From 7b812171257d4b8d9ef69321134c72b647e1ce9c Mon Sep 17 00:00:00 2001 From: Desmond Cheong Zhi Xi Date: Fri, 13 Aug 2021 16:54:50 +0800 Subject: drm: unexport drm_ioctl_permit Since the last user of drm_ioctl_permit was removed, and it's now only used in drm_ioctl.c, unexport the symbol. Reported-by: Daniel Vetter Signed-off-by: Desmond Cheong Zhi Xi Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20210813085450.32494-3-desmondcheongzx@gmail.com --- include/drm/drm_ioctl.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/drm/drm_ioctl.h b/include/drm/drm_ioctl.h index afb27cb6a7bd..6ed61c371f6c 100644 --- a/include/drm/drm_ioctl.h +++ b/include/drm/drm_ioctl.h @@ -167,7 +167,6 @@ struct drm_ioctl_desc { .name = #ioctl \ } -int drm_ioctl_permit(u32 flags, struct drm_file *file_priv); long drm_ioctl(struct file *filp, unsigned int cmd, unsigned long arg); long drm_ioctl_kernel(struct file *, drm_ioctl_t, void *, u32); #ifdef CONFIG_COMPAT -- cgit v1.2.3 From 32a4eb04d59ae8d5bb5baa5a8528e31094ae8e84 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Thu, 10 Jun 2021 13:12:34 +0200 Subject: drm/fourcc: Add macros to determine the modifier vendor When working with framebuffer modifiers, it can be useful to extract the vendor identifier or check a modifier against a given vendor identifier. Add one macro that extracts the vendor identifier and a helper to check a modifier against a given vendor identifier. Reviewed-by: Daniel Vetter Acked-by: Daniel Stone Signed-off-by: Thierry Reding Link: https://patchwork.freedesktop.org/patch/msgid/20210610111236.3814211-1-thierry.reding@gmail.com --- include/uapi/drm/drm_fourcc.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h index 9f4bb4a6f358..45a914850be0 100644 --- a/include/uapi/drm/drm_fourcc.h +++ b/include/uapi/drm/drm_fourcc.h @@ -373,6 +373,12 @@ extern "C" { #define DRM_FORMAT_RESERVED ((1ULL << 56) - 1) +#define fourcc_mod_get_vendor(modifier) \ + (((modifier) >> 56) & 0xff) + +#define fourcc_mod_is_vendor(modifier, vendor) \ + (fourcc_mod_get_vendor(modifier) == DRM_FORMAT_MOD_VENDOR_## vendor) + #define fourcc_mod_code(vendor, val) \ ((((__u64)DRM_FORMAT_MOD_VENDOR_## vendor) << 56) | ((val) & 0x00ffffffffffffffULL)) -- cgit v1.2.3 From 992c238188a83befa0094a8c00bfead31aa302ed Mon Sep 17 00:00:00 2001 From: Christian König Date: Wed, 28 Jul 2021 19:51:50 +0200 Subject: dma-buf: nuke seqno-fence MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Entirely unused. Signed-off-by: Christian König Acked-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20210729070330.41443-1-christian.koenig@amd.com --- drivers/dma-buf/Makefile | 2 +- drivers/dma-buf/seqno-fence.c | 71 --------------------------- include/linux/seqno-fence.h | 109 ------------------------------------------ 3 files changed, 1 insertion(+), 181 deletions(-) delete mode 100644 drivers/dma-buf/seqno-fence.c delete mode 100644 include/linux/seqno-fence.h (limited to 'include') diff --git a/drivers/dma-buf/Makefile b/drivers/dma-buf/Makefile index 40d81f23cacf..1ef021273a06 100644 --- a/drivers/dma-buf/Makefile +++ b/drivers/dma-buf/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-only obj-y := dma-buf.o dma-fence.o dma-fence-array.o dma-fence-chain.o \ - dma-resv.o seqno-fence.o + dma-resv.o obj-$(CONFIG_DMABUF_HEAPS) += dma-heap.o obj-$(CONFIG_DMABUF_HEAPS) += heaps/ obj-$(CONFIG_SYNC_FILE) += sync_file.o diff --git a/drivers/dma-buf/seqno-fence.c b/drivers/dma-buf/seqno-fence.c deleted file mode 100644 index bfe14e94c488..000000000000 --- a/drivers/dma-buf/seqno-fence.c +++ /dev/null @@ -1,71 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * seqno-fence, using a dma-buf to synchronize fencing - * - * Copyright (C) 2012 Texas Instruments - * Copyright (C) 2012-2014 Canonical Ltd - * Authors: - * Rob Clark - * Maarten Lankhorst - */ - -#include -#include -#include - -static const char *seqno_fence_get_driver_name(struct dma_fence *fence) -{ - struct seqno_fence *seqno_fence = to_seqno_fence(fence); - - return seqno_fence->ops->get_driver_name(fence); -} - -static const char *seqno_fence_get_timeline_name(struct dma_fence *fence) -{ - struct seqno_fence *seqno_fence = to_seqno_fence(fence); - - return seqno_fence->ops->get_timeline_name(fence); -} - -static bool seqno_enable_signaling(struct dma_fence *fence) -{ - struct seqno_fence *seqno_fence = to_seqno_fence(fence); - - return seqno_fence->ops->enable_signaling(fence); -} - -static bool seqno_signaled(struct dma_fence *fence) -{ - struct seqno_fence *seqno_fence = to_seqno_fence(fence); - - return seqno_fence->ops->signaled && seqno_fence->ops->signaled(fence); -} - -static void seqno_release(struct dma_fence *fence) -{ - struct seqno_fence *f = to_seqno_fence(fence); - - dma_buf_put(f->sync_buf); - if (f->ops->release) - f->ops->release(fence); - else - dma_fence_free(&f->base); -} - -static signed long seqno_wait(struct dma_fence *fence, bool intr, - signed long timeout) -{ - struct seqno_fence *f = to_seqno_fence(fence); - - return f->ops->wait(fence, intr, timeout); -} - -const struct dma_fence_ops seqno_fence_ops = { - .get_driver_name = seqno_fence_get_driver_name, - .get_timeline_name = seqno_fence_get_timeline_name, - .enable_signaling = seqno_enable_signaling, - .signaled = seqno_signaled, - .wait = seqno_wait, - .release = seqno_release, -}; -EXPORT_SYMBOL(seqno_fence_ops); diff --git a/include/linux/seqno-fence.h b/include/linux/seqno-fence.h deleted file mode 100644 index 3cca2b8fac43..000000000000 --- a/include/linux/seqno-fence.h +++ /dev/null @@ -1,109 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * seqno-fence, using a dma-buf to synchronize fencing - * - * Copyright (C) 2012 Texas Instruments - * Copyright (C) 2012 Canonical Ltd - * Authors: - * Rob Clark - * Maarten Lankhorst - */ - -#ifndef __LINUX_SEQNO_FENCE_H -#define __LINUX_SEQNO_FENCE_H - -#include -#include - -enum seqno_fence_condition { - SEQNO_FENCE_WAIT_GEQUAL, - SEQNO_FENCE_WAIT_NONZERO -}; - -struct seqno_fence { - struct dma_fence base; - - const struct dma_fence_ops *ops; - struct dma_buf *sync_buf; - uint32_t seqno_ofs; - enum seqno_fence_condition condition; -}; - -extern const struct dma_fence_ops seqno_fence_ops; - -/** - * to_seqno_fence - cast a fence to a seqno_fence - * @fence: fence to cast to a seqno_fence - * - * Returns NULL if the fence is not a seqno_fence, - * or the seqno_fence otherwise. - */ -static inline struct seqno_fence * -to_seqno_fence(struct dma_fence *fence) -{ - if (fence->ops != &seqno_fence_ops) - return NULL; - return container_of(fence, struct seqno_fence, base); -} - -/** - * seqno_fence_init - initialize a seqno fence - * @fence: seqno_fence to initialize - * @lock: pointer to spinlock to use for fence - * @sync_buf: buffer containing the memory location to signal on - * @context: the execution context this fence is a part of - * @seqno_ofs: the offset within @sync_buf - * @seqno: the sequence # to signal on - * @cond: fence wait condition - * @ops: the fence_ops for operations on this seqno fence - * - * This function initializes a struct seqno_fence with passed parameters, - * and takes a reference on sync_buf which is released on fence destruction. - * - * A seqno_fence is a dma_fence which can complete in software when - * enable_signaling is called, but it also completes when - * (s32)((sync_buf)[seqno_ofs] - seqno) >= 0 is true - * - * The seqno_fence will take a refcount on the sync_buf until it's - * destroyed, but actual lifetime of sync_buf may be longer if one of the - * callers take a reference to it. - * - * Certain hardware have instructions to insert this type of wait condition - * in the command stream, so no intervention from software would be needed. - * This type of fence can be destroyed before completed, however a reference - * on the sync_buf dma-buf can be taken. It is encouraged to re-use the same - * dma-buf for sync_buf, since mapping or unmapping the sync_buf to the - * device's vm can be expensive. - * - * It is recommended for creators of seqno_fence to call dma_fence_signal() - * before destruction. This will prevent possible issues from wraparound at - * time of issue vs time of check, since users can check dma_fence_is_signaled() - * before submitting instructions for the hardware to wait on the fence. - * However, when ops.enable_signaling is not called, it doesn't have to be - * done as soon as possible, just before there's any real danger of seqno - * wraparound. - */ -static inline void -seqno_fence_init(struct seqno_fence *fence, spinlock_t *lock, - struct dma_buf *sync_buf, uint32_t context, - uint32_t seqno_ofs, uint32_t seqno, - enum seqno_fence_condition cond, - const struct dma_fence_ops *ops) -{ - BUG_ON(!fence || !sync_buf || !ops); - BUG_ON(!ops->wait || !ops->enable_signaling || - !ops->get_driver_name || !ops->get_timeline_name); - - /* - * ops is used in dma_fence_init for get_driver_name, so needs to be - * initialized first - */ - fence->ops = ops; - dma_fence_init(&fence->base, &seqno_fence_ops, lock, context, seqno); - get_dma_buf(sync_buf); - fence->sync_buf = sync_buf; - fence->seqno_ofs = seqno_ofs; - fence->condition = cond; -} - -#endif /* __LINUX_SEQNO_FENCE_H */ -- cgit v1.2.3 From d5f45d1e2f08685c34483719b39f91010d6222e8 Mon Sep 17 00:00:00 2001 From: Christian König Date: Wed, 28 Jul 2021 15:05:52 +0200 Subject: drm/ttm: remove ttm_tt_destroy_common v2 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Move the functionality into ttm_tt_fini and ttm_bo_tt_destroy instead. We don't need this any more since we removed the unbind from the destroy code paths in the drivers. Also add a warning to ttm_tt_fini() if we try to fini a still populated TT object. v2: instead of reverting the patch move the functionality to different places. Signed-off-by: Christian König Reviewed-by: Thomas Hellström Link: https://patchwork.freedesktop.org/patch/msgid/20210728130552.2074-5-christian.koenig@amd.com --- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 1 - drivers/gpu/drm/drm_gem_vram_helper.c | 1 - drivers/gpu/drm/i915/gem/i915_gem_ttm.c | 1 - drivers/gpu/drm/nouveau/nouveau_bo.c | 1 - drivers/gpu/drm/nouveau/nouveau_sgdma.c | 1 - drivers/gpu/drm/qxl/qxl_ttm.c | 1 - drivers/gpu/drm/radeon/radeon_ttm.c | 2 -- drivers/gpu/drm/ttm/ttm_bo.c | 1 + drivers/gpu/drm/ttm/ttm_tt.c | 17 ++++++----------- drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c | 1 - include/drm/ttm/ttm_tt.h | 7 ------- 11 files changed, 7 insertions(+), 27 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 75d45623388a..489e22190e29 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -1066,7 +1066,6 @@ static void amdgpu_ttm_backend_destroy(struct ttm_device *bdev, { struct amdgpu_ttm_tt *gtt = (void *)ttm; - ttm_tt_destroy_common(bdev, ttm); if (gtt->usertask) put_task_struct(gtt->usertask); diff --git a/drivers/gpu/drm/drm_gem_vram_helper.c b/drivers/gpu/drm/drm_gem_vram_helper.c index 43cf7e887d1a..bfa386b98134 100644 --- a/drivers/gpu/drm/drm_gem_vram_helper.c +++ b/drivers/gpu/drm/drm_gem_vram_helper.c @@ -846,7 +846,6 @@ static const struct drm_gem_object_funcs drm_gem_vram_object_funcs = { static void bo_driver_ttm_tt_destroy(struct ttm_device *bdev, struct ttm_tt *tt) { - ttm_tt_destroy_common(bdev, tt); ttm_tt_fini(tt); kfree(tt); } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c index bf33724bed5c..e646aac9d7a4 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c @@ -118,7 +118,6 @@ static void i915_ttm_tt_destroy(struct ttm_device *bdev, struct ttm_tt *ttm) { struct i915_ttm_tt *i915_tt = container_of(ttm, typeof(*i915_tt), ttm); - ttm_tt_destroy_common(bdev, ttm); kfree(i915_tt); } diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c index c33a56c2f068..33dca2565cca 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.c +++ b/drivers/gpu/drm/nouveau/nouveau_bo.c @@ -1292,7 +1292,6 @@ nouveau_ttm_tt_destroy(struct ttm_device *bdev, #if IS_ENABLED(CONFIG_AGP) struct nouveau_drm *drm = nouveau_bdev(bdev); if (drm->agp.bridge) { - ttm_tt_destroy_common(bdev, ttm); ttm_agp_destroy(ttm); return; } diff --git a/drivers/gpu/drm/nouveau/nouveau_sgdma.c b/drivers/gpu/drm/nouveau/nouveau_sgdma.c index bde92a9dae7a..85c03c83259b 100644 --- a/drivers/gpu/drm/nouveau/nouveau_sgdma.c +++ b/drivers/gpu/drm/nouveau/nouveau_sgdma.c @@ -21,7 +21,6 @@ nouveau_sgdma_destroy(struct ttm_device *bdev, struct ttm_tt *ttm) struct nouveau_sgdma_be *nvbe = (struct nouveau_sgdma_be *)ttm; if (ttm) { - ttm_tt_destroy_common(bdev, ttm); ttm_tt_fini(&nvbe->ttm); kfree(nvbe); } diff --git a/drivers/gpu/drm/qxl/qxl_ttm.c b/drivers/gpu/drm/qxl/qxl_ttm.c index 37a1b6a6ad6d..b2e33d5ba5d0 100644 --- a/drivers/gpu/drm/qxl/qxl_ttm.c +++ b/drivers/gpu/drm/qxl/qxl_ttm.c @@ -101,7 +101,6 @@ int qxl_ttm_io_mem_reserve(struct ttm_device *bdev, */ static void qxl_ttm_backend_destroy(struct ttm_device *bdev, struct ttm_tt *ttm) { - ttm_tt_destroy_common(bdev, ttm); ttm_tt_fini(ttm); kfree(ttm); } diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c index ee343b76db54..7793249bc549 100644 --- a/drivers/gpu/drm/radeon/radeon_ttm.c +++ b/drivers/gpu/drm/radeon/radeon_ttm.c @@ -488,7 +488,6 @@ static void radeon_ttm_backend_destroy(struct ttm_device *bdev, struct ttm_tt *t { struct radeon_ttm_tt *gtt = (void *)ttm; - ttm_tt_destroy_common(bdev, ttm); ttm_tt_fini(>t->ttm); kfree(gtt); } @@ -651,7 +650,6 @@ static void radeon_ttm_tt_destroy(struct ttm_device *bdev, struct radeon_device *rdev = radeon_get_rdev(bdev); if (rdev->flags & RADEON_IS_AGP) { - ttm_tt_destroy_common(bdev, ttm); ttm_agp_destroy(ttm); return; } diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index ea4add2b9717..49f4bc97c35a 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -1224,6 +1224,7 @@ void ttm_bo_tt_destroy(struct ttm_buffer_object *bo) if (bo->ttm == NULL) return; + ttm_tt_unpopulate(bo->bdev, bo->ttm); ttm_tt_destroy(bo->bdev, bo->ttm); bo->ttm = NULL; } diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c index 24031a8acd2d..506b3c926a68 100644 --- a/drivers/gpu/drm/ttm/ttm_tt.c +++ b/drivers/gpu/drm/ttm/ttm_tt.c @@ -123,17 +123,6 @@ static int ttm_sg_tt_alloc_page_directory(struct ttm_tt *ttm) return 0; } -void ttm_tt_destroy_common(struct ttm_device *bdev, struct ttm_tt *ttm) -{ - ttm_tt_unpopulate(bdev, ttm); - - if (ttm->swap_storage) - fput(ttm->swap_storage); - - ttm->swap_storage = NULL; -} -EXPORT_SYMBOL(ttm_tt_destroy_common); - void ttm_tt_destroy(struct ttm_device *bdev, struct ttm_tt *ttm) { bdev->funcs->ttm_tt_destroy(bdev, ttm); @@ -168,6 +157,12 @@ EXPORT_SYMBOL(ttm_tt_init); void ttm_tt_fini(struct ttm_tt *ttm) { + WARN_ON(ttm->page_flags & TTM_PAGE_FLAG_PRIV_POPULATED); + + if (ttm->swap_storage) + fput(ttm->swap_storage); + ttm->swap_storage = NULL; + if (ttm->pages) kvfree(ttm->pages); else diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c index 904031d03dbe..f35bdc1cb197 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c @@ -526,7 +526,6 @@ static void vmw_ttm_destroy(struct ttm_device *bdev, struct ttm_tt *ttm) struct vmw_ttm_tt *vmw_be = container_of(ttm, struct vmw_ttm_tt, dma_ttm); - ttm_tt_destroy_common(bdev, ttm); vmw_ttm_unmap_dma(vmw_be); ttm_tt_fini(ttm); if (vmw_be->mob) diff --git a/include/drm/ttm/ttm_tt.h b/include/drm/ttm/ttm_tt.h index 818680c6a8ed..e402dab1d0f6 100644 --- a/include/drm/ttm/ttm_tt.h +++ b/include/drm/ttm/ttm_tt.h @@ -134,13 +134,6 @@ void ttm_tt_fini(struct ttm_tt *ttm); */ void ttm_tt_destroy(struct ttm_device *bdev, struct ttm_tt *ttm); -/** - * ttm_tt_destroy_common: - * - * Called from driver to destroy common path. - */ -void ttm_tt_destroy_common(struct ttm_device *bdev, struct ttm_tt *ttm); - /** * ttm_tt_swapin: * -- cgit v1.2.3 From 669076334bfa7915e6856cf49c6408a2ec07df7a Mon Sep 17 00:00:00 2001 From: Thomas Hellström Date: Fri, 13 Aug 2021 16:43:31 +0200 Subject: drm/ttm, drm/i915: Update ttm_move_memcpy for async use MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The buffer object argument to ttm_move_memcpy was only used to determine whether the destination memory should be cleared only or whether we should copy data. Replace it with a "clear" bool, and update the callers. The intention here is to be able to use ttm_move_memcpy() async under a dma-fence as a fallback if an accelerated blit fails in a security- critical path where data might leak if the blit is not properly performed. For that purpose the bo is an unsuitable argument since its relevant members might already have changed at call time. Finally, update the ttm_move_memcpy kerneldoc that seems to have ended up with a stale version. Cc: Christian König Signed-off-by: Thomas Hellström Reviewed-by: Matthew Auld Reviewed-by: Christian König Link: https://lore.kernel.org/r/20210813144331.372957-3-thomas.hellstrom@linux.intel.com Link: https://patchwork.freedesktop.org/patch/msgid/20210813144331.372957-3-thomas.hellstrom@linux.intel.com --- drivers/gpu/drm/i915/gem/i915_gem_ttm.c | 2 +- drivers/gpu/drm/ttm/ttm_bo_util.c | 20 ++++++++++---------- include/drm/ttm/ttm_bo_driver.h | 2 +- 3 files changed, 12 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c index d07de18529ab..6995c66cbe21 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c @@ -518,7 +518,7 @@ static void __i915_ttm_move(struct ttm_buffer_object *bo, bool clear, obj->ttm.cached_io_st, src_reg->region.start); - ttm_move_memcpy(bo, dst_mem->num_pages, dst_iter, src_iter); + ttm_move_memcpy(clear, dst_mem->num_pages, dst_iter, src_iter); } } diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c index 2f57f824e6db..e3747f069674 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_util.c +++ b/drivers/gpu/drm/ttm/ttm_bo_util.c @@ -75,22 +75,21 @@ void ttm_mem_io_free(struct ttm_device *bdev, /** * ttm_move_memcpy - Helper to perform a memcpy ttm move operation. - * @bo: The struct ttm_buffer_object. - * @new_mem: The struct ttm_resource we're moving to (copy destination). - * @new_iter: A struct ttm_kmap_iter representing the destination resource. + * @clear: Whether to clear rather than copy. + * @num_pages: Number of pages of the operation. + * @dst_iter: A struct ttm_kmap_iter representing the destination resource. * @src_iter: A struct ttm_kmap_iter representing the source resource. * * This function is intended to be able to move out async under a * dma-fence if desired. */ -void ttm_move_memcpy(struct ttm_buffer_object *bo, +void ttm_move_memcpy(bool clear, u32 num_pages, struct ttm_kmap_iter *dst_iter, struct ttm_kmap_iter *src_iter) { const struct ttm_kmap_iter_ops *dst_ops = dst_iter->ops; const struct ttm_kmap_iter_ops *src_ops = src_iter->ops; - struct ttm_tt *ttm = bo->ttm; struct dma_buf_map src_map, dst_map; pgoff_t i; @@ -99,10 +98,7 @@ void ttm_move_memcpy(struct ttm_buffer_object *bo, return; /* Don't move nonexistent data. Clear destination instead. */ - if (src_ops->maps_tt && (!ttm || !ttm_tt_is_populated(ttm))) { - if (ttm && !(ttm->page_flags & TTM_PAGE_FLAG_ZERO_ALLOC)) - return; - + if (clear) { for (i = 0; i < num_pages; ++i) { dst_ops->map_local(dst_iter, &dst_map, i); if (dst_map.is_iomem) @@ -146,6 +142,7 @@ int ttm_bo_move_memcpy(struct ttm_buffer_object *bo, struct ttm_kmap_iter_linear_io io; } _dst_iter, _src_iter; struct ttm_kmap_iter *dst_iter, *src_iter; + bool clear; int ret = 0; if (ttm && ((ttm->page_flags & TTM_PAGE_FLAG_SWAPPED) || @@ -169,7 +166,10 @@ int ttm_bo_move_memcpy(struct ttm_buffer_object *bo, goto out_src_iter; } - ttm_move_memcpy(bo, dst_mem->num_pages, dst_iter, src_iter); + clear = src_iter->ops->maps_tt && (!ttm || !ttm_tt_is_populated(ttm)); + if (!(clear && ttm && !(ttm->page_flags & TTM_PAGE_FLAG_ZERO_ALLOC))) + ttm_move_memcpy(clear, dst_mem->num_pages, dst_iter, src_iter); + src_copy = *src_mem; ttm_bo_move_sync_cleanup(bo, dst_mem); diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index 68d6069572aa..5f087575194b 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -322,7 +322,7 @@ int ttm_bo_tt_bind(struct ttm_buffer_object *bo, struct ttm_resource *mem); */ void ttm_bo_tt_destroy(struct ttm_buffer_object *bo); -void ttm_move_memcpy(struct ttm_buffer_object *bo, +void ttm_move_memcpy(bool clear, u32 num_pages, struct ttm_kmap_iter *dst_iter, struct ttm_kmap_iter *src_iter); -- cgit v1.2.3 From 880121be1179a0db3eb4fdb198108d9475b8be4c Mon Sep 17 00:00:00 2001 From: Christian König Date: Thu, 15 Apr 2021 13:56:23 +0200 Subject: mm/vmscan: add sync_shrinkers function v3 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit While unplugging a device the TTM shrinker implementation needs a barrier to make sure that all concurrent shrink operations are done and no other CPU is referring to a device specific pool any more. Taking and releasing the shrinker semaphore on the write side after unmapping and freeing all pages from the device pool should make sure that no shrinker is running in paralell. This allows us to avoid the contented mutex in the TTM pool implementation for every alloc/free operation. v2: rework the commit message to make clear why we need this v3: rename the function and add more doc as suggested by Daniel Signed-off-by: Christian König Acked-by: Huang Rui Acked-by: Andrew Morton Reviewed-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20210820120528.81114-2-christian.koenig@amd.com --- include/linux/shrinker.h | 1 + mm/vmscan.c | 15 +++++++++++++++ 2 files changed, 16 insertions(+) (limited to 'include') diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h index 9814fff58a69..76fbf92b04d9 100644 --- a/include/linux/shrinker.h +++ b/include/linux/shrinker.h @@ -93,4 +93,5 @@ extern void register_shrinker_prepared(struct shrinker *shrinker); extern int register_shrinker(struct shrinker *shrinker); extern void unregister_shrinker(struct shrinker *shrinker); extern void free_prealloced_shrinker(struct shrinker *shrinker); +extern void synchronize_shrinkers(void); #endif diff --git a/mm/vmscan.c b/mm/vmscan.c index 4620df62f0ff..5d22a63472f0 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -638,6 +638,21 @@ void unregister_shrinker(struct shrinker *shrinker) } EXPORT_SYMBOL(unregister_shrinker); +/** + * synchronize_shrinkers - Wait for all running shrinkers to complete. + * + * This is equivalent to calling unregister_shrink() and register_shrinker(), + * but atomically and with less overhead. This is useful to guarantee that all + * shrinker invocations have seen an update, before freeing memory, similar to + * rcu. + */ +void synchronize_shrinkers(void) +{ + down_write(&shrinker_rwsem); + up_write(&shrinker_rwsem); +} +EXPORT_SYMBOL(synchronize_shrinkers); + #define SHRINK_BATCH 128 static unsigned long do_shrink_slab(struct shrink_control *shrinkctl, -- cgit v1.2.3 From 4087d2fb286c85a1bde72e7523c496080ef39035 Mon Sep 17 00:00:00 2001 From: Alyssa Rosenzweig Date: Sun, 29 Aug 2021 12:04:01 -0400 Subject: drm/plane: Fix comment typo Minor typofix noticed when reading the KMS documentation. Signed-off-by: Alyssa Rosenzweig Signed-off-by: Simon Ser Reviewed-by: Simon Ser Link: https://patchwork.freedesktop.org/patch/msgid/20210829160401.4588-1-alyssa@rosenzweig.io --- include/drm/drm_plane.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/drm/drm_plane.h b/include/drm/drm_plane.h index fed97e35626f..0c1102dc4d88 100644 --- a/include/drm/drm_plane.h +++ b/include/drm/drm_plane.h @@ -43,7 +43,7 @@ enum drm_scaling_filter { /** * struct drm_plane_state - mutable plane state * - * Please not that the destination coordinates @crtc_x, @crtc_y, @crtc_h and + * Please note that the destination coordinates @crtc_x, @crtc_y, @crtc_h and * @crtc_w and the source coordinates @src_x, @src_y, @src_h and @src_w are the * raw coordinates provided by userspace. Drivers should use * drm_atomic_helper_check_plane_state() and only use the derived rectangles in -- cgit v1.2.3 From dbe48d030b285a1305a874bee523681709fba162 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Tue, 17 Aug 2021 10:49:16 +0200 Subject: drm/sched: Split drm_sched_job_init MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This is a very confusingly named function, because not just does it init an object, it arms it and provides a point of no return for pushing a job into the scheduler. It would be nice if that's a bit clearer in the interface. But the real reason is that I want to push the dependency tracking helpers into the scheduler code, and that means drm_sched_job_init must be called a lot earlier, without arming the job. v2: - don't change .gitignore (Steven) - don't forget v3d (Emma) v3: Emma noticed that I leak the memory allocated in drm_sched_job_init if we bail out before the point of no return in subsequent driver patches. To be able to fix this change drm_sched_job_cleanup() so it can handle being called both before and after drm_sched_job_arm(). Also improve the kerneldoc for this. v4: - Fix the drm_sched_job_cleanup logic, I inverted the booleans, as usual (Melissa) - Christian pointed out that drm_sched_entity_select_rq() also needs to be moved into drm_sched_job_arm, which made me realize that the job->id definitely needs to be moved too. Shuffle things to fit between job_init and job_arm. v5: Reshuffle the split between init/arm once more, amdgpu abuses drm_sched.ready to signal gpu reset failures. Also document this somewhat. (Christian) v6: Rebase on top of the msm drm/sched support. Note that the drm_sched_job_init() call is completely misplaced, and hence also the split-out drm_sched_entity_push_job(). I've put in a FIXME which the next patch will address. v7: Drop the FIXME in msm, after discussions with Rob I agree it shouldn't be a problem where it is now. Acked-by: Christian König Acked-by: Melissa Wen Cc: Melissa Wen Acked-by: Emma Anholt Acked-by: Steven Price (v2) Reviewed-by: Boris Brezillon (v5) Signed-off-by: Daniel Vetter Cc: Lucas Stach Cc: Russell King Cc: Christian Gmeiner Cc: Qiang Yu Cc: Rob Herring Cc: Tomeu Vizoso Cc: Steven Price Cc: Alyssa Rosenzweig Cc: David Airlie Cc: Daniel Vetter Cc: Sumit Semwal Cc: "Christian König" Cc: Masahiro Yamada Cc: Kees Cook Cc: Adam Borowski Cc: Nick Terrell Cc: Mauro Carvalho Chehab Cc: Paul Menzel Cc: Sami Tolvanen Cc: Viresh Kumar Cc: Alex Deucher Cc: Dave Airlie Cc: Nirmoy Das Cc: Deepak R Varma Cc: Lee Jones Cc: Kevin Wang Cc: Chen Li Cc: Luben Tuikov Cc: "Marek Olšák" Cc: Dennis Li Cc: Maarten Lankhorst Cc: Andrey Grodzovsky Cc: Sonny Jiang Cc: Boris Brezillon Cc: Tian Tao Cc: etnaviv@lists.freedesktop.org Cc: lima@lists.freedesktop.org Cc: linux-media@vger.kernel.org Cc: linaro-mm-sig@lists.linaro.org Cc: Emma Anholt Cc: Rob Clark Cc: Sean Paul Cc: linux-arm-msm@vger.kernel.org Cc: freedreno@lists.freedesktop.org Link: https://patchwork.freedesktop.org/patch/msgid/20210817084917.3555822-1-daniel.vetter@ffwll.ch --- drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 2 + drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 2 + drivers/gpu/drm/etnaviv/etnaviv_sched.c | 2 + drivers/gpu/drm/lima/lima_sched.c | 2 + drivers/gpu/drm/msm/msm_gem_submit.c | 2 + drivers/gpu/drm/panfrost/panfrost_job.c | 2 + drivers/gpu/drm/scheduler/sched_entity.c | 6 +-- drivers/gpu/drm/scheduler/sched_fence.c | 19 +++++---- drivers/gpu/drm/scheduler/sched_main.c | 69 +++++++++++++++++++++++++++----- drivers/gpu/drm/v3d/v3d_gem.c | 2 + include/drm/gpu_scheduler.h | 7 +++- 11 files changed, 93 insertions(+), 22 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index a152363b0254..2b7f4b77a572 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -1222,6 +1222,8 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p, if (r) goto error_unlock; + drm_sched_job_arm(&job->base); + /* No memory allocation is allowed while holding the notifier lock. * The lock is held until amdgpu_cs_submit is finished and fence is * added to BOs. diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c index d33e6d97cc89..5ddb955d2315 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c @@ -170,6 +170,8 @@ int amdgpu_job_submit(struct amdgpu_job *job, struct drm_sched_entity *entity, if (r) return r; + drm_sched_job_arm(&job->base); + *f = dma_fence_get(&job->base.s_fence->finished); amdgpu_job_free_resources(job); drm_sched_entity_push_job(&job->base, entity); diff --git a/drivers/gpu/drm/etnaviv/etnaviv_sched.c b/drivers/gpu/drm/etnaviv/etnaviv_sched.c index feb6da1b6ceb..05f412204118 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_sched.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_sched.c @@ -163,6 +163,8 @@ int etnaviv_sched_push_job(struct drm_sched_entity *sched_entity, if (ret) goto out_unlock; + drm_sched_job_arm(&submit->sched_job); + submit->out_fence = dma_fence_get(&submit->sched_job.s_fence->finished); submit->out_fence_id = idr_alloc_cyclic(&submit->gpu->fence_idr, submit->out_fence, 0, diff --git a/drivers/gpu/drm/lima/lima_sched.c b/drivers/gpu/drm/lima/lima_sched.c index dba8329937a3..38f755580507 100644 --- a/drivers/gpu/drm/lima/lima_sched.c +++ b/drivers/gpu/drm/lima/lima_sched.c @@ -129,6 +129,8 @@ int lima_sched_task_init(struct lima_sched_task *task, return err; } + drm_sched_job_arm(&task->base); + task->num_bos = num_bos; task->vm = lima_vm_get(vm); diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c index fdc5367aecaa..4d1c4d5f6a2a 100644 --- a/drivers/gpu/drm/msm/msm_gem_submit.c +++ b/drivers/gpu/drm/msm/msm_gem_submit.c @@ -52,6 +52,8 @@ static struct msm_gem_submit *submit_create(struct drm_device *dev, return ERR_PTR(ret); } + drm_sched_job_arm(&job->base); + xa_init_flags(&submit->deps, XA_FLAGS_ALLOC); kref_init(&submit->ref); diff --git a/drivers/gpu/drm/panfrost/panfrost_job.c b/drivers/gpu/drm/panfrost/panfrost_job.c index 763b7abfc88e..aaa662cbc43b 100644 --- a/drivers/gpu/drm/panfrost/panfrost_job.c +++ b/drivers/gpu/drm/panfrost/panfrost_job.c @@ -288,6 +288,8 @@ int panfrost_job_push(struct panfrost_job *job) goto unlock; } + drm_sched_job_arm(&job->base); + job->render_done_fence = dma_fence_get(&job->base.s_fence->finished); ret = panfrost_acquire_object_fences(job->bos, job->bo_count, diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c index 79554aa4dbb1..f7347c284886 100644 --- a/drivers/gpu/drm/scheduler/sched_entity.c +++ b/drivers/gpu/drm/scheduler/sched_entity.c @@ -485,9 +485,9 @@ void drm_sched_entity_select_rq(struct drm_sched_entity *entity) * @sched_job: job to submit * @entity: scheduler entity * - * Note: To guarantee that the order of insertion to queue matches - * the job's fence sequence number this function should be - * called with drm_sched_job_init under common lock. + * Note: To guarantee that the order of insertion to queue matches the job's + * fence sequence number this function should be called with drm_sched_job_arm() + * under common lock. * * Returns 0 for success, negative error code otherwise. */ diff --git a/drivers/gpu/drm/scheduler/sched_fence.c b/drivers/gpu/drm/scheduler/sched_fence.c index 69de2c76731f..bcea035cf4c6 100644 --- a/drivers/gpu/drm/scheduler/sched_fence.c +++ b/drivers/gpu/drm/scheduler/sched_fence.c @@ -90,7 +90,7 @@ static const char *drm_sched_fence_get_timeline_name(struct dma_fence *f) * * Free up the fence memory after the RCU grace period. */ -static void drm_sched_fence_free(struct rcu_head *rcu) +void drm_sched_fence_free(struct rcu_head *rcu) { struct dma_fence *f = container_of(rcu, struct dma_fence, rcu); struct drm_sched_fence *fence = to_drm_sched_fence(f); @@ -152,27 +152,32 @@ struct drm_sched_fence *to_drm_sched_fence(struct dma_fence *f) } EXPORT_SYMBOL(to_drm_sched_fence); -struct drm_sched_fence *drm_sched_fence_create(struct drm_sched_entity *entity, - void *owner) +struct drm_sched_fence *drm_sched_fence_alloc(struct drm_sched_entity *entity, + void *owner) { struct drm_sched_fence *fence = NULL; - unsigned seq; fence = kmem_cache_zalloc(sched_fence_slab, GFP_KERNEL); if (fence == NULL) return NULL; fence->owner = owner; - fence->sched = entity->rq->sched; spin_lock_init(&fence->lock); + return fence; +} + +void drm_sched_fence_init(struct drm_sched_fence *fence, + struct drm_sched_entity *entity) +{ + unsigned seq; + + fence->sched = entity->rq->sched; seq = atomic_inc_return(&entity->fence_seq); dma_fence_init(&fence->scheduled, &drm_sched_fence_ops_scheduled, &fence->lock, entity->fence_context, seq); dma_fence_init(&fence->finished, &drm_sched_fence_ops_finished, &fence->lock, entity->fence_context + 1, seq); - - return fence; } module_init(drm_sched_fence_slab_init); diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c index 67382621b429..719b1a6dbb90 100644 --- a/drivers/gpu/drm/scheduler/sched_main.c +++ b/drivers/gpu/drm/scheduler/sched_main.c @@ -48,9 +48,11 @@ #include #include #include +#include #include #include +#include #include #include @@ -564,7 +566,6 @@ EXPORT_SYMBOL(drm_sched_resubmit_jobs_ext); /** * drm_sched_job_init - init a scheduler job - * * @job: scheduler job to init * @entity: scheduler entity to use * @owner: job owner for debugging @@ -572,27 +573,28 @@ EXPORT_SYMBOL(drm_sched_resubmit_jobs_ext); * Refer to drm_sched_entity_push_job() documentation * for locking considerations. * + * Drivers must make sure drm_sched_job_cleanup() if this function returns + * successfully, even when @job is aborted before drm_sched_job_arm() is called. + * + * WARNING: amdgpu abuses &drm_sched.ready to signal when the hardware + * has died, which can mean that there's no valid runqueue for a @entity. + * This function returns -ENOENT in this case (which probably should be -EIO as + * a more meanigful return value). + * * Returns 0 for success, negative error code otherwise. */ int drm_sched_job_init(struct drm_sched_job *job, struct drm_sched_entity *entity, void *owner) { - struct drm_gpu_scheduler *sched; - drm_sched_entity_select_rq(entity); if (!entity->rq) return -ENOENT; - sched = entity->rq->sched; - - job->sched = sched; job->entity = entity; - job->s_priority = entity->rq - sched->sched_rq; - job->s_fence = drm_sched_fence_create(entity, owner); + job->s_fence = drm_sched_fence_alloc(entity, owner); if (!job->s_fence) return -ENOMEM; - job->id = atomic64_inc_return(&sched->job_id_count); INIT_LIST_HEAD(&job->list); @@ -601,13 +603,58 @@ int drm_sched_job_init(struct drm_sched_job *job, EXPORT_SYMBOL(drm_sched_job_init); /** - * drm_sched_job_cleanup - clean up scheduler job resources + * drm_sched_job_arm - arm a scheduler job for execution + * @job: scheduler job to arm + * + * This arms a scheduler job for execution. Specifically it initializes the + * &drm_sched_job.s_fence of @job, so that it can be attached to struct dma_resv + * or other places that need to track the completion of this job. + * + * Refer to drm_sched_entity_push_job() documentation for locking + * considerations. * + * This can only be called if drm_sched_job_init() succeeded. + */ +void drm_sched_job_arm(struct drm_sched_job *job) +{ + struct drm_gpu_scheduler *sched; + struct drm_sched_entity *entity = job->entity; + + BUG_ON(!entity); + + sched = entity->rq->sched; + + job->sched = sched; + job->s_priority = entity->rq - sched->sched_rq; + job->id = atomic64_inc_return(&sched->job_id_count); + + drm_sched_fence_init(job->s_fence, job->entity); +} +EXPORT_SYMBOL(drm_sched_job_arm); + +/** + * drm_sched_job_cleanup - clean up scheduler job resources * @job: scheduler job to clean up + * + * Cleans up the resources allocated with drm_sched_job_init(). + * + * Drivers should call this from their error unwind code if @job is aborted + * before drm_sched_job_arm() is called. + * + * After that point of no return @job is committed to be executed by the + * scheduler, and this function should be called from the + * &drm_sched_backend_ops.free_job callback. */ void drm_sched_job_cleanup(struct drm_sched_job *job) { - dma_fence_put(&job->s_fence->finished); + if (kref_read(&job->s_fence->finished.refcount)) { + /* drm_sched_job_arm() has been called */ + dma_fence_put(&job->s_fence->finished); + } else { + /* aborted job before committing to run it */ + drm_sched_fence_free(&job->s_fence->finished.rcu); + } + job->s_fence = NULL; } EXPORT_SYMBOL(drm_sched_job_cleanup); diff --git a/drivers/gpu/drm/v3d/v3d_gem.c b/drivers/gpu/drm/v3d/v3d_gem.c index 5689da118197..2e808097b4d1 100644 --- a/drivers/gpu/drm/v3d/v3d_gem.c +++ b/drivers/gpu/drm/v3d/v3d_gem.c @@ -480,6 +480,8 @@ v3d_push_job(struct v3d_file_priv *v3d_priv, if (ret) return ret; + drm_sched_job_arm(&job->base); + job->done_fence = dma_fence_get(&job->base.s_fence->finished); /* put by scheduler job completion */ diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h index 88ae7f331bb1..83afc3aa8e2f 100644 --- a/include/drm/gpu_scheduler.h +++ b/include/drm/gpu_scheduler.h @@ -348,6 +348,7 @@ void drm_sched_fini(struct drm_gpu_scheduler *sched); int drm_sched_job_init(struct drm_sched_job *job, struct drm_sched_entity *entity, void *owner); +void drm_sched_job_arm(struct drm_sched_job *job); void drm_sched_entity_modify_sched(struct drm_sched_entity *entity, struct drm_gpu_scheduler **sched_list, unsigned int num_sched_list); @@ -387,8 +388,12 @@ void drm_sched_entity_set_priority(struct drm_sched_entity *entity, enum drm_sched_priority priority); bool drm_sched_entity_is_ready(struct drm_sched_entity *entity); -struct drm_sched_fence *drm_sched_fence_create( +struct drm_sched_fence *drm_sched_fence_alloc( struct drm_sched_entity *s_entity, void *owner); +void drm_sched_fence_init(struct drm_sched_fence *fence, + struct drm_sched_entity *entity); +void drm_sched_fence_free(struct rcu_head *rcu); + void drm_sched_fence_scheduled(struct drm_sched_fence *fence); void drm_sched_fence_finished(struct drm_sched_fence *fence); -- cgit v1.2.3 From ebd5f74255b9f5f8a154ba5535f83387ae599d46 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Thu, 5 Aug 2021 12:46:49 +0200 Subject: drm/sched: Add dependency tracking MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Instead of just a callback we can just glue in the gem helpers that panfrost, v3d and lima currently use. There's really not that many ways to skin this cat. v2/3: Rebased. v4: Repaint this shed. The functions are now called _add_dependency() and _add_implicit_dependency() Reviewed-by: Christian König Reviewed-by: Boris Brezillon (v3) Reviewed-by: Steven Price (v1) Acked-by: Melissa Wen Signed-off-by: Daniel Vetter Cc: David Airlie Cc: Daniel Vetter Cc: Sumit Semwal Cc: "Christian König" Cc: Andrey Grodzovsky Cc: Lee Jones Cc: Nirmoy Das Cc: Boris Brezillon Cc: Luben Tuikov Cc: Alex Deucher Cc: linux-media@vger.kernel.org Cc: linaro-mm-sig@lists.linaro.org Link: https://patchwork.freedesktop.org/patch/msgid/20210805104705.862416-5-daniel.vetter@ffwll.ch --- drivers/gpu/drm/scheduler/sched_entity.c | 18 +++++- drivers/gpu/drm/scheduler/sched_main.c | 104 +++++++++++++++++++++++++++++++ include/drm/gpu_scheduler.h | 33 +++++++++- 3 files changed, 149 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c index 89e3f6eaf519..381fbf462ea7 100644 --- a/drivers/gpu/drm/scheduler/sched_entity.c +++ b/drivers/gpu/drm/scheduler/sched_entity.c @@ -211,6 +211,19 @@ static void drm_sched_entity_kill_jobs_cb(struct dma_fence *f, job->sched->ops->free_job(job); } +static struct dma_fence * +drm_sched_job_dependency(struct drm_sched_job *job, + struct drm_sched_entity *entity) +{ + if (!xa_empty(&job->dependencies)) + return xa_erase(&job->dependencies, job->last_dependency++); + + if (job->sched->ops->dependency) + return job->sched->ops->dependency(job, entity); + + return NULL; +} + /** * drm_sched_entity_kill_jobs - Make sure all remaining jobs are killed * @@ -229,7 +242,7 @@ static void drm_sched_entity_kill_jobs(struct drm_sched_entity *entity) struct drm_sched_fence *s_fence = job->s_fence; /* Wait for all dependencies to avoid data corruptions */ - while ((f = job->sched->ops->dependency(job, entity))) + while ((f = drm_sched_job_dependency(job, entity))) dma_fence_wait(f, false); drm_sched_fence_scheduled(s_fence); @@ -419,7 +432,6 @@ static bool drm_sched_entity_add_dependency_cb(struct drm_sched_entity *entity) */ struct drm_sched_job *drm_sched_entity_pop_job(struct drm_sched_entity *entity) { - struct drm_gpu_scheduler *sched = entity->rq->sched; struct drm_sched_job *sched_job; sched_job = to_drm_sched_job(spsc_queue_peek(&entity->job_queue)); @@ -427,7 +439,7 @@ struct drm_sched_job *drm_sched_entity_pop_job(struct drm_sched_entity *entity) return NULL; while ((entity->dependency = - sched->ops->dependency(sched_job, entity))) { + drm_sched_job_dependency(sched_job, entity))) { trace_drm_sched_job_wait_dep(sched_job, entity->dependency); if (drm_sched_entity_add_dependency_cb(entity)) diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c index 719b1a6dbb90..fbbd3b03902f 100644 --- a/drivers/gpu/drm/scheduler/sched_main.c +++ b/drivers/gpu/drm/scheduler/sched_main.c @@ -598,6 +598,8 @@ int drm_sched_job_init(struct drm_sched_job *job, INIT_LIST_HEAD(&job->list); + xa_init_flags(&job->dependencies, XA_FLAGS_ALLOC); + return 0; } EXPORT_SYMBOL(drm_sched_job_init); @@ -632,6 +634,99 @@ void drm_sched_job_arm(struct drm_sched_job *job) } EXPORT_SYMBOL(drm_sched_job_arm); +/** + * drm_sched_job_add_dependency - adds the fence as a job dependency + * @job: scheduler job to add the dependencies to + * @fence: the dma_fence to add to the list of dependencies. + * + * Note that @fence is consumed in both the success and error cases. + * + * Returns: + * 0 on success, or an error on failing to expand the array. + */ +int drm_sched_job_add_dependency(struct drm_sched_job *job, + struct dma_fence *fence) +{ + struct dma_fence *entry; + unsigned long index; + u32 id = 0; + int ret; + + if (!fence) + return 0; + + /* Deduplicate if we already depend on a fence from the same context. + * This lets the size of the array of deps scale with the number of + * engines involved, rather than the number of BOs. + */ + xa_for_each(&job->dependencies, index, entry) { + if (entry->context != fence->context) + continue; + + if (dma_fence_is_later(fence, entry)) { + dma_fence_put(entry); + xa_store(&job->dependencies, index, fence, GFP_KERNEL); + } else { + dma_fence_put(fence); + } + return 0; + } + + ret = xa_alloc(&job->dependencies, &id, fence, xa_limit_32b, GFP_KERNEL); + if (ret != 0) + dma_fence_put(fence); + + return ret; +} +EXPORT_SYMBOL(drm_sched_job_add_dependency); + +/** + * drm_sched_job_add_implicit_dependencies - adds implicit dependencies as job + * dependencies + * @job: scheduler job to add the dependencies to + * @obj: the gem object to add new dependencies from. + * @write: whether the job might write the object (so we need to depend on + * shared fences in the reservation object). + * + * This should be called after drm_gem_lock_reservations() on your array of + * GEM objects used in the job but before updating the reservations with your + * own fences. + * + * Returns: + * 0 on success, or an error on failing to expand the array. + */ +int drm_sched_job_add_implicit_dependencies(struct drm_sched_job *job, + struct drm_gem_object *obj, + bool write) +{ + int ret; + struct dma_fence **fences; + unsigned int i, fence_count; + + if (!write) { + struct dma_fence *fence = dma_resv_get_excl_unlocked(obj->resv); + + return drm_sched_job_add_dependency(job, fence); + } + + ret = dma_resv_get_fences(obj->resv, NULL, &fence_count, &fences); + if (ret || !fence_count) + return ret; + + for (i = 0; i < fence_count; i++) { + ret = drm_sched_job_add_dependency(job, fences[i]); + if (ret) + break; + } + + for (; i < fence_count; i++) + dma_fence_put(fences[i]); + kfree(fences); + return ret; +} +EXPORT_SYMBOL(drm_sched_job_add_implicit_dependencies); + + /** * drm_sched_job_cleanup - clean up scheduler job resources * @job: scheduler job to clean up @@ -647,6 +742,9 @@ EXPORT_SYMBOL(drm_sched_job_arm); */ void drm_sched_job_cleanup(struct drm_sched_job *job) { + struct dma_fence *fence; + unsigned long index; + if (kref_read(&job->s_fence->finished.refcount)) { /* drm_sched_job_arm() has been called */ dma_fence_put(&job->s_fence->finished); @@ -656,6 +754,12 @@ void drm_sched_job_cleanup(struct drm_sched_job *job) } job->s_fence = NULL; + + xa_for_each(&job->dependencies, index, fence) { + dma_fence_put(fence); + } + xa_destroy(&job->dependencies); + } EXPORT_SYMBOL(drm_sched_job_cleanup); diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h index 83afc3aa8e2f..a47946f904b6 100644 --- a/include/drm/gpu_scheduler.h +++ b/include/drm/gpu_scheduler.h @@ -27,9 +27,12 @@ #include #include #include +#include #define MAX_WAIT_SCHED_ENTITY_Q_EMPTY msecs_to_jiffies(1000) +struct drm_gem_object; + struct drm_gpu_scheduler; struct drm_sched_rq; @@ -198,6 +201,17 @@ struct drm_sched_job { enum drm_sched_priority s_priority; struct drm_sched_entity *entity; struct dma_fence_cb cb; + /** + * @dependencies: + * + * Contains the dependencies as struct dma_fence for this job, see + * drm_sched_job_add_dependency() and + * drm_sched_job_add_implicit_dependencies(). + */ + struct xarray dependencies; + + /** @last_dependency: tracks @dependencies as they signal */ + unsigned long last_dependency; }; static inline bool drm_sched_invalidate_job(struct drm_sched_job *s_job, @@ -220,9 +234,15 @@ enum drm_gpu_sched_stat { */ struct drm_sched_backend_ops { /** - * @dependency: Called when the scheduler is considering scheduling - * this job next, to get another struct dma_fence for this job to - * block on. Once it returns NULL, run_job() may be called. + * @dependency: + * + * Called when the scheduler is considering scheduling this job next, to + * get another struct dma_fence for this job to block on. Once it + * returns NULL, run_job() may be called. + * + * If a driver exclusively uses drm_sched_job_add_dependency() and + * drm_sched_job_add_implicit_dependencies() this can be ommitted and + * left as NULL. */ struct dma_fence *(*dependency)(struct drm_sched_job *sched_job, struct drm_sched_entity *s_entity); @@ -349,6 +369,13 @@ int drm_sched_job_init(struct drm_sched_job *job, struct drm_sched_entity *entity, void *owner); void drm_sched_job_arm(struct drm_sched_job *job); +int drm_sched_job_add_dependency(struct drm_sched_job *job, + struct dma_fence *fence); +int drm_sched_job_add_implicit_dependencies(struct drm_sched_job *job, + struct drm_gem_object *obj, + bool write); + + void drm_sched_entity_modify_sched(struct drm_sched_entity *entity, struct drm_gpu_scheduler **sched_list, unsigned int num_sched_list); -- cgit v1.2.3 From 0e10e9a1db230ae98c8ccfeaf0734545421c3995 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Thu, 5 Aug 2021 12:46:50 +0200 Subject: drm/sched: drop entity parameter from drm_sched_push_job MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Originally a job was only bound to the queue when we pushed this, but now that's done in drm_sched_job_init, making that parameter entirely redundant. Remove it. The same applies to the context parameter in lima_sched_context_queue_task, simplify that too. v2: Rebase on top of msm adopting drm/sched Reviewed-by: Christian König Acked-by: Emma Anholt Acked-by: Melissa Wen Reviewed-by: Steven Price (v1) Reviewed-by: Boris Brezillon (v1) Signed-off-by: Daniel Vetter Cc: Lucas Stach Cc: Russell King Cc: Christian Gmeiner Cc: Qiang Yu Cc: Rob Herring Cc: Tomeu Vizoso Cc: Steven Price Cc: Alyssa Rosenzweig Cc: Emma Anholt Cc: David Airlie Cc: Daniel Vetter Cc: Sumit Semwal Cc: "Christian König" Cc: Alex Deucher Cc: Nirmoy Das Cc: Dave Airlie Cc: Chen Li Cc: Lee Jones Cc: Deepak R Varma Cc: Kevin Wang Cc: Luben Tuikov Cc: "Marek Olšák" Cc: Maarten Lankhorst Cc: Andrey Grodzovsky Cc: Dennis Li Cc: Boris Brezillon Cc: etnaviv@lists.freedesktop.org Cc: lima@lists.freedesktop.org Cc: linux-media@vger.kernel.org Cc: linaro-mm-sig@lists.linaro.org Cc: Rob Clark Cc: Sean Paul Cc: Melissa Wen Cc: linux-arm-msm@vger.kernel.org Cc: freedreno@lists.freedesktop.org Link: https://patchwork.freedesktop.org/patch/msgid/20210805104705.862416-6-daniel.vetter@ffwll.ch --- drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 2 +- drivers/gpu/drm/etnaviv/etnaviv_sched.c | 2 +- drivers/gpu/drm/lima/lima_gem.c | 3 +-- drivers/gpu/drm/lima/lima_sched.c | 5 ++--- drivers/gpu/drm/lima/lima_sched.h | 3 +-- drivers/gpu/drm/msm/msm_gem_submit.c | 2 +- drivers/gpu/drm/panfrost/panfrost_job.c | 2 +- drivers/gpu/drm/scheduler/sched_entity.c | 6 ++---- drivers/gpu/drm/v3d/v3d_gem.c | 2 +- include/drm/gpu_scheduler.h | 3 +-- 11 files changed, 13 insertions(+), 19 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index 2b7f4b77a572..617e39122ea3 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -1261,7 +1261,7 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p, trace_amdgpu_cs_ioctl(job); amdgpu_vm_bo_trace_cs(&fpriv->vm, &p->ticket); - drm_sched_entity_push_job(&job->base, entity); + drm_sched_entity_push_job(&job->base); amdgpu_vm_move_to_lru_tail(p->adev, &fpriv->vm); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c index 5ddb955d2315..b8609cccc9c1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c @@ -174,7 +174,7 @@ int amdgpu_job_submit(struct amdgpu_job *job, struct drm_sched_entity *entity, *f = dma_fence_get(&job->base.s_fence->finished); amdgpu_job_free_resources(job); - drm_sched_entity_push_job(&job->base, entity); + drm_sched_entity_push_job(&job->base); return 0; } diff --git a/drivers/gpu/drm/etnaviv/etnaviv_sched.c b/drivers/gpu/drm/etnaviv/etnaviv_sched.c index 05f412204118..180bb633d5c5 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_sched.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_sched.c @@ -178,7 +178,7 @@ int etnaviv_sched_push_job(struct drm_sched_entity *sched_entity, /* the scheduler holds on to the job now */ kref_get(&submit->refcount); - drm_sched_entity_push_job(&submit->sched_job, sched_entity); + drm_sched_entity_push_job(&submit->sched_job); out_unlock: mutex_unlock(&submit->gpu->fence_lock); diff --git a/drivers/gpu/drm/lima/lima_gem.c b/drivers/gpu/drm/lima/lima_gem.c index de62966243cd..c528f40981bb 100644 --- a/drivers/gpu/drm/lima/lima_gem.c +++ b/drivers/gpu/drm/lima/lima_gem.c @@ -359,8 +359,7 @@ int lima_gem_submit(struct drm_file *file, struct lima_submit *submit) goto err_out2; } - fence = lima_sched_context_queue_task( - submit->ctx->context + submit->pipe, submit->task); + fence = lima_sched_context_queue_task(submit->task); for (i = 0; i < submit->nr_bos; i++) { if (submit->bos[i].flags & LIMA_SUBMIT_BO_WRITE) diff --git a/drivers/gpu/drm/lima/lima_sched.c b/drivers/gpu/drm/lima/lima_sched.c index 38f755580507..e968b5a8f0b0 100644 --- a/drivers/gpu/drm/lima/lima_sched.c +++ b/drivers/gpu/drm/lima/lima_sched.c @@ -177,13 +177,12 @@ void lima_sched_context_fini(struct lima_sched_pipe *pipe, drm_sched_entity_fini(&context->base); } -struct dma_fence *lima_sched_context_queue_task(struct lima_sched_context *context, - struct lima_sched_task *task) +struct dma_fence *lima_sched_context_queue_task(struct lima_sched_task *task) { struct dma_fence *fence = dma_fence_get(&task->base.s_fence->finished); trace_lima_task_submit(task); - drm_sched_entity_push_job(&task->base, &context->base); + drm_sched_entity_push_job(&task->base); return fence; } diff --git a/drivers/gpu/drm/lima/lima_sched.h b/drivers/gpu/drm/lima/lima_sched.h index 90f03c48ef4a..ac70006b0e26 100644 --- a/drivers/gpu/drm/lima/lima_sched.h +++ b/drivers/gpu/drm/lima/lima_sched.h @@ -98,8 +98,7 @@ int lima_sched_context_init(struct lima_sched_pipe *pipe, atomic_t *guilty); void lima_sched_context_fini(struct lima_sched_pipe *pipe, struct lima_sched_context *context); -struct dma_fence *lima_sched_context_queue_task(struct lima_sched_context *context, - struct lima_sched_task *task); +struct dma_fence *lima_sched_context_queue_task(struct lima_sched_task *task); int lima_sched_pipe_init(struct lima_sched_pipe *pipe, const char *name); void lima_sched_pipe_fini(struct lima_sched_pipe *pipe); diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c index 71b8c8f752a3..37a8059ac798 100644 --- a/drivers/gpu/drm/msm/msm_gem_submit.c +++ b/drivers/gpu/drm/msm/msm_gem_submit.c @@ -908,7 +908,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, /* The scheduler owns a ref now: */ msm_gem_submit_get(submit); - drm_sched_entity_push_job(&submit->base, &queue->entity); + drm_sched_entity_push_job(&submit->base); args->fence = submit->fence_id; diff --git a/drivers/gpu/drm/panfrost/panfrost_job.c b/drivers/gpu/drm/panfrost/panfrost_job.c index aaa662cbc43b..42aa01445ee4 100644 --- a/drivers/gpu/drm/panfrost/panfrost_job.c +++ b/drivers/gpu/drm/panfrost/panfrost_job.c @@ -301,7 +301,7 @@ int panfrost_job_push(struct panfrost_job *job) kref_get(&job->refcount); /* put by scheduler job completion */ - drm_sched_entity_push_job(&job->base, entity); + drm_sched_entity_push_job(&job->base); mutex_unlock(&pfdev->sched_lock); diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c index 381fbf462ea7..e4d33db1eb45 100644 --- a/drivers/gpu/drm/scheduler/sched_entity.c +++ b/drivers/gpu/drm/scheduler/sched_entity.c @@ -516,9 +516,7 @@ void drm_sched_entity_select_rq(struct drm_sched_entity *entity) /** * drm_sched_entity_push_job - Submit a job to the entity's job queue - * * @sched_job: job to submit - * @entity: scheduler entity * * Note: To guarantee that the order of insertion to queue matches the job's * fence sequence number this function should be called with drm_sched_job_arm() @@ -526,9 +524,9 @@ void drm_sched_entity_select_rq(struct drm_sched_entity *entity) * * Returns 0 for success, negative error code otherwise. */ -void drm_sched_entity_push_job(struct drm_sched_job *sched_job, - struct drm_sched_entity *entity) +void drm_sched_entity_push_job(struct drm_sched_job *sched_job) { + struct drm_sched_entity *entity = sched_job->entity; bool first; trace_drm_sched_job(sched_job, entity); diff --git a/drivers/gpu/drm/v3d/v3d_gem.c b/drivers/gpu/drm/v3d/v3d_gem.c index 2e808097b4d1..957228bef29c 100644 --- a/drivers/gpu/drm/v3d/v3d_gem.c +++ b/drivers/gpu/drm/v3d/v3d_gem.c @@ -487,7 +487,7 @@ v3d_push_job(struct v3d_file_priv *v3d_priv, /* put by scheduler job completion */ kref_get(&job->refcount); - drm_sched_entity_push_job(&job->base, &v3d_priv->sched_entity[queue]); + drm_sched_entity_push_job(&job->base); return 0; } diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h index a47946f904b6..b72f73b375a2 100644 --- a/include/drm/gpu_scheduler.h +++ b/include/drm/gpu_scheduler.h @@ -409,8 +409,7 @@ void drm_sched_entity_fini(struct drm_sched_entity *entity); void drm_sched_entity_destroy(struct drm_sched_entity *entity); void drm_sched_entity_select_rq(struct drm_sched_entity *entity); struct drm_sched_job *drm_sched_entity_pop_job(struct drm_sched_entity *entity); -void drm_sched_entity_push_job(struct drm_sched_job *sched_job, - struct drm_sched_entity *entity); +void drm_sched_entity_push_job(struct drm_sched_job *sched_job); void drm_sched_entity_set_priority(struct drm_sched_entity *entity, enum drm_sched_priority priority); bool drm_sched_entity_is_ready(struct drm_sched_entity *entity); -- cgit v1.2.3 From 981b04d9685612b3831a89772f477058d2b3bd79 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Thu, 5 Aug 2021 12:46:51 +0200 Subject: drm/sched: improve docs around drm_sched_entity MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit I found a few too many things that are tricky and not documented, so I started typing. I found a few more things that looked broken while typing, see the varios FIXME in drm_sched_entity. Also some of the usual logics: - actually include sched_entity.c declarations, that was lost in the move here: 620e762f9a98 ("drm/scheduler: move entity handling into separate file") - Ditch the kerneldoc for internal functions, keep the comments where they're describing more than what the function name already implies. - Switch drm_sched_entity to inline docs. Acked-by: Melissa Wen Reviewed-by: Boris Brezillon (v1) Signed-off-by: Daniel Vetter Cc: Lucas Stach Cc: David Airlie Cc: Daniel Vetter Cc: Maarten Lankhorst Cc: Maxime Ripard Cc: Thomas Zimmermann Cc: "Christian König" Cc: Boris Brezillon Cc: Steven Price Cc: Emma Anholt Cc: Lee Jones Cc: Andrey Grodzovsky Link: https://patchwork.freedesktop.org/patch/msgid/20210805104705.862416-7-daniel.vetter@ffwll.ch --- Documentation/gpu/drm-mm.rst | 3 + drivers/gpu/drm/scheduler/sched_entity.c | 85 ++++++------------ include/drm/gpu_scheduler.h | 145 +++++++++++++++++++++++++------ 3 files changed, 146 insertions(+), 87 deletions(-) (limited to 'include') diff --git a/Documentation/gpu/drm-mm.rst b/Documentation/gpu/drm-mm.rst index d5a73fa2c9ef..0198fa43d254 100644 --- a/Documentation/gpu/drm-mm.rst +++ b/Documentation/gpu/drm-mm.rst @@ -504,3 +504,6 @@ Scheduler Function References .. kernel-doc:: drivers/gpu/drm/scheduler/sched_main.c :export: + +.. kernel-doc:: drivers/gpu/drm/scheduler/sched_entity.c + :export: diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c index e4d33db1eb45..27e1573af96e 100644 --- a/drivers/gpu/drm/scheduler/sched_entity.c +++ b/drivers/gpu/drm/scheduler/sched_entity.c @@ -45,8 +45,14 @@ * @guilty: atomic_t set to 1 when a job on this queue * is found to be guilty causing a timeout * - * Note: the sched_list should have at least one element to schedule - * the entity + * Note that the &sched_list must have at least one element to schedule the entity. + * + * For changing @priority later on at runtime see + * drm_sched_entity_set_priority(). For changing the set of schedulers + * @sched_list at runtime see drm_sched_entity_modify_sched(). + * + * An entity is cleaned up by callind drm_sched_entity_fini(). See also + * drm_sched_entity_destroy(). * * Returns 0 on success or a negative error code on failure. */ @@ -92,6 +98,11 @@ EXPORT_SYMBOL(drm_sched_entity_init); * @sched_list: the list of new drm scheds which will replace * existing entity->sched_list * @num_sched_list: number of drm sched in sched_list + * + * Note that this must be called under the same common lock for @entity as + * drm_sched_job_arm() and drm_sched_entity_push_job(), or the driver needs to + * guarantee through some other means that this is never called while new jobs + * can be pushed to @entity. */ void drm_sched_entity_modify_sched(struct drm_sched_entity *entity, struct drm_gpu_scheduler **sched_list, @@ -104,13 +115,6 @@ void drm_sched_entity_modify_sched(struct drm_sched_entity *entity, } EXPORT_SYMBOL(drm_sched_entity_modify_sched); -/** - * drm_sched_entity_is_idle - Check if entity is idle - * - * @entity: scheduler entity - * - * Returns true if the entity does not have any unscheduled jobs. - */ static bool drm_sched_entity_is_idle(struct drm_sched_entity *entity) { rmb(); /* for list_empty to work without lock */ @@ -123,13 +127,7 @@ static bool drm_sched_entity_is_idle(struct drm_sched_entity *entity) return false; } -/** - * drm_sched_entity_is_ready - Check if entity is ready - * - * @entity: scheduler entity - * - * Return true if entity could provide a job. - */ +/* Return true if entity could provide a job. */ bool drm_sched_entity_is_ready(struct drm_sched_entity *entity) { if (spsc_queue_peek(&entity->job_queue) == NULL) @@ -192,14 +190,7 @@ long drm_sched_entity_flush(struct drm_sched_entity *entity, long timeout) } EXPORT_SYMBOL(drm_sched_entity_flush); -/** - * drm_sched_entity_kill_jobs_cb - helper for drm_sched_entity_kill_jobs - * - * @f: signaled fence - * @cb: our callback structure - * - * Signal the scheduler finished fence when the entity in question is killed. - */ +/* Signal the scheduler finished fence when the entity in question is killed. */ static void drm_sched_entity_kill_jobs_cb(struct dma_fence *f, struct dma_fence_cb *cb) { @@ -224,14 +215,6 @@ drm_sched_job_dependency(struct drm_sched_job *job, return NULL; } -/** - * drm_sched_entity_kill_jobs - Make sure all remaining jobs are killed - * - * @entity: entity which is cleaned up - * - * Makes sure that all remaining jobs in an entity are killed before it is - * destroyed. - */ static void drm_sched_entity_kill_jobs(struct drm_sched_entity *entity) { struct drm_sched_job *job; @@ -273,9 +256,11 @@ static void drm_sched_entity_kill_jobs(struct drm_sched_entity *entity) * * @entity: scheduler entity * - * This should be called after @drm_sched_entity_do_release. It goes over the - * entity and signals all jobs with an error code if the process was killed. + * Cleanups up @entity which has been initialized by drm_sched_entity_init(). * + * If there are potentially job still in flight or getting newly queued + * drm_sched_entity_flush() must be called first. This function then goes over + * the entity and signals all jobs with an error code if the process was killed. */ void drm_sched_entity_fini(struct drm_sched_entity *entity) { @@ -315,10 +300,10 @@ EXPORT_SYMBOL(drm_sched_entity_fini); /** * drm_sched_entity_destroy - Destroy a context entity - * * @entity: scheduler entity * - * Calls drm_sched_entity_do_release() and drm_sched_entity_cleanup() + * Calls drm_sched_entity_flush() and drm_sched_entity_fini() as a + * convenience wrapper. */ void drm_sched_entity_destroy(struct drm_sched_entity *entity) { @@ -327,9 +312,7 @@ void drm_sched_entity_destroy(struct drm_sched_entity *entity) } EXPORT_SYMBOL(drm_sched_entity_destroy); -/* - * drm_sched_entity_clear_dep - callback to clear the entities dependency - */ +/* drm_sched_entity_clear_dep - callback to clear the entities dependency */ static void drm_sched_entity_clear_dep(struct dma_fence *f, struct dma_fence_cb *cb) { @@ -371,11 +354,7 @@ void drm_sched_entity_set_priority(struct drm_sched_entity *entity, } EXPORT_SYMBOL(drm_sched_entity_set_priority); -/** - * drm_sched_entity_add_dependency_cb - add callback for the entities dependency - * - * @entity: entity with dependency - * +/* * Add a callback to the current dependency of the entity to wake up the * scheduler when the entity becomes available. */ @@ -423,13 +402,6 @@ static bool drm_sched_entity_add_dependency_cb(struct drm_sched_entity *entity) return false; } -/** - * drm_sched_entity_pop_job - get a ready to be scheduled job from the entity - * - * @entity: entity to get the job from - * - * Process all dependencies and try to get one job from the entities queue. - */ struct drm_sched_job *drm_sched_entity_pop_job(struct drm_sched_entity *entity) { struct drm_sched_job *sched_job; @@ -465,14 +437,6 @@ struct drm_sched_job *drm_sched_entity_pop_job(struct drm_sched_entity *entity) return sched_job; } -/** - * drm_sched_entity_select_rq - select a new rq for the entity - * - * @entity: scheduler entity - * - * Check all prerequisites and select a new rq for the entity for load - * balancing. - */ void drm_sched_entity_select_rq(struct drm_sched_entity *entity) { struct dma_fence *fence; @@ -520,7 +484,8 @@ void drm_sched_entity_select_rq(struct drm_sched_entity *entity) * * Note: To guarantee that the order of insertion to queue matches the job's * fence sequence number this function should be called with drm_sched_job_arm() - * under common lock. + * under common lock for the struct drm_sched_entity that was set up for + * @sched_job in drm_sched_job_init(). * * Returns 0 for success, negative error code otherwise. */ diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h index b72f73b375a2..7f77a455722c 100644 --- a/include/drm/gpu_scheduler.h +++ b/include/drm/gpu_scheduler.h @@ -53,56 +53,147 @@ enum drm_sched_priority { * struct drm_sched_entity - A wrapper around a job queue (typically * attached to the DRM file_priv). * - * @list: used to append this struct to the list of entities in the - * runqueue. - * @rq: runqueue on which this entity is currently scheduled. - * @sched_list: A list of schedulers (drm_gpu_schedulers). - * Jobs from this entity can be scheduled on any scheduler - * on this list. - * @num_sched_list: number of drm_gpu_schedulers in the sched_list. - * @priority: priority of the entity - * @rq_lock: lock to modify the runqueue to which this entity belongs. - * @job_queue: the list of jobs of this entity. - * @fence_seq: a linearly increasing seqno incremented with each - * new &drm_sched_fence which is part of the entity. - * @fence_context: a unique context for all the fences which belong - * to this entity. - * The &drm_sched_fence.scheduled uses the - * fence_context but &drm_sched_fence.finished uses - * fence_context + 1. - * @dependency: the dependency fence of the job which is on the top - * of the job queue. - * @cb: callback for the dependency fence above. - * @guilty: points to ctx's guilty. - * @fini_status: contains the exit status in case the process was signalled. - * @last_scheduled: points to the finished fence of the last scheduled job. - * @last_user: last group leader pushing a job into the entity. - * @stopped: Marks the enity as removed from rq and destined for termination. - * @entity_idle: Signals when enityt is not in use - * * Entities will emit jobs in order to their corresponding hardware * ring, and the scheduler will alternate between entities based on * scheduling policy. */ struct drm_sched_entity { + /** + * @list: + * + * Used to append this struct to the list of entities in the runqueue + * @rq under &drm_sched_rq.entities. + * + * Protected by &drm_sched_rq.lock of @rq. + */ struct list_head list; + + /** + * @rq: + * + * Runqueue on which this entity is currently scheduled. + * + * FIXME: Locking is very unclear for this. Writers are protected by + * @rq_lock, but readers are generally lockless and seem to just race + * with not even a READ_ONCE. + */ struct drm_sched_rq *rq; + + /** + * @sched_list: + * + * A list of schedulers (struct drm_gpu_scheduler). Jobs from this entity can + * be scheduled on any scheduler on this list. + * + * This can be modified by calling drm_sched_entity_modify_sched(). + * Locking is entirely up to the driver, see the above function for more + * details. + * + * This will be set to NULL if &num_sched_list equals 1 and @rq has been + * set already. + * + * FIXME: This means priority changes through + * drm_sched_entity_set_priority() will be lost henceforth in this case. + */ struct drm_gpu_scheduler **sched_list; + + /** + * @num_sched_list: + * + * Number of drm_gpu_schedulers in the @sched_list. + */ unsigned int num_sched_list; + + /** + * @priority: + * + * Priority of the entity. This can be modified by calling + * drm_sched_entity_set_priority(). Protected by &rq_lock. + */ enum drm_sched_priority priority; + + /** + * @rq_lock: + * + * Lock to modify the runqueue to which this entity belongs. + */ spinlock_t rq_lock; + /** + * @job_queue: the list of jobs of this entity. + */ struct spsc_queue job_queue; + /** + * @fence_seq: + * + * A linearly increasing seqno incremented with each new + * &drm_sched_fence which is part of the entity. + * + * FIXME: Callers of drm_sched_job_arm() need to ensure correct locking, + * this doesn't need to be atomic. + */ atomic_t fence_seq; + + /** + * @fence_context: + * + * A unique context for all the fences which belong to this entity. The + * &drm_sched_fence.scheduled uses the fence_context but + * &drm_sched_fence.finished uses fence_context + 1. + */ uint64_t fence_context; + /** + * @dependency: + * + * The dependency fence of the job which is on the top of the job queue. + */ struct dma_fence *dependency; + + /** + * @cb: + * + * Callback for the dependency fence above. + */ struct dma_fence_cb cb; + + /** + * @guilty: + * + * Points to entities' guilty. + */ atomic_t *guilty; + + /** + * @last_scheduled: + * + * Points to the finished fence of the last scheduled job. Only written + * by the scheduler thread, can be accessed locklessly from + * drm_sched_job_arm() iff the queue is empty. + */ struct dma_fence *last_scheduled; + + /** + * @last_user: last group leader pushing a job into the entity. + */ struct task_struct *last_user; + + /** + * @stopped: + * + * Marks the enity as removed from rq and destined for + * termination. This is set by calling drm_sched_entity_flush() and by + * drm_sched_fini(). + */ bool stopped; + + /** + * @entity_idle: + * + * Signals when entity is not in use, used to sequence entity cleanup in + * drm_sched_entity_fini(). + */ struct completion entity_idle; }; -- cgit v1.2.3 From d9edf92d496b61e5ac75b2b0aba5ea6c7f7ecdca Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Thu, 5 Aug 2021 12:47:05 +0200 Subject: dma-resv: Give the docs a do-over MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Specifically document the new/clarified rules around how the shared fences do not have any ordering requirements against the exclusive fence. But also document all the things a bit better, given how central struct dma_resv to dynamic buffer management the docs have been very inadequat. - Lots more links to other pieces of the puzzle. Unfortunately ttm_buffer_object has no docs, so no links :-( - Explain/complain a bit about dma_resv_locking_ctx(). I still don't like that one, but fixing the ttm call chains is going to be horrible. Plus we want to plug in real slowpath locking when we do that anyway. - Main part of the patch is some actual docs for struct dma_resv. Overall I think we still have a lot of bad naming in this area (e.g. dma_resv.fence is singular, but contains the multiple shared fences), but I think that's more indicative of how the semantics and rules are just not great. Another thing that's real awkard is how chaining exclusive fences right now means direct dma_resv.exclusive_fence pointer access with an rcu_assign_pointer. Not so great either. v2: - Fix a pile of typos (Matt, Jason) - Hammer it in that breaking the rules leads to use-after-free issues around dma-buf sharing (Christian) Reviewed-by: Christian König Cc: Jason Ekstrand Cc: Matthew Auld Reviewed-by: Matthew Auld Signed-off-by: Daniel Vetter Cc: Sumit Semwal Cc: "Christian König" Cc: linux-media@vger.kernel.org Cc: linaro-mm-sig@lists.linaro.org Link: https://patchwork.freedesktop.org/patch/msgid/20210805104705.862416-21-daniel.vetter@ffwll.ch --- drivers/dma-buf/dma-resv.c | 24 ++++++++--- include/linux/dma-buf.h | 7 +++ include/linux/dma-resv.h | 104 ++++++++++++++++++++++++++++++++++++++++++--- 3 files changed, 124 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/drivers/dma-buf/dma-resv.c b/drivers/dma-buf/dma-resv.c index e744fd87c63c..84fbe60629e3 100644 --- a/drivers/dma-buf/dma-resv.c +++ b/drivers/dma-buf/dma-resv.c @@ -48,6 +48,8 @@ * write operations) or N shared fences (read operations). The RCU * mechanism is used to protect read access to fences from locked * write-side updates. + * + * See struct dma_resv for more details. */ DEFINE_WD_CLASS(reservation_ww_class); @@ -137,7 +139,11 @@ EXPORT_SYMBOL(dma_resv_fini); * @num_fences: number of fences we want to add * * Should be called before dma_resv_add_shared_fence(). Must - * be called with obj->lock held. + * be called with @obj locked through dma_resv_lock(). + * + * Note that the preallocated slots need to be re-reserved if @obj is unlocked + * at any time before calling dma_resv_add_shared_fence(). This is validated + * when CONFIG_DEBUG_MUTEXES is enabled. * * RETURNS * Zero for success, or -errno @@ -234,8 +240,10 @@ EXPORT_SYMBOL(dma_resv_reset_shared_max); * @obj: the reservation object * @fence: the shared fence to add * - * Add a fence to a shared slot, obj->lock must be held, and + * Add a fence to a shared slot, @obj must be locked with dma_resv_lock(), and * dma_resv_reserve_shared() has been called. + * + * See also &dma_resv.fence for a discussion of the semantics. */ void dma_resv_add_shared_fence(struct dma_resv *obj, struct dma_fence *fence) { @@ -278,9 +286,11 @@ EXPORT_SYMBOL(dma_resv_add_shared_fence); /** * dma_resv_add_excl_fence - Add an exclusive fence. * @obj: the reservation object - * @fence: the shared fence to add + * @fence: the exclusive fence to add * - * Add a fence to the exclusive slot. The obj->lock must be held. + * Add a fence to the exclusive slot. @obj must be locked with dma_resv_lock(). + * Note that this function replaces all fences attached to @obj, see also + * &dma_resv.fence_excl for a discussion of the semantics. */ void dma_resv_add_excl_fence(struct dma_resv *obj, struct dma_fence *fence) { @@ -609,9 +619,11 @@ static inline int dma_resv_test_signaled_single(struct dma_fence *passed_fence) * fence * * Callers are not required to hold specific locks, but maybe hold - * dma_resv_lock() already + * dma_resv_lock() already. + * * RETURNS - * true if all fences signaled, else false + * + * True if all fences signaled, else false. */ bool dma_resv_test_signaled(struct dma_resv *obj, bool test_all) { diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index 8b32b4bdd590..66470c37e471 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -420,6 +420,13 @@ struct dma_buf { * - Dynamic importers should set fences for any access that they can't * disable immediately from their &dma_buf_attach_ops.move_notify * callback. + * + * IMPORTANT: + * + * All drivers must obey the struct dma_resv rules, specifically the + * rules for updating fences, see &dma_resv.fence_excl and + * &dma_resv.fence. If these dependency rules are broken access tracking + * can be lost resulting in use after free issues. */ struct dma_resv *resv; diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h index e1ca2080a1ff..9100dd3dc21f 100644 --- a/include/linux/dma-resv.h +++ b/include/linux/dma-resv.h @@ -62,16 +62,90 @@ struct dma_resv_list { /** * struct dma_resv - a reservation object manages fences for a buffer - * @lock: update side lock - * @seq: sequence count for managing RCU read-side synchronization - * @fence_excl: the exclusive fence, if there is one currently - * @fence: list of current shared fences + * + * There are multiple uses for this, with sometimes slightly different rules in + * how the fence slots are used. + * + * One use is to synchronize cross-driver access to a struct dma_buf, either for + * dynamic buffer management or just to handle implicit synchronization between + * different users of the buffer in userspace. See &dma_buf.resv for a more + * in-depth discussion. + * + * The other major use is to manage access and locking within a driver in a + * buffer based memory manager. struct ttm_buffer_object is the canonical + * example here, since this is where reservation objects originated from. But + * use in drivers is spreading and some drivers also manage struct + * drm_gem_object with the same scheme. */ struct dma_resv { + /** + * @lock: + * + * Update side lock. Don't use directly, instead use the wrapper + * functions like dma_resv_lock() and dma_resv_unlock(). + * + * Drivers which use the reservation object to manage memory dynamically + * also use this lock to protect buffer object state like placement, + * allocation policies or throughout command submission. + */ struct ww_mutex lock; + + /** + * @seq: + * + * Sequence count for managing RCU read-side synchronization, allows + * read-only access to @fence_excl and @fence while ensuring we take a + * consistent snapshot. + */ seqcount_ww_mutex_t seq; + /** + * @fence_excl: + * + * The exclusive fence, if there is one currently. + * + * There are two ways to update this fence: + * + * - First by calling dma_resv_add_excl_fence(), which replaces all + * fences attached to the reservation object. To guarantee that no + * fences are lost, this new fence must signal only after all previous + * fences, both shared and exclusive, have signalled. In some cases it + * is convenient to achieve that by attaching a struct dma_fence_array + * with all the new and old fences. + * + * - Alternatively the fence can be set directly, which leaves the + * shared fences unchanged. To guarantee that no fences are lost, this + * new fence must signal only after the previous exclusive fence has + * signalled. Since the shared fences are staying intact, it is not + * necessary to maintain any ordering against those. If semantically + * only a new access is added without actually treating the previous + * one as a dependency the exclusive fences can be strung together + * using struct dma_fence_chain. + * + * Note that actual semantics of what an exclusive or shared fence mean + * is defined by the user, for reservation objects shared across drivers + * see &dma_buf.resv. + */ struct dma_fence __rcu *fence_excl; + + /** + * @fence: + * + * List of current shared fences. + * + * There are no ordering constraints of shared fences against the + * exclusive fence slot. If a waiter needs to wait for all access, it + * has to wait for both sets of fences to signal. + * + * A new fence is added by calling dma_resv_add_shared_fence(). Since + * this often needs to be done past the point of no return in command + * submission it cannot fail, and therefore sufficient slots need to be + * reserved by calling dma_resv_reserve_shared(). + * + * Note that actual semantics of what an exclusive or shared fence mean + * is defined by the user, for reservation objects shared across drivers + * see &dma_buf.resv. + */ struct dma_resv_list __rcu *fence; }; @@ -98,6 +172,13 @@ static inline void dma_resv_reset_shared_max(struct dma_resv *obj) {} * undefined order, a #ww_acquire_ctx is passed to unwind if a cycle * is detected. See ww_mutex_lock() and ww_acquire_init(). A reservation * object may be locked by itself by passing NULL as @ctx. + * + * When a die situation is indicated by returning -EDEADLK all locks held by + * @ctx must be unlocked and then dma_resv_lock_slow() called on @obj. + * + * Unlocked by calling dma_resv_unlock(). + * + * See also dma_resv_lock_interruptible() for the interruptible variant. */ static inline int dma_resv_lock(struct dma_resv *obj, struct ww_acquire_ctx *ctx) @@ -119,6 +200,12 @@ static inline int dma_resv_lock(struct dma_resv *obj, * undefined order, a #ww_acquire_ctx is passed to unwind if a cycle * is detected. See ww_mutex_lock() and ww_acquire_init(). A reservation * object may be locked by itself by passing NULL as @ctx. + * + * When a die situation is indicated by returning -EDEADLK all locks held by + * @ctx must be unlocked and then dma_resv_lock_slow_interruptible() called on + * @obj. + * + * Unlocked by calling dma_resv_unlock(). */ static inline int dma_resv_lock_interruptible(struct dma_resv *obj, struct ww_acquire_ctx *ctx) @@ -134,6 +221,8 @@ static inline int dma_resv_lock_interruptible(struct dma_resv *obj, * Acquires the reservation object after a die case. This function * will sleep until the lock becomes available. See dma_resv_lock() as * well. + * + * See also dma_resv_lock_slow_interruptible() for the interruptible variant. */ static inline void dma_resv_lock_slow(struct dma_resv *obj, struct ww_acquire_ctx *ctx) @@ -167,7 +256,7 @@ static inline int dma_resv_lock_slow_interruptible(struct dma_resv *obj, * if they overlap with a writer. * * Also note that since no context is provided, no deadlock protection is - * possible. + * possible, which is also not needed for a trylock. * * Returns true if the lock was acquired, false otherwise. */ @@ -193,6 +282,11 @@ static inline bool dma_resv_is_locked(struct dma_resv *obj) * * Returns the context used to lock a reservation object or NULL if no context * was used or the object is not locked at all. + * + * WARNING: This interface is pretty horrible, but TTM needs it because it + * doesn't pass the struct ww_acquire_ctx around in some very long callchains. + * Everyone else just uses it to check whether they're holding a reservation or + * not. */ static inline struct ww_acquire_ctx *dma_resv_locking_ctx(struct dma_resv *obj) { -- cgit v1.2.3 From 32eadf52d4491f005d188ade02d17c60916df8c2 Mon Sep 17 00:00:00 2001 From: Andrey Grodzovsky Date: Tue, 24 Aug 2021 16:13:13 -0400 Subject: drm/ttm: Create pinned list MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This list will be used to capture all non VRAM BOs not on LRU so when device is hot unplugged we can iterate the list and unmap DMA mappings before device is removed. v2: Reanme function to ttm_bo_move_to_pinned v3: Move the pinned list to ttm device Signed-off-by: Andrey Grodzovsky Suggested-by: Christian König Reviewed-by: Christian König Link: https://patchwork.freedesktop.org/patch/451614/?series=93971 --- drivers/gpu/drm/ttm/ttm_bo.c | 18 ++++++++++++++---- drivers/gpu/drm/ttm/ttm_device.c | 1 + include/drm/ttm/ttm_device.h | 1 + 3 files changed, 16 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index 49f4bc97c35a..3573f9e393be 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -69,7 +69,17 @@ static void ttm_bo_mem_space_debug(struct ttm_buffer_object *bo, } } -static void ttm_bo_del_from_lru(struct ttm_buffer_object *bo) +static inline void ttm_bo_move_to_pinned(struct ttm_buffer_object *bo) +{ + struct ttm_device *bdev = bo->bdev; + + list_move_tail(&bo->lru, &bdev->pinned); + + if (bdev->funcs->del_from_lru_notify) + bdev->funcs->del_from_lru_notify(bo); +} + +static inline void ttm_bo_del_from_lru(struct ttm_buffer_object *bo) { struct ttm_device *bdev = bo->bdev; @@ -98,7 +108,7 @@ void ttm_bo_move_to_lru_tail(struct ttm_buffer_object *bo, dma_resv_assert_held(bo->base.resv); if (bo->pin_count) { - ttm_bo_del_from_lru(bo); + ttm_bo_move_to_pinned(bo); return; } @@ -342,7 +352,7 @@ static int ttm_bo_cleanup_refs(struct ttm_buffer_object *bo, return ret; } - ttm_bo_del_from_lru(bo); + ttm_bo_move_to_pinned(bo); list_del_init(&bo->ddestroy); spin_unlock(&bo->bdev->lru_lock); ttm_bo_cleanup_memtype_use(bo); @@ -1165,7 +1175,7 @@ int ttm_bo_swapout(struct ttm_buffer_object *bo, struct ttm_operation_ctx *ctx, return 0; } - ttm_bo_del_from_lru(bo); + ttm_bo_move_to_pinned(bo); /* TODO: Cleanup the locking */ spin_unlock(&bo->bdev->lru_lock); diff --git a/drivers/gpu/drm/ttm/ttm_device.c b/drivers/gpu/drm/ttm/ttm_device.c index 519deea8e39b..9eb8f54b66fc 100644 --- a/drivers/gpu/drm/ttm/ttm_device.c +++ b/drivers/gpu/drm/ttm/ttm_device.c @@ -210,6 +210,7 @@ int ttm_device_init(struct ttm_device *bdev, struct ttm_device_funcs *funcs, INIT_DELAYED_WORK(&bdev->wq, ttm_device_delayed_workqueue); spin_lock_init(&bdev->lru_lock); INIT_LIST_HEAD(&bdev->ddestroy); + INIT_LIST_HEAD(&bdev->pinned); bdev->dev_mapping = mapping; mutex_lock(&ttm_global_mutex); list_add_tail(&bdev->device_list, &glob->device_list); diff --git a/include/drm/ttm/ttm_device.h b/include/drm/ttm/ttm_device.h index cd592f8e941b..03fb44d061e0 100644 --- a/include/drm/ttm/ttm_device.h +++ b/include/drm/ttm/ttm_device.h @@ -265,6 +265,7 @@ struct ttm_device { */ spinlock_t lru_lock; struct list_head ddestroy; + struct list_head pinned; /* * Protected by load / firstopen / lastclose /unload sync. -- cgit v1.2.3 From c97f082c135210da06a82c373fb660f8bfd57d95 Mon Sep 17 00:00:00 2001 From: Andrey Grodzovsky Date: Fri, 27 Aug 2021 16:39:08 -0400 Subject: drm/ttm: Clear all DMA mappings on demand MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Used by drivers supporting hot unplug to handle all DMA IOMMU group related dependencies before the group is removed during device removal and we try to access it after free when last device pointer from user space is dropped. v3: Switch to ttm_bo_get_unless_zerom Iterate bdev for pinned list Switch to ttm_tt_unpopulate Signed-off-by: Andrey Grodzovsky Reviewed-by: Christian König Link: https://patchwork.freedesktop.org/patch/msgid/20210827203910.5565-3-andrey.grodzovsky@amd.com --- drivers/gpu/drm/ttm/ttm_device.c | 47 ++++++++++++++++++++++++++++++++++++++++ include/drm/ttm/ttm_device.h | 1 + 2 files changed, 48 insertions(+) (limited to 'include') diff --git a/drivers/gpu/drm/ttm/ttm_device.c b/drivers/gpu/drm/ttm/ttm_device.c index 9eb8f54b66fc..a021d029b730 100644 --- a/drivers/gpu/drm/ttm/ttm_device.c +++ b/drivers/gpu/drm/ttm/ttm_device.c @@ -248,3 +248,50 @@ void ttm_device_fini(struct ttm_device *bdev) ttm_global_release(); } EXPORT_SYMBOL(ttm_device_fini); + +void ttm_device_clear_dma_mappings(struct ttm_device *bdev) +{ + struct ttm_resource_manager *man; + struct ttm_buffer_object *bo; + unsigned int i, j; + + spin_lock(&bdev->lru_lock); + while (!list_empty(&bdev->pinned)) { + bo = list_first_entry(&bdev->pinned, struct ttm_buffer_object, lru); + /* Take ref against racing releases once lru_lock is unlocked */ + if (ttm_bo_get_unless_zero(bo)) { + list_del_init(&bo->lru); + spin_unlock(&bdev->lru_lock); + + if (bo->ttm) + ttm_tt_unpopulate(bo->bdev, bo->ttm); + + ttm_bo_put(bo); + spin_lock(&bdev->lru_lock); + } + } + + for (i = TTM_PL_SYSTEM; i < TTM_NUM_MEM_TYPES; ++i) { + man = ttm_manager_type(bdev, i); + if (!man || !man->use_tt) + continue; + + for (j = 0; j < TTM_MAX_BO_PRIORITY; ++j) { + while (!list_empty(&man->lru[j])) { + bo = list_first_entry(&man->lru[j], struct ttm_buffer_object, lru); + if (ttm_bo_get_unless_zero(bo)) { + list_del_init(&bo->lru); + spin_unlock(&bdev->lru_lock); + + if (bo->ttm) + ttm_tt_unpopulate(bo->bdev, bo->ttm); + + ttm_bo_put(bo); + spin_lock(&bdev->lru_lock); + } + } + } + } + spin_unlock(&bdev->lru_lock); +} +EXPORT_SYMBOL(ttm_device_clear_dma_mappings); diff --git a/include/drm/ttm/ttm_device.h b/include/drm/ttm/ttm_device.h index 03fb44d061e0..07d722950d5b 100644 --- a/include/drm/ttm/ttm_device.h +++ b/include/drm/ttm/ttm_device.h @@ -299,5 +299,6 @@ int ttm_device_init(struct ttm_device *bdev, struct ttm_device_funcs *funcs, struct drm_vma_offset_manager *vma_manager, bool use_dma_alloc, bool use_dma32); void ttm_device_fini(struct ttm_device *bdev); +void ttm_device_clear_dma_mappings(struct ttm_device *bdev); #endif -- cgit v1.2.3 From d72277b6c37db66b457fd6b77aabd5e930d58687 Mon Sep 17 00:00:00 2001 From: Christian König Date: Thu, 29 Jul 2021 08:39:31 +0200 Subject: dma-buf: nuke DMA_FENCE_TRACE macros v2 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Only the DRM GPU scheduler, radeon and amdgpu where using them and they depend on a non existing config option to actually emit some code. v2: keep the signal path as is for now Signed-off-by: Christian König Acked-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20210818105443.1578-1-christian.koenig@amd.com --- drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c | 10 +--------- drivers/gpu/drm/radeon/radeon_fence.c | 24 ++++-------------------- drivers/gpu/drm/scheduler/sched_fence.c | 18 ++---------------- include/linux/dma-fence.h | 22 ---------------------- 4 files changed, 7 insertions(+), 67 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c index 0b1c48590c43..c65994e382bd 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c @@ -246,7 +246,6 @@ bool amdgpu_fence_process(struct amdgpu_ring *ring) struct amdgpu_fence_driver *drv = &ring->fence_drv; struct amdgpu_device *adev = ring->adev; uint32_t seq, last_seq; - int r; do { last_seq = atomic_read(&ring->fence_drv.last_seq); @@ -278,12 +277,7 @@ bool amdgpu_fence_process(struct amdgpu_ring *ring) if (!fence) continue; - r = dma_fence_signal(fence); - if (!r) - DMA_FENCE_TRACE(fence, "signaled from irq context\n"); - else - BUG(); - + dma_fence_signal(fence); dma_fence_put(fence); pm_runtime_mark_last_busy(adev_to_drm(adev)->dev); pm_runtime_put_autosuspend(adev_to_drm(adev)->dev); @@ -639,8 +633,6 @@ static bool amdgpu_fence_enable_signaling(struct dma_fence *f) if (!timer_pending(&ring->fence_drv.fallback_timer)) amdgpu_fence_schedule_fallback(ring); - DMA_FENCE_TRACE(&fence->base, "armed on ring %i!\n", ring->idx); - return true; } diff --git a/drivers/gpu/drm/radeon/radeon_fence.c b/drivers/gpu/drm/radeon/radeon_fence.c index 18f2c2e0dfb3..3f351d222cbb 100644 --- a/drivers/gpu/drm/radeon/radeon_fence.c +++ b/drivers/gpu/drm/radeon/radeon_fence.c @@ -176,18 +176,11 @@ static int radeon_fence_check_signaled(wait_queue_entry_t *wait, unsigned mode, */ seq = atomic64_read(&fence->rdev->fence_drv[fence->ring].last_seq); if (seq >= fence->seq) { - int ret = dma_fence_signal_locked(&fence->base); - - if (!ret) - DMA_FENCE_TRACE(&fence->base, "signaled from irq context\n"); - else - DMA_FENCE_TRACE(&fence->base, "was already signaled\n"); - + dma_fence_signal_locked(&fence->base); radeon_irq_kms_sw_irq_put(fence->rdev, fence->ring); __remove_wait_queue(&fence->rdev->fence_queue, &fence->fence_wake); dma_fence_put(&fence->base); - } else - DMA_FENCE_TRACE(&fence->base, "pending\n"); + } return 0; } @@ -422,8 +415,6 @@ static bool radeon_fence_enable_signaling(struct dma_fence *f) fence->fence_wake.func = radeon_fence_check_signaled; __add_wait_queue(&rdev->fence_queue, &fence->fence_wake); dma_fence_get(f); - - DMA_FENCE_TRACE(&fence->base, "armed on ring %i!\n", fence->ring); return true; } @@ -441,11 +432,7 @@ bool radeon_fence_signaled(struct radeon_fence *fence) return true; if (radeon_fence_seq_signaled(fence->rdev, fence->seq, fence->ring)) { - int ret; - - ret = dma_fence_signal(&fence->base); - if (!ret) - DMA_FENCE_TRACE(&fence->base, "signaled from radeon_fence_signaled\n"); + dma_fence_signal(&fence->base); return true; } return false; @@ -550,7 +537,6 @@ long radeon_fence_wait_timeout(struct radeon_fence *fence, bool intr, long timeo { uint64_t seq[RADEON_NUM_RINGS] = {}; long r; - int r_sig; /* * This function should not be called on !radeon fences. @@ -567,9 +553,7 @@ long radeon_fence_wait_timeout(struct radeon_fence *fence, bool intr, long timeo return r; } - r_sig = dma_fence_signal(&fence->base); - if (!r_sig) - DMA_FENCE_TRACE(&fence->base, "signaled from fence_wait\n"); + dma_fence_signal(&fence->base); return r; } diff --git a/drivers/gpu/drm/scheduler/sched_fence.c b/drivers/gpu/drm/scheduler/sched_fence.c index bcea035cf4c6..db3fd1303fc4 100644 --- a/drivers/gpu/drm/scheduler/sched_fence.c +++ b/drivers/gpu/drm/scheduler/sched_fence.c @@ -50,26 +50,12 @@ static void __exit drm_sched_fence_slab_fini(void) void drm_sched_fence_scheduled(struct drm_sched_fence *fence) { - int ret = dma_fence_signal(&fence->scheduled); - - if (!ret) - DMA_FENCE_TRACE(&fence->scheduled, - "signaled from irq context\n"); - else - DMA_FENCE_TRACE(&fence->scheduled, - "was already signaled\n"); + dma_fence_signal(&fence->scheduled); } void drm_sched_fence_finished(struct drm_sched_fence *fence) { - int ret = dma_fence_signal(&fence->finished); - - if (!ret) - DMA_FENCE_TRACE(&fence->finished, - "signaled from irq context\n"); - else - DMA_FENCE_TRACE(&fence->finished, - "was already signaled\n"); + dma_fence_signal(&fence->finished); } static const char *drm_sched_fence_get_driver_name(struct dma_fence *fence) diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h index 6ffb4b2c6371..4cc119ab272f 100644 --- a/include/linux/dma-fence.h +++ b/include/linux/dma-fence.h @@ -590,26 +590,4 @@ struct dma_fence *dma_fence_get_stub(void); struct dma_fence *dma_fence_allocate_private_stub(void); u64 dma_fence_context_alloc(unsigned num); -#define DMA_FENCE_TRACE(f, fmt, args...) \ - do { \ - struct dma_fence *__ff = (f); \ - if (IS_ENABLED(CONFIG_DMA_FENCE_TRACE)) \ - pr_info("f %llu#%llu: " fmt, \ - __ff->context, __ff->seqno, ##args); \ - } while (0) - -#define DMA_FENCE_WARN(f, fmt, args...) \ - do { \ - struct dma_fence *__ff = (f); \ - pr_warn("f %llu#%llu: " fmt, __ff->context, __ff->seqno,\ - ##args); \ - } while (0) - -#define DMA_FENCE_ERR(f, fmt, args...) \ - do { \ - struct dma_fence *__ff = (f); \ - pr_err("f %llu#%llu: " fmt, __ff->context, __ff->seqno, \ - ##args); \ - } while (0) - #endif /* __LINUX_DMA_FENCE_H */ -- cgit v1.2.3 From b83dcd753dbe42d5e7467ab65124f3d0a6002dc3 Mon Sep 17 00:00:00 2001 From: Christian König Date: Wed, 21 Jul 2021 11:01:04 +0200 Subject: dma-buf: clarify dma_fence_ops->wait documentation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This callback is pretty much deprecated and should not be used by new implementations. Clarify that in the documentation as well. Signed-off-by: Christian König Reviewed-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20210901120240.7339-2-christian.koenig@amd.com --- include/linux/dma-fence.h | 10 +++------- 1 file changed, 3 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h index 4cc119ab272f..a706b7bf51d7 100644 --- a/include/linux/dma-fence.h +++ b/include/linux/dma-fence.h @@ -214,19 +214,15 @@ struct dma_fence_ops { * Custom wait implementation, defaults to dma_fence_default_wait() if * not set. * - * The dma_fence_default_wait implementation should work for any fence, as long - * as @enable_signaling works correctly. This hook allows drivers to - * have an optimized version for the case where a process context is - * already available, e.g. if @enable_signaling for the general case - * needs to set up a worker thread. + * Deprecated and should not be used by new implementations. Only used + * by existing implementations which need special handling for their + * hardware reset procedure. * * Must return -ERESTARTSYS if the wait is intr = true and the wait was * interrupted, and remaining jiffies if fence has signaled, or 0 if wait * timed out. Can also return other error values on custom implementations, * which should be treated as if the fence is signaled. For example a hardware * lockup could be reported like that. - * - * This callback is optional. */ signed long (*wait)(struct dma_fence *fence, bool intr, signed long timeout); -- cgit v1.2.3 From 98cca519df6da699240403721f5d251ecf702b3b Mon Sep 17 00:00:00 2001 From: Christian König Date: Mon, 30 Aug 2021 13:17:10 +0200 Subject: drm/ttm: cleanup ttm_resource_compat MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Move that function into the resource handling and remove an unused parameter. Signed-off-by: Christian König Reviewed-by: Huang Rui Link: https://patchwork.freedesktop.org/patch/msgid/20210831112110.113196-1-christian.koenig@amd.com --- drivers/gpu/drm/ttm/ttm_bo.c | 48 +------------------------------------ drivers/gpu/drm/ttm/ttm_resource.c | 49 ++++++++++++++++++++++++++++++++++++++ drivers/gpu/drm/vmwgfx/vmwgfx_bo.c | 15 +++++------- include/drm/ttm/ttm_bo_api.h | 12 ---------- include/drm/ttm/ttm_resource.h | 3 +++ 5 files changed, 59 insertions(+), 68 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index 3573f9e393be..0a3127436f61 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -924,57 +924,11 @@ out: return ret; } -static bool ttm_bo_places_compat(const struct ttm_place *places, - unsigned num_placement, - struct ttm_resource *mem, - uint32_t *new_flags) -{ - unsigned i; - - if (mem->placement & TTM_PL_FLAG_TEMPORARY) - return false; - - for (i = 0; i < num_placement; i++) { - const struct ttm_place *heap = &places[i]; - - if ((mem->start < heap->fpfn || - (heap->lpfn != 0 && (mem->start + mem->num_pages) > heap->lpfn))) - continue; - - *new_flags = heap->flags; - if ((mem->mem_type == heap->mem_type) && - (!(*new_flags & TTM_PL_FLAG_CONTIGUOUS) || - (mem->placement & TTM_PL_FLAG_CONTIGUOUS))) - return true; - } - return false; -} - -bool ttm_bo_mem_compat(struct ttm_placement *placement, - struct ttm_resource *mem, - uint32_t *new_flags) -{ - if (ttm_bo_places_compat(placement->placement, placement->num_placement, - mem, new_flags)) - return true; - - if ((placement->busy_placement != placement->placement || - placement->num_busy_placement > placement->num_placement) && - ttm_bo_places_compat(placement->busy_placement, - placement->num_busy_placement, - mem, new_flags)) - return true; - - return false; -} -EXPORT_SYMBOL(ttm_bo_mem_compat); - int ttm_bo_validate(struct ttm_buffer_object *bo, struct ttm_placement *placement, struct ttm_operation_ctx *ctx) { int ret; - uint32_t new_flags; dma_resv_assert_held(bo->base.resv); @@ -987,7 +941,7 @@ int ttm_bo_validate(struct ttm_buffer_object *bo, /* * Check whether we need to move buffer. */ - if (!ttm_bo_mem_compat(placement, bo->resource, &new_flags)) { + if (!ttm_resource_compat(bo->resource, placement)) { ret = ttm_bo_move_buffer(bo, placement, ctx); if (ret) return ret; diff --git a/drivers/gpu/drm/ttm/ttm_resource.c b/drivers/gpu/drm/ttm/ttm_resource.c index 2431717376e7..035d71332d18 100644 --- a/drivers/gpu/drm/ttm/ttm_resource.c +++ b/drivers/gpu/drm/ttm/ttm_resource.c @@ -67,6 +67,55 @@ void ttm_resource_free(struct ttm_buffer_object *bo, struct ttm_resource **res) } EXPORT_SYMBOL(ttm_resource_free); +static bool ttm_resource_places_compat(struct ttm_resource *res, + const struct ttm_place *places, + unsigned num_placement) +{ + unsigned i; + + if (res->placement & TTM_PL_FLAG_TEMPORARY) + return false; + + for (i = 0; i < num_placement; i++) { + const struct ttm_place *heap = &places[i]; + + if (res->start < heap->fpfn || (heap->lpfn && + (res->start + res->num_pages) > heap->lpfn)) + continue; + + if ((res->mem_type == heap->mem_type) && + (!(heap->flags & TTM_PL_FLAG_CONTIGUOUS) || + (res->placement & TTM_PL_FLAG_CONTIGUOUS))) + return true; + } + return false; +} + +/** + * ttm_resource_compat - check if resource is compatible with placement + * + * @res: the resource to check + * @placement: the placement to check against + * + * Returns true if the placement is compatible. + */ +bool ttm_resource_compat(struct ttm_resource *res, + struct ttm_placement *placement) +{ + if (ttm_resource_places_compat(res, placement->placement, + placement->num_placement)) + return true; + + if ((placement->busy_placement != placement->placement || + placement->num_busy_placement > placement->num_placement) && + ttm_resource_places_compat(res, placement->busy_placement, + placement->num_busy_placement)) + return true; + + return false; +} +EXPORT_SYMBOL(ttm_resource_compat); + /** * ttm_resource_manager_init * diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c index 9e3e1429db94..fd007f1c1776 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c @@ -94,7 +94,6 @@ int vmw_bo_pin_in_placement(struct vmw_private *dev_priv, struct ttm_operation_ctx ctx = {interruptible, false }; struct ttm_buffer_object *bo = &buf->base; int ret; - uint32_t new_flags; vmw_execbuf_release_pinned_bo(dev_priv); @@ -103,8 +102,8 @@ int vmw_bo_pin_in_placement(struct vmw_private *dev_priv, goto err; if (buf->base.pin_count > 0) - ret = ttm_bo_mem_compat(placement, bo->resource, - &new_flags) == true ? 0 : -EINVAL; + ret = ttm_resource_compat(bo->resource, placement) + ? 0 : -EINVAL; else ret = ttm_bo_validate(bo, placement, &ctx); @@ -136,7 +135,6 @@ int vmw_bo_pin_in_vram_or_gmr(struct vmw_private *dev_priv, struct ttm_operation_ctx ctx = {interruptible, false }; struct ttm_buffer_object *bo = &buf->base; int ret; - uint32_t new_flags; vmw_execbuf_release_pinned_bo(dev_priv); @@ -145,8 +143,8 @@ int vmw_bo_pin_in_vram_or_gmr(struct vmw_private *dev_priv, goto err; if (buf->base.pin_count > 0) { - ret = ttm_bo_mem_compat(&vmw_vram_gmr_placement, bo->resource, - &new_flags) == true ? 0 : -EINVAL; + ret = ttm_resource_compat(bo->resource, &vmw_vram_gmr_placement) + ? 0 : -EINVAL; goto out_unreserve; } @@ -208,7 +206,6 @@ int vmw_bo_pin_in_start_of_vram(struct vmw_private *dev_priv, struct ttm_placement placement; struct ttm_place place; int ret = 0; - uint32_t new_flags; place = vmw_vram_placement.placement[0]; place.lpfn = bo->resource->num_pages; @@ -236,8 +233,8 @@ int vmw_bo_pin_in_start_of_vram(struct vmw_private *dev_priv, } if (buf->base.pin_count > 0) - ret = ttm_bo_mem_compat(&placement, bo->resource, - &new_flags) == true ? 0 : -EINVAL; + ret = ttm_resource_compat(bo->resource, &placement) + ? 0 : -EINVAL; else ret = ttm_bo_validate(bo, &placement, &ctx); diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h index f681bbdbc698..76d7c33884da 100644 --- a/include/drm/ttm/ttm_bo_api.h +++ b/include/drm/ttm/ttm_bo_api.h @@ -264,18 +264,6 @@ static inline int ttm_bo_wait_ctx(struct ttm_buffer_object *bo, struct ttm_opera return ttm_bo_wait(bo, ctx->interruptible, ctx->no_wait_gpu); } -/** - * ttm_bo_mem_compat - Check if proposed placement is compatible with a bo - * - * @placement: Return immediately if buffer is busy. - * @mem: The struct ttm_resource indicating the region where the bo resides - * @new_flags: Describes compatible placement found - * - * Returns true if the placement is compatible - */ -bool ttm_bo_mem_compat(struct ttm_placement *placement, struct ttm_resource *mem, - uint32_t *new_flags); - /** * ttm_bo_validate * diff --git a/include/drm/ttm/ttm_resource.h b/include/drm/ttm/ttm_resource.h index 140b6b9a8bbe..32c5edd9e8b5 100644 --- a/include/drm/ttm/ttm_resource.h +++ b/include/drm/ttm/ttm_resource.h @@ -40,6 +40,7 @@ struct ttm_resource_manager; struct ttm_resource; struct ttm_place; struct ttm_buffer_object; +struct ttm_placement; struct dma_buf_map; struct io_mapping; struct sg_table; @@ -266,6 +267,8 @@ int ttm_resource_alloc(struct ttm_buffer_object *bo, const struct ttm_place *place, struct ttm_resource **res); void ttm_resource_free(struct ttm_buffer_object *bo, struct ttm_resource **res); +bool ttm_resource_compat(struct ttm_resource *res, + struct ttm_placement *placement); void ttm_resource_manager_init(struct ttm_resource_manager *man, unsigned long p_size); -- cgit v1.2.3 From a9fc4315553df6087c19537abe3340afcf0621fd Mon Sep 17 00:00:00 2001 From: zhangzhijie Date: Fri, 3 Sep 2021 11:24:02 +0800 Subject: drm: Improve the output_poll_changed description this callback was used by drm_kms_helper_hotplug_event() V2: (Thanks for Daniel's suggestions) - remove the FIXME below.since with the drm_client - infrastructure and the generic fbdev emulation we've - resolved this all very neatly now. V3: Add comments that This hook is deprecated - new implementation methods instead of this hook v4: used by drm_kms_helper_hotplug_event() - drm_fb_helper_hotplug_changed() is not found instead by drm_kms_helper_hotplug_event() Signed-off-by: ZhiJie.Zhang Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20210903032402.11935-1-zhangzhijie@loongson.cn --- include/drm/drm_mode_config.h | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/drm/drm_mode_config.h b/include/drm/drm_mode_config.h index 1ddf7783fdf7..48b7de80daf5 100644 --- a/include/drm/drm_mode_config.h +++ b/include/drm/drm_mode_config.h @@ -103,14 +103,13 @@ struct drm_mode_config_funcs { * Callback used by helpers to inform the driver of output configuration * changes. * - * Drivers implementing fbdev emulation with the helpers can call - * drm_fb_helper_hotplug_changed from this hook to inform the fbdev - * helper of output changes. + * Drivers implementing fbdev emulation use drm_kms_helper_hotplug_event() + * to call this hook to inform the fbdev helper of output changes. * - * FIXME: - * - * Except that there's no vtable for device-level helper callbacks - * there's no reason this is a core function. + * This hook is deprecated, drivers should instead use + * drm_fbdev_generic_setup() which takes care of any necessary + * hotplug event forwarding already without further involvement by + * the driver. */ void (*output_poll_changed)(struct drm_device *dev); -- cgit v1.2.3 From d4c16733e7960aa50d6d3bc4a03ee1578baaa47b Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Fri, 3 Sep 2021 14:05:54 +0200 Subject: drm/sched: Fix drm_sched_fence_free() so it can be passed an uninitialized fence drm_sched_job_cleanup() will pass an uninitialized fence to drm_sched_fence_free(), which will cause to_drm_sched_fence() to return a NULL fence object, causing a NULL pointer deref when this NULL object is passed to kmem_cache_free(). Let's create a new drm_sched_fence_free() function that takes a drm_sched_fence pointer and suffix the old function with _rcu. While at it, complain if drm_sched_fence_free() is passed an initialized fence or if drm_sched_fence_free_rcu() is passed an uninitialized fence. Fixes: dbe48d030b28 ("drm/sched: Split drm_sched_job_init") Signed-off-by: Boris Brezillon Reviewed-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20210903120554.444101-1-boris.brezillon@collabora.com --- drivers/gpu/drm/scheduler/sched_fence.c | 27 ++++++++++++++++++--------- drivers/gpu/drm/scheduler/sched_main.c | 2 +- include/drm/gpu_scheduler.h | 2 +- 3 files changed, 20 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/scheduler/sched_fence.c b/drivers/gpu/drm/scheduler/sched_fence.c index db3fd1303fc4..7fd869520ef2 100644 --- a/drivers/gpu/drm/scheduler/sched_fence.c +++ b/drivers/gpu/drm/scheduler/sched_fence.c @@ -69,19 +69,28 @@ static const char *drm_sched_fence_get_timeline_name(struct dma_fence *f) return (const char *)fence->sched->name; } +static void drm_sched_fence_free_rcu(struct rcu_head *rcu) +{ + struct dma_fence *f = container_of(rcu, struct dma_fence, rcu); + struct drm_sched_fence *fence = to_drm_sched_fence(f); + + if (!WARN_ON_ONCE(!fence)) + kmem_cache_free(sched_fence_slab, fence); +} + /** - * drm_sched_fence_free - free up the fence memory + * drm_sched_fence_free - free up an uninitialized fence * - * @rcu: RCU callback head + * @fence: fence to free * - * Free up the fence memory after the RCU grace period. + * Free up the fence memory. Should only be used if drm_sched_fence_init() + * has not been called yet. */ -void drm_sched_fence_free(struct rcu_head *rcu) +void drm_sched_fence_free(struct drm_sched_fence *fence) { - struct dma_fence *f = container_of(rcu, struct dma_fence, rcu); - struct drm_sched_fence *fence = to_drm_sched_fence(f); - - kmem_cache_free(sched_fence_slab, fence); + /* This function should not be called if the fence has been initialized. */ + if (!WARN_ON_ONCE(fence->sched)) + kmem_cache_free(sched_fence_slab, fence); } /** @@ -97,7 +106,7 @@ static void drm_sched_fence_release_scheduled(struct dma_fence *f) struct drm_sched_fence *fence = to_drm_sched_fence(f); dma_fence_put(fence->parent); - call_rcu(&fence->finished.rcu, drm_sched_fence_free); + call_rcu(&fence->finished.rcu, drm_sched_fence_free_rcu); } /** diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c index fbbd3b03902f..6987d412a946 100644 --- a/drivers/gpu/drm/scheduler/sched_main.c +++ b/drivers/gpu/drm/scheduler/sched_main.c @@ -750,7 +750,7 @@ void drm_sched_job_cleanup(struct drm_sched_job *job) dma_fence_put(&job->s_fence->finished); } else { /* aborted job before committing to run it */ - drm_sched_fence_free(&job->s_fence->finished.rcu); + drm_sched_fence_free(job->s_fence); } job->s_fence = NULL; diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h index 7f77a455722c..f011e4c407f2 100644 --- a/include/drm/gpu_scheduler.h +++ b/include/drm/gpu_scheduler.h @@ -509,7 +509,7 @@ struct drm_sched_fence *drm_sched_fence_alloc( struct drm_sched_entity *s_entity, void *owner); void drm_sched_fence_init(struct drm_sched_fence *fence, struct drm_sched_entity *entity); -void drm_sched_fence_free(struct rcu_head *rcu); +void drm_sched_fence_free(struct drm_sched_fence *fence); void drm_sched_fence_scheduled(struct drm_sched_fence *fence); void drm_sched_fence_finished(struct drm_sched_fence *fence); -- cgit v1.2.3 From 04f08eb44b5011493d77b602fdec29ff0f5c6cd5 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 8 Sep 2021 17:00:29 -0700 Subject: net/af_unix: fix a data-race in unix_dgram_poll syzbot reported another data-race in af_unix [1] Lets change __skb_insert() to use WRITE_ONCE() when changing skb head qlen. Also, change unix_dgram_poll() to use lockless version of unix_recvq_full() It is verry possible we can switch all/most unix_recvq_full() to the lockless version, this will be done in a future kernel version. [1] HEAD commit: 8596e589b787732c8346f0482919e83cc9362db1 BUG: KCSAN: data-race in skb_queue_tail / unix_dgram_poll write to 0xffff88814eeb24e0 of 4 bytes by task 25815 on cpu 0: __skb_insert include/linux/skbuff.h:1938 [inline] __skb_queue_before include/linux/skbuff.h:2043 [inline] __skb_queue_tail include/linux/skbuff.h:2076 [inline] skb_queue_tail+0x80/0xa0 net/core/skbuff.c:3264 unix_dgram_sendmsg+0xff2/0x1600 net/unix/af_unix.c:1850 sock_sendmsg_nosec net/socket.c:703 [inline] sock_sendmsg net/socket.c:723 [inline] ____sys_sendmsg+0x360/0x4d0 net/socket.c:2392 ___sys_sendmsg net/socket.c:2446 [inline] __sys_sendmmsg+0x315/0x4b0 net/socket.c:2532 __do_sys_sendmmsg net/socket.c:2561 [inline] __se_sys_sendmmsg net/socket.c:2558 [inline] __x64_sys_sendmmsg+0x53/0x60 net/socket.c:2558 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3d/0x90 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae read to 0xffff88814eeb24e0 of 4 bytes by task 25834 on cpu 1: skb_queue_len include/linux/skbuff.h:1869 [inline] unix_recvq_full net/unix/af_unix.c:194 [inline] unix_dgram_poll+0x2bc/0x3e0 net/unix/af_unix.c:2777 sock_poll+0x23e/0x260 net/socket.c:1288 vfs_poll include/linux/poll.h:90 [inline] ep_item_poll fs/eventpoll.c:846 [inline] ep_send_events fs/eventpoll.c:1683 [inline] ep_poll fs/eventpoll.c:1798 [inline] do_epoll_wait+0x6ad/0xf00 fs/eventpoll.c:2226 __do_sys_epoll_wait fs/eventpoll.c:2238 [inline] __se_sys_epoll_wait fs/eventpoll.c:2233 [inline] __x64_sys_epoll_wait+0xf6/0x120 fs/eventpoll.c:2233 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3d/0x90 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae value changed: 0x0000001b -> 0x00000001 Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 25834 Comm: syz-executor.1 Tainted: G W 5.14.0-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Fixes: 86b18aaa2b5b ("skbuff: fix a data race in skb_queue_len()") Cc: Qian Cai Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/skbuff.h | 2 +- net/unix/af_unix.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 6bdb0db3e825..841e2f0f5240 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1940,7 +1940,7 @@ static inline void __skb_insert(struct sk_buff *newsk, WRITE_ONCE(newsk->prev, prev); WRITE_ONCE(next->prev, newsk); WRITE_ONCE(prev->next, newsk); - list->qlen++; + WRITE_ONCE(list->qlen, list->qlen + 1); } static inline void __skb_queue_splice(const struct sk_buff_head *list, diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index eb47b9de2380..92345c9bb60c 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -3073,7 +3073,7 @@ static __poll_t unix_dgram_poll(struct file *file, struct socket *sock, other = unix_peer(sk); if (other && unix_peer(other) != sk && - unix_recvq_full(other) && + unix_recvq_full_lockless(other) && unix_dgram_peer_wake_me(sk, other)) writable = 0; -- cgit v1.2.3 From be77a2f4cfd20aa4a28fc98227bfbfd5e0c232e2 Mon Sep 17 00:00:00 2001 From: Christian König Date: Tue, 7 Sep 2021 09:14:43 +0200 Subject: drm/ttm: add kerneldoc for enum ttm_caching MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Briefly describe what this is all about. Signed-off-by: Christian König Reviewed-by: Alex Deucher Link: https://patchwork.freedesktop.org/patch/msgid/20210908132933.3269-4-christian.koenig@amd.com --- Documentation/gpu/drm-mm.rst | 3 +++ include/drm/ttm/ttm_caching.h | 17 +++++++++++++++++ 2 files changed, 20 insertions(+) (limited to 'include') diff --git a/Documentation/gpu/drm-mm.rst b/Documentation/gpu/drm-mm.rst index 6b7717af4f88..f22c9f9a2c0e 100644 --- a/Documentation/gpu/drm-mm.rst +++ b/Documentation/gpu/drm-mm.rst @@ -31,6 +31,9 @@ The Translation Table Manager (TTM) .. kernel-doc:: drivers/gpu/drm/ttm/ttm_module.c :doc: TTM +.. kernel-doc:: include/drm/ttm/ttm_caching.h + :internal: + The Graphics Execution Manager (GEM) ==================================== diff --git a/include/drm/ttm/ttm_caching.h b/include/drm/ttm/ttm_caching.h index 3c9dd65f5aaf..235a743d90e1 100644 --- a/include/drm/ttm/ttm_caching.h +++ b/include/drm/ttm/ttm_caching.h @@ -27,9 +27,26 @@ #define TTM_NUM_CACHING_TYPES 3 +/** + * enum ttm_caching - CPU caching and BUS snooping behavior. + */ enum ttm_caching { + /** + * @ttm_uncached: Most defensive option for device mappings, + * don't even allow write combining. + */ ttm_uncached, + + /** + * @ttm_write_combined: Don't cache read accesses, but allow at least + * writes to be combined. + */ ttm_write_combined, + + /** + * @ttm_cached: Fully cached like normal system memory, requires that + * devices snoop the CPU cache on accesses. + */ ttm_cached }; -- cgit v1.2.3 From c5fd9986719e4a75340b38ef4f6157e2c5fbe74d Mon Sep 17 00:00:00 2001 From: Christian König Date: Fri, 3 Sep 2021 13:44:46 +0200 Subject: drm/ttm: enable TTM device object kerneldoc v2 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix the remaining warnings, switch to inline structure documentation and finally enable this. v2: adjust based on suggestions from Alex Signed-off-by: Christian König Reviewed-by: Matthew Auld Link: https://patchwork.freedesktop.org/patch/msgid/20210908132933.3269-5-christian.koenig@amd.com --- Documentation/gpu/drm-mm.rst | 9 ++++++ include/drm/ttm/ttm_device.h | 72 ++++++++++++++++++++++++-------------------- 2 files changed, 48 insertions(+), 33 deletions(-) (limited to 'include') diff --git a/Documentation/gpu/drm-mm.rst b/Documentation/gpu/drm-mm.rst index f22c9f9a2c0e..3da81b7b4e71 100644 --- a/Documentation/gpu/drm-mm.rst +++ b/Documentation/gpu/drm-mm.rst @@ -34,6 +34,15 @@ The Translation Table Manager (TTM) .. kernel-doc:: include/drm/ttm/ttm_caching.h :internal: +TTM device object reference +--------------------------- + +.. kernel-doc:: include/drm/ttm/ttm_device.h + :internal: + +.. kernel-doc:: drivers/gpu/drm/ttm/ttm_device.c + :export: + The Graphics Execution Manager (GEM) ==================================== diff --git a/include/drm/ttm/ttm_device.h b/include/drm/ttm/ttm_device.h index 07d722950d5b..3cc1d9b76131 100644 --- a/include/drm/ttm/ttm_device.h +++ b/include/drm/ttm/ttm_device.h @@ -39,31 +39,23 @@ struct ttm_operation_ctx; /** * struct ttm_global - Buffer object driver global data. - * - * @dummy_read_page: Pointer to a dummy page used for mapping requests - * of unpopulated pages. - * @shrink: A shrink callback object used for buffer object swap. - * @device_list_mutex: Mutex protecting the device list. - * This mutex is held while traversing the device list for pm options. - * @lru_lock: Spinlock protecting the bo subsystem lru lists. - * @device_list: List of buffer object devices. - * @swap_lru: Lru list of buffer objects used for swapping. */ extern struct ttm_global { /** - * Constant after init. + * @dummy_read_page: Pointer to a dummy page used for mapping requests + * of unpopulated pages. Constant after init. */ - struct page *dummy_read_page; /** - * Protected by ttm_global_mutex. + * @device_list: List of buffer object devices. Protected by + * ttm_global_mutex. */ struct list_head device_list; /** - * Internal protection. + * @bo_count: Number of buffer objects allocated by devices. */ atomic_t bo_count; } ttm_glob; @@ -230,50 +222,64 @@ struct ttm_device_funcs { /** * struct ttm_device - Buffer object driver device-specific data. - * - * @device_list: Our entry in the global device list. - * @funcs: Function table for the device. - * @sysman: Resource manager for the system domain. - * @man_drv: An array of resource_managers. - * @vma_manager: Address space manager. - * @pool: page pool for the device. - * @dev_mapping: A pointer to the struct address_space representing the - * device address space. - * @wq: Work queue structure for the delayed delete workqueue. */ struct ttm_device { - /* + /** + * @device_list: Our entry in the global device list. * Constant after bo device init */ struct list_head device_list; + + /** + * @funcs: Function table for the device. + * Constant after bo device init + */ struct ttm_device_funcs *funcs; - /* + /** + * @sysman: Resource manager for the system domain. * Access via ttm_manager_type. */ struct ttm_resource_manager sysman; + + /** + * @man_drv: An array of resource_managers, one per resource type. + */ struct ttm_resource_manager *man_drv[TTM_NUM_MEM_TYPES]; - /* - * Protected by internal locks. + /** + * @vma_manager: Address space manager for finding BOs to mmap. */ struct drm_vma_offset_manager *vma_manager; + + /** + * @pool: page pool for the device. + */ struct ttm_pool pool; - /* - * Protection for the per manager LRU and ddestroy lists. + /** + * @lru_lock: Protection for the per manager LRU and ddestroy lists. */ spinlock_t lru_lock; + + /** + * @ddestroy: Destroyed but not yet cleaned up buffer objects. + */ struct list_head ddestroy; + + /** + * @pinned: Buffer objects which are pinned and so not on any LRU list. + */ struct list_head pinned; - /* - * Protected by load / firstopen / lastclose /unload sync. + /** + * @dev_mapping: A pointer to the struct address_space for invalidating + * CPU mappings on buffer move. Protected by load/unload sync. */ struct address_space *dev_mapping; - /* - * Internal protection. + /** + * @wq: Work queue structure for the delayed delete workqueue. */ struct delayed_work wq; }; -- cgit v1.2.3 From 324317add204db3f938da3539784a91d40f7141c Mon Sep 17 00:00:00 2001 From: Christian König Date: Fri, 3 Sep 2021 13:55:01 +0200 Subject: drm/ttm: enable TTM resource object kerneldoc v2 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix the last two remaining warnings and finally enable this. v2: add caching enum link Signed-off-by: Christian König Reviewed-by: Matthew Auld Reviewed-by: Alex Deucher Link: https://patchwork.freedesktop.org/patch/msgid/20210908132933.3269-6-christian.koenig@amd.com --- Documentation/gpu/drm-mm.rst | 9 +++++++++ include/drm/ttm/ttm_resource.h | 6 ++---- 2 files changed, 11 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/Documentation/gpu/drm-mm.rst b/Documentation/gpu/drm-mm.rst index 3da81b7b4e71..66d24b745c62 100644 --- a/Documentation/gpu/drm-mm.rst +++ b/Documentation/gpu/drm-mm.rst @@ -43,6 +43,15 @@ TTM device object reference .. kernel-doc:: drivers/gpu/drm/ttm/ttm_device.c :export: +TTM resource object reference +----------------------------- + +.. kernel-doc:: include/drm/ttm/ttm_resource.h + :internal: + +.. kernel-doc:: drivers/gpu/drm/ttm/ttm_resource.c + :export: + The Graphics Execution Manager (GEM) ==================================== diff --git a/include/drm/ttm/ttm_resource.h b/include/drm/ttm/ttm_resource.h index 32c5edd9e8b5..5952051091cd 100644 --- a/include/drm/ttm/ttm_resource.h +++ b/include/drm/ttm/ttm_resource.h @@ -103,10 +103,7 @@ struct ttm_resource_manager_func { * struct ttm_resource_manager * * @use_type: The memory type is enabled. - * @flags: TTM_MEMTYPE_XX flags identifying the traits of the memory - * managed by this memory type. - * @gpu_offset: If used, the GPU offset of the first managed page of - * fixed memory or the first managed location in an aperture. + * @use_tt: If a TT object should be used for the backing store. * @size: Size of the managed region. * @func: structure pointer implementing the range manager. See above * @move_lock: lock for move fence @@ -144,6 +141,7 @@ struct ttm_resource_manager { * @addr: mapped virtual address * @offset: physical addr * @is_iomem: is this io memory ? + * @caching: See enum ttm_caching * * Structure indicating the bus placement of an object. */ -- cgit v1.2.3 From d7fe6f8afead5838bd43adf10a06a66896bfe756 Mon Sep 17 00:00:00 2001 From: Christian König Date: Fri, 3 Sep 2021 14:14:41 +0200 Subject: drm/ttm: enable TTM placement kerneldoc MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix the last remaining warning and finally enable this. Signed-off-by: Christian König Reviewed-by: Matthew Auld Reviewed-by: Alex Deucher Link: https://patchwork.freedesktop.org/patch/msgid/20210908132933.3269-7-christian.koenig@amd.com --- Documentation/gpu/drm-mm.rst | 6 ++++++ include/drm/ttm/ttm_placement.h | 1 + 2 files changed, 7 insertions(+) (limited to 'include') diff --git a/Documentation/gpu/drm-mm.rst b/Documentation/gpu/drm-mm.rst index 66d24b745c62..1c9930fb5e7d 100644 --- a/Documentation/gpu/drm-mm.rst +++ b/Documentation/gpu/drm-mm.rst @@ -43,6 +43,12 @@ TTM device object reference .. kernel-doc:: drivers/gpu/drm/ttm/ttm_device.c :export: +TTM resource placement reference +-------------------------------- + +.. kernel-doc:: include/drm/ttm/ttm_placement.h + :internal: + TTM resource object reference ----------------------------- diff --git a/include/drm/ttm/ttm_placement.h b/include/drm/ttm/ttm_placement.h index 8995c9e4ec1b..76d1b9119a2b 100644 --- a/include/drm/ttm/ttm_placement.h +++ b/include/drm/ttm/ttm_placement.h @@ -58,6 +58,7 @@ * * @fpfn: first valid page frame number to put the object * @lpfn: last valid page frame number to put the object + * @mem_type: One of TTM_PL_* where the resource should be allocated from. * @flags: memory domain and caching flags for the object * * Structure indicating a possible place to put an object. -- cgit v1.2.3 From 4f4859d084f7b8c72ca3639f6169b74d0340ddb9 Mon Sep 17 00:00:00 2001 From: Christian König Date: Fri, 3 Sep 2021 14:19:38 +0200 Subject: drm/ttm: enable TTM TT object kerneldoc v2 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix the remaining warnings and finally enable this. v2: add caching enum link Signed-off-by: Christian König Reviewed-by: Matthew Auld Reviewed-by: Alex Deucher Link: https://patchwork.freedesktop.org/patch/msgid/20210908132933.3269-8-christian.koenig@amd.com --- Documentation/gpu/drm-mm.rst | 9 +++++++++ include/drm/ttm/ttm_tt.h | 11 ++++++++--- 2 files changed, 17 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/Documentation/gpu/drm-mm.rst b/Documentation/gpu/drm-mm.rst index 1c9930fb5e7d..69c4a20b95d0 100644 --- a/Documentation/gpu/drm-mm.rst +++ b/Documentation/gpu/drm-mm.rst @@ -58,6 +58,15 @@ TTM resource object reference .. kernel-doc:: drivers/gpu/drm/ttm/ttm_resource.c :export: +TTM TT object reference +----------------------- + +.. kernel-doc:: include/drm/ttm/ttm_tt.h + :internal: + +.. kernel-doc:: drivers/gpu/drm/ttm/ttm_tt.c + :export: + The Graphics Execution Manager (GEM) ==================================== diff --git a/include/drm/ttm/ttm_tt.h b/include/drm/ttm/ttm_tt.h index e402dab1d0f6..b3963ab12e1f 100644 --- a/include/drm/ttm/ttm_tt.h +++ b/include/drm/ttm/ttm_tt.h @@ -54,7 +54,7 @@ struct ttm_operation_ctx; * @dma_address: The DMA (bus) addresses of the pages * @swap_storage: Pointer to shmem struct file for swap storage. * @pages_list: used by some page allocation backend - * @caching: The current caching state of the pages. + * @caching: The current caching state of the pages, see enum ttm_caching. * * This is a structure holding the pages, caching- and aperture binding * status for a buffer object that isn't backed by fixed (VRAM / AGP) @@ -126,8 +126,9 @@ int ttm_sg_tt_init(struct ttm_tt *ttm_dma, struct ttm_buffer_object *bo, void ttm_tt_fini(struct ttm_tt *ttm); /** - * ttm_ttm_destroy: + * ttm_tt_destroy: * + * @bdev: the ttm_device this object belongs to * @ttm: The struct ttm_tt. * * Unbind, unpopulate and destroy common struct ttm_tt. @@ -148,15 +149,19 @@ int ttm_tt_swapout(struct ttm_device *bdev, struct ttm_tt *ttm, /** * ttm_tt_populate - allocate pages for a ttm * + * @bdev: the ttm_device this object belongs to * @ttm: Pointer to the ttm_tt structure + * @ctx: operation context for populating the tt object. * * Calls the driver method to allocate pages for a ttm */ -int ttm_tt_populate(struct ttm_device *bdev, struct ttm_tt *ttm, struct ttm_operation_ctx *ctx); +int ttm_tt_populate(struct ttm_device *bdev, struct ttm_tt *ttm, + struct ttm_operation_ctx *ctx); /** * ttm_tt_unpopulate - free pages from a ttm * + * @bdev: the ttm_device this object belongs to * @ttm: Pointer to the ttm_tt structure * * Calls the driver method to free all pages from a ttm -- cgit v1.2.3 From 361da7c34216382b7329521c397db0e3e8f6e02b Mon Sep 17 00:00:00 2001 From: Christian König Date: Tue, 7 Sep 2021 09:42:42 +0200 Subject: drm/ttm: enable TTM page pool kerneldoc MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix the remaining warnings and finally enable this. Signed-off-by: Christian König Reviewed-by: Alex Deucher Link: https://patchwork.freedesktop.org/patch/msgid/20210908132933.3269-9-christian.koenig@amd.com --- Documentation/gpu/drm-mm.rst | 9 +++++++++ include/drm/ttm/ttm_pool.h | 5 +++-- 2 files changed, 12 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/Documentation/gpu/drm-mm.rst b/Documentation/gpu/drm-mm.rst index 69c4a20b95d0..e0538083a2c0 100644 --- a/Documentation/gpu/drm-mm.rst +++ b/Documentation/gpu/drm-mm.rst @@ -67,6 +67,15 @@ TTM TT object reference .. kernel-doc:: drivers/gpu/drm/ttm/ttm_tt.c :export: +TTM page pool reference +----------------------- + +.. kernel-doc:: include/drm/ttm/ttm_pool.h + :internal: + +.. kernel-doc:: drivers/gpu/drm/ttm/ttm_pool.c + :export: + The Graphics Execution Manager (GEM) ==================================== diff --git a/include/drm/ttm/ttm_pool.h b/include/drm/ttm/ttm_pool.h index 4321728bdd11..ef09b23d29e3 100644 --- a/include/drm/ttm/ttm_pool.h +++ b/include/drm/ttm/ttm_pool.h @@ -37,7 +37,7 @@ struct ttm_pool; struct ttm_operation_ctx; /** - * ttm_pool_type - Pool for a certain memory type + * struct ttm_pool_type - Pool for a certain memory type * * @pool: the pool we belong to, might be NULL for the global ones * @order: the allocation order our pages have @@ -58,8 +58,9 @@ struct ttm_pool_type { }; /** - * ttm_pool - Pool for all caching and orders + * struct ttm_pool - Pool for all caching and orders * + * @dev: the device we allocate pages for * @use_dma_alloc: if coherent DMA allocations should be used * @use_dma32: if GFP_DMA32 should be used * @caching: pools for each caching/order -- cgit v1.2.3 From 353be7c2328ccba0add424d015ef51ddf423e202 Mon Sep 17 00:00:00 2001 From: Simon Ser Date: Fri, 3 Sep 2021 13:00:16 +0000 Subject: drm: document drm_mode_create_lease object requirements validate_lease expects one CRTC, one connector and one plane. Signed-off-by: Simon Ser Cc: Daniel Vetter Cc: Pekka Paalanen Cc: Keith Packard Reviewed-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20210903130000.1590-1-contact@emersion.fr --- include/uapi/drm/drm_mode.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/uapi/drm/drm_mode.h b/include/uapi/drm/drm_mode.h index 90c55383f1ee..e4a2570a6058 100644 --- a/include/uapi/drm/drm_mode.h +++ b/include/uapi/drm/drm_mode.h @@ -1110,6 +1110,9 @@ struct drm_mode_destroy_blob { * struct drm_mode_create_lease - Create lease * * Lease mode resources, creating another drm_master. + * + * The @object_ids array must reference at least one CRTC, one connector and + * one plane if &DRM_CLIENT_CAP_UNIVERSAL_PLANES is enabled. */ struct drm_mode_create_lease { /** @object_ids: Pointer to array of object ids (__u32) */ -- cgit v1.2.3 From 2f1aaf3ea666b737ad717b3d88667225aca23149 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Thu, 9 Sep 2021 08:49:59 -0700 Subject: bpf, mm: Fix lockdep warning triggered by stack_map_get_build_id_offset() Currently the bpf selftest "get_stack_raw_tp" triggered the warning: [ 1411.304463] WARNING: CPU: 3 PID: 140 at include/linux/mmap_lock.h:164 find_vma+0x47/0xa0 [ 1411.304469] Modules linked in: bpf_testmod(O) [last unloaded: bpf_testmod] [ 1411.304476] CPU: 3 PID: 140 Comm: systemd-journal Tainted: G W O 5.14.0+ #53 [ 1411.304479] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.14.0-0-g155821a1990b-prebuilt.qemu.org 04/01/2014 [ 1411.304481] RIP: 0010:find_vma+0x47/0xa0 [ 1411.304484] Code: de 48 89 ef e8 ba f5 fe ff 48 85 c0 74 2e 48 83 c4 08 5b 5d c3 48 8d bf 28 01 00 00 be ff ff ff ff e8 2d 9f d8 00 85 c0 75 d4 <0f> 0b 48 89 de 48 8 [ 1411.304487] RSP: 0018:ffffabd440403db8 EFLAGS: 00010246 [ 1411.304490] RAX: 0000000000000000 RBX: 00007f00ad80a0e0 RCX: 0000000000000000 [ 1411.304492] RDX: 0000000000000001 RSI: ffffffff9776b144 RDI: ffffffff977e1b0e [ 1411.304494] RBP: ffff9cf5c2f50000 R08: ffff9cf5c3eb25d8 R09: 00000000fffffffe [ 1411.304496] R10: 0000000000000001 R11: 00000000ef974e19 R12: ffff9cf5c39ae0e0 [ 1411.304498] R13: 0000000000000000 R14: 0000000000000000 R15: ffff9cf5c39ae0e0 [ 1411.304501] FS: 00007f00ae754780(0000) GS:ffff9cf5fba00000(0000) knlGS:0000000000000000 [ 1411.304504] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 1411.304506] CR2: 000000003e34343c CR3: 0000000103a98005 CR4: 0000000000370ee0 [ 1411.304508] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 1411.304510] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 1411.304512] Call Trace: [ 1411.304517] stack_map_get_build_id_offset+0x17c/0x260 [ 1411.304528] __bpf_get_stack+0x18f/0x230 [ 1411.304541] bpf_get_stack_raw_tp+0x5a/0x70 [ 1411.305752] RAX: 0000000000000000 RBX: 5541f689495641d7 RCX: 0000000000000000 [ 1411.305756] RDX: 0000000000000001 RSI: ffffffff9776b144 RDI: ffffffff977e1b0e [ 1411.305758] RBP: ffff9cf5c02b2f40 R08: ffff9cf5ca7606c0 R09: ffffcbd43ee02c04 [ 1411.306978] bpf_prog_32007c34f7726d29_bpf_prog1+0xaf/0xd9c [ 1411.307861] R10: 0000000000000001 R11: 0000000000000044 R12: ffff9cf5c2ef60e0 [ 1411.307865] R13: 0000000000000005 R14: 0000000000000000 R15: ffff9cf5c2ef6108 [ 1411.309074] bpf_trace_run2+0x8f/0x1a0 [ 1411.309891] FS: 00007ff485141700(0000) GS:ffff9cf5fae00000(0000) knlGS:0000000000000000 [ 1411.309896] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 1411.311221] syscall_trace_enter.isra.20+0x161/0x1f0 [ 1411.311600] CR2: 00007ff48514d90e CR3: 0000000107114001 CR4: 0000000000370ef0 [ 1411.312291] do_syscall_64+0x15/0x80 [ 1411.312941] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 1411.313803] entry_SYSCALL_64_after_hwframe+0x44/0xae [ 1411.314223] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 1411.315082] RIP: 0033:0x7f00ad80a0e0 [ 1411.315626] Call Trace: [ 1411.315632] stack_map_get_build_id_offset+0x17c/0x260 To reproduce, first build `test_progs` binary: make -C tools/testing/selftests/bpf -j60 and then run the binary at tools/testing/selftests/bpf directory: ./test_progs -t get_stack_raw_tp The warning is due to commit 5b78ed24e8ec ("mm/pagemap: add mmap_assert_locked() annotations to find_vma*()") which added mmap_assert_locked() in find_vma() function. The mmap_assert_locked() function asserts that mm->mmap_lock needs to be held. But this is not the case for bpf_get_stack() or bpf_get_stackid() helper (kernel/bpf/stackmap.c), which uses mmap_read_trylock_non_owner() instead. Since mm->mmap_lock is not held in bpf_get_stack[id]() use case, the above warning is emitted during test run. This patch fixed the issue by (1). using mmap_read_trylock() instead of mmap_read_trylock_non_owner() to satisfy lockdep checking in find_vma(), and (2). droping lockdep for mmap_lock right before the irq_work_queue(). The function mmap_read_trylock_non_owner() is also removed since after this patch nobody calls it any more. Fixes: 5b78ed24e8ec ("mm/pagemap: add mmap_assert_locked() annotations to find_vma*()") Suggested-by: Jason Gunthorpe Signed-off-by: Yonghong Song Signed-off-by: Daniel Borkmann Reviewed-by: Liam R. Howlett Cc: Luigi Rizzo Cc: Jason Gunthorpe Cc: linux-mm@kvack.org Link: https://lore.kernel.org/bpf/20210909155000.1610299-1-yhs@fb.com --- include/linux/mmap_lock.h | 9 --------- kernel/bpf/stackmap.c | 10 ++++++++-- 2 files changed, 8 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h index 0540f0156f58..3af8f7fb067d 100644 --- a/include/linux/mmap_lock.h +++ b/include/linux/mmap_lock.h @@ -144,15 +144,6 @@ static inline void mmap_read_unlock(struct mm_struct *mm) __mmap_lock_trace_released(mm, false); } -static inline bool mmap_read_trylock_non_owner(struct mm_struct *mm) -{ - if (mmap_read_trylock(mm)) { - rwsem_release(&mm->mmap_lock.dep_map, _RET_IP_); - return true; - } - return false; -} - static inline void mmap_read_unlock_non_owner(struct mm_struct *mm) { up_read_non_owner(&mm->mmap_lock); diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index e8eefdf8cf3e..09a3fd97d329 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -179,7 +179,7 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs, * with build_id. */ if (!user || !current || !current->mm || irq_work_busy || - !mmap_read_trylock_non_owner(current->mm)) { + !mmap_read_trylock(current->mm)) { /* cannot access current->mm, fall back to ips */ for (i = 0; i < trace_nr; i++) { id_offs[i].status = BPF_STACK_BUILD_ID_IP; @@ -204,9 +204,15 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs, } if (!work) { - mmap_read_unlock_non_owner(current->mm); + mmap_read_unlock(current->mm); } else { work->mm = current->mm; + + /* The lock will be released once we're out of interrupt + * context. Tell lockdep that we've released it now so + * it doesn't complain that we forgot to release it. + */ + rwsem_release(¤t->mm->mmap_lock.dep_map, _RET_IP_); irq_work_queue(&work->irq_work); } } -- cgit v1.2.3 From 7ad9bb9d0f357dcab5eb9a0f28d1c8983c48434c Mon Sep 17 00:00:00 2001 From: Wei Liu Date: Fri, 10 Sep 2021 18:57:13 +0000 Subject: asm-generic/hyperv: provide cpumask_to_vpset_noself This is a new variant which removes `self' cpu from the vpset. It will be used in Hyper-V enlightened IPI code. Signed-off-by: Wei Liu Reviewed-by: Michael Kelley Link: https://lore.kernel.org/r/20210910185714.299411-2-wei.liu@kernel.org --- include/asm-generic/mshyperv.h | 21 +++++++++++++++++++-- 1 file changed, 19 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/asm-generic/mshyperv.h b/include/asm-generic/mshyperv.h index 9a000ba2bb75..9a134806f1d5 100644 --- a/include/asm-generic/mshyperv.h +++ b/include/asm-generic/mshyperv.h @@ -184,10 +184,12 @@ static inline int hv_cpu_number_to_vp_number(int cpu_number) return hv_vp_index[cpu_number]; } -static inline int cpumask_to_vpset(struct hv_vpset *vpset, - const struct cpumask *cpus) +static inline int __cpumask_to_vpset(struct hv_vpset *vpset, + const struct cpumask *cpus, + bool exclude_self) { int cpu, vcpu, vcpu_bank, vcpu_offset, nr_bank = 1; + int this_cpu = smp_processor_id(); /* valid_bank_mask can represent up to 64 banks */ if (hv_max_vp_index / 64 >= 64) @@ -205,6 +207,8 @@ static inline int cpumask_to_vpset(struct hv_vpset *vpset, * Some banks may end up being empty but this is acceptable. */ for_each_cpu(cpu, cpus) { + if (exclude_self && cpu == this_cpu) + continue; vcpu = hv_cpu_number_to_vp_number(cpu); if (vcpu == VP_INVAL) return -1; @@ -219,6 +223,19 @@ static inline int cpumask_to_vpset(struct hv_vpset *vpset, return nr_bank; } +static inline int cpumask_to_vpset(struct hv_vpset *vpset, + const struct cpumask *cpus) +{ + return __cpumask_to_vpset(vpset, cpus, false); +} + +static inline int cpumask_to_vpset_noself(struct hv_vpset *vpset, + const struct cpumask *cpus) +{ + WARN_ON_ONCE(preemptible()); + return __cpumask_to_vpset(vpset, cpus, true); +} + void hyperv_report_panic(struct pt_regs *regs, long err, bool in_die); bool hv_is_hyperv_initialized(void); bool hv_is_hibernation_supported(void); -- cgit v1.2.3 From 617d5b34f22c66fe9fc9f150be27f5de1b87ca15 Mon Sep 17 00:00:00 2001 From: xinhui pan Date: Mon, 13 Sep 2021 16:09:50 +0800 Subject: drm/ttm: Try to check if new ttm man out of bounds during compile MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Allow TTM know if vendor set new ttm mananger out of bounds by adding build_bug_on. Signed-off-by: xinhui pan Reviewed-by: Christian König Link: https://patchwork.freedesktop.org/patch/msgid/20210913080950.180752-1-xinhui.pan@amd.com Signed-off-by: Christian König --- drivers/gpu/drm/ttm/ttm_range_manager.c | 8 ++++---- include/drm/ttm/ttm_device.h | 3 +++ include/drm/ttm/ttm_range_manager.h | 18 ++++++++++++++++-- 3 files changed, 23 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/ttm/ttm_range_manager.c b/drivers/gpu/drm/ttm/ttm_range_manager.c index f4b08a8705b3..67d68a4a8640 100644 --- a/drivers/gpu/drm/ttm/ttm_range_manager.c +++ b/drivers/gpu/drm/ttm/ttm_range_manager.c @@ -138,7 +138,7 @@ static const struct ttm_resource_manager_func ttm_range_manager_func = { * Initialise a generic range manager for the selected memory type. * The range manager is installed for this device in the type slot. */ -int ttm_range_man_init(struct ttm_device *bdev, +int ttm_range_man_init_nocheck(struct ttm_device *bdev, unsigned type, bool use_tt, unsigned long p_size) { @@ -163,7 +163,7 @@ int ttm_range_man_init(struct ttm_device *bdev, ttm_resource_manager_set_used(man, true); return 0; } -EXPORT_SYMBOL(ttm_range_man_init); +EXPORT_SYMBOL(ttm_range_man_init_nocheck); /** * ttm_range_man_fini @@ -173,7 +173,7 @@ EXPORT_SYMBOL(ttm_range_man_init); * * Remove the generic range manager from a slot and tear it down. */ -int ttm_range_man_fini(struct ttm_device *bdev, +int ttm_range_man_fini_nocheck(struct ttm_device *bdev, unsigned type) { struct ttm_resource_manager *man = ttm_manager_type(bdev, type); @@ -200,4 +200,4 @@ int ttm_range_man_fini(struct ttm_device *bdev, kfree(rman); return 0; } -EXPORT_SYMBOL(ttm_range_man_fini); +EXPORT_SYMBOL(ttm_range_man_fini_nocheck); diff --git a/include/drm/ttm/ttm_device.h b/include/drm/ttm/ttm_device.h index 3cc1d9b76131..cbe03d45e883 100644 --- a/include/drm/ttm/ttm_device.h +++ b/include/drm/ttm/ttm_device.h @@ -291,12 +291,15 @@ int ttm_device_swapout(struct ttm_device *bdev, struct ttm_operation_ctx *ctx, static inline struct ttm_resource_manager * ttm_manager_type(struct ttm_device *bdev, int mem_type) { + BUILD_BUG_ON(__builtin_constant_p(mem_type) + && mem_type >= TTM_NUM_MEM_TYPES); return bdev->man_drv[mem_type]; } static inline void ttm_set_driver_manager(struct ttm_device *bdev, int type, struct ttm_resource_manager *manager) { + BUILD_BUG_ON(__builtin_constant_p(type) && type >= TTM_NUM_MEM_TYPES); bdev->man_drv[type] = manager; } diff --git a/include/drm/ttm/ttm_range_manager.h b/include/drm/ttm/ttm_range_manager.h index 22b6fa42ac20..7963b957e9ef 100644 --- a/include/drm/ttm/ttm_range_manager.h +++ b/include/drm/ttm/ttm_range_manager.h @@ -4,6 +4,7 @@ #define _TTM_RANGE_MANAGER_H_ #include +#include #include /** @@ -33,10 +34,23 @@ to_ttm_range_mgr_node(struct ttm_resource *res) return container_of(res, struct ttm_range_mgr_node, base); } -int ttm_range_man_init(struct ttm_device *bdev, +int ttm_range_man_init_nocheck(struct ttm_device *bdev, unsigned type, bool use_tt, unsigned long p_size); -int ttm_range_man_fini(struct ttm_device *bdev, +int ttm_range_man_fini_nocheck(struct ttm_device *bdev, unsigned type); +static __always_inline int ttm_range_man_init(struct ttm_device *bdev, + unsigned int type, bool use_tt, + unsigned long p_size) +{ + BUILD_BUG_ON(__builtin_constant_p(type) && type >= TTM_NUM_MEM_TYPES); + return ttm_range_man_init_nocheck(bdev, type, use_tt, p_size); +} +static __always_inline int ttm_range_man_fini(struct ttm_device *bdev, + unsigned int type) +{ + BUILD_BUG_ON(__builtin_constant_p(type) && type >= TTM_NUM_MEM_TYPES); + return ttm_range_man_fini_nocheck(bdev, type); +} #endif -- cgit v1.2.3 From dd47c104533dedb90434a3f142e94a671ac623a6 Mon Sep 17 00:00:00 2001 From: Eugene Syromiatnikov Date: Mon, 13 Sep 2021 17:44:15 +0200 Subject: io-wq: provide IO_WQ_* constants for IORING_REGISTER_IOWQ_MAX_WORKERS arg items The items passed in the array pointed by the arg parameter of IORING_REGISTER_IOWQ_MAX_WORKERS io_uring_register operation carry certain semantics: they refer to different io-wq worker categories; provide IO_WQ_* constants in the UAPI, so these categories can be referenced in the user space code. Suggested-by: Jens Axboe Complements: 2e480058ddc21ec5 ("io-wq: provide a way to limit max number of workers") Signed-off-by: Eugene Syromiatnikov Link: https://lore.kernel.org/r/20210913154415.GA12890@asgard.redhat.com Signed-off-by: Jens Axboe --- fs/io-wq.c | 5 +++++ include/uapi/linux/io_uring.h | 8 +++++++- 2 files changed, 12 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/fs/io-wq.c b/fs/io-wq.c index 3d4460df845c..c2e0e8e80949 100644 --- a/fs/io-wq.c +++ b/fs/io-wq.c @@ -14,6 +14,7 @@ #include #include #include +#include #include "io-wq.h" @@ -1281,6 +1282,10 @@ int io_wq_max_workers(struct io_wq *wq, int *new_count) { int i, node, prev = 0; + BUILD_BUG_ON((int) IO_WQ_ACCT_BOUND != (int) IO_WQ_BOUND); + BUILD_BUG_ON((int) IO_WQ_ACCT_UNBOUND != (int) IO_WQ_UNBOUND); + BUILD_BUG_ON((int) IO_WQ_ACCT_NR != 2); + for (i = 0; i < 2; i++) { if (new_count[i] > task_rlimit(current, RLIMIT_NPROC)) new_count[i] = task_rlimit(current, RLIMIT_NPROC); diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 59ef35154e3d..b270a07b285e 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -317,13 +317,19 @@ enum { IORING_REGISTER_IOWQ_AFF = 17, IORING_UNREGISTER_IOWQ_AFF = 18, - /* set/get max number of workers */ + /* set/get max number of io-wq workers */ IORING_REGISTER_IOWQ_MAX_WORKERS = 19, /* this goes last */ IORING_REGISTER_LAST }; +/* io-wq worker categories */ +enum { + IO_WQ_BOUND, + IO_WQ_UNBOUND, +}; + /* deprecated, see struct io_uring_rsrc_update */ struct io_uring_files_update { __u32 offset; -- cgit v1.2.3 From 4eb6bd55cfb22ffc20652732340c4962f3ac9a91 Mon Sep 17 00:00:00 2001 From: Nick Desaulniers Date: Fri, 10 Sep 2021 16:40:39 -0700 Subject: compiler.h: drop fallback overflow checkers Once upgrading the minimum supported version of GCC to 5.1, we can drop the fallback code for !COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW. This is effectively a revert of commit f0907827a8a9 ("compiler.h: enable builtin overflow checkers and add fallback code") Link: https://github.com/ClangBuiltLinux/linux/issues/1438#issuecomment-916745801 Suggested-by: Rasmus Villemoes Signed-off-by: Nick Desaulniers Acked-by: Kees Cook Reviewed-by: Nathan Chancellor Signed-off-by: Linus Torvalds --- include/linux/compiler-clang.h | 13 ---- include/linux/compiler-gcc.h | 4 -- include/linux/overflow.h | 138 +----------------------------------- tools/include/linux/compiler-gcc.h | 4 -- tools/include/linux/overflow.h | 140 +------------------------------------ 5 files changed, 6 insertions(+), 293 deletions(-) (limited to 'include') diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index 49b0ac8b6fd3..3c4de9b6c6e3 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -62,19 +62,6 @@ #define __no_sanitize_coverage #endif -/* - * Not all versions of clang implement the type-generic versions - * of the builtin overflow checkers. Fortunately, clang implements - * __has_builtin allowing us to avoid awkward version - * checks. Unfortunately, we don't know which version of gcc clang - * pretends to be, so the macro may or may not be defined. - */ -#if __has_builtin(__builtin_mul_overflow) && \ - __has_builtin(__builtin_add_overflow) && \ - __has_builtin(__builtin_sub_overflow) -#define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1 -#endif - #if __has_feature(shadow_call_stack) # define __noscs __attribute__((__no_sanitize__("shadow-call-stack"))) #endif diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index cb9217fc60af..3f7f6fa0e051 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -128,10 +128,6 @@ #define __no_sanitize_coverage #endif -#if GCC_VERSION >= 50100 -#define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1 -#endif - /* * Turn individual warnings and errors on and off locally, depending * on version. diff --git a/include/linux/overflow.h b/include/linux/overflow.h index 0f12345c21fb..4669632bd72b 100644 --- a/include/linux/overflow.h +++ b/include/linux/overflow.h @@ -6,12 +6,9 @@ #include /* - * In the fallback code below, we need to compute the minimum and - * maximum values representable in a given type. These macros may also - * be useful elsewhere, so we provide them outside the - * COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW block. - * - * It would seem more obvious to do something like + * We need to compute the minimum and maximum values representable in a given + * type. These macros may also be useful elsewhere. It would seem more obvious + * to do something like: * * #define type_min(T) (T)(is_signed_type(T) ? (T)1 << (8*sizeof(T)-1) : 0) * #define type_max(T) (T)(is_signed_type(T) ? ((T)1 << (8*sizeof(T)-1)) - 1 : ~(T)0) @@ -54,7 +51,6 @@ static inline bool __must_check __must_check_overflow(bool overflow) return unlikely(overflow); } -#ifdef COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW /* * For simplicity and code hygiene, the fallback code below insists on * a, b and *d having the same type (similar to the min() and max() @@ -90,134 +86,6 @@ static inline bool __must_check __must_check_overflow(bool overflow) __builtin_mul_overflow(__a, __b, __d); \ })) -#else - - -/* Checking for unsigned overflow is relatively easy without causing UB. */ -#define __unsigned_add_overflow(a, b, d) ({ \ - typeof(a) __a = (a); \ - typeof(b) __b = (b); \ - typeof(d) __d = (d); \ - (void) (&__a == &__b); \ - (void) (&__a == __d); \ - *__d = __a + __b; \ - *__d < __a; \ -}) -#define __unsigned_sub_overflow(a, b, d) ({ \ - typeof(a) __a = (a); \ - typeof(b) __b = (b); \ - typeof(d) __d = (d); \ - (void) (&__a == &__b); \ - (void) (&__a == __d); \ - *__d = __a - __b; \ - __a < __b; \ -}) -/* - * If one of a or b is a compile-time constant, this avoids a division. - */ -#define __unsigned_mul_overflow(a, b, d) ({ \ - typeof(a) __a = (a); \ - typeof(b) __b = (b); \ - typeof(d) __d = (d); \ - (void) (&__a == &__b); \ - (void) (&__a == __d); \ - *__d = __a * __b; \ - __builtin_constant_p(__b) ? \ - __b > 0 && __a > type_max(typeof(__a)) / __b : \ - __a > 0 && __b > type_max(typeof(__b)) / __a; \ -}) - -/* - * For signed types, detecting overflow is much harder, especially if - * we want to avoid UB. But the interface of these macros is such that - * we must provide a result in *d, and in fact we must produce the - * result promised by gcc's builtins, which is simply the possibly - * wrapped-around value. Fortunately, we can just formally do the - * operations in the widest relevant unsigned type (u64) and then - * truncate the result - gcc is smart enough to generate the same code - * with and without the (u64) casts. - */ - -/* - * Adding two signed integers can overflow only if they have the same - * sign, and overflow has happened iff the result has the opposite - * sign. - */ -#define __signed_add_overflow(a, b, d) ({ \ - typeof(a) __a = (a); \ - typeof(b) __b = (b); \ - typeof(d) __d = (d); \ - (void) (&__a == &__b); \ - (void) (&__a == __d); \ - *__d = (u64)__a + (u64)__b; \ - (((~(__a ^ __b)) & (*__d ^ __a)) \ - & type_min(typeof(__a))) != 0; \ -}) - -/* - * Subtraction is similar, except that overflow can now happen only - * when the signs are opposite. In this case, overflow has happened if - * the result has the opposite sign of a. - */ -#define __signed_sub_overflow(a, b, d) ({ \ - typeof(a) __a = (a); \ - typeof(b) __b = (b); \ - typeof(d) __d = (d); \ - (void) (&__a == &__b); \ - (void) (&__a == __d); \ - *__d = (u64)__a - (u64)__b; \ - ((((__a ^ __b)) & (*__d ^ __a)) \ - & type_min(typeof(__a))) != 0; \ -}) - -/* - * Signed multiplication is rather hard. gcc always follows C99, so - * division is truncated towards 0. This means that we can write the - * overflow check like this: - * - * (a > 0 && (b > MAX/a || b < MIN/a)) || - * (a < -1 && (b > MIN/a || b < MAX/a) || - * (a == -1 && b == MIN) - * - * The redundant casts of -1 are to silence an annoying -Wtype-limits - * (included in -Wextra) warning: When the type is u8 or u16, the - * __b_c_e in check_mul_overflow obviously selects - * __unsigned_mul_overflow, but unfortunately gcc still parses this - * code and warns about the limited range of __b. - */ - -#define __signed_mul_overflow(a, b, d) ({ \ - typeof(a) __a = (a); \ - typeof(b) __b = (b); \ - typeof(d) __d = (d); \ - typeof(a) __tmax = type_max(typeof(a)); \ - typeof(a) __tmin = type_min(typeof(a)); \ - (void) (&__a == &__b); \ - (void) (&__a == __d); \ - *__d = (u64)__a * (u64)__b; \ - (__b > 0 && (__a > __tmax/__b || __a < __tmin/__b)) || \ - (__b < (typeof(__b))-1 && (__a > __tmin/__b || __a < __tmax/__b)) || \ - (__b == (typeof(__b))-1 && __a == __tmin); \ -}) - - -#define check_add_overflow(a, b, d) __must_check_overflow( \ - __builtin_choose_expr(is_signed_type(typeof(a)), \ - __signed_add_overflow(a, b, d), \ - __unsigned_add_overflow(a, b, d))) - -#define check_sub_overflow(a, b, d) __must_check_overflow( \ - __builtin_choose_expr(is_signed_type(typeof(a)), \ - __signed_sub_overflow(a, b, d), \ - __unsigned_sub_overflow(a, b, d))) - -#define check_mul_overflow(a, b, d) __must_check_overflow( \ - __builtin_choose_expr(is_signed_type(typeof(a)), \ - __signed_mul_overflow(a, b, d), \ - __unsigned_mul_overflow(a, b, d))) - -#endif /* COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW */ - /** check_shl_overflow() - Calculate a left-shifted value and check overflow * * @a: Value to be shifted diff --git a/tools/include/linux/compiler-gcc.h b/tools/include/linux/compiler-gcc.h index 95c072b70d0e..a590a1dfafd9 100644 --- a/tools/include/linux/compiler-gcc.h +++ b/tools/include/linux/compiler-gcc.h @@ -38,7 +38,3 @@ #endif #define __printf(a, b) __attribute__((format(printf, a, b))) #define __scanf(a, b) __attribute__((format(scanf, a, b))) - -#if GCC_VERSION >= 50100 -#define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1 -#endif diff --git a/tools/include/linux/overflow.h b/tools/include/linux/overflow.h index 8712ff70995f..dcb0c1bf6866 100644 --- a/tools/include/linux/overflow.h +++ b/tools/include/linux/overflow.h @@ -5,12 +5,9 @@ #include /* - * In the fallback code below, we need to compute the minimum and - * maximum values representable in a given type. These macros may also - * be useful elsewhere, so we provide them outside the - * COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW block. - * - * It would seem more obvious to do something like + * We need to compute the minimum and maximum values representable in a given + * type. These macros may also be useful elsewhere. It would seem more obvious + * to do something like: * * #define type_min(T) (T)(is_signed_type(T) ? (T)1 << (8*sizeof(T)-1) : 0) * #define type_max(T) (T)(is_signed_type(T) ? ((T)1 << (8*sizeof(T)-1)) - 1 : ~(T)0) @@ -36,8 +33,6 @@ #define type_max(T) ((T)((__type_half_max(T) - 1) + __type_half_max(T))) #define type_min(T) ((T)((T)-type_max(T)-(T)1)) - -#ifdef COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW /* * For simplicity and code hygiene, the fallback code below insists on * a, b and *d having the same type (similar to the min() and max() @@ -73,135 +68,6 @@ __builtin_mul_overflow(__a, __b, __d); \ }) -#else - - -/* Checking for unsigned overflow is relatively easy without causing UB. */ -#define __unsigned_add_overflow(a, b, d) ({ \ - typeof(a) __a = (a); \ - typeof(b) __b = (b); \ - typeof(d) __d = (d); \ - (void) (&__a == &__b); \ - (void) (&__a == __d); \ - *__d = __a + __b; \ - *__d < __a; \ -}) -#define __unsigned_sub_overflow(a, b, d) ({ \ - typeof(a) __a = (a); \ - typeof(b) __b = (b); \ - typeof(d) __d = (d); \ - (void) (&__a == &__b); \ - (void) (&__a == __d); \ - *__d = __a - __b; \ - __a < __b; \ -}) -/* - * If one of a or b is a compile-time constant, this avoids a division. - */ -#define __unsigned_mul_overflow(a, b, d) ({ \ - typeof(a) __a = (a); \ - typeof(b) __b = (b); \ - typeof(d) __d = (d); \ - (void) (&__a == &__b); \ - (void) (&__a == __d); \ - *__d = __a * __b; \ - __builtin_constant_p(__b) ? \ - __b > 0 && __a > type_max(typeof(__a)) / __b : \ - __a > 0 && __b > type_max(typeof(__b)) / __a; \ -}) - -/* - * For signed types, detecting overflow is much harder, especially if - * we want to avoid UB. But the interface of these macros is such that - * we must provide a result in *d, and in fact we must produce the - * result promised by gcc's builtins, which is simply the possibly - * wrapped-around value. Fortunately, we can just formally do the - * operations in the widest relevant unsigned type (u64) and then - * truncate the result - gcc is smart enough to generate the same code - * with and without the (u64) casts. - */ - -/* - * Adding two signed integers can overflow only if they have the same - * sign, and overflow has happened iff the result has the opposite - * sign. - */ -#define __signed_add_overflow(a, b, d) ({ \ - typeof(a) __a = (a); \ - typeof(b) __b = (b); \ - typeof(d) __d = (d); \ - (void) (&__a == &__b); \ - (void) (&__a == __d); \ - *__d = (u64)__a + (u64)__b; \ - (((~(__a ^ __b)) & (*__d ^ __a)) \ - & type_min(typeof(__a))) != 0; \ -}) - -/* - * Subtraction is similar, except that overflow can now happen only - * when the signs are opposite. In this case, overflow has happened if - * the result has the opposite sign of a. - */ -#define __signed_sub_overflow(a, b, d) ({ \ - typeof(a) __a = (a); \ - typeof(b) __b = (b); \ - typeof(d) __d = (d); \ - (void) (&__a == &__b); \ - (void) (&__a == __d); \ - *__d = (u64)__a - (u64)__b; \ - ((((__a ^ __b)) & (*__d ^ __a)) \ - & type_min(typeof(__a))) != 0; \ -}) - -/* - * Signed multiplication is rather hard. gcc always follows C99, so - * division is truncated towards 0. This means that we can write the - * overflow check like this: - * - * (a > 0 && (b > MAX/a || b < MIN/a)) || - * (a < -1 && (b > MIN/a || b < MAX/a) || - * (a == -1 && b == MIN) - * - * The redundant casts of -1 are to silence an annoying -Wtype-limits - * (included in -Wextra) warning: When the type is u8 or u16, the - * __b_c_e in check_mul_overflow obviously selects - * __unsigned_mul_overflow, but unfortunately gcc still parses this - * code and warns about the limited range of __b. - */ - -#define __signed_mul_overflow(a, b, d) ({ \ - typeof(a) __a = (a); \ - typeof(b) __b = (b); \ - typeof(d) __d = (d); \ - typeof(a) __tmax = type_max(typeof(a)); \ - typeof(a) __tmin = type_min(typeof(a)); \ - (void) (&__a == &__b); \ - (void) (&__a == __d); \ - *__d = (u64)__a * (u64)__b; \ - (__b > 0 && (__a > __tmax/__b || __a < __tmin/__b)) || \ - (__b < (typeof(__b))-1 && (__a > __tmin/__b || __a < __tmax/__b)) || \ - (__b == (typeof(__b))-1 && __a == __tmin); \ -}) - - -#define check_add_overflow(a, b, d) \ - __builtin_choose_expr(is_signed_type(typeof(a)), \ - __signed_add_overflow(a, b, d), \ - __unsigned_add_overflow(a, b, d)) - -#define check_sub_overflow(a, b, d) \ - __builtin_choose_expr(is_signed_type(typeof(a)), \ - __signed_sub_overflow(a, b, d), \ - __unsigned_sub_overflow(a, b, d)) - -#define check_mul_overflow(a, b, d) \ - __builtin_choose_expr(is_signed_type(typeof(a)), \ - __signed_mul_overflow(a, b, d), \ - __unsigned_mul_overflow(a, b, d)) - - -#endif /* COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW */ - /** * array_size() - Calculate size of 2-dimensional array. * -- cgit v1.2.3 From 4e59869aa6550657cb148ad49835605660ec9b88 Mon Sep 17 00:00:00 2001 From: Nick Desaulniers Date: Fri, 10 Sep 2021 16:40:46 -0700 Subject: compiler-gcc.h: drop checks for older GCC versions Now that GCC 5.1 is the minimally supported default, drop the values we don't use. Signed-off-by: Nick Desaulniers Reviewed-by: Kees Cook Reviewed-by: Nathan Chancellor Signed-off-by: Linus Torvalds --- include/linux/compiler-gcc.h | 4 +--- tools/include/linux/compiler-gcc.h | 4 +--- 2 files changed, 2 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 3f7f6fa0e051..fd82ce169ce9 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -98,10 +98,8 @@ #if GCC_VERSION >= 70000 #define KASAN_ABI_VERSION 5 -#elif GCC_VERSION >= 50000 +#else #define KASAN_ABI_VERSION 4 -#elif GCC_VERSION >= 40902 -#define KASAN_ABI_VERSION 3 #endif #if __has_attribute(__no_sanitize_address__) diff --git a/tools/include/linux/compiler-gcc.h b/tools/include/linux/compiler-gcc.h index a590a1dfafd9..43d9a46d36f0 100644 --- a/tools/include/linux/compiler-gcc.h +++ b/tools/include/linux/compiler-gcc.h @@ -16,9 +16,7 @@ # define __fallthrough __attribute__ ((fallthrough)) #endif -#if GCC_VERSION >= 40300 -# define __compiletime_error(message) __attribute__((error(message))) -#endif /* GCC_VERSION >= 40300 */ +#define __compiletime_error(message) __attribute__((error(message))) /* &a[0] degrades to a pointer: a different type from an array */ #define __must_be_array(a) BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0])) -- cgit v1.2.3 From 6f20fa2dfa549401860479328371f0d5cee9b114 Mon Sep 17 00:00:00 2001 From: Nick Desaulniers Date: Fri, 10 Sep 2021 16:40:47 -0700 Subject: vmlinux.lds.h: remove old check for GCC 4.9 Now that GCC 5.1 is the minimally supported version of GCC, we can effectively revert commit 85c2ce9104eb ("sched, vmlinux.lds: Increase STRUCT_ALIGNMENT to 64 bytes for GCC-4.9") Cc: Peter Zijlstra Signed-off-by: Nick Desaulniers Acked-by: Kees Cook Signed-off-by: Linus Torvalds --- include/asm-generic/vmlinux.lds.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index aa50bf2959fe..f2984af2b85b 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -116,11 +116,7 @@ * GCC 4.5 and later have a 32 bytes section alignment for structures. * Except GCC 4.9, that feels the need to align on 64 bytes. */ -#if __GNUC__ == 4 && __GNUC_MINOR__ == 9 -#define STRUCT_ALIGNMENT 64 -#else #define STRUCT_ALIGNMENT 32 -#endif #define STRUCT_ALIGN() . = ALIGN(STRUCT_ALIGNMENT) /* -- cgit v1.2.3 From 6d2ef226f2f18d530e48ead0cb5704505628b797 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 13 Sep 2021 10:20:01 -0700 Subject: compiler_attributes.h: drop __has_attribute() support for gcc4 Now that GCC 5.1 is the minimally supported default, the manual workaround for older gcc versions not having __has_attribute() are no longer relevant and can be removed. Signed-off-by: Linus Torvalds --- include/linux/compiler_attributes.h | 20 -------------------- 1 file changed, 20 deletions(-) (limited to 'include') diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h index 2487be0e7199..ba417a5c80af 100644 --- a/include/linux/compiler_attributes.h +++ b/include/linux/compiler_attributes.h @@ -20,26 +20,6 @@ * Provide links to the documentation of each supported compiler, if it exists. */ -/* - * __has_attribute is supported on gcc >= 5, clang >= 2.9 and icc >= 17. - * In the meantime, to support gcc < 5, we implement __has_attribute - * by hand. - */ -#ifndef __has_attribute -# define __has_attribute(x) __GCC4_has_attribute_##x -# define __GCC4_has_attribute___assume_aligned__ 1 -# define __GCC4_has_attribute___copy__ 0 -# define __GCC4_has_attribute___designated_init__ 0 -# define __GCC4_has_attribute___externally_visible__ 1 -# define __GCC4_has_attribute___no_caller_saved_registers__ 0 -# define __GCC4_has_attribute___noclone__ 1 -# define __GCC4_has_attribute___no_profile_instrument_function__ 0 -# define __GCC4_has_attribute___nonstring__ 0 -# define __GCC4_has_attribute___no_sanitize_address__ 1 -# define __GCC4_has_attribute___no_sanitize_undefined__ 1 -# define __GCC4_has_attribute___fallthrough__ 0 -#endif - /* * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-alias-function-attribute */ -- cgit v1.2.3 From df26327ea097eb78e7967c45df6b23010c43c28d Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 13 Sep 2021 10:29:44 -0700 Subject: Drop some straggling mentions of gcc-4.9 as being stale Fix up the admin-guide README file to the new gcc-5.1 requirement, and remove a stale comment about gcc support for the __assume_aligned__ attribute. Signed-off-by: Linus Torvalds --- Documentation/admin-guide/README.rst | 2 +- Documentation/translations/zh_CN/admin-guide/README.rst | 2 +- Documentation/translations/zh_TW/admin-guide/README.rst | 2 +- include/linux/compiler_attributes.h | 1 - 4 files changed, 3 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/Documentation/admin-guide/README.rst b/Documentation/admin-guide/README.rst index 35314b63008c..caa3c09a5c3f 100644 --- a/Documentation/admin-guide/README.rst +++ b/Documentation/admin-guide/README.rst @@ -259,7 +259,7 @@ Configuring the kernel Compiling the kernel -------------------- - - Make sure you have at least gcc 4.9 available. + - Make sure you have at least gcc 5.1 available. For more information, refer to :ref:`Documentation/process/changes.rst `. Please note that you can still run a.out user programs with this kernel. diff --git a/Documentation/translations/zh_CN/admin-guide/README.rst b/Documentation/translations/zh_CN/admin-guide/README.rst index 669a022f6817..980eb20521cf 100644 --- a/Documentation/translations/zh_CN/admin-guide/README.rst +++ b/Documentation/translations/zh_CN/admin-guide/README.rst @@ -223,7 +223,7 @@ Linux内核5.x版本 编译内核 --------- - - 确保您至少有gcc 4.9可用。 + - 确保您至少有gcc 5.1可用。 有关更多信息，请参阅 :ref:`Documentation/process/changes.rst ` 。 请注意，您仍然可以使用此内核运行a.out用户程序。 diff --git a/Documentation/translations/zh_TW/admin-guide/README.rst b/Documentation/translations/zh_TW/admin-guide/README.rst index b752e50359e6..6ce97edbab37 100644 --- a/Documentation/translations/zh_TW/admin-guide/README.rst +++ b/Documentation/translations/zh_TW/admin-guide/README.rst @@ -226,7 +226,7 @@ Linux內核5.x版本 編譯內核 --------- - - 確保您至少有gcc 4.9可用。 + - 確保您至少有gcc 5.1可用。 有關更多信息，請參閱 :ref:`Documentation/process/changes.rst ` 。 請注意，您仍然可以使用此內核運行a.out用戶程序。 diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h index ba417a5c80af..ee19cebabcf5 100644 --- a/include/linux/compiler_attributes.h +++ b/include/linux/compiler_attributes.h @@ -54,7 +54,6 @@ * compiler should see some alignment anyway, when the return value is * massaged by 'flags = ptr & 3; ptr &= ~3;'). * - * Optional: only supported since gcc >= 4.9 * Optional: not supported by icc * * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-assume_005faligned-function-attribute -- cgit v1.2.3 From 8520e224f547cd070c7c8f97b1fc6d58cff7ccaa Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 14 Sep 2021 01:07:57 +0200 Subject: bpf, cgroups: Fix cgroup v2 fallback on v1/v2 mixed mode Fix cgroup v1 interference when non-root cgroup v2 BPF programs are used. Back in the days, commit bd1060a1d671 ("sock, cgroup: add sock->sk_cgroup") embedded per-socket cgroup information into sock->sk_cgrp_data and in order to save 8 bytes in struct sock made both mutually exclusive, that is, when cgroup v1 socket tagging (e.g. net_cls/net_prio) is used, then cgroup v2 falls back to the root cgroup in sock_cgroup_ptr() (&cgrp_dfl_root.cgrp). The assumption made was "there is no reason to mix the two and this is in line with how legacy and v2 compatibility is handled" as stated in bd1060a1d671. However, with Kubernetes more widely supporting cgroups v2 as well nowadays, this assumption no longer holds, and the possibility of the v1/v2 mixed mode with the v2 root fallback being hit becomes a real security issue. Many of the cgroup v2 BPF programs are also used for policy enforcement, just to pick _one_ example, that is, to programmatically deny socket related system calls like connect(2) or bind(2). A v2 root fallback would implicitly cause a policy bypass for the affected Pods. In production environments, we have recently seen this case due to various circumstances: i) a different 3rd party agent and/or ii) a container runtime such as [0] in the user's environment configuring legacy cgroup v1 net_cls tags, which triggered implicitly mentioned root fallback. Another case is Kubernetes projects like kind [1] which create Kubernetes nodes in a container and also add cgroup namespaces to the mix, meaning programs which are attached to the cgroup v2 root of the cgroup namespace get attached to a non-root cgroup v2 path from init namespace point of view. And the latter's root is out of reach for agents on a kind Kubernetes node to configure. Meaning, any entity on the node setting cgroup v1 net_cls tag will trigger the bypass despite cgroup v2 BPF programs attached to the namespace root. Generally, this mutual exclusiveness does not hold anymore in today's user environments and makes cgroup v2 usage from BPF side fragile and unreliable. This fix adds proper struct cgroup pointer for the cgroup v2 case to struct sock_cgroup_data in order to address these issues; this implicitly also fixes the tradeoffs being made back then with regards to races and refcount leaks as stated in bd1060a1d671, and removes the fallback, so that cgroup v2 BPF programs always operate as expected. [0] https://github.com/nestybox/sysbox/ [1] https://kind.sigs.k8s.io/ Fixes: bd1060a1d671 ("sock, cgroup: add sock->sk_cgroup") Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Acked-by: Stanislav Fomichev Acked-by: Tejun Heo Link: https://lore.kernel.org/bpf/20210913230759.2313-1-daniel@iogearbox.net --- include/linux/cgroup-defs.h | 107 +++++++++++-------------------------------- include/linux/cgroup.h | 22 +-------- kernel/cgroup/cgroup.c | 50 ++++---------------- net/core/netclassid_cgroup.c | 7 +-- net/core/netprio_cgroup.c | 10 +--- 5 files changed, 41 insertions(+), 155 deletions(-) (limited to 'include') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index e1c705fdfa7c..db2e147e069f 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -752,107 +752,54 @@ static inline void cgroup_threadgroup_change_end(struct task_struct *tsk) {} * sock_cgroup_data is embedded at sock->sk_cgrp_data and contains * per-socket cgroup information except for memcg association. * - * On legacy hierarchies, net_prio and net_cls controllers directly set - * attributes on each sock which can then be tested by the network layer. - * On the default hierarchy, each sock is associated with the cgroup it was - * created in and the networking layer can match the cgroup directly. - * - * To avoid carrying all three cgroup related fields separately in sock, - * sock_cgroup_data overloads (prioidx, classid) and the cgroup pointer. - * On boot, sock_cgroup_data records the cgroup that the sock was created - * in so that cgroup2 matches can be made; however, once either net_prio or - * net_cls starts being used, the area is overridden to carry prioidx and/or - * classid. The two modes are distinguished by whether the lowest bit is - * set. Clear bit indicates cgroup pointer while set bit prioidx and - * classid. - * - * While userland may start using net_prio or net_cls at any time, once - * either is used, cgroup2 matching no longer works. There is no reason to - * mix the two and this is in line with how legacy and v2 compatibility is - * handled. On mode switch, cgroup references which are already being - * pointed to by socks may be leaked. While this can be remedied by adding - * synchronization around sock_cgroup_data, given that the number of leaked - * cgroups is bound and highly unlikely to be high, this seems to be the - * better trade-off. + * On legacy hierarchies, net_prio and net_cls controllers directly + * set attributes on each sock which can then be tested by the network + * layer. On the default hierarchy, each sock is associated with the + * cgroup it was created in and the networking layer can match the + * cgroup directly. */ struct sock_cgroup_data { - union { -#ifdef __LITTLE_ENDIAN - struct { - u8 is_data : 1; - u8 no_refcnt : 1; - u8 unused : 6; - u8 padding; - u16 prioidx; - u32 classid; - } __packed; -#else - struct { - u32 classid; - u16 prioidx; - u8 padding; - u8 unused : 6; - u8 no_refcnt : 1; - u8 is_data : 1; - } __packed; + struct cgroup *cgroup; /* v2 */ +#ifdef CONFIG_CGROUP_NET_CLASSID + u32 classid; /* v1 */ +#endif +#ifdef CONFIG_CGROUP_NET_PRIO + u16 prioidx; /* v1 */ #endif - u64 val; - }; }; -/* - * There's a theoretical window where the following accessors race with - * updaters and return part of the previous pointer as the prioidx or - * classid. Such races are short-lived and the result isn't critical. - */ static inline u16 sock_cgroup_prioidx(const struct sock_cgroup_data *skcd) { - /* fallback to 1 which is always the ID of the root cgroup */ - return (skcd->is_data & 1) ? skcd->prioidx : 1; +#ifdef CONFIG_CGROUP_NET_PRIO + return READ_ONCE(skcd->prioidx); +#else + return 1; +#endif } static inline u32 sock_cgroup_classid(const struct sock_cgroup_data *skcd) { - /* fallback to 0 which is the unconfigured default classid */ - return (skcd->is_data & 1) ? skcd->classid : 0; +#ifdef CONFIG_CGROUP_NET_CLASSID + return READ_ONCE(skcd->classid); +#else + return 0; +#endif } -/* - * If invoked concurrently, the updaters may clobber each other. The - * caller is responsible for synchronization. - */ static inline void sock_cgroup_set_prioidx(struct sock_cgroup_data *skcd, u16 prioidx) { - struct sock_cgroup_data skcd_buf = {{ .val = READ_ONCE(skcd->val) }}; - - if (sock_cgroup_prioidx(&skcd_buf) == prioidx) - return; - - if (!(skcd_buf.is_data & 1)) { - skcd_buf.val = 0; - skcd_buf.is_data = 1; - } - - skcd_buf.prioidx = prioidx; - WRITE_ONCE(skcd->val, skcd_buf.val); /* see sock_cgroup_ptr() */ +#ifdef CONFIG_CGROUP_NET_PRIO + WRITE_ONCE(skcd->prioidx, prioidx); +#endif } static inline void sock_cgroup_set_classid(struct sock_cgroup_data *skcd, u32 classid) { - struct sock_cgroup_data skcd_buf = {{ .val = READ_ONCE(skcd->val) }}; - - if (sock_cgroup_classid(&skcd_buf) == classid) - return; - - if (!(skcd_buf.is_data & 1)) { - skcd_buf.val = 0; - skcd_buf.is_data = 1; - } - - skcd_buf.classid = classid; - WRITE_ONCE(skcd->val, skcd_buf.val); /* see sock_cgroup_ptr() */ +#ifdef CONFIG_CGROUP_NET_CLASSID + WRITE_ONCE(skcd->classid, classid); +#endif } #else /* CONFIG_SOCK_CGROUP_DATA */ diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 7bf60454a313..75c151413fda 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -829,33 +829,13 @@ static inline void cgroup_account_cputime_field(struct task_struct *task, */ #ifdef CONFIG_SOCK_CGROUP_DATA -#if defined(CONFIG_CGROUP_NET_PRIO) || defined(CONFIG_CGROUP_NET_CLASSID) -extern spinlock_t cgroup_sk_update_lock; -#endif - -void cgroup_sk_alloc_disable(void); void cgroup_sk_alloc(struct sock_cgroup_data *skcd); void cgroup_sk_clone(struct sock_cgroup_data *skcd); void cgroup_sk_free(struct sock_cgroup_data *skcd); static inline struct cgroup *sock_cgroup_ptr(struct sock_cgroup_data *skcd) { -#if defined(CONFIG_CGROUP_NET_PRIO) || defined(CONFIG_CGROUP_NET_CLASSID) - unsigned long v; - - /* - * @skcd->val is 64bit but the following is safe on 32bit too as we - * just need the lower ulong to be written and read atomically. - */ - v = READ_ONCE(skcd->val); - - if (v & 3) - return &cgrp_dfl_root.cgrp; - - return (struct cgroup *)(unsigned long)v ?: &cgrp_dfl_root.cgrp; -#else - return (struct cgroup *)(unsigned long)skcd->val; -#endif + return skcd->cgroup; } #else /* CONFIG_CGROUP_DATA */ diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 881ce1470beb..8afa8690d288 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -6572,74 +6572,44 @@ int cgroup_parse_float(const char *input, unsigned dec_shift, s64 *v) */ #ifdef CONFIG_SOCK_CGROUP_DATA -#if defined(CONFIG_CGROUP_NET_PRIO) || defined(CONFIG_CGROUP_NET_CLASSID) - -DEFINE_SPINLOCK(cgroup_sk_update_lock); -static bool cgroup_sk_alloc_disabled __read_mostly; - -void cgroup_sk_alloc_disable(void) -{ - if (cgroup_sk_alloc_disabled) - return; - pr_info("cgroup: disabling cgroup2 socket matching due to net_prio or net_cls activation\n"); - cgroup_sk_alloc_disabled = true; -} - -#else - -#define cgroup_sk_alloc_disabled false - -#endif - void cgroup_sk_alloc(struct sock_cgroup_data *skcd) { - if (cgroup_sk_alloc_disabled) { - skcd->no_refcnt = 1; - return; - } - /* Don't associate the sock with unrelated interrupted task's cgroup. */ if (in_interrupt()) return; rcu_read_lock(); - while (true) { struct css_set *cset; cset = task_css_set(current); if (likely(cgroup_tryget(cset->dfl_cgrp))) { - skcd->val = (unsigned long)cset->dfl_cgrp; + skcd->cgroup = cset->dfl_cgrp; cgroup_bpf_get(cset->dfl_cgrp); break; } cpu_relax(); } - rcu_read_unlock(); } void cgroup_sk_clone(struct sock_cgroup_data *skcd) { - if (skcd->val) { - if (skcd->no_refcnt) - return; - /* - * We might be cloning a socket which is left in an empty - * cgroup and the cgroup might have already been rmdir'd. - * Don't use cgroup_get_live(). - */ - cgroup_get(sock_cgroup_ptr(skcd)); - cgroup_bpf_get(sock_cgroup_ptr(skcd)); - } + struct cgroup *cgrp = sock_cgroup_ptr(skcd); + + /* + * We might be cloning a socket which is left in an empty + * cgroup and the cgroup might have already been rmdir'd. + * Don't use cgroup_get_live(). + */ + cgroup_get(cgrp); + cgroup_bpf_get(cgrp); } void cgroup_sk_free(struct sock_cgroup_data *skcd) { struct cgroup *cgrp = sock_cgroup_ptr(skcd); - if (skcd->no_refcnt) - return; cgroup_bpf_put(cgrp); cgroup_put(cgrp); } diff --git a/net/core/netclassid_cgroup.c b/net/core/netclassid_cgroup.c index b49c57d35a88..1a6a86693b74 100644 --- a/net/core/netclassid_cgroup.c +++ b/net/core/netclassid_cgroup.c @@ -71,11 +71,8 @@ static int update_classid_sock(const void *v, struct file *file, unsigned n) struct update_classid_context *ctx = (void *)v; struct socket *sock = sock_from_file(file); - if (sock) { - spin_lock(&cgroup_sk_update_lock); + if (sock) sock_cgroup_set_classid(&sock->sk->sk_cgrp_data, ctx->classid); - spin_unlock(&cgroup_sk_update_lock); - } if (--ctx->batch == 0) { ctx->batch = UPDATE_CLASSID_BATCH; return n + 1; @@ -121,8 +118,6 @@ static int write_classid(struct cgroup_subsys_state *css, struct cftype *cft, struct css_task_iter it; struct task_struct *p; - cgroup_sk_alloc_disable(); - cs->classid = (u32)value; css_task_iter_start(css, 0, &it); diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c index 99a431c56f23..8456dfbe2eb4 100644 --- a/net/core/netprio_cgroup.c +++ b/net/core/netprio_cgroup.c @@ -207,8 +207,6 @@ static ssize_t write_priomap(struct kernfs_open_file *of, if (!dev) return -ENODEV; - cgroup_sk_alloc_disable(); - rtnl_lock(); ret = netprio_set_prio(of_css(of), dev, prio); @@ -221,12 +219,10 @@ static ssize_t write_priomap(struct kernfs_open_file *of, static int update_netprio(const void *v, struct file *file, unsigned n) { struct socket *sock = sock_from_file(file); - if (sock) { - spin_lock(&cgroup_sk_update_lock); + + if (sock) sock_cgroup_set_prioidx(&sock->sk->sk_cgrp_data, (unsigned long)v); - spin_unlock(&cgroup_sk_update_lock); - } return 0; } @@ -235,8 +231,6 @@ static void net_prio_attach(struct cgroup_taskset *tset) struct task_struct *p; struct cgroup_subsys_state *css; - cgroup_sk_alloc_disable(); - cgroup_taskset_for_each(p, css, tset) { void *v = (void *)(unsigned long)css->id; -- cgit v1.2.3 From 81065b35e2486c024c7aa86caed452e1f01a59d4 Mon Sep 17 00:00:00 2001 From: Tony Luck Date: Mon, 13 Sep 2021 14:52:39 -0700 Subject: x86/mce: Avoid infinite loop for copy from user recovery There are two cases for machine check recovery: 1) The machine check was triggered by ring3 (application) code. This is the simpler case. The machine check handler simply queues work to be executed on return to user. That code unmaps the page from all users and arranges to send a SIGBUS to the task that triggered the poison. 2) The machine check was triggered in kernel code that is covered by an exception table entry. In this case the machine check handler still queues a work entry to unmap the page, etc. but this will not be called right away because the #MC handler returns to the fix up code address in the exception table entry. Problems occur if the kernel triggers another machine check before the return to user processes the first queued work item. Specifically, the work is queued using the ->mce_kill_me callback structure in the task struct for the current thread. Attempting to queue a second work item using this same callback results in a loop in the linked list of work functions to call. So when the kernel does return to user, it enters an infinite loop processing the same entry for ever. There are some legitimate scenarios where the kernel may take a second machine check before returning to the user. 1) Some code (e.g. futex) first tries a get_user() with page faults disabled. If this fails, the code retries with page faults enabled expecting that this will resolve the page fault. 2) Copy from user code retries a copy in byte-at-time mode to check whether any additional bytes can be copied. On the other side of the fence are some bad drivers that do not check the return value from individual get_user() calls and may access multiple user addresses without noticing that some/all calls have failed. Fix by adding a counter (current->mce_count) to keep track of repeated machine checks before task_work() is called. First machine check saves the address information and calls task_work_add(). Subsequent machine checks before that task_work call back is executed check that the address is in the same page as the first machine check (since the callback will offline exactly one page). Expected worst case is four machine checks before moving on (e.g. one user access with page faults disabled, then a repeat to the same address with page faults enabled ... repeat in copy tail bytes). Just in case there is some code that loops forever enforce a limit of 10. [ bp: Massage commit message, drop noinstr, fix typo, extend panic messages. ] Fixes: 5567d11c21a1 ("x86/mce: Send #MC singal from task work") Signed-off-by: Tony Luck Signed-off-by: Borislav Petkov Cc: Link: https://lkml.kernel.org/r/YT/IJ9ziLqmtqEPu@agluck-desk2.amr.corp.intel.com --- arch/x86/kernel/cpu/mce/core.c | 43 +++++++++++++++++++++++++++++++----------- include/linux/sched.h | 1 + 2 files changed, 33 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 8cb7816d03b4..193204aee880 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -1253,6 +1253,9 @@ static void __mc_scan_banks(struct mce *m, struct pt_regs *regs, struct mce *fin static void kill_me_now(struct callback_head *ch) { + struct task_struct *p = container_of(ch, struct task_struct, mce_kill_me); + + p->mce_count = 0; force_sig(SIGBUS); } @@ -1262,6 +1265,7 @@ static void kill_me_maybe(struct callback_head *cb) int flags = MF_ACTION_REQUIRED; int ret; + p->mce_count = 0; pr_err("Uncorrected hardware memory error in user-access at %llx", p->mce_addr); if (!p->mce_ripv) @@ -1290,17 +1294,34 @@ static void kill_me_maybe(struct callback_head *cb) } } -static void queue_task_work(struct mce *m, int kill_current_task) +static void queue_task_work(struct mce *m, char *msg, int kill_current_task) { - current->mce_addr = m->addr; - current->mce_kflags = m->kflags; - current->mce_ripv = !!(m->mcgstatus & MCG_STATUS_RIPV); - current->mce_whole_page = whole_page(m); + int count = ++current->mce_count; - if (kill_current_task) - current->mce_kill_me.func = kill_me_now; - else - current->mce_kill_me.func = kill_me_maybe; + /* First call, save all the details */ + if (count == 1) { + current->mce_addr = m->addr; + current->mce_kflags = m->kflags; + current->mce_ripv = !!(m->mcgstatus & MCG_STATUS_RIPV); + current->mce_whole_page = whole_page(m); + + if (kill_current_task) + current->mce_kill_me.func = kill_me_now; + else + current->mce_kill_me.func = kill_me_maybe; + } + + /* Ten is likely overkill. Don't expect more than two faults before task_work() */ + if (count > 10) + mce_panic("Too many consecutive machine checks while accessing user data", m, msg); + + /* Second or later call, make sure page address matches the one from first call */ + if (count > 1 && (current->mce_addr >> PAGE_SHIFT) != (m->addr >> PAGE_SHIFT)) + mce_panic("Consecutive machine checks to different user pages", m, msg); + + /* Do not call task_work_add() more than once */ + if (count > 1) + return; task_work_add(current, ¤t->mce_kill_me, TWA_RESUME); } @@ -1438,7 +1459,7 @@ noinstr void do_machine_check(struct pt_regs *regs) /* If this triggers there is no way to recover. Die hard. */ BUG_ON(!on_thread_stack() || !user_mode(regs)); - queue_task_work(&m, kill_current_task); + queue_task_work(&m, msg, kill_current_task); } else { /* @@ -1456,7 +1477,7 @@ noinstr void do_machine_check(struct pt_regs *regs) } if (m.kflags & MCE_IN_KERNEL_COPYIN) - queue_task_work(&m, kill_current_task); + queue_task_work(&m, msg, kill_current_task); } out: mce_wrmsrl(MSR_IA32_MCG_STATUS, 0); diff --git a/include/linux/sched.h b/include/linux/sched.h index 1780260f237b..361c7bc72cbb 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1468,6 +1468,7 @@ struct task_struct { mce_whole_page : 1, __mce_reserved : 62; struct callback_head mce_kill_me; + int mce_count; #endif #ifdef CONFIG_KRETPROBES -- cgit v1.2.3 From 87ea95808d53e56b03e620e8f8f3add48899a88d Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Fri, 10 Sep 2021 15:09:39 +0200 Subject: drm/bridge: Add a function to abstract away panels Display drivers so far need to have a lot of boilerplate to first retrieve either the panel or bridge that they are connected to using drm_of_find_panel_or_bridge(), and then either deal with each with ad-hoc functions or create a drm panel bridge through drm_panel_bridge_add. In order to reduce the boilerplate and hopefully create a path of least resistance towards using the DRM panel bridge layer, let's create the function devm_drm_of_get_bridge() to reduce that boilerplate. Signed-off-by: Maxime Ripard Reviewed-by: Sam Ravnborg Link: https://patchwork.freedesktop.org/patch/msgid/20210910130941.1740182-2-maxime@cerno.tech --- drivers/gpu/drm/drm_bridge.c | 41 +++++++++++++++++++++++++++++++++++++---- drivers/gpu/drm/drm_of.c | 3 +++ include/drm/drm_bridge.h | 2 ++ 3 files changed, 42 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/drm_bridge.c b/drivers/gpu/drm/drm_bridge.c index a8ed66751c2d..4c68733fa660 100644 --- a/drivers/gpu/drm/drm_bridge.c +++ b/drivers/gpu/drm/drm_bridge.c @@ -28,6 +28,7 @@ #include #include #include +#include #include #include "drm_crtc_internal.h" @@ -51,10 +52,8 @@ * * Display drivers are responsible for linking encoders with the first bridge * in the chains. This is done by acquiring the appropriate bridge with - * of_drm_find_bridge() or drm_of_find_panel_or_bridge(), or creating it for a - * panel with drm_panel_bridge_add_typed() (or the managed version - * devm_drm_panel_bridge_add_typed()). Once acquired, the bridge shall be - * attached to the encoder with a call to drm_bridge_attach(). + * devm_drm_of_get_bridge(). Once acquired, the bridge shall be attached to the + * encoder with a call to drm_bridge_attach(). * * Bridges are responsible for linking themselves with the next bridge in the * chain, if any. This is done the same way as for encoders, with the call to @@ -1233,6 +1232,40 @@ struct drm_bridge *of_drm_find_bridge(struct device_node *np) return NULL; } EXPORT_SYMBOL(of_drm_find_bridge); + +/** + * devm_drm_of_get_bridge - Return next bridge in the chain + * @dev: device to tie the bridge lifetime to + * @np: device tree node containing encoder output ports + * @port: port in the device tree node + * @endpoint: endpoint in the device tree node + * + * Given a DT node's port and endpoint number, finds the connected node + * and returns the associated bridge if any, or creates and returns a + * drm panel bridge instance if a panel is connected. + * + * Returns a pointer to the bridge if successful, or an error pointer + * otherwise. + */ +struct drm_bridge *devm_drm_of_get_bridge(struct device *dev, + struct device_node *np, + u32 port, u32 endpoint) +{ + struct drm_bridge *bridge; + struct drm_panel *panel; + int ret; + + ret = drm_of_find_panel_or_bridge(np, port, endpoint, + &panel, &bridge); + if (ret) + return ERR_PTR(ret); + + if (panel) + bridge = devm_drm_panel_bridge_add(dev, panel); + + return bridge; +} +EXPORT_SYMBOL(devm_drm_of_get_bridge); #endif MODULE_AUTHOR("Ajay Kumar "); diff --git a/drivers/gpu/drm/drm_of.c b/drivers/gpu/drm/drm_of.c index 997b8827fed2..37c34146eea8 100644 --- a/drivers/gpu/drm/drm_of.c +++ b/drivers/gpu/drm/drm_of.c @@ -231,6 +231,9 @@ EXPORT_SYMBOL_GPL(drm_of_encoder_active_endpoint); * return either the associated struct drm_panel or drm_bridge device. Either * @panel or @bridge must not be NULL. * + * This function is deprecated and should not be used in new drivers. Use + * devm_drm_of_get_bridge() instead. + * * Returns zero if successful, or one of the standard error codes if it fails. */ int drm_of_find_panel_or_bridge(const struct device_node *np, diff --git a/include/drm/drm_bridge.h b/include/drm/drm_bridge.h index 46bdfa48c413..9cdbd209388e 100644 --- a/include/drm/drm_bridge.h +++ b/include/drm/drm_bridge.h @@ -911,6 +911,8 @@ struct drm_bridge *devm_drm_panel_bridge_add(struct device *dev, struct drm_bridge *devm_drm_panel_bridge_add_typed(struct device *dev, struct drm_panel *panel, u32 connector_type); +struct drm_bridge *devm_drm_of_get_bridge(struct device *dev, struct device_node *node, + u32 port, u32 endpoint); struct drm_connector *drm_panel_bridge_connector(struct drm_bridge *bridge); #endif -- cgit v1.2.3 From 8fb0f47a9d7acf620d0fd97831b69da9bc5e22ed Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 10 Sep 2021 11:18:36 -0600 Subject: iov_iter: add helper to save iov_iter state In an ideal world, when someone is passed an iov_iter and returns X bytes, then X bytes would have been consumed/advanced from the iov_iter. But we have use cases that always consume the entire iterator, a few examples of that are iomap and bdev O_DIRECT. This means we cannot rely on the state of the iov_iter once we've called ->read_iter() or ->write_iter(). This would be easier if we didn't always have to deal with truncate of the iov_iter, as rewinding would be trivial without that. We recently added a commit to track the truncate state, but that grew the iov_iter by 8 bytes and wasn't the best solution. Implement a helper to save enough of the iov_iter state to sanely restore it after we've called the read/write iterator helpers. This currently only works for IOVEC/BVEC/KVEC as that's all we need, support for other iterator types are left as an exercise for the reader. Link: https://lore.kernel.org/linux-fsdevel/CAHk-=wiacKV4Gh-MYjteU0LwNBSGpWrK-Ov25HdqB1ewinrFPg@mail.gmail.com/ Signed-off-by: Jens Axboe --- include/linux/uio.h | 15 +++++++++++++++ lib/iov_iter.c | 36 ++++++++++++++++++++++++++++++++++++ 2 files changed, 51 insertions(+) (limited to 'include') diff --git a/include/linux/uio.h b/include/linux/uio.h index 5265024e8b90..984c4ab74859 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -27,6 +27,12 @@ enum iter_type { ITER_DISCARD, }; +struct iov_iter_state { + size_t iov_offset; + size_t count; + unsigned long nr_segs; +}; + struct iov_iter { u8 iter_type; bool data_source; @@ -55,6 +61,14 @@ static inline enum iter_type iov_iter_type(const struct iov_iter *i) return i->iter_type; } +static inline void iov_iter_save_state(struct iov_iter *iter, + struct iov_iter_state *state) +{ + state->iov_offset = iter->iov_offset; + state->count = iter->count; + state->nr_segs = iter->nr_segs; +} + static inline bool iter_is_iovec(const struct iov_iter *i) { return iov_iter_type(i) == ITER_IOVEC; @@ -233,6 +247,7 @@ ssize_t iov_iter_get_pages(struct iov_iter *i, struct page **pages, ssize_t iov_iter_get_pages_alloc(struct iov_iter *i, struct page ***pages, size_t maxsize, size_t *start); int iov_iter_npages(const struct iov_iter *i, int maxpages); +void iov_iter_restore(struct iov_iter *i, struct iov_iter_state *state); const void *dup_iter(struct iov_iter *new, struct iov_iter *old, gfp_t flags); diff --git a/lib/iov_iter.c b/lib/iov_iter.c index f2d50d69a6c3..755c10c5138c 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -1972,3 +1972,39 @@ int import_single_range(int rw, void __user *buf, size_t len, return 0; } EXPORT_SYMBOL(import_single_range); + +/** + * iov_iter_restore() - Restore a &struct iov_iter to the same state as when + * iov_iter_save_state() was called. + * + * @i: &struct iov_iter to restore + * @state: state to restore from + * + * Used after iov_iter_save_state() to bring restore @i, if operations may + * have advanced it. + * + * Note: only works on ITER_IOVEC, ITER_BVEC, and ITER_KVEC + */ +void iov_iter_restore(struct iov_iter *i, struct iov_iter_state *state) +{ + if (WARN_ON_ONCE(!iov_iter_is_bvec(i) && !iter_is_iovec(i)) && + !iov_iter_is_kvec(i)) + return; + i->iov_offset = state->iov_offset; + i->count = state->count; + /* + * For the *vec iters, nr_segs + iov is constant - if we increment + * the vec, then we also decrement the nr_segs count. Hence we don't + * need to track both of these, just one is enough and we can deduct + * the other from that. ITER_KVEC and ITER_IOVEC are the same struct + * size, so we can just increment the iov pointer as they are unionzed. + * ITER_BVEC _may_ be the same size on some archs, but on others it is + * not. Be safe and handle it separately. + */ + BUILD_BUG_ON(sizeof(struct iovec) != sizeof(struct kvec)); + if (iov_iter_is_bvec(i)) + i->bvec -= state->nr_segs - i->nr_segs; + else + i->iov -= state->nr_segs - i->nr_segs; + i->nr_segs = state->nr_segs; +} -- cgit v1.2.3 From 77e02cf57b6cff9919949defb7fd9b8ac16399a2 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 14 Sep 2021 13:23:22 -0700 Subject: memblock: introduce saner 'memblock_free_ptr()' interface The boot-time allocation interface for memblock is a mess, with 'memblock_alloc()' returning a virtual pointer, but then you are supposed to free it with 'memblock_free()' that takes a _physical_ address. Not only is that all kinds of strange and illogical, but it actually causes bugs, when people then use it like a normal allocation function, and it fails spectacularly on a NULL pointer: https://lore.kernel.org/all/20210912140820.GD25450@xsang-OptiPlex-9020/ or just random memory corruption if the debug checks don't catch it: https://lore.kernel.org/all/61ab2d0c-3313-aaab-514c-e15b7aa054a0@suse.cz/ I really don't want to apply patches that treat the symptoms, when the fundamental cause is this horribly confusing interface. I started out looking at just automating a sane replacement sequence, but because of this mix or virtual and physical addresses, and because people have used the "__pa()" macro that can take either a regular kernel pointer, or just the raw "unsigned long" address, it's all quite messy. So this just introduces a new saner interface for freeing a virtual address that was allocated using 'memblock_alloc()', and that was kept as a regular kernel pointer. And then it converts a couple of users that are obvious and easy to test, including the 'xbc_nodes' case in lib/bootconfig.c that caused problems. Reported-by: kernel test robot Fixes: 40caa127f3c7 ("init: bootconfig: Remove all bootconfig data when the init memory is removed") Cc: Steven Rostedt Cc: Mike Rapoport Cc: Andrew Morton Cc: Ingo Molnar Cc: Masami Hiramatsu Cc: Vlastimil Babka Signed-off-by: Linus Torvalds --- arch/x86/kernel/setup_percpu.c | 2 +- arch/x86/mm/kasan_init_64.c | 6 ++---- arch/x86/mm/numa.c | 2 +- arch/x86/mm/numa_emulation.c | 3 +-- drivers/base/arch_numa.c | 2 +- drivers/macintosh/smu.c | 2 +- include/linux/memblock.h | 1 + init/main.c | 2 +- kernel/printk/printk.c | 4 ++-- lib/bootconfig.c | 2 +- mm/memblock.c | 16 +++++++++++++++- 11 files changed, 27 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index 78a32b956e81..5afd98559193 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -135,7 +135,7 @@ static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align) static void __init pcpu_fc_free(void *ptr, size_t size) { - memblock_free(__pa(ptr), size); + memblock_free_ptr(ptr, size); } static int __init pcpu_cpu_distance(unsigned int from, unsigned int to) diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c index 1a50434c8a4d..ef885370719a 100644 --- a/arch/x86/mm/kasan_init_64.c +++ b/arch/x86/mm/kasan_init_64.c @@ -49,8 +49,7 @@ static void __init kasan_populate_pmd(pmd_t *pmd, unsigned long addr, p = early_alloc(PMD_SIZE, nid, false); if (p && pmd_set_huge(pmd, __pa(p), PAGE_KERNEL)) return; - else if (p) - memblock_free(__pa(p), PMD_SIZE); + memblock_free_ptr(p, PMD_SIZE); } p = early_alloc(PAGE_SIZE, nid, true); @@ -86,8 +85,7 @@ static void __init kasan_populate_pud(pud_t *pud, unsigned long addr, p = early_alloc(PUD_SIZE, nid, false); if (p && pud_set_huge(pud, __pa(p), PAGE_KERNEL)) return; - else if (p) - memblock_free(__pa(p), PUD_SIZE); + memblock_free_ptr(p, PUD_SIZE); } p = early_alloc(PAGE_SIZE, nid, true); diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index a1b5c71099e6..1e9b93b088db 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -355,7 +355,7 @@ void __init numa_reset_distance(void) /* numa_distance could be 1LU marking allocation failure, test cnt */ if (numa_distance_cnt) - memblock_free(__pa(numa_distance), size); + memblock_free_ptr(numa_distance, size); numa_distance_cnt = 0; numa_distance = NULL; /* enable table creation */ } diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c index 737491b13728..e801e30089c4 100644 --- a/arch/x86/mm/numa_emulation.c +++ b/arch/x86/mm/numa_emulation.c @@ -517,8 +517,7 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt) } /* free the copied physical distance table */ - if (phys_dist) - memblock_free(__pa(phys_dist), phys_size); + memblock_free_ptr(phys_dist, phys_size); return; no_emu: diff --git a/drivers/base/arch_numa.c b/drivers/base/arch_numa.c index 46c503486e96..00fb4120a5b3 100644 --- a/drivers/base/arch_numa.c +++ b/drivers/base/arch_numa.c @@ -264,7 +264,7 @@ void __init numa_free_distance(void) size = numa_distance_cnt * numa_distance_cnt * sizeof(numa_distance[0]); - memblock_free(__pa(numa_distance), size); + memblock_free_ptr(numa_distance, size); numa_distance_cnt = 0; numa_distance = NULL; } diff --git a/drivers/macintosh/smu.c b/drivers/macintosh/smu.c index 94fb63a7b357..fe63d5ee201b 100644 --- a/drivers/macintosh/smu.c +++ b/drivers/macintosh/smu.c @@ -570,7 +570,7 @@ fail_msg_node: fail_db_node: of_node_put(smu->db_node); fail_bootmem: - memblock_free(__pa(smu), sizeof(struct smu_device)); + memblock_free_ptr(smu, sizeof(struct smu_device)); smu = NULL; fail_np: of_node_put(np); diff --git a/include/linux/memblock.h b/include/linux/memblock.h index b066024c62e3..34de69b3b8ba 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -118,6 +118,7 @@ int memblock_mark_nomap(phys_addr_t base, phys_addr_t size); int memblock_clear_nomap(phys_addr_t base, phys_addr_t size); void memblock_free_all(void); +void memblock_free_ptr(void *ptr, size_t size); void reset_node_managed_pages(pg_data_t *pgdat); void reset_all_zones_managed_pages(void); diff --git a/init/main.c b/init/main.c index 5c9a48df90e1..3f7216934441 100644 --- a/init/main.c +++ b/init/main.c @@ -924,7 +924,7 @@ static void __init print_unknown_bootoptions(void) end += sprintf(end, " %s", *p); pr_notice("Unknown command line parameters:%s\n", unknown_options); - memblock_free(__pa(unknown_options), len); + memblock_free_ptr(unknown_options, len); } asmlinkage __visible void __init __no_sanitize_address start_kernel(void) diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 825277e1e742..a8d0a58deebc 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -1166,9 +1166,9 @@ void __init setup_log_buf(int early) return; err_free_descs: - memblock_free(__pa(new_descs), new_descs_size); + memblock_free_ptr(new_descs, new_descs_size); err_free_log_buf: - memblock_free(__pa(new_log_buf), new_log_buf_len); + memblock_free_ptr(new_log_buf, new_log_buf_len); } static bool __read_mostly ignore_loglevel; diff --git a/lib/bootconfig.c b/lib/bootconfig.c index f8419cff1147..5ae248b29373 100644 --- a/lib/bootconfig.c +++ b/lib/bootconfig.c @@ -792,7 +792,7 @@ void __init xbc_destroy_all(void) xbc_data = NULL; xbc_data_size = 0; xbc_node_num = 0; - memblock_free(__pa(xbc_nodes), sizeof(struct xbc_node) * XBC_NODE_MAX); + memblock_free_ptr(xbc_nodes, sizeof(struct xbc_node) * XBC_NODE_MAX); xbc_nodes = NULL; brace_index = 0; } diff --git a/mm/memblock.c b/mm/memblock.c index 0ab5a749bfa6..184dcd2e5d99 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -472,7 +472,7 @@ static int __init_memblock memblock_double_array(struct memblock_type *type, kfree(old_array); else if (old_array != memblock_memory_init_regions && old_array != memblock_reserved_init_regions) - memblock_free(__pa(old_array), old_alloc_size); + memblock_free_ptr(old_array, old_alloc_size); /* * Reserve the new array if that comes from the memblock. Otherwise, we @@ -795,6 +795,20 @@ int __init_memblock memblock_remove(phys_addr_t base, phys_addr_t size) return memblock_remove_range(&memblock.memory, base, size); } +/** + * memblock_free_ptr - free boot memory allocation + * @ptr: starting address of the boot memory allocation + * @size: size of the boot memory block in bytes + * + * Free boot memory block previously allocated by memblock_alloc_xx() API. + * The freeing memory will not be released to the buddy allocator. + */ +void __init_memblock memblock_free_ptr(void *ptr, size_t size) +{ + if (ptr) + memblock_free(__pa(ptr), size); +} + /** * memblock_free - free boot memory block * @base: phys starting address of the boot memory block -- cgit v1.2.3 From 7dedd3e18077f996a10c47250ac85d080e5f474e Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 10 Sep 2021 11:19:58 -0600 Subject: Revert "iov_iter: track truncated size" This reverts commit 2112ff5ce0c1128fe7b4d19cfe7f2b8ce5b595fa. We no longer need to track the truncation count, the one user that did need it has been converted to using iov_iter_restore() instead. Signed-off-by: Jens Axboe --- include/linux/uio.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/uio.h b/include/linux/uio.h index 984c4ab74859..207101a9c5c3 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -53,7 +53,6 @@ struct iov_iter { }; loff_t xarray_start; }; - size_t truncated; }; static inline enum iter_type iov_iter_type(const struct iov_iter *i) @@ -270,10 +269,8 @@ static inline void iov_iter_truncate(struct iov_iter *i, u64 count) * conversion in assignement is by definition greater than all * values of size_t, including old i->count. */ - if (i->count > count) { - i->truncated += i->count - count; + if (i->count > count) i->count = count; - } } /* @@ -282,7 +279,6 @@ static inline void iov_iter_truncate(struct iov_iter *i, u64 count) */ static inline void iov_iter_reexpand(struct iov_iter *i, size_t count) { - i->truncated -= count - i->count; i->count = count; } -- cgit v1.2.3 From f6b5f1a56987de837f8e25cd560847106b8632a8 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Tue, 14 Sep 2021 20:52:24 -0700 Subject: compiler.h: Introduce absolute_pointer macro absolute_pointer() disassociates a pointer from its originating symbol type and context. Use it to prevent compiler warnings/errors such as drivers/net/ethernet/i825xx/82596.c: In function 'i82596_probe': arch/m68k/include/asm/string.h:72:25: error: '__builtin_memcpy' reading 6 bytes from a region of size 0 [-Werror=stringop-overread] Such warnings may be reported by gcc 11.x for string and memory operations on fixed addresses. Suggested-by: Linus Torvalds Signed-off-by: Guenter Roeck Reviewed-by: Geert Uytterhoeven Signed-off-by: Linus Torvalds --- include/linux/compiler.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index b67261a1e3e9..3d5af56337bd 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -188,6 +188,8 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, (typeof(ptr)) (__ptr + (off)); }) #endif +#define absolute_pointer(val) RELOC_HIDE((void *)(val), 0) + #ifndef OPTIMIZER_HIDE_VAR /* Make the optimizer believe the variable can be manipulated arbitrarily. */ #define OPTIMIZER_HIDE_VAR(var) \ -- cgit v1.2.3 From a57d8c217aadac75530b8e7ffb3a3e1b7bfd0330 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Tue, 14 Sep 2021 16:47:26 +0300 Subject: net: dsa: flush switchdev workqueue before tearing down CPU/DSA ports Sometimes when unbinding the mv88e6xxx driver on Turris MOX, these error messages appear: mv88e6085 d0032004.mdio-mii:12: port 1 failed to delete be:79:b4:9e:9e:96 vid 1 from fdb: -2 mv88e6085 d0032004.mdio-mii:12: port 1 failed to delete be:79:b4:9e:9e:96 vid 0 from fdb: -2 mv88e6085 d0032004.mdio-mii:12: port 1 failed to delete d8:58:d7:00:ca:6d vid 100 from fdb: -2 mv88e6085 d0032004.mdio-mii:12: port 1 failed to delete d8:58:d7:00:ca:6d vid 1 from fdb: -2 mv88e6085 d0032004.mdio-mii:12: port 1 failed to delete d8:58:d7:00:ca:6d vid 0 from fdb: -2 (and similarly for other ports) What happens is that DSA has a policy "even if there are bugs, let's at least not leak memory" and dsa_port_teardown() clears the dp->fdbs and dp->mdbs lists, which are supposed to be empty. But deleting that cleanup code, the warnings go away. => the FDB and MDB lists (used for refcounting on shared ports, aka CPU and DSA ports) will eventually be empty, but are not empty by the time we tear down those ports. Aka we are deleting them too soon. The addresses that DSA complains about are host-trapped addresses: the local addresses of the ports, and the MAC address of the bridge device. The problem is that offloading those entries happens from a deferred work item scheduled by the SWITCHDEV_FDB_DEL_TO_DEVICE handler, and this races with the teardown of the CPU and DSA ports where the refcounting is kept. In fact, not only it races, but fundamentally speaking, if we iterate through the port list linearly, we might end up tearing down the shared ports even before we delete a DSA user port which has a bridge upper. So as it turns out, we need to first tear down the user ports (and the unused ones, for no better place of doing that), then the shared ports (the CPU and DSA ports). In between, we need to ensure that all work items scheduled by our switchdev handlers (which only run for user ports, hence the reason why we tear them down first) have finished. Fixes: 161ca59d39e9 ("net: dsa: reference count the MDB entries at the cross-chip notifier level") Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Link: https://lore.kernel.org/r/20210914134726.2305133-1-vladimir.oltean@nxp.com Signed-off-by: Jakub Kicinski --- include/net/dsa.h | 5 +++++ net/dsa/dsa.c | 5 +++++ net/dsa/dsa2.c | 46 +++++++++++++++++++++++++++++++--------------- net/dsa/dsa_priv.h | 1 + 4 files changed, 42 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index f9a17145255a..258867eff230 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -447,6 +447,11 @@ static inline bool dsa_port_is_user(struct dsa_port *dp) return dp->type == DSA_PORT_TYPE_USER; } +static inline bool dsa_port_is_unused(struct dsa_port *dp) +{ + return dp->type == DSA_PORT_TYPE_UNUSED; +} + static inline bool dsa_is_unused_port(struct dsa_switch *ds, int p) { return dsa_to_port(ds, p)->type == DSA_PORT_TYPE_UNUSED; diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index 1dc45e40f961..41f36ad8b0ec 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -345,6 +345,11 @@ bool dsa_schedule_work(struct work_struct *work) return queue_work(dsa_owq, work); } +void dsa_flush_workqueue(void) +{ + flush_workqueue(dsa_owq); +} + int dsa_devlink_param_get(struct devlink *dl, u32 id, struct devlink_param_gset_ctx *ctx) { diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index 1b2b25d7bd02..eef13cd20f19 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -897,6 +897,33 @@ static void dsa_switch_teardown(struct dsa_switch *ds) ds->setup = false; } +/* First tear down the non-shared, then the shared ports. This ensures that + * all work items scheduled by our switchdev handlers for user ports have + * completed before we destroy the refcounting kept on the shared ports. + */ +static void dsa_tree_teardown_ports(struct dsa_switch_tree *dst) +{ + struct dsa_port *dp; + + list_for_each_entry(dp, &dst->ports, list) + if (dsa_port_is_user(dp) || dsa_port_is_unused(dp)) + dsa_port_teardown(dp); + + dsa_flush_workqueue(); + + list_for_each_entry(dp, &dst->ports, list) + if (dsa_port_is_dsa(dp) || dsa_port_is_cpu(dp)) + dsa_port_teardown(dp); +} + +static void dsa_tree_teardown_switches(struct dsa_switch_tree *dst) +{ + struct dsa_port *dp; + + list_for_each_entry(dp, &dst->ports, list) + dsa_switch_teardown(dp->ds); +} + static int dsa_tree_setup_switches(struct dsa_switch_tree *dst) { struct dsa_port *dp; @@ -923,26 +950,13 @@ static int dsa_tree_setup_switches(struct dsa_switch_tree *dst) return 0; teardown: - list_for_each_entry(dp, &dst->ports, list) - dsa_port_teardown(dp); + dsa_tree_teardown_ports(dst); - list_for_each_entry(dp, &dst->ports, list) - dsa_switch_teardown(dp->ds); + dsa_tree_teardown_switches(dst); return err; } -static void dsa_tree_teardown_switches(struct dsa_switch_tree *dst) -{ - struct dsa_port *dp; - - list_for_each_entry(dp, &dst->ports, list) - dsa_port_teardown(dp); - - list_for_each_entry(dp, &dst->ports, list) - dsa_switch_teardown(dp->ds); -} - static int dsa_tree_setup_master(struct dsa_switch_tree *dst) { struct dsa_port *dp; @@ -1052,6 +1066,8 @@ static void dsa_tree_teardown(struct dsa_switch_tree *dst) dsa_tree_teardown_master(dst); + dsa_tree_teardown_ports(dst); + dsa_tree_teardown_switches(dst); dsa_tree_teardown_cpu_ports(dst); diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index 33ab7d7af9eb..a5c9bc7b66c6 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -170,6 +170,7 @@ void dsa_tag_driver_put(const struct dsa_device_ops *ops); const struct dsa_device_ops *dsa_find_tagger_by_name(const char *buf); bool dsa_schedule_work(struct work_struct *work); +void dsa_flush_workqueue(void); const char *dsa_tag_protocol_to_str(const struct dsa_device_ops *ops); static inline int dsa_tag_protocol_overhead(const struct dsa_device_ops *ops) -- cgit v1.2.3 From 12235da8c80a1f9909008e4ca6036d5772b81192 Mon Sep 17 00:00:00 2001 From: Maarten Lankhorst Date: Thu, 9 Sep 2021 11:32:18 +0200 Subject: kernel/locking: Add context to ww_mutex_trylock() i915 will soon gain an eviction path that trylock a whole lot of locks for eviction, getting dmesg failures like below: BUG: MAX_LOCK_DEPTH too low! turning off the locking correctness validator. depth: 48 max: 48! 48 locks held by i915_selftest/5776: #0: ffff888101a79240 (&dev->mutex){....}-{3:3}, at: __driver_attach+0x88/0x160 #1: ffffc900009778c0 (reservation_ww_class_acquire){+.+.}-{0:0}, at: i915_vma_pin.constprop.63+0x39/0x1b0 [i915] #2: ffff88800cf74de8 (reservation_ww_class_mutex){+.+.}-{3:3}, at: i915_vma_pin.constprop.63+0x5f/0x1b0 [i915] #3: ffff88810c7f9e38 (&vm->mutex/1){+.+.}-{3:3}, at: i915_vma_pin_ww+0x1c4/0x9d0 [i915] #4: ffff88810bad5768 (reservation_ww_class_mutex){+.+.}-{3:3}, at: i915_gem_evict_something+0x110/0x860 [i915] #5: ffff88810bad60e8 (reservation_ww_class_mutex){+.+.}-{3:3}, at: i915_gem_evict_something+0x110/0x860 [i915] ... #46: ffff88811964d768 (reservation_ww_class_mutex){+.+.}-{3:3}, at: i915_gem_evict_something+0x110/0x860 [i915] #47: ffff88811964e0e8 (reservation_ww_class_mutex){+.+.}-{3:3}, at: i915_gem_evict_something+0x110/0x860 [i915] INFO: lockdep is turned off. Fixing eviction to nest into ww_class_acquire is a high priority, but it requires a rework of the entire driver, which can only be done one step at a time. As an intermediate solution, add an acquire context to ww_mutex_trylock, which allows us to do proper nesting annotations on the trylocks, making the above lockdep splat disappear. This is also useful in regulator_lock_nested, which may avoid dropping regulator_nesting_mutex in the uncontended path, so use it there. TTM may be another user for this, where we could lock a buffer in a fastpath with list locks held, without dropping all locks we hold. [peterz: rework actual ww_mutex_trylock() implementations] Signed-off-by: Maarten Lankhorst Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/YUBGPdDDjKlxAuXJ@hirez.programming.kicks-ass.net --- drivers/gpu/drm/drm_modeset_lock.c | 2 +- drivers/regulator/core.c | 2 +- include/linux/dma-resv.h | 2 +- include/linux/ww_mutex.h | 15 +------ kernel/locking/mutex.c | 41 ++++++++++++++++++ kernel/locking/test-ww_mutex.c | 86 ++++++++++++++++++++++++++++---------- kernel/locking/ww_rt_mutex.c | 25 +++++++++++ lib/locking-selftest.c | 2 +- 8 files changed, 137 insertions(+), 38 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/drm_modeset_lock.c b/drivers/gpu/drm/drm_modeset_lock.c index fcfe1a03c4a1..bf8a6e823a15 100644 --- a/drivers/gpu/drm/drm_modeset_lock.c +++ b/drivers/gpu/drm/drm_modeset_lock.c @@ -248,7 +248,7 @@ static inline int modeset_lock(struct drm_modeset_lock *lock, if (ctx->trylock_only) { lockdep_assert_held(&ctx->ww_ctx); - if (!ww_mutex_trylock(&lock->mutex)) + if (!ww_mutex_trylock(&lock->mutex, NULL)) return -EBUSY; else return 0; diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index ca6caba8a191..f4d441b1a8bf 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -145,7 +145,7 @@ static inline int regulator_lock_nested(struct regulator_dev *rdev, mutex_lock(®ulator_nesting_mutex); - if (ww_ctx || !ww_mutex_trylock(&rdev->mutex)) { + if (!ww_mutex_trylock(&rdev->mutex, ww_ctx)) { if (rdev->mutex_owner == current) rdev->ref_cnt++; else diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h index e1ca2080a1ff..39fefb86780b 100644 --- a/include/linux/dma-resv.h +++ b/include/linux/dma-resv.h @@ -173,7 +173,7 @@ static inline int dma_resv_lock_slow_interruptible(struct dma_resv *obj, */ static inline bool __must_check dma_resv_trylock(struct dma_resv *obj) { - return ww_mutex_trylock(&obj->lock); + return ww_mutex_trylock(&obj->lock, NULL); } /** diff --git a/include/linux/ww_mutex.h b/include/linux/ww_mutex.h index 29db736af86d..bb763085479a 100644 --- a/include/linux/ww_mutex.h +++ b/include/linux/ww_mutex.h @@ -28,12 +28,10 @@ #ifndef CONFIG_PREEMPT_RT #define WW_MUTEX_BASE mutex #define ww_mutex_base_init(l,n,k) __mutex_init(l,n,k) -#define ww_mutex_base_trylock(l) mutex_trylock(l) #define ww_mutex_base_is_locked(b) mutex_is_locked((b)) #else #define WW_MUTEX_BASE rt_mutex #define ww_mutex_base_init(l,n,k) __rt_mutex_init(l,n,k) -#define ww_mutex_base_trylock(l) rt_mutex_trylock(l) #define ww_mutex_base_is_locked(b) rt_mutex_base_is_locked(&(b)->rtmutex) #endif @@ -339,17 +337,8 @@ ww_mutex_lock_slow_interruptible(struct ww_mutex *lock, extern void ww_mutex_unlock(struct ww_mutex *lock); -/** - * ww_mutex_trylock - tries to acquire the w/w mutex without acquire context - * @lock: mutex to lock - * - * Trylocks a mutex without acquire context, so no deadlock detection is - * possible. Returns 1 if the mutex has been acquired successfully, 0 otherwise. - */ -static inline int __must_check ww_mutex_trylock(struct ww_mutex *lock) -{ - return ww_mutex_base_trylock(&lock->base); -} +extern int __must_check ww_mutex_trylock(struct ww_mutex *lock, + struct ww_acquire_ctx *ctx); /*** * ww_mutex_destroy - mark a w/w mutex unusable diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index d456579d0952..2fede72b6af5 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -94,6 +94,9 @@ static inline unsigned long __owner_flags(unsigned long owner) return owner & MUTEX_FLAGS; } +/* + * Returns: __mutex_owner(lock) on failure or NULL on success. + */ static inline struct task_struct *__mutex_trylock_common(struct mutex *lock, bool handoff) { unsigned long owner, curr = (unsigned long)current; @@ -736,6 +739,44 @@ __ww_mutex_lock(struct mutex *lock, unsigned int state, unsigned int subclass, return __mutex_lock_common(lock, state, subclass, NULL, ip, ww_ctx, true); } +/** + * ww_mutex_trylock - tries to acquire the w/w mutex with optional acquire context + * @ww: mutex to lock + * @ww_ctx: optional w/w acquire context + * + * Trylocks a mutex with the optional acquire context; no deadlock detection is + * possible. Returns 1 if the mutex has been acquired successfully, 0 otherwise. + * + * Unlike ww_mutex_lock, no deadlock handling is performed. However, if a @ctx is + * specified, -EALREADY handling may happen in calls to ww_mutex_trylock. + * + * A mutex acquired with this function must be released with ww_mutex_unlock. + */ +int ww_mutex_trylock(struct ww_mutex *ww, struct ww_acquire_ctx *ww_ctx) +{ + if (!ww_ctx) + return mutex_trylock(&ww->base); + + MUTEX_WARN_ON(ww->base.magic != &ww->base); + + /* + * Reset the wounded flag after a kill. No other process can + * race and wound us here, since they can't have a valid owner + * pointer if we don't have any locks held. + */ + if (ww_ctx->acquired == 0) + ww_ctx->wounded = 0; + + if (__mutex_trylock(&ww->base)) { + ww_mutex_set_context_fastpath(ww, ww_ctx); + mutex_acquire_nest(&ww->base.dep_map, 0, 1, &ww_ctx->dep_map, _RET_IP_); + return 1; + } + + return 0; +} +EXPORT_SYMBOL(ww_mutex_trylock); + #ifdef CONFIG_DEBUG_LOCK_ALLOC void __sched mutex_lock_nested(struct mutex *lock, unsigned int subclass) diff --git a/kernel/locking/test-ww_mutex.c b/kernel/locking/test-ww_mutex.c index 3e82f449b4ff..d63ac411f367 100644 --- a/kernel/locking/test-ww_mutex.c +++ b/kernel/locking/test-ww_mutex.c @@ -16,6 +16,15 @@ static DEFINE_WD_CLASS(ww_class); struct workqueue_struct *wq; +#ifdef CONFIG_DEBUG_WW_MUTEX_SLOWPATH +#define ww_acquire_init_noinject(a, b) do { \ + ww_acquire_init((a), (b)); \ + (a)->deadlock_inject_countdown = ~0U; \ + } while (0) +#else +#define ww_acquire_init_noinject(a, b) ww_acquire_init((a), (b)) +#endif + struct test_mutex { struct work_struct work; struct ww_mutex mutex; @@ -36,7 +45,7 @@ static void test_mutex_work(struct work_struct *work) wait_for_completion(&mtx->go); if (mtx->flags & TEST_MTX_TRY) { - while (!ww_mutex_trylock(&mtx->mutex)) + while (!ww_mutex_trylock(&mtx->mutex, NULL)) cond_resched(); } else { ww_mutex_lock(&mtx->mutex, NULL); @@ -109,19 +118,38 @@ static int test_mutex(void) return 0; } -static int test_aa(void) +static int test_aa(bool trylock) { struct ww_mutex mutex; struct ww_acquire_ctx ctx; int ret; + const char *from = trylock ? "trylock" : "lock"; ww_mutex_init(&mutex, &ww_class); ww_acquire_init(&ctx, &ww_class); - ww_mutex_lock(&mutex, &ctx); + if (!trylock) { + ret = ww_mutex_lock(&mutex, &ctx); + if (ret) { + pr_err("%s: initial lock failed!\n", __func__); + goto out; + } + } else { + if (!ww_mutex_trylock(&mutex, &ctx)) { + pr_err("%s: initial trylock failed!\n", __func__); + goto out; + } + } - if (ww_mutex_trylock(&mutex)) { - pr_err("%s: trylocked itself!\n", __func__); + if (ww_mutex_trylock(&mutex, NULL)) { + pr_err("%s: trylocked itself without context from %s!\n", __func__, from); + ww_mutex_unlock(&mutex); + ret = -EINVAL; + goto out; + } + + if (ww_mutex_trylock(&mutex, &ctx)) { + pr_err("%s: trylocked itself with context from %s!\n", __func__, from); ww_mutex_unlock(&mutex); ret = -EINVAL; goto out; @@ -129,17 +157,17 @@ static int test_aa(void) ret = ww_mutex_lock(&mutex, &ctx); if (ret != -EALREADY) { - pr_err("%s: missed deadlock for recursing, ret=%d\n", - __func__, ret); + pr_err("%s: missed deadlock for recursing, ret=%d from %s\n", + __func__, ret, from); if (!ret) ww_mutex_unlock(&mutex); ret = -EINVAL; goto out; } + ww_mutex_unlock(&mutex); ret = 0; out: - ww_mutex_unlock(&mutex); ww_acquire_fini(&ctx); return ret; } @@ -150,7 +178,7 @@ struct test_abba { struct ww_mutex b_mutex; struct completion a_ready; struct completion b_ready; - bool resolve; + bool resolve, trylock; int result; }; @@ -160,8 +188,13 @@ static void test_abba_work(struct work_struct *work) struct ww_acquire_ctx ctx; int err; - ww_acquire_init(&ctx, &ww_class); - ww_mutex_lock(&abba->b_mutex, &ctx); + ww_acquire_init_noinject(&ctx, &ww_class); + if (!abba->trylock) + ww_mutex_lock(&abba->b_mutex, &ctx); + else + WARN_ON(!ww_mutex_trylock(&abba->b_mutex, &ctx)); + + WARN_ON(READ_ONCE(abba->b_mutex.ctx) != &ctx); complete(&abba->b_ready); wait_for_completion(&abba->a_ready); @@ -181,7 +214,7 @@ static void test_abba_work(struct work_struct *work) abba->result = err; } -static int test_abba(bool resolve) +static int test_abba(bool trylock, bool resolve) { struct test_abba abba; struct ww_acquire_ctx ctx; @@ -192,12 +225,18 @@ static int test_abba(bool resolve) INIT_WORK_ONSTACK(&abba.work, test_abba_work); init_completion(&abba.a_ready); init_completion(&abba.b_ready); + abba.trylock = trylock; abba.resolve = resolve; schedule_work(&abba.work); - ww_acquire_init(&ctx, &ww_class); - ww_mutex_lock(&abba.a_mutex, &ctx); + ww_acquire_init_noinject(&ctx, &ww_class); + if (!trylock) + ww_mutex_lock(&abba.a_mutex, &ctx); + else + WARN_ON(!ww_mutex_trylock(&abba.a_mutex, &ctx)); + + WARN_ON(READ_ONCE(abba.a_mutex.ctx) != &ctx); complete(&abba.a_ready); wait_for_completion(&abba.b_ready); @@ -249,7 +288,7 @@ static void test_cycle_work(struct work_struct *work) struct ww_acquire_ctx ctx; int err, erra = 0; - ww_acquire_init(&ctx, &ww_class); + ww_acquire_init_noinject(&ctx, &ww_class); ww_mutex_lock(&cycle->a_mutex, &ctx); complete(cycle->a_signal); @@ -581,7 +620,9 @@ static int stress(int nlocks, int nthreads, unsigned int flags) static int __init test_ww_mutex_init(void) { int ncpus = num_online_cpus(); - int ret; + int ret, i; + + printk(KERN_INFO "Beginning ww mutex selftests\n"); wq = alloc_workqueue("test-ww_mutex", WQ_UNBOUND, 0); if (!wq) @@ -591,17 +632,19 @@ static int __init test_ww_mutex_init(void) if (ret) return ret; - ret = test_aa(); + ret = test_aa(false); if (ret) return ret; - ret = test_abba(false); + ret = test_aa(true); if (ret) return ret; - ret = test_abba(true); - if (ret) - return ret; + for (i = 0; i < 4; i++) { + ret = test_abba(i & 1, i & 2); + if (ret) + return ret; + } ret = test_cycle(ncpus); if (ret) @@ -619,6 +662,7 @@ static int __init test_ww_mutex_init(void) if (ret) return ret; + printk(KERN_INFO "All ww mutex selftests passed\n"); return 0; } diff --git a/kernel/locking/ww_rt_mutex.c b/kernel/locking/ww_rt_mutex.c index 3f1fff7d2780..0e00205cf467 100644 --- a/kernel/locking/ww_rt_mutex.c +++ b/kernel/locking/ww_rt_mutex.c @@ -9,6 +9,31 @@ #define WW_RT #include "rtmutex.c" +int ww_mutex_trylock(struct ww_mutex *lock, struct ww_acquire_ctx *ww_ctx) +{ + struct rt_mutex *rtm = &lock->base; + + if (!ww_ctx) + return rt_mutex_trylock(rtm); + + /* + * Reset the wounded flag after a kill. No other process can + * race and wound us here, since they can't have a valid owner + * pointer if we don't have any locks held. + */ + if (ww_ctx->acquired == 0) + ww_ctx->wounded = 0; + + if (__rt_mutex_trylock(&rtm->rtmutex)) { + ww_mutex_set_context_fastpath(lock, ww_ctx); + mutex_acquire_nest(&rtm->dep_map, 0, 1, ww_ctx->dep_map, _RET_IP_); + return 1; + } + + return 0; +} +EXPORT_SYMBOL(ww_mutex_trylock); + static int __sched __ww_rt_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ww_ctx, unsigned int state, unsigned long ip) diff --git a/lib/locking-selftest.c b/lib/locking-selftest.c index 161108e5d2fe..71652e1c397c 100644 --- a/lib/locking-selftest.c +++ b/lib/locking-selftest.c @@ -258,7 +258,7 @@ static void init_shared_classes(void) #define WWAF(x) ww_acquire_fini(x) #define WWL(x, c) ww_mutex_lock(x, c) -#define WWT(x) ww_mutex_trylock(x) +#define WWT(x) ww_mutex_trylock(x, NULL) #define WWL1(x) ww_mutex_lock(x, NULL) #define WWU(x) ww_mutex_unlock(x) -- cgit v1.2.3 From 9caea0007601d3bc6debec04f8b4cd6f4c2394be Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Sun, 19 Sep 2021 10:36:09 -0700 Subject: parisc: Declare pci_iounmap() parisc version only when CONFIG_PCI enabled Linus noticed odd declaration rules for pci_iounmap() in iomap.h and pci_iomap.h, where it dependend on either NO_GENERIC_PCI_IOPORT_MAP or GENERIC_IOMAP when CONFIG_PCI was disabled. Testing on parisc seems to indicate that we need pci_iounmap() only when CONFIG_PCI is enabled, so the declaration of pci_iounmap() can be moved cleanly into pci_iomap.h in sync with the declarations of pci_iomap(). Link: https://lore.kernel.org/all/CAHk-=wjRrh98pZoQ+AzfWmsTZacWxTJKXZ9eKU2X_0+jM=O8nw@mail.gmail.com/ Signed-off-by: Helge Deller Suggested-by: Linus Torvalds Fixes: 97a29d59fc22 ("[PARISC] fix compile break caused by iomap: make IOPORT/PCI mapping functions conditional") Cc: Arnd Bergmann Cc: Guenter Roeck Cc: Ulrich Teichert Cc: James Bottomley Signed-off-by: Linus Torvalds --- arch/parisc/lib/iomap.c | 4 +++- include/asm-generic/iomap.h | 10 ---------- include/asm-generic/pci_iomap.h | 3 +++ 3 files changed, 6 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/arch/parisc/lib/iomap.c b/arch/parisc/lib/iomap.c index f03adb1999e7..367f6397bda7 100644 --- a/arch/parisc/lib/iomap.c +++ b/arch/parisc/lib/iomap.c @@ -513,12 +513,15 @@ void ioport_unmap(void __iomem *addr) } } +#ifdef CONFIG_PCI void pci_iounmap(struct pci_dev *dev, void __iomem * addr) { if (!INDIRECT_ADDR(addr)) { iounmap(addr); } } +EXPORT_SYMBOL(pci_iounmap); +#endif EXPORT_SYMBOL(ioread8); EXPORT_SYMBOL(ioread16); @@ -544,4 +547,3 @@ EXPORT_SYMBOL(iowrite16_rep); EXPORT_SYMBOL(iowrite32_rep); EXPORT_SYMBOL(ioport_map); EXPORT_SYMBOL(ioport_unmap); -EXPORT_SYMBOL(pci_iounmap); diff --git a/include/asm-generic/iomap.h b/include/asm-generic/iomap.h index 9b3eb6d86200..08237ae8b840 100644 --- a/include/asm-generic/iomap.h +++ b/include/asm-generic/iomap.h @@ -110,16 +110,6 @@ static inline void __iomem *ioremap_np(phys_addr_t offset, size_t size) } #endif -#ifdef CONFIG_PCI -/* Destroy a virtual mapping cookie for a PCI BAR (memory or IO) */ -struct pci_dev; -extern void pci_iounmap(struct pci_dev *dev, void __iomem *); -#elif defined(CONFIG_GENERIC_IOMAP) -struct pci_dev; -static inline void pci_iounmap(struct pci_dev *dev, void __iomem *addr) -{ } -#endif - #include #endif diff --git a/include/asm-generic/pci_iomap.h b/include/asm-generic/pci_iomap.h index df636c6d8e6c..5a2f9bf53384 100644 --- a/include/asm-generic/pci_iomap.h +++ b/include/asm-generic/pci_iomap.h @@ -18,6 +18,7 @@ extern void __iomem *pci_iomap_range(struct pci_dev *dev, int bar, extern void __iomem *pci_iomap_wc_range(struct pci_dev *dev, int bar, unsigned long offset, unsigned long maxlen); +extern void pci_iounmap(struct pci_dev *dev, void __iomem *); /* Create a virtual mapping cookie for a port on a given PCI device. * Do not call this directly, it exists to make it easier for architectures * to override */ @@ -50,6 +51,8 @@ static inline void __iomem *pci_iomap_wc_range(struct pci_dev *dev, int bar, { return NULL; } +static inline void pci_iounmap(struct pci_dev *dev, void __iomem *addr) +{ } #endif #endif /* __ASM_GENERIC_PCI_IOMAP_H */ -- cgit v1.2.3 From 316e8d79a0959c302b0c462ab64b069599f10eef Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 19 Sep 2021 17:13:35 -0700 Subject: pci_iounmap'2: Electric Boogaloo: try to make sense of it all Nathan Chancellor reports that the recent change to pci_iounmap in commit 9caea0007601 ("parisc: Declare pci_iounmap() parisc version only when CONFIG_PCI enabled") causes build errors on arm64. It took me about two hours to convince myself that I think I know what the logic of that mess of #ifdef's in the header file really aim to do, and rewrite it to be easier to follow. Famous last words. Anyway, the code has now been lifted from that grotty header file into lib/pci_iomap.c, and has fairly extensive comments about what the logic is. It also avoids indirecting through another confusing (and badly named) helper function that has other preprocessor config conditionals. Let's see what odd architecture did something else strange in this area to break things. But my arm64 cross build is clean. Fixes: 9caea0007601 ("parisc: Declare pci_iounmap() parisc version only when CONFIG_PCI enabled") Reported-by: Nathan Chancellor Cc: Helge Deller Cc: Arnd Bergmann Cc: Guenter Roeck Cc: Ulrich Teichert Cc: James Bottomley Signed-off-by: Linus Torvalds --- include/asm-generic/io.h | 26 +++----------------------- lib/pci_iomap.c | 43 +++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 46 insertions(+), 23 deletions(-) (limited to 'include') diff --git a/include/asm-generic/io.h b/include/asm-generic/io.h index e93375c710b9..cc7338f9e0d1 100644 --- a/include/asm-generic/io.h +++ b/include/asm-generic/io.h @@ -1023,16 +1023,7 @@ static inline void __iomem *ioport_map(unsigned long port, unsigned int nr) port &= IO_SPACE_LIMIT; return (port > MMIO_UPPER_LIMIT) ? NULL : PCI_IOBASE + port; } -#define __pci_ioport_unmap __pci_ioport_unmap -static inline void __pci_ioport_unmap(void __iomem *p) -{ - uintptr_t start = (uintptr_t) PCI_IOBASE; - uintptr_t addr = (uintptr_t) p; - - if (addr >= start && addr < start + IO_SPACE_LIMIT) - return; - iounmap(p); -} +#define ARCH_HAS_GENERIC_IOPORT_MAP #endif #ifndef ioport_unmap @@ -1048,21 +1039,10 @@ extern void ioport_unmap(void __iomem *p); #endif /* CONFIG_HAS_IOPORT_MAP */ #ifndef CONFIG_GENERIC_IOMAP -struct pci_dev; -extern void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long max); - -#ifndef __pci_ioport_unmap -static inline void __pci_ioport_unmap(void __iomem *p) {} -#endif - #ifndef pci_iounmap -#define pci_iounmap pci_iounmap -static inline void pci_iounmap(struct pci_dev *dev, void __iomem *p) -{ - __pci_ioport_unmap(p); -} +#define ARCH_WANTS_GENERIC_PCI_IOUNMAP +#endif #endif -#endif /* CONFIG_GENERIC_IOMAP */ #ifndef xlate_dev_mem_ptr #define xlate_dev_mem_ptr xlate_dev_mem_ptr diff --git a/lib/pci_iomap.c b/lib/pci_iomap.c index 2d3eb1cb73b8..ce39ce9f3526 100644 --- a/lib/pci_iomap.c +++ b/lib/pci_iomap.c @@ -134,4 +134,47 @@ void __iomem *pci_iomap_wc(struct pci_dev *dev, int bar, unsigned long maxlen) return pci_iomap_wc_range(dev, bar, 0, maxlen); } EXPORT_SYMBOL_GPL(pci_iomap_wc); + +/* + * pci_iounmap() somewhat illogically comes from lib/iomap.c for the + * CONFIG_GENERIC_IOMAP case, because that's the code that knows about + * the different IOMAP ranges. + * + * But if the architecture does not use the generic iomap code, and if + * it has _not_ defined it's own private pci_iounmap function, we define + * it here. + * + * NOTE! This default implementation assumes that if the architecture + * support ioport mapping (HAS_IOPORT_MAP), the ioport mapping will + * be fixed to the range [ PCI_IOBASE, PCI_IOBASE+IO_SPACE_LIMIT [, + * and does not need unmapping with 'ioport_unmap()'. + * + * If you have different rules for your architecture, you need to + * implement your own pci_iounmap() that knows the rules for where + * and how IO vs MEM get mapped. + * + * This code is odd, and the ARCH_HAS/ARCH_WANTS #define logic comes + * from legacy header file behavior. In particular, + * it would seem to make sense to do the iounmap(p) for the non-IO-space + * case here regardless, but that's not what the old header file code + * did. Probably incorrectly, but this is meant to be bug-for-bug + * compatible. + */ +#if defined(ARCH_WANTS_GENERIC_PCI_IOUNMAP) + +void pci_iounmap(struct pci_dev *dev, void __iomem *p) +{ +#ifdef ARCH_HAS_GENERIC_IOPORT_MAP + uintptr_t start = (uintptr_t) PCI_IOBASE; + uintptr_t addr = (uintptr_t) p; + + if (addr >= start && addr < start + IO_SPACE_LIMIT) + return; + iounmap(p); +#endif +} +EXPORT_SYMBOL(pci_iounmap); + +#endif /* ARCH_WANTS_GENERIC_PCI_IOUNMAP */ + #endif /* CONFIG_PCI */ -- cgit v1.2.3 From d9f91a10c3e8b8b6f6762e35f2905a8914ca309d Mon Sep 17 00:00:00 2001 From: Douglas Anderson Date: Tue, 14 Sep 2021 13:21:50 -0700 Subject: drm/edid: Allow querying/working with the panel ID from the EDID EDIDs have 32-bits worth of data which is intended to be used to uniquely identify the make/model of a panel. This has historically been used only internally in the EDID processing code to identify quirks with panels. We'd like to use this panel ID in panel drivers to identify which panel is hooked up and from that information figure out power sequence timings. Let's expose this information from the EDID code and also allow it to be accessed early, before a connector has been created. To make matching in the panel drivers code easier, we'll return the panel ID as a 32-bit value. We'll provide some functions for converting this value back and forth to something more human readable. Signed-off-by: Douglas Anderson Acked-by: Sam Ravnborg Reviewed-by: Jani Nikula Acked-by: Linus Walleij Link: https://patchwork.freedesktop.org/patch/msgid/20210914132020.v5.3.I4a672175ba1894294d91d3dbd51da11a8239cf4a@changeid --- drivers/gpu/drm/drm_edid.c | 67 ++++++++++++++++++++++++++++++++++++++++++++++ include/drm/drm_edid.h | 45 +++++++++++++++++++++++++++++++ 2 files changed, 112 insertions(+) (limited to 'include') diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c index 520fe1391769..f84e0dd264f4 100644 --- a/drivers/gpu/drm/drm_edid.c +++ b/drivers/gpu/drm/drm_edid.c @@ -2087,6 +2087,73 @@ struct edid *drm_get_edid(struct drm_connector *connector, } EXPORT_SYMBOL(drm_get_edid); +static u32 edid_extract_panel_id(const struct edid *edid) +{ + /* + * In theory we could try to de-obfuscate this like edid_get_quirks() + * does, but it's easier to just deal with a 32-bit number since then + * it can be compared with "==". + * + * NOTE that we deal with endianness differently for the top half + * of this ID than for the bottom half. The bottom half (the product + * id) gets decoded as little endian by the EDID_PRODUCT_ID because + * that's how everyone seems to interpret it. The top half (the mfg_id) + * gets stored as big endian because that makes + * drm_edid_encode_panel_id() and drm_edid_decode_panel_id() easier + * to write (it's easier to extract the ASCII). It doesn't really + * matter, though, as long as the number here is unique. + */ + return (u32)edid->mfg_id[0] << 24 | + (u32)edid->mfg_id[1] << 16 | + (u32)EDID_PRODUCT_ID(edid); +} + +/** + * drm_edid_get_panel_id - Get a panel's ID through DDC + * @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 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). + * + * 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. + */ + +u32 drm_edid_get_panel_id(struct i2c_adapter *adapter) +{ + struct edid *edid; + u32 panel_id; + + edid = drm_do_get_edid_base_block(drm_do_probe_ddc_edid, adapter, + NULL, NULL); + + /* + * There are no manufacturer IDs of 0, so if there is a problem reading + * the EDID then we'll just return 0. + */ + if (IS_ERR_OR_NULL(edid)) + return 0; + + panel_id = edid_extract_panel_id(edid); + kfree(edid); + + return panel_id; +} +EXPORT_SYMBOL(drm_edid_get_panel_id); + /** * drm_get_edid_switcheroo - get EDID data for a vga_switcheroo output * @connector: connector we're probing diff --git a/include/drm/drm_edid.h b/include/drm/drm_edid.h index deccfd39e6db..ccc80cb7f86a 100644 --- a/include/drm/drm_edid.h +++ b/include/drm/drm_edid.h @@ -508,6 +508,50 @@ static inline u8 drm_eld_get_conn_type(const uint8_t *eld) return eld[DRM_ELD_SAD_COUNT_CONN_TYPE] & DRM_ELD_CONN_TYPE_MASK; } +/** + * drm_edid_encode_panel_id - Encode an ID for matching against drm_edid_get_panel_id() + * @vend: 3-character vendor string + * @product_id: The 16-bit product ID. + * + * This is a macro so that it can be calculated at compile time and used + * as an initializer. + * + * For instance: + * drm_edid_encode_panel_id("BOE", 0x2d08) => 0x09e52d08 + * + * Return: a 32-bit ID per panel. + */ +#define drm_edid_encode_panel_id(vend, product_id) \ + ((((u32)((vend)[0]) - '@') & 0x1f) << 26 | \ + (((u32)((vend)[1]) - '@') & 0x1f) << 21 | \ + (((u32)((vend)[2]) - '@') & 0x1f) << 16 | \ + ((product_id) & 0xffff)) + +/** + * drm_edid_decode_panel_id - Decode a panel ID from drm_edid_encode_panel_id() + * @panel_id: The panel ID to decode. + * @vend: A 4-byte buffer to store the 3-letter vendor string plus a '\0' + * termination + * @product_id: The product ID will be returned here. + * + * For instance, after: + * drm_edid_decode_panel_id(0x09e52d08, vend, &product_id) + * These will be true: + * vend[0] = 'B' + * vend[1] = 'O' + * vend[2] = 'E' + * vend[3] = '\0' + * product_id = 0x2d08 + */ +static inline void drm_edid_decode_panel_id(u32 panel_id, char vend[4], u16 *product_id) +{ + *product_id = (u16)(panel_id & 0xffff); + vend[0] = '@' + ((panel_id >> 26) & 0x1f); + vend[1] = '@' + ((panel_id >> 21) & 0x1f); + vend[2] = '@' + ((panel_id >> 16) & 0x1f); + vend[3] = '\0'; +} + bool drm_probe_ddc(struct i2c_adapter *adapter); struct edid *drm_do_get_edid(struct drm_connector *connector, int (*get_edid_block)(void *data, u8 *buf, unsigned int block, @@ -515,6 +559,7 @@ 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); 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 3229b906fb35b63515f0c703b917357c83e1ea22 Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Thu, 16 Sep 2021 20:15:57 +0200 Subject: lib: devres: Add managed arch_phys_wc_add() Add devm_arch_phys_wc_add() as managed wrapper around arch_phys_wc_add(). Useful for several graphics drivers that set framebuffer memory to write combining. v2: * fix typo in commit description Signed-off-by: Thomas Zimmermann Reviewed-by: Hans de Goede Link: https://patchwork.freedesktop.org/patch/msgid/20210916181601.9146-2-tzimmermann@suse.de --- include/linux/io.h | 2 ++ lib/devres.c | 36 ++++++++++++++++++++++++++++++++++++ 2 files changed, 38 insertions(+) (limited to 'include') diff --git a/include/linux/io.h b/include/linux/io.h index 9595151d800d..fcd8ea79c5df 100644 --- a/include/linux/io.h +++ b/include/linux/io.h @@ -132,6 +132,8 @@ static inline int arch_phys_wc_index(int handle) #endif #endif +int devm_arch_phys_wc_add(struct device *dev, unsigned long base, unsigned long size); + enum { /* See memremap() kernel-doc for usage description... */ MEMREMAP_WB = 1 << 0, diff --git a/lib/devres.c b/lib/devres.c index b0e1c6702c71..24d4d849ff67 100644 --- a/lib/devres.c +++ b/lib/devres.c @@ -528,3 +528,39 @@ void pcim_iounmap_regions(struct pci_dev *pdev, int mask) } EXPORT_SYMBOL(pcim_iounmap_regions); #endif /* CONFIG_PCI */ + +static void devm_arch_phys_ac_add_release(struct device *dev, void *res) +{ + arch_phys_wc_del(*((int *)res)); +} + +/** + * devm_arch_phys_wc_add - Managed arch_phys_wc_add() + * @dev: Managed device + * @base: Memory base address + * @size: Size of memory range + * + * Adds a WC MTRR using arch_phys_wc_add() and sets up a release callback. + * See arch_phys_wc_add() for more information. + */ +int devm_arch_phys_wc_add(struct device *dev, unsigned long base, unsigned long size) +{ + int *mtrr; + int ret; + + mtrr = devres_alloc(devm_arch_phys_ac_add_release, sizeof(*mtrr), GFP_KERNEL); + if (!mtrr) + return -ENOMEM; + + ret = arch_phys_wc_add(base, size); + if (ret < 0) { + devres_free(mtrr); + return ret; + } + + *mtrr = ret; + devres_add(dev, mtrr); + + return ret; +} +EXPORT_SYMBOL(devm_arch_phys_wc_add); -- cgit v1.2.3 From c822310725ee41af663de2448094155d442ff871 Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Thu, 16 Sep 2021 20:15:58 +0200 Subject: lib: devres: Add managed arch_io_reserve_memtype_wc() Add devm_arch_io_reserve_memtype_wc() as managed wrapper around arch_io_reserve_memtype_wc(). Useful for several graphics drivers that set framebuffer memory to write combining. v2: * fix typo in commit description Signed-off-by: Thomas Zimmermann Reviewed-by: Hans de Goede Link: https://patchwork.freedesktop.org/patch/msgid/20210916181601.9146-3-tzimmermann@suse.de --- include/linux/io.h | 3 +++ lib/devres.c | 46 ++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 49 insertions(+) (limited to 'include') diff --git a/include/linux/io.h b/include/linux/io.h index fcd8ea79c5df..5fc800390fe4 100644 --- a/include/linux/io.h +++ b/include/linux/io.h @@ -168,4 +168,7 @@ static inline void arch_io_free_memtype_wc(resource_size_t base, } #endif +int devm_arch_io_reserve_memtype_wc(struct device *dev, resource_size_t start, + resource_size_t size); + #endif /* _LINUX_IO_H */ diff --git a/lib/devres.c b/lib/devres.c index 24d4d849ff67..14664bbb4875 100644 --- a/lib/devres.c +++ b/lib/devres.c @@ -564,3 +564,49 @@ int devm_arch_phys_wc_add(struct device *dev, unsigned long base, unsigned long return ret; } EXPORT_SYMBOL(devm_arch_phys_wc_add); + +struct arch_io_reserve_memtype_wc_devres { + resource_size_t start; + resource_size_t size; +}; + +static void devm_arch_io_free_memtype_wc_release(struct device *dev, void *res) +{ + const struct arch_io_reserve_memtype_wc_devres *this = res; + + arch_io_free_memtype_wc(this->start, this->size); +} + +/** + * devm_arch_io_reserve_memtype_wc - Managed arch_io_reserve_memtype_wc() + * @dev: Managed device + * @start: Memory base address + * @size: Size of memory range + * + * Reserves a memory range with WC caching using arch_io_reserve_memtype_wc() + * and sets up a release callback See arch_io_reserve_memtype_wc() for more + * information. + */ +int devm_arch_io_reserve_memtype_wc(struct device *dev, resource_size_t start, + resource_size_t size) +{ + struct arch_io_reserve_memtype_wc_devres *dr; + int ret; + + dr = devres_alloc(devm_arch_io_free_memtype_wc_release, sizeof(*dr), GFP_KERNEL); + if (!dr) + return -ENOMEM; + + ret = arch_io_reserve_memtype_wc(start, size); + if (ret < 0) { + devres_free(dr); + return ret; + } + + dr->start = start; + dr->size = size; + devres_add(dev, dr); + + return ret; +} +EXPORT_SYMBOL(devm_arch_io_reserve_memtype_wc); -- cgit v1.2.3 From a1419fb4a73e47f0eab2985dff594ed52397471b Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Fri, 10 Sep 2021 12:11:57 +0200 Subject: drm/mipi-dsi: Create devm device registration Devices that take their data through the MIPI-DSI bus but are controlled through a secondary bus like I2C have to register a secondary device on the MIPI-DSI bus through the mipi_dsi_device_register_full() function. At removal or when an error occurs, that device needs to be removed through a call to mipi_dsi_device_unregister(). Let's create a device-managed variant of the registration function that will automatically unregister the device at unbind. Reviewed-by: Andrzej Hajda Signed-off-by: Maxime Ripard Link: https://patchwork.freedesktop.org/patch/msgid/20210910101218.1632297-4-maxime@cerno.tech --- drivers/gpu/drm/drm_mipi_dsi.c | 46 ++++++++++++++++++++++++++++++++++++++++++ include/drm/drm_mipi_dsi.h | 3 +++ 2 files changed, 49 insertions(+) (limited to 'include') diff --git a/drivers/gpu/drm/drm_mipi_dsi.c b/drivers/gpu/drm/drm_mipi_dsi.c index 5dd475e82995..ddf67463eaa1 100644 --- a/drivers/gpu/drm/drm_mipi_dsi.c +++ b/drivers/gpu/drm/drm_mipi_dsi.c @@ -246,6 +246,52 @@ void mipi_dsi_device_unregister(struct mipi_dsi_device *dsi) } EXPORT_SYMBOL(mipi_dsi_device_unregister); +static void devm_mipi_dsi_device_unregister(void *arg) +{ + struct mipi_dsi_device *dsi = arg; + + mipi_dsi_device_unregister(dsi); +} + +/** + * devm_mipi_dsi_device_register_full - create a managed MIPI DSI device + * @dev: device to tie the MIPI-DSI device lifetime to + * @host: DSI host to which this device is connected + * @info: pointer to template containing DSI device information + * + * Create a MIPI DSI device by using the device information provided by + * mipi_dsi_device_info template + * + * This is the managed version of mipi_dsi_device_register_full() which + * automatically calls mipi_dsi_device_unregister() when @dev is + * unbound. + * + * Returns: + * A pointer to the newly created MIPI DSI device, or, a pointer encoded + * with an error + */ +struct mipi_dsi_device * +devm_mipi_dsi_device_register_full(struct device *dev, + struct mipi_dsi_host *host, + const struct mipi_dsi_device_info *info) +{ + struct mipi_dsi_device *dsi; + int ret; + + dsi = mipi_dsi_device_register_full(host, info); + if (IS_ERR(dsi)) + return dsi; + + ret = devm_add_action_or_reset(dev, + devm_mipi_dsi_device_unregister, + dsi); + if (ret) + return ERR_PTR(ret); + + return dsi; +} +EXPORT_SYMBOL_GPL(devm_mipi_dsi_device_register_full); + static DEFINE_MUTEX(host_lock); static LIST_HEAD(host_list); diff --git a/include/drm/drm_mipi_dsi.h b/include/drm/drm_mipi_dsi.h index af7ba8071eb0..d0032e435e08 100644 --- a/include/drm/drm_mipi_dsi.h +++ b/include/drm/drm_mipi_dsi.h @@ -227,6 +227,9 @@ struct mipi_dsi_device * mipi_dsi_device_register_full(struct mipi_dsi_host *host, const struct mipi_dsi_device_info *info); void mipi_dsi_device_unregister(struct mipi_dsi_device *dsi); +struct mipi_dsi_device * +devm_mipi_dsi_device_register_full(struct device *dev, struct mipi_dsi_host *host, + const struct mipi_dsi_device_info *info); struct mipi_dsi_device *of_find_mipi_dsi_device_by_node(struct device_node *np); int mipi_dsi_attach(struct mipi_dsi_device *dsi); int mipi_dsi_detach(struct mipi_dsi_device *dsi); -- cgit v1.2.3 From db6568498b35a4d5d5a99420df27ed25fae31406 Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Fri, 10 Sep 2021 12:11:58 +0200 Subject: drm/mipi-dsi: Create devm device attachment MIPI-DSI devices need to call mipi_dsi_attach() when their probe is done to attach against their host. However, at removal or when an error occurs, that attachment needs to be undone through a call to mipi_dsi_detach(). Let's create a device-managed variant of the attachment function that will automatically detach the device at unbind. Reviewed-by: Andrzej Hajda Signed-off-by: Maxime Ripard Link: https://patchwork.freedesktop.org/patch/msgid/20210910101218.1632297-5-maxime@cerno.tech --- drivers/gpu/drm/drm_mipi_dsi.c | 35 +++++++++++++++++++++++++++++++++++ include/drm/drm_mipi_dsi.h | 1 + 2 files changed, 36 insertions(+) (limited to 'include') diff --git a/drivers/gpu/drm/drm_mipi_dsi.c b/drivers/gpu/drm/drm_mipi_dsi.c index ddf67463eaa1..18cef04df2f2 100644 --- a/drivers/gpu/drm/drm_mipi_dsi.c +++ b/drivers/gpu/drm/drm_mipi_dsi.c @@ -391,6 +391,41 @@ int mipi_dsi_detach(struct mipi_dsi_device *dsi) } EXPORT_SYMBOL(mipi_dsi_detach); +static void devm_mipi_dsi_detach(void *arg) +{ + struct mipi_dsi_device *dsi = arg; + + mipi_dsi_detach(dsi); +} + +/** + * devm_mipi_dsi_attach - Attach a MIPI-DSI device to its DSI Host + * @dev: device to tie the MIPI-DSI device attachment lifetime to + * @dsi: DSI peripheral + * + * This is the managed version of mipi_dsi_attach() which automatically + * calls mipi_dsi_detach() when @dev is unbound. + * + * Returns: + * 0 on success, a negative error code on failure. + */ +int devm_mipi_dsi_attach(struct device *dev, + struct mipi_dsi_device *dsi) +{ + int ret; + + ret = mipi_dsi_attach(dsi); + if (ret) + return ret; + + ret = devm_add_action_or_reset(dev, devm_mipi_dsi_detach, dsi); + if (ret) + return ret; + + return 0; +} +EXPORT_SYMBOL_GPL(devm_mipi_dsi_attach); + static ssize_t mipi_dsi_device_transfer(struct mipi_dsi_device *dsi, struct mipi_dsi_msg *msg) { diff --git a/include/drm/drm_mipi_dsi.h b/include/drm/drm_mipi_dsi.h index d0032e435e08..147e51b6d241 100644 --- a/include/drm/drm_mipi_dsi.h +++ b/include/drm/drm_mipi_dsi.h @@ -233,6 +233,7 @@ devm_mipi_dsi_device_register_full(struct device *dev, struct mipi_dsi_host *hos struct mipi_dsi_device *of_find_mipi_dsi_device_by_node(struct device_node *np); int mipi_dsi_attach(struct mipi_dsi_device *dsi); int mipi_dsi_detach(struct mipi_dsi_device *dsi); +int devm_mipi_dsi_attach(struct device *dev, struct mipi_dsi_device *dsi); int mipi_dsi_shutdown_peripheral(struct mipi_dsi_device *dsi); int mipi_dsi_turn_on_peripheral(struct mipi_dsi_device *dsi); int mipi_dsi_set_maximum_return_packet_size(struct mipi_dsi_device *dsi, -- cgit v1.2.3 From 7d1be0a09fa62139f1a29ccbe6d46aa04616539b Mon Sep 17 00:00:00 2001 From: Douglas Anderson Date: Fri, 24 Sep 2021 07:53:21 -0700 Subject: drm/edid: Fix EDID quirk compile error on older compilers Apparently some compilers [1] cannot handle doing math on dereferenced string constants at compile time. This has led to reports [2] of compile errors like: In file included from drivers/gpu/drm/drm_edid.c:42:0: ./include/drm/drm_edid.h:525:2: error: initializer element is not constant ((((u32)((vend)[0]) - '@') & 0x1f) << 26 | \ Go back to the syntax I used in v4 of the patch series [3] that added this code instead of what landed (v5). This syntax is slightly uglier but should be much more compatible with varied compilers. [1] https://gcc.gnu.org/bugzilla/show_bug.cgi?id=69960#c18 [2] https://lore.kernel.org/r/874kaabdt5.fsf@intel.com/ [3] https://lore.kernel.org/r/20210909135838.v4.4.I6103ce2b16e5e5a842b14c7022a034712b434609@changeid/ Fixes: d9f91a10c3e8 ("drm/edid: Allow querying/working with the panel ID from the EDID") Reported-by: Stanislav Lisovskiy Reported-by: Srikanth Myakam Signed-off-by: Douglas Anderson Acked-by: Randy Dunlap # build-tested Acked-by: Sam Ravnborg Link: https://patchwork.freedesktop.org/patch/msgid/20210924075317.1.I1e58d74d501613f1fe7585958f451160d11b8a98@changeid --- drivers/gpu/drm/drm_edid.c | 121 +++++++++++++++++++------------------- drivers/gpu/drm/panel/panel-edp.c | 23 ++++---- include/drm/drm_edid.h | 14 +++-- 3 files changed, 81 insertions(+), 77 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c index 53b342c058be..9b19eee0e1b4 100644 --- a/drivers/gpu/drm/drm_edid.c +++ b/drivers/gpu/drm/drm_edid.c @@ -100,9 +100,10 @@ struct detailed_mode_closure { #define LEVEL_GTF2 2 #define LEVEL_CVT 3 -#define EDID_QUIRK(vend, product_id, _quirks) \ +#define EDID_QUIRK(vend_chr_0, vend_chr_1, vend_chr_2, product_id, _quirks) \ { \ - .panel_id = drm_edid_encode_panel_id(vend, product_id), \ + .panel_id = drm_edid_encode_panel_id(vend_chr_0, vend_chr_1, vend_chr_2, \ + product_id), \ .quirks = _quirks \ } @@ -111,116 +112,116 @@ static const struct edid_quirk { u32 quirks; } edid_quirk_list[] = { /* Acer AL1706 */ - EDID_QUIRK("ACR", 44358, EDID_QUIRK_PREFER_LARGE_60), + EDID_QUIRK('A', 'C', 'R', 44358, EDID_QUIRK_PREFER_LARGE_60), /* Acer F51 */ - EDID_QUIRK("API", 0x7602, EDID_QUIRK_PREFER_LARGE_60), + EDID_QUIRK('A', 'P', 'I', 0x7602, EDID_QUIRK_PREFER_LARGE_60), /* AEO model 0 reports 8 bpc, but is a 6 bpc panel */ - EDID_QUIRK("AEO", 0, EDID_QUIRK_FORCE_6BPC), + EDID_QUIRK('A', 'E', 'O', 0, EDID_QUIRK_FORCE_6BPC), /* BOE model on HP Pavilion 15-n233sl reports 8 bpc, but is a 6 bpc panel */ - EDID_QUIRK("BOE", 0x78b, EDID_QUIRK_FORCE_6BPC), + EDID_QUIRK('B', 'O', 'E', 0x78b, EDID_QUIRK_FORCE_6BPC), /* CPT panel of Asus UX303LA reports 8 bpc, but is a 6 bpc panel */ - EDID_QUIRK("CPT", 0x17df, EDID_QUIRK_FORCE_6BPC), + EDID_QUIRK('C', 'P', 'T', 0x17df, EDID_QUIRK_FORCE_6BPC), /* SDC panel of Lenovo B50-80 reports 8 bpc, but is a 6 bpc panel */ - EDID_QUIRK("SDC", 0x3652, EDID_QUIRK_FORCE_6BPC), + EDID_QUIRK('S', 'D', 'C', 0x3652, EDID_QUIRK_FORCE_6BPC), /* BOE model 0x0771 reports 8 bpc, but is a 6 bpc panel */ - EDID_QUIRK("BOE", 0x0771, EDID_QUIRK_FORCE_6BPC), + EDID_QUIRK('B', 'O', 'E', 0x0771, EDID_QUIRK_FORCE_6BPC), /* Belinea 10 15 55 */ - EDID_QUIRK("MAX", 1516, EDID_QUIRK_PREFER_LARGE_60), - EDID_QUIRK("MAX", 0x77e, EDID_QUIRK_PREFER_LARGE_60), + EDID_QUIRK('M', 'A', 'X', 1516, EDID_QUIRK_PREFER_LARGE_60), + EDID_QUIRK('M', 'A', 'X', 0x77e, EDID_QUIRK_PREFER_LARGE_60), /* Envision Peripherals, Inc. EN-7100e */ - EDID_QUIRK("EPI", 59264, EDID_QUIRK_135_CLOCK_TOO_HIGH), + EDID_QUIRK('E', 'P', 'I', 59264, EDID_QUIRK_135_CLOCK_TOO_HIGH), /* Envision EN2028 */ - EDID_QUIRK("EPI", 8232, EDID_QUIRK_PREFER_LARGE_60), + EDID_QUIRK('E', 'P', 'I', 8232, EDID_QUIRK_PREFER_LARGE_60), /* Funai Electronics PM36B */ - EDID_QUIRK("FCM", 13600, EDID_QUIRK_PREFER_LARGE_75 | + EDID_QUIRK('F', 'C', 'M', 13600, EDID_QUIRK_PREFER_LARGE_75 | EDID_QUIRK_DETAILED_IN_CM), /* LGD panel of HP zBook 17 G2, eDP 10 bpc, but reports unknown bpc */ - EDID_QUIRK("LGD", 764, EDID_QUIRK_FORCE_10BPC), + EDID_QUIRK('L', 'G', 'D', 764, EDID_QUIRK_FORCE_10BPC), /* LG Philips LCD LP154W01-A5 */ - EDID_QUIRK("LPL", 0, EDID_QUIRK_DETAILED_USE_MAXIMUM_SIZE), - EDID_QUIRK("LPL", 0x2a00, EDID_QUIRK_DETAILED_USE_MAXIMUM_SIZE), + EDID_QUIRK('L', 'P', 'L', 0, EDID_QUIRK_DETAILED_USE_MAXIMUM_SIZE), + EDID_QUIRK('L', 'P', 'L', 0x2a00, EDID_QUIRK_DETAILED_USE_MAXIMUM_SIZE), /* Samsung SyncMaster 205BW. Note: irony */ - EDID_QUIRK("SAM", 541, EDID_QUIRK_DETAILED_SYNC_PP), + EDID_QUIRK('S', 'A', 'M', 541, EDID_QUIRK_DETAILED_SYNC_PP), /* Samsung SyncMaster 22[5-6]BW */ - EDID_QUIRK("SAM", 596, EDID_QUIRK_PREFER_LARGE_60), - EDID_QUIRK("SAM", 638, EDID_QUIRK_PREFER_LARGE_60), + EDID_QUIRK('S', 'A', 'M', 596, EDID_QUIRK_PREFER_LARGE_60), + EDID_QUIRK('S', 'A', 'M', 638, EDID_QUIRK_PREFER_LARGE_60), /* Sony PVM-2541A does up to 12 bpc, but only reports max 8 bpc */ - EDID_QUIRK("SNY", 0x2541, EDID_QUIRK_FORCE_12BPC), + EDID_QUIRK('S', 'N', 'Y', 0x2541, EDID_QUIRK_FORCE_12BPC), /* ViewSonic VA2026w */ - EDID_QUIRK("VSC", 5020, EDID_QUIRK_FORCE_REDUCED_BLANKING), + EDID_QUIRK('V', 'S', 'C', 5020, EDID_QUIRK_FORCE_REDUCED_BLANKING), /* Medion MD 30217 PG */ - EDID_QUIRK("MED", 0x7b8, EDID_QUIRK_PREFER_LARGE_75), + EDID_QUIRK('M', 'E', 'D', 0x7b8, EDID_QUIRK_PREFER_LARGE_75), /* Lenovo G50 */ - EDID_QUIRK("SDC", 18514, EDID_QUIRK_FORCE_6BPC), + EDID_QUIRK('S', 'D', 'C', 18514, EDID_QUIRK_FORCE_6BPC), /* Panel in Samsung NP700G7A-S01PL notebook reports 6bpc */ - EDID_QUIRK("SEC", 0xd033, EDID_QUIRK_FORCE_8BPC), + EDID_QUIRK('S', 'E', 'C', 0xd033, EDID_QUIRK_FORCE_8BPC), /* Rotel RSX-1058 forwards sink's EDID but only does HDMI 1.1*/ - EDID_QUIRK("ETR", 13896, EDID_QUIRK_FORCE_8BPC), + EDID_QUIRK('E', 'T', 'R', 13896, EDID_QUIRK_FORCE_8BPC), /* Valve Index Headset */ - EDID_QUIRK("VLV", 0x91a8, EDID_QUIRK_NON_DESKTOP), - EDID_QUIRK("VLV", 0x91b0, EDID_QUIRK_NON_DESKTOP), - EDID_QUIRK("VLV", 0x91b1, EDID_QUIRK_NON_DESKTOP), - EDID_QUIRK("VLV", 0x91b2, EDID_QUIRK_NON_DESKTOP), - EDID_QUIRK("VLV", 0x91b3, EDID_QUIRK_NON_DESKTOP), - EDID_QUIRK("VLV", 0x91b4, EDID_QUIRK_NON_DESKTOP), - EDID_QUIRK("VLV", 0x91b5, EDID_QUIRK_NON_DESKTOP), - EDID_QUIRK("VLV", 0x91b6, EDID_QUIRK_NON_DESKTOP), - EDID_QUIRK("VLV", 0x91b7, EDID_QUIRK_NON_DESKTOP), - EDID_QUIRK("VLV", 0x91b8, EDID_QUIRK_NON_DESKTOP), - EDID_QUIRK("VLV", 0x91b9, EDID_QUIRK_NON_DESKTOP), - EDID_QUIRK("VLV", 0x91ba, EDID_QUIRK_NON_DESKTOP), - EDID_QUIRK("VLV", 0x91bb, EDID_QUIRK_NON_DESKTOP), - EDID_QUIRK("VLV", 0x91bc, EDID_QUIRK_NON_DESKTOP), - EDID_QUIRK("VLV", 0x91bd, EDID_QUIRK_NON_DESKTOP), - EDID_QUIRK("VLV", 0x91be, EDID_QUIRK_NON_DESKTOP), - EDID_QUIRK("VLV", 0x91bf, EDID_QUIRK_NON_DESKTOP), + EDID_QUIRK('V', 'L', 'V', 0x91a8, EDID_QUIRK_NON_DESKTOP), + EDID_QUIRK('V', 'L', 'V', 0x91b0, EDID_QUIRK_NON_DESKTOP), + EDID_QUIRK('V', 'L', 'V', 0x91b1, EDID_QUIRK_NON_DESKTOP), + EDID_QUIRK('V', 'L', 'V', 0x91b2, EDID_QUIRK_NON_DESKTOP), + EDID_QUIRK('V', 'L', 'V', 0x91b3, EDID_QUIRK_NON_DESKTOP), + EDID_QUIRK('V', 'L', 'V', 0x91b4, EDID_QUIRK_NON_DESKTOP), + EDID_QUIRK('V', 'L', 'V', 0x91b5, EDID_QUIRK_NON_DESKTOP), + EDID_QUIRK('V', 'L', 'V', 0x91b6, EDID_QUIRK_NON_DESKTOP), + EDID_QUIRK('V', 'L', 'V', 0x91b7, EDID_QUIRK_NON_DESKTOP), + EDID_QUIRK('V', 'L', 'V', 0x91b8, EDID_QUIRK_NON_DESKTOP), + EDID_QUIRK('V', 'L', 'V', 0x91b9, EDID_QUIRK_NON_DESKTOP), + EDID_QUIRK('V', 'L', 'V', 0x91ba, EDID_QUIRK_NON_DESKTOP), + EDID_QUIRK('V', 'L', 'V', 0x91bb, EDID_QUIRK_NON_DESKTOP), + EDID_QUIRK('V', 'L', 'V', 0x91bc, EDID_QUIRK_NON_DESKTOP), + EDID_QUIRK('V', 'L', 'V', 0x91bd, EDID_QUIRK_NON_DESKTOP), + EDID_QUIRK('V', 'L', 'V', 0x91be, EDID_QUIRK_NON_DESKTOP), + EDID_QUIRK('V', 'L', 'V', 0x91bf, EDID_QUIRK_NON_DESKTOP), /* HTC Vive and Vive Pro VR Headsets */ - EDID_QUIRK("HVR", 0xaa01, EDID_QUIRK_NON_DESKTOP), - EDID_QUIRK("HVR", 0xaa02, EDID_QUIRK_NON_DESKTOP), + EDID_QUIRK('H', 'V', 'R', 0xaa01, EDID_QUIRK_NON_DESKTOP), + EDID_QUIRK('H', 'V', 'R', 0xaa02, EDID_QUIRK_NON_DESKTOP), /* Oculus Rift DK1, DK2, CV1 and Rift S VR Headsets */ - EDID_QUIRK("OVR", 0x0001, EDID_QUIRK_NON_DESKTOP), - EDID_QUIRK("OVR", 0x0003, EDID_QUIRK_NON_DESKTOP), - EDID_QUIRK("OVR", 0x0004, EDID_QUIRK_NON_DESKTOP), - EDID_QUIRK("OVR", 0x0012, EDID_QUIRK_NON_DESKTOP), + EDID_QUIRK('O', 'V', 'R', 0x0001, EDID_QUIRK_NON_DESKTOP), + EDID_QUIRK('O', 'V', 'R', 0x0003, EDID_QUIRK_NON_DESKTOP), + EDID_QUIRK('O', 'V', 'R', 0x0004, EDID_QUIRK_NON_DESKTOP), + EDID_QUIRK('O', 'V', 'R', 0x0012, EDID_QUIRK_NON_DESKTOP), /* Windows Mixed Reality Headsets */ - EDID_QUIRK("ACR", 0x7fce, EDID_QUIRK_NON_DESKTOP), - EDID_QUIRK("HPN", 0x3515, EDID_QUIRK_NON_DESKTOP), - EDID_QUIRK("LEN", 0x0408, EDID_QUIRK_NON_DESKTOP), - EDID_QUIRK("LEN", 0xb800, EDID_QUIRK_NON_DESKTOP), - EDID_QUIRK("FUJ", 0x1970, EDID_QUIRK_NON_DESKTOP), - EDID_QUIRK("DEL", 0x7fce, EDID_QUIRK_NON_DESKTOP), - EDID_QUIRK("SEC", 0x144a, EDID_QUIRK_NON_DESKTOP), - EDID_QUIRK("AUS", 0xc102, EDID_QUIRK_NON_DESKTOP), + EDID_QUIRK('A', 'C', 'R', 0x7fce, EDID_QUIRK_NON_DESKTOP), + EDID_QUIRK('H', 'P', 'N', 0x3515, EDID_QUIRK_NON_DESKTOP), + EDID_QUIRK('L', 'E', 'N', 0x0408, EDID_QUIRK_NON_DESKTOP), + EDID_QUIRK('L', 'E', 'N', 0xb800, EDID_QUIRK_NON_DESKTOP), + EDID_QUIRK('F', 'U', 'J', 0x1970, EDID_QUIRK_NON_DESKTOP), + EDID_QUIRK('D', 'E', 'L', 0x7fce, EDID_QUIRK_NON_DESKTOP), + EDID_QUIRK('S', 'E', 'C', 0x144a, EDID_QUIRK_NON_DESKTOP), + EDID_QUIRK('A', 'U', 'S', 0xc102, EDID_QUIRK_NON_DESKTOP), /* Sony PlayStation VR Headset */ - EDID_QUIRK("SNY", 0x0704, EDID_QUIRK_NON_DESKTOP), + EDID_QUIRK('S', 'N', 'Y', 0x0704, EDID_QUIRK_NON_DESKTOP), /* Sensics VR Headsets */ - EDID_QUIRK("SEN", 0x1019, EDID_QUIRK_NON_DESKTOP), + EDID_QUIRK('S', 'E', 'N', 0x1019, EDID_QUIRK_NON_DESKTOP), /* OSVR HDK and HDK2 VR Headsets */ - EDID_QUIRK("SVR", 0x1019, EDID_QUIRK_NON_DESKTOP), + EDID_QUIRK('S', 'V', 'R', 0x1019, EDID_QUIRK_NON_DESKTOP), }; /* diff --git a/drivers/gpu/drm/panel/panel-edp.c b/drivers/gpu/drm/panel/panel-edp.c index 4c37c4f6d26c..fc03046de134 100644 --- a/drivers/gpu/drm/panel/panel-edp.c +++ b/drivers/gpu/drm/panel/panel-edp.c @@ -1745,10 +1745,11 @@ static const struct panel_delay delay_200_500_e50 = { .enable = 50, }; -#define EDP_PANEL_ENTRY(vend, product_id, _delay, _name) \ +#define EDP_PANEL_ENTRY(vend_chr_0, vend_chr_1, vend_chr_2, product_id, _delay, _name) \ { \ .name = _name, \ - .panel_id = drm_edid_encode_panel_id(vend, product_id), \ + .panel_id = drm_edid_encode_panel_id(vend_chr_0, vend_chr_1, vend_chr_2, \ + product_id), \ .delay = _delay \ } @@ -1760,19 +1761,19 @@ static const struct panel_delay delay_200_500_e50 = { * Sort first by vendor, then by product ID. */ static const struct edp_panel_entry edp_panels[] = { - EDP_PANEL_ENTRY("AUO", 0x405c, &auo_b116xak01.delay, "B116XAK01"), - EDP_PANEL_ENTRY("AUO", 0x615c, &delay_200_500_e50, "B116XAN06.1"), + EDP_PANEL_ENTRY('A', 'U', 'O', 0x405c, &auo_b116xak01.delay, "B116XAK01"), + EDP_PANEL_ENTRY('A', 'U', 'O', 0x615c, &delay_200_500_e50, "B116XAN06.1"), - EDP_PANEL_ENTRY("BOE", 0x0786, &delay_200_500_p2e80, "NV116WHM-T01"), - EDP_PANEL_ENTRY("BOE", 0x07d1, &boe_nv133fhm_n61.delay, "NV133FHM-N61"), - EDP_PANEL_ENTRY("BOE", 0x082d, &boe_nv133fhm_n61.delay, "NV133FHM-N62"), - EDP_PANEL_ENTRY("BOE", 0x098d, &boe_nv110wtm_n61.delay, "NV110WTM-N61"), + EDP_PANEL_ENTRY('B', 'O', 'E', 0x0786, &delay_200_500_p2e80, "NV116WHM-T01"), + EDP_PANEL_ENTRY('B', 'O', 'E', 0x07d1, &boe_nv133fhm_n61.delay, "NV133FHM-N61"), + EDP_PANEL_ENTRY('B', 'O', 'E', 0x082d, &boe_nv133fhm_n61.delay, "NV133FHM-N62"), + EDP_PANEL_ENTRY('B', 'O', 'E', 0x098d, &boe_nv110wtm_n61.delay, "NV110WTM-N61"), - EDP_PANEL_ENTRY("CMN", 0x114c, &innolux_n116bca_ea1.delay, "N116BCA-EA1"), + EDP_PANEL_ENTRY('C', 'M', 'N', 0x114c, &innolux_n116bca_ea1.delay, "N116BCA-EA1"), - EDP_PANEL_ENTRY("KDB", 0x0624, &kingdisplay_kd116n21_30nv_a010.delay, "116N21-30NV-A010"), + EDP_PANEL_ENTRY('K', 'D', 'B', 0x0624, &kingdisplay_kd116n21_30nv_a010.delay, "116N21-30NV-A010"), - EDP_PANEL_ENTRY("SHP", 0x154c, &delay_200_500_p2e100, "LQ116M1JW10"), + EDP_PANEL_ENTRY('S', 'H', 'P', 0x154c, &delay_200_500_p2e100, "LQ116M1JW10"), { /* sentinal */ } }; diff --git a/include/drm/drm_edid.h b/include/drm/drm_edid.h index ccc80cb7f86a..4d17cd04fff7 100644 --- a/include/drm/drm_edid.h +++ b/include/drm/drm_edid.h @@ -510,21 +510,23 @@ static inline u8 drm_eld_get_conn_type(const uint8_t *eld) /** * drm_edid_encode_panel_id - Encode an ID for matching against drm_edid_get_panel_id() - * @vend: 3-character vendor string + * @vend_chr_0: First character of the vendor string. + * @vend_chr_2: Second character of the vendor string. + * @vend_chr_3: Third character of the vendor string. * @product_id: The 16-bit product ID. * * This is a macro so that it can be calculated at compile time and used * as an initializer. * * For instance: - * drm_edid_encode_panel_id("BOE", 0x2d08) => 0x09e52d08 + * drm_edid_encode_panel_id('B', 'O', 'E', 0x2d08) => 0x09e52d08 * * Return: a 32-bit ID per panel. */ -#define drm_edid_encode_panel_id(vend, product_id) \ - ((((u32)((vend)[0]) - '@') & 0x1f) << 26 | \ - (((u32)((vend)[1]) - '@') & 0x1f) << 21 | \ - (((u32)((vend)[2]) - '@') & 0x1f) << 16 | \ +#define drm_edid_encode_panel_id(vend_chr_0, vend_chr_1, vend_chr_2, product_id) \ + ((((u32)(vend_chr_0) - '@') & 0x1f) << 26 | \ + (((u32)(vend_chr_1) - '@') & 0x1f) << 21 | \ + (((u32)(vend_chr_2) - '@') & 0x1f) << 16 | \ ((product_id) & 0xffff)) /** -- cgit v1.2.3 From 306589856399e18894d20e717c217ede0a866d22 Mon Sep 17 00:00:00 2001 From: Douglas Anderson Date: Tue, 21 Sep 2021 08:28:01 -0700 Subject: drm/print: Add deprecation notes to DRM_...() functions It's hard for someone (like me) who's not following closely to know what the suggested best practices are for error printing in DRM drivers. Add some hints to the header file. In general, my understanding is that: * When possible we should be using a `struct drm_device` for logging and recent patches have tried to make it more possible to access a relevant `struct drm_device` in more places. * For most cases when we don't have a `struct drm_device`, we no longer bother with DRM-specific wrappers on the dev_...() functions or pr_...() functions and just encourage drivers to use the normal functions. * For debug-level functions where we might want filtering based on a category we'll still have DRM-specific wrappers, but we'll only support passing a `struct drm_device`, not a `struct device`. Presumably most of the cases where we want the filtering are messages that happen while the system is in a normal running state (AKA not during probe time) and we should have a `struct drm_device` then. If we absolutely can't get a `struct drm_device` then these functions begrudgingly accept NULL for the `struct drm_device` and hopefully the awkwardness of having to manually pass NULL will keep people from doing this unless absolutely necessary. Signed-off-by: Douglas Anderson Acked-by: Thomas Zimmermann Acked-by: Lyude Paul Link: https://patchwork.freedesktop.org/patch/msgid/20210921082757.RFC.1.Ibd82d98145615fa55f604947dc6a696cc82e8e43@changeid --- include/drm/drm_print.h | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) (limited to 'include') diff --git a/include/drm/drm_print.h b/include/drm/drm_print.h index 15a089a87c22..22fabdeed297 100644 --- a/include/drm/drm_print.h +++ b/include/drm/drm_print.h @@ -340,6 +340,8 @@ void drm_dev_dbg(const struct device *dev, enum drm_debug_category category, /** * DRM_DEV_ERROR() - Error output. * + * NOTE: this is deprecated in favor of drm_err() or dev_err(). + * * @dev: device pointer * @fmt: printf() like format string. */ @@ -349,6 +351,9 @@ void drm_dev_dbg(const struct device *dev, enum drm_debug_category category, /** * DRM_DEV_ERROR_RATELIMITED() - Rate limited error output. * + * NOTE: this is deprecated in favor of drm_err_ratelimited() or + * dev_err_ratelimited(). + * * @dev: device pointer * @fmt: printf() like format string. * @@ -364,9 +369,11 @@ void drm_dev_dbg(const struct device *dev, enum drm_debug_category category, DRM_DEV_ERROR(dev, fmt, ##__VA_ARGS__); \ }) +/* NOTE: this is deprecated in favor of drm_info() or dev_info(). */ #define DRM_DEV_INFO(dev, fmt, ...) \ drm_dev_printk(dev, KERN_INFO, fmt, ##__VA_ARGS__) +/* NOTE: this is deprecated in favor of drm_info_once() or dev_info_once(). */ #define DRM_DEV_INFO_ONCE(dev, fmt, ...) \ ({ \ static bool __print_once __read_mostly; \ @@ -379,6 +386,8 @@ void drm_dev_dbg(const struct device *dev, enum drm_debug_category category, /** * DRM_DEV_DEBUG() - Debug output for generic drm code * + * NOTE: this is deprecated in favor of drm_dbg_core(). + * * @dev: device pointer * @fmt: printf() like format string. */ @@ -387,6 +396,8 @@ void drm_dev_dbg(const struct device *dev, enum drm_debug_category category, /** * DRM_DEV_DEBUG_DRIVER() - Debug output for vendor specific part of the driver * + * NOTE: this is deprecated in favor of drm_dbg() or dev_dbg(). + * * @dev: device pointer * @fmt: printf() like format string. */ @@ -395,6 +406,8 @@ void drm_dev_dbg(const struct device *dev, enum drm_debug_category category, /** * DRM_DEV_DEBUG_KMS() - Debug output for modesetting code * + * NOTE: this is deprecated in favor of drm_dbg_kms(). + * * @dev: device pointer * @fmt: printf() like format string. */ @@ -480,47 +493,63 @@ void __drm_err(const char *format, ...); #define _DRM_PRINTK(once, level, fmt, ...) \ printk##once(KERN_##level "[" DRM_NAME "] " fmt, ##__VA_ARGS__) +/* NOTE: this is deprecated in favor of pr_info(). */ #define DRM_INFO(fmt, ...) \ _DRM_PRINTK(, INFO, fmt, ##__VA_ARGS__) +/* NOTE: this is deprecated in favor of pr_notice(). */ #define DRM_NOTE(fmt, ...) \ _DRM_PRINTK(, NOTICE, fmt, ##__VA_ARGS__) +/* NOTE: this is deprecated in favor of pr_warn(). */ #define DRM_WARN(fmt, ...) \ _DRM_PRINTK(, WARNING, fmt, ##__VA_ARGS__) +/* NOTE: this is deprecated in favor of pr_info_once(). */ #define DRM_INFO_ONCE(fmt, ...) \ _DRM_PRINTK(_once, INFO, fmt, ##__VA_ARGS__) +/* NOTE: this is deprecated in favor of pr_notice_once(). */ #define DRM_NOTE_ONCE(fmt, ...) \ _DRM_PRINTK(_once, NOTICE, fmt, ##__VA_ARGS__) +/* NOTE: this is deprecated in favor of pr_warn_once(). */ #define DRM_WARN_ONCE(fmt, ...) \ _DRM_PRINTK(_once, WARNING, fmt, ##__VA_ARGS__) +/* NOTE: this is deprecated in favor of pr_err(). */ #define DRM_ERROR(fmt, ...) \ __drm_err(fmt, ##__VA_ARGS__) +/* NOTE: this is deprecated in favor of pr_err_ratelimited(). */ #define DRM_ERROR_RATELIMITED(fmt, ...) \ DRM_DEV_ERROR_RATELIMITED(NULL, fmt, ##__VA_ARGS__) +/* NOTE: this is deprecated in favor of drm_dbg_core(NULL, ...). */ #define DRM_DEBUG(fmt, ...) \ __drm_dbg(DRM_UT_CORE, fmt, ##__VA_ARGS__) +/* NOTE: this is deprecated in favor of drm_dbg(NULL, ...). */ #define DRM_DEBUG_DRIVER(fmt, ...) \ __drm_dbg(DRM_UT_DRIVER, fmt, ##__VA_ARGS__) +/* NOTE: this is deprecated in favor of drm_dbg_kms(NULL, ...). */ #define DRM_DEBUG_KMS(fmt, ...) \ __drm_dbg(DRM_UT_KMS, fmt, ##__VA_ARGS__) +/* NOTE: this is deprecated in favor of drm_dbg_prime(NULL, ...). */ #define DRM_DEBUG_PRIME(fmt, ...) \ __drm_dbg(DRM_UT_PRIME, fmt, ##__VA_ARGS__) +/* NOTE: this is deprecated in favor of drm_dbg_atomic(NULL, ...). */ #define DRM_DEBUG_ATOMIC(fmt, ...) \ __drm_dbg(DRM_UT_ATOMIC, fmt, ##__VA_ARGS__) +/* NOTE: this is deprecated in favor of drm_dbg_vbl(NULL, ...). */ #define DRM_DEBUG_VBL(fmt, ...) \ __drm_dbg(DRM_UT_VBL, fmt, ##__VA_ARGS__) +/* NOTE: this is deprecated in favor of drm_dbg_lease(NULL, ...). */ #define DRM_DEBUG_LEASE(fmt, ...) \ __drm_dbg(DRM_UT_LEASE, fmt, ##__VA_ARGS__) +/* NOTE: this is deprecated in favor of drm_dbg_dp(NULL, ...). */ #define DRM_DEBUG_DP(fmt, ...) \ __drm_dbg(DRM_UT_DP, fmt, ## __VA_ARGS__) @@ -536,6 +565,7 @@ void __drm_err(const char *format, ...); #define drm_dbg_kms_ratelimited(drm, fmt, ...) \ __DRM_DEFINE_DBG_RATELIMITED(KMS, drm, fmt, ## __VA_ARGS__) +/* NOTE: this is deprecated in favor of drm_dbg_kms_ratelimited(NULL, ...). */ #define DRM_DEBUG_KMS_RATELIMITED(fmt, ...) drm_dbg_kms_ratelimited(NULL, fmt, ## __VA_ARGS__) /* -- cgit v1.2.3 From 116e5947d7bf49cf5a29e1eb30deec12ed8b53f8 Mon Sep 17 00:00:00 2001 From: Douglas Anderson Date: Mon, 27 Sep 2021 07:41:22 -0700 Subject: drm/edid: Fix drm_edid_encode_panel_id() kerneldoc warning Due to a simple typo (apparently I can't count. It goes 0, 1, 2 and not 0, 2, 3) we were getting a kernel doc warning that looked like this: include/drm/drm_edid.h:530: warning: Function parameter or member 'vend_chr_1' not described in 'drm_edid_encode_panel_id' include/drm/drm_edid.h:530: warning: Excess function parameter 'vend_chr_3' description in 'drm_edid_encode_panel_id' Fix it. Fixes: 7d1be0a09fa6 ("drm/edid: Fix EDID quirk compile error on older compilers") Reported-by: Stephen Rothwell Signed-off-by: Douglas Anderson Acked-by: Randy Dunlap Link: https://patchwork.freedesktop.org/patch/msgid/20210927074104.1.Ibf22f2a0b75287a5d636c0570c11498648bf61c6@changeid --- include/drm/drm_edid.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/drm/drm_edid.h b/include/drm/drm_edid.h index 4d17cd04fff7..18f6c700f6d0 100644 --- a/include/drm/drm_edid.h +++ b/include/drm/drm_edid.h @@ -511,8 +511,8 @@ static inline u8 drm_eld_get_conn_type(const uint8_t *eld) /** * drm_edid_encode_panel_id - Encode an ID for matching against drm_edid_get_panel_id() * @vend_chr_0: First character of the vendor string. - * @vend_chr_2: Second character of the vendor string. - * @vend_chr_3: Third character of the vendor string. + * @vend_chr_1: Second character of the vendor string. + * @vend_chr_2: Third character of the vendor string. * @product_id: The 16-bit product ID. * * This is a macro so that it can be calculated at compile time and used -- cgit v1.2.3 From b3ed524f84f573ece1aa2f26e9db3c34a593e0d1 Mon Sep 17 00:00:00 2001 From: Christian König Date: Thu, 23 Sep 2021 14:47:57 +0200 Subject: drm/msm: allow compile_test on !ARM MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit MSM is one of the few drivers which won't even compile test on !ARM platforms. Looking into this a bit more it turned out that there is actually not that much missing to at least let the driver compile on x86 as well. So this patch replaces the use of phys_to_page() with the open coded version and provides a dummy for of_drm_find_bridge(). Signed-off-by: Christian König Reviewed-by: Rob Clark Link: https://patchwork.freedesktop.org/patch/msgid/20210924071759.22659-2-christian.koenig@amd.com --- drivers/gpu/drm/msm/Kconfig | 4 ++-- drivers/gpu/drm/msm/msm_gem.c | 2 +- include/drm/drm_bridge.h | 10 +++++++++- 3 files changed, 12 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/msm/Kconfig b/drivers/gpu/drm/msm/Kconfig index e9c6af78b1d7..5879f67bc88c 100644 --- a/drivers/gpu/drm/msm/Kconfig +++ b/drivers/gpu/drm/msm/Kconfig @@ -3,9 +3,9 @@ config DRM_MSM tristate "MSM DRM" depends on DRM - depends on ARCH_QCOM || SOC_IMX5 || (ARM && COMPILE_TEST) + depends on ARCH_QCOM || SOC_IMX5 || COMPILE_TEST depends on IOMMU_SUPPORT - depends on OF && COMMON_CLK + depends on (OF && COMMON_CLK) || COMPILE_TEST depends on QCOM_OCMEM || QCOM_OCMEM=n depends on QCOM_LLCC || QCOM_LLCC=n depends on QCOM_COMMAND_DB || QCOM_COMMAND_DB=n diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c index 22308a1b66fc..40a9863f5951 100644 --- a/drivers/gpu/drm/msm/msm_gem.c +++ b/drivers/gpu/drm/msm/msm_gem.c @@ -85,7 +85,7 @@ static struct page **get_pages_vram(struct drm_gem_object *obj, int npages) paddr = physaddr(obj); for (i = 0; i < npages; i++) { - p[i] = phys_to_page(paddr); + p[i] = pfn_to_page(__phys_to_pfn(paddr)); paddr += PAGE_SIZE; } diff --git a/include/drm/drm_bridge.h b/include/drm/drm_bridge.h index 9cdbd209388e..a445298e1c25 100644 --- a/include/drm/drm_bridge.h +++ b/include/drm/drm_bridge.h @@ -790,11 +790,19 @@ drm_priv_to_bridge(struct drm_private_obj *priv) void drm_bridge_add(struct drm_bridge *bridge); void drm_bridge_remove(struct drm_bridge *bridge); -struct drm_bridge *of_drm_find_bridge(struct device_node *np); int drm_bridge_attach(struct drm_encoder *encoder, struct drm_bridge *bridge, struct drm_bridge *previous, enum drm_bridge_attach_flags flags); +#ifdef CONFIG_OF +struct drm_bridge *of_drm_find_bridge(struct device_node *np); +#else +static inline struct drm_bridge *of_drm_find_bridge(struct device_node *np) +{ + return NULL; +} +#endif + /** * drm_bridge_get_next_bridge() - Get the next bridge in the chain * @bridge: bridge object -- cgit v1.2.3 From 0464ed1a79b818d5e3eda1ac3c23a057ac0cc7c3 Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Tue, 14 Sep 2021 12:17:23 +0200 Subject: drm/probe-helper: Create a HPD IRQ event helper for a single connector The drm_helper_hpd_irq_event() function is iterating over all the connectors when an hotplug event is detected. During that iteration, it will call each connector detect function and figure out if its status changed. Finally, if any connector changed, it will notify the user-space and the clients that something changed on the DRM device. This is supposed to be used for drivers that don't have a hotplug interrupt for individual connectors. However, drivers that can use an interrupt for a single connector are left in the dust and can either reimplement the logic used during the iteration for each connector or use that helper and iterate over all connectors all the time. Since both are suboptimal, let's create a helper that will only perform the status detection on a single connector. Signed-off-by: Maxime Ripard Reviewed-by: Sam Ravnborg Link: https://patchwork.freedesktop.org/patch/msgid/20210914101724.266570-2-maxime@cerno.tech --- drivers/gpu/drm/drm_probe_helper.c | 116 +++++++++++++++++++++++++++---------- include/drm/drm_probe_helper.h | 1 + 2 files changed, 86 insertions(+), 31 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/drm_probe_helper.c b/drivers/gpu/drm/drm_probe_helper.c index 5b77fb5c1a32..61d5c57f23e1 100644 --- a/drivers/gpu/drm/drm_probe_helper.c +++ b/drivers/gpu/drm/drm_probe_helper.c @@ -795,6 +795,86 @@ void drm_kms_helper_poll_fini(struct drm_device *dev) } EXPORT_SYMBOL(drm_kms_helper_poll_fini); +static bool check_connector_changed(struct drm_connector *connector) +{ + struct drm_device *dev = connector->dev; + enum drm_connector_status old_status; + u64 old_epoch_counter; + + /* Only handle HPD capable connectors. */ + drm_WARN_ON(dev, !(connector->polled & DRM_CONNECTOR_POLL_HPD)); + + drm_WARN_ON(dev, !mutex_is_locked(&dev->mode_config.mutex)); + + old_status = connector->status; + old_epoch_counter = connector->epoch_counter; + connector->status = drm_helper_probe_detect(connector, NULL, false); + + if (old_epoch_counter == connector->epoch_counter) { + drm_dbg_kms(dev, "[CONNECTOR:%d:%s] Same epoch counter %llu\n", + connector->base.id, + connector->name, + connector->epoch_counter); + + return false; + } + + drm_dbg_kms(dev, "[CONNECTOR:%d:%s] status updated from %s to %s\n", + connector->base.id, + connector->name, + drm_get_connector_status_name(old_status), + drm_get_connector_status_name(connector->status)); + + drm_dbg_kms(dev, "[CONNECTOR:%d:%s] Changed epoch counter %llu => %llu\n", + connector->base.id, + connector->name, + old_epoch_counter, + connector->epoch_counter); + + return true; +} + +/** + * drm_connector_helper_hpd_irq_event - hotplug processing + * @connector: drm_connector + * + * Drivers can use this helper function to run a detect cycle on a connector + * which has the DRM_CONNECTOR_POLL_HPD flag set in its &polled member. + * + * This helper function is useful for drivers which can track hotplug + * interrupts for a single connector. Drivers that want to send a + * hotplug event for all connectors or can't track hotplug interrupts + * per connector need to use drm_helper_hpd_irq_event(). + * + * This function must be called from process context with no mode + * setting locks held. + * + * Note that a connector can be both polled and probed from the hotplug + * handler, in case the hotplug interrupt is known to be unreliable. + * + * Returns: + * A boolean indicating whether the connector status changed or not + */ +bool drm_connector_helper_hpd_irq_event(struct drm_connector *connector) +{ + struct drm_device *dev = connector->dev; + bool changed; + + mutex_lock(&dev->mode_config.mutex); + changed = check_connector_changed(connector); + mutex_unlock(&dev->mode_config.mutex); + + if (changed) { + drm_kms_helper_hotplug_event(dev); + drm_dbg_kms(dev, "[CONNECTOR:%d:%s] Sent hotplug event\n", + connector->base.id, + connector->name); + } + + return changed; +} +EXPORT_SYMBOL(drm_connector_helper_hpd_irq_event); + /** * drm_helper_hpd_irq_event - hotplug processing * @dev: drm_device @@ -808,9 +888,10 @@ EXPORT_SYMBOL(drm_kms_helper_poll_fini); * interrupts for each connector. * * Drivers which support hotplug interrupts for each connector individually and - * which have a more fine-grained detect logic should bypass this code and - * directly call drm_kms_helper_hotplug_event() in case the connector state - * changed. + * which have a more fine-grained detect logic can use + * drm_connector_helper_hpd_irq_event(). Alternatively, they should bypass this + * code and directly call drm_kms_helper_hotplug_event() in case the connector + * state changed. * * This function must be called from process context with no mode * setting locks held. @@ -825,9 +906,7 @@ bool drm_helper_hpd_irq_event(struct drm_device *dev) { struct drm_connector *connector; struct drm_connector_list_iter conn_iter; - enum drm_connector_status old_status; bool changed = false; - u64 old_epoch_counter; if (!dev->mode_config.poll_enabled) return false; @@ -839,33 +918,8 @@ bool drm_helper_hpd_irq_event(struct drm_device *dev) if (!(connector->polled & DRM_CONNECTOR_POLL_HPD)) continue; - old_status = connector->status; - - old_epoch_counter = connector->epoch_counter; - - DRM_DEBUG_KMS("[CONNECTOR:%d:%s] Old epoch counter %llu\n", connector->base.id, - connector->name, - old_epoch_counter); - - connector->status = drm_helper_probe_detect(connector, NULL, false); - DRM_DEBUG_KMS("[CONNECTOR:%d:%s] status updated from %s to %s\n", - connector->base.id, - connector->name, - drm_get_connector_status_name(old_status), - drm_get_connector_status_name(connector->status)); - - DRM_DEBUG_KMS("[CONNECTOR:%d:%s] New epoch counter %llu\n", - connector->base.id, - connector->name, - connector->epoch_counter); - - /* - * Check if epoch counter had changed, meaning that we need - * to send a uevent. - */ - if (old_epoch_counter != connector->epoch_counter) + if (check_connector_changed(connector)) changed = true; - } drm_connector_list_iter_end(&conn_iter); mutex_unlock(&dev->mode_config.mutex); diff --git a/include/drm/drm_probe_helper.h b/include/drm/drm_probe_helper.h index 8d3ed2834d34..04c57564c397 100644 --- a/include/drm/drm_probe_helper.h +++ b/include/drm/drm_probe_helper.h @@ -18,6 +18,7 @@ int drm_helper_probe_detect(struct drm_connector *connector, void drm_kms_helper_poll_init(struct drm_device *dev); void drm_kms_helper_poll_fini(struct drm_device *dev); bool drm_helper_hpd_irq_event(struct drm_device *dev); +bool drm_connector_helper_hpd_irq_event(struct drm_connector *connector); void drm_kms_helper_hotplug_event(struct drm_device *dev); void drm_kms_helper_poll_disable(struct drm_device *dev); -- cgit v1.2.3 From 34268c9dde4cbae0b701b66c44497da068f418ee Mon Sep 17 00:00:00 2001 From: Gurchetan Singh Date: Tue, 21 Sep 2021 16:20:13 -0700 Subject: virtio-gpu api: multiple context types with explicit initialization This feature allows for each virtio-gpu 3D context to be created with a "context_init" variable. This variable can specify: - the type of protocol used by the context via the capset id. This is useful for differentiating virgl, gfxstream, and venus protocols by host userspace. - other things in the future, such as the version of the context. In addition, each different context needs one or more timelines, so for example a virgl context's waiting can be independent on a gfxstream context's waiting. VIRTIO_GPU_FLAG_INFO_RING_IDX is introduced to specific to tell the host which per-context command ring (or "hardware queue", distinct from the virtio-queue) the fence should be associated with. The new capability sets (gfxstream, venus etc.) are only defined in the virtio-gpu spec and not defined in the header. Signed-off-by: Gurchetan Singh Acked-by: Lingfeng Yang Link: http://patchwork.freedesktop.org/patch/msgid/20210921232024.817-2-gurchetansingh@chromium.org Signed-off-by: Gerd Hoffmann --- include/uapi/linux/virtio_gpu.h | 18 +++++++++++++++--- 1 file changed, 15 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/virtio_gpu.h b/include/uapi/linux/virtio_gpu.h index 97523a95781d..f556fde07b76 100644 --- a/include/uapi/linux/virtio_gpu.h +++ b/include/uapi/linux/virtio_gpu.h @@ -59,6 +59,11 @@ * VIRTIO_GPU_CMD_RESOURCE_CREATE_BLOB */ #define VIRTIO_GPU_F_RESOURCE_BLOB 3 +/* + * VIRTIO_GPU_CMD_CREATE_CONTEXT with + * context_init and multiple timelines + */ +#define VIRTIO_GPU_F_CONTEXT_INIT 4 enum virtio_gpu_ctrl_type { VIRTIO_GPU_UNDEFINED = 0, @@ -122,14 +127,20 @@ enum virtio_gpu_shm_id { VIRTIO_GPU_SHM_ID_HOST_VISIBLE = 1 }; -#define VIRTIO_GPU_FLAG_FENCE (1 << 0) +#define VIRTIO_GPU_FLAG_FENCE (1 << 0) +/* + * If the following flag is set, then ring_idx contains the index + * of the command ring that needs to used when creating the fence + */ +#define VIRTIO_GPU_FLAG_INFO_RING_IDX (1 << 1) struct virtio_gpu_ctrl_hdr { __le32 type; __le32 flags; __le64 fence_id; __le32 ctx_id; - __le32 padding; + __u8 ring_idx; + __u8 padding[3]; }; /* data passed in the cursor vq */ @@ -269,10 +280,11 @@ struct virtio_gpu_resource_create_3d { }; /* VIRTIO_GPU_CMD_CTX_CREATE */ +#define VIRTIO_GPU_CONTEXT_INIT_CAPSET_ID_MASK 0x000000ff struct virtio_gpu_ctx_create { struct virtio_gpu_ctrl_hdr hdr; __le32 nlen; - __le32 padding; + __le32 context_init; char debug_name[64]; }; -- cgit v1.2.3 From b10790434cf2a40017bd796a99d5c4a6e949d616 Mon Sep 17 00:00:00 2001 From: Gurchetan Singh Date: Tue, 21 Sep 2021 16:20:14 -0700 Subject: drm/virtgpu api: create context init feature This change allows creating contexts of depending on set of context parameters. The meaning of each of the parameters is listed below: 1) VIRTGPU_CONTEXT_PARAM_CAPSET_ID This determines the type of a context based on the capability set ID. For example, the current capsets: VIRTIO_GPU_CAPSET_VIRGL VIRTIO_GPU_CAPSET_VIRGL2 define a Gallium, TGSI based "virgl" context. We only need 1 capset ID per context type, though virgl has two due a bug that has since been fixed. The use case is the "gfxstream" rendering library and "venus" renderer. gfxstream doesn't do Gallium/TGSI translation and mostly relies on auto-generated API streaming. Certain users prefer gfxstream over virgl for GLES on GLES emulation. {gfxstream vk}/{venus} are also required for Vulkan emulation. The maximum capset ID is 63. The goal is for guest userspace to choose the optimal context type depending on the situation/hardware. 2) VIRTGPU_CONTEXT_PARAM_NUM_RINGS This tells the number of independent command rings that the context will use. This value may be zero and is inferred to be zero if VIRTGPU_CONTEXT_PARAM_NUM_RINGS is not passed in. This is for backwards compatibility for virgl, which has one big giant command ring for all commands. The maxiumum number of rings is 64. In practice, multi-queue or multi-ring submission is used for powerful dGPUs and virtio-gpu may not be the best option in that case (see PCI passthrough or rendernode forwarding). 3) VIRTGPU_CONTEXT_PARAM_POLL_RING_IDX_MASK This is a mask of ring indices for which the DRM fd is pollable. For example, if VIRTGPU_CONTEXT_PARAM_NUM_RINGS is 2, then the mask may be: [ring idx] | [1 << ring_idx] | final mask ------------------------------------------- 0 1 1 1 2 3 The "Sommelier" guest Wayland proxy uses this to poll for events from the host compositor. Signed-off-by: Gurchetan Singh Acked-by: Lingfeng Yang Acked-by: Nicholas Verne Link: http://patchwork.freedesktop.org/patch/msgid/20210921232024.817-3-gurchetansingh@chromium.org Signed-off-by: Gerd Hoffmann --- include/uapi/drm/virtgpu_drm.h | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) (limited to 'include') diff --git a/include/uapi/drm/virtgpu_drm.h b/include/uapi/drm/virtgpu_drm.h index b9ec26e9c646..a13e20cc66b4 100644 --- a/include/uapi/drm/virtgpu_drm.h +++ b/include/uapi/drm/virtgpu_drm.h @@ -47,12 +47,15 @@ extern "C" { #define DRM_VIRTGPU_WAIT 0x08 #define DRM_VIRTGPU_GET_CAPS 0x09 #define DRM_VIRTGPU_RESOURCE_CREATE_BLOB 0x0a +#define DRM_VIRTGPU_CONTEXT_INIT 0x0b #define VIRTGPU_EXECBUF_FENCE_FD_IN 0x01 #define VIRTGPU_EXECBUF_FENCE_FD_OUT 0x02 +#define VIRTGPU_EXECBUF_RING_IDX 0x04 #define VIRTGPU_EXECBUF_FLAGS (\ VIRTGPU_EXECBUF_FENCE_FD_IN |\ VIRTGPU_EXECBUF_FENCE_FD_OUT |\ + VIRTGPU_EXECBUF_RING_IDX |\ 0) struct drm_virtgpu_map { @@ -68,6 +71,8 @@ struct drm_virtgpu_execbuffer { __u64 bo_handles; __u32 num_bo_handles; __s32 fence_fd; /* in/out fence fd (see VIRTGPU_EXECBUF_FENCE_FD_IN/OUT) */ + __u32 ring_idx; /* command ring index (see VIRTGPU_EXECBUF_RING_IDX) */ + __u32 pad; }; #define VIRTGPU_PARAM_3D_FEATURES 1 /* do we have 3D features in the hw */ @@ -75,6 +80,8 @@ struct drm_virtgpu_execbuffer { #define VIRTGPU_PARAM_RESOURCE_BLOB 3 /* DRM_VIRTGPU_RESOURCE_CREATE_BLOB */ #define VIRTGPU_PARAM_HOST_VISIBLE 4 /* Host blob resources are mappable */ #define VIRTGPU_PARAM_CROSS_DEVICE 5 /* Cross virtio-device resource sharing */ +#define VIRTGPU_PARAM_CONTEXT_INIT 6 /* DRM_VIRTGPU_CONTEXT_INIT */ +#define VIRTGPU_PARAM_SUPPORTED_CAPSET_IDs 7 /* Bitmask of supported capability set ids */ struct drm_virtgpu_getparam { __u64 param; @@ -173,6 +180,22 @@ struct drm_virtgpu_resource_create_blob { __u64 blob_id; }; +#define VIRTGPU_CONTEXT_PARAM_CAPSET_ID 0x0001 +#define VIRTGPU_CONTEXT_PARAM_NUM_RINGS 0x0002 +#define VIRTGPU_CONTEXT_PARAM_POLL_RINGS_MASK 0x0003 +struct drm_virtgpu_context_set_param { + __u64 param; + __u64 value; +}; + +struct drm_virtgpu_context_init { + __u32 num_params; + __u32 pad; + + /* pointer to drm_virtgpu_context_set_param array */ + __u64 ctx_set_params; +}; + #define DRM_IOCTL_VIRTGPU_MAP \ DRM_IOWR(DRM_COMMAND_BASE + DRM_VIRTGPU_MAP, struct drm_virtgpu_map) @@ -212,6 +235,10 @@ struct drm_virtgpu_resource_create_blob { DRM_IOWR(DRM_COMMAND_BASE + DRM_VIRTGPU_RESOURCE_CREATE_BLOB, \ struct drm_virtgpu_resource_create_blob) +#define DRM_IOCTL_VIRTGPU_CONTEXT_INIT \ + DRM_IOWR(DRM_COMMAND_BASE + DRM_VIRTGPU_CONTEXT_INIT, \ + struct drm_virtgpu_context_init) + #if defined(__cplusplus) } #endif -- cgit v1.2.3 From d0f5d790ae863079025398015eb59347b01db455 Mon Sep 17 00:00:00 2001 From: Matthew Auld Date: Mon, 27 Sep 2021 12:41:05 +0100 Subject: drm/ttm: remove TTM_PAGE_FLAG_NO_RETRY MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit No longer used it seems. Signed-off-by: Matthew Auld Cc: Thomas Hellström Cc: Christian König Reviewed-by: Christian König Link: https://patchwork.freedesktop.org/patch/msgid/20210927114114.152310-4-matthew.auld@intel.com Signed-off-by: Christian König --- include/drm/ttm/ttm_tt.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/drm/ttm/ttm_tt.h b/include/drm/ttm/ttm_tt.h index 89b15d673b22..842ce756213c 100644 --- a/include/drm/ttm/ttm_tt.h +++ b/include/drm/ttm/ttm_tt.h @@ -41,7 +41,6 @@ struct ttm_operation_ctx; #define TTM_PAGE_FLAG_SWAPPED (1 << 4) #define TTM_PAGE_FLAG_ZERO_ALLOC (1 << 6) #define TTM_PAGE_FLAG_SG (1 << 8) -#define TTM_PAGE_FLAG_NO_RETRY (1 << 9) #define TTM_PAGE_FLAG_PRIV_POPULATED (1 << 31) -- cgit v1.2.3 From 43d46f0b78bba5dc5ffb6f1b9a1d4c8d0c5dd1fc Mon Sep 17 00:00:00 2001 From: Matthew Auld Date: Wed, 29 Sep 2021 14:26:27 +0100 Subject: drm/ttm: s/FLAG_SG/FLAG_EXTERNAL/ MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit It covers more than just ttm_bo_type_sg usage, like with say dma-buf, since one other user is userptr in amdgpu, and in the future we might have some more. Hence EXTERNAL is likely a more suitable name. v2(Christian): - Rename these to TTM_TT_FLAGS_* - Fix up all the holes in the flag values Suggested-by: Christian König Signed-off-by: Matthew Auld Cc: Thomas Hellström Cc: Christian König Acked-by: Christian König Link: https://patchwork.freedesktop.org/patch/msgid/20210929132629.353541-1-matthew.auld@intel.com Signed-off-by: Christian König --- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 10 +++++----- drivers/gpu/drm/i915/gem/i915_gem_ttm.c | 6 +++--- drivers/gpu/drm/nouveau/nouveau_bo.c | 4 ++-- drivers/gpu/drm/radeon/radeon_ttm.c | 8 ++++---- drivers/gpu/drm/ttm/ttm_bo.c | 4 ++-- drivers/gpu/drm/ttm/ttm_bo_util.c | 4 ++-- drivers/gpu/drm/ttm/ttm_bo_vm.c | 2 +- drivers/gpu/drm/ttm/ttm_pool.c | 2 +- drivers/gpu/drm/ttm/ttm_tt.c | 24 ++++++++++++------------ include/drm/ttm/ttm_device.h | 2 +- include/drm/ttm/ttm_tt.h | 18 +++++++++--------- 11 files changed, 42 insertions(+), 42 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 60b12bb55244..e8d70b6e6737 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -894,7 +894,7 @@ static int amdgpu_ttm_backend_bind(struct ttm_device *bdev, DRM_ERROR("failed to pin userptr\n"); return r; } - } else if (ttm->page_flags & TTM_PAGE_FLAG_SG) { + } else if (ttm->page_flags & TTM_TT_FLAG_EXTERNAL) { if (!ttm->sg) { struct dma_buf_attachment *attach; struct sg_table *sgt; @@ -1130,7 +1130,7 @@ static int amdgpu_ttm_tt_populate(struct ttm_device *bdev, return 0; } - if (ttm->page_flags & TTM_PAGE_FLAG_SG) + if (ttm->page_flags & TTM_TT_FLAG_EXTERNAL) return 0; ret = ttm_pool_alloc(&adev->mman.bdev.pool, ttm, ctx); @@ -1165,7 +1165,7 @@ static void amdgpu_ttm_tt_unpopulate(struct ttm_device *bdev, return; } - if (ttm->page_flags & TTM_PAGE_FLAG_SG) + if (ttm->page_flags & TTM_TT_FLAG_EXTERNAL) return; for (i = 0; i < ttm->num_pages; ++i) @@ -1198,8 +1198,8 @@ int amdgpu_ttm_tt_set_userptr(struct ttm_buffer_object *bo, return -ENOMEM; } - /* Set TTM_PAGE_FLAG_SG before populate but after create. */ - bo->ttm->page_flags |= TTM_PAGE_FLAG_SG; + /* Set TTM_TT_FLAG_EXTERNAL before populate but after create. */ + bo->ttm->page_flags |= TTM_TT_FLAG_EXTERNAL; gtt = (void *)bo->ttm; gtt->userptr = addr; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c index f0a61a9474fc..8beef57ba52b 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c @@ -182,7 +182,7 @@ static struct ttm_tt *i915_ttm_tt_create(struct ttm_buffer_object *bo, if (obj->flags & I915_BO_ALLOC_CPU_CLEAR && man->use_tt) - page_flags |= TTM_PAGE_FLAG_ZERO_ALLOC; + page_flags |= TTM_TT_FLAG_ZERO_ALLOC; ret = ttm_tt_init(&i915_tt->ttm, bo, page_flags, i915_ttm_select_tt_caching(obj)); @@ -451,7 +451,7 @@ static int i915_ttm_accel_move(struct ttm_buffer_object *bo, if (bo->type == ttm_bo_type_kernel) return -EINVAL; - if (ttm && !(ttm->page_flags & TTM_PAGE_FLAG_ZERO_ALLOC)) + if (ttm && !(ttm->page_flags & TTM_TT_FLAG_ZERO_ALLOC)) return 0; intel_engine_pm_get(i915->gt.migrate.context->engine); @@ -525,7 +525,7 @@ static int i915_ttm_move(struct ttm_buffer_object *bo, bool evict, /* Populate ttm with pages if needed. Typically system memory. */ if (bo->ttm && (dst_man->use_tt || - (bo->ttm->page_flags & TTM_PAGE_FLAG_SWAPPED))) { + (bo->ttm->page_flags & TTM_TT_FLAG_SWAPPED))) { ret = ttm_tt_populate(bo->bdev, bo->ttm, ctx); if (ret) return ret; diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c index 33dca2565cca..b2c7e0802ac3 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.c +++ b/drivers/gpu/drm/nouveau/nouveau_bo.c @@ -1249,7 +1249,7 @@ nouveau_ttm_tt_populate(struct ttm_device *bdev, struct ttm_tt *ttm_dma = (void *)ttm; struct nouveau_drm *drm; struct device *dev; - bool slave = !!(ttm->page_flags & TTM_PAGE_FLAG_SG); + bool slave = !!(ttm->page_flags & TTM_TT_FLAG_EXTERNAL); if (ttm_tt_is_populated(ttm)) return 0; @@ -1272,7 +1272,7 @@ nouveau_ttm_tt_unpopulate(struct ttm_device *bdev, { struct nouveau_drm *drm; struct device *dev; - bool slave = !!(ttm->page_flags & TTM_PAGE_FLAG_SG); + bool slave = !!(ttm->page_flags & TTM_TT_FLAG_EXTERNAL); if (slave) return; diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c index 7793249bc549..11b21d605584 100644 --- a/drivers/gpu/drm/radeon/radeon_ttm.c +++ b/drivers/gpu/drm/radeon/radeon_ttm.c @@ -545,14 +545,14 @@ static int radeon_ttm_tt_populate(struct ttm_device *bdev, { struct radeon_device *rdev = radeon_get_rdev(bdev); struct radeon_ttm_tt *gtt = radeon_ttm_tt_to_gtt(rdev, ttm); - bool slave = !!(ttm->page_flags & TTM_PAGE_FLAG_SG); + bool slave = !!(ttm->page_flags & TTM_TT_FLAG_EXTERNAL); if (gtt && gtt->userptr) { ttm->sg = kzalloc(sizeof(struct sg_table), GFP_KERNEL); if (!ttm->sg) return -ENOMEM; - ttm->page_flags |= TTM_PAGE_FLAG_SG; + ttm->page_flags |= TTM_TT_FLAG_EXTERNAL; return 0; } @@ -569,13 +569,13 @@ static void radeon_ttm_tt_unpopulate(struct ttm_device *bdev, struct ttm_tt *ttm { struct radeon_device *rdev = radeon_get_rdev(bdev); struct radeon_ttm_tt *gtt = radeon_ttm_tt_to_gtt(rdev, ttm); - bool slave = !!(ttm->page_flags & TTM_PAGE_FLAG_SG); + bool slave = !!(ttm->page_flags & TTM_TT_FLAG_EXTERNAL); radeon_ttm_tt_unbind(bdev, ttm); if (gtt && gtt->userptr) { kfree(ttm->sg); - ttm->page_flags &= ~TTM_PAGE_FLAG_SG; + ttm->page_flags &= ~TTM_TT_FLAG_EXTERNAL; return; } diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index 3b22c0013dbf..d62b2013c367 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -1115,8 +1115,8 @@ int ttm_bo_swapout(struct ttm_buffer_object *bo, struct ttm_operation_ctx *ctx, return -EBUSY; if (!bo->ttm || !ttm_tt_is_populated(bo->ttm) || - bo->ttm->page_flags & TTM_PAGE_FLAG_SG || - bo->ttm->page_flags & TTM_PAGE_FLAG_SWAPPED || + bo->ttm->page_flags & TTM_TT_FLAG_EXTERNAL || + bo->ttm->page_flags & TTM_TT_FLAG_SWAPPED || !ttm_bo_get_unless_zero(bo)) { if (locked) dma_resv_unlock(bo->base.resv); diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c index 1c5ffe2935af..82af095f6b81 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_util.c +++ b/drivers/gpu/drm/ttm/ttm_bo_util.c @@ -103,7 +103,7 @@ void ttm_move_memcpy(struct ttm_buffer_object *bo, /* Don't move nonexistent data. Clear destination instead. */ if (src_ops->maps_tt && (!ttm || !ttm_tt_is_populated(ttm))) { - if (ttm && !(ttm->page_flags & TTM_PAGE_FLAG_ZERO_ALLOC)) + if (ttm && !(ttm->page_flags & TTM_TT_FLAG_ZERO_ALLOC)) return; for (i = 0; i < num_pages; ++i) { @@ -150,7 +150,7 @@ int ttm_bo_move_memcpy(struct ttm_buffer_object *bo, struct ttm_kmap_iter *dst_iter, *src_iter; int ret = 0; - if (ttm && ((ttm->page_flags & TTM_PAGE_FLAG_SWAPPED) || + if (ttm && ((ttm->page_flags & TTM_TT_FLAG_SWAPPED) || dst_man->use_tt)) { ret = ttm_tt_populate(bdev, ttm, ctx); if (ret) diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c index 9a2119fe4bdd..950f4f132802 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_vm.c +++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c @@ -162,7 +162,7 @@ vm_fault_t ttm_bo_vm_reserve(struct ttm_buffer_object *bo, * Refuse to fault imported pages. This should be handled * (if at all) by redirecting mmap to the exporter. */ - if (bo->ttm && (bo->ttm->page_flags & TTM_PAGE_FLAG_SG)) { + if (bo->ttm && (bo->ttm->page_flags & TTM_TT_FLAG_EXTERNAL)) { dma_resv_unlock(bo->base.resv); return VM_FAULT_SIGBUS; } diff --git a/drivers/gpu/drm/ttm/ttm_pool.c b/drivers/gpu/drm/ttm/ttm_pool.c index c961a788b519..1bba0a0ed3f9 100644 --- a/drivers/gpu/drm/ttm/ttm_pool.c +++ b/drivers/gpu/drm/ttm/ttm_pool.c @@ -371,7 +371,7 @@ int ttm_pool_alloc(struct ttm_pool *pool, struct ttm_tt *tt, WARN_ON(!num_pages || ttm_tt_is_populated(tt)); WARN_ON(dma_addr && !pool->dev); - if (tt->page_flags & TTM_PAGE_FLAG_ZERO_ALLOC) + if (tt->page_flags & TTM_TT_FLAG_ZERO_ALLOC) gfp_flags |= __GFP_ZERO; if (ctx->gfp_retry_mayfail) diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c index 980ecb079b2c..86f31fde6e35 100644 --- a/drivers/gpu/drm/ttm/ttm_tt.c +++ b/drivers/gpu/drm/ttm/ttm_tt.c @@ -68,12 +68,12 @@ int ttm_tt_create(struct ttm_buffer_object *bo, bool zero_alloc) switch (bo->type) { case ttm_bo_type_device: if (zero_alloc) - page_flags |= TTM_PAGE_FLAG_ZERO_ALLOC; + page_flags |= TTM_TT_FLAG_ZERO_ALLOC; break; case ttm_bo_type_kernel: break; case ttm_bo_type_sg: - page_flags |= TTM_PAGE_FLAG_SG; + page_flags |= TTM_TT_FLAG_EXTERNAL; break; default: pr_err("Illegal buffer object type\n"); @@ -156,7 +156,7 @@ EXPORT_SYMBOL(ttm_tt_init); void ttm_tt_fini(struct ttm_tt *ttm) { - WARN_ON(ttm->page_flags & TTM_PAGE_FLAG_PRIV_POPULATED); + WARN_ON(ttm->page_flags & TTM_TT_FLAG_PRIV_POPULATED); if (ttm->swap_storage) fput(ttm->swap_storage); @@ -178,7 +178,7 @@ int ttm_sg_tt_init(struct ttm_tt *ttm, struct ttm_buffer_object *bo, ttm_tt_init_fields(ttm, bo, page_flags, caching); - if (page_flags & TTM_PAGE_FLAG_SG) + if (page_flags & TTM_TT_FLAG_EXTERNAL) ret = ttm_sg_tt_alloc_page_directory(ttm); else ret = ttm_dma_tt_alloc_page_directory(ttm); @@ -224,7 +224,7 @@ int ttm_tt_swapin(struct ttm_tt *ttm) fput(swap_storage); ttm->swap_storage = NULL; - ttm->page_flags &= ~TTM_PAGE_FLAG_SWAPPED; + ttm->page_flags &= ~TTM_TT_FLAG_SWAPPED; return 0; @@ -279,7 +279,7 @@ int ttm_tt_swapout(struct ttm_device *bdev, struct ttm_tt *ttm, ttm_tt_unpopulate(bdev, ttm); ttm->swap_storage = swap_storage; - ttm->page_flags |= TTM_PAGE_FLAG_SWAPPED; + ttm->page_flags |= TTM_TT_FLAG_SWAPPED; return ttm->num_pages; @@ -300,7 +300,7 @@ int ttm_tt_populate(struct ttm_device *bdev, if (ttm_tt_is_populated(ttm)) return 0; - if (!(ttm->page_flags & TTM_PAGE_FLAG_SG)) { + if (!(ttm->page_flags & TTM_TT_FLAG_EXTERNAL)) { atomic_long_add(ttm->num_pages, &ttm_pages_allocated); if (bdev->pool.use_dma32) atomic_long_add(ttm->num_pages, @@ -325,8 +325,8 @@ int ttm_tt_populate(struct ttm_device *bdev, if (ret) goto error; - ttm->page_flags |= TTM_PAGE_FLAG_PRIV_POPULATED; - if (unlikely(ttm->page_flags & TTM_PAGE_FLAG_SWAPPED)) { + ttm->page_flags |= TTM_TT_FLAG_PRIV_POPULATED; + if (unlikely(ttm->page_flags & TTM_TT_FLAG_SWAPPED)) { ret = ttm_tt_swapin(ttm); if (unlikely(ret != 0)) { ttm_tt_unpopulate(bdev, ttm); @@ -337,7 +337,7 @@ int ttm_tt_populate(struct ttm_device *bdev, return 0; error: - if (!(ttm->page_flags & TTM_PAGE_FLAG_SG)) { + if (!(ttm->page_flags & TTM_TT_FLAG_EXTERNAL)) { atomic_long_sub(ttm->num_pages, &ttm_pages_allocated); if (bdev->pool.use_dma32) atomic_long_sub(ttm->num_pages, @@ -357,14 +357,14 @@ void ttm_tt_unpopulate(struct ttm_device *bdev, struct ttm_tt *ttm) else ttm_pool_free(&bdev->pool, ttm); - if (!(ttm->page_flags & TTM_PAGE_FLAG_SG)) { + if (!(ttm->page_flags & TTM_TT_FLAG_EXTERNAL)) { atomic_long_sub(ttm->num_pages, &ttm_pages_allocated); if (bdev->pool.use_dma32) atomic_long_sub(ttm->num_pages, &ttm_dma32_pages_allocated); } - ttm->page_flags &= ~TTM_PAGE_FLAG_PRIV_POPULATED; + ttm->page_flags &= ~TTM_TT_FLAG_PRIV_POPULATED; } #ifdef CONFIG_DEBUG_FS diff --git a/include/drm/ttm/ttm_device.h b/include/drm/ttm/ttm_device.h index cbe03d45e883..0a4ddec78d8f 100644 --- a/include/drm/ttm/ttm_device.h +++ b/include/drm/ttm/ttm_device.h @@ -65,7 +65,7 @@ struct ttm_device_funcs { * ttm_tt_create * * @bo: The buffer object to create the ttm for. - * @page_flags: Page flags as identified by TTM_PAGE_FLAG_XX flags. + * @page_flags: Page flags as identified by TTM_TT_FLAG_XX flags. * * Create a struct ttm_tt to back data with system memory pages. * No pages are actually allocated. diff --git a/include/drm/ttm/ttm_tt.h b/include/drm/ttm/ttm_tt.h index 842ce756213c..b023cd58ff38 100644 --- a/include/drm/ttm/ttm_tt.h +++ b/include/drm/ttm/ttm_tt.h @@ -38,17 +38,17 @@ struct ttm_resource; struct ttm_buffer_object; struct ttm_operation_ctx; -#define TTM_PAGE_FLAG_SWAPPED (1 << 4) -#define TTM_PAGE_FLAG_ZERO_ALLOC (1 << 6) -#define TTM_PAGE_FLAG_SG (1 << 8) +#define TTM_TT_FLAG_SWAPPED (1 << 0) +#define TTM_TT_FLAG_ZERO_ALLOC (1 << 1) +#define TTM_TT_FLAG_EXTERNAL (1 << 2) -#define TTM_PAGE_FLAG_PRIV_POPULATED (1 << 31) +#define TTM_TT_FLAG_PRIV_POPULATED (1 << 31) /** * struct ttm_tt * * @pages: Array of pages backing the data. - * @page_flags: see TTM_PAGE_FLAG_* + * @page_flags: see TTM_TT_FLAG_* * @num_pages: Number of pages in the page array. * @sg: for SG objects via dma-buf * @dma_address: The DMA (bus) addresses of the pages @@ -84,7 +84,7 @@ struct ttm_kmap_iter_tt { static inline bool ttm_tt_is_populated(struct ttm_tt *tt) { - return tt->page_flags & TTM_PAGE_FLAG_PRIV_POPULATED; + return tt->page_flags & TTM_TT_FLAG_PRIV_POPULATED; } /** @@ -103,7 +103,7 @@ int ttm_tt_create(struct ttm_buffer_object *bo, bool zero_alloc); * * @ttm: The struct ttm_tt. * @bo: The buffer object we create the ttm for. - * @page_flags: Page flags as identified by TTM_PAGE_FLAG_XX flags. + * @page_flags: Page flags as identified by TTM_TT_FLAG_XX flags. * @caching: the desired caching state of the pages * * Create a struct ttm_tt to back data with system memory pages. @@ -178,7 +178,7 @@ void ttm_tt_unpopulate(struct ttm_device *bdev, struct ttm_tt *ttm); */ static inline void ttm_tt_mark_for_clear(struct ttm_tt *ttm) { - ttm->page_flags |= TTM_PAGE_FLAG_ZERO_ALLOC; + ttm->page_flags |= TTM_TT_FLAG_ZERO_ALLOC; } void ttm_tt_mgr_init(unsigned long num_pages, unsigned long num_dma32_pages); @@ -194,7 +194,7 @@ struct ttm_kmap_iter *ttm_kmap_iter_tt_init(struct ttm_kmap_iter_tt *iter_tt, * * @bo: Buffer object we allocate the ttm for. * @bridge: The agp bridge this device is sitting on. - * @page_flags: Page flags as identified by TTM_PAGE_FLAG_XX flags. + * @page_flags: Page flags as identified by TTM_TT_FLAG_XX flags. * * * Create a TTM backend that uses the indicated AGP bridge as an aperture -- cgit v1.2.3 From a5a3dd42fe1314a77972d8682156078de3d0410d Mon Sep 17 00:00:00 2001 From: Matthew Auld Date: Wed, 29 Sep 2021 14:26:28 +0100 Subject: drm/ttm: add some kernel-doc for TTM_TT_FLAG_* MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Move it to inline kernel-doc, otherwise we can't add empty lines it seems. Also drop the kernel-doc for pages_list, which doesn't seem to exist. v2(Christian): - Add a note that FLAG_SWAPPED shouldn't need to be touched by drivers. - Mention what FLAG_POPULATED does. Signed-off-by: Matthew Auld Cc: Thomas Hellström Cc: Christian König Reviewed-by: Christian König Link: https://patchwork.freedesktop.org/patch/msgid/20210929132629.353541-2-matthew.auld@intel.com Signed-off-by: Christian König --- include/drm/ttm/ttm_tt.h | 60 +++++++++++++++++++++++++++++++++--------------- 1 file changed, 41 insertions(+), 19 deletions(-) (limited to 'include') diff --git a/include/drm/ttm/ttm_tt.h b/include/drm/ttm/ttm_tt.h index b023cd58ff38..86d74069be3e 100644 --- a/include/drm/ttm/ttm_tt.h +++ b/include/drm/ttm/ttm_tt.h @@ -38,35 +38,57 @@ struct ttm_resource; struct ttm_buffer_object; struct ttm_operation_ctx; -#define TTM_TT_FLAG_SWAPPED (1 << 0) -#define TTM_TT_FLAG_ZERO_ALLOC (1 << 1) -#define TTM_TT_FLAG_EXTERNAL (1 << 2) - -#define TTM_TT_FLAG_PRIV_POPULATED (1 << 31) - /** - * struct ttm_tt - * - * @pages: Array of pages backing the data. - * @page_flags: see TTM_TT_FLAG_* - * @num_pages: Number of pages in the page array. - * @sg: for SG objects via dma-buf - * @dma_address: The DMA (bus) addresses of the pages - * @swap_storage: Pointer to shmem struct file for swap storage. - * @pages_list: used by some page allocation backend - * @caching: The current caching state of the pages, see enum ttm_caching. - * - * This is a structure holding the pages, caching- and aperture binding - * status for a buffer object that isn't backed by fixed (VRAM / AGP) + * struct ttm_tt - This is a structure holding the pages, caching- and aperture + * binding status for a buffer object that isn't backed by fixed (VRAM / AGP) * memory. */ struct ttm_tt { + /** @pages: Array of pages backing the data. */ struct page **pages; + /** + * @page_flags: The page flags. + * + * Supported values: + * + * TTM_TT_FLAG_SWAPPED: Set by TTM when the pages have been unpopulated + * and swapped out by TTM. Calling ttm_tt_populate() will then swap the + * pages back in, and unset the flag. Drivers should in general never + * need to touch this. + * + * TTM_TT_FLAG_ZERO_ALLOC: Set if the pages will be zeroed on + * allocation. + * + * TTM_TT_FLAG_EXTERNAL: Set if the underlying pages were allocated + * externally, like with dma-buf or userptr. This effectively disables + * TTM swapping out such pages. Also important is to prevent TTM from + * ever directly mapping these pages. + * + * Note that enum ttm_bo_type.ttm_bo_type_sg objects will always enable + * this flag. + * + * TTM_TT_FLAG_PRIV_POPULATED: TTM internal only. DO NOT USE. This is + * set by TTM after ttm_tt_populate() has successfully returned, and is + * then unset when TTM calls ttm_tt_unpopulate(). + */ +#define TTM_TT_FLAG_SWAPPED (1 << 0) +#define TTM_TT_FLAG_ZERO_ALLOC (1 << 1) +#define TTM_TT_FLAG_EXTERNAL (1 << 2) + +#define TTM_TT_FLAG_PRIV_POPULATED (1 << 31) uint32_t page_flags; + /** @num_pages: Number of pages in the page array. */ uint32_t num_pages; + /** @sg: for SG objects via dma-buf. */ struct sg_table *sg; + /** @dma_address: The DMA (bus) addresses of the pages. */ dma_addr_t *dma_address; + /** @swap_storage: Pointer to shmem struct file for swap storage. */ struct file *swap_storage; + /** + * @caching: The current caching state of the pages, see enum + * ttm_caching. + */ enum ttm_caching caching; }; -- cgit v1.2.3 From 49e7f76fc514cecf2cad1303fa74d99be7e5d9a6 Mon Sep 17 00:00:00 2001 From: Matthew Auld Date: Wed, 29 Sep 2021 14:26:29 +0100 Subject: drm/ttm: add TTM_TT_FLAG_EXTERNAL_MAPPABLE MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In commit: commit 667a50db0477d47fdff01c666f5ee1ce26b5264c Author: Thomas Hellstrom Date: Fri Jan 3 11:17:18 2014 +0100 drm/ttm: Refuse to fault (prime-) imported pages we introduced the restriction that imported pages should not be directly mappable through TTM(this also extends to userptr). In the next patch we want to introduce a shmem_tt backend, which should follow all the existing rules with TTM_PAGE_FLAG_EXTERNAL, since it will need to handle swapping itself, but with the above mapping restriction lifted. v2(Christian): - Don't OR together EXTERNAL and EXTERNAL_MAPPABLE in the definition of EXTERNAL_MAPPABLE, just leave it the caller to handle this correctly, otherwise we might encounter subtle issues. Signed-off-by: Matthew Auld Cc: Thomas Hellström Cc: Christian König Link: https://patchwork.freedesktop.org/patch/msgid/20210929132629.353541-3-matthew.auld@intel.com Signed-off-by: Christian König --- drivers/gpu/drm/ttm/ttm_bo_vm.c | 6 ++++-- drivers/gpu/drm/ttm/ttm_tt.c | 3 +++ include/drm/ttm/ttm_tt.h | 19 ++++++++++++++++--- 3 files changed, 23 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c index 950f4f132802..33680c94127c 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_vm.c +++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c @@ -163,8 +163,10 @@ vm_fault_t ttm_bo_vm_reserve(struct ttm_buffer_object *bo, * (if at all) by redirecting mmap to the exporter. */ if (bo->ttm && (bo->ttm->page_flags & TTM_TT_FLAG_EXTERNAL)) { - dma_resv_unlock(bo->base.resv); - return VM_FAULT_SIGBUS; + if (!(bo->ttm->page_flags & TTM_TT_FLAG_EXTERNAL_MAPPABLE)) { + dma_resv_unlock(bo->base.resv); + return VM_FAULT_SIGBUS; + } } return 0; diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c index 86f31fde6e35..7e83c00a3f48 100644 --- a/drivers/gpu/drm/ttm/ttm_tt.c +++ b/drivers/gpu/drm/ttm/ttm_tt.c @@ -84,6 +84,9 @@ int ttm_tt_create(struct ttm_buffer_object *bo, bool zero_alloc) if (unlikely(bo->ttm == NULL)) return -ENOMEM; + WARN_ON(bo->ttm->page_flags & TTM_TT_FLAG_EXTERNAL_MAPPABLE && + !(bo->ttm->page_flags & TTM_TT_FLAG_EXTERNAL)); + return 0; } diff --git a/include/drm/ttm/ttm_tt.h b/include/drm/ttm/ttm_tt.h index 86d74069be3e..f20832139815 100644 --- a/include/drm/ttm/ttm_tt.h +++ b/include/drm/ttm/ttm_tt.h @@ -67,13 +67,26 @@ struct ttm_tt { * Note that enum ttm_bo_type.ttm_bo_type_sg objects will always enable * this flag. * + * TTM_TT_FLAG_EXTERNAL_MAPPABLE: Same behaviour as + * TTM_TT_FLAG_EXTERNAL, but with the reduced restriction that it is + * still valid to use TTM to map the pages directly. This is useful when + * implementing a ttm_tt backend which still allocates driver owned + * pages underneath(say with shmem). + * + * Note that since this also implies TTM_TT_FLAG_EXTERNAL, the usage + * here should always be: + * + * page_flags = TTM_TT_FLAG_EXTERNAL | + * TTM_TT_FLAG_EXTERNAL_MAPPABLE; + * * TTM_TT_FLAG_PRIV_POPULATED: TTM internal only. DO NOT USE. This is * set by TTM after ttm_tt_populate() has successfully returned, and is * then unset when TTM calls ttm_tt_unpopulate(). */ -#define TTM_TT_FLAG_SWAPPED (1 << 0) -#define TTM_TT_FLAG_ZERO_ALLOC (1 << 1) -#define TTM_TT_FLAG_EXTERNAL (1 << 2) +#define TTM_TT_FLAG_SWAPPED (1 << 0) +#define TTM_TT_FLAG_ZERO_ALLOC (1 << 1) +#define TTM_TT_FLAG_EXTERNAL (1 << 2) +#define TTM_TT_FLAG_EXTERNAL_MAPPABLE (1 << 3) #define TTM_TT_FLAG_PRIV_POPULATED (1 << 31) uint32_t page_flags; -- cgit v1.2.3 From 59050d783848d9b62e9d8fb6ce0cd00771c2bf87 Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Tue, 28 Sep 2021 20:13:33 +0200 Subject: drm/bridge: Add stubs for devm_drm_of_get_bridge when OF is disabled If CONFIG_OF is disabled, devm_drm_of_get_bridge won't be compiled in and drivers using that function will fail to build. Add an inline stub so that we can still build-test those cases. Reported-by: Randy Dunlap Signed-off-by: Maxime Ripard Acked-by: Randy Dunlap # build-tested Link: https://patchwork.freedesktop.org/patch/msgid/20210928181333.1176840-1-maxime@cerno.tech --- include/drm/drm_bridge.h | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/drm/drm_bridge.h b/include/drm/drm_bridge.h index a445298e1c25..061d87313fac 100644 --- a/include/drm/drm_bridge.h +++ b/include/drm/drm_bridge.h @@ -919,9 +919,20 @@ struct drm_bridge *devm_drm_panel_bridge_add(struct device *dev, struct drm_bridge *devm_drm_panel_bridge_add_typed(struct device *dev, struct drm_panel *panel, u32 connector_type); +struct drm_connector *drm_panel_bridge_connector(struct drm_bridge *bridge); +#endif + +#if defined(CONFIG_OF) && defined(CONFIG_DRM_PANEL_BRIDGE) struct drm_bridge *devm_drm_of_get_bridge(struct device *dev, struct device_node *node, u32 port, u32 endpoint); -struct drm_connector *drm_panel_bridge_connector(struct drm_bridge *bridge); +#else +static inline struct drm_bridge *devm_drm_of_get_bridge(struct device *dev, + struct device_node *node, + u32 port, + u32 endpoint) +{ + return ERR_PTR(-ENODEV); +} #endif #endif -- cgit v1.2.3 From 241ffeb028e4b1181c0e51e00e553390b42fb1e8 Mon Sep 17 00:00:00 2001 From: Fangzhi Zuo Date: Mon, 27 Sep 2021 15:23:24 -0400 Subject: drm/dp: Add Additional DP2 Headers Include FEC, DSC, Link Training related headers. Change since v2 - Align with the spec for DP_DSC_SUPPORT_AND_DSC_DECODER_COUNT Signed-off-by: Fangzhi Zuo Reviewed-by: Harry Wentland Signed-off-by: Rodrigo Siqueira Link: https://patchwork.freedesktop.org/patch/msgid/20210927192324.5428-1-Jerry.Zuo@amd.com --- include/drm/drm_dp_helper.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include') diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h index 1d5b3dbb6e56..a1df35aa6e68 100644 --- a/include/drm/drm_dp_helper.h +++ b/include/drm/drm_dp_helper.h @@ -453,6 +453,7 @@ struct drm_panel; # define DP_FEC_UNCORR_BLK_ERROR_COUNT_CAP (1 << 1) # define DP_FEC_CORR_BLK_ERROR_COUNT_CAP (1 << 2) # define DP_FEC_BIT_ERROR_COUNT_CAP (1 << 3) +#define DP_FEC_CAPABILITY_1 0x091 /* 2.0 */ /* DP-HDMI2.1 PCON DSC ENCODER SUPPORT */ #define DP_PCON_DSC_ENCODER_CAP_SIZE 0xC /* 0x9E - 0x92 */ @@ -537,6 +538,9 @@ struct drm_panel; #define DP_DSC_BRANCH_OVERALL_THROUGHPUT_1 0x0a1 #define DP_DSC_BRANCH_MAX_LINE_WIDTH 0x0a2 +/* DFP Capability Extension */ +#define DP_DFP_CAPABILITY_EXTENSION_SUPPORT 0x0a3 /* 2.0 */ + /* Link Configuration */ #define DP_LINK_BW_SET 0x100 # define DP_LINK_RATE_TABLE 0x00 /* eDP 1.4 */ @@ -688,6 +692,7 @@ struct drm_panel; #define DP_DSC_ENABLE 0x160 /* DP 1.4 */ # define DP_DECOMPRESSION_EN (1 << 0) +#define DP_DSC_CONFIGURATION 0x161 /* DP 2.0 */ #define DP_PSR_EN_CFG 0x170 /* XXX 1.2? */ # define DP_PSR_ENABLE BIT(0) @@ -743,6 +748,7 @@ struct drm_panel; # define DP_RECEIVE_PORT_0_STATUS (1 << 0) # define DP_RECEIVE_PORT_1_STATUS (1 << 1) # define DP_STREAM_REGENERATION_STATUS (1 << 2) /* 2.0 */ +# define DP_INTRA_HOP_AUX_REPLY_INDICATION (1 << 3) /* 2.0 */ #define DP_ADJUST_REQUEST_LANE0_1 0x206 #define DP_ADJUST_REQUEST_LANE2_3 0x207 @@ -865,6 +871,8 @@ struct drm_panel; # define DP_PHY_TEST_PATTERN_80BIT_CUSTOM 0x4 # define DP_PHY_TEST_PATTERN_CP2520 0x5 +#define DP_PHY_SQUARE_PATTERN 0x249 + #define DP_TEST_HBR2_SCRAMBLER_RESET 0x24A #define DP_TEST_80BIT_CUSTOM_PATTERN_7_0 0x250 #define DP_TEST_80BIT_CUSTOM_PATTERN_15_8 0x251 @@ -1109,6 +1117,18 @@ struct drm_panel; #define DP_128B132B_TRAINING_AUX_RD_INTERVAL 0x2216 /* 2.0 */ # define DP_128B132B_TRAINING_AUX_RD_INTERVAL_MASK 0x7f +#define DP_TEST_264BIT_CUSTOM_PATTERN_7_0 0x2230 +#define DP_TEST_264BIT_CUSTOM_PATTERN_263_256 0x2250 + +/* DSC Extended Capability Branch Total DSC Resources */ +#define DP_DSC_SUPPORT_AND_DSC_DECODER_COUNT 0x2260 /* 2.0 */ +# define DP_DSC_DECODER_COUNT_MASK (0b111 << 5) +# define DP_DSC_DECODER_COUNT_SHIFT 5 +#define DP_DSC_MAX_SLICE_COUNT_AND_AGGREGATION_0 0x2270 /* 2.0 */ +# define DP_DSC_DECODER_0_MAXIMUM_SLICE_COUNT_MASK (1 << 0) +# define DP_DSC_DECODER_0_AGGREGATION_SUPPORT_MASK (0b111 << 1) +# define DP_DSC_DECODER_0_AGGREGATION_SUPPORT_SHIFT 1 + /* Protocol Converter Extension */ /* HDMI CEC tunneling over AUX DP 1.3 section 5.3.3.3.1 DPCD 1.4+ */ #define DP_CEC_TUNNELING_CAPABILITY 0x3000 -- cgit v1.2.3 From 6b51b02a3a0ac49dfe302818d0746a799545e4e9 Mon Sep 17 00:00:00 2001 From: Christian König Date: Tue, 15 Jun 2021 13:12:33 +0200 Subject: dma-buf: fix and rework dma_buf_poll v7 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Daniel pointed me towards this function and there are multiple obvious problems in the implementation. First of all the retry loop is not working as intended. In general the retry makes only sense if you grab the reference first and then check the sequence values. Then we should always also wait for the exclusive fence. It's also good practice to keep the reference around when installing callbacks to fences you don't own. And last the whole implementation was unnecessary complex and rather hard to understand which could lead to probably unexpected behavior of the IOCTL. Fix all this by reworking the implementation from scratch. Dropping the whole RCU approach and taking the lock instead. Only mildly tested and needs a thoughtful review of the code. Pushing through drm-misc-next to avoid merge conflicts and give the code another round of testing. v2: fix the reference counting as well v3: keep the excl fence handling as is for stable v4: back to testing all fences, drop RCU v5: handle in and out separately v6: add missing clear of events v7: change coding style as suggested by Michel, drop unused variables Signed-off-by: Christian König Reviewed-by: Daniel Vetter Tested-by: Michel Dänzer CC: stable@vger.kernel.org Link: https://patchwork.freedesktop.org/patch/msgid/20210720131110.88512-1-christian.koenig@amd.com --- drivers/dma-buf/dma-buf.c | 152 +++++++++++++++++++++------------------------- include/linux/dma-buf.h | 2 +- 2 files changed, 71 insertions(+), 83 deletions(-) (limited to 'include') diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index 474de2d988ca..61e20ae7b08b 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -74,7 +74,7 @@ static void dma_buf_release(struct dentry *dentry) * If you hit this BUG() it means someone dropped their ref to the * dma-buf while still having pending operation to the buffer. */ - BUG_ON(dmabuf->cb_shared.active || dmabuf->cb_excl.active); + BUG_ON(dmabuf->cb_in.active || dmabuf->cb_out.active); dma_buf_stats_teardown(dmabuf); dmabuf->ops->release(dmabuf); @@ -206,16 +206,55 @@ static void dma_buf_poll_cb(struct dma_fence *fence, struct dma_fence_cb *cb) wake_up_locked_poll(dcb->poll, dcb->active); dcb->active = 0; spin_unlock_irqrestore(&dcb->poll->lock, flags); + dma_fence_put(fence); +} + +static bool dma_buf_poll_shared(struct dma_resv *resv, + struct dma_buf_poll_cb_t *dcb) +{ + struct dma_resv_list *fobj = dma_resv_shared_list(resv); + struct dma_fence *fence; + int i, r; + + if (!fobj) + return false; + + for (i = 0; i < fobj->shared_count; ++i) { + fence = rcu_dereference_protected(fobj->shared[i], + dma_resv_held(resv)); + dma_fence_get(fence); + r = dma_fence_add_callback(fence, &dcb->cb, dma_buf_poll_cb); + if (!r) + return true; + dma_fence_put(fence); + } + + return false; +} + +static bool dma_buf_poll_excl(struct dma_resv *resv, + struct dma_buf_poll_cb_t *dcb) +{ + struct dma_fence *fence = dma_resv_excl_fence(resv); + int r; + + if (!fence) + return false; + + dma_fence_get(fence); + r = dma_fence_add_callback(fence, &dcb->cb, dma_buf_poll_cb); + if (!r) + return true; + dma_fence_put(fence); + + return false; } static __poll_t dma_buf_poll(struct file *file, poll_table *poll) { struct dma_buf *dmabuf; struct dma_resv *resv; - struct dma_resv_list *fobj; - struct dma_fence *fence_excl; __poll_t events; - unsigned shared_count, seq; dmabuf = file->private_data; if (!dmabuf || !dmabuf->resv) @@ -229,101 +268,50 @@ static __poll_t dma_buf_poll(struct file *file, poll_table *poll) if (!events) return 0; -retry: - seq = read_seqcount_begin(&resv->seq); - rcu_read_lock(); - - fobj = rcu_dereference(resv->fence); - if (fobj) - shared_count = fobj->shared_count; - else - shared_count = 0; - fence_excl = dma_resv_excl_fence(resv); - if (read_seqcount_retry(&resv->seq, seq)) { - rcu_read_unlock(); - goto retry; - } - - if (fence_excl && (!(events & EPOLLOUT) || shared_count == 0)) { - struct dma_buf_poll_cb_t *dcb = &dmabuf->cb_excl; - __poll_t pevents = EPOLLIN; + dma_resv_lock(resv, NULL); - if (shared_count == 0) - pevents |= EPOLLOUT; + if (events & EPOLLOUT) { + struct dma_buf_poll_cb_t *dcb = &dmabuf->cb_out; + /* Check that callback isn't busy */ spin_lock_irq(&dmabuf->poll.lock); - if (dcb->active) { - dcb->active |= pevents; - events &= ~pevents; - } else - dcb->active = pevents; + if (dcb->active) + events &= ~EPOLLOUT; + else + dcb->active = EPOLLOUT; spin_unlock_irq(&dmabuf->poll.lock); - if (events & pevents) { - if (!dma_fence_get_rcu(fence_excl)) { - /* force a recheck */ - events &= ~pevents; - dma_buf_poll_cb(NULL, &dcb->cb); - } else if (!dma_fence_add_callback(fence_excl, &dcb->cb, - dma_buf_poll_cb)) { - events &= ~pevents; - dma_fence_put(fence_excl); - } else { - /* - * No callback queued, wake up any additional - * waiters. - */ - dma_fence_put(fence_excl); + if (events & EPOLLOUT) { + if (!dma_buf_poll_shared(resv, dcb) && + !dma_buf_poll_excl(resv, dcb)) + /* No callback queued, wake up any other waiters */ dma_buf_poll_cb(NULL, &dcb->cb); - } + else + events &= ~EPOLLOUT; } } - if ((events & EPOLLOUT) && shared_count > 0) { - struct dma_buf_poll_cb_t *dcb = &dmabuf->cb_shared; - int i; + if (events & EPOLLIN) { + struct dma_buf_poll_cb_t *dcb = &dmabuf->cb_in; - /* Only queue a new callback if no event has fired yet */ + /* Check that callback isn't busy */ spin_lock_irq(&dmabuf->poll.lock); if (dcb->active) - events &= ~EPOLLOUT; + events &= ~EPOLLIN; else - dcb->active = EPOLLOUT; + dcb->active = EPOLLIN; spin_unlock_irq(&dmabuf->poll.lock); - if (!(events & EPOLLOUT)) - goto out; - - for (i = 0; i < shared_count; ++i) { - struct dma_fence *fence = rcu_dereference(fobj->shared[i]); - - if (!dma_fence_get_rcu(fence)) { - /* - * fence refcount dropped to zero, this means - * that fobj has been freed - * - * call dma_buf_poll_cb and force a recheck! - */ - events &= ~EPOLLOUT; + if (events & EPOLLIN) { + if (!dma_buf_poll_excl(resv, dcb)) + /* No callback queued, wake up any other waiters */ dma_buf_poll_cb(NULL, &dcb->cb); - break; - } - if (!dma_fence_add_callback(fence, &dcb->cb, - dma_buf_poll_cb)) { - dma_fence_put(fence); - events &= ~EPOLLOUT; - break; - } - dma_fence_put(fence); + else + events &= ~EPOLLIN; } - - /* No callback queued, wake up any additional waiters. */ - if (i == shared_count) - dma_buf_poll_cb(NULL, &dcb->cb); } -out: - rcu_read_unlock(); + dma_resv_unlock(resv); return events; } @@ -566,8 +554,8 @@ struct dma_buf *dma_buf_export(const struct dma_buf_export_info *exp_info) dmabuf->owner = exp_info->owner; spin_lock_init(&dmabuf->name_lock); init_waitqueue_head(&dmabuf->poll); - dmabuf->cb_excl.poll = dmabuf->cb_shared.poll = &dmabuf->poll; - dmabuf->cb_excl.active = dmabuf->cb_shared.active = 0; + dmabuf->cb_in.poll = dmabuf->cb_out.poll = &dmabuf->poll; + dmabuf->cb_in.active = dmabuf->cb_out.active = 0; if (!resv) { resv = (struct dma_resv *)&dmabuf[1]; diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index 66470c37e471..02c2eb874da6 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -440,7 +440,7 @@ struct dma_buf { wait_queue_head_t *poll; __poll_t active; - } cb_excl, cb_shared; + } cb_in, cb_out; #ifdef CONFIG_DMABUF_SYSFS_STATS /** * @sysfs_entry: -- cgit v1.2.3 From 4bb2d367a5a2807185a04949ae922d247f650576 Mon Sep 17 00:00:00 2001 From: Simon Ser Date: Fri, 3 Sep 2021 13:00:32 +0000 Subject: drm/lease: allow empty leases MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This can be used to create a separate DRM file description, thus creating a new GEM handle namespace. My use-case is wlroots. The library splits responsibilities between separate components: the GBM allocator creates buffers, the GLES2 renderer uses EGL to import them and render to them, the DRM backend imports the buffers and displays them. wlroots has a modular architecture, and any of these components can be swapped and replaced with something else. For instance, the pipeline can be set up so that the DRM dumb buffer allocator is used instead of GBM and the Pixman renderer is used instead of GLES2. Library users can also replace any of these components with their own custom one. DMA-BUFs are used to pass buffer references across components. We could use GEM handles instead, but this would result in pain if multiple GPUs are in use: wlroots copies buffers across GPUs as needed. Importing a GEM handle created on one GPU into a completely different GPU will blow up (fail at best, mix unrelated buffers otherwise). Everything is fine if all components use Mesa. However, this isn't always desirable. For instance when running with DRM dumb buffers and the Pixman software renderer it's unfortunate to depend on GBM in the DRM backend just to turn DMA-BUFs into FB IDs. GBM loads Mesa drivers to perform an action which has nothing driver-specific. Additionally, drivers will fail the import if the 3D engine can't use the imported buffer, for instance amdgpu will refuse to import DRM dumb buffers [1]. We might also want to be running with a Vulkan renderer and a Vulkan allocator in the future, and GBM wouldn't be welcome in this setup. To address this, GBM can be side-stepped in the DRM backend, and can be replaced with drmPrimeFDToHandle calls. However because of GEM handle reference counting issues, care must be taken to avoid double-closing the same GEM handle. In particular, it's not possible to share a DRM FD with GBM or EGL and perform some drmPrimeFDToHandle calls manually. So wlroots needs to re-open the DRM FD to create a new GEM handle namespace. However there's no guarantee that the file-system permissions will be set up so that the primary FD can be opened by the compsoitor. On modern systems seatd or logind is a privileged process responsible for doing this, and other processes aren't expected to do it. For historical reasons systemd still allows physically logged in users to open primary DRM nodes, but this doesn't work on non-systemd setups and it's desirable to lock them down at some point. Some might suggest to open the render node instead of re-opening the primary node. However some systems don't have a render node at all (e.g. no GPU, or a split render/display SoC). Solutions to this issue have been discussed in [2]. One solution would be to open the magic /proc/self/fd/ file, but it's a Linux-specific hack (wlroots supports BSDs too). Another solution is to add support for re-opening a DRM primary node to seatd/logind, but they don't support it now and really haven't been designed for this (logind would need to grow a completely new API, because it assumes unique dev_t IDs). Also this seems like pushing down a kernel limitation to user-space a bit too hard. Another solution is to allow creating empty DRM leases. The lessee FD would have its own GEM handle namespace, so wouldn't conflict wth GBM/EGL. It would have the master bit set, but would be able to manage zero resources. wlroots doesn't intend to share this FD with any other process. All in all IMHO that seems like a pretty reasonable solution to the issue at hand. Note, I've discussed with Jonas Ådahl and Mutter plans to adopt a similar design in the future. Example usage in wlroots is available at [3]. IGT test available at [4]. [1]: https://github.com/swaywm/wlroots/issues/2916 [2]: https://gitlab.freedesktop.org/mesa/drm/-/merge_requests/110 [3]: https://github.com/swaywm/wlroots/pull/3158 [4]: https://patchwork.freedesktop.org/series/94323/ Signed-off-by: Simon Ser Cc: Daniel Vetter Cc: Daniel Stone Cc: Pekka Paalanen Cc: Michel Dänzer Cc: Emil Velikov Cc: Keith Packard Cc: Boris Brezillon Cc: Dave Airlie Acked-by: Pekka Paalanen Reviewed-by: Daniel Stone Link: https://patchwork.freedesktop.org/patch/msgid/20210903130000.1590-2-contact@emersion.fr --- drivers/gpu/drm/drm_lease.c | 39 ++++++++++++++++++--------------------- include/uapi/drm/drm_mode.h | 3 ++- 2 files changed, 20 insertions(+), 22 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/drm_lease.c b/drivers/gpu/drm/drm_lease.c index dee4f24a1808..d72c2fac0ff1 100644 --- a/drivers/gpu/drm/drm_lease.c +++ b/drivers/gpu/drm/drm_lease.c @@ -489,12 +489,6 @@ int drm_mode_create_lease_ioctl(struct drm_device *dev, if (!drm_core_check_feature(dev, DRIVER_MODESET)) return -EOPNOTSUPP; - /* need some objects */ - if (cl->object_count == 0) { - DRM_DEBUG_LEASE("no objects in lease\n"); - return -EINVAL; - } - if (cl->flags && (cl->flags & ~(O_CLOEXEC | O_NONBLOCK))) { DRM_DEBUG_LEASE("invalid flags\n"); return -EINVAL; @@ -510,23 +504,26 @@ int drm_mode_create_lease_ioctl(struct drm_device *dev, object_count = cl->object_count; - object_ids = memdup_user(u64_to_user_ptr(cl->object_ids), - array_size(object_count, sizeof(__u32))); - if (IS_ERR(object_ids)) { - ret = PTR_ERR(object_ids); - goto out_lessor; - } - + /* Handle leased objects, if any */ idr_init(&leases); + if (object_count != 0) { + object_ids = memdup_user(u64_to_user_ptr(cl->object_ids), + array_size(object_count, sizeof(__u32))); + if (IS_ERR(object_ids)) { + ret = PTR_ERR(object_ids); + idr_destroy(&leases); + goto out_lessor; + } - /* fill and validate the object idr */ - ret = fill_object_idr(dev, lessor_priv, &leases, - object_count, object_ids); - kfree(object_ids); - if (ret) { - DRM_DEBUG_LEASE("lease object lookup failed: %i\n", ret); - idr_destroy(&leases); - goto out_lessor; + /* fill and validate the object idr */ + ret = fill_object_idr(dev, lessor_priv, &leases, + object_count, object_ids); + kfree(object_ids); + if (ret) { + DRM_DEBUG_LEASE("lease object lookup failed: %i\n", ret); + idr_destroy(&leases); + goto out_lessor; + } } /* Allocate a file descriptor for the lease */ diff --git a/include/uapi/drm/drm_mode.h b/include/uapi/drm/drm_mode.h index e4a2570a6058..e1e351682872 100644 --- a/include/uapi/drm/drm_mode.h +++ b/include/uapi/drm/drm_mode.h @@ -1112,7 +1112,8 @@ struct drm_mode_destroy_blob { * Lease mode resources, creating another drm_master. * * The @object_ids array must reference at least one CRTC, one connector and - * one plane if &DRM_CLIENT_CAP_UNIVERSAL_PLANES is enabled. + * one plane if &DRM_CLIENT_CAP_UNIVERSAL_PLANES is enabled. Alternatively, + * the lease can be completely empty. */ struct drm_mode_create_lease { /** @object_ids: Pointer to array of object ids (__u32) */ -- cgit v1.2.3 From 8d813d1a535c8c7503a5f4061654a73026be8c5e Mon Sep 17 00:00:00 2001 From: Fernando Ramos Date: Fri, 24 Sep 2021 08:43:23 +0200 Subject: drm: cleanup: remove drm_modeset_(un)lock_all() Functions drm_modeset_lock_all() and drm_modeset_unlock_all() are no longer used anywhere and can be removed. Signed-off-by: Fernando Ramos Signed-off-by: Sean Paul Link: https://patchwork.freedesktop.org/patch/msgid/20210924064324.229457-17-greenfoo@u92.eu --- drivers/gpu/drm/drm_modeset_lock.c | 94 ++------------------------------------ include/drm/drm_modeset_lock.h | 2 - 2 files changed, 3 insertions(+), 93 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/drm_modeset_lock.c b/drivers/gpu/drm/drm_modeset_lock.c index fcfe1a03c4a1..afd1351749a5 100644 --- a/drivers/gpu/drm/drm_modeset_lock.c +++ b/drivers/gpu/drm/drm_modeset_lock.c @@ -77,93 +77,6 @@ static DEFINE_WW_CLASS(crtc_ww_class); -/** - * drm_modeset_lock_all - take all modeset locks - * @dev: DRM device - * - * This function takes all modeset locks, suitable where a more fine-grained - * scheme isn't (yet) implemented. Locks must be dropped by calling the - * drm_modeset_unlock_all() function. - * - * This function is deprecated. It allocates a lock acquisition context and - * stores it in &drm_device.mode_config. This facilitate conversion of - * existing code because it removes the need to manually deal with the - * acquisition context, but it is also brittle because the context is global - * and care must be taken not to nest calls. New code should use the - * drm_modeset_lock_all_ctx() function and pass in the context explicitly. - */ -void drm_modeset_lock_all(struct drm_device *dev) -{ - struct drm_mode_config *config = &dev->mode_config; - struct drm_modeset_acquire_ctx *ctx; - int ret; - - ctx = kzalloc(sizeof(*ctx), GFP_KERNEL | __GFP_NOFAIL); - if (WARN_ON(!ctx)) - return; - - mutex_lock(&config->mutex); - - drm_modeset_acquire_init(ctx, 0); - -retry: - ret = drm_modeset_lock_all_ctx(dev, ctx); - if (ret < 0) { - if (ret == -EDEADLK) { - drm_modeset_backoff(ctx); - goto retry; - } - - drm_modeset_acquire_fini(ctx); - kfree(ctx); - return; - } - ww_acquire_done(&ctx->ww_ctx); - - WARN_ON(config->acquire_ctx); - - /* - * We hold the locks now, so it is safe to stash the acquisition - * context for drm_modeset_unlock_all(). - */ - config->acquire_ctx = ctx; - - drm_warn_on_modeset_not_all_locked(dev); -} -EXPORT_SYMBOL(drm_modeset_lock_all); - -/** - * drm_modeset_unlock_all - drop all modeset locks - * @dev: DRM device - * - * This function drops all modeset locks taken by a previous call to the - * drm_modeset_lock_all() function. - * - * This function is deprecated. It uses the lock acquisition context stored - * in &drm_device.mode_config. This facilitates conversion of existing - * code because it removes the need to manually deal with the acquisition - * context, but it is also brittle because the context is global and care must - * be taken not to nest calls. New code should pass the acquisition context - * directly to the drm_modeset_drop_locks() function. - */ -void drm_modeset_unlock_all(struct drm_device *dev) -{ - struct drm_mode_config *config = &dev->mode_config; - struct drm_modeset_acquire_ctx *ctx = config->acquire_ctx; - - if (WARN_ON(!ctx)) - return; - - config->acquire_ctx = NULL; - drm_modeset_drop_locks(ctx); - drm_modeset_acquire_fini(ctx); - - kfree(ctx); - - mutex_unlock(&dev->mode_config.mutex); -} -EXPORT_SYMBOL(drm_modeset_unlock_all); - /** * drm_warn_on_modeset_not_all_locked - check that all modeset locks are locked * @dev: device @@ -380,10 +293,9 @@ EXPORT_SYMBOL(drm_modeset_unlock); * This function takes all modeset locks, suitable where a more fine-grained * scheme isn't (yet) implemented. * - * Unlike drm_modeset_lock_all(), it doesn't take the &drm_mode_config.mutex - * since that lock isn't required for modeset state changes. Callers which - * need to grab that lock too need to do so outside of the acquire context - * @ctx. + * It doesn't take the &drm_mode_config.mutex since that lock isn't required for + * modeset state changes. Callers which need to grab that lock too need to do so + * outside of the acquire context @ctx. * * Locks acquired with this function should be released by calling the * drm_modeset_drop_locks() function on @ctx. diff --git a/include/drm/drm_modeset_lock.h b/include/drm/drm_modeset_lock.h index aafd07388eb7..865e64bcc4cb 100644 --- a/include/drm/drm_modeset_lock.h +++ b/include/drm/drm_modeset_lock.h @@ -132,8 +132,6 @@ struct drm_device; struct drm_crtc; struct drm_plane; -void drm_modeset_lock_all(struct drm_device *dev); -void drm_modeset_unlock_all(struct drm_device *dev); void drm_warn_on_modeset_not_all_locked(struct drm_device *dev); int drm_modeset_lock_all_ctx(struct drm_device *dev, -- cgit v1.2.3 From bb3425efdcd99f2b4e608e850226f7107b2f993e Mon Sep 17 00:00:00 2001 From: Melissa Wen Date: Thu, 30 Sep 2021 17:18:50 +0100 Subject: drm/v3d: add generic ioctl extension Add support to attach generic extensions on job submission. This patch is third prep work to enable multiple syncobjs on job submission. With this work, when the job submission interface needs to be extended to accommodate a new feature, we will use a generic extension struct where an id determines the data type to be pointed. The first application is to enable multiples in/out syncobj (next patch), but the base is already done for future features. Therefore, to attach a new feature, a specific extension struct should subclass drm_v3d_extension and update the list of extensions in a job submission. v2: - remove redundant elements to subclass struct (Daniel) v3: - add comment for v3d_get_extensions Signed-off-by: Melissa Wen Reviewed-by: Iago Toral Quiroga Signed-off-by: Melissa Wen Link: https://patchwork.freedesktop.org/patch/msgid/ed53b1cd7e3125b76f18fe3fb995a04393639bc6.1633016479.git.mwen@igalia.com --- drivers/gpu/drm/v3d/v3d_drv.c | 4 +-- drivers/gpu/drm/v3d/v3d_gem.c | 74 +++++++++++++++++++++++++++++++++++++++++-- include/uapi/drm/v3d_drm.h | 31 ++++++++++++++++++ 3 files changed, 103 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/v3d/v3d_drv.c b/drivers/gpu/drm/v3d/v3d_drv.c index c1deab2cf38d..3d6b9bcce2f7 100644 --- a/drivers/gpu/drm/v3d/v3d_drv.c +++ b/drivers/gpu/drm/v3d/v3d_drv.c @@ -83,7 +83,6 @@ static int v3d_get_param_ioctl(struct drm_device *dev, void *data, return 0; } - switch (args->param) { case DRM_V3D_PARAM_SUPPORTS_TFU: args->value = 1; @@ -147,7 +146,7 @@ v3d_postclose(struct drm_device *dev, struct drm_file *file) DEFINE_DRM_GEM_FOPS(v3d_drm_fops); /* DRM_AUTH is required on SUBMIT_CL for now, while we don't have GMP - * protection between clients. Note that render nodes would be be + * protection between clients. Note that render nodes would be * able to submit CLs that could access BOs from clients authenticated * with the master node. The TFU doesn't use the GMP, so it would * need to stay DRM_AUTH until we do buffer size/offset validation. @@ -219,7 +218,6 @@ static int v3d_platform_drm_probe(struct platform_device *pdev) u32 mmu_debug; u32 ident1; - v3d = devm_drm_dev_alloc(dev, &v3d_drm_driver, struct v3d_dev, drm); if (IS_ERR(v3d)) return PTR_ERR(v3d); diff --git a/drivers/gpu/drm/v3d/v3d_gem.c b/drivers/gpu/drm/v3d/v3d_gem.c index f932e73fb5c6..93f130fb3a13 100644 --- a/drivers/gpu/drm/v3d/v3d_gem.c +++ b/drivers/gpu/drm/v3d/v3d_gem.c @@ -537,6 +537,36 @@ v3d_attach_fences_and_unlock_reservation(struct drm_file *file_priv, } } +/* Whenever userspace sets ioctl extensions, v3d_get_extensions parses data + * according to the extension id (name). + */ +static int +v3d_get_extensions(struct drm_file *file_priv, u64 ext_handles) +{ + struct drm_v3d_extension __user *user_ext; + + user_ext = u64_to_user_ptr(ext_handles); + while (user_ext) { + struct drm_v3d_extension ext; + + if (copy_from_user(&ext, user_ext, sizeof(ext))) { + DRM_DEBUG("Failed to copy submit extension\n"); + return -EFAULT; + } + + switch (ext.id) { + case 0: + default: + DRM_DEBUG_DRIVER("Unknown extension id: %d\n", ext.id); + return -EINVAL; + } + + user_ext = u64_to_user_ptr(ext.next); + } + + return 0; +} + /** * v3d_submit_cl_ioctl() - Submits a job (frame) to the V3D. * @dev: DRM device @@ -565,15 +595,24 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data, trace_v3d_submit_cl_ioctl(&v3d->drm, args->rcl_start, args->rcl_end); - if (args->pad != 0) + if (args->pad) return -EINVAL; - if (args->flags != 0 && - args->flags != DRM_V3D_SUBMIT_CL_FLUSH_CACHE) { + if (args->flags && + args->flags & ~(DRM_V3D_SUBMIT_CL_FLUSH_CACHE | + DRM_V3D_SUBMIT_EXTENSION)) { DRM_INFO("invalid flags: %d\n", args->flags); return -EINVAL; } + if (args->flags & DRM_V3D_SUBMIT_EXTENSION) { + ret = v3d_get_extensions(file_priv, args->extensions); + if (ret) { + DRM_DEBUG("Failed to get extensions.\n"); + return ret; + } + } + ret = v3d_job_init(v3d, file_priv, (void *)&render, sizeof(*render), v3d_render_job_free, args->in_sync_rcl, V3D_RENDER); if (ret) @@ -702,6 +741,19 @@ v3d_submit_tfu_ioctl(struct drm_device *dev, void *data, trace_v3d_submit_tfu_ioctl(&v3d->drm, args->iia); + if (args->flags && !(args->flags & DRM_V3D_SUBMIT_EXTENSION)) { + DRM_DEBUG("invalid flags: %d\n", args->flags); + return -EINVAL; + } + + if (args->flags & DRM_V3D_SUBMIT_EXTENSION) { + ret = v3d_get_extensions(file_priv, args->extensions); + if (ret) { + DRM_DEBUG("Failed to get extensions.\n"); + return ret; + } + } + ret = v3d_job_init(v3d, file_priv, (void *)&job, sizeof(*job), v3d_job_free, args->in_sync, V3D_TFU); if (ret) @@ -786,11 +838,27 @@ v3d_submit_csd_ioctl(struct drm_device *dev, void *data, trace_v3d_submit_csd_ioctl(&v3d->drm, args->cfg[5], args->cfg[6]); + if (args->pad) + return -EINVAL; + if (!v3d_has_csd(v3d)) { DRM_DEBUG("Attempting CSD submit on non-CSD hardware\n"); return -EINVAL; } + if (args->flags && !(args->flags & DRM_V3D_SUBMIT_EXTENSION)) { + DRM_INFO("invalid flags: %d\n", args->flags); + return -EINVAL; + } + + if (args->flags & DRM_V3D_SUBMIT_EXTENSION) { + ret = v3d_get_extensions(file_priv, args->extensions); + if (ret) { + DRM_DEBUG("Failed to get extensions.\n"); + return ret; + } + } + ret = v3d_job_init(v3d, file_priv, (void *)&job, sizeof(*job), v3d_job_free, args->in_sync, V3D_CSD); if (ret) diff --git a/include/uapi/drm/v3d_drm.h b/include/uapi/drm/v3d_drm.h index 4104f22fb3d3..55b443ca6c0b 100644 --- a/include/uapi/drm/v3d_drm.h +++ b/include/uapi/drm/v3d_drm.h @@ -58,6 +58,20 @@ extern "C" { struct drm_v3d_perfmon_get_values) #define DRM_V3D_SUBMIT_CL_FLUSH_CACHE 0x01 +#define DRM_V3D_SUBMIT_EXTENSION 0x02 + +/* struct drm_v3d_extension - ioctl extensions + * + * Linked-list of generic extensions where the id identify which struct is + * pointed by ext_data. Therefore, DRM_V3D_EXT_ID_* is used on id to identify + * the extension type. + */ +struct drm_v3d_extension { + __u64 next; + __u32 id; +#define DRM_V3D_EXT_ID_MULTI_SYNC 0x01 + __u32 flags; /* mbz */ +}; /** * struct drm_v3d_submit_cl - ioctl argument for submitting commands to the 3D @@ -135,12 +149,16 @@ struct drm_v3d_submit_cl { /* Number of BO handles passed in (size is that times 4). */ __u32 bo_handle_count; + /* DRM_V3D_SUBMIT_* properties */ __u32 flags; /* ID of the perfmon to attach to this job. 0 means no perfmon. */ __u32 perfmon_id; __u32 pad; + + /* Pointer to an array of ioctl extensions*/ + __u64 extensions; }; /** @@ -248,6 +266,12 @@ struct drm_v3d_submit_tfu { __u32 in_sync; /* Sync object to signal when the TFU job is done. */ __u32 out_sync; + + __u32 flags; + + /* Pointer to an array of ioctl extensions*/ + __u64 extensions; + }; /* Submits a compute shader for dispatch. This job will block on any @@ -276,6 +300,13 @@ struct drm_v3d_submit_csd { /* ID of the perfmon to attach to this job. 0 means no perfmon. */ __u32 perfmon_id; + + /* Pointer to an array of ioctl extensions*/ + __u64 extensions; + + __u32 flags; + + __u32 pad; }; enum { -- cgit v1.2.3 From e4165ae8304e5ea822fbe5909dd3be5445c058b7 Mon Sep 17 00:00:00 2001 From: Melissa Wen Date: Thu, 30 Sep 2021 17:19:56 +0100 Subject: drm/v3d: add multiple syncobjs support Using the generic extension from the previous patch, a specific multisync extension enables more than one in/out binary syncobj per job submission. Arrays of syncobjs are set in struct drm_v3d_multisync, that also cares of determining the stage for sync (wait deps) according to the job queue. v2: - subclass the generic extension struct (Daniel) - simplify adding dependency conditions to make understandable (Iago) v3: - fix conditions to consider single or multiples in/out_syncs (Iago) - remove irrelevant comment (Iago) Signed-off-by: Melissa Wen Reviewed-by: Iago Toral Quiroga Signed-off-by: Melissa Wen Link: https://patchwork.freedesktop.org/patch/msgid/ffd8b2e3dd2e0c686db441a0c0a4a0181ff85328.1633016479.git.mwen@igalia.com --- drivers/gpu/drm/v3d/v3d_drv.c | 6 +- drivers/gpu/drm/v3d/v3d_drv.h | 24 ++++-- drivers/gpu/drm/v3d/v3d_gem.c | 185 +++++++++++++++++++++++++++++++++++++----- include/uapi/drm/v3d_drm.h | 49 ++++++++++- 4 files changed, 232 insertions(+), 32 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/v3d/v3d_drv.c b/drivers/gpu/drm/v3d/v3d_drv.c index 3d6b9bcce2f7..bd46396a1ae0 100644 --- a/drivers/gpu/drm/v3d/v3d_drv.c +++ b/drivers/gpu/drm/v3d/v3d_drv.c @@ -96,6 +96,9 @@ static int v3d_get_param_ioctl(struct drm_device *dev, void *data, case DRM_V3D_PARAM_SUPPORTS_PERFMON: args->value = (v3d->ver >= 40); return 0; + case DRM_V3D_PARAM_SUPPORTS_MULTISYNC_EXT: + args->value = 1; + return 0; default: DRM_DEBUG("Unknown parameter %d\n", args->param); return -EINVAL; @@ -135,9 +138,8 @@ v3d_postclose(struct drm_device *dev, struct drm_file *file) struct v3d_file_priv *v3d_priv = file->driver_priv; enum v3d_queue q; - for (q = 0; q < V3D_MAX_QUEUES; q++) { + for (q = 0; q < V3D_MAX_QUEUES; q++) drm_sched_entity_destroy(&v3d_priv->sched_entity[q]); - } v3d_perfmon_close_file(v3d_priv); kfree(v3d_priv); diff --git a/drivers/gpu/drm/v3d/v3d_drv.h b/drivers/gpu/drm/v3d/v3d_drv.h index b900a050d5e2..b74b1351bfc8 100644 --- a/drivers/gpu/drm/v3d/v3d_drv.h +++ b/drivers/gpu/drm/v3d/v3d_drv.h @@ -19,15 +19,6 @@ struct reset_control; #define GMP_GRANULARITY (128 * 1024) -/* Enum for each of the V3D queues. */ -enum v3d_queue { - V3D_BIN, - V3D_RENDER, - V3D_TFU, - V3D_CSD, - V3D_CACHE_CLEAN, -}; - #define V3D_MAX_QUEUES (V3D_CACHE_CLEAN + 1) struct v3d_queue_state { @@ -294,6 +285,21 @@ struct v3d_csd_job { struct drm_v3d_submit_csd args; }; +struct v3d_submit_outsync { + struct drm_syncobj *syncobj; +}; + +struct v3d_submit_ext { + u32 flags; + u32 wait_stage; + + u32 in_sync_count; + u64 in_syncs; + + u32 out_sync_count; + struct v3d_submit_outsync *out_syncs; +}; + /** * __wait_for - magic wait macro * diff --git a/drivers/gpu/drm/v3d/v3d_gem.c b/drivers/gpu/drm/v3d/v3d_gem.c index 93f130fb3a13..6a000d77c568 100644 --- a/drivers/gpu/drm/v3d/v3d_gem.c +++ b/drivers/gpu/drm/v3d/v3d_gem.c @@ -454,11 +454,12 @@ v3d_job_add_deps(struct drm_file *file_priv, struct v3d_job *job, static int v3d_job_init(struct v3d_dev *v3d, struct drm_file *file_priv, void **container, size_t size, void (*free)(struct kref *ref), - u32 in_sync, enum v3d_queue queue) + u32 in_sync, struct v3d_submit_ext *se, enum v3d_queue queue) { struct v3d_file_priv *v3d_priv = file_priv->driver_priv; struct v3d_job *job; - int ret; + bool has_multisync = se && (se->flags & DRM_V3D_EXT_ID_MULTI_SYNC); + int ret, i; *container = kcalloc(1, size, GFP_KERNEL); if (!*container) { @@ -479,9 +480,28 @@ v3d_job_init(struct v3d_dev *v3d, struct drm_file *file_priv, if (ret) goto fail_job; - ret = v3d_job_add_deps(file_priv, job, in_sync, 0); - if (ret) - goto fail_deps; + if (has_multisync) { + if (se->in_sync_count && se->wait_stage == queue) { + struct drm_v3d_sem __user *handle = u64_to_user_ptr(se->in_syncs); + + for (i = 0; i < se->in_sync_count; i++) { + struct drm_v3d_sem in; + + ret = copy_from_user(&in, handle++, sizeof(in)); + if (ret) { + DRM_DEBUG("Failed to copy wait dep handle.\n"); + goto fail_deps; + } + ret = v3d_job_add_deps(file_priv, job, in.handle, 0); + if (ret) + goto fail_deps; + } + } + } else { + ret = v3d_job_add_deps(file_priv, job, in_sync, 0); + if (ret) + goto fail_deps; + } kref_init(&job->refcount); @@ -516,9 +536,11 @@ v3d_attach_fences_and_unlock_reservation(struct drm_file *file_priv, struct v3d_job *job, struct ww_acquire_ctx *acquire_ctx, u32 out_sync, + struct v3d_submit_ext *se, struct dma_fence *done_fence) { struct drm_syncobj *sync_out; + bool has_multisync = se && (se->flags & DRM_V3D_EXT_ID_MULTI_SYNC); int i; for (i = 0; i < job->bo_count; i++) { @@ -530,20 +552,130 @@ v3d_attach_fences_and_unlock_reservation(struct drm_file *file_priv, drm_gem_unlock_reservations(job->bo, job->bo_count, acquire_ctx); /* Update the return sync object for the job */ - sync_out = drm_syncobj_find(file_priv, out_sync); - if (sync_out) { - drm_syncobj_replace_fence(sync_out, done_fence); - drm_syncobj_put(sync_out); + /* If it only supports a single signal semaphore*/ + if (!has_multisync) { + sync_out = drm_syncobj_find(file_priv, out_sync); + if (sync_out) { + drm_syncobj_replace_fence(sync_out, done_fence); + drm_syncobj_put(sync_out); + } + return; + } + + /* If multiple semaphores extension is supported */ + if (se->out_sync_count) { + for (i = 0; i < se->out_sync_count; i++) { + drm_syncobj_replace_fence(se->out_syncs[i].syncobj, + done_fence); + drm_syncobj_put(se->out_syncs[i].syncobj); + } + kvfree(se->out_syncs); + } +} + +static void +v3d_put_multisync_post_deps(struct v3d_submit_ext *se) +{ + unsigned int i; + + if (!(se && se->out_sync_count)) + return; + + for (i = 0; i < se->out_sync_count; i++) + drm_syncobj_put(se->out_syncs[i].syncobj); + kvfree(se->out_syncs); +} + +static int +v3d_get_multisync_post_deps(struct drm_file *file_priv, + struct v3d_submit_ext *se, + u32 count, u64 handles) +{ + struct drm_v3d_sem __user *post_deps; + int i, ret; + + if (!count) + return 0; + + se->out_syncs = (struct v3d_submit_outsync *) + kvmalloc_array(count, + sizeof(struct v3d_submit_outsync), + GFP_KERNEL); + if (!se->out_syncs) + return -ENOMEM; + + post_deps = u64_to_user_ptr(handles); + + for (i = 0; i < count; i++) { + struct drm_v3d_sem out; + + ret = copy_from_user(&out, post_deps++, sizeof(out)); + if (ret) { + DRM_DEBUG("Failed to copy post dep handles\n"); + goto fail; + } + + se->out_syncs[i].syncobj = drm_syncobj_find(file_priv, + out.handle); + if (!se->out_syncs[i].syncobj) { + ret = -EINVAL; + goto fail; + } } + se->out_sync_count = count; + + return 0; + +fail: + for (i--; i >= 0; i--) + drm_syncobj_put(se->out_syncs[i].syncobj); + kvfree(se->out_syncs); + + return ret; +} + +/* Get data for multiple binary semaphores synchronization. Parse syncobj + * to be signaled when job completes (out_sync). + */ +static int +v3d_get_multisync_submit_deps(struct drm_file *file_priv, + struct drm_v3d_extension __user *ext, + void *data) +{ + struct drm_v3d_multi_sync multisync; + struct v3d_submit_ext *se = data; + int ret; + + ret = copy_from_user(&multisync, ext, sizeof(multisync)); + if (ret) + return ret; + + if (multisync.pad) + return -EINVAL; + + ret = v3d_get_multisync_post_deps(file_priv, data, multisync.out_sync_count, + multisync.out_syncs); + if (ret) + return ret; + + se->in_sync_count = multisync.in_sync_count; + se->in_syncs = multisync.in_syncs; + se->flags |= DRM_V3D_EXT_ID_MULTI_SYNC; + se->wait_stage = multisync.wait_stage; + + return 0; } /* Whenever userspace sets ioctl extensions, v3d_get_extensions parses data * according to the extension id (name). */ static int -v3d_get_extensions(struct drm_file *file_priv, u64 ext_handles) +v3d_get_extensions(struct drm_file *file_priv, + u64 ext_handles, + void *data) { struct drm_v3d_extension __user *user_ext; + int ret; user_ext = u64_to_user_ptr(ext_handles); while (user_ext) { @@ -555,7 +687,11 @@ v3d_get_extensions(struct drm_file *file_priv, u64 ext_handles) } switch (ext.id) { - case 0: + case DRM_V3D_EXT_ID_MULTI_SYNC: + ret = v3d_get_multisync_submit_deps(file_priv, user_ext, data); + if (ret) + return ret; + break; default: DRM_DEBUG_DRIVER("Unknown extension id: %d\n", ext.id); return -EINVAL; @@ -586,6 +722,7 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data, struct v3d_dev *v3d = to_v3d_dev(dev); struct v3d_file_priv *v3d_priv = file_priv->driver_priv; struct drm_v3d_submit_cl *args = data; + struct v3d_submit_ext se = {0}; struct v3d_bin_job *bin = NULL; struct v3d_render_job *render = NULL; struct v3d_job *clean_job = NULL; @@ -606,7 +743,7 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data, } if (args->flags & DRM_V3D_SUBMIT_EXTENSION) { - ret = v3d_get_extensions(file_priv, args->extensions); + ret = v3d_get_extensions(file_priv, args->extensions, &se); if (ret) { DRM_DEBUG("Failed to get extensions.\n"); return ret; @@ -614,7 +751,7 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data, } ret = v3d_job_init(v3d, file_priv, (void *)&render, sizeof(*render), - v3d_render_job_free, args->in_sync_rcl, V3D_RENDER); + v3d_render_job_free, args->in_sync_rcl, &se, V3D_RENDER); if (ret) goto fail; @@ -624,7 +761,7 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data, if (args->bcl_start != args->bcl_end) { ret = v3d_job_init(v3d, file_priv, (void *)&bin, sizeof(*bin), - v3d_job_free, args->in_sync_bcl, V3D_BIN); + v3d_job_free, args->in_sync_bcl, &se, V3D_BIN); if (ret) goto fail; @@ -638,7 +775,7 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data, if (args->flags & DRM_V3D_SUBMIT_CL_FLUSH_CACHE) { ret = v3d_job_init(v3d, file_priv, (void *)&clean_job, sizeof(*clean_job), - v3d_job_free, 0, V3D_CACHE_CLEAN); + v3d_job_free, 0, 0, V3D_CACHE_CLEAN); if (ret) goto fail; @@ -698,6 +835,7 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data, last_job, &acquire_ctx, args->out_sync, + &se, last_job->done_fence); if (bin) @@ -716,6 +854,7 @@ fail: v3d_job_cleanup((void *)bin); v3d_job_cleanup((void *)render); v3d_job_cleanup(clean_job); + v3d_put_multisync_post_deps(&se); return ret; } @@ -735,6 +874,7 @@ v3d_submit_tfu_ioctl(struct drm_device *dev, void *data, { struct v3d_dev *v3d = to_v3d_dev(dev); struct drm_v3d_submit_tfu *args = data; + struct v3d_submit_ext se = {0}; struct v3d_tfu_job *job = NULL; struct ww_acquire_ctx acquire_ctx; int ret = 0; @@ -747,7 +887,7 @@ v3d_submit_tfu_ioctl(struct drm_device *dev, void *data, } if (args->flags & DRM_V3D_SUBMIT_EXTENSION) { - ret = v3d_get_extensions(file_priv, args->extensions); + ret = v3d_get_extensions(file_priv, args->extensions, &se); if (ret) { DRM_DEBUG("Failed to get extensions.\n"); return ret; @@ -755,7 +895,7 @@ v3d_submit_tfu_ioctl(struct drm_device *dev, void *data, } ret = v3d_job_init(v3d, file_priv, (void *)&job, sizeof(*job), - v3d_job_free, args->in_sync, V3D_TFU); + v3d_job_free, args->in_sync, &se, V3D_TFU); if (ret) goto fail; @@ -803,6 +943,7 @@ v3d_submit_tfu_ioctl(struct drm_device *dev, void *data, v3d_attach_fences_and_unlock_reservation(file_priv, &job->base, &acquire_ctx, args->out_sync, + &se, job->base.done_fence); v3d_job_put(&job->base); @@ -811,6 +952,7 @@ v3d_submit_tfu_ioctl(struct drm_device *dev, void *data, fail: v3d_job_cleanup((void *)job); + v3d_put_multisync_post_deps(&se); return ret; } @@ -831,6 +973,7 @@ v3d_submit_csd_ioctl(struct drm_device *dev, void *data, struct v3d_dev *v3d = to_v3d_dev(dev); struct v3d_file_priv *v3d_priv = file_priv->driver_priv; struct drm_v3d_submit_csd *args = data; + struct v3d_submit_ext se = {0}; struct v3d_csd_job *job = NULL; struct v3d_job *clean_job = NULL; struct ww_acquire_ctx acquire_ctx; @@ -852,7 +995,7 @@ v3d_submit_csd_ioctl(struct drm_device *dev, void *data, } if (args->flags & DRM_V3D_SUBMIT_EXTENSION) { - ret = v3d_get_extensions(file_priv, args->extensions); + ret = v3d_get_extensions(file_priv, args->extensions, &se); if (ret) { DRM_DEBUG("Failed to get extensions.\n"); return ret; @@ -860,12 +1003,12 @@ v3d_submit_csd_ioctl(struct drm_device *dev, void *data, } ret = v3d_job_init(v3d, file_priv, (void *)&job, sizeof(*job), - v3d_job_free, args->in_sync, V3D_CSD); + v3d_job_free, args->in_sync, &se, V3D_CSD); if (ret) goto fail; ret = v3d_job_init(v3d, file_priv, (void *)&clean_job, sizeof(*clean_job), - v3d_job_free, 0, V3D_CACHE_CLEAN); + v3d_job_free, 0, 0, V3D_CACHE_CLEAN); if (ret) goto fail; @@ -904,6 +1047,7 @@ v3d_submit_csd_ioctl(struct drm_device *dev, void *data, clean_job, &acquire_ctx, args->out_sync, + &se, clean_job->done_fence); v3d_job_put(&job->base); @@ -918,6 +1062,7 @@ fail_unreserve: fail: v3d_job_cleanup((void *)job); v3d_job_cleanup(clean_job); + v3d_put_multisync_post_deps(&se); return ret; } diff --git a/include/uapi/drm/v3d_drm.h b/include/uapi/drm/v3d_drm.h index 55b443ca6c0b..3dfc0af8756a 100644 --- a/include/uapi/drm/v3d_drm.h +++ b/include/uapi/drm/v3d_drm.h @@ -73,6 +73,53 @@ struct drm_v3d_extension { __u32 flags; /* mbz */ }; +/* struct drm_v3d_sem - wait/signal semaphore + * + * If binary semaphore, it only takes syncobj handle and ignores flags and + * point fields. Point is defined for timeline syncobj feature. + */ +struct drm_v3d_sem { + __u32 handle; /* syncobj */ + /* rsv below, for future uses */ + __u32 flags; + __u64 point; /* for timeline sem support */ + __u64 mbz[2]; /* must be zero, rsv */ +}; + +/* Enum for each of the V3D queues. */ +enum v3d_queue { + V3D_BIN, + V3D_RENDER, + V3D_TFU, + V3D_CSD, + V3D_CACHE_CLEAN, +}; + +/** + * struct drm_v3d_multi_sync - ioctl extension to add support multiples + * syncobjs for commands submission. + * + * When an extension of DRM_V3D_EXT_ID_MULTI_SYNC id is defined, it points to + * this extension to define wait and signal dependencies, instead of single + * in/out sync entries on submitting commands. The field flags is used to + * determine the stage to set wait dependencies. + */ +struct drm_v3d_multi_sync { + struct drm_v3d_extension base; + /* Array of wait and signal semaphores */ + __u64 in_syncs; + __u64 out_syncs; + + /* Number of entries */ + __u32 in_sync_count; + __u32 out_sync_count; + + /* set the stage (v3d_queue) to sync */ + __u32 wait_stage; + + __u32 pad; /* mbz */ +}; + /** * struct drm_v3d_submit_cl - ioctl argument for submitting commands to the 3D * engine. @@ -228,6 +275,7 @@ enum drm_v3d_param { DRM_V3D_PARAM_SUPPORTS_CSD, DRM_V3D_PARAM_SUPPORTS_CACHE_FLUSH, DRM_V3D_PARAM_SUPPORTS_PERFMON, + DRM_V3D_PARAM_SUPPORTS_MULTISYNC_EXT, }; struct drm_v3d_get_param { @@ -271,7 +319,6 @@ struct drm_v3d_submit_tfu { /* Pointer to an array of ioctl extensions*/ __u64 extensions; - }; /* Submits a compute shader for dispatch. This job will block on any -- cgit v1.2.3 From cee0b7cbf1c02fc1e32a9eda6a66f1a4f85adae9 Mon Sep 17 00:00:00 2001 From: Noralf Trønnes Date: Wed, 29 Sep 2021 21:11:57 +0200 Subject: drm/format-helper: Add drm_fb_xrgb8888_to_rgb332() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add XRGB8888 emulation support for devices that can only do RGB332. v2: - Support Big Endian (Daniel) Reviewed-by: Daniel Vetter Acked-by: Thomas Zimmermann Signed-off-by: Noralf Trønnes Link: https://patchwork.freedesktop.org/patch/msgid/20210929191201.34456-3-noralf@tronnes.org --- drivers/gpu/drm/drm_format_helper.c | 50 +++++++++++++++++++++++++++++++++++++ include/drm/drm_format_helper.h | 2 ++ 2 files changed, 52 insertions(+) (limited to 'include') diff --git a/drivers/gpu/drm/drm_format_helper.c b/drivers/gpu/drm/drm_format_helper.c index 5231104b1498..dab4f382d469 100644 --- a/drivers/gpu/drm/drm_format_helper.c +++ b/drivers/gpu/drm/drm_format_helper.c @@ -135,6 +135,56 @@ void drm_fb_swab(void *dst, void *src, struct drm_framebuffer *fb, } EXPORT_SYMBOL(drm_fb_swab); +static void drm_fb_xrgb8888_to_rgb332_line(u8 *dbuf, __le32 *sbuf, unsigned int pixels) +{ + unsigned int x; + u32 pix; + + for (x = 0; x < pixels; x++) { + pix = le32_to_cpu(sbuf[x]); + dbuf[x] = ((pix & 0x00e00000) >> 16) | + ((pix & 0x0000e000) >> 11) | + ((pix & 0x000000c0) >> 6); + } +} + +/** + * drm_fb_xrgb8888_to_rgb332 - Convert XRGB8888 to RGB332 clip buffer + * @dst: RGB332 destination buffer + * @src: XRGB8888 source buffer + * @fb: DRM framebuffer + * @clip: Clip rectangle area to copy + * + * Drivers can use this function for RGB332 devices that don't natively support XRGB8888. + * + * This function does not apply clipping on dst, i.e. the destination is a small buffer + * containing the clip rect only. + */ +void drm_fb_xrgb8888_to_rgb332(void *dst, void *src, struct drm_framebuffer *fb, + struct drm_rect *clip) +{ + size_t width = drm_rect_width(clip); + size_t src_len = width * sizeof(u32); + unsigned int y; + void *sbuf; + + /* Use a buffer to speed up access on buffers with uncached read mapping (i.e. WC) */ + sbuf = kmalloc(src_len, GFP_KERNEL); + if (!sbuf) + return; + + src += clip_offset(clip, fb->pitches[0], sizeof(u32)); + for (y = 0; y < drm_rect_height(clip); y++) { + memcpy(sbuf, src, src_len); + drm_fb_xrgb8888_to_rgb332_line(dst, sbuf, width); + src += fb->pitches[0]; + dst += width; + } + + kfree(sbuf); +} +EXPORT_SYMBOL(drm_fb_xrgb8888_to_rgb332); + static void drm_fb_xrgb8888_to_rgb565_line(u16 *dbuf, u32 *sbuf, unsigned int pixels, bool swab) diff --git a/include/drm/drm_format_helper.h b/include/drm/drm_format_helper.h index 4e0258a61311..d0809aff5cf8 100644 --- a/include/drm/drm_format_helper.h +++ b/include/drm/drm_format_helper.h @@ -16,6 +16,8 @@ void drm_fb_memcpy_dstclip(void __iomem *dst, unsigned int dst_pitch, void *vadd struct drm_rect *clip); void drm_fb_swab(void *dst, void *src, struct drm_framebuffer *fb, struct drm_rect *clip, bool cached); +void drm_fb_xrgb8888_to_rgb332(void *dst, void *vaddr, struct drm_framebuffer *fb, + struct drm_rect *clip); void drm_fb_xrgb8888_to_rgb565(void *dst, void *vaddr, struct drm_framebuffer *fb, struct drm_rect *clip, bool swab); -- cgit v1.2.3 From bcf80d6ef17c97ca7a712d8e6b065910b406e3c3 Mon Sep 17 00:00:00 2001 From: Noralf Trønnes Date: Wed, 29 Sep 2021 21:11:58 +0200 Subject: drm/format-helper: Add drm_fb_xrgb8888_to_rgb888() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add XRGB8888 emulation support for devices that can only do RGB888. Reviewed-by: Daniel Vetter Acked-by: Thomas Zimmermann Signed-off-by: Noralf Trønnes Link: https://patchwork.freedesktop.org/patch/msgid/20210929191201.34456-4-noralf@tronnes.org --- drivers/gpu/drm/drm_format_helper.c | 38 +++++++++++++++++++++++++++++++++++++ include/drm/drm_format_helper.h | 2 ++ 2 files changed, 40 insertions(+) (limited to 'include') diff --git a/drivers/gpu/drm/drm_format_helper.c b/drivers/gpu/drm/drm_format_helper.c index dab4f382d469..69fde60e36b3 100644 --- a/drivers/gpu/drm/drm_format_helper.c +++ b/drivers/gpu/drm/drm_format_helper.c @@ -300,6 +300,44 @@ static void drm_fb_xrgb8888_to_rgb888_line(u8 *dbuf, u32 *sbuf, } } +/** + * drm_fb_xrgb8888_to_rgb888 - Convert XRGB8888 to RGB888 clip buffer + * @dst: RGB888 destination buffer + * @src: XRGB8888 source buffer + * @fb: DRM framebuffer + * @clip: Clip rectangle area to copy + * + * Drivers can use this function for RGB888 devices that don't natively + * support XRGB8888. + * + * This function does not apply clipping on dst, i.e. the destination + * is a small buffer containing the clip rect only. + */ +void drm_fb_xrgb8888_to_rgb888(void *dst, void *src, struct drm_framebuffer *fb, + struct drm_rect *clip) +{ + size_t width = drm_rect_width(clip); + size_t src_len = width * sizeof(u32); + unsigned int y; + void *sbuf; + + /* Use a buffer to speed up access on buffers with uncached read mapping (i.e. WC) */ + sbuf = kmalloc(src_len, GFP_KERNEL); + if (!sbuf) + return; + + src += clip_offset(clip, fb->pitches[0], sizeof(u32)); + for (y = 0; y < drm_rect_height(clip); y++) { + memcpy(sbuf, src, src_len); + drm_fb_xrgb8888_to_rgb888_line(dst, sbuf, width); + src += fb->pitches[0]; + dst += width * 3; + } + + kfree(sbuf); +} +EXPORT_SYMBOL(drm_fb_xrgb8888_to_rgb888); + /** * drm_fb_xrgb8888_to_rgb888_dstclip - Convert XRGB8888 to RGB888 clip buffer * @dst: RGB565 destination buffer (iomem) diff --git a/include/drm/drm_format_helper.h b/include/drm/drm_format_helper.h index d0809aff5cf8..e86925cf07b9 100644 --- a/include/drm/drm_format_helper.h +++ b/include/drm/drm_format_helper.h @@ -24,6 +24,8 @@ void drm_fb_xrgb8888_to_rgb565(void *dst, void *vaddr, void drm_fb_xrgb8888_to_rgb565_dstclip(void __iomem *dst, unsigned int dst_pitch, void *vaddr, struct drm_framebuffer *fb, struct drm_rect *clip, bool swab); +void drm_fb_xrgb8888_to_rgb888(void *dst, void *src, struct drm_framebuffer *fb, + struct drm_rect *clip); void drm_fb_xrgb8888_to_rgb888_dstclip(void __iomem *dst, unsigned int dst_pitch, void *vaddr, struct drm_framebuffer *fb, struct drm_rect *clip); -- cgit v1.2.3 From 4cabfedc096b14336fac1d42bec5cb8ff5090527 Mon Sep 17 00:00:00 2001 From: Noralf Trønnes Date: Wed, 29 Sep 2021 21:11:59 +0200 Subject: drm/gud: Add GUD_PIXEL_FORMAT_R8 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add support for 8-bit greyscale format. Acked-by: Thomas Zimmermann Signed-off-by: Noralf Trønnes Link: https://patchwork.freedesktop.org/patch/msgid/20210929191201.34456-5-noralf@tronnes.org --- drivers/gpu/drm/gud/gud_drv.c | 2 ++ drivers/gpu/drm/gud/gud_internal.h | 4 ++++ drivers/gpu/drm/gud/gud_pipe.c | 2 ++ include/drm/gud.h | 4 ++-- 4 files changed, 10 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/gud/gud_drv.c b/drivers/gpu/drm/gud/gud_drv.c index eb4e08846da4..a8d76c76e868 100644 --- a/drivers/gpu/drm/gud/gud_drv.c +++ b/drivers/gpu/drm/gud/gud_drv.c @@ -523,6 +523,8 @@ static int gud_probe(struct usb_interface *intf, const struct usb_device_id *id) switch (format) { case GUD_DRM_FORMAT_R1: fallthrough; + case DRM_FORMAT_R8: + fallthrough; case GUD_DRM_FORMAT_XRGB1111: if (!xrgb8888_emulation_format) xrgb8888_emulation_format = info; diff --git a/drivers/gpu/drm/gud/gud_internal.h b/drivers/gpu/drm/gud/gud_internal.h index 2a388e27d5d7..8499e713dbbc 100644 --- a/drivers/gpu/drm/gud/gud_internal.h +++ b/drivers/gpu/drm/gud/gud_internal.h @@ -80,6 +80,8 @@ static inline u8 gud_from_fourcc(u32 fourcc) switch (fourcc) { case GUD_DRM_FORMAT_R1: return GUD_PIXEL_FORMAT_R1; + case DRM_FORMAT_R8: + return GUD_PIXEL_FORMAT_R8; case GUD_DRM_FORMAT_XRGB1111: return GUD_PIXEL_FORMAT_XRGB1111; case DRM_FORMAT_RGB565: @@ -98,6 +100,8 @@ static inline u32 gud_to_fourcc(u8 format) switch (format) { case GUD_PIXEL_FORMAT_R1: return GUD_DRM_FORMAT_R1; + case GUD_PIXEL_FORMAT_R8: + return DRM_FORMAT_R8; case GUD_PIXEL_FORMAT_XRGB1111: return GUD_DRM_FORMAT_XRGB1111; case GUD_PIXEL_FORMAT_RGB565: diff --git a/drivers/gpu/drm/gud/gud_pipe.c b/drivers/gpu/drm/gud/gud_pipe.c index b9b0e435ea0f..be4f95b2d59c 100644 --- a/drivers/gpu/drm/gud/gud_pipe.c +++ b/drivers/gpu/drm/gud/gud_pipe.c @@ -189,6 +189,8 @@ retry: ret = -ENOMEM; goto end_cpu_access; } + } else if (format->format == DRM_FORMAT_R8) { + drm_fb_xrgb8888_to_gray8(buf, vaddr, fb, rect); } else if (format->format == DRM_FORMAT_RGB565) { drm_fb_xrgb8888_to_rgb565(buf, vaddr, fb, rect, gud_is_big_endian()); } else { diff --git a/include/drm/gud.h b/include/drm/gud.h index 0b46b54fe56e..1dc781009e62 100644 --- a/include/drm/gud.h +++ b/include/drm/gud.h @@ -246,8 +246,8 @@ struct gud_state_req { /* Get supported pixel formats as a byte array of GUD_PIXEL_FORMAT_* */ #define GUD_REQ_GET_FORMATS 0x40 #define GUD_FORMATS_MAX_NUM 32 - /* R1 is a 1-bit monochrome transfer format presented to userspace as XRGB8888 */ - #define GUD_PIXEL_FORMAT_R1 0x01 + #define GUD_PIXEL_FORMAT_R1 0x01 /* 1-bit monochrome */ + #define GUD_PIXEL_FORMAT_R8 0x08 /* 8-bit greyscale */ #define GUD_PIXEL_FORMAT_XRGB1111 0x20 #define GUD_PIXEL_FORMAT_RGB565 0x40 #define GUD_PIXEL_FORMAT_XRGB8888 0x80 -- cgit v1.2.3 From 1f25d0054258df239ffa420606466fd9b14e06d6 Mon Sep 17 00:00:00 2001 From: Noralf Trønnes Date: Wed, 29 Sep 2021 21:12:00 +0200 Subject: drm/gud: Add GUD_PIXEL_FORMAT_RGB332 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add support for the RGB332 pixel format. Acked-by: Thomas Zimmermann Signed-off-by: Noralf Trønnes Link: https://patchwork.freedesktop.org/patch/msgid/20210929191201.34456-6-noralf@tronnes.org --- drivers/gpu/drm/gud/gud_drv.c | 2 ++ drivers/gpu/drm/gud/gud_internal.h | 4 ++++ drivers/gpu/drm/gud/gud_pipe.c | 2 ++ include/drm/gud.h | 1 + 4 files changed, 9 insertions(+) (limited to 'include') diff --git a/drivers/gpu/drm/gud/gud_drv.c b/drivers/gpu/drm/gud/gud_drv.c index a8d76c76e868..e571ad10a12b 100644 --- a/drivers/gpu/drm/gud/gud_drv.c +++ b/drivers/gpu/drm/gud/gud_drv.c @@ -526,6 +526,8 @@ static int gud_probe(struct usb_interface *intf, const struct usb_device_id *id) case DRM_FORMAT_R8: fallthrough; case GUD_DRM_FORMAT_XRGB1111: + fallthrough; + case DRM_FORMAT_RGB332: if (!xrgb8888_emulation_format) xrgb8888_emulation_format = info; break; diff --git a/drivers/gpu/drm/gud/gud_internal.h b/drivers/gpu/drm/gud/gud_internal.h index 8499e713dbbc..249e02d1f5ed 100644 --- a/drivers/gpu/drm/gud/gud_internal.h +++ b/drivers/gpu/drm/gud/gud_internal.h @@ -84,6 +84,8 @@ static inline u8 gud_from_fourcc(u32 fourcc) return GUD_PIXEL_FORMAT_R8; case GUD_DRM_FORMAT_XRGB1111: return GUD_PIXEL_FORMAT_XRGB1111; + case DRM_FORMAT_RGB332: + return GUD_PIXEL_FORMAT_RGB332; case DRM_FORMAT_RGB565: return GUD_PIXEL_FORMAT_RGB565; case DRM_FORMAT_XRGB8888: @@ -104,6 +106,8 @@ static inline u32 gud_to_fourcc(u8 format) return DRM_FORMAT_R8; case GUD_PIXEL_FORMAT_XRGB1111: return GUD_DRM_FORMAT_XRGB1111; + case GUD_PIXEL_FORMAT_RGB332: + return DRM_FORMAT_RGB332; case GUD_PIXEL_FORMAT_RGB565: return DRM_FORMAT_RGB565; case GUD_PIXEL_FORMAT_XRGB8888: diff --git a/drivers/gpu/drm/gud/gud_pipe.c b/drivers/gpu/drm/gud/gud_pipe.c index be4f95b2d59c..868a0b8a1f3e 100644 --- a/drivers/gpu/drm/gud/gud_pipe.c +++ b/drivers/gpu/drm/gud/gud_pipe.c @@ -191,6 +191,8 @@ retry: } } else if (format->format == DRM_FORMAT_R8) { drm_fb_xrgb8888_to_gray8(buf, vaddr, fb, rect); + } else if (format->format == DRM_FORMAT_RGB332) { + drm_fb_xrgb8888_to_rgb332(buf, vaddr, fb, rect); } else if (format->format == DRM_FORMAT_RGB565) { drm_fb_xrgb8888_to_rgb565(buf, vaddr, fb, rect, gud_is_big_endian()); } else { diff --git a/include/drm/gud.h b/include/drm/gud.h index 1dc781009e62..4118dce2fcec 100644 --- a/include/drm/gud.h +++ b/include/drm/gud.h @@ -249,6 +249,7 @@ struct gud_state_req { #define GUD_PIXEL_FORMAT_R1 0x01 /* 1-bit monochrome */ #define GUD_PIXEL_FORMAT_R8 0x08 /* 8-bit greyscale */ #define GUD_PIXEL_FORMAT_XRGB1111 0x20 + #define GUD_PIXEL_FORMAT_RGB332 0x30 #define GUD_PIXEL_FORMAT_RGB565 0x40 #define GUD_PIXEL_FORMAT_XRGB8888 0x80 #define GUD_PIXEL_FORMAT_ARGB8888 0x81 -- cgit v1.2.3 From 83d7b6d54b8e8a3a487c8a4066e33e6bdd255c3d Mon Sep 17 00:00:00 2001 From: Noralf Trønnes Date: Wed, 29 Sep 2021 21:12:01 +0200 Subject: drm/gud: Add GUD_PIXEL_FORMAT_RGB888 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add support for the RGB888 pixel format. Acked-by: Thomas Zimmermann Signed-off-by: Noralf Trønnes Link: https://patchwork.freedesktop.org/patch/msgid/20210929191201.34456-7-noralf@tronnes.org --- drivers/gpu/drm/gud/gud_drv.c | 2 ++ drivers/gpu/drm/gud/gud_internal.h | 4 ++++ drivers/gpu/drm/gud/gud_pipe.c | 2 ++ include/drm/gud.h | 1 + 4 files changed, 9 insertions(+) (limited to 'include') diff --git a/drivers/gpu/drm/gud/gud_drv.c b/drivers/gpu/drm/gud/gud_drv.c index e571ad10a12b..3f9d4b9a1e3d 100644 --- a/drivers/gpu/drm/gud/gud_drv.c +++ b/drivers/gpu/drm/gud/gud_drv.c @@ -528,6 +528,8 @@ static int gud_probe(struct usb_interface *intf, const struct usb_device_id *id) case GUD_DRM_FORMAT_XRGB1111: fallthrough; case DRM_FORMAT_RGB332: + fallthrough; + case DRM_FORMAT_RGB888: if (!xrgb8888_emulation_format) xrgb8888_emulation_format = info; break; diff --git a/drivers/gpu/drm/gud/gud_internal.h b/drivers/gpu/drm/gud/gud_internal.h index 249e02d1f5ed..e351a1f1420d 100644 --- a/drivers/gpu/drm/gud/gud_internal.h +++ b/drivers/gpu/drm/gud/gud_internal.h @@ -88,6 +88,8 @@ static inline u8 gud_from_fourcc(u32 fourcc) return GUD_PIXEL_FORMAT_RGB332; case DRM_FORMAT_RGB565: return GUD_PIXEL_FORMAT_RGB565; + case DRM_FORMAT_RGB888: + return GUD_PIXEL_FORMAT_RGB888; case DRM_FORMAT_XRGB8888: return GUD_PIXEL_FORMAT_XRGB8888; case DRM_FORMAT_ARGB8888: @@ -110,6 +112,8 @@ static inline u32 gud_to_fourcc(u8 format) return DRM_FORMAT_RGB332; case GUD_PIXEL_FORMAT_RGB565: return DRM_FORMAT_RGB565; + case GUD_PIXEL_FORMAT_RGB888: + return DRM_FORMAT_RGB888; case GUD_PIXEL_FORMAT_XRGB8888: return DRM_FORMAT_XRGB8888; case GUD_PIXEL_FORMAT_ARGB8888: diff --git a/drivers/gpu/drm/gud/gud_pipe.c b/drivers/gpu/drm/gud/gud_pipe.c index 868a0b8a1f3e..daf75c178c2b 100644 --- a/drivers/gpu/drm/gud/gud_pipe.c +++ b/drivers/gpu/drm/gud/gud_pipe.c @@ -195,6 +195,8 @@ retry: drm_fb_xrgb8888_to_rgb332(buf, vaddr, fb, rect); } else if (format->format == DRM_FORMAT_RGB565) { drm_fb_xrgb8888_to_rgb565(buf, vaddr, fb, rect, gud_is_big_endian()); + } else if (format->format == DRM_FORMAT_RGB888) { + drm_fb_xrgb8888_to_rgb888(buf, vaddr, fb, rect); } else { len = gud_xrgb8888_to_color(buf, format, vaddr, fb, rect); } diff --git a/include/drm/gud.h b/include/drm/gud.h index 4118dce2fcec..c52a8ba4ae4e 100644 --- a/include/drm/gud.h +++ b/include/drm/gud.h @@ -251,6 +251,7 @@ struct gud_state_req { #define GUD_PIXEL_FORMAT_XRGB1111 0x20 #define GUD_PIXEL_FORMAT_RGB332 0x30 #define GUD_PIXEL_FORMAT_RGB565 0x40 + #define GUD_PIXEL_FORMAT_RGB888 0x50 #define GUD_PIXEL_FORMAT_XRGB8888 0x80 #define GUD_PIXEL_FORMAT_ARGB8888 0x81 -- cgit v1.2.3 From 294a0d9524b1b814499140d79b9127fb581acc9c Mon Sep 17 00:00:00 2001 From: Sean Paul Date: Sat, 2 Oct 2021 11:45:27 -0400 Subject: Revert "drm: cleanup: remove drm_modeset_(un)lock_all()" MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This reverts commit 8d813d1a535c8c7503a5f4061654a73026be8c5e. This patchset breaks on intel platforms and was previously NACK'd by Ville. Cc: Ville Syrjälä Cc: Fernando Ramos Acked-by: Ville Syrjälä Signed-off-by: Sean Paul Link: https://patchwork.freedesktop.org/patch/msgid/20211002154542.15800-1-sean@poorly.run --- drivers/gpu/drm/drm_modeset_lock.c | 94 ++++++++++++++++++++++++++++++++++++-- include/drm/drm_modeset_lock.h | 2 + 2 files changed, 93 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/drm_modeset_lock.c b/drivers/gpu/drm/drm_modeset_lock.c index afd1351749a5..fcfe1a03c4a1 100644 --- a/drivers/gpu/drm/drm_modeset_lock.c +++ b/drivers/gpu/drm/drm_modeset_lock.c @@ -77,6 +77,93 @@ static DEFINE_WW_CLASS(crtc_ww_class); +/** + * drm_modeset_lock_all - take all modeset locks + * @dev: DRM device + * + * This function takes all modeset locks, suitable where a more fine-grained + * scheme isn't (yet) implemented. Locks must be dropped by calling the + * drm_modeset_unlock_all() function. + * + * This function is deprecated. It allocates a lock acquisition context and + * stores it in &drm_device.mode_config. This facilitate conversion of + * existing code because it removes the need to manually deal with the + * acquisition context, but it is also brittle because the context is global + * and care must be taken not to nest calls. New code should use the + * drm_modeset_lock_all_ctx() function and pass in the context explicitly. + */ +void drm_modeset_lock_all(struct drm_device *dev) +{ + struct drm_mode_config *config = &dev->mode_config; + struct drm_modeset_acquire_ctx *ctx; + int ret; + + ctx = kzalloc(sizeof(*ctx), GFP_KERNEL | __GFP_NOFAIL); + if (WARN_ON(!ctx)) + return; + + mutex_lock(&config->mutex); + + drm_modeset_acquire_init(ctx, 0); + +retry: + ret = drm_modeset_lock_all_ctx(dev, ctx); + if (ret < 0) { + if (ret == -EDEADLK) { + drm_modeset_backoff(ctx); + goto retry; + } + + drm_modeset_acquire_fini(ctx); + kfree(ctx); + return; + } + ww_acquire_done(&ctx->ww_ctx); + + WARN_ON(config->acquire_ctx); + + /* + * We hold the locks now, so it is safe to stash the acquisition + * context for drm_modeset_unlock_all(). + */ + config->acquire_ctx = ctx; + + drm_warn_on_modeset_not_all_locked(dev); +} +EXPORT_SYMBOL(drm_modeset_lock_all); + +/** + * drm_modeset_unlock_all - drop all modeset locks + * @dev: DRM device + * + * This function drops all modeset locks taken by a previous call to the + * drm_modeset_lock_all() function. + * + * This function is deprecated. It uses the lock acquisition context stored + * in &drm_device.mode_config. This facilitates conversion of existing + * code because it removes the need to manually deal with the acquisition + * context, but it is also brittle because the context is global and care must + * be taken not to nest calls. New code should pass the acquisition context + * directly to the drm_modeset_drop_locks() function. + */ +void drm_modeset_unlock_all(struct drm_device *dev) +{ + struct drm_mode_config *config = &dev->mode_config; + struct drm_modeset_acquire_ctx *ctx = config->acquire_ctx; + + if (WARN_ON(!ctx)) + return; + + config->acquire_ctx = NULL; + drm_modeset_drop_locks(ctx); + drm_modeset_acquire_fini(ctx); + + kfree(ctx); + + mutex_unlock(&dev->mode_config.mutex); +} +EXPORT_SYMBOL(drm_modeset_unlock_all); + /** * drm_warn_on_modeset_not_all_locked - check that all modeset locks are locked * @dev: device @@ -293,9 +380,10 @@ EXPORT_SYMBOL(drm_modeset_unlock); * This function takes all modeset locks, suitable where a more fine-grained * scheme isn't (yet) implemented. * - * It doesn't take the &drm_mode_config.mutex since that lock isn't required for - * modeset state changes. Callers which need to grab that lock too need to do so - * outside of the acquire context @ctx. + * Unlike drm_modeset_lock_all(), it doesn't take the &drm_mode_config.mutex + * since that lock isn't required for modeset state changes. Callers which + * need to grab that lock too need to do so outside of the acquire context + * @ctx. * * Locks acquired with this function should be released by calling the * drm_modeset_drop_locks() function on @ctx. diff --git a/include/drm/drm_modeset_lock.h b/include/drm/drm_modeset_lock.h index 865e64bcc4cb..aafd07388eb7 100644 --- a/include/drm/drm_modeset_lock.h +++ b/include/drm/drm_modeset_lock.h @@ -132,6 +132,8 @@ struct drm_device; struct drm_crtc; struct drm_plane; +void drm_modeset_lock_all(struct drm_device *dev); +void drm_modeset_unlock_all(struct drm_device *dev); void drm_warn_on_modeset_not_all_locked(struct drm_device *dev); int drm_modeset_lock_all_ctx(struct drm_device *dev, -- cgit v1.2.3 From 288f1068975583bc63e68a61731453b0f07a46af Mon Sep 17 00:00:00 2001 From: Daniele Ceraolo Spurio Date: Fri, 24 Sep 2021 12:14:36 -0700 Subject: drm/i915/pxp: Define PXP component interface This will be used for communication between the i915 driver and the mei one. Defining it in a stand-alone patch to avoid circualr dependedencies between the patches modifying the 2 drivers. Split out from an original patch from Huang, Sean Z v2: rename the component struct (Rodrigo) Signed-off-by: Daniele Ceraolo Spurio Cc: Rodrigo Vivi Reviewed-by: Rodrigo Vivi Signed-off-by: Rodrigo Vivi Link: https://patchwork.freedesktop.org/patch/msgid/20210924191452.1539378-2-alan.previn.teres.alexis@intel.com --- include/drm/i915_component.h | 1 + include/drm/i915_pxp_tee_interface.h | 42 ++++++++++++++++++++++++++++++++++++ 2 files changed, 43 insertions(+) create mode 100644 include/drm/i915_pxp_tee_interface.h (limited to 'include') diff --git a/include/drm/i915_component.h b/include/drm/i915_component.h index 55c3b123581b..c1e2a43d2d1e 100644 --- a/include/drm/i915_component.h +++ b/include/drm/i915_component.h @@ -29,6 +29,7 @@ enum i915_component_type { I915_COMPONENT_AUDIO = 1, I915_COMPONENT_HDCP, + I915_COMPONENT_PXP }; /* MAX_PORT is the number of port diff --git a/include/drm/i915_pxp_tee_interface.h b/include/drm/i915_pxp_tee_interface.h new file mode 100644 index 000000000000..af593ec64469 --- /dev/null +++ b/include/drm/i915_pxp_tee_interface.h @@ -0,0 +1,42 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2020 Intel Corporation + */ + +#ifndef _I915_PXP_TEE_INTERFACE_H_ +#define _I915_PXP_TEE_INTERFACE_H_ + +#include +#include + +/** + * 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 + */ + struct module *owner; + + int (*send)(struct device *dev, const void *message, size_t size); + int (*recv)(struct device *dev, void *buffer, size_t size); +}; + +/** + * 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 { + struct device *tee_dev; + const struct i915_pxp_component_ops *ops; + + /* To protect the above members. */ + struct mutex mutex; +}; + +#endif /* _I915_TEE_PXP_INTERFACE_H_ */ -- cgit v1.2.3 From cbbd3764b2399ad882cda98435b25144e9ea2124 Mon Sep 17 00:00:00 2001 From: "Huang, Sean Z" Date: Fri, 24 Sep 2021 12:14:42 -0700 Subject: drm/i915/pxp: Create the arbitrary session after boot Create the arbitrary session, with the fixed session id 0xf, after system boot, for the case that application allocates the protected buffer without establishing any protection session. Because the hardware requires at least one alive session for protected buffer creation. This arbitrary session will need to be re-created after teardown or power event because hardware encryption key won't be valid after such cases. The session ID is exposed as part of the uapi so it can be used as part of userspace commands. v2: use gt->uncore->rpm (Chris) v3: s/arb_is_in_play/arb_is_valid (Chris), move set-up to the new init_hw function v4: move interface defs to separate header, set arb_is valid to false on fini (Rodrigo) v5: handle async component binding Signed-off-by: Huang, Sean Z Signed-off-by: Daniele Ceraolo Spurio Cc: Chris Wilson Cc: Rodrigo Vivi Reviewed-by: Rodrigo Vivi Signed-off-by: Rodrigo Vivi Link: https://patchwork.freedesktop.org/patch/msgid/20210924191452.1539378-8-alan.previn.teres.alexis@intel.com --- drivers/gpu/drm/i915/Makefile | 1 + drivers/gpu/drm/i915/pxp/intel_pxp.c | 12 +++ drivers/gpu/drm/i915/pxp/intel_pxp.h | 2 + drivers/gpu/drm/i915/pxp/intel_pxp_session.c | 74 ++++++++++++++++++ drivers/gpu/drm/i915/pxp/intel_pxp_session.h | 15 ++++ drivers/gpu/drm/i915/pxp/intel_pxp_tee.c | 87 ++++++++++++++++++++++ drivers/gpu/drm/i915/pxp/intel_pxp_tee.h | 3 + drivers/gpu/drm/i915/pxp/intel_pxp_tee_interface.h | 36 +++++++++ drivers/gpu/drm/i915/pxp/intel_pxp_types.h | 10 +++ include/uapi/drm/i915_drm.h | 3 + 10 files changed, 243 insertions(+) create mode 100644 drivers/gpu/drm/i915/pxp/intel_pxp_session.c create mode 100644 drivers/gpu/drm/i915/pxp/intel_pxp_session.h create mode 100644 drivers/gpu/drm/i915/pxp/intel_pxp_tee_interface.h (limited to 'include') diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile index d790b603fbdd..1152348c04a9 100644 --- a/drivers/gpu/drm/i915/Makefile +++ b/drivers/gpu/drm/i915/Makefile @@ -281,6 +281,7 @@ i915-y += i915_perf.o # Protected execution platform (PXP) support i915-$(CONFIG_DRM_I915_PXP) += \ pxp/intel_pxp.o \ + pxp/intel_pxp_session.o \ pxp/intel_pxp_tee.o # Post-mortem debug and GPU hang state capture diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp.c b/drivers/gpu/drm/i915/pxp/intel_pxp.c index f7166dd71d8f..65598487a7b2 100644 --- a/drivers/gpu/drm/i915/pxp/intel_pxp.c +++ b/drivers/gpu/drm/i915/pxp/intel_pxp.c @@ -3,6 +3,7 @@ * Copyright(c) 2020 Intel Corporation. */ #include "intel_pxp.h" +#include "intel_pxp_session.h" #include "intel_pxp_tee.h" #include "gt/intel_context.h" #include "i915_drv.h" @@ -12,6 +13,11 @@ struct intel_gt *pxp_to_gt(const struct intel_pxp *pxp) return container_of(pxp, struct intel_gt, pxp); } +bool intel_pxp_is_active(const struct intel_pxp *pxp) +{ + return pxp->arb_is_valid; +} + /* KCR register definitions */ #define KCR_INIT _MMIO(0x320f0) /* Setting KCR Init bit is required after system boot */ @@ -72,6 +78,8 @@ void intel_pxp_init(struct intel_pxp *pxp) if (!HAS_PXP(gt->i915)) return; + mutex_init(&pxp->tee_mutex); + ret = create_vcs_context(pxp); if (ret) return; @@ -93,6 +101,8 @@ void intel_pxp_fini(struct intel_pxp *pxp) if (!intel_pxp_is_enabled(pxp)) return; + pxp->arb_is_valid = false; + intel_pxp_tee_component_fini(pxp); destroy_vcs_context(pxp); @@ -101,6 +111,8 @@ void intel_pxp_fini(struct intel_pxp *pxp) void intel_pxp_init_hw(struct intel_pxp *pxp) { kcr_pxp_enable(pxp_to_gt(pxp)); + + intel_pxp_create_arb_session(pxp); } void intel_pxp_fini_hw(struct intel_pxp *pxp) diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp.h b/drivers/gpu/drm/i915/pxp/intel_pxp.h index cd6560b2605c..2960e8338c82 100644 --- a/drivers/gpu/drm/i915/pxp/intel_pxp.h +++ b/drivers/gpu/drm/i915/pxp/intel_pxp.h @@ -15,6 +15,8 @@ static inline bool intel_pxp_is_enabled(const struct intel_pxp *pxp) #ifdef CONFIG_DRM_I915_PXP struct intel_gt *pxp_to_gt(const struct intel_pxp *pxp); +bool intel_pxp_is_active(const struct intel_pxp *pxp); + void intel_pxp_init(struct intel_pxp *pxp); void intel_pxp_fini(struct intel_pxp *pxp); diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_session.c b/drivers/gpu/drm/i915/pxp/intel_pxp_session.c new file mode 100644 index 000000000000..3331868f354c --- /dev/null +++ b/drivers/gpu/drm/i915/pxp/intel_pxp_session.c @@ -0,0 +1,74 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright(c) 2020, Intel Corporation. All rights reserved. + */ + +#include "drm/i915_drm.h" +#include "i915_drv.h" + +#include "intel_pxp.h" +#include "intel_pxp_session.h" +#include "intel_pxp_tee.h" +#include "intel_pxp_types.h" + +#define ARB_SESSION I915_PROTECTED_CONTENT_DEFAULT_SESSION /* shorter define */ + +#define GEN12_KCR_SIP _MMIO(0x32260) /* KCR hwdrm session in play 0-31 */ + +static bool intel_pxp_session_is_in_play(struct intel_pxp *pxp, u32 id) +{ + struct intel_gt *gt = pxp_to_gt(pxp); + intel_wakeref_t wakeref; + u32 sip = 0; + + with_intel_runtime_pm(gt->uncore->rpm, wakeref) + sip = intel_uncore_read(gt->uncore, GEN12_KCR_SIP); + + return sip & BIT(id); +} + +static int pxp_wait_for_session_state(struct intel_pxp *pxp, u32 id, bool in_play) +{ + struct intel_gt *gt = pxp_to_gt(pxp); + intel_wakeref_t wakeref; + u32 mask = BIT(id); + int ret; + + with_intel_runtime_pm(gt->uncore->rpm, wakeref) + ret = intel_wait_for_register(gt->uncore, + GEN12_KCR_SIP, + mask, + in_play ? mask : 0, + 100); + + return ret; +} + +int intel_pxp_create_arb_session(struct intel_pxp *pxp) +{ + struct intel_gt *gt = pxp_to_gt(pxp); + int ret; + + pxp->arb_is_valid = false; + + if (intel_pxp_session_is_in_play(pxp, ARB_SESSION)) { + drm_err(>->i915->drm, "arb session already in play at creation time\n"); + return -EEXIST; + } + + ret = intel_pxp_tee_cmd_create_arb_session(pxp, ARB_SESSION); + if (ret) { + drm_err(>->i915->drm, "tee cmd for arb session creation failed\n"); + return ret; + } + + ret = pxp_wait_for_session_state(pxp, ARB_SESSION, true); + if (ret) { + drm_err(>->i915->drm, "arb session failed to go in play\n"); + return ret; + } + + pxp->arb_is_valid = true; + + return 0; +} diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_session.h b/drivers/gpu/drm/i915/pxp/intel_pxp_session.h new file mode 100644 index 000000000000..316c3bebed9c --- /dev/null +++ b/drivers/gpu/drm/i915/pxp/intel_pxp_session.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright(c) 2020, Intel Corporation. All rights reserved. + */ + +#ifndef __INTEL_PXP_SESSION_H__ +#define __INTEL_PXP_SESSION_H__ + +#include + +struct intel_pxp; + +int intel_pxp_create_arb_session(struct intel_pxp *pxp); + +#endif /* __INTEL_PXP_SESSION_H__ */ diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_tee.c b/drivers/gpu/drm/i915/pxp/intel_pxp_tee.c index 0c0c7946e6a0..accbbf9aa6d1 100644 --- a/drivers/gpu/drm/i915/pxp/intel_pxp_tee.c +++ b/drivers/gpu/drm/i915/pxp/intel_pxp_tee.c @@ -8,13 +8,63 @@ #include "drm/i915_component.h" #include "i915_drv.h" #include "intel_pxp.h" +#include "intel_pxp_session.h" #include "intel_pxp_tee.h" +#include "intel_pxp_tee_interface.h" static inline struct intel_pxp *i915_dev_to_pxp(struct device *i915_kdev) { return &kdev_to_i915(i915_kdev)->gt.pxp; } +static int intel_pxp_tee_io_message(struct intel_pxp *pxp, + void *msg_in, u32 msg_in_size, + void *msg_out, u32 msg_out_max_size, + u32 *msg_out_rcv_size) +{ + struct drm_i915_private *i915 = pxp_to_gt(pxp)->i915; + struct i915_pxp_component *pxp_component = pxp->pxp_component; + int ret = 0; + + mutex_lock(&pxp->tee_mutex); + + /* + * The binding of the component is asynchronous from i915 probe, so we + * can't be sure it has happened. + */ + if (!pxp_component) { + ret = -ENODEV; + goto unlock; + } + + ret = pxp_component->ops->send(pxp_component->tee_dev, msg_in, msg_in_size); + if (ret) { + drm_err(&i915->drm, "Failed to send PXP TEE message\n"); + goto unlock; + } + + ret = pxp_component->ops->recv(pxp_component->tee_dev, msg_out, msg_out_max_size); + if (ret < 0) { + drm_err(&i915->drm, "Failed to receive PXP TEE message\n"); + goto unlock; + } + + if (ret > msg_out_max_size) { + drm_err(&i915->drm, + "Failed to receive PXP TEE message due to unexpected output size\n"); + ret = -ENOSPC; + goto unlock; + } + + if (msg_out_rcv_size) + *msg_out_rcv_size = ret; + + ret = 0; +unlock: + mutex_unlock(&pxp->tee_mutex); + return ret; +} + /** * i915_pxp_tee_component_bind - bind function to pass the function pointers to pxp_tee * @i915_kdev: pointer to i915 kernel device @@ -28,14 +78,24 @@ static inline struct intel_pxp *i915_dev_to_pxp(struct device *i915_kdev) static int i915_pxp_tee_component_bind(struct device *i915_kdev, struct device *tee_kdev, void *data) { + struct drm_i915_private *i915 = kdev_to_i915(i915_kdev); struct intel_pxp *pxp = i915_dev_to_pxp(i915_kdev); + mutex_lock(&pxp->tee_mutex); pxp->pxp_component = data; pxp->pxp_component->tee_dev = tee_kdev; + mutex_unlock(&pxp->tee_mutex); /* the component is required to fully start the PXP HW */ intel_pxp_init_hw(pxp); + if (!pxp->arb_is_valid) { + drm_err(&i915->drm, "Failed to create arb session during bind\n"); + intel_pxp_fini_hw(pxp); + pxp->pxp_component = NULL; + return -EIO; + } + return 0; } @@ -46,7 +106,9 @@ static void i915_pxp_tee_component_unbind(struct device *i915_kdev, intel_pxp_fini_hw(pxp); + mutex_lock(&pxp->tee_mutex); pxp->pxp_component = NULL; + mutex_unlock(&pxp->tee_mutex); } static const struct component_ops i915_pxp_tee_component_ops = { @@ -82,3 +144,28 @@ void intel_pxp_tee_component_fini(struct intel_pxp *pxp) component_del(i915->drm.dev, &i915_pxp_tee_component_ops); pxp->pxp_component_added = false; } + +int intel_pxp_tee_cmd_create_arb_session(struct intel_pxp *pxp, + int arb_session_id) +{ + struct drm_i915_private *i915 = pxp_to_gt(pxp)->i915; + struct pxp_tee_create_arb_in msg_in = {0}; + struct pxp_tee_create_arb_out msg_out = {0}; + int ret; + + msg_in.header.api_version = PXP_TEE_APIVER; + msg_in.header.command_id = PXP_TEE_ARB_CMDID; + msg_in.header.buffer_len = sizeof(msg_in) - sizeof(msg_in.header); + msg_in.protection_mode = PXP_TEE_ARB_PROTECTION_MODE; + msg_in.session_id = arb_session_id; + + ret = intel_pxp_tee_io_message(pxp, + &msg_in, sizeof(msg_in), + &msg_out, sizeof(msg_out), + NULL); + + if (ret) + drm_err(&i915->drm, "Failed to send tee msg ret=[%d]\n", ret); + + return ret; +} diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_tee.h b/drivers/gpu/drm/i915/pxp/intel_pxp_tee.h index 23d050a5d3e7..c136053ce340 100644 --- a/drivers/gpu/drm/i915/pxp/intel_pxp_tee.h +++ b/drivers/gpu/drm/i915/pxp/intel_pxp_tee.h @@ -11,4 +11,7 @@ int intel_pxp_tee_component_init(struct intel_pxp *pxp); void intel_pxp_tee_component_fini(struct intel_pxp *pxp); +int intel_pxp_tee_cmd_create_arb_session(struct intel_pxp *pxp, + int arb_session_id); + #endif /* __INTEL_PXP_TEE_H__ */ diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_tee_interface.h b/drivers/gpu/drm/i915/pxp/intel_pxp_tee_interface.h new file mode 100644 index 000000000000..36e9b0868f5c --- /dev/null +++ b/drivers/gpu/drm/i915/pxp/intel_pxp_tee_interface.h @@ -0,0 +1,36 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright(c) 2020, Intel Corporation. All rights reserved. + */ + +#ifndef __INTEL_PXP_TEE_INTERFACE_H__ +#define __INTEL_PXP_TEE_INTERFACE_H__ + +#include + +#define PXP_TEE_APIVER 0x40002 +#define PXP_TEE_ARB_CMDID 0x1e +#define PXP_TEE_ARB_PROTECTION_MODE 0x2 + +/* PXP TEE message header */ +struct pxp_tee_cmd_header { + u32 api_version; + u32 command_id; + u32 status; + /* Length of the message (excluding the header) */ + u32 buffer_len; +} __packed; + +/* PXP TEE message input to create a arbitrary session */ +struct pxp_tee_create_arb_in { + struct pxp_tee_cmd_header header; + u32 protection_mode; + u32 session_id; +} __packed; + +/* PXP TEE message output to create a arbitrary session */ +struct pxp_tee_create_arb_out { + struct pxp_tee_cmd_header header; +} __packed; + +#endif /* __INTEL_PXP_TEE_INTERFACE_H__ */ diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_types.h b/drivers/gpu/drm/i915/pxp/intel_pxp_types.h index 3a8e17e591bd..d393e46a7d98 100644 --- a/drivers/gpu/drm/i915/pxp/intel_pxp_types.h +++ b/drivers/gpu/drm/i915/pxp/intel_pxp_types.h @@ -6,6 +6,7 @@ #ifndef __INTEL_PXP_TYPES_H__ #define __INTEL_PXP_TYPES_H__ +#include #include struct intel_context; @@ -16,6 +17,15 @@ struct intel_pxp { bool pxp_component_added; struct intel_context *ce; + + /* + * After a teardown, the arb session can still be in play on the HW + * even if the keys are gone, so we can't rely on the HW state of the + * session to know if it's valid and need to track the status in SW. + */ + bool arb_is_valid; + + struct mutex tee_mutex; /* protects the tee channel binding */ }; #endif /* __INTEL_PXP_TYPES_H__ */ diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h index bde5860b3686..920e9e852e5a 100644 --- a/include/uapi/drm/i915_drm.h +++ b/include/uapi/drm/i915_drm.h @@ -3038,6 +3038,9 @@ struct drm_i915_gem_create_ext_memory_regions { __u64 regions; }; +/* ID of the protected content session managed by i915 when PXP is active */ +#define I915_PROTECTED_CONTENT_DEFAULT_SESSION 0xf + #if defined(__cplusplus) } #endif -- cgit v1.2.3 From d3ac8d42168a9be7380be8035df8b6d3780ec2a1 Mon Sep 17 00:00:00 2001 From: Daniele Ceraolo Spurio Date: Fri, 24 Sep 2021 12:14:45 -0700 Subject: drm/i915/pxp: interfaces for using protected objects This api allow user mode to create protected buffers and to mark contexts as making use of such objects. Only when using contexts marked in such a way is the execution guaranteed to work as expected. Contexts can only be marked as using protected content at creation time (i.e. the parameter is immutable) and they must be both bannable and not recoverable. Given that the protected session gets invalidated on suspend, contexts created this way hold a runtime pm wakeref until they're either destroyed or invalidated. All protected objects and contexts will be considered invalid when the PXP session is destroyed and all new submissions using them will be rejected. All intel contexts within the invalidated gem contexts will be marked banned. Userspace can detect that an invalidation has occurred via the RESET_STATS ioctl, where we report it the same way as a ban due to a hang. v5: squash patches, rebase on proto_ctx, update kerneldoc v6: rebase on obj create_ext changes v7: Use session counter to check if an object it valid, hold wakeref in context, don't add a new flag to RESET_STATS (Daniel) v8: don't increase guilty count for contexts banned during pxp invalidation (Rodrigo) v9: better comments, avoid wakeref put race between pxp_inval and context_close, add usage examples (Rodrigo) v10: modify internal set/get-protected-context functions to not return -ENODEV when setting PXP param to false or getting param when running on pxp-unsupported hw or getting param when i915 was built with CONFIG_PXP off Signed-off-by: Alan Previn Signed-off-by: Daniele Ceraolo Spurio Signed-off-by: Bommu Krishnaiah Cc: Rodrigo Vivi Cc: Chris Wilson Cc: Lionel Landwerlin Cc: Jason Ekstrand Cc: Daniel Vetter Reviewed-by: Rodrigo Vivi Signed-off-by: Rodrigo Vivi Link: https://patchwork.freedesktop.org/patch/msgid/20210924191452.1539378-11-alan.previn.teres.alexis@intel.com --- drivers/gpu/drm/i915/gem/i915_gem_context.c | 95 +++++++++++++++++++---- drivers/gpu/drm/i915/gem/i915_gem_context.h | 6 ++ drivers/gpu/drm/i915/gem/i915_gem_context_types.h | 28 +++++++ drivers/gpu/drm/i915/gem/i915_gem_create.c | 72 ++++++++++++----- drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c | 18 +++++ drivers/gpu/drm/i915/gem/i915_gem_object.c | 1 + drivers/gpu/drm/i915/gem/i915_gem_object.h | 6 ++ drivers/gpu/drm/i915/gem/i915_gem_object_types.h | 9 ++- drivers/gpu/drm/i915/gem/selftests/mock_context.c | 4 +- drivers/gpu/drm/i915/pxp/intel_pxp.c | 77 ++++++++++++++++++ drivers/gpu/drm/i915/pxp/intel_pxp.h | 12 +++ drivers/gpu/drm/i915/pxp/intel_pxp_session.c | 6 ++ drivers/gpu/drm/i915/pxp/intel_pxp_types.h | 9 +++ include/uapi/drm/i915_drm.h | 94 ++++++++++++++++++++++ 14 files changed, 402 insertions(+), 35 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 8208fd5b72c3..08360d6bbd1e 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_context.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c @@ -77,6 +77,8 @@ #include "gt/intel_gpu_commands.h" #include "gt/intel_ring.h" +#include "pxp/intel_pxp.h" + #include "i915_gem_context.h" #include "i915_trace.h" #include "i915_user_extensions.h" @@ -186,10 +188,13 @@ static int validate_priority(struct drm_i915_private *i915, return 0; } -static void proto_context_close(struct i915_gem_proto_context *pc) +static void proto_context_close(struct drm_i915_private *i915, + struct i915_gem_proto_context *pc) { int i; + if (pc->pxp_wakeref) + intel_runtime_pm_put(&i915->runtime_pm, pc->pxp_wakeref); if (pc->vm) i915_vm_put(pc->vm); if (pc->user_engines) { @@ -241,6 +246,33 @@ static int proto_context_set_persistence(struct drm_i915_private *i915, return 0; } +static int proto_context_set_protected(struct drm_i915_private *i915, + struct i915_gem_proto_context *pc, + bool protected) +{ + int ret = 0; + + if (!protected) { + pc->uses_protected_content = false; + } else if (!intel_pxp_is_enabled(&i915->gt.pxp)) { + ret = -ENODEV; + } else if ((pc->user_flags & BIT(UCONTEXT_RECOVERABLE)) || + !(pc->user_flags & BIT(UCONTEXT_BANNABLE))) { + ret = -EPERM; + } else { + pc->uses_protected_content = true; + + /* + * protected context usage requires the PXP session to be up, + * which in turn requires the device to be active. + */ + pc->pxp_wakeref = intel_runtime_pm_get(&i915->runtime_pm); + ret = intel_pxp_wait_for_arb_start(&i915->gt.pxp); + } + + return ret; +} + static struct i915_gem_proto_context * proto_context_create(struct drm_i915_private *i915, unsigned int flags) { @@ -269,7 +301,7 @@ proto_context_create(struct drm_i915_private *i915, unsigned int flags) return pc; proto_close: - proto_context_close(pc); + proto_context_close(i915, pc); return err; } @@ -693,6 +725,8 @@ static int set_proto_ctx_param(struct drm_i915_file_private *fpriv, ret = -EPERM; else if (args->value) pc->user_flags |= BIT(UCONTEXT_BANNABLE); + else if (pc->uses_protected_content) + ret = -EPERM; else pc->user_flags &= ~BIT(UCONTEXT_BANNABLE); break; @@ -700,10 +734,12 @@ static int set_proto_ctx_param(struct drm_i915_file_private *fpriv, case I915_CONTEXT_PARAM_RECOVERABLE: if (args->size) ret = -EINVAL; - else if (args->value) - pc->user_flags |= BIT(UCONTEXT_RECOVERABLE); - else + else if (!args->value) pc->user_flags &= ~BIT(UCONTEXT_RECOVERABLE); + else if (pc->uses_protected_content) + ret = -EPERM; + else + pc->user_flags |= BIT(UCONTEXT_RECOVERABLE); break; case I915_CONTEXT_PARAM_PRIORITY: @@ -731,6 +767,11 @@ static int set_proto_ctx_param(struct drm_i915_file_private *fpriv, args->value); break; + case I915_CONTEXT_PARAM_PROTECTED_CONTENT: + ret = proto_context_set_protected(fpriv->dev_priv, pc, + args->value); + break; + case I915_CONTEXT_PARAM_NO_ZEROMAP: case I915_CONTEXT_PARAM_BAN_PERIOD: case I915_CONTEXT_PARAM_RINGSIZE: @@ -956,6 +997,9 @@ static void i915_gem_context_release_work(struct work_struct *work) if (vm) i915_vm_put(vm); + if (ctx->pxp_wakeref) + intel_runtime_pm_put(&ctx->i915->runtime_pm, ctx->pxp_wakeref); + mutex_destroy(&ctx->engines_mutex); mutex_destroy(&ctx->lut_mutex); @@ -1338,6 +1382,11 @@ i915_gem_create_context(struct drm_i915_private *i915, goto err_engines; } + if (pc->uses_protected_content) { + ctx->pxp_wakeref = intel_runtime_pm_get(&i915->runtime_pm); + ctx->uses_protected_content = true; + } + trace_i915_context_create(ctx); return ctx; @@ -1409,7 +1458,7 @@ int i915_gem_context_open(struct drm_i915_private *i915, } ctx = i915_gem_create_context(i915, pc); - proto_context_close(pc); + proto_context_close(i915, pc); if (IS_ERR(ctx)) { err = PTR_ERR(ctx); goto err; @@ -1436,7 +1485,7 @@ void i915_gem_context_close(struct drm_file *file) unsigned long idx; xa_for_each(&file_priv->proto_context_xa, idx, pc) - proto_context_close(pc); + proto_context_close(file_priv->dev_priv, pc); xa_destroy(&file_priv->proto_context_xa); mutex_destroy(&file_priv->proto_context_lock); @@ -1731,6 +1780,15 @@ static int set_priority(struct i915_gem_context *ctx, return 0; } +static int get_protected(struct i915_gem_context *ctx, + struct drm_i915_gem_context_param *args) +{ + args->size = 0; + args->value = i915_gem_context_uses_protected_content(ctx); + + return 0; +} + static int ctx_setparam(struct drm_i915_file_private *fpriv, struct i915_gem_context *ctx, struct drm_i915_gem_context_param *args) @@ -1754,6 +1812,8 @@ static int ctx_setparam(struct drm_i915_file_private *fpriv, ret = -EPERM; else if (args->value) i915_gem_context_set_bannable(ctx); + else if (i915_gem_context_uses_protected_content(ctx)) + ret = -EPERM; /* can't clear this for protected contexts */ else i915_gem_context_clear_bannable(ctx); break; @@ -1761,10 +1821,12 @@ static int ctx_setparam(struct drm_i915_file_private *fpriv, case I915_CONTEXT_PARAM_RECOVERABLE: if (args->size) ret = -EINVAL; - else if (args->value) - i915_gem_context_set_recoverable(ctx); - else + else if (!args->value) i915_gem_context_clear_recoverable(ctx); + else if (i915_gem_context_uses_protected_content(ctx)) + ret = -EPERM; /* can't set this for protected contexts */ + else + i915_gem_context_set_recoverable(ctx); break; case I915_CONTEXT_PARAM_PRIORITY: @@ -1779,6 +1841,7 @@ static int ctx_setparam(struct drm_i915_file_private *fpriv, ret = set_persistence(ctx, args); break; + case I915_CONTEXT_PARAM_PROTECTED_CONTENT: case I915_CONTEXT_PARAM_NO_ZEROMAP: case I915_CONTEXT_PARAM_BAN_PERIOD: case I915_CONTEXT_PARAM_RINGSIZE: @@ -1857,7 +1920,7 @@ finalize_create_context_locked(struct drm_i915_file_private *file_priv, old = xa_erase(&file_priv->proto_context_xa, id); GEM_BUG_ON(old != pc); - proto_context_close(pc); + proto_context_close(file_priv->dev_priv, pc); /* One for the xarray and one for the caller */ return i915_gem_context_get(ctx); @@ -1943,7 +2006,7 @@ int i915_gem_context_create_ioctl(struct drm_device *dev, void *data, goto err_pc; } - proto_context_close(ext_data.pc); + proto_context_close(i915, ext_data.pc); gem_context_register(ctx, ext_data.fpriv, id); } else { ret = proto_context_register(ext_data.fpriv, ext_data.pc, &id); @@ -1957,7 +2020,7 @@ int i915_gem_context_create_ioctl(struct drm_device *dev, void *data, return 0; err_pc: - proto_context_close(ext_data.pc); + proto_context_close(i915, ext_data.pc); return ret; } @@ -1988,7 +2051,7 @@ int i915_gem_context_destroy_ioctl(struct drm_device *dev, void *data, GEM_WARN_ON(ctx && pc); if (pc) - proto_context_close(pc); + proto_context_close(file_priv->dev_priv, pc); if (ctx) context_close(ctx); @@ -2106,6 +2169,10 @@ int i915_gem_context_getparam_ioctl(struct drm_device *dev, void *data, args->value = i915_gem_context_is_persistent(ctx); break; + case I915_CONTEXT_PARAM_PROTECTED_CONTENT: + ret = get_protected(ctx, args); + break; + case I915_CONTEXT_PARAM_NO_ZEROMAP: case I915_CONTEXT_PARAM_BAN_PERIOD: case I915_CONTEXT_PARAM_ENGINES: diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.h b/drivers/gpu/drm/i915/gem/i915_gem_context.h index d3279086a5e7..babfecb17ad1 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_context.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_context.h @@ -108,6 +108,12 @@ i915_gem_context_clear_user_engines(struct i915_gem_context *ctx) clear_bit(CONTEXT_USER_ENGINES, &ctx->flags); } +static inline bool +i915_gem_context_uses_protected_content(const struct i915_gem_context *ctx) +{ + return ctx->uses_protected_content; +} + /* i915_gem_context.c */ void i915_gem_init__contexts(struct drm_i915_private *i915); 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 c4617e4d9fa9..a627b09c4680 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h @@ -198,6 +198,12 @@ struct i915_gem_proto_context { /** @single_timeline: See See &i915_gem_context.syncobj */ bool single_timeline; + + /** @uses_protected_content: See &i915_gem_context.uses_protected_content */ + bool uses_protected_content; + + /** @pxp_wakeref: See &i915_gem_context.pxp_wakeref */ + intel_wakeref_t pxp_wakeref; }; /** @@ -321,6 +327,28 @@ struct i915_gem_context { #define CONTEXT_CLOSED 0 #define CONTEXT_USER_ENGINES 1 + /** + * @uses_protected_content: context uses PXP-encrypted objects. + * + * This flag can only be set at ctx creation time and it's immutable for + * the lifetime of the context. See I915_CONTEXT_PARAM_PROTECTED_CONTENT + * in uapi/drm/i915_drm.h for more info on setting restrictions and + * expected behaviour of marked contexts. + */ + bool uses_protected_content; + + /** + * @pxp_wakeref: wakeref to keep the device awake when PXP is in use + * + * PXP sessions are invalidated when the device is suspended, which in + * turns invalidates all contexts and objects using it. To keep the + * flow simple, we keep the device awake when contexts using PXP objects + * are in use. It is expected that the userspace application only uses + * PXP when the display is on, so taking a wakeref here shouldn't worsen + * our power metrics. + */ + intel_wakeref_t pxp_wakeref; + /** @mutex: guards everything that isn't engines or handles_vma */ struct mutex mutex; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_create.c b/drivers/gpu/drm/i915/gem/i915_gem_create.c index 1d341b8c47c0..8955d6abcef1 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_create.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_create.c @@ -6,6 +6,7 @@ #include "gem/i915_gem_ioctls.h" #include "gem/i915_gem_lmem.h" #include "gem/i915_gem_region.h" +#include "pxp/intel_pxp.h" #include "i915_drv.h" #include "i915_trace.h" @@ -82,21 +83,11 @@ static int i915_gem_publish(struct drm_i915_gem_object *obj, return 0; } -/** - * Creates a new object using the same path as DRM_I915_GEM_CREATE_EXT - * @i915: i915 private - * @size: size of the buffer, in bytes - * @placements: possible placement regions, in priority order - * @n_placements: number of possible placement regions - * - * This function is exposed primarily for selftests and does very little - * error checking. It is assumed that the set of placement regions has - * already been verified to be valid. - */ -struct drm_i915_gem_object * -__i915_gem_object_create_user(struct drm_i915_private *i915, u64 size, - struct intel_memory_region **placements, - unsigned int n_placements) +static struct drm_i915_gem_object * +__i915_gem_object_create_user_ext(struct drm_i915_private *i915, u64 size, + struct intel_memory_region **placements, + unsigned int n_placements, + unsigned int ext_flags) { struct intel_memory_region *mr = placements[0]; struct drm_i915_gem_object *obj; @@ -135,6 +126,9 @@ __i915_gem_object_create_user(struct drm_i915_private *i915, u64 size, GEM_BUG_ON(size != obj->base.size); + /* Add any flag set by create_ext options */ + obj->flags |= ext_flags; + trace_i915_gem_object_create(obj); return obj; @@ -145,6 +139,26 @@ object_free: return ERR_PTR(ret); } +/** + * Creates a new object using the same path as DRM_I915_GEM_CREATE_EXT + * @i915: i915 private + * @size: size of the buffer, in bytes + * @placements: possible placement regions, in priority order + * @n_placements: number of possible placement regions + * + * This function is exposed primarily for selftests and does very little + * error checking. It is assumed that the set of placement regions has + * already been verified to be valid. + */ +struct drm_i915_gem_object * +__i915_gem_object_create_user(struct drm_i915_private *i915, u64 size, + struct intel_memory_region **placements, + unsigned int n_placements) +{ + return __i915_gem_object_create_user_ext(i915, size, placements, + n_placements, 0); +} + int i915_gem_dumb_create(struct drm_file *file, struct drm_device *dev, @@ -224,6 +238,7 @@ struct create_ext { struct drm_i915_private *i915; struct intel_memory_region *placements[INTEL_REGION_UNKNOWN]; unsigned int n_placements; + unsigned long flags; }; static void repr_placements(char *buf, size_t size, @@ -353,8 +368,28 @@ static int ext_set_placements(struct i915_user_extension __user *base, return set_placements(&ext, data); } +static int ext_set_protected(struct i915_user_extension __user *base, void *data) +{ + struct drm_i915_gem_create_ext_protected_content ext; + struct create_ext *ext_data = data; + + if (copy_from_user(&ext, base, sizeof(ext))) + return -EFAULT; + + if (ext.flags) + return -EINVAL; + + if (!intel_pxp_is_enabled(&ext_data->i915->gt.pxp)) + return -ENODEV; + + ext_data->flags |= I915_BO_PROTECTED; + + return 0; +} + static const i915_user_extension_fn create_extensions[] = { [I915_GEM_CREATE_EXT_MEMORY_REGIONS] = ext_set_placements, + [I915_GEM_CREATE_EXT_PROTECTED_CONTENT] = ext_set_protected, }; /** @@ -389,9 +424,10 @@ i915_gem_create_ext_ioctl(struct drm_device *dev, void *data, ext_data.n_placements = 1; } - obj = __i915_gem_object_create_user(i915, args->size, - ext_data.placements, - ext_data.n_placements); + obj = __i915_gem_object_create_user_ext(i915, args->size, + ext_data.placements, + ext_data.n_placements, + ext_data.flags); if (IS_ERR(obj)) return PTR_ERR(obj); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c index c2f74dba0557..9447ce6ea500 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c @@ -21,6 +21,8 @@ #include "gt/intel_gt_pm.h" #include "gt/intel_ring.h" +#include "pxp/intel_pxp.h" + #include "i915_drv.h" #include "i915_gem_clflush.h" #include "i915_gem_context.h" @@ -810,6 +812,22 @@ static struct i915_vma *eb_lookup_vma(struct i915_execbuffer *eb, u32 handle) if (unlikely(!obj)) return ERR_PTR(-ENOENT); + /* + * If the user has opted-in for protected-object tracking, make + * sure the object encryption can be used. + * We only need to do this when the object is first used with + * this context, because the context itself will be banned when + * the protected objects become invalid. + */ + if (i915_gem_context_uses_protected_content(eb->gem_context) && + i915_gem_object_is_protected(obj)) { + err = intel_pxp_key_check(&vm->gt->pxp, obj); + if (err) { + i915_gem_object_put(obj); + return ERR_PTR(err); + } + } + vma = i915_vma_instance(obj, vm, NULL); if (IS_ERR(vma)) { i915_gem_object_put(obj); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.c b/drivers/gpu/drm/i915/gem/i915_gem_object.c index b88b121e244a..76ce6a1500bc 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_object.c @@ -25,6 +25,7 @@ #include #include "display/intel_frontbuffer.h" +#include "pxp/intel_pxp.h" #include "i915_drv.h" #include "i915_gem_clflush.h" #include "i915_gem_context.h" diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h index 7f9f2e5ba0ec..9df3ee60604e 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h @@ -272,6 +272,12 @@ i915_gem_object_clear_tiling_quirk(struct drm_i915_gem_object *obj) clear_bit(I915_TILING_QUIRK_BIT, &obj->flags); } +static inline bool +i915_gem_object_is_protected(const struct drm_i915_gem_object *obj) +{ + return obj->flags & I915_BO_PROTECTED; +} + static inline bool i915_gem_object_type_has(const struct drm_i915_gem_object *obj, unsigned long flags) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h index fa2ba9e2a4d0..7c3da4e3e737 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h @@ -304,7 +304,7 @@ struct drm_i915_gem_object { I915_BO_ALLOC_PM_EARLY) #define I915_BO_READONLY BIT(6) #define I915_TILING_QUIRK_BIT 7 /* unknown swizzling; do not release! */ - +#define I915_BO_PROTECTED BIT(8) /** * @mem_flags - Mutable placement-related flags * @@ -544,6 +544,13 @@ struct drm_i915_gem_object { bool created:1; } ttm; + /* + * Record which PXP key instance this object was created against (if + * any), so we can use it to determine if the encryption is valid by + * comparing against the current key instance. + */ + u32 pxp_key_instance; + /** Record of address bit 17 of each page at last unbind. */ unsigned long *bit_17; diff --git a/drivers/gpu/drm/i915/gem/selftests/mock_context.c b/drivers/gpu/drm/i915/gem/selftests/mock_context.c index 067d68a6fe4c..c0a8ef368044 100644 --- a/drivers/gpu/drm/i915/gem/selftests/mock_context.c +++ b/drivers/gpu/drm/i915/gem/selftests/mock_context.c @@ -88,7 +88,7 @@ live_context(struct drm_i915_private *i915, struct file *file) return ERR_CAST(pc); ctx = i915_gem_create_context(i915, pc); - proto_context_close(pc); + proto_context_close(i915, pc); if (IS_ERR(ctx)) return ctx; @@ -163,7 +163,7 @@ kernel_context(struct drm_i915_private *i915, } ctx = i915_gem_create_context(i915, pc); - proto_context_close(pc); + proto_context_close(i915, pc); if (IS_ERR(ctx)) return ctx; diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp.c b/drivers/gpu/drm/i915/pxp/intel_pxp.c index 2e188217c3b7..ee507fd8ae19 100644 --- a/drivers/gpu/drm/i915/pxp/intel_pxp.c +++ b/drivers/gpu/drm/i915/pxp/intel_pxp.c @@ -7,6 +7,7 @@ #include "intel_pxp_irq.h" #include "intel_pxp_session.h" #include "intel_pxp_tee.h" +#include "gem/i915_gem_context.h" #include "gt/intel_context.h" #include "i915_drv.h" @@ -178,3 +179,79 @@ void intel_pxp_fini_hw(struct intel_pxp *pxp) intel_pxp_irq_disable(pxp); } + +int intel_pxp_key_check(struct intel_pxp *pxp, struct drm_i915_gem_object *obj) +{ + if (!intel_pxp_is_active(pxp)) + return -ENODEV; + + if (!i915_gem_object_is_protected(obj)) + return -EINVAL; + + GEM_BUG_ON(!pxp->key_instance); + + /* + * If this is the first time we're using this object, it's not + * encrypted yet; it will be encrypted with the current key, so mark it + * as such. If the object is already encrypted, check instead if the + * used key is still valid. + */ + if (!obj->pxp_key_instance) + obj->pxp_key_instance = pxp->key_instance; + else if (obj->pxp_key_instance != pxp->key_instance) + return -ENOEXEC; + + return 0; +} + +void intel_pxp_invalidate(struct intel_pxp *pxp) +{ + struct drm_i915_private *i915 = pxp_to_gt(pxp)->i915; + struct i915_gem_context *ctx, *cn; + + /* ban all contexts marked as protected */ + spin_lock_irq(&i915->gem.contexts.lock); + list_for_each_entry_safe(ctx, cn, &i915->gem.contexts.list, link) { + struct i915_gem_engines_iter it; + struct intel_context *ce; + + if (!kref_get_unless_zero(&ctx->ref)) + continue; + + if (likely(!i915_gem_context_uses_protected_content(ctx))) { + i915_gem_context_put(ctx); + continue; + } + + spin_unlock_irq(&i915->gem.contexts.lock); + + /* + * By the time we get here we are either going to suspend with + * quiesced execution or the HW keys are already long gone and + * in this case it is worthless to attempt to close the context + * and wait for its execution. It will hang the GPU if it has + * not already. So, as a fast mitigation, we can ban the + * context as quick as we can. That might race with the + * execbuffer, but currently this is the best that can be done. + */ + for_each_gem_engine(ce, i915_gem_context_lock_engines(ctx), it) + intel_context_ban(ce, NULL); + i915_gem_context_unlock_engines(ctx); + + /* + * The context has been banned, no need to keep the wakeref. + * This is safe from races because the only other place this + * is touched is context_release and we're holding a ctx ref + */ + if (ctx->pxp_wakeref) { + intel_runtime_pm_put(&i915->runtime_pm, + ctx->pxp_wakeref); + ctx->pxp_wakeref = 0; + } + + spin_lock_irq(&i915->gem.contexts.lock); + list_safe_reset_next(ctx, cn, link); + i915_gem_context_put(ctx); + } + spin_unlock_irq(&i915->gem.contexts.lock); +} diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp.h b/drivers/gpu/drm/i915/pxp/intel_pxp.h index 54b268280379..430f01ea9860 100644 --- a/drivers/gpu/drm/i915/pxp/intel_pxp.h +++ b/drivers/gpu/drm/i915/pxp/intel_pxp.h @@ -8,6 +8,8 @@ #include "intel_pxp_types.h" +struct drm_i915_gem_object; + static inline bool intel_pxp_is_enabled(const struct intel_pxp *pxp) { return pxp->ce; @@ -25,6 +27,10 @@ void intel_pxp_fini_hw(struct intel_pxp *pxp); void intel_pxp_mark_termination_in_progress(struct intel_pxp *pxp); int intel_pxp_wait_for_arb_start(struct intel_pxp *pxp); + +int intel_pxp_key_check(struct intel_pxp *pxp, struct drm_i915_gem_object *obj); + +void intel_pxp_invalidate(struct intel_pxp *pxp); #else static inline void intel_pxp_init(struct intel_pxp *pxp) { @@ -38,6 +44,12 @@ static inline int intel_pxp_wait_for_arb_start(struct intel_pxp *pxp) { return -ENODEV; } + +static inline int intel_pxp_key_check(struct intel_pxp *pxp, + struct drm_i915_gem_object *obj) +{ + return -ENODEV; +} #endif #endif /* __INTEL_PXP_H__ */ diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_session.c b/drivers/gpu/drm/i915/pxp/intel_pxp_session.c index 67c30e534d50..c6a5e4197e40 100644 --- a/drivers/gpu/drm/i915/pxp/intel_pxp_session.c +++ b/drivers/gpu/drm/i915/pxp/intel_pxp_session.c @@ -72,6 +72,9 @@ static int pxp_create_arb_session(struct intel_pxp *pxp) return ret; } + if (!++pxp->key_instance) + ++pxp->key_instance; + pxp->arb_is_valid = true; return 0; @@ -85,6 +88,9 @@ static int pxp_terminate_arb_session_and_global(struct intel_pxp *pxp) /* must mark termination in progress calling this function */ GEM_WARN_ON(pxp->arb_is_valid); + /* invalidate protected objects */ + intel_pxp_invalidate(pxp); + /* terminate the hw sessions */ ret = intel_pxp_terminate_session(pxp, ARB_SESSION); if (ret) { diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_types.h b/drivers/gpu/drm/i915/pxp/intel_pxp_types.h index 5a170e43c959..c394ab2e452b 100644 --- a/drivers/gpu/drm/i915/pxp/intel_pxp_types.h +++ b/drivers/gpu/drm/i915/pxp/intel_pxp_types.h @@ -7,7 +7,9 @@ #define __INTEL_PXP_TYPES_H__ #include +#include #include +#include #include #include @@ -27,6 +29,13 @@ struct intel_pxp { */ bool arb_is_valid; + /* + * Keep track of which key instance we're on, so we can use it to + * determine if an object was created using the current key or a + * previous one. + */ + u32 key_instance; + struct mutex tee_mutex; /* protects the tee channel binding */ /* diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h index 920e9e852e5a..aa2a7eccfb94 100644 --- a/include/uapi/drm/i915_drm.h +++ b/include/uapi/drm/i915_drm.h @@ -1846,6 +1846,55 @@ struct drm_i915_gem_context_param { * attempted to use it, never re-use this context param number. */ #define I915_CONTEXT_PARAM_RINGSIZE 0xc + +/* + * I915_CONTEXT_PARAM_PROTECTED_CONTENT: + * + * Mark that the context makes use of protected content, which will result + * in the context being invalidated when the protected content session is. + * Given that the protected content session is killed on suspend, the device + * is kept awake for the lifetime of a protected context, so the user should + * make sure to dispose of them once done. + * This flag can only be set at context creation time and, when set to true, + * must be preceded by an explicit setting of I915_CONTEXT_PARAM_RECOVERABLE + * to false. This flag can't be set to true in conjunction with setting the + * I915_CONTEXT_PARAM_BANNABLE flag to false. Creation example: + * + * .. code-block:: C + * + * struct drm_i915_gem_context_create_ext_setparam p_protected = { + * .base = { + * .name = I915_CONTEXT_CREATE_EXT_SETPARAM, + * }, + * .param = { + * .param = I915_CONTEXT_PARAM_PROTECTED_CONTENT, + * .value = 1, + * } + * }; + * struct drm_i915_gem_context_create_ext_setparam p_norecover = { + * .base = { + * .name = I915_CONTEXT_CREATE_EXT_SETPARAM, + * .next_extension = to_user_pointer(&p_protected), + * }, + * .param = { + * .param = I915_CONTEXT_PARAM_RECOVERABLE, + * .value = 0, + * } + * }; + * struct drm_i915_gem_context_create_ext create = { + * .flags = I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS, + * .extensions = to_user_pointer(&p_norecover); + * }; + * + * ctx_id = gem_context_create_ext(drm_fd, &create); + * + * In addition to the normal failure cases, setting this flag during context + * creation can result in the following errors: + * + * -ENODEV: feature not available + * -EPERM: trying to mark a recoverable or not bannable context as protected + */ +#define I915_CONTEXT_PARAM_PROTECTED_CONTENT 0xd /* Must be kept compact -- no holes and well documented */ __u64 value; @@ -2979,8 +3028,12 @@ struct drm_i915_gem_create_ext { * * For I915_GEM_CREATE_EXT_MEMORY_REGIONS usage see * struct drm_i915_gem_create_ext_memory_regions. + * + * For I915_GEM_CREATE_EXT_PROTECTED_CONTENT usage see + * struct drm_i915_gem_create_ext_protected_content. */ #define I915_GEM_CREATE_EXT_MEMORY_REGIONS 0 +#define I915_GEM_CREATE_EXT_PROTECTED_CONTENT 1 __u64 extensions; }; @@ -3038,6 +3091,47 @@ struct drm_i915_gem_create_ext_memory_regions { __u64 regions; }; +/** + * struct drm_i915_gem_create_ext_protected_content - The + * I915_OBJECT_PARAM_PROTECTED_CONTENT extension. + * + * If this extension is provided, buffer contents are expected to be protected + * by PXP encryption and require decryption for scan out and processing. This + * is only possible on platforms that have PXP enabled, on all other scenarios + * using this extension will cause the ioctl to fail and return -ENODEV. The + * flags parameter is reserved for future expansion and must currently be set + * to zero. + * + * The buffer contents are considered invalid after a PXP session teardown. + * + * The encryption is guaranteed to be processed correctly only if the object + * is submitted with a context created using the + * I915_CONTEXT_PARAM_PROTECTED_CONTENT flag. This will also enable extra checks + * at submission time on the validity of the objects involved. + * + * Below is an example on how to create a protected object: + * + * .. code-block:: C + * + * struct drm_i915_gem_create_ext_protected_content protected_ext = { + * .base = { .name = I915_GEM_CREATE_EXT_PROTECTED_CONTENT }, + * .flags = 0, + * }; + * struct drm_i915_gem_create_ext create_ext = { + * .size = PAGE_SIZE, + * .extensions = (uintptr_t)&protected_ext, + * }; + * + * int err = ioctl(fd, DRM_IOCTL_I915_GEM_CREATE_EXT, &create_ext); + * if (err) ... + */ +struct drm_i915_gem_create_ext_protected_content { + /** @base: Extension link. See struct i915_user_extension. */ + struct i915_user_extension base; + /** @flags: reserved for future usage, currently MBZ */ + __u32 flags; +}; + /* ID of the protected content session managed by i915 when PXP is active */ #define I915_PROTECTED_CONTENT_DEFAULT_SESSION 0xf -- cgit v1.2.3 From 3ae695d691749aba2a15b2b0a3b2c6117d4bd247 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Mon, 9 Aug 2021 17:26:21 -0400 Subject: drm/amdgpu: add new asic_type for IP discovery MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add a new asic type for asics where we don't have an explicit entry in the PCI ID list. We don't need an asic type for these asics, other than something higher than the existing ones, so just use this for all new asics. Reviewed-by: Christian König Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 1 + include/drm/amd_asic_type.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 31c6d44208b5..9cecdf063111 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -125,6 +125,7 @@ const char *amdgpu_asic_name[] = { "DIMGREY_CAVEFISH", "BEIGE_GOBY", "YELLOW_CARP", + "IP DISCOVERY", "LAST", }; diff --git a/include/drm/amd_asic_type.h b/include/drm/amd_asic_type.h index 0f66a0d9f06d..90b69270f2fa 100644 --- a/include/drm/amd_asic_type.h +++ b/include/drm/amd_asic_type.h @@ -62,6 +62,7 @@ enum amd_asic_type { CHIP_DIMGREY_CAVEFISH, /* 33 */ CHIP_BEIGE_GOBY, /* 34 */ CHIP_YELLOW_CARP, /* 35 */ + CHIP_IP_DISCOVERY, /* 36 */ CHIP_LAST, }; -- cgit v1.2.3 From c921ff373b469ad7907cde219fa700909f59cac4 Mon Sep 17 00:00:00 2001 From: Christian König Date: Tue, 15 Jun 2021 15:10:03 +0200 Subject: dma-buf: add dma_resv_for_each_fence_unlocked v8 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Abstract the complexity of iterating over all the fences in a dma_resv object. The new loop handles the whole RCU and retry dance and returns only fences where we can be sure we grabbed the right one. v2: fix accessing the shared fences while they might be freed, improve kerneldoc, rename _cursor to _iter, add dma_resv_iter_is_exclusive, add dma_resv_iter_begin/end v3: restructor the code, move rcu_read_lock()/unlock() into the iterator, add dma_resv_iter_is_restarted() v4: fix NULL deref when no explicit fence exists, drop superflous rcu_read_lock()/unlock() calls. v5: fix typos in the documentation v6: fix coding error when excl fence is NULL v7: one more logic fix v8: fix index check in dma_resv_iter_is_exclusive() Signed-off-by: Christian König Reviewed-by: Tvrtko Ursulin (v7) Link: https://patchwork.freedesktop.org/patch/msgid/20211005113742.1101-2-christian.koenig@amd.com --- drivers/dma-buf/dma-resv.c | 100 +++++++++++++++++++++++++++++++++++++++++++++ include/linux/dma-resv.h | 95 ++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 195 insertions(+) (limited to 'include') diff --git a/drivers/dma-buf/dma-resv.c b/drivers/dma-buf/dma-resv.c index 84fbe60629e3..3cbcf66a137e 100644 --- a/drivers/dma-buf/dma-resv.c +++ b/drivers/dma-buf/dma-resv.c @@ -323,6 +323,106 @@ void dma_resv_add_excl_fence(struct dma_resv *obj, struct dma_fence *fence) } EXPORT_SYMBOL(dma_resv_add_excl_fence); +/** + * dma_resv_iter_restart_unlocked - restart the unlocked iterator + * @cursor: The dma_resv_iter object to restart + * + * Restart the unlocked iteration by initializing the cursor object. + */ +static void dma_resv_iter_restart_unlocked(struct dma_resv_iter *cursor) +{ + cursor->seq = read_seqcount_begin(&cursor->obj->seq); + cursor->index = -1; + if (cursor->all_fences) + cursor->fences = dma_resv_shared_list(cursor->obj); + else + cursor->fences = NULL; + cursor->is_restarted = true; +} + +/** + * dma_resv_iter_walk_unlocked - walk over fences in a dma_resv obj + * @cursor: cursor to record the current position + * + * Return all the fences in the dma_resv object which are not yet signaled. + * The returned fence has an extra local reference so will stay alive. + * If a concurrent modify is detected the whole iteration is started over again. + */ +static void dma_resv_iter_walk_unlocked(struct dma_resv_iter *cursor) +{ + struct dma_resv *obj = cursor->obj; + + do { + /* Drop the reference from the previous round */ + dma_fence_put(cursor->fence); + + if (cursor->index == -1) { + cursor->fence = dma_resv_excl_fence(obj); + cursor->index++; + if (!cursor->fence) + continue; + + } else if (!cursor->fences || + cursor->index >= cursor->fences->shared_count) { + cursor->fence = NULL; + break; + + } else { + struct dma_resv_list *fences = cursor->fences; + unsigned int idx = cursor->index++; + + cursor->fence = rcu_dereference(fences->shared[idx]); + } + cursor->fence = dma_fence_get_rcu(cursor->fence); + if (!cursor->fence || !dma_fence_is_signaled(cursor->fence)) + break; + } while (true); +} + +/** + * dma_resv_iter_first_unlocked - first fence in an unlocked dma_resv obj. + * @cursor: the cursor with the current position + * + * Returns the first fence from an unlocked dma_resv obj. + */ +struct dma_fence *dma_resv_iter_first_unlocked(struct dma_resv_iter *cursor) +{ + rcu_read_lock(); + do { + dma_resv_iter_restart_unlocked(cursor); + dma_resv_iter_walk_unlocked(cursor); + } while (read_seqcount_retry(&cursor->obj->seq, cursor->seq)); + rcu_read_unlock(); + + return cursor->fence; +} +EXPORT_SYMBOL(dma_resv_iter_first_unlocked); + +/** + * dma_resv_iter_next_unlocked - next fence in an unlocked dma_resv obj. + * @cursor: the cursor with the current position + * + * Returns the next fence from an unlocked dma_resv obj. + */ +struct dma_fence *dma_resv_iter_next_unlocked(struct dma_resv_iter *cursor) +{ + bool restart; + + rcu_read_lock(); + cursor->is_restarted = false; + restart = read_seqcount_retry(&cursor->obj->seq, cursor->seq); + do { + if (restart) + dma_resv_iter_restart_unlocked(cursor); + dma_resv_iter_walk_unlocked(cursor); + restart = true; + } while (read_seqcount_retry(&cursor->obj->seq, cursor->seq)); + rcu_read_unlock(); + + return cursor->fence; +} +EXPORT_SYMBOL(dma_resv_iter_next_unlocked); + /** * dma_resv_copy_fences - Copy all fences from src to dst. * @dst: the destination reservation object diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h index 9100dd3dc21f..764138ad8583 100644 --- a/include/linux/dma-resv.h +++ b/include/linux/dma-resv.h @@ -149,6 +149,101 @@ struct dma_resv { struct dma_resv_list __rcu *fence; }; +/** + * struct dma_resv_iter - current position into the dma_resv fences + * + * Don't touch this directly in the driver, use the accessor function instead. + */ +struct dma_resv_iter { + /** @obj: The dma_resv object we iterate over */ + struct dma_resv *obj; + + /** @all_fences: If all fences should be returned */ + bool all_fences; + + /** @fence: the currently handled fence */ + struct dma_fence *fence; + + /** @seq: sequence number to check for modifications */ + unsigned int seq; + + /** @index: index into the shared fences */ + unsigned int index; + + /** @fences: the shared fences */ + struct dma_resv_list *fences; + + /** @is_restarted: true if this is the first returned fence */ + bool is_restarted; +}; + +struct dma_fence *dma_resv_iter_first_unlocked(struct dma_resv_iter *cursor); +struct dma_fence *dma_resv_iter_next_unlocked(struct dma_resv_iter *cursor); + +/** + * dma_resv_iter_begin - initialize a dma_resv_iter object + * @cursor: The dma_resv_iter object to initialize + * @obj: The dma_resv object which we want to iterate over + * @all_fences: If all fences should be returned or just the exclusive one + */ +static inline void dma_resv_iter_begin(struct dma_resv_iter *cursor, + struct dma_resv *obj, + bool all_fences) +{ + cursor->obj = obj; + cursor->all_fences = all_fences; + cursor->fence = NULL; +} + +/** + * dma_resv_iter_end - cleanup a dma_resv_iter object + * @cursor: the dma_resv_iter object which should be cleaned up + * + * Make sure that the reference to the fence in the cursor is properly + * dropped. + */ +static inline void dma_resv_iter_end(struct dma_resv_iter *cursor) +{ + dma_fence_put(cursor->fence); +} + +/** + * dma_resv_iter_is_exclusive - test if the current fence is the exclusive one + * @cursor: the cursor of the current position + * + * Returns true if the currently returned fence is the exclusive one. + */ +static inline bool dma_resv_iter_is_exclusive(struct dma_resv_iter *cursor) +{ + return cursor->index == 0; +} + +/** + * dma_resv_iter_is_restarted - test if this is the first fence after a restart + * @cursor: the cursor with the current position + * + * Return true if this is the first fence in an iteration after a restart. + */ +static inline bool dma_resv_iter_is_restarted(struct dma_resv_iter *cursor) +{ + return cursor->is_restarted; +} + +/** + * dma_resv_for_each_fence_unlocked - unlocked fence iterator + * @cursor: a struct dma_resv_iter pointer + * @fence: the current fence + * + * Iterate over the fences in a struct dma_resv object without holding the + * &dma_resv.lock and using RCU instead. The cursor needs to be initialized + * with dma_resv_iter_begin() and cleaned up with dma_resv_iter_end(). Inside + * the iterator a reference to the dma_fence is held and the RCU lock dropped. + * When the dma_resv is modified the iteration starts over again. + */ +#define dma_resv_for_each_fence_unlocked(cursor, fence) \ + for (fence = dma_resv_iter_first_unlocked(cursor); \ + fence; fence = dma_resv_iter_next_unlocked(cursor)) + #define dma_resv_held(obj) lockdep_is_held(&(obj)->lock.base) #define dma_resv_assert_held(obj) lockdep_assert_held(&(obj)->lock.base) -- cgit v1.2.3