fix gmc page fault on navi1X
Subsystems (2)
v4 cover fix gmc page fault on navi1X
We hit gmc page fault on navi1X.
UMR tells that the physical address of pte is bad.
Two issues:
1) we did not sync job schedule fence while update mapping. fix it by adding bo fence to resv after every job submit.
2) we might unref page table bo during update ptes, at the same time, there is job pending on bo. and submit a job in commit after free bo. We need free the bo after adding all fence to bo.
change from v3:
use vm to get root bo resv.
add vm zombies list head.
change from v2:
use the correct page table bo resv
change from v1:
fix rebase issue.
xinhui pan (2):
drm_amdgpu: Add job fence to resv conditionally
drm/amdgpu: unref pt bo after job submit
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 24 ++++++++++++++++++--- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h | 3 +++ drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c | 4 +++- 3 files changed, 27 insertions(+), 4 deletions(-)
Signature · 6 lines
2.17.1 _______________________________________________ amd-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/amd-gfx
PATCH v4 1/2 drm_amdgpu: Add job fence to resv conditionally
Job fence on page table should be a shared one, so add it to the root page talbe bo resv.
--- drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c +3 -1
@@ -107,8 +107,10 @@ static int amdgpu_vm_sdma_commit(struct amdgpu_vm_update_params *p, tmp =dma_fence_get (f);if (p->direct)swap (p->vm->last_direct, tmp); -else +else { +dma_resv_add_shared_fence (p->vm->root.base.bo->tbo.base.resv, tmp);swap (p->vm->last_delayed, tmp); + }dma_fence_put (tmp);if (fence && !p->direct)
Signature · 6 lines
2.17.1 _______________________________________________ amd-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/amd-gfx
PATCH v4 2/2 drm/amdgpu: unref pt bo after job submit
In reply to xinhui panFree page table bo before job submit is insane. We might touch invalid memory while job is runnig.
we now have individualized bo resv during bo releasing. So any fences added to root PT bo is actually untested when a normal PT bo is releasing.
We might hit gmc page fault or memory just got overwrited.
--- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 24 +++++++++++++++++++++--- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h | 3 +++ 2 files changed, 24 insertions(+), 3 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +21 -3
@@ -937,6 +937,21 @@ static int amdgpu_vm_alloc_pts(struct amdgpu_device *adev,return r; } +static void amdgpu_vm_free_zombie_bo (struct amdgpu_device *adev, +struct amdgpu_vm *vm) +{ +struct amdgpu_vm_pt *entry; + +while (!list_empty (&vm->zombies)) { + entry = list_first_entry(&vm->zombies, struct amdgpu_vm_pt, + base.vm_status); +list_del (&entry->base.vm_status); + +amdgpu_bo_unref (&entry->base.bo->shadow); +amdgpu_bo_unref (&entry->base.bo); + } +} +/** * amdgpu_vm_free_table - fre one PD/PT *
@@ -945,10 +960,9 @@ static int amdgpu_vm_alloc_pts(struct amdgpu_device *adev,static void amdgpu_vm_free_table (struct amdgpu_vm_pt *entry) {if (entry->base.bo) { +list_move (&entry->base.vm_status, + &entry->base.bo->vm_bo->vm->zombies); entry->base.bo->vm_bo =NULL ; -list_del (&entry->base.vm_status); -amdgpu_bo_unref (&entry->base.bo->shadow); -amdgpu_bo_unref (&entry->base.bo); }kvfree (entry->entries); entry->entries =NULL ;
@@ -1624,6 +1638,7 @@ static int amdgpu_vm_bo_update_mapping(struct amdgpu_device *adev, r = vm->update_funcs->commit (¶ms, fence); error_unlock: +amdgpu_vm_free_zombie_bo (adev, vm);amdgpu_vm_eviction_unlock (vm);return r; }
@@ -2807,6 +2822,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,INIT_LIST_HEAD (&vm->invalidated);spin_lock_init (&vm->invalidated_lock);INIT_LIST_HEAD (&vm->freed); +INIT_LIST_HEAD (&vm->zombies);/* create scheduler entities for page table updates */
@@ -3119,6 +3135,8 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm) }amdgpu_vm_free_pts (adev, vm,NULL ); +amdgpu_vm_free_zombie_bo (adev, vm); +amdgpu_bo_unreserve (root);amdgpu_bo_unref (&root);WARN_ON (vm->root.base.bo);
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h +3 -0
@@ -269,6 +269,9 @@ struct amdgpu_vm {/* BO mappings freed, but not yet updated in the PT */ struct list_head freed; +/* BO will be freed soon */ +struct list_head zombies; +/* contains the page directory */ struct amdgpu_vm_pt root;struct dma_fence *last_update;
Signature · 6 lines
2.17.1 _______________________________________________ amd-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/amd-gfx
Re: [PATCH v4 2/2] drm/amdgpu: unref pt bo after job submit
This seems weird. This means that we update a page table, and then free it in the same amdgpu_vm_update_ptes call? That means the update is redundant. Can we eliminate the redundant PTE update if the page table is about to be freed anyway?
Regards,
Felix
Quoted 87 lines · xinhui pan
Free page table bo before job submit is insane. We might touch invalid memory while job is runnig.
we now have individualized bo resv during bo releasing. So any fences added to root PT bo is actually untested when a normal PT bo is releasing.
We might hit gmc page fault or memory just got overwrited.
Cc Christian König <[email protected]>Cc Alex Deucher <[email protected]>Cc Felix Kuehling <[email protected]>Signed-off-by xinhui pan <[email protected]>--- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 24 +++++++++++++++++++++--- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h | 3 +++ 2 files changed, 24 insertions(+), 3 deletions(-)drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +21
-3@@ -937,6 +937,21 @@ static int amdgpu_vm_alloc_pts(struct amdgpu_device *adev,return r; } +static void amdgpu_vm_free_zombie_bo (struct amdgpu_device *adev, +struct amdgpu_vm *vm) +{ +struct amdgpu_vm_pt *entry; + +while (!list_empty (&vm->zombies)) { + entry = list_first_entry(&vm->zombies, struct amdgpu_vm_pt, + base.vm_status); +list_del (&entry->base.vm_status); + +amdgpu_bo_unref (&entry->base.bo->shadow); +amdgpu_bo_unref (&entry->base.bo); + } +} +/** * amdgpu_vm_free_table - fre one PD/PT * @@ -945,10 +960,9 @@ static int amdgpu_vm_alloc_pts(struct amdgpu_device *adev,static void amdgpu_vm_free_table (struct amdgpu_vm_pt *entry) {if (entry->base.bo) { +list_move (&entry->base.vm_status, + &entry->base.bo->vm_bo->vm->zombies); entry->base.bo->vm_bo =NULL ; -list_del (&entry->base.vm_status); -amdgpu_bo_unref (&entry->base.bo->shadow); -amdgpu_bo_unref (&entry->base.bo); }kvfree (entry->entries); entry->entries =NULL ;@@ -1624,6 +1638,7 @@ static int amdgpu_vm_bo_update_mapping(struct amdgpu_device *adev, r = vm->update_funcs->commit (¶ms, fence); error_unlock: +amdgpu_vm_free_zombie_bo (adev, vm);amdgpu_vm_eviction_unlock (vm);return r; }@@ -2807,6 +2822,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,INIT_LIST_HEAD (&vm->invalidated);spin_lock_init (&vm->invalidated_lock);INIT_LIST_HEAD (&vm->freed); +INIT_LIST_HEAD (&vm->zombies);/* create scheduler entities for page table updates */ @@ -3119,6 +3135,8 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm) }amdgpu_vm_free_pts (adev, vm,NULL ); +amdgpu_vm_free_zombie_bo (adev, vm); +amdgpu_bo_unreserve (root);amdgpu_bo_unref (&root);WARN_ON (vm->root.base.bo);drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h +0
-0
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h struct amdgpu_vm { · line 277
Quoted 9 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h +3
-0@@ -269,6 +269,9 @@ struct amdgpu_vm {/* BO mappings freed, but not yet updated in the PT */ struct list_head freed; +/* BO will be freed soon */ +struct list_head zombies; +/* contains the page directory */ struct amdgpu_vm_pt root;struct dma_fence *last_update;
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
Christian König
maintainerRe: [PATCH v4 2/2] drm/amdgpu: unref pt bo after job submit
The page table is not updated and then freed. A higher level PDE is updated and because of this the lower level page tables is freed.
Without this it could be that the memory backing the freed page table is reused while the PDE is still pointing to it.
Rather unlikely that this causes problems, but better save than sorry.
Regards,
Christian.
Am 13.03.20 um 18:36 schrieb Felix Kuehling:
Quoted 93 lines
This seems weird. This means that we update a page table, and then free it in the same
amdgpu_vm_update_ptescall? That means the update is redundant. Can we eliminate the redundant PTE update if the page table is about to be freed anyway?Regards,
FelixQuoted 87 lines · xinhui pan
Free page table bo before job submit is insane. We might touch invalid memory while job is runnig.
we now have individualized bo resv during bo releasing. So any fences added to root PT bo is actually untested when a normal PT bo is releasing.
We might hit gmc page fault or memory just got overwrited.
Cc Christian König <[email protected]>Cc Alex Deucher <[email protected]>Cc Felix Kuehling <[email protected]>Signed-off-by xinhui pan <[email protected]>---
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c| 24 +++++++++++++++++++++---drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h| 3 +++2 files changed, 24 insertions(+), 3 deletions(-)drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +14
-0@@ -937,6 +937,21 @@ static int amdgpu_vm_alloc_pts(structamdgpu_device *adev, return r; } +static void amdgpu_vm_free_zombie_bo(struct amdgpu_device *adev, + struct amdgpu_vm *vm) +{ + struct amdgpu_vm_pt *entry; + + while (!list_empty(&vm->zombies)) { + entry = list_first_entry(&vm->zombies, struct amdgpu_vm_pt, + base.vm_status); + list_del(&entry->base.vm_status); + + amdgpu_bo_unref(&entry->base.bo->shadow); + amdgpu_bo_unref(&entry->base.bo); + } +} + /*** amdgpu_vm_free_table - fre one PD/PT *
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +2
-3@@ -945,10 +960,9 @@ static int amdgpu_vm_alloc_pts(structamdgpu_device *adev, static void amdgpu_vm_free_table(struct amdgpu_vm_pt *entry) { if (entry->base.bo) { + list_move(&entry->base.vm_status, + &entry->base.bo->vm_bo->vm->zombies); entry->base.bo->vm_bo = NULL; - list_del(&entry->base.vm_status); - amdgpu_bo_unref(&entry->base.bo->shadow); - amdgpu_bo_unref(&entry->base.bo); } kvfree(entry->entries);
entry->entries= NULL;drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +0
-0@@ -1624,6 +1638,7 @@ static int amdgpu_vm_bo_update_mapping(structamdgpu_device *adev, r = vm->update_funcs->commit(¶ms, fence);
error_unlock:
+amdgpu_vm_free_zombie_bo(adev, vm);
amdgpu_vm_eviction_unlock(vm);
return r;
}drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +3
-0@@ -2807,6 +2822,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev,struct amdgpu_vm *vm, INIT_LIST_HEAD(&vm->invalidated); spin_lock_init(&vm->invalidated_lock); INIT_LIST_HEAD(&vm->freed); + INIT_LIST_HEAD(&vm->zombies); /* create scheduler entities for page table updates */@@ -3119,6 +3135,8 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm) } amdgpu_vm_free_pts(adev, vm, NULL); + amdgpu_vm_free_zombie_bo(adev, vm); + amdgpu_bo_unreserve(root); amdgpu_bo_unref(&root); WARN_ON(vm->root.base.bo);drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h +0
-0@@ -269,6 +269,9 @@ struct amdgpu_vm {
Quoted 8 lines
Quoted 8 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h +0
-0/* BO mappings freed, but not yet updated in the PT */ struct list_head freed;+ /* BO will be freed soon */
+ struct list_head zombies;
+
/* contains the page directory */
struct amdgpu_vm_pt root;
struct dma_fence*last_update;
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
Re: [PATCH v4 2/2] drm/amdgpu: unref pt bo after job submit
hi, All
I think I found the root cause. here is what happened.
user: alloc/mapping memory
kernel: validate memory and update the bo mapping, and update the page table -> amdgpu_vm_bo_update_mapping -> amdgpu_vm_update_ptes -> amdgpu_vm_alloc_pts -> amdgpu_vm_clear_bo // it will submit a job and we have a fence. BUT it is NOT added in resv. user: free/unmapping memory kernel: unmapping mmeory and udpate the page table -> amdgpu_vm_bo_update_mapping sync last_delay fence if flag & AMDGPU_PTE_VALID // of source we did not sync it here, as this is unmapping. -> amdgpu_vm_update_ptes -> amdgpu_vm_free_pts // unref page table bo.
So from the sequence above, we know there is a race betwen bo releasing and bo clearing. bo might have been released before job running.
we can fix it in several ways,
1) sync last_delay in both mapping and unmapping case.
Chris, you just sync last_delay in mapping case, should it be ok to sync it also in unmapping case?
2) always add fence to resv after commit.
this is done by patchset v4. And only need patch 1. no need to move unref bo after commit.
3) move unref bo after commit, and add the last delay fence to resv. This is done by patchset V1.
any ideas?
thanks
xinhui
Quoted 100 lines
2020年3月14日 02:05,Koenig, Christian <[email protected]> 写道:
The page table is not updated and then freed. A higher level PDE is updated and because of this the lower level page tables is freed.
Without this it could be that the memory backing the freed page table is reused while the PDE is still pointing to it.
Rather unlikely that this causes problems, but better save than sorry.
Regards,
Christian.Am 13.03.20 um 18:36 schrieb Felix Kuehling:
Quoted 88 lines
This seems weird. This means that we update a page table, and then free it in the same
amdgpu_vm_update_ptescall? That means the update is redundant. Can we eliminate the redundant PTE update if the page table is about to be freed anyway?Regards,
FelixQuoted 82 lines · xinhui pan
Free page table bo before job submit is insane. We might touch invalid memory while job is runnig.
we now have individualized bo resv during bo releasing. So any fences added to root PT bo is actually untested when a normal PT bo is releasing.
We might hit gmc page fault or memory just got overwrited.
Cc Christian König <[email protected]>Cc Alex Deucher <[email protected]>Cc Felix Kuehling <[email protected]>Signed-off-by xinhui pan <[email protected]>--- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 24 +++++++++++++++++++++--- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h | 3 +++ 2 files changed, 24 insertions(+), 3 deletions(-)drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +20
-3@@ -937,6 +937,21 @@ static int amdgpu_vm_alloc_pts(struct amdgpu_device *adev,return r; } +static void amdgpu_vm_free_zombie_bo(struct amdgpu_device *adev, +struct amdgpu_vm *vm) +{ +struct amdgpu_vm_pt *entry; + +while (!list_empty (&vm->zombies)) { + entry = list_first_entry(&vm->zombies, struct amdgpu_vm_pt, + base.vm_status); +list_del (&entry->base.vm_status); + +amdgpu_bo_unref (&entry->base.bo->shadow); +amdgpu_bo_unref (&entry->base.bo); + } +} +/** * amdgpu_vm_free_table - fre one PD/PT * @@ -945,10 +960,9 @@ static int amdgpu_vm_alloc_pts(struct amdgpu_device *adev,static void amdgpu_vm_free_table (struct amdgpu_vm_pt *entry) {if (entry->base.bo) { +list_move (&entry->base.vm_status, + &entry->base.bo->vm_bo->vm->zombies); entry->base.bo->vm_bo =NULL ; -list_del (&entry->base.vm_status); -amdgpu_bo_unref (&entry->base.bo->shadow); -amdgpu_bo_unref (&entry->base.bo); }kvfree (entry->entries); entry->entries =NULL ;@@ -1624,6 +1638,7 @@ static int amdgpu_vm_bo_update_mapping(struct amdgpu_device *adev, r = vm->update_funcs->commit (¶ms, fence); error_unlock: +amdgpu_vm_free_zombie_bo (adev, vm);amdgpu_vm_eviction_unlock (vm);return r; }@@ -2807,6 +2822,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,INIT_LIST_HEAD (&vm->invalidated);spin_lock_init (&vm->invalidated_lock);INIT_LIST_HEAD (&vm->freed); +INIT_LIST_HEAD (&vm->zombies);/* create scheduler entities for page table updates */ @@ -3119,6 +3135,8 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm) }amdgpu_vm_free_pts (adev, vm,NULL ); +amdgpu_vm_free_zombie_bo (adev, vm); +amdgpu_bo_unreserve (root);amdgpu_bo_unref (&root);WARN_ON (vm->root.base.bo);drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h +0
-0@@ -269,6 +269,9 @@ struct amdgpu_vm {
Quoted 9 lines
Quoted 8 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h struct amdgpu_vm { · line 277
Quoted 8 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h +2
-0/* BO mappings freed, but not yet updated in the PT */ struct list_head freed; +/* BO will be freed soon */ + struct list_head zombies; +/* contains the page directory */ struct amdgpu_vm_pt root;struct dma_fence *last_update;
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
RE: [PATCH v4 2/2] drm/amdgpu: unref pt bo after job submit
Hi Xinhui
I encounter the same problem(page fault) when test vk_example benchmark. I use your first option which can fix the problem. Can you help submit one patch?
- if (flags & AMDGPU_PTE_VALID) {
- struct amdgpu_bo *root = vm->root.base.bo;
- if (!dma_fence_is_signaled(vm->last_direct))
- amdgpu_bo_fence(root, vm->last_direct, true);
+ if (!dma_fence_is_signaled(vm->last_direct))
+ amdgpu_bo_fence(root, vm->last_direct, true);
- if (!dma_fence_is_signaled(vm->last_delayed))
- amdgpu_bo_fence(root, vm->last_delayed, true);
- }
+ if (!dma_fence_is_signaled(vm->last_delayed))
+ amdgpu_bo_fence(root, vm->last_delayed, true);
Best Regards
Yintian Tao
-----Original Message-----
From: amd-gfx <[email protected]> On Behalf Of Pan, Xinhui
Sent: 2020年3月14日 21:07
To: Koenig, Christian <[email protected]>
Cc: Deucher, Alexander <[email protected]>; Kuehling, Felix <[email protected]>; Pan, Xinhui <[email protected]>; [email protected]
Subject: Re: [PATCH v4 2/2] drm/amdgpu: unref pt bo after job submit
hi, All
I think I found the root cause. here is what happened.
user: alloc/mapping memory
kernel: validate memory and update the bo mapping, and update the page table -> amdgpu_vm_bo_update_mapping -> amdgpu_vm_update_ptes -> amdgpu_vm_alloc_pts -> amdgpu_vm_clear_bo // it will submit a job and we have a fence. BUT it is NOT added in resv. user: free/unmapping memory kernel: unmapping mmeory and udpate the page table -> amdgpu_vm_bo_update_mapping sync last_delay fence if flag & AMDGPU_PTE_VALID // of source we did not sync it here, as this is unmapping. -> amdgpu_vm_update_ptes -> amdgpu_vm_free_pts // unref page table bo.
So from the sequence above, we know there is a race betwen bo releasing and bo clearing. bo might have been released before job running.
we can fix it in several ways,
1) sync last_delay in both mapping and unmapping case.
Chris, you just sync last_delay in mapping case, should it be ok to sync it also in unmapping case?
2) always add fence to resv after commit.
this is done by patchset v4. And only need patch 1. no need to move unref bo after commit.
3) move unref bo after commit, and add the last delay fence to resv. This is done by patchset V1.
any ideas?
thanks
xinhui
Quoted 102 lines
2020年3月14日 02:05,Koenig, Christian <[email protected]> 写道:
The page table is not updated and then freed. A higher level PDE is updated and because of this the lower level page tables is freed.
Without this it could be that the memory backing the freed page table is reused while the PDE is still pointing to it.
Rather unlikely that this causes problems, but better save than sorry.
Regards,
Christian.Am 13.03.20 um 18:36 schrieb Felix Kuehling:
Quoted 90 lines
This seems weird. This means that we update a page table, and then free it in the same
amdgpu_vm_update_ptescall? That means the update is redundant. Can we eliminate the redundant PTE update if the page table is about to be freed anyway?Regards,
FelixQuoted 84 lines · xinhui pan
Free page table bo before job submit is insane. We might touch invalid memory while job is runnig.
we now have individualized bo resv during bo releasing. So any fences added to root PT bo is actually untested when a normal PT bo is releasing.
We might hit gmc page fault or memory just got overwrited.
Cc Christian König <[email protected]>Cc Alex Deucher <[email protected]>Cc Felix Kuehling <[email protected]>Signed-off-by xinhui pan <[email protected]>--- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 24 +++++++++++++++++++++--- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h | 3 +++ 2 files changed, 24 insertions(+), 3 deletions(-)drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +20
-4@@ -937,6 +937,21 @@ static int amdgpu_vm_alloc_pts(struct amdgpu_device *adev,return r; } +static void amdgpu_vm_free_zombie_bo(struct amdgpu_device *adev, +struct amdgpu_vm *vm) +{ +struct amdgpu_vm_pt *entry; + +while (!list_empty (&vm->zombies)) { + entry = list_first_entry(&vm->zombies, struct amdgpu_vm_pt, + base.vm_status); +list_del (&entry->base.vm_status); + +amdgpu_bo_unref (&entry->base.bo->shadow); +amdgpu_bo_unref (&entry->base.bo); + } +} +/** * amdgpu_vm_free_table - fre one PD/PT * @@ -945,10 +960,9 @@ static int amdgpu_vm_alloc_pts(struct amdgpu_device *adev,static void amdgpu_vm_free_table (struct amdgpu_vm_pt *entry) {if (entry->base.bo) { +list_move (&entry->base.vm_status, + &entry->base.bo->vm_bo->vm->zombies); entry->base.bo->vm_bo =NULL ; -list_del (&entry->base.vm_status); -amdgpu_bo_unref (&entry->base.bo->shadow); -amdgpu_bo_unref (&entry->base.bo); }kvfree (entry->entries); entry->entries =NULL ;@@ -1624,6 +1638,7 @@ static int amdgpu_vm_bo_update_mapping(struct amdgpu_device *adev, r = vm->update_funcs->commit (¶ms, fence); error_unlock: +amdgpu_vm_free_zombie_bo (adev, vm);amdgpu_vm_eviction_unlock (vm);return r; }@@ -2807,6 +2822,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,INIT_LIST_HEAD (&vm->invalidated);spin_lock_init (&vm->invalidated_lock);INIT_LIST_HEAD (&vm->freed); +INIT_LIST_HEAD (&vm->zombies); /* create scheduler entities for page table updates */ @@ -3119,6 +3135,8 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm) }amdgpu_vm_free_pts (adev, vm,NULL ); +amdgpu_vm_free_zombie_bo (adev, vm); +amdgpu_bo_unreserve (root);amdgpu_bo_unref (&root);WARN_ON (vm->root.base.bo);drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h +0
-0@@ -269,6 +269,9 @@ struct amdgpu_vm {
Quoted 9 lines
Quoted 8 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h struct amdgpu_vm { · line 277
Quoted 8 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h +2
-0/* BO mappings freed, but not yet updated in the PT */ struct list_head freed; +/* BO will be freed soon */ + struct list_head zombies; +/* contains the page directory */ struct amdgpu_vm_pt root;struct dma_fence *last_update;
_______________________________________________
amd-gfx mailing list
[email protected]
https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Flists.freedesktop.org%2Fmailman%2Flistinfo%2Famd-gfx&data=02%7C01%7Cyintian.tao%40amd.com%7C580c8ec15d484bf546b208d7c8188cc2%7C3dd8961fe4884e608e11a82d994e183d%7C0%7C0%7C637197880120611671&sdata=dqSLasyuZhQskB38Kib6g8lQR9iMnyxFxfHGXXENoDc%3D&reserved=0
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
Re: [PATCH v4 2/2] drm/amdgpu: unref pt bo after job submit
[AMD Official Use Only - Internal Distribution Only]
I still hit page fault with option 1 while running oclperf test.
Looks like we need sync fence after commit.
________________________________
From: Tao, Yintian <[email protected]>
Sent: Monday, March 16, 2020 4:15:01 PM
To: Pan, Xinhui <[email protected]>; Koenig, Christian <[email protected]>
Cc: Deucher, Alexander <[email protected]>; Kuehling, Felix <[email protected]>; Pan, Xinhui <[email protected]>; [email protected] <[email protected]>
Subject: RE: [PATCH v4 2/2] drm/amdgpu: unref pt bo after job submit
Hi Xinhui
I encounter the same problem(page fault) when test vk_example benchmark. I use your first option which can fix the problem. Can you help submit one patch?
- if (flags & AMDGPU_PTE_VALID) {
- struct amdgpu_bo *root = vm->root.base.bo;
- if (!dma_fence_is_signaled(vm->last_direct))
- amdgpu_bo_fence(root, vm->last_direct, true);
+ if (!dma_fence_is_signaled(vm->last_direct))
+ amdgpu_bo_fence(root, vm->last_direct, true);
- if (!dma_fence_is_signaled(vm->last_delayed))
- amdgpu_bo_fence(root, vm->last_delayed, true);
- }
+ if (!dma_fence_is_signaled(vm->last_delayed))
+ amdgpu_bo_fence(root, vm->last_delayed, true);
Best Regards
Yintian Tao
-----Original Message-----
From: amd-gfx <[email protected]> On Behalf Of Pan, Xinhui
Sent: 2020年3月14日 21:07
To: Koenig, Christian <[email protected]>
Cc: Deucher, Alexander <[email protected]>; Kuehling, Felix <[email protected]>; Pan, Xinhui <[email protected]>; [email protected]
Subject: Re: [PATCH v4 2/2] drm/amdgpu: unref pt bo after job submit
hi, All
I think I found the root cause. here is what happened.
user: alloc/mapping memory
kernel: validate memory and update the bo mapping, and update the page table
-> amdgpu_vm_bo_update_mapping
-> amdgpu_vm_update_ptes
-> amdgpu_vm_alloc_pts
-> amdgpu_vm_clear_bo // it will submit a job and we have a fence. BUT it is NOT added in resv.
user: free/unmapping memory
kernel: unmapping mmeory and udpate the page table
-> amdgpu_vm_bo_update_mapping
sync last_delay fence if flag & AMDGPU_PTE_VALID // of source we did not sync it here, as this is unmapping.
-> amdgpu_vm_update_ptes
-> amdgpu_vm_free_pts // unref page table bo.So from the sequence above, we know there is a race betwen bo releasing and bo clearing. bo might have been released before job running.
we can fix it in several ways,
1) sync last_delay in both mapping and unmapping case.
Chris, you just sync last_delay in mapping case, should it be ok to sync it also in unmapping case?
2) always add fence to resv after commit.
this is done by patchset v4. And only need patch 1. no need to move unref bo after commit.
3) move unref bo after commit, and add the last delay fence to resv. This is done by patchset V1.
any ideas?
thanks
xinhui
Quoted 102 lines
2020年3月14日 02:05,Koenig, Christian <[email protected]> 写道:
The page table is not updated and then freed. A higher level PDE is updated and because of this the lower level page tables is freed.
Without this it could be that the memory backing the freed page table is reused while the PDE is still pointing to it.
Rather unlikely that this causes problems, but better save than sorry.
Regards,
Christian.Am 13.03.20 um 18:36 schrieb Felix Kuehling:
Quoted 90 lines
This seems weird. This means that we update a page table, and then free it in the same
amdgpu_vm_update_ptescall? That means the update is redundant. Can we eliminate the redundant PTE update if the page table is about to be freed anyway?Regards,
FelixQuoted 84 lines · xinhui pan
Free page table bo before job submit is insane. We might touch invalid memory while job is runnig.
we now have individualized bo resv during bo releasing. So any fences added to root PT bo is actually untested when a normal PT bo is releasing.
We might hit gmc page fault or memory just got overwrited.
Cc Christian König <[email protected]>Cc Alex Deucher <[email protected]>Cc Felix Kuehling <[email protected]>Signed-off-by xinhui pan <[email protected]>--- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 24 +++++++++++++++++++++--- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h | 3 +++ 2 files changed, 24 insertions(+), 3 deletions(-)drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +20
-4@@ -937,6 +937,21 @@ static int amdgpu_vm_alloc_pts(struct amdgpu_device *adev,return r; } +static void amdgpu_vm_free_zombie_bo(struct amdgpu_device *adev, +struct amdgpu_vm *vm) +{ +struct amdgpu_vm_pt *entry; + +while (!list_empty (&vm->zombies)) { + entry = list_first_entry(&vm->zombies, struct amdgpu_vm_pt, + base.vm_status); +list_del (&entry->base.vm_status); + +amdgpu_bo_unref (&entry->base.bo->shadow); +amdgpu_bo_unref (&entry->base.bo); + } +} +/** * amdgpu_vm_free_table - fre one PD/PT * @@ -945,10 +960,9 @@ static int amdgpu_vm_alloc_pts(struct amdgpu_device *adev,static void amdgpu_vm_free_table (struct amdgpu_vm_pt *entry) {if (entry->base.bo) { +list_move (&entry->base.vm_status, + &entry->base.bo->vm_bo->vm->zombies); entry->base.bo->vm_bo =NULL ; -list_del (&entry->base.vm_status); -amdgpu_bo_unref (&entry->base.bo->shadow); -amdgpu_bo_unref (&entry->base.bo); }kvfree (entry->entries); entry->entries =NULL ;@@ -1624,6 +1638,7 @@ static int amdgpu_vm_bo_update_mapping(struct amdgpu_device *adev, r = vm->update_funcs->commit (¶ms, fence); error_unlock: +amdgpu_vm_free_zombie_bo (adev, vm);amdgpu_vm_eviction_unlock (vm);return r; }@@ -2807,6 +2822,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,INIT_LIST_HEAD (&vm->invalidated);spin_lock_init (&vm->invalidated_lock);INIT_LIST_HEAD (&vm->freed); +INIT_LIST_HEAD (&vm->zombies); /* create scheduler entities for page table updates */ @@ -3119,6 +3135,8 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm) }amdgpu_vm_free_pts (adev, vm,NULL ); +amdgpu_vm_free_zombie_bo (adev, vm); +amdgpu_bo_unreserve (root);amdgpu_bo_unref (&root);WARN_ON (vm->root.base.bo);drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h +0
-0@@ -269,6 +269,9 @@ struct amdgpu_vm {
Quoted 9 lines
Quoted 8 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h struct amdgpu_vm { · line 277
Quoted 8 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h +2
-0/* BO mappings freed, but not yet updated in the PT */ struct list_head freed; +/* BO will be freed soon */ + struct list_head zombies; +/* contains the page directory */ struct amdgpu_vm_pt root;struct dma_fence *last_update;
_______________________________________________
amd-gfx mailing list
[email protected]
https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Flists.freedesktop.org%2Fmailman%2Flistinfo%2Famd-gfx&data=02%7C01%7Cyintian.tao%40amd.com%7C580c8ec15d484bf546b208d7c8188cc2%7C3dd8961fe4884e608e11a82d994e183d%7C0%7C0%7C637197880120611671&sdata=dqSLasyuZhQskB38Kib6g8lQR9iMnyxFxfHGXXENoDc%3D&reserved=0
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
RE: [PATCH v4 2/2] drm/amdgpu: unref pt bo after job submit
Hi Xinhui
Sure, can you submit one patch for it? I want to test it on my local server. Thanks in advance.
Best Regards
Yintian Tao
From: Pan, Xinhui <[email protected]>
Sent: 2020年3月16日 17:51
To: Koenig, Christian <[email protected]>; Tao, Yintian <[email protected]>
Cc: Deucher, Alexander <[email protected]>; Kuehling, Felix <[email protected]>; [email protected]
Subject: Re: [PATCH v4 2/2] drm/amdgpu: unref pt bo after job submit
[AMD Official Use Only - Internal Distribution Only]
I still hit page fault with option 1 while running oclperf test.
Looks like we need sync fence after commit.
________________________________
From: Tao, Yintian <[email protected]<mailto:[email protected]>>
Sent: Monday, March 16, 2020 4:15:01 PM
To: Pan, Xinhui <[email protected]<mailto:[email protected]>>; Koenig, Christian <[email protected]<mailto:[email protected]>>
Cc: Deucher, Alexander <[email protected]<mailto:[email protected]>>; Kuehling, Felix <[email protected]<mailto:[email protected]>>; Pan, Xinhui <[email protected]<mailto:[email protected]>>; [email protected]<mailto:[email protected]> <[email protected]<mailto:[email protected]>>
Subject: RE: [PATCH v4 2/2] drm/amdgpu: unref pt bo after job submit
Hi Xinhui
I encounter the same problem(page fault) when test vk_example benchmark. I use your first option which can fix the problem. Can you help submit one patch?
- if (flags & AMDGPU_PTE_VALID) {
- struct amdgpu_bo *root = vm->root.base.bo;
- if (!dma_fence_is_signaled(vm->last_direct))
- amdgpu_bo_fence(root, vm->last_direct, true);
+ if (!dma_fence_is_signaled(vm->last_direct))
+ amdgpu_bo_fence(root, vm->last_direct, true);
- if (!dma_fence_is_signaled(vm->last_delayed))
- amdgpu_bo_fence(root, vm->last_delayed, true);
- }
+ if (!dma_fence_is_signaled(vm->last_delayed))
+ amdgpu_bo_fence(root, vm->last_delayed, true);
Best Regards
Yintian Tao
-----Original Message-----
From: amd-gfx <[email protected]<mailto:[email protected]>> On Behalf Of Pan, Xinhui
Sent: 2020年3月14日 21:07
To: Koenig, Christian <[email protected]<mailto:[email protected]>>
Cc: Deucher, Alexander <[email protected]<mailto:[email protected]>>; Kuehling, Felix <[email protected]<mailto:[email protected]>>; Pan, Xinhui <[email protected]<mailto:[email protected]>>; [email protected]<mailto:[email protected]>
Subject: Re: [PATCH v4 2/2] drm/amdgpu: unref pt bo after job submit
hi, All
I think I found the root cause. here is what happened.
user: alloc/mapping memory
kernel: validate memory and update the bo mapping, and update the page table
-> amdgpu_vm_bo_update_mapping
-> amdgpu_vm_update_ptes
-> amdgpu_vm_alloc_pts
-> amdgpu_vm_clear_bo // it will submit a job and we have a fence. BUT it is NOT added in resv.
user: free/unmapping memory
kernel: unmapping mmeory and udpate the page table
-> amdgpu_vm_bo_update_mapping
sync last_delay fence if flag & AMDGPU_PTE_VALID // of source we did not sync it here, as this is unmapping.
-> amdgpu_vm_update_ptes
-> amdgpu_vm_free_pts // unref page table bo.So from the sequence above, we know there is a race betwen bo releasing and bo clearing. bo might have been released before job running.
we can fix it in several ways,
1) sync last_delay in both mapping and unmapping case.
Chris, you just sync last_delay in mapping case, should it be ok to sync it also in unmapping case?
2) always add fence to resv after commit.
this is done by patchset v4. And only need patch 1. no need to move unref bo after commit.
3) move unref bo after commit, and add the last delay fence to resv. This is done by patchset V1.
any ideas?
thanks
xinhui
Quoted 102 lines
2020年3月14日 02:05,Koenig, Christian <[email protected]<mailto:[email protected]>> 写道:
The page table is not updated and then freed. A higher level PDE is updated and because of this the lower level page tables is freed.
Without this it could be that the memory backing the freed page table is reused while the PDE is still pointing to it.
Rather unlikely that this causes problems, but better save than sorry.
Regards,
Christian.Am 13.03.20 um 18:36 schrieb Felix Kuehling:
Quoted 90 lines
This seems weird. This means that we update a page table, and then free it in the same
amdgpu_vm_update_ptescall? That means the update is redundant. Can we eliminate the redundant PTE update if the page table is about to be freed anyway?Regards,
FelixQuoted 84 lines · xinhui pan
Free page table bo before job submit is insane. We might touch invalid memory while job is runnig.
we now have individualized bo resv during bo releasing. So any fences added to root PT bo is actually untested when a normal PT bo is releasing.
We might hit gmc page fault or memory just got overwrited.
Cc Christian König <[email protected]<mailto:[email protected]>>Cc Alex Deucher <[email protected]<mailto:[email protected]>>Cc Felix Kuehling <[email protected]<mailto:[email protected]>>Signed-off-by xinhui pan <[email protected]<mailto:[email protected]>>--- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 24 +++++++++++++++++++++--- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h | 3 +++ 2 files changed, 24 insertions(+), 3 deletions(-)drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +20
-4@@ -937,6 +937,21 @@ static int amdgpu_vm_alloc_pts(struct amdgpu_device *adev,return r; } +static void amdgpu_vm_free_zombie_bo(struct amdgpu_device *adev, +struct amdgpu_vm *vm) +{ +struct amdgpu_vm_pt *entry; + +while (!list_empty (&vm->zombies)) { + entry = list_first_entry(&vm->zombies, struct amdgpu_vm_pt, + base.vm_status); +list_del (&entry->base.vm_status); + +amdgpu_bo_unref (&entry->base.bo->shadow); +amdgpu_bo_unref (&entry->base.bo); + } +} +/** * amdgpu_vm_free_table - fre one PD/PT * @@ -945,10 +960,9 @@ static int amdgpu_vm_alloc_pts(struct amdgpu_device *adev,static void amdgpu_vm_free_table (struct amdgpu_vm_pt *entry) {if (entry->base.bo) { +list_move (&entry->base.vm_status, + &entry->base.bo->vm_bo->vm->zombies); entry->base.bo->vm_bo =NULL ; -list_del (&entry->base.vm_status); -amdgpu_bo_unref (&entry->base.bo->shadow); -amdgpu_bo_unref (&entry->base.bo); }kvfree (entry->entries); entry->entries =NULL ;@@ -1624,6 +1638,7 @@ static int amdgpu_vm_bo_update_mapping(struct amdgpu_device *adev, r = vm->update_funcs->commit (¶ms, fence); error_unlock: +amdgpu_vm_free_zombie_bo (adev, vm);amdgpu_vm_eviction_unlock (vm);return r; }@@ -2807,6 +2822,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,INIT_LIST_HEAD (&vm->invalidated);spin_lock_init (&vm->invalidated_lock);INIT_LIST_HEAD (&vm->freed); +INIT_LIST_HEAD (&vm->zombies); /* create scheduler entities for page table updates */ @@ -3119,6 +3135,8 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm) }amdgpu_vm_free_pts (adev, vm,NULL ); +amdgpu_vm_free_zombie_bo (adev, vm); +amdgpu_bo_unreserve (root);amdgpu_bo_unref (&root);WARN_ON (vm->root.base.bo);drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h +0
-0@@ -269,6 +269,9 @@ struct amdgpu_vm {
Quoted 9 lines
Quoted 8 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h struct amdgpu_vm { · line 277
Quoted 8 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h +2
-0/* BO mappings freed, but not yet updated in the PT */ struct list_head freed; +/* BO will be freed soon */ + struct list_head zombies; +/* contains the page directory */ struct amdgpu_vm_pt root;struct dma_fence *last_update;
_______________________________________________
amd-gfx mailing list [email protected]<mailto:[email protected]>
https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Flists.freedesktop.org%2Fmailman%2Flistinfo%2Famd-gfx&data=02%7C01%7Cyintian.tao%40amd.com%7C580c8ec15d484bf546b208d7c8188cc2%7C3dd8961fe4884e608e11a82d994e183d%7C0%7C0%7C637197880120611671&sdata=dqSLasyuZhQskB38Kib6g8lQR9iMnyxFxfHGXXENoDc%3D&reserved=0
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
Christian König
maintainerRe: [PATCH v4 2/2] drm/amdgpu: unref pt bo after job submit
In reply to Tao, YintianHi Xinhui,
well that is quite an impressive analyses of the problem.
Quoted 1 line
should it be ok to sync it also in unmapping case?
Short answer no, but I think I need to get back to the drawing board with the direct unmapping case anyway.
Quoted 1 line
2) always add fence to resv after commit.
Yes, let's stick with that for now.
We also need to reinstate to ignore VM updates in the synchronization for good performance now, but I can take care of this.
Regards,
Christian.
Am 16.03.20 um 09:15 schrieb Tao, Yintian:
Quoted 172 lines
Hi Xinhui
I encounter the same problem(page fault) when test
vk_examplebenchmark. I use your first option which can fix the problem. Can you help submit one patch?(quoted diff) +4
-7- if (flags & AMDGPU_PTE_VALID) { - struct amdgpu_bo *root = vm->root.base.bo; - if (!dma_fence_is_signaled(vm->last_direct)) - amdgpu_bo_fence(root, vm->last_direct, true); + if (!dma_fence_is_signaled(vm->last_direct)) + amdgpu_bo_fence(root, vm->last_direct, true); - if (!dma_fence_is_signaled(vm->last_delayed)) - amdgpu_bo_fence(root, vm->last_delayed, true); - } + if (!dma_fence_is_signaled(vm->last_delayed)) + amdgpu_bo_fence(root, vm->last_delayed, true);Best Regards
Yintian Tao-----Original Message-----
From: amd-gfx <[email protected]> On Behalf Of Pan, Xinhui
Sent: 2020年3月14日 21:07
To: Koenig, Christian <[email protected]>
Cc: Deucher, Alexander <[email protected]>; Kuehling, Felix <[email protected]>; Pan, Xinhui <[email protected]>; [email protected]
Subject: Re: [PATCH v4 2/2] drm/amdgpu: unref pt bo after job submithi, All
I think I found the root cause. here is what happened.user: alloc/mapping memory
kernel: validate memory and update the bo mapping, and update the page table -> amdgpu_vm_bo_update_mapping -> amdgpu_vm_update_ptes -> amdgpu_vm_alloc_pts -> amdgpu_vm_clear_bo // it will submit a job and we have a fence. BUT it is NOT added in resv. user: free/unmapping memory kernel: unmapping mmeory and udpate the page table -> amdgpu_vm_bo_update_mapping sync last_delay fence if flag & AMDGPU_PTE_VALID // of source we did not sync it here, as this is unmapping. -> amdgpu_vm_update_ptes -> amdgpu_vm_free_pts // unref page table bo.So from the sequence above, we know there is a race betwen bo releasing and bo clearing. bo might have been released before job running.
we can fix it in several ways,
1) synclast_delayin both mapping and unmapping case.
Chris, you just synclast_delayin mapping case, should it be ok to sync it also in unmapping case?2) always add fence to resv after commit.
this is done by patchset v4. And only need patch 1. no need to move unref bo after commit.3) move unref bo after commit, and add the last delay fence to resv. This is done by patchset V1.
any ideas?
thanks
xinhuiQuoted 106 lines
2020年3月14日 02:05,Koenig, Christian <[email protected]> 写道:
The page table is not updated and then freed. A higher level PDE is updated and because of this the lower level page tables is freed.
Without this it could be that the memory backing the freed page table is reused while the PDE is still pointing to it.
Rather unlikely that this causes problems, but better save than sorry.
Regards,
Christian.Am 13.03.20 um 18:36 schrieb Felix Kuehling:
Quoted 94 lines
This seems weird. This means that we update a page table, and then free it in the same
amdgpu_vm_update_ptescall? That means the update is redundant. Can we eliminate the redundant PTE update if the page table is about to be freed anyway?Regards,
FelixQuoted 88 lines · xinhui pan
Free page table bo before job submit is insane. We might touch invalid memory while job is runnig.
we now have individualized bo resv during bo releasing. So any fences added to root PT bo is actually untested when a normal PT bo is releasing.
We might hit gmc page fault or memory just got overwrited.
Cc Christian König <[email protected]>Cc Alex Deucher <[email protected]>Cc Felix Kuehling <[email protected]>Signed-off-by xinhui pan <[email protected]>--- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 24 +++++++++++++++++++++--- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h | 3 +++ 2 files changed, 24 insertions(+), 3 deletions(-)drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +20
-4@@ -937,6 +937,21 @@ static int amdgpu_vm_alloc_pts(struct amdgpu_device *adev,return r; } +static void amdgpu_vm_free_zombie_bo(struct amdgpu_device *adev, +struct amdgpu_vm *vm) +{ +struct amdgpu_vm_pt *entry; + +while (!list_empty (&vm->zombies)) { + entry = list_first_entry(&vm->zombies, struct amdgpu_vm_pt, + base.vm_status); +list_del (&entry->base.vm_status); + +amdgpu_bo_unref (&entry->base.bo->shadow); +amdgpu_bo_unref (&entry->base.bo); + } +} +/** * amdgpu_vm_free_table - fre one PD/PT * @@ -945,10 +960,9 @@ static int amdgpu_vm_alloc_pts(struct amdgpu_device *adev,static void amdgpu_vm_free_table (struct amdgpu_vm_pt *entry) {if (entry->base.bo) { +list_move (&entry->base.vm_status, + &entry->base.bo->vm_bo->vm->zombies); entry->base.bo->vm_bo =NULL ; -list_del (&entry->base.vm_status); -amdgpu_bo_unref (&entry->base.bo->shadow); -amdgpu_bo_unref (&entry->base.bo); }kvfree (entry->entries); entry->entries =NULL ;@@ -1624,6 +1638,7 @@ static int amdgpu_vm_bo_update_mapping(struct amdgpu_device *adev, r = vm->update_funcs->commit (¶ms, fence); error_unlock: +amdgpu_vm_free_zombie_bo (adev, vm);amdgpu_vm_eviction_unlock (vm);return r; }@@ -2807,6 +2822,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,INIT_LIST_HEAD (&vm->invalidated);spin_lock_init (&vm->invalidated_lock);INIT_LIST_HEAD (&vm->freed); +INIT_LIST_HEAD (&vm->zombies); /* create scheduler entities for page table updates */ @@ -3119,6 +3135,8 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm) }amdgpu_vm_free_pts (adev, vm,NULL ); +amdgpu_vm_free_zombie_bo (adev, vm); +amdgpu_bo_unreserve (root);amdgpu_bo_unref (&root);WARN_ON (vm->root.base.bo);drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h +1
-0@@ -269,6 +269,9 @@ struct amdgpu_vm {/* BO mappings freed, but not yet updated in the PT */ struct list_head freed; +/* BO will be freed soon */ + struct list_head zombies;
Quoted 8 lines
Quoted 4 lines
Quoted 4 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h struct amdgpu_vm { · line 277
Quoted 4 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h +1
-0+/* contains the page directory */ struct amdgpu_vm_pt root;struct dma_fence *last_update;_______________________________________________
amd-gfx mailing list
[email protected]
https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Flists.freedesktop.org%2Fmailman%2Flistinfo%2Famd-gfx&data=02%7C01%7Cyintian.tao%40amd.com%7C580c8ec15d484bf546b208d7c8188cc2%7C3dd8961fe4884e608e11a82d994e183d%7C0%7C0%7C637197880120611671&sdata=dqSLasyuZhQskB38Kib6g8lQR9iMnyxFxfHGXXENoDc%3D&reserved=0
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx