diff options
1533 files changed, 11382 insertions, 6756 deletions
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index bb48ae24ae69..1518343bbe22 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -2677,6 +2677,23 @@ Default is Y (on). + kvm.enable_virt_at_load=[KVM,ARM64,LOONGARCH,MIPS,RISCV,X86] + If enabled, KVM will enable virtualization in hardware + when KVM is loaded, and disable virtualization when KVM + is unloaded (if KVM is built as a module). + + If disabled, KVM will dynamically enable and disable + virtualization on-demand when creating and destroying + VMs, i.e. on the 0=>1 and 1=>0 transitions of the + number of VMs. + + Enabling virtualization at module lode avoids potential + latency for creation of the 0=>1 VM, as KVM serializes + virtualization enabling across all online CPUs. The + "cost" of enabling virtualization when KVM is loaded, + is that doing so may interfere with using out-of-tree + hypervisors that want to "own" virtualization hardware. + kvm.enable_vmware_backdoor=[KVM] Support VMware backdoor PV interface. Default is false (don't support). diff --git a/Documentation/arch/arm/mem_alignment.rst b/Documentation/arch/arm/mem_alignment.rst index aa22893b62bc..64bd77959300 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 9eb5e70b4888..65bfab1b1861 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/arch/s390/vfio-ap.rst b/Documentation/arch/s390/vfio-ap.rst index ea744cbc8687..eba1991fbdba 100644 --- a/Documentation/arch/s390/vfio-ap.rst +++ b/Documentation/arch/s390/vfio-ap.rst @@ -999,6 +999,36 @@ the vfio_ap mediated device to which it is assigned as long as each new APQN resulting from plugging it in references a queue device bound to the vfio_ap device driver. +Driver Features +=============== +The vfio_ap driver exposes a sysfs file containing supported features. +This exists so third party tools (like Libvirt and mdevctl) can query the +availability of specific features. + +The features list can be found here: /sys/bus/matrix/devices/matrix/features + +Entries are space delimited. Each entry consists of a combination of +alphanumeric and underscore characters. + +Example: +cat /sys/bus/matrix/devices/matrix/features +guest_matrix dyn ap_config + +the following features are advertised: + +---------------+---------------------------------------------------------------+ +| Flag | Description | ++==============+===============================================================+ +| guest_matrix | guest_matrix attribute exists. It reports the matrix of | +| | adapters and domains that are or will be passed through to a | +| | guest when the mdev is attached to it. | ++--------------+---------------------------------------------------------------+ +| dyn | Indicates hot plug/unplug of AP adapters, domains and control | +| | domains for a guest to which the mdev is attached. | ++------------+-----------------------------------------------------------------+ +| ap_config | ap_config interface for one-shot modifications to mdev config | ++--------------+---------------------------------------------------------------+ + Limitations =========== Live guest migration is not supported for guests using AP devices without diff --git a/Documentation/core-api/cleanup.rst b/Documentation/core-api/cleanup.rst new file mode 100644 index 000000000000..527eb2f8ec6e --- /dev/null +++ b/Documentation/core-api/cleanup.rst @@ -0,0 +1,8 @@ +.. SPDX-License-Identifier: GPL-2.0 + +=========================== +Scope-based Cleanup Helpers +=========================== + +.. kernel-doc:: include/linux/cleanup.h + :doc: scope-based cleanup helpers diff --git a/Documentation/core-api/folio_queue.rst b/Documentation/core-api/folio_queue.rst new file mode 100644 index 000000000000..1fe7a9bc4b8d --- /dev/null +++ b/Documentation/core-api/folio_queue.rst @@ -0,0 +1,212 @@ +.. SPDX-License-Identifier: GPL-2.0+ + +=========== +Folio Queue +=========== + +:Author: David Howells <dhowells@redhat.com> + +.. 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 <linux/folio_queue.h> + +and to use the iterator:: + + #include <linux/uio.h> + + +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 e18a2ffe0787..6a875743dd4b 100644 --- a/Documentation/core-api/index.rst +++ b/Documentation/core-api/index.rst @@ -35,7 +35,9 @@ Library functionality that is used throughout the kernel. kobject 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 1ee82419d8aa..5ceeb80eb539 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 <asm/unaligned.h> header file. +put_unaligned() macros provided by the <linux/unaligned.h> header file. Going back to an earlier example of code that potentially causes unaligned access:: diff --git a/Documentation/devicetree/bindings/mailbox/mtk,adsp-mbox.yaml b/Documentation/devicetree/bindings/mailbox/mtk,adsp-mbox.yaml index 72c1d9e82c89..8a1369df4ecb 100644 --- a/Documentation/devicetree/bindings/mailbox/mtk,adsp-mbox.yaml +++ b/Documentation/devicetree/bindings/mailbox/mtk,adsp-mbox.yaml @@ -17,9 +17,15 @@ description: | properties: compatible: - enum: - - mediatek,mt8195-adsp-mbox - - mediatek,mt8186-adsp-mbox + oneOf: + - enum: + - mediatek,mt8186-adsp-mbox + - mediatek,mt8195-adsp-mbox + - items: + - enum: + - mediatek,mt8188-adsp-mbox + - const: mediatek,mt8186-adsp-mbox + "#mbox-cells": const: 0 diff --git a/Documentation/devicetree/bindings/mailbox/qcom-ipcc.yaml b/Documentation/devicetree/bindings/mailbox/qcom-ipcc.yaml index 05e4e1d51713..2d66770ed361 100644 --- a/Documentation/devicetree/bindings/mailbox/qcom-ipcc.yaml +++ b/Documentation/devicetree/bindings/mailbox/qcom-ipcc.yaml @@ -24,7 +24,9 @@ properties: compatible: items: - enum: + - qcom,qcs8300-ipcc - qcom,qdu1000-ipcc + - qcom,sa8255p-ipcc - qcom,sa8775p-ipcc - qcom,sc7280-ipcc - qcom,sc8280xp-ipcc diff --git a/Documentation/devicetree/bindings/net/xlnx,axi-ethernet.yaml b/Documentation/devicetree/bindings/net/xlnx,axi-ethernet.yaml index bbe89ea9590c..e95c21628281 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 7735e08d35ba..ab3206ffa4af 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 1d3acdc0c733..2e2e01493a5f 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 3bc93c59535e..6d0d1514cd42 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/driver-api/cxl/access-coordinates.rst b/Documentation/driver-api/cxl/access-coordinates.rst new file mode 100644 index 000000000000..b07950ea30c9 --- /dev/null +++ b/Documentation/driver-api/cxl/access-coordinates.rst @@ -0,0 +1,91 @@ +.. SPDX-License-Identifier: GPL-2.0 +.. include:: <isonum.txt> + +================================== +CXL Access Coordinates Computation +================================== + +Shared Upstream Link Calculation +================================ +For certain CXL region construction with endpoints behind CXL switches (SW) or +Root Ports (RP), there is the possibility of the total bandwidth for all +the endpoints behind a switch being more than the switch upstream link. +A similar situation can occur within the host, upstream of the root ports. +The CXL driver performs an additional pass after all the targets have +arrived for a region in order to recalculate the bandwidths with possible +upstream link being a limiting factor in mind. + +The algorithm assumes the configuration is a symmetric topology as that +maximizes performance. When asymmetric topology is detected, the calculation +is aborted. An asymmetric topology is detected during topology walk where the +number of RPs detected as a grandparent is not equal to the number of devices +iterated in the same iteration loop. The assumption is made that subtle +asymmetry in properties does not happen and all paths to EPs are equal. + +There can be multiple switches under an RP. There can be multiple RPs under +a CXL Host Bridge (HB). There can be multiple HBs under a CXL Fixed Memory +Window Structure (CFMWS). + +An example hierarchy: + +> CFMWS 0 +> | +> _________|_________ +> | | +> ACPI0017-0 ACPI0017-1 +> GP0/HB0/ACPI0016-0 GP1/HB1/ACPI0016-1 +> | | | | +> RP0 RP1 RP2 RP3 +> | | | | +> SW 0 SW 1 SW 2 SW 3 +> | | | | | | | | +> EP0 EP1 EP2 EP3 EP4 EP5 EP6 EP7 + +Computation for the example hierarchy: + +Min (GP0 to CPU BW, + Min(SW 0 Upstream Link to RP0 BW, + Min(SW0SSLBIS for SW0DSP0 (EP0), EP0 DSLBIS, EP0 Upstream Link) + + Min(SW0SSLBIS for SW0DSP1 (EP1), EP1 DSLBIS, EP1 Upstream link)) + + Min(SW 1 Upstream Link to RP1 BW, + Min(SW1SSLBIS for SW1DSP0 (EP2), EP2 DSLBIS, EP2 Upstream Link) + + Min(SW1SSLBIS for SW1DSP1 (EP3), EP3 DSLBIS, EP3 Upstream link))) + +Min (GP1 to CPU BW, + Min(SW 2 Upstream Link to RP2 BW, + Min(SW2SSLBIS for SW2DSP0 (EP4), EP4 DSLBIS, EP4 Upstream Link) + + Min(SW2SSLBIS for SW2DSP1 (EP5), EP5 DSLBIS, EP5 Upstream link)) + + Min(SW 3 Upstream Link to RP3 BW, + Min(SW3SSLBIS for SW3DSP0 (EP6), EP6 DSLBIS, EP6 Upstream Link) + + Min(SW3SSLBIS for SW3DSP1 (EP7), EP7 DSLBIS, EP7 Upstream link)))) + +The calculation starts at cxl_region_shared_upstream_perf_update(). A xarray +is created to collect all the endpoint bandwidths via the +cxl_endpoint_gather_bandwidth() function. The min() of bandwidth from the +endpoint CDAT and the upstream link bandwidth is calculated. If the endpoint +has a CXL switch as a parent, then min() of calculated bandwidth and the +bandwidth from the SSLBIS for the switch downstream port that is associated +with the endpoint is calculated. The final bandwidth is stored in a +'struct cxl_perf_ctx' in the xarray indexed by a device pointer. If the +endpoint is direct attached to a root port (RP), the device pointer would be an +RP device. If the endpoint is behind a switch, the device pointer would be the +upstream device of the parent switch. + +At the next stage, the code walks through one or more switches if they exist +in the topology. For endpoints directly attached to RPs, this step is skipped. +If there is another switch upstream, the code takes the min() of the current +gathered bandwidth and the upstream link bandwidth. If there's a switch +upstream, then the SSLBIS of the upstream switch. + +Once the topology walk reaches the RP, whether it's direct attached endpoints +or walking through the switch(es), cxl_rp_gather_bandwidth() is called. At +this point all the bandwidths are aggregated per each host bridge, which is +also the index for the resulting xarray. + +The next step is to take the min() of the per host bridge bandwidth and the +bandwidth from the Generic Port (GP). The bandwidths for the GP is retrieved +via ACPI tables SRAT/HMAT. The min bandwidth are aggregated under the same +ACPI0017 device to form a new xarray. + +Finally, the cxl_region_update_bandwidth() is called and the aggregated +bandwidth from all the members of the last xarray is updated for the +access coordinates residing in the cxl region (cxlr) context. diff --git a/Documentation/driver-api/cxl/index.rst b/Documentation/driver-api/cxl/index.rst index 12b82725d322..965ba90e8fb7 100644 --- a/Documentation/driver-api/cxl/index.rst +++ b/Documentation/driver-api/cxl/index.rst @@ -8,6 +8,7 @@ Compute Express Link :maxdepth: 1 memory-devices + access-coordinates maturity-map diff --git a/Documentation/driver-api/wmi.rst b/Documentation/driver-api/wmi.rst index 6ca58c8249e5..4e8dbdb1fc67 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 <wmi_device>`, so it supports -WMI devices sharing GUIDs and/or notification IDs. Drivers can then register -a :c:type:`struct wmi_driver <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 <wmi_device>`, so it supports WMI devices sharing the +same GUID. Drivers can then register a :c:type:`struct wmi_driver <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/drm-kms-helpers.rst b/Documentation/gpu/drm-kms-helpers.rst index 8435e8621cc0..c3e58856f75b 100644 --- a/Documentation/gpu/drm-kms-helpers.rst +++ b/Documentation/gpu/drm-kms-helpers.rst @@ -181,7 +181,7 @@ 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 +204,7 @@ 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/networking/napi.rst b/Documentation/networking/napi.rst index 7bf7b95c4f7a..dfa5d549be9c 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 29c33e7e0855..fbe0989a8ce5 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éžå¯¹é½è®¿é—®ï¼Œè¿™å¹¶ä¸æ˜¯ä¸åˆç†çš„ã€‚ä½ ä¼šæœŸæœ›field2ä½ é¿å…éžå¯¹é½è®¿é—® ============== -é¿å…éžå¯¹é½è®¿é—®çš„最简å•æ–¹æ³•æ˜¯ä½¿ç”¨<asm/unaligned.h>头文件æ供的get_unaligned()å’Œ +é¿å…éžå¯¹é½è®¿é—®çš„最简å•æ–¹æ³•æ˜¯ä½¿ç”¨<linux/unaligned.h>头文件æ供的get_unaligned()å’Œ put_unaligned()å®ã€‚ 回到å‰é¢çš„一个å¯èƒ½å¯¼è‡´éžå¯¹é½è®¿é—®çš„代ç 例å:: diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index b3be87489108..e32471977d0a 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -4214,7 +4214,9 @@ whether or not KVM_CAP_X86_USER_SPACE_MSR's KVM_MSR_EXIT_REASON_FILTER is enabled. If KVM_MSR_EXIT_REASON_FILTER is enabled, KVM will exit to userspace on denied accesses, i.e. userspace effectively intercepts the MSR access. If KVM_MSR_EXIT_REASON_FILTER is not enabled, KVM will inject a #GP into the guest -on denied accesses. +on denied accesses. Note, if an MSR access is denied during emulation of MSR +load/stores during VMX transitions, KVM ignores KVM_MSR_EXIT_REASON_FILTER. +See the below warning for full details. If an MSR access is allowed by userspace, KVM will emulate and/or virtualize the access in accordance with the vCPU model. Note, KVM may still ultimately @@ -4229,9 +4231,22 @@ filtering. In that mode, ``KVM_MSR_FILTER_DEFAULT_DENY`` is invalid and causes an error. .. warning:: - MSR accesses as part of nested VM-Enter/VM-Exit are not filtered. - This includes both writes to individual VMCS fields and reads/writes - through the MSR lists pointed to by the VMCS. + MSR accesses that are side effects of instruction execution (emulated or + native) are not filtered as hardware does not honor MSR bitmaps outside of + RDMSR and WRMSR, and KVM mimics that behavior when emulating instructions + to avoid pointless divergence from hardware. E.g. RDPID reads MSR_TSC_AUX, + SYSENTER reads the SYSENTER MSRs, etc. + + MSRs that are loaded/stored via dedicated VMCS fields are not filtered as + part of VM-Enter/VM-Exit emulation. + + MSRs that are loaded/store via VMX's load/store lists _are_ filtered as part + of VM-Enter/VM-Exit emulation. If an MSR access is denied on VM-Enter, KVM + synthesizes a consistency check VM-Exit(EXIT_REASON_MSR_LOAD_FAIL). If an + MSR access is denied on VM-Exit, KVM synthesizes a VM-Abort. In short, KVM + extends Intel's architectural list of MSRs that cannot be loaded/saved via + the VM-Enter/VM-Exit MSR list. It is platform owner's responsibility to + to communicate any such restrictions to their end users. x2APIC MSR accesses cannot be filtered (KVM silently ignores filters that cover any x2APIC MSRs). @@ -8082,6 +8097,14 @@ KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS By default, KVM emulates MONITOR/MWAIT (if guest CPUID on writes to MISC_ENABLE if KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT is disabled. + +KVM_X86_QUIRK_SLOT_ZAP_ALL By default, KVM invalidates all SPTEs in + fast way for memslot deletion when VM type + is KVM_X86_DEFAULT_VM. + When this quirk is disabled or when VM type + is other than KVM_X86_DEFAULT_VM, KVM zaps + only leaf SPTEs that are within the range of + the memslot being deleted. =================================== ============================================ 7.32 KVM_CAP_MAX_VCPU_ID diff --git a/Documentation/virt/kvm/locking.rst b/Documentation/virt/kvm/locking.rst index 02880d5552d5..20a9a37d1cdd 100644 --- a/Documentation/virt/kvm/locking.rst +++ b/Documentation/virt/kvm/locking.rst @@ -11,6 +11,8 @@ The acquisition orders for mutexes are as follows: - cpus_read_lock() is taken outside kvm_lock +- kvm_usage_lock is taken outside cpus_read_lock() + - kvm->lock is taken outside vcpu->mutex - kvm->lock is taken outside kvm->slots_lock and kvm->irq_lock @@ -24,6 +26,13 @@ The acquisition orders for mutexes are as follows: are taken on the waiting side when modifying memslots, so MMU notifiers must not take either kvm->slots_lock or kvm->slots_arch_lock. +cpus_read_lock() vs kvm_lock: + +- Taking cpus_read_lock() outside of kvm_lock is problematic, despite that + being the official ordering, as it is quite easy to unknowingly trigger + cpus_read_lock() while holding kvm_lock. Use caution when walking vm_list, + e.g. avoid complex operations when possible. + For SRCU: - ``synchronize_srcu(&kvm->srcu)`` is called inside critical sections @@ -227,10 +236,16 @@ time it will be set using the Dirty tracking mechanism described above. :Type: mutex :Arch: any :Protects: - vm_list - - kvm_usage_count + +``kvm_usage_lock`` +^^^^^^^^^^^^^^^^^^ + +:Type: mutex +:Arch: any +:Protects: - kvm_usage_count - hardware virtualization enable/disable -:Comment: KVM also disables CPU hotplug via cpus_read_lock() during - enable/disable. +:Comment: Exists to allow taking cpus_read_lock() while kvm_usage_count is + protected, which simplifies the virtualization enabling logic. ``kvm->mn_invalidate_lock`` ^^^^^^^^^^^^^^^^^^^^^^^^^^^ @@ -290,11 +305,12 @@ time it will be set using the Dirty tracking mechanism described above. wakeup. ``vendor_module_lock`` -^^^^^^^^^^^^^^^^^^^^^^^^^^^^ +^^^^^^^^^^^^^^^^^^^^^^ :Type: mutex :Arch: x86 :Protects: loading a vendor module (kvm_amd or kvm_intel) -:Comment: Exists because using kvm_lock leads to deadlock. cpu_hotplug_lock is - taken outside of kvm_lock, e.g. in KVM's CPU online/offline callbacks, and - many operations need to take cpu_hotplug_lock when loading a vendor module, - e.g. updating static calls. +:Comment: Exists because using kvm_lock leads to deadlock. kvm_lock is taken + in notifiers, e.g. __kvmclock_cpufreq_notifier(), that may be invoked while + cpu_hotplug_lock is held, e.g. from cpufreq_boost_trigger_state(), and many + operations need to take cpu_hotplug_lock when loading a vendor module, e.g. + updating static calls. diff --git a/Documentation/virt/uml/user_mode_linux_howto_v2.rst b/Documentation/virt/uml/user_mode_linux_howto_v2.rst index 27942446f406..584000b743f3 100644 --- a/Documentation/virt/uml/user_mode_linux_howto_v2.rst +++ b/Documentation/virt/uml/user_mode_linux_howto_v2.rst @@ -217,6 +217,8 @@ remote UML and other VM instances. +-----------+--------+------------------------------------+------------+ | fd | vector | dependent on fd type | varies | +-----------+--------+------------------------------------+------------+ +| vde | vector | dep. on VDE VPN: Virt.Net Locator | varies | ++-----------+--------+------------------------------------+------------+ | tuntap | legacy | none | ~ 500Mbit | +-----------+--------+------------------------------------+------------+ | daemon | legacy | none | ~ 450Mbit | @@ -573,6 +575,41 @@ https://github.com/NetSys/bess/wiki/Built-In-Modules-and-Ports BESS transport does not require any special privileges. +VDE vector transport +-------------------- + +Virtual Distributed Ethernet (VDE) is a project whose main goal is to provide a +highly flexible support for virtual networking. + +http://wiki.virtualsquare.org/#/tutorials/vdebasics + +Common usages of VDE include fast prototyping and teaching. + +Examples: + + ``vecX:transport=vde,vnl=tap://tap0`` + +use tap0 + + ``vecX:transport=vde,vnl=slirp://`` + +use slirp + + ``vec0:transport=vde,vnl=vde:///tmp/switch`` + +connect to a vde switch + + ``vecX:transport=\"vde,vnl=cmd://ssh remote.host //tmp/sshlirp\"`` + +connect to a remote slirp (instant VPN: convert ssh to VPN, it uses sshlirp) +https://github.com/virtualsquare/sshlirp + + ``vec0:transport=vde,vnl=vxvde://234.0.0.1`` + +connect to a local area cloud (all the UML nodes using the same +multicast address running on hosts in the same multicast domain (LAN) +will be automagically connected together to a virtual LAN. + Configuring Legacy transports ============================= diff --git a/Documentation/wmi/devices/dell-wmi-ddv.rst b/Documentation/wmi/devices/dell-wmi-ddv.rst index 2fcdfcf03327..e0c20af30948 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 00716c1faff6..a097afd76ded 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -860,7 +860,7 @@ F: drivers/crypto/allwinner/ ALLWINNER DMIC DRIVERS M: Ban Tao <fengzheng923@gmail.com> -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 <lars@metafoo.de> M: Nuno Sá <nuno.sa@analog.com> -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 <johannes@sipsolutions.net> 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 <jbrunet@baylibre.com> -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 PoviÅ¡er <povik+lin@cutebit.org> 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 <peda@axentia.se> -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 <clemens@ladisch.de> -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 <clemens@ladisch.de> -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/ @@ -5728,8 +5728,7 @@ L: linux-cxl@vger.kernel.org S: Maintained F: Documentation/driver-api/cxl F: drivers/cxl/ -F: include/linux/einj-cxl.h -F: include/linux/cxl-event.h +F: include/cxl/ F: include/uapi/linux/cxl_mem.h F: tools/testing/cxl/ @@ -7833,6 +7832,8 @@ F: drivers/gpu/drm/xlnx/ DRM GPU SCHEDULER M: Luben Tuikov <ltuikov89@gmail.com> M: Matthew Brost <matthew.brost@intel.com> +M: Danilo Krummrich <dakr@kernel.org> +M: Philipp Stanner <pstanner@redhat.com> L: dri-devel@lists.freedesktop.org S: Maintained T: git https://gitlab.freedesktop.org/drm/misc/kernel.git @@ -8253,7 +8254,7 @@ F: drivers/edac/ti_edac.c EDIROL UA-101/UA-1000 DRIVER M: Clemens Ladisch <clemens@ladisch.de> -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 @@ -8815,7 +8816,7 @@ F: drivers/net/can/usb/f81604.c FIREWIRE AUDIO DRIVERS and IEC 61883-1/6 PACKET STREAMING ENGINE M: Clemens Ladisch <clemens@ladisch.de> M: Takashi Sakamoto <o-takashi@sakamocchi.jp> -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 @@ -8889,7 +8890,7 @@ F: drivers/input/joystick/fsia6b.c FOCUSRITE SCARLETT2 MIXER DRIVER (Scarlett Gen 2+ and Clarett) M: Geoffrey D. Bennett <g@b4.vu> -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 @@ -8913,6 +8914,7 @@ 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 @@ -9210,7 +9212,7 @@ M: Shengjiu Wang <shengjiu.wang@gmail.com> M: Xiubo Li <Xiubo.Lee@gmail.com> R: Fabio Estevam <festevam@gmail.com> R: Nicolin Chen <nicoleotsuka@gmail.com> -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* @@ -9220,7 +9222,7 @@ FREESCALE SOC LPC32XX SOUND DRIVERS M: J.M.B. Downing <jonathan.downing@nautel.com> M: Piotr Wojtaszczyk <piotr.wojtaszczyk@timesys.com> R: Vladimir Zapolskiy <vz@mleia.com> -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 @@ -9228,7 +9230,7 @@ F: sound/soc/fsl/lpc3xxx-* FREESCALE SOC SOUND QMC DRIVER M: Herve Codina <herve.codina@bootlin.com> -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 @@ -11155,7 +11157,7 @@ F: drivers/iio/pressure/dps310.c INFINEON PEB2466 ASoC CODEC M: Herve Codina <herve.codina@bootlin.com> -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 @@ -11318,7 +11320,7 @@ M: Bard Liao <yung-chuan.liao@linux.intel.com> M: Ranjani Sridharan <ranjani.sridharan@linux.intel.com> M: Kai Vehmanen <kai.vehmanen@linux.intel.com> R: Pierre-Louis Bossart <pierre-louis.bossart@linux.dev> -L: alsa-devel@alsa-project.org (moderated for non-subscribers) +L: linux-sound@vger.kernel.org S: Supported F: sound/soc/intel/ @@ -11497,7 +11499,7 @@ F: include/uapi/linux/idxd.h INTEL IN FIELD SCAN (IFS) DEVICE M: Jithu Joseph <jithu.joseph@intel.com> -R: Ashok Raj <ashok.raj@intel.com> +R: Ashok Raj <ashok.raj.linux@gmail.com> R: Tony Luck <tony.luck@intel.com> S: Maintained F: drivers/platform/x86/intel/ifs @@ -12002,7 +12004,7 @@ F: drivers/tty/ipwireless/ IRON DEVICE AUDIO CODEC DRIVERS M: Kiseok Jo <kiseok.jo@irondevice.com> -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* @@ -12344,6 +12346,7 @@ 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 @@ -12460,7 +12463,7 @@ F: virt/kvm/* KERNEL VIRTUAL MACHINE FOR ARM64 (KVM/arm64) M: Marc Zyngier <maz@kernel.org> M: Oliver Upton <oliver.upton@linux.dev> -R: James Morse <james.morse@arm.com> +R: Joey Gouly <joey.gouly@arm.com> R: Suzuki K Poulose <suzuki.poulose@arm.com> R: Zenghui Yu <yuzenghui@huawei.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) @@ -13953,7 +13956,7 @@ F: drivers/media/i2c/max96717.c MAX9860 MONO AUDIO VOICE CODEC DRIVER M: Peter Rosin <peda@axentia.se> -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.* @@ -15086,7 +15089,7 @@ F: drivers/spi/spi-at91-usart.c MICROCHIP AUDIO ASOC DRIVERS M: Claudiu Beznea <claudiu.beznea@tuxon.dev> -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 @@ -15679,6 +15682,9 @@ F: include/dt-bindings/clock/mobileye,eyeq5-clk.h MODULE SUPPORT M: Luis Chamberlain <mcgrof@kernel.org> +R: Petr Pavlu <petr.pavlu@suse.com> +R: Sami Tolvanen <samitolvanen@google.com> +R: Daniel Gomez <da.gomez@samsung.com> L: linux-modules@vger.kernel.org L: linux-kernel@vger.kernel.org S: Maintained @@ -15955,7 +15961,7 @@ F: include/linux/mtd/*nand*.h NATIVE INSTRUMENTS USB SOUND INTERFACE DRIVER M: Daniel Mack <zonque@gmail.com> -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/ @@ -16726,7 +16732,7 @@ F: drivers/extcon/extcon-ptn5150.c NXP SGTL5000 DRIVER M: Fabio Estevam <festevam@gmail.com> -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* @@ -16750,7 +16756,7 @@ K: "nxp,tda998x" NXP TFA9879 DRIVER M: Peter Rosin <peda@axentia.se> -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* @@ -16762,7 +16768,7 @@ F: drivers/nfc/nxp-nci NXP/Goodix TFA989X (TFA1) DRIVER M: Stephan Gerhold <stephan@gerhold.net> -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 @@ -16848,7 +16854,7 @@ F: include/uapi/misc/ocxl.h OMAP AUDIO SUPPORT M: Peter Ujfalusi <peter.ujfalusi@gmail.com> M: Jarkko Nikula <jarkko.nikula@bitmer.com> -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 @@ -17405,7 +17411,7 @@ F: include/linux/pm_opp.h OPL4 DRIVER M: Clemens Ladisch <clemens@ladisch.de> -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/ @@ -18788,7 +18794,7 @@ F: drivers/crypto/intel/qat/ QCOM AUDIO (ASoC) DRIVERS M: Srinivas Kandagatla <srinivas.kandagatla@linaro.org> -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* @@ -19345,10 +19351,7 @@ F: drivers/char/random.c F: include/linux/random.h F: include/uapi/linux/random.h F: drivers/virt/vmgenid.c -F: include/vdso/getrandom.h -F: lib/vdso/getrandom.c -F: arch/x86/entry/vdso/vgetrandom* -F: arch/x86/include/asm/vdso/getrandom* +N: ^.*/vdso/[^/]*getrandom[^/]+$ RAPIDIO SUBSYSTEM M: Matt Porter <mporter@kernel.crashing.org> @@ -19653,7 +19656,7 @@ F: drivers/net/ethernet/renesas/rtsn.* RENESAS IDT821034 ASoC CODEC M: Herve Codina <herve.codina@bootlin.com> -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 @@ -20404,7 +20407,7 @@ F: security/safesetid/ SAMSUNG AUDIO (ASoC) DRIVERS M: Sylwester Nawrocki <s.nawrocki@samsung.com> -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* @@ -20940,7 +20943,7 @@ F: drivers/media/rc/serial_ir.c SERIAL LOW-POWER INTER-CHIP MEDIA BUS (SLIMbus) M: Srinivas Kandagatla <srinivas.kandagatla@linaro.org> -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/ @@ -21374,7 +21377,7 @@ 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/ @@ -21633,7 +21636,7 @@ F: tools/testing/selftests/alsa SOUND - COMPRESSED AUDIO M: Vinod Koul <vkoul@kernel.org> -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 @@ -21696,7 +21699,7 @@ M: Vinod Koul <vkoul@kernel.org> M: Bard Liao <yung-chuan.liao@linux.intel.com> R: Pierre-Louis Bossart <pierre-louis.bossart@linux.dev> R: Sanyog Kale <sanyog.r.kale@intel.com> -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/ @@ -22169,7 +22172,7 @@ F: kernel/static_call.c STI AUDIO (ASoC) DRIVERS M: Arnaud Pouliquen <arnaud.pouliquen@foss.st.com> -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/ @@ -22190,7 +22193,7 @@ F: drivers/media/usb/stk1160/ STM32 AUDIO (ASoC) DRIVERS M: Olivier Moysan <olivier.moysan@foss.st.com> M: Arnaud Pouliquen <arnaud.pouliquen@foss.st.com> -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 @@ -22893,7 +22896,7 @@ F: drivers/irqchip/irq-xtensa-* TEXAS INSTRUMENTS ASoC DRIVERS M: Peter Ujfalusi <peter.ujfalusi@gmail.com> -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/ @@ -22902,7 +22905,7 @@ TEXAS INSTRUMENTS AUDIO (ASoC/HDA) DRIVERS M: Shenghao Ding <shenghao-ding@ti.com> M: Kevin Lu <kevin-lu@ti.com> M: Baojun Xu <baojun.xu@ti.com> -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 @@ -23270,7 +23273,7 @@ F: drivers/soc/ti/* TI LM49xxx FAMILY ASoC CODEC DRIVERS M: M R Swami Reddy <mr.swami.reddy@ti.com> M: Vishwas A Deshpande <vishwas.a.deshpande@ti.com> -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* @@ -23285,14 +23288,14 @@ F: drivers/iio/adc/ti-lmp92064.c TI PCM3060 ASoC CODEC DRIVER M: Kirill Marinushkin <kmarinushkin@birdec.com> -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 <cernekee@chromium.org> -L: alsa-devel@alsa-project.org (moderated for non-subscribers) +L: linux-sound@vger.kernel.org S: Odd Fixes F: sound/soc/codecs/tas571x* @@ -23320,7 +23323,7 @@ F: drivers/iio/adc/ti-tsc2046.c TI TWL4030 SERIES SOC CODEC DRIVER M: Peter Ujfalusi <peter.ujfalusi@gmail.com> -L: alsa-devel@alsa-project.org (moderated for non-subscribers) +L: linux-sound@vger.kernel.org S: Maintained F: sound/soc/codecs/twl4030* @@ -23996,7 +23999,7 @@ F: drivers/usb/storage/ USB MIDI DRIVER M: Clemens Ladisch <clemens@ladisch.de> -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.* @@ -24656,7 +24659,7 @@ VIRTIO SOUND DRIVER M: Anton Yakovlev <anton.yakovlev@opensynergy.com> M: "Michael S. Tsirkin" <mst@redhat.com> 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/* @@ -25385,7 +25388,7 @@ F: include/xen/interface/io/usbif.h XEN SOUND FRONTEND DRIVER M: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com> 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/* @@ -1,8 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 6 -PATCHLEVEL = 11 +PATCHLEVEL = 12 SUBLEVEL = 0 -EXTRAVERSION = +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 98157b38f5cf..8af374ea1adc 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 6afae65e9a8b..a9a38c80c4a7 100644 --- a/arch/alpha/kernel/traps.c +++ b/arch/alpha/kernel/traps.c @@ -22,7 +22,7 @@ #include <asm/gentrap.h> #include <linux/uaccess.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <asm/sysinfo.h> #include <asm/hwrpb.h> #include <asm/mmu_context.h> diff --git a/arch/arc/include/asm/io.h b/arch/arc/include/asm/io.h index 4fdb7350636c..f57cb5a6b624 100644 --- a/arch/arc/include/asm/io.h +++ b/arch/arc/include/asm/io.h @@ -9,7 +9,7 @@ #include <linux/types.h> #include <asm/byteorder.h> #include <asm/page.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #ifdef CONFIG_ISA_ARCV2 #include <asm/barrier.h> diff --git a/arch/arc/include/asm/mmu.h b/arch/arc/include/asm/mmu.h index 9febf5bc3de6..4ae2db59d494 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 cf5a02382e0e..000000000000 --- 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 <asm-generic/unaligned.h> -#include <asm/ptrace.h> - -#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 a19751e824fb..8d2ea2cbd98b 100644 --- a/arch/arc/kernel/traps.c +++ b/arch/arc/kernel/traps.c @@ -18,8 +18,9 @@ #include <linux/kgdb.h> #include <asm/entry.h> #include <asm/setup.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <asm/kprobes.h> +#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 99a9b92ed98d..d2f5ceaaed1b 100644 --- a/arch/arc/kernel/unaligned.c +++ b/arch/arc/kernel/unaligned.c @@ -12,6 +12,7 @@ #include <linux/ptrace.h> #include <linux/uaccess.h> #include <asm/disasm.h> +#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 000000000000..5244453bb85f --- /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 9270d0a713c3..d8969dab12d4 100644 --- a/arch/arc/kernel/unwind.c +++ b/arch/arc/kernel/unwind.c @@ -19,7 +19,7 @@ #include <linux/uaccess.h> #include <linux/ptrace.h> #include <asm/sections.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <asm/unwind.h> 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 f5b66f4cf45d..21df5e7f51f9 100644 --- a/arch/arm/crypto/aes-ce-glue.c +++ b/arch/arm/crypto/aes-ce-glue.c @@ -8,7 +8,7 @@ #include <asm/hwcap.h> #include <asm/neon.h> #include <asm/simd.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <crypto/aes.h> #include <crypto/ctr.h> #include <crypto/internal/simd.h> diff --git a/arch/arm/crypto/crc32-ce-glue.c b/arch/arm/crypto/crc32-ce-glue.c index 4ff18044af07..20b4dff13e3a 100644 --- a/arch/arm/crypto/crc32-ce-glue.c +++ b/arch/arm/crypto/crc32-ce-glue.c @@ -18,7 +18,7 @@ #include <asm/hwcap.h> #include <asm/neon.h> #include <asm/simd.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #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 3ddf05b4234d..3af997082534 100644 --- a/arch/arm/crypto/ghash-ce-glue.c +++ b/arch/arm/crypto/ghash-ce-glue.c @@ -9,7 +9,7 @@ #include <asm/hwcap.h> #include <asm/neon.h> #include <asm/simd.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <crypto/aes.h> #include <crypto/gcm.h> #include <crypto/b128ops.h> diff --git a/arch/arm/crypto/poly1305-glue.c b/arch/arm/crypto/poly1305-glue.c index 8482e302c45a..4464ffbf8fd1 100644 --- a/arch/arm/crypto/poly1305-glue.c +++ b/arch/arm/crypto/poly1305-glue.c @@ -8,7 +8,7 @@ #include <asm/hwcap.h> #include <asm/neon.h> #include <asm/simd.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <crypto/algapi.h> #include <crypto/internal/hash.h> #include <crypto/internal/poly1305.h> diff --git a/arch/arm/crypto/sha2-ce-glue.c b/arch/arm/crypto/sha2-ce-glue.c index c62ce89dd3e0..aeac45bfbf9f 100644 --- a/arch/arm/crypto/sha2-ce-glue.c +++ b/arch/arm/crypto/sha2-ce-glue.c @@ -16,7 +16,7 @@ #include <asm/hwcap.h> #include <asm/simd.h> #include <asm/neon.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "sha256_glue.h" diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h index 6c9c16d767cf..f90be312418e 100644 --- a/arch/arm/include/asm/uaccess.h +++ b/arch/arm/include/asm/uaccess.h @@ -12,7 +12,7 @@ #include <linux/string.h> #include <asm/page.h> #include <asm/domain.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <asm/unified.h> #include <asm/pgtable.h> #include <asm/proc-fns.h> diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c index f8dd0b3cc8e0..3c6ddb1afdc4 100644 --- a/arch/arm/mm/alignment.c +++ b/arch/arm/mm/alignment.c @@ -22,7 +22,7 @@ #include <asm/cp15.h> #include <asm/system_info.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <asm/opcodes.h> #include "fault.h" diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 3e29b44d2d7b..fd9df6dcc593 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 $(cc-option,-fpatchable-function-entry=2) - select HAVE_DYNAMIC_FTRACE_WITH_ARGS config 64BIT def_bool y @@ -1097,6 +1096,7 @@ config ARM64_ERRATUM_3194386 * ARM Cortex-A78C erratum 3324346 * ARM Cortex-A78C erratum 3324347 * ARM Cortex-A710 erratam 3324338 + * ARM Cortex-A715 errartum 3456084 * ARM Cortex-A720 erratum 3456091 * ARM Cortex-A725 erratum 3456106 * ARM Cortex-X1 erratum 3324344 @@ -1107,6 +1107,7 @@ config ARM64_ERRATUM_3194386 * ARM Cortex-X925 erratum 3324334 * ARM Neoverse-N1 erratum 3324349 * ARM Neoverse N2 erratum 3324339 + * ARM Neoverse-N3 erratum 3456111 * ARM Neoverse-V1 erratum 3324341 * ARM Neoverse V2 erratum 3324336 * ARM Neoverse-V3 erratum 3312417 diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index b058c4803efb..9efd3f37c2fd 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -10,7 +10,7 @@ # # Copyright (C) 1995-2001 by Russell King -LDFLAGS_vmlinux :=--no-undefined -X +LDFLAGS_vmlinux :=--no-undefined -X --pic-veneer ifeq ($(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 ce9b28e3c7d6..a523b519700f 100644 --- a/arch/arm64/crypto/aes-ce-ccm-glue.c +++ b/arch/arm64/crypto/aes-ce-ccm-glue.c @@ -9,7 +9,7 @@ */ #include <asm/neon.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <crypto/aes.h> #include <crypto/scatterwalk.h> #include <crypto/internal/aead.h> diff --git a/arch/arm64/crypto/aes-ce-glue.c b/arch/arm64/crypto/aes-ce-glue.c index e921823ca103..00b8749013c5 100644 --- a/arch/arm64/crypto/aes-ce-glue.c +++ b/arch/arm64/crypto/aes-ce-glue.c @@ -7,7 +7,7 @@ #include <asm/neon.h> #include <asm/simd.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <crypto/aes.h> #include <crypto/algapi.h> #include <crypto/internal/simd.h> diff --git a/arch/arm64/crypto/ghash-ce-glue.c b/arch/arm64/crypto/ghash-ce-glue.c index 97331b454ea8..da7b7ec1a664 100644 --- a/arch/arm64/crypto/ghash-ce-glue.c +++ b/arch/arm64/crypto/ghash-ce-glue.c @@ -7,7 +7,7 @@ #include <asm/neon.h> #include <asm/simd.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <crypto/aes.h> #include <crypto/gcm.h> #include <crypto/algapi.h> diff --git a/arch/arm64/crypto/poly1305-glue.c b/arch/arm64/crypto/poly1305-glue.c index 9c4bfd62e789..18883ea438f3 100644 --- a/arch/arm64/crypto/poly1305-glue.c +++ b/arch/arm64/crypto/poly1305-glue.c @@ -8,7 +8,7 @@ #include <asm/hwcap.h> #include <asm/neon.h> #include <asm/simd.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <crypto/algapi.h> #include <crypto/internal/hash.h> #include <crypto/internal/poly1305.h> diff --git a/arch/arm64/crypto/sha1-ce-glue.c b/arch/arm64/crypto/sha1-ce-glue.c index 1dd93e1fcb39..cbd14f208f83 100644 --- a/arch/arm64/crypto/sha1-ce-glue.c +++ b/arch/arm64/crypto/sha1-ce-glue.c @@ -7,7 +7,7 @@ #include <asm/neon.h> #include <asm/simd.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <crypto/internal/hash.h> #include <crypto/internal/simd.h> #include <crypto/sha1.h> diff --git a/arch/arm64/crypto/sha2-ce-glue.c b/arch/arm64/crypto/sha2-ce-glue.c index 0a44d2e7ee1f..6b4866a88ded 100644 --- a/arch/arm64/crypto/sha2-ce-glue.c +++ b/arch/arm64/crypto/sha2-ce-glue.c @@ -7,7 +7,7 @@ #include <asm/neon.h> #include <asm/simd.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <crypto/internal/hash.h> #include <crypto/internal/simd.h> #include <crypto/sha2.h> diff --git a/arch/arm64/crypto/sha3-ce-glue.c b/arch/arm64/crypto/sha3-ce-glue.c index 250e1377c481..5662c3ac49e9 100644 --- a/arch/arm64/crypto/sha3-ce-glue.c +++ b/arch/arm64/crypto/sha3-ce-glue.c @@ -12,7 +12,7 @@ #include <asm/hwcap.h> #include <asm/neon.h> #include <asm/simd.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <crypto/internal/hash.h> #include <crypto/internal/simd.h> #include <crypto/sha3.h> diff --git a/arch/arm64/crypto/sha512-ce-glue.c b/arch/arm64/crypto/sha512-ce-glue.c index f3431fc62315..071f64293227 100644 --- a/arch/arm64/crypto/sha512-ce-glue.c +++ b/arch/arm64/crypto/sha512-ce-glue.c @@ -11,7 +11,7 @@ #include <asm/neon.h> #include <asm/simd.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <crypto/internal/hash.h> #include <crypto/internal/simd.h> #include <crypto/sha2.h> diff --git a/arch/arm64/crypto/sm3-ce-glue.c b/arch/arm64/crypto/sm3-ce-glue.c index 54bf6ebcfffb..1a71788c4cda 100644 --- a/arch/arm64/crypto/sm3-ce-glue.c +++ b/arch/arm64/crypto/sm3-ce-glue.c @@ -7,7 +7,7 @@ #include <asm/neon.h> #include <asm/simd.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <crypto/internal/hash.h> #include <crypto/internal/simd.h> #include <crypto/sm3.h> diff --git a/arch/arm64/crypto/sm3-neon-glue.c b/arch/arm64/crypto/sm3-neon-glue.c index 7182ee683f14..8dd71ce79b69 100644 --- a/arch/arm64/crypto/sm3-neon-glue.c +++ b/arch/arm64/crypto/sm3-neon-glue.c @@ -7,7 +7,7 @@ #include <asm/neon.h> #include <asm/simd.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <crypto/internal/hash.h> #include <crypto/internal/simd.h> #include <crypto/sm3.h> diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 5a7dfeb8e8eb..488f8e751349 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 329619c6fa96..94cff508874b 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 dfefbdf4073a..a78f247029ae 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/arm.c b/arch/arm64/kvm/arm.c index fe0764173cd0..a0d01c46e408 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -2164,7 +2164,7 @@ static void cpu_hyp_uninit(void *discard) } } -int kvm_arch_hardware_enable(void) +int kvm_arch_enable_virtualization_cpu(void) { /* * Most calls to this function are made with migration @@ -2184,7 +2184,7 @@ int kvm_arch_hardware_enable(void) return 0; } -void kvm_arch_hardware_disable(void) +void kvm_arch_disable_virtualization_cpu(void) { kvm_timer_cpu_down(); kvm_vgic_cpu_down(); @@ -2380,7 +2380,7 @@ static int __init do_pkvm_init(u32 hyp_va_bits) /* * The stub hypercalls are now disabled, so set our local flag to - * prevent a later re-init attempt in kvm_arch_hardware_enable(). + * prevent a later re-init attempt in kvm_arch_enable_virtualization_cpu(). */ __this_cpu_write(kvm_hyp_initialized, 1); preempt_enable(); diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index 46d52e8a3df3..5310fe1da616 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 87692b566d90..fefc89209f9e 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 187a5f4d56c0..077d4098548d 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 3eebea3a7b47..b7d9782827f5 100644 --- a/arch/loongarch/crypto/crc32-loongarch.c +++ b/arch/loongarch/crypto/crc32-loongarch.c @@ -13,7 +13,7 @@ #include <crypto/internal/hash.h> #include <asm/cpu-features.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define _CRC32(crc, value, size, type) \ do { \ diff --git a/arch/loongarch/kvm/main.c b/arch/loongarch/kvm/main.c index 844736b99d38..27e9b94c0a0b 100644 --- a/arch/loongarch/kvm/main.c +++ b/arch/loongarch/kvm/main.c @@ -261,7 +261,7 @@ long kvm_arch_dev_ioctl(struct file *filp, return -ENOIOCTLCMD; } -int kvm_arch_hardware_enable(void) +int kvm_arch_enable_virtualization_cpu(void) { unsigned long env, gcfg = 0; @@ -300,7 +300,7 @@ int kvm_arch_hardware_enable(void) return 0; } -void kvm_arch_hardware_disable(void) +void kvm_arch_disable_virtualization_cpu(void) { write_csr_gcfg(0); write_csr_gstat(0); diff --git a/arch/loongarch/vdso/vgetrandom-chacha.S b/arch/loongarch/vdso/vgetrandom-chacha.S index 7e86a50f6e85..c2733e6c3a8d 100644 --- a/arch/loongarch/vdso/vgetrandom-chacha.S +++ b/arch/loongarch/vdso/vgetrandom-chacha.S @@ -9,23 +9,11 @@ .text -/* Salsa20 quarter-round */ -.macro QR a b c d - add.w \a, \a, \b - xor \d, \d, \a - rotri.w \d, \d, 16 - - add.w \c, \c, \d - xor \b, \b, \c - rotri.w \b, \b, 20 - - add.w \a, \a, \b - xor \d, \d, \a - rotri.w \d, \d, 24 - - add.w \c, \c, \d - xor \b, \b, \c - rotri.w \b, \b, 25 +.macro OP_4REG op d0 d1 d2 d3 s0 s1 s2 s3 + \op \d0, \d0, \s0 + \op \d1, \d1, \s1 + \op \d2, \d2, \s2 + \op \d3, \d3, \s3 .endm /* @@ -74,6 +62,23 @@ SYM_FUNC_START(__arch_chacha20_blocks_nostack) /* Reuse i as copy3 */ #define copy3 i +/* Packs to be used with OP_4REG */ +#define line0 state0, state1, state2, state3 +#define line1 state4, state5, state6, state7 +#define line2 state8, state9, state10, state11 +#define line3 state12, state13, state14, state15 + +#define line1_perm state5, state6, state7, state4 +#define line2_perm state10, state11, state8, state9 +#define line3_perm state15, state12, state13, state14 + +#define copy copy0, copy1, copy2, copy3 + +#define _16 16, 16, 16, 16 +#define _20 20, 20, 20, 20 +#define _24 24, 24, 24, 24 +#define _25 25, 25, 25, 25 + /* * The ABI requires s0-s9 saved, and sp aligned to 16-byte. * This does not violate the stack-less requirement: no sensitive data @@ -126,16 +131,38 @@ SYM_FUNC_START(__arch_chacha20_blocks_nostack) li.w i, 10 .Lpermute: /* odd round */ - QR state0, state4, state8, state12 - QR state1, state5, state9, state13 - QR state2, state6, state10, state14 - QR state3, state7, state11, state15 + OP_4REG add.w line0, line1 + OP_4REG xor line3, line0 + OP_4REG rotri.w line3, _16 + + OP_4REG add.w line2, line3 + OP_4REG xor line1, line2 + OP_4REG rotri.w line1, _20 + + OP_4REG add.w line0, line1 + OP_4REG xor line3, line0 + OP_4REG rotri.w line3, _24 + + OP_4REG add.w line2, line3 + OP_4REG xor line1, line2 + OP_4REG rotri.w line1, _25 /* even round */ - QR state0, state5, state10, state15 - QR state1, state6, state11, state12 - QR state2, state7, state8, state13 - QR state3, state4, state9, state14 + OP_4REG add.w line0, line1_perm + OP_4REG xor line3_perm, line0 + OP_4REG rotri.w line3_perm, _16 + + OP_4REG add.w line2_perm, line3_perm + OP_4REG xor line1_perm, line2_perm + OP_4REG rotri.w line1_perm, _20 + + OP_4REG add.w line0, line1_perm + OP_4REG xor line3_perm, line0 + OP_4REG rotri.w line3_perm, _24 + + OP_4REG add.w line2_perm, line3_perm + OP_4REG xor line1_perm, line2_perm + OP_4REG rotri.w line1_perm, _25 addi.w i, i, -1 bnez i, .Lpermute @@ -147,10 +174,7 @@ SYM_FUNC_START(__arch_chacha20_blocks_nostack) li.w copy3, 0x6b206574 /* output[0,1,2,3] = copy[0,1,2,3] + state[0,1,2,3] */ - add.w state0, state0, copy0 - add.w state1, state1, copy1 - add.w state2, state2, copy2 - add.w state3, state3, copy3 + OP_4REG add.w line0, copy st.w state0, output, 0 st.w state1, output, 4 st.w state2, output, 8 @@ -165,10 +189,7 @@ SYM_FUNC_START(__arch_chacha20_blocks_nostack) ld.w state3, key, 12 /* output[4,5,6,7] = state[0,1,2,3] + state[4,5,6,7] */ - add.w state4, state4, state0 - add.w state5, state5, state1 - add.w state6, state6, state2 - add.w state7, state7, state3 + OP_4REG add.w line1, line0 st.w state4, output, 16 st.w state5, output, 20 st.w state6, output, 24 @@ -181,10 +202,7 @@ SYM_FUNC_START(__arch_chacha20_blocks_nostack) ld.w state3, key, 28 /* output[8,9,10,11] = state[0,1,2,3] + state[8,9,10,11] */ - add.w state8, state8, state0 - add.w state9, state9, state1 - add.w state10, state10, state2 - add.w state11, state11, state3 + OP_4REG add.w line2, line0 st.w state8, output, 32 st.w state9, output, 36 st.w state10, output, 40 diff --git a/arch/microblaze/include/asm/flat.h b/arch/microblaze/include/asm/flat.h index 79a749f4ad04..edff4306fa70 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 <asm/unaligned.h> +#include <linux/unaligned.h> /* * 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 adb6d5b0e6eb..90021c6a8cab 100644 --- a/arch/mips/boot/compressed/decompress.c +++ b/arch/mips/boot/compressed/decompress.c @@ -16,7 +16,7 @@ #include <linux/libfdt.h> #include <asm/addrspace.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <asm-generic/vmlinux.lds.h> #include "decompress.h" diff --git a/arch/mips/crypto/crc32-mips.c b/arch/mips/crypto/crc32-mips.c index 2a59b85f88aa..a7a1d43a1b2c 100644 --- a/arch/mips/crypto/crc32-mips.c +++ b/arch/mips/crypto/crc32-mips.c @@ -14,7 +14,7 @@ #include <linux/module.h> #include <linux/string.h> #include <asm/mipsregs.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <crypto/internal/hash.h> diff --git a/arch/mips/crypto/poly1305-glue.c b/arch/mips/crypto/poly1305-glue.c index 867728ee535a..c03ad0bbe69c 100644 --- a/arch/mips/crypto/poly1305-glue.c +++ b/arch/mips/crypto/poly1305-glue.c @@ -5,7 +5,7 @@ * Copyright (C) 2019 Linaro Ltd. <ard.biesheuvel@linaro.org> */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <crypto/algapi.h> #include <crypto/internal/hash.h> #include <crypto/internal/poly1305.h> diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h index 6743a57c1ab4..f7222eb594ea 100644 --- a/arch/mips/include/asm/kvm_host.h +++ b/arch/mips/include/asm/kvm_host.h @@ -728,8 +728,8 @@ struct kvm_mips_callbacks { int (*handle_fpe)(struct kvm_vcpu *vcpu); int (*handle_msa_disabled)(struct kvm_vcpu *vcpu); int (*handle_guest_exit)(struct kvm_vcpu *vcpu); - int (*hardware_enable)(void); - void (*hardware_disable)(void); + int (*enable_virtualization_cpu)(void); + void (*disable_virtualization_cpu)(void); int (*check_extension)(struct kvm *kvm, long ext); int (*vcpu_init)(struct kvm_vcpu *vcpu); void (*vcpu_uninit)(struct kvm_vcpu *vcpu); diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index b5de770b092e..60b43ea85c12 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -125,14 +125,14 @@ int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu) return 1; } -int kvm_arch_hardware_enable(void) +int kvm_arch_enable_virtualization_cpu(void) { - return kvm_mips_callbacks->hardware_enable(); + return kvm_mips_callbacks->enable_virtualization_cpu(); } -void kvm_arch_hardware_disable(void) +void kvm_arch_disable_virtualization_cpu(void) { - kvm_mips_callbacks->hardware_disable(); + kvm_mips_callbacks->disable_virtualization_cpu(); } int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) diff --git a/arch/mips/kvm/vz.c b/arch/mips/kvm/vz.c index 99d5a71e4300..ccab4d76b126 100644 --- a/arch/mips/kvm/vz.c +++ b/arch/mips/kvm/vz.c @@ -2869,7 +2869,7 @@ static unsigned int kvm_vz_resize_guest_vtlb(unsigned int size) return ret + 1; } -static int kvm_vz_hardware_enable(void) +static int kvm_vz_enable_virtualization_cpu(void) { unsigned int mmu_size, guest_mmu_size, ftlb_size; u64 guest_cvmctl, cvmvmconfig; @@ -2983,7 +2983,7 @@ static int kvm_vz_hardware_enable(void) return 0; } -static void kvm_vz_hardware_disable(void) +static void kvm_vz_disable_virtualization_cpu(void) { u64 cvmvmconfig; unsigned int mmu_size; @@ -3280,8 +3280,8 @@ static struct kvm_mips_callbacks kvm_vz_callbacks = { .handle_msa_disabled = kvm_trap_vz_handle_msa_disabled, .handle_guest_exit = kvm_trap_vz_handle_guest_exit, - .hardware_enable = kvm_vz_hardware_enable, - .hardware_disable = kvm_vz_hardware_disable, + .enable_virtualization_cpu = kvm_vz_enable_virtualization_cpu, + .disable_virtualization_cpu = kvm_vz_disable_virtualization_cpu, .check_extension = kvm_vz_check_extension, .vcpu_init = kvm_vz_vcpu_init, .vcpu_uninit = kvm_vz_vcpu_uninit, diff --git a/arch/nios2/kernel/misaligned.c b/arch/nios2/kernel/misaligned.c index 23e0544e117c..2f2862eab3c6 100644 --- a/arch/nios2/kernel/misaligned.c +++ b/arch/nios2/kernel/misaligned.c @@ -23,7 +23,7 @@ #include <linux/seq_file.h> #include <asm/traps.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /* instructions we emulate */ #define INST_LDHU 0x0b diff --git a/arch/parisc/boot/compressed/misc.c b/arch/parisc/boot/compressed/misc.c index d389359e22ac..9c83bd06ef15 100644 --- a/arch/parisc/boot/compressed/misc.c +++ b/arch/parisc/boot/compressed/misc.c @@ -6,7 +6,7 @@ #include <linux/uaccess.h> #include <linux/elf.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <asm/page.h> #include "sizes.h" diff --git a/arch/parisc/include/asm/unaligned.h b/arch/parisc/include/asm/unaligned.h deleted file mode 100644 index c0621295100d..000000000000 --- 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 <asm-generic/unaligned.h> - -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 294b0e026c9a..b9b3d527bc90 100644 --- a/arch/parisc/kernel/traps.c +++ b/arch/parisc/kernel/traps.c @@ -36,7 +36,7 @@ #include <asm/io.h> #include <asm/irq.h> #include <asm/traps.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/atomic.h> #include <asm/smp.h> #include <asm/pdc.h> @@ -47,6 +47,8 @@ #include <linux/kgdb.h> #include <linux/kprobes.h> +#include "unaligned.h" + #if defined(CONFIG_LIGHTWEIGHT_SPINLOCK_CHECK) #include <asm/spinlock.h> #endif diff --git a/arch/parisc/kernel/unaligned.c b/arch/parisc/kernel/unaligned.c index 3e79e40e361d..f4626943633a 100644 --- a/arch/parisc/kernel/unaligned.c +++ b/arch/parisc/kernel/unaligned.c @@ -12,9 +12,10 @@ #include <linux/ratelimit.h> #include <linux/uaccess.h> #include <linux/sysctl.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <asm/hardirq.h> #include <asm/traps.h> +#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 000000000000..c1aa4b12e284 --- /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 f62ee54076c0..f66ad56e765f 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 <asm/unaligned.h> +#include <linux/unaligned.h> #include <asm/simd.h> #include <asm/switch_to.h> #include <crypto/aes.h> diff --git a/arch/powerpc/crypto/poly1305-p10-glue.c b/arch/powerpc/crypto/poly1305-p10-glue.c index 95dd708573ee..369686e9370b 100644 --- a/arch/powerpc/crypto/poly1305-p10-glue.c +++ b/arch/powerpc/crypto/poly1305-p10-glue.c @@ -14,7 +14,7 @@ #include <crypto/internal/poly1305.h> #include <crypto/internal/simd.h> #include <linux/cpufeature.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <asm/simd.h> #include <asm/switch_to.h> diff --git a/arch/powerpc/kernel/vdso/Makefile b/arch/powerpc/kernel/vdso/Makefile index 56fb1633529a..31ca5a547004 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 d95e03b3d3e3..9e297f88adc5 100644 --- a/arch/powerpc/platforms/pseries/papr_scm.c +++ b/arch/powerpc/platforms/pseries/papr_scm.c @@ -19,7 +19,7 @@ #include <uapi/linux/papr_pdsm.h> #include <linux/papr_scm.h> #include <asm/mce.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/perf_event.h> #define BIND_ANY_ADDR (~0ul) diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 22dc5ea4196c..62545946ecf4 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 ebe52f96da34..9c10fb180f43 100644 --- a/arch/riscv/include/asm/thread_info.h +++ b/arch/riscv/include/asm/thread_info.h @@ -13,7 +13,12 @@ #include <linux/sizes.h> /* 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/riscv/kvm/main.c b/arch/riscv/kvm/main.c index bab2ec34cd87..f3427f6de608 100644 --- a/arch/riscv/kvm/main.c +++ b/arch/riscv/kvm/main.c @@ -20,7 +20,7 @@ long kvm_arch_dev_ioctl(struct file *filp, return -EINVAL; } -int kvm_arch_hardware_enable(void) +int kvm_arch_enable_virtualization_cpu(void) { csr_write(CSR_HEDELEG, KVM_HEDELEG_DEFAULT); csr_write(CSR_HIDELEG, KVM_HIDELEG_DEFAULT); @@ -35,7 +35,7 @@ int kvm_arch_hardware_enable(void) return 0; } -void kvm_arch_hardware_disable(void) +void kvm_arch_disable_virtualization_cpu(void) { kvm_riscv_aia_disable(); diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 7ec1b8cd0de9..9b57add02cd5 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -59,6 +59,7 @@ CONFIG_CMM=m CONFIG_APPLDATA_BASE=y CONFIG_S390_HYPFS_FS=y CONFIG_KVM=m +CONFIG_KVM_S390_UCONTROL=y CONFIG_S390_UNWIND_SELFTEST=m CONFIG_S390_KPROBES_SANITY_TEST=m CONFIG_S390_MODULES_SANITY_TEST=m diff --git a/arch/s390/kernel/vdso64/vdso_user_wrapper.S b/arch/s390/kernel/vdso64/vdso_user_wrapper.S index e26e68675c08..aa06c85bcbd3 100644 --- a/arch/s390/kernel/vdso64/vdso_user_wrapper.S +++ b/arch/s390/kernel/vdso64/vdso_user_wrapper.S @@ -13,10 +13,7 @@ * for details. */ .macro vdso_func func - .globl __kernel_\func - .type __kernel_\func,@function - __ALIGN -__kernel_\func: +SYM_FUNC_START(__kernel_\func) CFI_STARTPROC aghi %r15,-STACK_FRAME_VDSO_OVERHEAD CFI_DEF_CFA_OFFSET (STACK_FRAME_USER_OVERHEAD + STACK_FRAME_VDSO_OVERHEAD) @@ -32,7 +29,7 @@ __kernel_\func: CFI_RESTORE 15 br %r14 CFI_ENDPROC - .size __kernel_\func,.-__kernel_\func +SYM_FUNC_END(__kernel_\func) .endm vdso_func gettimeofday @@ -41,16 +38,13 @@ vdso_func clock_gettime vdso_func getcpu .macro vdso_syscall func,syscall - .globl __kernel_\func - .type __kernel_\func,@function - __ALIGN -__kernel_\func: +SYM_FUNC_START(__kernel_\func) CFI_STARTPROC svc \syscall /* Make sure we notice when a syscall returns, which shouldn't happen */ .word 0 CFI_ENDPROC - .size __kernel_\func,.-__kernel_\func +SYM_FUNC_END(__kernel_\func) .endm vdso_syscall restart_syscall,__NR_restart_syscall diff --git a/arch/s390/kernel/vdso64/vgetrandom-chacha.S b/arch/s390/kernel/vdso64/vgetrandom-chacha.S index d802b0a96f41..09c034c2f853 100644 --- a/arch/s390/kernel/vdso64/vgetrandom-chacha.S +++ b/arch/s390/kernel/vdso64/vgetrandom-chacha.S @@ -1,7 +1,9 @@ /* SPDX-License-Identifier: GPL-2.0 */ +#include <linux/stringify.h> #include <linux/linkage.h> #include <asm/alternative.h> +#include <asm/dwarf.h> #include <asm/fpu-insn.h> #define STATE0 %v0 @@ -12,9 +14,6 @@ #define COPY1 %v5 #define COPY2 %v6 #define COPY3 %v7 -#define PERM4 %v16 -#define PERM8 %v17 -#define PERM12 %v18 #define BEPERM %v19 #define TMP0 %v20 #define TMP1 %v21 @@ -23,13 +22,11 @@ .section .rodata - .balign 128 -.Lconstants: + .balign 32 +SYM_DATA_START_LOCAL(chacha20_constants) .long 0x61707865,0x3320646e,0x79622d32,0x6b206574 # endian-neutral - .long 0x04050607,0x08090a0b,0x0c0d0e0f,0x00010203 # rotl 4 bytes - .long 0x08090a0b,0x0c0d0e0f,0x00010203,0x04050607 # rotl 8 bytes - .long 0x0c0d0e0f,0x00010203,0x04050607,0x08090a0b # rotl 12 bytes .long 0x03020100,0x07060504,0x0b0a0908,0x0f0e0d0c # byte swap +SYM_DATA_END(chacha20_constants) .text /* @@ -43,13 +40,14 @@ * size_t nblocks) */ SYM_FUNC_START(__arch_chacha20_blocks_nostack) - larl %r1,.Lconstants + CFI_STARTPROC + larl %r1,chacha20_constants /* COPY0 = "expand 32-byte k" */ VL COPY0,0,,%r1 - /* PERM4-PERM12,BEPERM = byte selectors for VPERM */ - VLM PERM4,BEPERM,16,%r1 + /* BEPERM = byte selectors for VPERM */ + ALTERNATIVE __stringify(VL BEPERM,16,,%r1), "brcl 0,0", ALT_FACILITY(148) /* COPY1,COPY2 = key */ VLM COPY1,COPY2,0,%r3 @@ -89,11 +87,11 @@ SYM_FUNC_START(__arch_chacha20_blocks_nostack) VERLLF STATE1,STATE1,7 /* STATE1[0,1,2,3] = STATE1[1,2,3,0] */ - VPERM STATE1,STATE1,STATE1,PERM4 + VSLDB STATE1,STATE1,STATE1,4 /* STATE2[0,1,2,3] = STATE2[2,3,0,1] */ - VPERM STATE2,STATE2,STATE2,PERM8 + VSLDB STATE2,STATE2,STATE2,8 /* STATE3[0,1,2,3] = STATE3[3,0,1,2] */ - VPERM STATE3,STATE3,STATE3,PERM12 + VSLDB STATE3,STATE3,STATE3,12 /* STATE0 += STATE1, STATE3 = rotl32(STATE3 ^ STATE0, 16) */ VAF STATE0,STATE0,STATE1 @@ -116,32 +114,38 @@ SYM_FUNC_START(__arch_chacha20_blocks_nostack) VERLLF STATE1,STATE1,7 /* STATE1[0,1,2,3] = STATE1[3,0,1,2] */ - VPERM STATE1,STATE1,STATE1,PERM12 + VSLDB STATE1,STATE1,STATE1,12 /* STATE2[0,1,2,3] = STATE2[2,3,0,1] */ - VPERM STATE2,STATE2,STATE2,PERM8 + VSLDB STATE2,STATE2,STATE2,8 /* STATE3[0,1,2,3] = STATE3[1,2,3,0] */ - VPERM STATE3,STATE3,STATE3,PERM4 + VSLDB STATE3,STATE3,STATE3,4 brctg %r0,.Ldoubleround - /* OUTPUT0 = STATE0 + STATE0 */ + /* OUTPUT0 = STATE0 + COPY0 */ VAF STATE0,STATE0,COPY0 - /* OUTPUT1 = STATE1 + STATE1 */ + /* OUTPUT1 = STATE1 + COPY1 */ VAF STATE1,STATE1,COPY1 - /* OUTPUT2 = STATE2 + STATE2 */ + /* OUTPUT2 = STATE2 + COPY2 */ VAF STATE2,STATE2,COPY2 - /* OUTPUT2 = STATE3 + STATE3 */ + /* OUTPUT3 = STATE3 + COPY3 */ VAF STATE3,STATE3,COPY3 - /* - * 32 bit wise little endian store to OUTPUT. If the vector - * enhancement facility 2 is not installed use the slow path. - */ - ALTERNATIVE "brc 0xf,.Lstoreslow", "nop", ALT_FACILITY(148) - VSTBRF STATE0,0,,%r2 - VSTBRF STATE1,16,,%r2 - VSTBRF STATE2,32,,%r2 - VSTBRF STATE3,48,,%r2 -.Lstoredone: + ALTERNATIVE \ + __stringify( \ + /* Convert STATE to little endian and store to OUTPUT */\ + VPERM TMP0,STATE0,STATE0,BEPERM; \ + VPERM TMP1,STATE1,STATE1,BEPERM; \ + VPERM TMP2,STATE2,STATE2,BEPERM; \ + VPERM TMP3,STATE3,STATE3,BEPERM; \ + VSTM TMP0,TMP3,0,%r2), \ + __stringify( \ + /* 32 bit wise little endian store to OUTPUT */ \ + VSTBRF STATE0,0,,%r2; \ + VSTBRF STATE1,16,,%r2; \ + VSTBRF STATE2,32,,%r2; \ + VSTBRF STATE3,48,,%r2; \ + brcl 0,0), \ + ALT_FACILITY(148) /* ++COPY3.COUNTER */ /* alsih %r3,1 */ @@ -173,13 +177,5 @@ SYM_FUNC_START(__arch_chacha20_blocks_nostack) VZERO TMP3 br %r14 - -.Lstoreslow: - /* Convert STATE to little endian format and store to OUTPUT */ - VPERM TMP0,STATE0,STATE0,BEPERM - VPERM TMP1,STATE1,STATE1,BEPERM - VPERM TMP2,STATE2,STATE2,BEPERM - VPERM TMP3,STATE3,STATE3,BEPERM - VSTM TMP0,TMP3,0,%r2 - j .Lstoredone + CFI_ENDPROC SYM_FUNC_END(__arch_chacha20_blocks_nostack) diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 0fd96860fc45..bb7134faaebf 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -348,20 +348,29 @@ static inline int plo_test_bit(unsigned char nr) return cc == 0; } -static __always_inline void __insn32_query(unsigned int opcode, u8 *query) +static __always_inline void __sortl_query(u8 (*query)[32]) { asm volatile( " lghi 0,0\n" - " lgr 1,%[query]\n" + " la 1,%[query]\n" /* Parameter registers are ignored */ - " .insn rrf,%[opc] << 16,2,4,6,0\n" + " .insn rre,0xb9380000,2,4\n" + : [query] "=R" (*query) : - : [query] "d" ((unsigned long)query), [opc] "i" (opcode) - : "cc", "memory", "0", "1"); + : "cc", "0", "1"); } -#define INSN_SORTL 0xb938 -#define INSN_DFLTCC 0xb939 +static __always_inline void __dfltcc_query(u8 (*query)[32]) +{ + asm volatile( + " lghi 0,0\n" + " la 1,%[query]\n" + /* Parameter registers are ignored */ + " .insn rrf,0xb9390000,2,4,6,0\n" + : [query] "=R" (*query) + : + : "cc", "0", "1"); +} static void __init kvm_s390_cpu_feat_init(void) { @@ -415,10 +424,10 @@ static void __init kvm_s390_cpu_feat_init(void) kvm_s390_available_subfunc.kdsa); if (test_facility(150)) /* SORTL */ - __insn32_query(INSN_SORTL, kvm_s390_available_subfunc.sortl); + __sortl_query(&kvm_s390_available_subfunc.sortl); if (test_facility(151)) /* DFLTCC */ - __insn32_query(INSN_DFLTCC, kvm_s390_available_subfunc.dfltcc); + __dfltcc_query(&kvm_s390_available_subfunc.dfltcc); if (MACHINE_HAS_ESOP) allow_cpu_feat(KVM_S390_VM_CPU_FEAT_ESOP); diff --git a/arch/sh/include/asm/flat.h b/arch/sh/include/asm/flat.h index fee4f25555cb..70752c7bc55f 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 <asm/unaligned.h> +#include <linux/unaligned.h> 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 45c8ae20d109..a1b54bedc929 100644 --- a/arch/sh/kernel/dwarf.c +++ b/arch/sh/kernel/dwarf.c @@ -24,7 +24,7 @@ #include <asm/dwarf.h> #include <asm/unwinder.h> #include <asm/sections.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <asm/stacktrace.h> /* Reserve enough memory for two stack frames */ diff --git a/arch/sh/kernel/module.c b/arch/sh/kernel/module.c index b9cee98a754e..a469a80840d3 100644 --- a/arch/sh/kernel/module.c +++ b/arch/sh/kernel/module.c @@ -18,7 +18,7 @@ #include <linux/fs.h> #include <linux/string.h> #include <linux/kernel.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <asm/dwarf.h> int apply_relocate_add(Elf32_Shdr *sechdrs, diff --git a/arch/sparc/crypto/crc32c_glue.c b/arch/sparc/crypto/crc32c_glue.c index 688db0dcb97d..913b9a09e885 100644 --- a/arch/sparc/crypto/crc32c_glue.c +++ b/arch/sparc/crypto/crc32c_glue.c @@ -20,7 +20,7 @@ #include <asm/pstate.h> #include <asm/elf.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "opcodes.h" diff --git a/arch/um/Kconfig b/arch/um/Kconfig index dca84fd6d00a..c89575d05021 100644 --- a/arch/um/Kconfig +++ b/arch/um/Kconfig @@ -11,7 +11,6 @@ config UML select ARCH_HAS_KCOV select ARCH_HAS_STRNCPY_FROM_USER select ARCH_HAS_STRNLEN_USER - select ARCH_NO_PREEMPT_DYNAMIC select HAVE_ARCH_AUDITSYSCALL select HAVE_ARCH_KASAN if X86_64 select HAVE_ARCH_KASAN_VMALLOC if HAVE_ARCH_KASAN diff --git a/arch/um/drivers/vector_kern.c b/arch/um/drivers/vector_kern.c index 2d473282ab51..c992da83268d 100644 --- a/arch/um/drivers/vector_kern.c +++ b/arch/um/drivers/vector_kern.c @@ -22,6 +22,7 @@ #include <linux/interrupt.h> #include <linux/firmware.h> #include <linux/fs.h> +#include <asm/atomic.h> #include <uapi/linux/filter.h> #include <init.h> #include <irq_kern.h> @@ -102,18 +103,33 @@ static const struct { static void vector_reset_stats(struct vector_private *vp) { + /* We reuse the existing queue locks for stats */ + + /* RX stats are modified with RX head_lock held + * in vector_poll. + */ + + spin_lock(&vp->rx_queue->head_lock); vp->estats.rx_queue_max = 0; vp->estats.rx_queue_running_average = 0; - vp->estats.tx_queue_max = 0; - vp->estats.tx_queue_running_average = 0; vp->estats.rx_encaps_errors = 0; + vp->estats.sg_ok = 0; + vp->estats.sg_linearized = 0; + spin_unlock(&vp->rx_queue->head_lock); + + /* TX stats are modified with TX head_lock held + * in vector_send. + */ + + spin_lock(&vp->tx_queue->head_lock); vp->estats.tx_timeout_count = 0; vp->estats.tx_restart_queue = 0; vp->estats.tx_kicks = 0; vp->estats.tx_flow_control_xon = 0; vp->estats.tx_flow_control_xoff = 0; - vp->estats.sg_ok = 0; - vp->estats.sg_linearized = 0; + vp->estats.tx_queue_max = 0; + vp->estats.tx_queue_running_average = 0; + spin_unlock(&vp->tx_queue->head_lock); } static int get_mtu(struct arglist *def) @@ -232,12 +248,6 @@ static int get_transport_options(struct arglist *def) static char *drop_buffer; -/* Array backed queues optimized for bulk enqueue/dequeue and - * 1:N (small values of N) or 1:1 enqueuer/dequeuer ratios. - * For more details and full design rationale see - * http://foswiki.cambridgegreys.com/Main/EatYourTailAndEnjoyIt - */ - /* * Advance the mmsg queue head by n = advance. Resets the queue to @@ -247,27 +257,13 @@ static char *drop_buffer; static int vector_advancehead(struct vector_queue *qi, int advance) { - int queue_depth; - qi->head = (qi->head + advance) % qi->max_depth; - spin_lock(&qi->tail_lock); - qi->queue_depth -= advance; - - /* we are at 0, use this to - * reset head and tail so we can use max size vectors - */ - - if (qi->queue_depth == 0) { - qi->head = 0; - qi->tail = 0; - } - queue_depth = qi->queue_depth; - spin_unlock(&qi->tail_lock); - return queue_depth; + atomic_sub(advance, &qi->queue_depth); + return atomic_read(&qi->queue_depth); } /* Advance the queue tail by n = advance. @@ -277,16 +273,11 @@ static int vector_advancehead(struct vector_queue *qi, int advance) static int vector_advancetail(struct vector_queue *qi, int advance) { - int queue_depth; - qi->tail = (qi->tail + advance) % qi->max_depth; - spin_lock(&qi->head_lock); - qi->queue_depth += advance; - queue_depth = qi->queue_depth; - spin_unlock(&qi->head_lock); - return queue_depth; + atomic_add(advance, &qi->queue_depth); + return atomic_read(&qi->queue_depth); } static int prep_msg(struct vector_private *vp, @@ -339,9 +330,7 @@ static int vector_enqueue(struct vector_queue *qi, struct sk_buff *skb) int iov_count; spin_lock(&qi->tail_lock); - spin_lock(&qi->head_lock); - queue_depth = qi->queue_depth; - spin_unlock(&qi->head_lock); + queue_depth = atomic_read(&qi->queue_depth); if (skb) packet_len = skb->len; @@ -360,6 +349,7 @@ static int vector_enqueue(struct vector_queue *qi, struct sk_buff *skb) mmsg_vector->msg_hdr.msg_iovlen = iov_count; mmsg_vector->msg_hdr.msg_name = vp->fds->remote_addr; mmsg_vector->msg_hdr.msg_namelen = vp->fds->remote_addr_size; + wmb(); /* Make the packet visible to the NAPI poll thread */ queue_depth = vector_advancetail(qi, 1); } else goto drop; @@ -398,7 +388,7 @@ static int consume_vector_skbs(struct vector_queue *qi, int count) } /* - * Generic vector deque via sendmmsg with support for forming headers + * Generic vector dequeue via sendmmsg with support for forming headers * using transport specific callback. Allows GRE, L2TPv3, RAW and * other transports to use a common dequeue procedure in vector mode */ @@ -408,69 +398,64 @@ static int vector_send(struct vector_queue *qi) { struct vector_private *vp = netdev_priv(qi->dev); struct mmsghdr *send_from; - int result = 0, send_len, queue_depth = qi->max_depth; + int result = 0, send_len; if (spin_trylock(&qi->head_lock)) { - if (spin_trylock(&qi->tail_lock)) { - /* update queue_depth to current value */ - queue_depth = qi->queue_depth; - spin_unlock(&qi->tail_lock); - while (queue_depth > 0) { - /* Calculate the start of the vector */ - send_len = queue_depth; - send_from = qi->mmsg_vector; - send_from += qi->head; - /* Adjust vector size if wraparound */ - if (send_len + qi->head > qi->max_depth) - send_len = qi->max_depth - qi->head; - /* Try to TX as many packets as possible */ - if (send_len > 0) { - result = uml_vector_sendmmsg( - vp->fds->tx_fd, - send_from, - send_len, - 0 - ); - vp->in_write_poll = - (result != send_len); - } - /* For some of the sendmmsg error scenarios - * we may end being unsure in the TX success - * for all packets. It is safer to declare - * them all TX-ed and blame the network. - */ - if (result < 0) { - if (net_ratelimit()) - netdev_err(vp->dev, "sendmmsg err=%i\n", - result); - vp->in_error = true; - result = send_len; - } - if (result > 0) { - queue_depth = - consume_vector_skbs(qi, result); - /* This is equivalent to an TX IRQ. - * Restart the upper layers to feed us - * more packets. - */ - if (result > vp->estats.tx_queue_max) - vp->estats.tx_queue_max = result; - vp->estats.tx_queue_running_average = - (vp->estats.tx_queue_running_average + result) >> 1; - } - netif_wake_queue(qi->dev); - /* if TX is busy, break out of the send loop, - * poll write IRQ will reschedule xmit for us + /* update queue_depth to current value */ + while (atomic_read(&qi->queue_depth) > 0) { + /* Calculate the start of the vector */ + send_len = atomic_read(&qi->queue_depth); + send_from = qi->mmsg_vector; + send_from += qi->head; + /* Adjust vector size if wraparound */ + if (send_len + qi->head > qi->max_depth) + send_len = qi->max_depth - qi->head; + /* Try to TX as many packets as possible */ + if (send_len > 0) { + result = uml_vector_sendmmsg( + vp->fds->tx_fd, + send_from, + send_len, + 0 + ); + vp->in_write_poll = + (result != send_len); + } + /* For some of the sendmmsg error scenarios + * we may end being unsure in the TX success + * for all packets. It is safer to declare + * them all TX-ed and blame the network. + */ + if (result < 0) { + if (net_ratelimit()) + netdev_err(vp->dev, "sendmmsg err=%i\n", + result); + vp->in_error = true; + result = send_len; + } + if (result > 0) { + consume_vector_skbs(qi, result); + /* This is equivalent to an TX IRQ. + * Restart the upper layers to feed us + * more packets. */ - if (result != send_len) { - vp->estats.tx_restart_queue++; - break; - } + if (result > vp->estats.tx_queue_max) + vp->estats.tx_queue_max = result; + vp->estats.tx_queue_running_average = + (vp->estats.tx_queue_running_average + result) >> 1; + } + netif_wake_queue(qi->dev); + /* if TX is busy, break out of the send loop, + * poll write IRQ will reschedule xmit for us. + */ + if (result != send_len) { + vp->estats.tx_restart_queue++; + break; } } spin_unlock(&qi->head_lock); } - return queue_depth; + return atomic_read(&qi->queue_depth); } /* Queue destructor. Deliberately stateless so we can use @@ -589,7 +574,7 @@ static struct vector_queue *create_queue( } spin_lock_init(&result->head_lock); spin_lock_init(&result->tail_lock); - result->queue_depth = 0; + atomic_set(&result->queue_depth, 0); result->head = 0; result->tail = 0; return result; @@ -668,18 +653,27 @@ done: } -/* Prepare queue for recvmmsg one-shot rx - fill with fresh sk_buffs*/ +/* Prepare queue for recvmmsg one-shot rx - fill with fresh sk_buffs */ static void prep_queue_for_rx(struct vector_queue *qi) { struct vector_private *vp = netdev_priv(qi->dev); struct mmsghdr *mmsg_vector = qi->mmsg_vector; void **skbuff_vector = qi->skbuff_vector; - int i; + int i, queue_depth; + + queue_depth = atomic_read(&qi->queue_depth); - if (qi->queue_depth == 0) + if (queue_depth == 0) return; - for (i = 0; i < qi->queue_depth; i++) { + + /* RX is always emptied 100% during each cycle, so we do not + * have to do the tail wraparound math for it. + */ + + qi->head = qi->tail = 0; + + for (i = 0; i < queue_depth; i++) { /* it is OK if allocation fails - recvmmsg with NULL data in * iov argument still performs an RX, just drops the packet * This allows us stop faffing around with a "drop buffer" @@ -689,7 +683,7 @@ static void prep_queue_for_rx(struct vector_queue *qi) skbuff_vector++; mmsg_vector++; } - qi->queue_depth = 0; + atomic_set(&qi->queue_depth, 0); } static struct vector_device *find_device(int n) @@ -972,7 +966,7 @@ static int vector_mmsg_rx(struct vector_private *vp, int budget) budget = qi->max_depth; packet_count = uml_vector_recvmmsg( - vp->fds->rx_fd, qi->mmsg_vector, qi->max_depth, 0); + vp->fds->rx_fd, qi->mmsg_vector, budget, 0); if (packet_count < 0) vp->in_error = true; @@ -985,7 +979,7 @@ static int vector_mmsg_rx(struct vector_private *vp, int budget) * many do we need to prep the next time prep_queue_for_rx() is called. */ - qi->queue_depth = packet_count; + atomic_add(packet_count, &qi->queue_depth); for (i = 0; i < packet_count; i++) { skb = (*skbuff_vector); @@ -1172,6 +1166,7 @@ static int vector_poll(struct napi_struct *napi, int budget) if ((vp->options & VECTOR_TX) != 0) tx_enqueued = (vector_send(vp->tx_queue) > 0); + spin_lock(&vp->rx_queue->head_lock); if ((vp->options & VECTOR_RX) > 0) err = vector_mmsg_rx(vp, budget); else { @@ -1179,12 +1174,13 @@ static int vector_poll(struct napi_struct *napi, int budget) if (err > 0) err = 1; } + spin_unlock(&vp->rx_queue->head_lock); if (err > 0) work_done += err; if (tx_enqueued || err > 0) napi_schedule(napi); - if (work_done < budget) + if (work_done <= budget) napi_complete_done(napi, work_done); return work_done; } @@ -1225,7 +1221,7 @@ static int vector_net_open(struct net_device *dev) vp->rx_header_size, MAX_IOV_SIZE ); - vp->rx_queue->queue_depth = get_depth(vp->parsed); + atomic_set(&vp->rx_queue->queue_depth, get_depth(vp->parsed)); } else { vp->header_rxbuffer = kmalloc( vp->rx_header_size, @@ -1467,7 +1463,17 @@ static void vector_get_ethtool_stats(struct net_device *dev, { struct vector_private *vp = netdev_priv(dev); + /* Stats are modified in the dequeue portions of + * rx/tx which are protected by the head locks + * grabbing these locks here ensures they are up + * to date. + */ + + spin_lock(&vp->tx_queue->head_lock); + spin_lock(&vp->rx_queue->head_lock); memcpy(tmp_stats, &vp->estats, sizeof(struct vector_estats)); + spin_unlock(&vp->rx_queue->head_lock); + spin_unlock(&vp->tx_queue->head_lock); } static int vector_get_coalesce(struct net_device *netdev, diff --git a/arch/um/drivers/vector_kern.h b/arch/um/drivers/vector_kern.h index 806df551be0b..417834793658 100644 --- a/arch/um/drivers/vector_kern.h +++ b/arch/um/drivers/vector_kern.h @@ -14,6 +14,7 @@ #include <linux/ctype.h> #include <linux/workqueue.h> #include <linux/interrupt.h> +#include <asm/atomic.h> #include "vector_user.h" @@ -44,7 +45,8 @@ struct vector_queue { struct net_device *dev; spinlock_t head_lock; spinlock_t tail_lock; - int queue_depth, head, tail, max_depth, max_iov_frags; + atomic_t queue_depth; + int head, tail, max_depth, max_iov_frags; short options; }; diff --git a/arch/um/drivers/vector_user.c b/arch/um/drivers/vector_user.c index b16a5e5619d3..2ea67e6fd067 100644 --- a/arch/um/drivers/vector_user.c +++ b/arch/um/drivers/vector_user.c @@ -46,6 +46,9 @@ #define TRANS_FD "fd" #define TRANS_FD_LEN strlen(TRANS_FD) +#define TRANS_VDE "vde" +#define TRANS_VDE_LEN strlen(TRANS_VDE) + #define VNET_HDR_FAIL "could not enable vnet headers on fd %d" #define TUN_GET_F_FAIL "tapraw: TUNGETFEATURES failed: %s" #define L2TPV3_BIND_FAIL "l2tpv3_open : could not bind socket err=%i" @@ -434,6 +437,84 @@ fd_cleanup: return NULL; } +/* enough char to store an int type */ +#define ENOUGH(type) ((CHAR_BIT * sizeof(type) - 1) / 3 + 2) +#define ENOUGH_OCTAL(type) ((CHAR_BIT * sizeof(type) + 2) / 3) +/* vde_plug --descr xx --port2 xx --mod2 xx --group2 xx seqpacket://NN vnl (NULL) */ +#define VDE_MAX_ARGC 12 +#define VDE_SEQPACKET_HEAD "seqpacket://" +#define VDE_SEQPACKET_HEAD_LEN (sizeof(VDE_SEQPACKET_HEAD) - 1) +#define VDE_DEFAULT_DESCRIPTION "UML" + +static struct vector_fds *user_init_vde_fds(struct arglist *ifspec) +{ + char seqpacketvnl[VDE_SEQPACKET_HEAD_LEN + ENOUGH(int) + 1]; + char *argv[VDE_MAX_ARGC] = {"vde_plug"}; + int argc = 1; + int rv; + int sv[2]; + struct vector_fds *result = NULL; + + char *vnl = uml_vector_fetch_arg(ifspec,"vnl"); + char *descr = uml_vector_fetch_arg(ifspec,"descr"); + char *port = uml_vector_fetch_arg(ifspec,"port"); + char *mode = uml_vector_fetch_arg(ifspec,"mode"); + char *group = uml_vector_fetch_arg(ifspec,"group"); + if (descr == NULL) descr = VDE_DEFAULT_DESCRIPTION; + + argv[argc++] = "--descr"; + argv[argc++] = descr; + if (port != NULL) { + argv[argc++] = "--port2"; + argv[argc++] = port; + } + if (mode != NULL) { + argv[argc++] = "--mod2"; + argv[argc++] = mode; + } + if (group != NULL) { + argv[argc++] = "--group2"; + argv[argc++] = group; + } + argv[argc++] = seqpacketvnl; + argv[argc++] = vnl; + argv[argc++] = NULL; + + rv = socketpair(AF_UNIX, SOCK_SEQPACKET, 0, sv); + if (rv < 0) { + printk(UM_KERN_ERR "vde: seqpacket socketpair err %d", -errno); + return NULL; + } + rv = os_set_exec_close(sv[0]); + if (rv < 0) { + printk(UM_KERN_ERR "vde: seqpacket socketpair cloexec err %d", -errno); + goto vde_cleanup_sv; + } + snprintf(seqpacketvnl, sizeof(seqpacketvnl), VDE_SEQPACKET_HEAD "%d", sv[1]); + + run_helper(NULL, NULL, argv); + + close(sv[1]); + + result = uml_kmalloc(sizeof(struct vector_fds), UM_GFP_KERNEL); + if (result == NULL) { + printk(UM_KERN_ERR "fd open: allocation failed"); + goto vde_cleanup; + } + + result->rx_fd = sv[0]; + result->tx_fd = sv[0]; + result->remote_addr_size = 0; + result->remote_addr = NULL; + return result; + +vde_cleanup_sv: + close(sv[1]); +vde_cleanup: + close(sv[0]); + return NULL; +} + static struct vector_fds *user_init_raw_fds(struct arglist *ifspec) { int rxfd = -1, txfd = -1; @@ -673,6 +754,8 @@ struct vector_fds *uml_vector_user_open( return user_init_unix_fds(parsed, ID_BESS); if (strncmp(transport, TRANS_FD, TRANS_FD_LEN) == 0) return user_init_fd_fds(parsed); + if (strncmp(transport, TRANS_VDE, TRANS_VDE_LEN) == 0) + return user_init_vde_fds(parsed); return NULL; } diff --git a/arch/um/drivers/virt-pci.c b/arch/um/drivers/virt-pci.c index 6100819681b5..744e7f31e8ef 100644 --- a/arch/um/drivers/virt-pci.c +++ b/arch/um/drivers/virt-pci.c @@ -14,7 +14,7 @@ #include <linux/virtio-uml.h> #include <linux/delay.h> #include <linux/msi.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <irq_kern.h> #define MAX_DEVICES 8 diff --git a/arch/um/include/asm/pgtable.h b/arch/um/include/asm/pgtable.h index 5bb397b65efb..83373c9963e7 100644 --- a/arch/um/include/asm/pgtable.h +++ b/arch/um/include/asm/pgtable.h @@ -359,11 +359,4 @@ static inline pte_t pte_swp_clear_exclusive(pte_t pte) return pte; } -/* Clear a kernel PTE and flush it from the TLB */ -#define kpte_clear_flush(ptep, vaddr) \ -do { \ - pte_clear(&init_mm, (vaddr), (ptep)); \ - __flush_tlb_one((vaddr)); \ -} while (0) - #endif diff --git a/arch/um/include/asm/processor-generic.h b/arch/um/include/asm/processor-generic.h index 5a7c05275aa7..bce4595798da 100644 --- a/arch/um/include/asm/processor-generic.h +++ b/arch/um/include/asm/processor-generic.h @@ -28,20 +28,10 @@ struct thread_struct { struct arch_thread arch; jmp_buf switch_buf; struct { - int op; - union { - struct { - int pid; - } fork, exec; - struct { - int (*proc)(void *); - void *arg; - } thread; - struct { - void (*proc)(void *); - void *arg; - } cb; - } u; + struct { + int (*proc)(void *); + void *arg; + } thread; } request; }; @@ -51,7 +41,7 @@ struct thread_struct { .fault_addr = NULL, \ .prev_sched = NULL, \ .arch = INIT_ARCH_THREAD, \ - .request = { 0 } \ + .request = { } \ } /* diff --git a/arch/um/include/asm/sysrq.h b/arch/um/include/asm/sysrq.h deleted file mode 100644 index 8fc8c65cd357..000000000000 --- a/arch/um/include/asm/sysrq.h +++ /dev/null @@ -1,8 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __UM_SYSRQ_H -#define __UM_SYSRQ_H - -struct task_struct; -extern void show_trace(struct task_struct* task, unsigned long *stack); - -#endif diff --git a/arch/um/include/asm/uaccess.h b/arch/um/include/asm/uaccess.h index 7d9d60e41e4e..1d4b6bbc1b65 100644 --- a/arch/um/include/asm/uaccess.h +++ b/arch/um/include/asm/uaccess.h @@ -8,7 +8,7 @@ #define __UM_UACCESS_H #include <asm/elf.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define __under_task_size(addr, size) \ (((unsigned long) (addr) < TASK_SIZE) && \ diff --git a/arch/um/include/shared/skas/mm_id.h b/arch/um/include/shared/skas/mm_id.h index 1e76ba40feba..140388c282f6 100644 --- a/arch/um/include/shared/skas/mm_id.h +++ b/arch/um/include/shared/skas/mm_id.h @@ -7,10 +7,7 @@ #define __MM_ID_H struct mm_id { - union { - int mm_fd; - int pid; - } u; + int pid; unsigned long stack; int syscall_data_len; }; diff --git a/arch/um/include/shared/skas/skas.h b/arch/um/include/shared/skas/skas.h index ebaa116de30b..85c50122ab98 100644 --- a/arch/um/include/shared/skas/skas.h +++ b/arch/um/include/shared/skas/skas.h @@ -10,10 +10,8 @@ extern int userspace_pid[]; -extern int user_thread(unsigned long stack, int flags); extern void new_thread_handler(void); extern void handle_syscall(struct uml_pt_regs *regs); -extern long execute_syscall_skas(void *r); extern unsigned long current_stub_stack(void); extern struct mm_id *current_mm_id(void); extern void current_mm_sync(void); diff --git a/arch/um/kernel/exec.c b/arch/um/kernel/exec.c index 2c15bb2c104c..cb8b5cd9285c 100644 --- a/arch/um/kernel/exec.c +++ b/arch/um/kernel/exec.c @@ -35,8 +35,5 @@ void start_thread(struct pt_regs *regs, unsigned long eip, unsigned long esp) PT_REGS_IP(regs) = eip; PT_REGS_SP(regs) = esp; clear_thread_flag(TIF_SINGLESTEP); -#ifdef SUBARCH_EXECVE1 - SUBARCH_EXECVE1(regs->regs); -#endif } EXPORT_SYMBOL(start_thread); diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c index f36b63f53bab..be2856af6d4c 100644 --- a/arch/um/kernel/process.c +++ b/arch/um/kernel/process.c @@ -109,8 +109,8 @@ void new_thread_handler(void) schedule_tail(current->thread.prev_sched); current->thread.prev_sched = NULL; - fn = current->thread.request.u.thread.proc; - arg = current->thread.request.u.thread.arg; + fn = current->thread.request.thread.proc; + arg = current->thread.request.thread.arg; /* * callback returns only if the kernel thread execs a process @@ -158,8 +158,8 @@ int copy_thread(struct task_struct * p, const struct kernel_clone_args *args) arch_copy_thread(¤t->thread.arch, &p->thread.arch); } else { get_safe_registers(p->thread.regs.regs.gp, p->thread.regs.regs.fp); - p->thread.request.u.thread.proc = args->fn; - p->thread.request.u.thread.arg = args->fn_arg; + p->thread.request.thread.proc = args->fn; + p->thread.request.thread.arg = args->fn_arg; handler = new_thread_handler; } diff --git a/arch/um/kernel/reboot.c b/arch/um/kernel/reboot.c index 3736bca626ba..680bce4bd8fa 100644 --- a/arch/um/kernel/reboot.c +++ b/arch/um/kernel/reboot.c @@ -29,7 +29,7 @@ static void kill_off_processes(void) t = find_lock_task_mm(p); if (!t) continue; - pid = t->mm->context.id.u.pid; + pid = t->mm->context.id.pid; task_unlock(t); os_kill_ptraced_process(pid, 1); } diff --git a/arch/um/kernel/skas/mmu.c b/arch/um/kernel/skas/mmu.c index 47f98d87ea3c..886ed5e65674 100644 --- a/arch/um/kernel/skas/mmu.c +++ b/arch/um/kernel/skas/mmu.c @@ -32,11 +32,11 @@ int init_new_context(struct task_struct *task, struct mm_struct *mm) new_id->stack = stack; block_signals_trace(); - new_id->u.pid = start_userspace(stack); + new_id->pid = start_userspace(stack); unblock_signals_trace(); - if (new_id->u.pid < 0) { - ret = new_id->u.pid; + if (new_id->pid < 0) { + ret = new_id->pid; goto out_free; } @@ -83,12 +83,12 @@ void destroy_context(struct mm_struct *mm) * whole UML suddenly dying. Also, cover negative and * 1 cases, since they shouldn't happen either. */ - if (mmu->id.u.pid < 2) { + if (mmu->id.pid < 2) { printk(KERN_ERR "corrupt mm_context - pid = %d\n", - mmu->id.u.pid); + mmu->id.pid); return; } - os_kill_ptraced_process(mmu->id.u.pid, 1); + os_kill_ptraced_process(mmu->id.pid, 1); free_pages(mmu->id.stack, ilog2(STUB_DATA_PAGES)); } diff --git a/arch/um/kernel/skas/process.c b/arch/um/kernel/skas/process.c index 5f9c1c5f36e2..68657988c8d1 100644 --- a/arch/um/kernel/skas/process.c +++ b/arch/um/kernel/skas/process.c @@ -39,8 +39,8 @@ int __init start_uml(void) init_new_thread_signals(); - init_task.thread.request.u.thread.proc = start_kernel_proc; - init_task.thread.request.u.thread.arg = NULL; + init_task.thread.request.thread.proc = start_kernel_proc; + init_task.thread.request.thread.arg = NULL; return start_idle_thread(task_stack_page(&init_task), &init_task.thread.switch_buf); } diff --git a/arch/um/kernel/skas/syscall.c b/arch/um/kernel/skas/syscall.c index 9ee19e566da3..b09e85279d2b 100644 --- a/arch/um/kernel/skas/syscall.c +++ b/arch/um/kernel/skas/syscall.c @@ -12,23 +12,13 @@ #include <sysdep/syscalls.h> #include <linux/time-internal.h> #include <asm/unistd.h> +#include <asm/delay.h> void handle_syscall(struct uml_pt_regs *r) { struct pt_regs *regs = container_of(r, struct pt_regs, regs); int syscall; - /* - * If we have infinite CPU resources, then make every syscall also a - * preemption point, since we don't have any other preemption in this - * case, and kernel threads would basically never run until userspace - * went to sleep, even if said userspace interacts with the kernel in - * various ways. - */ - if (time_travel_mode == TT_MODE_INFCPU || - time_travel_mode == TT_MODE_EXTERNAL) - schedule(); - /* Initialize the syscall number and default return value. */ UPT_SYSCALL_NR(r) = PT_SYSCALL_NR(r->gp); PT_REGS_SET_SYSCALL_RETURN(regs, -ENOSYS); @@ -41,9 +31,25 @@ void handle_syscall(struct uml_pt_regs *r) goto out; syscall = UPT_SYSCALL_NR(r); - if (syscall >= 0 && syscall < __NR_syscalls) - PT_REGS_SET_SYSCALL_RETURN(regs, - EXECUTE_SYSCALL(syscall, regs)); + if (syscall >= 0 && syscall < __NR_syscalls) { + unsigned long ret = EXECUTE_SYSCALL(syscall, regs); + + PT_REGS_SET_SYSCALL_RETURN(regs, ret); + + /* + * An error value here can be some form of -ERESTARTSYS + * and then we'd just loop. Make any error syscalls take + * some time, so that it won't just loop if something is + * not ready, and hopefully other things will make some + * progress. + */ + if (IS_ERR_VALUE(ret) && + (time_travel_mode == TT_MODE_INFCPU || + time_travel_mode == TT_MODE_EXTERNAL)) { + um_udelay(1); + schedule(); + } + } out: syscall_trace_leave(regs); diff --git a/arch/um/kernel/sysrq.c b/arch/um/kernel/sysrq.c index 746715379f12..4bb8622dc512 100644 --- a/arch/um/kernel/sysrq.c +++ b/arch/um/kernel/sysrq.c @@ -11,7 +11,6 @@ #include <linux/sched/debug.h> #include <linux/sched/task_stack.h> -#include <asm/sysrq.h> #include <asm/stacktrace.h> #include <os.h> diff --git a/arch/um/kernel/time.c b/arch/um/kernel/time.c index 47b9f5e63566..29b27b90581f 100644 --- a/arch/um/kernel/time.c +++ b/arch/um/kernel/time.c @@ -839,7 +839,7 @@ static irqreturn_t um_timer(int irq, void *dev) if (get_current()->mm != NULL) { /* userspace - relay signal, results in correct userspace timers */ - os_alarm_process(get_current()->mm->context.id.u.pid); + os_alarm_process(get_current()->mm->context.id.pid); } (*timer_clockevent.event_handler)(&timer_clockevent); diff --git a/arch/um/kernel/tlb.c b/arch/um/kernel/tlb.c index 44c6fc697f3a..548af31d4111 100644 --- a/arch/um/kernel/tlb.c +++ b/arch/um/kernel/tlb.c @@ -82,16 +82,12 @@ static inline int update_pte_range(pmd_t *pmd, unsigned long addr, (x ? UM_PROT_EXEC : 0)); if (pte_newpage(*pte)) { if (pte_present(*pte)) { - if (pte_newpage(*pte)) { - __u64 offset; - unsigned long phys = - pte_val(*pte) & PAGE_MASK; - int fd = phys_mapping(phys, &offset); - - ret = ops->mmap(ops->mm_idp, addr, - PAGE_SIZE, prot, fd, - offset); - } + __u64 offset; + unsigned long phys = pte_val(*pte) & PAGE_MASK; + int fd = phys_mapping(phys, &offset); + + ret = ops->mmap(ops->mm_idp, addr, PAGE_SIZE, + prot, fd, offset); } else ret = ops->unmap(ops->mm_idp, addr, PAGE_SIZE); } else if (pte_newprot(*pte)) diff --git a/arch/um/os-Linux/file.c b/arch/um/os-Linux/file.c index 5adf8f630049..f1d03cf3957f 100644 --- a/arch/um/os-Linux/file.c +++ b/arch/um/os-Linux/file.c @@ -528,7 +528,8 @@ int os_shutdown_socket(int fd, int r, int w) ssize_t os_rcv_fd_msg(int fd, int *fds, unsigned int n_fds, void *data, size_t data_len) { - char buf[CMSG_SPACE(sizeof(*fds) * n_fds)]; +#define MAX_RCV_FDS 2 + char buf[CMSG_SPACE(sizeof(*fds) * MAX_RCV_FDS)]; struct cmsghdr *cmsg; struct iovec iov = { .iov_base = data, @@ -538,10 +539,13 @@ ssize_t os_rcv_fd_msg(int fd, int *fds, unsigned int n_fds, .msg_iov = &iov, .msg_iovlen = 1, .msg_control = buf, - .msg_controllen = sizeof(buf), + .msg_controllen = CMSG_SPACE(sizeof(*fds) * n_fds), }; int n; + if (n_fds > MAX_RCV_FDS) + return -EINVAL; + n = recvmsg(fd, &msg, 0); if (n < 0) return -errno; diff --git a/arch/um/os-Linux/skas/mem.c b/arch/um/os-Linux/skas/mem.c index c55430775efd..9a13ac23c606 100644 --- a/arch/um/os-Linux/skas/mem.c +++ b/arch/um/os-Linux/skas/mem.c @@ -78,7 +78,7 @@ static inline long do_syscall_stub(struct mm_id *mm_idp) { struct stub_data *proc_data = (void *)mm_idp->stack; int n, i; - int err, pid = mm_idp->u.pid; + int err, pid = mm_idp->pid; n = ptrace_setregs(pid, syscall_regs); if (n < 0) { diff --git a/arch/um/os-Linux/skas/process.c b/arch/um/os-Linux/skas/process.c index f7088345b3fc..b6f656bcffb1 100644 --- a/arch/um/os-Linux/skas/process.c +++ b/arch/um/os-Linux/skas/process.c @@ -588,5 +588,5 @@ void reboot_skas(void) void __switch_mm(struct mm_id *mm_idp) { - userspace_pid[0] = mm_idp->u.pid; + userspace_pid[0] = mm_idp->pid; } diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c index da8b66dce0da..327c45c5013f 100644 --- a/arch/x86/coco/tdx/tdx.c +++ b/arch/x86/coco/tdx/tdx.c @@ -16,6 +16,7 @@ #include <asm/insn-eval.h> #include <asm/pgtable.h> #include <asm/set_memory.h> +#include <asm/traps.h> /* MMIO direction */ #define EPT_READ 0 @@ -433,6 +434,11 @@ static int handle_mmio(struct pt_regs *regs, struct ve_info *ve) return -EINVAL; } + if (!fault_in_kernel_space(ve->gla)) { + WARN_ONCE(1, "Access to userspace address is not supported"); + return -EINVAL; + } + /* * Reject EPT violation #VEs that split pages. * diff --git a/arch/x86/crypto/camellia_glue.c b/arch/x86/crypto/camellia_glue.c index d45e9c0c42ac..f110708c8038 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 <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/crypto.h> #include <linux/init.h> #include <linux/module.h> diff --git a/arch/x86/crypto/ghash-clmulni-intel_glue.c b/arch/x86/crypto/ghash-clmulni-intel_glue.c index 700ecaee9a08..41bc02e48916 100644 --- a/arch/x86/crypto/ghash-clmulni-intel_glue.c +++ b/arch/x86/crypto/ghash-clmulni-intel_glue.c @@ -19,7 +19,7 @@ #include <crypto/internal/simd.h> #include <asm/cpu_device_id.h> #include <asm/simd.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define GHASH_BLOCK_SIZE 16 #define GHASH_DIGEST_SIZE 16 diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h index 8db2ec4d6cda..1f650b4dde50 100644 --- a/arch/x86/include/asm/atomic64_32.h +++ b/arch/x86/include/asm/atomic64_32.h @@ -163,20 +163,18 @@ static __always_inline s64 arch_atomic64_dec_return(atomic64_t *v) } #define arch_atomic64_dec_return arch_atomic64_dec_return -static __always_inline s64 arch_atomic64_add(s64 i, atomic64_t *v) +static __always_inline void arch_atomic64_add(s64 i, atomic64_t *v) { __alternative_atomic64(add, add_return, ASM_OUTPUT2("+A" (i), "+c" (v)), ASM_NO_INPUT_CLOBBER("memory")); - return i; } -static __always_inline s64 arch_atomic64_sub(s64 i, atomic64_t *v) +static __always_inline void arch_atomic64_sub(s64 i, atomic64_t *v) { __alternative_atomic64(sub, sub_return, ASM_OUTPUT2("+A" (i), "+c" (v)), ASM_NO_INPUT_CLOBBER("memory")); - return i; } static __always_inline void arch_atomic64_inc(atomic64_t *v) diff --git a/arch/x86/include/asm/cpuid.h b/arch/x86/include/asm/cpuid.h index 80cc6386d7b1..ca4243318aad 100644 --- a/arch/x86/include/asm/cpuid.h +++ b/arch/x86/include/asm/cpuid.h @@ -179,6 +179,7 @@ static __always_inline bool cpuid_function_is_indexed(u32 function) case 0x1d: case 0x1e: case 0x1f: + case 0x24: case 0x8000001d: return true; } diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h index 0152a81d9b4a..b4d719de2c84 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 <asm/ptrace.h> + #ifdef CONFIG_FUNCTION_TRACER #ifndef CC_USING_FENTRY # error Compiler does not support fentry? diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index 44949f972826..1a42f829667a 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -135,6 +135,8 @@ #define INTEL_LUNARLAKE_M IFM(6, 0xBD) +#define INTEL_PANTHERLAKE_L IFM(6, 0xCC) + /* "Small Core" Processors (Atom/E-Core) */ #define INTEL_ATOM_BONNELL IFM(6, 0x1C) /* Diamondville, Pineview */ @@ -178,4 +180,7 @@ #define INTEL_FAM5_QUARK_X1000 0x09 /* Quark X1000 SoC */ #define INTEL_QUARK_X1000 IFM(5, 0x09) /* Quark X1000 SoC */ +/* Family 19 */ +#define INTEL_PANTHERCOVE_X IFM(19, 0x01) /* Diamond Rapids */ + #endif /* _ASM_X86_INTEL_FAMILY_H */ diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h index 68ad4f923664..861d080ed4c6 100644 --- a/arch/x86/include/asm/kvm-x86-ops.h +++ b/arch/x86/include/asm/kvm-x86-ops.h @@ -14,8 +14,8 @@ BUILD_BUG_ON(1) * be __static_call_return0. */ KVM_X86_OP(check_processor_compatibility) -KVM_X86_OP(hardware_enable) -KVM_X86_OP(hardware_disable) +KVM_X86_OP(enable_virtualization_cpu) +KVM_X86_OP(disable_virtualization_cpu) KVM_X86_OP(hardware_unsetup) KVM_X86_OP(has_emulated_msr) KVM_X86_OP(vcpu_after_set_cpuid) @@ -125,7 +125,7 @@ KVM_X86_OP_OPTIONAL(mem_enc_unregister_region) KVM_X86_OP_OPTIONAL(vm_copy_enc_context_from) KVM_X86_OP_OPTIONAL(vm_move_enc_context_from) KVM_X86_OP_OPTIONAL(guest_memory_reclaimed) -KVM_X86_OP(get_msr_feature) +KVM_X86_OP(get_feature_msr) KVM_X86_OP(check_emulate_instruction) KVM_X86_OP(apic_init_signal_blocked) KVM_X86_OP_OPTIONAL(enable_l2_tlb_flush) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 4a68cb3eba78..6d9f763a7bb9 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -36,6 +36,7 @@ #include <asm/kvm_page_track.h> #include <asm/kvm_vcpu_regs.h> #include <asm/hyperv-tlfs.h> +#include <asm/reboot.h> #define __KVM_HAVE_ARCH_VCPU_DEBUGFS @@ -211,6 +212,7 @@ enum exit_fastpath_completion { EXIT_FASTPATH_NONE, EXIT_FASTPATH_REENTER_GUEST, EXIT_FASTPATH_EXIT_HANDLED, + EXIT_FASTPATH_EXIT_USERSPACE, }; typedef enum exit_fastpath_completion fastpath_t; @@ -280,10 +282,6 @@ enum x86_intercept_stage; #define PFERR_PRIVATE_ACCESS BIT_ULL(49) #define PFERR_SYNTHETIC_MASK (PFERR_IMPLICIT_ACCESS | PFERR_PRIVATE_ACCESS) -#define PFERR_NESTED_GUEST_PAGE (PFERR_GUEST_PAGE_MASK | \ - PFERR_WRITE_MASK | \ - PFERR_PRESENT_MASK) - /* apic attention bits */ #define KVM_APIC_CHECK_VAPIC 0 /* @@ -1629,8 +1627,10 @@ struct kvm_x86_ops { int (*check_processor_compatibility)(void); - int (*hardware_enable)(void); - void (*hardware_disable)(void); + int (*enable_virtualization_cpu)(void); + void (*disable_virtualization_cpu)(void); + cpu_emergency_virt_cb *emergency_disable_virtualization_cpu; + void (*hardware_unsetup)(void); bool (*has_emulated_msr)(struct kvm *kvm, u32 index); void (*vcpu_after_set_cpuid)(struct kvm_vcpu *vcpu); @@ -1727,6 +1727,8 @@ struct kvm_x86_ops { void (*enable_nmi_window)(struct kvm_vcpu *vcpu); void (*enable_irq_window)(struct kvm_vcpu *vcpu); void (*update_cr8_intercept)(struct kvm_vcpu *vcpu, int tpr, int irr); + + const bool x2apic_icr_is_split; const unsigned long required_apicv_inhibits; bool allow_apicv_in_x2apic_without_x2apic_virtualization; void (*refresh_apicv_exec_ctrl)(struct kvm_vcpu *vcpu); @@ -1806,7 +1808,7 @@ struct kvm_x86_ops { int (*vm_move_enc_context_from)(struct kvm *kvm, unsigned int source_fd); void (*guest_memory_reclaimed)(struct kvm *kvm); - int (*get_msr_feature)(struct kvm_msr_entry *entry); + int (*get_feature_msr)(u32 msr, u64 *data); int (*check_emulate_instruction)(struct kvm_vcpu *vcpu, int emul_type, void *insn, int insn_len); @@ -2060,6 +2062,8 @@ void kvm_prepare_emulation_failure_exit(struct kvm_vcpu *vcpu); void kvm_enable_efer_bits(u64); bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer); +int kvm_get_msr_with_filter(struct kvm_vcpu *vcpu, u32 index, u64 *data); +int kvm_set_msr_with_filter(struct kvm_vcpu *vcpu, u32 index, u64 data); int __kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data, bool host_initiated); int kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data); int kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data); @@ -2136,7 +2140,15 @@ int kvm_get_nr_pending_nmis(struct kvm_vcpu *vcpu); void kvm_update_dr7(struct kvm_vcpu *vcpu); -int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn); +bool __kvm_mmu_unprotect_gfn_and_retry(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, + bool always_retry); + +static inline bool kvm_mmu_unprotect_gfn_and_retry(struct kvm_vcpu *vcpu, + gpa_t cr2_or_gpa) +{ + return __kvm_mmu_unprotect_gfn_and_retry(vcpu, cr2_or_gpa, false); +} + void kvm_mmu_free_roots(struct kvm *kvm, struct kvm_mmu *mmu, ulong roots_to_free); void kvm_mmu_free_guest_mode_roots(struct kvm *kvm, struct kvm_mmu *mmu); @@ -2254,6 +2266,7 @@ int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v); int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu); int kvm_cpu_has_extint(struct kvm_vcpu *v); int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu); +int kvm_cpu_get_extint(struct kvm_vcpu *v); int kvm_cpu_get_interrupt(struct kvm_vcpu *v); void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event); @@ -2345,7 +2358,8 @@ int memslot_rmap_alloc(struct kvm_memory_slot *slot, unsigned long npages); KVM_X86_QUIRK_OUT_7E_INC_RIP | \ KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT | \ KVM_X86_QUIRK_FIX_HYPERCALL_INSN | \ - KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS) + KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS | \ + KVM_X86_QUIRK_SLOT_ZAP_ALL) /* * KVM previously used a u32 field in kvm_run to indicate the hypercall was diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index a7c06a46fb76..3ae84c3b8e6d 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -36,6 +36,20 @@ #define EFER_FFXSR (1<<_EFER_FFXSR) #define EFER_AUTOIBRS (1<<_EFER_AUTOIBRS) +/* + * Architectural memory types that are common to MTRRs, PAT, VMX MSRs, etc. + * Most MSRs support/allow only a subset of memory types, but the values + * themselves are common across all relevant MSRs. + */ +#define X86_MEMTYPE_UC 0ull /* Uncacheable, a.k.a. Strong Uncacheable */ +#define X86_MEMTYPE_WC 1ull /* Write Combining */ +/* RESERVED 2 */ +/* RESERVED 3 */ +#define X86_MEMTYPE_WT 4ull /* Write Through */ +#define X86_MEMTYPE_WP 5ull /* Write Protected */ +#define X86_MEMTYPE_WB 6ull /* Write Back */ +#define X86_MEMTYPE_UC_MINUS 7ull /* Weak Uncacheabled (PAT only) */ + /* FRED MSRs */ #define MSR_IA32_FRED_RSP0 0x1cc /* Level 0 stack pointer */ #define MSR_IA32_FRED_RSP1 0x1cd /* Level 1 stack pointer */ @@ -365,6 +379,12 @@ #define MSR_IA32_CR_PAT 0x00000277 +#define PAT_VALUE(p0, p1, p2, p3, p4, p5, p6, p7) \ + ((X86_MEMTYPE_ ## p0) | (X86_MEMTYPE_ ## p1 << 8) | \ + (X86_MEMTYPE_ ## p2 << 16) | (X86_MEMTYPE_ ## p3 << 24) | \ + (X86_MEMTYPE_ ## p4 << 32) | (X86_MEMTYPE_ ## p5 << 40) | \ + (X86_MEMTYPE_ ## p6 << 48) | (X86_MEMTYPE_ ## p7 << 56)) + #define MSR_IA32_DEBUGCTLMSR 0x000001d9 #define MSR_IA32_LASTBRANCHFROMIP 0x000001db #define MSR_IA32_LASTBRANCHTOIP 0x000001dc @@ -1159,15 +1179,6 @@ #define MSR_IA32_VMX_VMFUNC 0x00000491 #define MSR_IA32_VMX_PROCBASED_CTLS3 0x00000492 -/* VMX_BASIC bits and bitmasks */ -#define VMX_BASIC_VMCS_SIZE_SHIFT 32 -#define VMX_BASIC_TRUE_CTLS (1ULL << 55) -#define VMX_BASIC_64 0x0001000000000000LLU -#define VMX_BASIC_MEM_TYPE_SHIFT 50 -#define VMX_BASIC_MEM_TYPE_MASK 0x003c000000000000LLU -#define VMX_BASIC_MEM_TYPE_WB 6LLU -#define VMX_BASIC_INOUT 0x0040000000000000LLU - /* Resctrl MSRs: */ /* - Intel: */ #define MSR_IA32_L3_QOS_CFG 0xc81 @@ -1185,11 +1196,6 @@ #define MSR_IA32_SMBA_BW_BASE 0xc0000280 #define MSR_IA32_EVT_CFG_BASE 0xc0000400 -/* MSR_IA32_VMX_MISC bits */ -#define MSR_IA32_VMX_MISC_INTEL_PT (1ULL << 14) -#define MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS (1ULL << 29) -#define MSR_IA32_VMX_MISC_PREEMPTION_TIMER_SCALE 0x1F - /* AMD-V MSRs */ #define MSR_VM_CR 0xc0010114 #define MSR_VM_IGNNE 0xc0010115 diff --git a/arch/x86/include/asm/reboot.h b/arch/x86/include/asm/reboot.h index 6536873f8fc0..ecd58ea9a837 100644 --- a/arch/x86/include/asm/reboot.h +++ b/arch/x86/include/asm/reboot.h @@ -25,14 +25,16 @@ void __noreturn machine_real_restart(unsigned int type); #define MRR_BIOS 0 #define MRR_APM 1 -#if IS_ENABLED(CONFIG_KVM_INTEL) || IS_ENABLED(CONFIG_KVM_AMD) typedef void (cpu_emergency_virt_cb)(void); +#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); #else +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/include/asm/svm.h b/arch/x86/include/asm/svm.h index f0dea3750ca9..2b59b9951c90 100644 --- a/arch/x86/include/asm/svm.h +++ b/arch/x86/include/asm/svm.h @@ -516,6 +516,20 @@ struct ghcb { u32 ghcb_usage; } __packed; +struct vmcb { + struct vmcb_control_area control; + union { + struct vmcb_save_area save; + + /* + * For SEV-ES VMs, the save area in the VMCB is used only to + * save/load host state. Guest state resides in a separate + * page, the aptly named VM Save Area (VMSA), that is encrypted + * with the guest's private key. + */ + struct sev_es_save_area host_sev_es_save; + }; +} __packed; #define EXPECTED_VMCB_SAVE_AREA_SIZE 744 #define EXPECTED_GHCB_SAVE_AREA_SIZE 1032 @@ -532,6 +546,7 @@ static inline void __unused_size_checks(void) BUILD_BUG_ON(sizeof(struct ghcb_save_area) != EXPECTED_GHCB_SAVE_AREA_SIZE); BUILD_BUG_ON(sizeof(struct sev_es_save_area) != EXPECTED_SEV_ES_SAVE_AREA_SIZE); BUILD_BUG_ON(sizeof(struct vmcb_control_area) != EXPECTED_VMCB_CONTROL_AREA_SIZE); + BUILD_BUG_ON(offsetof(struct vmcb, save) != EXPECTED_VMCB_CONTROL_AREA_SIZE); BUILD_BUG_ON(sizeof(struct ghcb) != EXPECTED_GHCB_SIZE); /* Check offsets of reserved fields */ @@ -568,11 +583,6 @@ static inline void __unused_size_checks(void) BUILD_BUG_RESERVED_OFFSET(ghcb, 0xff0); } -struct vmcb { - struct vmcb_control_area control; - struct vmcb_save_area save; -} __packed; - #define SVM_CPUID_FUNC 0x8000000a #define SVM_SELECTOR_S_SHIFT 4 diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index d77a31039f24..f7fd4369b821 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -122,19 +122,17 @@ #define VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR 0x000011ff -#define VMX_MISC_PREEMPTION_TIMER_RATE_MASK 0x0000001f -#define VMX_MISC_SAVE_EFER_LMA 0x00000020 -#define VMX_MISC_ACTIVITY_HLT 0x00000040 -#define VMX_MISC_ACTIVITY_WAIT_SIPI 0x00000100 -#define VMX_MISC_ZERO_LEN_INS 0x40000000 -#define VMX_MISC_MSR_LIST_MULTIPLIER 512 - /* VMFUNC functions */ #define VMFUNC_CONTROL_BIT(x) BIT((VMX_FEATURE_##x & 0x1f) - 28) #define VMX_VMFUNC_EPTP_SWITCHING VMFUNC_CONTROL_BIT(EPTP_SWITCHING) #define VMFUNC_EPTP_ENTRIES 512 +#define VMX_BASIC_32BIT_PHYS_ADDR_ONLY BIT_ULL(48) +#define VMX_BASIC_DUAL_MONITOR_TREATMENT BIT_ULL(49) +#define VMX_BASIC_INOUT BIT_ULL(54) +#define VMX_BASIC_TRUE_CTLS BIT_ULL(55) + static inline u32 vmx_basic_vmcs_revision_id(u64 vmx_basic) { return vmx_basic & GENMASK_ULL(30, 0); @@ -145,9 +143,30 @@ static inline u32 vmx_basic_vmcs_size(u64 vmx_basic) return (vmx_basic & GENMASK_ULL(44, 32)) >> 32; } +static inline u32 vmx_basic_vmcs_mem_type(u64 vmx_basic) +{ + return (vmx_basic & GENMASK_ULL(53, 50)) >> 50; +} + +static inline u64 vmx_basic_encode_vmcs_info(u32 revision, u16 size, u8 memtype) +{ + return revision | ((u64)size << 32) | ((u64)memtype << 50); +} + +#define VMX_MISC_SAVE_EFER_LMA BIT_ULL(5) +#define VMX_MISC_ACTIVITY_HLT BIT_ULL(6) +#define VMX_MISC_ACTIVITY_SHUTDOWN BIT_ULL(7) +#define VMX_MISC_ACTIVITY_WAIT_SIPI BIT_ULL(8) +#define VMX_MISC_INTEL_PT BIT_ULL(14) +#define VMX_MISC_RDMSR_IN_SMM BIT_ULL(15) +#define VMX_MISC_VMXOFF_BLOCK_SMI BIT_ULL(28) +#define VMX_MISC_VMWRITE_SHADOW_RO_FIELDS BIT_ULL(29) +#define VMX_MISC_ZERO_LEN_INS BIT_ULL(30) +#define VMX_MISC_MSR_LIST_MULTIPLIER 512 + static inline int vmx_misc_preemption_timer_rate(u64 vmx_misc) { - return vmx_misc & VMX_MISC_PREEMPTION_TIMER_RATE_MASK; + return vmx_misc & GENMASK_ULL(4, 0); } static inline int vmx_misc_cr3_count(u64 vmx_misc) @@ -508,9 +527,10 @@ enum vmcs_field { #define VMX_EPTP_PWL_4 0x18ull #define VMX_EPTP_PWL_5 0x20ull #define VMX_EPTP_AD_ENABLE_BIT (1ull << 6) +/* The EPTP memtype is encoded in bits 2:0, i.e. doesn't need to be shifted. */ #define VMX_EPTP_MT_MASK 0x7ull -#define VMX_EPTP_MT_WB 0x6ull -#define VMX_EPTP_MT_UC 0x0ull +#define VMX_EPTP_MT_WB X86_MEMTYPE_WB +#define VMX_EPTP_MT_UC X86_MEMTYPE_UC #define VMX_EPT_READABLE_MASK 0x1ull #define VMX_EPT_WRITABLE_MASK 0x2ull #define VMX_EPT_EXECUTABLE_MASK 0x4ull diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index bf57a824f722..a8debbf2f702 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -439,6 +439,7 @@ struct kvm_sync_regs { #define KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT (1 << 4) #define KVM_X86_QUIRK_FIX_HYPERCALL_INSN (1 << 5) #define KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS (1 << 6) +#define KVM_X86_QUIRK_SLOT_ZAP_ALL (1 << 7) #define KVM_STATE_NESTED_FORMAT_VMX 0 #define KVM_STATE_NESTED_FORMAT_SVM 1 diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.c b/arch/x86/kernel/cpu/mtrr/mtrr.c index 2a2fc14955cd..989d368be04f 100644 --- a/arch/x86/kernel/cpu/mtrr/mtrr.c +++ b/arch/x86/kernel/cpu/mtrr/mtrr.c @@ -55,6 +55,12 @@ #include "mtrr.h" +static_assert(X86_MEMTYPE_UC == MTRR_TYPE_UNCACHABLE); +static_assert(X86_MEMTYPE_WC == MTRR_TYPE_WRCOMB); +static_assert(X86_MEMTYPE_WT == MTRR_TYPE_WRTHROUGH); +static_assert(X86_MEMTYPE_WP == MTRR_TYPE_WRPROT); +static_assert(X86_MEMTYPE_WB == MTRR_TYPE_WRBACK); + /* arch_phys_wc_add returns an MTRR register index plus this offset. */ #define MTRR_TO_PHYS_WC_OFFSET 1000 diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 0e0a4cf6b5eb..615922838c51 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 730c2f34d347..f09f13c01c6b 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 5494669a055a..f9dddb8cb466 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/cpuid.c b/arch/x86/kvm/cpuid.c index 2617be544480..41786b834b16 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -705,7 +705,7 @@ void kvm_set_cpu_caps(void) kvm_cpu_cap_init_kvm_defined(CPUID_7_1_EDX, F(AVX_VNNI_INT8) | F(AVX_NE_CONVERT) | F(PREFETCHITI) | - F(AMX_COMPLEX) + F(AMX_COMPLEX) | F(AVX10) ); kvm_cpu_cap_init_kvm_defined(CPUID_7_2_EDX, @@ -721,6 +721,10 @@ void kvm_set_cpu_caps(void) SF(SGX1) | SF(SGX2) | SF(SGX_EDECCSSA) ); + kvm_cpu_cap_init_kvm_defined(CPUID_24_0_EBX, + F(AVX10_128) | F(AVX10_256) | F(AVX10_512) + ); + kvm_cpu_cap_mask(CPUID_8000_0001_ECX, F(LAHF_LM) | F(CMP_LEGACY) | 0 /*SVM*/ | 0 /* ExtApicSpace */ | F(CR8_LEGACY) | F(ABM) | F(SSE4A) | F(MISALIGNSSE) | @@ -949,7 +953,7 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) switch (function) { case 0: /* Limited to the highest leaf implemented in KVM. */ - entry->eax = min(entry->eax, 0x1fU); + entry->eax = min(entry->eax, 0x24U); break; case 1: cpuid_entry_override(entry, CPUID_1_EDX); @@ -1174,6 +1178,28 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) break; } break; + case 0x24: { + u8 avx10_version; + + if (!kvm_cpu_cap_has(X86_FEATURE_AVX10)) { + entry->eax = entry->ebx = entry->ecx = entry->edx = 0; + break; + } + + /* + * The AVX10 version is encoded in EBX[7:0]. Note, the version + * is guaranteed to be >=1 if AVX10 is supported. Note #2, the + * version needs to be captured before overriding EBX features! + */ + avx10_version = min_t(u8, entry->ebx & 0xff, 1); + cpuid_entry_override(entry, CPUID_24_0_EBX); + entry->ebx |= avx10_version; + + entry->eax = 0; + entry->ecx = 0; + entry->edx = 0; + break; + } case KVM_CPUID_SIGNATURE: { const u32 *sigptr = (const u32 *)KVM_SIGNATURE; entry->eax = KVM_CPUID_FEATURES; diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c index 3d7eb11d0e45..63f66c51975a 100644 --- a/arch/x86/kvm/irq.c +++ b/arch/x86/kvm/irq.c @@ -108,7 +108,7 @@ EXPORT_SYMBOL_GPL(kvm_cpu_has_interrupt); * Read pending interrupt(from non-APIC source) * vector and intack. */ -static int kvm_cpu_get_extint(struct kvm_vcpu *v) +int kvm_cpu_get_extint(struct kvm_vcpu *v) { if (!kvm_cpu_has_extint(v)) { WARN_ON(!lapic_in_kernel(v)); @@ -131,6 +131,7 @@ static int kvm_cpu_get_extint(struct kvm_vcpu *v) } else return kvm_pic_read_irq(v->kvm); /* PIC */ } +EXPORT_SYMBOL_GPL(kvm_cpu_get_extint); /* * Read pending interrupt vector and intack. @@ -141,9 +142,12 @@ int kvm_cpu_get_interrupt(struct kvm_vcpu *v) if (vector != -1) return vector; /* PIC */ - return kvm_get_apic_interrupt(v); /* APIC */ + vector = kvm_apic_has_interrupt(v); /* APIC */ + if (vector != -1) + kvm_apic_ack_interrupt(v, vector); + + return vector; } -EXPORT_SYMBOL_GPL(kvm_cpu_get_interrupt); void kvm_inject_pending_timer_irqs(struct kvm_vcpu *vcpu) { diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 5bb481aefcbc..2098dc689088 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1944,7 +1944,7 @@ static void start_sw_tscdeadline(struct kvm_lapic *apic) u64 ns = 0; ktime_t expire; struct kvm_vcpu *vcpu = apic->vcpu; - unsigned long this_tsc_khz = vcpu->arch.virtual_tsc_khz; + u32 this_tsc_khz = vcpu->arch.virtual_tsc_khz; unsigned long flags; ktime_t now; @@ -2453,6 +2453,43 @@ void kvm_lapic_set_eoi(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_lapic_set_eoi); +#define X2APIC_ICR_RESERVED_BITS (GENMASK_ULL(31, 20) | GENMASK_ULL(17, 16) | BIT(13)) + +int kvm_x2apic_icr_write(struct kvm_lapic *apic, u64 data) +{ + if (data & X2APIC_ICR_RESERVED_BITS) + return 1; + + /* + * The BUSY bit is reserved on both Intel and AMD in x2APIC mode, but + * only AMD requires it to be zero, Intel essentially just ignores the + * bit. And if IPI virtualization (Intel) or x2AVIC (AMD) is enabled, + * the CPU performs the reserved bits checks, i.e. the underlying CPU + * behavior will "win". Arbitrarily clear the BUSY bit, as there is no + * sane way to provide consistent behavior with respect to hardware. + */ + data &= ~APIC_ICR_BUSY; + + kvm_apic_send_ipi(apic, (u32)data, (u32)(data >> 32)); + if (kvm_x86_ops.x2apic_icr_is_split) { + kvm_lapic_set_reg(apic, APIC_ICR, data); + kvm_lapic_set_reg(apic, APIC_ICR2, data >> 32); + } else { + kvm_lapic_set_reg64(apic, APIC_ICR, data); + } + trace_kvm_apic_write(APIC_ICR, data); + return 0; +} + +static u64 kvm_x2apic_icr_read(struct kvm_lapic *apic) +{ + if (kvm_x86_ops.x2apic_icr_is_split) + return (u64)kvm_lapic_get_reg(apic, APIC_ICR) | + (u64)kvm_lapic_get_reg(apic, APIC_ICR2) << 32; + + return kvm_lapic_get_reg64(apic, APIC_ICR); +} + /* emulate APIC access in a trap manner */ void kvm_apic_write_nodecode(struct kvm_vcpu *vcpu, u32 offset) { @@ -2470,7 +2507,7 @@ void kvm_apic_write_nodecode(struct kvm_vcpu *vcpu, u32 offset) * maybe-unecessary write, and both are in the noise anyways. */ if (apic_x2apic_mode(apic) && offset == APIC_ICR) - kvm_x2apic_icr_write(apic, kvm_lapic_get_reg64(apic, APIC_ICR)); + WARN_ON_ONCE(kvm_x2apic_icr_write(apic, kvm_x2apic_icr_read(apic))); else kvm_lapic_reg_write(apic, offset, kvm_lapic_get_reg(apic, offset)); } @@ -2922,14 +2959,13 @@ void kvm_inject_apic_timer_irqs(struct kvm_vcpu *vcpu) } } -int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu) +void kvm_apic_ack_interrupt(struct kvm_vcpu *vcpu, int vector) { - int vector = kvm_apic_has_interrupt(vcpu); struct kvm_lapic *apic = vcpu->arch.apic; u32 ppr; - if (vector == -1) - return -1; + if (WARN_ON_ONCE(vector < 0 || !apic)) + return; /* * We get here even with APIC virtualization enabled, if doing @@ -2957,8 +2993,8 @@ int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu) __apic_update_ppr(apic, &ppr); } - return vector; } +EXPORT_SYMBOL_GPL(kvm_apic_ack_interrupt); static int kvm_apic_state_fixup(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s, bool set) @@ -2990,18 +3026,22 @@ static int kvm_apic_state_fixup(struct kvm_vcpu *vcpu, /* * In x2APIC mode, the LDR is fixed and based on the id. And - * ICR is internally a single 64-bit register, but needs to be - * split to ICR+ICR2 in userspace for backwards compatibility. + * if the ICR is _not_ split, ICR is internally a single 64-bit + * register, but needs to be split to ICR+ICR2 in userspace for + * backwards compatibility. */ - if (set) { + if (set) *ldr = kvm_apic_calc_x2apic_ldr(x2apic_id); - icr = __kvm_lapic_get_reg(s->regs, APIC_ICR) | - (u64)__kvm_lapic_get_reg(s->regs, APIC_ICR2) << 32; - __kvm_lapic_set_reg64(s->regs, APIC_ICR, icr); - } else { - icr = __kvm_lapic_get_reg64(s->regs, APIC_ICR); - __kvm_lapic_set_reg(s->regs, APIC_ICR2, icr >> 32); + if (!kvm_x86_ops.x2apic_icr_is_split) { + if (set) { + icr = __kvm_lapic_get_reg(s->regs, APIC_ICR) | + (u64)__kvm_lapic_get_reg(s->regs, APIC_ICR2) << 32; + __kvm_lapic_set_reg64(s->regs, APIC_ICR, icr); + } else { + icr = __kvm_lapic_get_reg64(s->regs, APIC_ICR); + __kvm_lapic_set_reg(s->regs, APIC_ICR2, icr >> 32); + } } } @@ -3194,22 +3234,12 @@ int kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr) return 0; } -int kvm_x2apic_icr_write(struct kvm_lapic *apic, u64 data) -{ - data &= ~APIC_ICR_BUSY; - - kvm_apic_send_ipi(apic, (u32)data, (u32)(data >> 32)); - kvm_lapic_set_reg64(apic, APIC_ICR, data); - trace_kvm_apic_write(APIC_ICR, data); - return 0; -} - static int kvm_lapic_msr_read(struct kvm_lapic *apic, u32 reg, u64 *data) { u32 low; if (reg == APIC_ICR) { - *data = kvm_lapic_get_reg64(apic, APIC_ICR); + *data = kvm_x2apic_icr_read(apic); return 0; } diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index 7ef8ae73e82d..1b8ef9856422 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -88,15 +88,14 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu); void kvm_free_lapic(struct kvm_vcpu *vcpu); int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu); +void kvm_apic_ack_interrupt(struct kvm_vcpu *vcpu, int vector); int kvm_apic_accept_pic_intr(struct kvm_vcpu *vcpu); -int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu); int kvm_apic_accept_events(struct kvm_vcpu *vcpu); void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event); u64 kvm_lapic_get_cr8(struct kvm_vcpu *vcpu); void kvm_lapic_set_tpr(struct kvm_vcpu *vcpu, unsigned long cr8); void kvm_lapic_set_eoi(struct kvm_vcpu *vcpu); void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value); -u64 kvm_lapic_get_base(struct kvm_vcpu *vcpu); void kvm_recalculate_apic_map(struct kvm *kvm); void kvm_apic_set_version(struct kvm_vcpu *vcpu); void kvm_apic_after_set_mcg_cap(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 4341e0e28571..9dc5dd43ae7f 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -223,8 +223,6 @@ static inline u8 permission_fault(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, bool kvm_mmu_may_ignore_guest_pat(void); -int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu); - int kvm_mmu_post_init_vm(struct kvm *kvm); void kvm_mmu_pre_destroy_vm(struct kvm *kvm); diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 7813d28b082f..a9a23e058555 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -614,32 +614,6 @@ static u64 mmu_spte_get_lockless(u64 *sptep) return __get_spte_lockless(sptep); } -/* Returns the Accessed status of the PTE and resets it at the same time. */ -static bool mmu_spte_age(u64 *sptep) -{ - u64 spte = mmu_spte_get_lockless(sptep); - - if (!is_accessed_spte(spte)) - return false; - - if (spte_ad_enabled(spte)) { - clear_bit((ffs(shadow_accessed_mask) - 1), - (unsigned long *)sptep); - } else { - /* - * Capture the dirty status of the page, so that it doesn't get - * lost when the SPTE is marked for access tracking. - */ - if (is_writable_pte(spte)) - kvm_set_pfn_dirty(spte_to_pfn(spte)); - - spte = mark_spte_for_access_track(spte); - mmu_spte_update_no_track(sptep, spte); - } - - return true; -} - static inline bool is_tdp_mmu_active(struct kvm_vcpu *vcpu) { return tdp_mmu_enabled && vcpu->arch.mmu->root_role.direct; @@ -938,6 +912,7 @@ static struct kvm_memory_slot *gfn_to_memslot_dirty_bitmap(struct kvm_vcpu *vcpu * in this rmap chain. Otherwise, (rmap_head->val & ~1) points to a struct * pte_list_desc containing more mappings. */ +#define KVM_RMAP_MANY BIT(0) /* * Returns the number of pointers in the rmap chain, not counting the new one. @@ -950,16 +925,16 @@ static int pte_list_add(struct kvm_mmu_memory_cache *cache, u64 *spte, if (!rmap_head->val) { rmap_head->val = (unsigned long)spte; - } else if (!(rmap_head->val & 1)) { + } else if (!(rmap_head->val & KVM_RMAP_MANY)) { desc = kvm_mmu_memory_cache_alloc(cache); desc->sptes[0] = (u64 *)rmap_head->val; desc->sptes[1] = spte; desc->spte_count = 2; desc->tail_count = 0; - rmap_head->val = (unsigned long)desc | 1; + rmap_head->val = (unsigned long)desc | KVM_RMAP_MANY; ++count; } else { - desc = (struct pte_list_desc *)(rmap_head->val & ~1ul); + desc = (struct pte_list_desc *)(rmap_head->val & ~KVM_RMAP_MANY); count = desc->tail_count + desc->spte_count; /* @@ -968,10 +943,10 @@ static int pte_list_add(struct kvm_mmu_memory_cache *cache, u64 *spte, */ if (desc->spte_count == PTE_LIST_EXT) { desc = kvm_mmu_memory_cache_alloc(cache); - desc->more = (struct pte_list_desc *)(rmap_head->val & ~1ul); + desc->more = (struct pte_list_desc *)(rmap_head->val & ~KVM_RMAP_MANY); desc->spte_count = 0; desc->tail_count = count; - rmap_head->val = (unsigned long)desc | 1; + rmap_head->val = (unsigned long)desc | KVM_RMAP_MANY; } desc->sptes[desc->spte_count++] = spte; } @@ -982,7 +957,7 @@ static void pte_list_desc_remove_entry(struct kvm *kvm, struct kvm_rmap_head *rmap_head, struct pte_list_desc *desc, int i) { - struct pte_list_desc *head_desc = (struct pte_list_desc *)(rmap_head->val & ~1ul); + struct pte_list_desc *head_desc = (struct pte_list_desc *)(rmap_head->val & ~KVM_RMAP_MANY); int j = head_desc->spte_count - 1; /* @@ -1011,7 +986,7 @@ static void pte_list_desc_remove_entry(struct kvm *kvm, if (!head_desc->more) rmap_head->val = 0; else - rmap_head->val = (unsigned long)head_desc->more | 1; + rmap_head->val = (unsigned long)head_desc->more | KVM_RMAP_MANY; mmu_free_pte_list_desc(head_desc); } @@ -1024,13 +999,13 @@ static void pte_list_remove(struct kvm *kvm, u64 *spte, if (KVM_BUG_ON_DATA_CORRUPTION(!rmap_head->val, kvm)) return; - if (!(rmap_head->val & 1)) { + if (!(rmap_head->val & KVM_RMAP_MANY)) { if (KVM_BUG_ON_DATA_CORRUPTION((u64 *)rmap_head->val != spte, kvm)) return; rmap_head->val = 0; } else { - desc = (struct pte_list_desc *)(rmap_head->val & ~1ul); + desc = (struct pte_list_desc *)(rmap_head->val & ~KVM_RMAP_MANY); while (desc) { for (i = 0; i < desc->spte_count; ++i) { if (desc->sptes[i] == spte) { @@ -1063,12 +1038,12 @@ static bool kvm_zap_all_rmap_sptes(struct kvm *kvm, if (!rmap_head->val) return false; - if (!(rmap_head->val & 1)) { + if (!(rmap_head->val & KVM_RMAP_MANY)) { mmu_spte_clear_track_bits(kvm, (u64 *)rmap_head->val); goto out; } - desc = (struct pte_list_desc *)(rmap_head->val & ~1ul); + desc = (struct pte_list_desc *)(rmap_head->val & ~KVM_RMAP_MANY); for (; desc; desc = next) { for (i = 0; i < desc->spte_count; i++) @@ -1088,10 +1063,10 @@ unsigned int pte_list_count(struct kvm_rmap_head *rmap_head) if (!rmap_head->val) return 0; - else if (!(rmap_head->val & 1)) + else if (!(rmap_head->val & KVM_RMAP_MANY)) return 1; - desc = (struct pte_list_desc *)(rmap_head->val & ~1ul); + desc = (struct pte_list_desc *)(rmap_head->val & ~KVM_RMAP_MANY); return desc->tail_count + desc->spte_count; } @@ -1153,13 +1128,13 @@ static u64 *rmap_get_first(struct kvm_rmap_head *rmap_head, if (!rmap_head->val) return NULL; - if (!(rmap_head->val & 1)) { + if (!(rmap_head->val & KVM_RMAP_MANY)) { iter->desc = NULL; sptep = (u64 *)rmap_head->val; goto out; } - iter->desc = (struct pte_list_desc *)(rmap_head->val & ~1ul); + iter->desc = (struct pte_list_desc *)(rmap_head->val & ~KVM_RMAP_MANY); iter->pos = 0; sptep = iter->desc->sptes[iter->pos]; out: @@ -1307,15 +1282,6 @@ static bool __rmap_clear_dirty(struct kvm *kvm, struct kvm_rmap_head *rmap_head, return flush; } -/** - * kvm_mmu_write_protect_pt_masked - write protect selected PT level pages - * @kvm: kvm instance - * @slot: slot to protect - * @gfn_offset: start of the BITS_PER_LONG pages we care about - * @mask: indicates which pages we should protect - * - * Used when we do not need to care about huge page mappings. - */ static void kvm_mmu_write_protect_pt_masked(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn_offset, unsigned long mask) @@ -1339,16 +1305,6 @@ static void kvm_mmu_write_protect_pt_masked(struct kvm *kvm, } } -/** - * kvm_mmu_clear_dirty_pt_masked - clear MMU D-bit for PT level pages, or write - * protect the page if the D-bit isn't supported. - * @kvm: kvm instance - * @slot: slot to clear D-bit - * @gfn_offset: start of the BITS_PER_LONG pages we care about - * @mask: indicates which pages we should clear D-bit - * - * Used for PML to re-log the dirty GPAs after userspace querying dirty_bitmap. - */ static void kvm_mmu_clear_dirty_pt_masked(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn_offset, unsigned long mask) @@ -1372,24 +1328,16 @@ static void kvm_mmu_clear_dirty_pt_masked(struct kvm *kvm, } } -/** - * kvm_arch_mmu_enable_log_dirty_pt_masked - enable dirty logging for selected - * PT level pages. - * - * It calls kvm_mmu_write_protect_pt_masked to write protect selected pages to - * enable dirty logging for them. - * - * We need to care about huge page mappings: e.g. during dirty logging we may - * have such mappings. - */ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn_offset, unsigned long mask) { /* - * Huge pages are NOT write protected when we start dirty logging in - * initially-all-set mode; must write protect them here so that they - * are split to 4K on the first write. + * If the slot was assumed to be "initially all dirty", write-protect + * huge pages to ensure they are split to 4KiB on the first write (KVM + * dirty logs at 4KiB granularity). If eager page splitting is enabled, + * immediately try to split huge pages, e.g. so that vCPUs don't get + * saddled with the cost of splitting. * * The gfn_offset is guaranteed to be aligned to 64, but the base_gfn * of memslot has no such restriction, so the range can cross two large @@ -1411,7 +1359,16 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, PG_LEVEL_2M); } - /* Now handle 4K PTEs. */ + /* + * (Re)Enable dirty logging for all 4KiB SPTEs that map the GFNs in + * mask. If PML is enabled and the GFN doesn't need to be write- + * protected for other reasons, e.g. shadow paging, clear the Dirty bit. + * Otherwise clear the Writable bit. + * + * Note that kvm_mmu_clear_dirty_pt_masked() is called whenever PML is + * enabled but it chooses between clearing the Dirty bit and Writeable + * bit based on the context. + */ if (kvm_x86_ops.cpu_dirty_log_size) kvm_mmu_clear_dirty_pt_masked(kvm, slot, gfn_offset, mask); else @@ -1453,16 +1410,10 @@ static bool kvm_vcpu_write_protect_gfn(struct kvm_vcpu *vcpu, u64 gfn) return kvm_mmu_slot_gfn_write_protect(vcpu->kvm, slot, gfn, PG_LEVEL_4K); } -static bool __kvm_zap_rmap(struct kvm *kvm, struct kvm_rmap_head *rmap_head, - const struct kvm_memory_slot *slot) -{ - return kvm_zap_all_rmap_sptes(kvm, rmap_head); -} - static bool kvm_zap_rmap(struct kvm *kvm, struct kvm_rmap_head *rmap_head, - struct kvm_memory_slot *slot, gfn_t gfn, int level) + const struct kvm_memory_slot *slot) { - return __kvm_zap_rmap(kvm, rmap_head, slot); + return kvm_zap_all_rmap_sptes(kvm, rmap_head); } struct slot_rmap_walk_iterator { @@ -1513,7 +1464,7 @@ static bool slot_rmap_walk_okay(struct slot_rmap_walk_iterator *iterator) static void slot_rmap_walk_next(struct slot_rmap_walk_iterator *iterator) { while (++iterator->rmap <= iterator->end_rmap) { - iterator->gfn += (1UL << KVM_HPAGE_GFN_SHIFT(iterator->level)); + iterator->gfn += KVM_PAGES_PER_HPAGE(iterator->level); if (iterator->rmap->val) return; @@ -1534,23 +1485,71 @@ static void slot_rmap_walk_next(struct slot_rmap_walk_iterator *iterator) slot_rmap_walk_okay(_iter_); \ slot_rmap_walk_next(_iter_)) -typedef bool (*rmap_handler_t)(struct kvm *kvm, struct kvm_rmap_head *rmap_head, - struct kvm_memory_slot *slot, gfn_t gfn, - int level); +/* The return value indicates if tlb flush on all vcpus is needed. */ +typedef bool (*slot_rmaps_handler) (struct kvm *kvm, + struct kvm_rmap_head *rmap_head, + const struct kvm_memory_slot *slot); -static __always_inline bool kvm_handle_gfn_range(struct kvm *kvm, - struct kvm_gfn_range *range, - rmap_handler_t handler) +static __always_inline bool __walk_slot_rmaps(struct kvm *kvm, + const struct kvm_memory_slot *slot, + slot_rmaps_handler fn, + int start_level, int end_level, + gfn_t start_gfn, gfn_t end_gfn, + bool can_yield, bool flush_on_yield, + bool flush) { struct slot_rmap_walk_iterator iterator; - bool ret = false; - for_each_slot_rmap_range(range->slot, PG_LEVEL_4K, KVM_MAX_HUGEPAGE_LEVEL, - range->start, range->end - 1, &iterator) - ret |= handler(kvm, iterator.rmap, range->slot, iterator.gfn, - iterator.level); + lockdep_assert_held_write(&kvm->mmu_lock); - return ret; + for_each_slot_rmap_range(slot, start_level, end_level, start_gfn, + end_gfn, &iterator) { + if (iterator.rmap) + flush |= fn(kvm, iterator.rmap, slot); + + if (!can_yield) + continue; + + if (need_resched() || rwlock_needbreak(&kvm->mmu_lock)) { + if (flush && flush_on_yield) { + kvm_flush_remote_tlbs_range(kvm, start_gfn, + iterator.gfn - start_gfn + 1); + flush = false; + } + cond_resched_rwlock_write(&kvm->mmu_lock); + } + } + + return flush; +} + +static __always_inline bool walk_slot_rmaps(struct kvm *kvm, + const struct kvm_memory_slot *slot, + slot_rmaps_handler fn, + int start_level, int end_level, + bool flush_on_yield) +{ + return __walk_slot_rmaps(kvm, slot, fn, start_level, end_level, + slot->base_gfn, slot->base_gfn + slot->npages - 1, + true, flush_on_yield, false); +} + +static __always_inline bool walk_slot_rmaps_4k(struct kvm *kvm, + const struct kvm_memory_slot *slot, + slot_rmaps_handler fn, + bool flush_on_yield) +{ + return walk_slot_rmaps(kvm, slot, fn, PG_LEVEL_4K, PG_LEVEL_4K, flush_on_yield); +} + +static bool __kvm_rmap_zap_gfn_range(struct kvm *kvm, + const struct kvm_memory_slot *slot, + gfn_t start, gfn_t end, bool can_yield, + bool flush) +{ + return __walk_slot_rmaps(kvm, slot, kvm_zap_rmap, + PG_LEVEL_4K, KVM_MAX_HUGEPAGE_LEVEL, + start, end - 1, can_yield, true, flush); } bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range) @@ -1558,7 +1557,9 @@ bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range) bool flush = false; if (kvm_memslots_have_rmaps(kvm)) - flush = kvm_handle_gfn_range(kvm, range, kvm_zap_rmap); + flush = __kvm_rmap_zap_gfn_range(kvm, range->slot, + range->start, range->end, + range->may_block, flush); if (tdp_mmu_enabled) flush = kvm_tdp_mmu_unmap_gfn_range(kvm, range, flush); @@ -1570,31 +1571,6 @@ bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range) return flush; } -static bool kvm_age_rmap(struct kvm *kvm, struct kvm_rmap_head *rmap_head, - struct kvm_memory_slot *slot, gfn_t gfn, int level) -{ - u64 *sptep; - struct rmap_iterator iter; - int young = 0; - - for_each_rmap_spte(rmap_head, &iter, sptep) - young |= mmu_spte_age(sptep); - - return young; -} - -static bool kvm_test_age_rmap(struct kvm *kvm, struct kvm_rmap_head *rmap_head, - struct kvm_memory_slot *slot, gfn_t gfn, int level) -{ - u64 *sptep; - struct rmap_iterator iter; - - for_each_rmap_spte(rmap_head, &iter, sptep) - if (is_accessed_spte(*sptep)) - return true; - return false; -} - #define RMAP_RECYCLE_THRESHOLD 1000 static void __rmap_add(struct kvm *kvm, @@ -1629,12 +1605,52 @@ static void rmap_add(struct kvm_vcpu *vcpu, const struct kvm_memory_slot *slot, __rmap_add(vcpu->kvm, cache, slot, spte, gfn, access); } +static bool kvm_rmap_age_gfn_range(struct kvm *kvm, + struct kvm_gfn_range *range, bool test_only) +{ + struct slot_rmap_walk_iterator iterator; + struct rmap_iterator iter; + bool young = false; + u64 *sptep; + + for_each_slot_rmap_range(range->slot, PG_LEVEL_4K, KVM_MAX_HUGEPAGE_LEVEL, + range->start, range->end - 1, &iterator) { + for_each_rmap_spte(iterator.rmap, &iter, sptep) { + u64 spte = *sptep; + + if (!is_accessed_spte(spte)) + continue; + + if (test_only) + return true; + + if (spte_ad_enabled(spte)) { + clear_bit((ffs(shadow_accessed_mask) - 1), + (unsigned long *)sptep); + } else { + /* + * Capture the dirty status of the page, so that + * it doesn't get lost when the SPTE is marked + * for access tracking. + */ + if (is_writable_pte(spte)) + kvm_set_pfn_dirty(spte_to_pfn(spte)); + + spte = mark_spte_for_access_track(spte); + mmu_spte_update_no_track(sptep, spte); + } + young = true; + } + } + return young; +} + bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) { bool young = false; if (kvm_memslots_have_rmaps(kvm)) - young = kvm_handle_gfn_range(kvm, range, kvm_age_rmap); + young = kvm_rmap_age_gfn_range(kvm, range, false); if (tdp_mmu_enabled) young |= kvm_tdp_mmu_age_gfn_range(kvm, range); @@ -1647,7 +1663,7 @@ bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) bool young = false; if (kvm_memslots_have_rmaps(kvm)) - young = kvm_handle_gfn_range(kvm, range, kvm_test_age_rmap); + young = kvm_rmap_age_gfn_range(kvm, range, true); if (tdp_mmu_enabled) young |= kvm_tdp_mmu_test_age_gfn(kvm, range); @@ -1868,10 +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) { @@ -2713,36 +2733,49 @@ void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned long goal_nr_mmu_pages) write_unlock(&kvm->mmu_lock); } -int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn) +bool __kvm_mmu_unprotect_gfn_and_retry(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, + bool always_retry) { - struct kvm_mmu_page *sp; + struct kvm *kvm = vcpu->kvm; LIST_HEAD(invalid_list); - int r; + struct kvm_mmu_page *sp; + gpa_t gpa = cr2_or_gpa; + bool r = false; + + /* + * Bail early if there aren't any write-protected shadow pages to avoid + * unnecessarily taking mmu_lock lock, e.g. if the gfn is write-tracked + * by a third party. Reading indirect_shadow_pages without holding + * mmu_lock is safe, as this is purely an optimization, i.e. a false + * positive is benign, and a false negative will simply result in KVM + * skipping the unprotect+retry path, which is also an optimization. + */ + if (!READ_ONCE(kvm->arch.indirect_shadow_pages)) + goto out; + + if (!vcpu->arch.mmu->root_role.direct) { + gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2_or_gpa, NULL); + if (gpa == INVALID_GPA) + goto out; + } - r = 0; write_lock(&kvm->mmu_lock); - for_each_gfn_valid_sp_with_gptes(kvm, sp, gfn) { - r = 1; + for_each_gfn_valid_sp_with_gptes(kvm, sp, gpa_to_gfn(gpa)) kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list); - } + + /* + * Snapshot the result before zapping, as zapping will remove all list + * entries, i.e. checking the list later would yield a false negative. + */ + r = !list_empty(&invalid_list); kvm_mmu_commit_zap_page(kvm, &invalid_list); write_unlock(&kvm->mmu_lock); - return r; -} - -static int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva) -{ - gpa_t gpa; - int r; - - if (vcpu->arch.mmu->root_role.direct) - return 0; - - gpa = kvm_mmu_gva_to_gpa_read(vcpu, gva, NULL); - - r = kvm_mmu_unprotect_page(vcpu->kvm, gpa >> PAGE_SHIFT); - +out: + if (r || always_retry) { + vcpu->arch.last_retry_eip = kvm_rip_read(vcpu); + vcpu->arch.last_retry_addr = cr2_or_gpa; + } return r; } @@ -2914,10 +2947,8 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot, trace_kvm_mmu_set_spte(level, gfn, sptep); } - if (wrprot) { - if (write_fault) - ret = RET_PF_EMULATE; - } + if (wrprot && write_fault) + ret = RET_PF_WRITE_PROTECTED; if (flush) kvm_flush_remote_tlbs_gfn(vcpu->kvm, gfn, level); @@ -4549,7 +4580,7 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault return RET_PF_RETRY; if (page_fault_handle_page_track(vcpu, fault)) - return RET_PF_EMULATE; + return RET_PF_WRITE_PROTECTED; r = fast_page_fault(vcpu, fault); if (r != RET_PF_INVALID) @@ -4618,8 +4649,6 @@ int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code, if (!flags) { trace_kvm_page_fault(vcpu, fault_address, error_code); - if (kvm_event_needs_reinjection(vcpu)) - kvm_mmu_unprotect_page_virt(vcpu, fault_address); r = kvm_mmu_page_fault(vcpu, fault_address, error_code, insn, insn_len); } else if (flags & KVM_PV_REASON_PAGE_NOT_PRESENT) { @@ -4642,7 +4671,7 @@ static int kvm_tdp_mmu_page_fault(struct kvm_vcpu *vcpu, int r; if (page_fault_handle_page_track(vcpu, fault)) - return RET_PF_EMULATE; + return RET_PF_WRITE_PROTECTED; r = fast_page_fault(vcpu, fault); if (r != RET_PF_INVALID) @@ -4719,6 +4748,7 @@ static int kvm_tdp_map_page(struct kvm_vcpu *vcpu, gpa_t gpa, u64 error_code, switch (r) { case RET_PF_FIXED: case RET_PF_SPURIOUS: + case RET_PF_WRITE_PROTECTED: return 0; case RET_PF_EMULATE: @@ -5963,6 +5993,106 @@ void kvm_mmu_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new, write_unlock(&vcpu->kvm->mmu_lock); } +static bool is_write_to_guest_page_table(u64 error_code) +{ + const u64 mask = PFERR_GUEST_PAGE_MASK | PFERR_WRITE_MASK | PFERR_PRESENT_MASK; + + return (error_code & mask) == mask; +} + +static int kvm_mmu_write_protect_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, + u64 error_code, int *emulation_type) +{ + bool direct = vcpu->arch.mmu->root_role.direct; + + /* + * Do not try to unprotect and retry if the vCPU re-faulted on the same + * RIP with the same address that was previously unprotected, as doing + * so will likely put the vCPU into an infinite. E.g. if the vCPU uses + * a non-page-table modifying instruction on the PDE that points to the + * instruction, then unprotecting the gfn will unmap the instruction's + * code, i.e. make it impossible for the instruction to ever complete. + */ + if (vcpu->arch.last_retry_eip == kvm_rip_read(vcpu) && + vcpu->arch.last_retry_addr == cr2_or_gpa) + return RET_PF_EMULATE; + + /* + * Reset the unprotect+retry values that guard against infinite loops. + * The values will be refreshed if KVM explicitly unprotects a gfn and + * retries, in all other cases it's safe to retry in the future even if + * the next page fault happens on the same RIP+address. + */ + vcpu->arch.last_retry_eip = 0; + vcpu->arch.last_retry_addr = 0; + + /* + * It should be impossible to reach this point with an MMIO cache hit, + * as RET_PF_WRITE_PROTECTED is returned if and only if there's a valid, + * writable memslot, and creating a memslot should invalidate the MMIO + * cache by way of changing the memslot generation. WARN and disallow + * retry if MMIO is detected, as retrying MMIO emulation is pointless + * and could put the vCPU into an infinite loop because the processor + * will keep faulting on the non-existent MMIO address. + */ + if (WARN_ON_ONCE(mmio_info_in_cache(vcpu, cr2_or_gpa, direct))) + return RET_PF_EMULATE; + + /* + * Before emulating the instruction, check to see if the access was due + * to a read-only violation while the CPU was walking non-nested NPT + * page tables, i.e. for a direct MMU, for _guest_ page tables in L1. + * If L1 is sharing (a subset of) its page tables with L2, e.g. by + * having nCR3 share lower level page tables with hCR3, then when KVM + * (L0) write-protects the nested NPTs, i.e. npt12 entries, KVM is also + * unknowingly write-protecting L1's guest page tables, which KVM isn't + * shadowing. + * + * Because the CPU (by default) walks NPT page tables using a write + * access (to ensure the CPU can do A/D updates), page walks in L1 can + * trigger write faults for the above case even when L1 isn't modifying + * PTEs. As a result, KVM will unnecessarily emulate (or at least, try + * to emulate) an excessive number of L1 instructions; because L1's MMU + * isn't shadowed by KVM, there is no need to write-protect L1's gPTEs + * and thus no need to emulate in order to guarantee forward progress. + * + * Try to unprotect the gfn, i.e. zap any shadow pages, so that L1 can + * proceed without triggering emulation. If one or more shadow pages + * was zapped, skip emulation and resume L1 to let it natively execute + * the instruction. If no shadow pages were zapped, then the write- + * fault is due to something else entirely, i.e. KVM needs to emulate, + * as resuming the guest will put it into an infinite loop. + * + * Note, this code also applies to Intel CPUs, even though it is *very* + * unlikely that an L1 will share its page tables (IA32/PAE/paging64 + * format) with L2's page tables (EPT format). + * + * For indirect MMUs, i.e. if KVM is shadowing the current MMU, try to + * unprotect the gfn and retry if an event is awaiting reinjection. If + * KVM emulates multiple instructions before completing event injection, + * the event could be delayed beyond what is architecturally allowed, + * e.g. KVM could inject an IRQ after the TPR has been raised. + */ + if (((direct && is_write_to_guest_page_table(error_code)) || + (!direct && kvm_event_needs_reinjection(vcpu))) && + kvm_mmu_unprotect_gfn_and_retry(vcpu, cr2_or_gpa)) + return RET_PF_RETRY; + + /* + * The gfn is write-protected, but if KVM detects its emulating an + * instruction that is unlikely to be used to modify page tables, or if + * emulation fails, KVM can try to unprotect the gfn and let the CPU + * re-execute the instruction that caused the page fault. Do not allow + * retrying an instruction from a nested guest as KVM is only explicitly + * shadowing L1's page tables, i.e. unprotecting something for L1 isn't + * going to magically fix whatever issue caused L2 to fail. + */ + if (!is_guest_mode(vcpu)) + *emulation_type |= EMULTYPE_ALLOW_RETRY_PF; + + return RET_PF_EMULATE; +} + int noinline kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code, void *insn, int insn_len) { @@ -6008,6 +6138,10 @@ int noinline kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 err if (r < 0) return r; + if (r == RET_PF_WRITE_PROTECTED) + r = kvm_mmu_write_protect_fault(vcpu, cr2_or_gpa, error_code, + &emulation_type); + if (r == RET_PF_FIXED) vcpu->stat.pf_fixed++; else if (r == RET_PF_EMULATE) @@ -6018,32 +6152,6 @@ int noinline kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 err if (r != RET_PF_EMULATE) return 1; - /* - * Before emulating the instruction, check if the error code - * was due to a RO violation while translating the guest page. - * This can occur when using nested virtualization with nested - * paging in both guests. If true, we simply unprotect the page - * and resume the guest. - */ - if (vcpu->arch.mmu->root_role.direct && - (error_code & PFERR_NESTED_GUEST_PAGE) == PFERR_NESTED_GUEST_PAGE) { - kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(cr2_or_gpa)); - return 1; - } - - /* - * vcpu->arch.mmu.page_fault returned RET_PF_EMULATE, but we can still - * optimistically try to just unprotect the page and let the processor - * re-execute the instruction that caused the page fault. Do not allow - * retrying MMIO emulation, as it's not only pointless but could also - * cause us to enter an infinite loop because the processor will keep - * faulting on the non-existent MMIO address. Retrying an instruction - * from a nested guest is also pointless and dangerous as we are only - * explicitly shadowing L1's page tables, i.e. unprotecting something - * for L1 isn't going to magically fix whatever issue cause L2 to fail. - */ - if (!mmio_info_in_cache(vcpu, cr2_or_gpa, direct) && !is_guest_mode(vcpu)) - emulation_type |= EMULTYPE_ALLOW_RETRY_PF; emulate: return x86_emulate_instruction(vcpu, cr2_or_gpa, emulation_type, insn, insn_len); @@ -6202,59 +6310,6 @@ void kvm_configure_mmu(bool enable_tdp, int tdp_forced_root_level, } EXPORT_SYMBOL_GPL(kvm_configure_mmu); -/* The return value indicates if tlb flush on all vcpus is needed. */ -typedef bool (*slot_rmaps_handler) (struct kvm *kvm, - struct kvm_rmap_head *rmap_head, - const struct kvm_memory_slot *slot); - -static __always_inline bool __walk_slot_rmaps(struct kvm *kvm, - const struct kvm_memory_slot *slot, - slot_rmaps_handler fn, - int start_level, int end_level, - gfn_t start_gfn, gfn_t end_gfn, - bool flush_on_yield, bool flush) -{ - struct slot_rmap_walk_iterator iterator; - - lockdep_assert_held_write(&kvm->mmu_lock); - - for_each_slot_rmap_range(slot, start_level, end_level, start_gfn, - end_gfn, &iterator) { - if (iterator.rmap) - flush |= fn(kvm, iterator.rmap, slot); - - if (need_resched() || rwlock_needbreak(&kvm->mmu_lock)) { - if (flush && flush_on_yield) { - kvm_flush_remote_tlbs_range(kvm, start_gfn, - iterator.gfn - start_gfn + 1); - flush = false; - } - cond_resched_rwlock_write(&kvm->mmu_lock); - } - } - - return flush; -} - -static __always_inline bool walk_slot_rmaps(struct kvm *kvm, - const struct kvm_memory_slot *slot, - slot_rmaps_handler fn, - int start_level, int end_level, - bool flush_on_yield) -{ - return __walk_slot_rmaps(kvm, slot, fn, start_level, end_level, - slot->base_gfn, slot->base_gfn + slot->npages - 1, - flush_on_yield, false); -} - -static __always_inline bool walk_slot_rmaps_4k(struct kvm *kvm, - const struct kvm_memory_slot *slot, - slot_rmaps_handler fn, - bool flush_on_yield) -{ - return walk_slot_rmaps(kvm, slot, fn, PG_LEVEL_4K, PG_LEVEL_4K, flush_on_yield); -} - static void free_mmu_pages(struct kvm_mmu *mmu) { if (!tdp_enabled && mmu->pae_root) @@ -6528,9 +6583,8 @@ static bool kvm_rmap_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_e if (WARN_ON_ONCE(start >= end)) continue; - flush = __walk_slot_rmaps(kvm, memslot, __kvm_zap_rmap, - PG_LEVEL_4K, KVM_MAX_HUGEPAGE_LEVEL, - start, end - 1, true, flush); + flush = __kvm_rmap_zap_gfn_range(kvm, memslot, start, + end, true, flush); } } @@ -6818,7 +6872,7 @@ static void kvm_shadow_mmu_try_split_huge_pages(struct kvm *kvm, */ for (level = KVM_MAX_HUGEPAGE_LEVEL; level > target_level; level--) __walk_slot_rmaps(kvm, slot, shadow_mmu_try_split_huge_pages, - level, level, start, end - 1, true, false); + level, level, start, end - 1, true, true, false); } /* Must be called with the mmu_lock held in write-mode. */ @@ -6997,10 +7051,70 @@ void kvm_arch_flush_shadow_all(struct kvm *kvm) kvm_mmu_zap_all(kvm); } +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, + .start = slot->base_gfn, + .end = slot->base_gfn + slot->npages, + .may_block = true, + }; + bool flush; + + write_lock(&kvm->mmu_lock); + flush = kvm_unmap_gfn_range(kvm, &range); + kvm_mmu_zap_memslot_pages_and_flush(kvm, slot, flush); + write_unlock(&kvm->mmu_lock); +} + +static inline bool kvm_memslot_flush_zap_all(struct kvm *kvm) +{ + return kvm->arch.vm_type == KVM_X86_DEFAULT_VM && + kvm_check_has_quirk(kvm, KVM_X86_QUIRK_SLOT_ZAP_ALL); +} + void kvm_arch_flush_shadow_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) { - kvm_mmu_zap_all_fast(kvm); + if (kvm_memslot_flush_zap_all(kvm)) + kvm_mmu_zap_all_fast(kvm); + else + kvm_mmu_zap_memslot(kvm, slot); } void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen) diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h index 1721d97743e9..c98827840e07 100644 --- a/arch/x86/kvm/mmu/mmu_internal.h +++ b/arch/x86/kvm/mmu/mmu_internal.h @@ -258,6 +258,8 @@ int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault); * RET_PF_CONTINUE: So far, so good, keep handling the page fault. * RET_PF_RETRY: let CPU fault again on the address. * RET_PF_EMULATE: mmio page fault, emulate the instruction directly. + * RET_PF_WRITE_PROTECTED: the gfn is write-protected, either unprotected the + * gfn and retry, or emulate the instruction directly. * RET_PF_INVALID: the spte is invalid, let the real page fault path update it. * RET_PF_FIXED: The faulting entry has been fixed. * RET_PF_SPURIOUS: The faulting entry was already fixed, e.g. by another vCPU. @@ -274,6 +276,7 @@ enum { RET_PF_CONTINUE = 0, RET_PF_RETRY, RET_PF_EMULATE, + RET_PF_WRITE_PROTECTED, RET_PF_INVALID, RET_PF_FIXED, RET_PF_SPURIOUS, @@ -349,8 +352,6 @@ int kvm_mmu_max_mapping_level(struct kvm *kvm, void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault); void disallowed_hugepage_adjust(struct kvm_page_fault *fault, u64 spte, int cur_level); -void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc); - void track_possible_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp); void untrack_possible_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp); diff --git a/arch/x86/kvm/mmu/mmutrace.h b/arch/x86/kvm/mmu/mmutrace.h index 195d98bc8de8..f35a830ce469 100644 --- a/arch/x86/kvm/mmu/mmutrace.h +++ b/arch/x86/kvm/mmu/mmutrace.h @@ -57,6 +57,7 @@ TRACE_DEFINE_ENUM(RET_PF_CONTINUE); TRACE_DEFINE_ENUM(RET_PF_RETRY); TRACE_DEFINE_ENUM(RET_PF_EMULATE); +TRACE_DEFINE_ENUM(RET_PF_WRITE_PROTECTED); TRACE_DEFINE_ENUM(RET_PF_INVALID); TRACE_DEFINE_ENUM(RET_PF_FIXED); TRACE_DEFINE_ENUM(RET_PF_SPURIOUS); diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index 69941cebb3a8..ae7d39ff2d07 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -646,10 +646,10 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, * really care if it changes underneath us after this point). */ if (FNAME(gpte_changed)(vcpu, gw, top_level)) - goto out_gpte_changed; + return RET_PF_RETRY; if (WARN_ON_ONCE(!VALID_PAGE(vcpu->arch.mmu->root.hpa))) - goto out_gpte_changed; + return RET_PF_RETRY; /* * Load a new root and retry the faulting instruction in the extremely @@ -659,7 +659,7 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, */ if (unlikely(kvm_mmu_is_dummy_root(vcpu->arch.mmu->root.hpa))) { kvm_make_request(KVM_REQ_MMU_FREE_OBSOLETE_ROOTS, vcpu); - goto out_gpte_changed; + return RET_PF_RETRY; } for_each_shadow_entry(vcpu, fault->addr, it) { @@ -674,34 +674,38 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, sp = kvm_mmu_get_child_sp(vcpu, it.sptep, table_gfn, false, access); - if (sp != ERR_PTR(-EEXIST)) { - /* - * We must synchronize the pagetable before linking it - * because the guest doesn't need to flush tlb when - * the gpte is changed from non-present to present. - * Otherwise, the guest may use the wrong mapping. - * - * For PG_LEVEL_4K, kvm_mmu_get_page() has already - * synchronized it transiently via kvm_sync_page(). - * - * For higher level pagetable, we synchronize it via - * the slower mmu_sync_children(). If it needs to - * break, some progress has been made; return - * RET_PF_RETRY and retry on the next #PF. - * KVM_REQ_MMU_SYNC is not necessary but it - * expedites the process. - */ - if (sp->unsync_children && - mmu_sync_children(vcpu, sp, false)) - return RET_PF_RETRY; - } + /* + * Synchronize the new page before linking it, as the CPU (KVM) + * is architecturally disallowed from inserting non-present + * entries into the TLB, i.e. the guest isn't required to flush + * the TLB when changing the gPTE from non-present to present. + * + * For PG_LEVEL_4K, kvm_mmu_find_shadow_page() has already + * synchronized the page via kvm_sync_page(). + * + * For higher level pages, which cannot be unsync themselves + * but can have unsync children, synchronize via the slower + * mmu_sync_children(). If KVM needs to drop mmu_lock due to + * contention or to reschedule, instruct the caller to retry + * the #PF (mmu_sync_children() ensures forward progress will + * be made). + */ + if (sp != ERR_PTR(-EEXIST) && sp->unsync_children && + mmu_sync_children(vcpu, sp, false)) + return RET_PF_RETRY; /* - * Verify that the gpte in the page we've just write - * protected is still there. + * Verify that the gpte in the page, which is now either + * write-protected or unsync, wasn't modified between the fault + * and acquiring mmu_lock. This needs to be done even when + * reusing an existing shadow page to ensure the information + * gathered by the walker matches the information stored in the + * shadow page (which could have been modified by a different + * vCPU even if the page was already linked). Holding mmu_lock + * prevents the shadow page from changing after this point. */ if (FNAME(gpte_changed)(vcpu, gw, it.level - 1)) - goto out_gpte_changed; + return RET_PF_RETRY; if (sp != ERR_PTR(-EEXIST)) link_shadow_page(vcpu, it.sptep, sp); @@ -755,9 +759,6 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, FNAME(pte_prefetch)(vcpu, gw, it.sptep); return ret; - -out_gpte_changed: - return RET_PF_RETRY; } /* @@ -805,7 +806,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault if (page_fault_handle_page_track(vcpu, fault)) { shadow_page_table_clear_flood(vcpu, fault->addr); - return RET_PF_EMULATE; + return RET_PF_WRITE_PROTECTED; } r = mmu_topup_memory_caches(vcpu, true); diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 3c55955bcaf8..3b996c1fdaab 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -1046,10 +1046,8 @@ static int tdp_mmu_map_handle_target_level(struct kvm_vcpu *vcpu, * protected, emulation is needed. If the emulation was skipped, * the vCPU would have the same fault again. */ - if (wrprot) { - if (fault->write) - ret = RET_PF_EMULATE; - } + if (wrprot && fault->write) + ret = RET_PF_WRITE_PROTECTED; /* If a MMIO SPTE is installed, the MMIO will need to be emulated. */ if (unlikely(is_mmio_spte(vcpu->kvm, new_spte))) { diff --git a/arch/x86/kvm/reverse_cpuid.h b/arch/x86/kvm/reverse_cpuid.h index 2f4e155080ba..0d17d6b70639 100644 --- a/arch/x86/kvm/reverse_cpuid.h +++ b/arch/x86/kvm/reverse_cpuid.h @@ -17,6 +17,7 @@ enum kvm_only_cpuid_leafs { CPUID_8000_0007_EDX, CPUID_8000_0022_EAX, CPUID_7_2_EDX, + CPUID_24_0_EBX, NR_KVM_CPU_CAPS, NKVMCAPINTS = NR_KVM_CPU_CAPS - NCAPINTS, @@ -46,6 +47,7 @@ enum kvm_only_cpuid_leafs { #define X86_FEATURE_AVX_NE_CONVERT KVM_X86_FEATURE(CPUID_7_1_EDX, 5) #define X86_FEATURE_AMX_COMPLEX KVM_X86_FEATURE(CPUID_7_1_EDX, 8) #define X86_FEATURE_PREFETCHITI KVM_X86_FEATURE(CPUID_7_1_EDX, 14) +#define X86_FEATURE_AVX10 KVM_X86_FEATURE(CPUID_7_1_EDX, 19) /* Intel-defined sub-features, CPUID level 0x00000007:2 (EDX) */ #define X86_FEATURE_INTEL_PSFD KVM_X86_FEATURE(CPUID_7_2_EDX, 0) @@ -55,6 +57,11 @@ enum kvm_only_cpuid_leafs { #define KVM_X86_FEATURE_BHI_CTRL KVM_X86_FEATURE(CPUID_7_2_EDX, 4) #define X86_FEATURE_MCDT_NO KVM_X86_FEATURE(CPUID_7_2_EDX, 5) +/* Intel-defined sub-features, CPUID level 0x00000024:0 (EBX) */ +#define X86_FEATURE_AVX10_128 KVM_X86_FEATURE(CPUID_24_0_EBX, 16) +#define X86_FEATURE_AVX10_256 KVM_X86_FEATURE(CPUID_24_0_EBX, 17) +#define X86_FEATURE_AVX10_512 KVM_X86_FEATURE(CPUID_24_0_EBX, 18) + /* CPUID level 0x80000007 (EDX). */ #define KVM_X86_FEATURE_CONSTANT_TSC KVM_X86_FEATURE(CPUID_8000_0007_EDX, 8) @@ -90,6 +97,7 @@ static const struct cpuid_reg reverse_cpuid[] = { [CPUID_8000_0021_EAX] = {0x80000021, 0, CPUID_EAX}, [CPUID_8000_0022_EAX] = {0x80000022, 0, CPUID_EAX}, [CPUID_7_2_EDX] = { 7, 2, CPUID_EDX}, + [CPUID_24_0_EBX] = { 0x24, 0, CPUID_EBX}, }; /* diff --git a/arch/x86/kvm/smm.c b/arch/x86/kvm/smm.c index 00e3c27d2a87..85241c0c7f56 100644 --- a/arch/x86/kvm/smm.c +++ b/arch/x86/kvm/smm.c @@ -624,17 +624,31 @@ int emulator_leave_smm(struct x86_emulate_ctxt *ctxt) #endif /* - * Give leave_smm() a chance to make ISA-specific changes to the vCPU - * state (e.g. enter guest mode) before loading state from the SMM - * state-save area. + * FIXME: When resuming L2 (a.k.a. guest mode), the transition to guest + * mode should happen _after_ loading state from SMRAM. However, KVM + * piggybacks the nested VM-Enter flows (which is wrong for many other + * reasons), and so nSVM/nVMX would clobber state that is loaded from + * SMRAM and from the VMCS/VMCB. */ if (kvm_x86_call(leave_smm)(vcpu, &smram)) return X86EMUL_UNHANDLEABLE; #ifdef CONFIG_X86_64 if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) - return rsm_load_state_64(ctxt, &smram.smram64); + ret = rsm_load_state_64(ctxt, &smram.smram64); else #endif - return rsm_load_state_32(ctxt, &smram.smram32); + ret = rsm_load_state_32(ctxt, &smram.smram32); + + /* + * If RSM fails and triggers shutdown, architecturally the shutdown + * occurs *before* the transition to guest mode. But due to KVM's + * flawed handling of RSM to L2 (see above), the vCPU may already be + * in_guest_mode(). Force the vCPU out of guest mode before delivering + * the shutdown, so that L1 enters shutdown instead of seeing a VM-Exit + * that architecturally shouldn't be possible. + */ + if (ret != X86EMUL_CONTINUE && is_guest_mode(vcpu)) + kvm_leave_nested(vcpu); + return ret; } diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index 6f704c1037e5..d5314cb7dff4 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -1693,8 +1693,8 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, return -EINVAL; ret = -ENOMEM; - ctl = kzalloc(sizeof(*ctl), GFP_KERNEL_ACCOUNT); - save = kzalloc(sizeof(*save), GFP_KERNEL_ACCOUNT); + ctl = kzalloc(sizeof(*ctl), GFP_KERNEL); + save = kzalloc(sizeof(*save), GFP_KERNEL); if (!ctl || !save) goto out_free; diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 5ab2c92c7331..9df3e1e5ae81 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -573,7 +573,7 @@ static void __svm_write_tsc_multiplier(u64 multiplier) static __always_inline struct sev_es_save_area *sev_es_host_save_area(struct svm_cpu_data *sd) { - return page_address(sd->save_area) + 0x400; + return &sd->save_area->host_sev_es_save; } static inline void kvm_cpu_svm_disable(void) @@ -592,14 +592,14 @@ static inline void kvm_cpu_svm_disable(void) } } -static void svm_emergency_disable(void) +static void svm_emergency_disable_virtualization_cpu(void) { kvm_rebooting = true; kvm_cpu_svm_disable(); } -static void svm_hardware_disable(void) +static void svm_disable_virtualization_cpu(void) { /* Make sure we clean up behind us */ if (tsc_scaling) @@ -610,7 +610,7 @@ static void svm_hardware_disable(void) amd_pmu_disable_virt(); } -static int svm_hardware_enable(void) +static int svm_enable_virtualization_cpu(void) { struct svm_cpu_data *sd; @@ -696,7 +696,7 @@ static void svm_cpu_uninit(int cpu) return; kfree(sd->sev_vmcbs); - __free_page(sd->save_area); + __free_page(__sme_pa_to_page(sd->save_area_pa)); sd->save_area_pa = 0; sd->save_area = NULL; } @@ -704,23 +704,24 @@ static void svm_cpu_uninit(int cpu) static int svm_cpu_init(int cpu) { struct svm_cpu_data *sd = per_cpu_ptr(&svm_data, cpu); + struct page *save_area_page; int ret = -ENOMEM; memset(sd, 0, sizeof(struct svm_cpu_data)); - sd->save_area = snp_safe_alloc_page_node(cpu_to_node(cpu), GFP_KERNEL); - if (!sd->save_area) + save_area_page = snp_safe_alloc_page_node(cpu_to_node(cpu), GFP_KERNEL); + if (!save_area_page) return ret; ret = sev_cpu_init(sd); if (ret) goto free_save_area; - sd->save_area_pa = __sme_page_pa(sd->save_area); + sd->save_area = page_address(save_area_page); + sd->save_area_pa = __sme_page_pa(save_area_page); return 0; free_save_area: - __free_page(sd->save_area); - sd->save_area = NULL; + __free_page(save_area_page); return ret; } @@ -1124,8 +1125,7 @@ static void svm_hardware_unsetup(void) for_each_possible_cpu(cpu) svm_cpu_uninit(cpu); - __free_pages(pfn_to_page(iopm_base >> PAGE_SHIFT), - get_order(IOPM_SIZE)); + __free_pages(__sme_pa_to_page(iopm_base), get_order(IOPM_SIZE)); iopm_base = 0; } @@ -1301,7 +1301,7 @@ static void init_vmcb(struct kvm_vcpu *vcpu) if (!kvm_hlt_in_guest(vcpu->kvm)) svm_set_intercept(svm, INTERCEPT_HLT); - control->iopm_base_pa = __sme_set(iopm_base); + control->iopm_base_pa = iopm_base; control->msrpm_base_pa = __sme_set(__pa(svm->msrpm)); control->int_ctl = V_INTR_MASKING_MASK; @@ -1503,7 +1503,7 @@ static void svm_vcpu_free(struct kvm_vcpu *vcpu) sev_free_vcpu(vcpu); - __free_page(pfn_to_page(__sme_clr(svm->vmcb01.pa) >> PAGE_SHIFT)); + __free_page(__sme_pa_to_page(svm->vmcb01.pa)); __free_pages(virt_to_page(svm->msrpm), get_order(MSRPM_SIZE)); } @@ -1533,7 +1533,7 @@ static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu) * TSC_AUX is always virtualized for SEV-ES guests when the feature is * available. The user return MSR support is not required in this case * because TSC_AUX is restored on #VMEXIT from the host save area - * (which has been initialized in svm_hardware_enable()). + * (which has been initialized in svm_enable_virtualization_cpu()). */ if (likely(tsc_aux_uret_slot >= 0) && (!boot_cpu_has(X86_FEATURE_V_TSC_AUX) || !sev_es_guest(vcpu->kvm))) @@ -2825,17 +2825,17 @@ static int efer_trap(struct kvm_vcpu *vcpu) return kvm_complete_insn_gp(vcpu, ret); } -static int svm_get_msr_feature(struct kvm_msr_entry *msr) +static int svm_get_feature_msr(u32 msr, u64 *data) { - msr->data = 0; + *data = 0; - switch (msr->index) { + switch (msr) { case MSR_AMD64_DE_CFG: if (cpu_feature_enabled(X86_FEATURE_LFENCE_RDTSC)) - msr->data |= MSR_AMD64_DE_CFG_LFENCE_SERIALIZE; + *data |= MSR_AMD64_DE_CFG_LFENCE_SERIALIZE; break; default: - return KVM_MSR_RET_INVALID; + return KVM_MSR_RET_UNSUPPORTED; } return 0; @@ -3144,7 +3144,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) * feature is available. The user return MSR support is not * required in this case because TSC_AUX is restored on #VMEXIT * from the host save area (which has been initialized in - * svm_hardware_enable()). + * svm_enable_virtualization_cpu()). */ if (boot_cpu_has(X86_FEATURE_V_TSC_AUX) && sev_es_guest(vcpu->kvm)) break; @@ -3191,18 +3191,21 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) kvm_pr_unimpl_wrmsr(vcpu, ecx, data); break; case MSR_AMD64_DE_CFG: { - struct kvm_msr_entry msr_entry; + u64 supported_de_cfg; - msr_entry.index = msr->index; - if (svm_get_msr_feature(&msr_entry)) + if (svm_get_feature_msr(ecx, &supported_de_cfg)) return 1; - /* Check the supported bits */ - if (data & ~msr_entry.data) + if (data & ~supported_de_cfg) return 1; - /* Don't allow the guest to change a bit, #GP */ - if (!msr->host_initiated && (data ^ msr_entry.data)) + /* + * Don't let the guest change the host-programmed value. The + * MSR is very model specific, i.e. contains multiple bits that + * are completely unknown to KVM, and the one bit known to KVM + * is simply a reflection of hardware capabilities. + */ + if (!msr->host_initiated && data != svm->msr_decfg) return 1; svm->msr_decfg = data; @@ -4156,12 +4159,21 @@ static int svm_vcpu_pre_run(struct kvm_vcpu *vcpu) static fastpath_t svm_exit_handlers_fastpath(struct kvm_vcpu *vcpu) { + struct vcpu_svm *svm = to_svm(vcpu); + if (is_guest_mode(vcpu)) return EXIT_FASTPATH_NONE; - if (to_svm(vcpu)->vmcb->control.exit_code == SVM_EXIT_MSR && - to_svm(vcpu)->vmcb->control.exit_info_1) + switch (svm->vmcb->control.exit_code) { + case SVM_EXIT_MSR: + if (!svm->vmcb->control.exit_info_1) + break; return handle_fastpath_set_msr_irqoff(vcpu); + case SVM_EXIT_HLT: + return handle_fastpath_hlt(vcpu); + default: + break; + } return EXIT_FASTPATH_NONE; } @@ -4992,8 +5004,9 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .check_processor_compatibility = svm_check_processor_compat, .hardware_unsetup = svm_hardware_unsetup, - .hardware_enable = svm_hardware_enable, - .hardware_disable = svm_hardware_disable, + .enable_virtualization_cpu = svm_enable_virtualization_cpu, + .disable_virtualization_cpu = svm_disable_virtualization_cpu, + .emergency_disable_virtualization_cpu = svm_emergency_disable_virtualization_cpu, .has_emulated_msr = svm_has_emulated_msr, .vcpu_create = svm_vcpu_create, @@ -5011,7 +5024,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .vcpu_unblocking = avic_vcpu_unblocking, .update_exception_bitmap = svm_update_exception_bitmap, - .get_msr_feature = svm_get_msr_feature, + .get_feature_msr = svm_get_feature_msr, .get_msr = svm_get_msr, .set_msr = svm_set_msr, .get_segment_base = svm_get_segment_base, @@ -5062,6 +5075,8 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .enable_nmi_window = svm_enable_nmi_window, .enable_irq_window = svm_enable_irq_window, .update_cr8_intercept = svm_update_cr8_intercept, + + .x2apic_icr_is_split = true, .set_virtual_apic_mode = avic_refresh_virtual_apic_mode, .refresh_apicv_exec_ctrl = avic_refresh_apicv_exec_ctrl, .apicv_post_state_restore = avic_apicv_post_state_restore, @@ -5266,7 +5281,7 @@ static __init int svm_hardware_setup(void) iopm_va = page_address(iopm_pages); memset(iopm_va, 0xff, PAGE_SIZE * (1 << order)); - iopm_base = page_to_pfn(iopm_pages) << PAGE_SHIFT; + iopm_base = __sme_page_pa(iopm_pages); init_msrpm_offsets(); @@ -5425,8 +5440,6 @@ static struct kvm_x86_init_ops svm_init_ops __initdata = { static void __svm_exit(void) { kvm_x86_vendor_exit(); - - cpu_emergency_unregister_virt_callback(svm_emergency_disable); } static int __init svm_init(void) @@ -5442,8 +5455,6 @@ static int __init svm_init(void) if (r) return r; - cpu_emergency_register_virt_callback(svm_emergency_disable); - /* * Common KVM initialization _must_ come last, after this, /dev/kvm is * exposed to userspace! diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 76107c7d0595..43fa6a16eb19 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -25,7 +25,21 @@ #include "cpuid.h" #include "kvm_cache_regs.h" -#define __sme_page_pa(x) __sme_set(page_to_pfn(x) << PAGE_SHIFT) +/* + * Helpers to convert to/from physical addresses for pages whose address is + * consumed directly by hardware. Even though it's a physical address, SVM + * often restricts the address to the natural width, hence 'unsigned long' + * instead of 'hpa_t'. + */ +static inline unsigned long __sme_page_pa(struct page *page) +{ + return __sme_set(page_to_pfn(page) << PAGE_SHIFT); +} + +static inline struct page *__sme_pa_to_page(unsigned long pa) +{ + return pfn_to_page(__sme_clr(pa) >> PAGE_SHIFT); +} #define IOPM_SIZE PAGE_SIZE * 3 #define MSRPM_SIZE PAGE_SIZE * 2 @@ -321,7 +335,7 @@ struct svm_cpu_data { u32 next_asid; u32 min_asid; - struct page *save_area; + struct vmcb *save_area; unsigned long save_area_pa; struct vmcb *current_vmcb; diff --git a/arch/x86/kvm/svm/vmenter.S b/arch/x86/kvm/svm/vmenter.S index a0c8eb37d3e1..2ed80aea3bb1 100644 --- a/arch/x86/kvm/svm/vmenter.S +++ b/arch/x86/kvm/svm/vmenter.S @@ -209,10 +209,8 @@ SYM_FUNC_START(__svm_vcpu_run) 7: vmload %_ASM_AX 8: -#ifdef CONFIG_MITIGATION_RETPOLINE /* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */ - FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE -#endif + FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_VMEXIT /* Clobbers RAX, RCX, RDX. */ RESTORE_HOST_SPEC_CTRL @@ -348,10 +346,8 @@ SYM_FUNC_START(__svm_sev_es_vcpu_run) 2: cli -#ifdef CONFIG_MITIGATION_RETPOLINE /* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */ - FILL_RETURN_BUFFER %rax, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE -#endif + FILL_RETURN_BUFFER %rax, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_VMEXIT /* Clobbers RAX, RCX, RDX, consumes RDI (@svm) and RSI (@spec_ctrl_intercepted). */ RESTORE_HOST_SPEC_CTRL diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h index 41a4533f9989..cb6588238f46 100644 --- a/arch/x86/kvm/vmx/capabilities.h +++ b/arch/x86/kvm/vmx/capabilities.h @@ -54,9 +54,7 @@ struct nested_vmx_msrs { }; struct vmcs_config { - int size; - u32 basic_cap; - u32 revision_id; + u64 basic; u32 pin_based_exec_ctrl; u32 cpu_based_exec_ctrl; u32 cpu_based_2nd_exec_ctrl; @@ -76,7 +74,7 @@ extern struct vmx_capability vmx_capability __ro_after_init; static inline bool cpu_has_vmx_basic_inout(void) { - return (((u64)vmcs_config.basic_cap << 32) & VMX_BASIC_INOUT); + return vmcs_config.basic & VMX_BASIC_INOUT; } static inline bool cpu_has_virtual_nmis(void) @@ -225,7 +223,7 @@ static inline bool cpu_has_vmx_vmfunc(void) static inline bool cpu_has_vmx_shadow_vmcs(void) { /* check if the cpu supports writing r/o exit information fields */ - if (!(vmcs_config.misc & MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS)) + if (!(vmcs_config.misc & VMX_MISC_VMWRITE_SHADOW_RO_FIELDS)) return false; return vmcs_config.cpu_based_2nd_exec_ctrl & @@ -367,7 +365,7 @@ static inline bool cpu_has_vmx_invvpid_global(void) static inline bool cpu_has_vmx_intel_pt(void) { - return (vmcs_config.misc & MSR_IA32_VMX_MISC_INTEL_PT) && + return (vmcs_config.misc & VMX_MISC_INTEL_PT) && (vmcs_config.cpu_based_2nd_exec_ctrl & SECONDARY_EXEC_PT_USE_GPA) && (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_RTIT_CTL); } diff --git a/arch/x86/kvm/vmx/main.c b/arch/x86/kvm/vmx/main.c index 0bf35ebe8a1b..7668e2fb8043 100644 --- a/arch/x86/kvm/vmx/main.c +++ b/arch/x86/kvm/vmx/main.c @@ -23,8 +23,10 @@ struct kvm_x86_ops vt_x86_ops __initdata = { .hardware_unsetup = vmx_hardware_unsetup, - .hardware_enable = vmx_hardware_enable, - .hardware_disable = vmx_hardware_disable, + .enable_virtualization_cpu = vmx_enable_virtualization_cpu, + .disable_virtualization_cpu = vmx_disable_virtualization_cpu, + .emergency_disable_virtualization_cpu = vmx_emergency_disable_virtualization_cpu, + .has_emulated_msr = vmx_has_emulated_msr, .vm_size = sizeof(struct kvm_vmx), @@ -41,7 +43,7 @@ struct kvm_x86_ops vt_x86_ops __initdata = { .vcpu_put = vmx_vcpu_put, .update_exception_bitmap = vmx_update_exception_bitmap, - .get_msr_feature = vmx_get_msr_feature, + .get_feature_msr = vmx_get_feature_msr, .get_msr = vmx_get_msr, .set_msr = vmx_set_msr, .get_segment_base = vmx_get_segment_base, @@ -89,6 +91,8 @@ struct kvm_x86_ops vt_x86_ops __initdata = { .enable_nmi_window = vmx_enable_nmi_window, .enable_irq_window = vmx_enable_irq_window, .update_cr8_intercept = vmx_update_cr8_intercept, + + .x2apic_icr_is_split = false, .set_virtual_apic_mode = vmx_set_virtual_apic_mode, .set_apic_access_page_addr = vmx_set_apic_access_page_addr, .refresh_apicv_exec_ctrl = vmx_refresh_apicv_exec_ctrl, diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 2392a7ef254d..a8e7bc04d9bf 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -981,7 +981,7 @@ static u32 nested_vmx_load_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count) __func__, i, e.index, e.reserved); goto fail; } - if (kvm_set_msr(vcpu, e.index, e.value)) { + if (kvm_set_msr_with_filter(vcpu, e.index, e.value)) { pr_debug_ratelimited( "%s cannot write MSR (%u, 0x%x, 0x%llx)\n", __func__, i, e.index, e.value); @@ -1017,7 +1017,7 @@ static bool nested_vmx_get_vmexit_msr_value(struct kvm_vcpu *vcpu, } } - if (kvm_get_msr(vcpu, msr_index, data)) { + if (kvm_get_msr_with_filter(vcpu, msr_index, data)) { pr_debug_ratelimited("%s cannot read MSR (0x%x)\n", __func__, msr_index); return false; @@ -1112,9 +1112,9 @@ static void prepare_vmx_msr_autostore_list(struct kvm_vcpu *vcpu, /* * Emulated VMEntry does not fail here. Instead a less * accurate value will be returned by - * nested_vmx_get_vmexit_msr_value() using kvm_get_msr() - * instead of reading the value from the vmcs02 VMExit - * MSR-store area. + * nested_vmx_get_vmexit_msr_value() by reading KVM's + * internal MSR state instead of reading the value from + * the vmcs02 VMExit MSR-store area. */ pr_warn_ratelimited( "Not enough msr entries in msr_autostore. Can't add msr %x\n", @@ -1251,21 +1251,32 @@ static bool is_bitwise_subset(u64 superset, u64 subset, u64 mask) static int vmx_restore_vmx_basic(struct vcpu_vmx *vmx, u64 data) { - const u64 feature_and_reserved = - /* feature (except bit 48; see below) */ - BIT_ULL(49) | BIT_ULL(54) | BIT_ULL(55) | - /* reserved */ - BIT_ULL(31) | GENMASK_ULL(47, 45) | GENMASK_ULL(63, 56); + const u64 feature_bits = VMX_BASIC_DUAL_MONITOR_TREATMENT | + VMX_BASIC_INOUT | + VMX_BASIC_TRUE_CTLS; + + const u64 reserved_bits = GENMASK_ULL(63, 56) | + GENMASK_ULL(47, 45) | + BIT_ULL(31); + u64 vmx_basic = vmcs_config.nested.basic; - if (!is_bitwise_subset(vmx_basic, data, feature_and_reserved)) + BUILD_BUG_ON(feature_bits & reserved_bits); + + /* + * Except for 32BIT_PHYS_ADDR_ONLY, which is an anti-feature bit (has + * inverted polarity), the incoming value must not set feature bits or + * reserved bits that aren't allowed/supported by KVM. Fields, i.e. + * multi-bit values, are explicitly checked below. + */ + if (!is_bitwise_subset(vmx_basic, data, feature_bits | reserved_bits)) return -EINVAL; /* * KVM does not emulate a version of VMX that constrains physical * addresses of VMX structures (e.g. VMCS) to 32-bits. */ - if (data & BIT_ULL(48)) + if (data & VMX_BASIC_32BIT_PHYS_ADDR_ONLY) return -EINVAL; if (vmx_basic_vmcs_revision_id(vmx_basic) != @@ -1334,16 +1345,29 @@ vmx_restore_control_msr(struct vcpu_vmx *vmx, u32 msr_index, u64 data) static int vmx_restore_vmx_misc(struct vcpu_vmx *vmx, u64 data) { - const u64 feature_and_reserved_bits = - /* feature */ - BIT_ULL(5) | GENMASK_ULL(8, 6) | BIT_ULL(14) | BIT_ULL(15) | - BIT_ULL(28) | BIT_ULL(29) | BIT_ULL(30) | - /* reserved */ - GENMASK_ULL(13, 9) | BIT_ULL(31); + const u64 feature_bits = VMX_MISC_SAVE_EFER_LMA | + VMX_MISC_ACTIVITY_HLT | + VMX_MISC_ACTIVITY_SHUTDOWN | + VMX_MISC_ACTIVITY_WAIT_SIPI | + VMX_MISC_INTEL_PT | + VMX_MISC_RDMSR_IN_SMM | + VMX_MISC_VMWRITE_SHADOW_RO_FIELDS | + VMX_MISC_VMXOFF_BLOCK_SMI | + VMX_MISC_ZERO_LEN_INS; + + const u64 reserved_bits = BIT_ULL(31) | GENMASK_ULL(13, 9); + u64 vmx_misc = vmx_control_msr(vmcs_config.nested.misc_low, vmcs_config.nested.misc_high); - if (!is_bitwise_subset(vmx_misc, data, feature_and_reserved_bits)) + BUILD_BUG_ON(feature_bits & reserved_bits); + + /* + * The incoming value must not set feature bits or reserved bits that + * aren't allowed/supported by KVM. Fields, i.e. multi-bit values, are + * explicitly checked below. + */ + if (!is_bitwise_subset(vmx_misc, data, feature_bits | reserved_bits)) return -EINVAL; if ((vmx->nested.msrs.pinbased_ctls_high & @@ -2317,10 +2341,12 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct loaded_vmcs *vmcs0 /* Posted interrupts setting is only taken from vmcs12. */ vmx->nested.pi_pending = false; - if (nested_cpu_has_posted_intr(vmcs12)) + if (nested_cpu_has_posted_intr(vmcs12)) { vmx->nested.posted_intr_nv = vmcs12->posted_intr_nv; - else + } else { + vmx->nested.posted_intr_nv = -1; exec_control &= ~PIN_BASED_POSTED_INTR; + } pin_controls_set(vmx, exec_control); /* @@ -2470,6 +2496,7 @@ static void prepare_vmcs02_rare(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) if (!hv_evmcs || !(hv_evmcs->hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2)) { + vmcs_write16(GUEST_ES_SELECTOR, vmcs12->guest_es_selector); vmcs_write16(GUEST_CS_SELECTOR, vmcs12->guest_cs_selector); vmcs_write16(GUEST_SS_SELECTOR, vmcs12->guest_ss_selector); @@ -2507,7 +2534,7 @@ static void prepare_vmcs02_rare(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) vmcs_writel(GUEST_GDTR_BASE, vmcs12->guest_gdtr_base); vmcs_writel(GUEST_IDTR_BASE, vmcs12->guest_idtr_base); - vmx->segment_cache.bitmask = 0; + vmx_segment_cache_clear(vmx); } if (!hv_evmcs || !(hv_evmcs->hv_clean_fields & @@ -4284,11 +4311,52 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu) } if (kvm_cpu_has_interrupt(vcpu) && !vmx_interrupt_blocked(vcpu)) { + int irq; + if (block_nested_events) return -EBUSY; if (!nested_exit_on_intr(vcpu)) goto no_vmexit; - nested_vmx_vmexit(vcpu, EXIT_REASON_EXTERNAL_INTERRUPT, 0, 0); + + if (!nested_exit_intr_ack_set(vcpu)) { + nested_vmx_vmexit(vcpu, EXIT_REASON_EXTERNAL_INTERRUPT, 0, 0); + return 0; + } + + irq = kvm_cpu_get_extint(vcpu); + if (irq != -1) { + nested_vmx_vmexit(vcpu, EXIT_REASON_EXTERNAL_INTERRUPT, + INTR_INFO_VALID_MASK | INTR_TYPE_EXT_INTR | irq, 0); + return 0; + } + + irq = kvm_apic_has_interrupt(vcpu); + if (WARN_ON_ONCE(irq < 0)) + goto no_vmexit; + + /* + * If the IRQ is L2's PI notification vector, process posted + * interrupts for L2 instead of injecting VM-Exit, as the + * detection/morphing architecturally occurs when the IRQ is + * delivered to the CPU. Note, only interrupts that are routed + * through the local APIC trigger posted interrupt processing, + * and enabling posted interrupts requires ACK-on-exit. + */ + if (irq == vmx->nested.posted_intr_nv) { + vmx->nested.pi_pending = true; + kvm_apic_clear_irr(vcpu, irq); + goto no_vmexit; + } + + nested_vmx_vmexit(vcpu, EXIT_REASON_EXTERNAL_INTERRUPT, + INTR_INFO_VALID_MASK | INTR_TYPE_EXT_INTR | irq, 0); + + /* + * ACK the interrupt _after_ emulating VM-Exit, as the IRQ must + * be marked as in-service in vmcs01.GUEST_INTERRUPT_STATUS.SVI + * if APICv is active. + */ + kvm_apic_ack_interrupt(vcpu, irq); return 0; } @@ -4806,7 +4874,7 @@ static void nested_vmx_restore_host_state(struct kvm_vcpu *vcpu) goto vmabort; } - if (kvm_set_msr(vcpu, h.index, h.value)) { + if (kvm_set_msr_with_filter(vcpu, h.index, h.value)) { pr_debug_ratelimited( "%s WRMSR failed (%u, 0x%x, 0x%llx)\n", __func__, j, h.index, h.value); @@ -4969,14 +5037,6 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; if (likely(!vmx->fail)) { - if ((u16)vm_exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT && - nested_exit_intr_ack_set(vcpu)) { - int irq = kvm_cpu_get_interrupt(vcpu); - WARN_ON(irq < 0); - vmcs12->vm_exit_intr_info = irq | - INTR_INFO_VALID_MASK | INTR_TYPE_EXT_INTR; - } - if (vm_exit_reason != -1) trace_kvm_nested_vmexit_inject(vmcs12->vm_exit_reason, vmcs12->exit_qualification, @@ -7051,7 +7111,7 @@ static void nested_vmx_setup_misc_data(struct vmcs_config *vmcs_conf, { msrs->misc_low = (u32)vmcs_conf->misc & VMX_MISC_SAVE_EFER_LMA; msrs->misc_low |= - MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS | + VMX_MISC_VMWRITE_SHADOW_RO_FIELDS | VMX_MISC_EMULATED_PREEMPTION_TIMER_RATE | VMX_MISC_ACTIVITY_HLT | VMX_MISC_ACTIVITY_WAIT_SIPI; @@ -7066,12 +7126,10 @@ static void nested_vmx_setup_basic(struct nested_vmx_msrs *msrs) * guest, and the VMCS structure we give it - not about the * VMX support of the underlying hardware. */ - msrs->basic = - VMCS12_REVISION | - VMX_BASIC_TRUE_CTLS | - ((u64)VMCS12_SIZE << VMX_BASIC_VMCS_SIZE_SHIFT) | - (VMX_BASIC_MEM_TYPE_WB << VMX_BASIC_MEM_TYPE_SHIFT); + msrs->basic = vmx_basic_encode_vmcs_info(VMCS12_REVISION, VMCS12_SIZE, + X86_MEMTYPE_WB); + msrs->basic |= VMX_BASIC_TRUE_CTLS; if (cpu_has_vmx_basic_inout()) msrs->basic |= VMX_BASIC_INOUT; } diff --git a/arch/x86/kvm/vmx/nested.h b/arch/x86/kvm/vmx/nested.h index cce4e2aa30fb..2c296b6abb8c 100644 --- a/arch/x86/kvm/vmx/nested.h +++ b/arch/x86/kvm/vmx/nested.h @@ -39,11 +39,17 @@ bool nested_vmx_check_io_bitmaps(struct kvm_vcpu *vcpu, unsigned int port, static inline struct vmcs12 *get_vmcs12(struct kvm_vcpu *vcpu) { + lockdep_assert_once(lockdep_is_held(&vcpu->mutex) || + !refcount_read(&vcpu->kvm->users_count)); + return to_vmx(vcpu)->nested.cached_vmcs12; } static inline struct vmcs12 *get_shadow_vmcs12(struct kvm_vcpu *vcpu) { + lockdep_assert_once(lockdep_is_held(&vcpu->mutex) || + !refcount_read(&vcpu->kvm->users_count)); + return to_vmx(vcpu)->nested.cached_shadow_vmcs12; } @@ -109,7 +115,7 @@ static inline unsigned nested_cpu_vmx_misc_cr3_count(struct kvm_vcpu *vcpu) static inline bool nested_cpu_has_vmwrite_any_field(struct kvm_vcpu *vcpu) { return to_vmx(vcpu)->nested.msrs.misc_low & - MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS; + VMX_MISC_VMWRITE_SHADOW_RO_FIELDS; } static inline bool nested_cpu_has_zero_length_injection(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/vmx/sgx.c b/arch/x86/kvm/vmx/sgx.c index 6fef01e0536e..a3c3d2a51f47 100644 --- a/arch/x86/kvm/vmx/sgx.c +++ b/arch/x86/kvm/vmx/sgx.c @@ -274,7 +274,7 @@ static int handle_encls_ecreate(struct kvm_vcpu *vcpu) * simultaneously set SGX_ATTR_PROVISIONKEY to bypass the check to * enforce restriction of access to the PROVISIONKEY. */ - contents = (struct sgx_secs *)__get_free_page(GFP_KERNEL_ACCOUNT); + contents = (struct sgx_secs *)__get_free_page(GFP_KERNEL); if (!contents) return -ENOMEM; diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 733a0c45d1a6..1a4438358c5e 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -525,10 +525,6 @@ static const struct kvm_vmx_segment_field { VMX_SEGMENT_FIELD(LDTR), }; -static inline void vmx_segment_cache_clear(struct vcpu_vmx *vmx) -{ - vmx->segment_cache.bitmask = 0; -} static unsigned long host_idt_base; @@ -755,7 +751,7 @@ fault: return -EIO; } -static void vmx_emergency_disable(void) +void vmx_emergency_disable_virtualization_cpu(void) { int cpu = raw_smp_processor_id(); struct loaded_vmcs *v; @@ -1998,15 +1994,15 @@ static inline bool is_vmx_feature_control_msr_valid(struct vcpu_vmx *vmx, return !(msr->data & ~valid_bits); } -int vmx_get_msr_feature(struct kvm_msr_entry *msr) +int vmx_get_feature_msr(u32 msr, u64 *data) { - switch (msr->index) { + switch (msr) { case KVM_FIRST_EMULATED_VMX_MSR ... KVM_LAST_EMULATED_VMX_MSR: if (!nested) return 1; - return vmx_get_vmx_msr(&vmcs_config.nested, msr->index, &msr->data); + return vmx_get_vmx_msr(&vmcs_config.nested, msr, data); default: - return KVM_MSR_RET_INVALID; + return KVM_MSR_RET_UNSUPPORTED; } } @@ -2605,13 +2601,13 @@ static u64 adjust_vmx_controls64(u64 ctl_opt, u32 msr) static int setup_vmcs_config(struct vmcs_config *vmcs_conf, struct vmx_capability *vmx_cap) { - u32 vmx_msr_low, vmx_msr_high; u32 _pin_based_exec_control = 0; u32 _cpu_based_exec_control = 0; u32 _cpu_based_2nd_exec_control = 0; u64 _cpu_based_3rd_exec_control = 0; u32 _vmexit_control = 0; u32 _vmentry_control = 0; + u64 basic_msr; u64 misc_msr; int i; @@ -2734,29 +2730,29 @@ static int setup_vmcs_config(struct vmcs_config *vmcs_conf, _vmexit_control &= ~x_ctrl; } - rdmsr(MSR_IA32_VMX_BASIC, vmx_msr_low, vmx_msr_high); + rdmsrl(MSR_IA32_VMX_BASIC, basic_msr); /* IA-32 SDM Vol 3B: VMCS size is never greater than 4kB. */ - if ((vmx_msr_high & 0x1fff) > PAGE_SIZE) + if (vmx_basic_vmcs_size(basic_msr) > PAGE_SIZE) return -EIO; #ifdef CONFIG_X86_64 - /* IA-32 SDM Vol 3B: 64-bit CPUs always have VMX_BASIC_MSR[48]==0. */ - if (vmx_msr_high & (1u<<16)) + /* + * KVM expects to be able to shove all legal physical addresses into + * VMCS fields for 64-bit kernels, and per the SDM, "This bit is always + * 0 for processors that support Intel 64 architecture". + */ + if (basic_msr & VMX_BASIC_32BIT_PHYS_ADDR_ONLY) return -EIO; #endif /* Require Write-Back (WB) memory type for VMCS accesses. */ - if (((vmx_msr_high >> 18) & 15) != 6) + if (vmx_basic_vmcs_mem_type(basic_msr) != X86_MEMTYPE_WB) return -EIO; rdmsrl(MSR_IA32_VMX_MISC, misc_msr); - vmcs_conf->size = vmx_msr_high & 0x1fff; - vmcs_conf->basic_cap = vmx_msr_high & ~0x1fff; - - vmcs_conf->revision_id = vmx_msr_low; - + vmcs_conf->basic = basic_msr; vmcs_conf->pin_based_exec_ctrl = _pin_based_exec_control; vmcs_conf->cpu_based_exec_ctrl = _cpu_based_exec_control; vmcs_conf->cpu_based_2nd_exec_ctrl = _cpu_based_2nd_exec_control; @@ -2844,7 +2840,7 @@ fault: return -EFAULT; } -int vmx_hardware_enable(void) +int vmx_enable_virtualization_cpu(void) { int cpu = raw_smp_processor_id(); u64 phys_addr = __pa(per_cpu(vmxarea, cpu)); @@ -2881,7 +2877,7 @@ static void vmclear_local_loaded_vmcss(void) __loaded_vmcs_clear(v); } -void vmx_hardware_disable(void) +void vmx_disable_virtualization_cpu(void) { vmclear_local_loaded_vmcss(); @@ -2903,13 +2899,13 @@ struct vmcs *alloc_vmcs_cpu(bool shadow, int cpu, gfp_t flags) if (!pages) return NULL; vmcs = page_address(pages); - memset(vmcs, 0, vmcs_config.size); + memset(vmcs, 0, vmx_basic_vmcs_size(vmcs_config.basic)); /* KVM supports Enlightened VMCS v1 only */ if (kvm_is_using_evmcs()) vmcs->hdr.revision_id = KVM_EVMCS_VERSION; else - vmcs->hdr.revision_id = vmcs_config.revision_id; + vmcs->hdr.revision_id = vmx_basic_vmcs_revision_id(vmcs_config.basic); if (shadow) vmcs->hdr.shadow_vmcs = 1; @@ -3002,7 +2998,7 @@ static __init int alloc_kvm_area(void) * physical CPU. */ if (kvm_is_using_evmcs()) - vmcs->hdr.revision_id = vmcs_config.revision_id; + vmcs->hdr.revision_id = vmx_basic_vmcs_revision_id(vmcs_config.basic); per_cpu(vmxarea, cpu) = vmcs; } @@ -4219,6 +4215,13 @@ static int vmx_deliver_nested_posted_interrupt(struct kvm_vcpu *vcpu, { struct vcpu_vmx *vmx = to_vmx(vcpu); + /* + * DO NOT query the vCPU's vmcs12, as vmcs12 is dynamically allocated + * and freed, and must not be accessed outside of vcpu->mutex. The + * vCPU's cached PI NV is valid if and only if posted interrupts + * enabled in its vmcs12, i.e. checking the vector also checks that + * L1 has enabled posted interrupts for L2. + */ if (is_guest_mode(vcpu) && vector == vmx->nested.posted_intr_nv) { /* @@ -5804,8 +5807,9 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu) error_code |= (exit_qualification & EPT_VIOLATION_RWX_MASK) ? PFERR_PRESENT_MASK : 0; - error_code |= (exit_qualification & EPT_VIOLATION_GVA_TRANSLATED) != 0 ? - PFERR_GUEST_FINAL_MASK : PFERR_GUEST_PAGE_MASK; + if (error_code & EPT_VIOLATION_GVA_IS_VALID) + error_code |= (exit_qualification & EPT_VIOLATION_GVA_TRANSLATED) ? + PFERR_GUEST_FINAL_MASK : PFERR_GUEST_PAGE_MASK; /* * Check that the GPA doesn't exceed physical memory limits, as that is @@ -7265,6 +7269,8 @@ static fastpath_t vmx_exit_handlers_fastpath(struct kvm_vcpu *vcpu, return handle_fastpath_set_msr_irqoff(vcpu); case EXIT_REASON_PREEMPTION_TIMER: return handle_fastpath_preemption_timer(vcpu, force_immediate_exit); + case EXIT_REASON_HLT: + return handle_fastpath_hlt(vcpu); default: return EXIT_FASTPATH_NONE; } @@ -7965,6 +7971,7 @@ static __init void vmx_set_cpu_caps(void) kvm_cpu_cap_clear(X86_FEATURE_SGX_LC); kvm_cpu_cap_clear(X86_FEATURE_SGX1); kvm_cpu_cap_clear(X86_FEATURE_SGX2); + kvm_cpu_cap_clear(X86_FEATURE_SGX_EDECCSSA); } if (vmx_umip_emulated()) @@ -8515,7 +8522,7 @@ __init int vmx_hardware_setup(void) u64 use_timer_freq = 5000ULL * 1000 * 1000; cpu_preemption_timer_multi = - vmcs_config.misc & VMX_MISC_PREEMPTION_TIMER_RATE_MASK; + vmx_misc_preemption_timer_rate(vmcs_config.misc); if (tsc_khz) use_timer_freq = (u64)tsc_khz * 1000; @@ -8582,8 +8589,6 @@ static void __vmx_exit(void) { allow_smaller_maxphyaddr = false; - cpu_emergency_unregister_virt_callback(vmx_emergency_disable); - vmx_cleanup_l1d_flush(); } @@ -8630,8 +8635,6 @@ static int __init vmx_init(void) pi_init_cpu(cpu); } - cpu_emergency_register_virt_callback(vmx_emergency_disable); - vmx_check_vmcs12_offsets(); /* diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 42498fa63abb..2325f773a20b 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -17,10 +17,6 @@ #include "run_flags.h" #include "../mmu.h" -#define MSR_TYPE_R 1 -#define MSR_TYPE_W 2 -#define MSR_TYPE_RW 3 - #define X2APIC_MSR(r) (APIC_BASE_MSR + ((r) >> 4)) #ifdef CONFIG_X86_64 @@ -756,4 +752,9 @@ static inline bool vmx_can_use_ipiv(struct kvm_vcpu *vcpu) return lapic_in_kernel(vcpu) && enable_ipiv; } +static inline void vmx_segment_cache_clear(struct vcpu_vmx *vmx) +{ + vmx->segment_cache.bitmask = 0; +} + #endif /* __KVM_X86_VMX_H */ diff --git a/arch/x86/kvm/vmx/vmx_onhyperv.h b/arch/x86/kvm/vmx/vmx_onhyperv.h index eb48153bfd73..bba24ed99ee6 100644 --- a/arch/x86/kvm/vmx/vmx_onhyperv.h +++ b/arch/x86/kvm/vmx/vmx_onhyperv.h @@ -104,6 +104,14 @@ static inline void evmcs_load(u64 phys_addr) struct hv_vp_assist_page *vp_ap = hv_get_vp_assist_page(smp_processor_id()); + /* + * When enabling eVMCS, KVM verifies that every CPU has a valid hv_vp_assist_page() + * and aborts enabling the feature otherwise. CPU onlining path is also checked in + * vmx_hardware_enable(). + */ + if (KVM_BUG_ON(!vp_ap, kvm_get_running_vcpu()->kvm)) + return; + if (current_evmcs->hv_enlightenments_control.nested_flush_hypercall) vp_ap->nested_control.features.directhypercall = 1; vp_ap->current_nested_vmcs = phys_addr; diff --git a/arch/x86/kvm/vmx/vmx_ops.h b/arch/x86/kvm/vmx/vmx_ops.h index 8060e5fc6dbd..93e020dc88f6 100644 --- a/arch/x86/kvm/vmx/vmx_ops.h +++ b/arch/x86/kvm/vmx/vmx_ops.h @@ -47,7 +47,7 @@ static __always_inline void vmcs_check16(unsigned long field) BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6001) == 0x2001, "16-bit accessor invalid for 64-bit high field"); BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x4000, - "16-bit accessor invalid for 32-bit high field"); + "16-bit accessor invalid for 32-bit field"); BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x6000, "16-bit accessor invalid for natural width field"); } diff --git a/arch/x86/kvm/vmx/x86_ops.h b/arch/x86/kvm/vmx/x86_ops.h index ce3221cd1d01..a55981c5216e 100644 --- a/arch/x86/kvm/vmx/x86_ops.h +++ b/arch/x86/kvm/vmx/x86_ops.h @@ -13,8 +13,9 @@ extern struct kvm_x86_init_ops vt_init_ops __initdata; void vmx_hardware_unsetup(void); int vmx_check_processor_compat(void); -int vmx_hardware_enable(void); -void vmx_hardware_disable(void); +int vmx_enable_virtualization_cpu(void); +void vmx_disable_virtualization_cpu(void); +void vmx_emergency_disable_virtualization_cpu(void); int vmx_vm_init(struct kvm *kvm); void vmx_vm_destroy(struct kvm *kvm); int vmx_vcpu_precreate(struct kvm *kvm); @@ -56,7 +57,7 @@ bool vmx_has_emulated_msr(struct kvm *kvm, u32 index); void vmx_msr_filter_changed(struct kvm_vcpu *vcpu); void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu); void vmx_update_exception_bitmap(struct kvm_vcpu *vcpu); -int vmx_get_msr_feature(struct kvm_msr_entry *msr); +int vmx_get_feature_msr(u32 msr, u64 *data); int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info); u64 vmx_get_segment_base(struct kvm_vcpu *vcpu, int seg); void vmx_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index c983c8e434b8..83fe0a78146f 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -305,24 +305,237 @@ const struct kvm_stats_header kvm_vcpu_stats_header = { static struct kmem_cache *x86_emulator_cache; /* - * When called, it means the previous get/set msr reached an invalid msr. - * Return true if we want to ignore/silent this failed msr access. + * The three MSR lists(msrs_to_save, emulated_msrs, msr_based_features) track + * the set of MSRs that KVM exposes to userspace through KVM_GET_MSRS, + * KVM_SET_MSRS, and KVM_GET_MSR_INDEX_LIST. msrs_to_save holds MSRs that + * require host support, i.e. should be probed via RDMSR. emulated_msrs holds + * MSRs that KVM emulates without strictly requiring host support. + * msr_based_features holds MSRs that enumerate features, i.e. are effectively + * CPUID leafs. Note, msr_based_features isn't mutually exclusive with + * msrs_to_save and emulated_msrs. */ -static bool kvm_msr_ignored_check(u32 msr, u64 data, bool write) + +static const u32 msrs_to_save_base[] = { + MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP, + MSR_STAR, +#ifdef CONFIG_X86_64 + MSR_CSTAR, MSR_KERNEL_GS_BASE, MSR_SYSCALL_MASK, MSR_LSTAR, +#endif + MSR_IA32_TSC, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA, + MSR_IA32_FEAT_CTL, MSR_IA32_BNDCFGS, MSR_TSC_AUX, + MSR_IA32_SPEC_CTRL, MSR_IA32_TSX_CTRL, + MSR_IA32_RTIT_CTL, MSR_IA32_RTIT_STATUS, MSR_IA32_RTIT_CR3_MATCH, + MSR_IA32_RTIT_OUTPUT_BASE, MSR_IA32_RTIT_OUTPUT_MASK, + MSR_IA32_RTIT_ADDR0_A, MSR_IA32_RTIT_ADDR0_B, + MSR_IA32_RTIT_ADDR1_A, MSR_IA32_RTIT_ADDR1_B, + MSR_IA32_RTIT_ADDR2_A, MSR_IA32_RTIT_ADDR2_B, + MSR_IA32_RTIT_ADDR3_A, MSR_IA32_RTIT_ADDR3_B, + MSR_IA32_UMWAIT_CONTROL, + + MSR_IA32_XFD, MSR_IA32_XFD_ERR, +}; + +static const u32 msrs_to_save_pmu[] = { + MSR_ARCH_PERFMON_FIXED_CTR0, MSR_ARCH_PERFMON_FIXED_CTR1, + MSR_ARCH_PERFMON_FIXED_CTR0 + 2, + MSR_CORE_PERF_FIXED_CTR_CTRL, MSR_CORE_PERF_GLOBAL_STATUS, + MSR_CORE_PERF_GLOBAL_CTRL, + MSR_IA32_PEBS_ENABLE, MSR_IA32_DS_AREA, MSR_PEBS_DATA_CFG, + + /* This part of MSRs should match KVM_MAX_NR_INTEL_GP_COUNTERS. */ + MSR_ARCH_PERFMON_PERFCTR0, MSR_ARCH_PERFMON_PERFCTR1, + MSR_ARCH_PERFMON_PERFCTR0 + 2, MSR_ARCH_PERFMON_PERFCTR0 + 3, + MSR_ARCH_PERFMON_PERFCTR0 + 4, MSR_ARCH_PERFMON_PERFCTR0 + 5, + MSR_ARCH_PERFMON_PERFCTR0 + 6, MSR_ARCH_PERFMON_PERFCTR0 + 7, + MSR_ARCH_PERFMON_EVENTSEL0, MSR_ARCH_PERFMON_EVENTSEL1, + MSR_ARCH_PERFMON_EVENTSEL0 + 2, MSR_ARCH_PERFMON_EVENTSEL0 + 3, + MSR_ARCH_PERFMON_EVENTSEL0 + 4, MSR_ARCH_PERFMON_EVENTSEL0 + 5, + MSR_ARCH_PERFMON_EVENTSEL0 + 6, MSR_ARCH_PERFMON_EVENTSEL0 + 7, + + MSR_K7_EVNTSEL0, MSR_K7_EVNTSEL1, MSR_K7_EVNTSEL2, MSR_K7_EVNTSEL3, + MSR_K7_PERFCTR0, MSR_K7_PERFCTR1, MSR_K7_PERFCTR2, MSR_K7_PERFCTR3, + + /* This part of MSRs should match KVM_MAX_NR_AMD_GP_COUNTERS. */ + MSR_F15H_PERF_CTL0, MSR_F15H_PERF_CTL1, MSR_F15H_PERF_CTL2, + MSR_F15H_PERF_CTL3, MSR_F15H_PERF_CTL4, MSR_F15H_PERF_CTL5, + MSR_F15H_PERF_CTR0, MSR_F15H_PERF_CTR1, MSR_F15H_PERF_CTR2, + MSR_F15H_PERF_CTR3, MSR_F15H_PERF_CTR4, MSR_F15H_PERF_CTR5, + + MSR_AMD64_PERF_CNTR_GLOBAL_CTL, + MSR_AMD64_PERF_CNTR_GLOBAL_STATUS, + MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR, +}; + +static u32 msrs_to_save[ARRAY_SIZE(msrs_to_save_base) + + ARRAY_SIZE(msrs_to_save_pmu)]; +static unsigned num_msrs_to_save; + +static const u32 emulated_msrs_all[] = { + MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK, + MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW, + +#ifdef CONFIG_KVM_HYPERV + HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL, + HV_X64_MSR_TIME_REF_COUNT, HV_X64_MSR_REFERENCE_TSC, + HV_X64_MSR_TSC_FREQUENCY, HV_X64_MSR_APIC_FREQUENCY, + HV_X64_MSR_CRASH_P0, HV_X64_MSR_CRASH_P1, HV_X64_MSR_CRASH_P2, + HV_X64_MSR_CRASH_P3, HV_X64_MSR_CRASH_P4, HV_X64_MSR_CRASH_CTL, + HV_X64_MSR_RESET, + HV_X64_MSR_VP_INDEX, + HV_X64_MSR_VP_RUNTIME, + HV_X64_MSR_SCONTROL, + HV_X64_MSR_STIMER0_CONFIG, + HV_X64_MSR_VP_ASSIST_PAGE, + HV_X64_MSR_REENLIGHTENMENT_CONTROL, HV_X64_MSR_TSC_EMULATION_CONTROL, + HV_X64_MSR_TSC_EMULATION_STATUS, HV_X64_MSR_TSC_INVARIANT_CONTROL, + HV_X64_MSR_SYNDBG_OPTIONS, + HV_X64_MSR_SYNDBG_CONTROL, HV_X64_MSR_SYNDBG_STATUS, + HV_X64_MSR_SYNDBG_SEND_BUFFER, HV_X64_MSR_SYNDBG_RECV_BUFFER, + HV_X64_MSR_SYNDBG_PENDING_BUFFER, +#endif + + MSR_KVM_ASYNC_PF_EN, MSR_KVM_STEAL_TIME, + MSR_KVM_PV_EOI_EN, MSR_KVM_ASYNC_PF_INT, MSR_KVM_ASYNC_PF_ACK, + + MSR_IA32_TSC_ADJUST, + MSR_IA32_TSC_DEADLINE, + MSR_IA32_ARCH_CAPABILITIES, + MSR_IA32_PERF_CAPABILITIES, + MSR_IA32_MISC_ENABLE, + MSR_IA32_MCG_STATUS, + MSR_IA32_MCG_CTL, + MSR_IA32_MCG_EXT_CTL, + MSR_IA32_SMBASE, + MSR_SMI_COUNT, + MSR_PLATFORM_INFO, + MSR_MISC_FEATURES_ENABLES, + MSR_AMD64_VIRT_SPEC_CTRL, + MSR_AMD64_TSC_RATIO, + MSR_IA32_POWER_CTL, + MSR_IA32_UCODE_REV, + + /* + * KVM always supports the "true" VMX control MSRs, even if the host + * does not. The VMX MSRs as a whole are considered "emulated" as KVM + * doesn't strictly require them to exist in the host (ignoring that + * KVM would refuse to load in the first place if the core set of MSRs + * aren't supported). + */ + MSR_IA32_VMX_BASIC, + MSR_IA32_VMX_TRUE_PINBASED_CTLS, + MSR_IA32_VMX_TRUE_PROCBASED_CTLS, + MSR_IA32_VMX_TRUE_EXIT_CTLS, + MSR_IA32_VMX_TRUE_ENTRY_CTLS, + MSR_IA32_VMX_MISC, + MSR_IA32_VMX_CR0_FIXED0, + MSR_IA32_VMX_CR4_FIXED0, + MSR_IA32_VMX_VMCS_ENUM, + MSR_IA32_VMX_PROCBASED_CTLS2, + MSR_IA32_VMX_EPT_VPID_CAP, + MSR_IA32_VMX_VMFUNC, + + MSR_K7_HWCR, + MSR_KVM_POLL_CONTROL, +}; + +static u32 emulated_msrs[ARRAY_SIZE(emulated_msrs_all)]; +static unsigned num_emulated_msrs; + +/* + * List of MSRs that control the existence of MSR-based features, i.e. MSRs + * that are effectively CPUID leafs. VMX MSRs are also included in the set of + * feature MSRs, but are handled separately to allow expedited lookups. + */ +static const u32 msr_based_features_all_except_vmx[] = { + MSR_AMD64_DE_CFG, + MSR_IA32_UCODE_REV, + MSR_IA32_ARCH_CAPABILITIES, + MSR_IA32_PERF_CAPABILITIES, +}; + +static u32 msr_based_features[ARRAY_SIZE(msr_based_features_all_except_vmx) + + (KVM_LAST_EMULATED_VMX_MSR - KVM_FIRST_EMULATED_VMX_MSR + 1)]; +static unsigned int num_msr_based_features; + +/* + * All feature MSRs except uCode revID, which tracks the currently loaded uCode + * patch, are immutable once the vCPU model is defined. + */ +static bool kvm_is_immutable_feature_msr(u32 msr) { - const char *op = write ? "wrmsr" : "rdmsr"; + int i; - if (ignore_msrs) { - if (report_ignored_msrs) - kvm_pr_unimpl("ignored %s: 0x%x data 0x%llx\n", - op, msr, data); - /* Mask the error */ + if (msr >= KVM_FIRST_EMULATED_VMX_MSR && msr <= KVM_LAST_EMULATED_VMX_MSR) return true; - } else { + + for (i = 0; i < ARRAY_SIZE(msr_based_features_all_except_vmx); i++) { + if (msr == msr_based_features_all_except_vmx[i]) + return msr != MSR_IA32_UCODE_REV; + } + + return false; +} + +static bool kvm_is_advertised_msr(u32 msr_index) +{ + unsigned int i; + + for (i = 0; i < num_msrs_to_save; i++) { + if (msrs_to_save[i] == msr_index) + return true; + } + + for (i = 0; i < num_emulated_msrs; i++) { + if (emulated_msrs[i] == msr_index) + return true; + } + + return false; +} + +typedef int (*msr_access_t)(struct kvm_vcpu *vcpu, u32 index, u64 *data, + bool host_initiated); + +static __always_inline int kvm_do_msr_access(struct kvm_vcpu *vcpu, u32 msr, + u64 *data, bool host_initiated, + enum kvm_msr_access rw, + msr_access_t msr_access_fn) +{ + const char *op = rw == MSR_TYPE_W ? "wrmsr" : "rdmsr"; + int ret; + + BUILD_BUG_ON(rw != MSR_TYPE_R && rw != MSR_TYPE_W); + + /* + * Zero the data on read failures to avoid leaking stack data to the + * guest and/or userspace, e.g. if the failure is ignored below. + */ + ret = msr_access_fn(vcpu, msr, data, host_initiated); + if (ret && rw == MSR_TYPE_R) + *data = 0; + + if (ret != KVM_MSR_RET_UNSUPPORTED) + return ret; + + /* + * Userspace is allowed to read MSRs, and write '0' to MSRs, that KVM + * advertises to userspace, even if an MSR isn't fully supported. + * Simply check that @data is '0', which covers both the write '0' case + * and all reads (in which case @data is zeroed on failure; see above). + */ + if (host_initiated && !*data && kvm_is_advertised_msr(msr)) + return 0; + + if (!ignore_msrs) { kvm_debug_ratelimited("unhandled %s: 0x%x data 0x%llx\n", - op, msr, data); - return false; + op, msr, *data); + return ret; } + + if (report_ignored_msrs) + kvm_pr_unimpl("ignored %s: 0x%x data 0x%llx\n", op, msr, *data); + + return 0; } static struct kmem_cache *kvm_alloc_emulator_cache(void) @@ -355,7 +568,7 @@ static void kvm_on_user_return(struct user_return_notifier *urn) /* * Disabling irqs at this point since the following code could be - * interrupted and executed through kvm_arch_hardware_disable() + * interrupted and executed through kvm_arch_disable_virtualization_cpu() */ local_irq_save(flags); if (msrs->registered) { @@ -413,8 +626,7 @@ EXPORT_SYMBOL_GPL(kvm_find_user_return_msr); static void kvm_user_return_msr_cpu_online(void) { - unsigned int cpu = smp_processor_id(); - struct kvm_user_return_msrs *msrs = per_cpu_ptr(user_return_msrs, cpu); + struct kvm_user_return_msrs *msrs = this_cpu_ptr(user_return_msrs); u64 value; int i; @@ -621,12 +833,6 @@ static void kvm_queue_exception_vmexit(struct kvm_vcpu *vcpu, unsigned int vecto ex->payload = payload; } -/* Forcibly leave the nested mode in cases like a vCPU reset */ -static void kvm_leave_nested(struct kvm_vcpu *vcpu) -{ - kvm_x86_ops.nested_ops->leave_nested(vcpu); -} - static void kvm_multiple_exception(struct kvm_vcpu *vcpu, unsigned nr, bool has_error, u32 error_code, bool has_payload, unsigned long payload, bool reinject) @@ -1412,178 +1618,6 @@ int kvm_emulate_rdpmc(struct kvm_vcpu *vcpu) EXPORT_SYMBOL_GPL(kvm_emulate_rdpmc); /* - * The three MSR lists(msrs_to_save, emulated_msrs, msr_based_features) track - * the set of MSRs that KVM exposes to userspace through KVM_GET_MSRS, - * KVM_SET_MSRS, and KVM_GET_MSR_INDEX_LIST. msrs_to_save holds MSRs that - * require host support, i.e. should be probed via RDMSR. emulated_msrs holds - * MSRs that KVM emulates without strictly requiring host support. - * msr_based_features holds MSRs that enumerate features, i.e. are effectively - * CPUID leafs. Note, msr_based_features isn't mutually exclusive with - * msrs_to_save and emulated_msrs. - */ - -static const u32 msrs_to_save_base[] = { - MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP, - MSR_STAR, -#ifdef CONFIG_X86_64 - MSR_CSTAR, MSR_KERNEL_GS_BASE, MSR_SYSCALL_MASK, MSR_LSTAR, -#endif - MSR_IA32_TSC, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA, - MSR_IA32_FEAT_CTL, MSR_IA32_BNDCFGS, MSR_TSC_AUX, - MSR_IA32_SPEC_CTRL, MSR_IA32_TSX_CTRL, - MSR_IA32_RTIT_CTL, MSR_IA32_RTIT_STATUS, MSR_IA32_RTIT_CR3_MATCH, - MSR_IA32_RTIT_OUTPUT_BASE, MSR_IA32_RTIT_OUTPUT_MASK, - MSR_IA32_RTIT_ADDR0_A, MSR_IA32_RTIT_ADDR0_B, - MSR_IA32_RTIT_ADDR1_A, MSR_IA32_RTIT_ADDR1_B, - MSR_IA32_RTIT_ADDR2_A, MSR_IA32_RTIT_ADDR2_B, - MSR_IA32_RTIT_ADDR3_A, MSR_IA32_RTIT_ADDR3_B, - MSR_IA32_UMWAIT_CONTROL, - - MSR_IA32_XFD, MSR_IA32_XFD_ERR, -}; - -static const u32 msrs_to_save_pmu[] = { - MSR_ARCH_PERFMON_FIXED_CTR0, MSR_ARCH_PERFMON_FIXED_CTR1, - MSR_ARCH_PERFMON_FIXED_CTR0 + 2, - MSR_CORE_PERF_FIXED_CTR_CTRL, MSR_CORE_PERF_GLOBAL_STATUS, - MSR_CORE_PERF_GLOBAL_CTRL, - MSR_IA32_PEBS_ENABLE, MSR_IA32_DS_AREA, MSR_PEBS_DATA_CFG, - - /* This part of MSRs should match KVM_MAX_NR_INTEL_GP_COUNTERS. */ - MSR_ARCH_PERFMON_PERFCTR0, MSR_ARCH_PERFMON_PERFCTR1, - MSR_ARCH_PERFMON_PERFCTR0 + 2, MSR_ARCH_PERFMON_PERFCTR0 + 3, - MSR_ARCH_PERFMON_PERFCTR0 + 4, MSR_ARCH_PERFMON_PERFCTR0 + 5, - MSR_ARCH_PERFMON_PERFCTR0 + 6, MSR_ARCH_PERFMON_PERFCTR0 + 7, - MSR_ARCH_PERFMON_EVENTSEL0, MSR_ARCH_PERFMON_EVENTSEL1, - MSR_ARCH_PERFMON_EVENTSEL0 + 2, MSR_ARCH_PERFMON_EVENTSEL0 + 3, - MSR_ARCH_PERFMON_EVENTSEL0 + 4, MSR_ARCH_PERFMON_EVENTSEL0 + 5, - MSR_ARCH_PERFMON_EVENTSEL0 + 6, MSR_ARCH_PERFMON_EVENTSEL0 + 7, - - MSR_K7_EVNTSEL0, MSR_K7_EVNTSEL1, MSR_K7_EVNTSEL2, MSR_K7_EVNTSEL3, - MSR_K7_PERFCTR0, MSR_K7_PERFCTR1, MSR_K7_PERFCTR2, MSR_K7_PERFCTR3, - - /* This part of MSRs should match KVM_MAX_NR_AMD_GP_COUNTERS. */ - MSR_F15H_PERF_CTL0, MSR_F15H_PERF_CTL1, MSR_F15H_PERF_CTL2, - MSR_F15H_PERF_CTL3, MSR_F15H_PERF_CTL4, MSR_F15H_PERF_CTL5, - MSR_F15H_PERF_CTR0, MSR_F15H_PERF_CTR1, MSR_F15H_PERF_CTR2, - MSR_F15H_PERF_CTR3, MSR_F15H_PERF_CTR4, MSR_F15H_PERF_CTR5, - - MSR_AMD64_PERF_CNTR_GLOBAL_CTL, - MSR_AMD64_PERF_CNTR_GLOBAL_STATUS, - MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR, -}; - -static u32 msrs_to_save[ARRAY_SIZE(msrs_to_save_base) + - ARRAY_SIZE(msrs_to_save_pmu)]; -static unsigned num_msrs_to_save; - -static const u32 emulated_msrs_all[] = { - MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK, - MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW, - -#ifdef CONFIG_KVM_HYPERV - HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL, - HV_X64_MSR_TIME_REF_COUNT, HV_X64_MSR_REFERENCE_TSC, - HV_X64_MSR_TSC_FREQUENCY, HV_X64_MSR_APIC_FREQUENCY, - HV_X64_MSR_CRASH_P0, HV_X64_MSR_CRASH_P1, HV_X64_MSR_CRASH_P2, - HV_X64_MSR_CRASH_P3, HV_X64_MSR_CRASH_P4, HV_X64_MSR_CRASH_CTL, - HV_X64_MSR_RESET, - HV_X64_MSR_VP_INDEX, - HV_X64_MSR_VP_RUNTIME, - HV_X64_MSR_SCONTROL, - HV_X64_MSR_STIMER0_CONFIG, - HV_X64_MSR_VP_ASSIST_PAGE, - HV_X64_MSR_REENLIGHTENMENT_CONTROL, HV_X64_MSR_TSC_EMULATION_CONTROL, - HV_X64_MSR_TSC_EMULATION_STATUS, HV_X64_MSR_TSC_INVARIANT_CONTROL, - HV_X64_MSR_SYNDBG_OPTIONS, - HV_X64_MSR_SYNDBG_CONTROL, HV_X64_MSR_SYNDBG_STATUS, - HV_X64_MSR_SYNDBG_SEND_BUFFER, HV_X64_MSR_SYNDBG_RECV_BUFFER, - HV_X64_MSR_SYNDBG_PENDING_BUFFER, -#endif - - MSR_KVM_ASYNC_PF_EN, MSR_KVM_STEAL_TIME, - MSR_KVM_PV_EOI_EN, MSR_KVM_ASYNC_PF_INT, MSR_KVM_ASYNC_PF_ACK, - - MSR_IA32_TSC_ADJUST, - MSR_IA32_TSC_DEADLINE, - MSR_IA32_ARCH_CAPABILITIES, - MSR_IA32_PERF_CAPABILITIES, - MSR_IA32_MISC_ENABLE, - MSR_IA32_MCG_STATUS, - MSR_IA32_MCG_CTL, - MSR_IA32_MCG_EXT_CTL, - MSR_IA32_SMBASE, - MSR_SMI_COUNT, - MSR_PLATFORM_INFO, - MSR_MISC_FEATURES_ENABLES, - MSR_AMD64_VIRT_SPEC_CTRL, - MSR_AMD64_TSC_RATIO, - MSR_IA32_POWER_CTL, - MSR_IA32_UCODE_REV, - - /* - * KVM always supports the "true" VMX control MSRs, even if the host - * does not. The VMX MSRs as a whole are considered "emulated" as KVM - * doesn't strictly require them to exist in the host (ignoring that - * KVM would refuse to load in the first place if the core set of MSRs - * aren't supported). - */ - MSR_IA32_VMX_BASIC, - MSR_IA32_VMX_TRUE_PINBASED_CTLS, - MSR_IA32_VMX_TRUE_PROCBASED_CTLS, - MSR_IA32_VMX_TRUE_EXIT_CTLS, - MSR_IA32_VMX_TRUE_ENTRY_CTLS, - MSR_IA32_VMX_MISC, - MSR_IA32_VMX_CR0_FIXED0, - MSR_IA32_VMX_CR4_FIXED0, - MSR_IA32_VMX_VMCS_ENUM, - MSR_IA32_VMX_PROCBASED_CTLS2, - MSR_IA32_VMX_EPT_VPID_CAP, - MSR_IA32_VMX_VMFUNC, - - MSR_K7_HWCR, - MSR_KVM_POLL_CONTROL, -}; - -static u32 emulated_msrs[ARRAY_SIZE(emulated_msrs_all)]; -static unsigned num_emulated_msrs; - -/* - * List of MSRs that control the existence of MSR-based features, i.e. MSRs - * that are effectively CPUID leafs. VMX MSRs are also included in the set of - * feature MSRs, but are handled separately to allow expedited lookups. - */ -static const u32 msr_based_features_all_except_vmx[] = { - MSR_AMD64_DE_CFG, - MSR_IA32_UCODE_REV, - MSR_IA32_ARCH_CAPABILITIES, - MSR_IA32_PERF_CAPABILITIES, -}; - -static u32 msr_based_features[ARRAY_SIZE(msr_based_features_all_except_vmx) + - (KVM_LAST_EMULATED_VMX_MSR - KVM_FIRST_EMULATED_VMX_MSR + 1)]; -static unsigned int num_msr_based_features; - -/* - * All feature MSRs except uCode revID, which tracks the currently loaded uCode - * patch, are immutable once the vCPU model is defined. - */ -static bool kvm_is_immutable_feature_msr(u32 msr) -{ - int i; - - if (msr >= KVM_FIRST_EMULATED_VMX_MSR && msr <= KVM_LAST_EMULATED_VMX_MSR) - return true; - - for (i = 0; i < ARRAY_SIZE(msr_based_features_all_except_vmx); i++) { - if (msr == msr_based_features_all_except_vmx[i]) - return msr != MSR_IA32_UCODE_REV; - } - - return false; -} - -/* * Some IA32_ARCH_CAPABILITIES bits have dependencies on MSRs that KVM * does not yet virtualize. These include: * 10 - MISC_PACKAGE_CTRLS @@ -1660,40 +1694,31 @@ static u64 kvm_get_arch_capabilities(void) return data; } -static int kvm_get_msr_feature(struct kvm_msr_entry *msr) +static int kvm_get_feature_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data, + bool host_initiated) { - switch (msr->index) { + WARN_ON_ONCE(!host_initiated); + + switch (index) { case MSR_IA32_ARCH_CAPABILITIES: - msr->data = kvm_get_arch_capabilities(); + *data = kvm_get_arch_capabilities(); break; case MSR_IA32_PERF_CAPABILITIES: - msr->data = kvm_caps.supported_perf_cap; + *data = kvm_caps.supported_perf_cap; break; case MSR_IA32_UCODE_REV: - rdmsrl_safe(msr->index, &msr->data); + rdmsrl_safe(index, data); break; default: - return kvm_x86_call(get_msr_feature)(msr); + return kvm_x86_call(get_feature_msr)(index, data); } return 0; } -static int do_get_msr_feature(struct kvm_vcpu *vcpu, unsigned index, u64 *data) +static int do_get_feature_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data) { - struct kvm_msr_entry msr; - int r; - - /* Unconditionally clear the output for simplicity */ - msr.data = 0; - msr.index = index; - r = kvm_get_msr_feature(&msr); - - if (r == KVM_MSR_RET_INVALID && kvm_msr_ignored_check(index, 0, false)) - r = 0; - - *data = msr.data; - - return r; + return kvm_do_msr_access(vcpu, index, data, true, MSR_TYPE_R, + kvm_get_feature_msr); } static bool __kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer) @@ -1880,16 +1905,17 @@ static int __kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data, return kvm_x86_call(set_msr)(vcpu, &msr); } +static int _kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data, + bool host_initiated) +{ + return __kvm_set_msr(vcpu, index, *data, host_initiated); +} + static int kvm_set_msr_ignored_check(struct kvm_vcpu *vcpu, u32 index, u64 data, bool host_initiated) { - int ret = __kvm_set_msr(vcpu, index, data, host_initiated); - - if (ret == KVM_MSR_RET_INVALID) - if (kvm_msr_ignored_check(index, data, true)) - ret = 0; - - return ret; + return kvm_do_msr_access(vcpu, index, &data, host_initiated, MSR_TYPE_W, + _kvm_set_msr); } /* @@ -1928,31 +1954,25 @@ int __kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data, static int kvm_get_msr_ignored_check(struct kvm_vcpu *vcpu, u32 index, u64 *data, bool host_initiated) { - int ret = __kvm_get_msr(vcpu, index, data, host_initiated); - - if (ret == KVM_MSR_RET_INVALID) { - /* Unconditionally clear *data for simplicity */ - *data = 0; - if (kvm_msr_ignored_check(index, 0, false)) - ret = 0; - } - - return ret; + return kvm_do_msr_access(vcpu, index, data, host_initiated, MSR_TYPE_R, + __kvm_get_msr); } -static int kvm_get_msr_with_filter(struct kvm_vcpu *vcpu, u32 index, u64 *data) +int kvm_get_msr_with_filter(struct kvm_vcpu *vcpu, u32 index, u64 *data) { if (!kvm_msr_allowed(vcpu, index, KVM_MSR_FILTER_READ)) return KVM_MSR_RET_FILTERED; return kvm_get_msr_ignored_check(vcpu, index, data, false); } +EXPORT_SYMBOL_GPL(kvm_get_msr_with_filter); -static int kvm_set_msr_with_filter(struct kvm_vcpu *vcpu, u32 index, u64 data) +int kvm_set_msr_with_filter(struct kvm_vcpu *vcpu, u32 index, u64 data) { if (!kvm_msr_allowed(vcpu, index, KVM_MSR_FILTER_WRITE)) return KVM_MSR_RET_FILTERED; return kvm_set_msr_ignored_check(vcpu, index, data, false); } +EXPORT_SYMBOL_GPL(kvm_set_msr_with_filter); int kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data) { @@ -1999,7 +2019,7 @@ static int complete_fast_rdmsr(struct kvm_vcpu *vcpu) static u64 kvm_msr_reason(int r) { switch (r) { - case KVM_MSR_RET_INVALID: + case KVM_MSR_RET_UNSUPPORTED: return KVM_MSR_EXIT_REASON_UNKNOWN; case KVM_MSR_RET_FILTERED: return KVM_MSR_EXIT_REASON_FILTER; @@ -2162,31 +2182,34 @@ fastpath_t handle_fastpath_set_msr_irqoff(struct kvm_vcpu *vcpu) { u32 msr = kvm_rcx_read(vcpu); u64 data; - fastpath_t ret = EXIT_FASTPATH_NONE; + fastpath_t ret; + bool handled; kvm_vcpu_srcu_read_lock(vcpu); switch (msr) { case APIC_BASE_MSR + (APIC_ICR >> 4): data = kvm_read_edx_eax(vcpu); - if (!handle_fastpath_set_x2apic_icr_irqoff(vcpu, data)) { - kvm_skip_emulated_instruction(vcpu); - ret = EXIT_FASTPATH_EXIT_HANDLED; - } + handled = !handle_fastpath_set_x2apic_icr_irqoff(vcpu, data); break; case MSR_IA32_TSC_DEADLINE: data = kvm_read_edx_eax(vcpu); - if (!handle_fastpath_set_tscdeadline(vcpu, data)) { - kvm_skip_emulated_instruction(vcpu); - ret = EXIT_FASTPATH_REENTER_GUEST; - } + handled = !handle_fastpath_set_tscdeadline(vcpu, data); break; default: + handled = false; break; } - if (ret != EXIT_FASTPATH_NONE) + if (handled) { + if (!kvm_skip_emulated_instruction(vcpu)) + ret = EXIT_FASTPATH_EXIT_USERSPACE; + else + ret = EXIT_FASTPATH_REENTER_GUEST; trace_kvm_msr_write(msr, data); + } else { + ret = EXIT_FASTPATH_NONE; + } kvm_vcpu_srcu_read_unlock(vcpu); @@ -3746,18 +3769,6 @@ static void record_steal_time(struct kvm_vcpu *vcpu) mark_page_dirty_in_slot(vcpu->kvm, ghc->memslot, gpa_to_gfn(ghc->gpa)); } -static bool kvm_is_msr_to_save(u32 msr_index) -{ - unsigned int i; - - for (i = 0; i < num_msrs_to_save; i++) { - if (msrs_to_save[i] == msr_index) - return true; - } - - return false; -} - int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { u32 msr = msr_info->index; @@ -4139,15 +4150,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (kvm_pmu_is_valid_msr(vcpu, msr)) return kvm_pmu_set_msr(vcpu, msr_info); - /* - * Userspace is allowed to write '0' to MSRs that KVM reports - * as to-be-saved, even if an MSRs isn't fully supported. - */ - if (msr_info->host_initiated && !data && - kvm_is_msr_to_save(msr)) - break; - - return KVM_MSR_RET_INVALID; + return KVM_MSR_RET_UNSUPPORTED; } return 0; } @@ -4498,17 +4501,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (kvm_pmu_is_valid_msr(vcpu, msr_info->index)) return kvm_pmu_get_msr(vcpu, msr_info); - /* - * Userspace is allowed to read MSRs that KVM reports as - * to-be-saved, even if an MSR isn't fully supported. - */ - if (msr_info->host_initiated && - kvm_is_msr_to_save(msr_info->index)) { - msr_info->data = 0; - break; - } - - return KVM_MSR_RET_INVALID; + return KVM_MSR_RET_UNSUPPORTED; } return 0; } @@ -4946,7 +4939,7 @@ long kvm_arch_dev_ioctl(struct file *filp, break; } case KVM_GET_MSRS: - r = msr_io(NULL, argp, do_get_msr_feature, 1); + r = msr_io(NULL, argp, do_get_feature_msr, 1); break; #ifdef CONFIG_KVM_HYPERV case KVM_GET_SUPPORTED_HV_CPUID: @@ -7383,11 +7376,9 @@ out: static void kvm_probe_feature_msr(u32 msr_index) { - struct kvm_msr_entry msr = { - .index = msr_index, - }; + u64 data; - if (kvm_get_msr_feature(&msr)) + if (kvm_get_feature_msr(NULL, msr_index, &data, true)) return; msr_based_features[num_msr_based_features++] = msr_index; @@ -8865,60 +8856,13 @@ static int handle_emulation_failure(struct kvm_vcpu *vcpu, int emulation_type) return 1; } -static bool reexecute_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, - int emulation_type) +static bool kvm_unprotect_and_retry_on_failure(struct kvm_vcpu *vcpu, + gpa_t cr2_or_gpa, + int emulation_type) { - gpa_t gpa = cr2_or_gpa; - kvm_pfn_t pfn; - if (!(emulation_type & EMULTYPE_ALLOW_RETRY_PF)) return false; - if (WARN_ON_ONCE(is_guest_mode(vcpu)) || - WARN_ON_ONCE(!(emulation_type & EMULTYPE_PF))) - return false; - - if (!vcpu->arch.mmu->root_role.direct) { - /* - * Write permission should be allowed since only - * write access need to be emulated. - */ - gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2_or_gpa, NULL); - - /* - * If the mapping is invalid in guest, let cpu retry - * it to generate fault. - */ - if (gpa == INVALID_GPA) - return true; - } - - /* - * Do not retry the unhandleable instruction if it faults on the - * readonly host memory, otherwise it will goto a infinite loop: - * retry instruction -> write #PF -> emulation fail -> retry - * instruction -> ... - */ - pfn = gfn_to_pfn(vcpu->kvm, gpa_to_gfn(gpa)); - - /* - * If the instruction failed on the error pfn, it can not be fixed, - * report the error to userspace. - */ - if (is_error_noslot_pfn(pfn)) - return false; - - kvm_release_pfn_clean(pfn); - - /* - * If emulation may have been triggered by a write to a shadowed page - * table, unprotect the gfn (zap any relevant SPTEs) and re-enter the - * guest to let the CPU re-execute the instruction in the hope that the - * CPU can cleanly execute the instruction that KVM failed to emulate. - */ - if (vcpu->kvm->arch.indirect_shadow_pages) - kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(gpa)); - /* * If the failed instruction faulted on an access to page tables that * are used to translate any part of the instruction, KVM can't resolve @@ -8929,54 +8873,24 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, * then zap the SPTE to unprotect the gfn, and then do it all over * again. Report the error to userspace. */ - return !(emulation_type & EMULTYPE_WRITE_PF_TO_SP); -} - -static bool retry_instruction(struct x86_emulate_ctxt *ctxt, - gpa_t cr2_or_gpa, int emulation_type) -{ - struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); - unsigned long last_retry_eip, last_retry_addr, gpa = cr2_or_gpa; - - last_retry_eip = vcpu->arch.last_retry_eip; - last_retry_addr = vcpu->arch.last_retry_addr; + if (emulation_type & EMULTYPE_WRITE_PF_TO_SP) + return false; /* - * If the emulation is caused by #PF and it is non-page_table - * writing instruction, it means the VM-EXIT is caused by shadow - * page protected, we can zap the shadow page and retry this - * instruction directly. - * - * Note: if the guest uses a non-page-table modifying instruction - * on the PDE that points to the instruction, then we will unmap - * the instruction and go to an infinite loop. So, we cache the - * last retried eip and the last fault address, if we meet the eip - * and the address again, we can break out of the potential infinite - * loop. + * If emulation may have been triggered by a write to a shadowed page + * table, unprotect the gfn (zap any relevant SPTEs) and re-enter the + * guest to let the CPU re-execute the instruction in the hope that the + * CPU can cleanly execute the instruction that KVM failed to emulate. */ - vcpu->arch.last_retry_eip = vcpu->arch.last_retry_addr = 0; - - if (!(emulation_type & EMULTYPE_ALLOW_RETRY_PF)) - return false; - - if (WARN_ON_ONCE(is_guest_mode(vcpu)) || - WARN_ON_ONCE(!(emulation_type & EMULTYPE_PF))) - return false; - - if (x86_page_table_writing_insn(ctxt)) - return false; - - if (ctxt->eip == last_retry_eip && last_retry_addr == cr2_or_gpa) - return false; - - vcpu->arch.last_retry_eip = ctxt->eip; - vcpu->arch.last_retry_addr = cr2_or_gpa; - - if (!vcpu->arch.mmu->root_role.direct) - gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2_or_gpa, NULL); - - kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(gpa)); + __kvm_mmu_unprotect_gfn_and_retry(vcpu, cr2_or_gpa, true); + /* + * Retry even if _this_ vCPU didn't unprotect the gfn, as it's possible + * all SPTEs were already zapped by a different task. The alternative + * is to report the error to userspace and likely terminate the guest, + * and the last_retry_{eip,addr} checks will prevent retrying the page + * fault indefinitely, i.e. there's nothing to lose by retrying. + */ return true; } @@ -9176,6 +9090,11 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; bool writeback = true; + if ((emulation_type & EMULTYPE_ALLOW_RETRY_PF) && + (WARN_ON_ONCE(is_guest_mode(vcpu)) || + WARN_ON_ONCE(!(emulation_type & EMULTYPE_PF)))) + emulation_type &= ~EMULTYPE_ALLOW_RETRY_PF; + r = kvm_check_emulate_insn(vcpu, emulation_type, insn, insn_len); if (r != X86EMUL_CONTINUE) { if (r == X86EMUL_RETRY_INSTR || r == X86EMUL_PROPAGATE_FAULT) @@ -9206,8 +9125,8 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, kvm_queue_exception(vcpu, UD_VECTOR); return 1; } - if (reexecute_instruction(vcpu, cr2_or_gpa, - emulation_type)) + if (kvm_unprotect_and_retry_on_failure(vcpu, cr2_or_gpa, + emulation_type)) return 1; if (ctxt->have_exception && @@ -9254,7 +9173,15 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, return 1; } - if (retry_instruction(ctxt, cr2_or_gpa, emulation_type)) + /* + * If emulation was caused by a write-protection #PF on a non-page_table + * writing instruction, try to unprotect the gfn, i.e. zap shadow pages, + * and retry the instruction, as the vCPU is likely no longer using the + * gfn as a page table. + */ + if ((emulation_type & EMULTYPE_ALLOW_RETRY_PF) && + !x86_page_table_writing_insn(ctxt) && + kvm_mmu_unprotect_gfn_and_retry(vcpu, cr2_or_gpa)) return 1; /* this is needed for vmware backdoor interface to work since it @@ -9285,7 +9212,8 @@ restart: return 1; if (r == EMULATION_FAILED) { - if (reexecute_instruction(vcpu, cr2_or_gpa, emulation_type)) + if (kvm_unprotect_and_retry_on_failure(vcpu, cr2_or_gpa, + emulation_type)) return 1; return handle_emulation_failure(vcpu, emulation_type); @@ -9753,7 +9681,7 @@ int kvm_x86_vendor_init(struct kvm_x86_init_ops *ops) guard(mutex)(&vendor_module_lock); - if (kvm_x86_ops.hardware_enable) { + if (kvm_x86_ops.enable_virtualization_cpu) { pr_err("already loaded vendor module '%s'\n", kvm_x86_ops.name); return -EEXIST; } @@ -9880,7 +9808,7 @@ int kvm_x86_vendor_init(struct kvm_x86_init_ops *ops) return 0; out_unwind_ops: - kvm_x86_ops.hardware_enable = NULL; + kvm_x86_ops.enable_virtualization_cpu = NULL; kvm_x86_call(hardware_unsetup)(); out_mmu_exit: kvm_mmu_vendor_module_exit(); @@ -9921,56 +9849,11 @@ void kvm_x86_vendor_exit(void) WARN_ON(static_branch_unlikely(&kvm_xen_enabled.key)); #endif mutex_lock(&vendor_module_lock); - kvm_x86_ops.hardware_enable = NULL; + kvm_x86_ops.enable_virtualization_cpu = NULL; mutex_unlock(&vendor_module_lock); } EXPORT_SYMBOL_GPL(kvm_x86_vendor_exit); -static int __kvm_emulate_halt(struct kvm_vcpu *vcpu, int state, int reason) -{ - /* - * The vCPU has halted, e.g. executed HLT. Update the run state if the - * local APIC is in-kernel, the run loop will detect the non-runnable - * state and halt the vCPU. Exit to userspace if the local APIC is - * managed by userspace, in which case userspace is responsible for - * handling wake events. - */ - ++vcpu->stat.halt_exits; - if (lapic_in_kernel(vcpu)) { - vcpu->arch.mp_state = state; - return 1; - } else { - vcpu->run->exit_reason = reason; - return 0; - } -} - -int kvm_emulate_halt_noskip(struct kvm_vcpu *vcpu) -{ - return __kvm_emulate_halt(vcpu, KVM_MP_STATE_HALTED, KVM_EXIT_HLT); -} -EXPORT_SYMBOL_GPL(kvm_emulate_halt_noskip); - -int kvm_emulate_halt(struct kvm_vcpu *vcpu) -{ - int ret = kvm_skip_emulated_instruction(vcpu); - /* - * TODO: we might be squashing a GUESTDBG_SINGLESTEP-triggered - * KVM_EXIT_DEBUG here. - */ - return kvm_emulate_halt_noskip(vcpu) && ret; -} -EXPORT_SYMBOL_GPL(kvm_emulate_halt); - -int kvm_emulate_ap_reset_hold(struct kvm_vcpu *vcpu) -{ - int ret = kvm_skip_emulated_instruction(vcpu); - - return __kvm_emulate_halt(vcpu, KVM_MP_STATE_AP_RESET_HOLD, - KVM_EXIT_AP_RESET_HOLD) && ret; -} -EXPORT_SYMBOL_GPL(kvm_emulate_ap_reset_hold); - #ifdef CONFIG_X86_64 static int kvm_pv_clock_pairing(struct kvm_vcpu *vcpu, gpa_t paddr, unsigned long clock_type) @@ -11207,6 +11090,9 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (vcpu->arch.apic_attention) kvm_lapic_sync_from_vapic(vcpu); + if (unlikely(exit_fastpath == EXIT_FASTPATH_EXIT_USERSPACE)) + return 0; + r = kvm_x86_call(handle_exit)(vcpu, exit_fastpath); return r; @@ -11220,6 +11106,67 @@ out: return r; } +static bool kvm_vcpu_running(struct kvm_vcpu *vcpu) +{ + return (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE && + !vcpu->arch.apf.halted); +} + +static bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu) +{ + if (!list_empty_careful(&vcpu->async_pf.done)) + return true; + + if (kvm_apic_has_pending_init_or_sipi(vcpu) && + kvm_apic_init_sipi_allowed(vcpu)) + return true; + + if (vcpu->arch.pv.pv_unhalted) + return true; + + if (kvm_is_exception_pending(vcpu)) + return true; + + if (kvm_test_request(KVM_REQ_NMI, vcpu) || + (vcpu->arch.nmi_pending && + kvm_x86_call(nmi_allowed)(vcpu, false))) + return true; + +#ifdef CONFIG_KVM_SMM + if (kvm_test_request(KVM_REQ_SMI, vcpu) || + (vcpu->arch.smi_pending && + kvm_x86_call(smi_allowed)(vcpu, false))) + return true; +#endif + + if (kvm_test_request(KVM_REQ_PMI, vcpu)) + return true; + + if (kvm_test_request(KVM_REQ_UPDATE_PROTECTED_GUEST_STATE, vcpu)) + return true; + + if (kvm_arch_interrupt_allowed(vcpu) && kvm_cpu_has_interrupt(vcpu)) + return true; + + if (kvm_hv_has_stimer_pending(vcpu)) + return true; + + if (is_guest_mode(vcpu) && + kvm_x86_ops.nested_ops->has_events && + kvm_x86_ops.nested_ops->has_events(vcpu, false)) + return true; + + if (kvm_xen_has_pending_events(vcpu)) + return true; + + return false; +} + +int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu) +{ + return kvm_vcpu_running(vcpu) || kvm_vcpu_has_events(vcpu); +} + /* Called within kvm->srcu read side. */ static inline int vcpu_block(struct kvm_vcpu *vcpu) { @@ -11291,12 +11238,6 @@ static inline int vcpu_block(struct kvm_vcpu *vcpu) return 1; } -static inline bool kvm_vcpu_running(struct kvm_vcpu *vcpu) -{ - return (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE && - !vcpu->arch.apf.halted); -} - /* Called within kvm->srcu read side. */ static int vcpu_run(struct kvm_vcpu *vcpu) { @@ -11348,6 +11289,98 @@ static int vcpu_run(struct kvm_vcpu *vcpu) return r; } +static int __kvm_emulate_halt(struct kvm_vcpu *vcpu, int state, int reason) +{ + /* + * The vCPU has halted, e.g. executed HLT. Update the run state if the + * local APIC is in-kernel, the run loop will detect the non-runnable + * state and halt the vCPU. Exit to userspace if the local APIC is + * managed by userspace, in which case userspace is responsible for + * handling wake events. + */ + ++vcpu->stat.halt_exits; + if (lapic_in_kernel(vcpu)) { + if (kvm_vcpu_has_events(vcpu)) + vcpu->arch.pv.pv_unhalted = false; + else + vcpu->arch.mp_state = state; + return 1; + } else { + vcpu->run->exit_reason = reason; + return 0; + } +} + +int kvm_emulate_halt_noskip(struct kvm_vcpu *vcpu) +{ + return __kvm_emulate_halt(vcpu, KVM_MP_STATE_HALTED, KVM_EXIT_HLT); +} +EXPORT_SYMBOL_GPL(kvm_emulate_halt_noskip); + +int kvm_emulate_halt(struct kvm_vcpu *vcpu) +{ + int ret = kvm_skip_emulated_instruction(vcpu); + /* + * TODO: we might be squashing a GUESTDBG_SINGLESTEP-triggered + * KVM_EXIT_DEBUG here. + */ + return kvm_emulate_halt_noskip(vcpu) && ret; +} +EXPORT_SYMBOL_GPL(kvm_emulate_halt); + +fastpath_t handle_fastpath_hlt(struct kvm_vcpu *vcpu) +{ + int ret; + + kvm_vcpu_srcu_read_lock(vcpu); + ret = kvm_emulate_halt(vcpu); + kvm_vcpu_srcu_read_unlock(vcpu); + + if (!ret) + return EXIT_FASTPATH_EXIT_USERSPACE; + + if (kvm_vcpu_running(vcpu)) + return EXIT_FASTPATH_REENTER_GUEST; + + return EXIT_FASTPATH_EXIT_HANDLED; +} +EXPORT_SYMBOL_GPL(handle_fastpath_hlt); + +int kvm_emulate_ap_reset_hold(struct kvm_vcpu *vcpu) +{ + int ret = kvm_skip_emulated_instruction(vcpu); + + return __kvm_emulate_halt(vcpu, KVM_MP_STATE_AP_RESET_HOLD, + KVM_EXIT_AP_RESET_HOLD) && ret; +} +EXPORT_SYMBOL_GPL(kvm_emulate_ap_reset_hold); + +bool kvm_arch_dy_has_pending_interrupt(struct kvm_vcpu *vcpu) +{ + return kvm_vcpu_apicv_active(vcpu) && + kvm_x86_call(dy_apicv_has_pending_interrupt)(vcpu); +} + +bool kvm_arch_vcpu_preempted_in_kernel(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.preempted_in_kernel; +} + +bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu) +{ + if (READ_ONCE(vcpu->arch.pv.pv_unhalted)) + return true; + + if (kvm_test_request(KVM_REQ_NMI, vcpu) || +#ifdef CONFIG_KVM_SMM + kvm_test_request(KVM_REQ_SMI, vcpu) || +#endif + kvm_test_request(KVM_REQ_EVENT, vcpu)) + return true; + + return kvm_arch_dy_has_pending_interrupt(vcpu); +} + static inline int complete_emulated_io(struct kvm_vcpu *vcpu) { return kvm_emulate_instruction(vcpu, EMULTYPE_NO_DECODE); @@ -12264,8 +12297,6 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu); vcpu->arch.reserved_gpa_bits = kvm_vcpu_reserved_gpa_bits_raw(vcpu); - vcpu->arch.pat = MSR_IA32_CR_PAT_DEFAULT; - kvm_async_pf_hash_reset(vcpu); vcpu->arch.perf_capabilities = kvm_caps.supported_perf_cap; @@ -12431,6 +12462,8 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) if (!init_event) { vcpu->arch.smbase = 0x30000; + vcpu->arch.pat = MSR_IA32_CR_PAT_DEFAULT; + vcpu->arch.msr_misc_features_enables = 0; vcpu->arch.ia32_misc_enable_msr = MSR_IA32_MISC_ENABLE_PEBS_UNAVAIL | MSR_IA32_MISC_ENABLE_BTS_UNAVAIL; @@ -12516,7 +12549,17 @@ void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector) } EXPORT_SYMBOL_GPL(kvm_vcpu_deliver_sipi_vector); -int kvm_arch_hardware_enable(void) +void kvm_arch_enable_virtualization(void) +{ + cpu_emergency_register_virt_callback(kvm_x86_ops.emergency_disable_virtualization_cpu); +} + +void kvm_arch_disable_virtualization(void) +{ + cpu_emergency_unregister_virt_callback(kvm_x86_ops.emergency_disable_virtualization_cpu); +} + +int kvm_arch_enable_virtualization_cpu(void) { struct kvm *kvm; struct kvm_vcpu *vcpu; @@ -12532,7 +12575,7 @@ int kvm_arch_hardware_enable(void) if (ret) return ret; - ret = kvm_x86_call(hardware_enable)(); + ret = kvm_x86_call(enable_virtualization_cpu)(); if (ret != 0) return ret; @@ -12612,9 +12655,9 @@ int kvm_arch_hardware_enable(void) return 0; } -void kvm_arch_hardware_disable(void) +void kvm_arch_disable_virtualization_cpu(void) { - kvm_x86_call(hardware_disable)(); + kvm_x86_call(disable_virtualization_cpu)(); drop_user_return_notifiers(); } @@ -13162,87 +13205,6 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, kvm_arch_free_memslot(kvm, old); } -static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu) -{ - if (!list_empty_careful(&vcpu->async_pf.done)) - return true; - - if (kvm_apic_has_pending_init_or_sipi(vcpu) && - kvm_apic_init_sipi_allowed(vcpu)) - return true; - - if (vcpu->arch.pv.pv_unhalted) - return true; - - if (kvm_is_exception_pending(vcpu)) - return true; - - if (kvm_test_request(KVM_REQ_NMI, vcpu) || - (vcpu->arch.nmi_pending && - kvm_x86_call(nmi_allowed)(vcpu, false))) - return true; - -#ifdef CONFIG_KVM_SMM - if (kvm_test_request(KVM_REQ_SMI, vcpu) || - (vcpu->arch.smi_pending && - kvm_x86_call(smi_allowed)(vcpu, false))) - return true; -#endif - - if (kvm_test_request(KVM_REQ_PMI, vcpu)) - return true; - - if (kvm_test_request(KVM_REQ_UPDATE_PROTECTED_GUEST_STATE, vcpu)) - return true; - - if (kvm_arch_interrupt_allowed(vcpu) && kvm_cpu_has_interrupt(vcpu)) - return true; - - if (kvm_hv_has_stimer_pending(vcpu)) - return true; - - if (is_guest_mode(vcpu) && - kvm_x86_ops.nested_ops->has_events && - kvm_x86_ops.nested_ops->has_events(vcpu, false)) - return true; - - if (kvm_xen_has_pending_events(vcpu)) - return true; - - return false; -} - -int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu) -{ - return kvm_vcpu_running(vcpu) || kvm_vcpu_has_events(vcpu); -} - -bool kvm_arch_dy_has_pending_interrupt(struct kvm_vcpu *vcpu) -{ - return kvm_vcpu_apicv_active(vcpu) && - kvm_x86_call(dy_apicv_has_pending_interrupt)(vcpu); -} - -bool kvm_arch_vcpu_preempted_in_kernel(struct kvm_vcpu *vcpu) -{ - return vcpu->arch.preempted_in_kernel; -} - -bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu) -{ - if (READ_ONCE(vcpu->arch.pv.pv_unhalted)) - return true; - - if (kvm_test_request(KVM_REQ_NMI, vcpu) || -#ifdef CONFIG_KVM_SMM - kvm_test_request(KVM_REQ_SMI, vcpu) || -#endif - kvm_test_request(KVM_REQ_EVENT, vcpu)) - return true; - - return kvm_arch_dy_has_pending_interrupt(vcpu); -} - bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu) { if (vcpu->arch.guest_state_protected) diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 50596f6f8320..a84c48ef5278 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -103,11 +103,18 @@ static inline unsigned int __shrink_ple_window(unsigned int val, return max(val, min); } -#define MSR_IA32_CR_PAT_DEFAULT 0x0007040600070406ULL +#define MSR_IA32_CR_PAT_DEFAULT \ + PAT_VALUE(WB, WT, UC_MINUS, UC, WB, WT, UC_MINUS, UC) void kvm_service_local_tlb_flush_requests(struct kvm_vcpu *vcpu); int kvm_check_nested_events(struct kvm_vcpu *vcpu); +/* Forcibly leave the nested mode in cases like a vCPU reset */ +static inline void kvm_leave_nested(struct kvm_vcpu *vcpu) +{ + kvm_x86_ops.nested_ops->leave_nested(vcpu); +} + static inline bool kvm_vcpu_has_run(struct kvm_vcpu *vcpu) { return vcpu->arch.last_vmentry_cpu != -1; @@ -334,6 +341,7 @@ int x86_decode_emulated_instruction(struct kvm_vcpu *vcpu, int emulation_type, int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, int emulation_type, void *insn, int insn_len); fastpath_t handle_fastpath_set_msr_irqoff(struct kvm_vcpu *vcpu); +fastpath_t handle_fastpath_hlt(struct kvm_vcpu *vcpu); extern struct kvm_caps kvm_caps; extern struct kvm_host_values kvm_host; @@ -504,13 +512,26 @@ int kvm_handle_memory_failure(struct kvm_vcpu *vcpu, int r, int kvm_handle_invpcid(struct kvm_vcpu *vcpu, unsigned long type, gva_t gva); bool kvm_msr_allowed(struct kvm_vcpu *vcpu, u32 index, u32 type); +enum kvm_msr_access { + MSR_TYPE_R = BIT(0), + MSR_TYPE_W = BIT(1), + MSR_TYPE_RW = MSR_TYPE_R | MSR_TYPE_W, +}; + /* * Internal error codes that are used to indicate that MSR emulation encountered - * an error that should result in #GP in the guest, unless userspace - * handles it. + * an error that should result in #GP in the guest, unless userspace handles it. + * Note, '1', '0', and negative numbers are off limits, as they are used by KVM + * as part of KVM's lightly documented internal KVM_RUN return codes. + * + * UNSUPPORTED - The MSR isn't supported, either because it is completely + * unknown to KVM, or because the MSR should not exist according + * to the vCPU model. + * + * FILTERED - Access to the MSR is denied by a userspace MSR filter. */ -#define KVM_MSR_RET_INVALID 2 /* in-kernel MSR emulation #GP condition */ -#define KVM_MSR_RET_FILTERED 3 /* #GP due to userspace MSR filter */ +#define KVM_MSR_RET_UNSUPPORTED 2 +#define KVM_MSR_RET_FILTERED 3 #define __cr4_reserved_bits(__cpu_has, __c) \ ({ \ diff --git a/arch/x86/lib/atomic64_cx8_32.S b/arch/x86/lib/atomic64_cx8_32.S index 90afb488b396..b2eff07d65e4 100644 --- a/arch/x86/lib/atomic64_cx8_32.S +++ b/arch/x86/lib/atomic64_cx8_32.S @@ -16,6 +16,11 @@ cmpxchg8b (\reg) .endm +.macro read64_nonatomic reg + movl (\reg), %eax + movl 4(\reg), %edx +.endm + SYM_FUNC_START(atomic64_read_cx8) read64 %ecx RET @@ -51,7 +56,7 @@ SYM_FUNC_START(atomic64_\func\()_return_cx8) movl %edx, %edi movl %ecx, %ebp - read64 %ecx + read64_nonatomic %ecx 1: movl %eax, %ebx movl %edx, %ecx @@ -79,7 +84,7 @@ addsub_return sub sub sbb SYM_FUNC_START(atomic64_\func\()_return_cx8) pushl %ebx - read64 %esi + read64_nonatomic %esi 1: movl %eax, %ebx movl %edx, %ecx diff --git a/arch/x86/lib/insn.c b/arch/x86/lib/insn.c index 5952ab41c60f..6ffb931b9fb1 100644 --- a/arch/x86/lib/insn.c +++ b/arch/x86/lib/insn.c @@ -13,7 +13,7 @@ #endif #include <asm/inat.h> /*__ignore_sync_check__ */ #include <asm/insn.h> /* __ignore_sync_check__ */ -#include <asm/unaligned.h> /* __ignore_sync_check__ */ +#include <linux/unaligned.h> /* __ignore_sync_check__ */ #include <linux/errno.h> #include <linux/kconfig.h> diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c index f73b5ce270b3..feb8cc6a12bf 100644 --- a/arch/x86/mm/pat/memtype.c +++ b/arch/x86/mm/pat/memtype.c @@ -176,15 +176,6 @@ static inline void set_page_memtype(struct page *pg, } #endif -enum { - PAT_UC = 0, /* uncached */ - PAT_WC = 1, /* Write combining */ - PAT_WT = 4, /* Write Through */ - PAT_WP = 5, /* Write Protected */ - PAT_WB = 6, /* Write Back (default) */ - PAT_UC_MINUS = 7, /* UC, but can be overridden by MTRR */ -}; - #define CM(c) (_PAGE_CACHE_MODE_ ## c) static enum page_cache_mode __init pat_get_cache_mode(unsigned int pat_val, @@ -194,13 +185,13 @@ static enum page_cache_mode __init pat_get_cache_mode(unsigned int pat_val, char *cache_mode; switch (pat_val) { - case PAT_UC: cache = CM(UC); cache_mode = "UC "; break; - case PAT_WC: cache = CM(WC); cache_mode = "WC "; break; - case PAT_WT: cache = CM(WT); cache_mode = "WT "; break; - case PAT_WP: cache = CM(WP); cache_mode = "WP "; break; - case PAT_WB: cache = CM(WB); cache_mode = "WB "; break; - case PAT_UC_MINUS: cache = CM(UC_MINUS); cache_mode = "UC- "; break; - default: cache = CM(WB); cache_mode = "WB "; break; + case X86_MEMTYPE_UC: cache = CM(UC); cache_mode = "UC "; break; + case X86_MEMTYPE_WC: cache = CM(WC); cache_mode = "WC "; break; + case X86_MEMTYPE_WT: cache = CM(WT); cache_mode = "WT "; break; + case X86_MEMTYPE_WP: cache = CM(WP); cache_mode = "WP "; break; + case X86_MEMTYPE_WB: cache = CM(WB); cache_mode = "WB "; break; + case X86_MEMTYPE_UC_MINUS: cache = CM(UC_MINUS); cache_mode = "UC- "; break; + default: cache = CM(WB); cache_mode = "WB "; break; } memcpy(msg, cache_mode, 4); @@ -257,12 +248,6 @@ void pat_cpu_init(void) void __init pat_bp_init(void) { struct cpuinfo_x86 *c = &boot_cpu_data; -#define PAT(p0, p1, p2, p3, p4, p5, p6, p7) \ - (((u64)PAT_ ## p0) | ((u64)PAT_ ## p1 << 8) | \ - ((u64)PAT_ ## p2 << 16) | ((u64)PAT_ ## p3 << 24) | \ - ((u64)PAT_ ## p4 << 32) | ((u64)PAT_ ## p5 << 40) | \ - ((u64)PAT_ ## p6 << 48) | ((u64)PAT_ ## p7 << 56)) - if (!IS_ENABLED(CONFIG_X86_PAT)) pr_info_once("x86/PAT: PAT support disabled because CONFIG_X86_PAT is disabled in the kernel.\n"); @@ -293,7 +278,7 @@ void __init pat_bp_init(void) * NOTE: When WC or WP is used, it is redirected to UC- per * the default setup in __cachemode2pte_tbl[]. */ - pat_msr_val = PAT(WB, WT, UC_MINUS, UC, WB, WT, UC_MINUS, UC); + pat_msr_val = PAT_VALUE(WB, WT, UC_MINUS, UC, WB, WT, UC_MINUS, UC); } /* @@ -328,7 +313,7 @@ void __init pat_bp_init(void) * NOTE: When WT or WP is used, it is redirected to UC- per * the default setup in __cachemode2pte_tbl[]. */ - pat_msr_val = PAT(WB, WC, UC_MINUS, UC, WB, WC, UC_MINUS, UC); + pat_msr_val = PAT_VALUE(WB, WC, UC_MINUS, UC, WB, WC, UC_MINUS, UC); } else { /* * Full PAT support. We put WT in slot 7 to improve @@ -356,13 +341,12 @@ void __init pat_bp_init(void) * The reserved slots are unused, but mapped to their * corresponding types in the presence of PAT errata. */ - pat_msr_val = PAT(WB, WC, UC_MINUS, UC, WB, WP, UC_MINUS, WT); + pat_msr_val = PAT_VALUE(WB, WC, UC_MINUS, UC, WB, WP, UC_MINUS, WT); } memory_caching_control |= CACHE_PAT; init_cache_modes(pat_msr_val); -#undef PAT } static DEFINE_SPINLOCK(memtype_lock); /* protects memtype accesses */ diff --git a/arch/x86/um/sysrq_32.c b/arch/x86/um/sysrq_32.c index f2383484840d..a1ee415c008d 100644 --- a/arch/x86/um/sysrq_32.c +++ b/arch/x86/um/sysrq_32.c @@ -9,7 +9,6 @@ #include <linux/sched/debug.h> #include <linux/kallsyms.h> #include <asm/ptrace.h> -#include <asm/sysrq.h> /* This is declared by <linux/sched.h> */ void show_regs(struct pt_regs *regs) diff --git a/arch/x86/um/sysrq_64.c b/arch/x86/um/sysrq_64.c index 0bf6de40abff..340d8a243c8a 100644 --- a/arch/x86/um/sysrq_64.c +++ b/arch/x86/um/sysrq_64.c @@ -12,7 +12,6 @@ #include <linux/utsname.h> #include <asm/current.h> #include <asm/ptrace.h> -#include <asm/sysrq.h> void show_regs(struct pt_regs *regs) { diff --git a/arch/xtensa/include/asm/flat.h b/arch/xtensa/include/asm/flat.h index ed5870c779f9..4854419dcd86 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 <asm/unaligned.h> +#include <linux/unaligned.h> 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 0a2b1c5d0ebf..83b696ba0cac 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 9dc9323f84ac..384aa15e8260 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 0a747a0c782d..e259180c8914 100644 --- a/block/partitions/ldm.h +++ b/block/partitions/ldm.h @@ -15,7 +15,7 @@ #include <linux/types.h> #include <linux/list.h> #include <linux/fs.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <asm/byteorder.h> struct parsed_partitions; diff --git a/block/partitions/msdos.c b/block/partitions/msdos.c index b5d5c229cc3b..073be78ba0b0 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 <asm/unaligned.h> +#include <linux/unaligned.h> static inline sector_t nr_sects(struct msdos_partition *p) { diff --git a/block/t10-pi.c b/block/t10-pi.c index e7052a728966..2d05421f0fa5 100644 --- a/block/t10-pi.c +++ b/block/t10-pi.c @@ -9,7 +9,7 @@ #include <linux/crc-t10dif.h> #include <linux/crc64.h> #include <net/checksum.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "blk.h" struct blk_integrity_iter { diff --git a/crypto/aes_generic.c b/crypto/aes_generic.c index 666474b81c6a..3c66d425c97b 100644 --- a/crypto/aes_generic.c +++ b/crypto/aes_generic.c @@ -54,7 +54,7 @@ #include <linux/types.h> #include <linux/errno.h> #include <asm/byteorder.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> static inline u8 byte(const u32 x, const unsigned n) { diff --git a/crypto/blake2b_generic.c b/crypto/blake2b_generic.c index 32e380b714b6..04a712ddfb43 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 <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/bitops.h> diff --git a/crypto/blowfish_generic.c b/crypto/blowfish_generic.c index 0e74c7242e77..0146bc762c09 100644 --- a/crypto/blowfish_generic.c +++ b/crypto/blowfish_generic.c @@ -16,7 +16,7 @@ #include <linux/init.h> #include <linux/module.h> #include <linux/mm.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/types.h> #include <crypto/blowfish.h> diff --git a/crypto/camellia_generic.c b/crypto/camellia_generic.c index c04670cf51ac..197fcf3abc89 100644 --- a/crypto/camellia_generic.c +++ b/crypto/camellia_generic.c @@ -15,7 +15,7 @@ #include <linux/kernel.h> #include <linux/module.h> #include <linux/bitops.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> static const u32 camellia_sp1110[256] = { 0x70707000, 0x82828200, 0x2c2c2c00, 0xececec00, diff --git a/crypto/cast5_generic.c b/crypto/cast5_generic.c index 085a1eedae03..f3e57775fa02 100644 --- a/crypto/cast5_generic.c +++ b/crypto/cast5_generic.c @@ -13,7 +13,7 @@ */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <crypto/algapi.h> #include <linux/init.h> #include <linux/module.h> diff --git a/crypto/cast6_generic.c b/crypto/cast6_generic.c index 34f1ab53e3a7..11b725b12f27 100644 --- a/crypto/cast6_generic.c +++ b/crypto/cast6_generic.c @@ -10,7 +10,7 @@ */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <crypto/algapi.h> #include <linux/init.h> #include <linux/module.h> diff --git a/crypto/chacha_generic.c b/crypto/chacha_generic.c index 8beea79ab117..ba7fcb47f9aa 100644 --- a/crypto/chacha_generic.c +++ b/crypto/chacha_generic.c @@ -6,7 +6,7 @@ * Copyright (C) 2018 Google LLC */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <crypto/algapi.h> #include <crypto/internal/chacha.h> #include <crypto/internal/skcipher.h> diff --git a/crypto/crc32_generic.c b/crypto/crc32_generic.c index a989cb44fd16..d1251663ed66 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 <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/crc32.h> #include <crypto/internal/hash.h> #include <linux/init.h> diff --git a/crypto/crc32c_generic.c b/crypto/crc32c_generic.c index 768614738541..a8c90b3f4c6c 100644 --- a/crypto/crc32c_generic.c +++ b/crypto/crc32c_generic.c @@ -30,7 +30,7 @@ * Copyright (c) 2008 Herbert Xu <herbert@gondor.apana.org.au> */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <crypto/internal/hash.h> #include <linux/init.h> #include <linux/module.h> diff --git a/crypto/crc64_rocksoft_generic.c b/crypto/crc64_rocksoft_generic.c index 9e812bb26dba..ce0f3059b912 100644 --- a/crypto/crc64_rocksoft_generic.c +++ b/crypto/crc64_rocksoft_generic.c @@ -3,7 +3,7 @@ #include <linux/crc64.h> #include <linux/module.h> #include <crypto/internal/hash.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> static int chksum_init(struct shash_desc *desc) { diff --git a/crypto/ecc.c b/crypto/ecc.c index 420decdad7d9..50ad2d4ed672 100644 --- a/crypto/ecc.c +++ b/crypto/ecc.c @@ -33,7 +33,7 @@ #include <crypto/ecdh.h> #include <crypto/rng.h> #include <crypto/internal/ecc.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/ratelimit.h> #include "ecc_curve_defs.h" diff --git a/crypto/michael_mic.c b/crypto/michael_mic.c index f4c31049601c..0d14e980d4d6 100644 --- a/crypto/michael_mic.c +++ b/crypto/michael_mic.c @@ -7,7 +7,7 @@ * Copyright (c) 2004 Jouni Malinen <j@w1.fi> */ #include <crypto/internal/hash.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/init.h> #include <linux/module.h> #include <linux/string.h> diff --git a/crypto/nhpoly1305.c b/crypto/nhpoly1305.c index 8a3006c3b51b..a661d4f667cd 100644 --- a/crypto/nhpoly1305.c +++ b/crypto/nhpoly1305.c @@ -30,7 +30,7 @@ * (https://cr.yp.to/mac/poly1305-20050329.pdf) */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <crypto/algapi.h> #include <crypto/internal/hash.h> #include <crypto/internal/poly1305.h> diff --git a/crypto/poly1305_generic.c b/crypto/poly1305_generic.c index 94af47eb6fa6..e6f29a98725a 100644 --- a/crypto/poly1305_generic.c +++ b/crypto/poly1305_generic.c @@ -17,7 +17,7 @@ #include <linux/crypto.h> #include <linux/kernel.h> #include <linux/module.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> static int crypto_poly1305_init(struct shash_desc *desc) { diff --git a/crypto/polyval-generic.c b/crypto/polyval-generic.c index 16bfa6925b31..4f98910bcdb5 100644 --- a/crypto/polyval-generic.c +++ b/crypto/polyval-generic.c @@ -44,7 +44,7 @@ * */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <crypto/algapi.h> #include <crypto/gf128mul.h> #include <crypto/polyval.h> diff --git a/crypto/serpent_generic.c b/crypto/serpent_generic.c index c6bca47931e2..f6ef187be6fe 100644 --- a/crypto/serpent_generic.c +++ b/crypto/serpent_generic.c @@ -11,7 +11,7 @@ #include <linux/init.h> #include <linux/module.h> #include <linux/errno.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/types.h> #include <crypto/serpent.h> diff --git a/crypto/sha256_generic.c b/crypto/sha256_generic.c index bf147b01e313..b00521f1a6d4 100644 --- a/crypto/sha256_generic.c +++ b/crypto/sha256_generic.c @@ -15,7 +15,7 @@ #include <crypto/sha2.h> #include <crypto/sha256_base.h> #include <asm/byteorder.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> 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 3e4069935b53..b103642b56ea 100644 --- a/crypto/sha3_generic.c +++ b/crypto/sha3_generic.c @@ -13,7 +13,7 @@ #include <linux/module.h> #include <linux/types.h> #include <crypto/sha3.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /* * On some 32-bit architectures (h8300), GCC ends up using diff --git a/crypto/sha512_generic.c b/crypto/sha512_generic.c index be70e76d6d86..ed81813bd420 100644 --- a/crypto/sha512_generic.c +++ b/crypto/sha512_generic.c @@ -16,7 +16,7 @@ #include <crypto/sha512_base.h> #include <linux/percpu.h> #include <asm/byteorder.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> 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 d473e358a873..18c2fb73ba16 100644 --- a/crypto/sm3.c +++ b/crypto/sm3.c @@ -9,7 +9,7 @@ */ #include <linux/module.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <crypto/sm3.h> static const u32 ____cacheline_aligned K[64] = { diff --git a/crypto/sm3_generic.c b/crypto/sm3_generic.c index a215c1c37e73..a2d23a46924e 100644 --- a/crypto/sm3_generic.c +++ b/crypto/sm3_generic.c @@ -17,7 +17,7 @@ #include <crypto/sm3_base.h> #include <linux/bitops.h> #include <asm/byteorder.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> 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 2c44193bc27e..f4cd7edc11f0 100644 --- a/crypto/sm4.c +++ b/crypto/sm4.c @@ -8,7 +8,7 @@ */ #include <linux/module.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <crypto/sm4.h> static const u32 ____cacheline_aligned fk[4] = { diff --git a/crypto/sm4_generic.c b/crypto/sm4_generic.c index 560eba37dc55..7df86369ac00 100644 --- a/crypto/sm4_generic.c +++ b/crypto/sm4_generic.c @@ -14,7 +14,7 @@ #include <linux/types.h> #include <linux/errno.h> #include <asm/byteorder.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /** * sm4_setkey - Set the SM4 key. diff --git a/crypto/twofish_generic.c b/crypto/twofish_generic.c index 557915e4062d..19f2b365e140 100644 --- a/crypto/twofish_generic.c +++ b/crypto/twofish_generic.c @@ -24,7 +24,7 @@ * Third Edition. */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <crypto/algapi.h> #include <crypto/twofish.h> #include <linux/module.h> diff --git a/crypto/vmac.c b/crypto/vmac.c index 0a1d8efa6c1a..bd9d70eac22e 100644 --- a/crypto/vmac.c +++ b/crypto/vmac.c @@ -28,7 +28,7 @@ * Last modified: 17 APR 08, 1700 PDT */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/init.h> #include <linux/types.h> #include <linux/crypto.h> diff --git a/crypto/xxhash_generic.c b/crypto/xxhash_generic.c index 55d1c8a76127..ac206ad4184d 100644 --- a/crypto/xxhash_generic.c +++ b/crypto/xxhash_generic.c @@ -4,7 +4,7 @@ #include <linux/init.h> #include <linux/module.h> #include <linux/xxhash.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define XXHASH64_BLOCK_SIZE 32 #define XXHASH64_DIGEST_SIZE 8 diff --git a/drivers/acpi/apei/apei-base.c b/drivers/acpi/apei/apei-base.c index c7c26872f4ce..9c84f3da7c09 100644 --- a/drivers/acpi/apei/apei-base.c +++ b/drivers/acpi/apei/apei-base.c @@ -28,7 +28,7 @@ #include <linux/interrupt.h> #include <linux/debugfs.h> #include <acpi/apei.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "apei-internal.h" diff --git a/drivers/acpi/apei/einj-core.c b/drivers/acpi/apei/einj-core.c index 73903a497d73..5c22720f43cc 100644 --- a/drivers/acpi/apei/einj-core.c +++ b/drivers/acpi/apei/einj-core.c @@ -22,7 +22,7 @@ #include <linux/delay.h> #include <linux/mm.h> #include <linux/platform_device.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "apei-internal.h" diff --git a/drivers/acpi/apei/einj-cxl.c b/drivers/acpi/apei/einj-cxl.c index 8b8be0c90709..a4e709937236 100644 --- a/drivers/acpi/apei/einj-cxl.c +++ b/drivers/acpi/apei/einj-cxl.c @@ -7,9 +7,9 @@ * * Author: Ben Cheatham <benjamin.cheatham@amd.com> */ -#include <linux/einj-cxl.h> #include <linux/seq_file.h> #include <linux/pci.h> +#include <cxl/einj.h> #include "apei-internal.h" @@ -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/apei/ghes.c b/drivers/acpi/apei/ghes.c index 623cc0cb4a65..ada93cfde9ba 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -27,7 +27,6 @@ #include <linux/timer.h> #include <linux/cper.h> #include <linux/cleanup.h> -#include <linux/cxl-event.h> #include <linux/platform_device.h> #include <linux/mutex.h> #include <linux/ratelimit.h> @@ -50,6 +49,7 @@ #include <acpi/apei.h> #include <asm/fixmap.h> #include <asm/tlbflush.h> +#include <cxl/event.h> #include <ras/ras_event.h> #include "apei-internal.h" diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c index f4599261cfc3..65fa3444367a 100644 --- a/drivers/acpi/battery.c +++ b/drivers/acpi/battery.c @@ -21,7 +21,7 @@ #include <linux/suspend.h> #include <linux/types.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/acpi.h> #include <linux/power_supply.h> @@ -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 5b06e236aabe..b73b3aa92f3f 100644 --- a/drivers/acpi/cppc_acpi.c +++ b/drivers/acpi/cppc_acpi.c @@ -41,7 +41,7 @@ #include <linux/topology.h> #include <linux/dmi.h> #include <linux/units.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <acpi/cppc_acpi.h> diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c index 8a4726e2eb69..3d74ebe9dbd8 100644 --- a/drivers/acpi/resource.c +++ b/drivers/acpi/resource.c @@ -441,6 +441,13 @@ static const struct dmi_system_id irq1_level_low_skip_override[] = { }, }, { + /* Asus Vivobook X1704VAP */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_BOARD_NAME, "X1704VAP"), + }, + }, + { /* Asus ExpertBook B1402CBA */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), @@ -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 b70e84e8049a..015bd8e66c1c 100644 --- a/drivers/acpi/video_detect.c +++ b/drivers/acpi/video_detect.c @@ -845,6 +845,15 @@ static const struct dmi_system_id video_detect_dmi_table[] = { * 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, /* Dell OptiPlex 7760 AIO */ diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index cdb20a700b55..c085dd81ebe7 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -50,7 +50,7 @@ #include <scsi/scsi_host.h> #include <linux/libata.h> #include <asm/byteorder.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/cdrom.h> #include <linux/ratelimit.h> #include <linux/leds.h> diff --git a/drivers/ata/libata-sata.c b/drivers/ata/libata-sata.c index c8b119a06bb2..9c76fb1ad2ec 100644 --- a/drivers/ata/libata-sata.c +++ b/drivers/ata/libata-sata.c @@ -13,7 +13,7 @@ #include <scsi/scsi_device.h> #include <scsi/scsi_eh.h> #include <linux/libata.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "libata.h" #include "libata-transport.h" diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index a4aedf7e1775..f915e3df57a9 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -30,7 +30,7 @@ #include <linux/hdreg.h> #include <linux/uaccess.h> #include <linux/suspend.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/ioprio.h> #include <linux/of.h> diff --git a/drivers/auxdisplay/ht16k33.c b/drivers/auxdisplay/ht16k33.c index 8a7034b41d50..a816f9e10255 100644 --- a/drivers/auxdisplay/ht16k33.c +++ b/drivers/auxdisplay/ht16k33.c @@ -25,7 +25,7 @@ #include <linux/map_to_7segment.h> #include <linux/map_to_14segment.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "line-display.h" diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c index 9ed842d17642..4ded93687c1f 100644 --- a/drivers/base/regmap/regmap.c +++ b/drivers/base/regmap/regmap.c @@ -17,7 +17,7 @@ #include <linux/delay.h> #include <linux/log2.h> #include <linux/hwspinlock.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define CREATE_TRACE_POINTS #include "trace.h" diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c index cc9077b588d7..92b06d1de4cc 100644 --- a/drivers/block/aoe/aoecmd.c +++ b/drivers/block/aoe/aoecmd.c @@ -14,7 +14,7 @@ #include <linux/workqueue.h> #include <linux/kthread.h> #include <net/net_namespace.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/uio.h> #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 923a134fd766..66e617664c14 100644 --- a/drivers/block/aoe/aoenet.c +++ b/drivers/block/aoe/aoenet.c @@ -10,7 +10,7 @@ #include <linux/netdevice.h> #include <linux/moduleparam.h> #include <net/net_namespace.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "aoe.h" #define NECODES 5 diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c index 5d65c9754d83..720fc30e2ecc 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 <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/drbd_limits.h> #include <linux/kthread.h> diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index 499c110465e3..65b96c083b3c 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -71,7 +71,7 @@ #include <scsi/scsi_cmnd.h> #include <scsi/scsi_ioctl.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define DRIVER_NAME "pktcdvd" diff --git a/drivers/bluetooth/ath3k.c b/drivers/bluetooth/ath3k.c index ce97b336fbfb..fc796f1dbda9 100644 --- a/drivers/bluetooth/ath3k.c +++ b/drivers/bluetooth/ath3k.c @@ -11,7 +11,7 @@ #include <linux/errno.h> #include <linux/firmware.h> #include <linux/usb.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <net/bluetooth/bluetooth.h> #define VERSION "1.0" diff --git a/drivers/bluetooth/btbcm.c b/drivers/bluetooth/btbcm.c index f9a7c790d7e2..eef00467905e 100644 --- a/drivers/bluetooth/btbcm.c +++ b/drivers/bluetooth/btbcm.c @@ -12,7 +12,7 @@ #include <linux/dmi.h> #include <linux/of.h> #include <linux/string.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> diff --git a/drivers/bluetooth/btintel.c b/drivers/bluetooth/btintel.c index 1ccbb5157515..438b92967bc3 100644 --- a/drivers/bluetooth/btintel.c +++ b/drivers/bluetooth/btintel.c @@ -11,7 +11,7 @@ #include <linux/regmap.h> #include <linux/acpi.h> #include <acpi/acpi_bus.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/efi.h> #include <net/bluetooth/bluetooth.h> diff --git a/drivers/bluetooth/btintel_pcie.c b/drivers/bluetooth/btintel_pcie.c index fda47948c35d..5252125b003f 100644 --- a/drivers/bluetooth/btintel_pcie.c +++ b/drivers/bluetooth/btintel_pcie.c @@ -14,7 +14,7 @@ #include <linux/delay.h> #include <linux/interrupt.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> diff --git a/drivers/bluetooth/btmrvl_sdio.c b/drivers/bluetooth/btmrvl_sdio.c index 85b7f2bb4259..07cd308f7abf 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 2b7c80043aa2..9bbf20502163 100644 --- a/drivers/bluetooth/btmtk.c +++ b/drivers/bluetooth/btmtk.c @@ -6,7 +6,7 @@ #include <linux/firmware.h> #include <linux/usb.h> #include <linux/iopoll.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> diff --git a/drivers/bluetooth/btmtksdio.c b/drivers/bluetooth/btmtksdio.c index 497e4c87f5be..11d33cd7b08f 100644 --- a/drivers/bluetooth/btmtksdio.c +++ b/drivers/bluetooth/btmtksdio.c @@ -10,7 +10,7 @@ * */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/atomic.h> #include <linux/gpio/consumer.h> #include <linux/init.h> diff --git a/drivers/bluetooth/btmtkuart.c b/drivers/bluetooth/btmtkuart.c index aa87c3e78871..64e4d835af52 100644 --- a/drivers/bluetooth/btmtkuart.c +++ b/drivers/bluetooth/btmtkuart.c @@ -8,7 +8,7 @@ * */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/atomic.h> #include <linux/clk.h> #include <linux/firmware.h> diff --git a/drivers/bluetooth/btnxpuart.c b/drivers/bluetooth/btnxpuart.c index 7c2030cec10e..5ea0d23e88c0 100644 --- a/drivers/bluetooth/btnxpuart.c +++ b/drivers/bluetooth/btnxpuart.c @@ -10,7 +10,7 @@ #include <linux/serdev.h> #include <linux/of.h> #include <linux/skbuff.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/firmware.h> #include <linux/string.h> #include <linux/crc8.h> diff --git a/drivers/bluetooth/btrsi.c b/drivers/bluetooth/btrsi.c index 0c91d7635ac3..6c1f584c8a33 100644 --- a/drivers/bluetooth/btrsi.c +++ b/drivers/bluetooth/btrsi.c @@ -17,7 +17,7 @@ #include <linux/kernel.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <net/rsi_91x.h> #define RSI_DMA_ALIGN 8 diff --git a/drivers/bluetooth/btrtl.c b/drivers/bluetooth/btrtl.c index 2d95b3ea046d..0bcb44cf7b31 100644 --- a/drivers/bluetooth/btrtl.c +++ b/drivers/bluetooth/btrtl.c @@ -7,7 +7,7 @@ #include <linux/module.h> #include <linux/firmware.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/usb.h> #include <net/bluetooth/bluetooth.h> diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index 6c9c761d5b93..f23c8801ad5c 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -17,7 +17,7 @@ #include <linux/suspend.h> #include <linux/gpio/consumer.h> #include <linux/debugfs.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> diff --git a/drivers/bluetooth/h4_recv.h b/drivers/bluetooth/h4_recv.h index 647d37ca4cdd..28cf2d8c2d48 100644 --- a/drivers/bluetooth/h4_recv.h +++ b/drivers/bluetooth/h4_recv.h @@ -6,7 +6,7 @@ * Copyright (C) 2015-2018 Intel Corporation */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> struct h4_recv_pkt { u8 type; /* Packet type */ diff --git a/drivers/bluetooth/hci_bcm4377.c b/drivers/bluetooth/hci_bcm4377.c index 77a5454a8721..9bce53e49cfa 100644 --- a/drivers/bluetooth/hci_bcm4377.c +++ b/drivers/bluetooth/hci_bcm4377.c @@ -17,7 +17,7 @@ #include <linux/pci.h> #include <linux/printk.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> diff --git a/drivers/bluetooth/hci_bcsp.c b/drivers/bluetooth/hci_bcsp.c index 2a5a27d713f8..76878119d910 100644 --- a/drivers/bluetooth/hci_bcsp.c +++ b/drivers/bluetooth/hci_bcsp.c @@ -25,7 +25,7 @@ #include <linux/ioctl.h> #include <linux/skbuff.h> #include <linux/bitrev.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> diff --git a/drivers/bluetooth/hci_h4.c b/drivers/bluetooth/hci_h4.c index 1d0cdf023243..9070e31a68bf 100644 --- a/drivers/bluetooth/hci_h4.c +++ b/drivers/bluetooth/hci_h4.c @@ -25,7 +25,7 @@ #include <linux/signal.h> #include <linux/ioctl.h> #include <linux/skbuff.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> diff --git a/drivers/bluetooth/hci_nokia.c b/drivers/bluetooth/hci_nokia.c index 62633d9ba7c4..49bbe4975be4 100644 --- a/drivers/bluetooth/hci_nokia.c +++ b/drivers/bluetooth/hci_nokia.c @@ -20,7 +20,7 @@ #include <linux/slab.h> #include <linux/string.h> #include <linux/types.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c index 678f150229e7..37fddf6055be 100644 --- a/drivers/bluetooth/hci_qca.c +++ b/drivers/bluetooth/hci_qca.c @@ -32,7 +32,7 @@ #include <linux/regulator/consumer.h> #include <linux/serdev.h> #include <linux/mutex.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> diff --git a/drivers/bluetooth/hci_vhci.c b/drivers/bluetooth/hci_vhci.c index aa6af351d02d..7651321d351c 100644 --- a/drivers/bluetooth/hci_vhci.c +++ b/drivers/bluetooth/hci_vhci.c @@ -9,7 +9,7 @@ */ #include <linux/module.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/atomic.h> #include <linux/kernel.h> diff --git a/drivers/char/tpm/tpm2-sessions.c b/drivers/char/tpm/tpm2-sessions.c index 44f60730cff4..511c67061728 100644 --- a/drivers/char/tpm/tpm2-sessions.c +++ b/drivers/char/tpm/tpm2-sessions.c @@ -71,7 +71,7 @@ #include "tpm.h" #include <linux/random.h> #include <linux/scatterlist.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <crypto/kpp.h> #include <crypto/ecdh.h> #include <crypto/hash.h> diff --git a/drivers/char/tpm/tpm2-space.c b/drivers/char/tpm/tpm2-space.c index 25a66870c165..60354cd53b5c 100644 --- a/drivers/char/tpm/tpm2-space.c +++ b/drivers/char/tpm/tpm2-space.c @@ -12,7 +12,7 @@ */ #include <linux/gfp.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "tpm.h" enum tpm2_handle_types { diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c index 99a7f2441e70..c62b208b42f1 100644 --- a/drivers/char/virtio_console.c +++ b/drivers/char/virtio_console.c @@ -2006,25 +2006,27 @@ static int virtcons_probe(struct virtio_device *vdev) multiport = true; } - err = init_vqs(portdev); - if (err < 0) { - dev_err(&vdev->dev, "Error %d initializing vqs\n", err); - goto free_chrdev; - } - spin_lock_init(&portdev->ports_lock); INIT_LIST_HEAD(&portdev->ports); INIT_LIST_HEAD(&portdev->list); - virtio_device_ready(portdev->vdev); - INIT_WORK(&portdev->config_work, &config_work_handler); INIT_WORK(&portdev->control_work, &control_work_handler); if (multiport) { spin_lock_init(&portdev->c_ivq_lock); spin_lock_init(&portdev->c_ovq_lock); + } + err = init_vqs(portdev); + if (err < 0) { + dev_err(&vdev->dev, "Error %d initializing vqs\n", err); + goto free_chrdev; + } + + virtio_device_ready(portdev->vdev); + + if (multiport) { err = fill_queue(portdev->c_ivq, &portdev->c_ivq_lock); if (err < 0) { dev_err(&vdev->dev, diff --git a/drivers/clk/clk-si5341.c b/drivers/clk/clk-si5341.c index 6e8dd7387cfd..5004888c7eca 100644 --- a/drivers/clk/clk-si5341.c +++ b/drivers/clk/clk-si5341.c @@ -21,7 +21,7 @@ #include <linux/regmap.h> #include <linux/regulator/consumer.h> #include <linux/slab.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define SI5341_NUM_INPUTS 4 diff --git a/drivers/comedi/drivers/usbduxsigma.c b/drivers/comedi/drivers/usbduxsigma.c index 2aaeaf44fbe5..3f215ae228b2 100644 --- a/drivers/comedi/drivers/usbduxsigma.c +++ b/drivers/comedi/drivers/usbduxsigma.c @@ -39,7 +39,7 @@ #include <linux/input.h> #include <linux/fcntl.h> #include <linux/compiler.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/comedi/comedi_usb.h> /* timeout for the USB-transfer in ms*/ diff --git a/drivers/counter/104-quad-8.c b/drivers/counter/104-quad-8.c index ed1f57511955..4a6868b8f58b 100644 --- a/drivers/counter/104-quad-8.c +++ b/drivers/counter/104-quad-8.c @@ -22,7 +22,7 @@ #include <linux/spinlock.h> #include <linux/types.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define QUAD8_EXTENT 32 diff --git a/drivers/counter/i8254.c b/drivers/counter/i8254.c index c41e4fdc9601..6d74e8ef92f0 100644 --- a/drivers/counter/i8254.c +++ b/drivers/counter/i8254.c @@ -15,7 +15,7 @@ #include <linux/mutex.h> #include <linux/regmap.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #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 1a5ad184d28f..2b8708475ac7 100644 --- a/drivers/cpufreq/cppc_cpufreq.c +++ b/drivers/cpufreq/cppc_cpufreq.c @@ -22,7 +22,7 @@ #include <linux/vmalloc.h> #include <uapi/linux/sched/types.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <acpi/cppc_acpi.h> diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index aaea9a39eced..b0018f371ea3 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 f7893e4ac59d..434f2b271012 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 <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/scatterlist.h> /* This is a totally arbitrary value */ diff --git a/drivers/crypto/caam/caamalg.c b/drivers/crypto/caam/caamalg.c index 066f08a3a040..2cfb1b8d8c7c 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 <asm/unaligned.h> +#include <linux/unaligned.h> #include <crypto/internal/aead.h> #include <crypto/internal/engine.h> #include <crypto/internal/skcipher.h> diff --git a/drivers/crypto/caam/caamalg_qi.c b/drivers/crypto/caam/caamalg_qi.c index 13347dfecf7a..65f6adb6c673 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 <crypto/xts.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/device.h> #include <linux/err.h> #include <linux/dma-mapping.h> diff --git a/drivers/crypto/caam/caamalg_qi2.c b/drivers/crypto/caam/caamalg_qi2.c index 44e1f8f46967..e809d030ab11 100644 --- a/drivers/crypto/caam/caamalg_qi2.c +++ b/drivers/crypto/caam/caamalg_qi2.c @@ -22,7 +22,7 @@ #include <soc/fsl/dpaa2-io.h> #include <soc/fsl/dpaa2-fd.h> #include <crypto/xts.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define CAAM_CRA_PRIORITY 2000 diff --git a/drivers/crypto/inside-secure/safexcel_cipher.c b/drivers/crypto/inside-secure/safexcel_cipher.c index 42677f7458b7..919e5a2cab95 100644 --- a/drivers/crypto/inside-secure/safexcel_cipher.c +++ b/drivers/crypto/inside-secure/safexcel_cipher.c @@ -5,7 +5,7 @@ * Antoine Tenart <antoine.tenart@free-electrons.com> */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/device.h> #include <linux/dma-mapping.h> #include <linux/dmapool.h> diff --git a/drivers/crypto/rockchip/rk3288_crypto_ahash.c b/drivers/crypto/rockchip/rk3288_crypto_ahash.c index a235e6c300f1..69d6019d8abc 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 <asm/unaligned.h> +#include <linux/unaligned.h> #include <crypto/internal/hash.h> #include <linux/device.h> #include <linux/err.h> diff --git a/drivers/crypto/stm32/stm32-crc32.c b/drivers/crypto/stm32/stm32-crc32.c index b0cf6d2fd352..e0faddbf8990 100644 --- a/drivers/crypto/stm32/stm32-crc32.c +++ b/drivers/crypto/stm32/stm32-crc32.c @@ -17,7 +17,7 @@ #include <crypto/internal/hash.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define DRIVER_NAME "stm32-crc32" #define CHKSUM_DIGEST_SIZE 4 diff --git a/drivers/cxl/core/cdat.c b/drivers/cxl/core/cdat.c index bb83867d9fec..ef1621d40f05 100644 --- a/drivers/cxl/core/cdat.c +++ b/drivers/cxl/core/cdat.c @@ -9,13 +9,12 @@ #include "cxlmem.h" #include "core.h" #include "cxl.h" -#include "core.h" struct dsmas_entry { struct range dpa_range; u8 handle; struct access_coordinate coord[ACCESS_COORDINATE_MAX]; - + struct access_coordinate cdat_coord[ACCESS_COORDINATE_MAX]; int entries; int qos_class; }; @@ -163,7 +162,7 @@ static int cdat_dslbis_handler(union acpi_subtable_headers *header, void *arg, val = cdat_normalize(le16_to_cpu(le_val), le64_to_cpu(le_base), dslbis->data_type); - cxl_access_coordinate_set(dent->coord, dslbis->data_type, val); + cxl_access_coordinate_set(dent->cdat_coord, dslbis->data_type, val); return 0; } @@ -220,7 +219,7 @@ static int cxl_port_perf_data_calculate(struct cxl_port *port, xa_for_each(dsmas_xa, index, dent) { int qos_class; - cxl_coordinates_combine(dent->coord, dent->coord, ep_c); + cxl_coordinates_combine(dent->coord, dent->cdat_coord, ep_c); dent->entries = 1; rc = cxl_root->ops->qos_class(cxl_root, &dent->coord[ACCESS_COORDINATE_CPU], @@ -241,8 +240,10 @@ static int cxl_port_perf_data_calculate(struct cxl_port *port, static void update_perf_entry(struct device *dev, struct dsmas_entry *dent, struct cxl_dpa_perf *dpa_perf) { - for (int i = 0; i < ACCESS_COORDINATE_MAX; i++) + for (int i = 0; i < ACCESS_COORDINATE_MAX; i++) { dpa_perf->coord[i] = dent->coord[i]; + dpa_perf->cdat_coord[i] = dent->cdat_coord[i]; + } dpa_perf->dpa_range = dent->dpa_range; dpa_perf->qos_class = dent->qos_class; dev_dbg(dev, @@ -546,19 +547,37 @@ void cxl_coordinates_combine(struct access_coordinate *out, MODULE_IMPORT_NS(CXL); -void cxl_region_perf_data_calculate(struct cxl_region *cxlr, - struct cxl_endpoint_decoder *cxled) +static void cxl_bandwidth_add(struct access_coordinate *coord, + struct access_coordinate *c1, + struct access_coordinate *c2) +{ + for (int i = 0; i < ACCESS_COORDINATE_MAX; i++) { + coord[i].read_bandwidth = c1[i].read_bandwidth + + c2[i].read_bandwidth; + coord[i].write_bandwidth = c1[i].write_bandwidth + + c2[i].write_bandwidth; + } +} + +static bool dpa_perf_contains(struct cxl_dpa_perf *perf, + struct resource *dpa_res) { - struct cxl_memdev *cxlmd = cxled_to_memdev(cxled); - struct cxl_dev_state *cxlds = cxlmd->cxlds; - struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlds); struct range dpa = { - .start = cxled->dpa_res->start, - .end = cxled->dpa_res->end, + .start = dpa_res->start, + .end = dpa_res->end, }; + + return range_contains(&perf->dpa_range, &dpa); +} + +static struct cxl_dpa_perf *cxled_get_dpa_perf(struct cxl_endpoint_decoder *cxled, + enum cxl_decoder_mode mode) +{ + struct cxl_memdev *cxlmd = cxled_to_memdev(cxled); + struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds); struct cxl_dpa_perf *perf; - switch (cxlr->mode) { + switch (mode) { case CXL_DECODER_RAM: perf = &mds->ram_perf; break; @@ -566,12 +585,473 @@ void cxl_region_perf_data_calculate(struct cxl_region *cxlr, perf = &mds->pmem_perf; break; default: + return ERR_PTR(-EINVAL); + } + + if (!dpa_perf_contains(perf, cxled->dpa_res)) + return ERR_PTR(-EINVAL); + + return perf; +} + +/* + * Transient context for containing the current calculation of bandwidth when + * doing walking the port hierarchy to deal with shared upstream link. + */ +struct cxl_perf_ctx { + struct access_coordinate coord[ACCESS_COORDINATE_MAX]; + struct cxl_port *port; +}; + +/** + * cxl_endpoint_gather_bandwidth - collect all the endpoint bandwidth in an xarray + * @cxlr: CXL region for the bandwidth calculation + * @cxled: endpoint decoder to start on + * @usp_xa: (output) the xarray that collects all the bandwidth coordinates + * indexed by the upstream device with data of 'struct cxl_perf_ctx'. + * @gp_is_root: (output) bool of whether the grandparent is cxl root. + * + * Return: 0 for success or -errno + * + * Collects aggregated endpoint bandwidth and store the bandwidth in + * an xarray indexed by the upstream device of the switch or the RP + * device. Each endpoint consists the minimum of the bandwidth from DSLBIS + * from the endpoint CDAT, the endpoint upstream link bandwidth, and the + * bandwidth from the SSLBIS of the switch CDAT for the switch upstream port to + * the downstream port that's associated with the endpoint. If the + * device is directly connected to a RP, then no SSLBIS is involved. + */ +static int cxl_endpoint_gather_bandwidth(struct cxl_region *cxlr, + struct cxl_endpoint_decoder *cxled, + struct xarray *usp_xa, + bool *gp_is_root) +{ + struct cxl_port *endpoint = to_cxl_port(cxled->cxld.dev.parent); + struct cxl_port *parent_port = to_cxl_port(endpoint->dev.parent); + struct cxl_port *gp_port = to_cxl_port(parent_port->dev.parent); + struct access_coordinate pci_coord[ACCESS_COORDINATE_MAX]; + struct access_coordinate sw_coord[ACCESS_COORDINATE_MAX]; + struct access_coordinate ep_coord[ACCESS_COORDINATE_MAX]; + struct cxl_memdev *cxlmd = cxled_to_memdev(cxled); + struct cxl_dev_state *cxlds = cxlmd->cxlds; + struct pci_dev *pdev = to_pci_dev(cxlds->dev); + struct cxl_perf_ctx *perf_ctx; + struct cxl_dpa_perf *perf; + unsigned long index; + void *ptr; + int rc; + + if (cxlds->rcd) + return -ENODEV; + + perf = cxled_get_dpa_perf(cxled, cxlr->mode); + if (IS_ERR(perf)) + return PTR_ERR(perf); + + gp_port = to_cxl_port(parent_port->dev.parent); + *gp_is_root = is_cxl_root(gp_port); + + /* + * If the grandparent is cxl root, then index is the root port, + * otherwise it's the parent switch upstream device. + */ + if (*gp_is_root) + index = (unsigned long)endpoint->parent_dport->dport_dev; + else + index = (unsigned long)parent_port->uport_dev; + + perf_ctx = xa_load(usp_xa, index); + if (!perf_ctx) { + struct cxl_perf_ctx *c __free(kfree) = + kzalloc(sizeof(*perf_ctx), GFP_KERNEL); + + if (!c) + return -ENOMEM; + ptr = xa_store(usp_xa, index, c, GFP_KERNEL); + if (xa_is_err(ptr)) + return xa_err(ptr); + perf_ctx = no_free_ptr(c); + perf_ctx->port = parent_port; + } + + /* Direct upstream link from EP bandwidth */ + rc = cxl_pci_get_bandwidth(pdev, pci_coord); + if (rc < 0) + return rc; + + /* + * Min of upstream link bandwidth and Endpoint CDAT bandwidth from + * DSLBIS. + */ + cxl_coordinates_combine(ep_coord, pci_coord, perf->cdat_coord); + + /* + * If grandparent port is root, then there's no switch involved and + * the endpoint is connected to a root port. + */ + if (!*gp_is_root) { + /* + * Retrieve the switch SSLBIS for switch downstream port + * associated with the endpoint bandwidth. + */ + rc = cxl_port_get_switch_dport_bandwidth(endpoint, sw_coord); + if (rc) + return rc; + + /* + * Min of the earlier coordinates with the switch SSLBIS + * bandwidth + */ + cxl_coordinates_combine(ep_coord, ep_coord, sw_coord); + } + + /* + * Aggregate the computed bandwidth with the current aggregated bandwidth + * of the endpoints with the same switch upstream device or RP. + */ + cxl_bandwidth_add(perf_ctx->coord, perf_ctx->coord, ep_coord); + + return 0; +} + +static void free_perf_xa(struct xarray *xa) +{ + struct cxl_perf_ctx *ctx; + unsigned long index; + + if (!xa) return; + + xa_for_each(xa, index, ctx) + kfree(ctx); + xa_destroy(xa); + kfree(xa); +} +DEFINE_FREE(free_perf_xa, struct xarray *, if (_T) free_perf_xa(_T)) + +/** + * cxl_switch_gather_bandwidth - collect all the bandwidth at switch level in an xarray + * @cxlr: The region being operated on + * @input_xa: xarray indexed by upstream device of a switch with data of 'struct + * cxl_perf_ctx' + * @gp_is_root: (output) bool of whether the grandparent is cxl root. + * + * Return: a xarray of resulting cxl_perf_ctx per parent switch or root port + * or ERR_PTR(-errno) + * + * Iterate through the xarray. Take the minimum of the downstream calculated + * bandwidth, the upstream link bandwidth, and the SSLBIS of the upstream + * switch if exists. Sum the resulting bandwidth under the switch upstream + * device or a RP device. The function can be iterated over multiple switches + * if the switches are present. + */ +static struct xarray *cxl_switch_gather_bandwidth(struct cxl_region *cxlr, + struct xarray *input_xa, + bool *gp_is_root) +{ + struct xarray *res_xa __free(free_perf_xa) = + kzalloc(sizeof(*res_xa), GFP_KERNEL); + struct access_coordinate coords[ACCESS_COORDINATE_MAX]; + struct cxl_perf_ctx *ctx, *us_ctx; + unsigned long index, us_index; + int dev_count = 0; + int gp_count = 0; + void *ptr; + int rc; + + if (!res_xa) + return ERR_PTR(-ENOMEM); + xa_init(res_xa); + + xa_for_each(input_xa, index, ctx) { + struct device *dev = (struct device *)index; + struct cxl_port *port = ctx->port; + struct cxl_port *parent_port = to_cxl_port(port->dev.parent); + struct cxl_port *gp_port = to_cxl_port(parent_port->dev.parent); + struct cxl_dport *dport = port->parent_dport; + bool is_root = false; + + dev_count++; + if (is_cxl_root(gp_port)) { + is_root = true; + gp_count++; + } + + /* + * If the grandparent is cxl root, then index is the root port, + * otherwise it's the parent switch upstream device. + */ + if (is_root) + us_index = (unsigned long)port->parent_dport->dport_dev; + else + us_index = (unsigned long)parent_port->uport_dev; + + us_ctx = xa_load(res_xa, us_index); + if (!us_ctx) { + struct cxl_perf_ctx *n __free(kfree) = + kzalloc(sizeof(*n), GFP_KERNEL); + + if (!n) + return ERR_PTR(-ENOMEM); + + ptr = xa_store(res_xa, us_index, n, GFP_KERNEL); + if (xa_is_err(ptr)) + return ERR_PTR(xa_err(ptr)); + us_ctx = no_free_ptr(n); + us_ctx->port = parent_port; + } + + /* + * If the device isn't an upstream PCIe port, there's something + * wrong with the topology. + */ + if (!dev_is_pci(dev)) + return ERR_PTR(-EINVAL); + + /* Retrieve the upstream link bandwidth */ + rc = cxl_pci_get_bandwidth(to_pci_dev(dev), coords); + if (rc) + return ERR_PTR(-ENXIO); + + /* + * Take the min of downstream bandwidth and the upstream link + * bandwidth. + */ + cxl_coordinates_combine(coords, coords, ctx->coord); + + /* + * Take the min of the calculated bandwdith and the upstream + * switch SSLBIS bandwidth if there's a parent switch + */ + if (!is_root) + cxl_coordinates_combine(coords, coords, dport->coord); + + /* + * Aggregate the calculated bandwidth common to an upstream + * switch. + */ + cxl_bandwidth_add(us_ctx->coord, us_ctx->coord, coords); } + /* Asymmetric topology detected. */ + if (gp_count) { + if (gp_count != dev_count) { + dev_dbg(&cxlr->dev, + "Asymmetric hierarchy detected, bandwidth not updated\n"); + return ERR_PTR(-EOPNOTSUPP); + } + *gp_is_root = true; + } + + return no_free_ptr(res_xa); +} + +/** + * cxl_rp_gather_bandwidth - handle the root port level bandwidth collection + * @xa: the xarray that holds the cxl_perf_ctx that has the bandwidth calculated + * below each root port device. + * + * Return: xarray that holds cxl_perf_ctx per host bridge or ERR_PTR(-errno) + */ +static struct xarray *cxl_rp_gather_bandwidth(struct xarray *xa) +{ + struct xarray *hb_xa __free(free_perf_xa) = + kzalloc(sizeof(*hb_xa), GFP_KERNEL); + struct cxl_perf_ctx *ctx; + unsigned long index; + + if (!hb_xa) + return ERR_PTR(-ENOMEM); + xa_init(hb_xa); + + xa_for_each(xa, index, ctx) { + struct cxl_port *port = ctx->port; + unsigned long hb_index = (unsigned long)port->uport_dev; + struct cxl_perf_ctx *hb_ctx; + void *ptr; + + hb_ctx = xa_load(hb_xa, hb_index); + if (!hb_ctx) { + struct cxl_perf_ctx *n __free(kfree) = + kzalloc(sizeof(*n), GFP_KERNEL); + + if (!n) + return ERR_PTR(-ENOMEM); + ptr = xa_store(hb_xa, hb_index, n, GFP_KERNEL); + if (xa_is_err(ptr)) + return ERR_PTR(xa_err(ptr)); + hb_ctx = no_free_ptr(n); + hb_ctx->port = port; + } + + cxl_bandwidth_add(hb_ctx->coord, hb_ctx->coord, ctx->coord); + } + + return no_free_ptr(hb_xa); +} + +/** + * cxl_hb_gather_bandwidth - handle the host bridge level bandwidth collection + * @xa: the xarray that holds the cxl_perf_ctx that has the bandwidth calculated + * below each host bridge. + * + * Return: xarray that holds cxl_perf_ctx per ACPI0017 device or ERR_PTR(-errno) + */ +static struct xarray *cxl_hb_gather_bandwidth(struct xarray *xa) +{ + struct xarray *mw_xa __free(free_perf_xa) = + kzalloc(sizeof(*mw_xa), GFP_KERNEL); + struct cxl_perf_ctx *ctx; + unsigned long index; + + if (!mw_xa) + return ERR_PTR(-ENOMEM); + xa_init(mw_xa); + + xa_for_each(xa, index, ctx) { + struct cxl_port *port = ctx->port; + struct cxl_port *parent_port; + struct cxl_perf_ctx *mw_ctx; + struct cxl_dport *dport; + unsigned long mw_index; + void *ptr; + + parent_port = to_cxl_port(port->dev.parent); + mw_index = (unsigned long)parent_port->uport_dev; + + mw_ctx = xa_load(mw_xa, mw_index); + if (!mw_ctx) { + struct cxl_perf_ctx *n __free(kfree) = + kzalloc(sizeof(*n), GFP_KERNEL); + + if (!n) + return ERR_PTR(-ENOMEM); + ptr = xa_store(mw_xa, mw_index, n, GFP_KERNEL); + if (xa_is_err(ptr)) + return ERR_PTR(xa_err(ptr)); + mw_ctx = no_free_ptr(n); + } + + dport = port->parent_dport; + cxl_coordinates_combine(ctx->coord, ctx->coord, dport->coord); + cxl_bandwidth_add(mw_ctx->coord, mw_ctx->coord, ctx->coord); + } + + return no_free_ptr(mw_xa); +} + +/** + * cxl_region_update_bandwidth - Update the bandwidth access coordinates of a region + * @cxlr: The region being operated on + * @input_xa: xarray holds cxl_perf_ctx wht calculated bandwidth per ACPI0017 instance + */ +static void cxl_region_update_bandwidth(struct cxl_region *cxlr, + struct xarray *input_xa) +{ + struct access_coordinate coord[ACCESS_COORDINATE_MAX]; + struct cxl_perf_ctx *ctx; + unsigned long index; + + memset(coord, 0, sizeof(coord)); + xa_for_each(input_xa, index, ctx) + cxl_bandwidth_add(coord, coord, ctx->coord); + + for (int i = 0; i < ACCESS_COORDINATE_MAX; i++) { + cxlr->coord[i].read_bandwidth = coord[i].read_bandwidth; + cxlr->coord[i].write_bandwidth = coord[i].write_bandwidth; + } +} + +/** + * cxl_region_shared_upstream_bandwidth_update - Recalculate the bandwidth for + * the region + * @cxlr: the cxl region to recalculate + * + * The function walks the topology from bottom up and calculates the bandwidth. It + * starts at the endpoints, processes at the switches if any, processes at the rootport + * level, at the host bridge level, and finally aggregates at the region. + */ +void cxl_region_shared_upstream_bandwidth_update(struct cxl_region *cxlr) +{ + struct xarray *working_xa; + int root_count = 0; + bool is_root; + int rc; + + lockdep_assert_held(&cxl_dpa_rwsem); + + struct xarray *usp_xa __free(free_perf_xa) = + kzalloc(sizeof(*usp_xa), GFP_KERNEL); + + if (!usp_xa) + return; + + xa_init(usp_xa); + + /* Collect bandwidth data from all the endpoints. */ + for (int i = 0; i < cxlr->params.nr_targets; i++) { + struct cxl_endpoint_decoder *cxled = cxlr->params.targets[i]; + + is_root = false; + rc = cxl_endpoint_gather_bandwidth(cxlr, cxled, usp_xa, &is_root); + if (rc) + return; + root_count += is_root; + } + + /* Detect asymmetric hierarchy with some direct attached endpoints. */ + if (root_count && root_count != cxlr->params.nr_targets) { + dev_dbg(&cxlr->dev, + "Asymmetric hierarchy detected, bandwidth not updated\n"); + return; + } + + /* + * Walk up one or more switches to deal with the bandwidth of the + * switches if they exist. Endpoints directly attached to RPs skip + * over this part. + */ + if (!root_count) { + do { + working_xa = cxl_switch_gather_bandwidth(cxlr, usp_xa, + &is_root); + if (IS_ERR(working_xa)) + return; + free_perf_xa(usp_xa); + usp_xa = working_xa; + } while (!is_root); + } + + /* Handle the bandwidth at the root port of the hierarchy */ + working_xa = cxl_rp_gather_bandwidth(usp_xa); + if (IS_ERR(working_xa)) + return; + free_perf_xa(usp_xa); + usp_xa = working_xa; + + /* Handle the bandwidth at the host bridge of the hierarchy */ + working_xa = cxl_hb_gather_bandwidth(usp_xa); + if (IS_ERR(working_xa)) + return; + free_perf_xa(usp_xa); + usp_xa = working_xa; + + /* + * Aggregate all the bandwidth collected per CFMWS (ACPI0017) and + * update the region bandwidth with the final calculated values. + */ + cxl_region_update_bandwidth(cxlr, usp_xa); +} + +void cxl_region_perf_data_calculate(struct cxl_region *cxlr, + struct cxl_endpoint_decoder *cxled) +{ + struct cxl_dpa_perf *perf; + lockdep_assert_held(&cxl_dpa_rwsem); - if (!range_contains(&perf->dpa_range, &dpa)) + perf = cxled_get_dpa_perf(cxled, cxlr->mode); + if (IS_ERR(perf)) return; for (int i = 0; i < ACCESS_COORDINATE_MAX; i++) { diff --git a/drivers/cxl/core/core.h b/drivers/cxl/core/core.h index 72a506c9dbd0..0c62b4069ba0 100644 --- a/drivers/cxl/core/core.h +++ b/drivers/cxl/core/core.h @@ -103,9 +103,11 @@ enum cxl_poison_trace_type { }; long cxl_pci_get_latency(struct pci_dev *pdev); - +int cxl_pci_get_bandwidth(struct pci_dev *pdev, struct access_coordinate *c); int cxl_update_hmat_access_coordinates(int nid, struct cxl_region *cxlr, enum access_coordinate_class access); bool cxl_need_node_perf_attrs_update(int nid); +int cxl_port_get_switch_dport_bandwidth(struct cxl_port *port, + struct access_coordinate *c); #endif /* __CXL_CORE_H__ */ diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c index e5cdeafdf76e..5175138c4fb7 100644 --- a/drivers/cxl/core/mbox.c +++ b/drivers/cxl/core/mbox.c @@ -4,7 +4,7 @@ #include <linux/debugfs.h> #include <linux/ktime.h> #include <linux/mutex.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <cxlpci.h> #include <cxlmem.h> #include <cxl.h> @@ -225,7 +225,7 @@ static const char *cxl_mem_opcode_to_name(u16 opcode) /** * cxl_internal_send_cmd() - Kernel internal interface to send a mailbox command - * @mds: The driver data for the operation + * @cxl_mbox: CXL mailbox context * @mbox_cmd: initialized command to execute * * Context: Any context. @@ -241,19 +241,19 @@ static const char *cxl_mem_opcode_to_name(u16 opcode) * error. While this distinction can be useful for commands from userspace, the * kernel will only be able to use results when both are successful. */ -int cxl_internal_send_cmd(struct cxl_memdev_state *mds, +int cxl_internal_send_cmd(struct cxl_mailbox *cxl_mbox, struct cxl_mbox_cmd *mbox_cmd) { size_t out_size, min_out; int rc; - if (mbox_cmd->size_in > mds->payload_size || - mbox_cmd->size_out > mds->payload_size) + if (mbox_cmd->size_in > cxl_mbox->payload_size || + mbox_cmd->size_out > cxl_mbox->payload_size) return -E2BIG; out_size = mbox_cmd->size_out; min_out = mbox_cmd->min_out; - rc = mds->mbox_send(mds, mbox_cmd); + rc = cxl_mbox->mbox_send(cxl_mbox, mbox_cmd); /* * EIO is reserved for a payload size mismatch and mbox_send() * may not return this error. @@ -353,6 +353,7 @@ static int cxl_mbox_cmd_ctor(struct cxl_mbox_cmd *mbox, struct cxl_memdev_state *mds, u16 opcode, size_t in_size, size_t out_size, u64 in_payload) { + struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox; *mbox = (struct cxl_mbox_cmd) { .opcode = opcode, .size_in = in_size, @@ -374,7 +375,7 @@ static int cxl_mbox_cmd_ctor(struct cxl_mbox_cmd *mbox, /* Prepare to handle a full payload for variable sized output */ if (out_size == CXL_VARIABLE_PAYLOAD) - mbox->size_out = mds->payload_size; + mbox->size_out = cxl_mbox->payload_size; else mbox->size_out = out_size; @@ -398,6 +399,8 @@ static int cxl_to_mem_cmd_raw(struct cxl_mem_command *mem_cmd, const struct cxl_send_command *send_cmd, struct cxl_memdev_state *mds) { + struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox; + if (send_cmd->raw.rsvd) return -EINVAL; @@ -406,7 +409,7 @@ static int cxl_to_mem_cmd_raw(struct cxl_mem_command *mem_cmd, * gets passed along without further checking, so it must be * validated here. */ - if (send_cmd->out.size > mds->payload_size) + if (send_cmd->out.size > cxl_mbox->payload_size) return -EINVAL; if (!cxl_mem_raw_command_allowed(send_cmd->raw.opcode)) @@ -494,6 +497,7 @@ static int cxl_validate_cmd_from_user(struct cxl_mbox_cmd *mbox_cmd, struct cxl_memdev_state *mds, const struct cxl_send_command *send_cmd) { + struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox; struct cxl_mem_command mem_cmd; int rc; @@ -505,7 +509,7 @@ static int cxl_validate_cmd_from_user(struct cxl_mbox_cmd *mbox_cmd, * supports, but output can be arbitrarily large (simply write out as * much data as the hardware provides). */ - if (send_cmd->in.size > mds->payload_size) + if (send_cmd->in.size > cxl_mbox->payload_size) return -EINVAL; /* Sanitize and construct a cxl_mem_command */ @@ -542,7 +546,7 @@ int cxl_query_cmd(struct cxl_memdev *cxlmd, return put_user(ARRAY_SIZE(cxl_mem_commands), &q->n_commands); /* - * otherwise, return max(n_commands, total commands) cxl_command_info + * otherwise, return min(n_commands, total commands) cxl_command_info * structures. */ cxl_for_each_cmd(cmd) { @@ -591,6 +595,7 @@ static int handle_mailbox_cmd_from_user(struct cxl_memdev_state *mds, u64 out_payload, s32 *size_out, u32 *retval) { + struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox; struct device *dev = mds->cxlds.dev; int rc; @@ -601,7 +606,7 @@ static int handle_mailbox_cmd_from_user(struct cxl_memdev_state *mds, cxl_mem_opcode_to_name(mbox_cmd->opcode), mbox_cmd->opcode, mbox_cmd->size_in); - rc = mds->mbox_send(mds, mbox_cmd); + rc = cxl_mbox->mbox_send(cxl_mbox, mbox_cmd); if (rc) goto out; @@ -659,11 +664,12 @@ int cxl_send_cmd(struct cxl_memdev *cxlmd, struct cxl_send_command __user *s) static int cxl_xfer_log(struct cxl_memdev_state *mds, uuid_t *uuid, u32 *size, u8 *out) { + struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox; u32 remaining = *size; u32 offset = 0; while (remaining) { - u32 xfer_size = min_t(u32, remaining, mds->payload_size); + u32 xfer_size = min_t(u32, remaining, cxl_mbox->payload_size); struct cxl_mbox_cmd mbox_cmd; struct cxl_mbox_get_log log; int rc; @@ -682,7 +688,7 @@ static int cxl_xfer_log(struct cxl_memdev_state *mds, uuid_t *uuid, .payload_out = out, }; - rc = cxl_internal_send_cmd(mds, &mbox_cmd); + rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd); /* * The output payload length that indicates the number @@ -752,22 +758,23 @@ static void cxl_walk_cel(struct cxl_memdev_state *mds, size_t size, u8 *cel) static struct cxl_mbox_get_supported_logs *cxl_get_gsl(struct cxl_memdev_state *mds) { + struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox; struct cxl_mbox_get_supported_logs *ret; struct cxl_mbox_cmd mbox_cmd; int rc; - ret = kvmalloc(mds->payload_size, GFP_KERNEL); + ret = kvmalloc(cxl_mbox->payload_size, GFP_KERNEL); if (!ret) return ERR_PTR(-ENOMEM); mbox_cmd = (struct cxl_mbox_cmd) { .opcode = CXL_MBOX_OP_GET_SUPPORTED_LOGS, - .size_out = mds->payload_size, + .size_out = cxl_mbox->payload_size, .payload_out = ret, /* At least the record number field must be valid */ .min_out = 2, }; - rc = cxl_internal_send_cmd(mds, &mbox_cmd); + rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd); if (rc < 0) { kvfree(ret); return ERR_PTR(rc); @@ -910,6 +917,7 @@ static int cxl_clear_event_record(struct cxl_memdev_state *mds, enum cxl_event_log_type log, struct cxl_get_event_payload *get_pl) { + struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox; struct cxl_mbox_clear_event_payload *payload; u16 total = le16_to_cpu(get_pl->record_count); u8 max_handles = CXL_CLEAR_EVENT_MAX_HANDLES; @@ -920,8 +928,8 @@ static int cxl_clear_event_record(struct cxl_memdev_state *mds, int i; /* Payload size may limit the max handles */ - if (pl_size > mds->payload_size) { - max_handles = (mds->payload_size - sizeof(*payload)) / + if (pl_size > cxl_mbox->payload_size) { + max_handles = (cxl_mbox->payload_size - sizeof(*payload)) / sizeof(__le16); pl_size = struct_size(payload, handles, max_handles); } @@ -955,7 +963,7 @@ static int cxl_clear_event_record(struct cxl_memdev_state *mds, if (i == max_handles) { payload->nr_recs = i; - rc = cxl_internal_send_cmd(mds, &mbox_cmd); + rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd); if (rc) goto free_pl; i = 0; @@ -966,7 +974,7 @@ static int cxl_clear_event_record(struct cxl_memdev_state *mds, if (i) { payload->nr_recs = i; mbox_cmd.size_in = struct_size(payload, handles, i); - rc = cxl_internal_send_cmd(mds, &mbox_cmd); + rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd); if (rc) goto free_pl; } @@ -979,6 +987,7 @@ free_pl: static void cxl_mem_get_records_log(struct cxl_memdev_state *mds, enum cxl_event_log_type type) { + struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox; struct cxl_memdev *cxlmd = mds->cxlds.cxlmd; struct device *dev = mds->cxlds.dev; struct cxl_get_event_payload *payload; @@ -995,11 +1004,11 @@ static void cxl_mem_get_records_log(struct cxl_memdev_state *mds, .payload_in = &log_type, .size_in = sizeof(log_type), .payload_out = payload, - .size_out = mds->payload_size, + .size_out = cxl_mbox->payload_size, .min_out = struct_size(payload, records, 0), }; - rc = cxl_internal_send_cmd(mds, &mbox_cmd); + rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd); if (rc) { dev_err_ratelimited(dev, "Event log '%d': Failed to query event records : %d", @@ -1070,6 +1079,7 @@ EXPORT_SYMBOL_NS_GPL(cxl_mem_get_event_records, CXL); */ static int cxl_mem_get_partition_info(struct cxl_memdev_state *mds) { + struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox; struct cxl_mbox_get_partition_info pi; struct cxl_mbox_cmd mbox_cmd; int rc; @@ -1079,7 +1089,7 @@ static int cxl_mem_get_partition_info(struct cxl_memdev_state *mds) .size_out = sizeof(pi), .payload_out = &pi, }; - rc = cxl_internal_send_cmd(mds, &mbox_cmd); + rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd); if (rc) return rc; @@ -1106,6 +1116,7 @@ static int cxl_mem_get_partition_info(struct cxl_memdev_state *mds) */ int cxl_dev_state_identify(struct cxl_memdev_state *mds) { + struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox; /* See CXL 2.0 Table 175 Identify Memory Device Output Payload */ struct cxl_mbox_identify id; struct cxl_mbox_cmd mbox_cmd; @@ -1120,7 +1131,7 @@ int cxl_dev_state_identify(struct cxl_memdev_state *mds) .size_out = sizeof(id), .payload_out = &id, }; - rc = cxl_internal_send_cmd(mds, &mbox_cmd); + rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd); if (rc < 0) return rc; @@ -1148,6 +1159,7 @@ EXPORT_SYMBOL_NS_GPL(cxl_dev_state_identify, CXL); static int __cxl_mem_sanitize(struct cxl_memdev_state *mds, u16 cmd) { + struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox; int rc; u32 sec_out = 0; struct cxl_get_security_output { @@ -1159,14 +1171,13 @@ static int __cxl_mem_sanitize(struct cxl_memdev_state *mds, u16 cmd) .size_out = sizeof(out), }; struct cxl_mbox_cmd mbox_cmd = { .opcode = cmd }; - struct cxl_dev_state *cxlds = &mds->cxlds; if (cmd != CXL_MBOX_OP_SANITIZE && cmd != CXL_MBOX_OP_SECURE_ERASE) return -EINVAL; - rc = cxl_internal_send_cmd(mds, &sec_cmd); + rc = cxl_internal_send_cmd(cxl_mbox, &sec_cmd); if (rc < 0) { - dev_err(cxlds->dev, "Failed to get security state : %d", rc); + dev_err(cxl_mbox->host, "Failed to get security state : %d", rc); return rc; } @@ -1183,9 +1194,9 @@ static int __cxl_mem_sanitize(struct cxl_memdev_state *mds, u16 cmd) sec_out & CXL_PMEM_SEC_STATE_LOCKED) return -EINVAL; - rc = cxl_internal_send_cmd(mds, &mbox_cmd); + rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd); if (rc < 0) { - dev_err(cxlds->dev, "Failed to sanitize device : %d", rc); + dev_err(cxl_mbox->host, "Failed to sanitize device : %d", rc); return rc; } @@ -1214,7 +1225,7 @@ int cxl_mem_sanitize(struct cxl_memdev *cxlmd, u16 cmd) int rc; /* synchronize with cxl_mem_probe() and decoder write operations */ - device_lock(&cxlmd->dev); + guard(device)(&cxlmd->dev); endpoint = cxlmd->endpoint; down_read(&cxl_region_rwsem); /* @@ -1226,7 +1237,6 @@ int cxl_mem_sanitize(struct cxl_memdev *cxlmd, u16 cmd) else rc = -EBUSY; up_read(&cxl_region_rwsem); - device_unlock(&cxlmd->dev); return rc; } @@ -1300,6 +1310,7 @@ EXPORT_SYMBOL_NS_GPL(cxl_mem_create_range_info, CXL); int cxl_set_timestamp(struct cxl_memdev_state *mds) { + struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox; struct cxl_mbox_cmd mbox_cmd; struct cxl_mbox_set_timestamp_in pi; int rc; @@ -1311,7 +1322,7 @@ int cxl_set_timestamp(struct cxl_memdev_state *mds) .payload_in = &pi, }; - rc = cxl_internal_send_cmd(mds, &mbox_cmd); + rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd); /* * Command is optional. Devices may have another way of providing * a timestamp, or may return all 0s in timestamp fields. @@ -1328,6 +1339,7 @@ int cxl_mem_get_poison(struct cxl_memdev *cxlmd, u64 offset, u64 len, struct cxl_region *cxlr) { struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds); + struct cxl_mailbox *cxl_mbox = &cxlmd->cxlds->cxl_mbox; struct cxl_mbox_poison_out *po; struct cxl_mbox_poison_in pi; int nr_records = 0; @@ -1346,12 +1358,12 @@ int cxl_mem_get_poison(struct cxl_memdev *cxlmd, u64 offset, u64 len, .opcode = CXL_MBOX_OP_GET_POISON, .size_in = sizeof(pi), .payload_in = &pi, - .size_out = mds->payload_size, + .size_out = cxl_mbox->payload_size, .payload_out = po, .min_out = struct_size(po, record, 0), }; - rc = cxl_internal_send_cmd(mds, &mbox_cmd); + rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd); if (rc) break; @@ -1382,7 +1394,9 @@ static void free_poison_buf(void *buf) /* Get Poison List output buffer is protected by mds->poison.lock */ static int cxl_poison_alloc_buf(struct cxl_memdev_state *mds) { - mds->poison.list_out = kvmalloc(mds->payload_size, GFP_KERNEL); + struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox; + + mds->poison.list_out = kvmalloc(cxl_mbox->payload_size, GFP_KERNEL); if (!mds->poison.list_out) return -ENOMEM; @@ -1408,6 +1422,19 @@ int cxl_poison_state_init(struct cxl_memdev_state *mds) } EXPORT_SYMBOL_NS_GPL(cxl_poison_state_init, CXL); +int cxl_mailbox_init(struct cxl_mailbox *cxl_mbox, struct device *host) +{ + if (!cxl_mbox || !host) + return -EINVAL; + + cxl_mbox->host = host; + mutex_init(&cxl_mbox->mbox_mutex); + rcuwait_init(&cxl_mbox->mbox_wait); + + return 0; +} +EXPORT_SYMBOL_NS_GPL(cxl_mailbox_init, CXL); + struct cxl_memdev_state *cxl_memdev_state_create(struct device *dev) { struct cxl_memdev_state *mds; @@ -1418,7 +1445,6 @@ struct cxl_memdev_state *cxl_memdev_state_create(struct device *dev) return ERR_PTR(-ENOMEM); } - mutex_init(&mds->mbox_mutex); mutex_init(&mds->event.log_lock); mds->cxlds.dev = dev; mds->cxlds.reg_map.host = dev; diff --git a/drivers/cxl/core/memdev.c b/drivers/cxl/core/memdev.c index 0277726afd04..84fefb76dafa 100644 --- a/drivers/cxl/core/memdev.c +++ b/drivers/cxl/core/memdev.c @@ -58,7 +58,7 @@ static ssize_t payload_max_show(struct device *dev, if (!mds) return sysfs_emit(buf, "\n"); - return sysfs_emit(buf, "%zu\n", mds->payload_size); + return sysfs_emit(buf, "%zu\n", cxlds->cxl_mbox.payload_size); } static DEVICE_ATTR_RO(payload_max); @@ -124,15 +124,16 @@ static ssize_t security_state_show(struct device *dev, { struct cxl_memdev *cxlmd = to_cxl_memdev(dev); struct cxl_dev_state *cxlds = cxlmd->cxlds; + struct cxl_mailbox *cxl_mbox = &cxlds->cxl_mbox; struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlds); unsigned long state = mds->security.state; int rc = 0; /* sync with latest submission state */ - mutex_lock(&mds->mbox_mutex); + mutex_lock(&cxl_mbox->mbox_mutex); if (mds->security.sanitize_active) rc = sysfs_emit(buf, "sanitize\n"); - mutex_unlock(&mds->mbox_mutex); + mutex_unlock(&cxl_mbox->mbox_mutex); if (rc) return rc; @@ -277,7 +278,7 @@ static int cxl_validate_poison_dpa(struct cxl_memdev *cxlmd, u64 dpa) int cxl_inject_poison(struct cxl_memdev *cxlmd, u64 dpa) { - struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds); + struct cxl_mailbox *cxl_mbox = &cxlmd->cxlds->cxl_mbox; struct cxl_mbox_inject_poison inject; struct cxl_poison_record record; struct cxl_mbox_cmd mbox_cmd; @@ -307,13 +308,13 @@ int cxl_inject_poison(struct cxl_memdev *cxlmd, u64 dpa) .size_in = sizeof(inject), .payload_in = &inject, }; - rc = cxl_internal_send_cmd(mds, &mbox_cmd); + rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd); if (rc) goto out; cxlr = cxl_dpa_to_region(cxlmd, dpa); if (cxlr) - dev_warn_once(mds->cxlds.dev, + dev_warn_once(cxl_mbox->host, "poison inject dpa:%#llx region: %s\n", dpa, dev_name(&cxlr->dev)); @@ -332,7 +333,7 @@ EXPORT_SYMBOL_NS_GPL(cxl_inject_poison, CXL); int cxl_clear_poison(struct cxl_memdev *cxlmd, u64 dpa) { - struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds); + struct cxl_mailbox *cxl_mbox = &cxlmd->cxlds->cxl_mbox; struct cxl_mbox_clear_poison clear; struct cxl_poison_record record; struct cxl_mbox_cmd mbox_cmd; @@ -371,13 +372,13 @@ int cxl_clear_poison(struct cxl_memdev *cxlmd, u64 dpa) .payload_in = &clear, }; - rc = cxl_internal_send_cmd(mds, &mbox_cmd); + rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd); if (rc) goto out; cxlr = cxl_dpa_to_region(cxlmd, dpa); if (cxlr) - dev_warn_once(mds->cxlds.dev, + dev_warn_once(cxl_mbox->host, "poison clear dpa:%#llx region: %s\n", dpa, dev_name(&cxlr->dev)); @@ -714,6 +715,7 @@ static int cxl_memdev_release_file(struct inode *inode, struct file *file) */ static int cxl_mem_get_fw_info(struct cxl_memdev_state *mds) { + struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox; struct cxl_mbox_get_fw_info info; struct cxl_mbox_cmd mbox_cmd; int rc; @@ -724,7 +726,7 @@ static int cxl_mem_get_fw_info(struct cxl_memdev_state *mds) .payload_out = &info, }; - rc = cxl_internal_send_cmd(mds, &mbox_cmd); + rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd); if (rc < 0) return rc; @@ -748,6 +750,7 @@ static int cxl_mem_get_fw_info(struct cxl_memdev_state *mds) */ static int cxl_mem_activate_fw(struct cxl_memdev_state *mds, int slot) { + struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox; struct cxl_mbox_activate_fw activate; struct cxl_mbox_cmd mbox_cmd; @@ -764,7 +767,7 @@ static int cxl_mem_activate_fw(struct cxl_memdev_state *mds, int slot) activate.action = CXL_FW_ACTIVATE_OFFLINE; activate.slot = slot; - return cxl_internal_send_cmd(mds, &mbox_cmd); + return cxl_internal_send_cmd(cxl_mbox, &mbox_cmd); } /** @@ -779,6 +782,7 @@ static int cxl_mem_activate_fw(struct cxl_memdev_state *mds, int slot) */ static int cxl_mem_abort_fw_xfer(struct cxl_memdev_state *mds) { + struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox; struct cxl_mbox_transfer_fw *transfer; struct cxl_mbox_cmd mbox_cmd; int rc; @@ -798,7 +802,7 @@ static int cxl_mem_abort_fw_xfer(struct cxl_memdev_state *mds) transfer->action = CXL_FW_TRANSFER_ACTION_ABORT; - rc = cxl_internal_send_cmd(mds, &mbox_cmd); + rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd); kfree(transfer); return rc; } @@ -829,12 +833,13 @@ static enum fw_upload_err cxl_fw_prepare(struct fw_upload *fwl, const u8 *data, { struct cxl_memdev_state *mds = fwl->dd_handle; struct cxl_mbox_transfer_fw *transfer; + struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox; if (!size) return FW_UPLOAD_ERR_INVALID_SIZE; mds->fw.oneshot = struct_size(transfer, data, size) < - mds->payload_size; + cxl_mbox->payload_size; if (cxl_mem_get_fw_info(mds)) return FW_UPLOAD_ERR_HW_ERROR; @@ -854,6 +859,7 @@ static enum fw_upload_err cxl_fw_write(struct fw_upload *fwl, const u8 *data, { struct cxl_memdev_state *mds = fwl->dd_handle; struct cxl_dev_state *cxlds = &mds->cxlds; + struct cxl_mailbox *cxl_mbox = &cxlds->cxl_mbox; struct cxl_memdev *cxlmd = cxlds->cxlmd; struct cxl_mbox_transfer_fw *transfer; struct cxl_mbox_cmd mbox_cmd; @@ -877,7 +883,7 @@ static enum fw_upload_err cxl_fw_write(struct fw_upload *fwl, const u8 *data, * sizeof(*transfer) is 128. These constraints imply that @cur_size * will always be 128b aligned. */ - cur_size = min_t(size_t, size, mds->payload_size - sizeof(*transfer)); + cur_size = min_t(size_t, size, cxl_mbox->payload_size - sizeof(*transfer)); remaining = size - cur_size; size_in = struct_size(transfer, data, cur_size); @@ -921,7 +927,7 @@ static enum fw_upload_err cxl_fw_write(struct fw_upload *fwl, const u8 *data, .poll_count = 30, }; - rc = cxl_internal_send_cmd(mds, &mbox_cmd); + rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd); if (rc < 0) { rc = FW_UPLOAD_ERR_RW_ERROR; goto out_free; @@ -1059,16 +1065,17 @@ EXPORT_SYMBOL_NS_GPL(devm_cxl_add_memdev, CXL); static void sanitize_teardown_notifier(void *data) { struct cxl_memdev_state *mds = data; + struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox; struct kernfs_node *state; /* * Prevent new irq triggered invocations of the workqueue and * flush inflight invocations. */ - mutex_lock(&mds->mbox_mutex); + mutex_lock(&cxl_mbox->mbox_mutex); state = mds->security.sanitize_node; mds->security.sanitize_node = NULL; - mutex_unlock(&mds->mbox_mutex); + mutex_unlock(&cxl_mbox->mbox_mutex); cancel_delayed_work_sync(&mds->security.poll_dwork); sysfs_put(state); diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c index 51132a575b27..5b46bc46aaa9 100644 --- a/drivers/cxl/core/pci.c +++ b/drivers/cxl/core/pci.c @@ -211,37 +211,6 @@ int cxl_await_media_ready(struct cxl_dev_state *cxlds) } EXPORT_SYMBOL_NS_GPL(cxl_await_media_ready, CXL); -static int wait_for_valid(struct pci_dev *pdev, int d) -{ - u32 val; - int rc; - - /* - * Memory_Info_Valid: When set, indicates that the CXL Range 1 Size high - * and Size Low registers are valid. Must be set within 1 second of - * deassertion of reset to CXL device. Likely it is already set by the - * time this runs, but otherwise give a 1.5 second timeout in case of - * clock skew. - */ - rc = pci_read_config_dword(pdev, d + CXL_DVSEC_RANGE_SIZE_LOW(0), &val); - if (rc) - return rc; - - if (val & CXL_DVSEC_MEM_INFO_VALID) - return 0; - - msleep(1500); - - rc = pci_read_config_dword(pdev, d + CXL_DVSEC_RANGE_SIZE_LOW(0), &val); - if (rc) - return rc; - - if (val & CXL_DVSEC_MEM_INFO_VALID) - return 0; - - return -ETIMEDOUT; -} - static int cxl_set_mem_enable(struct cxl_dev_state *cxlds, u16 val) { struct pci_dev *pdev = to_pci_dev(cxlds->dev); @@ -322,11 +291,13 @@ static int devm_cxl_enable_hdm(struct device *host, struct cxl_hdm *cxlhdm) return devm_add_action_or_reset(host, disable_hdm, cxlhdm); } -int cxl_dvsec_rr_decode(struct device *dev, int d, +int cxl_dvsec_rr_decode(struct device *dev, struct cxl_port *port, struct cxl_endpoint_dvsec_info *info) { struct pci_dev *pdev = to_pci_dev(dev); + struct cxl_dev_state *cxlds = pci_get_drvdata(pdev); int hdm_count, rc, i, ranges = 0; + int d = cxlds->cxl_dvsec; u16 cap, ctrl; if (!d) { @@ -353,12 +324,6 @@ int cxl_dvsec_rr_decode(struct device *dev, int d, if (!hdm_count || hdm_count > 2) return -EINVAL; - rc = wait_for_valid(pdev, d); - if (rc) { - dev_dbg(dev, "Failure awaiting MEM_INFO_VALID (%d)\n", rc); - return rc; - } - /* * The current DVSEC values are moot if the memory capability is * disabled, and they will remain moot after the HDM Decoder @@ -376,6 +341,10 @@ int cxl_dvsec_rr_decode(struct device *dev, int d, u64 base, size; u32 temp; + rc = cxl_dvsec_mem_range_valid(cxlds, i); + if (rc) + return rc; + rc = pci_read_config_dword( pdev, d + CXL_DVSEC_RANGE_SIZE_HIGH(i), &temp); if (rc) @@ -390,10 +359,6 @@ int cxl_dvsec_rr_decode(struct device *dev, int d, size |= temp & CXL_DVSEC_MEM_SIZE_LOW_MASK; if (!size) { - info->dvsec_range[i] = (struct range) { - .start = 0, - .end = CXL_RESOURCE_NONE, - }; continue; } @@ -411,12 +376,10 @@ int cxl_dvsec_rr_decode(struct device *dev, int d, base |= temp & CXL_DVSEC_MEM_BASE_LOW_MASK; - info->dvsec_range[i] = (struct range) { + info->dvsec_range[ranges++] = (struct range) { .start = base, .end = base + size - 1 }; - - ranges++; } info->ranges = ranges; @@ -463,7 +426,15 @@ int cxl_hdm_decode_init(struct cxl_dev_state *cxlds, struct cxl_hdm *cxlhdm, return -ENODEV; } - for (i = 0, allowed = 0; info->mem_enabled && i < info->ranges; i++) { + if (!info->mem_enabled) { + rc = devm_cxl_enable_hdm(&port->dev, cxlhdm); + if (rc) + return rc; + + return devm_cxl_enable_mem(&port->dev, cxlds); + } + + for (i = 0, allowed = 0; i < info->ranges; i++) { struct device *cxld_dev; cxld_dev = device_find_child(&root->dev, &info->dvsec_range[i], @@ -477,7 +448,7 @@ int cxl_hdm_decode_init(struct cxl_dev_state *cxlds, struct cxl_hdm *cxlhdm, allowed++; } - if (!allowed && info->mem_enabled) { + if (!allowed) { dev_err(dev, "Range register decodes outside platform defined CXL ranges.\n"); return -ENXIO; } @@ -491,14 +462,7 @@ int cxl_hdm_decode_init(struct cxl_dev_state *cxlds, struct cxl_hdm *cxlhdm, * match. If at least one DVSEC range is enabled and allowed, skip HDM * Decoder Capability Enable. */ - if (info->mem_enabled) - return 0; - - rc = devm_cxl_enable_hdm(&port->dev, cxlhdm); - if (rc) - return rc; - - return devm_cxl_enable_mem(&port->dev, cxlds); + return 0; } EXPORT_SYMBOL_NS_GPL(cxl_hdm_decode_init, CXL); @@ -772,22 +736,20 @@ static bool cxl_handle_endpoint_ras(struct cxl_dev_state *cxlds) static void cxl_dport_map_rch_aer(struct cxl_dport *dport) { - struct cxl_rcrb_info *ri = &dport->rcrb; - void __iomem *dport_aer = NULL; resource_size_t aer_phys; struct device *host; + u16 aer_cap; - if (dport->rch && ri->aer_cap) { + aer_cap = cxl_rcrb_to_aer(dport->dport_dev, dport->rcrb.base); + if (aer_cap) { host = dport->reg_map.host; - aer_phys = ri->aer_cap + ri->base; - dport_aer = devm_cxl_iomap_block(host, aer_phys, - sizeof(struct aer_capability_regs)); + aer_phys = aer_cap + dport->rcrb.base; + dport->regs.dport_aer = devm_cxl_iomap_block(host, aer_phys, + sizeof(struct aer_capability_regs)); } - - dport->regs.dport_aer = dport_aer; } -static void cxl_dport_map_regs(struct cxl_dport *dport) +static void cxl_dport_map_ras(struct cxl_dport *dport) { struct cxl_register_map *map = &dport->reg_map; struct device *dev = dport->dport_dev; @@ -797,22 +759,16 @@ static void cxl_dport_map_regs(struct cxl_dport *dport) else if (cxl_map_component_regs(map, &dport->regs.component, BIT(CXL_CM_CAP_CAP_ID_RAS))) dev_dbg(dev, "Failed to map RAS capability.\n"); - - if (dport->rch) - cxl_dport_map_rch_aer(dport); } static void cxl_disable_rch_root_ints(struct cxl_dport *dport) { void __iomem *aer_base = dport->regs.dport_aer; - struct pci_host_bridge *bridge; u32 aer_cmd_mask, aer_cmd; if (!aer_base) return; - bridge = to_pci_host_bridge(dport->dport_dev); - /* * Disable RCH root port command interrupts. * CXL 3.0 12.2.1.1 - RCH Downstream Port-detected Errors @@ -821,34 +777,35 @@ static void cxl_disable_rch_root_ints(struct cxl_dport *dport) * the root cmd register's interrupts is required. But, PCI spec * shows these are disabled by default on reset. */ - if (bridge->native_aer) { - aer_cmd_mask = (PCI_ERR_ROOT_CMD_COR_EN | - PCI_ERR_ROOT_CMD_NONFATAL_EN | - PCI_ERR_ROOT_CMD_FATAL_EN); - aer_cmd = readl(aer_base + PCI_ERR_ROOT_COMMAND); - aer_cmd &= ~aer_cmd_mask; - writel(aer_cmd, aer_base + PCI_ERR_ROOT_COMMAND); - } + aer_cmd_mask = (PCI_ERR_ROOT_CMD_COR_EN | + PCI_ERR_ROOT_CMD_NONFATAL_EN | + PCI_ERR_ROOT_CMD_FATAL_EN); + aer_cmd = readl(aer_base + PCI_ERR_ROOT_COMMAND); + aer_cmd &= ~aer_cmd_mask; + writel(aer_cmd, aer_base + PCI_ERR_ROOT_COMMAND); } -void cxl_setup_parent_dport(struct device *host, struct cxl_dport *dport) +/** + * cxl_dport_init_ras_reporting - Setup CXL RAS report on this dport + * @dport: the cxl_dport that needs to be initialized + * @host: host device for devm operations + */ +void cxl_dport_init_ras_reporting(struct cxl_dport *dport, struct device *host) { - struct device *dport_dev = dport->dport_dev; + dport->reg_map.host = host; + cxl_dport_map_ras(dport); if (dport->rch) { - struct pci_host_bridge *host_bridge = to_pci_host_bridge(dport_dev); - - if (host_bridge->native_aer) - dport->rcrb.aer_cap = cxl_rcrb_to_aer(dport_dev, dport->rcrb.base); - } + struct pci_host_bridge *host_bridge = to_pci_host_bridge(dport->dport_dev); - dport->reg_map.host = host; - cxl_dport_map_regs(dport); + if (!host_bridge->native_aer) + return; - if (dport->rch) + cxl_dport_map_rch_aer(dport); cxl_disable_rch_root_ints(dport); + } } -EXPORT_SYMBOL_NS_GPL(cxl_setup_parent_dport, CXL); +EXPORT_SYMBOL_NS_GPL(cxl_dport_init_ras_reporting, CXL); static void cxl_handle_rdport_cor_ras(struct cxl_dev_state *cxlds, struct cxl_dport *dport) @@ -915,15 +872,13 @@ static void cxl_handle_rdport_errors(struct cxl_dev_state *cxlds) struct pci_dev *pdev = to_pci_dev(cxlds->dev); struct aer_capability_regs aer_regs; struct cxl_dport *dport; - struct cxl_port *port; int severity; - port = cxl_pci_find_port(pdev, &dport); + struct cxl_port *port __free(put_cxl_port) = + cxl_pci_find_port(pdev, &dport); if (!port) return; - put_device(&port->dev); - if (!cxl_rch_get_aer_info(dport->regs.dport_aer, &aer_regs)) return; @@ -1076,3 +1031,26 @@ bool cxl_endpoint_decoder_reset_detected(struct cxl_port *port) __cxl_endpoint_decoder_reset_detected); } EXPORT_SYMBOL_NS_GPL(cxl_endpoint_decoder_reset_detected, CXL); + +int cxl_pci_get_bandwidth(struct pci_dev *pdev, struct access_coordinate *c) +{ + int speed, bw; + u16 lnksta; + u32 width; + + speed = pcie_link_speed_mbps(pdev); + if (speed < 0) + return speed; + speed /= BITS_PER_BYTE; + + pcie_capability_read_word(pdev, PCI_EXP_LNKSTA, &lnksta); + width = FIELD_GET(PCI_EXP_LNKSTA_NLW, lnksta); + bw = speed * width; + + for (int i = 0; i < ACCESS_COORDINATE_MAX; i++) { + c[i].read_bandwidth = bw; + c[i].write_bandwidth = bw; + } + + return 0; +} diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c index 1d5007e3795a..e666ec6a9085 100644 --- a/drivers/cxl/core/port.c +++ b/drivers/cxl/core/port.c @@ -3,7 +3,6 @@ #include <linux/platform_device.h> #include <linux/memregion.h> #include <linux/workqueue.h> -#include <linux/einj-cxl.h> #include <linux/debugfs.h> #include <linux/device.h> #include <linux/module.h> @@ -11,6 +10,7 @@ #include <linux/slab.h> #include <linux/idr.h> #include <linux/node.h> +#include <cxl/einj.h> #include <cxlmem.h> #include <cxlpci.h> #include <cxl.h> @@ -828,27 +828,20 @@ static void cxl_debugfs_create_dport_dir(struct cxl_dport *dport) &cxl_einj_inject_fops); } -static struct cxl_port *__devm_cxl_add_port(struct device *host, - struct device *uport_dev, - resource_size_t component_reg_phys, - struct cxl_dport *parent_dport) +static int cxl_port_add(struct cxl_port *port, + resource_size_t component_reg_phys, + struct cxl_dport *parent_dport) { - struct cxl_port *port; - struct device *dev; + struct device *dev __free(put_device) = &port->dev; int rc; - port = cxl_port_alloc(uport_dev, parent_dport); - if (IS_ERR(port)) - return port; - - dev = &port->dev; - if (is_cxl_memdev(uport_dev)) { - struct cxl_memdev *cxlmd = to_cxl_memdev(uport_dev); + if (is_cxl_memdev(port->uport_dev)) { + struct cxl_memdev *cxlmd = to_cxl_memdev(port->uport_dev); struct cxl_dev_state *cxlds = cxlmd->cxlds; rc = dev_set_name(dev, "endpoint%d", port->id); if (rc) - goto err; + return rc; /* * The endpoint driver already enumerated the component and RAS @@ -861,19 +854,41 @@ static struct cxl_port *__devm_cxl_add_port(struct device *host, } else if (parent_dport) { rc = dev_set_name(dev, "port%d", port->id); if (rc) - goto err; + return rc; rc = cxl_port_setup_regs(port, component_reg_phys); if (rc) - goto err; - } else + return rc; + } else { rc = dev_set_name(dev, "root%d", port->id); - if (rc) - goto err; + if (rc) + return rc; + } rc = device_add(dev); if (rc) - goto err; + return rc; + + /* Inhibit the cleanup function invoked */ + dev = NULL; + return 0; +} + +static struct cxl_port *__devm_cxl_add_port(struct device *host, + struct device *uport_dev, + resource_size_t component_reg_phys, + struct cxl_dport *parent_dport) +{ + struct cxl_port *port; + int rc; + + port = cxl_port_alloc(uport_dev, parent_dport); + if (IS_ERR(port)) + return port; + + rc = cxl_port_add(port, component_reg_phys, parent_dport); + if (rc) + return ERR_PTR(rc); rc = devm_add_action_or_reset(host, unregister_port, port); if (rc) @@ -891,10 +906,6 @@ static struct cxl_port *__devm_cxl_add_port(struct device *host, port->pci_latency = cxl_pci_get_latency(to_pci_dev(uport_dev)); return port; - -err: - put_device(dev); - return ERR_PTR(rc); } /** @@ -941,7 +952,7 @@ struct cxl_root *devm_cxl_add_root(struct device *host, port = devm_cxl_add_port(host, host, CXL_RESOURCE_NONE, NULL); if (IS_ERR(port)) - return (struct cxl_root *)port; + return ERR_CAST(port); cxl_root = to_cxl_root(port); cxl_root->ops = ops; @@ -1258,18 +1269,13 @@ EXPORT_SYMBOL_NS_GPL(devm_cxl_add_rch_dport, CXL); static int add_ep(struct cxl_ep *new) { struct cxl_port *port = new->dport->port; - int rc; - device_lock(&port->dev); - if (port->dead) { - device_unlock(&port->dev); + guard(device)(&port->dev); + if (port->dead) return -ENXIO; - } - rc = xa_insert(&port->endpoints, (unsigned long)new->ep, new, - GFP_KERNEL); - device_unlock(&port->dev); - return rc; + return xa_insert(&port->endpoints, (unsigned long)new->ep, + new, GFP_KERNEL); } /** @@ -1393,14 +1399,14 @@ static void delete_endpoint(void *data) struct cxl_port *endpoint = cxlmd->endpoint; struct device *host = endpoint_host(endpoint); - device_lock(host); - if (host->driver && !endpoint->dead) { - devm_release_action(host, cxl_unlink_parent_dport, endpoint); - devm_release_action(host, cxl_unlink_uport, endpoint); - devm_release_action(host, unregister_port, endpoint); + scoped_guard(device, host) { + if (host->driver && !endpoint->dead) { + devm_release_action(host, cxl_unlink_parent_dport, endpoint); + devm_release_action(host, cxl_unlink_uport, endpoint); + devm_release_action(host, unregister_port, endpoint); + } + cxlmd->endpoint = NULL; } - cxlmd->endpoint = NULL; - device_unlock(host); put_device(&endpoint->dev); put_device(host); } @@ -1477,12 +1483,11 @@ static void cxl_detach_ep(void *data) .cxlmd = cxlmd, .depth = i, }; - struct device *dev; struct cxl_ep *ep; bool died = false; - dev = bus_find_device(&cxl_bus_type, NULL, &ctx, - port_has_memdev); + struct device *dev __free(put_device) = + bus_find_device(&cxl_bus_type, NULL, &ctx, port_has_memdev); if (!dev) continue; port = to_cxl_port(dev); @@ -1512,7 +1517,6 @@ static void cxl_detach_ep(void *data) dev_name(&port->dev)); delete_switch_port(port); } - put_device(&port->dev); device_unlock(&parent_port->dev); } } @@ -1540,7 +1544,6 @@ static int add_port_attach_ep(struct cxl_memdev *cxlmd, struct device *dport_dev) { struct device *dparent = grandparent(dport_dev); - struct cxl_port *port, *parent_port = NULL; struct cxl_dport *dport, *parent_dport; resource_size_t component_reg_phys; int rc; @@ -1556,50 +1559,52 @@ static int add_port_attach_ep(struct cxl_memdev *cxlmd, return -ENXIO; } - parent_port = find_cxl_port(dparent, &parent_dport); + struct cxl_port *parent_port __free(put_cxl_port) = + find_cxl_port(dparent, &parent_dport); if (!parent_port) { /* iterate to create this parent_port */ return -EAGAIN; } - device_lock(&parent_port->dev); - if (!parent_port->dev.driver) { - dev_warn(&cxlmd->dev, - "port %s:%s disabled, failed to enumerate CXL.mem\n", - dev_name(&parent_port->dev), dev_name(uport_dev)); - port = ERR_PTR(-ENXIO); - goto out; - } + /* + * Definition with __free() here to keep the sequence of + * dereferencing the device of the port before the parent_port releasing. + */ + struct cxl_port *port __free(put_cxl_port) = NULL; + scoped_guard(device, &parent_port->dev) { + if (!parent_port->dev.driver) { + dev_warn(&cxlmd->dev, + "port %s:%s disabled, failed to enumerate CXL.mem\n", + dev_name(&parent_port->dev), dev_name(uport_dev)); + return -ENXIO; + } - port = find_cxl_port_at(parent_port, dport_dev, &dport); - if (!port) { - component_reg_phys = find_component_registers(uport_dev); - port = devm_cxl_add_port(&parent_port->dev, uport_dev, - component_reg_phys, parent_dport); - /* retry find to pick up the new dport information */ - if (!IS_ERR(port)) + port = find_cxl_port_at(parent_port, dport_dev, &dport); + if (!port) { + component_reg_phys = find_component_registers(uport_dev); + port = devm_cxl_add_port(&parent_port->dev, uport_dev, + component_reg_phys, parent_dport); + if (IS_ERR(port)) + return PTR_ERR(port); + + /* retry find to pick up the new dport information */ port = find_cxl_port_at(parent_port, dport_dev, &dport); + if (!port) + return -ENXIO; + } } -out: - device_unlock(&parent_port->dev); - if (IS_ERR(port)) - rc = PTR_ERR(port); - else { - dev_dbg(&cxlmd->dev, "add to new port %s:%s\n", - dev_name(&port->dev), dev_name(port->uport_dev)); - rc = cxl_add_ep(dport, &cxlmd->dev); - if (rc == -EBUSY) { - /* - * "can't" happen, but this error code means - * something to the caller, so translate it. - */ - rc = -ENXIO; - } - put_device(&port->dev); + dev_dbg(&cxlmd->dev, "add to new port %s:%s\n", + dev_name(&port->dev), dev_name(port->uport_dev)); + rc = cxl_add_ep(dport, &cxlmd->dev); + if (rc == -EBUSY) { + /* + * "can't" happen, but this error code means + * something to the caller, so translate it. + */ + rc = -ENXIO; } - put_device(&parent_port->dev); return rc; } @@ -1630,7 +1635,6 @@ retry: struct device *dport_dev = grandparent(iter); struct device *uport_dev; struct cxl_dport *dport; - struct cxl_port *port; /* * The terminal "grandparent" in PCI is NULL and @platform_bus @@ -1649,7 +1653,8 @@ retry: dev_dbg(dev, "scan: iter: %s dport_dev: %s parent: %s\n", dev_name(iter), dev_name(dport_dev), dev_name(uport_dev)); - port = find_cxl_port(dport_dev, &dport); + struct cxl_port *port __free(put_cxl_port) = + find_cxl_port(dport_dev, &dport); if (port) { dev_dbg(&cxlmd->dev, "found already registered port %s:%s\n", @@ -1664,18 +1669,13 @@ retry: * the parent_port lock as the current port may be being * reaped. */ - if (rc && rc != -EBUSY) { - put_device(&port->dev); + if (rc && rc != -EBUSY) return rc; - } /* Any more ports to add between this one and the root? */ - if (!dev_is_cxl_root_child(&port->dev)) { - put_device(&port->dev); + if (!dev_is_cxl_root_child(&port->dev)) continue; - } - put_device(&port->dev); return 0; } @@ -1983,7 +1983,6 @@ EXPORT_SYMBOL_NS_GPL(cxl_decoder_add_locked, CXL); int cxl_decoder_add(struct cxl_decoder *cxld, int *target_map) { struct cxl_port *port; - int rc; if (WARN_ON_ONCE(!cxld)) return -EINVAL; @@ -1993,11 +1992,8 @@ int cxl_decoder_add(struct cxl_decoder *cxld, int *target_map) port = to_cxl_port(cxld->dev.parent); - device_lock(&port->dev); - rc = cxl_decoder_add_locked(cxld, target_map); - device_unlock(&port->dev); - - return rc; + guard(device)(&port->dev); + return cxl_decoder_add_locked(cxld, target_map); } EXPORT_SYMBOL_NS_GPL(cxl_decoder_add, CXL); @@ -2241,6 +2237,26 @@ int cxl_endpoint_get_perf_coordinates(struct cxl_port *port, } EXPORT_SYMBOL_NS_GPL(cxl_endpoint_get_perf_coordinates, CXL); +int cxl_port_get_switch_dport_bandwidth(struct cxl_port *port, + struct access_coordinate *c) +{ + struct cxl_dport *dport = port->parent_dport; + + /* Check this port is connected to a switch DSP and not an RP */ + if (parent_port_is_cxl_root(to_cxl_port(port->dev.parent))) + return -ENODEV; + + if (!coordinates_valid(dport->coord)) + return -EINVAL; + + for (int i = 0; i < ACCESS_COORDINATE_MAX; i++) { + c[i].read_bandwidth = dport->coord[i].read_bandwidth; + c[i].write_bandwidth = dport->coord[i].write_bandwidth; + } + + return 0; +} + /* for user tooling to ensure port disable work has completed */ static ssize_t flush_store(const struct bus_type *bus, const char *buf, size_t count) { diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c index 21ad5f242875..e701e4b04032 100644 --- a/drivers/cxl/core/region.c +++ b/drivers/cxl/core/region.c @@ -1983,6 +1983,7 @@ static int cxl_region_attach(struct cxl_region *cxlr, * then the region is already committed. */ p->state = CXL_CONFIG_COMMIT; + cxl_region_shared_upstream_bandwidth_update(cxlr); return 0; } @@ -2004,6 +2005,7 @@ static int cxl_region_attach(struct cxl_region *cxlr, if (rc) return rc; p->state = CXL_CONFIG_ACTIVE; + cxl_region_shared_upstream_bandwidth_update(cxlr); } cxled->cxld.interleave_ways = p->interleave_ways; @@ -2313,8 +2315,6 @@ static void unregister_region(void *_cxlr) struct cxl_region_params *p = &cxlr->params; int i; - unregister_memory_notifier(&cxlr->memory_notifier); - unregister_mt_adistance_algorithm(&cxlr->adist_notifier); device_del(&cxlr->dev); /* @@ -2391,18 +2391,6 @@ static bool cxl_region_update_coordinates(struct cxl_region *cxlr, int nid) return true; } -static int cxl_region_nid(struct cxl_region *cxlr) -{ - struct cxl_region_params *p = &cxlr->params; - struct resource *res; - - guard(rwsem_read)(&cxl_region_rwsem); - res = p->res; - if (!res) - return NUMA_NO_NODE; - return phys_to_target_node(res->start); -} - static int cxl_region_perf_attrs_callback(struct notifier_block *nb, unsigned long action, void *arg) { @@ -2415,7 +2403,11 @@ static int cxl_region_perf_attrs_callback(struct notifier_block *nb, if (nid == NUMA_NO_NODE || action != MEM_ONLINE) return NOTIFY_DONE; - region_nid = cxl_region_nid(cxlr); + /* + * No need to hold cxl_region_rwsem; region parameters are stable + * within the cxl_region driver. + */ + region_nid = phys_to_target_node(cxlr->params.res->start); if (nid != region_nid) return NOTIFY_DONE; @@ -2434,7 +2426,11 @@ static int cxl_region_calculate_adistance(struct notifier_block *nb, int *adist = data; int region_nid; - region_nid = cxl_region_nid(cxlr); + /* + * No need to hold cxl_region_rwsem; region parameters are stable + * within the cxl_region driver. + */ + region_nid = phys_to_target_node(cxlr->params.res->start); if (nid != region_nid) return NOTIFY_OK; @@ -2484,14 +2480,6 @@ static struct cxl_region *devm_cxl_add_region(struct cxl_root_decoder *cxlrd, if (rc) goto err; - cxlr->memory_notifier.notifier_call = cxl_region_perf_attrs_callback; - cxlr->memory_notifier.priority = CXL_CALLBACK_PRI; - register_memory_notifier(&cxlr->memory_notifier); - - cxlr->adist_notifier.notifier_call = cxl_region_calculate_adistance; - cxlr->adist_notifier.priority = 100; - register_mt_adistance_algorithm(&cxlr->adist_notifier); - rc = devm_add_action_or_reset(port->uport_dev, unregister_region, cxlr); if (rc) return ERR_PTR(rc); @@ -3094,11 +3082,11 @@ static void cxlr_release_nvdimm(void *_cxlr) struct cxl_region *cxlr = _cxlr; struct cxl_nvdimm_bridge *cxl_nvb = cxlr->cxl_nvb; - device_lock(&cxl_nvb->dev); - if (cxlr->cxlr_pmem) - devm_release_action(&cxl_nvb->dev, cxlr_pmem_unregister, - cxlr->cxlr_pmem); - device_unlock(&cxl_nvb->dev); + scoped_guard(device, &cxl_nvb->dev) { + if (cxlr->cxlr_pmem) + devm_release_action(&cxl_nvb->dev, cxlr_pmem_unregister, + cxlr->cxlr_pmem); + } cxlr->cxl_nvb = NULL; put_device(&cxl_nvb->dev); } @@ -3134,13 +3122,14 @@ static int devm_cxl_add_pmem_region(struct cxl_region *cxlr) dev_dbg(&cxlr->dev, "%s: register %s\n", dev_name(dev->parent), dev_name(dev)); - device_lock(&cxl_nvb->dev); - if (cxl_nvb->dev.driver) - rc = devm_add_action_or_reset(&cxl_nvb->dev, - cxlr_pmem_unregister, cxlr_pmem); - else - rc = -ENXIO; - device_unlock(&cxl_nvb->dev); + scoped_guard(device, &cxl_nvb->dev) { + if (cxl_nvb->dev.driver) + rc = devm_add_action_or_reset(&cxl_nvb->dev, + cxlr_pmem_unregister, + cxlr_pmem); + else + rc = -ENXIO; + } if (rc) goto err_bridge; @@ -3386,6 +3375,14 @@ static int is_system_ram(struct resource *res, void *arg) return 1; } +static void shutdown_notifiers(void *_cxlr) +{ + struct cxl_region *cxlr = _cxlr; + + unregister_memory_notifier(&cxlr->memory_notifier); + unregister_mt_adistance_algorithm(&cxlr->adist_notifier); +} + static int cxl_region_probe(struct device *dev) { struct cxl_region *cxlr = to_cxl_region(dev); @@ -3421,6 +3418,18 @@ out: if (rc) return rc; + cxlr->memory_notifier.notifier_call = cxl_region_perf_attrs_callback; + cxlr->memory_notifier.priority = CXL_CALLBACK_PRI; + register_memory_notifier(&cxlr->memory_notifier); + + cxlr->adist_notifier.notifier_call = cxl_region_calculate_adistance; + cxlr->adist_notifier.priority = 100; + register_mt_adistance_algorithm(&cxlr->adist_notifier); + + rc = devm_add_action_or_reset(&cxlr->dev, shutdown_notifiers, cxlr); + if (rc) + return rc; + switch (cxlr->mode) { case CXL_DECODER_PMEM: return devm_cxl_add_pmem_region(cxlr); diff --git a/drivers/cxl/core/trace.h b/drivers/cxl/core/trace.h index 9167cfba7f59..8672b42ee4d1 100644 --- a/drivers/cxl/core/trace.h +++ b/drivers/cxl/core/trace.h @@ -8,7 +8,7 @@ #include <linux/tracepoint.h> #include <linux/pci.h> -#include <asm-generic/unaligned.h> +#include <linux/unaligned.h> #include <cxl.h> #include <cxlmem.h> diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h index 9afb407d438f..0d8b810a51f0 100644 --- a/drivers/cxl/cxl.h +++ b/drivers/cxl/cxl.h @@ -744,6 +744,7 @@ struct cxl_root *find_cxl_root(struct cxl_port *port); void put_cxl_root(struct cxl_root *cxl_root); DEFINE_FREE(put_cxl_root, struct cxl_root *, if (_T) put_cxl_root(_T)) +DEFINE_FREE(put_cxl_port, struct cxl_port *, if (!IS_ERR_OR_NULL(_T)) put_device(&_T->dev)) int devm_cxl_enumerate_ports(struct cxl_memdev *cxlmd); void cxl_bus_rescan(void); void cxl_bus_drain(void); @@ -762,9 +763,10 @@ struct cxl_dport *devm_cxl_add_rch_dport(struct cxl_port *port, #ifdef CONFIG_PCIEAER_CXL void cxl_setup_parent_dport(struct device *host, struct cxl_dport *dport); +void cxl_dport_init_ras_reporting(struct cxl_dport *dport, struct device *host); #else -static inline void cxl_setup_parent_dport(struct device *host, - struct cxl_dport *dport) { } +static inline void cxl_dport_init_ras_reporting(struct cxl_dport *dport, + struct device *host) { } #endif struct cxl_decoder *to_cxl_decoder(struct device *dev); @@ -809,7 +811,7 @@ struct cxl_hdm *devm_cxl_setup_hdm(struct cxl_port *port, int devm_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm, struct cxl_endpoint_dvsec_info *info); int devm_cxl_add_passthrough_decoder(struct cxl_port *port); -int cxl_dvsec_rr_decode(struct device *dev, int dvsec, +int cxl_dvsec_rr_decode(struct device *dev, struct cxl_port *port, struct cxl_endpoint_dvsec_info *info); bool is_cxl_region(struct device *dev); @@ -889,6 +891,7 @@ int cxl_endpoint_get_perf_coordinates(struct cxl_port *port, struct access_coordinate *coord); void cxl_region_perf_data_calculate(struct cxl_region *cxlr, struct cxl_endpoint_decoder *cxled); +void cxl_region_shared_upstream_bandwidth_update(struct cxl_region *cxlr); void cxl_memdev_update_perf(struct cxl_memdev *cxlmd); diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h index afb53d058d62..2a25d1957ddb 100644 --- a/drivers/cxl/cxlmem.h +++ b/drivers/cxl/cxlmem.h @@ -3,11 +3,12 @@ #ifndef __CXL_MEM_H__ #define __CXL_MEM_H__ #include <uapi/linux/cxl_mem.h> +#include <linux/pci.h> #include <linux/cdev.h> #include <linux/uuid.h> -#include <linux/rcuwait.h> -#include <linux/cxl-event.h> #include <linux/node.h> +#include <cxl/event.h> +#include <cxl/mailbox.h> #include "cxl.h" /* CXL 2.0 8.2.8.5.1.1 Memory Device Status Register */ @@ -397,11 +398,13 @@ enum cxl_devtype { * struct cxl_dpa_perf - DPA performance property entry * @dpa_range: range for DPA address * @coord: QoS performance data (i.e. latency, bandwidth) + * @cdat_coord: raw QoS performance data from CDAT * @qos_class: QoS Class cookies */ struct cxl_dpa_perf { struct range dpa_range; struct access_coordinate coord[ACCESS_COORDINATE_MAX]; + struct access_coordinate cdat_coord[ACCESS_COORDINATE_MAX]; int qos_class; }; @@ -424,6 +427,7 @@ struct cxl_dpa_perf { * @ram_res: Active Volatile memory capacity configuration * @serial: PCIe Device Serial Number * @type: Generic Memory Class device or Vendor Specific Memory device + * @cxl_mbox: CXL mailbox context */ struct cxl_dev_state { struct device *dev; @@ -438,8 +442,14 @@ struct cxl_dev_state { struct resource ram_res; u64 serial; enum cxl_devtype type; + struct cxl_mailbox cxl_mbox; }; +static inline struct cxl_dev_state *mbox_to_cxlds(struct cxl_mailbox *cxl_mbox) +{ + return dev_get_drvdata(cxl_mbox->host); +} + /** * struct cxl_memdev_state - Generic Type-3 Memory Device Class driver data * @@ -448,11 +458,8 @@ struct cxl_dev_state { * the functionality related to that like Identify Memory Device and Get * Partition Info * @cxlds: Core driver state common across Type-2 and Type-3 devices - * @payload_size: Size of space for payload - * (CXL 2.0 8.2.8.4.3 Mailbox Capabilities Register) * @lsa_size: Size of Label Storage Area * (CXL 2.0 8.2.9.5.1.1 Identify Memory Device) - * @mbox_mutex: Mutex to synchronize mailbox access. * @firmware_version: Firmware version for the memory device. * @enabled_cmds: Hardware commands found enabled in CEL. * @exclusive_cmds: Commands that are kernel-internal only @@ -470,17 +477,13 @@ struct cxl_dev_state { * @poison: poison driver state info * @security: security driver state info * @fw: firmware upload / activation state - * @mbox_wait: RCU wait for mbox send completely - * @mbox_send: @dev specific transport for transmitting mailbox commands * * See CXL 3.0 8.2.9.8.2 Capacity Configuration and Label Storage for * details on capacity parameters. */ struct cxl_memdev_state { struct cxl_dev_state cxlds; - size_t payload_size; size_t lsa_size; - struct mutex mbox_mutex; /* Protects device mailbox and firmware */ char firmware_version[0x10]; DECLARE_BITMAP(enabled_cmds, CXL_MEM_COMMAND_ID_MAX); DECLARE_BITMAP(exclusive_cmds, CXL_MEM_COMMAND_ID_MAX); @@ -500,10 +503,6 @@ struct cxl_memdev_state { struct cxl_poison_state poison; struct cxl_security_state security; struct cxl_fw_state fw; - - struct rcuwait mbox_wait; - int (*mbox_send)(struct cxl_memdev_state *mds, - struct cxl_mbox_cmd *cmd); }; static inline struct cxl_memdev_state * @@ -814,7 +813,7 @@ enum { CXL_PMEM_SEC_PASS_USER, }; -int cxl_internal_send_cmd(struct cxl_memdev_state *mds, +int cxl_internal_send_cmd(struct cxl_mailbox *cxl_mbox, struct cxl_mbox_cmd *cmd); int cxl_dev_state_identify(struct cxl_memdev_state *mds); int cxl_await_media_ready(struct cxl_dev_state *cxlds); diff --git a/drivers/cxl/mem.c b/drivers/cxl/mem.c index 7de232eaeb17..a9fd5cd5a0d2 100644 --- a/drivers/cxl/mem.c +++ b/drivers/cxl/mem.c @@ -109,7 +109,6 @@ static int cxl_mem_probe(struct device *dev) struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds); struct cxl_dev_state *cxlds = cxlmd->cxlds; struct device *endpoint_parent; - struct cxl_port *parent_port; struct cxl_dport *dport; struct dentry *dentry; int rc; @@ -146,7 +145,8 @@ static int cxl_mem_probe(struct device *dev) if (rc) return rc; - parent_port = cxl_mem_find_port(cxlmd, &dport); + struct cxl_port *parent_port __free(put_cxl_port) = + cxl_mem_find_port(cxlmd, &dport); if (!parent_port) { dev_err(dev, "CXL port topology not found\n"); return -ENXIO; @@ -166,22 +166,19 @@ static int cxl_mem_probe(struct device *dev) else endpoint_parent = &parent_port->dev; - cxl_setup_parent_dport(dev, dport); + cxl_dport_init_ras_reporting(dport, dev); - device_lock(endpoint_parent); - if (!endpoint_parent->driver) { - dev_err(dev, "CXL port topology %s not enabled\n", - dev_name(endpoint_parent)); - rc = -ENXIO; - goto unlock; - } + scoped_guard(device, endpoint_parent) { + if (!endpoint_parent->driver) { + dev_err(dev, "CXL port topology %s not enabled\n", + dev_name(endpoint_parent)); + return -ENXIO; + } - rc = devm_cxl_add_endpoint(endpoint_parent, cxlmd, dport); -unlock: - device_unlock(endpoint_parent); - put_device(&parent_port->dev); - if (rc) - return rc; + rc = devm_cxl_add_endpoint(endpoint_parent, cxlmd, dport); + if (rc) + return rc; + } /* * The kernel may be operating out of CXL memory on this device, diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c index 4be35dc22202..188412d45e0d 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 <asm-generic/unaligned.h> +#include <linux/unaligned.h> #include <linux/io-64-nonatomic-lo-hi.h> #include <linux/moduleparam.h> #include <linux/module.h> @@ -11,6 +11,7 @@ #include <linux/pci.h> #include <linux/aer.h> #include <linux/io.h> +#include <cxl/mailbox.h> #include "cxlmem.h" #include "cxlpci.h" #include "cxl.h" @@ -124,6 +125,7 @@ static irqreturn_t cxl_pci_mbox_irq(int irq, void *id) u16 opcode; struct cxl_dev_id *dev_id = id; struct cxl_dev_state *cxlds = dev_id->cxlds; + struct cxl_mailbox *cxl_mbox = &cxlds->cxl_mbox; struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlds); if (!cxl_mbox_background_complete(cxlds)) @@ -132,13 +134,13 @@ static irqreturn_t cxl_pci_mbox_irq(int irq, void *id) reg = readq(cxlds->regs.mbox + CXLDEV_MBOX_BG_CMD_STATUS_OFFSET); opcode = FIELD_GET(CXLDEV_MBOX_BG_CMD_COMMAND_OPCODE_MASK, reg); if (opcode == CXL_MBOX_OP_SANITIZE) { - mutex_lock(&mds->mbox_mutex); + mutex_lock(&cxl_mbox->mbox_mutex); if (mds->security.sanitize_node) mod_delayed_work(system_wq, &mds->security.poll_dwork, 0); - mutex_unlock(&mds->mbox_mutex); + mutex_unlock(&cxl_mbox->mbox_mutex); } else { /* short-circuit the wait in __cxl_pci_mbox_send_cmd() */ - rcuwait_wake_up(&mds->mbox_wait); + rcuwait_wake_up(&cxl_mbox->mbox_wait); } return IRQ_HANDLED; @@ -152,8 +154,9 @@ static void cxl_mbox_sanitize_work(struct work_struct *work) struct cxl_memdev_state *mds = container_of(work, typeof(*mds), security.poll_dwork.work); struct cxl_dev_state *cxlds = &mds->cxlds; + struct cxl_mailbox *cxl_mbox = &cxlds->cxl_mbox; - mutex_lock(&mds->mbox_mutex); + mutex_lock(&cxl_mbox->mbox_mutex); if (cxl_mbox_background_complete(cxlds)) { mds->security.poll_tmo_secs = 0; if (mds->security.sanitize_node) @@ -167,12 +170,12 @@ static void cxl_mbox_sanitize_work(struct work_struct *work) mds->security.poll_tmo_secs = min(15 * 60, timeout); schedule_delayed_work(&mds->security.poll_dwork, timeout * HZ); } - mutex_unlock(&mds->mbox_mutex); + mutex_unlock(&cxl_mbox->mbox_mutex); } /** * __cxl_pci_mbox_send_cmd() - Execute a mailbox command - * @mds: The memory device driver data + * @cxl_mbox: CXL mailbox context * @mbox_cmd: Command to send to the memory device. * * Context: Any context. Expects mbox_mutex to be held. @@ -192,17 +195,18 @@ static void cxl_mbox_sanitize_work(struct work_struct *work) * not need to coordinate with each other. The driver only uses the primary * mailbox. */ -static int __cxl_pci_mbox_send_cmd(struct cxl_memdev_state *mds, +static int __cxl_pci_mbox_send_cmd(struct cxl_mailbox *cxl_mbox, struct cxl_mbox_cmd *mbox_cmd) { - struct cxl_dev_state *cxlds = &mds->cxlds; + struct cxl_dev_state *cxlds = mbox_to_cxlds(cxl_mbox); + struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlds); void __iomem *payload = cxlds->regs.mbox + CXLDEV_MBOX_PAYLOAD_OFFSET; struct device *dev = cxlds->dev; u64 cmd_reg, status_reg; size_t out_len; int rc; - lockdep_assert_held(&mds->mbox_mutex); + lockdep_assert_held(&cxl_mbox->mbox_mutex); /* * Here are the steps from 8.2.8.4 of the CXL 2.0 spec. @@ -315,10 +319,10 @@ static int __cxl_pci_mbox_send_cmd(struct cxl_memdev_state *mds, timeout = mbox_cmd->poll_interval_ms; for (i = 0; i < mbox_cmd->poll_count; i++) { - if (rcuwait_wait_event_timeout(&mds->mbox_wait, - cxl_mbox_background_complete(cxlds), - TASK_UNINTERRUPTIBLE, - msecs_to_jiffies(timeout)) > 0) + if (rcuwait_wait_event_timeout(&cxl_mbox->mbox_wait, + cxl_mbox_background_complete(cxlds), + TASK_UNINTERRUPTIBLE, + msecs_to_jiffies(timeout)) > 0) break; } @@ -360,7 +364,7 @@ success: */ size_t n; - n = min3(mbox_cmd->size_out, mds->payload_size, out_len); + n = min3(mbox_cmd->size_out, cxl_mbox->payload_size, out_len); memcpy_fromio(mbox_cmd->payload_out, payload, n); mbox_cmd->size_out = n; } else { @@ -370,14 +374,14 @@ success: return 0; } -static int cxl_pci_mbox_send(struct cxl_memdev_state *mds, +static int cxl_pci_mbox_send(struct cxl_mailbox *cxl_mbox, struct cxl_mbox_cmd *cmd) { int rc; - mutex_lock_io(&mds->mbox_mutex); - rc = __cxl_pci_mbox_send_cmd(mds, cmd); - mutex_unlock(&mds->mbox_mutex); + mutex_lock_io(&cxl_mbox->mbox_mutex); + rc = __cxl_pci_mbox_send_cmd(cxl_mbox, cmd); + mutex_unlock(&cxl_mbox->mbox_mutex); return rc; } @@ -385,6 +389,7 @@ static int cxl_pci_mbox_send(struct cxl_memdev_state *mds, static int cxl_pci_setup_mailbox(struct cxl_memdev_state *mds, bool irq_avail) { struct cxl_dev_state *cxlds = &mds->cxlds; + struct cxl_mailbox *cxl_mbox = &cxlds->cxl_mbox; const int cap = readl(cxlds->regs.mbox + CXLDEV_MBOX_CAPS_OFFSET); struct device *dev = cxlds->dev; unsigned long timeout; @@ -417,8 +422,8 @@ static int cxl_pci_setup_mailbox(struct cxl_memdev_state *mds, bool irq_avail) return -ETIMEDOUT; } - mds->mbox_send = cxl_pci_mbox_send; - mds->payload_size = + cxl_mbox->mbox_send = cxl_pci_mbox_send; + cxl_mbox->payload_size = 1 << FIELD_GET(CXLDEV_MBOX_CAP_PAYLOAD_SIZE_MASK, cap); /* @@ -428,16 +433,15 @@ static int cxl_pci_setup_mailbox(struct cxl_memdev_state *mds, bool irq_avail) * there's no point in going forward. If the size is too large, there's * no harm is soft limiting it. */ - mds->payload_size = min_t(size_t, mds->payload_size, SZ_1M); - if (mds->payload_size < 256) { + cxl_mbox->payload_size = min_t(size_t, cxl_mbox->payload_size, SZ_1M); + if (cxl_mbox->payload_size < 256) { dev_err(dev, "Mailbox is too small (%zub)", - mds->payload_size); + cxl_mbox->payload_size); return -ENXIO; } - dev_dbg(dev, "Mailbox payload sized %zu", mds->payload_size); + dev_dbg(dev, "Mailbox payload sized %zu", cxl_mbox->payload_size); - rcuwait_init(&mds->mbox_wait); INIT_DELAYED_WORK(&mds->security.poll_dwork, cxl_mbox_sanitize_work); /* background command interrupts are optional */ @@ -473,7 +477,6 @@ static bool is_cxl_restricted(struct pci_dev *pdev) static int cxl_rcrb_get_comp_regs(struct pci_dev *pdev, struct cxl_register_map *map) { - struct cxl_port *port; struct cxl_dport *dport; resource_size_t component_reg_phys; @@ -482,14 +485,12 @@ static int cxl_rcrb_get_comp_regs(struct pci_dev *pdev, .resource = CXL_RESOURCE_NONE, }; - port = cxl_pci_find_port(pdev, &dport); + struct cxl_port *port __free(put_cxl_port) = + cxl_pci_find_port(pdev, &dport); if (!port) return -EPROBE_DEFER; component_reg_phys = cxl_rcd_component_reg_phys(&pdev->dev, dport); - - put_device(&port->dev); - if (component_reg_phys == CXL_RESOURCE_NONE) return -ENXIO; @@ -578,9 +579,10 @@ static void free_event_buf(void *buf) */ static int cxl_mem_alloc_event_buf(struct cxl_memdev_state *mds) { + struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox; struct cxl_get_event_payload *buf; - buf = kvmalloc(mds->payload_size, GFP_KERNEL); + buf = kvmalloc(cxl_mbox->payload_size, GFP_KERNEL); if (!buf) return -ENOMEM; mds->event.buf = buf; @@ -653,6 +655,7 @@ static int cxl_event_req_irq(struct cxl_dev_state *cxlds, u8 setting) static int cxl_event_get_int_policy(struct cxl_memdev_state *mds, struct cxl_event_interrupt_policy *policy) { + struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox; struct cxl_mbox_cmd mbox_cmd = { .opcode = CXL_MBOX_OP_GET_EVT_INT_POLICY, .payload_out = policy, @@ -660,7 +663,7 @@ static int cxl_event_get_int_policy(struct cxl_memdev_state *mds, }; int rc; - rc = cxl_internal_send_cmd(mds, &mbox_cmd); + rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd); if (rc < 0) dev_err(mds->cxlds.dev, "Failed to get event interrupt policy : %d", rc); @@ -671,6 +674,7 @@ static int cxl_event_get_int_policy(struct cxl_memdev_state *mds, static int cxl_event_config_msgnums(struct cxl_memdev_state *mds, struct cxl_event_interrupt_policy *policy) { + struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox; struct cxl_mbox_cmd mbox_cmd; int rc; @@ -687,7 +691,7 @@ static int cxl_event_config_msgnums(struct cxl_memdev_state *mds, .size_in = sizeof(*policy), }; - rc = cxl_internal_send_cmd(mds, &mbox_cmd); + rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd); if (rc < 0) { dev_err(mds->cxlds.dev, "Failed to set event interrupt policy : %d", rc); @@ -786,6 +790,23 @@ static int cxl_event_config(struct pci_host_bridge *host_bridge, return 0; } +static int cxl_pci_type3_init_mailbox(struct cxl_dev_state *cxlds) +{ + int rc; + + /* + * Fail the init if there's no mailbox. For a type3 this is out of spec. + */ + if (!cxlds->reg_map.device_map.mbox.valid) + return -ENODEV; + + rc = cxl_mailbox_init(&cxlds->cxl_mbox, cxlds->dev); + if (rc) + return rc; + + return 0; +} + static int cxl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) { struct pci_host_bridge *host_bridge = pci_find_host_bridge(pdev->bus); @@ -846,6 +867,10 @@ static int cxl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (rc) dev_dbg(&pdev->dev, "Failed to map RAS capability.\n"); + rc = cxl_pci_type3_init_mailbox(cxlds); + if (rc) + return rc; + rc = cxl_await_media_ready(cxlds); if (rc == 0) cxlds->media_ready = true; diff --git a/drivers/cxl/pmem.c b/drivers/cxl/pmem.c index 4ef93da22335..d2d43a4fc053 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 <linux/libnvdimm.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/device.h> #include <linux/module.h> #include <linux/ndctl.h> @@ -102,13 +102,15 @@ static int cxl_pmem_get_config_size(struct cxl_memdev_state *mds, struct nd_cmd_get_config_size *cmd, unsigned int buf_len) { + struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox; + if (sizeof(*cmd) > buf_len) return -EINVAL; *cmd = (struct nd_cmd_get_config_size){ .config_size = mds->lsa_size, .max_xfer = - mds->payload_size - sizeof(struct cxl_mbox_set_lsa), + cxl_mbox->payload_size - sizeof(struct cxl_mbox_set_lsa), }; return 0; @@ -118,6 +120,7 @@ static int cxl_pmem_get_config_data(struct cxl_memdev_state *mds, struct nd_cmd_get_config_data_hdr *cmd, unsigned int buf_len) { + struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox; struct cxl_mbox_get_lsa get_lsa; struct cxl_mbox_cmd mbox_cmd; int rc; @@ -139,7 +142,7 @@ static int cxl_pmem_get_config_data(struct cxl_memdev_state *mds, .payload_out = cmd->out_buf, }; - rc = cxl_internal_send_cmd(mds, &mbox_cmd); + rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd); cmd->status = 0; return rc; @@ -149,6 +152,7 @@ static int cxl_pmem_set_config_data(struct cxl_memdev_state *mds, struct nd_cmd_set_config_hdr *cmd, unsigned int buf_len) { + struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox; struct cxl_mbox_set_lsa *set_lsa; struct cxl_mbox_cmd mbox_cmd; int rc; @@ -175,7 +179,7 @@ static int cxl_pmem_set_config_data(struct cxl_memdev_state *mds, .size_in = struct_size(set_lsa, data, cmd->in_length), }; - rc = cxl_internal_send_cmd(mds, &mbox_cmd); + rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd); /* * Set "firmware" status (4-packed bytes at the end of the input @@ -233,15 +237,13 @@ static int detach_nvdimm(struct device *dev, void *data) if (!is_cxl_nvdimm(dev)) return 0; - device_lock(dev); - if (!dev->driver) - goto out; - - cxl_nvd = to_cxl_nvdimm(dev); - if (cxl_nvd->cxlmd && cxl_nvd->cxlmd->cxl_nvb == data) - release = true; -out: - device_unlock(dev); + scoped_guard(device, dev) { + if (dev->driver) { + cxl_nvd = to_cxl_nvdimm(dev); + if (cxl_nvd->cxlmd && cxl_nvd->cxlmd->cxl_nvb == data) + release = true; + } + } if (release) device_release_driver(dev); return 0; diff --git a/drivers/cxl/port.c b/drivers/cxl/port.c index d7d5d982ce69..861dde65768f 100644 --- a/drivers/cxl/port.c +++ b/drivers/cxl/port.c @@ -98,7 +98,7 @@ static int cxl_endpoint_port_probe(struct cxl_port *port) struct cxl_port *root; int rc; - rc = cxl_dvsec_rr_decode(cxlds->dev, cxlds->cxl_dvsec, &info); + rc = cxl_dvsec_rr_decode(cxlds->dev, port, &info); if (rc < 0) return rc; diff --git a/drivers/cxl/security.c b/drivers/cxl/security.c index 21856a3f408e..ab793e8577c7 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 <linux/libnvdimm.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/module.h> #include <linux/async.h> #include <linux/slab.h> @@ -14,6 +14,7 @@ static unsigned long cxl_pmem_get_security_flags(struct nvdimm *nvdimm, { struct cxl_nvdimm *cxl_nvd = nvdimm_provider_data(nvdimm); struct cxl_memdev *cxlmd = cxl_nvd->cxlmd; + struct cxl_mailbox *cxl_mbox = &cxlmd->cxlds->cxl_mbox; struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds); unsigned long security_flags = 0; struct cxl_get_security_output { @@ -29,7 +30,7 @@ static unsigned long cxl_pmem_get_security_flags(struct nvdimm *nvdimm, .payload_out = &out, }; - rc = cxl_internal_send_cmd(mds, &mbox_cmd); + rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd); if (rc < 0) return 0; @@ -70,7 +71,7 @@ static int cxl_pmem_security_change_key(struct nvdimm *nvdimm, { struct cxl_nvdimm *cxl_nvd = nvdimm_provider_data(nvdimm); struct cxl_memdev *cxlmd = cxl_nvd->cxlmd; - struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds); + struct cxl_mailbox *cxl_mbox = &cxlmd->cxlds->cxl_mbox; struct cxl_mbox_cmd mbox_cmd; struct cxl_set_pass set_pass; @@ -87,7 +88,7 @@ static int cxl_pmem_security_change_key(struct nvdimm *nvdimm, .payload_in = &set_pass, }; - return cxl_internal_send_cmd(mds, &mbox_cmd); + return cxl_internal_send_cmd(cxl_mbox, &mbox_cmd); } static int __cxl_pmem_security_disable(struct nvdimm *nvdimm, @@ -96,7 +97,7 @@ static int __cxl_pmem_security_disable(struct nvdimm *nvdimm, { struct cxl_nvdimm *cxl_nvd = nvdimm_provider_data(nvdimm); struct cxl_memdev *cxlmd = cxl_nvd->cxlmd; - struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds); + struct cxl_mailbox *cxl_mbox = &cxlmd->cxlds->cxl_mbox; struct cxl_disable_pass dis_pass; struct cxl_mbox_cmd mbox_cmd; @@ -112,7 +113,7 @@ static int __cxl_pmem_security_disable(struct nvdimm *nvdimm, .payload_in = &dis_pass, }; - return cxl_internal_send_cmd(mds, &mbox_cmd); + return cxl_internal_send_cmd(cxl_mbox, &mbox_cmd); } static int cxl_pmem_security_disable(struct nvdimm *nvdimm, @@ -131,12 +132,12 @@ static int cxl_pmem_security_freeze(struct nvdimm *nvdimm) { struct cxl_nvdimm *cxl_nvd = nvdimm_provider_data(nvdimm); struct cxl_memdev *cxlmd = cxl_nvd->cxlmd; - struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds); + struct cxl_mailbox *cxl_mbox = &cxlmd->cxlds->cxl_mbox; struct cxl_mbox_cmd mbox_cmd = { .opcode = CXL_MBOX_OP_FREEZE_SECURITY, }; - return cxl_internal_send_cmd(mds, &mbox_cmd); + return cxl_internal_send_cmd(cxl_mbox, &mbox_cmd); } static int cxl_pmem_security_unlock(struct nvdimm *nvdimm, @@ -144,7 +145,7 @@ static int cxl_pmem_security_unlock(struct nvdimm *nvdimm, { struct cxl_nvdimm *cxl_nvd = nvdimm_provider_data(nvdimm); struct cxl_memdev *cxlmd = cxl_nvd->cxlmd; - struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds); + struct cxl_mailbox *cxl_mbox = &cxlmd->cxlds->cxl_mbox; u8 pass[NVDIMM_PASSPHRASE_LEN]; struct cxl_mbox_cmd mbox_cmd; int rc; @@ -156,7 +157,7 @@ static int cxl_pmem_security_unlock(struct nvdimm *nvdimm, .payload_in = pass, }; - rc = cxl_internal_send_cmd(mds, &mbox_cmd); + rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd); if (rc < 0) return rc; @@ -169,7 +170,7 @@ static int cxl_pmem_security_passphrase_erase(struct nvdimm *nvdimm, { struct cxl_nvdimm *cxl_nvd = nvdimm_provider_data(nvdimm); struct cxl_memdev *cxlmd = cxl_nvd->cxlmd; - struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds); + struct cxl_mailbox *cxl_mbox = &cxlmd->cxlds->cxl_mbox; struct cxl_mbox_cmd mbox_cmd; struct cxl_pass_erase erase; int rc; @@ -185,7 +186,7 @@ static int cxl_pmem_security_passphrase_erase(struct nvdimm *nvdimm, .payload_in = &erase, }; - rc = cxl_internal_send_cmd(mds, &mbox_cmd); + rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd); if (rc < 0) return rc; diff --git a/drivers/firewire/net.c b/drivers/firewire/net.c index 7a4d1a478e33..1bf0e15c1540 100644 --- a/drivers/firewire/net.c +++ b/drivers/firewire/net.c @@ -28,7 +28,7 @@ #include <linux/slab.h> #include <linux/spinlock.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <net/arp.h> #include <net/firewire.h> diff --git a/drivers/firmware/arm_scmi/common.h b/drivers/firmware/arm_scmi/common.h index 6d9227db473f..c4b8e7ff88aa 100644 --- a/drivers/firmware/arm_scmi/common.h +++ b/drivers/firmware/arm_scmi/common.h @@ -22,7 +22,7 @@ #include <linux/spinlock.h> #include <linux/types.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "protocols.h" #include "notify.h" diff --git a/drivers/firmware/arm_scmi/protocols.h b/drivers/firmware/arm_scmi/protocols.h index 8e95f53bd7b7..aaee57cdcd55 100644 --- a/drivers/firmware/arm_scmi/protocols.h +++ b/drivers/firmware/arm_scmi/protocols.h @@ -22,7 +22,7 @@ #include <linux/spinlock.h> #include <linux/types.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #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 23b002e4d4a0..fde0656481cc 100644 --- a/drivers/firmware/dmi_scan.c +++ b/drivers/firmware/dmi_scan.c @@ -9,7 +9,7 @@ #include <linux/memblock.h> #include <linux/random.h> #include <asm/dmi.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #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 0ec83ba58097..b815d2a754ee 100644 --- a/drivers/firmware/efi/fdtparams.c +++ b/drivers/firmware/efi/fdtparams.c @@ -8,7 +8,7 @@ #include <linux/libfdt.h> #include <linux/of_fdt.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> enum { SYSTAB, diff --git a/drivers/firmware/efi/libstub/riscv-stub.c b/drivers/firmware/efi/libstub/riscv-stub.c index c96d6dcee86c..e7d9204baee3 100644 --- a/drivers/firmware/efi/libstub/riscv-stub.c +++ b/drivers/firmware/efi/libstub/riscv-stub.c @@ -7,7 +7,7 @@ #include <asm/efi.h> #include <asm/sections.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "efistub.h" diff --git a/drivers/firmware/efi/libstub/riscv.c b/drivers/firmware/efi/libstub/riscv.c index 8022b104c3e6..f66f33ceb99e 100644 --- a/drivers/firmware/efi/libstub/riscv.c +++ b/drivers/firmware/efi/libstub/riscv.c @@ -7,7 +7,7 @@ #include <linux/libfdt.h> #include <asm/efi.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "efistub.h" diff --git a/drivers/firmware/efi/libstub/zboot.c b/drivers/firmware/efi/libstub/zboot.c index 1ceace956758..af23b3c50228 100644 --- a/drivers/firmware/efi/libstub/zboot.c +++ b/drivers/firmware/efi/libstub/zboot.c @@ -3,7 +3,7 @@ #include <linux/efi.h> #include <linux/pe.h> #include <asm/efi.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "efistub.h" diff --git a/drivers/firmware/sysfb.c b/drivers/firmware/sysfb.c index 02a07d3d0d40..a3df782fa687 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 2a82c726d6e5..6134cea86ac8 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 <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/delay.h> #include <linux/fpga/fpga-mgr.h> #include <linux/iopoll.h> diff --git a/drivers/fsi/fsi-occ.c b/drivers/fsi/fsi-occ.c index f58b158d097c..a6d4c8f123a5 100644 --- a/drivers/fsi/fsi-occ.c +++ b/drivers/fsi/fsi-occ.c @@ -20,7 +20,7 @@ #include <linux/sched.h> #include <linux/slab.h> #include <linux/uaccess.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #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 b54fef6b1e12..76b58c70b257 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 c6afbf434366..d5952ab7752c 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/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index dcd59040c449..9b1e0ede05a4 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -1083,10 +1083,6 @@ struct amdgpu_device { struct amdgpu_virt virt; - /* link all shadow bo */ - struct list_head shadow_list; - struct mutex shadow_list_lock; - /* record hw reset is performed */ bool has_hw_reset; u8 reset_magic[AMDGPU_RESET_MAGIC_NUM]; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c index 57bda66e85ef..2ca127173135 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c @@ -511,7 +511,7 @@ static int __aca_get_error_data(struct amdgpu_device *adev, struct aca_handle *h return -EINVAL; } - /* udpate aca bank to aca source error_cache first */ + /* update aca bank to aca source error_cache first */ ret = aca_banks_update(adev, smu_type, handler_aca_log_bank_error, qctx, NULL); if (ret) return ret; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c index 1254a43ec96b..3bc0cbf45bc5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c @@ -950,28 +950,30 @@ static void unlock_spi_csq_mutexes(struct amdgpu_device *adev) * @inst: xcc's instance number on a multi-XCC setup */ static void get_wave_count(struct amdgpu_device *adev, int queue_idx, - int *wave_cnt, int *vmid, uint32_t inst) + struct kfd_cu_occupancy *queue_cnt, uint32_t inst) { int pipe_idx; int queue_slot; unsigned int reg_val; - + unsigned int wave_cnt; /* * Program GRBM with appropriate MEID, PIPEID, QUEUEID and VMID * parameters to read out waves in flight. Get VMID if there are * non-zero waves in flight. */ - *vmid = 0xFF; - *wave_cnt = 0; pipe_idx = queue_idx / adev->gfx.mec.num_queue_per_pipe; queue_slot = queue_idx % adev->gfx.mec.num_queue_per_pipe; - soc15_grbm_select(adev, 1, pipe_idx, queue_slot, 0, inst); - reg_val = RREG32_SOC15_IP(GC, SOC15_REG_OFFSET(GC, inst, mmSPI_CSQ_WF_ACTIVE_COUNT_0) + - queue_slot); - *wave_cnt = reg_val & SPI_CSQ_WF_ACTIVE_COUNT_0__COUNT_MASK; - if (*wave_cnt != 0) - *vmid = (RREG32_SOC15(GC, inst, mmCP_HQD_VMID) & - CP_HQD_VMID__VMID_MASK) >> CP_HQD_VMID__VMID__SHIFT; + soc15_grbm_select(adev, 1, pipe_idx, queue_slot, 0, GET_INST(GC, inst)); + reg_val = RREG32_SOC15_IP(GC, SOC15_REG_OFFSET(GC, GET_INST(GC, inst), + mmSPI_CSQ_WF_ACTIVE_COUNT_0) + queue_slot); + wave_cnt = reg_val & SPI_CSQ_WF_ACTIVE_COUNT_0__COUNT_MASK; + if (wave_cnt != 0) { + queue_cnt->wave_cnt += wave_cnt; + queue_cnt->doorbell_off = + (RREG32_SOC15(GC, GET_INST(GC, inst), mmCP_HQD_PQ_DOORBELL_CONTROL) & + CP_HQD_PQ_DOORBELL_CONTROL__DOORBELL_OFFSET_MASK) >> + CP_HQD_PQ_DOORBELL_CONTROL__DOORBELL_OFFSET__SHIFT; + } } /** @@ -981,9 +983,8 @@ static void get_wave_count(struct amdgpu_device *adev, int queue_idx, * or more queues running and submitting waves to compute units. * * @adev: Handle of device from which to get number of waves in flight - * @pasid: Identifies the process for which this query call is invoked - * @pasid_wave_cnt: Output parameter updated with number of waves in flight that - * belong to process with given pasid + * @cu_occupancy: Array that gets filled with wave_cnt and doorbell offset + * for comparison later. * @max_waves_per_cu: Output parameter updated with maximum number of waves * possible per Compute Unit * @inst: xcc's instance number on a multi-XCC setup @@ -1011,34 +1012,28 @@ static void get_wave_count(struct amdgpu_device *adev, int queue_idx, * number of waves that are in flight for the queue at specified index. The * index ranges from 0 to 7. * - * If non-zero waves are in flight, read CP_HQD_VMID register to obtain VMID - * of the wave(s). + * If non-zero waves are in flight, store the corresponding doorbell offset + * of the queue, along with the wave count. * - * Determine if VMID from above step maps to pasid provided as parameter. If - * it matches agrregate the wave count. That the VMID will not match pasid is - * a normal condition i.e. a device is expected to support multiple queues - * from multiple proceses. + * Determine if the queue belongs to the process by comparing the doorbell + * offset against the process's queues. If it matches, aggregate the wave + * count for the process. * * Reading registers referenced above involves programming GRBM appropriately */ -void kgd_gfx_v9_get_cu_occupancy(struct amdgpu_device *adev, int pasid, - int *pasid_wave_cnt, int *max_waves_per_cu, uint32_t inst) +void kgd_gfx_v9_get_cu_occupancy(struct amdgpu_device *adev, + struct kfd_cu_occupancy *cu_occupancy, + int *max_waves_per_cu, uint32_t inst) { int qidx; - int vmid; int se_idx; - int sh_idx; int se_cnt; - int sh_cnt; - int wave_cnt; int queue_map; - int pasid_tmp; int max_queue_cnt; - int vmid_wave_cnt = 0; DECLARE_BITMAP(cp_queue_bitmap, AMDGPU_MAX_QUEUES); lock_spi_csq_mutexes(adev); - soc15_grbm_select(adev, 1, 0, 0, 0, inst); + soc15_grbm_select(adev, 1, 0, 0, 0, GET_INST(GC, inst)); /* * Iterate through the shader engines and arrays of the device @@ -1048,51 +1043,38 @@ void kgd_gfx_v9_get_cu_occupancy(struct amdgpu_device *adev, int pasid, AMDGPU_MAX_QUEUES); max_queue_cnt = adev->gfx.mec.num_pipe_per_mec * adev->gfx.mec.num_queue_per_pipe; - sh_cnt = adev->gfx.config.max_sh_per_se; se_cnt = adev->gfx.config.max_shader_engines; for (se_idx = 0; se_idx < se_cnt; se_idx++) { - for (sh_idx = 0; sh_idx < sh_cnt; sh_idx++) { + amdgpu_gfx_select_se_sh(adev, se_idx, 0, 0xffffffff, inst); + queue_map = RREG32_SOC15(GC, GET_INST(GC, inst), mmSPI_CSQ_WF_ACTIVE_STATUS); + + /* + * Assumption: queue map encodes following schema: four + * pipes per each micro-engine, with each pipe mapping + * eight queues. This schema is true for GFX9 devices + * and must be verified for newer device families + */ + for (qidx = 0; qidx < max_queue_cnt; qidx++) { + /* Skip qeueus that are not associated with + * compute functions + */ + if (!test_bit(qidx, cp_queue_bitmap)) + continue; - amdgpu_gfx_select_se_sh(adev, se_idx, sh_idx, 0xffffffff, inst); - queue_map = RREG32_SOC15(GC, inst, mmSPI_CSQ_WF_ACTIVE_STATUS); + if (!(queue_map & (1 << qidx))) + continue; - /* - * Assumption: queue map encodes following schema: four - * pipes per each micro-engine, with each pipe mapping - * eight queues. This schema is true for GFX9 devices - * and must be verified for newer device families - */ - for (qidx = 0; qidx < max_queue_cnt; qidx++) { - - /* Skip qeueus that are not associated with - * compute functions - */ - if (!test_bit(qidx, cp_queue_bitmap)) - continue; - - if (!(queue_map & (1 << qidx))) - continue; - - /* Get number of waves in flight and aggregate them */ - get_wave_count(adev, qidx, &wave_cnt, &vmid, - inst); - if (wave_cnt != 0) { - pasid_tmp = - RREG32(SOC15_REG_OFFSET(OSSSYS, inst, - mmIH_VMID_0_LUT) + vmid); - if (pasid_tmp == pasid) - vmid_wave_cnt += wave_cnt; - } - } + /* Get number of waves in flight and aggregate them */ + get_wave_count(adev, qidx, &cu_occupancy[qidx], + inst); } } amdgpu_gfx_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff, inst); - soc15_grbm_select(adev, 0, 0, 0, 0, inst); + soc15_grbm_select(adev, 0, 0, 0, 0, GET_INST(GC, inst)); unlock_spi_csq_mutexes(adev); /* Update the output parameters and return */ - *pasid_wave_cnt = vmid_wave_cnt; *max_waves_per_cu = adev->gfx.cu_info.simd_per_cu * adev->gfx.cu_info.max_waves_per_simd; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h index 988c50ac3be0..b6a91a552aa4 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h @@ -52,8 +52,9 @@ bool kgd_gfx_v9_get_atc_vmid_pasid_mapping_info(struct amdgpu_device *adev, uint8_t vmid, uint16_t *p_pasid); void kgd_gfx_v9_set_vm_context_page_table_base(struct amdgpu_device *adev, uint32_t vmid, uint64_t page_table_base); -void kgd_gfx_v9_get_cu_occupancy(struct amdgpu_device *adev, int pasid, - int *pasid_wave_cnt, int *max_waves_per_cu, uint32_t inst); +void kgd_gfx_v9_get_cu_occupancy(struct amdgpu_device *adev, + struct kfd_cu_occupancy *cu_occupancy, + int *max_waves_per_cu, uint32_t inst); void kgd_gfx_v9_program_trap_handler_settings(struct amdgpu_device *adev, uint32_t vmid, uint64_t tba_addr, uint64_t tma_addr, uint32_t inst); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index 4afef5b46c7d..ce5ca304dba9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -1499,7 +1499,7 @@ static int amdgpu_amdkfd_gpuvm_pin_bo(struct amdgpu_bo *bo, u32 domain) } } - ret = amdgpu_bo_pin_restricted(bo, domain, 0, 0); + ret = amdgpu_bo_pin(bo, domain); if (ret) pr_err("Error in Pinning BO to domain: %d\n", domain); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c index 42e64bce661e..45affc02548c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c @@ -87,8 +87,9 @@ static bool check_atom_bios(uint8_t *bios, size_t size) * part of the system bios. On boot, the system bios puts a * copy of the igp rom at the start of vram if a discrete card is * present. + * For SR-IOV, the vbios image is also put in VRAM in the VF. */ -static bool igp_read_bios_from_vram(struct amdgpu_device *adev) +static bool amdgpu_read_bios_from_vram(struct amdgpu_device *adev) { uint8_t __iomem *bios; resource_size_t vram_base; @@ -284,10 +285,6 @@ static bool amdgpu_atrm_get_bios(struct amdgpu_device *adev) acpi_status status; bool found = false; - /* ATRM is for the discrete card only */ - if (adev->flags & AMD_IS_APU) - return false; - /* ATRM is for on-platform devices only */ if (dev_is_removable(&adev->pdev->dev)) return false; @@ -343,11 +340,8 @@ static inline bool amdgpu_atrm_get_bios(struct amdgpu_device *adev) static bool amdgpu_read_disabled_bios(struct amdgpu_device *adev) { - if (adev->flags & AMD_IS_APU) - return igp_read_bios_from_vram(adev); - else - return (!adev->asic_funcs || !adev->asic_funcs->read_disabled_bios) ? - false : amdgpu_asic_read_disabled_bios(adev); + return (!adev->asic_funcs || !adev->asic_funcs->read_disabled_bios) ? + false : amdgpu_asic_read_disabled_bios(adev); } #ifdef CONFIG_ACPI @@ -414,7 +408,36 @@ static inline bool amdgpu_acpi_vfct_bios(struct amdgpu_device *adev) } #endif -bool amdgpu_get_bios(struct amdgpu_device *adev) +static bool amdgpu_get_bios_apu(struct amdgpu_device *adev) +{ + if (amdgpu_acpi_vfct_bios(adev)) { + dev_info(adev->dev, "Fetched VBIOS from VFCT\n"); + goto success; + } + + if (amdgpu_read_bios_from_vram(adev)) { + dev_info(adev->dev, "Fetched VBIOS from VRAM BAR\n"); + goto success; + } + + if (amdgpu_read_bios(adev)) { + dev_info(adev->dev, "Fetched VBIOS from ROM BAR\n"); + goto success; + } + + if (amdgpu_read_platform_bios(adev)) { + dev_info(adev->dev, "Fetched VBIOS from platform\n"); + goto success; + } + + dev_err(adev->dev, "Unable to locate a BIOS ROM\n"); + return false; + +success: + return true; +} + +static bool amdgpu_get_bios_dgpu(struct amdgpu_device *adev) { if (amdgpu_atrm_get_bios(adev)) { dev_info(adev->dev, "Fetched VBIOS from ATRM\n"); @@ -426,7 +449,8 @@ bool amdgpu_get_bios(struct amdgpu_device *adev) goto success; } - if (igp_read_bios_from_vram(adev)) { + /* this is required for SR-IOV */ + if (amdgpu_read_bios_from_vram(adev)) { dev_info(adev->dev, "Fetched VBIOS from VRAM BAR\n"); goto success; } @@ -455,10 +479,24 @@ bool amdgpu_get_bios(struct amdgpu_device *adev) return false; success: - adev->is_atom_fw = adev->asic_type >= CHIP_VEGA10; return true; } +bool amdgpu_get_bios(struct amdgpu_device *adev) +{ + bool found; + + if (adev->flags & AMD_IS_APU) + found = amdgpu_get_bios_apu(adev); + else + found = amdgpu_get_bios_dgpu(adev); + + if (found) + adev->is_atom_fw = adev->asic_type >= CHIP_VEGA10; + + return found; +} + /* helper function for soc15 and onwards to read bios from rom */ bool amdgpu_soc15_read_bios_from_rom(struct amdgpu_device *adev, u8 *bios, u32 length_bytes) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index f4628412dac4..c2394c8b4d6b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -4107,9 +4107,6 @@ int amdgpu_device_init(struct amdgpu_device *adev, spin_lock_init(&adev->mm_stats.lock); spin_lock_init(&adev->wb.lock); - INIT_LIST_HEAD(&adev->shadow_list); - mutex_init(&adev->shadow_list_lock); - INIT_LIST_HEAD(&adev->reset_list); INIT_LIST_HEAD(&adev->ras_list); @@ -5030,80 +5027,6 @@ static int amdgpu_device_ip_post_soft_reset(struct amdgpu_device *adev) } /** - * amdgpu_device_recover_vram - Recover some VRAM contents - * - * @adev: amdgpu_device pointer - * - * Restores the contents of VRAM buffers from the shadows in GTT. Used to - * restore things like GPUVM page tables after a GPU reset where - * the contents of VRAM might be lost. - * - * Returns: - * 0 on success, negative error code on failure. - */ -static int amdgpu_device_recover_vram(struct amdgpu_device *adev) -{ - struct dma_fence *fence = NULL, *next = NULL; - struct amdgpu_bo *shadow; - struct amdgpu_bo_vm *vmbo; - long r = 1, tmo; - - if (amdgpu_sriov_runtime(adev)) - tmo = msecs_to_jiffies(8000); - else - tmo = msecs_to_jiffies(100); - - dev_info(adev->dev, "recover vram bo from shadow start\n"); - mutex_lock(&adev->shadow_list_lock); - list_for_each_entry(vmbo, &adev->shadow_list, shadow_list) { - /* If vm is compute context or adev is APU, shadow will be NULL */ - if (!vmbo->shadow) - continue; - shadow = vmbo->shadow; - - /* No need to recover an evicted BO */ - if (!shadow->tbo.resource || - shadow->tbo.resource->mem_type != TTM_PL_TT || - shadow->tbo.resource->start == AMDGPU_BO_INVALID_OFFSET || - shadow->parent->tbo.resource->mem_type != TTM_PL_VRAM) - continue; - - r = amdgpu_bo_restore_shadow(shadow, &next); - if (r) - break; - - if (fence) { - tmo = dma_fence_wait_timeout(fence, false, tmo); - dma_fence_put(fence); - fence = next; - if (tmo == 0) { - r = -ETIMEDOUT; - break; - } else if (tmo < 0) { - r = tmo; - break; - } - } else { - fence = next; - } - } - mutex_unlock(&adev->shadow_list_lock); - - if (fence) - tmo = dma_fence_wait_timeout(fence, false, tmo); - dma_fence_put(fence); - - if (r < 0 || tmo <= 0) { - dev_err(adev->dev, "recover vram bo from shadow failed, r is %ld, tmo is %ld\n", r, tmo); - return -EIO; - } - - dev_info(adev->dev, "recover vram bo from shadow done\n"); - return 0; -} - - -/** * amdgpu_device_reset_sriov - reset ASIC for SR-IOV vf * * @adev: amdgpu_device pointer @@ -5165,12 +5088,8 @@ static int amdgpu_device_reset_sriov(struct amdgpu_device *adev, if (r) return r; - if (adev->virt.gim_feature & AMDGIM_FEATURE_GIM_FLR_VRAMLOST) { + if (adev->virt.gim_feature & AMDGIM_FEATURE_GIM_FLR_VRAMLOST) amdgpu_inc_vram_lost(adev); - r = amdgpu_device_recover_vram(adev); - } - if (r) - return r; /* need to be called during full access so we can't do it later like * bare-metal does. @@ -5569,9 +5488,7 @@ out: } } - if (!r) - r = amdgpu_device_recover_vram(tmp_adev); - else + if (r) tmp_adev->asic_reset_res = r; } @@ -6189,7 +6106,7 @@ bool amdgpu_device_is_peer_accessible(struct amdgpu_device *adev, p2p_addressable = !(adev->gmc.aper_base & address_mask || aper_limit & address_mask); } - return is_large_bar && p2p_access && p2p_addressable; + return pcie_p2p && is_large_bar && p2p_access && p2p_addressable; #else return false; #endif diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c index 092ec11258cd..b119d27271c1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c @@ -233,6 +233,7 @@ int amdgpu_display_crtc_page_flip_target(struct drm_crtc *crtc, } if (!adev->enable_virtual_display) { + new_abo->flags |= AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS; r = amdgpu_bo_pin(new_abo, amdgpu_display_supported_domains(adev, new_abo->flags)); if (unlikely(r != 0)) { @@ -1474,7 +1475,7 @@ bool amdgpu_display_crtc_scaling_mode_fixup(struct drm_crtc *crtc, if ((!(mode->flags & DRM_MODE_FLAG_INTERLACE)) && ((amdgpu_encoder->underscan_type == UNDERSCAN_ON) || ((amdgpu_encoder->underscan_type == UNDERSCAN_AUTO) && - connector->display_info.is_hdmi && + connector && connector->display_info.is_hdmi && amdgpu_display_is_hdtv_mode(mode)))) { if (amdgpu_encoder->underscan_hborder != 0) amdgpu_crtc->h_border = amdgpu_encoder->underscan_hborder; @@ -1759,6 +1760,7 @@ int amdgpu_display_resume_helper(struct amdgpu_device *adev) r = amdgpu_bo_reserve(aobj, true); if (r == 0) { + aobj->flags |= AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS; r = amdgpu_bo_pin(aobj, AMDGPU_GEM_DOMAIN_VRAM); if (r != 0) dev_err(adev->dev, "Failed to pin cursor BO (%d)\n", r); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index f57411ed2dc2..81d9877c8735 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -117,9 +117,10 @@ * - 3.56.0 - Update IB start address and size alignment for decode and encode * - 3.57.0 - Compute tunneling on GFX10+ * - 3.58.0 - Add GFX12 DCC support + * - 3.59.0 - Cleared VRAM */ #define KMS_DRIVER_MAJOR 3 -#define KMS_DRIVER_MINOR 58 +#define KMS_DRIVER_MINOR 59 #define KMS_DRIVER_PATCHLEVEL 0 /* diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c index 0e617dff8765..1a5df8b94661 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c @@ -43,8 +43,6 @@ #include "amdgpu_hmm.h" #include "amdgpu_xgmi.h" -static const struct drm_gem_object_funcs amdgpu_gem_object_funcs; - static vm_fault_t amdgpu_gem_fault(struct vm_fault *vmf) { struct ttm_buffer_object *bo = vmf->vma->vm_private_data; @@ -87,11 +85,11 @@ static const struct vm_operations_struct amdgpu_gem_vm_ops = { static void amdgpu_gem_object_free(struct drm_gem_object *gobj) { - struct amdgpu_bo *robj = gem_to_amdgpu_bo(gobj); + struct amdgpu_bo *aobj = gem_to_amdgpu_bo(gobj); - if (robj) { - amdgpu_hmm_unregister(robj); - amdgpu_bo_unref(&robj); + if (aobj) { + amdgpu_hmm_unregister(aobj); + ttm_bo_put(&aobj->tbo); } } @@ -126,7 +124,6 @@ int amdgpu_gem_object_create(struct amdgpu_device *adev, unsigned long size, bo = &ubo->bo; *obj = &bo->tbo.base; - (*obj)->funcs = &amdgpu_gem_object_funcs; return 0; } @@ -295,7 +292,7 @@ static int amdgpu_gem_object_mmap(struct drm_gem_object *obj, struct vm_area_str return drm_gem_ttm_mmap(obj, vma); } -static const struct drm_gem_object_funcs amdgpu_gem_object_funcs = { +const struct drm_gem_object_funcs amdgpu_gem_object_funcs = { .free = amdgpu_gem_object_free, .open = amdgpu_gem_object_open, .close = amdgpu_gem_object_close, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.h index f30264782ba2..3a8f57900a3a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.h @@ -33,6 +33,8 @@ #define AMDGPU_GEM_DOMAIN_MAX 0x3 #define gem_to_amdgpu_bo(gobj) container_of((gobj), struct amdgpu_bo, tbo.base) +extern const struct drm_gem_object_funcs amdgpu_gem_object_funcs; + unsigned long amdgpu_gem_timeout(uint64_t timeout_ns); /* diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c index ad6bf5d4e0a9..16f2605ac50b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c @@ -107,8 +107,11 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job) /* * Do the coredump immediately after a job timeout to get a very * close dump/snapshot/representation of GPU's current error status + * Skip it for SRIOV, since VF FLR will be triggered by host driver + * before job timeout */ - amdgpu_job_core_dump(adev, job); + if (!amdgpu_sriov_vf(adev)) + amdgpu_job_core_dump(adev, job); if (amdgpu_gpu_recovery && amdgpu_ring_soft_recovery(ring, job->vmid, s_job->s_fence->parent)) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index e32161f6b67a..44819cdba7fb 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -77,24 +77,6 @@ static void amdgpu_bo_user_destroy(struct ttm_buffer_object *tbo) amdgpu_bo_destroy(tbo); } -static void amdgpu_bo_vm_destroy(struct ttm_buffer_object *tbo) -{ - struct amdgpu_device *adev = amdgpu_ttm_adev(tbo->bdev); - struct amdgpu_bo *shadow_bo = ttm_to_amdgpu_bo(tbo), *bo; - struct amdgpu_bo_vm *vmbo; - - bo = shadow_bo->parent; - vmbo = to_amdgpu_bo_vm(bo); - /* in case amdgpu_device_recover_vram got NULL of bo->parent */ - if (!list_empty(&vmbo->shadow_list)) { - mutex_lock(&adev->shadow_list_lock); - list_del_init(&vmbo->shadow_list); - mutex_unlock(&adev->shadow_list_lock); - } - - amdgpu_bo_destroy(tbo); -} - /** * amdgpu_bo_is_amdgpu_bo - check if the buffer object is an &amdgpu_bo * @bo: buffer object to be checked @@ -108,8 +90,7 @@ static void amdgpu_bo_vm_destroy(struct ttm_buffer_object *tbo) bool amdgpu_bo_is_amdgpu_bo(struct ttm_buffer_object *bo) { if (bo->destroy == &amdgpu_bo_destroy || - bo->destroy == &amdgpu_bo_user_destroy || - bo->destroy == &amdgpu_bo_vm_destroy) + bo->destroy == &amdgpu_bo_user_destroy) return true; return false; @@ -583,6 +564,7 @@ int amdgpu_bo_create(struct amdgpu_device *adev, if (bo == NULL) return -ENOMEM; drm_gem_private_object_init(adev_to_drm(adev), &bo->tbo.base, size); + bo->tbo.base.funcs = &amdgpu_gem_object_funcs; bo->vm_bo = NULL; bo->preferred_domains = bp->preferred_domain ? bp->preferred_domain : bp->domain; @@ -723,52 +705,6 @@ int amdgpu_bo_create_vm(struct amdgpu_device *adev, } /** - * amdgpu_bo_add_to_shadow_list - add a BO to the shadow list - * - * @vmbo: BO that will be inserted into the shadow list - * - * Insert a BO to the shadow list. - */ -void amdgpu_bo_add_to_shadow_list(struct amdgpu_bo_vm *vmbo) -{ - struct amdgpu_device *adev = amdgpu_ttm_adev(vmbo->bo.tbo.bdev); - - mutex_lock(&adev->shadow_list_lock); - list_add_tail(&vmbo->shadow_list, &adev->shadow_list); - vmbo->shadow->parent = amdgpu_bo_ref(&vmbo->bo); - vmbo->shadow->tbo.destroy = &amdgpu_bo_vm_destroy; - mutex_unlock(&adev->shadow_list_lock); -} - -/** - * amdgpu_bo_restore_shadow - restore an &amdgpu_bo shadow - * - * @shadow: &amdgpu_bo shadow to be restored - * @fence: dma_fence associated with the operation - * - * Copies a buffer object's shadow content back to the object. - * This is used for recovering a buffer from its shadow in case of a gpu - * reset where vram context may be lost. - * - * Returns: - * 0 for success or a negative error code on failure. - */ -int amdgpu_bo_restore_shadow(struct amdgpu_bo *shadow, struct dma_fence **fence) - -{ - struct amdgpu_device *adev = amdgpu_ttm_adev(shadow->tbo.bdev); - struct amdgpu_ring *ring = adev->mman.buffer_funcs_ring; - uint64_t shadow_addr, parent_addr; - - shadow_addr = amdgpu_bo_gpu_offset(shadow); - parent_addr = amdgpu_bo_gpu_offset(shadow->parent); - - return amdgpu_copy_buffer(ring, shadow_addr, parent_addr, - amdgpu_bo_size(shadow), NULL, fence, - true, false, 0); -} - -/** * amdgpu_bo_kmap - map an &amdgpu_bo buffer object * @bo: &amdgpu_bo buffer object to be mapped * @ptr: kernel virtual address to be returned @@ -851,7 +787,7 @@ struct amdgpu_bo *amdgpu_bo_ref(struct amdgpu_bo *bo) if (bo == NULL) return NULL; - ttm_bo_get(&bo->tbo); + drm_gem_object_get(&bo->tbo.base); return bo; } @@ -863,40 +799,30 @@ struct amdgpu_bo *amdgpu_bo_ref(struct amdgpu_bo *bo) */ void amdgpu_bo_unref(struct amdgpu_bo **bo) { - struct ttm_buffer_object *tbo; - if ((*bo) == NULL) return; - tbo = &((*bo)->tbo); - ttm_bo_put(tbo); + drm_gem_object_put(&(*bo)->tbo.base); *bo = NULL; } /** - * amdgpu_bo_pin_restricted - pin an &amdgpu_bo buffer object + * amdgpu_bo_pin - pin an &amdgpu_bo buffer object * @bo: &amdgpu_bo buffer object to be pinned * @domain: domain to be pinned to - * @min_offset: the start of requested address range - * @max_offset: the end of requested address range * - * Pins the buffer object according to requested domain and address range. If - * the memory is unbound gart memory, binds the pages into gart table. Adjusts - * pin_count and pin_size accordingly. + * Pins the buffer object according to requested domain. If the memory is + * unbound gart memory, binds the pages into gart table. Adjusts pin_count and + * pin_size accordingly. * * Pinning means to lock pages in memory along with keeping them at a fixed * offset. It is required when a buffer can not be moved, for example, when * a display buffer is being scanned out. * - * Compared with amdgpu_bo_pin(), this function gives more flexibility on - * where to pin a buffer if there are specific restrictions on where a buffer - * must be located. - * * Returns: * 0 for success or a negative error code on failure. */ -int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain, - u64 min_offset, u64 max_offset) +int amdgpu_bo_pin(struct amdgpu_bo *bo, u32 domain) { struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev); struct ttm_operation_ctx ctx = { false, false }; @@ -905,9 +831,6 @@ int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain, if (amdgpu_ttm_tt_get_usermm(bo->tbo.ttm)) return -EPERM; - if (WARN_ON_ONCE(min_offset > max_offset)) - return -EINVAL; - /* Check domain to be pinned to against preferred domains */ if (bo->preferred_domains & domain) domain = bo->preferred_domains & domain; @@ -933,14 +856,6 @@ int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain, return -EINVAL; ttm_bo_pin(&bo->tbo); - - if (max_offset != 0) { - u64 domain_start = amdgpu_ttm_domain_start(adev, - mem_type); - WARN_ON_ONCE(max_offset < - (amdgpu_bo_gpu_offset(bo) - domain_start)); - } - return 0; } @@ -957,17 +872,6 @@ int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain, bo->flags |= AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED; amdgpu_bo_placement_from_domain(bo, domain); for (i = 0; i < bo->placement.num_placement; i++) { - unsigned int fpfn, lpfn; - - fpfn = min_offset >> PAGE_SHIFT; - lpfn = max_offset >> PAGE_SHIFT; - - if (fpfn > bo->placements[i].fpfn) - bo->placements[i].fpfn = fpfn; - if (!bo->placements[i].lpfn || - (lpfn && lpfn < bo->placements[i].lpfn)) - bo->placements[i].lpfn = lpfn; - if (bo->flags & AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS && bo->placements[i].mem_type == TTM_PL_VRAM) bo->placements[i].flags |= TTM_PL_FLAG_CONTIGUOUS; @@ -994,24 +898,6 @@ error: } /** - * amdgpu_bo_pin - pin an &amdgpu_bo buffer object - * @bo: &amdgpu_bo buffer object to be pinned - * @domain: domain to be pinned to - * - * A simple wrapper to amdgpu_bo_pin_restricted(). - * Provides a simpler API for buffers that do not have any strict restrictions - * on where a buffer must be located. - * - * Returns: - * 0 for success or a negative error code on failure. - */ -int amdgpu_bo_pin(struct amdgpu_bo *bo, u32 domain) -{ - bo->flags |= AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS; - return amdgpu_bo_pin_restricted(bo, domain, 0, 0); -} - -/** * amdgpu_bo_unpin - unpin an &amdgpu_bo buffer object * @bo: &amdgpu_bo buffer object to be unpinned * diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h index d7e27957013f..717e47b46167 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h @@ -136,8 +136,6 @@ struct amdgpu_bo_user { struct amdgpu_bo_vm { struct amdgpu_bo bo; - struct amdgpu_bo *shadow; - struct list_head shadow_list; struct amdgpu_vm_bo_base entries[]; }; @@ -275,22 +273,6 @@ static inline bool amdgpu_bo_encrypted(struct amdgpu_bo *bo) return bo->flags & AMDGPU_GEM_CREATE_ENCRYPTED; } -/** - * amdgpu_bo_shadowed - check if the BO is shadowed - * - * @bo: BO to be tested. - * - * Returns: - * NULL if not shadowed or else return a BO pointer. - */ -static inline struct amdgpu_bo *amdgpu_bo_shadowed(struct amdgpu_bo *bo) -{ - if (bo->tbo.type == ttm_bo_type_kernel) - return to_amdgpu_bo_vm(bo)->shadow; - - return NULL; -} - bool amdgpu_bo_is_amdgpu_bo(struct ttm_buffer_object *bo); void amdgpu_bo_placement_from_domain(struct amdgpu_bo *abo, u32 domain); @@ -322,8 +304,6 @@ void amdgpu_bo_kunmap(struct amdgpu_bo *bo); struct amdgpu_bo *amdgpu_bo_ref(struct amdgpu_bo *bo); void amdgpu_bo_unref(struct amdgpu_bo **bo); int amdgpu_bo_pin(struct amdgpu_bo *bo, u32 domain); -int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain, - u64 min_offset, u64 max_offset); void amdgpu_bo_unpin(struct amdgpu_bo *bo); int amdgpu_bo_init(struct amdgpu_device *adev); void amdgpu_bo_fini(struct amdgpu_device *adev); @@ -349,9 +329,6 @@ u64 amdgpu_bo_gpu_offset(struct amdgpu_bo *bo); u64 amdgpu_bo_gpu_offset_no_check(struct amdgpu_bo *bo); void amdgpu_bo_get_memory(struct amdgpu_bo *bo, struct amdgpu_mem_stats *stats); -void amdgpu_bo_add_to_shadow_list(struct amdgpu_bo_vm *vmbo); -int amdgpu_bo_restore_shadow(struct amdgpu_bo *shadow, - struct dma_fence **fence); uint32_t amdgpu_bo_get_preferred_domain(struct amdgpu_device *adev, uint32_t domain); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index 189574d53ebd..0b28b2cf1517 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -2853,7 +2853,7 @@ static int psp_load_non_psp_fw(struct psp_context *psp) if (ret) return ret; - /* Start rlc autoload after psp recieved all the gfx firmware */ + /* Start rlc autoload after psp received all the gfx firmware */ if (psp->autoload_supported && ucode->ucode_id == (amdgpu_sriov_vf(adev) ? adev->virt.autoload_ucode_id : AMDGPU_UCODE_ID_RLC_G)) { ret = psp_rlc_autoload_start(psp); @@ -3425,9 +3425,11 @@ int psp_init_sos_microcode(struct psp_context *psp, const char *chip_name) const struct psp_firmware_header_v1_2 *sos_hdr_v1_2; const struct psp_firmware_header_v1_3 *sos_hdr_v1_3; const struct psp_firmware_header_v2_0 *sos_hdr_v2_0; - int err = 0; + const struct psp_firmware_header_v2_1 *sos_hdr_v2_1; + int fw_index, fw_bin_count, start_index = 0; + const struct psp_fw_bin_desc *fw_bin; uint8_t *ucode_array_start_addr; - int fw_index = 0; + int err = 0; err = amdgpu_ucode_request(adev, &adev->psp.sos_fw, "amdgpu/%s_sos.bin", chip_name); if (err) @@ -3478,15 +3480,30 @@ int psp_init_sos_microcode(struct psp_context *psp, const char *chip_name) case 2: sos_hdr_v2_0 = (const struct psp_firmware_header_v2_0 *)adev->psp.sos_fw->data; - if (le32_to_cpu(sos_hdr_v2_0->psp_fw_bin_count) >= UCODE_MAX_PSP_PACKAGING) { + fw_bin_count = le32_to_cpu(sos_hdr_v2_0->psp_fw_bin_count); + + if (fw_bin_count >= UCODE_MAX_PSP_PACKAGING) { dev_err(adev->dev, "packed SOS count exceeds maximum limit\n"); err = -EINVAL; goto out; } - for (fw_index = 0; fw_index < le32_to_cpu(sos_hdr_v2_0->psp_fw_bin_count); fw_index++) { - err = parse_sos_bin_descriptor(psp, - &sos_hdr_v2_0->psp_fw_bin[fw_index], + if (sos_hdr_v2_0->header.header_version_minor == 1) { + sos_hdr_v2_1 = (const struct psp_firmware_header_v2_1 *)adev->psp.sos_fw->data; + + fw_bin = sos_hdr_v2_1->psp_fw_bin; + + if (psp_is_aux_sos_load_required(psp)) + start_index = le32_to_cpu(sos_hdr_v2_1->psp_aux_fw_bin_index); + else + fw_bin_count -= le32_to_cpu(sos_hdr_v2_1->psp_aux_fw_bin_index); + + } else { + fw_bin = sos_hdr_v2_0->psp_fw_bin; + } + + for (fw_index = start_index; fw_index < fw_bin_count; fw_index++) { + err = parse_sos_bin_descriptor(psp, fw_bin + fw_index, sos_hdr_v2_0); if (err) goto out; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h index 74a96516c913..e8abbbcb4326 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h @@ -138,6 +138,7 @@ struct psp_funcs { int (*vbflash_stat)(struct psp_context *psp); int (*fatal_error_recovery_quirk)(struct psp_context *psp); bool (*get_ras_capability)(struct psp_context *psp); + bool (*is_aux_sos_load_required)(struct psp_context *psp); }; struct ta_funcs { @@ -464,6 +465,9 @@ struct amdgpu_psp_funcs { ((psp)->funcs->fatal_error_recovery_quirk ? \ (psp)->funcs->fatal_error_recovery_quirk((psp)) : 0) +#define psp_is_aux_sos_load_required(psp) \ + ((psp)->funcs->is_aux_sos_load_required ? (psp)->funcs->is_aux_sos_load_required((psp)) : 0) + extern const struct amd_ip_funcs psp_ip_funcs; extern const struct amdgpu_ip_block_version psp_v3_1_ip_block; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index 61a2f386d9fb..1a1395c5fff1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -882,7 +882,7 @@ int amdgpu_ras_feature_enable_on_boot(struct amdgpu_device *adev, if (ret) return ret; - /* gfx block ras dsiable cmd must send to ras-ta */ + /* gfx block ras disable cmd must send to ras-ta */ if (head->block == AMDGPU_RAS_BLOCK__GFX) con->features |= BIT(head->block); @@ -3468,6 +3468,11 @@ init_ras_enabled_flag: /* aca is disabled by default */ adev->aca.is_enabled = false; + + /* bad page feature is not applicable to specific app platform */ + if (adev->gmc.is_app_apu && + amdgpu_ip_version(adev, UMC_HWIP, 0) == IP_VERSION(12, 0, 0)) + amdgpu_bad_page_threshold = 0; } static void amdgpu_ras_counte_dw(struct work_struct *work) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c index aab8077e5098..f28f6b4ba765 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c @@ -58,7 +58,7 @@ #define EEPROM_I2C_MADDR_4 0x40000 /* - * The 2 macros bellow represent the actual size in bytes that + * The 2 macros below represent the actual size in bytes that * those entities occupy in the EEPROM memory. * RAS_TABLE_RECORD_SIZE is different than sizeof(eeprom_table_record) which * uses uint64 to store 6b fields such as retired_page. diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c index bdf1ef825d89..c586ab4c911b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c @@ -260,6 +260,36 @@ int amdgpu_sync_resv(struct amdgpu_device *adev, struct amdgpu_sync *sync, return 0; } +/** + * amdgpu_sync_kfd - sync to KFD fences + * + * @sync: sync object to add KFD fences to + * @resv: reservation object with KFD fences + * + * Extract all KFD fences and add them to the sync object. + */ +int amdgpu_sync_kfd(struct amdgpu_sync *sync, struct dma_resv *resv) +{ + struct dma_resv_iter cursor; + struct dma_fence *f; + int r = 0; + + dma_resv_iter_begin(&cursor, resv, DMA_RESV_USAGE_BOOKKEEP); + dma_resv_for_each_fence_unlocked(&cursor, f) { + void *fence_owner = amdgpu_sync_get_owner(f); + + if (fence_owner != AMDGPU_FENCE_OWNER_KFD) + continue; + + r = amdgpu_sync_fence(sync, f); + if (r) + break; + } + dma_resv_iter_end(&cursor); + + return r; +} + /* Free the entry back to the slab */ static void amdgpu_sync_entry_free(struct amdgpu_sync_entry *e) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.h index cf1e9e858efd..e3272dce798d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.h @@ -51,6 +51,7 @@ int amdgpu_sync_fence(struct amdgpu_sync *sync, struct dma_fence *f); int amdgpu_sync_resv(struct amdgpu_device *adev, struct amdgpu_sync *sync, struct dma_resv *resv, enum amdgpu_sync_mode mode, void *owner); +int amdgpu_sync_kfd(struct amdgpu_sync *sync, struct dma_resv *resv); struct dma_fence *amdgpu_sync_peek_fence(struct amdgpu_sync *sync, struct amdgpu_ring *ring); struct dma_fence *amdgpu_sync_get_fence(struct amdgpu_sync *sync); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index b8bc7fa8c375..74adb983ab03 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -1970,7 +1970,7 @@ int amdgpu_ttm_init(struct amdgpu_device *adev) DRM_INFO("amdgpu: %uM of GTT memory ready.\n", (unsigned int)(gtt_size / (1024 * 1024))); - /* Initiailize doorbell pool on PCI BAR */ + /* Initialize doorbell pool on PCI BAR */ r = amdgpu_ttm_init_on_chip(adev, AMDGPU_PL_DOORBELL, adev->doorbell.size / PAGE_SIZE); if (r) { DRM_ERROR("Failed initializing doorbell heap.\n"); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h index 5bc37acd3981..4e23419b92d4 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h @@ -136,6 +136,14 @@ struct psp_firmware_header_v2_0 { struct psp_fw_bin_desc psp_fw_bin[]; }; +/* version_major=2, version_minor=1 */ +struct psp_firmware_header_v2_1 { + struct common_firmware_header header; + uint32_t psp_fw_bin_count; + uint32_t psp_aux_fw_bin_index; + struct psp_fw_bin_desc psp_fw_bin[]; +}; + /* version_major=1, version_minor=0 */ struct ta_firmware_header_v1_0 { struct common_firmware_header header; @@ -426,6 +434,7 @@ union amdgpu_firmware_header { struct psp_firmware_header_v1_1 psp_v1_1; struct psp_firmware_header_v1_3 psp_v1_3; struct psp_firmware_header_v2_0 psp_v2_0; + struct psp_firmware_header_v2_0 psp_v2_1; struct ta_firmware_header_v1_0 ta; struct ta_firmware_header_v2_0 ta_v2_0; struct gfx_firmware_header_v1_0 gfx; @@ -447,7 +456,7 @@ union amdgpu_firmware_header { uint8_t raw[0x100]; }; -#define UCODE_MAX_PSP_PACKAGING ((sizeof(union amdgpu_firmware_header) - sizeof(struct common_firmware_header) - 4) / sizeof(struct psp_fw_bin_desc)) +#define UCODE_MAX_PSP_PACKAGING (((sizeof(union amdgpu_firmware_header) - sizeof(struct common_firmware_header) - 4) / sizeof(struct psp_fw_bin_desc)) * 2) /* * fw loading support diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c index e5f508d34ed8..d4c2afafbb73 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c @@ -338,6 +338,7 @@ static int amdgpu_vkms_prepare_fb(struct drm_plane *plane, else domain = AMDGPU_GEM_DOMAIN_VRAM; + rbo->flags |= AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS; r = amdgpu_bo_pin(rbo, domain); if (unlikely(r != 0)) { if (r != -ERESTARTSYS) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 2452dfa6314f..6005280f5f38 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -465,7 +465,6 @@ int amdgpu_vm_validate(struct amdgpu_device *adev, struct amdgpu_vm *vm, { uint64_t new_vm_generation = amdgpu_vm_generation(adev, vm); struct amdgpu_vm_bo_base *bo_base; - struct amdgpu_bo *shadow; struct amdgpu_bo *bo; int r; @@ -486,16 +485,10 @@ int amdgpu_vm_validate(struct amdgpu_device *adev, struct amdgpu_vm *vm, spin_unlock(&vm->status_lock); bo = bo_base->bo; - shadow = amdgpu_bo_shadowed(bo); r = validate(param, bo); if (r) return r; - if (shadow) { - r = validate(param, shadow); - if (r) - return r; - } if (bo->tbo.type != ttm_bo_type_kernel) { amdgpu_vm_bo_moved(bo_base); @@ -1176,6 +1169,12 @@ int amdgpu_vm_bo_update(struct amdgpu_device *adev, struct amdgpu_bo_va *bo_va, AMDGPU_SYNC_EQ_OWNER, vm); if (r) goto error_free; + if (bo) { + r = amdgpu_sync_kfd(&sync, bo->tbo.base.resv); + if (r) + goto error_free; + } + } else { struct drm_gem_object *obj = &bo->tbo.base; @@ -2149,10 +2148,6 @@ void amdgpu_vm_bo_invalidate(struct amdgpu_device *adev, { struct amdgpu_vm_bo_base *bo_base; - /* shadow bo doesn't have bo base, its validation needs its parent */ - if (bo->parent && (amdgpu_bo_shadowed(bo->parent) == bo)) - bo = bo->parent; - for (bo_base = bo->vm_bo; bo_base; bo_base = bo_base->next) { struct amdgpu_vm *vm = bo_base->vm; @@ -2482,7 +2477,6 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm, root_bo = amdgpu_bo_ref(&root->bo); r = amdgpu_bo_reserve(root_bo, true); if (r) { - amdgpu_bo_unref(&root->shadow); amdgpu_bo_unref(&root_bo); goto error_free_delayed; } @@ -2575,11 +2569,6 @@ int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm) vm->last_update = dma_fence_get_stub(); vm->is_compute_context = true; - /* Free the shadow bo for compute VM */ - amdgpu_bo_unref(&to_amdgpu_bo_vm(vm->root.bo)->shadow); - - goto unreserve_bo; - unreserve_bo: amdgpu_bo_unreserve(vm->root.bo); return r; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c index a076f43097e4..f78a0434a48f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c @@ -383,14 +383,6 @@ int amdgpu_vm_pt_clear(struct amdgpu_device *adev, struct amdgpu_vm *vm, if (r) return r; - if (vmbo->shadow) { - struct amdgpu_bo *shadow = vmbo->shadow; - - r = ttm_bo_validate(&shadow->tbo, &shadow->placement, &ctx); - if (r) - return r; - } - if (!drm_dev_enter(adev_to_drm(adev), &idx)) return -ENODEV; @@ -448,10 +440,7 @@ int amdgpu_vm_pt_create(struct amdgpu_device *adev, struct amdgpu_vm *vm, int32_t xcp_id) { struct amdgpu_bo_param bp; - struct amdgpu_bo *bo; - struct dma_resv *resv; unsigned int num_entries; - int r; memset(&bp, 0, sizeof(bp)); @@ -484,42 +473,7 @@ int amdgpu_vm_pt_create(struct amdgpu_device *adev, struct amdgpu_vm *vm, if (vm->root.bo) bp.resv = vm->root.bo->tbo.base.resv; - r = amdgpu_bo_create_vm(adev, &bp, vmbo); - if (r) - return r; - - bo = &(*vmbo)->bo; - if (vm->is_compute_context || (adev->flags & AMD_IS_APU)) { - (*vmbo)->shadow = NULL; - return 0; - } - - if (!bp.resv) - WARN_ON(dma_resv_lock(bo->tbo.base.resv, - NULL)); - resv = bp.resv; - memset(&bp, 0, sizeof(bp)); - bp.size = amdgpu_vm_pt_size(adev, level); - bp.domain = AMDGPU_GEM_DOMAIN_GTT; - bp.flags = AMDGPU_GEM_CREATE_CPU_GTT_USWC; - bp.type = ttm_bo_type_kernel; - bp.resv = bo->tbo.base.resv; - bp.bo_ptr_size = sizeof(struct amdgpu_bo); - bp.xcp_id_plus1 = xcp_id + 1; - - r = amdgpu_bo_create(adev, &bp, &(*vmbo)->shadow); - - if (!resv) - dma_resv_unlock(bo->tbo.base.resv); - - if (r) { - amdgpu_bo_unref(&bo); - return r; - } - - amdgpu_bo_add_to_shadow_list(*vmbo); - - return 0; + return amdgpu_bo_create_vm(adev, &bp, vmbo); } /** @@ -569,7 +523,6 @@ static int amdgpu_vm_pt_alloc(struct amdgpu_device *adev, return 0; error_free_pt: - amdgpu_bo_unref(&pt->shadow); amdgpu_bo_unref(&pt_bo); return r; } @@ -581,17 +534,10 @@ error_free_pt: */ static void amdgpu_vm_pt_free(struct amdgpu_vm_bo_base *entry) { - struct amdgpu_bo *shadow; - if (!entry->bo) return; entry->bo->vm_bo = NULL; - shadow = amdgpu_bo_shadowed(entry->bo); - if (shadow) { - ttm_bo_set_bulk_move(&shadow->tbo, NULL); - amdgpu_bo_unref(&shadow); - } ttm_bo_set_bulk_move(&entry->bo->tbo, NULL); spin_lock(&entry->vm->status_lock); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c index 4772fba33285..46d9fb433ab2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c @@ -35,16 +35,7 @@ */ static int amdgpu_vm_sdma_map_table(struct amdgpu_bo_vm *table) { - int r; - - r = amdgpu_ttm_alloc_gart(&table->bo.tbo); - if (r) - return r; - - if (table->shadow) - r = amdgpu_ttm_alloc_gart(&table->shadow->tbo); - - return r; + return amdgpu_ttm_alloc_gart(&table->bo.tbo); } /* Allocate a new job for @count PTE updates */ @@ -265,17 +256,13 @@ static int amdgpu_vm_sdma_update(struct amdgpu_vm_update_params *p, if (!p->pages_addr) { /* set page commands needed */ - if (vmbo->shadow) - amdgpu_vm_sdma_set_ptes(p, vmbo->shadow, pe, addr, - count, incr, flags); amdgpu_vm_sdma_set_ptes(p, bo, pe, addr, count, incr, flags); return 0; } /* copy commands needed */ - ndw -= p->adev->vm_manager.vm_pte_funcs->copy_pte_num_dw * - (vmbo->shadow ? 2 : 1); + ndw -= p->adev->vm_manager.vm_pte_funcs->copy_pte_num_dw; /* for padding */ ndw -= 7; @@ -290,8 +277,6 @@ static int amdgpu_vm_sdma_update(struct amdgpu_vm_update_params *p, pte[i] |= flags; } - if (vmbo->shadow) - amdgpu_vm_sdma_copy_ptes(p, vmbo->shadow, pe, nptes); amdgpu_vm_sdma_copy_ptes(p, bo, pe, nptes); pe += nptes * 8; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.h index 90138bc5f03d..32775260556f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.h @@ -180,6 +180,6 @@ amdgpu_get_next_xcp(struct amdgpu_xcp_mgr *xcp_mgr, int *from) #define for_each_xcp(xcp_mgr, xcp, i) \ for (i = 0, xcp = amdgpu_get_next_xcp(xcp_mgr, &i); xcp; \ - xcp = amdgpu_get_next_xcp(xcp_mgr, &i)) + ++i, xcp = amdgpu_get_next_xcp(xcp_mgr, &i)) #endif diff --git a/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c b/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c index 26e2188101e7..5e8833e4fed2 100644 --- a/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c +++ b/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c @@ -94,8 +94,6 @@ static void aqua_vanjaram_set_xcp_id(struct amdgpu_device *adev, case AMDGPU_RING_TYPE_VCN_ENC: case AMDGPU_RING_TYPE_VCN_JPEG: ip_blk = AMDGPU_XCP_VCN; - if (aqua_vanjaram_xcp_vcn_shared(adev)) - inst_mask = 1 << (inst_idx * 2); break; default: DRM_ERROR("Not support ring type %d!", ring->funcs->type); @@ -105,6 +103,8 @@ static void aqua_vanjaram_set_xcp_id(struct amdgpu_device *adev, for (xcp_id = 0; xcp_id < adev->xcp_mgr->num_xcps; xcp_id++) { if (adev->xcp_mgr->xcp[xcp_id].ip[ip_blk].inst_mask & inst_mask) { ring->xcp_id = xcp_id; + dev_dbg(adev->dev, "ring:%s xcp_id :%u", ring->name, + ring->xcp_id); if (ring->funcs->type == AMDGPU_RING_TYPE_COMPUTE) adev->gfx.enforce_isolation[xcp_id].xcp_id = xcp_id; break; @@ -394,38 +394,31 @@ static int __aqua_vanjaram_get_xcp_ip_info(struct amdgpu_xcp_mgr *xcp_mgr, int x struct amdgpu_xcp_ip *ip) { struct amdgpu_device *adev = xcp_mgr->adev; + int num_sdma, num_vcn, num_shared_vcn, num_xcp; int num_xcc_xcp, num_sdma_xcp, num_vcn_xcp; - int num_sdma, num_vcn; num_sdma = adev->sdma.num_instances; num_vcn = adev->vcn.num_vcn_inst; + num_shared_vcn = 1; + + num_xcc_xcp = adev->gfx.num_xcc_per_xcp; + num_xcp = NUM_XCC(adev->gfx.xcc_mask) / num_xcc_xcp; switch (xcp_mgr->mode) { case AMDGPU_SPX_PARTITION_MODE: - num_sdma_xcp = num_sdma; - num_vcn_xcp = num_vcn; - break; case AMDGPU_DPX_PARTITION_MODE: - num_sdma_xcp = num_sdma / 2; - num_vcn_xcp = num_vcn / 2; - break; case AMDGPU_TPX_PARTITION_MODE: - num_sdma_xcp = num_sdma / 3; - num_vcn_xcp = num_vcn / 3; - break; case AMDGPU_QPX_PARTITION_MODE: - num_sdma_xcp = num_sdma / 4; - num_vcn_xcp = num_vcn / 4; - break; case AMDGPU_CPX_PARTITION_MODE: - num_sdma_xcp = 2; - num_vcn_xcp = num_vcn ? 1 : 0; + num_sdma_xcp = DIV_ROUND_UP(num_sdma, num_xcp); + num_vcn_xcp = DIV_ROUND_UP(num_vcn, num_xcp); break; default: return -EINVAL; } - num_xcc_xcp = adev->gfx.num_xcc_per_xcp; + if (num_vcn && num_xcp > num_vcn) + num_shared_vcn = num_xcp / num_vcn; switch (ip_id) { case AMDGPU_XCP_GFXHUB: @@ -441,7 +434,8 @@ static int __aqua_vanjaram_get_xcp_ip_info(struct amdgpu_xcp_mgr *xcp_mgr, int x ip->ip_funcs = &sdma_v4_4_2_xcp_funcs; break; case AMDGPU_XCP_VCN: - ip->inst_mask = XCP_INST_MASK(num_vcn_xcp, xcp_id); + ip->inst_mask = + XCP_INST_MASK(num_vcn_xcp, xcp_id / num_shared_vcn); /* TODO : Assign IP funcs */ break; default: diff --git a/drivers/gpu/drm/amd/amdgpu/atom.c b/drivers/gpu/drm/amd/amdgpu/atom.c index 09715b506468..81d195d366ce 100644 --- a/drivers/gpu/drm/amd/amdgpu/atom.c +++ b/drivers/gpu/drm/amd/amdgpu/atom.c @@ -27,7 +27,7 @@ #include <linux/slab.h> #include <linux/string_helpers.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <drm/drm_util.h> diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c index 742adbc460c9..70c1399f738d 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c @@ -1881,6 +1881,7 @@ static int dce_v10_0_crtc_do_set_base(struct drm_crtc *crtc, return r; if (!atomic) { + abo->flags |= AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS; r = amdgpu_bo_pin(abo, AMDGPU_GEM_DOMAIN_VRAM); if (unlikely(r != 0)) { amdgpu_bo_unreserve(abo); @@ -2401,6 +2402,7 @@ static int dce_v10_0_crtc_cursor_set2(struct drm_crtc *crtc, return ret; } + aobj->flags |= AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS; ret = amdgpu_bo_pin(aobj, AMDGPU_GEM_DOMAIN_VRAM); amdgpu_bo_unreserve(aobj); if (ret) { diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c index 8d46ebadfa46..f154c24499c8 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c @@ -1931,6 +1931,7 @@ static int dce_v11_0_crtc_do_set_base(struct drm_crtc *crtc, return r; if (!atomic) { + abo->flags |= AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS; r = amdgpu_bo_pin(abo, AMDGPU_GEM_DOMAIN_VRAM); if (unlikely(r != 0)) { amdgpu_bo_unreserve(abo); @@ -2485,6 +2486,7 @@ static int dce_v11_0_crtc_cursor_set2(struct drm_crtc *crtc, return ret; } + aobj->flags |= AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS; ret = amdgpu_bo_pin(aobj, AMDGPU_GEM_DOMAIN_VRAM); amdgpu_bo_unreserve(aobj); if (ret) { diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c index f08dc6a3886f..a7fcb135827f 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c @@ -1861,6 +1861,7 @@ static int dce_v6_0_crtc_do_set_base(struct drm_crtc *crtc, return r; if (!atomic) { + abo->flags |= AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS; r = amdgpu_bo_pin(abo, AMDGPU_GEM_DOMAIN_VRAM); if (unlikely(r != 0)) { amdgpu_bo_unreserve(abo); @@ -2321,6 +2322,7 @@ static int dce_v6_0_crtc_cursor_set2(struct drm_crtc *crtc, return ret; } + aobj->flags |= AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS; ret = amdgpu_bo_pin(aobj, AMDGPU_GEM_DOMAIN_VRAM); amdgpu_bo_unreserve(aobj); if (ret) { diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c index a6a3adf2ae13..77ac3f114d24 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c @@ -1828,6 +1828,7 @@ static int dce_v8_0_crtc_do_set_base(struct drm_crtc *crtc, return r; if (!atomic) { + abo->flags |= AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS; r = amdgpu_bo_pin(abo, AMDGPU_GEM_DOMAIN_VRAM); if (unlikely(r != 0)) { amdgpu_bo_unreserve(abo); @@ -2320,6 +2321,7 @@ static int dce_v8_0_crtc_cursor_set2(struct drm_crtc *crtc, return ret; } + aobj->flags |= AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS; ret = amdgpu_bo_pin(aobj, AMDGPU_GEM_DOMAIN_VRAM); amdgpu_bo_unreserve(aobj); if (ret) { diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c index d1357c01eb39..47b47d21f464 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c @@ -202,12 +202,16 @@ static const struct amdgpu_hwip_reg_entry gc_gfx_queue_reg_list_12[] = { SOC15_REG_ENTRY_STR(GC, 0, regCP_IB1_BUFSZ) }; -static const struct soc15_reg_golden golden_settings_gc_12_0[] = { +static const struct soc15_reg_golden golden_settings_gc_12_0_rev0[] = { SOC15_REG_GOLDEN_VALUE(GC, 0, regDB_MEM_CONFIG, 0x0000000f, 0x0000000f), SOC15_REG_GOLDEN_VALUE(GC, 0, regCB_HW_CONTROL_1, 0x03000000, 0x03000000), SOC15_REG_GOLDEN_VALUE(GC, 0, regGL2C_CTRL5, 0x00000070, 0x00000020) }; +static const struct soc15_reg_golden golden_settings_gc_12_0[] = { + SOC15_REG_GOLDEN_VALUE(GC, 0, regDB_MEM_CONFIG, 0x00008000, 0x00008000), +}; + #define DEFAULT_SH_MEM_CONFIG \ ((SH_MEM_ADDRESS_MODE_64 << SH_MEM_CONFIG__ADDRESS_MODE__SHIFT) | \ (SH_MEM_ALIGNMENT_MODE_UNALIGNED << SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT) | \ @@ -3495,10 +3499,14 @@ static void gfx_v12_0_init_golden_registers(struct amdgpu_device *adev) switch (amdgpu_ip_version(adev, GC_HWIP, 0)) { case IP_VERSION(12, 0, 0): case IP_VERSION(12, 0, 1): + soc15_program_register_sequence(adev, + golden_settings_gc_12_0, + (const u32)ARRAY_SIZE(golden_settings_gc_12_0)); + if (adev->rev_id == 0) soc15_program_register_sequence(adev, - golden_settings_gc_12_0, - (const u32)ARRAY_SIZE(golden_settings_gc_12_0)); + golden_settings_gc_12_0_rev0, + (const u32)ARRAY_SIZE(golden_settings_gc_12_0_rev0)); break; default: break; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c index 408e5600bb61..c100845409f7 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c @@ -1701,7 +1701,15 @@ static void gfx_v9_4_3_xcc_cp_compute_enable(struct amdgpu_device *adev, WREG32_SOC15_RLC(GC, GET_INST(GC, xcc_id), regCP_MEC_CNTL, 0); } else { WREG32_SOC15_RLC(GC, GET_INST(GC, xcc_id), regCP_MEC_CNTL, - (CP_MEC_CNTL__MEC_ME1_HALT_MASK | CP_MEC_CNTL__MEC_ME2_HALT_MASK)); + (CP_MEC_CNTL__MEC_INVALIDATE_ICACHE_MASK | + CP_MEC_CNTL__MEC_ME1_PIPE0_RESET_MASK | + CP_MEC_CNTL__MEC_ME1_PIPE1_RESET_MASK | + CP_MEC_CNTL__MEC_ME1_PIPE2_RESET_MASK | + CP_MEC_CNTL__MEC_ME1_PIPE3_RESET_MASK | + CP_MEC_CNTL__MEC_ME2_PIPE0_RESET_MASK | + CP_MEC_CNTL__MEC_ME2_PIPE1_RESET_MASK | + CP_MEC_CNTL__MEC_ME1_HALT_MASK | + CP_MEC_CNTL__MEC_ME2_HALT_MASK)); adev->gfx.kiq[xcc_id].ring.sched.ready = false; } udelay(50); @@ -2240,6 +2248,8 @@ static int gfx_v9_4_3_xcc_cp_resume(struct amdgpu_device *adev, int xcc_id) r = gfx_v9_4_3_xcc_cp_compute_load_microcode(adev, xcc_id); if (r) return r; + } else { + gfx_v9_4_3_xcc_cp_compute_enable(adev, false, xcc_id); } r = gfx_v9_4_3_xcc_kiq_resume(adev, xcc_id); @@ -2299,12 +2309,6 @@ static int gfx_v9_4_3_cp_resume(struct amdgpu_device *adev) return 0; } -static void gfx_v9_4_3_xcc_cp_enable(struct amdgpu_device *adev, bool enable, - int xcc_id) -{ - gfx_v9_4_3_xcc_cp_compute_enable(adev, enable, xcc_id); -} - static void gfx_v9_4_3_xcc_fini(struct amdgpu_device *adev, int xcc_id) { if (amdgpu_gfx_disable_kcq(adev, xcc_id)) @@ -2336,7 +2340,7 @@ static void gfx_v9_4_3_xcc_fini(struct amdgpu_device *adev, int xcc_id) } gfx_v9_4_3_xcc_kcq_fini_register(adev, xcc_id); - gfx_v9_4_3_xcc_cp_enable(adev, false, xcc_id); + gfx_v9_4_3_xcc_cp_compute_enable(adev, false, xcc_id); } static int gfx_v9_4_3_hw_init(void *handle) diff --git a/drivers/gpu/drm/amd/amdgpu/imu_v11_0.c b/drivers/gpu/drm/amd/amdgpu/imu_v11_0.c index 6c1891889c4d..d4f72e47ae9e 100644 --- a/drivers/gpu/drm/amd/amdgpu/imu_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/imu_v11_0.c @@ -153,7 +153,7 @@ static void imu_v11_0_setup(struct amdgpu_device *adev) WREG32_SOC15(GC, 0, regGFX_IMU_C2PMSG_16, imu_reg_val); } - //disble imu Rtavfs, SmsRepair, DfllBTC, and ClkB + //disable imu Rtavfs, SmsRepair, DfllBTC, and ClkB imu_reg_val = RREG32_SOC15(GC, 0, regGFX_IMU_SCRATCH_10); imu_reg_val |= 0x10007; WREG32_SOC15(GC, 0, regGFX_IMU_SCRATCH_10, imu_reg_val); diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c index ee91ff9e52a2..231a3d490ea8 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c @@ -161,7 +161,7 @@ static int mes_v11_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes, int api_status_off) { union MESAPI__QUERY_MES_STATUS mes_status_pkt; - signed long timeout = 3000000; /* 3000 ms */ + signed long timeout = 2100000; /* 2100 ms */ struct amdgpu_device *adev = mes->adev; struct amdgpu_ring *ring = &mes->ring[0]; struct MES_API_STATUS *api_status; diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c index e499b2857a01..8d27421689c9 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c @@ -146,7 +146,7 @@ static int mes_v12_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes, int api_status_off) { union MESAPI__QUERY_MES_STATUS mes_status_pkt; - signed long timeout = 3000000; /* 3000 ms */ + signed long timeout = 2100000; /* 2100 ms */ struct amdgpu_device *adev = mes->adev; struct amdgpu_ring *ring = &mes->ring[pipe]; spinlock_t *ring_lock = &mes->ring_lock[pipe]; @@ -479,6 +479,11 @@ static int mes_v12_0_misc_op(struct amdgpu_mes *mes, union MESAPI__MISC misc_pkt; int pipe; + if (mes->adev->enable_uni_mes) + pipe = AMDGPU_MES_KIQ_PIPE; + else + pipe = AMDGPU_MES_SCHED_PIPE; + memset(&misc_pkt, 0, sizeof(misc_pkt)); misc_pkt.header.type = MES_API_TYPE_SCHEDULER; @@ -513,6 +518,7 @@ static int mes_v12_0_misc_op(struct amdgpu_mes *mes, misc_pkt.wait_reg_mem.reg_offset2 = input->wrm_reg.reg1; break; case MES_MISC_OP_SET_SHADER_DEBUGGER: + pipe = AMDGPU_MES_SCHED_PIPE; misc_pkt.opcode = MESAPI_MISC__SET_SHADER_DEBUGGER; misc_pkt.set_shader_debugger.process_context_addr = input->set_shader_debugger.process_context_addr; @@ -530,11 +536,6 @@ static int mes_v12_0_misc_op(struct amdgpu_mes *mes, return -EINVAL; } - if (mes->adev->enable_uni_mes) - pipe = AMDGPU_MES_KIQ_PIPE; - else - pipe = AMDGPU_MES_SCHED_PIPE; - return mes_v12_0_submit_pkt_and_poll_completion(mes, pipe, &misc_pkt, sizeof(misc_pkt), offsetof(union MESAPI__MISC, api_status)); @@ -608,6 +609,7 @@ static int mes_v12_0_set_hw_resources(struct amdgpu_mes *mes, int pipe) mes_set_hw_res_pkt.disable_mes_log = 1; mes_set_hw_res_pkt.use_different_vmid_compute = 1; mes_set_hw_res_pkt.enable_reg_active_poll = 1; + mes_set_hw_res_pkt.enable_level_process_quantum_check = 1; /* * Keep oversubscribe timer for sdma . When we have unmapped doorbell diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c b/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c index fa479dfa1ec1..739fce4fa8fd 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c +++ b/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c @@ -365,7 +365,7 @@ static void nbio_v2_3_enable_aspm(struct amdgpu_device *adev, data &= ~PCIE_LC_CNTL__LC_PMI_TO_L1_DIS_MASK; } else { - /* Disbale ASPM L1 */ + /* Disable ASPM L1 */ data &= ~PCIE_LC_CNTL__LC_L1_INACTIVITY_MASK; /* Disable ASPM TxL0s */ data &= ~PCIE_LC_CNTL__LC_L0S_INACTIVITY_MASK; diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c index 1251ee38a676..51e470e8d67d 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c @@ -81,6 +81,8 @@ MODULE_FIRMWARE("amdgpu/psp_14_0_4_ta.bin"); /* memory training timeout define */ #define MEM_TRAIN_SEND_MSG_TIMEOUT_US 3000000 +#define regMP1_PUB_SCRATCH0 0x3b10090 + static int psp_v13_0_init_microcode(struct psp_context *psp) { struct amdgpu_device *adev = psp->adev; @@ -807,6 +809,20 @@ static bool psp_v13_0_get_ras_capability(struct psp_context *psp) } } +static bool psp_v13_0_is_aux_sos_load_required(struct psp_context *psp) +{ + struct amdgpu_device *adev = psp->adev; + u32 pmfw_ver; + + if (amdgpu_ip_version(adev, MP0_HWIP, 0) != IP_VERSION(13, 0, 6)) + return false; + + /* load 4e version of sos if pmfw version less than 85.115.0 */ + pmfw_ver = RREG32(regMP1_PUB_SCRATCH0 / 4); + + return (pmfw_ver < 0x557300); +} + static const struct psp_funcs psp_v13_0_funcs = { .init_microcode = psp_v13_0_init_microcode, .wait_for_bootloader = psp_v13_0_wait_for_bootloader_steady_state, @@ -830,6 +846,7 @@ static const struct psp_funcs psp_v13_0_funcs = { .vbflash_stat = psp_v13_0_vbflash_status, .fatal_error_recovery_quirk = psp_v13_0_fatal_error_recovery_quirk, .get_ras_capability = psp_v13_0_get_ras_capability, + .is_aux_sos_load_required = psp_v13_0_is_aux_sos_load_required, }; void psp_v13_0_set_psp_funcs(struct psp_context *psp) diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c index aa637541da58..e65194fe94af 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c @@ -710,7 +710,7 @@ static int sdma_v3_0_gfx_resume(struct amdgpu_device *adev) upper_32_bits(wptr_gpu_addr)); wptr_poll_cntl = RREG32(mmSDMA0_GFX_RB_WPTR_POLL_CNTL + sdma_offsets[i]); if (ring->use_pollmem) { - /*wptr polling is not enogh fast, directly clean the wptr register */ + /*wptr polling is not enough fast, directly clean the wptr register */ WREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[i], 0); wptr_poll_cntl = REG_SET_FIELD(wptr_poll_cntl, SDMA0_GFX_RB_WPTR_POLL_CNTL, diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c index cfd8e183ad50..a8763496aed3 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c @@ -1080,13 +1080,16 @@ static void sdma_v7_0_vm_copy_pte(struct amdgpu_ib *ib, unsigned bytes = count * 8; ib->ptr[ib->length_dw++] = SDMA_PKT_COPY_LINEAR_HEADER_OP(SDMA_OP_COPY) | - SDMA_PKT_COPY_LINEAR_HEADER_SUB_OP(SDMA_SUBOP_COPY_LINEAR); + SDMA_PKT_COPY_LINEAR_HEADER_SUB_OP(SDMA_SUBOP_COPY_LINEAR) | + SDMA_PKT_COPY_LINEAR_HEADER_CPV(1); + ib->ptr[ib->length_dw++] = bytes - 1; ib->ptr[ib->length_dw++] = 0; /* src/dst endian swap */ ib->ptr[ib->length_dw++] = lower_32_bits(src); ib->ptr[ib->length_dw++] = upper_32_bits(src); ib->ptr[ib->length_dw++] = lower_32_bits(pe); ib->ptr[ib->length_dw++] = upper_32_bits(pe); + ib->ptr[ib->length_dw++] = 0; } @@ -1744,7 +1747,7 @@ static void sdma_v7_0_set_buffer_funcs(struct amdgpu_device *adev) } static const struct amdgpu_vm_pte_funcs sdma_v7_0_vm_pte_funcs = { - .copy_pte_num_dw = 7, + .copy_pte_num_dw = 8, .copy_pte = sdma_v7_0_vm_copy_pte, .write_pte = sdma_v7_0_vm_write_pte, .set_pte_pde = sdma_v7_0_vm_set_pte_pde, diff --git a/drivers/gpu/drm/amd/amdgpu/smuio_v9_0.c b/drivers/gpu/drm/amd/amdgpu/smuio_v9_0.c index e4e30b9d481b..c04fdd2d5b38 100644 --- a/drivers/gpu/drm/amd/amdgpu/smuio_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/smuio_v9_0.c @@ -60,7 +60,7 @@ static void smuio_v9_0_get_clock_gating_state(struct amdgpu_device *adev, u64 *f { u32 data; - /* CGTT_ROM_CLK_CTRL0 is not availabe for APUs */ + /* CGTT_ROM_CLK_CTRL0 is not available for APUs */ if (adev->flags & AMD_IS_APU) return; diff --git a/drivers/gpu/drm/amd/amdgpu/soc24.c b/drivers/gpu/drm/amd/amdgpu/soc24.c index b0c3678cfb31..fd4c3d4f8387 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc24.c +++ b/drivers/gpu/drm/amd/amdgpu/soc24.c @@ -250,13 +250,6 @@ static void soc24_program_aspm(struct amdgpu_device *adev) adev->nbio.funcs->program_aspm(adev); } -static void soc24_enable_doorbell_aperture(struct amdgpu_device *adev, - bool enable) -{ - adev->nbio.funcs->enable_doorbell_aperture(adev, enable); - adev->nbio.funcs->enable_doorbell_selfring_aperture(adev, enable); -} - const struct amdgpu_ip_block_version soc24_common_ip_block = { .type = AMD_IP_BLOCK_TYPE_COMMON, .major = 1, @@ -454,6 +447,11 @@ static int soc24_common_late_init(void *handle) if (amdgpu_sriov_vf(adev)) xgpu_nv_mailbox_get_irq(adev); + /* Enable selfring doorbell aperture late because doorbell BAR + * aperture will change if resize BAR successfully in gmc sw_init. + */ + adev->nbio.funcs->enable_doorbell_selfring_aperture(adev, true); + return 0; } @@ -491,7 +489,7 @@ static int soc24_common_hw_init(void *handle) adev->df.funcs->hw_init(adev); /* enable the doorbell aperture */ - soc24_enable_doorbell_aperture(adev, true); + adev->nbio.funcs->enable_doorbell_aperture(adev, true); return 0; } @@ -500,8 +498,13 @@ static int soc24_common_hw_fini(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; - /* disable the doorbell aperture */ - soc24_enable_doorbell_aperture(adev, false); + /* Disable the doorbell aperture and selfring doorbell aperture + * separately in hw_fini because soc21_enable_doorbell_aperture + * has been removed and there is no need to delay disabling + * selfring doorbell. + */ + adev->nbio.funcs->enable_doorbell_aperture(adev, false); + adev->nbio.funcs->enable_doorbell_selfring_aperture(adev, false); if (amdgpu_sriov_vf(adev)) xgpu_nv_mailbox_put_irq(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c index b1fd226b7efb..9d4f5352a62c 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c @@ -1395,170 +1395,6 @@ static void vcn_v4_0_5_unified_ring_set_wptr(struct amdgpu_ring *ring) } } -static int vcn_v4_0_5_limit_sched(struct amdgpu_cs_parser *p, - struct amdgpu_job *job) -{ - struct drm_gpu_scheduler **scheds; - - /* The create msg must be in the first IB submitted */ - if (atomic_read(&job->base.entity->fence_seq)) - return -EINVAL; - - /* if VCN0 is harvested, we can't support AV1 */ - if (p->adev->vcn.harvest_config & AMDGPU_VCN_HARVEST_VCN0) - return -EINVAL; - - scheds = p->adev->gpu_sched[AMDGPU_HW_IP_VCN_ENC] - [AMDGPU_RING_PRIO_0].sched; - drm_sched_entity_modify_sched(job->base.entity, scheds, 1); - return 0; -} - -static int vcn_v4_0_5_dec_msg(struct amdgpu_cs_parser *p, struct amdgpu_job *job, - uint64_t addr) -{ - struct ttm_operation_ctx ctx = { false, false }; - struct amdgpu_bo_va_mapping *map; - uint32_t *msg, num_buffers; - struct amdgpu_bo *bo; - uint64_t start, end; - unsigned int i; - void *ptr; - int r; - - addr &= AMDGPU_GMC_HOLE_MASK; - r = amdgpu_cs_find_mapping(p, addr, &bo, &map); - if (r) { - DRM_ERROR("Can't find BO for addr 0x%08llx\n", addr); - return r; - } - - start = map->start * AMDGPU_GPU_PAGE_SIZE; - end = (map->last + 1) * AMDGPU_GPU_PAGE_SIZE; - if (addr & 0x7) { - DRM_ERROR("VCN messages must be 8 byte aligned!\n"); - return -EINVAL; - } - - bo->flags |= AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED; - amdgpu_bo_placement_from_domain(bo, bo->allowed_domains); - r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx); - if (r) { - DRM_ERROR("Failed validating the VCN message BO (%d)!\n", r); - return r; - } - - r = amdgpu_bo_kmap(bo, &ptr); - if (r) { - DRM_ERROR("Failed mapping the VCN message (%d)!\n", r); - return r; - } - - msg = ptr + addr - start; - - /* Check length */ - if (msg[1] > end - addr) { - r = -EINVAL; - goto out; - } - - if (msg[3] != RDECODE_MSG_CREATE) - goto out; - - num_buffers = msg[2]; - for (i = 0, msg = &msg[6]; i < num_buffers; ++i, msg += 4) { - uint32_t offset, size, *create; - - if (msg[0] != RDECODE_MESSAGE_CREATE) - continue; - - offset = msg[1]; - size = msg[2]; - - if (offset + size > end) { - r = -EINVAL; - goto out; - } - - create = ptr + addr + offset - start; - - /* H264, HEVC and VP9 can run on any instance */ - if (create[0] == 0x7 || create[0] == 0x10 || create[0] == 0x11) - continue; - - r = vcn_v4_0_5_limit_sched(p, job); - if (r) - goto out; - } - -out: - amdgpu_bo_kunmap(bo); - return r; -} - -#define RADEON_VCN_ENGINE_TYPE_ENCODE (0x00000002) -#define RADEON_VCN_ENGINE_TYPE_DECODE (0x00000003) - -#define RADEON_VCN_ENGINE_INFO (0x30000001) -#define RADEON_VCN_ENGINE_INFO_MAX_OFFSET 16 - -#define RENCODE_ENCODE_STANDARD_AV1 2 -#define RENCODE_IB_PARAM_SESSION_INIT 0x00000003 -#define RENCODE_IB_PARAM_SESSION_INIT_MAX_OFFSET 64 - -/* return the offset in ib if id is found, -1 otherwise - * to speed up the searching we only search upto max_offset - */ -static int vcn_v4_0_5_enc_find_ib_param(struct amdgpu_ib *ib, uint32_t id, int max_offset) -{ - int i; - - for (i = 0; i < ib->length_dw && i < max_offset && ib->ptr[i] >= 8; i += ib->ptr[i]/4) { - if (ib->ptr[i + 1] == id) - return i; - } - return -1; -} - -static int vcn_v4_0_5_ring_patch_cs_in_place(struct amdgpu_cs_parser *p, - struct amdgpu_job *job, - struct amdgpu_ib *ib) -{ - struct amdgpu_ring *ring = amdgpu_job_ring(job); - struct amdgpu_vcn_decode_buffer *decode_buffer; - uint64_t addr; - uint32_t val; - int idx; - - /* The first instance can decode anything */ - if (!ring->me) - return 0; - - /* RADEON_VCN_ENGINE_INFO is at the top of ib block */ - idx = vcn_v4_0_5_enc_find_ib_param(ib, RADEON_VCN_ENGINE_INFO, - RADEON_VCN_ENGINE_INFO_MAX_OFFSET); - if (idx < 0) /* engine info is missing */ - return 0; - - val = amdgpu_ib_get_value(ib, idx + 2); /* RADEON_VCN_ENGINE_TYPE */ - if (val == RADEON_VCN_ENGINE_TYPE_DECODE) { - decode_buffer = (struct amdgpu_vcn_decode_buffer *)&ib->ptr[idx + 6]; - - if (!(decode_buffer->valid_buf_flag & 0x1)) - return 0; - - addr = ((u64)decode_buffer->msg_buffer_address_hi) << 32 | - decode_buffer->msg_buffer_address_lo; - return vcn_v4_0_5_dec_msg(p, job, addr); - } else if (val == RADEON_VCN_ENGINE_TYPE_ENCODE) { - idx = vcn_v4_0_5_enc_find_ib_param(ib, RENCODE_IB_PARAM_SESSION_INIT, - RENCODE_IB_PARAM_SESSION_INIT_MAX_OFFSET); - if (idx >= 0 && ib->ptr[idx + 2] == RENCODE_ENCODE_STANDARD_AV1) - return vcn_v4_0_5_limit_sched(p, job); - } - return 0; -} - static const struct amdgpu_ring_funcs vcn_v4_0_5_unified_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_ENC, .align_mask = 0x3f, @@ -1566,7 +1402,6 @@ static const struct amdgpu_ring_funcs vcn_v4_0_5_unified_ring_vm_funcs = { .get_rptr = vcn_v4_0_5_unified_ring_get_rptr, .get_wptr = vcn_v4_0_5_unified_ring_get_wptr, .set_wptr = vcn_v4_0_5_unified_ring_set_wptr, - .patch_cs_in_place = vcn_v4_0_5_ring_patch_cs_in_place, .emit_frame_size = SOC15_FLUSH_GPU_TLB_NUM_WREG * 3 + SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 4 + diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c index 71b465f8d83e..648f40091aa3 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -3540,6 +3540,30 @@ int debug_refresh_runlist(struct device_queue_manager *dqm) return debug_map_and_unlock(dqm); } +bool kfd_dqm_is_queue_in_process(struct device_queue_manager *dqm, + struct qcm_process_device *qpd, + int doorbell_off, u32 *queue_format) +{ + struct queue *q; + bool r = false; + + if (!queue_format) + return r; + + dqm_lock(dqm); + + list_for_each_entry(q, &qpd->queues_list, list) { + if (q->properties.doorbell_off == doorbell_off) { + *queue_format = q->properties.format; + r = true; + goto out; + } + } + +out: + dqm_unlock(dqm); + return r; +} #if defined(CONFIG_DEBUG_FS) static void seq_reg_dump(struct seq_file *m, diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h index 08b40826ad1e..09ab36f8e8c6 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h @@ -324,6 +324,9 @@ void set_queue_snapshot_entry(struct queue *q, int debug_lock_and_unmap(struct device_queue_manager *dqm); int debug_map_and_unlock(struct device_queue_manager *dqm); int debug_refresh_runlist(struct device_queue_manager *dqm); +bool kfd_dqm_is_queue_in_process(struct device_queue_manager *dqm, + struct qcm_process_device *qpd, + int doorbell_off, u32 *queue_format); static inline unsigned int get_sh_mem_bases_32(struct kfd_process_device *pdd) { diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v10.c b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v10.c index bb8cbfc39b90..37b69fe0ede3 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v10.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v10.c @@ -306,23 +306,8 @@ static void event_interrupt_wq_v10(struct kfd_node *dev, client_id == SOC15_IH_CLIENTID_UTCL2) { struct kfd_vm_fault_info info = {0}; uint16_t ring_id = SOC15_RING_ID_FROM_IH_ENTRY(ih_ring_entry); - uint32_t node_id = SOC15_NODEID_FROM_IH_ENTRY(ih_ring_entry); - uint32_t vmid_type = SOC15_VMID_TYPE_FROM_IH_ENTRY(ih_ring_entry); - int hub_inst = 0; struct kfd_hsa_memory_exception_data exception_data; - /* gfxhub */ - if (!vmid_type && dev->adev->gfx.funcs->ih_node_to_logical_xcc) { - hub_inst = dev->adev->gfx.funcs->ih_node_to_logical_xcc(dev->adev, - node_id); - if (hub_inst < 0) - hub_inst = 0; - } - - /* mmhub */ - if (vmid_type && client_id == SOC15_IH_CLIENTID_VMC) - hub_inst = node_id / 4; - info.vmid = vmid; info.mc_id = client_id; info.page_addr = ih_ring_entry[4] | diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v12.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v12.c index d163d92a692f..2b72d5b4949b 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v12.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v12.c @@ -341,6 +341,10 @@ static void update_mqd_sdma(struct mqd_manager *mm, void *mqd, m->sdmax_rlcx_doorbell_offset = q->doorbell_off << SDMA0_QUEUE0_DOORBELL_OFFSET__OFFSET__SHIFT; + m->sdmax_rlcx_sched_cntl = (amdgpu_sdma_phase_quantum + << SDMA0_QUEUE0_SCHEDULE_CNTL__CONTEXT_QUANTUM__SHIFT) + & SDMA0_QUEUE0_SCHEDULE_CNTL__CONTEXT_QUANTUM_MASK; + m->sdma_engine_id = q->sdma_engine_id; m->sdma_queue_id = q->sdma_queue_id; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c index a902950cc060..d07acf1b2f93 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c @@ -270,6 +270,11 @@ static int kfd_get_cu_occupancy(struct attribute *attr, char *buffer) struct kfd_node *dev = NULL; struct kfd_process *proc = NULL; struct kfd_process_device *pdd = NULL; + int i; + struct kfd_cu_occupancy cu_occupancy[AMDGPU_MAX_QUEUES]; + u32 queue_format; + + memset(cu_occupancy, 0x0, sizeof(cu_occupancy)); pdd = container_of(attr, struct kfd_process_device, attr_cu_occupancy); dev = pdd->dev; @@ -287,8 +292,29 @@ static int kfd_get_cu_occupancy(struct attribute *attr, char *buffer) /* Collect wave count from device if it supports */ wave_cnt = 0; max_waves_per_cu = 0; - dev->kfd2kgd->get_cu_occupancy(dev->adev, proc->pasid, &wave_cnt, - &max_waves_per_cu, 0); + + /* + * For GFX 9.4.3, fetch the CU occupancy from the first XCC in the partition. + * For AQL queues, because of cooperative dispatch we multiply the wave count + * by number of XCCs in the partition to get the total wave counts across all + * XCCs in the partition. + * For PM4 queues, there is no cooperative dispatch so wave_cnt stay as it is. + */ + dev->kfd2kgd->get_cu_occupancy(dev->adev, cu_occupancy, + &max_waves_per_cu, ffs(dev->xcc_mask) - 1); + + for (i = 0; i < AMDGPU_MAX_QUEUES; i++) { + if (cu_occupancy[i].wave_cnt != 0 && + kfd_dqm_is_queue_in_process(dev->dqm, &pdd->qpd, + cu_occupancy[i].doorbell_off, + &queue_format)) { + if (unlikely(queue_format == KFD_QUEUE_FORMAT_PM4)) + wave_cnt += cu_occupancy[i].wave_cnt; + else + wave_cnt += (NUM_XCC(dev->xcc_mask) * + cu_occupancy[i].wave_cnt); + } + } /* Translate wave count to number of compute units */ cu_cnt = (wave_cnt + (max_waves_per_cu - 1)) / max_waves_per_cu; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c index b439d4d0bd84..01b960b15274 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c @@ -517,7 +517,6 @@ int pqm_destroy_queue(struct process_queue_manager *pqm, unsigned int qid) if (retval) goto err_destroy_queue; - kfd_procfs_del_queue(pqn->q); dqm = pqn->q->device->dqm; retval = dqm->ops.destroy_queue(dqm, &pdd->qpd, pqn->q); if (retval) { @@ -527,6 +526,7 @@ int pqm_destroy_queue(struct process_queue_manager *pqm, unsigned int qid) if (retval != -ETIME) goto err_destroy_queue; } + kfd_procfs_del_queue(pqn->q); kfd_queue_release_buffers(pdd, &pqn->q->properties); pqm_clean_queue_resource(pqm, pqn); uninit_queue(pqn->q); 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 0cff66735cfe..60c617fcc97e 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; @@ -808,6 +814,20 @@ static void dmub_hpd_callback(struct amdgpu_device *adev, } /** + * dmub_hpd_sense_callback - DMUB HPD sense processing callback. + * @adev: amdgpu_device pointer + * @notify: dmub notification structure + * + * HPD sense changes can occur during low power states and need to be + * notified from firmware to driver. + */ +static void dmub_hpd_sense_callback(struct amdgpu_device *adev, + struct dmub_notification *notify) +{ + DRM_DEBUG_DRIVER("DMUB HPD SENSE callback.\n"); +} + +/** * register_dmub_notify_callback - Sets callback for DMUB notify * @adev: amdgpu_device pointer * @type: Type of dmub notification @@ -1757,25 +1777,41 @@ static struct dml2_soc_bb *dm_dmub_get_vbios_bounding_box(struct amdgpu_device * static enum dmub_ips_disable_type dm_get_default_ips_mode( struct amdgpu_device *adev) { - /* - * On DCN35 systems with Z8 enabled, it's possible for IPS2 + Z8 to - * cause a hard hang. A fix exists for newer PMFW. - * - * As a workaround, for non-fixed PMFW, force IPS1+RCG as the deepest - * IPS state in all cases, except for s0ix and all displays off (DPMS), - * where IPS2 is allowed. - * - * When checking pmfw version, use the major and minor only. - */ - if (amdgpu_ip_version(adev, DCE_HWIP, 0) == IP_VERSION(3, 5, 0) && - (adev->pm.fw_version & 0x00FFFF00) < 0x005D6300) - return DMUB_IPS_RCG_IN_ACTIVE_IPS2_IN_OFF; + enum dmub_ips_disable_type ret = DMUB_IPS_ENABLE; - if (amdgpu_ip_version(adev, DCE_HWIP, 0) >= IP_VERSION(3, 5, 0)) - return DMUB_IPS_ENABLE; + switch (amdgpu_ip_version(adev, DCE_HWIP, 0)) { + case IP_VERSION(3, 5, 0): + /* + * On DCN35 systems with Z8 enabled, it's possible for IPS2 + Z8 to + * cause a hard hang. A fix exists for newer PMFW. + * + * As a workaround, for non-fixed PMFW, force IPS1+RCG as the deepest + * IPS state in all cases, except for s0ix and all displays off (DPMS), + * where IPS2 is allowed. + * + * When checking pmfw version, use the major and minor only. + */ + if ((adev->pm.fw_version & 0x00FFFF00) < 0x005D6300) + ret = DMUB_IPS_RCG_IN_ACTIVE_IPS2_IN_OFF; + else if (amdgpu_ip_version(adev, GC_HWIP, 0) > IP_VERSION(11, 5, 0)) + /* + * Other ASICs with DCN35 that have residency issues with + * IPS2 in idle. + * We want them to use IPS2 only in display off cases. + */ + ret = DMUB_IPS_RCG_IN_ACTIVE_IPS2_IN_OFF; + break; + case IP_VERSION(3, 5, 1): + ret = DMUB_IPS_RCG_IN_ACTIVE_IPS2_IN_OFF; + break; + default: + /* ASICs older than DCN35 do not have IPSs */ + if (amdgpu_ip_version(adev, DCE_HWIP, 0) < IP_VERSION(3, 5, 0)) + ret = DMUB_IPS_DISABLE_ALL; + break; + } - /* ASICs older than DCN35 do not have IPSs */ - return DMUB_IPS_DISABLE_ALL; + return ret; } static int amdgpu_dm_init(struct amdgpu_device *adev) @@ -1996,7 +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) { @@ -3808,6 +3845,12 @@ static int register_hpd_handlers(struct amdgpu_device *adev) DRM_ERROR("amdgpu: fail to register dmub hpd callback"); return -EINVAL; } + + if (!register_dmub_notify_callback(adev, DMUB_NOTIFICATION_HPD_SENSE_NOTIFY, + dmub_hpd_sense_callback, true)) { + DRM_ERROR("amdgpu: fail to register dmub hpd sense callback"); + return -EINVAL; + } } list_for_each_entry(connector, @@ -4449,6 +4492,7 @@ static int amdgpu_dm_mode_config_init(struct amdgpu_device *adev) #define AMDGPU_DM_DEFAULT_MIN_BACKLIGHT 12 #define AMDGPU_DM_DEFAULT_MAX_BACKLIGHT 255 +#define AMDGPU_DM_MIN_SPREAD ((AMDGPU_DM_DEFAULT_MAX_BACKLIGHT - AMDGPU_DM_DEFAULT_MIN_BACKLIGHT) / 2) #define AUX_BL_DEFAULT_TRANSITION_TIME_MS 50 static void amdgpu_dm_update_backlight_caps(struct amdgpu_display_manager *dm, @@ -4463,6 +4507,21 @@ static void amdgpu_dm_update_backlight_caps(struct amdgpu_display_manager *dm, return; amdgpu_acpi_get_backlight_caps(&caps); + + /* validate the firmware value is sane */ + if (caps.caps_valid) { + int spread = caps.max_input_signal - caps.min_input_signal; + + if (caps.max_input_signal > AMDGPU_DM_DEFAULT_MAX_BACKLIGHT || + caps.min_input_signal < 0 || + spread > AMDGPU_DM_DEFAULT_MAX_BACKLIGHT || + spread < AMDGPU_DM_MIN_SPREAD) { + DRM_DEBUG_KMS("DM: Invalid backlight caps: min=%d, max=%d\n", + caps.min_input_signal, caps.max_input_signal); + caps.caps_valid = false; + } + } + if (caps.caps_valid) { dm->backlight_caps[bl_idx].caps_valid = true; if (caps.aux_support) @@ -6683,12 +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.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h index 2d7755e2b6c3..15d4690c74d6 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h @@ -50,7 +50,7 @@ #define AMDGPU_DM_MAX_NUM_EDP 2 -#define AMDGPU_DMUB_NOTIFICATION_MAX 6 +#define AMDGPU_DMUB_NOTIFICATION_MAX 7 #define HDMI_AMD_VENDOR_SPECIFIC_DATA_BLOCK_IEEE_REGISTRATION_ID 0x00001A #define AMD_VSDB_VERSION_3_FEATURECAP_REPLAYMODE 0x40 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 50109d13d967..069e0195e50a 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 c0c61c03984c..a08e8a0b696c 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; @@ -1147,7 +1156,7 @@ static int compute_mst_dsc_configs_for_link(struct drm_atomic_state *state, params[count].num_slices_v = aconnector->dsc_settings.dsc_num_slices_v; params[count].bpp_overwrite = aconnector->dsc_settings.dsc_bits_per_pixel; params[count].compression_possible = stream->sink->dsc_caps.dsc_dec_caps.is_dsc_supported; - dc_dsc_get_policy_for_timing(params[count].timing, 0, &dsc_policy); + dc_dsc_get_policy_for_timing(params[count].timing, 0, &dsc_policy, dc_link_get_highest_encoding_format(stream->link)); if (!dc_dsc_compute_bandwidth_range( stream->sink->ctx->dc->res_pool->dscs[0], stream->sink->ctx->dc->debug.dsc_min_slice_height_override, @@ -1681,7 +1690,7 @@ static bool is_dsc_common_config_possible(struct dc_stream_state *stream, { struct dc_dsc_policy dsc_policy = {0}; - dc_dsc_get_policy_for_timing(&stream->timing, 0, &dsc_policy); + dc_dsc_get_policy_for_timing(&stream->timing, 0, &dsc_policy, dc_link_get_highest_encoding_format(stream->link)); dc_dsc_compute_bandwidth_range(stream->sink->ctx->dc->res_pool->dscs[0], stream->sink->ctx->dc->debug.dsc_min_slice_height_override, dsc_policy.min_target_bpp * 16, diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c index 25f63b2e7a8e..495e3cd70426 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c @@ -961,6 +961,7 @@ static int amdgpu_dm_plane_helper_prepare_fb(struct drm_plane *plane, else domain = AMDGPU_GEM_DOMAIN_VRAM; + rbo->flags |= AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS; r = amdgpu_bo_pin(rbo, domain); if (unlikely(r != 0)) { if (r != -ERESTARTSYS) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_wb.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_wb.c index 08c494a7a21b..0d5fefb0f591 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_wb.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_wb.c @@ -114,6 +114,7 @@ static int amdgpu_dm_wb_prepare_job(struct drm_writeback_connector *wb_connector domain = amdgpu_display_supported_domains(adev, rbo->flags); + rbo->flags |= AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS; r = amdgpu_bo_pin(rbo, domain); if (unlikely(r != 0)) { if (r != -ERESTARTSYS) diff --git a/drivers/gpu/drm/amd/display/dc/basics/dce_calcs.c b/drivers/gpu/drm/amd/display/dc/basics/dce_calcs.c index e47e9db062f4..681799468487 100644 --- a/drivers/gpu/drm/amd/display/dc/basics/dce_calcs.c +++ b/drivers/gpu/drm/amd/display/dc/basics/dce_calcs.c @@ -569,7 +569,7 @@ static void calculate_bandwidth( break; } data->lb_partitions[i] = bw_floor2(bw_div(data->lb_size_per_component[i], data->lb_line_pitch), bw_int_to_fixed(1)); - /*clamp the partitions to the maxium number supported by the lb*/ + /* clamp the partitions to the maximum number supported by the lb */ if ((surface_type[i] != bw_def_graphics || dceip->graphics_lb_nodownscaling_multi_line_prefetching == 1)) { data->lb_partitions_max[i] = bw_int_to_fixed(10); } diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c index f770828df149..0e243f4344d0 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c @@ -59,6 +59,7 @@ int clk_mgr_helper_get_active_display_cnt( display_count = 0; for (i = 0; i < context->stream_count; i++) { const struct dc_stream_state *stream = context->streams[i]; + const struct dc_stream_status *stream_status = &context->stream_status[i]; /* Don't count SubVP phantom pipes as part of active * display count @@ -66,13 +67,7 @@ int clk_mgr_helper_get_active_display_cnt( if (dc_state_get_stream_subvp_type(context, stream) == SUBVP_PHANTOM) continue; - /* - * Only notify active stream or virtual stream. - * Need to notify virtual stream to work around - * headless case. HPD does not fire when system is in - * S0i2. - */ - if (!stream->dpms_off || stream->signal == SIGNAL_TYPE_VIRTUAL) + if (!stream->dpms_off || (stream_status && stream_status->plane_count)) display_count++; } diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c index 97164b5585a8..b46a3afe48ca 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c @@ -1222,6 +1222,12 @@ void dcn35_clk_mgr_construct( ctx->dc->debug.disable_dpp_power_gate = false; ctx->dc->debug.disable_hubp_power_gate = false; ctx->dc->debug.disable_dsc_power_gate = false; + + /* Disable dynamic IPS2 in older PMFW (93.12) for Z8 interop. */ + if (ctx->dc->config.disable_ips == DMUB_IPS_ENABLE && + ctx->dce_version == DCN_VERSION_3_5 && + ((clk_mgr->base.smu_ver & 0x00FFFFFF) <= 0x005d0c00)) + ctx->dc->config.disable_ips = DMUB_IPS_RCG_IN_ACTIVE_IPS2_IN_OFF; } else { /*let's reset the config control flag*/ ctx->dc->config.disable_ips = DMUB_IPS_DISABLE_ALL; /*pmfw not support it, disable it all*/ diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index ae788154896c..5c39390ecbd5 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -1767,7 +1767,7 @@ bool dc_validate_boot_timing(const struct dc *dc, if (crtc_timing->pix_clk_100hz != pix_clk_100hz) return false; - if (!se->funcs->dp_get_pixel_format) + if (!se || !se->funcs->dp_get_pixel_format) return false; if (!se->funcs->dp_get_pixel_format( @@ -2376,7 +2376,7 @@ static bool is_surface_in_context( return false; } -static enum surface_update_type get_plane_info_update_type(const struct dc_surface_update *u) +static enum surface_update_type get_plane_info_update_type(const struct dc *dc, const struct dc_surface_update *u) { union surface_update_flags *update_flags = &u->surface->update_flags; enum surface_update_type update_type = UPDATE_TYPE_FAST; @@ -2455,7 +2455,7 @@ static enum surface_update_type get_plane_info_update_type(const struct dc_surfa /* todo: below are HW dependent, we should add a hook to * DCE/N resource and validated there. */ - if (u->plane_info->tiling_info.gfx9.swizzle != DC_SW_LINEAR) { + if (!dc->debug.skip_full_updated_if_possible) { /* swizzled mode requires RQ to be setup properly, * thus need to run DML to calculate RQ settings */ @@ -2547,7 +2547,7 @@ static enum surface_update_type det_surface_update(const struct dc *dc, update_flags->raw = 0; // Reset all flags - type = get_plane_info_update_type(u); + type = get_plane_info_update_type(dc, u); elevate_update_type(&overall_type, type); type = get_scaling_info_update_type(dc, u); @@ -2596,6 +2596,12 @@ static enum surface_update_type det_surface_update(const struct dc *dc, elevate_update_type(&overall_type, UPDATE_TYPE_MED); } + if (u->sdr_white_level_nits) + if (u->sdr_white_level_nits != u->surface->sdr_white_level_nits) { + update_flags->bits.sdr_white_level_nits = 1; + elevate_update_type(&overall_type, UPDATE_TYPE_FULL); + } + if (u->cm2_params) { if ((u->cm2_params->component_settings.shaper_3dlut_setting != u->surface->mcm_shaper_3dlut_setting) @@ -2876,6 +2882,10 @@ static void copy_surface_update_to_plane( surface->hdr_mult = srf_update->hdr_mult; + if (srf_update->sdr_white_level_nits) + surface->sdr_white_level_nits = + srf_update->sdr_white_level_nits; + if (srf_update->blend_tf) memcpy(&surface->blend_tf, srf_update->blend_tf, sizeof(surface->blend_tf)); @@ -4679,6 +4689,8 @@ static bool full_update_required(struct dc *dc, srf_updates[i].scaling_info || (srf_updates[i].hdr_mult.value && srf_updates[i].hdr_mult.value != srf_updates->surface->hdr_mult.value) || + (srf_updates[i].sdr_white_level_nits && + srf_updates[i].sdr_white_level_nits != srf_updates->surface->sdr_white_level_nits) || srf_updates[i].in_transfer_func || srf_updates[i].func_shaper || srf_updates[i].lut3d_func || @@ -5744,6 +5756,27 @@ enum dc_status dc_process_dmub_set_mst_slots(const struct dc *dc, } /** + * dc_process_dmub_dpia_set_tps_notification - Submits tps notification + * + * @dc: [in] dc structure + * @link_index: [in] link index + * @tps: [in] request tps + * + * Submits set_tps_notification command to dmub via inbox message + */ +void dc_process_dmub_dpia_set_tps_notification(const struct dc *dc, uint32_t link_index, uint8_t tps) +{ + union dmub_rb_cmd cmd = {0}; + + cmd.set_tps_notification.header.type = DMUB_CMD__DPIA; + cmd.set_tps_notification.header.sub_type = DMUB_CMD__DPIA_SET_TPS_NOTIFICATION; + cmd.set_tps_notification.tps_notification.instance = dc->links[link_index]->ddc_hw_inst; + cmd.set_tps_notification.tps_notification.tps = tps; + + dc_wake_and_execute_dmub_cmd(dc->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT); +} + +/** * dc_process_dmub_dpia_hpd_int_enable - Submits DPIA DPD interruption * * @dc: [in] dc structure diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index 4c94dd38be4b..3992ad73165b 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -55,7 +55,7 @@ struct aux_payload; struct set_config_cmd_payload; struct dmub_notification; -#define DC_VER "3.2.299" +#define DC_VER "3.2.301" #define MAX_SURFACES 3 #define MAX_PLANES 6 @@ -462,6 +462,7 @@ struct dc_config { bool support_edp0_on_dp1; unsigned int enable_fpo_flicker_detection; bool disable_hbr_audio_dp2; + bool consolidated_dpia_dp_lt; }; enum visual_confirm { @@ -762,7 +763,8 @@ union dpia_debug_options { uint32_t disable_mst_dsc_work_around:1; /* bit 3 */ uint32_t enable_force_tbt3_work_around:1; /* bit 4 */ uint32_t disable_usb4_pm_support:1; /* bit 5 */ - uint32_t reserved:26; + uint32_t enable_consolidated_dpia_dp_lt:1; /* bit 6 */ + uint32_t reserved:25; } bits; uint32_t raw; }; @@ -1056,6 +1058,9 @@ struct dc_debug_options { unsigned int force_lls; bool notify_dpia_hr_bw; bool enable_ips_visual_confirm; + unsigned int sharpen_policy; + unsigned int scale_to_sharpness_policy; + bool skip_full_updated_if_possible; }; @@ -1269,6 +1274,7 @@ union surface_update_flags { uint32_t tmz_changed:1; uint32_t mcm_transfer_function_enable_change:1; /* disable or enable MCM transfer func */ uint32_t full_update:1; + uint32_t sdr_white_level_nits:1; } bits; uint32_t raw; @@ -1351,6 +1357,7 @@ struct dc_plane_state { bool adaptive_sharpness_en; int sharpness_level; enum linear_light_scaling linear_light_scaling; + unsigned int sdr_white_level_nits; }; struct dc_plane_info { @@ -1508,6 +1515,7 @@ struct dc_surface_update { */ struct dc_cm2_parameters *cm2_params; const struct dc_csc_transform *cursor_csc_color_matrix; + unsigned int sdr_white_level_nits; }; /* @@ -2520,6 +2528,8 @@ enum dc_status dc_process_dmub_set_mst_slots(const struct dc *dc, uint8_t mst_alloc_slots, uint8_t *mst_slots_in_use); +void dc_process_dmub_dpia_set_tps_notification(const struct dc *dc, uint32_t link_index, uint8_t tps); + void dc_process_dmub_dpia_hpd_int_enable(const struct dc *dc, uint32_t hpd_int_enable); diff --git a/drivers/gpu/drm/amd/display/dc/dc_dp_types.h b/drivers/gpu/drm/amd/display/dc/dc_dp_types.h index 519c3df78ee5..41bd95e9177a 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_dp_types.h +++ b/drivers/gpu/drm/amd/display/dc/dc_dp_types.h @@ -969,6 +969,14 @@ union dp_sink_video_fallback_formats { uint8_t raw; }; +union dpcd_max_uncompressed_pixel_rate_cap { + struct { + uint16_t max_uncompressed_pixel_rate_cap :15; + uint16_t valid :1; + } bits; + uint8_t raw[2]; +}; + union dp_fec_capability1 { struct { uint8_t AGGREGATED_ERROR_COUNTERS_CAPABLE :1; @@ -1170,6 +1178,7 @@ struct dpcd_caps { struct dc_lttpr_caps lttpr_caps; struct adaptive_sync_caps adaptive_sync_caps; struct dpcd_usb4_dp_tunneling_info usb4_dp_tun_info; + union dpcd_max_uncompressed_pixel_rate_cap max_uncompressed_pixel_rate_cap; union dp_128b_132b_supported_link_rates dp_128b_132b_supported_link_rates; union dp_main_line_channel_coding_cap channel_coding_cap; @@ -1340,6 +1349,9 @@ struct dp_trace { #ifndef DP_CABLE_ATTRIBUTES_UPDATED_BY_DPTX #define DP_CABLE_ATTRIBUTES_UPDATED_BY_DPTX 0x110 #endif +#ifndef DPCD_MAX_UNCOMPRESSED_PIXEL_RATE_CAP +#define DPCD_MAX_UNCOMPRESSED_PIXEL_RATE_CAP 0x221c +#endif #ifndef DP_REPEATER_CONFIGURATION_AND_STATUS_SIZE #define DP_REPEATER_CONFIGURATION_AND_STATUS_SIZE 0x50 #endif diff --git a/drivers/gpu/drm/amd/display/dc/dc_dsc.h b/drivers/gpu/drm/amd/display/dc/dc_dsc.h index fe3078b8789e..9014c2409817 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_dsc.h +++ b/drivers/gpu/drm/amd/display/dc/dc_dsc.h @@ -59,6 +59,7 @@ struct dc_dsc_config_options { uint32_t max_target_bpp_limit_override_x16; uint32_t slice_height_granularity; uint32_t dsc_force_odm_hslice_override; + bool force_dsc_when_not_needed; }; bool dc_dsc_parse_dsc_dpcd(const struct dc *dc, @@ -100,7 +101,8 @@ uint32_t dc_dsc_stream_bandwidth_overhead_in_kbps( */ void dc_dsc_get_policy_for_timing(const struct dc_crtc_timing *timing, uint32_t max_target_bpp_limit_override_x16, - struct dc_dsc_policy *policy); + struct dc_dsc_policy *policy, + const enum dc_link_encoding_format link_encoding); void dc_dsc_policy_set_max_target_bpp_limit(uint32_t limit); diff --git a/drivers/gpu/drm/amd/display/dc/dc_spl_translate.c b/drivers/gpu/drm/amd/display/dc/dc_spl_translate.c index cd6de93eb91c..603552dbd771 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_spl_translate.c +++ b/drivers/gpu/drm/amd/display/dc/dc_spl_translate.c @@ -186,19 +186,17 @@ void translate_SPL_in_params_from_pipe_ctx(struct pipe_ctx *pipe_ctx, struct spl spl_in->h_active = pipe_ctx->plane_res.scl_data.h_active; spl_in->v_active = pipe_ctx->plane_res.scl_data.v_active; + + spl_in->debug.sharpen_policy = (enum sharpen_policy)pipe_ctx->stream->ctx->dc->debug.sharpen_policy; + spl_in->debug.scale_to_sharpness_policy = + (enum scale_to_sharpness_policy)pipe_ctx->stream->ctx->dc->debug.scale_to_sharpness_policy; + /* Check if it is stream is in fullscreen and if its HDR. * Use this to determine sharpness levels */ spl_in->is_fullscreen = dm_helpers_is_fullscreen(pipe_ctx->stream->ctx, pipe_ctx->stream); spl_in->is_hdr_on = dm_helpers_is_hdr_on(pipe_ctx->stream->ctx, pipe_ctx->stream); - spl_in->hdr_multx100 = 0; - if (spl_in->is_hdr_on) { - spl_in->hdr_multx100 = (uint32_t)dc_fixpt_floor(dc_fixpt_mul(plane_state->hdr_mult, - dc_fixpt_from_int(100))); - /* Disable sharpness for HDR Mult > 6.0 */ - if (spl_in->hdr_multx100 > 600) - spl_in->adaptive_sharpness.enable = false; - } + spl_in->sdr_white_level_nits = plane_state->sdr_white_level_nits; } /// @brief Translate SPL output parameters to pipe context diff --git a/drivers/gpu/drm/amd/display/dc/dc_types.h b/drivers/gpu/drm/amd/display/dc/dc_types.h index fd6dca735714..6d7989b751e2 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/dml/dcn20/display_rq_dlg_calc_20.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.c index e7019c95ba79..4fce64a030b6 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.c @@ -313,9 +313,6 @@ static void handle_det_buf_split(struct display_mode_lib *mode_lib, if (swath_height_c > 0) log2_swath_height_c = dml_log2(swath_height_c); - - if (req128_c && log2_swath_height_c > 0) - log2_swath_height_c -= 1; } rq_param->dlg.rq_l.swath_height = 1 << log2_swath_height_l; diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.c index ae5251041728..3fa9a5da02f6 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.c @@ -313,9 +313,6 @@ static void handle_det_buf_split(struct display_mode_lib *mode_lib, if (swath_height_c > 0) log2_swath_height_c = dml_log2(swath_height_c); - - if (req128_c && log2_swath_height_c > 0) - log2_swath_height_c -= 1; } rq_param->dlg.rq_l.swath_height = 1 << log2_swath_height_l; diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c b/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c index 0b132ce1d2cd..2b275e680379 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c @@ -1924,15 +1924,6 @@ static unsigned int CalculateVMAndRowBytes( *PixelPTEReqWidth = 32768.0 / BytePerPixel; *PTERequestSize = 64; FractionOfPTEReturnDrop = 0; - } else if (MacroTileSizeBytes == 4096) { - PixelPTEReqHeightPTEs = 1; - *PixelPTEReqHeight = MacroTileHeight; - *PixelPTEReqWidth = 8 * *MacroTileWidth; - *PTERequestSize = 64; - if (ScanDirection != dm_vert) - FractionOfPTEReturnDrop = 0; - else - FractionOfPTEReturnDrop = 7.0 / 8; } else if (GPUVMMinPageSize == 4 && MacroTileSizeBytes > 4096) { PixelPTEReqHeightPTEs = 16; *PixelPTEReqHeight = 16 * BlockHeight256Bytes; diff --git a/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c b/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c index 547dfcc80fde..d851c081e376 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c +++ b/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c @@ -8926,7 +8926,7 @@ void dml_core_mode_programming(struct display_mode_lib_st *mode_lib, const struc // The prefetch scheduling should only be calculated once as per AllowForPStateChangeOrStutterInVBlank requirement // If the AllowForPStateChangeOrStutterInVBlank requirement is not strict (i.e. only try those power saving feature - // if possible, then will try to program for the best power saving features in order of diffculty (dram, fclk, stutter) + // if possible, then will try to program for the best power saving features in order of difficulty (dram, fclk, stutter) s->iteration = 0; s->MaxTotalRDBandwidth = 0; s->AllPrefetchModeTested = false; @@ -9977,7 +9977,7 @@ void dml_core_get_row_heights( dml_print("DML_DLG: %s: GPUVMMinPageSizeKBytes = %u\n", __func__, GPUVMMinPageSizeKBytes); #endif - // just suppluy with enough parameters to calculate meta and dte + // just supply with enough parameters to calculate meta and dte CalculateVMAndRowBytes( 0, // dml_bool_t ViewportStationary, 1, // dml_bool_t DCCEnable, @@ -10110,7 +10110,7 @@ dml_bool_t dml_mode_support( /// Note: In this function, it is assumed that DCFCLK, SOCCLK freq are the state values, and mode_program will just use the DML calculated DPPCLK and DISPCLK /// @param mode_lib mode_lib data struct that house all the input/output/bbox and calculation values. /// @param state_idx Power state idx chosen -/// @param display_cfg Display Congiuration +/// @param display_cfg Display Configuration /// @param call_standalone Calling mode_programming without calling mode support. Some of the "support" struct member will be pre-calculated before doing mode programming /// TODO: Add clk_cfg input, could be useful for standalone mode dml_bool_t dml_mode_programming( diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c index b0d9aed0f265..8697eac1e1f7 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c +++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c @@ -858,7 +858,9 @@ static void populate_dml21_plane_config_from_plane_state(struct dml2_context *dm plane->immediate_flip = plane_state->flip_immediate; - plane->composition.rect_out_height_spans_vactive = plane_state->dst_rect.height >= stream->timing.v_addressable; + plane->composition.rect_out_height_spans_vactive = + plane_state->dst_rect.height >= stream->timing.v_addressable && + stream->dst.height >= stream->timing.v_addressable; } //TODO : Could be possibly moved to a common helper layer. diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_pmo/dml2_pmo_dcn4_fams2.c b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_pmo/dml2_pmo_dcn4_fams2.c index d63558ee3135..1cf9015e854a 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_pmo/dml2_pmo_dcn4_fams2.c +++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_pmo/dml2_pmo_dcn4_fams2.c @@ -940,9 +940,11 @@ static void build_synchronized_timing_groups( /* find synchronizable timing groups */ for (j = i + 1; j < display_config->display_config.num_streams; j++) { if (memcmp(master_timing, - &display_config->display_config.stream_descriptors[j].timing, - sizeof(struct dml2_timing_cfg)) == 0 && - display_config->display_config.stream_descriptors[i].output.output_encoder == display_config->display_config.stream_descriptors[j].output.output_encoder) { + &display_config->display_config.stream_descriptors[j].timing, + sizeof(struct dml2_timing_cfg)) == 0 && + display_config->display_config.stream_descriptors[i].output.output_encoder == display_config->display_config.stream_descriptors[j].output.output_encoder && + (display_config->display_config.stream_descriptors[i].output.output_encoder != dml2_hdmi || //hdmi requires formats match + display_config->display_config.stream_descriptors[i].output.output_format == display_config->display_config.stream_descriptors[j].output.output_format)) { set_bit_in_bitfield(&pmo->scratch.pmo_dcn4.synchronized_timing_group_masks[timing_group_idx], j); set_bit_in_bitfield(&stream_mapped_mask, j); } 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 c4c52173ef22..11c904ae2958 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/dsc/dc_dsc.c b/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c index a1727e5bf024..ebd5df1a36e8 100644 --- a/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c +++ b/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c @@ -668,6 +668,7 @@ static bool decide_dsc_bandwidth_range( */ static bool decide_dsc_target_bpp_x16( const struct dc_dsc_policy *policy, + const struct dc_dsc_config_options *options, const struct dsc_enc_caps *dsc_common_caps, const int target_bandwidth_kbps, const struct dc_crtc_timing *timing, @@ -682,7 +683,7 @@ static bool decide_dsc_target_bpp_x16( if (decide_dsc_bandwidth_range(policy->min_target_bpp * 16, policy->max_target_bpp * 16, num_slices_h, dsc_common_caps, timing, link_encoding, &range)) { if (target_bandwidth_kbps >= range.stream_kbps) { - if (policy->enable_dsc_when_not_needed) + if (policy->enable_dsc_when_not_needed || options->force_dsc_when_not_needed) /* enable max bpp even dsc is not needed */ *target_bpp_x16 = range.max_target_bpp_x16; } else if (target_bandwidth_kbps >= range.max_kbps) { @@ -882,7 +883,7 @@ static bool setup_dsc_config( memset(dsc_cfg, 0, sizeof(struct dc_dsc_config)); - dc_dsc_get_policy_for_timing(timing, options->max_target_bpp_limit_override_x16, &policy); + dc_dsc_get_policy_for_timing(timing, options->max_target_bpp_limit_override_x16, &policy, link_encoding); pic_width = timing->h_addressable + timing->h_border_left + timing->h_border_right; pic_height = timing->v_addressable + timing->v_border_top + timing->v_border_bottom; @@ -1080,6 +1081,7 @@ static bool setup_dsc_config( if (target_bandwidth_kbps > 0) { is_dsc_possible = decide_dsc_target_bpp_x16( &policy, + options, &dsc_common_caps, target_bandwidth_kbps, timing, @@ -1171,7 +1173,8 @@ uint32_t dc_dsc_stream_bandwidth_overhead_in_kbps( void dc_dsc_get_policy_for_timing(const struct dc_crtc_timing *timing, uint32_t max_target_bpp_limit_override_x16, - struct dc_dsc_policy *policy) + struct dc_dsc_policy *policy, + const enum dc_link_encoding_format link_encoding) { uint32_t bpc = 0; @@ -1235,10 +1238,7 @@ void dc_dsc_get_policy_for_timing(const struct dc_crtc_timing *timing, policy->max_target_bpp = max_target_bpp_limit_override_x16 / 16; /* enable DSC when not needed, default false */ - if (dsc_policy_enable_dsc_when_not_needed) - policy->enable_dsc_when_not_needed = dsc_policy_enable_dsc_when_not_needed; - else - policy->enable_dsc_when_not_needed = false; + policy->enable_dsc_when_not_needed = dsc_policy_enable_dsc_when_not_needed; } void dc_dsc_policy_set_max_target_bpp_limit(uint32_t limit) @@ -1267,4 +1267,5 @@ void dc_dsc_get_default_config_option(const struct dc *dc, struct dc_dsc_config_ options->dsc_force_odm_hslice_override = dc->debug.force_odm_combine; options->max_target_bpp_limit_override_x16 = 0; options->slice_height_granularity = 1; + options->force_dsc_when_not_needed = false; } diff --git a/drivers/gpu/drm/amd/display/dc/hubbub/dcn35/dcn35_hubbub.c b/drivers/gpu/drm/amd/display/dc/hubbub/dcn35/dcn35_hubbub.c index 6293173ba2b9..5eb3da8d5206 100644 --- a/drivers/gpu/drm/amd/display/dc/hubbub/dcn35/dcn35_hubbub.c +++ b/drivers/gpu/drm/amd/display/dc/hubbub/dcn35/dcn35_hubbub.c @@ -545,6 +545,7 @@ static void hubbub35_init(struct hubbub *hubbub) DCHUBBUB_ARB_MAX_REQ_OUTSTAND, 256, DCHUBBUB_ARB_MIN_REQ_OUTSTAND, 256); + memset(&hubbub2->watermarks.a.cstate_pstate, 0, sizeof(hubbub2->watermarks.a.cstate_pstate)); } /*static void hubbub35_set_request_limit(struct hubbub *hubbub, diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c index d52ce58c6a98..4fbed0298adf 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c @@ -57,6 +57,7 @@ #include "panel_cntl.h" #include "dc_state_priv.h" #include "dpcd_defs.h" +#include "dsc.h" /* include DCE11 register header files */ #include "dce/dce_11_0_d.h" #include "dce/dce_11_0_sh_mask.h" @@ -1823,6 +1824,48 @@ static void get_edp_links_with_sink( } } +static void clean_up_dsc_blocks(struct dc *dc) +{ + struct display_stream_compressor *dsc = NULL; + struct timing_generator *tg = NULL; + struct stream_encoder *se = NULL; + struct dccg *dccg = dc->res_pool->dccg; + struct pg_cntl *pg_cntl = dc->res_pool->pg_cntl; + int i; + + if (dc->ctx->dce_version != DCN_VERSION_3_5 && + dc->ctx->dce_version != DCN_VERSION_3_51) + return; + + for (i = 0; i < dc->res_pool->res_cap->num_dsc; i++) { + struct dcn_dsc_state s = {0}; + + dsc = dc->res_pool->dscs[i]; + dsc->funcs->dsc_read_state(dsc, &s); + if (s.dsc_fw_en) { + /* disable DSC in OPTC */ + if (i < dc->res_pool->timing_generator_count) { + tg = dc->res_pool->timing_generators[i]; + tg->funcs->set_dsc_config(tg, OPTC_DSC_DISABLED, 0, 0); + } + /* disable DSC in stream encoder */ + if (i < dc->res_pool->stream_enc_count) { + se = dc->res_pool->stream_enc[i]; + se->funcs->dp_set_dsc_config(se, OPTC_DSC_DISABLED, 0, 0); + se->funcs->dp_set_dsc_pps_info_packet(se, false, NULL, true); + } + /* disable DSC block */ + if (dccg->funcs->set_ref_dscclk) + dccg->funcs->set_ref_dscclk(dccg, dsc->inst); + dsc->funcs->dsc_disable(dsc); + + /* power down DSC */ + if (pg_cntl != NULL) + pg_cntl->funcs->dsc_pg_control(pg_cntl, dsc->inst, false); + } + } +} + /* * When ASIC goes from VBIOS/VGA mode to driver/accelerated mode we need: * 1. Power down all DC HW blocks @@ -1927,6 +1970,13 @@ void dce110_enable_accelerated_mode(struct dc *dc, struct dc_state *context) clk_mgr_exit_optimized_pwr_state(dc, dc->clk_mgr); power_down_all_hw_blocks(dc); + + /* DSC could be enabled on eDP during VBIOS post. + * To clean up dsc blocks if eDP is in link but not active. + */ + if (edp_link_with_sink && (edp_stream_num == 0)) + clean_up_dsc_blocks(dc); + disable_vga_and_power_gate_all_controllers(dc); if (edp_link_with_sink && !keep_edp_vdd_on) dc->hwss.edp_power_control(edp_link_with_sink, false); @@ -2046,13 +2096,20 @@ static void set_drr(struct pipe_ctx **pipe_ctx, * as well. */ for (i = 0; i < num_pipes; i++) { - pipe_ctx[i]->stream_res.tg->funcs->set_drr( - pipe_ctx[i]->stream_res.tg, ¶ms); - - if (adjust.v_total_max != 0 && adjust.v_total_min != 0) - pipe_ctx[i]->stream_res.tg->funcs->set_static_screen_control( - pipe_ctx[i]->stream_res.tg, - event_triggers, num_frames); + /* dc_state_destruct() might null the stream resources, so fetch tg + * here first to avoid a race condition. The lifetime of the pointee + * itself (the timing_generator object) is not a problem here. + */ + struct timing_generator *tg = pipe_ctx[i]->stream_res.tg; + + if ((tg != NULL) && tg->funcs) { + if (tg->funcs->set_drr) + tg->funcs->set_drr(tg, ¶ms); + if (adjust.v_total_max != 0 && adjust.v_total_min != 0) + if (tg->funcs->set_static_screen_control) + tg->funcs->set_static_screen_control( + tg, event_triggers, num_frames); + } } } diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.c index 42c52284a868..bded33575493 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.c @@ -455,7 +455,7 @@ bool dcn30_mmhubbub_warmup( struct mcif_wb *mcif_wb; struct mcif_warmup_params warmup_params = {0}; unsigned int i, i_buf; - /*make sure there is no active DWB eanbled */ + /* make sure there is no active DWB enabled */ for (i = 0; i < num_dwb; i++) { dwb = dc->res_pool->dwbc[wb_info[i].dwb_pipe_inst]; if (dwb->dwb_is_efc_transition || dwb->dwb_is_drc) { diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c index a36e11606f90..2e8c9f738259 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c @@ -1032,6 +1032,20 @@ void dcn32_update_dsc_on_stream(struct pipe_ctx *pipe_ctx, bool enable) struct dsc_config dsc_cfg; struct dsc_optc_config dsc_optc_cfg = {0}; enum optc_dsc_mode optc_dsc_mode; + struct dcn_dsc_state dsc_state = {0}; + + if (!dsc) { + DC_LOG_DSC("DSC is NULL for tg instance %d:", pipe_ctx->stream_res.tg->inst); + return; + } + + if (dsc->funcs->dsc_read_state) { + dsc->funcs->dsc_read_state(dsc, &dsc_state); + if (!dsc_state.dsc_fw_en) { + DC_LOG_DSC("DSC has been disabled for tg instance %d:", pipe_ctx->stream_res.tg->inst); + return; + } + } /* Enable DSC hw block */ dsc_cfg.pic_width = (stream->timing.h_addressable + stream->timing.h_border_left + stream->timing.h_border_right) / opp_cnt; diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c index 479fd3e89e5a..bd309dbdf7b2 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c @@ -334,7 +334,20 @@ static void update_dsc_on_stream(struct pipe_ctx *pipe_ctx, bool enable) struct dsc_config dsc_cfg; struct dsc_optc_config dsc_optc_cfg = {0}; enum optc_dsc_mode optc_dsc_mode; + struct dcn_dsc_state dsc_state = {0}; + if (!dsc) { + DC_LOG_DSC("DSC is NULL for tg instance %d:", pipe_ctx->stream_res.tg->inst); + return; + } + + if (dsc->funcs->dsc_read_state) { + dsc->funcs->dsc_read_state(dsc, &dsc_state); + if (!dsc_state.dsc_fw_en) { + DC_LOG_DSC("DSC has been disabled for tg instance %d:", pipe_ctx->stream_res.tg->inst); + return; + } + } /* Enable DSC hw block */ dsc_cfg.pic_width = (stream->timing.h_addressable + stream->timing.h_border_left + stream->timing.h_border_right) / opp_cnt; dsc_cfg.pic_height = stream->timing.v_addressable + stream->timing.v_border_top + stream->timing.v_border_bottom; diff --git a/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dpia.c b/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dpia.c index 46fb3649bc86..6499807af72a 100644 --- a/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dpia.c +++ b/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dpia.c @@ -50,8 +50,31 @@ static void update_dpia_stream_allocation_table(struct dc_link *link, DC_LOG_MST("dpia : status[%d]: alloc_slots[%d]: used_slots[%d]\n", status, mst_alloc_slots, prev_mst_slots_in_use); - ASSERT(link_enc); - link_enc->funcs->update_mst_stream_allocation_table(link_enc, table); + if (link_enc) + link_enc->funcs->update_mst_stream_allocation_table(link_enc, table); +} + +static void set_dio_dpia_link_test_pattern(struct dc_link *link, + const struct link_resource *link_res, + struct encoder_set_dp_phy_pattern_param *tp_params) +{ + if (tp_params->dp_phy_pattern != DP_TEST_PATTERN_VIDEO_MODE) + return; + + struct link_encoder *link_enc = link_enc_cfg_get_link_enc(link); + + if (!link_enc) + return; + + link_enc->funcs->dp_set_phy_pattern(link_enc, tp_params); + link->dc->link_srv->dp_trace_source_sequence(link, DPCD_SOURCE_SEQ_AFTER_SET_SOURCE_PATTERN); +} + +static void set_dio_dpia_lane_settings(struct dc_link *link, + const struct link_resource *link_res, + const struct dc_link_settings *link_settings, + const struct dc_lane_settings lane_settings[LANE_COUNT_DP_MAX]) +{ } static const struct link_hwss dpia_link_hwss = { @@ -65,8 +88,8 @@ static const struct link_hwss dpia_link_hwss = { .ext = { .set_throttled_vcp_size = set_dio_throttled_vcp_size, .enable_dp_link_output = enable_dio_dp_link_output, - .set_dp_link_test_pattern = set_dio_dp_link_test_pattern, - .set_dp_lane_settings = set_dio_dp_lane_settings, + .set_dp_link_test_pattern = set_dio_dpia_link_test_pattern, + .set_dp_lane_settings = set_dio_dpia_lane_settings, .update_stream_allocation_table = update_dpia_stream_allocation_table, }, }; diff --git a/drivers/gpu/drm/amd/display/dc/link/link_validation.c b/drivers/gpu/drm/amd/display/dc/link/link_validation.c index 1aed55b0ab6a..60f15a9ba7a5 100644 --- a/drivers/gpu/drm/amd/display/dc/link/link_validation.c +++ b/drivers/gpu/drm/amd/display/dc/link/link_validation.c @@ -287,6 +287,13 @@ static bool dp_validate_mode_timing( req_bw = dc_bandwidth_in_kbps_from_timing(timing, dc_link_get_highest_encoding_format(link)); max_bw = dp_link_bandwidth_kbps(link, link_setting); + bool is_max_uncompressed_pixel_rate_exceeded = link->dpcd_caps.max_uncompressed_pixel_rate_cap.bits.valid && + timing->pix_clk_100hz > link->dpcd_caps.max_uncompressed_pixel_rate_cap.bits.max_uncompressed_pixel_rate_cap * 10000; + + if (is_max_uncompressed_pixel_rate_exceeded && !timing->flags.DSC) { + return false; + } + if (req_bw <= max_bw) { /* remember the biggest mode here, during * initial link training (to get diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c index 34a618a7278b..d78c8ec4de79 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c @@ -1942,6 +1942,11 @@ static bool retrieve_link_cap(struct dc_link *link) DC_LOG_DP2("\tFEC aggregated error counters are supported"); } + core_link_read_dpcd(link, + DPCD_MAX_UNCOMPRESSED_PIXEL_RATE_CAP, + link->dpcd_caps.max_uncompressed_pixel_rate_cap.raw, + sizeof(link->dpcd_caps.max_uncompressed_pixel_rate_cap.raw)); + retrieve_cable_id(link); dpcd_write_cable_id_to_dprx(link); diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c index 988999c44475..27b881f947e8 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c @@ -515,6 +515,41 @@ bool dp_is_interlane_aligned(union lane_align_status_updated align_status) return align_status.bits.INTERLANE_ALIGN_DONE == 1; } +bool dp_check_interlane_aligned(union lane_align_status_updated align_status, + struct dc_link *link, + uint8_t retries) +{ + /* Take into consideration corner case for DP 1.4a LL Compliance CTS as USB4 + * has to share encoders unlike DP and USBC + */ + return (dp_is_interlane_aligned(align_status) || + (link->skip_fallback_on_link_loss && retries)); +} + +uint32_t dp_get_eq_aux_rd_interval( + const struct dc_link *link, + const struct link_training_settings *lt_settings, + uint32_t offset, + uint8_t retries) +{ + if (link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA) { + if (offset == 0 && retries == 1 && lt_settings->lttpr_mode == LTTPR_MODE_NON_TRANSPARENT) + return max(lt_settings->eq_pattern_time, (uint32_t) DPIA_CLK_SYNC_DELAY); + else + return dpia_get_eq_aux_rd_interval(link, lt_settings, offset); + } else if (is_repeater(lt_settings, offset)) + return dp_translate_training_aux_read_interval( + link->dpcd_caps.lttpr_caps.aux_rd_interval[offset - 1]); + else + return lt_settings->eq_pattern_time; +} + +bool dp_check_dpcd_reqeust_status(const struct dc_link *link, + enum dc_status status) +{ + return (status != DC_OK && link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA); +} + enum link_training_result dp_check_link_loss_status( struct dc_link *link, const struct link_training_settings *link_training_setting) @@ -973,13 +1008,17 @@ void repeater_training_done(struct dc_link *link, uint32_t offset) dpcd_pattern.v1_4.TRAINING_PATTERN_SET); } -static void dpcd_exit_training_mode(struct dc_link *link, enum dp_link_encoding encoding) +static enum link_training_result dpcd_exit_training_mode(struct dc_link *link, enum dp_link_encoding encoding) { + enum dc_status status; uint8_t sink_status = 0; uint8_t i; /* clear training pattern set */ - dpcd_set_training_pattern(link, DP_TRAINING_PATTERN_VIDEOIDLE); + status = dpcd_set_training_pattern(link, DP_TRAINING_PATTERN_VIDEOIDLE); + + if (dp_check_dpcd_reqeust_status(link, status)) + return LINK_TRAINING_ABORT; if (encoding == DP_128b_132b_ENCODING) { /* poll for intra-hop disable */ @@ -990,6 +1029,8 @@ static void dpcd_exit_training_mode(struct dc_link *link, enum dp_link_encoding fsleep(1000); } } + + return LINK_TRAINING_SUCCESS; } enum dc_status dpcd_configure_channel_coding(struct dc_link *link, @@ -1013,17 +1054,18 @@ enum dc_status dpcd_configure_channel_coding(struct dc_link *link, return status; } -void dpcd_set_training_pattern( +enum dc_status dpcd_set_training_pattern( struct dc_link *link, enum dc_dp_training_pattern training_pattern) { + enum dc_status status; union dpcd_training_pattern dpcd_pattern = {0}; dpcd_pattern.v1_4.TRAINING_PATTERN_SET = dp_training_pattern_to_dpcd_training_pattern( link, training_pattern); - core_link_write_dpcd( + status = core_link_write_dpcd( link, DP_TRAINING_PATTERN_SET, &dpcd_pattern.raw, @@ -1033,6 +1075,8 @@ void dpcd_set_training_pattern( __func__, DP_TRAINING_PATTERN_SET, dpcd_pattern.v1_4.TRAINING_PATTERN_SET); + + return status; } enum dc_status dpcd_set_link_settings( @@ -1185,6 +1229,13 @@ void dpcd_set_lt_pattern_and_lane_settings( dpcd_lt_buffer[DP_TRAINING_PATTERN_SET - DP_TRAINING_PATTERN_SET] = dpcd_pattern.raw; + if (link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA) + dpia_set_tps_notification( + link, + lt_settings, + dpcd_pattern.v1_4.TRAINING_PATTERN_SET, + offset); + if (is_repeater(lt_settings, offset)) { DC_LOG_HW_LINK_TRAINING("%s\n LTTPR Repeater ID: %d\n 0x%X pattern = %x\n", __func__, @@ -1455,7 +1506,8 @@ static enum link_training_result dp_transition_to_video_idle( */ if (link->connector_signal != SIGNAL_TYPE_EDP && status == LINK_TRAINING_SUCCESS) { msleep(5); - status = dp_check_link_loss_status(link, lt_settings); + if (!link->skip_fallback_on_link_loss) + status = dp_check_link_loss_status(link, lt_settings); } return status; } @@ -1521,7 +1573,9 @@ enum link_training_result dp_perform_link_training( ASSERT(0); /* exit training mode */ - dpcd_exit_training_mode(link, encoding); + if ((dpcd_exit_training_mode(link, encoding) != LINK_TRAINING_SUCCESS || status == LINK_TRAINING_ABORT) && + link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA) + dpia_training_abort(link, <_settings, 0); /* switch to video idle */ if ((status == LINK_TRAINING_SUCCESS) || !skip_video_pattern) @@ -1599,8 +1653,7 @@ bool perform_link_training_with_retries( dp_perform_link_training_skip_aux(link, &pipe_ctx->link_res, &cur_link_settings); return true; } else { - /** @todo Consolidate USB4 DP and DPx.x training. */ - if (link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA) { + if (!link->dc->config.consolidated_dpia_dp_lt && link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA) { status = dpia_perform_link_training( link, &pipe_ctx->link_res, @@ -1629,8 +1682,17 @@ bool perform_link_training_with_retries( dp_trace_lt_total_count_increment(link, false); dp_trace_lt_result_update(link, status, false); dp_trace_set_lt_end_timestamp(link, false); - if (status == LINK_TRAINING_SUCCESS && !is_link_bw_low) + if (status == LINK_TRAINING_SUCCESS && !is_link_bw_low) { + // Update verified link settings to current one + // Because DPIA LT might fallback to lower link setting. + if (link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA && + stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST) { + link->verified_link_cap.link_rate = link->cur_link_settings.link_rate; + link->verified_link_cap.lane_count = link->cur_link_settings.lane_count; + dm_helpers_dp_mst_update_branch_bandwidth(link->ctx, link); + } return true; + } } fail_count++; diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.h b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.h index 851bd17317a0..0b18aa35c33c 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.h +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.h @@ -55,7 +55,7 @@ void dp_set_hw_test_pattern( uint8_t *custom_pattern, uint32_t custom_pattern_size); -void dpcd_set_training_pattern( +enum dc_status dpcd_set_training_pattern( struct dc_link *link, enum dc_dp_training_pattern training_pattern); @@ -182,4 +182,18 @@ uint32_t dp_translate_training_aux_read_interval( uint8_t dp_get_nibble_at_index(const uint8_t *buf, uint32_t index); + +bool dp_check_interlane_aligned(union lane_align_status_updated align_status, + struct dc_link *link, + uint8_t retries); + +uint32_t dp_get_eq_aux_rd_interval( + const struct dc_link *link, + const struct link_training_settings *lt_settings, + uint32_t offset, + uint8_t retries); + +bool dp_check_dpcd_reqeust_status(const struct dc_link *link, + enum dc_status status); + #endif /* __DC_LINK_DP_TRAINING_H__ */ diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_8b_10b.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_8b_10b.c index 2b4c15b0b407..3bdce32a85e3 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_8b_10b.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_8b_10b.c @@ -157,6 +157,7 @@ enum link_training_result perform_8b_10b_clock_recovery_sequence( struct link_training_settings *lt_settings, uint32_t offset) { + enum dc_status status; uint32_t retries_cr; uint32_t retry_count; uint32_t wait_time_microsec; @@ -216,7 +217,7 @@ enum link_training_result perform_8b_10b_clock_recovery_sequence( /* 4. Read lane status and requested drive * settings as set by the sink */ - dp_get_lane_status_and_lane_adjust( + status = dp_get_lane_status_and_lane_adjust( link, lt_settings, dpcd_lane_status, @@ -224,6 +225,9 @@ enum link_training_result perform_8b_10b_clock_recovery_sequence( dpcd_lane_adjust, offset); + if (dp_check_dpcd_reqeust_status(link, status)) + return LINK_TRAINING_ABORT; + /* 5. check CR done*/ if (dp_is_cr_done(lane_count, dpcd_lane_status)) { DC_LOG_HW_LINK_TRAINING("%s: Clock recovery OK\n", __func__); @@ -273,6 +277,7 @@ enum link_training_result perform_8b_10b_channel_equalization_sequence( struct link_training_settings *lt_settings, uint32_t offset) { + enum dc_status status; enum dc_dp_training_pattern tr_pattern; uint32_t retries_ch_eq; uint32_t wait_time_microsec; @@ -308,12 +313,7 @@ enum link_training_result perform_8b_10b_channel_equalization_sequence( dpcd_set_lane_settings(link, lt_settings, offset); /* 3. wait for receiver to lock-on*/ - wait_time_microsec = lt_settings->eq_pattern_time; - - if (is_repeater(lt_settings, offset)) - wait_time_microsec = - dp_translate_training_aux_read_interval( - link->dpcd_caps.lttpr_caps.aux_rd_interval[offset - 1]); + wait_time_microsec = dp_get_eq_aux_rd_interval(link, lt_settings, offset, retries_ch_eq); dp_wait_for_training_aux_rd_interval( link, @@ -322,7 +322,7 @@ enum link_training_result perform_8b_10b_channel_equalization_sequence( /* 4. Read lane status and requested * drive settings as set by the sink*/ - dp_get_lane_status_and_lane_adjust( + status = dp_get_lane_status_and_lane_adjust( link, lt_settings, dpcd_lane_status, @@ -330,6 +330,9 @@ enum link_training_result perform_8b_10b_channel_equalization_sequence( dpcd_lane_adjust, offset); + if (dp_check_dpcd_reqeust_status(link, status)) + return LINK_TRAINING_ABORT; + /* 5. check CR done*/ if (!dp_is_cr_done(lane_count, dpcd_lane_status)) return dpcd_lane_status[0].bits.CR_DONE_0 ? @@ -339,7 +342,7 @@ enum link_training_result perform_8b_10b_channel_equalization_sequence( /* 6. check CHEQ done*/ if (dp_is_ch_eq_done(lane_count, dpcd_lane_status) && dp_is_symbol_locked(lane_count, dpcd_lane_status) && - dp_is_interlane_aligned(dpcd_lane_status_updated)) + dp_check_interlane_aligned(dpcd_lane_status_updated, link, retries_ch_eq)) return LINK_TRAINING_SUCCESS; /* 7. update VS/PE/PC2 in lt_settings*/ diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_dpia.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_dpia.c index cd1975c03f38..39e4b7dc9588 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_dpia.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_dpia.c @@ -43,9 +43,6 @@ #define DC_LOGGER \ link->ctx->logger -/* The approximate time (us) it takes to transmit 9 USB4 DP clock sync packets. */ -#define DPIA_CLK_SYNC_DELAY 16000 - /* Extend interval between training status checks for manual testing. */ #define DPIA_DEBUG_EXTENDED_AUX_RD_INTERVAL_US 60000000 @@ -566,28 +563,6 @@ static enum link_training_result dpia_training_cr_phase( return result; } -/* Return status read interval during equalization phase. */ -static uint32_t dpia_get_eq_aux_rd_interval( - const struct dc_link *link, - const struct link_training_settings *lt_settings, - uint32_t hop) -{ - uint32_t wait_time_microsec; - - if (hop == DPRX) - wait_time_microsec = lt_settings->eq_pattern_time; - else - wait_time_microsec = - dp_translate_training_aux_read_interval( - link->dpcd_caps.lttpr_caps.aux_rd_interval[hop - 1]); - - /* Check debug option for extending aux read interval. */ - if (link->dc->debug.dpia_debug.bits.extend_aux_rd_interval) - wait_time_microsec = DPIA_DEBUG_EXTENDED_AUX_RD_INTERVAL_US; - - return wait_time_microsec; -} - /* Execute equalization phase of link training for specified hop in display * path in non-transparent mode: * - driver issues both DPCD and SET_CONFIG transactions. @@ -936,6 +911,22 @@ static enum link_training_result dpia_training_end( return result; } +/* Return status read interval during equalization phase. */ +uint32_t dpia_get_eq_aux_rd_interval( + const struct dc_link *link, + const struct link_training_settings *lt_settings, + uint32_t hop) +{ + /* Check debug option for extending aux read interval. */ + if (link->dc->debug.dpia_debug.bits.extend_aux_rd_interval) + return DPIA_DEBUG_EXTENDED_AUX_RD_INTERVAL_US; + else if (hop == DPRX) + return lt_settings->eq_pattern_time; + else + return dp_translate_training_aux_read_interval( + link->dpcd_caps.lttpr_caps.aux_rd_interval[hop - 1]); +} + /* When aborting training of specified hop in display path, clean up by: * - Attempting to clear DPCD TRAINING_PATTERN_SET, LINK_BW_SET and LANE_COUNT_SET. * - Sending SET_CONFIG(SET_LINK) with lane count and link rate set to 0. @@ -943,7 +934,7 @@ static enum link_training_result dpia_training_end( * @param link DPIA link being trained. * @param hop Hop in display path. DPRX = 0. */ -static void dpia_training_abort( +void dpia_training_abort( struct dc_link *link, struct link_training_settings *lt_settings, uint32_t hop) @@ -968,7 +959,26 @@ static void dpia_training_abort( core_link_write_dpcd(link, dpcd_tps_offset, &data, 1); core_link_write_dpcd(link, DP_LINK_BW_SET, &data, 1); core_link_write_dpcd(link, DP_LANE_COUNT_SET, &data, 1); - core_link_send_set_config(link, DPIA_SET_CFG_SET_LINK, data); + + if (!link->dc->config.consolidated_dpia_dp_lt) + core_link_send_set_config(link, DPIA_SET_CFG_SET_LINK, data); +} + +void dpia_set_tps_notification( + struct dc_link *link, + const struct link_training_settings *lt_settings, + uint8_t pattern, + uint32_t hop) +{ + uint8_t repeater_cnt = 0; /* Number of hops/repeaters in display path. */ + + if (lt_settings->lttpr_mode != LTTPR_MODE_NON_TRANSPARENT || pattern == DPCD_TRAINING_PATTERN_VIDEOIDLE) + return; + + repeater_cnt = dp_parse_lttpr_repeater_count(link->dpcd_caps.lttpr_caps.phy_repeater_cnt); + + if (hop != repeater_cnt) + dc_process_dmub_dpia_set_tps_notification(link->ctx->dc, link->link_index, pattern); } enum link_training_result dpia_perform_link_training( diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_dpia.h b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_dpia.h index b39fb9faf1c2..9f4eceb494c2 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_dpia.h +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_dpia.h @@ -28,6 +28,9 @@ #define __DC_LINK_DP_TRAINING_DPIA_H__ #include "link_dp_training.h" +/* The approximate time (us) it takes to transmit 9 USB4 DP clock sync packets. */ +#define DPIA_CLK_SYNC_DELAY 16000 + /* Train DP tunneling link for USB4 DPIA display endpoint. * DPIA equivalent of dc_link_dp_perfrorm_link_training. * Aborts link training upon detection of sink unplug. @@ -38,4 +41,20 @@ enum link_training_result dpia_perform_link_training( const struct dc_link_settings *link_setting, bool skip_video_pattern); +void dpia_training_abort( + struct dc_link *link, + struct link_training_settings *lt_settings, + uint32_t hop); + +uint32_t dpia_get_eq_aux_rd_interval( + const struct dc_link *link, + const struct link_training_settings *lt_settings, + uint32_t hop); + +void dpia_set_tps_notification( + struct dc_link *link, + const struct link_training_settings *lt_settings, + uint8_t pattern, + uint32_t offset); + #endif /* __DC_LINK_DP_TRAINING_DPIA_H__ */ diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c index 46ad684fe192..893a9d9ee870 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c @@ -2155,6 +2155,7 @@ static bool dcn35_resource_construct( dc->dml2_options.max_segments_per_hubp = 24; dc->dml2_options.det_segment_size = DCN3_2_DET_SEG_SIZE;/*todo*/ + dc->dml2_options.override_det_buffer_size_kbytes = true; if (dc->config.sdpif_request_limit_words_per_umc == 0) dc->config.sdpif_request_limit_words_per_umc = 16;/*todo*/ 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 4c5e722baa3a..70abd32ce2ad 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 @@ -736,7 +736,7 @@ static const struct dc_debug_options debug_defaults_drv = { .hdmichar = true, .dpstream = true, .symclk32_se = true, - .symclk32_le = true, + .symclk32_le = false, .symclk_fe = true, .physymclk = false, .dpiasymclk = true, @@ -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 = { @@ -2133,6 +2134,7 @@ static bool dcn351_resource_construct( dc->dml2_options.max_segments_per_hubp = 24; dc->dml2_options.det_segment_size = DCN3_2_DET_SEG_SIZE;/*todo*/ + dc->dml2_options.override_det_buffer_size_kbytes = true; if (dc->config.sdpif_request_limit_words_per_umc == 0) dc->config.sdpif_request_limit_words_per_umc = 16;/*todo*/ diff --git a/drivers/gpu/drm/amd/display/dc/spl/dc_spl.c b/drivers/gpu/drm/amd/display/dc/spl/dc_spl.c index 15f7eda903e6..014e8a296f0c 100644 --- a/drivers/gpu/drm/amd/display/dc/spl/dc_spl.c +++ b/drivers/gpu/drm/amd/display/dc/spl/dc_spl.c @@ -813,6 +813,14 @@ static bool enable_easf(struct spl_in *spl_in, struct spl_scratch *spl_scratch) return skip_easf; } +/* Check if video is in fullscreen mode */ +static bool spl_is_video_fullscreen(struct spl_in *spl_in) +{ + if (spl_is_yuv420(spl_in->basic_in.format) && spl_in->is_fullscreen) + return true; + return false; +} + static bool spl_get_isharp_en(struct spl_in *spl_in, struct spl_scratch *spl_scratch) { @@ -820,6 +828,7 @@ static bool spl_get_isharp_en(struct spl_in *spl_in, int vratio = 0; int hratio = 0; struct spl_taps taps = spl_scratch->scl_data.taps; + bool fullscreen = spl_is_video_fullscreen(spl_in); /* Return if adaptive sharpness is disabled */ if (spl_in->adaptive_sharpness.enable == false) @@ -835,9 +844,18 @@ static bool spl_get_isharp_en(struct spl_in *spl_in, // Scaling is up to 1:1 (no scaling) or upscaling /* - * Apply sharpness to all RGB surfaces and to - * NV12/P010 surfaces + * Apply sharpness to RGB and YUV (NV12/P010) + * surfaces based on policy setting */ + if (!spl_is_yuv420(spl_in->basic_in.format) && + (spl_in->debug.sharpen_policy == SHARPEN_YUV)) + return enable_isharp; + else if ((spl_is_yuv420(spl_in->basic_in.format) && !fullscreen) && + (spl_in->debug.sharpen_policy == SHARPEN_RGB_FULLSCREEN_YUV)) + return enable_isharp; + else if (!spl_in->is_fullscreen && + spl_in->debug.sharpen_policy == SHARPEN_FULLSCREEN_ALL) + return enable_isharp; /* * Apply sharpness if supports horizontal taps 4,6 AND @@ -1155,14 +1173,19 @@ static void spl_set_dscl_prog_data(struct spl_in *spl_in, struct spl_scratch *sp } /* Calculate C0-C3 coefficients based on HDR_mult */ -static void spl_calculate_c0_c3_hdr(struct dscl_prog_data *dscl_prog_data, uint32_t hdr_multx100) +static void spl_calculate_c0_c3_hdr(struct dscl_prog_data *dscl_prog_data, uint32_t sdr_white_level_nits) { struct spl_fixed31_32 hdr_mult, c0_mult, c1_mult, c2_mult; struct spl_fixed31_32 c0_calc, c1_calc, c2_calc; struct spl_custom_float_format fmt; + uint32_t hdr_multx100_int; - SPL_ASSERT(hdr_multx100); - hdr_mult = spl_fixpt_from_fraction((long long)hdr_multx100, 100LL); + if ((sdr_white_level_nits >= 80) && (sdr_white_level_nits <= 480)) + hdr_multx100_int = sdr_white_level_nits * 100 / 80; + else + hdr_multx100_int = 100; /* default for 80 nits otherwise */ + + hdr_mult = spl_fixpt_from_fraction((long long)hdr_multx100_int, 100LL); c0_mult = spl_fixpt_from_fraction(2126LL, 10000LL); c1_mult = spl_fixpt_from_fraction(7152LL, 10000LL); c2_mult = spl_fixpt_from_fraction(722LL, 10000LL); @@ -1191,7 +1214,7 @@ static void spl_calculate_c0_c3_hdr(struct dscl_prog_data *dscl_prog_data, uint3 static void spl_set_easf_data(struct spl_scratch *spl_scratch, struct spl_out *spl_out, bool enable_easf_v, bool enable_easf_h, enum linear_light_scaling lls_pref, enum spl_pixel_format format, enum system_setup setup, - uint32_t hdr_multx100) + uint32_t sdr_white_level_nits) { struct dscl_prog_data *dscl_prog_data = spl_out->dscl_prog_data; if (enable_easf_v) { @@ -1499,7 +1522,7 @@ static void spl_set_easf_data(struct spl_scratch *spl_scratch, struct spl_out *s dscl_prog_data->easf_ltonl_en = 1; // Linear input if ((setup == HDR_L) && (spl_is_rgb8(format))) { /* Calculate C0-C3 coefficients based on HDR multiplier */ - spl_calculate_c0_c3_hdr(dscl_prog_data, hdr_multx100); + spl_calculate_c0_c3_hdr(dscl_prog_data, sdr_white_level_nits); } else { // HDR_L ( DWM ) and SDR_L dscl_prog_data->easf_matrix_c0 = 0x4EF7; // fp1.5.10, C0 coefficient (LN_rec709: 0.2126 * (2^14)/125 = 27.86590720) @@ -1557,7 +1580,7 @@ static void spl_set_isharp_data(struct dscl_prog_data *dscl_prog_data, struct adaptive_sharpness adp_sharpness, bool enable_isharp, enum linear_light_scaling lls_pref, enum spl_pixel_format format, const struct spl_scaler_data *data, struct spl_fixed31_32 ratio, - enum system_setup setup) + enum system_setup setup, enum scale_to_sharpness_policy scale_to_sharpness_policy) { /* Turn off sharpener if not required */ if (!enable_isharp) { @@ -1565,6 +1588,11 @@ static void spl_set_isharp_data(struct dscl_prog_data *dscl_prog_data, return; } + spl_build_isharp_1dlut_from_reference_curve(ratio, setup, adp_sharpness, + scale_to_sharpness_policy); + dscl_prog_data->isharp_delta = spl_get_pregen_filter_isharp_1D_lut(setup); + dscl_prog_data->sharpness_level = adp_sharpness.sharpness_level; + dscl_prog_data->isharp_en = 1; // ISHARP_EN // Set ISHARP_NOISEDET_MODE if htaps = 6-tap if (data->taps.h_taps == 6) { @@ -1662,11 +1690,6 @@ static void spl_set_isharp_data(struct dscl_prog_data *dscl_prog_data, dscl_prog_data->isharp_lba.base_seg[5] = 0; // ISHARP LBA PWL for Seg 5. BASE value in U0.6 format } - - spl_build_isharp_1dlut_from_reference_curve(ratio, setup, adp_sharpness); - dscl_prog_data->isharp_delta = spl_get_pregen_filter_isharp_1D_lut(setup); - dscl_prog_data->sharpness_level = adp_sharpness.sharpness_level; - // Program the nldelta soft clip values if (lls_pref == LLS_PREF_YES) { dscl_prog_data->isharp_nldelta_sclip.enable_p = 0; /* ISHARP_NLDELTA_SCLIP_EN_P */ @@ -1750,7 +1773,7 @@ bool spl_calculate_scaler_params(struct spl_in *spl_in, struct spl_out *spl_out) // Set EASF spl_set_easf_data(&spl_scratch, spl_out, enable_easf_v, enable_easf_h, spl_in->lls_pref, - spl_in->basic_in.format, setup, spl_in->hdr_multx100); + spl_in->basic_in.format, setup, spl_in->sdr_white_level_nits); // Set iSHARP vratio = spl_fixpt_ceil(spl_scratch.scl_data.ratios.vert); @@ -1761,7 +1784,8 @@ bool spl_calculate_scaler_params(struct spl_in *spl_in, struct spl_out *spl_out) isharp_scale_ratio = spl_scratch.scl_data.recip_ratios.horz; spl_set_isharp_data(spl_out->dscl_prog_data, spl_in->adaptive_sharpness, enable_isharp, - spl_in->lls_pref, spl_in->basic_in.format, data, isharp_scale_ratio, setup); + spl_in->lls_pref, spl_in->basic_in.format, data, isharp_scale_ratio, setup, + spl_in->debug.scale_to_sharpness_policy); return res; } diff --git a/drivers/gpu/drm/amd/display/dc/spl/dc_spl_isharp_filters.c b/drivers/gpu/drm/amd/display/dc/spl/dc_spl_isharp_filters.c index 33712f50d303..e0572252c640 100644 --- a/drivers/gpu/drm/amd/display/dc/spl/dc_spl_isharp_filters.c +++ b/drivers/gpu/drm/amd/display/dc/spl/dc_spl_isharp_filters.c @@ -500,6 +500,15 @@ struct isharp_1D_lut_pregen filter_isharp_1D_lut_pregen[NUM_SHARPNESS_SETUPS] = }, }; +struct scale_ratio_to_sharpness_level_adj sharpness_level_adj[NUM_SHARPNESS_ADJ_LEVELS] = { + {1125, 1000, 0}, + {11, 10, 1}, + {1075, 1000, 2}, + {105, 100, 3}, + {1025, 1000, 4}, + {1, 1, 5}, +}; + const uint32_t *spl_get_filter_isharp_1D_lut_0(void) { return filter_isharp_1D_lut_0; @@ -541,19 +550,72 @@ uint16_t *spl_get_filter_isharp_bs_3tap_64p(void) return filter_isharp_bs_3tap_64p_s1_12; } -static unsigned int spl_calculate_sharpness_level(int discrete_sharpness_level, enum system_setup setup, - struct spl_sharpness_range sharpness_range) +static unsigned int spl_calculate_sharpness_level_adj(struct spl_fixed31_32 ratio) +{ + int j; + struct spl_fixed31_32 ratio_level; + struct scale_ratio_to_sharpness_level_adj *lookup_ptr; + unsigned int sharpness_level_down_adj; + + /* + * Adjust sharpness level based on current scaling ratio + * + * We have 5 discrete scaling ratios which we will use to adjust the + * sharpness level down by 1 as we pass each ratio. The ratios + * are + * + * 1.125 upscale and higher - no adj + * 1.100 - under 1.125 - adj level down 1 + * 1.075 - under 1.100 - adj level down 2 + * 1.050 - under 1.075 - adj level down 3 + * 1.025 - under 1.050 - adj level down 4 + * 1.000 - under 1.025 - adj level down 5 + * + */ + j = 0; + sharpness_level_down_adj = 0; + lookup_ptr = sharpness_level_adj; + while (j < NUM_SHARPNESS_ADJ_LEVELS) { + ratio_level = spl_fixpt_from_fraction(lookup_ptr->ratio_numer, + lookup_ptr->ratio_denom); + if (ratio.value >= ratio_level.value) { + sharpness_level_down_adj = lookup_ptr->level_down_adj; + break; + } + lookup_ptr++; + j++; + } + return sharpness_level_down_adj; +} + +static unsigned int spl_calculate_sharpness_level(struct spl_fixed31_32 ratio, + int discrete_sharpness_level, enum system_setup setup, + struct spl_sharpness_range sharpness_range, + enum scale_to_sharpness_policy scale_to_sharpness_policy) { unsigned int sharpness_level = 0; + unsigned int sharpness_level_down_adj = 0; int min_sharpness, max_sharpness, mid_sharpness; + /* + * Adjust sharpness level if policy requires we adjust it based on + * scale ratio. Based on scale ratio, we may adjust the sharpness + * level down by a certain number of steps. We will not select + * a sharpness value of 0 so the lowest sharpness level will be + * 0 or 1 depending on what the min_sharpness is + * + * If the policy is no required, this code maybe removed at a later + * date + */ switch (setup) { case HDR_L: min_sharpness = sharpness_range.hdr_rgb_min; max_sharpness = sharpness_range.hdr_rgb_max; mid_sharpness = sharpness_range.hdr_rgb_mid; + if (scale_to_sharpness_policy == SCALE_TO_SHARPNESS_ADJ_ALL) + sharpness_level_down_adj = spl_calculate_sharpness_level_adj(ratio); break; case HDR_NL: /* currently no use case, use Non-linear SDR values for now */ @@ -561,15 +623,26 @@ static unsigned int spl_calculate_sharpness_level(int discrete_sharpness_level, min_sharpness = sharpness_range.sdr_yuv_min; max_sharpness = sharpness_range.sdr_yuv_max; mid_sharpness = sharpness_range.sdr_yuv_mid; + if (scale_to_sharpness_policy >= SCALE_TO_SHARPNESS_ADJ_YUV) + sharpness_level_down_adj = spl_calculate_sharpness_level_adj(ratio); break; case SDR_L: default: min_sharpness = sharpness_range.sdr_rgb_min; max_sharpness = sharpness_range.sdr_rgb_max; mid_sharpness = sharpness_range.sdr_rgb_mid; + if (scale_to_sharpness_policy == SCALE_TO_SHARPNESS_ADJ_ALL) + sharpness_level_down_adj = spl_calculate_sharpness_level_adj(ratio); break; } + if ((min_sharpness == 0) && (sharpness_level_down_adj >= discrete_sharpness_level)) + discrete_sharpness_level = 1; + else if (sharpness_level_down_adj >= discrete_sharpness_level) + discrete_sharpness_level = 0; + else + discrete_sharpness_level -= sharpness_level_down_adj; + int lower_half_step_size = (mid_sharpness - min_sharpness) / 5; int upper_half_step_size = (max_sharpness - mid_sharpness) / 5; @@ -584,7 +657,7 @@ static unsigned int spl_calculate_sharpness_level(int discrete_sharpness_level, } void spl_build_isharp_1dlut_from_reference_curve(struct spl_fixed31_32 ratio, enum system_setup setup, - struct adaptive_sharpness sharpness) + struct adaptive_sharpness sharpness, enum scale_to_sharpness_policy scale_to_sharpness_policy) { uint8_t *byte_ptr_1dlut_src, *byte_ptr_1dlut_dst; struct spl_fixed31_32 sharp_base, sharp_calc, sharp_level; @@ -594,8 +667,9 @@ void spl_build_isharp_1dlut_from_reference_curve(struct spl_fixed31_32 ratio, en uint32_t filter_pregen_store[ISHARP_LUT_TABLE_SIZE]; /* Custom sharpnessX1000 value */ - unsigned int sharpnessX1000 = spl_calculate_sharpness_level(sharpness.sharpness_level, - setup, sharpness.sharpness_range); + unsigned int sharpnessX1000 = spl_calculate_sharpness_level(ratio, + sharpness.sharpness_level, setup, + sharpness.sharpness_range, scale_to_sharpness_policy); sharp_level = spl_fixpt_from_fraction(sharpnessX1000, 1000); /* @@ -606,7 +680,6 @@ void spl_build_isharp_1dlut_from_reference_curve(struct spl_fixed31_32 ratio, en (filter_isharp_1D_lut_pregen[setup].sharpness_denom == 1000)) return; - /* * Calculate LUT_128_gained with this equation: * diff --git a/drivers/gpu/drm/amd/display/dc/spl/dc_spl_isharp_filters.h b/drivers/gpu/drm/amd/display/dc/spl/dc_spl_isharp_filters.h index fe0b12571f2c..afcc66206ca2 100644 --- a/drivers/gpu/drm/amd/display/dc/spl/dc_spl_isharp_filters.h +++ b/drivers/gpu/drm/amd/display/dc/spl/dc_spl_isharp_filters.h @@ -20,11 +20,11 @@ uint16_t *spl_get_filter_isharp_bs_3tap_64p(void); const uint16_t *spl_get_filter_isharp_wide_6tap_64p(void); uint16_t *spl_dscl_get_blur_scale_coeffs_64p(int taps); -struct scale_ratio_to_sharpness_level_lookup { +#define NUM_SHARPNESS_ADJ_LEVELS 6 +struct scale_ratio_to_sharpness_level_adj { unsigned int ratio_numer; unsigned int ratio_denom; - unsigned int sharpness_numer; - unsigned int sharpness_denom; + unsigned int level_down_adj; /* adjust sharpness level down */ }; struct isharp_1D_lut_pregen { @@ -45,6 +45,7 @@ void spl_init_blur_scale_coeffs(void); void spl_set_blur_scale_data(struct dscl_prog_data *dscl_prog_data, const struct spl_scaler_data *data); -void spl_build_isharp_1dlut_from_reference_curve(struct spl_fixed31_32 ratio, enum system_setup setup, struct adaptive_sharpness sharpness); +void spl_build_isharp_1dlut_from_reference_curve(struct spl_fixed31_32 ratio, enum system_setup setup, + struct adaptive_sharpness sharpness, enum scale_to_sharpness_policy scale_to_sharpness_policy); uint32_t *spl_get_pregen_filter_isharp_1D_lut(enum system_setup setup); #endif /* __DC_SPL_ISHARP_FILTERS_H__ */ diff --git a/drivers/gpu/drm/amd/display/dc/spl/dc_spl_types.h b/drivers/gpu/drm/amd/display/dc/spl/dc_spl_types.h index 85b19ebe2c57..2a74ff5fdfdb 100644 --- a/drivers/gpu/drm/amd/display/dc/spl/dc_spl_types.h +++ b/drivers/gpu/drm/amd/display/dc/spl/dc_spl_types.h @@ -487,6 +487,17 @@ enum linear_light_scaling { // convert it in translation logic LLS_PREF_YES, LLS_PREF_NO }; +enum sharpen_policy { + SHARPEN_ALWAYS = 0, + SHARPEN_YUV = 1, + SHARPEN_RGB_FULLSCREEN_YUV = 2, + SHARPEN_FULLSCREEN_ALL = 3 +}; +enum scale_to_sharpness_policy { + NO_SCALE_TO_SHARPNESS_ADJ = 0, + SCALE_TO_SHARPNESS_ADJ_YUV = 1, + SCALE_TO_SHARPNESS_ADJ_ALL = 2 +}; struct spl_funcs { void (*spl_calc_lb_num_partitions) (bool alpha_en, @@ -499,6 +510,8 @@ struct spl_funcs { struct spl_debug { int visual_confirm_base_offset; int visual_confirm_dpp_offset; + enum sharpen_policy sharpen_policy; + enum scale_to_sharpness_policy scale_to_sharpness_policy; }; struct spl_in { @@ -518,7 +531,7 @@ struct spl_in { bool is_hdr_on; int h_active; int v_active; - int hdr_multx100; + int sdr_white_level_nits; }; // end of SPL inputs diff --git a/drivers/gpu/drm/amd/display/dmub/dmub_srv.h b/drivers/gpu/drm/amd/display/dmub/dmub_srv.h index cd70453aeae0..fe5b6f7a3eb1 100644 --- a/drivers/gpu/drm/amd/display/dmub/dmub_srv.h +++ b/drivers/gpu/drm/amd/display/dmub/dmub_srv.h @@ -300,6 +300,7 @@ struct dmub_srv_hw_params { enum dmub_ips_disable_type disable_ips; bool disallow_phy_access; bool disable_sldo_opt; + bool enable_non_transparent_setconfig; }; /** diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h index e20c220aa8b4..ebcf68bfae2b 100644 --- a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h +++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h @@ -682,7 +682,7 @@ union dmub_fw_boot_options { uint32_t gpint_scratch8: 1; /* 1 if GPINT is in scratch8*/ uint32_t usb4_cm_version: 1; /**< 1 CM support */ uint32_t dpia_hpd_int_enable_supported: 1; /* 1 if dpia hpd int enable supported */ - uint32_t reserved0: 1; + uint32_t enable_non_transparent_setconfig: 1; /* 1 if dpia use conventional dp lt flow*/ uint32_t disable_clk_ds: 1; /* 1 if disallow dispclk_ds and dppclk_ds*/ uint32_t disable_timeout_recovery : 1; /* 1 if timeout recovery should be disabled */ uint32_t ips_pg_disable: 1; /* 1 to disable ONO domains power gating*/ @@ -1308,6 +1308,7 @@ enum dmub_cmd_dpia_type { DMUB_CMD__DPIA_DIG1_DPIA_CONTROL = 0, DMUB_CMD__DPIA_SET_CONFIG_ACCESS = 1, DMUB_CMD__DPIA_MST_ALLOC_SLOTS = 2, + DMUB_CMD__DPIA_SET_TPS_NOTIFICATION = 3, }; /* DMUB_OUT_CMD__DPIA_NOTIFICATION command types. */ @@ -2139,6 +2140,24 @@ struct dmub_rb_cmd_set_mst_alloc_slots { }; /** + * Data passed from driver to FW in a DMUB_CMD__SET_TPS_NOTIFICATION command. + */ +struct dmub_cmd_tps_notification_data { + uint8_t instance; /* DPIA instance */ + uint8_t tps; /* requested training pattern */ + uint8_t reserved1; + uint8_t reserved2; +}; + +/** + * DMUB command structure for SET_TPS_NOTIFICATION command. + */ +struct dmub_rb_cmd_set_tps_notification { + struct dmub_cmd_header header; /* header */ + struct dmub_cmd_tps_notification_data tps_notification; /* set tps_notification data */ +}; + +/** * DMUB command structure for DPIA HPD int enable control. */ struct dmub_rb_cmd_dpia_hpd_int_enable { @@ -5305,6 +5324,10 @@ union dmub_rb_cmd { */ struct dmub_rb_cmd_set_mst_alloc_slots set_mst_alloc_slots; /** + * Definition of a DMUB_CMD__DPIA_SET_TPS_NOTIFICATION command. + */ + struct dmub_rb_cmd_set_tps_notification set_tps_notification; + /** * Definition of a DMUB_CMD__EDID_CEA command. */ struct dmub_rb_cmd_edid_cea edid_cea; diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn35.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn35.c index 746696b6f09a..2ccad79053c5 100644 --- a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn35.c +++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn35.c @@ -425,6 +425,7 @@ void dmub_dcn35_enable_dmub_boot_options(struct dmub_srv *dmub, const struct dmu boot_options.bits.ips_disable = params->disable_ips; boot_options.bits.ips_sequential_ono = params->ips_sequential_ono; boot_options.bits.disable_sldo_opt = params->disable_sldo_opt; + boot_options.bits.enable_non_transparent_setconfig = params->enable_non_transparent_setconfig; REG_WRITE(DMCUB_SCRATCH14, boot_options.all); } diff --git a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c index a40e6590215a..bbd259cea4f4 100644 --- a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c +++ b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c @@ -134,7 +134,7 @@ unsigned int mod_freesync_calc_v_total_from_refresh( v_total = div64_u64(div64_u64(((unsigned long long)( frame_duration_in_ns) * (stream->timing.pix_clk_100hz / 10)), - stream->timing.h_total), 1000000); + stream->timing.h_total) + 500000, 1000000); /* v_total cannot be less than nominal */ if (v_total < stream->timing.v_total) { diff --git a/drivers/gpu/drm/amd/include/amd_shared.h b/drivers/gpu/drm/amd/include/amd_shared.h index 745fd052840d..3f91926a50e9 100644 --- a/drivers/gpu/drm/amd/include/amd_shared.h +++ b/drivers/gpu/drm/amd/include/amd_shared.h @@ -85,7 +85,7 @@ enum amd_apu_flags { * @AMD_IP_BLOCK_TYPE_MES: Micro-Engine Scheduler * @AMD_IP_BLOCK_TYPE_JPEG: JPEG Engine * @AMD_IP_BLOCK_TYPE_VPE: Video Processing Engine -* @AMD_IP_BLOCK_TYPE_UMSCH_MM: User Mode Schduler for Multimedia +* @AMD_IP_BLOCK_TYPE_UMSCH_MM: User Mode Scheduler for Multimedia * @AMD_IP_BLOCK_TYPE_ISP: Image Signal Processor * @AMD_IP_BLOCK_TYPE_NUM: Total number of IP block types */ diff --git a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h index 7744ca3ef4b1..e3e635a31b8a 100644 --- a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h +++ b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h @@ -71,6 +71,11 @@ enum kgd_memory_pool { KGD_POOL_FRAMEBUFFER = 3, }; +struct kfd_cu_occupancy { + u32 wave_cnt; + u32 doorbell_off; +}; + /** * enum kfd_sched_policy * @@ -313,8 +318,9 @@ struct kfd2kgd_calls { uint32_t grace_period, uint32_t *reg_offset, uint32_t *reg_data); - void (*get_cu_occupancy)(struct amdgpu_device *adev, int pasid, - int *wave_cnt, int *max_waves_per_cu, uint32_t inst); + void (*get_cu_occupancy)(struct amdgpu_device *adev, + struct kfd_cu_occupancy *cu_occupancy, + int *max_waves_per_cu, uint32_t inst); void (*program_trap_handler_settings)(struct amdgpu_device *adev, uint32_t vmid, uint64_t tba_addr, uint64_t tma_addr, uint32_t inst); diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_pmfw.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_pmfw.h index 0b3c2f54a343..822c6425d90e 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_pmfw.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_pmfw.h @@ -123,7 +123,7 @@ typedef enum { VOLTAGE_GUARDBAND_COUNT } GFX_GUARDBAND_e; -#define SMU_METRICS_TABLE_VERSION 0xC +#define SMU_METRICS_TABLE_VERSION 0xD typedef struct __attribute__((packed, aligned(4))) { uint32_t AccumulationCounter; @@ -227,6 +227,10 @@ typedef struct __attribute__((packed, aligned(4))) { // PCIE LINK Speed and width uint32_t PCIeLinkSpeed; uint32_t PCIeLinkWidth; + + // PER XCD ACTIVITY + uint32_t GfxBusy[8]; + uint64_t GfxBusyAcc[8]; } MetricsTableX_t; typedef struct __attribute__((packed, aligned(4))) { diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c index a887ab945dfa..1d024b122b0c 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c @@ -2569,10 +2569,14 @@ static int smu_v13_0_0_set_power_profile_mode(struct smu_context *smu, } } - return smu_cmn_send_smc_msg_with_param(smu, + ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_SetWorkloadMask, workload_mask, NULL); + if (!ret) + smu->workload_mask = workload_mask; + + return ret; } static bool smu_v13_0_0_is_mode1_reset_supported(struct smu_context *smu) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c index 9974c9f8135e..55ed6247eb61 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c @@ -2107,8 +2107,12 @@ static int smu_v13_0_6_i2c_xfer(struct i2c_adapter *i2c_adap, } mutex_lock(&adev->pm.mutex); r = smu_v13_0_6_request_i2c_xfer(smu, req); - if (r) - goto fail; + if (r) { + /* Retry once, in case of an i2c collision */ + r = smu_v13_0_6_request_i2c_xfer(smu, req); + if (r) + goto fail; + } for (c = i = 0; i < num_msgs; i++) { if (!(msg[i].flags & I2C_M_RD)) { diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c index 7bc95c404377..b891a5e0a396 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c @@ -2501,8 +2501,11 @@ static int smu_v13_0_7_set_power_profile_mode(struct smu_context *smu, long *inp return -EINVAL; ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_SetWorkloadMask, 1 << workload_type, NULL); + if (ret) dev_err(smu->adev->dev, "[%s] Failed to set work load mask!", __func__); + else + smu->workload_mask = (1 << workload_type); return ret; } diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c index 43820d7d2c54..5899d01fa73d 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c @@ -1861,10 +1861,14 @@ static int smu_v14_0_2_set_power_profile_mode(struct smu_context *smu, if (workload_type < 0) return -EINVAL; - return smu_cmn_send_smc_msg_with_param(smu, + ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_SetWorkloadMask, 1 << workload_type, NULL); + if (!ret) + smu->workload_mask = 1 << workload_type; + + return ret; } static int smu_v14_0_2_baco_enter(struct smu_context *smu) diff --git a/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-core.c b/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-core.c index dee640ab1d3a..41f72d458487 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 <drm/drm_print.h> #include <drm/drm_probe_helper.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #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 5e3b8edcf794..31832ba4017f 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 <linux/io.h> #include <linux/iopoll.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <drm/display/drm_hdcp_helper.h> diff --git a/drivers/gpu/drm/bridge/samsung-dsim.c b/drivers/gpu/drm/bridge/samsung-dsim.c index e7e53a9e42af..430f8adebf9c 100644 --- a/drivers/gpu/drm/bridge/samsung-dsim.c +++ b/drivers/gpu/drm/bridge/samsung-dsim.c @@ -10,7 +10,7 @@ * Tomasz Figa <t.figa@samsung.com> */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/clk.h> #include <linux/delay.h> diff --git a/drivers/gpu/drm/bridge/sil-sii8620.c b/drivers/gpu/drm/bridge/sil-sii8620.c index 6bb755e9f0a5..26b8d137bce0 100644 --- a/drivers/gpu/drm/bridge/sil-sii8620.c +++ b/drivers/gpu/drm/bridge/sil-sii8620.c @@ -6,7 +6,7 @@ * Andrzej Hajda <a.hajda@samsung.com> */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <drm/bridge/mhl.h> #include <drm/drm_bridge.h> diff --git a/drivers/gpu/drm/bridge/tc358775.c b/drivers/gpu/drm/bridge/tc358775.c index 3b7cc3be2ccd..0b4efaca6d68 100644 --- a/drivers/gpu/drm/bridge/tc358775.c +++ b/drivers/gpu/drm/bridge/tc358775.c @@ -19,7 +19,7 @@ #include <linux/regulator/consumer.h> #include <linux/slab.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <drm/display/drm_dp_helper.h> #include <drm/drm_atomic_helper.h> diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi86.c b/drivers/gpu/drm/bridge/ti-sn65dsi86.c index 84698a0b27a8..582cf4f73a74 100644 --- a/drivers/gpu/drm/bridge/ti-sn65dsi86.c +++ b/drivers/gpu/drm/bridge/ti-sn65dsi86.c @@ -21,7 +21,7 @@ #include <linux/regmap.h> #include <linux/regulator/consumer.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <drm/display/drm_dp_aux_bus.h> #include <drm/display/drm_dp_helper.h> diff --git a/drivers/gpu/drm/display/drm_dp_mst_topology.c b/drivers/gpu/drm/display/drm_dp_mst_topology.c index a040d7dfced1..ac90118b9e7a 100644 --- a/drivers/gpu/drm/display/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/display/drm_dp_mst_topology.c @@ -6083,6 +6083,7 @@ struct drm_dp_aux *drm_dp_mst_dsc_aux_for_port(struct drm_dp_mst_port *port) struct drm_dp_aux *immediate_upstream_aux; struct drm_dp_mst_port *fec_port; struct drm_dp_desc desc = {}; + u8 upstream_dsc; u8 endpoint_fec; u8 endpoint_dsc; @@ -6109,8 +6110,6 @@ struct drm_dp_aux *drm_dp_mst_dsc_aux_for_port(struct drm_dp_mst_port *port) /* DP-to-DP peer device */ if (drm_dp_mst_is_virtual_dpcd(immediate_upstream_port)) { - u8 upstream_dsc; - if (drm_dp_dpcd_read(&port->aux, DP_DSC_SUPPORT, &endpoint_dsc, 1) != 1) return NULL; @@ -6156,6 +6155,13 @@ struct drm_dp_aux *drm_dp_mst_dsc_aux_for_port(struct drm_dp_mst_port *port) if (drm_dp_has_quirk(&desc, DP_DPCD_QUIRK_DSC_WITHOUT_VIRTUAL_DPCD)) { u8 dpcd_ext[DP_RECEIVER_CAP_SIZE]; + if (drm_dp_dpcd_read(immediate_upstream_aux, + DP_DSC_SUPPORT, &upstream_dsc, 1) != 1) + return NULL; + + if (!(upstream_dsc & DP_DSC_DECOMPRESSION_IS_SUPPORTED)) + return NULL; + if (drm_dp_read_dpcd_caps(immediate_upstream_aux, dpcd_ext) < 0) return NULL; diff --git a/drivers/gpu/drm/display/drm_hdmi_state_helper.c b/drivers/gpu/drm/display/drm_hdmi_state_helper.c index 7854820089ec..feb7a3a75981 100644 --- a/drivers/gpu/drm/display/drm_hdmi_state_helper.c +++ b/drivers/gpu/drm/display/drm_hdmi_state_helper.c @@ -521,8 +521,6 @@ int drm_atomic_helper_connector_hdmi_check(struct drm_connector *connector, } EXPORT_SYMBOL(drm_atomic_helper_connector_hdmi_check); -#define HDMI_MAX_INFOFRAME_SIZE 29 - static int clear_device_infoframe(struct drm_connector *connector, enum hdmi_infoframe_type type) { @@ -563,7 +561,7 @@ static int write_device_infoframe(struct drm_connector *connector, { const struct drm_connector_hdmi_funcs *funcs = connector->hdmi.funcs; struct drm_device *dev = connector->dev; - u8 buffer[HDMI_MAX_INFOFRAME_SIZE]; + u8 buffer[HDMI_INFOFRAME_SIZE(MAX)]; int ret; int len; diff --git a/drivers/gpu/drm/drm_atomic_uapi.c b/drivers/gpu/drm/drm_atomic_uapi.c index 7936c2023955..370dc676e3aa 100644 --- a/drivers/gpu/drm/drm_atomic_uapi.c +++ b/drivers/gpu/drm/drm_atomic_uapi.c @@ -543,7 +543,7 @@ static int drm_atomic_plane_set_property(struct drm_plane *plane, &state->fb_damage_clips, val, -1, - sizeof(struct drm_rect), + sizeof(struct drm_mode_rect), &replaced); return ret; } else if (property == plane->scaling_filter_property) { diff --git a/drivers/gpu/drm/drm_debugfs.c b/drivers/gpu/drm/drm_debugfs.c index 6b239a24f1df..9d3e6dd68810 100644 --- a/drivers/gpu/drm/drm_debugfs.c +++ b/drivers/gpu/drm/drm_debugfs.c @@ -520,8 +520,6 @@ static const struct file_operations drm_connector_fops = { .write = connector_write }; -#define HDMI_MAX_INFOFRAME_SIZE 29 - static ssize_t audio_infoframe_read(struct file *filp, char __user *ubuf, size_t count, loff_t *ppos) { @@ -579,7 +577,7 @@ static ssize_t _f##_read_infoframe(struct file *filp, \ struct drm_connector *connector; \ union hdmi_infoframe *frame; \ struct drm_device *dev; \ - u8 buf[HDMI_MAX_INFOFRAME_SIZE]; \ + u8 buf[HDMI_INFOFRAME_SIZE(MAX)]; \ ssize_t len = 0; \ \ connector = filp->private_data; \ diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c index 00fbe9f8c03a..b1c294236cc8 100644 --- a/drivers/gpu/drm/i915/display/intel_ddi.c +++ b/drivers/gpu/drm/i915/display/intel_ddi.c @@ -916,7 +916,7 @@ intel_ddi_main_link_aux_domain(struct intel_digital_port *dig_port, * instead of a specific AUX_IO_<port> reference without powering up any * extra wells. */ - if (intel_encoder_can_psr(&dig_port->base)) + if (intel_psr_needs_aux_io_power(&dig_port->base, crtc_state)) return intel_display_power_aux_io_domain(i915, dig_port->aux_ch); else if (DISPLAY_VER(i915) < 14 && (intel_crtc_has_dp_encoder(crtc_state) || diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index a1fcedfd404b..90fa73575feb 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -531,6 +531,10 @@ static void intel_dp_set_source_rates(struct intel_dp *intel_dp) { /* The values must be in increasing order */ + static const int bmg_rates[] = { + 162000, 216000, 243000, 270000, 324000, 432000, 540000, 675000, + 810000, 1000000, 1350000, + }; static const int mtl_rates[] = { 162000, 216000, 243000, 270000, 324000, 432000, 540000, 675000, 810000, 1000000, 2000000, @@ -561,8 +565,13 @@ intel_dp_set_source_rates(struct intel_dp *intel_dp) intel_dp->source_rates || intel_dp->num_source_rates); if (DISPLAY_VER(dev_priv) >= 14) { - source_rates = mtl_rates; - size = ARRAY_SIZE(mtl_rates); + if (IS_BATTLEMAGE(dev_priv)) { + source_rates = bmg_rates; + size = ARRAY_SIZE(bmg_rates); + } else { + source_rates = mtl_rates; + size = ARRAY_SIZE(mtl_rates); + } max_rate = mtl_max_source_rate(intel_dp); } else if (DISPLAY_VER(dev_priv) >= 11) { source_rates = icl_rates; @@ -4058,6 +4067,9 @@ intel_edp_init_dpcd(struct intel_dp *intel_dp, struct intel_connector *connector drm_dp_is_branch(intel_dp->dpcd)); intel_init_dpcd_quirks(intel_dp, &intel_dp->desc.ident); + intel_dp->colorimetry_support = + intel_dp_get_colorimetry_status(intel_dp); + /* * Read the eDP display control registers. * @@ -4171,6 +4183,9 @@ intel_dp_get_dpcd(struct intel_dp *intel_dp) intel_init_dpcd_quirks(intel_dp, &intel_dp->desc.ident); + intel_dp->colorimetry_support = + intel_dp_get_colorimetry_status(intel_dp); + intel_dp_update_sink_caps(intel_dp); } @@ -6922,9 +6937,6 @@ intel_dp_init_connector(struct intel_digital_port *dig_port, "HDCP init failed, skipping.\n"); } - intel_dp->colorimetry_support = - intel_dp_get_colorimetry_status(intel_dp); - intel_dp->frl.is_trained = false; intel_dp->frl.trained_rate_gbps = 0; diff --git a/drivers/gpu/drm/i915/display/intel_dsi_vbt.c b/drivers/gpu/drm/i915/display/intel_dsi_vbt.c index d8951464bd2b..f0e3be0fe420 100644 --- a/drivers/gpu/drm/i915/display/intel_dsi_vbt.c +++ b/drivers/gpu/drm/i915/display/intel_dsi_vbt.c @@ -32,7 +32,7 @@ #include <linux/slab.h> #include <linux/string_helpers.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <drm/drm_crtc.h> #include <drm/drm_edid.h> diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c index 1f83b3b67ea6..136a0d6ca970 100644 --- a/drivers/gpu/drm/i915/display/intel_psr.c +++ b/drivers/gpu/drm/i915/display/intel_psr.c @@ -203,6 +203,25 @@ bool intel_encoder_can_psr(struct intel_encoder *encoder) return false; } +bool intel_psr_needs_aux_io_power(struct intel_encoder *encoder, + const struct intel_crtc_state *crtc_state) +{ + /* + * For PSR/PR modes only eDP requires the AUX IO power to be enabled whenever + * the output is enabled. For non-eDP outputs the main link is always + * on, hence it doesn't require the HW initiated AUX wake-up signaling used + * for eDP. + * + * TODO: + * - Consider leaving AUX IO disabled for eDP / PR as well, in case + * the ALPM with main-link off mode is not enabled. + * - Leave AUX IO enabled for DP / PR, once support for ALPM with + * main-link off mode is added for it and this mode gets enabled. + */ + return intel_crtc_has_type(crtc_state, INTEL_OUTPUT_EDP) && + intel_encoder_can_psr(encoder); +} + static bool psr_global_enabled(struct intel_dp *intel_dp) { struct intel_display *display = to_intel_display(intel_dp); @@ -2784,13 +2803,6 @@ static int _psr1_ready_for_pipe_update_locked(struct intel_dp *intel_dp) EDP_PSR_STATUS_STATE_MASK, 50); } -static int _panel_replay_ready_for_pipe_update_locked(struct intel_dp *intel_dp) -{ - return intel_dp_is_edp(intel_dp) ? - _psr2_ready_for_pipe_update_locked(intel_dp) : - _psr1_ready_for_pipe_update_locked(intel_dp); -} - /** * intel_psr_wait_for_idle_locked - wait for PSR be ready for a pipe update * @new_crtc_state: new CRTC state @@ -2813,12 +2825,10 @@ void intel_psr_wait_for_idle_locked(const struct intel_crtc_state *new_crtc_stat lockdep_assert_held(&intel_dp->psr.lock); - if (!intel_dp->psr.enabled) + if (!intel_dp->psr.enabled || intel_dp->psr.panel_replay_enabled) continue; - if (intel_dp->psr.panel_replay_enabled) - ret = _panel_replay_ready_for_pipe_update_locked(intel_dp); - else if (intel_dp->psr.sel_update_enabled) + if (intel_dp->psr.sel_update_enabled) ret = _psr2_ready_for_pipe_update_locked(intel_dp); else ret = _psr1_ready_for_pipe_update_locked(intel_dp); diff --git a/drivers/gpu/drm/i915/display/intel_psr.h b/drivers/gpu/drm/i915/display/intel_psr.h index 4e09c10908e4..6eb5f15f674f 100644 --- a/drivers/gpu/drm/i915/display/intel_psr.h +++ b/drivers/gpu/drm/i915/display/intel_psr.h @@ -25,6 +25,8 @@ struct intel_plane_state; (intel_dp)->psr.source_panel_replay_support) bool intel_encoder_can_psr(struct intel_encoder *encoder); +bool intel_psr_needs_aux_io_power(struct intel_encoder *encoder, + const struct intel_crtc_state *crtc_state); void intel_psr_init_dpcd(struct intel_dp *intel_dp); void intel_psr_enable_sink(struct intel_dp *intel_dp, const struct intel_crtc_state *crtc_state); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c index 5c72462d1f57..b22e2019768f 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c @@ -1131,7 +1131,7 @@ static vm_fault_t vm_fault_ttm(struct vm_fault *vmf) GEM_WARN_ON(!i915_ttm_cpu_maps_iomem(bo->resource)); } - if (wakeref & CONFIG_DRM_I915_USERFAULT_AUTOSUSPEND) + if (wakeref && CONFIG_DRM_I915_USERFAULT_AUTOSUSPEND != 0) intel_wakeref_auto(&to_i915(obj->base.dev)->runtime_pm.userfault_wakeref, msecs_to_jiffies_timeout(CONFIG_DRM_I915_USERFAULT_AUTOSUSPEND)); diff --git a/drivers/gpu/drm/nouveau/include/nvif/os.h b/drivers/gpu/drm/nouveau/include/nvif/os.h index a2eaf3929ac3..4a1123b81fee 100644 --- a/drivers/gpu/drm/nouveau/include/nvif/os.h +++ b/drivers/gpu/drm/nouveau/include/nvif/os.h @@ -30,7 +30,7 @@ #include <linux/iommu.h> #include <linux/of_device.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <soc/tegra/fuse.h> #include <soc/tegra/pmc.h> diff --git a/drivers/gpu/drm/panthor/panthor_drv.c b/drivers/gpu/drm/panthor/panthor_drv.c index 34182f67136c..c520f156e2d7 100644 --- a/drivers/gpu/drm/panthor/panthor_drv.c +++ b/drivers/gpu/drm/panthor/panthor_drv.c @@ -1383,6 +1383,7 @@ static const struct file_operations panthor_drm_driver_fops = { .read = drm_read, .llseek = noop_llseek, .mmap = panthor_mmap, + .fop_flags = FOP_UNSIGNED_OFFSET, }; #ifdef CONFIG_DEBUG_FS diff --git a/drivers/gpu/drm/panthor/panthor_mmu.c b/drivers/gpu/drm/panthor/panthor_mmu.c index bbc12728437f..3cd2bce59edc 100644 --- a/drivers/gpu/drm/panthor/panthor_mmu.c +++ b/drivers/gpu/drm/panthor/panthor_mmu.c @@ -1251,9 +1251,17 @@ static int panthor_vm_prepare_map_op_ctx(struct panthor_vm_op_ctx *op_ctx, goto err_cleanup; } + /* drm_gpuvm_bo_obtain_prealloc() will call drm_gpuvm_bo_put() on our + * pre-allocated BO if the <BO,VM> association exists. Given we + * only have one ref on preallocated_vm_bo, drm_gpuvm_bo_destroy() will + * be called immediately, and we have to hold the VM resv lock when + * calling this function. + */ + dma_resv_lock(panthor_vm_resv(vm), NULL); mutex_lock(&bo->gpuva_list_lock); op_ctx->map.vm_bo = drm_gpuvm_bo_obtain_prealloc(preallocated_vm_bo); mutex_unlock(&bo->gpuva_list_lock); + dma_resv_unlock(panthor_vm_resv(vm)); /* If the a vm_bo for this <VM,BO> combination exists, it already * retains a pin ref, and we can release the one we took earlier. diff --git a/drivers/gpu/drm/panthor/panthor_sched.c b/drivers/gpu/drm/panthor/panthor_sched.c index 91a31b70c037..aee362abb710 100644 --- a/drivers/gpu/drm/panthor/panthor_sched.c +++ b/drivers/gpu/drm/panthor/panthor_sched.c @@ -1103,7 +1103,13 @@ cs_slot_sync_queue_state_locked(struct panthor_device *ptdev, u32 csg_id, u32 cs list_move_tail(&group->wait_node, &group->ptdev->scheduler->groups.waiting); } - group->blocked_queues |= BIT(cs_id); + + /* The queue is only blocked if there's no deferred operation + * pending, which can be checked through the scoreboard status. + */ + if (!cs_iface->output->status_scoreboards) + group->blocked_queues |= BIT(cs_id); + queue->syncwait.gpu_va = cs_iface->output->status_wait_sync_ptr; queue->syncwait.ref = cs_iface->output->status_wait_sync_value; status_wait_cond = cs_iface->output->status_wait & CS_STATUS_WAIT_SYNC_COND_MASK; @@ -2046,6 +2052,7 @@ static void tick_ctx_cleanup(struct panthor_scheduler *sched, struct panthor_sched_tick_ctx *ctx) { + struct panthor_device *ptdev = sched->ptdev; struct panthor_group *group, *tmp; u32 i; @@ -2054,7 +2061,7 @@ tick_ctx_cleanup(struct panthor_scheduler *sched, /* If everything went fine, we should only have groups * to be terminated in the old_groups lists. */ - drm_WARN_ON(&group->ptdev->base, !ctx->csg_upd_failed_mask && + drm_WARN_ON(&ptdev->base, !ctx->csg_upd_failed_mask && group_can_run(group)); if (!group_can_run(group)) { @@ -2077,7 +2084,7 @@ tick_ctx_cleanup(struct panthor_scheduler *sched, /* If everything went fine, the groups to schedule lists should * be empty. */ - drm_WARN_ON(&group->ptdev->base, + drm_WARN_ON(&ptdev->base, !ctx->csg_upd_failed_mask && !list_empty(&ctx->groups[i])); list_for_each_entry_safe(group, tmp, &ctx->groups[i], run_node) { @@ -3242,6 +3249,18 @@ int panthor_group_destroy(struct panthor_file *pfile, u32 group_handle) return 0; } +static struct panthor_group *group_from_handle(struct panthor_group_pool *pool, + u32 group_handle) +{ + struct panthor_group *group; + + xa_lock(&pool->xa); + group = group_get(xa_load(&pool->xa, group_handle)); + xa_unlock(&pool->xa); + + return group; +} + int panthor_group_get_state(struct panthor_file *pfile, struct drm_panthor_group_get_state *get_state) { @@ -3253,7 +3272,7 @@ int panthor_group_get_state(struct panthor_file *pfile, if (get_state->pad) return -EINVAL; - group = group_get(xa_load(&gpool->xa, get_state->group_handle)); + group = group_from_handle(gpool, get_state->group_handle); if (!group) return -EINVAL; @@ -3384,7 +3403,7 @@ panthor_job_create(struct panthor_file *pfile, job->call_info.latest_flush = qsubmit->latest_flush; INIT_LIST_HEAD(&job->node); - job->group = group_get(xa_load(&gpool->xa, group_handle)); + job->group = group_from_handle(gpool, group_handle); if (!job->group) { ret = -EINVAL; goto err_put_job; @@ -3424,13 +3443,8 @@ void panthor_job_update_resvs(struct drm_exec *exec, struct drm_sched_job *sched { struct panthor_job *job = container_of(sched_job, struct panthor_job, base); - /* Still not sure why we want USAGE_WRITE for external objects, since I - * was assuming this would be handled through explicit syncs being imported - * to external BOs with DMA_BUF_IOCTL_IMPORT_SYNC_FILE, but other drivers - * seem to pass DMA_RESV_USAGE_WRITE, so there must be a good reason. - */ panthor_vm_update_resvs(job->group->vm, exec, &sched_job->s_fence->finished, - DMA_RESV_USAGE_BOOKKEEP, DMA_RESV_USAGE_WRITE); + DMA_RESV_USAGE_BOOKKEEP, DMA_RESV_USAGE_BOOKKEEP); } void panthor_sched_unplug(struct panthor_device *ptdev) diff --git a/drivers/gpu/drm/radeon/atom.c b/drivers/gpu/drm/radeon/atom.c index 5bc3e6b41c34..b31125eb9a65 100644 --- a/drivers/gpu/drm/radeon/atom.c +++ b/drivers/gpu/drm/radeon/atom.c @@ -27,7 +27,7 @@ #include <linux/slab.h> #include <linux/string_helpers.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <drm/drm_device.h> #include <drm/drm_util.h> diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c index 58c8161289fe..a75eede8bf8d 100644 --- a/drivers/gpu/drm/scheduler/sched_entity.c +++ b/drivers/gpu/drm/scheduler/sched_entity.c @@ -133,8 +133,10 @@ void drm_sched_entity_modify_sched(struct drm_sched_entity *entity, { WARN_ON(!num_sched_list || !sched_list); + spin_lock(&entity->rq_lock); entity->sched_list = sched_list; entity->num_sched_list = num_sched_list; + spin_unlock(&entity->rq_lock); } EXPORT_SYMBOL(drm_sched_entity_modify_sched); @@ -380,7 +382,7 @@ static void drm_sched_entity_wakeup(struct dma_fence *f, container_of(cb, struct drm_sched_entity, cb); drm_sched_entity_clear_dep(f, cb); - drm_sched_wakeup(entity->rq->sched, entity); + drm_sched_wakeup(entity->rq->sched); } /** @@ -597,6 +599,9 @@ void drm_sched_entity_push_job(struct drm_sched_job *sched_job) /* first job wakes up scheduler */ if (first) { + struct drm_gpu_scheduler *sched; + struct drm_sched_rq *rq; + /* Add the entity to the run queue */ spin_lock(&entity->rq_lock); if (entity->stopped) { @@ -606,13 +611,16 @@ void drm_sched_entity_push_job(struct drm_sched_job *sched_job) return; } - drm_sched_rq_add_entity(entity->rq, entity); + rq = entity->rq; + sched = rq->sched; + + drm_sched_rq_add_entity(rq, entity); spin_unlock(&entity->rq_lock); if (drm_sched_policy == DRM_SCHED_POLICY_FIFO) drm_sched_rq_update_fifo(entity, submit_ts); - drm_sched_wakeup(entity->rq->sched, entity); + drm_sched_wakeup(sched); } } EXPORT_SYMBOL(drm_sched_entity_push_job); diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c index ab53ab486fe6..6f27cab0b76d 100644 --- a/drivers/gpu/drm/scheduler/sched_main.c +++ b/drivers/gpu/drm/scheduler/sched_main.c @@ -1013,15 +1013,12 @@ EXPORT_SYMBOL(drm_sched_job_cleanup); /** * drm_sched_wakeup - Wake up the scheduler if it is ready to queue * @sched: scheduler instance - * @entity: the scheduler entity * * Wake up the scheduler if we can queue jobs. */ -void drm_sched_wakeup(struct drm_gpu_scheduler *sched, - struct drm_sched_entity *entity) +void drm_sched_wakeup(struct drm_gpu_scheduler *sched) { - if (drm_sched_can_queue(sched, entity)) - drm_sched_run_job_queue(sched); + drm_sched_run_job_queue(sched); } /** diff --git a/drivers/gpu/drm/udl/udl_transfer.c b/drivers/gpu/drm/udl/udl_transfer.c index 5ff1037a3453..62224992988f 100644 --- a/drivers/gpu/drm/udl/udl_transfer.c +++ b/drivers/gpu/drm/udl/udl_transfer.c @@ -7,7 +7,7 @@ * Copyright (C) 2009 Bernie Thompson <bernie@plugable.com> */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "udl_drv.h" #include "udl_proto.h" diff --git a/drivers/gpu/drm/vboxvideo/hgsmi_base.c b/drivers/gpu/drm/vboxvideo/hgsmi_base.c index 8c041d7ce4f1..87dccaecc3e5 100644 --- a/drivers/gpu/drm/vboxvideo/hgsmi_base.c +++ b/drivers/gpu/drm/vboxvideo/hgsmi_base.c @@ -139,7 +139,15 @@ int hgsmi_update_pointer_shape(struct gen_pool *ctx, u32 flags, flags |= VBOX_MOUSE_POINTER_VISIBLE; } - p = hgsmi_buffer_alloc(ctx, sizeof(*p) + pixel_len, HGSMI_CH_VBVA, + /* + * The 4 extra bytes come from switching struct vbva_mouse_pointer_shape + * from having a 4 bytes fixed array at the end to using a proper VLA + * at the end. These 4 extra bytes were not subtracted from sizeof(*p) + * before the switch to the VLA, so this way the behavior is unchanged. + * Chances are these 4 extra bytes are not necessary but they are kept + * to avoid regressions. + */ + p = hgsmi_buffer_alloc(ctx, sizeof(*p) + pixel_len + 4, HGSMI_CH_VBVA, VBVA_MOUSE_POINTER_SHAPE); if (!p) return -ENOMEM; diff --git a/drivers/gpu/drm/vboxvideo/vboxvideo.h b/drivers/gpu/drm/vboxvideo/vboxvideo.h index f60d82504da0..79ec8481de0e 100644 --- a/drivers/gpu/drm/vboxvideo/vboxvideo.h +++ b/drivers/gpu/drm/vboxvideo/vboxvideo.h @@ -351,10 +351,8 @@ struct vbva_mouse_pointer_shape { * Bytes in the gap between the AND and the XOR mask are undefined. * XOR mask scanlines have no gap between them and size of XOR mask is: * xor_len = width * 4 * height. - * - * Preallocate 4 bytes for accessing actual data as p->data. */ - u8 data[4]; + u8 data[]; } __packed; /* pointer is visible */ diff --git a/drivers/gpu/drm/xe/regs/xe_gt_regs.h b/drivers/gpu/drm/xe/regs/xe_gt_regs.h index 660ff42e45a6..ac9c437e103d 100644 --- a/drivers/gpu/drm/xe/regs/xe_gt_regs.h +++ b/drivers/gpu/drm/xe/regs/xe_gt_regs.h @@ -169,6 +169,8 @@ #define XEHP_SLICE_COMMON_ECO_CHICKEN1 XE_REG_MCR(0x731c, XE_REG_OPTION_MASKED) #define MSC_MSAA_REODER_BUF_BYPASS_DISABLE REG_BIT(14) +#define XE2LPM_CCCHKNREG1 XE_REG(0x82a8) + #define VF_PREEMPTION XE_REG(0x83a4, XE_REG_OPTION_MASKED) #define PREEMPTION_VERTEX_COUNT REG_GENMASK(15, 0) @@ -378,6 +380,9 @@ #define L3SQCREG3 XE_REG_MCR(0xb108) #define COMPPWOVERFETCHEN REG_BIT(28) +#define SCRATCH3_LBCF XE_REG_MCR(0xb154) +#define RWFLUSHALLEN REG_BIT(17) + #define XEHP_L3SQCREG5 XE_REG_MCR(0xb158) #define L3_PWM_TIMER_INIT_VAL_MASK REG_GENMASK(9, 0) @@ -391,6 +396,12 @@ #define SCRATCH1LPFC XE_REG(0xb474) #define EN_L3_RW_CCS_CACHE_FLUSH REG_BIT(0) +#define XE2LPM_L3SQCREG2 XE_REG_MCR(0xb604) + +#define XE2LPM_L3SQCREG3 XE_REG_MCR(0xb608) + +#define XE2LPM_SCRATCH3_LBCF XE_REG_MCR(0xb654) + #define XE2LPM_L3SQCREG5 XE_REG_MCR(0xb658) #define XE2_TDF_CTRL XE_REG(0xb418) diff --git a/drivers/gpu/drm/xe/xe_bb.c b/drivers/gpu/drm/xe/xe_bb.c index a13e0b3a169e..ef777dbdf4ec 100644 --- a/drivers/gpu/drm/xe/xe_bb.c +++ b/drivers/gpu/drm/xe/xe_bb.c @@ -65,7 +65,8 @@ __xe_bb_create_job(struct xe_exec_queue *q, struct xe_bb *bb, u64 *addr) { u32 size = drm_suballoc_size(bb->bo); - bb->cs[bb->len++] = MI_BATCH_BUFFER_END; + if (bb->len == 0 || bb->cs[bb->len - 1] != MI_BATCH_BUFFER_END) + bb->cs[bb->len++] = MI_BATCH_BUFFER_END; xe_gt_assert(q->gt, bb->len * 4 + bb_prefetch(q->gt) <= size); diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c index 06911e9a3bf5..e5f51fd23c65 100644 --- a/drivers/gpu/drm/xe/xe_bo.c +++ b/drivers/gpu/drm/xe/xe_bo.c @@ -680,8 +680,8 @@ static int xe_bo_move(struct ttm_buffer_object *ttm_bo, bool evict, tt_has_data = ttm && (ttm_tt_is_populated(ttm) || (ttm->page_flags & TTM_TT_FLAG_SWAPPED)); - move_lacks_source = handle_system_ccs ? (!bo->ccs_cleared) : - (!mem_type_is_vram(old_mem_type) && !tt_has_data); + move_lacks_source = !old_mem || (handle_system_ccs ? (!bo->ccs_cleared) : + (!mem_type_is_vram(old_mem_type) && !tt_has_data)); needs_clear = (ttm && ttm->page_flags & TTM_TT_FLAG_ZERO_ALLOC) || (!ttm && ttm_bo->type == ttm_bo_type_device); @@ -2320,6 +2320,20 @@ void xe_bo_put_commit(struct llist_head *deferred) drm_gem_object_free(&bo->ttm.base.refcount); } +void xe_bo_put(struct xe_bo *bo) +{ + might_sleep(); + if (bo) { +#ifdef CONFIG_PROC_FS + if (bo->client) + might_lock(&bo->client->bos_lock); +#endif + if (bo->ggtt_node && bo->ggtt_node->ggtt) + might_lock(&bo->ggtt_node->ggtt->lock); + drm_gem_object_put(&bo->ttm.base); + } +} + /** * xe_bo_dumb_create - Create a dumb bo as backing for a fb * @file_priv: ... diff --git a/drivers/gpu/drm/xe/xe_bo.h b/drivers/gpu/drm/xe/xe_bo.h index dbfb3209615d..6e4be52306df 100644 --- a/drivers/gpu/drm/xe/xe_bo.h +++ b/drivers/gpu/drm/xe/xe_bo.h @@ -126,11 +126,7 @@ static inline struct xe_bo *xe_bo_get(struct xe_bo *bo) return bo; } -static inline void xe_bo_put(struct xe_bo *bo) -{ - if (bo) - drm_gem_object_put(&bo->ttm.base); -} +void xe_bo_put(struct xe_bo *bo); static inline void __xe_bo_unset_bulk_move(struct xe_bo *bo) { diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c index 70d4e4d46c3c..5a63d135ba96 100644 --- a/drivers/gpu/drm/xe/xe_device.c +++ b/drivers/gpu/drm/xe/xe_device.c @@ -171,10 +171,8 @@ static void xe_file_close(struct drm_device *dev, struct drm_file *file) xe_exec_queue_kill(q); xe_exec_queue_put(q); } - mutex_lock(&xef->vm.lock); xa_for_each(&xef->vm.xa, idx, vm) xe_vm_close_and_put(vm); - mutex_unlock(&xef->vm.lock); xe_file_put(xef); @@ -298,6 +296,9 @@ static void xe_device_destroy(struct drm_device *dev, void *dummy) if (xe->unordered_wq) destroy_workqueue(xe->unordered_wq); + if (xe->destroy_wq) + destroy_workqueue(xe->destroy_wq); + ttm_device_fini(&xe->ttm); } @@ -336,9 +337,7 @@ struct xe_device *xe_device_create(struct pci_dev *pdev, init_waitqueue_head(&xe->ufence_wq); - err = drmm_mutex_init(&xe->drm, &xe->usm.lock); - if (err) - goto err; + init_rwsem(&xe->usm.lock); xa_init_flags(&xe->usm.asid_to_vm, XA_FLAGS_ALLOC); @@ -363,8 +362,9 @@ struct xe_device *xe_device_create(struct pci_dev *pdev, xe->preempt_fence_wq = alloc_ordered_workqueue("xe-preempt-fence-wq", 0); xe->ordered_wq = alloc_ordered_workqueue("xe-ordered-wq", 0); xe->unordered_wq = alloc_workqueue("xe-unordered-wq", 0, 0); + xe->destroy_wq = alloc_workqueue("xe-destroy-wq", 0, 0); if (!xe->ordered_wq || !xe->unordered_wq || - !xe->preempt_fence_wq) { + !xe->preempt_fence_wq || !xe->destroy_wq) { /* * Cleanup done in xe_device_destroy via * drmm_add_action_or_reset register above diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h index ec7eb7811126..09d731a9125c 100644 --- a/drivers/gpu/drm/xe/xe_device_types.h +++ b/drivers/gpu/drm/xe/xe_device_types.h @@ -369,7 +369,7 @@ struct xe_device { /** @usm.next_asid: next ASID, used to cyclical alloc asids */ u32 next_asid; /** @usm.lock: protects UM state */ - struct mutex lock; + struct rw_semaphore lock; } usm; /** @pinned: pinned BO state */ @@ -396,6 +396,9 @@ struct xe_device { /** @unordered_wq: used to serialize unordered work, mostly display */ struct workqueue_struct *unordered_wq; + /** @destroy_wq: used to serialize user destroy work, like queue */ + struct workqueue_struct *destroy_wq; + /** @tiles: device tiles */ struct xe_tile tiles[XE_MAX_TILES_PER_DEVICE]; @@ -567,15 +570,23 @@ struct xe_file { struct { /** @vm.xe: xarray to store VMs */ struct xarray xa; - /** @vm.lock: protects file VM state */ + /** + * @vm.lock: Protects VM lookup + reference and removal a from + * file xarray. Not an intended to be an outer lock which does + * thing while being held. + */ struct mutex lock; } vm; /** @exec_queue: Submission exec queue state for file */ struct { - /** @exec_queue.xe: xarray to store engines */ + /** @exec_queue.xa: xarray to store exece queues */ struct xarray xa; - /** @exec_queue.lock: protects file engine state */ + /** + * @exec_queue.lock: Protects exec queue lookup + reference and + * removal a frommfile xarray. Not an intended to be an outer + * lock which does thing while being held. + */ struct mutex lock; } exec_queue; diff --git a/drivers/gpu/drm/xe/xe_drm_client.c b/drivers/gpu/drm/xe/xe_drm_client.c index 95a05c5bc897..fb52a23e28f8 100644 --- a/drivers/gpu/drm/xe/xe_drm_client.c +++ b/drivers/gpu/drm/xe/xe_drm_client.c @@ -168,15 +168,10 @@ static void bo_meminfo(struct xe_bo *bo, struct drm_memory_stats stats[TTM_NUM_MEM_TYPES]) { u64 sz = bo->size; - u32 mem_type; + u32 mem_type = bo->ttm.resource->mem_type; xe_bo_assert_held(bo); - if (bo->placement.placement) - mem_type = bo->placement.placement->mem_type; - else - mem_type = XE_PL_TT; - if (drm_gem_object_is_shared_for_memory_stats(&bo->ttm.base)) stats[mem_type].shared += sz; else @@ -288,8 +283,15 @@ static void show_run_ticks(struct drm_printer *p, struct drm_file *file) /* Accumulate all the exec queues from this client */ mutex_lock(&xef->exec_queue.lock); - xa_for_each(&xef->exec_queue.xa, i, q) + xa_for_each(&xef->exec_queue.xa, i, q) { + xe_exec_queue_get(q); + mutex_unlock(&xef->exec_queue.lock); + xe_exec_queue_update_run_ticks(q); + + mutex_lock(&xef->exec_queue.lock); + xe_exec_queue_put(q); + } mutex_unlock(&xef->exec_queue.lock); /* Get the total GPU cycles */ diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c index 7f28b7fc68d5..d098d2dd1b2d 100644 --- a/drivers/gpu/drm/xe/xe_exec_queue.c +++ b/drivers/gpu/drm/xe/xe_exec_queue.c @@ -635,14 +635,14 @@ int xe_exec_queue_create_ioctl(struct drm_device *dev, void *data, } } - mutex_lock(&xef->exec_queue.lock); + q->xef = xe_file_get(xef); + + /* user id alloc must always be last in ioctl to prevent UAF */ err = xa_alloc(&xef->exec_queue.xa, &id, q, xa_limit_32b, GFP_KERNEL); - mutex_unlock(&xef->exec_queue.lock); if (err) goto kill_exec_queue; args->exec_queue_id = id; - q->xef = xe_file_get(xef); return 0; diff --git a/drivers/gpu/drm/xe/xe_gpu_scheduler.c b/drivers/gpu/drm/xe/xe_gpu_scheduler.c index c518d1d16d82..50361b4638f9 100644 --- a/drivers/gpu/drm/xe/xe_gpu_scheduler.c +++ b/drivers/gpu/drm/xe/xe_gpu_scheduler.c @@ -90,6 +90,11 @@ void xe_sched_submission_stop(struct xe_gpu_scheduler *sched) cancel_work_sync(&sched->work_process_msg); } +void xe_sched_submission_resume_tdr(struct xe_gpu_scheduler *sched) +{ + drm_sched_resume_timeout(&sched->base, sched->base.timeout); +} + void xe_sched_add_msg(struct xe_gpu_scheduler *sched, struct xe_sched_msg *msg) { diff --git a/drivers/gpu/drm/xe/xe_gpu_scheduler.h b/drivers/gpu/drm/xe/xe_gpu_scheduler.h index cee9c6809fc0..5ad5629a6c60 100644 --- a/drivers/gpu/drm/xe/xe_gpu_scheduler.h +++ b/drivers/gpu/drm/xe/xe_gpu_scheduler.h @@ -22,6 +22,8 @@ void xe_sched_fini(struct xe_gpu_scheduler *sched); void xe_sched_submission_start(struct xe_gpu_scheduler *sched); void xe_sched_submission_stop(struct xe_gpu_scheduler *sched); +void xe_sched_submission_resume_tdr(struct xe_gpu_scheduler *sched); + void xe_sched_add_msg(struct xe_gpu_scheduler *sched, struct xe_sched_msg *msg); void xe_sched_add_msg_locked(struct xe_gpu_scheduler *sched, diff --git a/drivers/gpu/drm/xe/xe_gt_freq.c b/drivers/gpu/drm/xe/xe_gt_freq.c index 68a5778b4319..ab76973f3e1e 100644 --- a/drivers/gpu/drm/xe/xe_gt_freq.c +++ b/drivers/gpu/drm/xe/xe_gt_freq.c @@ -237,11 +237,11 @@ int xe_gt_freq_init(struct xe_gt *gt) if (!gt->freq) return -ENOMEM; - err = devm_add_action(xe->drm.dev, freq_fini, gt->freq); + err = sysfs_create_files(gt->freq, freq_attrs); if (err) return err; - err = sysfs_create_files(gt->freq, freq_attrs); + err = devm_add_action_or_reset(xe->drm.dev, freq_fini, gt->freq); if (err) return err; diff --git a/drivers/gpu/drm/xe/xe_gt_mcr.c b/drivers/gpu/drm/xe/xe_gt_mcr.c index 7d7bd0be6233..c834f64b0178 100644 --- a/drivers/gpu/drm/xe/xe_gt_mcr.c +++ b/drivers/gpu/drm/xe/xe_gt_mcr.c @@ -439,7 +439,7 @@ void xe_gt_mcr_init(struct xe_gt *gt) if (gt->info.type == XE_GT_TYPE_MEDIA) { drm_WARN_ON(&xe->drm, MEDIA_VER(xe) < 13); - if (MEDIA_VER(xe) >= 20) { + if (MEDIA_VERx100(xe) >= 1301) { gt->steering[OADDRM].ranges = xe2lpm_gpmxmt_steering_table; gt->steering[INSTANCE0].ranges = xe2lpm_instance0_steering_table; } else { diff --git a/drivers/gpu/drm/xe/xe_gt_pagefault.c b/drivers/gpu/drm/xe/xe_gt_pagefault.c index 730eec07795e..79c426dc2505 100644 --- a/drivers/gpu/drm/xe/xe_gt_pagefault.c +++ b/drivers/gpu/drm/xe/xe_gt_pagefault.c @@ -185,6 +185,21 @@ unlock_dma_resv: return err; } +static struct xe_vm *asid_to_vm(struct xe_device *xe, u32 asid) +{ + struct xe_vm *vm; + + down_read(&xe->usm.lock); + vm = xa_load(&xe->usm.asid_to_vm, asid); + if (vm && xe_vm_in_fault_mode(vm)) + xe_vm_get(vm); + else + vm = ERR_PTR(-EINVAL); + up_read(&xe->usm.lock); + + return vm; +} + static int handle_pagefault(struct xe_gt *gt, struct pagefault *pf) { struct xe_device *xe = gt_to_xe(gt); @@ -197,21 +212,20 @@ static int handle_pagefault(struct xe_gt *gt, struct pagefault *pf) if (pf->trva_fault) return -EFAULT; - /* ASID to VM */ - mutex_lock(&xe->usm.lock); - vm = xa_load(&xe->usm.asid_to_vm, pf->asid); - if (vm && xe_vm_in_fault_mode(vm)) - xe_vm_get(vm); - else - vm = NULL; - mutex_unlock(&xe->usm.lock); - if (!vm) - return -EINVAL; + vm = asid_to_vm(xe, pf->asid); + if (IS_ERR(vm)) + return PTR_ERR(vm); /* * TODO: Change to read lock? Using write lock for simplicity. */ down_write(&vm->lock); + + if (xe_vm_is_closed(vm)) { + err = -ENOENT; + goto unlock_vm; + } + vma = lookup_vma(vm, pf->page_addr); if (!vma) { err = -EINVAL; @@ -542,14 +556,9 @@ static int handle_acc(struct xe_gt *gt, struct acc *acc) if (acc->access_type != ACC_TRIGGER) return -EINVAL; - /* ASID to VM */ - mutex_lock(&xe->usm.lock); - vm = xa_load(&xe->usm.asid_to_vm, acc->asid); - if (vm) - xe_vm_get(vm); - mutex_unlock(&xe->usm.lock); - if (!vm || !xe_vm_in_fault_mode(vm)) - return -EINVAL; + vm = asid_to_vm(xe, acc->asid); + if (IS_ERR(vm)) + return PTR_ERR(vm); down_read(&vm->lock); diff --git a/drivers/gpu/drm/xe/xe_gt_sysfs.c b/drivers/gpu/drm/xe/xe_gt_sysfs.c index a05c3699e8b9..ec2b8246204b 100644 --- a/drivers/gpu/drm/xe/xe_gt_sysfs.c +++ b/drivers/gpu/drm/xe/xe_gt_sysfs.c @@ -51,5 +51,5 @@ int xe_gt_sysfs_init(struct xe_gt *gt) gt->sysfs = &kg->base; - return devm_add_action(xe->drm.dev, gt_sysfs_fini, gt); + return devm_add_action_or_reset(xe->drm.dev, gt_sysfs_fini, gt); } diff --git a/drivers/gpu/drm/xe/xe_guc.h b/drivers/gpu/drm/xe/xe_guc.h index c3e6b51f7a09..42116b167c98 100644 --- a/drivers/gpu/drm/xe/xe_guc.h +++ b/drivers/gpu/drm/xe/xe_guc.h @@ -18,8 +18,10 @@ */ #define MAKE_GUC_VER(maj, min, pat) (((maj) << 16) | ((min) << 8) | (pat)) #define MAKE_GUC_VER_STRUCT(ver) MAKE_GUC_VER((ver).major, (ver).minor, (ver).patch) -#define GUC_SUBMIT_VER(guc) MAKE_VER_STRUCT((guc)->fw.versions.found[XE_UC_FW_VER_COMPATIBILITY]) -#define GUC_FIRMWARE_VER(guc) MAKE_VER_STRUCT((guc)->fw.versions.found[XE_UC_FW_VER_RELEASE]) +#define GUC_SUBMIT_VER(guc) \ + MAKE_GUC_VER_STRUCT((guc)->fw.versions.found[XE_UC_FW_VER_COMPATIBILITY]) +#define GUC_FIRMWARE_VER(guc) \ + MAKE_GUC_VER_STRUCT((guc)->fw.versions.found[XE_UC_FW_VER_RELEASE]) struct drm_printer; diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c index fbbe6a487bbb..80062e1d3f66 100644 --- a/drivers/gpu/drm/xe/xe_guc_submit.c +++ b/drivers/gpu/drm/xe/xe_guc_submit.c @@ -276,10 +276,26 @@ static struct workqueue_struct *get_submit_wq(struct xe_guc *guc) } #endif +static void xe_guc_submit_fini(struct xe_guc *guc) +{ + struct xe_device *xe = guc_to_xe(guc); + struct xe_gt *gt = guc_to_gt(guc); + int ret; + + ret = wait_event_timeout(guc->submission_state.fini_wq, + xa_empty(&guc->submission_state.exec_queue_lookup), + HZ * 5); + + drain_workqueue(xe->destroy_wq); + + xe_gt_assert(gt, ret); +} + static void guc_submit_fini(struct drm_device *drm, void *arg) { struct xe_guc *guc = arg; + xe_guc_submit_fini(guc); xa_destroy(&guc->submission_state.exec_queue_lookup); free_submit_wq(guc); } @@ -290,9 +306,15 @@ static void guc_submit_wedged_fini(void *arg) struct xe_exec_queue *q; unsigned long index; - xa_for_each(&guc->submission_state.exec_queue_lookup, index, q) - if (exec_queue_wedged(q)) + mutex_lock(&guc->submission_state.lock); + xa_for_each(&guc->submission_state.exec_queue_lookup, index, q) { + if (exec_queue_wedged(q)) { + mutex_unlock(&guc->submission_state.lock); xe_exec_queue_put(q); + mutex_lock(&guc->submission_state.lock); + } + } + mutex_unlock(&guc->submission_state.lock); } static const struct xe_exec_queue_ops guc_exec_queue_ops; @@ -345,6 +367,8 @@ int xe_guc_submit_init(struct xe_guc *guc, unsigned int num_ids) xa_init(&guc->submission_state.exec_queue_lookup); + init_waitqueue_head(&guc->submission_state.fini_wq); + primelockdep(guc); return drmm_add_action_or_reset(&xe->drm, guc_submit_fini, guc); @@ -361,6 +385,9 @@ static void __release_guc_id(struct xe_guc *guc, struct xe_exec_queue *q, u32 xa xe_guc_id_mgr_release_locked(&guc->submission_state.idm, q->guc->id, q->width); + + if (xa_empty(&guc->submission_state.exec_queue_lookup)) + wake_up(&guc->submission_state.fini_wq); } static int alloc_guc_id(struct xe_guc *guc, struct xe_exec_queue *q) @@ -1268,13 +1295,16 @@ static void __guc_exec_queue_fini_async(struct work_struct *w) static void guc_exec_queue_fini_async(struct xe_exec_queue *q) { + struct xe_guc *guc = exec_queue_to_guc(q); + struct xe_device *xe = guc_to_xe(guc); + INIT_WORK(&q->guc->fini_async, __guc_exec_queue_fini_async); /* We must block on kernel engines so slabs are empty on driver unload */ if (q->flags & EXEC_QUEUE_FLAG_PERMANENT || exec_queue_wedged(q)) __guc_exec_queue_fini_async(&q->guc->fini_async); else - queue_work(system_wq, &q->guc->fini_async); + queue_work(xe->destroy_wq, &q->guc->fini_async); } static void __guc_exec_queue_fini(struct xe_guc *guc, struct xe_exec_queue *q) @@ -1796,6 +1826,7 @@ static void guc_exec_queue_start(struct xe_exec_queue *q) } xe_sched_submission_start(sched); + xe_sched_submission_resume_tdr(sched); } int xe_guc_submit_start(struct xe_guc *guc) diff --git a/drivers/gpu/drm/xe/xe_guc_types.h b/drivers/gpu/drm/xe/xe_guc_types.h index 546ac6350a31..69046f698271 100644 --- a/drivers/gpu/drm/xe/xe_guc_types.h +++ b/drivers/gpu/drm/xe/xe_guc_types.h @@ -81,6 +81,8 @@ struct xe_guc { #endif /** @submission_state.enabled: submission is enabled */ bool enabled; + /** @submission_state.fini_wq: submit fini wait queue */ + wait_queue_head_t fini_wq; } submission_state; /** @hwconfig: Hardware config state */ struct { diff --git a/drivers/gpu/drm/xe/xe_oa.c b/drivers/gpu/drm/xe/xe_oa.c index eae38a49ee8e..2804f14f8f29 100644 --- a/drivers/gpu/drm/xe/xe_oa.c +++ b/drivers/gpu/drm/xe/xe_oa.c @@ -709,8 +709,7 @@ static int xe_oa_configure_oar_context(struct xe_oa_stream *stream, bool enable) { RING_CONTEXT_CONTROL(stream->hwe->mmio_base), regs_offset + CTX_CONTEXT_CONTROL, - _MASKED_FIELD(CTX_CTRL_OAC_CONTEXT_ENABLE, - enable ? CTX_CTRL_OAC_CONTEXT_ENABLE : 0) + _MASKED_BIT_ENABLE(CTX_CTRL_OAC_CONTEXT_ENABLE), }, }; struct xe_oa_reg reg_lri = { OAR_OACONTROL, oacontrol }; @@ -742,10 +741,8 @@ static int xe_oa_configure_oac_context(struct xe_oa_stream *stream, bool enable) { RING_CONTEXT_CONTROL(stream->hwe->mmio_base), regs_offset + CTX_CONTEXT_CONTROL, - _MASKED_FIELD(CTX_CTRL_OAC_CONTEXT_ENABLE, - enable ? CTX_CTRL_OAC_CONTEXT_ENABLE : 0) | - _MASKED_FIELD(CTX_CTRL_RUN_ALONE, - enable ? CTX_CTRL_RUN_ALONE : 0), + _MASKED_BIT_ENABLE(CTX_CTRL_OAC_CONTEXT_ENABLE) | + _MASKED_FIELD(CTX_CTRL_RUN_ALONE, enable ? CTX_CTRL_RUN_ALONE : 0), }, }; struct xe_oa_reg reg_lri = { OAC_OACONTROL, oacontrol }; diff --git a/drivers/gpu/drm/xe/xe_pci.c b/drivers/gpu/drm/xe/xe_pci.c index 937c3e064f0d..5e962e72c97e 100644 --- a/drivers/gpu/drm/xe/xe_pci.c +++ b/drivers/gpu/drm/xe/xe_pci.c @@ -924,6 +924,8 @@ static int xe_pci_resume(struct device *dev) if (err) return err; + pci_restore_state(pdev); + err = pci_enable_device(pdev); if (err) return err; diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c index d6353e8969f0..f27f579f4d85 100644 --- a/drivers/gpu/drm/xe/xe_pt.c +++ b/drivers/gpu/drm/xe/xe_pt.c @@ -2188,5 +2188,5 @@ void xe_pt_update_ops_abort(struct xe_tile *tile, struct xe_vma_ops *vops) pt_op->num_entries); } - xe_bo_put_commit(&vops->pt_update_ops[tile->id].deferred); + xe_pt_update_ops_fini(tile, vops); } diff --git a/drivers/gpu/drm/xe/xe_tuning.c b/drivers/gpu/drm/xe/xe_tuning.c index faa1bf42e50e..0d5e04158917 100644 --- a/drivers/gpu/drm/xe/xe_tuning.c +++ b/drivers/gpu/drm/xe/xe_tuning.c @@ -42,20 +42,48 @@ static const struct xe_rtp_entry_sr gt_tunings[] = { XE_RTP_ACTIONS(CLR(CCCHKNREG1, ENCOMPPERFFIX), SET(CCCHKNREG1, L3CMPCTRL)) }, + { XE_RTP_NAME("Tuning: Compression Overfetch - media"), + XE_RTP_RULES(MEDIA_VERSION(2000)), + XE_RTP_ACTIONS(CLR(XE2LPM_CCCHKNREG1, ENCOMPPERFFIX), + SET(XE2LPM_CCCHKNREG1, L3CMPCTRL)) + }, { XE_RTP_NAME("Tuning: Enable compressible partial write overfetch in L3"), XE_RTP_RULES(GRAPHICS_VERSION_RANGE(2001, XE_RTP_END_VERSION_UNDEFINED)), XE_RTP_ACTIONS(SET(L3SQCREG3, COMPPWOVERFETCHEN)) }, + { XE_RTP_NAME("Tuning: Enable compressible partial write overfetch in L3 - media"), + XE_RTP_RULES(MEDIA_VERSION(2000)), + XE_RTP_ACTIONS(SET(XE2LPM_L3SQCREG3, COMPPWOVERFETCHEN)) + }, { XE_RTP_NAME("Tuning: L2 Overfetch Compressible Only"), XE_RTP_RULES(GRAPHICS_VERSION_RANGE(2001, XE_RTP_END_VERSION_UNDEFINED)), XE_RTP_ACTIONS(SET(L3SQCREG2, COMPMEMRD256BOVRFETCHEN)) }, + { XE_RTP_NAME("Tuning: L2 Overfetch Compressible Only - media"), + XE_RTP_RULES(MEDIA_VERSION(2000)), + XE_RTP_ACTIONS(SET(XE2LPM_L3SQCREG2, + COMPMEMRD256BOVRFETCHEN)) + }, { XE_RTP_NAME("Tuning: Stateless compression control"), XE_RTP_RULES(GRAPHICS_VERSION_RANGE(2001, XE_RTP_END_VERSION_UNDEFINED)), XE_RTP_ACTIONS(FIELD_SET(STATELESS_COMPRESSION_CTRL, UNIFIED_COMPRESSION_FORMAT, REG_FIELD_PREP(UNIFIED_COMPRESSION_FORMAT, 0))) }, + { XE_RTP_NAME("Tuning: Stateless compression control - media"), + XE_RTP_RULES(MEDIA_VERSION_RANGE(1301, 2000)), + XE_RTP_ACTIONS(FIELD_SET(STATELESS_COMPRESSION_CTRL, UNIFIED_COMPRESSION_FORMAT, + REG_FIELD_PREP(UNIFIED_COMPRESSION_FORMAT, 0))) + }, + { XE_RTP_NAME("Tuning: L3 RW flush all Cache"), + XE_RTP_RULES(GRAPHICS_VERSION(2004)), + XE_RTP_ACTIONS(SET(SCRATCH3_LBCF, RWFLUSHALLEN)) + }, + { XE_RTP_NAME("Tuning: L3 RW flush all cache - media"), + XE_RTP_RULES(MEDIA_VERSION(2000)), + XE_RTP_ACTIONS(SET(XE2LPM_SCRATCH3_LBCF, RWFLUSHALLEN)) + }, + {} }; diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c index 7acd5fc9d032..ce9dca4d4e87 100644 --- a/drivers/gpu/drm/xe/xe_vm.c +++ b/drivers/gpu/drm/xe/xe_vm.c @@ -1613,7 +1613,7 @@ void xe_vm_close_and_put(struct xe_vm *vm) up_write(&vm->lock); - mutex_lock(&xe->usm.lock); + down_write(&xe->usm.lock); if (vm->usm.asid) { void *lookup; @@ -1623,7 +1623,7 @@ void xe_vm_close_and_put(struct xe_vm *vm) lookup = xa_erase(&xe->usm.asid_to_vm, vm->usm.asid); xe_assert(xe, lookup == vm); } - mutex_unlock(&xe->usm.lock); + up_write(&xe->usm.lock); for_each_tile(tile, xe, id) xe_range_fence_tree_fini(&vm->rftree[id]); @@ -1765,25 +1765,18 @@ int xe_vm_create_ioctl(struct drm_device *dev, void *data, if (IS_ERR(vm)) return PTR_ERR(vm); - mutex_lock(&xef->vm.lock); - err = xa_alloc(&xef->vm.xa, &id, vm, xa_limit_32b, GFP_KERNEL); - mutex_unlock(&xef->vm.lock); - if (err) - goto err_close_and_put; - if (xe->info.has_asid) { - mutex_lock(&xe->usm.lock); + down_write(&xe->usm.lock); err = xa_alloc_cyclic(&xe->usm.asid_to_vm, &asid, vm, XA_LIMIT(1, XE_MAX_ASID - 1), &xe->usm.next_asid, GFP_KERNEL); - mutex_unlock(&xe->usm.lock); + up_write(&xe->usm.lock); if (err < 0) - goto err_free_id; + goto err_close_and_put; vm->usm.asid = asid; } - args->vm_id = id; vm->xef = xe_file_get(xef); /* Record BO memory for VM pagetable created against client */ @@ -1796,12 +1789,15 @@ int xe_vm_create_ioctl(struct drm_device *dev, void *data, args->reserved[0] = xe_bo_main_addr(vm->pt_root[0]->bo, XE_PAGE_SIZE); #endif + /* user id alloc must always be last in ioctl to prevent UAF */ + err = xa_alloc(&xef->vm.xa, &id, vm, xa_limit_32b, GFP_KERNEL); + if (err) + goto err_close_and_put; + + args->vm_id = id; + return 0; -err_free_id: - mutex_lock(&xef->vm.lock); - xa_erase(&xef->vm.xa, id); - mutex_unlock(&xef->vm.lock); err_close_and_put: xe_vm_close_and_put(vm); diff --git a/drivers/gpu/drm/xe/xe_vram.c b/drivers/gpu/drm/xe/xe_vram.c index 5bcd59190353..80ba2fc78837 100644 --- a/drivers/gpu/drm/xe/xe_vram.c +++ b/drivers/gpu/drm/xe/xe_vram.c @@ -182,6 +182,7 @@ static inline u64 get_flat_ccs_offset(struct xe_gt *gt, u64 tile_size) offset = offset_hi << 32; /* HW view bits 39:32 */ offset |= offset_lo << 6; /* HW view bits 31:6 */ offset *= num_enabled; /* convert to SW view */ + offset = round_up(offset, SZ_128K); /* SW must round up to nearest 128K */ /* We don't expect any holes */ xe_assert_msg(xe, offset == (xe_mmio_read64_2x32(gt, GSMBASE) - ccs_size), diff --git a/drivers/greybus/es2.c b/drivers/greybus/es2.c index 69e46b1dff1f..7630a36ecf81 100644 --- a/drivers/greybus/es2.c +++ b/drivers/greybus/es2.c @@ -12,7 +12,7 @@ #include <linux/debugfs.h> #include <linux/list.h> #include <linux/greybus.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "arpc.h" #include "greybus_trace.h" diff --git a/drivers/greybus/gb-beagleplay.c b/drivers/greybus/gb-beagleplay.c index 3a1ade84737c..473ac3f2d382 100644 --- a/drivers/greybus/gb-beagleplay.c +++ b/drivers/greybus/gb-beagleplay.c @@ -6,7 +6,7 @@ * Copyright (c) 2023 BeagleBoard.org Foundation */ -#include <asm-generic/unaligned.h> +#include <linux/unaligned.h> #include <linux/crc32.h> #include <linux/gpio/consumer.h> #include <linux/firmware.h> diff --git a/drivers/hid/bpf/hid_bpf_struct_ops.c b/drivers/hid/bpf/hid_bpf_struct_ops.c index cd696c59ba0f..702c22fae136 100644 --- a/drivers/hid/bpf/hid_bpf_struct_ops.c +++ b/drivers/hid/bpf/hid_bpf_struct_ops.c @@ -276,9 +276,23 @@ static int __hid_bpf_rdesc_fixup(struct hid_bpf_ctx *ctx) return 0; } +static int __hid_bpf_hw_request(struct hid_bpf_ctx *ctx, unsigned char reportnum, + enum hid_report_type rtype, enum hid_class_request reqtype, + u64 source) +{ + return 0; +} + +static int __hid_bpf_hw_output_report(struct hid_bpf_ctx *ctx, u64 source) +{ + return 0; +} + static struct hid_bpf_ops __bpf_hid_bpf_ops = { .hid_device_event = __hid_bpf_device_event, .hid_rdesc_fixup = __hid_bpf_rdesc_fixup, + .hid_hw_request = __hid_bpf_hw_request, + .hid_hw_output_report = __hid_bpf_hw_output_report, }; static struct bpf_struct_ops bpf_hid_bpf_ops = { diff --git a/drivers/hid/hid-alps.c b/drivers/hid/hid-alps.c index 669d769ea1dc..ba00f6e6324b 100644 --- a/drivers/hid/hid-alps.c +++ b/drivers/hid/hid-alps.c @@ -8,7 +8,7 @@ #include <linux/input.h> #include <linux/input/mt.h> #include <linux/module.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "hid-ids.h" /* ALPS Device Product ID */ diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index 30de92d0bf0f..612ee6ddfc8d 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -20,7 +20,7 @@ #include <linux/list.h> #include <linux/mm.h> #include <linux/spinlock.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <asm/byteorder.h> #include <linux/input.h> #include <linux/wait.h> diff --git a/drivers/hid/hid-generic.c b/drivers/hid/hid-generic.c index f9db991d3c5a..d2439399fb35 100644 --- a/drivers/hid/hid-generic.c +++ b/drivers/hid/hid-generic.c @@ -16,7 +16,7 @@ #include <linux/module.h> #include <linux/slab.h> #include <linux/kernel.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <asm/byteorder.h> #include <linux/hid.h> diff --git a/drivers/hid/hid-goodix-spi.c b/drivers/hid/hid-goodix-spi.c index 0e59663814dd..0f87bf9c67cf 100644 --- a/drivers/hid/hid-goodix-spi.c +++ b/drivers/hid/hid-goodix-spi.c @@ -4,7 +4,7 @@ * * Copyright (C) 2024 Godix, Inc. */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/delay.h> #include <linux/hid.h> #include <linux/interrupt.h> diff --git a/drivers/hid/hid-google-hammer.c b/drivers/hid/hid-google-hammer.c index 4e79fafeeafa..22683ec819aa 100644 --- a/drivers/hid/hid-google-hammer.c +++ b/drivers/hid/hid-google-hammer.c @@ -23,7 +23,7 @@ #include <linux/platform_data/cros_ec_proto.h> #include <linux/platform_device.h> #include <linux/pm_wakeup.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "hid-ids.h" #include "hid-vivaldi-common.h" diff --git a/drivers/hid/hid-kye.c b/drivers/hid/hid-kye.c index 32344331282f..bd96bfa7af70 100644 --- a/drivers/hid/hid-kye.c +++ b/drivers/hid/hid-kye.c @@ -8,7 +8,7 @@ * Copyright (c) 2023 David Yang */ -#include <asm-generic/unaligned.h> +#include <linux/unaligned.h> #include <linux/device.h> #include <linux/hid.h> #include <linux/module.h> diff --git a/drivers/hid/hid-letsketch.c b/drivers/hid/hid-letsketch.c index 229820fda960..8602c63ed9c6 100644 --- a/drivers/hid/hid-letsketch.c +++ b/drivers/hid/hid-letsketch.c @@ -41,7 +41,7 @@ #include <linux/timer.h> #include <linux/usb.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "hid-ids.h" diff --git a/drivers/hid/hid-logitech-dj.c b/drivers/hid/hid-logitech-dj.c index d9580bc3e19a..34fa71ceec2b 100644 --- a/drivers/hid/hid-logitech-dj.c +++ b/drivers/hid/hid-logitech-dj.c @@ -13,7 +13,7 @@ #include <linux/kfifo.h> #include <linux/delay.h> #include <linux/usb.h> /* For to_usb_interface for kvm extra intf check */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "hid-ids.h" #define DJ_MAX_PAIRED_DEVICES 7 diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c index 0e33fa0eb8db..cf7a6986cf20 100644 --- a/drivers/hid/hid-logitech-hidpp.c +++ b/drivers/hid/hid-logitech-hidpp.c @@ -23,7 +23,7 @@ #include <linux/workqueue.h> #include <linux/atomic.h> #include <linux/fixp-arith.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "usbhid/usbhid.h" #include "hid-ids.h" diff --git a/drivers/hid/hid-nintendo.c b/drivers/hid/hid-nintendo.c index 58cd0506e431..55153a2f7988 100644 --- a/drivers/hid/hid-nintendo.c +++ b/drivers/hid/hid-nintendo.c @@ -29,7 +29,7 @@ */ #include "hid-ids.h" -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/delay.h> #include <linux/device.h> #include <linux/kernel.h> diff --git a/drivers/hid/hid-playstation.c b/drivers/hid/hid-playstation.c index 0d90d7ee693c..1468fb11e39d 100644 --- a/drivers/hid/hid-playstation.c +++ b/drivers/hid/hid-playstation.c @@ -15,7 +15,7 @@ #include <linux/led-class-multicolor.h> #include <linux/module.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "hid-ids.h" diff --git a/drivers/hid/hid-sony.c b/drivers/hid/hid-sony.c index df29c614e490..d2486f3734f0 100644 --- a/drivers/hid/hid-sony.c +++ b/drivers/hid/hid-sony.c @@ -40,7 +40,7 @@ #include <linux/crc32.h> #include <linux/usb.h> #include <linux/timer.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "hid-ids.h" diff --git a/drivers/hid/hid-uclogic-params.c b/drivers/hid/hid-uclogic-params.c index 87fd4eb76c70..ef26c7defcf6 100644 --- a/drivers/hid/hid-uclogic-params.c +++ b/drivers/hid/hid-uclogic-params.c @@ -19,7 +19,7 @@ #include "hid-ids.h" #include <linux/ctype.h> #include <linux/string.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /** * uclogic_params_pen_inrange_to_str() - Convert a pen in-range reporting type diff --git a/drivers/hid/hid-uclogic-rdesc.c b/drivers/hid/hid-uclogic-rdesc.c index 964d17e08f26..9b9cbc2aae36 100644 --- a/drivers/hid/hid-uclogic-rdesc.c +++ b/drivers/hid/hid-uclogic-rdesc.c @@ -16,7 +16,7 @@ #include "hid-uclogic-rdesc.h" #include <linux/slab.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <kunit/visibility.h> /* Fixed WP4030U report descriptor */ diff --git a/drivers/hid/i2c-hid/i2c-hid-core.c b/drivers/hid/i2c-hid/i2c-hid-core.c index 2f8a9d3f1e86..be5d342d5d13 100644 --- a/drivers/hid/i2c-hid/i2c-hid-core.c +++ b/drivers/hid/i2c-hid/i2c-hid-core.c @@ -36,7 +36,7 @@ #include <linux/kernel.h> #include <linux/hid.h> #include <linux/mutex.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <drm/drm_panel.h> diff --git a/drivers/hid/surface-hid/surface_hid.c b/drivers/hid/surface-hid/surface_hid.c index 61e5814b0ad7..eae47e0d95ed 100644 --- a/drivers/hid/surface-hid/surface_hid.c +++ b/drivers/hid/surface-hid/surface_hid.c @@ -8,7 +8,7 @@ * Maximilian Luz <luzmaximilian@gmail.com> */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/hid.h> #include <linux/kernel.h> #include <linux/module.h> diff --git a/drivers/hid/surface-hid/surface_hid_core.c b/drivers/hid/surface-hid/surface_hid_core.c index a3e9cceddfac..6690c24f28f0 100644 --- a/drivers/hid/surface-hid/surface_hid_core.c +++ b/drivers/hid/surface-hid/surface_hid_core.c @@ -7,7 +7,7 @@ * Copyright (C) 2019-2021 Maximilian Luz <luzmaximilian@gmail.com> */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/hid.h> #include <linux/kernel.h> #include <linux/module.h> diff --git a/drivers/hid/surface-hid/surface_kbd.c b/drivers/hid/surface-hid/surface_kbd.c index 8c0cbb2deb11..383200d9121a 100644 --- a/drivers/hid/surface-hid/surface_kbd.c +++ b/drivers/hid/surface-hid/surface_kbd.c @@ -7,7 +7,7 @@ * Copyright (C) 2019-2021 Maximilian Luz <luzmaximilian@gmail.com> */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/hid.h> #include <linux/kernel.h> #include <linux/module.h> diff --git a/drivers/hid/usbhid/hid-core.c b/drivers/hid/usbhid/hid-core.c index cb687ea7325c..a9e85bdd4cc6 100644 --- a/drivers/hid/usbhid/hid-core.c +++ b/drivers/hid/usbhid/hid-core.c @@ -21,7 +21,7 @@ #include <linux/mutex.h> #include <linux/property.h> #include <linux/spinlock.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <asm/byteorder.h> #include <linux/input.h> #include <linux/wait.h> diff --git a/drivers/hid/wacom.h b/drivers/hid/wacom.h index 77c5fb26cd14..6f1443999d1d 100644 --- a/drivers/hid/wacom.h +++ b/drivers/hid/wacom.h @@ -89,7 +89,7 @@ #include <linux/usb/input.h> #include <linux/power_supply.h> #include <linux/timer.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /* * Version Information diff --git a/drivers/hwmon/adt7310.c b/drivers/hwmon/adt7310.c index 25281739aa3b..6a834a37bc65 100644 --- a/drivers/hwmon/adt7310.c +++ b/drivers/hwmon/adt7310.c @@ -10,7 +10,7 @@ #include <linux/init.h> #include <linux/regmap.h> #include <linux/spi/spi.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "adt7x10.h" diff --git a/drivers/hwmon/aquacomputer_d5next.c b/drivers/hwmon/aquacomputer_d5next.c index 8e55cd2f46f5..34cac27e4dde 100644 --- a/drivers/hwmon/aquacomputer_d5next.c +++ b/drivers/hwmon/aquacomputer_d5next.c @@ -22,7 +22,7 @@ #include <linux/module.h> #include <linux/mutex.h> #include <linux/seq_file.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define USB_VENDOR_ID_AQUACOMPUTER 0x0c70 #define USB_PRODUCT_ID_AQUAERO 0xf001 diff --git a/drivers/hwmon/asus-ec-sensors.c b/drivers/hwmon/asus-ec-sensors.c index ee396f21fac5..9555366aeaf0 100644 --- a/drivers/hwmon/asus-ec-sensors.c +++ b/drivers/hwmon/asus-ec-sensors.c @@ -34,7 +34,7 @@ #include <linux/sort.h> #include <linux/units.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> static char *mutex_path_override; diff --git a/drivers/hwmon/asus_rog_ryujin.c b/drivers/hwmon/asus_rog_ryujin.c index f8b20346a995..e5e93a20723c 100644 --- a/drivers/hwmon/asus_rog_ryujin.c +++ b/drivers/hwmon/asus_rog_ryujin.c @@ -11,7 +11,7 @@ #include <linux/jiffies.h> #include <linux/module.h> #include <linux/spinlock.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define DRIVER_NAME "asus_rog_ryujin" diff --git a/drivers/hwmon/dell-smm-hwmon.c b/drivers/hwmon/dell-smm-hwmon.c index f9b3a3030f13..f5bdf842040e 100644 --- a/drivers/hwmon/dell-smm-hwmon.c +++ b/drivers/hwmon/dell-smm-hwmon.c @@ -38,7 +38,7 @@ #include <linux/wmi.h> #include <linux/i8k.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define I8K_SMM_FN_STATUS 0x0025 #define I8K_SMM_POWER_STATUS 0x0069 diff --git a/drivers/hwmon/gigabyte_waterforce.c b/drivers/hwmon/gigabyte_waterforce.c index 8129d7b3ceaf..27487e215bdd 100644 --- a/drivers/hwmon/gigabyte_waterforce.c +++ b/drivers/hwmon/gigabyte_waterforce.c @@ -11,7 +11,7 @@ #include <linux/jiffies.h> #include <linux/module.h> #include <linux/spinlock.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define DRIVER_NAME "gigabyte_waterforce" diff --git a/drivers/hwmon/nzxt-kraken2.c b/drivers/hwmon/nzxt-kraken2.c index 7caf387eb144..ed38645a1dc2 100644 --- a/drivers/hwmon/nzxt-kraken2.c +++ b/drivers/hwmon/nzxt-kraken2.c @@ -9,7 +9,7 @@ * Copyright 2019-2021 Jonas Malaco <jonas@protocubo.io> */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/hid.h> #include <linux/hwmon.h> #include <linux/jiffies.h> diff --git a/drivers/hwmon/nzxt-kraken3.c b/drivers/hwmon/nzxt-kraken3.c index 00f3ac90a290..d00409bcab93 100644 --- a/drivers/hwmon/nzxt-kraken3.c +++ b/drivers/hwmon/nzxt-kraken3.c @@ -17,7 +17,7 @@ #include <linux/mutex.h> #include <linux/spinlock.h> #include <linux/wait.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define USB_VENDOR_ID_NZXT 0x1e71 #define USB_PRODUCT_ID_X53 0x2007 diff --git a/drivers/hwmon/nzxt-smart2.c b/drivers/hwmon/nzxt-smart2.c index df6fa72a6b59..c2d1173f42fe 100644 --- a/drivers/hwmon/nzxt-smart2.c +++ b/drivers/hwmon/nzxt-smart2.c @@ -14,7 +14,7 @@ #include <linux/wait.h> #include <asm/byteorder.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /* * The device has only 3 fan channels/connectors. But all HID reports have diff --git a/drivers/hwmon/occ/common.c b/drivers/hwmon/occ/common.c index dd690f700d49..9486db249c64 100644 --- a/drivers/hwmon/occ/common.c +++ b/drivers/hwmon/occ/common.c @@ -12,7 +12,7 @@ #include <linux/mutex.h> #include <linux/property.h> #include <linux/sysfs.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "common.h" diff --git a/drivers/hwmon/occ/p8_i2c.c b/drivers/hwmon/occ/p8_i2c.c index 31159606cec7..5817a099c622 100644 --- a/drivers/hwmon/occ/p8_i2c.c +++ b/drivers/hwmon/occ/p8_i2c.c @@ -8,7 +8,7 @@ #include <linux/jiffies.h> #include <linux/module.h> #include <linux/sched.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "common.h" diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig index 53f18b351f53..6b3ba7e5723a 100644 --- a/drivers/i2c/busses/Kconfig +++ b/drivers/i2c/busses/Kconfig @@ -782,6 +782,7 @@ config I2C_JZ4780 config I2C_KEBA tristate "KEBA I2C controller support" depends on HAS_IOMEM + depends on KEBA_CP500 || COMPILE_TEST select AUXILIARY_BUS help This driver supports the I2C controller found in KEBA system FPGA diff --git a/drivers/i2c/busses/i2c-designware-common.c b/drivers/i2c/busses/i2c-designware-common.c index 080204182bb5..f31d352d98b5 100644 --- a/drivers/i2c/busses/i2c-designware-common.c +++ b/drivers/i2c/busses/i2c-designware-common.c @@ -523,6 +523,7 @@ err_release_lock: void __i2c_dw_disable(struct dw_i2c_dev *dev) { + struct i2c_timings *t = &dev->timings; unsigned int raw_intr_stats; unsigned int enable; int timeout = 100; @@ -535,6 +536,19 @@ void __i2c_dw_disable(struct dw_i2c_dev *dev) abort_needed = raw_intr_stats & DW_IC_INTR_MST_ON_HOLD; if (abort_needed) { + if (!(enable & DW_IC_ENABLE_ENABLE)) { + regmap_write(dev->map, DW_IC_ENABLE, DW_IC_ENABLE_ENABLE); + /* + * Wait 10 times the signaling period of the highest I2C + * transfer supported by the driver (for 400KHz this is + * 25us) to ensure the I2C ENABLE bit is already set + * as described in the DesignWare I2C databook. + */ + fsleep(DIV_ROUND_CLOSEST_ULL(10 * MICRO, t->bus_freq_hz)); + /* Set ENABLE bit before setting ABORT */ + enable |= DW_IC_ENABLE_ENABLE; + } + regmap_write(dev->map, DW_IC_ENABLE, enable | DW_IC_ENABLE_ABORT); ret = regmap_read_poll_timeout(dev->map, DW_IC_ENABLE, enable, !(enable & DW_IC_ENABLE_ABORT), 10, diff --git a/drivers/i2c/busses/i2c-designware-core.h b/drivers/i2c/busses/i2c-designware-core.h index 1ac2afd03a0a..8e8854ec9882 100644 --- a/drivers/i2c/busses/i2c-designware-core.h +++ b/drivers/i2c/busses/i2c-designware-core.h @@ -108,6 +108,7 @@ DW_IC_INTR_RX_UNDER | \ DW_IC_INTR_RD_REQ) +#define DW_IC_ENABLE_ENABLE BIT(0) #define DW_IC_ENABLE_ABORT BIT(1) #define DW_IC_STATUS_ACTIVITY BIT(0) diff --git a/drivers/i2c/busses/i2c-designware-master.c b/drivers/i2c/busses/i2c-designware-master.c index e46f1b22c360..e8ac9a7bf0b3 100644 --- a/drivers/i2c/busses/i2c-designware-master.c +++ b/drivers/i2c/busses/i2c-designware-master.c @@ -271,6 +271,34 @@ static void i2c_dw_xfer_init(struct dw_i2c_dev *dev) __i2c_dw_write_intr_mask(dev, DW_IC_INTR_MASTER_MASK); } +/* + * This function waits for the controller to be idle before disabling I2C + * When the controller is not in the IDLE state, the MST_ACTIVITY bit + * (IC_STATUS[5]) is set. + * + * Values: + * 0x1 (ACTIVE): Controller not idle + * 0x0 (IDLE): Controller is idle + * + * The function is called after completing the current transfer. + * + * Returns: + * False when the controller is in the IDLE state. + * True when the controller is in the ACTIVE state. + */ +static bool i2c_dw_is_controller_active(struct dw_i2c_dev *dev) +{ + u32 status; + + regmap_read(dev->map, DW_IC_STATUS, &status); + if (!(status & DW_IC_STATUS_MASTER_ACTIVITY)) + return false; + + return regmap_read_poll_timeout(dev->map, DW_IC_STATUS, status, + !(status & DW_IC_STATUS_MASTER_ACTIVITY), + 1100, 20000) != 0; +} + static int i2c_dw_check_stopbit(struct dw_i2c_dev *dev) { u32 val; @@ -807,6 +835,16 @@ i2c_dw_xfer(struct i2c_adapter *adap, struct i2c_msg msgs[], int num) } /* + * This happens rarely (~1:500) and is hard to reproduce. Debug trace + * showed that IC_STATUS had value of 0x23 when STOP_DET occurred, + * if disable IC_ENABLE.ENABLE immediately that can result in + * IC_RAW_INTR_STAT.MASTER_ON_HOLD holding SCL low. Check if + * controller is still ACTIVE before disabling I2C. + */ + if (i2c_dw_is_controller_active(dev)) + dev_err(dev->dev, "controller active\n"); + + /* * We must disable the adapter before returning and signaling the end * of the current transfer. Otherwise the hardware might continue * generating interrupts which in turn causes a race condition with diff --git a/drivers/i2c/busses/i2c-nvidia-gpu.c b/drivers/i2c/busses/i2c-nvidia-gpu.c index 9bcaa29a7191..541d808d62d0 100644 --- a/drivers/i2c/busses/i2c-nvidia-gpu.c +++ b/drivers/i2c/busses/i2c-nvidia-gpu.c @@ -16,7 +16,7 @@ #include <linux/pm_runtime.h> #include <linux/power_supply.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "i2c-ccgx-ucsi.h" diff --git a/drivers/i2c/busses/i2c-stm32f7.c b/drivers/i2c/busses/i2c-stm32f7.c index cfee2d9c09de..0174ead99de6 100644 --- a/drivers/i2c/busses/i2c-stm32f7.c +++ b/drivers/i2c/busses/i2c-stm32f7.c @@ -2395,7 +2395,7 @@ static int __maybe_unused stm32f7_i2c_runtime_suspend(struct device *dev) struct stm32f7_i2c_dev *i2c_dev = dev_get_drvdata(dev); if (!stm32f7_i2c_is_slave_registered(i2c_dev)) - clk_disable_unprepare(i2c_dev->clk); + clk_disable(i2c_dev->clk); return 0; } @@ -2406,9 +2406,9 @@ static int __maybe_unused stm32f7_i2c_runtime_resume(struct device *dev) int ret; if (!stm32f7_i2c_is_slave_registered(i2c_dev)) { - ret = clk_prepare_enable(i2c_dev->clk); + ret = clk_enable(i2c_dev->clk); if (ret) { - dev_err(dev, "failed to prepare_enable clock\n"); + dev_err(dev, "failed to enable clock\n"); return ret; } } diff --git a/drivers/i2c/busses/i2c-synquacer.c b/drivers/i2c/busses/i2c-synquacer.c index 4eccbcd0fbfc..bbb9062669e4 100644 --- a/drivers/i2c/busses/i2c-synquacer.c +++ b/drivers/i2c/busses/i2c-synquacer.c @@ -550,12 +550,13 @@ static int synquacer_i2c_probe(struct platform_device *pdev) device_property_read_u32(&pdev->dev, "socionext,pclk-rate", &i2c->pclkrate); - pclk = devm_clk_get_enabled(&pdev->dev, "pclk"); + pclk = devm_clk_get_optional_enabled(&pdev->dev, "pclk"); if (IS_ERR(pclk)) return dev_err_probe(&pdev->dev, PTR_ERR(pclk), "failed to get and enable clock\n"); - i2c->pclkrate = clk_get_rate(pclk); + if (pclk) + i2c->pclkrate = clk_get_rate(pclk); if (i2c->pclkrate < SYNQUACER_I2C_MIN_CLK_RATE || i2c->pclkrate > SYNQUACER_I2C_MAX_CLK_RATE) diff --git a/drivers/i2c/busses/i2c-xiic.c b/drivers/i2c/busses/i2c-xiic.c index 4c89aad02451..1d68177241a6 100644 --- a/drivers/i2c/busses/i2c-xiic.c +++ b/drivers/i2c/busses/i2c-xiic.c @@ -1337,8 +1337,8 @@ static int xiic_i2c_probe(struct platform_device *pdev) return 0; err_pm_disable: - pm_runtime_set_suspended(&pdev->dev); pm_runtime_disable(&pdev->dev); + pm_runtime_set_suspended(&pdev->dev); return ret; } diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c index 9457e34b9e32..67aebfe0fed6 100644 --- a/drivers/idle/intel_idle.c +++ b/drivers/idle/intel_idle.c @@ -121,6 +121,12 @@ static unsigned int mwait_substates __initdata; #define CPUIDLE_FLAG_INIT_XSTATE BIT(17) /* + * Ignore the sub-state when matching mwait hints between the ACPI _CST and + * custom tables. + */ +#define CPUIDLE_FLAG_PARTIAL_HINT_MATCH BIT(18) + +/* * MWAIT takes an 8-bit "hint" in EAX "suggesting" * the C-state (top nibble) and sub-state (bottom nibble) * 0x00 means "MWAIT(C1)", 0x10 means "MWAIT(C2)" etc. @@ -1043,7 +1049,8 @@ static struct cpuidle_state gnr_cstates[] __initdata = { .name = "C6", .desc = "MWAIT 0x20", .flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED | - CPUIDLE_FLAG_INIT_XSTATE, + CPUIDLE_FLAG_INIT_XSTATE | + CPUIDLE_FLAG_PARTIAL_HINT_MATCH, .exit_latency = 170, .target_residency = 650, .enter = &intel_idle, @@ -1052,7 +1059,8 @@ static struct cpuidle_state gnr_cstates[] __initdata = { .name = "C6P", .desc = "MWAIT 0x21", .flags = MWAIT2flg(0x21) | CPUIDLE_FLAG_TLB_FLUSHED | - CPUIDLE_FLAG_INIT_XSTATE, + CPUIDLE_FLAG_INIT_XSTATE | + CPUIDLE_FLAG_PARTIAL_HINT_MATCH, .exit_latency = 210, .target_residency = 1000, .enter = &intel_idle, @@ -1354,7 +1362,8 @@ static struct cpuidle_state srf_cstates[] __initdata = { { .name = "C6S", .desc = "MWAIT 0x22", - .flags = MWAIT2flg(0x22) | CPUIDLE_FLAG_TLB_FLUSHED, + .flags = MWAIT2flg(0x22) | CPUIDLE_FLAG_TLB_FLUSHED | + CPUIDLE_FLAG_PARTIAL_HINT_MATCH, .exit_latency = 270, .target_residency = 700, .enter = &intel_idle, @@ -1362,7 +1371,8 @@ static struct cpuidle_state srf_cstates[] __initdata = { { .name = "C6SP", .desc = "MWAIT 0x23", - .flags = MWAIT2flg(0x23) | CPUIDLE_FLAG_TLB_FLUSHED, + .flags = MWAIT2flg(0x23) | CPUIDLE_FLAG_TLB_FLUSHED | + CPUIDLE_FLAG_PARTIAL_HINT_MATCH, .exit_latency = 310, .target_residency = 900, .enter = &intel_idle, @@ -1744,7 +1754,7 @@ static void __init intel_idle_init_cstates_acpi(struct cpuidle_driver *drv) } } -static bool __init intel_idle_off_by_default(u32 mwait_hint) +static bool __init intel_idle_off_by_default(unsigned int flags, u32 mwait_hint) { int cstate, limit; @@ -1761,7 +1771,15 @@ static bool __init intel_idle_off_by_default(u32 mwait_hint) * the interesting states are ACPI_CSTATE_FFH. */ for (cstate = 1; cstate < limit; cstate++) { - if (acpi_state_table.states[cstate].address == mwait_hint) + u32 acpi_hint = acpi_state_table.states[cstate].address; + u32 table_hint = mwait_hint; + + if (flags & CPUIDLE_FLAG_PARTIAL_HINT_MATCH) { + acpi_hint &= ~MWAIT_SUBSTATE_MASK; + table_hint &= ~MWAIT_SUBSTATE_MASK; + } + + if (acpi_hint == table_hint) return false; } return true; @@ -1771,7 +1789,10 @@ static bool __init intel_idle_off_by_default(u32 mwait_hint) static inline bool intel_idle_acpi_cst_extract(void) { return false; } static inline void intel_idle_init_cstates_acpi(struct cpuidle_driver *drv) { } -static inline bool intel_idle_off_by_default(u32 mwait_hint) { return false; } +static inline bool intel_idle_off_by_default(unsigned int flags, u32 mwait_hint) +{ + return false; +} #endif /* !CONFIG_ACPI_PROCESSOR_CSTATE */ /** @@ -2098,7 +2119,7 @@ static void __init intel_idle_init_cstates_icpu(struct cpuidle_driver *drv) if ((disabled_states_mask & BIT(drv->state_count)) || ((icpu->use_acpi || force_use_acpi) && - intel_idle_off_by_default(mwait_hint) && + intel_idle_off_by_default(state->flags, mwait_hint) && !(state->flags & CPUIDLE_FLAG_ALWAYS_ENABLE))) state->flags |= CPUIDLE_FLAG_OFF; diff --git a/drivers/iio/accel/adxl355_core.c b/drivers/iio/accel/adxl355_core.c index 0c9225d18fb2..eabaefa92f19 100644 --- a/drivers/iio/accel/adxl355_core.c +++ b/drivers/iio/accel/adxl355_core.c @@ -22,7 +22,7 @@ #include <linux/regmap.h> #include <linux/units.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "adxl355.h" diff --git a/drivers/iio/accel/adxl367.c b/drivers/iio/accel/adxl367.c index 1c046e96aef9..e790a66d86c7 100644 --- a/drivers/iio/accel/adxl367.c +++ b/drivers/iio/accel/adxl367.c @@ -16,7 +16,7 @@ #include <linux/mod_devicetable.h> #include <linux/regmap.h> #include <linux/regulator/consumer.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "adxl367.h" diff --git a/drivers/iio/accel/adxl380.c b/drivers/iio/accel/adxl380.c index 98863e22bb6b..f80527d899be 100644 --- a/drivers/iio/accel/adxl380.c +++ b/drivers/iio/accel/adxl380.c @@ -13,7 +13,7 @@ #include <linux/regmap.h> #include <linux/units.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/iio/buffer.h> #include <linux/iio/events.h> diff --git a/drivers/iio/accel/bma400_core.c b/drivers/iio/accel/bma400_core.c index 89db242f06e0..f4e43c3bbf1a 100644 --- a/drivers/iio/accel/bma400_core.c +++ b/drivers/iio/accel/bma400_core.c @@ -22,7 +22,7 @@ #include <linux/regulator/consumer.h> #include <linux/slab.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/iio/iio.h> #include <linux/iio/buffer.h> diff --git a/drivers/iio/accel/bmi088-accel-core.c b/drivers/iio/accel/bmi088-accel-core.c index 469a1255d93c..fc1c1613d673 100644 --- a/drivers/iio/accel/bmi088-accel-core.c +++ b/drivers/iio/accel/bmi088-accel-core.c @@ -18,7 +18,7 @@ #include <linux/pm_runtime.h> #include <linux/regmap.h> #include <linux/slab.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "bmi088-accel.h" diff --git a/drivers/iio/accel/dmard09.c b/drivers/iio/accel/dmard09.c index 6644c1fec3e6..4ec70ca6910d 100644 --- a/drivers/iio/accel/dmard09.c +++ b/drivers/iio/accel/dmard09.c @@ -5,7 +5,7 @@ * Copyright (c) 2016, Jelle van der Waa <jelle@vdwaa.nl> */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/module.h> #include <linux/i2c.h> #include <linux/iio/iio.h> diff --git a/drivers/iio/accel/sca3300.c b/drivers/iio/accel/sca3300.c index fca77d660625..ca0ce83e42b2 100644 --- a/drivers/iio/accel/sca3300.c +++ b/drivers/iio/accel/sca3300.c @@ -12,7 +12,7 @@ #include <linux/module.h> #include <linux/spi/spi.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/iio/buffer.h> #include <linux/iio/iio.h> diff --git a/drivers/iio/adc/ad4130.c b/drivers/iio/adc/ad4130.c index e134d6497827..de32cc9d18c5 100644 --- a/drivers/iio/adc/ad4130.c +++ b/drivers/iio/adc/ad4130.c @@ -23,7 +23,7 @@ #include <linux/units.h> #include <asm/div64.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/iio/buffer.h> #include <linux/iio/iio.h> diff --git a/drivers/iio/adc/ad_sigma_delta.c b/drivers/iio/adc/ad_sigma_delta.c index e2bed2d648f2..ea4aabd3960a 100644 --- a/drivers/iio/adc/ad_sigma_delta.c +++ b/drivers/iio/adc/ad_sigma_delta.c @@ -23,7 +23,7 @@ #include <linux/iio/triggered_buffer.h> #include <linux/iio/adc/ad_sigma_delta.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define AD_SD_COMM_CHAN_MASK 0x3 diff --git a/drivers/iio/adc/axp20x_adc.c b/drivers/iio/adc/axp20x_adc.c index d43c8d124a0c..6c1a5d1b0a83 100644 --- a/drivers/iio/adc/axp20x_adc.c +++ b/drivers/iio/adc/axp20x_adc.c @@ -5,7 +5,7 @@ * Quentin Schulz <quentin.schulz@free-electrons.com> */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/bitfield.h> #include <linux/completion.h> #include <linux/interrupt.h> diff --git a/drivers/iio/adc/intel_mrfld_adc.c b/drivers/iio/adc/intel_mrfld_adc.c index 0590a126f321..30733252aa56 100644 --- a/drivers/iio/adc/intel_mrfld_adc.c +++ b/drivers/iio/adc/intel_mrfld_adc.c @@ -25,7 +25,7 @@ #include <linux/iio/iio.h> #include <linux/iio/machine.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define BCOVE_GPADCREQ 0xDC #define BCOVE_GPADCREQ_BUSY BIT(0) diff --git a/drivers/iio/adc/ltc2497.c b/drivers/iio/adc/ltc2497.c index f010b2fd1202..eb9d521e86e5 100644 --- a/drivers/iio/adc/ltc2497.c +++ b/drivers/iio/adc/ltc2497.c @@ -14,7 +14,7 @@ #include <linux/mod_devicetable.h> #include <linux/property.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "ltc2497.h" diff --git a/drivers/iio/adc/max11100.c b/drivers/iio/adc/max11100.c index 2f07437caec3..520e37f75aac 100644 --- a/drivers/iio/adc/max11100.c +++ b/drivers/iio/adc/max11100.c @@ -12,7 +12,7 @@ #include <linux/module.h> #include <linux/regulator/consumer.h> #include <linux/spi/spi.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/iio/iio.h> #include <linux/iio/driver.h> diff --git a/drivers/iio/adc/max11410.c b/drivers/iio/adc/max11410.c index 45368850b220..f0dc4b460903 100644 --- a/drivers/iio/adc/max11410.c +++ b/drivers/iio/adc/max11410.c @@ -15,7 +15,7 @@ #include <linux/regulator/consumer.h> #include <linux/spi/spi.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/iio/buffer.h> #include <linux/iio/sysfs.h> diff --git a/drivers/iio/adc/mcp3422.c b/drivers/iio/adc/mcp3422.c index 0778a8fb6866..50834fdcf738 100644 --- a/drivers/iio/adc/mcp3422.c +++ b/drivers/iio/adc/mcp3422.c @@ -19,7 +19,7 @@ #include <linux/mod_devicetable.h> #include <linux/delay.h> #include <linux/sysfs.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/iio/iio.h> #include <linux/iio/sysfs.h> diff --git a/drivers/iio/adc/mcp3911.c b/drivers/iio/adc/mcp3911.c index d0e77971c5d3..b097f04172c8 100644 --- a/drivers/iio/adc/mcp3911.c +++ b/drivers/iio/adc/mcp3911.c @@ -23,7 +23,7 @@ #include <linux/iio/trigger_consumer.h> #include <linux/iio/trigger.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define MCP3911_REG_CHANNEL0 0x00 #define MCP3911_REG_CHANNEL1 0x03 diff --git a/drivers/iio/adc/mt6360-adc.c b/drivers/iio/adc/mt6360-adc.c index e2ec805e834f..83161e6d29b9 100644 --- a/drivers/iio/adc/mt6360-adc.c +++ b/drivers/iio/adc/mt6360-adc.c @@ -16,7 +16,7 @@ #include <linux/iio/trigger_consumer.h> #include <linux/iio/triggered_buffer.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define MT6360_REG_PMUCHGCTRL3 0x313 #define MT6360_REG_PMUADCCFG 0x356 diff --git a/drivers/iio/adc/pac1921.c b/drivers/iio/adc/pac1921.c index 4c2a1c07bc39..36e813d9c73f 100644 --- a/drivers/iio/adc/pac1921.c +++ b/drivers/iio/adc/pac1921.c @@ -5,7 +5,7 @@ * Copyright (C) 2024 Matteo Martelli <matteomartelli3@gmail.com> */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/bitfield.h> #include <linux/i2c.h> #include <linux/iio/events.h> diff --git a/drivers/iio/adc/pac1934.c b/drivers/iio/adc/pac1934.c index 8210728034d0..7ef249d83286 100644 --- a/drivers/iio/adc/pac1934.c +++ b/drivers/iio/adc/pac1934.c @@ -19,7 +19,7 @@ #include <linux/i2c.h> #include <linux/iio/iio.h> #include <linux/iio/sysfs.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /* * maximum accumulation time should be (17 * 60 * 1000) around 17 minutes@1024 sps diff --git a/drivers/iio/adc/qcom-spmi-rradc.c b/drivers/iio/adc/qcom-spmi-rradc.c index 6aa70b4629a7..63ebaf13ef19 100644 --- a/drivers/iio/adc/qcom-spmi-rradc.c +++ b/drivers/iio/adc/qcom-spmi-rradc.c @@ -20,7 +20,7 @@ #include <linux/types.h> #include <linux/units.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/iio/iio.h> #include <linux/iio/types.h> diff --git a/drivers/iio/adc/ti-ads124s08.c b/drivers/iio/adc/ti-ads124s08.c index 14941f384dad..425b48d8986f 100644 --- a/drivers/iio/adc/ti-ads124s08.c +++ b/drivers/iio/adc/ti-ads124s08.c @@ -21,7 +21,7 @@ #include <linux/iio/triggered_buffer.h> #include <linux/iio/sysfs.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /* Commands */ #define ADS124S08_CMD_NOP 0x00 diff --git a/drivers/iio/adc/ti-ads1298.c b/drivers/iio/adc/ti-ads1298.c index 13cb32125eef..0f9f75baaebb 100644 --- a/drivers/iio/adc/ti-ads1298.c +++ b/drivers/iio/adc/ti-ads1298.c @@ -23,7 +23,7 @@ #include <linux/iio/buffer.h> #include <linux/iio/kfifo_buf.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /* Commands */ #define ADS1298_CMD_WAKEUP 0x02 diff --git a/drivers/iio/adc/ti-ads131e08.c b/drivers/iio/adc/ti-ads131e08.c index 91a427eb0882..31f1f229d97a 100644 --- a/drivers/iio/adc/ti-ads131e08.c +++ b/drivers/iio/adc/ti-ads131e08.c @@ -23,7 +23,7 @@ #include <linux/regulator/consumer.h> #include <linux/spi/spi.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /* Commands */ #define ADS131E08_CMD_RESET 0x06 diff --git a/drivers/iio/adc/ti-tsc2046.c b/drivers/iio/adc/ti-tsc2046.c index 311d97001249..b56f2503f14c 100644 --- a/drivers/iio/adc/ti-tsc2046.c +++ b/drivers/iio/adc/ti-tsc2046.c @@ -13,7 +13,7 @@ #include <linux/spi/spi.h> #include <linux/units.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/iio/buffer.h> #include <linux/iio/trigger_consumer.h> diff --git a/drivers/iio/addac/ad74115.c b/drivers/iio/addac/ad74115.c index 12dc43d487b4..3ee0dd5537c1 100644 --- a/drivers/iio/addac/ad74115.c +++ b/drivers/iio/addac/ad74115.c @@ -16,7 +16,7 @@ #include <linux/spi/spi.h> #include <linux/units.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/iio/buffer.h> #include <linux/iio/iio.h> diff --git a/drivers/iio/addac/ad74413r.c b/drivers/iio/addac/ad74413r.c index 2410d72da49b..69c586525d21 100644 --- a/drivers/iio/addac/ad74413r.c +++ b/drivers/iio/addac/ad74413r.c @@ -4,7 +4,7 @@ * Author: Cosmin Tanislav <cosmin.tanislav@analog.com> */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/bitfield.h> #include <linux/crc8.h> #include <linux/device.h> diff --git a/drivers/iio/amplifiers/ada4250.c b/drivers/iio/amplifiers/ada4250.c index 4b32d350dc5d..566f0e1c98a5 100644 --- a/drivers/iio/amplifiers/ada4250.c +++ b/drivers/iio/amplifiers/ada4250.c @@ -14,7 +14,7 @@ #include <linux/regulator/consumer.h> #include <linux/spi/spi.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /* ADA4250 Register Map */ #define ADA4250_REG_GAIN_MUX 0x00 diff --git a/drivers/iio/cdc/ad7746.c b/drivers/iio/cdc/ad7746.c index d11bc3496dda..ba18dbbe0940 100644 --- a/drivers/iio/cdc/ad7746.c +++ b/drivers/iio/cdc/ad7746.c @@ -16,7 +16,7 @@ #include <linux/stat.h> #include <linux/sysfs.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/iio/iio.h> #include <linux/iio/sysfs.h> diff --git a/drivers/iio/chemical/bme680_core.c b/drivers/iio/chemical/bme680_core.c index 5d2e750ca2b9..0b96534c6867 100644 --- a/drivers/iio/chemical/bme680_core.c +++ b/drivers/iio/chemical/bme680_core.c @@ -19,7 +19,7 @@ #include <linux/iio/iio.h> #include <linux/iio/sysfs.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "bme680.h" diff --git a/drivers/iio/chemical/pms7003.c b/drivers/iio/chemical/pms7003.c index 43025866d5b7..d0bd94912e0a 100644 --- a/drivers/iio/chemical/pms7003.c +++ b/drivers/iio/chemical/pms7003.c @@ -5,7 +5,7 @@ * Copyright (c) Tomasz Duszynski <tduszyns@gmail.com> */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/completion.h> #include <linux/device.h> #include <linux/errno.h> diff --git a/drivers/iio/chemical/scd30_i2c.c b/drivers/iio/chemical/scd30_i2c.c index bd3b01ded246..b31dfaf52df9 100644 --- a/drivers/iio/chemical/scd30_i2c.c +++ b/drivers/iio/chemical/scd30_i2c.c @@ -13,7 +13,7 @@ #include <linux/mod_devicetable.h> #include <linux/module.h> #include <linux/types.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "scd30.h" diff --git a/drivers/iio/chemical/scd30_serial.c b/drivers/iio/chemical/scd30_serial.c index 2adb76dbb020..55044f07d5a3 100644 --- a/drivers/iio/chemical/scd30_serial.c +++ b/drivers/iio/chemical/scd30_serial.c @@ -15,7 +15,7 @@ #include <linux/serdev.h> #include <linux/string.h> #include <linux/types.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "scd30.h" diff --git a/drivers/iio/chemical/scd4x.c b/drivers/iio/chemical/scd4x.c index ca6b20270711..52cad54e8572 100644 --- a/drivers/iio/chemical/scd4x.c +++ b/drivers/iio/chemical/scd4x.c @@ -11,7 +11,7 @@ * https://www.sensirion.com/file/datasheet_scd4x */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/crc8.h> #include <linux/delay.h> #include <linux/device.h> diff --git a/drivers/iio/chemical/sps30_i2c.c b/drivers/iio/chemical/sps30_i2c.c index 5c31299813ec..1b21b6bcd0e7 100644 --- a/drivers/iio/chemical/sps30_i2c.c +++ b/drivers/iio/chemical/sps30_i2c.c @@ -6,7 +6,7 @@ * * I2C slave address: 0x69 */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/crc8.h> #include <linux/delay.h> #include <linux/device.h> diff --git a/drivers/iio/common/st_sensors/st_sensors_core.c b/drivers/iio/common/st_sensors/st_sensors_core.c index c69399ac6657..1b4287991d00 100644 --- a/drivers/iio/common/st_sensors/st_sensors_core.c +++ b/drivers/iio/common/st_sensors/st_sensors_core.c @@ -16,7 +16,7 @@ #include <linux/property.h> #include <linux/regulator/consumer.h> #include <linux/regmap.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/iio/common/st_sensors.h> #include "st_sensors_core.h" diff --git a/drivers/iio/dac/ad3552r.c b/drivers/iio/dac/ad3552r.c index bd37d304ca70..7d61b2fe6624 100644 --- a/drivers/iio/dac/ad3552r.c +++ b/drivers/iio/dac/ad3552r.c @@ -5,7 +5,7 @@ * * Copyright 2021 Analog Devices Inc. */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/device.h> #include <linux/iio/triggered_buffer.h> #include <linux/iio/trigger_consumer.h> diff --git a/drivers/iio/dac/ad5064.c b/drivers/iio/dac/ad5064.c index 7712dc6be608..905988724f27 100644 --- a/drivers/iio/dac/ad5064.c +++ b/drivers/iio/dac/ad5064.c @@ -18,7 +18,7 @@ #include <linux/slab.h> #include <linux/sysfs.h> #include <linux/regulator/consumer.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/iio/iio.h> #include <linux/iio/sysfs.h> diff --git a/drivers/iio/dac/ad5446.c b/drivers/iio/dac/ad5446.c index 8103d2cd13f6..708629efc157 100644 --- a/drivers/iio/dac/ad5446.c +++ b/drivers/iio/dac/ad5446.c @@ -22,7 +22,7 @@ #include <linux/iio/iio.h> #include <linux/iio/sysfs.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define MODE_PWRDWN_1k 0x1 #define MODE_PWRDWN_100k 0x2 diff --git a/drivers/iio/dac/ad5449.c b/drivers/iio/dac/ad5449.c index 953fcfa2110b..1c996016756a 100644 --- a/drivers/iio/dac/ad5449.c +++ b/drivers/iio/dac/ad5449.c @@ -15,7 +15,7 @@ #include <linux/slab.h> #include <linux/sysfs.h> #include <linux/regulator/consumer.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/iio/iio.h> #include <linux/iio/sysfs.h> diff --git a/drivers/iio/dac/ad5593r.c b/drivers/iio/dac/ad5593r.c index fae5e5a0e72f..62e1fbb9e910 100644 --- a/drivers/iio/dac/ad5593r.c +++ b/drivers/iio/dac/ad5593r.c @@ -13,7 +13,7 @@ #include <linux/module.h> #include <linux/mod_devicetable.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define AD5593R_MODE_CONF (0 << 4) #define AD5593R_MODE_DAC_WRITE (1 << 4) diff --git a/drivers/iio/dac/ad5624r_spi.c b/drivers/iio/dac/ad5624r_spi.c index 7e6f824de299..9304d0499bae 100644 --- a/drivers/iio/dac/ad5624r_spi.c +++ b/drivers/iio/dac/ad5624r_spi.c @@ -18,7 +18,7 @@ #include <linux/iio/iio.h> #include <linux/iio/sysfs.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "ad5624r.h" diff --git a/drivers/iio/dac/ad5766.c b/drivers/iio/dac/ad5766.c index 899894523752..f658ac8086aa 100644 --- a/drivers/iio/dac/ad5766.c +++ b/drivers/iio/dac/ad5766.c @@ -14,7 +14,7 @@ #include <linux/iio/trigger_consumer.h> #include <linux/module.h> #include <linux/spi/spi.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define AD5766_UPPER_WORD_SPI_MASK GENMASK(31, 16) #define AD5766_LOWER_WORD_SPI_MASK GENMASK(15, 0) diff --git a/drivers/iio/dac/ad7293.c b/drivers/iio/dac/ad7293.c index 06f05750d921..1d4032670482 100644 --- a/drivers/iio/dac/ad7293.c +++ b/drivers/iio/dac/ad7293.c @@ -16,7 +16,7 @@ #include <linux/regulator/consumer.h> #include <linux/spi/spi.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define AD7293_R1B BIT(16) #define AD7293_R2B BIT(17) diff --git a/drivers/iio/dac/ltc2632.c b/drivers/iio/dac/ltc2632.c index 3a3c4f4874e4..a4fb2509c950 100644 --- a/drivers/iio/dac/ltc2632.c +++ b/drivers/iio/dac/ltc2632.c @@ -13,7 +13,7 @@ #include <linux/property.h> #include <linux/regulator/consumer.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define LTC2632_CMD_WRITE_INPUT_N 0x0 #define LTC2632_CMD_UPDATE_DAC_N 0x1 diff --git a/drivers/iio/dac/mcp4821.c b/drivers/iio/dac/mcp4821.c index 782e8f6b7782..c1a59bbbba3c 100644 --- a/drivers/iio/dac/mcp4821.c +++ b/drivers/iio/dac/mcp4821.c @@ -23,7 +23,7 @@ #include <linux/iio/iio.h> #include <linux/iio/types.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define MCP4821_ACTIVE_MODE BIT(12) #define MCP4802_SECOND_CHAN BIT(15) diff --git a/drivers/iio/frequency/adf4377.c b/drivers/iio/frequency/adf4377.c index 25fbc2cef1f7..45ceeb828d6b 100644 --- a/drivers/iio/frequency/adf4377.c +++ b/drivers/iio/frequency/adf4377.c @@ -20,7 +20,7 @@ #include <linux/regmap.h> #include <linux/units.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /* ADF4377 REG0000 Map */ #define ADF4377_0000_SOFT_RESET_R_MSK BIT(7) diff --git a/drivers/iio/frequency/admv1013.c b/drivers/iio/frequency/admv1013.c index c0cd5d9844fe..8ef583680ad0 100644 --- a/drivers/iio/frequency/admv1013.c +++ b/drivers/iio/frequency/admv1013.c @@ -18,7 +18,7 @@ #include <linux/spi/spi.h> #include <linux/units.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /* ADMV1013 Register Map */ #define ADMV1013_REG_SPI_CONTROL 0x00 diff --git a/drivers/iio/frequency/admv1014.c b/drivers/iio/frequency/admv1014.c index b46b73b89eb7..986b87a72577 100644 --- a/drivers/iio/frequency/admv1014.c +++ b/drivers/iio/frequency/admv1014.c @@ -19,7 +19,7 @@ #include <linux/spi/spi.h> #include <linux/units.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /* ADMV1014 Register Map */ #define ADMV1014_REG_SPI_CONTROL 0x00 diff --git a/drivers/iio/frequency/admv4420.c b/drivers/iio/frequency/admv4420.c index 863ba8e98c95..3ae462b4f5c9 100644 --- a/drivers/iio/frequency/admv4420.c +++ b/drivers/iio/frequency/admv4420.c @@ -13,7 +13,7 @@ #include <linux/spi/spi.h> #include <linux/units.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /* ADMV4420 Register Map */ #define ADMV4420_SPI_CONFIG_1 0x00 diff --git a/drivers/iio/frequency/adrf6780.c b/drivers/iio/frequency/adrf6780.c index 3f46032c9275..57ee908fc747 100644 --- a/drivers/iio/frequency/adrf6780.c +++ b/drivers/iio/frequency/adrf6780.c @@ -16,7 +16,7 @@ #include <linux/mod_devicetable.h> #include <linux/spi/spi.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /* ADRF6780 Register Map */ #define ADRF6780_REG_CONTROL 0x00 diff --git a/drivers/iio/gyro/adis16130.c b/drivers/iio/gyro/adis16130.c index 33cde9e6fca5..2535e3c94037 100644 --- a/drivers/iio/gyro/adis16130.c +++ b/drivers/iio/gyro/adis16130.c @@ -12,7 +12,7 @@ #include <linux/iio/iio.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define ADIS16130_CON 0x0 #define ADIS16130_CON_RD (1 << 6) diff --git a/drivers/iio/health/afe4403.c b/drivers/iio/health/afe4403.c index 85637e8ac45f..13e1dd4dd62c 100644 --- a/drivers/iio/health/afe4403.c +++ b/drivers/iio/health/afe4403.c @@ -23,7 +23,7 @@ #include <linux/iio/triggered_buffer.h> #include <linux/iio/trigger_consumer.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "afe440x.h" diff --git a/drivers/iio/humidity/ens210.c b/drivers/iio/humidity/ens210.c index e9167574203a..77418d97f30d 100644 --- a/drivers/iio/humidity/ens210.c +++ b/drivers/iio/humidity/ens210.c @@ -22,7 +22,7 @@ #include <linux/module.h> #include <linux/types.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /* register definitions */ #define ENS210_REG_PART_ID 0x00 diff --git a/drivers/iio/humidity/hdc3020.c b/drivers/iio/humidity/hdc3020.c index a82dcc3da421..ffb25596d3a8 100644 --- a/drivers/iio/humidity/hdc3020.c +++ b/drivers/iio/humidity/hdc3020.c @@ -26,7 +26,7 @@ #include <linux/regulator/consumer.h> #include <linux/units.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/iio/events.h> #include <linux/iio/iio.h> diff --git a/drivers/iio/imu/adis.c b/drivers/iio/imu/adis.c index 876848b42f69..99410733c1ca 100644 --- a/drivers/iio/imu/adis.c +++ b/drivers/iio/imu/adis.c @@ -13,7 +13,7 @@ #include <linux/kernel.h> #include <linux/spi/spi.h> #include <linux/module.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/iio/iio.h> #include <linux/iio/imu/adis.h> diff --git a/drivers/iio/imu/bmi323/bmi323_core.c b/drivers/iio/imu/bmi323/bmi323_core.c index 671401ce80dc..beda8d2de53f 100644 --- a/drivers/iio/imu/bmi323/bmi323_core.c +++ b/drivers/iio/imu/bmi323/bmi323_core.c @@ -19,7 +19,7 @@ #include <linux/regulator/consumer.h> #include <linux/units.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/iio/buffer.h> #include <linux/iio/events.h> diff --git a/drivers/iio/light/apds9306.c b/drivers/iio/light/apds9306.c index 66a063ea3db4..079e02be1005 100644 --- a/drivers/iio/light/apds9306.c +++ b/drivers/iio/light/apds9306.c @@ -28,7 +28,7 @@ #include <linux/iio/events.h> #include <linux/iio/sysfs.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define APDS9306_MAIN_CTRL_REG 0x00 #define APDS9306_ALS_MEAS_RATE_REG 0x04 diff --git a/drivers/iio/light/gp2ap020a00f.c b/drivers/iio/light/gp2ap020a00f.c index b3f87dded040..81e718cdeae3 100644 --- a/drivers/iio/light/gp2ap020a00f.c +++ b/drivers/iio/light/gp2ap020a00f.c @@ -43,7 +43,7 @@ #include <linux/regmap.h> #include <linux/regulator/consumer.h> #include <linux/slab.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/iio/buffer.h> #include <linux/iio/events.h> #include <linux/iio/iio.h> diff --git a/drivers/iio/light/ltr390.c b/drivers/iio/light/ltr390.c index 7e58b50f3660..4f6975e63a8f 100644 --- a/drivers/iio/light/ltr390.c +++ b/drivers/iio/light/ltr390.c @@ -27,7 +27,7 @@ #include <linux/iio/iio.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define LTR390_MAIN_CTRL 0x00 #define LTR390_ALS_UVS_MEAS_RATE 0x04 diff --git a/drivers/iio/light/ltrf216a.c b/drivers/iio/light/ltrf216a.c index bc8444516689..37eecff571b9 100644 --- a/drivers/iio/light/ltrf216a.c +++ b/drivers/iio/light/ltrf216a.c @@ -26,7 +26,7 @@ #include <linux/iio/iio.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define LTRF216A_ALS_RESET_MASK BIT(4) #define LTRF216A_ALS_DATA_STATUS BIT(3) diff --git a/drivers/iio/light/si1133.c b/drivers/iio/light/si1133.c index eeff6cc792f2..44fa152dbd24 100644 --- a/drivers/iio/light/si1133.c +++ b/drivers/iio/light/si1133.c @@ -17,7 +17,7 @@ #include <linux/util_macros.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define SI1133_REG_PART_ID 0x00 #define SI1133_REG_REV_ID 0x01 diff --git a/drivers/iio/light/tsl2591.c b/drivers/iio/light/tsl2591.c index 7bdbfe72f0f0..850c2465992f 100644 --- a/drivers/iio/light/tsl2591.c +++ b/drivers/iio/light/tsl2591.c @@ -21,7 +21,7 @@ #include <linux/pm_runtime.h> #include <linux/sysfs.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/iio/events.h> #include <linux/iio/iio.h> diff --git a/drivers/iio/light/zopt2201.c b/drivers/iio/light/zopt2201.c index 327f94e447af..604be60e92ac 100644 --- a/drivers/iio/light/zopt2201.c +++ b/drivers/iio/light/zopt2201.c @@ -19,7 +19,7 @@ #include <linux/iio/iio.h> #include <linux/iio/sysfs.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define ZOPT2201_DRV_NAME "zopt2201" diff --git a/drivers/iio/magnetometer/rm3100-core.c b/drivers/iio/magnetometer/rm3100-core.c index 0e03a772fa43..baab918b3825 100644 --- a/drivers/iio/magnetometer/rm3100-core.c +++ b/drivers/iio/magnetometer/rm3100-core.c @@ -22,7 +22,7 @@ #include <linux/iio/triggered_buffer.h> #include <linux/iio/trigger_consumer.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "rm3100.h" diff --git a/drivers/iio/magnetometer/yamaha-yas530.c b/drivers/iio/magnetometer/yamaha-yas530.c index 7b041bb38693..65011a8598d3 100644 --- a/drivers/iio/magnetometer/yamaha-yas530.c +++ b/drivers/iio/magnetometer/yamaha-yas530.c @@ -43,7 +43,7 @@ #include <linux/iio/trigger_consumer.h> #include <linux/iio/triggered_buffer.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /* Commonly used registers */ #define YAS5XX_DEVICE_ID 0x80 diff --git a/drivers/iio/pressure/bmp280-core.c b/drivers/iio/pressure/bmp280-core.c index da379230c837..a8b97b9b0461 100644 --- a/drivers/iio/pressure/bmp280-core.c +++ b/drivers/iio/pressure/bmp280-core.c @@ -46,7 +46,7 @@ #include <linux/iio/trigger_consumer.h> #include <linux/iio/triggered_buffer.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "bmp280.h" diff --git a/drivers/iio/pressure/dlhl60d.c b/drivers/iio/pressure/dlhl60d.c index c1cea9d40424..e99e97ea6300 100644 --- a/drivers/iio/pressure/dlhl60d.c +++ b/drivers/iio/pressure/dlhl60d.c @@ -15,7 +15,7 @@ #include <linux/iio/buffer.h> #include <linux/iio/trigger_consumer.h> #include <linux/iio/triggered_buffer.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /* Commands */ #define DLH_START_SINGLE 0xAA diff --git a/drivers/iio/pressure/hp206c.c b/drivers/iio/pressure/hp206c.c index 261af1562827..442740941933 100644 --- a/drivers/iio/pressure/hp206c.c +++ b/drivers/iio/pressure/hp206c.c @@ -18,7 +18,7 @@ #include <linux/delay.h> #include <linux/util_macros.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /* I2C commands: */ #define HP206C_CMD_SOFT_RST 0x06 diff --git a/drivers/iio/pressure/hsc030pa.c b/drivers/iio/pressure/hsc030pa.c index 1682b90d4557..4e6f10eeabc3 100644 --- a/drivers/iio/pressure/hsc030pa.c +++ b/drivers/iio/pressure/hsc030pa.c @@ -28,7 +28,7 @@ #include <linux/iio/trigger_consumer.h> #include <linux/iio/triggered_buffer.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "hsc030pa.h" diff --git a/drivers/iio/pressure/mprls0025pa.c b/drivers/iio/pressure/mprls0025pa.c index 33a15d4c642c..3b6145348c2e 100644 --- a/drivers/iio/pressure/mprls0025pa.c +++ b/drivers/iio/pressure/mprls0025pa.c @@ -26,7 +26,7 @@ #include <linux/regulator/consumer.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "mprls0025pa.h" diff --git a/drivers/iio/pressure/ms5611_i2c.c b/drivers/iio/pressure/ms5611_i2c.c index 9a0f52321fcb..7e2cb8b6afa2 100644 --- a/drivers/iio/pressure/ms5611_i2c.c +++ b/drivers/iio/pressure/ms5611_i2c.c @@ -16,7 +16,7 @@ #include <linux/module.h> #include <linux/mod_devicetable.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "ms5611.h" diff --git a/drivers/iio/pressure/ms5611_spi.c b/drivers/iio/pressure/ms5611_spi.c index cc9d1f68c53c..87181963a3e3 100644 --- a/drivers/iio/pressure/ms5611_spi.c +++ b/drivers/iio/pressure/ms5611_spi.c @@ -11,7 +11,7 @@ #include <linux/spi/spi.h> #include <linux/mod_devicetable.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "ms5611.h" diff --git a/drivers/iio/pressure/sdp500.c b/drivers/iio/pressure/sdp500.c index 6ff32e3fa637..9828c73c4855 100644 --- a/drivers/iio/pressure/sdp500.c +++ b/drivers/iio/pressure/sdp500.c @@ -10,7 +10,7 @@ #include <linux/iio/iio.h> #include <linux/mod_devicetable.h> #include <linux/regulator/consumer.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define SDP500_CRC8_POLYNOMIAL 0x31 /* x8+x5+x4+1 (normalized to 0x31) */ #define SDP500_READ_SIZE 3 diff --git a/drivers/iio/pressure/st_pressure_core.c b/drivers/iio/pressure/st_pressure_core.c index 80176e3083af..597bf268ea51 100644 --- a/drivers/iio/pressure/st_pressure_core.c +++ b/drivers/iio/pressure/st_pressure_core.c @@ -14,7 +14,7 @@ #include <linux/iio/iio.h> #include <linux/iio/sysfs.h> #include <linux/iio/trigger.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/iio/common/st_sensors.h> #include "st_pressure.h" diff --git a/drivers/iio/pressure/zpa2326.c b/drivers/iio/pressure/zpa2326.c index dcc87a9015e8..950f8dee2b26 100644 --- a/drivers/iio/pressure/zpa2326.c +++ b/drivers/iio/pressure/zpa2326.c @@ -64,7 +64,7 @@ #include <linux/iio/trigger.h> #include <linux/iio/trigger_consumer.h> #include <linux/iio/triggered_buffer.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "zpa2326.h" /* 200 ms should be enough for the longest conversion time in one-shot mode. */ diff --git a/drivers/iio/proximity/aw96103.c b/drivers/iio/proximity/aw96103.c index db9d78e961fd..707ba0a510aa 100644 --- a/drivers/iio/proximity/aw96103.c +++ b/drivers/iio/proximity/aw96103.c @@ -17,7 +17,7 @@ #include <linux/regulator/consumer.h> #include <linux/regmap.h> #include <linux/slab.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define AW_DATA_PROCESS_FACTOR 1024 #define AW96103_CHIP_ID 0xa961 diff --git a/drivers/iio/proximity/cros_ec_mkbp_proximity.c b/drivers/iio/proximity/cros_ec_mkbp_proximity.c index cff57d851762..c25472b14d4b 100644 --- a/drivers/iio/proximity/cros_ec_mkbp_proximity.c +++ b/drivers/iio/proximity/cros_ec_mkbp_proximity.c @@ -21,7 +21,7 @@ #include <linux/iio/iio.h> #include <linux/iio/sysfs.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> struct cros_ec_mkbp_proximity_data { struct cros_ec_device *ec; diff --git a/drivers/iio/proximity/hx9023s.c b/drivers/iio/proximity/hx9023s.c index 8b9f84400e00..d8fb34060d3d 100644 --- a/drivers/iio/proximity/hx9023s.c +++ b/drivers/iio/proximity/hx9023s.c @@ -29,7 +29,7 @@ #include <linux/units.h> #include <asm/byteorder.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/iio/buffer.h> #include <linux/iio/events.h> diff --git a/drivers/iio/proximity/irsd200.c b/drivers/iio/proximity/irsd200.c index 323ac6dac90e..6e96b764fed8 100644 --- a/drivers/iio/proximity/irsd200.c +++ b/drivers/iio/proximity/irsd200.c @@ -5,7 +5,7 @@ * Copyright (C) 2023 Axis Communications AB */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/bitfield.h> #include <linux/i2c.h> #include <linux/module.h> diff --git a/drivers/iio/temperature/ltc2983.c b/drivers/iio/temperature/ltc2983.c index 21f2cfc55bf8..f8ea2219ab48 100644 --- a/drivers/iio/temperature/ltc2983.c +++ b/drivers/iio/temperature/ltc2983.c @@ -22,7 +22,7 @@ #include <linux/spi/spi.h> #include <asm/byteorder.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /* register map */ #define LTC2983_STATUS_REG 0x0000 diff --git a/drivers/iio/temperature/max31856.c b/drivers/iio/temperature/max31856.c index 8307aae2cb45..7ddec5cbe558 100644 --- a/drivers/iio/temperature/max31856.c +++ b/drivers/iio/temperature/max31856.c @@ -16,7 +16,7 @@ #include <linux/iio/iio.h> #include <linux/iio/sysfs.h> #include <linux/util_macros.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <dt-bindings/iio/temperature/thermocouple.h> /* * The MSB of the register value determines whether the following byte will diff --git a/drivers/iio/temperature/max31865.c b/drivers/iio/temperature/max31865.c index 29e23652ba5a..5a6fbe3c80e5 100644 --- a/drivers/iio/temperature/max31865.c +++ b/drivers/iio/temperature/max31865.c @@ -18,7 +18,7 @@ #include <linux/iio/sysfs.h> #include <linux/property.h> #include <linux/spi/spi.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /* * The MSB of the register value determines whether the following byte will diff --git a/drivers/input/joystick/adafruit-seesaw.c b/drivers/input/joystick/adafruit-seesaw.c index 5c775ca886a5..c248c15b849d 100644 --- a/drivers/input/joystick/adafruit-seesaw.c +++ b/drivers/input/joystick/adafruit-seesaw.c @@ -15,7 +15,7 @@ * - Add interrupt support */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/bits.h> #include <linux/delay.h> #include <linux/i2c.h> diff --git a/drivers/input/joystick/adc-joystick.c b/drivers/input/joystick/adc-joystick.c index 02713e624df1..ff44f9978b71 100644 --- a/drivers/input/joystick/adc-joystick.c +++ b/drivers/input/joystick/adc-joystick.c @@ -11,7 +11,7 @@ #include <linux/platform_device.h> #include <linux/property.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> struct adc_joystick_axis { u32 code; diff --git a/drivers/input/joystick/iforce/iforce-main.c b/drivers/input/joystick/iforce/iforce-main.c index 84b87526b7ba..55e6321adab9 100644 --- a/drivers/input/joystick/iforce/iforce-main.c +++ b/drivers/input/joystick/iforce/iforce-main.c @@ -6,7 +6,7 @@ * USB/RS232 I-Force joysticks and wheels. */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "iforce.h" MODULE_AUTHOR("Vojtech Pavlik <vojtech@ucw.cz>, Johann Deneux <johann.deneux@gmail.com>"); diff --git a/drivers/input/joystick/iforce/iforce-packets.c b/drivers/input/joystick/iforce/iforce-packets.c index 763642c8cee9..08c889a72f6c 100644 --- a/drivers/input/joystick/iforce/iforce-packets.c +++ b/drivers/input/joystick/iforce/iforce-packets.c @@ -6,7 +6,7 @@ * USB/RS232 I-Force joysticks and wheels. */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "iforce.h" static struct { diff --git a/drivers/input/joystick/spaceball.c b/drivers/input/joystick/spaceball.c index 49101f1c858b..4f2221001a95 100644 --- a/drivers/input/joystick/spaceball.c +++ b/drivers/input/joystick/spaceball.c @@ -16,7 +16,7 @@ #include <linux/module.h> #include <linux/input.h> #include <linux/serio.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define DRIVER_DESC "SpaceTec SpaceBall 2003/3003/4000 FLX driver" diff --git a/drivers/input/keyboard/adp5589-keys.c b/drivers/input/keyboard/adp5589-keys.c index 8996e00cd63a..922d3ab998f3 100644 --- a/drivers/input/keyboard/adp5589-keys.c +++ b/drivers/input/keyboard/adp5589-keys.c @@ -391,10 +391,17 @@ static int adp5589_gpio_get_value(struct gpio_chip *chip, unsigned off) struct adp5589_kpad *kpad = gpiochip_get_data(chip); unsigned int bank = kpad->var->bank(kpad->gpiomap[off]); unsigned int bit = kpad->var->bit(kpad->gpiomap[off]); + int val; - return !!(adp5589_read(kpad->client, - kpad->var->reg(ADP5589_GPI_STATUS_A) + bank) & - bit); + mutex_lock(&kpad->gpio_lock); + if (kpad->dir[bank] & bit) + val = kpad->dat_out[bank]; + else + val = adp5589_read(kpad->client, + kpad->var->reg(ADP5589_GPI_STATUS_A) + bank); + mutex_unlock(&kpad->gpio_lock); + + return !!(val & bit); } static void adp5589_gpio_set_value(struct gpio_chip *chip, @@ -936,10 +943,9 @@ static int adp5589_keypad_add(struct adp5589_kpad *kpad, unsigned int revid) static void adp5589_clear_config(void *data) { - struct i2c_client *client = data; - struct adp5589_kpad *kpad = i2c_get_clientdata(client); + struct adp5589_kpad *kpad = data; - adp5589_write(client, kpad->var->reg(ADP5589_GENERAL_CFG), 0); + adp5589_write(kpad->client, kpad->var->reg(ADP5589_GENERAL_CFG), 0); } static int adp5589_probe(struct i2c_client *client) @@ -983,7 +989,7 @@ static int adp5589_probe(struct i2c_client *client) } error = devm_add_action_or_reset(&client->dev, adp5589_clear_config, - client); + kpad); if (error) return error; @@ -1010,8 +1016,6 @@ static int adp5589_probe(struct i2c_client *client) if (error) return error; - i2c_set_clientdata(client, kpad); - dev_info(&client->dev, "Rev.%d keypad, irq %d\n", revid, client->irq); return 0; } diff --git a/drivers/input/keyboard/applespi.c b/drivers/input/keyboard/applespi.c index 707c5a8ae736..2c993fa8306a 100644 --- a/drivers/input/keyboard/applespi.c +++ b/drivers/input/keyboard/applespi.c @@ -57,7 +57,7 @@ #include <linux/workqueue.h> #include <asm/barrier.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define CREATE_TRACE_POINTS #include "applespi.h" diff --git a/drivers/input/keyboard/cros_ec_keyb.c b/drivers/input/keyboard/cros_ec_keyb.c index 12eb9df180ee..4c81b20ff6af 100644 --- a/drivers/input/keyboard/cros_ec_keyb.c +++ b/drivers/input/keyboard/cros_ec_keyb.c @@ -27,7 +27,7 @@ #include <linux/platform_data/cros_ec_commands.h> #include <linux/platform_data/cros_ec_proto.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /** * struct cros_ec_keyb - Structure representing EC keyboard device diff --git a/drivers/input/misc/ims-pcu.c b/drivers/input/misc/ims-pcu.c index 058f3470b7ae..4215f9b9c2b0 100644 --- a/drivers/input/misc/ims-pcu.c +++ b/drivers/input/misc/ims-pcu.c @@ -17,7 +17,7 @@ #include <linux/types.h> #include <linux/usb/input.h> #include <linux/usb/cdc.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define IMS_PCU_KEYMAP_LEN 32 diff --git a/drivers/input/misc/iqs7222.c b/drivers/input/misc/iqs7222.c index 9ca5a743f19f..be80a31de9f8 100644 --- a/drivers/input/misc/iqs7222.c +++ b/drivers/input/misc/iqs7222.c @@ -20,7 +20,7 @@ #include <linux/module.h> #include <linux/property.h> #include <linux/slab.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define IQS7222_PROD_NUM 0x00 #define IQS7222_PROD_NUM_A 840 diff --git a/drivers/input/mouse/Kconfig b/drivers/input/mouse/Kconfig index 8a27a20d04b0..833b643f0616 100644 --- a/drivers/input/mouse/Kconfig +++ b/drivers/input/mouse/Kconfig @@ -69,18 +69,6 @@ config MOUSE_PS2_LOGIPS2PP If unsure, say Y. -config MOUSE_PS2_PIXART - bool "PixArt PS/2 touchpad protocol extension" if EXPERT - default y - depends on MOUSE_PS2 - help - This driver supports the PixArt PS/2 touchpad found in some - laptops. - Say Y here if you have a PixArt PS/2 TouchPad connected to - your system. - - If unsure, say Y. - config MOUSE_PS2_SYNAPTICS bool "Synaptics PS/2 mouse protocol extension" if EXPERT default y diff --git a/drivers/input/mouse/Makefile b/drivers/input/mouse/Makefile index 563029551529..a1336d5bee6f 100644 --- a/drivers/input/mouse/Makefile +++ b/drivers/input/mouse/Makefile @@ -32,7 +32,6 @@ psmouse-$(CONFIG_MOUSE_PS2_ELANTECH) += elantech.o psmouse-$(CONFIG_MOUSE_PS2_OLPC) += hgpk.o psmouse-$(CONFIG_MOUSE_PS2_LOGIPS2PP) += logips2pp.o psmouse-$(CONFIG_MOUSE_PS2_LIFEBOOK) += lifebook.o -psmouse-$(CONFIG_MOUSE_PS2_PIXART) += pixart_ps2.o psmouse-$(CONFIG_MOUSE_PS2_SENTELIC) += sentelic.o psmouse-$(CONFIG_MOUSE_PS2_TRACKPOINT) += trackpoint.o psmouse-$(CONFIG_MOUSE_PS2_TOUCHKIT) += touchkit_ps2.o diff --git a/drivers/input/mouse/cyapa_gen3.c b/drivers/input/mouse/cyapa_gen3.c index 60c83bc71d84..fc3fb954523b 100644 --- a/drivers/input/mouse/cyapa_gen3.c +++ b/drivers/input/mouse/cyapa_gen3.c @@ -20,7 +20,7 @@ #include <linux/input/mt.h> #include <linux/module.h> #include <linux/slab.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "cyapa.h" diff --git a/drivers/input/mouse/cyapa_gen5.c b/drivers/input/mouse/cyapa_gen5.c index 2e6bcb07257e..3b4439f10635 100644 --- a/drivers/input/mouse/cyapa_gen5.c +++ b/drivers/input/mouse/cyapa_gen5.c @@ -17,7 +17,7 @@ #include <linux/mutex.h> #include <linux/completion.h> #include <linux/slab.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/crc-itu-t.h> #include <linux/pm_runtime.h> #include "cyapa.h" diff --git a/drivers/input/mouse/cyapa_gen6.c b/drivers/input/mouse/cyapa_gen6.c index 4ffe08fee10c..570c06dcef78 100644 --- a/drivers/input/mouse/cyapa_gen6.c +++ b/drivers/input/mouse/cyapa_gen6.c @@ -17,7 +17,7 @@ #include <linux/mutex.h> #include <linux/completion.h> #include <linux/slab.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/crc-itu-t.h> #include "cyapa.h" diff --git a/drivers/input/mouse/elan_i2c_core.c b/drivers/input/mouse/elan_i2c_core.c index ce96513b34f6..7521981274bd 100644 --- a/drivers/input/mouse/elan_i2c_core.c +++ b/drivers/input/mouse/elan_i2c_core.c @@ -36,7 +36,7 @@ #include <linux/pm_wakeirq.h> #include <linux/property.h> #include <linux/regulator/consumer.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "elan_i2c.h" diff --git a/drivers/input/mouse/elan_i2c_i2c.c b/drivers/input/mouse/elan_i2c_i2c.c index 13dc097eb6c6..15cf4463b64e 100644 --- a/drivers/input/mouse/elan_i2c_i2c.c +++ b/drivers/input/mouse/elan_i2c_i2c.c @@ -21,7 +21,7 @@ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/sched.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "elan_i2c.h" diff --git a/drivers/input/mouse/elantech.c b/drivers/input/mouse/elantech.c index b4723ea395eb..79ad98cc1e79 100644 --- a/drivers/input/mouse/elantech.c +++ b/drivers/input/mouse/elantech.c @@ -17,7 +17,7 @@ #include <linux/platform_device.h> #include <linux/serio.h> #include <linux/libps2.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "psmouse.h" #include "elantech.h" #include "elan_i2c.h" diff --git a/drivers/input/mouse/pixart_ps2.c b/drivers/input/mouse/pixart_ps2.c deleted file mode 100644 index 1993fc760d7b..000000000000 --- a/drivers/input/mouse/pixart_ps2.c +++ /dev/null @@ -1,300 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * Pixart Touchpad Controller 1336U PS2 driver - * - * Author: Jon Xie <jon_xie@pixart.com> - * Jay Lee <jay_lee@pixart.com> - * Further cleanup and restructuring by: - * Binbin Zhou <zhoubinbin@loongson.cn> - * - * Copyright (C) 2021-2024 Pixart Imaging. - * Copyright (C) 2024 Loongson Technology Corporation Limited. - * - */ - -#include <linux/bitfield.h> -#include <linux/delay.h> -#include <linux/device.h> -#include <linux/input.h> -#include <linux/input/mt.h> -#include <linux/libps2.h> -#include <linux/serio.h> -#include <linux/slab.h> - -#include "pixart_ps2.h" - -static int pixart_read_tp_mode(struct ps2dev *ps2dev, u8 *mode) -{ - int error; - u8 param[1] = { 0 }; - - error = ps2_command(ps2dev, param, PIXART_CMD_REPORT_FORMAT); - if (error) - return error; - - *mode = param[0] == 1 ? PIXART_MODE_ABS : PIXART_MODE_REL; - - return 0; -} - -static int pixart_read_tp_type(struct ps2dev *ps2dev, u8 *type) -{ - int error; - u8 param[3] = { 0 }; - - param[0] = 0x0a; - error = ps2_command(ps2dev, param, PSMOUSE_CMD_SETRATE); - if (error) - return error; - - param[0] = 0x0; - error = ps2_command(ps2dev, param, PSMOUSE_CMD_SETRES); - if (error) - return error; - - error = ps2_command(ps2dev, param, PSMOUSE_CMD_SETRES); - if (error) - return error; - - error = ps2_command(ps2dev, param, PSMOUSE_CMD_SETRES); - if (error) - return error; - - param[0] = 0x03; - error = ps2_command(ps2dev, param, PSMOUSE_CMD_SETRES); - if (error) - return error; - - error = ps2_command(ps2dev, param, PSMOUSE_CMD_GETINFO); - if (error) - return error; - - *type = param[0] == 0x0e ? PIXART_TYPE_TOUCHPAD : PIXART_TYPE_CLICKPAD; - - return 0; -} - -static void pixart_reset(struct psmouse *psmouse) -{ - ps2_command(&psmouse->ps2dev, NULL, PSMOUSE_CMD_RESET_DIS); - - /* according to PixArt, 100ms is required for the upcoming reset */ - msleep(100); - psmouse_reset(psmouse); -} - -static void pixart_process_packet(struct psmouse *psmouse) -{ - struct pixart_data *priv = psmouse->private; - struct input_dev *dev = psmouse->dev; - const u8 *pkt = psmouse->packet; - unsigned int contact_cnt = FIELD_GET(CONTACT_CNT_MASK, pkt[0]); - unsigned int i, id, abs_x, abs_y; - bool tip; - - for (i = 0; i < contact_cnt; i++) { - const u8 *p = &pkt[i * 3]; - - id = FIELD_GET(SLOT_ID_MASK, p[3]); - abs_y = FIELD_GET(ABS_Y_MASK, p[3]) << 8 | p[1]; - abs_x = FIELD_GET(ABS_X_MASK, p[3]) << 8 | p[2]; - - if (i == PIXART_MAX_FINGERS - 1) - tip = pkt[14] & BIT(1); - else - tip = pkt[3 * contact_cnt + 1] & BIT(2 * i + 1); - - input_mt_slot(dev, id); - if (input_mt_report_slot_state(dev, MT_TOOL_FINGER, tip)) { - input_report_abs(dev, ABS_MT_POSITION_Y, abs_y); - input_report_abs(dev, ABS_MT_POSITION_X, abs_x); - } - } - - input_mt_sync_frame(dev); - - if (priv->type == PIXART_TYPE_CLICKPAD) { - input_report_key(dev, BTN_LEFT, pkt[0] & 0x03); - } else { - input_report_key(dev, BTN_LEFT, pkt[0] & BIT(0)); - input_report_key(dev, BTN_RIGHT, pkt[0] & BIT(1)); - } - - input_sync(dev); -} - -static psmouse_ret_t pixart_protocol_handler(struct psmouse *psmouse) -{ - u8 *pkt = psmouse->packet; - u8 contact_cnt; - - if ((pkt[0] & 0x8c) != 0x80) - return PSMOUSE_BAD_DATA; - - contact_cnt = FIELD_GET(CONTACT_CNT_MASK, pkt[0]); - if (contact_cnt > PIXART_MAX_FINGERS) - return PSMOUSE_BAD_DATA; - - if (contact_cnt == PIXART_MAX_FINGERS && - psmouse->pktcnt < psmouse->pktsize) { - return PSMOUSE_GOOD_DATA; - } - - if (contact_cnt == 0 && psmouse->pktcnt < 5) - return PSMOUSE_GOOD_DATA; - - if (psmouse->pktcnt < 3 * contact_cnt + 2) - return PSMOUSE_GOOD_DATA; - - pixart_process_packet(psmouse); - - return PSMOUSE_FULL_PACKET; -} - -static void pixart_disconnect(struct psmouse *psmouse) -{ - pixart_reset(psmouse); - kfree(psmouse->private); - psmouse->private = NULL; -} - -static int pixart_reconnect(struct psmouse *psmouse) -{ - struct ps2dev *ps2dev = &psmouse->ps2dev; - u8 mode; - int error; - - pixart_reset(psmouse); - - error = pixart_read_tp_mode(ps2dev, &mode); - if (error) - return error; - - if (mode != PIXART_MODE_ABS) - return -EIO; - - error = ps2_command(ps2dev, NULL, PIXART_CMD_SWITCH_PROTO); - if (error) - return error; - - return 0; -} - -static int pixart_set_input_params(struct input_dev *dev, - struct pixart_data *priv) -{ - /* No relative support */ - __clear_bit(EV_REL, dev->evbit); - __clear_bit(REL_X, dev->relbit); - __clear_bit(REL_Y, dev->relbit); - __clear_bit(BTN_MIDDLE, dev->keybit); - - /* Buttons */ - __set_bit(EV_KEY, dev->evbit); - __set_bit(BTN_LEFT, dev->keybit); - if (priv->type == PIXART_TYPE_CLICKPAD) - __set_bit(INPUT_PROP_BUTTONPAD, dev->propbit); - else - __set_bit(BTN_RIGHT, dev->keybit); - - /* Absolute position */ - input_set_abs_params(dev, ABS_X, 0, PIXART_PAD_WIDTH, 0, 0); - input_set_abs_params(dev, ABS_Y, 0, PIXART_PAD_HEIGHT, 0, 0); - - input_set_abs_params(dev, ABS_MT_POSITION_X, - 0, PIXART_PAD_WIDTH, 0, 0); - input_set_abs_params(dev, ABS_MT_POSITION_Y, - 0, PIXART_PAD_HEIGHT, 0, 0); - - return input_mt_init_slots(dev, PIXART_MAX_FINGERS, INPUT_MT_POINTER); -} - -static int pixart_query_hardware(struct ps2dev *ps2dev, u8 *mode, u8 *type) -{ - int error; - - error = pixart_read_tp_type(ps2dev, type); - if (error) - return error; - - error = pixart_read_tp_mode(ps2dev, mode); - if (error) - return error; - - return 0; -} - -int pixart_detect(struct psmouse *psmouse, bool set_properties) -{ - u8 type; - int error; - - pixart_reset(psmouse); - - error = pixart_read_tp_type(&psmouse->ps2dev, &type); - if (error) - return error; - - if (set_properties) { - psmouse->vendor = "PixArt"; - psmouse->name = (type == PIXART_TYPE_TOUCHPAD) ? - "touchpad" : "clickpad"; - } - - return 0; -} - -int pixart_init(struct psmouse *psmouse) -{ - int error; - struct pixart_data *priv; - - priv = kzalloc(sizeof(*priv), GFP_KERNEL); - if (!priv) - return -ENOMEM; - - psmouse->private = priv; - pixart_reset(psmouse); - - error = pixart_query_hardware(&psmouse->ps2dev, - &priv->mode, &priv->type); - if (error) { - psmouse_err(psmouse, "init: Unable to query PixArt touchpad hardware.\n"); - goto err_exit; - } - - /* Relative mode follows standard PS/2 mouse protocol */ - if (priv->mode != PIXART_MODE_ABS) { - error = -EIO; - goto err_exit; - } - - /* Set absolute mode */ - error = ps2_command(&psmouse->ps2dev, NULL, PIXART_CMD_SWITCH_PROTO); - if (error) { - psmouse_err(psmouse, "init: Unable to initialize PixArt absolute mode.\n"); - goto err_exit; - } - - error = pixart_set_input_params(psmouse->dev, priv); - if (error) { - psmouse_err(psmouse, "init: Unable to set input params.\n"); - goto err_exit; - } - - psmouse->pktsize = 15; - psmouse->protocol_handler = pixart_protocol_handler; - psmouse->disconnect = pixart_disconnect; - psmouse->reconnect = pixart_reconnect; - psmouse->cleanup = pixart_reset; - /* resync is not supported yet */ - psmouse->resync_time = 0; - - return 0; - -err_exit: - pixart_reset(psmouse); - kfree(priv); - psmouse->private = NULL; - return error; -} diff --git a/drivers/input/mouse/pixart_ps2.h b/drivers/input/mouse/pixart_ps2.h deleted file mode 100644 index 47a1d040f2d1..000000000000 --- a/drivers/input/mouse/pixart_ps2.h +++ /dev/null @@ -1,36 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -#ifndef _PIXART_PS2_H -#define _PIXART_PS2_H - -#include "psmouse.h" - -#define PIXART_PAD_WIDTH 1023 -#define PIXART_PAD_HEIGHT 579 -#define PIXART_MAX_FINGERS 4 - -#define PIXART_CMD_REPORT_FORMAT 0x01d8 -#define PIXART_CMD_SWITCH_PROTO 0x00de - -#define PIXART_MODE_REL 0 -#define PIXART_MODE_ABS 1 - -#define PIXART_TYPE_CLICKPAD 0 -#define PIXART_TYPE_TOUCHPAD 1 - -#define CONTACT_CNT_MASK GENMASK(6, 4) - -#define SLOT_ID_MASK GENMASK(2, 0) -#define ABS_Y_MASK GENMASK(5, 4) -#define ABS_X_MASK GENMASK(7, 6) - -struct pixart_data { - u8 mode; - u8 type; - int x_max; - int y_max; -}; - -int pixart_detect(struct psmouse *psmouse, bool set_properties); -int pixart_init(struct psmouse *psmouse); - -#endif /* _PIXART_PS2_H */ diff --git a/drivers/input/mouse/psmouse-base.c b/drivers/input/mouse/psmouse-base.c index 5a4defe9cf32..a2c9f7144864 100644 --- a/drivers/input/mouse/psmouse-base.c +++ b/drivers/input/mouse/psmouse-base.c @@ -36,7 +36,6 @@ #include "focaltech.h" #include "vmmouse.h" #include "byd.h" -#include "pixart_ps2.h" #define DRIVER_DESC "PS/2 mouse driver" @@ -907,15 +906,6 @@ static const struct psmouse_protocol psmouse_protocols[] = { .init = byd_init, }, #endif -#ifdef CONFIG_MOUSE_PS2_PIXART - { - .type = PSMOUSE_PIXART, - .name = "PixArtPS/2", - .alias = "pixart", - .detect = pixart_detect, - .init = pixart_init, - }, -#endif { .type = PSMOUSE_AUTO, .name = "auto", @@ -1182,13 +1172,6 @@ static int psmouse_extensions(struct psmouse *psmouse, return ret; } - /* Try PixArt touchpad */ - if (max_proto > PSMOUSE_IMEX && - psmouse_try_protocol(psmouse, PSMOUSE_PIXART, &max_proto, - set_properties, true)) { - return PSMOUSE_PIXART; - } - if (max_proto > PSMOUSE_IMEX) { if (psmouse_try_protocol(psmouse, PSMOUSE_GENPS, &max_proto, set_properties, true)) diff --git a/drivers/input/mouse/psmouse.h b/drivers/input/mouse/psmouse.h index 23f7fa7243cb..4d8acfe0d82a 100644 --- a/drivers/input/mouse/psmouse.h +++ b/drivers/input/mouse/psmouse.h @@ -69,7 +69,6 @@ enum psmouse_type { PSMOUSE_BYD, PSMOUSE_SYNAPTICS_SMBUS, PSMOUSE_ELANTECH_SMBUS, - PSMOUSE_PIXART, PSMOUSE_AUTO /* This one should always be last */ }; @@ -95,7 +94,7 @@ struct psmouse { const char *vendor; const char *name; const struct psmouse_protocol *protocol; - unsigned char packet[16]; + unsigned char packet[8]; unsigned char badbyte; unsigned char pktcnt; unsigned char pktsize; diff --git a/drivers/input/rmi4/rmi_f01.c b/drivers/input/rmi4/rmi_f01.c index cc1d4b424640..47be64284b25 100644 --- a/drivers/input/rmi4/rmi_f01.c +++ b/drivers/input/rmi4/rmi_f01.c @@ -9,7 +9,7 @@ #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/of.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "rmi_driver.h" #define RMI_PRODUCT_ID_LENGTH 10 diff --git a/drivers/input/rmi4/rmi_f34.c b/drivers/input/rmi4/rmi_f34.c index 3b3ac71e53dc..e2468bc04a5c 100644 --- a/drivers/input/rmi4/rmi_f34.c +++ b/drivers/input/rmi4/rmi_f34.c @@ -7,7 +7,7 @@ #include <linux/kernel.h> #include <linux/rmi.h> #include <linux/firmware.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/bitops.h> #include "rmi_driver.h" diff --git a/drivers/input/rmi4/rmi_f34v7.c b/drivers/input/rmi4/rmi_f34v7.c index 886557b01eba..fd49acc02071 100644 --- a/drivers/input/rmi4/rmi_f34v7.c +++ b/drivers/input/rmi4/rmi_f34v7.c @@ -13,7 +13,7 @@ #include <linux/delay.h> #include <linux/slab.h> #include <linux/jiffies.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "rmi_driver.h" #include "rmi_f34.h" diff --git a/drivers/input/tablet/aiptek.c b/drivers/input/tablet/aiptek.c index 2d176fbab251..2b3fbb0455d5 100644 --- a/drivers/input/tablet/aiptek.c +++ b/drivers/input/tablet/aiptek.c @@ -63,7 +63,7 @@ #include <linux/module.h> #include <linux/usb/input.h> #include <linux/uaccess.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /* * Aiptek status packet: diff --git a/drivers/input/tablet/kbtab.c b/drivers/input/tablet/kbtab.c index 38d36d25f6f4..794caa102909 100644 --- a/drivers/input/tablet/kbtab.c +++ b/drivers/input/tablet/kbtab.c @@ -3,7 +3,7 @@ #include <linux/slab.h> #include <linux/module.h> #include <linux/usb/input.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /* * Pressure-threshold modules param code from Alex Perry <alex.perry@ieee.org> diff --git a/drivers/input/touchscreen/ads7846.c b/drivers/input/touchscreen/ads7846.c index f89c0dd15d8b..607f18af7010 100644 --- a/drivers/input/touchscreen/ads7846.c +++ b/drivers/input/touchscreen/ads7846.c @@ -30,7 +30,7 @@ #include <linux/spi/ads7846.h> #include <linux/regulator/consumer.h> #include <linux/module.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /* * This code has been heavily tested on a Nokia 770, and lightly diff --git a/drivers/input/touchscreen/atmel_mxt_ts.c b/drivers/input/touchscreen/atmel_mxt_ts.c index cfc92157701f..3ddabc5a2c99 100644 --- a/drivers/input/touchscreen/atmel_mxt_ts.c +++ b/drivers/input/touchscreen/atmel_mxt_ts.c @@ -26,7 +26,7 @@ #include <linux/slab.h> #include <linux/regulator/consumer.h> #include <linux/gpio/consumer.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <media/v4l2-device.h> #include <media/v4l2-ioctl.h> #include <media/videobuf2-v4l2.h> diff --git a/drivers/input/touchscreen/chipone_icn8505.c b/drivers/input/touchscreen/chipone_icn8505.c index c1b4fc28fa8d..cde0e4789503 100644 --- a/drivers/input/touchscreen/chipone_icn8505.c +++ b/drivers/input/touchscreen/chipone_icn8505.c @@ -8,7 +8,7 @@ * Hans de Goede <hdegoede@redhat.com> */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/acpi.h> #include <linux/crc32.h> #include <linux/delay.h> diff --git a/drivers/input/touchscreen/cy8ctma140.c b/drivers/input/touchscreen/cy8ctma140.c index 567c9dcaac91..2d4b6e343203 100644 --- a/drivers/input/touchscreen/cy8ctma140.c +++ b/drivers/input/touchscreen/cy8ctma140.c @@ -16,7 +16,7 @@ * same. */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/input.h> diff --git a/drivers/input/touchscreen/cyttsp5.c b/drivers/input/touchscreen/cyttsp5.c index 3ca246ab192e..eafe5a9b8964 100644 --- a/drivers/input/touchscreen/cyttsp5.c +++ b/drivers/input/touchscreen/cyttsp5.c @@ -21,7 +21,7 @@ #include <linux/mod_devicetable.h> #include <linux/module.h> #include <linux/regmap.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define CYTTSP5_NAME "cyttsp5" #define CY_I2C_DATA_SIZE (2 * 256) diff --git a/drivers/input/touchscreen/edt-ft5x06.c b/drivers/input/touchscreen/edt-ft5x06.c index e70415f189a5..fda49b2fe088 100644 --- a/drivers/input/touchscreen/edt-ft5x06.c +++ b/drivers/input/touchscreen/edt-ft5x06.c @@ -32,7 +32,7 @@ #include <linux/slab.h> #include <linux/uaccess.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define WORK_REGISTER_THRESHOLD 0x00 #define WORK_REGISTER_REPORT_RATE 0x08 diff --git a/drivers/input/touchscreen/eeti_ts.c b/drivers/input/touchscreen/eeti_ts.c index 48c69788b84a..87eb18977b71 100644 --- a/drivers/input/touchscreen/eeti_ts.c +++ b/drivers/input/touchscreen/eeti_ts.c @@ -21,7 +21,7 @@ #include <linux/gpio/consumer.h> #include <linux/of.h> #include <linux/slab.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> struct eeti_ts { struct i2c_client *client; diff --git a/drivers/input/touchscreen/elants_i2c.c b/drivers/input/touchscreen/elants_i2c.c index 365765d40e62..3fd170f75b4a 100644 --- a/drivers/input/touchscreen/elants_i2c.c +++ b/drivers/input/touchscreen/elants_i2c.c @@ -40,7 +40,7 @@ #include <linux/gpio/consumer.h> #include <linux/regulator/consumer.h> #include <linux/uuid.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /* Device, Driver information */ #define DEVICE_NAME "elants_i2c" diff --git a/drivers/input/touchscreen/exc3000.c b/drivers/input/touchscreen/exc3000.c index 2e77cfb63f32..fdda8412b164 100644 --- a/drivers/input/touchscreen/exc3000.c +++ b/drivers/input/touchscreen/exc3000.c @@ -22,7 +22,7 @@ #include <linux/regulator/consumer.h> #include <linux/sizes.h> #include <linux/timer.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define EXC3000_NUM_SLOTS 10 #define EXC3000_SLOTS_PER_FRAME 5 diff --git a/drivers/input/touchscreen/goodix.c b/drivers/input/touchscreen/goodix.c index 435714f18c23..a3e8a51c9144 100644 --- a/drivers/input/touchscreen/goodix.c +++ b/drivers/input/touchscreen/goodix.c @@ -22,7 +22,7 @@ #include <linux/slab.h> #include <linux/acpi.h> #include <linux/of.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "goodix.h" #define GOODIX_GPIO_INT_NAME "irq" diff --git a/drivers/input/touchscreen/goodix_berlin_core.c b/drivers/input/touchscreen/goodix_berlin_core.c index 0bfca897ce5a..3fc03cf0ca23 100644 --- a/drivers/input/touchscreen/goodix_berlin_core.c +++ b/drivers/input/touchscreen/goodix_berlin_core.c @@ -31,7 +31,7 @@ #include <linux/regmap.h> #include <linux/regulator/consumer.h> #include <linux/sizes.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "goodix_berlin.h" diff --git a/drivers/input/touchscreen/goodix_berlin_spi.c b/drivers/input/touchscreen/goodix_berlin_spi.c index a2d80e84391b..0662e87b8692 100644 --- a/drivers/input/touchscreen/goodix_berlin_spi.c +++ b/drivers/input/touchscreen/goodix_berlin_spi.c @@ -7,7 +7,7 @@ * * Based on goodix_ts_berlin driver. */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/regmap.h> diff --git a/drivers/input/touchscreen/hideep.c b/drivers/input/touchscreen/hideep.c index 682abbbe5bd6..a73369e15dda 100644 --- a/drivers/input/touchscreen/hideep.c +++ b/drivers/input/touchscreen/hideep.c @@ -17,7 +17,7 @@ #include <linux/input/mt.h> #include <linux/input/touchscreen.h> #include <linux/regulator/consumer.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define HIDEEP_TS_NAME "HiDeep Touchscreen" #define HIDEEP_I2C_NAME "hideep_ts" diff --git a/drivers/input/touchscreen/hycon-hy46xx.c b/drivers/input/touchscreen/hycon-hy46xx.c index 2e01d87977c1..b2ff7a45b908 100644 --- a/drivers/input/touchscreen/hycon-hy46xx.c +++ b/drivers/input/touchscreen/hycon-hy46xx.c @@ -15,7 +15,7 @@ #include <linux/regulator/consumer.h> #include <linux/regmap.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define HY46XX_CHKSUM_CODE 0x1 #define HY46XX_FINGER_NUM 0x2 diff --git a/drivers/input/touchscreen/hynitron_cstxxx.c b/drivers/input/touchscreen/hynitron_cstxxx.c index f72834859282..1d8ca90dcda6 100644 --- a/drivers/input/touchscreen/hynitron_cstxxx.c +++ b/drivers/input/touchscreen/hynitron_cstxxx.c @@ -22,7 +22,7 @@ #include <linux/mod_devicetable.h> #include <linux/module.h> #include <linux/property.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /* Per chip data */ struct hynitron_ts_chip_data { diff --git a/drivers/input/touchscreen/ili210x.c b/drivers/input/touchscreen/ili210x.c index 4573844c3395..260c83dc23a2 100644 --- a/drivers/input/touchscreen/ili210x.c +++ b/drivers/input/touchscreen/ili210x.c @@ -12,7 +12,7 @@ #include <linux/module.h> #include <linux/sizes.h> #include <linux/slab.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define ILI2XXX_POLL_PERIOD 15 diff --git a/drivers/input/touchscreen/ilitek_ts_i2c.c b/drivers/input/touchscreen/ilitek_ts_i2c.c index 5569641f05f6..0dd632724a00 100644 --- a/drivers/input/touchscreen/ilitek_ts_i2c.c +++ b/drivers/input/touchscreen/ilitek_ts_i2c.c @@ -19,7 +19,7 @@ #include <linux/errno.h> #include <linux/acpi.h> #include <linux/input/touchscreen.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define ILITEK_TS_NAME "ilitek_ts" diff --git a/drivers/input/touchscreen/iqs5xx.c b/drivers/input/touchscreen/iqs5xx.c index 4d226118f3cc..4ebd7565ae6e 100644 --- a/drivers/input/touchscreen/iqs5xx.c +++ b/drivers/input/touchscreen/iqs5xx.c @@ -26,7 +26,7 @@ #include <linux/mod_devicetable.h> #include <linux/module.h> #include <linux/slab.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define IQS5XX_FW_FILE_LEN 64 #define IQS5XX_NUM_RETRIES 10 diff --git a/drivers/input/touchscreen/iqs7211.c b/drivers/input/touchscreen/iqs7211.c index f0a56cde899e..c5d447ee6f53 100644 --- a/drivers/input/touchscreen/iqs7211.c +++ b/drivers/input/touchscreen/iqs7211.c @@ -22,7 +22,7 @@ #include <linux/of_device.h> #include <linux/property.h> #include <linux/slab.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define IQS7211_PROD_NUM 0x00 diff --git a/drivers/input/touchscreen/melfas_mip4.c b/drivers/input/touchscreen/melfas_mip4.c index b99a0e3c4084..a6946e3d8376 100644 --- a/drivers/input/touchscreen/melfas_mip4.c +++ b/drivers/input/touchscreen/melfas_mip4.c @@ -18,7 +18,7 @@ #include <linux/module.h> #include <linux/of.h> #include <linux/slab.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define MIP4_DEVICE_NAME "mip4_ts" diff --git a/drivers/input/touchscreen/novatek-nvt-ts.c b/drivers/input/touchscreen/novatek-nvt-ts.c index 1a797e410a3f..0afee41ac9de 100644 --- a/drivers/input/touchscreen/novatek-nvt-ts.c +++ b/drivers/input/touchscreen/novatek-nvt-ts.c @@ -15,7 +15,7 @@ #include <linux/input/touchscreen.h> #include <linux/module.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define NVT_TS_TOUCH_START 0x00 #define NVT_TS_TOUCH_SIZE 6 diff --git a/drivers/input/touchscreen/pixcir_i2c_ts.c b/drivers/input/touchscreen/pixcir_i2c_ts.c index 4ede0687beb0..83bf27085ebc 100644 --- a/drivers/input/touchscreen/pixcir_i2c_ts.c +++ b/drivers/input/touchscreen/pixcir_i2c_ts.c @@ -5,7 +5,7 @@ * Copyright (C) 2010-2011 Pixcir, Inc. */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/delay.h> #include <linux/gpio/consumer.h> #include <linux/i2c.h> diff --git a/drivers/input/touchscreen/raydium_i2c_ts.c b/drivers/input/touchscreen/raydium_i2c_ts.c index 92d75057de2d..f975b53e8825 100644 --- a/drivers/input/touchscreen/raydium_i2c_ts.c +++ b/drivers/input/touchscreen/raydium_i2c_ts.c @@ -24,7 +24,7 @@ #include <linux/pm_wakeirq.h> #include <linux/regulator/consumer.h> #include <linux/slab.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /* Slave I2C mode */ #define RM_BOOT_BLDR 0x02 diff --git a/drivers/input/touchscreen/s6sy761.c b/drivers/input/touchscreen/s6sy761.c index a529217e748f..e1518a75a51b 100644 --- a/drivers/input/touchscreen/s6sy761.c +++ b/drivers/input/touchscreen/s6sy761.c @@ -4,7 +4,7 @@ // Copyright (c) 2017 Samsung Electronics Co., Ltd. // Copyright (c) 2017 Andi Shyti <andi@etezian.org> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/delay.h> #include <linux/i2c.h> #include <linux/input/mt.h> diff --git a/drivers/input/touchscreen/silead.c b/drivers/input/touchscreen/silead.c index 6a42b27c4599..5ccc96764742 100644 --- a/drivers/input/touchscreen/silead.c +++ b/drivers/input/touchscreen/silead.c @@ -24,7 +24,7 @@ #include <linux/irq.h> #include <linux/regulator/consumer.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define SILEAD_TS_NAME "silead_ts" diff --git a/drivers/input/touchscreen/sis_i2c.c b/drivers/input/touchscreen/sis_i2c.c index 2023c6df416f..a625f2ad809d 100644 --- a/drivers/input/touchscreen/sis_i2c.c +++ b/drivers/input/touchscreen/sis_i2c.c @@ -15,7 +15,7 @@ #include <linux/gpio/consumer.h> #include <linux/module.h> #include <linux/slab.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define SIS_I2C_NAME "sis_i2c_ts" diff --git a/drivers/input/touchscreen/surface3_spi.c b/drivers/input/touchscreen/surface3_spi.c index 7efbcd0fde4f..6074b7730e86 100644 --- a/drivers/input/touchscreen/surface3_spi.c +++ b/drivers/input/touchscreen/surface3_spi.c @@ -18,7 +18,7 @@ #include <linux/spi/spi.h> #include <linux/acpi.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define SURFACE3_PACKET_SIZE 264 diff --git a/drivers/input/touchscreen/wacom_i2c.c b/drivers/input/touchscreen/wacom_i2c.c index 486230985bf0..fd97a83f5664 100644 --- a/drivers/input/touchscreen/wacom_i2c.c +++ b/drivers/input/touchscreen/wacom_i2c.c @@ -13,7 +13,7 @@ #include <linux/slab.h> #include <linux/irq.h> #include <linux/interrupt.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /* Bitmasks (for data[3]) */ #define WACOM_TIP_SWITCH BIT(0) diff --git a/drivers/input/touchscreen/wdt87xx_i2c.c b/drivers/input/touchscreen/wdt87xx_i2c.c index 698fc7e0ee7f..27941245e962 100644 --- a/drivers/input/touchscreen/wdt87xx_i2c.c +++ b/drivers/input/touchscreen/wdt87xx_i2c.c @@ -20,7 +20,7 @@ #include <linux/firmware.h> #include <linux/input/mt.h> #include <linux/acpi.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define WDT87XX_NAME "wdt87xx_i2c" #define WDT87XX_FW_NAME "wdt87xx_fw.bin" diff --git a/drivers/input/touchscreen/zet6223.c b/drivers/input/touchscreen/zet6223.c index 27333fded9a9..943634ba9cd9 100644 --- a/drivers/input/touchscreen/zet6223.c +++ b/drivers/input/touchscreen/zet6223.c @@ -11,7 +11,7 @@ #include <linux/interrupt.h> #include <linux/module.h> #include <linux/regulator/consumer.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define ZET6223_MAX_FINGERS 16 #define ZET6223_MAX_PKT_SIZE (3 + 4 * ZET6223_MAX_FINGERS) diff --git a/drivers/input/touchscreen/zforce_ts.c b/drivers/input/touchscreen/zforce_ts.c index 4b8c4ebfff96..df42fdf36ae3 100644 --- a/drivers/input/touchscreen/zforce_ts.c +++ b/drivers/input/touchscreen/zforce_ts.c @@ -22,7 +22,7 @@ #include <linux/property.h> #include <linux/regulator/consumer.h> #include <linux/slab.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define WAIT_TIMEOUT msecs_to_jiffies(1000) diff --git a/drivers/isdn/hardware/mISDN/avmfritz.c b/drivers/isdn/hardware/mISDN/avmfritz.c index 509b362d6465..044e4961376c 100644 --- a/drivers/isdn/hardware/mISDN/avmfritz.c +++ b/drivers/isdn/hardware/mISDN/avmfritz.c @@ -13,7 +13,7 @@ #include <linux/delay.h> #include <linux/mISDNhw.h> #include <linux/slab.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "ipac.h" diff --git a/drivers/leds/rgb/leds-mt6370-rgb.c b/drivers/leds/rgb/leds-mt6370-rgb.c index 359ef00498b4..10a0b5b45227 100644 --- a/drivers/leds/rgb/leds-mt6370-rgb.c +++ b/drivers/leds/rgb/leds-mt6370-rgb.c @@ -21,7 +21,7 @@ #include <linux/regmap.h> #include <linux/util_macros.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> enum { MT6370_LED_ISNK1 = 0, diff --git a/drivers/macintosh/adb-iop.c b/drivers/macintosh/adb-iop.c index 2633bc254935..126dd1cfba8e 100644 --- a/drivers/macintosh/adb-iop.c +++ b/drivers/macintosh/adb-iop.c @@ -19,7 +19,7 @@ #include <asm/macints.h> #include <asm/mac_iop.h> #include <asm/adb_iop.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/adb.h> diff --git a/drivers/mailbox/Kconfig b/drivers/mailbox/Kconfig index 4eed97295927..6fb995778636 100644 --- a/drivers/mailbox/Kconfig +++ b/drivers/mailbox/Kconfig @@ -25,6 +25,7 @@ config ARM_MHU_V2 config ARM_MHU_V3 tristate "ARM MHUv3 Mailbox" + depends on ARM64 || COMPILE_TEST depends on HAS_IOMEM || COMPILE_TEST depends on OF help @@ -73,7 +74,7 @@ config ARMADA_37XX_RWTM_MBOX config OMAP2PLUS_MBOX tristate "OMAP2+ Mailbox framework support" - depends on ARCH_OMAP2PLUS || ARCH_K3 + depends on ARCH_OMAP2PLUS || ARCH_K3 || COMPILE_TEST help Mailbox implementation for OMAP family chips with hardware for interprocessor communication involving DSP, IVA1.0 and IVA2 in diff --git a/drivers/mailbox/bcm2835-mailbox.c b/drivers/mailbox/bcm2835-mailbox.c index fbfd0202047c..ea12fb8d2401 100644 --- a/drivers/mailbox/bcm2835-mailbox.c +++ b/drivers/mailbox/bcm2835-mailbox.c @@ -145,7 +145,8 @@ static int bcm2835_mbox_probe(struct platform_device *pdev) spin_lock_init(&mbox->lock); ret = devm_request_irq(dev, irq_of_parse_and_map(dev->of_node, 0), - bcm2835_mbox_irq, 0, dev_name(dev), mbox); + bcm2835_mbox_irq, IRQF_NO_SUSPEND, dev_name(dev), + mbox); if (ret) { dev_err(dev, "Failed to register a mailbox IRQ handler: %d\n", ret); diff --git a/drivers/mailbox/imx-mailbox.c b/drivers/mailbox/imx-mailbox.c index d17efb1dd0cb..f815dab3be50 100644 --- a/drivers/mailbox/imx-mailbox.c +++ b/drivers/mailbox/imx-mailbox.c @@ -30,7 +30,7 @@ #define IMX_MU_SCU_CHANS 6 /* TX0/RX0 */ #define IMX_MU_S4_CHANS 2 -#define IMX_MU_CHAN_NAME_SIZE 20 +#define IMX_MU_CHAN_NAME_SIZE 32 #define IMX_MU_V2_PAR_OFF 0x4 #define IMX_MU_V2_TR_MASK GENMASK(7, 0) @@ -782,7 +782,7 @@ static int imx_mu_init_generic(struct imx_mu_priv *priv) cp->chan = &priv->mbox_chans[i]; priv->mbox_chans[i].con_priv = cp; snprintf(cp->irq_desc, sizeof(cp->irq_desc), - "imx_mu_chan[%i-%i]", cp->type, cp->idx); + "%s[%i-%i]", dev_name(priv->dev), cp->type, cp->idx); } priv->mbox.num_chans = IMX_MU_CHANS; @@ -819,7 +819,7 @@ static int imx_mu_init_specific(struct imx_mu_priv *priv) cp->chan = &priv->mbox_chans[i]; priv->mbox_chans[i].con_priv = cp; snprintf(cp->irq_desc, sizeof(cp->irq_desc), - "imx_mu_chan[%i-%i]", cp->type, cp->idx); + "%s[%i-%i]", dev_name(priv->dev), cp->type, cp->idx); } priv->mbox.num_chans = num_chans; diff --git a/drivers/mailbox/mailbox.c b/drivers/mailbox/mailbox.c index ebff3baf3045..d3d26a2c9895 100644 --- a/drivers/mailbox/mailbox.c +++ b/drivers/mailbox/mailbox.c @@ -450,30 +450,20 @@ struct mbox_chan *mbox_request_channel_byname(struct mbox_client *cl, const char *name) { struct device_node *np = cl->dev->of_node; - struct property *prop; - const char *mbox_name; - int index = 0; + int index; if (!np) { dev_err(cl->dev, "%s() currently only supports DT\n", __func__); return ERR_PTR(-EINVAL); } - if (!of_get_property(np, "mbox-names", NULL)) { - dev_err(cl->dev, - "%s() requires an \"mbox-names\" property\n", __func__); + index = of_property_match_string(np, "mbox-names", name); + if (index < 0) { + dev_err(cl->dev, "%s() could not locate channel named \"%s\"\n", + __func__, name); return ERR_PTR(-EINVAL); } - - of_property_for_each_string(np, "mbox-names", prop, mbox_name) { - if (!strncmp(name, mbox_name, strlen(name))) - return mbox_request_channel(cl, index); - index++; - } - - dev_err(cl->dev, "%s() could not locate channel named \"%s\"\n", - __func__, name); - return ERR_PTR(-EINVAL); + return mbox_request_channel(cl, index); } EXPORT_SYMBOL_GPL(mbox_request_channel_byname); diff --git a/drivers/mailbox/omap-mailbox.c b/drivers/mailbox/omap-mailbox.c index 7a87424657a1..6797770474a5 100644 --- a/drivers/mailbox/omap-mailbox.c +++ b/drivers/mailbox/omap-mailbox.c @@ -603,7 +603,7 @@ static struct platform_driver omap_mbox_driver = { .driver = { .name = "omap-mailbox", .pm = &omap_mbox_pm_ops, - .of_match_table = of_match_ptr(omap_mailbox_of_match), + .of_match_table = omap_mailbox_of_match, }, }; module_platform_driver(omap_mbox_driver); diff --git a/drivers/mailbox/rockchip-mailbox.c b/drivers/mailbox/rockchip-mailbox.c index 8ffad059e898..4d966cb2ed03 100644 --- a/drivers/mailbox/rockchip-mailbox.c +++ b/drivers/mailbox/rockchip-mailbox.c @@ -159,7 +159,7 @@ static const struct of_device_id rockchip_mbox_of_match[] = { { .compatible = "rockchip,rk3368-mailbox", .data = &rk3368_drv_data}, { }, }; -MODULE_DEVICE_TABLE(of, rockchp_mbox_of_match); +MODULE_DEVICE_TABLE(of, rockchip_mbox_of_match); static int rockchip_mbox_probe(struct platform_device *pdev) { diff --git a/drivers/mailbox/sprd-mailbox.c b/drivers/mailbox/sprd-mailbox.c index 9ae57de77d4d..ee8539dfcef5 100644 --- a/drivers/mailbox/sprd-mailbox.c +++ b/drivers/mailbox/sprd-mailbox.c @@ -62,7 +62,6 @@ struct sprd_mbox_priv { void __iomem *outbox_base; /* Base register address for supplementary outbox */ void __iomem *supp_base; - struct clk *clk; u32 outbox_fifo_depth; struct mutex lock; @@ -291,19 +290,13 @@ static const struct mbox_chan_ops sprd_mbox_ops = { .shutdown = sprd_mbox_shutdown, }; -static void sprd_mbox_disable(void *data) -{ - struct sprd_mbox_priv *priv = data; - - clk_disable_unprepare(priv->clk); -} - static int sprd_mbox_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct sprd_mbox_priv *priv; int ret, inbox_irq, outbox_irq, supp_irq; unsigned long id, supp; + struct clk *clk; priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); if (!priv) @@ -331,20 +324,10 @@ static int sprd_mbox_probe(struct platform_device *pdev) if (IS_ERR(priv->outbox_base)) return PTR_ERR(priv->outbox_base); - priv->clk = devm_clk_get(dev, "enable"); - if (IS_ERR(priv->clk)) { + clk = devm_clk_get_enabled(dev, "enable"); + if (IS_ERR(clk)) { dev_err(dev, "failed to get mailbox clock\n"); - return PTR_ERR(priv->clk); - } - - ret = clk_prepare_enable(priv->clk); - if (ret) - return ret; - - ret = devm_add_action_or_reset(dev, sprd_mbox_disable, priv); - if (ret) { - dev_err(dev, "failed to add mailbox disable action\n"); - return ret; + return PTR_ERR(clk); } inbox_irq = platform_get_irq_byname(pdev, "inbox"); diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 5228b03b6fe0..1ae2c71bb383 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -28,7 +28,7 @@ #include <linux/rbtree.h> #include <linux/ctype.h> #include <asm/page.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <crypto/hash.h> #include <crypto/md5.h> #include <crypto/skcipher.h> diff --git a/drivers/md/dm-vdo/murmurhash3.c b/drivers/md/dm-vdo/murmurhash3.c index 3a989efae142..13008b089206 100644 --- a/drivers/md/dm-vdo/murmurhash3.c +++ b/drivers/md/dm-vdo/murmurhash3.c @@ -8,7 +8,7 @@ #include "murmurhash3.h" -#include <asm/unaligned.h> +#include <linux/unaligned.h> static inline u64 rotl64(u64 x, s8 r) { diff --git a/drivers/md/dm-vdo/numeric.h b/drivers/md/dm-vdo/numeric.h index dc8c400b21d2..f568dc59e6f1 100644 --- a/drivers/md/dm-vdo/numeric.h +++ b/drivers/md/dm-vdo/numeric.h @@ -6,7 +6,7 @@ #ifndef UDS_NUMERIC_H #define UDS_NUMERIC_H -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/kernel.h> #include <linux/types.h> diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c index 36e4ddfe2d15..7d4d90b4395a 100644 --- a/drivers/md/dm-verity-target.c +++ b/drivers/md/dm-verity-target.c @@ -36,11 +36,13 @@ #define DM_VERITY_OPT_LOGGING "ignore_corruption" #define DM_VERITY_OPT_RESTART "restart_on_corruption" #define DM_VERITY_OPT_PANIC "panic_on_corruption" +#define DM_VERITY_OPT_ERROR_RESTART "restart_on_error" +#define DM_VERITY_OPT_ERROR_PANIC "panic_on_error" #define DM_VERITY_OPT_IGN_ZEROES "ignore_zero_blocks" #define DM_VERITY_OPT_AT_MOST_ONCE "check_at_most_once" #define DM_VERITY_OPT_TASKLET_VERIFY "try_verify_in_tasklet" -#define DM_VERITY_OPTS_MAX (4 + DM_VERITY_OPTS_FEC + \ +#define DM_VERITY_OPTS_MAX (5 + DM_VERITY_OPTS_FEC + \ DM_VERITY_ROOT_HASH_VERIFICATION_OPTS) static unsigned int dm_verity_prefetch_cluster = DM_VERITY_DEFAULT_PREFETCH_SIZE; @@ -273,10 +275,8 @@ out: if (v->mode == DM_VERITY_MODE_LOGGING) return 0; - if (v->mode == DM_VERITY_MODE_RESTART) { - pr_emerg("dm-verity device corrupted\n"); - emergency_restart(); - } + if (v->mode == DM_VERITY_MODE_RESTART) + kernel_restart("dm-verity device corrupted"); if (v->mode == DM_VERITY_MODE_PANIC) panic("dm-verity device corrupted"); @@ -585,6 +585,11 @@ static inline bool verity_is_system_shutting_down(void) || system_state == SYSTEM_RESTART; } +static void restart_io_error(struct work_struct *w) +{ + kernel_restart("dm-verity device has I/O error"); +} + /* * End one "io" structure with a given error. */ @@ -602,18 +607,18 @@ static void verity_finish_io(struct dm_verity_io *io, blk_status_t status) if (unlikely(status != BLK_STS_OK) && unlikely(!(bio->bi_opf & REQ_RAHEAD)) && !verity_is_system_shutting_down()) { - if (v->mode == DM_VERITY_MODE_RESTART || - v->mode == DM_VERITY_MODE_PANIC) - DMERR_LIMIT("%s has error: %s", v->data_dev->name, - blk_status_to_str(status)); - - if (v->mode == DM_VERITY_MODE_RESTART) { - pr_emerg("dm-verity device corrupted\n"); - emergency_restart(); + if (v->error_mode == DM_VERITY_MODE_PANIC) { + panic("dm-verity device has I/O error"); + } + if (v->error_mode == DM_VERITY_MODE_RESTART) { + static DECLARE_WORK(restart_work, restart_io_error); + queue_work(v->verify_wq, &restart_work); + /* + * We deliberately don't call bio_endio here, because + * the machine will be restarted anyway. + */ + return; } - - if (v->mode == DM_VERITY_MODE_PANIC) - panic("dm-verity device corrupted"); } bio_endio(bio); @@ -824,6 +829,8 @@ static void verity_status(struct dm_target *ti, status_type_t type, DMEMIT("%02x", v->salt[x]); if (v->mode != DM_VERITY_MODE_EIO) args++; + if (v->error_mode != DM_VERITY_MODE_EIO) + args++; if (verity_fec_is_enabled(v)) args += DM_VERITY_OPTS_FEC; if (v->zero_digest) @@ -853,6 +860,19 @@ static void verity_status(struct dm_target *ti, status_type_t type, BUG(); } } + if (v->error_mode != DM_VERITY_MODE_EIO) { + DMEMIT(" "); + switch (v->error_mode) { + case DM_VERITY_MODE_RESTART: + DMEMIT(DM_VERITY_OPT_ERROR_RESTART); + break; + case DM_VERITY_MODE_PANIC: + DMEMIT(DM_VERITY_OPT_ERROR_PANIC); + break; + default: + BUG(); + } + } if (v->zero_digest) DMEMIT(" " DM_VERITY_OPT_IGN_ZEROES); if (v->validated_blocks) @@ -905,6 +925,19 @@ static void verity_status(struct dm_target *ti, status_type_t type, DMEMIT("invalid"); } } + if (v->error_mode != DM_VERITY_MODE_EIO) { + DMEMIT(",verity_error_mode="); + switch (v->error_mode) { + case DM_VERITY_MODE_RESTART: + DMEMIT(DM_VERITY_OPT_ERROR_RESTART); + break; + case DM_VERITY_MODE_PANIC: + DMEMIT(DM_VERITY_OPT_ERROR_PANIC); + break; + default: + DMEMIT("invalid"); + } + } DMEMIT(";"); break; } @@ -1107,6 +1140,25 @@ static int verity_parse_verity_mode(struct dm_verity *v, const char *arg_name) return 0; } +static inline bool verity_is_verity_error_mode(const char *arg_name) +{ + return (!strcasecmp(arg_name, DM_VERITY_OPT_ERROR_RESTART) || + !strcasecmp(arg_name, DM_VERITY_OPT_ERROR_PANIC)); +} + +static int verity_parse_verity_error_mode(struct dm_verity *v, const char *arg_name) +{ + if (v->error_mode) + return -EINVAL; + + if (!strcasecmp(arg_name, DM_VERITY_OPT_ERROR_RESTART)) + v->error_mode = DM_VERITY_MODE_RESTART; + else if (!strcasecmp(arg_name, DM_VERITY_OPT_ERROR_PANIC)) + v->error_mode = DM_VERITY_MODE_PANIC; + + return 0; +} + static int verity_parse_opt_args(struct dm_arg_set *as, struct dm_verity *v, struct dm_verity_sig_opts *verify_args, bool only_modifier_opts) @@ -1141,6 +1193,16 @@ static int verity_parse_opt_args(struct dm_arg_set *as, struct dm_verity *v, } continue; + } else if (verity_is_verity_error_mode(arg_name)) { + if (only_modifier_opts) + continue; + r = verity_parse_verity_error_mode(v, arg_name); + if (r) { + ti->error = "Conflicting error handling parameters"; + return r; + } + continue; + } else if (!strcasecmp(arg_name, DM_VERITY_OPT_IGN_ZEROES)) { if (only_modifier_opts) continue; diff --git a/drivers/md/dm-verity.h b/drivers/md/dm-verity.h index 754e70bb5fe0..6b75159bf835 100644 --- a/drivers/md/dm-verity.h +++ b/drivers/md/dm-verity.h @@ -64,6 +64,7 @@ struct dm_verity { unsigned int digest_size; /* digest size for the current hash algorithm */ unsigned int hash_reqsize; /* the size of temporary space for crypto */ enum verity_mode mode; /* mode for handling verification errors */ + enum verity_mode error_mode;/* mode for handling I/O errors */ unsigned int corrupted_errs;/* Number of errors for corrupted blocks */ struct workqueue_struct *verify_wq; diff --git a/drivers/media/dvb-frontends/mxl5xx.c b/drivers/media/dvb-frontends/mxl5xx.c index 91e9c378397c..930da176e5bf 100644 --- a/drivers/media/dvb-frontends/mxl5xx.c +++ b/drivers/media/dvb-frontends/mxl5xx.c @@ -21,7 +21,7 @@ #include <linux/mutex.h> #include <linux/vmalloc.h> #include <asm/div64.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <media/dvb_frontend.h> #include "mxl5xx.h" diff --git a/drivers/media/i2c/ccs/ccs-reg-access.c b/drivers/media/i2c/ccs/ccs-reg-access.c index ed79075505e6..a696a0ec8ff5 100644 --- a/drivers/media/i2c/ccs/ccs-reg-access.c +++ b/drivers/media/i2c/ccs/ccs-reg-access.c @@ -9,7 +9,7 @@ * Contact: Sakari Ailus <sakari.ailus@linux.intel.com> */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/delay.h> #include <linux/i2c.h> diff --git a/drivers/media/i2c/hi556.c b/drivers/media/i2c/hi556.c index b440f386f062..f31f9886c924 100644 --- a/drivers/media/i2c/hi556.c +++ b/drivers/media/i2c/hi556.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 // Copyright (c) 2019 Intel Corporation. -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/acpi.h> #include <linux/clk.h> #include <linux/delay.h> diff --git a/drivers/media/i2c/hi846.c b/drivers/media/i2c/hi846.c index 52d9ca68a86c..172772decd3d 100644 --- a/drivers/media/i2c/hi846.c +++ b/drivers/media/i2c/hi846.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 // Copyright (c) 2021 Purism SPC -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/clk.h> #include <linux/delay.h> #include <linux/gpio/consumer.h> diff --git a/drivers/media/i2c/hi847.c b/drivers/media/i2c/hi847.c index 72c60747a839..546833f5b5f5 100644 --- a/drivers/media/i2c/hi847.c +++ b/drivers/media/i2c/hi847.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 // Copyright (c) 2022 Intel Corporation. -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/acpi.h> #include <linux/delay.h> #include <linux/i2c.h> diff --git a/drivers/media/i2c/imx208.c b/drivers/media/i2c/imx208.c index 639e05340dbb..2184c90f7864 100644 --- a/drivers/media/i2c/imx208.c +++ b/drivers/media/i2c/imx208.c @@ -8,7 +8,7 @@ #include <linux/pm_runtime.h> #include <media/v4l2-ctrls.h> #include <media/v4l2-device.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define IMX208_REG_MODE_SELECT 0x0100 #define IMX208_MODE_STANDBY 0x00 diff --git a/drivers/media/i2c/imx258.c b/drivers/media/i2c/imx258.c index 1a99eaaff21a..9e30fce1f223 100644 --- a/drivers/media/i2c/imx258.c +++ b/drivers/media/i2c/imx258.c @@ -12,7 +12,7 @@ #include <media/v4l2-ctrls.h> #include <media/v4l2-device.h> #include <media/v4l2-fwnode.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define IMX258_REG_MODE_SELECT CCI_REG8(0x0100) #define IMX258_MODE_STANDBY 0x00 diff --git a/drivers/media/i2c/imx290.c b/drivers/media/i2c/imx290.c index 4150e6e4b9a6..458905dfb3e1 100644 --- a/drivers/media/i2c/imx290.c +++ b/drivers/media/i2c/imx290.c @@ -18,7 +18,7 @@ #include <linux/regmap.h> #include <linux/regulator/consumer.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <media/media-entity.h> #include <media/v4l2-cci.h> diff --git a/drivers/media/i2c/imx319.c b/drivers/media/i2c/imx319.c index 8fe3933f3146..dd1b4ff983dc 100644 --- a/drivers/media/i2c/imx319.c +++ b/drivers/media/i2c/imx319.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 // Copyright (C) 2018 Intel Corporation -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/acpi.h> #include <linux/i2c.h> #include <linux/module.h> diff --git a/drivers/media/i2c/imx334.c b/drivers/media/i2c/imx334.c index 40863d87d341..a544fc3df39c 100644 --- a/drivers/media/i2c/imx334.c +++ b/drivers/media/i2c/imx334.c @@ -4,7 +4,7 @@ * * Copyright (C) 2021 Intel Corporation */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/clk.h> #include <linux/delay.h> diff --git a/drivers/media/i2c/imx335.c b/drivers/media/i2c/imx335.c index 54a1de53d497..fcfd1d851bd4 100644 --- a/drivers/media/i2c/imx335.c +++ b/drivers/media/i2c/imx335.c @@ -4,7 +4,7 @@ * * Copyright (C) 2021 Intel Corporation */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/clk.h> #include <linux/delay.h> diff --git a/drivers/media/i2c/imx355.c b/drivers/media/i2c/imx355.c index 0dd25eeea60b..b2dce67c0b6b 100644 --- a/drivers/media/i2c/imx355.c +++ b/drivers/media/i2c/imx355.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 // Copyright (C) 2018 Intel Corporation -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/acpi.h> #include <linux/i2c.h> #include <linux/module.h> diff --git a/drivers/media/i2c/imx412.c b/drivers/media/i2c/imx412.c index 7d1f7af0a9df..0bfe3046fcc8 100644 --- a/drivers/media/i2c/imx412.c +++ b/drivers/media/i2c/imx412.c @@ -4,7 +4,7 @@ * * Copyright (C) 2021 Intel Corporation */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/clk.h> #include <linux/delay.h> diff --git a/drivers/media/i2c/ir-kbd-i2c.c b/drivers/media/i2c/ir-kbd-i2c.c index b37a2aaf8ac0..c84e1e0e6109 100644 --- a/drivers/media/i2c/ir-kbd-i2c.c +++ b/drivers/media/i2c/ir-kbd-i2c.c @@ -35,7 +35,7 @@ * Copyright (C) 2011 Andy Walls <awalls@md.metrocast.net> */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/module.h> #include <linux/init.h> #include <linux/kernel.h> diff --git a/drivers/media/i2c/og01a1b.c b/drivers/media/i2c/og01a1b.c index e906435fc49a..78d5d406e4b7 100644 --- a/drivers/media/i2c/og01a1b.c +++ b/drivers/media/i2c/og01a1b.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 // Copyright (c) 2022 Intel Corporation. -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/acpi.h> #include <linux/clk.h> #include <linux/delay.h> diff --git a/drivers/media/i2c/ov01a10.c b/drivers/media/i2c/ov01a10.c index 5606437f37d0..0b9fb1ddbe59 100644 --- a/drivers/media/i2c/ov01a10.c +++ b/drivers/media/i2c/ov01a10.c @@ -3,7 +3,7 @@ * Copyright (c) 2023 Intel Corporation. */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/acpi.h> #include <linux/bitfield.h> diff --git a/drivers/media/i2c/ov08x40.c b/drivers/media/i2c/ov08x40.c index 48df077522ad..7ead3c720e0e 100644 --- a/drivers/media/i2c/ov08x40.c +++ b/drivers/media/i2c/ov08x40.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 // Copyright (c) 2022 Intel Corporation. -#include <asm-generic/unaligned.h> +#include <linux/unaligned.h> #include <linux/acpi.h> #include <linux/i2c.h> #include <linux/module.h> diff --git a/drivers/media/i2c/ov2740.c b/drivers/media/i2c/ov2740.c index c48dbcde9877..bd0b2f0f0d45 100644 --- a/drivers/media/i2c/ov2740.c +++ b/drivers/media/i2c/ov2740.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 // Copyright (c) 2020 Intel Corporation. -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/acpi.h> #include <linux/clk.h> #include <linux/delay.h> diff --git a/drivers/media/i2c/ov5670.c b/drivers/media/i2c/ov5670.c index 2aee85965cf7..f051045d340f 100644 --- a/drivers/media/i2c/ov5670.c +++ b/drivers/media/i2c/ov5670.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 // Copyright (c) 2017 Intel Corporation. -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/acpi.h> #include <linux/clk.h> #include <linux/delay.h> diff --git a/drivers/media/i2c/ov5675.c b/drivers/media/i2c/ov5675.c index 5b5127f8953f..2833b14ee139 100644 --- a/drivers/media/i2c/ov5675.c +++ b/drivers/media/i2c/ov5675.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 // Copyright (c) 2019 Intel Corporation. -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/acpi.h> #include <linux/clk.h> #include <linux/delay.h> diff --git a/drivers/media/i2c/ov8856.c b/drivers/media/i2c/ov8856.c index 6ffe10e57b5b..3b94338f55ed 100644 --- a/drivers/media/i2c/ov8856.c +++ b/drivers/media/i2c/ov8856.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 // Copyright (c) 2019 Intel Corporation. -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/acpi.h> #include <linux/clk.h> #include <linux/delay.h> diff --git a/drivers/media/i2c/ov8858.c b/drivers/media/i2c/ov8858.c index 174c65f76886..326f50a5ab51 100644 --- a/drivers/media/i2c/ov8858.c +++ b/drivers/media/i2c/ov8858.c @@ -5,7 +5,7 @@ * Copyright (C) 2017 Fuzhou Rockchip Electronics Co., Ltd. */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/clk.h> #include <linux/delay.h> diff --git a/drivers/media/i2c/ov9282.c b/drivers/media/i2c/ov9282.c index 251a4b534914..9f52af6f047f 100644 --- a/drivers/media/i2c/ov9282.c +++ b/drivers/media/i2c/ov9282.c @@ -4,7 +4,7 @@ * * Copyright (C) 2021 Intel Corporation */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/clk.h> #include <linux/delay.h> diff --git a/drivers/media/i2c/ov9734.c b/drivers/media/i2c/ov9734.c index d99728597431..bf9e2adbff34 100644 --- a/drivers/media/i2c/ov9734.c +++ b/drivers/media/i2c/ov9734.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 // Copyright (c) 2020 Intel Corporation. -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/acpi.h> #include <linux/delay.h> #include <linux/i2c.h> diff --git a/drivers/media/i2c/thp7312.c b/drivers/media/i2c/thp7312.c index 75225ff5eff6..c77440ff098c 100644 --- a/drivers/media/i2c/thp7312.c +++ b/drivers/media/i2c/thp7312.c @@ -4,7 +4,7 @@ * Copyright (C) 2023 Ideas on Board Oy */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/clk.h> #include <linux/delay.h> diff --git a/drivers/media/i2c/vgxy61.c b/drivers/media/i2c/vgxy61.c index 30378e962016..409d2d4ffb4b 100644 --- a/drivers/media/i2c/vgxy61.c +++ b/drivers/media/i2c/vgxy61.c @@ -16,7 +16,7 @@ #include <linux/regulator/consumer.h> #include <linux/units.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <media/mipi-csi2.h> #include <media/v4l2-async.h> diff --git a/drivers/media/pci/bt8xx/bttv-cards.c b/drivers/media/pci/bt8xx/bttv-cards.c index 867c1308de23..365b04e5ae4d 100644 --- a/drivers/media/pci/bt8xx/bttv-cards.c +++ b/drivers/media/pci/bt8xx/bttv-cards.c @@ -24,7 +24,7 @@ #include <linux/firmware.h> #include <net/checksum.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <asm/io.h> #include "bttvp.h" diff --git a/drivers/media/platform/chips-media/coda/coda-jpeg.c b/drivers/media/platform/chips-media/coda/coda-jpeg.c index ba8f41002917..5746892658b1 100644 --- a/drivers/media/platform/chips-media/coda/coda-jpeg.c +++ b/drivers/media/platform/chips-media/coda/coda-jpeg.c @@ -5,7 +5,7 @@ * Copyright (C) 2014 Philipp Zabel, Pengutronix */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/irqreturn.h> #include <linux/kernel.h> #include <linux/ktime.h> diff --git a/drivers/media/platform/renesas/rcar_jpu.c b/drivers/media/platform/renesas/rcar_jpu.c index fff349e45067..e50fe7525a73 100644 --- a/drivers/media/platform/renesas/rcar_jpu.c +++ b/drivers/media/platform/renesas/rcar_jpu.c @@ -14,7 +14,7 @@ * 3) V4L2_CID_JPEG_ACTIVE_MARKER */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/clk.h> #include <linux/err.h> #include <linux/interrupt.h> diff --git a/drivers/media/platform/verisilicon/hantro_g1_mpeg2_dec.c b/drivers/media/platform/verisilicon/hantro_g1_mpeg2_dec.c index 9aea331e1a3c..e0d6bd0a6e44 100644 --- a/drivers/media/platform/verisilicon/hantro_g1_mpeg2_dec.c +++ b/drivers/media/platform/verisilicon/hantro_g1_mpeg2_dec.c @@ -5,7 +5,7 @@ * Copyright (C) 2018 Rockchip Electronics Co., Ltd. */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/bitfield.h> #include <media/v4l2-mem2mem.h> #include "hantro.h" diff --git a/drivers/media/platform/verisilicon/hantro_h1_jpeg_enc.c b/drivers/media/platform/verisilicon/hantro_h1_jpeg_enc.c index 12d69503d6ba..86cc1a07026f 100644 --- a/drivers/media/platform/verisilicon/hantro_h1_jpeg_enc.c +++ b/drivers/media/platform/verisilicon/hantro_h1_jpeg_enc.c @@ -5,7 +5,7 @@ * Copyright (C) 2018 Rockchip Electronics Co., Ltd. */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <media/v4l2-mem2mem.h> #include "hantro_jpeg.h" #include "hantro.h" diff --git a/drivers/media/platform/verisilicon/rockchip_vpu2_hw_jpeg_enc.c b/drivers/media/platform/verisilicon/rockchip_vpu2_hw_jpeg_enc.c index 8395c4d48dd0..61621b1be8a2 100644 --- a/drivers/media/platform/verisilicon/rockchip_vpu2_hw_jpeg_enc.c +++ b/drivers/media/platform/verisilicon/rockchip_vpu2_hw_jpeg_enc.c @@ -22,7 +22,7 @@ * zigzag, nor linear. */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <media/v4l2-mem2mem.h> #include "hantro_jpeg.h" #include "hantro.h" diff --git a/drivers/media/platform/verisilicon/rockchip_vpu2_hw_mpeg2_dec.c b/drivers/media/platform/verisilicon/rockchip_vpu2_hw_mpeg2_dec.c index b66737fab46b..50a3a3eeaa00 100644 --- a/drivers/media/platform/verisilicon/rockchip_vpu2_hw_mpeg2_dec.c +++ b/drivers/media/platform/verisilicon/rockchip_vpu2_hw_mpeg2_dec.c @@ -5,7 +5,7 @@ * Copyright (C) 2018 Rockchip Electronics Co., Ltd. */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/bitfield.h> #include <media/v4l2-mem2mem.h> #include "hantro.h" diff --git a/drivers/media/radio/radio-raremono.c b/drivers/media/radio/radio-raremono.c index c3180d53c282..64c7452c05b5 100644 --- a/drivers/media/radio/radio-raremono.c +++ b/drivers/media/radio/radio-raremono.c @@ -12,7 +12,7 @@ #include <linux/hid.h> #include <linux/mutex.h> #include <linux/videodev2.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <media/v4l2-device.h> #include <media/v4l2-ioctl.h> #include <media/v4l2-ctrls.h> diff --git a/drivers/media/radio/si470x/radio-si470x.h b/drivers/media/radio/si470x/radio-si470x.h index e57ab54a27fc..2915c0023fcd 100644 --- a/drivers/media/radio/si470x/radio-si470x.h +++ b/drivers/media/radio/si470x/radio-si470x.h @@ -26,7 +26,7 @@ #include <media/v4l2-ctrls.h> #include <media/v4l2-event.h> #include <media/v4l2-device.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> diff --git a/drivers/media/rc/ir_toy.c b/drivers/media/rc/ir_toy.c index 69e630d85262..533faa117517 100644 --- a/drivers/media/rc/ir_toy.c +++ b/drivers/media/rc/ir_toy.c @@ -12,7 +12,7 @@ * Copyright (C) 2011 Peter Kooiman <pkooiman@gmail.com> */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/completion.h> #include <linux/kernel.h> #include <linux/module.h> diff --git a/drivers/media/rc/redrat3.c b/drivers/media/rc/redrat3.c index 9f2947af33aa..d89a4cfe3c89 100644 --- a/drivers/media/rc/redrat3.c +++ b/drivers/media/rc/redrat3.c @@ -31,7 +31,7 @@ * -- */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/device.h> #include <linux/leds.h> #include <linux/module.h> diff --git a/drivers/media/tuners/xc2028.c b/drivers/media/tuners/xc2028.c index 352b8a3679b7..8e6638e5f688 100644 --- a/drivers/media/tuners/xc2028.c +++ b/drivers/media/tuners/xc2028.c @@ -14,7 +14,7 @@ #include <media/tuner.h> #include <linux/mutex.h> #include <linux/slab.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "tuner-i2c.h" #include "xc2028.h" #include "xc2028-types.h" diff --git a/drivers/media/tuners/xc4000.c b/drivers/media/tuners/xc4000.c index 29bc63021c5a..3cf54d776d36 100644 --- a/drivers/media/tuners/xc4000.c +++ b/drivers/media/tuners/xc4000.c @@ -16,7 +16,7 @@ #include <linux/dvb/frontend.h> #include <linux/i2c.h> #include <linux/mutex.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <media/dvb_frontend.h> diff --git a/drivers/media/usb/dvb-usb/m920x.c b/drivers/media/usb/dvb-usb/m920x.c index c88a202daf5f..a2054b1b100f 100644 --- a/drivers/media/usb/dvb-usb/m920x.c +++ b/drivers/media/usb/dvb-usb/m920x.c @@ -17,7 +17,7 @@ #include <media/tuner.h> #include "tuner-simple.h" -#include <asm/unaligned.h> +#include <linux/unaligned.h> /* debug */ static int dvb_usb_m920x_debug; diff --git a/drivers/media/usb/uvc/uvc_driver.c b/drivers/media/usb/uvc/uvc_driver.c index f0febdc08c2d..0fac689c6350 100644 --- a/drivers/media/usb/uvc/uvc_driver.c +++ b/drivers/media/usb/uvc/uvc_driver.c @@ -19,7 +19,7 @@ #include <linux/videodev2.h> #include <linux/vmalloc.h> #include <linux/wait.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <media/v4l2-common.h> #include <media/v4l2-ioctl.h> diff --git a/drivers/media/usb/uvc/uvc_video.c b/drivers/media/usb/uvc/uvc_video.c index cd9c29532fb0..e00f38dd07d9 100644 --- a/drivers/media/usb/uvc/uvc_video.c +++ b/drivers/media/usb/uvc/uvc_video.c @@ -18,7 +18,7 @@ #include <linux/vmalloc.h> #include <linux/wait.h> #include <linux/atomic.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <media/v4l2-common.h> diff --git a/drivers/media/v4l2-core/v4l2-cci.c b/drivers/media/v4l2-core/v4l2-cci.c index 1ff94affbaf3..e9ecf4785946 100644 --- a/drivers/media/v4l2-core/v4l2-cci.c +++ b/drivers/media/v4l2-core/v4l2-cci.c @@ -12,7 +12,7 @@ #include <linux/regmap.h> #include <linux/types.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <media/v4l2-cci.h> diff --git a/drivers/media/v4l2-core/v4l2-jpeg.c b/drivers/media/v4l2-core/v4l2-jpeg.c index b8bece739d07..6e2647323522 100644 --- a/drivers/media/v4l2-core/v4l2-jpeg.c +++ b/drivers/media/v4l2-core/v4l2-jpeg.c @@ -9,7 +9,7 @@ * [1] https://www.w3.org/Graphics/JPEG/itu-t81.pdf */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/errno.h> #include <linux/kernel.h> #include <linux/module.h> diff --git a/drivers/memstick/host/rtsx_usb_ms.c b/drivers/memstick/host/rtsx_usb_ms.c index 246876ac713c..ffdd8de9ec5d 100644 --- a/drivers/memstick/host/rtsx_usb_ms.c +++ b/drivers/memstick/host/rtsx_usb_ms.c @@ -19,7 +19,7 @@ #include <linux/mutex.h> #include <linux/sched.h> #include <linux/completion.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> struct rtsx_usb_ms { struct platform_device *pdev; diff --git a/drivers/message/fusion/mptctl.c b/drivers/message/fusion/mptctl.c index 4766d8518dc9..77fa55df70d0 100644 --- a/drivers/message/fusion/mptctl.c +++ b/drivers/message/fusion/mptctl.c @@ -1609,7 +1609,7 @@ mptctl_eventreport (MPT_ADAPTER *ioc, unsigned long arg) maxEvents = numBytes/sizeof(MPT_IOCTL_EVENTS); - max = MPTCTL_EVENT_LOG_SIZE < maxEvents ? MPTCTL_EVENT_LOG_SIZE : maxEvents; + max = min(maxEvents, MPTCTL_EVENT_LOG_SIZE); /* If fewer than 1 event is requested, there must have * been some type of error. diff --git a/drivers/mfd/gateworks-gsc.c b/drivers/mfd/gateworks-gsc.c index 6ca867b8f5f1..a3301502ce6a 100644 --- a/drivers/mfd/gateworks-gsc.c +++ b/drivers/mfd/gateworks-gsc.c @@ -20,7 +20,7 @@ #include <linux/platform_device.h> #include <linux/regmap.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /* * The GSC suffers from an errata where occasionally during diff --git a/drivers/mfd/iqs62x.c b/drivers/mfd/iqs62x.c index 1b465590567c..ee017617d1d1 100644 --- a/drivers/mfd/iqs62x.c +++ b/drivers/mfd/iqs62x.c @@ -31,7 +31,7 @@ #include <linux/property.h> #include <linux/regmap.h> #include <linux/slab.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define IQS62X_PROD_NUM 0x00 diff --git a/drivers/mfd/ntxec.c b/drivers/mfd/ntxec.c index 4416cd37e539..08c68de0f01b 100644 --- a/drivers/mfd/ntxec.c +++ b/drivers/mfd/ntxec.c @@ -21,7 +21,7 @@ #include <linux/reboot.h> #include <linux/regmap.h> #include <linux/types.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define NTXEC_REG_VERSION 0x00 #define NTXEC_REG_POWEROFF 0x50 diff --git a/drivers/mfd/rave-sp.c b/drivers/mfd/rave-sp.c index ef326d6d566e..c1b78d127a26 100644 --- a/drivers/mfd/rave-sp.c +++ b/drivers/mfd/rave-sp.c @@ -21,7 +21,7 @@ #include <linux/of_platform.h> #include <linux/sched.h> #include <linux/serdev.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /* * UART protocol using following entities: diff --git a/drivers/mfd/si476x-cmd.c b/drivers/mfd/si476x-cmd.c index c9a0ec084aa8..3bb2decfebd3 100644 --- a/drivers/mfd/si476x-cmd.c +++ b/drivers/mfd/si476x-cmd.c @@ -20,7 +20,7 @@ #include <linux/mfd/si476x-core.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define msb(x) ((u8)((u16) x >> 8)) #define lsb(x) ((u8)((u16) x & 0x00FF)) diff --git a/drivers/misc/altera-stapl/altera.c b/drivers/misc/altera-stapl/altera.c index 587427b73914..bbe3967c3a4c 100644 --- a/drivers/misc/altera-stapl/altera.c +++ b/drivers/misc/altera-stapl/altera.c @@ -9,7 +9,7 @@ * Copyright (C) 2010,2011 Igor M. Liplianin <liplianin@netup.ru> */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/ctype.h> #include <linux/string.h> #include <linux/firmware.h> diff --git a/drivers/misc/bcm-vk/bcm_vk_sg.c b/drivers/misc/bcm-vk/bcm_vk_sg.c index 2e9daaf3e492..d309216ee181 100644 --- a/drivers/misc/bcm-vk/bcm_vk_sg.c +++ b/drivers/misc/bcm-vk/bcm_vk_sg.c @@ -9,7 +9,7 @@ #include <linux/vmalloc.h> #include <asm/page.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <uapi/linux/misc/bcm_vk.h> diff --git a/drivers/misc/cardreader/rtsx_pcr.c b/drivers/misc/cardreader/rtsx_pcr.c index 117b3c24f910..be3d4e0e50cc 100644 --- a/drivers/misc/cardreader/rtsx_pcr.c +++ b/drivers/misc/cardreader/rtsx_pcr.c @@ -19,7 +19,7 @@ #include <linux/mfd/core.h> #include <linux/rtsx_pci.h> #include <linux/mmc/card.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/pm.h> #include <linux/pm_runtime.h> diff --git a/drivers/misc/lattice-ecp3-config.c b/drivers/misc/lattice-ecp3-config.c index bac4df2e5231..93949df3bcff 100644 --- a/drivers/misc/lattice-ecp3-config.c +++ b/drivers/misc/lattice-ecp3-config.c @@ -11,7 +11,7 @@ #include <linux/spi/spi.h> #include <linux/platform_device.h> #include <linux/delay.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define FIRMWARE_NAME "lattice-ecp3.bit" diff --git a/drivers/misc/mei/platform-vsc.c b/drivers/misc/mei/platform-vsc.c index d02f6e881139..20a11b299bcd 100644 --- a/drivers/misc/mei/platform-vsc.c +++ b/drivers/misc/mei/platform-vsc.c @@ -19,7 +19,7 @@ #include <linux/types.h> #include <asm-generic/bug.h> -#include <asm-generic/unaligned.h> +#include <linux/unaligned.h> #include "mei_dev.h" #include "vsc-tp.h" diff --git a/drivers/misc/mei/vsc-fw-loader.c b/drivers/misc/mei/vsc-fw-loader.c index 084d0205f97d..9f129bc641f6 100644 --- a/drivers/misc/mei/vsc-fw-loader.c +++ b/drivers/misc/mei/vsc-fw-loader.c @@ -15,7 +15,7 @@ #include <linux/string_helpers.h> #include <linux/types.h> -#include <asm-generic/unaligned.h> +#include <linux/unaligned.h> #include "vsc-tp.h" diff --git a/drivers/mmc/host/atmel-mci.c b/drivers/mmc/host/atmel-mci.c index 6490df54a6f5..cdbd2edf4b2e 100644 --- a/drivers/mmc/host/atmel-mci.c +++ b/drivers/mmc/host/atmel-mci.c @@ -37,7 +37,7 @@ #include <asm/cacheflush.h> #include <asm/io.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define ATMCI_MAX_NR_SLOTS 2 diff --git a/drivers/mmc/host/mmc_spi.c b/drivers/mmc/host/mmc_spi.c index c9caa1ece7ef..8fee7052f2ef 100644 --- a/drivers/mmc/host/mmc_spi.c +++ b/drivers/mmc/host/mmc_spi.c @@ -26,7 +26,7 @@ #include <linux/spi/spi.h> #include <linux/spi/mmc_spi.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /* NOTES: diff --git a/drivers/mmc/host/mvsdio.c b/drivers/mmc/host/mvsdio.c index af7f21888e27..d859b1a3ab71 100644 --- a/drivers/mmc/host/mvsdio.c +++ b/drivers/mmc/host/mvsdio.c @@ -22,7 +22,7 @@ #include <linux/mmc/slot-gpio.h> #include <linux/sizes.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "mvsdio.h" diff --git a/drivers/mmc/host/rtsx_pci_sdmmc.c b/drivers/mmc/host/rtsx_pci_sdmmc.c index 7dfe7c4e0077..20e79109be16 100644 --- a/drivers/mmc/host/rtsx_pci_sdmmc.c +++ b/drivers/mmc/host/rtsx_pci_sdmmc.c @@ -20,7 +20,7 @@ #include <linux/mmc/sdio.h> #include <linux/mmc/card.h> #include <linux/rtsx_pci.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/pm_runtime.h> struct realtek_pci_sdmmc { diff --git a/drivers/mmc/host/rtsx_usb_sdmmc.c b/drivers/mmc/host/rtsx_usb_sdmmc.c index ded9b6849e35..4e86f0a705b6 100644 --- a/drivers/mmc/host/rtsx_usb_sdmmc.c +++ b/drivers/mmc/host/rtsx_usb_sdmmc.c @@ -21,7 +21,7 @@ #include <linux/pm_runtime.h> #include <linux/rtsx_usb.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #if defined(CONFIG_LEDS_CLASS) || (defined(CONFIG_LEDS_CLASS_MODULE) && \ defined(CONFIG_MMC_REALTEK_USB_MODULE)) diff --git a/drivers/mtd/nand/raw/intel-nand-controller.c b/drivers/mtd/nand/raw/intel-nand-controller.c index 78174c463b36..f0f0522b2fa2 100644 --- a/drivers/mtd/nand/raw/intel-nand-controller.c +++ b/drivers/mtd/nand/raw/intel-nand-controller.c @@ -22,7 +22,7 @@ #include <linux/slab.h> #include <linux/types.h> #include <linux/units.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define EBU_CLC 0x000 #define EBU_CLC_RST 0x00000000u diff --git a/drivers/mtd/nand/raw/marvell_nand.c b/drivers/mtd/nand/raw/marvell_nand.c index 26648b72e691..aa113a5d88c8 100644 --- a/drivers/mtd/nand/raw/marvell_nand.c +++ b/drivers/mtd/nand/raw/marvell_nand.c @@ -84,7 +84,7 @@ #include <linux/slab.h> #include <linux/mfd/syscon.h> #include <linux/regmap.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/dmaengine.h> #include <linux/dma-mapping.h> diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c index 3e7526274e34..3bc56517fe7a 100644 --- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c +++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c @@ -12,7 +12,7 @@ // Copyright (c) 2019 Martin Sperl <kernel@martin.sperl.org> // -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/bitfield.h> #include <linux/clk.h> #include <linux/device.h> diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-regmap.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-regmap.c index 65150e762007..8c5be8d1c519 100644 --- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-regmap.c +++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-regmap.c @@ -8,7 +8,7 @@ #include "mcp251xfd.h" -#include <asm/unaligned.h> +#include <linux/unaligned.h> static const struct regmap_config mcp251xfd_regmap_crc; diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-ring.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-ring.c index 83c18035b2a2..e684991fa391 100644 --- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-ring.c +++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-ring.c @@ -12,7 +12,7 @@ // Copyright (c) 2019 Martin Sperl <kernel@martin.sperl.org> // -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "mcp251xfd.h" #include "mcp251xfd-ram.h" diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-tx.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-tx.c index b1de8052a45c..747ae3e8a768 100644 --- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-tx.c +++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-tx.c @@ -12,7 +12,7 @@ // Copyright (c) 2019 Martin Sperl <kernel@martin.sperl.org> // -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/bitfield.h> #include "mcp251xfd.h" diff --git a/drivers/net/can/usb/etas_es58x/es581_4.c b/drivers/net/can/usb/etas_es58x/es581_4.c index 4151b18fd045..1888ca1de7b6 100644 --- a/drivers/net/can/usb/etas_es58x/es581_4.c +++ b/drivers/net/can/usb/etas_es58x/es581_4.c @@ -9,7 +9,7 @@ * Copyright (c) 2020-2022 Vincent Mailhol <mailhol.vincent@wanadoo.fr> */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/kernel.h> #include <linux/units.h> diff --git a/drivers/net/can/usb/etas_es58x/es58x_core.c b/drivers/net/can/usb/etas_es58x/es58x_core.c index 5e3a72b7c469..71f24dc0a927 100644 --- a/drivers/net/can/usb/etas_es58x/es58x_core.c +++ b/drivers/net/can/usb/etas_es58x/es58x_core.c @@ -10,7 +10,7 @@ * Copyright (c) 2020-2022 Vincent Mailhol <mailhol.vincent@wanadoo.fr> */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/crc16.h> #include <linux/ethtool.h> #include <linux/kernel.h> diff --git a/drivers/net/can/usb/etas_es58x/es58x_fd.c b/drivers/net/can/usb/etas_es58x/es58x_fd.c index fa87b0b78e3e..84ffa1839bac 100644 --- a/drivers/net/can/usb/etas_es58x/es58x_fd.c +++ b/drivers/net/can/usb/etas_es58x/es58x_fd.c @@ -11,7 +11,7 @@ * Copyright (c) 2020-2022 Vincent Mailhol <mailhol.vincent@wanadoo.fr> */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/kernel.h> #include <linux/units.h> diff --git a/drivers/net/can/usb/f81604.c b/drivers/net/can/usb/f81604.c index ec8cef7fd2d5..bc0c8903fe77 100644 --- a/drivers/net/can/usb/f81604.c +++ b/drivers/net/can/usb/f81604.c @@ -13,7 +13,7 @@ #include <linux/can/error.h> #include <linux/can/platform/sja1000.h> -#include <asm-generic/unaligned.h> +#include <linux/unaligned.h> /* vendor and product id */ #define F81604_VENDOR_ID 0x2c42 diff --git a/drivers/net/can/usb/mcba_usb.c b/drivers/net/can/usb/mcba_usb.c index 47619e9cb005..41c0a1c399bf 100644 --- a/drivers/net/can/usb/mcba_usb.c +++ b/drivers/net/can/usb/mcba_usb.c @@ -6,7 +6,7 @@ * This driver is inspired by the 4.6.2 version of net/can/usb/usb_8dev.c */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/can.h> #include <linux/can/dev.h> #include <linux/can/error.h> diff --git a/drivers/net/can/usb/peak_usb/pcan_usb.c b/drivers/net/can/usb/peak_usb/pcan_usb.c index b211b6e283a2..c75df1755b3b 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb.c @@ -8,7 +8,7 @@ * * Many thanks to Klaus Hitschler <klaus.hitschler@gmx.de> */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/ethtool.h> #include <linux/module.h> diff --git a/drivers/net/dsa/b53/b53_spi.c b/drivers/net/dsa/b53/b53_spi.c index 308f15d3832e..467da057579e 100644 --- a/drivers/net/dsa/b53/b53_spi.c +++ b/drivers/net/dsa/b53/b53_spi.c @@ -16,7 +16,7 @@ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/delay.h> #include <linux/kernel.h> diff --git a/drivers/net/dsa/microchip/ksz_spi.c b/drivers/net/dsa/microchip/ksz_spi.c index e3e341431f09..1c6652f2b9fe 100644 --- a/drivers/net/dsa/microchip/ksz_spi.c +++ b/drivers/net/dsa/microchip/ksz_spi.c @@ -6,7 +6,7 @@ * Tristram Ha <Tristram.Ha@microchip.com> */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/delay.h> #include <linux/kernel.h> diff --git a/drivers/net/ethernet/adi/adin1110.c b/drivers/net/ethernet/adi/adin1110.c index 3431a7e62b0d..a98b3139606a 100644 --- a/drivers/net/ethernet/adi/adin1110.c +++ b/drivers/net/ethernet/adi/adin1110.c @@ -26,7 +26,7 @@ #include <net/switchdev.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define ADIN1110_PHY_ID 0x1 diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c b/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c index 484fc2b5626f..ca163c8e3729 100644 --- a/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c +++ b/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #define pr_fmt(fmt) "bcmasp_ethtool: " fmt -#include <asm-generic/unaligned.h> +#include <linux/unaligned.h> #include <linux/ethtool.h> #include <linux/netdevice.h> #include <linux/platform_device.h> diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index c7e7dac057a3..f7be886570d8 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -37,7 +37,7 @@ #include <linux/phy.h> #include <linux/platform_data/bcmgenet.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "bcmgenet.h" diff --git a/drivers/net/ethernet/dec/tulip/de2104x.c b/drivers/net/ethernet/dec/tulip/de2104x.c index cd3dc4b89518..0a161a4db242 100644 --- a/drivers/net/ethernet/dec/tulip/de2104x.c +++ b/drivers/net/ethernet/dec/tulip/de2104x.c @@ -49,7 +49,7 @@ #include <asm/io.h> #include <asm/irq.h> #include <linux/uaccess.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> MODULE_AUTHOR("Jeff Garzik <jgarzik@pobox.com>"); MODULE_DESCRIPTION("Intel/Digital 21040/1 series PCI Ethernet driver"); diff --git a/drivers/net/ethernet/dec/tulip/eeprom.c b/drivers/net/ethernet/dec/tulip/eeprom.c index d5657ff15e3c..71ff9e6db209 100644 --- a/drivers/net/ethernet/dec/tulip/eeprom.c +++ b/drivers/net/ethernet/dec/tulip/eeprom.c @@ -13,7 +13,7 @@ #include <linux/pci.h> #include <linux/slab.h> #include "tulip.h" -#include <asm/unaligned.h> +#include <linux/unaligned.h> diff --git a/drivers/net/ethernet/dec/tulip/tulip.h b/drivers/net/ethernet/dec/tulip/tulip.h index bd786dfbc066..5e010e1fa6f7 100644 --- a/drivers/net/ethernet/dec/tulip/tulip.h +++ b/drivers/net/ethernet/dec/tulip/tulip.h @@ -23,7 +23,7 @@ #include <linux/pci.h> #include <asm/io.h> #include <asm/irq.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> diff --git a/drivers/net/ethernet/dec/tulip/tulip_core.c b/drivers/net/ethernet/dec/tulip/tulip_core.c index ecfad43df45a..27e01d780cd0 100644 --- a/drivers/net/ethernet/dec/tulip/tulip_core.c +++ b/drivers/net/ethernet/dec/tulip/tulip_core.c @@ -23,7 +23,7 @@ #include <linux/delay.h> #include <linux/mii.h> #include <linux/crc32.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/uaccess.h> #ifdef CONFIG_SPARC diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c index 11b14555802c..8f6b0bf48139 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) /* Copyright 2017-2019 NXP */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/mdio.h> #include <linux/module.h> #include <linux/fsl/enetc_mdio.h> diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h index a19cb2a786fd..1cca0425d493 100644 --- a/drivers/net/ethernet/freescale/fec.h +++ b/drivers/net/ethernet/freescale/fec.h @@ -691,10 +691,19 @@ struct fec_enet_private { /* XDP BPF Program */ struct bpf_prog *xdp_prog; + struct { + int pps_enable; + u64 ns_sys, ns_phc; + u32 at_corr; + u8 at_inc_corr; + } ptp_saved_state; + u64 ethtool_stats[]; }; void fec_ptp_init(struct platform_device *pdev, int irq_idx); +void fec_ptp_restore_state(struct fec_enet_private *fep); +void fec_ptp_save_state(struct fec_enet_private *fep); void fec_ptp_stop(struct platform_device *pdev); void fec_ptp_start_cyclecounter(struct net_device *ndev); int fec_ptp_set(struct net_device *ndev, struct kernel_hwtstamp_config *config, diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index acbb627d51bf..31ebf6a4f973 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -1077,6 +1077,8 @@ fec_restart(struct net_device *ndev) u32 rcntl = OPT_FRAME_SIZE | 0x04; u32 ecntl = FEC_ECR_ETHEREN; + fec_ptp_save_state(fep); + /* Whack a reset. We should wait for this. * For i.MX6SX SOC, enet use AXI bus, we use disable MAC * instead of reset MAC itself. @@ -1244,8 +1246,10 @@ fec_restart(struct net_device *ndev) writel(ecntl, fep->hwp + FEC_ECNTRL); fec_enet_active_rxring(ndev); - if (fep->bufdesc_ex) + if (fep->bufdesc_ex) { fec_ptp_start_cyclecounter(ndev); + fec_ptp_restore_state(fep); + } /* Enable interrupts we wish to service */ if (fep->link) @@ -1336,6 +1340,8 @@ fec_stop(struct net_device *ndev) netdev_err(ndev, "Graceful transmit stop did not complete!\n"); } + fec_ptp_save_state(fep); + /* Whack a reset. We should wait for this. * For i.MX6SX SOC, enet use AXI bus, we use disable MAC * instead of reset MAC itself. @@ -1366,6 +1372,9 @@ fec_stop(struct net_device *ndev) val = readl(fep->hwp + FEC_ECNTRL); val |= FEC_ECR_EN1588; writel(val, fep->hwp + FEC_ECNTRL); + + fec_ptp_start_cyclecounter(ndev); + fec_ptp_restore_state(fep); } } diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c index 4cffda363a14..a4eb6edb850a 100644 --- a/drivers/net/ethernet/freescale/fec_ptp.c +++ b/drivers/net/ethernet/freescale/fec_ptp.c @@ -764,6 +764,56 @@ void fec_ptp_init(struct platform_device *pdev, int irq_idx) schedule_delayed_work(&fep->time_keep, HZ); } +void fec_ptp_save_state(struct fec_enet_private *fep) +{ + unsigned long flags; + u32 atime_inc_corr; + + spin_lock_irqsave(&fep->tmreg_lock, flags); + + fep->ptp_saved_state.pps_enable = fep->pps_enable; + + fep->ptp_saved_state.ns_phc = timecounter_read(&fep->tc); + fep->ptp_saved_state.ns_sys = ktime_get_ns(); + + fep->ptp_saved_state.at_corr = readl(fep->hwp + FEC_ATIME_CORR); + atime_inc_corr = readl(fep->hwp + FEC_ATIME_INC) & FEC_T_INC_CORR_MASK; + fep->ptp_saved_state.at_inc_corr = (u8)(atime_inc_corr >> FEC_T_INC_CORR_OFFSET); + + spin_unlock_irqrestore(&fep->tmreg_lock, flags); +} + +/* Restore PTP functionality after a reset */ +void fec_ptp_restore_state(struct fec_enet_private *fep) +{ + u32 atime_inc = readl(fep->hwp + FEC_ATIME_INC) & FEC_T_INC_MASK; + unsigned long flags; + u32 counter; + u64 ns; + + spin_lock_irqsave(&fep->tmreg_lock, flags); + + /* Reset turned it off, so adjust our status flag */ + fep->pps_enable = 0; + + writel(fep->ptp_saved_state.at_corr, fep->hwp + FEC_ATIME_CORR); + atime_inc |= ((u32)fep->ptp_saved_state.at_inc_corr) << FEC_T_INC_CORR_OFFSET; + writel(atime_inc, fep->hwp + FEC_ATIME_INC); + + ns = ktime_get_ns() - fep->ptp_saved_state.ns_sys + fep->ptp_saved_state.ns_phc; + counter = ns & fep->cc.mask; + writel(counter, fep->hwp + FEC_ATIME); + timecounter_init(&fep->tc, &fep->cc, ns); + + spin_unlock_irqrestore(&fep->tmreg_lock, flags); + + /* Restart PPS if needed */ + if (fep->ptp_saved_state.pps_enable) { + /* Re-enable PPS */ + fec_ptp_enable_pps(fep, 1); + } +} + void fec_ptp_stop(struct platform_device *pdev) { struct net_device *ndev = platform_get_drvdata(pdev); diff --git a/drivers/net/ethernet/intel/e100.c b/drivers/net/ethernet/intel/e100.c index aa139b67a55b..3a5bbda235cb 100644 --- a/drivers/net/ethernet/intel/e100.c +++ b/drivers/net/ethernet/intel/e100.c @@ -146,7 +146,7 @@ #include <linux/string.h> #include <linux/firmware.h> #include <linux/rtnetlink.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define DRV_NAME "e100" diff --git a/drivers/net/ethernet/intel/ice/ice_fw_update.c b/drivers/net/ethernet/intel/ice/ice_fw_update.c index f81db6c107c8..2702a0da5c3e 100644 --- a/drivers/net/ethernet/intel/ice/ice_fw_update.c +++ b/drivers/net/ethernet/intel/ice/ice_fw_update.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (C) 2018-2019, Intel Corporation. */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/uuid.h> #include <linux/crc32.h> #include <linux/pldmfw.h> diff --git a/drivers/net/ethernet/lantiq_etop.c b/drivers/net/ethernet/lantiq_etop.c index 3c289bfe0a09..7179271f63b6 100644 --- a/drivers/net/ethernet/lantiq_etop.c +++ b/drivers/net/ethernet/lantiq_etop.c @@ -481,7 +481,9 @@ ltq_etop_tx(struct sk_buff *skb, struct net_device *dev) unsigned long flags; u32 byte_offset; - len = skb->len < ETH_ZLEN ? ETH_ZLEN : skb->len; + if (skb_put_padto(skb, ETH_ZLEN)) + return NETDEV_TX_OK; + len = skb->len; if ((desc->ctl & (LTQ_DMA_OWN | LTQ_DMA_C)) || ch->skb[ch->dma.desc]) { netdev_err(dev, "tx ring full\n"); diff --git a/drivers/net/ethernet/mediatek/mtk_wed_mcu.c b/drivers/net/ethernet/mediatek/mtk_wed_mcu.c index ea0884186d76..c06e5ad18b01 100644 --- a/drivers/net/ethernet/mediatek/mtk_wed_mcu.c +++ b/drivers/net/ethernet/mediatek/mtk_wed_mcu.c @@ -10,7 +10,7 @@ #include <linux/of_reserved_mem.h> #include <linux/mfd/syscon.h> #include <linux/soc/mediatek/mtk_wed.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "mtk_wed_regs.h" #include "mtk_wed_wo.h" diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index da0a1c65ec4a..57b7298a0e79 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -627,7 +627,7 @@ struct mlx5e_shampo_hd { struct mlx5e_dma_info *info; struct mlx5e_frag_page *pages; u16 curr_page_index; - u16 hd_per_wq; + u32 hd_per_wq; u16 hd_per_wqe; unsigned long *bitmap; u16 pi; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tir.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tir.c index d4239e3b3c88..11f724ad90db 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tir.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tir.c @@ -23,6 +23,9 @@ struct mlx5e_tir_builder *mlx5e_tir_builder_alloc(bool modify) struct mlx5e_tir_builder *builder; builder = kvzalloc(sizeof(*builder), GFP_KERNEL); + if (!builder) + return NULL; + builder->modify = modify; return builder; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c index 3d274599015b..ca92e518be76 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c @@ -67,7 +67,6 @@ static void mlx5e_ipsec_handle_sw_limits(struct work_struct *_work) return; spin_lock_bh(&x->lock); - xfrm_state_check_expire(x); if (x->km.state == XFRM_STATE_EXPIRED) { sa_entry->attrs.drop = true; spin_unlock_bh(&x->lock); @@ -75,6 +74,13 @@ static void mlx5e_ipsec_handle_sw_limits(struct work_struct *_work) mlx5e_accel_ipsec_fs_modify(sa_entry); return; } + + if (x->km.state != XFRM_STATE_VALID) { + spin_unlock_bh(&x->lock); + return; + } + + xfrm_state_check_expire(x); spin_unlock_bh(&x->lock); queue_delayed_work(sa_entry->ipsec->wq, &dwork->dwork, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index b09e9abd39f3..f8c7912abe0e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -642,7 +642,6 @@ mlx5e_sq_xmit_mpwqe(struct mlx5e_txqsq *sq, struct sk_buff *skb, return; err_unmap: - mlx5e_dma_unmap_wqe_err(sq, 1); sq->stats->dropped++; dev_kfree_skb_any(skb); mlx5e_tx_flush(sq); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/pci_vsc.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/pci_vsc.c index d0b595ba6110..432c98f2626d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/pci_vsc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/pci_vsc.c @@ -24,6 +24,11 @@ pci_write_config_dword((dev)->pdev, (dev)->vsc_addr + (offset), (val)) #define VSC_MAX_RETRIES 2048 +/* Reading VSC registers can take relatively long time. + * Yield the cpu every 128 registers read. + */ +#define VSC_GW_READ_BLOCK_COUNT 128 + enum { VSC_CTRL_OFFSET = 0x4, VSC_COUNTER_OFFSET = 0x8, @@ -273,6 +278,7 @@ int mlx5_vsc_gw_read_block_fast(struct mlx5_core_dev *dev, u32 *data, { unsigned int next_read_addr = 0; unsigned int read_addr = 0; + unsigned int count = 0; while (read_addr < length) { if (mlx5_vsc_gw_read_fast(dev, read_addr, &next_read_addr, @@ -280,6 +286,10 @@ int mlx5_vsc_gw_read_block_fast(struct mlx5_core_dev *dev, u32 *data, return read_addr; read_addr = next_read_addr; + if (++count == VSC_GW_READ_BLOCK_COUNT) { + cond_resched(); + count = 0; + } } return length; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_bwc_complex.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_bwc_complex.c index bb563f50ef09..601fad5fc54a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_bwc_complex.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_bwc_complex.c @@ -33,7 +33,7 @@ bool mlx5hws_bwc_match_params_is_complex(struct mlx5hws_context *ctx, * and let the usual match creation path handle it, * both for good and bad flows. */ - if (ret == E2BIG) { + if (ret == -E2BIG) { is_complex = true; mlx5hws_dbg(ctx, "Matcher definer layout: need complex matcher\n"); } else { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_definer.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_definer.c index 3bdb5c90efff..d566d2ddf424 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_definer.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_definer.c @@ -1845,7 +1845,7 @@ hws_definer_find_best_match_fit(struct mlx5hws_context *ctx, return 0; } - return E2BIG; + return -E2BIG; } static void @@ -1931,7 +1931,7 @@ mlx5hws_definer_calc_layout(struct mlx5hws_context *ctx, /* Find the match definer layout for header layout match union */ ret = hws_definer_find_best_match_fit(ctx, match_definer, match_hl); if (ret) { - if (ret == E2BIG) + if (ret == -E2BIG) mlx5hws_dbg(ctx, "Failed to create match definer from header layout - E2BIG\n"); else diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_matcher.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_matcher.c index 33d2b31e4b46..61a1155d4b4f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_matcher.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_matcher.c @@ -675,7 +675,7 @@ static int hws_matcher_bind_mt(struct mlx5hws_matcher *matcher) if (!(matcher->flags & MLX5HWS_MATCHER_FLAGS_COLLISION)) { ret = mlx5hws_definer_mt_init(ctx, matcher->mt); if (ret) { - if (ret == E2BIG) + if (ret == -E2BIG) mlx5hws_err(ctx, "Failed to set matcher templates with match definers\n"); return ret; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_send.c index a1adbb48735c..0c7989184c30 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_send.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_send.c @@ -653,6 +653,12 @@ static int hws_send_ring_create_sq(struct mlx5_core_dev *mdev, u32 pdn, return err; } +static void hws_send_ring_destroy_sq(struct mlx5_core_dev *mdev, + struct mlx5hws_send_ring_sq *sq) +{ + mlx5_core_destroy_sq(mdev, sq->sqn); +} + static int hws_send_ring_set_sq_rdy(struct mlx5_core_dev *mdev, u32 sqn) { void *in, *sqc; @@ -696,7 +702,7 @@ static int hws_send_ring_create_sq_rdy(struct mlx5_core_dev *mdev, u32 pdn, err = hws_send_ring_set_sq_rdy(mdev, sq->sqn); if (err) - hws_send_ring_close_sq(sq); + hws_send_ring_destroy_sq(mdev, sq); return err; } diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_devlink.c b/drivers/net/ethernet/meta/fbnic/fbnic_devlink.c index ef05ae8f5039..0072d612215e 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_devlink.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_devlink.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) Meta Platforms, Inc. and affiliates. */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/pci.h> #include <linux/types.h> #include <net/devlink.h> diff --git a/drivers/net/ethernet/microchip/fdma/Kconfig b/drivers/net/ethernet/microchip/fdma/Kconfig index 59159ad6701a..ec228c061351 100644 --- a/drivers/net/ethernet/microchip/fdma/Kconfig +++ b/drivers/net/ethernet/microchip/fdma/Kconfig @@ -6,7 +6,7 @@ if NET_VENDOR_MICROCHIP config FDMA - bool "FDMA API" + bool "FDMA API" if COMPILE_TEST help Provides the basic FDMA functionality for multiple Microchip switchcores. diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c b/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c index f3f5fb420468..70427643f777 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c @@ -45,8 +45,12 @@ void sparx5_ifh_parse(u32 *ifh, struct frame_info *info) fwd = (fwd >> 5); info->src_port = FIELD_GET(GENMASK(7, 1), fwd); + /* + * Bit 270-271 are occasionally unexpectedly set by the hardware, + * clear bits before extracting timestamp + */ info->timestamp = - ((u64)xtr_hdr[2] << 24) | + ((u64)(xtr_hdr[2] & GENMASK(5, 0)) << 24) | ((u64)xtr_hdr[3] << 16) | ((u64)xtr_hdr[4] << 8) | ((u64)xtr_hdr[5] << 0); diff --git a/drivers/net/ethernet/netronome/nfp/crypto/ipsec.c b/drivers/net/ethernet/netronome/nfp/crypto/ipsec.c index cc54faca2283..515069d5637b 100644 --- a/drivers/net/ethernet/netronome/nfp/crypto/ipsec.c +++ b/drivers/net/ethernet/netronome/nfp/crypto/ipsec.c @@ -6,7 +6,7 @@ #include <linux/kernel.h> #include <linux/init.h> #include <linux/netdevice.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/ktime.h> #include <net/xfrm.h> diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c index 3f10c5365c80..7c2200b49ce4 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c @@ -15,7 +15,7 @@ * abstraction builds upon this BAR interface. */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/kref.h> diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cppcore.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cppcore.c index a8286d0032d1..669f9f8fb507 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cppcore.c +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cppcore.c @@ -9,7 +9,7 @@ * Rolf Neugebauer <rolf.neugebauer@netronome.com> */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/delay.h> #include <linux/device.h> #include <linux/ioport.h> diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cpplib.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cpplib.c index 508ae6b571ca..addf02c63b1a 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cpplib.c +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cpplib.c @@ -9,7 +9,7 @@ * Rolf Neugebauer <rolf.neugebauer@netronome.com> */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/bitfield.h> #include <linux/delay.h> #include <linux/kernel.h> diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_hwinfo.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_hwinfo.c index f05dd34ab89f..cfa4db5d3f85 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_hwinfo.c +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_hwinfo.c @@ -15,7 +15,7 @@ */ #include <asm/byteorder.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/delay.h> #include <linux/log2.h> #include <linux/kernel.h> diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c index df0234a338a8..0bd6477292a6 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c @@ -7,7 +7,7 @@ * Jason McMullan <jason.mcmullan@netronome.com> */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/bitfield.h> #include <linux/delay.h> #include <linux/firmware.h> diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_rtsym.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_rtsym.c index 2260c2403a83..68862ac062d2 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_rtsym.c +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_rtsym.c @@ -10,7 +10,7 @@ * Francois H. Theron <francois.theron@netronome.com> */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/slab.h> diff --git a/drivers/net/ethernet/packetengines/hamachi.c b/drivers/net/ethernet/packetengines/hamachi.c index 1cc001087193..a36d422b5173 100644 --- a/drivers/net/ethernet/packetengines/hamachi.c +++ b/drivers/net/ethernet/packetengines/hamachi.c @@ -163,7 +163,7 @@ static int tx_params[MAX_UNITS] = {-1, -1, -1, -1, -1, -1, -1, -1}; #include <linux/uaccess.h> #include <asm/processor.h> /* Processor type for cache alignment. */ #include <asm/io.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <asm/cache.h> static const char version[] = diff --git a/drivers/net/ethernet/packetengines/yellowfin.c b/drivers/net/ethernet/packetengines/yellowfin.c index 640ac01689fb..c0515dc63246 100644 --- a/drivers/net/ethernet/packetengines/yellowfin.c +++ b/drivers/net/ethernet/packetengines/yellowfin.c @@ -102,7 +102,7 @@ static int gx_fix; #include <linux/bitops.h> #include <linux/uaccess.h> #include <asm/processor.h> /* Processor type for cache alignment. */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <asm/io.h> /* These identify the driver base version and may not be removed. */ diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index 305ec19ccef1..0cc9baaecb1b 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -28,7 +28,7 @@ #include <linux/bitfield.h> #include <linux/prefetch.h> #include <linux/ipv6.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <net/ip6_checksum.h> #include <net/netdev_queues.h> diff --git a/drivers/net/ethernet/smsc/smsc9420.c b/drivers/net/ethernet/smsc/smsc9420.c index 15cb96c2506d..f30d4b17c7fb 100644 --- a/drivers/net/ethernet/smsc/smsc9420.c +++ b/drivers/net/ethernet/smsc/smsc9420.c @@ -18,7 +18,7 @@ #include <linux/crc32.h> #include <linux/slab.h> #include <linux/module.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "smsc9420.h" #define DRV_NAME "smsc9420" diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index a1858f083eef..e65a65666cc1 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -14,6 +14,7 @@ #include <linux/slab.h> #include <linux/ethtool.h> #include <linux/io.h> +#include <linux/iopoll.h> #include "stmmac.h" #include "stmmac_pcs.h" #include "dwmac4.h" @@ -471,7 +472,7 @@ static int dwmac4_write_vlan_filter(struct net_device *dev, u8 index, u32 data) { void __iomem *ioaddr = (void __iomem *)dev->base_addr; - int i, timeout = 10; + int ret; u32 val; if (index >= hw->num_vlan) @@ -487,16 +488,15 @@ static int dwmac4_write_vlan_filter(struct net_device *dev, writel(val, ioaddr + GMAC_VLAN_TAG); - for (i = 0; i < timeout; i++) { - val = readl(ioaddr + GMAC_VLAN_TAG); - if (!(val & GMAC_VLAN_TAG_CTRL_OB)) - return 0; - udelay(1); + ret = readl_poll_timeout(ioaddr + GMAC_VLAN_TAG, val, + !(val & GMAC_VLAN_TAG_CTRL_OB), + 1000, 500000); + if (ret) { + netdev_err(dev, "Timeout accessing MAC_VLAN_Tag_Filter\n"); + return -EBUSY; } - netdev_err(dev, "Timeout accessing MAC_VLAN_Tag_Filter\n"); - - return -EBUSY; + return 0; } static int dwmac4_add_hw_vlan_rx_fltr(struct net_device *dev, diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index cbe99017cbfa..d253727b160f 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -763,7 +763,7 @@ fail_tx: k3_udma_glue_disable_rx_chn(rx_chn->rx_chn); fail_rx: - for (i = 0; i < common->rx_ch_num_flows; i--) + for (i = 0; i < common->rx_ch_num_flows; i++) k3_udma_glue_reset_rx_chn(rx_chn->rx_chn, i, &rx_chn->flows[i], am65_cpsw_nuss_rx_cleanup, 0); diff --git a/drivers/net/ethernet/ti/cpsw_ale.c b/drivers/net/ethernet/ti/cpsw_ale.c index 0d5d8917c70b..8d02d2b21429 100644 --- a/drivers/net/ethernet/ti/cpsw_ale.c +++ b/drivers/net/ethernet/ti/cpsw_ale.c @@ -96,6 +96,7 @@ enum { * @features: features supported by ALE * @tbl_entries: number of ALE entries * @reg_fields: pointer to array of register field configuration + * @num_fields: number of fields in the reg_fields array * @nu_switch_ale: NU Switch ALE * @vlan_entry_tbl: ALE vlan entry fields description tbl */ @@ -104,6 +105,7 @@ struct cpsw_ale_dev_id { u32 features; u32 tbl_entries; const struct reg_field *reg_fields; + int num_fields; bool nu_switch_ale; const struct ale_entry_fld *vlan_entry_tbl; }; @@ -1400,6 +1402,7 @@ static const struct cpsw_ale_dev_id cpsw_ale_id_match[] = { .dev_id = "cpsw", .tbl_entries = 1024, .reg_fields = ale_fields_cpsw, + .num_fields = ARRAY_SIZE(ale_fields_cpsw), .vlan_entry_tbl = vlan_entry_cpsw, }, { @@ -1407,12 +1410,14 @@ static const struct cpsw_ale_dev_id cpsw_ale_id_match[] = { .dev_id = "66ak2h-xgbe", .tbl_entries = 2048, .reg_fields = ale_fields_cpsw, + .num_fields = ARRAY_SIZE(ale_fields_cpsw), .vlan_entry_tbl = vlan_entry_cpsw, }, { .dev_id = "66ak2el", .features = CPSW_ALE_F_STATUS_REG, .reg_fields = ale_fields_cpsw_nu, + .num_fields = ARRAY_SIZE(ale_fields_cpsw_nu), .nu_switch_ale = true, .vlan_entry_tbl = vlan_entry_nu, }, @@ -1421,6 +1426,7 @@ static const struct cpsw_ale_dev_id cpsw_ale_id_match[] = { .features = CPSW_ALE_F_STATUS_REG, .tbl_entries = 64, .reg_fields = ale_fields_cpsw_nu, + .num_fields = ARRAY_SIZE(ale_fields_cpsw_nu), .nu_switch_ale = true, .vlan_entry_tbl = vlan_entry_nu, }, @@ -1429,6 +1435,7 @@ static const struct cpsw_ale_dev_id cpsw_ale_id_match[] = { .features = CPSW_ALE_F_STATUS_REG | CPSW_ALE_F_HW_AUTOAGING, .tbl_entries = 64, .reg_fields = ale_fields_cpsw_nu, + .num_fields = ARRAY_SIZE(ale_fields_cpsw_nu), .nu_switch_ale = true, .vlan_entry_tbl = vlan_entry_nu, }, @@ -1436,12 +1443,14 @@ static const struct cpsw_ale_dev_id cpsw_ale_id_match[] = { .dev_id = "j721e-cpswxg", .features = CPSW_ALE_F_STATUS_REG | CPSW_ALE_F_HW_AUTOAGING, .reg_fields = ale_fields_cpsw_nu, + .num_fields = ARRAY_SIZE(ale_fields_cpsw_nu), .vlan_entry_tbl = vlan_entry_k3_cpswxg, }, { .dev_id = "am64-cpswxg", .features = CPSW_ALE_F_STATUS_REG | CPSW_ALE_F_HW_AUTOAGING, .reg_fields = ale_fields_cpsw_nu, + .num_fields = ARRAY_SIZE(ale_fields_cpsw_nu), .vlan_entry_tbl = vlan_entry_k3_cpswxg, .tbl_entries = 512, }, @@ -1477,7 +1486,7 @@ static int cpsw_ale_regfield_init(struct cpsw_ale *ale) struct regmap *regmap = ale->regmap; int i; - for (i = 0; i < ALE_FIELDS_MAX; i++) { + for (i = 0; i < ale->params.num_fields; i++) { ale->fields[i] = devm_regmap_field_alloc(dev, regmap, reg_fields[i]); if (IS_ERR(ale->fields[i])) { @@ -1503,6 +1512,7 @@ struct cpsw_ale *cpsw_ale_create(struct cpsw_ale_params *params) params->ale_entries = ale_dev_id->tbl_entries; params->nu_switch_ale = ale_dev_id->nu_switch_ale; params->reg_fields = ale_dev_id->reg_fields; + params->num_fields = ale_dev_id->num_fields; ale = devm_kzalloc(params->dev, sizeof(*ale), GFP_KERNEL); if (!ale) diff --git a/drivers/net/ethernet/ti/cpsw_ale.h b/drivers/net/ethernet/ti/cpsw_ale.h index 1e4e9a3dd234..87b7d1b3a34a 100644 --- a/drivers/net/ethernet/ti/cpsw_ale.h +++ b/drivers/net/ethernet/ti/cpsw_ale.h @@ -24,6 +24,7 @@ struct cpsw_ale_params { */ bool nu_switch_ale; const struct reg_field *reg_fields; + int num_fields; const char *dev_id; unsigned long bus_freq; }; diff --git a/drivers/net/ieee802154/Kconfig b/drivers/net/ieee802154/Kconfig index 95da876c5613..1075e24b11de 100644 --- a/drivers/net/ieee802154/Kconfig +++ b/drivers/net/ieee802154/Kconfig @@ -101,6 +101,7 @@ config IEEE802154_CA8210_DEBUGFS config IEEE802154_MCR20A tristate "MCR20A transceiver driver" + select REGMAP_SPI depends on IEEE802154_DRIVERS && MAC802154 depends on SPI help diff --git a/drivers/net/ieee802154/cc2520.c b/drivers/net/ieee802154/cc2520.c index a94d8dd71aad..2b7034193a00 100644 --- a/drivers/net/ieee802154/cc2520.c +++ b/drivers/net/ieee802154/cc2520.c @@ -16,7 +16,7 @@ #include <linux/skbuff.h> #include <linux/ieee802154.h> #include <linux/crc-ccitt.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <net/mac802154.h> #include <net/cfg802154.h> diff --git a/drivers/net/ieee802154/mcr20a.c b/drivers/net/ieee802154/mcr20a.c index 433fb5839203..020d392a98b6 100644 --- a/drivers/net/ieee802154/mcr20a.c +++ b/drivers/net/ieee802154/mcr20a.c @@ -1302,16 +1302,13 @@ mcr20a_probe(struct spi_device *spi) irq_type = IRQF_TRIGGER_FALLING; ret = devm_request_irq(&spi->dev, spi->irq, mcr20a_irq_isr, - irq_type, dev_name(&spi->dev), lp); + irq_type | IRQF_NO_AUTOEN, dev_name(&spi->dev), lp); if (ret) { dev_err(&spi->dev, "could not request_irq for mcr20a\n"); ret = -ENODEV; goto free_dev; } - /* disable_irq by default and wait for starting hardware */ - disable_irq(spi->irq); - ret = ieee802154_register_hw(hw); if (ret) { dev_crit(&spi->dev, "ieee802154_register_hw failed\n"); diff --git a/drivers/net/mctp/mctp-i3c.c b/drivers/net/mctp/mctp-i3c.c index 8e989c157caa..1bc87a062686 100644 --- a/drivers/net/mctp/mctp-i3c.c +++ b/drivers/net/mctp/mctp-i3c.c @@ -13,7 +13,7 @@ #include <linux/i3c/device.h> #include <linux/i3c/master.h> #include <linux/if_arp.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <net/mctp.h> #include <net/mctpdevice.h> diff --git a/drivers/net/pcs/pcs-xpcs-wx.c b/drivers/net/pcs/pcs-xpcs-wx.c index 19c75886f070..5f5cd3596cb8 100644 --- a/drivers/net/pcs/pcs-xpcs-wx.c +++ b/drivers/net/pcs/pcs-xpcs-wx.c @@ -109,7 +109,7 @@ static void txgbe_pma_config_1g(struct dw_xpcs *xpcs) txgbe_write_pma(xpcs, TXGBE_DFE_TAP_CTL0, 0); val = txgbe_read_pma(xpcs, TXGBE_RX_GEN_CTL3); val = u16_replace_bits(val, 0x4, TXGBE_RX_GEN_CTL3_LOS_TRSHLD0); - txgbe_write_pma(xpcs, TXGBE_RX_EQ_ATTN_CTL, val); + txgbe_write_pma(xpcs, TXGBE_RX_GEN_CTL3, val); txgbe_write_pma(xpcs, TXGBE_MPLLA_CTL0, 0x20); txgbe_write_pma(xpcs, TXGBE_MPLLA_CTL3, 0x46); diff --git a/drivers/net/phy/air_en8811h.c b/drivers/net/phy/air_en8811h.c index 3cdc8c6b30b6..8d076b9609fd 100644 --- a/drivers/net/phy/air_en8811h.c +++ b/drivers/net/phy/air_en8811h.c @@ -15,7 +15,7 @@ #include <linux/firmware.h> #include <linux/property.h> #include <linux/wordpart.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define EN8811H_PHY_ID 0x03a2a411 diff --git a/drivers/net/phy/aquantia/aquantia_firmware.c b/drivers/net/phy/aquantia/aquantia_firmware.c index dac6464b5fe2..dab3af80593f 100644 --- a/drivers/net/phy/aquantia/aquantia_firmware.c +++ b/drivers/net/phy/aquantia/aquantia_firmware.c @@ -6,7 +6,7 @@ #include <linux/crc-itu-t.h> #include <linux/nvmem-consumer.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "aquantia.h" diff --git a/drivers/net/phy/bcm-phy-ptp.c b/drivers/net/phy/bcm-phy-ptp.c index 874a1b64b115..208e8f561e06 100644 --- a/drivers/net/phy/bcm-phy-ptp.c +++ b/drivers/net/phy/bcm-phy-ptp.c @@ -4,7 +4,7 @@ * Copyright (C) 2022 Jonathan Lemon <jonathan.lemon@gmail.com> */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/mii.h> #include <linux/phy.h> #include <linux/ptp_classify.h> diff --git a/drivers/net/phy/mscc/mscc_ptp.c b/drivers/net/phy/mscc/mscc_ptp.c index c1ddae36a2ae..738a8822fcf0 100644 --- a/drivers/net/phy/mscc/mscc_ptp.c +++ b/drivers/net/phy/mscc/mscc_ptp.c @@ -15,7 +15,7 @@ #include <linux/ptp_classify.h> #include <linux/ptp_clock_kernel.h> #include <linux/udp.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "mscc.h" #include "mscc_ptp.h" diff --git a/drivers/net/phy/qt2025.rs b/drivers/net/phy/qt2025.rs index 28d8981f410b..1ab065798175 100644 --- a/drivers/net/phy/qt2025.rs +++ b/drivers/net/phy/qt2025.rs @@ -15,7 +15,7 @@ use kernel::firmware::Firmware; use kernel::net::phy::{ self, reg::{Mmd, C45}, - DeviceId, Driver, + Driver, }; use kernel::prelude::*; use kernel::sizes::{SZ_16K, SZ_8K}; @@ -23,7 +23,7 @@ use kernel::sizes::{SZ_16K, SZ_8K}; kernel::module_phy_driver! { drivers: [PhyQT2025], device_table: [ - DeviceId::new_with_driver::<PhyQT2025>(), + phy::DeviceId::new_with_driver::<PhyQT2025>(), ], name: "qt2025_phy", author: "FUJITA Tomonori <fujita.tomonori@gmail.com>", diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c index 25e5bfbb6f89..c15d2f66ef0d 100644 --- a/drivers/net/phy/realtek.c +++ b/drivers/net/phy/realtek.c @@ -527,6 +527,9 @@ static int rtl8211f_led_hw_control_get(struct phy_device *phydev, u8 index, { int val; + if (index >= RTL8211F_LED_COUNT) + return -EINVAL; + val = phy_read_paged(phydev, 0xd04, RTL8211F_LEDCR); if (val < 0) return val; diff --git a/drivers/net/ppp/ppp_async.c b/drivers/net/ppp/ppp_async.c index c33c3db3cc08..a940b9a67107 100644 --- a/drivers/net/ppp/ppp_async.c +++ b/drivers/net/ppp/ppp_async.c @@ -29,7 +29,7 @@ #include <linux/interrupt.h> #include <linux/jiffies.h> #include <linux/slab.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/uaccess.h> #include <asm/string.h> diff --git a/drivers/net/ppp/ppp_deflate.c b/drivers/net/ppp/ppp_deflate.c index 4d2ff63f2ee2..d93aeacc0dba 100644 --- a/drivers/net/ppp/ppp_deflate.c +++ b/drivers/net/ppp/ppp_deflate.c @@ -16,7 +16,7 @@ #include <linux/ppp-comp.h> #include <linux/zlib.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /* * State for a Deflate (de)compressor. diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index 4b2971e2bf48..4583e15ad03a 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -44,7 +44,7 @@ #include <linux/mutex.h> #include <linux/slab.h> #include <linux/file.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <net/slhc_vj.h> #include <linux/atomic.h> #include <linux/refcount.h> @@ -2269,7 +2269,7 @@ static bool ppp_channel_bridge_input(struct channel *pch, struct sk_buff *skb) if (!pchb) goto out_rcu; - spin_lock(&pchb->downl); + spin_lock_bh(&pchb->downl); if (!pchb->chan) { /* channel got unregistered */ kfree_skb(skb); @@ -2281,7 +2281,7 @@ static bool ppp_channel_bridge_input(struct channel *pch, struct sk_buff *skb) kfree_skb(skb); outl: - spin_unlock(&pchb->downl); + spin_unlock_bh(&pchb->downl); out_rcu: rcu_read_unlock(); diff --git a/drivers/net/ppp/ppp_mppe.c b/drivers/net/ppp/ppp_mppe.c index 208f6e24f37c..bcc1eaedf58f 100644 --- a/drivers/net/ppp/ppp_mppe.c +++ b/drivers/net/ppp/ppp_mppe.c @@ -56,7 +56,7 @@ #include <linux/ppp_defs.h> #include <linux/ppp-comp.h> #include <linux/scatterlist.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "ppp_mppe.h" diff --git a/drivers/net/ppp/ppp_synctty.c b/drivers/net/ppp/ppp_synctty.c index 45bf59ac8f57..644e99fc3623 100644 --- a/drivers/net/ppp/ppp_synctty.c +++ b/drivers/net/ppp/ppp_synctty.c @@ -43,7 +43,7 @@ #include <linux/interrupt.h> #include <linux/slab.h> #include <linux/refcount.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/uaccess.h> #define PPP_VERSION "2.4.2" diff --git a/drivers/net/slip/slhc.c b/drivers/net/slip/slhc.c index 18df7ca66198..252cd757d3a2 100644 --- a/drivers/net/slip/slhc.c +++ b/drivers/net/slip/slhc.c @@ -77,7 +77,7 @@ #include <linux/timer.h> #include <linux/uaccess.h> #include <net/checksum.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> static unsigned char *encode(unsigned char *cp, unsigned short n); static long decode(unsigned char **cpp); diff --git a/drivers/net/usb/net1080.c b/drivers/net/usb/net1080.c index b0c0c9dd6a02..5d4a1fd2b524 100644 --- a/drivers/net/usb/net1080.c +++ b/drivers/net/usb/net1080.c @@ -17,7 +17,7 @@ #include <linux/usb/usbnet.h> #include <linux/slab.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /* diff --git a/drivers/net/usb/sierra_net.c b/drivers/net/usb/sierra_net.c index 673d3aa83792..3d239b8d1a1b 100644 --- a/drivers/net/usb/sierra_net.c +++ b/drivers/net/usb/sierra_net.c @@ -30,7 +30,7 @@ static const char driver_name[] = "sierra_net"; #include <linux/usb/cdc.h> #include <net/ip.h> #include <net/udp.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/usb/usbnet.h> #define SWI_USB_REQUEST_GET_FW_ATTR 0x06 diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index 4d8ccaf9a2b4..4087f72f0d2b 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -608,7 +608,9 @@ static void vrf_finish_direct(struct sk_buff *skb) eth_zero_addr(eth->h_dest); eth->h_proto = skb->protocol; + rcu_read_lock_bh(); dev_queue_xmit_nit(skb, vrf_dev); + rcu_read_unlock_bh(); skb_pull(skb, ETH_HLEN); } diff --git a/drivers/net/wireless/ath/ath5k/base.c b/drivers/net/wireless/ath/ath5k/base.c index abe41330fb69..4d88b02ffa79 100644 --- a/drivers/net/wireless/ath/ath5k/base.c +++ b/drivers/net/wireless/ath/ath5k/base.c @@ -59,7 +59,7 @@ #include <net/cfg80211.h> #include <net/ieee80211_radiotap.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <net/mac80211.h> #include "base.h" diff --git a/drivers/net/wireless/ath/ath5k/mac80211-ops.c b/drivers/net/wireless/ath/ath5k/mac80211-ops.c index eea4bda77608..d81b2ad0b095 100644 --- a/drivers/net/wireless/ath/ath5k/mac80211-ops.c +++ b/drivers/net/wireless/ath/ath5k/mac80211-ops.c @@ -44,7 +44,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <net/mac80211.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "ath5k.h" #include "base.h" diff --git a/drivers/net/wireless/ath/ath5k/pcu.c b/drivers/net/wireless/ath/ath5k/pcu.c index 3f4ce4e9c532..90e0859a8e50 100644 --- a/drivers/net/wireless/ath/ath5k/pcu.c +++ b/drivers/net/wireless/ath/ath5k/pcu.c @@ -24,7 +24,7 @@ * Protocol Control Unit Functions * \*********************************/ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "ath5k.h" #include "reg.h" diff --git a/drivers/net/wireless/ath/ath5k/phy.c b/drivers/net/wireless/ath/ath5k/phy.c index 7ee4e1616f45..4825f9cb9cb8 100644 --- a/drivers/net/wireless/ath/ath5k/phy.c +++ b/drivers/net/wireless/ath/ath5k/phy.c @@ -27,7 +27,7 @@ #include <linux/delay.h> #include <linux/slab.h> #include <linux/sort.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "ath5k.h" #include "reg.h" diff --git a/drivers/net/wireless/ath/ath5k/reset.c b/drivers/net/wireless/ath/ath5k/reset.c index 9fdb5283b39c..c67f163c0858 100644 --- a/drivers/net/wireless/ath/ath5k/reset.c +++ b/drivers/net/wireless/ath/ath5k/reset.c @@ -25,7 +25,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/pci.h> /* To determine if a card is pci-e */ #include <linux/log2.h> diff --git a/drivers/net/wireless/ath/ath6kl/htc_mbox.c b/drivers/net/wireless/ath/ath6kl/htc_mbox.c index fb5144e2d86c..f8a94d764be6 100644 --- a/drivers/net/wireless/ath/ath6kl/htc_mbox.c +++ b/drivers/net/wireless/ath/ath6kl/htc_mbox.c @@ -21,7 +21,7 @@ #include "hif-ops.h" #include "trace.h" -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define CALC_TXRX_PADDED_LEN(dev, len) (__ALIGN_MASK((len), (dev)->block_mask)) diff --git a/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c b/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c index 944f46cdf34c..73c38a6b4880 100644 --- a/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c +++ b/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c @@ -14,7 +14,7 @@ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/kernel.h> #include "hw.h" #include "ar9003_phy.h" diff --git a/drivers/net/wireless/ath/ath9k/debug.c b/drivers/net/wireless/ath/ath9k/debug.c index 51abc470125b..eff894958a73 100644 --- a/drivers/net/wireless/ath/ath9k/debug.c +++ b/drivers/net/wireless/ath/ath9k/debug.c @@ -17,7 +17,7 @@ #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/export.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "ath9k.h" diff --git a/drivers/net/wireless/ath/ath9k/eeprom_4k.c b/drivers/net/wireless/ath/ath9k/eeprom_4k.c index 27b860b0c769..3e16cfe059f3 100644 --- a/drivers/net/wireless/ath/ath9k/eeprom_4k.c +++ b/drivers/net/wireless/ath/ath9k/eeprom_4k.c @@ -14,7 +14,7 @@ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "hw.h" #include "ar9002_phy.h" diff --git a/drivers/net/wireless/ath/ath9k/eeprom_9287.c b/drivers/net/wireless/ath/ath9k/eeprom_9287.c index d85472ee4d85..c139ac49ccf6 100644 --- a/drivers/net/wireless/ath/ath9k/eeprom_9287.c +++ b/drivers/net/wireless/ath/ath9k/eeprom_9287.c @@ -14,7 +14,7 @@ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "hw.h" #include "ar9002_phy.h" diff --git a/drivers/net/wireless/ath/ath9k/eeprom_def.c b/drivers/net/wireless/ath/ath9k/eeprom_def.c index 84b31caf8ca6..5ba467cb7425 100644 --- a/drivers/net/wireless/ath/ath9k/eeprom_def.c +++ b/drivers/net/wireless/ath/ath9k/eeprom_def.c @@ -14,7 +14,7 @@ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "hw.h" #include "ar9002_phy.h" diff --git a/drivers/net/wireless/ath/ath9k/hif_usb.c b/drivers/net/wireless/ath/ath9k/hif_usb.c index a3733c9b484e..7265766cddbd 100644 --- a/drivers/net/wireless/ath/ath9k/hif_usb.c +++ b/drivers/net/wireless/ath/ath9k/hif_usb.c @@ -14,7 +14,7 @@ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "htc.h" MODULE_FIRMWARE(HTC_7010_MODULE_FW); diff --git a/drivers/net/wireless/ath/ath9k/hw.c b/drivers/net/wireless/ath/ath9k/hw.c index 04a4b9ea61c3..c3a6368bfc68 100644 --- a/drivers/net/wireless/ath/ath9k/hw.c +++ b/drivers/net/wireless/ath/ath9k/hw.c @@ -21,7 +21,7 @@ #include <linux/bitops.h> #include <linux/etherdevice.h> #include <linux/gpio.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "hw.h" #include "hw-ops.h" diff --git a/drivers/net/wireless/ath/carl9170/mac.c b/drivers/net/wireless/ath/carl9170/mac.c index 6cdbee5beb07..20ceed0dd4be 100644 --- a/drivers/net/wireless/ath/carl9170/mac.c +++ b/drivers/net/wireless/ath/carl9170/mac.c @@ -36,7 +36,7 @@ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "carl9170.h" #include "cmd.h" diff --git a/drivers/net/wireless/ath/hw.c b/drivers/net/wireless/ath/hw.c index 85955572a705..b301e6fbce6c 100644 --- a/drivers/net/wireless/ath/hw.c +++ b/drivers/net/wireless/ath/hw.c @@ -15,7 +15,7 @@ */ #include <linux/export.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "ath.h" #include "reg.h" diff --git a/drivers/net/wireless/ath/key.c b/drivers/net/wireless/ath/key.c index 21a93fec284d..0ae436bd9b66 100644 --- a/drivers/net/wireless/ath/key.c +++ b/drivers/net/wireless/ath/key.c @@ -16,7 +16,7 @@ */ #include <linux/export.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <net/mac80211.h> #include "ath.h" diff --git a/drivers/net/wireless/broadcom/b43/main.c b/drivers/net/wireless/broadcom/b43/main.c index 8e56dcf9309d..25b4ef9d3c9a 100644 --- a/drivers/net/wireless/broadcom/b43/main.c +++ b/drivers/net/wireless/broadcom/b43/main.c @@ -30,7 +30,7 @@ #include <linux/io.h> #include <linux/dma-mapping.h> #include <linux/slab.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "b43.h" #include "main.h" diff --git a/drivers/net/wireless/broadcom/b43legacy/main.c b/drivers/net/wireless/broadcom/b43legacy/main.c index 441d6440671b..2370a2e6a2e3 100644 --- a/drivers/net/wireless/broadcom/b43legacy/main.c +++ b/drivers/net/wireless/broadcom/b43legacy/main.c @@ -27,7 +27,7 @@ #include <linux/dma-mapping.h> #include <linux/slab.h> #include <net/dst.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "b43legacy.h" #include "main.h" diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.h index 9ca1b2aadcb5..eed439b84010 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.h +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.h @@ -7,7 +7,7 @@ #ifndef FWEH_H_ #define FWEH_H_ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/skbuff.h> #include <linux/if_ether.h> #include <linux/if.h> diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c index ce482a3877e9..5dee54819fbd 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c @@ -16,7 +16,7 @@ #include <linux/kthread.h> #include <linux/io.h> #include <linux/random.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <soc.h> #include <chipcommon.h> diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c index 1461dc453ac2..7b936668c1b6 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c @@ -23,7 +23,7 @@ #include <linux/bcma/bcma.h> #include <linux/debugfs.h> #include <linux/vmalloc.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <defs.h> #include <brcmu_wifi.h> #include <brcmu_utils.h> diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/xtlv.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/xtlv.c index 2f8908074303..08841b9a5b81 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/xtlv.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/xtlv.c @@ -3,7 +3,7 @@ * Copyright (c) 2019 Broadcom */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/math.h> #include <linux/string.h> diff --git a/drivers/net/wireless/intel/iwlegacy/3945.c b/drivers/net/wireless/intel/iwlegacy/3945.c index e95800b77f6b..14d2331ee6cb 100644 --- a/drivers/net/wireless/intel/iwlegacy/3945.c +++ b/drivers/net/wireless/intel/iwlegacy/3945.c @@ -20,7 +20,7 @@ #include <linux/netdevice.h> #include <linux/firmware.h> #include <linux/etherdevice.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <net/mac80211.h> #include "common.h" diff --git a/drivers/net/wireless/intel/iwlegacy/4965.c b/drivers/net/wireless/intel/iwlegacy/4965.c index c34729f576cd..b63e29590b04 100644 --- a/drivers/net/wireless/intel/iwlegacy/4965.c +++ b/drivers/net/wireless/intel/iwlegacy/4965.c @@ -20,7 +20,7 @@ #include <linux/units.h> #include <net/mac80211.h> #include <linux/etherdevice.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "common.h" #include "4965.h" diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/led.c b/drivers/net/wireless/intel/iwlwifi/dvm/led.c index 71f67a019cf6..5ca85d90a8d6 100644 --- a/drivers/net/wireless/intel/iwlwifi/dvm/led.c +++ b/drivers/net/wireless/intel/iwlwifi/dvm/led.c @@ -13,7 +13,7 @@ #include <linux/netdevice.h> #include <net/mac80211.h> #include <linux/etherdevice.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "iwl-io.h" #include "iwl-trans.h" #include "iwl-modparams.h" diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/rx.c b/drivers/net/wireless/intel/iwlwifi/dvm/rx.c index e9d2717362cf..7f67e602940c 100644 --- a/drivers/net/wireless/intel/iwlwifi/dvm/rx.c +++ b/drivers/net/wireless/intel/iwlwifi/dvm/rx.c @@ -13,7 +13,7 @@ #include <linux/slab.h> #include <linux/sched.h> #include <net/mac80211.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "iwl-trans.h" #include "iwl-io.h" diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rx.c b/drivers/net/wireless/intel/iwlwifi/mvm/rx.c index 047c020f8efa..1a0b5f8d4339 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rx.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rx.c @@ -4,7 +4,7 @@ * Copyright (C) 2013-2015 Intel Mobile Communications GmbH * Copyright (C) 2016-2017 Intel Deutschland GmbH */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/etherdevice.h> #include <linux/skbuff.h> #include "iwl-trans.h" diff --git a/drivers/net/wireless/marvell/libertas/cfg.c b/drivers/net/wireless/marvell/libertas/cfg.c index b700c213d10c..afe9bcd3ad46 100644 --- a/drivers/net/wireless/marvell/libertas/cfg.c +++ b/drivers/net/wireless/marvell/libertas/cfg.c @@ -15,7 +15,7 @@ #include <linux/slab.h> #include <linux/ieee80211.h> #include <net/cfg80211.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "decl.h" #include "cfg.h" diff --git a/drivers/net/wireless/marvell/libertas/cmdresp.c b/drivers/net/wireless/marvell/libertas/cmdresp.c index 74cb7551f427..f2aa659e7714 100644 --- a/drivers/net/wireless/marvell/libertas/cmdresp.c +++ b/drivers/net/wireless/marvell/libertas/cmdresp.c @@ -8,7 +8,7 @@ #include <linux/slab.h> #include <linux/delay.h> #include <linux/sched.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <net/cfg80211.h> #include "cfg.h" diff --git a/drivers/net/wireless/marvell/mwifiex/cmdevt.c b/drivers/net/wireless/marvell/mwifiex/cmdevt.c index 7894102f03eb..1cff001bdc51 100644 --- a/drivers/net/wireless/marvell/mwifiex/cmdevt.c +++ b/drivers/net/wireless/marvell/mwifiex/cmdevt.c @@ -5,7 +5,7 @@ * Copyright 2011-2020 NXP */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "decl.h" #include "ioctl.h" #include "util.h" diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c b/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c index bcd24c9072ec..4de45a56812d 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c @@ -10,7 +10,7 @@ #include <linux/mtd/mtd.h> #include <linux/mtd/partitions.h> #include <linux/etherdevice.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "mt76x0.h" #include "eeprom.h" #include "../mt76x02_phy.h" diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_eeprom.c b/drivers/net/wireless/mediatek/mt76/mt76x02_eeprom.c index 5d402cf2951c..a5e3392c0b48 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x02_eeprom.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x02_eeprom.c @@ -4,7 +4,7 @@ * Copyright (C) 2018 Lorenzo Bianconi <lorenzo.bianconi83@gmail.com> */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "mt76x02_eeprom.h" diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/eeprom.c b/drivers/net/wireless/mediatek/mt76/mt76x2/eeprom.c index 1fe5f5a02f93..156b16c17b2b 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x2/eeprom.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x2/eeprom.c @@ -5,7 +5,7 @@ #include <linux/module.h> #include <linux/of.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "mt76x2.h" #include "eeprom.h" diff --git a/drivers/net/wireless/mediatek/mt7601u/dma.h b/drivers/net/wireless/mediatek/mt7601u/dma.h index 81e559ec1c7b..cda9c267516e 100644 --- a/drivers/net/wireless/mediatek/mt7601u/dma.h +++ b/drivers/net/wireless/mediatek/mt7601u/dma.h @@ -7,7 +7,7 @@ #ifndef __MT7601U_DMA_H #define __MT7601U_DMA_H -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/skbuff.h> #define MT_DMA_HDR_LEN 4 diff --git a/drivers/net/wireless/mediatek/mt7601u/eeprom.c b/drivers/net/wireless/mediatek/mt7601u/eeprom.c index 625bebe60538..d4d31a546556 100644 --- a/drivers/net/wireless/mediatek/mt7601u/eeprom.c +++ b/drivers/net/wireless/mediatek/mt7601u/eeprom.c @@ -8,7 +8,7 @@ #include <linux/mtd/mtd.h> #include <linux/mtd/partitions.h> #include <linux/etherdevice.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "mt7601u.h" #include "eeprom.h" #include "mac.h" diff --git a/drivers/net/wireless/purelifi/plfxlc/usb.c b/drivers/net/wireless/purelifi/plfxlc/usb.c index 15334940287d..56d1139ba8bc 100644 --- a/drivers/net/wireless/purelifi/plfxlc/usb.c +++ b/drivers/net/wireless/purelifi/plfxlc/usb.c @@ -16,7 +16,7 @@ #include <linux/string.h> #include <linux/module.h> #include <net/mac80211.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/sysfs.h> #include "mac.h" diff --git a/drivers/net/wireless/zydas/zd1211rw/zd_usb.c b/drivers/net/wireless/zydas/zd1211rw/zd_usb.c index a8a94edf2a70..9ae10f65f2af 100644 --- a/drivers/net/wireless/zydas/zd1211rw/zd_usb.c +++ b/drivers/net/wireless/zydas/zd1211rw/zd_usb.c @@ -17,7 +17,7 @@ #include <linux/workqueue.h> #include <linux/module.h> #include <net/mac80211.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "zd_def.h" #include "zd_mac.h" diff --git a/drivers/net/wwan/qcom_bam_dmux.c b/drivers/net/wwan/qcom_bam_dmux.c index 26ca719fa0de..5dcb9a84a12e 100644 --- a/drivers/net/wwan/qcom_bam_dmux.c +++ b/drivers/net/wwan/qcom_bam_dmux.c @@ -823,17 +823,17 @@ static int bam_dmux_probe(struct platform_device *pdev) ret = devm_request_threaded_irq(dev, pc_ack_irq, NULL, bam_dmux_pc_ack_irq, IRQF_ONESHOT, NULL, dmux); if (ret) - return ret; + goto err_disable_pm; ret = devm_request_threaded_irq(dev, dmux->pc_irq, NULL, bam_dmux_pc_irq, IRQF_ONESHOT, NULL, dmux); if (ret) - return ret; + goto err_disable_pm; ret = irq_get_irqchip_state(dmux->pc_irq, IRQCHIP_STATE_LINE_LEVEL, &dmux->pc_state); if (ret) - return ret; + goto err_disable_pm; /* Check if remote finished initialization before us */ if (dmux->pc_state) { @@ -844,6 +844,11 @@ static int bam_dmux_probe(struct platform_device *pdev) } return 0; + +err_disable_pm: + pm_runtime_disable(dev); + pm_runtime_dont_use_autosuspend(dev); + return ret; } static void bam_dmux_remove(struct platform_device *pdev) diff --git a/drivers/nfc/nfcmrvl/fw_dnld.c b/drivers/nfc/nfcmrvl/fw_dnld.c index e83f65596a88..93094418fd24 100644 --- a/drivers/nfc/nfcmrvl/fw_dnld.c +++ b/drivers/nfc/nfcmrvl/fw_dnld.c @@ -6,7 +6,7 @@ */ #include <linux/module.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/firmware.h> #include <linux/nfc.h> #include <net/nfc/nci.h> diff --git a/drivers/nfc/nxp-nci/firmware.c b/drivers/nfc/nxp-nci/firmware.c index 119bf305c642..381b5bb75477 100644 --- a/drivers/nfc/nxp-nci/firmware.c +++ b/drivers/nfc/nxp-nci/firmware.c @@ -13,7 +13,7 @@ #include <linux/completion.h> #include <linux/firmware.h> #include <linux/nfc.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "nxp-nci.h" diff --git a/drivers/nfc/nxp-nci/i2c.c b/drivers/nfc/nxp-nci/i2c.c index a8aced0b8010..049662ffdf97 100644 --- a/drivers/nfc/nxp-nci/i2c.c +++ b/drivers/nfc/nxp-nci/i2c.c @@ -19,7 +19,7 @@ #include <linux/module.h> #include <linux/nfc.h> #include <linux/gpio/consumer.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <net/nfc/nfc.h> diff --git a/drivers/nfc/pn544/i2c.c b/drivers/nfc/pn544/i2c.c index e2a6575b9ff7..a0dfb3f98d5a 100644 --- a/drivers/nfc/pn544/i2c.c +++ b/drivers/nfc/pn544/i2c.c @@ -17,7 +17,7 @@ #include <linux/firmware.h> #include <linux/gpio/consumer.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <net/nfc/hci.h> #include <net/nfc/llc.h> diff --git a/drivers/nvme/common/auth.c b/drivers/nvme/common/auth.c index a3455f1d67fa..9b7126e1a19d 100644 --- a/drivers/nvme/common/auth.c +++ b/drivers/nvme/common/auth.c @@ -8,7 +8,7 @@ #include <linux/base64.h> #include <linux/prandom.h> #include <linux/scatterlist.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <crypto/hash.h> #include <crypto/dh.h> #include <linux/nvme.h> diff --git a/drivers/nvme/host/auth.c b/drivers/nvme/host/auth.c index 371e14f0a203..5ea0e21709da 100644 --- a/drivers/nvme/host/auth.c +++ b/drivers/nvme/host/auth.c @@ -6,7 +6,7 @@ #include <linux/crc32.h> #include <linux/base64.h> #include <linux/prandom.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <crypto/hash.h> #include <crypto/dh.h> #include "nvme.h" diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index ba6508455e18..43d73d31c66f 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -22,7 +22,7 @@ #include <linux/nvme_ioctl.h> #include <linux/pm_qos.h> #include <linux/ratelimit.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "nvme.h" #include "fabrics.h" diff --git a/drivers/nvme/host/hwmon.c b/drivers/nvme/host/hwmon.c index 8df73a0b3980..89a1a1043d63 100644 --- a/drivers/nvme/host/hwmon.c +++ b/drivers/nvme/host/hwmon.c @@ -6,7 +6,7 @@ #include <linux/hwmon.h> #include <linux/units.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "nvme.h" diff --git a/drivers/nvme/host/pr.c b/drivers/nvme/host/pr.c index 7347ddf85f00..dc7922f22600 100644 --- a/drivers/nvme/host/pr.c +++ b/drivers/nvme/host/pr.c @@ -5,7 +5,7 @@ */ #include <linux/blkdev.h> #include <linux/pr.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "nvme.h" diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index c8fd0e8f0237..24a2759798d0 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -18,7 +18,7 @@ #include <linux/mutex.h> #include <linux/scatterlist.h> #include <linux/nvme.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <rdma/ib_verbs.h> #include <rdma/rdma_cm.h> diff --git a/drivers/nvme/host/trace.c b/drivers/nvme/host/trace.c index 0288315f0050..87c437fc070d 100644 --- a/drivers/nvme/host/trace.c +++ b/drivers/nvme/host/trace.c @@ -4,7 +4,7 @@ * Copyright (c) 2018 Johannes Thumshirn, SUSE Linux GmbH */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "trace.h" static const char *nvme_trace_delete_sq(struct trace_seq *p, u8 *cdw10) diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c index 954d4c074770..081f0473cd9e 100644 --- a/drivers/nvme/target/admin-cmd.c +++ b/drivers/nvme/target/admin-cmd.c @@ -9,7 +9,7 @@ #include <linux/part_stat.h> #include <generated/utsrelease.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "nvmet.h" u32 nvmet_get_log_page_len(struct nvme_command *cmd) diff --git a/drivers/nvme/target/auth.c b/drivers/nvme/target/auth.c index 7897d02c681d..29f8639cfe7f 100644 --- a/drivers/nvme/target/auth.c +++ b/drivers/nvme/target/auth.c @@ -15,7 +15,7 @@ #include <linux/ctype.h> #include <linux/random.h> #include <linux/nvme-auth.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "nvmet.h" diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c index 1b6264fa5803..ade285308450 100644 --- a/drivers/nvme/target/rdma.c +++ b/drivers/nvme/target/rdma.c @@ -16,7 +16,7 @@ #include <linux/string.h> #include <linux/wait.h> #include <linux/inet.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <rdma/ib_verbs.h> #include <rdma/rdma_cm.h> diff --git a/drivers/nvme/target/trace.c b/drivers/nvme/target/trace.c index 8d1806a82887..9a3548179a8e 100644 --- a/drivers/nvme/target/trace.c +++ b/drivers/nvme/target/trace.c @@ -4,7 +4,7 @@ * Copyright (c) 2018 Johannes Thumshirn, SUSE Linux GmbH */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "trace.h" static const char *nvmet_trace_admin_identify(struct trace_seq *p, u8 *cdw10) diff --git a/drivers/pci/vpd.c b/drivers/pci/vpd.c index 485a642b9304..e4300f5f304f 100644 --- a/drivers/pci/vpd.c +++ b/drivers/pci/vpd.c @@ -9,7 +9,7 @@ #include <linux/delay.h> #include <linux/export.h> #include <linux/sched/signal.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "pci.h" #define PCI_VPD_LRDT_TAG_SIZE 3 diff --git a/drivers/pcmcia/cistpl.c b/drivers/pcmcia/cistpl.c index 948b763dc451..d018f36f3a89 100644 --- a/drivers/pcmcia/cistpl.c +++ b/drivers/pcmcia/cistpl.c @@ -23,7 +23,7 @@ #include <linux/io.h> #include <linux/security.h> #include <asm/byteorder.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <pcmcia/ss.h> #include <pcmcia/cisreg.h> diff --git a/drivers/peci/controller/peci-aspeed.c b/drivers/peci/controller/peci-aspeed.c index de7046e6b9c4..b93eb6f43b98 100644 --- a/drivers/peci/controller/peci-aspeed.c +++ b/drivers/peci/controller/peci-aspeed.c @@ -2,7 +2,7 @@ // Copyright (c) 2012-2017 ASPEED Technology Inc. // Copyright (c) 2018-2021 Intel Corporation -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/bitfield.h> #include <linux/clk.h> diff --git a/drivers/peci/request.c b/drivers/peci/request.c index 8d6dd7b6b559..87eefe66743f 100644 --- a/drivers/peci/request.c +++ b/drivers/peci/request.c @@ -8,7 +8,7 @@ #include <linux/slab.h> #include <linux/types.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "internal.h" diff --git a/drivers/perf/riscv_pmu_legacy.c b/drivers/perf/riscv_pmu_legacy.c index 04487ad7fba0..93c8e0fdb589 100644 --- a/drivers/perf/riscv_pmu_legacy.c +++ b/drivers/perf/riscv_pmu_legacy.c @@ -22,13 +22,13 @@ static int pmu_legacy_ctr_get_idx(struct perf_event *event) struct perf_event_attr *attr = &event->attr; if (event->attr.type != PERF_TYPE_HARDWARE) - return -EOPNOTSUPP; + return -ENOENT; if (attr->config == PERF_COUNT_HW_CPU_CYCLES) return RISCV_PMU_LEGACY_CYCLE; else if (attr->config == PERF_COUNT_HW_INSTRUCTIONS) return RISCV_PMU_LEGACY_INSTRET; else - return -EOPNOTSUPP; + return -ENOENT; } /* For legacy config & counter index are same */ diff --git a/drivers/perf/riscv_pmu_sbi.c b/drivers/perf/riscv_pmu_sbi.c index 5c39fbd8ed04..391ca1422cae 100644 --- a/drivers/perf/riscv_pmu_sbi.c +++ b/drivers/perf/riscv_pmu_sbi.c @@ -309,7 +309,7 @@ static void pmu_sbi_check_event(struct sbi_pmu_event_data *edata) ret.value, 0x1, SBI_PMU_STOP_FLAG_RESET, 0, 0, 0); } else if (ret.error == SBI_ERR_NOT_SUPPORTED) { /* This event cannot be monitored by any counter */ - edata->event_idx = -EINVAL; + edata->event_idx = -ENOENT; } } @@ -556,7 +556,7 @@ static int pmu_sbi_event_map(struct perf_event *event, u64 *econfig) } break; default: - ret = -EINVAL; + ret = -ENOENT; break; } diff --git a/drivers/platform/arm64/acer-aspire1-ec.c b/drivers/platform/arm64/acer-aspire1-ec.c index dbb1cce13965..2df42406430d 100644 --- a/drivers/platform/arm64/acer-aspire1-ec.c +++ b/drivers/platform/arm64/acer-aspire1-ec.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-only /* Copyright (c) 2024, Nikita Travkin <nikita@trvn.ru> */ -#include <asm-generic/unaligned.h> +#include <linux/unaligned.h> #include <drm/drm_bridge.h> #include <linux/bits.h> #include <linux/delay.h> diff --git a/drivers/platform/chrome/cros_ec_proto.c b/drivers/platform/chrome/cros_ec_proto.c index 73f75958e15c..5c9a53dffcf9 100644 --- a/drivers/platform/chrome/cros_ec_proto.c +++ b/drivers/platform/chrome/cros_ec_proto.c @@ -10,7 +10,7 @@ #include <linux/platform_data/cros_ec_commands.h> #include <linux/platform_data/cros_ec_proto.h> #include <linux/slab.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "cros_ec_trace.h" diff --git a/drivers/platform/chrome/cros_ec_proto_test.c b/drivers/platform/chrome/cros_ec_proto_test.c index 7ca9895a0065..3f281996a686 100644 --- a/drivers/platform/chrome/cros_ec_proto_test.c +++ b/drivers/platform/chrome/cros_ec_proto_test.c @@ -5,7 +5,7 @@ #include <kunit/test.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/platform_data/cros_ec_commands.h> #include <linux/platform_data/cros_ec_proto.h> diff --git a/drivers/platform/chrome/wilco_ec/properties.c b/drivers/platform/chrome/wilco_ec/properties.c index c2bf4c95c5d2..9951c8db04da 100644 --- a/drivers/platform/chrome/wilco_ec/properties.c +++ b/drivers/platform/chrome/wilco_ec/properties.c @@ -8,7 +8,7 @@ #include <linux/platform_data/wilco-ec.h> #include <linux/string.h> #include <linux/types.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /* Operation code; what the EC should do with the property */ enum ec_property_op { diff --git a/drivers/platform/cznic/turris-omnia-mcu-gpio.c b/drivers/platform/cznic/turris-omnia-mcu-gpio.c index 91da56a704c7..88e208d45882 100644 --- a/drivers/platform/cznic/turris-omnia-mcu-gpio.c +++ b/drivers/platform/cznic/turris-omnia-mcu-gpio.c @@ -20,7 +20,7 @@ #include <linux/sysfs.h> #include <linux/types.h> #include <linux/workqueue.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/turris-omnia-mcu-interface.h> #include "turris-omnia-mcu.h" diff --git a/drivers/platform/cznic/turris-omnia-mcu.h b/drivers/platform/cznic/turris-omnia-mcu.h index fed0d357fea3..57ef5d350043 100644 --- a/drivers/platform/cznic/turris-omnia-mcu.h +++ b/drivers/platform/cznic/turris-omnia-mcu.h @@ -18,7 +18,7 @@ #include <linux/watchdog.h> #include <linux/workqueue.h> #include <asm/byteorder.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> struct i2c_client; struct rtc_device; diff --git a/drivers/platform/surface/aggregator/ssh_msgb.h b/drivers/platform/surface/aggregator/ssh_msgb.h index 438873e06098..80aa568a0759 100644 --- a/drivers/platform/surface/aggregator/ssh_msgb.h +++ b/drivers/platform/surface/aggregator/ssh_msgb.h @@ -8,7 +8,7 @@ #ifndef _SURFACE_AGGREGATOR_SSH_MSGB_H #define _SURFACE_AGGREGATOR_SSH_MSGB_H -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/types.h> #include <linux/surface_aggregator/controller.h> diff --git a/drivers/platform/surface/aggregator/ssh_packet_layer.c b/drivers/platform/surface/aggregator/ssh_packet_layer.c index d726b1a86319..6081b0146d5f 100644 --- a/drivers/platform/surface/aggregator/ssh_packet_layer.c +++ b/drivers/platform/surface/aggregator/ssh_packet_layer.c @@ -5,7 +5,7 @@ * Copyright (C) 2019-2022 Maximilian Luz <luzmaximilian@gmail.com> */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/atomic.h> #include <linux/error-injection.h> #include <linux/jiffies.h> diff --git a/drivers/platform/surface/aggregator/ssh_parser.c b/drivers/platform/surface/aggregator/ssh_parser.c index a6f668694365..6cfda85d3b33 100644 --- a/drivers/platform/surface/aggregator/ssh_parser.c +++ b/drivers/platform/surface/aggregator/ssh_parser.c @@ -5,7 +5,7 @@ * Copyright (C) 2019-2022 Maximilian Luz <luzmaximilian@gmail.com> */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/compiler.h> #include <linux/device.h> #include <linux/types.h> diff --git a/drivers/platform/surface/aggregator/ssh_request_layer.c b/drivers/platform/surface/aggregator/ssh_request_layer.c index 90634dcacabf..879ca9ee7ff6 100644 --- a/drivers/platform/surface/aggregator/ssh_request_layer.c +++ b/drivers/platform/surface/aggregator/ssh_request_layer.c @@ -5,7 +5,7 @@ * Copyright (C) 2019-2022 Maximilian Luz <luzmaximilian@gmail.com> */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/atomic.h> #include <linux/completion.h> #include <linux/error-injection.h> diff --git a/drivers/platform/surface/aggregator/trace.h b/drivers/platform/surface/aggregator/trace.h index 55cc61bba1da..caf7d3cb5d8b 100644 --- a/drivers/platform/surface/aggregator/trace.h +++ b/drivers/platform/surface/aggregator/trace.h @@ -13,7 +13,7 @@ #include <linux/surface_aggregator/serial_hub.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/tracepoint.h> TRACE_DEFINE_ENUM(SSH_FRAME_TYPE_DATA_SEQ); diff --git a/drivers/platform/surface/surface3_power.c b/drivers/platform/surface/surface3_power.c index 4c0f92562a79..1ee5239269ae 100644 --- a/drivers/platform/surface/surface3_power.c +++ b/drivers/platform/surface/surface3_power.c @@ -40,7 +40,7 @@ #include <linux/slab.h> #include <linux/types.h> #include <linux/uuid.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define SURFACE_3_POLL_INTERVAL (2 * HZ) #define SURFACE_3_STRLEN 10 diff --git a/drivers/platform/surface/surface_acpi_notify.c b/drivers/platform/surface/surface_acpi_notify.c index 20f3870915d2..14a9d8a267cb 100644 --- a/drivers/platform/surface/surface_acpi_notify.c +++ b/drivers/platform/surface/surface_acpi_notify.c @@ -11,7 +11,7 @@ * Copyright (C) 2019-2022 Maximilian Luz <luzmaximilian@gmail.com> */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/acpi.h> #include <linux/delay.h> #include <linux/jiffies.h> diff --git a/drivers/platform/surface/surface_aggregator_tabletsw.c b/drivers/platform/surface/surface_aggregator_tabletsw.c index c0a1a5869246..ffa36ed92897 100644 --- a/drivers/platform/surface/surface_aggregator_tabletsw.c +++ b/drivers/platform/surface/surface_aggregator_tabletsw.c @@ -5,7 +5,7 @@ * Copyright (C) 2022 Maximilian Luz <luzmaximilian@gmail.com> */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/input.h> #include <linux/kernel.h> #include <linux/module.h> diff --git a/drivers/platform/surface/surface_platform_profile.c b/drivers/platform/surface/surface_platform_profile.c index 3de864bc6610..08db878f1d7d 100644 --- a/drivers/platform/surface/surface_platform_profile.c +++ b/drivers/platform/surface/surface_platform_profile.c @@ -6,7 +6,7 @@ * Copyright (C) 2021-2022 Maximilian Luz <luzmaximilian@gmail.com> */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/platform_profile.h> diff --git a/drivers/platform/x86/asus-tf103c-dock.c b/drivers/platform/x86/asus-tf103c-dock.c index b441d8ca72d3..ca4670d0dc67 100644 --- a/drivers/platform/x86/asus-tf103c-dock.c +++ b/drivers/platform/x86/asus-tf103c-dock.c @@ -26,7 +26,7 @@ #include <linux/module.h> #include <linux/pm.h> #include <linux/workqueue.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> static bool fnlock; module_param(fnlock, bool, 0644); diff --git a/drivers/platform/x86/dell/dell-laptop.c b/drivers/platform/x86/dell/dell-laptop.c index a3cd0505f282..5671bd0deee7 100644 --- a/drivers/platform/x86/dell/dell-laptop.c +++ b/drivers/platform/x86/dell/dell-laptop.c @@ -2391,12 +2391,18 @@ static struct attribute *dell_battery_attrs[] = { }; ATTRIBUTE_GROUPS(dell_battery); +static bool dell_battery_supported(struct power_supply *battery) +{ + /* We currently only support the primary battery */ + return strcmp(battery->desc->name, "BAT0") == 0; +} + static int dell_battery_add(struct power_supply *battery, struct acpi_battery_hook *hook) { - /* this currently only supports the primary battery */ - if (strcmp(battery->desc->name, "BAT0") != 0) - return -ENODEV; + /* Return 0 instead of an error to avoid being unloaded */ + if (!dell_battery_supported(battery)) + return 0; return device_add_groups(&battery->dev, dell_battery_groups); } @@ -2404,6 +2410,9 @@ static int dell_battery_add(struct power_supply *battery, static int dell_battery_remove(struct power_supply *battery, struct acpi_battery_hook *hook) { + if (!dell_battery_supported(battery)) + return 0; + device_remove_groups(&battery->dev, dell_battery_groups); return 0; } diff --git a/drivers/platform/x86/dell/dell-wmi-ddv.c b/drivers/platform/x86/dell/dell-wmi-ddv.c index 0b2299f7a2de..e75cd6e1efe6 100644 --- a/drivers/platform/x86/dell/dell-wmi-ddv.c +++ b/drivers/platform/x86/dell/dell-wmi-ddv.c @@ -31,7 +31,7 @@ #include <acpi/battery.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define DRIVER_NAME "dell-wmi-ddv" diff --git a/drivers/platform/x86/dell/dell-wmi-sysman/sysman.c b/drivers/platform/x86/dell/dell-wmi-sysman/sysman.c index 9def7983d7d6..40ddc6eb7562 100644 --- a/drivers/platform/x86/dell/dell-wmi-sysman/sysman.c +++ b/drivers/platform/x86/dell/dell-wmi-sysman/sysman.c @@ -521,6 +521,7 @@ static int __init sysman_init(void) int ret = 0; if (!dmi_find_device(DMI_DEV_TYPE_OEM_STRING, "Dell System", NULL) && + !dmi_find_device(DMI_DEV_TYPE_OEM_STRING, "Alienware", NULL) && !dmi_find_device(DMI_DEV_TYPE_OEM_STRING, "www.dell.com", NULL)) { pr_err("Unable to run on non-Dell system\n"); return -ENODEV; diff --git a/drivers/platform/x86/intel/pmc/spt.c b/drivers/platform/x86/intel/pmc/spt.c index 2cd2b3c68e46..ab993a69e33e 100644 --- a/drivers/platform/x86/intel/pmc/spt.c +++ b/drivers/platform/x86/intel/pmc/spt.c @@ -130,8 +130,6 @@ const struct pmc_reg_map spt_reg_map = { .ppfear_buckets = SPT_PPFEAR_NUM_ENTRIES, .pm_cfg_offset = SPT_PMC_PM_CFG_OFFSET, .pm_read_disable_bit = SPT_PMC_READ_DISABLE_BIT, - .acpi_pm_tmr_ctl_offset = SPT_PMC_ACPI_PM_TMR_CTL_OFFSET, - .acpi_pm_tmr_disable_bit = SPT_PMC_BIT_ACPI_PM_TMR_DISABLE, .ltr_ignore_max = SPT_NUM_IP_IGN_ALLOWED, .pm_vric1_offset = SPT_PMC_VRIC1_OFFSET, }; diff --git a/drivers/platform/x86/intel/speed_select_if/isst_if_common.c b/drivers/platform/x86/intel/speed_select_if/isst_if_common.c index 9ad35fefea47..1e46e30dae96 100644 --- a/drivers/platform/x86/intel/speed_select_if/isst_if_common.c +++ b/drivers/platform/x86/intel/speed_select_if/isst_if_common.c @@ -316,7 +316,9 @@ static struct pci_dev *_isst_if_get_pci_dev(int cpu, int bus_no, int dev, int fn cpu >= nr_cpu_ids || cpu >= num_possible_cpus()) return NULL; - pkg_id = topology_physical_package_id(cpu); + pkg_id = topology_logical_package_id(cpu); + if (pkg_id >= topology_max_packages()) + return NULL; bus_number = isst_cpu_info[cpu].bus_info[bus_no]; if (bus_number < 0) @@ -807,6 +809,7 @@ static const struct x86_cpu_id isst_cpu_ids[] = { X86_MATCH_VFM(INTEL_GRANITERAPIDS_X, SST_HPM_SUPPORTED), X86_MATCH_VFM(INTEL_ICELAKE_D, 0), X86_MATCH_VFM(INTEL_ICELAKE_X, 0), + X86_MATCH_VFM(INTEL_PANTHERCOVE_X, SST_HPM_SUPPORTED), X86_MATCH_VFM(INTEL_SAPPHIRERAPIDS_X, 0), X86_MATCH_VFM(INTEL_SKYLAKE_X, SST_MBOX_SUPPORTED), {} diff --git a/drivers/platform/x86/intel/tpmi_power_domains.c b/drivers/platform/x86/intel/tpmi_power_domains.c index 4eb02553957c..0609a8320f7e 100644 --- a/drivers/platform/x86/intel/tpmi_power_domains.c +++ b/drivers/platform/x86/intel/tpmi_power_domains.c @@ -82,6 +82,7 @@ static const struct x86_cpu_id tpmi_cpu_ids[] = { X86_MATCH_VFM(INTEL_ATOM_CRESTMONT_X, NULL), X86_MATCH_VFM(INTEL_ATOM_CRESTMONT, NULL), X86_MATCH_VFM(INTEL_GRANITERAPIDS_D, NULL), + X86_MATCH_VFM(INTEL_PANTHERCOVE_X, NULL), {} }; MODULE_DEVICE_TABLE(x86cpu, tpmi_cpu_ids); diff --git a/drivers/platform/x86/msi-wmi-platform.c b/drivers/platform/x86/msi-wmi-platform.c index 436fb91a47db..9b5c7f8c79b0 100644 --- a/drivers/platform/x86/msi-wmi-platform.c +++ b/drivers/platform/x86/msi-wmi-platform.c @@ -22,7 +22,7 @@ #include <linux/types.h> #include <linux/wmi.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define DRIVER_NAME "msi-wmi-platform" diff --git a/drivers/platform/x86/quickstart.c b/drivers/platform/x86/quickstart.c index df496c7e7171..8d540a1c8602 100644 --- a/drivers/platform/x86/quickstart.c +++ b/drivers/platform/x86/quickstart.c @@ -26,7 +26,7 @@ #include <linux/sysfs.h> #include <linux/types.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define DRIVER_NAME "quickstart" diff --git a/drivers/platform/x86/x86-android-tablets/core.c b/drivers/platform/x86/x86-android-tablets/core.c index 1427a9a39008..ef572b90e06b 100644 --- a/drivers/platform/x86/x86-android-tablets/core.c +++ b/drivers/platform/x86/x86-android-tablets/core.c @@ -390,8 +390,9 @@ static __init int x86_android_tablet_probe(struct platform_device *pdev) for (i = 0; i < pdev_count; i++) { pdevs[i] = platform_device_register_full(&dev_info->pdev_info[i]); if (IS_ERR(pdevs[i])) { + ret = PTR_ERR(pdevs[i]); x86_android_tablet_remove(pdev); - return PTR_ERR(pdevs[i]); + return ret; } } @@ -443,8 +444,9 @@ static __init int x86_android_tablet_probe(struct platform_device *pdev) PLATFORM_DEVID_AUTO, &pdata, sizeof(pdata)); if (IS_ERR(pdevs[pdev_count])) { + ret = PTR_ERR(pdevs[pdev_count]); x86_android_tablet_remove(pdev); - return PTR_ERR(pdevs[pdev_count]); + return ret; } pdev_count++; } diff --git a/drivers/power/supply/axp288_fuel_gauge.c b/drivers/power/supply/axp288_fuel_gauge.c index 95d9a35243c2..a3d71fc72064 100644 --- a/drivers/power/supply/axp288_fuel_gauge.c +++ b/drivers/power/supply/axp288_fuel_gauge.c @@ -21,7 +21,7 @@ #include <linux/platform_device.h> #include <linux/power_supply.h> #include <linux/iio/consumer.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <asm/iosf_mbi.h> #define PS_STAT_VBUS_TRIGGER (1 << 0) diff --git a/drivers/power/supply/bq27xxx_battery_i2c.c b/drivers/power/supply/bq27xxx_battery_i2c.c index c1737f964840..ba0d22d90429 100644 --- a/drivers/power/supply/bq27xxx_battery_i2c.c +++ b/drivers/power/supply/bq27xxx_battery_i2c.c @@ -9,7 +9,7 @@ #include <linux/i2c.h> #include <linux/interrupt.h> #include <linux/module.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/power/bq27xxx_battery.h> diff --git a/drivers/power/supply/cros_peripheral_charger.c b/drivers/power/supply/cros_peripheral_charger.c index d406f2a78449..962a6fd29832 100644 --- a/drivers/power/supply/cros_peripheral_charger.c +++ b/drivers/power/supply/cros_peripheral_charger.c @@ -15,7 +15,7 @@ #include <linux/slab.h> #include <linux/stringify.h> #include <linux/types.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define DRV_NAME "cros-ec-pchg" #define PCHG_DIR_PREFIX "peripheral" diff --git a/drivers/power/supply/max1720x_battery.c b/drivers/power/supply/max1720x_battery.c index 2bc3dce963a3..33105419e242 100644 --- a/drivers/power/supply/max1720x_battery.c +++ b/drivers/power/supply/max1720x_battery.c @@ -14,7 +14,7 @@ #include <linux/power_supply.h> #include <linux/regmap.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /* Nonvolatile registers */ #define MAX1720X_NXTABLE0 0x80 diff --git a/drivers/power/supply/rk817_charger.c b/drivers/power/supply/rk817_charger.c index a3d377a32b49..57b6ddefad28 100644 --- a/drivers/power/supply/rk817_charger.c +++ b/drivers/power/supply/rk817_charger.c @@ -8,7 +8,7 @@ * Chris Morgan <macromorgan@hotmail.com> */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/devm-helpers.h> #include <linux/mfd/rk808.h> #include <linux/irq.h> diff --git a/drivers/power/supply/surface_battery.c b/drivers/power/supply/surface_battery.c index 196d290dc596..ebd1edde28f1 100644 --- a/drivers/power/supply/surface_battery.c +++ b/drivers/power/supply/surface_battery.c @@ -6,7 +6,7 @@ * Copyright (C) 2019-2021 Maximilian Luz <luzmaximilian@gmail.com> */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/jiffies.h> #include <linux/kernel.h> #include <linux/module.h> diff --git a/drivers/power/supply/surface_charger.c b/drivers/power/supply/surface_charger.c index 7a6c62d6f883..90b823848c99 100644 --- a/drivers/power/supply/surface_charger.c +++ b/drivers/power/supply/surface_charger.c @@ -6,7 +6,7 @@ * Copyright (C) 2019-2021 Maximilian Luz <luzmaximilian@gmail.com> */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/mutex.h> diff --git a/drivers/ptp/ptp_clockmatrix.c b/drivers/ptp/ptp_clockmatrix.c index 209a45a76e6b..b6f1941308b1 100644 --- a/drivers/ptp/ptp_clockmatrix.c +++ b/drivers/ptp/ptp_clockmatrix.c @@ -17,7 +17,7 @@ #include <linux/of.h> #include <linux/mfd/rsmu.h> #include <linux/mfd/idt8a340_reg.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "ptp_private.h" #include "ptp_clockmatrix.h" diff --git a/drivers/ptp/ptp_fc3.c b/drivers/ptp/ptp_fc3.c index 6ef982862e27..e14e149b746e 100644 --- a/drivers/ptp/ptp_fc3.c +++ b/drivers/ptp/ptp_fc3.c @@ -18,7 +18,7 @@ #include <linux/bitfield.h> #include <linux/mfd/rsmu.h> #include <linux/mfd/idtRC38xxx_reg.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "ptp_private.h" #include "ptp_fc3.h" diff --git a/drivers/remoteproc/Kconfig b/drivers/remoteproc/Kconfig index 7a80c92b785e..955e4e38477e 100644 --- a/drivers/remoteproc/Kconfig +++ b/drivers/remoteproc/Kconfig @@ -330,8 +330,7 @@ config STM32_RPROC config TI_K3_DSP_REMOTEPROC tristate "TI K3 DSP remoteproc support" depends on ARCH_K3 - select MAILBOX - select OMAP2PLUS_MBOX + depends on OMAP2PLUS_MBOX help Say m here to support TI's C66x and C71x DSP remote processor subsystems on various TI K3 family of SoCs through the remote @@ -356,8 +355,7 @@ config TI_K3_M4_REMOTEPROC config TI_K3_R5_REMOTEPROC tristate "TI K3 R5 remoteproc support" depends on ARCH_K3 - select MAILBOX - select OMAP2PLUS_MBOX + depends on OMAP2PLUS_MBOX help Say m here to support TI's R5F remote processor subsystems on various TI K3 family of SoCs through the remote processor diff --git a/drivers/rtc/rtc-max31335.c b/drivers/rtc/rtc-max31335.c index 9a456f537d3b..3fbcf5f6b92f 100644 --- a/drivers/rtc/rtc-max31335.c +++ b/drivers/rtc/rtc-max31335.c @@ -8,7 +8,7 @@ * */ -#include <asm-generic/unaligned.h> +#include <linux/unaligned.h> #include <linux/bcd.h> #include <linux/bitfield.h> #include <linux/bitops.h> diff --git a/drivers/rtc/rtc-pm8xxx.c b/drivers/rtc/rtc-pm8xxx.c index f6b779c12ca7..c32fba550c8e 100644 --- a/drivers/rtc/rtc-pm8xxx.c +++ b/drivers/rtc/rtc-pm8xxx.c @@ -17,7 +17,7 @@ #include <linux/slab.h> #include <linux/spinlock.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /* RTC_CTRL register bit fields */ #define PM8xxx_RTC_ENABLE BIT(7) diff --git a/drivers/s390/crypto/vfio_ap_drv.c b/drivers/s390/crypto/vfio_ap_drv.c index 4aeb3e1213c7..67a807e2e75b 100644 --- a/drivers/s390/crypto/vfio_ap_drv.c +++ b/drivers/s390/crypto/vfio_ap_drv.c @@ -26,6 +26,18 @@ MODULE_LICENSE("GPL v2"); struct ap_matrix_dev *matrix_dev; debug_info_t *vfio_ap_dbf_info; +static ssize_t features_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + return sysfs_emit(buf, "guest_matrix hotplug ap_config\n"); +} +static DEVICE_ATTR_RO(features); + +static struct attribute *matrix_dev_attrs[] = { + &dev_attr_features.attr, + NULL, +}; +ATTRIBUTE_GROUPS(matrix_dev); + /* Only type 10 adapters (CEX4 and later) are supported * by the AP matrix device driver */ @@ -68,6 +80,7 @@ static struct device_driver matrix_driver = { .name = "vfio_ap", .bus = &matrix_bus, .suppress_bind_attrs = true, + .dev_groups = matrix_dev_groups, }; static int vfio_ap_matrix_dev_create(void) diff --git a/drivers/scsi/aacraid/aachba.c b/drivers/scsi/aacraid/aachba.c index ec3834bda111..abf6a82b74af 100644 --- a/drivers/scsi/aacraid/aachba.c +++ b/drivers/scsi/aacraid/aachba.c @@ -27,7 +27,7 @@ #include <linux/uaccess.h> #include <linux/module.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <scsi/scsi.h> #include <scsi/scsi_cmnd.h> diff --git a/drivers/scsi/csiostor/csio_lnode.c b/drivers/scsi/csiostor/csio_lnode.c index 5b3ffefae476..6cc1d53165a0 100644 --- a/drivers/scsi/csiostor/csio_lnode.c +++ b/drivers/scsi/csiostor/csio_lnode.c @@ -38,7 +38,7 @@ #include <linux/utsname.h> #include <scsi/scsi_device.h> #include <scsi/scsi_transport_fc.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <scsi/fc/fc_els.h> #include <scsi/fc/fc_fs.h> #include <scsi/fc/fc_gs.h> diff --git a/drivers/scsi/csiostor/csio_scsi.c b/drivers/scsi/csiostor/csio_scsi.c index 05e1a63e00c3..8329f0cab4e7 100644 --- a/drivers/scsi/csiostor/csio_scsi.c +++ b/drivers/scsi/csiostor/csio_scsi.c @@ -41,7 +41,7 @@ #include <linux/compiler.h> #include <linux/export.h> #include <linux/module.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <asm/page.h> #include <scsi/scsi.h> #include <scsi/scsi_device.h> diff --git a/drivers/scsi/cxgbi/libcxgbi.h b/drivers/scsi/cxgbi/libcxgbi.h index d92cf1dccc2f..0909b03e2497 100644 --- a/drivers/scsi/cxgbi/libcxgbi.h +++ b/drivers/scsi/cxgbi/libcxgbi.h @@ -485,7 +485,6 @@ struct cxgbi_device { unsigned char nmtus; unsigned char nports; struct pci_dev *pdev; - struct dentry *debugfs_root; struct iscsi_transport *itp; struct module *owner; @@ -499,7 +498,6 @@ struct cxgbi_device { unsigned int rxq_idx_cntr; struct cxgbi_ports_map pmap; - void (*dev_ddp_cleanup)(struct cxgbi_device *); struct cxgbi_ppm* (*cdev2ppm)(struct cxgbi_device *); int (*csk_ddp_set_map)(struct cxgbi_ppm *, struct cxgbi_sock *, struct cxgbi_task_tag_info *); @@ -512,7 +510,6 @@ struct cxgbi_device { unsigned int, int); void (*csk_release_offload_resources)(struct cxgbi_sock *); - int (*csk_rx_pdu_ready)(struct cxgbi_sock *, struct sk_buff *); u32 (*csk_send_rx_credits)(struct cxgbi_sock *, u32); int (*csk_push_tx_frames)(struct cxgbi_sock *, int); void (*csk_send_abort_req)(struct cxgbi_sock *); diff --git a/drivers/scsi/cxlflash/lunmgt.c b/drivers/scsi/cxlflash/lunmgt.c index 52405c6462f8..962c797fda07 100644 --- a/drivers/scsi/cxlflash/lunmgt.c +++ b/drivers/scsi/cxlflash/lunmgt.c @@ -8,7 +8,7 @@ * Copyright (C) 2015 IBM Corporation */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/interrupt.h> #include <linux/pci.h> diff --git a/drivers/scsi/cxlflash/main.c b/drivers/scsi/cxlflash/main.c index e4b45b7e3277..60d62b93d624 100644 --- a/drivers/scsi/cxlflash/main.c +++ b/drivers/scsi/cxlflash/main.c @@ -13,7 +13,7 @@ #include <linux/module.h> #include <linux/pci.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <scsi/scsi_cmnd.h> #include <scsi/scsi_host.h> diff --git a/drivers/scsi/cxlflash/superpipe.c b/drivers/scsi/cxlflash/superpipe.c index 2d356fe2457a..b375509d1470 100644 --- a/drivers/scsi/cxlflash/superpipe.c +++ b/drivers/scsi/cxlflash/superpipe.c @@ -13,7 +13,7 @@ #include <linux/interrupt.h> #include <linux/pci.h> #include <linux/syscalls.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <scsi/scsi.h> #include <scsi/scsi_host.h> diff --git a/drivers/scsi/cxlflash/vlun.c b/drivers/scsi/cxlflash/vlun.c index 35326e311991..32e807703377 100644 --- a/drivers/scsi/cxlflash/vlun.c +++ b/drivers/scsi/cxlflash/vlun.c @@ -11,7 +11,7 @@ #include <linux/interrupt.h> #include <linux/pci.h> #include <linux/syscalls.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <asm/bitsperlong.h> #include <scsi/scsi_cmnd.h> diff --git a/drivers/scsi/device_handler/scsi_dh_alua.c b/drivers/scsi/device_handler/scsi_dh_alua.c index 4eb0837298d4..1bf5948d1188 100644 --- a/drivers/scsi/device_handler/scsi_dh_alua.c +++ b/drivers/scsi/device_handler/scsi_dh_alua.c @@ -8,7 +8,7 @@ #include <linux/slab.h> #include <linux/delay.h> #include <linux/module.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <scsi/scsi.h> #include <scsi/scsi_proto.h> #include <scsi/scsi_dbg.h> diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c index feda9b54b443..4cd3a3eab6f1 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c +++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c @@ -2421,7 +2421,7 @@ out: spin_lock_irqsave(&device->done_lock, flags); if (test_bit(SAS_HA_FROZEN, &ha->state)) { spin_unlock_irqrestore(&device->done_lock, flags); - dev_info(dev, "slot complete: task(%pK) ignored\n ", + dev_info(dev, "slot complete: task(%pK) ignored\n", task); return; } diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c index e044ed09d7e0..0c49414c1f35 100644 --- a/drivers/scsi/hpsa.c +++ b/drivers/scsi/hpsa.c @@ -51,7 +51,7 @@ #include <linux/jiffies.h> #include <linux/percpu-defs.h> #include <linux/percpu.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <asm/div64.h> #include "hpsa_cmd.h" #include "hpsa.h" diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c index a3d1013c8307..e66c3ef74267 100644 --- a/drivers/scsi/ibmvscsi/ibmvfc.c +++ b/drivers/scsi/ibmvscsi/ibmvfc.c @@ -37,6 +37,7 @@ static unsigned int default_timeout = IBMVFC_DEFAULT_TIMEOUT; static u64 max_lun = IBMVFC_MAX_LUN; static unsigned int max_targets = IBMVFC_MAX_TARGETS; static unsigned int max_requests = IBMVFC_MAX_REQUESTS_DEFAULT; +static u16 max_sectors = IBMVFC_MAX_SECTORS; static u16 scsi_qdepth = IBMVFC_SCSI_QDEPTH; static unsigned int disc_threads = IBMVFC_MAX_DISC_THREADS; static unsigned int ibmvfc_debug = IBMVFC_DEBUG; @@ -83,6 +84,9 @@ MODULE_PARM_DESC(default_timeout, module_param_named(max_requests, max_requests, uint, S_IRUGO); MODULE_PARM_DESC(max_requests, "Maximum requests for this adapter. " "[Default=" __stringify(IBMVFC_MAX_REQUESTS_DEFAULT) "]"); +module_param_named(max_sectors, max_sectors, ushort, S_IRUGO); +MODULE_PARM_DESC(max_sectors, "Maximum sectors for this adapter. " + "[Default=" __stringify(IBMVFC_MAX_SECTORS) "]"); module_param_named(scsi_qdepth, scsi_qdepth, ushort, S_IRUGO); MODULE_PARM_DESC(scsi_qdepth, "Maximum scsi command depth per adapter queue. " "[Default=" __stringify(IBMVFC_SCSI_QDEPTH) "]"); @@ -1494,7 +1498,7 @@ static void ibmvfc_set_login_info(struct ibmvfc_host *vhost) memset(login_info, 0, sizeof(*login_info)); login_info->ostype = cpu_to_be32(IBMVFC_OS_LINUX); - login_info->max_dma_len = cpu_to_be64(IBMVFC_MAX_SECTORS << 9); + login_info->max_dma_len = cpu_to_be64(max_sectors << 9); login_info->max_payload = cpu_to_be32(sizeof(struct ibmvfc_fcp_cmd_iu)); login_info->max_response = cpu_to_be32(sizeof(struct ibmvfc_fcp_rsp)); login_info->partition_num = cpu_to_be32(vhost->partition_number); @@ -5230,7 +5234,7 @@ static void ibmvfc_npiv_login_done(struct ibmvfc_event *evt) } vhost->logged_in = 1; - npiv_max_sectors = min((uint)(be64_to_cpu(rsp->max_dma_len) >> 9), IBMVFC_MAX_SECTORS); + npiv_max_sectors = min((uint)(be64_to_cpu(rsp->max_dma_len) >> 9), max_sectors); dev_info(vhost->dev, "Host partition: %s, device: %s %s %s max sectors %u\n", rsp->partition_name, rsp->device_name, rsp->port_loc_code, rsp->drc_name, npiv_max_sectors); @@ -6329,7 +6333,7 @@ static int ibmvfc_probe(struct vio_dev *vdev, const struct vio_device_id *id) shost->can_queue = scsi_qdepth; shost->max_lun = max_lun; shost->max_id = max_targets; - shost->max_sectors = IBMVFC_MAX_SECTORS; + shost->max_sectors = max_sectors; shost->max_cmd_len = IBMVFC_MAX_CDB_LEN; shost->unique_id = shost->host_no; shost->nr_hw_queues = mq_enabled ? min(max_scsi_queues, nr_scsi_hw_queues) : 1; @@ -6556,6 +6560,7 @@ static struct fc_function_template ibmvfc_transport_functions = { **/ static int __init ibmvfc_module_init(void) { + int min_max_sectors = PAGE_SIZE >> 9; int rc; if (!firmware_has_feature(FW_FEATURE_VIO)) @@ -6564,6 +6569,16 @@ static int __init ibmvfc_module_init(void) printk(KERN_INFO IBMVFC_NAME": IBM Virtual Fibre Channel Driver version: %s %s\n", IBMVFC_DRIVER_VERSION, IBMVFC_DRIVER_DATE); + /* + * Range check the max_sectors module parameter. The upper bounds is + * implicity checked since the parameter is a ushort. + */ + if (max_sectors < min_max_sectors) { + printk(KERN_ERR IBMVFC_NAME ": max_sectors must be at least %d.\n", + min_max_sectors); + max_sectors = min_max_sectors; + } + ibmvfc_transport_template = fc_attach_transport(&ibmvfc_transport_functions); if (!ibmvfc_transport_template) return -ENOMEM; diff --git a/drivers/scsi/ibmvscsi/ibmvfc.h b/drivers/scsi/ibmvscsi/ibmvfc.h index 745ad5ac7251..c73ed2314ad0 100644 --- a/drivers/scsi/ibmvscsi/ibmvfc.h +++ b/drivers/scsi/ibmvscsi/ibmvfc.h @@ -32,7 +32,7 @@ #define IBMVFC_DEBUG 0 #define IBMVFC_MAX_TARGETS 1024 #define IBMVFC_MAX_LUN 0xffffffff -#define IBMVFC_MAX_SECTORS 0xffffu +#define IBMVFC_MAX_SECTORS 2048 #define IBMVFC_MAX_DISC_THREADS 4 #define IBMVFC_TGT_MEMPOOL_SZ 64 #define IBMVFC_MAX_CMDS_PER_LUN 64 diff --git a/drivers/scsi/ipr.h b/drivers/scsi/ipr.h index b2b643c6dbbe..fde7145835de 100644 --- a/drivers/scsi/ipr.h +++ b/drivers/scsi/ipr.h @@ -13,7 +13,7 @@ #ifndef _IPR_H #define _IPR_H -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/types.h> #include <linux/completion.h> #include <linux/list.h> diff --git a/drivers/scsi/libfc/fc_disc.c b/drivers/scsi/libfc/fc_disc.c index 384f48ff64d7..60d621ad0024 100644 --- a/drivers/scsi/libfc/fc_disc.c +++ b/drivers/scsi/libfc/fc_disc.c @@ -26,7 +26,7 @@ #include <linux/export.h> #include <linux/list.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <scsi/fc/fc_gs.h> diff --git a/drivers/scsi/libfc/fc_elsct.c b/drivers/scsi/libfc/fc_elsct.c index 8d3006edbe12..4fa18a317f77 100644 --- a/drivers/scsi/libfc/fc_elsct.c +++ b/drivers/scsi/libfc/fc_elsct.c @@ -10,7 +10,7 @@ */ #include <linux/export.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <scsi/fc/fc_gs.h> #include <scsi/fc/fc_ns.h> #include <scsi/fc/fc_els.h> diff --git a/drivers/scsi/libfc/fc_encode.h b/drivers/scsi/libfc/fc_encode.h index 6b7e4ca6b7b5..02e31db31d68 100644 --- a/drivers/scsi/libfc/fc_encode.h +++ b/drivers/scsi/libfc/fc_encode.h @@ -7,7 +7,7 @@ #ifndef _FC_ENCODE_H_ #define _FC_ENCODE_H_ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/utsname.h> #include <scsi/fc/fc_ms.h> diff --git a/drivers/scsi/libfc/fc_lport.c b/drivers/scsi/libfc/fc_lport.c index ab06e9aeb613..310fa5add5f0 100644 --- a/drivers/scsi/libfc/fc_lport.c +++ b/drivers/scsi/libfc/fc_lport.c @@ -79,7 +79,7 @@ #include <linux/delay.h> #include <linux/module.h> #include <linux/slab.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <scsi/fc/fc_gs.h> diff --git a/drivers/scsi/libfc/fc_rport.c b/drivers/scsi/libfc/fc_rport.c index 308cb4872f96..c25979d96808 100644 --- a/drivers/scsi/libfc/fc_rport.c +++ b/drivers/scsi/libfc/fc_rport.c @@ -55,7 +55,7 @@ #include <linux/export.h> #include <linux/rculist.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <scsi/libfc.h> diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c index 0fda8905eabd..2b1bf990a9dc 100644 --- a/drivers/scsi/libiscsi.c +++ b/drivers/scsi/libiscsi.c @@ -15,7 +15,7 @@ #include <linux/slab.h> #include <linux/sched/signal.h> #include <linux/module.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <net/tcp.h> #include <scsi/scsi_cmnd.h> #include <scsi/scsi_device.h> diff --git a/drivers/scsi/libsas/sas_expander.c b/drivers/scsi/libsas/sas_expander.c index 4e6bb3d0f163..2b8004eb6f1b 100644 --- a/drivers/scsi/libsas/sas_expander.c +++ b/drivers/scsi/libsas/sas_expander.c @@ -11,7 +11,7 @@ #include <linux/scatterlist.h> #include <linux/blkdev.h> #include <linux/slab.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "sas_internal.h" diff --git a/drivers/scsi/lpfc/lpfc_bsg.c b/drivers/scsi/lpfc/lpfc_bsg.c index 4756a3f82531..85059b83ea6b 100644 --- a/drivers/scsi/lpfc/lpfc_bsg.c +++ b/drivers/scsi/lpfc/lpfc_bsg.c @@ -3208,6 +3208,9 @@ lpfc_bsg_diag_loopback_run(struct bsg_job *job) cmdiocbq->num_bdes = num_bde; cmdiocbq->cmd_flag |= LPFC_IO_LIBDFC; cmdiocbq->cmd_flag |= LPFC_IO_LOOPBACK; + if (phba->cfg_vmid_app_header) + cmdiocbq->cmd_flag |= LPFC_IO_VMID; + cmdiocbq->vport = phba->pport; cmdiocbq->cmd_cmpl = NULL; cmdiocbq->bpl_dmabuf = txbmp; diff --git a/drivers/scsi/lpfc/lpfc_ct.c b/drivers/scsi/lpfc/lpfc_ct.c index 2dedd1493e5b..134bc96dd134 100644 --- a/drivers/scsi/lpfc/lpfc_ct.c +++ b/drivers/scsi/lpfc/lpfc_ct.c @@ -1572,8 +1572,8 @@ lpfc_cmpl_ct_cmd_gft_id(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, } } } else - lpfc_printf_vlog(vport, KERN_ERR, LOG_TRACE_EVENT, - "3065 GFT_ID failed x%08x\n", ulp_status); + lpfc_vlog_msg(vport, KERN_WARNING, LOG_DISCOVERY, + "3065 GFT_ID status x%08x\n", ulp_status); out: lpfc_ct_free_iocb(phba, cmdiocb); @@ -1647,6 +1647,18 @@ lpfc_cmpl_ct(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, } out: + /* If the caller wanted a synchronous DA_ID completion, signal the + * wait obj and clear flag to reset the vport. + */ + if (ndlp->save_flags & NLP_WAIT_FOR_DA_ID) { + if (ndlp->da_id_waitq) + wake_up(ndlp->da_id_waitq); + } + + spin_lock_irq(&ndlp->lock); + ndlp->save_flags &= ~NLP_WAIT_FOR_DA_ID; + spin_unlock_irq(&ndlp->lock); + lpfc_ct_free_iocb(phba, cmdiocb); lpfc_nlp_put(ndlp); return; @@ -2246,7 +2258,7 @@ lpfc_cmpl_ct_disc_fdmi(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, } lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY, - "0229 FDMI cmd %04x failed, latt = %d " + "0229 FDMI cmd %04x latt = %d " "ulp_status: x%x, rid x%x\n", be16_to_cpu(fdmi_cmd), latt, ulp_status, ulp_word4); @@ -2263,9 +2275,9 @@ lpfc_cmpl_ct_disc_fdmi(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, /* Check for a CT LS_RJT response */ cmd = be16_to_cpu(fdmi_cmd); if (be16_to_cpu(fdmi_rsp) == SLI_CT_RESPONSE_FS_RJT) { - /* FDMI rsp failed */ + /* Log FDMI reject */ lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY | LOG_ELS, - "0220 FDMI cmd failed FS_RJT Data: x%x", cmd); + "0220 FDMI cmd FS_RJT Data: x%x", cmd); /* Should we fallback to FDMI-2 / FDMI-1 ? */ switch (cmd) { diff --git a/drivers/scsi/lpfc/lpfc_disc.h b/drivers/scsi/lpfc/lpfc_disc.h index f82615d87c4b..f5ae8cc15820 100644 --- a/drivers/scsi/lpfc/lpfc_disc.h +++ b/drivers/scsi/lpfc/lpfc_disc.h @@ -90,6 +90,8 @@ enum lpfc_nlp_save_flags { NLP_IN_RECOV_POST_DEV_LOSS = 0x1, /* wait for outstanding LOGO to cmpl */ NLP_WAIT_FOR_LOGO = 0x2, + /* wait for outstanding DA_ID to finish */ + NLP_WAIT_FOR_DA_ID = 0x4 }; struct lpfc_nodelist { @@ -159,7 +161,12 @@ struct lpfc_nodelist { uint32_t nvme_fb_size; /* NVME target's supported byte cnt */ #define NVME_FB_BIT_SHIFT 9 /* PRLI Rsp first burst in 512B units. */ uint32_t nlp_defer_did; + + /* These wait objects are NPIV specific. These IOs must complete + * synchronously. + */ wait_queue_head_t *logo_waitq; + wait_queue_head_t *da_id_waitq; }; struct lpfc_node_rrq { diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c index de0ec945d2f1..d737b897ddd8 100644 --- a/drivers/scsi/lpfc/lpfc_els.c +++ b/drivers/scsi/lpfc/lpfc_els.c @@ -979,7 +979,7 @@ lpfc_cmpl_els_flogi(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, phba->fcoe_cvl_eventtag_attn = phba->fcoe_cvl_eventtag; lpfc_printf_log(phba, KERN_WARNING, LOG_FIP | LOG_ELS, - "2611 FLOGI failed on FCF (x%x), " + "2611 FLOGI FCF (x%x), " "status:x%x/x%x, tmo:x%x, perform " "roundrobin FCF failover\n", phba->fcf.current_rec.fcf_indx, @@ -997,11 +997,11 @@ stop_rr_fcf_flogi: if (!(ulp_status == IOSTAT_LOCAL_REJECT && ((ulp_word4 & IOERR_PARAM_MASK) == IOERR_LOOP_OPEN_FAILURE))) - lpfc_printf_vlog(vport, KERN_ERR, LOG_TRACE_EVENT, - "2858 FLOGI failure Status:x%x/x%x TMO" - ":x%x Data x%lx x%x\n", - ulp_status, ulp_word4, tmo, - phba->hba_flag, phba->fcf.fcf_flag); + lpfc_vlog_msg(vport, KERN_WARNING, LOG_ELS, + "2858 FLOGI Status:x%x/x%x TMO" + ":x%x Data x%lx x%x\n", + ulp_status, ulp_word4, tmo, + phba->hba_flag, phba->fcf.fcf_flag); /* Check for retry */ if (lpfc_els_retry(phba, cmdiocb, rspiocb)) { @@ -1023,7 +1023,7 @@ stop_rr_fcf_flogi: lpfc_nlp_put(ndlp); lpfc_printf_vlog(vport, KERN_WARNING, LOG_ELS, - "0150 FLOGI failure Status:x%x/x%x " + "0150 FLOGI Status:x%x/x%x " "xri x%x TMO:x%x refcnt %d\n", ulp_status, ulp_word4, cmdiocb->sli4_xritag, tmo, kref_read(&ndlp->kref)); @@ -1032,11 +1032,11 @@ stop_rr_fcf_flogi: if (!(ulp_status == IOSTAT_LOCAL_REJECT && ((ulp_word4 & IOERR_PARAM_MASK) == IOERR_LOOP_OPEN_FAILURE))) { - /* FLOGI failure */ - lpfc_printf_vlog(vport, KERN_ERR, LOG_TRACE_EVENT, - "0100 FLOGI failure Status:x%x/x%x " - "TMO:x%x\n", - ulp_status, ulp_word4, tmo); + /* Warn FLOGI status */ + lpfc_vlog_msg(vport, KERN_WARNING, LOG_ELS, + "0100 FLOGI Status:x%x/x%x " + "TMO:x%x\n", + ulp_status, ulp_word4, tmo); goto flogifail; } @@ -1964,16 +1964,16 @@ lpfc_cmpl_els_rrq(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, if (ulp_status) { /* Check for retry */ - /* RRQ failed Don't print the vport to vport rjts */ + /* Warn RRQ status Don't print the vport to vport rjts */ if (ulp_status != IOSTAT_LS_RJT || (((ulp_word4) >> 16 != LSRJT_INVALID_CMD) && ((ulp_word4) >> 16 != LSRJT_UNABLE_TPC)) || (phba)->pport->cfg_log_verbose & LOG_ELS) - lpfc_printf_vlog(vport, KERN_ERR, LOG_TRACE_EVENT, - "2881 RRQ failure DID:%06X Status:" - "x%x/x%x\n", - ndlp->nlp_DID, ulp_status, - ulp_word4); + lpfc_vlog_msg(vport, KERN_WARNING, LOG_ELS, + "2881 RRQ DID:%06X Status:" + "x%x/x%x\n", + ndlp->nlp_DID, ulp_status, + ulp_word4); } lpfc_clr_rrq_active(phba, rrq->xritag, rrq); @@ -2077,16 +2077,16 @@ lpfc_cmpl_els_plogi(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, } goto out; } - /* PLOGI failed Don't print the vport to vport rjts */ + /* Warn PLOGI status Don't print the vport to vport rjts */ if (ulp_status != IOSTAT_LS_RJT || (((ulp_word4) >> 16 != LSRJT_INVALID_CMD) && ((ulp_word4) >> 16 != LSRJT_UNABLE_TPC)) || (phba)->pport->cfg_log_verbose & LOG_ELS) - lpfc_printf_vlog(vport, KERN_ERR, LOG_TRACE_EVENT, - "2753 PLOGI failure DID:%06X " - "Status:x%x/x%x\n", - ndlp->nlp_DID, ulp_status, - ulp_word4); + lpfc_vlog_msg(vport, KERN_WARNING, LOG_ELS, + "2753 PLOGI DID:%06X " + "Status:x%x/x%x\n", + ndlp->nlp_DID, ulp_status, + ulp_word4); /* Do not call DSM for lpfc_els_abort'ed ELS cmds */ if (!lpfc_error_lost_link(vport, ulp_status, ulp_word4)) @@ -2323,7 +2323,6 @@ lpfc_cmpl_els_prli(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, struct lpfc_vport *vport = cmdiocb->vport; struct lpfc_nodelist *ndlp; char *mode; - u32 loglevel; u32 ulp_status; u32 ulp_word4; bool release_node = false; @@ -2372,17 +2371,14 @@ lpfc_cmpl_els_prli(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, * could be expected. */ if (test_bit(FC_FABRIC, &vport->fc_flag) || - vport->cfg_enable_fc4_type != LPFC_ENABLE_BOTH) { - mode = KERN_ERR; - loglevel = LOG_TRACE_EVENT; - } else { + vport->cfg_enable_fc4_type != LPFC_ENABLE_BOTH) + mode = KERN_WARNING; + else mode = KERN_INFO; - loglevel = LOG_ELS; - } - /* PRLI failed */ - lpfc_printf_vlog(vport, mode, loglevel, - "2754 PRLI failure DID:%06X Status:x%x/x%x, " + /* Warn PRLI status */ + lpfc_printf_vlog(vport, mode, LOG_ELS, + "2754 PRLI DID:%06X Status:x%x/x%x, " "data: x%x x%x x%x\n", ndlp->nlp_DID, ulp_status, ulp_word4, ndlp->nlp_state, @@ -2854,11 +2850,11 @@ lpfc_cmpl_els_adisc(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, } goto out; } - /* ADISC failed */ - lpfc_printf_vlog(vport, KERN_ERR, LOG_TRACE_EVENT, - "2755 ADISC failure DID:%06X Status:x%x/x%x\n", - ndlp->nlp_DID, ulp_status, - ulp_word4); + /* Warn ADISC status */ + lpfc_vlog_msg(vport, KERN_WARNING, LOG_ELS, + "2755 ADISC DID:%06X Status:x%x/x%x\n", + ndlp->nlp_DID, ulp_status, + ulp_word4); lpfc_disc_state_machine(vport, ndlp, cmdiocb, NLP_EVT_CMPL_ADISC); @@ -3045,12 +3041,12 @@ lpfc_cmpl_els_logo(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, * discovery. The PLOGI will retry. */ if (ulp_status) { - /* LOGO failed */ - lpfc_printf_vlog(vport, KERN_ERR, LOG_TRACE_EVENT, - "2756 LOGO failure, No Retry DID:%06X " - "Status:x%x/x%x\n", - ndlp->nlp_DID, ulp_status, - ulp_word4); + /* Warn LOGO status */ + lpfc_vlog_msg(vport, KERN_WARNING, LOG_ELS, + "2756 LOGO, No Retry DID:%06X " + "Status:x%x/x%x\n", + ndlp->nlp_DID, ulp_status, + ulp_word4); if (lpfc_error_lost_link(vport, ulp_status, ulp_word4)) skip_recovery = 1; @@ -4837,11 +4833,10 @@ lpfc_els_retry(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, if ((phba->sli3_options & LPFC_SLI3_NPIV_ENABLED) && (cmd == ELS_CMD_FDISC) && (stat.un.b.lsRjtRsnCodeExp == LSEXP_OUT_OF_RESOURCE)){ - lpfc_printf_vlog(vport, KERN_ERR, - LOG_TRACE_EVENT, - "0125 FDISC Failed (x%x). " - "Fabric out of resources\n", - stat.un.lsRjtError); + lpfc_vlog_msg(vport, KERN_WARNING, LOG_ELS, + "0125 FDISC (x%x). " + "Fabric out of resources\n", + stat.un.lsRjtError); lpfc_vport_set_state(vport, FC_VPORT_NO_FABRIC_RSCS); } @@ -4877,11 +4872,10 @@ lpfc_els_retry(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, LSEXP_NOTHING_MORE) { vport->fc_sparam.cmn.bbRcvSizeMsb &= 0xf; retry = 1; - lpfc_printf_vlog(vport, KERN_ERR, - LOG_TRACE_EVENT, - "0820 FLOGI Failed (x%x). " - "BBCredit Not Supported\n", - stat.un.lsRjtError); + lpfc_vlog_msg(vport, KERN_WARNING, LOG_ELS, + "0820 FLOGI (x%x). " + "BBCredit Not Supported\n", + stat.un.lsRjtError); } break; @@ -4891,11 +4885,10 @@ lpfc_els_retry(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, ((stat.un.b.lsRjtRsnCodeExp == LSEXP_INVALID_PNAME) || (stat.un.b.lsRjtRsnCodeExp == LSEXP_INVALID_NPORT_ID)) ) { - lpfc_printf_vlog(vport, KERN_ERR, - LOG_TRACE_EVENT, - "0122 FDISC Failed (x%x). " - "Fabric Detected Bad WWN\n", - stat.un.lsRjtError); + lpfc_vlog_msg(vport, KERN_WARNING, LOG_ELS, + "0122 FDISC (x%x). " + "Fabric Detected Bad WWN\n", + stat.un.lsRjtError); lpfc_vport_set_state(vport, FC_VPORT_FABRIC_REJ_WWN); } @@ -5355,8 +5348,8 @@ lpfc_cmpl_els_rsp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, u32 ulp_status, ulp_word4, tmo, did, iotag; if (!vport) { - lpfc_printf_log(phba, KERN_ERR, LOG_TRACE_EVENT, - "3177 ELS response failed\n"); + lpfc_printf_log(phba, KERN_WARNING, LOG_ELS, + "3177 null vport in ELS rsp\n"); goto out; } if (cmdiocb->context_un.mbox) @@ -9658,11 +9651,12 @@ lpfc_els_flush_cmd(struct lpfc_vport *vport) if (piocb->cmd_flag & LPFC_DRIVER_ABORTED && !mbx_tmo_err) continue; - /* On the ELS ring we can have ELS_REQUESTs or - * GEN_REQUESTs waiting for a response. + /* On the ELS ring we can have ELS_REQUESTs, ELS_RSPs, + * or GEN_REQUESTs waiting for a CQE response. */ ulp_command = get_job_cmnd(phba, piocb); - if (ulp_command == CMD_ELS_REQUEST64_CR) { + if (ulp_command == CMD_ELS_REQUEST64_WQE || + ulp_command == CMD_XMIT_ELS_RSP64_WQE) { list_add_tail(&piocb->dlist, &abort_list); /* If the link is down when flushing ELS commands @@ -11327,10 +11321,10 @@ lpfc_cmpl_els_fdisc(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, /* Check for retry */ if (lpfc_els_retry(phba, cmdiocb, rspiocb)) goto out; - /* FDISC failed */ - lpfc_printf_vlog(vport, KERN_ERR, LOG_TRACE_EVENT, - "0126 FDISC failed. (x%x/x%x)\n", - ulp_status, ulp_word4); + /* Warn FDISC status */ + lpfc_vlog_msg(vport, KERN_WARNING, LOG_ELS, + "0126 FDISC cmpl status: x%x/x%x)\n", + ulp_status, ulp_word4); goto fdisc_failed; } diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c index 35c9181c6608..9241075f72fa 100644 --- a/drivers/scsi/lpfc/lpfc_hbadisc.c +++ b/drivers/scsi/lpfc/lpfc_hbadisc.c @@ -527,6 +527,9 @@ lpfc_dev_loss_tmo_handler(struct lpfc_nodelist *ndlp) * the following lpfc_nlp_put is necessary after fabric node is * recovered. */ + spin_lock_irqsave(&ndlp->lock, iflags); + ndlp->nlp_flag &= ~NLP_IN_DEV_LOSS; + spin_unlock_irqrestore(&ndlp->lock, iflags); if (recovering) { lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY | LOG_NODE, @@ -539,6 +542,7 @@ lpfc_dev_loss_tmo_handler(struct lpfc_nodelist *ndlp) spin_lock_irqsave(&ndlp->lock, iflags); ndlp->save_flags |= NLP_IN_RECOV_POST_DEV_LOSS; spin_unlock_irqrestore(&ndlp->lock, iflags); + return fcf_inuse; } else if (ndlp->nlp_state == NLP_STE_UNMAPPED_NODE) { /* Fabric node fully recovered before this dev_loss_tmo * queue work is processed. Thus, ignore the @@ -552,15 +556,9 @@ lpfc_dev_loss_tmo_handler(struct lpfc_nodelist *ndlp) ndlp->nlp_DID, kref_read(&ndlp->kref), ndlp, ndlp->nlp_flag, vport->port_state); - spin_lock_irqsave(&ndlp->lock, iflags); - ndlp->nlp_flag &= ~NLP_IN_DEV_LOSS; - spin_unlock_irqrestore(&ndlp->lock, iflags); return fcf_inuse; } - spin_lock_irqsave(&ndlp->lock, iflags); - ndlp->nlp_flag &= ~NLP_IN_DEV_LOSS; - spin_unlock_irqrestore(&ndlp->lock, iflags); lpfc_nlp_put(ndlp); return fcf_inuse; } diff --git a/drivers/scsi/lpfc/lpfc_hw.h b/drivers/scsi/lpfc/lpfc_hw.h index 2108b4cb7815..d5c15742f7f2 100644 --- a/drivers/scsi/lpfc/lpfc_hw.h +++ b/drivers/scsi/lpfc/lpfc_hw.h @@ -562,6 +562,27 @@ struct fc_vft_header { #include <uapi/scsi/fc/fc_els.h> /* + * Application Header + */ +struct fc_app_header { + uint32_t dst_app_id; + uint32_t src_app_id; +#define LOOPBACK_SRC_APPID 0x4321 + uint32_t word2; + uint32_t word3; +}; + +/* + * dfctl optional header definition + */ +enum lpfc_fc_dfctl { + LPFC_FC_NO_DEVICE_HEADER, + LPFC_FC_16B_DEVICE_HEADER, + LPFC_FC_32B_DEVICE_HEADER, + LPFC_FC_64B_DEVICE_HEADER, +}; + +/* * Extended Link Service LS_COMMAND codes (Payload Word 0) */ #ifdef __BIG_ENDIAN_BITFIELD diff --git a/drivers/scsi/lpfc/lpfc_hw4.h b/drivers/scsi/lpfc/lpfc_hw4.h index 500253007b1d..26e1313ebb21 100644 --- a/drivers/scsi/lpfc/lpfc_hw4.h +++ b/drivers/scsi/lpfc/lpfc_hw4.h @@ -4847,6 +4847,7 @@ struct fcp_iwrite64_wqe { #define cmd_buff_len_SHIFT 16 #define cmd_buff_len_MASK 0x00000ffff #define cmd_buff_len_WORD word3 +/* Note: payload_offset_len field depends on ASIC support */ #define payload_offset_len_SHIFT 0 #define payload_offset_len_MASK 0x0000ffff #define payload_offset_len_WORD word3 @@ -4863,6 +4864,7 @@ struct fcp_iread64_wqe { #define cmd_buff_len_SHIFT 16 #define cmd_buff_len_MASK 0x00000ffff #define cmd_buff_len_WORD word3 +/* Note: payload_offset_len field depends on ASIC support */ #define payload_offset_len_SHIFT 0 #define payload_offset_len_MASK 0x0000ffff #define payload_offset_len_WORD word3 @@ -4879,6 +4881,7 @@ struct fcp_icmnd64_wqe { #define cmd_buff_len_SHIFT 16 #define cmd_buff_len_MASK 0x00000ffff #define cmd_buff_len_WORD word3 +/* Note: payload_offset_len field depends on ASIC support */ #define payload_offset_len_SHIFT 0 #define payload_offset_len_MASK 0x0000ffff #define payload_offset_len_WORD word3 diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c index 50620918becd..0dd451009b07 100644 --- a/drivers/scsi/lpfc/lpfc_init.c +++ b/drivers/scsi/lpfc/lpfc_init.c @@ -4699,6 +4699,7 @@ lpfc_create_port(struct lpfc_hba *phba, int instance, struct device *dev) uint64_t wwn; bool use_no_reset_hba = false; int rc; + u8 if_type; if (lpfc_no_hba_reset_cnt) { if (phba->sli_rev < LPFC_SLI_REV4 && @@ -4773,10 +4774,24 @@ lpfc_create_port(struct lpfc_hba *phba, int instance, struct device *dev) shost->max_id = LPFC_MAX_TARGET; shost->max_lun = vport->cfg_max_luns; shost->this_id = -1; - if (phba->sli_rev == LPFC_SLI_REV4) - shost->max_cmd_len = LPFC_FCP_CDB_LEN_32; - else + + /* Set max_cmd_len applicable to ASIC support */ + if (phba->sli_rev == LPFC_SLI_REV4) { + if_type = bf_get(lpfc_sli_intf_if_type, + &phba->sli4_hba.sli_intf); + switch (if_type) { + case LPFC_SLI_INTF_IF_TYPE_2: + fallthrough; + case LPFC_SLI_INTF_IF_TYPE_6: + shost->max_cmd_len = LPFC_FCP_CDB_LEN_32; + break; + default: + shost->max_cmd_len = LPFC_FCP_CDB_LEN; + break; + } + } else { shost->max_cmd_len = LPFC_FCP_CDB_LEN; + } if (phba->sli_rev == LPFC_SLI_REV4) { if (!phba->cfg_fcp_mq_threshold || @@ -10436,6 +10451,7 @@ lpfc_sli4_queue_create(struct lpfc_hba *phba) struct lpfc_vector_map_info *cpup; struct lpfc_vector_map_info *eqcpup; struct lpfc_eq_intr_info *eqi; + u32 wqesize; /* * Create HBA Record arrays. @@ -10655,9 +10671,15 @@ lpfc_sli4_queue_create(struct lpfc_hba *phba) * Create ELS Work Queues */ - /* Create slow-path ELS Work Queue */ + /* + * Create slow-path ELS Work Queue. + * Increase the ELS WQ size when WQEs contain an embedded cdb + */ + wqesize = (phba->fcp_embed_io) ? + LPFC_WQE128_SIZE : phba->sli4_hba.wq_esize; + qdesc = lpfc_sli4_queue_alloc(phba, LPFC_DEFAULT_PAGE_SIZE, - phba->sli4_hba.wq_esize, + wqesize, phba->sli4_hba.wq_ecount, cpu); if (!qdesc) { lpfc_printf_log(phba, KERN_ERR, LOG_TRACE_EVENT, diff --git a/drivers/scsi/lpfc/lpfc_nvme.c b/drivers/scsi/lpfc/lpfc_nvme.c index d70da2736c94..fec23c723730 100644 --- a/drivers/scsi/lpfc/lpfc_nvme.c +++ b/drivers/scsi/lpfc/lpfc_nvme.c @@ -24,7 +24,7 @@ #include <linux/slab.h> #include <linux/interrupt.h> #include <linux/delay.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/crc-t10dif.h> #include <net/checksum.h> diff --git a/drivers/scsi/lpfc/lpfc_nvmet.c b/drivers/scsi/lpfc/lpfc_nvmet.c index 0cef5d089f34..55c3e2c2bf8f 100644 --- a/drivers/scsi/lpfc/lpfc_nvmet.c +++ b/drivers/scsi/lpfc/lpfc_nvmet.c @@ -24,7 +24,7 @@ #include <linux/slab.h> #include <linux/interrupt.h> #include <linux/delay.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/crc-t10dif.h> #include <net/checksum.h> diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c index 60cd60ebff38..11c974bffa72 100644 --- a/drivers/scsi/lpfc/lpfc_scsi.c +++ b/drivers/scsi/lpfc/lpfc_scsi.c @@ -25,7 +25,7 @@ #include <linux/interrupt.h> #include <linux/export.h> #include <linux/delay.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/t10-pi.h> #include <linux/crc-t10dif.h> #include <linux/blk-cgroup.h> @@ -4760,7 +4760,7 @@ static int lpfc_scsi_prep_cmnd_buf_s4(struct lpfc_vport *vport, /* Word 3 */ bf_set(payload_offset_len, &wqe->fcp_icmd, - sizeof(struct fcp_cmnd32) + sizeof(struct fcp_rsp)); + sizeof(struct fcp_cmnd) + sizeof(struct fcp_rsp)); /* Word 6 */ bf_set(wqe_ctxt_tag, &wqe->generic.wqe_com, diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c index 332b8d2348e9..2ec6e55771b4 100644 --- a/drivers/scsi/lpfc/lpfc_sli.c +++ b/drivers/scsi/lpfc/lpfc_sli.c @@ -1940,12 +1940,15 @@ lpfc_issue_cmf_sync_wqe(struct lpfc_hba *phba, u32 ms, u64 total) atot = atomic_xchg(&phba->cgn_sync_alarm_cnt, 0); wtot = atomic_xchg(&phba->cgn_sync_warn_cnt, 0); + spin_lock_irqsave(&phba->hbalock, iflags); + /* ONLY Managed mode will send the CMF_SYNC_WQE to the HBA */ if (phba->cmf_active_mode != LPFC_CFG_MANAGED || - phba->link_state == LPFC_LINK_DOWN) - return 0; + phba->link_state < LPFC_LINK_UP) { + ret_val = 0; + goto out_unlock; + } - spin_lock_irqsave(&phba->hbalock, iflags); sync_buf = __lpfc_sli_get_iocbq(phba); if (!sync_buf) { lpfc_printf_log(phba, KERN_ERR, LOG_CGN_MGMT, @@ -8818,7 +8821,7 @@ lpfc_sli4_hba_setup(struct lpfc_hba *phba) rc = lpfc_sli4_queue_setup(phba); if (unlikely(rc)) { lpfc_printf_log(phba, KERN_ERR, LOG_TRACE_EVENT, - "0381 Error %d during queue setup.\n ", rc); + "0381 Error %d during queue setup.\n", rc); goto out_stop_timers; } /* Initialize the driver internal SLI layer lists. */ @@ -11090,9 +11093,17 @@ __lpfc_sli_prep_xmit_seq64_s4(struct lpfc_iocbq *cmdiocbq, /* Word 9 */ bf_set(wqe_rcvoxid, &wqe->xmit_sequence.wqe_com, ox_id); - /* Word 12 */ - if (cmdiocbq->cmd_flag & (LPFC_IO_LIBDFC | LPFC_IO_LOOPBACK)) + if (cmdiocbq->cmd_flag & (LPFC_IO_LIBDFC | LPFC_IO_LOOPBACK)) { + /* Word 10 */ + if (cmdiocbq->cmd_flag & LPFC_IO_VMID) { + bf_set(wqe_appid, &wqe->xmit_sequence.wqe_com, 1); + bf_set(wqe_wqes, &wqe->xmit_sequence.wqe_com, 1); + wqe->words[31] = LOOPBACK_SRC_APPID; + } + + /* Word 12 */ wqe->xmit_sequence.xmit_len = full_size; + } else wqe->xmit_sequence.xmit_len = wqe->xmit_sequence.bde.tus.f.bdeSize; @@ -18431,6 +18442,7 @@ lpfc_fc_frame_check(struct lpfc_hba *phba, struct fc_frame_header *fc_hdr) { /* make rctl_names static to save stack space */ struct fc_vft_header *fc_vft_hdr; + struct fc_app_header *fc_app_hdr; uint32_t *header = (uint32_t *) fc_hdr; #define FC_RCTL_MDS_DIAGS 0xF4 @@ -18486,6 +18498,32 @@ lpfc_fc_frame_check(struct lpfc_hba *phba, struct fc_frame_header *fc_hdr) goto drop; } + if (unlikely(phba->link_flag == LS_LOOPBACK_MODE && + phba->cfg_vmid_app_header)) { + /* Application header is 16B device header */ + if (fc_hdr->fh_df_ctl & LPFC_FC_16B_DEVICE_HEADER) { + fc_app_hdr = (struct fc_app_header *) (fc_hdr + 1); + if (be32_to_cpu(fc_app_hdr->src_app_id) != + LOOPBACK_SRC_APPID) { + lpfc_printf_log(phba, KERN_WARNING, + LOG_ELS | LOG_LIBDFC, + "1932 Loopback src app id " + "not matched, app_id:x%x\n", + be32_to_cpu(fc_app_hdr->src_app_id)); + + goto drop; + } + } else { + lpfc_printf_log(phba, KERN_WARNING, + LOG_ELS | LOG_LIBDFC, + "1933 Loopback df_ctl bit not set, " + "df_ctl:x%x\n", + fc_hdr->fh_df_ctl); + + goto drop; + } + } + lpfc_printf_log(phba, KERN_INFO, LOG_ELS, "2538 Received frame rctl:x%x, type:x%x, " "frame Data:%08x %08x %08x %08x %08x %08x %08x\n", @@ -21149,7 +21187,7 @@ lpfc_drain_txq(struct lpfc_hba *phba) if (!piocbq) { spin_unlock_irqrestore(&pring->ring_lock, iflags); lpfc_printf_log(phba, KERN_ERR, LOG_TRACE_EVENT, - "2823 txq empty and txq_cnt is %d\n ", + "2823 txq empty and txq_cnt is %d\n", txq_cnt); break; } diff --git a/drivers/scsi/lpfc/lpfc_version.h b/drivers/scsi/lpfc/lpfc_version.h index 2fe0386a1fee..e70f163fab90 100644 --- a/drivers/scsi/lpfc/lpfc_version.h +++ b/drivers/scsi/lpfc/lpfc_version.h @@ -20,7 +20,7 @@ * included with this package. * *******************************************************************/ -#define LPFC_DRIVER_VERSION "14.4.0.4" +#define LPFC_DRIVER_VERSION "14.4.0.5" #define LPFC_DRIVER_NAME "lpfc" /* Used for SLI 2/3 */ diff --git a/drivers/scsi/lpfc/lpfc_vport.c b/drivers/scsi/lpfc/lpfc_vport.c index 4439167a5188..7a4d4d8e2ad5 100644 --- a/drivers/scsi/lpfc/lpfc_vport.c +++ b/drivers/scsi/lpfc/lpfc_vport.c @@ -626,6 +626,7 @@ lpfc_vport_delete(struct fc_vport *fc_vport) struct Scsi_Host *shost = lpfc_shost_from_vport(vport); struct lpfc_hba *phba = vport->phba; int rc; + DECLARE_WAIT_QUEUE_HEAD_ONSTACK(waitq); if (vport->port_type == LPFC_PHYSICAL_PORT) { lpfc_printf_vlog(vport, KERN_ERR, LOG_TRACE_EVENT, @@ -679,21 +680,49 @@ lpfc_vport_delete(struct fc_vport *fc_vport) if (!ndlp) goto skip_logo; + /* Send the DA_ID and Fabric LOGO to cleanup the NPIV fabric entries. */ if (ndlp && ndlp->nlp_state == NLP_STE_UNMAPPED_NODE && phba->link_state >= LPFC_LINK_UP && phba->fc_topology != LPFC_TOPOLOGY_LOOP) { if (vport->cfg_enable_da_id) { - /* Send DA_ID and wait for a completion. */ + /* Send DA_ID and wait for a completion. This is best + * effort. If the DA_ID fails, likely the fabric will + * "leak" NportIDs but at least the driver issued the + * command. + */ + ndlp = lpfc_findnode_did(vport, NameServer_DID); + if (!ndlp) + goto issue_logo; + + spin_lock_irq(&ndlp->lock); + ndlp->da_id_waitq = &waitq; + ndlp->save_flags |= NLP_WAIT_FOR_DA_ID; + spin_unlock_irq(&ndlp->lock); + rc = lpfc_ns_cmd(vport, SLI_CTNS_DA_ID, 0, 0); - if (rc) { - lpfc_printf_log(vport->phba, KERN_WARNING, - LOG_VPORT, - "1829 CT command failed to " - "delete objects on fabric, " - "rc %d\n", rc); + if (!rc) { + wait_event_timeout(waitq, + !(ndlp->save_flags & NLP_WAIT_FOR_DA_ID), + msecs_to_jiffies(phba->fc_ratov * 2000)); } + + lpfc_printf_vlog(vport, KERN_INFO, LOG_VPORT | LOG_ELS, + "1829 DA_ID issue status %d. " + "SFlag x%x NState x%x, NFlag x%x " + "Rpi x%x\n", + rc, ndlp->save_flags, ndlp->nlp_state, + ndlp->nlp_flag, ndlp->nlp_rpi); + + /* Remove the waitq and save_flags. It no + * longer matters if the wake happened. + */ + spin_lock_irq(&ndlp->lock); + ndlp->da_id_waitq = NULL; + ndlp->save_flags &= ~NLP_WAIT_FOR_DA_ID; + spin_unlock_irq(&ndlp->lock); } +issue_logo: /* * If the vpi is not registered, then a valid FDISC doesn't * exist and there is no need for a ELS LOGO. Just cleanup diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c index 6c79c350a4d5..8e75e2e279a4 100644 --- a/drivers/scsi/megaraid/megaraid_sas_base.c +++ b/drivers/scsi/megaraid/megaraid_sas_base.c @@ -29,7 +29,7 @@ #include <linux/uio.h> #include <linux/slab.h> #include <linux/uaccess.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/fs.h> #include <linux/compat.h> #include <linux/blkdev.h> @@ -6380,7 +6380,7 @@ static int megasas_init_fw(struct megasas_instance *instance) GFP_KERNEL); if (!fusion->stream_detect_by_ld[i]) { dev_err(&instance->pdev->dev, - "unable to allocate stream detect by LD\n "); + "unable to allocate stream detect by LD\n"); for (j = 0; j < i; ++j) kfree(fusion->stream_detect_by_ld[j]); kfree(fusion->stream_detect_by_ld); diff --git a/drivers/scsi/mpi3mr/mpi/mpi30_cnfg.h b/drivers/scsi/mpi3mr/mpi/mpi30_cnfg.h index 4b7a8f6314a3..00cd18edfad6 100644 --- a/drivers/scsi/mpi3mr/mpi/mpi30_cnfg.h +++ b/drivers/scsi/mpi3mr/mpi/mpi30_cnfg.h @@ -67,6 +67,7 @@ #define MPI3_SECURITY_PGAD_SLOT_GROUP_MASK (0x0000ff00) #define MPI3_SECURITY_PGAD_SLOT_GROUP_SHIFT (8) #define MPI3_SECURITY_PGAD_SLOT_MASK (0x000000ff) +#define MPI3_INSTANCE_PGAD_INSTANCE_MASK (0x0000ffff) struct mpi3_config_request { __le16 host_tag; u8 ioc_use_only02; @@ -75,7 +76,8 @@ struct mpi3_config_request { u8 ioc_use_only06; u8 msg_flags; __le16 change_count; - __le16 reserved0a; + u8 proxy_ioc_number; + u8 reserved0b; u8 page_version; u8 page_number; u8 page_type; @@ -206,6 +208,9 @@ struct mpi3_config_page_header { #define MPI3_MFGPAGE_DEVID_SAS5116_MPI_MGMT (0x00b5) #define MPI3_MFGPAGE_DEVID_SAS5116_NVME_MGMT (0x00b6) #define MPI3_MFGPAGE_DEVID_SAS5116_PCIE_SWITCH (0x00b8) +#define MPI3_MFGPAGE_DEVID_SAS5248_MPI (0x00f0) +#define MPI3_MFGPAGE_DEVID_SAS5248_MPI_NS (0x00f1) +#define MPI3_MFGPAGE_DEVID_SAS5248_PCIE_SWITCH (0x00f2) struct mpi3_man_page0 { struct mpi3_config_page_header header; u8 chip_revision[8]; @@ -1074,6 +1079,8 @@ struct mpi3_io_unit_page8 { #define MPI3_IOUNIT8_SBSTATE_SVN_UPDATE_PENDING (0x04) #define MPI3_IOUNIT8_SBSTATE_KEY_UPDATE_PENDING (0x02) #define MPI3_IOUNIT8_SBSTATE_SECURE_BOOT_ENABLED (0x01) +#define MPI3_IOUNIT8_SBMODE_CURRENT_KEY_IOUNIT17 (0x10) +#define MPI3_IOUNIT8_SBMODE_HARD_SECURE_RECERTIFIED (0x08) struct mpi3_io_unit_page9 { struct mpi3_config_page_header header; __le32 flags; @@ -1089,6 +1096,8 @@ struct mpi3_io_unit_page9 { #define MPI3_IOUNIT9_FLAGS_UBM_ENCLOSURE_ORDER_BACKPLANE_TYPE (0x00000004) #define MPI3_IOUNIT9_FLAGS_VDFIRST_ENABLED (0x00000001) #define MPI3_IOUNIT9_FIRSTDEVICE_UNKNOWN (0xffff) +#define MPI3_IOUNIT9_FIRSTDEVICE_IN_DRIVER_PAGE_0 (0xfffe) + struct mpi3_io_unit_page10 { struct mpi3_config_page_header header; u8 flags; @@ -1224,6 +1233,19 @@ struct mpi3_io_unit_page15 { #define MPI3_IOUNIT15_FLAGS_EPRSUPPORT_WITHOUT_POWER_BRAKE_GPIO (0x01) #define MPI3_IOUNIT15_FLAGS_EPRSUPPORT_WITH_POWER_BRAKE_GPIO (0x02) #define MPI3_IOUNIT15_NUMPOWERBUDGETDATA_POWER_BUDGETING_DISABLED (0x00) + +struct mpi3_io_unit_page17 { + struct mpi3_config_page_header header; + u8 num_instances; + u8 instance; + __le16 reserved0a; + __le32 reserved0c[4]; + __le16 key_length; + u8 encryption_algorithm; + u8 reserved1f; + __le32 current_key[]; +}; +#define MPI3_IOUNIT17_PAGEVERSION (0x00) struct mpi3_ioc_page0 { struct mpi3_config_page_header header; __le32 reserved08; @@ -1311,7 +1333,7 @@ struct mpi3_driver_page0 { u8 tur_interval; u8 reserved10; u8 security_key_timeout; - __le16 reserved12; + __le16 first_device; __le32 reserved14; __le32 reserved18; }; @@ -1324,10 +1346,13 @@ struct mpi3_driver_page0 { #define MPI3_DRIVER0_BSDOPTS_REGISTRATION_IOC_AND_DEVS (0x00000000) #define MPI3_DRIVER0_BSDOPTS_REGISTRATION_IOC_ONLY (0x00000001) #define MPI3_DRIVER0_BSDOPTS_REGISTRATION_IOC_AND_INTERNAL_DEVS (0x00000002) +#define MPI3_DRIVER0_FIRSTDEVICE_IGNORE1 (0x0000) +#define MPI3_DRIVER0_FIRSTDEVICE_IGNORE2 (0xffff) struct mpi3_driver_page1 { struct mpi3_config_page_header header; __le32 flags; - __le32 reserved0c; + u8 time_stamp_update; + u8 reserved0d[3]; __le16 host_diag_trace_max_size; __le16 host_diag_trace_min_size; __le16 host_diag_trace_decrement_size; @@ -2347,6 +2372,10 @@ struct mpi3_device0_vd_format { #define MPI3_DEVICE0_VD_DEVICE_INFO_SAS (0x0001) #define MPI3_DEVICE0_VD_FLAGS_IO_THROTTLE_GROUP_QD_MASK (0xf000) #define MPI3_DEVICE0_VD_FLAGS_IO_THROTTLE_GROUP_QD_SHIFT (12) +#define MPI3_DEVICE0_VD_FLAGS_OSEXPOSURE_MASK (0x0003) +#define MPI3_DEVICE0_VD_FLAGS_OSEXPOSURE_HDD (0x0000) +#define MPI3_DEVICE0_VD_FLAGS_OSEXPOSURE_SSD (0x0001) +#define MPI3_DEVICE0_VD_FLAGS_OSEXPOSURE_NO_GUIDANCE (0x0002) union mpi3_device0_dev_spec_format { struct mpi3_device0_sas_sata_format sas_sata_format; struct mpi3_device0_pcie_format pcie_format; diff --git a/drivers/scsi/mpi3mr/mpi/mpi30_image.h b/drivers/scsi/mpi3mr/mpi/mpi30_image.h index 7df242190135..2c6e548cbd0f 100644 --- a/drivers/scsi/mpi3mr/mpi/mpi30_image.h +++ b/drivers/scsi/mpi3mr/mpi/mpi30_image.h @@ -205,13 +205,14 @@ struct mpi3_encrypted_hash_entry { u8 hash_image_type; u8 hash_algorithm; u8 encryption_algorithm; - u8 reserved03; + u8 flags; __le16 public_key_size; __le16 signature_size; __le32 public_key[MPI3_PUBLIC_KEY_MAX]; }; - -#define MPI3_HASH_IMAGE_TYPE_KEY_WITH_SIGNATURE (0x03) +#define MPI3_HASH_IMAGE_TYPE_KEY_WITH_HASH (0x03) +#define MPI3_HASH_IMAGE_TYPE_KEY_WITH_HASH_1_OF_2 (0x04) +#define MPI3_HASH_IMAGE_TYPE_KEY_WITH_HASH_2_OF_2 (0x05) #define MPI3_HASH_ALGORITHM_VERSION_MASK (0xe0) #define MPI3_HASH_ALGORITHM_VERSION_NONE (0x00) #define MPI3_HASH_ALGORITHM_VERSION_SHA1 (0x20) @@ -230,6 +231,12 @@ struct mpi3_encrypted_hash_entry { #define MPI3_ENCRYPTION_ALGORITHM_RSA4096 (0x05) #define MPI3_ENCRYPTION_ALGORITHM_RSA3072 (0x06) +/* hierarchical signature system (hss) */ +#define MPI3_ENCRYPTION_ALGORITHM_ML_DSA_87 (0x0b) +#define MPI3_ENCRYPTION_ALGORITHM_ML_DSA_65 (0x0c) +#define MPI3_ENCRYPTION_ALGORITHM_ML_DSA_44 (0x0d) +#define MPI3_ENCRYPTED_HASH_ENTRY_FLAGS_PAIRED_KEY_MASK (0x0f) + #ifndef MPI3_ENCRYPTED_HASH_ENTRY_MAX #define MPI3_ENCRYPTED_HASH_ENTRY_MAX (1) #endif diff --git a/drivers/scsi/mpi3mr/mpi/mpi30_ioc.h b/drivers/scsi/mpi3mr/mpi/mpi30_ioc.h index c9fa0d69b75f..c374867f9ba0 100644 --- a/drivers/scsi/mpi3mr/mpi/mpi30_ioc.h +++ b/drivers/scsi/mpi3mr/mpi/mpi30_ioc.h @@ -39,6 +39,12 @@ struct mpi3_ioc_init_request { #define MPI3_WHOINIT_HOST_DRIVER (0x03) #define MPI3_WHOINIT_MANUFACTURER (0x04) +#define MPI3_IOCINIT_DRIVERCAP_OSEXPOSURE_MASK (0x00000003) +#define MPI3_IOCINIT_DRIVERCAP_OSEXPOSURE_NO_GUIDANCE (0x00000000) +#define MPI3_IOCINIT_DRIVERCAP_OSEXPOSURE_NO_SPECIAL (0x00000001) +#define MPI3_IOCINIT_DRIVERCAP_OSEXPOSURE_REPORT_AS_HDD (0x00000002) +#define MPI3_IOCINIT_DRIVERCAP_OSEXPOSURE_REPORT_AS_SSD (0x00000003) + struct mpi3_ioc_facts_request { __le16 host_tag; u8 ioc_use_only02; @@ -140,6 +146,8 @@ struct mpi3_ioc_facts_data { #define MPI3_IOCFACTS_EXCEPT_MANUFACT_CHECKSUM_FAIL (0x0020) #define MPI3_IOCFACTS_EXCEPT_FW_CHECKSUM_FAIL (0x0010) #define MPI3_IOCFACTS_EXCEPT_CONFIG_CHECKSUM_FAIL (0x0008) +#define MPI3_IOCFACTS_EXCEPT_BLOCKING_BOOT_EVENT (0x0004) +#define MPI3_IOCFACTS_EXCEPT_SECURITY_SELFTEST_FAILURE (0x0002) #define MPI3_IOCFACTS_EXCEPT_BOOTSTAT_MASK (0x0001) #define MPI3_IOCFACTS_EXCEPT_BOOTSTAT_PRIMARY (0x0000) #define MPI3_IOCFACTS_EXCEPT_BOOTSTAT_SECONDARY (0x0001) diff --git a/drivers/scsi/mpi3mr/mpi/mpi30_transport.h b/drivers/scsi/mpi3mr/mpi/mpi30_transport.h index fdc3d1968e43..b2ab25a1cfeb 100644 --- a/drivers/scsi/mpi3mr/mpi/mpi30_transport.h +++ b/drivers/scsi/mpi3mr/mpi/mpi30_transport.h @@ -18,7 +18,7 @@ union mpi3_version_union { #define MPI3_VERSION_MAJOR (3) #define MPI3_VERSION_MINOR (0) -#define MPI3_VERSION_UNIT (31) +#define MPI3_VERSION_UNIT (34) #define MPI3_VERSION_DEV (0) #define MPI3_DEVHANDLE_INVALID (0xffff) struct mpi3_sysif_oper_queue_indexes { @@ -158,6 +158,7 @@ struct mpi3_sysif_registers { #define MPI3_SYSIF_FAULT_CODE_SOFT_RESET_NEEDED (0x0000f004) #define MPI3_SYSIF_FAULT_CODE_POWER_CYCLE_REQUIRED (0x0000f005) #define MPI3_SYSIF_FAULT_CODE_TEMP_THRESHOLD_EXCEEDED (0x0000f006) +#define MPI3_SYSIF_FAULT_CODE_INSUFFICIENT_PCI_SLOT_POWER (0x0000f007) #define MPI3_SYSIF_FAULT_INFO0_OFFSET (0x00001c14) #define MPI3_SYSIF_FAULT_INFO1_OFFSET (0x00001c18) #define MPI3_SYSIF_FAULT_INFO2_OFFSET (0x00001c1c) @@ -410,6 +411,7 @@ struct mpi3_default_reply { #define MPI3_IOCSTATUS_INSUFFICIENT_RESOURCES (0x0006) #define MPI3_IOCSTATUS_INVALID_FIELD (0x0007) #define MPI3_IOCSTATUS_INVALID_STATE (0x0008) +#define MPI3_IOCSTATUS_SHUTDOWN_ACTIVE (0x0009) #define MPI3_IOCSTATUS_INSUFFICIENT_POWER (0x000a) #define MPI3_IOCSTATUS_INVALID_CHANGE_COUNT (0x000b) #define MPI3_IOCSTATUS_ALLOWED_CMD_BLOCK (0x000c) diff --git a/drivers/scsi/mpi3mr/mpi3mr.h b/drivers/scsi/mpi3mr/mpi3mr.h index 1dc640de3efc..14eeac08660f 100644 --- a/drivers/scsi/mpi3mr/mpi3mr.h +++ b/drivers/scsi/mpi3mr/mpi3mr.h @@ -31,7 +31,7 @@ #include <linux/uaccess.h> #include <linux/utsname.h> #include <linux/workqueue.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <scsi/scsi.h> #include <scsi/scsi_cmnd.h> #include <scsi/scsi_dbg.h> @@ -57,8 +57,8 @@ extern struct list_head mrioc_list; extern int prot_mask; extern atomic64_t event_counter; -#define MPI3MR_DRIVER_VERSION "8.10.0.5.50" -#define MPI3MR_DRIVER_RELDATE "08-Aug-2024" +#define MPI3MR_DRIVER_VERSION "8.12.0.0.50" +#define MPI3MR_DRIVER_RELDATE "05-Sept-2024" #define MPI3MR_DRIVER_NAME "mpi3mr" #define MPI3MR_DRIVER_LICENSE "GPL" @@ -178,7 +178,7 @@ extern atomic64_t event_counter; #define MPI3MR_DEFAULT_SDEV_QD 32 /* Definitions for Threaded IRQ poll*/ -#define MPI3MR_IRQ_POLL_SLEEP 2 +#define MPI3MR_IRQ_POLL_SLEEP 20 #define MPI3MR_IRQ_POLL_TRIGGER_IOCOUNT 8 /* Definitions for the controller security status*/ @@ -1090,6 +1090,7 @@ struct scmd_priv { * @evtack_cmds_bitmap: Event Ack bitmap * @delayed_evtack_cmds_list: Delayed event acknowledgment list * @ts_update_counter: Timestamp update counter + * @ts_update_interval: Timestamp update interval * @reset_in_progress: Reset in progress flag * @unrecoverable: Controller unrecoverable flag * @prev_reset_result: Result of previous reset @@ -1277,7 +1278,8 @@ struct mpi3mr_ioc { unsigned long *evtack_cmds_bitmap; struct list_head delayed_evtack_cmds_list; - u32 ts_update_counter; + u16 ts_update_counter; + u16 ts_update_interval; u8 reset_in_progress; u8 unrecoverable; int prev_reset_result; diff --git a/drivers/scsi/mpi3mr/mpi3mr_fw.c b/drivers/scsi/mpi3mr/mpi3mr_fw.c index 2e1a92d306b2..f1ab76351bd8 100644 --- a/drivers/scsi/mpi3mr/mpi3mr_fw.c +++ b/drivers/scsi/mpi3mr/mpi3mr_fw.c @@ -728,7 +728,7 @@ static irqreturn_t mpi3mr_isr_poll(int irq, void *privdata) mpi3mr_process_op_reply_q(mrioc, intr_info->op_reply_q); - usleep_range(MPI3MR_IRQ_POLL_SLEEP, 10 * MPI3MR_IRQ_POLL_SLEEP); + usleep_range(MPI3MR_IRQ_POLL_SLEEP, MPI3MR_IRQ_POLL_SLEEP + 1); } while (atomic_read(&intr_info->op_reply_q->pend_ios) && (num_op_reply < mrioc->max_host_ios)); @@ -1362,6 +1362,10 @@ static int mpi3mr_bring_ioc_ready(struct mpi3mr_ioc *mrioc) int retval = 0; enum mpi3mr_iocstate ioc_state; u64 base_info; + u8 retry = 0; + u64 start_time, elapsed_time_sec; + +retry_bring_ioc_ready: ioc_status = readl(&mrioc->sysif_regs->ioc_status); ioc_config = readl(&mrioc->sysif_regs->ioc_configuration); @@ -1380,26 +1384,23 @@ static int mpi3mr_bring_ioc_ready(struct mpi3mr_ioc *mrioc) ioc_info(mrioc, "controller is in %s state during detection\n", mpi3mr_iocstate_name(ioc_state)); - if (ioc_state == MRIOC_STATE_BECOMING_READY || - ioc_state == MRIOC_STATE_RESET_REQUESTED) { - timeout = mrioc->ready_timeout * 10; - do { - msleep(100); - } while (--timeout); + timeout = mrioc->ready_timeout * 10; + + do { + ioc_state = mpi3mr_get_iocstate(mrioc); + + if (ioc_state != MRIOC_STATE_BECOMING_READY && + ioc_state != MRIOC_STATE_RESET_REQUESTED) + break; if (!pci_device_is_present(mrioc->pdev)) { mrioc->unrecoverable = 1; - ioc_err(mrioc, - "controller is not present while waiting to reset\n"); - retval = -1; + ioc_err(mrioc, "controller is not present while waiting to reset\n"); goto out_device_not_present; } - ioc_state = mpi3mr_get_iocstate(mrioc); - ioc_info(mrioc, - "controller is in %s state after waiting to reset\n", - mpi3mr_iocstate_name(ioc_state)); - } + msleep(100); + } while (--timeout); if (ioc_state == MRIOC_STATE_READY) { ioc_info(mrioc, "issuing message unit reset (MUR) to bring to reset state\n"); @@ -1460,6 +1461,9 @@ static int mpi3mr_bring_ioc_ready(struct mpi3mr_ioc *mrioc) ioc_config |= MPI3_SYSIF_IOC_CONFIG_ENABLE_IOC; writel(ioc_config, &mrioc->sysif_regs->ioc_configuration); + if (retry == 0) + start_time = jiffies; + timeout = mrioc->ready_timeout * 10; do { ioc_state = mpi3mr_get_iocstate(mrioc); @@ -1469,6 +1473,12 @@ static int mpi3mr_bring_ioc_ready(struct mpi3mr_ioc *mrioc) mpi3mr_iocstate_name(ioc_state)); return 0; } + ioc_status = readl(&mrioc->sysif_regs->ioc_status); + if ((ioc_status & MPI3_SYSIF_IOC_STATUS_RESET_HISTORY) || + (ioc_status & MPI3_SYSIF_IOC_STATUS_FAULT)) { + mpi3mr_print_fault_info(mrioc); + goto out_failed; + } if (!pci_device_is_present(mrioc->pdev)) { mrioc->unrecoverable = 1; ioc_err(mrioc, @@ -1477,9 +1487,19 @@ static int mpi3mr_bring_ioc_ready(struct mpi3mr_ioc *mrioc) goto out_device_not_present; } msleep(100); - } while (--timeout); + elapsed_time_sec = jiffies_to_msecs(jiffies - start_time)/1000; + } while (elapsed_time_sec < mrioc->ready_timeout); out_failed: + elapsed_time_sec = jiffies_to_msecs(jiffies - start_time)/1000; + if ((retry < 2) && (elapsed_time_sec < (mrioc->ready_timeout - 60))) { + retry++; + + ioc_warn(mrioc, "retrying to bring IOC ready, retry_count:%d\n" + " elapsed time =%llu\n", retry, elapsed_time_sec); + + goto retry_bring_ioc_ready; + } ioc_state = mpi3mr_get_iocstate(mrioc); ioc_err(mrioc, "failed to bring to ready state, current state: %s\n", @@ -2671,7 +2691,7 @@ static void mpi3mr_watchdog_work(struct work_struct *work) return; } - if (mrioc->ts_update_counter++ >= MPI3MR_TSUPDATE_INTERVAL) { + if (mrioc->ts_update_counter++ >= mrioc->ts_update_interval) { mrioc->ts_update_counter = 0; mpi3mr_sync_timestamp(mrioc); } @@ -3845,6 +3865,29 @@ static int mpi3mr_repost_diag_bufs(struct mpi3mr_ioc *mrioc) } /** + * mpi3mr_read_tsu_interval - Update time stamp interval + * @mrioc: Adapter instance reference + * + * Update time stamp interval if its defined in driver page 1, + * otherwise use default value. + * + * Return: Nothing + */ +static void +mpi3mr_read_tsu_interval(struct mpi3mr_ioc *mrioc) +{ + struct mpi3_driver_page1 driver_pg1; + u16 pg_sz = sizeof(driver_pg1); + int retval = 0; + + mrioc->ts_update_interval = MPI3MR_TSUPDATE_INTERVAL; + + retval = mpi3mr_cfg_get_driver_pg1(mrioc, &driver_pg1, pg_sz); + if (!retval && driver_pg1.time_stamp_update) + mrioc->ts_update_interval = (driver_pg1.time_stamp_update * 60); +} + +/** * mpi3mr_print_ioc_info - Display controller information * @mrioc: Adapter instance reference * @@ -4140,6 +4183,7 @@ retry_init: goto out_failed_noretry; } + mpi3mr_read_tsu_interval(mrioc); mpi3mr_print_ioc_info(mrioc); if (!mrioc->cfg_page) { @@ -4321,6 +4365,7 @@ retry_init: goto out_failed_noretry; } + mpi3mr_read_tsu_interval(mrioc); mpi3mr_print_ioc_info(mrioc); if (is_resume) { diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index 9a24f7776d64..ed5046593fda 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -8898,9 +8898,8 @@ _base_check_ioc_facts_changes(struct MPT3SAS_ADAPTER *ioc) ioc->device_remove_in_progress, pd_handles_sz, GFP_KERNEL); if (!device_remove_in_progress) { ioc_info(ioc, - "Unable to allocate the memory for " - "device_remove_in_progress of sz: %d\n " - , pd_handles_sz); + "Unable to allocate the memory for device_remove_in_progress of sz: %d\n", + pd_handles_sz); return -ENOMEM; } memset(device_remove_in_progress + diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c index 728cced42b0e..f2a55aa5fe65 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c +++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c @@ -54,7 +54,7 @@ #include <linux/interrupt.h> #include <linux/raid_class.h> #include <linux/blk-mq-pci.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "mpt3sas_base.h" diff --git a/drivers/scsi/mpt3sas/mpt3sas_warpdrive.c b/drivers/scsi/mpt3sas/mpt3sas_warpdrive.c index 1d64e5056a8a..2b04f0852dec 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_warpdrive.c +++ b/drivers/scsi/mpt3sas/mpt3sas_warpdrive.c @@ -42,7 +42,7 @@ #include <linux/module.h> #include <linux/errno.h> #include <linux/types.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "mpt3sas_base.h" diff --git a/drivers/scsi/mvsas/mv_sas.h b/drivers/scsi/mvsas/mv_sas.h index 68df771e2975..19b01f7c4767 100644 --- a/drivers/scsi/mvsas/mv_sas.h +++ b/drivers/scsi/mvsas/mv_sas.h @@ -23,7 +23,7 @@ #include <linux/irq.h> #include <linux/slab.h> #include <linux/vmalloc.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <scsi/libsas.h> #include <scsi/scsi.h> #include <scsi/scsi_tcq.h> diff --git a/drivers/scsi/myrb.c b/drivers/scsi/myrb.c index bfc2b835e612..a7e64b867c8e 100644 --- a/drivers/scsi/myrb.c +++ b/drivers/scsi/myrb.c @@ -16,7 +16,7 @@ #include <linux/interrupt.h> #include <linux/pci.h> #include <linux/raid_class.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <scsi/scsi.h> #include <scsi/scsi_host.h> #include <scsi/scsi_device.h> diff --git a/drivers/scsi/myrs.c b/drivers/scsi/myrs.c index 3392feb15cb4..1469d0c54e45 100644 --- a/drivers/scsi/myrs.c +++ b/drivers/scsi/myrs.c @@ -17,7 +17,7 @@ #include <linux/interrupt.h> #include <linux/pci.h> #include <linux/raid_class.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <scsi/scsi.h> #include <scsi/scsi_host.h> #include <scsi/scsi_device.h> diff --git a/drivers/scsi/pm8001/pm8001_init.c b/drivers/scsi/pm8001/pm8001_init.c index 1e63cb6cd8e3..33e1eba62ca1 100644 --- a/drivers/scsi/pm8001/pm8001_init.c +++ b/drivers/scsi/pm8001/pm8001_init.c @@ -100,10 +100,12 @@ static void pm8001_map_queues(struct Scsi_Host *shost) struct pm8001_hba_info *pm8001_ha = sha->lldd_ha; struct blk_mq_queue_map *qmap = &shost->tag_set.map[HCTX_TYPE_DEFAULT]; - if (pm8001_ha->number_of_intr > 1) + if (pm8001_ha->number_of_intr > 1) { blk_mq_pci_map_queues(qmap, pm8001_ha->pdev, 1); + return; + } - return blk_mq_map_queues(qmap); + blk_mq_map_queues(qmap); } /* diff --git a/drivers/scsi/pm8001/pm80xx_hwi.c b/drivers/scsi/pm8001/pm80xx_hwi.c index 8fe886dc5e47..a9869cd8c4c0 100644 --- a/drivers/scsi/pm8001/pm80xx_hwi.c +++ b/drivers/scsi/pm8001/pm80xx_hwi.c @@ -2037,7 +2037,7 @@ mpi_ssp_completion(struct pm8001_hba_info *pm8001_ha, void *piomb) atomic_dec(&pm8001_dev->running_req); break; } - pm8001_dbg(pm8001_ha, IO, "scsi_status = 0x%x\n ", + pm8001_dbg(pm8001_ha, IO, "scsi_status = 0x%x\n", psspPayload->ssp_resp_iu.status); spin_lock_irqsave(&t->task_state_lock, flags); t->task_state_flags &= ~SAS_TASK_STATE_PENDING; diff --git a/drivers/scsi/pmcraid.c b/drivers/scsi/pmcraid.c index 72a4c6e3d0c8..4c5881917d76 100644 --- a/drivers/scsi/pmcraid.c +++ b/drivers/scsi/pmcraid.c @@ -1946,7 +1946,7 @@ static void pmcraid_soft_reset(struct pmcraid_cmd *cmd) } iowrite32(doorbell, pinstance->int_regs.host_ioa_interrupt_reg); - ioread32(pinstance->int_regs.host_ioa_interrupt_reg), + ioread32(pinstance->int_regs.host_ioa_interrupt_reg); int_reg = ioread32(pinstance->int_regs.ioa_host_interrupt_reg); pmcraid_info("Waiting for IOA to become operational %x:%x\n", diff --git a/drivers/scsi/qedf/qedf_io.c b/drivers/scsi/qedf/qedf_io.c index 054a51713d55..fcfc3bed02c6 100644 --- a/drivers/scsi/qedf/qedf_io.c +++ b/drivers/scsi/qedf/qedf_io.c @@ -310,7 +310,7 @@ struct qedf_ioreq *qedf_alloc_cmd(struct qedf_rport *fcport, u8 cmd_type) if (!free_sqes) { QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_IO, - "Returning NULL, free_sqes=%d.\n ", + "Returning NULL, free_sqes=%d.\n", free_sqes); goto out_failed; } diff --git a/drivers/scsi/qla2xxx/qla_dsd.h b/drivers/scsi/qla2xxx/qla_dsd.h index 20788054b91b..52e060f83b37 100644 --- a/drivers/scsi/qla2xxx/qla_dsd.h +++ b/drivers/scsi/qla2xxx/qla_dsd.h @@ -1,7 +1,7 @@ #ifndef _QLA_DSD_H_ #define _QLA_DSD_H_ -#include <asm/unaligned.h> +#include <linux/unaligned.h> /* 32-bit data segment descriptor (8 bytes) */ struct dsd32 { diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index d7551b1443e4..11eadb3bd36e 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -23,7 +23,7 @@ #include <linux/delay.h> #include <linux/list.h> #include <linux/workqueue.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <scsi/scsi.h> #include <scsi/scsi_host.h> #include <scsi/scsi_tcq.h> diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c index 7e7460a747a4..ceaf1c7b1d17 100644 --- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c +++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c @@ -24,7 +24,7 @@ #include <linux/string.h> #include <linux/configfs.h> #include <linux/ctype.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <scsi/scsi_host.h> #include <target/target_core_base.h> #include <target/target_core_fabric.h> diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c index ee69bd35889d..a77e0499b738 100644 --- a/drivers/scsi/scsi.c +++ b/drivers/scsi/scsi.c @@ -55,7 +55,7 @@ #include <linux/notifier.h> #include <linux/cpu.h> #include <linux/mutex.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <scsi/scsi.h> #include <scsi/scsi_cmnd.h> diff --git a/drivers/scsi/scsi_common.c b/drivers/scsi/scsi_common.c index 04749fde1636..e1a2a62b6910 100644 --- a/drivers/scsi/scsi_common.c +++ b/drivers/scsi/scsi_common.c @@ -9,7 +9,7 @@ #include <linux/errno.h> #include <linux/module.h> #include <uapi/linux/pr.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <scsi/scsi_common.h> MODULE_DESCRIPTION("SCSI functions used by both the initiator and the target code"); diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c index a9d8a9c62663..de15fc0df104 100644 --- a/drivers/scsi/scsi_debug.c +++ b/drivers/scsi/scsi_debug.c @@ -47,7 +47,7 @@ #include <net/checksum.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <scsi/scsi.h> #include <scsi/scsi_cmnd.h> @@ -2760,7 +2760,6 @@ static int resp_mode_sense(struct scsi_cmnd *scp, else bd_len = 0; alloc_len = msense_6 ? cmd[4] : get_unaligned_be16(cmd + 7); - memset(arr, 0, SDEBUG_MAX_MSENSE_SZ); if (0x3 == pcontrol) { /* Saving values not supported */ mk_sense_buffer(scp, ILLEGAL_REQUEST, SAVING_PARAMS_UNSUP, 0); return check_condition_result; diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index 612489afe8d2..10154d78e336 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -48,7 +48,7 @@ #include <trace/events/scsi.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /* * These should *probably* be handled by the host itself. diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 0561b318dade..adee6f60c966 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -23,7 +23,7 @@ #include <linux/blk-mq.h> #include <linux/blk-integrity.h> #include <linux/ratelimit.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <scsi/scsi.h> #include <scsi/scsi_cmnd.h> diff --git a/drivers/scsi/scsi_proto_test.c b/drivers/scsi/scsi_proto_test.c index 7fa0a78a2ad1..c093389edabb 100644 --- a/drivers/scsi/scsi_proto_test.c +++ b/drivers/scsi/scsi_proto_test.c @@ -3,7 +3,7 @@ * Copyright 2023 Google LLC */ #include <kunit/test.h> -#include <asm-generic/unaligned.h> +#include <linux/unaligned.h> #include <scsi/scsi_proto.h> static void test_scsi_proto(struct kunit *test) diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c index c0b72199b4fa..042329b74c6e 100644 --- a/drivers/scsi/scsi_scan.c +++ b/drivers/scsi/scsi_scan.c @@ -35,7 +35,7 @@ #include <linux/spinlock.h> #include <linux/async.h> #include <linux/slab.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <scsi/scsi.h> #include <scsi/scsi_cmnd.h> diff --git a/drivers/scsi/scsi_trace.c b/drivers/scsi/scsi_trace.c index 3e47c4472a80..b3baae91e7a2 100644 --- a/drivers/scsi/scsi_trace.c +++ b/drivers/scsi/scsi_trace.c @@ -5,7 +5,7 @@ */ #include <linux/kernel.h> #include <linux/trace_seq.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <trace/events/scsi.h> #define SERVICE_ACTION16(cdb) (cdb[1] & 0x1f) diff --git a/drivers/scsi/scsicam.c b/drivers/scsi/scsicam.c index dd69342bbe78..19e6c3852d50 100644 --- a/drivers/scsi/scsicam.c +++ b/drivers/scsi/scsicam.c @@ -18,7 +18,7 @@ #include <linux/blkdev.h> #include <linux/pagemap.h> #include <linux/msdos_partition.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <scsi/scsicam.h> diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 76f488ef6a7e..ca4bc0ac76ad 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -38,7 +38,6 @@ #include <linux/fs.h> #include <linux/kernel.h> #include <linux/mm.h> -#include <linux/bio-integrity.h> #include <linux/hdreg.h> #include <linux/errno.h> #include <linux/idr.h> @@ -58,7 +57,7 @@ #include <linux/pr.h> #include <linux/t10-pi.h> #include <linux/uaccess.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <scsi/scsi.h> #include <scsi/scsi_cmnd.h> @@ -3404,7 +3403,7 @@ static void sd_read_block_characteristics(struct scsi_disk *sdkp, rcu_read_lock(); vpd = rcu_dereference(sdkp->device->vpd_pgb1); - if (!vpd || vpd->len < 8) { + if (!vpd || vpd->len <= 8) { rcu_read_unlock(); return; } @@ -4093,9 +4092,38 @@ static int sd_start_stop_device(struct scsi_disk *sdkp, int start) { unsigned char cmd[6] = { START_STOP }; /* START_VALID */ struct scsi_sense_hdr sshdr; + struct scsi_failure failure_defs[] = { + { + /* Power on, reset, or bus device reset occurred */ + .sense = UNIT_ATTENTION, + .asc = 0x29, + .ascq = 0, + .result = SAM_STAT_CHECK_CONDITION, + }, + { + /* Power on occurred */ + .sense = UNIT_ATTENTION, + .asc = 0x29, + .ascq = 1, + .result = SAM_STAT_CHECK_CONDITION, + }, + { + /* SCSI bus reset */ + .sense = UNIT_ATTENTION, + .asc = 0x29, + .ascq = 2, + .result = SAM_STAT_CHECK_CONDITION, + }, + {} + }; + struct scsi_failures failures = { + .total_allowed = 3, + .failure_definitions = failure_defs, + }; const struct scsi_exec_args exec_args = { .sshdr = &sshdr, .req_flags = BLK_MQ_REQ_PM, + .failures = &failures, }; struct scsi_device *sdp = sdkp->device; int res; diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c index c8b9654d30f0..ee2b74238758 100644 --- a/drivers/scsi/sd_zbc.c +++ b/drivers/scsi/sd_zbc.c @@ -13,7 +13,7 @@ #include <linux/sched/mm.h> #include <linux/mutex.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <scsi/scsi.h> #include <scsi/scsi_cmnd.h> diff --git a/drivers/scsi/ses.c b/drivers/scsi/ses.c index e22c7f5e652b..2c61624cb4b0 100644 --- a/drivers/scsi/ses.c +++ b/drivers/scsi/ses.c @@ -9,7 +9,7 @@ #include <linux/module.h> #include <linux/kernel.h> #include <linux/enclosure.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <scsi/scsi.h> #include <scsi/scsi_cmnd.h> diff --git a/drivers/scsi/smartpqi/smartpqi_init.c b/drivers/scsi/smartpqi/smartpqi_init.c index 7fd5a8c813dc..870f37b70546 100644 --- a/drivers/scsi/smartpqi/smartpqi_init.c +++ b/drivers/scsi/smartpqi/smartpqi_init.c @@ -25,7 +25,7 @@ #include <scsi/scsi_device.h> #include <scsi/scsi_eh.h> #include <scsi/scsi_transport_sas.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "smartpqi.h" #include "smartpqi_sis.h" diff --git a/drivers/scsi/smartpqi/smartpqi_sas_transport.c b/drivers/scsi/smartpqi/smartpqi_sas_transport.c index a981d0377948..93e96705754e 100644 --- a/drivers/scsi/smartpqi/smartpqi_sas_transport.c +++ b/drivers/scsi/smartpqi/smartpqi_sas_transport.c @@ -14,7 +14,7 @@ #include <scsi/scsi_host.h> #include <scsi/scsi_cmnd.h> #include <scsi/scsi_transport_sas.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "smartpqi.h" static struct pqi_sas_phy *pqi_alloc_sas_phy(struct pqi_sas_port *pqi_sas_port) diff --git a/drivers/scsi/smartpqi/smartpqi_sis.c b/drivers/scsi/smartpqi/smartpqi_sis.c index ca1df36b83f7..ae5a264d062d 100644 --- a/drivers/scsi/smartpqi/smartpqi_sis.c +++ b/drivers/scsi/smartpqi/smartpqi_sis.c @@ -14,7 +14,7 @@ #include <linux/delay.h> #include <linux/pci.h> #include <scsi/scsi_device.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "smartpqi.h" #include "smartpqi_sis.h" diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c index 3f491019103e..198bec87bb8e 100644 --- a/drivers/scsi/sr.c +++ b/drivers/scsi/sr.c @@ -52,7 +52,7 @@ #include <linux/pm_runtime.h> #include <linux/uaccess.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <scsi/scsi.h> #include <scsi/scsi_dbg.h> diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c index 0d8ce1a92168..beb88f25dbb9 100644 --- a/drivers/scsi/st.c +++ b/drivers/scsi/st.c @@ -46,7 +46,7 @@ static const char *verstr = "20160209"; #include <linux/uaccess.h> #include <asm/dma.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <scsi/scsi.h> #include <scsi/scsi_dbg.h> @@ -834,6 +834,9 @@ static int flush_buffer(struct scsi_tape *STp, int seek_next) int backspace, result; struct st_partstat *STps; + if (STp->ready != ST_READY) + return 0; + /* * If there was a bus reset, block further access * to this device. @@ -841,8 +844,6 @@ static int flush_buffer(struct scsi_tape *STp, int seek_next) if (STp->pos_unknown) return (-EIO); - if (STp->ready != ST_READY) - return 0; STps = &(STp->ps[STp->partition]); if (STps->rw == ST_WRITING) /* Writing */ return st_flush_write_buffer(STp); diff --git a/drivers/scsi/zalon.c b/drivers/scsi/zalon.c index 22d412cab91d..15602ec862e3 100644 --- a/drivers/scsi/zalon.c +++ b/drivers/scsi/zalon.c @@ -139,7 +139,7 @@ zalon_probe(struct parisc_device *dev) return -ENODEV; if (request_irq(dev->irq, ncr53c8xx_intr, IRQF_SHARED, "zalon", host)) { - dev_printk(KERN_ERR, &dev->dev, "irq problem with %d, detaching\n ", + dev_printk(KERN_ERR, &dev->dev, "irq problem with %d, detaching\n", dev->irq); goto fail; } diff --git a/drivers/soc/qcom/socinfo.c b/drivers/soc/qcom/socinfo.c index 24c3971f2ef1..64fc4f41da77 100644 --- a/drivers/soc/qcom/socinfo.c +++ b/drivers/soc/qcom/socinfo.c @@ -17,7 +17,7 @@ #include <linux/sys_soc.h> #include <linux/types.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <dt-bindings/arm/qcom,ids.h> diff --git a/drivers/spi/atmel-quadspi.c b/drivers/spi/atmel-quadspi.c index 4f288f07e38f..95cdfc28361e 100644 --- a/drivers/spi/atmel-quadspi.c +++ b/drivers/spi/atmel-quadspi.c @@ -377,7 +377,7 @@ static int atmel_qspi_set_cfg(struct atmel_qspi *aq, */ if (!(aq->mr & QSPI_MR_SMM)) { aq->mr |= QSPI_MR_SMM; - atmel_qspi_write(aq->scr, aq, QSPI_MR); + atmel_qspi_write(aq->mr, aq, QSPI_MR); } /* Clear pending interrupts */ diff --git a/drivers/spi/spi-airoha-snfi.c b/drivers/spi/spi-airoha-snfi.c index 94458df53eae..1369691a997b 100644 --- a/drivers/spi/spi-airoha-snfi.c +++ b/drivers/spi/spi-airoha-snfi.c @@ -23,7 +23,7 @@ #include <linux/spi/spi.h> #include <linux/spi/spi-mem.h> #include <linux/types.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /* SPI */ #define REG_SPI_CTRL_BASE 0x1FA10000 diff --git a/drivers/spi/spi-cadence.c b/drivers/spi/spi-cadence.c index e07e081de5ea..3c87d2bf786a 100644 --- a/drivers/spi/spi-cadence.c +++ b/drivers/spi/spi-cadence.c @@ -678,8 +678,8 @@ static int cdns_spi_probe(struct platform_device *pdev) clk_dis_all: if (!spi_controller_is_target(ctlr)) { - pm_runtime_set_suspended(&pdev->dev); pm_runtime_disable(&pdev->dev); + pm_runtime_set_suspended(&pdev->dev); } remove_ctlr: spi_controller_put(ctlr); @@ -701,8 +701,10 @@ static void cdns_spi_remove(struct platform_device *pdev) cdns_spi_write(xspi, CDNS_SPI_ER, CDNS_SPI_ER_DISABLE); - pm_runtime_set_suspended(&pdev->dev); - pm_runtime_disable(&pdev->dev); + if (!spi_controller_is_target(ctlr)) { + pm_runtime_disable(&pdev->dev); + pm_runtime_set_suspended(&pdev->dev); + } spi_unregister_controller(ctlr); } diff --git a/drivers/spi/spi-dln2.c b/drivers/spi/spi-dln2.c index d319dc357fef..4ba1d9245c9f 100644 --- a/drivers/spi/spi-dln2.c +++ b/drivers/spi/spi-dln2.c @@ -12,7 +12,7 @@ #include <linux/mfd/dln2.h> #include <linux/spi/spi.h> #include <linux/pm_runtime.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define DLN2_SPI_MODULE_ID 0x02 #define DLN2_SPI_CMD(cmd) DLN2_CMD(cmd, DLN2_SPI_MODULE_ID) diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c index 85bd1a82a34e..4c31d36f3130 100644 --- a/drivers/spi/spi-imx.c +++ b/drivers/spi/spi-imx.c @@ -1865,8 +1865,8 @@ out_register_controller: spi_imx_sdma_exit(spi_imx); out_runtime_pm_put: pm_runtime_dont_use_autosuspend(spi_imx->dev); - pm_runtime_set_suspended(&pdev->dev); pm_runtime_disable(spi_imx->dev); + pm_runtime_set_suspended(&pdev->dev); clk_disable_unprepare(spi_imx->clk_ipg); out_put_per: diff --git a/drivers/spi/spi-npcm-pspi.c b/drivers/spi/spi-npcm-pspi.c index a7feb20b06ee..30aa37b0c3b8 100644 --- a/drivers/spi/spi-npcm-pspi.c +++ b/drivers/spi/spi-npcm-pspi.c @@ -12,7 +12,7 @@ #include <linux/spi/spi.h> #include <linux/reset.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/regmap.h> #include <linux/mfd/syscon.h> diff --git a/drivers/spi/spi-orion.c b/drivers/spi/spi-orion.c index eee9ff4bfa5b..4730e4ba8901 100644 --- a/drivers/spi/spi-orion.c +++ b/drivers/spi/spi-orion.c @@ -18,7 +18,7 @@ #include <linux/of_address.h> #include <linux/clk.h> #include <linux/sizes.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define DRIVER_NAME "orion_spi" diff --git a/drivers/spi/spi-rpc-if.c b/drivers/spi/spi-rpc-if.c index b468a95972bf..c24dad51a0e9 100644 --- a/drivers/spi/spi-rpc-if.c +++ b/drivers/spi/spi-rpc-if.c @@ -14,7 +14,7 @@ #include <memory/renesas-rpc-if.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> static void rpcif_spi_mem_prepare(struct spi_device *spi_dev, const struct spi_mem_op *spi_op, diff --git a/drivers/spi/spi-s3c64xx.c b/drivers/spi/spi-s3c64xx.c index 51a002b3f518..8c9e5e97041f 100644 --- a/drivers/spi/spi-s3c64xx.c +++ b/drivers/spi/spi-s3c64xx.c @@ -245,7 +245,7 @@ static void s3c64xx_flush_fifo(struct s3c64xx_spi_driver_data *sdd) loops = msecs_to_loops(1); do { val = readl(regs + S3C64XX_SPI_STATUS); - } while (TX_FIFO_LVL(val, sdd) && loops--); + } while (TX_FIFO_LVL(val, sdd) && --loops); if (loops == 0) dev_warn(&sdd->pdev->dev, "Timed out flushing TX FIFO\n"); @@ -258,7 +258,7 @@ static void s3c64xx_flush_fifo(struct s3c64xx_spi_driver_data *sdd) readl(regs + S3C64XX_SPI_RX_DATA); else break; - } while (loops--); + } while (--loops); if (loops == 0) dev_warn(&sdd->pdev->dev, "Timed out flushing RX FIFO\n"); diff --git a/drivers/spi/spi-sh-msiof.c b/drivers/spi/spi-sh-msiof.c index 6f12e4fb2e2e..3519656515ea 100644 --- a/drivers/spi/spi-sh-msiof.c +++ b/drivers/spi/spi-sh-msiof.c @@ -27,7 +27,7 @@ #include <linux/spi/sh_msiof.h> #include <linux/spi/spi.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define SH_MSIOF_FLAG_FIXED_DTDL_200 BIT(0) diff --git a/drivers/spi/spi-uniphier.c b/drivers/spi/spi-uniphier.c index 4a18cf896194..07b155980e71 100644 --- a/drivers/spi/spi-uniphier.c +++ b/drivers/spi/spi-uniphier.c @@ -15,7 +15,7 @@ #include <linux/platform_device.h> #include <linux/spi/spi.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define SSI_TIMEOUT_MS 2000 #define SSI_POLL_TIMEOUT_US 200 diff --git a/drivers/spi/spi-xcomm.c b/drivers/spi/spi-xcomm.c index 846f00e23b71..3bd0149d8f4e 100644 --- a/drivers/spi/spi-xcomm.c +++ b/drivers/spi/spi-xcomm.c @@ -12,7 +12,7 @@ #include <linux/i2c.h> #include <linux/gpio/driver.h> #include <linux/spi/spi.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define SPI_XCOMM_SETTINGS_LEN_OFFSET 10 #define SPI_XCOMM_SETTINGS_3WIRE BIT(6) diff --git a/drivers/staging/media/av7110/av7110.c b/drivers/staging/media/av7110/av7110.c index 728b3892a20c..bc9a2a40afcb 100644 --- a/drivers/staging/media/av7110/av7110.c +++ b/drivers/staging/media/av7110/av7110.c @@ -32,7 +32,7 @@ #include <linux/i2c.h> #include <linux/kthread.h> #include <linux/slab.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <asm/byteorder.h> #include <linux/dvb/frontend.h> diff --git a/drivers/staging/rtl8192e/rtl819x_BAProc.c b/drivers/staging/rtl8192e/rtl819x_BAProc.c index 834329886ea2..c400d4f8ff9a 100644 --- a/drivers/staging/rtl8192e/rtl819x_BAProc.c +++ b/drivers/staging/rtl8192e/rtl819x_BAProc.c @@ -5,7 +5,7 @@ * Contact Information: wlanfae <wlanfae@realtek.com> */ #include <asm/byteorder.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/etherdevice.h> #include "rtllib.h" #include "rtl819x_BA.h" diff --git a/drivers/staging/rtl8723bs/core/rtw_ap.c b/drivers/staging/rtl8723bs/core/rtw_ap.c index e55b4f7e0aef..a6dc88dd4ba1 100644 --- a/drivers/staging/rtl8723bs/core/rtw_ap.c +++ b/drivers/staging/rtl8723bs/core/rtw_ap.c @@ -6,7 +6,7 @@ ******************************************************************************/ #include <drv_types.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> void init_mlme_ap_info(struct adapter *padapter) { diff --git a/drivers/staging/rtl8723bs/core/rtw_ieee80211.c b/drivers/staging/rtl8723bs/core/rtw_ieee80211.c index 5a76069a8222..0ed420f3d096 100644 --- a/drivers/staging/rtl8723bs/core/rtw_ieee80211.c +++ b/drivers/staging/rtl8723bs/core/rtw_ieee80211.c @@ -7,7 +7,7 @@ #include <drv_types.h> #include <linux/of.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> u8 RTW_WPA_OUI_TYPE[] = { 0x00, 0x50, 0xf2, 1 }; u16 RTW_WPA_VERSION = 1; diff --git a/drivers/staging/rtl8723bs/core/rtw_mlme_ext.c b/drivers/staging/rtl8723bs/core/rtw_mlme_ext.c index bbdd5fce28a1..4d4bec47d187 100644 --- a/drivers/staging/rtl8723bs/core/rtw_mlme_ext.c +++ b/drivers/staging/rtl8723bs/core/rtw_mlme_ext.c @@ -8,7 +8,7 @@ #include <rtw_wifi_regd.h> #include <hal_btcoex.h> #include <linux/kernel.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> static struct mlme_handler mlme_sta_tbl[] = { {WIFI_ASSOCREQ, "OnAssocReq", &OnAssocReq}, diff --git a/drivers/staging/rtl8723bs/core/rtw_recv.c b/drivers/staging/rtl8723bs/core/rtw_recv.c index b30f026789b6..a389ba5ecc6f 100644 --- a/drivers/staging/rtl8723bs/core/rtw_recv.c +++ b/drivers/staging/rtl8723bs/core/rtw_recv.c @@ -8,7 +8,7 @@ #include <linux/jiffies.h> #include <rtw_recv.h> #include <net/cfg80211.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> static u8 SNAP_ETH_TYPE_IPX[2] = {0x81, 0x37}; static u8 SNAP_ETH_TYPE_APPLETALK_AARP[2] = {0x80, 0xf3}; diff --git a/drivers/staging/rtl8723bs/os_dep/recv_linux.c b/drivers/staging/rtl8723bs/os_dep/recv_linux.c index 746f45cf9aac..ca808ded61ac 100644 --- a/drivers/staging/rtl8723bs/os_dep/recv_linux.c +++ b/drivers/staging/rtl8723bs/os_dep/recv_linux.c @@ -7,7 +7,7 @@ #include <drv_types.h> #include <linux/jiffies.h> #include <net/cfg80211.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> void rtw_os_free_recvframe(union recv_frame *precvframe) { diff --git a/drivers/target/iscsi/cxgbit/cxgbit_target.c b/drivers/target/iscsi/cxgbit/cxgbit_target.c index acfc39683c87..3698f2eb097e 100644 --- a/drivers/target/iscsi/cxgbit/cxgbit_target.c +++ b/drivers/target/iscsi/cxgbit/cxgbit_target.c @@ -7,7 +7,7 @@ #include <linux/kthread.h> #include <linux/sched/signal.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <net/tcp.h> #include <target/target_core_base.h> #include <target/target_core_fabric.h> diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index 1d25e64b068a..6002283cbeba 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -17,7 +17,7 @@ #include <linux/idr.h> #include <linux/delay.h> #include <linux/sched/signal.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/inet.h> #include <net/ipv6.h> #include <scsi/scsi_proto.h> diff --git a/drivers/target/iscsi/iscsi_target_tmr.c b/drivers/target/iscsi/iscsi_target_tmr.c index 9c4aa01b6351..f60b156ede12 100644 --- a/drivers/target/iscsi/iscsi_target_tmr.c +++ b/drivers/target/iscsi/iscsi_target_tmr.c @@ -8,7 +8,7 @@ * ******************************************************************************/ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <scsi/scsi_proto.h> #include <scsi/iscsi_proto.h> #include <target/target_core_base.h> diff --git a/drivers/target/sbp/sbp_target.c b/drivers/target/sbp/sbp_target.c index b604fcae21e1..3b89b5a70331 100644 --- a/drivers/target/sbp/sbp_target.c +++ b/drivers/target/sbp/sbp_target.c @@ -23,7 +23,7 @@ #include <target/target_core_base.h> #include <target/target_core_backend.h> #include <target/target_core_fabric.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "sbp_target.h" diff --git a/drivers/target/target_core_alua.c b/drivers/target/target_core_alua.c index 01751faad386..10250aca5a81 100644 --- a/drivers/target/target_core_alua.c +++ b/drivers/target/target_core_alua.c @@ -19,7 +19,7 @@ #include <linux/file.h> #include <linux/fs.h> #include <scsi/scsi_proto.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <target/target_core_base.h> #include <target/target_core_backend.h> diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c index bf4892544cfd..7d43d92c44d4 100644 --- a/drivers/target/target_core_device.c +++ b/drivers/target/target_core_device.c @@ -21,7 +21,7 @@ #include <linux/in.h> #include <linux/export.h> #include <linux/t10-pi.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <net/sock.h> #include <net/tcp.h> #include <scsi/scsi_common.h> diff --git a/drivers/target/target_core_fabric_lib.c b/drivers/target/target_core_fabric_lib.c index 6600ae44f29d..43f47e3aa448 100644 --- a/drivers/target/target_core_fabric_lib.c +++ b/drivers/target/target_core_fabric_lib.c @@ -21,7 +21,7 @@ #include <linux/ctype.h> #include <linux/spinlock.h> #include <linux/export.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <scsi/scsi_proto.h> diff --git a/drivers/target/target_core_file.c b/drivers/target/target_core_file.c index 94e6cd4e7e43..2d78ef74633c 100644 --- a/drivers/target/target_core_file.c +++ b/drivers/target/target_core_file.c @@ -22,7 +22,7 @@ #include <linux/uio.h> #include <linux/scatterlist.h> #include <scsi/scsi_proto.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <target/target_core_base.h> #include <target/target_core_backend.h> diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c index a3e09adc4e76..c8dc92a7d63e 100644 --- a/drivers/target/target_core_iblock.c +++ b/drivers/target/target_core_iblock.c @@ -26,7 +26,7 @@ #include <linux/pr.h> #include <scsi/scsi_proto.h> #include <scsi/scsi_common.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <target/target_core_base.h> #include <target/target_core_backend.h> diff --git a/drivers/target/target_core_pr.c b/drivers/target/target_core_pr.c index 80b7d85030d0..4f4ad6af416c 100644 --- a/drivers/target/target_core_pr.c +++ b/drivers/target/target_core_pr.c @@ -19,7 +19,7 @@ #include <linux/fcntl.h> #include <linux/fs.h> #include <scsi/scsi_proto.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <target/target_core_base.h> #include <target/target_core_backend.h> diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c index f98ebb18666b..440e07b1d5cd 100644 --- a/drivers/target/target_core_pscsi.c +++ b/drivers/target/target_core_pscsi.c @@ -20,7 +20,7 @@ #include <linux/cdrom.h> #include <linux/ratelimit.h> #include <linux/module.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <scsi/scsi_device.h> #include <scsi/scsi_host.h> diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c index 6a02561cc20c..fe8beb7dbab1 100644 --- a/drivers/target/target_core_sbc.c +++ b/drivers/target/target_core_sbc.c @@ -12,7 +12,7 @@ #include <linux/ratelimit.h> #include <linux/crc-t10dif.h> #include <linux/t10-pi.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <scsi/scsi_proto.h> #include <scsi/scsi_tcq.h> diff --git a/drivers/target/target_core_spc.c b/drivers/target/target_core_spc.c index 50290abc07bc..ea14a3835681 100644 --- a/drivers/target/target_core_spc.c +++ b/drivers/target/target_core_spc.c @@ -9,7 +9,7 @@ #include <linux/kernel.h> #include <linux/module.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <scsi/scsi_proto.h> #include <scsi/scsi_common.h> diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index 73d0d6133ac8..05d29201b730 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -22,7 +22,7 @@ #include <linux/module.h> #include <linux/ratelimit.h> #include <linux/vmalloc.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <net/sock.h> #include <net/tcp.h> #include <scsi/scsi_proto.h> diff --git a/drivers/target/target_core_xcopy.c b/drivers/target/target_core_xcopy.c index 4128631c9dfd..877ce58c0a70 100644 --- a/drivers/target/target_core_xcopy.c +++ b/drivers/target/target_core_xcopy.c @@ -19,7 +19,7 @@ #include <linux/configfs.h> #include <linux/ratelimit.h> #include <scsi/scsi_proto.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <target/target_core_base.h> #include <target/target_core_backend.h> diff --git a/drivers/target/tcm_fc/tfc_cmd.c b/drivers/target/tcm_fc/tfc_cmd.c index 21783cd71c15..34ab628809e8 100644 --- a/drivers/target/tcm_fc/tfc_cmd.c +++ b/drivers/target/tcm_fc/tfc_cmd.c @@ -16,7 +16,7 @@ #include <linux/configfs.h> #include <linux/ctype.h> #include <linux/hash.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <scsi/scsi_tcq.h> #include <scsi/libfc.h> diff --git a/drivers/target/tcm_fc/tfc_conf.c b/drivers/target/tcm_fc/tfc_conf.c index 5ee03d1cba2b..639fc358ed0f 100644 --- a/drivers/target/tcm_fc/tfc_conf.c +++ b/drivers/target/tcm_fc/tfc_conf.c @@ -25,7 +25,7 @@ #include <linux/configfs.h> #include <linux/kernel.h> #include <linux/ctype.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <scsi/libfc.h> #include <target/target_core_base.h> diff --git a/drivers/target/tcm_fc/tfc_io.c b/drivers/target/tcm_fc/tfc_io.c index bbe2e29612fa..45329284f52f 100644 --- a/drivers/target/tcm_fc/tfc_io.c +++ b/drivers/target/tcm_fc/tfc_io.c @@ -26,7 +26,7 @@ #include <linux/ctype.h> #include <linux/hash.h> #include <linux/ratelimit.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <scsi/libfc.h> #include <target/target_core_base.h> diff --git a/drivers/target/tcm_fc/tfc_sess.c b/drivers/target/tcm_fc/tfc_sess.c index 593540da9346..d6afaba52ea5 100644 --- a/drivers/target/tcm_fc/tfc_sess.c +++ b/drivers/target/tcm_fc/tfc_sess.c @@ -19,7 +19,7 @@ #include <linux/rcupdate.h> #include <linux/rculist.h> #include <linux/kref.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <scsi/libfc.h> #include <target/target_core_base.h> diff --git a/drivers/thermal/qcom/qcom-spmi-adc-tm5.c b/drivers/thermal/qcom/qcom-spmi-adc-tm5.c index 7c9f4023babc..5e94a45eba3e 100644 --- a/drivers/thermal/qcom/qcom-spmi-adc-tm5.c +++ b/drivers/thermal/qcom/qcom-spmi-adc-tm5.c @@ -18,7 +18,7 @@ #include <linux/regmap.h> #include <linux/thermal.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "../thermal_hwmon.h" diff --git a/drivers/tty/serial/max3100.c b/drivers/tty/serial/max3100.c index fda63918d1eb..cde5f1c86353 100644 --- a/drivers/tty/serial/max3100.c +++ b/drivers/tty/serial/max3100.c @@ -32,7 +32,7 @@ #include <linux/tty.h> #include <linux/types.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define MAX3100_C (1<<14) #define MAX3100_D (0<<14) diff --git a/drivers/tty/vt/vc_screen.c b/drivers/tty/vt/vc_screen.c index da33c6c4691c..79b33d998d43 100644 --- a/drivers/tty/vt/vc_screen.c +++ b/drivers/tty/vt/vc_screen.c @@ -48,7 +48,7 @@ #include <linux/uaccess.h> #include <asm/byteorder.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define HEADER_SIZE 4u #define CON_BUF_SIZE (IS_ENABLED(CONFIG_BASE_SMALL) ? 256 : PAGE_SIZE) diff --git a/drivers/ufs/core/ufs-mcq.c b/drivers/ufs/core/ufs-mcq.c index 5891cdacd0b3..8402151330fe 100644 --- a/drivers/ufs/core/ufs-mcq.c +++ b/drivers/ufs/core/ufs-mcq.c @@ -7,7 +7,7 @@ * Can Guo <quic_cang@quicinc.com> */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/dma-mapping.h> #include <linux/module.h> #include <linux/platform_device.h> diff --git a/drivers/ufs/core/ufs-sysfs.c b/drivers/ufs/core/ufs-sysfs.c index fe313800aed0..265f21133b63 100644 --- a/drivers/ufs/core/ufs-sysfs.c +++ b/drivers/ufs/core/ufs-sysfs.c @@ -4,7 +4,7 @@ #include <linux/err.h> #include <linux/string.h> #include <linux/bitfield.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <ufs/ufs.h> #include <ufs/unipro.h> diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index 24a32e2fd75e..fc55fdab526b 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -36,7 +36,7 @@ #include "ufs-fault-injection.h" #include "ufs_bsg.h" #include "ufshcd-crypto.h" -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define CREATE_TRACE_POINTS #include "ufs_trace.h" diff --git a/drivers/ufs/host/ufs-exynos.c b/drivers/ufs/host/ufs-exynos.c index 9ec318ef52bf..5867e6338562 100644 --- a/drivers/ufs/host/ufs-exynos.c +++ b/drivers/ufs/host/ufs-exynos.c @@ -8,7 +8,7 @@ * */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <crypto/aes.h> #include <linux/arm-smccc.h> #include <linux/clk.h> diff --git a/drivers/ufs/host/ufs-qcom.c b/drivers/ufs/host/ufs-qcom.c index c87fdc849c62..ecdfff2456e3 100644 --- a/drivers/ufs/host/ufs-qcom.c +++ b/drivers/ufs/host/ufs-qcom.c @@ -93,7 +93,7 @@ static const struct __ufs_qcom_bw_table { [MODE_HS_RB][UFS_HS_G3][UFS_LANE_2] = { 1492582, 204800 }, [MODE_HS_RB][UFS_HS_G4][UFS_LANE_2] = { 2915200, 409600 }, [MODE_HS_RB][UFS_HS_G5][UFS_LANE_2] = { 5836800, 819200 }, - [MODE_MAX][0][0] = { 7643136, 307200 }, + [MODE_MAX][0][0] = { 7643136, 819200 }, }; static void ufs_qcom_get_default_testbus_cfg(struct ufs_qcom_host *host); diff --git a/drivers/usb/atm/cxacru.c b/drivers/usb/atm/cxacru.c index 8f3b9a0a38e1..0dd85d2635b9 100644 --- a/drivers/usb/atm/cxacru.c +++ b/drivers/usb/atm/cxacru.c @@ -24,7 +24,7 @@ #include <linux/device.h> #include <linux/firmware.h> #include <linux/mutex.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "usbatm.h" diff --git a/drivers/usb/atm/ueagle-atm.c b/drivers/usb/atm/ueagle-atm.c index 16703815be0c..e8e43c38aa1b 100644 --- a/drivers/usb/atm/ueagle-atm.c +++ b/drivers/usb/atm/ueagle-atm.c @@ -25,7 +25,7 @@ #include <linux/slab.h> #include <linux/kernel.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "usbatm.h" diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index 605fea461102..6b37d1c47fce 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -35,7 +35,7 @@ #include <linux/usb.h> #include <linux/usb/cdc.h> #include <asm/byteorder.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/idr.h> #include <linux/list.h> diff --git a/drivers/usb/class/cdc-wdm.c b/drivers/usb/class/cdc-wdm.c index 6830be4419e2..86ee39db013f 100644 --- a/drivers/usb/class/cdc-wdm.c +++ b/drivers/usb/class/cdc-wdm.c @@ -26,7 +26,7 @@ #include <linux/usb/cdc.h> #include <linux/wwan.h> #include <asm/byteorder.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/usb/cdc-wdm.h> #define DRIVER_AUTHOR "Oliver Neukum" diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c index 1ff7d901fede..500dc35e6477 100644 --- a/drivers/usb/core/hcd.c +++ b/drivers/usb/core/hcd.c @@ -24,7 +24,7 @@ #include <linux/mutex.h> #include <asm/irq.h> #include <asm/byteorder.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/platform_device.h> #include <linux/workqueue.h> #include <linux/pm_runtime.h> diff --git a/drivers/usb/fotg210/fotg210-hcd.c b/drivers/usb/fotg210/fotg210-hcd.c index 8c5aaf860635..3d404d19a205 100644 --- a/drivers/usb/fotg210/fotg210-hcd.c +++ b/drivers/usb/fotg210/fotg210-hcd.c @@ -36,7 +36,7 @@ #include <asm/byteorder.h> #include <asm/irq.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "fotg210.h" diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c index f45d5bedda68..f25dd2cb5d03 100644 --- a/drivers/usb/gadget/composite.c +++ b/drivers/usb/gadget/composite.c @@ -19,7 +19,7 @@ #include <linux/usb/composite.h> #include <linux/usb/otg.h> #include <linux/usb/webusb.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "u_os_desc.h" diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index c626bb73ea59..2920f8000bbd 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -28,7 +28,7 @@ #include <linux/sched/signal.h> #include <linux/uio.h> #include <linux/vmalloc.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/usb/ccid.h> #include <linux/usb/composite.h> diff --git a/drivers/usb/gadget/function/f_mass_storage.c b/drivers/usb/gadget/function/f_mass_storage.c index e11d8c0edf06..08e0d1c511e8 100644 --- a/drivers/usb/gadget/function/f_mass_storage.c +++ b/drivers/usb/gadget/function/f_mass_storage.c @@ -188,7 +188,7 @@ #include <linux/freezer.h> #include <linux/module.h> #include <linux/uaccess.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/usb/ch9.h> #include <linux/usb/gadget.h> diff --git a/drivers/usb/gadget/function/f_printer.c b/drivers/usb/gadget/function/f_printer.c index ef2ffde625c3..d295ade8fa67 100644 --- a/drivers/usb/gadget/function/f_printer.c +++ b/drivers/usb/gadget/function/f_printer.c @@ -37,7 +37,7 @@ #include <linux/io.h> #include <linux/irq.h> #include <linux/uaccess.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/usb/ch9.h> #include <linux/usb/composite.h> diff --git a/drivers/usb/gadget/function/f_tcm.c b/drivers/usb/gadget/function/f_tcm.c index 90906d714736..15bb3aa12aa8 100644 --- a/drivers/usb/gadget/function/f_tcm.c +++ b/drivers/usb/gadget/function/f_tcm.c @@ -19,7 +19,7 @@ #include <scsi/scsi_tcq.h> #include <target/target_core_base.h> #include <target/target_core_fabric.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "tcm.h" #include "u_tcm.h" diff --git a/drivers/usb/gadget/function/rndis.c b/drivers/usb/gadget/function/rndis.c index 12c5d9cf450c..afd75d72412c 100644 --- a/drivers/usb/gadget/function/rndis.c +++ b/drivers/usb/gadget/function/rndis.c @@ -31,7 +31,7 @@ #include <asm/io.h> #include <asm/byteorder.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "u_rndis.h" diff --git a/drivers/usb/gadget/function/storage_common.h b/drivers/usb/gadget/function/storage_common.h index 0a544a82cbf8..ced5d2b09234 100644 --- a/drivers/usb/gadget/function/storage_common.h +++ b/drivers/usb/gadget/function/storage_common.h @@ -5,7 +5,7 @@ #include <linux/device.h> #include <linux/usb/storage.h> #include <scsi/scsi.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #ifndef DEBUG #undef VERBOSE_DEBUG diff --git a/drivers/usb/gadget/function/uvc_video.c b/drivers/usb/gadget/function/uvc_video.c index a9edd60fbbf7..57a851151225 100644 --- a/drivers/usb/gadget/function/uvc_video.c +++ b/drivers/usb/gadget/function/uvc_video.c @@ -12,7 +12,7 @@ #include <linux/usb/ch9.h> #include <linux/usb/gadget.h> #include <linux/usb/video.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <media/v4l2-dev.h> diff --git a/drivers/usb/gadget/legacy/tcm_usb_gadget.c b/drivers/usb/gadget/legacy/tcm_usb_gadget.c index 40870227999a..fc1e06246d9d 100644 --- a/drivers/usb/gadget/legacy/tcm_usb_gadget.c +++ b/drivers/usb/gadget/legacy/tcm_usb_gadget.c @@ -19,7 +19,7 @@ #include <scsi/scsi_tcq.h> #include <target/target_core_base.h> #include <target/target_core_fabric.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "u_tcm.h" diff --git a/drivers/usb/gadget/u_os_desc.h b/drivers/usb/gadget/u_os_desc.h index 5d7d35c8cc31..f8b9f0faa9b1 100644 --- a/drivers/usb/gadget/u_os_desc.h +++ b/drivers/usb/gadget/u_os_desc.h @@ -13,7 +13,7 @@ #ifndef __U_OS_DESC_H__ #define __U_OS_DESC_H__ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/nls.h> #define USB_EXT_PROP_DW_SIZE 0 diff --git a/drivers/usb/gadget/udc/bdc/bdc.h b/drivers/usb/gadget/udc/bdc/bdc.h index 8d00b1239f21..2f4abf6f8f77 100644 --- a/drivers/usb/gadget/udc/bdc/bdc.h +++ b/drivers/usb/gadget/udc/bdc/bdc.h @@ -20,7 +20,7 @@ #include <linux/debugfs.h> #include <linux/usb/ch9.h> #include <linux/usb/gadget.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define BRCM_BDC_NAME "bdc" #define BRCM_BDC_DESC "Broadcom USB Device Controller driver" diff --git a/drivers/usb/gadget/udc/bdc/bdc_ep.c b/drivers/usb/gadget/udc/bdc/bdc_ep.c index fa88f210ecd5..f995cfa9b99e 100644 --- a/drivers/usb/gadget/udc/bdc/bdc_ep.c +++ b/drivers/usb/gadget/udc/bdc/bdc_ep.c @@ -30,7 +30,7 @@ #include <linux/pm.h> #include <linux/io.h> #include <linux/irq.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/platform_device.h> #include <linux/usb/composite.h> diff --git a/drivers/usb/gadget/udc/bdc/bdc_udc.c b/drivers/usb/gadget/udc/bdc/bdc_udc.c index 53ffaf4e2e37..23826fd7a8e6 100644 --- a/drivers/usb/gadget/udc/bdc/bdc_udc.c +++ b/drivers/usb/gadget/udc/bdc/bdc_udc.c @@ -29,7 +29,7 @@ #include <linux/pm.h> #include <linux/io.h> #include <linux/irq.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/platform_device.h> #include "bdc.h" diff --git a/drivers/usb/gadget/udc/cdns2/cdns2-ep0.c b/drivers/usb/gadget/udc/cdns2/cdns2-ep0.c index fa12a5d46f2e..a5a9d395fd0d 100644 --- a/drivers/usb/gadget/udc/cdns2/cdns2-ep0.c +++ b/drivers/usb/gadget/udc/cdns2/cdns2-ep0.c @@ -8,7 +8,7 @@ */ #include <linux/usb/composite.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "cdns2-gadget.h" #include "cdns2-trace.h" diff --git a/drivers/usb/gadget/udc/dummy_hcd.c b/drivers/usb/gadget/udc/dummy_hcd.c index ff7bee78bcc4..8820d9924448 100644 --- a/drivers/usb/gadget/udc/dummy_hcd.c +++ b/drivers/usb/gadget/udc/dummy_hcd.c @@ -42,7 +42,7 @@ #include <asm/byteorder.h> #include <linux/io.h> #include <asm/irq.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define DRIVER_DESC "USB Host+Gadget Emulator" #define DRIVER_VERSION "02 May 2005" diff --git a/drivers/usb/gadget/udc/fsl_udc_core.c b/drivers/usb/gadget/udc/fsl_udc_core.c index 3432ebfae978..0cabd4eee6ac 100644 --- a/drivers/usb/gadget/udc/fsl_udc_core.c +++ b/drivers/usb/gadget/udc/fsl_udc_core.c @@ -39,7 +39,7 @@ #include <asm/byteorder.h> #include <asm/io.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <asm/dma.h> #include "fsl_usb2_udc.h" diff --git a/drivers/usb/gadget/udc/goku_udc.c b/drivers/usb/gadget/udc/goku_udc.c index 5ffb3d5c635b..b860c2e76449 100644 --- a/drivers/usb/gadget/udc/goku_udc.c +++ b/drivers/usb/gadget/udc/goku_udc.c @@ -40,7 +40,7 @@ #include <asm/byteorder.h> #include <asm/io.h> #include <asm/irq.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "goku_udc.h" diff --git a/drivers/usb/gadget/udc/mv_udc_core.c b/drivers/usb/gadget/udc/mv_udc_core.c index 78308b64955d..71012b282891 100644 --- a/drivers/usb/gadget/udc/mv_udc_core.c +++ b/drivers/usb/gadget/udc/mv_udc_core.c @@ -30,7 +30,7 @@ #include <linux/platform_device.h> #include <linux/clk.h> #include <linux/platform_data/mv_usb.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "mv_udc.h" diff --git a/drivers/usb/gadget/udc/net2272.c b/drivers/usb/gadget/udc/net2272.c index 19bbc38f3d35..9230db57dab7 100644 --- a/drivers/usb/gadget/udc/net2272.c +++ b/drivers/usb/gadget/udc/net2272.c @@ -28,7 +28,7 @@ #include <linux/usb/gadget.h> #include <asm/byteorder.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "net2272.h" diff --git a/drivers/usb/gadget/udc/net2280.c b/drivers/usb/gadget/udc/net2280.c index 1b929c519cd7..b2903e4bbf54 100644 --- a/drivers/usb/gadget/udc/net2280.c +++ b/drivers/usb/gadget/udc/net2280.c @@ -56,7 +56,7 @@ #include <asm/byteorder.h> #include <asm/irq.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define DRIVER_DESC "PLX NET228x/USB338x USB Peripheral Controller" #define DRIVER_VERSION "2005 Sept 27/v3.0" diff --git a/drivers/usb/gadget/udc/omap_udc.c b/drivers/usb/gadget/udc/omap_udc.c index e13b8ec8ef8a..61a45e4657d5 100644 --- a/drivers/usb/gadget/udc/omap_udc.c +++ b/drivers/usb/gadget/udc/omap_udc.c @@ -36,7 +36,7 @@ #include <asm/byteorder.h> #include <asm/irq.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <asm/mach-types.h> #include <linux/omap-dma.h> diff --git a/drivers/usb/gadget/udc/pxa25x_udc.c b/drivers/usb/gadget/udc/pxa25x_udc.c index 1ac26cb49ecf..7c96fc9f680f 100644 --- a/drivers/usb/gadget/udc/pxa25x_udc.c +++ b/drivers/usb/gadget/udc/pxa25x_udc.c @@ -38,7 +38,7 @@ #include <asm/byteorder.h> #include <asm/dma.h> #include <asm/mach-types.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/usb/ch9.h> #include <linux/usb/gadget.h> diff --git a/drivers/usb/gadget/udc/snps_udc_core.c b/drivers/usb/gadget/udc/snps_udc_core.c index 2fc5d4d277bc..cd89532adec2 100644 --- a/drivers/usb/gadget/udc/snps_udc_core.c +++ b/drivers/usb/gadget/udc/snps_udc_core.c @@ -33,7 +33,7 @@ #include <linux/prefetch.h> #include <linux/moduleparam.h> #include <asm/byteorder.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "amd5536udc.h" static void udc_setup_endpoints(struct udc *dev); diff --git a/drivers/usb/host/ehci-hcd.c b/drivers/usb/host/ehci-hcd.c index 802bfafb1012..cbc0b86fcc36 100644 --- a/drivers/usb/host/ehci-hcd.c +++ b/drivers/usb/host/ehci-hcd.c @@ -32,7 +32,7 @@ #include <asm/byteorder.h> #include <asm/io.h> #include <asm/irq.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #if defined(CONFIG_PPC_PS3) #include <asm/firmware.h> diff --git a/drivers/usb/host/isp1362-hcd.c b/drivers/usb/host/isp1362-hcd.c index a52c3d858f3e..31059c8f94e6 100644 --- a/drivers/usb/host/isp1362-hcd.c +++ b/drivers/usb/host/isp1362-hcd.c @@ -83,7 +83,7 @@ #include <asm/irq.h> #include <asm/byteorder.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> static int dbg_level; #ifdef ISP1362_DEBUG diff --git a/drivers/usb/host/ohci-da8xx.c b/drivers/usb/host/ohci-da8xx.c index d9adae53466b..d2b67da76762 100644 --- a/drivers/usb/host/ohci-da8xx.c +++ b/drivers/usb/host/ohci-da8xx.c @@ -22,7 +22,7 @@ #include <linux/regulator/consumer.h> #include <linux/usb.h> #include <linux/usb/hcd.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "ohci.h" diff --git a/drivers/usb/host/ohci-hcd.c b/drivers/usb/host/ohci-hcd.c index 5cec7640e913..9b24181fee60 100644 --- a/drivers/usb/host/ohci-hcd.c +++ b/drivers/usb/host/ohci-hcd.c @@ -44,7 +44,7 @@ #include <asm/io.h> #include <asm/irq.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <asm/byteorder.h> diff --git a/drivers/usb/host/oxu210hp-hcd.c b/drivers/usb/host/oxu210hp-hcd.c index 3f871fe62b90..ca3859463ba1 100644 --- a/drivers/usb/host/oxu210hp-hcd.c +++ b/drivers/usb/host/oxu210hp-hcd.c @@ -27,7 +27,7 @@ #include <linux/iopoll.h> #include <asm/irq.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/irq.h> #include <linux/platform_device.h> diff --git a/drivers/usb/host/sl811-hcd.c b/drivers/usb/host/sl811-hcd.c index 2b871540bb50..92f2d1238448 100644 --- a/drivers/usb/host/sl811-hcd.c +++ b/drivers/usb/host/sl811-hcd.c @@ -54,7 +54,7 @@ #include <asm/io.h> #include <asm/irq.h> #include <asm/byteorder.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "sl811.h" diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c index d27c30ac17fd..8d774f19271e 100644 --- a/drivers/usb/host/xhci-hub.c +++ b/drivers/usb/host/xhci-hub.c @@ -10,7 +10,7 @@ #include <linux/slab.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/bitfield.h> #include "xhci.h" diff --git a/drivers/usb/host/xhci-pci-renesas.c b/drivers/usb/host/xhci-pci-renesas.c index 30cc5a1380a5..65fc9319d5e7 100644 --- a/drivers/usb/host/xhci-pci-renesas.c +++ b/drivers/usb/host/xhci-pci-renesas.c @@ -6,7 +6,7 @@ #include <linux/module.h> #include <linux/pci.h> #include <linux/slab.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "xhci.h" #include "xhci-trace.h" diff --git a/drivers/usb/isp1760/isp1760-hcd.c b/drivers/usb/isp1760/isp1760-hcd.c index 0e5e4cb74c87..add2d2e3b61b 100644 --- a/drivers/usb/isp1760/isp1760-hcd.c +++ b/drivers/usb/isp1760/isp1760-hcd.c @@ -27,7 +27,7 @@ #include <linux/iopoll.h> #include <linux/mm.h> #include <linux/timer.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <asm/cacheflush.h> #include "isp1760-core.h" diff --git a/drivers/usb/misc/usb-ljca.c b/drivers/usb/misc/usb-ljca.c index 1a8d5e80b9ae..01ceafc4ab78 100644 --- a/drivers/usb/misc/usb-ljca.c +++ b/drivers/usb/misc/usb-ljca.c @@ -18,7 +18,7 @@ #include <linux/usb.h> #include <linux/usb/ljca.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /* command flags */ #define LJCA_ACK_FLAG BIT(0) diff --git a/drivers/usb/musb/musb_virthub.c b/drivers/usb/musb/musb_virthub.c index 2b2164e028b3..ce6f25a9650b 100644 --- a/drivers/usb/musb/musb_virthub.c +++ b/drivers/usb/musb/musb_virthub.c @@ -14,7 +14,7 @@ #include <linux/time.h> #include <linux/timer.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "musb_core.h" diff --git a/drivers/usb/phy/phy-fsl-usb.c b/drivers/usb/phy/phy-fsl-usb.c index 1ebbf189a535..c5c6b818998e 100644 --- a/drivers/usb/phy/phy-fsl-usb.c +++ b/drivers/usb/phy/phy-fsl-usb.c @@ -27,7 +27,7 @@ #include <linux/platform_device.h> #include <linux/uaccess.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "phy-fsl-usb.h" diff --git a/drivers/usb/serial/aircable.c b/drivers/usb/serial/aircable.c index aa517242d060..2a76f1f0ee4f 100644 --- a/drivers/usb/serial/aircable.c +++ b/drivers/usb/serial/aircable.c @@ -35,7 +35,7 @@ * */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/tty.h> #include <linux/slab.h> #include <linux/module.h> diff --git a/drivers/usb/serial/ch341.c b/drivers/usb/serial/ch341.c index 02945ccf531d..d10e4c4848a0 100644 --- a/drivers/usb/serial/ch341.c +++ b/drivers/usb/serial/ch341.c @@ -19,7 +19,7 @@ #include <linux/usb.h> #include <linux/usb/serial.h> #include <linux/serial.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define DEFAULT_BAUD_RATE 9600 #define DEFAULT_TIMEOUT 1000 diff --git a/drivers/usb/serial/cypress_m8.c b/drivers/usb/serial/cypress_m8.c index ce9134bb30f3..e29569d65991 100644 --- a/drivers/usb/serial/cypress_m8.c +++ b/drivers/usb/serial/cypress_m8.c @@ -36,7 +36,7 @@ #include <linux/kfifo.h> #include <linux/delay.h> #include <linux/uaccess.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "cypress_m8.h" diff --git a/drivers/usb/serial/kl5kusb105.c b/drivers/usb/serial/kl5kusb105.c index a2c0bebc041f..d36155b6d2bf 100644 --- a/drivers/usb/serial/kl5kusb105.c +++ b/drivers/usb/serial/kl5kusb105.c @@ -39,7 +39,7 @@ #include <linux/tty_flip.h> #include <linux/module.h> #include <linux/uaccess.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/usb.h> #include <linux/usb/serial.h> #include "kl5kusb105.h" diff --git a/drivers/usb/serial/mct_u232.c b/drivers/usb/serial/mct_u232.c index e5a139ed5d90..2bce8cc03aca 100644 --- a/drivers/usb/serial/mct_u232.c +++ b/drivers/usb/serial/mct_u232.c @@ -26,7 +26,7 @@ #include <linux/module.h> #include <linux/spinlock.h> #include <linux/uaccess.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/usb.h> #include <linux/usb/serial.h> #include <linux/serial.h> diff --git a/drivers/usb/serial/mxuport.c b/drivers/usb/serial/mxuport.c index 57e4f2b215d8..ad5fdf55a02e 100644 --- a/drivers/usb/serial/mxuport.c +++ b/drivers/usb/serial/mxuport.c @@ -25,7 +25,7 @@ #include <linux/uaccess.h> #include <linux/usb.h> #include <linux/usb/serial.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /* Definitions for the vendor ID and device ID */ #define MX_USBSERIAL_VID 0x110A diff --git a/drivers/usb/serial/pl2303.c b/drivers/usb/serial/pl2303.c index ab48f8875249..ad41363e3cea 100644 --- a/drivers/usb/serial/pl2303.c +++ b/drivers/usb/serial/pl2303.c @@ -24,7 +24,7 @@ #include <linux/uaccess.h> #include <linux/usb.h> #include <linux/usb/serial.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "pl2303.h" diff --git a/drivers/usb/serial/quatech2.c b/drivers/usb/serial/quatech2.c index 4167a45d1be3..a317bdbd00ad 100644 --- a/drivers/usb/serial/quatech2.c +++ b/drivers/usb/serial/quatech2.c @@ -9,7 +9,7 @@ * */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/errno.h> #include <linux/slab.h> #include <linux/tty.h> diff --git a/drivers/usb/typec/ucsi/ucsi.h b/drivers/usb/typec/ucsi/ucsi.h index 4a017eb6a65b..1cf5aad4c23a 100644 --- a/drivers/usb/typec/ucsi/ucsi.h +++ b/drivers/usb/typec/ucsi/ucsi.h @@ -11,7 +11,7 @@ #include <linux/usb/typec.h> #include <linux/usb/pd.h> #include <linux/usb/role.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /* -------------------------------------------------------------------------- */ diff --git a/drivers/usb/typec/ucsi/ucsi_ccg.c b/drivers/usb/typec/ucsi/ucsi_ccg.c index b3ec799fc873..ba58d11907bc 100644 --- a/drivers/usb/typec/ucsi/ucsi_ccg.c +++ b/drivers/usb/typec/ucsi/ucsi_ccg.c @@ -18,7 +18,7 @@ #include <linux/pm_runtime.h> #include <linux/usb/typec_dp.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "ucsi.h" enum enum_fw_mode { diff --git a/drivers/usb/typec/ucsi/ucsi_stm32g0.c b/drivers/usb/typec/ucsi/ucsi_stm32g0.c index ddbec2b78c8e..6923fad31d79 100644 --- a/drivers/usb/typec/ucsi/ucsi_stm32g0.c +++ b/drivers/usb/typec/ucsi/ucsi_stm32g0.c @@ -12,7 +12,7 @@ #include <linux/interrupt.h> #include <linux/module.h> #include <linux/platform_device.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "ucsi.h" diff --git a/drivers/vdpa/octeon_ep/octep_vdpa_hw.c b/drivers/vdpa/octeon_ep/octep_vdpa_hw.c index 11bd76ae18cf..1d4767b33315 100644 --- a/drivers/vdpa/octeon_ep/octep_vdpa_hw.c +++ b/drivers/vdpa/octeon_ep/octep_vdpa_hw.c @@ -475,11 +475,11 @@ int octep_hw_caps_read(struct octep_hw *oct_hw, struct pci_dev *pdev) dev_err(dev, "Incomplete PCI capabilities"); return -EIO; } - dev_info(dev, "common cfg mapped at: 0x%016llx\n", (u64)(uintptr_t)oct_hw->common_cfg); - dev_info(dev, "device cfg mapped at: 0x%016llx\n", (u64)(uintptr_t)oct_hw->dev_cfg); - dev_info(dev, "isr cfg mapped at: 0x%016llx\n", (u64)(uintptr_t)oct_hw->isr); - dev_info(dev, "notify base: 0x%016llx, notify off multiplier: %u\n", - (u64)(uintptr_t)oct_hw->notify_base, oct_hw->notify_off_multiplier); + dev_info(dev, "common cfg mapped at: %p\n", oct_hw->common_cfg); + dev_info(dev, "device cfg mapped at: %p\n", oct_hw->dev_cfg); + dev_info(dev, "isr cfg mapped at: %p\n", oct_hw->isr); + dev_info(dev, "notify base: %p, notify off multiplier: %u\n", + oct_hw->notify_base, oct_hw->notify_off_multiplier); oct_hw->config_size = octep_get_config_size(oct_hw); oct_hw->features = octep_hw_get_dev_features(oct_hw); @@ -511,7 +511,7 @@ int octep_hw_caps_read(struct octep_hw *oct_hw, struct pci_dev *pdev) } mbox = octep_get_mbox(oct_hw); octep_mbox_init(mbox); - dev_info(dev, "mbox mapped at: 0x%016llx\n", (u64)(uintptr_t)mbox); + dev_info(dev, "mbox mapped at: %p\n", mbox); return 0; } diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index 006ffacf1c56..718fa4e0b31e 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -27,7 +27,7 @@ #include <linux/miscdevice.h> #include <linux/blk_types.h> #include <linux/bio.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <scsi/scsi_common.h> #include <scsi/scsi_proto.h> #include <target/target_core_base.h> @@ -1029,20 +1029,23 @@ vhost_scsi_get_req(struct vhost_virtqueue *vq, struct vhost_scsi_ctx *vc, /* virtio-scsi spec requires byte 0 of the lun to be 1 */ vq_err(vq, "Illegal virtio-scsi lun: %u\n", *vc->lunp); } else { - struct vhost_scsi_tpg **vs_tpg, *tpg; - - vs_tpg = vhost_vq_get_backend(vq); /* validated at handler entry */ - - tpg = READ_ONCE(vs_tpg[*vc->target]); - if (unlikely(!tpg)) { - vq_err(vq, "Target 0x%x does not exist\n", *vc->target); - } else { - if (tpgp) - *tpgp = tpg; - ret = 0; + struct vhost_scsi_tpg **vs_tpg, *tpg = NULL; + + if (vc->target) { + /* validated at handler entry */ + vs_tpg = vhost_vq_get_backend(vq); + tpg = READ_ONCE(vs_tpg[*vc->target]); + if (unlikely(!tpg)) { + vq_err(vq, "Target 0x%x does not exist\n", *vc->target); + goto out; + } } - } + if (tpgp) + *tpgp = tpg; + ret = 0; + } +out: return ret; } diff --git a/drivers/video/fbdev/aty/mach64_accel.c b/drivers/video/fbdev/aty/mach64_accel.c index e4b2c89baee2..826fb04de64c 100644 --- a/drivers/video/fbdev/aty/mach64_accel.c +++ b/drivers/video/fbdev/aty/mach64_accel.c @@ -5,7 +5,7 @@ */ #include <linux/delay.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/fb.h> #include <video/mach64.h> #include "atyfb.h" diff --git a/drivers/video/fbdev/c2p_iplan2.c b/drivers/video/fbdev/c2p_iplan2.c index 19156dc6158c..cfd2361f24b1 100644 --- a/drivers/video/fbdev/c2p_iplan2.c +++ b/drivers/video/fbdev/c2p_iplan2.c @@ -11,7 +11,7 @@ #include <linux/module.h> #include <linux/string.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "c2p.h" #include "c2p_core.h" diff --git a/drivers/video/fbdev/c2p_planar.c b/drivers/video/fbdev/c2p_planar.c index 22c8c1b6db60..819c82a98ac0 100644 --- a/drivers/video/fbdev/c2p_planar.c +++ b/drivers/video/fbdev/c2p_planar.c @@ -11,7 +11,7 @@ #include <linux/module.h> #include <linux/string.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "c2p.h" #include "c2p_core.h" diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c index 2e093535884b..e8b4e8c119b5 100644 --- a/drivers/video/fbdev/core/fbcon.c +++ b/drivers/video/fbdev/core/fbcon.c @@ -512,8 +512,10 @@ static int search_fb_in_map(int idx) int i, retval = 0; for (i = first_fb_vc; i <= last_fb_vc; i++) { - if (con2fb_map[i] == idx) + if (con2fb_map[i] == idx) { retval = 1; + break; + } } return retval; } @@ -523,8 +525,10 @@ static int search_for_mapped_con(void) int i, retval = 0; for (i = first_fb_vc; i <= last_fb_vc; i++) { - if (con2fb_map[i] != -1) + if (con2fb_map[i] != -1) { retval = 1; + break; + } } return retval; } @@ -861,6 +865,8 @@ static int set_con2fb_map(int unit, int newidx, int user) return err; fbcon_add_cursor_work(info); + } else if (vc) { + set_blitting_type(vc, info); } con2fb_map[unit] = newidx; diff --git a/drivers/video/fbdev/matrox/matroxfb_base.h b/drivers/video/fbdev/matrox/matroxfb_base.h index c93c69bbcd57..a6437c40fc57 100644 --- a/drivers/video/fbdev/matrox/matroxfb_base.h +++ b/drivers/video/fbdev/matrox/matroxfb_base.h @@ -44,7 +44,7 @@ #include <linux/kd.h> #include <asm/io.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #if defined(CONFIG_PPC_PMAC) #include "../macmodes.h" diff --git a/drivers/video/fbdev/metronomefb.c b/drivers/video/fbdev/metronomefb.c index 130394616a7c..c15353a356b6 100644 --- a/drivers/video/fbdev/metronomefb.c +++ b/drivers/video/fbdev/metronomefb.c @@ -37,7 +37,7 @@ #include <video/metronomefb.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /* Display specific information */ #define DPY_W 832 diff --git a/drivers/video/fbdev/omap2/omapfb/dss/dss-of.c b/drivers/video/fbdev/omap2/omapfb/dss/dss-of.c index 4040e247e026..d5a43b3bf45e 100644 --- a/drivers/video/fbdev/omap2/omapfb/dss/dss-of.c +++ b/drivers/video/fbdev/omap2/omapfb/dss/dss-of.c @@ -129,12 +129,9 @@ omapdss_of_find_source_for_first_ep(struct device_node *node) return ERR_PTR(-EINVAL); src_port = of_graph_get_remote_port(ep); - if (!src_port) { - of_node_put(ep); - return ERR_PTR(-EINVAL); - } - of_node_put(ep); + if (!src_port) + return ERR_PTR(-EINVAL); src = omap_dss_find_output_by_port_node(src_port); diff --git a/drivers/video/fbdev/sis/sis_main.c b/drivers/video/fbdev/sis/sis_main.c index 009bf1d92644..75033e6be15a 100644 --- a/drivers/video/fbdev/sis/sis_main.c +++ b/drivers/video/fbdev/sis/sis_main.c @@ -183,7 +183,7 @@ static void sisfb_search_mode(char *name, bool quiet) { unsigned int j = 0, xres = 0, yres = 0, depth = 0, rate = 0; int i = 0; - char strbuf[16], strbuf1[20]; + char strbuf[24], strbuf1[20]; char *nameptr = name; /* We don't know the hardware specs yet and there is no ivideo */ diff --git a/drivers/video/fbdev/udlfb.c b/drivers/video/fbdev/udlfb.c index 1514ddac4caf..71ac9e36f67c 100644 --- a/drivers/video/fbdev/udlfb.c +++ b/drivers/video/fbdev/udlfb.c @@ -23,7 +23,7 @@ #include <linux/vmalloc.h> #include <linux/slab.h> #include <linux/delay.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <video/udlfb.h> #include "edid.h" diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index be7309b1e860..98374ed7c577 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -2588,7 +2588,7 @@ irqreturn_t vring_interrupt(int irq, void *_vq) /* Just a hint for performance: so it's ok that this can be racy! */ if (vq->event) - vq->event_triggered = true; + data_race(vq->event_triggered = true); pr_debug("virtqueue callback for %p (%p)\n", vq, vq->vq.callback); if (vq->vq.callback) diff --git a/drivers/watchdog/ziirave_wdt.c b/drivers/watchdog/ziirave_wdt.c index 5ed33df68e9a..775838346bb5 100644 --- a/drivers/watchdog/ziirave_wdt.c +++ b/drivers/watchdog/ziirave_wdt.c @@ -20,7 +20,7 @@ #include <linux/types.h> #include <linux/watchdog.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define ZIIRAVE_TIMEOUT_MIN 3 #define ZIIRAVE_TIMEOUT_MAX 255 diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig index 62035fe16bb8..72ddee4c1544 100644 --- a/drivers/xen/Kconfig +++ b/drivers/xen/Kconfig @@ -261,7 +261,7 @@ config XEN_SCSI_BACKEND config XEN_PRIVCMD tristate "Xen hypercall passthrough driver" depends on XEN - imply CONFIG_XEN_PCIDEV_BACKEND + imply XEN_PCIDEV_BACKEND default m help The hypercall passthrough driver allows privileged user programs to diff --git a/fs/adfs/map.c b/fs/adfs/map.c index a81de80c45c1..a0ce272b4098 100644 --- a/fs/adfs/map.c +++ b/fs/adfs/map.c @@ -6,7 +6,7 @@ */ #include <linux/slab.h> #include <linux/statfs.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "adfs.h" /* diff --git a/fs/afs/afs_vl.h b/fs/afs/afs_vl.h index 9c65ffb8a523..a06296c8827d 100644 --- a/fs/afs/afs_vl.h +++ b/fs/afs/afs_vl.h @@ -134,13 +134,4 @@ struct afs_uvldbentry__xdr { __be32 spares9; }; -struct afs_address_list { - refcount_t usage; - unsigned int version; - unsigned int nr_addrs; - struct sockaddr_rxrpc addrs[]; -}; - -extern void afs_put_address_list(struct afs_address_list *alist); - #endif /* AFS_VL_H */ diff --git a/fs/afs/file.c b/fs/afs/file.c index 492d857a3fa0..6762eff97517 100644 --- a/fs/afs/file.c +++ b/fs/afs/file.c @@ -420,6 +420,7 @@ const struct netfs_request_ops afs_req_ops = { .begin_writeback = afs_begin_writeback, .prepare_write = afs_prepare_write, .issue_write = afs_issue_write, + .retry_request = afs_retry_request, }; static void afs_add_open_mmap(struct afs_vnode *vnode) diff --git a/fs/afs/fs_operation.c b/fs/afs/fs_operation.c index 3546b087e791..428721bbe4f6 100644 --- a/fs/afs/fs_operation.c +++ b/fs/afs/fs_operation.c @@ -201,7 +201,7 @@ void afs_wait_for_operation(struct afs_operation *op) } } - if (op->call_responded) + if (op->call_responded && op->server) set_bit(AFS_SERVER_FL_RESPONDING, &op->server->flags); if (!afs_op_error(op)) { diff --git a/fs/afs/fs_probe.c b/fs/afs/fs_probe.c index 580de4adaaf6..b516d05b0fef 100644 --- a/fs/afs/fs_probe.c +++ b/fs/afs/fs_probe.c @@ -506,10 +506,10 @@ int afs_wait_for_one_fs_probe(struct afs_server *server, struct afs_endpoint_sta finish_wait(&server->probe_wq, &wait); dont_wait: - if (estate->responsive_set & ~exclude) - return 1; if (test_bit(AFS_ESTATE_SUPERSEDED, &estate->flags)) return 0; + if (estate->responsive_set & ~exclude) + return 1; if (is_intr && signal_pending(current)) return -ERESTARTSYS; if (timo == 0) diff --git a/fs/afs/rotate.c b/fs/afs/rotate.c index ed09d4d4c211..d612983d6f38 100644 --- a/fs/afs/rotate.c +++ b/fs/afs/rotate.c @@ -632,8 +632,10 @@ iterate_address: wait_for_more_probe_results: error = afs_wait_for_one_fs_probe(op->server, op->estate, op->addr_tried, !(op->flags & AFS_OPERATION_UNINTR)); - if (!error) + if (error == 1) goto iterate_address; + if (!error) + goto restart_from_beginning; /* We've now had a failure to respond on all of a server's addresses - * immediately probe them again and consider retrying the server. @@ -644,10 +646,13 @@ wait_for_more_probe_results: error = afs_wait_for_one_fs_probe(op->server, op->estate, op->addr_tried, !(op->flags & AFS_OPERATION_UNINTR)); switch (error) { - case 0: + case 1: op->flags &= ~AFS_OPERATION_RETRY_SERVER; - trace_afs_rotate(op, afs_rotate_trace_retry_server, 0); + trace_afs_rotate(op, afs_rotate_trace_retry_server, 1); goto retry_server; + case 0: + trace_afs_rotate(op, afs_rotate_trace_retry_server, 0); + goto restart_from_beginning; case -ERESTARTSYS: afs_op_set_error(op, error); goto failed; diff --git a/fs/bcachefs/alloc_background.c b/fs/bcachefs/alloc_background.c index 645b5ed4babb..4e4a448f6931 100644 --- a/fs/bcachefs/alloc_background.c +++ b/fs/bcachefs/alloc_background.c @@ -332,7 +332,6 @@ void bch2_alloc_v4_swab(struct bkey_s k) a->io_time[1] = swab64(a->io_time[1]); a->stripe = swab32(a->stripe); a->nr_external_backpointers = swab32(a->nr_external_backpointers); - a->fragmentation_lru = swab64(a->fragmentation_lru); a->stripe_sectors = swab32(a->stripe_sectors); bps = alloc_v4_backpointers(a); @@ -347,6 +346,7 @@ void bch2_alloc_to_text(struct printbuf *out, struct bch_fs *c, struct bkey_s_c { struct bch_alloc_v4 _a; const struct bch_alloc_v4 *a = bch2_alloc_to_v4(k, &_a); + struct bch_dev *ca = c ? bch2_dev_bucket_tryget_noerror(c, k.k->p) : NULL; prt_newline(out); printbuf_indent_add(out, 2); @@ -364,9 +364,13 @@ void bch2_alloc_to_text(struct printbuf *out, struct bch_fs *c, struct bkey_s_c prt_printf(out, "stripe_redundancy %u\n", a->stripe_redundancy); prt_printf(out, "io_time[READ] %llu\n", a->io_time[READ]); prt_printf(out, "io_time[WRITE] %llu\n", a->io_time[WRITE]); - prt_printf(out, "fragmentation %llu\n", a->fragmentation_lru); + + if (ca) + prt_printf(out, "fragmentation %llu\n", alloc_lru_idx_fragmentation(*a, ca)); prt_printf(out, "bp_start %llu\n", BCH_ALLOC_V4_BACKPOINTERS_START(a)); printbuf_indent_sub(out, 2); + + bch2_dev_put(ca); } void __bch2_alloc_to_v4(struct bkey_s_c k, struct bch_alloc_v4 *out) @@ -882,12 +886,13 @@ int bch2_trigger_alloc(struct btree_trans *trans, goto err; } - new_a->fragmentation_lru = alloc_lru_idx_fragmentation(*new_a, ca); - if (old_a->fragmentation_lru != new_a->fragmentation_lru) { + old_lru = alloc_lru_idx_fragmentation(*old_a, ca); + new_lru = alloc_lru_idx_fragmentation(*new_a, ca); + if (old_lru != new_lru) { ret = bch2_lru_change(trans, BCH_LRU_FRAGMENTATION_START, bucket_to_u64(new.k->p), - old_a->fragmentation_lru, new_a->fragmentation_lru); + old_lru, new_lru); if (ret) goto err; } @@ -1629,18 +1634,22 @@ static int bch2_check_alloc_to_lru_ref(struct btree_trans *trans, if (ret) return ret; + struct bch_dev *ca = bch2_dev_tryget_noerror(c, alloc_k.k->p.inode); + if (!ca) + return 0; + a = bch2_alloc_to_v4(alloc_k, &a_convert); - if (a->fragmentation_lru) { + u64 lru_idx = alloc_lru_idx_fragmentation(*a, ca); + if (lru_idx) { ret = bch2_lru_check_set(trans, BCH_LRU_FRAGMENTATION_START, - a->fragmentation_lru, - alloc_k, last_flushed); + lru_idx, alloc_k, last_flushed); if (ret) - return ret; + goto err; } if (a->data_type != BCH_DATA_cached) - return 0; + goto err; if (fsck_err_on(!a->io_time[READ], trans, alloc_key_cached_but_read_time_zero, @@ -1669,6 +1678,7 @@ static int bch2_check_alloc_to_lru_ref(struct btree_trans *trans, goto err; err: fsck_err: + bch2_dev_put(ca); printbuf_exit(&buf); return ret; } diff --git a/fs/bcachefs/alloc_background_format.h b/fs/bcachefs/alloc_background_format.h index f754a2951d8a..befdaa95c515 100644 --- a/fs/bcachefs/alloc_background_format.h +++ b/fs/bcachefs/alloc_background_format.h @@ -70,7 +70,7 @@ struct bch_alloc_v4 { __u32 stripe; __u32 nr_external_backpointers; /* end of fields in original version of alloc_v4 */ - __u64 fragmentation_lru; + __u64 _fragmentation_lru; /* obsolete */ __u32 stripe_sectors; __u32 pad; } __packed __aligned(8); diff --git a/fs/bcachefs/backpointers.c b/fs/bcachefs/backpointers.c index e11989a57ca0..47455a85c909 100644 --- a/fs/bcachefs/backpointers.c +++ b/fs/bcachefs/backpointers.c @@ -501,7 +501,7 @@ found: prt_printf(&buf, "\n %s ", bch2_btree_id_str(o_btree)); bch2_bkey_val_to_text(&buf, c, extent2); - struct nonce nonce = extent_nonce(extent.k->version, p.crc); + struct nonce nonce = extent_nonce(extent.k->bversion, p.crc); struct bch_csum csum = bch2_checksum(c, p.crc.csum_type, nonce, data_buf, bytes); if (fsck_err_on(bch2_crc_cmp(csum, p.crc.csum), trans, dup_backpointer_to_bad_csum_extent, diff --git a/fs/bcachefs/bcachefs.h b/fs/bcachefs/bcachefs.h index c711d4c27a03..f4151ee51b03 100644 --- a/fs/bcachefs/bcachefs.h +++ b/fs/bcachefs/bcachefs.h @@ -594,6 +594,7 @@ struct bch_dev { #define BCH_FS_FLAGS() \ x(new_fs) \ x(started) \ + x(clean_recovery) \ x(btree_running) \ x(accounting_replay_done) \ x(may_go_rw) \ @@ -776,7 +777,7 @@ struct bch_fs { unsigned nsec_per_time_unit; u64 features; u64 compat; - unsigned long errors_silent[BITS_TO_LONGS(BCH_SB_ERR_MAX)]; + unsigned long errors_silent[BITS_TO_LONGS(BCH_FSCK_ERR_MAX)]; u64 btrees_lost_data; } sb; diff --git a/fs/bcachefs/bcachefs_format.h b/fs/bcachefs/bcachefs_format.h index 8c4addddd07e..84832c2d4df9 100644 --- a/fs/bcachefs/bcachefs_format.h +++ b/fs/bcachefs/bcachefs_format.h @@ -217,13 +217,13 @@ struct bkey { #if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ __u8 pad[1]; - struct bversion version; + struct bversion bversion; __u32 size; /* extent size, in sectors */ struct bpos p; #elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ struct bpos p; __u32 size; /* extent size, in sectors */ - struct bversion version; + struct bversion bversion; __u8 pad[1]; #endif @@ -328,8 +328,8 @@ enum bch_bkey_fields { bkey_format_field(OFFSET, p.offset), \ bkey_format_field(SNAPSHOT, p.snapshot), \ bkey_format_field(SIZE, size), \ - bkey_format_field(VERSION_HI, version.hi), \ - bkey_format_field(VERSION_LO, version.lo), \ + bkey_format_field(VERSION_HI, bversion.hi), \ + bkey_format_field(VERSION_LO, bversion.lo), \ }, \ }) diff --git a/fs/bcachefs/bkey.h b/fs/bcachefs/bkey.h index e34cb2bf329c..41df24a53d97 100644 --- a/fs/bcachefs/bkey.h +++ b/fs/bcachefs/bkey.h @@ -214,9 +214,9 @@ static __always_inline int bversion_cmp(struct bversion l, struct bversion r) #define ZERO_VERSION ((struct bversion) { .hi = 0, .lo = 0 }) #define MAX_VERSION ((struct bversion) { .hi = ~0, .lo = ~0ULL }) -static __always_inline int bversion_zero(struct bversion v) +static __always_inline bool bversion_zero(struct bversion v) { - return !bversion_cmp(v, ZERO_VERSION); + return bversion_cmp(v, ZERO_VERSION) == 0; } #ifdef CONFIG_BCACHEFS_DEBUG @@ -554,8 +554,8 @@ static inline void bch2_bkey_pack_test(void) {} x(BKEY_FIELD_OFFSET, p.offset) \ x(BKEY_FIELD_SNAPSHOT, p.snapshot) \ x(BKEY_FIELD_SIZE, size) \ - x(BKEY_FIELD_VERSION_HI, version.hi) \ - x(BKEY_FIELD_VERSION_LO, version.lo) + x(BKEY_FIELD_VERSION_HI, bversion.hi) \ + x(BKEY_FIELD_VERSION_LO, bversion.lo) struct bkey_format_state { u64 field_min[BKEY_NR_FIELDS]; diff --git a/fs/bcachefs/bkey_methods.c b/fs/bcachefs/bkey_methods.c index 88d8958281e8..e7ac227ba7e8 100644 --- a/fs/bcachefs/bkey_methods.c +++ b/fs/bcachefs/bkey_methods.c @@ -289,7 +289,7 @@ void bch2_bkey_to_text(struct printbuf *out, const struct bkey *k) bch2_bpos_to_text(out, k->p); - prt_printf(out, " len %u ver %llu", k->size, k->version.lo); + prt_printf(out, " len %u ver %llu", k->size, k->bversion.lo); } else { prt_printf(out, "(null)"); } diff --git a/fs/bcachefs/bkey_methods.h b/fs/bcachefs/bkey_methods.h index 3df3dd2723a1..018fb72e32d3 100644 --- a/fs/bcachefs/bkey_methods.h +++ b/fs/bcachefs/bkey_methods.h @@ -70,7 +70,7 @@ bool bch2_bkey_normalize(struct bch_fs *, struct bkey_s); static inline bool bch2_bkey_maybe_mergable(const struct bkey *l, const struct bkey *r) { return l->type == r->type && - !bversion_cmp(l->version, r->version) && + !bversion_cmp(l->bversion, r->bversion) && bpos_eq(l->p, bkey_start_pos(r)); } diff --git a/fs/bcachefs/bset.c b/fs/bcachefs/bset.c index d1f6092624d8..9a4a83d6fd2d 100644 --- a/fs/bcachefs/bset.c +++ b/fs/bcachefs/bset.c @@ -13,7 +13,7 @@ #include "trace.h" #include "util.h" -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/console.h> #include <linux/random.h> #include <linux/prefetch.h> diff --git a/fs/bcachefs/btree_gc.c b/fs/bcachefs/btree_gc.c index b5e0692f03c6..771154e3a291 100644 --- a/fs/bcachefs/btree_gc.c +++ b/fs/bcachefs/btree_gc.c @@ -513,6 +513,8 @@ int bch2_check_topology(struct bch_fs *c) struct bpos pulled_from_scan = POS_MIN; int ret = 0; + bch2_trans_srcu_unlock(trans); + for (unsigned i = 0; i < btree_id_nr_alive(c) && !ret; i++) { struct btree_root *r = bch2_btree_id_root(c, i); bool reconstructed_root = false; @@ -599,15 +601,15 @@ static int bch2_gc_mark_key(struct btree_trans *trans, enum btree_id btree_id, if (initial) { BUG_ON(bch2_journal_seq_verify && - k.k->version.lo > atomic64_read(&c->journal.seq)); + k.k->bversion.lo > atomic64_read(&c->journal.seq)); if (fsck_err_on(btree_id != BTREE_ID_accounting && - k.k->version.lo > atomic64_read(&c->key_version), + k.k->bversion.lo > atomic64_read(&c->key_version), trans, bkey_version_in_future, "key version number higher than recorded %llu\n %s", atomic64_read(&c->key_version), (bch2_bkey_val_to_text(&buf, c, k), buf.buf))) - atomic64_set(&c->key_version, k.k->version.lo); + atomic64_set(&c->key_version, k.k->bversion.lo); } if (mustfix_fsck_err_on(level && !bch2_dev_btree_bitmap_marked(c, k), @@ -826,8 +828,6 @@ static int bch2_alloc_write_key(struct btree_trans *trans, return ret; } - gc.fragmentation_lru = alloc_lru_idx_fragmentation(gc, ca); - if (fsck_err_on(new.data_type != gc.data_type, trans, alloc_key_data_type_wrong, "bucket %llu:%llu gen %u has wrong data_type" @@ -855,7 +855,6 @@ static int bch2_alloc_write_key(struct btree_trans *trans, copy_bucket_field(alloc_key_cached_sectors_wrong, cached_sectors); copy_bucket_field(alloc_key_stripe_wrong, stripe); copy_bucket_field(alloc_key_stripe_redundancy_wrong, stripe_redundancy); - copy_bucket_field(alloc_key_fragmentation_lru_wrong, fragmentation_lru); #undef copy_bucket_field if (!bch2_alloc_v4_cmp(*old, new)) diff --git a/fs/bcachefs/btree_io.c b/fs/bcachefs/btree_io.c index cb48a9477514..1c1448b52207 100644 --- a/fs/bcachefs/btree_io.c +++ b/fs/bcachefs/btree_io.c @@ -1195,6 +1195,10 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca, set_btree_bset(b, b->set, &b->data->keys); b->nr = bch2_key_sort_fix_overlapping(c, &sorted->keys, iter); + memset((uint8_t *)(sorted + 1) + b->nr.live_u64s * sizeof(u64), 0, + btree_buf_bytes(b) - + sizeof(struct btree_node) - + b->nr.live_u64s * sizeof(u64)); u64s = le16_to_cpu(sorted->keys.u64s); *sorted = *b->data; @@ -1219,7 +1223,7 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca, ret = bch2_bkey_val_validate(c, u.s_c, READ); if (ret == -BCH_ERR_fsck_delete_bkey || (bch2_inject_invalid_keys && - !bversion_cmp(u.k->version, MAX_VERSION))) { + !bversion_cmp(u.k->bversion, MAX_VERSION))) { btree_keys_account_key_drop(&b->nr, 0, k); i->u64s = cpu_to_le16(le16_to_cpu(i->u64s) - k->u64s); diff --git a/fs/bcachefs/btree_node_scan.c b/fs/bcachefs/btree_node_scan.c index b28c649c6838..1e694fedc5da 100644 --- a/fs/bcachefs/btree_node_scan.c +++ b/fs/bcachefs/btree_node_scan.c @@ -275,7 +275,7 @@ static int read_btree_nodes(struct find_btree_nodes *f) w->ca = ca; t = kthread_run(read_btree_nodes_worker, w, "read_btree_nodes/%s", ca->name); - ret = IS_ERR_OR_NULL(t); + ret = PTR_ERR_OR_ZERO(t); if (ret) { percpu_ref_put(&ca->io_ref); closure_put(&cl); diff --git a/fs/bcachefs/btree_trans_commit.c b/fs/bcachefs/btree_trans_commit.c index 91884da4e30a..9bf471fa4361 100644 --- a/fs/bcachefs/btree_trans_commit.c +++ b/fs/bcachefs/btree_trans_commit.c @@ -684,10 +684,10 @@ bch2_trans_commit_write_locked(struct btree_trans *trans, unsigned flags, !(flags & BCH_TRANS_COMMIT_no_journal_res)) { if (bch2_journal_seq_verify) trans_for_each_update(trans, i) - i->k->k.version.lo = trans->journal_res.seq; + i->k->k.bversion.lo = trans->journal_res.seq; else if (bch2_inject_invalid_keys) trans_for_each_update(trans, i) - i->k->k.version = MAX_VERSION; + i->k->k.bversion = MAX_VERSION; } h = trans->hooks; @@ -700,27 +700,31 @@ bch2_trans_commit_write_locked(struct btree_trans *trans, unsigned flags, struct jset_entry *entry = trans->journal_entries; - if (likely(!(flags & BCH_TRANS_COMMIT_skip_accounting_apply))) { - percpu_down_read(&c->mark_lock); + percpu_down_read(&c->mark_lock); + + for (entry = trans->journal_entries; + entry != (void *) ((u64 *) trans->journal_entries + trans->journal_entries_u64s); + entry = vstruct_next(entry)) + if (entry->type == BCH_JSET_ENTRY_write_buffer_keys && + entry->start->k.type == KEY_TYPE_accounting) { + BUG_ON(!trans->journal_res.ref); + + struct bkey_i_accounting *a = bkey_i_to_accounting(entry->start); - for (entry = trans->journal_entries; - entry != (void *) ((u64 *) trans->journal_entries + trans->journal_entries_u64s); - entry = vstruct_next(entry)) - if (jset_entry_is_key(entry) && entry->start->k.type == KEY_TYPE_accounting) { - struct bkey_i_accounting *a = bkey_i_to_accounting(entry->start); + a->k.bversion = journal_pos_to_bversion(&trans->journal_res, + (u64 *) entry - (u64 *) trans->journal_entries); + BUG_ON(bversion_zero(a->k.bversion)); - a->k.version = journal_pos_to_bversion(&trans->journal_res, - (u64 *) entry - (u64 *) trans->journal_entries); - BUG_ON(bversion_zero(a->k.version)); - ret = bch2_accounting_mem_mod_locked(trans, accounting_i_to_s_c(a), false, false); + if (likely(!(flags & BCH_TRANS_COMMIT_skip_accounting_apply))) { + ret = bch2_accounting_mem_mod_locked(trans, accounting_i_to_s_c(a), BCH_ACCOUNTING_normal); if (ret) goto revert_fs_usage; } - percpu_up_read(&c->mark_lock); + } + percpu_up_read(&c->mark_lock); - /* XXX: we only want to run this if deltas are nonzero */ - bch2_trans_account_disk_usage_change(trans); - } + /* XXX: we only want to run this if deltas are nonzero */ + bch2_trans_account_disk_usage_change(trans); trans_for_each_update(trans, i) if (btree_node_type_has_atomic_triggers(i->bkey_type)) { @@ -735,6 +739,40 @@ bch2_trans_commit_write_locked(struct btree_trans *trans, unsigned flags, goto fatal_err; } + trans_for_each_update(trans, i) { + enum bch_validate_flags invalid_flags = 0; + + if (!(flags & BCH_TRANS_COMMIT_no_journal_res)) + invalid_flags |= BCH_VALIDATE_write|BCH_VALIDATE_commit; + + ret = bch2_bkey_validate(c, bkey_i_to_s_c(i->k), + i->bkey_type, invalid_flags); + if (unlikely(ret)){ + bch2_trans_inconsistent(trans, "invalid bkey on insert from %s -> %ps\n", + trans->fn, (void *) i->ip_allocated); + goto fatal_err; + } + btree_insert_entry_checks(trans, i); + } + + for (struct jset_entry *i = trans->journal_entries; + i != (void *) ((u64 *) trans->journal_entries + trans->journal_entries_u64s); + i = vstruct_next(i)) { + enum bch_validate_flags invalid_flags = 0; + + if (!(flags & BCH_TRANS_COMMIT_no_journal_res)) + invalid_flags |= BCH_VALIDATE_write|BCH_VALIDATE_commit; + + ret = bch2_journal_entry_validate(c, NULL, i, + bcachefs_metadata_version_current, + CPU_BIG_ENDIAN, invalid_flags); + if (unlikely(ret)) { + bch2_trans_inconsistent(trans, "invalid journal entry on insert from %s\n", + trans->fn); + goto fatal_err; + } + } + if (likely(!(flags & BCH_TRANS_COMMIT_no_journal_res))) { struct journal *j = &c->journal; struct jset_entry *entry; @@ -794,11 +832,12 @@ revert_fs_usage: for (struct jset_entry *entry2 = trans->journal_entries; entry2 != entry; entry2 = vstruct_next(entry2)) - if (jset_entry_is_key(entry2) && entry2->start->k.type == KEY_TYPE_accounting) { + if (entry2->type == BCH_JSET_ENTRY_write_buffer_keys && + entry2->start->k.type == KEY_TYPE_accounting) { struct bkey_s_accounting a = bkey_i_to_s_accounting(entry2->start); bch2_accounting_neg(a); - bch2_accounting_mem_mod_locked(trans, a.c, false, false); + bch2_accounting_mem_mod_locked(trans, a.c, BCH_ACCOUNTING_normal); bch2_accounting_neg(a); } percpu_up_read(&c->mark_lock); @@ -1019,40 +1058,6 @@ int __bch2_trans_commit(struct btree_trans *trans, unsigned flags) if (ret) goto out_reset; - trans_for_each_update(trans, i) { - enum bch_validate_flags invalid_flags = 0; - - if (!(flags & BCH_TRANS_COMMIT_no_journal_res)) - invalid_flags |= BCH_VALIDATE_write|BCH_VALIDATE_commit; - - ret = bch2_bkey_validate(c, bkey_i_to_s_c(i->k), - i->bkey_type, invalid_flags); - if (unlikely(ret)){ - bch2_trans_inconsistent(trans, "invalid bkey on insert from %s -> %ps\n", - trans->fn, (void *) i->ip_allocated); - return ret; - } - btree_insert_entry_checks(trans, i); - } - - for (struct jset_entry *i = trans->journal_entries; - i != (void *) ((u64 *) trans->journal_entries + trans->journal_entries_u64s); - i = vstruct_next(i)) { - enum bch_validate_flags invalid_flags = 0; - - if (!(flags & BCH_TRANS_COMMIT_no_journal_res)) - invalid_flags |= BCH_VALIDATE_write|BCH_VALIDATE_commit; - - ret = bch2_journal_entry_validate(c, NULL, i, - bcachefs_metadata_version_current, - CPU_BIG_ENDIAN, invalid_flags); - if (unlikely(ret)) { - bch2_trans_inconsistent(trans, "invalid journal entry on insert from %s\n", - trans->fn); - return ret; - } - } - if (unlikely(!test_bit(BCH_FS_may_go_rw, &c->flags))) { ret = do_bch2_trans_commit_to_journal_replay(trans); goto out_reset; diff --git a/fs/bcachefs/btree_update.h b/fs/bcachefs/btree_update.h index 60393e98084d..6a454f2fa005 100644 --- a/fs/bcachefs/btree_update.h +++ b/fs/bcachefs/btree_update.h @@ -220,7 +220,8 @@ static inline struct bkey_i *__bch2_bkey_make_mut_noupdate(struct btree_trans *t if (type && k.k->type != type) return ERR_PTR(-ENOENT); - mut = bch2_trans_kmalloc_nomemzero(trans, bytes); + /* extra padding for varint_decode_fast... */ + mut = bch2_trans_kmalloc_nomemzero(trans, bytes + 8); if (!IS_ERR(mut)) { bkey_reassemble(mut, k); diff --git a/fs/bcachefs/data_update.c b/fs/bcachefs/data_update.c index 757b9884ef55..462b1a2fe1ad 100644 --- a/fs/bcachefs/data_update.c +++ b/fs/bcachefs/data_update.c @@ -639,7 +639,7 @@ int bch2_data_update_init(struct btree_trans *trans, bch2_write_op_init(&m->op, c, io_opts); m->op.pos = bkey_start_pos(k.k); - m->op.version = k.k->version; + m->op.version = k.k->bversion; m->op.target = data_opts.target; m->op.write_point = wp; m->op.nr_replicas = 0; diff --git a/fs/bcachefs/disk_accounting.c b/fs/bcachefs/disk_accounting.c index e972e2bca546..9f3133e3e7e5 100644 --- a/fs/bcachefs/disk_accounting.c +++ b/fs/bcachefs/disk_accounting.c @@ -134,6 +134,10 @@ int bch2_accounting_validate(struct bch_fs *c, struct bkey_s_c k, void *end = &acc_k + 1; int ret = 0; + bkey_fsck_err_on(bversion_zero(k.k->bversion), + c, accounting_key_version_0, + "accounting key with version=0"); + switch (acc_k.type) { case BCH_DISK_ACCOUNTING_nr_inodes: end = field_end(acc_k, nr_inodes); @@ -291,7 +295,7 @@ static int __bch2_accounting_mem_insert(struct bch_fs *c, struct bkey_s_c_accoun struct accounting_mem_entry n = { .pos = a.k->p, - .version = a.k->version, + .bversion = a.k->bversion, .nr_counters = bch2_accounting_counters(a.k), .v[0] = __alloc_percpu_gfp(n.nr_counters * sizeof(u64), sizeof(u64), GFP_KERNEL), @@ -319,11 +323,13 @@ err: return -BCH_ERR_ENOMEM_disk_accounting; } -int bch2_accounting_mem_insert(struct bch_fs *c, struct bkey_s_c_accounting a, bool gc) +int bch2_accounting_mem_insert(struct bch_fs *c, struct bkey_s_c_accounting a, + enum bch_accounting_mode mode) { struct bch_replicas_padded r; - if (accounting_to_replicas(&r.e, a.k->p) && + if (mode != BCH_ACCOUNTING_read && + accounting_to_replicas(&r.e, a.k->p) && !bch2_replicas_marked_locked(c, &r.e)) return -BCH_ERR_btree_insert_need_mark_replicas; @@ -566,7 +572,9 @@ int bch2_gc_accounting_done(struct bch_fs *c) struct { __BKEY_PADDED(k, BCH_ACCOUNTING_MAX_COUNTERS); } k_i; accounting_key_init(&k_i.k, &acc_k, src_v, nr); - bch2_accounting_mem_mod_locked(trans, bkey_i_to_s_c_accounting(&k_i.k), false, false); + bch2_accounting_mem_mod_locked(trans, + bkey_i_to_s_c_accounting(&k_i.k), + BCH_ACCOUNTING_normal); preempt_disable(); struct bch_fs_usage_base *dst = this_cpu_ptr(c->usage); @@ -589,30 +597,14 @@ fsck_err: static int accounting_read_key(struct btree_trans *trans, struct bkey_s_c k) { struct bch_fs *c = trans->c; - struct printbuf buf = PRINTBUF; if (k.k->type != KEY_TYPE_accounting) return 0; percpu_down_read(&c->mark_lock); - int ret = bch2_accounting_mem_mod_locked(trans, bkey_s_c_to_accounting(k), false, true); + int ret = bch2_accounting_mem_mod_locked(trans, bkey_s_c_to_accounting(k), + BCH_ACCOUNTING_read); percpu_up_read(&c->mark_lock); - - if (bch2_accounting_key_is_zero(bkey_s_c_to_accounting(k)) && - ret == -BCH_ERR_btree_insert_need_mark_replicas) - ret = 0; - - struct disk_accounting_pos acc; - bpos_to_disk_accounting_pos(&acc, k.k->p); - - if (fsck_err_on(ret == -BCH_ERR_btree_insert_need_mark_replicas, - trans, accounting_replicas_not_marked, - "accounting not marked in superblock replicas\n %s", - (bch2_accounting_key_to_text(&buf, &acc), - buf.buf))) - ret = bch2_accounting_update_sb_one(c, k.k->p); -fsck_err: - printbuf_exit(&buf); return ret; } @@ -624,6 +616,7 @@ int bch2_accounting_read(struct bch_fs *c) { struct bch_accounting_mem *acc = &c->accounting; struct btree_trans *trans = bch2_trans_get(c); + struct printbuf buf = PRINTBUF; int ret = for_each_btree_key(trans, iter, BTREE_ID_accounting, POS_MIN, @@ -647,7 +640,7 @@ int bch2_accounting_read(struct bch_fs *c) accounting_pos_cmp, &k.k->p); bool applied = idx < acc->k.nr && - bversion_cmp(acc->k.data[idx].version, k.k->version) >= 0; + bversion_cmp(acc->k.data[idx].bversion, k.k->bversion) >= 0; if (applied) continue; @@ -655,7 +648,7 @@ int bch2_accounting_read(struct bch_fs *c) if (i + 1 < &darray_top(*keys) && i[1].k->k.type == KEY_TYPE_accounting && !journal_key_cmp(i, i + 1)) { - BUG_ON(bversion_cmp(i[0].k->k.version, i[1].k->k.version) >= 0); + WARN_ON(bversion_cmp(i[0].k->k.bversion, i[1].k->k.bversion) >= 0); i[1].journal_seq = i[0].journal_seq; @@ -674,6 +667,45 @@ int bch2_accounting_read(struct bch_fs *c) keys->gap = keys->nr = dst - keys->data; percpu_down_read(&c->mark_lock); + for (unsigned i = 0; i < acc->k.nr; i++) { + u64 v[BCH_ACCOUNTING_MAX_COUNTERS]; + bch2_accounting_mem_read_counters(acc, i, v, ARRAY_SIZE(v), false); + + if (bch2_is_zero(v, sizeof(v[0]) * acc->k.data[i].nr_counters)) + continue; + + struct bch_replicas_padded r; + if (!accounting_to_replicas(&r.e, acc->k.data[i].pos)) + continue; + + /* + * If the replicas entry is invalid it'll get cleaned up by + * check_allocations: + */ + if (bch2_replicas_entry_validate(&r.e, c, &buf)) + continue; + + struct disk_accounting_pos k; + bpos_to_disk_accounting_pos(&k, acc->k.data[i].pos); + + if (fsck_err_on(!bch2_replicas_marked_locked(c, &r.e), + trans, accounting_replicas_not_marked, + "accounting not marked in superblock replicas\n %s", + (printbuf_reset(&buf), + bch2_accounting_key_to_text(&buf, &k), + buf.buf))) { + /* + * We're not RW yet and still single threaded, dropping + * and retaking lock is ok: + */ + percpu_up_read(&c->mark_lock); + ret = bch2_mark_replicas(c, &r.e); + if (ret) + goto fsck_err; + percpu_down_read(&c->mark_lock); + } + } + preempt_disable(); struct bch_fs_usage_base *usage = this_cpu_ptr(c->usage); @@ -709,8 +741,10 @@ int bch2_accounting_read(struct bch_fs *c) } } preempt_enable(); +fsck_err: percpu_up_read(&c->mark_lock); err: + printbuf_exit(&buf); bch2_trans_put(trans); bch_err_fn(c, ret); return ret; diff --git a/fs/bcachefs/disk_accounting.h b/fs/bcachefs/disk_accounting.h index f29fd0dd9581..4ea6c8a092bc 100644 --- a/fs/bcachefs/disk_accounting.h +++ b/fs/bcachefs/disk_accounting.h @@ -36,8 +36,8 @@ static inline void bch2_accounting_accumulate(struct bkey_i_accounting *dst, for (unsigned i = 0; i < bch2_accounting_counters(&dst->k); i++) dst->v.d[i] += src.v->d[i]; - if (bversion_cmp(dst->k.version, src.k->version) < 0) - dst->k.version = src.k->version; + if (bversion_cmp(dst->k.bversion, src.k->bversion) < 0) + dst->k.bversion = src.k->bversion; } static inline void fs_usage_data_type_to_base(struct bch_fs_usage_base *fs_usage, @@ -103,23 +103,35 @@ static inline int accounting_pos_cmp(const void *_l, const void *_r) return bpos_cmp(*l, *r); } -int bch2_accounting_mem_insert(struct bch_fs *, struct bkey_s_c_accounting, bool); +enum bch_accounting_mode { + BCH_ACCOUNTING_normal, + BCH_ACCOUNTING_gc, + BCH_ACCOUNTING_read, +}; + +int bch2_accounting_mem_insert(struct bch_fs *, struct bkey_s_c_accounting, enum bch_accounting_mode); void bch2_accounting_mem_gc(struct bch_fs *); /* * Update in memory counters so they match the btree update we're doing; called * from transaction commit path */ -static inline int bch2_accounting_mem_mod_locked(struct btree_trans *trans, struct bkey_s_c_accounting a, bool gc, bool read) +static inline int bch2_accounting_mem_mod_locked(struct btree_trans *trans, + struct bkey_s_c_accounting a, + enum bch_accounting_mode mode) { struct bch_fs *c = trans->c; + struct bch_accounting_mem *acc = &c->accounting; struct disk_accounting_pos acc_k; bpos_to_disk_accounting_pos(&acc_k, a.k->p); + bool gc = mode == BCH_ACCOUNTING_gc; + + EBUG_ON(gc && !acc->gc_running); if (acc_k.type == BCH_DISK_ACCOUNTING_inum) return 0; - if (!gc && !read) { + if (mode == BCH_ACCOUNTING_normal) { switch (acc_k.type) { case BCH_DISK_ACCOUNTING_persistent_reserved: trans->fs_usage_delta.reserved += acc_k.persistent_reserved.nr_replicas * a.v->d[0]; @@ -140,14 +152,11 @@ static inline int bch2_accounting_mem_mod_locked(struct btree_trans *trans, stru } } - struct bch_accounting_mem *acc = &c->accounting; unsigned idx; - EBUG_ON(gc && !acc->gc_running); - while ((idx = eytzinger0_find(acc->k.data, acc->k.nr, sizeof(acc->k.data[0]), accounting_pos_cmp, &a.k->p)) >= acc->k.nr) { - int ret = bch2_accounting_mem_insert(c, a, gc); + int ret = bch2_accounting_mem_insert(c, a, mode); if (ret) return ret; } @@ -164,7 +173,7 @@ static inline int bch2_accounting_mem_mod_locked(struct btree_trans *trans, stru static inline int bch2_accounting_mem_add(struct btree_trans *trans, struct bkey_s_c_accounting a, bool gc) { percpu_down_read(&trans->c->mark_lock); - int ret = bch2_accounting_mem_mod_locked(trans, a, gc, false); + int ret = bch2_accounting_mem_mod_locked(trans, a, gc ? BCH_ACCOUNTING_gc : BCH_ACCOUNTING_normal); percpu_up_read(&trans->c->mark_lock); return ret; } diff --git a/fs/bcachefs/disk_accounting_types.h b/fs/bcachefs/disk_accounting_types.h index 1687a45177a7..b1982131b206 100644 --- a/fs/bcachefs/disk_accounting_types.h +++ b/fs/bcachefs/disk_accounting_types.h @@ -6,7 +6,7 @@ struct accounting_mem_entry { struct bpos pos; - struct bversion version; + struct bversion bversion; unsigned nr_counters; u64 __percpu *v[2]; }; diff --git a/fs/bcachefs/error.c b/fs/bcachefs/error.c index 95afa7bf2020..7a79f695ba2e 100644 --- a/fs/bcachefs/error.c +++ b/fs/bcachefs/error.c @@ -239,7 +239,19 @@ int __bch2_fsck_err(struct bch_fs *c, if (!c) c = trans->c; - WARN_ON(!trans && bch2_current_has_btree_trans(c)); + /* + * Ugly: if there's a transaction in the current task it has to be + * passed in to unlock if we prompt for user input. + * + * But, plumbing a transaction and transaction restarts into + * bkey_validate() is problematic. + * + * So: + * - make all bkey errors AUTOFIX, they're simple anyways (we just + * delete the key) + * - and we don't need to warn if we're not prompting + */ + WARN_ON(!(flags & FSCK_AUTOFIX) && !trans && bch2_current_has_btree_trans(c)); if ((flags & FSCK_CAN_FIX) && test_bit(err, c->sb.errors_silent)) @@ -381,6 +393,14 @@ int __bch2_fsck_err(struct bch_fs *c, !(flags & FSCK_CAN_IGNORE))) ret = -BCH_ERR_fsck_errors_not_fixed; + bool exiting = + test_bit(BCH_FS_fsck_running, &c->flags) && + (ret != -BCH_ERR_fsck_fix && + ret != -BCH_ERR_fsck_ignore); + + if (exiting) + print = true; + if (print) { if (bch2_fs_stdio_redirect(c)) bch2_print(c, "%s\n", out->buf); @@ -388,9 +408,7 @@ int __bch2_fsck_err(struct bch_fs *c, bch2_print_string_as_lines(KERN_ERR, out->buf); } - if (test_bit(BCH_FS_fsck_running, &c->flags) && - (ret != -BCH_ERR_fsck_fix && - ret != -BCH_ERR_fsck_ignore)) + if (exiting) bch_err(c, "Unable to continue, halting"); else if (suppressing) bch_err(c, "Ratelimiting new instances of previous error"); @@ -418,10 +436,17 @@ err: int __bch2_bkey_fsck_err(struct bch_fs *c, struct bkey_s_c k, - enum bch_fsck_flags flags, + enum bch_validate_flags validate_flags, enum bch_sb_error_id err, const char *fmt, ...) { + if (validate_flags & BCH_VALIDATE_silent) + return -BCH_ERR_fsck_delete_bkey; + + unsigned fsck_flags = 0; + if (!(validate_flags & (BCH_VALIDATE_write|BCH_VALIDATE_commit))) + fsck_flags |= FSCK_AUTOFIX|FSCK_CAN_FIX; + struct printbuf buf = PRINTBUF; va_list args; @@ -433,7 +458,7 @@ int __bch2_bkey_fsck_err(struct bch_fs *c, va_end(args); prt_str(&buf, ": delete?"); - int ret = __bch2_fsck_err(c, NULL, flags, err, "%s", buf.buf); + int ret = __bch2_fsck_err(c, NULL, fsck_flags, err, "%s", buf.buf); printbuf_exit(&buf); return ret; } diff --git a/fs/bcachefs/error.h b/fs/bcachefs/error.h index 2f1b86978f36..6551ada926b6 100644 --- a/fs/bcachefs/error.h +++ b/fs/bcachefs/error.h @@ -167,10 +167,11 @@ void bch2_flush_fsck_errs(struct bch_fs *); #define fsck_err_on(cond, c, _err_type, ...) \ __fsck_err_on(cond, c, FSCK_CAN_FIX|FSCK_CAN_IGNORE, _err_type, __VA_ARGS__) +enum bch_validate_flags; __printf(5, 6) int __bch2_bkey_fsck_err(struct bch_fs *, struct bkey_s_c, - enum bch_fsck_flags, + enum bch_validate_flags, enum bch_sb_error_id, const char *, ...); @@ -180,11 +181,7 @@ int __bch2_bkey_fsck_err(struct bch_fs *, */ #define bkey_fsck_err(c, _err_type, _err_msg, ...) \ do { \ - if ((flags & BCH_VALIDATE_silent)) { \ - ret = -BCH_ERR_fsck_delete_bkey; \ - goto fsck_err; \ - } \ - int _ret = __bch2_bkey_fsck_err(c, k, FSCK_CAN_FIX, \ + int _ret = __bch2_bkey_fsck_err(c, k, flags, \ BCH_FSCK_ERR_##_err_type, \ _err_msg, ##__VA_ARGS__); \ if (_ret != -BCH_ERR_fsck_fix && \ diff --git a/fs/bcachefs/fs.c b/fs/bcachefs/fs.c index 4a1bb07a2574..5bfc26d58270 100644 --- a/fs/bcachefs/fs.c +++ b/fs/bcachefs/fs.c @@ -174,20 +174,24 @@ static const struct rhashtable_params bch2_vfs_inodes_params = { .automatic_shrinking = true, }; -static void __wait_on_freeing_inode(struct inode *inode) +struct bch_inode_info *__bch2_inode_hash_find(struct bch_fs *c, subvol_inum inum) { - wait_queue_head_t *wq; - DEFINE_WAIT_BIT(wait, &inode->i_state, __I_NEW); - wq = bit_waitqueue(&inode->i_state, __I_NEW); - prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE); - spin_unlock(&inode->i_lock); - schedule(); - finish_wait(wq, &wait.wq_entry); + return rhashtable_lookup_fast(&c->vfs_inodes_table, &inum, bch2_vfs_inodes_params); } -struct bch_inode_info *__bch2_inode_hash_find(struct bch_fs *c, subvol_inum inum) +static void __wait_on_freeing_inode(struct bch_fs *c, + struct bch_inode_info *inode, + subvol_inum inum) { - return rhashtable_lookup_fast(&c->vfs_inodes_table, &inum, bch2_vfs_inodes_params); + wait_queue_head_t *wq; + DEFINE_WAIT_BIT(wait, &inode->v.i_state, __I_NEW); + wq = inode_bit_waitqueue(&wait, &inode->v, __I_NEW); + prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE); + spin_unlock(&inode->v.i_lock); + + if (__bch2_inode_hash_find(c, inum) == inode) + schedule_timeout(HZ * 10); + finish_wait(wq, &wait.wq_entry); } static struct bch_inode_info *bch2_inode_hash_find(struct bch_fs *c, struct btree_trans *trans, @@ -204,10 +208,10 @@ repeat: } if ((inode->v.i_state & (I_FREEING|I_WILL_FREE))) { if (!trans) { - __wait_on_freeing_inode(&inode->v); + __wait_on_freeing_inode(c, inode, inum); } else { bch2_trans_unlock(trans); - __wait_on_freeing_inode(&inode->v); + __wait_on_freeing_inode(c, inode, inum); int ret = bch2_trans_relock(trans); if (ret) return ERR_PTR(ret); @@ -232,6 +236,11 @@ static void bch2_inode_hash_remove(struct bch_fs *c, struct bch_inode_info *inod &inode->hash, bch2_vfs_inodes_params); BUG_ON(ret); inode->v.i_hash.pprev = NULL; + /* + * This pairs with the bch2_inode_hash_find() -> + * __wait_on_freeing_inode() path + */ + inode_wake_up_bit(&inode->v, __I_NEW); } } diff --git a/fs/bcachefs/fsck.c b/fs/bcachefs/fsck.c index 9b3470a97546..b8a6ceb0cc7a 100644 --- a/fs/bcachefs/fsck.c +++ b/fs/bcachefs/fsck.c @@ -21,6 +21,49 @@ #include <linux/bsearch.h> #include <linux/dcache.h> /* struct qstr */ +static bool inode_points_to_dirent(struct bch_inode_unpacked *inode, + struct bkey_s_c_dirent d) +{ + return inode->bi_dir == d.k->p.inode && + inode->bi_dir_offset == d.k->p.offset; +} + +static int dirent_points_to_inode_nowarn(struct bkey_s_c_dirent d, + struct bch_inode_unpacked *inode) +{ + if (d.v->d_type == DT_SUBVOL + ? le32_to_cpu(d.v->d_child_subvol) == inode->bi_subvol + : le64_to_cpu(d.v->d_inum) == inode->bi_inum) + return 0; + return -BCH_ERR_ENOENT_dirent_doesnt_match_inode; +} + +static void dirent_inode_mismatch_msg(struct printbuf *out, + struct bch_fs *c, + struct bkey_s_c_dirent dirent, + struct bch_inode_unpacked *inode) +{ + prt_str(out, "inode points to dirent that does not point back:"); + prt_newline(out); + bch2_bkey_val_to_text(out, c, dirent.s_c); + prt_newline(out); + bch2_inode_unpacked_to_text(out, inode); +} + +static int dirent_points_to_inode(struct bch_fs *c, + struct bkey_s_c_dirent dirent, + struct bch_inode_unpacked *inode) +{ + int ret = dirent_points_to_inode_nowarn(dirent, inode); + if (ret) { + struct printbuf buf = PRINTBUF; + dirent_inode_mismatch_msg(&buf, c, dirent, inode); + bch_warn(c, "%s", buf.buf); + printbuf_exit(&buf); + } + return ret; +} + /* * XXX: this is handling transaction restarts without returning * -BCH_ERR_transaction_restart_nested, this is not how we do things anymore: @@ -94,16 +137,15 @@ found: return ret; } -static int lookup_inode(struct btree_trans *trans, u64 inode_nr, - struct bch_inode_unpacked *inode, - u32 *snapshot) +static int lookup_inode(struct btree_trans *trans, u64 inode_nr, u32 snapshot, + struct bch_inode_unpacked *inode) { struct btree_iter iter; struct bkey_s_c k; int ret; k = bch2_bkey_get_iter(trans, &iter, BTREE_ID_inodes, - SPOS(0, inode_nr, *snapshot), 0); + SPOS(0, inode_nr, snapshot), 0); ret = bkey_err(k); if (ret) goto err; @@ -111,8 +153,6 @@ static int lookup_inode(struct btree_trans *trans, u64 inode_nr, ret = bkey_is_inode(k.k) ? bch2_inode_unpack(k, inode) : -BCH_ERR_ENOENT_inode; - if (!ret) - *snapshot = iter.pos.snapshot; err: bch2_trans_iter_exit(trans, &iter); return ret; @@ -207,8 +247,7 @@ static int lookup_lostfound(struct btree_trans *trans, u32 snapshot, struct bch_inode_unpacked root_inode; struct bch_hash_info root_hash_info; - u32 root_inode_snapshot = snapshot; - ret = lookup_inode(trans, root_inum.inum, &root_inode, &root_inode_snapshot); + ret = lookup_inode(trans, root_inum.inum, snapshot, &root_inode); bch_err_msg(c, ret, "looking up root inode %llu for subvol %u", root_inum.inum, le32_to_cpu(st.master_subvol)); if (ret) @@ -234,17 +273,23 @@ static int lookup_lostfound(struct btree_trans *trans, u32 snapshot, * The bch2_check_dirents pass has already run, dangling dirents * shouldn't exist here: */ - ret = lookup_inode(trans, inum, lostfound, &snapshot); + ret = lookup_inode(trans, inum, snapshot, lostfound); bch_err_msg(c, ret, "looking up lost+found %llu:%u in (root inode %llu, snapshot root %u)", inum, snapshot, root_inum.inum, bch2_snapshot_root(c, snapshot)); return ret; create_lostfound: /* + * we always create lost+found in the root snapshot; we don't want + * different branches of the snapshot tree to have different lost+found + */ + snapshot = le32_to_cpu(st.root_snapshot); + /* * XXX: we could have a nicer log message here if we had a nice way to * walk backpointers to print a path */ - bch_notice(c, "creating lost+found in snapshot %u", le32_to_cpu(st.root_snapshot)); + bch_notice(c, "creating lost+found in subvol %llu snapshot %u", + root_inum.subvol, le32_to_cpu(st.root_snapshot)); u64 now = bch2_current_time(c); struct btree_iter lostfound_iter = { NULL }; @@ -253,6 +298,7 @@ create_lostfound: bch2_inode_init_early(c, lostfound); bch2_inode_init_late(lostfound, now, 0, 0, S_IFDIR|0700, 0, &root_inode); lostfound->bi_dir = root_inode.bi_inum; + lostfound->bi_snapshot = le32_to_cpu(st.root_snapshot); root_inode.bi_nlink++; @@ -280,9 +326,7 @@ err: return ret; } -static int reattach_inode(struct btree_trans *trans, - struct bch_inode_unpacked *inode, - u32 inode_snapshot) +static int reattach_inode(struct btree_trans *trans, struct bch_inode_unpacked *inode) { struct bch_fs *c = trans->c; struct bch_hash_info dir_hash; @@ -290,7 +334,7 @@ static int reattach_inode(struct btree_trans *trans, char name_buf[20]; struct qstr name; u64 dir_offset = 0; - u32 dirent_snapshot = inode_snapshot; + u32 dirent_snapshot = inode->bi_snapshot; int ret; if (inode->bi_subvol) { @@ -311,14 +355,18 @@ static int reattach_inode(struct btree_trans *trans, if (ret) return ret; - if (S_ISDIR(inode->bi_mode)) { - lostfound.bi_nlink++; + lostfound.bi_nlink += S_ISDIR(inode->bi_mode); - ret = __bch2_fsck_write_inode(trans, &lostfound, U32_MAX); - if (ret) - return ret; + /* ensure lost+found inode is also present in inode snapshot */ + if (!inode->bi_subvol) { + BUG_ON(!bch2_snapshot_is_ancestor(c, inode->bi_snapshot, lostfound.bi_snapshot)); + lostfound.bi_snapshot = inode->bi_snapshot; } + ret = __bch2_fsck_write_inode(trans, &lostfound); + if (ret) + return ret; + dir_hash = bch2_hash_info_init(c, &lostfound); name = (struct qstr) QSTR(name_buf); @@ -340,20 +388,23 @@ static int reattach_inode(struct btree_trans *trans, inode->bi_dir = lostfound.bi_inum; inode->bi_dir_offset = dir_offset; - return __bch2_fsck_write_inode(trans, inode, inode_snapshot); + return __bch2_fsck_write_inode(trans, inode); } static int remove_backpointer(struct btree_trans *trans, struct bch_inode_unpacked *inode) { - struct btree_iter iter; - struct bkey_s_c_dirent d; - int ret; + if (!inode->bi_dir) + return 0; - d = bch2_bkey_get_iter_typed(trans, &iter, BTREE_ID_dirents, - POS(inode->bi_dir, inode->bi_dir_offset), 0, + struct bch_fs *c = trans->c; + struct btree_iter iter; + struct bkey_s_c_dirent d = + bch2_bkey_get_iter_typed(trans, &iter, BTREE_ID_dirents, + SPOS(inode->bi_dir, inode->bi_dir_offset, inode->bi_snapshot), 0, dirent); - ret = bkey_err(d) ?: + int ret = bkey_err(d) ?: + dirent_points_to_inode(c, d, inode) ?: __remove_dirent(trans, d.k->p); bch2_trans_iter_exit(trans, &iter); return ret; @@ -371,11 +422,12 @@ static int reattach_subvol(struct btree_trans *trans, struct bkey_s_c_subvolume return ret; ret = remove_backpointer(trans, &inode); - bch_err_msg(c, ret, "removing dirent"); + if (!bch2_err_matches(ret, ENOENT)) + bch_err_msg(c, ret, "removing dirent"); if (ret) return ret; - ret = reattach_inode(trans, &inode, le32_to_cpu(s.v->snapshot)); + ret = reattach_inode(trans, &inode); bch_err_msg(c, ret, "reattaching inode %llu", inode.bi_inum); return ret; } @@ -493,8 +545,9 @@ static int reconstruct_inode(struct btree_trans *trans, enum btree_id btree, u32 bch2_inode_init_late(&new_inode, bch2_current_time(c), 0, 0, i_mode|0600, 0, NULL); new_inode.bi_size = i_size; new_inode.bi_inum = inum; + new_inode.bi_snapshot = snapshot; - return __bch2_fsck_write_inode(trans, &new_inode, snapshot); + return __bch2_fsck_write_inode(trans, &new_inode); } struct snapshots_seen { @@ -626,12 +679,12 @@ static int ref_visible2(struct bch_fs *c, struct inode_walker_entry { struct bch_inode_unpacked inode; u32 snapshot; - bool seen_this_pos; u64 count; }; struct inode_walker { bool first_this_inode; + bool have_inodes; bool recalculate_sums; struct bpos last_pos; @@ -669,6 +722,12 @@ static int get_inodes_all_snapshots(struct btree_trans *trans, struct bkey_s_c k; int ret; + /* + * We no longer have inodes for w->last_pos; clear this to avoid + * screwing up check_i_sectors/check_subdir_count if we take a + * transaction restart here: + */ + w->have_inodes = false; w->recalculate_sums = false; w->inodes.nr = 0; @@ -686,6 +745,7 @@ static int get_inodes_all_snapshots(struct btree_trans *trans, return ret; w->first_this_inode = true; + w->have_inodes = true; return 0; } @@ -740,9 +800,6 @@ static struct inode_walker_entry *walk_inode(struct btree_trans *trans, int ret = get_inodes_all_snapshots(trans, w, k.k->p.inode); if (ret) return ERR_PTR(ret); - } else if (bkey_cmp(w->last_pos, k.k->p)) { - darray_for_each(w->inodes, i) - i->seen_this_pos = false; } w->last_pos = k.k->p; @@ -896,21 +953,6 @@ static struct bkey_s_c_dirent inode_get_dirent(struct btree_trans *trans, return dirent_get_by_pos(trans, iter, SPOS(inode->bi_dir, inode->bi_dir_offset, *snapshot)); } -static bool inode_points_to_dirent(struct bch_inode_unpacked *inode, - struct bkey_s_c_dirent d) -{ - return inode->bi_dir == d.k->p.inode && - inode->bi_dir_offset == d.k->p.offset; -} - -static bool dirent_points_to_inode(struct bkey_s_c_dirent d, - struct bch_inode_unpacked *inode) -{ - return d.v->d_type == DT_SUBVOL - ? le32_to_cpu(d.v->d_child_subvol) == inode->bi_subvol - : le64_to_cpu(d.v->d_inum) == inode->bi_inum; -} - static int check_inode_deleted_list(struct btree_trans *trans, struct bpos p) { struct btree_iter iter; @@ -920,13 +962,14 @@ static int check_inode_deleted_list(struct btree_trans *trans, struct bpos p) return ret; } -static int check_inode_dirent_inode(struct btree_trans *trans, struct bkey_s_c inode_k, +static int check_inode_dirent_inode(struct btree_trans *trans, struct bch_inode_unpacked *inode, - u32 inode_snapshot, bool *write_inode) + bool *write_inode) { struct bch_fs *c = trans->c; struct printbuf buf = PRINTBUF; + u32 inode_snapshot = inode->bi_snapshot; struct btree_iter dirent_iter = {}; struct bkey_s_c_dirent d = inode_get_dirent(trans, &dirent_iter, inode, &inode_snapshot); int ret = bkey_err(d); @@ -936,13 +979,13 @@ static int check_inode_dirent_inode(struct btree_trans *trans, struct bkey_s_c i if (fsck_err_on(ret, trans, inode_points_to_missing_dirent, "inode points to missing dirent\n%s", - (bch2_bkey_val_to_text(&buf, c, inode_k), buf.buf)) || - fsck_err_on(!ret && !dirent_points_to_inode(d, inode), + (bch2_inode_unpacked_to_text(&buf, inode), buf.buf)) || + fsck_err_on(!ret && dirent_points_to_inode_nowarn(d, inode), trans, inode_points_to_wrong_dirent, - "inode points to dirent that does not point back:\n%s", - (bch2_bkey_val_to_text(&buf, c, inode_k), - prt_newline(&buf), - bch2_bkey_val_to_text(&buf, c, d.s_c), buf.buf))) { + "%s", + (printbuf_reset(&buf), + dirent_inode_mismatch_msg(&buf, c, d, inode), + buf.buf))) { /* * We just clear the backpointer fields for now. If we find a * dirent that points to this inode in check_dirents(), we'll @@ -963,7 +1006,7 @@ fsck_err: return ret; } -static bool bch2_inode_open(struct bch_fs *c, struct bpos p) +static bool bch2_inode_is_open(struct bch_fs *c, struct bpos p) { subvol_inum inum = { .subvol = snapshot_t(c, p.snapshot)->subvol, @@ -972,7 +1015,7 @@ static bool bch2_inode_open(struct bch_fs *c, struct bpos p) /* snapshot tree corruption, can't safely delete */ if (!inum.subvol) { - bch_err_ratelimited(c, "%s(): snapshot %u has no subvol", __func__, p.snapshot); + bch_warn_ratelimited(c, "%s(): snapshot %u has no subvol, unlinked but can't safely delete", __func__, p.snapshot); return true; } @@ -987,6 +1030,7 @@ static int check_inode(struct btree_trans *trans, bool full) { struct bch_fs *c = trans->c; + struct printbuf buf = PRINTBUF; struct bch_inode_unpacked u; bool do_update = false; int ret; @@ -1020,7 +1064,41 @@ static int check_inode(struct btree_trans *trans, trans, inode_snapshot_mismatch, "inodes in different snapshots don't match")) { bch_err(c, "repair not implemented yet"); - return -BCH_ERR_fsck_repair_unimplemented; + ret = -BCH_ERR_fsck_repair_unimplemented; + goto err_noprint; + } + + if (u.bi_dir || u.bi_dir_offset) { + ret = check_inode_dirent_inode(trans, &u, &do_update); + if (ret) + goto err; + } + + if (fsck_err_on(u.bi_dir && (u.bi_flags & BCH_INODE_unlinked), + trans, inode_unlinked_but_has_dirent, + "inode unlinked but has dirent\n%s", + (printbuf_reset(&buf), + bch2_inode_unpacked_to_text(&buf, &u), + buf.buf))) { + u.bi_flags &= ~BCH_INODE_unlinked; + do_update = true; + } + + if (S_ISDIR(u.bi_mode) && (u.bi_flags & BCH_INODE_unlinked)) { + /* Check for this early so that check_unreachable_inode() will reattach it */ + + ret = bch2_empty_dir_snapshot(trans, k.k->p.offset, 0, k.k->p.snapshot); + if (ret && ret != -BCH_ERR_ENOTEMPTY_dir_not_empty) + goto err; + + fsck_err_on(ret, trans, inode_dir_unlinked_but_not_empty, + "dir unlinked but not empty\n%s", + (printbuf_reset(&buf), + bch2_inode_unpacked_to_text(&buf, &u), + buf.buf)); + u.bi_flags &= ~BCH_INODE_unlinked; + do_update = true; + ret = 0; } if ((u.bi_flags & (BCH_INODE_i_size_dirty|BCH_INODE_unlinked)) && @@ -1033,42 +1111,56 @@ static int check_inode(struct btree_trans *trans, u.bi_flags &= ~BCH_INODE_i_size_dirty|BCH_INODE_unlinked; - ret = __bch2_fsck_write_inode(trans, &u, iter->pos.snapshot); + ret = __bch2_fsck_write_inode(trans, &u); bch_err_msg(c, ret, "in fsck updating inode"); if (ret) - return ret; + goto err_noprint; if (!bpos_eq(new_min_pos, POS_MIN)) bch2_btree_iter_set_pos(iter, bpos_predecessor(new_min_pos)); - return 0; + goto err_noprint; } if (u.bi_flags & BCH_INODE_unlinked) { - ret = check_inode_deleted_list(trans, k.k->p); - if (ret < 0) - return ret; + if (!test_bit(BCH_FS_started, &c->flags)) { + /* + * If we're not in online fsck, don't delete unlinked + * inodes, just make sure they're on the deleted list. + * + * They might be referred to by a logged operation - + * i.e. we might have crashed in the middle of a + * truncate on an unlinked but open file - so we want to + * let the delete_dead_inodes kill it after resuming + * logged ops. + */ + ret = check_inode_deleted_list(trans, k.k->p); + if (ret < 0) + goto err_noprint; - fsck_err_on(!ret, - trans, unlinked_inode_not_on_deleted_list, - "inode %llu:%u unlinked, but not on deleted list", - u.bi_inum, k.k->p.snapshot); - ret = 0; - } + fsck_err_on(!ret, + trans, unlinked_inode_not_on_deleted_list, + "inode %llu:%u unlinked, but not on deleted list", + u.bi_inum, k.k->p.snapshot); - if (u.bi_flags & BCH_INODE_unlinked && - !bch2_inode_open(c, k.k->p) && - (!c->sb.clean || - fsck_err(trans, inode_unlinked_but_clean, - "filesystem marked clean, but inode %llu unlinked", - u.bi_inum))) { - ret = bch2_inode_rm_snapshot(trans, u.bi_inum, iter->pos.snapshot); - bch_err_msg(c, ret, "in fsck deleting inode"); - return ret; + ret = bch2_btree_bit_mod_buffered(trans, BTREE_ID_deleted_inodes, k.k->p, 1); + if (ret) + goto err; + } else { + if (fsck_err_on(!bch2_inode_is_open(c, k.k->p), + trans, inode_unlinked_and_not_open, + "inode %llu%u unlinked and not open", + u.bi_inum, u.bi_snapshot)) { + ret = bch2_inode_rm_snapshot(trans, u.bi_inum, iter->pos.snapshot); + bch_err_msg(c, ret, "in fsck deleting inode"); + goto err_noprint; + } + } } + /* i_size_dirty is vestigal, since we now have logged ops for truncate * */ if (u.bi_flags & BCH_INODE_i_size_dirty && - (!c->sb.clean || + (!test_bit(BCH_FS_clean_recovery, &c->flags) || fsck_err(trans, inode_i_size_dirty_but_clean, "filesystem marked clean, but inode %llu has i_size dirty", u.bi_inum))) { @@ -1097,8 +1189,9 @@ static int check_inode(struct btree_trans *trans, do_update = true; } + /* i_sectors_dirty is vestigal, i_sectors is always updated transactionally */ if (u.bi_flags & BCH_INODE_i_sectors_dirty && - (!c->sb.clean || + (!test_bit(BCH_FS_clean_recovery, &c->flags) || fsck_err(trans, inode_i_sectors_dirty_but_clean, "filesystem marked clean, but inode %llu has i_sectors dirty", u.bi_inum))) { @@ -1125,12 +1218,6 @@ static int check_inode(struct btree_trans *trans, do_update = true; } - if (u.bi_dir || u.bi_dir_offset) { - ret = check_inode_dirent_inode(trans, k, &u, k.k->p.snapshot, &do_update); - if (ret) - goto err; - } - if (fsck_err_on(u.bi_parent_subvol && (u.bi_subvol == 0 || u.bi_subvol == BCACHEFS_ROOT_SUBVOL), @@ -1172,14 +1259,16 @@ static int check_inode(struct btree_trans *trans, } do_update: if (do_update) { - ret = __bch2_fsck_write_inode(trans, &u, iter->pos.snapshot); + ret = __bch2_fsck_write_inode(trans, &u); bch_err_msg(c, ret, "in fsck updating inode"); if (ret) - return ret; + goto err_noprint; } err: fsck_err: bch_err_fn(c, ret); +err_noprint: + printbuf_exit(&buf); return ret; } @@ -1295,7 +1384,7 @@ static int check_i_sectors_notnested(struct btree_trans *trans, struct inode_wal w->last_pos.inode, i->snapshot, i->inode.bi_sectors, i->count)) { i->inode.bi_sectors = i->count; - ret = bch2_fsck_write_inode(trans, &i->inode, i->snapshot); + ret = bch2_fsck_write_inode(trans, &i->inode); if (ret) break; } @@ -1555,10 +1644,10 @@ static int check_extent(struct btree_trans *trans, struct btree_iter *iter, struct bkey_s_c k, struct inode_walker *inode, struct snapshots_seen *s, - struct extent_ends *extent_ends) + struct extent_ends *extent_ends, + struct disk_reservation *res) { struct bch_fs *c = trans->c; - struct inode_walker_entry *i; struct printbuf buf = PRINTBUF; int ret = 0; @@ -1568,7 +1657,7 @@ static int check_extent(struct btree_trans *trans, struct btree_iter *iter, goto out; } - if (inode->last_pos.inode != k.k->p.inode) { + if (inode->last_pos.inode != k.k->p.inode && inode->have_inodes) { ret = check_i_sectors(trans, inode); if (ret) goto err; @@ -1578,12 +1667,12 @@ static int check_extent(struct btree_trans *trans, struct btree_iter *iter, if (ret) goto err; - i = walk_inode(trans, inode, k); - ret = PTR_ERR_OR_ZERO(i); + struct inode_walker_entry *extent_i = walk_inode(trans, inode, k); + ret = PTR_ERR_OR_ZERO(extent_i); if (ret) goto err; - ret = check_key_has_inode(trans, iter, inode, i, k); + ret = check_key_has_inode(trans, iter, inode, extent_i, k); if (ret) goto err; @@ -1592,24 +1681,19 @@ static int check_extent(struct btree_trans *trans, struct btree_iter *iter, &inode->recalculate_sums); if (ret) goto err; - } - - /* - * Check inodes in reverse order, from oldest snapshots to newest, - * starting from the inode that matches this extent's snapshot. If we - * didn't have one, iterate over all inodes: - */ - if (!i) - i = &darray_last(inode->inodes); - for (; - inode->inodes.data && i >= inode->inodes.data; - --i) { - if (i->snapshot > k.k->p.snapshot || - !key_visible_in_snapshot(c, s, i->snapshot, k.k->p.snapshot)) - continue; + /* + * Check inodes in reverse order, from oldest snapshots to + * newest, starting from the inode that matches this extent's + * snapshot. If we didn't have one, iterate over all inodes: + */ + for (struct inode_walker_entry *i = extent_i ?: &darray_last(inode->inodes); + inode->inodes.data && i >= inode->inodes.data; + --i) { + if (i->snapshot > k.k->p.snapshot || + !key_visible_in_snapshot(c, s, i->snapshot, k.k->p.snapshot)) + continue; - if (k.k->type != KEY_TYPE_whiteout) { if (fsck_err_on(!(i->inode.bi_flags & BCH_INODE_i_size_dirty) && k.k->p.offset > round_up(i->inode.bi_size, block_bytes(c)) >> 9 && !bkey_extent_is_reservation(k), @@ -1629,13 +1713,25 @@ static int check_extent(struct btree_trans *trans, struct btree_iter *iter, goto err; iter->k.type = KEY_TYPE_whiteout; + break; } - - if (bkey_extent_is_allocation(k.k)) - i->count += k.k->size; } + } - i->seen_this_pos = true; + ret = bch2_trans_commit(trans, res, NULL, BCH_TRANS_COMMIT_no_enospc); + if (ret) + goto err; + + if (bkey_extent_is_allocation(k.k)) { + for (struct inode_walker_entry *i = extent_i ?: &darray_last(inode->inodes); + inode->inodes.data && i >= inode->inodes.data; + --i) { + if (i->snapshot > k.k->p.snapshot || + !key_visible_in_snapshot(c, s, i->snapshot, k.k->p.snapshot)) + continue; + + i->count += k.k->size; + } } if (k.k->type != KEY_TYPE_whiteout) { @@ -1666,13 +1762,11 @@ int bch2_check_extents(struct bch_fs *c) extent_ends_init(&extent_ends); int ret = bch2_trans_run(c, - for_each_btree_key_commit(trans, iter, BTREE_ID_extents, + for_each_btree_key(trans, iter, BTREE_ID_extents, POS(BCACHEFS_ROOT_INO, 0), - BTREE_ITER_prefetch|BTREE_ITER_all_snapshots, k, - &res, NULL, - BCH_TRANS_COMMIT_no_enospc, ({ + BTREE_ITER_prefetch|BTREE_ITER_all_snapshots, k, ({ bch2_disk_reservation_put(c, &res); - check_extent(trans, &iter, k, &w, &s, &extent_ends) ?: + check_extent(trans, &iter, k, &w, &s, &extent_ends, &res) ?: check_extent_overbig(trans, &iter, k); })) ?: check_i_sectors_notnested(trans, &w)); @@ -1732,7 +1826,7 @@ static int check_subdir_count_notnested(struct btree_trans *trans, struct inode_ "directory %llu:%u with wrong i_nlink: got %u, should be %llu", w->last_pos.inode, i->snapshot, i->inode.bi_nlink, i->count)) { i->inode.bi_nlink = i->count; - ret = bch2_fsck_write_inode(trans, &i->inode, i->snapshot); + ret = bch2_fsck_write_inode(trans, &i->inode); if (ret) break; } @@ -1753,16 +1847,42 @@ noinline_for_stack static int check_dirent_inode_dirent(struct btree_trans *trans, struct btree_iter *iter, struct bkey_s_c_dirent d, - struct bch_inode_unpacked *target, - u32 target_snapshot) + struct bch_inode_unpacked *target) { struct bch_fs *c = trans->c; struct printbuf buf = PRINTBUF; + struct btree_iter bp_iter = { NULL }; int ret = 0; if (inode_points_to_dirent(target, d)) return 0; + if (!target->bi_dir && + !target->bi_dir_offset) { + fsck_err_on(S_ISDIR(target->bi_mode), + trans, inode_dir_missing_backpointer, + "directory with missing backpointer\n%s", + (printbuf_reset(&buf), + bch2_bkey_val_to_text(&buf, c, d.s_c), + prt_printf(&buf, "\n"), + bch2_inode_unpacked_to_text(&buf, target), + buf.buf)); + + fsck_err_on(target->bi_flags & BCH_INODE_unlinked, + trans, inode_unlinked_but_has_dirent, + "inode unlinked but has dirent\n%s", + (printbuf_reset(&buf), + bch2_bkey_val_to_text(&buf, c, d.s_c), + prt_printf(&buf, "\n"), + bch2_inode_unpacked_to_text(&buf, target), + buf.buf)); + + target->bi_flags &= ~BCH_INODE_unlinked; + target->bi_dir = d.k->p.inode; + target->bi_dir_offset = d.k->p.offset; + return __bch2_fsck_write_inode(trans, target); + } + if (bch2_inode_should_have_bp(target) && !fsck_err(trans, inode_wrong_backpointer, "dirent points to inode that does not point back:\n %s", @@ -1770,18 +1890,10 @@ static int check_dirent_inode_dirent(struct btree_trans *trans, prt_printf(&buf, "\n "), bch2_inode_unpacked_to_text(&buf, target), buf.buf))) - goto out_noiter; - - if (!target->bi_dir && - !target->bi_dir_offset) { - target->bi_dir = d.k->p.inode; - target->bi_dir_offset = d.k->p.offset; - return __bch2_fsck_write_inode(trans, target, target_snapshot); - } + goto err; - struct btree_iter bp_iter = { NULL }; struct bkey_s_c_dirent bp_dirent = dirent_get_by_pos(trans, &bp_iter, - SPOS(target->bi_dir, target->bi_dir_offset, target_snapshot)); + SPOS(target->bi_dir, target->bi_dir_offset, target->bi_snapshot)); ret = bkey_err(bp_dirent); if (ret && !bch2_err_matches(ret, ENOENT)) goto err; @@ -1794,14 +1906,14 @@ static int check_dirent_inode_dirent(struct btree_trans *trans, "inode %llu:%u has wrong backpointer:\n" "got %llu:%llu\n" "should be %llu:%llu", - target->bi_inum, target_snapshot, + target->bi_inum, target->bi_snapshot, target->bi_dir, target->bi_dir_offset, d.k->p.inode, d.k->p.offset)) { target->bi_dir = d.k->p.inode; target->bi_dir_offset = d.k->p.offset; - ret = __bch2_fsck_write_inode(trans, target, target_snapshot); + ret = __bch2_fsck_write_inode(trans, target); goto out; } @@ -1816,7 +1928,7 @@ static int check_dirent_inode_dirent(struct btree_trans *trans, trans, inode_dir_multiple_links, "%s %llu:%u with multiple links\n%s", S_ISDIR(target->bi_mode) ? "directory" : "subvolume", - target->bi_inum, target_snapshot, buf.buf)) { + target->bi_inum, target->bi_snapshot, buf.buf)) { ret = __remove_dirent(trans, d.k->p); goto out; } @@ -1829,10 +1941,10 @@ static int check_dirent_inode_dirent(struct btree_trans *trans, if (fsck_err_on(backpointer_exists && !target->bi_nlink, trans, inode_multiple_links_but_nlink_0, "inode %llu:%u type %s has multiple links but i_nlink 0\n%s", - target->bi_inum, target_snapshot, bch2_d_types[d.v->d_type], buf.buf)) { + target->bi_inum, target->bi_snapshot, bch2_d_types[d.v->d_type], buf.buf)) { target->bi_nlink++; target->bi_flags &= ~BCH_INODE_unlinked; - ret = __bch2_fsck_write_inode(trans, target, target_snapshot); + ret = __bch2_fsck_write_inode(trans, target); if (ret) goto err; } @@ -1840,7 +1952,6 @@ out: err: fsck_err: bch2_trans_iter_exit(trans, &bp_iter); -out_noiter: printbuf_exit(&buf); bch_err_fn(c, ret); return ret; @@ -1850,15 +1961,14 @@ noinline_for_stack static int check_dirent_target(struct btree_trans *trans, struct btree_iter *iter, struct bkey_s_c_dirent d, - struct bch_inode_unpacked *target, - u32 target_snapshot) + struct bch_inode_unpacked *target) { struct bch_fs *c = trans->c; struct bkey_i_dirent *n; struct printbuf buf = PRINTBUF; int ret = 0; - ret = check_dirent_inode_dirent(trans, iter, d, target, target_snapshot); + ret = check_dirent_inode_dirent(trans, iter, d, target); if (ret) goto err; @@ -2017,7 +2127,7 @@ static int check_dirent_to_subvol(struct btree_trans *trans, struct btree_iter * u64 target_inum = le64_to_cpu(s.v->inode); u32 target_snapshot = le32_to_cpu(s.v->snapshot); - ret = lookup_inode(trans, target_inum, &subvol_root, &target_snapshot); + ret = lookup_inode(trans, target_inum, target_snapshot, &subvol_root); if (ret && !bch2_err_matches(ret, ENOENT)) goto err; @@ -2033,13 +2143,13 @@ static int check_dirent_to_subvol(struct btree_trans *trans, struct btree_iter * target_inum, subvol_root.bi_parent_subvol, parent_subvol)) { subvol_root.bi_parent_subvol = parent_subvol; - ret = __bch2_fsck_write_inode(trans, &subvol_root, target_snapshot); + subvol_root.bi_snapshot = le32_to_cpu(s.v->snapshot); + ret = __bch2_fsck_write_inode(trans, &subvol_root); if (ret) goto err; } - ret = check_dirent_target(trans, iter, d, &subvol_root, - target_snapshot); + ret = check_dirent_target(trans, iter, d, &subvol_root); if (ret) goto err; out: @@ -2075,7 +2185,7 @@ static int check_dirent(struct btree_trans *trans, struct btree_iter *iter, if (k.k->type == KEY_TYPE_whiteout) goto out; - if (dir->last_pos.inode != k.k->p.inode) { + if (dir->last_pos.inode != k.k->p.inode && dir->have_inodes) { ret = check_subdir_count(trans, dir); if (ret) goto err; @@ -2132,16 +2242,19 @@ static int check_dirent(struct btree_trans *trans, struct btree_iter *iter, } darray_for_each(target->inodes, i) { - ret = check_dirent_target(trans, iter, d, - &i->inode, i->snapshot); + ret = check_dirent_target(trans, iter, d, &i->inode); if (ret) goto err; } - - if (d.v->d_type == DT_DIR) - for_each_visible_inode(c, s, dir, d.k->p.snapshot, i) - i->count++; } + + ret = bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc); + if (ret) + goto err; + + if (d.v->d_type == DT_DIR) + for_each_visible_inode(c, s, dir, d.k->p.snapshot, i) + i->count++; out: err: fsck_err: @@ -2164,12 +2277,9 @@ int bch2_check_dirents(struct bch_fs *c) snapshots_seen_init(&s); int ret = bch2_trans_run(c, - for_each_btree_key_commit(trans, iter, BTREE_ID_dirents, + for_each_btree_key(trans, iter, BTREE_ID_dirents, POS(BCACHEFS_ROOT_INO, 0), - BTREE_ITER_prefetch|BTREE_ITER_all_snapshots, - k, - NULL, NULL, - BCH_TRANS_COMMIT_no_enospc, + BTREE_ITER_prefetch|BTREE_ITER_all_snapshots, k, check_dirent(trans, &iter, k, &hash_info, &dir, &target, &s)) ?: check_subdir_count_notnested(trans, &dir)); @@ -2273,7 +2383,7 @@ static int check_root_trans(struct btree_trans *trans) goto err; } - ret = lookup_inode(trans, BCACHEFS_ROOT_INO, &root_inode, &snapshot); + ret = lookup_inode(trans, BCACHEFS_ROOT_INO, snapshot, &root_inode); if (ret && !bch2_err_matches(ret, ENOENT)) return ret; @@ -2286,8 +2396,9 @@ static int check_root_trans(struct btree_trans *trans) bch2_inode_init(c, &root_inode, 0, 0, S_IFDIR|0755, 0, NULL); root_inode.bi_inum = inum; + root_inode.bi_snapshot = snapshot; - ret = __bch2_fsck_write_inode(trans, &root_inode, snapshot); + ret = __bch2_fsck_write_inode(trans, &root_inode); bch_err_msg(c, ret, "writing root inode"); } err: @@ -2314,22 +2425,6 @@ static bool darray_u32_has(darray_u32 *d, u32 v) return false; } -/* - * We've checked that inode backpointers point to valid dirents; here, it's - * sufficient to check that the subvolume root has a dirent: - */ -static int subvol_has_dirent(struct btree_trans *trans, struct bkey_s_c_subvolume s) -{ - struct bch_inode_unpacked inode; - int ret = bch2_inode_find_by_inum_trans(trans, - (subvol_inum) { s.k->p.offset, le64_to_cpu(s.v->inode) }, - &inode); - if (ret) - return ret; - - return inode.bi_dir != 0; -} - static int check_subvol_path(struct btree_trans *trans, struct btree_iter *iter, struct bkey_s_c k) { struct bch_fs *c = trans->c; @@ -2348,14 +2443,24 @@ static int check_subvol_path(struct btree_trans *trans, struct btree_iter *iter, struct bkey_s_c_subvolume s = bkey_s_c_to_subvolume(k); - ret = subvol_has_dirent(trans, s); - if (ret < 0) + struct bch_inode_unpacked subvol_root; + ret = bch2_inode_find_by_inum_trans(trans, + (subvol_inum) { s.k->p.offset, le64_to_cpu(s.v->inode) }, + &subvol_root); + if (ret) break; - if (fsck_err_on(!ret, + /* + * We've checked that inode backpointers point to valid dirents; + * here, it's sufficient to check that the subvolume root has a + * dirent: + */ + if (fsck_err_on(!subvol_root.bi_dir, trans, subvol_unreachable, "unreachable subvolume %s", (bch2_bkey_val_to_text(&buf, c, s.s_c), + prt_newline(&buf), + bch2_inode_unpacked_to_text(&buf, &subvol_root), buf.buf))) { ret = reattach_subvol(trans, s); break; @@ -2450,10 +2555,8 @@ static int check_path(struct btree_trans *trans, pathbuf *p, struct bkey_s_c ino if (ret && !bch2_err_matches(ret, ENOENT)) break; - if (!ret && !dirent_points_to_inode(d, &inode)) { + if (!ret && (ret = dirent_points_to_inode(c, d, &inode))) bch2_trans_iter_exit(trans, &dirent_iter); - ret = -BCH_ERR_ENOENT_dirent_doesnt_match_inode; - } if (bch2_err_matches(ret, ENOENT)) { ret = 0; @@ -2462,7 +2565,7 @@ static int check_path(struct btree_trans *trans, pathbuf *p, struct bkey_s_c ino (printbuf_reset(&buf), bch2_bkey_val_to_text(&buf, c, inode_k), buf.buf))) - ret = reattach_inode(trans, &inode, snapshot); + ret = reattach_inode(trans, &inode); goto out; } @@ -2508,7 +2611,7 @@ static int check_path(struct btree_trans *trans, pathbuf *p, struct bkey_s_c ino if (ret) break; - ret = reattach_inode(trans, &inode, snapshot); + ret = reattach_inode(trans, &inode); bch_err_msg(c, ret, "reattaching inode %llu", inode.bi_inum); } break; @@ -2738,7 +2841,7 @@ static int check_nlinks_update_inode(struct btree_trans *trans, struct btree_ite u.bi_inum, bch2_d_types[mode_to_type(u.bi_mode)], bch2_inode_nlink_get(&u), link->count)) { bch2_inode_nlink_set(&u, link->count); - ret = __bch2_fsck_write_inode(trans, &u, k.k->p.snapshot); + ret = __bch2_fsck_write_inode(trans, &u); } fsck_err: return ret; diff --git a/fs/bcachefs/inode.c b/fs/bcachefs/inode.c index 6ac0ff7e074b..3e5bc01961b8 100644 --- a/fs/bcachefs/inode.c +++ b/fs/bcachefs/inode.c @@ -20,7 +20,7 @@ #include <linux/random.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define x(name, ...) #name, const char * const bch2_inode_opts[] = { @@ -320,27 +320,27 @@ static noinline int bch2_inode_unpack_slowpath(struct bkey_s_c k, int bch2_inode_unpack(struct bkey_s_c k, struct bch_inode_unpacked *unpacked) { - if (likely(k.k->type == KEY_TYPE_inode_v3)) - return bch2_inode_unpack_v3(k, unpacked); - return bch2_inode_unpack_slowpath(k, unpacked); + unpacked->bi_snapshot = k.k->p.snapshot; + + return likely(k.k->type == KEY_TYPE_inode_v3) + ? bch2_inode_unpack_v3(k, unpacked) + : bch2_inode_unpack_slowpath(k, unpacked); } -int bch2_inode_peek_nowarn(struct btree_trans *trans, - struct btree_iter *iter, - struct bch_inode_unpacked *inode, - subvol_inum inum, unsigned flags) +int __bch2_inode_peek(struct btree_trans *trans, + struct btree_iter *iter, + struct bch_inode_unpacked *inode, + subvol_inum inum, unsigned flags, + bool warn) { - struct bkey_s_c k; u32 snapshot; - int ret; - - ret = bch2_subvolume_get_snapshot(trans, inum.subvol, &snapshot); + int ret = __bch2_subvolume_get_snapshot(trans, inum.subvol, &snapshot, warn); if (ret) return ret; - k = bch2_bkey_get_iter(trans, iter, BTREE_ID_inodes, - SPOS(0, inum.inum, snapshot), - flags|BTREE_ITER_cached); + struct bkey_s_c k = bch2_bkey_get_iter(trans, iter, BTREE_ID_inodes, + SPOS(0, inum.inum, snapshot), + flags|BTREE_ITER_cached); ret = bkey_err(k); if (ret) return ret; @@ -355,20 +355,12 @@ int bch2_inode_peek_nowarn(struct btree_trans *trans, return 0; err: + if (warn) + bch_err_msg(trans->c, ret, "looking up inum %llu:%llu:", inum.subvol, inum.inum); bch2_trans_iter_exit(trans, iter); return ret; } -int bch2_inode_peek(struct btree_trans *trans, - struct btree_iter *iter, - struct bch_inode_unpacked *inode, - subvol_inum inum, unsigned flags) -{ - int ret = bch2_inode_peek_nowarn(trans, iter, inode, inum, flags); - bch_err_msg(trans->c, ret, "looking up inum %llu:%llu:", inum.subvol, inum.inum); - return ret; -} - int bch2_inode_write_flags(struct btree_trans *trans, struct btree_iter *iter, struct bch_inode_unpacked *inode, @@ -385,9 +377,7 @@ int bch2_inode_write_flags(struct btree_trans *trans, return bch2_trans_update(trans, iter, &inode_p->inode.k_i, flags); } -int __bch2_fsck_write_inode(struct btree_trans *trans, - struct bch_inode_unpacked *inode, - u32 snapshot) +int __bch2_fsck_write_inode(struct btree_trans *trans, struct bch_inode_unpacked *inode) { struct bkey_inode_buf *inode_p = bch2_trans_kmalloc(trans, sizeof(*inode_p)); @@ -396,19 +386,17 @@ int __bch2_fsck_write_inode(struct btree_trans *trans, return PTR_ERR(inode_p); bch2_inode_pack(inode_p, inode); - inode_p->inode.k.p.snapshot = snapshot; + inode_p->inode.k.p.snapshot = inode->bi_snapshot; return bch2_btree_insert_nonextent(trans, BTREE_ID_inodes, &inode_p->inode.k_i, BTREE_UPDATE_internal_snapshot_node); } -int bch2_fsck_write_inode(struct btree_trans *trans, - struct bch_inode_unpacked *inode, - u32 snapshot) +int bch2_fsck_write_inode(struct btree_trans *trans, struct bch_inode_unpacked *inode) { int ret = commit_do(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc, - __bch2_fsck_write_inode(trans, inode, snapshot)); + __bch2_fsck_write_inode(trans, inode)); bch_err_fn(trans->c, ret); return ret; } @@ -557,7 +545,7 @@ static void __bch2_inode_unpacked_to_text(struct printbuf *out, void bch2_inode_unpacked_to_text(struct printbuf *out, struct bch_inode_unpacked *inode) { - prt_printf(out, "inum: %llu ", inode->bi_inum); + prt_printf(out, "inum: %llu:%u ", inode->bi_inum, inode->bi_snapshot); __bch2_inode_unpacked_to_text(out, inode); } @@ -1111,7 +1099,7 @@ static int may_delete_deleted_inode(struct btree_trans *trans, pos.offset, pos.snapshot)) goto delete; - if (c->sb.clean && + if (test_bit(BCH_FS_clean_recovery, &c->flags) && !fsck_err(trans, deleted_inode_but_clean, "filesystem marked as clean but have deleted inode %llu:%u", pos.offset, pos.snapshot)) { diff --git a/fs/bcachefs/inode.h b/fs/bcachefs/inode.h index f1fcb4c58039..9c1f67705684 100644 --- a/fs/bcachefs/inode.h +++ b/fs/bcachefs/inode.h @@ -69,6 +69,7 @@ typedef u64 u96; struct bch_inode_unpacked { u64 bi_inum; + u32 bi_snapshot; u64 bi_journal_seq; __le64 bi_hash_seed; u64 bi_size; @@ -96,10 +97,26 @@ struct bkey_i *bch2_inode_to_v3(struct btree_trans *, struct bkey_i *); void bch2_inode_unpacked_to_text(struct printbuf *, struct bch_inode_unpacked *); -int bch2_inode_peek_nowarn(struct btree_trans *, struct btree_iter *, - struct bch_inode_unpacked *, subvol_inum, unsigned); -int bch2_inode_peek(struct btree_trans *, struct btree_iter *, - struct bch_inode_unpacked *, subvol_inum, unsigned); +int __bch2_inode_peek(struct btree_trans *, struct btree_iter *, + struct bch_inode_unpacked *, subvol_inum, unsigned, bool); + +static inline int bch2_inode_peek_nowarn(struct btree_trans *trans, + struct btree_iter *iter, + struct bch_inode_unpacked *inode, + subvol_inum inum, unsigned flags) +{ + return __bch2_inode_peek(trans, iter, inode, inum, flags, false); +} + +static inline int bch2_inode_peek(struct btree_trans *trans, + struct btree_iter *iter, + struct bch_inode_unpacked *inode, + subvol_inum inum, unsigned flags) +{ + return __bch2_inode_peek(trans, iter, inode, inum, flags, true); + int ret = bch2_inode_peek_nowarn(trans, iter, inode, inum, flags); + return ret; +} int bch2_inode_write_flags(struct btree_trans *, struct btree_iter *, struct bch_inode_unpacked *, enum btree_iter_update_trigger_flags); @@ -111,8 +128,8 @@ static inline int bch2_inode_write(struct btree_trans *trans, return bch2_inode_write_flags(trans, iter, inode, 0); } -int __bch2_fsck_write_inode(struct btree_trans *, struct bch_inode_unpacked *, u32); -int bch2_fsck_write_inode(struct btree_trans *, struct bch_inode_unpacked *, u32); +int __bch2_fsck_write_inode(struct btree_trans *, struct bch_inode_unpacked *); +int bch2_fsck_write_inode(struct btree_trans *, struct bch_inode_unpacked *); void bch2_inode_init_early(struct bch_fs *, struct bch_inode_unpacked *); diff --git a/fs/bcachefs/io_misc.c b/fs/bcachefs/io_misc.c index 177ed331c00b..307ed0a45184 100644 --- a/fs/bcachefs/io_misc.c +++ b/fs/bcachefs/io_misc.c @@ -224,13 +224,14 @@ void bch2_logged_op_truncate_to_text(struct printbuf *out, struct bch_fs *c, str static int truncate_set_isize(struct btree_trans *trans, subvol_inum inum, - u64 new_i_size) + u64 new_i_size, + bool warn) { struct btree_iter iter = { NULL }; struct bch_inode_unpacked inode_u; int ret; - ret = bch2_inode_peek(trans, &iter, &inode_u, inum, BTREE_ITER_intent) ?: + ret = __bch2_inode_peek(trans, &iter, &inode_u, inum, BTREE_ITER_intent, warn) ?: (inode_u.bi_size = new_i_size, 0) ?: bch2_inode_write(trans, &iter, &inode_u); @@ -247,10 +248,11 @@ static int __bch2_resume_logged_op_truncate(struct btree_trans *trans, struct bkey_i_logged_op_truncate *op = bkey_i_to_logged_op_truncate(op_k); subvol_inum inum = { le32_to_cpu(op->v.subvol), le64_to_cpu(op->v.inum) }; u64 new_i_size = le64_to_cpu(op->v.new_i_size); + bool warn_errors = i_sectors_delta != NULL; int ret; ret = commit_do(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc, - truncate_set_isize(trans, inum, new_i_size)); + truncate_set_isize(trans, inum, new_i_size, i_sectors_delta != NULL)); if (ret) goto err; @@ -263,8 +265,8 @@ static int __bch2_resume_logged_op_truncate(struct btree_trans *trans, if (bch2_err_matches(ret, BCH_ERR_transaction_restart)) ret = 0; err: - bch2_logged_op_finish(trans, op_k); - bch_err_fn(c, ret); + if (warn_errors) + bch_err_fn(c, ret); return ret; } @@ -288,9 +290,14 @@ int bch2_truncate(struct bch_fs *c, subvol_inum inum, u64 new_i_size, u64 *i_sec * resume only proceeding in one of the snapshots */ down_read(&c->snapshot_create_lock); - int ret = bch2_trans_run(c, - bch2_logged_op_start(trans, &op.k_i) ?: - __bch2_resume_logged_op_truncate(trans, &op.k_i, i_sectors_delta)); + struct btree_trans *trans = bch2_trans_get(c); + int ret = bch2_logged_op_start(trans, &op.k_i); + if (ret) + goto out; + ret = __bch2_resume_logged_op_truncate(trans, &op.k_i, i_sectors_delta); + ret = bch2_logged_op_finish(trans, &op.k_i) ?: ret; +out: + bch2_trans_put(trans); up_read(&c->snapshot_create_lock); return ret; @@ -308,7 +315,8 @@ void bch2_logged_op_finsert_to_text(struct printbuf *out, struct bch_fs *c, stru prt_printf(out, " src_offset=%llu", le64_to_cpu(op.v->src_offset)); } -static int adjust_i_size(struct btree_trans *trans, subvol_inum inum, u64 offset, s64 len) +static int adjust_i_size(struct btree_trans *trans, subvol_inum inum, + u64 offset, s64 len, bool warn) { struct btree_iter iter; struct bch_inode_unpacked inode_u; @@ -317,7 +325,7 @@ static int adjust_i_size(struct btree_trans *trans, subvol_inum inum, u64 offset offset <<= 9; len <<= 9; - ret = bch2_inode_peek(trans, &iter, &inode_u, inum, BTREE_ITER_intent); + ret = __bch2_inode_peek(trans, &iter, &inode_u, inum, BTREE_ITER_intent, warn); if (ret) return ret; @@ -357,12 +365,22 @@ static int __bch2_resume_logged_op_finsert(struct btree_trans *trans, u64 len = abs(shift); u64 pos = le64_to_cpu(op->v.pos); bool insert = shift > 0; + u32 snapshot; + bool warn_errors = i_sectors_delta != NULL; int ret = 0; ret = bch2_inum_opts_get(trans, inum, &opts); if (ret) return ret; + /* + * check for missing subvolume before fpunch, as in resume we don't want + * it to be a fatal error + */ + ret = __bch2_subvolume_get_snapshot(trans, inum.subvol, &snapshot, warn_errors); + if (ret) + return ret; + bch2_trans_iter_init(trans, &iter, BTREE_ID_extents, POS(inum.inum, 0), BTREE_ITER_intent); @@ -373,7 +391,7 @@ case LOGGED_OP_FINSERT_start: if (insert) { ret = commit_do(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc, - adjust_i_size(trans, inum, src_offset, len) ?: + adjust_i_size(trans, inum, src_offset, len, warn_errors) ?: bch2_logged_op_update(trans, &op->k_i)); if (ret) goto err; @@ -396,11 +414,11 @@ case LOGGED_OP_FINSERT_shift_extents: struct bkey_i delete, *copy; struct bkey_s_c k; struct bpos src_pos = POS(inum.inum, src_offset); - u32 snapshot; bch2_trans_begin(trans); - ret = bch2_subvolume_get_snapshot(trans, inum.subvol, &snapshot); + ret = __bch2_subvolume_get_snapshot(trans, inum.subvol, &snapshot, + warn_errors); if (ret) goto btree_err; @@ -463,12 +481,12 @@ btree_err: if (!insert) { ret = commit_do(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc, - adjust_i_size(trans, inum, src_offset, shift) ?: + adjust_i_size(trans, inum, src_offset, shift, warn_errors) ?: bch2_logged_op_update(trans, &op->k_i)); } else { /* We need an inode update to update bi_journal_seq for fsync: */ ret = commit_do(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc, - adjust_i_size(trans, inum, 0, 0) ?: + adjust_i_size(trans, inum, 0, 0, warn_errors) ?: bch2_logged_op_update(trans, &op->k_i)); } @@ -477,9 +495,9 @@ case LOGGED_OP_FINSERT_finish: break; } err: - bch_err_fn(c, ret); - bch2_logged_op_finish(trans, op_k); bch2_trans_iter_exit(trans, &iter); + if (warn_errors) + bch_err_fn(c, ret); return ret; } @@ -508,9 +526,14 @@ int bch2_fcollapse_finsert(struct bch_fs *c, subvol_inum inum, * resume only proceeding in one of the snapshots */ down_read(&c->snapshot_create_lock); - int ret = bch2_trans_run(c, - bch2_logged_op_start(trans, &op.k_i) ?: - __bch2_resume_logged_op_finsert(trans, &op.k_i, i_sectors_delta)); + struct btree_trans *trans = bch2_trans_get(c); + int ret = bch2_logged_op_start(trans, &op.k_i); + if (ret) + goto out; + ret = __bch2_resume_logged_op_finsert(trans, &op.k_i, i_sectors_delta); + ret = bch2_logged_op_finish(trans, &op.k_i) ?: ret; +out: + bch2_trans_put(trans); up_read(&c->snapshot_create_lock); return ret; diff --git a/fs/bcachefs/io_read.c b/fs/bcachefs/io_read.c index b2f50e74bb76..e4fc17c548fd 100644 --- a/fs/bcachefs/io_read.c +++ b/fs/bcachefs/io_read.c @@ -517,7 +517,7 @@ static int __bch2_rbio_narrow_crcs(struct btree_trans *trans, if ((ret = bkey_err(k))) goto out; - if (bversion_cmp(k.k->version, rbio->version) || + if (bversion_cmp(k.k->bversion, rbio->version) || !bch2_bkey_matches_ptr(c, k, rbio->pick.ptr, data_offset)) goto out; @@ -1031,7 +1031,7 @@ get_bio: rbio->read_pos = read_pos; rbio->data_btree = data_btree; rbio->data_pos = data_pos; - rbio->version = k.k->version; + rbio->version = k.k->bversion; rbio->promote = promote; INIT_WORK(&rbio->work, NULL); diff --git a/fs/bcachefs/io_write.c b/fs/bcachefs/io_write.c index d3b5be7fd9bf..b5fe9e0dc155 100644 --- a/fs/bcachefs/io_write.c +++ b/fs/bcachefs/io_write.c @@ -697,7 +697,7 @@ static void init_append_extent(struct bch_write_op *op, e = bkey_extent_init(op->insert_keys.top); e->k.p = op->pos; e->k.size = crc.uncompressed_size; - e->k.version = version; + e->k.bversion = version; if (crc.csum_type || crc.compression_type || @@ -1544,7 +1544,7 @@ static void bch2_write_data_inline(struct bch_write_op *op, unsigned data_len) id = bkey_inline_data_init(op->insert_keys.top); id->k.p = op->pos; - id->k.version = op->version; + id->k.bversion = op->version; id->k.size = sectors; iter = bio->bi_iter; diff --git a/fs/bcachefs/journal_io.c b/fs/bcachefs/journal_io.c index 30460bce04be..954f6a96e0f4 100644 --- a/fs/bcachefs/journal_io.c +++ b/fs/bcachefs/journal_io.c @@ -605,7 +605,7 @@ static int journal_entry_data_usage_validate(struct bch_fs *c, goto out; } - if (journal_entry_err_on(bch2_replicas_entry_validate(&u->r, c->disk_sb.sb, &err), + if (journal_entry_err_on(bch2_replicas_entry_validate(&u->r, c, &err), c, version, jset, entry, journal_entry_data_usage_bad_size, "invalid journal entry usage: %s", err.buf)) { diff --git a/fs/bcachefs/logged_ops.c b/fs/bcachefs/logged_ops.c index f49fdca1d07d..60e00702d1a4 100644 --- a/fs/bcachefs/logged_ops.c +++ b/fs/bcachefs/logged_ops.c @@ -34,21 +34,30 @@ static int resume_logged_op(struct btree_trans *trans, struct btree_iter *iter, struct bkey_s_c k) { struct bch_fs *c = trans->c; - const struct bch_logged_op_fn *fn = logged_op_fn(k.k->type); - struct bkey_buf sk; u32 restart_count = trans->restart_count; + struct printbuf buf = PRINTBUF; + int ret = 0; - if (!fn) - return 0; + fsck_err_on(test_bit(BCH_FS_clean_recovery, &c->flags), + trans, logged_op_but_clean, + "filesystem marked as clean but have logged op\n%s", + (bch2_bkey_val_to_text(&buf, c, k), + buf.buf)); + struct bkey_buf sk; bch2_bkey_buf_init(&sk); bch2_bkey_buf_reassemble(&sk, c, k); - fn->resume(trans, sk.k); + const struct bch_logged_op_fn *fn = logged_op_fn(sk.k->k.type); + if (fn) + fn->resume(trans, sk.k); - bch2_bkey_buf_exit(&sk, c); + ret = bch2_logged_op_finish(trans, sk.k); - return trans_was_restarted(trans, restart_count); + bch2_bkey_buf_exit(&sk, c); +fsck_err: + printbuf_exit(&buf); + return ret ?: trans_was_restarted(trans, restart_count); } int bch2_resume_logged_ops(struct bch_fs *c) @@ -84,7 +93,7 @@ int bch2_logged_op_start(struct btree_trans *trans, struct bkey_i *k) __bch2_logged_op_start(trans, k)); } -void bch2_logged_op_finish(struct btree_trans *trans, struct bkey_i *k) +int bch2_logged_op_finish(struct btree_trans *trans, struct bkey_i *k) { int ret = commit_do(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc, bch2_btree_delete(trans, BTREE_ID_logged_ops, k->k.p, 0)); @@ -104,4 +113,6 @@ void bch2_logged_op_finish(struct btree_trans *trans, struct bkey_i *k) buf.buf, bch2_err_str(ret)); printbuf_exit(&buf); } + + return ret; } diff --git a/fs/bcachefs/logged_ops.h b/fs/bcachefs/logged_ops.h index 4d1e786a27a8..30ae9ef737dd 100644 --- a/fs/bcachefs/logged_ops.h +++ b/fs/bcachefs/logged_ops.h @@ -15,6 +15,6 @@ static inline int bch2_logged_op_update(struct btree_trans *trans, struct bkey_i int bch2_resume_logged_ops(struct bch_fs *); int bch2_logged_op_start(struct btree_trans *, struct bkey_i *); -void bch2_logged_op_finish(struct btree_trans *, struct bkey_i *); +int bch2_logged_op_finish(struct btree_trans *, struct bkey_i *); #endif /* _BCACHEFS_LOGGED_OPS_H */ diff --git a/fs/bcachefs/lru.c b/fs/bcachefs/lru.c index 96f2f4f8c397..10857eccdeaf 100644 --- a/fs/bcachefs/lru.c +++ b/fs/bcachefs/lru.c @@ -2,6 +2,7 @@ #include "bcachefs.h" #include "alloc_background.h" +#include "bkey_buf.h" #include "btree_iter.h" #include "btree_update.h" #include "btree_write_buffer.h" @@ -118,7 +119,7 @@ fsck_err: static int bch2_check_lru_key(struct btree_trans *trans, struct btree_iter *lru_iter, struct bkey_s_c lru_k, - struct bpos *last_flushed_pos) + struct bkey_buf *last_flushed) { struct bch_fs *c = trans->c; struct btree_iter iter; @@ -132,11 +133,13 @@ static int bch2_check_lru_key(struct btree_trans *trans, u64 idx; int ret; - if (fsck_err_on(!bch2_dev_bucket_exists(c, alloc_pos), + struct bch_dev *ca = bch2_dev_bucket_tryget_noerror(c, alloc_pos); + + if (fsck_err_on(!ca, trans, lru_entry_to_invalid_bucket, "lru key points to nonexistent device:bucket %llu:%llu", alloc_pos.inode, alloc_pos.offset)) - return bch2_btree_delete_at(trans, lru_iter, 0); + return bch2_btree_bit_mod_buffered(trans, BTREE_ID_lru, lru_iter->pos, false); k = bch2_bkey_get_iter(trans, &iter, BTREE_ID_alloc, alloc_pos, 0); ret = bkey_err(k); @@ -150,18 +153,15 @@ static int bch2_check_lru_key(struct btree_trans *trans, idx = alloc_lru_idx_read(*a); break; case BCH_LRU_fragmentation: - idx = a->fragmentation_lru; + idx = alloc_lru_idx_fragmentation(*a, ca); break; } if (lru_k.k->type != KEY_TYPE_set || lru_pos_time(lru_k.k->p) != idx) { - if (!bpos_eq(*last_flushed_pos, lru_k.k->p)) { - *last_flushed_pos = lru_k.k->p; - ret = bch2_btree_write_buffer_flush_sync(trans) ?: - -BCH_ERR_transaction_restart_write_buffer_flush; - goto out; - } + ret = bch2_btree_write_buffer_maybe_flush(trans, lru_k, last_flushed); + if (ret) + goto err; if (fsck_err(trans, lru_entry_bad, "incorrect lru entry: lru %s time %llu\n" @@ -171,12 +171,12 @@ static int bch2_check_lru_key(struct btree_trans *trans, lru_pos_time(lru_k.k->p), (bch2_bkey_val_to_text(&buf1, c, lru_k), buf1.buf), (bch2_bkey_val_to_text(&buf2, c, k), buf2.buf))) - ret = bch2_btree_delete_at(trans, lru_iter, 0); + ret = bch2_btree_bit_mod_buffered(trans, BTREE_ID_lru, lru_iter->pos, false); } -out: err: fsck_err: bch2_trans_iter_exit(trans, &iter); + bch2_dev_put(ca); printbuf_exit(&buf2); printbuf_exit(&buf1); return ret; @@ -184,12 +184,18 @@ fsck_err: int bch2_check_lrus(struct bch_fs *c) { - struct bpos last_flushed_pos = POS_MIN; + struct bkey_buf last_flushed; + + bch2_bkey_buf_init(&last_flushed); + bkey_init(&last_flushed.k->k); + int ret = bch2_trans_run(c, for_each_btree_key_commit(trans, iter, BTREE_ID_lru, POS_MIN, BTREE_ITER_prefetch, k, NULL, NULL, BCH_TRANS_COMMIT_no_enospc|BCH_TRANS_COMMIT_lazy_rw, - bch2_check_lru_key(trans, &iter, k, &last_flushed_pos))); + bch2_check_lru_key(trans, &iter, k, &last_flushed))); + + bch2_bkey_buf_exit(&last_flushed, c); bch_err_fn(c, ret); return ret; diff --git a/fs/bcachefs/move.c b/fs/bcachefs/move.c index 7d3920e03742..8c456d8b8b99 100644 --- a/fs/bcachefs/move.c +++ b/fs/bcachefs/move.c @@ -692,7 +692,7 @@ int bch2_evacuate_bucket(struct moving_context *ctxt, a = bch2_alloc_to_v4(k, &a_convert); dirty_sectors = bch2_bucket_sectors_dirty(*a); bucket_size = ca->mi.bucket_size; - fragmentation = a->fragmentation_lru; + fragmentation = alloc_lru_idx_fragmentation(*a, ca); ret = bch2_btree_write_buffer_tryflush(trans); bch_err_msg(c, ret, "flushing btree write buffer"); diff --git a/fs/bcachefs/movinggc.c b/fs/bcachefs/movinggc.c index d86565bf07c8..d658be90f737 100644 --- a/fs/bcachefs/movinggc.c +++ b/fs/bcachefs/movinggc.c @@ -73,6 +73,7 @@ move_bucket_in_flight_add(struct buckets_in_flight *list, struct move_bucket b) static int bch2_bucket_is_movable(struct btree_trans *trans, struct move_bucket *b, u64 time) { + struct bch_fs *c = trans->c; struct btree_iter iter; struct bkey_s_c k; struct bch_alloc_v4 _a; @@ -90,14 +91,19 @@ static int bch2_bucket_is_movable(struct btree_trans *trans, if (ret) return ret; + struct bch_dev *ca = bch2_dev_tryget(c, k.k->p.inode); + if (!ca) + goto out; + a = bch2_alloc_to_v4(k, &_a); b->k.gen = a->gen; b->sectors = bch2_bucket_sectors_dirty(*a); + u64 lru_idx = alloc_lru_idx_fragmentation(*a, ca); - ret = data_type_movable(a->data_type) && - a->fragmentation_lru && - a->fragmentation_lru <= time; + ret = lru_idx && lru_idx <= time; + bch2_dev_put(ca); +out: bch2_trans_iter_exit(trans, &iter); return ret; } diff --git a/fs/bcachefs/recovery.c b/fs/bcachefs/recovery.c index be1e7ca4362f..6db72d3bad7d 100644 --- a/fs/bcachefs/recovery.c +++ b/fs/bcachefs/recovery.c @@ -151,7 +151,7 @@ static int bch2_journal_replay_accounting_key(struct btree_trans *trans, struct bkey_s_c old = bch2_btree_path_peek_slot(btree_iter_path(trans, &iter), &u); /* Has this delta already been applied to the btree? */ - if (bversion_cmp(old.k->version, k->k->k.version) >= 0) { + if (bversion_cmp(old.k->bversion, k->k->k.bversion) >= 0) { ret = 0; goto out; } @@ -717,6 +717,8 @@ int bch2_fs_recovery(struct bch_fs *c) if (c->opts.fsck) set_bit(BCH_FS_fsck_running, &c->flags); + if (c->sb.clean) + set_bit(BCH_FS_clean_recovery, &c->flags); ret = bch2_blacklist_table_initialize(c); if (ret) { @@ -862,6 +864,9 @@ use_clean: clear_bit(BCH_FS_fsck_running, &c->flags); + /* in case we don't run journal replay, i.e. norecovery mode */ + set_bit(BCH_FS_accounting_replay_done, &c->flags); + /* fsync if we fixed errors */ if (test_bit(BCH_FS_errors_fixed, &c->flags) && bch2_write_ref_tryget(c, BCH_WRITE_REF_fsync)) { diff --git a/fs/bcachefs/recovery_passes_types.h b/fs/bcachefs/recovery_passes_types.h index 8c7dee5983d2..50406ce0e4ef 100644 --- a/fs/bcachefs/recovery_passes_types.h +++ b/fs/bcachefs/recovery_passes_types.h @@ -50,7 +50,7 @@ x(check_directory_structure, 30, PASS_ONLINE|PASS_FSCK) \ x(check_nlinks, 31, PASS_FSCK) \ x(resume_logged_ops, 23, PASS_ALWAYS) \ - x(delete_dead_inodes, 32, PASS_FSCK|PASS_UNCLEAN) \ + x(delete_dead_inodes, 32, PASS_ALWAYS) \ x(fix_reflink_p, 33, 0) \ x(set_fs_needs_rebalance, 34, 0) \ diff --git a/fs/bcachefs/reflink.c b/fs/bcachefs/reflink.c index e59c0abb4772..f457925fa362 100644 --- a/fs/bcachefs/reflink.c +++ b/fs/bcachefs/reflink.c @@ -367,7 +367,7 @@ static int bch2_make_extent_indirect(struct btree_trans *trans, r_v->k.type = bkey_type_to_indirect(&orig->k); r_v->k.p = reflink_iter.pos; bch2_key_resize(&r_v->k, orig->k.size); - r_v->k.version = orig->k.version; + r_v->k.bversion = orig->k.bversion; set_bkey_val_bytes(&r_v->k, sizeof(__le64) + bkey_val_bytes(&orig->k)); diff --git a/fs/bcachefs/replicas.c b/fs/bcachefs/replicas.c index 998c0bd06802..bcb3276747e0 100644 --- a/fs/bcachefs/replicas.c +++ b/fs/bcachefs/replicas.c @@ -66,9 +66,9 @@ void bch2_replicas_entry_to_text(struct printbuf *out, prt_printf(out, "]"); } -int bch2_replicas_entry_validate(struct bch_replicas_entry_v1 *r, - struct bch_sb *sb, - struct printbuf *err) +static int bch2_replicas_entry_validate_locked(struct bch_replicas_entry_v1 *r, + struct bch_sb *sb, + struct printbuf *err) { if (!r->nr_devs) { prt_printf(err, "no devices in entry "); @@ -94,6 +94,16 @@ bad: return -BCH_ERR_invalid_replicas_entry; } +int bch2_replicas_entry_validate(struct bch_replicas_entry_v1 *r, + struct bch_fs *c, + struct printbuf *err) +{ + mutex_lock(&c->sb_lock); + int ret = bch2_replicas_entry_validate_locked(r, c->disk_sb.sb, err); + mutex_unlock(&c->sb_lock); + return ret; +} + void bch2_cpu_replicas_to_text(struct printbuf *out, struct bch_replicas_cpu *r) { @@ -676,7 +686,7 @@ static int bch2_cpu_replicas_validate(struct bch_replicas_cpu *cpu_r, struct bch_replicas_entry_v1 *e = cpu_replicas_entry(cpu_r, i); - int ret = bch2_replicas_entry_validate(e, sb, err); + int ret = bch2_replicas_entry_validate_locked(e, sb, err); if (ret) return ret; diff --git a/fs/bcachefs/replicas.h b/fs/bcachefs/replicas.h index 622482559c3d..5aba2c1ce133 100644 --- a/fs/bcachefs/replicas.h +++ b/fs/bcachefs/replicas.h @@ -10,7 +10,7 @@ void bch2_replicas_entry_sort(struct bch_replicas_entry_v1 *); void bch2_replicas_entry_to_text(struct printbuf *, struct bch_replicas_entry_v1 *); int bch2_replicas_entry_validate(struct bch_replicas_entry_v1 *, - struct bch_sb *, struct printbuf *); + struct bch_fs *, struct printbuf *); void bch2_cpu_replicas_to_text(struct printbuf *, struct bch_replicas_cpu *); static inline struct bch_replicas_entry_v1 * diff --git a/fs/bcachefs/sb-clean.c b/fs/bcachefs/sb-clean.c index 025848a9c4c0..005275281804 100644 --- a/fs/bcachefs/sb-clean.c +++ b/fs/bcachefs/sb-clean.c @@ -167,6 +167,7 @@ struct bch_sb_field_clean *bch2_read_superblock_clean(struct bch_fs *c) ret = bch2_sb_clean_validate_late(c, clean, READ); if (ret) { + kfree(clean); mutex_unlock(&c->sb_lock); return ERR_PTR(ret); } diff --git a/fs/bcachefs/sb-downgrade.c b/fs/bcachefs/sb-downgrade.c index c7e4cdd3f6a5..5102059a0f1d 100644 --- a/fs/bcachefs/sb-downgrade.c +++ b/fs/bcachefs/sb-downgrade.c @@ -312,8 +312,7 @@ static void bch2_sb_downgrade_to_text(struct printbuf *out, struct bch_sb *sb, if (!first) prt_char(out, ','); first = false; - unsigned e = le16_to_cpu(i->errors[j]); - prt_str(out, e < BCH_SB_ERR_MAX ? bch2_sb_error_strs[e] : "(unknown)"); + bch2_sb_error_id_to_text(out, le16_to_cpu(i->errors[j])); } prt_newline(out); } @@ -353,7 +352,9 @@ int bch2_sb_downgrade_update(struct bch_fs *c) for (unsigned i = 0; i < src->nr_errors; i++) dst->errors[i] = cpu_to_le16(src->errors[i]); - downgrade_table_extra(c, &table); + ret = downgrade_table_extra(c, &table); + if (ret) + goto out; if (!dst->recovery_passes[0] && !dst->recovery_passes[1] && @@ -399,7 +400,7 @@ void bch2_sb_set_downgrade(struct bch_fs *c, unsigned new_minor, unsigned old_mi for (unsigned j = 0; j < le16_to_cpu(i->nr_errors); j++) { unsigned e = le16_to_cpu(i->errors[j]); - if (e < BCH_SB_ERR_MAX) + if (e < BCH_FSCK_ERR_MAX) __set_bit(e, c->sb.errors_silent); if (e < sizeof(ext->errors_silent) * 8) __set_bit_le64(e, ext->errors_silent); diff --git a/fs/bcachefs/sb-errors.c b/fs/bcachefs/sb-errors.c index c1270d790e43..013a96883b4e 100644 --- a/fs/bcachefs/sb-errors.c +++ b/fs/bcachefs/sb-errors.c @@ -7,12 +7,12 @@ const char * const bch2_sb_error_strs[] = { #define x(t, n, ...) [n] = #t, BCH_SB_ERRS() - NULL +#undef x }; -static void bch2_sb_error_id_to_text(struct printbuf *out, enum bch_sb_error_id id) +void bch2_sb_error_id_to_text(struct printbuf *out, enum bch_sb_error_id id) { - if (id < BCH_SB_ERR_MAX) + if (id < BCH_FSCK_ERR_MAX) prt_str(out, bch2_sb_error_strs[id]); else prt_printf(out, "(unknown error %u)", id); diff --git a/fs/bcachefs/sb-errors.h b/fs/bcachefs/sb-errors.h index 8889001e7db4..b2357b8e6107 100644 --- a/fs/bcachefs/sb-errors.h +++ b/fs/bcachefs/sb-errors.h @@ -6,6 +6,8 @@ extern const char * const bch2_sb_error_strs[]; +void bch2_sb_error_id_to_text(struct printbuf *, enum bch_sb_error_id); + extern const struct bch_sb_field_ops bch_sb_field_ops_errors; void bch2_sb_error_count(struct bch_fs *, enum bch_sb_error_id); diff --git a/fs/bcachefs/sb-errors_format.h b/fs/bcachefs/sb-errors_format.h index f0c14702f9e6..4135b1ea2fec 100644 --- a/fs/bcachefs/sb-errors_format.h +++ b/fs/bcachefs/sb-errors_format.h @@ -115,8 +115,8 @@ enum bch_fsck_flags { x(alloc_key_data_type_inconsistency, 101, 0) \ x(alloc_key_to_missing_dev_bucket, 102, 0) \ x(alloc_key_cached_inconsistency, 103, 0) \ - x(alloc_key_cached_but_read_time_zero, 104, 0) \ - x(alloc_key_to_missing_lru_entry, 105, 0) \ + x(alloc_key_cached_but_read_time_zero, 104, FSCK_AUTOFIX) \ + x(alloc_key_to_missing_lru_entry, 105, FSCK_AUTOFIX) \ x(alloc_key_data_type_wrong, 106, FSCK_AUTOFIX) \ x(alloc_key_gen_wrong, 107, FSCK_AUTOFIX) \ x(alloc_key_dirty_sectors_wrong, 108, FSCK_AUTOFIX) \ @@ -129,20 +129,20 @@ enum bch_fsck_flags { x(freespace_key_wrong, 115, 0) \ x(freespace_hole_missing, 116, 0) \ x(bucket_gens_val_size_bad, 117, 0) \ - x(bucket_gens_key_wrong, 118, 0) \ - x(bucket_gens_hole_wrong, 119, 0) \ - x(bucket_gens_to_invalid_dev, 120, 0) \ - x(bucket_gens_to_invalid_buckets, 121, 0) \ - x(bucket_gens_nonzero_for_invalid_buckets, 122, 0) \ + x(bucket_gens_key_wrong, 118, FSCK_AUTOFIX) \ + x(bucket_gens_hole_wrong, 119, FSCK_AUTOFIX) \ + x(bucket_gens_to_invalid_dev, 120, FSCK_AUTOFIX) \ + x(bucket_gens_to_invalid_buckets, 121, FSCK_AUTOFIX) \ + x(bucket_gens_nonzero_for_invalid_buckets, 122, FSCK_AUTOFIX) \ x(need_discard_freespace_key_to_invalid_dev_bucket, 123, 0) \ x(need_discard_freespace_key_bad, 124, 0) \ x(backpointer_bucket_offset_wrong, 125, 0) \ x(backpointer_to_missing_device, 126, 0) \ x(backpointer_to_missing_alloc, 127, 0) \ x(backpointer_to_missing_ptr, 128, 0) \ - x(lru_entry_at_time_0, 129, 0) \ - x(lru_entry_to_invalid_bucket, 130, 0) \ - x(lru_entry_bad, 131, 0) \ + x(lru_entry_at_time_0, 129, FSCK_AUTOFIX) \ + x(lru_entry_to_invalid_bucket, 130, FSCK_AUTOFIX) \ + x(lru_entry_bad, 131, FSCK_AUTOFIX) \ x(btree_ptr_val_too_big, 132, 0) \ x(btree_ptr_v2_val_too_big, 133, 0) \ x(btree_ptr_has_non_ptr, 134, 0) \ @@ -158,9 +158,9 @@ enum bch_fsck_flags { x(ptr_after_last_bucket, 144, 0) \ x(ptr_before_first_bucket, 145, 0) \ x(ptr_spans_multiple_buckets, 146, 0) \ - x(ptr_to_missing_backpointer, 147, 0) \ - x(ptr_to_missing_alloc_key, 148, 0) \ - x(ptr_to_missing_replicas_entry, 149, 0) \ + x(ptr_to_missing_backpointer, 147, FSCK_AUTOFIX) \ + x(ptr_to_missing_alloc_key, 148, FSCK_AUTOFIX) \ + x(ptr_to_missing_replicas_entry, 149, FSCK_AUTOFIX) \ x(ptr_to_missing_stripe, 150, 0) \ x(ptr_to_incorrect_stripe, 151, 0) \ x(ptr_gen_newer_than_bucket_gen, 152, 0) \ @@ -194,7 +194,7 @@ enum bch_fsck_flags { x(snapshot_skiplist_not_normalized, 180, 0) \ x(snapshot_skiplist_bad, 181, 0) \ x(snapshot_should_not_have_subvol, 182, 0) \ - x(snapshot_to_bad_snapshot_tree, 183, 0) \ + x(snapshot_to_bad_snapshot_tree, 183, FSCK_AUTOFIX) \ x(snapshot_bad_depth, 184, 0) \ x(snapshot_bad_skiplist, 185, 0) \ x(subvol_pos_bad, 186, 0) \ @@ -210,22 +210,26 @@ enum bch_fsck_flags { x(inode_snapshot_mismatch, 196, 0) \ x(inode_unlinked_but_clean, 197, 0) \ x(inode_unlinked_but_nlink_nonzero, 198, 0) \ + x(inode_unlinked_and_not_open, 281, 0) \ + x(inode_unlinked_but_has_dirent, 285, 0) \ x(inode_checksum_type_invalid, 199, 0) \ x(inode_compression_type_invalid, 200, 0) \ x(inode_subvol_root_but_not_dir, 201, 0) \ - x(inode_i_size_dirty_but_clean, 202, 0) \ - x(inode_i_sectors_dirty_but_clean, 203, 0) \ - x(inode_i_sectors_wrong, 204, 0) \ - x(inode_dir_wrong_nlink, 205, 0) \ - x(inode_dir_multiple_links, 206, 0) \ - x(inode_multiple_links_but_nlink_0, 207, 0) \ - x(inode_wrong_backpointer, 208, 0) \ - x(inode_wrong_nlink, 209, 0) \ - x(inode_unreachable, 210, 0) \ - x(deleted_inode_but_clean, 211, 0) \ - x(deleted_inode_missing, 212, 0) \ - x(deleted_inode_is_dir, 213, 0) \ - x(deleted_inode_not_unlinked, 214, 0) \ + x(inode_i_size_dirty_but_clean, 202, FSCK_AUTOFIX) \ + x(inode_i_sectors_dirty_but_clean, 203, FSCK_AUTOFIX) \ + x(inode_i_sectors_wrong, 204, FSCK_AUTOFIX) \ + x(inode_dir_wrong_nlink, 205, FSCK_AUTOFIX) \ + x(inode_dir_multiple_links, 206, FSCK_AUTOFIX) \ + x(inode_dir_missing_backpointer, 284, FSCK_AUTOFIX) \ + x(inode_dir_unlinked_but_not_empty, 286, FSCK_AUTOFIX) \ + x(inode_multiple_links_but_nlink_0, 207, FSCK_AUTOFIX) \ + x(inode_wrong_backpointer, 208, FSCK_AUTOFIX) \ + x(inode_wrong_nlink, 209, FSCK_AUTOFIX) \ + x(inode_unreachable, 210, FSCK_AUTOFIX) \ + x(deleted_inode_but_clean, 211, FSCK_AUTOFIX) \ + x(deleted_inode_missing, 212, FSCK_AUTOFIX) \ + x(deleted_inode_is_dir, 213, FSCK_AUTOFIX) \ + x(deleted_inode_not_unlinked, 214, FSCK_AUTOFIX) \ x(extent_overlapping, 215, 0) \ x(key_in_missing_inode, 216, 0) \ x(key_in_wrong_inode_type, 217, 0) \ @@ -255,7 +259,7 @@ enum bch_fsck_flags { x(dir_loop, 241, 0) \ x(hash_table_key_duplicate, 242, 0) \ x(hash_table_key_wrong_offset, 243, 0) \ - x(unlinked_inode_not_on_deleted_list, 244, 0) \ + x(unlinked_inode_not_on_deleted_list, 244, FSCK_AUTOFIX) \ x(reflink_p_front_pad_bad, 245, 0) \ x(journal_entry_dup_same_device, 246, 0) \ x(inode_bi_subvol_missing, 247, 0) \ @@ -270,7 +274,7 @@ enum bch_fsck_flags { x(subvol_children_not_set, 256, 0) \ x(subvol_children_bad, 257, 0) \ x(subvol_loop, 258, 0) \ - x(subvol_unreachable, 259, 0) \ + x(subvol_unreachable, 259, FSCK_AUTOFIX) \ x(btree_node_bkey_bad_u64s, 260, 0) \ x(btree_node_topology_empty_interior_node, 261, 0) \ x(btree_ptr_v2_min_key_bad, 262, 0) \ @@ -282,8 +286,8 @@ enum bch_fsck_flags { x(btree_ptr_v2_written_0, 268, 0) \ x(subvol_snapshot_bad, 269, 0) \ x(subvol_inode_bad, 270, 0) \ - x(alloc_key_stripe_sectors_wrong, 271, 0) \ - x(accounting_mismatch, 272, 0) \ + x(alloc_key_stripe_sectors_wrong, 271, FSCK_AUTOFIX) \ + x(accounting_mismatch, 272, FSCK_AUTOFIX) \ x(accounting_replicas_not_marked, 273, 0) \ x(invalid_btree_id, 274, 0) \ x(alloc_key_io_time_bad, 275, 0) \ @@ -292,12 +296,14 @@ enum bch_fsck_flags { x(accounting_key_replicas_nr_devs_0, 278, FSCK_AUTOFIX) \ x(accounting_key_replicas_nr_required_bad, 279, FSCK_AUTOFIX) \ x(accounting_key_replicas_devs_unsorted, 280, FSCK_AUTOFIX) \ + x(accounting_key_version_0, 282, FSCK_AUTOFIX) \ + x(logged_op_but_clean, 283, FSCK_AUTOFIX) \ + x(MAX, 287, 0) enum bch_sb_error_id { #define x(t, n, ...) BCH_FSCK_ERR_##t = n, BCH_SB_ERRS() #undef x - BCH_SB_ERR_MAX }; struct bch_sb_field_errors { diff --git a/fs/bcachefs/siphash.c b/fs/bcachefs/siphash.c index dc1a27cc31cd..a1cc44e66c7e 100644 --- a/fs/bcachefs/siphash.c +++ b/fs/bcachefs/siphash.c @@ -45,7 +45,7 @@ */ #include <asm/byteorder.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/bitops.h> #include <linux/string.h> diff --git a/fs/bcachefs/six.c b/fs/bcachefs/six.c index 9cbd3c14c94f..617d07e53b20 100644 --- a/fs/bcachefs/six.c +++ b/fs/bcachefs/six.c @@ -169,11 +169,17 @@ static int __do_six_trylock(struct six_lock *lock, enum six_lock_type type, ret = -1 - SIX_LOCK_write; } } else if (type == SIX_LOCK_write && lock->readers) { - if (try) { + if (try) atomic_add(SIX_LOCK_HELD_write, &lock->state); - smp_mb__after_atomic(); - } + /* + * Make sure atomic_add happens before pcpu_read_count and + * six_set_bitmask in slow path happens before pcpu_read_count. + * + * Paired with the smp_mb() in read lock fast path (per-cpu mode) + * and the one before atomic_read in read unlock path. + */ + smp_mb(); ret = !pcpu_read_count(lock); if (try && !ret) { diff --git a/fs/bcachefs/snapshot.c b/fs/bcachefs/snapshot.c index 8b18a9b483a4..1809442b00ee 100644 --- a/fs/bcachefs/snapshot.c +++ b/fs/bcachefs/snapshot.c @@ -469,6 +469,7 @@ static u32 bch2_snapshot_tree_oldest_subvol(struct bch_fs *c, u32 snapshot_root) u32 id = snapshot_root; u32 subvol = 0, s; + rcu_read_lock(); while (id) { s = snapshot_t(c, id)->subvol; @@ -477,6 +478,7 @@ static u32 bch2_snapshot_tree_oldest_subvol(struct bch_fs *c, u32 snapshot_root) id = bch2_snapshot_tree_next(c, id); } + rcu_read_unlock(); return subvol; } @@ -1782,6 +1784,7 @@ static int bch2_propagate_key_to_snapshot_leaf(struct btree_trans *trans, new->k.p.snapshot = leaf_id; ret = bch2_trans_update(trans, &iter, new, 0); out: + bch2_set_btree_iter_dontneed(&iter); bch2_trans_iter_exit(trans, &iter); return ret; } diff --git a/fs/bcachefs/subvolume.c b/fs/bcachefs/subvolume.c index dbe834cb349f..91d8187ee168 100644 --- a/fs/bcachefs/subvolume.c +++ b/fs/bcachefs/subvolume.c @@ -92,34 +92,33 @@ static int check_subvol(struct btree_trans *trans, } struct bch_inode_unpacked inode; - struct btree_iter inode_iter = {}; - ret = bch2_inode_peek_nowarn(trans, &inode_iter, &inode, + ret = bch2_inode_find_by_inum_nowarn_trans(trans, (subvol_inum) { k.k->p.offset, le64_to_cpu(subvol.v->inode) }, - 0); - bch2_trans_iter_exit(trans, &inode_iter); - - if (ret && !bch2_err_matches(ret, ENOENT)) - return ret; - - if (fsck_err_on(ret, - trans, subvol_to_missing_root, - "subvolume %llu points to missing subvolume root %llu:%u", - k.k->p.offset, le64_to_cpu(subvol.v->inode), - le32_to_cpu(subvol.v->snapshot))) { - ret = bch2_subvolume_delete(trans, iter->pos.offset); - bch_err_msg(c, ret, "deleting subvolume %llu", iter->pos.offset); - return ret ?: -BCH_ERR_transaction_restart_nested; - } - - if (fsck_err_on(inode.bi_subvol != subvol.k->p.offset, - trans, subvol_root_wrong_bi_subvol, - "subvol root %llu:%u has wrong bi_subvol field: got %u, should be %llu", - inode.bi_inum, inode_iter.k.p.snapshot, - inode.bi_subvol, subvol.k->p.offset)) { - inode.bi_subvol = subvol.k->p.offset; - ret = __bch2_fsck_write_inode(trans, &inode, le32_to_cpu(subvol.v->snapshot)); - if (ret) + &inode); + if (!ret) { + if (fsck_err_on(inode.bi_subvol != subvol.k->p.offset, + trans, subvol_root_wrong_bi_subvol, + "subvol root %llu:%u has wrong bi_subvol field: got %u, should be %llu", + inode.bi_inum, inode.bi_snapshot, + inode.bi_subvol, subvol.k->p.offset)) { + inode.bi_subvol = subvol.k->p.offset; + inode.bi_snapshot = le32_to_cpu(subvol.v->snapshot); + ret = __bch2_fsck_write_inode(trans, &inode); + if (ret) + goto err; + } + } else if (bch2_err_matches(ret, ENOENT)) { + if (fsck_err(trans, subvol_to_missing_root, + "subvolume %llu points to missing subvolume root %llu:%u", + k.k->p.offset, le64_to_cpu(subvol.v->inode), + le32_to_cpu(subvol.v->snapshot))) { + ret = bch2_subvolume_delete(trans, iter->pos.offset); + bch_err_msg(c, ret, "deleting subvolume %llu", iter->pos.offset); + ret = ret ?: -BCH_ERR_transaction_restart_nested; goto err; + } + } else { + goto err; } if (!BCH_SUBVOLUME_SNAP(subvol.v)) { @@ -137,7 +136,7 @@ static int check_subvol(struct btree_trans *trans, "%s: snapshot tree %u not found", __func__, snapshot_tree); if (ret) - return ret; + goto err; if (fsck_err_on(le32_to_cpu(st.master_subvol) != subvol.k->p.offset, trans, subvol_not_master_and_not_snapshot, @@ -147,7 +146,7 @@ static int check_subvol(struct btree_trans *trans, bch2_bkey_make_mut_typed(trans, iter, &subvol.s_c, 0, subvolume); ret = PTR_ERR_OR_ZERO(s); if (ret) - return ret; + goto err; SET_BCH_SUBVOLUME_SNAP(&s->v, true); } @@ -333,8 +332,8 @@ int bch2_snapshot_get_subvol(struct btree_trans *trans, u32 snapshot, bch2_subvolume_get(trans, le32_to_cpu(snap.subvol), true, 0, subvol); } -int bch2_subvolume_get_snapshot(struct btree_trans *trans, u32 subvolid, - u32 *snapid) +int __bch2_subvolume_get_snapshot(struct btree_trans *trans, u32 subvolid, + u32 *snapid, bool warn) { struct btree_iter iter; struct bkey_s_c_subvolume subvol; @@ -345,7 +344,8 @@ int bch2_subvolume_get_snapshot(struct btree_trans *trans, u32 subvolid, BTREE_ITER_cached|BTREE_ITER_with_updates, subvolume); ret = bkey_err(subvol); - bch2_fs_inconsistent_on(bch2_err_matches(ret, ENOENT), trans->c, + + bch2_fs_inconsistent_on(warn && bch2_err_matches(ret, ENOENT), trans->c, "missing subvolume %u", subvolid); if (likely(!ret)) @@ -354,6 +354,12 @@ int bch2_subvolume_get_snapshot(struct btree_trans *trans, u32 subvolid, return ret; } +int bch2_subvolume_get_snapshot(struct btree_trans *trans, u32 subvolid, + u32 *snapid) +{ + return __bch2_subvolume_get_snapshot(trans, subvolid, snapid, true); +} + static int bch2_subvolume_reparent(struct btree_trans *trans, struct btree_iter *iter, struct bkey_s_c k, diff --git a/fs/bcachefs/subvolume.h b/fs/bcachefs/subvolume.h index e62f876541fe..f897d106e142 100644 --- a/fs/bcachefs/subvolume.h +++ b/fs/bcachefs/subvolume.h @@ -26,6 +26,8 @@ int bch2_subvolume_trigger(struct btree_trans *, enum btree_id, unsigned, int bch2_subvol_has_children(struct btree_trans *, u32); int bch2_subvolume_get(struct btree_trans *, unsigned, bool, int, struct bch_subvolume *); +int __bch2_subvolume_get_snapshot(struct btree_trans *, u32, + u32 *, bool); int bch2_subvolume_get_snapshot(struct btree_trans *, u32, u32 *); int bch2_subvol_is_ro_trans(struct btree_trans *, u32); diff --git a/fs/bcachefs/super-io.c b/fs/bcachefs/super-io.c index d86d5dae54c9..ce7410d72089 100644 --- a/fs/bcachefs/super-io.c +++ b/fs/bcachefs/super-io.c @@ -799,8 +799,10 @@ retry: i < layout.sb_offset + layout.nr_superblocks; i++) { offset = le64_to_cpu(*i); - if (offset == opt_get(*opts, sb)) + if (offset == opt_get(*opts, sb)) { + ret = -BCH_ERR_invalid; continue; + } ret = read_one_super(sb, offset, &err); if (!ret) @@ -1188,7 +1190,8 @@ static void bch2_sb_ext_to_text(struct printbuf *out, struct bch_sb *sb, le_bitvector_to_cpu(errors_silent, (void *) e->errors_silent, sizeof(e->errors_silent) * 8); prt_printf(out, "Errors to silently fix:\t"); - prt_bitflags_vector(out, bch2_sb_error_strs, errors_silent, sizeof(e->errors_silent) * 8); + prt_bitflags_vector(out, bch2_sb_error_strs, errors_silent, + min(BCH_FSCK_ERR_MAX, sizeof(e->errors_silent) * 8)); prt_newline(out); kfree(errors_silent); diff --git a/fs/bcachefs/tests.c b/fs/bcachefs/tests.c index 01b768c9b767..b2f209743afe 100644 --- a/fs/bcachefs/tests.c +++ b/fs/bcachefs/tests.c @@ -394,7 +394,7 @@ static int insert_test_extent(struct bch_fs *c, k.k_i.k.p.offset = end; k.k_i.k.p.snapshot = U32_MAX; k.k_i.k.size = end - start; - k.k_i.k.version.lo = test_version++; + k.k_i.k.bversion.lo = test_version++; ret = bch2_btree_insert(c, BTREE_ID_extents, &k.k_i, NULL, 0, 0); bch_err_fn(c, ret); diff --git a/fs/bcachefs/util.c b/fs/bcachefs/util.c index 42f565c76181..e0a876cbaa6b 100644 --- a/fs/bcachefs/util.c +++ b/fs/bcachefs/util.c @@ -222,7 +222,7 @@ u64 bch2_read_flag_list(const char *opt, const char * const list[]) break; } - ret |= 1 << flag; + ret |= BIT_ULL(flag); } kfree(d); diff --git a/fs/bcachefs/varint.c b/fs/bcachefs/varint.c index a9ebcd82c602..6a78553d9b0c 100644 --- a/fs/bcachefs/varint.c +++ b/fs/bcachefs/varint.c @@ -3,7 +3,7 @@ #include <linux/bitops.h> #include <linux/math.h> #include <linux/string.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #ifdef CONFIG_VALGRIND #include <valgrind/memcheck.h> diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c index cd6d5bbb4b9d..390808ce935d 100644 --- a/fs/binfmt_flat.c +++ b/fs/binfmt_flat.c @@ -39,7 +39,7 @@ #include <linux/vmalloc.h> #include <asm/byteorder.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <asm/cacheflush.h> #include <asm/page.h> #include <asm/flat.h> diff --git a/fs/btrfs/accessors.c b/fs/btrfs/accessors.c index 79026917db19..e3716516ca38 100644 --- a/fs/btrfs/accessors.c +++ b/fs/btrfs/accessors.c @@ -3,7 +3,7 @@ * Copyright (C) 2007 Oracle. All rights reserved. */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "messages.h" #include "extent_io.h" #include "fs.h" diff --git a/fs/btrfs/accessors.h b/fs/btrfs/accessors.h index b2eb9cde2c5d..7a7e0ef69973 100644 --- a/fs/btrfs/accessors.h +++ b/fs/btrfs/accessors.h @@ -3,7 +3,7 @@ #ifndef BTRFS_ACCESSORS_H #define BTRFS_ACCESSORS_H -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/stddef.h> #include <linux/types.h> #include <linux/align.h> diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index e2f478ecd7fd..f8e1d5b2c512 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -3179,10 +3179,14 @@ void btrfs_backref_release_cache(struct btrfs_backref_cache *cache) btrfs_backref_cleanup_node(cache, node); } - cache->last_trans = 0; - - for (i = 0; i < BTRFS_MAX_LEVEL; i++) - ASSERT(list_empty(&cache->pending[i])); + for (i = 0; i < BTRFS_MAX_LEVEL; i++) { + while (!list_empty(&cache->pending[i])) { + node = list_first_entry(&cache->pending[i], + struct btrfs_backref_node, + list); + btrfs_backref_cleanup_node(cache, node); + } + } ASSERT(list_empty(&cache->pending_edge)); ASSERT(list_empty(&cache->useless_node)); ASSERT(list_empty(&cache->changed)); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 25d768e67e37..4ad5db619b00 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -17,7 +17,7 @@ #include <linux/error-injection.h> #include <linux/crc32c.h> #include <linux/sched/mm.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <crypto/hash.h> #include "ctree.h" #include "disk-io.h" @@ -4256,6 +4256,17 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info) btrfs_cleanup_defrag_inodes(fs_info); /* + * Wait for any fixup workers to complete. + * If we don't wait for them here and they are still running by the time + * we call kthread_stop() against the cleaner kthread further below, we + * get an use-after-free on the cleaner because the fixup worker adds an + * inode to the list of delayed iputs and then attempts to wakeup the + * cleaner kthread, which was already stopped and destroyed. We parked + * already the cleaner, but below we run all pending delayed iputs. + */ + btrfs_flush_workqueue(fs_info->fixup_workers); + + /* * After we parked the cleaner kthread, ordered extents may have * completed and created new delayed iputs. If one of the async reclaim * tasks is running and in the RUN_DELAYED_IPUTS flush state, then we diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index edac499fd83d..5618ca02934a 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -32,7 +32,7 @@ #include <linux/migrate.h> #include <linux/sched/mm.h> #include <linux/iomap.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/fsverity.h> #include "misc.h" #include "ctree.h" @@ -3111,6 +3111,11 @@ int btrfs_finish_one_ordered(struct btrfs_ordered_extent *ordered_extent) ret = btrfs_update_inode_fallback(trans, inode); if (ret) /* -ENOMEM or corruption */ btrfs_abort_transaction(trans, ret); + + ret = btrfs_insert_raid_extent(trans, ordered_extent); + if (ret) + btrfs_abort_transaction(trans, ret); + goto out; } diff --git a/fs/btrfs/messages.c b/fs/btrfs/messages.c index 77752eec125d..363fd28c0268 100644 --- a/fs/btrfs/messages.c +++ b/fs/btrfs/messages.c @@ -239,7 +239,8 @@ void __cold _btrfs_printk(const struct btrfs_fs_info *fs_info, const char *fmt, vaf.fmt = fmt; vaf.va = &args; - if (__ratelimit(ratelimit)) { + /* Do not ratelimit if CONFIG_BTRFS_DEBUG is enabled. */ + if (IS_ENABLED(CONFIG_BTRFS_DEBUG) || __ratelimit(ratelimit)) { if (fs_info) { char statestr[STATE_STRING_BUF_LEN]; diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index ea4ed85919ec..f3834f8d26b4 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -232,70 +232,6 @@ static struct btrfs_backref_node *walk_down_backref( return NULL; } -static void update_backref_node(struct btrfs_backref_cache *cache, - struct btrfs_backref_node *node, u64 bytenr) -{ - struct rb_node *rb_node; - rb_erase(&node->rb_node, &cache->rb_root); - node->bytenr = bytenr; - rb_node = rb_simple_insert(&cache->rb_root, node->bytenr, &node->rb_node); - if (rb_node) - btrfs_backref_panic(cache->fs_info, bytenr, -EEXIST); -} - -/* - * update backref cache after a transaction commit - */ -static int update_backref_cache(struct btrfs_trans_handle *trans, - struct btrfs_backref_cache *cache) -{ - struct btrfs_backref_node *node; - int level = 0; - - if (cache->last_trans == 0) { - cache->last_trans = trans->transid; - return 0; - } - - if (cache->last_trans == trans->transid) - return 0; - - /* - * detached nodes are used to avoid unnecessary backref - * lookup. transaction commit changes the extent tree. - * so the detached nodes are no longer useful. - */ - while (!list_empty(&cache->detached)) { - node = list_entry(cache->detached.next, - struct btrfs_backref_node, list); - btrfs_backref_cleanup_node(cache, node); - } - - while (!list_empty(&cache->changed)) { - node = list_entry(cache->changed.next, - struct btrfs_backref_node, list); - list_del_init(&node->list); - BUG_ON(node->pending); - update_backref_node(cache, node, node->new_bytenr); - } - - /* - * some nodes can be left in the pending list if there were - * errors during processing the pending nodes. - */ - for (level = 0; level < BTRFS_MAX_LEVEL; level++) { - list_for_each_entry(node, &cache->pending[level], list) { - BUG_ON(!node->pending); - if (node->bytenr == node->new_bytenr) - continue; - update_backref_node(cache, node, node->new_bytenr); - } - } - - cache->last_trans = 0; - return 1; -} - static bool reloc_root_is_dead(const struct btrfs_root *root) { /* @@ -551,9 +487,6 @@ static int clone_backref_node(struct btrfs_trans_handle *trans, struct btrfs_backref_edge *new_edge; struct rb_node *rb_node; - if (cache->last_trans > 0) - update_backref_cache(trans, cache); - rb_node = rb_simple_search(&cache->rb_root, src->commit_root->start); if (rb_node) { node = rb_entry(rb_node, struct btrfs_backref_node, rb_node); @@ -923,7 +856,7 @@ int btrfs_update_reloc_root(struct btrfs_trans_handle *trans, btrfs_grab_root(reloc_root); /* root->reloc_root will stay until current relocation finished */ - if (fs_info->reloc_ctl->merge_reloc_tree && + if (fs_info->reloc_ctl && fs_info->reloc_ctl->merge_reloc_tree && btrfs_root_refs(root_item) == 0) { set_bit(BTRFS_ROOT_DEAD_RELOC_TREE, &root->state); /* @@ -3698,11 +3631,9 @@ static noinline_for_stack int relocate_block_group(struct reloc_control *rc) break; } restart: - if (update_backref_cache(trans, &rc->backref_cache)) { - btrfs_end_transaction(trans); - trans = NULL; - continue; - } + if (rc->backref_cache.last_trans != trans->transid) + btrfs_backref_release_cache(&rc->backref_cache); + rc->backref_cache.last_trans = trans->transid; ret = find_next_extent(rc, path, &key); if (ret < 0) diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 7f48ba6c1c77..27306d98ec43 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -346,8 +346,10 @@ struct name_cache_entry { u64 parent_gen; int ret; int need_later_update; + /* Name length without NUL terminator. */ int name_len; - char name[] __counted_by(name_len); + /* Not NUL terminated. */ + char name[] __counted_by(name_len) __nonstring; }; /* See the comment at lru_cache.h about struct btrfs_lru_cache_entry. */ @@ -2388,7 +2390,7 @@ out_cache: /* * Store the result of the lookup in the name cache. */ - nce = kmalloc(sizeof(*nce) + fs_path_len(dest) + 1, GFP_KERNEL); + nce = kmalloc(sizeof(*nce) + fs_path_len(dest), GFP_KERNEL); if (!nce) { ret = -ENOMEM; goto out; @@ -2400,7 +2402,7 @@ out_cache: nce->parent_gen = *parent_gen; nce->name_len = fs_path_len(dest); nce->ret = ret; - strcpy(nce->name, dest->start); + memcpy(nce->name, dest->start, nce->name_len); if (ino < sctx->send_progress) nce->need_later_update = 0; @@ -6187,8 +6189,29 @@ static int send_write_or_clone(struct send_ctx *sctx, if (ret < 0) return ret; - if (clone_root->offset + num_bytes == info.size) + if (clone_root->offset + num_bytes == info.size) { + /* + * The final size of our file matches the end offset, but it may + * be that its current size is larger, so we have to truncate it + * to any value between the start offset of the range and the + * final i_size, otherwise the clone operation is invalid + * because it's unaligned and it ends before the current EOF. + * We do this truncate to the final i_size when we finish + * processing the inode, but it's too late by then. And here we + * truncate to the start offset of the range because it's always + * sector size aligned while if it were the final i_size it + * would result in dirtying part of a page, filling part of a + * page with zeroes and then having the clone operation at the + * receiver trigger IO and wait for it due to the dirty page. + */ + if (sctx->parent_root != NULL) { + ret = send_truncate(sctx, sctx->cur_ino, + sctx->cur_inode_gen, offset); + if (ret < 0) + return ret; + } goto clone_data; + } write_data: ret = send_extent_data(sctx, path, offset, num_bytes); diff --git a/fs/btrfs/uuid-tree.c b/fs/btrfs/uuid-tree.c index c6399513c66f..aca2861f2187 100644 --- a/fs/btrfs/uuid-tree.c +++ b/fs/btrfs/uuid-tree.c @@ -5,7 +5,7 @@ #include <linux/kthread.h> #include <linux/uuid.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "messages.h" #include "ctree.h" #include "transaction.h" diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c index f53977169db4..2b3f9935dbb4 100644 --- a/fs/cachefiles/namei.c +++ b/fs/cachefiles/namei.c @@ -595,14 +595,12 @@ static bool cachefiles_open_file(struct cachefiles_object *object, * write and readdir but not lookup or open). */ touch_atime(&file->f_path); - dput(dentry); return true; check_failed: fscache_cookie_lookup_negative(object->cookie); cachefiles_unmark_inode_in_use(object, file); fput(file); - dput(dentry); if (ret == -ESTALE) return cachefiles_create_file(object); return false; @@ -611,7 +609,6 @@ error_fput: fput(file); error: cachefiles_do_unmark_inode_in_use(object, d_inode(dentry)); - dput(dentry); return false; } @@ -654,7 +651,9 @@ bool cachefiles_look_up_object(struct cachefiles_object *object) goto new_file; } - if (!cachefiles_open_file(object, dentry)) + ret = cachefiles_open_file(object, dentry); + dput(dentry); + if (!ret) return false; _leave(" = t [%lu]", file_inode(object->file)->i_ino); diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 5d9ccda098cc..c2a9e2cc03de 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -96,7 +96,6 @@ static bool ceph_dirty_folio(struct address_space *mapping, struct folio *folio) /* dirty the head */ spin_lock(&ci->i_ceph_lock); - BUG_ON(ci->i_wr_ref == 0); // caller should hold Fw reference if (__ceph_have_pending_cap_snap(ci)) { struct ceph_cap_snap *capsnap = list_last_entry(&ci->i_cap_snaps, @@ -490,8 +489,11 @@ static int ceph_init_request(struct netfs_io_request *rreq, struct file *file) rreq->io_streams[0].sreq_max_len = fsc->mount_options->rsize; out: - if (ret < 0) + if (ret < 0) { + if (got) + ceph_put_cap_refs(ceph_inode(inode), got); kfree(priv); + } return ret; } @@ -2146,7 +2148,7 @@ static int __ceph_pool_perm_get(struct ceph_inode_info *ci, } pool_ns_len = pool_ns ? pool_ns->len : 0; - perm = kmalloc(sizeof(*perm) + pool_ns_len + 1, GFP_NOFS); + perm = kmalloc(struct_size(perm, pool_ns, pool_ns_len + 1), GFP_NOFS); if (!perm) { err = -ENOMEM; goto out_unlock; diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 808c9c048276..bed34fc11c91 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -10,6 +10,7 @@ #include <linux/writeback.h> #include <linux/iversion.h> #include <linux/filelock.h> +#include <linux/jiffies.h> #include "super.h" #include "mds_client.h" @@ -4149,7 +4150,7 @@ retry: ceph_remove_cap(mdsc, cap, false); goto out_unlock; } else if (tsession) { - /* add placeholder for the export tagert */ + /* add placeholder for the export target */ int flag = (cap == ci->i_auth_cap) ? CEPH_CAP_FLAG_AUTH : 0; tcap = new_cap; ceph_add_cap(inode, tsession, t_cap_id, issued, 0, @@ -4602,7 +4603,7 @@ flush_cap_releases: __ceph_queue_cap_release(session, cap); spin_unlock(&session->s_cap_lock); } - ceph_flush_cap_releases(mdsc, session); + ceph_flush_session_cap_releases(mdsc, session); goto done; bad: @@ -4659,7 +4660,7 @@ unsigned long ceph_check_delayed_caps(struct ceph_mds_client *mdsc) * slowness doesn't block mdsc delayed work, * preventing send_renew_caps() from running. */ - if (jiffies - loop_start >= 5 * HZ) + if (time_after_eq(jiffies, loop_start + 5 * HZ)) break; } spin_unlock(&mdsc->cap_delay_lock); @@ -4701,6 +4702,28 @@ void ceph_flush_dirty_caps(struct ceph_mds_client *mdsc) ceph_mdsc_iterate_sessions(mdsc, flush_dirty_session_caps, true); } +/* + * Flush all cap releases to the mds + */ +static void flush_cap_releases(struct ceph_mds_session *s) +{ + struct ceph_mds_client *mdsc = s->s_mdsc; + struct ceph_client *cl = mdsc->fsc->client; + + doutc(cl, "begin\n"); + spin_lock(&s->s_cap_lock); + if (s->s_num_cap_releases) + ceph_flush_session_cap_releases(mdsc, s); + spin_unlock(&s->s_cap_lock); + doutc(cl, "done\n"); + +} + +void ceph_flush_cap_releases(struct ceph_mds_client *mdsc) +{ + ceph_mdsc_iterate_sessions(mdsc, flush_cap_releases, true); +} + void __ceph_touch_fmode(struct ceph_inode_info *ci, struct ceph_mds_client *mdsc, int fmode) { diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index ddec8c9244ee..952109292d69 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -2058,7 +2058,7 @@ static int ceph_d_delete(const struct dentry *dentry) return 0; if (ceph_snap(d_inode(dentry)) != CEPH_NOSNAP) return 0; - /* vaild lease? */ + /* valid lease? */ di = ceph_dentry(dentry); if (di) { if (__dentry_lease_is_valid(di)) diff --git a/fs/ceph/export.c b/fs/ceph/export.c index a79f163ae4ed..44451749c544 100644 --- a/fs/ceph/export.c +++ b/fs/ceph/export.c @@ -3,7 +3,7 @@ #include <linux/exportfs.h> #include <linux/slab.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "super.h" #include "mds_client.h" diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 4a8eec46254b..315ef02f9a3f 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -1779,7 +1779,7 @@ retry_lookup: if (err < 0) goto done; } else if (rinfo->head->is_dentry && req->r_dentry) { - /* parent inode is not locked, be carefull */ + /* parent inode is not locked, be careful */ struct ceph_vino *ptvino = NULL; dvino.ino = le64_to_cpu(rinfo->diri.in->ino); dvino.snap = le64_to_cpu(rinfo->diri.in->snapid); diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 276e34ab3e2c..c4a5fd94bbbb 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -2266,7 +2266,7 @@ int ceph_trim_caps(struct ceph_mds_client *mdsc, trim_caps - remaining); } - ceph_flush_cap_releases(mdsc, session); + ceph_flush_session_cap_releases(mdsc, session); return 0; } @@ -2420,7 +2420,7 @@ static void ceph_cap_release_work(struct work_struct *work) ceph_put_mds_session(session); } -void ceph_flush_cap_releases(struct ceph_mds_client *mdsc, +void ceph_flush_session_cap_releases(struct ceph_mds_client *mdsc, struct ceph_mds_session *session) { struct ceph_client *cl = mdsc->fsc->client; @@ -2447,7 +2447,7 @@ void __ceph_queue_cap_release(struct ceph_mds_session *session, session->s_num_cap_releases++; if (!(session->s_num_cap_releases % CEPH_CAPS_PER_RELEASE)) - ceph_flush_cap_releases(session->s_mdsc, session); + ceph_flush_session_cap_releases(session->s_mdsc, session); } static void ceph_cap_reclaim_work(struct work_struct *work) @@ -4340,7 +4340,7 @@ skip_cap_auths: /* flush cap releases */ spin_lock(&session->s_cap_lock); if (session->s_num_cap_releases) - ceph_flush_cap_releases(mdsc, session); + ceph_flush_session_cap_releases(mdsc, session); spin_unlock(&session->s_cap_lock); send_flushmsg_ack(mdsc, session, seq); @@ -4910,7 +4910,7 @@ static void send_mds_reconnect(struct ceph_mds_client *mdsc, } else { recon_state.msg_version = 2; } - /* trsaverse this session's caps */ + /* traverse this session's caps */ err = ceph_iterate_session_caps(session, reconnect_caps_cb, &recon_state); spin_lock(&session->s_cap_lock); @@ -5446,7 +5446,7 @@ static void delayed_work(struct work_struct *work) } mutex_unlock(&mdsc->mutex); - ceph_flush_cap_releases(mdsc, s); + ceph_flush_session_cap_releases(mdsc, s); mutex_lock(&s->s_mutex); if (renew_caps) @@ -5877,6 +5877,7 @@ void ceph_mdsc_sync(struct ceph_mds_client *mdsc) mutex_unlock(&mdsc->mutex); ceph_flush_dirty_caps(mdsc); + ceph_flush_cap_releases(mdsc); spin_lock(&mdsc->cap_dirty_lock); want_flush = mdsc->last_cap_flush_tid; if (!list_empty(&mdsc->cap_flush_list)) { @@ -6015,6 +6016,18 @@ static void ceph_mdsc_stop(struct ceph_mds_client *mdsc) ceph_mdsmap_destroy(mdsc->mdsmap); kfree(mdsc->sessions); ceph_caps_finalize(mdsc); + + if (mdsc->s_cap_auths) { + int i; + + for (i = 0; i < mdsc->s_cap_auths_num; i++) { + kfree(mdsc->s_cap_auths[i].match.gids); + kfree(mdsc->s_cap_auths[i].match.path); + kfree(mdsc->s_cap_auths[i].match.fs_name); + } + kfree(mdsc->s_cap_auths); + } + ceph_pool_perm_destroy(mdsc); } diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index 9bcc7f181bfe..3dd54587944a 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -559,9 +559,6 @@ extern struct ceph_mds_session * ceph_get_mds_session(struct ceph_mds_session *s); extern void ceph_put_mds_session(struct ceph_mds_session *s); -extern int ceph_send_msg_mds(struct ceph_mds_client *mdsc, - struct ceph_msg *msg, int mds); - extern int ceph_mdsc_init(struct ceph_fs_client *fsc); extern void ceph_mdsc_close_sessions(struct ceph_mds_client *mdsc); extern void ceph_mdsc_force_umount(struct ceph_mds_client *mdsc); @@ -602,8 +599,8 @@ extern void ceph_mdsc_iterate_sessions(struct ceph_mds_client *mdsc, extern struct ceph_msg *ceph_create_session_msg(u32 op, u64 seq); extern void __ceph_queue_cap_release(struct ceph_mds_session *session, struct ceph_cap *cap); -extern void ceph_flush_cap_releases(struct ceph_mds_client *mdsc, - struct ceph_mds_session *session); +extern void ceph_flush_session_cap_releases(struct ceph_mds_client *mdsc, + struct ceph_mds_session *session); extern void ceph_queue_cap_reclaim_work(struct ceph_mds_client *mdsc); extern void ceph_reclaim_caps_nr(struct ceph_mds_client *mdsc, int nr); extern void ceph_queue_cap_unlink_work(struct ceph_mds_client *mdsc); diff --git a/fs/ceph/super.c b/fs/ceph/super.c index 0cdf84cd1791..73f321b52895 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -126,6 +126,7 @@ static int ceph_sync_fs(struct super_block *sb, int wait) if (!wait) { doutc(cl, "(non-blocking)\n"); ceph_flush_dirty_caps(fsc->mdsc); + ceph_flush_cap_releases(fsc->mdsc); doutc(cl, "(non-blocking) done\n"); return 0; } diff --git a/fs/ceph/super.h b/fs/ceph/super.h index 6e817bf1337c..037eac35a9e0 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -5,7 +5,7 @@ #include <linux/ceph/ceph_debug.h> #include <linux/ceph/osd_client.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/backing-dev.h> #include <linux/completion.h> #include <linux/exportfs.h> @@ -1056,8 +1056,6 @@ extern int ceph_fill_trace(struct super_block *sb, extern int ceph_readdir_prepopulate(struct ceph_mds_request *req, struct ceph_mds_session *session); -extern int ceph_inode_holds_cap(struct inode *inode, int mask); - extern bool ceph_inode_set_size(struct inode *inode, loff_t size); extern void __ceph_do_pending_vmtruncate(struct inode *inode); @@ -1208,10 +1206,6 @@ static inline void ceph_init_inode_acls(struct inode *inode, struct ceph_acl_sec_ctx *as_ctx) { } -static inline int ceph_acl_chmod(struct dentry *dentry, struct inode *inode) -{ - return 0; -} static inline void ceph_forget_all_cached_acls(struct inode *inode) { @@ -1270,6 +1264,7 @@ extern bool __ceph_should_report_size(struct ceph_inode_info *ci); extern void ceph_check_caps(struct ceph_inode_info *ci, int flags); extern unsigned long ceph_check_delayed_caps(struct ceph_mds_client *mdsc); extern void ceph_flush_dirty_caps(struct ceph_mds_client *mdsc); +extern void ceph_flush_cap_releases(struct ceph_mds_client *mdsc); extern int ceph_drop_caps_for_unlink(struct inode *inode); extern int ceph_encode_inode_release(void **p, struct inode *inode, int mds, int drop, int unless, int force); diff --git a/fs/crypto/keyring.c b/fs/crypto/keyring.c index 6681a71625f0..206835e31efa 100644 --- a/fs/crypto/keyring.c +++ b/fs/crypto/keyring.c @@ -18,7 +18,7 @@ * information about these ioctls. */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <crypto/skcipher.h> #include <linux/key-type.h> #include <linux/random.h> @@ -1305,11 +1305,15 @@ int dax_file_unshare(struct inode *inode, loff_t pos, loff_t len, struct iomap_iter iter = { .inode = inode, .pos = pos, - .len = len, .flags = IOMAP_WRITE | IOMAP_UNSHARE | IOMAP_DAX, }; + loff_t size = i_size_read(inode); int ret; + if (pos < 0 || pos >= size) + return 0; + + iter.len = min(len, size - pos); while ((ret = iomap_iter(&iter, ops)) > 0) iter.processed = dax_unshare_iter(&iter); return ret; diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c index d39a1a69fecc..827278525fd9 100644 --- a/fs/ecryptfs/crypto.c +++ b/fs/ecryptfs/crypto.c @@ -21,7 +21,7 @@ #include <linux/file.h> #include <linux/scatterlist.h> #include <linux/slab.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/kernel.h> #include <linux/xattr.h> #include "ecryptfs_kernel.h" diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index 5ed1e4cf6c0b..cbdf82f0183f 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -21,7 +21,7 @@ #include <linux/posix_acl.h> #include <linux/posix_acl_xattr.h> #include <linux/fileattr.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "ecryptfs_kernel.h" static int lock_parent(struct dentry *dentry, diff --git a/fs/ecryptfs/mmap.c b/fs/ecryptfs/mmap.c index 287e5d407f08..ceda5555971a 100644 --- a/fs/ecryptfs/mmap.c +++ b/fs/ecryptfs/mmap.c @@ -19,7 +19,7 @@ #include <linux/scatterlist.h> #include <linux/slab.h> #include <linux/xattr.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "ecryptfs_kernel.h" /* diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c index e980e29873a5..1253a8456e59 100644 --- a/fs/erofs/zmap.c +++ b/fs/erofs/zmap.c @@ -4,7 +4,7 @@ * https://www.huawei.com/ */ #include "internal.h" -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <trace/events/erofs.h> struct z_erofs_maprecorder { diff --git a/fs/exfat/cache.c b/fs/exfat/cache.c index 7cc200d89821..d5ce0ae660ba 100644 --- a/fs/exfat/cache.c +++ b/fs/exfat/cache.c @@ -11,7 +11,7 @@ */ #include <linux/slab.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/buffer_head.h> #include "exfat_raw.h" diff --git a/fs/exfat/fatent.c b/fs/exfat/fatent.c index 56b870d9cc0d..773c320d68f3 100644 --- a/fs/exfat/fatent.c +++ b/fs/exfat/fatent.c @@ -4,7 +4,7 @@ */ #include <linux/slab.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/buffer_head.h> #include <linux/blkdev.h> diff --git a/fs/exfat/nls.c b/fs/exfat/nls.c index 1ac011088ce7..d47896a89596 100644 --- a/fs/exfat/nls.c +++ b/fs/exfat/nls.c @@ -6,7 +6,7 @@ #include <linux/string.h> #include <linux/slab.h> #include <linux/buffer_head.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "exfat_raw.h" #include "exfat_fs.h" diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c index eaa5f5b51f50..b33664f6ce2a 100644 --- a/fs/ext4/fast_commit.c +++ b/fs/ext4/fast_commit.c @@ -379,7 +379,7 @@ void ext4_fc_mark_ineligible(struct super_block *sb, int reason, handle_t *handl */ static int ext4_fc_track_template( handle_t *handle, struct inode *inode, - int (*__fc_track_fn)(struct inode *, void *, bool), + int (*__fc_track_fn)(handle_t *handle, struct inode *, void *, bool), void *args, int enqueue) { bool update = false; @@ -396,7 +396,7 @@ static int ext4_fc_track_template( ext4_fc_reset_inode(inode); ei->i_sync_tid = tid; } - ret = __fc_track_fn(inode, args, update); + ret = __fc_track_fn(handle, inode, args, update); mutex_unlock(&ei->i_fc_lock); if (!enqueue) @@ -420,7 +420,8 @@ struct __track_dentry_update_args { }; /* __track_fn for directory entry updates. Called with ei->i_fc_lock. */ -static int __track_dentry_update(struct inode *inode, void *arg, bool update) +static int __track_dentry_update(handle_t *handle, struct inode *inode, + void *arg, bool update) { struct ext4_fc_dentry_update *node; struct ext4_inode_info *ei = EXT4_I(inode); @@ -435,14 +436,14 @@ static int __track_dentry_update(struct inode *inode, void *arg, bool update) if (IS_ENCRYPTED(dir)) { ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_ENCRYPTED_FILENAME, - NULL); + handle); mutex_lock(&ei->i_fc_lock); return -EOPNOTSUPP; } node = kmem_cache_alloc(ext4_fc_dentry_cachep, GFP_NOFS); if (!node) { - ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_NOMEM, NULL); + ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_NOMEM, handle); mutex_lock(&ei->i_fc_lock); return -ENOMEM; } @@ -454,7 +455,7 @@ static int __track_dentry_update(struct inode *inode, void *arg, bool update) node->fcd_name.name = kmalloc(dentry->d_name.len, GFP_NOFS); if (!node->fcd_name.name) { kmem_cache_free(ext4_fc_dentry_cachep, node); - ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_NOMEM, NULL); + ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_NOMEM, handle); mutex_lock(&ei->i_fc_lock); return -ENOMEM; } @@ -576,7 +577,8 @@ void ext4_fc_track_create(handle_t *handle, struct dentry *dentry) } /* __track_fn for inode tracking */ -static int __track_inode(struct inode *inode, void *arg, bool update) +static int __track_inode(handle_t *handle, struct inode *inode, void *arg, + bool update) { if (update) return -EEXIST; @@ -614,7 +616,8 @@ struct __track_range_args { }; /* __track_fn for tracking data updates */ -static int __track_range(struct inode *inode, void *arg, bool update) +static int __track_range(handle_t *handle, struct inode *inode, void *arg, + bool update) { struct ext4_inode_info *ei = EXT4_I(inode); ext4_lblk_t oldstart; diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index e04eb08b9060..a2704f064361 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -230,8 +230,8 @@ struct ext4_new_flex_group_data { #define MAX_RESIZE_BG 16384 /* - * alloc_flex_gd() allocates a ext4_new_flex_group_data with size of - * @flexbg_size. + * alloc_flex_gd() allocates an ext4_new_flex_group_data that satisfies the + * resizing from @o_group to @n_group, its size is typically @flexbg_size. * * Returns NULL on failure otherwise address of the allocated structure. */ @@ -239,25 +239,27 @@ static struct ext4_new_flex_group_data *alloc_flex_gd(unsigned int flexbg_size, ext4_group_t o_group, ext4_group_t n_group) { ext4_group_t last_group; + unsigned int max_resize_bg; struct ext4_new_flex_group_data *flex_gd; flex_gd = kmalloc(sizeof(*flex_gd), GFP_NOFS); if (flex_gd == NULL) goto out3; - if (unlikely(flexbg_size > MAX_RESIZE_BG)) - flex_gd->resize_bg = MAX_RESIZE_BG; - else - flex_gd->resize_bg = flexbg_size; + max_resize_bg = umin(flexbg_size, MAX_RESIZE_BG); + flex_gd->resize_bg = max_resize_bg; /* Avoid allocating large 'groups' array if not needed */ last_group = o_group | (flex_gd->resize_bg - 1); if (n_group <= last_group) - flex_gd->resize_bg = 1 << fls(n_group - o_group + 1); + flex_gd->resize_bg = 1 << fls(n_group - o_group); else if (n_group - last_group < flex_gd->resize_bg) - flex_gd->resize_bg = 1 << max(fls(last_group - o_group + 1), + flex_gd->resize_bg = 1 << max(fls(last_group - o_group), fls(n_group - last_group)); + if (WARN_ON_ONCE(flex_gd->resize_bg > max_resize_bg)) + flex_gd->resize_bg = max_resize_bg; + flex_gd->groups = kmalloc_array(flex_gd->resize_bg, sizeof(struct ext4_new_group_data), GFP_NOFS); diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index e0e1956dcdd3..7647e9f6e190 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -2559,6 +2559,8 @@ retry: error = ext4_xattr_set_handle(handle, inode, name_index, name, value, value_len, flags); + ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_XATTR, + handle); error2 = ext4_journal_stop(handle); if (error == -ENOSPC && ext4_should_retry_alloc(sb, &retries)) @@ -2566,7 +2568,6 @@ retry: if (error == 0) error = error2; } - ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_XATTR, NULL); return error; } diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c index 1136539a57a8..47a5c806cf16 100644 --- a/fs/f2fs/dir.c +++ b/fs/f2fs/dir.c @@ -5,7 +5,7 @@ * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/fs.h> #include <linux/f2fs_fs.h> #include <linux/sched/signal.h> diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c index 9756f0f2b7f7..e4d81b8705d1 100644 --- a/fs/f2fs/recovery.c +++ b/fs/f2fs/recovery.c @@ -5,7 +5,7 @@ * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/fs.h> #include <linux/f2fs_fs.h> #include <linux/sched/mm.h> diff --git a/fs/fat/inode.c b/fs/fat/inode.c index 75722bbd6b5f..3852bb66358c 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -19,7 +19,7 @@ #include <linux/uio.h> #include <linux/blkdev.h> #include <linux/backing-dev.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/random.h> #include <linux/iversion.h> #include "fat.h" diff --git a/fs/file.c b/fs/file.c index 5125607d040a..eb093e736972 100644 --- a/fs/file.c +++ b/fs/file.c @@ -272,59 +272,45 @@ static inline bool fd_is_open(unsigned int fd, const struct fdtable *fdt) return test_bit(fd, fdt->open_fds); } -static unsigned int count_open_files(struct fdtable *fdt) -{ - unsigned int size = fdt->max_fds; - unsigned int i; - - /* Find the last open fd */ - for (i = size / BITS_PER_LONG; i > 0; ) { - if (fdt->open_fds[--i]) - break; - } - i = (i + 1) * BITS_PER_LONG; - return i; -} - /* * Note that a sane fdtable size always has to be a multiple of * BITS_PER_LONG, since we have bitmaps that are sized by this. * - * 'max_fds' will normally already be properly aligned, but it - * turns out that in the close_range() -> __close_range() -> - * unshare_fd() -> dup_fd() -> sane_fdtable_size() we can end - * up having a 'max_fds' value that isn't already aligned. - * - * Rather than make close_range() have to worry about this, - * just make that BITS_PER_LONG alignment be part of a sane - * fdtable size. Becuase that's really what it is. + * punch_hole is optional - when close_range() is asked to unshare + * and close, we don't need to copy descriptors in that range, so + * a smaller cloned descriptor table might suffice if the last + * currently opened descriptor falls into that range. */ -static unsigned int sane_fdtable_size(struct fdtable *fdt, unsigned int max_fds) +static unsigned int sane_fdtable_size(struct fdtable *fdt, struct fd_range *punch_hole) { - unsigned int count; - - count = count_open_files(fdt); - if (max_fds < NR_OPEN_DEFAULT) - max_fds = NR_OPEN_DEFAULT; - return ALIGN(min(count, max_fds), BITS_PER_LONG); + unsigned int last = find_last_bit(fdt->open_fds, fdt->max_fds); + + if (last == fdt->max_fds) + return NR_OPEN_DEFAULT; + if (punch_hole && punch_hole->to >= last && punch_hole->from <= last) { + last = find_last_bit(fdt->open_fds, punch_hole->from); + if (last == punch_hole->from) + return NR_OPEN_DEFAULT; + } + return ALIGN(last + 1, BITS_PER_LONG); } /* - * Allocate a new files structure and copy contents from the - * passed in files structure. - * errorp will be valid only when the returned files_struct is NULL. + * Allocate a new descriptor table and copy contents from the passed in + * instance. Returns a pointer to cloned table on success, ERR_PTR() + * on failure. For 'punch_hole' see sane_fdtable_size(). */ -struct files_struct *dup_fd(struct files_struct *oldf, unsigned int max_fds, int *errorp) +struct files_struct *dup_fd(struct files_struct *oldf, struct fd_range *punch_hole) { struct files_struct *newf; struct file **old_fds, **new_fds; unsigned int open_files, i; struct fdtable *old_fdt, *new_fdt; + int error; - *errorp = -ENOMEM; newf = kmem_cache_alloc(files_cachep, GFP_KERNEL); if (!newf) - goto out; + return ERR_PTR(-ENOMEM); atomic_set(&newf->count, 1); @@ -341,7 +327,7 @@ struct files_struct *dup_fd(struct files_struct *oldf, unsigned int max_fds, int spin_lock(&oldf->file_lock); old_fdt = files_fdtable(oldf); - open_files = sane_fdtable_size(old_fdt, max_fds); + open_files = sane_fdtable_size(old_fdt, punch_hole); /* * Check whether we need to allocate a larger fd array and fd set. @@ -354,14 +340,14 @@ struct files_struct *dup_fd(struct files_struct *oldf, unsigned int max_fds, int new_fdt = alloc_fdtable(open_files - 1); if (!new_fdt) { - *errorp = -ENOMEM; + error = -ENOMEM; goto out_release; } /* beyond sysctl_nr_open; nothing to do */ if (unlikely(new_fdt->max_fds < open_files)) { __free_fdtable(new_fdt); - *errorp = -EMFILE; + error = -EMFILE; goto out_release; } @@ -372,7 +358,7 @@ struct files_struct *dup_fd(struct files_struct *oldf, unsigned int max_fds, int */ spin_lock(&oldf->file_lock); old_fdt = files_fdtable(oldf); - open_files = sane_fdtable_size(old_fdt, max_fds); + open_files = sane_fdtable_size(old_fdt, punch_hole); } copy_fd_bitmaps(new_fdt, old_fdt, open_files / BITS_PER_LONG); @@ -406,8 +392,7 @@ struct files_struct *dup_fd(struct files_struct *oldf, unsigned int max_fds, int out_release: kmem_cache_free(files_cachep, newf); -out: - return NULL; + return ERR_PTR(error); } static struct fdtable *close_files(struct files_struct * files) @@ -748,37 +733,25 @@ int __close_range(unsigned fd, unsigned max_fd, unsigned int flags) if (fd > max_fd) return -EINVAL; - if (flags & CLOSE_RANGE_UNSHARE) { - int ret; - unsigned int max_unshare_fds = NR_OPEN_MAX; + if ((flags & CLOSE_RANGE_UNSHARE) && atomic_read(&cur_fds->count) > 1) { + struct fd_range range = {fd, max_fd}, *punch_hole = ⦥ /* * If the caller requested all fds to be made cloexec we always * copy all of the file descriptors since they still want to * use them. */ - if (!(flags & CLOSE_RANGE_CLOEXEC)) { - /* - * If the requested range is greater than the current - * maximum, we're closing everything so only copy all - * file descriptors beneath the lowest file descriptor. - */ - rcu_read_lock(); - if (max_fd >= last_fd(files_fdtable(cur_fds))) - max_unshare_fds = fd; - rcu_read_unlock(); - } - - ret = unshare_fd(CLONE_FILES, max_unshare_fds, &fds); - if (ret) - return ret; + if (flags & CLOSE_RANGE_CLOEXEC) + punch_hole = NULL; + fds = dup_fd(cur_fds, punch_hole); + if (IS_ERR(fds)) + return PTR_ERR(fds); /* * We used to share our file descriptor table, and have now * created a private one, make sure we're using it below. */ - if (fds) - swap(cur_fds, fds); + swap(cur_fds, fds); } if (flags & CLOSE_RANGE_CLOEXEC) diff --git a/fs/hfsplus/wrapper.c b/fs/hfsplus/wrapper.c index ce9346099c72..9592ffcb44e5 100644 --- a/fs/hfsplus/wrapper.c +++ b/fs/hfsplus/wrapper.c @@ -12,7 +12,7 @@ #include <linux/fs.h> #include <linux/blkdev.h> #include <linux/cdrom.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "hfsplus_fs.h" #include "hfsplus_raw.h" diff --git a/fs/hpfs/hpfs_fn.h b/fs/hpfs/hpfs_fn.h index f5a2476c47bf..237c1c23e855 100644 --- a/fs/hpfs/hpfs_fn.h +++ b/fs/hpfs/hpfs_fn.h @@ -21,7 +21,7 @@ #include <linux/slab.h> #include <linux/sched/signal.h> #include <linux/blkdev.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "hpfs.h" diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 11ea747228ae..78ebd265f425 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -1321,7 +1321,7 @@ static loff_t iomap_unshare_iter(struct iomap_iter *iter) return length; /* - * Don't bother with holes or unwritten extents. + * Don't bother with delalloc reservations, holes or unwritten extents. * * Note that we use srcmap directly instead of iomap_iter_srcmap as * unsharing requires providing a separate source map, and the presence @@ -1330,6 +1330,7 @@ static loff_t iomap_unshare_iter(struct iomap_iter *iter) * fork for XFS. */ if (iter->srcmap.type == IOMAP_HOLE || + iter->srcmap.type == IOMAP_DELALLOC || iter->srcmap.type == IOMAP_UNWRITTEN) return length; @@ -1374,11 +1375,15 @@ iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len, struct iomap_iter iter = { .inode = inode, .pos = pos, - .len = len, .flags = IOMAP_WRITE | IOMAP_UNSHARE, }; + loff_t size = i_size_read(inode); int ret; + if (pos < 0 || pos >= size) + return 0; + + iter.len = min(len, size - pos); while ((ret = iomap_iter(&iter, ops)) > 0) iter.processed = iomap_unshare_iter(&iter); return ret; diff --git a/fs/isofs/isofs.h b/fs/isofs/isofs.h index dcdc191ed183..2d55207c9a99 100644 --- a/fs/isofs/isofs.h +++ b/fs/isofs/isofs.h @@ -3,7 +3,7 @@ #include <linux/buffer_head.h> #include <linux/exportfs.h> #include <linux/iso_fs.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> enum isofs_file_format { isofs_file_normal = 0, diff --git a/fs/lockd/mon.c b/fs/lockd/mon.c index 87a0f207df0b..b8fc732e1c67 100644 --- a/fs/lockd/mon.c +++ b/fs/lockd/mon.c @@ -18,7 +18,7 @@ #include <linux/sunrpc/svc.h> #include <linux/lockd/lockd.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "netns.h" diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h index c9f0ed24cb7b..c562aec3b483 100644 --- a/fs/netfs/internal.h +++ b/fs/netfs/internal.h @@ -58,6 +58,7 @@ static inline void netfs_proc_del_rreq(struct netfs_io_request *rreq) {} /* * misc.c */ +struct folio_queue *netfs_buffer_make_space(struct netfs_io_request *rreq); int netfs_buffer_append_folio(struct netfs_io_request *rreq, struct folio *folio, bool needs_put); struct folio_queue *netfs_delete_buffer_head(struct netfs_io_request *wreq); diff --git a/fs/netfs/misc.c b/fs/netfs/misc.c index 0ad0982ce0e2..78fe5796b2b2 100644 --- a/fs/netfs/misc.c +++ b/fs/netfs/misc.c @@ -9,34 +9,66 @@ #include "internal.h" /* - * Append a folio to the rolling queue. + * Make sure there's space in the rolling queue. */ -int netfs_buffer_append_folio(struct netfs_io_request *rreq, struct folio *folio, - bool needs_put) +struct folio_queue *netfs_buffer_make_space(struct netfs_io_request *rreq) { - struct folio_queue *tail = rreq->buffer_tail; - unsigned int slot, order = folio_order(folio); + struct folio_queue *tail = rreq->buffer_tail, *prev; + unsigned int prev_nr_slots = 0; if (WARN_ON_ONCE(!rreq->buffer && tail) || WARN_ON_ONCE(rreq->buffer && !tail)) - return -EIO; - - if (!tail || folioq_full(tail)) { - tail = kmalloc(sizeof(*tail), GFP_NOFS); - if (!tail) - return -ENOMEM; - netfs_stat(&netfs_n_folioq); - folioq_init(tail); - tail->prev = rreq->buffer_tail; - if (tail->prev) - tail->prev->next = tail; - rreq->buffer_tail = tail; - if (!rreq->buffer) { - rreq->buffer = tail; - iov_iter_folio_queue(&rreq->io_iter, ITER_SOURCE, tail, 0, 0, 0); + return ERR_PTR(-EIO); + + prev = tail; + if (prev) { + if (!folioq_full(tail)) + return tail; + prev_nr_slots = folioq_nr_slots(tail); + } + + tail = kmalloc(sizeof(*tail), GFP_NOFS); + if (!tail) + return ERR_PTR(-ENOMEM); + netfs_stat(&netfs_n_folioq); + folioq_init(tail); + tail->prev = prev; + if (prev) + /* [!] NOTE: After we set prev->next, the consumer is entirely + * at liberty to delete prev. + */ + WRITE_ONCE(prev->next, tail); + + rreq->buffer_tail = tail; + if (!rreq->buffer) { + rreq->buffer = tail; + iov_iter_folio_queue(&rreq->io_iter, ITER_SOURCE, tail, 0, 0, 0); + } else { + /* Make sure we don't leave the master iterator pointing to a + * block that might get immediately consumed. + */ + if (rreq->io_iter.folioq == prev && + rreq->io_iter.folioq_slot == prev_nr_slots) { + rreq->io_iter.folioq = tail; + rreq->io_iter.folioq_slot = 0; } - rreq->buffer_tail_slot = 0; } + rreq->buffer_tail_slot = 0; + return tail; +} + +/* + * Append a folio to the rolling queue. + */ +int netfs_buffer_append_folio(struct netfs_io_request *rreq, struct folio *folio, + bool needs_put) +{ + struct folio_queue *tail; + unsigned int slot, order = folio_order(folio); + + tail = netfs_buffer_make_space(rreq); + if (IS_ERR(tail)) + return PTR_ERR(tail); rreq->io_iter.count += PAGE_SIZE << order; @@ -70,7 +102,7 @@ void netfs_clear_buffer(struct netfs_io_request *rreq) while ((p = rreq->buffer)) { rreq->buffer = p->next; - for (int slot = 0; slot < folioq_nr_slots(p); slot++) { + for (int slot = 0; slot < folioq_count(p); slot++) { struct folio *folio = folioq_folio(p, slot); if (!folio) continue; diff --git a/fs/netfs/write_issue.c b/fs/netfs/write_issue.c index 04e66d587f77..bf6d507578e5 100644 --- a/fs/netfs/write_issue.c +++ b/fs/netfs/write_issue.c @@ -153,12 +153,22 @@ static void netfs_prepare_write(struct netfs_io_request *wreq, loff_t start) { struct netfs_io_subrequest *subreq; + struct iov_iter *wreq_iter = &wreq->io_iter; + + /* Make sure we don't point the iterator at a used-up folio_queue + * struct being used as a placeholder to prevent the queue from + * collapsing. In such a case, extend the queue. + */ + if (iov_iter_is_folioq(wreq_iter) && + wreq_iter->folioq_slot >= folioq_nr_slots(wreq_iter->folioq)) { + netfs_buffer_make_space(wreq); + } subreq = netfs_alloc_subrequest(wreq); subreq->source = stream->source; subreq->start = start; subreq->stream_nr = stream->stream_nr; - subreq->io_iter = wreq->io_iter; + subreq->io_iter = *wreq_iter; _enter("R=%x[%x]", wreq->debug_id, subreq->debug_index); @@ -307,6 +317,7 @@ static int netfs_write_folio(struct netfs_io_request *wreq, struct netfs_io_stream *stream; struct netfs_group *fgroup; /* TODO: Use this with ceph */ struct netfs_folio *finfo; + size_t iter_off = 0; size_t fsize = folio_size(folio), flen = fsize, foff = 0; loff_t fpos = folio_pos(folio), i_size; bool to_eof = false, streamw = false; @@ -462,7 +473,12 @@ static int netfs_write_folio(struct netfs_io_request *wreq, if (choose_s < 0) break; stream = &wreq->io_streams[choose_s]; - wreq->io_iter.iov_offset = stream->submit_off; + + /* Advance the iterator(s). */ + if (stream->submit_off > iter_off) { + iov_iter_advance(&wreq->io_iter, stream->submit_off - iter_off); + iter_off = stream->submit_off; + } atomic64_set(&wreq->issued_to, fpos + stream->submit_off); stream->submit_extendable_to = fsize - stream->submit_off; @@ -477,8 +493,8 @@ static int netfs_write_folio(struct netfs_io_request *wreq, debug = true; } - wreq->io_iter.iov_offset = 0; - iov_iter_advance(&wreq->io_iter, fsize); + if (fsize > iter_off) + iov_iter_advance(&wreq->io_iter, fsize - iter_off); atomic64_set(&wreq->issued_to, fpos + fsize); if (!debug) @@ -493,6 +509,30 @@ static int netfs_write_folio(struct netfs_io_request *wreq, } /* + * End the issuing of writes, letting the collector know we're done. + */ +static void netfs_end_issue_write(struct netfs_io_request *wreq) +{ + bool needs_poke = true; + + smp_wmb(); /* Write subreq lists before ALL_QUEUED. */ + set_bit(NETFS_RREQ_ALL_QUEUED, &wreq->flags); + + for (int s = 0; s < NR_IO_STREAMS; s++) { + struct netfs_io_stream *stream = &wreq->io_streams[s]; + + if (!stream->active) + continue; + if (!list_empty(&stream->subrequests)) + needs_poke = false; + netfs_issue_write(wreq, stream); + } + + if (needs_poke) + netfs_wake_write_collector(wreq, false); +} + +/* * Write some of the pending data back to the server */ int netfs_writepages(struct address_space *mapping, @@ -543,10 +583,7 @@ int netfs_writepages(struct address_space *mapping, break; } while ((folio = writeback_iter(mapping, wbc, folio, &error))); - for (int s = 0; s < NR_IO_STREAMS; s++) - netfs_issue_write(wreq, &wreq->io_streams[s]); - smp_wmb(); /* Write lists before ALL_QUEUED. */ - set_bit(NETFS_RREQ_ALL_QUEUED, &wreq->flags); + netfs_end_issue_write(wreq); mutex_unlock(&ictx->wb_lock); @@ -634,10 +671,7 @@ int netfs_end_writethrough(struct netfs_io_request *wreq, struct writeback_contr if (writethrough_cache) netfs_write_folio(wreq, wbc, writethrough_cache); - netfs_issue_write(wreq, &wreq->io_streams[0]); - netfs_issue_write(wreq, &wreq->io_streams[1]); - smp_wmb(); /* Write lists before ALL_QUEUED. */ - set_bit(NETFS_RREQ_ALL_QUEUED, &wreq->flags); + netfs_end_issue_write(wreq); mutex_unlock(&ictx->wb_lock); @@ -683,13 +717,7 @@ int netfs_unbuffered_write(struct netfs_io_request *wreq, bool may_wait, size_t break; } - netfs_issue_write(wreq, upload); - - smp_wmb(); /* Write lists before ALL_QUEUED. */ - set_bit(NETFS_RREQ_ALL_QUEUED, &wreq->flags); - if (list_empty(&upload->subrequests)) - netfs_wake_write_collector(wreq, false); - + netfs_end_issue_write(wreq); _leave(" = %d", error); return error; } diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c index 19bb88c7eebd..ea1ca374cdab 100644 --- a/fs/nfsd/filecache.c +++ b/fs/nfsd/filecache.c @@ -792,7 +792,7 @@ nfsd_file_cache_init(void) } nfsd_file_fsnotify_group = fsnotify_alloc_group(&nfsd_file_fsnotify_ops, - FSNOTIFY_GROUP_NOFS); + 0); if (IS_ERR(nfsd_file_fsnotify_group)) { pr_err("nfsd: unable to create fsnotify group: %ld\n", PTR_ERR(nfsd_file_fsnotify_group)); diff --git a/fs/nls/nls_ucs2_utils.c b/fs/nls/nls_ucs2_utils.c index d4564b79d7bf..b81c298e4966 100644 --- a/fs/nls/nls_ucs2_utils.c +++ b/fs/nls/nls_ucs2_utils.c @@ -13,7 +13,7 @@ #include <linux/fs.h> #include <linux/module.h> #include <linux/slab.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "nls_ucs2_utils.h" MODULE_DESCRIPTION("NLS UCS-2"); diff --git a/fs/notify/dnotify/dnotify.c b/fs/notify/dnotify/dnotify.c index 46440fbb8662..d5dbef7f5c95 100644 --- a/fs/notify/dnotify/dnotify.c +++ b/fs/notify/dnotify/dnotify.c @@ -406,8 +406,7 @@ static int __init dnotify_init(void) SLAB_PANIC|SLAB_ACCOUNT); dnotify_mark_cache = KMEM_CACHE(dnotify_mark, SLAB_PANIC|SLAB_ACCOUNT); - dnotify_group = fsnotify_alloc_group(&dnotify_fsnotify_ops, - FSNOTIFY_GROUP_NOFS); + dnotify_group = fsnotify_alloc_group(&dnotify_fsnotify_ops, 0); if (IS_ERR(dnotify_group)) panic("unable to allocate fsnotify group for dnotify\n"); dnotify_sysctl_init(); diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 13454e5fd3fb..9644bc72e457 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -1480,7 +1480,7 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) /* fsnotify_alloc_group takes a ref. Dropped in fanotify_release */ group = fsnotify_alloc_group(&fanotify_fsnotify_ops, - FSNOTIFY_GROUP_USER | FSNOTIFY_GROUP_NOFS); + FSNOTIFY_GROUP_USER); if (IS_ERR(group)) { return PTR_ERR(group); } diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c index 272c8a1dab3c..82ae8254c068 100644 --- a/fs/notify/fsnotify.c +++ b/fs/notify/fsnotify.c @@ -183,8 +183,10 @@ static bool fsnotify_event_needs_parent(struct inode *inode, __u32 mnt_mask, BUILD_BUG_ON(FS_EVENTS_POSS_ON_CHILD & ~FS_EVENTS_POSS_TO_PARENT); /* Did either inode/sb/mount subscribe for events with parent/name? */ - marks_mask |= fsnotify_parent_needed_mask(inode->i_fsnotify_mask); - marks_mask |= fsnotify_parent_needed_mask(inode->i_sb->s_fsnotify_mask); + marks_mask |= fsnotify_parent_needed_mask( + READ_ONCE(inode->i_fsnotify_mask)); + marks_mask |= fsnotify_parent_needed_mask( + READ_ONCE(inode->i_sb->s_fsnotify_mask)); marks_mask |= fsnotify_parent_needed_mask(mnt_mask); /* Did they subscribe for this event with parent/name info? */ @@ -195,8 +197,8 @@ static bool fsnotify_event_needs_parent(struct inode *inode, __u32 mnt_mask, static inline bool fsnotify_object_watched(struct inode *inode, __u32 mnt_mask, __u32 mask) { - __u32 marks_mask = inode->i_fsnotify_mask | mnt_mask | - inode->i_sb->s_fsnotify_mask; + __u32 marks_mask = READ_ONCE(inode->i_fsnotify_mask) | mnt_mask | + READ_ONCE(inode->i_sb->s_fsnotify_mask); return mask & marks_mask & ALL_FSNOTIFY_EVENTS; } @@ -213,7 +215,8 @@ int __fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data, int data_type) { const struct path *path = fsnotify_data_path(data, data_type); - __u32 mnt_mask = path ? real_mount(path->mnt)->mnt_fsnotify_mask : 0; + __u32 mnt_mask = path ? + READ_ONCE(real_mount(path->mnt)->mnt_fsnotify_mask) : 0; struct inode *inode = d_inode(dentry); struct dentry *parent; bool parent_watched = dentry->d_flags & DCACHE_FSNOTIFY_PARENT_WATCHED; @@ -557,13 +560,13 @@ int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir, (!inode2 || !inode2->i_fsnotify_marks)) return 0; - marks_mask = sb->s_fsnotify_mask; + marks_mask = READ_ONCE(sb->s_fsnotify_mask); if (mnt) - marks_mask |= mnt->mnt_fsnotify_mask; + marks_mask |= READ_ONCE(mnt->mnt_fsnotify_mask); if (inode) - marks_mask |= inode->i_fsnotify_mask; + marks_mask |= READ_ONCE(inode->i_fsnotify_mask); if (inode2) - marks_mask |= inode2->i_fsnotify_mask; + marks_mask |= READ_ONCE(inode2->i_fsnotify_mask); /* diff --git a/fs/notify/group.c b/fs/notify/group.c index 1de6631a3925..18446b7b0d49 100644 --- a/fs/notify/group.c +++ b/fs/notify/group.c @@ -115,7 +115,6 @@ static struct fsnotify_group *__fsnotify_alloc_group( const struct fsnotify_ops *ops, int flags, gfp_t gfp) { - static struct lock_class_key nofs_marks_lock; struct fsnotify_group *group; group = kzalloc(sizeof(struct fsnotify_group), gfp); @@ -136,16 +135,6 @@ static struct fsnotify_group *__fsnotify_alloc_group( group->ops = ops; group->flags = flags; - /* - * For most backends, eviction of inode with a mark is not expected, - * because marks hold a refcount on the inode against eviction. - * - * Use a different lockdep class for groups that support evictable - * inode marks, because with evictable marks, mark_mutex is NOT - * fs-reclaim safe - the mutex is taken when evicting inodes. - */ - if (flags & FSNOTIFY_GROUP_NOFS) - lockdep_set_class(&group->mark_mutex, &nofs_marks_lock); return group; } diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c index c7e451d5bd51..0794dcaf1e47 100644 --- a/fs/notify/inotify/inotify_user.c +++ b/fs/notify/inotify/inotify_user.c @@ -569,7 +569,7 @@ static int inotify_update_existing_watch(struct fsnotify_group *group, /* more bits in old than in new? */ int dropped = (old_mask & ~new_mask); /* more bits in this fsn_mark than the inode's mask? */ - int do_inode = (new_mask & ~inode->i_fsnotify_mask); + int do_inode = (new_mask & ~READ_ONCE(inode->i_fsnotify_mask)); /* update the inode with this new fsn_mark */ if (dropped || do_inode) diff --git a/fs/notify/mark.c b/fs/notify/mark.c index 5e170e713088..c45b222cf9c1 100644 --- a/fs/notify/mark.c +++ b/fs/notify/mark.c @@ -128,7 +128,7 @@ __u32 fsnotify_conn_mask(struct fsnotify_mark_connector *conn) if (WARN_ON(!fsnotify_valid_obj_type(conn->type))) return 0; - return *fsnotify_conn_mask_p(conn); + return READ_ONCE(*fsnotify_conn_mask_p(conn)); } static void fsnotify_get_sb_watched_objects(struct super_block *sb) @@ -245,7 +245,11 @@ static void *__fsnotify_recalc_mask(struct fsnotify_mark_connector *conn) !(mark->flags & FSNOTIFY_MARK_FLAG_NO_IREF)) want_iref = true; } - *fsnotify_conn_mask_p(conn) = new_mask; + /* + * We use WRITE_ONCE() to prevent silly compiler optimizations from + * confusing readers not holding conn->lock with partial updates. + */ + WRITE_ONCE(*fsnotify_conn_mask_p(conn), new_mask); return fsnotify_update_iref(conn, want_iref); } diff --git a/fs/ntfs3/lib/decompress_common.h b/fs/ntfs3/lib/decompress_common.h index dd7ced000d0e..f0cad9c4a289 100644 --- a/fs/ntfs3/lib/decompress_common.h +++ b/fs/ntfs3/lib/decompress_common.h @@ -12,7 +12,7 @@ #include <linux/compiler.h> #include <linux/types.h> #include <linux/slab.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /* "Force inline" macro (not required, but helpful for performance) */ diff --git a/fs/orangefs/orangefs-kernel.h b/fs/orangefs/orangefs-kernel.h index e2df7eeadc7a..3d4b883a7660 100644 --- a/fs/orangefs/orangefs-kernel.h +++ b/fs/orangefs/orangefs-kernel.h @@ -53,7 +53,7 @@ #include <linux/exportfs.h> #include <linux/hashtable.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "orangefs-dev-proto.h" diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c index 2b7a5a3a7a2f..4504493b20be 100644 --- a/fs/overlayfs/file.c +++ b/fs/overlayfs/file.c @@ -117,7 +117,7 @@ static int ovl_real_fdget_meta(const struct file *file, struct fd *real, struct file *f = ovl_open_realfile(file, &realpath); if (IS_ERR(f)) return PTR_ERR(f); - real->word = (unsigned long)ovl_open_realfile(file, &realpath) | FDPUT_FPUT; + real->word = (unsigned long)f | FDPUT_FPUT; return 0; } diff --git a/fs/pidfs.c b/fs/pidfs.c index 7ffdc88dfb52..80675b6bf884 100644 --- a/fs/pidfs.c +++ b/fs/pidfs.c @@ -120,6 +120,7 @@ static long pidfd_ioctl(struct file *file, unsigned int cmd, unsigned long arg) struct nsproxy *nsp __free(put_nsproxy) = NULL; struct pid *pid = pidfd_pid(file); struct ns_common *ns_common = NULL; + struct pid_namespace *pid_ns; if (arg) return -EINVAL; @@ -202,7 +203,9 @@ static long pidfd_ioctl(struct file *file, unsigned int cmd, unsigned long arg) case PIDFD_GET_PID_NAMESPACE: if (IS_ENABLED(CONFIG_PID_NS)) { rcu_read_lock(); - ns_common = to_ns_common( get_pid_ns(task_active_pid_ns(task))); + pid_ns = task_active_pid_ns(task); + if (pid_ns) + ns_common = to_ns_common(get_pid_ns(pid_ns)); rcu_read_unlock(); } break; diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index 72c53129c952..d39ee5f6c075 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -12,7 +12,7 @@ #include <linux/highmem.h> #include <linux/slab.h> #include <linux/uaccess.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/buffer_head.h> #include <linux/mpage.h> #include <linux/writeback.h> diff --git a/fs/reiserfs/reiserfs.h b/fs/reiserfs/reiserfs.h index f0e1f29f20ee..12fc20af8e17 100644 --- a/fs/reiserfs/reiserfs.h +++ b/fs/reiserfs/reiserfs.h @@ -11,7 +11,7 @@ #include <linux/sched.h> #include <linux/bug.h> #include <linux/workqueue.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/bitops.h> #include <linux/proc_fs.h> #include <linux/buffer_head.h> diff --git a/fs/smb/client/cifsacl.h b/fs/smb/client/cifsacl.h index 6529478b7f48..31b51a8fc256 100644 --- a/fs/smb/client/cifsacl.h +++ b/fs/smb/client/cifsacl.h @@ -55,7 +55,7 @@ struct smb3_sd { #define ACL_CONTROL_SI 0x0800 /* SACL Auto-Inherited */ #define ACL_CONTROL_DI 0x0400 /* DACL Auto-Inherited */ #define ACL_CONTROL_SC 0x0200 /* SACL computed through inheritance */ -#define ACL_CONTROL_DC 0x0100 /* DACL computed through inheritence */ +#define ACL_CONTROL_DC 0x0100 /* DACL computed through inheritance */ #define ACL_CONTROL_SS 0x0080 /* Create server ACL */ #define ACL_CONTROL_DT 0x0040 /* DACL provided by trusted source */ #define ACL_CONTROL_SD 0x0020 /* SACL defaulted */ diff --git a/fs/smb/client/cifsencrypt.c b/fs/smb/client/cifsencrypt.c index 7481b21a0489..7a43daacc815 100644 --- a/fs/smb/client/cifsencrypt.c +++ b/fs/smb/client/cifsencrypt.c @@ -239,7 +239,7 @@ int cifs_verify_signature(struct smb_rqst *rqst, cifs_dbg(FYI, "dummy signature received for smb command 0x%x\n", cifs_pdu->Command); - /* save off the origiginal signature so we can modify the smb and check + /* save off the original signature so we can modify the smb and check its signature against what the server sent */ memcpy(server_response_sig, cifs_pdu->Signature.SecuritySignature, 8); @@ -416,7 +416,7 @@ find_timestamp(struct cifs_ses *ses) } static int calc_ntlmv2_hash(struct cifs_ses *ses, char *ntlmv2_hash, - const struct nls_table *nls_cp) + const struct nls_table *nls_cp, struct shash_desc *hmacmd5) { int rc = 0; int len; @@ -425,34 +425,26 @@ static int calc_ntlmv2_hash(struct cifs_ses *ses, char *ntlmv2_hash, wchar_t *domain; wchar_t *server; - if (!ses->server->secmech.hmacmd5) { - cifs_dbg(VFS, "%s: can't generate ntlmv2 hash\n", __func__); - return -1; - } - /* calculate md4 hash of password */ E_md4hash(ses->password, nt_hash, nls_cp); - rc = crypto_shash_setkey(ses->server->secmech.hmacmd5->tfm, nt_hash, - CIFS_NTHASH_SIZE); + rc = crypto_shash_setkey(hmacmd5->tfm, nt_hash, CIFS_NTHASH_SIZE); if (rc) { - cifs_dbg(VFS, "%s: Could not set NT Hash as a key\n", __func__); + cifs_dbg(VFS, "%s: Could not set NT hash as a key, rc=%d\n", __func__, rc); return rc; } - rc = crypto_shash_init(ses->server->secmech.hmacmd5); + rc = crypto_shash_init(hmacmd5); if (rc) { - cifs_dbg(VFS, "%s: Could not init hmacmd5\n", __func__); + cifs_dbg(VFS, "%s: Could not init HMAC-MD5, rc=%d\n", __func__, rc); return rc; } /* convert ses->user_name to unicode */ len = ses->user_name ? strlen(ses->user_name) : 0; user = kmalloc(2 + (len * 2), GFP_KERNEL); - if (user == NULL) { - rc = -ENOMEM; - return rc; - } + if (user == NULL) + return -ENOMEM; if (len) { len = cifs_strtoUTF16(user, ses->user_name, len, nls_cp); @@ -461,11 +453,10 @@ static int calc_ntlmv2_hash(struct cifs_ses *ses, char *ntlmv2_hash, *(u16 *)user = 0; } - rc = crypto_shash_update(ses->server->secmech.hmacmd5, - (char *)user, 2 * len); + rc = crypto_shash_update(hmacmd5, (char *)user, 2 * len); kfree(user); if (rc) { - cifs_dbg(VFS, "%s: Could not update with user\n", __func__); + cifs_dbg(VFS, "%s: Could not update with user, rc=%d\n", __func__, rc); return rc; } @@ -474,19 +465,15 @@ static int calc_ntlmv2_hash(struct cifs_ses *ses, char *ntlmv2_hash, len = strlen(ses->domainName); domain = kmalloc(2 + (len * 2), GFP_KERNEL); - if (domain == NULL) { - rc = -ENOMEM; - return rc; - } + if (domain == NULL) + return -ENOMEM; + len = cifs_strtoUTF16((__le16 *)domain, ses->domainName, len, nls_cp); - rc = - crypto_shash_update(ses->server->secmech.hmacmd5, - (char *)domain, 2 * len); + rc = crypto_shash_update(hmacmd5, (char *)domain, 2 * len); kfree(domain); if (rc) { - cifs_dbg(VFS, "%s: Could not update with domain\n", - __func__); + cifs_dbg(VFS, "%s: Could not update with domain, rc=%d\n", __func__, rc); return rc; } } else { @@ -494,33 +481,27 @@ static int calc_ntlmv2_hash(struct cifs_ses *ses, char *ntlmv2_hash, len = strlen(ses->ip_addr); server = kmalloc(2 + (len * 2), GFP_KERNEL); - if (server == NULL) { - rc = -ENOMEM; - return rc; - } - len = cifs_strtoUTF16((__le16 *)server, ses->ip_addr, len, - nls_cp); - rc = - crypto_shash_update(ses->server->secmech.hmacmd5, - (char *)server, 2 * len); + if (server == NULL) + return -ENOMEM; + + len = cifs_strtoUTF16((__le16 *)server, ses->ip_addr, len, nls_cp); + rc = crypto_shash_update(hmacmd5, (char *)server, 2 * len); kfree(server); if (rc) { - cifs_dbg(VFS, "%s: Could not update with server\n", - __func__); + cifs_dbg(VFS, "%s: Could not update with server, rc=%d\n", __func__, rc); return rc; } } - rc = crypto_shash_final(ses->server->secmech.hmacmd5, - ntlmv2_hash); + rc = crypto_shash_final(hmacmd5, ntlmv2_hash); if (rc) - cifs_dbg(VFS, "%s: Could not generate md5 hash\n", __func__); + cifs_dbg(VFS, "%s: Could not generate MD5 hash, rc=%d\n", __func__, rc); return rc; } static int -CalcNTLMv2_response(const struct cifs_ses *ses, char *ntlmv2_hash) +CalcNTLMv2_response(const struct cifs_ses *ses, char *ntlmv2_hash, struct shash_desc *hmacmd5) { int rc; struct ntlmv2_resp *ntlmv2 = (struct ntlmv2_resp *) @@ -531,43 +512,33 @@ CalcNTLMv2_response(const struct cifs_ses *ses, char *ntlmv2_hash) hash_len = ses->auth_key.len - (CIFS_SESS_KEY_SIZE + offsetof(struct ntlmv2_resp, challenge.key[0])); - if (!ses->server->secmech.hmacmd5) { - cifs_dbg(VFS, "%s: can't generate ntlmv2 hash\n", __func__); - return -1; - } - - rc = crypto_shash_setkey(ses->server->secmech.hmacmd5->tfm, - ntlmv2_hash, CIFS_HMAC_MD5_HASH_SIZE); + rc = crypto_shash_setkey(hmacmd5->tfm, ntlmv2_hash, CIFS_HMAC_MD5_HASH_SIZE); if (rc) { - cifs_dbg(VFS, "%s: Could not set NTLMV2 Hash as a key\n", - __func__); + cifs_dbg(VFS, "%s: Could not set NTLMv2 hash as a key, rc=%d\n", __func__, rc); return rc; } - rc = crypto_shash_init(ses->server->secmech.hmacmd5); + rc = crypto_shash_init(hmacmd5); if (rc) { - cifs_dbg(VFS, "%s: Could not init hmacmd5\n", __func__); + cifs_dbg(VFS, "%s: Could not init HMAC-MD5, rc=%d\n", __func__, rc); return rc; } if (ses->server->negflavor == CIFS_NEGFLAVOR_EXTENDED) - memcpy(ntlmv2->challenge.key, - ses->ntlmssp->cryptkey, CIFS_SERVER_CHALLENGE_SIZE); + memcpy(ntlmv2->challenge.key, ses->ntlmssp->cryptkey, CIFS_SERVER_CHALLENGE_SIZE); else - memcpy(ntlmv2->challenge.key, - ses->server->cryptkey, CIFS_SERVER_CHALLENGE_SIZE); - rc = crypto_shash_update(ses->server->secmech.hmacmd5, - ntlmv2->challenge.key, hash_len); + memcpy(ntlmv2->challenge.key, ses->server->cryptkey, CIFS_SERVER_CHALLENGE_SIZE); + + rc = crypto_shash_update(hmacmd5, ntlmv2->challenge.key, hash_len); if (rc) { - cifs_dbg(VFS, "%s: Could not update with response\n", __func__); + cifs_dbg(VFS, "%s: Could not update with response, rc=%d\n", __func__, rc); return rc; } /* Note that the MD5 digest over writes anon.challenge_key.key */ - rc = crypto_shash_final(ses->server->secmech.hmacmd5, - ntlmv2->ntlmv2_hash); + rc = crypto_shash_final(hmacmd5, ntlmv2->ntlmv2_hash); if (rc) - cifs_dbg(VFS, "%s: Could not generate md5 hash\n", __func__); + cifs_dbg(VFS, "%s: Could not generate MD5 hash, rc=%d\n", __func__, rc); return rc; } @@ -575,6 +546,7 @@ CalcNTLMv2_response(const struct cifs_ses *ses, char *ntlmv2_hash) int setup_ntlmv2_rsp(struct cifs_ses *ses, const struct nls_table *nls_cp) { + struct shash_desc *hmacmd5 = NULL; int rc; int baselen; unsigned int tilen; @@ -640,55 +612,51 @@ setup_ntlmv2_rsp(struct cifs_ses *ses, const struct nls_table *nls_cp) cifs_server_lock(ses->server); - rc = cifs_alloc_hash("hmac(md5)", &ses->server->secmech.hmacmd5); + rc = cifs_alloc_hash("hmac(md5)", &hmacmd5); if (rc) { + cifs_dbg(VFS, "Could not allocate HMAC-MD5, rc=%d\n", rc); goto unlock; } /* calculate ntlmv2_hash */ - rc = calc_ntlmv2_hash(ses, ntlmv2_hash, nls_cp); + rc = calc_ntlmv2_hash(ses, ntlmv2_hash, nls_cp, hmacmd5); if (rc) { - cifs_dbg(VFS, "Could not get v2 hash rc %d\n", rc); + cifs_dbg(VFS, "Could not get NTLMv2 hash, rc=%d\n", rc); goto unlock; } /* calculate first part of the client response (CR1) */ - rc = CalcNTLMv2_response(ses, ntlmv2_hash); + rc = CalcNTLMv2_response(ses, ntlmv2_hash, hmacmd5); if (rc) { - cifs_dbg(VFS, "Could not calculate CR1 rc: %d\n", rc); + cifs_dbg(VFS, "Could not calculate CR1, rc=%d\n", rc); goto unlock; } /* now calculate the session key for NTLMv2 */ - rc = crypto_shash_setkey(ses->server->secmech.hmacmd5->tfm, - ntlmv2_hash, CIFS_HMAC_MD5_HASH_SIZE); + rc = crypto_shash_setkey(hmacmd5->tfm, ntlmv2_hash, CIFS_HMAC_MD5_HASH_SIZE); if (rc) { - cifs_dbg(VFS, "%s: Could not set NTLMV2 Hash as a key\n", - __func__); + cifs_dbg(VFS, "%s: Could not set NTLMv2 hash as a key, rc=%d\n", __func__, rc); goto unlock; } - rc = crypto_shash_init(ses->server->secmech.hmacmd5); + rc = crypto_shash_init(hmacmd5); if (rc) { - cifs_dbg(VFS, "%s: Could not init hmacmd5\n", __func__); + cifs_dbg(VFS, "%s: Could not init HMAC-MD5, rc=%d\n", __func__, rc); goto unlock; } - rc = crypto_shash_update(ses->server->secmech.hmacmd5, - ntlmv2->ntlmv2_hash, - CIFS_HMAC_MD5_HASH_SIZE); + rc = crypto_shash_update(hmacmd5, ntlmv2->ntlmv2_hash, CIFS_HMAC_MD5_HASH_SIZE); if (rc) { - cifs_dbg(VFS, "%s: Could not update with response\n", __func__); + cifs_dbg(VFS, "%s: Could not update with response, rc=%d\n", __func__, rc); goto unlock; } - rc = crypto_shash_final(ses->server->secmech.hmacmd5, - ses->auth_key.response); + rc = crypto_shash_final(hmacmd5, ses->auth_key.response); if (rc) - cifs_dbg(VFS, "%s: Could not generate md5 hash\n", __func__); - + cifs_dbg(VFS, "%s: Could not generate MD5 hash, rc=%d\n", __func__, rc); unlock: cifs_server_unlock(ses->server); + cifs_free_hash(&hmacmd5); setup_ntlmv2_rsp_ret: kfree_sensitive(tiblob); @@ -733,15 +701,19 @@ cifs_crypto_secmech_release(struct TCP_Server_Info *server) cifs_free_hash(&server->secmech.hmacsha256); cifs_free_hash(&server->secmech.md5); cifs_free_hash(&server->secmech.sha512); - cifs_free_hash(&server->secmech.hmacmd5); - if (server->secmech.enc) { - crypto_free_aead(server->secmech.enc); - server->secmech.enc = NULL; - } + if (!SERVER_IS_CHAN(server)) { + if (server->secmech.enc) { + crypto_free_aead(server->secmech.enc); + server->secmech.enc = NULL; + } - if (server->secmech.dec) { - crypto_free_aead(server->secmech.dec); + if (server->secmech.dec) { + crypto_free_aead(server->secmech.dec); + server->secmech.dec = NULL; + } + } else { + server->secmech.enc = NULL; server->secmech.dec = NULL; } } diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c index 2a2523c93944..000e1ef3beea 100644 --- a/fs/smb/client/cifsfs.c +++ b/fs/smb/client/cifsfs.c @@ -161,7 +161,7 @@ __u32 cifs_lock_secret; /* * Bumps refcount for cifs super block. - * Note that it should be only called if a referece to VFS super block is + * Note that it should be only called if a reference to VFS super block is * already held, e.g. in open-type syscalls context. Otherwise it can race with * atomic_dec_and_test in deactivate_locked_super. */ @@ -289,7 +289,7 @@ static void cifs_kill_sb(struct super_block *sb) struct cifs_sb_info *cifs_sb = CIFS_SB(sb); /* - * We ned to release all dentries for the cached directories + * We need to release all dentries for the cached directories * before we kill the sb. */ if (cifs_sb->root) { @@ -313,8 +313,17 @@ cifs_statfs(struct dentry *dentry, struct kstatfs *buf) struct TCP_Server_Info *server = tcon->ses->server; unsigned int xid; int rc = 0; + const char *full_path; + void *page; xid = get_xid(); + page = alloc_dentry_path(); + + full_path = build_path_from_dentry(dentry, page); + if (IS_ERR(full_path)) { + rc = PTR_ERR(full_path); + goto statfs_out; + } if (le32_to_cpu(tcon->fsAttrInfo.MaxPathNameComponentLength) > 0) buf->f_namelen = @@ -330,8 +339,10 @@ cifs_statfs(struct dentry *dentry, struct kstatfs *buf) buf->f_ffree = 0; /* unlimited */ if (server->ops->queryfs) - rc = server->ops->queryfs(xid, tcon, cifs_sb, buf); + rc = server->ops->queryfs(xid, tcon, full_path, cifs_sb, buf); +statfs_out: + free_dentry_path(page); free_xid(xid); return rc; } diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h index 15571cf0ba63..5041b1ffc244 100644 --- a/fs/smb/client/cifsglob.h +++ b/fs/smb/client/cifsglob.h @@ -178,7 +178,6 @@ struct session_key { /* crypto hashing related structure/fields, not specific to a sec mech */ struct cifs_secmech { - struct shash_desc *hmacmd5; /* hmacmd5 hash function, for NTLMv2/CR1 hashes */ struct shash_desc *md5; /* md5 hash function, for CIFS/SMB1 signatures */ struct shash_desc *hmacsha256; /* hmac-sha256 hash function, for SMB2 signatures */ struct shash_desc *sha512; /* sha512 hash function, for SMB3.1.1 preauth hash */ @@ -482,7 +481,7 @@ struct smb_version_operations { __u16 net_fid, struct cifsInodeInfo *cifs_inode); /* query remote filesystem */ int (*queryfs)(const unsigned int, struct cifs_tcon *, - struct cifs_sb_info *, struct kstatfs *); + const char *, struct cifs_sb_info *, struct kstatfs *); /* send mandatory brlock to the server */ int (*mand_lock)(const unsigned int, struct cifsFileInfo *, __u64, __u64, __u32, int, int, bool); @@ -776,7 +775,7 @@ struct TCP_Server_Info { } compression; __u16 signing_algorithm; __le16 cipher_type; - /* save initital negprot hash */ + /* save initial negprot hash */ __u8 preauth_sha_hash[SMB2_PREAUTH_HASH_SIZE]; bool signing_negotiated; /* true if valid signing context rcvd from server */ bool posix_ext_supported; diff --git a/fs/smb/client/cifspdu.h b/fs/smb/client/cifspdu.h index c3b6263060b0..ee78bb6741d6 100644 --- a/fs/smb/client/cifspdu.h +++ b/fs/smb/client/cifspdu.h @@ -10,7 +10,7 @@ #define _CIFSPDU_H #include <net/sock.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "../common/smbfsctl.h" #define CIFS_PROT 0 @@ -781,7 +781,7 @@ typedef struct smb_com_logoff_andx_rsp { __u16 ByteCount; } __attribute__((packed)) LOGOFF_ANDX_RSP; -typedef union smb_com_tree_disconnect { /* as an altetnative can use flag on +typedef union smb_com_tree_disconnect { /* as an alternative can use flag on tree_connect PDU to effect disconnect */ /* tdis is probably simplest SMB PDU */ struct { @@ -2406,7 +2406,7 @@ struct cifs_posix_ace { /* access control entry (ACE) */ __le64 cifs_uid; /* or gid */ } __attribute__((packed)); -struct cifs_posix_acl { /* access conrol list (ACL) */ +struct cifs_posix_acl { /* access control list (ACL) */ __le16 version; __le16 access_entry_count; /* access ACL - count of entries */ __le16 default_entry_count; /* default ACL - count of entries */ diff --git a/fs/smb/client/cifssmb.c b/fs/smb/client/cifssmb.c index 131f20b91c3e..c6f15dbe860a 100644 --- a/fs/smb/client/cifssmb.c +++ b/fs/smb/client/cifssmb.c @@ -1215,7 +1215,7 @@ openRetry: req->CreateDisposition = cpu_to_le32(disposition); req->CreateOptions = cpu_to_le32(create_options & CREATE_OPTIONS_MASK); - /* BB Expirement with various impersonation levels and verify */ + /* BB Experiment with various impersonation levels and verify */ req->ImpersonationLevel = cpu_to_le32(SECURITY_IMPERSONATION); req->SecurityFlags = SECURITY_CONTEXT_TRACKING|SECURITY_EFFECTIVE_ONLY; @@ -3018,7 +3018,7 @@ static void cifs_init_ace(struct cifs_posix_ace *cifs_ace, /** * posix_acl_to_cifs - convert ACLs from POSIX ACL to cifs format - * @parm_data: ACLs in cifs format to conver to + * @parm_data: ACLs in cifs format to convert to * @acl: ACLs in POSIX ACL format to convert from * @acl_type: the type of POSIX ACLs stored in @acl * @@ -3995,7 +3995,7 @@ findFirstRetry: name_len = cifsConvertToUTF16((__le16 *) pSMB->FileName, searchName, PATH_MAX, nls_codepage, remap); - /* We can not add the asterik earlier in case + /* We can not add the asterisk earlier in case it got remapped to 0xF03A as if it were part of the directory name instead of a wildcard */ name_len *= 2; diff --git a/fs/smb/client/compress/lz77.c b/fs/smb/client/compress/lz77.c index 553e253ada29..96e8a8057a77 100644 --- a/fs/smb/client/compress/lz77.c +++ b/fs/smb/client/compress/lz77.c @@ -9,7 +9,7 @@ #include <linux/slab.h> #include <linux/sizes.h> #include <linux/count_zeros.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "lz77.h" diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index 78b59c4ef3ce..a58a3333ecc3 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -2502,7 +2502,7 @@ refind_writable: } } } - /* couldn't find useable FH with same pid, try any available */ + /* couldn't find usable FH with same pid, try any available */ if (!any_available) { any_available = true; goto refind_writable; diff --git a/fs/smb/client/fs_context.h b/fs/smb/client/fs_context.h index 69f9d938b336..890d6d9d4a59 100644 --- a/fs/smb/client/fs_context.h +++ b/fs/smb/client/fs_context.h @@ -260,7 +260,7 @@ struct smb3_fs_context { unsigned int min_offload; unsigned int retrans; bool sockopt_tcp_nodelay:1; - /* attribute cache timemout for files and directories in jiffies */ + /* attribute cache timeout for files and directories in jiffies */ unsigned long acregmax; unsigned long acdirmax; /* timeout for deferred close of files in jiffies */ diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c index 647f9bedd9fc..eff3f57235ee 100644 --- a/fs/smb/client/inode.c +++ b/fs/smb/client/inode.c @@ -629,10 +629,16 @@ cifs_sfu_type(struct cifs_fattr *fattr, const char *path, &symlink_len_utf16, &symlink_buf_utf16, &buf_type); + /* + * Check that read buffer has valid length and does not + * contain UTF-16 null codepoint (via UniStrnlen() call) + * because Linux cannot process symlink with null byte. + */ if ((rc == 0) && (symlink_len_utf16 > 0) && (symlink_len_utf16 < fattr->cf_eof-8 + 1) && - (symlink_len_utf16 % 2 == 0)) { + (symlink_len_utf16 % 2 == 0) && + (UniStrnlen((wchar_t *)symlink_buf_utf16, symlink_len_utf16/2) == symlink_len_utf16/2)) { fattr->cf_symlink_target = cifs_strndup_from_utf16(symlink_buf_utf16, symlink_len_utf16, diff --git a/fs/smb/client/misc.c b/fs/smb/client/misc.c index 054f10ebf65a..4373dd64b66d 100644 --- a/fs/smb/client/misc.c +++ b/fs/smb/client/misc.c @@ -254,7 +254,7 @@ free_rsp_buf(int resp_buftype, void *rsp) } /* NB: MID can not be set if treeCon not passed in, in that - case it is responsbility of caller to set the mid */ + case it is responsibility of caller to set the mid */ void header_assemble(struct smb_hdr *buffer, char smb_command /* command */ , const struct cifs_tcon *treeCon, int word_count diff --git a/fs/smb/client/netmisc.c b/fs/smb/client/netmisc.c index 1b52e6ac431c..2a8d71221e5e 100644 --- a/fs/smb/client/netmisc.c +++ b/fs/smb/client/netmisc.c @@ -1003,7 +1003,7 @@ struct timespec64 cnvrtDosUnixTm(__le16 le_date, __le16 le_time, int offset) year is 2**7, the last year is 1980+127, which means we need only consider 2 special case years, ie the years 2000 and 2100, and only adjust for the lack of leap year for the year 2100, as 2000 was a - leap year (divisable by 400) */ + leap year (divisible by 400) */ if (year >= 120) /* the year 2100 */ days = days - 1; /* do not count leap year for the year 2100 */ diff --git a/fs/smb/client/readdir.c b/fs/smb/client/readdir.c index ebe1cb30e18e..b3a8f9c6fcff 100644 --- a/fs/smb/client/readdir.c +++ b/fs/smb/client/readdir.c @@ -553,7 +553,7 @@ static void cifs_fill_dirent_std(struct cifs_dirent *de, const FIND_FILE_STANDARD_INFO *info) { de->name = &info->FileName[0]; - /* one byte length, no endianess conversion */ + /* one byte length, no endianness conversion */ de->namelen = info->FileNameLength; de->resume_key = info->ResumeKey; } @@ -815,7 +815,7 @@ static bool emit_cached_dirents(struct cached_dirents *cde, * However, this sequence of ->pos values may have holes * in it, for example dot-dirs returned from the server * are suppressed. - * Handle this bu forcing ctx->pos to be the same as the + * Handle this by forcing ctx->pos to be the same as the * ->pos of the current dirent we emit from the cache. * This means that when we emit these entries from the cache * we now emit them with the same ->pos value as in the diff --git a/fs/smb/client/reparse.c b/fs/smb/client/reparse.c index 3b48a093cfb1..c848b5e88d32 100644 --- a/fs/smb/client/reparse.c +++ b/fs/smb/client/reparse.c @@ -320,22 +320,51 @@ static int parse_reparse_posix(struct reparse_posix_data *buf, unsigned int len; u64 type; + len = le16_to_cpu(buf->ReparseDataLength); + if (len < sizeof(buf->InodeType)) { + cifs_dbg(VFS, "srv returned malformed nfs buffer\n"); + return -EIO; + } + + len -= sizeof(buf->InodeType); + switch ((type = le64_to_cpu(buf->InodeType))) { case NFS_SPECFILE_LNK: - len = le16_to_cpu(buf->ReparseDataLength); + if (len == 0 || (len % 2)) { + cifs_dbg(VFS, "srv returned malformed nfs symlink buffer\n"); + return -EIO; + } + /* + * Check that buffer does not contain UTF-16 null codepoint + * because Linux cannot process symlink with null byte. + */ + if (UniStrnlen((wchar_t *)buf->DataBuffer, len/2) != len/2) { + cifs_dbg(VFS, "srv returned null byte in nfs symlink target location\n"); + return -EIO; + } data->symlink_target = cifs_strndup_from_utf16(buf->DataBuffer, len, true, cifs_sb->local_nls); if (!data->symlink_target) return -ENOMEM; - convert_delimiter(data->symlink_target, '/'); cifs_dbg(FYI, "%s: target path: %s\n", __func__, data->symlink_target); break; case NFS_SPECFILE_CHR: case NFS_SPECFILE_BLK: + /* DataBuffer for block and char devices contains two 32-bit numbers */ + if (len != 8) { + cifs_dbg(VFS, "srv returned malformed nfs buffer for type: 0x%llx\n", type); + return -EIO; + } + break; case NFS_SPECFILE_FIFO: case NFS_SPECFILE_SOCK: + /* DataBuffer for fifos and sockets is empty */ + if (len != 0) { + cifs_dbg(VFS, "srv returned malformed nfs buffer for type: 0x%llx\n", type); + return -EIO; + } break; default: cifs_dbg(VFS, "%s: unhandled inode type: 0x%llx\n", @@ -482,12 +511,18 @@ bool cifs_reparse_point_to_fattr(struct cifs_sb_info *cifs_sb, u32 tag = data->reparse.tag; if (tag == IO_REPARSE_TAG_NFS && buf) { + if (le16_to_cpu(buf->ReparseDataLength) < sizeof(buf->InodeType)) + return false; switch (le64_to_cpu(buf->InodeType)) { case NFS_SPECFILE_CHR: + if (le16_to_cpu(buf->ReparseDataLength) != sizeof(buf->InodeType) + 8) + return false; fattr->cf_mode |= S_IFCHR; fattr->cf_rdev = reparse_mkdev(buf->DataBuffer); break; case NFS_SPECFILE_BLK: + if (le16_to_cpu(buf->ReparseDataLength) != sizeof(buf->InodeType) + 8) + return false; fattr->cf_mode |= S_IFBLK; fattr->cf_rdev = reparse_mkdev(buf->DataBuffer); break; diff --git a/fs/smb/client/smb1ops.c b/fs/smb/client/smb1ops.c index e03c91a49650..9a6ece66c4d3 100644 --- a/fs/smb/client/smb1ops.c +++ b/fs/smb/client/smb1ops.c @@ -909,7 +909,7 @@ cifs_oplock_response(struct cifs_tcon *tcon, __u64 persistent_fid, static int cifs_queryfs(const unsigned int xid, struct cifs_tcon *tcon, - struct cifs_sb_info *cifs_sb, struct kstatfs *buf) + const char *path, struct cifs_sb_info *cifs_sb, struct kstatfs *buf) { int rc = -EOPNOTSUPP; diff --git a/fs/smb/client/smb2inode.c b/fs/smb/client/smb2inode.c index b992117377e9..4e9e225520a6 100644 --- a/fs/smb/client/smb2inode.c +++ b/fs/smb/client/smb2inode.c @@ -1205,9 +1205,12 @@ struct inode *smb2_get_reparse_inode(struct cifs_open_info_data *data, struct cifs_sb_info *cifs_sb = CIFS_SB(sb); struct cifsFileInfo *cfile; struct inode *new = NULL; + int out_buftype[4] = {}; + struct kvec out_iov[4] = {}; struct kvec in_iov[2]; int cmds[2]; int rc; + int i; oparms = CIFS_OPARMS(cifs_sb, tcon, full_path, SYNCHRONIZE | DELETE | @@ -1228,7 +1231,7 @@ struct inode *smb2_get_reparse_inode(struct cifs_open_info_data *data, cmds[1] = SMB2_OP_POSIX_QUERY_INFO; cifs_get_writable_path(tcon, full_path, FIND_WR_ANY, &cfile); rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, &oparms, - in_iov, cmds, 2, cfile, NULL, NULL, NULL); + in_iov, cmds, 2, cfile, out_iov, out_buftype, NULL); if (!rc) { rc = smb311_posix_get_inode_info(&new, full_path, data, sb, xid); @@ -1237,12 +1240,29 @@ struct inode *smb2_get_reparse_inode(struct cifs_open_info_data *data, cmds[1] = SMB2_OP_QUERY_INFO; cifs_get_writable_path(tcon, full_path, FIND_WR_ANY, &cfile); rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, &oparms, - in_iov, cmds, 2, cfile, NULL, NULL, NULL); + in_iov, cmds, 2, cfile, out_iov, out_buftype, NULL); if (!rc) { rc = cifs_get_inode_info(&new, full_path, data, sb, xid, NULL); } } + + + /* + * If CREATE was successful but SMB2_OP_SET_REPARSE failed then + * remove the intermediate object created by CREATE. Otherwise + * empty object stay on the server when reparse call failed. + */ + if (rc && + out_iov[0].iov_base != NULL && out_buftype[0] != CIFS_NO_BUFFER && + ((struct smb2_hdr *)out_iov[0].iov_base)->Status == STATUS_SUCCESS && + (out_iov[1].iov_base == NULL || out_buftype[1] == CIFS_NO_BUFFER || + ((struct smb2_hdr *)out_iov[1].iov_base)->Status != STATUS_SUCCESS)) + smb2_unlink(xid, tcon, full_path, cifs_sb, NULL); + + for (i = 0; i < ARRAY_SIZE(out_buftype); i++) + free_rsp_buf(out_buftype[i], out_iov[i].iov_base); + return rc ? ERR_PTR(rc) : new; } diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index 1ee2dd4a1cae..6b385fce3f2a 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -2177,7 +2177,7 @@ smb3_enum_snapshots(const unsigned int xid, struct cifs_tcon *tcon, NULL, 0 /* no input data */, max_response_size, (char **)&retbuf, &ret_data_len); - cifs_dbg(FYI, "enum snaphots ioctl returned %d and ret buflen is %d\n", + cifs_dbg(FYI, "enum snapshots ioctl returned %d and ret buflen is %d\n", rc, ret_data_len); if (rc) return rc; @@ -2838,7 +2838,7 @@ out_free_path: static int smb2_queryfs(const unsigned int xid, struct cifs_tcon *tcon, - struct cifs_sb_info *cifs_sb, struct kstatfs *buf) + const char *path, struct cifs_sb_info *cifs_sb, struct kstatfs *buf) { struct smb2_query_info_rsp *rsp; struct smb2_fs_full_size_info *info = NULL; @@ -2847,7 +2847,7 @@ smb2_queryfs(const unsigned int xid, struct cifs_tcon *tcon, int rc; - rc = smb2_query_info_compound(xid, tcon, "", + rc = smb2_query_info_compound(xid, tcon, path, FILE_READ_ATTRIBUTES, FS_FULL_SIZE_INFORMATION, SMB2_O_INFO_FILESYSTEM, @@ -2875,28 +2875,33 @@ qfs_exit: static int smb311_queryfs(const unsigned int xid, struct cifs_tcon *tcon, - struct cifs_sb_info *cifs_sb, struct kstatfs *buf) + const char *path, struct cifs_sb_info *cifs_sb, struct kstatfs *buf) { int rc; - __le16 srch_path = 0; /* Null - open root of share */ + __le16 *utf16_path = NULL; u8 oplock = SMB2_OPLOCK_LEVEL_NONE; struct cifs_open_parms oparms; struct cifs_fid fid; if (!tcon->posix_extensions) - return smb2_queryfs(xid, tcon, cifs_sb, buf); + return smb2_queryfs(xid, tcon, path, cifs_sb, buf); oparms = (struct cifs_open_parms) { .tcon = tcon, - .path = "", + .path = path, .desired_access = FILE_READ_ATTRIBUTES, .disposition = FILE_OPEN, .create_options = cifs_create_options(cifs_sb, 0), .fid = &fid, }; - rc = SMB2_open(xid, &oparms, &srch_path, &oplock, NULL, NULL, + utf16_path = cifs_convert_path_to_utf16(path, cifs_sb); + if (utf16_path == NULL) + return -ENOMEM; + + rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, NULL, NULL, NULL); + kfree(utf16_path); if (rc) return rc; @@ -3583,7 +3588,7 @@ static long smb3_simple_falloc(struct file *file, struct cifs_tcon *tcon, /* * At this point, we are trying to fallocate an internal * regions of a sparse file. Since smb2 does not have a - * fallocate command we have two otions on how to emulate this. + * fallocate command we have two options on how to emulate this. * We can either turn the entire file to become non-sparse * which we only do if the fallocate is for virtually * the whole file, or we can overwrite the region with zeroes @@ -4309,7 +4314,7 @@ smb2_get_enc_key(struct TCP_Server_Info *server, __u64 ses_id, int enc, u8 *key) */ static int crypt_message(struct TCP_Server_Info *server, int num_rqst, - struct smb_rqst *rqst, int enc) + struct smb_rqst *rqst, int enc, struct crypto_aead *tfm) { struct smb2_transform_hdr *tr_hdr = (struct smb2_transform_hdr *)rqst[0].rq_iov[0].iov_base; @@ -4320,8 +4325,6 @@ crypt_message(struct TCP_Server_Info *server, int num_rqst, u8 key[SMB3_ENC_DEC_KEY_SIZE]; struct aead_request *req; u8 *iv; - DECLARE_CRYPTO_WAIT(wait); - struct crypto_aead *tfm; unsigned int crypt_len = le32_to_cpu(tr_hdr->OriginalMessageSize); void *creq; size_t sensitive_size; @@ -4333,14 +4336,6 @@ crypt_message(struct TCP_Server_Info *server, int num_rqst, return rc; } - rc = smb3_crypto_aead_allocate(server); - if (rc) { - cifs_server_dbg(VFS, "%s: crypto alloc failed\n", __func__); - return rc; - } - - tfm = enc ? server->secmech.enc : server->secmech.dec; - if ((server->cipher_type == SMB2_ENCRYPTION_AES256_CCM) || (server->cipher_type == SMB2_ENCRYPTION_AES256_GCM)) rc = crypto_aead_setkey(tfm, key, SMB3_GCM256_CRYPTKEY_SIZE); @@ -4380,11 +4375,7 @@ crypt_message(struct TCP_Server_Info *server, int num_rqst, aead_request_set_crypt(req, sg, sg, crypt_len, iv); aead_request_set_ad(req, assoc_data_len); - aead_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG, - crypto_req_done, &wait); - - rc = crypto_wait_req(enc ? crypto_aead_encrypt(req) - : crypto_aead_decrypt(req), &wait); + rc = enc ? crypto_aead_encrypt(req) : crypto_aead_decrypt(req); if (!rc && enc) memcpy(&tr_hdr->Signature, sign, SMB2_SIGNATURE_SIZE); @@ -4526,7 +4517,7 @@ smb3_init_transform_rq(struct TCP_Server_Info *server, int num_rqst, /* fill the 1st iov with a transform header */ fill_transform_hdr(tr_hdr, orig_len, old_rq, server->cipher_type); - rc = crypt_message(server, num_rqst, new_rq, 1); + rc = crypt_message(server, num_rqst, new_rq, 1, server->secmech.enc); cifs_dbg(FYI, "Encrypt message returned %d\n", rc); if (rc) goto err_free; @@ -4551,8 +4542,9 @@ decrypt_raw_data(struct TCP_Server_Info *server, char *buf, unsigned int buf_data_size, struct iov_iter *iter, bool is_offloaded) { - struct kvec iov[2]; + struct crypto_aead *tfm; struct smb_rqst rqst = {NULL}; + struct kvec iov[2]; size_t iter_size = 0; int rc; @@ -4568,9 +4560,31 @@ decrypt_raw_data(struct TCP_Server_Info *server, char *buf, iter_size = iov_iter_count(iter); } - rc = crypt_message(server, 1, &rqst, 0); + if (is_offloaded) { + if ((server->cipher_type == SMB2_ENCRYPTION_AES128_GCM) || + (server->cipher_type == SMB2_ENCRYPTION_AES256_GCM)) + tfm = crypto_alloc_aead("gcm(aes)", 0, 0); + else + tfm = crypto_alloc_aead("ccm(aes)", 0, 0); + if (IS_ERR(tfm)) { + rc = PTR_ERR(tfm); + cifs_server_dbg(VFS, "%s: Failed alloc decrypt TFM, rc=%d\n", __func__, rc); + + return rc; + } + } else { + if (unlikely(!server->secmech.dec)) + return -EIO; + + tfm = server->secmech.dec; + } + + rc = crypt_message(server, 1, &rqst, 0, tfm); cifs_dbg(FYI, "Decrypt message returned %d\n", rc); + if (is_offloaded) + crypto_free_aead(tfm); + if (rc) return rc; diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index bb225758448a..b2f16a7b696d 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -1266,6 +1266,16 @@ SMB2_negotiate(const unsigned int xid, else cifs_server_dbg(VFS, "Missing expected negotiate contexts\n"); } + + if (server->cipher_type && !rc) { + if (!SERVER_IS_CHAN(server)) { + rc = smb3_crypto_aead_allocate(server); + } else { + /* For channels, just reuse the primary server crypto secmech. */ + server->secmech.enc = server->primary_server->secmech.enc; + server->secmech.dec = server->primary_server->secmech.dec; + } + } neg_exit: free_rsp_buf(resp_buftype, rsp); return rc; @@ -2976,7 +2986,7 @@ replay_again: SMB2_close(xid, tcon, rsp->PersistentFileId, rsp->VolatileFileId); - /* Eventually save off posix specific response info and timestaps */ + /* Eventually save off posix specific response info and timestamps */ err_free_rsp_buf: free_rsp_buf(resp_buftype, rsp); @@ -4571,7 +4581,7 @@ smb2_readv_callback(struct mid_q_entry *mid) } #ifdef CONFIG_CIFS_SMB_DIRECT /* - * If this rdata has a memmory registered, the MR can be freed + * If this rdata has a memory registered, the MR can be freed * MR needs to be freed as soon as I/O finishes to prevent deadlock * because they have limited number and are used for future I/Os */ diff --git a/fs/smb/client/smb2transport.c b/fs/smb/client/smb2transport.c index e4636fca821d..b486b14bb330 100644 --- a/fs/smb/client/smb2transport.c +++ b/fs/smb/client/smb2transport.c @@ -242,7 +242,7 @@ smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server, ses = smb2_find_smb_ses(server, le64_to_cpu(shdr->SessionId)); if (unlikely(!ses)) { - cifs_server_dbg(VFS, "%s: Could not find session\n", __func__); + cifs_server_dbg(FYI, "%s: Could not find session\n", __func__); return -ENOENT; } @@ -696,7 +696,7 @@ smb2_verify_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server) shdr->Command); /* - * Save off the origiginal signature so we can modify the smb and check + * Save off the original signature so we can modify the smb and check * our calculated signature against what the server sent. */ memcpy(server_response_sig, shdr->Signature, SMB2_SIGNATURE_SIZE); diff --git a/fs/smb/client/smbdirect.c b/fs/smb/client/smbdirect.c index 0c64b37e2660..b0b7254661e9 100644 --- a/fs/smb/client/smbdirect.c +++ b/fs/smb/client/smbdirect.c @@ -219,7 +219,7 @@ static int smbd_conn_upcall( case RDMA_CM_EVENT_DEVICE_REMOVAL: case RDMA_CM_EVENT_DISCONNECTED: - /* This happenes when we fail the negotiation */ + /* This happens when we fail the negotiation */ if (info->transport_status == SMBD_NEGOTIATE_FAILED) { info->transport_status = SMBD_DISCONNECTED; wake_up(&info->conn_wait); @@ -1344,7 +1344,7 @@ void smbd_destroy(struct TCP_Server_Info *server) * are not locked by srv_mutex. It is possible some processes are * blocked on transport srv_mutex while holding memory registration. * Release the transport srv_mutex to allow them to hit the failure - * path when sending data, and then release memory registartions. + * path when sending data, and then release memory registrations. */ log_rdma_event(INFO, "freeing mr list\n"); wake_up_interruptible_all(&info->wait_mr); diff --git a/fs/smb/client/smbdirect.h b/fs/smb/client/smbdirect.h index 83f239f376f0..c08e3665150d 100644 --- a/fs/smb/client/smbdirect.h +++ b/fs/smb/client/smbdirect.h @@ -111,7 +111,7 @@ struct smbd_connection { /* Used by transport to wait until all MRs are returned */ wait_queue_head_t wait_for_mr_cleanup; - /* Activity accoutning */ + /* Activity accounting */ atomic_t send_pending; wait_queue_head_t wait_send_pending; wait_queue_head_t wait_post_send; diff --git a/fs/smb/common/smb2pdu.h b/fs/smb/common/smb2pdu.h index c769f9dbc0b4..9f272cc8f566 100644 --- a/fs/smb/common/smb2pdu.h +++ b/fs/smb/common/smb2pdu.h @@ -6,7 +6,7 @@ * Note that, due to trying to use names similar to the protocol specifications, * there are many mixed case field names in the structures below. Although * this does not match typical Linux kernel style, it is necessary to be - * able to match against the protocol specfication. + * able to match against the protocol specification. * * SMB2 commands * Some commands have minimal (wct=0,bcc=0), or uninteresting, responses @@ -491,7 +491,7 @@ struct smb2_encryption_neg_context { __le16 ContextType; /* 2 */ __le16 DataLength; __le32 Reserved; - /* CipherCount usally 2, but can be 3 when AES256-GCM enabled */ + /* CipherCount usually 2, but can be 3 when AES256-GCM enabled */ __le16 CipherCount; /* AES128-GCM and AES128-CCM by default */ __le16 Ciphers[]; } __packed; @@ -1061,7 +1061,7 @@ struct smb2_server_client_notification { #define IL_IMPERSONATION cpu_to_le32(0x00000002) #define IL_DELEGATE cpu_to_le32(0x00000003) -/* File Attrubutes */ +/* File Attributes */ #define FILE_ATTRIBUTE_READONLY 0x00000001 #define FILE_ATTRIBUTE_HIDDEN 0x00000002 #define FILE_ATTRIBUTE_SYSTEM 0x00000004 diff --git a/fs/smb/common/smbfsctl.h b/fs/smb/common/smbfsctl.h index a94d658b88e8..4b379e84c46b 100644 --- a/fs/smb/common/smbfsctl.h +++ b/fs/smb/common/smbfsctl.h @@ -140,20 +140,21 @@ /* Used by the DFS filter See MS-DFSC */ #define IO_REPARSE_TAG_DFSR 0x80000012 #define IO_REPARSE_TAG_FILTER_MANAGER 0x8000000B -/* See section MS-FSCC 2.1.2.4 */ +/* Native SMB symlinks since Windows Vista, see MS-FSCC 2.1.2.4 */ #define IO_REPARSE_TAG_SYMLINK 0xA000000C #define IO_REPARSE_TAG_DEDUP 0x80000013 #define IO_REPARSE_APPXSTREAM 0xC0000014 -/* NFS symlinks, Win 8/SMB3 and later */ +/* NFS special files used by Windows NFS server since Windows Server 2012, see MS-FSCC 2.1.2.6 */ #define IO_REPARSE_TAG_NFS 0x80000014 /* * AzureFileSync - see * https://docs.microsoft.com/en-us/azure/storage/files/storage-sync-cloud-tiering */ #define IO_REPARSE_TAG_AZ_FILE_SYNC 0x8000001e +/* Native Win32 AF_UNIX sockets since Windows 10 April 2018 Update, used also by WSL */ +#define IO_REPARSE_TAG_AF_UNIX 0x80000023 /* WSL reparse tags */ #define IO_REPARSE_TAG_LX_SYMLINK 0xA000001D -#define IO_REPARSE_TAG_AF_UNIX 0x80000023 #define IO_REPARSE_TAG_LX_FIFO 0x80000024 #define IO_REPARSE_TAG_LX_CHR 0x80000025 #define IO_REPARSE_TAG_LX_BLK 0x80000026 diff --git a/fs/smb/server/connection.c b/fs/smb/server/connection.c index cac80e7bfefc..aa2a37a7ce84 100644 --- a/fs/smb/server/connection.c +++ b/fs/smb/server/connection.c @@ -25,7 +25,7 @@ DECLARE_RWSEM(conn_list_lock); /** * ksmbd_conn_free() - free resources of the connection instance * - * @conn: connection instance to be cleand up + * @conn: connection instance to be cleaned up * * During the thread termination, the corresponding conn instance * resources(sock/memory) are released and finally the conn object is freed. diff --git a/fs/smb/server/ksmbd_netlink.h b/fs/smb/server/ksmbd_netlink.h index f4e55199938d..38e6fd2da3b8 100644 --- a/fs/smb/server/ksmbd_netlink.h +++ b/fs/smb/server/ksmbd_netlink.h @@ -213,7 +213,7 @@ struct ksmbd_tree_connect_response { }; /* - * IPC Request struture to disconnect tree connection. + * IPC Request structure to disconnect tree connection. */ struct ksmbd_tree_disconnect_request { __u64 session_id; /* session id */ diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c index 246cde380dfb..4142c7ad5fa9 100644 --- a/fs/smb/server/oplock.c +++ b/fs/smb/server/oplock.c @@ -796,7 +796,7 @@ out: /** * smb2_lease_break_noti() - break lease when a new client request * write lease - * @opinfo: conains lease state information + * @opinfo: contains lease state information * * Return: 0 on success, otherwise error */ @@ -1484,7 +1484,7 @@ void create_lease_buf(u8 *rbuf, struct lease *lease) } /** - * parse_lease_state() - parse lease context containted in file open request + * parse_lease_state() - parse lease context contained in file open request * @open_req: buffer containing smb2 file open(create) request * * Return: allocated lease context object on success, otherwise NULL diff --git a/fs/smb/server/server.c b/fs/smb/server/server.c index c402d4abe826..231d2d224656 100644 --- a/fs/smb/server/server.c +++ b/fs/smb/server/server.c @@ -279,7 +279,7 @@ static void handle_ksmbd_work(struct work_struct *wk) /** * queue_ksmbd_work() - queue a smb request to worker thread queue - * for proccessing smb command and sending response + * for processing smb command and sending response * @conn: connection instance * * read remaining data from socket create and submit work. diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index e6bdc1b20727..797b0f24097b 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -1335,8 +1335,7 @@ static int ntlm_negotiate(struct ksmbd_work *work, return rc; sz = le16_to_cpu(rsp->SecurityBufferOffset); - chgblob = - (struct challenge_message *)((char *)&rsp->hdr.ProtocolId + sz); + chgblob = (struct challenge_message *)rsp->Buffer; memset(chgblob, 0, sizeof(struct challenge_message)); if (!work->conn->use_spnego) { @@ -1369,9 +1368,7 @@ static int ntlm_negotiate(struct ksmbd_work *work, goto out; } - sz = le16_to_cpu(rsp->SecurityBufferOffset); - unsafe_memcpy((char *)&rsp->hdr.ProtocolId + sz, spnego_blob, spnego_blob_len, - /* alloc is larger than blob, see smb2_allocate_rsp_buf() */); + memcpy(rsp->Buffer, spnego_blob, spnego_blob_len); rsp->SecurityBufferLength = cpu_to_le16(spnego_blob_len); out: @@ -1453,10 +1450,7 @@ static int ntlm_authenticate(struct ksmbd_work *work, if (rc) return -ENOMEM; - sz = le16_to_cpu(rsp->SecurityBufferOffset); - unsafe_memcpy((char *)&rsp->hdr.ProtocolId + sz, spnego_blob, - spnego_blob_len, - /* alloc is larger than blob, see smb2_allocate_rsp_buf() */); + memcpy(rsp->Buffer, spnego_blob, spnego_blob_len); rsp->SecurityBufferLength = cpu_to_le16(spnego_blob_len); kfree(spnego_blob); } @@ -2058,18 +2052,20 @@ out_err1: * @access: file access flags * @disposition: file disposition flags * @may_flags: set with MAY_ flags - * @is_dir: is creating open flags for directory + * @coptions: file creation options + * @mode: file mode * * Return: file open flags */ static int smb2_create_open_flags(bool file_present, __le32 access, __le32 disposition, int *may_flags, - bool is_dir) + __le32 coptions, + umode_t mode) { int oflags = O_NONBLOCK | O_LARGEFILE; - if (is_dir) { + if (coptions & FILE_DIRECTORY_FILE_LE || S_ISDIR(mode)) { access &= ~FILE_WRITE_DESIRE_ACCESS_LE; ksmbd_debug(SMB, "Discard write access to a directory\n"); } @@ -2086,7 +2082,7 @@ static int smb2_create_open_flags(bool file_present, __le32 access, *may_flags = MAY_OPEN | MAY_READ; } - if (access == FILE_READ_ATTRIBUTES_LE) + if (access == FILE_READ_ATTRIBUTES_LE || S_ISBLK(mode) || S_ISCHR(mode)) oflags |= O_PATH; if (file_present) { @@ -3181,8 +3177,8 @@ int smb2_open(struct ksmbd_work *work) open_flags = smb2_create_open_flags(file_present, daccess, req->CreateDisposition, &may_flags, - req->CreateOptions & FILE_DIRECTORY_FILE_LE || - (file_present && S_ISDIR(d_inode(path.dentry)->i_mode))); + req->CreateOptions, + file_present ? d_inode(path.dentry)->i_mode : 0); if (!test_tree_conn_flag(tcon, KSMBD_TREE_CONN_FLAG_WRITABLE)) { if (open_flags & (O_CREAT | O_TRUNC)) { @@ -3531,8 +3527,9 @@ int smb2_open(struct ksmbd_work *work) memcpy(fp->create_guid, dh_info.CreateGuid, SMB2_CREATE_GUID_SIZE); if (dh_info.timeout) - fp->durable_timeout = min(dh_info.timeout, - DURABLE_HANDLE_MAX_TIMEOUT); + fp->durable_timeout = + min_t(unsigned int, dh_info.timeout, + DURABLE_HANDLE_MAX_TIMEOUT); else fp->durable_timeout = 60; } @@ -4586,7 +4583,7 @@ static int smb2_get_ea(struct ksmbd_work *work, struct ksmbd_file *fp, path = &fp->filp->f_path; /* single EA entry is requested with given user.* name */ if (req->InputBufferLength) { - if (le32_to_cpu(req->InputBufferLength) < + if (le32_to_cpu(req->InputBufferLength) <= sizeof(struct smb2_ea_info_req)) return -EINVAL; @@ -4886,7 +4883,7 @@ static void get_file_alternate_info(struct ksmbd_work *work, spin_unlock(&dentry->d_lock); file_info->FileNameLength = cpu_to_le32(conv_len); rsp->OutputBufferLength = - cpu_to_le32(sizeof(struct smb2_file_alt_name_info) + conv_len); + cpu_to_le32(struct_size(file_info, FileName, conv_len)); } static int get_file_stream_info(struct ksmbd_work *work, @@ -7565,7 +7562,6 @@ static int fsctl_copychunk(struct ksmbd_work *work, ci_rsp->TotalBytesWritten = cpu_to_le32(ksmbd_server_side_copy_max_total_size()); - chunks = (struct srv_copychunk *)&ci_req->Chunks[0]; chunk_count = le32_to_cpu(ci_req->ChunkCount); if (chunk_count == 0) goto out; @@ -7573,12 +7569,12 @@ static int fsctl_copychunk(struct ksmbd_work *work, /* verify the SRV_COPYCHUNK_COPY packet */ if (chunk_count > ksmbd_server_side_copy_max_chunk_count() || - input_count < offsetof(struct copychunk_ioctl_req, Chunks) + - chunk_count * sizeof(struct srv_copychunk)) { + input_count < struct_size(ci_req, Chunks, chunk_count)) { rsp->hdr.Status = STATUS_INVALID_PARAMETER; return -EINVAL; } + chunks = &ci_req->Chunks[0]; for (i = 0; i < chunk_count; i++) { if (le32_to_cpu(chunks[i].Length) == 0 || le32_to_cpu(chunks[i].Length) > ksmbd_server_side_copy_max_chunk_size()) @@ -8090,7 +8086,7 @@ int smb2_ioctl(struct ksmbd_work *work) goto out; } - if (in_buf_len < sizeof(struct copychunk_ioctl_req)) { + if (in_buf_len <= sizeof(struct copychunk_ioctl_req)) { ret = -EINVAL; goto out; } diff --git a/fs/smb/server/smb2pdu.h b/fs/smb/server/smb2pdu.h index 3be7d5ae65a8..649dacf7e8c4 100644 --- a/fs/smb/server/smb2pdu.h +++ b/fs/smb/server/smb2pdu.h @@ -190,13 +190,6 @@ struct resume_key_ioctl_rsp { __u8 Context[4]; /* ignored, Windows sets to 4 bytes of zero */ } __packed; -struct copychunk_ioctl_req { - __le64 ResumeKey[3]; - __le32 ChunkCount; - __le32 Reserved; - __u8 Chunks[1]; /* array of srv_copychunk */ -} __packed; - struct srv_copychunk { __le64 SourceOffset; __le64 TargetOffset; @@ -204,6 +197,13 @@ struct srv_copychunk { __le32 Reserved; } __packed; +struct copychunk_ioctl_req { + __le64 ResumeKey[3]; + __le32 ChunkCount; + __le32 Reserved; + struct srv_copychunk Chunks[] __counted_by_le(ChunkCount); +} __packed; + struct copychunk_ioctl_rsp { __le32 ChunksWritten; __le32 ChunkBytesWritten; @@ -370,7 +370,7 @@ struct smb2_file_attr_tag_info { struct smb2_ea_info_req { __le32 NextEntryOffset; __u8 EaNameLength; - char name[1]; + char name[]; } __packed; /* level 15 Query */ struct smb2_ea_info { diff --git a/fs/smb/server/smb_common.c b/fs/smb/server/smb_common.c index cc4bb2377cbd..5b8d75e78ffb 100644 --- a/fs/smb/server/smb_common.c +++ b/fs/smb/server/smb_common.c @@ -488,7 +488,7 @@ int ksmbd_populate_dot_dotdot_entries(struct ksmbd_work *work, int info_level, * @shortname: destination short filename * * Return: shortname length or 0 when source long name is '.' or '..' - * TODO: Though this function comforms the restriction of 8.3 Filename spec, + * TODO: Though this function conforms the restriction of 8.3 Filename spec, * but the result is different with Windows 7's one. need to check. */ int ksmbd_extract_shortname(struct ksmbd_conn *conn, const char *longname, diff --git a/fs/smb/server/transport_rdma.c b/fs/smb/server/transport_rdma.c index 44c87e300c16..17c76713c6d0 100644 --- a/fs/smb/server/transport_rdma.c +++ b/fs/smb/server/transport_rdma.c @@ -1405,8 +1405,8 @@ static int smb_direct_rdma_xmit(struct smb_direct_transport *t, /* build rdma_rw_ctx for each descriptor */ desc_buf = buf; for (i = 0; i < desc_num; i++) { - msg = kzalloc(offsetof(struct smb_direct_rdma_rw_msg, sg_list) + - sizeof(struct scatterlist) * SG_CHUNK_SIZE, GFP_KERNEL); + msg = kzalloc(struct_size(msg, sg_list, SG_CHUNK_SIZE), + GFP_KERNEL); if (!msg) { ret = -ENOMEM; goto out; diff --git a/fs/smb/server/unicode.c b/fs/smb/server/unicode.c index 43ed29ee44ea..217106ff7b82 100644 --- a/fs/smb/server/unicode.c +++ b/fs/smb/server/unicode.c @@ -8,7 +8,7 @@ */ #include <linux/fs.h> #include <linux/slab.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "glob.h" #include "unicode.h" #include "smb_common.h" diff --git a/fs/smb/server/vfs_cache.h b/fs/smb/server/vfs_cache.h index b0f6d0f94cb8..5bbb179736c2 100644 --- a/fs/smb/server/vfs_cache.h +++ b/fs/smb/server/vfs_cache.h @@ -100,8 +100,8 @@ struct ksmbd_file { struct list_head blocked_works; struct list_head lock_list; - int durable_timeout; - int durable_scavenger_timeout; + unsigned int durable_timeout; + unsigned int durable_scavenger_timeout; /* if ls is happening on directory, below is valid*/ struct ksmbd_readdir_data readdir_data; diff --git a/fs/smb/server/xattr.h b/fs/smb/server/xattr.h index fa3e27d6971b..505101a8104c 100644 --- a/fs/smb/server/xattr.h +++ b/fs/smb/server/xattr.h @@ -99,7 +99,7 @@ struct xattr_ntacl { __u8 posix_acl_hash[XATTR_SD_HASH_SIZE]; /* 64bytes hash for posix acl */ }; -/* DOS ATTRIBUITE XATTR PREFIX */ +/* DOS ATTRIBUTE XATTR PREFIX */ #define DOS_ATTRIBUTE_PREFIX "DOSATTRIB" #define DOS_ATTRIBUTE_PREFIX_LEN (sizeof(DOS_ATTRIBUTE_PREFIX) - 1) #define XATTR_NAME_DOS_ATTRIBUTE (XATTR_USER_PREFIX DOS_ATTRIBUTE_PREFIX) diff --git a/fs/udf/balloc.c b/fs/udf/balloc.c index d8fc11765d61..807c493ed0cd 100644 --- a/fs/udf/balloc.c +++ b/fs/udf/balloc.c @@ -370,6 +370,7 @@ static void udf_table_free_blocks(struct super_block *sb, struct extent_position oepos, epos; int8_t etype; struct udf_inode_info *iinfo; + int ret = 0; mutex_lock(&sbi->s_alloc_mutex); iinfo = UDF_I(table); @@ -383,8 +384,12 @@ static void udf_table_free_blocks(struct super_block *sb, epos.block = oepos.block = iinfo->i_location; epos.bh = oepos.bh = NULL; - while (count && - (etype = udf_next_aext(table, &epos, &eloc, &elen, 1)) != -1) { + while (count) { + ret = udf_next_aext(table, &epos, &eloc, &elen, &etype, 1); + if (ret < 0) + goto error_return; + if (ret == 0) + break; if (((eloc.logicalBlockNum + (elen >> sb->s_blocksize_bits)) == start)) { if ((0x3FFFFFFF - elen) < @@ -459,11 +464,8 @@ static void udf_table_free_blocks(struct super_block *sb, adsize = sizeof(struct short_ad); else if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_LONG) adsize = sizeof(struct long_ad); - else { - brelse(oepos.bh); - brelse(epos.bh); + else goto error_return; - } if (epos.offset + (2 * adsize) > sb->s_blocksize) { /* Steal a block from the extent being free'd */ @@ -479,10 +481,10 @@ static void udf_table_free_blocks(struct super_block *sb, __udf_add_aext(table, &epos, &eloc, elen, 1); } +error_return: brelse(epos.bh); brelse(oepos.bh); -error_return: mutex_unlock(&sbi->s_alloc_mutex); return; } @@ -498,6 +500,7 @@ static int udf_table_prealloc_blocks(struct super_block *sb, struct extent_position epos; int8_t etype = -1; struct udf_inode_info *iinfo; + int ret = 0; if (first_block >= sbi->s_partmaps[partition].s_partition_len) return 0; @@ -516,11 +519,14 @@ static int udf_table_prealloc_blocks(struct super_block *sb, epos.bh = NULL; eloc.logicalBlockNum = 0xFFFFFFFF; - while (first_block != eloc.logicalBlockNum && - (etype = udf_next_aext(table, &epos, &eloc, &elen, 1)) != -1) { + while (first_block != eloc.logicalBlockNum) { + ret = udf_next_aext(table, &epos, &eloc, &elen, &etype, 1); + if (ret < 0) + goto err_out; + if (ret == 0) + break; udf_debug("eloc=%u, elen=%u, first_block=%u\n", eloc.logicalBlockNum, elen, first_block); - ; /* empty loop body */ } if (first_block == eloc.logicalBlockNum) { @@ -539,6 +545,7 @@ static int udf_table_prealloc_blocks(struct super_block *sb, alloc_count = 0; } +err_out: brelse(epos.bh); if (alloc_count) @@ -560,6 +567,7 @@ static udf_pblk_t udf_table_new_block(struct super_block *sb, struct extent_position epos, goal_epos; int8_t etype; struct udf_inode_info *iinfo = UDF_I(table); + int ret = 0; *err = -ENOSPC; @@ -583,8 +591,10 @@ static udf_pblk_t udf_table_new_block(struct super_block *sb, epos.block = iinfo->i_location; epos.bh = goal_epos.bh = NULL; - while (spread && - (etype = udf_next_aext(table, &epos, &eloc, &elen, 1)) != -1) { + while (spread) { + ret = udf_next_aext(table, &epos, &eloc, &elen, &etype, 1); + if (ret <= 0) + break; if (goal >= eloc.logicalBlockNum) { if (goal < eloc.logicalBlockNum + (elen >> sb->s_blocksize_bits)) @@ -612,9 +622,11 @@ static udf_pblk_t udf_table_new_block(struct super_block *sb, brelse(epos.bh); - if (spread == 0xFFFFFFFF) { + if (ret < 0 || spread == 0xFFFFFFFF) { brelse(goal_epos.bh); mutex_unlock(&sbi->s_alloc_mutex); + if (ret < 0) + *err = ret; return 0; } diff --git a/fs/udf/directory.c b/fs/udf/directory.c index 93153665eb37..632453aa3893 100644 --- a/fs/udf/directory.c +++ b/fs/udf/directory.c @@ -166,13 +166,19 @@ static struct buffer_head *udf_fiiter_bread_blk(struct udf_fileident_iter *iter) */ static int udf_fiiter_advance_blk(struct udf_fileident_iter *iter) { + int8_t etype = -1; + int err = 0; + iter->loffset++; if (iter->loffset < DIV_ROUND_UP(iter->elen, 1<<iter->dir->i_blkbits)) return 0; iter->loffset = 0; - if (udf_next_aext(iter->dir, &iter->epos, &iter->eloc, &iter->elen, 1) - != (EXT_RECORDED_ALLOCATED >> 30)) { + err = udf_next_aext(iter->dir, &iter->epos, &iter->eloc, + &iter->elen, &etype, 1); + if (err < 0) + return err; + else if (err == 0 || etype != (EXT_RECORDED_ALLOCATED >> 30)) { if (iter->pos == iter->dir->i_size) { iter->elen = 0; return 0; @@ -240,6 +246,7 @@ int udf_fiiter_init(struct udf_fileident_iter *iter, struct inode *dir, { struct udf_inode_info *iinfo = UDF_I(dir); int err = 0; + int8_t etype; iter->dir = dir; iter->bh[0] = iter->bh[1] = NULL; @@ -259,9 +266,9 @@ int udf_fiiter_init(struct udf_fileident_iter *iter, struct inode *dir, goto out; } - if (inode_bmap(dir, iter->pos >> dir->i_blkbits, &iter->epos, - &iter->eloc, &iter->elen, &iter->loffset) != - (EXT_RECORDED_ALLOCATED >> 30)) { + err = inode_bmap(dir, iter->pos >> dir->i_blkbits, &iter->epos, + &iter->eloc, &iter->elen, &iter->loffset, &etype); + if (err <= 0 || etype != (EXT_RECORDED_ALLOCATED >> 30)) { if (pos == dir->i_size) return 0; udf_err(dir->i_sb, @@ -457,6 +464,7 @@ int udf_fiiter_append_blk(struct udf_fileident_iter *iter) sector_t block; uint32_t old_elen = iter->elen; int err; + int8_t etype; if (WARN_ON_ONCE(iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB)) return -EINVAL; @@ -471,8 +479,9 @@ int udf_fiiter_append_blk(struct udf_fileident_iter *iter) udf_fiiter_update_elen(iter, old_elen); return err; } - if (inode_bmap(iter->dir, block, &iter->epos, &iter->eloc, &iter->elen, - &iter->loffset) != (EXT_RECORDED_ALLOCATED >> 30)) { + err = inode_bmap(iter->dir, block, &iter->epos, &iter->eloc, &iter->elen, + &iter->loffset, &etype); + if (err <= 0 || etype != (EXT_RECORDED_ALLOCATED >> 30)) { udf_err(iter->dir->i_sb, "block %llu not allocated in directory (ino %lu)\n", (unsigned long long)block, iter->dir->i_ino); diff --git a/fs/udf/inode.c b/fs/udf/inode.c index eaee57b91c6c..70c907fe8af9 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -404,7 +404,7 @@ struct udf_map_rq { static int udf_map_block(struct inode *inode, struct udf_map_rq *map) { - int err; + int ret; struct udf_inode_info *iinfo = UDF_I(inode); if (WARN_ON_ONCE(iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB)) @@ -416,18 +416,24 @@ static int udf_map_block(struct inode *inode, struct udf_map_rq *map) uint32_t elen; sector_t offset; struct extent_position epos = {}; + int8_t etype; down_read(&iinfo->i_data_sem); - if (inode_bmap(inode, map->lblk, &epos, &eloc, &elen, &offset) - == (EXT_RECORDED_ALLOCATED >> 30)) { + ret = inode_bmap(inode, map->lblk, &epos, &eloc, &elen, &offset, + &etype); + if (ret < 0) + goto out_read; + if (ret > 0 && etype == (EXT_RECORDED_ALLOCATED >> 30)) { map->pblk = udf_get_lb_pblock(inode->i_sb, &eloc, offset); map->oflags |= UDF_BLK_MAPPED; + ret = 0; } +out_read: up_read(&iinfo->i_data_sem); brelse(epos.bh); - return 0; + return ret; } down_write(&iinfo->i_data_sem); @@ -438,9 +444,9 @@ static int udf_map_block(struct inode *inode, struct udf_map_rq *map) if (((loff_t)map->lblk) << inode->i_blkbits >= iinfo->i_lenExtents) udf_discard_prealloc(inode); udf_clear_extent_cache(inode); - err = inode_getblk(inode, map); + ret = inode_getblk(inode, map); up_write(&iinfo->i_data_sem); - return err; + return ret; } static int __udf_get_block(struct inode *inode, sector_t block, @@ -543,6 +549,7 @@ static int udf_do_extend_file(struct inode *inode, } else { struct kernel_lb_addr tmploc; uint32_t tmplen; + int8_t tmptype; udf_write_aext(inode, last_pos, &last_ext->extLocation, last_ext->extLength, 1); @@ -552,8 +559,12 @@ static int udf_do_extend_file(struct inode *inode, * more extents, we may need to enter possible following * empty indirect extent. */ - if (new_block_bytes) - udf_next_aext(inode, last_pos, &tmploc, &tmplen, 0); + if (new_block_bytes) { + err = udf_next_aext(inode, last_pos, &tmploc, &tmplen, + &tmptype, 0); + if (err < 0) + goto out_err; + } } iinfo->i_lenExtents += add; @@ -657,8 +668,10 @@ static int udf_extend_file(struct inode *inode, loff_t newsize) */ udf_discard_prealloc(inode); - etype = inode_bmap(inode, first_block, &epos, &eloc, &elen, &offset); - within_last_ext = (etype != -1); + err = inode_bmap(inode, first_block, &epos, &eloc, &elen, &offset, &etype); + if (err < 0) + goto out; + within_last_ext = (err == 1); /* We don't expect extents past EOF... */ WARN_ON_ONCE(within_last_ext && elen > ((loff_t)offset + 1) << inode->i_blkbits); @@ -672,8 +685,10 @@ static int udf_extend_file(struct inode *inode, loff_t newsize) extent.extLength = EXT_NOT_RECORDED_NOT_ALLOCATED; } else { epos.offset -= adsize; - etype = udf_next_aext(inode, &epos, &extent.extLocation, - &extent.extLength, 0); + err = udf_next_aext(inode, &epos, &extent.extLocation, + &extent.extLength, &etype, 0); + if (err <= 0) + goto out; extent.extLength |= etype << 30; } @@ -710,11 +725,11 @@ static int inode_getblk(struct inode *inode, struct udf_map_rq *map) loff_t lbcount = 0, b_off = 0; udf_pblk_t newblocknum; sector_t offset = 0; - int8_t etype; + int8_t etype, tmpetype; struct udf_inode_info *iinfo = UDF_I(inode); udf_pblk_t goal = 0, pgoal = iinfo->i_location.logicalBlockNum; int lastblock = 0; - bool isBeyondEOF; + bool isBeyondEOF = false; int ret = 0; prev_epos.offset = udf_file_entry_alloc_offset(inode); @@ -746,9 +761,13 @@ static int inode_getblk(struct inode *inode, struct udf_map_rq *map) prev_epos.offset = cur_epos.offset; cur_epos.offset = next_epos.offset; - etype = udf_next_aext(inode, &next_epos, &eloc, &elen, 1); - if (etype == -1) + ret = udf_next_aext(inode, &next_epos, &eloc, &elen, &etype, 1); + if (ret < 0) { + goto out_free; + } else if (ret == 0) { + isBeyondEOF = true; break; + } c = !c; @@ -769,13 +788,17 @@ static int inode_getblk(struct inode *inode, struct udf_map_rq *map) * Move prev_epos and cur_epos into indirect extent if we are at * the pointer to it */ - udf_next_aext(inode, &prev_epos, &tmpeloc, &tmpelen, 0); - udf_next_aext(inode, &cur_epos, &tmpeloc, &tmpelen, 0); + ret = udf_next_aext(inode, &prev_epos, &tmpeloc, &tmpelen, &tmpetype, 0); + if (ret < 0) + goto out_free; + ret = udf_next_aext(inode, &cur_epos, &tmpeloc, &tmpelen, &tmpetype, 0); + if (ret < 0) + goto out_free; /* if the extent is allocated and recorded, return the block if the extent is not a multiple of the blocksize, round up */ - if (etype == (EXT_RECORDED_ALLOCATED >> 30)) { + if (!isBeyondEOF && etype == (EXT_RECORDED_ALLOCATED >> 30)) { if (elen & (inode->i_sb->s_blocksize - 1)) { elen = EXT_RECORDED_ALLOCATED | ((elen + inode->i_sb->s_blocksize - 1) & @@ -791,10 +814,9 @@ static int inode_getblk(struct inode *inode, struct udf_map_rq *map) } /* Are we beyond EOF and preallocated extent? */ - if (etype == -1) { + if (isBeyondEOF) { loff_t hole_len; - isBeyondEOF = true; if (count) { if (c) laarr[0] = laarr[1]; @@ -830,7 +852,6 @@ static int inode_getblk(struct inode *inode, struct udf_map_rq *map) endnum = c + 1; lastblock = 1; } else { - isBeyondEOF = false; endnum = startnum = ((count > 2) ? 2 : count); /* if the current extent is in position 0, @@ -844,15 +865,17 @@ static int inode_getblk(struct inode *inode, struct udf_map_rq *map) /* if the current block is located in an extent, read the next extent */ - etype = udf_next_aext(inode, &next_epos, &eloc, &elen, 0); - if (etype != -1) { + ret = udf_next_aext(inode, &next_epos, &eloc, &elen, &etype, 0); + if (ret > 0) { laarr[c + 1].extLength = (etype << 30) | elen; laarr[c + 1].extLocation = eloc; count++; startnum++; endnum++; - } else + } else if (ret == 0) lastblock = 1; + else + goto out_free; } /* if the current extent is not recorded but allocated, get the @@ -1170,6 +1193,7 @@ static int udf_update_extents(struct inode *inode, struct kernel_long_ad *laarr, int start = 0, i; struct kernel_lb_addr tmploc; uint32_t tmplen; + int8_t tmpetype; int err; if (startnum > endnum) { @@ -1187,14 +1211,19 @@ static int udf_update_extents(struct inode *inode, struct kernel_long_ad *laarr, */ if (err < 0) return err; - udf_next_aext(inode, epos, &laarr[i].extLocation, - &laarr[i].extLength, 1); + err = udf_next_aext(inode, epos, &laarr[i].extLocation, + &laarr[i].extLength, &tmpetype, 1); + if (err < 0) + return err; start++; } } for (i = start; i < endnum; i++) { - udf_next_aext(inode, epos, &tmploc, &tmplen, 0); + err = udf_next_aext(inode, epos, &tmploc, &tmplen, &tmpetype, 0); + if (err < 0) + return err; + udf_write_aext(inode, epos, &laarr[i].extLocation, laarr[i].extLength, 1); } @@ -1953,6 +1982,7 @@ int udf_setup_indirect_aext(struct inode *inode, udf_pblk_t block, struct extent_position nepos; struct kernel_lb_addr neloc; int ver, adsize; + int err = 0; if (UDF_I(inode)->i_alloc_type == ICBTAG_FLAG_AD_SHORT) adsize = sizeof(struct short_ad); @@ -1997,10 +2027,12 @@ int udf_setup_indirect_aext(struct inode *inode, udf_pblk_t block, if (epos->offset + adsize > sb->s_blocksize) { struct kernel_lb_addr cp_loc; uint32_t cp_len; - int cp_type; + int8_t cp_type; epos->offset -= adsize; - cp_type = udf_current_aext(inode, epos, &cp_loc, &cp_len, 0); + err = udf_current_aext(inode, epos, &cp_loc, &cp_len, &cp_type, 0); + if (err <= 0) + goto err_out; cp_len |= ((uint32_t)cp_type) << 30; __udf_add_aext(inode, &nepos, &cp_loc, cp_len, 1); @@ -2015,6 +2047,9 @@ int udf_setup_indirect_aext(struct inode *inode, udf_pblk_t block, *epos = nepos; return 0; +err_out: + brelse(bh); + return err; } /* @@ -2160,21 +2195,30 @@ void udf_write_aext(struct inode *inode, struct extent_position *epos, */ #define UDF_MAX_INDIR_EXTS 16 -int8_t udf_next_aext(struct inode *inode, struct extent_position *epos, - struct kernel_lb_addr *eloc, uint32_t *elen, int inc) +/* + * Returns 1 on success, -errno on error, 0 on hit EOF. + */ +int udf_next_aext(struct inode *inode, struct extent_position *epos, + struct kernel_lb_addr *eloc, uint32_t *elen, int8_t *etype, + int inc) { - int8_t etype; unsigned int indirections = 0; + int ret = 0; + udf_pblk_t block; - while ((etype = udf_current_aext(inode, epos, eloc, elen, inc)) == - (EXT_NEXT_EXTENT_ALLOCDESCS >> 30)) { - udf_pblk_t block; + while (1) { + ret = udf_current_aext(inode, epos, eloc, elen, + etype, inc); + if (ret <= 0) + return ret; + if (*etype != (EXT_NEXT_EXTENT_ALLOCDESCS >> 30)) + return ret; if (++indirections > UDF_MAX_INDIR_EXTS) { udf_err(inode->i_sb, "too many indirect extents in inode %lu\n", inode->i_ino); - return -1; + return -EFSCORRUPTED; } epos->block = *eloc; @@ -2184,18 +2228,19 @@ int8_t udf_next_aext(struct inode *inode, struct extent_position *epos, epos->bh = sb_bread(inode->i_sb, block); if (!epos->bh) { udf_debug("reading block %u failed!\n", block); - return -1; + return -EIO; } } - - return etype; } -int8_t udf_current_aext(struct inode *inode, struct extent_position *epos, - struct kernel_lb_addr *eloc, uint32_t *elen, int inc) +/* + * Returns 1 on success, -errno on error, 0 on hit EOF. + */ +int udf_current_aext(struct inode *inode, struct extent_position *epos, + struct kernel_lb_addr *eloc, uint32_t *elen, int8_t *etype, + int inc) { int alen; - int8_t etype; uint8_t *ptr; struct short_ad *sad; struct long_ad *lad; @@ -2210,20 +2255,23 @@ int8_t udf_current_aext(struct inode *inode, struct extent_position *epos, alen = udf_file_entry_alloc_offset(inode) + iinfo->i_lenAlloc; } else { + struct allocExtDesc *header = + (struct allocExtDesc *)epos->bh->b_data; + if (!epos->offset) epos->offset = sizeof(struct allocExtDesc); ptr = epos->bh->b_data + epos->offset; - alen = sizeof(struct allocExtDesc) + - le32_to_cpu(((struct allocExtDesc *)epos->bh->b_data)-> - lengthAllocDescs); + if (check_add_overflow(sizeof(struct allocExtDesc), + le32_to_cpu(header->lengthAllocDescs), &alen)) + return -1; } switch (iinfo->i_alloc_type) { case ICBTAG_FLAG_AD_SHORT: sad = udf_get_fileshortad(ptr, alen, &epos->offset, inc); if (!sad) - return -1; - etype = le32_to_cpu(sad->extLength) >> 30; + return 0; + *etype = le32_to_cpu(sad->extLength) >> 30; eloc->logicalBlockNum = le32_to_cpu(sad->extPosition); eloc->partitionReferenceNum = iinfo->i_location.partitionReferenceNum; @@ -2232,17 +2280,17 @@ int8_t udf_current_aext(struct inode *inode, struct extent_position *epos, case ICBTAG_FLAG_AD_LONG: lad = udf_get_filelongad(ptr, alen, &epos->offset, inc); if (!lad) - return -1; - etype = le32_to_cpu(lad->extLength) >> 30; + return 0; + *etype = le32_to_cpu(lad->extLength) >> 30; *eloc = lelb_to_cpu(lad->extLocation); *elen = le32_to_cpu(lad->extLength) & UDF_EXTENT_LENGTH_MASK; break; default: udf_debug("alloc_type = %u unsupported\n", iinfo->i_alloc_type); - return -1; + return -EINVAL; } - return etype; + return 1; } static int udf_insert_aext(struct inode *inode, struct extent_position epos, @@ -2251,20 +2299,24 @@ static int udf_insert_aext(struct inode *inode, struct extent_position epos, struct kernel_lb_addr oeloc; uint32_t oelen; int8_t etype; - int err; + int ret; if (epos.bh) get_bh(epos.bh); - while ((etype = udf_next_aext(inode, &epos, &oeloc, &oelen, 0)) != -1) { + while (1) { + ret = udf_next_aext(inode, &epos, &oeloc, &oelen, &etype, 0); + if (ret <= 0) + break; udf_write_aext(inode, &epos, &neloc, nelen, 1); neloc = oeloc; nelen = (etype << 30) | oelen; } - err = udf_add_aext(inode, &epos, &neloc, nelen, 1); + if (ret == 0) + ret = udf_add_aext(inode, &epos, &neloc, nelen, 1); brelse(epos.bh); - return err; + return ret; } int8_t udf_delete_aext(struct inode *inode, struct extent_position epos) @@ -2276,6 +2328,7 @@ int8_t udf_delete_aext(struct inode *inode, struct extent_position epos) struct udf_inode_info *iinfo; struct kernel_lb_addr eloc; uint32_t elen; + int ret; if (epos.bh) { get_bh(epos.bh); @@ -2291,10 +2344,18 @@ int8_t udf_delete_aext(struct inode *inode, struct extent_position epos) adsize = 0; oepos = epos; - if (udf_next_aext(inode, &epos, &eloc, &elen, 1) == -1) + if (udf_next_aext(inode, &epos, &eloc, &elen, &etype, 1) <= 0) return -1; - while ((etype = udf_next_aext(inode, &epos, &eloc, &elen, 1)) != -1) { + while (1) { + ret = udf_next_aext(inode, &epos, &eloc, &elen, &etype, 1); + if (ret < 0) { + brelse(epos.bh); + brelse(oepos.bh); + return -1; + } + if (ret == 0) + break; udf_write_aext(inode, &oepos, &eloc, (etype << 30) | elen, 1); if (oepos.bh != epos.bh) { oepos.block = epos.block; @@ -2351,14 +2412,17 @@ int8_t udf_delete_aext(struct inode *inode, struct extent_position epos) return (elen >> 30); } -int8_t inode_bmap(struct inode *inode, sector_t block, - struct extent_position *pos, struct kernel_lb_addr *eloc, - uint32_t *elen, sector_t *offset) +/* + * Returns 1 on success, -errno on error, 0 on hit EOF. + */ +int inode_bmap(struct inode *inode, sector_t block, struct extent_position *pos, + struct kernel_lb_addr *eloc, uint32_t *elen, sector_t *offset, + int8_t *etype) { unsigned char blocksize_bits = inode->i_sb->s_blocksize_bits; loff_t lbcount = 0, bcount = (loff_t) block << blocksize_bits; - int8_t etype; struct udf_inode_info *iinfo; + int err = 0; iinfo = UDF_I(inode); if (!udf_read_extent_cache(inode, bcount, &lbcount, pos)) { @@ -2368,11 +2432,13 @@ int8_t inode_bmap(struct inode *inode, sector_t block, } *elen = 0; do { - etype = udf_next_aext(inode, pos, eloc, elen, 1); - if (etype == -1) { - *offset = (bcount - lbcount) >> blocksize_bits; - iinfo->i_lenExtents = lbcount; - return -1; + err = udf_next_aext(inode, pos, eloc, elen, etype, 1); + if (err <= 0) { + if (err == 0) { + *offset = (bcount - lbcount) >> blocksize_bits; + iinfo->i_lenExtents = lbcount; + } + return err; } lbcount += *elen; } while (lbcount <= bcount); @@ -2380,5 +2446,5 @@ int8_t inode_bmap(struct inode *inode, sector_t block, udf_update_extent_cache(inode, lbcount - *elen, pos); *offset = (bcount + *elen - lbcount) >> blocksize_bits; - return etype; + return 1; } diff --git a/fs/udf/partition.c b/fs/udf/partition.c index af877991edc1..2b85c9501bed 100644 --- a/fs/udf/partition.c +++ b/fs/udf/partition.c @@ -282,9 +282,11 @@ static uint32_t udf_try_read_meta(struct inode *inode, uint32_t block, sector_t ext_offset; struct extent_position epos = {}; uint32_t phyblock; + int8_t etype; + int err = 0; - if (inode_bmap(inode, block, &epos, &eloc, &elen, &ext_offset) != - (EXT_RECORDED_ALLOCATED >> 30)) + err = inode_bmap(inode, block, &epos, &eloc, &elen, &ext_offset, &etype); + if (err <= 0 || etype != (EXT_RECORDED_ALLOCATED >> 30)) phyblock = 0xFFFFFFFF; else { map = &UDF_SB(sb)->s_partmaps[partition]; diff --git a/fs/udf/super.c b/fs/udf/super.c index 3460ecc826d1..1c8a736b3309 100644 --- a/fs/udf/super.c +++ b/fs/udf/super.c @@ -2482,13 +2482,14 @@ static unsigned int udf_count_free_table(struct super_block *sb, uint32_t elen; struct kernel_lb_addr eloc; struct extent_position epos; + int8_t etype; mutex_lock(&UDF_SB(sb)->s_alloc_mutex); epos.block = UDF_I(table)->i_location; epos.offset = sizeof(struct unallocSpaceEntry); epos.bh = NULL; - while (udf_next_aext(table, &epos, &eloc, &elen, 1) != -1) + while (udf_next_aext(table, &epos, &eloc, &elen, &etype, 1) > 0) accum += (elen >> table->i_sb->s_blocksize_bits); brelse(epos.bh); diff --git a/fs/udf/truncate.c b/fs/udf/truncate.c index a686c10fd709..4f33a4a48886 100644 --- a/fs/udf/truncate.c +++ b/fs/udf/truncate.c @@ -69,6 +69,7 @@ void udf_truncate_tail_extent(struct inode *inode) int8_t etype = -1, netype; int adsize; struct udf_inode_info *iinfo = UDF_I(inode); + int ret; if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB || inode->i_size == iinfo->i_lenExtents) @@ -85,7 +86,10 @@ void udf_truncate_tail_extent(struct inode *inode) BUG(); /* Find the last extent in the file */ - while ((netype = udf_next_aext(inode, &epos, &eloc, &elen, 1)) != -1) { + while (1) { + ret = udf_next_aext(inode, &epos, &eloc, &elen, &netype, 1); + if (ret <= 0) + break; etype = netype; lbcount += elen; if (lbcount > inode->i_size) { @@ -101,7 +105,8 @@ void udf_truncate_tail_extent(struct inode *inode) epos.offset -= adsize; extent_trunc(inode, &epos, &eloc, etype, elen, nelen); epos.offset += adsize; - if (udf_next_aext(inode, &epos, &eloc, &elen, 1) != -1) + if (udf_next_aext(inode, &epos, &eloc, &elen, + &netype, 1) > 0) udf_err(inode->i_sb, "Extent after EOF in inode %u\n", (unsigned)inode->i_ino); @@ -110,7 +115,8 @@ void udf_truncate_tail_extent(struct inode *inode) } /* This inode entry is in-memory only and thus we don't have to mark * the inode dirty */ - iinfo->i_lenExtents = inode->i_size; + if (ret == 0) + iinfo->i_lenExtents = inode->i_size; brelse(epos.bh); } @@ -124,6 +130,8 @@ void udf_discard_prealloc(struct inode *inode) int8_t etype = -1; struct udf_inode_info *iinfo = UDF_I(inode); int bsize = i_blocksize(inode); + int8_t tmpetype = -1; + int ret; if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB || ALIGN(inode->i_size, bsize) == ALIGN(iinfo->i_lenExtents, bsize)) @@ -132,15 +140,23 @@ void udf_discard_prealloc(struct inode *inode) epos.block = iinfo->i_location; /* Find the last extent in the file */ - while (udf_next_aext(inode, &epos, &eloc, &elen, 0) != -1) { + while (1) { + ret = udf_next_aext(inode, &epos, &eloc, &elen, &tmpetype, 0); + if (ret < 0) + goto out; + if (ret == 0) + break; brelse(prev_epos.bh); prev_epos = epos; if (prev_epos.bh) get_bh(prev_epos.bh); - etype = udf_next_aext(inode, &epos, &eloc, &elen, 1); + ret = udf_next_aext(inode, &epos, &eloc, &elen, &etype, 1); + if (ret < 0) + goto out; lbcount += elen; } + if (etype == (EXT_NOT_RECORDED_ALLOCATED >> 30)) { lbcount -= elen; udf_delete_aext(inode, prev_epos); @@ -150,6 +166,7 @@ void udf_discard_prealloc(struct inode *inode) /* This inode entry is in-memory only and thus we don't have to mark * the inode dirty */ iinfo->i_lenExtents = lbcount; +out: brelse(epos.bh); brelse(prev_epos.bh); } @@ -188,6 +205,7 @@ int udf_truncate_extents(struct inode *inode) loff_t byte_offset; int adsize; struct udf_inode_info *iinfo = UDF_I(inode); + int ret = 0; if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_SHORT) adsize = sizeof(struct short_ad); @@ -196,10 +214,12 @@ int udf_truncate_extents(struct inode *inode) else BUG(); - etype = inode_bmap(inode, first_block, &epos, &eloc, &elen, &offset); + ret = inode_bmap(inode, first_block, &epos, &eloc, &elen, &offset, &etype); + if (ret < 0) + return ret; byte_offset = (offset << sb->s_blocksize_bits) + (inode->i_size & (sb->s_blocksize - 1)); - if (etype == -1) { + if (ret == 0) { /* We should extend the file? */ WARN_ON(byte_offset); return 0; @@ -217,8 +237,8 @@ int udf_truncate_extents(struct inode *inode) else lenalloc -= sizeof(struct allocExtDesc); - while ((etype = udf_current_aext(inode, &epos, &eloc, - &elen, 0)) != -1) { + while ((ret = udf_current_aext(inode, &epos, &eloc, + &elen, &etype, 0)) > 0) { if (etype == (EXT_NEXT_EXTENT_ALLOCDESCS >> 30)) { udf_write_aext(inode, &epos, &neloc, nelen, 0); if (indirect_ext_len) { @@ -253,6 +273,11 @@ int udf_truncate_extents(struct inode *inode) } } + if (ret < 0) { + brelse(epos.bh); + return ret; + } + if (indirect_ext_len) { BUG_ON(!epos.bh); udf_free_blocks(sb, NULL, &epos.block, 0, indirect_ext_len); diff --git a/fs/udf/udfdecl.h b/fs/udf/udfdecl.h index 88692512a466..d159f20d61e8 100644 --- a/fs/udf/udfdecl.h +++ b/fs/udf/udfdecl.h @@ -157,8 +157,9 @@ extern struct buffer_head *udf_bread(struct inode *inode, udf_pblk_t block, extern int udf_setsize(struct inode *, loff_t); extern void udf_evict_inode(struct inode *); extern int udf_write_inode(struct inode *, struct writeback_control *wbc); -extern int8_t inode_bmap(struct inode *, sector_t, struct extent_position *, - struct kernel_lb_addr *, uint32_t *, sector_t *); +extern int inode_bmap(struct inode *inode, sector_t block, + struct extent_position *pos, struct kernel_lb_addr *eloc, + uint32_t *elen, sector_t *offset, int8_t *etype); int udf_get_block(struct inode *, sector_t, struct buffer_head *, int); extern int udf_setup_indirect_aext(struct inode *inode, udf_pblk_t block, struct extent_position *epos); @@ -169,10 +170,12 @@ extern int udf_add_aext(struct inode *, struct extent_position *, extern void udf_write_aext(struct inode *, struct extent_position *, struct kernel_lb_addr *, uint32_t, int); extern int8_t udf_delete_aext(struct inode *, struct extent_position); -extern int8_t udf_next_aext(struct inode *, struct extent_position *, - struct kernel_lb_addr *, uint32_t *, int); -extern int8_t udf_current_aext(struct inode *, struct extent_position *, - struct kernel_lb_addr *, uint32_t *, int); +extern int udf_next_aext(struct inode *inode, struct extent_position *epos, + struct kernel_lb_addr *eloc, uint32_t *elen, + int8_t *etype, int inc); +extern int udf_current_aext(struct inode *inode, struct extent_position *epos, + struct kernel_lb_addr *eloc, uint32_t *elen, + int8_t *etype, int inc); extern void udf_update_extra_perms(struct inode *inode, umode_t mode); /* misc.c */ diff --git a/fs/ufs/namei.c b/fs/ufs/namei.c index 24bd12186647..c8390976ab6a 100644 --- a/fs/ufs/namei.c +++ b/fs/ufs/namei.c @@ -307,7 +307,7 @@ static int ufs_rename(struct mnt_idmap *idmap, struct inode *old_dir, if (old_dir != new_dir) ufs_set_link(old_inode, dir_de, dir_folio, new_dir, 0); else - folio_release_kmap(dir_folio, new_dir); + folio_release_kmap(dir_folio, dir_de); inode_dec_link_count(old_dir); } return 0; diff --git a/fs/xfs/xfs_linux.h b/fs/xfs/xfs_linux.h index 54a098fe7285..9a2221b4aa21 100644 --- a/fs/xfs/xfs_linux.h +++ b/fs/xfs/xfs_linux.h @@ -69,7 +69,7 @@ typedef __u32 xfs_nlink_t; #include <asm/param.h> #include <linux/uaccess.h> #include <asm/byteorder.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "xfs_fs.h" #include "xfs_stats.h" diff --git a/fs/zonefs/sysfs.c b/fs/zonefs/sysfs.c index 8ccb65c2b419..ff9a688f1f9c 100644 --- a/fs/zonefs/sysfs.c +++ b/fs/zonefs/sysfs.c @@ -92,6 +92,7 @@ int zonefs_sysfs_register(struct super_block *sb) struct zonefs_sb_info *sbi = ZONEFS_SB(sb); int ret; + super_set_sysfs_name_id(sb); init_completion(&sbi->s_kobj_unregister); ret = kobject_init_and_add(&sbi->s_kobj, &zonefs_sb_ktype, zonefs_sysfs_root, "%s", sb->s_id); diff --git a/include/asm-generic/Kbuild b/include/asm-generic/Kbuild index 620b6da429d4..1b43c3a77012 100644 --- a/include/asm-generic/Kbuild +++ b/include/asm-generic/Kbuild @@ -58,7 +58,6 @@ mandatory-y += tlbflush.h mandatory-y += topology.h mandatory-y += trace_clock.h mandatory-y += uaccess.h -mandatory-y += unaligned.h mandatory-y += vermagic.h mandatory-y += vga.h mandatory-y += video.h diff --git a/include/asm-generic/uaccess.h b/include/asm-generic/uaccess.h index a5be9e61a2a2..b276f783494c 100644 --- a/include/asm-generic/uaccess.h +++ b/include/asm-generic/uaccess.h @@ -11,7 +11,7 @@ #include <asm-generic/access_ok.h> #ifdef CONFIG_UACCESS_MEMCPY -#include <asm/unaligned.h> +#include <linux/unaligned.h> static __always_inline int __get_user_fn(size_t size, const void __user *from, void *to) diff --git a/include/crypto/chacha.h b/include/crypto/chacha.h index b3ea73b81944..5bae6a55b333 100644 --- a/include/crypto/chacha.h +++ b/include/crypto/chacha.h @@ -15,7 +15,7 @@ #ifndef _CRYPTO_CHACHA_H #define _CRYPTO_CHACHA_H -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/types.h> /* 32-bit stream position, then 96-bit nonce (RFC7539 convention) */ diff --git a/include/crypto/internal/ecc.h b/include/crypto/internal/ecc.h index 0717a53ae732..065f00e4bf40 100644 --- a/include/crypto/internal/ecc.h +++ b/include/crypto/internal/ecc.h @@ -27,7 +27,7 @@ #define _CRYPTO_ECC_H #include <crypto/ecc_curve.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /* One digit is u64 qword. */ #define ECC_CURVE_NIST_P192_DIGITS 3 diff --git a/include/crypto/internal/poly1305.h b/include/crypto/internal/poly1305.h index 196aa769f296..e614594f88c1 100644 --- a/include/crypto/internal/poly1305.h +++ b/include/crypto/internal/poly1305.h @@ -6,7 +6,7 @@ #ifndef _CRYPTO_INTERNAL_POLY1305_H #define _CRYPTO_INTERNAL_POLY1305_H -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/types.h> #include <crypto/poly1305.h> diff --git a/include/crypto/sha1_base.h b/include/crypto/sha1_base.h index 2e0e7c3827d1..0c342ed0d038 100644 --- a/include/crypto/sha1_base.h +++ b/include/crypto/sha1_base.h @@ -14,7 +14,7 @@ #include <linux/module.h> #include <linux/string.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> typedef void (sha1_block_fn)(struct sha1_state *sst, u8 const *src, int blocks); diff --git a/include/crypto/sha256_base.h b/include/crypto/sha256_base.h index ab904d82236f..e0418818d63c 100644 --- a/include/crypto/sha256_base.h +++ b/include/crypto/sha256_base.h @@ -9,7 +9,7 @@ #define _CRYPTO_SHA256_BASE_H #include <asm/byteorder.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <crypto/internal/hash.h> #include <crypto/sha2.h> #include <linux/string.h> diff --git a/include/crypto/sha512_base.h b/include/crypto/sha512_base.h index b370b3340b16..679916a84cb2 100644 --- a/include/crypto/sha512_base.h +++ b/include/crypto/sha512_base.h @@ -14,7 +14,7 @@ #include <linux/module.h> #include <linux/string.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> typedef void (sha512_block_fn)(struct sha512_state *sst, u8 const *src, int blocks); diff --git a/include/crypto/sm3_base.h b/include/crypto/sm3_base.h index 2f3a32ab97bb..b33ed39c2bce 100644 --- a/include/crypto/sm3_base.h +++ b/include/crypto/sm3_base.h @@ -14,7 +14,7 @@ #include <linux/crypto.h> #include <linux/module.h> #include <linux/string.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> typedef void (sm3_block_fn)(struct sm3_state *sst, u8 const *src, int blocks); diff --git a/include/crypto/utils.h b/include/crypto/utils.h index acbb917a00c6..2594f45777b5 100644 --- a/include/crypto/utils.h +++ b/include/crypto/utils.h @@ -7,7 +7,7 @@ #ifndef _CRYPTO_UTILS_H #define _CRYPTO_UTILS_H -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/compiler_attributes.h> #include <linux/types.h> diff --git a/include/linux/einj-cxl.h b/include/cxl/einj.h index 624ff6ff41f9..624ff6ff41f9 100644 --- a/include/linux/einj-cxl.h +++ b/include/cxl/einj.h diff --git a/include/linux/cxl-event.h b/include/cxl/event.h index 0bea1afbd747..0bea1afbd747 100644 --- a/include/linux/cxl-event.h +++ b/include/cxl/event.h diff --git a/include/cxl/mailbox.h b/include/cxl/mailbox.h new file mode 100644 index 000000000000..bacd111e75f1 --- /dev/null +++ b/include/cxl/mailbox.h @@ -0,0 +1,28 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright(c) 2024 Intel Corporation. */ +#ifndef __CXL_MBOX_H__ +#define __CXL_MBOX_H__ +#include <linux/rcuwait.h> + +struct cxl_mbox_cmd; + +/** + * struct cxl_mailbox - context for CXL mailbox operations + * @host: device that hosts the mailbox + * @payload_size: Size of space for payload + * (CXL 3.1 8.2.8.4.3 Mailbox Capabilities Register) + * @mbox_mutex: mutex protects device mailbox and firmware + * @mbox_wait: rcuwait for mailbox + * @mbox_send: @dev specific transport for transmitting mailbox commands + */ +struct cxl_mailbox { + struct device *host; + size_t payload_size; + struct mutex mbox_mutex; /* lock to protect mailbox context */ + struct rcuwait mbox_wait; + int (*mbox_send)(struct cxl_mailbox *cxl_mbox, struct cxl_mbox_cmd *cmd); +}; + +int cxl_mailbox_init(struct cxl_mailbox *cxl_mbox, struct device *host); + +#endif diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h index fe8edb917360..9c437a057e5d 100644 --- a/include/drm/gpu_scheduler.h +++ b/include/drm/gpu_scheduler.h @@ -574,7 +574,7 @@ void drm_sched_entity_modify_sched(struct drm_sched_entity *entity, void drm_sched_tdr_queue_imm(struct drm_gpu_scheduler *sched); void drm_sched_job_cleanup(struct drm_sched_job *job); -void drm_sched_wakeup(struct drm_gpu_scheduler *sched, struct drm_sched_entity *entity); +void drm_sched_wakeup(struct drm_gpu_scheduler *sched); bool drm_sched_wqueue_ready(struct drm_gpu_scheduler *sched); void drm_sched_wqueue_stop(struct drm_gpu_scheduler *sched); void drm_sched_wqueue_start(struct drm_gpu_scheduler *sched); diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index d3b66d77df7a..262b6596eca5 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -203,12 +203,12 @@ unsigned long bitmap_find_next_zero_area_off(unsigned long *map, * the bit offset of all zero areas this function finds is multiples of that * power of 2. A @align_mask of 0 means no alignment is required. */ -static inline unsigned long -bitmap_find_next_zero_area(unsigned long *map, - unsigned long size, - unsigned long start, - unsigned int nr, - unsigned long align_mask) +static __always_inline +unsigned long bitmap_find_next_zero_area(unsigned long *map, + unsigned long size, + unsigned long start, + unsigned int nr, + unsigned long align_mask) { return bitmap_find_next_zero_area_off(map, size, start, nr, align_mask, 0); @@ -228,7 +228,7 @@ void bitmap_fold(unsigned long *dst, const unsigned long *orig, #define bitmap_size(nbits) (ALIGN(nbits, BITS_PER_LONG) / BITS_PER_BYTE) -static inline void bitmap_zero(unsigned long *dst, unsigned int nbits) +static __always_inline void bitmap_zero(unsigned long *dst, unsigned int nbits) { unsigned int len = bitmap_size(nbits); @@ -238,7 +238,7 @@ static inline void bitmap_zero(unsigned long *dst, unsigned int nbits) memset(dst, 0, len); } -static inline void bitmap_fill(unsigned long *dst, unsigned int nbits) +static __always_inline void bitmap_fill(unsigned long *dst, unsigned int nbits) { unsigned int len = bitmap_size(nbits); @@ -248,8 +248,8 @@ static inline void bitmap_fill(unsigned long *dst, unsigned int nbits) memset(dst, 0xff, len); } -static inline void bitmap_copy(unsigned long *dst, const unsigned long *src, - unsigned int nbits) +static __always_inline +void bitmap_copy(unsigned long *dst, const unsigned long *src, unsigned int nbits) { unsigned int len = bitmap_size(nbits); @@ -262,8 +262,8 @@ static inline void bitmap_copy(unsigned long *dst, const unsigned long *src, /* * Copy bitmap and clear tail bits in last word. */ -static inline void bitmap_copy_clear_tail(unsigned long *dst, - const unsigned long *src, unsigned int nbits) +static __always_inline +void bitmap_copy_clear_tail(unsigned long *dst, const unsigned long *src, unsigned int nbits) { bitmap_copy(dst, src, nbits); if (nbits % BITS_PER_LONG) @@ -318,16 +318,18 @@ void bitmap_to_arr64(u64 *buf, const unsigned long *bitmap, unsigned int nbits); bitmap_copy_clear_tail((unsigned long *)(buf), (const unsigned long *)(bitmap), (nbits)) #endif -static inline bool bitmap_and(unsigned long *dst, const unsigned long *src1, - const unsigned long *src2, unsigned int nbits) +static __always_inline +bool bitmap_and(unsigned long *dst, const unsigned long *src1, + const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) return (*dst = *src1 & *src2 & BITMAP_LAST_WORD_MASK(nbits)) != 0; return __bitmap_and(dst, src1, src2, nbits); } -static inline void bitmap_or(unsigned long *dst, const unsigned long *src1, - const unsigned long *src2, unsigned int nbits) +static __always_inline +void bitmap_or(unsigned long *dst, const unsigned long *src1, + const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) *dst = *src1 | *src2; @@ -335,8 +337,9 @@ static inline void bitmap_or(unsigned long *dst, const unsigned long *src1, __bitmap_or(dst, src1, src2, nbits); } -static inline void bitmap_xor(unsigned long *dst, const unsigned long *src1, - const unsigned long *src2, unsigned int nbits) +static __always_inline +void bitmap_xor(unsigned long *dst, const unsigned long *src1, + const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) *dst = *src1 ^ *src2; @@ -344,16 +347,17 @@ static inline void bitmap_xor(unsigned long *dst, const unsigned long *src1, __bitmap_xor(dst, src1, src2, nbits); } -static inline bool bitmap_andnot(unsigned long *dst, const unsigned long *src1, - const unsigned long *src2, unsigned int nbits) +static __always_inline +bool bitmap_andnot(unsigned long *dst, const unsigned long *src1, + const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) return (*dst = *src1 & ~(*src2) & BITMAP_LAST_WORD_MASK(nbits)) != 0; return __bitmap_andnot(dst, src1, src2, nbits); } -static inline void bitmap_complement(unsigned long *dst, const unsigned long *src, - unsigned int nbits) +static __always_inline +void bitmap_complement(unsigned long *dst, const unsigned long *src, unsigned int nbits) { if (small_const_nbits(nbits)) *dst = ~(*src); @@ -368,8 +372,8 @@ static inline void bitmap_complement(unsigned long *dst, const unsigned long *sr #endif #define BITMAP_MEM_MASK (BITMAP_MEM_ALIGNMENT - 1) -static inline bool bitmap_equal(const unsigned long *src1, - const unsigned long *src2, unsigned int nbits) +static __always_inline +bool bitmap_equal(const unsigned long *src1, const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) return !((*src1 ^ *src2) & BITMAP_LAST_WORD_MASK(nbits)); @@ -388,10 +392,9 @@ static inline bool bitmap_equal(const unsigned long *src1, * * Returns: True if (*@src1 | *@src2) == *@src3, false otherwise */ -static inline bool bitmap_or_equal(const unsigned long *src1, - const unsigned long *src2, - const unsigned long *src3, - unsigned int nbits) +static __always_inline +bool bitmap_or_equal(const unsigned long *src1, const unsigned long *src2, + const unsigned long *src3, unsigned int nbits) { if (!small_const_nbits(nbits)) return __bitmap_or_equal(src1, src2, src3, nbits); @@ -399,9 +402,8 @@ static inline bool bitmap_or_equal(const unsigned long *src1, return !(((*src1 | *src2) ^ *src3) & BITMAP_LAST_WORD_MASK(nbits)); } -static inline bool bitmap_intersects(const unsigned long *src1, - const unsigned long *src2, - unsigned int nbits) +static __always_inline +bool bitmap_intersects(const unsigned long *src1, const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) return ((*src1 & *src2) & BITMAP_LAST_WORD_MASK(nbits)) != 0; @@ -409,8 +411,8 @@ static inline bool bitmap_intersects(const unsigned long *src1, return __bitmap_intersects(src1, src2, nbits); } -static inline bool bitmap_subset(const unsigned long *src1, - const unsigned long *src2, unsigned int nbits) +static __always_inline +bool bitmap_subset(const unsigned long *src1, const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) return ! ((*src1 & ~(*src2)) & BITMAP_LAST_WORD_MASK(nbits)); @@ -418,7 +420,8 @@ static inline bool bitmap_subset(const unsigned long *src1, return __bitmap_subset(src1, src2, nbits); } -static inline bool bitmap_empty(const unsigned long *src, unsigned nbits) +static __always_inline +bool bitmap_empty(const unsigned long *src, unsigned nbits) { if (small_const_nbits(nbits)) return ! (*src & BITMAP_LAST_WORD_MASK(nbits)); @@ -426,7 +429,8 @@ static inline bool bitmap_empty(const unsigned long *src, unsigned nbits) return find_first_bit(src, nbits) == nbits; } -static inline bool bitmap_full(const unsigned long *src, unsigned int nbits) +static __always_inline +bool bitmap_full(const unsigned long *src, unsigned int nbits) { if (small_const_nbits(nbits)) return ! (~(*src) & BITMAP_LAST_WORD_MASK(nbits)); @@ -460,8 +464,8 @@ unsigned long bitmap_weight_andnot(const unsigned long *src1, return __bitmap_weight_andnot(src1, src2, nbits); } -static __always_inline void bitmap_set(unsigned long *map, unsigned int start, - unsigned int nbits) +static __always_inline +void bitmap_set(unsigned long *map, unsigned int start, unsigned int nbits) { if (__builtin_constant_p(nbits) && nbits == 1) __set_bit(start, map); @@ -476,8 +480,8 @@ static __always_inline void bitmap_set(unsigned long *map, unsigned int start, __bitmap_set(map, start, nbits); } -static __always_inline void bitmap_clear(unsigned long *map, unsigned int start, - unsigned int nbits) +static __always_inline +void bitmap_clear(unsigned long *map, unsigned int start, unsigned int nbits) { if (__builtin_constant_p(nbits) && nbits == 1) __clear_bit(start, map); @@ -492,8 +496,9 @@ static __always_inline void bitmap_clear(unsigned long *map, unsigned int start, __bitmap_clear(map, start, nbits); } -static inline void bitmap_shift_right(unsigned long *dst, const unsigned long *src, - unsigned int shift, unsigned int nbits) +static __always_inline +void bitmap_shift_right(unsigned long *dst, const unsigned long *src, + unsigned int shift, unsigned int nbits) { if (small_const_nbits(nbits)) *dst = (*src & BITMAP_LAST_WORD_MASK(nbits)) >> shift; @@ -501,8 +506,9 @@ static inline void bitmap_shift_right(unsigned long *dst, const unsigned long *s __bitmap_shift_right(dst, src, shift, nbits); } -static inline void bitmap_shift_left(unsigned long *dst, const unsigned long *src, - unsigned int shift, unsigned int nbits) +static __always_inline +void bitmap_shift_left(unsigned long *dst, const unsigned long *src, + unsigned int shift, unsigned int nbits) { if (small_const_nbits(nbits)) *dst = (*src << shift) & BITMAP_LAST_WORD_MASK(nbits); @@ -510,11 +516,12 @@ static inline void bitmap_shift_left(unsigned long *dst, const unsigned long *sr __bitmap_shift_left(dst, src, shift, nbits); } -static inline void bitmap_replace(unsigned long *dst, - const unsigned long *old, - const unsigned long *new, - const unsigned long *mask, - unsigned int nbits) +static __always_inline +void bitmap_replace(unsigned long *dst, + const unsigned long *old, + const unsigned long *new, + const unsigned long *mask, + unsigned int nbits) { if (small_const_nbits(nbits)) *dst = (*old & ~(*mask)) | (*new & *mask); @@ -557,8 +564,9 @@ static inline void bitmap_replace(unsigned long *dst, * bitmap_gather() can be seen as the 'reverse' bitmap_scatter() operation. * See bitmap_scatter() for details related to this relationship. */ -static inline void bitmap_scatter(unsigned long *dst, const unsigned long *src, - const unsigned long *mask, unsigned int nbits) +static __always_inline +void bitmap_scatter(unsigned long *dst, const unsigned long *src, + const unsigned long *mask, unsigned int nbits) { unsigned int n = 0; unsigned int bit; @@ -611,8 +619,9 @@ static inline void bitmap_scatter(unsigned long *dst, const unsigned long *src, * bitmap_scatter(res, src, mask, n) and a call to * bitmap_scatter(res, result, mask, n) will lead to the same res value. */ -static inline void bitmap_gather(unsigned long *dst, const unsigned long *src, - const unsigned long *mask, unsigned int nbits) +static __always_inline +void bitmap_gather(unsigned long *dst, const unsigned long *src, + const unsigned long *mask, unsigned int nbits) { unsigned int n = 0; unsigned int bit; @@ -623,9 +632,9 @@ static inline void bitmap_gather(unsigned long *dst, const unsigned long *src, __assign_bit(n++, dst, test_bit(bit, src)); } -static inline void bitmap_next_set_region(unsigned long *bitmap, - unsigned int *rs, unsigned int *re, - unsigned int end) +static __always_inline +void bitmap_next_set_region(unsigned long *bitmap, unsigned int *rs, + unsigned int *re, unsigned int end) { *rs = find_next_bit(bitmap, end, *rs); *re = find_next_zero_bit(bitmap, end, *rs + 1); @@ -640,7 +649,8 @@ static inline void bitmap_next_set_region(unsigned long *bitmap, * This is the complement to __bitmap_find_free_region() and releases * the found region (by clearing it in the bitmap). */ -static inline void bitmap_release_region(unsigned long *bitmap, unsigned int pos, int order) +static __always_inline +void bitmap_release_region(unsigned long *bitmap, unsigned int pos, int order) { bitmap_clear(bitmap, pos, BIT(order)); } @@ -656,7 +666,8 @@ static inline void bitmap_release_region(unsigned long *bitmap, unsigned int pos * Returns: 0 on success, or %-EBUSY if specified region wasn't * free (not all bits were zero). */ -static inline int bitmap_allocate_region(unsigned long *bitmap, unsigned int pos, int order) +static __always_inline +int bitmap_allocate_region(unsigned long *bitmap, unsigned int pos, int order) { unsigned int len = BIT(order); @@ -680,7 +691,8 @@ static inline int bitmap_allocate_region(unsigned long *bitmap, unsigned int pos * Returns: the bit offset in bitmap of the allocated region, * or -errno on failure. */ -static inline int bitmap_find_free_region(unsigned long *bitmap, unsigned int bits, int order) +static __always_inline +int bitmap_find_free_region(unsigned long *bitmap, unsigned int bits, int order) { unsigned int pos, end; /* scans bitmap by regions of size order */ @@ -734,7 +746,7 @@ static inline int bitmap_find_free_region(unsigned long *bitmap, unsigned int bi * That is ``(u32 *)(&val)[0]`` gets the upper 32 bits, * but we expect the lower 32-bits of u64. */ -static inline void bitmap_from_u64(unsigned long *dst, u64 mask) +static __always_inline void bitmap_from_u64(unsigned long *dst, u64 mask) { bitmap_from_arr64(dst, &mask, 64); } @@ -749,9 +761,8 @@ static inline void bitmap_from_u64(unsigned long *dst, u64 mask) * @map memory region. For @nbits = 0 and @nbits > BITS_PER_LONG the return * value is undefined. */ -static inline unsigned long bitmap_read(const unsigned long *map, - unsigned long start, - unsigned long nbits) +static __always_inline +unsigned long bitmap_read(const unsigned long *map, unsigned long start, unsigned long nbits) { size_t index = BIT_WORD(start); unsigned long offset = start % BITS_PER_LONG; @@ -784,8 +795,9 @@ static inline unsigned long bitmap_read(const unsigned long *map, * * For @nbits == 0 and @nbits > BITS_PER_LONG no writes are performed. */ -static inline void bitmap_write(unsigned long *map, unsigned long value, - unsigned long start, unsigned long nbits) +static __always_inline +void bitmap_write(unsigned long *map, unsigned long value, + unsigned long start, unsigned long nbits) { size_t index; unsigned long offset; diff --git a/include/linux/bits.h b/include/linux/bits.h index 0eb24d21aac2..60044b608817 100644 --- a/include/linux/bits.h +++ b/include/linux/bits.h @@ -36,4 +36,19 @@ #define GENMASK_ULL(h, l) \ (GENMASK_INPUT_CHECK(h, l) + __GENMASK_ULL(h, l)) +#if !defined(__ASSEMBLY__) +/* + * Missing asm support + * + * __GENMASK_U128() depends on _BIT128() which would not work + * in the asm code, as it shifts an 'unsigned __init128' data + * type instead of direct representation of 128 bit constants + * such as long and unsigned long. The fundamental problem is + * that a 128 bit constant will get silently truncated by the + * gcc compiler. + */ +#define GENMASK_U128(h, l) \ + (GENMASK_INPUT_CHECK(h, l) + __GENMASK_U128(h, l)) +#endif + #endif /* __LINUX_BITS_H */ diff --git a/include/linux/ceph/decode.h b/include/linux/ceph/decode.h index 04f3ace5787b..8fc1aed64113 100644 --- a/include/linux/ceph/decode.h +++ b/include/linux/ceph/decode.h @@ -6,7 +6,7 @@ #include <linux/bug.h> #include <linux/slab.h> #include <linux/time.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/ceph/types.h> diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 4497d0a6772c..15fb566d3f46 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -4,7 +4,7 @@ #include <linux/ceph/ceph_debug.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/backing-dev.h> #include <linux/completion.h> #include <linux/exportfs.h> diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index f66f6aac74f6..d7941478158c 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -449,8 +449,6 @@ extern int ceph_osdc_init(struct ceph_osd_client *osdc, extern void ceph_osdc_stop(struct ceph_osd_client *osdc); extern void ceph_osdc_reopen_osds(struct ceph_osd_client *osdc); -extern void ceph_osdc_handle_reply(struct ceph_osd_client *osdc, - struct ceph_msg *msg); extern void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg); void ceph_osdc_update_epoch_barrier(struct ceph_osd_client *osdc, u32 eb); diff --git a/include/linux/cleanup.h b/include/linux/cleanup.h index a3d3e888cf1f..038b2d523bf8 100644 --- a/include/linux/cleanup.h +++ b/include/linux/cleanup.h @@ -4,6 +4,142 @@ #include <linux/compiler.h> +/** + * DOC: scope-based cleanup helpers + * + * The "goto error" pattern is notorious for introducing subtle resource + * leaks. It is tedious and error prone to add new resource acquisition + * constraints into code paths that already have several unwind + * conditions. The "cleanup" helpers enable the compiler to help with + * this tedium and can aid in maintaining LIFO (last in first out) + * unwind ordering to avoid unintentional leaks. + * + * As drivers make up the majority of the kernel code base, here is an + * example of using these helpers to clean up PCI drivers. The target of + * the cleanups are occasions where a goto is used to unwind a device + * reference (pci_dev_put()), or unlock the device (pci_dev_unlock()) + * before returning. + * + * The DEFINE_FREE() macro can arrange for PCI device references to be + * dropped when the associated variable goes out of scope:: + * + * DEFINE_FREE(pci_dev_put, struct pci_dev *, if (_T) pci_dev_put(_T)) + * ... + * struct pci_dev *dev __free(pci_dev_put) = + * pci_get_slot(parent, PCI_DEVFN(0, 0)); + * + * The above will automatically call pci_dev_put() if @dev is non-NULL + * when @dev goes out of scope (automatic variable scope). If a function + * wants to invoke pci_dev_put() on error, but return @dev (i.e. without + * freeing it) on success, it can do:: + * + * return no_free_ptr(dev); + * + * ...or:: + * + * return_ptr(dev); + * + * The DEFINE_GUARD() macro can arrange for the PCI device lock to be + * dropped when the scope where guard() is invoked ends:: + * + * DEFINE_GUARD(pci_dev, struct pci_dev *, pci_dev_lock(_T), pci_dev_unlock(_T)) + * ... + * guard(pci_dev)(dev); + * + * The lifetime of the lock obtained by the guard() helper follows the + * scope of automatic variable declaration. Take the following example:: + * + * func(...) + * { + * if (...) { + * ... + * guard(pci_dev)(dev); // pci_dev_lock() invoked here + * ... + * } // <- implied pci_dev_unlock() triggered here + * } + * + * Observe the lock is held for the remainder of the "if ()" block not + * the remainder of "func()". + * + * Now, when a function uses both __free() and guard(), or multiple + * instances of __free(), the LIFO order of variable definition order + * matters. GCC documentation says: + * + * "When multiple variables in the same scope have cleanup attributes, + * at exit from the scope their associated cleanup functions are run in + * reverse order of definition (last defined, first cleanup)." + * + * When the unwind order matters it requires that variables be defined + * mid-function scope rather than at the top of the file. Take the + * following example and notice the bug highlighted by "!!":: + * + * LIST_HEAD(list); + * DEFINE_MUTEX(lock); + * + * struct object { + * struct list_head node; + * }; + * + * static struct object *alloc_add(void) + * { + * struct object *obj; + * + * lockdep_assert_held(&lock); + * obj = kzalloc(sizeof(*obj), GFP_KERNEL); + * if (obj) { + * LIST_HEAD_INIT(&obj->node); + * list_add(obj->node, &list): + * } + * return obj; + * } + * + * static void remove_free(struct object *obj) + * { + * lockdep_assert_held(&lock); + * list_del(&obj->node); + * kfree(obj); + * } + * + * DEFINE_FREE(remove_free, struct object *, if (_T) remove_free(_T)) + * static int init(void) + * { + * struct object *obj __free(remove_free) = NULL; + * int err; + * + * guard(mutex)(&lock); + * obj = alloc_add(); + * + * if (!obj) + * return -ENOMEM; + * + * err = other_init(obj); + * if (err) + * return err; // remove_free() called without the lock!! + * + * no_free_ptr(obj); + * return 0; + * } + * + * That bug is fixed by changing init() to call guard() and define + + * initialize @obj in this order:: + * + * guard(mutex)(&lock); + * struct object *obj __free(remove_free) = alloc_add(); + * + * Given that the "__free(...) = NULL" pattern for variables defined at + * the top of the function poses this potential interdependency problem + * the recommendation is to always define and assign variables in one + * statement and not group variable definitions at the top of the + * function when __free() is used. + * + * Lastly, given that the benefit of cleanup helpers is removal of + * "goto", and that the "goto" statement can jump between scopes, the + * expectation is that usage of "goto" and cleanup helpers is never + * mixed in the same function. I.e. for a given routine, convert all + * resources that need a "goto" cleanup to scope-based cleanup, or + * convert none of them. + */ + /* * DEFINE_FREE(name, type, free): * simple helper macro that defines the required wrapper for a __free() diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index e0e19d9c1323..7fe0981a7e46 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -1107,10 +1107,9 @@ static inline int parse_perf_domain(int cpu, const char *list_name, const char *cell_name, struct of_phandle_args *args) { - struct device_node *cpu_np; int ret; - cpu_np = of_cpu_device_node_get(cpu); + struct device_node *cpu_np __free(device_node) = of_cpu_device_node_get(cpu); if (!cpu_np) return -ENODEV; @@ -1118,9 +1117,6 @@ static inline int parse_perf_domain(int cpu, const char *list_name, args); if (ret < 0) return ret; - - of_node_put(cpu_np); - return 0; } diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 53158de44b83..9278a50d514f 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -30,7 +30,7 @@ extern unsigned int nr_cpu_ids; #endif -static inline void set_nr_cpu_ids(unsigned int nr) +static __always_inline void set_nr_cpu_ids(unsigned int nr) { #if (NR_CPUS == 1) || defined(CONFIG_FORCE_NR_CPUS) WARN_ON(nr != nr_cpu_ids); @@ -149,7 +149,7 @@ static __always_inline unsigned int cpumask_check(unsigned int cpu) * * Return: >= nr_cpu_ids if no cpus set. */ -static inline unsigned int cpumask_first(const struct cpumask *srcp) +static __always_inline unsigned int cpumask_first(const struct cpumask *srcp) { return find_first_bit(cpumask_bits(srcp), small_cpumask_bits); } @@ -160,7 +160,7 @@ static inline unsigned int cpumask_first(const struct cpumask *srcp) * * Return: >= nr_cpu_ids if all cpus are set. */ -static inline unsigned int cpumask_first_zero(const struct cpumask *srcp) +static __always_inline unsigned int cpumask_first_zero(const struct cpumask *srcp) { return find_first_zero_bit(cpumask_bits(srcp), small_cpumask_bits); } @@ -172,7 +172,7 @@ static inline unsigned int cpumask_first_zero(const struct cpumask *srcp) * * Return: >= nr_cpu_ids if no cpus set in both. See also cpumask_next_and(). */ -static inline +static __always_inline unsigned int cpumask_first_and(const struct cpumask *srcp1, const struct cpumask *srcp2) { return find_first_and_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits); @@ -186,7 +186,7 @@ unsigned int cpumask_first_and(const struct cpumask *srcp1, const struct cpumask * * Return: >= nr_cpu_ids if no cpus set in all. */ -static inline +static __always_inline unsigned int cpumask_first_and_and(const struct cpumask *srcp1, const struct cpumask *srcp2, const struct cpumask *srcp3) @@ -201,7 +201,7 @@ unsigned int cpumask_first_and_and(const struct cpumask *srcp1, * * Return: >= nr_cpumask_bits if no CPUs set. */ -static inline unsigned int cpumask_last(const struct cpumask *srcp) +static __always_inline unsigned int cpumask_last(const struct cpumask *srcp) { return find_last_bit(cpumask_bits(srcp), small_cpumask_bits); } @@ -213,7 +213,7 @@ static inline unsigned int cpumask_last(const struct cpumask *srcp) * * Return: >= nr_cpu_ids if no further cpus set. */ -static inline +static __always_inline unsigned int cpumask_next(int n, const struct cpumask *srcp) { /* -1 is a legal arg here. */ @@ -229,7 +229,8 @@ unsigned int cpumask_next(int n, const struct cpumask *srcp) * * Return: >= nr_cpu_ids if no further cpus unset. */ -static inline unsigned int cpumask_next_zero(int n, const struct cpumask *srcp) +static __always_inline +unsigned int cpumask_next_zero(int n, const struct cpumask *srcp) { /* -1 is a legal arg here. */ if (n != -1) @@ -239,18 +240,21 @@ static inline unsigned int cpumask_next_zero(int n, const struct cpumask *srcp) #if NR_CPUS == 1 /* Uniprocessor: there is only one valid CPU */ -static inline unsigned int cpumask_local_spread(unsigned int i, int node) +static __always_inline +unsigned int cpumask_local_spread(unsigned int i, int node) { return 0; } -static inline unsigned int cpumask_any_and_distribute(const struct cpumask *src1p, - const struct cpumask *src2p) +static __always_inline +unsigned int cpumask_any_and_distribute(const struct cpumask *src1p, + const struct cpumask *src2p) { return cpumask_first_and(src1p, src2p); } -static inline unsigned int cpumask_any_distribute(const struct cpumask *srcp) +static __always_inline +unsigned int cpumask_any_distribute(const struct cpumask *srcp) { return cpumask_first(srcp); } @@ -269,9 +273,9 @@ unsigned int cpumask_any_distribute(const struct cpumask *srcp); * * Return: >= nr_cpu_ids if no further cpus set in both. */ -static inline +static __always_inline unsigned int cpumask_next_and(int n, const struct cpumask *src1p, - const struct cpumask *src2p) + const struct cpumask *src2p) { /* -1 is a legal arg here. */ if (n != -1) @@ -291,7 +295,7 @@ unsigned int cpumask_next_and(int n, const struct cpumask *src1p, for_each_set_bit(cpu, cpumask_bits(mask), small_cpumask_bits) #if NR_CPUS == 1 -static inline +static __always_inline unsigned int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap) { cpumask_check(start); @@ -394,7 +398,7 @@ unsigned int __pure cpumask_next_wrap(int n, const struct cpumask *mask, int sta * Often used to find any cpu but smp_processor_id() in a mask. * Return: >= nr_cpu_ids if no cpus set. */ -static inline +static __always_inline unsigned int cpumask_any_but(const struct cpumask *mask, unsigned int cpu) { unsigned int i; @@ -414,7 +418,7 @@ unsigned int cpumask_any_but(const struct cpumask *mask, unsigned int cpu) * * Returns >= nr_cpu_ids if no cpus set. */ -static inline +static __always_inline unsigned int cpumask_any_and_but(const struct cpumask *mask1, const struct cpumask *mask2, unsigned int cpu) @@ -436,7 +440,8 @@ unsigned int cpumask_any_and_but(const struct cpumask *mask1, * * Return: >= nr_cpu_ids if such cpu doesn't exist. */ -static inline unsigned int cpumask_nth(unsigned int cpu, const struct cpumask *srcp) +static __always_inline +unsigned int cpumask_nth(unsigned int cpu, const struct cpumask *srcp) { return find_nth_bit(cpumask_bits(srcp), small_cpumask_bits, cpumask_check(cpu)); } @@ -449,7 +454,7 @@ static inline unsigned int cpumask_nth(unsigned int cpu, const struct cpumask *s * * Return: >= nr_cpu_ids if such cpu doesn't exist. */ -static inline +static __always_inline unsigned int cpumask_nth_and(unsigned int cpu, const struct cpumask *srcp1, const struct cpumask *srcp2) { @@ -465,7 +470,7 @@ unsigned int cpumask_nth_and(unsigned int cpu, const struct cpumask *srcp1, * * Return: >= nr_cpu_ids if such cpu doesn't exist. */ -static inline +static __always_inline unsigned int cpumask_nth_andnot(unsigned int cpu, const struct cpumask *srcp1, const struct cpumask *srcp2) { @@ -508,12 +513,14 @@ unsigned int cpumask_nth_and_andnot(unsigned int cpu, const struct cpumask *srcp * @cpu: cpu number (< nr_cpu_ids) * @dstp: the cpumask pointer */ -static __always_inline void cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp) +static __always_inline +void cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp) { set_bit(cpumask_check(cpu), cpumask_bits(dstp)); } -static __always_inline void __cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp) +static __always_inline +void __cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp) { __set_bit(cpumask_check(cpu), cpumask_bits(dstp)); } @@ -557,7 +564,8 @@ static __always_inline void __cpumask_assign_cpu(int cpu, struct cpumask *dstp, * * Return: true if @cpu is set in @cpumask, else returns false */ -static __always_inline bool cpumask_test_cpu(int cpu, const struct cpumask *cpumask) +static __always_inline +bool cpumask_test_cpu(int cpu, const struct cpumask *cpumask) { return test_bit(cpumask_check(cpu), cpumask_bits((cpumask))); } @@ -571,7 +579,8 @@ static __always_inline bool cpumask_test_cpu(int cpu, const struct cpumask *cpum * * Return: true if @cpu is set in old bitmap of @cpumask, else returns false */ -static __always_inline bool cpumask_test_and_set_cpu(int cpu, struct cpumask *cpumask) +static __always_inline +bool cpumask_test_and_set_cpu(int cpu, struct cpumask *cpumask) { return test_and_set_bit(cpumask_check(cpu), cpumask_bits(cpumask)); } @@ -585,7 +594,8 @@ static __always_inline bool cpumask_test_and_set_cpu(int cpu, struct cpumask *cp * * Return: true if @cpu is set in old bitmap of @cpumask, else returns false */ -static __always_inline bool cpumask_test_and_clear_cpu(int cpu, struct cpumask *cpumask) +static __always_inline +bool cpumask_test_and_clear_cpu(int cpu, struct cpumask *cpumask) { return test_and_clear_bit(cpumask_check(cpu), cpumask_bits(cpumask)); } @@ -594,7 +604,7 @@ static __always_inline bool cpumask_test_and_clear_cpu(int cpu, struct cpumask * * cpumask_setall - set all cpus (< nr_cpu_ids) in a cpumask * @dstp: the cpumask pointer */ -static inline void cpumask_setall(struct cpumask *dstp) +static __always_inline void cpumask_setall(struct cpumask *dstp) { if (small_const_nbits(small_cpumask_bits)) { cpumask_bits(dstp)[0] = BITMAP_LAST_WORD_MASK(nr_cpumask_bits); @@ -607,7 +617,7 @@ static inline void cpumask_setall(struct cpumask *dstp) * cpumask_clear - clear all cpus (< nr_cpu_ids) in a cpumask * @dstp: the cpumask pointer */ -static inline void cpumask_clear(struct cpumask *dstp) +static __always_inline void cpumask_clear(struct cpumask *dstp) { bitmap_zero(cpumask_bits(dstp), large_cpumask_bits); } @@ -620,9 +630,9 @@ static inline void cpumask_clear(struct cpumask *dstp) * * Return: false if *@dstp is empty, else returns true */ -static inline bool cpumask_and(struct cpumask *dstp, - const struct cpumask *src1p, - const struct cpumask *src2p) +static __always_inline +bool cpumask_and(struct cpumask *dstp, const struct cpumask *src1p, + const struct cpumask *src2p) { return bitmap_and(cpumask_bits(dstp), cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); @@ -634,8 +644,9 @@ static inline bool cpumask_and(struct cpumask *dstp, * @src1p: the first input * @src2p: the second input */ -static inline void cpumask_or(struct cpumask *dstp, const struct cpumask *src1p, - const struct cpumask *src2p) +static __always_inline +void cpumask_or(struct cpumask *dstp, const struct cpumask *src1p, + const struct cpumask *src2p) { bitmap_or(cpumask_bits(dstp), cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); @@ -647,9 +658,9 @@ static inline void cpumask_or(struct cpumask *dstp, const struct cpumask *src1p, * @src1p: the first input * @src2p: the second input */ -static inline void cpumask_xor(struct cpumask *dstp, - const struct cpumask *src1p, - const struct cpumask *src2p) +static __always_inline +void cpumask_xor(struct cpumask *dstp, const struct cpumask *src1p, + const struct cpumask *src2p) { bitmap_xor(cpumask_bits(dstp), cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); @@ -663,9 +674,9 @@ static inline void cpumask_xor(struct cpumask *dstp, * * Return: false if *@dstp is empty, else returns true */ -static inline bool cpumask_andnot(struct cpumask *dstp, - const struct cpumask *src1p, - const struct cpumask *src2p) +static __always_inline +bool cpumask_andnot(struct cpumask *dstp, const struct cpumask *src1p, + const struct cpumask *src2p) { return bitmap_andnot(cpumask_bits(dstp), cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); @@ -678,8 +689,8 @@ static inline bool cpumask_andnot(struct cpumask *dstp, * * Return: true if the cpumasks are equal, false if not */ -static inline bool cpumask_equal(const struct cpumask *src1p, - const struct cpumask *src2p) +static __always_inline +bool cpumask_equal(const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_equal(cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); @@ -694,9 +705,9 @@ static inline bool cpumask_equal(const struct cpumask *src1p, * Return: true if first cpumask ORed with second cpumask == third cpumask, * otherwise false */ -static inline bool cpumask_or_equal(const struct cpumask *src1p, - const struct cpumask *src2p, - const struct cpumask *src3p) +static __always_inline +bool cpumask_or_equal(const struct cpumask *src1p, const struct cpumask *src2p, + const struct cpumask *src3p) { return bitmap_or_equal(cpumask_bits(src1p), cpumask_bits(src2p), cpumask_bits(src3p), small_cpumask_bits); @@ -710,8 +721,8 @@ static inline bool cpumask_or_equal(const struct cpumask *src1p, * Return: true if first cpumask ANDed with second cpumask is non-empty, * otherwise false */ -static inline bool cpumask_intersects(const struct cpumask *src1p, - const struct cpumask *src2p) +static __always_inline +bool cpumask_intersects(const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_intersects(cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); @@ -724,8 +735,8 @@ static inline bool cpumask_intersects(const struct cpumask *src1p, * * Return: true if *@src1p is a subset of *@src2p, else returns false */ -static inline bool cpumask_subset(const struct cpumask *src1p, - const struct cpumask *src2p) +static __always_inline +bool cpumask_subset(const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_subset(cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); @@ -737,7 +748,7 @@ static inline bool cpumask_subset(const struct cpumask *src1p, * * Return: true if srcp is empty (has no bits set), else false */ -static inline bool cpumask_empty(const struct cpumask *srcp) +static __always_inline bool cpumask_empty(const struct cpumask *srcp) { return bitmap_empty(cpumask_bits(srcp), small_cpumask_bits); } @@ -748,7 +759,7 @@ static inline bool cpumask_empty(const struct cpumask *srcp) * * Return: true if srcp is full (has all bits set), else false */ -static inline bool cpumask_full(const struct cpumask *srcp) +static __always_inline bool cpumask_full(const struct cpumask *srcp) { return bitmap_full(cpumask_bits(srcp), nr_cpumask_bits); } @@ -759,7 +770,7 @@ static inline bool cpumask_full(const struct cpumask *srcp) * * Return: count of bits set in *srcp */ -static inline unsigned int cpumask_weight(const struct cpumask *srcp) +static __always_inline unsigned int cpumask_weight(const struct cpumask *srcp) { return bitmap_weight(cpumask_bits(srcp), small_cpumask_bits); } @@ -771,8 +782,8 @@ static inline unsigned int cpumask_weight(const struct cpumask *srcp) * * Return: count of bits set in both *srcp1 and *srcp2 */ -static inline unsigned int cpumask_weight_and(const struct cpumask *srcp1, - const struct cpumask *srcp2) +static __always_inline +unsigned int cpumask_weight_and(const struct cpumask *srcp1, const struct cpumask *srcp2) { return bitmap_weight_and(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits); } @@ -784,8 +795,9 @@ static inline unsigned int cpumask_weight_and(const struct cpumask *srcp1, * * Return: count of bits set in both *srcp1 and *srcp2 */ -static inline unsigned int cpumask_weight_andnot(const struct cpumask *srcp1, - const struct cpumask *srcp2) +static __always_inline +unsigned int cpumask_weight_andnot(const struct cpumask *srcp1, + const struct cpumask *srcp2) { return bitmap_weight_andnot(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits); } @@ -796,8 +808,8 @@ static inline unsigned int cpumask_weight_andnot(const struct cpumask *srcp1, * @srcp: the input to shift * @n: the number of bits to shift by */ -static inline void cpumask_shift_right(struct cpumask *dstp, - const struct cpumask *srcp, int n) +static __always_inline +void cpumask_shift_right(struct cpumask *dstp, const struct cpumask *srcp, int n) { bitmap_shift_right(cpumask_bits(dstp), cpumask_bits(srcp), n, small_cpumask_bits); @@ -809,8 +821,8 @@ static inline void cpumask_shift_right(struct cpumask *dstp, * @srcp: the input to shift * @n: the number of bits to shift by */ -static inline void cpumask_shift_left(struct cpumask *dstp, - const struct cpumask *srcp, int n) +static __always_inline +void cpumask_shift_left(struct cpumask *dstp, const struct cpumask *srcp, int n) { bitmap_shift_left(cpumask_bits(dstp), cpumask_bits(srcp), n, nr_cpumask_bits); @@ -821,8 +833,8 @@ static inline void cpumask_shift_left(struct cpumask *dstp, * @dstp: the result * @srcp: the input cpumask */ -static inline void cpumask_copy(struct cpumask *dstp, - const struct cpumask *srcp) +static __always_inline +void cpumask_copy(struct cpumask *dstp, const struct cpumask *srcp) { bitmap_copy(cpumask_bits(dstp), cpumask_bits(srcp), large_cpumask_bits); } @@ -858,8 +870,8 @@ static inline void cpumask_copy(struct cpumask *dstp, * * Return: -errno, or 0 for success. */ -static inline int cpumask_parse_user(const char __user *buf, int len, - struct cpumask *dstp) +static __always_inline +int cpumask_parse_user(const char __user *buf, int len, struct cpumask *dstp) { return bitmap_parse_user(buf, len, cpumask_bits(dstp), nr_cpumask_bits); } @@ -872,8 +884,8 @@ static inline int cpumask_parse_user(const char __user *buf, int len, * * Return: -errno, or 0 for success. */ -static inline int cpumask_parselist_user(const char __user *buf, int len, - struct cpumask *dstp) +static __always_inline +int cpumask_parselist_user(const char __user *buf, int len, struct cpumask *dstp) { return bitmap_parselist_user(buf, len, cpumask_bits(dstp), nr_cpumask_bits); @@ -886,7 +898,7 @@ static inline int cpumask_parselist_user(const char __user *buf, int len, * * Return: -errno, or 0 for success. */ -static inline int cpumask_parse(const char *buf, struct cpumask *dstp) +static __always_inline int cpumask_parse(const char *buf, struct cpumask *dstp) { return bitmap_parse(buf, UINT_MAX, cpumask_bits(dstp), nr_cpumask_bits); } @@ -898,7 +910,7 @@ static inline int cpumask_parse(const char *buf, struct cpumask *dstp) * * Return: -errno, or 0 for success. */ -static inline int cpulist_parse(const char *buf, struct cpumask *dstp) +static __always_inline int cpulist_parse(const char *buf, struct cpumask *dstp) { return bitmap_parselist(buf, cpumask_bits(dstp), nr_cpumask_bits); } @@ -908,7 +920,7 @@ static inline int cpulist_parse(const char *buf, struct cpumask *dstp) * * Return: size to allocate for a &struct cpumask in bytes */ -static inline unsigned int cpumask_size(void) +static __always_inline unsigned int cpumask_size(void) { return bitmap_size(large_cpumask_bits); } @@ -920,7 +932,7 @@ static inline unsigned int cpumask_size(void) bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node); -static inline +static __always_inline bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) { return alloc_cpumask_var_node(mask, flags | __GFP_ZERO, node); @@ -938,13 +950,13 @@ bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) * * Return: %true if allocation succeeded, %false if not */ -static inline +static __always_inline bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { return alloc_cpumask_var_node(mask, flags, NUMA_NO_NODE); } -static inline +static __always_inline bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { return alloc_cpumask_var(mask, flags | __GFP_ZERO); @@ -954,7 +966,7 @@ void alloc_bootmem_cpumask_var(cpumask_var_t *mask); void free_cpumask_var(cpumask_var_t mask); void free_bootmem_cpumask_var(cpumask_var_t mask); -static inline bool cpumask_available(cpumask_var_t mask) +static __always_inline bool cpumask_available(cpumask_var_t mask) { return mask != NULL; } @@ -964,43 +976,43 @@ static inline bool cpumask_available(cpumask_var_t mask) #define this_cpu_cpumask_var_ptr(x) this_cpu_ptr(x) #define __cpumask_var_read_mostly -static inline bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) +static __always_inline bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { return true; } -static inline bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, +static __always_inline bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) { return true; } -static inline bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) +static __always_inline bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { cpumask_clear(*mask); return true; } -static inline bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, +static __always_inline bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) { cpumask_clear(*mask); return true; } -static inline void alloc_bootmem_cpumask_var(cpumask_var_t *mask) +static __always_inline void alloc_bootmem_cpumask_var(cpumask_var_t *mask) { } -static inline void free_cpumask_var(cpumask_var_t mask) +static __always_inline void free_cpumask_var(cpumask_var_t mask) { } -static inline void free_bootmem_cpumask_var(cpumask_var_t mask) +static __always_inline void free_bootmem_cpumask_var(cpumask_var_t mask) { } -static inline bool cpumask_available(cpumask_var_t mask) +static __always_inline bool cpumask_available(cpumask_var_t mask) { return true; } @@ -1058,7 +1070,7 @@ void set_cpu_online(unsigned int cpu, bool online); ((struct cpumask *)(1 ? (bitmap) \ : (void *)sizeof(__check_is_bitmap(bitmap)))) -static inline int __check_is_bitmap(const unsigned long *bitmap) +static __always_inline int __check_is_bitmap(const unsigned long *bitmap) { return 1; } @@ -1073,7 +1085,7 @@ static inline int __check_is_bitmap(const unsigned long *bitmap) extern const unsigned long cpu_bit_bitmap[BITS_PER_LONG+1][BITS_TO_LONGS(NR_CPUS)]; -static inline const struct cpumask *get_cpu_mask(unsigned int cpu) +static __always_inline const struct cpumask *get_cpu_mask(unsigned int cpu) { const unsigned long *p = cpu_bit_bitmap[1 + cpu % BITS_PER_LONG]; p -= cpu / BITS_PER_LONG; @@ -1100,32 +1112,32 @@ static __always_inline unsigned int num_online_cpus(void) #define num_present_cpus() cpumask_weight(cpu_present_mask) #define num_active_cpus() cpumask_weight(cpu_active_mask) -static inline bool cpu_online(unsigned int cpu) +static __always_inline bool cpu_online(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_online_mask); } -static inline bool cpu_enabled(unsigned int cpu) +static __always_inline bool cpu_enabled(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_enabled_mask); } -static inline bool cpu_possible(unsigned int cpu) +static __always_inline bool cpu_possible(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_possible_mask); } -static inline bool cpu_present(unsigned int cpu) +static __always_inline bool cpu_present(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_present_mask); } -static inline bool cpu_active(unsigned int cpu) +static __always_inline bool cpu_active(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_active_mask); } -static inline bool cpu_dying(unsigned int cpu) +static __always_inline bool cpu_dying(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_dying_mask); } @@ -1138,32 +1150,32 @@ static inline bool cpu_dying(unsigned int cpu) #define num_present_cpus() 1U #define num_active_cpus() 1U -static inline bool cpu_online(unsigned int cpu) +static __always_inline bool cpu_online(unsigned int cpu) { return cpu == 0; } -static inline bool cpu_possible(unsigned int cpu) +static __always_inline bool cpu_possible(unsigned int cpu) { return cpu == 0; } -static inline bool cpu_enabled(unsigned int cpu) +static __always_inline bool cpu_enabled(unsigned int cpu) { return cpu == 0; } -static inline bool cpu_present(unsigned int cpu) +static __always_inline bool cpu_present(unsigned int cpu) { return cpu == 0; } -static inline bool cpu_active(unsigned int cpu) +static __always_inline bool cpu_active(unsigned int cpu) { return cpu == 0; } -static inline bool cpu_dying(unsigned int cpu) +static __always_inline bool cpu_dying(unsigned int cpu) { return false; } @@ -1197,7 +1209,7 @@ static inline bool cpu_dying(unsigned int cpu) * Return: the length of the (null-terminated) @buf string, zero if * nothing is copied. */ -static inline ssize_t +static __always_inline ssize_t cpumap_print_to_pagebuf(bool list, char *buf, const struct cpumask *mask) { return bitmap_print_to_pagebuf(list, buf, cpumask_bits(mask), @@ -1220,9 +1232,9 @@ cpumap_print_to_pagebuf(bool list, char *buf, const struct cpumask *mask) * Return: the length of how many bytes have been copied, excluding * terminating '\0'. */ -static inline ssize_t -cpumap_print_bitmask_to_buf(char *buf, const struct cpumask *mask, - loff_t off, size_t count) +static __always_inline +ssize_t cpumap_print_bitmask_to_buf(char *buf, const struct cpumask *mask, + loff_t off, size_t count) { return bitmap_print_bitmask_to_buf(buf, cpumask_bits(mask), nr_cpu_ids, off, count) - 1; @@ -1242,9 +1254,9 @@ cpumap_print_bitmask_to_buf(char *buf, const struct cpumask *mask, * Return: the length of how many bytes have been copied, excluding * terminating '\0'. */ -static inline ssize_t -cpumap_print_list_to_buf(char *buf, const struct cpumask *mask, - loff_t off, size_t count) +static __always_inline +ssize_t cpumap_print_list_to_buf(char *buf, const struct cpumask *mask, + loff_t off, size_t count) { return bitmap_print_list_to_buf(buf, cpumask_bits(mask), nr_cpu_ids, off, count) - 1; diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index 30114c25ad12..ecf203f01034 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -21,7 +21,7 @@ #include <linux/netdevice.h> #include <linux/random.h> #include <linux/crc32.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <asm/bitsperlong.h> #ifdef __KERNEL__ diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h index 2944d4aa413b..b1c5722f2b3c 100644 --- a/include/linux/fdtable.h +++ b/include/linux/fdtable.h @@ -22,7 +22,6 @@ * as this is the granularity returned by copy_fdset(). */ #define NR_OPEN_DEFAULT BITS_PER_LONG -#define NR_OPEN_MAX ~0U struct fdtable { unsigned int max_fds; @@ -106,7 +105,10 @@ struct task_struct; void put_files_struct(struct files_struct *fs); int unshare_files(void); -struct files_struct *dup_fd(struct files_struct *, unsigned, int *) __latent_entropy; +struct fd_range { + unsigned int from, to; +}; +struct files_struct *dup_fd(struct files_struct *, struct fd_range *) __latent_entropy; void do_close_on_exec(struct files_struct *); int iterate_fd(struct files_struct *, unsigned, int (*)(const void *, struct file *, unsigned), @@ -115,8 +117,6 @@ int iterate_fd(struct files_struct *, unsigned, extern int close_fd(unsigned int fd); extern int __close_range(unsigned int fd, unsigned int max_fd, unsigned int flags); extern struct file *file_close_fd(unsigned int fd); -extern int unshare_fd(unsigned long unshare_flags, unsigned int max_fds, - struct files_struct **new_fdp); extern struct kmem_cache *files_cachep; diff --git a/include/linux/find.h b/include/linux/find.h index 5dfca4225fef..68685714bc18 100644 --- a/include/linux/find.h +++ b/include/linux/find.h @@ -52,7 +52,7 @@ unsigned long _find_next_bit_le(const unsigned long *addr, unsigned * Returns the bit number for the next set bit * If no bits are set, returns @size. */ -static inline +static __always_inline unsigned long find_next_bit(const unsigned long *addr, unsigned long size, unsigned long offset) { @@ -81,7 +81,7 @@ unsigned long find_next_bit(const unsigned long *addr, unsigned long size, * Returns the bit number for the next set bit * If no bits are set, returns @size. */ -static inline +static __always_inline unsigned long find_next_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long offset) @@ -112,7 +112,7 @@ unsigned long find_next_and_bit(const unsigned long *addr1, * Returns the bit number for the next set bit * If no bits are set, returns @size. */ -static inline +static __always_inline unsigned long find_next_andnot_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long offset) @@ -142,7 +142,7 @@ unsigned long find_next_andnot_bit(const unsigned long *addr1, * Returns the bit number for the next set bit * If no bits are set, returns @size. */ -static inline +static __always_inline unsigned long find_next_or_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long offset) @@ -171,7 +171,7 @@ unsigned long find_next_or_bit(const unsigned long *addr1, * Returns the bit number of the next zero bit * If no bits are zero, returns @size. */ -static inline +static __always_inline unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size, unsigned long offset) { @@ -198,7 +198,7 @@ unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size, * Returns the bit number of the first set bit. * If no bits are set, returns @size. */ -static inline +static __always_inline unsigned long find_first_bit(const unsigned long *addr, unsigned long size) { if (small_const_nbits(size)) { @@ -224,7 +224,7 @@ unsigned long find_first_bit(const unsigned long *addr, unsigned long size) * Returns the bit number of the N'th set bit. * If no such, returns >= @size. */ -static inline +static __always_inline unsigned long find_nth_bit(const unsigned long *addr, unsigned long size, unsigned long n) { if (n >= size) @@ -249,7 +249,7 @@ unsigned long find_nth_bit(const unsigned long *addr, unsigned long size, unsign * Returns the bit number of the N'th set bit. * If no such, returns @size. */ -static inline +static __always_inline unsigned long find_nth_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long n) { @@ -276,7 +276,7 @@ unsigned long find_nth_and_bit(const unsigned long *addr1, const unsigned long * * Returns the bit number of the N'th set bit. * If no such, returns @size. */ -static inline +static __always_inline unsigned long find_nth_andnot_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long n) { @@ -332,7 +332,7 @@ unsigned long find_nth_and_andnot_bit(const unsigned long *addr1, * Returns the bit number for the next set bit * If no bits are set, returns @size. */ -static inline +static __always_inline unsigned long find_first_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size) @@ -357,7 +357,7 @@ unsigned long find_first_and_bit(const unsigned long *addr1, * Returns the bit number for the first set bit * If no bits are set, returns @size. */ -static inline +static __always_inline unsigned long find_first_and_and_bit(const unsigned long *addr1, const unsigned long *addr2, const unsigned long *addr3, @@ -381,7 +381,7 @@ unsigned long find_first_and_and_bit(const unsigned long *addr1, * Returns the bit number of the first cleared bit. * If no bits are zero, returns @size. */ -static inline +static __always_inline unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size) { if (small_const_nbits(size)) { @@ -402,7 +402,7 @@ unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size) * * Returns the bit number of the last set bit, or size. */ -static inline +static __always_inline unsigned long find_last_bit(const unsigned long *addr, unsigned long size) { if (small_const_nbits(size)) { @@ -425,7 +425,7 @@ unsigned long find_last_bit(const unsigned long *addr, unsigned long size) * Returns the bit number for the next set bit, or first set bit up to @offset * If no bits are set, returns @size. */ -static inline +static __always_inline unsigned long find_next_and_bit_wrap(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long offset) @@ -448,7 +448,7 @@ unsigned long find_next_and_bit_wrap(const unsigned long *addr1, * Returns the bit number for the next set bit, or first set bit up to @offset * If no bits are set, returns @size. */ -static inline +static __always_inline unsigned long find_next_bit_wrap(const unsigned long *addr, unsigned long size, unsigned long offset) { @@ -465,7 +465,7 @@ unsigned long find_next_bit_wrap(const unsigned long *addr, * Helper for for_each_set_bit_wrap(). Make sure you're doing right thing * before using it alone. */ -static inline +static __always_inline unsigned long __for_each_wrap(const unsigned long *bitmap, unsigned long size, unsigned long start, unsigned long n) { @@ -506,20 +506,20 @@ extern unsigned long find_next_clump8(unsigned long *clump, #if defined(__LITTLE_ENDIAN) -static inline unsigned long find_next_zero_bit_le(const void *addr, - unsigned long size, unsigned long offset) +static __always_inline +unsigned long find_next_zero_bit_le(const void *addr, unsigned long size, unsigned long offset) { return find_next_zero_bit(addr, size, offset); } -static inline unsigned long find_next_bit_le(const void *addr, - unsigned long size, unsigned long offset) +static __always_inline +unsigned long find_next_bit_le(const void *addr, unsigned long size, unsigned long offset) { return find_next_bit(addr, size, offset); } -static inline unsigned long find_first_zero_bit_le(const void *addr, - unsigned long size) +static __always_inline +unsigned long find_first_zero_bit_le(const void *addr, unsigned long size) { return find_first_zero_bit(addr, size); } @@ -527,7 +527,7 @@ static inline unsigned long find_first_zero_bit_le(const void *addr, #elif defined(__BIG_ENDIAN) #ifndef find_next_zero_bit_le -static inline +static __always_inline unsigned long find_next_zero_bit_le(const void *addr, unsigned long size, unsigned long offset) { @@ -546,7 +546,7 @@ unsigned long find_next_zero_bit_le(const void *addr, unsigned #endif #ifndef find_first_zero_bit_le -static inline +static __always_inline unsigned long find_first_zero_bit_le(const void *addr, unsigned long size) { if (small_const_nbits(size)) { @@ -560,7 +560,7 @@ unsigned long find_first_zero_bit_le(const void *addr, unsigned long size) #endif #ifndef find_next_bit_le -static inline +static __always_inline unsigned long find_next_bit_le(const void *addr, unsigned long size, unsigned long offset) { diff --git a/include/linux/folio_queue.h b/include/linux/folio_queue.h index 955680c3bb5f..3abe614ef5f0 100644 --- a/include/linux/folio_queue.h +++ b/include/linux/folio_queue.h @@ -3,6 +3,12 @@ * * Copyright (C) 2024 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) + * + * See: + * + * Documentation/core-api/folio_queue.rst + * + * for a description of the API. */ #ifndef _LINUX_FOLIO_QUEUE_H @@ -33,6 +39,13 @@ struct folio_queue { #endif }; +/** + * folioq_init - Initialise a folio queue segment + * @folioq: The segment to initialise + * + * Initialise a folio queue segment. Note that the folio pointers are + * left uninitialised. + */ static inline void folioq_init(struct folio_queue *folioq) { folio_batch_init(&folioq->vec); @@ -43,62 +56,155 @@ static inline void folioq_init(struct folio_queue *folioq) folioq->marks3 = 0; } +/** + * folioq_nr_slots: Query the capacity of a folio queue segment + * @folioq: The segment to query + * + * Query the number of folios that a particular folio queue segment might hold. + * [!] NOTE: This must not be assumed to be the same for every segment! + */ static inline unsigned int folioq_nr_slots(const struct folio_queue *folioq) { return PAGEVEC_SIZE; } +/** + * folioq_count: Query the occupancy of a folio queue segment + * @folioq: The segment to query + * + * Query the number of folios that have been added to a folio queue segment. + * Note that this is not decreased as folios are removed from a segment. + */ static inline unsigned int folioq_count(struct folio_queue *folioq) { return folio_batch_count(&folioq->vec); } +/** + * folioq_full: Query if a folio queue segment is full + * @folioq: The segment to query + * + * Query if a folio queue segment is fully occupied. Note that this does not + * change if folios are removed from a segment. + */ static inline bool folioq_full(struct folio_queue *folioq) { //return !folio_batch_space(&folioq->vec); return folioq_count(folioq) >= folioq_nr_slots(folioq); } +/** + * folioq_is_marked: Check first folio mark in a folio queue segment + * @folioq: The segment to query + * @slot: The slot number of the folio to query + * + * Determine if the first mark is set for the folio in the specified slot in a + * folio queue segment. + */ static inline bool folioq_is_marked(const struct folio_queue *folioq, unsigned int slot) { return test_bit(slot, &folioq->marks); } +/** + * folioq_mark: Set the first mark on a folio in a folio queue segment + * @folioq: The segment to modify + * @slot: The slot number of the folio to modify + * + * Set the first mark for the folio in the specified slot in a folio queue + * segment. + */ static inline void folioq_mark(struct folio_queue *folioq, unsigned int slot) { set_bit(slot, &folioq->marks); } +/** + * folioq_unmark: Clear the first mark on a folio in a folio queue segment + * @folioq: The segment to modify + * @slot: The slot number of the folio to modify + * + * Clear the first mark for the folio in the specified slot in a folio queue + * segment. + */ static inline void folioq_unmark(struct folio_queue *folioq, unsigned int slot) { clear_bit(slot, &folioq->marks); } +/** + * folioq_is_marked2: Check second folio mark in a folio queue segment + * @folioq: The segment to query + * @slot: The slot number of the folio to query + * + * Determine if the second mark is set for the folio in the specified slot in a + * folio queue segment. + */ static inline bool folioq_is_marked2(const struct folio_queue *folioq, unsigned int slot) { return test_bit(slot, &folioq->marks2); } +/** + * folioq_mark2: Set the second mark on a folio in a folio queue segment + * @folioq: The segment to modify + * @slot: The slot number of the folio to modify + * + * Set the second mark for the folio in the specified slot in a folio queue + * segment. + */ static inline void folioq_mark2(struct folio_queue *folioq, unsigned int slot) { set_bit(slot, &folioq->marks2); } +/** + * folioq_unmark2: Clear the second mark on a folio in a folio queue segment + * @folioq: The segment to modify + * @slot: The slot number of the folio to modify + * + * Clear the second mark for the folio in the specified slot in a folio queue + * segment. + */ static inline void folioq_unmark2(struct folio_queue *folioq, unsigned int slot) { clear_bit(slot, &folioq->marks2); } +/** + * folioq_is_marked3: Check third folio mark in a folio queue segment + * @folioq: The segment to query + * @slot: The slot number of the folio to query + * + * Determine if the third mark is set for the folio in the specified slot in a + * folio queue segment. + */ static inline bool folioq_is_marked3(const struct folio_queue *folioq, unsigned int slot) { return test_bit(slot, &folioq->marks3); } +/** + * folioq_mark3: Set the third mark on a folio in a folio queue segment + * @folioq: The segment to modify + * @slot: The slot number of the folio to modify + * + * Set the third mark for the folio in the specified slot in a folio queue + * segment. + */ static inline void folioq_mark3(struct folio_queue *folioq, unsigned int slot) { set_bit(slot, &folioq->marks3); } +/** + * folioq_unmark3: Clear the third mark on a folio in a folio queue segment + * @folioq: The segment to modify + * @slot: The slot number of the folio to modify + * + * Clear the third mark for the folio in the specified slot in a folio queue + * segment. + */ static inline void folioq_unmark3(struct folio_queue *folioq, unsigned int slot) { clear_bit(slot, &folioq->marks3); @@ -111,6 +217,19 @@ static inline unsigned int __folio_order(struct folio *folio) return folio->_flags_1 & 0xff; } +/** + * folioq_append: Add a folio to a folio queue segment + * @folioq: The segment to add to + * @folio: The folio to add + * + * Add a folio to the tail of the sequence in a folio queue segment, increasing + * the occupancy count and returning the slot number for the folio just added. + * The folio size is extracted and stored in the queue and the marks are left + * unmodified. + * + * Note that it's left up to the caller to check that the segment capacity will + * not be exceeded and to extend the queue. + */ static inline unsigned int folioq_append(struct folio_queue *folioq, struct folio *folio) { unsigned int slot = folioq->vec.nr++; @@ -120,6 +239,19 @@ static inline unsigned int folioq_append(struct folio_queue *folioq, struct foli return slot; } +/** + * folioq_append_mark: Add a folio to a folio queue segment + * @folioq: The segment to add to + * @folio: The folio to add + * + * Add a folio to the tail of the sequence in a folio queue segment, increasing + * the occupancy count and returning the slot number for the folio just added. + * The folio size is extracted and stored in the queue, the first mark is set + * and and the second and third marks are left unmodified. + * + * Note that it's left up to the caller to check that the segment capacity will + * not be exceeded and to extend the queue. + */ static inline unsigned int folioq_append_mark(struct folio_queue *folioq, struct folio *folio) { unsigned int slot = folioq->vec.nr++; @@ -130,21 +262,57 @@ static inline unsigned int folioq_append_mark(struct folio_queue *folioq, struct return slot; } +/** + * folioq_folio: Get a folio from a folio queue segment + * @folioq: The segment to access + * @slot: The folio slot to access + * + * Retrieve the folio in the specified slot from a folio queue segment. Note + * that no bounds check is made and if the slot hasn't been added into yet, the + * pointer will be undefined. If the slot has been cleared, NULL will be + * returned. + */ static inline struct folio *folioq_folio(const struct folio_queue *folioq, unsigned int slot) { return folioq->vec.folios[slot]; } +/** + * folioq_folio_order: Get the order of a folio from a folio queue segment + * @folioq: The segment to access + * @slot: The folio slot to access + * + * Retrieve the order of the folio in the specified slot from a folio queue + * segment. Note that no bounds check is made and if the slot hasn't been + * added into yet, the order returned will be 0. + */ static inline unsigned int folioq_folio_order(const struct folio_queue *folioq, unsigned int slot) { return folioq->orders[slot]; } +/** + * folioq_folio_size: Get the size of a folio from a folio queue segment + * @folioq: The segment to access + * @slot: The folio slot to access + * + * Retrieve the size of the folio in the specified slot from a folio queue + * segment. Note that no bounds check is made and if the slot hasn't been + * added into yet, the size returned will be PAGE_SIZE. + */ static inline size_t folioq_folio_size(const struct folio_queue *folioq, unsigned int slot) { return PAGE_SIZE << folioq_folio_order(folioq, slot); } +/** + * folioq_clear: Clear a folio from a folio queue segment + * @folioq: The segment to clear + * @slot: The folio slot to clear + * + * Clear a folio from a sequence in a folio queue segment and clear its marks. + * The occupancy count is left unchanged. + */ static inline void folioq_clear(struct folio_queue *folioq, unsigned int slot) { folioq->vec.folios[slot] = NULL; diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 8be029bc50b1..3ecf7768e577 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -217,7 +217,6 @@ struct fsnotify_group { #define FSNOTIFY_GROUP_USER 0x01 /* user allocated group */ #define FSNOTIFY_GROUP_DUPS 0x02 /* allow multiple marks per object */ -#define FSNOTIFY_GROUP_NOFS 0x04 /* group lock is not direct reclaim safe */ int flags; unsigned int owner_flags; /* stored flags of mark_mutex owner */ @@ -268,22 +267,19 @@ struct fsnotify_group { static inline void fsnotify_group_lock(struct fsnotify_group *group) { mutex_lock(&group->mark_mutex); - if (group->flags & FSNOTIFY_GROUP_NOFS) - group->owner_flags = memalloc_nofs_save(); + group->owner_flags = memalloc_nofs_save(); } static inline void fsnotify_group_unlock(struct fsnotify_group *group) { - if (group->flags & FSNOTIFY_GROUP_NOFS) - memalloc_nofs_restore(group->owner_flags); + memalloc_nofs_restore(group->owner_flags); mutex_unlock(&group->mark_mutex); } static inline void fsnotify_group_assert_locked(struct fsnotify_group *group) { WARN_ON_ONCE(!mutex_is_locked(&group->mark_mutex)); - if (group->flags & FSNOTIFY_GROUP_NOFS) - WARN_ON_ONCE(!(current->flags & PF_MEMALLOC_NOFS)); + WARN_ON_ONCE(!(current->flags & PF_MEMALLOC_NOFS)); } /* When calling fsnotify tell it if the data is a path or inode */ diff --git a/include/linux/hdmi.h b/include/linux/hdmi.h index 3bb87bf6bc65..455f855bc084 100644 --- a/include/linux/hdmi.h +++ b/include/linux/hdmi.h @@ -59,6 +59,15 @@ enum hdmi_infoframe_type { #define HDMI_DRM_INFOFRAME_SIZE 26 #define HDMI_VENDOR_INFOFRAME_SIZE 4 +/* + * HDMI 1.3a table 5-14 states that the largest InfoFrame_length is 27, + * not including the packet header or checksum byte. We include the + * checksum byte in HDMI_INFOFRAME_HEADER_SIZE, so this should allow + * HDMI_INFOFRAME_SIZE(MAX) to be the largest buffer we could ever need + * for any HDMI infoframe. + */ +#define HDMI_MAX_INFOFRAME_SIZE 27 + #define HDMI_INFOFRAME_SIZE(type) \ (HDMI_INFOFRAME_HEADER_SIZE + HDMI_ ## type ## _INFOFRAME_SIZE) diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 30cef3b940eb..456bca45ff05 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -20,7 +20,7 @@ #include <linux/etherdevice.h> #include <linux/bitfield.h> #include <asm/byteorder.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /* * DS bit usage diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 0d5125a3e31a..db567d26f7b9 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1529,8 +1529,22 @@ static inline void kvm_create_vcpu_debugfs(struct kvm_vcpu *vcpu) {} #endif #ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING -int kvm_arch_hardware_enable(void); -void kvm_arch_hardware_disable(void); +/* + * kvm_arch_{enable,disable}_virtualization() are called on one CPU, under + * kvm_usage_lock, immediately after/before 0=>1 and 1=>0 transitions of + * kvm_usage_count, i.e. at the beginning of the generic hardware enabling + * sequence, and at the end of the generic hardware disabling sequence. + */ +void kvm_arch_enable_virtualization(void); +void kvm_arch_disable_virtualization(void); +/* + * kvm_arch_{enable,disable}_virtualization_cpu() are called on "every" CPU to + * do the actual twiddling of hardware bits. The hooks are called on all + * online CPUs when KVM enables/disabled virtualization, and on a single CPU + * when that CPU is onlined/offlined (including for Resume/Suspend). + */ +int kvm_arch_enable_virtualization_cpu(void); +void kvm_arch_disable_virtualization_cpu(void); #endif int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu); bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu); diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 97f6de69f616..96d369112bfa 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -2138,7 +2138,7 @@ struct mlx5_ifc_cmd_hca_cap_2_bits { u8 ts_cqe_metadata_size2wqe_counter[0x5]; u8 reserved_at_250[0x10]; - u8 reserved_at_260[0x120]; + u8 reserved_at_260[0x20]; u8 format_select_dw_gtpu_dw_0[0x8]; u8 format_select_dw_gtpu_dw_1[0x8]; diff --git a/include/linux/mtd/map.h b/include/linux/mtd/map.h index b4fa92a6e44b..1b56796f6cb3 100644 --- a/include/linux/mtd/map.h +++ b/include/linux/mtd/map.h @@ -15,7 +15,7 @@ #include <linux/kernel.h> #include <linux/io.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <asm/barrier.h> #ifdef CONFIG_MTD_MAP_BANK_WIDTH_1 diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index e87b5e488325..4d20c776a4ff 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -5029,6 +5029,24 @@ void netif_set_tso_max_segs(struct net_device *dev, unsigned int segs); void netif_inherit_tso_max(struct net_device *to, const struct net_device *from); +static inline unsigned int +netif_get_gro_max_size(const struct net_device *dev, const struct sk_buff *skb) +{ + /* pairs with WRITE_ONCE() in netif_set_gro(_ipv4)_max_size() */ + return skb->protocol == htons(ETH_P_IPV6) ? + READ_ONCE(dev->gro_max_size) : + READ_ONCE(dev->gro_ipv4_max_size); +} + +static inline unsigned int +netif_get_gso_max_size(const struct net_device *dev, const struct sk_buff *skb) +{ + /* pairs with WRITE_ONCE() in netif_set_gso(_ipv4)_max_size() */ + return skb->protocol == htons(ETH_P_IPV6) ? + READ_ONCE(dev->gso_max_size) : + READ_ONCE(dev->gso_ipv4_max_size); +} + static inline bool netif_is_macsec(const struct net_device *dev) { return dev->priv_flags & IFF_MACSEC; diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h index b61438313a73..9fd7a0ce9c1a 100644 --- a/include/linux/nodemask.h +++ b/include/linux/nodemask.h @@ -107,11 +107,11 @@ extern nodemask_t _unused_nodemask_arg_; */ #define nodemask_pr_args(maskp) __nodemask_pr_numnodes(maskp), \ __nodemask_pr_bits(maskp) -static inline unsigned int __nodemask_pr_numnodes(const nodemask_t *m) +static __always_inline unsigned int __nodemask_pr_numnodes(const nodemask_t *m) { return m ? MAX_NUMNODES : 0; } -static inline const unsigned long *__nodemask_pr_bits(const nodemask_t *m) +static __always_inline const unsigned long *__nodemask_pr_bits(const nodemask_t *m) { return m ? m->bits : NULL; } @@ -132,19 +132,19 @@ static __always_inline void __node_set(int node, volatile nodemask_t *dstp) } #define node_clear(node, dst) __node_clear((node), &(dst)) -static inline void __node_clear(int node, volatile nodemask_t *dstp) +static __always_inline void __node_clear(int node, volatile nodemask_t *dstp) { clear_bit(node, dstp->bits); } #define nodes_setall(dst) __nodes_setall(&(dst), MAX_NUMNODES) -static inline void __nodes_setall(nodemask_t *dstp, unsigned int nbits) +static __always_inline void __nodes_setall(nodemask_t *dstp, unsigned int nbits) { bitmap_fill(dstp->bits, nbits); } #define nodes_clear(dst) __nodes_clear(&(dst), MAX_NUMNODES) -static inline void __nodes_clear(nodemask_t *dstp, unsigned int nbits) +static __always_inline void __nodes_clear(nodemask_t *dstp, unsigned int nbits) { bitmap_zero(dstp->bits, nbits); } @@ -154,14 +154,14 @@ static inline void __nodes_clear(nodemask_t *dstp, unsigned int nbits) #define node_test_and_set(node, nodemask) \ __node_test_and_set((node), &(nodemask)) -static inline bool __node_test_and_set(int node, nodemask_t *addr) +static __always_inline bool __node_test_and_set(int node, nodemask_t *addr) { return test_and_set_bit(node, addr->bits); } #define nodes_and(dst, src1, src2) \ __nodes_and(&(dst), &(src1), &(src2), MAX_NUMNODES) -static inline void __nodes_and(nodemask_t *dstp, const nodemask_t *src1p, +static __always_inline void __nodes_and(nodemask_t *dstp, const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { bitmap_and(dstp->bits, src1p->bits, src2p->bits, nbits); @@ -169,7 +169,7 @@ static inline void __nodes_and(nodemask_t *dstp, const nodemask_t *src1p, #define nodes_or(dst, src1, src2) \ __nodes_or(&(dst), &(src1), &(src2), MAX_NUMNODES) -static inline void __nodes_or(nodemask_t *dstp, const nodemask_t *src1p, +static __always_inline void __nodes_or(nodemask_t *dstp, const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { bitmap_or(dstp->bits, src1p->bits, src2p->bits, nbits); @@ -177,7 +177,7 @@ static inline void __nodes_or(nodemask_t *dstp, const nodemask_t *src1p, #define nodes_xor(dst, src1, src2) \ __nodes_xor(&(dst), &(src1), &(src2), MAX_NUMNODES) -static inline void __nodes_xor(nodemask_t *dstp, const nodemask_t *src1p, +static __always_inline void __nodes_xor(nodemask_t *dstp, const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { bitmap_xor(dstp->bits, src1p->bits, src2p->bits, nbits); @@ -185,7 +185,7 @@ static inline void __nodes_xor(nodemask_t *dstp, const nodemask_t *src1p, #define nodes_andnot(dst, src1, src2) \ __nodes_andnot(&(dst), &(src1), &(src2), MAX_NUMNODES) -static inline void __nodes_andnot(nodemask_t *dstp, const nodemask_t *src1p, +static __always_inline void __nodes_andnot(nodemask_t *dstp, const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { bitmap_andnot(dstp->bits, src1p->bits, src2p->bits, nbits); @@ -193,7 +193,7 @@ static inline void __nodes_andnot(nodemask_t *dstp, const nodemask_t *src1p, #define nodes_complement(dst, src) \ __nodes_complement(&(dst), &(src), MAX_NUMNODES) -static inline void __nodes_complement(nodemask_t *dstp, +static __always_inline void __nodes_complement(nodemask_t *dstp, const nodemask_t *srcp, unsigned int nbits) { bitmap_complement(dstp->bits, srcp->bits, nbits); @@ -201,7 +201,7 @@ static inline void __nodes_complement(nodemask_t *dstp, #define nodes_equal(src1, src2) \ __nodes_equal(&(src1), &(src2), MAX_NUMNODES) -static inline bool __nodes_equal(const nodemask_t *src1p, +static __always_inline bool __nodes_equal(const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { return bitmap_equal(src1p->bits, src2p->bits, nbits); @@ -209,7 +209,7 @@ static inline bool __nodes_equal(const nodemask_t *src1p, #define nodes_intersects(src1, src2) \ __nodes_intersects(&(src1), &(src2), MAX_NUMNODES) -static inline bool __nodes_intersects(const nodemask_t *src1p, +static __always_inline bool __nodes_intersects(const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { return bitmap_intersects(src1p->bits, src2p->bits, nbits); @@ -217,33 +217,33 @@ static inline bool __nodes_intersects(const nodemask_t *src1p, #define nodes_subset(src1, src2) \ __nodes_subset(&(src1), &(src2), MAX_NUMNODES) -static inline bool __nodes_subset(const nodemask_t *src1p, +static __always_inline bool __nodes_subset(const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { return bitmap_subset(src1p->bits, src2p->bits, nbits); } #define nodes_empty(src) __nodes_empty(&(src), MAX_NUMNODES) -static inline bool __nodes_empty(const nodemask_t *srcp, unsigned int nbits) +static __always_inline bool __nodes_empty(const nodemask_t *srcp, unsigned int nbits) { return bitmap_empty(srcp->bits, nbits); } #define nodes_full(nodemask) __nodes_full(&(nodemask), MAX_NUMNODES) -static inline bool __nodes_full(const nodemask_t *srcp, unsigned int nbits) +static __always_inline bool __nodes_full(const nodemask_t *srcp, unsigned int nbits) { return bitmap_full(srcp->bits, nbits); } #define nodes_weight(nodemask) __nodes_weight(&(nodemask), MAX_NUMNODES) -static inline int __nodes_weight(const nodemask_t *srcp, unsigned int nbits) +static __always_inline int __nodes_weight(const nodemask_t *srcp, unsigned int nbits) { return bitmap_weight(srcp->bits, nbits); } #define nodes_shift_right(dst, src, n) \ __nodes_shift_right(&(dst), &(src), (n), MAX_NUMNODES) -static inline void __nodes_shift_right(nodemask_t *dstp, +static __always_inline void __nodes_shift_right(nodemask_t *dstp, const nodemask_t *srcp, int n, int nbits) { bitmap_shift_right(dstp->bits, srcp->bits, n, nbits); @@ -251,7 +251,7 @@ static inline void __nodes_shift_right(nodemask_t *dstp, #define nodes_shift_left(dst, src, n) \ __nodes_shift_left(&(dst), &(src), (n), MAX_NUMNODES) -static inline void __nodes_shift_left(nodemask_t *dstp, +static __always_inline void __nodes_shift_left(nodemask_t *dstp, const nodemask_t *srcp, int n, int nbits) { bitmap_shift_left(dstp->bits, srcp->bits, n, nbits); @@ -261,13 +261,13 @@ static inline void __nodes_shift_left(nodemask_t *dstp, > MAX_NUMNODES, then the silly min_ts could be dropped. */ #define first_node(src) __first_node(&(src)) -static inline unsigned int __first_node(const nodemask_t *srcp) +static __always_inline unsigned int __first_node(const nodemask_t *srcp) { return min_t(unsigned int, MAX_NUMNODES, find_first_bit(srcp->bits, MAX_NUMNODES)); } #define next_node(n, src) __next_node((n), &(src)) -static inline unsigned int __next_node(int n, const nodemask_t *srcp) +static __always_inline unsigned int __next_node(int n, const nodemask_t *srcp) { return min_t(unsigned int, MAX_NUMNODES, find_next_bit(srcp->bits, MAX_NUMNODES, n+1)); } @@ -277,7 +277,7 @@ static inline unsigned int __next_node(int n, const nodemask_t *srcp) * the first node in src if needed. Returns MAX_NUMNODES if src is empty. */ #define next_node_in(n, src) __next_node_in((n), &(src)) -static inline unsigned int __next_node_in(int node, const nodemask_t *srcp) +static __always_inline unsigned int __next_node_in(int node, const nodemask_t *srcp) { unsigned int ret = __next_node(node, srcp); @@ -286,7 +286,7 @@ static inline unsigned int __next_node_in(int node, const nodemask_t *srcp) return ret; } -static inline void init_nodemask_of_node(nodemask_t *mask, int node) +static __always_inline void init_nodemask_of_node(nodemask_t *mask, int node) { nodes_clear(*mask); node_set(node, *mask); @@ -304,7 +304,7 @@ static inline void init_nodemask_of_node(nodemask_t *mask, int node) }) #define first_unset_node(mask) __first_unset_node(&(mask)) -static inline unsigned int __first_unset_node(const nodemask_t *maskp) +static __always_inline unsigned int __first_unset_node(const nodemask_t *maskp) { return min_t(unsigned int, MAX_NUMNODES, find_first_zero_bit(maskp->bits, MAX_NUMNODES)); @@ -338,21 +338,21 @@ static inline unsigned int __first_unset_node(const nodemask_t *maskp) #define nodemask_parse_user(ubuf, ulen, dst) \ __nodemask_parse_user((ubuf), (ulen), &(dst), MAX_NUMNODES) -static inline int __nodemask_parse_user(const char __user *buf, int len, +static __always_inline int __nodemask_parse_user(const char __user *buf, int len, nodemask_t *dstp, int nbits) { return bitmap_parse_user(buf, len, dstp->bits, nbits); } #define nodelist_parse(buf, dst) __nodelist_parse((buf), &(dst), MAX_NUMNODES) -static inline int __nodelist_parse(const char *buf, nodemask_t *dstp, int nbits) +static __always_inline int __nodelist_parse(const char *buf, nodemask_t *dstp, int nbits) { return bitmap_parselist(buf, dstp->bits, nbits); } #define node_remap(oldbit, old, new) \ __node_remap((oldbit), &(old), &(new), MAX_NUMNODES) -static inline int __node_remap(int oldbit, +static __always_inline int __node_remap(int oldbit, const nodemask_t *oldp, const nodemask_t *newp, int nbits) { return bitmap_bitremap(oldbit, oldp->bits, newp->bits, nbits); @@ -360,7 +360,7 @@ static inline int __node_remap(int oldbit, #define nodes_remap(dst, src, old, new) \ __nodes_remap(&(dst), &(src), &(old), &(new), MAX_NUMNODES) -static inline void __nodes_remap(nodemask_t *dstp, const nodemask_t *srcp, +static __always_inline void __nodes_remap(nodemask_t *dstp, const nodemask_t *srcp, const nodemask_t *oldp, const nodemask_t *newp, int nbits) { bitmap_remap(dstp->bits, srcp->bits, oldp->bits, newp->bits, nbits); @@ -368,7 +368,7 @@ static inline void __nodes_remap(nodemask_t *dstp, const nodemask_t *srcp, #define nodes_onto(dst, orig, relmap) \ __nodes_onto(&(dst), &(orig), &(relmap), MAX_NUMNODES) -static inline void __nodes_onto(nodemask_t *dstp, const nodemask_t *origp, +static __always_inline void __nodes_onto(nodemask_t *dstp, const nodemask_t *origp, const nodemask_t *relmapp, int nbits) { bitmap_onto(dstp->bits, origp->bits, relmapp->bits, nbits); @@ -376,7 +376,7 @@ static inline void __nodes_onto(nodemask_t *dstp, const nodemask_t *origp, #define nodes_fold(dst, orig, sz) \ __nodes_fold(&(dst), &(orig), sz, MAX_NUMNODES) -static inline void __nodes_fold(nodemask_t *dstp, const nodemask_t *origp, +static __always_inline void __nodes_fold(nodemask_t *dstp, const nodemask_t *origp, int sz, int nbits) { bitmap_fold(dstp->bits, origp->bits, sz, nbits); @@ -418,22 +418,22 @@ enum node_states { extern nodemask_t node_states[NR_NODE_STATES]; #if MAX_NUMNODES > 1 -static inline int node_state(int node, enum node_states state) +static __always_inline int node_state(int node, enum node_states state) { return node_isset(node, node_states[state]); } -static inline void node_set_state(int node, enum node_states state) +static __always_inline void node_set_state(int node, enum node_states state) { __node_set(node, &node_states[state]); } -static inline void node_clear_state(int node, enum node_states state) +static __always_inline void node_clear_state(int node, enum node_states state) { __node_clear(node, &node_states[state]); } -static inline int num_node_state(enum node_states state) +static __always_inline int num_node_state(enum node_states state) { return nodes_weight(node_states[state]); } @@ -443,11 +443,11 @@ static inline int num_node_state(enum node_states state) #define first_online_node first_node(node_states[N_ONLINE]) #define first_memory_node first_node(node_states[N_MEMORY]) -static inline unsigned int next_online_node(int nid) +static __always_inline unsigned int next_online_node(int nid) { return next_node(nid, node_states[N_ONLINE]); } -static inline unsigned int next_memory_node(int nid) +static __always_inline unsigned int next_memory_node(int nid) { return next_node(nid, node_states[N_MEMORY]); } @@ -455,13 +455,13 @@ static inline unsigned int next_memory_node(int nid) extern unsigned int nr_node_ids; extern unsigned int nr_online_nodes; -static inline void node_set_online(int nid) +static __always_inline void node_set_online(int nid) { node_set_state(nid, N_ONLINE); nr_online_nodes = num_node_state(N_ONLINE); } -static inline void node_set_offline(int nid) +static __always_inline void node_set_offline(int nid) { node_clear_state(nid, N_ONLINE); nr_online_nodes = num_node_state(N_ONLINE); @@ -469,20 +469,20 @@ static inline void node_set_offline(int nid) #else -static inline int node_state(int node, enum node_states state) +static __always_inline int node_state(int node, enum node_states state) { return node == 0; } -static inline void node_set_state(int node, enum node_states state) +static __always_inline void node_set_state(int node, enum node_states state) { } -static inline void node_clear_state(int node, enum node_states state) +static __always_inline void node_clear_state(int node, enum node_states state) { } -static inline int num_node_state(enum node_states state) +static __always_inline int num_node_state(enum node_states state) { return 1; } @@ -502,7 +502,7 @@ static inline int num_node_state(enum node_states state) #endif -static inline int node_random(const nodemask_t *maskp) +static __always_inline int node_random(const nodemask_t *maskp) { #if defined(CONFIG_NUMA) && (MAX_NUMNODES > 1) int w, bit; diff --git a/include/linux/ptp_classify.h b/include/linux/ptp_classify.h index 1b5a953c6bbc..3a74f69e0b59 100644 --- a/include/linux/ptp_classify.h +++ b/include/linux/ptp_classify.h @@ -10,7 +10,7 @@ #ifndef _PTP_CLASSIFY_H_ #define _PTP_CLASSIFY_H_ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/ip.h> #include <linux/ktime.h> #include <linux/skbuff.h> diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index 2f8dc47f1eb0..5f775e104f9a 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -13,7 +13,7 @@ #include <linux/uio.h> #include <asm/byteorder.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/scatterlist.h> struct bio_vec; diff --git a/include/linux/tpm.h b/include/linux/tpm.h index e93ee8d936a9..587b96b4418e 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -537,7 +537,7 @@ int tpm_buf_check_hmac_response(struct tpm_chip *chip, struct tpm_buf *buf, int rc); void tpm2_end_auth_session(struct tpm_chip *chip); #else -#include <asm/unaligned.h> +#include <linux/unaligned.h> static inline int tpm2_start_auth_session(struct tpm_chip *chip) { diff --git a/include/asm-generic/unaligned.h b/include/linux/unaligned.h index 95acdd70b3b2..4a9651017e3c 100644 --- a/include/asm-generic/unaligned.h +++ b/include/linux/unaligned.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __ASM_GENERIC_UNALIGNED_H -#define __ASM_GENERIC_UNALIGNED_H +#ifndef __LINUX_UNALIGNED_H +#define __LINUX_UNALIGNED_H /* * This is the most generic implementation of unaligned accesses @@ -143,4 +143,4 @@ static inline u64 get_unaligned_be48(const void *p) return __get_unaligned_be48(p); } -#endif /* __ASM_GENERIC_UNALIGNED_H */ +#endif /* __LINUX_UNALIGNED_H */ diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index 276ca543ef44..02a9f4dc594d 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -103,8 +103,10 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, if (!skb_partial_csum_set(skb, start, off)) return -EINVAL; + if (skb_transport_offset(skb) < nh_min_len) + return -EINVAL; - nh_min_len = max_t(u32, nh_min_len, skb_transport_offset(skb)); + nh_min_len = skb_transport_offset(skb); p_off = nh_min_len + thlen; if (!pskb_may_pull(skb, p_off)) return -EINVAL; diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h index 313d0b972e06..d9c767cf773d 100644 --- a/include/net/bluetooth/l2cap.h +++ b/include/net/bluetooth/l2cap.h @@ -27,7 +27,7 @@ #ifndef __L2CAP_H #define __L2CAP_H -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/atomic.h> /* L2CAP defaults */ diff --git a/include/net/calipso.h b/include/net/calipso.h index f8667a3fda9e..76b9e08c10c2 100644 --- a/include/net/calipso.h +++ b/include/net/calipso.h @@ -25,7 +25,7 @@ #include <net/netlabel.h> #include <net/request_sock.h> #include <linux/refcount.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /* known doi values */ #define CALIPSO_DOI_UNKNOWN 0x00000000 diff --git a/include/net/cipso_ipv4.h b/include/net/cipso_ipv4.h index c9111bb2f59b..d6780d7903f4 100644 --- a/include/net/cipso_ipv4.h +++ b/include/net/cipso_ipv4.h @@ -28,7 +28,7 @@ #include <net/request_sock.h> #include <linux/atomic.h> #include <linux/refcount.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /* known doi values */ #define CIPSO_V4_DOI_UNKNOWN 0x00000000 diff --git a/include/net/ieee80211_radiotap.h b/include/net/ieee80211_radiotap.h index 91762faecc13..02fbc036f34e 100644 --- a/include/net/ieee80211_radiotap.h +++ b/include/net/ieee80211_radiotap.h @@ -18,7 +18,7 @@ #define __RADIOTAP_H #include <linux/kernel.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /** * struct ieee80211_radiotap_header - base radiotap header diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 954dff901b69..333e0fae6796 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -22,7 +22,7 @@ #include <net/cfg80211.h> #include <net/codel.h> #include <net/ieee80211_radiotap.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /** * DOC: Introduction diff --git a/include/net/mac802154.h b/include/net/mac802154.h index 1b5488fa2ff0..d72006a85f02 100644 --- a/include/net/mac802154.h +++ b/include/net/mac802154.h @@ -7,7 +7,7 @@ #ifndef NET_MAC802154_H #define NET_MAC802154_H -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <net/af_ieee802154.h> #include <linux/ieee802154.h> #include <linux/skbuff.h> diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 49708e7e1339..91ae20cb7648 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -2,7 +2,7 @@ #ifndef _NET_NF_TABLES_H #define _NET_NF_TABLES_H -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/list.h> #include <linux/netfilter.h> #include <linux/netfilter/nfnetlink.h> diff --git a/include/rdma/ib_hdrs.h b/include/rdma/ib_hdrs.h index 8ae07c0ecdf7..1c4c1a69937a 100644 --- a/include/rdma/ib_hdrs.h +++ b/include/rdma/ib_hdrs.h @@ -7,7 +7,7 @@ #define IB_HDRS_H #include <linux/types.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <rdma/ib_verbs.h> #define IB_SEQ_NAK (3 << 29) diff --git a/include/rdma/iba.h b/include/rdma/iba.h index 6a1115b02a0d..dcae154edc26 100644 --- a/include/rdma/iba.h +++ b/include/rdma/iba.h @@ -7,7 +7,7 @@ #include <linux/kernel.h> #include <linux/bitfield.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> static inline u32 _iba_get8(const u8 *ptr) { diff --git a/include/scsi/scsi_transport_fc.h b/include/scsi/scsi_transport_fc.h index 8e6c60090c62..d02b55261307 100644 --- a/include/scsi/scsi_transport_fc.h +++ b/include/scsi/scsi_transport_fc.h @@ -12,7 +12,7 @@ #include <linux/sched.h> #include <linux/bsg-lib.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <scsi/scsi.h> #include <scsi/scsi_netlink.h> #include <scsi/scsi_host.h> diff --git a/include/sound/hdaudio.h b/include/sound/hdaudio.h index 7e39d486374a..b098ceadbe74 100644 --- a/include/sound/hdaudio.h +++ b/include/sound/hdaudio.h @@ -590,7 +590,7 @@ void snd_hdac_stream_sync_trigger(struct hdac_stream *azx_dev, bool set, void snd_hdac_stream_sync(struct hdac_stream *azx_dev, bool start, unsigned int streams); void snd_hdac_stream_timecounter_init(struct hdac_stream *azx_dev, - unsigned int streams); + unsigned int streams, bool start); int snd_hdac_get_stream_stripe_ctl(struct hdac_bus *bus, struct snd_pcm_substream *substream); diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h index 739df993aa5e..4063a701081b 100644 --- a/include/target/target_core_backend.h +++ b/include/target/target_core_backend.h @@ -3,7 +3,7 @@ #define TARGET_CORE_BACKEND_H #include <linux/types.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <target/target_core_base.h> #define TRANSPORT_FLAG_PASSTHROUGH 0x1 diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h index bf60ad50011e..af6b3827fb1d 100644 --- a/include/trace/events/btrfs.h +++ b/include/trace/events/btrfs.h @@ -1716,7 +1716,7 @@ DECLARE_EVENT_CLASS(btrfs_qgroup_extent, ), TP_fast_assign_btrfs(fs_info, - __entry->bytenr = rec->bytenr, + __entry->bytenr = rec->bytenr; __entry->num_bytes = rec->num_bytes; ), diff --git a/include/trace/events/dma.h b/include/trace/events/dma.h index f57f05331d73..569f86a44aaa 100644 --- a/include/trace/events/dma.h +++ b/include/trace/events/dma.h @@ -176,9 +176,9 @@ TRACE_EVENT(dma_free, ); TRACE_EVENT(dma_map_sg, - TP_PROTO(struct device *dev, struct scatterlist *sg, int nents, + TP_PROTO(struct device *dev, struct scatterlist *sgl, int nents, int ents, enum dma_data_direction dir, unsigned long attrs), - TP_ARGS(dev, sg, nents, ents, dir, attrs), + TP_ARGS(dev, sgl, nents, ents, dir, attrs), TP_STRUCT__entry( __string(device, dev_name(dev)) @@ -190,17 +190,17 @@ TRACE_EVENT(dma_map_sg, ), TP_fast_assign( + struct scatterlist *sg; int i; __assign_str(device); - for (i = 0; i < nents; i++) - ((u64 *)__get_dynamic_array(phys_addrs))[i] = - sg_phys(sg + i); - for (i = 0; i < ents; i++) { + for_each_sg(sgl, sg, nents, i) + ((u64 *)__get_dynamic_array(phys_addrs))[i] = sg_phys(sg); + for_each_sg(sgl, sg, ents, i) { ((u64 *)__get_dynamic_array(dma_addrs))[i] = - sg_dma_address(sg + i); + sg_dma_address(sg); ((unsigned int *)__get_dynamic_array(lengths))[i] = - sg_dma_len(sg + i); + sg_dma_len(sg); } __entry->dir = dir; __entry->attrs = attrs; @@ -222,9 +222,9 @@ TRACE_EVENT(dma_map_sg, ); TRACE_EVENT(dma_unmap_sg, - TP_PROTO(struct device *dev, struct scatterlist *sg, int nents, + TP_PROTO(struct device *dev, struct scatterlist *sgl, int nents, enum dma_data_direction dir, unsigned long attrs), - TP_ARGS(dev, sg, nents, dir, attrs), + TP_ARGS(dev, sgl, nents, dir, attrs), TP_STRUCT__entry( __string(device, dev_name(dev)) @@ -234,12 +234,12 @@ TRACE_EVENT(dma_unmap_sg, ), TP_fast_assign( + struct scatterlist *sg; int i; __assign_str(device); - for (i = 0; i < nents; i++) - ((u64 *)__get_dynamic_array(addrs))[i] = - sg_phys(sg + i); + for_each_sg(sgl, sg, nents, i) + ((u64 *)__get_dynamic_array(addrs))[i] = sg_phys(sg); __entry->dir = dir; __entry->attrs = attrs; ), @@ -290,9 +290,9 @@ DEFINE_EVENT(dma_sync_single, dma_sync_single_for_device, TP_ARGS(dev, dma_addr, size, dir)); DECLARE_EVENT_CLASS(dma_sync_sg, - TP_PROTO(struct device *dev, struct scatterlist *sg, int nents, + TP_PROTO(struct device *dev, struct scatterlist *sgl, int nents, enum dma_data_direction dir), - TP_ARGS(dev, sg, nents, dir), + TP_ARGS(dev, sgl, nents, dir), TP_STRUCT__entry( __string(device, dev_name(dev)) @@ -302,14 +302,15 @@ DECLARE_EVENT_CLASS(dma_sync_sg, ), TP_fast_assign( + struct scatterlist *sg; int i; __assign_str(device); - for (i = 0; i < nents; i++) { + for_each_sg(sgl, sg, nents, i) { ((u64 *)__get_dynamic_array(dma_addrs))[i] = - sg_dma_address(sg + i); + sg_dma_address(sg); ((unsigned int *)__get_dynamic_array(lengths))[i] = - sg_dma_len(sg + i); + sg_dma_len(sg); } __entry->dir = dir; ), diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h index 76bd42a96815..1d7c52821e55 100644 --- a/include/trace/events/netfs.h +++ b/include/trace/events/netfs.h @@ -448,7 +448,8 @@ TRACE_EVENT(netfs_folio, ), TP_fast_assign( - __entry->ino = folio->mapping->host->i_ino; + struct address_space *__m = READ_ONCE(folio->mapping); + __entry->ino = __m ? __m->host->i_ino : 0; __entry->why = why; __entry->index = folio_index(folio); __entry->nr = folio_nr_pages(folio); diff --git a/include/uapi/linux/bits.h b/include/uapi/linux/bits.h index 3c2a101986a3..5ee30f882736 100644 --- a/include/uapi/linux/bits.h +++ b/include/uapi/linux/bits.h @@ -12,4 +12,7 @@ (((~_ULL(0)) - (_ULL(1) << (l)) + 1) & \ (~_ULL(0) >> (__BITS_PER_LONG_LONG - 1 - (h)))) +#define __GENMASK_U128(h, l) \ + ((_BIT128((h)) << 1) - (_BIT128(l))) + #endif /* _UAPI_LINUX_BITS_H */ diff --git a/include/uapi/linux/const.h b/include/uapi/linux/const.h index a429381e7ca5..e16be0d37746 100644 --- a/include/uapi/linux/const.h +++ b/include/uapi/linux/const.h @@ -28,6 +28,23 @@ #define _BITUL(x) (_UL(1) << (x)) #define _BITULL(x) (_ULL(1) << (x)) +#if !defined(__ASSEMBLY__) +/* + * Missing asm support + * + * __BIT128() would not work in the asm code, as it shifts an + * 'unsigned __init128' data type as direct representation of + * 128 bit constants is not supported in the gcc compiler, as + * they get silently truncated. + * + * TODO: Please revisit this implementation when gcc compiler + * starts representing 128 bit constants directly like long + * and unsigned long etc. Subsequently drop the comment for + * GENMASK_U128() which would then start supporting asm code. + */ +#define _BIT128(x) ((unsigned __int128)(1) << (x)) +#endif + #define __ALIGN_KERNEL(x, a) __ALIGN_KERNEL_MASK(x, (__typeof__(x))(a) - 1) #define __ALIGN_KERNEL_MASK(x, mask) (((x) + (mask)) & ~(mask)) diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index d6476ca5d7a6..9e9079321380 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -1694,7 +1694,7 @@ enum nft_flowtable_flags { * * @NFTA_FLOWTABLE_TABLE: name of the table containing the expression (NLA_STRING) * @NFTA_FLOWTABLE_NAME: name of this flow table (NLA_STRING) - * @NFTA_FLOWTABLE_HOOK: netfilter hook configuration(NLA_U32) + * @NFTA_FLOWTABLE_HOOK: netfilter hook configuration (NLA_NESTED) * @NFTA_FLOWTABLE_USE: number of references to this flow table (NLA_U32) * @NFTA_FLOWTABLE_HANDLE: object handle (NLA_U64) * @NFTA_FLOWTABLE_FLAGS: flags (NLA_U32) diff --git a/init/Kconfig b/init/Kconfig index fbd0cb06a50a..530a382ee0fe 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1946,10 +1946,11 @@ config RUST depends on !GCC_PLUGIN_RANDSTRUCT depends on !RANDSTRUCT depends on !DEBUG_INFO_BTF || PAHOLE_HAS_LANG_EXCLUDE - depends on !CFI_CLANG || RUSTC_VERSION >= 107900 && $(cc-option,-fsanitize=kcfi -fsanitize-cfi-icall-experimental-normalize-integers) + depends on !CFI_CLANG || RUSTC_VERSION >= 107900 && HAVE_CFI_ICALL_NORMALIZE_INTEGERS select CFI_ICALL_NORMALIZE_INTEGERS if CFI_CLANG - depends on !CALL_PADDING || RUSTC_VERSION >= 108000 + depends on !CALL_PADDING || RUSTC_VERSION >= 108100 depends on !KASAN_SW_TAGS + depends on !(MITIGATION_RETHUNK && KASAN) || RUSTC_VERSION >= 108300 help Enables Rust support in the kernel. diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index feb61d68dca6..b2736e3491b8 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -321,7 +321,7 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) sizeof(struct io_kiocb)); ret |= io_futex_cache_init(ctx); if (ret) - goto err; + goto free_ref; init_completion(&ctx->ref_comp); xa_init_flags(&ctx->personalities, XA_FLAGS_ALLOC1); mutex_init(&ctx->uring_lock); @@ -349,6 +349,9 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) io_napi_init(ctx); return ctx; + +free_ref: + percpu_ref_exit(&ctx->refs); err: io_alloc_cache_free(&ctx->rsrc_node_cache, kfree); io_alloc_cache_free(&ctx->apoll_cache, kfree); @@ -2038,7 +2041,7 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, req->opcode = opcode = READ_ONCE(sqe->opcode); /* same numerical values with corresponding REQ_F_*, safe to copy */ sqe_flags = READ_ONCE(sqe->flags); - req->flags = (io_req_flags_t) sqe_flags; + req->flags = (__force io_req_flags_t) sqe_flags; req->cqe.user_data = READ_ONCE(sqe->user_data); req->file = NULL; req->rsrc_node = NULL; diff --git a/io_uring/net.c b/io_uring/net.c index f10f5a22d66a..18507658a921 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -1133,6 +1133,7 @@ int io_recv(struct io_kiocb *req, unsigned int issue_flags) int ret, min_ret = 0; bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; size_t len = sr->len; + bool mshot_finished; if (!(req->flags & REQ_F_POLLED) && (sr->flags & IORING_RECVSEND_POLL_FIRST)) @@ -1187,6 +1188,7 @@ out_free: req_set_fail(req); } + mshot_finished = ret <= 0; if (ret > 0) ret += sr->done_io; else if (sr->done_io) @@ -1194,7 +1196,7 @@ out_free: else io_kbuf_recycle(req, issue_flags); - if (!io_recv_finish(req, &ret, kmsg, ret <= 0, issue_flags)) + if (!io_recv_finish(req, &ret, kmsg, mshot_finished, issue_flags)) goto retry_multishot; return ret; diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 4e07cc057d6f..5e77c58e0601 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -40,7 +40,7 @@ #include <linux/execmem.h> #include <asm/barrier.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /* Registers */ #define BPF_R0 regs[BPF_REG_0] diff --git a/kernel/debug/gdbstub.c b/kernel/debug/gdbstub.c index 9d34d2364b5a..f625172d4b67 100644 --- a/kernel/debug/gdbstub.c +++ b/kernel/debug/gdbstub.c @@ -33,7 +33,7 @@ #include <linux/reboot.h> #include <linux/uaccess.h> #include <asm/cacheflush.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "debug_core.h" #define KGDB_MAX_THREAD_QUERY 17 diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 2ec796e2f055..4b52cb2ae6d6 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -1545,7 +1545,7 @@ static struct xol_area *__create_xol_area(unsigned long vaddr) if (!area->bitmap) goto free_area; - area->page = alloc_page(GFP_HIGHUSER); + area->page = alloc_page(GFP_HIGHUSER | __GFP_ZERO); if (!area->page) goto free_bitmap; diff --git a/kernel/fork.c b/kernel/fork.c index 60c0b4868fd4..89ceb4a68af2 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1756,33 +1756,30 @@ static int copy_files(unsigned long clone_flags, struct task_struct *tsk, int no_files) { struct files_struct *oldf, *newf; - int error = 0; /* * A background process may not have any files ... */ oldf = current->files; if (!oldf) - goto out; + return 0; if (no_files) { tsk->files = NULL; - goto out; + return 0; } if (clone_flags & CLONE_FILES) { atomic_inc(&oldf->count); - goto out; + return 0; } - newf = dup_fd(oldf, NR_OPEN_MAX, &error); - if (!newf) - goto out; + newf = dup_fd(oldf, NULL); + if (IS_ERR(newf)) + return PTR_ERR(newf); tsk->files = newf; - error = 0; -out: - return error; + return 0; } static int copy_sighand(unsigned long clone_flags, struct task_struct *tsk) @@ -3238,17 +3235,16 @@ static int unshare_fs(unsigned long unshare_flags, struct fs_struct **new_fsp) /* * Unshare file descriptor table if it is being shared */ -int unshare_fd(unsigned long unshare_flags, unsigned int max_fds, - struct files_struct **new_fdp) +static int unshare_fd(unsigned long unshare_flags, struct files_struct **new_fdp) { struct files_struct *fd = current->files; - int error = 0; if ((unshare_flags & CLONE_FILES) && (fd && atomic_read(&fd->count) > 1)) { - *new_fdp = dup_fd(fd, max_fds, &error); - if (!*new_fdp) - return error; + fd = dup_fd(fd, NULL); + if (IS_ERR(fd)) + return PTR_ERR(fd); + *new_fdp = fd; } return 0; @@ -3306,7 +3302,7 @@ int ksys_unshare(unsigned long unshare_flags) err = unshare_fs(unshare_flags, &new_fs); if (err) goto bad_unshare_out; - err = unshare_fd(unshare_flags, NR_OPEN_MAX, &new_fd); + err = unshare_fd(unshare_flags, &new_fd); if (err) goto bad_unshare_cleanup_fs; err = unshare_userns(unshare_flags, &new_cred); @@ -3398,7 +3394,7 @@ int unshare_files(void) struct files_struct *old, *copy = NULL; int error; - error = unshare_fd(CLONE_FILES, NR_OPEN_MAX, ©); + error = unshare_fd(CLONE_FILES, ©); if (error || !copy) return error; diff --git a/kernel/jump_label.c b/kernel/jump_label.c index 6dc76b590703..93a822d3c468 100644 --- a/kernel/jump_label.c +++ b/kernel/jump_label.c @@ -168,7 +168,7 @@ bool static_key_slow_inc_cpuslocked(struct static_key *key) jump_label_update(key); /* * Ensure that when static_key_fast_inc_not_disabled() or - * static_key_slow_try_dec() observe the positive value, + * static_key_dec_not_one() observe the positive value, * they must also observe all the text changes. */ atomic_set_release(&key->enabled, 1); @@ -250,7 +250,7 @@ void static_key_disable(struct static_key *key) } EXPORT_SYMBOL_GPL(static_key_disable); -static bool static_key_slow_try_dec(struct static_key *key) +static bool static_key_dec_not_one(struct static_key *key) { int v; @@ -274,6 +274,14 @@ static bool static_key_slow_try_dec(struct static_key *key) * enabled. This suggests an ordering problem on the user side. */ WARN_ON_ONCE(v < 0); + + /* + * Warn about underflow, and lie about success in an attempt to + * not make things worse. + */ + if (WARN_ON_ONCE(v == 0)) + return true; + if (v <= 1) return false; } while (!likely(atomic_try_cmpxchg(&key->enabled, &v, v - 1))); @@ -284,15 +292,27 @@ static bool static_key_slow_try_dec(struct static_key *key) static void __static_key_slow_dec_cpuslocked(struct static_key *key) { lockdep_assert_cpus_held(); + int val; - if (static_key_slow_try_dec(key)) + if (static_key_dec_not_one(key)) return; guard(mutex)(&jump_label_mutex); - if (atomic_cmpxchg(&key->enabled, 1, 0) == 1) + val = atomic_read(&key->enabled); + /* + * It should be impossible to observe -1 with jump_label_mutex held, + * see static_key_slow_inc_cpuslocked(). + */ + if (WARN_ON_ONCE(val == -1)) + return; + /* + * Cannot already be 0, something went sideways. + */ + if (WARN_ON_ONCE(val == 0)) + return; + + if (atomic_dec_and_test(&key->enabled)) jump_label_update(key); - else - WARN_ON_ONCE(!static_key_slow_try_dec(key)); } static void __static_key_slow_dec(struct static_key *key) @@ -329,7 +349,7 @@ void __static_key_slow_dec_deferred(struct static_key *key, { STATIC_KEY_CHECK_USE(key); - if (static_key_slow_try_dec(key)) + if (static_key_dec_not_one(key)) return; schedule_delayed_work(work, timeout); diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 7963deac33c3..536bd471557f 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -788,7 +788,7 @@ static void lockdep_print_held_locks(struct task_struct *p) printk("no locks held by %s/%d.\n", p->comm, task_pid_nr(p)); else printk("%d lock%s held by %s/%d:\n", depth, - depth > 1 ? "s" : "", p->comm, task_pid_nr(p)); + str_plural(depth), p->comm, task_pid_nr(p)); /* * It's not reliable to print a task's held locks if it's not sleeping * and it's not the current task. @@ -2084,6 +2084,9 @@ static noinline void print_bfs_bug(int ret) /* * Breadth-first-search failed, graph got corrupted? */ + if (ret == BFS_EQUEUEFULL) + pr_warn("Increase LOCKDEP_CIRCULAR_QUEUE_BITS to avoid this warning:\n"); + WARN(1, "lockdep bfs error:%d\n", ret); } @@ -6263,25 +6266,27 @@ static struct pending_free *get_pending_free(void) static void free_zapped_rcu(struct rcu_head *cb); /* - * Schedule an RCU callback if no RCU callback is pending. Must be called with - * the graph lock held. - */ -static void call_rcu_zapped(struct pending_free *pf) +* See if we need to queue an RCU callback, must called with +* the lockdep lock held, returns false if either we don't have +* any pending free or the callback is already scheduled. +* Otherwise, a call_rcu() must follow this function call. +*/ +static bool prepare_call_rcu_zapped(struct pending_free *pf) { WARN_ON_ONCE(inside_selftest()); if (list_empty(&pf->zapped)) - return; + return false; if (delayed_free.scheduled) - return; + return false; delayed_free.scheduled = true; WARN_ON_ONCE(delayed_free.pf + delayed_free.index != pf); delayed_free.index ^= 1; - call_rcu(&delayed_free.rcu_head, free_zapped_rcu); + return true; } /* The caller must hold the graph lock. May be called from RCU context. */ @@ -6307,6 +6312,7 @@ static void free_zapped_rcu(struct rcu_head *ch) { struct pending_free *pf; unsigned long flags; + bool need_callback; if (WARN_ON_ONCE(ch != &delayed_free.rcu_head)) return; @@ -6318,14 +6324,18 @@ static void free_zapped_rcu(struct rcu_head *ch) pf = delayed_free.pf + (delayed_free.index ^ 1); __free_zapped_classes(pf); delayed_free.scheduled = false; + need_callback = + prepare_call_rcu_zapped(delayed_free.pf + delayed_free.index); + lockdep_unlock(); + raw_local_irq_restore(flags); /* - * If there's anything on the open list, close and start a new callback. - */ - call_rcu_zapped(delayed_free.pf + delayed_free.index); + * If there's pending free and its callback has not been scheduled, + * queue an RCU callback. + */ + if (need_callback) + call_rcu(&delayed_free.rcu_head, free_zapped_rcu); - lockdep_unlock(); - raw_local_irq_restore(flags); } /* @@ -6365,6 +6375,7 @@ static void lockdep_free_key_range_reg(void *start, unsigned long size) { struct pending_free *pf; unsigned long flags; + bool need_callback; init_data_structures_once(); @@ -6372,10 +6383,11 @@ static void lockdep_free_key_range_reg(void *start, unsigned long size) lockdep_lock(); pf = get_pending_free(); __lockdep_free_key_range(pf, start, size); - call_rcu_zapped(pf); + need_callback = prepare_call_rcu_zapped(pf); lockdep_unlock(); raw_local_irq_restore(flags); - + if (need_callback) + call_rcu(&delayed_free.rcu_head, free_zapped_rcu); /* * Wait for any possible iterators from look_up_lock_class() to pass * before continuing to free the memory they refer to. @@ -6469,6 +6481,7 @@ static void lockdep_reset_lock_reg(struct lockdep_map *lock) struct pending_free *pf; unsigned long flags; int locked; + bool need_callback = false; raw_local_irq_save(flags); locked = graph_lock(); @@ -6477,11 +6490,13 @@ static void lockdep_reset_lock_reg(struct lockdep_map *lock) pf = get_pending_free(); __lockdep_reset_lock(pf, lock); - call_rcu_zapped(pf); + need_callback = prepare_call_rcu_zapped(pf); graph_unlock(); out_irq: raw_local_irq_restore(flags); + if (need_callback) + call_rcu(&delayed_free.rcu_head, free_zapped_rcu); } /* @@ -6525,6 +6540,7 @@ void lockdep_unregister_key(struct lock_class_key *key) struct pending_free *pf; unsigned long flags; bool found = false; + bool need_callback = false; might_sleep(); @@ -6545,11 +6561,14 @@ void lockdep_unregister_key(struct lock_class_key *key) if (found) { pf = get_pending_free(); __lockdep_free_key_range(pf, key, 1); - call_rcu_zapped(pf); + need_callback = prepare_call_rcu_zapped(pf); } lockdep_unlock(); raw_local_irq_restore(flags); + if (need_callback) + call_rcu(&delayed_free.rcu_head, free_zapped_rcu); + /* Wait until is_dynamic_key() has finished accessing k->hash_entry. */ synchronize_rcu(); } diff --git a/kernel/locking/lockdep_proc.c b/kernel/locking/lockdep_proc.c index e2bfb1db589d..6db0f43fc4df 100644 --- a/kernel/locking/lockdep_proc.c +++ b/kernel/locking/lockdep_proc.c @@ -424,7 +424,7 @@ static void seq_line(struct seq_file *m, char c, int offset, int length) for (i = 0; i < offset; i++) seq_puts(m, " "); for (i = 0; i < length; i++) - seq_printf(m, "%c", c); + seq_putc(m, c); seq_puts(m, "\n"); } diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c index 5ded7dff46ef..2bbb6eca5144 100644 --- a/kernel/locking/rwsem.c +++ b/kernel/locking/rwsem.c @@ -181,12 +181,21 @@ static inline void rwsem_set_reader_owned(struct rw_semaphore *sem) __rwsem_set_reader_owned(sem, current); } +#ifdef CONFIG_DEBUG_RWSEMS +/* + * Return just the real task structure pointer of the owner + */ +static inline struct task_struct *rwsem_owner(struct rw_semaphore *sem) +{ + return (struct task_struct *) + (atomic_long_read(&sem->owner) & ~RWSEM_OWNER_FLAGS_MASK); +} + /* * Return true if the rwsem is owned by a reader. */ static inline bool is_rwsem_reader_owned(struct rw_semaphore *sem) { -#ifdef CONFIG_DEBUG_RWSEMS /* * Check the count to see if it is write-locked. */ @@ -194,11 +203,9 @@ static inline bool is_rwsem_reader_owned(struct rw_semaphore *sem) if (count & RWSEM_WRITER_MASK) return false; -#endif return rwsem_test_oflags(sem, RWSEM_READER_OWNED); } -#ifdef CONFIG_DEBUG_RWSEMS /* * With CONFIG_DEBUG_RWSEMS configured, it will make sure that if there * is a task pointer in owner of a reader-owned rwsem, it will be the @@ -266,15 +273,6 @@ static inline bool rwsem_write_trylock(struct rw_semaphore *sem) } /* - * Return just the real task structure pointer of the owner - */ -static inline struct task_struct *rwsem_owner(struct rw_semaphore *sem) -{ - return (struct task_struct *) - (atomic_long_read(&sem->owner) & ~RWSEM_OWNER_FLAGS_MASK); -} - -/* * Return the real task structure pointer of the owner and the embedded * flags in the owner. pflags must be non-NULL. */ diff --git a/kernel/module/Kconfig b/kernel/module/Kconfig index 05a9a06a140c..7c6588148d42 100644 --- a/kernel/module/Kconfig +++ b/kernel/module/Kconfig @@ -229,7 +229,7 @@ comment "Do not forget to sign required modules with scripts/sign-file" depends on MODULE_SIG_FORCE && !MODULE_SIG_ALL choice - prompt "Which hash algorithm should modules be signed with?" + prompt "Hash algorithm to sign modules" depends on MODULE_SIG || IMA_APPRAISE_MODSIG help This determines which sort of hashing algorithm will be used during @@ -239,31 +239,31 @@ choice the signature on that module. config MODULE_SIG_SHA1 - bool "Sign modules with SHA-1" + bool "SHA-1" select CRYPTO_SHA1 config MODULE_SIG_SHA256 - bool "Sign modules with SHA-256" + bool "SHA-256" select CRYPTO_SHA256 config MODULE_SIG_SHA384 - bool "Sign modules with SHA-384" + bool "SHA-384" select CRYPTO_SHA512 config MODULE_SIG_SHA512 - bool "Sign modules with SHA-512" + bool "SHA-512" select CRYPTO_SHA512 config MODULE_SIG_SHA3_256 - bool "Sign modules with SHA3-256" + bool "SHA3-256" select CRYPTO_SHA3 config MODULE_SIG_SHA3_384 - bool "Sign modules with SHA3-384" + bool "SHA3-384" select CRYPTO_SHA3 config MODULE_SIG_SHA3_512 - bool "Sign modules with SHA3-512" + bool "SHA3-512" select CRYPTO_SHA3 endchoice @@ -279,64 +279,65 @@ config MODULE_SIG_HASH default "sha3-384" if MODULE_SIG_SHA3_384 default "sha3-512" if MODULE_SIG_SHA3_512 -choice - prompt "Module compression mode" +config MODULE_COMPRESS + bool "Module compression" help - This option allows you to choose the algorithm which will be used to - compress modules when 'make modules_install' is run. (or, you can - choose to not compress modules at all.) - - External modules will also be compressed in the same way during the - installation. - - For modules inside an initrd or initramfs, it's more efficient to - compress the whole initrd or initramfs instead. - + Enable module compression to reduce on-disk size of module binaries. This is fully compatible with signed modules. - Please note that the tool used to load modules needs to support the - corresponding algorithm. module-init-tools MAY support gzip, and kmod - MAY support gzip, xz and zstd. + The tool used to work with modules needs to support the selected + compression type. kmod MAY support gzip, xz and zstd. Other tools + might have a limited selection of the supported types. - Your build system needs to provide the appropriate compression tool - to compress the modules. + Note that for modules inside an initrd or initramfs, it's more + efficient to compress the whole ramdisk instead. - If in doubt, select 'None'. + If unsure, say N. -config MODULE_COMPRESS_NONE - bool "None" +choice + prompt "Module compression type" + depends on MODULE_COMPRESS help - Do not compress modules. The installed modules are suffixed - with .ko. + Choose the supported algorithm for module compression. config MODULE_COMPRESS_GZIP bool "GZIP" help - Compress modules with GZIP. The installed modules are suffixed - with .ko.gz. + Support modules compressed with GZIP. The installed modules are + suffixed with .ko.gz. config MODULE_COMPRESS_XZ bool "XZ" help - Compress modules with XZ. The installed modules are suffixed - with .ko.xz. + Support modules compressed with XZ. The installed modules are + suffixed with .ko.xz. config MODULE_COMPRESS_ZSTD bool "ZSTD" help - Compress modules with ZSTD. The installed modules are suffixed - with .ko.zst. + Support modules compressed with ZSTD. The installed modules are + suffixed with .ko.zst. endchoice +config MODULE_COMPRESS_ALL + bool "Automatically compress all modules" + default y + depends on MODULE_COMPRESS + help + Compress all modules during 'make modules_install'. + + Your build system needs to provide the appropriate compression tool + for the selected compression type. External modules will also be + compressed in the same way during the installation. + config MODULE_DECOMPRESS bool "Support in-kernel module decompression" - depends on MODULE_COMPRESS_GZIP || MODULE_COMPRESS_XZ || MODULE_COMPRESS_ZSTD + depends on MODULE_COMPRESS select ZLIB_INFLATE if MODULE_COMPRESS_GZIP select XZ_DEC if MODULE_COMPRESS_XZ select ZSTD_DECOMPRESS if MODULE_COMPRESS_ZSTD help - Support for decompressing kernel modules by the kernel itself instead of relying on userspace to perform this task. Useful when load pinning security policy is enabled. diff --git a/kernel/module/debug_kmemleak.c b/kernel/module/debug_kmemleak.c index 12a569d361e8..b4cc03842d70 100644 --- a/kernel/module/debug_kmemleak.c +++ b/kernel/module/debug_kmemleak.c @@ -12,19 +12,9 @@ void kmemleak_load_module(const struct module *mod, const struct load_info *info) { - unsigned int i; - - /* only scan the sections containing data */ - kmemleak_scan_area(mod, sizeof(struct module), GFP_KERNEL); - - for (i = 1; i < info->hdr->e_shnum; i++) { - /* Scan all writable sections that's not executable */ - if (!(info->sechdrs[i].sh_flags & SHF_ALLOC) || - !(info->sechdrs[i].sh_flags & SHF_WRITE) || - (info->sechdrs[i].sh_flags & SHF_EXECINSTR)) - continue; - - kmemleak_scan_area((void *)info->sechdrs[i].sh_addr, - info->sechdrs[i].sh_size, GFP_KERNEL); + /* only scan writable, non-executable sections */ + for_each_mod_mem_type(type) { + if (type != MOD_DATA && type != MOD_INIT_DATA) + kmemleak_no_scan(mod->mem[type].base); } } diff --git a/kernel/module/sysfs.c b/kernel/module/sysfs.c index 26efe1305c12..456358e1fdc4 100644 --- a/kernel/module/sysfs.c +++ b/kernel/module/sysfs.c @@ -69,12 +69,13 @@ static void free_sect_attrs(struct module_sect_attrs *sect_attrs) kfree(sect_attrs); } -static void add_sect_attrs(struct module *mod, const struct load_info *info) +static int add_sect_attrs(struct module *mod, const struct load_info *info) { unsigned int nloaded = 0, i, size[2]; struct module_sect_attrs *sect_attrs; struct module_sect_attr *sattr; struct bin_attribute **gattr; + int ret; /* Count loaded sections and allocate structures */ for (i = 0; i < info->hdr->e_shnum; i++) @@ -85,7 +86,7 @@ static void add_sect_attrs(struct module *mod, const struct load_info *info) size[1] = (nloaded + 1) * sizeof(sect_attrs->grp.bin_attrs[0]); sect_attrs = kzalloc(size[0] + size[1], GFP_KERNEL); if (!sect_attrs) - return; + return -ENOMEM; /* Setup section attributes. */ sect_attrs->grp.name = "sections"; @@ -103,8 +104,10 @@ static void add_sect_attrs(struct module *mod, const struct load_info *info) sattr->address = sec->sh_addr; sattr->battr.attr.name = kstrdup(info->secstrings + sec->sh_name, GFP_KERNEL); - if (!sattr->battr.attr.name) + if (!sattr->battr.attr.name) { + ret = -ENOMEM; goto out; + } sect_attrs->nsections++; sattr->battr.read = module_sect_read; sattr->battr.size = MODULE_SECT_READ_SIZE; @@ -113,13 +116,15 @@ static void add_sect_attrs(struct module *mod, const struct load_info *info) } *gattr = NULL; - if (sysfs_create_group(&mod->mkobj.kobj, §_attrs->grp)) + ret = sysfs_create_group(&mod->mkobj.kobj, §_attrs->grp); + if (ret) goto out; mod->sect_attrs = sect_attrs; - return; + return 0; out: free_sect_attrs(sect_attrs); + return ret; } static void remove_sect_attrs(struct module *mod) @@ -158,15 +163,12 @@ static void free_notes_attrs(struct module_notes_attrs *notes_attrs, kfree(notes_attrs); } -static void add_notes_attrs(struct module *mod, const struct load_info *info) +static int add_notes_attrs(struct module *mod, const struct load_info *info) { unsigned int notes, loaded, i; struct module_notes_attrs *notes_attrs; struct bin_attribute *nattr; - - /* failed to create section attributes, so can't create notes */ - if (!mod->sect_attrs) - return; + int ret; /* Count notes sections and allocate structures. */ notes = 0; @@ -176,12 +178,12 @@ static void add_notes_attrs(struct module *mod, const struct load_info *info) ++notes; if (notes == 0) - return; + return 0; notes_attrs = kzalloc(struct_size(notes_attrs, attrs, notes), GFP_KERNEL); if (!notes_attrs) - return; + return -ENOMEM; notes_attrs->notes = notes; nattr = ¬es_attrs->attrs[0]; @@ -201,19 +203,23 @@ static void add_notes_attrs(struct module *mod, const struct load_info *info) } notes_attrs->dir = kobject_create_and_add("notes", &mod->mkobj.kobj); - if (!notes_attrs->dir) + if (!notes_attrs->dir) { + ret = -ENOMEM; goto out; + } - for (i = 0; i < notes; ++i) - if (sysfs_create_bin_file(notes_attrs->dir, - ¬es_attrs->attrs[i])) + for (i = 0; i < notes; ++i) { + ret = sysfs_create_bin_file(notes_attrs->dir, ¬es_attrs->attrs[i]); + if (ret) goto out; + } mod->notes_attrs = notes_attrs; - return; + return 0; out: free_notes_attrs(notes_attrs, i); + return ret; } static void remove_notes_attrs(struct module *mod) @@ -223,9 +229,15 @@ static void remove_notes_attrs(struct module *mod) } #else /* !CONFIG_KALLSYMS */ -static inline void add_sect_attrs(struct module *mod, const struct load_info *info) { } +static inline int add_sect_attrs(struct module *mod, const struct load_info *info) +{ + return 0; +} static inline void remove_sect_attrs(struct module *mod) { } -static inline void add_notes_attrs(struct module *mod, const struct load_info *info) { } +static inline int add_notes_attrs(struct module *mod, const struct load_info *info) +{ + return 0; +} static inline void remove_notes_attrs(struct module *mod) { } #endif /* CONFIG_KALLSYMS */ @@ -385,11 +397,20 @@ int mod_sysfs_setup(struct module *mod, if (err) goto out_unreg_modinfo_attrs; - add_sect_attrs(mod, info); - add_notes_attrs(mod, info); + err = add_sect_attrs(mod, info); + if (err) + goto out_del_usage_links; + + err = add_notes_attrs(mod, info); + if (err) + goto out_unreg_sect_attrs; return 0; +out_unreg_sect_attrs: + remove_sect_attrs(mod); +out_del_usage_links: + del_usage_links(mod); out_unreg_modinfo_attrs: module_remove_modinfo_attrs(mod, -1); out_unreg_param: diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index a60616e69b66..b1f883fcd918 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -3607,11 +3607,12 @@ kvfree_rcu_queue_batch(struct kfree_rcu_cpu *krcp) } // One work is per one batch, so there are three - // "free channels", the batch can handle. It can - // be that the work is in the pending state when - // channels have been detached following by each - // other. + // "free channels", the batch can handle. Break + // the loop since it is done with this CPU thus + // queuing an RCU work is _always_ success here. queued = queue_rcu_work(system_unbound_wq, &krwp->rcu_work); + WARN_ON_ONCE(!queued); + break; } } diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index c09e3dc38c34..3cd7c50a51c5 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -9,6 +9,7 @@ #define SCX_OP_IDX(op) (offsetof(struct sched_ext_ops, op) / sizeof(void (*)(void))) enum scx_consts { + SCX_SLICE_BYPASS = SCX_SLICE_DFL / 4, SCX_DSP_DFL_MAX_BATCH = 32, SCX_DSP_MAX_LOOPS = 32, SCX_WATCHDOG_MAX_TIMEOUT = 30 * HZ, @@ -778,7 +779,6 @@ enum scx_tg_flags { }; enum scx_ops_enable_state { - SCX_OPS_PREPPING, SCX_OPS_ENABLING, SCX_OPS_ENABLED, SCX_OPS_DISABLING, @@ -786,7 +786,6 @@ enum scx_ops_enable_state { }; static const char *scx_ops_enable_state_str[] = { - [SCX_OPS_PREPPING] = "prepping", [SCX_OPS_ENABLING] = "enabling", [SCX_OPS_ENABLED] = "enabled", [SCX_OPS_DISABLING] = "disabling", @@ -854,6 +853,7 @@ DEFINE_STATIC_KEY_FALSE(__scx_ops_enabled); DEFINE_STATIC_PERCPU_RWSEM(scx_fork_rwsem); static atomic_t scx_ops_enable_state_var = ATOMIC_INIT(SCX_OPS_DISABLED); static atomic_t scx_ops_bypass_depth = ATOMIC_INIT(0); +static bool scx_ops_init_task_enabled; static bool scx_switching_all; DEFINE_STATIC_KEY_FALSE(__scx_switched_all); @@ -925,8 +925,15 @@ static unsigned long __percpu *scx_kick_cpus_pnt_seqs; */ static DEFINE_PER_CPU(struct task_struct *, direct_dispatch_task); -/* dispatch queues */ -static struct scx_dispatch_q __cacheline_aligned_in_smp scx_dsq_global; +/* + * Dispatch queues. + * + * The global DSQ (%SCX_DSQ_GLOBAL) is split per-node for scalability. This is + * to avoid live-locking in bypass mode where all tasks are dispatched to + * %SCX_DSQ_GLOBAL and all CPUs consume from it. If per-node split isn't + * sufficient, it can be further split. + */ +static struct scx_dispatch_q **global_dsqs; static const struct rhashtable_params dsq_hash_params = { .key_len = 8, @@ -1029,6 +1036,16 @@ static bool u32_before(u32 a, u32 b) return (s32)(a - b) < 0; } +static struct scx_dispatch_q *find_global_dsq(struct task_struct *p) +{ + return global_dsqs[cpu_to_node(task_cpu(p))]; +} + +static struct scx_dispatch_q *find_user_dsq(u64 dsq_id) +{ + return rhashtable_lookup_fast(&dsq_hash, &dsq_id, dsq_hash_params); +} + /* * scx_kf_mask enforcement. Some kfuncs can only be called from specific SCX * ops. When invoking SCX ops, SCX_CALL_OP[_RET]() should be used to indicate @@ -1637,7 +1654,7 @@ static void dispatch_enqueue(struct scx_dispatch_q *dsq, struct task_struct *p, scx_ops_error("attempting to dispatch to a destroyed dsq"); /* fall back to the global dsq */ raw_spin_unlock(&dsq->lock); - dsq = &scx_dsq_global; + dsq = find_global_dsq(p); raw_spin_lock(&dsq->lock); } } @@ -1803,21 +1820,6 @@ static void dispatch_dequeue(struct rq *rq, struct task_struct *p) raw_spin_unlock(&dsq->lock); } -static struct scx_dispatch_q *find_user_dsq(u64 dsq_id) -{ - return rhashtable_lookup_fast(&dsq_hash, &dsq_id, dsq_hash_params); -} - -static struct scx_dispatch_q *find_non_local_dsq(u64 dsq_id) -{ - lockdep_assert(rcu_read_lock_any_held()); - - if (dsq_id == SCX_DSQ_GLOBAL) - return &scx_dsq_global; - else - return find_user_dsq(dsq_id); -} - static struct scx_dispatch_q *find_dsq_for_dispatch(struct rq *rq, u64 dsq_id, struct task_struct *p) { @@ -1830,16 +1832,20 @@ static struct scx_dispatch_q *find_dsq_for_dispatch(struct rq *rq, u64 dsq_id, s32 cpu = dsq_id & SCX_DSQ_LOCAL_CPU_MASK; if (!ops_cpu_valid(cpu, "in SCX_DSQ_LOCAL_ON dispatch verdict")) - return &scx_dsq_global; + return find_global_dsq(p); return &cpu_rq(cpu)->scx.local_dsq; } - dsq = find_non_local_dsq(dsq_id); + if (dsq_id == SCX_DSQ_GLOBAL) + dsq = find_global_dsq(p); + else + dsq = find_user_dsq(dsq_id); + if (unlikely(!dsq)) { scx_ops_error("non-existent DSQ 0x%llx for %s[%d]", dsq_id, p->comm, p->pid); - return &scx_dsq_global; + return find_global_dsq(p); } return dsq; @@ -1938,6 +1944,7 @@ static bool scx_rq_online(struct rq *rq) static void do_enqueue_task(struct rq *rq, struct task_struct *p, u64 enq_flags, int sticky_cpu) { + bool bypassing = scx_rq_bypassing(rq); struct task_struct **ddsp_taskp; unsigned long qseq; @@ -1955,7 +1962,7 @@ static void do_enqueue_task(struct rq *rq, struct task_struct *p, u64 enq_flags, if (!scx_rq_online(rq)) goto local; - if (scx_rq_bypassing(rq)) + if (bypassing) goto global; if (p->scx.ddsp_dsq_id != SCX_DSQ_INVALID) @@ -2010,8 +2017,8 @@ local_norefill: global: touch_core_sched(rq, p); /* see the comment in local: */ - p->scx.slice = SCX_SLICE_DFL; - dispatch_enqueue(&scx_dsq_global, p, enq_flags); + p->scx.slice = bypassing ? SCX_SLICE_BYPASS : SCX_SLICE_DFL; + dispatch_enqueue(find_global_dsq(p), p, enq_flags); } static bool task_runnable(const struct task_struct *p) @@ -2357,6 +2364,7 @@ static bool consume_remote_task(struct rq *this_rq, struct task_struct *p, } } #else /* CONFIG_SMP */ +static inline void move_remote_task_to_local_dsq(struct task_struct *p, u64 enq_flags, struct rq *src_rq, struct rq *dst_rq) { WARN_ON_ONCE(1); } static inline bool task_can_run_on_remote_rq(struct task_struct *p, struct rq *rq, bool trigger_error) { return false; } static inline bool consume_remote_task(struct rq *this_rq, struct task_struct *p, struct scx_dispatch_q *dsq, struct rq *task_rq) { return false; } #endif /* CONFIG_SMP */ @@ -2396,6 +2404,13 @@ retry: return false; } +static bool consume_global_dsq(struct rq *rq) +{ + int node = cpu_to_node(cpu_of(rq)); + + return consume_dispatch_q(rq, global_dsqs[node]); +} + /** * dispatch_to_local_dsq - Dispatch a task to a local dsq * @rq: current rq which is locked @@ -2429,7 +2444,8 @@ static void dispatch_to_local_dsq(struct rq *rq, struct scx_dispatch_q *dst_dsq, #ifdef CONFIG_SMP if (unlikely(!task_can_run_on_remote_rq(p, dst_rq, true))) { - dispatch_enqueue(&scx_dsq_global, p, enq_flags | SCX_ENQ_CLEAR_OPSS); + dispatch_enqueue(find_global_dsq(p), p, + enq_flags | SCX_ENQ_CLEAR_OPSS); return; } @@ -2629,7 +2645,7 @@ static int balance_one(struct rq *rq, struct task_struct *prev) if (rq->scx.local_dsq.nr) goto has_tasks; - if (consume_dispatch_q(rq, &scx_dsq_global)) + if (consume_global_dsq(rq)) goto has_tasks; if (!SCX_HAS_OP(dispatch) || scx_rq_bypassing(rq) || !scx_rq_online(rq)) @@ -2654,7 +2670,7 @@ static int balance_one(struct rq *rq, struct task_struct *prev) if (rq->scx.local_dsq.nr) goto has_tasks; - if (consume_dispatch_q(rq, &scx_dsq_global)) + if (consume_global_dsq(rq)) goto has_tasks; /* @@ -3058,22 +3074,13 @@ static s32 scx_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, * there is an idle core elsewhere on the system. */ cpu = smp_processor_id(); - if ((wake_flags & SCX_WAKE_SYNC) && p->nr_cpus_allowed > 1 && + if ((wake_flags & SCX_WAKE_SYNC) && !cpumask_empty(idle_masks.cpu) && !(current->flags & PF_EXITING) && cpu_rq(cpu)->scx.local_dsq.nr == 0) { if (cpumask_test_cpu(cpu, p->cpus_ptr)) goto cpu_found; } - if (p->nr_cpus_allowed == 1) { - if (test_and_clear_cpu_idle(prev_cpu)) { - cpu = prev_cpu; - goto cpu_found; - } else { - return prev_cpu; - } - } - /* * If CPU has SMT, any wholly idle CPU is likely a better pick than * partially idle @prev_cpu. @@ -3550,7 +3557,7 @@ int scx_fork(struct task_struct *p) { percpu_rwsem_assert_held(&scx_fork_rwsem); - if (scx_enabled()) + if (scx_ops_init_task_enabled) return scx_ops_init_task(p, task_group(p), true); else return 0; @@ -3558,7 +3565,7 @@ int scx_fork(struct task_struct *p) void scx_post_fork(struct task_struct *p) { - if (scx_enabled()) { + if (scx_ops_init_task_enabled) { scx_set_task_state(p, SCX_TASK_READY); /* @@ -3690,6 +3697,7 @@ bool scx_can_stop_tick(struct rq *rq) #ifdef CONFIG_EXT_GROUP_SCHED DEFINE_STATIC_PERCPU_RWSEM(scx_cgroup_rwsem); +static bool scx_cgroup_enabled; static bool cgroup_warned_missing_weight; static bool cgroup_warned_missing_idle; @@ -3709,8 +3717,7 @@ static void scx_cgroup_warn_missing_weight(struct task_group *tg) static void scx_cgroup_warn_missing_idle(struct task_group *tg) { - if (scx_ops_enable_state() == SCX_OPS_DISABLED || - cgroup_warned_missing_idle) + if (!scx_cgroup_enabled || cgroup_warned_missing_idle) return; if (!tg->idle) @@ -3731,15 +3738,18 @@ int scx_tg_online(struct task_group *tg) scx_cgroup_warn_missing_weight(tg); - if (SCX_HAS_OP(cgroup_init)) { - struct scx_cgroup_init_args args = { .weight = tg->scx_weight }; + if (scx_cgroup_enabled) { + if (SCX_HAS_OP(cgroup_init)) { + struct scx_cgroup_init_args args = + { .weight = tg->scx_weight }; - ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, cgroup_init, - tg->css.cgroup, &args); - if (!ret) + ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, cgroup_init, + tg->css.cgroup, &args); + if (ret) + ret = ops_sanitize_err("cgroup_init", ret); + } + if (ret == 0) tg->scx_flags |= SCX_TG_ONLINE | SCX_TG_INITED; - else - ret = ops_sanitize_err("cgroup_init", ret); } else { tg->scx_flags |= SCX_TG_ONLINE; } @@ -3770,7 +3780,7 @@ int scx_cgroup_can_attach(struct cgroup_taskset *tset) /* released in scx_finish/cancel_attach() */ percpu_down_read(&scx_cgroup_rwsem); - if (!scx_enabled()) + if (!scx_cgroup_enabled) return 0; cgroup_taskset_for_each(p, css, tset) { @@ -3813,7 +3823,7 @@ err: void scx_move_task(struct task_struct *p) { - if (!scx_enabled()) + if (!scx_cgroup_enabled) return; /* @@ -3849,7 +3859,7 @@ void scx_cgroup_cancel_attach(struct cgroup_taskset *tset) struct cgroup_subsys_state *css; struct task_struct *p; - if (!scx_enabled()) + if (!scx_cgroup_enabled) goto out_unlock; cgroup_taskset_for_each(p, css, tset) { @@ -3866,7 +3876,7 @@ void scx_group_set_weight(struct task_group *tg, unsigned long weight) { percpu_down_read(&scx_cgroup_rwsem); - if (tg->scx_weight != weight) { + if (scx_cgroup_enabled && tg->scx_weight != weight) { if (SCX_HAS_OP(cgroup_set_weight)) SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_set_weight, tg_cgrp(tg), weight); @@ -4038,6 +4048,9 @@ static void scx_cgroup_exit(void) percpu_rwsem_assert_held(&scx_cgroup_rwsem); + WARN_ON_ONCE(!scx_cgroup_enabled); + scx_cgroup_enabled = false; + /* * scx_tg_on/offline() are excluded through scx_cgroup_rwsem. If we walk * cgroups and exit all the inited ones, all online cgroups are exited. @@ -4113,6 +4126,9 @@ static int scx_cgroup_init(void) } rcu_read_unlock(); + WARN_ON_ONCE(scx_cgroup_enabled); + scx_cgroup_enabled = true; + return 0; } @@ -4431,19 +4447,23 @@ static void scx_ops_disable_workfn(struct kthread_work *work) WRITE_ONCE(scx_switching_all, false); /* - * Avoid racing against fork and cgroup changes. See scx_ops_enable() - * for explanation on the locking order. + * Shut down cgroup support before tasks so that the cgroup attach path + * doesn't race against scx_ops_exit_task(). */ - percpu_down_write(&scx_fork_rwsem); - cpus_read_lock(); scx_cgroup_lock(); + scx_cgroup_exit(); + scx_cgroup_unlock(); - spin_lock_irq(&scx_tasks_lock); - scx_task_iter_init(&sti); /* * The BPF scheduler is going away. All tasks including %TASK_DEAD ones * must be switched out and exited synchronously. */ + percpu_down_write(&scx_fork_rwsem); + + scx_ops_init_task_enabled = false; + + spin_lock_irq(&scx_tasks_lock); + scx_task_iter_init(&sti); while ((p = scx_task_iter_next_locked(&sti))) { const struct sched_class *old_class = p->sched_class; struct sched_enq_and_set_ctx ctx; @@ -4461,23 +4481,18 @@ static void scx_ops_disable_workfn(struct kthread_work *work) } scx_task_iter_exit(&sti); spin_unlock_irq(&scx_tasks_lock); + percpu_up_write(&scx_fork_rwsem); /* no task is on scx, turn off all the switches and flush in-progress calls */ - static_branch_disable_cpuslocked(&__scx_ops_enabled); + static_branch_disable(&__scx_ops_enabled); for (i = SCX_OPI_BEGIN; i < SCX_OPI_END; i++) - static_branch_disable_cpuslocked(&scx_has_op[i]); - static_branch_disable_cpuslocked(&scx_ops_enq_last); - static_branch_disable_cpuslocked(&scx_ops_enq_exiting); - static_branch_disable_cpuslocked(&scx_ops_cpu_preempt); - static_branch_disable_cpuslocked(&scx_builtin_idle_enabled); + static_branch_disable(&scx_has_op[i]); + static_branch_disable(&scx_ops_enq_last); + static_branch_disable(&scx_ops_enq_exiting); + static_branch_disable(&scx_ops_cpu_preempt); + static_branch_disable(&scx_builtin_idle_enabled); synchronize_rcu(); - scx_cgroup_exit(); - - scx_cgroup_unlock(); - cpus_read_unlock(); - percpu_up_write(&scx_fork_rwsem); - if (ei->kind >= SCX_EXIT_ERROR) { pr_err("sched_ext: BPF scheduler \"%s\" disabled (%s)\n", scx_ops.name, ei->reason); @@ -4929,7 +4944,7 @@ static int scx_ops_enable(struct sched_ext_ops *ops, struct bpf_link *link) struct scx_task_iter sti; struct task_struct *p; unsigned long timeout; - int i, cpu, ret; + int i, cpu, node, ret; if (!cpumask_equal(housekeeping_cpumask(HK_TYPE_DOMAIN), cpu_possible_mask)) { @@ -4948,6 +4963,34 @@ static int scx_ops_enable(struct sched_ext_ops *ops, struct bpf_link *link) } } + if (!global_dsqs) { + struct scx_dispatch_q **dsqs; + + dsqs = kcalloc(nr_node_ids, sizeof(dsqs[0]), GFP_KERNEL); + if (!dsqs) { + ret = -ENOMEM; + goto err_unlock; + } + + for_each_node_state(node, N_POSSIBLE) { + struct scx_dispatch_q *dsq; + + dsq = kzalloc_node(sizeof(*dsq), GFP_KERNEL, node); + if (!dsq) { + for_each_node_state(node, N_POSSIBLE) + kfree(dsqs[node]); + kfree(dsqs); + ret = -ENOMEM; + goto err_unlock; + } + + init_dsq(dsq, SCX_DSQ_GLOBAL); + dsqs[node] = dsq; + } + + global_dsqs = dsqs; + } + if (scx_ops_enable_state() != SCX_OPS_DISABLED) { ret = -EBUSY; goto err_unlock; @@ -4971,12 +5014,12 @@ static int scx_ops_enable(struct sched_ext_ops *ops, struct bpf_link *link) } /* - * Set scx_ops, transition to PREPPING and clear exit info to arm the + * Set scx_ops, transition to ENABLING and clear exit info to arm the * disable path. Failure triggers full disabling from here on. */ scx_ops = *ops; - WARN_ON_ONCE(scx_ops_set_enable_state(SCX_OPS_PREPPING) != + WARN_ON_ONCE(scx_ops_set_enable_state(SCX_OPS_ENABLING) != SCX_OPS_DISABLED); atomic_set(&scx_exit_kind, SCX_EXIT_NONE); @@ -4997,7 +5040,8 @@ static int scx_ops_enable(struct sched_ext_ops *ops, struct bpf_link *link) ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, init); if (ret) { ret = ops_sanitize_err("init", ret); - goto err_disable_unlock_cpus; + cpus_read_unlock(); + goto err_disable; } } @@ -5005,6 +5049,7 @@ static int scx_ops_enable(struct sched_ext_ops *ops, struct bpf_link *link) if (((void (**)(void))ops)[i]) static_branch_enable_cpuslocked(&scx_has_op[i]); + check_hotplug_seq(ops); cpus_read_unlock(); ret = validate_ops(ops); @@ -5032,57 +5077,40 @@ static int scx_ops_enable(struct sched_ext_ops *ops, struct bpf_link *link) scx_watchdog_timeout / 2); /* - * Lock out forks, cgroup on/offlining and moves before opening the - * floodgate so that they don't wander into the operations prematurely. - * - * We don't need to keep the CPUs stable but static_branch_*() requires - * cpus_read_lock() and scx_cgroup_rwsem must nest inside - * cpu_hotplug_lock because of the following dependency chain: - * - * cpu_hotplug_lock --> cgroup_threadgroup_rwsem --> scx_cgroup_rwsem - * - * So, we need to do cpus_read_lock() before scx_cgroup_lock() and use - * static_branch_*_cpuslocked(). - * - * Note that cpu_hotplug_lock must nest inside scx_fork_rwsem due to the - * following dependency chain: - * - * scx_fork_rwsem --> pernet_ops_rwsem --> cpu_hotplug_lock + * Once __scx_ops_enabled is set, %current can be switched to SCX + * anytime. This can lead to stalls as some BPF schedulers (e.g. + * userspace scheduling) may not function correctly before all tasks are + * switched. Init in bypass mode to guarantee forward progress. */ - percpu_down_write(&scx_fork_rwsem); - cpus_read_lock(); - scx_cgroup_lock(); - - check_hotplug_seq(ops); + scx_ops_bypass(true); for (i = SCX_OPI_NORMAL_BEGIN; i < SCX_OPI_NORMAL_END; i++) if (((void (**)(void))ops)[i]) - static_branch_enable_cpuslocked(&scx_has_op[i]); + static_branch_enable(&scx_has_op[i]); if (ops->flags & SCX_OPS_ENQ_LAST) - static_branch_enable_cpuslocked(&scx_ops_enq_last); + static_branch_enable(&scx_ops_enq_last); if (ops->flags & SCX_OPS_ENQ_EXITING) - static_branch_enable_cpuslocked(&scx_ops_enq_exiting); + static_branch_enable(&scx_ops_enq_exiting); if (scx_ops.cpu_acquire || scx_ops.cpu_release) - static_branch_enable_cpuslocked(&scx_ops_cpu_preempt); + static_branch_enable(&scx_ops_cpu_preempt); if (!ops->update_idle || (ops->flags & SCX_OPS_KEEP_BUILTIN_IDLE)) { reset_idle_masks(); - static_branch_enable_cpuslocked(&scx_builtin_idle_enabled); + static_branch_enable(&scx_builtin_idle_enabled); } else { - static_branch_disable_cpuslocked(&scx_builtin_idle_enabled); + static_branch_disable(&scx_builtin_idle_enabled); } /* - * All cgroups should be initialized before letting in tasks. cgroup - * on/offlining and task migrations are already locked out. + * Lock out forks, cgroup on/offlining and moves before opening the + * floodgate so that they don't wander into the operations prematurely. */ - ret = scx_cgroup_init(); - if (ret) - goto err_disable_unlock_all; + percpu_down_write(&scx_fork_rwsem); - static_branch_enable_cpuslocked(&__scx_ops_enabled); + WARN_ON_ONCE(scx_ops_init_task_enabled); + scx_ops_init_task_enabled = true; /* * Enable ops for every task. Fork is excluded by scx_fork_rwsem @@ -5090,9 +5118,19 @@ static int scx_ops_enable(struct sched_ext_ops *ops, struct bpf_link *link) * leaving as sched_ext_free() can handle both prepped and enabled * tasks. Prep all tasks first and then enable them with preemption * disabled. + * + * All cgroups should be initialized before scx_ops_init_task() so that + * the BPF scheduler can reliably track each task's cgroup membership + * from scx_ops_init_task(). Lock out cgroup on/offlining and task + * migrations while tasks are being initialized so that + * scx_cgroup_can_attach() never sees uninitialized tasks. */ - spin_lock_irq(&scx_tasks_lock); + scx_cgroup_lock(); + ret = scx_cgroup_init(); + if (ret) + goto err_disable_unlock_all; + spin_lock_irq(&scx_tasks_lock); scx_task_iter_init(&sti); while ((p = scx_task_iter_next_locked(&sti))) { /* @@ -5117,43 +5155,30 @@ static int scx_ops_enable(struct sched_ext_ops *ops, struct bpf_link *link) goto err_disable_unlock_all; } + scx_set_task_state(p, SCX_TASK_READY); + put_task_struct(p); spin_lock_irq(&scx_tasks_lock); } scx_task_iter_exit(&sti); + spin_unlock_irq(&scx_tasks_lock); + scx_cgroup_unlock(); + percpu_up_write(&scx_fork_rwsem); /* - * All tasks are prepped but are still ops-disabled. Ensure that - * %current can't be scheduled out and switch everyone. - * preempt_disable() is necessary because we can't guarantee that - * %current won't be starved if scheduled out while switching. - */ - preempt_disable(); - - /* - * From here on, the disable path must assume that tasks have ops - * enabled and need to be recovered. - * - * Transition to ENABLING fails iff the BPF scheduler has already - * triggered scx_bpf_error(). Returning an error code here would lose - * the recorded error information. Exit indicating success so that the - * error is notified through ops.exit() with all the details. + * All tasks are READY. It's safe to turn on scx_enabled() and switch + * all eligible tasks. */ - if (!scx_ops_tryset_enable_state(SCX_OPS_ENABLING, SCX_OPS_PREPPING)) { - preempt_enable(); - spin_unlock_irq(&scx_tasks_lock); - WARN_ON_ONCE(atomic_read(&scx_exit_kind) == SCX_EXIT_NONE); - ret = 0; - goto err_disable_unlock_all; - } + WRITE_ONCE(scx_switching_all, !(ops->flags & SCX_OPS_SWITCH_PARTIAL)); + static_branch_enable(&__scx_ops_enabled); /* - * We're fully committed and can't fail. The PREPPED -> ENABLED + * We're fully committed and can't fail. The task READY -> ENABLED * transitions here are synchronized against sched_ext_free() through * scx_tasks_lock. */ - WRITE_ONCE(scx_switching_all, !(ops->flags & SCX_OPS_SWITCH_PARTIAL)); - + percpu_down_write(&scx_fork_rwsem); + spin_lock_irq(&scx_tasks_lock); scx_task_iter_init(&sti); while ((p = scx_task_iter_next_locked(&sti))) { const struct sched_class *old_class = p->sched_class; @@ -5161,7 +5186,6 @@ static int scx_ops_enable(struct sched_ext_ops *ops, struct bpf_link *link) sched_deq_and_put_task(p, DEQUEUE_SAVE | DEQUEUE_MOVE, &ctx); - scx_set_task_state(p, SCX_TASK_READY); __setscheduler_prio(p, p->prio); check_class_changing(task_rq(p), p, old_class); @@ -5170,14 +5194,16 @@ static int scx_ops_enable(struct sched_ext_ops *ops, struct bpf_link *link) check_class_changed(task_rq(p), p, old_class, p->prio); } scx_task_iter_exit(&sti); - spin_unlock_irq(&scx_tasks_lock); - preempt_enable(); - scx_cgroup_unlock(); - cpus_read_unlock(); percpu_up_write(&scx_fork_rwsem); - /* see above ENABLING transition for the explanation on exiting with 0 */ + scx_ops_bypass(false); + + /* + * Returning an error code here would lose the recorded error + * information. Exit indicating success so that the error is notified + * through ops.exit() with all the details. + */ if (!scx_ops_tryset_enable_state(SCX_OPS_ENABLED, SCX_OPS_ENABLING)) { WARN_ON_ONCE(atomic_read(&scx_exit_kind) == SCX_EXIT_NONE); ret = 0; @@ -5212,8 +5238,7 @@ err_unlock: err_disable_unlock_all: scx_cgroup_unlock(); percpu_up_write(&scx_fork_rwsem); -err_disable_unlock_cpus: - cpus_read_unlock(); + scx_ops_bypass(false); err_disable: mutex_unlock(&scx_ops_enable_mutex); /* must be fully disabled before returning */ @@ -5782,7 +5807,6 @@ void __init init_sched_ext_class(void) SCX_TG_ONLINE); BUG_ON(rhashtable_init(&dsq_hash, &dsq_hash_params)); - init_dsq(&scx_dsq_global, SCX_DSQ_GLOBAL); #ifdef CONFIG_SMP BUG_ON(!alloc_cpumask_var(&idle_masks.cpu, GFP_KERNEL)); BUG_ON(!alloc_cpumask_var(&idle_masks.smt, GFP_KERNEL)); @@ -6058,7 +6082,7 @@ static bool scx_dispatch_from_dsq(struct bpf_iter_scx_dsq_kern *kit, if (dst_dsq->id == SCX_DSQ_LOCAL) { dst_rq = container_of(dst_dsq, struct rq, scx.local_dsq); if (!task_can_run_on_remote_rq(p, dst_rq, true)) { - dst_dsq = &scx_dsq_global; + dst_dsq = find_global_dsq(p); dst_rq = src_rq; } } else { @@ -6175,7 +6199,7 @@ __bpf_kfunc bool scx_bpf_consume(u64 dsq_id) flush_dispatch_buf(dspc->rq); - dsq = find_non_local_dsq(dsq_id); + dsq = find_user_dsq(dsq_id); if (unlikely(!dsq)) { scx_ops_error("invalid DSQ ID 0x%016llx", dsq_id); return false; @@ -6496,7 +6520,7 @@ __bpf_kfunc s32 scx_bpf_dsq_nr_queued(u64 dsq_id) goto out; } } else { - dsq = find_non_local_dsq(dsq_id); + dsq = find_user_dsq(dsq_id); if (dsq) { ret = READ_ONCE(dsq->nr); goto out; @@ -6545,7 +6569,7 @@ __bpf_kfunc int bpf_iter_scx_dsq_new(struct bpf_iter_scx_dsq *it, u64 dsq_id, if (flags & ~__SCX_DSQ_ITER_USER_FLAGS) return -EINVAL; - kit->dsq = find_non_local_dsq(dsq_id); + kit->dsq = find_user_dsq(dsq_id); if (!kit->dsq) return -ENOENT; diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index 020d58967d4e..84dad1511d1e 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -769,12 +769,13 @@ static void record_times(struct psi_group_cpu *groupc, u64 now) } static void psi_group_change(struct psi_group *group, int cpu, - unsigned int clear, unsigned int set, u64 now, + unsigned int clear, unsigned int set, bool wake_clock) { struct psi_group_cpu *groupc; unsigned int t, m; u32 state_mask; + u64 now; lockdep_assert_rq_held(cpu_rq(cpu)); groupc = per_cpu_ptr(group->pcpu, cpu); @@ -789,6 +790,7 @@ static void psi_group_change(struct psi_group *group, int cpu, * SOME and FULL time these may have resulted in. */ write_seqcount_begin(&groupc->seq); + now = cpu_clock(cpu); /* * Start with TSK_ONCPU, which doesn't have a corresponding @@ -899,18 +901,15 @@ void psi_task_change(struct task_struct *task, int clear, int set) { int cpu = task_cpu(task); struct psi_group *group; - u64 now; if (!task->pid) return; psi_flags_change(task, clear, set); - now = cpu_clock(cpu); - group = task_psi_group(task); do { - psi_group_change(group, cpu, clear, set, now, true); + psi_group_change(group, cpu, clear, set, true); } while ((group = group->parent)); } @@ -919,7 +918,6 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next, { struct psi_group *group, *common = NULL; int cpu = task_cpu(prev); - u64 now = cpu_clock(cpu); if (next->pid) { psi_flags_change(next, 0, TSK_ONCPU); @@ -936,7 +934,7 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next, break; } - psi_group_change(group, cpu, 0, TSK_ONCPU, now, true); + psi_group_change(group, cpu, 0, TSK_ONCPU, true); } while ((group = group->parent)); } @@ -974,7 +972,7 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next, do { if (group == common) break; - psi_group_change(group, cpu, clear, set, now, wake_clock); + psi_group_change(group, cpu, clear, set, wake_clock); } while ((group = group->parent)); /* @@ -986,7 +984,7 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next, if ((prev->psi_flags ^ next->psi_flags) & ~TSK_ONCPU) { clear &= ~TSK_ONCPU; for (; group; group = group->parent) - psi_group_change(group, cpu, clear, set, now, wake_clock); + psi_group_change(group, cpu, clear, set, wake_clock); } } } @@ -997,8 +995,8 @@ void psi_account_irqtime(struct rq *rq, struct task_struct *curr, struct task_st int cpu = task_cpu(curr); struct psi_group *group; struct psi_group_cpu *groupc; - u64 now, irq; s64 delta; + u64 irq; if (static_branch_likely(&psi_disabled)) return; @@ -1011,7 +1009,6 @@ void psi_account_irqtime(struct rq *rq, struct task_struct *curr, struct task_st if (prev && task_psi_group(prev) == group) return; - now = cpu_clock(cpu); irq = irq_time_read(cpu); delta = (s64)(irq - rq->psi_irq_time); if (delta < 0) @@ -1019,12 +1016,15 @@ void psi_account_irqtime(struct rq *rq, struct task_struct *curr, struct task_st rq->psi_irq_time = irq; do { + u64 now; + if (!group->enabled) continue; groupc = per_cpu_ptr(group->pcpu, cpu); write_seqcount_begin(&groupc->seq); + now = cpu_clock(cpu); record_times(groupc, now); groupc->times[PSI_IRQ_FULL] += delta; @@ -1223,11 +1223,9 @@ void psi_cgroup_restart(struct psi_group *group) for_each_possible_cpu(cpu) { struct rq *rq = cpu_rq(cpu); struct rq_flags rf; - u64 now; rq_lock_irq(rq, &rf); - now = cpu_clock(cpu); - psi_group_change(group, cpu, 0, 0, now, true); + psi_group_change(group, cpu, 0, 0, true); rq_unlock_irq(rq, &rf); } } diff --git a/kernel/static_call_inline.c b/kernel/static_call_inline.c index 639397b5491c..5259cda486d0 100644 --- a/kernel/static_call_inline.c +++ b/kernel/static_call_inline.c @@ -411,6 +411,17 @@ static void static_call_del_module(struct module *mod) for (site = start; site < stop; site++) { key = static_call_key(site); + + /* + * If the key was not updated due to a memory allocation + * failure in __static_call_init() then treating key::sites + * as key::mods in the code below would cause random memory + * access and #GP. In that case all subsequent sites have + * not been touched either, so stop iterating. + */ + if (!static_call_key_has_mods(key)) + break; + if (key == prev_key) continue; @@ -442,7 +453,7 @@ static int static_call_module_notify(struct notifier_block *nb, case MODULE_STATE_COMING: ret = static_call_add_module(mod); if (ret) { - WARN(1, "Failed to allocate memory for static calls"); + pr_warn("Failed to allocate memory for static calls\n"); static_call_del_module(mod); } break; diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index c01375adc471..1c69ca1f1088 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -3697,8 +3697,8 @@ static void test_can_verify(void) void trace_check_vprintf(struct trace_iterator *iter, const char *fmt, va_list ap) { - long text_delta = iter->tr->text_delta; - long data_delta = iter->tr->data_delta; + long text_delta = 0; + long data_delta = 0; const char *p = fmt; const char *str; bool good; @@ -3710,6 +3710,17 @@ void trace_check_vprintf(struct trace_iterator *iter, const char *fmt, if (static_branch_unlikely(&trace_no_verify)) goto print; + /* + * When the kernel is booted with the tp_printk command line + * parameter, trace events go directly through to printk(). + * It also is checked by this function, but it does not + * have an associated trace_array (tr) for it. + */ + if (iter->tr) { + text_delta = iter->tr->text_delta; + data_delta = iter->tr->data_delta; + } + /* Don't bother checking when doing a ftrace_dump() */ if (iter->fmt == static_fmt_buf) goto print; diff --git a/kernel/trace/trace_hwlat.c b/kernel/trace/trace_hwlat.c index b791524a6536..3bd6071441ad 100644 --- a/kernel/trace/trace_hwlat.c +++ b/kernel/trace/trace_hwlat.c @@ -520,6 +520,8 @@ static void hwlat_hotplug_workfn(struct work_struct *dummy) if (!hwlat_busy || hwlat_data.thread_mode != MODE_PER_CPU) goto out_unlock; + if (!cpu_online(cpu)) + goto out_unlock; if (!cpumask_test_cpu(cpu, tr->tracing_cpumask)) goto out_unlock; diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c index 1439064f65d6..a50ed23bee77 100644 --- a/kernel/trace/trace_osnoise.c +++ b/kernel/trace/trace_osnoise.c @@ -1953,12 +1953,8 @@ static void stop_kthread(unsigned int cpu) { struct task_struct *kthread; - mutex_lock(&interface_lock); - kthread = per_cpu(per_cpu_osnoise_var, cpu).kthread; + kthread = xchg_relaxed(&(per_cpu(per_cpu_osnoise_var, cpu).kthread), NULL); if (kthread) { - per_cpu(per_cpu_osnoise_var, cpu).kthread = NULL; - mutex_unlock(&interface_lock); - if (cpumask_test_and_clear_cpu(cpu, &kthread_cpumask) && !WARN_ON(!test_bit(OSN_WORKLOAD, &osnoise_options))) { kthread_stop(kthread); @@ -1972,7 +1968,6 @@ static void stop_kthread(unsigned int cpu) put_task_struct(kthread); } } else { - mutex_unlock(&interface_lock); /* if no workload, just return */ if (!test_bit(OSN_WORKLOAD, &osnoise_options)) { /* @@ -1994,8 +1989,12 @@ static void stop_per_cpu_kthreads(void) { int cpu; - for_each_possible_cpu(cpu) + cpus_read_lock(); + + for_each_online_cpu(cpu) stop_kthread(cpu); + + cpus_read_unlock(); } /* @@ -2007,6 +2006,10 @@ static int start_kthread(unsigned int cpu) void *main = osnoise_main; char comm[24]; + /* Do not start a new thread if it is already running */ + if (per_cpu(per_cpu_osnoise_var, cpu).kthread) + return 0; + if (timerlat_enabled()) { snprintf(comm, 24, "timerlat/%d", cpu); main = timerlat_main; @@ -2061,11 +2064,10 @@ static int start_per_cpu_kthreads(void) if (cpumask_test_and_clear_cpu(cpu, &kthread_cpumask)) { struct task_struct *kthread; - kthread = per_cpu(per_cpu_osnoise_var, cpu).kthread; + kthread = xchg_relaxed(&(per_cpu(per_cpu_osnoise_var, cpu).kthread), NULL); if (!WARN_ON(!kthread)) kthread_stop(kthread); } - per_cpu(per_cpu_osnoise_var, cpu).kthread = NULL; } for_each_cpu(cpu, current_mask) { @@ -2095,6 +2097,8 @@ static void osnoise_hotplug_workfn(struct work_struct *dummy) mutex_lock(&interface_lock); cpus_read_lock(); + if (!cpu_online(cpu)) + goto out_unlock; if (!cpumask_test_cpu(cpu, &osnoise_cpumask)) goto out_unlock; diff --git a/lib/842/842.h b/lib/842/842.h index 7b1f581a2907..f9e8a5dd790f 100644 --- a/lib/842/842.h +++ b/lib/842/842.h @@ -78,7 +78,7 @@ #include <linux/kernel.h> #include <linux/bitops.h> #include <linux/crc32.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/sw842.h> diff --git a/lib/crypto/aes.c b/lib/crypto/aes.c index 827fe89922ff..eafe14d021f5 100644 --- a/lib/crypto/aes.c +++ b/lib/crypto/aes.c @@ -6,7 +6,7 @@ #include <crypto/aes.h> #include <linux/crypto.h> #include <linux/module.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /* * Emit the sbox as volatile const to prevent the compiler from doing diff --git a/lib/crypto/blake2s-generic.c b/lib/crypto/blake2s-generic.c index 3b6dcfdd9628..09682136b57c 100644 --- a/lib/crypto/blake2s-generic.c +++ b/lib/crypto/blake2s-generic.c @@ -14,7 +14,7 @@ #include <linux/kernel.h> #include <linux/init.h> #include <linux/bug.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> static const u8 blake2s_sigma[10][16] = { { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 }, diff --git a/lib/crypto/chacha.c b/lib/crypto/chacha.c index b748fd3d256e..3cdda3b5ee06 100644 --- a/lib/crypto/chacha.c +++ b/lib/crypto/chacha.c @@ -10,7 +10,7 @@ #include <linux/export.h> #include <linux/bitops.h> #include <linux/string.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <crypto/chacha.h> static void chacha_permute(u32 *x, int nrounds) diff --git a/lib/crypto/chacha20poly1305-selftest.c b/lib/crypto/chacha20poly1305-selftest.c index fa43deda2660..2ea61c28be4f 100644 --- a/lib/crypto/chacha20poly1305-selftest.c +++ b/lib/crypto/chacha20poly1305-selftest.c @@ -7,7 +7,7 @@ #include <crypto/chacha.h> #include <crypto/poly1305.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/bug.h> #include <linux/init.h> #include <linux/mm.h> diff --git a/lib/crypto/chacha20poly1305.c b/lib/crypto/chacha20poly1305.c index fa6a9440fc95..a839c0ac60b2 100644 --- a/lib/crypto/chacha20poly1305.c +++ b/lib/crypto/chacha20poly1305.c @@ -13,7 +13,7 @@ #include <crypto/poly1305.h> #include <crypto/scatterwalk.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/kernel.h> #include <linux/init.h> #include <linux/mm.h> diff --git a/lib/crypto/curve25519-fiat32.c b/lib/crypto/curve25519-fiat32.c index 2fde0ec33dbd..2e0ba634e299 100644 --- a/lib/crypto/curve25519-fiat32.c +++ b/lib/crypto/curve25519-fiat32.c @@ -10,7 +10,7 @@ * with 128-bit integer types. */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <crypto/curve25519.h> #include <linux/string.h> diff --git a/lib/crypto/curve25519-hacl64.c b/lib/crypto/curve25519-hacl64.c index c40e5d913234..c4204133afb7 100644 --- a/lib/crypto/curve25519-hacl64.c +++ b/lib/crypto/curve25519-hacl64.c @@ -10,7 +10,7 @@ * integer types. */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <crypto/curve25519.h> #include <linux/string.h> diff --git a/lib/crypto/des.c b/lib/crypto/des.c index 9518658b97cf..d3423b34a8e9 100644 --- a/lib/crypto/des.c +++ b/lib/crypto/des.c @@ -17,7 +17,7 @@ #include <linux/string.h> #include <linux/types.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <crypto/des.h> #include <crypto/internal/des.h> diff --git a/lib/crypto/memneq.c b/lib/crypto/memneq.c index 243d8677cc51..a2afd10349c9 100644 --- a/lib/crypto/memneq.c +++ b/lib/crypto/memneq.c @@ -59,7 +59,7 @@ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <crypto/algapi.h> #include <linux/module.h> diff --git a/lib/crypto/poly1305-donna32.c b/lib/crypto/poly1305-donna32.c index 7fb71845cc84..0a4a2d99e365 100644 --- a/lib/crypto/poly1305-donna32.c +++ b/lib/crypto/poly1305-donna32.c @@ -7,7 +7,7 @@ */ #include <linux/kernel.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <crypto/internal/poly1305.h> void poly1305_core_setkey(struct poly1305_core_key *key, diff --git a/lib/crypto/poly1305-donna64.c b/lib/crypto/poly1305-donna64.c index 988702c9b3b2..530287531b2e 100644 --- a/lib/crypto/poly1305-donna64.c +++ b/lib/crypto/poly1305-donna64.c @@ -7,7 +7,7 @@ */ #include <linux/kernel.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <crypto/internal/poly1305.h> void poly1305_core_setkey(struct poly1305_core_key *key, diff --git a/lib/crypto/poly1305.c b/lib/crypto/poly1305.c index 5d8378d23e95..6e80214ebad8 100644 --- a/lib/crypto/poly1305.c +++ b/lib/crypto/poly1305.c @@ -10,7 +10,7 @@ #include <crypto/internal/poly1305.h> #include <linux/kernel.h> #include <linux/module.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> void poly1305_init_generic(struct poly1305_desc_ctx *desc, const u8 key[POLY1305_KEY_SIZE]) diff --git a/lib/crypto/sha1.c b/lib/crypto/sha1.c index 6d2922747cab..ebb60519ae93 100644 --- a/lib/crypto/sha1.c +++ b/lib/crypto/sha1.c @@ -12,7 +12,7 @@ #include <linux/bitops.h> #include <linux/string.h> #include <crypto/sha1.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /* * If you have 32 registers or more, the compiler can (and should) diff --git a/lib/crypto/sha256.c b/lib/crypto/sha256.c index 3f42d203c7bc..04c1f2557e6c 100644 --- a/lib/crypto/sha256.c +++ b/lib/crypto/sha256.c @@ -11,7 +11,7 @@ * Copyright (c) 2014 Red Hat Inc. */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <crypto/sha256_base.h> #include <linux/kernel.h> #include <linux/module.h> diff --git a/lib/crypto/utils.c b/lib/crypto/utils.c index 373364141408..87da2a6dd161 100644 --- a/lib/crypto/utils.c +++ b/lib/crypto/utils.c @@ -5,7 +5,7 @@ * Copyright (c) 2006 Herbert Xu <herbert@gondor.apana.org.au> */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <crypto/utils.h> #include <linux/module.h> diff --git a/lib/decompress_unlz4.c b/lib/decompress_unlz4.c index e6327391b6b6..c0dbb3cea915 100644 --- a/lib/decompress_unlz4.c +++ b/lib/decompress_unlz4.c @@ -16,7 +16,7 @@ #include <linux/decompress/mm.h> #include <linux/compiler.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /* * Note: Uncompressed chunk size is used in the compressor side diff --git a/lib/decompress_unlzo.c b/lib/decompress_unlzo.c index 64c1358500ce..57a9e93743e1 100644 --- a/lib/decompress_unlzo.c +++ b/lib/decompress_unlzo.c @@ -28,7 +28,7 @@ #include <linux/decompress/mm.h> #include <linux/compiler.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> static const unsigned char lzop_magic[] = { 0x89, 0x4c, 0x5a, 0x4f, 0x00, 0x0d, 0x0a, 0x1a, 0x0a }; diff --git a/lib/hexdump.c b/lib/hexdump.c index 06833d404398..c3db7c3a7643 100644 --- a/lib/hexdump.c +++ b/lib/hexdump.c @@ -9,7 +9,7 @@ #include <linux/kernel.h> #include <linux/minmax.h> #include <linux/export.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> const char hex_asc[] = "0123456789abcdef"; EXPORT_SYMBOL(hex_asc); diff --git a/lib/iov_iter.c b/lib/iov_iter.c index 97003155bfac..1abb32c0da50 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -1033,7 +1033,7 @@ static ssize_t iter_folioq_get_pages(struct iov_iter *iter, if (maxpages == 0 || extracted >= maxsize) break; - if (offset >= fsize) { + if (iov_offset >= fsize) { iov_offset = 0; slot++; if (slot == folioq_nr_slots(folioq) && folioq->next) { diff --git a/lib/lz4/lz4_compress.c b/lib/lz4/lz4_compress.c index 90bb67994688..b0bbeeb74b9e 100644 --- a/lib/lz4/lz4_compress.c +++ b/lib/lz4/lz4_compress.c @@ -37,7 +37,7 @@ #include "lz4defs.h" #include <linux/module.h> #include <linux/kernel.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> static const int LZ4_minLength = (MFLIMIT + 1); static const int LZ4_64Klimit = ((64 * KB) + (MFLIMIT - 1)); diff --git a/lib/lz4/lz4_decompress.c b/lib/lz4/lz4_decompress.c index 59fe69a63800..0e31e6da5ce7 100644 --- a/lib/lz4/lz4_decompress.c +++ b/lib/lz4/lz4_decompress.c @@ -38,7 +38,7 @@ #include <linux/init.h> #include <linux/module.h> #include <linux/kernel.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /*-***************************** * Decompression functions diff --git a/lib/lz4/lz4defs.h b/lib/lz4/lz4defs.h index 330aa539b46e..cb358d6bde5a 100644 --- a/lib/lz4/lz4defs.h +++ b/lib/lz4/lz4defs.h @@ -35,7 +35,7 @@ * Sven Schmidt <4sschmid@informatik.uni-hamburg.de> */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/bitops.h> #include <linux/string.h> /* memset, memcpy */ diff --git a/lib/lzo/lzo1x_compress.c b/lib/lzo/lzo1x_compress.c index 9d31e7126606..47d6d43ea957 100644 --- a/lib/lzo/lzo1x_compress.c +++ b/lib/lzo/lzo1x_compress.c @@ -14,7 +14,7 @@ #include <linux/module.h> #include <linux/kernel.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/lzo.h> #include "lzodefs.h" diff --git a/lib/lzo/lzo1x_decompress_safe.c b/lib/lzo/lzo1x_decompress_safe.c index 7892a40cf765..c94f4928e188 100644 --- a/lib/lzo/lzo1x_decompress_safe.c +++ b/lib/lzo/lzo1x_decompress_safe.c @@ -16,7 +16,7 @@ #include <linux/module.h> #include <linux/kernel.h> #endif -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/lzo.h> #include "lzodefs.h" diff --git a/lib/pldmfw/pldmfw.c b/lib/pldmfw/pldmfw.c index 54e1809a38fd..6e1581b9a616 100644 --- a/lib/pldmfw/pldmfw.c +++ b/lib/pldmfw/pldmfw.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (C) 2018-2019, Intel Corporation. */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/crc32.h> #include <linux/device.h> #include <linux/firmware.h> diff --git a/lib/random32.c b/lib/random32.c index 32060b852668..0a5a0e3600c8 100644 --- a/lib/random32.c +++ b/lib/random32.c @@ -40,7 +40,7 @@ #include <linux/sched.h> #include <linux/bitops.h> #include <linux/slab.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /** * prandom_u32_state - seeded pseudo-random number generator. diff --git a/lib/siphash.c b/lib/siphash.c index 15bc5b6f368c..9e4e88752d2e 100644 --- a/lib/siphash.c +++ b/lib/siphash.c @@ -10,7 +10,7 @@ */ #include <linux/siphash.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #if defined(CONFIG_DCACHE_WORD_ACCESS) && BITS_PER_LONG == 64 #include <linux/dcache.h> diff --git a/lib/slub_kunit.c b/lib/slub_kunit.c index 6e3a1e5a7142..80e39f003344 100644 --- a/lib/slub_kunit.c +++ b/lib/slub_kunit.c @@ -164,10 +164,16 @@ struct test_kfree_rcu_struct { static void test_kfree_rcu(struct kunit *test) { - struct kmem_cache *s = test_kmem_cache_create("TestSlub_kfree_rcu", - sizeof(struct test_kfree_rcu_struct), - SLAB_NO_MERGE); - struct test_kfree_rcu_struct *p = kmem_cache_alloc(s, GFP_KERNEL); + struct kmem_cache *s; + struct test_kfree_rcu_struct *p; + + if (IS_BUILTIN(CONFIG_SLUB_KUNIT_TEST)) + kunit_skip(test, "can't do kfree_rcu() when test is built-in"); + + s = test_kmem_cache_create("TestSlub_kfree_rcu", + sizeof(struct test_kfree_rcu_struct), + SLAB_NO_MERGE); + p = kmem_cache_alloc(s, GFP_KERNEL); kfree_rcu(p, rcu); kmem_cache_destroy(s); @@ -177,13 +183,13 @@ static void test_kfree_rcu(struct kunit *test) static void test_leak_destroy(struct kunit *test) { - struct kmem_cache *s = test_kmem_cache_create("TestSlub_kfree_rcu", + struct kmem_cache *s = test_kmem_cache_create("TestSlub_leak_destroy", 64, SLAB_NO_MERGE); kmem_cache_alloc(s, GFP_KERNEL); kmem_cache_destroy(s); - KUNIT_EXPECT_EQ(test, 1, slab_errors); + KUNIT_EXPECT_EQ(test, 2, slab_errors); } static int test_init(struct kunit *test) diff --git a/lib/string.c b/lib/string.c index 966da44bfc86..76327b51e36f 100644 --- a/lib/string.c +++ b/lib/string.c @@ -27,7 +27,7 @@ #include <asm/page.h> #include <asm/rwonce.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <asm/word-at-a-time.h> #ifndef __HAVE_ARCH_STRNCASECMP diff --git a/lib/test_bits.c b/lib/test_bits.c index 01313980f175..c7b38d91e1f1 100644 --- a/lib/test_bits.c +++ b/lib/test_bits.c @@ -39,6 +39,36 @@ static void genmask_ull_test(struct kunit *test) #endif } +static void genmask_u128_test(struct kunit *test) +{ +#ifdef CONFIG_ARCH_SUPPORTS_INT128 + /* Below 64 bit masks */ + KUNIT_EXPECT_EQ(test, 0x0000000000000001ull, GENMASK_U128(0, 0)); + KUNIT_EXPECT_EQ(test, 0x0000000000000003ull, GENMASK_U128(1, 0)); + KUNIT_EXPECT_EQ(test, 0x0000000000000006ull, GENMASK_U128(2, 1)); + KUNIT_EXPECT_EQ(test, 0x00000000ffffffffull, GENMASK_U128(31, 0)); + KUNIT_EXPECT_EQ(test, 0x000000ffffe00000ull, GENMASK_U128(39, 21)); + KUNIT_EXPECT_EQ(test, 0xffffffffffffffffull, GENMASK_U128(63, 0)); + + /* Above 64 bit masks - only 64 bit portion can be validated once */ + KUNIT_EXPECT_EQ(test, 0xffffffffffffffffull, GENMASK_U128(64, 0) >> 1); + KUNIT_EXPECT_EQ(test, 0x00000000ffffffffull, GENMASK_U128(81, 50) >> 50); + KUNIT_EXPECT_EQ(test, 0x0000000000ffffffull, GENMASK_U128(87, 64) >> 64); + KUNIT_EXPECT_EQ(test, 0x0000000000ff0000ull, GENMASK_U128(87, 80) >> 64); + + KUNIT_EXPECT_EQ(test, 0xffffffffffffffffull, GENMASK_U128(127, 0) >> 64); + KUNIT_EXPECT_EQ(test, 0xffffffffffffffffull, (u64)GENMASK_U128(127, 0)); + KUNIT_EXPECT_EQ(test, 0x0000000000000003ull, GENMASK_U128(127, 126) >> 126); + KUNIT_EXPECT_EQ(test, 0x0000000000000001ull, GENMASK_U128(127, 127) >> 127); +#ifdef TEST_GENMASK_FAILURES + /* these should fail compilation */ + GENMASK_U128(0, 1); + GENMASK_U128(0, 10); + GENMASK_U128(9, 10); +#endif /* TEST_GENMASK_FAILURES */ +#endif /* CONFIG_ARCH_SUPPORTS_INT128 */ +} + static void genmask_input_check_test(struct kunit *test) { unsigned int x, y; @@ -56,12 +86,16 @@ static void genmask_input_check_test(struct kunit *test) /* Valid input */ KUNIT_EXPECT_EQ(test, 0, GENMASK_INPUT_CHECK(1, 1)); KUNIT_EXPECT_EQ(test, 0, GENMASK_INPUT_CHECK(39, 21)); + KUNIT_EXPECT_EQ(test, 0, GENMASK_INPUT_CHECK(100, 80)); + KUNIT_EXPECT_EQ(test, 0, GENMASK_INPUT_CHECK(110, 65)); + KUNIT_EXPECT_EQ(test, 0, GENMASK_INPUT_CHECK(127, 0)); } static struct kunit_case bits_test_cases[] = { KUNIT_CASE(genmask_test), KUNIT_CASE(genmask_ull_test), + KUNIT_CASE(genmask_u128_test), KUNIT_CASE(genmask_input_check_test), {} }; diff --git a/lib/vsprintf.c b/lib/vsprintf.c index 09f022ba1c05..c5e2ec9303c5 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -51,7 +51,7 @@ #include <asm/page.h> /* for PAGE_SIZE */ #include <asm/byteorder.h> /* cpu_to_le16 */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/string_helpers.h> #include "kstrtox.h" diff --git a/lib/xxhash.c b/lib/xxhash.c index d5bb9ff10607..b5bd567aa6b3 100644 --- a/lib/xxhash.c +++ b/lib/xxhash.c @@ -38,7 +38,7 @@ * - xxHash source repository: https://github.com/Cyan4973/xxHash */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/errno.h> #include <linux/compiler.h> #include <linux/kernel.h> diff --git a/lib/xz/xz_private.h b/lib/xz/xz_private.h index 5f1294a1408c..8409784b1639 100644 --- a/lib/xz/xz_private.h +++ b/lib/xz/xz_private.h @@ -12,7 +12,7 @@ #ifdef __KERNEL__ # include <linux/xz.h> # include <linux/kernel.h> -# include <asm/unaligned.h> +# include <linux/unaligned.h> /* XZ_PREBOOT may be defined only via decompress_unxz.c. */ # ifndef XZ_PREBOOT # include <linux/slab.h> diff --git a/lib/zstd/common/mem.h b/lib/zstd/common/mem.h index 1d9cc03924ca..c22a2e69bf46 100644 --- a/lib/zstd/common/mem.h +++ b/lib/zstd/common/mem.h @@ -15,7 +15,7 @@ /*-**************************************** * Dependencies ******************************************/ -#include <asm/unaligned.h> /* get_unaligned, put_unaligned* */ +#include <linux/unaligned.h> /* get_unaligned, put_unaligned* */ #include <linux/compiler.h> /* inline */ #include <linux/swab.h> /* swab32, swab64 */ #include <linux/types.h> /* size_t, ptrdiff_t */ diff --git a/mm/slab.h b/mm/slab.h index f22fb760b286..6c6fe6d630ce 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -310,7 +310,7 @@ struct kmem_cache { }; #if defined(CONFIG_SYSFS) && !defined(CONFIG_SLUB_TINY) -#define SLAB_SUPPORTS_SYSFS +#define SLAB_SUPPORTS_SYSFS 1 void sysfs_slab_unlink(struct kmem_cache *s); void sysfs_slab_release(struct kmem_cache *s); #else @@ -546,6 +546,12 @@ static inline bool kmem_cache_debug_flags(struct kmem_cache *s, slab_flags_t fla return false; } +#if IS_ENABLED(CONFIG_SLUB_DEBUG) && IS_ENABLED(CONFIG_KUNIT) +bool slab_in_kunit_test(void); +#else +static inline bool slab_in_kunit_test(void) { return false; } +#endif + #ifdef CONFIG_SLAB_OBJ_EXT /* diff --git a/mm/slab_common.c b/mm/slab_common.c index 744324465615..3d26c257ed8b 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -508,8 +508,9 @@ void kmem_cache_destroy(struct kmem_cache *s) kasan_cache_shutdown(s); err = __kmem_cache_shutdown(s); - WARN(err, "%s %s: Slab cache still has objects when called from %pS", - __func__, s->name, (void *)_RET_IP_); + if (!slab_in_kunit_test()) + WARN(err, "%s %s: Slab cache still has objects when called from %pS", + __func__, s->name, (void *)_RET_IP_); list_del(&s->list); diff --git a/mm/slub.c b/mm/slub.c index 21f71cb6cc06..5b832512044e 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -827,7 +827,7 @@ static bool slab_add_kunit_errors(void) return true; } -static bool slab_in_kunit_test(void) +bool slab_in_kunit_test(void) { struct kunit_resource *resource; @@ -843,7 +843,6 @@ static bool slab_in_kunit_test(void) } #else static inline bool slab_add_kunit_errors(void) { return false; } -static inline bool slab_in_kunit_test(void) { return false; } #endif static inline unsigned int size_from_object(struct kmem_cache *s) @@ -5436,6 +5435,8 @@ static void list_slab_objects(struct kmem_cache *s, struct slab *slab, for_each_object(p, s, addr, slab->objects) { if (!test_bit(__obj_to_index(s, addr, p), object_map)) { + if (slab_add_kunit_errors()) + continue; pr_err("Object 0x%p @offset=%tu\n", p, p - addr); print_tracking(s, p); } diff --git a/net/802/garp.c b/net/802/garp.c index 6a743d004301..27f0ab146026 100644 --- a/net/802/garp.c +++ b/net/802/garp.c @@ -16,7 +16,7 @@ #include <net/llc.h> #include <net/llc_pdu.h> #include <net/garp.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> static unsigned int garp_join_time __read_mostly = 200; module_param(garp_join_time, uint, 0644); diff --git a/net/802/mrp.c b/net/802/mrp.c index 3154d7409493..e0c96d0da8d5 100644 --- a/net/802/mrp.c +++ b/net/802/mrp.c @@ -16,7 +16,7 @@ #include <linux/slab.h> #include <linux/module.h> #include <net/mrp.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> static unsigned int mrp_join_time __read_mostly = 200; module_param(mrp_join_time, uint, 0644); diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c index 4c7e85534324..801eff8a40e5 100644 --- a/net/batman-adv/distributed-arp-table.c +++ b/net/batman-adv/distributed-arp-table.c @@ -7,7 +7,7 @@ #include "distributed-arp-table.h" #include "main.h" -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/atomic.h> #include <linux/bitops.h> #include <linux/byteorder/generic.h> diff --git a/net/bluetooth/bnep/core.c b/net/bluetooth/bnep/core.c index ec45f77fce21..a3bc0934cc13 100644 --- a/net/bluetooth/bnep/core.c +++ b/net/bluetooth/bnep/core.c @@ -29,7 +29,7 @@ #include <linux/kthread.h> #include <linux/file.h> #include <linux/etherdevice.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/l2cap.h> diff --git a/net/bluetooth/coredump.c b/net/bluetooth/coredump.c index ec97a4bab1c9..c18df3a08607 100644 --- a/net/bluetooth/coredump.c +++ b/net/bluetooth/coredump.c @@ -5,7 +5,7 @@ #include <linux/devcoredump.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> diff --git a/net/bluetooth/eir.h b/net/bluetooth/eir.h index 0df19f2f4af9..5c89a05e8b29 100644 --- a/net/bluetooth/eir.h +++ b/net/bluetooth/eir.h @@ -5,7 +5,7 @@ * Copyright (C) 2021 Intel Corporation */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> void eir_create(struct hci_dev *hdev, u8 *data); diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index d6976db02c06..629c302f7407 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -33,7 +33,7 @@ #include <linux/property.h> #include <linux/suspend.h> #include <linux/wait.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> @@ -3782,6 +3782,8 @@ static void hci_acldata_packet(struct hci_dev *hdev, struct sk_buff *skb) hci_dev_lock(hdev); conn = hci_conn_hash_lookup_handle(hdev, handle); + if (conn && hci_dev_test_flag(hdev, HCI_MGMT)) + mgmt_device_connected(hdev, conn, NULL, 0); hci_dev_unlock(hdev); if (conn) { diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 1c82dcdf6e8f..0bbad90ddd6f 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -25,7 +25,7 @@ /* Bluetooth HCI event handling. */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/crypto.h> #include <crypto/algapi.h> @@ -3706,7 +3706,7 @@ static void hci_remote_features_evt(struct hci_dev *hdev, void *data, goto unlock; } - if (!ev->status && !test_bit(HCI_CONN_MGMT_CONNECTED, &conn->flags)) { + if (!ev->status) { struct hci_cp_remote_name_req cp; memset(&cp, 0, sizeof(cp)); bacpy(&cp.bdaddr, &conn->dst); @@ -5324,19 +5324,16 @@ static void hci_user_confirm_request_evt(struct hci_dev *hdev, void *data, goto unlock; } - /* If no side requires MITM protection; auto-accept */ + /* If no side requires MITM protection; use JUST_CFM method */ if ((!loc_mitm || conn->remote_cap == HCI_IO_NO_INPUT_OUTPUT) && (!rem_mitm || conn->io_capability == HCI_IO_NO_INPUT_OUTPUT)) { - /* If we're not the initiators request authorization to - * proceed from user space (mgmt_user_confirm with - * confirm_hint set to 1). The exception is if neither - * side had MITM or if the local IO capability is - * NoInputNoOutput, in which case we do auto-accept + /* If we're not the initiator of request authorization and the + * local IO capability is not NoInputNoOutput, use JUST_WORKS + * method (mgmt_user_confirm with confirm_hint set to 1). */ if (!test_bit(HCI_CONN_AUTH_PEND, &conn->flags) && - conn->io_capability != HCI_IO_NO_INPUT_OUTPUT && - (loc_mitm || rem_mitm)) { + conn->io_capability != HCI_IO_NO_INPUT_OUTPUT) { bt_dev_dbg(hdev, "Confirming auto-accept as acceptor"); confirm_hint = 1; goto confirm; diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index 69c2ba1e843e..2272e1849ebd 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -27,7 +27,7 @@ #include <linux/export.h> #include <linux/utsname.h> #include <linux/sched.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 9988ba382b68..6544c1ed7143 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -4066,17 +4066,9 @@ response: static int l2cap_connect_req(struct l2cap_conn *conn, struct l2cap_cmd_hdr *cmd, u16 cmd_len, u8 *data) { - struct hci_dev *hdev = conn->hcon->hdev; - struct hci_conn *hcon = conn->hcon; - if (cmd_len < sizeof(struct l2cap_conn_req)) return -EPROTO; - hci_dev_lock(hdev); - if (hci_dev_test_flag(hdev, HCI_MGMT)) - mgmt_device_connected(hdev, hcon, NULL, 0); - hci_dev_unlock(hdev); - l2cap_connect(conn, cmd, data, L2CAP_CONN_RSP); return 0; } diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index e4f564d6f6fb..a429661b676a 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -25,7 +25,7 @@ /* Bluetooth HCI Management interface */ #include <linux/module.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> @@ -1453,10 +1453,15 @@ static void cmd_status_rsp(struct mgmt_pending_cmd *cmd, void *data) static void cmd_complete_rsp(struct mgmt_pending_cmd *cmd, void *data) { - if (cmd->cmd_complete) { - u8 *status = data; + struct cmd_lookup *match = data; + + /* dequeue cmd_sync entries using cmd as data as that is about to be + * removed/freed. + */ + hci_cmd_sync_dequeue(match->hdev, NULL, cmd, NULL); - cmd->cmd_complete(cmd, *status); + if (cmd->cmd_complete) { + cmd->cmd_complete(cmd, match->mgmt_status); mgmt_pending_remove(cmd); return; @@ -9394,12 +9399,12 @@ void mgmt_index_added(struct hci_dev *hdev) void mgmt_index_removed(struct hci_dev *hdev) { struct mgmt_ev_ext_index ev; - u8 status = MGMT_STATUS_INVALID_INDEX; + struct cmd_lookup match = { NULL, hdev, MGMT_STATUS_INVALID_INDEX }; if (test_bit(HCI_QUIRK_RAW_DEVICE, &hdev->quirks)) return; - mgmt_pending_foreach(0, hdev, cmd_complete_rsp, &status); + mgmt_pending_foreach(0, hdev, cmd_complete_rsp, &match); if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) { mgmt_index_event(MGMT_EV_UNCONF_INDEX_REMOVED, hdev, NULL, 0, @@ -9450,7 +9455,7 @@ void mgmt_power_on(struct hci_dev *hdev, int err) void __mgmt_power_off(struct hci_dev *hdev) { struct cmd_lookup match = { NULL, hdev }; - u8 status, zero_cod[] = { 0, 0, 0 }; + u8 zero_cod[] = { 0, 0, 0 }; mgmt_pending_foreach(MGMT_OP_SET_POWERED, hdev, settings_rsp, &match); @@ -9462,11 +9467,11 @@ void __mgmt_power_off(struct hci_dev *hdev) * status responses. */ if (hci_dev_test_flag(hdev, HCI_UNREGISTER)) - status = MGMT_STATUS_INVALID_INDEX; + match.mgmt_status = MGMT_STATUS_INVALID_INDEX; else - status = MGMT_STATUS_NOT_POWERED; + match.mgmt_status = MGMT_STATUS_NOT_POWERED; - mgmt_pending_foreach(0, hdev, cmd_complete_rsp, &status); + mgmt_pending_foreach(0, hdev, cmd_complete_rsp, &match); if (memcmp(hdev->dev_class, zero_cod, sizeof(zero_cod)) != 0) { mgmt_limited_event(MGMT_EV_CLASS_OF_DEV_CHANGED, hdev, diff --git a/net/bluetooth/mgmt_util.c b/net/bluetooth/mgmt_util.c index 0115f783bde8..17ab909a7c07 100644 --- a/net/bluetooth/mgmt_util.c +++ b/net/bluetooth/mgmt_util.c @@ -21,7 +21,7 @@ SOFTWARE IS DISCLAIMED. */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c index 1d34d8497033..ad5177e3a69b 100644 --- a/net/bluetooth/rfcomm/core.c +++ b/net/bluetooth/rfcomm/core.c @@ -28,7 +28,7 @@ #include <linux/module.h> #include <linux/debugfs.h> #include <linux/kthread.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index ad7a42b505ef..642b8ccaae8e 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -18,7 +18,7 @@ #include <linux/random.h> #include <linux/slab.h> #include <linux/atomic.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/if_vlan.h> #include <net/switchdev.h> #include <trace/events/bridge.h> diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index bc37e47ad829..1a52a0bca086 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -1674,7 +1674,7 @@ int br_mdb_get(struct net_device *dev, struct nlattr *tb[], u32 portid, u32 seq, spin_lock_bh(&br->multicast_lock); mp = br_mdb_ip_get(br, &group); - if (!mp) { + if (!mp || (!mp->ports && !mp->host_joined)) { NL_SET_ERR_MSG_MOD(extack, "MDB entry not found"); err = -ENOENT; goto unlock; diff --git a/net/bridge/br_stp_bpdu.c b/net/bridge/br_stp_bpdu.c index 0e4572f31330..7895489ac6fe 100644 --- a/net/bridge/br_stp_bpdu.c +++ b/net/bridge/br_stp_bpdu.c @@ -17,7 +17,7 @@ #include <net/llc.h> #include <net/llc_pdu.h> #include <net/stp.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "br_private.h" #include "br_private_stp.h" diff --git a/net/caif/cfrfml.c b/net/caif/cfrfml.c index 7b0af33bdb97..3c335057f255 100644 --- a/net/caif/cfrfml.c +++ b/net/caif/cfrfml.c @@ -9,7 +9,7 @@ #include <linux/stddef.h> #include <linux/spinlock.h> #include <linux/slab.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <net/caif/caif_layer.h> #include <net/caif/cfsrvl.h> #include <net/caif/cfpkt.h> diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 3c8b78d9c4d1..d1b5705dc0c6 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -1254,7 +1254,7 @@ static int ceph_dns_resolve_name(const char *name, size_t namelen, colon_p = memchr(name, ':', namelen); if (delim_p && colon_p) - end = delim_p < colon_p ? delim_p : colon_p; + end = min(delim_p, colon_p); else if (!delim_p && colon_p) end = colon_p; else { diff --git a/net/core/dev.c b/net/core/dev.c index cd479f5f22f6..ea5fbcd133ae 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3512,7 +3512,7 @@ static netdev_features_t gso_features_check(const struct sk_buff *skb, if (gso_segs > READ_ONCE(dev->gso_max_segs)) return features & ~NETIF_F_GSO_MASK; - if (unlikely(skb->len >= READ_ONCE(dev->gso_max_size))) + if (unlikely(skb->len >= netif_get_gso_max_size(dev, skb))) return features & ~NETIF_F_GSO_MASK; if (!skb_shinfo(skb)->gso_type) { @@ -3758,7 +3758,7 @@ static void qdisc_pkt_len_init(struct sk_buff *skb) sizeof(_tcphdr), &_tcphdr); if (likely(th)) hdr_len += __tcp_hdrlen(th); - } else { + } else if (shinfo->gso_type & SKB_GSO_UDP_L4) { struct udphdr _udphdr; if (skb_header_pointer(skb, hdr_len, @@ -3766,10 +3766,14 @@ static void qdisc_pkt_len_init(struct sk_buff *skb) hdr_len += sizeof(struct udphdr); } - if (shinfo->gso_type & SKB_GSO_DODGY) - gso_segs = DIV_ROUND_UP(skb->len - hdr_len, - shinfo->gso_size); + if (unlikely(shinfo->gso_type & SKB_GSO_DODGY)) { + int payload = skb->len - hdr_len; + /* Malicious packet. */ + if (payload <= 0) + return; + gso_segs = DIV_ROUND_UP(payload, shinfo->gso_size); + } qdisc_skb_cb(skb)->pkt_len += (gso_segs - 1) * hdr_len; } } diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index 2e0ae3328232..6efd4cccc9dd 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -37,7 +37,7 @@ #include <trace/events/napi.h> #include <trace/events/devlink.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define TRACE_ON 1 #define TRACE_OFF 0 diff --git a/net/core/filter.c b/net/core/filter.c index cd3524cb326b..bd0d08bf76bb 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -42,7 +42,7 @@ #include <linux/errno.h> #include <linux/timer.h> #include <linux/uaccess.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/filter.h> #include <linux/ratelimit.h> #include <linux/seccomp.h> diff --git a/net/core/gro.c b/net/core/gro.c index 802b4a062400..d1f44084e978 100644 --- a/net/core/gro.c +++ b/net/core/gro.c @@ -98,7 +98,6 @@ int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb) unsigned int headlen = skb_headlen(skb); unsigned int len = skb_gro_len(skb); unsigned int delta_truesize; - unsigned int gro_max_size; unsigned int new_truesize; struct sk_buff *lp; int segs; @@ -112,12 +111,8 @@ int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb) if (p->pp_recycle != skb->pp_recycle) return -ETOOMANYREFS; - /* pairs with WRITE_ONCE() in netif_set_gro(_ipv4)_max_size() */ - gro_max_size = p->protocol == htons(ETH_P_IPV6) ? - READ_ONCE(p->dev->gro_max_size) : - READ_ONCE(p->dev->gro_ipv4_max_size); - - if (unlikely(p->len + len >= gro_max_size || NAPI_GRO_CB(skb)->flush)) + if (unlikely(p->len + len >= netif_get_gro_max_size(p->dev, p) || + NAPI_GRO_CB(skb)->flush)) return -E2BIG; if (unlikely(p->len + len >= GRO_LEGACY_MAX_SIZE)) { diff --git a/net/core/net-traces.c b/net/core/net-traces.c index 6aef976bc1da..f2fa34b1d78d 100644 --- a/net/core/net-traces.c +++ b/net/core/net-traces.c @@ -23,7 +23,7 @@ #include <linux/net_dropmon.h> #include <linux/slab.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <asm/bitops.h> #define CREATE_TRACE_POINTS diff --git a/net/core/netpoll.c b/net/core/netpoll.c index ca52cbe0f63c..aa49b92e9194 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -34,7 +34,7 @@ #include <net/addrconf.h> #include <net/ndisc.h> #include <net/ip6_checksum.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <trace/events/napi.h> #include <linux/kconfig.h> diff --git a/net/core/sock.c b/net/core/sock.c index fe87f9bd8f16..039be95c40cf 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -85,7 +85,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/capability.h> #include <linux/errno.h> #include <linux/errqueue.h> diff --git a/net/core/tso.c b/net/core/tso.c index e00796e3b146..6df997b9076e 100644 --- a/net/core/tso.c +++ b/net/core/tso.c @@ -3,7 +3,7 @@ #include <linux/if_vlan.h> #include <net/ip.h> #include <net/tso.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> void tso_build_hdr(const struct sk_buff *skb, char *hdr, struct tso_t *tso, int size, bool is_last) diff --git a/net/dccp/ccids/ccid3.c b/net/dccp/ccids/ccid3.c index ca8670f78ac6..f349d16dd8f6 100644 --- a/net/dccp/ccids/ccid3.c +++ b/net/dccp/ccids/ccid3.c @@ -22,7 +22,7 @@ #include "../dccp.h" #include "ccid3.h" -#include <asm/unaligned.h> +#include <linux/unaligned.h> #ifdef CONFIG_IP_DCCP_CCID3_DEBUG static bool ccid3_debug; diff --git a/net/dccp/options.c b/net/dccp/options.c index d24cad05001e..db62d4767024 100644 --- a/net/dccp/options.c +++ b/net/dccp/options.c @@ -10,7 +10,7 @@ #include <linux/dccp.h> #include <linux/module.h> #include <linux/types.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/kernel.h> #include <linux/skbuff.h> diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index 668c729946ea..1664547deffd 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -1577,6 +1577,7 @@ EXPORT_SYMBOL_GPL(dsa_unregister_switch); void dsa_switch_shutdown(struct dsa_switch *ds) { struct net_device *conduit, *user_dev; + LIST_HEAD(close_list); struct dsa_port *dp; mutex_lock(&dsa2_mutex); @@ -1586,10 +1587,16 @@ void dsa_switch_shutdown(struct dsa_switch *ds) rtnl_lock(); + dsa_switch_for_each_cpu_port(dp, ds) + list_add(&dp->conduit->close_list, &close_list); + + dev_close_many(&close_list, true); + dsa_switch_for_each_user_port(dp, ds) { conduit = dsa_port_to_conduit(dp); user_dev = dp->user; + netif_device_detach(user_dev); netdev_upper_dev_unlink(conduit, user_dev); } diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index 8cc0e2f4159d..740af8541d2f 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -37,7 +37,7 @@ #include <net/cipso_ipv4.h> #include <linux/atomic.h> #include <linux/bug.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /* List of available DOI definitions */ /* XXX - This currently assumes a minimal number of different DOIs in use, diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 5f6fd382af38..f1f31ebfc793 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -662,11 +662,11 @@ static netdev_tx_t ipgre_xmit(struct sk_buff *skb, if (skb_cow_head(skb, 0)) goto free_skb; - tnl_params = (const struct iphdr *)skb->data; - - if (!pskb_network_may_pull(skb, pull_len)) + if (!pskb_may_pull(skb, pull_len)) goto free_skb; + tnl_params = (const struct iphdr *)skb->data; + /* ip_tunnel_xmit() needs skb->data pointing to gre header. */ skb_pull(skb, pull_len); skb_reset_mac_header(skb); diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c index a9e22a098872..68aedb8877b9 100644 --- a/net/ipv4/ip_options.c +++ b/net/ipv4/ip_options.c @@ -17,7 +17,7 @@ #include <linux/slab.h> #include <linux/types.h> #include <linux/uaccess.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/skbuff.h> #include <linux/ip.h> #include <linux/icmp.h> diff --git a/net/ipv4/netfilter/nf_dup_ipv4.c b/net/ipv4/netfilter/nf_dup_ipv4.c index f4aed0789d69..ec94ee1051c7 100644 --- a/net/ipv4/netfilter/nf_dup_ipv4.c +++ b/net/ipv4/netfilter/nf_dup_ipv4.c @@ -53,8 +53,9 @@ void nf_dup_ipv4(struct net *net, struct sk_buff *skb, unsigned int hooknum, { struct iphdr *iph; + local_bh_disable(); if (this_cpu_read(nf_skb_duplicated)) - return; + goto out; /* * Copy the skb, and route the copy. Will later return %XT_CONTINUE for * the original skb, which should continue on its way as if nothing has @@ -62,7 +63,7 @@ void nf_dup_ipv4(struct net *net, struct sk_buff *skb, unsigned int hooknum, */ skb = pskb_copy(skb, GFP_ATOMIC); if (skb == NULL) - return; + goto out; #if IS_ENABLED(CONFIG_NF_CONNTRACK) /* Avoid counting cloned packets towards the original connection. */ @@ -91,6 +92,8 @@ void nf_dup_ipv4(struct net *net, struct sk_buff *skb, unsigned int hooknum, } else { kfree_skb(skb); } +out: + local_bh_enable(); } EXPORT_SYMBOL_GPL(nf_dup_ipv4); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 9f314dfa1490..cc05ec1faac8 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -75,7 +75,7 @@ #include <net/proto_memory.h> #include <net/inet_common.h> #include <linux/ipsec.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/errqueue.h> #include <trace/events/tcp.h> #include <linux/jump_label_ratelimit.h> diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c index e4ad3311e148..2308665b51c5 100644 --- a/net/ipv4/tcp_offload.c +++ b/net/ipv4/tcp_offload.c @@ -101,8 +101,14 @@ static struct sk_buff *tcp4_gso_segment(struct sk_buff *skb, if (!pskb_may_pull(skb, sizeof(struct tcphdr))) return ERR_PTR(-EINVAL); - if (skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST) - return __tcp4_gso_segment_list(skb, features); + if (skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST) { + struct tcphdr *th = tcp_hdr(skb); + + if (skb_pagelen(skb) - th->doff * 4 == skb_shinfo(skb)->gso_size) + return __tcp4_gso_segment_list(skb, features); + + skb->ip_summed = CHECKSUM_NONE; + } if (unlikely(skb->ip_summed != CHECKSUM_PARTIAL)) { const struct iphdr *iph = ip_hdr(skb); diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index d842303587af..a5be6e4ed326 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -296,8 +296,26 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, return NULL; } - if (skb_shinfo(gso_skb)->gso_type & SKB_GSO_FRAGLIST) - return __udp_gso_segment_list(gso_skb, features, is_ipv6); + if (skb_shinfo(gso_skb)->gso_type & SKB_GSO_FRAGLIST) { + /* Detect modified geometry and pass those to skb_segment. */ + if (skb_pagelen(gso_skb) - sizeof(*uh) == skb_shinfo(gso_skb)->gso_size) + return __udp_gso_segment_list(gso_skb, features, is_ipv6); + + /* Setup csum, as fraglist skips this in udp4_gro_receive. */ + gso_skb->csum_start = skb_transport_header(gso_skb) - gso_skb->head; + gso_skb->csum_offset = offsetof(struct udphdr, check); + gso_skb->ip_summed = CHECKSUM_PARTIAL; + + uh = udp_hdr(gso_skb); + if (is_ipv6) + uh->check = ~udp_v6_check(gso_skb->len, + &ipv6_hdr(gso_skb)->saddr, + &ipv6_hdr(gso_skb)->daddr, 0); + else + uh->check = ~udp_v4_check(gso_skb->len, + ip_hdr(gso_skb)->saddr, + ip_hdr(gso_skb)->daddr, 0); + } skb_pull(gso_skb, sizeof(*uh)); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index d680beb91b0a..94dceac52884 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -85,7 +85,7 @@ #include <linux/netconf.h> #include <linux/random.h> #include <linux/uaccess.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> diff --git a/net/ipv6/calipso.c b/net/ipv6/calipso.c index eb8ee1e9373a..dbcea9fee626 100644 --- a/net/ipv6/calipso.c +++ b/net/ipv6/calipso.c @@ -29,7 +29,7 @@ #include <net/calipso.h> #include <linux/atomic.h> #include <linux/bug.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/crc-ccitt.h> /* Maximium size of the calipso option including diff --git a/net/ipv6/netfilter/nf_dup_ipv6.c b/net/ipv6/netfilter/nf_dup_ipv6.c index a0a2de30be3e..0c39c77fe8a8 100644 --- a/net/ipv6/netfilter/nf_dup_ipv6.c +++ b/net/ipv6/netfilter/nf_dup_ipv6.c @@ -47,11 +47,12 @@ static bool nf_dup_ipv6_route(struct net *net, struct sk_buff *skb, void nf_dup_ipv6(struct net *net, struct sk_buff *skb, unsigned int hooknum, const struct in6_addr *gw, int oif) { + local_bh_disable(); if (this_cpu_read(nf_skb_duplicated)) - return; + goto out; skb = pskb_copy(skb, GFP_ATOMIC); if (skb == NULL) - return; + goto out; #if IS_ENABLED(CONFIG_NF_CONNTRACK) nf_reset_ct(skb); @@ -69,6 +70,8 @@ void nf_dup_ipv6(struct net *net, struct sk_buff *skb, unsigned int hooknum, } else { kfree_skb(skb); } +out: + local_bh_enable(); } EXPORT_SYMBOL_GPL(nf_dup_ipv6); diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c index 23971903e66d..a45bf17cb2a1 100644 --- a/net/ipv6/tcpv6_offload.c +++ b/net/ipv6/tcpv6_offload.c @@ -159,8 +159,14 @@ static struct sk_buff *tcp6_gso_segment(struct sk_buff *skb, if (!pskb_may_pull(skb, sizeof(*th))) return ERR_PTR(-EINVAL); - if (skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST) - return __tcp6_gso_segment_list(skb, features); + if (skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST) { + struct tcphdr *th = tcp_hdr(skb); + + if (skb_pagelen(skb) - th->doff * 4 == skb_shinfo(skb)->gso_size) + return __tcp6_gso_segment_list(skb, features); + + skb->ip_summed = CHECKSUM_NONE; + } if (unlikely(skb->ip_summed != CHECKSUM_PARTIAL)) { const struct ipv6hdr *ipv6h = ipv6_hdr(skb); diff --git a/net/mac80211/key.c b/net/mac80211/key.c index eecdd2265eaa..6fac3ba00d88 100644 --- a/net/mac80211/key.c +++ b/net/mac80211/key.c @@ -18,7 +18,7 @@ #include <linux/slab.h> #include <linux/export.h> #include <net/mac80211.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "ieee80211_i.h" #include "driver-ops.h" #include "debugfs_key.h" diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index f94e4be0be12..640239f4425b 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -7,7 +7,7 @@ */ #include <linux/slab.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "ieee80211_i.h" #include "mesh.h" #include "wme.h" diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c index 024f48db6b05..579d0f24ac9d 100644 --- a/net/mac80211/mesh_hwmp.c +++ b/net/mac80211/mesh_hwmp.c @@ -7,7 +7,7 @@ #include <linux/slab.h> #include <linux/etherdevice.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "wme.h" #include "mesh.h" diff --git a/net/mac80211/michael.c b/net/mac80211/michael.c index a57502d9ffec..8a1afc93e749 100644 --- a/net/mac80211/michael.c +++ b/net/mac80211/michael.c @@ -6,7 +6,7 @@ #include <linux/types.h> #include <linux/bitops.h> #include <linux/ieee80211.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "michael.h" diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 735e78adb0db..0303972c23e4 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -23,7 +23,7 @@ #include <linux/slab.h> #include <linux/export.h> #include <net/mac80211.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "ieee80211_i.h" #include "driver-ops.h" diff --git a/net/mac80211/ocb.c b/net/mac80211/ocb.c index 9ef14e475c90..f4c51e4a1e29 100644 --- a/net/mac80211/ocb.c +++ b/net/mac80211/ocb.c @@ -16,7 +16,7 @@ #include <linux/etherdevice.h> #include <linux/rtnetlink.h> #include <net/mac80211.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "ieee80211_i.h" #include "driver-ops.h" diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 59ad24a71141..694b43091fec 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -22,7 +22,7 @@ #include <kunit/visibility.h> #include <net/mac80211.h> #include <net/ieee80211_radiotap.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "ieee80211_i.h" #include "driver-ops.h" diff --git a/net/mac80211/status.c b/net/mac80211/status.c index d1cf987de13b..b41b867f43b2 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -11,7 +11,7 @@ #include <linux/export.h> #include <linux/etherdevice.h> #include <net/mac80211.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "ieee80211_i.h" #include "rate.h" #include "mesh.h" diff --git a/net/mac80211/tkip.c b/net/mac80211/tkip.c index e7f57bb18f6e..880a1fa8705a 100644 --- a/net/mac80211/tkip.c +++ b/net/mac80211/tkip.c @@ -9,7 +9,7 @@ #include <linux/types.h> #include <linux/netdevice.h> #include <linux/export.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <net/mac80211.h> #include "driver-ops.h" diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index a9ee86982259..0ff8b56f5807 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -24,7 +24,7 @@ #include <net/mac80211.h> #include <net/codel.h> #include <net/codel_impl.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <net/fq_impl.h> #include <net/gso.h> diff --git a/net/mac80211/wep.c b/net/mac80211/wep.c index 5c01e121481a..93b8668079a7 100644 --- a/net/mac80211/wep.c +++ b/net/mac80211/wep.c @@ -16,7 +16,7 @@ #include <linux/mm.h> #include <linux/scatterlist.h> #include <linux/slab.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <net/mac80211.h> #include "ieee80211_i.h" diff --git a/net/mac80211/wpa.c b/net/mac80211/wpa.c index 047a33797020..293afa3f57c5 100644 --- a/net/mac80211/wpa.c +++ b/net/mac80211/wpa.c @@ -12,7 +12,7 @@ #include <linux/compiler.h> #include <linux/ieee80211.h> #include <linux/gfp.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <net/mac80211.h> #include <crypto/aes.h> #include <crypto/utils.h> diff --git a/net/mac802154/rx.c b/net/mac802154/rx.c index e40a988d6c80..aac359b5c71d 100644 --- a/net/mac802154/rx.c +++ b/net/mac802154/rx.c @@ -13,7 +13,7 @@ #include <linux/module.h> #include <linux/netdevice.h> #include <linux/crc-ccitt.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <net/mac802154.h> #include <net/ieee802154_netdev.h> diff --git a/net/mac802154/scan.c b/net/mac802154/scan.c index 1c0eeaa76560..a6dab3cc3ad8 100644 --- a/net/mac802154/scan.c +++ b/net/mac802154/scan.c @@ -176,6 +176,7 @@ void mac802154_scan_worker(struct work_struct *work) struct ieee802154_local *local = container_of(work, struct ieee802154_local, scan_work.work); struct cfg802154_scan_request *scan_req; + enum nl802154_scan_types scan_req_type; struct ieee802154_sub_if_data *sdata; unsigned int scan_duration = 0; struct wpan_phy *wpan_phy; @@ -209,6 +210,7 @@ void mac802154_scan_worker(struct work_struct *work) } wpan_phy = scan_req->wpan_phy; + scan_req_type = scan_req->type; scan_req_duration = scan_req->duration; /* Look for the next valid chan */ @@ -246,7 +248,7 @@ void mac802154_scan_worker(struct work_struct *work) goto end_scan; } - if (scan_req->type == NL802154_SCAN_ACTIVE) { + if (scan_req_type == NL802154_SCAN_ACTIVE) { ret = mac802154_transmit_beacon_req(local, sdata); if (ret) dev_err(&sdata->dev->dev, diff --git a/net/mac802154/tx.c b/net/mac802154/tx.c index 6fbed5bb5c3e..337d6faf0d2a 100644 --- a/net/mac802154/tx.c +++ b/net/mac802154/tx.c @@ -12,7 +12,7 @@ #include <linux/netdevice.h> #include <linux/if_arp.h> #include <linux/crc-ccitt.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <net/rtnetlink.h> #include <net/ieee802154_netdev.h> diff --git a/net/mptcp/crypto.c b/net/mptcp/crypto.c index a8931349933c..b08ba959ac4f 100644 --- a/net/mptcp/crypto.c +++ b/net/mptcp/crypto.c @@ -22,7 +22,7 @@ #include <linux/kernel.h> #include <crypto/sha2.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "protocol.h" diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c index 5ecf611c8820..5cf55bde366d 100644 --- a/net/ncsi/ncsi-manage.c +++ b/net/ncsi/ncsi-manage.c @@ -1954,6 +1954,8 @@ void ncsi_unregister_dev(struct ncsi_dev *nd) list_del_rcu(&ndp->node); spin_unlock_irqrestore(&ncsi_dev_lock, flags); + disable_work_sync(&ndp->work); + kfree(ndp); } EXPORT_SYMBOL_GPL(ncsi_unregister_dev); diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c index f53899d12416..d8a284999544 100644 --- a/net/netfilter/ipvs/ip_vs_ftp.c +++ b/net/netfilter/ipvs/ip_vs_ftp.c @@ -35,7 +35,7 @@ #include <linux/gfp.h> #include <net/protocol.h> #include <net/tcp.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <net/ip_vs.h> diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index be74c0906dda..3402675bf521 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -51,7 +51,7 @@ #include <linux/kernel.h> #include <linux/sched/signal.h> -#include <asm/unaligned.h> /* Used for ntoh_seq and hton_seq */ +#include <linux/unaligned.h> /* Used for ntoh_seq and hton_seq */ #include <net/ip.h> #include <net/sock.h> diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index ae493599a3ef..0c1d086e96cb 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -14,7 +14,7 @@ #include <linux/skbuff.h> #include <linux/ipv6.h> #include <net/ip6_checksum.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <net/tcp.h> diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c index 5b140c12b7df..3fa3f5dfb264 100644 --- a/net/netfilter/nf_synproxy_core.c +++ b/net/netfilter/nf_synproxy_core.c @@ -5,7 +5,7 @@ #include <linux/module.h> #include <linux/skbuff.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <net/tcp.h> #include <net/netns/generic.h> #include <linux/proc_fs.h> diff --git a/net/netfilter/nft_byteorder.c b/net/netfilter/nft_byteorder.c index 2f82a444d21b..af9206a3afd1 100644 --- a/net/netfilter/nft_byteorder.c +++ b/net/netfilter/nft_byteorder.c @@ -5,7 +5,7 @@ * Development of this code funded by Astaro AG (http://www.astaro.com/) */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/kernel.h> #include <linux/init.h> #include <linux/module.h> diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c index 6bfd33516241..b8d03364566c 100644 --- a/net/netfilter/nft_exthdr.c +++ b/net/netfilter/nft_exthdr.c @@ -5,7 +5,7 @@ * Development of this code funded by Astaro AG (http://www.astaro.com/) */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/kernel.h> #include <linux/netlink.h> #include <linux/netfilter.h> diff --git a/net/phonet/af_phonet.c b/net/phonet/af_phonet.c index 2b582da1e88c..a27efa4faa4e 100644 --- a/net/phonet/af_phonet.c +++ b/net/phonet/af_phonet.c @@ -13,7 +13,7 @@ #include <linux/kernel.h> #include <linux/module.h> #include <linux/slab.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <net/sock.h> #include <linux/if_phonet.h> diff --git a/net/sched/em_cmp.c b/net/sched/em_cmp.c index c90ad7ea26b4..64b637f18bc7 100644 --- a/net/sched/em_cmp.c +++ b/net/sched/em_cmp.c @@ -10,7 +10,7 @@ #include <linux/kernel.h> #include <linux/skbuff.h> #include <linux/tc_ematch/tc_em_cmp.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <net/pkt_cls.h> static inline int cmp_needs_transformation(struct tcf_em_cmp *cmp) diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 32f76f1298da..078bcb3858c7 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -8557,8 +8557,10 @@ static int sctp_listen_start(struct sock *sk, int backlog) */ inet_sk_set_state(sk, SCTP_SS_LISTENING); if (!ep->base.bind_addr.port) { - if (sctp_autobind(sk)) + if (sctp_autobind(sk)) { + inet_sk_set_state(sk, SCTP_SS_CLOSED); return -EAGAIN; + } } else { if (sctp_get_port(sk, inet_sk(sk)->inet_num)) { inet_sk_set_state(sk, SCTP_SS_CLOSED); diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c index d72953f29258..ae3fb9bc8a21 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c +++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c @@ -94,7 +94,7 @@ #include <linux/slab.h> #include <linux/spinlock.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <rdma/ib_verbs.h> #include <rdma/rdma_cm.h> diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c index bb5436b719e0..96154a2367a1 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c +++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c @@ -100,7 +100,7 @@ */ #include <linux/spinlock.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <rdma/ib_verbs.h> #include <rdma/rdma_cm.h> diff --git a/net/tls/trace.h b/net/tls/trace.h index 9ba5f600ea43..2d8ce4ff3265 100644 --- a/net/tls/trace.h +++ b/net/tls/trace.h @@ -7,7 +7,7 @@ #if !defined(_TLS_TRACE_H_) || defined(TRACE_HEADER_MULTI_READ) #define _TLS_TRACE_H_ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/tracepoint.h> struct sock; diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index 85e423921734..b58c3818f284 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -96,7 +96,7 @@ out_rcu: /* Caller need to hold vsock->tx_lock on vq */ static int virtio_transport_send_skb(struct sk_buff *skb, struct virtqueue *vq, - struct virtio_vsock *vsock) + struct virtio_vsock *vsock, gfp_t gfp) { int ret, in_sg = 0, out_sg = 0; struct scatterlist **sgs; @@ -140,7 +140,7 @@ static int virtio_transport_send_skb(struct sk_buff *skb, struct virtqueue *vq, } } - ret = virtqueue_add_sgs(vq, sgs, out_sg, in_sg, skb, GFP_KERNEL); + ret = virtqueue_add_sgs(vq, sgs, out_sg, in_sg, skb, gfp); /* Usually this means that there is no more space available in * the vq */ @@ -178,7 +178,7 @@ virtio_transport_send_pkt_work(struct work_struct *work) reply = virtio_vsock_skb_reply(skb); - ret = virtio_transport_send_skb(skb, vq, vsock); + ret = virtio_transport_send_skb(skb, vq, vsock, GFP_KERNEL); if (ret < 0) { virtio_vsock_skb_queue_head(&vsock->send_pkt_queue, skb); break; @@ -221,7 +221,7 @@ static int virtio_transport_send_skb_fast_path(struct virtio_vsock *vsock, struc if (unlikely(ret == 0)) return -EBUSY; - ret = virtio_transport_send_skb(skb, vq, vsock); + ret = virtio_transport_send_skb(skb, vq, vsock, GFP_ATOMIC); if (ret == 0) virtqueue_kick(vq); diff --git a/net/wireless/radiotap.c b/net/wireless/radiotap.c index ae2e1a896461..b7e3e46ec16d 100644 --- a/net/wireless/radiotap.c +++ b/net/wireless/radiotap.c @@ -18,7 +18,7 @@ #include <linux/export.h> #include <net/cfg80211.h> #include <net/ieee80211_radiotap.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /* function prototypes and related defs are in include/net/cfg80211.h */ diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 55f039ec3d59..2b10a45ff124 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -33,7 +33,7 @@ #if IS_ENABLED(CONFIG_IPV6) #include <linux/in6.h> #endif -#include <asm/unaligned.h> +#include <linux/unaligned.h> static int verify_one_alg(struct nlattr **attrs, enum xfrm_attr_type_t type, struct netlink_ext_ack *extack) diff --git a/rust/bindgen_parameters b/rust/bindgen_parameters index a721d466bee4..b7c7483123b7 100644 --- a/rust/bindgen_parameters +++ b/rust/bindgen_parameters @@ -24,3 +24,8 @@ # These functions use the `__preserve_most` calling convention, which neither bindgen # nor Rust currently understand, and which Clang currently declares to be unstable. --blocklist-function __list_.*_report + +# These constants are sometimes not recognized by bindgen depending on config. +# We use const helpers to aid bindgen, to avoid conflicts when constants are +# recognized, block generation of the non-helper constants. +--blocklist-item ARCH_SLAB_MINALIGN diff --git a/rust/helpers/mutex.c b/rust/helpers/mutex.c index 200db7e6279f..a17ca8cdb50c 100644 --- a/rust/helpers/mutex.c +++ b/rust/helpers/mutex.c @@ -7,3 +7,9 @@ void rust_helper_mutex_lock(struct mutex *lock) { mutex_lock(lock); } + +void rust_helper___mutex_init(struct mutex *mutex, const char *name, + struct lock_class_key *key) +{ + __mutex_init(mutex, name, key); +} diff --git a/rust/kernel/kunit.rs b/rust/kernel/kunit.rs index 0ba77276ae7e..824da0e9738a 100644 --- a/rust/kernel/kunit.rs +++ b/rust/kernel/kunit.rs @@ -18,7 +18,7 @@ pub fn err(args: fmt::Arguments<'_>) { #[cfg(CONFIG_PRINTK)] unsafe { bindings::_printk( - b"\x013%pA\0".as_ptr() as _, + c"\x013%pA".as_ptr() as _, &args as *const _ as *const c_void, ); } @@ -34,7 +34,7 @@ pub fn info(args: fmt::Arguments<'_>) { #[cfg(CONFIG_PRINTK)] unsafe { bindings::_printk( - b"\x016%pA\0".as_ptr() as _, + c"\x016%pA".as_ptr() as _, &args as *const _ as *const c_void, ); } diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs index 22a3bfa5a9e9..b5f4b3ce6b48 100644 --- a/rust/kernel/lib.rs +++ b/rust/kernel/lib.rs @@ -44,8 +44,8 @@ pub mod net; pub mod page; pub mod prelude; pub mod print; -pub mod sizes; pub mod rbtree; +pub mod sizes; mod static_assert; #[doc(hidden)] pub mod std_vendor; diff --git a/rust/kernel/sync/locked_by.rs b/rust/kernel/sync/locked_by.rs index babc731bd5f6..ce2ee8d87865 100644 --- a/rust/kernel/sync/locked_by.rs +++ b/rust/kernel/sync/locked_by.rs @@ -83,8 +83,12 @@ pub struct LockedBy<T: ?Sized, U: ?Sized> { // SAFETY: `LockedBy` can be transferred across thread boundaries iff the data it protects can. unsafe impl<T: ?Sized + Send, U: ?Sized> Send for LockedBy<T, U> {} -// SAFETY: `LockedBy` serialises the interior mutability it provides, so it is `Sync` as long as the -// data it protects is `Send`. +// SAFETY: If `T` is not `Sync`, then parallel shared access to this `LockedBy` allows you to use +// `access_mut` to hand out `&mut T` on one thread at the time. The requirement that `T: Send` is +// sufficient to allow that. +// +// If `T` is `Sync`, then the `access` method also becomes available, which allows you to obtain +// several `&T` from several threads at once. However, this is okay as `T` is `Sync`. unsafe impl<T: ?Sized + Send, U: ?Sized> Sync for LockedBy<T, U> {} impl<T, U> LockedBy<T, U> { @@ -118,7 +122,10 @@ impl<T: ?Sized, U> LockedBy<T, U> { /// /// Panics if `owner` is different from the data protected by the lock used in /// [`new`](LockedBy::new). - pub fn access<'a>(&'a self, owner: &'a U) -> &'a T { + pub fn access<'a>(&'a self, owner: &'a U) -> &'a T + where + T: Sync, + { build_assert!( size_of::<U>() > 0, "`U` cannot be a ZST because `owner` wouldn't be unique" @@ -127,7 +134,10 @@ impl<T: ?Sized, U> LockedBy<T, U> { panic!("mismatched owners"); } - // SAFETY: `owner` is evidence that the owner is locked. + // SAFETY: `owner` is evidence that there are only shared references to the owner for the + // duration of 'a, so it's not possible to use `Self::access_mut` to obtain a mutable + // reference to the inner value that aliases with this shared reference. The type is `Sync` + // so there are no other requirements. unsafe { &*self.data.get() } } diff --git a/scripts/Makefile.dtbs b/scripts/Makefile.dtbs index 46009d5f1486..8d56c0815f33 100644 --- a/scripts/Makefile.dtbs +++ b/scripts/Makefile.dtbs @@ -34,12 +34,14 @@ $(obj)/dtbs-list: $(dtb-y) FORCE # Assembly file to wrap dtb(o) # --------------------------------------------------------------------------- +builtin-dtb-section = $(if $(filter arch/$(SRCARCH)/boot/dts%, $(obj)),.dtb.init.rodata,.rodata) + # Generate an assembly file to wrap the output of the device tree compiler quiet_cmd_wrap_S_dtb = WRAP $@ cmd_wrap_S_dtb = { \ symbase=__$(patsubst .%,%,$(suffix $<))_$(subst -,_,$(notdir $*)); \ echo '\#include <asm-generic/vmlinux.lds.h>'; \ - echo '.section .dtb.init.rodata,"a"'; \ + echo '.section $(builtin-dtb-section),"a"'; \ echo '.balign STRUCT_ALIGNMENT'; \ echo ".global $${symbase}_begin"; \ echo "$${symbase}_begin:"; \ diff --git a/scripts/Makefile.modinst b/scripts/Makefile.modinst index 4d81ed9af294..d97720943189 100644 --- a/scripts/Makefile.modinst +++ b/scripts/Makefile.modinst @@ -53,9 +53,11 @@ $(foreach x, % :, $(if $(findstring $x, $(dst)), \ $(error module installation path cannot contain '$x'))) suffix-y := +ifdef CONFIG_MODULE_COMPRESS_ALL suffix-$(CONFIG_MODULE_COMPRESS_GZIP) := .gz suffix-$(CONFIG_MODULE_COMPRESS_XZ) := .xz suffix-$(CONFIG_MODULE_COMPRESS_ZSTD) := .zst +endif modules := $(patsubst $(extmod_prefix)%.o, $(dst)/%.ko$(suffix-y), $(modules)) install-$(CONFIG_MODULES) += $(modules) diff --git a/scripts/coccinelle/api/string_choices.cocci b/scripts/coccinelle/api/string_choices.cocci index 5e729f187f22..375045086912 100644 --- a/scripts/coccinelle/api/string_choices.cocci +++ b/scripts/coccinelle/api/string_choices.cocci @@ -14,23 +14,18 @@ expression E; - ((E == 1) ? "" : "s") + str_plural(E) | -- ((E != 1) ? "s" : "") -+ str_plural(E) -| - ((E > 1) ? "s" : "") + str_plural(E) ) -@str_plural_r depends on !patch exists@ +@str_plural_r depends on !patch@ expression E; position P; @@ ( -* ((E@P == 1) ? "" : "s") -| -* ((E@P != 1) ? "s" : "") +* (E@P == 1) ? "" : "s" | -* ((E@P > 1) ? "s" : "") +* (E@P > 1) ? "s" : "" ) @script:python depends on report@ @@ -40,21 +35,17 @@ e << str_plural_r.E; coccilib.report.print_report(p[0], "opportunity for str_plural(%s)" % e) -@str_up_down depends on patch@ +@str_up_down depends on patch disable neg_if_exp@ expression E; @@ -( - ((E) ? "up" : "down") + str_up_down(E) -) -@str_up_down_r depends on !patch exists@ +@str_up_down_r depends on !patch disable neg_if_exp@ expression E; position P; @@ -( -* ((E@P) ? "up" : "down") -) +* E@P ? "up" : "down" @script:python depends on report@ p << str_up_down_r.P; @@ -63,21 +54,17 @@ e << str_up_down_r.E; coccilib.report.print_report(p[0], "opportunity for str_up_down(%s)" % e) -@str_down_up depends on patch@ +@str_down_up depends on patch disable neg_if_exp@ expression E; @@ -( - ((E) ? "down" : "up") + str_down_up(E) -) -@str_down_up_r depends on !patch exists@ +@str_down_up_r depends on !patch disable neg_if_exp@ expression E; position P; @@ -( -* ((E@P) ? "down" : "up") -) +* E@P ? "down" : "up" @script:python depends on report@ p << str_down_up_r.P; @@ -85,3 +72,231 @@ e << str_down_up_r.E; @@ coccilib.report.print_report(p[0], "opportunity for str_down_up(%s)" % e) + +@str_true_false depends on patch disable neg_if_exp@ +expression E; +@@ +- ((E) ? "true" : "false") ++ str_true_false(E) + +@str_true_false_r depends on !patch disable neg_if_exp@ +expression E; +position P; +@@ +* E@P ? "true" : "false" + +@script:python depends on report@ +p << str_true_false_r.P; +e << str_true_false_r.E; +@@ + +coccilib.report.print_report(p[0], "opportunity for str_true_false(%s)" % e) + +@str_false_true depends on patch disable neg_if_exp@ +expression E; +@@ +- ((E) ? "false" : "true") ++ str_false_true(E) + +@str_false_true_r depends on !patch disable neg_if_exp@ +expression E; +position P; +@@ +* E@P ? "false" : "true" + +@script:python depends on report@ +p << str_false_true_r.P; +e << str_false_true_r.E; +@@ + +coccilib.report.print_report(p[0], "opportunity for str_false_true(%s)" % e) + +@str_hi_lo depends on patch disable neg_if_exp@ +expression E; +@@ +- ((E) ? "hi" : "lo") ++ str_hi_lo(E) + +@str_hi_lo_r depends on !patch disable neg_if_exp@ +expression E; +position P; +@@ +* E@P ? "hi" : "lo" + +@script:python depends on report@ +p << str_hi_lo_r.P; +e << str_hi_lo_r.E; +@@ + +coccilib.report.print_report(p[0], "opportunity for str_hi_lo(%s)" % e) + +@str_high_low depends on patch disable neg_if_exp@ +expression E; +@@ +- ((E) ? "high" : "low") ++ str_high_low(E) + +@str_high_low_r depends on !patch disable neg_if_exp@ +expression E; +position P; +@@ +* E@P ? "high" : "low" + +@script:python depends on report@ +p << str_high_low_r.P; +e << str_high_low_r.E; +@@ + +coccilib.report.print_report(p[0], "opportunity for str_high_low(%s)" % e) + +@str_lo_hi depends on patch disable neg_if_exp@ +expression E; +@@ +- ((E) ? "lo" : "hi") ++ str_lo_hi(E) + +@str_lo_hi_r depends on !patch disable neg_if_exp@ +expression E; +position P; +@@ +* E@P ? "lo" : "hi" + +@script:python depends on report@ +p << str_lo_hi_r.P; +e << str_lo_hi_r.E; +@@ + +coccilib.report.print_report(p[0], "opportunity for str_lo_hi(%s)" % e) + +@str_low_high depends on patch disable neg_if_exp@ +expression E; +@@ +- ((E) ? "low" : "high") ++ str_low_high(E) + +@str_low_high_r depends on !patch disable neg_if_exp@ +expression E; +position P; +@@ +* E@P ? "low" : "high" + +@script:python depends on report@ +p << str_low_high_r.P; +e << str_low_high_r.E; +@@ + +coccilib.report.print_report(p[0], "opportunity for str_low_high(%s)" % e) + +@str_enable_disable depends on patch@ +expression E; +@@ +- ((E) ? "enable" : "disable") ++ str_enable_disable(E) + +@str_enable_disable_r depends on !patch@ +expression E; +position P; +@@ +* E@P ? "enable" : "disable" + +@script:python depends on report@ +p << str_enable_disable_r.P; +e << str_enable_disable_r.E; +@@ + +coccilib.report.print_report(p[0], "opportunity for str_enable_disable(%s)" % e) + +@str_enabled_disabled depends on patch@ +expression E; +@@ +- ((E) ? "enabled" : "disabled") ++ str_enabled_disabled(E) + +@str_enabled_disabled_r depends on !patch@ +expression E; +position P; +@@ +* E@P ? "enabled" : "disabled" + +@script:python depends on report@ +p << str_enabled_disabled_r.P; +e << str_enabled_disabled_r.E; +@@ + +coccilib.report.print_report(p[0], "opportunity for str_enabled_disabled(%s)" % e) + +@str_read_write depends on patch disable neg_if_exp@ +expression E; +@@ +- ((E) ? "read" : "write") ++ str_read_write(E) + +@str_read_write_r depends on !patch disable neg_if_exp@ +expression E; +position P; +@@ +* E@P ? "read" : "write" + +@script:python depends on report@ +p << str_read_write_r.P; +e << str_read_write_r.E; +@@ + +coccilib.report.print_report(p[0], "opportunity for str_read_write(%s)" % e) + +@str_write_read depends on patch disable neg_if_exp@ +expression E; +@@ +- ((E) ? "write" : "read") ++ str_write_read(E) + +@str_write_read_r depends on !patch disable neg_if_exp@ +expression E; +position P; +@@ +* E@P ? "write" : "read" + +@script:python depends on report@ +p << str_write_read_r.P; +e << str_write_read_r.E; +@@ + +coccilib.report.print_report(p[0], "opportunity for str_write_read(%s)" % e) + +@str_on_off depends on patch@ +expression E; +@@ +- ((E) ? "on" : "off") ++ str_on_off(E) + +@str_on_off_r depends on !patch@ +expression E; +position P; +@@ +* E@P ? "on" : "off" + +@script:python depends on report@ +p << str_on_off_r.P; +e << str_on_off_r.E; +@@ + +coccilib.report.print_report(p[0], "opportunity for str_on_off(%s)" % e) + +@str_yes_no depends on patch@ +expression E; +@@ +- ((E) ? "yes" : "no") ++ str_yes_no(E) + +@str_yes_no_r depends on !patch@ +expression E; +position P; +@@ +* E@P ? "yes" : "no" + +@script:python depends on report@ +p << str_yes_no_r.P; +e << str_yes_no_r.E; +@@ + +coccilib.report.print_report(p[0], "opportunity for str_yes_no(%s)" % e) diff --git a/scripts/include/list.h b/scripts/include/list.h index fea1e2b79063..8bdcaadca709 100644 --- a/scripts/include/list.h +++ b/scripts/include/list.h @@ -128,6 +128,36 @@ static inline void list_del(struct list_head *entry) } /** + * list_replace - replace old entry by new one + * @old : the element to be replaced + * @new : the new element to insert + * + * If @old was empty, it will be overwritten. + */ +static inline void list_replace(struct list_head *old, + struct list_head *new) +{ + new->next = old->next; + new->next->prev = new; + new->prev = old->prev; + new->prev->next = new; +} + +/** + * list_replace_init - replace old entry by new one and initialize the old one + * @old : the element to be replaced + * @new : the new element to insert + * + * If @old was empty, it will be overwritten. + */ +static inline void list_replace_init(struct list_head *old, + struct list_head *new) +{ + list_replace(old, new); + INIT_LIST_HEAD(old); +} + +/** * list_move - delete from one list and add as another's head * @list: the entry to move * @head: the head that will precede our entry @@ -151,6 +181,26 @@ static inline void list_move_tail(struct list_head *list, } /** + * list_is_first -- tests whether @list is the first entry in list @head + * @list: the entry to test + * @head: the head of the list + */ +static inline int list_is_first(const struct list_head *list, const struct list_head *head) +{ + return list->prev == head; +} + +/** + * list_is_last - tests whether @list is the last entry in list @head + * @list: the entry to test + * @head: the head of the list + */ +static inline int list_is_last(const struct list_head *list, const struct list_head *head) +{ + return list->next == head; +} + +/** * list_is_head - tests whether @list is the list @head * @list: the entry to test * @head: the head of the list diff --git a/scripts/kconfig/expr.c b/scripts/kconfig/expr.c index 78738ef412de..16f92c4a775a 100644 --- a/scripts/kconfig/expr.c +++ b/scripts/kconfig/expr.c @@ -47,6 +47,7 @@ static struct expr *expr_lookup(enum expr_type type, void *l, void *r) e->type = type; e->left._initdata = l; e->right._initdata = r; + e->val_is_valid = false; hash_add(expr_hashtable, &e->node, hash); diff --git a/scripts/kconfig/parser.y b/scripts/kconfig/parser.y index 1ad60f9e164e..bc43fb67c7c4 100644 --- a/scripts/kconfig/parser.y +++ b/scripts/kconfig/parser.y @@ -159,8 +159,14 @@ config_stmt: config_entry_start config_option_list yynerrs++; } - list_add_tail(¤t_entry->sym->choice_link, - ¤t_choice->choice_members); + /* + * If the same symbol appears twice in a choice block, the list + * node would be added twice, leading to a broken linked list. + * list_empty() ensures that this symbol has not yet added. + */ + if (list_empty(¤t_entry->sym->choice_link)) + list_add_tail(¤t_entry->sym->choice_link, + ¤t_choice->choice_members); } printd(DEBUG_PARSE, "%s:%d:endconfig\n", cur_filename, cur_lineno); diff --git a/scripts/kconfig/qconf.cc b/scripts/kconfig/qconf.cc index 97fce13e551e..e260cab1c2af 100644 --- a/scripts/kconfig/qconf.cc +++ b/scripts/kconfig/qconf.cc @@ -1166,7 +1166,7 @@ void ConfigInfoView::clicked(const QUrl &url) { QByteArray str = url.toEncoded(); const std::size_t count = str.size(); - char *data = new char[count + 1]; + char *data = new char[count + 2]; // '$' + '\0' struct symbol **result; struct menu *m = NULL; @@ -1505,6 +1505,8 @@ ConfigMainWindow::ConfigMainWindow(void) connect(helpText, &ConfigInfoView::menuSelected, this, &ConfigMainWindow::setMenuLink); + conf_read(NULL); + QString listMode = configSettings->value("/listMode", "symbol").toString(); if (listMode == "single") showSingleView(); @@ -1906,8 +1908,6 @@ int main(int ac, char** av) configApp->connect(configApp, SIGNAL(lastWindowClosed()), SLOT(quit())); configApp->connect(configApp, SIGNAL(aboutToQuit()), v, SLOT(saveSettings())); - conf_read(NULL); - v->show(); configApp->exec(); diff --git a/scripts/package/builddeb b/scripts/package/builddeb index c1757db6aa8a..404587fc71fe 100755 --- a/scripts/package/builddeb +++ b/scripts/package/builddeb @@ -74,7 +74,6 @@ install_linux_image () { mkdir -p "${pdir}/DEBIAN" cat <<-EOF > "${pdir}/DEBIAN/${script}" - #!/bin/sh set -e diff --git a/security/Kconfig.hardening b/security/Kconfig.hardening index 2cff851ebfd7..c9d5ca3d8d08 100644 --- a/security/Kconfig.hardening +++ b/security/Kconfig.hardening @@ -340,7 +340,7 @@ choice config RANDSTRUCT_FULL bool "Fully randomize structure layout" depends on CC_HAS_RANDSTRUCT || GCC_PLUGINS - select MODVERSIONS if MODULES + select MODVERSIONS if MODULES && !COMPILE_TEST help Fully randomize the member layout of sensitive structures as much as possible, which may have both a @@ -356,7 +356,7 @@ choice config RANDSTRUCT_PERFORMANCE bool "Limit randomization of structure layout to cache-lines" depends on GCC_PLUGINS - select MODVERSIONS if MODULES + select MODVERSIONS if MODULES && !COMPILE_TEST help Randomization of sensitive kernel structures will make a best effort at restricting randomization to cacheline-sized diff --git a/security/apparmor/policy_unpack.c b/security/apparmor/policy_unpack.c index 5a570235427d..3483c595f999 100644 --- a/security/apparmor/policy_unpack.c +++ b/security/apparmor/policy_unpack.c @@ -13,7 +13,7 @@ * All policy is validated before it is used. */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <kunit/visibility.h> #include <linux/ctype.h> #include <linux/errno.h> diff --git a/security/keys/trusted-keys/trusted_tpm2.c b/security/keys/trusted-keys/trusted_tpm2.c index 8b7dd73d94c1..024be262702f 100644 --- a/security/keys/trusted-keys/trusted_tpm2.c +++ b/security/keys/trusted-keys/trusted_tpm2.c @@ -14,7 +14,7 @@ #include <keys/trusted-type.h> #include <keys/trusted_tpm.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "tpm2key.asn1.h" diff --git a/security/tomoyo/domain.c b/security/tomoyo/domain.c index 90b53500a236..aed9e3ef2c9e 100644 --- a/security/tomoyo/domain.c +++ b/security/tomoyo/domain.c @@ -723,10 +723,13 @@ int tomoyo_find_next_domain(struct linux_binprm *bprm) ee->r.obj = &ee->obj; ee->obj.path1 = bprm->file->f_path; /* Get symlink's pathname of program. */ - retval = -ENOENT; exename.name = tomoyo_realpath_nofollow(original_name); - if (!exename.name) - goto out; + if (!exename.name) { + /* Fallback to realpath if symlink's pathname does not exist. */ + exename.name = tomoyo_realpath_from_path(&bprm->file->f_path); + if (!exename.name) + goto out; + } tomoyo_fill_path_info(&exename); retry: /* Check 'aggregator' directive. */ diff --git a/sound/aoa/codecs/onyx.c b/sound/aoa/codecs/onyx.c index e90e03bb0dc0..ac347a14f282 100644 --- a/sound/aoa/codecs/onyx.c +++ b/sound/aoa/codecs/onyx.c @@ -1040,7 +1040,7 @@ static void onyx_i2c_remove(struct i2c_client *client) } static const struct i2c_device_id onyx_i2c_id[] = { - { "MAC,pcm3052", 0 }, + { "MAC,pcm3052" }, { } }; MODULE_DEVICE_TABLE(i2c,onyx_i2c_id); diff --git a/sound/aoa/codecs/tas.c b/sound/aoa/codecs/tas.c index be9822ebf9f8..804b2ebbe28f 100644 --- a/sound/aoa/codecs/tas.c +++ b/sound/aoa/codecs/tas.c @@ -927,7 +927,7 @@ static void tas_i2c_remove(struct i2c_client *client) } static const struct i2c_device_id tas_i2c_id[] = { - { "MAC,tas3004", 0 }, + { "MAC,tas3004" }, { } }; MODULE_DEVICE_TABLE(i2c,tas_i2c_id); diff --git a/sound/core/compress_offload.c b/sound/core/compress_offload.c index b8c0d6edbdd1..bdf1d78de833 100644 --- a/sound/core/compress_offload.c +++ b/sound/core/compress_offload.c @@ -288,7 +288,7 @@ static ssize_t snd_compr_write(struct file *f, const char __user *buf, stream = &data->stream; guard(mutex)(&stream->device->lock); - /* write is allowed when stream is running or has been steup */ + /* write is allowed when stream is running or has been setup */ switch (stream->runtime->state) { case SNDRV_PCM_STATE_SETUP: case SNDRV_PCM_STATE_PREPARED: diff --git a/sound/core/control.c b/sound/core/control.c index 2f790a7b1e90..0ddade871b52 100644 --- a/sound/core/control.c +++ b/sound/core/control.c @@ -1641,6 +1641,8 @@ static int snd_ctl_elem_add(struct snd_ctl_file *file, count = info->owner; if (count == 0) count = 1; + if (count > MAX_CONTROL_COUNT) + return -EINVAL; /* Arrange access permissions if needed. */ access = info->access; diff --git a/sound/core/init.c b/sound/core/init.c index b92aa7103589..114fb87de990 100644 --- a/sound/core/init.c +++ b/sound/core/init.c @@ -654,13 +654,19 @@ void snd_card_free(struct snd_card *card) } EXPORT_SYMBOL(snd_card_free); +/* check, if the character is in the valid ASCII range */ +static inline bool safe_ascii_char(char c) +{ + return isascii(c) && isalnum(c); +} + /* retrieve the last word of shortname or longname */ static const char *retrieve_id_from_card_name(const char *name) { const char *spos = name; while (*name) { - if (isspace(*name) && isalnum(name[1])) + if (isspace(*name) && safe_ascii_char(name[1])) spos = name + 1; name++; } @@ -687,12 +693,12 @@ static void copy_valid_id_string(struct snd_card *card, const char *src, { char *id = card->id; - while (*nid && !isalnum(*nid)) + while (*nid && !safe_ascii_char(*nid)) nid++; if (isdigit(*nid)) *id++ = isalpha(*src) ? *src : 'D'; while (*nid && (size_t)(id - card->id) < sizeof(card->id) - 1) { - if (isalnum(*nid)) + if (safe_ascii_char(*nid)) *id++ = *nid; nid++; } @@ -787,7 +793,7 @@ static ssize_t id_store(struct device *dev, struct device_attribute *attr, for (idx = 0; idx < copy; idx++) { c = buf[idx]; - if (!isalnum(c) && c != '_' && c != '-') + if (!safe_ascii_char(c) && c != '_' && c != '-') return -EINVAL; } memcpy(buf1, buf, copy); diff --git a/sound/core/oss/mixer_oss.c b/sound/core/oss/mixer_oss.c index 668604d0ec9d..05fc8911479c 100644 --- a/sound/core/oss/mixer_oss.c +++ b/sound/core/oss/mixer_oss.c @@ -900,8 +900,8 @@ static void snd_mixer_oss_slot_free(struct snd_mixer_oss_slot *chn) struct slot *p = chn->private_data; if (p) { if (p->allocated && p->assigned) { - kfree_const(p->assigned->name); - kfree_const(p->assigned); + kfree(p->assigned->name); + kfree(p->assigned); } kfree(p); } diff --git a/sound/core/oss/rate.c b/sound/core/oss/rate.c index 98269119347f..b56eeda5e30e 100644 --- a/sound/core/oss/rate.c +++ b/sound/core/oss/rate.c @@ -294,7 +294,7 @@ static int rate_action(struct snd_pcm_plugin *plugin, default: break; } - return 0; /* silenty ignore other actions */ + return 0; /* silently ignore other actions */ } int snd_pcm_plugin_build_rate(struct snd_pcm_substream *plug, diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index 5b9076829ade..b465fb6e1f5f 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -3115,7 +3115,7 @@ struct snd_pcm_sync_ptr32 { } c; } __packed; -/* recalcuate the boundary within 32bit */ +/* recalculate the boundary within 32bit */ static snd_pcm_uframes_t recalculate_boundary(struct snd_pcm_runtime *runtime) { snd_pcm_uframes_t boundary; diff --git a/sound/core/sound.c b/sound/core/sound.c index b9db9aa0bfcb..6531a67f13b3 100644 --- a/sound/core/sound.c +++ b/sound/core/sound.c @@ -133,7 +133,7 @@ static struct snd_minor *autoload_device(unsigned int minor) /* /dev/aloadSEQ */ snd_request_other(minor); } - mutex_lock(&sound_mutex); /* reacuire lock */ + mutex_lock(&sound_mutex); /* reacquire lock */ return snd_minors[minor]; } #else /* !CONFIG_MODULES */ diff --git a/sound/hda/hdac_stream.c b/sound/hda/hdac_stream.c index b53de020309f..2670792f43b4 100644 --- a/sound/hda/hdac_stream.c +++ b/sound/hda/hdac_stream.c @@ -657,6 +657,7 @@ static void azx_timecounter_init(struct hdac_stream *azx_dev, * snd_hdac_stream_timecounter_init - initialize time counter * @azx_dev: HD-audio core stream (master stream) * @streams: bit flags of streams to set up + * @start: true for PCM trigger start, false for other cases * * Initializes the time counter of streams marked by the bit flags (each * bit corresponds to the stream index). @@ -664,7 +665,7 @@ static void azx_timecounter_init(struct hdac_stream *azx_dev, * updated accordingly, too. */ void snd_hdac_stream_timecounter_init(struct hdac_stream *azx_dev, - unsigned int streams) + unsigned int streams, bool start) { struct hdac_bus *bus = azx_dev->bus; struct snd_pcm_runtime *runtime = azx_dev->substream->runtime; @@ -672,6 +673,9 @@ void snd_hdac_stream_timecounter_init(struct hdac_stream *azx_dev, bool inited = false; u64 cycle_last = 0; + if (!start) + goto skip; + list_for_each_entry(s, &bus->stream_list, list) { if ((streams & (1 << s->index))) { azx_timecounter_init(s, inited, cycle_last); @@ -682,6 +686,7 @@ void snd_hdac_stream_timecounter_init(struct hdac_stream *azx_dev, } } +skip: snd_pcm_gettime(runtime, &runtime->trigger_tstamp); runtime->trigger_tstamp_latched = true; } diff --git a/sound/i2c/cs8427.c b/sound/i2c/cs8427.c index 29a1a7a0d050..46f081268348 100644 --- a/sound/i2c/cs8427.c +++ b/sound/i2c/cs8427.c @@ -10,7 +10,7 @@ #include <linux/init.h> #include <linux/bitrev.h> #include <linux/module.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <sound/core.h> #include <sound/control.h> #include <sound/pcm.h> diff --git a/sound/isa/gus/gus_pcm.c b/sound/isa/gus/gus_pcm.c index bcbcaa924c12..16f9bbb43a54 100644 --- a/sound/isa/gus/gus_pcm.c +++ b/sound/isa/gus/gus_pcm.c @@ -364,7 +364,7 @@ static int snd_gf1_pcm_playback_copy(struct snd_pcm_substream *substream, bpos = get_bpos(pcmp, voice, pos, len); if (bpos < 0) - return pos; + return bpos; if (copy_from_iter(runtime->dma_area + bpos, len, src) != len) return -EFAULT; return playback_copy_ack(substream, bpos, len); @@ -381,7 +381,7 @@ static int snd_gf1_pcm_playback_silence(struct snd_pcm_substream *substream, bpos = get_bpos(pcmp, voice, pos, len); if (bpos < 0) - return pos; + return bpos; snd_pcm_format_set_silence(runtime->format, runtime->dma_area + bpos, bytes_to_samples(runtime, count)); return playback_copy_ack(substream, bpos, len); diff --git a/sound/pci/hda/cs35l41_hda_i2c.c b/sound/pci/hda/cs35l41_hda_i2c.c index 603e9bff3a71..bb84740c8520 100644 --- a/sound/pci/hda/cs35l41_hda_i2c.c +++ b/sound/pci/hda/cs35l41_hda_i2c.c @@ -39,7 +39,7 @@ static void cs35l41_hda_i2c_remove(struct i2c_client *clt) } static const struct i2c_device_id cs35l41_hda_i2c_id[] = { - { "cs35l41-hda", 0 }, + { "cs35l41-hda" }, {} }; diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c index 3dd1bda0c5c6..14763c0f31ad 100644 --- a/sound/pci/hda/hda_codec.c +++ b/sound/pci/hda/hda_codec.c @@ -1734,9 +1734,9 @@ EXPORT_SYMBOL_GPL(snd_hda_ctl_add); /** * snd_hda_add_nid - Assign a NID to a control element * @codec: HD-audio codec - * @nid: corresponding NID (optional) * @kctl: the control element to assign * @index: index to kctl + * @nid: corresponding NID (optional) * * Add the given control element to an array inside the codec instance. * This function is used when #snd_hda_ctl_add cannot be used for 1:1 diff --git a/sound/pci/hda/hda_controller.c b/sound/pci/hda/hda_controller.c index 5d86e5a9c814..f3330b7e0fcf 100644 --- a/sound/pci/hda/hda_controller.c +++ b/sound/pci/hda/hda_controller.c @@ -275,8 +275,7 @@ static int azx_pcm_trigger(struct snd_pcm_substream *substream, int cmd) spin_lock(&bus->reg_lock); /* reset SYNC bits */ snd_hdac_stream_sync_trigger(hstr, false, sbits, sync_reg); - if (start) - snd_hdac_stream_timecounter_init(hstr, sbits); + snd_hdac_stream_timecounter_init(hstr, sbits, start); spin_unlock(&bus->reg_lock); return 0; } diff --git a/sound/pci/hda/hda_controller.h b/sound/pci/hda/hda_controller.h index 68c883f202ca..c2d0109866e6 100644 --- a/sound/pci/hda/hda_controller.h +++ b/sound/pci/hda/hda_controller.h @@ -28,7 +28,7 @@ #else #define AZX_DCAPS_I915_COMPONENT 0 /* NOP */ #endif -#define AZX_DCAPS_AMD_ALLOC_FIX (1 << 14) /* AMD allocation workaround */ +/* 14 unused */ #define AZX_DCAPS_CTX_WORKAROUND (1 << 15) /* X-Fi workaround */ #define AZX_DCAPS_POSFIX_LPIB (1 << 16) /* Use LPIB as default */ #define AZX_DCAPS_AMD_WORKAROUND (1 << 17) /* AMD-specific workaround */ diff --git a/sound/pci/hda/hda_eld.c b/sound/pci/hda/hda_eld.c index 1d108ed5c6f2..301730432375 100644 --- a/sound/pci/hda/hda_eld.c +++ b/sound/pci/hda/hda_eld.c @@ -12,7 +12,7 @@ #include <linux/init.h> #include <linux/slab.h> #include <sound/core.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <sound/hda_chmap.h> #include <sound/hda_codec.h> #include "hda_local.h" diff --git a/sound/pci/hda/hda_generic.c b/sound/pci/hda/hda_generic.c index 9cff87dfbecb..b34d84fedcc8 100644 --- a/sound/pci/hda/hda_generic.c +++ b/sound/pci/hda/hda_generic.c @@ -1383,7 +1383,7 @@ static int try_assign_dacs(struct hda_codec *codec, int num_outs, struct nid_path *path; hda_nid_t pin = pins[i]; - if (!spec->obey_preferred_dacs) { + if (!spec->preferred_dacs) { path = snd_hda_get_path_from_idx(codec, path_idx[i]); if (path) { badness += assign_out_path_ctls(codec, path); @@ -1395,7 +1395,7 @@ static int try_assign_dacs(struct hda_codec *codec, int num_outs, if (dacs[i]) { if (is_dac_already_used(codec, dacs[i])) badness += bad->shared_primary; - } else if (spec->obey_preferred_dacs) { + } else if (spec->preferred_dacs) { badness += BAD_NO_PRIMARY_DAC; } diff --git a/sound/pci/hda/hda_generic.h b/sound/pci/hda/hda_generic.h index 08544601b4ce..9612afaa61c2 100644 --- a/sound/pci/hda/hda_generic.h +++ b/sound/pci/hda/hda_generic.h @@ -232,7 +232,6 @@ struct hda_gen_spec { unsigned int power_down_unused:1; /* power down unused widgets */ unsigned int dac_min_mute:1; /* minimal = mute for DACs */ unsigned int suppress_vmaster:1; /* don't create vmaster kctls */ - unsigned int obey_preferred_dacs:1; /* obey preferred_dacs assignment */ /* other internal flags */ unsigned int no_analog:1; /* digital I/O only */ diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 045cd555c291..b4540c5cd2a6 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -40,7 +40,6 @@ #ifdef CONFIG_X86 /* for snoop control */ -#include <linux/dma-map-ops.h> #include <asm/set_memory.h> #include <asm/cpufeature.h> #endif @@ -307,7 +306,7 @@ enum { /* quirks for ATI HDMI with snoop off */ #define AZX_DCAPS_PRESET_ATI_HDMI_NS \ - (AZX_DCAPS_PRESET_ATI_HDMI | AZX_DCAPS_AMD_ALLOC_FIX) + (AZX_DCAPS_PRESET_ATI_HDMI | AZX_DCAPS_SNOOP_OFF) /* quirks for AMD SB */ #define AZX_DCAPS_PRESET_AMD_SB \ @@ -1707,13 +1706,6 @@ static void azx_check_snoop_available(struct azx *chip) if (chip->driver_caps & AZX_DCAPS_SNOOP_OFF) snoop = false; -#ifdef CONFIG_X86 - /* check the presence of DMA ops (i.e. IOMMU), disable snoop conditionally */ - if ((chip->driver_caps & AZX_DCAPS_AMD_ALLOC_FIX) && - !get_dma_ops(chip->card->dev)) - snoop = false; -#endif - chip->snoop = snoop; if (!snoop) { dev_info(chip->card->dev, "Force to non-snoop mode\n"); diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c index e851785ff058..b61ce5e6f5ec 100644 --- a/sound/pci/hda/patch_conexant.c +++ b/sound/pci/hda/patch_conexant.c @@ -166,18 +166,18 @@ static void cxt_init_gpio_led(struct hda_codec *codec) static void cx_fixup_headset_recog(struct hda_codec *codec) { - unsigned int mic_persent; + unsigned int mic_present; /* fix some headset type recognize fail issue, such as EDIFIER headset */ - /* set micbiasd output current comparator threshold from 66% to 55%. */ + /* set micbias output current comparator threshold from 66% to 55%. */ snd_hda_codec_write(codec, 0x1c, 0, 0x320, 0x010); - /* set OFF voltage for DFET from -1.2V to -0.8V, set headset micbias registor + /* set OFF voltage for DFET from -1.2V to -0.8V, set headset micbias register * value adjustment trim from 2.2K ohms to 2.0K ohms. */ snd_hda_codec_write(codec, 0x1c, 0, 0x3b0, 0xe10); /* fix reboot headset type recognize fail issue */ - mic_persent = snd_hda_codec_read(codec, 0x19, 0, AC_VERB_GET_PIN_SENSE, 0x0); - if (mic_persent & AC_PINSENSE_PRESENCE) + mic_present = snd_hda_codec_read(codec, 0x19, 0, AC_VERB_GET_PIN_SENSE, 0x0); + if (mic_present & AC_PINSENSE_PRESENCE) /* enable headset mic VREF */ snd_hda_codec_write(codec, 0x19, 0, AC_VERB_SET_PIN_WIDGET_CONTROL, 0x24); else @@ -249,9 +249,9 @@ static void cx_update_headset_mic_vref(struct hda_codec *codec, struct hda_jack_ { unsigned int mic_present; - /* In cx8070 and sn6140, the node 16 can only be config to headphone or disabled, - * the node 19 can only be config to microphone or disabled. - * Check hp&mic tag to process headset pulgin&plugout. + /* In cx8070 and sn6140, the node 16 can only be configured to headphone or disabled, + * the node 19 can only be configured to microphone or disabled. + * Check hp&mic tag to process headset plugin & plugout. */ mic_present = snd_hda_codec_read(codec, 0x19, 0, AC_VERB_GET_PIN_SENSE, 0x0); if (!(mic_present & AC_PINSENSE_PRESENCE)) /* mic plugout */ @@ -816,6 +816,23 @@ static const struct hda_pintbl cxt_pincfg_sws_js201d[] = { {} }; +/* pincfg quirk for Tuxedo Sirius; + * unfortunately the (PCI) SSID conflicts with System76 Pangolin pang14, + * which has incompatible pin setup, so we check the codec SSID (luckily + * different one!) and conditionally apply the quirk here + */ +static void cxt_fixup_sirius_top_speaker(struct hda_codec *codec, + const struct hda_fixup *fix, + int action) +{ + /* ignore for incorrectly picked-up pang14 */ + if (codec->core.subsystem_id == 0x278212b3) + return; + /* set up the top speaker pin */ + if (action == HDA_FIXUP_ACT_PRE_PROBE) + snd_hda_codec_set_pincfg(codec, 0x1d, 0x82170111); +} + static const struct hda_fixup cxt_fixups[] = { [CXT_PINCFG_LENOVO_X200] = { .type = HDA_FIXUP_PINS, @@ -976,11 +993,8 @@ static const struct hda_fixup cxt_fixups[] = { .v.pins = cxt_pincfg_sws_js201d, }, [CXT_PINCFG_TOP_SPEAKER] = { - .type = HDA_FIXUP_PINS, - .v.pins = (const struct hda_pintbl[]) { - { 0x1d, 0x82170111 }, - { } - }, + .type = HDA_FIXUP_FUNC, + .v.func = cxt_fixup_sirius_top_speaker, }, }; diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 4ca66234e561..5e2e927656cd 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -587,6 +587,7 @@ static void alc_shutup_pins(struct hda_codec *codec) switch (codec->core.vendor_id) { case 0x10ec0236: case 0x10ec0256: + case 0x10ec0257: case 0x19e58326: case 0x10ec0283: case 0x10ec0285: @@ -6644,10 +6645,8 @@ static void alc289_fixup_asus_ga401(struct hda_codec *codec, }; struct alc_spec *spec = codec->spec; - if (action == HDA_FIXUP_ACT_PRE_PROBE) { + if (action == HDA_FIXUP_ACT_PRE_PROBE) spec->gen.preferred_dacs = preferred_pairs; - spec->gen.obey_preferred_dacs = 1; - } } /* The DAC of NID 0x3 will introduce click/pop noise on headphones, so invalidate it */ @@ -10349,6 +10348,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8896, "HP EliteBook 855 G8 Notebook PC", ALC285_FIXUP_HP_MUTE_LED), SND_PCI_QUIRK(0x103c, 0x8898, "HP EliteBook 845 G8 Notebook PC", ALC285_FIXUP_HP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x103c, 0x88d0, "HP Pavilion 15-eh1xxx (mainboard 88D0)", ALC287_FIXUP_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x88dd, "HP Pavilion 15z-ec200", ALC285_FIXUP_HP_MUTE_LED), SND_PCI_QUIRK(0x103c, 0x8902, "HP OMEN 16", ALC285_FIXUP_HP_MUTE_LED), SND_PCI_QUIRK(0x103c, 0x890e, "HP 255 G8 Notebook PC", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2), SND_PCI_QUIRK(0x103c, 0x8919, "HP Pavilion Aero Laptop 13-be0xxx", ALC287_FIXUP_HP_GPIO_LED), @@ -10490,6 +10490,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8ca2, "HP ZBook Power", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8ca4, "HP ZBook Fury", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8ca7, "HP ZBook Fury", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8caf, "HP Elite mt645 G8 Mobile Thin Client", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8cbd, "HP Pavilion Aero Laptop 13-bg0xxx", ALC245_FIXUP_HP_X360_MUTE_LEDS), SND_PCI_QUIRK(0x103c, 0x8cdd, "HP Spectre", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x103c, 0x8cde, "HP Spectre", ALC287_FIXUP_CS35L41_I2C_2), @@ -10842,6 +10843,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x38cd, "Y790 VECO DUAL", ALC287_FIXUP_TAS2781_I2C), SND_PCI_QUIRK(0x17aa, 0x38d2, "Lenovo Yoga 9 14IMH9", ALC287_FIXUP_YOGA9_14IMH9_BASS_SPK_PIN), SND_PCI_QUIRK(0x17aa, 0x38d7, "Lenovo Yoga 9 14IMH9", ALC287_FIXUP_YOGA9_14IMH9_BASS_SPK_PIN), + SND_PCI_QUIRK(0x17aa, 0x38df, "Y990 YG DUAL", ALC287_FIXUP_TAS2781_I2C), SND_PCI_QUIRK(0x17aa, 0x38f9, "Thinkbook 16P Gen5", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x17aa, 0x38fa, "Thinkbook 16P Gen5", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x17aa, 0x3902, "Lenovo E50-80", ALC269_FIXUP_DMIC_THINKPAD_ACPI), @@ -10878,6 +10880,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1854, 0x048a, "LG gram 17 (17ZD90R)", ALC298_FIXUP_SAMSUNG_AMP_V2_4_AMPS), SND_PCI_QUIRK(0x19e5, 0x3204, "Huawei MACH-WX9", ALC256_FIXUP_HUAWEI_MACH_WX9_PINS), SND_PCI_QUIRK(0x19e5, 0x320f, "Huawei WRT-WX9 ", ALC256_FIXUP_ASUS_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x19e5, 0x3212, "Huawei KLV-WX9 ", ALC256_FIXUP_ACER_HEADSET_MIC), SND_PCI_QUIRK(0x1b35, 0x1235, "CZC B20", ALC269_FIXUP_CZC_B20), SND_PCI_QUIRK(0x1b35, 0x1236, "CZC TMI", ALC269_FIXUP_CZC_TMI), SND_PCI_QUIRK(0x1b35, 0x1237, "CZC L101", ALC269_FIXUP_CZC_L101), diff --git a/sound/pci/hda/tas2781_hda_i2c.c b/sound/pci/hda/tas2781_hda_i2c.c index f58f434e7110..370d847517f9 100644 --- a/sound/pci/hda/tas2781_hda_i2c.c +++ b/sound/pci/hda/tas2781_hda_i2c.c @@ -7,7 +7,7 @@ // Author: Shenghao Ding <shenghao-ding@ti.com> // Current maintainer: Baojun Xu <baojun.xu@ti.com> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/acpi.h> #include <linux/crc8.h> #include <linux/crc32.h> @@ -951,7 +951,7 @@ static const struct dev_pm_ops tas2781_hda_pm_ops = { }; static const struct i2c_device_id tas2781_hda_i2c_id[] = { - { "tas2781-hda", 0 }, + { "tas2781-hda" }, {} }; diff --git a/sound/soc/amd/acp/acp-sdw-sof-mach.c b/sound/soc/amd/acp/acp-sdw-sof-mach.c index 6c50c8276538..306854fb08e3 100644 --- a/sound/soc/amd/acp/acp-sdw-sof-mach.c +++ b/sound/soc/amd/acp/acp-sdw-sof-mach.c @@ -400,9 +400,6 @@ err_dai: return ret; } -/* SoC card */ -static const char sdw_card_long_name[] = "AMD Soundwire SOF"; - static int mc_probe(struct platform_device *pdev) { struct snd_soc_acpi_mach *mach = dev_get_platdata(&pdev->dev); @@ -463,8 +460,6 @@ static int mc_probe(struct platform_device *pdev) if (!card->components) return -ENOMEM; - card->long_name = sdw_card_long_name; - /* Register the card */ ret = devm_snd_soc_register_card(card->dev, card); if (ret) { diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c index 06349bf0b658..ace6328e91e3 100644 --- a/sound/soc/amd/yc/acp6x-mach.c +++ b/sound/soc/amd/yc/acp6x-mach.c @@ -448,6 +448,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { .driver_data = &acp6x_card, .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "HP"), + DMI_MATCH(DMI_BOARD_NAME, "8A7F"), + } + }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "HP"), DMI_MATCH(DMI_BOARD_NAME, "8B27"), } }, diff --git a/sound/soc/atmel/mchp-pdmc.c b/sound/soc/atmel/mchp-pdmc.c index 939cd44ebc8a..06dc3c48e7e8 100644 --- a/sound/soc/atmel/mchp-pdmc.c +++ b/sound/soc/atmel/mchp-pdmc.c @@ -302,6 +302,9 @@ static int mchp_pdmc_chmap_ctl_put(struct snd_kcontrol *kcontrol, if (!substream) return -ENODEV; + if (!substream->runtime) + return 0; /* just for avoiding error from alsactl restore */ + map = mchp_pdmc_chmap_get(substream, info); if (!map) return -EINVAL; diff --git a/sound/soc/codecs/adau1701.c b/sound/soc/codecs/adau1701.c index 8bd6067df7f7..291249e0a2a3 100644 --- a/sound/soc/codecs/adau1701.c +++ b/sound/soc/codecs/adau1701.c @@ -21,7 +21,7 @@ #include <sound/pcm_params.h> #include <sound/soc.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "sigmadsp.h" #include "adau1701.h" diff --git a/sound/soc/codecs/adau17x1.c b/sound/soc/codecs/adau17x1.c index f2932713b4de..4dcc984761e0 100644 --- a/sound/soc/codecs/adau17x1.c +++ b/sound/soc/codecs/adau17x1.c @@ -19,7 +19,7 @@ #include <linux/i2c.h> #include <linux/spi/spi.h> #include <linux/regmap.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "sigmadsp.h" #include "adau17x1.h" diff --git a/sound/soc/codecs/cs35l45-tables.c b/sound/soc/codecs/cs35l45-tables.c index e1cebb9e4dc6..405dab137b3b 100644 --- a/sound/soc/codecs/cs35l45-tables.c +++ b/sound/soc/codecs/cs35l45-tables.c @@ -315,7 +315,7 @@ static const struct { { 0x3B, 24576000 }, }; -unsigned int cs35l45_get_clk_freq_id(unsigned int freq) +int cs35l45_get_clk_freq_id(unsigned int freq) { int i; diff --git a/sound/soc/codecs/cs35l45.h b/sound/soc/codecs/cs35l45.h index e2ebcf58d7e0..7a790d2acac7 100644 --- a/sound/soc/codecs/cs35l45.h +++ b/sound/soc/codecs/cs35l45.h @@ -507,7 +507,7 @@ extern const struct dev_pm_ops cs35l45_pm_ops; extern const struct regmap_config cs35l45_i2c_regmap; extern const struct regmap_config cs35l45_spi_regmap; int cs35l45_apply_patch(struct cs35l45_private *cs35l45); -unsigned int cs35l45_get_clk_freq_id(unsigned int freq); +int cs35l45_get_clk_freq_id(unsigned int freq); int cs35l45_probe(struct cs35l45_private *cs35l45); void cs35l45_remove(struct cs35l45_private *cs35l45); diff --git a/sound/soc/codecs/lpass-rx-macro.c b/sound/soc/codecs/lpass-rx-macro.c index 71e0d3bffd3f..ef7a70fa6966 100644 --- a/sound/soc/codecs/lpass-rx-macro.c +++ b/sound/soc/codecs/lpass-rx-macro.c @@ -958,7 +958,7 @@ static const struct reg_default rx_defaults[] = { { CDC_RX_BCL_VBAT_PK_EST2, 0x01 }, { CDC_RX_BCL_VBAT_PK_EST3, 0x40 }, { CDC_RX_BCL_VBAT_RF_PROC1, 0x2A }, - { CDC_RX_BCL_VBAT_RF_PROC1, 0x00 }, + { CDC_RX_BCL_VBAT_RF_PROC2, 0x00 }, { CDC_RX_BCL_VBAT_TAC1, 0x00 }, { CDC_RX_BCL_VBAT_TAC2, 0x18 }, { CDC_RX_BCL_VBAT_TAC3, 0x18 }, diff --git a/sound/soc/codecs/pcm6240.c b/sound/soc/codecs/pcm6240.c index 6641e7c1ddf4..5d99877f8839 100644 --- a/sound/soc/codecs/pcm6240.c +++ b/sound/soc/codecs/pcm6240.c @@ -12,7 +12,7 @@ // Author: Shenghao Ding <shenghao-ding@ti.com> // -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/firmware.h> #include <linux/gpio.h> #include <linux/i2c.h> diff --git a/sound/soc/codecs/peb2466.c b/sound/soc/codecs/peb2466.c index 74b628ae1964..bb9ca6354ae1 100644 --- a/sound/soc/codecs/peb2466.c +++ b/sound/soc/codecs/peb2466.c @@ -6,7 +6,7 @@ // // Author: Herve Codina <herve.codina@bootlin.com> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/clk.h> #include <linux/firmware.h> #include <linux/gpio/consumer.h> diff --git a/sound/soc/codecs/sigmadsp-i2c.c b/sound/soc/codecs/sigmadsp-i2c.c index cb4c491078c2..07c9d89ab24a 100644 --- a/sound/soc/codecs/sigmadsp-i2c.c +++ b/sound/soc/codecs/sigmadsp-i2c.c @@ -9,7 +9,7 @@ #include <linux/i2c.h> #include <linux/module.h> #include <linux/slab.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "sigmadsp.h" diff --git a/sound/soc/codecs/tas2781-fmwlib.c b/sound/soc/codecs/tas2781-fmwlib.c index 3de0132c345d..ae360c97fe1e 100644 --- a/sound/soc/codecs/tas2781-fmwlib.c +++ b/sound/soc/codecs/tas2781-fmwlib.c @@ -20,7 +20,7 @@ #include <sound/soc.h> #include <sound/tlv.h> #include <sound/tas2781.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define ERROR_PRAM_CRCCHK 0x0000000 #define ERROR_YRAM_CRCCHK 0x0000001 diff --git a/sound/soc/codecs/tas2781-i2c.c b/sound/soc/codecs/tas2781-i2c.c index d0ba7cbe03a8..12d093437ba9 100644 --- a/sound/soc/codecs/tas2781-i2c.c +++ b/sound/soc/codecs/tas2781-i2c.c @@ -31,7 +31,7 @@ #include <sound/tlv.h> #include <sound/tas2563-tlv.h> #include <sound/tas2781-tlv.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define X2563_CL_STT_VAL(xreg, xval) \ { .reg = xreg, \ diff --git a/sound/soc/codecs/tas571x.c b/sound/soc/codecs/tas571x.c index f249e93e2a4e..6c6e7ae07d80 100644 --- a/sound/soc/codecs/tas571x.c +++ b/sound/soc/codecs/tas571x.c @@ -27,7 +27,7 @@ #include <sound/pcm_params.h> #include <sound/soc.h> #include <sound/tlv.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "tas571x.h" diff --git a/sound/soc/codecs/tlv320aic31xx.c b/sound/soc/codecs/tlv320aic31xx.c index 187d68e8688c..d81ab9c25c29 100644 --- a/sound/soc/codecs/tlv320aic31xx.c +++ b/sound/soc/codecs/tlv320aic31xx.c @@ -12,7 +12,7 @@ * and mono/stereo Class-D speaker driver. */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/init.h> diff --git a/sound/soc/codecs/wm5102.c b/sound/soc/codecs/wm5102.c index 651f1319204d..9fc7a8325724 100644 --- a/sound/soc/codecs/wm5102.c +++ b/sound/soc/codecs/wm5102.c @@ -25,7 +25,7 @@ #include <linux/mfd/arizona/core.h> #include <linux/mfd/arizona/registers.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "arizona.h" #include "wm5102.h" diff --git a/sound/soc/codecs/wm8958-dsp2.c b/sound/soc/codecs/wm8958-dsp2.c index 7878c7a58ff1..d08419b108fe 100644 --- a/sound/soc/codecs/wm8958-dsp2.c +++ b/sound/soc/codecs/wm8958-dsp2.c @@ -25,7 +25,7 @@ #include <linux/mfd/wm8994/pdata.h> #include <linux/mfd/wm8994/gpio.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "wm8994.h" diff --git a/sound/soc/fsl/fsl_sai.c b/sound/soc/fsl/fsl_sai.c index ab58a4461073..634168d2bb6e 100644 --- a/sound/soc/fsl/fsl_sai.c +++ b/sound/soc/fsl/fsl_sai.c @@ -613,6 +613,9 @@ static int fsl_sai_hw_params(struct snd_pcm_substream *substream, val_cr4 |= FSL_SAI_CR4_FRSZ(slots); + /* Set to avoid channel swap */ + val_cr4 |= FSL_SAI_CR4_FCONT; + /* Set to output mode to avoid tri-stated data pins */ if (tx) val_cr4 |= FSL_SAI_CR4_CHMOD; @@ -699,7 +702,7 @@ static int fsl_sai_hw_params(struct snd_pcm_substream *substream, regmap_update_bits(sai->regmap, FSL_SAI_xCR4(tx, ofs), FSL_SAI_CR4_SYWD_MASK | FSL_SAI_CR4_FRSZ_MASK | - FSL_SAI_CR4_CHMOD_MASK, + FSL_SAI_CR4_CHMOD_MASK | FSL_SAI_CR4_FCONT_MASK, val_cr4); regmap_update_bits(sai->regmap, FSL_SAI_xCR5(tx, ofs), FSL_SAI_CR5_WNW_MASK | FSL_SAI_CR5_W0W_MASK | diff --git a/sound/soc/fsl/fsl_sai.h b/sound/soc/fsl/fsl_sai.h index dadbd16ee394..9c4d19fe22c6 100644 --- a/sound/soc/fsl/fsl_sai.h +++ b/sound/soc/fsl/fsl_sai.h @@ -137,6 +137,7 @@ /* SAI Transmit and Receive Configuration 4 Register */ +#define FSL_SAI_CR4_FCONT_MASK BIT(28) #define FSL_SAI_CR4_FCONT BIT(28) #define FSL_SAI_CR4_FCOMB_SHIFT BIT(26) #define FSL_SAI_CR4_FCOMB_SOFT BIT(27) diff --git a/sound/soc/fsl/imx-card.c b/sound/soc/fsl/imx-card.c index 98b37dd2b901..a7215bad6484 100644 --- a/sound/soc/fsl/imx-card.c +++ b/sound/soc/fsl/imx-card.c @@ -710,6 +710,7 @@ static int imx_card_probe(struct platform_device *pdev) data->plat_data = plat_data; data->card.dev = &pdev->dev; + data->card.owner = THIS_MODULE; dev_set_drvdata(&pdev->dev, &data->card); snd_soc_card_set_drvdata(&data->card, data); diff --git a/sound/soc/intel/boards/sof_sdw.c b/sound/soc/intel/boards/sof_sdw.c index 5196d96f5c0e..35d707d3ae9c 100644 --- a/sound/soc/intel/boards/sof_sdw.c +++ b/sound/soc/intel/boards/sof_sdw.c @@ -800,6 +800,9 @@ static int create_ssp_dailinks(struct snd_soc_card *card, char *cpu_dai_name = devm_kasprintf(dev, GFP_KERNEL, "SSP%d Pin", i); char *codec_name = devm_kasprintf(dev, GFP_KERNEL, "i2c-%s:0%d", ssp_info->acpi_id, j++); + if (!name || !cpu_dai_name || !codec_name) + return -ENOMEM; + int playback = ssp_info->dais[0].direction[SNDRV_PCM_STREAM_PLAYBACK]; int capture = ssp_info->dais[0].direction[SNDRV_PCM_STREAM_CAPTURE]; @@ -866,6 +869,9 @@ static int create_hdmi_dailinks(struct snd_soc_card *card, for (i = 0; i < hdmi_num; i++) { char *name = devm_kasprintf(dev, GFP_KERNEL, "iDisp%d", i + 1); char *cpu_dai_name = devm_kasprintf(dev, GFP_KERNEL, "iDisp%d Pin", i + 1); + if (!name || !cpu_dai_name) + return -ENOMEM; + char *codec_name, *codec_dai_name; if (intel_ctx->hdmi.idisp_codec) { @@ -877,6 +883,9 @@ static int create_hdmi_dailinks(struct snd_soc_card *card, codec_dai_name = "snd-soc-dummy-dai"; } + if (!codec_dai_name) + return -ENOMEM; + ret = asoc_sdw_init_simple_dai_link(dev, *dai_links, be_id, name, 1, 0, // HDMI only supports playback cpu_dai_name, platform_component->name, @@ -900,6 +909,9 @@ static int create_bt_dailinks(struct snd_soc_card *card, SOF_BT_OFFLOAD_SSP_SHIFT; char *name = devm_kasprintf(dev, GFP_KERNEL, "SSP%d-BT", port); char *cpu_dai_name = devm_kasprintf(dev, GFP_KERNEL, "SSP%d Pin", port); + if (!name || !cpu_dai_name) + return -ENOMEM; + int ret; ret = asoc_sdw_init_simple_dai_link(dev, *dai_links, be_id, name, diff --git a/sound/soc/intel/common/soc-acpi-intel-arl-match.c b/sound/soc/intel/common/soc-acpi-intel-arl-match.c index c97c961187dd..072b8486d072 100644 --- a/sound/soc/intel/common/soc-acpi-intel-arl-match.c +++ b/sound/soc/intel/common/soc-acpi-intel-arl-match.c @@ -191,6 +191,7 @@ static const struct snd_soc_acpi_link_adr arl_cs42l43_l0[] = { .num_adr = ARRAY_SIZE(cs42l43_0_adr), .adr_d = cs42l43_0_adr, }, + {} }; static const struct snd_soc_acpi_link_adr arl_cs42l43_l2[] = { @@ -199,6 +200,7 @@ static const struct snd_soc_acpi_link_adr arl_cs42l43_l2[] = { .num_adr = ARRAY_SIZE(cs42l43_2_adr), .adr_d = cs42l43_2_adr, }, + {} }; static const struct snd_soc_acpi_link_adr arl_cs42l43_l2_cs35l56_l3[] = { diff --git a/sound/soc/intel/common/soc-acpi-intel-rpl-match.c b/sound/soc/intel/common/soc-acpi-intel-rpl-match.c index bc8817633b81..b83ac2e6337c 100644 --- a/sound/soc/intel/common/soc-acpi-intel-rpl-match.c +++ b/sound/soc/intel/common/soc-acpi-intel-rpl-match.c @@ -198,6 +198,7 @@ static const struct snd_soc_acpi_link_adr rpl_cs42l43_l0[] = { .num_adr = ARRAY_SIZE(cs42l43_0_adr), .adr_d = cs42l43_0_adr, }, + {} }; static const struct snd_soc_acpi_link_adr rpl_sdca_3_in_1[] = { diff --git a/sound/soc/qcom/sm8250.c b/sound/soc/qcom/sm8250.c index 274bab28209a..19adadedc88a 100644 --- a/sound/soc/qcom/sm8250.c +++ b/sound/soc/qcom/sm8250.c @@ -174,6 +174,7 @@ static int sm8250_platform_probe(struct platform_device *pdev) static const struct of_device_id snd_sm8250_dt_match[] = { {.compatible = "qcom,sm8250-sndcard"}, + {.compatible = "qcom,qrb4210-rb2-sndcard"}, {.compatible = "qcom,qrb5165-rb5-sndcard"}, {} }; diff --git a/sound/soc/soc-topology.c b/sound/soc/soc-topology.c index af3158cdc8d5..97517423d1f0 100644 --- a/sound/soc/soc-topology.c +++ b/sound/soc/soc-topology.c @@ -889,7 +889,7 @@ static int soc_tplg_dbytes_create(struct soc_tplg *tplg, size_t size) return ret; /* register dynamic object */ - sbe = (struct soc_bytes_ext *)&kc.private_value; + sbe = (struct soc_bytes_ext *)kc.private_value; INIT_LIST_HEAD(&sbe->dobj.list); sbe->dobj.type = SND_SOC_DOBJ_BYTES; @@ -923,7 +923,7 @@ static int soc_tplg_dmixer_create(struct soc_tplg *tplg, size_t size) return ret; /* register dynamic object */ - sm = (struct soc_mixer_control *)&kc.private_value; + sm = (struct soc_mixer_control *)kc.private_value; INIT_LIST_HEAD(&sm->dobj.list); sm->dobj.type = SND_SOC_DOBJ_MIXER; diff --git a/sound/soc/sof/iomem-utils.c b/sound/soc/sof/iomem-utils.c index cd9cb54e7b23..f6cb79082672 100644 --- a/sound/soc/sof/iomem-utils.c +++ b/sound/soc/sof/iomem-utils.c @@ -10,7 +10,7 @@ #include <linux/io-64-nonatomic-lo-hi.h> #include <linux/platform_device.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <sound/soc.h> #include <sound/sof.h> #include "sof-priv.h" diff --git a/sound/soc/sof/sof-utils.c b/sound/soc/sof/sof-utils.c index 44608682e9f8..f70089317b8c 100644 --- a/sound/soc/sof/sof-utils.c +++ b/sound/soc/sof/sof-utils.c @@ -8,7 +8,7 @@ // Author: Keyon Jie <yang.jie@linux.intel.com> // -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/io-64-nonatomic-lo-hi.h> #include <linux/device.h> #include <sound/memalloc.h> diff --git a/sound/usb/line6/podhd.c b/sound/usb/line6/podhd.c index ffd8c157a281..70de08635f54 100644 --- a/sound/usb/line6/podhd.c +++ b/sound/usb/line6/podhd.c @@ -507,7 +507,7 @@ static const struct line6_properties podhd_properties_table[] = { [LINE6_PODHD500X] = { .id = "PODHD500X", .name = "POD HD500X", - .capabilities = LINE6_CAP_CONTROL + .capabilities = LINE6_CAP_CONTROL | LINE6_CAP_HWMON_CTL | LINE6_CAP_PCM | LINE6_CAP_HWMON, .altsetting = 1, .ep_ctrl_r = 0x81, diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index f62631b54e10..e6278a245795 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -2221,6 +2221,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { QUIRK_FLAG_DISABLE_AUTOSUSPEND), DEVICE_FLG(0x17aa, 0x104d, /* Lenovo ThinkStation P620 Internal Speaker + Front Headset */ QUIRK_FLAG_DISABLE_AUTOSUSPEND), + DEVICE_FLG(0x1852, 0x5062, /* Luxman D-08u */ + QUIRK_FLAG_ITF_USB_DSD_DAC | QUIRK_FLAG_CTL_MSG_DELAY), DEVICE_FLG(0x1852, 0x5065, /* Luxman DA-06 */ QUIRK_FLAG_ITF_USB_DSD_DAC | QUIRK_FLAG_CTL_MSG_DELAY), DEVICE_FLG(0x1901, 0x0191, /* GE B850V3 CP2114 audio interface */ @@ -2279,6 +2281,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { QUIRK_FLAG_GENERIC_IMPLICIT_FB), DEVICE_FLG(0x2b53, 0x0031, /* Fiero SC-01 (firmware v1.1.0) */ QUIRK_FLAG_GENERIC_IMPLICIT_FB), + DEVICE_FLG(0x2d95, 0x8011, /* VIVO USB-C HEADSET */ + QUIRK_FLAG_CTL_MSG_DELAY_1M), DEVICE_FLG(0x2d95, 0x8021, /* VIVO USB-C-XE710 HEADSET */ QUIRK_FLAG_CTL_MSG_DELAY_1M), DEVICE_FLG(0x30be, 0x0101, /* Schiit Hel */ diff --git a/tools/arch/x86/lib/insn.c b/tools/arch/x86/lib/insn.c index a43b37346a22..ab5cdc3337da 100644 --- a/tools/arch/x86/lib/insn.c +++ b/tools/arch/x86/lib/insn.c @@ -13,7 +13,7 @@ #endif #include "../include/asm/inat.h" /* __ignore_sync_check__ */ #include "../include/asm/insn.h" /* __ignore_sync_check__ */ -#include "../include/asm-generic/unaligned.h" /* __ignore_sync_check__ */ +#include "../include/linux/unaligned.h" /* __ignore_sync_check__ */ #include <linux/errno.h> #include <linux/kconfig.h> diff --git a/tools/include/linux/linkage.h b/tools/include/linux/linkage.h index b7183576d8eb..7baaa5898ca2 100644 --- a/tools/include/linux/linkage.h +++ b/tools/include/linux/linkage.h @@ -4,7 +4,9 @@ #include <linux/export.h> #define SYM_FUNC_START(x) .globl x; x: - #define SYM_FUNC_END(x) +#define SYM_DATA_START(x) .globl x; x: +#define SYM_DATA_START_LOCAL(x) x: +#define SYM_DATA_END(x) #endif /* _TOOLS_INCLUDE_LINUX_LINKAGE_H */ diff --git a/tools/include/asm-generic/unaligned.h b/tools/include/linux/unaligned.h index cdd2fd078027..bc0633bc4650 100644 --- a/tools/include/asm-generic/unaligned.h +++ b/tools/include/linux/unaligned.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __ASM_GENERIC_UNALIGNED_H -#define __ASM_GENERIC_UNALIGNED_H +#ifndef __LINUX_UNALIGNED_H +#define __LINUX_UNALIGNED_H /* * This is the most generic implementation of unaligned accesses @@ -154,4 +154,4 @@ static inline u64 get_unaligned_be48(const void *p) } #pragma GCC diagnostic pop -#endif /* __ASM_GENERIC_UNALIGNED_H */ +#endif /* __LINUX_UNALIGNED_H */ diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh index f1080d409666..29adbb423327 100755 --- a/tools/perf/check-headers.sh +++ b/tools/perf/check-headers.sh @@ -187,7 +187,7 @@ check arch/x86/lib/memcpy_64.S '-I "^EXPORT_SYMBOL" -I "^#include <asm/ex check arch/x86/lib/memset_64.S '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>" -I"^SYM_FUNC_START\(_LOCAL\)*(memset_\(erms\|orig\))"' check arch/x86/include/asm/amd-ibs.h '-I "^#include [<\"]\(asm/\)*msr-index.h"' check arch/arm64/include/asm/cputype.h '-I "^#include [<\"]\(asm/\)*sysreg.h"' -check include/asm-generic/unaligned.h '-I "^#include <linux/unaligned/packed_struct.h>" -I "^#include <asm/byteorder.h>" -I "^#pragma GCC diagnostic"' +check include/linux/unaligned.h '-I "^#include <linux/unaligned/packed_struct.h>" -I "^#include <asm/byteorder.h>" -I "^#pragma GCC diagnostic"' check include/uapi/asm-generic/mman.h '-I "^#include <\(uapi/\)*asm-generic/mman-common\(-tools\)*.h>"' check include/uapi/linux/mman.h '-I "^#include <\(uapi/\)*asm/mman.h>"' check include/linux/build_bug.h '-I "^#\(ifndef\|endif\)\( \/\/\)* static_assert$"' diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c b/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c index 7bf607d0f6d8..4cef10a83962 100644 --- a/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c +++ b/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c @@ -11,7 +11,7 @@ #include <linux/bitops.h> #include <stdarg.h> #include <linux/kernel.h> -#include <asm-generic/unaligned.h> +#include <linux/unaligned.h> #include "arm-spe-pkt-decoder.h" diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c index bccb988a7a44..94fb16cf9e0c 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c @@ -10,7 +10,7 @@ #include <byteswap.h> #include <linux/kernel.h> #include <linux/compiler.h> -#include <asm-generic/unaligned.h> +#include <linux/unaligned.h> #include "intel-pt-pkt-decoder.h" diff --git a/tools/sched_ext/include/scx/common.bpf.h b/tools/sched_ext/include/scx/common.bpf.h index f538c75db183..225f61f9bfca 100644 --- a/tools/sched_ext/include/scx/common.bpf.h +++ b/tools/sched_ext/include/scx/common.bpf.h @@ -7,7 +7,13 @@ #ifndef __SCX_COMMON_BPF_H #define __SCX_COMMON_BPF_H +#ifdef LSP +#define __bpf__ +#include "../vmlinux/vmlinux.h" +#else #include "vmlinux.h" +#endif + #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> #include <asm-generic/errno.h> @@ -309,6 +315,15 @@ void bpf_cpumask_copy(struct bpf_cpumask *dst, const struct cpumask *src) __ksym u32 bpf_cpumask_any_distribute(const struct cpumask *cpumask) __ksym; u32 bpf_cpumask_any_and_distribute(const struct cpumask *src1, const struct cpumask *src2) __ksym; +u32 bpf_cpumask_weight(const struct cpumask *cpumask) __ksym; + +/* + * Access a cpumask in read-only mode (typically to check bits). + */ +const struct cpumask *cast_mask(struct bpf_cpumask *mask) +{ + return (const struct cpumask *)mask; +} /* rcu */ void bpf_rcu_read_lock(void) __ksym; diff --git a/tools/sched_ext/include/scx/compat.bpf.h b/tools/sched_ext/include/scx/compat.bpf.h index 3d2fe1208900..e5afe9efd3f3 100644 --- a/tools/sched_ext/include/scx/compat.bpf.h +++ b/tools/sched_ext/include/scx/compat.bpf.h @@ -15,6 +15,25 @@ __ret; \ }) +/* v6.12: 819513666966 ("sched_ext: Add cgroup support") */ +#define __COMPAT_scx_bpf_task_cgroup(p) \ + (bpf_ksym_exists(scx_bpf_task_cgroup) ? \ + scx_bpf_task_cgroup((p)) : NULL) + +/* v6.12: 4c30f5ce4f7a ("sched_ext: Implement scx_bpf_dispatch[_vtime]_from_dsq()") */ +#define __COMPAT_scx_bpf_dispatch_from_dsq_set_slice(it, slice) \ + (bpf_ksym_exists(scx_bpf_dispatch_from_dsq_set_slice) ? \ + scx_bpf_dispatch_from_dsq_set_slice((it), (slice)) : (void)0) +#define __COMPAT_scx_bpf_dispatch_from_dsq_set_vtime(it, vtime) \ + (bpf_ksym_exists(scx_bpf_dispatch_from_dsq_set_vtime) ? \ + scx_bpf_dispatch_from_dsq_set_vtime((it), (vtime)) : (void)0) +#define __COMPAT_scx_bpf_dispatch_from_dsq(it, p, dsq_id, enq_flags) \ + (bpf_ksym_exists(scx_bpf_dispatch_from_dsq) ? \ + scx_bpf_dispatch_from_dsq((it), (p), (dsq_id), (enq_flags)) : false) +#define __COMPAT_scx_bpf_dispatch_vtime_from_dsq(it, p, dsq_id, enq_flags) \ + (bpf_ksym_exists(scx_bpf_dispatch_vtime_from_dsq) ? \ + scx_bpf_dispatch_vtime_from_dsq((it), (p), (dsq_id), (enq_flags)) : false) + /* * Define sched_ext_ops. This may be expanded to define multiple variants for * backward compatibility. See compat.h::SCX_OPS_LOAD/ATTACH(). diff --git a/tools/sched_ext/include/scx/user_exit_info.h b/tools/sched_ext/include/scx/user_exit_info.h index 891693ee604e..8ce2734402e1 100644 --- a/tools/sched_ext/include/scx/user_exit_info.h +++ b/tools/sched_ext/include/scx/user_exit_info.h @@ -25,7 +25,11 @@ struct user_exit_info { #ifdef __bpf__ +#ifdef LSP +#include "../vmlinux/vmlinux.h" +#else #include "vmlinux.h" +#endif #include <bpf/bpf_core_read.h> #define UEI_DEFINE(__name) \ diff --git a/tools/sched_ext/scx_flatcg.bpf.c b/tools/sched_ext/scx_flatcg.bpf.c index 3ab2b60781a0..b722baf6da4b 100644 --- a/tools/sched_ext/scx_flatcg.bpf.c +++ b/tools/sched_ext/scx_flatcg.bpf.c @@ -49,7 +49,10 @@ /* * Maximum amount of retries to find a valid cgroup. */ -#define CGROUP_MAX_RETRIES 1024 +enum { + FALLBACK_DSQ = 0, + CGROUP_MAX_RETRIES = 1024, +}; char _license[] SEC("license") = "GPL"; @@ -225,7 +228,7 @@ static void cgrp_refresh_hweight(struct cgroup *cgrp, struct fcg_cgrp_ctx *cgc) break; /* - * We can be oppotunistic here and not grab the + * We can be opportunistic here and not grab the * cgv_tree_lock and deal with the occasional races. * However, hweight updates are already cached and * relatively low-frequency. Let's just do the @@ -258,8 +261,7 @@ static void cgrp_cap_budget(struct cgv_node *cgv_node, struct fcg_cgrp_ctx *cgc) * and thus can't be updated and repositioned. Instead, we collect the * vtime deltas separately and apply it asynchronously here. */ - delta = cgc->cvtime_delta; - __sync_fetch_and_sub(&cgc->cvtime_delta, delta); + delta = __sync_fetch_and_sub(&cgc->cvtime_delta, cgc->cvtime_delta); cvtime = cgv_node->cvtime + delta; /* @@ -378,12 +380,12 @@ void BPF_STRUCT_OPS(fcg_enqueue, struct task_struct *p, u64 enq_flags) scx_bpf_dispatch(p, SCX_DSQ_LOCAL, SCX_SLICE_DFL, enq_flags); } else { stat_inc(FCG_STAT_GLOBAL); - scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags); + scx_bpf_dispatch(p, FALLBACK_DSQ, SCX_SLICE_DFL, enq_flags); } return; } - cgrp = scx_bpf_task_cgroup(p); + cgrp = __COMPAT_scx_bpf_task_cgroup(p); cgc = find_cgrp_ctx(cgrp); if (!cgc) goto out_release; @@ -509,7 +511,7 @@ void BPF_STRUCT_OPS(fcg_runnable, struct task_struct *p, u64 enq_flags) { struct cgroup *cgrp; - cgrp = scx_bpf_task_cgroup(p); + cgrp = __COMPAT_scx_bpf_task_cgroup(p); update_active_weight_sums(cgrp, true); bpf_cgroup_release(cgrp); } @@ -522,7 +524,7 @@ void BPF_STRUCT_OPS(fcg_running, struct task_struct *p) if (fifo_sched) return; - cgrp = scx_bpf_task_cgroup(p); + cgrp = __COMPAT_scx_bpf_task_cgroup(p); cgc = find_cgrp_ctx(cgrp); if (cgc) { /* @@ -565,7 +567,7 @@ void BPF_STRUCT_OPS(fcg_stopping, struct task_struct *p, bool runnable) if (!taskc->bypassed_at) return; - cgrp = scx_bpf_task_cgroup(p); + cgrp = __COMPAT_scx_bpf_task_cgroup(p); cgc = find_cgrp_ctx(cgrp); if (cgc) { __sync_fetch_and_add(&cgc->cvtime_delta, @@ -579,7 +581,7 @@ void BPF_STRUCT_OPS(fcg_quiescent, struct task_struct *p, u64 deq_flags) { struct cgroup *cgrp; - cgrp = scx_bpf_task_cgroup(p); + cgrp = __COMPAT_scx_bpf_task_cgroup(p); update_active_weight_sums(cgrp, false); bpf_cgroup_release(cgrp); } @@ -781,7 +783,7 @@ void BPF_STRUCT_OPS(fcg_dispatch, s32 cpu, struct task_struct *prev) pick_next_cgroup: cpuc->cur_at = now; - if (scx_bpf_consume(SCX_DSQ_GLOBAL)) { + if (scx_bpf_consume(FALLBACK_DSQ)) { cpuc->cur_cgid = 0; return; } @@ -838,7 +840,7 @@ int BPF_STRUCT_OPS_SLEEPABLE(fcg_cgroup_init, struct cgroup *cgrp, int ret; /* - * Technically incorrect as cgroup ID is full 64bit while dq ID is + * Technically incorrect as cgroup ID is full 64bit while dsq ID is * 63bit. Should not be a problem in practice and easy to spot in the * unlikely case that it breaks. */ @@ -926,6 +928,11 @@ void BPF_STRUCT_OPS(fcg_cgroup_move, struct task_struct *p, p->scx.dsq_vtime = to_cgc->tvtime_now + vtime_delta; } +s32 BPF_STRUCT_OPS_SLEEPABLE(fcg_init) +{ + return scx_bpf_create_dsq(FALLBACK_DSQ, -1); +} + void BPF_STRUCT_OPS(fcg_exit, struct scx_exit_info *ei) { UEI_RECORD(uei, ei); @@ -944,6 +951,7 @@ SCX_OPS_DEFINE(flatcg_ops, .cgroup_init = (void *)fcg_cgroup_init, .cgroup_exit = (void *)fcg_cgroup_exit, .cgroup_move = (void *)fcg_cgroup_move, + .init = (void *)fcg_init, .exit = (void *)fcg_exit, .flags = SCX_OPS_HAS_CGROUP_WEIGHT | SCX_OPS_ENQ_EXITING, .name = "flatcg"); diff --git a/tools/sched_ext/scx_qmap.bpf.c b/tools/sched_ext/scx_qmap.bpf.c index 83c8f54c1e31..67e2a7968cc9 100644 --- a/tools/sched_ext/scx_qmap.bpf.c +++ b/tools/sched_ext/scx_qmap.bpf.c @@ -318,11 +318,11 @@ static bool dispatch_highpri(bool from_timer) if (tctx->highpri) { /* exercise the set_*() and vtime interface too */ - scx_bpf_dispatch_from_dsq_set_slice( + __COMPAT_scx_bpf_dispatch_from_dsq_set_slice( BPF_FOR_EACH_ITER, slice_ns * 2); - scx_bpf_dispatch_from_dsq_set_vtime( + __COMPAT_scx_bpf_dispatch_from_dsq_set_vtime( BPF_FOR_EACH_ITER, highpri_seq++); - scx_bpf_dispatch_vtime_from_dsq( + __COMPAT_scx_bpf_dispatch_vtime_from_dsq( BPF_FOR_EACH_ITER, p, HIGHPRI_DSQ, 0); } } @@ -340,9 +340,9 @@ static bool dispatch_highpri(bool from_timer) else cpu = scx_bpf_pick_any_cpu(p->cpus_ptr, 0); - if (scx_bpf_dispatch_from_dsq(BPF_FOR_EACH_ITER, p, - SCX_DSQ_LOCAL_ON | cpu, - SCX_ENQ_PREEMPT)) { + if (__COMPAT_scx_bpf_dispatch_from_dsq(BPF_FOR_EACH_ITER, p, + SCX_DSQ_LOCAL_ON | cpu, + SCX_ENQ_PREEMPT)) { if (cpu == this_cpu) { dispatched = true; __sync_fetch_and_add(&nr_expedited_local, 1); diff --git a/tools/testing/cxl/Kbuild b/tools/testing/cxl/Kbuild index 3d1ca9e38b1f..b1256fee3567 100644 --- a/tools/testing/cxl/Kbuild +++ b/tools/testing/cxl/Kbuild @@ -14,7 +14,7 @@ ldflags-y += --wrap=cxl_dvsec_rr_decode ldflags-y += --wrap=devm_cxl_add_rch_dport ldflags-y += --wrap=cxl_rcd_component_reg_phys ldflags-y += --wrap=cxl_endpoint_parse_cdat -ldflags-y += --wrap=cxl_setup_parent_dport +ldflags-y += --wrap=cxl_dport_init_ras_reporting DRIVERS := ../../../drivers CXL_SRC := $(DRIVERS)/cxl diff --git a/tools/testing/cxl/mock_acpi.c b/tools/testing/cxl/mock_acpi.c index 55813de26d46..8da94378ccec 100644 --- a/tools/testing/cxl/mock_acpi.c +++ b/tools/testing/cxl/mock_acpi.c @@ -18,7 +18,7 @@ struct acpi_device *to_cxl_host_bridge(struct device *host, struct device *dev) goto out; } - if (dev->bus == &platform_bus_type) + if (dev_is_platform(dev)) goto out; adev = to_acpi_device(dev); diff --git a/tools/testing/cxl/test/mem.c b/tools/testing/cxl/test/mem.c index 129f179b0ac5..ad5c4c18c5c6 100644 --- a/tools/testing/cxl/test/mem.c +++ b/tools/testing/cxl/test/mem.c @@ -8,7 +8,8 @@ #include <linux/delay.h> #include <linux/sizes.h> #include <linux/bits.h> -#include <asm/unaligned.h> +#include <cxl/mailbox.h> +#include <linux/unaligned.h> #include <crypto/sha2.h> #include <cxlmem.h> @@ -534,6 +535,7 @@ static int mock_gsl(struct cxl_mbox_cmd *cmd) static int mock_get_log(struct cxl_memdev_state *mds, struct cxl_mbox_cmd *cmd) { + struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox; struct cxl_mbox_get_log *gl = cmd->payload_in; u32 offset = le32_to_cpu(gl->offset); u32 length = le32_to_cpu(gl->length); @@ -542,7 +544,7 @@ static int mock_get_log(struct cxl_memdev_state *mds, struct cxl_mbox_cmd *cmd) if (cmd->size_in < sizeof(*gl)) return -EINVAL; - if (length > mds->payload_size) + if (length > cxl_mbox->payload_size) return -EINVAL; if (offset + length > sizeof(mock_cel)) return -EINVAL; @@ -617,12 +619,13 @@ void cxl_mockmem_sanitize_work(struct work_struct *work) { struct cxl_memdev_state *mds = container_of(work, typeof(*mds), security.poll_dwork.work); + struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox; - mutex_lock(&mds->mbox_mutex); + mutex_lock(&cxl_mbox->mbox_mutex); if (mds->security.sanitize_node) sysfs_notify_dirent(mds->security.sanitize_node); mds->security.sanitize_active = false; - mutex_unlock(&mds->mbox_mutex); + mutex_unlock(&cxl_mbox->mbox_mutex); dev_dbg(mds->cxlds.dev, "sanitize complete\n"); } @@ -631,6 +634,7 @@ static int mock_sanitize(struct cxl_mockmem_data *mdata, struct cxl_mbox_cmd *cmd) { struct cxl_memdev_state *mds = mdata->mds; + struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox; int rc = 0; if (cmd->size_in != 0) @@ -648,14 +652,14 @@ static int mock_sanitize(struct cxl_mockmem_data *mdata, return -ENXIO; } - mutex_lock(&mds->mbox_mutex); + mutex_lock(&cxl_mbox->mbox_mutex); if (schedule_delayed_work(&mds->security.poll_dwork, msecs_to_jiffies(mdata->sanitize_timeout))) { mds->security.sanitize_active = true; dev_dbg(mds->cxlds.dev, "sanitize issued\n"); } else rc = -EBUSY; - mutex_unlock(&mds->mbox_mutex); + mutex_unlock(&cxl_mbox->mbox_mutex); return rc; } @@ -1333,12 +1337,13 @@ static int mock_activate_fw(struct cxl_mockmem_data *mdata, return -EINVAL; } -static int cxl_mock_mbox_send(struct cxl_memdev_state *mds, +static int cxl_mock_mbox_send(struct cxl_mailbox *cxl_mbox, struct cxl_mbox_cmd *cmd) { - struct cxl_dev_state *cxlds = &mds->cxlds; - struct device *dev = cxlds->dev; + struct device *dev = cxl_mbox->host; struct cxl_mockmem_data *mdata = dev_get_drvdata(dev); + struct cxl_memdev_state *mds = mdata->mds; + struct cxl_dev_state *cxlds = &mds->cxlds; int rc = -EIO; switch (cmd->opcode) { @@ -1453,6 +1458,17 @@ static ssize_t event_trigger_store(struct device *dev, } static DEVICE_ATTR_WO(event_trigger); +static int cxl_mock_mailbox_create(struct cxl_dev_state *cxlds) +{ + int rc; + + rc = cxl_mailbox_init(&cxlds->cxl_mbox, cxlds->dev); + if (rc) + return rc; + + return 0; +} + static int cxl_mock_mem_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -1460,6 +1476,7 @@ static int cxl_mock_mem_probe(struct platform_device *pdev) struct cxl_memdev_state *mds; struct cxl_dev_state *cxlds; struct cxl_mockmem_data *mdata; + struct cxl_mailbox *cxl_mbox; int rc; mdata = devm_kzalloc(dev, sizeof(*mdata), GFP_KERNEL); @@ -1487,13 +1504,18 @@ static int cxl_mock_mem_probe(struct platform_device *pdev) if (IS_ERR(mds)) return PTR_ERR(mds); + cxlds = &mds->cxlds; + rc = cxl_mock_mailbox_create(cxlds); + if (rc) + return rc; + + cxl_mbox = &mds->cxlds.cxl_mbox; mdata->mds = mds; - mds->mbox_send = cxl_mock_mbox_send; - mds->payload_size = SZ_4K; + cxl_mbox->mbox_send = cxl_mock_mbox_send; + cxl_mbox->payload_size = SZ_4K; mds->event.buf = (struct cxl_get_event_payload *) mdata->event_buf; INIT_DELAYED_WORK(&mds->security.poll_dwork, cxl_mockmem_sanitize_work); - cxlds = &mds->cxlds; cxlds->serial = pdev->id; if (is_rcd(pdev)) cxlds->rcd = true; diff --git a/tools/testing/cxl/test/mock.c b/tools/testing/cxl/test/mock.c index d619672faa49..f4ce96cc11d4 100644 --- a/tools/testing/cxl/test/mock.c +++ b/tools/testing/cxl/test/mock.c @@ -228,7 +228,7 @@ int __wrap_cxl_hdm_decode_init(struct cxl_dev_state *cxlds, } EXPORT_SYMBOL_NS_GPL(__wrap_cxl_hdm_decode_init, CXL); -int __wrap_cxl_dvsec_rr_decode(struct device *dev, int dvsec, +int __wrap_cxl_dvsec_rr_decode(struct device *dev, struct cxl_port *port, struct cxl_endpoint_dvsec_info *info) { int rc = 0, index; @@ -237,7 +237,7 @@ int __wrap_cxl_dvsec_rr_decode(struct device *dev, int dvsec, if (ops && ops->is_mock_dev(dev)) rc = 0; else - rc = cxl_dvsec_rr_decode(dev, dvsec, info); + rc = cxl_dvsec_rr_decode(dev, port, info); put_cxl_mock_ops(index); return rc; @@ -299,17 +299,17 @@ void __wrap_cxl_endpoint_parse_cdat(struct cxl_port *port) } EXPORT_SYMBOL_NS_GPL(__wrap_cxl_endpoint_parse_cdat, CXL); -void __wrap_cxl_setup_parent_dport(struct device *host, struct cxl_dport *dport) +void __wrap_cxl_dport_init_ras_reporting(struct cxl_dport *dport, struct device *host) { int index; struct cxl_mock_ops *ops = get_cxl_mock_ops(&index); if (!ops || !ops->is_mock_port(dport->dport_dev)) - cxl_setup_parent_dport(host, dport); + cxl_dport_init_ras_reporting(dport, host); put_cxl_mock_ops(index); } -EXPORT_SYMBOL_NS_GPL(__wrap_cxl_setup_parent_dport, CXL); +EXPORT_SYMBOL_NS_GPL(__wrap_cxl_dport_init_ras_reporting, CXL); MODULE_LICENSE("GPL v2"); MODULE_IMPORT_NS(ACPI); diff --git a/tools/testing/selftests/alsa/Makefile b/tools/testing/selftests/alsa/Makefile index 25be68025290..944279160fed 100644 --- a/tools/testing/selftests/alsa/Makefile +++ b/tools/testing/selftests/alsa/Makefile @@ -1,5 +1,9 @@ # SPDX-License-Identifier: GPL-2.0 # +ifneq ($(shell pkg-config --exists alsa && echo 0 || echo 1),0) +$(error Package alsa not found, please install alsa development package or \ + add directory containing `alsa.pc` in PKG_CONFIG_PATH) +endif CFLAGS += $(shell pkg-config --cflags alsa) $(KHDR_INCLUDES) LDLIBS += $(shell pkg-config --libs alsa) diff --git a/tools/testing/selftests/bpf/progs/test_tcp_custom_syncookie.h b/tools/testing/selftests/bpf/progs/test_tcp_custom_syncookie.h index f8b1b7e68d2e..34024de6337e 100644 --- a/tools/testing/selftests/bpf/progs/test_tcp_custom_syncookie.h +++ b/tools/testing/selftests/bpf/progs/test_tcp_custom_syncookie.h @@ -22,7 +22,7 @@ __builtin_memcpy(b, __tmp, sizeof(a)); \ } while (0) -/* asm-generic/unaligned.h */ +/* linux/unaligned.h */ #define __get_unaligned_t(type, ptr) ({ \ const struct { type x; } __packed * __pptr = (typeof(__pptr))(ptr); \ __pptr->x; \ diff --git a/tools/testing/selftests/breakpoints/step_after_suspend_test.c b/tools/testing/selftests/breakpoints/step_after_suspend_test.c index dfec31fb9b30..8d275f03e977 100644 --- a/tools/testing/selftests/breakpoints/step_after_suspend_test.c +++ b/tools/testing/selftests/breakpoints/step_after_suspend_test.c @@ -152,7 +152,10 @@ void suspend(void) if (err < 0) ksft_exit_fail_msg("timerfd_settime() failed\n"); - if (write(power_state_fd, "mem", strlen("mem")) != strlen("mem")) + system("(echo mem > /sys/power/state) 2> /dev/null"); + + timerfd_gettime(timerfd, &spec); + if (spec.it_value.tv_sec != 0 || spec.it_value.tv_nsec != 0) ksft_exit_fail_msg("Failed to enter Suspend state\n"); close(timerfd); diff --git a/tools/testing/selftests/clone3/clone3_cap_checkpoint_restore.c b/tools/testing/selftests/clone3/clone3_cap_checkpoint_restore.c index 31b56d625655..3c196fa86c99 100644 --- a/tools/testing/selftests/clone3/clone3_cap_checkpoint_restore.c +++ b/tools/testing/selftests/clone3/clone3_cap_checkpoint_restore.c @@ -27,8 +27,6 @@ #include "../kselftest_harness.h" #include "clone3_selftests.h" -#define MAX_PID_NS_LEVEL 32 - static void child_exit(int ret) { fflush(stdout); diff --git a/tools/testing/selftests/core/.gitignore b/tools/testing/selftests/core/.gitignore index 6e6712ce5817..7999361992aa 100644 --- a/tools/testing/selftests/core/.gitignore +++ b/tools/testing/selftests/core/.gitignore @@ -1 +1,2 @@ close_range_test +unshare_test diff --git a/tools/testing/selftests/devices/probe/test_discoverable_devices.py b/tools/testing/selftests/devices/probe/test_discoverable_devices.py index d94a74b8a054..d7a2bb91c807 100755 --- a/tools/testing/selftests/devices/probe/test_discoverable_devices.py +++ b/tools/testing/selftests/devices/probe/test_discoverable_devices.py @@ -45,7 +45,7 @@ def find_pci_controller_dirs(): def find_usb_controller_dirs(): - usb_controller_sysfs_dir = "usb[\d]+" + usb_controller_sysfs_dir = r"usb[\d]+" dir_regex = re.compile(usb_controller_sysfs_dir) for d in os.scandir(sysfs_usb_devices): @@ -91,7 +91,7 @@ def get_acpi_uid(sysfs_dev_dir): def get_usb_version(sysfs_dev_dir): - re_usb_version = re.compile("PRODUCT=.*/(\d)/.*") + re_usb_version = re.compile(r"PRODUCT=.*/(\d)/.*") with open(os.path.join(sysfs_dev_dir, "uevent")) as f: return int(re_usb_version.search(f.read()).group(1)) diff --git a/tools/testing/selftests/exec/.gitignore b/tools/testing/selftests/exec/.gitignore index 90c238ba6a4b..a0dc5d4bf733 100644 --- a/tools/testing/selftests/exec/.gitignore +++ b/tools/testing/selftests/exec/.gitignore @@ -9,7 +9,8 @@ execveat.ephemeral execveat.denatured non-regular null-argv -/load_address_* +/load_address.* +!load_address.c /recursion-depth xxxxxxxx* pipe diff --git a/tools/testing/selftests/hid/Makefile b/tools/testing/selftests/hid/Makefile index 72be55ac4bdf..38ae31bb07b5 100644 --- a/tools/testing/selftests/hid/Makefile +++ b/tools/testing/selftests/hid/Makefile @@ -17,6 +17,8 @@ TEST_PROGS += hid-tablet.sh TEST_PROGS += hid-usb_crash.sh TEST_PROGS += hid-wacom.sh +TEST_FILES := run-hid-tools-tests.sh + CXX ?= $(CROSS_COMPILE)g++ HOSTPKG_CONFIG := pkg-config diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore index 6d9381d60172..7f57abf936e7 100644 --- a/tools/testing/selftests/kvm/.gitignore +++ b/tools/testing/selftests/kvm/.gitignore @@ -5,3 +5,7 @@ !*.h !*.S !*.sh +!.gitignore +!config +!settings +!Makefile diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 0c4b254ab56b..960cf6a77198 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -130,6 +130,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/max_vcpuid_cap_test TEST_GEN_PROGS_x86_64 += x86_64/triple_fault_event_test TEST_GEN_PROGS_x86_64 += x86_64/recalc_apic_map_test TEST_GEN_PROGS_x86_64 += access_tracking_perf_test +TEST_GEN_PROGS_x86_64 += coalesced_io_test TEST_GEN_PROGS_x86_64 += demand_paging_test TEST_GEN_PROGS_x86_64 += dirty_log_test TEST_GEN_PROGS_x86_64 += dirty_log_perf_test @@ -167,6 +168,7 @@ TEST_GEN_PROGS_aarch64 += aarch64/vpmu_counter_access TEST_GEN_PROGS_aarch64 += aarch64/no-vgic-v3 TEST_GEN_PROGS_aarch64 += access_tracking_perf_test TEST_GEN_PROGS_aarch64 += arch_timer +TEST_GEN_PROGS_aarch64 += coalesced_io_test TEST_GEN_PROGS_aarch64 += demand_paging_test TEST_GEN_PROGS_aarch64 += dirty_log_test TEST_GEN_PROGS_aarch64 += dirty_log_perf_test @@ -188,6 +190,7 @@ TEST_GEN_PROGS_s390x += s390x/tprot TEST_GEN_PROGS_s390x += s390x/cmma_test TEST_GEN_PROGS_s390x += s390x/debug_test TEST_GEN_PROGS_s390x += s390x/shared_zeropage_test +TEST_GEN_PROGS_s390x += s390x/ucontrol_test TEST_GEN_PROGS_s390x += demand_paging_test TEST_GEN_PROGS_s390x += dirty_log_test TEST_GEN_PROGS_s390x += guest_print_test @@ -200,6 +203,7 @@ TEST_GEN_PROGS_s390x += kvm_binary_stats_test TEST_GEN_PROGS_riscv += riscv/sbi_pmu_test TEST_GEN_PROGS_riscv += riscv/ebreak_test TEST_GEN_PROGS_riscv += arch_timer +TEST_GEN_PROGS_riscv += coalesced_io_test TEST_GEN_PROGS_riscv += demand_paging_test TEST_GEN_PROGS_riscv += dirty_log_test TEST_GEN_PROGS_riscv += get-reg-list diff --git a/tools/testing/selftests/kvm/coalesced_io_test.c b/tools/testing/selftests/kvm/coalesced_io_test.c new file mode 100644 index 000000000000..60cb25454899 --- /dev/null +++ b/tools/testing/selftests/kvm/coalesced_io_test.c @@ -0,0 +1,236 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <signal.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/ioctl.h> + +#include <linux/sizes.h> + +#include <kvm_util.h> +#include <processor.h> + +#include "ucall_common.h" + +struct kvm_coalesced_io { + struct kvm_coalesced_mmio_ring *ring; + uint32_t ring_size; + uint64_t mmio_gpa; + uint64_t *mmio; + + /* + * x86-only, but define pio_port for all architectures to minimize the + * amount of #ifdeffery and complexity, without having to sacrifice + * verbose error messages. + */ + uint8_t pio_port; +}; + +static struct kvm_coalesced_io kvm_builtin_io_ring; + +#ifdef __x86_64__ +static const int has_pio = 1; +#else +static const int has_pio = 0; +#endif + +static void guest_code(struct kvm_coalesced_io *io) +{ + int i, j; + + for (;;) { + for (j = 0; j < 1 + has_pio; j++) { + /* + * KVM always leaves one free entry, i.e. exits to + * userspace before the last entry is filled. + */ + for (i = 0; i < io->ring_size - 1; i++) { +#ifdef __x86_64__ + if (i & 1) + outl(io->pio_port, io->pio_port + i); + else +#endif + WRITE_ONCE(*io->mmio, io->mmio_gpa + i); + } +#ifdef __x86_64__ + if (j & 1) + outl(io->pio_port, io->pio_port + i); + else +#endif + WRITE_ONCE(*io->mmio, io->mmio_gpa + i); + } + GUEST_SYNC(0); + + WRITE_ONCE(*io->mmio, io->mmio_gpa + i); +#ifdef __x86_64__ + outl(io->pio_port, io->pio_port + i); +#endif + } +} + +static void vcpu_run_and_verify_io_exit(struct kvm_vcpu *vcpu, + struct kvm_coalesced_io *io, + uint32_t ring_start, + uint32_t expected_exit) +{ + const bool want_pio = expected_exit == KVM_EXIT_IO; + struct kvm_coalesced_mmio_ring *ring = io->ring; + struct kvm_run *run = vcpu->run; + uint32_t pio_value; + + WRITE_ONCE(ring->first, ring_start); + WRITE_ONCE(ring->last, ring_start); + + vcpu_run(vcpu); + + /* + * Annoyingly, reading PIO data is safe only for PIO exits, otherwise + * data_offset is garbage, e.g. an MMIO gpa. + */ + if (run->exit_reason == KVM_EXIT_IO) + pio_value = *(uint32_t *)((void *)run + run->io.data_offset); + else + pio_value = 0; + + TEST_ASSERT((!want_pio && (run->exit_reason == KVM_EXIT_MMIO && run->mmio.is_write && + run->mmio.phys_addr == io->mmio_gpa && run->mmio.len == 8 && + *(uint64_t *)run->mmio.data == io->mmio_gpa + io->ring_size - 1)) || + (want_pio && (run->exit_reason == KVM_EXIT_IO && run->io.port == io->pio_port && + run->io.direction == KVM_EXIT_IO_OUT && run->io.count == 1 && + pio_value == io->pio_port + io->ring_size - 1)), + "For start = %u, expected exit on %u-byte %s write 0x%llx = %lx, got exit_reason = %u (%s)\n " + "(MMIO addr = 0x%llx, write = %u, len = %u, data = %lx)\n " + "(PIO port = 0x%x, write = %u, len = %u, count = %u, data = %x", + ring_start, want_pio ? 4 : 8, want_pio ? "PIO" : "MMIO", + want_pio ? (unsigned long long)io->pio_port : io->mmio_gpa, + (want_pio ? io->pio_port : io->mmio_gpa) + io->ring_size - 1, run->exit_reason, + run->exit_reason == KVM_EXIT_MMIO ? "MMIO" : run->exit_reason == KVM_EXIT_IO ? "PIO" : "other", + run->mmio.phys_addr, run->mmio.is_write, run->mmio.len, *(uint64_t *)run->mmio.data, + run->io.port, run->io.direction, run->io.size, run->io.count, pio_value); +} + +static void vcpu_run_and_verify_coalesced_io(struct kvm_vcpu *vcpu, + struct kvm_coalesced_io *io, + uint32_t ring_start, + uint32_t expected_exit) +{ + struct kvm_coalesced_mmio_ring *ring = io->ring; + int i; + + vcpu_run_and_verify_io_exit(vcpu, io, ring_start, expected_exit); + + TEST_ASSERT((ring->last + 1) % io->ring_size == ring->first, + "Expected ring to be full (minus 1), first = %u, last = %u, max = %u, start = %u", + ring->first, ring->last, io->ring_size, ring_start); + + for (i = 0; i < io->ring_size - 1; i++) { + uint32_t idx = (ring->first + i) % io->ring_size; + struct kvm_coalesced_mmio *entry = &ring->coalesced_mmio[idx]; + +#ifdef __x86_64__ + if (i & 1) + TEST_ASSERT(entry->phys_addr == io->pio_port && + entry->len == 4 && entry->pio && + *(uint32_t *)entry->data == io->pio_port + i, + "Wanted 4-byte port I/O 0x%x = 0x%x in entry %u, got %u-byte %s 0x%llx = 0x%x", + io->pio_port, io->pio_port + i, i, + entry->len, entry->pio ? "PIO" : "MMIO", + entry->phys_addr, *(uint32_t *)entry->data); + else +#endif + TEST_ASSERT(entry->phys_addr == io->mmio_gpa && + entry->len == 8 && !entry->pio, + "Wanted 8-byte MMIO to 0x%lx = %lx in entry %u, got %u-byte %s 0x%llx = 0x%lx", + io->mmio_gpa, io->mmio_gpa + i, i, + entry->len, entry->pio ? "PIO" : "MMIO", + entry->phys_addr, *(uint64_t *)entry->data); + } +} + +static void test_coalesced_io(struct kvm_vcpu *vcpu, + struct kvm_coalesced_io *io, uint32_t ring_start) +{ + struct kvm_coalesced_mmio_ring *ring = io->ring; + + kvm_vm_register_coalesced_io(vcpu->vm, io->mmio_gpa, 8, false /* pio */); +#ifdef __x86_64__ + kvm_vm_register_coalesced_io(vcpu->vm, io->pio_port, 8, true /* pio */); +#endif + + vcpu_run_and_verify_coalesced_io(vcpu, io, ring_start, KVM_EXIT_MMIO); +#ifdef __x86_64__ + vcpu_run_and_verify_coalesced_io(vcpu, io, ring_start, KVM_EXIT_IO); +#endif + + /* + * Verify ucall, which may use non-coalesced MMIO or PIO, generates an + * immediate exit. + */ + WRITE_ONCE(ring->first, ring_start); + WRITE_ONCE(ring->last, ring_start); + vcpu_run(vcpu); + TEST_ASSERT_EQ(get_ucall(vcpu, NULL), UCALL_SYNC); + TEST_ASSERT_EQ(ring->first, ring_start); + TEST_ASSERT_EQ(ring->last, ring_start); + + /* Verify that non-coalesced MMIO/PIO generates an exit to userspace. */ + kvm_vm_unregister_coalesced_io(vcpu->vm, io->mmio_gpa, 8, false /* pio */); + vcpu_run_and_verify_io_exit(vcpu, io, ring_start, KVM_EXIT_MMIO); + +#ifdef __x86_64__ + kvm_vm_unregister_coalesced_io(vcpu->vm, io->pio_port, 8, true /* pio */); + vcpu_run_and_verify_io_exit(vcpu, io, ring_start, KVM_EXIT_IO); +#endif +} + +int main(int argc, char *argv[]) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + int i; + + TEST_REQUIRE(kvm_has_cap(KVM_CAP_COALESCED_MMIO)); + +#ifdef __x86_64__ + TEST_REQUIRE(kvm_has_cap(KVM_CAP_COALESCED_PIO)); +#endif + + vm = vm_create_with_one_vcpu(&vcpu, guest_code); + + kvm_builtin_io_ring = (struct kvm_coalesced_io) { + /* + * The I/O ring is a kernel-allocated page whose address is + * relative to each vCPU's run page, with the page offset + * provided by KVM in the return of KVM_CAP_COALESCED_MMIO. + */ + .ring = (void *)vcpu->run + + (kvm_check_cap(KVM_CAP_COALESCED_MMIO) * getpagesize()), + + /* + * The size of the I/O ring is fixed, but KVM defines the sized + * based on the kernel's PAGE_SIZE. Thus, userspace must query + * the host's page size at runtime to compute the ring size. + */ + .ring_size = (getpagesize() - sizeof(struct kvm_coalesced_mmio_ring)) / + sizeof(struct kvm_coalesced_mmio), + + /* + * Arbitrary address+port (MMIO mustn't overlap memslots), with + * the MMIO GPA identity mapped in the guest. + */ + .mmio_gpa = 4ull * SZ_1G, + .mmio = (uint64_t *)(4ull * SZ_1G), + .pio_port = 0x80, + }; + + virt_map(vm, (uint64_t)kvm_builtin_io_ring.mmio, kvm_builtin_io_ring.mmio_gpa, 1); + + sync_global_to_guest(vm, kvm_builtin_io_ring); + vcpu_args_set(vcpu, 1, &kvm_builtin_io_ring); + + for (i = 0; i < kvm_builtin_io_ring.ring_size; i++) + test_coalesced_io(vcpu, &kvm_builtin_io_ring, i); + + kvm_vm_free(vm); + return 0; +} diff --git a/tools/testing/selftests/kvm/guest_print_test.c b/tools/testing/selftests/kvm/guest_print_test.c index 8092c2d0f5d6..bcf582852db9 100644 --- a/tools/testing/selftests/kvm/guest_print_test.c +++ b/tools/testing/selftests/kvm/guest_print_test.c @@ -107,6 +107,21 @@ static void ucall_abort(const char *assert_msg, const char *expected_assert_msg) expected_assert_msg, &assert_msg[offset]); } +/* + * Open code vcpu_run(), sans the UCALL_ABORT handling, so that intentional + * guest asserts guest can be verified instead of being reported as failures. + */ +static void do_vcpu_run(struct kvm_vcpu *vcpu) +{ + int r; + + do { + r = __vcpu_run(vcpu); + } while (r == -1 && errno == EINTR); + + TEST_ASSERT(!r, KVM_IOCTL_ERROR(KVM_RUN, r)); +} + static void run_test(struct kvm_vcpu *vcpu, const char *expected_printf, const char *expected_assert) { @@ -114,7 +129,7 @@ static void run_test(struct kvm_vcpu *vcpu, const char *expected_printf, struct ucall uc; while (1) { - vcpu_run(vcpu); + do_vcpu_run(vcpu); TEST_ASSERT(run->exit_reason == UCALL_EXIT_REASON, "Unexpected exit reason: %u (%s),", @@ -159,7 +174,7 @@ static void test_limits(void) vm = vm_create_with_one_vcpu(&vcpu, guest_code_limits); run = vcpu->run; - vcpu_run(vcpu); + do_vcpu_run(vcpu); TEST_ASSERT(run->exit_reason == UCALL_EXIT_REASON, "Unexpected exit reason: %u (%s),", diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h index 63c2aaae51f3..bc7c242480d6 100644 --- a/tools/testing/selftests/kvm/include/kvm_util.h +++ b/tools/testing/selftests/kvm/include/kvm_util.h @@ -428,8 +428,6 @@ const char *vm_guest_mode_string(uint32_t i); void kvm_vm_free(struct kvm_vm *vmp); void kvm_vm_restart(struct kvm_vm *vmp); void kvm_vm_release(struct kvm_vm *vmp); -int kvm_memcmp_hva_gva(void *hva, struct kvm_vm *vm, const vm_vaddr_t gva, - size_t len); void kvm_vm_elf_load(struct kvm_vm *vm, const char *filename); int kvm_memfd_alloc(size_t size, bool hugepages); @@ -460,6 +458,32 @@ static inline uint32_t kvm_vm_reset_dirty_ring(struct kvm_vm *vm) return __vm_ioctl(vm, KVM_RESET_DIRTY_RINGS, NULL); } +static inline void kvm_vm_register_coalesced_io(struct kvm_vm *vm, + uint64_t address, + uint64_t size, bool pio) +{ + struct kvm_coalesced_mmio_zone zone = { + .addr = address, + .size = size, + .pio = pio, + }; + + vm_ioctl(vm, KVM_REGISTER_COALESCED_MMIO, &zone); +} + +static inline void kvm_vm_unregister_coalesced_io(struct kvm_vm *vm, + uint64_t address, + uint64_t size, bool pio) +{ + struct kvm_coalesced_mmio_zone zone = { + .addr = address, + .size = size, + .pio = pio, + }; + + vm_ioctl(vm, KVM_UNREGISTER_COALESCED_MMIO, &zone); +} + static inline int vm_get_stats_fd(struct kvm_vm *vm) { int fd = __vm_ioctl(vm, KVM_GET_STATS_FD, NULL); diff --git a/tools/testing/selftests/kvm/include/s390x/debug_print.h b/tools/testing/selftests/kvm/include/s390x/debug_print.h new file mode 100644 index 000000000000..1bf275631cc6 --- /dev/null +++ b/tools/testing/selftests/kvm/include/s390x/debug_print.h @@ -0,0 +1,69 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Definition for kernel virtual machines on s390x + * + * Copyright IBM Corp. 2024 + * + * Authors: + * Christoph Schlameuss <schlameuss@linux.ibm.com> + */ + +#ifndef SELFTEST_KVM_DEBUG_PRINT_H +#define SELFTEST_KVM_DEBUG_PRINT_H + +#include "asm/ptrace.h" +#include "kvm_util.h" +#include "sie.h" + +static inline void print_hex_bytes(const char *name, u64 addr, size_t len) +{ + u64 pos; + + pr_debug("%s (%p)\n", name, (void *)addr); + pr_debug(" 0/0x00---------|"); + if (len > 8) + pr_debug(" 8/0x08---------|"); + if (len > 16) + pr_debug(" 16/0x10--------|"); + if (len > 24) + pr_debug(" 24/0x18--------|"); + for (pos = 0; pos < len; pos += 8) { + if ((pos % 32) == 0) + pr_debug("\n %3lu 0x%.3lx ", pos, pos); + pr_debug(" %16lx", *((u64 *)(addr + pos))); + } + pr_debug("\n"); +} + +static inline void print_hex(const char *name, u64 addr) +{ + print_hex_bytes(name, addr, 512); +} + +static inline void print_psw(struct kvm_run *run, struct kvm_s390_sie_block *sie_block) +{ + pr_debug("flags:0x%x psw:0x%.16llx:0x%.16llx exit:%u %s\n", + run->flags, + run->psw_mask, run->psw_addr, + run->exit_reason, exit_reason_str(run->exit_reason)); + pr_debug("sie_block psw:0x%.16llx:0x%.16llx\n", + sie_block->psw_mask, sie_block->psw_addr); +} + +static inline void print_run(struct kvm_run *run, struct kvm_s390_sie_block *sie_block) +{ + print_hex_bytes("run", (u64)run, 0x150); + print_hex("sie_block", (u64)sie_block); + print_psw(run, sie_block); +} + +static inline void print_regs(struct kvm_run *run) +{ + struct kvm_sync_regs *sync_regs = &run->s.regs; + + print_hex_bytes("GPRS", (u64)sync_regs->gprs, 8 * NUM_GPRS); + print_hex_bytes("ACRS", (u64)sync_regs->acrs, 4 * NUM_ACRS); + print_hex_bytes("CRS", (u64)sync_regs->crs, 8 * NUM_CRS); +} + +#endif /* SELFTEST_KVM_DEBUG_PRINT_H */ diff --git a/tools/testing/selftests/kvm/include/s390x/processor.h b/tools/testing/selftests/kvm/include/s390x/processor.h index 255c9b990f4c..481bd2fd6a32 100644 --- a/tools/testing/selftests/kvm/include/s390x/processor.h +++ b/tools/testing/selftests/kvm/include/s390x/processor.h @@ -21,6 +21,11 @@ #define PAGE_PROTECT 0x200 /* HW read-only bit */ #define PAGE_NOEXEC 0x100 /* HW no-execute bit */ +/* Page size definitions */ +#define PAGE_SHIFT 12 +#define PAGE_SIZE BIT_ULL(PAGE_SHIFT) +#define PAGE_MASK (~(PAGE_SIZE - 1)) + /* Is there a portable way to do this? */ static inline void cpu_relax(void) { diff --git a/tools/testing/selftests/kvm/include/s390x/sie.h b/tools/testing/selftests/kvm/include/s390x/sie.h new file mode 100644 index 000000000000..160acd4a1db9 --- /dev/null +++ b/tools/testing/selftests/kvm/include/s390x/sie.h @@ -0,0 +1,240 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Definition for kernel virtual machines on s390. + * + * Adapted copy of struct definition kvm_s390_sie_block from + * arch/s390/include/asm/kvm_host.h for use in userspace selftest programs. + * + * Copyright IBM Corp. 2008, 2024 + * + * Authors: + * Christoph Schlameuss <schlameuss@linux.ibm.com> + * Carsten Otte <cotte@de.ibm.com> + */ + +#ifndef SELFTEST_KVM_SIE_H +#define SELFTEST_KVM_SIE_H + +#include <linux/types.h> + +struct kvm_s390_sie_block { +#define CPUSTAT_STOPPED 0x80000000 +#define CPUSTAT_WAIT 0x10000000 +#define CPUSTAT_ECALL_PEND 0x08000000 +#define CPUSTAT_STOP_INT 0x04000000 +#define CPUSTAT_IO_INT 0x02000000 +#define CPUSTAT_EXT_INT 0x01000000 +#define CPUSTAT_RUNNING 0x00800000 +#define CPUSTAT_RETAINED 0x00400000 +#define CPUSTAT_TIMING_SUB 0x00020000 +#define CPUSTAT_SIE_SUB 0x00010000 +#define CPUSTAT_RRF 0x00008000 +#define CPUSTAT_SLSV 0x00004000 +#define CPUSTAT_SLSR 0x00002000 +#define CPUSTAT_ZARCH 0x00000800 +#define CPUSTAT_MCDS 0x00000100 +#define CPUSTAT_KSS 0x00000200 +#define CPUSTAT_SM 0x00000080 +#define CPUSTAT_IBS 0x00000040 +#define CPUSTAT_GED2 0x00000010 +#define CPUSTAT_G 0x00000008 +#define CPUSTAT_GED 0x00000004 +#define CPUSTAT_J 0x00000002 +#define CPUSTAT_P 0x00000001 + __u32 cpuflags; /* 0x0000 */ + __u32: 1; /* 0x0004 */ + __u32 prefix : 18; + __u32: 1; + __u32 ibc : 12; + __u8 reserved08[4]; /* 0x0008 */ +#define PROG_IN_SIE BIT(0) + __u32 prog0c; /* 0x000c */ + union { + __u8 reserved10[16]; /* 0x0010 */ + struct { + __u64 pv_handle_cpu; + __u64 pv_handle_config; + }; + }; +#define PROG_BLOCK_SIE BIT(0) +#define PROG_REQUEST BIT(1) + __u32 prog20; /* 0x0020 */ + __u8 reserved24[4]; /* 0x0024 */ + __u64 cputm; /* 0x0028 */ + __u64 ckc; /* 0x0030 */ + __u64 epoch; /* 0x0038 */ + __u32 svcc; /* 0x0040 */ +#define LCTL_CR0 0x8000 +#define LCTL_CR6 0x0200 +#define LCTL_CR9 0x0040 +#define LCTL_CR10 0x0020 +#define LCTL_CR11 0x0010 +#define LCTL_CR14 0x0002 + __u16 lctl; /* 0x0044 */ + __s16 icpua; /* 0x0046 */ +#define ICTL_OPEREXC 0x80000000 +#define ICTL_PINT 0x20000000 +#define ICTL_LPSW 0x00400000 +#define ICTL_STCTL 0x00040000 +#define ICTL_ISKE 0x00004000 +#define ICTL_SSKE 0x00002000 +#define ICTL_RRBE 0x00001000 +#define ICTL_TPROT 0x00000200 + __u32 ictl; /* 0x0048 */ +#define ECA_CEI 0x80000000 +#define ECA_IB 0x40000000 +#define ECA_SIGPI 0x10000000 +#define ECA_MVPGI 0x01000000 +#define ECA_AIV 0x00200000 +#define ECA_VX 0x00020000 +#define ECA_PROTEXCI 0x00002000 +#define ECA_APIE 0x00000008 +#define ECA_SII 0x00000001 + __u32 eca; /* 0x004c */ +#define ICPT_INST 0x04 +#define ICPT_PROGI 0x08 +#define ICPT_INSTPROGI 0x0C +#define ICPT_EXTREQ 0x10 +#define ICPT_EXTINT 0x14 +#define ICPT_IOREQ 0x18 +#define ICPT_WAIT 0x1c +#define ICPT_VALIDITY 0x20 +#define ICPT_STOP 0x28 +#define ICPT_OPEREXC 0x2C +#define ICPT_PARTEXEC 0x38 +#define ICPT_IOINST 0x40 +#define ICPT_KSS 0x5c +#define ICPT_MCHKREQ 0x60 +#define ICPT_INT_ENABLE 0x64 +#define ICPT_PV_INSTR 0x68 +#define ICPT_PV_NOTIFY 0x6c +#define ICPT_PV_PREF 0x70 + __u8 icptcode; /* 0x0050 */ + __u8 icptstatus; /* 0x0051 */ + __u16 ihcpu; /* 0x0052 */ + __u8 reserved54; /* 0x0054 */ +#define IICTL_CODE_NONE 0x00 +#define IICTL_CODE_MCHK 0x01 +#define IICTL_CODE_EXT 0x02 +#define IICTL_CODE_IO 0x03 +#define IICTL_CODE_RESTART 0x04 +#define IICTL_CODE_SPECIFICATION 0x10 +#define IICTL_CODE_OPERAND 0x11 + __u8 iictl; /* 0x0055 */ + __u16 ipa; /* 0x0056 */ + __u32 ipb; /* 0x0058 */ + __u32 scaoh; /* 0x005c */ +#define FPF_BPBC 0x20 + __u8 fpf; /* 0x0060 */ +#define ECB_GS 0x40 +#define ECB_TE 0x10 +#define ECB_SPECI 0x08 +#define ECB_SRSI 0x04 +#define ECB_HOSTPROTINT 0x02 +#define ECB_PTF 0x01 + __u8 ecb; /* 0x0061 */ +#define ECB2_CMMA 0x80 +#define ECB2_IEP 0x20 +#define ECB2_PFMFI 0x08 +#define ECB2_ESCA 0x04 +#define ECB2_ZPCI_LSI 0x02 + __u8 ecb2; /* 0x0062 */ +#define ECB3_AISI 0x20 +#define ECB3_AISII 0x10 +#define ECB3_DEA 0x08 +#define ECB3_AES 0x04 +#define ECB3_RI 0x01 + __u8 ecb3; /* 0x0063 */ +#define ESCA_SCAOL_MASK ~0x3fU + __u32 scaol; /* 0x0064 */ + __u8 sdf; /* 0x0068 */ + __u8 epdx; /* 0x0069 */ + __u8 cpnc; /* 0x006a */ + __u8 reserved6b; /* 0x006b */ + __u32 todpr; /* 0x006c */ +#define GISA_FORMAT1 0x00000001 + __u32 gd; /* 0x0070 */ + __u8 reserved74[12]; /* 0x0074 */ + __u64 mso; /* 0x0080 */ + __u64 msl; /* 0x0088 */ + __u64 psw_mask; /* 0x0090 */ + __u64 psw_addr; /* 0x0098 */ + __u64 gg14; /* 0x00a0 */ + __u64 gg15; /* 0x00a8 */ + __u8 reservedb0[8]; /* 0x00b0 */ +#define HPID_KVM 0x4 +#define HPID_VSIE 0x5 + __u8 hpid; /* 0x00b8 */ + __u8 reservedb9[7]; /* 0x00b9 */ + union { + struct { + __u32 eiparams; /* 0x00c0 */ + __u16 extcpuaddr; /* 0x00c4 */ + __u16 eic; /* 0x00c6 */ + }; + __u64 mcic; /* 0x00c0 */ + } __packed; + __u32 reservedc8; /* 0x00c8 */ + union { + struct { + __u16 pgmilc; /* 0x00cc */ + __u16 iprcc; /* 0x00ce */ + }; + __u32 edc; /* 0x00cc */ + } __packed; + union { + struct { + __u32 dxc; /* 0x00d0 */ + __u16 mcn; /* 0x00d4 */ + __u8 perc; /* 0x00d6 */ + __u8 peratmid; /* 0x00d7 */ + }; + __u64 faddr; /* 0x00d0 */ + } __packed; + __u64 peraddr; /* 0x00d8 */ + __u8 eai; /* 0x00e0 */ + __u8 peraid; /* 0x00e1 */ + __u8 oai; /* 0x00e2 */ + __u8 armid; /* 0x00e3 */ + __u8 reservede4[4]; /* 0x00e4 */ + union { + __u64 tecmc; /* 0x00e8 */ + struct { + __u16 subchannel_id; /* 0x00e8 */ + __u16 subchannel_nr; /* 0x00ea */ + __u32 io_int_parm; /* 0x00ec */ + __u32 io_int_word; /* 0x00f0 */ + }; + } __packed; + __u8 reservedf4[8]; /* 0x00f4 */ +#define CRYCB_FORMAT_MASK 0x00000003 +#define CRYCB_FORMAT0 0x00000000 +#define CRYCB_FORMAT1 0x00000001 +#define CRYCB_FORMAT2 0x00000003 + __u32 crycbd; /* 0x00fc */ + __u64 gcr[16]; /* 0x0100 */ + union { + __u64 gbea; /* 0x0180 */ + __u64 sidad; + }; + __u8 reserved188[8]; /* 0x0188 */ + __u64 sdnxo; /* 0x0190 */ + __u8 reserved198[8]; /* 0x0198 */ + __u32 fac; /* 0x01a0 */ + __u8 reserved1a4[20]; /* 0x01a4 */ + __u64 cbrlo; /* 0x01b8 */ + __u8 reserved1c0[8]; /* 0x01c0 */ +#define ECD_HOSTREGMGMT 0x20000000 +#define ECD_MEF 0x08000000 +#define ECD_ETOKENF 0x02000000 +#define ECD_ECC 0x00200000 + __u32 ecd; /* 0x01c8 */ + __u8 reserved1cc[18]; /* 0x01cc */ + __u64 pp; /* 0x01de */ + __u8 reserved1e6[2]; /* 0x01e6 */ + __u64 itdba; /* 0x01e8 */ + __u64 riccbd; /* 0x01f0 */ + __u64 gvrd; /* 0x01f8 */ +} __packed __aligned(512); + +#endif /* SELFTEST_KVM_SIE_H */ diff --git a/tools/testing/selftests/kvm/include/x86_64/apic.h b/tools/testing/selftests/kvm/include/x86_64/apic.h index 0f268b55fa06..51990094effd 100644 --- a/tools/testing/selftests/kvm/include/x86_64/apic.h +++ b/tools/testing/selftests/kvm/include/x86_64/apic.h @@ -11,6 +11,7 @@ #include <stdint.h> #include "processor.h" +#include "ucall_common.h" #define APIC_DEFAULT_GPA 0xfee00000ULL @@ -93,9 +94,27 @@ static inline uint64_t x2apic_read_reg(unsigned int reg) return rdmsr(APIC_BASE_MSR + (reg >> 4)); } +static inline uint8_t x2apic_write_reg_safe(unsigned int reg, uint64_t value) +{ + return wrmsr_safe(APIC_BASE_MSR + (reg >> 4), value); +} + static inline void x2apic_write_reg(unsigned int reg, uint64_t value) { - wrmsr(APIC_BASE_MSR + (reg >> 4), value); + uint8_t fault = x2apic_write_reg_safe(reg, value); + + __GUEST_ASSERT(!fault, "Unexpected fault 0x%x on WRMSR(%x) = %lx\n", + fault, APIC_BASE_MSR + (reg >> 4), value); } +static inline void x2apic_write_reg_fault(unsigned int reg, uint64_t value) +{ + uint8_t fault = x2apic_write_reg_safe(reg, value); + + __GUEST_ASSERT(fault == GP_VECTOR, + "Wanted #GP on WRMSR(%x) = %lx, got 0x%x\n", + APIC_BASE_MSR + (reg >> 4), value, fault); +} + + #endif /* SELFTEST_KVM_APIC_H */ diff --git a/tools/testing/selftests/kvm/include/x86_64/hyperv.h b/tools/testing/selftests/kvm/include/x86_64/hyperv.h index fa65b908b13e..6849e2552f1b 100644 --- a/tools/testing/selftests/kvm/include/x86_64/hyperv.h +++ b/tools/testing/selftests/kvm/include/x86_64/hyperv.h @@ -186,6 +186,18 @@ #define HV_X64_ENLIGHTENED_VMCS_RECOMMENDED \ KVM_X86_CPU_FEATURE(HYPERV_CPUID_ENLIGHTMENT_INFO, 0, EAX, 14) +/* HYPERV_CPUID_NESTED_FEATURES.EAX */ +#define HV_X64_NESTED_DIRECT_FLUSH \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_NESTED_FEATURES, 0, EAX, 17) +#define HV_X64_NESTED_GUEST_MAPPING_FLUSH \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_NESTED_FEATURES, 0, EAX, 18) +#define HV_X64_NESTED_MSR_BITMAP \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_NESTED_FEATURES, 0, EAX, 19) + +/* HYPERV_CPUID_NESTED_FEATURES.EBX */ +#define HV_X64_NESTED_EVMCS1_PERF_GLOBAL_CTRL \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_NESTED_FEATURES, 0, EBX, 0) + /* HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES.EAX */ #define HV_X64_SYNDBG_CAP_ALLOW_KERNEL_DEBUGGING \ KVM_X86_CPU_FEATURE(HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES, 0, EAX, 1) @@ -343,4 +355,10 @@ struct hyperv_test_pages *vcpu_alloc_hyperv_test_pages(struct kvm_vm *vm, /* HV_X64_MSR_TSC_INVARIANT_CONTROL bits */ #define HV_INVARIANT_TSC_EXPOSED BIT_ULL(0) +const struct kvm_cpuid2 *kvm_get_supported_hv_cpuid(void); +const struct kvm_cpuid2 *vcpu_get_supported_hv_cpuid(struct kvm_vcpu *vcpu); +void vcpu_set_hv_cpuid(struct kvm_vcpu *vcpu); + +bool kvm_hv_cpu_has(struct kvm_x86_cpu_feature feature); + #endif /* !SELFTEST_KVM_HYPERV_H */ diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h index a0c1440017bb..e247f99e0473 100644 --- a/tools/testing/selftests/kvm/include/x86_64/processor.h +++ b/tools/testing/selftests/kvm/include/x86_64/processor.h @@ -25,6 +25,10 @@ extern bool host_cpu_is_intel; extern bool host_cpu_is_amd; extern uint64_t guest_tsc_khz; +#ifndef MAX_NR_CPUID_ENTRIES +#define MAX_NR_CPUID_ENTRIES 100 +#endif + /* Forced emulation prefix, used to invoke the emulator unconditionally. */ #define KVM_FEP "ud2; .byte 'k', 'v', 'm';" @@ -908,8 +912,6 @@ static inline void vcpu_xcrs_set(struct kvm_vcpu *vcpu, struct kvm_xcrs *xcrs) const struct kvm_cpuid_entry2 *get_cpuid_entry(const struct kvm_cpuid2 *cpuid, uint32_t function, uint32_t index); const struct kvm_cpuid2 *kvm_get_supported_cpuid(void); -const struct kvm_cpuid2 *kvm_get_supported_hv_cpuid(void); -const struct kvm_cpuid2 *vcpu_get_supported_hv_cpuid(struct kvm_vcpu *vcpu); static inline uint32_t kvm_cpu_fms(void) { @@ -1009,7 +1011,6 @@ static inline struct kvm_cpuid2 *allocate_kvm_cpuid2(int nr_entries) } void vcpu_init_cpuid(struct kvm_vcpu *vcpu, const struct kvm_cpuid2 *cpuid); -void vcpu_set_hv_cpuid(struct kvm_vcpu *vcpu); static inline struct kvm_cpuid_entry2 *__vcpu_get_cpuid_entry(struct kvm_vcpu *vcpu, uint32_t function, diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index 56b170b725b3..a2b7df5f1d39 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -712,16 +712,13 @@ void kvm_vm_release(struct kvm_vm *vmp) } static void __vm_mem_region_delete(struct kvm_vm *vm, - struct userspace_mem_region *region, - bool unlink) + struct userspace_mem_region *region) { int ret; - if (unlink) { - rb_erase(®ion->gpa_node, &vm->regions.gpa_tree); - rb_erase(®ion->hva_node, &vm->regions.hva_tree); - hash_del(®ion->slot_node); - } + rb_erase(®ion->gpa_node, &vm->regions.gpa_tree); + rb_erase(®ion->hva_node, &vm->regions.hva_tree); + hash_del(®ion->slot_node); region->region.memory_size = 0; vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION2, ®ion->region); @@ -762,7 +759,7 @@ void kvm_vm_free(struct kvm_vm *vmp) /* Free userspace_mem_regions. */ hash_for_each_safe(vmp->regions.slot_hash, ctr, node, region, slot_node) - __vm_mem_region_delete(vmp, region, false); + __vm_mem_region_delete(vmp, region); /* Free sparsebit arrays. */ sparsebit_free(&vmp->vpages_valid); @@ -794,76 +791,6 @@ int kvm_memfd_alloc(size_t size, bool hugepages) return fd; } -/* - * Memory Compare, host virtual to guest virtual - * - * Input Args: - * hva - Starting host virtual address - * vm - Virtual Machine - * gva - Starting guest virtual address - * len - number of bytes to compare - * - * Output Args: None - * - * Input/Output Args: None - * - * Return: - * Returns 0 if the bytes starting at hva for a length of len - * are equal the guest virtual bytes starting at gva. Returns - * a value < 0, if bytes at hva are less than those at gva. - * Otherwise a value > 0 is returned. - * - * Compares the bytes starting at the host virtual address hva, for - * a length of len, to the guest bytes starting at the guest virtual - * address given by gva. - */ -int kvm_memcmp_hva_gva(void *hva, struct kvm_vm *vm, vm_vaddr_t gva, size_t len) -{ - size_t amt; - - /* - * Compare a batch of bytes until either a match is found - * or all the bytes have been compared. - */ - for (uintptr_t offset = 0; offset < len; offset += amt) { - uintptr_t ptr1 = (uintptr_t)hva + offset; - - /* - * Determine host address for guest virtual address - * at offset. - */ - uintptr_t ptr2 = (uintptr_t)addr_gva2hva(vm, gva + offset); - - /* - * Determine amount to compare on this pass. - * Don't allow the comparsion to cross a page boundary. - */ - amt = len - offset; - if ((ptr1 >> vm->page_shift) != ((ptr1 + amt) >> vm->page_shift)) - amt = vm->page_size - (ptr1 % vm->page_size); - if ((ptr2 >> vm->page_shift) != ((ptr2 + amt) >> vm->page_shift)) - amt = vm->page_size - (ptr2 % vm->page_size); - - assert((ptr1 >> vm->page_shift) == ((ptr1 + amt - 1) >> vm->page_shift)); - assert((ptr2 >> vm->page_shift) == ((ptr2 + amt - 1) >> vm->page_shift)); - - /* - * Perform the comparison. If there is a difference - * return that result to the caller, otherwise need - * to continue on looking for a mismatch. - */ - int ret = memcmp((void *)ptr1, (void *)ptr2, amt); - if (ret != 0) - return ret; - } - - /* - * No mismatch found. Let the caller know the two memory - * areas are equal. - */ - return 0; -} - static void vm_userspace_mem_region_gpa_insert(struct rb_root *gpa_tree, struct userspace_mem_region *region) { @@ -1270,7 +1197,7 @@ void vm_mem_region_move(struct kvm_vm *vm, uint32_t slot, uint64_t new_gpa) */ void vm_mem_region_delete(struct kvm_vm *vm, uint32_t slot) { - __vm_mem_region_delete(vm, memslot2region(vm, slot), true); + __vm_mem_region_delete(vm, memslot2region(vm, slot)); } void vm_guest_mem_fallocate(struct kvm_vm *vm, uint64_t base, uint64_t size, diff --git a/tools/testing/selftests/kvm/lib/s390x/processor.c b/tools/testing/selftests/kvm/lib/s390x/processor.c index 4ad4492eea1d..20cfe970e3e3 100644 --- a/tools/testing/selftests/kvm/lib/s390x/processor.c +++ b/tools/testing/selftests/kvm/lib/s390x/processor.c @@ -14,7 +14,7 @@ void virt_arch_pgd_alloc(struct kvm_vm *vm) { vm_paddr_t paddr; - TEST_ASSERT(vm->page_size == 4096, "Unsupported page size: 0x%x", + TEST_ASSERT(vm->page_size == PAGE_SIZE, "Unsupported page size: 0x%x", vm->page_size); if (vm->pgd_created) @@ -79,7 +79,7 @@ void virt_arch_pg_map(struct kvm_vm *vm, uint64_t gva, uint64_t gpa) } /* Fill in page table entry */ - idx = (gva >> 12) & 0x0ffu; /* page index */ + idx = (gva >> PAGE_SHIFT) & 0x0ffu; /* page index */ if (!(entry[idx] & PAGE_INVALID)) fprintf(stderr, "WARNING: PTE for gpa=0x%"PRIx64" already set!\n", gpa); @@ -91,7 +91,7 @@ vm_paddr_t addr_arch_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva) int ri, idx; uint64_t *entry; - TEST_ASSERT(vm->page_size == 4096, "Unsupported page size: 0x%x", + TEST_ASSERT(vm->page_size == PAGE_SIZE, "Unsupported page size: 0x%x", vm->page_size); entry = addr_gpa2hva(vm, vm->pgd); @@ -103,7 +103,7 @@ vm_paddr_t addr_arch_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva) entry = addr_gpa2hva(vm, entry[idx] & REGION_ENTRY_ORIGIN); } - idx = (gva >> 12) & 0x0ffu; /* page index */ + idx = (gva >> PAGE_SHIFT) & 0x0ffu; /* page index */ TEST_ASSERT(!(entry[idx] & PAGE_INVALID), "No page mapping for vm virtual address 0x%lx", gva); @@ -168,7 +168,7 @@ struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id) struct kvm_sregs sregs; struct kvm_vcpu *vcpu; - TEST_ASSERT(vm->page_size == 4096, "Unsupported page size: 0x%x", + TEST_ASSERT(vm->page_size == PAGE_SIZE, "Unsupported page size: 0x%x", vm->page_size); stack_vaddr = __vm_vaddr_alloc(vm, stack_size, diff --git a/tools/testing/selftests/kvm/lib/x86_64/hyperv.c b/tools/testing/selftests/kvm/lib/x86_64/hyperv.c index efb7e7a1354d..15bc8cd583aa 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/hyperv.c +++ b/tools/testing/selftests/kvm/lib/x86_64/hyperv.c @@ -8,6 +8,73 @@ #include "processor.h" #include "hyperv.h" +const struct kvm_cpuid2 *kvm_get_supported_hv_cpuid(void) +{ + static struct kvm_cpuid2 *cpuid; + int kvm_fd; + + if (cpuid) + return cpuid; + + cpuid = allocate_kvm_cpuid2(MAX_NR_CPUID_ENTRIES); + kvm_fd = open_kvm_dev_path_or_exit(); + + kvm_ioctl(kvm_fd, KVM_GET_SUPPORTED_HV_CPUID, cpuid); + + close(kvm_fd); + return cpuid; +} + +void vcpu_set_hv_cpuid(struct kvm_vcpu *vcpu) +{ + static struct kvm_cpuid2 *cpuid_full; + const struct kvm_cpuid2 *cpuid_sys, *cpuid_hv; + int i, nent = 0; + + if (!cpuid_full) { + cpuid_sys = kvm_get_supported_cpuid(); + cpuid_hv = kvm_get_supported_hv_cpuid(); + + cpuid_full = allocate_kvm_cpuid2(cpuid_sys->nent + cpuid_hv->nent); + if (!cpuid_full) { + perror("malloc"); + abort(); + } + + /* Need to skip KVM CPUID leaves 0x400000xx */ + for (i = 0; i < cpuid_sys->nent; i++) { + if (cpuid_sys->entries[i].function >= 0x40000000 && + cpuid_sys->entries[i].function < 0x40000100) + continue; + cpuid_full->entries[nent] = cpuid_sys->entries[i]; + nent++; + } + + memcpy(&cpuid_full->entries[nent], cpuid_hv->entries, + cpuid_hv->nent * sizeof(struct kvm_cpuid_entry2)); + cpuid_full->nent = nent + cpuid_hv->nent; + } + + vcpu_init_cpuid(vcpu, cpuid_full); +} + +const struct kvm_cpuid2 *vcpu_get_supported_hv_cpuid(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid2 *cpuid = allocate_kvm_cpuid2(MAX_NR_CPUID_ENTRIES); + + vcpu_ioctl(vcpu, KVM_GET_SUPPORTED_HV_CPUID, cpuid); + + return cpuid; +} + +bool kvm_hv_cpu_has(struct kvm_x86_cpu_feature feature) +{ + if (!kvm_has_cap(KVM_CAP_SYS_HYPERV_CPUID)) + return false; + + return kvm_cpuid_has(kvm_get_supported_hv_cpuid(), feature); +} + struct hyperv_test_pages *vcpu_alloc_hyperv_test_pages(struct kvm_vm *vm, vm_vaddr_t *p_hv_pages_gva) { diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index 153739f2e201..974bcd2df6d7 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c @@ -19,8 +19,6 @@ #define KERNEL_DS 0x10 #define KERNEL_TSS 0x18 -#define MAX_NR_CPUID_ENTRIES 100 - vm_vaddr_t exception_handlers; bool host_cpu_is_amd; bool host_cpu_is_intel; @@ -566,10 +564,8 @@ void route_exception(struct ex_regs *regs) if (kvm_fixup_exception(regs)) return; - ucall_assert(UCALL_UNHANDLED, - "Unhandled exception in guest", __FILE__, __LINE__, - "Unhandled exception '0x%lx' at guest RIP '0x%lx'", - regs->vector, regs->rip); + GUEST_FAIL("Unhandled exception '0x%lx' at guest RIP '0x%lx'", + regs->vector, regs->rip); } static void vm_init_descriptor_tables(struct kvm_vm *vm) @@ -611,7 +607,7 @@ void assert_on_unhandled_exception(struct kvm_vcpu *vcpu) { struct ucall uc; - if (get_ucall(vcpu, &uc) == UCALL_UNHANDLED) + if (get_ucall(vcpu, &uc) == UCALL_ABORT) REPORT_GUEST_ASSERT(uc); } @@ -1195,65 +1191,6 @@ void xen_hypercall(uint64_t nr, uint64_t a0, void *a1) GUEST_ASSERT(!__xen_hypercall(nr, a0, a1)); } -const struct kvm_cpuid2 *kvm_get_supported_hv_cpuid(void) -{ - static struct kvm_cpuid2 *cpuid; - int kvm_fd; - - if (cpuid) - return cpuid; - - cpuid = allocate_kvm_cpuid2(MAX_NR_CPUID_ENTRIES); - kvm_fd = open_kvm_dev_path_or_exit(); - - kvm_ioctl(kvm_fd, KVM_GET_SUPPORTED_HV_CPUID, cpuid); - - close(kvm_fd); - return cpuid; -} - -void vcpu_set_hv_cpuid(struct kvm_vcpu *vcpu) -{ - static struct kvm_cpuid2 *cpuid_full; - const struct kvm_cpuid2 *cpuid_sys, *cpuid_hv; - int i, nent = 0; - - if (!cpuid_full) { - cpuid_sys = kvm_get_supported_cpuid(); - cpuid_hv = kvm_get_supported_hv_cpuid(); - - cpuid_full = allocate_kvm_cpuid2(cpuid_sys->nent + cpuid_hv->nent); - if (!cpuid_full) { - perror("malloc"); - abort(); - } - - /* Need to skip KVM CPUID leaves 0x400000xx */ - for (i = 0; i < cpuid_sys->nent; i++) { - if (cpuid_sys->entries[i].function >= 0x40000000 && - cpuid_sys->entries[i].function < 0x40000100) - continue; - cpuid_full->entries[nent] = cpuid_sys->entries[i]; - nent++; - } - - memcpy(&cpuid_full->entries[nent], cpuid_hv->entries, - cpuid_hv->nent * sizeof(struct kvm_cpuid_entry2)); - cpuid_full->nent = nent + cpuid_hv->nent; - } - - vcpu_init_cpuid(vcpu, cpuid_full); -} - -const struct kvm_cpuid2 *vcpu_get_supported_hv_cpuid(struct kvm_vcpu *vcpu) -{ - struct kvm_cpuid2 *cpuid = allocate_kvm_cpuid2(MAX_NR_CPUID_ENTRIES); - - vcpu_ioctl(vcpu, KVM_GET_SUPPORTED_HV_CPUID, cpuid); - - return cpuid; -} - unsigned long vm_compute_max_gfn(struct kvm_vm *vm) { const unsigned long num_ht_pages = 12 << (30 - vm->page_shift); /* 12 GiB */ diff --git a/tools/testing/selftests/kvm/memslot_modification_stress_test.c b/tools/testing/selftests/kvm/memslot_modification_stress_test.c index 49f162573126..c81a84990eab 100644 --- a/tools/testing/selftests/kvm/memslot_modification_stress_test.c +++ b/tools/testing/selftests/kvm/memslot_modification_stress_test.c @@ -79,6 +79,7 @@ struct test_params { useconds_t delay; uint64_t nr_iterations; bool partition_vcpu_memory_access; + bool disable_slot_zap_quirk; }; static void run_test(enum vm_guest_mode mode, void *arg) @@ -89,6 +90,13 @@ static void run_test(enum vm_guest_mode mode, void *arg) vm = memstress_create_vm(mode, nr_vcpus, guest_percpu_mem_size, 1, VM_MEM_SRC_ANONYMOUS, p->partition_vcpu_memory_access); +#ifdef __x86_64__ + if (p->disable_slot_zap_quirk) + vm_enable_cap(vm, KVM_CAP_DISABLE_QUIRKS2, KVM_X86_QUIRK_SLOT_ZAP_ALL); + + pr_info("Memslot zap quirk %s\n", p->disable_slot_zap_quirk ? + "disabled" : "enabled"); +#endif pr_info("Finished creating vCPUs\n"); @@ -107,11 +115,12 @@ static void run_test(enum vm_guest_mode mode, void *arg) static void help(char *name) { puts(""); - printf("usage: %s [-h] [-m mode] [-d delay_usec]\n" + printf("usage: %s [-h] [-m mode] [-d delay_usec] [-q]\n" " [-b memory] [-v vcpus] [-o] [-i iterations]\n", name); guest_modes_help(); printf(" -d: add a delay between each iteration of adding and\n" " deleting a memslot in usec.\n"); + printf(" -q: Disable memslot zap quirk.\n"); printf(" -b: specify the size of the memory region which should be\n" " accessed by each vCPU. e.g. 10M or 3G.\n" " Default: 1G\n"); @@ -137,7 +146,7 @@ int main(int argc, char *argv[]) guest_modes_append_default(); - while ((opt = getopt(argc, argv, "hm:d:b:v:oi:")) != -1) { + while ((opt = getopt(argc, argv, "hm:d:qb:v:oi:")) != -1) { switch (opt) { case 'm': guest_modes_cmdline(optarg); @@ -160,6 +169,14 @@ int main(int argc, char *argv[]) case 'i': p.nr_iterations = atoi_positive("Number of iterations", optarg); break; +#ifdef __x86_64__ + case 'q': + p.disable_slot_zap_quirk = true; + + TEST_REQUIRE(kvm_check_cap(KVM_CAP_DISABLE_QUIRKS2) & + KVM_X86_QUIRK_SLOT_ZAP_ALL); + break; +#endif case 'h': default: help(argv[0]); diff --git a/tools/testing/selftests/kvm/memslot_perf_test.c b/tools/testing/selftests/kvm/memslot_perf_test.c index 579a64f97333..989ffe0d047f 100644 --- a/tools/testing/selftests/kvm/memslot_perf_test.c +++ b/tools/testing/selftests/kvm/memslot_perf_test.c @@ -113,6 +113,9 @@ static_assert(ATOMIC_BOOL_LOCK_FREE == 2, "atomic bool is not lockless"); static sem_t vcpu_ready; static bool map_unmap_verify; +#ifdef __x86_64__ +static bool disable_slot_zap_quirk; +#endif static bool verbose; #define pr_info_v(...) \ @@ -578,6 +581,11 @@ static bool test_memslot_move_prepare(struct vm_data *data, uint32_t guest_page_size = data->vm->page_size; uint64_t movesrcgpa, movetestgpa; +#ifdef __x86_64__ + if (disable_slot_zap_quirk) + vm_enable_cap(data->vm, KVM_CAP_DISABLE_QUIRKS2, KVM_X86_QUIRK_SLOT_ZAP_ALL); +#endif + movesrcgpa = vm_slot2gpa(data, data->nslots - 1); if (isactive) { @@ -896,6 +904,7 @@ static void help(char *name, struct test_args *targs) pr_info(" -h: print this help screen.\n"); pr_info(" -v: enable verbose mode (not for benchmarking).\n"); pr_info(" -d: enable extra debug checks.\n"); + pr_info(" -q: Disable memslot zap quirk during memslot move.\n"); pr_info(" -s: specify memslot count cap (-1 means no cap; currently: %i)\n", targs->nslots); pr_info(" -f: specify the first test to run (currently: %i; max %zu)\n", @@ -954,7 +963,7 @@ static bool parse_args(int argc, char *argv[], uint32_t max_mem_slots; int opt; - while ((opt = getopt(argc, argv, "hvds:f:e:l:r:")) != -1) { + while ((opt = getopt(argc, argv, "hvdqs:f:e:l:r:")) != -1) { switch (opt) { case 'h': default: @@ -966,6 +975,13 @@ static bool parse_args(int argc, char *argv[], case 'd': map_unmap_verify = true; break; +#ifdef __x86_64__ + case 'q': + disable_slot_zap_quirk = true; + TEST_REQUIRE(kvm_check_cap(KVM_CAP_DISABLE_QUIRKS2) & + KVM_X86_QUIRK_SLOT_ZAP_ALL); + break; +#endif case 's': targs->nslots = atoi_paranoid(optarg); if (targs->nslots <= 1 && targs->nslots != -1) { diff --git a/tools/testing/selftests/kvm/s390x/cmma_test.c b/tools/testing/selftests/kvm/s390x/cmma_test.c index b39033844756..e32dd59703a0 100644 --- a/tools/testing/selftests/kvm/s390x/cmma_test.c +++ b/tools/testing/selftests/kvm/s390x/cmma_test.c @@ -17,16 +17,17 @@ #include "kvm_util.h" #include "kselftest.h" #include "ucall_common.h" +#include "processor.h" #define MAIN_PAGE_COUNT 512 #define TEST_DATA_PAGE_COUNT 512 #define TEST_DATA_MEMSLOT 1 -#define TEST_DATA_START_GFN 4096 +#define TEST_DATA_START_GFN PAGE_SIZE #define TEST_DATA_TWO_PAGE_COUNT 256 #define TEST_DATA_TWO_MEMSLOT 2 -#define TEST_DATA_TWO_START_GFN 8192 +#define TEST_DATA_TWO_START_GFN (2 * PAGE_SIZE) static char cmma_value_buf[MAIN_PAGE_COUNT + TEST_DATA_PAGE_COUNT]; @@ -66,7 +67,7 @@ static void guest_dirty_test_data(void) " lghi 5,%[page_count]\n" /* r5 += r1 */ "2: agfr 5,1\n" - /* r2 = r1 << 12 */ + /* r2 = r1 << PAGE_SHIFT */ "1: sllg 2,1,12(0)\n" /* essa(r4, r2, SET_STABLE) */ " .insn rrf,0xb9ab0000,4,2,1,0\n" diff --git a/tools/testing/selftests/kvm/s390x/config b/tools/testing/selftests/kvm/s390x/config new file mode 100644 index 000000000000..23270f2d679f --- /dev/null +++ b/tools/testing/selftests/kvm/s390x/config @@ -0,0 +1,2 @@ +CONFIG_KVM=y +CONFIG_KVM_S390_UCONTROL=y diff --git a/tools/testing/selftests/kvm/s390x/debug_test.c b/tools/testing/selftests/kvm/s390x/debug_test.c index 84313fb27529..ad8095968601 100644 --- a/tools/testing/selftests/kvm/s390x/debug_test.c +++ b/tools/testing/selftests/kvm/s390x/debug_test.c @@ -2,12 +2,12 @@ /* Test KVM debugging features. */ #include "kvm_util.h" #include "test_util.h" +#include "sie.h" #include <linux/kvm.h> #define __LC_SVC_NEW_PSW 0x1c0 #define __LC_PGM_NEW_PSW 0x1d0 -#define ICPT_INSTRUCTION 0x04 #define IPA0_DIAG 0x8300 #define PGM_SPECIFICATION 0x06 @@ -85,7 +85,7 @@ static void test_step_pgm_diag(void) vm = test_step_int_1(&vcpu, test_step_pgm_diag_guest_code, __LC_PGM_NEW_PSW, new_psw); TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_S390_SIEIC); - TEST_ASSERT_EQ(vcpu->run->s390_sieic.icptcode, ICPT_INSTRUCTION); + TEST_ASSERT_EQ(vcpu->run->s390_sieic.icptcode, ICPT_INST); TEST_ASSERT_EQ(vcpu->run->s390_sieic.ipa & 0xff00, IPA0_DIAG); vcpu_ioctl(vcpu, KVM_S390_IRQ, &irq); vcpu_run(vcpu); diff --git a/tools/testing/selftests/kvm/s390x/memop.c b/tools/testing/selftests/kvm/s390x/memop.c index f2df7416be84..4374b4cd2a80 100644 --- a/tools/testing/selftests/kvm/s390x/memop.c +++ b/tools/testing/selftests/kvm/s390x/memop.c @@ -16,6 +16,7 @@ #include "kvm_util.h" #include "kselftest.h" #include "ucall_common.h" +#include "processor.h" enum mop_target { LOGICAL, @@ -226,9 +227,6 @@ static void memop_ioctl(struct test_info info, struct kvm_s390_mem_op *ksmo, #define CHECK_N_DO(f, ...) ({ f(__VA_ARGS__, CHECK_ONLY); f(__VA_ARGS__); }) -#define PAGE_SHIFT 12 -#define PAGE_SIZE (1ULL << PAGE_SHIFT) -#define PAGE_MASK (~(PAGE_SIZE - 1)) #define CR0_FETCH_PROTECTION_OVERRIDE (1UL << (63 - 38)) #define CR0_STORAGE_PROTECTION_OVERRIDE (1UL << (63 - 39)) diff --git a/tools/testing/selftests/kvm/s390x/tprot.c b/tools/testing/selftests/kvm/s390x/tprot.c index 7a742a673b7c..12d5e1cb62e3 100644 --- a/tools/testing/selftests/kvm/s390x/tprot.c +++ b/tools/testing/selftests/kvm/s390x/tprot.c @@ -9,9 +9,8 @@ #include "kvm_util.h" #include "kselftest.h" #include "ucall_common.h" +#include "processor.h" -#define PAGE_SHIFT 12 -#define PAGE_SIZE (1 << PAGE_SHIFT) #define CR0_FETCH_PROTECTION_OVERRIDE (1UL << (63 - 38)) #define CR0_STORAGE_PROTECTION_OVERRIDE (1UL << (63 - 39)) @@ -151,7 +150,7 @@ static enum stage perform_next_stage(int *i, bool mapped_0) * instead. * In order to skip these tests we detect this inside the guest */ - skip = tests[*i].addr < (void *)4096 && + skip = tests[*i].addr < (void *)PAGE_SIZE && tests[*i].expected != TRANSL_UNAVAIL && !mapped_0; if (!skip) { diff --git a/tools/testing/selftests/kvm/s390x/ucontrol_test.c b/tools/testing/selftests/kvm/s390x/ucontrol_test.c new file mode 100644 index 000000000000..f257beec1430 --- /dev/null +++ b/tools/testing/selftests/kvm/s390x/ucontrol_test.c @@ -0,0 +1,332 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Test code for the s390x kvm ucontrol interface + * + * Copyright IBM Corp. 2024 + * + * Authors: + * Christoph Schlameuss <schlameuss@linux.ibm.com> + */ +#include "debug_print.h" +#include "kselftest_harness.h" +#include "kvm_util.h" +#include "processor.h" +#include "sie.h" + +#include <linux/capability.h> +#include <linux/sizes.h> + +#define VM_MEM_SIZE (4 * SZ_1M) + +/* so directly declare capget to check caps without libcap */ +int capget(cap_user_header_t header, cap_user_data_t data); + +/** + * In order to create user controlled virtual machines on S390, + * check KVM_CAP_S390_UCONTROL and use the flag KVM_VM_S390_UCONTROL + * as privileged user (SYS_ADMIN). + */ +void require_ucontrol_admin(void) +{ + struct __user_cap_data_struct data[_LINUX_CAPABILITY_U32S_3]; + struct __user_cap_header_struct hdr = { + .version = _LINUX_CAPABILITY_VERSION_3, + }; + int rc; + + rc = capget(&hdr, data); + TEST_ASSERT_EQ(0, rc); + TEST_REQUIRE((data->effective & CAP_TO_MASK(CAP_SYS_ADMIN)) > 0); + + TEST_REQUIRE(kvm_has_cap(KVM_CAP_S390_UCONTROL)); +} + +/* Test program setting some registers and looping */ +extern char test_gprs_asm[]; +asm("test_gprs_asm:\n" + "xgr %r0, %r0\n" + "lgfi %r1,1\n" + "lgfi %r2,2\n" + "lgfi %r3,3\n" + "lgfi %r4,4\n" + "lgfi %r5,5\n" + "lgfi %r6,6\n" + "lgfi %r7,7\n" + "0:\n" + " diag 0,0,0x44\n" + " ahi %r0,1\n" + " j 0b\n" +); + +FIXTURE(uc_kvm) +{ + struct kvm_s390_sie_block *sie_block; + struct kvm_run *run; + uintptr_t base_gpa; + uintptr_t code_gpa; + uintptr_t base_hva; + uintptr_t code_hva; + int kvm_run_size; + void *vm_mem; + int vcpu_fd; + int kvm_fd; + int vm_fd; +}; + +/** + * create VM with single vcpu, map kvm_run and SIE control block for easy access + */ +FIXTURE_SETUP(uc_kvm) +{ + struct kvm_s390_vm_cpu_processor info; + int rc; + + require_ucontrol_admin(); + + self->kvm_fd = open_kvm_dev_path_or_exit(); + self->vm_fd = ioctl(self->kvm_fd, KVM_CREATE_VM, KVM_VM_S390_UCONTROL); + ASSERT_GE(self->vm_fd, 0); + + kvm_device_attr_get(self->vm_fd, KVM_S390_VM_CPU_MODEL, + KVM_S390_VM_CPU_PROCESSOR, &info); + TH_LOG("create VM 0x%llx", info.cpuid); + + self->vcpu_fd = ioctl(self->vm_fd, KVM_CREATE_VCPU, 0); + ASSERT_GE(self->vcpu_fd, 0); + + self->kvm_run_size = ioctl(self->kvm_fd, KVM_GET_VCPU_MMAP_SIZE, NULL); + ASSERT_GE(self->kvm_run_size, sizeof(struct kvm_run)) + TH_LOG(KVM_IOCTL_ERROR(KVM_GET_VCPU_MMAP_SIZE, self->kvm_run_size)); + self->run = (struct kvm_run *)mmap(NULL, self->kvm_run_size, + PROT_READ | PROT_WRITE, MAP_SHARED, self->vcpu_fd, 0); + ASSERT_NE(self->run, MAP_FAILED); + /** + * For virtual cpus that have been created with S390 user controlled + * virtual machines, the resulting vcpu fd can be memory mapped at page + * offset KVM_S390_SIE_PAGE_OFFSET in order to obtain a memory map of + * the virtual cpu's hardware control block. + */ + self->sie_block = (struct kvm_s390_sie_block *)mmap(NULL, PAGE_SIZE, + PROT_READ | PROT_WRITE, MAP_SHARED, + self->vcpu_fd, KVM_S390_SIE_PAGE_OFFSET << PAGE_SHIFT); + ASSERT_NE(self->sie_block, MAP_FAILED); + + TH_LOG("VM created %p %p", self->run, self->sie_block); + + self->base_gpa = 0; + self->code_gpa = self->base_gpa + (3 * SZ_1M); + + self->vm_mem = aligned_alloc(SZ_1M, VM_MEM_SIZE); + ASSERT_NE(NULL, self->vm_mem) TH_LOG("malloc failed %u", errno); + self->base_hva = (uintptr_t)self->vm_mem; + self->code_hva = self->base_hva - self->base_gpa + self->code_gpa; + struct kvm_s390_ucas_mapping map = { + .user_addr = self->base_hva, + .vcpu_addr = self->base_gpa, + .length = VM_MEM_SIZE, + }; + TH_LOG("ucas map %p %p 0x%llx", + (void *)map.user_addr, (void *)map.vcpu_addr, map.length); + rc = ioctl(self->vcpu_fd, KVM_S390_UCAS_MAP, &map); + ASSERT_EQ(0, rc) TH_LOG("ucas map result %d not expected, %s", + rc, strerror(errno)); + + TH_LOG("page in %p", (void *)self->base_gpa); + rc = ioctl(self->vcpu_fd, KVM_S390_VCPU_FAULT, self->base_gpa); + ASSERT_EQ(0, rc) TH_LOG("vcpu fault (%p) result %d not expected, %s", + (void *)self->base_hva, rc, strerror(errno)); + + self->sie_block->cpuflags &= ~CPUSTAT_STOPPED; +} + +FIXTURE_TEARDOWN(uc_kvm) +{ + munmap(self->sie_block, PAGE_SIZE); + munmap(self->run, self->kvm_run_size); + close(self->vcpu_fd); + close(self->vm_fd); + close(self->kvm_fd); + free(self->vm_mem); +} + +TEST_F(uc_kvm, uc_sie_assertions) +{ + /* assert interception of Code 08 (Program Interruption) is set */ + EXPECT_EQ(0, self->sie_block->ecb & ECB_SPECI); +} + +TEST_F(uc_kvm, uc_attr_mem_limit) +{ + u64 limit; + struct kvm_device_attr attr = { + .group = KVM_S390_VM_MEM_CTRL, + .attr = KVM_S390_VM_MEM_LIMIT_SIZE, + .addr = (unsigned long)&limit, + }; + int rc; + + rc = ioctl(self->vm_fd, KVM_GET_DEVICE_ATTR, &attr); + EXPECT_EQ(0, rc); + EXPECT_EQ(~0UL, limit); + + /* assert set not supported */ + rc = ioctl(self->vm_fd, KVM_SET_DEVICE_ATTR, &attr); + EXPECT_EQ(-1, rc); + EXPECT_EQ(EINVAL, errno); +} + +TEST_F(uc_kvm, uc_no_dirty_log) +{ + struct kvm_dirty_log dlog; + int rc; + + rc = ioctl(self->vm_fd, KVM_GET_DIRTY_LOG, &dlog); + EXPECT_EQ(-1, rc); + EXPECT_EQ(EINVAL, errno); +} + +/** + * Assert HPAGE CAP cannot be enabled on UCONTROL VM + */ +TEST(uc_cap_hpage) +{ + int rc, kvm_fd, vm_fd, vcpu_fd; + struct kvm_enable_cap cap = { + .cap = KVM_CAP_S390_HPAGE_1M, + }; + + require_ucontrol_admin(); + + kvm_fd = open_kvm_dev_path_or_exit(); + vm_fd = ioctl(kvm_fd, KVM_CREATE_VM, KVM_VM_S390_UCONTROL); + ASSERT_GE(vm_fd, 0); + + /* assert hpages are not supported on ucontrol vm */ + rc = ioctl(vm_fd, KVM_CHECK_EXTENSION, KVM_CAP_S390_HPAGE_1M); + EXPECT_EQ(0, rc); + + /* Test that KVM_CAP_S390_HPAGE_1M can't be enabled for a ucontrol vm */ + rc = ioctl(vm_fd, KVM_ENABLE_CAP, cap); + EXPECT_EQ(-1, rc); + EXPECT_EQ(EINVAL, errno); + + /* assert HPAGE CAP is rejected after vCPU creation */ + vcpu_fd = ioctl(vm_fd, KVM_CREATE_VCPU, 0); + ASSERT_GE(vcpu_fd, 0); + rc = ioctl(vm_fd, KVM_ENABLE_CAP, cap); + EXPECT_EQ(-1, rc); + EXPECT_EQ(EBUSY, errno); + + close(vcpu_fd); + close(vm_fd); + close(kvm_fd); +} + +/* verify SIEIC exit + * * fail on codes not expected in the test cases + */ +static bool uc_handle_sieic(FIXTURE_DATA(uc_kvm) * self) +{ + struct kvm_s390_sie_block *sie_block = self->sie_block; + struct kvm_run *run = self->run; + + /* check SIE interception code */ + pr_info("sieic: 0x%.2x 0x%.4x 0x%.4x\n", + run->s390_sieic.icptcode, + run->s390_sieic.ipa, + run->s390_sieic.ipb); + switch (run->s390_sieic.icptcode) { + case ICPT_INST: + /* end execution in caller on intercepted instruction */ + pr_info("sie instruction interception\n"); + return false; + case ICPT_OPEREXC: + /* operation exception */ + TEST_FAIL("sie exception on %.4x%.8x", sie_block->ipa, sie_block->ipb); + default: + TEST_FAIL("UNEXPECTED SIEIC CODE %d", run->s390_sieic.icptcode); + } + return true; +} + +/* verify VM state on exit */ +static bool uc_handle_exit(FIXTURE_DATA(uc_kvm) * self) +{ + struct kvm_run *run = self->run; + + switch (run->exit_reason) { + case KVM_EXIT_S390_SIEIC: + return uc_handle_sieic(self); + default: + pr_info("exit_reason %2d not handled\n", run->exit_reason); + } + return true; +} + +/* run the VM until interrupted */ +static int uc_run_once(FIXTURE_DATA(uc_kvm) * self) +{ + int rc; + + rc = ioctl(self->vcpu_fd, KVM_RUN, NULL); + print_run(self->run, self->sie_block); + print_regs(self->run); + pr_debug("run %d / %d %s\n", rc, errno, strerror(errno)); + return rc; +} + +static void uc_assert_diag44(FIXTURE_DATA(uc_kvm) * self) +{ + struct kvm_s390_sie_block *sie_block = self->sie_block; + + /* assert vm was interrupted by diag 0x0044 */ + TEST_ASSERT_EQ(KVM_EXIT_S390_SIEIC, self->run->exit_reason); + TEST_ASSERT_EQ(ICPT_INST, sie_block->icptcode); + TEST_ASSERT_EQ(0x8300, sie_block->ipa); + TEST_ASSERT_EQ(0x440000, sie_block->ipb); +} + +TEST_F(uc_kvm, uc_gprs) +{ + struct kvm_sync_regs *sync_regs = &self->run->s.regs; + struct kvm_run *run = self->run; + struct kvm_regs regs = {}; + + /* Set registers to values that are different from the ones that we expect below */ + for (int i = 0; i < 8; i++) + sync_regs->gprs[i] = 8; + run->kvm_dirty_regs |= KVM_SYNC_GPRS; + + /* copy test_gprs_asm to code_hva / code_gpa */ + TH_LOG("copy code %p to vm mapped memory %p / %p", + &test_gprs_asm, (void *)self->code_hva, (void *)self->code_gpa); + memcpy((void *)self->code_hva, &test_gprs_asm, PAGE_SIZE); + + /* DAT disabled + 64 bit mode */ + run->psw_mask = 0x0000000180000000ULL; + run->psw_addr = self->code_gpa; + + /* run and expect interception of diag 44 */ + ASSERT_EQ(0, uc_run_once(self)); + ASSERT_EQ(false, uc_handle_exit(self)); + uc_assert_diag44(self); + + /* Retrieve and check guest register values */ + ASSERT_EQ(0, ioctl(self->vcpu_fd, KVM_GET_REGS, ®s)); + for (int i = 0; i < 8; i++) { + ASSERT_EQ(i, regs.gprs[i]); + ASSERT_EQ(i, sync_regs->gprs[i]); + } + + /* run and expect interception of diag 44 again */ + ASSERT_EQ(0, uc_run_once(self)); + ASSERT_EQ(false, uc_handle_exit(self)); + uc_assert_diag44(self); + + /* check continued increment of register 0 value */ + ASSERT_EQ(0, ioctl(self->vcpu_fd, KVM_GET_REGS, ®s)); + ASSERT_EQ(1, regs.gprs[0]); + ASSERT_EQ(1, sync_regs->gprs[0]); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/kvm/set_memory_region_test.c b/tools/testing/selftests/kvm/set_memory_region_test.c index bb8002084f52..a8267628e9ed 100644 --- a/tools/testing/selftests/kvm/set_memory_region_test.c +++ b/tools/testing/selftests/kvm/set_memory_region_test.c @@ -175,7 +175,7 @@ static void guest_code_move_memory_region(void) GUEST_DONE(); } -static void test_move_memory_region(void) +static void test_move_memory_region(bool disable_slot_zap_quirk) { pthread_t vcpu_thread; struct kvm_vcpu *vcpu; @@ -184,6 +184,9 @@ static void test_move_memory_region(void) vm = spawn_vm(&vcpu, &vcpu_thread, guest_code_move_memory_region); + if (disable_slot_zap_quirk) + vm_enable_cap(vm, KVM_CAP_DISABLE_QUIRKS2, KVM_X86_QUIRK_SLOT_ZAP_ALL); + hva = addr_gpa2hva(vm, MEM_REGION_GPA); /* @@ -266,7 +269,7 @@ static void guest_code_delete_memory_region(void) GUEST_ASSERT(0); } -static void test_delete_memory_region(void) +static void test_delete_memory_region(bool disable_slot_zap_quirk) { pthread_t vcpu_thread; struct kvm_vcpu *vcpu; @@ -276,6 +279,9 @@ static void test_delete_memory_region(void) vm = spawn_vm(&vcpu, &vcpu_thread, guest_code_delete_memory_region); + if (disable_slot_zap_quirk) + vm_enable_cap(vm, KVM_CAP_DISABLE_QUIRKS2, KVM_X86_QUIRK_SLOT_ZAP_ALL); + /* Delete the memory region, the guest should not die. */ vm_mem_region_delete(vm, MEM_REGION_SLOT); wait_for_vcpu(); @@ -553,7 +559,10 @@ int main(int argc, char *argv[]) { #ifdef __x86_64__ int i, loops; + int j, disable_slot_zap_quirk = 0; + if (kvm_check_cap(KVM_CAP_DISABLE_QUIRKS2) & KVM_X86_QUIRK_SLOT_ZAP_ALL) + disable_slot_zap_quirk = 1; /* * FIXME: the zero-memslot test fails on aarch64 and s390x because * KVM_RUN fails with ENOEXEC or EFAULT. @@ -579,13 +588,17 @@ int main(int argc, char *argv[]) else loops = 10; - pr_info("Testing MOVE of in-use region, %d loops\n", loops); - for (i = 0; i < loops; i++) - test_move_memory_region(); + for (j = 0; j <= disable_slot_zap_quirk; j++) { + pr_info("Testing MOVE of in-use region, %d loops, slot zap quirk %s\n", + loops, j ? "disabled" : "enabled"); + for (i = 0; i < loops; i++) + test_move_memory_region(!!j); - pr_info("Testing DELETE of in-use region, %d loops\n", loops); - for (i = 0; i < loops; i++) - test_delete_memory_region(); + pr_info("Testing DELETE of in-use region, %d loops, slot zap quirk %s\n", + loops, j ? "disabled" : "enabled"); + for (i = 0; i < loops; i++) + test_delete_memory_region(!!j); + } #endif return 0; diff --git a/tools/testing/selftests/kvm/x86_64/debug_regs.c b/tools/testing/selftests/kvm/x86_64/debug_regs.c index f6b295e0b2d2..76cc2df9238a 100644 --- a/tools/testing/selftests/kvm/x86_64/debug_regs.c +++ b/tools/testing/selftests/kvm/x86_64/debug_regs.c @@ -47,15 +47,18 @@ static void guest_code(void) /* * Single step test, covers 2 basic instructions and 2 emulated * - * Enable interrupts during the single stepping to see that - * pending interrupt we raised is not handled due to KVM_GUESTDBG_BLOCKIRQ + * Enable interrupts during the single stepping to see that pending + * interrupt we raised is not handled due to KVM_GUESTDBG_BLOCKIRQ. + * + * Write MSR_IA32_TSC_DEADLINE to verify that KVM's fastpath handler + * exits to userspace due to single-step being enabled. */ asm volatile("ss_start: " "sti\n\t" "xor %%eax,%%eax\n\t" "cpuid\n\t" - "movl $0x1a0,%%ecx\n\t" - "rdmsr\n\t" + "movl $" __stringify(MSR_IA32_TSC_DEADLINE) ", %%ecx\n\t" + "wrmsr\n\t" "cli\n\t" : : : "eax", "ebx", "ecx", "edx"); diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_evmcs.c b/tools/testing/selftests/kvm/x86_64/hyperv_evmcs.c index e192720bfe14..74cf19661309 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_evmcs.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_evmcs.c @@ -242,7 +242,7 @@ int main(int argc, char *argv[]) TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX)); TEST_REQUIRE(kvm_has_cap(KVM_CAP_NESTED_STATE)); TEST_REQUIRE(kvm_has_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS)); - TEST_REQUIRE(kvm_has_cap(KVM_CAP_HYPERV_DIRECT_TLBFLUSH)); + TEST_REQUIRE(kvm_hv_cpu_has(HV_X64_NESTED_DIRECT_FLUSH)); vm = vm_create_with_one_vcpu(&vcpu, guest_code); diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c b/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c index b987a3d79715..0ddb63229bcb 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c @@ -157,7 +157,7 @@ int main(int argc, char *argv[]) int stage; TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_SVM)); - TEST_REQUIRE(kvm_has_cap(KVM_CAP_HYPERV_DIRECT_TLBFLUSH)); + TEST_REQUIRE(kvm_hv_cpu_has(HV_X64_NESTED_DIRECT_FLUSH)); /* Create VM */ vm = vm_create_with_one_vcpu(&vcpu, guest_code); diff --git a/tools/testing/selftests/kvm/x86_64/sev_smoke_test.c b/tools/testing/selftests/kvm/x86_64/sev_smoke_test.c index 7c70c0da4fb7..2e9197eb1652 100644 --- a/tools/testing/selftests/kvm/x86_64/sev_smoke_test.c +++ b/tools/testing/selftests/kvm/x86_64/sev_smoke_test.c @@ -160,6 +160,36 @@ static void test_sev(void *guest_code, uint64_t policy) kvm_vm_free(vm); } +static void guest_shutdown_code(void) +{ + struct desc_ptr idt; + + /* Clobber the IDT so that #UD is guaranteed to trigger SHUTDOWN. */ + memset(&idt, 0, sizeof(idt)); + __asm__ __volatile__("lidt %0" :: "m"(idt)); + + __asm__ __volatile__("ud2"); +} + +static void test_sev_es_shutdown(void) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + + uint32_t type = KVM_X86_SEV_ES_VM; + + vm = vm_sev_create_with_one_vcpu(type, guest_shutdown_code, &vcpu); + + vm_sev_launch(vm, SEV_POLICY_ES, NULL); + + vcpu_run(vcpu); + TEST_ASSERT(vcpu->run->exit_reason == KVM_EXIT_SHUTDOWN, + "Wanted SHUTDOWN, got %s", + exit_reason_str(vcpu->run->exit_reason)); + + kvm_vm_free(vm); +} + int main(int argc, char *argv[]) { TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_SEV)); @@ -171,6 +201,8 @@ int main(int argc, char *argv[]) test_sev(guest_sev_es_code, SEV_POLICY_ES | SEV_POLICY_NO_DBG); test_sev(guest_sev_es_code, SEV_POLICY_ES); + test_sev_es_shutdown(); + if (kvm_has_cap(KVM_CAP_XCRS) && (xgetbv(0) & XFEATURE_MASK_X87_AVX) == XFEATURE_MASK_X87_AVX) { test_sync_vmsa(0); diff --git a/tools/testing/selftests/kvm/x86_64/xapic_state_test.c b/tools/testing/selftests/kvm/x86_64/xapic_state_test.c index 618cd2442390..88bcca188799 100644 --- a/tools/testing/selftests/kvm/x86_64/xapic_state_test.c +++ b/tools/testing/selftests/kvm/x86_64/xapic_state_test.c @@ -13,6 +13,7 @@ struct xapic_vcpu { struct kvm_vcpu *vcpu; bool is_x2apic; + bool has_xavic_errata; }; static void xapic_guest_code(void) @@ -31,6 +32,10 @@ static void xapic_guest_code(void) } } +#define X2APIC_RSVD_BITS_MASK (GENMASK_ULL(31, 20) | \ + GENMASK_ULL(17, 16) | \ + GENMASK_ULL(13, 13)) + static void x2apic_guest_code(void) { asm volatile("cli"); @@ -41,7 +46,12 @@ static void x2apic_guest_code(void) uint64_t val = x2apic_read_reg(APIC_IRR) | x2apic_read_reg(APIC_IRR + 0x10) << 32; - x2apic_write_reg(APIC_ICR, val); + if (val & X2APIC_RSVD_BITS_MASK) { + x2apic_write_reg_fault(APIC_ICR, val); + } else { + x2apic_write_reg(APIC_ICR, val); + GUEST_ASSERT_EQ(x2apic_read_reg(APIC_ICR), val); + } GUEST_SYNC(val); } while (1); } @@ -71,27 +81,28 @@ static void ____test_icr(struct xapic_vcpu *x, uint64_t val) icr = (u64)(*((u32 *)&xapic.regs[APIC_ICR])) | (u64)(*((u32 *)&xapic.regs[APIC_ICR2])) << 32; if (!x->is_x2apic) { - val &= (-1u | (0xffull << (32 + 24))); - TEST_ASSERT_EQ(icr, val & ~APIC_ICR_BUSY); - } else { - TEST_ASSERT_EQ(icr & ~APIC_ICR_BUSY, val & ~APIC_ICR_BUSY); + if (!x->has_xavic_errata) + val &= (-1u | (0xffull << (32 + 24))); + } else if (val & X2APIC_RSVD_BITS_MASK) { + return; } -} -#define X2APIC_RSVED_BITS_MASK (GENMASK_ULL(31,20) | \ - GENMASK_ULL(17,16) | \ - GENMASK_ULL(13,13)) + if (x->has_xavic_errata) + TEST_ASSERT_EQ(icr & ~APIC_ICR_BUSY, val & ~APIC_ICR_BUSY); + else + TEST_ASSERT_EQ(icr, val & ~APIC_ICR_BUSY); +} static void __test_icr(struct xapic_vcpu *x, uint64_t val) { - if (x->is_x2apic) { - /* Hardware writing vICR register requires reserved bits 31:20, - * 17:16 and 13 kept as zero to avoid #GP exception. Data value - * written to vICR should mask out those bits above. - */ - val &= ~X2APIC_RSVED_BITS_MASK; - } - ____test_icr(x, val | APIC_ICR_BUSY); + /* + * The BUSY bit is reserved on both AMD and Intel, but only AMD treats + * it is as _must_ be zero. Intel simply ignores the bit. Don't test + * the BUSY bit for x2APIC, as there is no single correct behavior. + */ + if (!x->is_x2apic) + ____test_icr(x, val | APIC_ICR_BUSY); + ____test_icr(x, val & ~(u64)APIC_ICR_BUSY); } @@ -231,6 +242,15 @@ int main(int argc, char *argv[]) vm = vm_create_with_one_vcpu(&x.vcpu, xapic_guest_code); x.is_x2apic = false; + /* + * AMD's AVIC implementation is buggy (fails to clear the ICR BUSY bit), + * and also diverges from KVM with respect to ICR2[23:0] (KVM and Intel + * drops writes, AMD does not). Account for the errata when checking + * that KVM reads back what was written. + */ + x.has_xavic_errata = host_cpu_is_amd && + get_kvm_amd_param_bool("avic"); + vcpu_clear_cpuid_feature(x.vcpu, X86_FEATURE_X2APIC); virt_pg_map(vm, APIC_DEFAULT_GPA, APIC_DEFAULT_GPA); diff --git a/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c b/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c index e149d0574961..2585087cdf5c 100644 --- a/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c +++ b/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c @@ -10,6 +10,7 @@ #include "test_util.h" #include "kvm_util.h" #include "processor.h" +#include "hyperv.h" #define HCALL_REGION_GPA 0xc0000000ULL #define HCALL_REGION_SLOT 10 diff --git a/tools/testing/selftests/net/netfilter/conntrack_dump_flush.c b/tools/testing/selftests/net/netfilter/conntrack_dump_flush.c index bd9317bf5ada..dc056fec993b 100644 --- a/tools/testing/selftests/net/netfilter/conntrack_dump_flush.c +++ b/tools/testing/selftests/net/netfilter/conntrack_dump_flush.c @@ -207,6 +207,7 @@ static int conntrack_data_generate_v6(struct mnl_socket *sock, static int count_entries(const struct nlmsghdr *nlh, void *data) { reply_counter++; + return MNL_CB_OK; } static int conntracK_count_zone(struct mnl_socket *sock, uint16_t zone) diff --git a/tools/testing/selftests/net/netfilter/nft_audit.sh b/tools/testing/selftests/net/netfilter/nft_audit.sh index 902f8114bc80..87f2b4c725aa 100755 --- a/tools/testing/selftests/net/netfilter/nft_audit.sh +++ b/tools/testing/selftests/net/netfilter/nft_audit.sh @@ -48,12 +48,31 @@ logread_pid=$! trap 'kill $logread_pid; rm -f $logfile $rulefile' EXIT exec 3<"$logfile" +lsplit='s/^\(.*\) entries=\([^ ]*\) \(.*\)$/pfx="\1"\nval="\2"\nsfx="\3"/' +summarize_logs() { + sum=0 + while read line; do + eval $(sed "$lsplit" <<< "$line") + [[ $sum -gt 0 ]] && { + [[ "$pfx $sfx" == "$tpfx $tsfx" ]] && { + let "sum += val" + continue + } + echo "$tpfx entries=$sum $tsfx" + } + tpfx="$pfx" + tsfx="$sfx" + sum=$val + done + echo "$tpfx entries=$sum $tsfx" +} + do_test() { # (cmd, log) echo -n "testing for cmd: $1 ... " cat <&3 >/dev/null $1 >/dev/null || exit 1 sleep 0.1 - res=$(diff -a -u <(echo "$2") - <&3) + res=$(diff -a -u <(echo "$2") <(summarize_logs <&3)) [ $? -eq 0 ] && { echo "OK"; return; } echo "FAIL" grep -v '^\(---\|+++\|@@\)' <<< "$res" @@ -152,31 +171,17 @@ do_test 'nft reset rules t1 c2' \ 'table=t1 family=2 entries=3 op=nft_reset_rule' do_test 'nft reset rules table t1' \ -'table=t1 family=2 entries=3 op=nft_reset_rule -table=t1 family=2 entries=3 op=nft_reset_rule -table=t1 family=2 entries=3 op=nft_reset_rule' +'table=t1 family=2 entries=9 op=nft_reset_rule' do_test 'nft reset rules t2 c3' \ -'table=t2 family=2 entries=189 op=nft_reset_rule -table=t2 family=2 entries=188 op=nft_reset_rule -table=t2 family=2 entries=126 op=nft_reset_rule' +'table=t2 family=2 entries=503 op=nft_reset_rule' do_test 'nft reset rules t2' \ -'table=t2 family=2 entries=3 op=nft_reset_rule -table=t2 family=2 entries=3 op=nft_reset_rule -table=t2 family=2 entries=186 op=nft_reset_rule -table=t2 family=2 entries=188 op=nft_reset_rule -table=t2 family=2 entries=129 op=nft_reset_rule' +'table=t2 family=2 entries=509 op=nft_reset_rule' do_test 'nft reset rules' \ -'table=t1 family=2 entries=3 op=nft_reset_rule -table=t1 family=2 entries=3 op=nft_reset_rule -table=t1 family=2 entries=3 op=nft_reset_rule -table=t2 family=2 entries=3 op=nft_reset_rule -table=t2 family=2 entries=3 op=nft_reset_rule -table=t2 family=2 entries=180 op=nft_reset_rule -table=t2 family=2 entries=188 op=nft_reset_rule -table=t2 family=2 entries=135 op=nft_reset_rule' +'table=t1 family=2 entries=9 op=nft_reset_rule +table=t2 family=2 entries=509 op=nft_reset_rule' # resetting sets and elements @@ -200,13 +205,11 @@ do_test 'nft reset counters t1' \ 'table=t1 family=2 entries=1 op=nft_reset_obj' do_test 'nft reset counters t2' \ -'table=t2 family=2 entries=342 op=nft_reset_obj -table=t2 family=2 entries=158 op=nft_reset_obj' +'table=t2 family=2 entries=500 op=nft_reset_obj' do_test 'nft reset counters' \ 'table=t1 family=2 entries=1 op=nft_reset_obj -table=t2 family=2 entries=341 op=nft_reset_obj -table=t2 family=2 entries=159 op=nft_reset_obj' +table=t2 family=2 entries=500 op=nft_reset_obj' # resetting quotas @@ -217,13 +220,11 @@ do_test 'nft reset quotas t1' \ 'table=t1 family=2 entries=1 op=nft_reset_obj' do_test 'nft reset quotas t2' \ -'table=t2 family=2 entries=315 op=nft_reset_obj -table=t2 family=2 entries=185 op=nft_reset_obj' +'table=t2 family=2 entries=500 op=nft_reset_obj' do_test 'nft reset quotas' \ 'table=t1 family=2 entries=1 op=nft_reset_obj -table=t2 family=2 entries=314 op=nft_reset_obj -table=t2 family=2 entries=186 op=nft_reset_obj' +table=t2 family=2 entries=500 op=nft_reset_obj' # deleting rules diff --git a/tools/testing/selftests/net/rds/Makefile b/tools/testing/selftests/net/rds/Makefile index da9714bc7aad..cf30307a829b 100644 --- a/tools/testing/selftests/net/rds/Makefile +++ b/tools/testing/selftests/net/rds/Makefile @@ -4,9 +4,10 @@ all: @echo mk_build_dir="$(shell pwd)" > include.sh TEST_PROGS := run.sh \ - include.sh \ test.py +TEST_FILES := include.sh + EXTRA_CLEAN := /tmp/rds_logs include ../../lib.mk diff --git a/tools/testing/selftests/net/rds/test.py b/tools/testing/selftests/net/rds/test.py index e6bb109bcead..e6bb109bcead 100644..100755 --- a/tools/testing/selftests/net/rds/test.py +++ b/tools/testing/selftests/net/rds/test.py diff --git a/tools/testing/selftests/rtc/rtctest.c b/tools/testing/selftests/rtc/rtctest.c index 9647b14b47c5..38a8e67de77d 100644 --- a/tools/testing/selftests/rtc/rtctest.c +++ b/tools/testing/selftests/rtc/rtctest.c @@ -412,6 +412,8 @@ TEST_F_TIMEOUT(rtc, alarm_wkalm_set_minute, 65) { int main(int argc, char **argv) { + int ret = -1; + switch (argc) { case 2: rtc_file = argv[1]; @@ -423,5 +425,12 @@ int main(int argc, char **argv) return 1; } - return test_harness_run(argc, argv); + /* Run the test if rtc_file is accessible */ + if (access(rtc_file, R_OK) == 0) + ret = test_harness_run(argc, argv); + else + ksft_exit_skip("[SKIP]: Cannot access rtc file %s - Exiting\n", + rtc_file); + + return ret; } diff --git a/tools/testing/selftests/timers/posix_timers.c b/tools/testing/selftests/timers/posix_timers.c index 16bd49492efa..ddb1cebc844e 100644 --- a/tools/testing/selftests/timers/posix_timers.c +++ b/tools/testing/selftests/timers/posix_timers.c @@ -26,13 +26,17 @@ static void __fatal_error(const char *test, const char *name, const char *what) { char buf[64]; + char *ret_str = NULL; - strerror_r(errno, buf, sizeof(buf)); + ret_str = strerror_r(errno, buf, sizeof(buf)); - if (name && strlen(name)) - ksft_exit_fail_msg("%s %s %s %s\n", test, name, what, buf); + if (name && strlen(name) && ret_str) + ksft_exit_fail_msg("%s %s %s %s\n", test, name, what, ret_str); + else if (ret_str) + ksft_exit_fail_msg("%s %s %s\n", test, what, ret_str); else - ksft_exit_fail_msg("%s %s %s\n", test, what, buf); + ksft_exit_fail_msg("%s %s\n", test, what); + } #define fatal_error(name, what) __fatal_error(__func__, name, what) diff --git a/tools/testing/selftests/vDSO/vdso_standalone_test_x86.c b/tools/testing/selftests/vDSO/vdso_standalone_test_x86.c index 27f6fdf11969..644915862af8 100644 --- a/tools/testing/selftests/vDSO/vdso_standalone_test_x86.c +++ b/tools/testing/selftests/vDSO/vdso_standalone_test_x86.c @@ -131,6 +131,8 @@ asm ( "_start:\n\t" #ifdef __x86_64__ "mov %rsp,%rdi\n\t" + "and $-16,%rsp\n\t" + "sub $8,%rsp\n\t" "jmp c_main" #else "push %esp\n\t" diff --git a/tools/testing/selftests/vDSO/vdso_test_getrandom.c b/tools/testing/selftests/vDSO/vdso_test_getrandom.c index 72a1d9b43a84..e5e83dbec589 100644 --- a/tools/testing/selftests/vDSO/vdso_test_getrandom.c +++ b/tools/testing/selftests/vDSO/vdso_test_getrandom.c @@ -59,10 +59,12 @@ static void *vgetrandom_get_state(void) size_t page_size = getpagesize(); size_t new_cap; size_t alloc_size, num = sysconf(_SC_NPROCESSORS_ONLN); /* Just a decent heuristic. */ + size_t state_size_aligned, cache_line_size = sysconf(_SC_LEVEL1_DCACHE_LINESIZE) ?: 1; void *new_block, *new_states; - alloc_size = (num * vgrnd.params.size_of_opaque_state + page_size - 1) & (~(page_size - 1)); - num = (page_size / vgrnd.params.size_of_opaque_state) * (alloc_size / page_size); + state_size_aligned = (vgrnd.params.size_of_opaque_state + cache_line_size - 1) & (~(cache_line_size - 1)); + alloc_size = (num * state_size_aligned + page_size - 1) & (~(page_size - 1)); + num = (page_size / state_size_aligned) * (alloc_size / page_size); new_block = mmap(0, alloc_size, vgrnd.params.mmap_prot, vgrnd.params.mmap_flags, -1, 0); if (new_block == MAP_FAILED) goto out; @@ -78,7 +80,7 @@ static void *vgetrandom_get_state(void) if (((uintptr_t)new_block & (page_size - 1)) + vgrnd.params.size_of_opaque_state > page_size) new_block = (void *)(((uintptr_t)new_block + page_size - 1) & (~(page_size - 1))); vgrnd.states[i] = new_block; - new_block += vgrnd.params.size_of_opaque_state; + new_block += state_size_aligned; } vgrnd.len = num; goto success; diff --git a/tools/tracing/rtla/Makefile.rtla b/tools/tracing/rtla/Makefile.rtla index 3ff0b8970896..cc1d6b615475 100644 --- a/tools/tracing/rtla/Makefile.rtla +++ b/tools/tracing/rtla/Makefile.rtla @@ -38,7 +38,7 @@ BINDIR := /usr/bin .PHONY: install install: doc_install @$(MKDIR) -p $(DESTDIR)$(BINDIR) - $(call QUIET_INSTALL,rtla)$(INSTALL) rtla -m 755 $(DESTDIR)$(BINDIR) + $(call QUIET_INSTALL,rtla)$(INSTALL) $(RTLA) -m 755 $(DESTDIR)$(BINDIR) @$(STRIP) $(DESTDIR)$(BINDIR)/rtla @test ! -f $(DESTDIR)$(BINDIR)/osnoise || $(RM) $(DESTDIR)$(BINDIR)/osnoise @$(LN) rtla $(DESTDIR)$(BINDIR)/osnoise diff --git a/tools/tracing/rtla/src/osnoise_top.c b/tools/tracing/rtla/src/osnoise_top.c index 2f756628613d..30e3853076a0 100644 --- a/tools/tracing/rtla/src/osnoise_top.c +++ b/tools/tracing/rtla/src/osnoise_top.c @@ -442,7 +442,7 @@ struct osnoise_top_params *osnoise_top_parse_args(int argc, char **argv) case 'd': params->duration = parse_seconds_duration(optarg); if (!params->duration) - osnoise_top_usage(params, "Invalid -D duration\n"); + osnoise_top_usage(params, "Invalid -d duration\n"); break; case 'e': tevent = trace_event_alloc(optarg); diff --git a/tools/tracing/rtla/src/timerlat_top.c b/tools/tracing/rtla/src/timerlat_top.c index 8c16419fe22a..210b0f533534 100644 --- a/tools/tracing/rtla/src/timerlat_top.c +++ b/tools/tracing/rtla/src/timerlat_top.c @@ -459,7 +459,7 @@ static void timerlat_top_usage(char *usage) " -c/--cpus cpus: run the tracer only on the given cpus", " -H/--house-keeping cpus: run rtla control threads only on the given cpus", " -C/--cgroup[=cgroup_name]: set cgroup, if no cgroup_name is passed, the rtla's cgroup will be inherited", - " -d/--duration time[m|h|d]: duration of the session in seconds", + " -d/--duration time[s|m|h|d]: duration of the session", " -D/--debug: print debug info", " --dump-tasks: prints the task running on all CPUs if stop conditions are met (depends on !--no-aa)", " -t/--trace[file]: save the stopped trace to [file|timerlat_trace.txt]", @@ -613,7 +613,7 @@ static struct timerlat_top_params case 'd': params->duration = parse_seconds_duration(optarg); if (!params->duration) - timerlat_top_usage("Invalid -D duration\n"); + timerlat_top_usage("Invalid -d duration\n"); break; case 'e': tevent = trace_event_alloc(optarg); diff --git a/virt/kvm/coalesced_mmio.c b/virt/kvm/coalesced_mmio.c index 1b90acb6e3fe..375d6285475e 100644 --- a/virt/kvm/coalesced_mmio.c +++ b/virt/kvm/coalesced_mmio.c @@ -40,27 +40,6 @@ static int coalesced_mmio_in_range(struct kvm_coalesced_mmio_dev *dev, return 1; } -static int coalesced_mmio_has_room(struct kvm_coalesced_mmio_dev *dev, u32 last) -{ - struct kvm_coalesced_mmio_ring *ring; - unsigned avail; - - /* Are we able to batch it ? */ - - /* last is the first free entry - * check if we don't meet the first used entry - * there is always one unused entry in the buffer - */ - ring = dev->kvm->coalesced_mmio_ring; - avail = (ring->first - last - 1) % KVM_COALESCED_MMIO_MAX; - if (avail == 0) { - /* full */ - return 0; - } - - return 1; -} - static int coalesced_mmio_write(struct kvm_vcpu *vcpu, struct kvm_io_device *this, gpa_t addr, int len, const void *val) @@ -74,9 +53,15 @@ static int coalesced_mmio_write(struct kvm_vcpu *vcpu, spin_lock(&dev->kvm->ring_lock); + /* + * last is the index of the entry to fill. Verify userspace hasn't + * set last to be out of range, and that there is room in the ring. + * Leave one entry free in the ring so that userspace can differentiate + * between an empty ring and a full ring. + */ insert = READ_ONCE(ring->last); - if (!coalesced_mmio_has_room(dev, insert) || - insert >= KVM_COALESCED_MMIO_MAX) { + if (insert >= KVM_COALESCED_MMIO_MAX || + (insert + 1) % KVM_COALESCED_MMIO_MAX == READ_ONCE(ring->first)) { spin_unlock(&dev->kvm->ring_lock); return -EOPNOTSUPP; } diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 4f81366f8b61..05cbb2548d99 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -136,8 +136,8 @@ static int kvm_no_compat_open(struct inode *inode, struct file *file) #define KVM_COMPAT(c) .compat_ioctl = kvm_no_compat_ioctl, \ .open = kvm_no_compat_open #endif -static int hardware_enable_all(void); -static void hardware_disable_all(void); +static int kvm_enable_virtualization(void); +static void kvm_disable_virtualization(void); static void kvm_io_bus_destroy(struct kvm_io_bus *bus); @@ -1220,7 +1220,7 @@ static struct kvm *kvm_create_vm(unsigned long type, const char *fdname) if (r) goto out_err_no_arch_destroy_vm; - r = hardware_enable_all(); + r = kvm_enable_virtualization(); if (r) goto out_err_no_disable; @@ -1263,7 +1263,7 @@ out_no_coalesced_mmio: mmu_notifier_unregister(&kvm->mmu_notifier, current->mm); #endif out_err_no_mmu_notifier: - hardware_disable_all(); + kvm_disable_virtualization(); out_err_no_disable: kvm_arch_destroy_vm(kvm); out_err_no_arch_destroy_vm: @@ -1360,7 +1360,7 @@ static void kvm_destroy_vm(struct kvm *kvm) #endif kvm_arch_free_vm(kvm); preempt_notifier_dec(); - hardware_disable_all(); + kvm_disable_virtualization(); mmdrop(mm); } @@ -3270,6 +3270,9 @@ static int __kvm_read_guest_page(struct kvm_memory_slot *slot, gfn_t gfn, int r; unsigned long addr; + if (WARN_ON_ONCE(offset + len > PAGE_SIZE)) + return -EFAULT; + addr = gfn_to_hva_memslot_prot(slot, gfn, NULL); if (kvm_is_error_hva(addr)) return -EFAULT; @@ -3343,6 +3346,9 @@ static int __kvm_read_guest_atomic(struct kvm_memory_slot *slot, gfn_t gfn, int r; unsigned long addr; + if (WARN_ON_ONCE(offset + len > PAGE_SIZE)) + return -EFAULT; + addr = gfn_to_hva_memslot_prot(slot, gfn, NULL); if (kvm_is_error_hva(addr)) return -EFAULT; @@ -3373,6 +3379,9 @@ static int __kvm_write_guest_page(struct kvm *kvm, int r; unsigned long addr; + if (WARN_ON_ONCE(offset + len > PAGE_SIZE)) + return -EFAULT; + addr = gfn_to_hva_memslot(memslot, gfn); if (kvm_is_error_hva(addr)) return -EFAULT; @@ -3576,7 +3585,7 @@ int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len) int ret; while ((seg = next_segment(len, offset)) != 0) { - ret = kvm_write_guest_page(kvm, gfn, zero_page, offset, len); + ret = kvm_write_guest_page(kvm, gfn, zero_page, offset, seg); if (ret < 0) return ret; offset = 0; @@ -5566,137 +5575,67 @@ static struct miscdevice kvm_dev = { }; #ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING +static bool enable_virt_at_load = true; +module_param(enable_virt_at_load, bool, 0444); + __visible bool kvm_rebooting; EXPORT_SYMBOL_GPL(kvm_rebooting); -static DEFINE_PER_CPU(bool, hardware_enabled); +static DEFINE_PER_CPU(bool, virtualization_enabled); +static DEFINE_MUTEX(kvm_usage_lock); static int kvm_usage_count; -static int __hardware_enable_nolock(void) +__weak void kvm_arch_enable_virtualization(void) +{ + +} + +__weak void kvm_arch_disable_virtualization(void) +{ + +} + +static int kvm_enable_virtualization_cpu(void) { - if (__this_cpu_read(hardware_enabled)) + if (__this_cpu_read(virtualization_enabled)) return 0; - if (kvm_arch_hardware_enable()) { + if (kvm_arch_enable_virtualization_cpu()) { pr_info("kvm: enabling virtualization on CPU%d failed\n", raw_smp_processor_id()); return -EIO; } - __this_cpu_write(hardware_enabled, true); + __this_cpu_write(virtualization_enabled, true); return 0; } -static void hardware_enable_nolock(void *failed) -{ - if (__hardware_enable_nolock()) - atomic_inc(failed); -} - static int kvm_online_cpu(unsigned int cpu) { - int ret = 0; - /* * Abort the CPU online process if hardware virtualization cannot * be enabled. Otherwise running VMs would encounter unrecoverable * errors when scheduled to this CPU. */ - mutex_lock(&kvm_lock); - if (kvm_usage_count) - ret = __hardware_enable_nolock(); - mutex_unlock(&kvm_lock); - return ret; + return kvm_enable_virtualization_cpu(); } -static void hardware_disable_nolock(void *junk) +static void kvm_disable_virtualization_cpu(void *ign) { - /* - * Note, hardware_disable_all_nolock() tells all online CPUs to disable - * hardware, not just CPUs that successfully enabled hardware! - */ - if (!__this_cpu_read(hardware_enabled)) + if (!__this_cpu_read(virtualization_enabled)) return; - kvm_arch_hardware_disable(); + kvm_arch_disable_virtualization_cpu(); - __this_cpu_write(hardware_enabled, false); + __this_cpu_write(virtualization_enabled, false); } static int kvm_offline_cpu(unsigned int cpu) { - mutex_lock(&kvm_lock); - if (kvm_usage_count) - hardware_disable_nolock(NULL); - mutex_unlock(&kvm_lock); + kvm_disable_virtualization_cpu(NULL); return 0; } -static void hardware_disable_all_nolock(void) -{ - BUG_ON(!kvm_usage_count); - - kvm_usage_count--; - if (!kvm_usage_count) - on_each_cpu(hardware_disable_nolock, NULL, 1); -} - -static void hardware_disable_all(void) -{ - cpus_read_lock(); - mutex_lock(&kvm_lock); - hardware_disable_all_nolock(); - mutex_unlock(&kvm_lock); - cpus_read_unlock(); -} - -static int hardware_enable_all(void) -{ - atomic_t failed = ATOMIC_INIT(0); - int r; - - /* - * Do not enable hardware virtualization if the system is going down. - * If userspace initiated a forced reboot, e.g. reboot -f, then it's - * possible for an in-flight KVM_CREATE_VM to trigger hardware enabling - * after kvm_reboot() is called. Note, this relies on system_state - * being set _before_ kvm_reboot(), which is why KVM uses a syscore ops - * hook instead of registering a dedicated reboot notifier (the latter - * runs before system_state is updated). - */ - if (system_state == SYSTEM_HALT || system_state == SYSTEM_POWER_OFF || - system_state == SYSTEM_RESTART) - return -EBUSY; - - /* - * When onlining a CPU, cpu_online_mask is set before kvm_online_cpu() - * is called, and so on_each_cpu() between them includes the CPU that - * is being onlined. As a result, hardware_enable_nolock() may get - * invoked before kvm_online_cpu(), which also enables hardware if the - * usage count is non-zero. Disable CPU hotplug to avoid attempting to - * enable hardware multiple times. - */ - cpus_read_lock(); - mutex_lock(&kvm_lock); - - r = 0; - - kvm_usage_count++; - if (kvm_usage_count == 1) { - on_each_cpu(hardware_enable_nolock, &failed, 1); - - if (atomic_read(&failed)) { - hardware_disable_all_nolock(); - r = -EBUSY; - } - } - - mutex_unlock(&kvm_lock); - cpus_read_unlock(); - - return r; -} - static void kvm_shutdown(void) { /* @@ -5712,34 +5651,32 @@ static void kvm_shutdown(void) */ pr_info("kvm: exiting hardware virtualization\n"); kvm_rebooting = true; - on_each_cpu(hardware_disable_nolock, NULL, 1); + on_each_cpu(kvm_disable_virtualization_cpu, NULL, 1); } static int kvm_suspend(void) { /* * Secondary CPUs and CPU hotplug are disabled across the suspend/resume - * callbacks, i.e. no need to acquire kvm_lock to ensure the usage count - * is stable. Assert that kvm_lock is not held to ensure the system - * isn't suspended while KVM is enabling hardware. Hardware enabling - * can be preempted, but the task cannot be frozen until it has dropped - * all locks (userspace tasks are frozen via a fake signal). + * callbacks, i.e. no need to acquire kvm_usage_lock to ensure the usage + * count is stable. Assert that kvm_usage_lock is not held to ensure + * the system isn't suspended while KVM is enabling hardware. Hardware + * enabling can be preempted, but the task cannot be frozen until it has + * dropped all locks (userspace tasks are frozen via a fake signal). */ - lockdep_assert_not_held(&kvm_lock); + lockdep_assert_not_held(&kvm_usage_lock); lockdep_assert_irqs_disabled(); - if (kvm_usage_count) - hardware_disable_nolock(NULL); + kvm_disable_virtualization_cpu(NULL); return 0; } static void kvm_resume(void) { - lockdep_assert_not_held(&kvm_lock); + lockdep_assert_not_held(&kvm_usage_lock); lockdep_assert_irqs_disabled(); - if (kvm_usage_count) - WARN_ON_ONCE(__hardware_enable_nolock()); + WARN_ON_ONCE(kvm_enable_virtualization_cpu()); } static struct syscore_ops kvm_syscore_ops = { @@ -5747,13 +5684,95 @@ static struct syscore_ops kvm_syscore_ops = { .resume = kvm_resume, .shutdown = kvm_shutdown, }; + +static int kvm_enable_virtualization(void) +{ + int r; + + guard(mutex)(&kvm_usage_lock); + + if (kvm_usage_count++) + return 0; + + kvm_arch_enable_virtualization(); + + r = cpuhp_setup_state(CPUHP_AP_KVM_ONLINE, "kvm/cpu:online", + kvm_online_cpu, kvm_offline_cpu); + if (r) + goto err_cpuhp; + + register_syscore_ops(&kvm_syscore_ops); + + /* + * Undo virtualization enabling and bail if the system is going down. + * If userspace initiated a forced reboot, e.g. reboot -f, then it's + * possible for an in-flight operation to enable virtualization after + * syscore_shutdown() is called, i.e. without kvm_shutdown() being + * invoked. Note, this relies on system_state being set _before_ + * kvm_shutdown(), e.g. to ensure either kvm_shutdown() is invoked + * or this CPU observes the impending shutdown. Which is why KVM uses + * a syscore ops hook instead of registering a dedicated reboot + * notifier (the latter runs before system_state is updated). + */ + if (system_state == SYSTEM_HALT || system_state == SYSTEM_POWER_OFF || + system_state == SYSTEM_RESTART) { + r = -EBUSY; + goto err_rebooting; + } + + return 0; + +err_rebooting: + unregister_syscore_ops(&kvm_syscore_ops); + cpuhp_remove_state(CPUHP_AP_KVM_ONLINE); +err_cpuhp: + kvm_arch_disable_virtualization(); + --kvm_usage_count; + return r; +} + +static void kvm_disable_virtualization(void) +{ + guard(mutex)(&kvm_usage_lock); + + if (--kvm_usage_count) + return; + + unregister_syscore_ops(&kvm_syscore_ops); + cpuhp_remove_state(CPUHP_AP_KVM_ONLINE); + kvm_arch_disable_virtualization(); +} + +static int kvm_init_virtualization(void) +{ + if (enable_virt_at_load) + return kvm_enable_virtualization(); + + return 0; +} + +static void kvm_uninit_virtualization(void) +{ + if (enable_virt_at_load) + kvm_disable_virtualization(); +} #else /* CONFIG_KVM_GENERIC_HARDWARE_ENABLING */ -static int hardware_enable_all(void) +static int kvm_enable_virtualization(void) +{ + return 0; +} + +static int kvm_init_virtualization(void) { return 0; } -static void hardware_disable_all(void) +static void kvm_disable_virtualization(void) +{ + +} + +static void kvm_uninit_virtualization(void) { } @@ -6454,15 +6473,6 @@ int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module) int r; int cpu; -#ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING - r = cpuhp_setup_state_nocalls(CPUHP_AP_KVM_ONLINE, "kvm/cpu:online", - kvm_online_cpu, kvm_offline_cpu); - if (r) - return r; - - register_syscore_ops(&kvm_syscore_ops); -#endif - /* A kmem cache lets us meet the alignment requirements of fx_save. */ if (!vcpu_align) vcpu_align = __alignof__(struct kvm_vcpu); @@ -6473,10 +6483,8 @@ int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module) offsetofend(struct kvm_vcpu, stats_id) - offsetof(struct kvm_vcpu, arch), NULL); - if (!kvm_vcpu_cache) { - r = -ENOMEM; - goto err_vcpu_cache; - } + if (!kvm_vcpu_cache) + return -ENOMEM; for_each_possible_cpu(cpu) { if (!alloc_cpumask_var_node(&per_cpu(cpu_kick_mask, cpu), @@ -6510,6 +6518,10 @@ int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module) kvm_gmem_init(module); + r = kvm_init_virtualization(); + if (r) + goto err_virt; + /* * Registration _must_ be the very last thing done, as this exposes * /dev/kvm to userspace, i.e. all infrastructure must be setup! @@ -6523,6 +6535,8 @@ int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module) return 0; err_register: + kvm_uninit_virtualization(); +err_virt: kvm_vfio_ops_exit(); err_vfio: kvm_async_pf_deinit(); @@ -6533,11 +6547,6 @@ err_cpu_kick_mask: for_each_possible_cpu(cpu) free_cpumask_var(per_cpu(cpu_kick_mask, cpu)); kmem_cache_destroy(kvm_vcpu_cache); -err_vcpu_cache: -#ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING - unregister_syscore_ops(&kvm_syscore_ops); - cpuhp_remove_state_nocalls(CPUHP_AP_KVM_ONLINE); -#endif return r; } EXPORT_SYMBOL_GPL(kvm_init); @@ -6553,16 +6562,14 @@ void kvm_exit(void) */ misc_deregister(&kvm_dev); + kvm_uninit_virtualization(); + debugfs_remove_recursive(kvm_debugfs_dir); for_each_possible_cpu(cpu) free_cpumask_var(per_cpu(cpu_kick_mask, cpu)); kmem_cache_destroy(kvm_vcpu_cache); kvm_vfio_ops_exit(); kvm_async_pf_deinit(); -#ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING - unregister_syscore_ops(&kvm_syscore_ops); - cpuhp_remove_state_nocalls(CPUHP_AP_KVM_ONLINE); -#endif kvm_irqfd_exit(); } EXPORT_SYMBOL_GPL(kvm_exit); |