From 84a1ed5e67565b09b8fd22a26754d2897de55ce0 Mon Sep 17 00:00:00 2001 From: Francois Dugast Date: Thu, 22 Feb 2024 18:23:56 -0500 Subject: drm/xe/uapi: Remove unused flags MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Those cases missed in previous uAPI cleanups were mostly accidentally brought in from i915 or created to exercise the possibilities of gpuvm but they are not used by userspace yet, so let's remove them. They can still be brought back later if needed. v2: - Fix XE_VM_FLAG_FAULT_MODE support in xe_lrc.c (Brian Welty) - Leave DRM_XE_VM_BIND_OP_UNMAP_ALL (José Roberto de Souza) - Ensure invalid flag values are rejected (Rodrigo Vivi) v3: Rebase after removal of persistent exec_queues (Francois Dugast) v4: Rodrigo: Rebase after the new dumpable flag. Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs") Cc: Thomas Hellström Cc: Rodrigo Vivi Signed-off-by: Francois Dugast Reviewed-by: Rodrigo Vivi Signed-off-by: Rodrigo Vivi Link: https://patchwork.freedesktop.org/patch/msgid/20240222232356.175431-1-rodrigo.vivi@intel.com --- include/uapi/drm/xe_drm.h | 19 ------------------- 1 file changed, 19 deletions(-) (limited to 'include') diff --git a/include/uapi/drm/xe_drm.h b/include/uapi/drm/xe_drm.h index 2fefec9c0e94..538a3ac95c54 100644 --- a/include/uapi/drm/xe_drm.h +++ b/include/uapi/drm/xe_drm.h @@ -862,10 +862,6 @@ struct drm_xe_vm_destroy { * - %DRM_XE_VM_BIND_OP_PREFETCH * * and the @flags can be: - * - %DRM_XE_VM_BIND_FLAG_READONLY - * - %DRM_XE_VM_BIND_FLAG_IMMEDIATE - Valid on a faulting VM only, do the - * MAP operation immediately rather than deferring the MAP to the page - * fault handler. * - %DRM_XE_VM_BIND_FLAG_NULL - When the NULL flag is set, the page * tables are setup with a special bit which indicates writes are * dropped and all reads return zero. In the future, the NULL flags @@ -958,8 +954,6 @@ struct drm_xe_vm_bind_op { /** @op: Bind operation to perform */ __u32 op; -#define DRM_XE_VM_BIND_FLAG_READONLY (1 << 0) -#define DRM_XE_VM_BIND_FLAG_IMMEDIATE (1 << 1) #define DRM_XE_VM_BIND_FLAG_NULL (1 << 2) #define DRM_XE_VM_BIND_FLAG_DUMPABLE (1 << 3) /** @flags: Bind flags */ @@ -1076,19 +1070,6 @@ struct drm_xe_exec_queue_create { #define DRM_XE_EXEC_QUEUE_EXTENSION_SET_PROPERTY 0 #define DRM_XE_EXEC_QUEUE_SET_PROPERTY_PRIORITY 0 #define DRM_XE_EXEC_QUEUE_SET_PROPERTY_TIMESLICE 1 -#define DRM_XE_EXEC_QUEUE_SET_PROPERTY_PREEMPTION_TIMEOUT 2 -#define DRM_XE_EXEC_QUEUE_SET_PROPERTY_JOB_TIMEOUT 4 -#define DRM_XE_EXEC_QUEUE_SET_PROPERTY_ACC_TRIGGER 5 -#define DRM_XE_EXEC_QUEUE_SET_PROPERTY_ACC_NOTIFY 6 -#define DRM_XE_EXEC_QUEUE_SET_PROPERTY_ACC_GRANULARITY 7 -/* Monitor 128KB contiguous region with 4K sub-granularity */ -#define DRM_XE_ACC_GRANULARITY_128K 0 -/* Monitor 2MB contiguous region with 64KB sub-granularity */ -#define DRM_XE_ACC_GRANULARITY_2M 1 -/* Monitor 16MB contiguous region with 512KB sub-granularity */ -#define DRM_XE_ACC_GRANULARITY_16M 2 -/* Monitor 64MB contiguous region with 2M sub-granularity */ -#define DRM_XE_ACC_GRANULARITY_64M 3 /** @extensions: Pointer to the first extension struct, if any */ __u64 extensions; -- cgit v1.2.3 From b2121f2bd2232cd0556b2182078d159d81497885 Mon Sep 17 00:00:00 2001 From: Francois Dugast Date: Thu, 8 Feb 2024 10:35:39 -0800 Subject: drm/xe: Extend uAPI to query HuC micro-controler firmware version MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The infrastructure to query GuC firmware version is already in place. It is extended with a new micro-controller type to query the HuC firmware version. It can be used from user space to know if HuC is running. Cc: John Harrison Cc: Francois Dugast Cc: Lucas De Marchi Signed-off-by: Francois Dugast Signed-off-by: José Roberto de Souza Reviewed-by: Rodrigo Vivi Reviewed-by: John Harrison Link: https://patchwork.freedesktop.org/patch/msgid/20240208183539.185095-2-jose.souza@intel.com --- drivers/gpu/drm/xe/xe_query.c | 38 ++++++++++++++++++++++++++++++++++---- include/uapi/drm/xe_drm.h | 1 + 2 files changed, 35 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/xe/xe_query.c b/drivers/gpu/drm/xe/xe_query.c index f1876b556ab4..a6a20a6dd360 100644 --- a/drivers/gpu/drm/xe/xe_query.c +++ b/drivers/gpu/drm/xe/xe_query.c @@ -540,14 +540,44 @@ query_uc_fw_version(struct xe_device *xe, struct drm_xe_device_query *query) version = &guc->fw.versions.found[XE_UC_FW_VER_COMPATIBILITY]; break; } + case XE_QUERY_UC_TYPE_HUC: { + struct xe_gt *media_gt = NULL; + struct xe_huc *huc; + + if (MEDIA_VER(xe) >= 13) { + struct xe_tile *tile; + u8 gt_id; + + for_each_tile(tile, xe, gt_id) { + if (tile->media_gt) { + media_gt = tile->media_gt; + break; + } + } + } else { + media_gt = xe->tiles[0].primary_gt; + } + + if (!media_gt) + break; + + huc = &media_gt->uc.huc; + if (huc->fw.status == XE_UC_FIRMWARE_RUNNING) + version = &huc->fw.versions.found[XE_UC_FW_VER_RELEASE]; + break; + } default: return -EINVAL; } - resp.branch_ver = 0; - resp.major_ver = version->major; - resp.minor_ver = version->minor; - resp.patch_ver = version->patch; + if (version) { + resp.branch_ver = 0; + resp.major_ver = version->major; + resp.minor_ver = version->minor; + resp.patch_ver = version->patch; + } else { + return -ENODEV; + } if (copy_to_user(query_ptr, &resp, size)) return -EFAULT; diff --git a/include/uapi/drm/xe_drm.h b/include/uapi/drm/xe_drm.h index 538a3ac95c54..2fc19177d2b0 100644 --- a/include/uapi/drm/xe_drm.h +++ b/include/uapi/drm/xe_drm.h @@ -583,6 +583,7 @@ struct drm_xe_query_engine_cycles { struct drm_xe_query_uc_fw_version { /** @uc_type: The micro-controller type to query firmware version */ #define XE_QUERY_UC_TYPE_GUC_SUBMISSION 0 +#define XE_QUERY_UC_TYPE_HUC 1 __u16 uc_type; /** @pad: MBZ */ -- cgit v1.2.3 From 0f25e493a2462dbdd2e34f4e100405380cc0201a Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 29 Feb 2024 17:22:15 +0100 Subject: drm/panthor: Add uAPI Panthor follows the lead of other recently submitted drivers with ioctls allowing us to support modern Vulkan features, like sparse memory binding: - Pretty standard GEM management ioctls (BO_CREATE and BO_MMAP_OFFSET), with the 'exclusive-VM' bit to speed-up BO reservation on job submission - VM management ioctls (VM_CREATE, VM_DESTROY and VM_BIND). The VM_BIND ioctl is loosely based on the Xe model, and can handle both asynchronous and synchronous requests - GPU execution context creation/destruction, tiler heap context creation and job submission. Those ioctls reflect how the hardware/scheduler works and are thus driver specific. We also have a way to expose IO regions, such that the usermode driver can directly access specific/well-isolate registers, like the LATEST_FLUSH register used to implement cache-flush reduction. This uAPI intentionally keeps usermode queues out of the scope, which explains why doorbell registers and command stream ring-buffers are not directly exposed to userspace. v6: - Add Maxime's and Heiko's acks v5: - Fix typo - Add Liviu's R-b v4: - Add a VM_GET_STATE ioctl - Fix doc - Expose the CORE_FEATURES register so we can deal with variants in the UMD - Add Steve's R-b v3: - Add the concept of sync-only VM operation - Fix support for 32-bit userspace - Rework drm_panthor_vm_create to pass the user VA size instead of the kernel VA size (suggested by Robin Murphy) - Typo fixes - Explicitly cast enums with top bit set to avoid compiler warnings in -pedantic mode. - Drop property core_group_count as it can be easily calculated by the number of bits set in l2_present. Co-developed-by: Steven Price Signed-off-by: Steven Price Signed-off-by: Boris Brezillon Reviewed-by: Steven Price Reviewed-by: Liviu Dudau Acked-by: Maxime Ripard Acked-by: Heiko Stuebner Link: https://patchwork.freedesktop.org/patch/msgid/20240229162230.2634044-2-boris.brezillon@collabora.com --- Documentation/gpu/driver-uapi.rst | 5 + include/uapi/drm/panthor_drm.h | 945 ++++++++++++++++++++++++++++++++++++++ 2 files changed, 950 insertions(+) create mode 100644 include/uapi/drm/panthor_drm.h (limited to 'include') diff --git a/Documentation/gpu/driver-uapi.rst b/Documentation/gpu/driver-uapi.rst index e5070a0e95ab..971cdb4816fc 100644 --- a/Documentation/gpu/driver-uapi.rst +++ b/Documentation/gpu/driver-uapi.rst @@ -18,6 +18,11 @@ VM_BIND / EXEC uAPI .. kernel-doc:: include/uapi/drm/nouveau_drm.h +drm/panthor uAPI +================ + +.. kernel-doc:: include/uapi/drm/panthor_drm.h + drm/xe uAPI =========== diff --git a/include/uapi/drm/panthor_drm.h b/include/uapi/drm/panthor_drm.h new file mode 100644 index 000000000000..373df80f41ed --- /dev/null +++ b/include/uapi/drm/panthor_drm.h @@ -0,0 +1,945 @@ +/* SPDX-License-Identifier: MIT */ +/* Copyright (C) 2023 Collabora ltd. */ +#ifndef _PANTHOR_DRM_H_ +#define _PANTHOR_DRM_H_ + +#include "drm.h" + +#if defined(__cplusplus) +extern "C" { +#endif + +/** + * DOC: Introduction + * + * This documentation describes the Panthor IOCTLs. + * + * Just a few generic rules about the data passed to the Panthor IOCTLs: + * + * - Structures must be aligned on 64-bit/8-byte. If the object is not + * naturally aligned, a padding field must be added. + * - Fields must be explicitly aligned to their natural type alignment with + * pad[0..N] fields. + * - All padding fields will be checked by the driver to make sure they are + * zeroed. + * - Flags can be added, but not removed/replaced. + * - New fields can be added to the main structures (the structures + * directly passed to the ioctl). Those fields can be added at the end of + * the structure, or replace existing padding fields. Any new field being + * added must preserve the behavior that existed before those fields were + * added when a value of zero is passed. + * - New fields can be added to indirect objects (objects pointed by the + * main structure), iff those objects are passed a size to reflect the + * size known by the userspace driver (see drm_panthor_obj_array::stride + * or drm_panthor_dev_query::size). + * - If the kernel driver is too old to know some fields, those will be + * ignored if zero, and otherwise rejected (and so will be zero on output). + * - If userspace is too old to know some fields, those will be zeroed + * (input) before the structure is parsed by the kernel driver. + * - Each new flag/field addition must come with a driver version update so + * the userspace driver doesn't have to trial and error to know which + * flags are supported. + * - Structures should not contain unions, as this would defeat the + * extensibility of such structures. + * - IOCTLs can't be removed or replaced. New IOCTL IDs should be placed + * at the end of the drm_panthor_ioctl_id enum. + */ + +/** + * DOC: MMIO regions exposed to userspace. + * + * .. c:macro:: DRM_PANTHOR_USER_MMIO_OFFSET + * + * File offset for all MMIO regions being exposed to userspace. Don't use + * this value directly, use DRM_PANTHOR_USER__OFFSET values instead. + * pgoffset passed to mmap2() is an unsigned long, which forces us to use a + * different offset on 32-bit and 64-bit systems. + * + * .. c:macro:: DRM_PANTHOR_USER_FLUSH_ID_MMIO_OFFSET + * + * File offset for the LATEST_FLUSH_ID register. The Userspace driver controls + * GPU cache flushing through CS instructions, but the flush reduction + * mechanism requires a flush_id. This flush_id could be queried with an + * ioctl, but Arm provides a well-isolated register page containing only this + * read-only register, so let's expose this page through a static mmap offset + * and allow direct mapping of this MMIO region so we can avoid the + * user <-> kernel round-trip. + */ +#define DRM_PANTHOR_USER_MMIO_OFFSET_32BIT (1ull << 43) +#define DRM_PANTHOR_USER_MMIO_OFFSET_64BIT (1ull << 56) +#define DRM_PANTHOR_USER_MMIO_OFFSET (sizeof(unsigned long) < 8 ? \ + DRM_PANTHOR_USER_MMIO_OFFSET_32BIT : \ + DRM_PANTHOR_USER_MMIO_OFFSET_64BIT) +#define DRM_PANTHOR_USER_FLUSH_ID_MMIO_OFFSET (DRM_PANTHOR_USER_MMIO_OFFSET | 0) + +/** + * DOC: IOCTL IDs + * + * enum drm_panthor_ioctl_id - IOCTL IDs + * + * Place new ioctls at the end, don't re-order, don't replace or remove entries. + * + * These IDs are not meant to be used directly. Use the DRM_IOCTL_PANTHOR_xxx + * definitions instead. + */ +enum drm_panthor_ioctl_id { + /** @DRM_PANTHOR_DEV_QUERY: Query device information. */ + DRM_PANTHOR_DEV_QUERY = 0, + + /** @DRM_PANTHOR_VM_CREATE: Create a VM. */ + DRM_PANTHOR_VM_CREATE, + + /** @DRM_PANTHOR_VM_DESTROY: Destroy a VM. */ + DRM_PANTHOR_VM_DESTROY, + + /** @DRM_PANTHOR_VM_BIND: Bind/unbind memory to a VM. */ + DRM_PANTHOR_VM_BIND, + + /** @DRM_PANTHOR_VM_GET_STATE: Get VM state. */ + DRM_PANTHOR_VM_GET_STATE, + + /** @DRM_PANTHOR_BO_CREATE: Create a buffer object. */ + DRM_PANTHOR_BO_CREATE, + + /** + * @DRM_PANTHOR_BO_MMAP_OFFSET: Get the file offset to pass to + * mmap to map a GEM object. + */ + DRM_PANTHOR_BO_MMAP_OFFSET, + + /** @DRM_PANTHOR_GROUP_CREATE: Create a scheduling group. */ + DRM_PANTHOR_GROUP_CREATE, + + /** @DRM_PANTHOR_GROUP_DESTROY: Destroy a scheduling group. */ + DRM_PANTHOR_GROUP_DESTROY, + + /** + * @DRM_PANTHOR_GROUP_SUBMIT: Submit jobs to queues belonging + * to a specific scheduling group. + */ + DRM_PANTHOR_GROUP_SUBMIT, + + /** @DRM_PANTHOR_GROUP_GET_STATE: Get the state of a scheduling group. */ + DRM_PANTHOR_GROUP_GET_STATE, + + /** @DRM_PANTHOR_TILER_HEAP_CREATE: Create a tiler heap. */ + DRM_PANTHOR_TILER_HEAP_CREATE, + + /** @DRM_PANTHOR_TILER_HEAP_DESTROY: Destroy a tiler heap. */ + DRM_PANTHOR_TILER_HEAP_DESTROY, +}; + +/** + * DRM_IOCTL_PANTHOR() - Build a Panthor IOCTL number + * @__access: Access type. Must be R, W or RW. + * @__id: One of the DRM_PANTHOR_xxx id. + * @__type: Suffix of the type being passed to the IOCTL. + * + * Don't use this macro directly, use the DRM_IOCTL_PANTHOR_xxx + * values instead. + * + * Return: An IOCTL number to be passed to ioctl() from userspace. + */ +#define DRM_IOCTL_PANTHOR(__access, __id, __type) \ + DRM_IO ## __access(DRM_COMMAND_BASE + DRM_PANTHOR_ ## __id, \ + struct drm_panthor_ ## __type) + +#define DRM_IOCTL_PANTHOR_DEV_QUERY \ + DRM_IOCTL_PANTHOR(WR, DEV_QUERY, dev_query) +#define DRM_IOCTL_PANTHOR_VM_CREATE \ + DRM_IOCTL_PANTHOR(WR, VM_CREATE, vm_create) +#define DRM_IOCTL_PANTHOR_VM_DESTROY \ + DRM_IOCTL_PANTHOR(WR, VM_DESTROY, vm_destroy) +#define DRM_IOCTL_PANTHOR_VM_BIND \ + DRM_IOCTL_PANTHOR(WR, VM_BIND, vm_bind) +#define DRM_IOCTL_PANTHOR_VM_GET_STATE \ + DRM_IOCTL_PANTHOR(WR, VM_GET_STATE, vm_get_state) +#define DRM_IOCTL_PANTHOR_BO_CREATE \ + DRM_IOCTL_PANTHOR(WR, BO_CREATE, bo_create) +#define DRM_IOCTL_PANTHOR_BO_MMAP_OFFSET \ + DRM_IOCTL_PANTHOR(WR, BO_MMAP_OFFSET, bo_mmap_offset) +#define DRM_IOCTL_PANTHOR_GROUP_CREATE \ + DRM_IOCTL_PANTHOR(WR, GROUP_CREATE, group_create) +#define DRM_IOCTL_PANTHOR_GROUP_DESTROY \ + DRM_IOCTL_PANTHOR(WR, GROUP_DESTROY, group_destroy) +#define DRM_IOCTL_PANTHOR_GROUP_SUBMIT \ + DRM_IOCTL_PANTHOR(WR, GROUP_SUBMIT, group_submit) +#define DRM_IOCTL_PANTHOR_GROUP_GET_STATE \ + DRM_IOCTL_PANTHOR(WR, GROUP_GET_STATE, group_get_state) +#define DRM_IOCTL_PANTHOR_TILER_HEAP_CREATE \ + DRM_IOCTL_PANTHOR(WR, TILER_HEAP_CREATE, tiler_heap_create) +#define DRM_IOCTL_PANTHOR_TILER_HEAP_DESTROY \ + DRM_IOCTL_PANTHOR(WR, TILER_HEAP_DESTROY, tiler_heap_destroy) + +/** + * DOC: IOCTL arguments + */ + +/** + * struct drm_panthor_obj_array - Object array. + * + * This object is used to pass an array of objects whose size is subject to changes in + * future versions of the driver. In order to support this mutability, we pass a stride + * describing the size of the object as known by userspace. + * + * You shouldn't fill drm_panthor_obj_array fields directly. You should instead use + * the DRM_PANTHOR_OBJ_ARRAY() macro that takes care of initializing the stride to + * the object size. + */ +struct drm_panthor_obj_array { + /** @stride: Stride of object struct. Used for versioning. */ + __u32 stride; + + /** @count: Number of objects in the array. */ + __u32 count; + + /** @array: User pointer to an array of objects. */ + __u64 array; +}; + +/** + * DRM_PANTHOR_OBJ_ARRAY() - Initialize a drm_panthor_obj_array field. + * @cnt: Number of elements in the array. + * @ptr: Pointer to the array to pass to the kernel. + * + * Macro initializing a drm_panthor_obj_array based on the object size as known + * by userspace. + */ +#define DRM_PANTHOR_OBJ_ARRAY(cnt, ptr) \ + { .stride = sizeof((ptr)[0]), .count = (cnt), .array = (__u64)(uintptr_t)(ptr) } + +/** + * enum drm_panthor_sync_op_flags - Synchronization operation flags. + */ +enum drm_panthor_sync_op_flags { + /** @DRM_PANTHOR_SYNC_OP_HANDLE_TYPE_MASK: Synchronization handle type mask. */ + DRM_PANTHOR_SYNC_OP_HANDLE_TYPE_MASK = 0xff, + + /** @DRM_PANTHOR_SYNC_OP_HANDLE_TYPE_SYNCOBJ: Synchronization object type. */ + DRM_PANTHOR_SYNC_OP_HANDLE_TYPE_SYNCOBJ = 0, + + /** + * @DRM_PANTHOR_SYNC_OP_HANDLE_TYPE_TIMELINE_SYNCOBJ: Timeline synchronization + * object type. + */ + DRM_PANTHOR_SYNC_OP_HANDLE_TYPE_TIMELINE_SYNCOBJ = 1, + + /** @DRM_PANTHOR_SYNC_OP_WAIT: Wait operation. */ + DRM_PANTHOR_SYNC_OP_WAIT = 0 << 31, + + /** @DRM_PANTHOR_SYNC_OP_SIGNAL: Signal operation. */ + DRM_PANTHOR_SYNC_OP_SIGNAL = (int)(1u << 31), +}; + +/** + * struct drm_panthor_sync_op - Synchronization operation. + */ +struct drm_panthor_sync_op { + /** @flags: Synchronization operation flags. Combination of DRM_PANTHOR_SYNC_OP values. */ + __u32 flags; + + /** @handle: Sync handle. */ + __u32 handle; + + /** + * @timeline_value: MBZ if + * (flags & DRM_PANTHOR_SYNC_OP_HANDLE_TYPE_MASK) != + * DRM_PANTHOR_SYNC_OP_HANDLE_TYPE_TIMELINE_SYNCOBJ. + */ + __u64 timeline_value; +}; + +/** + * enum drm_panthor_dev_query_type - Query type + * + * Place new types at the end, don't re-order, don't remove or replace. + */ +enum drm_panthor_dev_query_type { + /** @DRM_PANTHOR_DEV_QUERY_GPU_INFO: Query GPU information. */ + DRM_PANTHOR_DEV_QUERY_GPU_INFO = 0, + + /** @DRM_PANTHOR_DEV_QUERY_CSIF_INFO: Query command-stream interface information. */ + DRM_PANTHOR_DEV_QUERY_CSIF_INFO, +}; + +/** + * struct drm_panthor_gpu_info - GPU information + * + * Structure grouping all queryable information relating to the GPU. + */ +struct drm_panthor_gpu_info { + /** @gpu_id : GPU ID. */ + __u32 gpu_id; +#define DRM_PANTHOR_ARCH_MAJOR(x) ((x) >> 28) +#define DRM_PANTHOR_ARCH_MINOR(x) (((x) >> 24) & 0xf) +#define DRM_PANTHOR_ARCH_REV(x) (((x) >> 20) & 0xf) +#define DRM_PANTHOR_PRODUCT_MAJOR(x) (((x) >> 16) & 0xf) +#define DRM_PANTHOR_VERSION_MAJOR(x) (((x) >> 12) & 0xf) +#define DRM_PANTHOR_VERSION_MINOR(x) (((x) >> 4) & 0xff) +#define DRM_PANTHOR_VERSION_STATUS(x) ((x) & 0xf) + + /** @gpu_rev: GPU revision. */ + __u32 gpu_rev; + + /** @csf_id: Command stream frontend ID. */ + __u32 csf_id; +#define DRM_PANTHOR_CSHW_MAJOR(x) (((x) >> 26) & 0x3f) +#define DRM_PANTHOR_CSHW_MINOR(x) (((x) >> 20) & 0x3f) +#define DRM_PANTHOR_CSHW_REV(x) (((x) >> 16) & 0xf) +#define DRM_PANTHOR_MCU_MAJOR(x) (((x) >> 10) & 0x3f) +#define DRM_PANTHOR_MCU_MINOR(x) (((x) >> 4) & 0x3f) +#define DRM_PANTHOR_MCU_REV(x) ((x) & 0xf) + + /** @l2_features: L2-cache features. */ + __u32 l2_features; + + /** @tiler_features: Tiler features. */ + __u32 tiler_features; + + /** @mem_features: Memory features. */ + __u32 mem_features; + + /** @mmu_features: MMU features. */ + __u32 mmu_features; +#define DRM_PANTHOR_MMU_VA_BITS(x) ((x) & 0xff) + + /** @thread_features: Thread features. */ + __u32 thread_features; + + /** @max_threads: Maximum number of threads. */ + __u32 max_threads; + + /** @thread_max_workgroup_size: Maximum workgroup size. */ + __u32 thread_max_workgroup_size; + + /** + * @thread_max_barrier_size: Maximum number of threads that can wait + * simultaneously on a barrier. + */ + __u32 thread_max_barrier_size; + + /** @coherency_features: Coherency features. */ + __u32 coherency_features; + + /** @texture_features: Texture features. */ + __u32 texture_features[4]; + + /** @as_present: Bitmask encoding the number of address-space exposed by the MMU. */ + __u32 as_present; + + /** @shader_present: Bitmask encoding the shader cores exposed by the GPU. */ + __u64 shader_present; + + /** @l2_present: Bitmask encoding the L2 caches exposed by the GPU. */ + __u64 l2_present; + + /** @tiler_present: Bitmask encoding the tiler units exposed by the GPU. */ + __u64 tiler_present; + + /* @core_features: Used to discriminate core variants when they exist. */ + __u32 core_features; + + /* @pad: MBZ. */ + __u32 pad; +}; + +/** + * struct drm_panthor_csif_info - Command stream interface information + * + * Structure grouping all queryable information relating to the command stream interface. + */ +struct drm_panthor_csif_info { + /** @csg_slot_count: Number of command stream group slots exposed by the firmware. */ + __u32 csg_slot_count; + + /** @cs_slot_count: Number of command stream slots per group. */ + __u32 cs_slot_count; + + /** @cs_reg_count: Number of command stream registers. */ + __u32 cs_reg_count; + + /** @scoreboard_slot_count: Number of scoreboard slots. */ + __u32 scoreboard_slot_count; + + /** + * @unpreserved_cs_reg_count: Number of command stream registers reserved by + * the kernel driver to call a userspace command stream. + * + * All registers can be used by a userspace command stream, but the + * [cs_slot_count - unpreserved_cs_reg_count .. cs_slot_count] registers are + * used by the kernel when DRM_PANTHOR_IOCTL_GROUP_SUBMIT is called. + */ + __u32 unpreserved_cs_reg_count; + + /** + * @pad: Padding field, set to zero. + */ + __u32 pad; +}; + +/** + * struct drm_panthor_dev_query - Arguments passed to DRM_PANTHOR_IOCTL_DEV_QUERY + */ +struct drm_panthor_dev_query { + /** @type: the query type (see drm_panthor_dev_query_type). */ + __u32 type; + + /** + * @size: size of the type being queried. + * + * If pointer is NULL, size is updated by the driver to provide the + * output structure size. If pointer is not NULL, the driver will + * only copy min(size, actual_structure_size) bytes to the pointer, + * and update the size accordingly. This allows us to extend query + * types without breaking userspace. + */ + __u32 size; + + /** + * @pointer: user pointer to a query type struct. + * + * Pointer can be NULL, in which case, nothing is copied, but the + * actual structure size is returned. If not NULL, it must point to + * a location that's large enough to hold size bytes. + */ + __u64 pointer; +}; + +/** + * struct drm_panthor_vm_create - Arguments passed to DRM_PANTHOR_IOCTL_VM_CREATE + */ +struct drm_panthor_vm_create { + /** @flags: VM flags, MBZ. */ + __u32 flags; + + /** @id: Returned VM ID. */ + __u32 id; + + /** + * @user_va_range: Size of the VA space reserved for user objects. + * + * The kernel will pick the remaining space to map kernel-only objects to the + * VM (heap chunks, heap context, ring buffers, kernel synchronization objects, + * ...). If the space left for kernel objects is too small, kernel object + * allocation will fail further down the road. One can use + * drm_panthor_gpu_info::mmu_features to extract the total virtual address + * range, and chose a user_va_range that leaves some space to the kernel. + * + * If user_va_range is zero, the kernel will pick a sensible value based on + * TASK_SIZE and the virtual range supported by the GPU MMU (the kernel/user + * split should leave enough VA space for userspace processes to support SVM, + * while still allowing the kernel to map some amount of kernel objects in + * the kernel VA range). The value chosen by the driver will be returned in + * @user_va_range. + * + * User VA space always starts at 0x0, kernel VA space is always placed after + * the user VA range. + */ + __u64 user_va_range; +}; + +/** + * struct drm_panthor_vm_destroy - Arguments passed to DRM_PANTHOR_IOCTL_VM_DESTROY + */ +struct drm_panthor_vm_destroy { + /** @id: ID of the VM to destroy. */ + __u32 id; + + /** @pad: MBZ. */ + __u32 pad; +}; + +/** + * enum drm_panthor_vm_bind_op_flags - VM bind operation flags + */ +enum drm_panthor_vm_bind_op_flags { + /** + * @DRM_PANTHOR_VM_BIND_OP_MAP_READONLY: Map the memory read-only. + * + * Only valid with DRM_PANTHOR_VM_BIND_OP_TYPE_MAP. + */ + DRM_PANTHOR_VM_BIND_OP_MAP_READONLY = 1 << 0, + + /** + * @DRM_PANTHOR_VM_BIND_OP_MAP_NOEXEC: Map the memory not-executable. + * + * Only valid with DRM_PANTHOR_VM_BIND_OP_TYPE_MAP. + */ + DRM_PANTHOR_VM_BIND_OP_MAP_NOEXEC = 1 << 1, + + /** + * @DRM_PANTHOR_VM_BIND_OP_MAP_UNCACHED: Map the memory uncached. + * + * Only valid with DRM_PANTHOR_VM_BIND_OP_TYPE_MAP. + */ + DRM_PANTHOR_VM_BIND_OP_MAP_UNCACHED = 1 << 2, + + /** + * @DRM_PANTHOR_VM_BIND_OP_TYPE_MASK: Mask used to determine the type of operation. + */ + DRM_PANTHOR_VM_BIND_OP_TYPE_MASK = (int)(0xfu << 28), + + /** @DRM_PANTHOR_VM_BIND_OP_TYPE_MAP: Map operation. */ + DRM_PANTHOR_VM_BIND_OP_TYPE_MAP = 0 << 28, + + /** @DRM_PANTHOR_VM_BIND_OP_TYPE_UNMAP: Unmap operation. */ + DRM_PANTHOR_VM_BIND_OP_TYPE_UNMAP = 1 << 28, + + /** + * @DRM_PANTHOR_VM_BIND_OP_TYPE_SYNC_ONLY: No VM operation. + * + * Just serves as a synchronization point on a VM queue. + * + * Only valid if %DRM_PANTHOR_VM_BIND_ASYNC is set in drm_panthor_vm_bind::flags, + * and drm_panthor_vm_bind_op::syncs contains at least one element. + */ + DRM_PANTHOR_VM_BIND_OP_TYPE_SYNC_ONLY = 2 << 28, +}; + +/** + * struct drm_panthor_vm_bind_op - VM bind operation + */ +struct drm_panthor_vm_bind_op { + /** @flags: Combination of drm_panthor_vm_bind_op_flags flags. */ + __u32 flags; + + /** + * @bo_handle: Handle of the buffer object to map. + * MBZ for unmap or sync-only operations. + */ + __u32 bo_handle; + + /** + * @bo_offset: Buffer object offset. + * MBZ for unmap or sync-only operations. + */ + __u64 bo_offset; + + /** + * @va: Virtual address to map/unmap. + * MBZ for sync-only operations. + */ + __u64 va; + + /** + * @size: Size to map/unmap. + * MBZ for sync-only operations. + */ + __u64 size; + + /** + * @syncs: Array of struct drm_panthor_sync_op synchronization + * operations. + * + * This array must be empty if %DRM_PANTHOR_VM_BIND_ASYNC is not set on + * the drm_panthor_vm_bind object containing this VM bind operation. + * + * This array shall not be empty for sync-only operations. + */ + struct drm_panthor_obj_array syncs; + +}; + +/** + * enum drm_panthor_vm_bind_flags - VM bind flags + */ +enum drm_panthor_vm_bind_flags { + /** + * @DRM_PANTHOR_VM_BIND_ASYNC: VM bind operations are queued to the VM + * queue instead of being executed synchronously. + */ + DRM_PANTHOR_VM_BIND_ASYNC = 1 << 0, +}; + +/** + * struct drm_panthor_vm_bind - Arguments passed to DRM_IOCTL_PANTHOR_VM_BIND + */ +struct drm_panthor_vm_bind { + /** @vm_id: VM targeted by the bind request. */ + __u32 vm_id; + + /** @flags: Combination of drm_panthor_vm_bind_flags flags. */ + __u32 flags; + + /** @ops: Array of struct drm_panthor_vm_bind_op bind operations. */ + struct drm_panthor_obj_array ops; +}; + +/** + * enum drm_panthor_vm_state - VM states. + */ +enum drm_panthor_vm_state { + /** + * @DRM_PANTHOR_VM_STATE_USABLE: VM is usable. + * + * New VM operations will be accepted on this VM. + */ + DRM_PANTHOR_VM_STATE_USABLE, + + /** + * @DRM_PANTHOR_VM_STATE_UNUSABLE: VM is unusable. + * + * Something put the VM in an unusable state (like an asynchronous + * VM_BIND request failing for any reason). + * + * Once the VM is in this state, all new MAP operations will be + * rejected, and any GPU job targeting this VM will fail. + * UNMAP operations are still accepted. + * + * The only way to recover from an unusable VM is to create a new + * VM, and destroy the old one. + */ + DRM_PANTHOR_VM_STATE_UNUSABLE, +}; + +/** + * struct drm_panthor_vm_get_state - Get VM state. + */ +struct drm_panthor_vm_get_state { + /** @vm_id: VM targeted by the get_state request. */ + __u32 vm_id; + + /** + * @state: state returned by the driver. + * + * Must be one of the enum drm_panthor_vm_state values. + */ + __u32 state; +}; + +/** + * enum drm_panthor_bo_flags - Buffer object flags, passed at creation time. + */ +enum drm_panthor_bo_flags { + /** @DRM_PANTHOR_BO_NO_MMAP: The buffer object will never be CPU-mapped in userspace. */ + DRM_PANTHOR_BO_NO_MMAP = (1 << 0), +}; + +/** + * struct drm_panthor_bo_create - Arguments passed to DRM_IOCTL_PANTHOR_BO_CREATE. + */ +struct drm_panthor_bo_create { + /** + * @size: Requested size for the object + * + * The (page-aligned) allocated size for the object will be returned. + */ + __u64 size; + + /** + * @flags: Flags. Must be a combination of drm_panthor_bo_flags flags. + */ + __u32 flags; + + /** + * @exclusive_vm_id: Exclusive VM this buffer object will be mapped to. + * + * If not zero, the field must refer to a valid VM ID, and implies that: + * - the buffer object will only ever be bound to that VM + * - cannot be exported as a PRIME fd + */ + __u32 exclusive_vm_id; + + /** + * @handle: Returned handle for the object. + * + * Object handles are nonzero. + */ + __u32 handle; + + /** @pad: MBZ. */ + __u32 pad; +}; + +/** + * struct drm_panthor_bo_mmap_offset - Arguments passed to DRM_IOCTL_PANTHOR_BO_MMAP_OFFSET. + */ +struct drm_panthor_bo_mmap_offset { + /** @handle: Handle of the object we want an mmap offset for. */ + __u32 handle; + + /** @pad: MBZ. */ + __u32 pad; + + /** @offset: The fake offset to use for subsequent mmap calls. */ + __u64 offset; +}; + +/** + * struct drm_panthor_queue_create - Queue creation arguments. + */ +struct drm_panthor_queue_create { + /** + * @priority: Defines the priority of queues inside a group. Goes from 0 to 15, + * 15 being the highest priority. + */ + __u8 priority; + + /** @pad: Padding fields, MBZ. */ + __u8 pad[3]; + + /** @ringbuf_size: Size of the ring buffer to allocate to this queue. */ + __u32 ringbuf_size; +}; + +/** + * enum drm_panthor_group_priority - Scheduling group priority + */ +enum drm_panthor_group_priority { + /** @PANTHOR_GROUP_PRIORITY_LOW: Low priority group. */ + PANTHOR_GROUP_PRIORITY_LOW = 0, + + /** @PANTHOR_GROUP_PRIORITY_MEDIUM: Medium priority group. */ + PANTHOR_GROUP_PRIORITY_MEDIUM, + + /** @PANTHOR_GROUP_PRIORITY_HIGH: High priority group. */ + PANTHOR_GROUP_PRIORITY_HIGH, +}; + +/** + * struct drm_panthor_group_create - Arguments passed to DRM_IOCTL_PANTHOR_GROUP_CREATE + */ +struct drm_panthor_group_create { + /** @queues: Array of drm_panthor_queue_create elements. */ + struct drm_panthor_obj_array queues; + + /** + * @max_compute_cores: Maximum number of cores that can be used by compute + * jobs across CS queues bound to this group. + * + * Must be less or equal to the number of bits set in @compute_core_mask. + */ + __u8 max_compute_cores; + + /** + * @max_fragment_cores: Maximum number of cores that can be used by fragment + * jobs across CS queues bound to this group. + * + * Must be less or equal to the number of bits set in @fragment_core_mask. + */ + __u8 max_fragment_cores; + + /** + * @max_tiler_cores: Maximum number of tilers that can be used by tiler jobs + * across CS queues bound to this group. + * + * Must be less or equal to the number of bits set in @tiler_core_mask. + */ + __u8 max_tiler_cores; + + /** @priority: Group priority (see enum drm_panthor_group_priority). */ + __u8 priority; + + /** @pad: Padding field, MBZ. */ + __u32 pad; + + /** + * @compute_core_mask: Mask encoding cores that can be used for compute jobs. + * + * This field must have at least @max_compute_cores bits set. + * + * The bits set here should also be set in drm_panthor_gpu_info::shader_present. + */ + __u64 compute_core_mask; + + /** + * @fragment_core_mask: Mask encoding cores that can be used for fragment jobs. + * + * This field must have at least @max_fragment_cores bits set. + * + * The bits set here should also be set in drm_panthor_gpu_info::shader_present. + */ + __u64 fragment_core_mask; + + /** + * @tiler_core_mask: Mask encoding cores that can be used for tiler jobs. + * + * This field must have at least @max_tiler_cores bits set. + * + * The bits set here should also be set in drm_panthor_gpu_info::tiler_present. + */ + __u64 tiler_core_mask; + + /** + * @vm_id: VM ID to bind this group to. + * + * All submission to queues bound to this group will use this VM. + */ + __u32 vm_id; + + /** + * @group_handle: Returned group handle. Passed back when submitting jobs or + * destroying a group. + */ + __u32 group_handle; +}; + +/** + * struct drm_panthor_group_destroy - Arguments passed to DRM_IOCTL_PANTHOR_GROUP_DESTROY + */ +struct drm_panthor_group_destroy { + /** @group_handle: Group to destroy */ + __u32 group_handle; + + /** @pad: Padding field, MBZ. */ + __u32 pad; +}; + +/** + * struct drm_panthor_queue_submit - Job submission arguments. + * + * This is describing the userspace command stream to call from the kernel + * command stream ring-buffer. Queue submission is always part of a group + * submission, taking one or more jobs to submit to the underlying queues. + */ +struct drm_panthor_queue_submit { + /** @queue_index: Index of the queue inside a group. */ + __u32 queue_index; + + /** + * @stream_size: Size of the command stream to execute. + * + * Must be 64-bit/8-byte aligned (the size of a CS instruction) + * + * Can be zero if stream_addr is zero too. + */ + __u32 stream_size; + + /** + * @stream_addr: GPU address of the command stream to execute. + * + * Must be aligned on 64-byte. + * + * Can be zero is stream_size is zero too. + */ + __u64 stream_addr; + + /** + * @latest_flush: FLUSH_ID read at the time the stream was built. + * + * This allows cache flush elimination for the automatic + * flush+invalidate(all) done at submission time, which is needed to + * ensure the GPU doesn't get garbage when reading the indirect command + * stream buffers. If you want the cache flush to happen + * unconditionally, pass a zero here. + */ + __u32 latest_flush; + + /** @pad: MBZ. */ + __u32 pad; + + /** @syncs: Array of struct drm_panthor_sync_op sync operations. */ + struct drm_panthor_obj_array syncs; +}; + +/** + * struct drm_panthor_group_submit - Arguments passed to DRM_IOCTL_PANTHOR_GROUP_SUBMIT + */ +struct drm_panthor_group_submit { + /** @group_handle: Handle of the group to queue jobs to. */ + __u32 group_handle; + + /** @pad: MBZ. */ + __u32 pad; + + /** @queue_submits: Array of drm_panthor_queue_submit objects. */ + struct drm_panthor_obj_array queue_submits; +}; + +/** + * enum drm_panthor_group_state_flags - Group state flags + */ +enum drm_panthor_group_state_flags { + /** + * @DRM_PANTHOR_GROUP_STATE_TIMEDOUT: Group had unfinished jobs. + * + * When a group ends up with this flag set, no jobs can be submitted to its queues. + */ + DRM_PANTHOR_GROUP_STATE_TIMEDOUT = 1 << 0, + + /** + * @DRM_PANTHOR_GROUP_STATE_FATAL_FAULT: Group had fatal faults. + * + * When a group ends up with this flag set, no jobs can be submitted to its queues. + */ + DRM_PANTHOR_GROUP_STATE_FATAL_FAULT = 1 << 1, +}; + +/** + * struct drm_panthor_group_get_state - Arguments passed to DRM_IOCTL_PANTHOR_GROUP_GET_STATE + * + * Used to query the state of a group and decide whether a new group should be created to + * replace it. + */ +struct drm_panthor_group_get_state { + /** @group_handle: Handle of the group to query state on */ + __u32 group_handle; + + /** + * @state: Combination of DRM_PANTHOR_GROUP_STATE_* flags encoding the + * group state. + */ + __u32 state; + + /** @fatal_queues: Bitmask of queues that faced fatal faults. */ + __u32 fatal_queues; + + /** @pad: MBZ */ + __u32 pad; +}; + +/** + * struct drm_panthor_tiler_heap_create - Arguments passed to DRM_IOCTL_PANTHOR_TILER_HEAP_CREATE + */ +struct drm_panthor_tiler_heap_create { + /** @vm_id: VM ID the tiler heap should be mapped to */ + __u32 vm_id; + + /** @initial_chunk_count: Initial number of chunks to allocate. */ + __u32 initial_chunk_count; + + /** @chunk_size: Chunk size. Must be a power of two at least 256KB large. */ + __u32 chunk_size; + + /** @max_chunks: Maximum number of chunks that can be allocated. */ + __u32 max_chunks; + + /** + * @target_in_flight: Maximum number of in-flight render passes. + * + * If the heap has more than tiler jobs in-flight, the FW will wait for render + * passes to finish before queuing new tiler jobs. + */ + __u32 target_in_flight; + + /** @handle: Returned heap handle. Passed back to DESTROY_TILER_HEAP. */ + __u32 handle; + + /** @tiler_heap_ctx_gpu_va: Returned heap GPU virtual address returned */ + __u64 tiler_heap_ctx_gpu_va; + + /** + * @first_heap_chunk_gpu_va: First heap chunk. + * + * The tiler heap is formed of heap chunks forming a single-link list. This + * is the first element in the list. + */ + __u64 first_heap_chunk_gpu_va; +}; + +/** + * struct drm_panthor_tiler_heap_destroy - Arguments passed to DRM_IOCTL_PANTHOR_TILER_HEAP_DESTROY + */ +struct drm_panthor_tiler_heap_destroy { + /** @handle: Handle of the tiler heap to destroy */ + __u32 handle; + + /** @pad: Padding field, MBZ. */ + __u32 pad; +}; + +#if defined(__cplusplus) +} +#endif + +#endif /* _PANTHOR_DRM_H_ */ -- cgit v1.2.3 From d10612f8303fab350d82f8b7d5793683af50ee3c Mon Sep 17 00:00:00 2001 From: Nirmoy Das Date: Thu, 29 Feb 2024 14:29:18 +0100 Subject: drm/i915: Add missing doc for drm_i915_reset_stats Add missing doc for struct drm_i915_reset_stats. Cc: Andi Shyti Signed-off-by: Nirmoy Das Reviewed-by: Andi Shyti Link: https://patchwork.freedesktop.org/patch/msgid/20240229132918.10205-1-nirmoy.das@intel.com --- include/uapi/drm/i915_drm.h | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h index bd87386a8243..fb195d3b3e9f 100644 --- a/include/uapi/drm/i915_drm.h +++ b/include/uapi/drm/i915_drm.h @@ -2623,19 +2623,29 @@ struct drm_i915_reg_read { * */ +/* + * struct drm_i915_reset_stats - Return global reset and other context stats + * + * Driver keeps few stats for each contexts and also global reset count. + * This struct can be used to query those stats. + */ struct drm_i915_reset_stats { + /** @ctx_id: ID of the requested context */ __u32 ctx_id; + + /** @flags: MBZ */ __u32 flags; - /* All resets since boot/module reload, for all contexts */ + /** @reset_count: All resets since boot/module reload, for all contexts */ __u32 reset_count; - /* Number of batches lost when active in GPU, for this context */ + /** @batch_active: Number of batches lost when active in GPU, for this context */ __u32 batch_active; - /* Number of batches lost pending for execution, for this context */ + /** @batch_pending: Number of batches lost pending for execution, for this context */ __u32 batch_pending; + /** @pad: MBZ */ __u32 pad; }; -- cgit v1.2.3 From cc941c70df3927be89dfb875a9b3cec3ef5cf2c8 Mon Sep 17 00:00:00 2001 From: Christian König Date: Wed, 6 Dec 2023 16:37:29 +0100 Subject: drm/ttm: improve idle/busy handling v5 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Previously we would never try to move a BO into the preferred placements when it ever landed in a busy placement since those were considered compatible. Rework the whole handling and finally unify the idle and busy handling. ttm_bo_validate() is now responsible to try idle placement first and then use the busy placement if that didn't worked. Drawback is that we now always try the idle placement first for each validation which might cause some additional CPU overhead on overcommit. v2: fix kerneldoc warning and coding style v3: take care of XE as well v4: keep the ttm_bo_mem_space functionality as it is for now, only add new handling for ttm_bo_validate as suggested by Thomas v5: fix bug pointed out by Matthew Signed-off-by: Christian König Reviewed-by: Zack Rusin v3 Link: https://patchwork.freedesktop.org/patch/msgid/20240229134003.3688-1-christian.koenig@amd.com Reviewed-by: Thomas Hellström --- drivers/gpu/drm/ttm/ttm_bo.c | 231 +++++++++++++++++-------------------- drivers/gpu/drm/ttm/ttm_resource.c | 16 ++- include/drm/ttm/ttm_resource.h | 3 +- 3 files changed, 121 insertions(+), 129 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index 96a724e8f3ff..e059b1e1b13b 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -724,64 +724,36 @@ static int ttm_bo_add_move_fence(struct ttm_buffer_object *bo, return ret; } -/* - * Repeatedly evict memory from the LRU for @mem_type until we create enough - * space, or we've evicted everything and there isn't enough space. - */ -static int ttm_bo_mem_force_space(struct ttm_buffer_object *bo, - const struct ttm_place *place, - struct ttm_resource **mem, - struct ttm_operation_ctx *ctx) -{ - struct ttm_device *bdev = bo->bdev; - struct ttm_resource_manager *man; - struct ww_acquire_ctx *ticket; - int ret; - - man = ttm_manager_type(bdev, place->mem_type); - ticket = dma_resv_locking_ctx(bo->base.resv); - do { - ret = ttm_resource_alloc(bo, place, mem); - if (likely(!ret)) - break; - if (unlikely(ret != -ENOSPC)) - return ret; - ret = ttm_mem_evict_first(bdev, man, place, ctx, - ticket); - if (unlikely(ret != 0)) - return ret; - } while (1); - - return ttm_bo_add_move_fence(bo, man, *mem, ctx->no_wait_gpu); -} - /** - * ttm_bo_mem_space + * ttm_bo_alloc_resource - Allocate backing store for a BO * - * @bo: Pointer to a struct ttm_buffer_object. the data of which - * we want to allocate space for. - * @placement: Proposed new placement for the buffer object. - * @mem: A struct ttm_resource. + * @bo: Pointer to a struct ttm_buffer_object of which we want a resource for + * @placement: Proposed new placement for the buffer object * @ctx: if and how to sleep, lock buffers and alloc memory + * @force_space: If we should evict buffers to force space + * @res: The resulting struct ttm_resource. * - * Allocate memory space for the buffer object pointed to by @bo, using - * the placement flags in @placement, potentially evicting other idle buffer objects. - * This function may sleep while waiting for space to become available. + * Allocates a resource for the buffer object pointed to by @bo, using the + * placement flags in @placement, potentially evicting other buffer objects when + * @force_space is true. + * This function may sleep while waiting for resources to become available. * Returns: - * -EBUSY: No space available (only if no_wait == 1). + * -EBUSY: No space available (only if no_wait == true). * -ENOSPC: Could not allocate space for the buffer object, either due to * fragmentation or concurrent allocators. * -ERESTARTSYS: An interruptible sleep was interrupted by a signal. */ -int ttm_bo_mem_space(struct ttm_buffer_object *bo, - struct ttm_placement *placement, - struct ttm_resource **mem, - struct ttm_operation_ctx *ctx) +static int ttm_bo_alloc_resource(struct ttm_buffer_object *bo, + struct ttm_placement *placement, + struct ttm_operation_ctx *ctx, + bool force_space, + struct ttm_resource **res) { struct ttm_device *bdev = bo->bdev; - bool type_found = false; + struct ww_acquire_ctx *ticket; int i, ret; + ticket = dma_resv_locking_ctx(bo->base.resv); ret = dma_resv_reserve_fences(bo->base.resv, 1); if (unlikely(ret)) return ret; @@ -790,98 +762,73 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo, const struct ttm_place *place = &placement->placement[i]; struct ttm_resource_manager *man; - if (place->flags & TTM_PL_FLAG_FALLBACK) - continue; - man = ttm_manager_type(bdev, place->mem_type); if (!man || !ttm_resource_manager_used(man)) continue; - type_found = true; - ret = ttm_resource_alloc(bo, place, mem); - if (ret == -ENOSPC) + if (place->flags & (force_space ? TTM_PL_FLAG_DESIRED : + TTM_PL_FLAG_FALLBACK)) + continue; + + do { + ret = ttm_resource_alloc(bo, place, res); + if (unlikely(ret && ret != -ENOSPC)) + return ret; + if (likely(!ret) || !force_space) + break; + + ret = ttm_mem_evict_first(bdev, man, place, ctx, + ticket); + if (unlikely(ret == -EBUSY)) + break; + if (unlikely(ret)) + return ret; + } while (1); + if (ret) continue; - if (unlikely(ret)) - goto error; - ret = ttm_bo_add_move_fence(bo, man, *mem, ctx->no_wait_gpu); + ret = ttm_bo_add_move_fence(bo, man, *res, ctx->no_wait_gpu); if (unlikely(ret)) { - ttm_resource_free(bo, mem); + ttm_resource_free(bo, res); if (ret == -EBUSY) continue; - goto error; + return ret; } return 0; } - for (i = 0; i < placement->num_placement; ++i) { - const struct ttm_place *place = &placement->placement[i]; - struct ttm_resource_manager *man; - - if (place->flags & TTM_PL_FLAG_DESIRED) - continue; - - man = ttm_manager_type(bdev, place->mem_type); - if (!man || !ttm_resource_manager_used(man)) - continue; - - type_found = true; - ret = ttm_bo_mem_force_space(bo, place, mem, ctx); - if (likely(!ret)) - return 0; - - if (ret && ret != -EBUSY) - goto error; - } - - ret = -ENOSPC; - if (!type_found) { - pr_err(TTM_PFX "No compatible memory type found\n"); - ret = -EINVAL; - } - -error: - return ret; + return -ENOSPC; } -EXPORT_SYMBOL(ttm_bo_mem_space); -static int ttm_bo_move_buffer(struct ttm_buffer_object *bo, - struct ttm_placement *placement, - struct ttm_operation_ctx *ctx) +/* + * ttm_bo_mem_space - Wrapper around ttm_bo_alloc_resource + * + * @bo: Pointer to a struct ttm_buffer_object of which we want a resource for + * @placement: Proposed new placement for the buffer object + * @res: The resulting struct ttm_resource. + * @ctx: if and how to sleep, lock buffers and alloc memory + * + * Tries both idle allocation and forcefully eviction of buffers. See + * ttm_bo_alloc_resource for details. + */ +int ttm_bo_mem_space(struct ttm_buffer_object *bo, + struct ttm_placement *placement, + struct ttm_resource **res, + struct ttm_operation_ctx *ctx) { - struct ttm_resource *mem; - struct ttm_place hop; + bool force_space = false; int ret; - dma_resv_assert_held(bo->base.resv); + do { + ret = ttm_bo_alloc_resource(bo, placement, ctx, + force_space, res); + force_space = !force_space; + } while (ret == -ENOSPC && force_space); - /* - * Determine where to move the buffer. - * - * If driver determines move is going to need - * an extra step then it will return -EMULTIHOP - * and the buffer will be moved to the temporary - * stop and the driver will be called to make - * the second hop. - */ - ret = ttm_bo_mem_space(bo, placement, &mem, ctx); - if (ret) - return ret; -bounce: - ret = ttm_bo_handle_move_mem(bo, mem, false, ctx, &hop); - if (ret == -EMULTIHOP) { - ret = ttm_bo_bounce_temp_buffer(bo, &mem, ctx, &hop); - if (ret) - goto out; - /* try and move to final place now. */ - goto bounce; - } -out: - if (ret) - ttm_resource_free(bo, &mem); return ret; } +EXPORT_SYMBOL(ttm_bo_mem_space); /** * ttm_bo_validate @@ -902,6 +849,9 @@ int ttm_bo_validate(struct ttm_buffer_object *bo, struct ttm_placement *placement, struct ttm_operation_ctx *ctx) { + struct ttm_resource *res; + struct ttm_place hop; + bool force_space; int ret; dma_resv_assert_held(bo->base.resv); @@ -912,20 +862,53 @@ int ttm_bo_validate(struct ttm_buffer_object *bo, if (!placement->num_placement) return ttm_bo_pipeline_gutting(bo); - /* Check whether we need to move buffer. */ - if (bo->resource && ttm_resource_compatible(bo->resource, placement)) - return 0; + force_space = false; + do { + /* Check whether we need to move buffer. */ + if (bo->resource && + ttm_resource_compatible(bo->resource, placement, + force_space)) + return 0; - /* Moving of pinned BOs is forbidden */ - if (bo->pin_count) - return -EINVAL; + /* Moving of pinned BOs is forbidden */ + if (bo->pin_count) + return -EINVAL; + + /* + * Determine where to move the buffer. + * + * If driver determines move is going to need + * an extra step then it will return -EMULTIHOP + * and the buffer will be moved to the temporary + * stop and the driver will be called to make + * the second hop. + */ + ret = ttm_bo_alloc_resource(bo, placement, ctx, force_space, + &res); + force_space = !force_space; + if (ret == -ENOSPC) + continue; + if (ret) + return ret; + +bounce: + ret = ttm_bo_handle_move_mem(bo, res, false, ctx, &hop); + if (ret == -EMULTIHOP) { + ret = ttm_bo_bounce_temp_buffer(bo, &res, ctx, &hop); + /* try and move to final place now. */ + if (!ret) + goto bounce; + } + if (ret) { + ttm_resource_free(bo, &res); + return ret; + } + + } while (ret && force_space); - ret = ttm_bo_move_buffer(bo, placement, ctx); /* For backward compatibility with userspace */ if (ret == -ENOSPC) return -ENOMEM; - if (ret) - return ret; /* * We might need to add a TTM. diff --git a/drivers/gpu/drm/ttm/ttm_resource.c b/drivers/gpu/drm/ttm/ttm_resource.c index fb14f7716cf8..65155f2013ca 100644 --- a/drivers/gpu/drm/ttm/ttm_resource.c +++ b/drivers/gpu/drm/ttm/ttm_resource.c @@ -295,11 +295,13 @@ bool ttm_resource_intersects(struct ttm_device *bdev, * * @res: the resource to check * @placement: the placement to check against + * @evicting: true if the caller is doing evictions * * Returns true if the placement is compatible. */ bool ttm_resource_compatible(struct ttm_resource *res, - struct ttm_placement *placement) + struct ttm_placement *placement, + bool evicting) { struct ttm_buffer_object *bo = res->bo; struct ttm_device *bdev = bo->bdev; @@ -315,14 +317,20 @@ bool ttm_resource_compatible(struct ttm_resource *res, if (res->mem_type != place->mem_type) continue; + if (place->flags & (evicting ? TTM_PL_FLAG_DESIRED : + TTM_PL_FLAG_FALLBACK)) + continue; + + if (place->flags & TTM_PL_FLAG_CONTIGUOUS && + !(res->placement & TTM_PL_FLAG_CONTIGUOUS)) + continue; + man = ttm_manager_type(bdev, res->mem_type); if (man->func->compatible && !man->func->compatible(man, res, place, bo->base.size)) continue; - if ((!(place->flags & TTM_PL_FLAG_CONTIGUOUS) || - (res->placement & TTM_PL_FLAG_CONTIGUOUS))) - return true; + return true; } return false; } diff --git a/include/drm/ttm/ttm_resource.h b/include/drm/ttm/ttm_resource.h index 1afa13f0c22b..7561023db43d 100644 --- a/include/drm/ttm/ttm_resource.h +++ b/include/drm/ttm/ttm_resource.h @@ -366,7 +366,8 @@ bool ttm_resource_intersects(struct ttm_device *bdev, const struct ttm_place *place, size_t size); bool ttm_resource_compatible(struct ttm_resource *res, - struct ttm_placement *placement); + struct ttm_placement *placement, + bool evicting); void ttm_resource_set_bo(struct ttm_resource *res, struct ttm_buffer_object *bo); -- cgit v1.2.3 From 460be1d527a8e296d85301e8b14923299508d4fc Mon Sep 17 00:00:00 2001 From: Karol Herbst Date: Tue, 5 Mar 2024 14:38:53 +0100 Subject: drm/nouveau: move more missing UAPI bits Those are already de-facto UAPI, so let's just move it into the uapi header. Signed-off-by: Karol Herbst Reviewed-by: Lyude Paul Reviewed-by: Danilo Krummrich Link: https://patchwork.freedesktop.org/patch/msgid/20240305133853.2214268-2-kherbst@redhat.com --- drivers/gpu/drm/nouveau/nouveau_abi16.c | 20 +++++++++++++++----- drivers/gpu/drm/nouveau/nouveau_abi16.h | 12 ------------ include/uapi/drm/nouveau_drm.h | 22 ++++++++++++++++++++++ 3 files changed, 37 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/nouveau/nouveau_abi16.c b/drivers/gpu/drm/nouveau/nouveau_abi16.c index cd14f993bdd1..92f9127b284a 100644 --- a/drivers/gpu/drm/nouveau/nouveau_abi16.c +++ b/drivers/gpu/drm/nouveau/nouveau_abi16.c @@ -312,11 +312,21 @@ nouveau_abi16_ioctl_channel_alloc(ABI16_IOCTL_ARGS) if (device->info.family >= NV_DEVICE_INFO_V0_KEPLER) { if (init->fb_ctxdma_handle == ~0) { switch (init->tt_ctxdma_handle) { - case 0x01: engine = NV_DEVICE_HOST_RUNLIST_ENGINES_GR ; break; - case 0x02: engine = NV_DEVICE_HOST_RUNLIST_ENGINES_MSPDEC; break; - case 0x04: engine = NV_DEVICE_HOST_RUNLIST_ENGINES_MSPPP ; break; - case 0x08: engine = NV_DEVICE_HOST_RUNLIST_ENGINES_MSVLD ; break; - case 0x30: engine = NV_DEVICE_HOST_RUNLIST_ENGINES_CE ; break; + case NOUVEAU_FIFO_ENGINE_GR: + engine = NV_DEVICE_HOST_RUNLIST_ENGINES_GR; + break; + case NOUVEAU_FIFO_ENGINE_VP: + engine = NV_DEVICE_HOST_RUNLIST_ENGINES_MSPDEC; + break; + case NOUVEAU_FIFO_ENGINE_PPP: + engine = NV_DEVICE_HOST_RUNLIST_ENGINES_MSPPP; + break; + case NOUVEAU_FIFO_ENGINE_BSP: + engine = NV_DEVICE_HOST_RUNLIST_ENGINES_MSVLD; + break; + case NOUVEAU_FIFO_ENGINE_CE: + engine = NV_DEVICE_HOST_RUNLIST_ENGINES_CE; + break; default: return nouveau_abi16_put(abi16, -ENOSYS); } diff --git a/drivers/gpu/drm/nouveau/nouveau_abi16.h b/drivers/gpu/drm/nouveau/nouveau_abi16.h index 11c8c4a80079..661b901d8ecc 100644 --- a/drivers/gpu/drm/nouveau/nouveau_abi16.h +++ b/drivers/gpu/drm/nouveau/nouveau_abi16.h @@ -50,18 +50,6 @@ struct drm_nouveau_grobj_alloc { int class; }; -struct drm_nouveau_notifierobj_alloc { - uint32_t channel; - uint32_t handle; - uint32_t size; - uint32_t offset; -}; - -struct drm_nouveau_gpuobj_free { - int channel; - uint32_t handle; -}; - struct drm_nouveau_setparam { uint64_t param; uint64_t value; diff --git a/include/uapi/drm/nouveau_drm.h b/include/uapi/drm/nouveau_drm.h index cd84227f1b42..8ad8d1cd1566 100644 --- a/include/uapi/drm/nouveau_drm.h +++ b/include/uapi/drm/nouveau_drm.h @@ -73,6 +73,16 @@ struct drm_nouveau_getparam { __u64 value; }; +/* + * Those are used to support selecting the main engine used on Kepler. + * This goes into drm_nouveau_channel_alloc::tt_ctxdma_handle + */ +#define NOUVEAU_FIFO_ENGINE_GR 0x01 +#define NOUVEAU_FIFO_ENGINE_VP 0x02 +#define NOUVEAU_FIFO_ENGINE_PPP 0x04 +#define NOUVEAU_FIFO_ENGINE_BSP 0x08 +#define NOUVEAU_FIFO_ENGINE_CE 0x30 + struct drm_nouveau_channel_alloc { __u32 fb_ctxdma_handle; __u32 tt_ctxdma_handle; @@ -95,6 +105,18 @@ struct drm_nouveau_channel_free { __s32 channel; }; +struct drm_nouveau_notifierobj_alloc { + __u32 channel; + __u32 handle; + __u32 size; + __u32 offset; +}; + +struct drm_nouveau_gpuobj_free { + __s32 channel; + __u32 handle; +}; + #define NOUVEAU_GEM_DOMAIN_CPU (1 << 0) #define NOUVEAU_GEM_DOMAIN_VRAM (1 << 1) #define NOUVEAU_GEM_DOMAIN_GART (1 << 2) -- cgit v1.2.3 From 6a9b38cc68a03b948df1f3fcb907c7557cfc315c Mon Sep 17 00:00:00 2001 From: Matt Roper Date: Tue, 5 Mar 2024 16:40:49 -0800 Subject: drm/xe/arl: Add Arrow Lake H support ARL-H uses the same media and display IP as MTL, and a version 12.74 graphics IP (referred to as Xe_LPG+). From a driver point of view, we should be able to just treat the whole platform as MTL and rely on GRAPHICS_VERx100 checks to handle any spots where ARL's Xe_LPG+ needs different handling from MTL's Xe_LPG (i.e., workarounds). v2: Resolve conflict and Reorder PCI ids in sorted order v3: Append signed-off-by commiter to this commit Bspec: 55420 Signed-off-by: Matt Roper Signed-off-by: Dnyaneshwar Bhadane Reviewed-by: Matt Atwood Link: https://patchwork.freedesktop.org/patch/msgid/20240229070806.3402641-4-dnyaneshwar.bhadane@intel.com --- include/drm/xe_pciids.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/drm/xe_pciids.h b/include/drm/xe_pciids.h index de1a344737bc..bc7cbef6e9d8 100644 --- a/include/drm/xe_pciids.h +++ b/include/drm/xe_pciids.h @@ -176,10 +176,13 @@ /* MTL / ARL */ #define XE_MTL_IDS(MACRO__, ...) \ MACRO__(0x7D40, ## __VA_ARGS__), \ + MACRO__(0x7D41, ## __VA_ARGS__), \ MACRO__(0x7D45, ## __VA_ARGS__), \ + MACRO__(0x7D51, ## __VA_ARGS__), \ MACRO__(0x7D55, ## __VA_ARGS__), \ MACRO__(0x7D60, ## __VA_ARGS__), \ MACRO__(0x7D67, ## __VA_ARGS__), \ + MACRO__(0x7DD1, ## __VA_ARGS__), \ MACRO__(0x7DD5, ## __VA_ARGS__) #define XE_LNL_IDS(MACRO__, ...) \ -- cgit v1.2.3 From 2cddf770be0cebb663af3d72c049b9e24928f335 Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Wed, 6 Mar 2024 20:31:08 +0200 Subject: drm/kunit: fix drm_kunit_helpers.h kernel-doc s/_features/_feat/ to match code. Reviewed-by: Thomas Zimmermann Signed-off-by: Jani Nikula Link: https://patchwork.freedesktop.org/patch/msgid/f909224abc8d542a89b66b957a32f152f42e9bba.1709749576.git.jani.nikula@intel.com --- include/drm/drm_kunit_helpers.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/drm/drm_kunit_helpers.h b/include/drm/drm_kunit_helpers.h index 6e99627edf45..e7cc17ee4934 100644 --- a/include/drm/drm_kunit_helpers.h +++ b/include/drm/drm_kunit_helpers.h @@ -75,7 +75,7 @@ __drm_kunit_helper_alloc_drm_device(struct kunit *test, * @_dev: The parent device object * @_type: the type of the struct which contains struct &drm_device * @_member: the name of the &drm_device within @_type. - * @_features: Mocked DRM device driver features + * @_feat: Mocked DRM device driver features * * This function creates a struct &drm_driver and will create a struct * &drm_device from @_dev and that driver. -- cgit v1.2.3 From eddb24a800ce89be9a01587f5572816213634ddc Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Wed, 6 Mar 2024 20:31:09 +0200 Subject: drm/amdgpu: make amd_asic_type.h self-contained Include for u8. Reviewed-by: Thomas Zimmermann Acked-by: Alex Deucher Signed-off-by: Jani Nikula Link: https://patchwork.freedesktop.org/patch/msgid/115327b880b69b1c8ad157e5ff7f6b419868fab0.1709749576.git.jani.nikula@intel.com --- include/drm/amd_asic_type.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/drm/amd_asic_type.h b/include/drm/amd_asic_type.h index 724c45e3e9a7..9be85b821aa6 100644 --- a/include/drm/amd_asic_type.h +++ b/include/drm/amd_asic_type.h @@ -22,6 +22,9 @@ #ifndef __AMD_ASIC_TYPE_H__ #define __AMD_ASIC_TYPE_H__ + +#include + /* * Supported ASIC types */ -- cgit v1.2.3 From 9811a99cddbafcdde06d9a7f15f073fb452f23e7 Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Wed, 6 Mar 2024 20:31:10 +0200 Subject: drm: bridge: samsung-dsim: make samsung-dsim.h self-contained Include and forward declare struct platform device. Reviewed-by: Thomas Zimmermann Signed-off-by: Jani Nikula Link: https://patchwork.freedesktop.org/patch/msgid/9534ca7dfba96580950e116c84ce0fa68fdf93a4.1709749576.git.jani.nikula@intel.com --- include/drm/bridge/samsung-dsim.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/drm/bridge/samsung-dsim.h b/include/drm/bridge/samsung-dsim.h index e0c105051246..9764d6eb5beb 100644 --- a/include/drm/bridge/samsung-dsim.h +++ b/include/drm/bridge/samsung-dsim.h @@ -11,9 +11,11 @@ #include #include -#include +#include #include +#include +struct platform_device; struct samsung_dsim; #define DSIM_STATE_ENABLED BIT(0) -- cgit v1.2.3 From ca892057e03ed935113b3fcf23cf2f609cf6b26e Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Wed, 6 Mar 2024 20:31:11 +0200 Subject: drm/dp_mst: fix drm_dp_mst_helper.h kernel-doc Drop excess vcpi member documentation. Reviewed-by: Thomas Zimmermann Signed-off-by: Jani Nikula Link: https://patchwork.freedesktop.org/patch/msgid/606eee280718ba372093fdebbda42c7581dbd827.1709749576.git.jani.nikula@intel.com --- include/drm/display/drm_dp_mst_helper.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/drm/display/drm_dp_mst_helper.h b/include/drm/display/drm_dp_mst_helper.h index 9b19d8bd520a..3ae88a383a41 100644 --- a/include/drm/display/drm_dp_mst_helper.h +++ b/include/drm/display/drm_dp_mst_helper.h @@ -83,7 +83,6 @@ struct drm_dp_mst_branch; * @passthrough_aux: parent aux to which DSC pass-through requests should be * sent, only set if DSC pass-through is possible. * @parent: branch device parent of this port - * @vcpi: Virtual Channel Payload info for this port. * @connector: DRM connector this port is connected to. Protected by * &drm_dp_mst_topology_mgr.base.lock. * @mgr: topology manager this port lives under. -- cgit v1.2.3 From b0da0d9e86df27162ced208465de2e5caec1f95a Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Wed, 6 Mar 2024 20:31:12 +0200 Subject: drm/crc: make drm_debugfs_crc.h self-contained and fix kernel-doc Add a number of require includes and forward declare struct drm_crtc. s/crc/crcs/ kernel-doc to match code. Reviewed-by: Thomas Zimmermann Signed-off-by: Jani Nikula Link: https://patchwork.freedesktop.org/patch/msgid/290b006bb348a03bd7c4c062d337df21fdaced53.1709749576.git.jani.nikula@intel.com --- include/drm/drm_debugfs_crc.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/drm/drm_debugfs_crc.h b/include/drm/drm_debugfs_crc.h index b225eeb30d05..1b4c98c2f838 100644 --- a/include/drm/drm_debugfs_crc.h +++ b/include/drm/drm_debugfs_crc.h @@ -22,13 +22,19 @@ #ifndef __DRM_DEBUGFS_CRC_H__ #define __DRM_DEBUGFS_CRC_H__ +#include +#include +#include + +struct drm_crtc; + #define DRM_MAX_CRC_NR 10 /** * struct drm_crtc_crc_entry - entry describing a frame's content * @has_frame_counter: whether the source was able to provide a frame number * @frame: number of the frame this CRC is about, if @has_frame_counter is true - * @crc: array of values that characterize the frame + * @crcs: array of values that characterize the frame */ struct drm_crtc_crc_entry { bool has_frame_counter; -- cgit v1.2.3 From efc86a8769b96e0ee8d842fa8fde909678a998f8 Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Wed, 6 Mar 2024 20:31:14 +0200 Subject: drm: fix drm_format_helper.h kernel-doc warnings As the documentation says, all the fields are considered private. Mark them private also for kernel-doc to silence warnings. Reviewed-by: Thomas Zimmermann Signed-off-by: Jani Nikula Link: https://patchwork.freedesktop.org/patch/msgid/6dc5b1df34abc10d416c2db5b390440cf56e21ce.1709749576.git.jani.nikula@intel.com --- include/drm/drm_format_helper.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/drm/drm_format_helper.h b/include/drm/drm_format_helper.h index f13b34e0b752..428d81afe215 100644 --- a/include/drm/drm_format_helper.h +++ b/include/drm/drm_format_helper.h @@ -25,6 +25,7 @@ struct iosys_map; * All fields are considered private. */ struct drm_format_conv_state { + /* private: */ struct { void *mem; size_t size; -- cgit v1.2.3 From dbae67ed6ac6a565d4b2075fcecdc122dff66752 Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Wed, 6 Mar 2024 20:31:15 +0200 Subject: drm/lease: make drm_lease.h self-contained Include for types used. Reviewed-by: Thomas Zimmermann Signed-off-by: Jani Nikula Link: https://patchwork.freedesktop.org/patch/msgid/3a38688e90bb775380aad5b6aad5dce3d9d87ca7.1709749576.git.jani.nikula@intel.com --- include/drm/drm_lease.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/drm/drm_lease.h b/include/drm/drm_lease.h index 5c9ef6a2aeae..53545b4ca9ef 100644 --- a/include/drm/drm_lease.h +++ b/include/drm/drm_lease.h @@ -6,6 +6,8 @@ #ifndef _DRM_LEASE_H_ #define _DRM_LEASE_H_ +#include + struct drm_file; struct drm_device; struct drm_master; -- cgit v1.2.3 From d0589a3a6c36f3fbe1caa2300a8fd527aef6301a Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Wed, 6 Mar 2024 20:31:16 +0200 Subject: drm: fix drm_gem_vram_helper.h kernel-doc Remove excess funcs kernel-doc. Reviewed-by: Thomas Zimmermann Signed-off-by: Jani Nikula Link: https://patchwork.freedesktop.org/patch/msgid/02000be3455de639f32bde88f632ae8744142083.1709749576.git.jani.nikula@intel.com --- include/drm/drm_gem_vram_helper.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/drm/drm_gem_vram_helper.h b/include/drm/drm_gem_vram_helper.h index e18429f09e53..c89c9bafeb44 100644 --- a/include/drm/drm_gem_vram_helper.h +++ b/include/drm/drm_gem_vram_helper.h @@ -170,7 +170,6 @@ void drm_gem_vram_simple_display_pipe_cleanup_fb( * @vram_base: Base address of the managed video memory * @vram_size: Size of the managed video memory in bytes * @bdev: The TTM BO device. - * @funcs: TTM BO functions * * The fields &struct drm_vram_mm.vram_base and * &struct drm_vram_mm.vrm_size are managed by VRAM MM, but are -- cgit v1.2.3 From 08179fe18a67cf7909411705dc68c549b18fa574 Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Wed, 6 Mar 2024 20:31:17 +0200 Subject: drm/of: make drm_of.h self-contained Include for ERR_PTR. Reviewed-by: Thomas Zimmermann Signed-off-by: Jani Nikula Link: https://patchwork.freedesktop.org/patch/msgid/e9b3ea30984b913f6e32ed35e0575438dff8278c.1709749576.git.jani.nikula@intel.com --- include/drm/drm_of.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/drm/drm_of.h b/include/drm/drm_of.h index 082a6e980d01..02d1cdd7f798 100644 --- a/include/drm/drm_of.h +++ b/include/drm/drm_of.h @@ -2,6 +2,7 @@ #ifndef __DRM_OF_H__ #define __DRM_OF_H__ +#include #include #if IS_ENABLED(CONFIG_OF) && IS_ENABLED(CONFIG_DRM_PANEL_BRIDGE) #include -- cgit v1.2.3 From 6a91585edc70009a8075639f12d5d1e1597b8544 Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Wed, 6 Mar 2024 20:31:19 +0200 Subject: drm/suballoc: fix drm_suballoc.h kernel-doc Rename dma_fence to fence to match code. Reviewed-by: Thomas Zimmermann Signed-off-by: Jani Nikula Link: https://patchwork.freedesktop.org/patch/msgid/36d18b315fd9a6788484667f644b3fea347fb007.1709749576.git.jani.nikula@intel.com --- include/drm/drm_suballoc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/drm/drm_suballoc.h b/include/drm/drm_suballoc.h index c2188bb0b157..7ba72a81a808 100644 --- a/include/drm/drm_suballoc.h +++ b/include/drm/drm_suballoc.h @@ -37,7 +37,7 @@ struct drm_suballoc_manager { * @manager: The drm_suballoc_manager. * @soffset: Start offset. * @eoffset: End offset + 1 so that @eoffset - @soffset = size. - * @dma_fence: The fence protecting the allocation. + * @fence: The fence protecting the allocation. */ struct drm_suballoc { struct list_head olist; -- cgit v1.2.3 From cec82816d0d018f178b9b7f88fe4bf80d66954e9 Mon Sep 17 00:00:00 2001 From: Vinay Belgaumkar Date: Tue, 5 Mar 2024 17:27:59 -0800 Subject: drm/i915/guc: Use context hints for GT frequency Allow user to provide a low latency context hint. When set, KMD sends a hint to GuC which results in special handling for this context. SLPC will ramp the GT frequency aggressively every time it switches to this context. The down freq threshold will also be lower so GuC will ramp down the GT freq for this context more slowly. We also disable waitboost for this context as that will interfere with the strategy. We need to enable the use of SLPC Compute strategy during init, but it will apply only to contexts that set this bit during context creation. Userland can check whether this feature is supported using a new param- I915_PARAM_HAS_CONTEXT_FREQ_HINT. This flag is true for all guc submission enabled platforms as they use SLPC for frequency management. The Mesa usage model for this flag is here - https://gitlab.freedesktop.org/sushmave/mesa/-/commits/compute_hint v2: Rename flags as per review suggestions (Rodrigo, Tvrtko). Also, use flag bits in intel_context as it allows finer control for toggling per engine if needed (Tvrtko). v3: Minor review comments (Tvrtko) v4: Update comment (Sushma) Cc: Rodrigo Vivi Cc: Tvrtko Ursulin Cc: Sushma Venkatesh Reddy Reviewed-by: Rodrigo Vivi Acked-by: Ivan Briano Signed-off-by: Vinay Belgaumkar Signed-off-by: John Harrison Link: https://patchwork.freedesktop.org/patch/msgid/20240306012759.204938-1-vinay.belgaumkar@intel.com --- drivers/gpu/drm/i915/gem/i915_gem_context.c | 16 ++++++++++++++-- drivers/gpu/drm/i915/gem/i915_gem_context_types.h | 1 + drivers/gpu/drm/i915/gt/intel_context_types.h | 1 + drivers/gpu/drm/i915/gt/intel_rps.c | 4 ++++ .../gpu/drm/i915/gt/uc/abi/guc_actions_slpc_abi.h | 21 +++++++++++++++++++++ drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c | 17 +++++++++++++++++ drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.h | 1 + drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c | 6 ++++++ drivers/gpu/drm/i915/i915_getparam.c | 6 ++++++ include/uapi/drm/i915_drm.h | 15 +++++++++++++++ 10 files changed, 86 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c index dcbfe32fd30c..81f65cab1330 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_context.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c @@ -879,6 +879,7 @@ static int set_proto_ctx_param(struct drm_i915_file_private *fpriv, struct i915_gem_proto_context *pc, struct drm_i915_gem_context_param *args) { + struct drm_i915_private *i915 = fpriv->i915; int ret = 0; switch (args->param) { @@ -904,6 +905,13 @@ static int set_proto_ctx_param(struct drm_i915_file_private *fpriv, pc->user_flags &= ~BIT(UCONTEXT_BANNABLE); break; + case I915_CONTEXT_PARAM_LOW_LATENCY: + if (intel_uc_uses_guc_submission(&to_gt(i915)->uc)) + pc->user_flags |= BIT(UCONTEXT_LOW_LATENCY); + else + ret = -EINVAL; + break; + case I915_CONTEXT_PARAM_RECOVERABLE: if (args->size) ret = -EINVAL; @@ -992,6 +1000,9 @@ static int intel_context_set_gem(struct intel_context *ce, if (sseu.slice_mask && !WARN_ON(ce->engine->class != RENDER_CLASS)) ret = intel_context_reconfigure_sseu(ce, sseu); + if (test_bit(UCONTEXT_LOW_LATENCY, &ctx->user_flags)) + __set_bit(CONTEXT_LOW_LATENCY, &ce->flags); + return ret; } @@ -1630,6 +1641,9 @@ i915_gem_create_context(struct drm_i915_private *i915, if (vm) ctx->vm = vm; + /* Assign early so intel_context_set_gem can access these flags */ + ctx->user_flags = pc->user_flags; + mutex_init(&ctx->engines_mutex); if (pc->num_user_engines >= 0) { i915_gem_context_set_user_engines(ctx); @@ -1652,8 +1666,6 @@ i915_gem_create_context(struct drm_i915_private *i915, * is no remap info, it will be a NOP. */ ctx->remap_slice = ALL_L3_SLICES(i915); - ctx->user_flags = pc->user_flags; - for (i = 0; i < ARRAY_SIZE(ctx->hang_timestamp); i++) ctx->hang_timestamp[i] = jiffies - CONTEXT_FAST_HANG_JIFFIES; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h index 03bc7f9d191b..b6d97da63d1f 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h @@ -338,6 +338,7 @@ struct i915_gem_context { #define UCONTEXT_BANNABLE 2 #define UCONTEXT_RECOVERABLE 3 #define UCONTEXT_PERSISTENCE 4 +#define UCONTEXT_LOW_LATENCY 5 /** * @flags: small set of booleans diff --git a/drivers/gpu/drm/i915/gt/intel_context_types.h b/drivers/gpu/drm/i915/gt/intel_context_types.h index 7eccbd70d89f..ed95a7b57cbb 100644 --- a/drivers/gpu/drm/i915/gt/intel_context_types.h +++ b/drivers/gpu/drm/i915/gt/intel_context_types.h @@ -130,6 +130,7 @@ struct intel_context { #define CONTEXT_PERMA_PIN 11 #define CONTEXT_IS_PARKING 12 #define CONTEXT_EXITING 13 +#define CONTEXT_LOW_LATENCY 14 struct { u64 timeout_us; diff --git a/drivers/gpu/drm/i915/gt/intel_rps.c b/drivers/gpu/drm/i915/gt/intel_rps.c index 9c6812257ac2..a929aa6e3c85 100644 --- a/drivers/gpu/drm/i915/gt/intel_rps.c +++ b/drivers/gpu/drm/i915/gt/intel_rps.c @@ -1013,6 +1013,10 @@ void intel_rps_boost(struct i915_request *rq) if (i915_request_signaled(rq) || i915_request_has_waitboost(rq)) return; + /* Waitboost is not needed for contexts marked with a Freq hint */ + if (test_bit(CONTEXT_LOW_LATENCY, &rq->context->flags)) + return; + /* Serializes with i915_request_retire() */ if (!test_and_set_bit(I915_FENCE_FLAG_BOOST, &rq->fence.flags)) { struct intel_rps *rps = &READ_ONCE(rq->engine)->gt->rps; diff --git a/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_slpc_abi.h b/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_slpc_abi.h index 811add10c30d..c34674e797c6 100644 --- a/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_slpc_abi.h +++ b/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_slpc_abi.h @@ -207,6 +207,27 @@ struct slpc_shared_data { u8 reserved_mode_definition[4096]; } __packed; +struct slpc_context_frequency_request { + u32 frequency_request:16; + u32 reserved:12; + u32 is_compute:1; + u32 ignore_busyness:1; + u32 is_minimum:1; + u32 is_predefined:1; +} __packed; + +#define SLPC_CTX_FREQ_REQ_IS_COMPUTE REG_BIT(28) + +struct slpc_optimized_strategies { + u32 compute:1; + u32 async_flip:1; + u32 media:1; + u32 vsync_flip:1; + u32 reserved:28; +} __packed; + +#define SLPC_OPTIMIZED_STRATEGY_COMPUTE REG_BIT(0) + /** * DOC: SLPC H2G MESSAGE FORMAT * diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c index 3e681ab6fbf9..706fffca698b 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c @@ -537,6 +537,20 @@ int intel_guc_slpc_get_min_freq(struct intel_guc_slpc *slpc, u32 *val) return ret; } +int intel_guc_slpc_set_strategy(struct intel_guc_slpc *slpc, u32 val) +{ + struct drm_i915_private *i915 = slpc_to_i915(slpc); + intel_wakeref_t wakeref; + int ret = 0; + + with_intel_runtime_pm(&i915->runtime_pm, wakeref) + ret = slpc_set_param(slpc, + SLPC_PARAM_STRATEGIES, + val); + + return ret; +} + int intel_guc_slpc_set_media_ratio_mode(struct intel_guc_slpc *slpc, u32 val) { struct drm_i915_private *i915 = slpc_to_i915(slpc); @@ -711,6 +725,9 @@ int intel_guc_slpc_enable(struct intel_guc_slpc *slpc) /* Set cached media freq ratio mode */ intel_guc_slpc_set_media_ratio_mode(slpc, slpc->media_ratio_mode); + /* Enable SLPC Optimized Strategy for compute */ + intel_guc_slpc_set_strategy(slpc, SLPC_OPTIMIZED_STRATEGY_COMPUTE); + return 0; } diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.h index 6ac6503c39d4..1cb5fd44f05c 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.h @@ -45,5 +45,6 @@ void intel_guc_pm_intrmsk_enable(struct intel_gt *gt); void intel_guc_slpc_boost(struct intel_guc_slpc *slpc); void intel_guc_slpc_dec_waiters(struct intel_guc_slpc *slpc); int intel_guc_slpc_set_ignore_eff_freq(struct intel_guc_slpc *slpc, bool val); +int intel_guc_slpc_set_strategy(struct intel_guc_slpc *slpc, u32 val); #endif diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c index cc076e9302ad..e5c645137cfe 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -2645,6 +2645,7 @@ MAKE_CONTEXT_POLICY_ADD(execution_quantum, EXECUTION_QUANTUM) MAKE_CONTEXT_POLICY_ADD(preemption_timeout, PREEMPTION_TIMEOUT) MAKE_CONTEXT_POLICY_ADD(priority, SCHEDULING_PRIORITY) MAKE_CONTEXT_POLICY_ADD(preempt_to_idle, PREEMPT_TO_IDLE_ON_QUANTUM_EXPIRY) +MAKE_CONTEXT_POLICY_ADD(slpc_ctx_freq_req, SLPM_GT_FREQUENCY) #undef MAKE_CONTEXT_POLICY_ADD @@ -2664,6 +2665,7 @@ static int guc_context_policy_init_v70(struct intel_context *ce, bool loop) struct context_policy policy; u32 execution_quantum; u32 preemption_timeout; + u32 slpc_ctx_freq_req = 0; unsigned long flags; int ret; @@ -2675,11 +2677,15 @@ static int guc_context_policy_init_v70(struct intel_context *ce, bool loop) execution_quantum = engine->props.timeslice_duration_ms * 1000; preemption_timeout = engine->props.preempt_timeout_ms * 1000; + if (ce && (ce->flags & BIT(CONTEXT_LOW_LATENCY))) + slpc_ctx_freq_req |= SLPC_CTX_FREQ_REQ_IS_COMPUTE; + __guc_context_policy_start_klv(&policy, ce->guc_id.id); __guc_context_policy_add_priority(&policy, ce->guc_state.prio); __guc_context_policy_add_execution_quantum(&policy, execution_quantum); __guc_context_policy_add_preemption_timeout(&policy, preemption_timeout); + __guc_context_policy_add_slpc_ctx_freq_req(&policy, slpc_ctx_freq_req); if (engine->flags & I915_ENGINE_WANT_FORCED_PREEMPTION) __guc_context_policy_add_preempt_to_idle(&policy, 1); diff --git a/drivers/gpu/drm/i915/i915_getparam.c b/drivers/gpu/drm/i915/i915_getparam.c index 5c3fec63cb4c..95c58805b2a4 100644 --- a/drivers/gpu/drm/i915/i915_getparam.c +++ b/drivers/gpu/drm/i915/i915_getparam.c @@ -155,6 +155,12 @@ int i915_getparam_ioctl(struct drm_device *dev, void *data, */ value = 1; break; + case I915_PARAM_HAS_CONTEXT_FREQ_HINT: + if (intel_uc_uses_guc_submission(&to_gt(i915)->uc)) + value = 1; + else + value = -EINVAL; + break; case I915_PARAM_HAS_CONTEXT_ISOLATION: value = intel_engines_has_context_isolation(i915); break; diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h index 2ee338860b7e..558d95baf851 100644 --- a/include/uapi/drm/i915_drm.h +++ b/include/uapi/drm/i915_drm.h @@ -806,6 +806,12 @@ typedef struct drm_i915_irq_wait { */ #define I915_PARAM_PXP_STATUS 58 +/* + * Query if kernel allows marking a context to send a Freq hint to SLPC. This + * will enable use of the strategies allowed by the SLPC algorithm. + */ +#define I915_PARAM_HAS_CONTEXT_FREQ_HINT 59 + /* Must be kept compact -- no holes and well documented */ /** @@ -2148,6 +2154,15 @@ struct drm_i915_gem_context_param { * -EIO: The firmware did not succeed in creating the protected context. */ #define I915_CONTEXT_PARAM_PROTECTED_CONTENT 0xd + +/* + * I915_CONTEXT_PARAM_LOW_LATENCY: + * + * Mark this context as a low latency workload which requires aggressive GT + * frequency scaling. Use I915_PARAM_HAS_CONTEXT_FREQ_HINT to check if the kernel + * supports this per context flag. + */ +#define I915_CONTEXT_PARAM_LOW_LATENCY 0xe /* Must be kept compact -- no holes and well documented */ /** @value: Context parameter value to be set or queried */ -- cgit v1.2.3 From 9f08bb3959cd1672e43e939636dce7847c3ad313 Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Fri, 8 Mar 2024 13:55:41 +0200 Subject: drm/encoder: improve drm_encoder_slave.h kernel-doc Document structs drm_encoder_slave_funcs, drm_encoder_slave, and drm_i2c_encoder_driver. v2: Actually document the structs instead of just silencing kernel-doc Reviewed-by: Alex Deucher Signed-off-by: Jani Nikula Link: https://patchwork.freedesktop.org/patch/msgid/19bc9672c8ae4f7aee235665a4d2360e8790193d.1709898638.git.jani.nikula@intel.com --- include/drm/drm_encoder_slave.h | 91 +++++++++++++++++++++++++++++++++-------- 1 file changed, 74 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/include/drm/drm_encoder_slave.h b/include/drm/drm_encoder_slave.h index 7214101fd731..49172166a164 100644 --- a/include/drm/drm_encoder_slave.h +++ b/include/drm/drm_encoder_slave.h @@ -34,12 +34,6 @@ /** * struct drm_encoder_slave_funcs - Entry points exposed by a slave encoder driver - * @set_config: Initialize any encoder-specific modesetting parameters. - * The meaning of the @params parameter is implementation - * dependent. It will usually be a structure with DVO port - * data format settings or timings. It's not required for - * the new parameters to take effect until the next mode - * is set. * * Most of its members are analogous to the function pointers in * &drm_encoder_helper_funcs and they can optionally be used to @@ -48,41 +42,85 @@ * if the encoder is the currently selected one for the connector. */ struct drm_encoder_slave_funcs { + /** + * @set_config: Initialize any encoder-specific modesetting parameters. + * The meaning of the @params parameter is implementation dependent. It + * will usually be a structure with DVO port data format settings or + * timings. It's not required for the new parameters to take effect + * until the next mode is set. + */ void (*set_config)(struct drm_encoder *encoder, void *params); + /** + * @destroy: Analogous to &drm_encoder_funcs @destroy callback. + */ void (*destroy)(struct drm_encoder *encoder); + + /** + * @dpms: Analogous to &drm_encoder_helper_funcs @dpms callback. Wrapped + * by drm_i2c_encoder_dpms(). + */ void (*dpms)(struct drm_encoder *encoder, int mode); + + /** + * @save: Save state. Wrapped by drm_i2c_encoder_save(). + */ void (*save)(struct drm_encoder *encoder); + + /** + * @restore: Restore state. Wrapped by drm_i2c_encoder_restore(). + */ void (*restore)(struct drm_encoder *encoder); + + /** + * @mode_fixup: Analogous to &drm_encoder_helper_funcs @mode_fixup + * callback. Wrapped by drm_i2c_encoder_mode_fixup(). + */ bool (*mode_fixup)(struct drm_encoder *encoder, const struct drm_display_mode *mode, struct drm_display_mode *adjusted_mode); + + /** + * @mode_valid: Analogous to &drm_encoder_helper_funcs @mode_valid. + */ int (*mode_valid)(struct drm_encoder *encoder, struct drm_display_mode *mode); + /** + * @mode_set: Analogous to &drm_encoder_helper_funcs @mode_set + * callback. Wrapped by drm_i2c_encoder_mode_set(). + */ void (*mode_set)(struct drm_encoder *encoder, struct drm_display_mode *mode, struct drm_display_mode *adjusted_mode); + /** + * @detect: Analogous to &drm_encoder_helper_funcs @detect + * callback. Wrapped by drm_i2c_encoder_detect(). + */ enum drm_connector_status (*detect)(struct drm_encoder *encoder, struct drm_connector *connector); + /** + * @get_modes: Get modes. + */ int (*get_modes)(struct drm_encoder *encoder, struct drm_connector *connector); + /** + * @create_resources: Create resources. + */ int (*create_resources)(struct drm_encoder *encoder, struct drm_connector *connector); + /** + * @set_property: Set property. + */ int (*set_property)(struct drm_encoder *encoder, struct drm_connector *connector, struct drm_property *property, uint64_t val); - }; /** * struct drm_encoder_slave - Slave encoder struct - * @base: DRM encoder object. - * @slave_funcs: Slave encoder callbacks. - * @slave_priv: Slave encoder private data. - * @bus_priv: Bus specific data. * * A &drm_encoder_slave has two sets of callbacks, @slave_funcs and the * ones in @base. The former are never actually called by the common @@ -95,10 +133,24 @@ struct drm_encoder_slave_funcs { * this. */ struct drm_encoder_slave { + /** + * @base: DRM encoder object. + */ struct drm_encoder base; + /** + * @slave_funcs: Slave encoder callbacks. + */ const struct drm_encoder_slave_funcs *slave_funcs; + + /** + * @slave_priv: Slave encoder private data. + */ void *slave_priv; + + /** + * @bus_priv: Bus specific data. + */ void *bus_priv; }; #define to_encoder_slave(x) container_of((x), struct drm_encoder_slave, base) @@ -112,16 +164,20 @@ int drm_i2c_encoder_init(struct drm_device *dev, /** * struct drm_i2c_encoder_driver * - * Describes a device driver for an encoder connected to the GPU - * through an I2C bus. In addition to the entry points in @i2c_driver - * an @encoder_init function should be provided. It will be called to - * give the driver an opportunity to allocate any per-encoder data - * structures and to initialize the @slave_funcs and (optionally) - * @slave_priv members of @encoder. + * Describes a device driver for an encoder connected to the GPU through an I2C + * bus. */ struct drm_i2c_encoder_driver { + /** + * @i2c_driver: I2C device driver description. + */ struct i2c_driver i2c_driver; + /** + * @encoder_init: Callback to allocate any per-encoder data structures + * and to initialize the @slave_funcs and (optionally) @slave_priv + * members of @encoder. + */ int (*encoder_init)(struct i2c_client *client, struct drm_device *dev, struct drm_encoder_slave *encoder); @@ -133,6 +189,7 @@ struct drm_i2c_encoder_driver { /** * drm_i2c_encoder_get_client - Get the I2C client corresponding to an encoder + * @encoder: The encoder */ static inline struct i2c_client *drm_i2c_encoder_get_client(struct drm_encoder *encoder) { -- cgit v1.2.3 From c68ca0a9ea872cf53e84d13ab6546daa2108c63a Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Fri, 8 Mar 2024 13:55:43 +0200 Subject: drm/i915: fix i915_gsc_proxy_mei_interface.h kernel-doc There's no proper way to document function pointer members, but at least silence the warnings. Acked-by: Thomas Zimmermann Reviewed-by: Lucas De Marchi Signed-off-by: Jani Nikula Link: https://patchwork.freedesktop.org/patch/msgid/a84bd76162290940f709f5cb6e432e5e1f75a3b9.1709898638.git.jani.nikula@intel.com --- include/drm/i915_gsc_proxy_mei_interface.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/drm/i915_gsc_proxy_mei_interface.h b/include/drm/i915_gsc_proxy_mei_interface.h index 9462341d3ae1..850dfbf40607 100644 --- a/include/drm/i915_gsc_proxy_mei_interface.h +++ b/include/drm/i915_gsc_proxy_mei_interface.h @@ -21,7 +21,7 @@ struct i915_gsc_proxy_component_ops { struct module *owner; /** - * send - Sends a proxy message to ME FW. + * @send: Sends a proxy message to ME FW. * @dev: device struct corresponding to the mei device * @buf: message buffer to send * @size: size of the message @@ -30,7 +30,7 @@ struct i915_gsc_proxy_component_ops { int (*send)(struct device *dev, const void *buf, size_t size); /** - * recv - Receives a proxy message from ME FW. + * @recv: Receives a proxy message from ME FW. * @dev: device struct corresponding to the mei device * @buf: message buffer to contain the received message * @size: size of the buffer -- cgit v1.2.3 From efcb7ef88a8c9ba027d36e0925b9c1ddce38c3bc Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Fri, 8 Mar 2024 13:55:44 +0200 Subject: drm/i915/hdcp: fix i915_hdcp_interface.h kernel-doc warnings Make the documentation match code. v2: Small fixups while at it (Lucas) Acked-by: Thomas Zimmermann Reviewed-by: Lucas De Marchi Signed-off-by: Jani Nikula Link: https://patchwork.freedesktop.org/patch/msgid/5c7ba8db172101c40b686463f169ec579a509f29.1709898638.git.jani.nikula@intel.com --- include/drm/i915_hdcp_interface.h | 18 +++++++++++++----- 1 file changed, 13 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/drm/i915_hdcp_interface.h b/include/drm/i915_hdcp_interface.h index 4c9c8167c2d5..d776ed7dcd00 100644 --- a/include/drm/i915_hdcp_interface.h +++ b/include/drm/i915_hdcp_interface.h @@ -54,7 +54,7 @@ enum hdcp_ddi { }; /** - * enum hdcp_tc - ME/GSC Firmware defined index for transcoders + * enum hdcp_transcoder - ME/GSC Firmware defined index for transcoders * @HDCP_INVALID_TRANSCODER: Index for Invalid transcoder * @HDCP_TRANSCODER_EDP: Index for EDP Transcoder * @HDCP_TRANSCODER_DSI0: Index for DSI0 Transcoder @@ -106,7 +106,7 @@ struct hdcp_port_data { * And Prepare AKE_Init. * @verify_receiver_cert_prepare_km: Verify the Receiver Certificate * AKE_Send_Cert and prepare - AKE_Stored_Km/AKE_No_Stored_Km + * AKE_Stored_Km/AKE_No_Stored_Km * @verify_hprime: Verify AKE_Send_H_prime * @store_pairing_info: Store pairing info received * @initiate_locality_check: Prepare LC_Init @@ -170,14 +170,22 @@ struct i915_hdcp_ops { /** * struct i915_hdcp_arbiter - Used for communication between i915 * and hdcp drivers for the HDCP2.2 services - * @hdcp_dev: device that provide the HDCP2.2 service from MEI Bus. - * @hdcp_ops: Ops implemented by hdcp driver or intel_hdcp_gsc , used by i915 driver. */ struct i915_hdcp_arbiter { + /** + * @hdcp_dev: device that provides the HDCP2.2 service from MEI Bus. + */ struct device *hdcp_dev; + + /** + * @ops: Ops implemented by hdcp driver or intel_hdcp_gsc, used by i915 + * driver. + */ const struct i915_hdcp_ops *ops; - /* To protect the above members. */ + /** + * @mutex: To protect the above members. + */ struct mutex mutex; }; -- cgit v1.2.3 From 6e0fe04fe8c8b1f5d3ce7cad4ac51cfde29c2bd1 Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Fri, 8 Mar 2024 13:55:45 +0200 Subject: drm/i915/pxp: fix i915_pxp_tee_interface.h kernel-doc warnings Make documentation match code. Slightly fix up the documentation comments while at it. v2: - Move comments next to members instead of struct comment (Lucas) - Small fixups while at it Cc: Lucas De Marchi Acked-by: Thomas Zimmermann Reviewed-by: Lucas De Marchi Signed-off-by: Jani Nikula Link: https://patchwork.freedesktop.org/patch/msgid/7c26256dc00f970f94d145b73e341c36f553dfe4.1709898638.git.jani.nikula@intel.com --- include/drm/i915_pxp_tee_interface.h | 27 ++++++++++++++++++++------- 1 file changed, 20 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/drm/i915_pxp_tee_interface.h b/include/drm/i915_pxp_tee_interface.h index 7d96985f2d05..a532d32f58f3 100644 --- a/include/drm/i915_pxp_tee_interface.h +++ b/include/drm/i915_pxp_tee_interface.h @@ -12,20 +12,26 @@ struct scatterlist; /** * struct i915_pxp_component_ops - ops for PXP services. - * @owner: Module providing the ops - * @send: sends data to PXP - * @receive: receives data from PXP */ struct i915_pxp_component_ops { /** - * @owner: owner of the module provding the ops + * @owner: Module providing the ops. */ struct module *owner; + /** + * @send: Send a PXP message. + */ int (*send)(struct device *dev, const void *message, size_t size, unsigned long timeout_ms); + /** + * @recv: Receive a PXP message. + */ int (*recv)(struct device *dev, void *buffer, size_t size, unsigned long timeout_ms); + /** + * @gsc_command: Send a GSC command. + */ ssize_t (*gsc_command)(struct device *dev, u8 client_id, u32 fence_id, struct scatterlist *sg_in, size_t total_in_len, struct scatterlist *sg_out); @@ -35,14 +41,21 @@ struct i915_pxp_component_ops { /** * struct i915_pxp_component - Used for communication between i915 and TEE * drivers for the PXP services - * @tee_dev: device that provide the PXP service from TEE Bus. - * @pxp_ops: Ops implemented by TEE driver, used by i915 driver. */ struct i915_pxp_component { + /** + * @tee_dev: device that provide the PXP service from TEE Bus. + */ struct device *tee_dev; + + /** + * @ops: Ops implemented by TEE driver, used by i915 driver. + */ const struct i915_pxp_component_ops *ops; - /* To protect the above members. */ + /** + * @mutex: To protect the above members. + */ struct mutex mutex; }; -- cgit v1.2.3 From 4f51e057c0a28f52fc17824c628cf3123b0ef12f Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Fri, 8 Mar 2024 18:07:50 +0200 Subject: drm/ttm: fix ttm_bo.h kernel-doc warnings MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Some renames, some formatting fixes, add some missing documentation. v3: Fix struct ttm_buffer_object .sg documentation (Christian) Cc: Christian Koenig Cc: Huang Rui Acked-by: Thomas Zimmermann Reviewed-by: Christian König Signed-off-by: Jani Nikula Link: https://patchwork.freedesktop.org/patch/msgid/20240308160750.3741833-1-jani.nikula@intel.com --- include/drm/ttm/ttm_bo.h | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/drm/ttm/ttm_bo.h b/include/drm/ttm/ttm_bo.h index 0223a41a64b2..6ccf96c91f3a 100644 --- a/include/drm/ttm/ttm_bo.h +++ b/include/drm/ttm/ttm_bo.h @@ -83,6 +83,9 @@ enum ttm_bo_type { * @resource: structure describing current placement. * @ttm: TTM structure holding system pages. * @deleted: True if the object is only a zombie and already deleted. + * @bulk_move: The bulk move object. + * @priority: Priority for LRU, BOs with lower priority are evicted first. + * @pin_count: Pin count. * * Base class for TTM buffer object, that deals with data placement and CPU * mappings. GPU mappings are really up to the driver, but for simpler GPUs @@ -128,26 +131,27 @@ struct ttm_buffer_object { struct work_struct delayed_delete; /** - * Special members that are protected by the reserve lock - * and the bo::lock when written to. Can be read with - * either of these locks held. + * @sg: external source of pages and DMA addresses, protected by the + * reservation lock. */ struct sg_table *sg; }; +#define TTM_BO_MAP_IOMEM_MASK 0x80 + /** * struct ttm_bo_kmap_obj * * @virtual: The current kernel virtual address. * @page: The page when kmap'ing a single page. * @bo_kmap_type: Type of bo_kmap. + * @bo: The TTM BO. * * Object describing a kernel mapping. Since a TTM bo may be located * in various memory types with various caching policies, the * mapping can either be an ioremap, a vmap, a kmap or part of a * premapped region. */ -#define TTM_BO_MAP_IOMEM_MASK 0x80 struct ttm_bo_kmap_obj { void *virtual; struct page *page; @@ -171,6 +175,7 @@ struct ttm_bo_kmap_obj { * @force_alloc: Don't check the memory account during suspend or CPU page * faults. Should only be used by TTM internally. * @resv: Reservation object to allow reserved evictions with. + * @bytes_moved: Statistics on how many bytes have been moved. * * Context for TTM operations like changing buffer placement or general memory * allocation. @@ -264,7 +269,7 @@ static inline int ttm_bo_reserve(struct ttm_buffer_object *bo, * ttm_bo_reserve_slowpath: * @bo: A pointer to a struct ttm_buffer_object. * @interruptible: Sleep interruptible if waiting. - * @sequence: Set (@bo)->sequence to this value after lock + * @ticket: Ticket used to acquire the ww_mutex. * * This is called after ttm_bo_reserve returns -EAGAIN and we backed off * from all our other reservations. Because there are no other reservations @@ -303,7 +308,7 @@ static inline void ttm_bo_assign_mem(struct ttm_buffer_object *bo, } /** - * ttm_bo_move_null = assign memory for a buffer object. + * ttm_bo_move_null - assign memory for a buffer object. * @bo: The bo to assign the memory to * @new_mem: The memory to be assigned. * -- cgit v1.2.3 From 2c6f6831876acabfc917248927e7622fa789eb24 Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Fri, 8 Mar 2024 13:55:48 +0200 Subject: drm/ttm: make ttm_caching.h self-contained MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Include for pgprot_t. Cc: Christian Koenig Cc: Huang Rui Acked-by: Thomas Zimmermann Reviewed-by: Christian König Reviewed-by: Alex Deucher Signed-off-by: Jani Nikula Link: https://patchwork.freedesktop.org/patch/msgid/fb87ab4b4490c53e9ece66d53c4f178ead244cb5.1709898638.git.jani.nikula@intel.com --- include/drm/ttm/ttm_caching.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/drm/ttm/ttm_caching.h b/include/drm/ttm/ttm_caching.h index 235a743d90e1..a18f43e93aba 100644 --- a/include/drm/ttm/ttm_caching.h +++ b/include/drm/ttm/ttm_caching.h @@ -25,6 +25,8 @@ #ifndef _TTM_CACHING_H_ #define _TTM_CACHING_H_ +#include + #define TTM_NUM_CACHING_TYPES 3 /** -- cgit v1.2.3 From bc6adc2e340bb3b59f85562ff4f47316015a95ae Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Fri, 8 Mar 2024 13:55:49 +0200 Subject: drm/ttm: fix ttm_execbuf_util.h kernel-doc warnings MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix some formatting errors and excess documentation. Cc: Christian Koenig Cc: Huang Rui Acked-by: Thomas Zimmermann Reviewed-by: Christian König Signed-off-by: Jani Nikula Link: https://patchwork.freedesktop.org/patch/msgid/b0f6d243c4e5eb1564ef2f4bb5bb834ee2c0305b.1709898638.git.jani.nikula@intel.com --- include/drm/ttm/ttm_execbuf_util.h | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/drm/ttm/ttm_execbuf_util.h b/include/drm/ttm/ttm_execbuf_util.h index 03aca29d3ce4..fac1e3e57ebd 100644 --- a/include/drm/ttm/ttm_execbuf_util.h +++ b/include/drm/ttm/ttm_execbuf_util.h @@ -52,7 +52,7 @@ struct ttm_validate_buffer { }; /** - * function ttm_eu_backoff_reservation + * ttm_eu_backoff_reservation * * @ticket: ww_acquire_ctx from reserve call * @list: thread private list of ttm_validate_buffer structs. @@ -64,14 +64,13 @@ void ttm_eu_backoff_reservation(struct ww_acquire_ctx *ticket, struct list_head *list); /** - * function ttm_eu_reserve_buffers + * ttm_eu_reserve_buffers * * @ticket: [out] ww_acquire_ctx filled in by call, or NULL if only * non-blocking reserves should be tried. * @list: thread private list of ttm_validate_buffer structs. * @intr: should the wait be interruptible * @dups: [out] optional list of duplicates. - * @del_lru: true if BOs should be removed from the LRU. * * Tries to reserve bos pointed to by the list entries for validation. * If the function returns 0, all buffers are marked as "unfenced", @@ -102,7 +101,7 @@ int ttm_eu_reserve_buffers(struct ww_acquire_ctx *ticket, struct list_head *dups); /** - * function ttm_eu_fence_buffer_objects. + * ttm_eu_fence_buffer_objects * * @ticket: ww_acquire_ctx from reserve call * @list: thread private list of ttm_validate_buffer structs. -- cgit v1.2.3 From c136883b10ce62c4101f96cd27c7f691fa7b9882 Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Fri, 8 Mar 2024 13:55:50 +0200 Subject: drm/ttm: fix ttm_kmap_iter.h kernel-doc warnings MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There's no proper way to document function pointer members, but at least silence the warnings. Cc: Christian Koenig Cc: Huang Rui Acked-by: Thomas Zimmermann Reviewed-by: Christian König Signed-off-by: Jani Nikula Link: https://patchwork.freedesktop.org/patch/msgid/e80e74ac4b6c5f1df3bc2dd98651ba289aae8e83.1709898638.git.jani.nikula@intel.com --- include/drm/ttm/ttm_kmap_iter.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/drm/ttm/ttm_kmap_iter.h b/include/drm/ttm/ttm_kmap_iter.h index cc5c09a211b4..fe72631a6e93 100644 --- a/include/drm/ttm/ttm_kmap_iter.h +++ b/include/drm/ttm/ttm_kmap_iter.h @@ -20,7 +20,7 @@ struct iosys_map; */ struct ttm_kmap_iter_ops { /** - * kmap_local() - Map a PAGE_SIZE part of the resource using + * @map_local: Map a PAGE_SIZE part of the resource using * kmap_local semantics. * @res_iter: Pointer to the struct ttm_kmap_iter representing * the resource. @@ -31,7 +31,7 @@ struct ttm_kmap_iter_ops { void (*map_local)(struct ttm_kmap_iter *res_iter, struct iosys_map *dmap, pgoff_t i); /** - * unmap_local() - Unmap a PAGE_SIZE part of the resource previously + * @unmap_local: Unmap a PAGE_SIZE part of the resource previously * mapped using kmap_local. * @res_iter: Pointer to the struct ttm_kmap_iter representing * the resource. -- cgit v1.2.3 From 2042ada01519d0751bcffa1434209ffb6b53bf96 Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Fri, 8 Mar 2024 13:55:51 +0200 Subject: drm/ttm: make ttm_pool.h self-contained MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit struct seq_file needs a forward declaration in some configs. Sort the forward declarations while at it. Cc: Christian Koenig Cc: Huang Rui Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202403072259.EEC2Vf1X-lkp@intel.com/ Reviewed-by: Christian König Reviewed-by: Alex Deucher Signed-off-by: Jani Nikula Link: https://patchwork.freedesktop.org/patch/msgid/b92373759bba305ddf8d24fdca345f195400e206.1709898638.git.jani.nikula@intel.com --- include/drm/ttm/ttm_pool.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/drm/ttm/ttm_pool.h b/include/drm/ttm/ttm_pool.h index 4490d43c63e3..160d954a261e 100644 --- a/include/drm/ttm/ttm_pool.h +++ b/include/drm/ttm/ttm_pool.h @@ -32,9 +32,10 @@ #include struct device; -struct ttm_tt; -struct ttm_pool; +struct seq_file; struct ttm_operation_ctx; +struct ttm_pool; +struct ttm_tt; /** * struct ttm_pool_type - Pool for a certain memory type -- cgit v1.2.3 From 8e3ed5440b0c305dcd1d5fa7419bd8066d22ef42 Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Fri, 8 Mar 2024 13:55:42 +0200 Subject: drm/i2c: silence ch7006.h and sil164.h kernel-doc warnings Mark some members private to silence kernel-doc warnings, and add FIXME comments. Acked-by: Thomas Zimmermann Signed-off-by: Jani Nikula Link: https://patchwork.freedesktop.org/patch/msgid/ffc58be256d71e6a98eb9f13337add64458d3476.1709898638.git.jani.nikula@intel.com --- include/drm/i2c/ch7006.h | 1 + include/drm/i2c/sil164.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include') diff --git a/include/drm/i2c/ch7006.h b/include/drm/i2c/ch7006.h index 8390b437a1f8..5305b9797f93 100644 --- a/include/drm/i2c/ch7006.h +++ b/include/drm/i2c/ch7006.h @@ -37,6 +37,7 @@ * meaning. */ struct ch7006_encoder_params { + /* private: FIXME: document the members */ enum { CH7006_FORMAT_RGB16 = 0, CH7006_FORMAT_YCrCb24m16, diff --git a/include/drm/i2c/sil164.h b/include/drm/i2c/sil164.h index 205e27384c83..ddf248693c8b 100644 --- a/include/drm/i2c/sil164.h +++ b/include/drm/i2c/sil164.h @@ -36,6 +36,7 @@ * See "http://www.siliconimage.com/docs/SiI-DS-0021-E-164.pdf". */ struct sil164_encoder_params { + /* private: FIXME: document the members */ enum { SIL164_INPUT_EDGE_FALLING = 0, SIL164_INPUT_EDGE_RISING -- cgit v1.2.3 From ec144244a43f6e4ca9767bf9fb1b2c9e293c2a31 Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Tue, 27 Feb 2024 11:14:48 +0100 Subject: drm/gem-shmem: Acquire reservation lock in GEM pin/unpin callbacks MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Export drm_gem_shmem_pin_locked() and acquire the reservation lock directly in GEM pin callback. Same for unpin. Prepares for further changes. Dma-buf locking semantics require callers to hold the buffer's reservation lock when invoking the pin and unpin callbacks. Prepare gem-shmem accordingly by pushing locking out of the implementation. A follow-up patch will fix locking for all GEM code at once. Signed-off-by: Thomas Zimmermann Reviewed-by: Dmitry Osipenko Tested-by: Dmitry Osipenko # virtio-gpu Acked-by: Christian König Acked-by: Zack Rusin Link: https://patchwork.freedesktop.org/patch/msgid/20240227113853.8464-2-tzimmermann@suse.de --- drivers/gpu/drm/drm_gem_shmem_helper.c | 6 ++++-- include/drm/drm_gem_shmem_helper.h | 16 ++++++++++++++-- 2 files changed, 18 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/drm_gem_shmem_helper.c b/drivers/gpu/drm/drm_gem_shmem_helper.c index e435f986cd13..0ac3dddb917f 100644 --- a/drivers/gpu/drm/drm_gem_shmem_helper.c +++ b/drivers/gpu/drm/drm_gem_shmem_helper.c @@ -228,7 +228,7 @@ void drm_gem_shmem_put_pages(struct drm_gem_shmem_object *shmem) } EXPORT_SYMBOL(drm_gem_shmem_put_pages); -static int drm_gem_shmem_pin_locked(struct drm_gem_shmem_object *shmem) +int drm_gem_shmem_pin_locked(struct drm_gem_shmem_object *shmem) { int ret; @@ -238,13 +238,15 @@ static int drm_gem_shmem_pin_locked(struct drm_gem_shmem_object *shmem) return ret; } +EXPORT_SYMBOL(drm_gem_shmem_pin_locked); -static void drm_gem_shmem_unpin_locked(struct drm_gem_shmem_object *shmem) +void drm_gem_shmem_unpin_locked(struct drm_gem_shmem_object *shmem) { dma_resv_assert_held(shmem->base.resv); drm_gem_shmem_put_pages(shmem); } +EXPORT_SYMBOL(drm_gem_shmem_unpin_locked); /** * drm_gem_shmem_pin - Pin backing pages for a shmem GEM object diff --git a/include/drm/drm_gem_shmem_helper.h b/include/drm/drm_gem_shmem_helper.h index bf0c31aa8fbe..eb12aa9a8c55 100644 --- a/include/drm/drm_gem_shmem_helper.h +++ b/include/drm/drm_gem_shmem_helper.h @@ -108,6 +108,9 @@ void drm_gem_shmem_vunmap(struct drm_gem_shmem_object *shmem, struct iosys_map *map); int drm_gem_shmem_mmap(struct drm_gem_shmem_object *shmem, struct vm_area_struct *vma); +int drm_gem_shmem_pin_locked(struct drm_gem_shmem_object *shmem); +void drm_gem_shmem_unpin_locked(struct drm_gem_shmem_object *shmem); + int drm_gem_shmem_madvise(struct drm_gem_shmem_object *shmem, int madv); static inline bool drm_gem_shmem_is_purgeable(struct drm_gem_shmem_object *shmem) @@ -172,8 +175,15 @@ static inline void drm_gem_shmem_object_print_info(struct drm_printer *p, unsign static inline int drm_gem_shmem_object_pin(struct drm_gem_object *obj) { struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj); + int ret; + + ret = dma_resv_lock_interruptible(shmem->base.resv, NULL); + if (ret) + return ret; + ret = drm_gem_shmem_pin_locked(shmem); + dma_resv_unlock(shmem->base.resv); - return drm_gem_shmem_pin(shmem); + return ret; } /** @@ -187,7 +197,9 @@ static inline void drm_gem_shmem_object_unpin(struct drm_gem_object *obj) { struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj); - drm_gem_shmem_unpin(shmem); + dma_resv_lock(shmem->base.resv, NULL); + drm_gem_shmem_unpin_locked(shmem); + dma_resv_unlock(shmem->base.resv); } /** -- cgit v1.2.3 From a78027847226493ea6f09a00875fa4871fd29e69 Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Tue, 27 Feb 2024 11:14:56 +0100 Subject: drm/gem: Acquire reservation lock in drm_gem_{pin/unpin}() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Acquire the buffer object's reservation lock in drm_gem_pin() and remove locking the drivers' GEM callbacks where necessary. Same for unpin(). DRM drivers and memory managers modified by this patch will now have correct dma-buf locking semantics: the caller is responsible for holding the reservation lock when calling the pin or unpin callback. DRM drivers and memory managers that are not modified will now be protected against concurent invocation of their pin and unpin callbacks. PRIME does not implement struct dma_buf_ops.pin, which requires the caller to hold the reservation lock. It does implement struct dma_buf_ops.attach, which requires to callee to acquire the reservation lock. The PRIME code uses drm_gem_pin(), so locks are now taken as specified. Same for unpin and detach. The patch harmonizes GEM pin and unpin to have non-interruptible reservation locking across all drivers, as is already the case for vmap and vunmap. This affects gem-shmem, gem-vram, loongson, qxl and radeon. Signed-off-by: Thomas Zimmermann Reviewed-by: Christian König Reviewed-by: Zack Rusin Reviewed-by: Dmitry Osipenko Tested-by: Dmitry Osipenko # virtio-gpu Link: https://patchwork.freedesktop.org/patch/msgid/20240227113853.8464-10-tzimmermann@suse.de --- drivers/gpu/drm/drm_gem.c | 22 ++++++++++++++++++++-- drivers/gpu/drm/drm_gem_vram_helper.c | 15 +-------------- drivers/gpu/drm/drm_internal.h | 2 ++ drivers/gpu/drm/loongson/lsdc_gem.c | 13 ++----------- drivers/gpu/drm/msm/msm_gem_prime.c | 4 ---- drivers/gpu/drm/nouveau/nouveau_prime.c | 11 ----------- drivers/gpu/drm/qxl/qxl_prime.c | 14 +------------- drivers/gpu/drm/radeon/radeon_prime.c | 11 ----------- drivers/gpu/drm/vmwgfx/vmwgfx_gem.c | 25 ++++++------------------- include/drm/drm_gem_shmem_helper.h | 11 +---------- 10 files changed, 33 insertions(+), 95 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c index 44a948b80ee1..e0f80c6a7096 100644 --- a/drivers/gpu/drm/drm_gem.c +++ b/drivers/gpu/drm/drm_gem.c @@ -1161,7 +1161,7 @@ void drm_gem_print_info(struct drm_printer *p, unsigned int indent, obj->funcs->print_info(p, indent, obj); } -int drm_gem_pin(struct drm_gem_object *obj) +int drm_gem_pin_locked(struct drm_gem_object *obj) { if (obj->funcs->pin) return obj->funcs->pin(obj); @@ -1169,12 +1169,30 @@ int drm_gem_pin(struct drm_gem_object *obj) return 0; } -void drm_gem_unpin(struct drm_gem_object *obj) +void drm_gem_unpin_locked(struct drm_gem_object *obj) { if (obj->funcs->unpin) obj->funcs->unpin(obj); } +int drm_gem_pin(struct drm_gem_object *obj) +{ + int ret; + + dma_resv_lock(obj->resv, NULL); + ret = drm_gem_pin_locked(obj); + dma_resv_unlock(obj->resv); + + return ret; +} + +void drm_gem_unpin(struct drm_gem_object *obj) +{ + dma_resv_lock(obj->resv, NULL); + drm_gem_unpin_locked(obj); + dma_resv_unlock(obj->resv); +} + int drm_gem_vmap(struct drm_gem_object *obj, struct iosys_map *map) { int ret; diff --git a/drivers/gpu/drm/drm_gem_vram_helper.c b/drivers/gpu/drm/drm_gem_vram_helper.c index 15029d89badf..5a16b3e0a413 100644 --- a/drivers/gpu/drm/drm_gem_vram_helper.c +++ b/drivers/gpu/drm/drm_gem_vram_helper.c @@ -774,11 +774,6 @@ EXPORT_SYMBOL(drm_gem_vram_simple_display_pipe_cleanup_fb); static int drm_gem_vram_object_pin(struct drm_gem_object *gem) { struct drm_gem_vram_object *gbo = drm_gem_vram_of_gem(gem); - int ret; - - ret = ttm_bo_reserve(&gbo->bo, true, false, NULL); - if (ret) - return ret; /* * Fbdev console emulation is the use case of these PRIME @@ -789,10 +784,7 @@ static int drm_gem_vram_object_pin(struct drm_gem_object *gem) * the buffer to be pinned to VRAM, implement a callback that * sets the flags accordingly. */ - ret = drm_gem_vram_pin_locked(gbo, 0); - ttm_bo_unreserve(&gbo->bo); - - return ret; + return drm_gem_vram_pin_locked(gbo, 0); } /** @@ -803,13 +795,8 @@ static int drm_gem_vram_object_pin(struct drm_gem_object *gem) static void drm_gem_vram_object_unpin(struct drm_gem_object *gem) { struct drm_gem_vram_object *gbo = drm_gem_vram_of_gem(gem); - int ret; - ret = ttm_bo_reserve(&gbo->bo, true, false, NULL); - if (ret) - return; drm_gem_vram_unpin_locked(gbo); - ttm_bo_unreserve(&gbo->bo); } /** diff --git a/drivers/gpu/drm/drm_internal.h b/drivers/gpu/drm/drm_internal.h index d69744c9ac15..2215baef9a3e 100644 --- a/drivers/gpu/drm/drm_internal.h +++ b/drivers/gpu/drm/drm_internal.h @@ -173,6 +173,8 @@ void drm_gem_release(struct drm_device *dev, struct drm_file *file_private); void drm_gem_print_info(struct drm_printer *p, unsigned int indent, const struct drm_gem_object *obj); +int drm_gem_pin_locked(struct drm_gem_object *obj); +void drm_gem_unpin_locked(struct drm_gem_object *obj); int drm_gem_pin(struct drm_gem_object *obj); void drm_gem_unpin(struct drm_gem_object *obj); int drm_gem_vmap(struct drm_gem_object *obj, struct iosys_map *map); diff --git a/drivers/gpu/drm/loongson/lsdc_gem.c b/drivers/gpu/drm/loongson/lsdc_gem.c index 04293df2f0de..a720d8f53209 100644 --- a/drivers/gpu/drm/loongson/lsdc_gem.c +++ b/drivers/gpu/drm/loongson/lsdc_gem.c @@ -19,33 +19,24 @@ static int lsdc_gem_prime_pin(struct drm_gem_object *obj) struct lsdc_bo *lbo = gem_to_lsdc_bo(obj); int ret; - ret = lsdc_bo_reserve(lbo); - if (unlikely(ret)) - return ret; + dma_resv_assert_held(obj->resv); ret = lsdc_bo_pin(lbo, LSDC_GEM_DOMAIN_GTT, NULL); if (likely(ret == 0)) lbo->sharing_count++; - lsdc_bo_unreserve(lbo); - return ret; } static void lsdc_gem_prime_unpin(struct drm_gem_object *obj) { struct lsdc_bo *lbo = gem_to_lsdc_bo(obj); - int ret; - ret = lsdc_bo_reserve(lbo); - if (unlikely(ret)) - return; + dma_resv_assert_held(obj->resv); lsdc_bo_unpin(lbo); if (lbo->sharing_count) lbo->sharing_count--; - - lsdc_bo_unreserve(lbo); } static struct sg_table *lsdc_gem_prime_get_sg_table(struct drm_gem_object *obj) diff --git a/drivers/gpu/drm/msm/msm_gem_prime.c b/drivers/gpu/drm/msm/msm_gem_prime.c index 0d22df53ab98..ee267490c935 100644 --- a/drivers/gpu/drm/msm/msm_gem_prime.c +++ b/drivers/gpu/drm/msm/msm_gem_prime.c @@ -53,11 +53,9 @@ int msm_gem_prime_pin(struct drm_gem_object *obj) if (obj->import_attach) return 0; - msm_gem_lock(obj); pages = msm_gem_pin_pages_locked(obj); if (IS_ERR(pages)) ret = PTR_ERR(pages); - msm_gem_unlock(obj); return ret; } @@ -67,7 +65,5 @@ void msm_gem_prime_unpin(struct drm_gem_object *obj) if (obj->import_attach) return; - msm_gem_lock(obj); msm_gem_unpin_pages_locked(obj); - msm_gem_unlock(obj); } diff --git a/drivers/gpu/drm/nouveau/nouveau_prime.c b/drivers/gpu/drm/nouveau/nouveau_prime.c index 774f9bd03110..b58ab595faf8 100644 --- a/drivers/gpu/drm/nouveau/nouveau_prime.c +++ b/drivers/gpu/drm/nouveau/nouveau_prime.c @@ -86,17 +86,12 @@ unlock: int nouveau_gem_prime_pin(struct drm_gem_object *obj) { struct nouveau_bo *nvbo = nouveau_gem_object(obj); - struct ttm_buffer_object *bo = &nvbo->bo; int ret; - ret = ttm_bo_reserve(bo, false, false, NULL); - if (ret) - return -EINVAL; /* pin buffer into GTT */ ret = nouveau_bo_pin_locked(nvbo, NOUVEAU_GEM_DOMAIN_GART, false); if (ret) ret = -EINVAL; - ttm_bo_unreserve(bo); return ret; } @@ -104,14 +99,8 @@ int nouveau_gem_prime_pin(struct drm_gem_object *obj) void nouveau_gem_prime_unpin(struct drm_gem_object *obj) { struct nouveau_bo *nvbo = nouveau_gem_object(obj); - struct ttm_buffer_object *bo = &nvbo->bo; - int ret; - ret = ttm_bo_reserve(bo, false, false, NULL); - if (ret) - return; nouveau_bo_unpin_locked(nvbo); - ttm_bo_unreserve(bo); } struct dma_buf *nouveau_gem_prime_export(struct drm_gem_object *gobj, diff --git a/drivers/gpu/drm/qxl/qxl_prime.c b/drivers/gpu/drm/qxl/qxl_prime.c index f2646603e12e..19bf551a7b31 100644 --- a/drivers/gpu/drm/qxl/qxl_prime.c +++ b/drivers/gpu/drm/qxl/qxl_prime.c @@ -31,27 +31,15 @@ int qxl_gem_prime_pin(struct drm_gem_object *obj) { struct qxl_bo *bo = gem_to_qxl_bo(obj); - int r; - r = qxl_bo_reserve(bo); - if (r) - return r; - r = qxl_bo_pin_locked(bo); - qxl_bo_unreserve(bo); - - return r; + return qxl_bo_pin_locked(bo); } void qxl_gem_prime_unpin(struct drm_gem_object *obj) { struct qxl_bo *bo = gem_to_qxl_bo(obj); - int r; - r = qxl_bo_reserve(bo); - if (r) - return; qxl_bo_unpin_locked(bo); - qxl_bo_unreserve(bo); } struct sg_table *qxl_gem_prime_get_sg_table(struct drm_gem_object *obj) diff --git a/drivers/gpu/drm/radeon/radeon_prime.c b/drivers/gpu/drm/radeon/radeon_prime.c index b3cfc99f4d7e..a77881f035e7 100644 --- a/drivers/gpu/drm/radeon/radeon_prime.c +++ b/drivers/gpu/drm/radeon/radeon_prime.c @@ -73,32 +73,21 @@ int radeon_gem_prime_pin(struct drm_gem_object *obj) struct radeon_bo *bo = gem_to_radeon_bo(obj); int ret = 0; - ret = radeon_bo_reserve(bo, false); - if (unlikely(ret != 0)) - return ret; - /* pin buffer into GTT */ ret = radeon_bo_pin(bo, RADEON_GEM_DOMAIN_GTT, NULL); if (likely(ret == 0)) bo->prime_shared_count++; - radeon_bo_unreserve(bo); return ret; } void radeon_gem_prime_unpin(struct drm_gem_object *obj) { struct radeon_bo *bo = gem_to_radeon_bo(obj); - int ret = 0; - - ret = radeon_bo_reserve(bo, false); - if (unlikely(ret != 0)) - return; radeon_bo_unpin(bo); if (bo->prime_shared_count) bo->prime_shared_count--; - radeon_bo_unreserve(bo); } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_gem.c b/drivers/gpu/drm/vmwgfx/vmwgfx_gem.c index 12787bb9c111..186150f41fbc 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_gem.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_gem.c @@ -48,33 +48,20 @@ static void vmw_gem_object_close(struct drm_gem_object *obj, { } -static int vmw_gem_pin_private(struct drm_gem_object *obj, bool do_pin) +static int vmw_gem_object_pin(struct drm_gem_object *obj) { - struct ttm_buffer_object *bo = drm_gem_ttm_of_gem(obj); struct vmw_bo *vbo = to_vmw_bo(obj); - int ret; - - ret = ttm_bo_reserve(bo, false, false, NULL); - if (unlikely(ret != 0)) - goto err; - - vmw_bo_pin_reserved(vbo, do_pin); - - ttm_bo_unreserve(bo); - -err: - return ret; -} + vmw_bo_pin_reserved(vbo, true); -static int vmw_gem_object_pin(struct drm_gem_object *obj) -{ - return vmw_gem_pin_private(obj, true); + return 0; } static void vmw_gem_object_unpin(struct drm_gem_object *obj) { - vmw_gem_pin_private(obj, false); + struct vmw_bo *vbo = to_vmw_bo(obj); + + vmw_bo_pin_reserved(vbo, false); } static struct sg_table *vmw_gem_object_get_sg_table(struct drm_gem_object *obj) diff --git a/include/drm/drm_gem_shmem_helper.h b/include/drm/drm_gem_shmem_helper.h index eb12aa9a8c55..efbc9f27312b 100644 --- a/include/drm/drm_gem_shmem_helper.h +++ b/include/drm/drm_gem_shmem_helper.h @@ -175,15 +175,8 @@ static inline void drm_gem_shmem_object_print_info(struct drm_printer *p, unsign static inline int drm_gem_shmem_object_pin(struct drm_gem_object *obj) { struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj); - int ret; - ret = dma_resv_lock_interruptible(shmem->base.resv, NULL); - if (ret) - return ret; - ret = drm_gem_shmem_pin_locked(shmem); - dma_resv_unlock(shmem->base.resv); - - return ret; + return drm_gem_shmem_pin_locked(shmem); } /** @@ -197,9 +190,7 @@ static inline void drm_gem_shmem_object_unpin(struct drm_gem_object *obj) { struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj); - dma_resv_lock(shmem->base.resv, NULL); drm_gem_shmem_unpin_locked(shmem); - dma_resv_unlock(shmem->base.resv); } /** -- cgit v1.2.3 From b4b0193e83cb987143583e2b4011b35331f429bd Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Tue, 27 Feb 2024 11:14:57 +0100 Subject: drm/fbdev-generic: Fix locking with drm_client_buffer_vmap_local() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Temporarily lock the fbdev buffer object during updates to prevent memory managers from evicting/moving the buffer. Moving a buffer object while update its content results in undefined behaviour. Fbdev-generic updates its buffer object from a shadow buffer. Gem-shmem and gem-dma helpers do not move buffer objects, so they are safe to be used with fbdev-generic. Gem-vram and qxl are based on TTM, but pin buffer objects are part of the vmap operation. So both are also safe to be used with fbdev-generic. Amdgpu and nouveau do not pin or lock the buffer object during an update. Their TTM-based memory management could move the buffer object while the update is ongoing. The new vmap_local and vunmap_local helpers hold the buffer object's reservation lock during the buffer update. This prevents moving the buffer object on all memory managers. Signed-off-by: Thomas Zimmermann Reviewed-by: Christian König Reviewed-by: Dmitry Osipenko Tested-by: Dmitry Osipenko # virtio-gpu Acked-by: Zack Rusin Link: https://patchwork.freedesktop.org/patch/msgid/20240227113853.8464-11-tzimmermann@suse.de --- drivers/gpu/drm/drm_client.c | 68 ++++++++++++++++++++++++++++++++----- drivers/gpu/drm/drm_fbdev_generic.c | 4 +-- drivers/gpu/drm/drm_gem.c | 12 +++++++ include/drm/drm_client.h | 10 ++++++ include/drm/drm_gem.h | 3 ++ 5 files changed, 87 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/drm_client.c b/drivers/gpu/drm/drm_client.c index 9403b3f576f7..2cc81831236b 100644 --- a/drivers/gpu/drm/drm_client.c +++ b/drivers/gpu/drm/drm_client.c @@ -304,6 +304,66 @@ err_delete: return ERR_PTR(ret); } +/** + * drm_client_buffer_vmap_local - Map DRM client buffer into address space + * @buffer: DRM client buffer + * @map_copy: Returns the mapped memory's address + * + * This function maps a client buffer into kernel address space. If the + * buffer is already mapped, it returns the existing mapping's address. + * + * Client buffer mappings are not ref'counted. Each call to + * drm_client_buffer_vmap_local() should be closely followed by a call to + * drm_client_buffer_vunmap_local(). See drm_client_buffer_vmap() for + * long-term mappings. + * + * The returned address is a copy of the internal value. In contrast to + * other vmap interfaces, you don't need it for the client's vunmap + * function. So you can modify it at will during blit and draw operations. + * + * Returns: + * 0 on success, or a negative errno code otherwise. + */ +int drm_client_buffer_vmap_local(struct drm_client_buffer *buffer, + struct iosys_map *map_copy) +{ + struct drm_gem_object *gem = buffer->gem; + struct iosys_map *map = &buffer->map; + int ret; + + drm_gem_lock(gem); + + ret = drm_gem_vmap(gem, map); + if (ret) + goto err_drm_gem_vmap_unlocked; + *map_copy = *map; + + return 0; + +err_drm_gem_vmap_unlocked: + drm_gem_unlock(gem); + return 0; +} +EXPORT_SYMBOL(drm_client_buffer_vmap_local); + +/** + * drm_client_buffer_vunmap_local - Unmap DRM client buffer + * @buffer: DRM client buffer + * + * This function removes a client buffer's memory mapping established + * with drm_client_buffer_vunmap_local(). Calling this function is only + * required by clients that manage their buffer mappings by themselves. + */ +void drm_client_buffer_vunmap_local(struct drm_client_buffer *buffer) +{ + struct drm_gem_object *gem = buffer->gem; + struct iosys_map *map = &buffer->map; + + drm_gem_vunmap(gem, map); + drm_gem_unlock(gem); +} +EXPORT_SYMBOL(drm_client_buffer_vunmap_local); + /** * drm_client_buffer_vmap - Map DRM client buffer into address space * @buffer: DRM client buffer @@ -331,14 +391,6 @@ drm_client_buffer_vmap(struct drm_client_buffer *buffer, struct iosys_map *map = &buffer->map; int ret; - /* - * FIXME: The dependency on GEM here isn't required, we could - * convert the driver handle to a dma-buf instead and use the - * backend-agnostic dma-buf vmap support instead. This would - * require that the handle2fd prime ioctl is reworked to pull the - * fd_install step out of the driver backend hooks, to make that - * final step optional for internal users. - */ ret = drm_gem_vmap_unlocked(buffer->gem, map); if (ret) return ret; diff --git a/drivers/gpu/drm/drm_fbdev_generic.c b/drivers/gpu/drm/drm_fbdev_generic.c index d647d89764cb..be357f926fae 100644 --- a/drivers/gpu/drm/drm_fbdev_generic.c +++ b/drivers/gpu/drm/drm_fbdev_generic.c @@ -197,14 +197,14 @@ static int drm_fbdev_generic_damage_blit(struct drm_fb_helper *fb_helper, */ mutex_lock(&fb_helper->lock); - ret = drm_client_buffer_vmap(buffer, &map); + ret = drm_client_buffer_vmap_local(buffer, &map); if (ret) goto out; dst = map; drm_fbdev_generic_damage_blit_real(fb_helper, clip, &dst); - drm_client_buffer_vunmap(buffer); + drm_client_buffer_vunmap_local(buffer); out: mutex_unlock(&fb_helper->lock); diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c index e0f80c6a7096..d4bbc5d109c8 100644 --- a/drivers/gpu/drm/drm_gem.c +++ b/drivers/gpu/drm/drm_gem.c @@ -1227,6 +1227,18 @@ void drm_gem_vunmap(struct drm_gem_object *obj, struct iosys_map *map) } EXPORT_SYMBOL(drm_gem_vunmap); +void drm_gem_lock(struct drm_gem_object *obj) +{ + dma_resv_lock(obj->resv, NULL); +} +EXPORT_SYMBOL(drm_gem_lock); + +void drm_gem_unlock(struct drm_gem_object *obj) +{ + dma_resv_unlock(obj->resv); +} +EXPORT_SYMBOL(drm_gem_unlock); + int drm_gem_vmap_unlocked(struct drm_gem_object *obj, struct iosys_map *map) { int ret; diff --git a/include/drm/drm_client.h b/include/drm/drm_client.h index d47458ecdac4..bc0e66f9c425 100644 --- a/include/drm/drm_client.h +++ b/include/drm/drm_client.h @@ -141,6 +141,13 @@ struct drm_client_buffer { /** * @gem: GEM object backing this buffer + * + * FIXME: The dependency on GEM here isn't required, we could + * convert the driver handle to a dma-buf instead and use the + * backend-agnostic dma-buf vmap support instead. This would + * require that the handle2fd prime ioctl is reworked to pull the + * fd_install step out of the driver backend hooks, to make that + * final step optional for internal users. */ struct drm_gem_object *gem; @@ -159,6 +166,9 @@ struct drm_client_buffer * drm_client_framebuffer_create(struct drm_client_dev *client, u32 width, u32 height, u32 format); void drm_client_framebuffer_delete(struct drm_client_buffer *buffer); int drm_client_framebuffer_flush(struct drm_client_buffer *buffer, struct drm_rect *rect); +int drm_client_buffer_vmap_local(struct drm_client_buffer *buffer, + struct iosys_map *map_copy); +void drm_client_buffer_vunmap_local(struct drm_client_buffer *buffer); int drm_client_buffer_vmap(struct drm_client_buffer *buffer, struct iosys_map *map); void drm_client_buffer_vunmap(struct drm_client_buffer *buffer); diff --git a/include/drm/drm_gem.h b/include/drm/drm_gem.h index 2ebec3984cd4..bae4865b2101 100644 --- a/include/drm/drm_gem.h +++ b/include/drm/drm_gem.h @@ -527,6 +527,9 @@ struct page **drm_gem_get_pages(struct drm_gem_object *obj); void drm_gem_put_pages(struct drm_gem_object *obj, struct page **pages, bool dirty, bool accessed); +void drm_gem_lock(struct drm_gem_object *obj); +void drm_gem_unlock(struct drm_gem_object *obj); + int drm_gem_vmap_unlocked(struct drm_gem_object *obj, struct iosys_map *map); void drm_gem_vunmap_unlocked(struct drm_gem_object *obj, struct iosys_map *map); -- cgit v1.2.3 From 38d707c54df4ca58cd9ceae2ddcbd6f606b99e9f Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Fri, 8 Mar 2024 11:58:54 +0100 Subject: sched/balancing: Change 'enum cpu_idle_type' to have more natural definitions The cpu_idle_type enum has the confusingly inverted property that 'not idle' is 1, and 'idle' is '0'. This resulted in a number of unnecessary complications in the code. Reverse the order, remove the CPU_NOT_IDLE type, and convert all code to a natural boolean form. It's much more readable: - enum cpu_idle_type idle = this_rq->idle_balance ? - CPU_IDLE : CPU_NOT_IDLE; - + enum cpu_idle_type idle = this_rq->idle_balance; -------------------------------- - if (env->idle == CPU_NOT_IDLE || !busiest->sum_nr_running) + if (!env->idle || !busiest->sum_nr_running) -------------------------------- And gets rid of the double negation in these usages: - if (env->idle != CPU_NOT_IDLE && env->src_rq->nr_running <= 1) + if (env->idle && env->src_rq->nr_running <= 1) Furthermore, this makes code much more obvious where there's differentiation between CPU_IDLE and CPU_NEWLY_IDLE. Signed-off-by: Ingo Molnar Reviewed-by: Valentin Schneider Reviewed-by: Vincent Guittot Cc: "Gautham R. Shenoy" Link: https://lore.kernel.org/r/20240308105901.1096078-4-mingo@kernel.org --- include/linux/sched/idle.h | 2 +- kernel/sched/fair.c | 27 ++++++++++++--------------- 2 files changed, 13 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/include/linux/sched/idle.h b/include/linux/sched/idle.h index 478084f9105e..e670ac282333 100644 --- a/include/linux/sched/idle.h +++ b/include/linux/sched/idle.h @@ -5,8 +5,8 @@ #include enum cpu_idle_type { + __CPU_NOT_IDLE = 0, CPU_IDLE, - CPU_NOT_IDLE, CPU_NEWLY_IDLE, CPU_MAX_IDLE_TYPES }; diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 2ef89b36aed1..3a510cf1fb00 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -9070,7 +9070,7 @@ static int detach_tasks(struct lb_env *env) * We don't want to steal all, otherwise we may be treated likewise, * which could at worst lead to a livelock crash. */ - if (env->idle != CPU_NOT_IDLE && env->src_rq->nr_running <= 1) + if (env->idle && env->src_rq->nr_running <= 1) break; env->loop++; @@ -9803,7 +9803,7 @@ static inline bool smt_vs_nonsmt_groups(struct sched_group *sg1, static inline bool smt_balance(struct lb_env *env, struct sg_lb_stats *sgs, struct sched_group *group) { - if (env->idle == CPU_NOT_IDLE) + if (!env->idle) return false; /* @@ -9827,7 +9827,7 @@ static inline long sibling_imbalance(struct lb_env *env, int ncores_busiest, ncores_local; long imbalance; - if (env->idle == CPU_NOT_IDLE || !busiest->sum_nr_running) + if (!env->idle || !busiest->sum_nr_running) return 0; ncores_busiest = sds->busiest->cores; @@ -9927,8 +9927,7 @@ static inline void update_sg_lb_stats(struct lb_env *env, sgs->group_misfit_task_load = rq->misfit_task_load; *sg_status |= SG_OVERLOAD; } - } else if ((env->idle != CPU_NOT_IDLE) && - sched_reduced_capacity(rq, env->sd)) { + } else if (env->idle && sched_reduced_capacity(rq, env->sd)) { /* Check for a task running on a CPU with reduced capacity */ if (sgs->group_misfit_task_load < load) sgs->group_misfit_task_load = load; @@ -9940,7 +9939,7 @@ static inline void update_sg_lb_stats(struct lb_env *env, sgs->group_weight = group->group_weight; /* Check if dst CPU is idle and preferred to this group */ - if (!local_group && env->idle != CPU_NOT_IDLE && sgs->sum_h_nr_running && + if (!local_group && env->idle && sgs->sum_h_nr_running && sched_group_asym(env, sgs, group)) sgs->group_asym_packing = 1; @@ -10698,7 +10697,7 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s * waiting task in this overloaded busiest group. Let's * try to pull it. */ - if (env->idle != CPU_NOT_IDLE && env->imbalance == 0) { + if (env->idle && env->imbalance == 0) { env->migration_type = migrate_task; env->imbalance = 1; } @@ -10913,7 +10912,7 @@ static struct sched_group *find_busiest_group(struct lb_env *env) goto force_balance; if (busiest->group_type != group_overloaded) { - if (env->idle == CPU_NOT_IDLE) { + if (!env->idle) { /* * If the busiest group is not overloaded (and as a * result the local one too) but this CPU is already @@ -11121,7 +11120,7 @@ asym_active_balance(struct lb_env *env) * the lower priority @env::dst_cpu help it. Do not follow * CPU priority. */ - return env->idle != CPU_NOT_IDLE && sched_use_asym_prio(env->sd, env->dst_cpu) && + return env->idle && sched_use_asym_prio(env->sd, env->dst_cpu) && (sched_asym_prefer(env->dst_cpu, env->src_cpu) || !sched_use_asym_prio(env->sd, env->src_cpu)); } @@ -11159,7 +11158,7 @@ static int need_active_balance(struct lb_env *env) * because of other sched_class or IRQs if more capacity stays * available on dst_cpu. */ - if ((env->idle != CPU_NOT_IDLE) && + if (env->idle && (env->src_rq->cfs.h_nr_running == 1)) { if ((check_cpu_capacity(env->src_rq, sd)) && (capacity_of(env->src_cpu)*sd->imbalance_pct < capacity_of(env->dst_cpu)*100)) @@ -11735,8 +11734,8 @@ static void rebalance_domains(struct rq *rq, enum cpu_idle_type idle) * env->dst_cpu, so we can't know our idle * state even if we migrated tasks. Update it. */ - idle = idle_cpu(cpu) ? CPU_IDLE : CPU_NOT_IDLE; - busy = idle != CPU_IDLE && !sched_idle_cpu(cpu); + idle = idle_cpu(cpu); + busy = !idle && !sched_idle_cpu(cpu); } sd->last_balance = jiffies; interval = get_sd_balance_interval(sd, busy); @@ -12416,9 +12415,7 @@ out: static __latent_entropy void run_rebalance_domains(struct softirq_action *h) { struct rq *this_rq = this_rq(); - enum cpu_idle_type idle = this_rq->idle_balance ? - CPU_IDLE : CPU_NOT_IDLE; - + enum cpu_idle_type idle = this_rq->idle_balance; /* * If this CPU has a pending nohz_balance_kick, then do the * balancing on behalf of the other idle CPUs whose ticks are -- cgit v1.2.3 From 86dd6c04ef9f213e14d60c9f64bce1cc019f816e Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Fri, 8 Mar 2024 12:18:08 +0100 Subject: sched/balancing: Rename scheduler_tick() => sched_tick() - Standardize on prefixing scheduler-internal functions defined in with sched_*() prefix. scheduler_tick() was the only function using the scheduler_ prefix. Harmonize it. - The other reason to rename it is the NOHZ scheduler tick handling functions are already named sched_tick_*(). Make the 'git grep sched_tick' more meaningful. Signed-off-by: Ingo Molnar Acked-by: Valentin Schneider Reviewed-by: Shrikanth Hegde Link: https://lore.kernel.org/r/20240308111819.1101550-3-mingo@kernel.org --- Documentation/scheduler/sched-domains.rst | 4 ++-- Documentation/translations/zh_CN/scheduler/sched-domains.rst | 4 ++-- include/linux/sched.h | 2 +- kernel/sched/core.c | 4 ++-- kernel/sched/loadavg.c | 2 +- kernel/time/timer.c | 2 +- kernel/workqueue.c | 2 +- tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc | 2 +- 8 files changed, 11 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/Documentation/scheduler/sched-domains.rst b/Documentation/scheduler/sched-domains.rst index 6577b068f921..541d6c617971 100644 --- a/Documentation/scheduler/sched-domains.rst +++ b/Documentation/scheduler/sched-domains.rst @@ -32,13 +32,13 @@ load of each of its member CPUs, and only when the load of a group becomes out of balance are tasks moved between groups. In kernel/sched/core.c, trigger_load_balance() is run periodically on each CPU -through scheduler_tick(). It raises a softirq after the next regularly scheduled +through sched_tick(). It raises a softirq after the next regularly scheduled rebalancing event for the current runqueue has arrived. The actual load balancing workhorse, sched_balance_softirq()->rebalance_domains(), is then run in softirq context (SCHED_SOFTIRQ). The latter function takes two arguments: the runqueue of current CPU and whether -the CPU was idle at the time the scheduler_tick() happened and iterates over all +the CPU was idle at the time the sched_tick() happened and iterates over all sched domains our CPU is on, starting from its base domain and going up the ->parent chain. While doing that, it checks to see if the current domain has exhausted its rebalance interval. If so, it runs load_balance() on that domain. It then checks diff --git a/Documentation/translations/zh_CN/scheduler/sched-domains.rst b/Documentation/translations/zh_CN/scheduler/sched-domains.rst index fbc326668e37..fa0c0bcc6ba5 100644 --- a/Documentation/translations/zh_CN/scheduler/sched-domains.rst +++ b/Documentation/translations/zh_CN/scheduler/sched-domains.rst @@ -34,12 +34,12 @@ CPU共享。任意两个组的CPU掩码的交集不一定为空，如果是这 调度域中的负载均衡发生在调度组中。也就是说，每个组被视为一个实体。组的负载被定义为它 管辖的每个CPU的负载之和。仅当组的负载不均衡后，任务才在组之间发生迁移。 -在kernel/sched/core.c中，trigger_load_balance()在每个CPU上通过scheduler_tick() +在kernel/sched/core.c中，trigger_load_balance()在每个CPU上通过sched_tick() 周期执行。在当前运行队列下一个定期调度再平衡事件到达后，它引发一个软中断。负载均衡真正 的工作由sched_balance_softirq()->rebalance_domains()完成，在软中断上下文中执行 （SCHED_SOFTIRQ）。 -后一个函数有两个入参：当前CPU的运行队列、它在scheduler_tick()调用时是否空闲。函数会从 +后一个函数有两个入参：当前CPU的运行队列、它在sched_tick()调用时是否空闲。函数会从 当前CPU所在的基调度域开始迭代执行，并沿着parent指针链向上进入更高层级的调度域。在迭代 过程中，函数会检查当前调度域是否已经耗尽了再平衡的时间间隔，如果是，它在该调度域运行 load_balance()。接下来它检查父调度域（如果存在），再后来父调度域的父调度域，以此类推。 diff --git a/include/linux/sched.h b/include/linux/sched.h index 17cb0761ff65..7eb7f31af796 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -301,7 +301,7 @@ enum { TASK_COMM_LEN = 16, }; -extern void scheduler_tick(void); +extern void sched_tick(void); #define MAX_SCHEDULE_TIMEOUT LONG_MAX diff --git a/kernel/sched/core.c b/kernel/sched/core.c index d44efa0d0611..71b7a08a6502 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5662,7 +5662,7 @@ static inline u64 cpu_resched_latency(struct rq *rq) { return 0; } * This function gets called by the timer code, with HZ frequency. * We call it with interrupts disabled. */ -void scheduler_tick(void) +void sched_tick(void) { int cpu = smp_processor_id(); struct rq *rq = cpu_rq(cpu); @@ -6585,7 +6585,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) * paths. For example, see arch/x86/entry_64.S. * * To drive preemption between tasks, the scheduler sets the flag in timer - * interrupt handler scheduler_tick(). + * interrupt handler sched_tick(). * * 3. Wakeups don't really cause entry into schedule(). They add a * task to the run-queue and that's it. diff --git a/kernel/sched/loadavg.c b/kernel/sched/loadavg.c index 52c8f8226b0d..ca9da66cc894 100644 --- a/kernel/sched/loadavg.c +++ b/kernel/sched/loadavg.c @@ -379,7 +379,7 @@ void calc_global_load(void) } /* - * Called from scheduler_tick() to periodically update this CPU's + * Called from sched_tick() to periodically update this CPU's * active count. */ void calc_global_load_tick(struct rq *this_rq) diff --git a/kernel/time/timer.c b/kernel/time/timer.c index e69e75d3858c..ff49ddcc9800 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -2478,7 +2478,7 @@ void update_process_times(int user_tick) if (in_irq()) irq_work_tick(); #endif - scheduler_tick(); + sched_tick(); if (IS_ENABLED(CONFIG_POSIX_TIMERS)) run_posix_cpu_timers(); } diff --git a/kernel/workqueue.c b/kernel/workqueue.c index bf2bdac46843..8fbb0ec39079 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -1464,7 +1464,7 @@ void wq_worker_sleeping(struct task_struct *task) * wq_worker_tick - a scheduler tick occurred while a kworker is running * @task: task currently running * - * Called from scheduler_tick(). We're in the IRQ context and the current + * Called from sched_tick(). We're in the IRQ context and the current * worker's fields which follow the 'K' locking rule can be accessed safely. */ void wq_worker_tick(struct task_struct *task) diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc index 25432b8cd5bd..073a748b9380 100644 --- a/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc +++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc @@ -19,7 +19,7 @@ fail() { # mesg FILTER=set_ftrace_filter FUNC1="schedule" -FUNC2="scheduler_tick" +FUNC2="sched_tick" ALL_FUNCS="#### all functions enabled ####" -- cgit v1.2.3 From 4c3e509ea9f249458e8692f8298cceac73105948 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Fri, 8 Mar 2024 12:18:11 +0100 Subject: sched/balancing: Rename load_balance() => sched_balance_rq() Standardize scheduler load-balancing function names on the sched_balance_() prefix. Also load_balance() has become somewhat of a misnomer: historically it was the first and primary load-balancing function that was called, but with the introduction of sched domains, it's become a lower layer function that balances runqueues. Rename it to sched_balance_rq() accordingly. Signed-off-by: Ingo Molnar Reviewed-by: Shrikanth Hegde Link: https://lore.kernel.org/r/20240308111819.1101550-6-mingo@kernel.org --- Documentation/scheduler/sched-domains.rst | 4 +-- Documentation/scheduler/sched-stats.rst | 32 +++++++++++----------- .../translations/zh_CN/scheduler/sched-domains.rst | 4 +-- .../translations/zh_CN/scheduler/sched-stats.rst | 30 ++++++++++---------- include/linux/sched/topology.h | 2 +- kernel/sched/fair.c | 10 +++---- 6 files changed, 41 insertions(+), 41 deletions(-) (limited to 'include') diff --git a/Documentation/scheduler/sched-domains.rst b/Documentation/scheduler/sched-domains.rst index 5d8e8b8b269e..5e996fe973b1 100644 --- a/Documentation/scheduler/sched-domains.rst +++ b/Documentation/scheduler/sched-domains.rst @@ -41,11 +41,11 @@ The latter function takes two arguments: the runqueue of current CPU and whether the CPU was idle at the time the sched_tick() happened and iterates over all sched domains our CPU is on, starting from its base domain and going up the ->parent chain. While doing that, it checks to see if the current domain has exhausted its -rebalance interval. If so, it runs load_balance() on that domain. It then checks +rebalance interval. If so, it runs sched_balance_rq() on that domain. It then checks the parent sched_domain (if it exists), and the parent of the parent and so forth. -Initially, load_balance() finds the busiest group in the current sched domain. +Initially, sched_balance_rq() finds the busiest group in the current sched domain. If it succeeds, it looks for the busiest runqueue of all the CPUs' runqueues in that group. If it manages to find such a runqueue, it locks both our initial CPU's runqueue and the newly found busiest one and starts moving tasks from it diff --git a/Documentation/scheduler/sched-stats.rst b/Documentation/scheduler/sched-stats.rst index 73c412666655..7c2b16c4729d 100644 --- a/Documentation/scheduler/sched-stats.rst +++ b/Documentation/scheduler/sched-stats.rst @@ -77,53 +77,53 @@ domain 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 The first field is a bit mask indicating what cpus this domain operates over. -The next 24 are a variety of load_balance() statistics in grouped into types +The next 24 are a variety of sched_balance_rq() statistics in grouped into types of idleness (idle, busy, and newly idle): - 1) # of times in this domain load_balance() was called when the + 1) # of times in this domain sched_balance_rq() was called when the cpu was idle - 2) # of times in this domain load_balance() checked but found + 2) # of times in this domain sched_balance_rq() checked but found the load did not require balancing when the cpu was idle - 3) # of times in this domain load_balance() tried to move one or + 3) # of times in this domain sched_balance_rq() tried to move one or more tasks and failed, when the cpu was idle 4) sum of imbalances discovered (if any) with each call to - load_balance() in this domain when the cpu was idle + sched_balance_rq() in this domain when the cpu was idle 5) # of times in this domain pull_task() was called when the cpu was idle 6) # of times in this domain pull_task() was called even though the target task was cache-hot when idle - 7) # of times in this domain load_balance() was called but did + 7) # of times in this domain sched_balance_rq() was called but did not find a busier queue while the cpu was idle 8) # of times in this domain a busier queue was found while the cpu was idle but no busier group was found - 9) # of times in this domain load_balance() was called when the + 9) # of times in this domain sched_balance_rq() was called when the cpu was busy - 10) # of times in this domain load_balance() checked but found the + 10) # of times in this domain sched_balance_rq() checked but found the load did not require balancing when busy - 11) # of times in this domain load_balance() tried to move one or + 11) # of times in this domain sched_balance_rq() tried to move one or more tasks and failed, when the cpu was busy 12) sum of imbalances discovered (if any) with each call to - load_balance() in this domain when the cpu was busy + sched_balance_rq() in this domain when the cpu was busy 13) # of times in this domain pull_task() was called when busy 14) # of times in this domain pull_task() was called even though the target task was cache-hot when busy - 15) # of times in this domain load_balance() was called but did not + 15) # of times in this domain sched_balance_rq() was called but did not find a busier queue while the cpu was busy 16) # of times in this domain a busier queue was found while the cpu was busy but no busier group was found - 17) # of times in this domain load_balance() was called when the + 17) # of times in this domain sched_balance_rq() was called when the cpu was just becoming idle - 18) # of times in this domain load_balance() checked but found the + 18) # of times in this domain sched_balance_rq() checked but found the load did not require balancing when the cpu was just becoming idle - 19) # of times in this domain load_balance() tried to move one or more + 19) # of times in this domain sched_balance_rq() tried to move one or more tasks and failed, when the cpu was just becoming idle 20) sum of imbalances discovered (if any) with each call to - load_balance() in this domain when the cpu was just becoming idle + sched_balance_rq() in this domain when the cpu was just becoming idle 21) # of times in this domain pull_task() was called when newly idle 22) # of times in this domain pull_task() was called even though the target task was cache-hot when just becoming idle - 23) # of times in this domain load_balance() was called but did not + 23) # of times in this domain sched_balance_rq() was called but did not find a busier queue while the cpu was just becoming idle 24) # of times in this domain a busier queue was found while the cpu was just becoming idle but no busier group was found diff --git a/Documentation/translations/zh_CN/scheduler/sched-domains.rst b/Documentation/translations/zh_CN/scheduler/sched-domains.rst index e6590fd80640..06363169c56b 100644 --- a/Documentation/translations/zh_CN/scheduler/sched-domains.rst +++ b/Documentation/translations/zh_CN/scheduler/sched-domains.rst @@ -42,9 +42,9 @@ CPU共享。任意两个组的CPU掩码的交集不一定为空，如果是这 后一个函数有两个入参：当前CPU的运行队列、它在sched_tick()调用时是否空闲。函数会从 当前CPU所在的基调度域开始迭代执行，并沿着parent指针链向上进入更高层级的调度域。在迭代 过程中，函数会检查当前调度域是否已经耗尽了再平衡的时间间隔，如果是，它在该调度域运行 -load_balance()。接下来它检查父调度域（如果存在），再后来父调度域的父调度域，以此类推。 +sched_balance_rq()。接下来它检查父调度域（如果存在），再后来父调度域的父调度域，以此类推。 -起初，load_balance()查找当前调度域中最繁忙的调度组。如果成功，在该调度组管辖的全部CPU +起初，sched_balance_rq()查找当前调度域中最繁忙的调度组。如果成功，在该调度组管辖的全部CPU 的运行队列中找出最繁忙的运行队列。如能找到，对当前的CPU运行队列和新找到的最繁忙运行 队列均加锁，并把任务从最繁忙队列中迁移到当前CPU上。被迁移的任务数量等于在先前迭代执行 中计算出的该调度域的调度组的不均衡值。 diff --git a/Documentation/translations/zh_CN/scheduler/sched-stats.rst b/Documentation/translations/zh_CN/scheduler/sched-stats.rst index c5e0be663837..09eee2517610 100644 --- a/Documentation/translations/zh_CN/scheduler/sched-stats.rst +++ b/Documentation/translations/zh_CN/scheduler/sched-stats.rst @@ -75,42 +75,42 @@ domain 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 繁忙，新空闲）： - 1) 当CPU空闲时，load_balance()在这个调度域中被调用了#次 - 2) 当CPU空闲时，load_balance()在这个调度域中被调用，但是发现负载无需 + 1) 当CPU空闲时，sched_balance_rq()在这个调度域中被调用了#次 + 2) 当CPU空闲时，sched_balance_rq()在这个调度域中被调用，但是发现负载无需 均衡#次 - 3) 当CPU空闲时，load_balance()在这个调度域中被调用，试图迁移1个或更多 + 3) 当CPU空闲时，sched_balance_rq()在这个调度域中被调用，试图迁移1个或更多 任务且失败了#次 - 4) 当CPU空闲时，load_balance()在这个调度域中被调用，发现不均衡（如果有） + 4) 当CPU空闲时，sched_balance_rq()在这个调度域中被调用，发现不均衡（如果有） #次 5) 当CPU空闲时，pull_task()在这个调度域中被调用#次 6) 当CPU空闲时，尽管目标任务是热缓存状态，pull_task()依然被调用#次 - 7) 当CPU空闲时，load_balance()在这个调度域中被调用，未能找到更繁忙的 + 7) 当CPU空闲时，sched_balance_rq()在这个调度域中被调用，未能找到更繁忙的 队列#次 8) 当CPU空闲时，在调度域中找到了更繁忙的队列，但未找到更繁忙的调度组 #次 - 9) 当CPU繁忙时，load_balance()在这个调度域中被调用了#次 - 10) 当CPU繁忙时，load_balance()在这个调度域中被调用，但是发现负载无需 + 9) 当CPU繁忙时，sched_balance_rq()在这个调度域中被调用了#次 + 10) 当CPU繁忙时，sched_balance_rq()在这个调度域中被调用，但是发现负载无需 均衡#次 - 11) 当CPU繁忙时，load_balance()在这个调度域中被调用，试图迁移1个或更多 + 11) 当CPU繁忙时，sched_balance_rq()在这个调度域中被调用，试图迁移1个或更多 任务且失败了#次 - 12) 当CPU繁忙时，load_balance()在这个调度域中被调用，发现不均衡（如果有） + 12) 当CPU繁忙时，sched_balance_rq()在这个调度域中被调用，发现不均衡（如果有） #次 13) 当CPU繁忙时，pull_task()在这个调度域中被调用#次 14) 当CPU繁忙时，尽管目标任务是热缓存状态，pull_task()依然被调用#次 - 15) 当CPU繁忙时，load_balance()在这个调度域中被调用，未能找到更繁忙的 + 15) 当CPU繁忙时，sched_balance_rq()在这个调度域中被调用，未能找到更繁忙的 队列#次 16) 当CPU繁忙时，在调度域中找到了更繁忙的队列，但未找到更繁忙的调度组 #次 - 17) 当CPU新空闲时，load_balance()在这个调度域中被调用了#次 - 18) 当CPU新空闲时，load_balance()在这个调度域中被调用，但是发现负载无需 + 17) 当CPU新空闲时，sched_balance_rq()在这个调度域中被调用了#次 + 18) 当CPU新空闲时，sched_balance_rq()在这个调度域中被调用，但是发现负载无需 均衡#次 - 19) 当CPU新空闲时，load_balance()在这个调度域中被调用，试图迁移1个或更多 + 19) 当CPU新空闲时，sched_balance_rq()在这个调度域中被调用，试图迁移1个或更多 任务且失败了#次 - 20) 当CPU新空闲时，load_balance()在这个调度域中被调用，发现不均衡（如果有） + 20) 当CPU新空闲时，sched_balance_rq()在这个调度域中被调用，发现不均衡（如果有） #次 21) 当CPU新空闲时，pull_task()在这个调度域中被调用#次 22) 当CPU新空闲时，尽管目标任务是热缓存状态，pull_task()依然被调用#次 - 23) 当CPU新空闲时，load_balance()在这个调度域中被调用，未能找到更繁忙的 + 23) 当CPU新空闲时，sched_balance_rq()在这个调度域中被调用，未能找到更繁忙的 队列#次 24) 当CPU新空闲时，在调度域中找到了更繁忙的队列，但未找到更繁忙的调度组 #次 diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index 18572c9ea724..c8fe9bab981b 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -110,7 +110,7 @@ struct sched_domain { unsigned long last_decay_max_lb_cost; #ifdef CONFIG_SCHEDSTATS - /* load_balance() stats */ + /* sched_balance_rq() stats */ unsigned int lb_count[CPU_MAX_IDLE_TYPES]; unsigned int lb_failed[CPU_MAX_IDLE_TYPES]; unsigned int lb_balanced[CPU_MAX_IDLE_TYPES]; diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 330788b0c617..0d2753c50be9 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -6866,7 +6866,7 @@ dequeue_throttle: #ifdef CONFIG_SMP -/* Working cpumask for: load_balance, load_balance_newidle. */ +/* Working cpumask for: sched_balance_rq, load_balance_newidle. */ static DEFINE_PER_CPU(cpumask_var_t, load_balance_mask); static DEFINE_PER_CPU(cpumask_var_t, select_rq_mask); static DEFINE_PER_CPU(cpumask_var_t, should_we_balance_tmpmask); @@ -11242,7 +11242,7 @@ static int should_we_balance(struct lb_env *env) * Check this_cpu to ensure it is balanced within domain. Attempt to move * tasks if there is an imbalance. */ -static int load_balance(int this_cpu, struct rq *this_rq, +static int sched_balance_rq(int this_cpu, struct rq *this_rq, struct sched_domain *sd, enum cpu_idle_type idle, int *continue_balancing) { @@ -11647,7 +11647,7 @@ out_unlock: static atomic_t sched_balance_running = ATOMIC_INIT(0); /* - * Scale the max load_balance interval with the number of CPUs in the system. + * Scale the max sched_balance_rq interval with the number of CPUs in the system. * This trades load-balance latency on larger machines for less cross talk. */ void update_max_interval(void) @@ -11727,7 +11727,7 @@ static void sched_balance_domains(struct rq *rq, enum cpu_idle_type idle) } if (time_after_eq(jiffies, sd->last_balance + interval)) { - if (load_balance(cpu, rq, sd, idle, &continue_balancing)) { + if (sched_balance_rq(cpu, rq, sd, idle, &continue_balancing)) { /* * The LBF_DST_PINNED logic could have changed * env->dst_cpu, so we can't know our idle @@ -12353,7 +12353,7 @@ static int newidle_balance(struct rq *this_rq, struct rq_flags *rf) if (sd->flags & SD_BALANCE_NEWIDLE) { - pulled_task = load_balance(this_cpu, this_rq, + pulled_task = sched_balance_rq(this_cpu, this_rq, sd, CPU_NEWLY_IDLE, &continue_balancing); -- cgit v1.2.3 From e27b02e23a701e5761f1d6028643e1203a1c56de Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sat, 9 Mar 2024 14:45:38 -0800 Subject: ssb: drop use of non-existing CONFIG_SSB_DEBUG symbol MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit CONFIG_SSB_DEBUG is used in one header file and nowhere else, so remove it and the now-empty inline function that contained it. Also remove the call to the empty inline function. The empty "default:" case is kept to prevent 2 compiler warnings: drivers/ssb/main.c:1133:9: warning: enumeration value 'SSB_BUSTYPE_PCMCIA' not handled in switch [-Wswitch] drivers/ssb/main.c:1133:9: warning: enumeration value 'SSB_BUSTYPE_SDIO' not handled in switch [-Wswitch] Reported-by: Ying Sun Link: https://lore.kernel.org/lkml/4e8525fe.607e2.18a8ddfdce8.Coremail.sunying@isrc.iscas.ac.cn/ Signed-off-by: Randy Dunlap Cc: Michael Büsch Cc: linux-wireless@vger.kernel.org Cc: Kalle Valo Acked-by: Michael Büsch Signed-off-by: Kalle Valo Link: https://msgid.link/20240309224540.22682-1-rdunlap@infradead.org --- drivers/ssb/main.c | 1 - include/linux/ssb/ssb.h | 8 -------- 2 files changed, 9 deletions(-) (limited to 'include') diff --git a/drivers/ssb/main.c b/drivers/ssb/main.c index bdb6595ffd2d..8210bf28a340 100644 --- a/drivers/ssb/main.c +++ b/drivers/ssb/main.c @@ -1146,7 +1146,6 @@ u32 ssb_dma_translation(struct ssb_device *dev) return SSB_PCI_DMA; } default: - __ssb_dma_not_implemented(dev); } return 0; } diff --git a/include/linux/ssb/ssb.h b/include/linux/ssb/ssb.h index 1f326da289d3..a2257380c3f1 100644 --- a/include/linux/ssb/ssb.h +++ b/include/linux/ssb/ssb.h @@ -621,14 +621,6 @@ extern u32 ssb_dma_translation(struct ssb_device *dev); #define SSB_DMA_TRANSLATION_MASK 0xC0000000 #define SSB_DMA_TRANSLATION_SHIFT 30 -static inline void __cold __ssb_dma_not_implemented(struct ssb_device *dev) -{ -#ifdef CONFIG_SSB_DEBUG - printk(KERN_ERR "SSB: BUG! Calling DMA API for " - "unsupported bustype %d\n", dev->bus->bustype); -#endif /* DEBUG */ -} - #ifdef CONFIG_SSB_PCIHOST /* PCI-host wrapper driver */ extern int ssb_pcihost_register(struct pci_driver *driver); -- cgit v1.2.3 From 8e61e3192a77e1006c1c54c022173026f7afae2c Mon Sep 17 00:00:00 2001 From: Matt Roper Date: Tue, 12 Mar 2024 14:12:25 -0700 Subject: drm/xe/uapi: Add IP version and stepping to GT list query For modern platforms (MTL and later), both kernel and userspace drivers are expected to apply GT programming and workarounds based on the IP version and stepping self-reported by the GT hardware via the GMD_ID registers. Since userspace drivers can't access these registers directly, pass along the version and stepping information via the GT list query. Note that the new query fields will remain 0's when running on pre-GMD_ID platforms. Userspace is expected to continue using PCI devid / revid on those older platforms. Although the hardware also has a GMD_ID register for display version/stepping, that value is intentionally *not* included anywhere in the Xe uapi. Display userspace should be using platform-agnostic APIs and auto-detecting platform capabilities rather than matching specific IP versions. v2: - s/revid/rev/ (Lucas) - Fix kerneldoc copy/paste mistakes Signed-off-by: Matt Roper Reviewed-by: Lucas De Marchi Link: https://patchwork.freedesktop.org/patch/msgid/20240312211229.2871288-4-matthew.d.roper@intel.com --- drivers/gpu/drm/xe/xe_query.c | 8 ++++++++ include/uapi/drm/xe_drm.h | 10 +++++++++- 2 files changed, 17 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/gpu/drm/xe/xe_query.c b/drivers/gpu/drm/xe/xe_query.c index a6a20a6dd360..e80321b34918 100644 --- a/drivers/gpu/drm/xe/xe_query.c +++ b/drivers/gpu/drm/xe/xe_query.c @@ -12,6 +12,7 @@ #include #include "regs/xe_engine_regs.h" +#include "regs/xe_gt_regs.h" #include "xe_bo.h" #include "xe_device.h" #include "xe_exec_queue.h" @@ -401,6 +402,13 @@ static int query_gt_list(struct xe_device *xe, struct drm_xe_device_query *query BIT(gt_to_tile(gt)->id) << 1; gt_list->gt_list[id].far_mem_regions = xe->info.mem_region_mask ^ gt_list->gt_list[id].near_mem_regions; + + gt_list->gt_list[id].ip_ver_major = + REG_FIELD_GET(GMD_ID_ARCH_MASK, gt->info.gmdid); + gt_list->gt_list[id].ip_ver_minor = + REG_FIELD_GET(GMD_ID_RELEASE_MASK, gt->info.gmdid); + gt_list->gt_list[id].ip_ver_rev = + REG_FIELD_GET(GMD_ID_REVID, gt->info.gmdid); } if (copy_to_user(query_ptr, gt_list, size)) { diff --git a/include/uapi/drm/xe_drm.h b/include/uapi/drm/xe_drm.h index 2fc19177d2b0..808ad1c308ec 100644 --- a/include/uapi/drm/xe_drm.h +++ b/include/uapi/drm/xe_drm.h @@ -459,8 +459,16 @@ struct drm_xe_gt { * by struct drm_xe_query_mem_regions' mem_class. */ __u64 far_mem_regions; + /** @ip_ver_major: Graphics/media IP major version on GMD_ID platforms */ + __u16 ip_ver_major; + /** @ip_ver_minor: Graphics/media IP minor version on GMD_ID platforms */ + __u16 ip_ver_minor; + /** @ip_ver_rev: Graphics/media IP revision version on GMD_ID platforms */ + __u16 ip_ver_rev; + /** @pad2: MBZ */ + __u16 pad2; /** @reserved: Reserved */ - __u64 reserved[8]; + __u64 reserved[7]; }; /** -- cgit v1.2.3 From 1793f69326266269a8117d3f5324ac78db18931c Mon Sep 17 00:00:00 2001 From: Wei Yang Date: Wed, 13 Mar 2024 07:58:36 +0000 Subject: vmlinux.lds.h: Fix a typo in comment Signed-off-by: Wei Yang Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20240313075839.8321-2-richard.weiyang@gmail.com --- include/asm-generic/vmlinux.lds.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 5dd3a61d673d..514d3002ad8a 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -3,7 +3,7 @@ * linker scripts. * * A minimal linker scripts has following content: - * [This is a sample, architectures may have special requiriements] + * [This is a sample, architectures may have special requirements] * * OUTPUT_FORMAT(...) * OUTPUT_ARCH(...) -- cgit v1.2.3 From 64be03575f9e9772ebdebc7f067d533348602083 Mon Sep 17 00:00:00 2001 From: Fiona Klute Date: Mon, 11 Mar 2024 11:37:13 +0100 Subject: wifi: rtw88: SDIO device driver for RTL8723CS This driver uses the new rtw8703b chip driver code. Acked-by: Ping-Ke Shih Acked-by: Ulf Hansson # For SDIO Tested-by: Pavel Machek Signed-off-by: Fiona Klute Signed-off-by: Kalle Valo Link: https://msgid.link/20240311103735.615541-10-fiona.klute@gmx.de --- drivers/net/wireless/realtek/rtw88/Kconfig | 18 ++++++++++++++ drivers/net/wireless/realtek/rtw88/Makefile | 6 +++++ drivers/net/wireless/realtek/rtw88/rtw8723cs.c | 34 ++++++++++++++++++++++++++ include/linux/mmc/sdio_ids.h | 1 + 4 files changed, 59 insertions(+) create mode 100644 drivers/net/wireless/realtek/rtw88/rtw8723cs.c (limited to 'include') diff --git a/drivers/net/wireless/realtek/rtw88/Kconfig b/drivers/net/wireless/realtek/rtw88/Kconfig index 07b5b2f6eef7..22838ede03cd 100644 --- a/drivers/net/wireless/realtek/rtw88/Kconfig +++ b/drivers/net/wireless/realtek/rtw88/Kconfig @@ -31,6 +31,10 @@ config RTW88_8822C config RTW88_8723X tristate +config RTW88_8703B + tristate + select RTW88_8723X + config RTW88_8723D tristate select RTW88_8723X @@ -126,6 +130,20 @@ config RTW88_8723DS 802.11n SDIO wireless network adapter +config RTW88_8723CS + tristate "Realtek 8723CS SDIO wireless network adapter" + depends on MMC + select RTW88_CORE + select RTW88_SDIO + select RTW88_8703B + help + Select this option to enable support for 8723CS chipset (EXPERIMENTAL) + + This module adds support for the 8723CS 802.11n SDIO + wireless network adapter. + + If you choose to build a module, it'll be called rtw88_8723cs. + config RTW88_8723DU tristate "Realtek 8723DU USB wireless network adapter" depends on USB diff --git a/drivers/net/wireless/realtek/rtw88/Makefile b/drivers/net/wireless/realtek/rtw88/Makefile index 22516c984608..8f47359b4380 100644 --- a/drivers/net/wireless/realtek/rtw88/Makefile +++ b/drivers/net/wireless/realtek/rtw88/Makefile @@ -47,6 +47,12 @@ rtw88_8822cu-objs := rtw8822cu.o obj-$(CONFIG_RTW88_8723X) += rtw88_8723x.o rtw88_8723x-objs := rtw8723x.o +obj-$(CONFIG_RTW88_8703B) += rtw88_8703b.o +rtw88_8703b-objs := rtw8703b.o rtw8703b_tables.o + +obj-$(CONFIG_RTW88_8723CS) += rtw88_8723cs.o +rtw88_8723cs-objs := rtw8723cs.o + obj-$(CONFIG_RTW88_8723D) += rtw88_8723d.o rtw88_8723d-objs := rtw8723d.o rtw8723d_table.o diff --git a/drivers/net/wireless/realtek/rtw88/rtw8723cs.c b/drivers/net/wireless/realtek/rtw88/rtw8723cs.c new file mode 100644 index 000000000000..8d38d36be8c0 --- /dev/null +++ b/drivers/net/wireless/realtek/rtw88/rtw8723cs.c @@ -0,0 +1,34 @@ +// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause +/* Copyright Fiona Klute */ + +#include +#include +#include +#include "main.h" +#include "rtw8703b.h" +#include "sdio.h" + +static const struct sdio_device_id rtw_8723cs_id_table[] = { + { + SDIO_DEVICE(SDIO_VENDOR_ID_REALTEK, + SDIO_DEVICE_ID_REALTEK_RTW8723CS), + .driver_data = (kernel_ulong_t)&rtw8703b_hw_spec, + }, + {} +}; +MODULE_DEVICE_TABLE(sdio, rtw_8723cs_id_table); + +static struct sdio_driver rtw_8723cs_driver = { + .name = "rtw8723cs", + .id_table = rtw_8723cs_id_table, + .probe = rtw_sdio_probe, + .remove = rtw_sdio_remove, + .drv = { + .pm = &rtw_sdio_pm_ops, + .shutdown = rtw_sdio_shutdown + }}; +module_sdio_driver(rtw_8723cs_driver); + +MODULE_AUTHOR("Fiona Klute "); +MODULE_DESCRIPTION("Realtek 802.11n wireless 8723cs driver"); +MODULE_LICENSE("Dual BSD/GPL"); diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h index 7fada7a714fe..7cddfdac2f57 100644 --- a/include/linux/mmc/sdio_ids.h +++ b/include/linux/mmc/sdio_ids.h @@ -124,6 +124,7 @@ #define SDIO_DEVICE_ID_REALTEK_RTW8723DS_2ANT 0xd723 #define SDIO_DEVICE_ID_REALTEK_RTW8723DS_1ANT 0xd724 #define SDIO_DEVICE_ID_REALTEK_RTW8821DS 0xd821 +#define SDIO_DEVICE_ID_REALTEK_RTW8723CS 0xb703 #define SDIO_VENDOR_ID_SIANO 0x039a #define SDIO_DEVICE_ID_SIANO_NOVA_B0 0x0201 -- cgit v1.2.3 From a0b39da11618897e0a2b85ea28e34b8cbcbd3274 Mon Sep 17 00:00:00 2001 From: Hsin-Yi Wang Date: Thu, 7 Mar 2024 14:57:41 -0800 Subject: drm_edid: Add a function to get EDID base block It's found that some panels have variants that they share the same panel id although their EDID and names are different. Besides panel id, now we need more information from the EDID base block to distinguish these panel variants. Add drm_edid_read_base_block() to return the EDID base block, which is wrapped in struct drm_edid. Caller can further use it to get panel id or check if the block contains certain strings, such as panel name. Merge drm_edid_get_panel_id() and edid_extract_panel_id() into one function. Signed-off-by: Hsin-Yi Wang Reviewed-by: Douglas Anderson Reviewed-by: Jani Nikula Signed-off-by: Douglas Anderson Link: https://patchwork.freedesktop.org/patch/msgid/20240307230653.1807557-2-hsinyi@chromium.org --- drivers/gpu/drm/drm_edid.c | 71 +++++++++++++++++++++++---------------- drivers/gpu/drm/panel/panel-edp.c | 8 +++-- include/drm/drm_edid.h | 3 +- 3 files changed, 50 insertions(+), 32 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c index 923c4423151c..ecd6e9255b67 100644 --- a/drivers/gpu/drm/drm_edid.c +++ b/drivers/gpu/drm/drm_edid.c @@ -2749,8 +2749,27 @@ const struct drm_edid *drm_edid_read(struct drm_connector *connector) } EXPORT_SYMBOL(drm_edid_read); -static u32 edid_extract_panel_id(const struct edid *edid) +/** + * drm_edid_get_panel_id - Get a panel's ID from EDID + * @drm_edid: EDID that contains panel ID. + * + * This function uses the first block of the EDID of a panel and (assuming + * that the EDID is valid) extracts the ID out of it. The ID is a 32-bit value + * (16 bits of manufacturer ID and 16 bits of per-manufacturer ID) that's + * supposed to be different for each different modem of panel. + * + * Return: A 32-bit ID that should be different for each make/model of panel. + * See the functions drm_edid_encode_panel_id() and + * drm_edid_decode_panel_id() for some details on the structure of this + * ID. Return 0 if the EDID size is less than a base block. + */ +u32 drm_edid_get_panel_id(const struct drm_edid *drm_edid) { + const struct edid *edid = drm_edid->edid; + + if (drm_edid->size < EDID_LENGTH) + return 0; + /* * We represent the ID as a 32-bit number so it can easily be compared * with "==". @@ -2768,60 +2787,54 @@ static u32 edid_extract_panel_id(const struct edid *edid) (u32)edid->mfg_id[1] << 16 | (u32)EDID_PRODUCT_ID(edid); } +EXPORT_SYMBOL(drm_edid_get_panel_id); /** - * drm_edid_get_panel_id - Get a panel's ID through DDC + * drm_edid_read_base_block - Get a panel's EDID base block * @adapter: I2C adapter to use for DDC * - * This function reads the first block of the EDID of a panel and (assuming - * that the EDID is valid) extracts the ID out of it. The ID is a 32-bit value - * (16 bits of manufacturer ID and 16 bits of per-manufacturer ID) that's - * supposed to be different for each different modem of panel. + * This function returns the drm_edid containing the first block of the EDID of + * a panel. * * This function is intended to be used during early probing on devices where * more than one panel might be present. Because of its intended use it must - * assume that the EDID of the panel is correct, at least as far as the ID - * is concerned (in other words, we don't process any overrides here). + * assume that the EDID of the panel is correct, at least as far as the base + * block is concerned (in other words, we don't process any overrides here). + * + * Caller should call drm_edid_free() after use. * * NOTE: it's expected that this function and drm_do_get_edid() will both * be read the EDID, but there is no caching between them. Since we're only * reading the first block, hopefully this extra overhead won't be too big. * - * Return: A 32-bit ID that should be different for each make/model of panel. - * See the functions drm_edid_encode_panel_id() and - * drm_edid_decode_panel_id() for some details on the structure of this - * ID. + * WARNING: Only use this function when the connector is unknown. For example, + * during the early probe of panel. The EDID read from the function is temporary + * and should be replaced by the full EDID returned from other drm_edid_read. + * + * Return: Pointer to allocated EDID base block, or NULL on any failure. */ - -u32 drm_edid_get_panel_id(struct i2c_adapter *adapter) +const struct drm_edid *drm_edid_read_base_block(struct i2c_adapter *adapter) { enum edid_block_status status; void *base_block; - u32 panel_id = 0; - - /* - * There are no manufacturer IDs of 0, so if there is a problem reading - * the EDID then we'll just return 0. - */ base_block = kzalloc(EDID_LENGTH, GFP_KERNEL); if (!base_block) - return 0; + return NULL; status = edid_block_read(base_block, 0, drm_do_probe_ddc_edid, adapter); edid_block_status_print(status, base_block, 0); - if (edid_block_status_valid(status, edid_block_tag(base_block))) - panel_id = edid_extract_panel_id(base_block); - else + if (!edid_block_status_valid(status, edid_block_tag(base_block))) { edid_block_dump(KERN_NOTICE, base_block, 0); + kfree(base_block); + return NULL; + } - kfree(base_block); - - return panel_id; + return _drm_edid_alloc(base_block, EDID_LENGTH); } -EXPORT_SYMBOL(drm_edid_get_panel_id); +EXPORT_SYMBOL(drm_edid_read_base_block); /** * drm_get_edid_switcheroo - get EDID data for a vga_switcheroo output @@ -2906,7 +2919,7 @@ EXPORT_SYMBOL(drm_edid_duplicate); */ static u32 edid_get_quirks(const struct drm_edid *drm_edid) { - u32 panel_id = edid_extract_panel_id(drm_edid->edid); + u32 panel_id = drm_edid_get_panel_id(drm_edid); const struct edid_quirk *quirk; int i; diff --git a/drivers/gpu/drm/panel/panel-edp.c b/drivers/gpu/drm/panel/panel-edp.c index 2906a382aae0..f7db5b10e233 100644 --- a/drivers/gpu/drm/panel/panel-edp.c +++ b/drivers/gpu/drm/panel/panel-edp.c @@ -766,6 +766,7 @@ static const struct edp_panel_entry *find_edp_panel(u32 panel_id); static int generic_edp_panel_probe(struct device *dev, struct panel_edp *panel) { struct panel_desc *desc; + const struct drm_edid *base_block; u32 panel_id; char vend[4]; u16 product_id; @@ -795,8 +796,11 @@ static int generic_edp_panel_probe(struct device *dev, struct panel_edp *panel) goto exit; } - panel_id = drm_edid_get_panel_id(panel->ddc); - if (!panel_id) { + base_block = drm_edid_read_base_block(panel->ddc); + if (base_block) { + panel_id = drm_edid_get_panel_id(base_block); + drm_edid_free(base_block); + } else { dev_err(dev, "Couldn't identify panel via EDID\n"); ret = -EIO; goto exit; diff --git a/include/drm/drm_edid.h b/include/drm/drm_edid.h index 7923bc00dc7a..9686a7cee6a6 100644 --- a/include/drm/drm_edid.h +++ b/include/drm/drm_edid.h @@ -410,7 +410,8 @@ struct edid *drm_do_get_edid(struct drm_connector *connector, void *data); struct edid *drm_get_edid(struct drm_connector *connector, struct i2c_adapter *adapter); -u32 drm_edid_get_panel_id(struct i2c_adapter *adapter); +const struct drm_edid *drm_edid_read_base_block(struct i2c_adapter *adapter); +u32 drm_edid_get_panel_id(const struct drm_edid *drm_edid); struct edid *drm_get_edid_switcheroo(struct drm_connector *connector, struct i2c_adapter *adapter); struct edid *drm_edid_duplicate(const struct edid *edid); -- cgit v1.2.3 From 6e3fdedcf0bc03c852d9fdbb5443f1e43103195f Mon Sep 17 00:00:00 2001 From: Hsin-Yi Wang Date: Thu, 7 Mar 2024 14:57:42 -0800 Subject: drm/edid: Add a function to match EDID with identity Create a type drm_edid_ident as the identity of an EDID. Currently it contains panel id and monitor name. Create a function that can match a given EDID and an identity: 1. Reject if the panel id doesn't match. 2. If name is not null in identity, try to match it in the detailed timing blocks. Note that some panel vendors put the monitor name after EDID_DETAIL_MONITOR_STRING. Signed-off-by: Hsin-Yi Wang Reviewed-by: Douglas Anderson Reviewed-by: Jani Nikula Signed-off-by: Douglas Anderson Link: https://patchwork.freedesktop.org/patch/msgid/20240307230653.1807557-3-hsinyi@chromium.org --- drivers/gpu/drm/drm_edid.c | 65 ++++++++++++++++++++++++++++++++++++++++++++++ include/drm/drm_edid.h | 9 +++++++ 2 files changed, 74 insertions(+) (limited to 'include') diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c index ecd6e9255b67..8fed2131f424 100644 --- a/drivers/gpu/drm/drm_edid.c +++ b/drivers/gpu/drm/drm_edid.c @@ -102,6 +102,11 @@ struct detailed_mode_closure { int modes; }; +struct drm_edid_match_closure { + const struct drm_edid_ident *ident; + bool matched; +}; + #define LEVEL_DMT 0 #define LEVEL_GTF 1 #define LEVEL_GTF2 2 @@ -5455,6 +5460,66 @@ drm_parse_hdmi_vsdb_audio(struct drm_connector *connector, const u8 *db) connector->audio_latency[0], connector->audio_latency[1]); } +static void +match_identity(const struct detailed_timing *timing, void *data) +{ + struct drm_edid_match_closure *closure = data; + unsigned int i; + const char *name = closure->ident->name; + unsigned int name_len = strlen(name); + const char *desc = timing->data.other_data.data.str.str; + unsigned int desc_len = ARRAY_SIZE(timing->data.other_data.data.str.str); + + if (name_len > desc_len || + !(is_display_descriptor(timing, EDID_DETAIL_MONITOR_NAME) || + is_display_descriptor(timing, EDID_DETAIL_MONITOR_STRING))) + return; + + if (strncmp(name, desc, name_len)) + return; + + for (i = name_len; i < desc_len; i++) { + if (desc[i] == '\n') + break; + /* Allow white space before EDID string terminator. */ + if (!isspace(desc[i])) + return; + } + + closure->matched = true; +} + +/** + * drm_edid_match - match drm_edid with given identity + * @drm_edid: EDID + * @ident: the EDID identity to match with + * + * Check if the EDID matches with the given identity. + * + * Return: True if the given identity matched with EDID, false otherwise. + */ +bool drm_edid_match(const struct drm_edid *drm_edid, + const struct drm_edid_ident *ident) +{ + if (!drm_edid || drm_edid_get_panel_id(drm_edid) != ident->panel_id) + return false; + + /* Match with name only if it's not NULL. */ + if (ident->name) { + struct drm_edid_match_closure closure = { + .ident = ident, + .matched = false, + }; + + drm_for_each_detailed_block(drm_edid, match_identity, &closure); + + return closure.matched; + } + + return true; +} +EXPORT_SYMBOL(drm_edid_match); + static void monitor_name(const struct detailed_timing *timing, void *data) { diff --git a/include/drm/drm_edid.h b/include/drm/drm_edid.h index 9686a7cee6a6..6f65bbf655a1 100644 --- a/include/drm/drm_edid.h +++ b/include/drm/drm_edid.h @@ -312,6 +312,13 @@ struct edid { u8 checksum; } __packed; +/* EDID matching */ +struct drm_edid_ident { + /* ID encoded by drm_edid_encode_panel_id() */ + u32 panel_id; + const char *name; +}; + #define EDID_PRODUCT_ID(e) ((e)->prod_code[0] | ((e)->prod_code[1] << 8)) /* Short Audio Descriptor */ @@ -412,6 +419,8 @@ struct edid *drm_get_edid(struct drm_connector *connector, struct i2c_adapter *adapter); const struct drm_edid *drm_edid_read_base_block(struct i2c_adapter *adapter); u32 drm_edid_get_panel_id(const struct drm_edid *drm_edid); +bool drm_edid_match(const struct drm_edid *drm_edid, + const struct drm_edid_ident *ident); struct edid *drm_get_edid_switcheroo(struct drm_connector *connector, struct i2c_adapter *adapter); struct edid *drm_edid_duplicate(const struct edid *edid); -- cgit v1.2.3 From 7d2cc63eca0c993c99d18893214abf8f85d566d8 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Fri, 8 Mar 2024 06:38:07 +0100 Subject: bpf: Take return from set_memory_ro() into account with bpf_prog_lock_ro() set_memory_ro() can fail, leaving memory unprotected. Check its return and take it into account as an error. Link: https://github.com/KSPP/linux/issues/7 Signed-off-by: Christophe Leroy Cc: linux-hardening@vger.kernel.org Reviewed-by: Kees Cook Message-ID: <286def78955e04382b227cb3e4b6ba272a7442e3.1709850515.git.christophe.leroy@csgroup.eu> Signed-off-by: Alexei Starovoitov --- include/linux/filter.h | 5 +++-- kernel/bpf/core.c | 4 +++- kernel/bpf/verifier.c | 8 ++++++-- 3 files changed, 12 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/filter.h b/include/linux/filter.h index c99bc3df2d28..9107ee1de66f 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -887,14 +887,15 @@ bpf_ctx_narrow_access_offset(u32 off, u32 size, u32 size_default) #define bpf_classic_proglen(fprog) (fprog->len * sizeof(fprog->filter[0])) -static inline void bpf_prog_lock_ro(struct bpf_prog *fp) +static inline int __must_check bpf_prog_lock_ro(struct bpf_prog *fp) { #ifndef CONFIG_BPF_JIT_ALWAYS_ON if (!fp->jited) { set_vm_flush_reset_perms(fp); - set_memory_ro((unsigned long)fp, fp->pages); + return set_memory_ro((unsigned long)fp, fp->pages); } #endif + return 0; } static inline void bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr) diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 696bc55de8e8..63f100def31b 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -2403,7 +2403,9 @@ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err) } finalize: - bpf_prog_lock_ro(fp); + *err = bpf_prog_lock_ro(fp); + if (*err) + return fp; /* The tail call compatibility check can only be done at * this late stage as we need to determine, if we deal diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 7b208e5d38f6..de7813947981 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -19263,10 +19263,14 @@ static int jit_subprogs(struct bpf_verifier_env *env) * bpf_prog_load will add the kallsyms for the main program. */ for (i = 1; i < env->subprog_cnt; i++) { - bpf_prog_lock_ro(func[i]); - bpf_prog_kallsyms_add(func[i]); + err = bpf_prog_lock_ro(func[i]); + if (err) + goto out_free; } + for (i = 1; i < env->subprog_cnt; i++) + bpf_prog_kallsyms_add(func[i]); + /* Last step: make now unused interpreter insns from main * prog consistent for later dump requests, so they can * later look the same as if they were interpreted only. -- cgit v1.2.3 From e60adf513275c3a38e5cb67f7fd12387e43a3ff5 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Fri, 8 Mar 2024 06:38:08 +0100 Subject: bpf: Take return from set_memory_rox() into account with bpf_jit_binary_lock_ro() set_memory_rox() can fail, leaving memory unprotected. Check return and bail out when bpf_jit_binary_lock_ro() returns an error. Link: https://github.com/KSPP/linux/issues/7 Signed-off-by: Christophe Leroy Cc: linux-hardening@vger.kernel.org Reviewed-by: Kees Cook Reviewed-by: Puranjay Mohan Reviewed-by: Ilya Leoshkevich # s390x Acked-by: Tiezhu Yang # LoongArch Reviewed-by: Johan Almbladh # MIPS Part Message-ID: <036b6393f23a2032ce75a1c92220b2afcb798d5d.1709850515.git.christophe.leroy@csgroup.eu> Signed-off-by: Alexei Starovoitov --- arch/arm/net/bpf_jit_32.c | 25 ++++++++++++------------- arch/loongarch/net/bpf_jit.c | 22 ++++++++++++++++------ arch/mips/net/bpf_jit_comp.c | 3 ++- arch/parisc/net/bpf_jit_core.c | 8 +++++++- arch/s390/net/bpf_jit_comp.c | 6 +++++- arch/sparc/net/bpf_jit_comp_64.c | 6 +++++- arch/x86/net/bpf_jit_comp32.c | 3 +-- include/linux/filter.h | 5 +++-- 8 files changed, 51 insertions(+), 27 deletions(-) (limited to 'include') diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c index 1d672457d02f..01516f83a95a 100644 --- a/arch/arm/net/bpf_jit_32.c +++ b/arch/arm/net/bpf_jit_32.c @@ -2222,28 +2222,21 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) /* If building the body of the JITed code fails somehow, * we fall back to the interpretation. */ - if (build_body(&ctx) < 0) { - image_ptr = NULL; - bpf_jit_binary_free(header); - prog = orig_prog; - goto out_imms; - } + if (build_body(&ctx) < 0) + goto out_free; build_epilogue(&ctx); /* 3.) Extra pass to validate JITed Code */ - if (validate_code(&ctx)) { - image_ptr = NULL; - bpf_jit_binary_free(header); - prog = orig_prog; - goto out_imms; - } + if (validate_code(&ctx)) + goto out_free; flush_icache_range((u32)header, (u32)(ctx.target + ctx.idx)); if (bpf_jit_enable > 1) /* there are 2 passes here */ bpf_jit_dump(prog->len, image_size, 2, ctx.target); - bpf_jit_binary_lock_ro(header); + if (bpf_jit_binary_lock_ro(header)) + goto out_free; prog->bpf_func = (void *)ctx.target; prog->jited = 1; prog->jited_len = image_size; @@ -2260,5 +2253,11 @@ out: bpf_jit_prog_release_other(prog, prog == orig_prog ? tmp : orig_prog); return prog; + +out_free: + image_ptr = NULL; + bpf_jit_binary_free(header); + prog = orig_prog; + goto out_imms; } diff --git a/arch/loongarch/net/bpf_jit.c b/arch/loongarch/net/bpf_jit.c index e73323d759d0..7dbefd4ba210 100644 --- a/arch/loongarch/net/bpf_jit.c +++ b/arch/loongarch/net/bpf_jit.c @@ -1294,16 +1294,19 @@ skip_init_ctx: flush_icache_range((unsigned long)header, (unsigned long)(ctx.image + ctx.idx)); if (!prog->is_func || extra_pass) { + int err; + if (extra_pass && ctx.idx != jit_data->ctx.idx) { pr_err_once("multi-func JIT bug %d != %d\n", ctx.idx, jit_data->ctx.idx); - bpf_jit_binary_free(header); - prog->bpf_func = NULL; - prog->jited = 0; - prog->jited_len = 0; - goto out_offset; + goto out_free; + } + err = bpf_jit_binary_lock_ro(header); + if (err) { + pr_err_once("bpf_jit_binary_lock_ro() returned %d\n", + err); + goto out_free; } - bpf_jit_binary_lock_ro(header); } else { jit_data->ctx = ctx; jit_data->image = image_ptr; @@ -1334,6 +1337,13 @@ out: out_offset = -1; return prog; + +out_free: + bpf_jit_binary_free(header); + prog->bpf_func = NULL; + prog->jited = 0; + prog->jited_len = 0; + goto out_offset; } /* Indicate the JIT backend supports mixing bpf2bpf and tailcalls. */ diff --git a/arch/mips/net/bpf_jit_comp.c b/arch/mips/net/bpf_jit_comp.c index a40d926b6513..e355dfca4400 100644 --- a/arch/mips/net/bpf_jit_comp.c +++ b/arch/mips/net/bpf_jit_comp.c @@ -1012,7 +1012,8 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) bpf_prog_fill_jited_linfo(prog, &ctx.descriptors[1]); /* Set as read-only exec and flush instruction cache */ - bpf_jit_binary_lock_ro(header); + if (bpf_jit_binary_lock_ro(header)) + goto out_err; flush_icache_range((unsigned long)header, (unsigned long)&ctx.target[ctx.jit_index]); diff --git a/arch/parisc/net/bpf_jit_core.c b/arch/parisc/net/bpf_jit_core.c index d6ee2fd45550..979f45d4d1fb 100644 --- a/arch/parisc/net/bpf_jit_core.c +++ b/arch/parisc/net/bpf_jit_core.c @@ -167,7 +167,13 @@ skip_init_ctx: bpf_flush_icache(jit_data->header, ctx->insns + ctx->ninsns); if (!prog->is_func || extra_pass) { - bpf_jit_binary_lock_ro(jit_data->header); + if (bpf_jit_binary_lock_ro(jit_data->header)) { + bpf_jit_binary_free(jit_data->header); + prog->bpf_func = NULL; + prog->jited = 0; + prog->jited_len = 0; + goto out_offset; + } prologue_len = ctx->epilogue_offset - ctx->body_len; for (i = 0; i < prog->len; i++) ctx->offset[i] += prologue_len; diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index b418333bb086..e613eebfd349 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -2111,7 +2111,11 @@ skip_init_ctx: print_fn_code(jit.prg_buf, jit.size_prg); } if (!fp->is_func || extra_pass) { - bpf_jit_binary_lock_ro(header); + if (bpf_jit_binary_lock_ro(header)) { + bpf_jit_binary_free(header); + fp = orig_fp; + goto free_addrs; + } } else { jit_data->header = header; jit_data->ctx = jit; diff --git a/arch/sparc/net/bpf_jit_comp_64.c b/arch/sparc/net/bpf_jit_comp_64.c index fa0759bfe498..73bf0aea8baf 100644 --- a/arch/sparc/net/bpf_jit_comp_64.c +++ b/arch/sparc/net/bpf_jit_comp_64.c @@ -1602,7 +1602,11 @@ skip_init_ctx: bpf_flush_icache(header, (u8 *)header + header->size); if (!prog->is_func || extra_pass) { - bpf_jit_binary_lock_ro(header); + if (bpf_jit_binary_lock_ro(header)) { + bpf_jit_binary_free(header); + prog = orig_prog; + goto out_off; + } } else { jit_data->ctx = ctx; jit_data->image = image_ptr; diff --git a/arch/x86/net/bpf_jit_comp32.c b/arch/x86/net/bpf_jit_comp32.c index c10083a8e68e..de0f9e5f9f73 100644 --- a/arch/x86/net/bpf_jit_comp32.c +++ b/arch/x86/net/bpf_jit_comp32.c @@ -2600,8 +2600,7 @@ out_image: if (bpf_jit_enable > 1) bpf_jit_dump(prog->len, proglen, pass + 1, image); - if (image) { - bpf_jit_binary_lock_ro(header); + if (image && !bpf_jit_binary_lock_ro(header)) { prog->bpf_func = (void *)image; prog->jited = 1; prog->jited_len = proglen; diff --git a/include/linux/filter.h b/include/linux/filter.h index 9107ee1de66f..c0d51bff8f96 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -898,10 +898,11 @@ static inline int __must_check bpf_prog_lock_ro(struct bpf_prog *fp) return 0; } -static inline void bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr) +static inline int __must_check +bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr) { set_vm_flush_reset_perms(hdr); - set_memory_rox((unsigned long)hdr, hdr->size >> PAGE_SHIFT); + return set_memory_rox((unsigned long)hdr, hdr->size >> PAGE_SHIFT); } int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap); -- cgit v1.2.3 From 734364d0ddee6c145705bac89400266c972efc0b Mon Sep 17 00:00:00 2001 From: Abel Vesa Date: Fri, 23 Feb 2024 16:37:55 +0200 Subject: dt-bindings: arm: qcom,ids: Add SoC ID for X1E80100 Add the ID for the Qualcomm X1E80100 SoC. Signed-off-by: Abel Vesa Reviewed-by: Konrad Dybcio Reviewed-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20240223-x1e80100-socinfo-v1-1-be581ca60f27@linaro.org Signed-off-by: Bjorn Andersson --- include/dt-bindings/arm/qcom,ids.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/dt-bindings/arm/qcom,ids.h b/include/dt-bindings/arm/qcom,ids.h index 19ac7b36f608..d040033dc8ee 100644 --- a/include/dt-bindings/arm/qcom,ids.h +++ b/include/dt-bindings/arm/qcom,ids.h @@ -258,6 +258,7 @@ #define QCOM_ID_QRU1000 539 #define QCOM_ID_SM8475_2 540 #define QCOM_ID_QDU1000 545 +#define QCOM_ID_X1E80100 555 #define QCOM_ID_SM8650 557 #define QCOM_ID_SM4450 568 #define QCOM_ID_QDU1010 587 -- cgit v1.2.3 From 01c0cce88c5480cc2505b79330246ef12eda938f Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Wed, 28 Feb 2024 08:35:32 +0200 Subject: drm/omapdrm: Fix console with deferred ops Commit 95da53d63dcf ("drm/omapdrm: Use regular fbdev I/O helpers") stopped console from updating for command mode displays because there is no damage handling in fb_sys_write() unlike we had earlier in drm_fb_helper_sys_write(). Let's fix the issue by adding FB_GEN_DEFAULT_DEFERRED_DMAMEM_OPS and FB_DMAMEM_HELPERS_DEFERRED as suggested by Thomas. We cannot use the FB_DEFAULT_DEFERRED_OPS as fb_deferred_io_mmap() won't work properly for write-combine. Fixes: 95da53d63dcf ("drm/omapdrm: Use regular fbdev I/O helpers") Suggested-by: Thomas Zimmermann Reviewed-by: Thomas Zimmermann Signed-off-by: Tony Lindgren Signed-off-by: Tomi Valkeinen Link: https://patchwork.freedesktop.org/patch/msgid/20240228063540.4444-3-tony@atomide.com --- drivers/gpu/drm/omapdrm/Kconfig | 2 +- drivers/gpu/drm/omapdrm/omap_fbdev.c | 28 ++++++++++++++++++++++------ drivers/video/fbdev/core/Kconfig | 6 ++++++ include/linux/fb.h | 4 ++++ 4 files changed, 33 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/omapdrm/Kconfig b/drivers/gpu/drm/omapdrm/Kconfig index b715301ec79f..6c49270cb290 100644 --- a/drivers/gpu/drm/omapdrm/Kconfig +++ b/drivers/gpu/drm/omapdrm/Kconfig @@ -4,7 +4,7 @@ config DRM_OMAP depends on DRM && OF depends on ARCH_OMAP2PLUS select DRM_KMS_HELPER - select FB_DMAMEM_HELPERS if DRM_FBDEV_EMULATION + select FB_DMAMEM_HELPERS_DEFERRED if DRM_FBDEV_EMULATION select VIDEOMODE_HELPERS select HDMI default n diff --git a/drivers/gpu/drm/omapdrm/omap_fbdev.c b/drivers/gpu/drm/omapdrm/omap_fbdev.c index 7c5af3de1e72..523be34682ca 100644 --- a/drivers/gpu/drm/omapdrm/omap_fbdev.c +++ b/drivers/gpu/drm/omapdrm/omap_fbdev.c @@ -51,6 +51,10 @@ static void pan_worker(struct work_struct *work) omap_gem_roll(bo, fbi->var.yoffset * npages); } +FB_GEN_DEFAULT_DEFERRED_DMAMEM_OPS(omap_fbdev, + drm_fb_helper_damage_range, + drm_fb_helper_damage_area) + static int omap_fbdev_pan_display(struct fb_var_screeninfo *var, struct fb_info *fbi) { @@ -78,11 +82,9 @@ fallback: static int omap_fbdev_fb_mmap(struct fb_info *info, struct vm_area_struct *vma) { - struct drm_fb_helper *helper = info->par; - struct drm_framebuffer *fb = helper->fb; - struct drm_gem_object *bo = drm_gem_fb_get_obj(fb, 0); + vma->vm_page_prot = pgprot_writecombine(vm_get_page_prot(vma->vm_flags)); - return drm_gem_mmap_obj(bo, omap_gem_mmap_size(bo), vma); + return fb_deferred_io_mmap(info, vma); } static void omap_fbdev_fb_destroy(struct fb_info *info) @@ -94,6 +96,7 @@ static void omap_fbdev_fb_destroy(struct fb_info *info) DBG(); + fb_deferred_io_cleanup(info); drm_fb_helper_fini(helper); omap_gem_unpin(bo); @@ -104,15 +107,19 @@ static void omap_fbdev_fb_destroy(struct fb_info *info) kfree(fbdev); } +/* + * For now, we cannot use FB_DEFAULT_DEFERRED_OPS and fb_deferred_io_mmap() + * because we use write-combine. + */ static const struct fb_ops omap_fb_ops = { .owner = THIS_MODULE, - __FB_DEFAULT_DMAMEM_OPS_RDWR, + __FB_DEFAULT_DEFERRED_OPS_RDWR(omap_fbdev), .fb_check_var = drm_fb_helper_check_var, .fb_set_par = drm_fb_helper_set_par, .fb_setcmap = drm_fb_helper_setcmap, .fb_blank = drm_fb_helper_blank, .fb_pan_display = omap_fbdev_pan_display, - __FB_DEFAULT_DMAMEM_OPS_DRAW, + __FB_DEFAULT_DEFERRED_OPS_DRAW(omap_fbdev), .fb_ioctl = drm_fb_helper_ioctl, .fb_mmap = omap_fbdev_fb_mmap, .fb_destroy = omap_fbdev_fb_destroy, @@ -213,6 +220,15 @@ static int omap_fbdev_create(struct drm_fb_helper *helper, fbi->fix.smem_start = dma_addr; fbi->fix.smem_len = bo->size; + /* deferred I/O */ + helper->fbdefio.delay = HZ / 20; + helper->fbdefio.deferred_io = drm_fb_helper_deferred_io; + + fbi->fbdefio = &helper->fbdefio; + ret = fb_deferred_io_init(fbi); + if (ret) + goto fail; + /* if we have DMM, then we can use it for scrolling by just * shuffling pages around in DMM rather than doing sw blit. */ diff --git a/drivers/video/fbdev/core/Kconfig b/drivers/video/fbdev/core/Kconfig index db09fe87fcd4..0ab8848ba2f1 100644 --- a/drivers/video/fbdev/core/Kconfig +++ b/drivers/video/fbdev/core/Kconfig @@ -144,6 +144,12 @@ config FB_DMAMEM_HELPERS select FB_SYS_IMAGEBLIT select FB_SYSMEM_FOPS +config FB_DMAMEM_HELPERS_DEFERRED + bool + depends on FB_CORE + select FB_DEFERRED_IO + select FB_DMAMEM_HELPERS + config FB_IOMEM_FOPS tristate depends on FB_CORE diff --git a/include/linux/fb.h b/include/linux/fb.h index 708e6a177b1b..5e210bf72fc9 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -688,6 +688,10 @@ extern int fb_deferred_io_fsync(struct file *file, loff_t start, __FB_GEN_DEFAULT_DEFERRED_OPS_RDWR(__prefix, __damage_range, sys) \ __FB_GEN_DEFAULT_DEFERRED_OPS_DRAW(__prefix, __damage_area, sys) +#define FB_GEN_DEFAULT_DEFERRED_DMAMEM_OPS(__prefix, __damage_range, __damage_area) \ + __FB_GEN_DEFAULT_DEFERRED_OPS_RDWR(__prefix, __damage_range, sys) \ + __FB_GEN_DEFAULT_DEFERRED_OPS_DRAW(__prefix, __damage_area, sys) + /* * Initializes struct fb_ops for deferred I/O. */ -- cgit v1.2.3 From e3362acd796789dc0562eb1a3937007b0beb0c5b Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Sat, 16 Mar 2024 08:35:40 +0100 Subject: bpf: Remove arch_unprotect_bpf_trampoline() Last user of arch_unprotect_bpf_trampoline() was removed by commit 187e2af05abe ("bpf: struct_ops supports more than one page for trampolines.") Remove arch_unprotect_bpf_trampoline() Reported-by: Daniel Borkmann Fixes: 187e2af05abe ("bpf: struct_ops supports more than one page for trampolines.") Signed-off-by: Christophe Leroy Link: https://lore.kernel.org/r/42c635bb54d3af91db0f9b85d724c7c290069f67.1710574353.git.christophe.leroy@csgroup.eu Signed-off-by: Martin KaFai Lau --- arch/arm64/net/bpf_jit_comp.c | 4 ---- arch/x86/net/bpf_jit_comp.c | 4 ---- include/linux/bpf.h | 1 - kernel/bpf/trampoline.c | 7 ------- 4 files changed, 16 deletions(-) (limited to 'include') diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index c5b461dda438..132c8ffba109 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -2180,10 +2180,6 @@ void arch_protect_bpf_trampoline(void *image, unsigned int size) { } -void arch_unprotect_bpf_trampoline(void *image, unsigned int size) -{ -} - int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *ro_image, void *ro_image_end, const struct btf_func_model *m, u32 flags, struct bpf_tramp_links *tlinks, diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index a7ba8e178645..7a56d2d84512 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -3008,10 +3008,6 @@ void arch_protect_bpf_trampoline(void *image, unsigned int size) { } -void arch_unprotect_bpf_trampoline(void *image, unsigned int size) -{ -} - int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *image_end, const struct btf_func_model *m, u32 flags, struct bpf_tramp_links *tlinks, diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 4f20f62f9d63..d89bdefb42e2 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1117,7 +1117,6 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i void *arch_alloc_bpf_trampoline(unsigned int size); void arch_free_bpf_trampoline(void *image, unsigned int size); void arch_protect_bpf_trampoline(void *image, unsigned int size); -void arch_unprotect_bpf_trampoline(void *image, unsigned int size); int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags, struct bpf_tramp_links *tlinks, void *func_addr); diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c index db7599c59c78..04fd1abd3661 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -1078,13 +1078,6 @@ void __weak arch_protect_bpf_trampoline(void *image, unsigned int size) set_memory_rox((long)image, 1); } -void __weak arch_unprotect_bpf_trampoline(void *image, unsigned int size) -{ - WARN_ON_ONCE(size > PAGE_SIZE); - set_memory_nx((long)image, 1); - set_memory_rw((long)image, 1); -} - int __weak arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags, struct bpf_tramp_links *tlinks, void *func_addr) { -- cgit v1.2.3 From c733239f8f530872a1f80d8c45dcafbaff368737 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Sat, 16 Mar 2024 08:35:41 +0100 Subject: bpf: Check return from set_memory_rox() arch_protect_bpf_trampoline() and alloc_new_pack() call set_memory_rox() which can fail, leading to unprotected memory. Take into account return from set_memory_rox() function and add __must_check flag to arch_protect_bpf_trampoline(). Signed-off-by: Christophe Leroy Reviewed-by: Kees Cook Link: https://lore.kernel.org/r/fe1c163c83767fde5cab31d209a4a6be3ddb3a73.1710574353.git.christophe.leroy@csgroup.eu Signed-off-by: Martin KaFai Lau --- arch/arm64/net/bpf_jit_comp.c | 3 ++- arch/x86/net/bpf_jit_comp.c | 3 ++- include/linux/bpf.h | 2 +- kernel/bpf/bpf_struct_ops.c | 8 ++++++-- kernel/bpf/core.c | 28 +++++++++++++++++++++------- kernel/bpf/trampoline.c | 8 +++++--- net/bpf/bpf_dummy_struct_ops.c | 4 +++- 7 files changed, 40 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index 132c8ffba109..bc16eb694657 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -2176,8 +2176,9 @@ void arch_free_bpf_trampoline(void *image, unsigned int size) bpf_prog_pack_free(image, size); } -void arch_protect_bpf_trampoline(void *image, unsigned int size) +int arch_protect_bpf_trampoline(void *image, unsigned int size) { + return 0; } int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *ro_image, diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 7a56d2d84512..4900b1ee019f 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -3004,8 +3004,9 @@ void arch_free_bpf_trampoline(void *image, unsigned int size) bpf_prog_pack_free(image, size); } -void arch_protect_bpf_trampoline(void *image, unsigned int size) +int arch_protect_bpf_trampoline(void *image, unsigned int size) { + return 0; } int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *image_end, diff --git a/include/linux/bpf.h b/include/linux/bpf.h index d89bdefb42e2..17843e66a1d3 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1116,7 +1116,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i void *func_addr); void *arch_alloc_bpf_trampoline(unsigned int size); void arch_free_bpf_trampoline(void *image, unsigned int size); -void arch_protect_bpf_trampoline(void *image, unsigned int size); +int __must_check arch_protect_bpf_trampoline(void *image, unsigned int size); int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags, struct bpf_tramp_links *tlinks, void *func_addr); diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c index 3fcd35314ce5..86c7884abaf8 100644 --- a/kernel/bpf/bpf_struct_ops.c +++ b/kernel/bpf/bpf_struct_ops.c @@ -740,8 +740,12 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, if (err) goto reset_unlock; } - for (i = 0; i < st_map->image_pages_cnt; i++) - arch_protect_bpf_trampoline(st_map->image_pages[i], PAGE_SIZE); + for (i = 0; i < st_map->image_pages_cnt; i++) { + err = arch_protect_bpf_trampoline(st_map->image_pages[i], + PAGE_SIZE); + if (err) + goto reset_unlock; + } if (st_map->map.map_flags & BPF_F_LINK) { err = 0; diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 63f100def31b..5aacb1d3c4cc 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -908,23 +908,30 @@ static LIST_HEAD(pack_list); static struct bpf_prog_pack *alloc_new_pack(bpf_jit_fill_hole_t bpf_fill_ill_insns) { struct bpf_prog_pack *pack; + int err; pack = kzalloc(struct_size(pack, bitmap, BITS_TO_LONGS(BPF_PROG_CHUNK_COUNT)), GFP_KERNEL); if (!pack) return NULL; pack->ptr = bpf_jit_alloc_exec(BPF_PROG_PACK_SIZE); - if (!pack->ptr) { - kfree(pack); - return NULL; - } + if (!pack->ptr) + goto out; bpf_fill_ill_insns(pack->ptr, BPF_PROG_PACK_SIZE); bitmap_zero(pack->bitmap, BPF_PROG_PACK_SIZE / BPF_PROG_CHUNK_SIZE); - list_add_tail(&pack->list, &pack_list); set_vm_flush_reset_perms(pack->ptr); - set_memory_rox((unsigned long)pack->ptr, BPF_PROG_PACK_SIZE / PAGE_SIZE); + err = set_memory_rox((unsigned long)pack->ptr, + BPF_PROG_PACK_SIZE / PAGE_SIZE); + if (err) + goto out; + list_add_tail(&pack->list, &pack_list); return pack; + +out: + bpf_jit_free_exec(pack->ptr); + kfree(pack); + return NULL; } void *bpf_prog_pack_alloc(u32 size, bpf_jit_fill_hole_t bpf_fill_ill_insns) @@ -939,9 +946,16 @@ void *bpf_prog_pack_alloc(u32 size, bpf_jit_fill_hole_t bpf_fill_ill_insns) size = round_up(size, PAGE_SIZE); ptr = bpf_jit_alloc_exec(size); if (ptr) { + int err; + bpf_fill_ill_insns(ptr, size); set_vm_flush_reset_perms(ptr); - set_memory_rox((unsigned long)ptr, size / PAGE_SIZE); + err = set_memory_rox((unsigned long)ptr, + size / PAGE_SIZE); + if (err) { + bpf_jit_free_exec(ptr); + ptr = NULL; + } } goto out; } diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c index 04fd1abd3661..cc50607f8d8c 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -456,7 +456,9 @@ again: if (err < 0) goto out_free; - arch_protect_bpf_trampoline(im->image, im->size); + err = arch_protect_bpf_trampoline(im->image, im->size); + if (err) + goto out_free; WARN_ON(tr->cur_image && total == 0); if (tr->cur_image) @@ -1072,10 +1074,10 @@ void __weak arch_free_bpf_trampoline(void *image, unsigned int size) bpf_jit_free_exec(image); } -void __weak arch_protect_bpf_trampoline(void *image, unsigned int size) +int __weak arch_protect_bpf_trampoline(void *image, unsigned int size) { WARN_ON_ONCE(size > PAGE_SIZE); - set_memory_rox((long)image, 1); + return set_memory_rox((long)image, 1); } int __weak arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags, diff --git a/net/bpf/bpf_dummy_struct_ops.c b/net/bpf/bpf_dummy_struct_ops.c index de33dc1b0daa..25b75844891a 100644 --- a/net/bpf/bpf_dummy_struct_ops.c +++ b/net/bpf/bpf_dummy_struct_ops.c @@ -133,7 +133,9 @@ int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr, if (err < 0) goto out; - arch_protect_bpf_trampoline(image, PAGE_SIZE); + err = arch_protect_bpf_trampoline(image, PAGE_SIZE); + if (err) + goto out; prog_ret = dummy_ops_call_op(image, args); err = dummy_ops_copy_args(args); -- cgit v1.2.3 From 8522f6b760ca588928eede740d5d69dd1e936b49 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 28 Feb 2024 15:00:02 +0100 Subject: printk: Let no_printk() use _printk() When printk-indexing is enabled, each printk() invocation emits a pi_entry structure, containing the format string and other information related to its location in the kernel sources. This is even true for no_printk(): while the actual code to print the message is optimized out by the compiler due to the always-false check, the pi_entry structure is still emitted. As the main purpose of no_printk() is to provide a helper to maintain printf()-style format checking when debugging is disabled, this leads to the inclusion in the index of lots of printk formats that cannot be emitted by the current kernel. Fix this by switching no_printk() from printk() to _printk(). This reduces the size of an arm64 defconfig kernel with CONFIG_PRINTK_INDEX=y by 576 KiB. Fixes: 337015573718b161 ("printk: Userspace format indexing support") Signed-off-by: Geert Uytterhoeven Reviewed-by: Andy Shevchenko Reviewed-by: Xiubo Li Reviewed-by: Chris Down Reviewed-by: Petr Mladek Link: https://lore.kernel.org/r/56cf92edccffea970e1f40a075334dd6cf5bb2a4.1709127473.git.geert+renesas@glider.be Signed-off-by: Petr Mladek --- include/linux/printk.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/printk.h b/include/linux/printk.h index 955e31860095..2fde40cc9677 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -126,7 +126,7 @@ struct va_format { #define no_printk(fmt, ...) \ ({ \ if (0) \ - printk(fmt, ##__VA_ARGS__); \ + _printk(fmt, ##__VA_ARGS__); \ 0; \ }) -- cgit v1.2.3 From c26ec799042a3888935d59b599f33e41efedf5f8 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 28 Feb 2024 15:00:03 +0100 Subject: dev_printk: Add and use dev_no_printk() When printk-indexing is enabled, each dev_printk() invocation emits a pi_entry structure. This is even true when the dev_printk() is protected by an always-false check, as is typically the case for debug messages: while the actual code to print the message is optimized out by the compiler, the pi_entry structure is still emitted. Avoid emitting pi_entry structures for unavailable dev_printk() kernel messages by: 1. Introducing a dev_no_printk() helper, mimicked after the existing no_printk() helper, which calls _dev_printk() instead of dev_printk(), 2. Replacing all "if (0) dev_printk(...)" constructs by calls to the new helper. This reduces the size of an arm64 defconfig kernel with CONFIG_PRINTK_INDEX=y by 957 KiB. Fixes: ad7d61f159db7397 ("printk: index: Add indexing support to dev_printk") Signed-off-by: Geert Uytterhoeven Reviewed-by: Andy Shevchenko Reviewed-by: Xiubo Li Reviewed-by: Chris Down Reviewed-by: Petr Mladek Link: https://lore.kernel.org/r/8583d54f1687c801c6cda8edddf2cf0344c6e883.1709127473.git.geert+renesas@glider.be Signed-off-by: Petr Mladek --- include/linux/dev_printk.h | 25 +++++++++++++------------ 1 file changed, 13 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/linux/dev_printk.h b/include/linux/dev_printk.h index 6bfe70decc9f..ae80a303c216 100644 --- a/include/linux/dev_printk.h +++ b/include/linux/dev_printk.h @@ -129,6 +129,16 @@ void _dev_info(const struct device *dev, const char *fmt, ...) _dev_printk(level, dev, fmt, ##__VA_ARGS__); \ }) +/* + * Dummy dev_printk for disabled debugging statements to use whilst maintaining + * gcc's format checking. + */ +#define dev_no_printk(level, dev, fmt, ...) \ + ({ \ + if (0) \ + _dev_printk(level, dev, fmt, ##__VA_ARGS__); \ + }) + /* * #defines for all the dev_ macros to prefix with whatever * possible use of #define dev_fmt(fmt) ... @@ -158,10 +168,7 @@ void _dev_info(const struct device *dev, const char *fmt, ...) dev_printk(KERN_DEBUG, dev, dev_fmt(fmt), ##__VA_ARGS__) #else #define dev_dbg(dev, fmt, ...) \ -({ \ - if (0) \ - dev_printk(KERN_DEBUG, dev, dev_fmt(fmt), ##__VA_ARGS__); \ -}) + dev_no_printk(KERN_DEBUG, dev, dev_fmt(fmt), ##__VA_ARGS__) #endif #ifdef CONFIG_PRINTK @@ -247,20 +254,14 @@ do { \ } while (0) #else #define dev_dbg_ratelimited(dev, fmt, ...) \ -do { \ - if (0) \ - dev_printk(KERN_DEBUG, dev, dev_fmt(fmt), ##__VA_ARGS__); \ -} while (0) + dev_no_printk(KERN_DEBUG, dev, dev_fmt(fmt), ##__VA_ARGS__) #endif #ifdef VERBOSE_DEBUG #define dev_vdbg dev_dbg #else #define dev_vdbg(dev, fmt, ...) \ -({ \ - if (0) \ - dev_printk(KERN_DEBUG, dev, dev_fmt(fmt), ##__VA_ARGS__); \ -}) + dev_no_printk(KERN_DEBUG, dev, dev_fmt(fmt), ##__VA_ARGS__) #endif /* -- cgit v1.2.3 From 0381e588949380704005dacdbef6e9a2920260df Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 28 Feb 2024 15:00:04 +0100 Subject: dyndbg: Use *no_printk() helpers When printk-indexing is enabled, each printk() or dev_printk() invocation emits a pi_entry structure. This is even true when the call is protected by an always-false check: while the actual code to print the message is optimized out by the compiler, the pi_entry structure is still emitted. Fix this by replacing "if (0) *printk(...)" constructs by calls to the corresponding *no_printk() helpers. Note that this has minimal impact, as most (all?) callers of dynamic_{pr,dev}_debug() are protected by checks for DYNAMIC_DEBUG anyway. Still, using the helpers serves as a good example to follow. Signed-off-by: Geert Uytterhoeven Reviewed-by: Andy Shevchenko Reviewed-by: Xiubo Li Reviewed-by: Chris Down Reviewed-by: Petr Mladek Link: https://lore.kernel.org/r/32e18ceb528b99d9147be9c1af578a1965e2bad9.1709127473.git.geert+renesas@glider.be Signed-off-by: Petr Mladek --- include/linux/dynamic_debug.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/dynamic_debug.h b/include/linux/dynamic_debug.h index 4fcbf4d4fd0a..ff44ec346162 100644 --- a/include/linux/dynamic_debug.h +++ b/include/linux/dynamic_debug.h @@ -305,9 +305,9 @@ void __dynamic_ibdev_dbg(struct _ddebug *descriptor, #define DYNAMIC_DEBUG_BRANCH(descriptor) false #define dynamic_pr_debug(fmt, ...) \ - do { if (0) printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__); } while (0) + no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #define dynamic_dev_dbg(dev, fmt, ...) \ - do { if (0) dev_printk(KERN_DEBUG, dev, fmt, ##__VA_ARGS__); } while (0) + dev_no_printk(KERN_DEBUG, dev, fmt, ##__VA_ARGS__) #define dynamic_hex_dump(prefix_str, prefix_type, rowsize, \ groupsize, buf, len, ascii) \ do { if (0) \ -- cgit v1.2.3 From b37cafacbf98ead69c2ecb220fb82b06aee916b9 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 28 Feb 2024 15:00:05 +0100 Subject: ceph: Use no_printk() helper When printk-indexing is enabled, each printk() invocation emits a pi_entry structure. This is even true when the call is protected by an always-false check: while the actual code to print the message is optimized out by the compiler, the pi_entry structure is still emitted. Fix this by replacing "if (0) printk(...)" constructs by calls to the no_printk() helper. This reduces the size of an arm64 kernel with CONFIG_PRINTK_INDEX=y and CONFIG_CEPH_FS=y by ca. 4 KiB. Signed-off-by: Geert Uytterhoeven Reviewed-by: Andy Shevchenko Reviewed-by: Xiubo Li Reviewed-by: Chris Down Reviewed-by: Petr Mladek Link: https://lore.kernel.org/r/a21767eccb823435a7f18cdf115d7d572b4e945d.1709127473.git.geert+renesas@glider.be Signed-off-by: Petr Mladek --- include/linux/ceph/ceph_debug.h | 18 +++++++----------- 1 file changed, 7 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/linux/ceph/ceph_debug.h b/include/linux/ceph/ceph_debug.h index 11a92a946016..5f904591fa5f 100644 --- a/include/linux/ceph/ceph_debug.h +++ b/include/linux/ceph/ceph_debug.h @@ -27,17 +27,13 @@ ##__VA_ARGS__) # else /* faux printk call just to see any compiler warnings. */ -# define dout(fmt, ...) do { \ - if (0) \ - printk(KERN_DEBUG fmt, ##__VA_ARGS__); \ - } while (0) -# define doutc(client, fmt, ...) do { \ - if (0) \ - printk(KERN_DEBUG "[%pU %llu] " fmt, \ - &client->fsid, \ - client->monc.auth->global_id, \ - ##__VA_ARGS__); \ - } while (0) +# define dout(fmt, ...) \ + no_printk(KERN_DEBUG fmt, ##__VA_ARGS__) +# define doutc(client, fmt, ...) \ + no_printk(KERN_DEBUG "[%pU %llu] " fmt, \ + &client->fsid, \ + client->monc.auth->global_id, \ + ##__VA_ARGS__) # endif #else -- cgit v1.2.3 From d4dfc5700e867b22ab94f960f9a9972696a637d5 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 19 Mar 2024 16:38:49 -0700 Subject: bpf: pass whole link instead of prog when triggering raw tracepoint Instead of passing prog as an argument to bpf_trace_runX() helpers, that are called from tracepoint triggering calls, store BPF link itself (struct bpf_raw_tp_link for raw tracepoints). This will allow to pass extra information like BPF cookie into raw tracepoint registration. Instead of replacing `struct bpf_prog *prog = __data;` with corresponding `struct bpf_raw_tp_link *link = __data;` assignment in `__bpf_trace_##call` I just passed `__data` through into underlying bpf_trace_runX() call. This works well because we implicitly cast `void *`, and it also avoids naming clashes with arguments coming from tracepoint's "proto" list. We could have run into the same problem with "prog", we just happened to not have a tracepoint that has "prog" input argument. We are less lucky with "link", as there are tracepoints using "link" argument name already. So instead of trying to avoid naming conflicts, let's just remove intermediate local variable. It doesn't hurt readibility, it's either way a bit of a maze of calls and macros, that requires careful reading. Acked-by: Stanislav Fomichev Signed-off-by: Andrii Nakryiko Message-ID: <20240319233852.1977493-3-andrii@kernel.org> Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 5 +++++ include/linux/trace_events.h | 36 ++++++++++++++++++++---------------- include/trace/bpf_probe.h | 3 +-- kernel/bpf/syscall.c | 9 ++------- kernel/trace/bpf_trace.c | 18 ++++++++++-------- 5 files changed, 38 insertions(+), 33 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 17843e66a1d3..2ea8ce59f582 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1607,6 +1607,11 @@ struct bpf_tracing_link { struct bpf_prog *tgt_prog; }; +struct bpf_raw_tp_link { + struct bpf_link link; + struct bpf_raw_event_map *btp; +}; + struct bpf_link_primer { struct bpf_link *link; struct file *file; diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index d68ff9b1247f..a7fc6fb6de3c 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -759,8 +759,11 @@ unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx); int perf_event_attach_bpf_prog(struct perf_event *event, struct bpf_prog *prog, u64 bpf_cookie); void perf_event_detach_bpf_prog(struct perf_event *event); int perf_event_query_prog_array(struct perf_event *event, void __user *info); -int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog *prog); -int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_prog *prog); + +struct bpf_raw_tp_link; +int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_raw_tp_link *link); +int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_raw_tp_link *link); + struct bpf_raw_event_map *bpf_get_raw_tracepoint(const char *name); void bpf_put_raw_tracepoint(struct bpf_raw_event_map *btp); int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id, @@ -788,11 +791,12 @@ perf_event_query_prog_array(struct perf_event *event, void __user *info) { return -EOPNOTSUPP; } -static inline int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog *p) +struct bpf_raw_tp_link; +static inline int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_raw_tp_link *link) { return -EOPNOTSUPP; } -static inline int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_prog *p) +static inline int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_raw_tp_link *link) { return -EOPNOTSUPP; } @@ -903,31 +907,31 @@ void *perf_trace_buf_alloc(int size, struct pt_regs **regs, int *rctxp); int perf_event_set_bpf_prog(struct perf_event *event, struct bpf_prog *prog, u64 bpf_cookie); void perf_event_free_bpf_prog(struct perf_event *event); -void bpf_trace_run1(struct bpf_prog *prog, u64 arg1); -void bpf_trace_run2(struct bpf_prog *prog, u64 arg1, u64 arg2); -void bpf_trace_run3(struct bpf_prog *prog, u64 arg1, u64 arg2, +void bpf_trace_run1(struct bpf_raw_tp_link *link, u64 arg1); +void bpf_trace_run2(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2); +void bpf_trace_run3(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3); -void bpf_trace_run4(struct bpf_prog *prog, u64 arg1, u64 arg2, +void bpf_trace_run4(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3, u64 arg4); -void bpf_trace_run5(struct bpf_prog *prog, u64 arg1, u64 arg2, +void bpf_trace_run5(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3, u64 arg4, u64 arg5); -void bpf_trace_run6(struct bpf_prog *prog, u64 arg1, u64 arg2, +void bpf_trace_run6(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3, u64 arg4, u64 arg5, u64 arg6); -void bpf_trace_run7(struct bpf_prog *prog, u64 arg1, u64 arg2, +void bpf_trace_run7(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7); -void bpf_trace_run8(struct bpf_prog *prog, u64 arg1, u64 arg2, +void bpf_trace_run8(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7, u64 arg8); -void bpf_trace_run9(struct bpf_prog *prog, u64 arg1, u64 arg2, +void bpf_trace_run9(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7, u64 arg8, u64 arg9); -void bpf_trace_run10(struct bpf_prog *prog, u64 arg1, u64 arg2, +void bpf_trace_run10(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7, u64 arg8, u64 arg9, u64 arg10); -void bpf_trace_run11(struct bpf_prog *prog, u64 arg1, u64 arg2, +void bpf_trace_run11(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7, u64 arg8, u64 arg9, u64 arg10, u64 arg11); -void bpf_trace_run12(struct bpf_prog *prog, u64 arg1, u64 arg2, +void bpf_trace_run12(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7, u64 arg8, u64 arg9, u64 arg10, u64 arg11, u64 arg12); void perf_trace_run_bpf_submit(void *raw_data, int size, int rctx, diff --git a/include/trace/bpf_probe.h b/include/trace/bpf_probe.h index e609cd7da47e..a2ea11cc912e 100644 --- a/include/trace/bpf_probe.h +++ b/include/trace/bpf_probe.h @@ -46,8 +46,7 @@ static notrace void \ __bpf_trace_##call(void *__data, proto) \ { \ - struct bpf_prog *prog = __data; \ - CONCATENATE(bpf_trace_run, COUNT_ARGS(args))(prog, CAST_TO_U64(args)); \ + CONCATENATE(bpf_trace_run, COUNT_ARGS(args))(__data, CAST_TO_U64(args)); \ } #undef DECLARE_EVENT_CLASS diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index ae2ff73bde7e..1cb4c3809af4 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -3469,17 +3469,12 @@ out_put_prog: return err; } -struct bpf_raw_tp_link { - struct bpf_link link; - struct bpf_raw_event_map *btp; -}; - static void bpf_raw_tp_link_release(struct bpf_link *link) { struct bpf_raw_tp_link *raw_tp = container_of(link, struct bpf_raw_tp_link, link); - bpf_probe_unregister(raw_tp->btp, raw_tp->link.prog); + bpf_probe_unregister(raw_tp->btp, raw_tp); bpf_put_raw_tracepoint(raw_tp->btp); } @@ -3833,7 +3828,7 @@ static int bpf_raw_tp_link_attach(struct bpf_prog *prog, goto out_put_btp; } - err = bpf_probe_register(link->btp, prog); + err = bpf_probe_register(link->btp, link); if (err) { bpf_link_cleanup(&link_primer); goto out_put_btp; diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 30ecf62f8a17..17de91ad4a1f 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -2366,8 +2366,10 @@ void bpf_put_raw_tracepoint(struct bpf_raw_event_map *btp) } static __always_inline -void __bpf_trace_run(struct bpf_prog *prog, u64 *args) +void __bpf_trace_run(struct bpf_raw_tp_link *link, u64 *args) { + struct bpf_prog *prog = link->link.prog; + cant_sleep(); if (unlikely(this_cpu_inc_return(*(prog->active)) != 1)) { bpf_prog_inc_misses_counter(prog); @@ -2404,12 +2406,12 @@ out: #define __SEQ_0_11 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11 #define BPF_TRACE_DEFN_x(x) \ - void bpf_trace_run##x(struct bpf_prog *prog, \ + void bpf_trace_run##x(struct bpf_raw_tp_link *link, \ REPEAT(x, SARG, __DL_COM, __SEQ_0_11)) \ { \ u64 args[x]; \ REPEAT(x, COPY, __DL_SEM, __SEQ_0_11); \ - __bpf_trace_run(prog, args); \ + __bpf_trace_run(link, args); \ } \ EXPORT_SYMBOL_GPL(bpf_trace_run##x) BPF_TRACE_DEFN_x(1); @@ -2425,9 +2427,10 @@ BPF_TRACE_DEFN_x(10); BPF_TRACE_DEFN_x(11); BPF_TRACE_DEFN_x(12); -int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog *prog) +int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_raw_tp_link *link) { struct tracepoint *tp = btp->tp; + struct bpf_prog *prog = link->link.prog; /* * check that program doesn't access arguments beyond what's @@ -2439,13 +2442,12 @@ int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog *prog) if (prog->aux->max_tp_access > btp->writable_size) return -EINVAL; - return tracepoint_probe_register_may_exist(tp, (void *)btp->bpf_func, - prog); + return tracepoint_probe_register_may_exist(tp, (void *)btp->bpf_func, link); } -int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_prog *prog) +int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_raw_tp_link *link) { - return tracepoint_probe_unregister(btp->tp, (void *)btp->bpf_func, prog); + return tracepoint_probe_unregister(btp->tp, (void *)btp->bpf_func, link); } int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id, -- cgit v1.2.3 From 68ca5d4eebb8c4de246ee5f634eee26bc689562d Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 19 Mar 2024 16:38:50 -0700 Subject: bpf: support BPF cookie in raw tracepoint (raw_tp, tp_btf) programs Wire up BPF cookie for raw tracepoint programs (both BTF and non-BTF aware variants). This brings them up to part w.r.t. BPF cookie usage with classic tracepoint and fentry/fexit programs. Acked-by: Stanislav Fomichev Acked-by: Eduard Zingerman Signed-off-by: Andrii Nakryiko Message-ID: <20240319233852.1977493-4-andrii@kernel.org> Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 1 + include/uapi/linux/bpf.h | 6 ++++-- kernel/bpf/syscall.c | 13 +++++++++---- kernel/trace/bpf_trace.c | 13 +++++++++++++ tools/include/uapi/linux/bpf.h | 1 + 5 files changed, 28 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 2ea8ce59f582..62762390c93d 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1610,6 +1610,7 @@ struct bpf_tracing_link { struct bpf_raw_tp_link { struct bpf_link link; struct bpf_raw_event_map *btp; + u64 cookie; }; struct bpf_link_primer { diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 3c42b9f1bada..9585f5345353 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1662,8 +1662,10 @@ union bpf_attr { } query; struct { /* anonymous struct used by BPF_RAW_TRACEPOINT_OPEN command */ - __u64 name; - __u32 prog_fd; + __u64 name; + __u32 prog_fd; + __u32 :32; + __aligned_u64 cookie; } raw_tracepoint; struct { /* anonymous struct for BPF_BTF_LOAD */ diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 1cb4c3809af4..e44c276e8617 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -3774,7 +3774,7 @@ static int bpf_perf_link_attach(const union bpf_attr *attr, struct bpf_prog *pro #endif /* CONFIG_PERF_EVENTS */ static int bpf_raw_tp_link_attach(struct bpf_prog *prog, - const char __user *user_tp_name) + const char __user *user_tp_name, u64 cookie) { struct bpf_link_primer link_primer; struct bpf_raw_tp_link *link; @@ -3821,6 +3821,7 @@ static int bpf_raw_tp_link_attach(struct bpf_prog *prog, bpf_link_init(&link->link, BPF_LINK_TYPE_RAW_TRACEPOINT, &bpf_raw_tp_link_lops, prog); link->btp = btp; + link->cookie = cookie; err = bpf_link_prime(&link->link, &link_primer); if (err) { @@ -3841,11 +3842,13 @@ out_put_btp: return err; } -#define BPF_RAW_TRACEPOINT_OPEN_LAST_FIELD raw_tracepoint.prog_fd +#define BPF_RAW_TRACEPOINT_OPEN_LAST_FIELD raw_tracepoint.cookie static int bpf_raw_tracepoint_open(const union bpf_attr *attr) { struct bpf_prog *prog; + void __user *tp_name; + __u64 cookie; int fd; if (CHECK_ATTR(BPF_RAW_TRACEPOINT_OPEN)) @@ -3855,7 +3858,9 @@ static int bpf_raw_tracepoint_open(const union bpf_attr *attr) if (IS_ERR(prog)) return PTR_ERR(prog); - fd = bpf_raw_tp_link_attach(prog, u64_to_user_ptr(attr->raw_tracepoint.name)); + tp_name = u64_to_user_ptr(attr->raw_tracepoint.name); + cookie = attr->raw_tracepoint.cookie; + fd = bpf_raw_tp_link_attach(prog, tp_name, cookie); if (fd < 0) bpf_prog_put(prog); return fd; @@ -5193,7 +5198,7 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr) goto out; } if (prog->expected_attach_type == BPF_TRACE_RAW_TP) - ret = bpf_raw_tp_link_attach(prog, NULL); + ret = bpf_raw_tp_link_attach(prog, NULL, attr->link_create.tracing.cookie); else if (prog->expected_attach_type == BPF_TRACE_ITER) ret = bpf_iter_link_attach(attr, uattr, prog); else if (prog->expected_attach_type == BPF_LSM_CGROUP) diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 17de91ad4a1f..434e3ece6688 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -2004,6 +2004,8 @@ raw_tp_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_stackid_proto_raw_tp; case BPF_FUNC_get_stack: return &bpf_get_stack_proto_raw_tp; + case BPF_FUNC_get_attach_cookie: + return &bpf_get_attach_cookie_proto_tracing; default: return bpf_tracing_func_proto(func_id, prog); } @@ -2066,6 +2068,9 @@ tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_get_func_arg_cnt: return bpf_prog_has_trampoline(prog) ? &bpf_get_func_arg_cnt_proto : NULL; case BPF_FUNC_get_attach_cookie: + if (prog->type == BPF_PROG_TYPE_TRACING && + prog->expected_attach_type == BPF_TRACE_RAW_TP) + return &bpf_get_attach_cookie_proto_tracing; return bpf_prog_has_trampoline(prog) ? &bpf_get_attach_cookie_proto_tracing : NULL; default: fn = raw_tp_prog_func_proto(func_id, prog); @@ -2369,15 +2374,23 @@ static __always_inline void __bpf_trace_run(struct bpf_raw_tp_link *link, u64 *args) { struct bpf_prog *prog = link->link.prog; + struct bpf_run_ctx *old_run_ctx; + struct bpf_trace_run_ctx run_ctx; cant_sleep(); if (unlikely(this_cpu_inc_return(*(prog->active)) != 1)) { bpf_prog_inc_misses_counter(prog); goto out; } + + run_ctx.bpf_cookie = link->cookie; + old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); + rcu_read_lock(); (void) bpf_prog_run(prog, args); rcu_read_unlock(); + + bpf_reset_run_ctx(old_run_ctx); out: this_cpu_dec(*(prog->active)); } diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 3c42b9f1bada..bf80b614c4db 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1664,6 +1664,7 @@ union bpf_attr { struct { /* anonymous struct used by BPF_RAW_TRACEPOINT_OPEN command */ __u64 name; __u32 prog_fd; + __aligned_u64 cookie; } raw_tracepoint; struct { /* anonymous struct for BPF_BTF_LOAD */ -- cgit v1.2.3 From 5a95f39d9b214d59cbe742002767737e03d43844 Mon Sep 17 00:00:00 2001 From: Christian König Date: Tue, 12 Mar 2024 11:37:58 +0100 Subject: drm/ttm: warn when resv objs are mixed in a bulk_move MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The BOs in a bulk move must share all the same reservation object to make sure that we lock the whole bulk during eviction. Actually document and enforce that with a warning. Signed-off-by: Christian König Reviewed-by: Thomas Hellström Link: https://patchwork.freedesktop.org/patch/msgid/20240312105555.3065-1-christian.koenig@amd.com --- drivers/gpu/drm/ttm/ttm_resource.c | 1 + include/drm/ttm/ttm_resource.h | 3 +++ 2 files changed, 4 insertions(+) (limited to 'include') diff --git a/drivers/gpu/drm/ttm/ttm_resource.c b/drivers/gpu/drm/ttm/ttm_resource.c index 65155f2013ca..be8d286513f9 100644 --- a/drivers/gpu/drm/ttm/ttm_resource.c +++ b/drivers/gpu/drm/ttm/ttm_resource.c @@ -105,6 +105,7 @@ static void ttm_lru_bulk_move_add(struct ttm_lru_bulk_move *bulk, pos->first = res; pos->last = res; } else { + WARN_ON(pos->first->bo->base.resv != res->bo->base.resv); ttm_lru_bulk_move_pos_tail(pos, res); } } diff --git a/include/drm/ttm/ttm_resource.h b/include/drm/ttm/ttm_resource.h index 7561023db43d..69769355139f 100644 --- a/include/drm/ttm/ttm_resource.h +++ b/include/drm/ttm/ttm_resource.h @@ -251,6 +251,9 @@ struct ttm_lru_bulk_move_pos { * * Container for the current bulk move state. Should be used with * ttm_lru_bulk_move_init() and ttm_bo_set_bulk_move(). + * All BOs in a bulk_move structure need to share the same reservation object to + * ensure that the bulk as a whole is locked for eviction even if only one BO of + * the bulk is evicted. */ struct ttm_lru_bulk_move { struct ttm_lru_bulk_move_pos pos[TTM_NUM_MEM_TYPES][TTM_MAX_BO_PRIORITY]; -- cgit v1.2.3 From 281a2cc71a1b9fce8fde59b39671ca55c2bf6307 Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Tue, 19 Mar 2024 11:12:48 +0200 Subject: drm/mst: read sideband messaging cap MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Amend drm_dp_read_mst_cap() to return an enum, indicating "SST", "SST with sideband messaging", or "MST". Modify all call sites to take the new return value into account. v2: - Rename enumerators (Ville) Cc: Arun R Murthy Cc: Ville Syrjälä Cc: Karol Herbst Cc: Lyude Paul Cc: Danilo Krummrich Reviewed-by: Ville Syrjälä Acked-by: Maxime Ripard Acked-by: Danilo Krummrich Link: https://patchwork.freedesktop.org/patch/msgid/b32a3704934871a67d06420b760e148b76c5ced8.1710839496.git.jani.nikula@intel.com Signed-off-by: Jani Nikula --- drivers/gpu/drm/display/drm_dp_mst_topology.c | 20 +++++++++++++------- drivers/gpu/drm/i915/display/intel_dp.c | 4 ++-- drivers/gpu/drm/nouveau/nouveau_dp.c | 2 +- include/drm/display/drm_dp_mst_helper.h | 23 ++++++++++++++++++++++- 4 files changed, 38 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/display/drm_dp_mst_topology.c b/drivers/gpu/drm/display/drm_dp_mst_topology.c index 03d528209426..c193be3577f7 100644 --- a/drivers/gpu/drm/display/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/display/drm_dp_mst_topology.c @@ -3608,24 +3608,30 @@ fixed20_12 drm_dp_get_vc_payload_bw(const struct drm_dp_mst_topology_mgr *mgr, EXPORT_SYMBOL(drm_dp_get_vc_payload_bw); /** - * drm_dp_read_mst_cap() - check whether or not a sink supports MST + * drm_dp_read_mst_cap() - Read the sink's MST mode capability * @aux: The DP AUX channel to use * @dpcd: A cached copy of the DPCD capabilities for this sink * - * Returns: %True if the sink supports MST, %false otherwise + * Returns: enum drm_dp_mst_mode to indicate MST mode capability */ -bool drm_dp_read_mst_cap(struct drm_dp_aux *aux, - const u8 dpcd[DP_RECEIVER_CAP_SIZE]) +enum drm_dp_mst_mode drm_dp_read_mst_cap(struct drm_dp_aux *aux, + const u8 dpcd[DP_RECEIVER_CAP_SIZE]) { u8 mstm_cap; if (dpcd[DP_DPCD_REV] < DP_DPCD_REV_12) - return false; + return DRM_DP_SST; if (drm_dp_dpcd_readb(aux, DP_MSTM_CAP, &mstm_cap) != 1) - return false; + return DRM_DP_SST; + + if (mstm_cap & DP_MST_CAP) + return DRM_DP_MST; + + if (mstm_cap & DP_SINGLE_STREAM_SIDEBAND_MSG) + return DRM_DP_SST_SIDEBAND_MSG; - return mstm_cap & DP_MST_CAP; + return DRM_DP_SST; } EXPORT_SYMBOL(drm_dp_read_mst_cap); diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index b6d45ab41ff7..3fb9a5ac1551 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -4046,7 +4046,7 @@ intel_dp_can_mst(struct intel_dp *intel_dp) return i915->display.params.enable_dp_mst && intel_dp_mst_source_support(intel_dp) && - drm_dp_read_mst_cap(&intel_dp->aux, intel_dp->dpcd); + drm_dp_read_mst_cap(&intel_dp->aux, intel_dp->dpcd) == DRM_DP_MST; } static void @@ -4055,7 +4055,7 @@ intel_dp_configure_mst(struct intel_dp *intel_dp) struct drm_i915_private *i915 = dp_to_i915(intel_dp); struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base; - bool sink_can_mst = drm_dp_read_mst_cap(&intel_dp->aux, intel_dp->dpcd); + bool sink_can_mst = drm_dp_read_mst_cap(&intel_dp->aux, intel_dp->dpcd) == DRM_DP_MST; drm_dbg_kms(&i915->drm, "[ENCODER:%d:%s] MST support: port: %s, sink: %s, modparam: %s\n", diff --git a/drivers/gpu/drm/nouveau/nouveau_dp.c b/drivers/gpu/drm/nouveau/nouveau_dp.c index 7de7707ec6a8..fb06ee17d9e5 100644 --- a/drivers/gpu/drm/nouveau/nouveau_dp.c +++ b/drivers/gpu/drm/nouveau/nouveau_dp.c @@ -181,7 +181,7 @@ nouveau_dp_probe_dpcd(struct nouveau_connector *nv_connector, if (nouveau_mst) { mstm = outp->dp.mstm; if (mstm) - mstm->can_mst = drm_dp_read_mst_cap(aux, dpcd); + mstm->can_mst = drm_dp_read_mst_cap(aux, dpcd) == DRM_DP_MST; } if (nouveau_dp_has_sink_count(connector, outp)) { diff --git a/include/drm/display/drm_dp_mst_helper.h b/include/drm/display/drm_dp_mst_helper.h index 9b19d8bd520a..3c9e128c444a 100644 --- a/include/drm/display/drm_dp_mst_helper.h +++ b/include/drm/display/drm_dp_mst_helper.h @@ -818,7 +818,28 @@ int drm_dp_mst_topology_mgr_init(struct drm_dp_mst_topology_mgr *mgr, void drm_dp_mst_topology_mgr_destroy(struct drm_dp_mst_topology_mgr *mgr); -bool drm_dp_read_mst_cap(struct drm_dp_aux *aux, const u8 dpcd[DP_RECEIVER_CAP_SIZE]); +/** + * enum drm_dp_mst_mode - sink's MST mode capability + */ +enum drm_dp_mst_mode { + /** + * @DRM_DP_SST: The sink does not support MST nor single stream sideband + * messaging. + */ + DRM_DP_SST, + /** + * @DRM_DP_MST: Sink supports MST, more than one stream and single + * stream sideband messaging. + */ + DRM_DP_MST, + /** + * @DRM_DP_SST_SIDEBAND_MSG: Sink supports only one stream and single + * stream sideband messaging. + */ + DRM_DP_SST_SIDEBAND_MSG, +}; + +enum drm_dp_mst_mode drm_dp_read_mst_cap(struct drm_dp_aux *aux, const u8 dpcd[DP_RECEIVER_CAP_SIZE]); int drm_dp_mst_topology_mgr_set_mst(struct drm_dp_mst_topology_mgr *mgr, bool mst_state); int drm_dp_mst_hpd_irq_handle_event(struct drm_dp_mst_topology_mgr *mgr, -- cgit v1.2.3 From 8f69cba096b5cfd09be2d06c15d08dbd4a58c9d7 Mon Sep 17 00:00:00 2001 From: "Xin Li (Intel)" Date: Fri, 22 Mar 2024 01:16:16 -0700 Subject: x86: Rename __{start,end}_init_task to __{start,end}_init_stack The stack of a task has been separated from the memory of a task_struct struture for a long time on x86, as a result __{start,end}_init_task no longer mark the start and end of the init_task structure, but its stack only. Rename __{start,end}_init_task to __{start,end}_init_stack. Note other architectures are not affected because __{start,end}_init_task are used on x86 only. Signed-off-by: Xin Li (Intel) Signed-off-by: Ingo Molnar Reviewed-by: Juergen Gross Link: https://lore.kernel.org/r/20240322081616.3346181-1-xin@zytor.com --- arch/x86/kernel/vmlinux.lds.S | 2 +- include/asm-generic/vmlinux.lds.h | 6 +++--- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 91085c3430de..4c04a366f07d 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -173,7 +173,7 @@ SECTIONS INIT_TASK_DATA(THREAD_SIZE) /* equivalent to task_pt_regs(&init_task) */ - __top_init_kernel_stack = __end_init_task - TOP_OF_KERNEL_STACK_PADDING - PTREGS_SIZE; + __top_init_kernel_stack = __end_init_stack - TOP_OF_KERNEL_STACK_PADDING - PTREGS_SIZE; #ifdef CONFIG_X86_32 /* 32 bit has nosave before _edata */ diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index f7749d0f2562..87082434e244 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -399,13 +399,13 @@ #define INIT_TASK_DATA(align) \ . = ALIGN(align); \ - __start_init_task = .; \ + __start_init_stack = .; \ init_thread_union = .; \ init_stack = .; \ KEEP(*(.data..init_task)) \ KEEP(*(.data..init_thread_info)) \ - . = __start_init_task + THREAD_SIZE; \ - __end_init_task = .; + . = __start_init_stack + THREAD_SIZE; \ + __end_init_stack = .; #define JUMP_TABLE_DATA \ . = ALIGN(8); \ -- cgit v1.2.3 From 91a1d97ef482c1e4c9d4c1c656a53b0f6b16d0ed Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 13 Mar 2024 19:01:03 +0100 Subject: jump_label,module: Don't alloc static_key_mod for __ro_after_init keys When a static_key is marked ro_after_init, its state will never change (after init), therefore jump_label_update() will never need to iterate the entries, and thus module load won't actually need to track this -- avoiding the static_key::next write. Therefore, mark these keys such that jump_label_add_module() might recognise them and avoid the modification. Use the special state: 'static_key_linked(key) && !static_key_mod(key)' to denote such keys. jump_label_add_module() does not exist under CONFIG_JUMP_LABEL=n, so the newly-introduced jump_label_init_ro() can be defined as a nop for that configuration. [ mingo: Renamed jump_label_ro() to jump_label_init_ro() ] Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Valentin Schneider Signed-off-by: Ingo Molnar Acked-by: Josh Poimboeuf Link: https://lore.kernel.org/r/20240313180106.2917308-2-vschneid@redhat.com --- include/asm-generic/sections.h | 5 ++++ include/linux/jump_label.h | 3 +++ init/main.c | 1 + kernel/jump_label.c | 53 ++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 62 insertions(+) (limited to 'include') diff --git a/include/asm-generic/sections.h b/include/asm-generic/sections.h index db13bb620f52..c768de6f19a9 100644 --- a/include/asm-generic/sections.h +++ b/include/asm-generic/sections.h @@ -180,6 +180,11 @@ static inline bool is_kernel_rodata(unsigned long addr) addr < (unsigned long)__end_rodata; } +static inline bool is_kernel_ro_after_init(unsigned long addr) +{ + return addr >= (unsigned long)__start_ro_after_init && + addr < (unsigned long)__end_ro_after_init; +} /** * is_kernel_inittext - checks if the pointer address is located in the * .init.text section diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index f0a949b7c973..f5a2727ca4a9 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -216,6 +216,7 @@ extern struct jump_entry __start___jump_table[]; extern struct jump_entry __stop___jump_table[]; extern void jump_label_init(void); +extern void jump_label_init_ro(void); extern void jump_label_lock(void); extern void jump_label_unlock(void); extern void arch_jump_label_transform(struct jump_entry *entry, @@ -265,6 +266,8 @@ static __always_inline void jump_label_init(void) static_key_initialized = true; } +static __always_inline void jump_label_init_ro(void) { } + static __always_inline bool static_key_false(struct static_key *key) { if (unlikely_notrace(static_key_count(key) > 0)) diff --git a/init/main.c b/init/main.c index 2ca52474d0c3..6c3f251d6ef8 100644 --- a/init/main.c +++ b/init/main.c @@ -1408,6 +1408,7 @@ static void mark_readonly(void) * insecure pages which are W+X. */ flush_module_init_free_work(); + jump_label_init_ro(); mark_rodata_ro(); debug_checkwx(); rodata_test(); diff --git a/kernel/jump_label.c b/kernel/jump_label.c index d9c822bbffb8..3218fa5688b9 100644 --- a/kernel/jump_label.c +++ b/kernel/jump_label.c @@ -530,6 +530,45 @@ void __init jump_label_init(void) cpus_read_unlock(); } +static inline bool static_key_sealed(struct static_key *key) +{ + return (key->type & JUMP_TYPE_LINKED) && !(key->type & ~JUMP_TYPE_MASK); +} + +static inline void static_key_seal(struct static_key *key) +{ + unsigned long type = key->type & JUMP_TYPE_TRUE; + key->type = JUMP_TYPE_LINKED | type; +} + +void jump_label_init_ro(void) +{ + struct jump_entry *iter_start = __start___jump_table; + struct jump_entry *iter_stop = __stop___jump_table; + struct jump_entry *iter; + + if (WARN_ON_ONCE(!static_key_initialized)) + return; + + cpus_read_lock(); + jump_label_lock(); + + for (iter = iter_start; iter < iter_stop; iter++) { + struct static_key *iterk = jump_entry_key(iter); + + if (!is_kernel_ro_after_init((unsigned long)iterk)) + continue; + + if (static_key_sealed(iterk)) + continue; + + static_key_seal(iterk); + } + + jump_label_unlock(); + cpus_read_unlock(); +} + #ifdef CONFIG_MODULES enum jump_label_type jump_label_init_type(struct jump_entry *entry) @@ -650,6 +689,15 @@ static int jump_label_add_module(struct module *mod) static_key_set_entries(key, iter); continue; } + + /* + * If the key was sealed at init, then there's no need to keep a + * reference to its module entries - just patch them now and be + * done with it. + */ + if (static_key_sealed(key)) + goto do_poke; + jlm = kzalloc(sizeof(struct static_key_mod), GFP_KERNEL); if (!jlm) return -ENOMEM; @@ -675,6 +723,7 @@ static int jump_label_add_module(struct module *mod) static_key_set_linked(key); /* Only update if we've changed from our initial state */ +do_poke: if (jump_label_type(iter) != jump_label_init_type(iter)) __jump_label_update(key, iter, iter_stop, true); } @@ -699,6 +748,10 @@ static void jump_label_del_module(struct module *mod) if (within_module((unsigned long)key, mod)) continue; + /* No @jlm allocated because key was sealed at init. */ + if (static_key_sealed(key)) + continue; + /* No memory during module load */ if (WARN_ON(!static_key_linked(key))) continue; -- cgit v1.2.3 From 5edeb7d312628961046eec9b26a7e72f44baf846 Mon Sep 17 00:00:00 2001 From: Joy Zou Date: Mon, 18 Mar 2024 17:56:32 +0800 Subject: regulator: pca9450: add pca9451a support Adding support for new pmic pca9451a. Signed-off-by: Joy Zou Link: https://msgid.link/r/20240318095633.4079027-3-joy.zou@nxp.com Signed-off-by: Mark Brown --- drivers/regulator/pca9450-regulator.c | 194 +++++++++++++++++++++++++++++++++- include/linux/regulator/pca9450.h | 1 + 2 files changed, 193 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/regulator/pca9450-regulator.c b/drivers/regulator/pca9450-regulator.c index 2ab365d2749f..242ff25f5b83 100644 --- a/drivers/regulator/pca9450-regulator.c +++ b/drivers/regulator/pca9450-regulator.c @@ -106,6 +106,14 @@ static const struct linear_range pca9450_dvs_buck_volts[] = { REGULATOR_LINEAR_RANGE(600000, 0x00, 0x7F, 12500), }; +/* + * BUCK1/3 + * 0.65 to 2.2375V (12.5mV step) + */ +static const struct linear_range pca9451a_dvs_buck_volts[] = { + REGULATOR_LINEAR_RANGE(650000, 0x00, 0x7F, 12500), +}; + /* * BUCK4/5/6 * 0.6V to 3.4V (25mV step) @@ -662,6 +670,178 @@ static const struct pca9450_regulator_desc pca9450bc_regulators[] = { }, }; +static const struct pca9450_regulator_desc pca9451a_regulators[] = { + { + .desc = { + .name = "buck1", + .of_match = of_match_ptr("BUCK1"), + .regulators_node = of_match_ptr("regulators"), + .id = PCA9450_BUCK1, + .ops = &pca9450_dvs_buck_regulator_ops, + .type = REGULATOR_VOLTAGE, + .n_voltages = PCA9450_BUCK1_VOLTAGE_NUM, + .linear_ranges = pca9451a_dvs_buck_volts, + .n_linear_ranges = ARRAY_SIZE(pca9451a_dvs_buck_volts), + .vsel_reg = PCA9450_REG_BUCK1OUT_DVS0, + .vsel_mask = BUCK1OUT_DVS0_MASK, + .enable_reg = PCA9450_REG_BUCK1CTRL, + .enable_mask = BUCK1_ENMODE_MASK, + .enable_val = BUCK_ENMODE_ONREQ, + .ramp_mask = BUCK1_RAMP_MASK, + .ramp_delay_table = pca9450_dvs_buck_ramp_table, + .n_ramp_values = ARRAY_SIZE(pca9450_dvs_buck_ramp_table), + .owner = THIS_MODULE, + .of_parse_cb = pca9450_set_dvs_levels, + }, + .dvs = { + .run_reg = PCA9450_REG_BUCK1OUT_DVS0, + .run_mask = BUCK1OUT_DVS0_MASK, + .standby_reg = PCA9450_REG_BUCK1OUT_DVS1, + .standby_mask = BUCK1OUT_DVS1_MASK, + }, + }, + { + .desc = { + .name = "buck2", + .of_match = of_match_ptr("BUCK2"), + .regulators_node = of_match_ptr("regulators"), + .id = PCA9450_BUCK2, + .ops = &pca9450_dvs_buck_regulator_ops, + .type = REGULATOR_VOLTAGE, + .n_voltages = PCA9450_BUCK2_VOLTAGE_NUM, + .linear_ranges = pca9450_dvs_buck_volts, + .n_linear_ranges = ARRAY_SIZE(pca9450_dvs_buck_volts), + .vsel_reg = PCA9450_REG_BUCK2OUT_DVS0, + .vsel_mask = BUCK2OUT_DVS0_MASK, + .enable_reg = PCA9450_REG_BUCK2CTRL, + .enable_mask = BUCK2_ENMODE_MASK, + .enable_val = BUCK_ENMODE_ONREQ_STBYREQ, + .ramp_mask = BUCK2_RAMP_MASK, + .ramp_delay_table = pca9450_dvs_buck_ramp_table, + .n_ramp_values = ARRAY_SIZE(pca9450_dvs_buck_ramp_table), + .owner = THIS_MODULE, + .of_parse_cb = pca9450_set_dvs_levels, + }, + .dvs = { + .run_reg = PCA9450_REG_BUCK2OUT_DVS0, + .run_mask = BUCK2OUT_DVS0_MASK, + .standby_reg = PCA9450_REG_BUCK2OUT_DVS1, + .standby_mask = BUCK2OUT_DVS1_MASK, + }, + }, + { + .desc = { + .name = "buck4", + .of_match = of_match_ptr("BUCK4"), + .regulators_node = of_match_ptr("regulators"), + .id = PCA9450_BUCK4, + .ops = &pca9450_buck_regulator_ops, + .type = REGULATOR_VOLTAGE, + .n_voltages = PCA9450_BUCK4_VOLTAGE_NUM, + .linear_ranges = pca9450_buck_volts, + .n_linear_ranges = ARRAY_SIZE(pca9450_buck_volts), + .vsel_reg = PCA9450_REG_BUCK4OUT, + .vsel_mask = BUCK4OUT_MASK, + .enable_reg = PCA9450_REG_BUCK4CTRL, + .enable_mask = BUCK4_ENMODE_MASK, + .enable_val = BUCK_ENMODE_ONREQ, + .owner = THIS_MODULE, + }, + }, + { + .desc = { + .name = "buck5", + .of_match = of_match_ptr("BUCK5"), + .regulators_node = of_match_ptr("regulators"), + .id = PCA9450_BUCK5, + .ops = &pca9450_buck_regulator_ops, + .type = REGULATOR_VOLTAGE, + .n_voltages = PCA9450_BUCK5_VOLTAGE_NUM, + .linear_ranges = pca9450_buck_volts, + .n_linear_ranges = ARRAY_SIZE(pca9450_buck_volts), + .vsel_reg = PCA9450_REG_BUCK5OUT, + .vsel_mask = BUCK5OUT_MASK, + .enable_reg = PCA9450_REG_BUCK5CTRL, + .enable_mask = BUCK5_ENMODE_MASK, + .enable_val = BUCK_ENMODE_ONREQ, + .owner = THIS_MODULE, + }, + }, + { + .desc = { + .name = "buck6", + .of_match = of_match_ptr("BUCK6"), + .regulators_node = of_match_ptr("regulators"), + .id = PCA9450_BUCK6, + .ops = &pca9450_buck_regulator_ops, + .type = REGULATOR_VOLTAGE, + .n_voltages = PCA9450_BUCK6_VOLTAGE_NUM, + .linear_ranges = pca9450_buck_volts, + .n_linear_ranges = ARRAY_SIZE(pca9450_buck_volts), + .vsel_reg = PCA9450_REG_BUCK6OUT, + .vsel_mask = BUCK6OUT_MASK, + .enable_reg = PCA9450_REG_BUCK6CTRL, + .enable_mask = BUCK6_ENMODE_MASK, + .enable_val = BUCK_ENMODE_ONREQ, + .owner = THIS_MODULE, + }, + }, + { + .desc = { + .name = "ldo1", + .of_match = of_match_ptr("LDO1"), + .regulators_node = of_match_ptr("regulators"), + .id = PCA9450_LDO1, + .ops = &pca9450_ldo_regulator_ops, + .type = REGULATOR_VOLTAGE, + .n_voltages = PCA9450_LDO1_VOLTAGE_NUM, + .linear_ranges = pca9450_ldo1_volts, + .n_linear_ranges = ARRAY_SIZE(pca9450_ldo1_volts), + .vsel_reg = PCA9450_REG_LDO1CTRL, + .vsel_mask = LDO1OUT_MASK, + .enable_reg = PCA9450_REG_LDO1CTRL, + .enable_mask = LDO1_EN_MASK, + .owner = THIS_MODULE, + }, + }, + { + .desc = { + .name = "ldo4", + .of_match = of_match_ptr("LDO4"), + .regulators_node = of_match_ptr("regulators"), + .id = PCA9450_LDO4, + .ops = &pca9450_ldo_regulator_ops, + .type = REGULATOR_VOLTAGE, + .n_voltages = PCA9450_LDO4_VOLTAGE_NUM, + .linear_ranges = pca9450_ldo34_volts, + .n_linear_ranges = ARRAY_SIZE(pca9450_ldo34_volts), + .vsel_reg = PCA9450_REG_LDO4CTRL, + .vsel_mask = LDO4OUT_MASK, + .enable_reg = PCA9450_REG_LDO4CTRL, + .enable_mask = LDO4_EN_MASK, + .owner = THIS_MODULE, + }, + }, + { + .desc = { + .name = "ldo5", + .of_match = of_match_ptr("LDO5"), + .regulators_node = of_match_ptr("regulators"), + .id = PCA9450_LDO5, + .ops = &pca9450_ldo_regulator_ops, + .type = REGULATOR_VOLTAGE, + .n_voltages = PCA9450_LDO5_VOLTAGE_NUM, + .linear_ranges = pca9450_ldo5_volts, + .n_linear_ranges = ARRAY_SIZE(pca9450_ldo5_volts), + .vsel_reg = PCA9450_REG_LDO5CTRL_H, + .vsel_mask = LDO5HOUT_MASK, + .enable_reg = PCA9450_REG_LDO5CTRL_H, + .enable_mask = LDO5H_EN_MASK, + .owner = THIS_MODULE, + }, + }, +}; + static irqreturn_t pca9450_irq_handler(int irq, void *data) { struct pca9450 *pca9450 = data; @@ -729,6 +909,10 @@ static int pca9450_i2c_probe(struct i2c_client *i2c) regulator_desc = pca9450bc_regulators; pca9450->rcnt = ARRAY_SIZE(pca9450bc_regulators); break; + case PCA9450_TYPE_PCA9451A: + regulator_desc = pca9451a_regulators; + pca9450->rcnt = ARRAY_SIZE(pca9451a_regulators); + break; default: dev_err(&i2c->dev, "Unknown device type"); return -EINVAL; @@ -755,7 +939,8 @@ static int pca9450_i2c_probe(struct i2c_client *i2c) /* Check your board and dts for match the right pmic */ if (((device_id >> 4) != 0x1 && type == PCA9450_TYPE_PCA9450A) || - ((device_id >> 4) != 0x3 && type == PCA9450_TYPE_PCA9450BC)) { + ((device_id >> 4) != 0x3 && type == PCA9450_TYPE_PCA9450BC) || + ((device_id >> 4) != 0x9 && type == PCA9450_TYPE_PCA9451A)) { dev_err(&i2c->dev, "Device id(%x) mismatched\n", device_id >> 4); return -EINVAL; @@ -846,7 +1031,8 @@ static int pca9450_i2c_probe(struct i2c_client *i2c) } dev_info(&i2c->dev, "%s probed.\n", - type == PCA9450_TYPE_PCA9450A ? "pca9450a" : "pca9450bc"); + type == PCA9450_TYPE_PCA9450A ? "pca9450a" : + (type == PCA9450_TYPE_PCA9451A ? "pca9451a" : "pca9450bc")); return 0; } @@ -864,6 +1050,10 @@ static const struct of_device_id pca9450_of_match[] = { .compatible = "nxp,pca9450c", .data = (void *)PCA9450_TYPE_PCA9450BC, }, + { + .compatible = "nxp,pca9451a", + .data = (void *)PCA9450_TYPE_PCA9451A, + }, { } }; MODULE_DEVICE_TABLE(of, pca9450_of_match); diff --git a/include/linux/regulator/pca9450.h b/include/linux/regulator/pca9450.h index 505c908dbb81..243633c8dceb 100644 --- a/include/linux/regulator/pca9450.h +++ b/include/linux/regulator/pca9450.h @@ -9,6 +9,7 @@ enum pca9450_chip_type { PCA9450_TYPE_PCA9450A = 0, PCA9450_TYPE_PCA9450BC, + PCA9450_TYPE_PCA9451A, PCA9450_TYPE_AMOUNT, }; -- cgit v1.2.3 From d650d1c46d8471bf8ebf556629ac13077f13e647 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 8 Mar 2024 18:27:46 +0200 Subject: spi: xilinx: Fix kernel documentation in the xilinx_spi.h While updating the data structure layout the kernel documentation became outdated. Synchronize kernel documentation with the actual data structure layout. Fixes: 1dd46599f83a ("spi: xilinx: add force_irq for QSPI mode") Fixes: 082339bc63cc ("spi: spi-xilinx: Add run run-time endian detection") Reviewed-by: Michal Simek Signed-off-by: Andy Shevchenko Link: https://msgid.link/r/20240308162920.46816-2-andriy.shevchenko@linux.intel.com Signed-off-by: Mark Brown --- include/linux/spi/xilinx_spi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/spi/xilinx_spi.h b/include/linux/spi/xilinx_spi.h index 3934ce789d87..fd6add419e94 100644 --- a/include/linux/spi/xilinx_spi.h +++ b/include/linux/spi/xilinx_spi.h @@ -5,10 +5,10 @@ /** * struct xspi_platform_data - Platform data of the Xilinx SPI driver * @num_chipselect: Number of chip select by the IP. - * @little_endian: If registers should be accessed little endian or not. * @bits_per_word: Number of bits per word. * @devices: Devices to add when the driver is probed. * @num_devices: Number of devices in the devices array. + * @force_irq: If set, forces QSPI transaction requirements. */ struct xspi_platform_data { u16 num_chipselect; -- cgit v1.2.3 From 8f40647d87610ecff6637d673024fe7bd045c913 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 8 Mar 2024 18:27:47 +0200 Subject: spi: xilinx: Add necessary inclusion and forward declaration xilinx_spi.h is mnissing inclusion and forward declaration, add them. Signed-off-by: Andy Shevchenko Acked-by: Michal Simek Link: https://msgid.link/r/20240308162920.46816-3-andriy.shevchenko@linux.intel.com Signed-off-by: Mark Brown --- include/linux/spi/xilinx_spi.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/spi/xilinx_spi.h b/include/linux/spi/xilinx_spi.h index fd6add419e94..4ba8f53ce570 100644 --- a/include/linux/spi/xilinx_spi.h +++ b/include/linux/spi/xilinx_spi.h @@ -2,6 +2,10 @@ #ifndef __LINUX_SPI_XILINX_SPI_H #define __LINUX_SPI_XILINX_SPI_H +#include + +struct spi_board_info; + /** * struct xspi_platform_data - Platform data of the Xilinx SPI driver * @num_chipselect: Number of chip select by the IP. -- cgit v1.2.3 From a39111b1cf0864b1782f30f9a1fa65260d057327 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 8 Mar 2024 18:27:48 +0200 Subject: spi: xilinx: Make num_chipselect 8-bit in the struct xspi_platform_data There is no use for whole 16-bit for the number of chip select pins. Drop it to 8 bits and reshuffle the data structure layout to avoid unnecessary paddings. Signed-off-by: Andy Shevchenko Reviewed-by: Michal Simek Link: https://msgid.link/r/20240308162920.46816-4-andriy.shevchenko@linux.intel.com Signed-off-by: Mark Brown --- include/linux/spi/xilinx_spi.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/spi/xilinx_spi.h b/include/linux/spi/xilinx_spi.h index 4ba8f53ce570..1b8d984668b6 100644 --- a/include/linux/spi/xilinx_spi.h +++ b/include/linux/spi/xilinx_spi.h @@ -8,17 +8,17 @@ struct spi_board_info; /** * struct xspi_platform_data - Platform data of the Xilinx SPI driver - * @num_chipselect: Number of chip select by the IP. - * @bits_per_word: Number of bits per word. * @devices: Devices to add when the driver is probed. * @num_devices: Number of devices in the devices array. + * @num_chipselect: Number of chip select by the IP. + * @bits_per_word: Number of bits per word. * @force_irq: If set, forces QSPI transaction requirements. */ struct xspi_platform_data { - u16 num_chipselect; - u8 bits_per_word; struct spi_board_info *devices; u8 num_devices; + u8 num_chipselect; + u8 bits_per_word; bool force_irq; }; -- cgit v1.2.3 From 7fd54c205f104317b853fc417ac7e9d0b9531ddb Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 7 Mar 2024 21:47:45 +0200 Subject: spi: pxa2xx: Kill pxa2xx_set_spi_info() There is the only one user of the pxa2xx_set_spi_info(). Unexport it and inline to the actual user. Signed-off-by: Andy Shevchenko Acked-by: Arnd Bergmann Link: https://msgid.link/r/20240307195056.4059864-2-andriy.shevchenko@linux.intel.com Signed-off-by: Mark Brown --- arch/arm/mach-pxa/devices.c | 18 ------------------ arch/arm/mach-pxa/spitz.c | 14 +++++++++++++- include/linux/spi/pxa2xx_spi.h | 8 -------- 3 files changed, 13 insertions(+), 27 deletions(-) (limited to 'include') diff --git a/arch/arm/mach-pxa/devices.c b/arch/arm/mach-pxa/devices.c index 661b3fc43275..1e4cd502340e 100644 --- a/arch/arm/mach-pxa/devices.c +++ b/arch/arm/mach-pxa/devices.c @@ -7,7 +7,6 @@ #include #include #include -#include #include #include @@ -665,23 +664,6 @@ struct platform_device pxa27x_device_gpio = { .resource = pxa_resource_gpio, }; -/* pxa2xx-spi platform-device ID equals respective SSP platform-device ID + 1. - * See comment in arch/arm/mach-pxa/ssp.c::ssp_probe() */ -void __init pxa2xx_set_spi_info(unsigned id, struct pxa2xx_spi_controller *info) -{ - struct platform_device *pd; - - pd = platform_device_alloc("pxa2xx-spi", id); - if (pd == NULL) { - printk(KERN_ERR "pxa2xx-spi: failed to allocate device id %d\n", - id); - return; - } - - pd->dev.platform_data = info; - platform_device_add(pd); -} - static struct resource pxa_dma_resource[] = { [0] = { .start = 0x40000000, diff --git a/arch/arm/mach-pxa/spitz.c b/arch/arm/mach-pxa/spitz.c index cc691b199429..318402ad685e 100644 --- a/arch/arm/mach-pxa/spitz.c +++ b/arch/arm/mach-pxa/spitz.c @@ -585,6 +585,9 @@ static struct gpiod_lookup_table spitz_spi_gpio_table = { static void __init spitz_spi_init(void) { + struct platform_device *pd; + int id = 2; + if (machine_is_akita()) gpiod_add_lookup_table(&akita_lcdcon_gpio_table); else @@ -592,7 +595,16 @@ static void __init spitz_spi_init(void) gpiod_add_lookup_table(&spitz_ads7846_gpio_table); gpiod_add_lookup_table(&spitz_spi_gpio_table); - pxa2xx_set_spi_info(2, &spitz_spi_info); + + /* pxa2xx-spi platform-device ID equals respective SSP platform-device ID + 1 */ + pd = platform_device_alloc("pxa2xx-spi", id); + if (pd == NULL) { + pr_err("pxa2xx-spi: failed to allocate device id %d\n", id); + } else { + pd->dev.platform_data = &spitz_spi_info; + platform_device_add(pd); + } + spi_register_board_info(ARRAY_AND_SIZE(spitz_spi_devices)); } #else diff --git a/include/linux/spi/pxa2xx_spi.h b/include/linux/spi/pxa2xx_spi.h index ca2cd4e30ead..56aba2f737b1 100644 --- a/include/linux/spi/pxa2xx_spi.h +++ b/include/linux/spi/pxa2xx_spi.h @@ -45,12 +45,4 @@ struct pxa2xx_spi_chip { u32 timeout; }; -#if defined(CONFIG_ARCH_PXA) || defined(CONFIG_ARCH_MMP) - -#include - -extern void pxa2xx_set_spi_info(unsigned id, struct pxa2xx_spi_controller *info); - -#endif - #endif /* __LINUX_SPI_PXA2XX_SPI_H */ -- cgit v1.2.3 From e3f209e269d32ebc0ba7f497f5d2af21ed4f0dd0 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 7 Mar 2024 21:47:46 +0200 Subject: spi: pxa2xx: Make num_chipselect 8-bit in the struct pxa2xx_spi_controller There is no use for whole 16-bit for the number of chip select pins. Drop it to 8 bits. Acked-by: Arnd Bergmann Signed-off-by: Andy Shevchenko Link: https://msgid.link/r/20240307195056.4059864-3-andriy.shevchenko@linux.intel.com Signed-off-by: Mark Brown --- Documentation/spi/pxa2xx.rst | 2 +- include/linux/spi/pxa2xx_spi.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/Documentation/spi/pxa2xx.rst b/Documentation/spi/pxa2xx.rst index 19479b801826..0997d8eaf190 100644 --- a/Documentation/spi/pxa2xx.rst +++ b/Documentation/spi/pxa2xx.rst @@ -24,7 +24,7 @@ arch/.../mach-*/board-*.c as a "platform device". The host controller configurat is passed to the driver via a table found in include/linux/spi/pxa2xx_spi.h:: struct pxa2xx_spi_controller { - u16 num_chipselect; + u8 num_chipselect; u8 enable_dma; ... }; diff --git a/include/linux/spi/pxa2xx_spi.h b/include/linux/spi/pxa2xx_spi.h index 56aba2f737b1..e5a4a045fb67 100644 --- a/include/linux/spi/pxa2xx_spi.h +++ b/include/linux/spi/pxa2xx_spi.h @@ -17,7 +17,7 @@ struct dma_chan; * (resides in device.platform_data). */ struct pxa2xx_spi_controller { - u16 num_chipselect; + u8 num_chipselect; u8 enable_dma; u8 dma_burst_size; bool is_target; -- cgit v1.2.3 From cee28113db17f0de58df0eaea4e2756c404ee01f Mon Sep 17 00:00:00 2001 From: Tomi Valkeinen Date: Tue, 19 Mar 2024 10:22:36 +0200 Subject: ASoC: dmaengine_pcm: Allow passing component name via config At the moment we cannot instantiate two dmaengine_pcms with the same parent device, as the components will be named the same, leading to conflicts. Add 'name' field to the snd_dmaengine_pcm_config, and use that (if defined) as the component name instead of deriving the component name from the device. Signed-off-by: Tomi Valkeinen Link: https://msgid.link/r/20240319-xilinx-dp-audio-v2-1-92d6d3a7ca7e@ideasonboard.com Signed-off-by: Mark Brown --- include/sound/dmaengine_pcm.h | 2 ++ sound/soc/soc-core.c | 8 +++++--- sound/soc/soc-generic-dmaengine-pcm.c | 3 +++ 3 files changed, 10 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/sound/dmaengine_pcm.h b/include/sound/dmaengine_pcm.h index d70c55f17df7..c11aaf8079fb 100644 --- a/include/sound/dmaengine_pcm.h +++ b/include/sound/dmaengine_pcm.h @@ -118,6 +118,7 @@ int snd_dmaengine_pcm_refine_runtime_hwparams( * which do not use devicetree. * @process: Callback used to apply processing on samples transferred from/to * user space. + * @name: Component name. If null, dev_name will be used. * @compat_filter_fn: Will be used as the filter function when requesting a * channel for platforms which do not use devicetree. The filter parameter * will be the DAI's DMA data. @@ -143,6 +144,7 @@ struct snd_dmaengine_pcm_config { int (*process)(struct snd_pcm_substream *substream, int channel, unsigned long hwoff, unsigned long bytes); + const char *name; dma_filter_fn compat_filter_fn; struct device *dma_dev; const char *chan_names[SNDRV_PCM_STREAM_LAST + 1]; diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c index 2ec13d1634b6..3ab6626ad680 100644 --- a/sound/soc/soc-core.c +++ b/sound/soc/soc-core.c @@ -2796,10 +2796,12 @@ int snd_soc_component_initialize(struct snd_soc_component *component, INIT_LIST_HEAD(&component->list); mutex_init(&component->io_mutex); - component->name = fmt_single_name(dev, &component->id); if (!component->name) { - dev_err(dev, "ASoC: Failed to allocate name\n"); - return -ENOMEM; + component->name = fmt_single_name(dev, &component->id); + if (!component->name) { + dev_err(dev, "ASoC: Failed to allocate name\n"); + return -ENOMEM; + } } component->dev = dev; diff --git a/sound/soc/soc-generic-dmaengine-pcm.c b/sound/soc/soc-generic-dmaengine-pcm.c index 092ca09f3631..83db1a83d8ba 100644 --- a/sound/soc/soc-generic-dmaengine-pcm.c +++ b/sound/soc/soc-generic-dmaengine-pcm.c @@ -441,6 +441,9 @@ int snd_dmaengine_pcm_register(struct device *dev, pcm->config = config; pcm->flags = flags; + if (config->name) + pcm->component.name = config->name; + ret = dmaengine_pcm_request_chan_of(pcm, dev, config); if (ret) goto err_free_dma; -- cgit v1.2.3 From ada5caa4e081b067736e872f2701e1c677290f22 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Mon, 25 Mar 2024 02:57:29 +0000 Subject: fbdev: omap2: replace of_graph_get_next_endpoint() From DT point of view, in general, drivers should be asking for a specific port number because their function is fixed in the binding. of_graph_get_next_endpoint() doesn't match to this concept. Simply replace - of_graph_get_next_endpoint(xxx, NULL); + of_graph_get_endpoint_by_regs(xxx, 0, -1); Link: https://lore.kernel.org/r/20240202174941.GA310089-robh@kernel.org Signed-off-by: Kuninori Morimoto Reviewed-by: Laurent Pinchart Signed-off-by: Helge Deller --- drivers/video/fbdev/omap2/omapfb/dss/dsi.c | 3 ++- drivers/video/fbdev/omap2/omapfb/dss/dss-of.c | 20 +------------------- drivers/video/fbdev/omap2/omapfb/dss/hdmi4.c | 3 ++- drivers/video/fbdev/omap2/omapfb/dss/hdmi5.c | 3 ++- drivers/video/fbdev/omap2/omapfb/dss/venc.c | 3 ++- drivers/video/fbdev/pxafb.c | 2 +- include/video/omapfb_dss.h | 3 --- 7 files changed, 10 insertions(+), 27 deletions(-) (limited to 'include') diff --git a/drivers/video/fbdev/omap2/omapfb/dss/dsi.c b/drivers/video/fbdev/omap2/omapfb/dss/dsi.c index b7eb17a16ec4..1f13bcf73da5 100644 --- a/drivers/video/fbdev/omap2/omapfb/dss/dsi.c +++ b/drivers/video/fbdev/omap2/omapfb/dss/dsi.c @@ -28,6 +28,7 @@ #include #include #include +#include #include #include @@ -5079,7 +5080,7 @@ static int dsi_probe_of(struct platform_device *pdev) struct device_node *ep; struct omap_dsi_pin_config pin_cfg; - ep = omapdss_of_get_first_endpoint(node); + ep = of_graph_get_endpoint_by_regs(node, 0, -1); if (!ep) return 0; diff --git a/drivers/video/fbdev/omap2/omapfb/dss/dss-of.c b/drivers/video/fbdev/omap2/omapfb/dss/dss-of.c index 0282d4eef139..14965a3fd05b 100644 --- a/drivers/video/fbdev/omap2/omapfb/dss/dss-of.c +++ b/drivers/video/fbdev/omap2/omapfb/dss/dss-of.c @@ -130,24 +130,6 @@ static struct device_node *omapdss_of_get_remote_port(const struct device_node * return np; } -struct device_node * -omapdss_of_get_first_endpoint(const struct device_node *parent) -{ - struct device_node *port, *ep; - - port = omapdss_of_get_next_port(parent, NULL); - - if (!port) - return NULL; - - ep = omapdss_of_get_next_endpoint(port, NULL); - - of_node_put(port); - - return ep; -} -EXPORT_SYMBOL_GPL(omapdss_of_get_first_endpoint); - struct omap_dss_device * omapdss_of_find_source_for_first_ep(struct device_node *node) { @@ -155,7 +137,7 @@ omapdss_of_find_source_for_first_ep(struct device_node *node) struct device_node *src_port; struct omap_dss_device *src; - ep = omapdss_of_get_first_endpoint(node); + ep = of_graph_get_endpoint_by_regs(node, 0, -1); if (!ep) return ERR_PTR(-EINVAL); diff --git a/drivers/video/fbdev/omap2/omapfb/dss/hdmi4.c b/drivers/video/fbdev/omap2/omapfb/dss/hdmi4.c index f05b4e35a842..8f407ec134dc 100644 --- a/drivers/video/fbdev/omap2/omapfb/dss/hdmi4.c +++ b/drivers/video/fbdev/omap2/omapfb/dss/hdmi4.c @@ -20,6 +20,7 @@ #include #include #include +#include #include #include #include