emergency_disable_virtualization(void) {} -#endif /* CONFIG_KVM_INTEL || CONFIG_KVM_AMD */ +#endif /* CONFIG_KVM_X86 */ typedef void (*nmi_shootdown_cb)(int, struct pt_regs*); void nmi_shootdown_cpus(nmi_shootdown_cb callback); diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 0e0a4cf6b5eb1702d61a94583e69f26a228d1940..615922838c510bdd634f50cfba5f385b18b0c587 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -530,7 +530,7 @@ static inline void kb_wait(void) static inline void nmi_shootdown_cpus_on_restart(void); -#if IS_ENABLED(CONFIG_KVM_INTEL) || IS_ENABLED(CONFIG_KVM_AMD) +#if IS_ENABLED(CONFIG_KVM_X86) /* RCU-protected callback to disable virtualization prior to reboot. */ static cpu_emergency_virt_cb __rcu *cpu_emergency_virt_callback; @@ -600,7 +600,7 @@ static void emergency_reboot_disable_virtualization(void) } #else static void emergency_reboot_disable_virtualization(void) { } -#endif /* CONFIG_KVM_INTEL || CONFIG_KVM_AMD */ +#endif /* CONFIG_KVM_X86 */ void __attribute__((weak)) mach_reboot_fixups(void) { diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index 730c2f34d3479676224d0268a5969002798d98d1..f09f13c01c6bbd28fa37fdf50547abf4403658c9 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -17,8 +17,8 @@ menuconfig VIRTUALIZATION if VIRTUALIZATION -config KVM - tristate "Kernel-based Virtual Machine (KVM) support" +config KVM_X86 + def_tristate KVM if KVM_INTEL || KVM_AMD depends on X86_LOCAL_APIC select KVM_COMMON select KVM_GENERIC_MMU_NOTIFIER @@ -44,7 +44,11 @@ config KVM select HAVE_KVM_PM_NOTIFIER if PM select KVM_GENERIC_HARDWARE_ENABLING select KVM_GENERIC_PRE_FAULT_MEMORY + select KVM_GENERIC_PRIVATE_MEM if KVM_SW_PROTECTED_VM select KVM_WERROR if WERROR + +config KVM + tristate "Kernel-based Virtual Machine (KVM) support" help Support hosting fully virtualized guest machines using hardware virtualization extensions. You will need a fairly recent @@ -77,7 +81,6 @@ config KVM_SW_PROTECTED_VM bool "Enable support for KVM software-protected VMs" depends on EXPERT depends on KVM && X86_64 - select KVM_GENERIC_PRIVATE_MEM help Enable support for KVM software-protected VMs. Currently, software- protected VMs are purely a development and testing vehicle for diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index 5494669a055a6e87c2b70b358cc3166d7fa29509..f9dddb8cb46698a15468bfb6e442803edc811021 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -32,7 +32,7 @@ kvm-intel-y += vmx/vmx_onhyperv.o vmx/hyperv_evmcs.o kvm-amd-y += svm/svm_onhyperv.o endif -obj-$(CONFIG_KVM) += kvm.o +obj-$(CONFIG_KVM_X86) += kvm.o obj-$(CONFIG_KVM_INTEL) += kvm-intel.o obj-$(CONFIG_KVM_AMD) += kvm-amd.o diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index e52f990548df6370a403ac5a19b69fa74caca090..a9a23e058555b92bf12f14ef01557eacb296fe9e 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -1884,10 +1884,14 @@ static bool sp_has_gptes(struct kvm_mmu_page *sp) if (is_obsolete_sp((_kvm), (_sp))) { \ } else -#define for_each_gfn_valid_sp_with_gptes(_kvm, _sp, _gfn) \ +#define for_each_gfn_valid_sp(_kvm, _sp, _gfn) \ for_each_valid_sp(_kvm, _sp, \ &(_kvm)->arch.mmu_page_hash[kvm_page_table_hashfn(_gfn)]) \ - if ((_sp)->gfn != (_gfn) || !sp_has_gptes(_sp)) {} else + if ((_sp)->gfn != (_gfn)) {} else + +#define for_each_gfn_valid_sp_with_gptes(_kvm, _sp, _gfn) \ + for_each_gfn_valid_sp(_kvm, _sp, _gfn) \ + if (!sp_has_gptes(_sp)) {} else static bool kvm_sync_page_check(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) { @@ -7047,14 +7051,42 @@ void kvm_arch_flush_shadow_all(struct kvm *kvm) kvm_mmu_zap_all(kvm); } -/* - * Zapping leaf SPTEs with memslot range when a memslot is moved/deleted. - * - * Zapping non-leaf SPTEs, a.k.a. not-last SPTEs, isn't required, worst - * case scenario we'll have unused shadow pages lying around until they - * are recycled due to age or when the VM is destroyed. - */ -static void kvm_mmu_zap_memslot_leafs(struct kvm *kvm, struct kvm_memory_slot *slot) +static void kvm_mmu_zap_memslot_pages_and_flush(struct kvm *kvm, + struct kvm_memory_slot *slot, + bool flush) +{ + LIST_HEAD(invalid_list); + unsigned long i; + + if (list_empty(&kvm->arch.active_mmu_pages)) + goto out_flush; + + /* + * Since accounting information is stored in struct kvm_arch_memory_slot, + * shadow pages deletion (e.g. unaccount_shadowed()) requires that all + * gfns with a shadow page have a corresponding memslot. Do so before + * the memslot goes away. + */ + for (i = 0; i < slot->npages; i++) { + struct kvm_mmu_page *sp; + gfn_t gfn = slot->base_gfn + i; + + for_each_gfn_valid_sp(kvm, sp, gfn) + kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list); + + if (need_resched() || rwlock_needbreak(&kvm->mmu_lock)) { + kvm_mmu_remote_flush_or_zap(kvm, &invalid_list, flush); + flush = false; + cond_resched_rwlock_write(&kvm->mmu_lock); + } + } + +out_flush: + kvm_mmu_remote_flush_or_zap(kvm, &invalid_list, flush); +} + +static void kvm_mmu_zap_memslot(struct kvm *kvm, + struct kvm_memory_slot *slot) { struct kvm_gfn_range range = { .slot = slot, @@ -7062,11 +7094,11 @@ static void kvm_mmu_zap_memslot_leafs(struct kvm *kvm, struct kvm_memory_slot *s .end = slot->base_gfn + slot->npages, .may_block = true, }; + bool flush; write_lock(&kvm->mmu_lock); - if (kvm_unmap_gfn_range(kvm, &range)) - kvm_flush_remote_tlbs_memslot(kvm, slot); - + flush = kvm_unmap_gfn_range(kvm, &range); + kvm_mmu_zap_memslot_pages_and_flush(kvm, slot, flush); write_unlock(&kvm->mmu_lock); } @@ -7082,7 +7114,7 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm, if (kvm_memslot_flush_zap_all(kvm)) kvm_mmu_zap_all_fast(kvm); else - kvm_mmu_zap_memslot_leafs(kvm, slot); + kvm_mmu_zap_memslot(kvm, slot); } void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen) diff --git a/arch/x86/lib/insn.c b/arch/x86/lib/insn.c index 5952ab41c60f4def412a27f97e287c482b6d3832..6ffb931b9fb14ff87251a60bc61c9639497238c9 100644 --- a/arch/x86/lib/insn.c +++ b/arch/x86/lib/insn.c @@ -13,7 +13,7 @@ #endif #include /*__ignore_sync_check__ */ #include /* __ignore_sync_check__ */ -#include /* __ignore_sync_check__ */ +#include /* __ignore_sync_check__ */ #include #include diff --git a/arch/xtensa/include/asm/flat.h b/arch/xtensa/include/asm/flat.h index ed5870c779f92d940609b811b635d457bece2219..4854419dcd861e120c8f9bec7be9cd134da77f83 100644 --- a/arch/xtensa/include/asm/flat.h +++ b/arch/xtensa/include/asm/flat.h @@ -2,7 +2,7 @@ #ifndef __ASM_XTENSA_FLAT_H #define __ASM_XTENSA_FLAT_H -#include +#include static inline int flat_get_addr_from_rp(u32 __user *rp, u32 relval, u32 flags, u32 *addr) diff --git a/block/blk-integrity.c b/block/blk-integrity.c index 0a2b1c5d0ebf1281f7ab2101b3cc64736530348c..83b696ba0cac3142878668fbde8a603c03853604 100644 --- a/block/blk-integrity.c +++ b/block/blk-integrity.c @@ -56,8 +56,7 @@ new_segment: /** * blk_rq_map_integrity_sg - Map integrity metadata into a scatterlist - * @q: request queue - * @bio: bio with integrity metadata attached + * @rq: request to map * @sglist: target scatterlist * * Description: Map the integrity vectors in request into a diff --git a/block/blk-iocost.c b/block/blk-iocost.c index 9dc9323f84ac1c1f722ef45047189d8215a50ef3..384aa15e8260bd4d83b00f1c03efb87829950327 100644 --- a/block/blk-iocost.c +++ b/block/blk-iocost.c @@ -3166,7 +3166,7 @@ static u64 ioc_qos_prfill(struct seq_file *sf, struct blkg_policy_data *pd, if (!dname) return 0; - spin_lock_irq(&ioc->lock); + spin_lock(&ioc->lock); seq_printf(sf, "%s enable=%d ctrl=%s rpct=%u.%02u rlat=%u wpct=%u.%02u wlat=%u min=%u.%02u max=%u.%02u\n", dname, ioc->enabled, ioc->user_qos_params ? "user" : "auto", ioc->params.qos[QOS_RPPM] / 10000, @@ -3179,7 +3179,7 @@ static u64 ioc_qos_prfill(struct seq_file *sf, struct blkg_policy_data *pd, ioc->params.qos[QOS_MIN] % 10000 / 100, ioc->params.qos[QOS_MAX] / 10000, ioc->params.qos[QOS_MAX] % 10000 / 100); - spin_unlock_irq(&ioc->lock); + spin_unlock(&ioc->lock); return 0; } @@ -3366,14 +3366,14 @@ static u64 ioc_cost_model_prfill(struct seq_file *sf, if (!dname) return 0; - spin_lock_irq(&ioc->lock); + spin_lock(&ioc->lock); seq_printf(sf, "%s ctrl=%s model=linear " "rbps=%llu rseqiops=%llu rrandiops=%llu " "wbps=%llu wseqiops=%llu wrandiops=%llu\n", dname, ioc->user_cost_model ? "user" : "auto", u[I_LCOEF_RBPS], u[I_LCOEF_RSEQIOPS], u[I_LCOEF_RRANDIOPS], u[I_LCOEF_WBPS], u[I_LCOEF_WSEQIOPS], u[I_LCOEF_WRANDIOPS]); - spin_unlock_irq(&ioc->lock); + spin_unlock(&ioc->lock); return 0; } diff --git a/block/partitions/ldm.h b/block/partitions/ldm.h index 0a747a0c782d5d03023fc72d0b7bbda209e0e11f..e259180c89148bdcd0d2ae5c901af8c1e51f8576 100644 --- a/block/partitions/ldm.h +++ b/block/partitions/ldm.h @@ -15,7 +15,7 @@ #include #include #include -#include +#include #include struct parsed_partitions; diff --git a/block/partitions/msdos.c b/block/partitions/msdos.c index b5d5c229cc3b94cb06ab51d30798581326927e75..073be78ba0b0d74323c8b8882c2c298c0f919ea5 100644 --- a/block/partitions/msdos.c +++ b/block/partitions/msdos.c @@ -36,7 +36,7 @@ * the nr_sects and start_sect partition table entries are * at a 2 (mod 4) address. */ -#include +#include static inline sector_t nr_sects(struct msdos_partition *p) { diff --git a/block/t10-pi.c b/block/t10-pi.c index e7052a728966fa58ecaa7668ddb9d2fd024d4e84..2d05421f0fa566f8b7884bec023681d086c78735 100644 --- a/block/t10-pi.c +++ b/block/t10-pi.c @@ -9,7 +9,7 @@ #include #include #include -#include +#include #include "blk.h" struct blk_integrity_iter { diff --git a/crypto/aes_generic.c b/crypto/aes_generic.c index 666474b81c6aa5655fd48eee511cc57203dd1410..3c66d425c97b5d197c021bdb562a0e00cbbf1694 100644 --- a/crypto/aes_generic.c +++ b/crypto/aes_generic.c @@ -54,7 +54,7 @@ #include #include #include -#include +#include static inline u8 byte(const u32 x, const unsigned n) { diff --git a/crypto/blake2b_generic.c b/crypto/blake2b_generic.c index 32e380b714b6ccc1a2b0aa1074f0311e9245fe37..04a712ddfb43092afc36be73629b4e842010db0f 100644 --- a/crypto/blake2b_generic.c +++ b/crypto/blake2b_generic.c @@ -15,7 +15,7 @@ * More information about BLAKE2 can be found at https://blake2.net. */ -#include +#include #include #include #include diff --git a/crypto/blowfish_generic.c b/crypto/blowfish_generic.c index 0e74c7242e77e409ebfa7b71d1759a5f3f10081e..0146bc762c09a4ea5f2c914f46815e2568dae694 100644 --- a/crypto/blowfish_generic.c +++ b/crypto/blowfish_generic.c @@ -16,7 +16,7 @@ #include #include #include -#include +#include #include #include diff --git a/crypto/camellia_generic.c b/crypto/camellia_generic.c index c04670cf51acfb7fe089ccb4005c442c5f8dda6a..197fcf3abc892154f831085a21d10add177e10a9 100644 --- a/crypto/camellia_generic.c +++ b/crypto/camellia_generic.c @@ -15,7 +15,7 @@ #include #include #include -#include +#include static const u32 camellia_sp1110[256] = { 0x70707000, 0x82828200, 0x2c2c2c00, 0xececec00, diff --git a/crypto/cast5_generic.c b/crypto/cast5_generic.c index 085a1eedae03bbfed08ab4b505fb0e5d1be10d7a..f3e57775fa02ead8269e1fbd2be747057e2ef38a 100644 --- a/crypto/cast5_generic.c +++ b/crypto/cast5_generic.c @@ -13,7 +13,7 @@ */ -#include +#include #include #include #include diff --git a/crypto/cast6_generic.c b/crypto/cast6_generic.c index 34f1ab53e3a713ba44a8442b917e95e8f56f7edd..11b725b12f27418c196a047609b465dd46d6114b 100644 --- a/crypto/cast6_generic.c +++ b/crypto/cast6_generic.c @@ -10,7 +10,7 @@ */ -#include +#include #include #include #include diff --git a/crypto/chacha_generic.c b/crypto/chacha_generic.c index 8beea79ab1178298f0c72ad1df8a40a1febae2ec..ba7fcb47f9aa02e7afbd2035922aeabc2d35e7f0 100644 --- a/crypto/chacha_generic.c +++ b/crypto/chacha_generic.c @@ -6,7 +6,7 @@ * Copyright (C) 2018 Google LLC */ -#include +#include #include #include #include diff --git a/crypto/crc32_generic.c b/crypto/crc32_generic.c index a989cb44fd16081c01966071ac8203108f259236..d1251663ed6683561adeeda6b5726b1b3c5485d9 100644 --- a/crypto/crc32_generic.c +++ b/crypto/crc32_generic.c @@ -7,7 +7,7 @@ * This is crypto api shash wrappers to crc32_le. */ -#include +#include #include #include #include diff --git a/crypto/crc32c_generic.c b/crypto/crc32c_generic.c index 7686147385412a42e74dac14101172c69d611b75..a8c90b3f4c6c5580e6d14f315b6130eb6398ed03 100644 --- a/crypto/crc32c_generic.c +++ b/crypto/crc32c_generic.c @@ -30,7 +30,7 @@ * Copyright (c) 2008 Herbert Xu */ -#include +#include #include #include #include diff --git a/crypto/crc64_rocksoft_generic.c b/crypto/crc64_rocksoft_generic.c index 9e812bb26dba6420dde39aab464fc383e6d1387d..ce0f3059b9125a99d4a11c219a076b7aa02f0c40 100644 --- a/crypto/crc64_rocksoft_generic.c +++ b/crypto/crc64_rocksoft_generic.c @@ -3,7 +3,7 @@ #include #include #include -#include +#include static int chksum_init(struct shash_desc *desc) { diff --git a/crypto/ecc.c b/crypto/ecc.c index 420decdad7d94f40bdf4bdf60862c957c810496e..50ad2d4ed672c527ee95c78dba926ca6c7787257 100644 --- a/crypto/ecc.c +++ b/crypto/ecc.c @@ -33,7 +33,7 @@ #include #include #include -#include +#include #include #include "ecc_curve_defs.h" diff --git a/crypto/michael_mic.c b/crypto/michael_mic.c index f4c31049601c9d91d389b627b16c6ba128ecef48..0d14e980d4d6135cdc08a411b4e4bdfca2506730 100644 --- a/crypto/michael_mic.c +++ b/crypto/michael_mic.c @@ -7,7 +7,7 @@ * Copyright (c) 2004 Jouni Malinen */ #include -#include +#include #include #include #include diff --git a/crypto/nhpoly1305.c b/crypto/nhpoly1305.c index 8a3006c3b51b9c5e3324b4591a701e28443afc76..a661d4f667cde54199fd120d196f21d64f5c1dfb 100644 --- a/crypto/nhpoly1305.c +++ b/crypto/nhpoly1305.c @@ -30,7 +30,7 @@ * (https://cr.yp.to/mac/poly1305-20050329.pdf) */ -#include +#include #include #include #include diff --git a/crypto/poly1305_generic.c b/crypto/poly1305_generic.c index 94af47eb6fa699745a7cc6dffaebc10a1b2e455c..e6f29a98725a83979c48fc4493e87185ac647aef 100644 --- a/crypto/poly1305_generic.c +++ b/crypto/poly1305_generic.c @@ -17,7 +17,7 @@ #include #include #include -#include +#include static int crypto_poly1305_init(struct shash_desc *desc) { diff --git a/crypto/polyval-generic.c b/crypto/polyval-generic.c index 16bfa6925b31eb68bd68329130fd3685786399ae..4f98910bcdb589f5c77ab2343a77a2ca8daff9c5 100644 --- a/crypto/polyval-generic.c +++ b/crypto/polyval-generic.c @@ -44,7 +44,7 @@ * */ -#include +#include #include #include #include diff --git a/crypto/serpent_generic.c b/crypto/serpent_generic.c index c6bca47931e21ec86a8196097f05257bb025654e..f6ef187be6fe7a715a994e2c62fb155ee836bcb1 100644 --- a/crypto/serpent_generic.c +++ b/crypto/serpent_generic.c @@ -11,7 +11,7 @@ #include #include #include -#include +#include #include #include diff --git a/crypto/sha256_generic.c b/crypto/sha256_generic.c index bf147b01e313547fba544cf8e99248e5d988098d..b00521f1a6d4555adf5b64ac745a1390b587239c 100644 --- a/crypto/sha256_generic.c +++ b/crypto/sha256_generic.c @@ -15,7 +15,7 @@ #include #include #include -#include +#include const u8 sha224_zero_message_hash[SHA224_DIGEST_SIZE] = { 0xd1, 0x4a, 0x02, 0x8c, 0x2a, 0x3a, 0x2b, 0xc9, 0x47, diff --git a/crypto/sha3_generic.c b/crypto/sha3_generic.c index 3e4069935b53ba513445e062a5dc40c27b646118..b103642b56ea12eed5f3ff8ec38a34a312ec82e3 100644 --- a/crypto/sha3_generic.c +++ b/crypto/sha3_generic.c @@ -13,7 +13,7 @@ #include #include #include -#include +#include /* * On some 32-bit architectures (h8300), GCC ends up using diff --git a/crypto/sha512_generic.c b/crypto/sha512_generic.c index be70e76d6d8623ac5ec58990b024b4c03c78859d..ed81813bd4201331ecab1c1b742f1466a65913ea 100644 --- a/crypto/sha512_generic.c +++ b/crypto/sha512_generic.c @@ -16,7 +16,7 @@ #include #include #include -#include +#include const u8 sha384_zero_message_hash[SHA384_DIGEST_SIZE] = { 0x38, 0xb0, 0x60, 0xa7, 0x51, 0xac, 0x96, 0x38, diff --git a/crypto/sm3.c b/crypto/sm3.c index d473e358a873a82cdabbb322e90ea24a193c0604..18c2fb73ba16e9b120e3375b1f0607a828974545 100644 --- a/crypto/sm3.c +++ b/crypto/sm3.c @@ -9,7 +9,7 @@ */ #include -#include +#include #include static const u32 ____cacheline_aligned K[64] = { diff --git a/crypto/sm3_generic.c b/crypto/sm3_generic.c index a215c1c37e730a08174afe8c697b8ab6e39d3e2c..a2d23a46924eabf68f670b4a27516916e55deb0d 100644 --- a/crypto/sm3_generic.c +++ b/crypto/sm3_generic.c @@ -17,7 +17,7 @@ #include #include #include -#include +#include const u8 sm3_zero_message_hash[SM3_DIGEST_SIZE] = { 0x1A, 0xB2, 0x1D, 0x83, 0x55, 0xCF, 0xA1, 0x7F, diff --git a/crypto/sm4.c b/crypto/sm4.c index 2c44193bc27e4a0369a795ed641a6e32ca33cb6b..f4cd7edc11f0545952a8251b591e8988e59bd517 100644 --- a/crypto/sm4.c +++ b/crypto/sm4.c @@ -8,7 +8,7 @@ */ #include -#include +#include #include static const u32 ____cacheline_aligned fk[4] = { diff --git a/crypto/sm4_generic.c b/crypto/sm4_generic.c index 560eba37dc55eae6e2f9cacb5ec339a71618c0fb..7df86369ac0091b11d0980925935b40749f2612f 100644 --- a/crypto/sm4_generic.c +++ b/crypto/sm4_generic.c @@ -14,7 +14,7 @@ #include #include #include -#include +#include /** * sm4_setkey - Set the SM4 key. diff --git a/crypto/twofish_generic.c b/crypto/twofish_generic.c index 557915e4062d7ca55eb62859cca742a5d46d0bfb..19f2b365e140b2a4c5ab0feb75bc5f01f982f42d 100644 --- a/crypto/twofish_generic.c +++ b/crypto/twofish_generic.c @@ -24,7 +24,7 @@ * Third Edition. */ -#include +#include #include #include #include diff --git a/crypto/vmac.c b/crypto/vmac.c index 0a1d8efa6c1a6f42f368342f7eadef33e1b546a5..bd9d70eac22e00388deacb889b06b69b833101f4 100644 --- a/crypto/vmac.c +++ b/crypto/vmac.c @@ -28,7 +28,7 @@ * Last modified: 17 APR 08, 1700 PDT */ -#include +#include #include #include #include diff --git a/crypto/xxhash_generic.c b/crypto/xxhash_generic.c index 55d1c8a761273e5d2a1a8897ee0c9971820a6957..ac206ad4184df1cd14a398a7e6f4be9639e5520c 100644 --- a/crypto/xxhash_generic.c +++ b/crypto/xxhash_generic.c @@ -4,7 +4,7 @@ #include #include #include -#include +#include #define XXHASH64_BLOCK_SIZE 32 #define XXHASH64_DIGEST_SIZE 8 diff --git a/drivers/accel/ivpu/Kconfig b/drivers/accel/ivpu/Kconfig index 682c532452863e0415d2d6b771e171e79925350c..9e055b5ce03d22b89b79233b55caed24dfd00ead 100644 --- a/drivers/accel/ivpu/Kconfig +++ b/drivers/accel/ivpu/Kconfig @@ -8,6 +8,7 @@ config DRM_ACCEL_IVPU select FW_LOADER select DRM_GEM_SHMEM_HELPER select GENERIC_ALLOCATOR + select WANT_DEV_COREDUMP help Choose this option if you have a system with an 14th generation Intel CPU (Meteor Lake) or newer. Intel NPU (formerly called Intel VPU) @@ -15,3 +16,12 @@ config DRM_ACCEL_IVPU and Deep Learning applications. If "M" is selected, the module will be called intel_vpu. + +config DRM_ACCEL_IVPU_DEBUG + bool "Intel NPU debug mode" + depends on DRM_ACCEL_IVPU + help + Choose this option to enable additional + debug features for the Intel NPU driver: + - Always print debug messages regardless of dyndbg config, + - Enable unsafe module params. diff --git a/drivers/accel/ivpu/Makefile b/drivers/accel/ivpu/Makefile index ebd682a42eb124e0a8dd14f3c0e12953b1c283fb..1029e0bab0615f359ebf5d78c0d4b0b22815a705 100644 --- a/drivers/accel/ivpu/Makefile +++ b/drivers/accel/ivpu/Makefile @@ -16,8 +16,14 @@ intel_vpu-y := \ ivpu_mmu_context.o \ ivpu_ms.o \ ivpu_pm.o \ - ivpu_sysfs.o + ivpu_sysfs.o \ + ivpu_trace_points.o intel_vpu-$(CONFIG_DEBUG_FS) += ivpu_debugfs.o +intel_vpu-$(CONFIG_DEV_COREDUMP) += ivpu_coredump.o obj-$(CONFIG_DRM_ACCEL_IVPU) += intel_vpu.o + +subdir-ccflags-$(CONFIG_DRM_ACCEL_IVPU_DEBUG) += -DDEBUG + +CFLAGS_ivpu_trace_points.o = -I$(src) diff --git a/drivers/accel/ivpu/ivpu_coredump.c b/drivers/accel/ivpu/ivpu_coredump.c new file mode 100644 index 0000000000000000000000000000000000000000..16ad0c30818ccf9d33f303b9d036e3c7592efe5e --- /dev/null +++ b/drivers/accel/ivpu/ivpu_coredump.c @@ -0,0 +1,39 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2020-2024 Intel Corporation + */ + +#include +#include + +#include "ivpu_coredump.h" +#include "ivpu_fw.h" +#include "ivpu_gem.h" +#include "vpu_boot_api.h" + +#define CRASH_DUMP_HEADER "Intel NPU crash dump" +#define CRASH_DUMP_HEADERS_SIZE SZ_4K + +void ivpu_dev_coredump(struct ivpu_device *vdev) +{ + struct drm_print_iterator pi = {}; + struct drm_printer p; + size_t coredump_size; + char *coredump; + + coredump_size = CRASH_DUMP_HEADERS_SIZE + FW_VERSION_HEADER_SIZE + + ivpu_bo_size(vdev->fw->mem_log_crit) + ivpu_bo_size(vdev->fw->mem_log_verb); + coredump = vmalloc(coredump_size); + if (!coredump) + return; + + pi.data = coredump; + pi.remain = coredump_size; + p = drm_coredump_printer(&pi); + + drm_printf(&p, "%s\n", CRASH_DUMP_HEADER); + drm_printf(&p, "FW version: %s\n", vdev->fw->version); + ivpu_fw_log_print(vdev, false, &p); + + dev_coredumpv(vdev->drm.dev, coredump, pi.offset, GFP_KERNEL); +} diff --git a/drivers/accel/ivpu/ivpu_coredump.h b/drivers/accel/ivpu/ivpu_coredump.h new file mode 100644 index 0000000000000000000000000000000000000000..8efb09d024411519f278be32d95bdf4a862eb266 --- /dev/null +++ b/drivers/accel/ivpu/ivpu_coredump.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2020-2024 Intel Corporation + */ + +#ifndef __IVPU_COREDUMP_H__ +#define __IVPU_COREDUMP_H__ + +#include + +#include "ivpu_drv.h" +#include "ivpu_fw_log.h" + +#ifdef CONFIG_DEV_COREDUMP +void ivpu_dev_coredump(struct ivpu_device *vdev); +#else +static inline void ivpu_dev_coredump(struct ivpu_device *vdev) +{ + struct drm_printer p = drm_info_printer(vdev->drm.dev); + + ivpu_fw_log_print(vdev, false, &p); +} +#endif + +#endif /* __IVPU_COREDUMP_H__ */ diff --git a/drivers/accel/ivpu/ivpu_debugfs.c b/drivers/accel/ivpu/ivpu_debugfs.c index 6f86f8df30db0fc263f13a7a4bc98d9e1d3d687b..8958145c49adb628bd52a8f81fc971ef0319c6d7 100644 --- a/drivers/accel/ivpu/ivpu_debugfs.c +++ b/drivers/accel/ivpu/ivpu_debugfs.c @@ -45,6 +45,14 @@ static int fw_name_show(struct seq_file *s, void *v) return 0; } +static int fw_version_show(struct seq_file *s, void *v) +{ + struct ivpu_device *vdev = seq_to_ivpu(s); + + seq_printf(s, "%s\n", vdev->fw->version); + return 0; +} + static int fw_trace_capability_show(struct seq_file *s, void *v) { struct ivpu_device *vdev = seq_to_ivpu(s); @@ -111,6 +119,7 @@ static int reset_pending_show(struct seq_file *s, void *v) static const struct drm_debugfs_info vdev_debugfs_list[] = { {"bo_list", bo_list_show, 0}, {"fw_name", fw_name_show, 0}, + {"fw_version", fw_version_show, 0}, {"fw_trace_capability", fw_trace_capability_show, 0}, {"fw_trace_config", fw_trace_config_show, 0}, {"last_bootmode", last_bootmode_show, 0}, @@ -118,32 +127,23 @@ static const struct drm_debugfs_info vdev_debugfs_list[] = { {"reset_pending", reset_pending_show, 0}, }; -static ssize_t -dvfs_mode_fops_write(struct file *file, const char __user *user_buf, size_t size, loff_t *pos) +static int dvfs_mode_get(void *data, u64 *dvfs_mode) { - struct ivpu_device *vdev = file->private_data; - struct ivpu_fw_info *fw = vdev->fw; - u32 dvfs_mode; - int ret; - - ret = kstrtou32_from_user(user_buf, size, 0, &dvfs_mode); - if (ret < 0) - return ret; + struct ivpu_device *vdev = (struct ivpu_device *)data; - fw->dvfs_mode = dvfs_mode; + *dvfs_mode = vdev->fw->dvfs_mode; + return 0; +} - ret = pci_try_reset_function(to_pci_dev(vdev->drm.dev)); - if (ret) - return ret; +static int dvfs_mode_set(void *data, u64 dvfs_mode) +{ + struct ivpu_device *vdev = (struct ivpu_device *)data; - return size; + vdev->fw->dvfs_mode = (u32)dvfs_mode; + return pci_try_reset_function(to_pci_dev(vdev->drm.dev)); } -static const struct file_operations dvfs_mode_fops = { - .owner = THIS_MODULE, - .open = simple_open, - .write = dvfs_mode_fops_write, -}; +DEFINE_DEBUGFS_ATTRIBUTE(dvfs_mode_fops, dvfs_mode_get, dvfs_mode_set, "%llu\n"); static ssize_t fw_dyndbg_fops_write(struct file *file, const char __user *user_buf, size_t size, loff_t *pos) @@ -192,7 +192,7 @@ fw_log_fops_write(struct file *file, const char __user *user_buf, size_t size, l if (!size) return -EINVAL; - ivpu_fw_log_clear(vdev); + ivpu_fw_log_mark_read(vdev); return size; } @@ -337,49 +337,23 @@ static const struct file_operations ivpu_force_recovery_fops = { .write = ivpu_force_recovery_fn, }; -static ssize_t -ivpu_reset_engine_fn(struct file *file, const char __user *user_buf, size_t size, loff_t *pos) +static int ivpu_reset_engine_fn(void *data, u64 val) { - struct ivpu_device *vdev = file->private_data; - - if (!size) - return -EINVAL; + struct ivpu_device *vdev = (struct ivpu_device *)data; - if (ivpu_jsm_reset_engine(vdev, DRM_IVPU_ENGINE_COMPUTE)) - return -ENODEV; - if (ivpu_jsm_reset_engine(vdev, DRM_IVPU_ENGINE_COPY)) - return -ENODEV; - - return size; + return ivpu_jsm_reset_engine(vdev, (u32)val); } -static const struct file_operations ivpu_reset_engine_fops = { - .owner = THIS_MODULE, - .open = simple_open, - .write = ivpu_reset_engine_fn, -}; +DEFINE_DEBUGFS_ATTRIBUTE(ivpu_reset_engine_fops, NULL, ivpu_reset_engine_fn, "0x%02llx\n"); -static ssize_t -ivpu_resume_engine_fn(struct file *file, const char __user *user_buf, size_t size, loff_t *pos) +static int ivpu_resume_engine_fn(void *data, u64 val) { - struct ivpu_device *vdev = file->private_data; - - if (!size) - return -EINVAL; + struct ivpu_device *vdev = (struct ivpu_device *)data; - if (ivpu_jsm_hws_resume_engine(vdev, DRM_IVPU_ENGINE_COMPUTE)) - return -ENODEV; - if (ivpu_jsm_hws_resume_engine(vdev, DRM_IVPU_ENGINE_COPY)) - return -ENODEV; - - return size; + return ivpu_jsm_hws_resume_engine(vdev, (u32)val); } -static const struct file_operations ivpu_resume_engine_fops = { - .owner = THIS_MODULE, - .open = simple_open, - .write = ivpu_resume_engine_fn, -}; +DEFINE_DEBUGFS_ATTRIBUTE(ivpu_resume_engine_fops, NULL, ivpu_resume_engine_fn, "0x%02llx\n"); static int dct_active_get(void *data, u64 *active_percent) { @@ -423,7 +397,7 @@ void ivpu_debugfs_init(struct ivpu_device *vdev) debugfs_create_file("force_recovery", 0200, debugfs_root, vdev, &ivpu_force_recovery_fops); - debugfs_create_file("dvfs_mode", 0200, debugfs_root, vdev, + debugfs_create_file("dvfs_mode", 0644, debugfs_root, vdev, &dvfs_mode_fops); debugfs_create_file("fw_dyndbg", 0200, debugfs_root, vdev, diff --git a/drivers/accel/ivpu/ivpu_drv.c b/drivers/accel/ivpu/ivpu_drv.c index c91400ecf926513f1529c1a2c3b3e399dc47aa1a..ca2bf47ce2484a8e7ecca0f936e5a3438b22ff81 100644 --- a/drivers/accel/ivpu/ivpu_drv.c +++ b/drivers/accel/ivpu/ivpu_drv.c @@ -7,6 +7,7 @@ #include #include #include +#include #include #include @@ -14,7 +15,7 @@ #include #include -#include "vpu_boot_api.h" +#include "ivpu_coredump.h" #include "ivpu_debugfs.h" #include "ivpu_drv.h" #include "ivpu_fw.h" @@ -29,10 +30,10 @@ #include "ivpu_ms.h" #include "ivpu_pm.h" #include "ivpu_sysfs.h" +#include "vpu_boot_api.h" #ifndef DRIVER_VERSION_STR -#define DRIVER_VERSION_STR __stringify(DRM_IVPU_DRIVER_MAJOR) "." \ - __stringify(DRM_IVPU_DRIVER_MINOR) "." +#define DRIVER_VERSION_STR "1.0.0 " UTS_RELEASE #endif static struct lock_class_key submitted_jobs_xa_lock_class_key; @@ -42,8 +43,10 @@ module_param_named(dbg_mask, ivpu_dbg_mask, int, 0644); MODULE_PARM_DESC(dbg_mask, "Driver debug mask. See IVPU_DBG_* macros."); int ivpu_test_mode; +#if IS_ENABLED(CONFIG_DRM_ACCEL_IVPU_DEBUG) module_param_named_unsafe(test_mode, ivpu_test_mode, int, 0644); MODULE_PARM_DESC(test_mode, "Test mode mask. See IVPU_TEST_MODE_* macros."); +#endif u8 ivpu_pll_min_ratio; module_param_named(pll_min_ratio, ivpu_pll_min_ratio, byte, 0644); @@ -53,9 +56,9 @@ u8 ivpu_pll_max_ratio = U8_MAX; module_param_named(pll_max_ratio, ivpu_pll_max_ratio, byte, 0644); MODULE_PARM_DESC(pll_max_ratio, "Maximum PLL ratio used to set NPU frequency"); -int ivpu_sched_mode; +int ivpu_sched_mode = IVPU_SCHED_MODE_AUTO; module_param_named(sched_mode, ivpu_sched_mode, int, 0444); -MODULE_PARM_DESC(sched_mode, "Scheduler mode: 0 - Default scheduler, 1 - Force HW scheduler"); +MODULE_PARM_DESC(sched_mode, "Scheduler mode: -1 - Use default scheduler, 0 - Use OS scheduler, 1 - Use HW scheduler"); bool ivpu_disable_mmu_cont_pages; module_param_named(disable_mmu_cont_pages, ivpu_disable_mmu_cont_pages, bool, 0444); @@ -85,7 +88,7 @@ static void file_priv_unbind(struct ivpu_device *vdev, struct ivpu_file_priv *fi ivpu_cmdq_release_all_locked(file_priv); ivpu_bo_unbind_all_bos_from_context(vdev, &file_priv->ctx); - ivpu_mmu_user_context_fini(vdev, &file_priv->ctx); + ivpu_mmu_context_fini(vdev, &file_priv->ctx); file_priv->bound = false; drm_WARN_ON(&vdev->drm, !xa_erase_irq(&vdev->context_xa, file_priv->ctx.id)); } @@ -103,6 +106,8 @@ static void file_priv_release(struct kref *ref) pm_runtime_get_sync(vdev->drm.dev); mutex_lock(&vdev->context_list_lock); file_priv_unbind(vdev, file_priv); + drm_WARN_ON(&vdev->drm, !xa_empty(&file_priv->cmdq_xa)); + xa_destroy(&file_priv->cmdq_xa); mutex_unlock(&vdev->context_list_lock); pm_runtime_put_autosuspend(vdev->drm.dev); @@ -116,8 +121,6 @@ void ivpu_file_priv_put(struct ivpu_file_priv **link) struct ivpu_file_priv *file_priv = *link; struct ivpu_device *vdev = file_priv->vdev; - drm_WARN_ON(&vdev->drm, !file_priv); - ivpu_dbg(vdev, KREF, "file_priv put: ctx %u refcount %u\n", file_priv->ctx.id, kref_read(&file_priv->ref)); @@ -255,9 +258,14 @@ static int ivpu_open(struct drm_device *dev, struct drm_file *file) goto err_unlock; } - ret = ivpu_mmu_user_context_init(vdev, &file_priv->ctx, ctx_id); - if (ret) - goto err_xa_erase; + ivpu_mmu_context_init(vdev, &file_priv->ctx, ctx_id); + + file_priv->job_limit.min = FIELD_PREP(IVPU_JOB_ID_CONTEXT_MASK, (file_priv->ctx.id - 1)); + file_priv->job_limit.max = file_priv->job_limit.min | IVPU_JOB_ID_JOB_MASK; + + xa_init_flags(&file_priv->cmdq_xa, XA_FLAGS_ALLOC1); + file_priv->cmdq_limit.min = IVPU_CMDQ_MIN_ID; + file_priv->cmdq_limit.max = IVPU_CMDQ_MAX_ID; mutex_unlock(&vdev->context_list_lock); drm_dev_exit(idx); @@ -269,8 +277,6 @@ static int ivpu_open(struct drm_device *dev, struct drm_file *file) return 0; -err_xa_erase: - xa_erase_irq(&vdev->context_xa, ctx_id); err_unlock: mutex_unlock(&vdev->context_list_lock); mutex_destroy(&file_priv->ms_lock); @@ -346,7 +352,7 @@ static int ivpu_hw_sched_init(struct ivpu_device *vdev) { int ret = 0; - if (vdev->hw->sched_mode == VPU_SCHEDULING_MODE_HW) { + if (vdev->fw->sched_mode == VPU_SCHEDULING_MODE_HW) { ret = ivpu_jsm_hws_setup_priority_bands(vdev); if (ret) { ivpu_err(vdev, "Failed to enable hw scheduler: %d", ret); @@ -380,10 +386,7 @@ int ivpu_boot(struct ivpu_device *vdev) ret = ivpu_wait_for_ready(vdev); if (ret) { ivpu_err(vdev, "Failed to boot the firmware: %d\n", ret); - ivpu_hw_diagnose_failure(vdev); - ivpu_mmu_evtq_dump(vdev); - ivpu_fw_log_dump(vdev); - return ret; + goto err_diagnose_failure; } ivpu_hw_irq_clear(vdev); @@ -394,12 +397,20 @@ int ivpu_boot(struct ivpu_device *vdev) if (ivpu_fw_is_cold_boot(vdev)) { ret = ivpu_pm_dct_init(vdev); if (ret) - return ret; + goto err_diagnose_failure; - return ivpu_hw_sched_init(vdev); + ret = ivpu_hw_sched_init(vdev); + if (ret) + goto err_diagnose_failure; } return 0; + +err_diagnose_failure: + ivpu_hw_diagnose_failure(vdev); + ivpu_mmu_evtq_dump(vdev); + ivpu_dev_coredump(vdev); + return ret; } void ivpu_prepare_for_reset(struct ivpu_device *vdev) @@ -446,9 +457,16 @@ static const struct drm_driver driver = { .name = DRIVER_NAME, .desc = DRIVER_DESC, + +#ifdef DRIVER_DATE .date = DRIVER_DATE, - .major = DRM_IVPU_DRIVER_MAJOR, - .minor = DRM_IVPU_DRIVER_MINOR, + .major = DRIVER_MAJOR, + .minor = DRIVER_MINOR, + .patchlevel = DRIVER_PATCHLEVEL, +#else + .date = UTS_RELEASE, + .major = 1, +#endif }; static void ivpu_context_abort_invalid(struct ivpu_device *vdev) @@ -606,6 +624,9 @@ static int ivpu_dev_init(struct ivpu_device *vdev) lockdep_set_class(&vdev->submitted_jobs_xa.xa_lock, &submitted_jobs_xa_lock_class_key); INIT_LIST_HEAD(&vdev->bo_list); + vdev->db_limit.min = IVPU_MIN_DB; + vdev->db_limit.max = IVPU_MAX_DB; + ret = drmm_mutex_init(&vdev->drm, &vdev->context_list_lock); if (ret) goto err_xa_destroy; @@ -632,9 +653,7 @@ static int ivpu_dev_init(struct ivpu_device *vdev) if (ret) goto err_shutdown; - ret = ivpu_mmu_global_context_init(vdev); - if (ret) - goto err_shutdown; + ivpu_mmu_global_context_init(vdev); ret = ivpu_mmu_init(vdev); if (ret) @@ -722,6 +741,7 @@ static struct pci_device_id ivpu_pci_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_MTL) }, { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_ARL) }, { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_LNL) }, + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_PTL_P) }, { } }; MODULE_DEVICE_TABLE(pci, ivpu_pci_ids); diff --git a/drivers/accel/ivpu/ivpu_drv.h b/drivers/accel/ivpu/ivpu_drv.h index 63f13b697eed719367c57f699041fd7d2b9c8337..3fdff3f6cffd8589c0adf5514075344346b3811a 100644 --- a/drivers/accel/ivpu/ivpu_drv.h +++ b/drivers/accel/ivpu/ivpu_drv.h @@ -21,11 +21,11 @@ #define DRIVER_NAME "intel_vpu" #define DRIVER_DESC "Driver for Intel NPU (Neural Processing Unit)" -#define DRIVER_DATE "20230117" -#define PCI_DEVICE_ID_MTL 0x7d1d -#define PCI_DEVICE_ID_ARL 0xad1d -#define PCI_DEVICE_ID_LNL 0x643e +#define PCI_DEVICE_ID_MTL 0x7d1d +#define PCI_DEVICE_ID_ARL 0xad1d +#define PCI_DEVICE_ID_LNL 0x643e +#define PCI_DEVICE_ID_PTL_P 0xb03e #define IVPU_HW_IP_37XX 37 #define IVPU_HW_IP_40XX 40 @@ -46,17 +46,22 @@ #define IVPU_MIN_DB 1 #define IVPU_MAX_DB 255 -#define IVPU_NUM_ENGINES 2 +#define IVPU_JOB_ID_JOB_MASK GENMASK(7, 0) +#define IVPU_JOB_ID_CONTEXT_MASK GENMASK(31, 8) + #define IVPU_NUM_PRIORITIES 4 -#define IVPU_NUM_CMDQS_PER_CTX (IVPU_NUM_ENGINES * IVPU_NUM_PRIORITIES) +#define IVPU_NUM_CMDQS_PER_CTX (IVPU_NUM_PRIORITIES) -#define IVPU_CMDQ_INDEX(engine, priority) ((engine) * IVPU_NUM_PRIORITIES + (priority)) +#define IVPU_CMDQ_MIN_ID 1 +#define IVPU_CMDQ_MAX_ID 255 #define IVPU_PLATFORM_SILICON 0 #define IVPU_PLATFORM_SIMICS 2 #define IVPU_PLATFORM_FPGA 3 #define IVPU_PLATFORM_INVALID 8 +#define IVPU_SCHED_MODE_AUTO -1 + #define IVPU_DBG_REG BIT(0) #define IVPU_DBG_IRQ BIT(1) #define IVPU_DBG_MMU BIT(2) @@ -134,6 +139,8 @@ struct ivpu_device { struct xa_limit context_xa_limit; struct xarray db_xa; + struct xa_limit db_limit; + u32 db_next; struct mutex bo_list_lock; /* Protects bo_list */ struct list_head bo_list; @@ -152,6 +159,7 @@ struct ivpu_device { int tdr; int autosuspend; int d0i3_entry_msg; + int state_dump_msg; } timeout; }; @@ -163,11 +171,15 @@ struct ivpu_file_priv { struct kref ref; struct ivpu_device *vdev; struct mutex lock; /* Protects cmdq */ - struct ivpu_cmdq *cmdq[IVPU_NUM_CMDQS_PER_CTX]; + struct xarray cmdq_xa; struct ivpu_mmu_context ctx; struct mutex ms_lock; /* Protects ms_instance_list, ms_info_bo */ struct list_head ms_instance_list; struct ivpu_bo *ms_info_bo; + struct xa_limit job_limit; + u32 job_id_next; + struct xa_limit cmdq_limit; + u32 cmdq_id_next; bool has_mmu_faults; bool bound; bool aborted; @@ -185,9 +197,9 @@ extern bool ivpu_force_snoop; #define IVPU_TEST_MODE_NULL_SUBMISSION BIT(2) #define IVPU_TEST_MODE_D0I3_MSG_DISABLE BIT(4) #define IVPU_TEST_MODE_D0I3_MSG_ENABLE BIT(5) -#define IVPU_TEST_MODE_PREEMPTION_DISABLE BIT(6) -#define IVPU_TEST_MODE_HWS_EXTRA_EVENTS BIT(7) +#define IVPU_TEST_MODE_MIP_DISABLE BIT(6) #define IVPU_TEST_MODE_DISABLE_TIMEOUTS BIT(8) +#define IVPU_TEST_MODE_TURBO BIT(9) extern int ivpu_test_mode; struct ivpu_file_priv *ivpu_file_priv_get(struct ivpu_file_priv *file_priv); @@ -215,6 +227,8 @@ static inline int ivpu_hw_ip_gen(struct ivpu_device *vdev) return IVPU_HW_IP_37XX; case PCI_DEVICE_ID_LNL: return IVPU_HW_IP_40XX; + case PCI_DEVICE_ID_PTL_P: + return IVPU_HW_IP_50XX; default: dump_stack(); ivpu_err(vdev, "Unknown NPU IP generation\n"); @@ -229,6 +243,7 @@ static inline int ivpu_hw_btrs_gen(struct ivpu_device *vdev) case PCI_DEVICE_ID_ARL: return IVPU_HW_BTRS_MTL; case PCI_DEVICE_ID_LNL: + case PCI_DEVICE_ID_PTL_P: return IVPU_HW_BTRS_LNL; default: dump_stack(); diff --git a/drivers/accel/ivpu/ivpu_fw.c b/drivers/accel/ivpu/ivpu_fw.c index ede6165e09d90d106c2ab7bbc7c52369d81e6bd3..6037ec0b309689bafaf6d765941dbc2384f78f4d 100644 --- a/drivers/accel/ivpu/ivpu_fw.c +++ b/drivers/accel/ivpu/ivpu_fw.c @@ -25,7 +25,6 @@ #define FW_SHAVE_NN_MAX_SIZE SZ_2M #define FW_RUNTIME_MIN_ADDR (FW_GLOBAL_MEM_START) #define FW_RUNTIME_MAX_ADDR (FW_GLOBAL_MEM_END - FW_SHARED_MEM_SIZE) -#define FW_VERSION_HEADER_SIZE SZ_4K #define FW_FILE_IMAGE_OFFSET (VPU_FW_HEADER_SIZE + FW_VERSION_HEADER_SIZE) #define WATCHDOG_MSS_REDIRECT 32 @@ -47,8 +46,10 @@ #define IVPU_FOCUS_PRESENT_TIMER_MS 1000 static char *ivpu_firmware; +#if IS_ENABLED(CONFIG_DRM_ACCEL_IVPU_DEBUG) module_param_named_unsafe(firmware, ivpu_firmware, charp, 0644); MODULE_PARM_DESC(firmware, "NPU firmware binary in /lib/firmware/.."); +#endif static struct { int gen; @@ -58,11 +59,14 @@ static struct { { IVPU_HW_IP_37XX, "intel/vpu/vpu_37xx_v0.0.bin" }, { IVPU_HW_IP_40XX, "vpu_40xx.bin" }, { IVPU_HW_IP_40XX, "intel/vpu/vpu_40xx_v0.0.bin" }, + { IVPU_HW_IP_50XX, "vpu_50xx.bin" }, + { IVPU_HW_IP_50XX, "intel/vpu/vpu_50xx_v0.0.bin" }, }; /* Production fw_names from the table above */ MODULE_FIRMWARE("intel/vpu/vpu_37xx_v0.0.bin"); MODULE_FIRMWARE("intel/vpu/vpu_40xx_v0.0.bin"); +MODULE_FIRMWARE("intel/vpu/vpu_50xx_v0.0.bin"); static int ivpu_fw_request(struct ivpu_device *vdev) { @@ -135,6 +139,15 @@ static bool is_within_range(u64 addr, size_t size, u64 range_start, size_t range return true; } +static u32 +ivpu_fw_sched_mode_select(struct ivpu_device *vdev, const struct vpu_firmware_header *fw_hdr) +{ + if (ivpu_sched_mode != IVPU_SCHED_MODE_AUTO) + return ivpu_sched_mode; + + return VPU_SCHEDULING_MODE_OS; +} + static int ivpu_fw_parse(struct ivpu_device *vdev) { struct ivpu_fw_info *fw = vdev->fw; @@ -191,8 +204,10 @@ static int ivpu_fw_parse(struct ivpu_device *vdev) ivpu_dbg(vdev, FW_BOOT, "Header version: 0x%x, format 0x%x\n", fw_hdr->header_version, fw_hdr->image_format); - ivpu_info(vdev, "Firmware: %s, version: %s", fw->name, - (const char *)fw_hdr + VPU_FW_HEADER_SIZE); + if (!scnprintf(fw->version, sizeof(fw->version), "%s", fw->file->data + VPU_FW_HEADER_SIZE)) + ivpu_warn(vdev, "Missing firmware version\n"); + + ivpu_info(vdev, "Firmware: %s, version: %s\n", fw->name, fw->version); if (IVPU_FW_CHECK_API_COMPAT(vdev, fw_hdr, BOOT, 3)) return -EINVAL; @@ -208,14 +223,16 @@ static int ivpu_fw_parse(struct ivpu_device *vdev) fw->cold_boot_entry_point = fw_hdr->entry_point; fw->entry_point = fw->cold_boot_entry_point; - fw->trace_level = min_t(u32, ivpu_log_level, IVPU_FW_LOG_FATAL); + fw->trace_level = min_t(u32, ivpu_fw_log_level, IVPU_FW_LOG_FATAL); fw->trace_destination_mask = VPU_TRACE_DESTINATION_VERBOSE_TRACING; fw->trace_hw_component_mask = -1; fw->dvfs_mode = 0; + fw->sched_mode = ivpu_fw_sched_mode_select(vdev, fw_hdr); fw->primary_preempt_buf_size = fw_hdr->preemption_buffer_1_size; fw->secondary_preempt_buf_size = fw_hdr->preemption_buffer_2_size; + ivpu_info(vdev, "Scheduler mode: %s\n", fw->sched_mode ? "HW" : "OS"); if (fw_hdr->ro_section_start_address && !is_within_range(fw_hdr->ro_section_start_address, fw_hdr->ro_section_size, @@ -311,7 +328,7 @@ static int ivpu_fw_mem_init(struct ivpu_device *vdev) goto err_free_fw_mem; } - if (ivpu_log_level <= IVPU_FW_LOG_INFO) + if (ivpu_fw_log_level <= IVPU_FW_LOG_INFO) log_verb_size = IVPU_FW_VERBOSE_BUFFER_LARGE_SIZE; else log_verb_size = IVPU_FW_VERBOSE_BUFFER_SMALL_SIZE; @@ -567,8 +584,10 @@ void ivpu_fw_boot_params_setup(struct ivpu_device *vdev, struct vpu_boot_params boot_params->ipc_payload_area_start = ipc_mem_rx->vpu_addr + ivpu_bo_size(ipc_mem_rx) / 2; boot_params->ipc_payload_area_size = ivpu_bo_size(ipc_mem_rx) / 2; - boot_params->global_aliased_pio_base = vdev->hw->ranges.user.start; - boot_params->global_aliased_pio_size = ivpu_hw_range_size(&vdev->hw->ranges.user); + if (ivpu_hw_ip_gen(vdev) == IVPU_HW_IP_37XX) { + boot_params->global_aliased_pio_base = vdev->hw->ranges.user.start; + boot_params->global_aliased_pio_size = ivpu_hw_range_size(&vdev->hw->ranges.user); + } /* Allow configuration for L2C_PAGE_TABLE with boot param value */ boot_params->autoconfig = 1; @@ -604,8 +623,8 @@ void ivpu_fw_boot_params_setup(struct ivpu_device *vdev, struct vpu_boot_params boot_params->punit_telemetry_sram_base = ivpu_hw_telemetry_offset_get(vdev); boot_params->punit_telemetry_sram_size = ivpu_hw_telemetry_size_get(vdev); boot_params->vpu_telemetry_enable = ivpu_hw_telemetry_enable_get(vdev); - boot_params->vpu_scheduling_mode = vdev->hw->sched_mode; - if (vdev->hw->sched_mode == VPU_SCHEDULING_MODE_HW) + boot_params->vpu_scheduling_mode = vdev->fw->sched_mode; + if (vdev->fw->sched_mode == VPU_SCHEDULING_MODE_HW) boot_params->vpu_focus_present_timer_ms = IVPU_FOCUS_PRESENT_TIMER_MS; boot_params->dvfs_mode = vdev->fw->dvfs_mode; if (!IVPU_WA(disable_d0i3_msg)) diff --git a/drivers/accel/ivpu/ivpu_fw.h b/drivers/accel/ivpu/ivpu_fw.h index 40d9d17be3f528739093b70707581cc35e4211f2..1d0b2bd9d65cf02ac8a6ba2592ae551504135ff4 100644 --- a/drivers/accel/ivpu/ivpu_fw.h +++ b/drivers/accel/ivpu/ivpu_fw.h @@ -1,11 +1,16 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * Copyright (C) 2020-2023 Intel Corporation + * Copyright (C) 2020-2024 Intel Corporation */ #ifndef __IVPU_FW_H__ #define __IVPU_FW_H__ +#include "vpu_jsm_api.h" + +#define FW_VERSION_HEADER_SIZE SZ_4K +#define FW_VERSION_STR_SIZE SZ_256 + struct ivpu_device; struct ivpu_bo; struct vpu_boot_params; @@ -13,6 +18,7 @@ struct vpu_boot_params; struct ivpu_fw_info { const struct firmware *file; const char *name; + char version[FW_VERSION_STR_SIZE]; struct ivpu_bo *mem; struct ivpu_bo *mem_shave_nn; struct ivpu_bo *mem_log_crit; @@ -32,6 +38,7 @@ struct ivpu_fw_info { u32 secondary_preempt_buf_size; u64 read_only_addr; u32 read_only_size; + u32 sched_mode; }; int ivpu_fw_init(struct ivpu_device *vdev); diff --git a/drivers/accel/ivpu/ivpu_fw_log.c b/drivers/accel/ivpu/ivpu_fw_log.c index ef0adb5e0fbeb3416c1f7cbc374200de045405af..337c906b0210720b53a32eb1fa10871415b7f1f9 100644 --- a/drivers/accel/ivpu/ivpu_fw_log.c +++ b/drivers/accel/ivpu/ivpu_fw_log.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Copyright (C) 2020-2023 Intel Corporation + * Copyright (C) 2020-2024 Intel Corporation */ #include @@ -15,19 +15,19 @@ #include "ivpu_fw_log.h" #include "ivpu_gem.h" -#define IVPU_FW_LOG_LINE_LENGTH 256 +#define IVPU_FW_LOG_LINE_LENGTH 256 -unsigned int ivpu_log_level = IVPU_FW_LOG_ERROR; -module_param(ivpu_log_level, uint, 0444); -MODULE_PARM_DESC(ivpu_log_level, - "NPU firmware default trace level: debug=" __stringify(IVPU_FW_LOG_DEBUG) +unsigned int ivpu_fw_log_level = IVPU_FW_LOG_ERROR; +module_param_named(fw_log_level, ivpu_fw_log_level, uint, 0444); +MODULE_PARM_DESC(fw_log_level, + "NPU firmware default log level: debug=" __stringify(IVPU_FW_LOG_DEBUG) " info=" __stringify(IVPU_FW_LOG_INFO) " warn=" __stringify(IVPU_FW_LOG_WARN) " error=" __stringify(IVPU_FW_LOG_ERROR) " fatal=" __stringify(IVPU_FW_LOG_FATAL)); -static int fw_log_ptr(struct ivpu_device *vdev, struct ivpu_bo *bo, u32 *offset, - struct vpu_tracing_buffer_header **log_header) +static int fw_log_from_bo(struct ivpu_device *vdev, struct ivpu_bo *bo, u32 *offset, + struct vpu_tracing_buffer_header **out_log) { struct vpu_tracing_buffer_header *log; @@ -48,7 +48,7 @@ static int fw_log_ptr(struct ivpu_device *vdev, struct ivpu_bo *bo, u32 *offset, return -EINVAL; } - *log_header = log; + *out_log = log; *offset += log->size; ivpu_dbg(vdev, FW_BOOT, @@ -59,7 +59,7 @@ static int fw_log_ptr(struct ivpu_device *vdev, struct ivpu_bo *bo, u32 *offset, return 0; } -static void buffer_print(char *buffer, u32 size, struct drm_printer *p) +static void fw_log_print_lines(char *buffer, u32 size, struct drm_printer *p) { char line[IVPU_FW_LOG_LINE_LENGTH]; u32 index = 0; @@ -87,56 +87,89 @@ static void buffer_print(char *buffer, u32 size, struct drm_printer *p) } line[index] = 0; if (index != 0) - drm_printf(p, "%s\n", line); + drm_printf(p, "%s", line); } -static void fw_log_print_buffer(struct ivpu_device *vdev, struct vpu_tracing_buffer_header *log, - const char *prefix, bool only_new_msgs, struct drm_printer *p) +static void fw_log_print_buffer(struct vpu_tracing_buffer_header *log, const char *prefix, + bool only_new_msgs, struct drm_printer *p) { - char *log_buffer = (void *)log + log->header_size; - u32 log_size = log->size - log->header_size; - u32 log_start = log->read_index; - u32 log_end = log->write_index; - - if (!(log->write_index || log->wrap_count) || - (log->write_index == log->read_index && only_new_msgs)) { - drm_printf(p, "==== %s \"%s\" log empty ====\n", prefix, log->name); - return; + char *log_data = (void *)log + log->header_size; + u32 data_size = log->size - log->header_size; + u32 log_start = only_new_msgs ? READ_ONCE(log->read_index) : 0; + u32 log_end = READ_ONCE(log->write_index); + + if (log->wrap_count == log->read_wrap_count) { + if (log_end <= log_start) { + drm_printf(p, "==== %s \"%s\" log empty ====\n", prefix, log->name); + return; + } + } else if (log->wrap_count == log->read_wrap_count + 1) { + if (log_end > log_start) + log_start = log_end; + } else { + log_start = log_end; } drm_printf(p, "==== %s \"%s\" log start ====\n", prefix, log->name); - if (log->write_index > log->read_index) { - buffer_print(log_buffer + log_start, log_end - log_start, p); + if (log_end > log_start) { + fw_log_print_lines(log_data + log_start, log_end - log_start, p); } else { - buffer_print(log_buffer + log_end, log_size - log_end, p); - buffer_print(log_buffer, log_end, p); + fw_log_print_lines(log_data + log_start, data_size - log_start, p); + fw_log_print_lines(log_data, log_end, p); } - drm_printf(p, "\x1b[0m"); + drm_printf(p, "\n\x1b[0m"); /* add new line and clear formatting */ drm_printf(p, "==== %s \"%s\" log end ====\n", prefix, log->name); } -void ivpu_fw_log_print(struct ivpu_device *vdev, bool only_new_msgs, struct drm_printer *p) +static void +fw_log_print_all_in_bo(struct ivpu_device *vdev, const char *name, + struct ivpu_bo *bo, bool only_new_msgs, struct drm_printer *p) { - struct vpu_tracing_buffer_header *log_header; + struct vpu_tracing_buffer_header *log; u32 next = 0; - while (fw_log_ptr(vdev, vdev->fw->mem_log_crit, &next, &log_header) == 0) - fw_log_print_buffer(vdev, log_header, "NPU critical", only_new_msgs, p); + while (fw_log_from_bo(vdev, bo, &next, &log) == 0) + fw_log_print_buffer(log, name, only_new_msgs, p); +} + +void ivpu_fw_log_print(struct ivpu_device *vdev, bool only_new_msgs, struct drm_printer *p) +{ + fw_log_print_all_in_bo(vdev, "NPU critical", vdev->fw->mem_log_crit, only_new_msgs, p); + fw_log_print_all_in_bo(vdev, "NPU verbose", vdev->fw->mem_log_verb, only_new_msgs, p); +} + +void ivpu_fw_log_mark_read(struct ivpu_device *vdev) +{ + struct vpu_tracing_buffer_header *log; + u32 next; + + next = 0; + while (fw_log_from_bo(vdev, vdev->fw->mem_log_crit, &next, &log) == 0) { + log->read_index = READ_ONCE(log->write_index); + log->read_wrap_count = READ_ONCE(log->wrap_count); + } next = 0; - while (fw_log_ptr(vdev, vdev->fw->mem_log_verb, &next, &log_header) == 0) - fw_log_print_buffer(vdev, log_header, "NPU verbose", only_new_msgs, p); + while (fw_log_from_bo(vdev, vdev->fw->mem_log_verb, &next, &log) == 0) { + log->read_index = READ_ONCE(log->write_index); + log->read_wrap_count = READ_ONCE(log->wrap_count); + } } -void ivpu_fw_log_clear(struct ivpu_device *vdev) +void ivpu_fw_log_reset(struct ivpu_device *vdev) { - struct vpu_tracing_buffer_header *log_header; - u32 next = 0; + struct vpu_tracing_buffer_header *log; + u32 next; - while (fw_log_ptr(vdev, vdev->fw->mem_log_crit, &next, &log_header) == 0) - log_header->read_index = log_header->write_index; + next = 0; + while (fw_log_from_bo(vdev, vdev->fw->mem_log_crit, &next, &log) == 0) { + log->read_index = 0; + log->read_wrap_count = 0; + } next = 0; - while (fw_log_ptr(vdev, vdev->fw->mem_log_verb, &next, &log_header) == 0) - log_header->read_index = log_header->write_index; + while (fw_log_from_bo(vdev, vdev->fw->mem_log_verb, &next, &log) == 0) { + log->read_index = 0; + log->read_wrap_count = 0; + } } diff --git a/drivers/accel/ivpu/ivpu_fw_log.h b/drivers/accel/ivpu/ivpu_fw_log.h index 0b2573f6f315198521416130f2c0a186c94f4365..8bb528a73cb7e52668b37a3a711aabc3075d3592 100644 --- a/drivers/accel/ivpu/ivpu_fw_log.h +++ b/drivers/accel/ivpu/ivpu_fw_log.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * Copyright (C) 2020-2023 Intel Corporation + * Copyright (C) 2020-2024 Intel Corporation */ #ifndef __IVPU_FW_LOG_H__ @@ -8,8 +8,6 @@ #include -#include - #include "ivpu_drv.h" #define IVPU_FW_LOG_DEFAULT 0 @@ -19,20 +17,15 @@ #define IVPU_FW_LOG_ERROR 4 #define IVPU_FW_LOG_FATAL 5 -extern unsigned int ivpu_log_level; - #define IVPU_FW_VERBOSE_BUFFER_SMALL_SIZE SZ_1M #define IVPU_FW_VERBOSE_BUFFER_LARGE_SIZE SZ_8M #define IVPU_FW_CRITICAL_BUFFER_SIZE SZ_512K -void ivpu_fw_log_print(struct ivpu_device *vdev, bool only_new_msgs, struct drm_printer *p); -void ivpu_fw_log_clear(struct ivpu_device *vdev); +extern unsigned int ivpu_fw_log_level; -static inline void ivpu_fw_log_dump(struct ivpu_device *vdev) -{ - struct drm_printer p = drm_info_printer(vdev->drm.dev); +void ivpu_fw_log_print(struct ivpu_device *vdev, bool only_new_msgs, struct drm_printer *p); +void ivpu_fw_log_mark_read(struct ivpu_device *vdev); +void ivpu_fw_log_reset(struct ivpu_device *vdev); - ivpu_fw_log_print(vdev, false, &p); -} #endif /* __IVPU_FW_LOG_H__ */ diff --git a/drivers/accel/ivpu/ivpu_gem.c b/drivers/accel/ivpu/ivpu_gem.c index 1b409dbd332d806ba310ad6e6b2c986cb1fd32b8..d8e97a760fbc0a137fe25cf085f3ff3021f41af8 100644 --- a/drivers/accel/ivpu/ivpu_gem.c +++ b/drivers/accel/ivpu/ivpu_gem.c @@ -384,6 +384,9 @@ int ivpu_bo_wait_ioctl(struct drm_device *dev, void *data, struct drm_file *file timeout = drm_timeout_abs_to_jiffies(args->timeout_ns); + /* Add 1 jiffy to ensure the wait function never times out before intended timeout_ns */ + timeout += 1; + obj = drm_gem_object_lookup(file, args->handle); if (!obj) return -EINVAL; diff --git a/drivers/accel/ivpu/ivpu_hw.c b/drivers/accel/ivpu/ivpu_hw.c index 27f0fe4d54e00628b524d263f817c90075844602..09ada8b500b99661679d38ab099b0617ebeeae89 100644 --- a/drivers/accel/ivpu/ivpu_hw.c +++ b/drivers/accel/ivpu/ivpu_hw.c @@ -89,12 +89,14 @@ static void timeouts_init(struct ivpu_device *vdev) vdev->timeout.tdr = 2000000; vdev->timeout.autosuspend = -1; vdev->timeout.d0i3_entry_msg = 500; + vdev->timeout.state_dump_msg = 10; } else if (ivpu_is_simics(vdev)) { vdev->timeout.boot = 50; vdev->timeout.jsm = 500; vdev->timeout.tdr = 10000; - vdev->timeout.autosuspend = -1; + vdev->timeout.autosuspend = 100; vdev->timeout.d0i3_entry_msg = 100; + vdev->timeout.state_dump_msg = 10; } else { vdev->timeout.boot = 1000; vdev->timeout.jsm = 500; @@ -104,6 +106,7 @@ static void timeouts_init(struct ivpu_device *vdev) else vdev->timeout.autosuspend = 100; vdev->timeout.d0i3_entry_msg = 5; + vdev->timeout.state_dump_msg = 10; } } @@ -111,14 +114,14 @@ static void memory_ranges_init(struct ivpu_device *vdev) { if (ivpu_hw_ip_gen(vdev) == IVPU_HW_IP_37XX) { ivpu_hw_range_init(&vdev->hw->ranges.global, 0x80000000, SZ_512M); - ivpu_hw_range_init(&vdev->hw->ranges.user, 0xc0000000, 255 * SZ_1M); + ivpu_hw_range_init(&vdev->hw->ranges.user, 0x88000000, 511 * SZ_1M); ivpu_hw_range_init(&vdev->hw->ranges.shave, 0x180000000, SZ_2G); - ivpu_hw_range_init(&vdev->hw->ranges.dma, 0x200000000, SZ_8G); + ivpu_hw_range_init(&vdev->hw->ranges.dma, 0x200000000, SZ_128G); } else { ivpu_hw_range_init(&vdev->hw->ranges.global, 0x80000000, SZ_512M); - ivpu_hw_range_init(&vdev->hw->ranges.user, 0x80000000, SZ_256M); - ivpu_hw_range_init(&vdev->hw->ranges.shave, 0x80000000 + SZ_256M, SZ_2G - SZ_256M); - ivpu_hw_range_init(&vdev->hw->ranges.dma, 0x200000000, SZ_8G); + ivpu_hw_range_init(&vdev->hw->ranges.shave, 0x80000000, SZ_2G); + ivpu_hw_range_init(&vdev->hw->ranges.user, 0x100000000, SZ_256G); + vdev->hw->ranges.dma = vdev->hw->ranges.user; } } diff --git a/drivers/accel/ivpu/ivpu_hw.h b/drivers/accel/ivpu/ivpu_hw.h index 1c0c98e3afb88d78fc514989cd8c7ca09d83737b..dc5518248c40514ae8f3594bc7758a396bcad4e8 100644 --- a/drivers/accel/ivpu/ivpu_hw.h +++ b/drivers/accel/ivpu/ivpu_hw.h @@ -46,7 +46,6 @@ struct ivpu_hw_info { u32 profiling_freq; } pll; u32 tile_fuse; - u32 sched_mode; u32 sku; u16 config; int dma_bits; diff --git a/drivers/accel/ivpu/ivpu_hw_40xx_reg.h b/drivers/accel/ivpu/ivpu_hw_40xx_reg.h index d0b795b344c7f7f4211766ee2e33fffa52475686..fc0ee8d637f9689e7d50fe9d9784b11d39c5b9d6 100644 --- a/drivers/accel/ivpu/ivpu_hw_40xx_reg.h +++ b/drivers/accel/ivpu/ivpu_hw_40xx_reg.h @@ -115,6 +115,8 @@ #define VPU_50XX_HOST_SS_AON_PWR_ISLAND_EN_POST_DLY 0x00030068u #define VPU_50XX_HOST_SS_AON_PWR_ISLAND_EN_POST_DLY_POST_DLY_MASK GENMASK(7, 0) +#define VPU_50XX_HOST_SS_AON_PWR_ISLAND_EN_POST_DLY_POST1_DLY_MASK GENMASK(15, 8) +#define VPU_50XX_HOST_SS_AON_PWR_ISLAND_EN_POST_DLY_POST2_DLY_MASK GENMASK(23, 16) #define VPU_50XX_HOST_SS_AON_PWR_ISLAND_STATUS_DLY 0x0003006cu #define VPU_50XX_HOST_SS_AON_PWR_ISLAND_STATUS_DLY_STATUS_DLY_MASK GENMASK(7, 0) diff --git a/drivers/accel/ivpu/ivpu_hw_btrs.c b/drivers/accel/ivpu/ivpu_hw_btrs.c index 745e5248803daf66d652eda98876e825ff922067..3212c99f36823a792e25820eae7ed6fd9ee55bfa 100644 --- a/drivers/accel/ivpu/ivpu_hw_btrs.c +++ b/drivers/accel/ivpu/ivpu_hw_btrs.c @@ -141,16 +141,10 @@ static int read_tile_config_fuse(struct ivpu_device *vdev, u32 *tile_fuse_config } config = REG_GET_FLD(VPU_HW_BTRS_LNL_TILE_FUSE, CONFIG, fuse); - if (!tile_disable_check(config)) { - ivpu_err(vdev, "Fuse: Invalid tile disable config (0x%x)\n", config); - return -EIO; - } + if (!tile_disable_check(config)) + ivpu_warn(vdev, "More than 1 tile disabled, tile fuse config mask: 0x%x\n", config); - if (config) - ivpu_dbg(vdev, MISC, "Fuse: %d tiles enabled. Tile number %d disabled\n", - BTRS_LNL_TILE_MAX_NUM - 1, ffs(config) - 1); - else - ivpu_dbg(vdev, MISC, "Fuse: All %d tiles enabled\n", BTRS_LNL_TILE_MAX_NUM); + ivpu_dbg(vdev, MISC, "Tile disable config mask: 0x%x\n", config); *tile_fuse_config = config; return 0; @@ -163,7 +157,6 @@ static int info_init_mtl(struct ivpu_device *vdev) hw->tile_fuse = BTRS_MTL_TILE_FUSE_ENABLE_BOTH; hw->sku = BTRS_MTL_TILE_SKU_BOTH; hw->config = BTRS_MTL_WP_CONFIG_2_TILE_4_3_RATIO; - hw->sched_mode = ivpu_sched_mode; return 0; } @@ -178,7 +171,6 @@ static int info_init_lnl(struct ivpu_device *vdev) if (ret) return ret; - hw->sched_mode = ivpu_sched_mode; hw->tile_fuse = tile_fuse_config; hw->pll.profiling_freq = PLL_PROFILING_FREQ_DEFAULT; @@ -315,10 +307,6 @@ static void prepare_wp_request(struct ivpu_device *vdev, struct wp_request *wp, wp->cdyn = enable ? PLL_CDYN_DEFAULT : 0; wp->epp = enable ? PLL_EPP_DEFAULT : 0; } - - /* Simics cannot start without at least one tile */ - if (enable && ivpu_is_simics(vdev)) - wp->cfg = 1; } static int wait_for_pll_lock(struct ivpu_device *vdev, bool enable) @@ -465,9 +453,6 @@ int ivpu_hw_btrs_wait_for_clock_res_own_ack(struct ivpu_device *vdev) if (ivpu_hw_btrs_gen(vdev) == IVPU_HW_BTRS_MTL) return 0; - if (ivpu_is_simics(vdev)) - return 0; - return REGB_POLL_FLD(VPU_HW_BTRS_LNL_VPU_STATUS, CLOCK_RESOURCE_OWN_ACK, 1, TIMEOUT_US); } diff --git a/drivers/accel/ivpu/ivpu_hw_ip.c b/drivers/accel/ivpu/ivpu_hw_ip.c index dfd2f4a5b5268583165c101206e749c304e81928..b9b16f404143461db537fb6f0f68d8c3465f6368 100644 --- a/drivers/accel/ivpu/ivpu_hw_ip.c +++ b/drivers/accel/ivpu/ivpu_hw_ip.c @@ -8,15 +8,12 @@ #include "ivpu_hw.h" #include "ivpu_hw_37xx_reg.h" #include "ivpu_hw_40xx_reg.h" +#include "ivpu_hw_btrs.h" #include "ivpu_hw_ip.h" #include "ivpu_hw_reg_io.h" #include "ivpu_mmu.h" #include "ivpu_pm.h" -#define PWR_ISLAND_EN_POST_DLY_FREQ_DEFAULT 0 -#define PWR_ISLAND_EN_POST_DLY_FREQ_HIGH 18 -#define PWR_ISLAND_STATUS_DLY_FREQ_DEFAULT 3 -#define PWR_ISLAND_STATUS_DLY_FREQ_HIGH 46 #define PWR_ISLAND_STATUS_TIMEOUT_US (5 * USEC_PER_MSEC) #define TIM_SAFE_ENABLE 0xf1d0dead @@ -268,20 +265,15 @@ void ivpu_hw_ip_idle_gen_disable(struct ivpu_device *vdev) idle_gen_drive_40xx(vdev, false); } -static void pwr_island_delay_set_50xx(struct ivpu_device *vdev) +static void +pwr_island_delay_set_50xx(struct ivpu_device *vdev, u32 post, u32 post1, u32 post2, u32 status) { - u32 val, post, status; - - if (vdev->hw->pll.profiling_freq == PLL_PROFILING_FREQ_DEFAULT) { - post = PWR_ISLAND_EN_POST_DLY_FREQ_DEFAULT; - status = PWR_ISLAND_STATUS_DLY_FREQ_DEFAULT; - } else { - post = PWR_ISLAND_EN_POST_DLY_FREQ_HIGH; - status = PWR_ISLAND_STATUS_DLY_FREQ_HIGH; - } + u32 val; val = REGV_RD32(VPU_50XX_HOST_SS_AON_PWR_ISLAND_EN_POST_DLY); val = REG_SET_FLD_NUM(VPU_50XX_HOST_SS_AON_PWR_ISLAND_EN_POST_DLY, POST_DLY, post, val); + val = REG_SET_FLD_NUM(VPU_50XX_HOST_SS_AON_PWR_ISLAND_EN_POST_DLY, POST1_DLY, post1, val); + val = REG_SET_FLD_NUM(VPU_50XX_HOST_SS_AON_PWR_ISLAND_EN_POST_DLY, POST2_DLY, post2, val); REGV_WR32(VPU_50XX_HOST_SS_AON_PWR_ISLAND_EN_POST_DLY, val); val = REGV_RD32(VPU_50XX_HOST_SS_AON_PWR_ISLAND_STATUS_DLY); @@ -311,9 +303,6 @@ static void pwr_island_trickle_drive_40xx(struct ivpu_device *vdev, bool enable) val = REG_CLR_FLD(VPU_40XX_HOST_SS_AON_PWR_ISLAND_TRICKLE_EN0, CSS_CPU, val); REGV_WR32(VPU_40XX_HOST_SS_AON_PWR_ISLAND_TRICKLE_EN0, val); - - if (enable) - ndelay(500); } static void pwr_island_drive_37xx(struct ivpu_device *vdev, bool enable) @@ -326,9 +315,6 @@ static void pwr_island_drive_37xx(struct ivpu_device *vdev, bool enable) val = REG_CLR_FLD(VPU_40XX_HOST_SS_AON_PWR_ISLAND_EN0, CSS_CPU, val); REGV_WR32(VPU_40XX_HOST_SS_AON_PWR_ISLAND_EN0, val); - - if (!enable) - ndelay(500); } static void pwr_island_drive_40xx(struct ivpu_device *vdev, bool enable) @@ -347,9 +333,11 @@ static void pwr_island_enable(struct ivpu_device *vdev) { if (ivpu_hw_ip_gen(vdev) == IVPU_HW_IP_37XX) { pwr_island_trickle_drive_37xx(vdev, true); + ndelay(500); pwr_island_drive_37xx(vdev, true); } else { pwr_island_trickle_drive_40xx(vdev, true); + ndelay(500); pwr_island_drive_40xx(vdev, true); } } @@ -686,13 +674,36 @@ static void dpu_active_drive_37xx(struct ivpu_device *vdev, bool enable) REGV_WR32(VPU_37XX_HOST_SS_AON_DPU_ACTIVE, val); } +static void pwr_island_delay_set(struct ivpu_device *vdev) +{ + bool high = vdev->hw->pll.profiling_freq == PLL_PROFILING_FREQ_HIGH; + u32 post, post1, post2, status; + + if (ivpu_hw_ip_gen(vdev) < IVPU_HW_IP_50XX) + return; + + switch (ivpu_device_id(vdev)) { + case PCI_DEVICE_ID_PTL_P: + post = high ? 18 : 0; + post1 = 0; + post2 = 0; + status = high ? 46 : 3; + break; + + default: + dump_stack(); + ivpu_err(vdev, "Unknown device ID\n"); + return; + } + + pwr_island_delay_set_50xx(vdev, post, post1, post2, status); +} + int ivpu_hw_ip_pwr_domain_enable(struct ivpu_device *vdev) { int ret; - if (ivpu_hw_ip_gen(vdev) == IVPU_HW_IP_50XX) - pwr_island_delay_set_50xx(vdev); - + pwr_island_delay_set(vdev); pwr_island_enable(vdev); ret = wait_for_pwr_island_status(vdev, 0x1); diff --git a/drivers/accel/ivpu/ivpu_ipc.c b/drivers/accel/ivpu/ivpu_ipc.c index 78b32a8232419eccf8fa50a931d1874f93d0dff2..01ebf88fe6ef0a97bb027fa2d6e38f5142155fa1 100644 --- a/drivers/accel/ivpu/ivpu_ipc.c +++ b/drivers/accel/ivpu/ivpu_ipc.c @@ -15,6 +15,7 @@ #include "ivpu_ipc.h" #include "ivpu_jsm_msg.h" #include "ivpu_pm.h" +#include "ivpu_trace.h" #define IPC_MAX_RX_MSG 128 @@ -227,6 +228,7 @@ int ivpu_ipc_send(struct ivpu_device *vdev, struct ivpu_ipc_consumer *cons, stru goto unlock; ivpu_ipc_tx(vdev, cons->tx_vpu_addr); + trace_jsm("[tx]", req); unlock: mutex_unlock(&ipc->lock); @@ -278,12 +280,13 @@ int ivpu_ipc_receive(struct ivpu_device *vdev, struct ivpu_ipc_consumer *cons, u32 size = min_t(int, rx_msg->ipc_hdr->data_size, sizeof(*jsm_msg)); if (rx_msg->jsm_msg->result != VPU_JSM_STATUS_SUCCESS) { - ivpu_dbg(vdev, IPC, "IPC resp result error: %d\n", rx_msg->jsm_msg->result); + ivpu_err(vdev, "IPC resp result error: %d\n", rx_msg->jsm_msg->result); ret = -EBADMSG; } if (jsm_msg) memcpy(jsm_msg, rx_msg->jsm_msg, size); + trace_jsm("[rx]", rx_msg->jsm_msg); } ivpu_ipc_rx_msg_del(vdev, rx_msg); @@ -291,15 +294,16 @@ int ivpu_ipc_receive(struct ivpu_device *vdev, struct ivpu_ipc_consumer *cons, return ret; } -static int +int ivpu_ipc_send_receive_internal(struct ivpu_device *vdev, struct vpu_jsm_msg *req, enum vpu_ipc_msg_type expected_resp_type, - struct vpu_jsm_msg *resp, u32 channel, - unsigned long timeout_ms) + struct vpu_jsm_msg *resp, u32 channel, unsigned long timeout_ms) { struct ivpu_ipc_consumer cons; int ret; + drm_WARN_ON(&vdev->drm, pm_runtime_status_suspended(vdev->drm.dev)); + ivpu_ipc_consumer_add(vdev, &cons, channel, NULL); ret = ivpu_ipc_send(vdev, &cons, req); @@ -325,19 +329,21 @@ consumer_del: return ret; } -int ivpu_ipc_send_receive_active(struct ivpu_device *vdev, struct vpu_jsm_msg *req, - enum vpu_ipc_msg_type expected_resp, struct vpu_jsm_msg *resp, - u32 channel, unsigned long timeout_ms) +int ivpu_ipc_send_receive(struct ivpu_device *vdev, struct vpu_jsm_msg *req, + enum vpu_ipc_msg_type expected_resp, struct vpu_jsm_msg *resp, + u32 channel, unsigned long timeout_ms) { struct vpu_jsm_msg hb_req = { .type = VPU_JSM_MSG_QUERY_ENGINE_HB }; struct vpu_jsm_msg hb_resp; int ret, hb_ret; - drm_WARN_ON(&vdev->drm, pm_runtime_status_suspended(vdev->drm.dev)); + ret = ivpu_rpm_get(vdev); + if (ret < 0) + return ret; ret = ivpu_ipc_send_receive_internal(vdev, req, expected_resp, resp, channel, timeout_ms); if (ret != -ETIMEDOUT) - return ret; + goto rpm_put; hb_ret = ivpu_ipc_send_receive_internal(vdev, &hb_req, VPU_JSM_MSG_QUERY_ENGINE_HB_DONE, &hb_resp, VPU_IPC_CHAN_ASYNC_CMD, @@ -345,21 +351,33 @@ int ivpu_ipc_send_receive_active(struct ivpu_device *vdev, struct vpu_jsm_msg *r if (hb_ret == -ETIMEDOUT) ivpu_pm_trigger_recovery(vdev, "IPC timeout"); +rpm_put: + ivpu_rpm_put(vdev); return ret; } -int ivpu_ipc_send_receive(struct ivpu_device *vdev, struct vpu_jsm_msg *req, - enum vpu_ipc_msg_type expected_resp, struct vpu_jsm_msg *resp, - u32 channel, unsigned long timeout_ms) +int ivpu_ipc_send_and_wait(struct ivpu_device *vdev, struct vpu_jsm_msg *req, + u32 channel, unsigned long timeout_ms) { + struct ivpu_ipc_consumer cons; int ret; ret = ivpu_rpm_get(vdev); if (ret < 0) return ret; - ret = ivpu_ipc_send_receive_active(vdev, req, expected_resp, resp, channel, timeout_ms); + ivpu_ipc_consumer_add(vdev, &cons, channel, NULL); + ret = ivpu_ipc_send(vdev, &cons, req); + if (ret) { + ivpu_warn_ratelimited(vdev, "IPC send failed: %d\n", ret); + goto consumer_del; + } + + msleep(timeout_ms); + +consumer_del: + ivpu_ipc_consumer_del(vdev, &cons); ivpu_rpm_put(vdev); return ret; } @@ -518,7 +536,6 @@ void ivpu_ipc_fini(struct ivpu_device *vdev) { struct ivpu_ipc_info *ipc = vdev->ipc; - drm_WARN_ON(&vdev->drm, ipc->on); drm_WARN_ON(&vdev->drm, !list_empty(&ipc->cons_list)); drm_WARN_ON(&vdev->drm, !list_empty(&ipc->cb_msg_list)); drm_WARN_ON(&vdev->drm, atomic_read(&ipc->rx_msg_count) > 0); diff --git a/drivers/accel/ivpu/ivpu_ipc.h b/drivers/accel/ivpu/ivpu_ipc.h index 4fe38141045ea370c40e86b22e682401abb18c2c..b4dfb504679bac3c4537e2fb337a67dffa632601 100644 --- a/drivers/accel/ivpu/ivpu_ipc.h +++ b/drivers/accel/ivpu/ivpu_ipc.h @@ -101,12 +101,13 @@ int ivpu_ipc_send(struct ivpu_device *vdev, struct ivpu_ipc_consumer *cons, int ivpu_ipc_receive(struct ivpu_device *vdev, struct ivpu_ipc_consumer *cons, struct ivpu_ipc_hdr *ipc_buf, struct vpu_jsm_msg *jsm_msg, unsigned long timeout_ms); - -int ivpu_ipc_send_receive_active(struct ivpu_device *vdev, struct vpu_jsm_msg *req, - enum vpu_ipc_msg_type expected_resp, struct vpu_jsm_msg *resp, - u32 channel, unsigned long timeout_ms); +int ivpu_ipc_send_receive_internal(struct ivpu_device *vdev, struct vpu_jsm_msg *req, + enum vpu_ipc_msg_type expected_resp_type, + struct vpu_jsm_msg *resp, u32 channel, unsigned long timeout_ms); int ivpu_ipc_send_receive(struct ivpu_device *vdev, struct vpu_jsm_msg *req, enum vpu_ipc_msg_type expected_resp, struct vpu_jsm_msg *resp, u32 channel, unsigned long timeout_ms); +int ivpu_ipc_send_and_wait(struct ivpu_device *vdev, struct vpu_jsm_msg *req, + u32 channel, unsigned long timeout_ms); #endif /* __IVPU_IPC_H__ */ diff --git a/drivers/accel/ivpu/ivpu_job.c b/drivers/accel/ivpu/ivpu_job.c index be2e2bf0f43f022768d02c171130db028237d773..7149312f16e193e68a4cb9985b9fa4b1ef8840ef 100644 --- a/drivers/accel/ivpu/ivpu_job.c +++ b/drivers/accel/ivpu/ivpu_job.c @@ -18,11 +18,10 @@ #include "ivpu_job.h" #include "ivpu_jsm_msg.h" #include "ivpu_pm.h" +#include "ivpu_trace.h" #include "vpu_boot_api.h" #define CMD_BUF_IDX 0 -#define JOB_ID_JOB_MASK GENMASK(7, 0) -#define JOB_ID_CONTEXT_MASK GENMASK(31, 8) #define JOB_MAX_BUFFER_COUNT 65535 static void ivpu_cmdq_ring_db(struct ivpu_device *vdev, struct ivpu_cmdq *cmdq) @@ -35,24 +34,20 @@ static int ivpu_preemption_buffers_create(struct ivpu_device *vdev, { u64 primary_size = ALIGN(vdev->fw->primary_preempt_buf_size, PAGE_SIZE); u64 secondary_size = ALIGN(vdev->fw->secondary_preempt_buf_size, PAGE_SIZE); - struct ivpu_addr_range range; - if (vdev->hw->sched_mode != VPU_SCHEDULING_MODE_HW) + if (vdev->fw->sched_mode != VPU_SCHEDULING_MODE_HW || + ivpu_test_mode & IVPU_TEST_MODE_MIP_DISABLE) return 0; - range.start = vdev->hw->ranges.user.end - (primary_size * IVPU_NUM_CMDQS_PER_CTX); - range.end = vdev->hw->ranges.user.end; - cmdq->primary_preempt_buf = ivpu_bo_create(vdev, &file_priv->ctx, &range, primary_size, - DRM_IVPU_BO_WC); + cmdq->primary_preempt_buf = ivpu_bo_create(vdev, &file_priv->ctx, &vdev->hw->ranges.user, + primary_size, DRM_IVPU_BO_WC); if (!cmdq->primary_preempt_buf) { ivpu_err(vdev, "Failed to create primary preemption buffer\n"); return -ENOMEM; } - range.start = vdev->hw->ranges.shave.end - (secondary_size * IVPU_NUM_CMDQS_PER_CTX); - range.end = vdev->hw->ranges.shave.end; - cmdq->secondary_preempt_buf = ivpu_bo_create(vdev, &file_priv->ctx, &range, secondary_size, - DRM_IVPU_BO_WC); + cmdq->secondary_preempt_buf = ivpu_bo_create(vdev, &file_priv->ctx, &vdev->hw->ranges.dma, + secondary_size, DRM_IVPU_BO_WC); if (!cmdq->secondary_preempt_buf) { ivpu_err(vdev, "Failed to create secondary preemption buffer\n"); goto err_free_primary; @@ -62,24 +57,24 @@ static int ivpu_preemption_buffers_create(struct ivpu_device *vdev, err_free_primary: ivpu_bo_free(cmdq->primary_preempt_buf); + cmdq->primary_preempt_buf = NULL; return -ENOMEM; } static void ivpu_preemption_buffers_free(struct ivpu_device *vdev, struct ivpu_file_priv *file_priv, struct ivpu_cmdq *cmdq) { - if (vdev->hw->sched_mode != VPU_SCHEDULING_MODE_HW) + if (vdev->fw->sched_mode != VPU_SCHEDULING_MODE_HW) return; - drm_WARN_ON(&vdev->drm, !cmdq->primary_preempt_buf); - drm_WARN_ON(&vdev->drm, !cmdq->secondary_preempt_buf); - ivpu_bo_free(cmdq->primary_preempt_buf); - ivpu_bo_free(cmdq->secondary_preempt_buf); + if (cmdq->primary_preempt_buf) + ivpu_bo_free(cmdq->primary_preempt_buf); + if (cmdq->secondary_preempt_buf) + ivpu_bo_free(cmdq->secondary_preempt_buf); } static struct ivpu_cmdq *ivpu_cmdq_alloc(struct ivpu_file_priv *file_priv) { - struct xa_limit db_xa_limit = {.max = IVPU_MAX_DB, .min = IVPU_MIN_DB}; struct ivpu_device *vdev = file_priv->vdev; struct ivpu_cmdq *cmdq; int ret; @@ -88,25 +83,33 @@ static struct ivpu_cmdq *ivpu_cmdq_alloc(struct ivpu_file_priv *file_priv) if (!cmdq) return NULL; - ret = xa_alloc(&vdev->db_xa, &cmdq->db_id, NULL, db_xa_limit, GFP_KERNEL); - if (ret) { + ret = xa_alloc_cyclic(&vdev->db_xa, &cmdq->db_id, NULL, vdev->db_limit, &vdev->db_next, + GFP_KERNEL); + if (ret < 0) { ivpu_err(vdev, "Failed to allocate doorbell id: %d\n", ret); goto err_free_cmdq; } + ret = xa_alloc_cyclic(&file_priv->cmdq_xa, &cmdq->id, cmdq, file_priv->cmdq_limit, + &file_priv->cmdq_id_next, GFP_KERNEL); + if (ret < 0) { + ivpu_err(vdev, "Failed to allocate command queue id: %d\n", ret); + goto err_erase_db_xa; + } + cmdq->mem = ivpu_bo_create_global(vdev, SZ_4K, DRM_IVPU_BO_WC | DRM_IVPU_BO_MAPPABLE); if (!cmdq->mem) - goto err_erase_xa; + goto err_erase_cmdq_xa; ret = ivpu_preemption_buffers_create(vdev, file_priv, cmdq); if (ret) - goto err_free_cmdq_mem; + ivpu_warn(vdev, "Failed to allocate preemption buffers, preemption limited\n"); return cmdq; -err_free_cmdq_mem: - ivpu_bo_free(cmdq->mem); -err_erase_xa: +err_erase_cmdq_xa: + xa_erase(&file_priv->cmdq_xa, cmdq->id); +err_erase_db_xa: xa_erase(&vdev->db_xa, cmdq->db_id); err_free_cmdq: kfree(cmdq); @@ -130,13 +133,13 @@ static int ivpu_hws_cmdq_init(struct ivpu_file_priv *file_priv, struct ivpu_cmdq struct ivpu_device *vdev = file_priv->vdev; int ret; - ret = ivpu_jsm_hws_create_cmdq(vdev, file_priv->ctx.id, file_priv->ctx.id, cmdq->db_id, + ret = ivpu_jsm_hws_create_cmdq(vdev, file_priv->ctx.id, file_priv->ctx.id, cmdq->id, task_pid_nr(current), engine, cmdq->mem->vpu_addr, ivpu_bo_size(cmdq->mem)); if (ret) return ret; - ret = ivpu_jsm_hws_set_context_sched_properties(vdev, file_priv->ctx.id, cmdq->db_id, + ret = ivpu_jsm_hws_set_context_sched_properties(vdev, file_priv->ctx.id, cmdq->id, priority); if (ret) return ret; @@ -149,21 +152,22 @@ static int ivpu_register_db(struct ivpu_file_priv *file_priv, struct ivpu_cmdq * struct ivpu_device *vdev = file_priv->vdev; int ret; - if (vdev->hw->sched_mode == VPU_SCHEDULING_MODE_HW) - ret = ivpu_jsm_hws_register_db(vdev, file_priv->ctx.id, cmdq->db_id, cmdq->db_id, + if (vdev->fw->sched_mode == VPU_SCHEDULING_MODE_HW) + ret = ivpu_jsm_hws_register_db(vdev, file_priv->ctx.id, cmdq->id, cmdq->db_id, cmdq->mem->vpu_addr, ivpu_bo_size(cmdq->mem)); else ret = ivpu_jsm_register_db(vdev, file_priv->ctx.id, cmdq->db_id, cmdq->mem->vpu_addr, ivpu_bo_size(cmdq->mem)); if (!ret) - ivpu_dbg(vdev, JOB, "DB %d registered to ctx %d\n", cmdq->db_id, file_priv->ctx.id); + ivpu_dbg(vdev, JOB, "DB %d registered to cmdq %d ctx %d\n", + cmdq->db_id, cmdq->id, file_priv->ctx.id); return ret; } static int -ivpu_cmdq_init(struct ivpu_file_priv *file_priv, struct ivpu_cmdq *cmdq, u16 engine, u8 priority) +ivpu_cmdq_init(struct ivpu_file_priv *file_priv, struct ivpu_cmdq *cmdq, u8 priority) { struct ivpu_device *vdev = file_priv->vdev; struct vpu_job_queue_header *jobq_header; @@ -179,13 +183,18 @@ ivpu_cmdq_init(struct ivpu_file_priv *file_priv, struct ivpu_cmdq *cmdq, u16 eng cmdq->jobq = (struct vpu_job_queue *)ivpu_bo_vaddr(cmdq->mem); jobq_header = &cmdq->jobq->header; - jobq_header->engine_idx = engine; + jobq_header->engine_idx = VPU_ENGINE_COMPUTE; jobq_header->head = 0; jobq_header->tail = 0; + if (ivpu_test_mode & IVPU_TEST_MODE_TURBO) { + ivpu_dbg(vdev, JOB, "Turbo mode enabled"); + jobq_header->flags = VPU_JOB_QUEUE_FLAGS_TURBO_MODE; + } + wmb(); /* Flush WC buffer for jobq->header */ - if (vdev->hw->sched_mode == VPU_SCHEDULING_MODE_HW) { - ret = ivpu_hws_cmdq_init(file_priv, cmdq, engine, priority); + if (vdev->fw->sched_mode == VPU_SCHEDULING_MODE_HW) { + ret = ivpu_hws_cmdq_init(file_priv, cmdq, VPU_ENGINE_COMPUTE, priority); if (ret) return ret; } @@ -211,10 +220,10 @@ static int ivpu_cmdq_fini(struct ivpu_file_priv *file_priv, struct ivpu_cmdq *cm cmdq->db_registered = false; - if (vdev->hw->sched_mode == VPU_SCHEDULING_MODE_HW) { - ret = ivpu_jsm_hws_destroy_cmdq(vdev, file_priv->ctx.id, cmdq->db_id); + if (vdev->fw->sched_mode == VPU_SCHEDULING_MODE_HW) { + ret = ivpu_jsm_hws_destroy_cmdq(vdev, file_priv->ctx.id, cmdq->id); if (!ret) - ivpu_dbg(vdev, JOB, "Command queue %d destroyed\n", cmdq->db_id); + ivpu_dbg(vdev, JOB, "Command queue %d destroyed\n", cmdq->id); } ret = ivpu_jsm_unregister_db(vdev, cmdq->db_id); @@ -224,55 +233,46 @@ static int ivpu_cmdq_fini(struct ivpu_file_priv *file_priv, struct ivpu_cmdq *cm return 0; } -static struct ivpu_cmdq *ivpu_cmdq_acquire(struct ivpu_file_priv *file_priv, u16 engine, - u8 priority) +static struct ivpu_cmdq *ivpu_cmdq_acquire(struct ivpu_file_priv *file_priv, u8 priority) { - int cmdq_idx = IVPU_CMDQ_INDEX(engine, priority); - struct ivpu_cmdq *cmdq = file_priv->cmdq[cmdq_idx]; + struct ivpu_cmdq *cmdq; + unsigned long cmdq_id; int ret; lockdep_assert_held(&file_priv->lock); + xa_for_each(&file_priv->cmdq_xa, cmdq_id, cmdq) + if (cmdq->priority == priority) + break; + if (!cmdq) { cmdq = ivpu_cmdq_alloc(file_priv); if (!cmdq) return NULL; - file_priv->cmdq[cmdq_idx] = cmdq; + cmdq->priority = priority; } - ret = ivpu_cmdq_init(file_priv, cmdq, engine, priority); + ret = ivpu_cmdq_init(file_priv, cmdq, priority); if (ret) return NULL; return cmdq; } -static void ivpu_cmdq_release_locked(struct ivpu_file_priv *file_priv, u16 engine, u8 priority) +void ivpu_cmdq_release_all_locked(struct ivpu_file_priv *file_priv) { - int cmdq_idx = IVPU_CMDQ_INDEX(engine, priority); - struct ivpu_cmdq *cmdq = file_priv->cmdq[cmdq_idx]; + struct ivpu_cmdq *cmdq; + unsigned long cmdq_id; lockdep_assert_held(&file_priv->lock); - if (cmdq) { - file_priv->cmdq[cmdq_idx] = NULL; + xa_for_each(&file_priv->cmdq_xa, cmdq_id, cmdq) { + xa_erase(&file_priv->cmdq_xa, cmdq_id); ivpu_cmdq_fini(file_priv, cmdq); ivpu_cmdq_free(file_priv, cmdq); } } -void ivpu_cmdq_release_all_locked(struct ivpu_file_priv *file_priv) -{ - u16 engine; - u8 priority; - - lockdep_assert_held(&file_priv->lock); - - for (engine = 0; engine < IVPU_NUM_ENGINES; engine++) - for (priority = 0; priority < IVPU_NUM_PRIORITIES; priority++) - ivpu_cmdq_release_locked(file_priv, engine, priority); -} - /* * Mark the doorbell as unregistered * This function needs to be called when the VPU hardware is restarted @@ -281,20 +281,13 @@ void ivpu_cmdq_release_all_locked(struct ivpu_file_priv *file_priv) */ static void ivpu_cmdq_reset(struct ivpu_file_priv *file_priv) { - u16 engine; - u8 priority; + struct ivpu_cmdq *cmdq; + unsigned long cmdq_id; mutex_lock(&file_priv->lock); - for (engine = 0; engine < IVPU_NUM_ENGINES; engine++) { - for (priority = 0; priority < IVPU_NUM_PRIORITIES; priority++) { - int cmdq_idx = IVPU_CMDQ_INDEX(engine, priority); - struct ivpu_cmdq *cmdq = file_priv->cmdq[cmdq_idx]; - - if (cmdq) - cmdq->db_registered = false; - } - } + xa_for_each(&file_priv->cmdq_xa, cmdq_id, cmdq) + cmdq->db_registered = false; mutex_unlock(&file_priv->lock); } @@ -314,17 +307,11 @@ void ivpu_cmdq_reset_all_contexts(struct ivpu_device *vdev) static void ivpu_cmdq_fini_all(struct ivpu_file_priv *file_priv) { - u16 engine; - u8 priority; - - for (engine = 0; engine < IVPU_NUM_ENGINES; engine++) { - for (priority = 0; priority < IVPU_NUM_PRIORITIES; priority++) { - int cmdq_idx = IVPU_CMDQ_INDEX(engine, priority); + struct ivpu_cmdq *cmdq; + unsigned long cmdq_id; - if (file_priv->cmdq[cmdq_idx]) - ivpu_cmdq_fini(file_priv, file_priv->cmdq[cmdq_idx]); - } - } + xa_for_each(&file_priv->cmdq_xa, cmdq_id, cmdq) + ivpu_cmdq_fini(file_priv, cmdq); } void ivpu_context_abort_locked(struct ivpu_file_priv *file_priv) @@ -335,7 +322,7 @@ void ivpu_context_abort_locked(struct ivpu_file_priv *file_priv) ivpu_cmdq_fini_all(file_priv); - if (vdev->hw->sched_mode == VPU_SCHEDULING_MODE_OS) + if (vdev->fw->sched_mode == VPU_SCHEDULING_MODE_OS) ivpu_jsm_context_release(vdev, file_priv->ctx.id); } @@ -349,24 +336,29 @@ static int ivpu_cmdq_push_job(struct ivpu_cmdq *cmdq, struct ivpu_job *job) /* Check if there is space left in job queue */ if (next_entry == header->head) { - ivpu_dbg(vdev, JOB, "Job queue full: ctx %d engine %d db %d head %d tail %d\n", - job->file_priv->ctx.id, job->engine_idx, cmdq->db_id, header->head, tail); + ivpu_dbg(vdev, JOB, "Job queue full: ctx %d cmdq %d db %d head %d tail %d\n", + job->file_priv->ctx.id, cmdq->id, cmdq->db_id, header->head, tail); return -EBUSY; } - entry = &cmdq->jobq->job[tail]; + entry = &cmdq->jobq->slot[tail].job; entry->batch_buf_addr = job->cmd_buf_vpu_addr; entry->job_id = job->job_id; entry->flags = 0; if (unlikely(ivpu_test_mode & IVPU_TEST_MODE_NULL_SUBMISSION)) entry->flags = VPU_JOB_FLAGS_NULL_SUBMISSION_MASK; - if (vdev->hw->sched_mode == VPU_SCHEDULING_MODE_HW && - (unlikely(!(ivpu_test_mode & IVPU_TEST_MODE_PREEMPTION_DISABLE)))) { - entry->primary_preempt_buf_addr = cmdq->primary_preempt_buf->vpu_addr; - entry->primary_preempt_buf_size = ivpu_bo_size(cmdq->primary_preempt_buf); - entry->secondary_preempt_buf_addr = cmdq->secondary_preempt_buf->vpu_addr; - entry->secondary_preempt_buf_size = ivpu_bo_size(cmdq->secondary_preempt_buf); + if (vdev->fw->sched_mode == VPU_SCHEDULING_MODE_HW) { + if (cmdq->primary_preempt_buf) { + entry->primary_preempt_buf_addr = cmdq->primary_preempt_buf->vpu_addr; + entry->primary_preempt_buf_size = ivpu_bo_size(cmdq->primary_preempt_buf); + } + + if (cmdq->secondary_preempt_buf) { + entry->secondary_preempt_buf_addr = cmdq->secondary_preempt_buf->vpu_addr; + entry->secondary_preempt_buf_size = + ivpu_bo_size(cmdq->secondary_preempt_buf); + } } wmb(); /* Ensure that tail is updated after filling entry */ @@ -457,6 +449,7 @@ ivpu_job_create(struct ivpu_file_priv *file_priv, u32 engine_idx, u32 bo_count) job->file_priv = ivpu_file_priv_get(file_priv); + trace_job("create", job); ivpu_dbg(vdev, JOB, "Job created: ctx %2d engine %d", file_priv->ctx.id, job->engine_idx); return job; @@ -496,6 +489,7 @@ static int ivpu_job_signal_and_destroy(struct ivpu_device *vdev, u32 job_id, u32 job->bos[CMD_BUF_IDX]->job_status = job_status; dma_fence_signal(job->done_fence); + trace_job("done", job); ivpu_dbg(vdev, JOB, "Job complete: id %3u ctx %2d engine %d status 0x%x\n", job->job_id, job->file_priv->ctx.id, job->engine_idx, job_status); @@ -519,7 +513,6 @@ static int ivpu_job_submit(struct ivpu_job *job, u8 priority) { struct ivpu_file_priv *file_priv = job->file_priv; struct ivpu_device *vdev = job->vdev; - struct xa_limit job_id_range; struct ivpu_cmdq *cmdq; bool is_first_job; int ret; @@ -530,7 +523,7 @@ static int ivpu_job_submit(struct ivpu_job *job, u8 priority) mutex_lock(&file_priv->lock); - cmdq = ivpu_cmdq_acquire(job->file_priv, job->engine_idx, priority); + cmdq = ivpu_cmdq_acquire(file_priv, priority); if (!cmdq) { ivpu_warn_ratelimited(vdev, "Failed to get job queue, ctx %d engine %d prio %d\n", file_priv->ctx.id, job->engine_idx, priority); @@ -538,13 +531,11 @@ static int ivpu_job_submit(struct ivpu_job *job, u8 priority) goto err_unlock_file_priv; } - job_id_range.min = FIELD_PREP(JOB_ID_CONTEXT_MASK, (file_priv->ctx.id - 1)); - job_id_range.max = job_id_range.min | JOB_ID_JOB_MASK; - xa_lock(&vdev->submitted_jobs_xa); is_first_job = xa_empty(&vdev->submitted_jobs_xa); - ret = __xa_alloc(&vdev->submitted_jobs_xa, &job->job_id, job, job_id_range, GFP_KERNEL); - if (ret) { + ret = __xa_alloc_cyclic(&vdev->submitted_jobs_xa, &job->job_id, job, file_priv->job_limit, + &file_priv->job_id_next, GFP_KERNEL); + if (ret < 0) { ivpu_dbg(vdev, JOB, "Too many active jobs in ctx %d\n", file_priv->ctx.id); ret = -EBUSY; @@ -566,6 +557,7 @@ static int ivpu_job_submit(struct ivpu_job *job, u8 priority) vdev->busy_start_ts = ktime_get(); } + trace_job("submit", job); ivpu_dbg(vdev, JOB, "Job submitted: id %3u ctx %2d engine %d prio %d addr 0x%llx next %d\n", job->job_id, file_priv->ctx.id, job->engine_idx, priority, job->cmd_buf_vpu_addr, cmdq->jobq->header.tail); @@ -673,7 +665,7 @@ int ivpu_submit_ioctl(struct drm_device *dev, void *data, struct drm_file *file) int idx, ret; u8 priority; - if (params->engine > DRM_IVPU_ENGINE_COPY) + if (params->engine != DRM_IVPU_ENGINE_COMPUTE) return -EINVAL; if (params->priority > DRM_IVPU_JOB_PRIORITY_REALTIME) diff --git a/drivers/accel/ivpu/ivpu_job.h b/drivers/accel/ivpu/ivpu_job.h index 6accb94028c7a2d8468a5418648266c0c6be4890..8b19e3f8b4cfb36df485ad9ab1c57181a08ac07d 100644 --- a/drivers/accel/ivpu/ivpu_job.h +++ b/drivers/accel/ivpu/ivpu_job.h @@ -28,8 +28,10 @@ struct ivpu_cmdq { struct ivpu_bo *secondary_preempt_buf; struct ivpu_bo *mem; u32 entry_count; + u32 id; u32 db_id; bool db_registered; + u8 priority; }; /** diff --git a/drivers/accel/ivpu/ivpu_jsm_msg.c b/drivers/accel/ivpu/ivpu_jsm_msg.c index 46ef16c3c06910a43c7dd504e3955d6ca9ee33f0..30a40be769301919cba64f3af1604b46bb6181ed 100644 --- a/drivers/accel/ivpu/ivpu_jsm_msg.c +++ b/drivers/accel/ivpu/ivpu_jsm_msg.c @@ -48,9 +48,10 @@ const char *ivpu_jsm_msg_type_to_str(enum vpu_ipc_msg_type type) IVPU_CASE_TO_STR(VPU_JSM_MSG_HWS_RESUME_ENGINE_DONE); IVPU_CASE_TO_STR(VPU_JSM_MSG_STATE_DUMP); IVPU_CASE_TO_STR(VPU_JSM_MSG_STATE_DUMP_RSP); - IVPU_CASE_TO_STR(VPU_JSM_MSG_BLOB_DEINIT); + IVPU_CASE_TO_STR(VPU_JSM_MSG_BLOB_DEINIT_DEPRECATED); IVPU_CASE_TO_STR(VPU_JSM_MSG_DYNDBG_CONTROL); IVPU_CASE_TO_STR(VPU_JSM_MSG_JOB_DONE); + IVPU_CASE_TO_STR(VPU_JSM_MSG_NATIVE_FENCE_SIGNALLED); IVPU_CASE_TO_STR(VPU_JSM_MSG_ENGINE_RESET_DONE); IVPU_CASE_TO_STR(VPU_JSM_MSG_ENGINE_PREEMPT_DONE); IVPU_CASE_TO_STR(VPU_JSM_MSG_REGISTER_DB_DONE); @@ -131,7 +132,7 @@ int ivpu_jsm_get_heartbeat(struct ivpu_device *vdev, u32 engine, u64 *heartbeat) struct vpu_jsm_msg resp; int ret; - if (engine > VPU_ENGINE_COPY) + if (engine != VPU_ENGINE_COMPUTE) return -EINVAL; req.payload.query_engine_hb.engine_idx = engine; @@ -154,7 +155,7 @@ int ivpu_jsm_reset_engine(struct ivpu_device *vdev, u32 engine) struct vpu_jsm_msg resp; int ret; - if (engine > VPU_ENGINE_COPY) + if (engine != VPU_ENGINE_COMPUTE) return -EINVAL; req.payload.engine_reset.engine_idx = engine; @@ -173,7 +174,7 @@ int ivpu_jsm_preempt_engine(struct ivpu_device *vdev, u32 engine, u32 preempt_id struct vpu_jsm_msg resp; int ret; - if (engine > VPU_ENGINE_COPY) + if (engine != VPU_ENGINE_COMPUTE) return -EINVAL; req.payload.engine_preempt.engine_idx = engine; @@ -196,7 +197,7 @@ int ivpu_jsm_dyndbg_control(struct ivpu_device *vdev, char *command, size_t size strscpy(req.payload.dyndbg_control.dyndbg_cmd, command, VPU_DYNDBG_CMD_MAX_LEN); ret = ivpu_ipc_send_receive(vdev, &req, VPU_JSM_MSG_DYNDBG_CONTROL_RSP, &resp, - VPU_IPC_CHAN_ASYNC_CMD, vdev->timeout.jsm); + VPU_IPC_CHAN_GEN_CMD, vdev->timeout.jsm); if (ret) ivpu_warn_ratelimited(vdev, "Failed to send command \"%s\": ret %d\n", command, ret); @@ -270,9 +271,8 @@ int ivpu_jsm_pwr_d0i3_enter(struct ivpu_device *vdev) req.payload.pwr_d0i3_enter.send_response = 1; - ret = ivpu_ipc_send_receive_active(vdev, &req, VPU_JSM_MSG_PWR_D0I3_ENTER_DONE, - &resp, VPU_IPC_CHAN_GEN_CMD, - vdev->timeout.d0i3_entry_msg); + ret = ivpu_ipc_send_receive_internal(vdev, &req, VPU_JSM_MSG_PWR_D0I3_ENTER_DONE, &resp, + VPU_IPC_CHAN_GEN_CMD, vdev->timeout.d0i3_entry_msg); if (ret) return ret; @@ -346,7 +346,7 @@ int ivpu_jsm_hws_resume_engine(struct ivpu_device *vdev, u32 engine) struct vpu_jsm_msg resp; int ret; - if (engine >= VPU_ENGINE_NB) + if (engine != VPU_ENGINE_COMPUTE) return -EINVAL; req.payload.hws_resume_engine.engine_idx = engine; @@ -394,8 +394,6 @@ int ivpu_jsm_hws_set_scheduling_log(struct ivpu_device *vdev, u32 engine_idx, u3 req.payload.hws_set_scheduling_log.host_ssid = host_ssid; req.payload.hws_set_scheduling_log.vpu_log_buffer_va = vpu_log_buffer_va; req.payload.hws_set_scheduling_log.notify_index = 0; - req.payload.hws_set_scheduling_log.enable_extra_events = - ivpu_test_mode & IVPU_TEST_MODE_HWS_EXTRA_EVENTS; ret = ivpu_ipc_send_receive(vdev, &req, VPU_JSM_MSG_HWS_SET_SCHEDULING_LOG_RSP, &resp, VPU_IPC_CHAN_ASYNC_CMD, vdev->timeout.jsm); @@ -430,8 +428,8 @@ int ivpu_jsm_hws_setup_priority_bands(struct ivpu_device *vdev) req.payload.hws_priority_band_setup.normal_band_percentage = 10; - ret = ivpu_ipc_send_receive_active(vdev, &req, VPU_JSM_MSG_SET_PRIORITY_BAND_SETUP_RSP, - &resp, VPU_IPC_CHAN_ASYNC_CMD, vdev->timeout.jsm); + ret = ivpu_ipc_send_receive_internal(vdev, &req, VPU_JSM_MSG_SET_PRIORITY_BAND_SETUP_RSP, + &resp, VPU_IPC_CHAN_ASYNC_CMD, vdev->timeout.jsm); if (ret) ivpu_warn_ratelimited(vdev, "Failed to set priority bands: %d\n", ret); @@ -544,9 +542,8 @@ int ivpu_jsm_dct_enable(struct ivpu_device *vdev, u32 active_us, u32 inactive_us req.payload.pwr_dct_control.dct_active_us = active_us; req.payload.pwr_dct_control.dct_inactive_us = inactive_us; - return ivpu_ipc_send_receive_active(vdev, &req, VPU_JSM_MSG_DCT_ENABLE_DONE, - &resp, VPU_IPC_CHAN_ASYNC_CMD, - vdev->timeout.jsm); + return ivpu_ipc_send_receive_internal(vdev, &req, VPU_JSM_MSG_DCT_ENABLE_DONE, &resp, + VPU_IPC_CHAN_ASYNC_CMD, vdev->timeout.jsm); } int ivpu_jsm_dct_disable(struct ivpu_device *vdev) @@ -554,7 +551,14 @@ int ivpu_jsm_dct_disable(struct ivpu_device *vdev) struct vpu_jsm_msg req = { .type = VPU_JSM_MSG_DCT_DISABLE }; struct vpu_jsm_msg resp; - return ivpu_ipc_send_receive_active(vdev, &req, VPU_JSM_MSG_DCT_DISABLE_DONE, - &resp, VPU_IPC_CHAN_ASYNC_CMD, - vdev->timeout.jsm); + return ivpu_ipc_send_receive_internal(vdev, &req, VPU_JSM_MSG_DCT_DISABLE_DONE, &resp, + VPU_IPC_CHAN_ASYNC_CMD, vdev->timeout.jsm); +} + +int ivpu_jsm_state_dump(struct ivpu_device *vdev) +{ + struct vpu_jsm_msg req = { .type = VPU_JSM_MSG_STATE_DUMP }; + + return ivpu_ipc_send_and_wait(vdev, &req, VPU_IPC_CHAN_ASYNC_CMD, + vdev->timeout.state_dump_msg); } diff --git a/drivers/accel/ivpu/ivpu_jsm_msg.h b/drivers/accel/ivpu/ivpu_jsm_msg.h index e4e42c0ff6e65614b36eb7ff52395d6628d9b0e1..9e84d3526a14635cde1d9b3dfe5ef471df67ec90 100644 --- a/drivers/accel/ivpu/ivpu_jsm_msg.h +++ b/drivers/accel/ivpu/ivpu_jsm_msg.h @@ -43,4 +43,6 @@ int ivpu_jsm_metric_streamer_info(struct ivpu_device *vdev, u64 metric_group_mas u64 buffer_size, u32 *sample_size, u64 *info_size); int ivpu_jsm_dct_enable(struct ivpu_device *vdev, u32 active_us, u32 inactive_us); int ivpu_jsm_dct_disable(struct ivpu_device *vdev); +int ivpu_jsm_state_dump(struct ivpu_device *vdev); + #endif diff --git a/drivers/accel/ivpu/ivpu_mmu.c b/drivers/accel/ivpu/ivpu_mmu.c index c078e214b221297ed606ceccaf641e268f598838..26ef52fbb93e53a8bb8234d97fbe02c9a50ca208 100644 --- a/drivers/accel/ivpu/ivpu_mmu.c +++ b/drivers/accel/ivpu/ivpu_mmu.c @@ -696,7 +696,7 @@ unlock: return ret; } -static int ivpu_mmu_cd_add(struct ivpu_device *vdev, u32 ssid, u64 cd_dma) +static int ivpu_mmu_cdtab_entry_set(struct ivpu_device *vdev, u32 ssid, u64 cd_dma, bool valid) { struct ivpu_mmu_info *mmu = vdev->mmu; struct ivpu_mmu_cdtab *cdtab = &mmu->cdtab; @@ -708,30 +708,29 @@ static int ivpu_mmu_cd_add(struct ivpu_device *vdev, u32 ssid, u64 cd_dma) return -EINVAL; entry = cdtab->base + (ssid * IVPU_MMU_CDTAB_ENT_SIZE); - - if (cd_dma != 0) { - cd[0] = FIELD_PREP(IVPU_MMU_CD_0_TCR_T0SZ, IVPU_MMU_T0SZ_48BIT) | - FIELD_PREP(IVPU_MMU_CD_0_TCR_TG0, 0) | - FIELD_PREP(IVPU_MMU_CD_0_TCR_IRGN0, 0) | - FIELD_PREP(IVPU_MMU_CD_0_TCR_ORGN0, 0) | - FIELD_PREP(IVPU_MMU_CD_0_TCR_SH0, 0) | - FIELD_PREP(IVPU_MMU_CD_0_TCR_IPS, IVPU_MMU_IPS_48BIT) | - FIELD_PREP(IVPU_MMU_CD_0_ASID, ssid) | - IVPU_MMU_CD_0_TCR_EPD1 | - IVPU_MMU_CD_0_AA64 | - IVPU_MMU_CD_0_R | - IVPU_MMU_CD_0_ASET | - IVPU_MMU_CD_0_V; - cd[1] = cd_dma & IVPU_MMU_CD_1_TTB0_MASK; - cd[2] = 0; - cd[3] = 0x0000000000007444; - - /* For global context generate memory fault on VPU */ - if (ssid == IVPU_GLOBAL_CONTEXT_MMU_SSID) - cd[0] |= IVPU_MMU_CD_0_A; - } else { - memset(cd, 0, sizeof(cd)); - } + drm_WARN_ON(&vdev->drm, (entry[0] & IVPU_MMU_CD_0_V) == valid); + + cd[0] = FIELD_PREP(IVPU_MMU_CD_0_TCR_T0SZ, IVPU_MMU_T0SZ_48BIT) | + FIELD_PREP(IVPU_MMU_CD_0_TCR_TG0, 0) | + FIELD_PREP(IVPU_MMU_CD_0_TCR_IRGN0, 0) | + FIELD_PREP(IVPU_MMU_CD_0_TCR_ORGN0, 0) | + FIELD_PREP(IVPU_MMU_CD_0_TCR_SH0, 0) | + FIELD_PREP(IVPU_MMU_CD_0_TCR_IPS, IVPU_MMU_IPS_48BIT) | + FIELD_PREP(IVPU_MMU_CD_0_ASID, ssid) | + IVPU_MMU_CD_0_TCR_EPD1 | + IVPU_MMU_CD_0_AA64 | + IVPU_MMU_CD_0_R | + IVPU_MMU_CD_0_ASET; + cd[1] = cd_dma & IVPU_MMU_CD_1_TTB0_MASK; + cd[2] = 0; + cd[3] = 0x0000000000007444; + + /* For global context generate memory fault on VPU */ + if (ssid == IVPU_GLOBAL_CONTEXT_MMU_SSID) + cd[0] |= IVPU_MMU_CD_0_A; + + if (valid) + cd[0] |= IVPU_MMU_CD_0_V; WRITE_ONCE(entry[1], cd[1]); WRITE_ONCE(entry[2], cd[2]); @@ -741,8 +740,8 @@ static int ivpu_mmu_cd_add(struct ivpu_device *vdev, u32 ssid, u64 cd_dma) if (!ivpu_is_force_snoop_enabled(vdev)) clflush_cache_range(entry, IVPU_MMU_CDTAB_ENT_SIZE); - ivpu_dbg(vdev, MMU, "CDTAB %s entry (SSID=%u, dma=%pad): 0x%llx, 0x%llx, 0x%llx, 0x%llx\n", - cd_dma ? "write" : "clear", ssid, &cd_dma, cd[0], cd[1], cd[2], cd[3]); + ivpu_dbg(vdev, MMU, "CDTAB set %s entry (SSID=%u, dma=%pad): 0x%llx, 0x%llx, 0x%llx, 0x%llx\n", + valid ? "valid" : "invalid", ssid, &cd_dma, cd[0], cd[1], cd[2], cd[3]); mutex_lock(&mmu->lock); if (!mmu->on) @@ -750,38 +749,18 @@ static int ivpu_mmu_cd_add(struct ivpu_device *vdev, u32 ssid, u64 cd_dma) ret = ivpu_mmu_cmdq_write_cfgi_all(vdev); if (ret) - goto unlock; + goto err_invalidate; ret = ivpu_mmu_cmdq_sync(vdev); + if (ret) + goto err_invalidate; unlock: mutex_unlock(&mmu->lock); - return ret; -} - -static int ivpu_mmu_cd_add_gbl(struct ivpu_device *vdev) -{ - int ret; - - ret = ivpu_mmu_cd_add(vdev, 0, vdev->gctx.pgtable.pgd_dma); - if (ret) - ivpu_err(vdev, "Failed to add global CD entry: %d\n", ret); - - return ret; -} - -static int ivpu_mmu_cd_add_user(struct ivpu_device *vdev, u32 ssid, dma_addr_t cd_dma) -{ - int ret; - - if (ssid == 0) { - ivpu_err(vdev, "Invalid SSID: %u\n", ssid); - return -EINVAL; - } - - ret = ivpu_mmu_cd_add(vdev, ssid, cd_dma); - if (ret) - ivpu_err(vdev, "Failed to add CD entry SSID=%u: %d\n", ssid, ret); + return 0; +err_invalidate: + WRITE_ONCE(entry[0], 0); + mutex_unlock(&mmu->lock); return ret; } @@ -808,12 +787,6 @@ int ivpu_mmu_init(struct ivpu_device *vdev) return ret; } - ret = ivpu_mmu_cd_add_gbl(vdev); - if (ret) { - ivpu_err(vdev, "Failed to initialize strtab: %d\n", ret); - return ret; - } - ret = ivpu_mmu_enable(vdev); if (ret) { ivpu_err(vdev, "Failed to resume MMU: %d\n", ret); @@ -966,12 +939,12 @@ void ivpu_mmu_irq_gerr_handler(struct ivpu_device *vdev) REGV_WR32(IVPU_MMU_REG_GERRORN, gerror_val); } -int ivpu_mmu_set_pgtable(struct ivpu_device *vdev, int ssid, struct ivpu_mmu_pgtable *pgtable) +int ivpu_mmu_cd_set(struct ivpu_device *vdev, int ssid, struct ivpu_mmu_pgtable *pgtable) { - return ivpu_mmu_cd_add_user(vdev, ssid, pgtable->pgd_dma); + return ivpu_mmu_cdtab_entry_set(vdev, ssid, pgtable->pgd_dma, true); } -void ivpu_mmu_clear_pgtable(struct ivpu_device *vdev, int ssid) +void ivpu_mmu_cd_clear(struct ivpu_device *vdev, int ssid) { - ivpu_mmu_cd_add_user(vdev, ssid, 0); /* 0 will clear CD entry */ + ivpu_mmu_cdtab_entry_set(vdev, ssid, 0, false); } diff --git a/drivers/accel/ivpu/ivpu_mmu.h b/drivers/accel/ivpu/ivpu_mmu.h index 6fa35c240710625670b6879098833c6cd680fb40..7afea9cd8731d575cf72d84321a22914a5a38ffa 100644 --- a/drivers/accel/ivpu/ivpu_mmu.h +++ b/drivers/accel/ivpu/ivpu_mmu.h @@ -40,8 +40,8 @@ struct ivpu_mmu_info { int ivpu_mmu_init(struct ivpu_device *vdev); void ivpu_mmu_disable(struct ivpu_device *vdev); int ivpu_mmu_enable(struct ivpu_device *vdev); -int ivpu_mmu_set_pgtable(struct ivpu_device *vdev, int ssid, struct ivpu_mmu_pgtable *pgtable); -void ivpu_mmu_clear_pgtable(struct ivpu_device *vdev, int ssid); +int ivpu_mmu_cd_set(struct ivpu_device *vdev, int ssid, struct ivpu_mmu_pgtable *pgtable); +void ivpu_mmu_cd_clear(struct ivpu_device *vdev, int ssid); int ivpu_mmu_invalidate_tlb(struct ivpu_device *vdev, u16 ssid); void ivpu_mmu_irq_evtq_handler(struct ivpu_device *vdev); diff --git a/drivers/accel/ivpu/ivpu_mmu_context.c b/drivers/accel/ivpu/ivpu_mmu_context.c index bbe652a7019d0300ed1b7f42d829f2aca53cb2c5..891967a95bc3c76cb946e3ffd07eb1c767f4c006 100644 --- a/drivers/accel/ivpu/ivpu_mmu_context.c +++ b/drivers/accel/ivpu/ivpu_mmu_context.c @@ -90,19 +90,6 @@ static void ivpu_pgtable_free_page(struct ivpu_device *vdev, u64 *cpu_addr, dma_ } } -static int ivpu_mmu_pgtable_init(struct ivpu_device *vdev, struct ivpu_mmu_pgtable *pgtable) -{ - dma_addr_t pgd_dma; - - pgtable->pgd_dma_ptr = ivpu_pgtable_alloc_page(vdev, &pgd_dma); - if (!pgtable->pgd_dma_ptr) - return -ENOMEM; - - pgtable->pgd_dma = pgd_dma; - - return 0; -} - static void ivpu_mmu_pgtables_free(struct ivpu_device *vdev, struct ivpu_mmu_pgtable *pgtable) { int pgd_idx, pud_idx, pmd_idx; @@ -140,6 +127,27 @@ static void ivpu_mmu_pgtables_free(struct ivpu_device *vdev, struct ivpu_mmu_pgt } ivpu_pgtable_free_page(vdev, pgtable->pgd_dma_ptr, pgtable->pgd_dma); + pgtable->pgd_dma_ptr = NULL; + pgtable->pgd_dma = 0; +} + +static u64* +ivpu_mmu_ensure_pgd(struct ivpu_device *vdev, struct ivpu_mmu_pgtable *pgtable) +{ + u64 *pgd_dma_ptr = pgtable->pgd_dma_ptr; + dma_addr_t pgd_dma; + + if (pgd_dma_ptr) + return pgd_dma_ptr; + + pgd_dma_ptr = ivpu_pgtable_alloc_page(vdev, &pgd_dma); + if (!pgd_dma_ptr) + return NULL; + + pgtable->pgd_dma_ptr = pgd_dma_ptr; + pgtable->pgd_dma = pgd_dma; + + return pgd_dma_ptr; } static u64* @@ -237,6 +245,12 @@ ivpu_mmu_context_map_page(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx int pmd_idx = FIELD_GET(IVPU_MMU_PMD_INDEX_MASK, vpu_addr); int pte_idx = FIELD_GET(IVPU_MMU_PTE_INDEX_MASK, vpu_addr); + drm_WARN_ON(&vdev->drm, ctx->id == IVPU_RESERVED_CONTEXT_MMU_SSID); + + /* Allocate PGD - first level page table if needed */ + if (!ivpu_mmu_ensure_pgd(vdev, &ctx->pgtable)) + return -ENOMEM; + /* Allocate PUD - second level page table if needed */ if (!ivpu_mmu_ensure_pud(vdev, &ctx->pgtable, pgd_idx)) return -ENOMEM; @@ -418,6 +432,7 @@ int ivpu_mmu_context_map_sgt(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx, u64 vpu_addr, struct sg_table *sgt, bool llc_coherent) { + size_t start_vpu_addr = vpu_addr; struct scatterlist *sg; int ret; u64 prot; @@ -448,20 +463,36 @@ ivpu_mmu_context_map_sgt(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx, ret = ivpu_mmu_context_map_pages(vdev, ctx, vpu_addr, dma_addr, size, prot); if (ret) { ivpu_err(vdev, "Failed to map context pages\n"); - mutex_unlock(&ctx->lock); - return ret; + goto err_unmap_pages; } vpu_addr += size; } + if (!ctx->is_cd_valid) { + ret = ivpu_mmu_cd_set(vdev, ctx->id, &ctx->pgtable); + if (ret) { + ivpu_err(vdev, "Failed to set context descriptor for context %u: %d\n", + ctx->id, ret); + goto err_unmap_pages; + } + ctx->is_cd_valid = true; + } + /* Ensure page table modifications are flushed from wc buffers to memory */ wmb(); - mutex_unlock(&ctx->lock); - ret = ivpu_mmu_invalidate_tlb(vdev, ctx->id); - if (ret) + if (ret) { ivpu_err(vdev, "Failed to invalidate TLB for ctx %u: %d\n", ctx->id, ret); + goto err_unmap_pages; + } + + mutex_unlock(&ctx->lock); + return 0; + +err_unmap_pages: + ivpu_mmu_context_unmap_pages(ctx, start_vpu_addr, vpu_addr - start_vpu_addr); + mutex_unlock(&ctx->lock); return ret; } @@ -530,65 +561,75 @@ ivpu_mmu_context_remove_node(struct ivpu_mmu_context *ctx, struct drm_mm_node *n mutex_unlock(&ctx->lock); } -static int -ivpu_mmu_context_init(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx, u32 context_id) +void ivpu_mmu_context_init(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx, u32 context_id) { u64 start, end; - int ret; mutex_init(&ctx->lock); - ret = ivpu_mmu_pgtable_init(vdev, &ctx->pgtable); - if (ret) { - ivpu_err(vdev, "Failed to initialize pgtable for ctx %u: %d\n", context_id, ret); - return ret; - } - if (!context_id) { start = vdev->hw->ranges.global.start; end = vdev->hw->ranges.shave.end; } else { - start = vdev->hw->ranges.user.start; - end = vdev->hw->ranges.dma.end; + start = min_t(u64, vdev->hw->ranges.user.start, vdev->hw->ranges.shave.start); + end = max_t(u64, vdev->hw->ranges.user.end, vdev->hw->ranges.dma.end); } drm_mm_init(&ctx->mm, start, end - start); ctx->id = context_id; - - return 0; } -static void ivpu_mmu_context_fini(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx) +void ivpu_mmu_context_fini(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx) { - if (drm_WARN_ON(&vdev->drm, !ctx->pgtable.pgd_dma_ptr)) - return; + if (ctx->is_cd_valid) { + ivpu_mmu_cd_clear(vdev, ctx->id); + ctx->is_cd_valid = false; + } mutex_destroy(&ctx->lock); ivpu_mmu_pgtables_free(vdev, &ctx->pgtable); drm_mm_takedown(&ctx->mm); - - ctx->pgtable.pgd_dma_ptr = NULL; - ctx->pgtable.pgd_dma = 0; } -int ivpu_mmu_global_context_init(struct ivpu_device *vdev) +void ivpu_mmu_global_context_init(struct ivpu_device *vdev) { - return ivpu_mmu_context_init(vdev, &vdev->gctx, IVPU_GLOBAL_CONTEXT_MMU_SSID); + ivpu_mmu_context_init(vdev, &vdev->gctx, IVPU_GLOBAL_CONTEXT_MMU_SSID); } void ivpu_mmu_global_context_fini(struct ivpu_device *vdev) { - return ivpu_mmu_context_fini(vdev, &vdev->gctx); + ivpu_mmu_context_fini(vdev, &vdev->gctx); } int ivpu_mmu_reserved_context_init(struct ivpu_device *vdev) { - return ivpu_mmu_user_context_init(vdev, &vdev->rctx, IVPU_RESERVED_CONTEXT_MMU_SSID); + int ret; + + ivpu_mmu_context_init(vdev, &vdev->rctx, IVPU_RESERVED_CONTEXT_MMU_SSID); + + mutex_lock(&vdev->rctx.lock); + + if (!ivpu_mmu_ensure_pgd(vdev, &vdev->rctx.pgtable)) { + ivpu_err(vdev, "Failed to allocate root page table for reserved context\n"); + ret = -ENOMEM; + goto unlock; + } + + ret = ivpu_mmu_cd_set(vdev, vdev->rctx.id, &vdev->rctx.pgtable); + if (ret) { + ivpu_err(vdev, "Failed to set context descriptor for reserved context\n"); + goto unlock; + } + +unlock: + mutex_unlock(&vdev->rctx.lock); + return ret; } void ivpu_mmu_reserved_context_fini(struct ivpu_device *vdev) { - return ivpu_mmu_user_context_fini(vdev, &vdev->rctx); + ivpu_mmu_cd_clear(vdev, vdev->rctx.id); + ivpu_mmu_context_fini(vdev, &vdev->rctx); } void ivpu_mmu_user_context_mark_invalid(struct ivpu_device *vdev, u32 ssid) @@ -603,36 +644,3 @@ void ivpu_mmu_user_context_mark_invalid(struct ivpu_device *vdev, u32 ssid) xa_unlock(&vdev->context_xa); } - -int ivpu_mmu_user_context_init(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx, u32 ctx_id) -{ - int ret; - - drm_WARN_ON(&vdev->drm, !ctx_id); - - ret = ivpu_mmu_context_init(vdev, ctx, ctx_id); - if (ret) { - ivpu_err(vdev, "Failed to initialize context %u: %d\n", ctx_id, ret); - return ret; - } - - ret = ivpu_mmu_set_pgtable(vdev, ctx_id, &ctx->pgtable); - if (ret) { - ivpu_err(vdev, "Failed to set page table for context %u: %d\n", ctx_id, ret); - goto err_context_fini; - } - - return 0; - -err_context_fini: - ivpu_mmu_context_fini(vdev, ctx); - return ret; -} - -void ivpu_mmu_user_context_fini(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx) -{ - drm_WARN_ON(&vdev->drm, !ctx->id); - - ivpu_mmu_clear_pgtable(vdev, ctx->id); - ivpu_mmu_context_fini(vdev, ctx); -} diff --git a/drivers/accel/ivpu/ivpu_mmu_context.h b/drivers/accel/ivpu/ivpu_mmu_context.h index 7f9aaf3d10c2f7a567329fa153eba8c623d6aa51..8042fc0670622bca4529d312933ee1521db99279 100644 --- a/drivers/accel/ivpu/ivpu_mmu_context.h +++ b/drivers/accel/ivpu/ivpu_mmu_context.h @@ -23,19 +23,20 @@ struct ivpu_mmu_pgtable { }; struct ivpu_mmu_context { - struct mutex lock; /* Protects: mm, pgtable */ + struct mutex lock; /* Protects: mm, pgtable, is_cd_valid */ struct drm_mm mm; struct ivpu_mmu_pgtable pgtable; + bool is_cd_valid; u32 id; }; -int ivpu_mmu_global_context_init(struct ivpu_device *vdev); +void ivpu_mmu_context_init(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx, u32 context_id); +void ivpu_mmu_context_fini(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx); +void ivpu_mmu_global_context_init(struct ivpu_device *vdev); void ivpu_mmu_global_context_fini(struct ivpu_device *vdev); int ivpu_mmu_reserved_context_init(struct ivpu_device *vdev); void ivpu_mmu_reserved_context_fini(struct ivpu_device *vdev); -int ivpu_mmu_user_context_init(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx, u32 ctx_id); -void ivpu_mmu_user_context_fini(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx); void ivpu_mmu_user_context_mark_invalid(struct ivpu_device *vdev, u32 ssid); int ivpu_mmu_context_insert_node(struct ivpu_mmu_context *ctx, const struct ivpu_addr_range *range, diff --git a/drivers/accel/ivpu/ivpu_ms.c b/drivers/accel/ivpu/ivpu_ms.c index 2f9d37f5c208a921ae33b55e467359dc5bda2f38..ffe7b10f8a767b9f67ec336a88adb217a2dd0169 100644 --- a/drivers/accel/ivpu/ivpu_ms.c +++ b/drivers/accel/ivpu/ivpu_ms.c @@ -11,7 +11,7 @@ #include "ivpu_ms.h" #include "ivpu_pm.h" -#define MS_INFO_BUFFER_SIZE SZ_16K +#define MS_INFO_BUFFER_SIZE SZ_64K #define MS_NUM_BUFFERS 2 #define MS_READ_PERIOD_MULTIPLIER 2 #define MS_MIN_SAMPLE_PERIOD_NS 1000000 diff --git a/drivers/accel/ivpu/ivpu_pm.c b/drivers/accel/ivpu/ivpu_pm.c index 59d3170f5e3541b76cff63ffa7b411f02e81ced4..dbc0711e28d138d5a6d1617e58abb6d8163eca07 100644 --- a/drivers/accel/ivpu/ivpu_pm.c +++ b/drivers/accel/ivpu/ivpu_pm.c @@ -9,21 +9,25 @@ #include #include -#include "vpu_boot_api.h" +#include "ivpu_coredump.h" #include "ivpu_drv.h" -#include "ivpu_hw.h" #include "ivpu_fw.h" #include "ivpu_fw_log.h" +#include "ivpu_hw.h" #include "ivpu_ipc.h" #include "ivpu_job.h" #include "ivpu_jsm_msg.h" #include "ivpu_mmu.h" #include "ivpu_ms.h" #include "ivpu_pm.h" +#include "ivpu_trace.h" +#include "vpu_boot_api.h" static bool ivpu_disable_recovery; +#if IS_ENABLED(CONFIG_DRM_ACCEL_IVPU_DEBUG) module_param_named_unsafe(disable_recovery, ivpu_disable_recovery, bool, 0644); MODULE_PARM_DESC(disable_recovery, "Disables recovery when NPU hang is detected"); +#endif static unsigned long ivpu_tdr_timeout_ms; module_param_named(tdr_timeout_ms, ivpu_tdr_timeout_ms, ulong, 0644); @@ -37,6 +41,7 @@ static void ivpu_pm_prepare_cold_boot(struct ivpu_device *vdev) ivpu_cmdq_reset_all_contexts(vdev); ivpu_ipc_reset(vdev); + ivpu_fw_log_reset(vdev); ivpu_fw_load(vdev); fw->entry_point = fw->cold_boot_entry_point; } @@ -123,7 +128,8 @@ static void ivpu_pm_recovery_work(struct work_struct *work) if (ret) ivpu_err(vdev, "Failed to resume NPU: %d\n", ret); - ivpu_fw_log_dump(vdev); + ivpu_jsm_state_dump(vdev); + ivpu_dev_coredump(vdev); atomic_inc(&vdev->pm->reset_counter); atomic_set(&vdev->pm->reset_pending, 1); @@ -195,6 +201,7 @@ int ivpu_pm_suspend_cb(struct device *dev) struct ivpu_device *vdev = to_ivpu_device(drm); unsigned long timeout; + trace_pm("suspend"); ivpu_dbg(vdev, PM, "Suspend..\n"); timeout = jiffies + msecs_to_jiffies(vdev->timeout.tdr); @@ -212,6 +219,7 @@ int ivpu_pm_suspend_cb(struct device *dev) ivpu_pm_prepare_warm_boot(vdev); ivpu_dbg(vdev, PM, "Suspend done.\n"); + trace_pm("suspend done"); return 0; } @@ -222,6 +230,7 @@ int ivpu_pm_resume_cb(struct device *dev) struct ivpu_device *vdev = to_ivpu_device(drm); int ret; + trace_pm("resume"); ivpu_dbg(vdev, PM, "Resume..\n"); ret = ivpu_resume(vdev); @@ -229,6 +238,7 @@ int ivpu_pm_resume_cb(struct device *dev) ivpu_err(vdev, "Failed to resume: %d\n", ret); ivpu_dbg(vdev, PM, "Resume done.\n"); + trace_pm("resume done"); return ret; } @@ -243,6 +253,7 @@ int ivpu_pm_runtime_suspend_cb(struct device *dev) drm_WARN_ON(&vdev->drm, !xa_empty(&vdev->submitted_jobs_xa)); drm_WARN_ON(&vdev->drm, work_pending(&vdev->pm->recovery_work)); + trace_pm("runtime suspend"); ivpu_dbg(vdev, PM, "Runtime suspend..\n"); ivpu_mmu_disable(vdev); @@ -262,13 +273,14 @@ int ivpu_pm_runtime_suspend_cb(struct device *dev) if (!is_idle || ret_d0i3) { ivpu_err(vdev, "Forcing cold boot due to previous errors\n"); atomic_inc(&vdev->pm->reset_counter); - ivpu_fw_log_dump(vdev); + ivpu_dev_coredump(vdev); ivpu_pm_prepare_cold_boot(vdev); } else { ivpu_pm_prepare_warm_boot(vdev); } ivpu_dbg(vdev, PM, "Runtime suspend done.\n"); + trace_pm("runtime suspend done"); return 0; } @@ -279,6 +291,7 @@ int ivpu_pm_runtime_resume_cb(struct device *dev) struct ivpu_device *vdev = to_ivpu_device(drm); int ret; + trace_pm("runtime resume"); ivpu_dbg(vdev, PM, "Runtime resume..\n"); ret = ivpu_resume(vdev); @@ -286,6 +299,7 @@ int ivpu_pm_runtime_resume_cb(struct device *dev) ivpu_err(vdev, "Failed to set RESUME state: %d\n", ret); ivpu_dbg(vdev, PM, "Runtime resume done.\n"); + trace_pm("runtime resume done"); return ret; } @@ -411,7 +425,7 @@ int ivpu_pm_dct_enable(struct ivpu_device *vdev, u8 active_percent) ret = ivpu_jsm_dct_enable(vdev, active_us, inactive_us); if (ret) { - ivpu_err_ratelimited(vdev, "Filed to enable DCT: %d\n", ret); + ivpu_err_ratelimited(vdev, "Failed to enable DCT: %d\n", ret); return ret; } @@ -428,7 +442,7 @@ int ivpu_pm_dct_disable(struct ivpu_device *vdev) ret = ivpu_jsm_dct_disable(vdev); if (ret) { - ivpu_err_ratelimited(vdev, "Filed to disable DCT: %d\n", ret); + ivpu_err_ratelimited(vdev, "Failed to disable DCT: %d\n", ret); return ret; } diff --git a/drivers/accel/ivpu/ivpu_sysfs.c b/drivers/accel/ivpu/ivpu_sysfs.c index 913669f1786e86c7028d9556469a33b37e5df6ba..616477fc17fa071c5a3168de4e151d08c9bede8d 100644 --- a/drivers/accel/ivpu/ivpu_sysfs.c +++ b/drivers/accel/ivpu/ivpu_sysfs.c @@ -6,6 +6,8 @@ #include #include +#include "ivpu_drv.h" +#include "ivpu_fw.h" #include "ivpu_hw.h" #include "ivpu_sysfs.h" @@ -39,8 +41,30 @@ npu_busy_time_us_show(struct device *dev, struct device_attribute *attr, char *b static DEVICE_ATTR_RO(npu_busy_time_us); +/** + * DOC: sched_mode + * + * The sched_mode is used to report current NPU scheduling mode. + * + * It returns following strings: + * - "HW" - Hardware Scheduler mode + * - "OS" - Operating System Scheduler mode + * + */ +static ssize_t +sched_mode_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct drm_device *drm = dev_get_drvdata(dev); + struct ivpu_device *vdev = to_ivpu_device(drm); + + return sysfs_emit(buf, "%s\n", vdev->fw->sched_mode ? "HW" : "OS"); +} + +static DEVICE_ATTR_RO(sched_mode); + static struct attribute *ivpu_dev_attrs[] = { &dev_attr_npu_busy_time_us.attr, + &dev_attr_sched_mode.attr, NULL, }; diff --git a/drivers/accel/ivpu/ivpu_trace.h b/drivers/accel/ivpu/ivpu_trace.h new file mode 100644 index 0000000000000000000000000000000000000000..eb792038e7010cdc4f5ff907028b7421f1f377e2 --- /dev/null +++ b/drivers/accel/ivpu/ivpu_trace.h @@ -0,0 +1,73 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2020-2024 Intel Corporation + */ + +#if !defined(__IVPU_TRACE_H__) || defined(TRACE_HEADER_MULTI_READ) +#define __IVPU_TRACE_H__ + +#include +#include "ivpu_drv.h" +#include "ivpu_job.h" +#include "vpu_jsm_api.h" +#include "ivpu_jsm_msg.h" +#include "ivpu_ipc.h" + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM vpu +#define TRACE_INCLUDE_FILE ivpu_trace + +TRACE_EVENT(pm, + TP_PROTO(const char *event), + TP_ARGS(event), + TP_STRUCT__entry(__field(const char *, event)), + TP_fast_assign(__entry->event = event;), + TP_printk("%s", __entry->event) +); + +TRACE_EVENT(job, + TP_PROTO(const char *event, struct ivpu_job *job), + TP_ARGS(event, job), + TP_STRUCT__entry(__field(const char *, event) + __field(u32, ctx_id) + __field(u32, engine_id) + __field(u32, job_id) + ), + TP_fast_assign(__entry->event = event; + __entry->ctx_id = job->file_priv->ctx.id; + __entry->engine_id = job->engine_idx; + __entry->job_id = job->job_id;), + TP_printk("%s context:%d engine:%d job:%d", + __entry->event, + __entry->ctx_id, + __entry->engine_id, + __entry->job_id) +); + +TRACE_EVENT(jsm, + TP_PROTO(const char *event, struct vpu_jsm_msg *msg), + TP_ARGS(event, msg), + TP_STRUCT__entry(__field(const char *, event) + __field(const char *, type) + __field(enum vpu_ipc_msg_status, status) + __field(u32, request_id) + __field(u32, result) + ), + TP_fast_assign(__entry->event = event; + __entry->type = ivpu_jsm_msg_type_to_str(msg->type); + __entry->status = msg->status; + __entry->request_id = msg->request_id; + __entry->result = msg->result;), + TP_printk("%s type:%s, status:%#x, id:%#x, result:%#x", + __entry->event, + __entry->type, + __entry->status, + __entry->request_id, + __entry->result) +); + +#endif /* __IVPU_TRACE_H__ */ + +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . +#include diff --git a/drivers/accel/ivpu/ivpu_trace_points.c b/drivers/accel/ivpu/ivpu_trace_points.c new file mode 100644 index 0000000000000000000000000000000000000000..f8fb99de0de32a517e8e0928c64352379da35e40 --- /dev/null +++ b/drivers/accel/ivpu/ivpu_trace_points.c @@ -0,0 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2020-2024 Intel Corporation + */ + +#ifndef __CHECKER__ +#define CREATE_TRACE_POINTS +#include "ivpu_trace.h" +#endif diff --git a/drivers/accel/ivpu/vpu_boot_api.h b/drivers/accel/ivpu/vpu_boot_api.h index 82954b91b7481c26bd6d2a68020cd512ee4fdee7..908e68ea1c39c24359138ed190ee672d0194431b 100644 --- a/drivers/accel/ivpu/vpu_boot_api.h +++ b/drivers/accel/ivpu/vpu_boot_api.h @@ -1,14 +1,13 @@ /* SPDX-License-Identifier: MIT */ /* - * Copyright (c) 2020-2023, Intel Corporation. + * Copyright (c) 2020-2024, Intel Corporation. */ #ifndef VPU_BOOT_API_H #define VPU_BOOT_API_H /* - * =========== FW API version information beginning ================ - * The bellow values will be used to construct the version info this way: + * The below values will be used to construct the version info this way: * fw_bin_header->api_version[VPU_BOOT_API_VER_ID] = (VPU_BOOT_API_VER_MAJOR << 16) | * VPU_BOOT_API_VER_MINOR; * VPU_BOOT_API_VER_PATCH will be ignored. KMD and compatibility is not affected if this changes @@ -27,19 +26,18 @@ * Minor version changes when API backward compatibility is preserved. * Resets to 0 if Major version is incremented. */ -#define VPU_BOOT_API_VER_MINOR 24 +#define VPU_BOOT_API_VER_MINOR 26 /* * API header changed (field names, documentation, formatting) but API itself has not been changed */ -#define VPU_BOOT_API_VER_PATCH 0 +#define VPU_BOOT_API_VER_PATCH 3 /* * Index in the API version table * Must be unique for each API */ #define VPU_BOOT_API_VER_INDEX 0 -/* ------------ FW API version information end ---------------------*/ #pragma pack(push, 4) @@ -164,8 +162,6 @@ enum vpu_trace_destination { /* VPU 30xx HW component IDs are sequential, so define first and last IDs. */ #define VPU_TRACE_PROC_BIT_30XX_FIRST VPU_TRACE_PROC_BIT_LRT #define VPU_TRACE_PROC_BIT_30XX_LAST VPU_TRACE_PROC_BIT_SHV_15 -#define VPU_TRACE_PROC_BIT_KMB_FIRST VPU_TRACE_PROC_BIT_30XX_FIRST -#define VPU_TRACE_PROC_BIT_KMB_LAST VPU_TRACE_PROC_BIT_30XX_LAST struct vpu_boot_l2_cache_config { u8 use; @@ -199,6 +195,17 @@ struct vpu_warm_boot_section { */ #define POWER_PROFILE_SURVIVABILITY 0x1 +/** + * Enum for dvfs_mode boot param. + */ +enum vpu_governor { + VPU_GOV_DEFAULT = 0, /* Default Governor for the system */ + VPU_GOV_MAX_PERFORMANCE = 1, /* Maximum performance governor */ + VPU_GOV_ON_DEMAND = 2, /* On Demand frequency control governor */ + VPU_GOV_POWER_SAVE = 3, /* Power save governor */ + VPU_GOV_ON_DEMAND_PRIORITY_AWARE = 4 /* On Demand priority based governor */ +}; + struct vpu_boot_params { u32 magic; u32 vpu_id; @@ -301,7 +308,14 @@ struct vpu_boot_params { u32 temp_sensor_period_ms; /** PLL ratio for efficient clock frequency */ u32 pn_freq_pll_ratio; - /** DVFS Mode: Default: 0, Max Performance: 1, On Demand: 2, Power Save: 3 */ + /** + * DVFS Mode: + * 0 - Default, DVFS mode selected by the firmware + * 1 - Max Performance + * 2 - On Demand + * 3 - Power Save + * 4 - On Demand Priority Aware + */ u32 dvfs_mode; /** * Depending on DVFS Mode: @@ -332,8 +346,8 @@ struct vpu_boot_params { u64 d0i3_entry_vpu_ts; /* * The system time of the host operating system in microseconds. - * E.g the number of microseconds since 1st of January 1970, or whatever date the - * host operating system uses to maintain system time. + * E.g the number of microseconds since 1st of January 1970, or whatever + * date the host operating system uses to maintain system time. * This value will be used to track system time on the VPU. * The KMD is required to update this value on every VPU reset. */ @@ -382,10 +396,7 @@ struct vpu_boot_params { u32 pad6[734]; }; -/* - * Magic numbers set between host and vpu to detect corruptio of tracing init - */ - +/* Magic numbers set between host and vpu to detect corruption of tracing init */ #define VPU_TRACING_BUFFER_CANARY (0xCAFECAFE) /* Tracing buffer message format definitions */ @@ -405,7 +416,9 @@ struct vpu_tracing_buffer_header { u32 host_canary_start; /* offset from start of buffer for trace entries */ u32 read_index; - u32 pad_to_cache_line_size_0[14]; + /* keeps track of wrapping on the reader side */ + u32 read_wrap_count; + u32 pad_to_cache_line_size_0[13]; /* End of first cache line */ /** diff --git a/drivers/accel/ivpu/vpu_jsm_api.h b/drivers/accel/ivpu/vpu_jsm_api.h index 33f462b1a25d88879a44582c3ceb106c4e8d0ef6..7215c144158cbd6c3577cee95b6a7163e8c74786 100644 --- a/drivers/accel/ivpu/vpu_jsm_api.h +++ b/drivers/accel/ivpu/vpu_jsm_api.h @@ -22,7 +22,7 @@ /* * Minor version changes when API backward compatibility is preserved. */ -#define VPU_JSM_API_VER_MINOR 16 +#define VPU_JSM_API_VER_MINOR 25 /* * API header changed (field names, documentation, formatting) but API itself has not been changed @@ -36,7 +36,7 @@ /* * Number of Priority Bands for Hardware Scheduling - * Bands: RealTime, Focus, Normal, Idle + * Bands: Idle(0), Normal(1), Focus(2), RealTime(3) */ #define VPU_HWS_NUM_PRIORITY_BANDS 4 @@ -74,6 +74,7 @@ #define VPU_JSM_STATUS_MVNCI_INTERNAL_ERROR 0xCU /* Job status returned when the job was preempted mid-inference */ #define VPU_JSM_STATUS_PREEMPTED_MID_INFERENCE 0xDU +#define VPU_JSM_STATUS_MVNCI_CONTEXT_VIOLATION_HW 0xEU /* * Host <-> VPU IPC channels. @@ -86,18 +87,58 @@ /* * Job flags bit masks. */ -#define VPU_JOB_FLAGS_NULL_SUBMISSION_MASK 0x00000001 -#define VPU_JOB_FLAGS_PRIVATE_DATA_MASK 0xFF000000 +enum { + /* + * Null submission mask. + * When set, batch buffer's commands are not processed but returned as + * successful immediately, except fences and timestamps. + * When cleared, batch buffer's commands are processed normally. + * Used for testing and profiling purposes. + */ + VPU_JOB_FLAGS_NULL_SUBMISSION_MASK = (1 << 0U), + /* + * Inline command mask. + * When set, the object in job queue is an inline command (see struct vpu_inline_cmd below). + * When cleared, the object in job queue is a job (see struct vpu_job_queue_entry below). + */ + VPU_JOB_FLAGS_INLINE_CMD_MASK = (1 << 1U), + /* + * VPU private data mask. + * Reserved for the VPU to store private data about the job (or inline command) + * while being processed. + */ + VPU_JOB_FLAGS_PRIVATE_DATA_MASK = 0xFFFF0000U +}; /* - * Sizes of the reserved areas in jobs, in bytes. + * Job queue flags bit masks. */ -#define VPU_JOB_RESERVED_BYTES 8 +enum { + /* + * No job done notification mask. + * When set, indicates that no job done notification should be sent for any + * job from this queue. When cleared, indicates that job done notification + * should be sent for every job completed from this queue. + */ + VPU_JOB_QUEUE_FLAGS_NO_JOB_DONE_MASK = (1 << 0U), + /* + * Native fence usage mask. + * When set, indicates that job queue uses native fences (as inline commands + * in job queue). Such queues may also use legacy fences (as commands in batch buffers). + * When cleared, indicates the job queue only uses legacy fences. + * NOTE: For queues using native fences, VPU expects that all jobs in the queue + * are immediately followed by an inline command object. This object is expected + * to be a fence signal command in most cases, but can also be a NOP in case the host + * does not need per-job fence signalling. Other inline commands objects can be + * inserted between "job and inline command" pairs. + */ + VPU_JOB_QUEUE_FLAGS_USE_NATIVE_FENCE_MASK = (1 << 1U), -/* - * Sizes of the reserved areas in job queues, in bytes. - */ -#define VPU_JOB_QUEUE_RESERVED_BYTES 52 + /* + * Enable turbo mode for testing NPU performance; not recommended for regular usage. + */ + VPU_JOB_QUEUE_FLAGS_TURBO_MODE = (1 << 2U) +}; /* * Max length (including trailing NULL char) of trace entity name (e.g., the @@ -140,24 +181,113 @@ */ #define VPU_HWS_INVALID_CMDQ_HANDLE 0ULL +/* + * Inline commands types. + */ +/* + * NOP. + * VPU does nothing other than consuming the inline command object. + */ +#define VPU_INLINE_CMD_TYPE_NOP 0x0 +/* + * Fence wait. + * VPU waits for the fence current value to reach monitored value. + * Fence wait operations are executed upon job dispatching. While waiting for + * the fence to be satisfied, VPU blocks fetching of the next objects in the queue. + * Jobs present in the queue prior to the fence wait object may be processed + * concurrently. + */ +#define VPU_INLINE_CMD_TYPE_FENCE_WAIT 0x1 +/* + * Fence signal. + * VPU sets the fence current value to the provided value. If new current value + * is equal to or higher than monitored value, VPU sends fence signalled notification + * to the host. Fence signal operations are executed upon completion of all the jobs + * present in the queue prior to them, and in-order relative to each other in the queue. + * But jobs in-between them may be processed concurrently and may complete out-of-order. + */ +#define VPU_INLINE_CMD_TYPE_FENCE_SIGNAL 0x2 + +/* + * Job scheduling priority bands for both hardware scheduling and OS scheduling. + */ +enum vpu_job_scheduling_priority_band { + VPU_JOB_SCHEDULING_PRIORITY_BAND_IDLE = 0, + VPU_JOB_SCHEDULING_PRIORITY_BAND_NORMAL = 1, + VPU_JOB_SCHEDULING_PRIORITY_BAND_FOCUS = 2, + VPU_JOB_SCHEDULING_PRIORITY_BAND_REALTIME = 3, + VPU_JOB_SCHEDULING_PRIORITY_BAND_COUNT = 4, +}; + /* * Job format. + * Jobs defines the actual workloads to be executed by a given engine. */ struct vpu_job_queue_entry { - u64 batch_buf_addr; /**< Address of VPU commands batch buffer */ - u32 job_id; /**< Job ID */ - u32 flags; /**< Flags bit field, see VPU_JOB_FLAGS_* above */ - u64 root_page_table_addr; /**< Address of root page table to use for this job */ - u64 root_page_table_update_counter; /**< Page tables update events counter */ - u64 primary_preempt_buf_addr; + /**< Address of VPU commands batch buffer */ + u64 batch_buf_addr; + /**< Job ID */ + u32 job_id; + /**< Flags bit field, see VPU_JOB_FLAGS_* above */ + u32 flags; + /** + * Doorbell ring timestamp taken by KMD from SoC's global system clock, in + * microseconds. NPU can convert this value to its own fixed clock's timebase, + * to match other profiling timestamps. + */ + u64 doorbell_timestamp; + /**< Extra id for job tracking, used only in the firmware perf traces */ + u64 host_tracking_id; /**< Address of the primary preemption buffer to use for this job */ - u32 primary_preempt_buf_size; + u64 primary_preempt_buf_addr; /**< Size of the primary preemption buffer to use for this job */ - u32 secondary_preempt_buf_size; + u32 primary_preempt_buf_size; /**< Size of secondary preemption buffer to use for this job */ - u64 secondary_preempt_buf_addr; + u32 secondary_preempt_buf_size; /**< Address of secondary preemption buffer to use for this job */ - u8 reserved_0[VPU_JOB_RESERVED_BYTES]; + u64 secondary_preempt_buf_addr; + u64 reserved_0; +}; + +/* + * Inline command format. + * Inline commands are the commands executed at scheduler level (typically, + * synchronization directives). Inline command and job objects must be of + * the same size and have flags field at same offset. + */ +struct vpu_inline_cmd { + u64 reserved_0; + /* Inline command type, see VPU_INLINE_CMD_TYPE_* defines. */ + u32 type; + /* Flags bit field, see VPU_JOB_FLAGS_* above. */ + u32 flags; + /* Inline command payload. Depends on inline command type. */ + union { + /* Fence (wait and signal) commands' payload. */ + struct { + /* Fence object handle. */ + u64 fence_handle; + /* User VA of the current fence value. */ + u64 current_value_va; + /* User VA of the monitored fence value (read-only). */ + u64 monitored_value_va; + /* Value to wait for or write in fence location. */ + u64 value; + /* User VA of the log buffer in which to add log entry on completion. */ + u64 log_buffer_va; + } fence; + /* Other commands do not have a payload. */ + /* Payload definition for future inline commands can be inserted here. */ + u64 reserved_1[6]; + } payload; +}; + +/* + * Job queue slots can be populated either with job objects or inline command objects. + */ +union vpu_jobq_slot { + struct vpu_job_queue_entry job; + struct vpu_inline_cmd inline_cmd; }; /* @@ -167,7 +297,21 @@ struct vpu_job_queue_header { u32 engine_idx; u32 head; u32 tail; - u8 reserved_0[VPU_JOB_QUEUE_RESERVED_BYTES]; + u32 flags; + /* Set to 1 to indicate priority_band field is valid */ + u32 priority_band_valid; + /* + * Priority for the work of this job queue, valid only if the HWS is NOT used + * and the `priority_band_valid` is set to 1. It is applied only during + * the VPU_JSM_MSG_REGISTER_DB message processing. + * The device firmware might use the `priority_band` to optimize the power + * management logic, but it will not affect the order of jobs. + * Available priority bands: @see enum vpu_job_scheduling_priority_band + */ + u32 priority_band; + /* Inside realtime band assigns a further priority, limited to 0..31 range */ + u32 realtime_priority_level; + u32 reserved_0[9]; }; /* @@ -175,7 +319,7 @@ struct vpu_job_queue_header { */ struct vpu_job_queue { struct vpu_job_queue_header header; - struct vpu_job_queue_entry job[]; + union vpu_jobq_slot slot[]; }; /** @@ -197,9 +341,7 @@ enum vpu_trace_entity_type { struct vpu_hws_log_buffer_header { /* Written by VPU after adding a log entry. Initialised by host to 0. */ u32 first_free_entry_index; - /* Incremented by VPU every time the VPU overwrites the 0th entry; - * initialised by host to 0. - */ + /* Incremented by VPU every time the VPU writes the 0th entry; initialised by host to 0. */ u32 wraparound_count; /* * This is the number of buffers that can be stored in the log buffer provided by the host. @@ -230,14 +372,80 @@ struct vpu_hws_log_buffer_entry { u64 operation_data[2]; }; +/* Native fence log buffer types. */ +enum vpu_hws_native_fence_log_type { + VPU_HWS_NATIVE_FENCE_LOG_TYPE_WAITS = 1, + VPU_HWS_NATIVE_FENCE_LOG_TYPE_SIGNALS = 2 +}; + +/* HWS native fence log buffer header. */ +struct vpu_hws_native_fence_log_header { + union { + struct { + /* Index of the first free entry in buffer. */ + u32 first_free_entry_idx; + /* Incremented each time NPU wraps around the buffer to write next entry. */ + u32 wraparound_count; + }; + /* Field allowing atomic update of both fields above. */ + u64 atomic_wraparound_and_entry_idx; + }; + /* Log buffer type, see enum vpu_hws_native_fence_log_type. */ + u64 type; + /* Allocated number of entries in the log buffer. */ + u64 entry_nb; + u64 reserved[2]; +}; + +/* Native fence log operation types. */ +enum vpu_hws_native_fence_log_op { + VPU_HWS_NATIVE_FENCE_LOG_OP_SIGNAL_EXECUTED = 0, + VPU_HWS_NATIVE_FENCE_LOG_OP_WAIT_UNBLOCKED = 1 +}; + +/* HWS native fence log entry. */ +struct vpu_hws_native_fence_log_entry { + /* Newly signaled/unblocked fence value. */ + u64 fence_value; + /* Native fence object handle to which this operation belongs. */ + u64 fence_handle; + /* Operation type, see enum vpu_hws_native_fence_log_op. */ + u64 op_type; + u64 reserved_0; + /* + * VPU_HWS_NATIVE_FENCE_LOG_OP_WAIT_UNBLOCKED only: Timestamp at which fence + * wait was started (in NPU SysTime). + */ + u64 fence_wait_start_ts; + u64 reserved_1; + /* Timestamp at which fence operation was completed (in NPU SysTime). */ + u64 fence_end_ts; +}; + +/* Native fence log buffer. */ +struct vpu_hws_native_fence_log_buffer { + struct vpu_hws_native_fence_log_header header; + struct vpu_hws_native_fence_log_entry entry[]; +}; + /* * Host <-> VPU IPC messages types. */ enum vpu_ipc_msg_type { VPU_JSM_MSG_UNKNOWN = 0xFFFFFFFF, + /* IPC Host -> Device, Async commands */ VPU_JSM_MSG_ASYNC_CMD = 0x1100, VPU_JSM_MSG_ENGINE_RESET = VPU_JSM_MSG_ASYNC_CMD, + /** + * Preempt engine. The NPU stops (preempts) all the jobs currently + * executing on the target engine making the engine become idle and ready to + * execute new jobs. + * NOTE: The NPU does not remove unstarted jobs (if any) from job queues of + * the target engine, but it stops processing them (until the queue doorbell + * is rung again); the host is responsible to reset the job queue, either + * after preemption or when resubmitting jobs to the queue. + */ VPU_JSM_MSG_ENGINE_PREEMPT = 0x1101, VPU_JSM_MSG_REGISTER_DB = 0x1102, VPU_JSM_MSG_UNREGISTER_DB = 0x1103, @@ -323,9 +531,10 @@ enum vpu_ipc_msg_type { * NOTE: Please introduce new ASYNC commands before this one. * */ VPU_JSM_MSG_STATE_DUMP = 0x11FF, + /* IPC Host -> Device, General commands */ VPU_JSM_MSG_GENERAL_CMD = 0x1200, - VPU_JSM_MSG_BLOB_DEINIT = VPU_JSM_MSG_GENERAL_CMD, + VPU_JSM_MSG_BLOB_DEINIT_DEPRECATED = VPU_JSM_MSG_GENERAL_CMD, /** * Control dyndbg behavior by executing a dyndbg command; equivalent to * Linux command: `echo '' > /dynamic_debug/control`. @@ -335,8 +544,12 @@ enum vpu_ipc_msg_type { * Perform the save procedure for the D0i3 entry */ VPU_JSM_MSG_PWR_D0I3_ENTER = 0x1202, + /* IPC Device -> Host, Job completion */ VPU_JSM_MSG_JOB_DONE = 0x2100, + /* IPC Device -> Host, Fence signalled */ + VPU_JSM_MSG_NATIVE_FENCE_SIGNALLED = 0x2101, + /* IPC Device -> Host, Async command completion */ VPU_JSM_MSG_ASYNC_CMD_DONE = 0x2200, VPU_JSM_MSG_ENGINE_RESET_DONE = VPU_JSM_MSG_ASYNC_CMD_DONE, @@ -422,6 +635,7 @@ enum vpu_ipc_msg_type { * NOTE: Please introduce new ASYNC responses before this one. * */ VPU_JSM_MSG_STATE_DUMP_RSP = 0x22FF, + /* IPC Device -> Host, General command completion */ VPU_JSM_MSG_GENERAL_CMD_DONE = 0x2300, VPU_JSM_MSG_BLOB_DEINIT_DONE = VPU_JSM_MSG_GENERAL_CMD_DONE, @@ -600,11 +814,6 @@ struct vpu_jsm_metric_streamer_update { u64 next_buffer_size; }; -struct vpu_ipc_msg_payload_blob_deinit { - /* 64-bit unique ID for the blob to be de-initialized. */ - u64 blob_id; -}; - struct vpu_ipc_msg_payload_job_done { /* Engine to which the job was submitted. */ u32 engine_idx; @@ -622,6 +831,21 @@ struct vpu_ipc_msg_payload_job_done { u64 cmdq_id; }; +/* + * Notification message upon native fence signalling. + * @see VPU_JSM_MSG_NATIVE_FENCE_SIGNALLED + */ +struct vpu_ipc_msg_payload_native_fence_signalled { + /* Engine ID. */ + u32 engine_idx; + /* Host SSID. */ + u32 host_ssid; + /* CMDQ ID */ + u64 cmdq_id; + /* Fence object handle. */ + u64 fence_handle; +}; + struct vpu_jsm_engine_reset_context { /* Host SSID */ u32 host_ssid; @@ -700,11 +924,6 @@ struct vpu_ipc_msg_payload_get_power_level_count_done { u8 power_limit[16]; }; -struct vpu_ipc_msg_payload_blob_deinit_done { - /* 64-bit unique ID for the blob de-initialized. */ - u64 blob_id; -}; - /* HWS priority band setup request / response */ struct vpu_ipc_msg_payload_hws_priority_band_setup { /* @@ -794,7 +1013,10 @@ struct vpu_ipc_msg_payload_hws_set_context_sched_properties { u32 reserved_0; /* Command queue id */ u64 cmdq_id; - /* Priority band to assign to work of this context */ + /* + * Priority band to assign to work of this context. + * Available priority bands: @see enum vpu_job_scheduling_priority_band + */ u32 priority_band; /* Inside realtime band assigns a further priority */ u32 realtime_priority_level; @@ -869,9 +1091,7 @@ struct vpu_ipc_msg_payload_hws_set_scheduling_log { */ u64 notify_index; /* - * Enable extra events to be output to log for debug of scheduling algorithm. - * Interpreted by VPU as a boolean to enable or disable, expected values are - * 0 and 1. + * Field is now deprecated, will be removed when KMD is updated to support removal */ u32 enable_extra_events; /* Zero Padding */ @@ -1243,10 +1463,10 @@ union vpu_ipc_msg_payload { struct vpu_jsm_metric_streamer_start metric_streamer_start; struct vpu_jsm_metric_streamer_stop metric_streamer_stop; struct vpu_jsm_metric_streamer_update metric_streamer_update; - struct vpu_ipc_msg_payload_blob_deinit blob_deinit; struct vpu_ipc_msg_payload_ssid_release ssid_release; struct vpu_jsm_hws_register_db hws_register_db; struct vpu_ipc_msg_payload_job_done job_done; + struct vpu_ipc_msg_payload_native_fence_signalled native_fence_signalled; struct vpu_ipc_msg_payload_engine_reset_done engine_reset_done; struct vpu_ipc_msg_payload_engine_preempt_done engine_preempt_done; struct vpu_ipc_msg_payload_register_db_done register_db_done; @@ -1254,7 +1474,6 @@ union vpu_ipc_msg_payload { struct vpu_ipc_msg_payload_query_engine_hb_done query_engine_hb_done; struct vpu_ipc_msg_payload_get_power_level_count_done get_power_level_count_done; struct vpu_jsm_metric_streamer_done metric_streamer_done; - struct vpu_ipc_msg_payload_blob_deinit_done blob_deinit_done; struct vpu_ipc_msg_payload_trace_config trace_config; struct vpu_ipc_msg_payload_trace_capability_rsp trace_capability; struct vpu_ipc_msg_payload_trace_get_name trace_get_name; diff --git a/drivers/accel/qaic/mhi_controller.c b/drivers/accel/qaic/mhi_controller.c index ada9b1eb0787e33375d659e0bd6f0ce5991e3856..8ab82e78dd94487116beca3bcf28f2a05f834af2 100644 --- a/drivers/accel/qaic/mhi_controller.c +++ b/drivers/accel/qaic/mhi_controller.c @@ -405,6 +405,38 @@ static const struct mhi_channel_config aic100_channels[] = { .auto_queue = false, .wake_capable = false, }, + { + .name = "IPCR", + .num = 24, + .num_elements = 32, + .local_elements = 0, + .event_ring = 0, + .dir = DMA_TO_DEVICE, + .ee_mask = MHI_CH_EE_AMSS, + .pollcfg = 0, + .doorbell = MHI_DB_BRST_DISABLE, + .lpm_notify = false, + .offload_channel = false, + .doorbell_mode_switch = false, + .auto_queue = false, + .wake_capable = false, + }, + { + .name = "IPCR", + .num = 25, + .num_elements = 32, + .local_elements = 0, + .event_ring = 0, + .dir = DMA_FROM_DEVICE, + .ee_mask = MHI_CH_EE_AMSS, + .pollcfg = 0, + .doorbell = MHI_DB_BRST_DISABLE, + .lpm_notify = false, + .offload_channel = false, + .doorbell_mode_switch = false, + .auto_queue = true, + .wake_capable = false, + }, }; static struct mhi_event_config aic100_events[] = { diff --git a/drivers/accel/qaic/qaic_debugfs.c b/drivers/accel/qaic/qaic_debugfs.c index 20b653d99e524a5c0d451b68b66ffcd10547377d..ba0cf2f94732cc6178abeaeab40adf6eb830ad19 100644 --- a/drivers/accel/qaic/qaic_debugfs.c +++ b/drivers/accel/qaic/qaic_debugfs.c @@ -64,20 +64,9 @@ static int bootlog_show(struct seq_file *s, void *unused) return 0; } -static int bootlog_fops_open(struct inode *inode, struct file *file) -{ - return single_open(file, bootlog_show, inode->i_private); -} - -static const struct file_operations bootlog_fops = { - .owner = THIS_MODULE, - .open = bootlog_fops_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; +DEFINE_SHOW_ATTRIBUTE(bootlog); -static int read_dbc_fifo_size(struct seq_file *s, void *unused) +static int fifo_size_show(struct seq_file *s, void *unused) { struct dma_bridge_chan *dbc = s->private; @@ -85,20 +74,9 @@ static int read_dbc_fifo_size(struct seq_file *s, void *unused) return 0; } -static int fifo_size_open(struct inode *inode, struct file *file) -{ - return single_open(file, read_dbc_fifo_size, inode->i_private); -} - -static const struct file_operations fifo_size_fops = { - .owner = THIS_MODULE, - .open = fifo_size_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; +DEFINE_SHOW_ATTRIBUTE(fifo_size); -static int read_dbc_queued(struct seq_file *s, void *unused) +static int queued_show(struct seq_file *s, void *unused) { struct dma_bridge_chan *dbc = s->private; u32 tail = 0, head = 0; @@ -115,18 +93,7 @@ static int read_dbc_queued(struct seq_file *s, void *unused) return 0; } -static int queued_open(struct inode *inode, struct file *file) -{ - return single_open(file, read_dbc_queued, inode->i_private); -} - -static const struct file_operations queued_fops = { - .owner = THIS_MODULE, - .open = queued_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; +DEFINE_SHOW_ATTRIBUTE(queued); void qaic_debugfs_init(struct qaic_drm_device *qddev) { diff --git a/drivers/accel/qaic/qaic_drv.c b/drivers/accel/qaic/qaic_drv.c index bf10156c334e7144e7dcb7277a4bd26fb75d3dc3..3575e0c984d69f84baab6b03cb7b954741db1fab 100644 --- a/drivers/accel/qaic/qaic_drv.c +++ b/drivers/accel/qaic/qaic_drv.c @@ -34,6 +34,7 @@ MODULE_IMPORT_NS(DMA_BUF); +#define PCI_DEV_AIC080 0xa080 #define PCI_DEV_AIC100 0xa100 #define QAIC_NAME "qaic" #define QAIC_DESC "Qualcomm Cloud AI Accelerators" @@ -53,12 +54,12 @@ static void qaicm_wq_release(struct drm_device *dev, void *res) destroy_workqueue(wq); } -static struct workqueue_struct *qaicm_wq_init(struct drm_device *dev, const char *fmt) +static struct workqueue_struct *qaicm_wq_init(struct drm_device *dev, const char *name) { struct workqueue_struct *wq; int ret; - wq = alloc_workqueue(fmt, WQ_UNBOUND, 0); + wq = alloc_workqueue("%s", WQ_UNBOUND, 0, name); if (!wq) return ERR_PTR(-ENOMEM); ret = drmm_add_action_or_reset(dev, qaicm_wq_release, wq); @@ -365,7 +366,7 @@ static struct qaic_device *create_qdev(struct pci_dev *pdev, const struct pci_de return NULL; qdev->dev_state = QAIC_OFFLINE; - if (id->device == PCI_DEV_AIC100) { + if (id->device == PCI_DEV_AIC080 || id->device == PCI_DEV_AIC100) { qdev->num_dbc = 16; qdev->dbc = devm_kcalloc(dev, qdev->num_dbc, sizeof(*qdev->dbc), GFP_KERNEL); if (!qdev->dbc) @@ -607,6 +608,7 @@ static struct mhi_driver qaic_mhi_driver = { }; static const struct pci_device_id qaic_ids[] = { + { PCI_DEVICE(PCI_VENDOR_ID_QCOM, PCI_DEV_AIC080), }, { PCI_DEVICE(PCI_VENDOR_ID_QCOM, PCI_DEV_AIC100), }, { } }; diff --git a/drivers/accel/qaic/sahara.c b/drivers/accel/qaic/sahara.c index bf94bbab6be5a1507626fa9ccf78ab44ccbe3c8f..6d772143d6125656025ddae591c11e3ad873f610 100644 --- a/drivers/accel/qaic/sahara.c +++ b/drivers/accel/qaic/sahara.c @@ -2,6 +2,7 @@ /* Copyright (c) 2024 Qualcomm Innovation Center, Inc. All rights reserved. */ +#include #include #include #include @@ -9,6 +10,7 @@ #include #include #include +#include #include #include "sahara.h" @@ -36,12 +38,14 @@ #define SAHARA_PACKET_MAX_SIZE 0xffffU /* MHI_MAX_MTU */ #define SAHARA_TRANSFER_MAX_SIZE 0x80000 +#define SAHARA_READ_MAX_SIZE 0xfff0U /* Avoid unaligned requests */ #define SAHARA_NUM_TX_BUF DIV_ROUND_UP(SAHARA_TRANSFER_MAX_SIZE,\ SAHARA_PACKET_MAX_SIZE) #define SAHARA_IMAGE_ID_NONE U32_MAX #define SAHARA_VERSION 2 #define SAHARA_SUCCESS 0 +#define SAHARA_TABLE_ENTRY_STR_LEN 20 #define SAHARA_MODE_IMAGE_TX_PENDING 0x0 #define SAHARA_MODE_IMAGE_TX_COMPLETE 0x1 @@ -53,6 +57,8 @@ #define SAHARA_END_OF_IMAGE_LENGTH 0x10 #define SAHARA_DONE_LENGTH 0x8 #define SAHARA_RESET_LENGTH 0x8 +#define SAHARA_MEM_DEBUG64_LENGTH 0x18 +#define SAHARA_MEM_READ64_LENGTH 0x18 struct sahara_packet { __le32 cmd; @@ -80,18 +86,95 @@ struct sahara_packet { __le32 image; __le32 status; } end_of_image; + struct { + __le64 table_address; + __le64 table_length; + } memory_debug64; + struct { + __le64 memory_address; + __le64 memory_length; + } memory_read64; }; }; +struct sahara_debug_table_entry64 { + __le64 type; + __le64 address; + __le64 length; + char description[SAHARA_TABLE_ENTRY_STR_LEN]; + char filename[SAHARA_TABLE_ENTRY_STR_LEN]; +}; + +struct sahara_dump_table_entry { + u64 type; + u64 address; + u64 length; + char description[SAHARA_TABLE_ENTRY_STR_LEN]; + char filename[SAHARA_TABLE_ENTRY_STR_LEN]; +}; + +#define SAHARA_DUMP_V1_MAGIC 0x1234567890abcdef +#define SAHARA_DUMP_V1_VER 1 +struct sahara_memory_dump_meta_v1 { + u64 magic; + u64 version; + u64 dump_size; + u64 table_size; +}; + +/* + * Layout of crashdump provided to user via devcoredump + * +------------------------------------------+ + * | Crashdump Meta structure | + * | type: struct sahara_memory_dump_meta_v1 | + * +------------------------------------------+ + * | Crashdump Table | + * | type: array of struct | + * | sahara_dump_table_entry | + * | | + * | | + * +------------------------------------------+ + * | Crashdump | + * | | + * | | + * | | + * | | + * | | + * +------------------------------------------+ + * + * First is the metadata header. Userspace can use the magic number to verify + * the content type, and then check the version for the rest of the format. + * New versions should keep the magic number location/value, and version + * location, but increment the version value. + * + * For v1, the metadata lists the size of the entire dump (header + table + + * dump) and the size of the table. Then the dump image table, which describes + * the contents of the dump. Finally all the images are listed in order, with + * no deadspace in between. Userspace can use the sizes listed in the image + * table to reconstruct the individual images. + */ + struct sahara_context { struct sahara_packet *tx[SAHARA_NUM_TX_BUF]; struct sahara_packet *rx; - struct work_struct work; + struct work_struct fw_work; + struct work_struct dump_work; struct mhi_device *mhi_dev; const char **image_table; u32 table_size; u32 active_image_id; const struct firmware *firmware; + u64 dump_table_address; + u64 dump_table_length; + size_t rx_size; + size_t rx_size_requested; + void *mem_dump; + size_t mem_dump_sz; + struct sahara_dump_table_entry *dump_image; + u64 dump_image_offset; + void *mem_dump_freespace; + u64 dump_images_left; + bool is_mem_dump_mode; }; static const char *aic100_image_table[] = { @@ -153,6 +236,8 @@ static void sahara_send_reset(struct sahara_context *context) { int ret; + context->is_mem_dump_mode = false; + context->tx[0]->cmd = cpu_to_le32(SAHARA_RESET_CMD); context->tx[0]->length = cpu_to_le32(SAHARA_RESET_LENGTH); @@ -186,7 +271,8 @@ static void sahara_hello(struct sahara_context *context) } if (le32_to_cpu(context->rx->hello.mode) != SAHARA_MODE_IMAGE_TX_PENDING && - le32_to_cpu(context->rx->hello.mode) != SAHARA_MODE_IMAGE_TX_COMPLETE) { + le32_to_cpu(context->rx->hello.mode) != SAHARA_MODE_IMAGE_TX_COMPLETE && + le32_to_cpu(context->rx->hello.mode) != SAHARA_MODE_MEMORY_DEBUG) { dev_err(&context->mhi_dev->dev, "Unsupported hello packet - mode %d\n", le32_to_cpu(context->rx->hello.mode)); return; @@ -320,9 +406,70 @@ static void sahara_end_of_image(struct sahara_context *context) dev_dbg(&context->mhi_dev->dev, "Unable to send done response %d\n", ret); } +static void sahara_memory_debug64(struct sahara_context *context) +{ + int ret; + + dev_dbg(&context->mhi_dev->dev, + "MEMORY DEBUG64 cmd received. length:%d table_address:%#llx table_length:%#llx\n", + le32_to_cpu(context->rx->length), + le64_to_cpu(context->rx->memory_debug64.table_address), + le64_to_cpu(context->rx->memory_debug64.table_length)); + + if (le32_to_cpu(context->rx->length) != SAHARA_MEM_DEBUG64_LENGTH) { + dev_err(&context->mhi_dev->dev, "Malformed memory debug64 packet - length %d\n", + le32_to_cpu(context->rx->length)); + return; + } + + context->dump_table_address = le64_to_cpu(context->rx->memory_debug64.table_address); + context->dump_table_length = le64_to_cpu(context->rx->memory_debug64.table_length); + + if (context->dump_table_length % sizeof(struct sahara_debug_table_entry64) != 0 || + !context->dump_table_length) { + dev_err(&context->mhi_dev->dev, "Malformed memory debug64 packet - table length %lld\n", + context->dump_table_length); + return; + } + + /* + * From this point, the protocol flips. We make memory_read requests to + * the device, and the device responds with the raw data. If the device + * has an error, it will send an End of Image command. First we need to + * request the memory dump table so that we know where all the pieces + * of the dump are that we can consume. + */ + + context->is_mem_dump_mode = true; + + /* + * Assume that the table is smaller than our MTU so that we can read it + * in one shot. The spec does not put an upper limit on the table, but + * no known device will exceed this. + */ + if (context->dump_table_length > SAHARA_PACKET_MAX_SIZE) { + dev_err(&context->mhi_dev->dev, "Memory dump table length %lld exceeds supported size. Discarding dump\n", + context->dump_table_length); + sahara_send_reset(context); + return; + } + + context->tx[0]->cmd = cpu_to_le32(SAHARA_MEM_READ64_CMD); + context->tx[0]->length = cpu_to_le32(SAHARA_MEM_READ64_LENGTH); + context->tx[0]->memory_read64.memory_address = cpu_to_le64(context->dump_table_address); + context->tx[0]->memory_read64.memory_length = cpu_to_le64(context->dump_table_length); + + context->rx_size_requested = context->dump_table_length; + + ret = mhi_queue_buf(context->mhi_dev, DMA_TO_DEVICE, context->tx[0], + SAHARA_MEM_READ64_LENGTH, MHI_EOT); + if (ret) + dev_err(&context->mhi_dev->dev, "Unable to send read for dump table %d\n", ret); +} + static void sahara_processing(struct work_struct *work) { - struct sahara_context *context = container_of(work, struct sahara_context, work); + struct sahara_context *context = container_of(work, struct sahara_context, fw_work); int ret; switch (le32_to_cpu(context->rx->cmd)) { @@ -338,6 +485,12 @@ static void sahara_processing(struct work_struct *work) case SAHARA_DONE_RESP_CMD: /* Intentional do nothing as we don't need to exit an app */ break; + case SAHARA_RESET_RESP_CMD: + /* Intentional do nothing as we don't need to exit an app */ + break; + case SAHARA_MEM_DEBUG64_CMD: + sahara_memory_debug64(context); + break; default: dev_err(&context->mhi_dev->dev, "Unknown command %d\n", le32_to_cpu(context->rx->cmd)); @@ -350,6 +503,217 @@ static void sahara_processing(struct work_struct *work) dev_err(&context->mhi_dev->dev, "Unable to requeue rx buf %d\n", ret); } +static void sahara_parse_dump_table(struct sahara_context *context) +{ + struct sahara_dump_table_entry *image_out_table; + struct sahara_debug_table_entry64 *dev_table; + struct sahara_memory_dump_meta_v1 *dump_meta; + u64 table_nents; + u64 dump_length; + int ret; + u64 i; + + table_nents = context->dump_table_length / sizeof(*dev_table); + context->dump_images_left = table_nents; + dump_length = 0; + + dev_table = (struct sahara_debug_table_entry64 *)(context->rx); + for (i = 0; i < table_nents; ++i) { + /* Do not trust the device, ensure the strings are terminated */ + dev_table[i].description[SAHARA_TABLE_ENTRY_STR_LEN - 1] = 0; + dev_table[i].filename[SAHARA_TABLE_ENTRY_STR_LEN - 1] = 0; + + dump_length = size_add(dump_length, le64_to_cpu(dev_table[i].length)); + if (dump_length == SIZE_MAX) { + /* Discard the dump */ + sahara_send_reset(context); + return; + } + + dev_dbg(&context->mhi_dev->dev, + "Memory dump table entry %lld type: %lld address: %#llx length: %#llx description: \"%s\" filename \"%s\"\n", + i, + le64_to_cpu(dev_table[i].type), + le64_to_cpu(dev_table[i].address), + le64_to_cpu(dev_table[i].length), + dev_table[i].description, + dev_table[i].filename); + } + + dump_length = size_add(dump_length, sizeof(*dump_meta)); + if (dump_length == SIZE_MAX) { + /* Discard the dump */ + sahara_send_reset(context); + return; + } + dump_length = size_add(dump_length, size_mul(sizeof(*image_out_table), table_nents)); + if (dump_length == SIZE_MAX) { + /* Discard the dump */ + sahara_send_reset(context); + return; + } + + context->mem_dump_sz = dump_length; + context->mem_dump = vzalloc(dump_length); + if (!context->mem_dump) { + /* Discard the dump */ + sahara_send_reset(context); + return; + } + + /* Populate the dump metadata and table for userspace */ + dump_meta = context->mem_dump; + dump_meta->magic = SAHARA_DUMP_V1_MAGIC; + dump_meta->version = SAHARA_DUMP_V1_VER; + dump_meta->dump_size = dump_length; + dump_meta->table_size = context->dump_table_length; + + image_out_table = context->mem_dump + sizeof(*dump_meta); + for (i = 0; i < table_nents; ++i) { + image_out_table[i].type = le64_to_cpu(dev_table[i].type); + image_out_table[i].address = le64_to_cpu(dev_table[i].address); + image_out_table[i].length = le64_to_cpu(dev_table[i].length); + strscpy(image_out_table[i].description, dev_table[i].description, + SAHARA_TABLE_ENTRY_STR_LEN); + strscpy(image_out_table[i].filename, + dev_table[i].filename, + SAHARA_TABLE_ENTRY_STR_LEN); + } + + context->mem_dump_freespace = &image_out_table[i]; + + /* Done parsing the table, switch to image dump mode */ + context->dump_table_length = 0; + + /* Request the first chunk of the first image */ + context->dump_image = &image_out_table[0]; + dump_length = min(context->dump_image->length, SAHARA_READ_MAX_SIZE); + /* Avoid requesting EOI sized data so that we can identify errors */ + if (dump_length == SAHARA_END_OF_IMAGE_LENGTH) + dump_length = SAHARA_END_OF_IMAGE_LENGTH / 2; + + context->dump_image_offset = dump_length; + + context->tx[0]->cmd = cpu_to_le32(SAHARA_MEM_READ64_CMD); + context->tx[0]->length = cpu_to_le32(SAHARA_MEM_READ64_LENGTH); + context->tx[0]->memory_read64.memory_address = cpu_to_le64(context->dump_image->address); + context->tx[0]->memory_read64.memory_length = cpu_to_le64(dump_length); + + context->rx_size_requested = dump_length; + + ret = mhi_queue_buf(context->mhi_dev, DMA_TO_DEVICE, context->tx[0], + SAHARA_MEM_READ64_LENGTH, MHI_EOT); + if (ret) + dev_err(&context->mhi_dev->dev, "Unable to send read for dump content %d\n", ret); +} + +static void sahara_parse_dump_image(struct sahara_context *context) +{ + u64 dump_length; + int ret; + + memcpy(context->mem_dump_freespace, context->rx, context->rx_size); + context->mem_dump_freespace += context->rx_size; + + if (context->dump_image_offset >= context->dump_image->length) { + /* Need to move to next image */ + context->dump_image++; + context->dump_images_left--; + context->dump_image_offset = 0; + + if (!context->dump_images_left) { + /* Dump done */ + dev_coredumpv(context->mhi_dev->mhi_cntrl->cntrl_dev, + context->mem_dump, + context->mem_dump_sz, + GFP_KERNEL); + context->mem_dump = NULL; + sahara_send_reset(context); + return; + } + } + + /* Get next image chunk */ + dump_length = context->dump_image->length - context->dump_image_offset; + dump_length = min(dump_length, SAHARA_READ_MAX_SIZE); + /* Avoid requesting EOI sized data so that we can identify errors */ + if (dump_length == SAHARA_END_OF_IMAGE_LENGTH) + dump_length = SAHARA_END_OF_IMAGE_LENGTH / 2; + + context->tx[0]->cmd = cpu_to_le32(SAHARA_MEM_READ64_CMD); + context->tx[0]->length = cpu_to_le32(SAHARA_MEM_READ64_LENGTH); + context->tx[0]->memory_read64.memory_address = + cpu_to_le64(context->dump_image->address + context->dump_image_offset); + context->tx[0]->memory_read64.memory_length = cpu_to_le64(dump_length); + + context->dump_image_offset += dump_length; + context->rx_size_requested = dump_length; + + ret = mhi_queue_buf(context->mhi_dev, DMA_TO_DEVICE, context->tx[0], + SAHARA_MEM_READ64_LENGTH, MHI_EOT); + if (ret) + dev_err(&context->mhi_dev->dev, + "Unable to send read for dump content %d\n", ret); +} + +static void sahara_dump_processing(struct work_struct *work) +{ + struct sahara_context *context = container_of(work, struct sahara_context, dump_work); + int ret; + + /* + * We should get the expected raw data, but if the device has an error + * it is supposed to send EOI with an error code. + */ + if (context->rx_size != context->rx_size_requested && + context->rx_size != SAHARA_END_OF_IMAGE_LENGTH) { + dev_err(&context->mhi_dev->dev, + "Unexpected response to read_data. Expected size: %#zx got: %#zx\n", + context->rx_size_requested, + context->rx_size); + goto error; + } + + if (context->rx_size == SAHARA_END_OF_IMAGE_LENGTH && + le32_to_cpu(context->rx->cmd) == SAHARA_END_OF_IMAGE_CMD) { + dev_err(&context->mhi_dev->dev, + "Unexpected EOI response to read_data. Status: %d\n", + le32_to_cpu(context->rx->end_of_image.status)); + goto error; + } + + if (context->rx_size == SAHARA_END_OF_IMAGE_LENGTH && + le32_to_cpu(context->rx->cmd) != SAHARA_END_OF_IMAGE_CMD) { + dev_err(&context->mhi_dev->dev, + "Invalid EOI response to read_data. CMD: %d\n", + le32_to_cpu(context->rx->cmd)); + goto error; + } + + /* + * Need to know if we received the dump table, or part of a dump image. + * Since we get raw data, we cannot tell from the data itself. Instead, + * we use the stored dump_table_length, which we zero after we read and + * process the entire table. + */ + if (context->dump_table_length) + sahara_parse_dump_table(context); + else + sahara_parse_dump_image(context); + + ret = mhi_queue_buf(context->mhi_dev, DMA_FROM_DEVICE, context->rx, + SAHARA_PACKET_MAX_SIZE, MHI_EOT); + if (ret) + dev_err(&context->mhi_dev->dev, "Unable to requeue rx buf %d\n", ret); + + return; + +error: + vfree(context->mem_dump); + context->mem_dump = NULL; + sahara_send_reset(context); +} + static int sahara_mhi_probe(struct mhi_device *mhi_dev, const struct mhi_device_id *id) { struct sahara_context *context; @@ -382,7 +746,8 @@ static int sahara_mhi_probe(struct mhi_device *mhi_dev, const struct mhi_device_ } context->mhi_dev = mhi_dev; - INIT_WORK(&context->work, sahara_processing); + INIT_WORK(&context->fw_work, sahara_processing); + INIT_WORK(&context->dump_work, sahara_dump_processing); context->image_table = aic100_image_table; context->table_size = ARRAY_SIZE(aic100_image_table); context->active_image_id = SAHARA_IMAGE_ID_NONE; @@ -405,7 +770,10 @@ static void sahara_mhi_remove(struct mhi_device *mhi_dev) { struct sahara_context *context = dev_get_drvdata(&mhi_dev->dev); - cancel_work_sync(&context->work); + cancel_work_sync(&context->fw_work); + cancel_work_sync(&context->dump_work); + if (context->mem_dump) + vfree(context->mem_dump); sahara_release_image(context); mhi_unprepare_from_transfer(mhi_dev); } @@ -418,8 +786,14 @@ static void sahara_mhi_dl_xfer_cb(struct mhi_device *mhi_dev, struct mhi_result { struct sahara_context *context = dev_get_drvdata(&mhi_dev->dev); - if (!mhi_result->transaction_status) - schedule_work(&context->work); + if (!mhi_result->transaction_status) { + context->rx_size = mhi_result->bytes_xferd; + if (context->is_mem_dump_mode) + schedule_work(&context->dump_work); + else + schedule_work(&context->fw_work); + } + } static const struct mhi_device_id sahara_mhi_match_table[] = { diff --git a/drivers/acpi/apei/apei-base.c b/drivers/acpi/apei/apei-base.c index c7c26872f4cec11a3be409204b25e54bd727b482..9c84f3da7c09004079c1e0a52988f7f29c641f08 100644 --- a/drivers/acpi/apei/apei-base.c +++ b/drivers/acpi/apei/apei-base.c @@ -28,7 +28,7 @@ #include #include #include -#include +#include #include "apei-internal.h" diff --git a/drivers/acpi/apei/einj-core.c b/drivers/acpi/apei/einj-core.c index 73903a497d73f7549e913ee00d85507398643464..5c22720f43ccb971d69505ea88f30310ce5c562b 100644 --- a/drivers/acpi/apei/einj-core.c +++ b/drivers/acpi/apei/einj-core.c @@ -22,7 +22,7 @@ #include #include #include -#include +#include #include "apei-internal.h" diff --git a/drivers/acpi/apei/einj-cxl.c b/drivers/acpi/apei/einj-cxl.c index 4f81a119ec0896b4b93601865d783d56f24c76dc..a4e709937236f66146790c044df473b151257892 100644 --- a/drivers/acpi/apei/einj-cxl.c +++ b/drivers/acpi/apei/einj-cxl.c @@ -63,7 +63,7 @@ static int cxl_dport_get_sbdf(struct pci_dev *dport_dev, u64 *sbdf) seg = bridge->domain_nr; bus = pbus->number; - *sbdf = (seg << 24) | (bus << 16) | dport_dev->devfn; + *sbdf = (seg << 24) | (bus << 16) | (dport_dev->devfn << 8); return 0; } diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c index f4599261cfc31cdbf9c371fa4de0d87f17fd862f..65fa3444367a13ac83644444076a11f08152c382 100644 --- a/drivers/acpi/battery.c +++ b/drivers/acpi/battery.c @@ -21,7 +21,7 @@ #include #include -#include +#include #include #include @@ -703,28 +703,35 @@ static LIST_HEAD(acpi_battery_list); static LIST_HEAD(battery_hook_list); static DEFINE_MUTEX(hook_mutex); -static void __battery_hook_unregister(struct acpi_battery_hook *hook, int lock) +static void battery_hook_unregister_unlocked(struct acpi_battery_hook *hook) { struct acpi_battery *battery; + /* * In order to remove a hook, we first need to * de-register all the batteries that are registered. */ - if (lock) - mutex_lock(&hook_mutex); list_for_each_entry(battery, &acpi_battery_list, list) { if (!hook->remove_battery(battery->bat, hook)) power_supply_changed(battery->bat); } - list_del(&hook->list); - if (lock) - mutex_unlock(&hook_mutex); + list_del_init(&hook->list); + pr_info("extension unregistered: %s\n", hook->name); } void battery_hook_unregister(struct acpi_battery_hook *hook) { - __battery_hook_unregister(hook, 1); + mutex_lock(&hook_mutex); + /* + * Ignore already unregistered battery hooks. This might happen + * if a battery hook was previously unloaded due to an error when + * adding a new battery. + */ + if (!list_empty(&hook->list)) + battery_hook_unregister_unlocked(hook); + + mutex_unlock(&hook_mutex); } EXPORT_SYMBOL_GPL(battery_hook_unregister); @@ -733,7 +740,6 @@ void battery_hook_register(struct acpi_battery_hook *hook) struct acpi_battery *battery; mutex_lock(&hook_mutex); - INIT_LIST_HEAD(&hook->list); list_add(&hook->list, &battery_hook_list); /* * Now that the driver is registered, we need @@ -750,7 +756,7 @@ void battery_hook_register(struct acpi_battery_hook *hook) * hooks. */ pr_err("extension failed to load: %s", hook->name); - __battery_hook_unregister(hook, 0); + battery_hook_unregister_unlocked(hook); goto end; } @@ -804,7 +810,7 @@ static void battery_hook_add_battery(struct acpi_battery *battery) */ pr_err("error in extension, unloading: %s", hook_node->name); - __battery_hook_unregister(hook_node, 0); + battery_hook_unregister_unlocked(hook_node); } } mutex_unlock(&hook_mutex); @@ -837,7 +843,7 @@ static void __exit battery_hook_exit(void) * need to remove the hooks. */ list_for_each_entry_safe(hook, ptr, &battery_hook_list, list) { - __battery_hook_unregister(hook, 1); + battery_hook_unregister(hook); } mutex_destroy(&hook_mutex); } diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c index 5b06e236aabef2bae1834a056436afa8b47e8e02..b73b3aa92f3f688e384f1b98fdf4f5db90115c2a 100644 --- a/drivers/acpi/cppc_acpi.c +++ b/drivers/acpi/cppc_acpi.c @@ -41,7 +41,7 @@ #include #include #include -#include +#include #include diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c index 8a4726e2eb6938da0992138eb6fc0bce11597d9f..3d74ebe9dbd80458fd7e6ef22a1581f3b180a09b 100644 --- a/drivers/acpi/resource.c +++ b/drivers/acpi/resource.c @@ -440,6 +440,13 @@ static const struct dmi_system_id irq1_level_low_skip_override[] = { DMI_MATCH(DMI_BOARD_NAME, "S5602ZA"), }, }, + { + /* Asus Vivobook X1704VAP */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_BOARD_NAME, "X1704VAP"), + }, + }, { /* Asus ExpertBook B1402CBA */ .matches = { @@ -504,24 +511,24 @@ static const struct dmi_system_id irq1_level_low_skip_override[] = { }, }, { - /* Asus Vivobook Go E1404GAB */ + /* Asus ExpertBook B2502CVA */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), - DMI_MATCH(DMI_BOARD_NAME, "E1404GAB"), + DMI_MATCH(DMI_BOARD_NAME, "B2502CVA"), }, }, { - /* Asus Vivobook E1504GA */ + /* Asus Vivobook Go E1404GA* */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), - DMI_MATCH(DMI_BOARD_NAME, "E1504GA"), + DMI_MATCH(DMI_BOARD_NAME, "E1404GA"), }, }, { - /* Asus Vivobook E1504GAB */ + /* Asus Vivobook E1504GA* */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), - DMI_MATCH(DMI_BOARD_NAME, "E1504GAB"), + DMI_MATCH(DMI_BOARD_NAME, "E1504GA"), }, }, { diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c index b70e84e8049aa79902dcaa9f18615d165ceebcbf..015bd8e66c1cf85f301b74c1184a7a760c601915 100644 --- a/drivers/acpi/video_detect.c +++ b/drivers/acpi/video_detect.c @@ -844,6 +844,15 @@ static const struct dmi_system_id video_detect_dmi_table[] = { * controller board in their ACPI tables (and may even have one), but * which need native backlight control nevertheless. */ + { + /* https://github.com/zabbly/linux/issues/26 */ + .callback = video_detect_force_native, + /* Dell OptiPlex 5480 AIO */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 5480 AIO"), + }, + }, { /* https://bugzilla.redhat.com/show_bug.cgi?id=2303936 */ .callback = video_detect_force_native, diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index cdb20a700b55b8aeaa21eba31456b1e62d40718a..c085dd81ebe7f646c061cd813fdcb3f4428b16cb 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -50,7 +50,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/drivers/ata/libata-sata.c b/drivers/ata/libata-sata.c index c8b119a06bb23dc1d7f4f9bd92d3b5481530dc42..9c76fb1ad2ec506879bb481509e20e1ede971f3d 100644 --- a/drivers/ata/libata-sata.c +++ b/drivers/ata/libata-sata.c @@ -13,7 +13,7 @@ #include #include #include -#include +#include #include "libata.h" #include "libata-transport.h" diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index a4aedf7e177580efb459af29fc540508aef82324..f915e3df57a9a0c29f5a912531c9f43a0a181e18 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -30,7 +30,7 @@ #include #include #include -#include +#include #include #include diff --git a/drivers/auxdisplay/ht16k33.c b/drivers/auxdisplay/ht16k33.c index 8a7034b41d50e8f0ab1228000bb4b703f277e825..a816f9e102559574c5d492501be51129faf18bce 100644 --- a/drivers/auxdisplay/ht16k33.c +++ b/drivers/auxdisplay/ht16k33.c @@ -25,7 +25,7 @@ #include #include -#include +#include #include "line-display.h" diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c index 9ed842d17642b54b7de05676cc659e94c828e2ee..4ded93687c1f0ab3584947c61398cd6333b2e72c 100644 --- a/drivers/base/regmap/regmap.c +++ b/drivers/base/regmap/regmap.c @@ -17,7 +17,7 @@ #include #include #include -#include +#include #define CREATE_TRACE_POINTS #include "trace.h" diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c index cc9077b588d7e7af30401ab03c826a358b2a232c..92b06d1de4cc7b7c4ea6f5fad6aa6c4518c1001b 100644 --- a/drivers/block/aoe/aoecmd.c +++ b/drivers/block/aoe/aoecmd.c @@ -14,7 +14,7 @@ #include #include #include -#include +#include #include #include "aoe.h" @@ -361,6 +361,7 @@ ata_rw_frameinit(struct frame *f) } ah->cmdstat = ATA_CMD_PIO_READ | writebit | extbit; + dev_hold(t->ifp->nd); skb->dev = t->ifp->nd; } @@ -401,6 +402,8 @@ aoecmd_ata_rw(struct aoedev *d) __skb_queue_head_init(&queue); __skb_queue_tail(&queue, skb); aoenet_xmit(&queue); + } else { + dev_put(f->t->ifp->nd); } return 1; } @@ -483,10 +486,13 @@ resend(struct aoedev *d, struct frame *f) memcpy(h->dst, t->addr, sizeof h->dst); memcpy(h->src, t->ifp->nd->dev_addr, sizeof h->src); + dev_hold(t->ifp->nd); skb->dev = t->ifp->nd; skb = skb_clone(skb, GFP_ATOMIC); - if (skb == NULL) + if (skb == NULL) { + dev_put(t->ifp->nd); return; + } f->sent = ktime_get(); __skb_queue_head_init(&queue); __skb_queue_tail(&queue, skb); @@ -617,6 +623,8 @@ probe(struct aoetgt *t) __skb_queue_head_init(&queue); __skb_queue_tail(&queue, skb); aoenet_xmit(&queue); + } else { + dev_put(f->t->ifp->nd); } } @@ -1395,6 +1403,7 @@ aoecmd_ata_id(struct aoedev *d) ah->cmdstat = ATA_CMD_ID_ATA; ah->lba3 = 0xa0; + dev_hold(t->ifp->nd); skb->dev = t->ifp->nd; d->rttavg = RTTAVG_INIT; @@ -1404,6 +1413,8 @@ aoecmd_ata_id(struct aoedev *d) skb = skb_clone(skb, GFP_ATOMIC); if (skb) f->sent = ktime_get(); + else + dev_put(t->ifp->nd); return skb; } diff --git a/drivers/block/aoe/aoenet.c b/drivers/block/aoe/aoenet.c index 923a134fd766562fcf9d33a993739040517258c1..66e617664c143aa38da45ab08ee693f8022574f2 100644 --- a/drivers/block/aoe/aoenet.c +++ b/drivers/block/aoe/aoenet.c @@ -10,7 +10,7 @@ #include #include #include -#include +#include #include "aoe.h" #define NECODES 5 diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c index 5d65c9754d8377e60f59228f7abb2eac9669a439..720fc30e2ecc921d7ddc1f285e5aa509647d1f69 100644 --- a/drivers/block/drbd/drbd_nl.c +++ b/drivers/block/drbd/drbd_nl.c @@ -25,7 +25,7 @@ #include "drbd_protocol.h" #include "drbd_req.h" #include "drbd_state_change.h" -#include +#include #include #include diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index 499c110465e34f0fc766caa8436d8719315dd90f..65b96c083b3cad28aa73868fda222a7c16d15dc6 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -71,7 +71,7 @@ #include #include -#include +#include #define DRIVER_NAME "pktcdvd" diff --git a/drivers/bluetooth/ath3k.c b/drivers/bluetooth/ath3k.c index ce97b336fbfb8aad7d3d5b6e5ab49feb022762d3..fc796f1dbda9742bedd7e2f52c073f235be3c03d 100644 --- a/drivers/bluetooth/ath3k.c +++ b/drivers/bluetooth/ath3k.c @@ -11,7 +11,7 @@ #include #include #include -#include +#include #include #define VERSION "1.0" diff --git a/drivers/bluetooth/btbcm.c b/drivers/bluetooth/btbcm.c index f9a7c790d7e2ec958a43c8b577a2c775d1307207..eef00467905eb3bc5e9b29a4dde6c24e541b7929 100644 --- a/drivers/bluetooth/btbcm.c +++ b/drivers/bluetooth/btbcm.c @@ -12,7 +12,7 @@ #include #include #include -#include +#include #include #include diff --git a/drivers/bluetooth/btintel.c b/drivers/bluetooth/btintel.c index 1ccbb5157515331daaaef87b7a8eeb1370942278..438b92967bc364c63f46242630466c5c62009634 100644 --- a/drivers/bluetooth/btintel.c +++ b/drivers/bluetooth/btintel.c @@ -11,7 +11,7 @@ #include #include #include -#include +#include #include #include diff --git a/drivers/bluetooth/btintel_pcie.c b/drivers/bluetooth/btintel_pcie.c index fda47948c35d7cf76c2d6b1044ee5c2f2b51d207..5252125b003f58fc582089b3a6133373546d97b5 100644 --- a/drivers/bluetooth/btintel_pcie.c +++ b/drivers/bluetooth/btintel_pcie.c @@ -14,7 +14,7 @@ #include #include -#include +#include #include #include diff --git a/drivers/bluetooth/btmrvl_sdio.c b/drivers/bluetooth/btmrvl_sdio.c index 85b7f2bb425982c35638b54df1c9cf56495e9f0c..07cd308f7abf6debe114452ed4e3e6de82efc1f8 100644 --- a/drivers/bluetooth/btmrvl_sdio.c +++ b/drivers/bluetooth/btmrvl_sdio.c @@ -92,7 +92,7 @@ static int btmrvl_sdio_probe_of(struct device *dev, } else { ret = devm_request_irq(dev, cfg->irq_bt, btmrvl_wake_irq_bt, - 0, "bt_wake", card); + IRQF_NO_AUTOEN, "bt_wake", card); if (ret) { dev_err(dev, "Failed to request irq_bt %d (%d)\n", @@ -101,7 +101,6 @@ static int btmrvl_sdio_probe_of(struct device *dev, /* Configure wakeup (enabled by default) */ device_init_wakeup(dev, true); - disable_irq(cfg->irq_bt); } } diff --git a/drivers/bluetooth/btmtk.c b/drivers/bluetooth/btmtk.c index 2b7c80043aa2ebd4c525d78e77af423df142d7cc..9bbf205021634f02407fa64eea5e45f0426e0a21 100644 --- a/drivers/bluetooth/btmtk.c +++ b/drivers/bluetooth/btmtk.c @@ -6,7 +6,7 @@ #include #include #include -#include +#include #include #include diff --git a/drivers/bluetooth/btmtksdio.c b/drivers/bluetooth/btmtksdio.c index 497e4c87f5be56d5919f74ba4a53b20a079e0a54..11d33cd7b08fc04fc1d5b55807c232f8c00425f4 100644 --- a/drivers/bluetooth/btmtksdio.c +++ b/drivers/bluetooth/btmtksdio.c @@ -10,7 +10,7 @@ * */ -#include +#include #include #include #include diff --git a/drivers/bluetooth/btmtkuart.c b/drivers/bluetooth/btmtkuart.c index aa87c3e788718feeb7999608aeb25be41c6ce3a0..64e4d835af5211dc762358ebb2a2bfd3bf5961ba 100644 --- a/drivers/bluetooth/btmtkuart.c +++ b/drivers/bluetooth/btmtkuart.c @@ -8,7 +8,7 @@ * */ -#include +#include #include #include #include diff --git a/drivers/bluetooth/btnxpuart.c b/drivers/bluetooth/btnxpuart.c index 7c2030cec10e186db9c46109deea557102de9443..5ea0d23e88c02ba33b14b6caa0a96b890b744255 100644 --- a/drivers/bluetooth/btnxpuart.c +++ b/drivers/bluetooth/btnxpuart.c @@ -10,7 +10,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/drivers/bluetooth/btrsi.c b/drivers/bluetooth/btrsi.c index 0c91d7635ac39e9082eabe3ece06efeabefb1588..6c1f584c8a33725b6c437cfc920bb296efee86bd 100644 --- a/drivers/bluetooth/btrsi.c +++ b/drivers/bluetooth/btrsi.c @@ -17,7 +17,7 @@ #include #include #include -#include +#include #include #define RSI_DMA_ALIGN 8 diff --git a/drivers/bluetooth/btrtl.c b/drivers/bluetooth/btrtl.c index 2d95b3ea046dff1b8e02e33b6fb4971292a4a4ec..0bcb44cf7b31d7d0c2d2a17f3576806fbaf28a9b 100644 --- a/drivers/bluetooth/btrtl.c +++ b/drivers/bluetooth/btrtl.c @@ -7,7 +7,7 @@ #include #include -#include +#include #include #include diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index 6c9c761d5b93a8c7505b348b5d7b3caf9f69c9cb..f23c8801ad5cc48491b2a0d6d3bcbb5d486cf1b5 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -17,7 +17,7 @@ #include #include #include -#include +#include #include #include diff --git a/drivers/bluetooth/h4_recv.h b/drivers/bluetooth/h4_recv.h index 647d37ca4cdda203fdfe1fa45dd8ca266c693929..28cf2d8c2d48e93df9801738257ed173478316b4 100644 --- a/drivers/bluetooth/h4_recv.h +++ b/drivers/bluetooth/h4_recv.h @@ -6,7 +6,7 @@ * Copyright (C) 2015-2018 Intel Corporation */ -#include +#include struct h4_recv_pkt { u8 type; /* Packet type */ diff --git a/drivers/bluetooth/hci_bcm4377.c b/drivers/bluetooth/hci_bcm4377.c index 77a5454a8721e84877407614c989be9f627d45d5..9bce53e49cfa60c6ee9ea734e5d7a0708dc7a679 100644 --- a/drivers/bluetooth/hci_bcm4377.c +++ b/drivers/bluetooth/hci_bcm4377.c @@ -17,7 +17,7 @@ #include #include -#include +#include #include #include diff --git a/drivers/bluetooth/hci_bcsp.c b/drivers/bluetooth/hci_bcsp.c index 2a5a27d713f8a0f04d6357eb642885203648ea3b..76878119d910cf55ef7d3526fc86f25c971ff12b 100644 --- a/drivers/bluetooth/hci_bcsp.c +++ b/drivers/bluetooth/hci_bcsp.c @@ -25,7 +25,7 @@ #include #include #include -#include +#include #include #include diff --git a/drivers/bluetooth/hci_h4.c b/drivers/bluetooth/hci_h4.c index 1d0cdf02324373062f82e69d7acb1cd28c4271f9..9070e31a68bfd22cc31c66c53caf122a17d32f53 100644 --- a/drivers/bluetooth/hci_h4.c +++ b/drivers/bluetooth/hci_h4.c @@ -25,7 +25,7 @@ #include #include #include -#include +#include #include #include diff --git a/drivers/bluetooth/hci_nokia.c b/drivers/bluetooth/hci_nokia.c index 62633d9ba7c43eedefa657337b9fa2521d330a88..49bbe4975be4bc3ab24615e73683a66acabe1931 100644 --- a/drivers/bluetooth/hci_nokia.c +++ b/drivers/bluetooth/hci_nokia.c @@ -20,7 +20,7 @@ #include #include #include -#include +#include #include #include diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c index 678f150229e7796b237f5b538292100383d58407..37fddf6055bebbbd9cab493a3d366060f0f25c3d 100644 --- a/drivers/bluetooth/hci_qca.c +++ b/drivers/bluetooth/hci_qca.c @@ -32,7 +32,7 @@ #include #include #include -#include +#include #include #include diff --git a/drivers/bluetooth/hci_vhci.c b/drivers/bluetooth/hci_vhci.c index aa6af351d02de2b73ea6090b2ef8e6a1dee9c1b4..7651321d351ccd5a96503bb555b5d9eb2c35b4ff 100644 --- a/drivers/bluetooth/hci_vhci.c +++ b/drivers/bluetooth/hci_vhci.c @@ -9,7 +9,7 @@ */ #include -#include +#include #include #include diff --git a/drivers/char/tpm/tpm2-sessions.c b/drivers/char/tpm/tpm2-sessions.c index 44f60730cff4415c94a44c26086264c15770495a..511c67061728ad5255e9cf6ef0008940df3f4076 100644 --- a/drivers/char/tpm/tpm2-sessions.c +++ b/drivers/char/tpm/tpm2-sessions.c @@ -71,7 +71,7 @@ #include "tpm.h" #include #include -#include +#include #include #include #include diff --git a/drivers/char/tpm/tpm2-space.c b/drivers/char/tpm/tpm2-space.c index 25a66870c165c503b58cbb45c4c6906583384bb9..60354cd53b5c121f7f5fcbfe85cc88e3b903719a 100644 --- a/drivers/char/tpm/tpm2-space.c +++ b/drivers/char/tpm/tpm2-space.c @@ -12,7 +12,7 @@ */ #include -#include +#include #include "tpm.h" enum tpm2_handle_types { diff --git a/drivers/clk/clk-si5341.c b/drivers/clk/clk-si5341.c index 6e8dd7387cfdd48e03cda92f466232c10e64239f..5004888c7eca5f85a444ec6de684b8dd79635622 100644 --- a/drivers/clk/clk-si5341.c +++ b/drivers/clk/clk-si5341.c @@ -21,7 +21,7 @@ #include #include #include -#include +#include #define SI5341_NUM_INPUTS 4 diff --git a/drivers/comedi/drivers/usbduxsigma.c b/drivers/comedi/drivers/usbduxsigma.c index 2aaeaf44fbe57d29db63baccce4ffa9e655c5162..3f215ae228b2d3a7a82b7881f4751a7177d0fe3f 100644 --- a/drivers/comedi/drivers/usbduxsigma.c +++ b/drivers/comedi/drivers/usbduxsigma.c @@ -39,7 +39,7 @@ #include #include #include -#include +#include #include /* timeout for the USB-transfer in ms*/ diff --git a/drivers/counter/104-quad-8.c b/drivers/counter/104-quad-8.c index ed1f57511955856af1bbb76fc8b3e81ce51ae7b8..4a6868b8f58bce508ce2d50b1416275f6aeb582b 100644 --- a/drivers/counter/104-quad-8.c +++ b/drivers/counter/104-quad-8.c @@ -22,7 +22,7 @@ #include #include -#include +#include #define QUAD8_EXTENT 32 diff --git a/drivers/counter/i8254.c b/drivers/counter/i8254.c index c41e4fdc96011752a55b029a2a76e668cda16ce6..6d74e8ef92f009d31e5806fbfe2d37d46ee0dae6 100644 --- a/drivers/counter/i8254.c +++ b/drivers/counter/i8254.c @@ -15,7 +15,7 @@ #include #include -#include +#include #define I8254_COUNTER_REG(_counter) (_counter) #define I8254_CONTROL_REG 0x3 diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c index 1a5ad184d28fc24e318f17e4cdad06efbb74ad90..2b8708475ac7761e18bf9a4a7be14957e0937133 100644 --- a/drivers/cpufreq/cppc_cpufreq.c +++ b/drivers/cpufreq/cppc_cpufreq.c @@ -22,7 +22,7 @@ #include #include -#include +#include #include diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index aaea9a39ecedb4a3f4de5779fd1a26f501e18255..b0018f371ea3a5e996cc9e94dd98e4bc7ae5af02 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -1845,7 +1845,7 @@ static void intel_pstate_notify_work(struct work_struct *work) wrmsrl_on_cpu(cpudata->cpu, MSR_HWP_STATUS, 0); } -static DEFINE_SPINLOCK(hwp_notify_lock); +static DEFINE_RAW_SPINLOCK(hwp_notify_lock); static cpumask_t hwp_intr_enable_mask; #define HWP_GUARANTEED_PERF_CHANGE_STATUS BIT(0) @@ -1868,7 +1868,7 @@ void notify_hwp_interrupt(void) if (!(value & status_mask)) return; - spin_lock_irqsave(&hwp_notify_lock, flags); + raw_spin_lock_irqsave(&hwp_notify_lock, flags); if (!cpumask_test_cpu(this_cpu, &hwp_intr_enable_mask)) goto ack_intr; @@ -1876,13 +1876,13 @@ void notify_hwp_interrupt(void) schedule_delayed_work(&all_cpu_data[this_cpu]->hwp_notify_work, msecs_to_jiffies(10)); - spin_unlock_irqrestore(&hwp_notify_lock, flags); + raw_spin_unlock_irqrestore(&hwp_notify_lock, flags); return; ack_intr: wrmsrl_safe(MSR_HWP_STATUS, 0); - spin_unlock_irqrestore(&hwp_notify_lock, flags); + raw_spin_unlock_irqrestore(&hwp_notify_lock, flags); } static void intel_pstate_disable_hwp_interrupt(struct cpudata *cpudata) @@ -1895,9 +1895,9 @@ static void intel_pstate_disable_hwp_interrupt(struct cpudata *cpudata) /* wrmsrl_on_cpu has to be outside spinlock as this can result in IPC */ wrmsrl_on_cpu(cpudata->cpu, MSR_HWP_INTERRUPT, 0x00); - spin_lock_irq(&hwp_notify_lock); + raw_spin_lock_irq(&hwp_notify_lock); cancel_work = cpumask_test_and_clear_cpu(cpudata->cpu, &hwp_intr_enable_mask); - spin_unlock_irq(&hwp_notify_lock); + raw_spin_unlock_irq(&hwp_notify_lock); if (cancel_work) cancel_delayed_work_sync(&cpudata->hwp_notify_work); @@ -1912,10 +1912,10 @@ static void intel_pstate_enable_hwp_interrupt(struct cpudata *cpudata) if (boot_cpu_has(X86_FEATURE_HWP_NOTIFY)) { u64 interrupt_mask = HWP_GUARANTEED_PERF_CHANGE_REQ; - spin_lock_irq(&hwp_notify_lock); + raw_spin_lock_irq(&hwp_notify_lock); INIT_DELAYED_WORK(&cpudata->hwp_notify_work, intel_pstate_notify_work); cpumask_set_cpu(cpudata->cpu, &hwp_intr_enable_mask); - spin_unlock_irq(&hwp_notify_lock); + raw_spin_unlock_irq(&hwp_notify_lock); if (cpu_feature_enabled(X86_FEATURE_HWP_HIGHEST_PERF_CHANGE)) interrupt_mask |= HWP_HIGHEST_PERF_CHANGE_REQ; diff --git a/drivers/crypto/allwinner/sun4i-ss/sun4i-ss-hash.c b/drivers/crypto/allwinner/sun4i-ss/sun4i-ss-hash.c index f7893e4ac59dd8ceea2993d18ded40d6ee91f55a..434f2b2710120034328bae2498a21a23ff53a8bf 100644 --- a/drivers/crypto/allwinner/sun4i-ss/sun4i-ss-hash.c +++ b/drivers/crypto/allwinner/sun4i-ss/sun4i-ss-hash.c @@ -9,7 +9,7 @@ * You could find the datasheet in Documentation/arch/arm/sunxi.rst */ #include "sun4i-ss.h" -#include +#include #include /* This is a totally arbitrary value */ diff --git a/drivers/crypto/caam/caamalg.c b/drivers/crypto/caam/caamalg.c index 066f08a3a040d875aab98bc9f2603fbb2381a3f6..2cfb1b8d8c7cfc585f405c6f3a5c13be0aee08d0 100644 --- a/drivers/crypto/caam/caamalg.c +++ b/drivers/crypto/caam/caamalg.c @@ -56,7 +56,7 @@ #include "sg_sw_sec4.h" #include "key_gen.h" #include "caamalg_desc.h" -#include +#include #include #include #include diff --git a/drivers/crypto/caam/caamalg_qi.c b/drivers/crypto/caam/caamalg_qi.c index 13347dfecf7ac0ebc4783541dc7eef6755311850..65f6adb6c673f8016533b018035b9715b6be3c64 100644 --- a/drivers/crypto/caam/caamalg_qi.c +++ b/drivers/crypto/caam/caamalg_qi.c @@ -19,7 +19,7 @@ #include "jr.h" #include "caamalg_desc.h" #include -#include +#include #include #include #include diff --git a/drivers/crypto/caam/caamalg_qi2.c b/drivers/crypto/caam/caamalg_qi2.c index 44e1f8f469674ba46969237c33e0ea16638c7378..e809d030ab1135ad43887a99c0e115f58ae9f7b1 100644 --- a/drivers/crypto/caam/caamalg_qi2.c +++ b/drivers/crypto/caam/caamalg_qi2.c @@ -22,7 +22,7 @@ #include #include #include -#include +#include #define CAAM_CRA_PRIORITY 2000 diff --git a/drivers/crypto/inside-secure/safexcel_cipher.c b/drivers/crypto/inside-secure/safexcel_cipher.c index 42677f7458b787e3722760efa42013834dc05e95..919e5a2cab95e3b46f2068e871e5495775620206 100644 --- a/drivers/crypto/inside-secure/safexcel_cipher.c +++ b/drivers/crypto/inside-secure/safexcel_cipher.c @@ -5,7 +5,7 @@ * Antoine Tenart */ -#include +#include #include #include #include diff --git a/drivers/crypto/rockchip/rk3288_crypto_ahash.c b/drivers/crypto/rockchip/rk3288_crypto_ahash.c index a235e6c300f1e5419eb06945757946ced70f12e2..69d6019d8abcf0dc3d49942a65cfd0d20a53f549 100644 --- a/drivers/crypto/rockchip/rk3288_crypto_ahash.c +++ b/drivers/crypto/rockchip/rk3288_crypto_ahash.c @@ -9,7 +9,7 @@ * Some ideas are from marvell/cesa.c and s5p-sss.c driver. */ -#include +#include #include #include #include diff --git a/drivers/crypto/stm32/stm32-crc32.c b/drivers/crypto/stm32/stm32-crc32.c index b0cf6d2fd352ff6dc486f389f79d6d9848292ebb..e0faddbf8990cb334e3a7151bffc02e81835e66e 100644 --- a/drivers/crypto/stm32/stm32-crc32.c +++ b/drivers/crypto/stm32/stm32-crc32.c @@ -17,7 +17,7 @@ #include -#include +#include #define DRIVER_NAME "stm32-crc32" #define CHKSUM_DIGEST_SIZE 4 diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c index 946f8e44455f79c6dc945e443d35bb75f9ab7ff8..5175138c4fb7382426145640d7d04967b02b22dc 100644 --- a/drivers/cxl/core/mbox.c +++ b/drivers/cxl/core/mbox.c @@ -4,7 +4,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/drivers/cxl/core/trace.h b/drivers/cxl/core/trace.h index 9167cfba7f592cfdf2f13b87cbb4ed779eb48266..8672b42ee4d1b376063b09d29922fcce83a70168 100644 --- a/drivers/cxl/core/trace.h +++ b/drivers/cxl/core/trace.h @@ -8,7 +8,7 @@ #include #include -#include +#include #include #include diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c index 37164174b5fb0e50b14918331a822b3b204ce0b8..188412d45e0d266b19f7401a1cdc51ed6fb0ea0a 100644 --- a/drivers/cxl/pci.c +++ b/drivers/cxl/pci.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only /* Copyright(c) 2020 Intel Corporation. All rights reserved. */ -#include +#include #include #include #include diff --git a/drivers/cxl/pmem.c b/drivers/cxl/pmem.c index a6538a5f5c9fb10d512375d83a65a92f116ea70b..d2d43a4fc05387fdd643d5f7d73612e49b5762bc 100644 --- a/drivers/cxl/pmem.c +++ b/drivers/cxl/pmem.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-only /* Copyright(c) 2021 Intel Corporation. All rights reserved. */ #include -#include +#include #include #include #include diff --git a/drivers/cxl/security.c b/drivers/cxl/security.c index 452d1a9b9148a871975025c3a43e8eb6c8a7f49a..ab793e8577c782180f673f220188394b9db16789 100644 --- a/drivers/cxl/security.c +++ b/drivers/cxl/security.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-only /* Copyright(c) 2022 Intel Corporation. All rights reserved. */ #include -#include +#include #include #include #include diff --git a/drivers/dma-buf/Kconfig b/drivers/dma-buf/Kconfig index b46eb8a552d7be02cb305f65aaf4ba168f03fee2..fee04fdb08220c1ea745bdf56802a0d1d9b231a5 100644 --- a/drivers/dma-buf/Kconfig +++ b/drivers/dma-buf/Kconfig @@ -36,6 +36,7 @@ config UDMABUF depends on DMA_SHARED_BUFFER depends on MEMFD_CREATE || COMPILE_TEST depends on MMU + select VMAP_PFN help A driver to let userspace turn memfd regions into dma-bufs. Qemu can use this to create host dmabufs for guest framebuffers. diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index 8892bc701a662d89ef74264eaeb3b733259755fa..5ad0e9e2e1b93b4095b48ce2c7dd37f8c4701666 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -176,8 +176,9 @@ static loff_t dma_buf_llseek(struct file *file, loff_t offset, int whence) dmabuf = file->private_data; /* only support discovering the end of the buffer, - but also allow SEEK_SET to maintain the idiomatic - SEEK_END(0), SEEK_CUR(0) pattern */ + * but also allow SEEK_SET to maintain the idiomatic + * SEEK_END(0), SEEK_CUR(0) pattern. + */ if (whence == SEEK_END) base = dmabuf->size; else if (whence == SEEK_SET) @@ -558,7 +559,7 @@ static struct file *dma_buf_getfile(size_t size, int flags) * Override ->i_ino with the unique and dmabuffs specific * value. */ - inode->i_ino = atomic64_add_return(1, &dmabuf_inode); + inode->i_ino = atomic64_inc_return(&dmabuf_inode); flags &= O_ACCMODE | O_NONBLOCK; file = alloc_file_pseudo(inode, dma_buf_mnt, "dmabuf", flags, &dma_buf_fops); @@ -782,13 +783,14 @@ static void mangle_sg_table(struct sg_table *sg_table) /* To catch abuse of the underlying struct page by importers mix * up the bits, but take care to preserve the low SG_ bits to * not corrupt the sgt. The mixing is undone in __unmap_dma_buf - * before passing the sgt back to the exporter. */ + * before passing the sgt back to the exporter. + */ for_each_sgtable_sg(sg_table, sg, i) sg->page_link ^= ~0xffUL; #endif } -static struct sg_table * __map_dma_buf(struct dma_buf_attachment *attach, +static struct sg_table *__map_dma_buf(struct dma_buf_attachment *attach, enum dma_data_direction direction) { struct sg_table *sg_table; @@ -1296,10 +1298,12 @@ EXPORT_SYMBOL_NS_GPL(dma_buf_move_notify, DMA_BUF); * vmap interface is introduced. Note that on very old 32-bit architectures * vmalloc space might be limited and result in vmap calls failing. * - * Interfaces:: + * Interfaces: * - * void \*dma_buf_vmap(struct dma_buf \*dmabuf, struct iosys_map \*map) - * void dma_buf_vunmap(struct dma_buf \*dmabuf, struct iosys_map \*map) + * .. code-block:: c + * + * void *dma_buf_vmap(struct dma_buf *dmabuf, struct iosys_map *map) + * void dma_buf_vunmap(struct dma_buf *dmabuf, struct iosys_map *map) * * The vmap call can fail if there is no vmap support in the exporter, or if * it runs out of vmalloc space. Note that the dma-buf layer keeps a reference @@ -1356,10 +1360,11 @@ EXPORT_SYMBOL_NS_GPL(dma_buf_move_notify, DMA_BUF); * enough, since adding interfaces to intercept pagefaults and allow pte * shootdowns would increase the complexity quite a bit. * - * Interface:: + * Interface: + * + * .. code-block:: c * - * int dma_buf_mmap(struct dma_buf \*, struct vm_area_struct \*, - * unsigned long); + * int dma_buf_mmap(struct dma_buf *, struct vm_area_struct *, unsigned long); * * If the importing subsystem simply provides a special-purpose mmap call to * set up a mapping in userspace, calling do_mmap with &dma_buf.file will @@ -1694,7 +1699,7 @@ static int dma_buf_init_debugfs(void) dma_buf_debugfs_dir = d; - d = debugfs_create_file("bufinfo", S_IRUGO, dma_buf_debugfs_dir, + d = debugfs_create_file("bufinfo", 0444, dma_buf_debugfs_dir, NULL, &dma_buf_debug_fops); if (IS_ERR(d)) { pr_debug("dma_buf: debugfs: failed to create node bufinfo\n"); diff --git a/drivers/dma-buf/dma-fence.c b/drivers/dma-buf/dma-fence.c index 0393a9bba3a8a9b9977b6f7e00e0d20c6d890a33..f0cdd3e99d369cacaf82ebf54bef0312116777a1 100644 --- a/drivers/dma-buf/dma-fence.c +++ b/drivers/dma-buf/dma-fence.c @@ -309,8 +309,8 @@ bool dma_fence_begin_signalling(void) if (in_atomic()) return true; - /* ... and non-recursive readlock */ - lock_acquire(&dma_fence_lockdep_map, 0, 0, 1, 1, NULL, _RET_IP_); + /* ... and non-recursive successful read_trylock */ + lock_acquire(&dma_fence_lockdep_map, 0, 1, 1, 1, NULL, _RET_IP_); return false; } @@ -341,7 +341,7 @@ void __dma_fence_might_wait(void) lock_map_acquire(&dma_fence_lockdep_map); lock_map_release(&dma_fence_lockdep_map); if (tmp) - lock_acquire(&dma_fence_lockdep_map, 0, 0, 1, 1, NULL, _THIS_IP_); + lock_acquire(&dma_fence_lockdep_map, 0, 1, 1, 1, NULL, _THIS_IP_); } #endif @@ -412,7 +412,7 @@ int dma_fence_signal_timestamp(struct dma_fence *fence, ktime_t timestamp) unsigned long flags; int ret; - if (!fence) + if (WARN_ON(!fence)) return -EINVAL; spin_lock_irqsave(fence->lock, flags); @@ -464,7 +464,7 @@ int dma_fence_signal(struct dma_fence *fence) int ret; bool tmp; - if (!fence) + if (WARN_ON(!fence)) return -EINVAL; tmp = dma_fence_begin_signalling(); diff --git a/drivers/dma-buf/heaps/cma_heap.c b/drivers/dma-buf/heaps/cma_heap.c index 93be88b805fe7859feb8e9a581ba71eeb6434f0f..9512d050563a9ad0a735230c4870c3d3b3b01b25 100644 --- a/drivers/dma-buf/heaps/cma_heap.c +++ b/drivers/dma-buf/heaps/cma_heap.c @@ -309,13 +309,13 @@ static struct dma_buf *cma_heap_allocate(struct dma_heap *heap, struct page *page = cma_pages; while (nr_clear_pages > 0) { - void *vaddr = kmap_atomic(page); + void *vaddr = kmap_local_page(page); memset(vaddr, 0, PAGE_SIZE); - kunmap_atomic(vaddr); + kunmap_local(vaddr); /* * Avoid wasting time zeroing memory if the process - * has been killed by by SIGKILL + * has been killed by SIGKILL. */ if (fatal_signal_pending(current)) goto free_cma; @@ -366,7 +366,7 @@ static const struct dma_heap_ops cma_heap_ops = { .allocate = cma_heap_allocate, }; -static int __add_cma_heap(struct cma *cma, void *data) +static int __init __add_cma_heap(struct cma *cma, void *data) { struct cma_heap *cma_heap; struct dma_heap_export_info exp_info; @@ -391,7 +391,7 @@ static int __add_cma_heap(struct cma *cma, void *data) return 0; } -static int add_default_cma_heap(void) +static int __init add_default_cma_heap(void) { struct cma *default_cma = dev_get_cma_area(NULL); int ret = 0; diff --git a/drivers/dma-buf/heaps/system_heap.c b/drivers/dma-buf/heaps/system_heap.c index d78cdb9d01e5e404f5024ea04cd6acbffa5bd0f6..26d5dc89ea1663a0d078e3a5723ca3d8d12b935f 100644 --- a/drivers/dma-buf/heaps/system_heap.c +++ b/drivers/dma-buf/heaps/system_heap.c @@ -421,7 +421,7 @@ static const struct dma_heap_ops system_heap_ops = { .allocate = system_heap_allocate, }; -static int system_heap_create(void) +static int __init system_heap_create(void) { struct dma_heap_export_info exp_info; diff --git a/drivers/dma-buf/sw_sync.c b/drivers/dma-buf/sw_sync.c index c353029789cf1a3b9c4915552114c8a07fe1ff42..f5905d67dedbbbf55a7c6c516ac2c9ff20bd544a 100644 --- a/drivers/dma-buf/sw_sync.c +++ b/drivers/dma-buf/sw_sync.c @@ -173,11 +173,6 @@ static bool timeline_fence_signaled(struct dma_fence *fence) return !__dma_fence_is_later(fence->seqno, parent->value, fence->ops); } -static bool timeline_fence_enable_signaling(struct dma_fence *fence) -{ - return true; -} - static void timeline_fence_value_str(struct dma_fence *fence, char *str, int size) { @@ -211,7 +206,6 @@ static void timeline_fence_set_deadline(struct dma_fence *fence, ktime_t deadlin static const struct dma_fence_ops timeline_fence_ops = { .get_driver_name = timeline_fence_get_driver_name, .get_timeline_name = timeline_fence_get_timeline_name, - .enable_signaling = timeline_fence_enable_signaling, .signaled = timeline_fence_signaled, .release = timeline_fence_release, .fence_value_str = timeline_fence_value_str, diff --git a/drivers/dma-buf/udmabuf.c b/drivers/dma-buf/udmabuf.c index 047c3cd2cefff6ee326fc55dc7e937bf0e50942f..8ce1f074c2d32a0a9f59ff7184359e37d56548c6 100644 --- a/drivers/dma-buf/udmabuf.c +++ b/drivers/dma-buf/udmabuf.c @@ -27,15 +27,21 @@ MODULE_PARM_DESC(size_limit_mb, "Max size of a dmabuf, in megabytes. Default is struct udmabuf { pgoff_t pagecount; struct folio **folios; + + /** + * Unlike folios, pinned_folios is only used for unpin. + * So, nr_pinned is not the same to pagecount, the pinned_folios + * only set each folio which already pinned when udmabuf_create. + * Note that, since a folio may be pinned multiple times, each folio + * can be added to pinned_folios multiple times, depending on how many + * times the folio has been pinned when create. + */ + pgoff_t nr_pinned; + struct folio **pinned_folios; + struct sg_table *sg; struct miscdevice *device; pgoff_t *offsets; - struct list_head unpin_list; -}; - -struct udmabuf_folio { - struct folio *folio; - struct list_head list; }; static vm_fault_t udmabuf_vm_fault(struct vm_fault *vmf) @@ -43,7 +49,8 @@ static vm_fault_t udmabuf_vm_fault(struct vm_fault *vmf) struct vm_area_struct *vma = vmf->vma; struct udmabuf *ubuf = vma->vm_private_data; pgoff_t pgoff = vmf->pgoff; - unsigned long pfn; + unsigned long addr, pfn; + vm_fault_t ret; if (pgoff >= ubuf->pagecount) return VM_FAULT_SIGBUS; @@ -51,7 +58,35 @@ static vm_fault_t udmabuf_vm_fault(struct vm_fault *vmf) pfn = folio_pfn(ubuf->folios[pgoff]); pfn += ubuf->offsets[pgoff] >> PAGE_SHIFT; - return vmf_insert_pfn(vma, vmf->address, pfn); + ret = vmf_insert_pfn(vma, vmf->address, pfn); + if (ret & VM_FAULT_ERROR) + return ret; + + /* pre fault */ + pgoff = vma->vm_pgoff; + addr = vma->vm_start; + + for (; addr < vma->vm_end; pgoff++, addr += PAGE_SIZE) { + if (addr == vmf->address) + continue; + + if (WARN_ON(pgoff >= ubuf->pagecount)) + break; + + pfn = folio_pfn(ubuf->folios[pgoff]); + pfn += ubuf->offsets[pgoff] >> PAGE_SHIFT; + + /** + * If the below vmf_insert_pfn() fails, we do not return an + * error here during this pre-fault step. However, an error + * will be returned if the failure occurs when the addr is + * truly accessed. + */ + if (vmf_insert_pfn(vma, addr, pfn) & VM_FAULT_ERROR) + break; + } + + return ret; } static const struct vm_operations_struct udmabuf_vm_ops = { @@ -74,21 +109,29 @@ static int mmap_udmabuf(struct dma_buf *buf, struct vm_area_struct *vma) static int vmap_udmabuf(struct dma_buf *buf, struct iosys_map *map) { struct udmabuf *ubuf = buf->priv; - struct page **pages; + unsigned long *pfns; void *vaddr; pgoff_t pg; dma_resv_assert_held(buf->resv); - pages = kmalloc_array(ubuf->pagecount, sizeof(*pages), GFP_KERNEL); - if (!pages) + /** + * HVO may free tail pages, so just use pfn to map each folio + * into vmalloc area. + */ + pfns = kvmalloc_array(ubuf->pagecount, sizeof(*pfns), GFP_KERNEL); + if (!pfns) return -ENOMEM; - for (pg = 0; pg < ubuf->pagecount; pg++) - pages[pg] = &ubuf->folios[pg]->page; + for (pg = 0; pg < ubuf->pagecount; pg++) { + unsigned long pfn = folio_pfn(ubuf->folios[pg]); + + pfn += ubuf->offsets[pg] >> PAGE_SHIFT; + pfns[pg] = pfn; + } - vaddr = vm_map_ram(pages, ubuf->pagecount, -1); - kfree(pages); + vaddr = vmap_pfn(pfns, ubuf->pagecount, PAGE_KERNEL); + kvfree(pfns); if (!vaddr) return -EINVAL; @@ -159,34 +202,42 @@ static void unmap_udmabuf(struct dma_buf_attachment *at, return put_sg_table(at->dev, sg, direction); } -static void unpin_all_folios(struct list_head *unpin_list) +static void unpin_all_folios(struct udmabuf *ubuf) { - struct udmabuf_folio *ubuf_folio; + pgoff_t i; - while (!list_empty(unpin_list)) { - ubuf_folio = list_first_entry(unpin_list, - struct udmabuf_folio, list); - unpin_folio(ubuf_folio->folio); + for (i = 0; i < ubuf->nr_pinned; ++i) + unpin_folio(ubuf->pinned_folios[i]); - list_del(&ubuf_folio->list); - kfree(ubuf_folio); - } + kvfree(ubuf->pinned_folios); } -static int add_to_unpin_list(struct list_head *unpin_list, - struct folio *folio) +static __always_inline int init_udmabuf(struct udmabuf *ubuf, pgoff_t pgcnt) { - struct udmabuf_folio *ubuf_folio; + ubuf->folios = kvmalloc_array(pgcnt, sizeof(*ubuf->folios), GFP_KERNEL); + if (!ubuf->folios) + return -ENOMEM; - ubuf_folio = kzalloc(sizeof(*ubuf_folio), GFP_KERNEL); - if (!ubuf_folio) + ubuf->offsets = kvcalloc(pgcnt, sizeof(*ubuf->offsets), GFP_KERNEL); + if (!ubuf->offsets) + return -ENOMEM; + + ubuf->pinned_folios = kvmalloc_array(pgcnt, + sizeof(*ubuf->pinned_folios), + GFP_KERNEL); + if (!ubuf->pinned_folios) return -ENOMEM; - ubuf_folio->folio = folio; - list_add_tail(&ubuf_folio->list, unpin_list); return 0; } +static __always_inline void deinit_udmabuf(struct udmabuf *ubuf) +{ + unpin_all_folios(ubuf); + kvfree(ubuf->offsets); + kvfree(ubuf->folios); +} + static void release_udmabuf(struct dma_buf *buf) { struct udmabuf *ubuf = buf->priv; @@ -195,9 +246,7 @@ static void release_udmabuf(struct dma_buf *buf) if (ubuf->sg) put_sg_table(dev, ubuf->sg, DMA_BIDIRECTIONAL); - unpin_all_folios(&ubuf->unpin_list); - kfree(ubuf->offsets); - kfree(ubuf->folios); + deinit_udmabuf(ubuf); kfree(ubuf); } @@ -254,9 +303,6 @@ static int check_memfd_seals(struct file *memfd) { int seals; - if (!memfd) - return -EBADFD; - if (!shmem_file(memfd) && !is_file_hugepages(memfd)) return -EBADFD; @@ -291,100 +337,116 @@ static int export_udmabuf(struct udmabuf *ubuf, return dma_buf_fd(buf, flags); } +static long udmabuf_pin_folios(struct udmabuf *ubuf, struct file *memfd, + loff_t start, loff_t size, struct folio **folios) +{ + pgoff_t nr_pinned = ubuf->nr_pinned; + pgoff_t upgcnt = ubuf->pagecount; + u32 cur_folio, cur_pgcnt; + pgoff_t pgoff, pgcnt; + long nr_folios; + loff_t end; + + pgcnt = size >> PAGE_SHIFT; + end = start + (pgcnt << PAGE_SHIFT) - 1; + nr_folios = memfd_pin_folios(memfd, start, end, folios, pgcnt, &pgoff); + if (nr_folios <= 0) + return nr_folios ? nr_folios : -EINVAL; + + cur_pgcnt = 0; + for (cur_folio = 0; cur_folio < nr_folios; ++cur_folio) { + pgoff_t subpgoff = pgoff; + size_t fsize = folio_size(folios[cur_folio]); + + ubuf->pinned_folios[nr_pinned++] = folios[cur_folio]; + + for (; subpgoff < fsize; subpgoff += PAGE_SIZE) { + ubuf->folios[upgcnt] = folios[cur_folio]; + ubuf->offsets[upgcnt] = subpgoff; + ++upgcnt; + + if (++cur_pgcnt >= pgcnt) + goto end; + } + + /** + * In a given range, only the first subpage of the first folio + * has an offset, that is returned by memfd_pin_folios(). + * The first subpages of other folios (in the range) have an + * offset of 0. + */ + pgoff = 0; + } +end: + ubuf->pagecount = upgcnt; + ubuf->nr_pinned = nr_pinned; + return 0; +} + static long udmabuf_create(struct miscdevice *device, struct udmabuf_create_list *head, struct udmabuf_create_item *list) { - pgoff_t pgoff, pgcnt, pglimit, pgbuf = 0; - long nr_folios, ret = -EINVAL; - struct file *memfd = NULL; - struct folio **folios; + unsigned long max_nr_folios = 0; + struct folio **folios = NULL; + pgoff_t pgcnt = 0, pglimit; struct udmabuf *ubuf; - u32 i, j, k, flags; - loff_t end; + long ret = -EINVAL; + u32 i, flags; ubuf = kzalloc(sizeof(*ubuf), GFP_KERNEL); if (!ubuf) return -ENOMEM; - INIT_LIST_HEAD(&ubuf->unpin_list); pglimit = (size_limit_mb * 1024 * 1024) >> PAGE_SHIFT; for (i = 0; i < head->count; i++) { - if (!IS_ALIGNED(list[i].offset, PAGE_SIZE)) - goto err; - if (!IS_ALIGNED(list[i].size, PAGE_SIZE)) - goto err; - ubuf->pagecount += list[i].size >> PAGE_SHIFT; - if (ubuf->pagecount > pglimit) - goto err; + pgoff_t subpgcnt; + + if (!PAGE_ALIGNED(list[i].offset)) + goto err_noinit; + if (!PAGE_ALIGNED(list[i].size)) + goto err_noinit; + + subpgcnt = list[i].size >> PAGE_SHIFT; + pgcnt += subpgcnt; + if (pgcnt > pglimit) + goto err_noinit; + + max_nr_folios = max_t(unsigned long, subpgcnt, max_nr_folios); } - if (!ubuf->pagecount) - goto err; + if (!pgcnt) + goto err_noinit; - ubuf->folios = kmalloc_array(ubuf->pagecount, sizeof(*ubuf->folios), - GFP_KERNEL); - if (!ubuf->folios) { - ret = -ENOMEM; + ret = init_udmabuf(ubuf, pgcnt); + if (ret) goto err; - } - ubuf->offsets = kcalloc(ubuf->pagecount, sizeof(*ubuf->offsets), - GFP_KERNEL); - if (!ubuf->offsets) { + + folios = kvmalloc_array(max_nr_folios, sizeof(*folios), GFP_KERNEL); + if (!folios) { ret = -ENOMEM; goto err; } - pgbuf = 0; for (i = 0; i < head->count; i++) { - memfd = fget(list[i].memfd); - ret = check_memfd_seals(memfd); - if (ret < 0) - goto err; + struct file *memfd = fget(list[i].memfd); - pgcnt = list[i].size >> PAGE_SHIFT; - folios = kmalloc_array(pgcnt, sizeof(*folios), GFP_KERNEL); - if (!folios) { - ret = -ENOMEM; + if (!memfd) { + ret = -EBADFD; goto err; } - end = list[i].offset + (pgcnt << PAGE_SHIFT) - 1; - ret = memfd_pin_folios(memfd, list[i].offset, end, - folios, pgcnt, &pgoff); - if (ret <= 0) { - kfree(folios); - if (!ret) - ret = -EINVAL; + ret = check_memfd_seals(memfd); + if (ret < 0) { + fput(memfd); goto err; } - nr_folios = ret; - pgoff >>= PAGE_SHIFT; - for (j = 0, k = 0; j < pgcnt; j++) { - ubuf->folios[pgbuf] = folios[k]; - ubuf->offsets[pgbuf] = pgoff << PAGE_SHIFT; - - if (j == 0 || ubuf->folios[pgbuf-1] != folios[k]) { - ret = add_to_unpin_list(&ubuf->unpin_list, - folios[k]); - if (ret < 0) { - kfree(folios); - goto err; - } - } - - pgbuf++; - if (++pgoff == folio_nr_pages(folios[k])) { - pgoff = 0; - if (++k == nr_folios) - break; - } - } - - kfree(folios); + ret = udmabuf_pin_folios(ubuf, memfd, list[i].offset, + list[i].size, folios); fput(memfd); - memfd = NULL; + if (ret) + goto err; } flags = head->flags & UDMABUF_FLAGS_CLOEXEC ? O_CLOEXEC : 0; @@ -392,15 +454,14 @@ static long udmabuf_create(struct miscdevice *device, if (ret < 0) goto err; + kvfree(folios); return ret; err: - if (memfd) - fput(memfd); - unpin_all_folios(&ubuf->unpin_list); - kfree(ubuf->offsets); - kfree(ubuf->folios); + deinit_udmabuf(ubuf); +err_noinit: kfree(ubuf); + kvfree(folios); return ret; } diff --git a/drivers/firewire/net.c b/drivers/firewire/net.c index 7a4d1a478e33e2ccace6bc5b2ef184113f335ca3..1bf0e15c15408e68305306b231e6af54e591be40 100644 --- a/drivers/firewire/net.c +++ b/drivers/firewire/net.c @@ -28,7 +28,7 @@ #include #include -#include +#include #include #include diff --git a/drivers/firmware/arm_scmi/common.h b/drivers/firmware/arm_scmi/common.h index 6d9227db473ff67d3ab63301eefdbdeb063a8546..c4b8e7ff88aa2357fdf5739b96185f234d475b97 100644 --- a/drivers/firmware/arm_scmi/common.h +++ b/drivers/firmware/arm_scmi/common.h @@ -22,7 +22,7 @@ #include #include -#include +#include #include "protocols.h" #include "notify.h" diff --git a/drivers/firmware/arm_scmi/protocols.h b/drivers/firmware/arm_scmi/protocols.h index 8e95f53bd7b76aec08d78721e3a3b523e82cf68a..aaee57cdcd5589ee8c3f28f782ba5f84fd83d792 100644 --- a/drivers/firmware/arm_scmi/protocols.h +++ b/drivers/firmware/arm_scmi/protocols.h @@ -22,7 +22,7 @@ #include #include -#include +#include #define PROTOCOL_REV_MINOR_MASK GENMASK(15, 0) #define PROTOCOL_REV_MAJOR_MASK GENMASK(31, 16) diff --git a/drivers/firmware/dmi_scan.c b/drivers/firmware/dmi_scan.c index 23b002e4d4a0be5f72408ea485da93c0f6a46840..fde0656481cc9577b05b781b703a8071e8d3fc4e 100644 --- a/drivers/firmware/dmi_scan.c +++ b/drivers/firmware/dmi_scan.c @@ -9,7 +9,7 @@ #include #include #include -#include +#include #ifndef SMBIOS_ENTRY_POINT_SCAN_START #define SMBIOS_ENTRY_POINT_SCAN_START 0xF0000 diff --git a/drivers/firmware/efi/fdtparams.c b/drivers/firmware/efi/fdtparams.c index 0ec83ba580972f24a19f4f4d10f609119197cfc2..b815d2a754eef33b5157830fc739ca47dd666d3f 100644 --- a/drivers/firmware/efi/fdtparams.c +++ b/drivers/firmware/efi/fdtparams.c @@ -8,7 +8,7 @@ #include #include -#include +#include enum { SYSTAB, diff --git a/drivers/firmware/efi/libstub/riscv-stub.c b/drivers/firmware/efi/libstub/riscv-stub.c index c96d6dcee86c20656e8b6c9504734c66b26854c1..e7d9204baee3126acf0c7cbd3df3d0c257a5a30a 100644 --- a/drivers/firmware/efi/libstub/riscv-stub.c +++ b/drivers/firmware/efi/libstub/riscv-stub.c @@ -7,7 +7,7 @@ #include #include -#include +#include #include "efistub.h" diff --git a/drivers/firmware/efi/libstub/riscv.c b/drivers/firmware/efi/libstub/riscv.c index 8022b104c3e6ec22af349a10ca2c6e9b155a411c..f66f33ceb99e3028cbb3dd38598a8909c8d48c54 100644 --- a/drivers/firmware/efi/libstub/riscv.c +++ b/drivers/firmware/efi/libstub/riscv.c @@ -7,7 +7,7 @@ #include #include -#include +#include #include "efistub.h" diff --git a/drivers/firmware/efi/libstub/zboot.c b/drivers/firmware/efi/libstub/zboot.c index 1ceace956758682f592f6fe3f280b7260f7ca562..af23b3c502282f9bd644c38af445875c225cdf42 100644 --- a/drivers/firmware/efi/libstub/zboot.c +++ b/drivers/firmware/efi/libstub/zboot.c @@ -3,7 +3,7 @@ #include #include #include -#include +#include #include "efistub.h" diff --git a/drivers/firmware/sysfb.c b/drivers/firmware/sysfb.c index 02a07d3d0d40a91770b5039d818bf944813800f5..a3df782fa687b0f14a2646eccaf635c3bb247b2b 100644 --- a/drivers/firmware/sysfb.c +++ b/drivers/firmware/sysfb.c @@ -67,9 +67,11 @@ static bool sysfb_unregister(void) void sysfb_disable(struct device *dev) { struct screen_info *si = &screen_info; + struct device *parent; mutex_lock(&disable_lock); - if (!dev || dev == sysfb_parent_dev(si)) { + parent = sysfb_parent_dev(si); + if (!dev || !parent || dev == parent) { sysfb_unregister(); disabled = true; } diff --git a/drivers/fpga/microchip-spi.c b/drivers/fpga/microchip-spi.c index 2a82c726d6e59c9a29feb3d4271eae4b19d0b88f..6134cea86ac8560c76a53d029d143a8235d2675c 100644 --- a/drivers/fpga/microchip-spi.c +++ b/drivers/fpga/microchip-spi.c @@ -3,7 +3,7 @@ * Microchip Polarfire FPGA programming over slave SPI interface. */ -#include +#include #include #include #include diff --git a/drivers/fsi/fsi-occ.c b/drivers/fsi/fsi-occ.c index f58b158d097ce524bb5fa2a5fa0eb2966e407b01..a6d4c8f123a5a93552eed42c35b3924828f4f213 100644 --- a/drivers/fsi/fsi-occ.c +++ b/drivers/fsi/fsi-occ.c @@ -20,7 +20,7 @@ #include #include #include -#include +#include #define OCC_SRAM_BYTES 4096 #define OCC_CMD_DATA_BYTES 4090 diff --git a/drivers/gpio/gpio-davinci.c b/drivers/gpio/gpio-davinci.c index b54fef6b1e121f5e1a6a8bb417a02d334da3379a..76b58c70b2577f80ce7127892010d6a366f3122e 100644 --- a/drivers/gpio/gpio-davinci.c +++ b/drivers/gpio/gpio-davinci.c @@ -253,7 +253,7 @@ static int davinci_gpio_probe(struct platform_device *pdev) * serve as EDMA event triggers. */ -static void gpio_irq_disable(struct irq_data *d) +static void gpio_irq_mask(struct irq_data *d) { struct davinci_gpio_regs __iomem *g = irq2regs(d); uintptr_t mask = (uintptr_t)irq_data_get_irq_handler_data(d); @@ -262,7 +262,7 @@ static void gpio_irq_disable(struct irq_data *d) writel_relaxed(mask, &g->clr_rising); } -static void gpio_irq_enable(struct irq_data *d) +static void gpio_irq_unmask(struct irq_data *d) { struct davinci_gpio_regs __iomem *g = irq2regs(d); uintptr_t mask = (uintptr_t)irq_data_get_irq_handler_data(d); @@ -288,8 +288,8 @@ static int gpio_irq_type(struct irq_data *d, unsigned trigger) static struct irq_chip gpio_irqchip = { .name = "GPIO", - .irq_enable = gpio_irq_enable, - .irq_disable = gpio_irq_disable, + .irq_unmask = gpio_irq_unmask, + .irq_mask = gpio_irq_mask, .irq_set_type = gpio_irq_type, .flags = IRQCHIP_SET_TYPE_MASKED | IRQCHIP_SKIP_SET_WAKE, }; @@ -472,7 +472,7 @@ static int davinci_gpio_irq_setup(struct platform_device *pdev) return PTR_ERR(clk); } - if (chips->gpio_unbanked) { + if (!chips->gpio_unbanked) { irq = devm_irq_alloc_descs(dev, -1, 0, ngpio, 0); if (irq < 0) { dev_err(dev, "Couldn't allocate IRQ numbers\n"); diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index c6afbf434366bc5f7a5a09aedeb2ccf201c1ce58..d5952ab7752c2a8ecc1b04abaa2588455d24e578 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -114,12 +114,12 @@ const char *gpiod_get_label(struct gpio_desc *desc) srcu_read_lock_held(&desc->gdev->desc_srcu)); if (test_bit(FLAG_USED_AS_IRQ, &flags)) - return label->str ?: "interrupt"; + return label ? label->str : "interrupt"; if (!test_bit(FLAG_REQUESTED, &flags)) return NULL; - return label->str; + return label ? label->str : NULL; } static void desc_free_label(struct rcu_head *rh) diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig index 1cb5a4f1929335fcf0a135ccf7cc30acf958da8c..5504721007cc190e7d768d42aa9633baa0115f5e 100644 --- a/drivers/gpu/drm/Kconfig +++ b/drivers/gpu/drm/Kconfig @@ -9,9 +9,6 @@ menuconfig DRM tristate "Direct Rendering Manager (XFree86 4.1.0 and higher DRI support)" depends on (AGP || AGP=n) && !EMULATED_CMPXCHG && HAS_DMA select DRM_PANEL_ORIENTATION_QUIRKS - select DRM_KMS_HELPER if DRM_FBDEV_EMULATION - select FB_CORE if DRM_FBDEV_EMULATION - select FB_SYSMEM_HELPERS_DEFERRED if DRM_FBDEV_EMULATION select HDMI select I2C select DMA_SHARED_BUFFER @@ -152,6 +149,7 @@ config DRM_PANIC_SCREEN config DRM_PANIC_SCREEN_QR_CODE bool "Add a panic screen with a QR code" depends on DRM_PANIC && RUST + select ZLIB_DEFLATE help This option adds a QR code generator, and a panic screen with a QR code. The QR code will contain the last lines of kmsg and other debug @@ -210,9 +208,47 @@ config DRM_DEBUG_MODESET_LOCK If in doubt, say "N". +config DRM_CLIENT + bool + depends on DRM + help + Enables support for DRM clients. DRM drivers that need + struct drm_client_dev and its interfaces should select this + option. Drivers that support the default clients should + select DRM_CLIENT_SELECTION instead. + +config DRM_CLIENT_LIB + tristate + depends on DRM + select DRM_KMS_HELPER if DRM_FBDEV_EMULATION + select FB_CORE if DRM_FBDEV_EMULATION + help + This option enables the DRM client library and selects all + modules and components according to the enabled clients. + +config DRM_CLIENT_SELECTION + tristate + depends on DRM + select DRM_CLIENT_LIB if DRM_FBDEV_EMULATION + help + Drivers that support in-kernel DRM clients have to select this + option. + +config DRM_CLIENT_SETUP + bool + depends on DRM_CLIENT_SELECTION + help + Enables the DRM client selection. DRM drivers that support the + default clients should select DRM_CLIENT_SELECTION instead. + +menu "Supported DRM clients" + depends on DRM_CLIENT_SELECTION + config DRM_FBDEV_EMULATION bool "Enable legacy fbdev support for your modesetting driver" - depends on DRM + depends on DRM_CLIENT_SELECTION + select DRM_CLIENT + select DRM_CLIENT_SETUP select FRAMEBUFFER_CONSOLE_DETECT_PRIMARY if FRAMEBUFFER_CONSOLE default FB help @@ -251,6 +287,8 @@ config DRM_FBDEV_LEAK_PHYS_SMEM If in doubt, say "N" or spread the word to your closed source library vendor. +endmenu + config DRM_LOAD_EDID_FIRMWARE bool "Allow to specify an EDID data set instead of probing for it" depends on DRM @@ -320,19 +358,21 @@ config DRM_TTM_HELPER tristate depends on DRM select DRM_TTM + select FB_SYSMEM_HELPERS_DEFERRED if DRM_FBDEV_EMULATION help Helpers for ttm-based gem objects config DRM_GEM_DMA_HELPER tristate depends on DRM - select FB_DMAMEM_HELPERS if DRM_FBDEV_EMULATION + select FB_DMAMEM_HELPERS_DEFERRED if DRM_FBDEV_EMULATION help Choose this if you need the GEM DMA helper functions config DRM_GEM_SHMEM_HELPER tristate depends on DRM && MMU + select FB_SYSMEM_HELPERS_DEFERRED if DRM_FBDEV_EMULATION help Choose this if you need the GEM shmem helper functions @@ -472,6 +512,7 @@ source "drivers/gpu/drm/imagination/Kconfig" config DRM_HYPERV tristate "DRM Support for Hyper-V synthetic video device" depends on DRM && PCI && MMU && HYPERV + select DRM_CLIENT_SELECTION select DRM_KMS_HELPER select DRM_GEM_SHMEM_HELPER help diff --git a/drivers/gpu/drm/Makefile b/drivers/gpu/drm/Makefile index 784229d4504dcb7d4ad6427fe238b024c5946946..463afad1b5ca6275e61223adc8ca036c3d4d6b03 100644 --- a/drivers/gpu/drm/Makefile +++ b/drivers/gpu/drm/Makefile @@ -34,15 +34,12 @@ endif subdir-ccflags-$(CONFIG_DRM_WERROR) += -Werror drm-y := \ - drm_aperture.o \ drm_atomic.o \ drm_atomic_uapi.o \ drm_auth.o \ drm_blend.o \ drm_bridge.o \ drm_cache.o \ - drm_client.o \ - drm_client_modeset.o \ drm_color_mgmt.o \ drm_connector.o \ drm_crtc.o \ @@ -68,6 +65,7 @@ drm-y := \ drm_prime.o \ drm_print.o \ drm_property.o \ + drm_rect.o \ drm_syncobj.o \ drm_sysfs.o \ drm_trace_points.o \ @@ -75,6 +73,10 @@ drm-y := \ drm_vblank_work.o \ drm_vma_manager.o \ drm_writeback.o +drm-$(CONFIG_DRM_CLIENT) += \ + drm_client.o \ + drm_client_event.o \ + drm_client_modeset.o drm-$(CONFIG_DRM_LIB_RANDOM) += lib/drm_random.o drm-$(CONFIG_COMPAT) += drm_ioc32.o drm-$(CONFIG_DRM_PANEL) += drm_panel.o @@ -140,13 +142,20 @@ drm_kms_helper-y := \ drm_modeset_helper.o \ drm_plane_helper.o \ drm_probe_helper.o \ - drm_rect.o \ drm_self_refresh_helper.o \ drm_simple_kms_helper.o drm_kms_helper-$(CONFIG_DRM_PANEL_BRIDGE) += bridge/panel.o drm_kms_helper-$(CONFIG_DRM_FBDEV_EMULATION) += drm_fb_helper.o obj-$(CONFIG_DRM_KMS_HELPER) += drm_kms_helper.o +# +# DRM clients +# + +drm_client_lib-y := drm_client_setup.o +drm_client_lib-$(CONFIG_DRM_FBDEV_EMULATION) += drm_fbdev_client.o +obj-$(CONFIG_DRM_CLIENT_LIB) += drm_client_lib.o + # # Drivers and the rest # diff --git a/drivers/gpu/drm/amd/amdgpu/Kconfig b/drivers/gpu/drm/amd/amdgpu/Kconfig index 0051fb1b437fb853f21af4afa351522f51180d6e..41fa3377d9cf566294c6f86eedd8b31a22c77510 100644 --- a/drivers/gpu/drm/amd/amdgpu/Kconfig +++ b/drivers/gpu/drm/amd/amdgpu/Kconfig @@ -5,7 +5,10 @@ config DRM_AMDGPU depends on DRM && PCI && MMU depends on !UML select FW_LOADER + select DRM_CLIENT + select DRM_CLIENT_SELECTION select DRM_DISPLAY_DP_HELPER + select DRM_DISPLAY_DSC_HELPER select DRM_DISPLAY_HDMI_HELPER select DRM_DISPLAY_HDCP_HELPER select DRM_DISPLAY_HELPER diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c index 9435af2e6bdc01895776c17215a363ec42bcfafd..9abf29b58ac75a9be2f7e1406b22e2040cf9b3f2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c @@ -299,7 +299,7 @@ static int suspend_resume_compute_scheduler(struct amdgpu_device *adev, bool sus if (r) goto out; } else { - drm_sched_start(&ring->sched); + drm_sched_start(&ring->sched, 0); } } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index c2394c8b4d6b21f5dfc05da533007f3c32cf191d..5a1ae08817baa7be0aeb7f557213e07035b3ea16 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -25,6 +25,8 @@ * Alex Deucher * Jerome Glisse */ + +#include #include #include #include @@ -35,10 +37,9 @@ #include #include -#include #include +#include #include -#include #include #include #include @@ -4199,7 +4200,7 @@ int amdgpu_device_init(struct amdgpu_device *adev, return r; /* Get rid of things like offb */ - r = drm_aperture_remove_conflicting_pci_framebuffers(adev->pdev, &amdgpu_kms_driver); + r = aperture_remove_conflicting_pci_devices(adev->pdev, amdgpu_kms_driver.name); if (r) return r; @@ -4711,13 +4712,13 @@ unprepare: * amdgpu_device_suspend - initiate device suspend * * @dev: drm dev pointer - * @fbcon : notify the fbdev of suspend + * @notify_clients: notify in-kernel DRM clients * * Puts the hw in the suspend state (all asics). * Returns 0 for success or an error on failure. * Called at driver suspend. */ -int amdgpu_device_suspend(struct drm_device *dev, bool fbcon) +int amdgpu_device_suspend(struct drm_device *dev, bool notify_clients) { struct amdgpu_device *adev = drm_to_adev(dev); int r = 0; @@ -4737,8 +4738,8 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon) if (amdgpu_acpi_smart_shift_update(dev, AMDGPU_SS_DEV_D3)) DRM_WARN("smart shift update failed\n"); - if (fbcon) - drm_fb_helper_set_suspend_unlocked(adev_to_drm(adev)->fb_helper, true); + if (notify_clients) + drm_client_dev_suspend(adev_to_drm(adev), false); cancel_delayed_work_sync(&adev->delayed_init_work); @@ -4773,13 +4774,13 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon) * amdgpu_device_resume - initiate device resume * * @dev: drm dev pointer - * @fbcon : notify the fbdev of resume + * @notify_clients: notify in-kernel DRM clients * * Bring the hw back to operating state (all asics). * Returns 0 for success or an error on failure. * Called at driver resume. */ -int amdgpu_device_resume(struct drm_device *dev, bool fbcon) +int amdgpu_device_resume(struct drm_device *dev, bool notify_clients) { struct amdgpu_device *adev = drm_to_adev(dev); int r = 0; @@ -4835,8 +4836,8 @@ exit: /* Make sure IB tests flushed */ flush_delayed_work(&adev->delayed_init_work); - if (fbcon) - drm_fb_helper_set_suspend_unlocked(adev_to_drm(adev)->fb_helper, false); + if (notify_clients) + drm_client_dev_resume(adev_to_drm(adev), false); amdgpu_ras_resume(adev); @@ -5448,7 +5449,7 @@ int amdgpu_do_asic_reset(struct list_head *device_list_handle, if (r) goto out; - drm_fb_helper_set_suspend_unlocked(adev_to_drm(tmp_adev)->fb_helper, false); + drm_client_dev_resume(adev_to_drm(tmp_adev), false); /* * The GPU enters bad state once faulty pages @@ -5734,7 +5735,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev, */ amdgpu_unregister_gpu_instance(tmp_adev); - drm_fb_helper_set_suspend_unlocked(adev_to_drm(tmp_adev)->fb_helper, true); + drm_client_dev_suspend(adev_to_drm(tmp_adev), false); /* disable ras on ALL IPs */ if (!need_emergency_restart && @@ -5824,7 +5825,7 @@ skip_hw_reset: if (!amdgpu_ring_sched_ready(ring)) continue; - drm_sched_start(&ring->sched); + drm_sched_start(&ring->sched, 0); } if (!drm_drv_uses_atomic_modeset(adev_to_drm(tmp_adev)) && !job_signaled) @@ -6331,7 +6332,7 @@ void amdgpu_pci_resume(struct pci_dev *pdev) if (!amdgpu_ring_sched_ready(ring)) continue; - drm_sched_start(&ring->sched); + drm_sched_start(&ring->sched, 0); } amdgpu_device_unset_mp1_state(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 81d9877c87357d6dcef27f3df10d9dbf086bc813..7273c98c3963b837edf1503ccec03df4bfb171d9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -23,6 +23,7 @@ */ #include +#include #include #include #include @@ -2365,11 +2366,15 @@ retry_init: */ if (adev->mode_info.mode_config_initialized && !list_empty(&adev_to_drm(adev)->mode_config.connector_list)) { + const struct drm_format_info *format; + /* select 8 bpp console on low vram cards */ if (adev->gmc.real_vram_size <= (32*1024*1024)) - drm_fbdev_ttm_setup(adev_to_drm(adev), 8); + format = drm_format_info(DRM_FORMAT_C8); else - drm_fbdev_ttm_setup(adev_to_drm(adev), 32); + format = NULL; + + drm_client_setup(adev_to_drm(adev), format); } ret = amdgpu_debugfs_init(adev); @@ -2982,6 +2987,7 @@ static const struct drm_driver amdgpu_kms_driver = { .num_ioctls = ARRAY_SIZE(amdgpu_ioctls_kms), .dumb_create = amdgpu_mode_dumb_create, .dumb_map_offset = amdgpu_mode_dumb_mmap, + DRM_FBDEV_TTM_DRIVER_OPS, .fops = &amdgpu_driver_kms_fops, .release = &amdgpu_driver_release_kms, #ifdef CONFIG_PROC_FS @@ -3008,6 +3014,7 @@ const struct drm_driver amdgpu_partition_driver = { .num_ioctls = ARRAY_SIZE(amdgpu_ioctls_kms), .dumb_create = amdgpu_mode_dumb_create, .dumb_map_offset = amdgpu_mode_dumb_mmap, + DRM_FBDEV_TTM_DRIVER_OPS, .fops = &amdgpu_driver_kms_fops, .release = &amdgpu_driver_release_kms, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c index 16f2605ac50b9964c39d378f01963e8bc5fba9e5..fffa4430784f46e4bb983925839bde5dc1bc6fa7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c @@ -149,7 +149,7 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job) atomic_inc(&ring->adev->gpu_reset_counter); amdgpu_fence_driver_force_completion(ring); if (amdgpu_ring_sched_ready(ring)) - drm_sched_start(&ring->sched); + drm_sched_start(&ring->sched, 0); goto exit; } } diff --git a/drivers/gpu/drm/amd/amdgpu/atom.c b/drivers/gpu/drm/amd/amdgpu/atom.c index 09715b506468df3779423e5bcadd25fbac35b5fa..81d195d366ceba5bcf9a89be4614de3ace65033f 100644 --- a/drivers/gpu/drm/amd/amdgpu/atom.c +++ b/drivers/gpu/drm/amd/amdgpu/atom.c @@ -27,7 +27,7 @@ #include #include -#include +#include #include diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 6e79028c5d7897d5636aa0bc49c790f1dd243de0..60c617fcc97ee783aa7fa3d3451e453d9bd07767 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -770,6 +770,12 @@ static void dmub_hpd_callback(struct amdgpu_device *adev, return; } + /* Skip DMUB HPD IRQ in suspend/resume. We will probe them later. */ + if (notify->type == DMUB_NOTIFICATION_HPD && adev->in_suspend) { + DRM_INFO("Skip DMUB HPD IRQ callback in suspend/resume\n"); + return; + } + link_index = notify->link_index; link = adev->dm.dc->links[link_index]; dev = adev->dm.ddev; @@ -2026,7 +2032,8 @@ static int amdgpu_dm_init(struct amdgpu_device *adev) DRM_ERROR("amdgpu: failed to initialize vblank_workqueue.\n"); } - if (adev->dm.dc->caps.ips_support && adev->dm.dc->config.disable_ips == DMUB_IPS_ENABLE) + if (adev->dm.dc->caps.ips_support && + adev->dm.dc->config.disable_ips != DMUB_IPS_DISABLE_ALL) adev->dm.idle_workqueue = idle_create_workqueue(adev); if (adev->dm.dc->caps.max_links > 0 && adev->family >= AMDGPU_FAMILY_RV) { @@ -6735,12 +6742,21 @@ create_stream_for_sink(struct drm_connector *connector, if (stream->signal == SIGNAL_TYPE_DISPLAY_PORT || stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST || stream->signal == SIGNAL_TYPE_EDP) { + const struct dc_edid_caps *edid_caps; + unsigned int disable_colorimetry = 0; + + if (aconnector->dc_sink) { + edid_caps = &aconnector->dc_sink->edid_caps; + disable_colorimetry = edid_caps->panel_patch.disable_colorimetry; + } + // // should decide stream support vsc sdp colorimetry capability // before building vsc info packet // stream->use_vsc_sdp_for_colorimetry = stream->link->dpcd_caps.dpcd_rev.raw >= 0x14 && - stream->link->dpcd_caps.dprx_feature.bits.VSC_SDP_COLORIMETRY_SUPPORTED; + stream->link->dpcd_caps.dprx_feature.bits.VSC_SDP_COLORIMETRY_SUPPORTED && + !disable_colorimetry; if (stream->out_transfer_func.tf == TRANSFER_FUNCTION_GAMMA22) tf = TRANSFER_FUNC_GAMMA_22; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c index 50109d13d9671ea2c087086b157547602c38934b..069e0195e50a422ccd2903b11d593dd665059e6a 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c @@ -73,6 +73,10 @@ static void apply_edid_quirks(struct edid *edid, struct dc_edid_caps *edid_caps) DRM_DEBUG_DRIVER("Clearing DPCD 0x317 on monitor with panel id %X\n", panel_id); edid_caps->panel_patch.remove_sink_ext_caps = true; break; + case drm_edid_encode_panel_id('S', 'D', 'C', 0x4154): + DRM_DEBUG_DRIVER("Disabling VSC on monitor with panel id %X\n", panel_id); + edid_caps->panel_patch.disable_colorimetry = true; + break; default: return; } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c index 83a31b97e96bf6739e837a7c4251e6c10b774517..a08e8a0b696c60f65514476ab7e6994f0937fe6e 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c @@ -1027,6 +1027,7 @@ static int try_disable_dsc(struct drm_atomic_state *state, int remaining_to_try = 0; int ret; uint16_t fec_overhead_multiplier_x1000 = get_fec_overhead_multiplier(dc_link); + int var_pbn; for (i = 0; i < count; i++) { if (vars[i + k].dsc_enabled @@ -1057,13 +1058,18 @@ static int try_disable_dsc(struct drm_atomic_state *state, break; DRM_DEBUG_DRIVER("MST_DSC index #%d, try no compression\n", next_index); + var_pbn = vars[next_index].pbn; vars[next_index].pbn = kbps_to_peak_pbn(params[next_index].bw_range.stream_kbps, fec_overhead_multiplier_x1000); ret = drm_dp_atomic_find_time_slots(state, params[next_index].port->mgr, params[next_index].port, vars[next_index].pbn); - if (ret < 0) + if (ret < 0) { + DRM_DEBUG_DRIVER("%s:%d MST_DSC index #%d, failed to set pbn to the state, %d\n", + __func__, __LINE__, next_index, ret); + vars[next_index].pbn = var_pbn; return ret; + } ret = drm_dp_mst_atomic_check(state); if (ret == 0) { @@ -1071,14 +1077,17 @@ static int try_disable_dsc(struct drm_atomic_state *state, vars[next_index].dsc_enabled = false; vars[next_index].bpp_x16 = 0; } else { - DRM_DEBUG_DRIVER("MST_DSC index #%d, restore minimum compression\n", next_index); - vars[next_index].pbn = kbps_to_peak_pbn(params[next_index].bw_range.max_kbps, fec_overhead_multiplier_x1000); + DRM_DEBUG_DRIVER("MST_DSC index #%d, restore optimized pbn value\n", next_index); + vars[next_index].pbn = var_pbn; ret = drm_dp_atomic_find_time_slots(state, params[next_index].port->mgr, params[next_index].port, vars[next_index].pbn); - if (ret < 0) + if (ret < 0) { + DRM_DEBUG_DRIVER("%s:%d MST_DSC index #%d, failed to set pbn to the state, %d\n", + __func__, __LINE__, next_index, ret); return ret; + } } tried[next_index] = true; diff --git a/drivers/gpu/drm/amd/display/dc/dc_types.h b/drivers/gpu/drm/amd/display/dc/dc_types.h index fd6dca73571434ca65ee38aa1bc2495ef65f4668..6d7989b751e2cecbc8f5cbe837f1ce43a20d94d4 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_types.h +++ b/drivers/gpu/drm/amd/display/dc/dc_types.h @@ -178,6 +178,7 @@ struct dc_panel_patch { unsigned int skip_avmute; unsigned int mst_start_top_delay; unsigned int remove_sink_ext_caps; + unsigned int disable_colorimetry; }; struct dc_edid_caps { diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_policy.c b/drivers/gpu/drm/amd/display/dc/dml2/dml2_policy.c index c4c52173ef2240d181fef8309891cc921535fc4e..11c904ae29586d8b6b179a4011894bb58d6dcc8b 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_policy.c +++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_policy.c @@ -303,7 +303,6 @@ void build_unoptimized_policy_settings(enum dml_project_id project, struct dml_m if (project == dml_project_dcn35 || project == dml_project_dcn351) { policy->DCCProgrammingAssumesScanDirectionUnknownFinal = false; - policy->EnhancedPrefetchScheduleAccelerationFinal = 0; policy->AllowForPStateChangeOrStutterInVBlankFinal = dml_prefetch_support_uclk_fclk_and_stutter_if_possible; /*new*/ policy->UseOnlyMaxPrefetchModes = 1; } diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c index da9101b83e8c1ea421c90100376fdaea47435d39..70abd32ce2ad18c1475a1355437d0ef72e154b3c 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c @@ -766,6 +766,7 @@ static const struct dc_debug_options debug_defaults_drv = { .disable_dmub_reallow_idle = false, .static_screen_wait_frames = 2, .notify_dpia_hr_bw = true, + .min_disp_clk_khz = 50000, }; static const struct dc_panel_config panel_config_defaults = { diff --git a/drivers/gpu/drm/arm/Kconfig b/drivers/gpu/drm/arm/Kconfig index ddf20708370f9906800d198fe4d5bc634a4ca83f..c901ac00c0c3a8f356bd53d97305c6b39b3e6662 100644 --- a/drivers/gpu/drm/arm/Kconfig +++ b/drivers/gpu/drm/arm/Kconfig @@ -6,6 +6,7 @@ config DRM_HDLCD tristate "ARM HDLCD" depends on DRM && OF && (ARM || ARM64 || COMPILE_TEST) depends on COMMON_CLK + select DRM_CLIENT_SELECTION select DRM_KMS_HELPER select DRM_GEM_DMA_HELPER help @@ -27,6 +28,7 @@ config DRM_MALI_DISPLAY tristate "ARM Mali Display Processor" depends on DRM && OF && (ARM || ARM64 || COMPILE_TEST) depends on COMMON_CLK + select DRM_CLIENT_SELECTION select DRM_KMS_HELPER select DRM_GEM_DMA_HELPER select VIDEOMODE_HELPERS diff --git a/drivers/gpu/drm/arm/display/Kconfig b/drivers/gpu/drm/arm/display/Kconfig index 4acc4285a4eb06dd5c3e462963e50df75a587484..415c10a6374bc4eeb6c1c46a4e37f62a3eee71ee 100644 --- a/drivers/gpu/drm/arm/display/Kconfig +++ b/drivers/gpu/drm/arm/display/Kconfig @@ -3,6 +3,7 @@ config DRM_KOMEDA tristate "ARM Komeda display driver" depends on DRM && OF depends on COMMON_CLK + select DRM_CLIENT_SELECTION select DRM_KMS_HELPER select DRM_GEM_DMA_HELPER select VIDEOMODE_HELPERS diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_drv.c b/drivers/gpu/drm/arm/display/komeda/komeda_drv.c index 55c3773befde25a823f9dadc342d20bc18cc06bb..6d475bb34002ee4936685996ba912e1215512b56 100644 --- a/drivers/gpu/drm/arm/display/komeda/komeda_drv.c +++ b/drivers/gpu/drm/arm/display/komeda/komeda_drv.c @@ -9,7 +9,7 @@ #include #include #include -#include +#include #include #include #include "komeda_dev.h" @@ -84,7 +84,7 @@ static int komeda_platform_probe(struct platform_device *pdev) } dev_set_drvdata(dev, mdrv); - drm_fbdev_dma_setup(&mdrv->kms->base, 32); + drm_client_setup(&mdrv->kms->base, NULL); return 0; diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_kms.c b/drivers/gpu/drm/arm/display/komeda/komeda_kms.c index e5eb5d672bcd7d8900c26662f12953d8ba3b4d19..1e7b1fcb2848e72c19c44f11786e7eb91791ab3b 100644 --- a/drivers/gpu/drm/arm/display/komeda/komeda_kms.c +++ b/drivers/gpu/drm/arm/display/komeda/komeda_kms.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include #include @@ -58,6 +59,7 @@ static irqreturn_t komeda_kms_irq_handler(int irq, void *data) static const struct drm_driver komeda_kms_driver = { .driver_features = DRIVER_GEM | DRIVER_MODESET | DRIVER_ATOMIC, DRM_GEM_DMA_DRIVER_OPS_WITH_DUMB_CREATE(komeda_gem_dma_dumb_create), + DRM_FBDEV_DMA_DRIVER_OPS, .fops = &komeda_cma_fops, .name = "komeda", .desc = "Arm Komeda Display Processor driver", diff --git a/drivers/gpu/drm/arm/hdlcd_drv.c b/drivers/gpu/drm/arm/hdlcd_drv.c index 32be9e370049564f9adc99250495adb5366302c0..cd4389809d42d3d469b5c02afaaf96c2d5989bc3 100644 --- a/drivers/gpu/drm/arm/hdlcd_drv.c +++ b/drivers/gpu/drm/arm/hdlcd_drv.c @@ -9,6 +9,7 @@ * ARM HDLCD Driver */ +#include #include #include #include @@ -21,8 +22,8 @@ #include #include -#include #include +#include #include #include #include @@ -228,6 +229,7 @@ DEFINE_DRM_GEM_DMA_FOPS(fops); static const struct drm_driver hdlcd_driver = { .driver_features = DRIVER_GEM | DRIVER_MODESET | DRIVER_ATOMIC, DRM_GEM_DMA_DRIVER_OPS, + DRM_FBDEV_DMA_DRIVER_OPS, .fops = &fops, .name = "hdlcd", .desc = "ARM HDLCD Controller DRM", @@ -285,7 +287,7 @@ static int hdlcd_drm_bind(struct device *dev) */ if (hdlcd_read(hdlcd, HDLCD_REG_COMMAND)) { hdlcd_write(hdlcd, HDLCD_REG_COMMAND, 0); - drm_aperture_remove_framebuffers(&hdlcd_driver); + aperture_remove_all_conflicting_devices(hdlcd_driver.name); } drm_mode_config_reset(drm); @@ -299,7 +301,7 @@ static int hdlcd_drm_bind(struct device *dev) if (ret) goto err_register; - drm_fbdev_dma_setup(drm, 32); + drm_client_setup(drm, NULL); return 0; diff --git a/drivers/gpu/drm/arm/malidp_drv.c b/drivers/gpu/drm/arm/malidp_drv.c index 6682131d29104464a30f66d512782d785b4e4120..4cb25004b84fec2c83ddaa1ac06179d3c5ebe866 100644 --- a/drivers/gpu/drm/arm/malidp_drv.c +++ b/drivers/gpu/drm/arm/malidp_drv.c @@ -18,6 +18,7 @@ #include #include +#include #include #include #include @@ -562,6 +563,7 @@ static void malidp_debugfs_init(struct drm_minor *minor) static const struct drm_driver malidp_driver = { .driver_features = DRIVER_GEM | DRIVER_MODESET | DRIVER_ATOMIC, DRM_GEM_DMA_DRIVER_OPS_WITH_DUMB_CREATE(malidp_dumb_create), + DRM_FBDEV_DMA_DRIVER_OPS, #ifdef CONFIG_DEBUG_FS .debugfs_init = malidp_debugfs_init, #endif @@ -852,7 +854,7 @@ static int malidp_bind(struct device *dev) if (ret) goto register_fail; - drm_fbdev_dma_setup(drm, 32); + drm_client_setup(drm, NULL); return 0; diff --git a/drivers/gpu/drm/armada/Kconfig b/drivers/gpu/drm/armada/Kconfig index e5597d7c9ae1a8b215b93df704448eb5b5f7616e..b22c891a670bee78ff2ea7b215fc251468f05173 100644 --- a/drivers/gpu/drm/armada/Kconfig +++ b/drivers/gpu/drm/armada/Kconfig @@ -2,6 +2,7 @@ config DRM_ARMADA tristate "DRM support for Marvell Armada SoCs" depends on DRM && HAVE_CLK && ARM && MMU + select DRM_CLIENT_SELECTION select DRM_KMS_HELPER select FB_IOMEM_HELPERS if DRM_FBDEV_EMULATION help diff --git a/drivers/gpu/drm/armada/armada_drm.h b/drivers/gpu/drm/armada/armada_drm.h index c303e8c7ff6c76475a478cd568b932eaf09da84b..3c0ff221a43b507947adc7984074958864ab85d4 100644 --- a/drivers/gpu/drm/armada/armada_drm.h +++ b/drivers/gpu/drm/armada/armada_drm.h @@ -16,6 +16,8 @@ struct armada_crtc; struct armada_gem_object; struct clk; struct drm_display_mode; +struct drm_fb_helper; +struct drm_fb_helper_surface_size; static inline void armada_updatel(uint32_t val, uint32_t mask, void __iomem *ptr) @@ -74,10 +76,13 @@ struct armada_private { #define drm_to_armada_dev(dev) container_of(dev, struct armada_private, drm) #if defined(CONFIG_DRM_FBDEV_EMULATION) -void armada_fbdev_setup(struct drm_device *dev); +int armada_fbdev_driver_fbdev_probe(struct drm_fb_helper *fbh, + struct drm_fb_helper_surface_size *sizes); +#define ARMADA_FBDEV_DRIVER_OPS \ + .fbdev_probe = armada_fbdev_driver_fbdev_probe #else -static inline void armada_fbdev_setup(struct drm_device *dev) -{ } +#define ARMADA_FBDEV_DRIVER_OPS \ + .fbdev_probe = NULL #endif int armada_overlay_plane_create(struct drm_device *, unsigned long); diff --git a/drivers/gpu/drm/armada/armada_drv.c b/drivers/gpu/drm/armada/armada_drv.c index e51ecc4f7ef4483a6009faad52e5d4d23b5d5943..5c26f0409478a47678ec14581423666ad116bae3 100644 --- a/drivers/gpu/drm/armada/armada_drv.c +++ b/drivers/gpu/drm/armada/armada_drv.c @@ -3,6 +3,7 @@ * Copyright (C) 2012 Russell King */ +#include #include #include #include @@ -10,8 +11,8 @@ #include #include -#include #include +#include #include #include #include @@ -39,6 +40,7 @@ DEFINE_DRM_GEM_FOPS(armada_drm_fops); static const struct drm_driver armada_drm_driver = { .gem_prime_import = armada_gem_prime_import, .dumb_create = armada_gem_dumb_create, + ARMADA_FBDEV_DRIVER_OPS, .major = 1, .minor = 0, .name = "armada-drm", @@ -91,7 +93,7 @@ static int armada_drm_bind(struct device *dev) } /* Remove early framebuffers */ - ret = drm_aperture_remove_framebuffers(&armada_drm_driver); + ret = aperture_remove_all_conflicting_devices(armada_drm_driver.name); if (ret) { dev_err(dev, "[" DRM_NAME ":%s] can't kick out simple-fb: %d\n", __func__, ret); @@ -137,7 +139,7 @@ static int armada_drm_bind(struct device *dev) armada_drm_debugfs_init(priv->drm.primary); #endif - armada_fbdev_setup(&priv->drm); + drm_client_setup(&priv->drm, NULL); return 0; diff --git a/drivers/gpu/drm/armada/armada_fbdev.c b/drivers/gpu/drm/armada/armada_fbdev.c index d223176912b634921a23b40af960ee5f896a8c68..6ee7ce04ee7138835a57f7431162fc733982a658 100644 --- a/drivers/gpu/drm/armada/armada_fbdev.c +++ b/drivers/gpu/drm/armada/armada_fbdev.c @@ -39,8 +39,10 @@ static const struct fb_ops armada_fb_ops = { .fb_destroy = armada_fbdev_fb_destroy, }; -static int armada_fbdev_create(struct drm_fb_helper *fbh, - struct drm_fb_helper_surface_size *sizes) +static const struct drm_fb_helper_funcs armada_fbdev_helper_funcs; + +int armada_fbdev_driver_fbdev_probe(struct drm_fb_helper *fbh, + struct drm_fb_helper_surface_size *sizes) { struct drm_device *dev = fbh->dev; struct drm_mode_fb_cmd2 mode; @@ -98,6 +100,7 @@ static int armada_fbdev_create(struct drm_fb_helper *fbh, info->fix.smem_len = obj->obj.size; info->screen_size = obj->obj.size; info->screen_base = ptr; + fbh->funcs = &armada_fbdev_helper_funcs; fbh->fb = &dfb->fb; drm_fb_helper_fill_info(info, fbh, sizes); @@ -112,109 +115,3 @@ static int armada_fbdev_create(struct drm_fb_helper *fbh, dfb->fb.funcs->destroy(&dfb->fb); return ret; } - -static int armada_fb_probe(struct drm_fb_helper *fbh, - struct drm_fb_helper_surface_size *sizes) -{ - int ret = 0; - - if (!fbh->fb) { - ret = armada_fbdev_create(fbh, sizes); - if (ret == 0) - ret = 1; - } - return ret; -} - -static const struct drm_fb_helper_funcs armada_fb_helper_funcs = { - .fb_probe = armada_fb_probe, -}; - -/* - * Fbdev client and struct drm_client_funcs - */ - -static void armada_fbdev_client_unregister(struct drm_client_dev *client) -{ - struct drm_fb_helper *fbh = drm_fb_helper_from_client(client); - - if (fbh->info) { - drm_fb_helper_unregister_info(fbh); - } else { - drm_client_release(&fbh->client); - drm_fb_helper_unprepare(fbh); - kfree(fbh); - } -} - -static int armada_fbdev_client_restore(struct drm_client_dev *client) -{ - drm_fb_helper_lastclose(client->dev); - - return 0; -} - -static int armada_fbdev_client_hotplug(struct drm_client_dev *client) -{ - struct drm_fb_helper *fbh = drm_fb_helper_from_client(client); - struct drm_device *dev = client->dev; - int ret; - - if (dev->fb_helper) - return drm_fb_helper_hotplug_event(dev->fb_helper); - - ret = drm_fb_helper_init(dev, fbh); - if (ret) - goto err_drm_err; - - if (!drm_drv_uses_atomic_modeset(dev)) - drm_helper_disable_unused_functions(dev); - - ret = drm_fb_helper_initial_config(fbh); - if (ret) - goto err_drm_fb_helper_fini; - - return 0; - -err_drm_fb_helper_fini: - drm_fb_helper_fini(fbh); -err_drm_err: - drm_err(dev, "armada: Failed to setup fbdev emulation (ret=%d)\n", ret); - return ret; -} - -static const struct drm_client_funcs armada_fbdev_client_funcs = { - .owner = THIS_MODULE, - .unregister = armada_fbdev_client_unregister, - .restore = armada_fbdev_client_restore, - .hotplug = armada_fbdev_client_hotplug, -}; - -void armada_fbdev_setup(struct drm_device *dev) -{ - struct drm_fb_helper *fbh; - int ret; - - drm_WARN(dev, !dev->registered, "Device has not been registered.\n"); - drm_WARN(dev, dev->fb_helper, "fb_helper is already set!\n"); - - fbh = kzalloc(sizeof(*fbh), GFP_KERNEL); - if (!fbh) - return; - drm_fb_helper_prepare(dev, fbh, 32, &armada_fb_helper_funcs); - - ret = drm_client_init(dev, &fbh->client, "fbdev", &armada_fbdev_client_funcs); - if (ret) { - drm_err(dev, "Failed to register client: %d\n", ret); - goto err_drm_client_init; - } - - drm_client_register(&fbh->client); - - return; - -err_drm_client_init: - drm_fb_helper_unprepare(fbh); - kfree(fbh); - return; -} diff --git a/drivers/gpu/drm/aspeed/Kconfig b/drivers/gpu/drm/aspeed/Kconfig index 8137c39b057bb386a8a109d6ce0d817e91e341ac..6e68f20aac21b1dfb7e5d2c2630abf2b9cf3396f 100644 --- a/drivers/gpu/drm/aspeed/Kconfig +++ b/drivers/gpu/drm/aspeed/Kconfig @@ -4,6 +4,7 @@ config DRM_ASPEED_GFX depends on DRM && OF depends on (COMPILE_TEST || ARCH_ASPEED) depends on MMU + select DRM_CLIENT_SELECTION select DRM_KMS_HELPER select DRM_GEM_DMA_HELPER select DMA_CMA if HAVE_DMA_CONTIGUOUS diff --git a/drivers/gpu/drm/aspeed/aspeed_gfx_drv.c b/drivers/gpu/drm/aspeed/aspeed_gfx_drv.c index a7a6b70220eb8cc95919e97216d95a9690c82bd9..109023815fa2c6d072bda03eef5ec07658e4e2c8 100644 --- a/drivers/gpu/drm/aspeed/aspeed_gfx_drv.c +++ b/drivers/gpu/drm/aspeed/aspeed_gfx_drv.c @@ -14,6 +14,7 @@ #include #include +#include #include #include #include @@ -247,6 +248,7 @@ DEFINE_DRM_GEM_DMA_FOPS(fops); static const struct drm_driver aspeed_gfx_driver = { .driver_features = DRIVER_GEM | DRIVER_MODESET | DRIVER_ATOMIC, DRM_GEM_DMA_DRIVER_OPS, + DRM_FBDEV_DMA_DRIVER_OPS, .fops = &fops, .name = "aspeed-gfx-drm", .desc = "ASPEED GFX DRM", @@ -339,7 +341,7 @@ static int aspeed_gfx_probe(struct platform_device *pdev) if (ret) goto err_unload; - drm_fbdev_dma_setup(&priv->drm, 32); + drm_client_setup(&priv->drm, NULL); return 0; err_unload: diff --git a/drivers/gpu/drm/ast/Kconfig b/drivers/gpu/drm/ast/Kconfig index 563fa7a3b546c8d1ecdad397827c3648b8bf255e..da0663542e8a45caca565f0af2f93df82678cc91 100644 --- a/drivers/gpu/drm/ast/Kconfig +++ b/drivers/gpu/drm/ast/Kconfig @@ -2,6 +2,7 @@ config DRM_AST tristate "AST server chips" depends on DRM && PCI && MMU + select DRM_CLIENT_SELECTION select DRM_GEM_SHMEM_HELPER select DRM_KMS_HELPER select I2C diff --git a/drivers/gpu/drm/ast/ast_dp.c b/drivers/gpu/drm/ast/ast_dp.c index 00b364f9a71e547bc8679568566f10a423a13951..0e282b7b167c6b09116e6079d2842f6336213732 100644 --- a/drivers/gpu/drm/ast/ast_dp.c +++ b/drivers/gpu/drm/ast/ast_dp.c @@ -149,28 +149,22 @@ int ast_dp_launch(struct ast_device *ast) return 0; } -static bool ast_dp_power_is_on(struct ast_device *ast) +static bool ast_dp_get_phy_sleep(struct ast_device *ast) { - u8 vgacre3; + u8 vgacre3 = ast_get_index_reg(ast, AST_IO_VGACRI, 0xe3); - vgacre3 = ast_get_index_reg(ast, AST_IO_VGACRI, 0xe3); - - return !(vgacre3 & AST_DP_PHY_SLEEP); + return (vgacre3 & AST_IO_VGACRE3_DP_PHY_SLEEP); } -static void ast_dp_power_on_off(struct drm_device *dev, bool on) +static void ast_dp_set_phy_sleep(struct ast_device *ast, bool sleep) { - struct ast_device *ast = to_ast_device(dev); - // Read and Turn off DP PHY sleep - u8 bE3 = ast_get_index_reg_mask(ast, AST_IO_VGACRI, 0xE3, AST_DP_VIDEO_ENABLE); - - // Turn on DP PHY sleep - if (!on) - bE3 |= AST_DP_PHY_SLEEP; + u8 vgacre3 = 0x00; - // DP Power on/off - ast_set_index_reg_mask(ast, AST_IO_VGACRI, 0xE3, (u8) ~AST_DP_PHY_SLEEP, bE3); + if (sleep) + vgacre3 |= AST_IO_VGACRE3_DP_PHY_SLEEP; + ast_set_index_reg_mask(ast, AST_IO_VGACRI, 0xe3, (u8)~AST_IO_VGACRE3_DP_PHY_SLEEP, + vgacre3); msleep(50); } @@ -192,23 +186,39 @@ static void ast_dp_link_training(struct ast_device *ast) drm_err(dev, "Link training failed\n"); } -static void ast_dp_set_on_off(struct drm_device *dev, bool on) +static bool __ast_dp_wait_enable(struct ast_device *ast, bool enabled) { - struct ast_device *ast = to_ast_device(dev); - u8 video_on_off = on; - u32 i = 0; - - // Video On/Off - ast_set_index_reg_mask(ast, AST_IO_VGACRI, 0xE3, (u8) ~AST_DP_VIDEO_ENABLE, on); - - video_on_off <<= 4; - while (ast_get_index_reg_mask(ast, AST_IO_VGACRI, 0xDF, - ASTDP_MIRROR_VIDEO_ENABLE) != video_on_off) { - // wait 1 ms - mdelay(1); - if (++i > 200) - break; + u8 vgacrdf_test = 0x00; + u8 vgacrdf; + unsigned int i; + + if (enabled) + vgacrdf_test |= AST_IO_VGACRDF_DP_VIDEO_ENABLE; + + for (i = 0; i < 200; ++i) { + if (i) + mdelay(1); + vgacrdf = ast_get_index_reg_mask(ast, AST_IO_VGACRI, 0xdf, + AST_IO_VGACRDF_DP_VIDEO_ENABLE); + if (vgacrdf == vgacrdf_test) + return true; } + + return false; +} + +static void ast_dp_set_enable(struct ast_device *ast, bool enabled) +{ + struct drm_device *dev = &ast->base; + u8 vgacre3 = 0x00; + + if (enabled) + vgacre3 |= AST_IO_VGACRE3_DP_VIDEO_ENABLE; + + ast_set_index_reg_mask(ast, AST_IO_VGACRI, 0xe3, (u8)~AST_IO_VGACRE3_DP_VIDEO_ENABLE, + vgacre3); + + drm_WARN_ON(dev, !__ast_dp_wait_enable(ast, enabled)); } static void ast_dp_set_mode(struct drm_crtc *crtc, struct ast_vbios_mode_info *vbios_mode) @@ -317,26 +327,25 @@ static void ast_astdp_encoder_helper_atomic_mode_set(struct drm_encoder *encoder static void ast_astdp_encoder_helper_atomic_enable(struct drm_encoder *encoder, struct drm_atomic_state *state) { - struct drm_device *dev = encoder->dev; - struct ast_device *ast = to_ast_device(dev); + struct ast_device *ast = to_ast_device(encoder->dev); struct ast_connector *ast_connector = &ast->output.astdp.connector; if (ast_connector->physical_status == connector_status_connected) { - ast_dp_power_on_off(dev, AST_DP_POWER_ON); + ast_dp_set_phy_sleep(ast, false); ast_dp_link_training(ast); ast_wait_for_vretrace(ast); - ast_dp_set_on_off(dev, 1); + ast_dp_set_enable(ast, true); } } static void ast_astdp_encoder_helper_atomic_disable(struct drm_encoder *encoder, struct drm_atomic_state *state) { - struct drm_device *dev = encoder->dev; + struct ast_device *ast = to_ast_device(encoder->dev); - ast_dp_set_on_off(dev, 0); - ast_dp_power_on_off(dev, AST_DP_POWER_OFF); + ast_dp_set_enable(ast, false); + ast_dp_set_phy_sleep(ast, true); } static const struct drm_encoder_helper_funcs ast_astdp_encoder_helper_funcs = { @@ -383,22 +392,21 @@ static int ast_astdp_connector_helper_detect_ctx(struct drm_connector *connector bool force) { struct ast_connector *ast_connector = to_ast_connector(connector); - struct drm_device *dev = connector->dev; struct ast_device *ast = to_ast_device(connector->dev); enum drm_connector_status status = connector_status_disconnected; - bool power_is_on; + bool phy_sleep; mutex_lock(&ast->modeset_lock); - power_is_on = ast_dp_power_is_on(ast); - if (!power_is_on) - ast_dp_power_on_off(dev, true); + phy_sleep = ast_dp_get_phy_sleep(ast); + if (phy_sleep) + ast_dp_set_phy_sleep(ast, false); if (ast_astdp_is_connected(ast)) status = connector_status_connected; - if (!power_is_on && status == connector_status_disconnected) - ast_dp_power_on_off(dev, false); + if (phy_sleep && status == connector_status_disconnected) + ast_dp_set_phy_sleep(ast, true); mutex_unlock(&ast->modeset_lock); @@ -414,6 +422,10 @@ static const struct drm_connector_helper_funcs ast_astdp_connector_helper_funcs .detect_ctx = ast_astdp_connector_helper_detect_ctx, }; +/* + * Output + */ + static const struct drm_connector_funcs ast_astdp_connector_funcs = { .reset = drm_atomic_helper_connector_reset, .fill_modes = drm_helper_probe_single_connector_modes, @@ -422,34 +434,18 @@ static const struct drm_connector_funcs ast_astdp_connector_funcs = { .atomic_destroy_state = drm_atomic_helper_connector_destroy_state, }; -static int ast_astdp_connector_init(struct drm_device *dev, struct drm_connector *connector) -{ - int ret; - - ret = drm_connector_init(dev, connector, &ast_astdp_connector_funcs, - DRM_MODE_CONNECTOR_DisplayPort); - if (ret) - return ret; - - drm_connector_helper_add(connector, &ast_astdp_connector_helper_funcs); - - connector->interlace_allowed = 0; - connector->doublescan_allowed = 0; - - connector->polled = DRM_CONNECTOR_POLL_CONNECT | DRM_CONNECTOR_POLL_DISCONNECT; - - return 0; -} - int ast_astdp_output_init(struct ast_device *ast) { struct drm_device *dev = &ast->base; struct drm_crtc *crtc = &ast->crtc; - struct drm_encoder *encoder = &ast->output.astdp.encoder; - struct ast_connector *ast_connector = &ast->output.astdp.connector; - struct drm_connector *connector = &ast_connector->base; + struct drm_encoder *encoder; + struct ast_connector *ast_connector; + struct drm_connector *connector; int ret; + /* encoder */ + + encoder = &ast->output.astdp.encoder; ret = drm_encoder_init(dev, encoder, &ast_astdp_encoder_funcs, DRM_MODE_ENCODER_TMDS, NULL); if (ret) @@ -458,9 +454,20 @@ int ast_astdp_output_init(struct ast_device *ast) encoder->possible_crtcs = drm_crtc_mask(crtc); - ret = ast_astdp_connector_init(dev, connector); + /* connector */ + + ast_connector = &ast->output.astdp.connector; + connector = &ast_connector->base; + ret = drm_connector_init(dev, connector, &ast_astdp_connector_funcs, + DRM_MODE_CONNECTOR_DisplayPort); if (ret) return ret; + drm_connector_helper_add(connector, &ast_astdp_connector_helper_funcs); + + connector->interlace_allowed = 0; + connector->doublescan_allowed = 0; + connector->polled = DRM_CONNECTOR_POLL_CONNECT | DRM_CONNECTOR_POLL_DISCONNECT; + ast_connector->physical_status = connector->status; ret = drm_connector_attach_encoder(connector, encoder); diff --git a/drivers/gpu/drm/ast/ast_dp501.c b/drivers/gpu/drm/ast/ast_dp501.c index e4c636f4508207a7fb82c5c6f4049193819caa22..9e19d8c17730834bbbb8782b3d58999c79b96098 100644 --- a/drivers/gpu/drm/ast/ast_dp501.c +++ b/drivers/gpu/drm/ast/ast_dp501.c @@ -21,9 +21,9 @@ static void ast_release_firmware(void *data) ast->dp501_fw = NULL; } -static int ast_load_dp501_microcode(struct drm_device *dev) +static int ast_load_dp501_microcode(struct ast_device *ast) { - struct ast_device *ast = to_ast_device(dev); + struct drm_device *dev = &ast->base; int ret; ret = request_firmware(&ast->dp501_fw, "ast_dp501_fw.bin", dev->dev); @@ -109,10 +109,10 @@ static bool wait_fw_ready(struct ast_device *ast) } #endif -static bool ast_write_cmd(struct drm_device *dev, u8 data) +static bool ast_write_cmd(struct ast_device *ast, u8 data) { - struct ast_device *ast = to_ast_device(dev); int retry = 0; + if (wait_nack(ast)) { send_nack(ast); ast_set_index_reg_mask(ast, AST_IO_VGACRI, 0x9a, 0x00, data); @@ -131,10 +131,8 @@ static bool ast_write_cmd(struct drm_device *dev, u8 data) return false; } -static bool ast_write_data(struct drm_device *dev, u8 data) +static bool ast_write_data(struct ast_device *ast, u8 data) { - struct ast_device *ast = to_ast_device(dev); - if (wait_nack(ast)) { send_nack(ast); ast_set_index_reg_mask(ast, AST_IO_VGACRI, 0x9a, 0x00, data); @@ -175,10 +173,10 @@ static void clear_cmd(struct ast_device *ast) } #endif -static void ast_set_dp501_video_output(struct drm_device *dev, u8 mode) +static void ast_set_dp501_video_output(struct ast_device *ast, u8 mode) { - ast_write_cmd(dev, 0x40); - ast_write_data(dev, mode); + ast_write_cmd(ast, 0x40); + ast_write_data(ast, mode); msleep(10); } @@ -188,9 +186,8 @@ static u32 get_fw_base(struct ast_device *ast) return ast_mindwm(ast, 0x1e6e2104) & 0x7fffffff; } -bool ast_backup_fw(struct drm_device *dev, u8 *addr, u32 size) +bool ast_backup_fw(struct ast_device *ast, u8 *addr, u32 size) { - struct ast_device *ast = to_ast_device(dev); u32 i, data; u32 boot_address; @@ -207,9 +204,8 @@ bool ast_backup_fw(struct drm_device *dev, u8 *addr, u32 size) return false; } -static bool ast_launch_m68k(struct drm_device *dev) +static bool ast_launch_m68k(struct ast_device *ast) { - struct ast_device *ast = to_ast_device(dev); u32 i, data, len = 0; u32 boot_address; u8 *fw_addr = NULL; @@ -226,7 +222,7 @@ static bool ast_launch_m68k(struct drm_device *dev) len = 32*1024; } else { if (!ast->dp501_fw && - ast_load_dp501_microcode(dev) < 0) + ast_load_dp501_microcode(ast) < 0) return false; fw_addr = (u8 *)ast->dp501_fw->data; @@ -348,9 +344,8 @@ static int ast_dp512_read_edid_block(void *data, u8 *buf, unsigned int block, si return true; } -static bool ast_init_dvo(struct drm_device *dev) +static bool ast_init_dvo(struct ast_device *ast) { - struct ast_device *ast = to_ast_device(dev); u8 jreg; u32 data; ast_write32(ast, 0xf004, 0x1e6e0000); @@ -421,9 +416,8 @@ static bool ast_init_dvo(struct drm_device *dev) } -static void ast_init_analog(struct drm_device *dev) +static void ast_init_analog(struct ast_device *ast) { - struct ast_device *ast = to_ast_device(dev); u32 data; /* @@ -448,28 +442,28 @@ static void ast_init_analog(struct drm_device *dev) ast_set_index_reg_mask(ast, AST_IO_VGACRI, 0xa3, 0xcf, 0x00); } -void ast_init_3rdtx(struct drm_device *dev) +void ast_init_3rdtx(struct ast_device *ast) { - struct ast_device *ast = to_ast_device(dev); - u8 jreg; + u8 vgacrd1; if (IS_AST_GEN4(ast) || IS_AST_GEN5(ast)) { - jreg = ast_get_index_reg_mask(ast, AST_IO_VGACRI, 0xd1, 0xff); - switch (jreg & 0x0e) { - case 0x04: - ast_init_dvo(dev); + vgacrd1 = ast_get_index_reg_mask(ast, AST_IO_VGACRI, 0xd1, + AST_IO_VGACRD1_TX_TYPE_MASK); + switch (vgacrd1) { + case AST_IO_VGACRD1_TX_SIL164_VBIOS: + ast_init_dvo(ast); break; - case 0x08: - ast_launch_m68k(dev); + case AST_IO_VGACRD1_TX_DP501_VBIOS: + ast_launch_m68k(ast); break; - case 0x0c: - ast_init_dvo(dev); + case AST_IO_VGACRD1_TX_FW_EMBEDDED_FW: + ast_init_dvo(ast); break; default: - if (ast->tx_chip_types & BIT(AST_TX_SIL164)) - ast_init_dvo(dev); + if (ast->tx_chip == AST_TX_SIL164) + ast_init_dvo(ast); else - ast_init_analog(dev); + ast_init_analog(ast); } } } @@ -485,17 +479,17 @@ static const struct drm_encoder_funcs ast_dp501_encoder_funcs = { static void ast_dp501_encoder_helper_atomic_enable(struct drm_encoder *encoder, struct drm_atomic_state *state) { - struct drm_device *dev = encoder->dev; + struct ast_device *ast = to_ast_device(encoder->dev); - ast_set_dp501_video_output(dev, 1); + ast_set_dp501_video_output(ast, 1); } static void ast_dp501_encoder_helper_atomic_disable(struct drm_encoder *encoder, struct drm_atomic_state *state) { - struct drm_device *dev = encoder->dev; + struct ast_device *ast = to_ast_device(encoder->dev); - ast_set_dp501_video_output(dev, 0); + ast_set_dp501_video_output(ast, 0); } static const struct drm_encoder_helper_funcs ast_dp501_encoder_helper_funcs = { @@ -567,34 +561,22 @@ static const struct drm_connector_funcs ast_dp501_connector_funcs = { .atomic_destroy_state = drm_atomic_helper_connector_destroy_state, }; -static int ast_dp501_connector_init(struct drm_device *dev, struct drm_connector *connector) -{ - int ret; - - ret = drm_connector_init(dev, connector, &ast_dp501_connector_funcs, - DRM_MODE_CONNECTOR_DisplayPort); - if (ret) - return ret; - - drm_connector_helper_add(connector, &ast_dp501_connector_helper_funcs); - - connector->interlace_allowed = 0; - connector->doublescan_allowed = 0; - - connector->polled = DRM_CONNECTOR_POLL_CONNECT | DRM_CONNECTOR_POLL_DISCONNECT; - - return 0; -} +/* + * Output + */ int ast_dp501_output_init(struct ast_device *ast) { struct drm_device *dev = &ast->base; struct drm_crtc *crtc = &ast->crtc; - struct drm_encoder *encoder = &ast->output.dp501.encoder; - struct ast_connector *ast_connector = &ast->output.dp501.connector; - struct drm_connector *connector = &ast_connector->base; + struct drm_encoder *encoder; + struct ast_connector *ast_connector; + struct drm_connector *connector; int ret; + /* encoder */ + + encoder = &ast->output.dp501.encoder; ret = drm_encoder_init(dev, encoder, &ast_dp501_encoder_funcs, DRM_MODE_ENCODER_TMDS, NULL); if (ret) @@ -603,9 +585,20 @@ int ast_dp501_output_init(struct ast_device *ast) encoder->possible_crtcs = drm_crtc_mask(crtc); - ret = ast_dp501_connector_init(dev, connector); + /* connector */ + + ast_connector = &ast->output.dp501.connector; + connector = &ast_connector->base; + ret = drm_connector_init(dev, connector, &ast_dp501_connector_funcs, + DRM_MODE_CONNECTOR_DisplayPort); if (ret) return ret; + drm_connector_helper_add(connector, &ast_dp501_connector_helper_funcs); + + connector->interlace_allowed = 0; + connector->doublescan_allowed = 0; + connector->polled = DRM_CONNECTOR_POLL_CONNECT | DRM_CONNECTOR_POLL_DISCONNECT; + ast_connector->physical_status = connector->status; ret = drm_connector_attach_encoder(connector, encoder); diff --git a/drivers/gpu/drm/ast/ast_drv.c b/drivers/gpu/drm/ast/ast_drv.c index 3a908bb015fe33a09983d335bf3cc760bb13f8fa..4afe4be072efc9c08848896e1b7911b43576335c 100644 --- a/drivers/gpu/drm/ast/ast_drv.c +++ b/drivers/gpu/drm/ast/ast_drv.c @@ -26,12 +26,13 @@ * Authors: Dave Airlie */ +#include #include #include #include -#include #include +#include #include #include #include @@ -64,7 +65,8 @@ static const struct drm_driver ast_driver = { .minor = DRIVER_MINOR, .patchlevel = DRIVER_PATCHLEVEL, - DRM_GEM_SHMEM_DRIVER_OPS + DRM_GEM_SHMEM_DRIVER_OPS, + DRM_FBDEV_SHMEM_DRIVER_OPS, }; /* @@ -279,7 +281,7 @@ static int ast_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) struct drm_device *drm; bool need_post = false; - ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, &ast_driver); + ret = aperture_remove_conflicting_pci_devices(pdev, ast_driver.name); if (ret) return ret; @@ -360,7 +362,7 @@ static int ast_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (ret) return ret; - drm_fbdev_shmem_setup(drm, 32); + drm_client_setup(drm, NULL); return 0; } @@ -396,7 +398,7 @@ static int ast_drm_thaw(struct drm_device *dev) ast_enable_vga(ast->ioregs); ast_open_key(ast->ioregs); ast_enable_mmio(dev->dev, ast->ioregs); - ast_post_gpu(dev); + ast_post_gpu(ast); return drm_mode_config_helper_resume(dev); } diff --git a/drivers/gpu/drm/ast/ast_drv.h b/drivers/gpu/drm/ast/ast_drv.h index 91fe07cf7b07e30f091b75b2909c59faf20b30a2..21ce3769bf0d2c00d1565ee787e1f5f1810880c5 100644 --- a/drivers/gpu/drm/ast/ast_drv.h +++ b/drivers/gpu/drm/ast/ast_drv.h @@ -91,11 +91,6 @@ enum ast_tx_chip { AST_TX_ASTDP, }; -#define AST_TX_NONE_BIT BIT(AST_TX_NONE) -#define AST_TX_SIL164_BIT BIT(AST_TX_SIL164) -#define AST_TX_DP501_BIT BIT(AST_TX_DP501) -#define AST_TX_ASTDP_BIT BIT(AST_TX_ASTDP) - enum ast_config_mode { ast_use_p2a, ast_use_dt, @@ -187,10 +182,12 @@ struct ast_device { struct mutex modeset_lock; /* Protects access to modeset I/O registers in ioregs */ + enum ast_tx_chip tx_chip; + struct ast_plane primary_plane; struct ast_plane cursor_plane; struct drm_crtc crtc; - struct { + union { struct { struct drm_encoder encoder; struct ast_connector connector; @@ -211,7 +208,6 @@ struct ast_device { bool support_wide_screen; - unsigned long tx_chip_types; /* bitfield of enum ast_chip_type */ u8 *dp501_fw_addr; const struct firmware *dp501_fw; /* dp501 fw */ }; @@ -407,9 +403,6 @@ int ast_mode_config_init(struct ast_device *ast); #define AST_DP501_LINKRATE 0xf014 #define AST_DP501_EDID_DATA 0xf020 -#define AST_DP_POWER_ON true -#define AST_DP_POWER_OFF false - /* * ASTDP resoultion table: * EX: ASTDP_A_B_C: @@ -453,7 +446,7 @@ int ast_mode_config_init(struct ast_device *ast); int ast_mm_init(struct ast_device *ast); /* ast post */ -void ast_post_gpu(struct drm_device *dev); +void ast_post_gpu(struct ast_device *ast); u32 ast_mindwm(struct ast_device *ast, u32 r); void ast_moutdwm(struct ast_device *ast, u32 r, u32 v); void ast_patch_ahb_2500(void __iomem *regs); @@ -462,8 +455,8 @@ int ast_vga_output_init(struct ast_device *ast); int ast_sil164_output_init(struct ast_device *ast); /* ast dp501 */ -bool ast_backup_fw(struct drm_device *dev, u8 *addr, u32 size); -void ast_init_3rdtx(struct drm_device *dev); +bool ast_backup_fw(struct ast_device *ast, u8 *addr, u32 size); +void ast_init_3rdtx(struct ast_device *ast); int ast_dp501_output_init(struct ast_device *ast); /* aspeed DP */ diff --git a/drivers/gpu/drm/ast/ast_main.c b/drivers/gpu/drm/ast/ast_main.c index d836f2a4f9f3e0e6aac70d5eea0f2b9f0ade4ca8..bc37c65305d48604dc4be857a37ff29b55fbf44f 100644 --- a/drivers/gpu/drm/ast/ast_main.c +++ b/drivers/gpu/drm/ast/ast_main.c @@ -68,11 +68,33 @@ static void ast_detect_widescreen(struct ast_device *ast) static void ast_detect_tx_chip(struct ast_device *ast, bool need_post) { + static const char * const info_str[] = { + "analog VGA", + "Sil164 TMDS transmitter", + "DP501 DisplayPort transmitter", + "ASPEED DisplayPort transmitter", + }; + struct drm_device *dev = &ast->base; - u8 jreg; + u8 jreg, vgacrd1; + + /* + * Several of the listed TX chips are not explicitly supported + * by the ast driver. If these exist in real-world devices, they + * are most likely reported as VGA or SIL164 outputs. We warn here + * to get bug reports for these devices. If none come in for some + * time, we can begin to fail device probing on these values. + */ + vgacrd1 = ast_get_index_reg_mask(ast, AST_IO_VGACRI, 0xd1, AST_IO_VGACRD1_TX_TYPE_MASK); + drm_WARN(dev, vgacrd1 == AST_IO_VGACRD1_TX_ITE66121_VBIOS, + "ITE IT66121 detected, 0x%x, Gen%lu\n", vgacrd1, AST_GEN(ast)); + drm_WARN(dev, vgacrd1 == AST_IO_VGACRD1_TX_CH7003_VBIOS, + "Chrontel CH7003 detected, 0x%x, Gen%lu\n", vgacrd1, AST_GEN(ast)); + drm_WARN(dev, vgacrd1 == AST_IO_VGACRD1_TX_ANX9807_VBIOS, + "Analogix ANX9807 detected, 0x%x, Gen%lu\n", vgacrd1, AST_GEN(ast)); /* Check 3rd Tx option (digital output afaik) */ - ast->tx_chip_types |= AST_TX_NONE_BIT; + ast->tx_chip = AST_TX_NONE; /* * VGACRA3 Enhanced Color Mode Register, check if DVO is already @@ -85,7 +107,7 @@ static void ast_detect_tx_chip(struct ast_device *ast, bool need_post) if (!need_post) { jreg = ast_get_index_reg_mask(ast, AST_IO_VGACRI, 0xa3, 0xff); if (jreg & 0x80) - ast->tx_chip_types = AST_TX_SIL164_BIT; + ast->tx_chip = AST_TX_SIL164; } if (IS_AST_GEN4(ast) || IS_AST_GEN5(ast) || IS_AST_GEN6(ast)) { @@ -94,49 +116,42 @@ static void ast_detect_tx_chip(struct ast_device *ast, bool need_post) * the SOC scratch register #1 bits 11:8 (interestingly marked * as "reserved" in the spec) */ - jreg = ast_get_index_reg_mask(ast, AST_IO_VGACRI, 0xd1, 0xff); + jreg = ast_get_index_reg_mask(ast, AST_IO_VGACRI, 0xd1, + AST_IO_VGACRD1_TX_TYPE_MASK); switch (jreg) { - case 0x04: - ast->tx_chip_types = AST_TX_SIL164_BIT; + case AST_IO_VGACRD1_TX_SIL164_VBIOS: + ast->tx_chip = AST_TX_SIL164; break; - case 0x08: + case AST_IO_VGACRD1_TX_DP501_VBIOS: ast->dp501_fw_addr = drmm_kzalloc(dev, 32*1024, GFP_KERNEL); if (ast->dp501_fw_addr) { /* backup firmware */ - if (ast_backup_fw(dev, ast->dp501_fw_addr, 32*1024)) { + if (ast_backup_fw(ast, ast->dp501_fw_addr, 32*1024)) { drmm_kfree(dev, ast->dp501_fw_addr); ast->dp501_fw_addr = NULL; } } fallthrough; - case 0x0c: - ast->tx_chip_types = AST_TX_DP501_BIT; + case AST_IO_VGACRD1_TX_FW_EMBEDDED_FW: + ast->tx_chip = AST_TX_DP501; } } else if (IS_AST_GEN7(ast)) { - if (ast_get_index_reg_mask(ast, AST_IO_VGACRI, 0xD1, TX_TYPE_MASK) == - ASTDP_DPMCU_TX) { + if (ast_get_index_reg_mask(ast, AST_IO_VGACRI, 0xd1, AST_IO_VGACRD1_TX_TYPE_MASK) == + AST_IO_VGACRD1_TX_ASTDP) { int ret = ast_dp_launch(ast); if (!ret) - ast->tx_chip_types = AST_TX_ASTDP_BIT; + ast->tx_chip = AST_TX_ASTDP; } } - /* Print stuff for diagnostic purposes */ - if (ast->tx_chip_types & AST_TX_NONE_BIT) - drm_info(dev, "Using analog VGA\n"); - if (ast->tx_chip_types & AST_TX_SIL164_BIT) - drm_info(dev, "Using Sil164 TMDS transmitter\n"); - if (ast->tx_chip_types & AST_TX_DP501_BIT) - drm_info(dev, "Using DP501 DisplayPort transmitter\n"); - if (ast->tx_chip_types & AST_TX_ASTDP_BIT) - drm_info(dev, "Using ASPEED DisplayPort transmitter\n"); + drm_info(dev, "Using %s\n", info_str[ast->tx_chip]); } -static int ast_get_dram_info(struct drm_device *dev) +static int ast_get_dram_info(struct ast_device *ast) { + struct drm_device *dev = &ast->base; struct device_node *np = dev->dev->of_node; - struct ast_device *ast = to_ast_device(dev); uint32_t mcr_cfg, mcr_scu_mpll, mcr_scu_strap; uint32_t denum, num, div, ref_pll, dsel; @@ -278,7 +293,7 @@ struct drm_device *ast_device_create(struct pci_dev *pdev, ast_detect_widescreen(ast); ast_detect_tx_chip(ast, need_post); - ret = ast_get_dram_info(dev); + ret = ast_get_dram_info(ast); if (ret) return ERR_PTR(ret); @@ -286,7 +301,7 @@ struct drm_device *ast_device_create(struct pci_dev *pdev, ast->mclk, ast->dram_type, ast->dram_bus_width); if (need_post) - ast_post_gpu(dev); + ast_post_gpu(ast); ret = ast_mm_init(ast); if (ret) diff --git a/drivers/gpu/drm/ast/ast_mode.c b/drivers/gpu/drm/ast/ast_mode.c index ed496fb32bf349566f60690fc4d1bf4a51a00eb8..9d5321c81e68d6a5ee1b3fc32c1f422aeeb1d414 100644 --- a/drivers/gpu/drm/ast/ast_mode.c +++ b/drivers/gpu/drm/ast/ast_mode.c @@ -1287,9 +1287,9 @@ static const struct drm_crtc_funcs ast_crtc_funcs = { .atomic_destroy_state = ast_crtc_atomic_destroy_state, }; -static int ast_crtc_init(struct drm_device *dev) +static int ast_crtc_init(struct ast_device *ast) { - struct ast_device *ast = to_ast_device(dev); + struct drm_device *dev = &ast->base; struct drm_crtc *crtc = &ast->crtc; int ret; @@ -1396,28 +1396,26 @@ int ast_mode_config_init(struct ast_device *ast) if (ret) return ret; - ast_crtc_init(dev); + ret = ast_crtc_init(ast); + if (ret) + return ret; - if (ast->tx_chip_types & AST_TX_NONE_BIT) { + switch (ast->tx_chip) { + case AST_TX_NONE: ret = ast_vga_output_init(ast); - if (ret) - return ret; - } - if (ast->tx_chip_types & AST_TX_SIL164_BIT) { + break; + case AST_TX_SIL164: ret = ast_sil164_output_init(ast); - if (ret) - return ret; - } - if (ast->tx_chip_types & AST_TX_DP501_BIT) { + break; + case AST_TX_DP501: ret = ast_dp501_output_init(ast); - if (ret) - return ret; - } - if (ast->tx_chip_types & AST_TX_ASTDP_BIT) { + break; + case AST_TX_ASTDP: ret = ast_astdp_output_init(ast); - if (ret) - return ret; + break; } + if (ret) + return ret; drm_mode_config_reset(dev); diff --git a/drivers/gpu/drm/ast/ast_post.c b/drivers/gpu/drm/ast/ast_post.c index 65755798ab94a503fd8522aa8f435fc70b07e7aa..364030f97571d7fc1b11713c929d7279fa5b1137 100644 --- a/drivers/gpu/drm/ast/ast_post.c +++ b/drivers/gpu/drm/ast/ast_post.c @@ -34,16 +34,14 @@ #include "ast_dram_tables.h" #include "ast_drv.h" -static void ast_post_chip_2300(struct drm_device *dev); -static void ast_post_chip_2500(struct drm_device *dev); +static void ast_post_chip_2300(struct ast_device *ast); +static void ast_post_chip_2500(struct ast_device *ast); static const u8 extreginfo[] = { 0x0f, 0x04, 0x1c, 0xff }; static const u8 extreginfo_ast2300[] = { 0x0f, 0x04, 0x1f, 0xff }; -static void -ast_set_def_ext_reg(struct drm_device *dev) +static void ast_set_def_ext_reg(struct ast_device *ast) { - struct ast_device *ast = to_ast_device(dev); u8 i, index, reg; const u8 *ext_reg_info; @@ -252,9 +250,8 @@ cbr_start: -static void ast_init_dram_reg(struct drm_device *dev) +static void ast_init_dram_reg(struct ast_device *ast) { - struct ast_device *ast = to_ast_device(dev); u8 j; u32 data, temp, i; const struct ast_dramstruct *dram_reg_info; @@ -343,26 +340,24 @@ static void ast_init_dram_reg(struct drm_device *dev) } while ((j & 0x40) == 0); } -void ast_post_gpu(struct drm_device *dev) +void ast_post_gpu(struct ast_device *ast) { - struct ast_device *ast = to_ast_device(dev); - - ast_set_def_ext_reg(dev); + ast_set_def_ext_reg(ast); if (IS_AST_GEN7(ast)) { - if (ast->tx_chip_types & AST_TX_ASTDP_BIT) + if (ast->tx_chip == AST_TX_ASTDP) ast_dp_launch(ast); } else if (ast->config_mode == ast_use_p2a) { if (IS_AST_GEN6(ast)) - ast_post_chip_2500(dev); + ast_post_chip_2500(ast); else if (IS_AST_GEN5(ast) || IS_AST_GEN4(ast)) - ast_post_chip_2300(dev); + ast_post_chip_2300(ast); else - ast_init_dram_reg(dev); + ast_init_dram_reg(ast); - ast_init_3rdtx(dev); + ast_init_3rdtx(ast); } else { - if (ast->tx_chip_types & AST_TX_SIL164_BIT) + if (ast->tx_chip == AST_TX_SIL164) ast_set_index_reg_mask(ast, AST_IO_VGACRI, 0xa3, 0xcf, 0x80); /* Enable DVO */ } } @@ -1569,9 +1564,8 @@ ddr2_init_start: } -static void ast_post_chip_2300(struct drm_device *dev) +static void ast_post_chip_2300(struct ast_device *ast) { - struct ast_device *ast = to_ast_device(dev); struct ast2300_dram_param param; u32 temp; u8 reg; @@ -2038,9 +2032,9 @@ void ast_patch_ahb_2500(void __iomem *regs) __ast_moutdwm(regs, 0x1e6e207c, 0x08000000); /* clear fast reset */ } -void ast_post_chip_2500(struct drm_device *dev) +void ast_post_chip_2500(struct ast_device *ast) { - struct ast_device *ast = to_ast_device(dev); + struct drm_device *dev = &ast->base; u32 temp; u8 reg; diff --git a/drivers/gpu/drm/ast/ast_reg.h b/drivers/gpu/drm/ast/ast_reg.h index 040961cc1a198d9d6d003cddb647d98d57e9cb5d..2aadf07d135afadcaa57f23d3c74bbb38eb437ae 100644 --- a/drivers/gpu/drm/ast/ast_reg.h +++ b/drivers/gpu/drm/ast/ast_reg.h @@ -37,28 +37,29 @@ #define AST_IO_VGACRCB_HWC_16BPP BIT(0) /* set: ARGB4444, cleared: 2bpp palette */ #define AST_IO_VGACRCB_HWC_ENABLED BIT(1) -#define AST_IO_VGACRD1_MCU_FW_EXECUTING BIT(5) +#define AST_IO_VGACRD1_MCU_FW_EXECUTING BIT(5) +/* Display Transmitter Type */ +#define AST_IO_VGACRD1_TX_TYPE_MASK GENMASK(3, 1) +#define AST_IO_VGACRD1_NO_TX 0x00 +#define AST_IO_VGACRD1_TX_ITE66121_VBIOS 0x02 +#define AST_IO_VGACRD1_TX_SIL164_VBIOS 0x04 +#define AST_IO_VGACRD1_TX_CH7003_VBIOS 0x06 +#define AST_IO_VGACRD1_TX_DP501_VBIOS 0x08 +#define AST_IO_VGACRD1_TX_ANX9807_VBIOS 0x0a +#define AST_IO_VGACRD1_TX_FW_EMBEDDED_FW 0x0c /* special case of DP501 */ +#define AST_IO_VGACRD1_TX_ASTDP 0x0e + #define AST_IO_VGACRD7_EDID_VALID_FLAG BIT(0) #define AST_IO_VGACRDC_LINK_SUCCESS BIT(0) #define AST_IO_VGACRDF_HPD BIT(0) +#define AST_IO_VGACRDF_DP_VIDEO_ENABLE BIT(4) /* mirrors AST_IO_VGACRE3_DP_VIDEO_ENABLE */ +#define AST_IO_VGACRE3_DP_VIDEO_ENABLE BIT(0) +#define AST_IO_VGACRE3_DP_PHY_SLEEP BIT(4) #define AST_IO_VGACRE5_EDID_READ_DONE BIT(0) #define AST_IO_VGAIR1_R (0x5A) #define AST_IO_VGAIR1_VREFRESH BIT(3) -/* - * Display Transmitter Type - */ - -#define TX_TYPE_MASK GENMASK(3, 1) -#define NO_TX (0 << 1) -#define ITE66121_VBIOS_TX (1 << 1) -#define SI164_VBIOS_TX (2 << 1) -#define CH7003_VBIOS_TX (3 << 1) -#define DP501_VBIOS_TX (4 << 1) -#define ANX9807_VBIOS_TX (5 << 1) -#define TX_FW_EMBEDDED_FW_TX (6 << 1) -#define ASTDP_DPMCU_TX (7 << 1) #define AST_VRAM_INIT_STATUS_MASK GENMASK(7, 6) //#define AST_VRAM_INIT_BY_BMC BIT(7) @@ -68,18 +69,6 @@ * AST DisplayPort */ -/* Define for Soc scratched reg used on ASTDP */ -#define AST_DP_PHY_SLEEP BIT(4) -#define AST_DP_VIDEO_ENABLE BIT(0) - -/* - * CRDF[b4]: Mirror of AST_DP_VIDEO_ENABLE - * Precondition: A. ~AST_DP_PHY_SLEEP && - * B. DP_HPD && - * C. DP_LINK_SUCCESS - */ -#define ASTDP_MIRROR_VIDEO_ENABLE BIT(4) - /* * ASTDP setmode registers: * CRE0[7:0]: MISC0 ((0x00: 18-bpp) or (0x20: 24-bpp) diff --git a/drivers/gpu/drm/ast/ast_sil164.c b/drivers/gpu/drm/ast/ast_sil164.c index 496c7120e515536cae3496554e89bf7f7e8731d9..6a72268d2314c722a035faced2b2467a6f7045b7 100644 --- a/drivers/gpu/drm/ast/ast_sil164.c +++ b/drivers/gpu/drm/ast/ast_sil164.c @@ -71,52 +71,49 @@ static const struct drm_connector_funcs ast_sil164_connector_funcs = { .atomic_destroy_state = drm_atomic_helper_connector_destroy_state, }; -static int ast_sil164_connector_init(struct drm_device *dev, struct drm_connector *connector) +/* + * Output + */ + +int ast_sil164_output_init(struct ast_device *ast) { - struct ast_device *ast = to_ast_device(dev); + struct drm_device *dev = &ast->base; + struct drm_crtc *crtc = &ast->crtc; struct i2c_adapter *ddc; + struct drm_encoder *encoder; + struct ast_connector *ast_connector; + struct drm_connector *connector; int ret; + /* DDC */ + ddc = ast_ddc_create(ast); - if (IS_ERR(ddc)) { - ret = PTR_ERR(ddc); - drm_err(dev, "failed to add DDC bus for connector; ret=%d\n", ret); + if (IS_ERR(ddc)) + return PTR_ERR(ddc); + + /* encoder */ + + encoder = &ast->output.sil164.encoder; + ret = drm_encoder_init(dev, encoder, &ast_sil164_encoder_funcs, + DRM_MODE_ENCODER_TMDS, NULL); + if (ret) return ret; - } + encoder->possible_crtcs = drm_crtc_mask(crtc); + + /* connector */ + ast_connector = &ast->output.sil164.connector; + connector = &ast_connector->base; ret = drm_connector_init_with_ddc(dev, connector, &ast_sil164_connector_funcs, DRM_MODE_CONNECTOR_DVII, ddc); if (ret) return ret; - drm_connector_helper_add(connector, &ast_sil164_connector_helper_funcs); connector->interlace_allowed = 0; connector->doublescan_allowed = 0; - connector->polled = DRM_CONNECTOR_POLL_CONNECT | DRM_CONNECTOR_POLL_DISCONNECT; - return 0; -} - -int ast_sil164_output_init(struct ast_device *ast) -{ - struct drm_device *dev = &ast->base; - struct drm_crtc *crtc = &ast->crtc; - struct drm_encoder *encoder = &ast->output.sil164.encoder; - struct ast_connector *ast_connector = &ast->output.sil164.connector; - struct drm_connector *connector = &ast_connector->base; - int ret; - - ret = drm_encoder_init(dev, encoder, &ast_sil164_encoder_funcs, - DRM_MODE_ENCODER_TMDS, NULL); - if (ret) - return ret; - encoder->possible_crtcs = drm_crtc_mask(crtc); - - ret = ast_sil164_connector_init(dev, connector); - if (ret) - return ret; ast_connector->physical_status = connector->status; ret = drm_connector_attach_encoder(connector, encoder); diff --git a/drivers/gpu/drm/ast/ast_vga.c b/drivers/gpu/drm/ast/ast_vga.c index 3e815da43fbd638067016621eadb67118a0dabb6..5c79b773af57f9993c669545c2c3054888cb803b 100644 --- a/drivers/gpu/drm/ast/ast_vga.c +++ b/drivers/gpu/drm/ast/ast_vga.c @@ -71,52 +71,49 @@ static const struct drm_connector_funcs ast_vga_connector_funcs = { .atomic_destroy_state = drm_atomic_helper_connector_destroy_state, }; -static int ast_vga_connector_init(struct drm_device *dev, struct drm_connector *connector) +/* + * Output + */ + +int ast_vga_output_init(struct ast_device *ast) { - struct ast_device *ast = to_ast_device(dev); + struct drm_device *dev = &ast->base; + struct drm_crtc *crtc = &ast->crtc; struct i2c_adapter *ddc; + struct drm_encoder *encoder; + struct ast_connector *ast_connector; + struct drm_connector *connector; int ret; + /* DDC */ + ddc = ast_ddc_create(ast); - if (IS_ERR(ddc)) { - ret = PTR_ERR(ddc); - drm_err(dev, "failed to add DDC bus for connector; ret=%d\n", ret); + if (IS_ERR(ddc)) + return PTR_ERR(ddc); + + /* encoder */ + + encoder = &ast->output.vga.encoder; + ret = drm_encoder_init(dev, encoder, &ast_vga_encoder_funcs, + DRM_MODE_ENCODER_DAC, NULL); + if (ret) return ret; - } + encoder->possible_crtcs = drm_crtc_mask(crtc); + + /* connector */ + ast_connector = &ast->output.vga.connector; + connector = &ast_connector->base; ret = drm_connector_init_with_ddc(dev, connector, &ast_vga_connector_funcs, DRM_MODE_CONNECTOR_VGA, ddc); if (ret) return ret; - drm_connector_helper_add(connector, &ast_vga_connector_helper_funcs); connector->interlace_allowed = 0; connector->doublescan_allowed = 0; - connector->polled = DRM_CONNECTOR_POLL_CONNECT | DRM_CONNECTOR_POLL_DISCONNECT; - return 0; -} - -int ast_vga_output_init(struct ast_device *ast) -{ - struct drm_device *dev = &ast->base; - struct drm_crtc *crtc = &ast->crtc; - struct drm_encoder *encoder = &ast->output.vga.encoder; - struct ast_connector *ast_connector = &ast->output.vga.connector; - struct drm_connector *connector = &ast_connector->base; - int ret; - - ret = drm_encoder_init(dev, encoder, &ast_vga_encoder_funcs, - DRM_MODE_ENCODER_DAC, NULL); - if (ret) - return ret; - encoder->possible_crtcs = drm_crtc_mask(crtc); - - ret = ast_vga_connector_init(dev, connector); - if (ret) - return ret; ast_connector->physical_status = connector->status; ret = drm_connector_attach_encoder(connector, encoder); diff --git a/drivers/gpu/drm/atmel-hlcdc/Kconfig b/drivers/gpu/drm/atmel-hlcdc/Kconfig index 945f3aa7bb240907e5bbcf2747c768e9ca06cc77..f8b9c91907d8ec697d072269090da8deaa54a6d9 100644 --- a/drivers/gpu/drm/atmel-hlcdc/Kconfig +++ b/drivers/gpu/drm/atmel-hlcdc/Kconfig @@ -2,6 +2,7 @@ config DRM_ATMEL_HLCDC tristate "DRM Support for ATMEL HLCDC Display Controller" depends on DRM && OF && COMMON_CLK && ((MFD_ATMEL_HLCDC && ARM) || COMPILE_TEST) + select DRM_CLIENT_SELECTION select DRM_GEM_DMA_HELPER select DRM_KMS_HELPER select DRM_PANEL diff --git a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_dc.c b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_dc.c index 9ce429f889cac2802717aa5c87403ca7b0b35be1..792dcc19e8e7a30e428f3fc6260ed2060fe519b5 100644 --- a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_dc.c +++ b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_dc.c @@ -18,8 +18,10 @@ #include #include +#include #include #include +#include #include #include #include @@ -840,6 +842,7 @@ DEFINE_DRM_GEM_DMA_FOPS(fops); static const struct drm_driver atmel_hlcdc_dc_driver = { .driver_features = DRIVER_GEM | DRIVER_MODESET | DRIVER_ATOMIC, DRM_GEM_DMA_DRIVER_OPS, + DRM_FBDEV_DMA_DRIVER_OPS, .fops = &fops, .name = "atmel-hlcdc", .desc = "Atmel HLCD Controller DRM", @@ -865,7 +868,7 @@ static int atmel_hlcdc_dc_drm_probe(struct platform_device *pdev) if (ret) goto err_unload; - drm_fbdev_dma_setup(ddev, 24); + drm_client_setup_with_fourcc(ddev, DRM_FORMAT_RGB888); return 0; diff --git a/drivers/gpu/drm/bridge/Kconfig b/drivers/gpu/drm/bridge/Kconfig index 3eb955333c809e23a8faece88db728d3dd119a79..609f4d0ac93d7a372cc0fbeb384c4298ec81051a 100644 --- a/drivers/gpu/drm/bridge/Kconfig +++ b/drivers/gpu/drm/bridge/Kconfig @@ -140,6 +140,8 @@ config DRM_LONTIUM_LT9611 select DRM_PANEL_BRIDGE select DRM_KMS_HELPER select DRM_MIPI_DSI + select DRM_DISPLAY_HELPER + select DRM_DISPLAY_HDMI_STATE_HELPER select REGMAP_I2C help Driver for Lontium LT9611 DSI to HDMI bridge @@ -368,6 +370,13 @@ config DRM_TI_DLPC3433 It supports up to 720p resolution with 60 and 120 Hz refresh rates. +config DRM_TI_TDP158 + tristate "TI TDP158 HDMI/TMDS bridge" + depends on OF + select DRM_PANEL_BRIDGE + help + Texas Instruments TDP158 HDMI/TMDS Bridge driver + config DRM_TI_TFP410 tristate "TI TFP410 DVI/HDMI bridge" depends on OF diff --git a/drivers/gpu/drm/bridge/Makefile b/drivers/gpu/drm/bridge/Makefile index 7df87b582dca34c75f14b35a938891ba3b2bd34f..3daf803ce80b648a2133723be1562e0671d3a903 100644 --- a/drivers/gpu/drm/bridge/Makefile +++ b/drivers/gpu/drm/bridge/Makefile @@ -32,6 +32,7 @@ obj-$(CONFIG_DRM_I2C_ADV7511) += adv7511/ obj-$(CONFIG_DRM_TI_DLPC3433) += ti-dlpc3433.o obj-$(CONFIG_DRM_TI_SN65DSI83) += ti-sn65dsi83.o obj-$(CONFIG_DRM_TI_SN65DSI86) += ti-sn65dsi86.o +obj-$(CONFIG_DRM_TI_TDP158) += ti-tdp158.o obj-$(CONFIG_DRM_TI_TFP410) += ti-tfp410.o obj-$(CONFIG_DRM_TI_TPD12S015) += ti-tpd12s015.o obj-$(CONFIG_DRM_NWL_MIPI_DSI) += nwl-dsi.o diff --git a/drivers/gpu/drm/bridge/analogix/anx7625.c b/drivers/gpu/drm/bridge/analogix/anx7625.c index a2e9bb485c366e5dafcd655b5b1198097e6f8965..a2675b121fe44b96945f34215fd900f35bfde43a 100644 --- a/drivers/gpu/drm/bridge/analogix/anx7625.c +++ b/drivers/gpu/drm/bridge/analogix/anx7625.c @@ -2551,6 +2551,8 @@ static int __maybe_unused anx7625_runtime_pm_suspend(struct device *dev) mutex_lock(&ctx->lock); anx7625_stop_dp_work(ctx); + if (!ctx->pdata.panel_bridge) + anx7625_remove_edid(ctx); anx7625_power_standby(ctx); mutex_unlock(&ctx->lock); diff --git a/drivers/gpu/drm/bridge/aux-bridge.c b/drivers/gpu/drm/bridge/aux-bridge.c index b29980f95379ec7af873ed6e0fb79a9abb663c7b..e3e95ccec1aefe2c62d392611c04a728d6a84d0c 100644 --- a/drivers/gpu/drm/bridge/aux-bridge.c +++ b/drivers/gpu/drm/bridge/aux-bridge.c @@ -120,6 +120,10 @@ static int drm_aux_bridge_probe(struct auxiliary_device *auxdev, data->bridge.funcs = &drm_aux_bridge_funcs; data->bridge.of_node = data->dev->of_node; + /* passthrough data, allow everything */ + data->bridge.interlace_allowed = true; + data->bridge.ycbcr_420_allowed = true; + return devm_drm_bridge_add(data->dev, &data->bridge); } diff --git a/drivers/gpu/drm/bridge/aux-hpd-bridge.c b/drivers/gpu/drm/bridge/aux-hpd-bridge.c index 6886db2d9e00c4544ee3d81e29e779f806c8a9b7..48f297c78ee67c8f9034869f6824a6dc7f88bdd7 100644 --- a/drivers/gpu/drm/bridge/aux-hpd-bridge.c +++ b/drivers/gpu/drm/bridge/aux-hpd-bridge.c @@ -180,6 +180,10 @@ static int drm_aux_hpd_bridge_probe(struct auxiliary_device *auxdev, data->bridge.ops = DRM_BRIDGE_OP_HPD; data->bridge.type = id->driver_data; + /* passthrough data, allow everything */ + data->bridge.interlace_allowed = true; + data->bridge.ycbcr_420_allowed = true; + auxiliary_set_drvdata(auxdev, data); return devm_drm_bridge_add(data->dev, &data->bridge); diff --git a/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-core.c b/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-core.c index dee640ab1d3ad5b3550fcee9caa385c3bbc75dd5..41f72d458487fb27a34f2fa475c51de55725bc23 100644 --- a/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-core.c +++ b/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-core.c @@ -47,7 +47,7 @@ #include #include -#include +#include #include "cdns-mhdp8546-core.h" #include "cdns-mhdp8546-hdcp.h" diff --git a/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-hdcp.c b/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-hdcp.c index 5e3b8edcf79487a4cd9c22a7dd9ef053cf739268..31832ba4017f1a8489c7dd653aa259be02e3183d 100644 --- a/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-hdcp.c +++ b/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-hdcp.c @@ -9,7 +9,7 @@ #include #include -#include +#include #include diff --git a/drivers/gpu/drm/bridge/display-connector.c b/drivers/gpu/drm/bridge/display-connector.c index ab8e00baf3f163fb64baa21aba90098e24635fb5..aab9ce7be94c58d899d8a746c3049f867d5931cd 100644 --- a/drivers/gpu/drm/bridge/display-connector.c +++ b/drivers/gpu/drm/bridge/display-connector.c @@ -270,6 +270,10 @@ static int display_connector_probe(struct platform_device *pdev) /* All the supported connector types support interlaced modes. */ conn->bridge.interlace_allowed = true; + if (type == DRM_MODE_CONNECTOR_HDMIA || + type == DRM_MODE_CONNECTOR_DisplayPort) + conn->bridge.ycbcr_420_allowed = true; + /* Get the optional connector label. */ of_property_read_string(pdev->dev.of_node, "label", &label); diff --git a/drivers/gpu/drm/bridge/imx/Kconfig b/drivers/gpu/drm/bridge/imx/Kconfig index 8dd89efa8ea7d9e44976a64a83219fe48fd0543c..9a480c6abb856276df9b71d23b39a43b3a9c542d 100644 --- a/drivers/gpu/drm/bridge/imx/Kconfig +++ b/drivers/gpu/drm/bridge/imx/Kconfig @@ -3,6 +3,16 @@ if ARCH_MXC || COMPILE_TEST config DRM_IMX_LDB_HELPER tristate +config DRM_IMX_LEGACY_BRIDGE + tristate + depends on DRM_IMX + help + This is a DRM bridge implementation for the DRM i.MX IPUv3 driver, + that uses of_get_drm_display_mode to acquire display mode. + + Newer designs should not use this bridge and should use proper panel + driver instead. + config DRM_IMX8MP_DW_HDMI_BRIDGE tristate "Freescale i.MX8MP HDMI-TX bridge support" depends on OF diff --git a/drivers/gpu/drm/bridge/imx/Makefile b/drivers/gpu/drm/bridge/imx/Makefile index edb0a7b71b30a361898e5c08f995299c3210634b..dd5d4858480663bade98bd58039d1cb6f8aa18da 100644 --- a/drivers/gpu/drm/bridge/imx/Makefile +++ b/drivers/gpu/drm/bridge/imx/Makefile @@ -1,4 +1,5 @@ obj-$(CONFIG_DRM_IMX_LDB_HELPER) += imx-ldb-helper.o +obj-$(CONFIG_DRM_IMX_LEGACY_BRIDGE) += imx-legacy-bridge.o obj-$(CONFIG_DRM_IMX8MP_DW_HDMI_BRIDGE) += imx8mp-hdmi-tx.o obj-$(CONFIG_DRM_IMX8MP_HDMI_PVI) += imx8mp-hdmi-pvi.o obj-$(CONFIG_DRM_IMX8QM_LDB) += imx8qm-ldb.o diff --git a/drivers/gpu/drm/bridge/imx/imx-legacy-bridge.c b/drivers/gpu/drm/bridge/imx/imx-legacy-bridge.c new file mode 100644 index 0000000000000000000000000000000000000000..3ebf0b9866de13b12fab2b3c1e4db5f3d446089a --- /dev/null +++ b/drivers/gpu/drm/bridge/imx/imx-legacy-bridge.c @@ -0,0 +1,88 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Freescale i.MX drm driver + * + * bridge driver for legacy DT bindings, utilizing display-timings node + */ + +#include +#include +#include +#include + +#include