drm/amdkfd: support concurrent userptr update for HMM v2
Subsystems (3)
PATCH 1/3 drm/amdkfd: support concurrent userptr update for HMM v2
Userptr restore may have concurrent userptr invalidation after hmm_vma_fault adds the range to the hmm->ranges list, needs call hmm_vma_range_done to remove the range from hmm->ranges list first, then reschedule the restore worker. Otherwise hmm_vma_fault will add same range to the list, this will cause loop in the list because range->next point to range itself.
Add function untrack_invalid_user_pages to reduce code duplication.
--- .../gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 25 ++++++++++++++----- 1 file changed, 19 insertions(+), 6 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +19 -6
@@ -1935,6 +1935,23 @@ static int update_invalid_user_pages(struct amdkfd_process_info *process_info,return 0 ; } +/* Remove invalid userptr BOs from hmm track list +* +* Stop HMM track the userptr update +*/ +static void untrack_invalid_user_pages (struct amdkfd_process_info *process_info) +{ +struct kgd_mem *mem, *tmp_mem; +struct amdgpu_bo *bo; + +list_for_each_entry_safe (mem, tmp_mem, + &process_info->userptr_inval_list, + validate_list.head) { + bo = mem->bo; +amdgpu_ttm_tt_get_user_pages_done (bo->tbo.ttm); + } +} +/* Validate invalid userptr BOs * * Validates BOs on the userptr_inval_list, and moves them back to the
@@ -2052,12 +2069,6 @@ static int validate_invalid_user_pages(struct amdkfd_process_info *process_info) out_free:kfree (pd_bo_list_entries); out_no_mem: -list_for_each_entry_safe (mem, tmp_mem, - &process_info->userptr_inval_list, - validate_list.head) { - bo = mem->bo; -amdgpu_ttm_tt_get_user_pages_done (bo->tbo.ttm); - }return ret; }
@@ -2122,7 +2133,9 @@ static void amdgpu_amdkfd_restore_userptr_worker(struct work_struct *work)* hanging. No point trying again. */ } + unlock_out: +untrack_invalid_user_pages (process_info);mutex_unlock (&process_info->lock);mmput (mm);put_task_struct (usertask);
Signature · 6 lines
2.17.1 _______________________________________________ amd-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/amd-gfx
A message that is not in the archive (sent off-list or not yet received): [email protected]
PATCH 2/3 drm/amdgpu: support userptr cross VMAs case with HMM v2
userptr may cross two VMAs if the forked child process (not call exec after fork) malloc buffer, then free it, and then malloc larger size buf, kerenl will create new VMA adjacent to old VMA which was cloned from parent process, some pages of userptr are in the first VMA, the rest pages are in the second VMA.
HMM expects range only have one VMA, loop over all VMAs in the address range, create multiple ranges to handle this case. See is_mergeable_anon_vma in mm/mmap.c for details.
--- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 123 +++++++++++++++++------- 1 file changed, 88 insertions(+), 35 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +88 -35
@@ -711,7 +711,8 @@ struct amdgpu_ttm_tt {struct task_struct *usertask;uint32_t userflags;#if IS_ENABLED (CONFIG_DRM_AMDGPU_USERPTR ) -struct hmm_range range; +struct hmm_range *ranges; +int nr_ranges;#endif };
@@ -723,62 +724,105 @@ struct amdgpu_ttm_tt {* once afterwards to stop HMM tracking */ #if IS_ENABLED (CONFIG_DRM_AMDGPU_USERPTR ) + +/* Support Userptr pages cross max 16 vmas */ +#define MAX_NR_VMAS (16) +int amdgpu_ttm_tt_get_user_pages (struct ttm_tt *ttm,struct page **pages) {struct amdgpu_ttm_tt *gtt = (void *)ttm;struct mm_struct *mm = gtt->usertask->mm; -unsigned long end = gtt->userptr + ttm->num_pages *PAGE_SIZE ; -struct hmm_range *range = >t->range; -int r =0 , i; +unsigned long start = gtt->userptr; +unsigned long end = start + ttm->num_pages *PAGE_SIZE ; +struct hmm_range *ranges; +struct vm_area_struct *vma =NULL , *vmas[MAX_NR_VMAS ]; +uint64_t *pfns, f; +int r =0 , i, nr_pages;if (!mm)/* Happens during process shutdown */ return -ESRCH ; -amdgpu_hmm_init_range (range); -down_read (&mm->mmap_sem); - range->vma =find_vma (mm, gtt->userptr); -if (!range_in_vma (range->vma, gtt->userptr, end)) - r = -EFAULT ; -else if ((gtt->userflags &AMDGPU_GEM_USERPTR_ANONONLY ) && - range->vma->vm_file) +/* user pages may cross multiple VMAs */ + gtt->nr_ranges =0 ; +do { +if (gtt->nr_ranges >=MAX_NR_VMAS ) { +DRM_ERROR ("Too many VMAs in userptr range\n" ); + r = -EFAULT ; + goto out; + } + + vma =find_vma (mm, vma ? vma->vm_end : start); +if (unlikely (!vma)) { + r = -EFAULT ; + goto out; + } + vmas[gtt->nr_ranges++] = vma; + }while (end > vma->vm_end); + +DRM_DEBUG_DRIVER ("0x%lx nr_ranges %d pages 0x%lx\n" , + start, gtt->nr_ranges, ttm->num_pages); + +if (unlikely ((gtt->userflags &AMDGPU_GEM_USERPTR_ANONONLY ) && + vmas[0 ]->vm_file)) { r = -EPERM ; -if (r) goto out; + } - range->pfns =kvmalloc_array (ttm->num_pages,sizeof (uint64_t ), -GFP_KERNEL ); -if (range->pfns ==NULL ) { + ranges =kvmalloc_array (gtt->nr_ranges,sizeof (*ranges),GFP_KERNEL ); +if (unlikely (!ranges)) { r = -ENOMEM ; goto out; } - range->start = gtt->userptr; - range->end = end; - range->pfns[0 ] = range->flags[HMM_PFN_VALID ]; - range->pfns[0 ] |=amdgpu_ttm_tt_is_readonly (ttm) ? -0 : range->flags[HMM_PFN_WRITE ]; -for (i =1 ; i < ttm->num_pages; i++) - range->pfns[i] = range->pfns[0 ]; + pfns =kvmalloc_array (ttm->num_pages,sizeof (*pfns),GFP_KERNEL ); +if (unlikely (!pfns)) { + r = -ENOMEM ; + goto out_free_ranges; + } + +for (i =0 ; i < gtt->nr_ranges; i++) +amdgpu_hmm_init_range (&ranges[i]); + + f = ranges[0 ].flags[HMM_PFN_VALID ]; + f |=amdgpu_ttm_tt_is_readonly (ttm) ? +0 : ranges[0 ].flags[HMM_PFN_WRITE ]; +memset64 (pfns, f, ttm->num_pages); + +for (nr_pages =0 , i =0 ; i < gtt->nr_ranges; i++) { + ranges[i].vma = vmas[i]; + ranges[i].start =max (start, vmas[i]->vm_start); + ranges[i].end =min (end, vmas[i]->vm_end); + ranges[i].pfns = pfns + nr_pages; + nr_pages += (ranges[i].end - ranges[i].start) /PAGE_SIZE ; + + r =hmm_vma_fault (&ranges[i], true); +if (unlikely (r)) +break ; + } +if (unlikely (r)) { +while (i--) +hmm_vma_range_done (&ranges[i]); -/* This may trigger page table update */ - r =hmm_vma_fault (range, true); -if (r) goto out_free_pfns; + }up_read (&mm->mmap_sem);for (i =0 ; i < ttm->num_pages; i++) - pages[i] =hmm_pfn_to_page (range, range->pfns[i]); + pages[i] =hmm_pfn_to_page (&ranges[0 ], pfns[i]); + gtt->ranges = ranges;return 0 ; out_free_pfns: -kvfree (range->pfns); - range->pfns =NULL ; +kvfree (pfns); +out_free_ranges: +kvfree (ranges); out:up_read (&mm->mmap_sem); +return r; }
@@ -792,15 +836,23 @@ bool amdgpu_ttm_tt_get_user_pages_done(struct ttm_tt *ttm) {struct amdgpu_ttm_tt *gtt = (void *)ttm;bool r = false; +int i;if (!gtt || !gtt->userptr)return false; -WARN_ONCE (!gtt->range.pfns,"No user pages to check\n" ); -if (gtt->range.pfns) { - r =hmm_vma_range_done (>t->range); -kvfree (gtt->range.pfns); - gtt->range.pfns =NULL ; +DRM_DEBUG_DRIVER ("user_pages_done 0x%llx nr_ranges %d pages 0x%lx\n" , + gtt->userptr, gtt->nr_ranges, ttm->num_pages); + +WARN_ONCE (!gtt->ranges || !gtt->ranges[0 ].pfns, +"No user pages to check\n" ); + +if (gtt->ranges) { +for (i =0 ; i < gtt->nr_ranges; i++) + r |=hmm_vma_range_done (>t->ranges[i]); +kvfree (gtt->ranges[0 ].pfns); +kvfree (gtt->ranges); + gtt->ranges =NULL ; }return r;
@@ -884,8 +936,9 @@ static void amdgpu_ttm_tt_unpin_userptr(struct ttm_tt *ttm)sg_free_table (ttm->sg);#if IS_ENABLED (CONFIG_DRM_AMDGPU_USERPTR ) -if (gtt->range.pfns && - ttm->pages[0 ] ==hmm_pfn_to_page (>t->range, gtt->range.pfns[0 ])) +if (gtt->ranges && + ttm->pages[0 ] ==hmm_pfn_to_page (>t->ranges[0 ], + gtt->ranges[0 ].pfns[0 ]))WARN_ONCE (1 ,"Missing get_user_page_done\n" );#endif }
Signature · 6 lines
2.17.1 _______________________________________________ amd-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/amd-gfx
A message that is not in the archive (sent off-list or not yet received): [email protected]
Re: [PATCH 2/3] drm/amdgpu: support userptr cross VMAs case with HMM v2
See one comment inline. There are still some potential problems that you're not catching.
Quoted 64 lines · Philip
userptr may cross two VMAs if the forked child process (not call exec after fork) malloc buffer, then free it, and then malloc larger size buf, kerenl will create new VMA adjacent to old VMA which was cloned from parent process, some pages of userptr are in the first VMA, the rest pages are in the second VMA.
HMM expects range only have one VMA, loop over all VMAs in the address range, create multiple ranges to handle this case. See
is_mergeable_anon_vmainmm/mmap.cfor details.Change-Id I0ca8c77e28deabccc139906f9ffee04b7e383314Signed-off-by Philip Yang <[email protected]>--- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 123 +++++++++++++++++------- 1 file changed, 88 insertions(+), 35 deletions(-)drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +12
-11@@ -711,7 +711,8 @@ struct amdgpu_ttm_tt {struct task_struct *usertask;uint32_t userflags;#if IS_ENABLED (CONFIG_DRM_AMDGPU_USERPTR ) -struct hmm_range range; +struct hmm_range *ranges; +int nr_ranges;#endif };@@ -723,62 +724,105 @@ struct amdgpu_ttm_tt {* once afterwards to stop HMM tracking */ #if IS_ENABLED (CONFIG_DRM_AMDGPU_USERPTR ) + +/* Support Userptr pages cross max 16 vmas */ +#define MAX_NR_VMAS (16) +int amdgpu_ttm_tt_get_user_pages (struct ttm_tt *ttm,struct page **pages) {struct amdgpu_ttm_tt *gtt = (void *)ttm;struct mm_struct *mm = gtt->usertask->mm; -unsigned long end = gtt->userptr + ttm->num_pages *PAGE_SIZE ; -struct hmm_range *range = >t->range; -int r =0 , i; +unsigned long start = gtt->userptr; +unsigned long end = start + ttm->num_pages *PAGE_SIZE ; +struct hmm_range *ranges; +struct vm_area_struct *vma =NULL , *vmas[MAX_NR_VMAS ]; +uint64_t *pfns, f; +int r =0 , i, nr_pages;if (!mm)/* Happens during process shutdown */ return -ESRCH ; -amdgpu_hmm_init_range (range); -down_read (&mm->mmap_sem); - range->vma =find_vma (mm, gtt->userptr); -if (!range_in_vma (range->vma, gtt->userptr, end)) - r = -EFAULT ; -else if ((gtt->userflags &AMDGPU_GEM_USERPTR_ANONONLY ) && - range->vma->vm_file)
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c struct amdgpu_ttm_tt { · line 756
Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +10
-0+/* user pages may cross multiple VMAs */ + gtt->nr_ranges =0 ; + do { + if (gtt->nr_ranges >= MAX_NR_VMAS) { + DRM_ERROR("Too many VMAs in userptr range\n"); + r = -EFAULT; + goto out; + } + + vma = find_vma(mm, vma ? vma->vm_end : start);
You need a check here that vma->vm_start <= the requested start address. Otherwise you can end up with gaps in your userptr mapping that don't have valid pages.
Regards,
Felix
Quoted 119 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +62
-22+if (unlikely (!vma)) { + r = -EFAULT ; + goto out; + } + vmas[gtt->nr_ranges++] = vma; + }while (end > vma->vm_end);+ +DRM_DEBUG_DRIVER ("0x%lx nr_ranges %d pages 0x%lx\n" , + start, gtt->nr_ranges, ttm->num_pages); + +if (unlikely ((gtt->userflags &AMDGPU_GEM_USERPTR_ANONONLY ) && + vmas[0 ]->vm_file)) { r = -EPERM ; -if (r) goto out; + } - range->pfns =kvmalloc_array (ttm->num_pages,sizeof (uint64_t ), -GFP_KERNEL ); -if (range->pfns ==NULL ) { + ranges =kvmalloc_array (gtt->nr_ranges,sizeof (*ranges),GFP_KERNEL ); +if (unlikely (!ranges)) { r = -ENOMEM ; goto out; } - range->start = gtt->userptr; - range->end = end; - range->pfns[0 ] = range->flags[HMM_PFN_VALID ]; - range->pfns[0 ] |=amdgpu_ttm_tt_is_readonly (ttm) ? -0 : range->flags[HMM_PFN_WRITE ]; -for (i =1 ; i < ttm->num_pages; i++) - range->pfns[i] = range->pfns[0 ]; + pfns =kvmalloc_array (ttm->num_pages,sizeof (*pfns),GFP_KERNEL ); +if (unlikely (!pfns)) { + r = -ENOMEM ; + goto out_free_ranges; + } + +for (i =0 ; i < gtt->nr_ranges; i++) +amdgpu_hmm_init_range (&ranges[i]); + + f = ranges[0 ].flags[HMM_PFN_VALID ]; + f |=amdgpu_ttm_tt_is_readonly (ttm) ? +0 : ranges[0 ].flags[HMM_PFN_WRITE ]; +memset64 (pfns, f, ttm->num_pages); + +for (nr_pages =0 , i =0 ; i < gtt->nr_ranges; i++) { + ranges[i].vma = vmas[i]; + ranges[i].start =max (start, vmas[i]->vm_start); + ranges[i].end =min (end, vmas[i]->vm_end); + ranges[i].pfns = pfns + nr_pages; + nr_pages += (ranges[i].end - ranges[i].start) /PAGE_SIZE ; + + r =hmm_vma_fault (&ranges[i], true); +if (unlikely (r)) +break ; + } +if (unlikely (r)) { +while (i--) +hmm_vma_range_done (&ranges[i]); -/* This may trigger page table update */ - r =hmm_vma_fault (range, true); -if (r) goto out_free_pfns; + }up_read (&mm->mmap_sem);for (i =0 ; i < ttm->num_pages; i++) - pages[i] =hmm_pfn_to_page (range, range->pfns[i]); + pages[i] =hmm_pfn_to_page (&ranges[0 ], pfns[i]); + gtt->ranges = ranges;return 0 ; out_free_pfns: -kvfree (range->pfns); - range->pfns =NULL ; +kvfree (pfns); +out_free_ranges: +kvfree (ranges); out:up_read (&mm->mmap_sem); +return r; }@@ -792,15 +836,23 @@ bool amdgpu_ttm_tt_get_user_pages_done(struct ttm_tt *ttm) {struct amdgpu_ttm_tt *gtt = (void *)ttm;bool r = false; +int i;if (!gtt || !gtt->userptr)return false; -WARN_ONCE (!gtt->range.pfns,"No user pages to check\n" ); -if (gtt->range.pfns) { - r =hmm_vma_range_done (>t->range); -kvfree (gtt->range.pfns); - gtt->range.pfns =NULL ; +DRM_DEBUG_DRIVER ("user_pages_done 0x%llx nr_ranges %d pages 0x%lx\n" , + gtt->userptr, gtt->nr_ranges, ttm->num_pages); + +WARN_ONCE (!gtt->ranges || !gtt->ranges[0 ].pfns, +"No user pages to check\n" ); + +if (gtt->ranges) { +for (i =0 ; i < gtt->nr_ranges; i++) + r |=hmm_vma_range_done (>t->ranges[i]); +kvfree (gtt->ranges[0 ].pfns); +kvfree (gtt->ranges); + gtt->ranges =NULL ; }return r;@@ -884,8 +936,9 @@ static void amdgpu_ttm_tt_unpin_userptr(struct ttm_tt *ttm)sg_free_table (ttm->sg);
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c static void amdgpu_ttm_tt_unpin_userptr(struct ttm_tt *ttm) · line 944
Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +3
-2#if IS_ENABLED (CONFIG_DRM_AMDGPU_USERPTR ) -if (gtt->range.pfns && - ttm->pages[0 ] ==hmm_pfn_to_page (>t->range, gtt->range.pfns[0 ])) +if (gtt->ranges && + ttm->pages[0 ] ==hmm_pfn_to_page (>t->ranges[0 ], + gtt->ranges[0 ].pfns[0 ]))WARN_ONCE (1 ,"Missing get_user_page_done\n" );#endif }
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
A message that is not in the archive (sent off-list or not yet received): e5f7016c-5d5f-802c-4efd-d59608009e61-5C7GfCeVMHo@public.gmane.org
Re: [PATCH 2/3] drm/amdgpu: support userptr cross VMAs case with HMM v2
Hi Felix,
Submitted v3 to fix the potential problems with invalid userptr.
Philip
Quoted 207 lines · Felix
See one comment inline. There are still some potential problems that you're not catching.
Quoted 64 lines · Philip
userptr may cross two VMAs if the forked child process (not call exec after fork) malloc buffer, then free it, and then malloc larger size buf, kerenl will create new VMA adjacent to old VMA which was cloned from parent process, some pages of userptr are in the first VMA, the rest pages are in the second VMA.
HMM expects range only have one VMA, loop over all VMAs in the address range, create multiple ranges to handle this case. See
is_mergeable_anon_vmainmm/mmap.cfor details.Change-Id I0ca8c77e28deabccc139906f9ffee04b7e383314Signed-off-by Philip Yang <[email protected]>--- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 123 +++++++++++++++++------- 1 file changed, 88 insertions(+), 35 deletions(-)drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +12
-11@@ -711,7 +711,8 @@ struct amdgpu_ttm_tt {struct task_struct *usertask;uint32_t userflags;#if IS_ENABLED (CONFIG_DRM_AMDGPU_USERPTR ) -struct hmm_range range; +struct hmm_range *ranges; +int nr_ranges;#endif };@@ -723,62 +724,105 @@ struct amdgpu_ttm_tt {* once afterwards to stop HMM tracking */ #if IS_ENABLED (CONFIG_DRM_AMDGPU_USERPTR ) + +/* Support Userptr pages cross max 16 vmas */ +#define MAX_NR_VMAS (16) +int amdgpu_ttm_tt_get_user_pages (struct ttm_tt *ttm,struct page **pages) {struct amdgpu_ttm_tt *gtt = (void *)ttm;struct mm_struct *mm = gtt->usertask->mm; -unsigned long end = gtt->userptr + ttm->num_pages *PAGE_SIZE ; -struct hmm_range *range = >t->range; -int r =0 , i; +unsigned long start = gtt->userptr; +unsigned long end = start + ttm->num_pages *PAGE_SIZE ; +struct hmm_range *ranges; +struct vm_area_struct *vma =NULL , *vmas[MAX_NR_VMAS ]; +uint64_t *pfns, f; +int r =0 , i, nr_pages;if (!mm)/* Happens during process shutdown */ return -ESRCH ; -amdgpu_hmm_init_range (range); -down_read (&mm->mmap_sem); - range->vma =find_vma (mm, gtt->userptr); -if (!range_in_vma (range->vma, gtt->userptr, end)) - r = -EFAULT ; -else if ((gtt->userflags &AMDGPU_GEM_USERPTR_ANONONLY ) && - range->vma->vm_file)drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c struct amdgpu_ttm_tt { · line 756
Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +10
-0+/* user pages may cross multiple VMAs */ + gtt->nr_ranges =0 ; + do { + if (gtt->nr_ranges >= MAX_NR_VMAS) { + DRM_ERROR("Too many VMAs in userptr range\n"); + r = -EFAULT; + goto out; + } + + vma = find_vma(mm, vma ? vma->vm_end : start);You need a check here that
vma->vm_start<= the requested start address. Otherwise you can end up with gaps in your userptr mapping that don't have valid pages.Regards,
FelixQuoted 120 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +62
-22+if (unlikely (!vma)) { + r = -EFAULT ; + goto out; + } + vmas[gtt->nr_ranges++] = vma; + }while (end > vma->vm_end);+ +DRM_DEBUG_DRIVER ("0x%lx nr_ranges %d pages 0x%lx\n" , + start, gtt->nr_ranges, ttm->num_pages); + +if (unlikely ((gtt->userflags &AMDGPU_GEM_USERPTR_ANONONLY ) && + vmas[0 ]->vm_file)) { r = -EPERM ; -if (r) goto out; + } - range->pfns =kvmalloc_array (ttm->num_pages,sizeof (uint64_t ), -GFP_KERNEL ); -if (range->pfns ==NULL ) { + ranges =kvmalloc_array (gtt->nr_ranges,sizeof (*ranges),GFP_KERNEL ); +if (unlikely (!ranges)) { r = -ENOMEM ; goto out; } - range->start = gtt->userptr; - range->end = end; - range->pfns[0 ] = range->flags[HMM_PFN_VALID ]; - range->pfns[0 ] |=amdgpu_ttm_tt_is_readonly (ttm) ? -0 : range->flags[HMM_PFN_WRITE ]; -for (i =1 ; i < ttm->num_pages; i++) - range->pfns[i] = range->pfns[0 ]; + pfns =kvmalloc_array (ttm->num_pages,sizeof (*pfns),GFP_KERNEL ); +if (unlikely (!pfns)) { + r = -ENOMEM ; + goto out_free_ranges; + } + +for (i =0 ; i < gtt->nr_ranges; i++) +amdgpu_hmm_init_range (&ranges[i]); + + f = ranges[0 ].flags[HMM_PFN_VALID ]; + f |=amdgpu_ttm_tt_is_readonly (ttm) ? +0 : ranges[0 ].flags[HMM_PFN_WRITE ]; +memset64 (pfns, f, ttm->num_pages); + +for (nr_pages =0 , i =0 ; i < gtt->nr_ranges; i++) { + ranges[i].vma = vmas[i]; + ranges[i].start =max (start, vmas[i]->vm_start); + ranges[i].end =min (end, vmas[i]->vm_end); + ranges[i].pfns = pfns + nr_pages; + nr_pages += (ranges[i].end - ranges[i].start) /PAGE_SIZE ; + + r =hmm_vma_fault (&ranges[i], true); +if (unlikely (r)) +break ; + } +if (unlikely (r)) { +while (i--) +hmm_vma_range_done (&ranges[i]); -/* This may trigger page table update */ - r =hmm_vma_fault (range, true); -if (r) goto out_free_pfns; + }up_read (&mm->mmap_sem);for (i =0 ; i < ttm->num_pages; i++) - pages[i] =hmm_pfn_to_page (range, range->pfns[i]); + pages[i] =hmm_pfn_to_page (&ranges[0 ], pfns[i]); + gtt->ranges = ranges;return 0 ; out_free_pfns: -kvfree (range->pfns); - range->pfns =NULL ; +kvfree (pfns); +out_free_ranges: +kvfree (ranges); out:up_read (&mm->mmap_sem); +return r; }@@ -792,15 +836,23 @@ bool amdgpu_ttm_tt_get_user_pages_done(struct ttm_tt *ttm) {struct amdgpu_ttm_tt *gtt = (void *)ttm;bool r = false; +int i;if (!gtt || !gtt->userptr)return false; -WARN_ONCE (!gtt->range.pfns,"No user pages to check\n" ); -if (gtt->range.pfns) { - r =hmm_vma_range_done (>t->range); -kvfree (gtt->range.pfns); - gtt->range.pfns =NULL ; +DRM_DEBUG_DRIVER ("user_pages_done 0x%llx nr_ranges %d pages 0x%lx\n" , + gtt->userptr, gtt->nr_ranges, ttm->num_pages); + +WARN_ONCE (!gtt->ranges || !gtt->ranges[0 ].pfns, +"No user pages to check\n" ); + +if (gtt->ranges) { +for (i =0 ; i < gtt->nr_ranges; i++) + r |=hmm_vma_range_done (>t->ranges[i]); +kvfree (gtt->ranges[0 ].pfns); +kvfree (gtt->ranges); + gtt->ranges =NULL ; }return r;@@ -884,8 +936,9 @@ static void amdgpu_ttm_tt_unpin_userptr(struct ttm_tt *ttm)sg_free_table (ttm->sg);
Quoted 9 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c static void amdgpu_ttm_tt_unpin_userptr(struct ttm_tt *ttm) · line 944
Quoted 9 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +3
-2#if IS_ENABLED (CONFIG_DRM_AMDGPU_USERPTR ) -if (gtt->range.pfns && - ttm->pages[0 ] ==hmm_pfn_to_page (>t->range, gtt->range.pfns[0 ])) +if (gtt->ranges && + ttm->pages[0 ] ==hmm_pfn_to_page (>t->ranges[0 ], + gtt->ranges[0 ].pfns[0 ]))WARN_ONCE (1 ,"Missing get_user_page_done\n" );#endif }
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
Quoted 11 lines · Philip
Userptr restore may have concurrent userptr invalidation after
hmm_vma_faultadds the range to thehmm->rangeslist, needs callhmm_vma_range_doneto remove the range fromhmm->rangeslist first, then reschedule the restore worker. Otherwisehmm_vma_faultwill add same range to the list, this will cause loop in the list becauserange->nextpoint to range itself.Add function
untrack_invalid_user_pagesto reduce code duplication.Change-Id I31407739dc10554f8e418c7a0e0415d3d95552f1Signed-off-by Philip Yang <[email protected]>
This patch is Reviewed-by: Felix Kuehling <[email protected]>
Quoted 46 lines
--- .../gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 25 ++++++++++++++----- 1 file changed, 19 insertions(+), 6 deletions(-)drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +17
-6@@ -1935,6 +1935,23 @@ static int update_invalid_user_pages(struct amdkfd_process_info *process_info,return 0 ; } +/* Remove invalid userptr BOs from hmm track list +* +* Stop HMM track the userptr update +*/ +static void untrack_invalid_user_pages (struct amdkfd_process_info *process_info) +{ +struct kgd_mem *mem, *tmp_mem; +struct amdgpu_bo *bo; + +list_for_each_entry_safe (mem, tmp_mem, + &process_info->userptr_inval_list, + validate_list.head) { + bo = mem->bo; +amdgpu_ttm_tt_get_user_pages_done (bo->tbo.ttm); + } +} +/* Validate invalid userptr BOs * * Validates BOs on the userptr_inval_list, and moves them back to the @@ -2052,12 +2069,6 @@ static int validate_invalid_user_pages(struct amdkfd_process_info *process_info) out_free:kfree (pd_bo_list_entries); out_no_mem: -list_for_each_entry_safe (mem, tmp_mem, - &process_info->userptr_inval_list, - validate_list.head) { - bo = mem->bo; -amdgpu_ttm_tt_get_user_pages_done (bo->tbo.ttm); - }return ret; }
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c static void amdgpu_amdkfd_restore_userptr_worker(struct work_struct *work) · line 2141
Quoted 9 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +2
-0@@ -2122,7 +2133,9 @@ static void amdgpu_amdkfd_restore_userptr_worker(struct work_struct *work)* hanging. No point trying again. */ } + unlock_out: +untrack_invalid_user_pages (process_info);mutex_unlock (&process_info->lock);mmput (mm);put_task_struct (usertask);
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx