drm/amdkfd: Unmap SVM range from GPU set to no-access
Subsystems (3)
v2 cover drm/amdkfd: Unmap SVM range from GPU set to no-access
Setting KFD_IOCTL_SVM_ATTR_NO_ACCESS on a GPU used to do nothing: the range stayed mapped, so the MMU notifier kept evicting GPU queues on CPU page faults even though the app wanted no access from that GPU.
Patch 1 adds a helper to update the fault checkpoint timestamp and makes the timestamp atomic so the page fault handler can read it locklessly.
Patch 2 unmaps the range from each GPU set to no-access. Once no GPU maps the range, the MMU notifier skips queue eviction. It bumps the checkpoint timestamp so retry faults queued before the unmap are dropped.
Philip Yang (2):
drm/amdkfd: Add helper svm_range_update_checkpoint_timestamp drm/amdkfd: Unmap svm range from GPU set to no-access
drivers/gpu/drm/amd/amdkfd/kfd_priv.h | 2 +- drivers/gpu/drm/amd/amdkfd/kfd_queue.c | 5 +- drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 190 +++++++++++++++---------- drivers/gpu/drm/amd/amdkfd/kfd_svm.h | 7 +- 4 files changed, 125 insertions(+), 79 deletions(-)
Signature · 1 line
2.50.1
PATCH v2 1/2 drm/amdkfd: Add helper svm_range_update_checkpoint_timestamp
Extract svm_range_update_checkpoint_timestamp() from svm_range_unmap_from_cpu(). The next patch calls it when the app sets the no-access attribute.
Change checkpoint_ts in svm_range_list from uint64_t to atomic64_t so svm_range_restore_pages() can read it from the page fault handler without holding the svms lock.
No functional change, preparation for the next patch.
--- drivers/gpu/drm/amd/amdkfd/kfd_priv.h | 2 +- drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 83 +++++++++++++++------------ 2 files changed, 48 insertions(+), 37 deletions(-)
drivers/gpu/drm/amd/amdkfd/kfd_priv.h +1 -1
@@ -895,7 +895,7 @@ struct svm_range_list {DECLARE_BITMAP (bitmap_supported,MAX_GPU_INSTANCE );struct task_struct *faulting_task;/* check point ts decides if page fault recovery need be dropped */ -uint64_t checkpoint_ts[MAX_GPU_INSTANCE ]; +atomic64_t checkpoint_ts[MAX_GPU_INSTANCE ];/* Default granularity to use in buffer migration * and restoration of backing memory while handling
drivers/gpu/drm/amd/amdkfd/kfd_svm.c +47 -36
113 lines not on this page · raw message
Signature · 1 line
2.50.1
Re: [PATCH v2 1/2] drm/amdkfd: Add helper svm_range_update_checkpoint_timestamp
Quoted 131 lines · Philip Yang
Extract
svm_range_update_checkpoint_timestamp()fromsvm_range_unmap_from_cpu(). The next patch calls it when the app sets the no-access attribute.Change
checkpoint_tsinsvm_range_listfromuint64_ttoatomic64_tsosvm_range_restore_pages()can read it from the page fault handler without holding the svms lock.No functional change, preparation for the next patch.
Signed-off-by Philip Yang <[email protected]>--- drivers/gpu/drm/amd/amdkfd/kfd_priv.h | 2 +- drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 83 +++++++++++++++------------ 2 files changed, 48 insertions(+), 37 deletions(-)drivers/gpu/drm/amd/amdkfd/kfd_priv.h +1
-1@@ -895,7 +895,7 @@ struct svm_range_list {DECLARE_BITMAP (bitmap_supported,MAX_GPU_INSTANCE );struct task_struct *faulting_task;/* check point ts decides if page fault recovery need be dropped */ -uint64_t checkpoint_ts[MAX_GPU_INSTANCE ]; +atomic64_t checkpoint_ts[MAX_GPU_INSTANCE ];/* Default granularity to use in buffer migration * and restoration of backing memory while handling drivers/gpu/drm/amd/amdkfd/kfd_svm.c +43
-33@@ -759,6 +759,48 @@ svm_range_check_attr(struct kfd_process *p,return 0 ; } +static void svm_range_update_checkpoint_timestamp (struct kfd_process *p) +{ +struct svm_range_list *svms; +int i; + + svms = &p->svms; + +/* calculate time stamps that are used to decide which page faults need be +* dropped or handled before unmap pages from gpu vm +*/ +for_each_set_bit (i, svms->bitmap_supported, p->n_pdds) { +struct kfd_process_device *pdd; +struct amdgpu_device *adev; +struct amdgpu_ih_ring *ih; +uint32_t checkpoint_wptr; + + pdd = p->pdds[i]; +if (!pdd) +continue ; + + adev = pdd->dev->adev; + +/* Check and drain ih1 ring if cam not available */ +if (!adev->irq.retry_cam_enabled && adev->irq.ih1.ring_size) { + ih = &adev->irq.ih1; + checkpoint_wptr =amdgpu_ih_get_wptr (adev, ih); +if (ih->rptr != checkpoint_wptr) { +atomic64_set (&svms->checkpoint_ts[i], +amdgpu_ih_decode_iv_ts (adev, ih, checkpoint_wptr,-1 )); +continue ; + } + } + +/* check if dev->irq.ih_soft is not empty */ + ih = &adev->irq.ih_soft; + checkpoint_wptr =amdgpu_ih_get_wptr (adev, ih); +if (ih->rptr != checkpoint_wptr) +atomic64_set (&svms->checkpoint_ts[i], +amdgpu_ih_decode_iv_ts (adev, ih, checkpoint_wptr,-1 )); + } +} + static void svm_range_apply_attrs(struct kfd_process *p, struct svm_range *prange, uint32_t nattr, struct kfd_ioctl_svm_attribute *attrs,@@ -2556,7 +2598,6 @@ svm_range_unmap_from_cpu(struct mm_struct *mm, struct svm_range *prange,struct kfd_process *p;unsigned long s, l;bool unmap_parent; -uint32_t i;if (atomic_read (&prange->queue_refcount)) {int r;@@ -2576,38 +2617,7 @@ svm_range_unmap_from_cpu(struct mm_struct *mm, struct svm_range *prange,pr_debug ("svms 0x%p prange 0x%p [0x%lx 0x%lx] [0x%lx 0x%lx]\n" , svms, prange, prange->start, prange->last, start, last); -/* calculate time stamps that are used to decide which page faults need be -* dropped or handled before unmap pages from gpu vm -*/ -for_each_set_bit (i, svms->bitmap_supported, p->n_pdds) { -struct kfd_process_device *pdd; -struct amdgpu_device *adev; -struct amdgpu_ih_ring *ih; -uint32_t checkpoint_wptr; - - pdd = p->pdds[i]; -if (!pdd) -continue ; - - adev = pdd->dev->adev; - -/* Check and drain ih1 ring if cam not available */ -if (!adev->irq.retry_cam_enabled && adev->irq.ih1.ring_size) { - ih = &adev->irq.ih1; - checkpoint_wptr =amdgpu_ih_get_wptr (adev, ih); -if (ih->rptr != checkpoint_wptr) { - svms->checkpoint_ts[i] = -amdgpu_ih_decode_iv_ts (adev, ih, checkpoint_wptr,-1 ); -continue ; - } - } - -/* check if dev->irq.ih_soft is not empty */ - ih = &adev->irq.ih_soft; - checkpoint_wptr =amdgpu_ih_get_wptr (adev, ih); -if (ih->rptr != checkpoint_wptr) - svms->checkpoint_ts[i] =amdgpu_ih_decode_iv_ts (adev, ih, checkpoint_wptr,-1 ); - } +svm_range_update_checkpoint_timestamp (p); unmap_parent = start <= prange->start && last >= prange->last;
drivers/gpu/drm/amd/amdkfd/kfd_svm.c svm_range_restore_pages(struct amdgpu_device *adev, unsigned int pasid, · line 3132
Quoted 8 lines
drivers/gpu/drm/amd/amdkfd/kfd_svm.c +3
-2@@ -3117,8 +3127,9 @@ svm_range_restore_pages(struct amdgpu_device *adev, unsigned int pasid,mutex_lock (&svms->lock);/* check if this page fault time stamp is before svms->checkpoint_ts */ -if (svms->checkpoint_ts[gpuidx] !=0 ) { -if (amdgpu_ih_ts_after_or_equal (ts, svms->checkpoint_ts[gpuidx])) { +if (atomic64_read (&svms->checkpoint_ts[gpuidx]) !=0 ) { +if (amdgpu_ih_ts_after_or_equal (ts, +atomic64_read (&svms->checkpoint_ts[gpuidx]))) {
You lose atomicity here by reading the checkpoint twice. It would be better to read it into a local variable once only and then using the same value twice.
With that fixed, the patch is
Quoted 12 lines
drivers/gpu/drm/amd/amdkfd/kfd_svm.c +1
-1pr_debug ("draining retry fault, drop fault 0x%llx\n" , addr);if (write_locked)mmap_write_downgrade (mm);@@ -3128,7 +3139,7 @@ svm_range_restore_pages(struct amdgpu_device *adev, unsigned int pasid,/* ts is after svms->checkpoint_ts now, reset svms->checkpoint_ts * to zero to avoid following ts wrap around give wrong comparing */ - svms->checkpoint_ts[gpuidx] =0 ; +atomic64_set (&svms->checkpoint_ts[gpuidx],0 ); } }
PATCH v2 2/2 drm/amdkfd: Unmap svm range from GPU set to no-access
In reply to Philip YangWhen KFD_IOCTL_SVM_ATTR_NO_ACCESS is applied to a GPU that has an SVM range mapped, unmap the range from that GPU. Once no GPU maps the range, the MMU notifier can skip queue eviction on CPU page faults.
Replace the mapped_to_gpu boolean with bitmap_mapped to track which GPUs currently have the range mapped. Set bits in svm_range_map_to_gpus() and clear them in svm_range_unmap_from_gpus(). This is separate from bitmap_access/bitmap_aip which track user-requested attributes and must not be used to determine mapping state.
Add bitmap_needs_unmap to svm_range, set for each GPU given no-access. Add svm_range_needs_unmap() to unmap the range from those GPUs when the app sets the no-access attribute.
Bump the checkpoint timestamp on unmap so retry faults queued before the no-access unmap are dropped instead of restoring the mapping.
v4:
- Rename and set prange->mapping_done to false if validate and map not complete successfully (Felix)
v3:
- Correct error handling, support app retry update mapping (Felix)
v2:
- Add bitmap_mapped to not break get_attr (Felix)
--- drivers/gpu/drm/amd/amdkfd/kfd_queue.c | 5 +- drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 107 ++++++++++++++++--------- drivers/gpu/drm/amd/amdkfd/kfd_svm.h | 7 +- 3 files changed, 77 insertions(+), 42 deletions(-)
drivers/gpu/drm/amd/amdkfd/kfd_queue.c +2 -3
@@ -112,12 +112,11 @@ static int kfd_queue_buffer_svm_get(struct kfd_process_device *pdd, u64 addr, u6if (!prange)break ; -if (!prange->mapped_to_gpu) -break ; - r =kfd_process_gpuid_from_node (p, pdd->dev, &gpuid, &gpuidx);if (r <0 )break ; +if (!test_bit (gpuidx, prange->bitmap_mapped)) +break ;if (!test_bit (gpuidx, prange->bitmap_access) && !test_bit (gpuidx, prange->bitmap_aip))break ;
drivers/gpu/drm/amd/amdkfd/kfd_svm.c +69 -38
255 lines not on this page · raw message
drivers/gpu/drm/amd/amdkfd/kfd_svm.h +6 -1
@@ -100,6 +100,9 @@ struct svm_work_list_item {* @child_list: list header for split ranges which are not added to svms yet * @bitmap_access: index bitmap of GPUs which can access the range * @bitmap_aip: index bitmap of GPUs which can access the range in place +* @bitmap_needs_unmap: index bitmap of GPUs which currently set NO_ACCESS +* @bitmap_mapped: index bitmap of GPUs which currently have the range mapped +* @mapping_done: true if range_validate_and_map complete successfully * * Data structure for virtual memory range shared by CPU and GPUs, it can be * allocated from system memory ram or device vram, and migrate from ram to vram
@@ -135,7 +138,9 @@ struct svm_range {struct list_head child_list;DECLARE_BITMAP (bitmap_access,MAX_GPU_INSTANCE );DECLARE_BITMAP (bitmap_aip,MAX_GPU_INSTANCE ); -bool mapped_to_gpu; +DECLARE_BITMAP (bitmap_needs_unmap,MAX_GPU_INSTANCE ); +DECLARE_BITMAP (bitmap_mapped,MAX_GPU_INSTANCE ); +bool mapping_done;atomic_t queue_refcount; };
Signature · 1 line
2.50.1
Felix Kuehling
maintainerRe: [PATCH v2 2/2] drm/amdkfd: Unmap svm range from GPU set to no-access
Quoted 56 lines · Philip Yang
When
KFD_IOCTL_SVM_ATTR_NO_ACCESSis applied to a GPU that has an SVM range mapped, unmap the range from that GPU. Once no GPU maps the range, the MMU notifier can skip queue eviction on CPU page faults.Replace the
mapped_to_gpuboolean withbitmap_mappedto track which GPUs currently have the range mapped. Set bits insvm_range_map_to_gpus()and clear them insvm_range_unmap_from_gpus(). This is separate from bitmap_access/bitmap_aip which track user-requested attributes and must not be used to determine mapping state.Add
bitmap_needs_unmaptosvm_range, set for each GPU given no-access. Addsvm_range_needs_unmap()to unmap the range from those GPUs when the app sets the no-access attribute.Bump the checkpoint timestamp on unmap so retry faults queued before the no-access unmap are dropped instead of restoring the mapping.
v4:
- Rename and setprange->mapping_doneto false if validate and map not complete successfully (Felix)
v3:
- Correct error handling, support app retry update mapping (Felix)
v2:
- Addbitmap_mappedto not breakget_attr(Felix)Signed-off-by Philip Yang <[email protected]>--- drivers/gpu/drm/amd/amdkfd/kfd_queue.c | 5 +- drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 107 ++++++++++++++++--------- drivers/gpu/drm/amd/amdkfd/kfd_svm.h | 7 +- 3 files changed, 77 insertions(+), 42 deletions(-)drivers/gpu/drm/amd/amdkfd/kfd_queue.c +2
-3@@ -112,12 +112,11 @@ static int kfd_queue_buffer_svm_get(struct kfd_process_device *pdd, u64 addr, u6if (!prange)break ; -if (!prange->mapped_to_gpu) -break ; - r =kfd_process_gpuid_from_node (p, pdd->dev, &gpuid, &gpuidx);if (r <0 )break ; +if (!test_bit (gpuidx, prange->bitmap_mapped)) +break ;if (!test_bit (gpuidx, prange->bitmap_access) && !test_bit (gpuidx, prange->bitmap_aip))break ;drivers/gpu/drm/amd/amdkfd/kfd_svm.c +0
-0
drivers/gpu/drm/amd/amdkfd/kfd_svm.c svm_range_apply_attrs(struct kfd_process *p, struct svm_range *prange, · line 829
Quoted 4 lines
drivers/gpu/drm/amd/amdkfd/kfd_svm.c +1
-0@@ -826,8 +826,13 @@ svm_range_apply_attrs(struct kfd_process *p, struct svm_range *prange, gpuidx =kfd_process_gpuidx_from_gpuid (p, attrs[i].value);if (attrs[i].type ==KFD_IOCTL_SVM_ATTR_NO_ACCESS ) { +svm_range_update_checkpoint_timestamp (p);
In the last version I suggested moving this into svm_range_needs_unmap so we only update the checkpoint (and drop interrupts) when anything is actually unmapped (after the bitmap_empty check for bitmap_needs_unmap). Did that not work for some reason?
Regards,
Felix
Quoted 295 lines
drivers/gpu/drm/amd/amdkfd/kfd_svm.c +68
-38+bitmap_clear (prange->bitmap_access, gpuidx,1 );bitmap_clear (prange->bitmap_aip, gpuidx,1 ); + +if (test_bit (gpuidx, prange->bitmap_mapped)) +bitmap_set (prange->bitmap_needs_unmap, gpuidx,1 ); }else if (attrs[i].type ==KFD_IOCTL_SVM_ATTR_ACCESS ) {bitmap_set (prange->bitmap_access, gpuidx,1 );bitmap_clear (prange->bitmap_aip, gpuidx,1 );@@ -1118,9 +1123,10 @@ svm_range_split_adjust(struct svm_range *new, struct svm_range *old, new->prefetch_loc = old->prefetch_loc; new->actual_loc = old->actual_loc; new->granularity = old->granularity; - new->mapped_to_gpu = old->mapped_to_gpu; + new->mapping_done = old->mapping_done;bitmap_copy (new->bitmap_access, old->bitmap_access,MAX_GPU_INSTANCE );bitmap_copy (new->bitmap_aip, old->bitmap_aip,MAX_GPU_INSTANCE ); +bitmap_copy (new->bitmap_mapped, old->bitmap_mapped,MAX_GPU_INSTANCE );atomic_set (&new->queue_refcount,atomic_read (&old->queue_refcount));return 0 ;@@ -1421,7 +1427,8 @@ svm_range_unmap_from_gpu(struct amdgpu_device *adev, struct amdgpu_vm *vm,static int svm_range_unmap_from_gpus (struct svm_range *prange,unsigned long start, -unsigned long last,uint32_t trigger) +unsigned long last,unsigned long *bitmap_unmap, +uint32_t trigger) {struct kfd_process_device *pdd;struct dma_fence *fence =NULL ;@@ -1429,21 +1436,15 @@ svm_range_unmap_from_gpus(struct svm_range *prange, unsigned long start,uint32_t gpuidx;int r =0 ; -if (!prange->mapped_to_gpu) { -pr_debug ("prange 0x%p [0x%lx 0x%lx] not mapped to GPU\n" , - prange, prange->start, prange->last); -return 0 ; - } - -if (prange->start == start && prange->last == last) { -pr_debug ("unmap svms 0x%p prange 0x%p\n" , prange->svms, prange); - prange->mapped_to_gpu = false; - } - p = container_of(prange->svms, struct kfd_process, svms); -for_each_or_bit (gpuidx, prange->bitmap_access, prange->bitmap_aip,MAX_GPU_INSTANCE ) { -pr_debug ("unmap from gpu idx 0x%x\n" , gpuidx); +for_each_set_bit (gpuidx, bitmap_unmap,MAX_GPU_INSTANCE ) { +if (prange->start == start && prange->last == last) { +pr_debug ("unmap svms 0x%p prange 0x%p from gpu_idx 0x%x\n" , + prange->svms, prange, gpuidx); +clear_bit (gpuidx, prange->bitmap_mapped); + } + pdd =kfd_process_device_from_gpuidx (p, gpuidx);if (!pdd) {pr_debug ("failed to find device idx %d\n" , gpuidx);@@ -1596,6 +1597,8 @@ svm_range_map_to_gpus(struct svm_range *prange, unsigned long offset,continue ; } +set_bit (gpuidx, prange->bitmap_mapped); + r = svm_range_map_to_gpu(pdd, prange, offset, npages, readonly, prange->dma_addr[gpuidx], bo_adev, wait ? &fence : NULL,@@ -1741,7 +1744,9 @@ static int svm_range_validate_and_map(struct mm_struct *mm,bitmap_zero (ctx->bitmap,MAX_GPU_INSTANCE );bitmap_set (ctx->bitmap, gpuidx,1 ); }else if (ctx->process->xnack_enabled) { -bitmap_copy (ctx->bitmap, prange->bitmap_aip,MAX_GPU_INSTANCE ); +/* Update mapping on already mapped or access in place GPU */ +bitmap_or (ctx->bitmap, prange->bitmap_mapped, prange->bitmap_aip, +MAX_GPU_INSTANCE );/* If prefetch range to GPU, or GPU retry fault migrate range to * GPU, which has ACCESS attribute to the range, create mapping @@ -1761,14 +1766,12 @@ static int svm_range_validate_and_map(struct mm_struct *mm, }/* -* If prange is already mapped or with always mapped flag, -* update mapping on GPUs with ACCESS attribute +* If prange with always mapped flag, update mapping on GPUs with +* ACCESS attribute */ -if (bitmap_empty (ctx->bitmap,MAX_GPU_INSTANCE )) { -if (prange->mapped_to_gpu || - prange->flags &KFD_IOCTL_SVM_FLAG_GPU_ALWAYS_MAPPED ) -bitmap_copy (ctx->bitmap, prange->bitmap_access,MAX_GPU_INSTANCE ); - } +if (prange->flags &KFD_IOCTL_SVM_FLAG_GPU_ALWAYS_MAPPED ) +bitmap_or (ctx->bitmap, ctx->bitmap, prange->bitmap_access, +MAX_GPU_INSTANCE ); }else {bitmap_or (ctx->bitmap, prange->bitmap_access, prange->bitmap_aip,MAX_GPU_INSTANCE );@@ -1834,6 +1837,7 @@ static int svm_range_validate_and_map(struct mm_struct *mm, e =min (end, prange->last);if (e >= s) r =svm_range_unmap_from_gpus (prange, s, e, + prange->bitmap_mapped,KFD_SVM_UNMAP_TRIGGER_UNMAP_FROM_CPU );svm_range_unlock (prange);/* If unmap returns non-zero, we'll bail on the next for loop @@ -1896,7 +1900,9 @@ static int svm_range_validate_and_map(struct mm_struct *mm, }if (!r && next == end) - prange->mapped_to_gpu = true; + prange->mapping_done = true; +else + prange->mapping_done = false;svm_range_unlock (prange);@@ -2066,10 +2072,10 @@ svm_range_evict(struct svm_range *prange, struct mm_struct *mm,if (!p->xnack_enabled || (prange->flags &KFD_IOCTL_SVM_FLAG_GPU_ALWAYS_MAPPED )) {int evicted_ranges; -bool mapped = prange->mapped_to_gpu; +bool mapped = !bitmap_empty (prange->bitmap_mapped,MAX_GPU_INSTANCE );list_for_each_entry (pchild, &prange->child_list, child_list) { -if (!pchild->mapped_to_gpu) +if (bitmap_empty (pchild->bitmap_mapped,MAX_GPU_INSTANCE ))continue ; mapped = true;mutex_lock_nested (&pchild->lock,1 );@@ -2118,13 +2124,14 @@ svm_range_evict(struct svm_range *prange, struct mm_struct *mm, s =max (start, pchild->start); l =min (last, pchild->last);if (l >= s) -svm_range_unmap_from_gpus (pchild, s, l, trigger); +svm_range_unmap_from_gpus (pchild, s, l, prange->bitmap_mapped, + trigger);mutex_unlock (&pchild->lock); } s =max (start, prange->start); l =min (last, prange->last);if (l >= s) -svm_range_unmap_from_gpus (prange, s, l, trigger); +svm_range_unmap_from_gpus (prange, s, l, prange->bitmap_mapped, trigger); }return r;@@ -2154,10 +2161,11 @@ static struct svm_range *svm_range_clone(struct svm_range *old) new->prefetch_loc = old->prefetch_loc; new->actual_loc = old->actual_loc; new->granularity = old->granularity; - new->mapped_to_gpu = old->mapped_to_gpu; + new->mapping_done = old->mapping_done; new->vram_pages = old->vram_pages;bitmap_copy (new->bitmap_access, old->bitmap_access,MAX_GPU_INSTANCE );bitmap_copy (new->bitmap_aip, old->bitmap_aip,MAX_GPU_INSTANCE ); +bitmap_copy (new->bitmap_mapped, old->bitmap_mapped,MAX_GPU_INSTANCE );atomic_set (&new->queue_refcount,atomic_read (&old->queue_refcount));return new;@@ -2277,7 +2285,7 @@ svm_range_add(struct kfd_process *p, uint64_t start, uint64_t size, next_start =min (node->last, last) +1 ;if (svm_range_is_same_attrs (p, prange, nattr, attrs) && - prange->mapped_to_gpu) { + prange->mapping_done) {/* nothing to do */ }else if (node->start < start || node->last > last) {/* node intersects the update range and its attributes @@ -2626,14 +2634,14 @@ svm_range_unmap_from_cpu(struct mm_struct *mm, struct svm_range *prange, s =max (start, pchild->start); l =min (last, pchild->last);if (l >= s) -svm_range_unmap_from_gpus (pchild, s, l, trigger); +svm_range_unmap_from_gpus (pchild, s, l, prange->bitmap_mapped, trigger);svm_range_unmap_split (prange, pchild, start, last);mutex_unlock (&pchild->lock); } s =max (start, prange->start); l =min (last, prange->last);if (l >= s) -svm_range_unmap_from_gpus (prange, s, l, trigger); +svm_range_unmap_from_gpus (prange, s, l, prange->bitmap_mapped, trigger);svm_range_unmap_split (prange, prange, start, last);if (unmap_parent)@@ -3723,6 +3731,23 @@ static void svm_range_evict_svm_bo_worker(struct work_struct *work)svm_range_bo_unref (svm_bo); } +static bool svm_range_needs_unmap (struct kfd_process *p,struct svm_range *prange) +{ +if (bitmap_empty (prange->bitmap_needs_unmap,MAX_GPU_INSTANCE )) +return false; + +pr_debug ("prange 0x%p no access set for [0x%lx 0x%lx]\n" , + prange, prange->start, prange->last); + +svm_range_unmap_from_gpus (prange, prange->start, + prange->last, prange->bitmap_needs_unmap, +KFD_SVM_UNMAP_TRIGGER_UNMAP_FROM_CPU ); + +bitmap_clear (prange->bitmap_needs_unmap,0 ,MAX_GPU_INSTANCE ); + +return bitmap_empty (prange->bitmap_mapped,MAX_GPU_INSTANCE ); +} + static int svm_range_set_attr(struct kfd_process *p, struct mm_struct *mm, uint64_t start, uint64_t size, uint32_t nattr,@@ -3778,10 +3803,10 @@ svm_range_set_attr(struct kfd_process *p, struct mm_struct *mm,svm_range_add_to_svms (prange);svm_range_add_notifier_locked (mm, prange); } -list_for_each_entry (prange, &update_list, update_list) { + +list_for_each_entry (prange, &update_list, update_list)svm_range_apply_attrs (p, prange, nattr, attrs, &update_mapping); -/* TODO: unmap ranges from GPU that lost access */ - } + update_mapping |= !p->xnack_enabled && !list_empty (&remap_list);list_for_each_entry_safe (prange, next, &remove_list, update_list) {@@ -3802,6 +3827,9 @@ svm_range_set_attr(struct kfd_process *p, struct mm_struct *mm,list_for_each_entry (prange, &update_list, update_list) {bool migrated; +if (svm_range_needs_unmap (p, prange)) +continue ; +mutex_lock (&prange->migrate_mutex); r =svm_range_trigger_migration (mm, prange, &migrated);@@ -3810,7 +3838,7 @@ svm_range_set_attr(struct kfd_process *p, struct mm_struct *mm,if (migrated && (!p->xnack_enabled || (prange->flags &KFD_IOCTL_SVM_FLAG_GPU_ALWAYS_MAPPED )) && - prange->mapped_to_gpu) { + !bitmap_empty (prange->bitmap_mapped,MAX_GPU_INSTANCE )) {pr_debug ("restore_work will update mappings of GPUs\n" );mutex_unlock (&prange->migrate_mutex);continue ;@@ -3821,7 +3849,8 @@ svm_range_set_attr(struct kfd_process *p, struct mm_struct *mm,continue ; } - flush_tlb = !migrated && update_mapping && prange->mapped_to_gpu; + flush_tlb = !migrated && update_mapping && + !bitmap_empty (prange->bitmap_mapped,MAX_GPU_INSTANCE ); r =svm_range_validate_and_map (mm, prange->start, prange->last, prange,MAX_GPU_INSTANCE , true, true, flush_tlb);@@ -3835,11 +3864,13 @@ svm_range_set_attr(struct kfd_process *p, struct mm_struct *mm, }list_for_each_entry (prange, &remap_list, update_list) { + flush_tlb = !bitmap_empty (prange->bitmap_mapped,MAX_GPU_INSTANCE ); +pr_debug ("Remapping prange 0x%p [0x%lx 0x%lx]\n" , prange, prange->start, prange->last);mutex_lock (&prange->migrate_mutex); r =svm_range_validate_and_map (mm, prange->start, prange->last, prange, -MAX_GPU_INSTANCE , true, true, prange->mapped_to_gpu); +MAX_GPU_INSTANCE , true, true, flush_tlb);if (r)pr_debug ("failed %d on remap svm range\n" , r);mutex_unlock (&prange->migrate_mutex);drivers/gpu/drm/amd/amdkfd/kfd_svm.h +6
-1@@ -100,6 +100,9 @@ struct svm_work_list_item {* @child_list: list header for split ranges which are not added to svms yet * @bitmap_access: index bitmap of GPUs which can access the range * @bitmap_aip: index bitmap of GPUs which can access the range in place +* @bitmap_needs_unmap: index bitmap of GPUs which currently set NO_ACCESS +* @bitmap_mapped: index bitmap of GPUs which currently have the range mapped +* @mapping_done: true if range_validate_and_map complete successfully * * Data structure for virtual memory range shared by CPU and GPUs, it can be * allocated from system memory ram or device vram, and migrate from ram to vram @@ -135,7 +138,9 @@ struct svm_range {struct list_head child_list;DECLARE_BITMAP (bitmap_access,MAX_GPU_INSTANCE );DECLARE_BITMAP (bitmap_aip,MAX_GPU_INSTANCE ); -bool mapped_to_gpu; +DECLARE_BITMAP (bitmap_needs_unmap,MAX_GPU_INSTANCE ); +DECLARE_BITMAP (bitmap_mapped,MAX_GPU_INSTANCE ); +bool mapping_done;atomic_t queue_refcount; };