From 9a4903e49e495bfd2650862dfae4178bebe4db9c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 25 Jul 2019 17:56:46 -0700 Subject: mm/hmm: replace the block argument to hmm_range_fault with a flags value This allows easier expansion to other flags, and also makes the callers a little easier to read. Link: https://lore.kernel.org/r/20190726005650.2566-4-rcampbell@nvidia.com Signed-off-by: Christoph Hellwig Signed-off-by: Ralph Campbell Reviewed-by: Jason Gunthorpe Signed-off-by: Jason Gunthorpe --- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index e51b48ac48eb..12a59ac83f72 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -832,7 +832,7 @@ retry: down_read(&mm->mmap_sem); - r = hmm_range_fault(range, true); + r = hmm_range_fault(range, 0); if (unlikely(r < 0)) { if (likely(r == -EAGAIN)) { /* -- cgit v1.2.3 From ab2f7a5c18b5c17cc94aaab7ae2e7d1fa08993d6 Mon Sep 17 00:00:00 2001 From: Felix Kuehling Date: Tue, 9 Jul 2019 19:12:44 -0400 Subject: drm/amdgpu: Implement VRAM wipe on release MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Wipe VRAM memory containing sensitive data when moving or releasing BOs. Clearing the memory is pipelined to minimize any impact on subsequent memory allocation latency. Use of a poison value should help debug future use-after-free bugs. When moving BOs, the existing ttm_bo_pipelined_move ensures that the memory won't be reused before being wiped. When releasing BOs, the BO is fenced with the memory fill operation, which results in queuing the BO for a delayed delete. v2: Move amdgpu_amdkfd_unreserve_memory_limit into amdgpu_bo_release_notify so that KFD can use memory that's still being cleared in the background Signed-off-by: Felix Kuehling Reviewed-by: Christian König Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 39 +++++++++++++++++++++++++++--- drivers/gpu/drm/amd/amdgpu/amdgpu_object.h | 1 + drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 17 +++++++++++++ drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h | 2 ++ 4 files changed, 56 insertions(+), 3 deletions(-) (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index 531251dff150..0c0a8e83ab83 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -80,9 +80,6 @@ static void amdgpu_bo_destroy(struct ttm_buffer_object *tbo) if (bo->pin_count > 0) amdgpu_bo_subtract_pin_size(bo); - if (bo->kfd_bo) - amdgpu_amdkfd_unreserve_memory_limit(bo); - amdgpu_bo_kunmap(bo); if (bo->gem_base.import_attach) @@ -1220,6 +1217,42 @@ void amdgpu_bo_move_notify(struct ttm_buffer_object *bo, trace_amdgpu_bo_move(abo, new_mem->mem_type, old_mem->mem_type); } +/** + * amdgpu_bo_move_notify - notification about a BO being released + * @bo: pointer to a buffer object + * + * Wipes VRAM buffers whose contents should not be leaked before the + * memory is released. + */ +void amdgpu_bo_release_notify(struct ttm_buffer_object *bo) +{ + struct dma_fence *fence = NULL; + struct amdgpu_bo *abo; + int r; + + if (!amdgpu_bo_is_amdgpu_bo(bo)) + return; + + abo = ttm_to_amdgpu_bo(bo); + + if (abo->kfd_bo) + amdgpu_amdkfd_unreserve_memory_limit(abo); + + if (bo->mem.mem_type != TTM_PL_VRAM || !bo->mem.mm_node || + !(abo->flags & AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE)) + return; + + reservation_object_lock(bo->resv, NULL); + + r = amdgpu_fill_buffer(abo, AMDGPU_POISON, bo->resv, &fence); + if (!WARN_ON(r)) { + amdgpu_bo_fence(abo, fence, false); + dma_fence_put(fence); + } + + reservation_object_unlock(bo->resv); +} + /** * amdgpu_bo_fault_reserve_notify - notification about a memory fault * @bo: pointer to a buffer object diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h index dc44cf36d025..5a3c1779e200 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h @@ -265,6 +265,7 @@ int amdgpu_bo_get_metadata(struct amdgpu_bo *bo, void *buffer, void amdgpu_bo_move_notify(struct ttm_buffer_object *bo, bool evict, struct ttm_mem_reg *new_mem); +void amdgpu_bo_release_notify(struct ttm_buffer_object *bo); int amdgpu_bo_fault_reserve_notify(struct ttm_buffer_object *bo); void amdgpu_bo_fence(struct amdgpu_bo *bo, struct dma_fence *fence, bool shared); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 2bb9420b77a1..018d1d347896 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -444,6 +444,22 @@ static int amdgpu_move_blit(struct ttm_buffer_object *bo, if (r) goto error; + /* clear the space being freed */ + if (old_mem->mem_type == TTM_PL_VRAM && + (ttm_to_amdgpu_bo(bo)->flags & + AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE)) { + struct dma_fence *wipe_fence = NULL; + + r = amdgpu_fill_buffer(ttm_to_amdgpu_bo(bo), AMDGPU_POISON, + NULL, &wipe_fence); + if (r) { + goto error; + } else if (wipe_fence) { + dma_fence_put(fence); + fence = wipe_fence; + } + } + /* Always block for VM page tables before committing the new location */ if (bo->type == ttm_bo_type_kernel) r = ttm_bo_move_accel_cleanup(bo, fence, true, new_mem); @@ -1599,6 +1615,7 @@ static struct ttm_bo_driver amdgpu_bo_driver = { .move = &amdgpu_bo_move, .verify_access = &amdgpu_verify_access, .move_notify = &amdgpu_bo_move_notify, + .release_notify = &amdgpu_bo_release_notify, .fault_reserve_notify = &amdgpu_bo_fault_reserve_notify, .io_mem_reserve = &amdgpu_ttm_io_mem_reserve, .io_mem_free = &amdgpu_ttm_io_mem_free, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h index caa76c693700..bccb8c49e597 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h @@ -38,6 +38,8 @@ #define AMDGPU_GTT_MAX_TRANSFER_SIZE 512 #define AMDGPU_GTT_NUM_TRANSFER_WINDOWS 2 +#define AMDGPU_POISON 0xd0bed0be + struct amdgpu_mman { struct ttm_bo_device bdev; bool mem_global_referenced; -- cgit v1.2.3 From 9d0a16658f840335325508e06a797be1883e6c56 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 6 Aug 2019 19:05:39 +0300 Subject: amdgpu: remove -EAGAIN handling for hmm_range_fault hmm_range_fault can only return -EAGAIN if called with the HMM_FAULT_ALLOW_RETRY flag, which amdgpu never does. Remove the handling for the -EAGAIN case with its non-standard locking scheme. Link: https://lore.kernel.org/r/20190806160554.14046-2-hch@lst.de Signed-off-by: Christoph Hellwig Reviewed-by: Jason Gunthorpe Reviewed-by: Felix Kuehling Signed-off-by: Jason Gunthorpe --- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 23 +++-------------------- 1 file changed, 3 insertions(+), 20 deletions(-) (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 12a59ac83f72..f0821638bbc6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -778,7 +778,6 @@ int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, struct page **pages) struct hmm_range *range; unsigned long i; uint64_t *pfns; - int retry = 0; int r = 0; if (!mm) /* Happens during process shutdown */ @@ -822,7 +821,6 @@ int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, struct page **pages) hmm_range_register(range, mirror, start, start + ttm->num_pages * PAGE_SIZE, PAGE_SHIFT); -retry: /* * Just wait for range to be valid, safe to ignore return value as we * will use the return value of hmm_range_fault() below under the @@ -831,24 +829,12 @@ retry: hmm_range_wait_until_valid(range, HMM_RANGE_DEFAULT_TIMEOUT); down_read(&mm->mmap_sem); - r = hmm_range_fault(range, 0); - if (unlikely(r < 0)) { - if (likely(r == -EAGAIN)) { - /* - * return -EAGAIN, mmap_sem is dropped - */ - if (retry++ < MAX_RETRY_HMM_RANGE_FAULT) - goto retry; - else - pr_err("Retry hmm fault too many times\n"); - } - - goto out_up_read; - } - up_read(&mm->mmap_sem); + if (unlikely(r < 0)) + goto out_free_pfns; + for (i = 0; i < ttm->num_pages; i++) { pages[i] = hmm_device_entry_to_page(range, pfns[i]); if (unlikely(!pages[i])) { @@ -864,9 +850,6 @@ retry: return 0; -out_up_read: - if (likely(r != -EAGAIN)) - up_read(&mm->mmap_sem); out_free_pfns: hmm_range_unregister(range); kvfree(pfns); -- cgit v1.2.3 From fac555ac93d453a0d2265eef88bf4c249dd63e07 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 6 Aug 2019 19:05:44 +0300 Subject: mm/hmm: remove superfluous arguments from hmm_range_register The start, end and page_shift values are all saved in the range structure, so we might as well use that for argument passing. Link: https://lore.kernel.org/r/20190806160554.14046-7-hch@lst.de Signed-off-by: Christoph Hellwig Reviewed-by: Jason Gunthorpe Reviewed-by: Felix Kuehling Signed-off-by: Jason Gunthorpe --- Documentation/vm/hmm.rst | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 7 +++++-- drivers/gpu/drm/nouveau/nouveau_svm.c | 5 ++--- include/linux/hmm.h | 6 +----- mm/hmm.c | 20 +++++--------------- 5 files changed, 14 insertions(+), 26 deletions(-) (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c') diff --git a/Documentation/vm/hmm.rst b/Documentation/vm/hmm.rst index ddcb5ca8b296..e63c11f7e0e0 100644 --- a/Documentation/vm/hmm.rst +++ b/Documentation/vm/hmm.rst @@ -222,7 +222,7 @@ The usage pattern is:: range.flags = ...; range.values = ...; range.pfn_shift = ...; - hmm_range_register(&range); + hmm_range_register(&range, mirror); /* * Just wait for range to be valid, safe to ignore return value as we diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index f0821638bbc6..71d6e7087b0b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -818,8 +818,11 @@ int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, struct page **pages) 0 : range->flags[HMM_PFN_WRITE]; range->pfn_flags_mask = 0; range->pfns = pfns; - hmm_range_register(range, mirror, start, - start + ttm->num_pages * PAGE_SIZE, PAGE_SHIFT); + range->page_shift = PAGE_SHIFT; + range->start = start; + range->end = start + ttm->num_pages * PAGE_SIZE; + + hmm_range_register(range, mirror); /* * Just wait for range to be valid, safe to ignore return value as we diff --git a/drivers/gpu/drm/nouveau/nouveau_svm.c b/drivers/gpu/drm/nouveau/nouveau_svm.c index 98072fd48cf7..41fad4719ac6 100644 --- a/drivers/gpu/drm/nouveau/nouveau_svm.c +++ b/drivers/gpu/drm/nouveau/nouveau_svm.c @@ -492,9 +492,7 @@ nouveau_range_fault(struct nouveau_svmm *svmm, struct hmm_range *range) range->default_flags = 0; range->pfn_flags_mask = -1UL; - ret = hmm_range_register(range, &svmm->mirror, - range->start, range->end, - PAGE_SHIFT); + ret = hmm_range_register(range, &svmm->mirror); if (ret) { up_read(&svmm->mm->mmap_sem); return (int)ret; @@ -682,6 +680,7 @@ nouveau_svm_fault(struct nvif_notify *notify) args.i.p.addr + args.i.p.size, fn - fi); /* Have HMM fault pages within the fault window to the GPU. */ + range.page_shift = PAGE_SHIFT; range.start = args.i.p.addr; range.end = args.i.p.addr + args.i.p.size; range.pfns = args.phys; diff --git a/include/linux/hmm.h b/include/linux/hmm.h index 59be0aa2476d..c5b51376b453 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -400,11 +400,7 @@ void hmm_mirror_unregister(struct hmm_mirror *mirror); /* * Please see Documentation/vm/hmm.rst for how to use the range API. */ -int hmm_range_register(struct hmm_range *range, - struct hmm_mirror *mirror, - unsigned long start, - unsigned long end, - unsigned page_shift); +int hmm_range_register(struct hmm_range *range, struct hmm_mirror *mirror); void hmm_range_unregister(struct hmm_range *range); /* diff --git a/mm/hmm.c b/mm/hmm.c index 160ecb47d04b..ab22fdb655c8 100644 --- a/mm/hmm.c +++ b/mm/hmm.c @@ -850,35 +850,25 @@ static void hmm_pfns_clear(struct hmm_range *range, * hmm_range_register() - start tracking change to CPU page table over a range * @range: range * @mm: the mm struct for the range of virtual address - * @start: start virtual address (inclusive) - * @end: end virtual address (exclusive) - * @page_shift: expect page shift for the range + * * Return: 0 on success, -EFAULT if the address space is no longer valid * * Track updates to the CPU page table see include/linux/hmm.h */ -int hmm_range_register(struct hmm_range *range, - struct hmm_mirror *mirror, - unsigned long start, - unsigned long end, - unsigned page_shift) +int hmm_range_register(struct hmm_range *range, struct hmm_mirror *mirror) { - unsigned long mask = ((1UL << page_shift) - 1UL); + unsigned long mask = ((1UL << range->page_shift) - 1UL); struct hmm *hmm = mirror->hmm; unsigned long flags; range->valid = false; range->hmm = NULL; - if ((start & mask) || (end & mask)) + if ((range->start & mask) || (range->end & mask)) return -EINVAL; - if (start >= end) + if (range->start >= range->end) return -EINVAL; - range->page_shift = page_shift; - range->start = start; - range->end = end; - /* Prevent hmm_release() from running while the range is valid */ if (!mmget_not_zero(hmm->mm)) return -EFAULT; -- cgit v1.2.3 From 7f08263d9bc6627382da14f9e81d643d0329d5d1 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 6 Aug 2019 19:05:45 +0300 Subject: mm/hmm: remove the page_shift member from struct hmm_range All users pass PAGE_SIZE here, and if we wanted to support single entries for huge pages we should really just add a HMM_FAULT_HUGEPAGE flag instead that uses the huge page size instead of having the caller calculate that size once, just for the hmm code to verify it. Link: https://lore.kernel.org/r/20190806160554.14046-8-hch@lst.de Signed-off-by: Christoph Hellwig Acked-by: Felix Kuehling Reviewed-by: Jason Gunthorpe Signed-off-by: Jason Gunthorpe --- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 1 - drivers/gpu/drm/nouveau/nouveau_svm.c | 1 - include/linux/hmm.h | 22 ----------------- mm/hmm.c | 42 +++++++-------------------------- 4 files changed, 9 insertions(+), 57 deletions(-) (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 71d6e7087b0b..8bf79288c4e2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -818,7 +818,6 @@ int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, struct page **pages) 0 : range->flags[HMM_PFN_WRITE]; range->pfn_flags_mask = 0; range->pfns = pfns; - range->page_shift = PAGE_SHIFT; range->start = start; range->end = start + ttm->num_pages * PAGE_SIZE; diff --git a/drivers/gpu/drm/nouveau/nouveau_svm.c b/drivers/gpu/drm/nouveau/nouveau_svm.c index 41fad4719ac6..668d4bd0c118 100644 --- a/drivers/gpu/drm/nouveau/nouveau_svm.c +++ b/drivers/gpu/drm/nouveau/nouveau_svm.c @@ -680,7 +680,6 @@ nouveau_svm_fault(struct nvif_notify *notify) args.i.p.addr + args.i.p.size, fn - fi); /* Have HMM fault pages within the fault window to the GPU. */ - range.page_shift = PAGE_SHIFT; range.start = args.i.p.addr; range.end = args.i.p.addr + args.i.p.size; range.pfns = args.phys; diff --git a/include/linux/hmm.h b/include/linux/hmm.h index c5b51376b453..51e18fbb8953 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -158,7 +158,6 @@ enum hmm_pfn_value_e { * @values: pfn value for some special case (none, special, error, ...) * @default_flags: default flags for the range (write, read, ... see hmm doc) * @pfn_flags_mask: allows to mask pfn flags so that only default_flags matter - * @page_shift: device virtual address shift value (should be >= PAGE_SHIFT) * @pfn_shifts: pfn shift value (should be <= PAGE_SHIFT) * @valid: pfns array did not change since it has been fill by an HMM function */ @@ -172,31 +171,10 @@ struct hmm_range { const uint64_t *values; uint64_t default_flags; uint64_t pfn_flags_mask; - uint8_t page_shift; uint8_t pfn_shift; bool valid; }; -/* - * hmm_range_page_shift() - return the page shift for the range - * @range: range being queried - * Return: page shift (page size = 1 << page shift) for the range - */ -static inline unsigned hmm_range_page_shift(const struct hmm_range *range) -{ - return range->page_shift; -} - -/* - * hmm_range_page_size() - return the page size for the range - * @range: range being queried - * Return: page size for the range in bytes - */ -static inline unsigned long hmm_range_page_size(const struct hmm_range *range) -{ - return 1UL << hmm_range_page_shift(range); -} - /* * hmm_range_wait_until_valid() - wait for range to be valid * @range: range affected by invalidation to wait on diff --git a/mm/hmm.c b/mm/hmm.c index ab22fdb655c8..9e0052e037fe 100644 --- a/mm/hmm.c +++ b/mm/hmm.c @@ -345,13 +345,12 @@ static int hmm_vma_walk_hole_(unsigned long addr, unsigned long end, struct hmm_vma_walk *hmm_vma_walk = walk->private; struct hmm_range *range = hmm_vma_walk->range; uint64_t *pfns = range->pfns; - unsigned long i, page_size; + unsigned long i; hmm_vma_walk->last = addr; - page_size = hmm_range_page_size(range); - i = (addr - range->start) >> range->page_shift; + i = (addr - range->start) >> PAGE_SHIFT; - for (; addr < end; addr += page_size, i++) { + for (; addr < end; addr += PAGE_SIZE, i++) { pfns[i] = range->values[HMM_PFN_NONE]; if (fault || write_fault) { int ret; @@ -779,7 +778,7 @@ static int hmm_vma_walk_hugetlb_entry(pte_t *pte, unsigned long hmask, struct mm_walk *walk) { #ifdef CONFIG_HUGETLB_PAGE - unsigned long addr = start, i, pfn, mask, size, pfn_inc; + unsigned long addr = start, i, pfn, mask; struct hmm_vma_walk *hmm_vma_walk = walk->private; struct hmm_range *range = hmm_vma_walk->range; struct vm_area_struct *vma = walk->vma; @@ -790,24 +789,12 @@ static int hmm_vma_walk_hugetlb_entry(pte_t *pte, unsigned long hmask, pte_t entry; int ret = 0; - size = huge_page_size(h); - mask = size - 1; - if (range->page_shift != PAGE_SHIFT) { - /* Make sure we are looking at a full page. */ - if (start & mask) - return -EINVAL; - if (end < (start + size)) - return -EINVAL; - pfn_inc = size >> PAGE_SHIFT; - } else { - pfn_inc = 1; - size = PAGE_SIZE; - } + mask = huge_page_size(h) - 1; ptl = huge_pte_lock(hstate_vma(vma), walk->mm, pte); entry = huge_ptep_get(pte); - i = (start - range->start) >> range->page_shift; + i = (start - range->start) >> PAGE_SHIFT; orig_pfn = range->pfns[i]; range->pfns[i] = range->values[HMM_PFN_NONE]; cpu_flags = pte_to_hmm_pfn_flags(range, entry); @@ -819,8 +806,8 @@ static int hmm_vma_walk_hugetlb_entry(pte_t *pte, unsigned long hmask, goto unlock; } - pfn = pte_pfn(entry) + ((start & mask) >> range->page_shift); - for (; addr < end; addr += size, i++, pfn += pfn_inc) + pfn = pte_pfn(entry) + ((start & mask) >> PAGE_SHIFT); + for (; addr < end; addr += PAGE_SIZE, i++, pfn++) range->pfns[i] = hmm_device_entry_from_pfn(range, pfn) | cpu_flags; hmm_vma_walk->last = end; @@ -857,14 +844,13 @@ static void hmm_pfns_clear(struct hmm_range *range, */ int hmm_range_register(struct hmm_range *range, struct hmm_mirror *mirror) { - unsigned long mask = ((1UL << range->page_shift) - 1UL); struct hmm *hmm = mirror->hmm; unsigned long flags; range->valid = false; range->hmm = NULL; - if ((range->start & mask) || (range->end & mask)) + if ((range->start & (PAGE_SIZE - 1)) || (range->end & (PAGE_SIZE - 1))) return -EINVAL; if (range->start >= range->end) return -EINVAL; @@ -971,16 +957,6 @@ long hmm_range_fault(struct hmm_range *range, unsigned int flags) if (vma == NULL || (vma->vm_flags & device_vma)) return -EFAULT; - if (is_vm_hugetlb_page(vma)) { - if (huge_page_shift(hstate_vma(vma)) != - range->page_shift && - range->page_shift != PAGE_SHIFT) - return -EINVAL; - } else { - if (range->page_shift != PAGE_SHIFT) - return -EINVAL; - } - if (!(vma->vm_flags & VM_READ)) { /* * If vma do not allow read access, then assume that it -- cgit v1.2.3 From 90489ce18c3a504c781c8cfcec013258c3459328 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 15 Aug 2019 09:27:01 +0200 Subject: drm/amdgpu: handle PCIe root ports with addressing limitations MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit amdgpu uses a need_dma32 flag to indicate to the drm core that some allocations need to be done using GFP_DMA32, but it only checks the device addressing capabilities to make that decision. Unfortunately PCIe root ports that have limited addressing exist as well. Use the dma_addressing_limited instead to also take those into account. Reviewed-by: Christian König Signed-off-by: Christoph Hellwig Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 8f8b7a350b8b..bbb4c96ed5f9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -1745,7 +1745,7 @@ int amdgpu_ttm_init(struct amdgpu_device *adev) r = ttm_bo_device_init(&adev->mman.bdev, &amdgpu_bo_driver, adev->ddev->anon_inode->i_mapping, - adev->need_dma32); + dma_addressing_limited(adev->dev)); if (r) { DRM_ERROR("failed initializing buffer object driver(%d).\n", r); return r; -- cgit v1.2.3 From 994dcfaa7ee321a23ec398f6b0e709f11ab2f577 Mon Sep 17 00:00:00 2001 From: "Tianci.Yin" Date: Wed, 28 Aug 2019 18:51:19 +0800 Subject: drm/amdgpu: keep the stolen memory in visible vram region MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit stolen memory should be fixed in visible region. Reviewed-by: Christian König Signed-off-by: Tianci.Yin Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 6 ++++-- drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c | 3 ++- 2 files changed, 6 insertions(+), 3 deletions(-) (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index bbb4c96ed5f9..a29110a4e492 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -1738,6 +1738,7 @@ int amdgpu_ttm_init(struct amdgpu_device *adev) uint64_t gtt_size; int r; u64 vis_vram_limit; + void *stolen_vga_buf; mutex_init(&adev->mman.gtt_window_lock); @@ -1792,7 +1793,7 @@ int amdgpu_ttm_init(struct amdgpu_device *adev) r = amdgpu_bo_create_kernel(adev, adev->gmc.stolen_size, PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM, &adev->stolen_vga_memory, - NULL, NULL); + NULL, &stolen_vga_buf); if (r) return r; DRM_INFO("amdgpu: %uM of VRAM memory ready\n", @@ -1856,8 +1857,9 @@ int amdgpu_ttm_init(struct amdgpu_device *adev) */ void amdgpu_ttm_late_init(struct amdgpu_device *adev) { + void *stolen_vga_buf; /* return the VGA stolen memory (if any) back to VRAM */ - amdgpu_bo_free_kernel(&adev->stolen_vga_memory, NULL, NULL); + amdgpu_bo_free_kernel(&adev->stolen_vga_memory, NULL, &stolen_vga_buf); } /** diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c index 8efda03920e3..f91337030dc0 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c @@ -1238,6 +1238,7 @@ static int gmc_v9_0_sw_init(void *handle) static int gmc_v9_0_sw_fini(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; + void *stolen_vga_buf; if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__UMC) && adev->gmc.umc_ras_if) { @@ -1270,7 +1271,7 @@ static int gmc_v9_0_sw_fini(void *handle) amdgpu_vm_manager_fini(adev); if (gmc_v9_0_keep_stolen_memory(adev)) - amdgpu_bo_free_kernel(&adev->stolen_vga_memory, NULL, NULL); + amdgpu_bo_free_kernel(&adev->stolen_vga_memory, NULL, &stolen_vga_buf); amdgpu_gart_table_vram_free(adev); amdgpu_bo_fini(adev); -- cgit v1.2.3