drm/amdkfd: Fix some double free when destroy queue fails
Subsystems (3)
PATCH v2 1/2 drm/amdkfd: Fix some double free when destroy queue fails
Handle queue destroy failure while CP hang.
Once CP got hang, kfd trigger GPU reset and set related flags to stop driver touching the queue. As we leave the queue as it is, we need keep the resource as it is too.
Regardless user-space tries to destroy the queue again or not. We need put queue back to the list so process termination would do the cleanup work. What's more, if userspace tries to destroy the queue again, we would not free its resource twice.
Kfd return -EIO in this case, so lets handle it now.
Paste some error log below without this patch.
amdgpu: Can't create new usermode queue because -1 queues were already created
refcount_t: underflow; use-after-free.
Call Trace: kobject_put+0xe6/0x1b0 kfd_procfs_del_queue+0x37/0x50 [amdgpu] pqm_destroy_queue+0x17a/0x390 [amdgpu] kfd_ioctl_destroy_queue+0x57/0xc0 [amdgpu] kfd_ioctl+0x463/0x690 [amdgpu]
BUG kmalloc-32 (Tainted: G W ): Object already free
INFO: Allocated in allocate_sdma_mqd+0x30/0xb0 [amdgpu] age=4796 cpu=2 pid=2511
__slab_alloc+0x72/0x80 kmem_cache_alloc_trace+0x81f/0x8c0 allocate_sdma_mqd+0x30/0xb0 [amdgpu] create_queue_cpsch+0xbf/0x470 [amdgpu] pqm_create_queue+0x28d/0x6d0 [amdgpu] kfd_ioctl_create_queue+0x492/0xae0 [amdgpu] INFO: Freed in free_mqd_hiq_sdma+0x20/0x60 [amdgpu] age=2537 cpu=7 pid=2511 kfree+0x322/0x340 free_mqd_hiq_sdma+0x20/0x60 [amdgpu] destroy_queue_cpsch+0x20c/0x330 [amdgpu] pqm_destroy_queue+0x1a3/0x390 [amdgpu] kfd_ioctl_destroy_queue+0x57/0xc0 [amdgpu]
--- .../gpu/drm/amd/amdkfd/kfd_device_queue_manager.c | 13 +++++++++++++ drivers/gpu/drm/amd/amdkfd/kfd_process.c | 4 +++- .../gpu/drm/amd/amdkfd/kfd_process_queue_manager.c | 2 ++ 3 files changed, 18 insertions(+), 1 deletion(-)
drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +13 -0
@@ -1530,6 +1530,11 @@ static int destroy_queue_cpsch(struct device_queue_manager *dqm, KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0);if (retval == -ETIME ) qpd->reset_wavefronts = true; +/* In gpu reset? We leave the queue as it is, so do NOT +* cleanup the resource. +*/ +else if (retval == -EIO ) + goto failed_execute_queue;if (q->properties.is_gws) { dqm->gws_queue_count--; qpd->mapped_gws_queue = false;
@@ -1551,6 +1556,14 @@ static int destroy_queue_cpsch(struct device_queue_manager *dqm,return retval; +failed_execute_queue: +/* Put queue back to the list, then we have chance to destroy it. +* FIXME: we do NOT want the queue in the runlist again. +*/ +list_add (&q->list, &qpd->queues_list); + qpd->queue_count++; +if (q->properties.is_active) +increment_queue_count (dqm, q->properties.type); failed_try_destroy_debugged_queue:dqm_unlock (dqm);
drivers/gpu/drm/amd/amdkfd/kfd_process.c +3 -1
@@ -607,11 +607,13 @@ static int kfd_procfs_add_sysfs_files(struct kfd_process *p)void kfd_procfs_del_queue (struct queue *q) { -if (!q) +if (!q || !kobject_get_unless_zero (&q->kobj))return ;kobject_del (&q->kobj);kobject_put (&q->kobj); +/* paired with the get above */ +kobject_put (&q->kobj); }int kfd_process_create_wq (void )
drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c +2 -0
@@ -373,6 +373,7 @@ int pqm_destroy_queue(struct process_queue_manager *pqm, unsigned int qid) dqm = pqn->kq->dev->dqm; dqm->ops.destroy_kernel_queue (dqm, pqn->kq, &pdd->qpd);kernel_queue_uninit (pqn->kq, false); + pqn->kq =NULL ; }if (pqn->q) {
@@ -396,6 +397,7 @@ int pqm_destroy_queue(struct process_queue_manager *pqm, unsigned int qid)kfree (pqn->q->properties.cu_mask); pqn->q->properties.cu_mask =NULL ;uninit_queue (pqn->q); + pqn->q =NULL ; }list_del (&pqn->process_queue_list);
Signature · 6 lines
2.25.1 _______________________________________________ amd-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/amd-gfx
PATCH v2 2/2 drm/amdkfd: Walk through list with dqm lock hold
To avoid any list corruption.
--- .../drm/amd/amdkfd/kfd_device_queue_manager.c | 22 ++++++++++--------- 1 file changed, 12 insertions(+), 10 deletions(-)
drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +12 -10
@@ -1722,7 +1722,7 @@ static int process_termination_cpsch(struct device_queue_manager *dqm, struct qcm_process_device *qpd) {int retval; -struct queue *q, *next; +struct queue *q;struct kernel_queue *kq, *kq_next;struct mqd_manager *mqd_mgr;struct device_process_node *cur, *next_dpn;
@@ -1779,24 +1779,26 @@ static int process_termination_cpsch(struct device_queue_manager *dqm, qpd->reset_wavefronts = false; } -dqm_unlock (dqm); - -/* Outside the DQM lock because under the DQM lock we can't do -* reclaim or take other locks that others hold while reclaiming. -*/ -if (found) -kfd_dec_compute_active (dqm->dev); -/* Lastly, free mqd resources. * Do free_mqd() after dqm_unlock to avoid circular locking. */ -list_for_each_entry_safe (q, next, &qpd->queues_list, list) { +while (!list_empty (&qpd->queues_list)) { + q = list_first_entry(&qpd->queues_list, struct queue, list); mqd_mgr = dqm->mqd_mgrs[get_mqd_type_from_queue_type ( q->properties.type)];list_del (&q->list); qpd->queue_count--; +dqm_unlock (dqm); mqd_mgr->free_mqd (mqd_mgr, q->mqd, q->mqd_mem_obj); +dqm_lock (dqm); } +dqm_unlock (dqm); + +/* Outside the DQM lock because under the DQM lock we can't do +* reclaim or take other locks that others hold while reclaiming. +*/ +if (found) +kfd_dec_compute_active (dqm->dev);return retval; }
Signature · 6 lines
2.25.1 _______________________________________________ amd-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/amd-gfx
Re: [PATCH v2 2/2] drm/amdkfd: Walk through list with dqm lock hold
Am 2021-06-17 um 8:02 a.m. schrieb xinhui pan:
Quoted 3 lines
To avoid any list corruption.
Signed-off-by xinhui pan <[email protected]>
This patch is
Quoted 43 lines
--- .../drm/amd/amdkfd/kfd_device_queue_manager.c | 22 ++++++++++--------- 1 file changed, 12 insertions(+), 10 deletions(-)drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +5
-10@@ -1722,7 +1722,7 @@ static int process_termination_cpsch(struct device_queue_manager *dqm, struct qcm_process_device *qpd) {int retval; -struct queue *q, *next; +struct queue *q;struct kernel_queue *kq, *kq_next;struct mqd_manager *mqd_mgr;struct device_process_node *cur, *next_dpn;@@ -1779,24 +1779,26 @@ static int process_termination_cpsch(struct device_queue_manager *dqm, qpd->reset_wavefronts = false; } -dqm_unlock (dqm); - -/* Outside the DQM lock because under the DQM lock we can't do -* reclaim or take other locks that others hold while reclaiming. -*/ -if (found) -kfd_dec_compute_active (dqm->dev); -/* Lastly, free mqd resources. * Do free_mqd() after dqm_unlock to avoid circular locking. */ -list_for_each_entry_safe (q, next, &qpd->queues_list, list) { +while (!list_empty (&qpd->queues_list)) { + q = list_first_entry(&qpd->queues_list, struct queue, list); mqd_mgr = dqm->mqd_mgrs[get_mqd_type_from_queue_type ( q->properties.type)];list_del (&q->list); qpd->queue_count--; +dqm_unlock (dqm); mqd_mgr->free_mqd (mqd_mgr, q->mqd, q->mqd_mem_obj); +dqm_lock (dqm); }
drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c static int process_termination_cpsch(struct device_queue_manager *dqm, · line 1804
Quoted 10 lines
drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +7
-0+dqm_unlock (dqm); + +/* Outside the DQM lock because under the DQM lock we can't do +* reclaim or take other locks that others hold while reclaiming. +*/ +if (found) +kfd_dec_compute_active (dqm->dev);return retval; }
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
Felix
what I am thinking of like below looks like more simple. :)
@@ -1501,6 +1501,11 @@ static int destroy_queue_cpsch(struct device_queue_manager *dqm,
/* remove queue from list to prevent rescheduling after preemption */
dqm_lock(dqm);+ if (dqm->is_hws_hang) {
+ retval = -EIO;
+ goto failed_try_destroy_debugged_queue;
+ }
+
if (qpd->is_debug) {
/*
* error, currently we do not allow to destroy a queueQuoted 124 lines
2021年6月17日 20:02,Pan, Xinhui <[email protected]> 写道:
Handle queue destroy failure while CP hang.
Once CP got hang, kfd trigger GPU reset and set related flags to stop driver touching the queue. As we leave the queue as it is, we need keep the resource as it is too.Regardless user-space tries to destroy the queue again or not. We need put queue back to the list so process termination would do the cleanup work. What's more, if userspace tries to destroy the queue again, we would not free its resource twice.
Kfd return
-EIOin this case, so lets handle it now.Paste some error log below without this patch.
amdgpu: Can't create new usermode queue because -1 queues were already created
refcount_t: underflow; use-after-free.Call Trace: kobject_put+0xe6/0x1b0 kfd_procfs_del_queue+0x37/0x50 [amdgpu] pqm_destroy_queue+0x17a/0x390 [amdgpu] kfd_ioctl_destroy_queue+0x57/0xc0 [amdgpu] kfd_ioctl+0x463/0x690 [amdgpu]BUG kmalloc-32 (Tainted: G W ): Object already free
INFO: Allocated inallocate_sdma_mqd+0x30/0xb0[amdgpu] age=4796 cpu=2 pid=2511__slab_alloc+0x72/0x80 kmem_cache_alloc_trace+0x81f/0x8c0 allocate_sdma_mqd+0x30/0xb0 [amdgpu] create_queue_cpsch+0xbf/0x470 [amdgpu] pqm_create_queue+0x28d/0x6d0 [amdgpu] kfd_ioctl_create_queue+0x492/0xae0 [amdgpu] INFO: Freed in free_mqd_hiq_sdma+0x20/0x60 [amdgpu] age=2537 cpu=7 pid=2511 kfree+0x322/0x340 free_mqd_hiq_sdma+0x20/0x60 [amdgpu] destroy_queue_cpsch+0x20c/0x330 [amdgpu] pqm_destroy_queue+0x1a3/0x390 [amdgpu] kfd_ioctl_destroy_queue+0x57/0xc0 [amdgpu]Signed-off-by xinhui pan <[email protected]>---
.../gpu/drm/amd/amdkfd/kfd_device_queue_manager.c | 13 +++++++++++++ drivers/gpu/drm/amd/amdkfd/kfd_process.c | 4 +++- .../gpu/drm/amd/amdkfd/kfd_process_queue_manager.c | 2 ++ 3 files changed, 18 insertions(+), 1 deletion(-)drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +13
-0@@ -1530,6 +1530,11 @@ static int destroy_queue_cpsch(struct device_queue_manager *dqm, KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0);if (retval == -ETIME ) qpd->reset_wavefronts = true; +/* In gpu reset? We leave the queue as it is, so do NOT +* cleanup the resource. +*/ +else if (retval == -EIO ) + goto failed_execute_queue;if (q->properties.is_gws) { dqm->gws_queue_count--; qpd->mapped_gws_queue = false;@@ -1551,6 +1556,14 @@ static int destroy_queue_cpsch(struct device_queue_manager *dqm,return retval; +failed_execute_queue: +/* Put queue back to the list, then we have chance to destroy it. +* FIXME: we do NOT want the queue in the runlist again. +*/ +list_add (&q->list, &qpd->queues_list); + qpd->queue_count++; +if (q->properties.is_active) +increment_queue_count (dqm, q->properties.type);
failed_try_destroy_debugged_queue:dqm_unlock(dqm);drivers/gpu/drm/amd/amdkfd/kfd_process.c +3
-1@@ -607,11 +607,13 @@ static int kfd_procfs_add_sysfs_files(struct kfd_process *p)void kfd_procfs_del_queue (struct queue *q) { -if (!q) +if (!q || !kobject_get_unless_zero (&q->kobj))return ;kobject_del (&q->kobj);kobject_put (&q->kobj); +/* paired with the get above */ +kobject_put (&q->kobj); }int kfd_process_create_wq (void )drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c +2
-0@@ -373,6 +373,7 @@ int pqm_destroy_queue(struct process_queue_manager *pqm, unsigned int qid) dqm = pqn->kq->dev->dqm; dqm->ops.destroy_kernel_queue (dqm, pqn->kq, &pdd->qpd);kernel_queue_uninit (pqn->kq, false); + pqn->kq =NULL ; }if (pqn->q) {@@ -396,6 +397,7 @@ int pqm_destroy_queue(struct process_queue_manager *pqm, unsigned int qid)kfree (pqn->q->properties.cu_mask); pqn->q->properties.cu_mask =NULL ;uninit_queue (pqn->q); + pqn->q =NULL ; }list_del (&pqn->process_queue_list);Signature · 1 line
2.25.1
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
Felix
What I am wondreing is that if CP got hang, could we assume all usermode queues have stopped? If so, we can do cleanupwork regardless of the retval of execute_queues_cpsch().
Quoted 138 lines
2021年6月17日 20:11,Pan, Xinhui <[email protected]> 写道:
Felix
what I am thinking of like below looks like more simple. :)(quoted diff) +5
-0@@ -1501,6 +1501,11 @@ static int destroy_queue_cpsch(struct device_queue_manager *dqm, /* remove queue from list to prevent rescheduling after preemption */ dqm_lock(dqm); + if (dqm->is_hws_hang) { + retval = -EIO; + goto failed_try_destroy_debugged_queue; + } + if (qpd->is_debug) { /* * error, currently we do not allow to destroy a queueQuoted 121 lines
2021年6月17日 20:02,Pan, Xinhui <[email protected]> 写道:
Handle queue destroy failure while CP hang.
Once CP got hang, kfd trigger GPU reset and set related flags to stop driver touching the queue. As we leave the queue as it is, we need keep the resource as it is too.Regardless user-space tries to destroy the queue again or not. We need put queue back to the list so process termination would do the cleanup work. What's more, if userspace tries to destroy the queue again, we would not free its resource twice.
Kfd return
-EIOin this case, so lets handle it now.Paste some error log below without this patch.
amdgpu: Can't create new usermode queue because -1 queues were already created
refcount_t: underflow; use-after-free.Call Trace: kobject_put+0xe6/0x1b0 kfd_procfs_del_queue+0x37/0x50 [amdgpu] pqm_destroy_queue+0x17a/0x390 [amdgpu] kfd_ioctl_destroy_queue+0x57/0xc0 [amdgpu] kfd_ioctl+0x463/0x690 [amdgpu]BUG kmalloc-32 (Tainted: G W ): Object already free
INFO: Allocated inallocate_sdma_mqd+0x30/0xb0[amdgpu] age=4796 cpu=2 pid=2511__slab_alloc+0x72/0x80 kmem_cache_alloc_trace+0x81f/0x8c0 allocate_sdma_mqd+0x30/0xb0 [amdgpu] create_queue_cpsch+0xbf/0x470 [amdgpu] pqm_create_queue+0x28d/0x6d0 [amdgpu] kfd_ioctl_create_queue+0x492/0xae0 [amdgpu] INFO: Freed in free_mqd_hiq_sdma+0x20/0x60 [amdgpu] age=2537 cpu=7 pid=2511 kfree+0x322/0x340 free_mqd_hiq_sdma+0x20/0x60 [amdgpu] destroy_queue_cpsch+0x20c/0x330 [amdgpu] pqm_destroy_queue+0x1a3/0x390 [amdgpu] kfd_ioctl_destroy_queue+0x57/0xc0 [amdgpu]Signed-off-by xinhui pan <[email protected]>---
.../gpu/drm/amd/amdkfd/kfd_device_queue_manager.c | 13 +++++++++++++ drivers/gpu/drm/amd/amdkfd/kfd_process.c | 4 +++- .../gpu/drm/amd/amdkfd/kfd_process_queue_manager.c | 2 ++ 3 files changed, 18 insertions(+), 1 deletion(-)drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +13
-0@@ -1530,6 +1530,11 @@ static int destroy_queue_cpsch(struct device_queue_manager *dqm, KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0);if (retval == -ETIME ) qpd->reset_wavefronts = true; +/* In gpu reset? We leave the queue as it is, so do NOT +* cleanup the resource. +*/ +else if (retval == -EIO ) + goto failed_execute_queue;if (q->properties.is_gws) { dqm->gws_queue_count--; qpd->mapped_gws_queue = false;@@ -1551,6 +1556,14 @@ static int destroy_queue_cpsch(struct device_queue_manager *dqm,return retval; +failed_execute_queue: +/* Put queue back to the list, then we have chance to destroy it. +* FIXME: we do NOT want the queue in the runlist again. +*/ +list_add (&q->list, &qpd->queues_list); + qpd->queue_count++; +if (q->properties.is_active) +increment_queue_count (dqm, q->properties.type);
failed_try_destroy_debugged_queue:dqm_unlock(dqm);drivers/gpu/drm/amd/amdkfd/kfd_process.c +3
-1@@ -607,11 +607,13 @@ static int kfd_procfs_add_sysfs_files(struct kfd_process *p)void kfd_procfs_del_queue (struct queue *q) { -if (!q) +if (!q || !kobject_get_unless_zero (&q->kobj))return ;kobject_del (&q->kobj);kobject_put (&q->kobj); +/* paired with the get above */ +kobject_put (&q->kobj); }int kfd_process_create_wq (void )drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c +2
-0@@ -373,6 +373,7 @@ int pqm_destroy_queue(struct process_queue_manager *pqm, unsigned int qid) dqm = pqn->kq->dev->dqm; dqm->ops.destroy_kernel_queue (dqm, pqn->kq, &pdd->qpd);kernel_queue_uninit (pqn->kq, false); + pqn->kq =NULL ; }if (pqn->q) {@@ -396,6 +397,7 @@ int pqm_destroy_queue(struct process_queue_manager *pqm, unsigned int qid)kfree (pqn->q->properties.cu_mask); pqn->q->properties.cu_mask =NULL ;uninit_queue (pqn->q); + pqn->q =NULL ; }
Quoted 5 lines
Quoted 4 lines
drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c +0
-0list_del (&pqn->process_queue_list);Signature · 1 line
2.25.1
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
Felix Kuehling
maintainerAm 2021-06-17 um 8:41 a.m. schrieb Pan, Xinhui:
Quoted 3 lines
Felix
What I am wondreing is that if CP got hang, could we assume all usermode queues have stopped? If so, we can do cleanupwork regardless of the retval ofexecute_queues_cpsch().
Right. That's what we currently do with ETIME, which happens when the hang is first detected. I don't know why we need to treat the case differently when we're already in a reset.
Regards,
Felix
Quoted 139 lines
Quoted 139 lines
2021年6月17日 20:11,Pan, Xinhui <[email protected]> 写道:
Felix
what I am thinking of like below looks like more simple. :)(quoted diff) +5
-0@@ -1501,6 +1501,11 @@ static int destroy_queue_cpsch(struct device_queue_manager *dqm, /* remove queue from list to prevent rescheduling after preemption */ dqm_lock(dqm); + if (dqm->is_hws_hang) { + retval = -EIO; + goto failed_try_destroy_debugged_queue; + } + if (qpd->is_debug) { /* * error, currently we do not allow to destroy a queueQuoted 121 lines
2021年6月17日 20:02,Pan, Xinhui <[email protected]> 写道:
Handle queue destroy failure while CP hang.
Once CP got hang, kfd trigger GPU reset and set related flags to stop driver touching the queue. As we leave the queue as it is, we need keep the resource as it is too.Regardless user-space tries to destroy the queue again or not. We need put queue back to the list so process termination would do the cleanup work. What's more, if userspace tries to destroy the queue again, we would not free its resource twice.
Kfd return
-EIOin this case, so lets handle it now.Paste some error log below without this patch.
amdgpu: Can't create new usermode queue because -1 queues were already created
refcount_t: underflow; use-after-free.Call Trace: kobject_put+0xe6/0x1b0 kfd_procfs_del_queue+0x37/0x50 [amdgpu] pqm_destroy_queue+0x17a/0x390 [amdgpu] kfd_ioctl_destroy_queue+0x57/0xc0 [amdgpu] kfd_ioctl+0x463/0x690 [amdgpu]BUG kmalloc-32 (Tainted: G W ): Object already free
INFO: Allocated inallocate_sdma_mqd+0x30/0xb0[amdgpu] age=4796 cpu=2 pid=2511__slab_alloc+0x72/0x80 kmem_cache_alloc_trace+0x81f/0x8c0 allocate_sdma_mqd+0x30/0xb0 [amdgpu] create_queue_cpsch+0xbf/0x470 [amdgpu] pqm_create_queue+0x28d/0x6d0 [amdgpu] kfd_ioctl_create_queue+0x492/0xae0 [amdgpu] INFO: Freed in free_mqd_hiq_sdma+0x20/0x60 [amdgpu] age=2537 cpu=7 pid=2511 kfree+0x322/0x340 free_mqd_hiq_sdma+0x20/0x60 [amdgpu] destroy_queue_cpsch+0x20c/0x330 [amdgpu] pqm_destroy_queue+0x1a3/0x390 [amdgpu] kfd_ioctl_destroy_queue+0x57/0xc0 [amdgpu]Signed-off-by xinhui pan <[email protected]>---
.../gpu/drm/amd/amdkfd/kfd_device_queue_manager.c | 13 +++++++++++++ drivers/gpu/drm/amd/amdkfd/kfd_process.c | 4 +++- .../gpu/drm/amd/amdkfd/kfd_process_queue_manager.c | 2 ++ 3 files changed, 18 insertions(+), 1 deletion(-)drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +13
-0@@ -1530,6 +1530,11 @@ static int destroy_queue_cpsch(struct device_queue_manager *dqm, KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0);if (retval == -ETIME ) qpd->reset_wavefronts = true; +/* In gpu reset? We leave the queue as it is, so do NOT +* cleanup the resource. +*/ +else if (retval == -EIO ) + goto failed_execute_queue;if (q->properties.is_gws) { dqm->gws_queue_count--; qpd->mapped_gws_queue = false;@@ -1551,6 +1556,14 @@ static int destroy_queue_cpsch(struct device_queue_manager *dqm,return retval; +failed_execute_queue: +/* Put queue back to the list, then we have chance to destroy it. +* FIXME: we do NOT want the queue in the runlist again. +*/ +list_add (&q->list, &qpd->queues_list); + qpd->queue_count++; +if (q->properties.is_active) +increment_queue_count (dqm, q->properties.type);
failed_try_destroy_debugged_queue:dqm_unlock(dqm);drivers/gpu/drm/amd/amdkfd/kfd_process.c +3
-1@@ -607,11 +607,13 @@ static int kfd_procfs_add_sysfs_files(struct kfd_process *p)void kfd_procfs_del_queue (struct queue *q) { -if (!q) +if (!q || !kobject_get_unless_zero (&q->kobj))return ;kobject_del (&q->kobj);kobject_put (&q->kobj); +/* paired with the get above */ +kobject_put (&q->kobj); }int kfd_process_create_wq (void )drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c +2
-0@@ -373,6 +373,7 @@ int pqm_destroy_queue(struct process_queue_manager *pqm, unsigned int qid) dqm = pqn->kq->dev->dqm; dqm->ops.destroy_kernel_queue (dqm, pqn->kq, &pdd->qpd);kernel_queue_uninit (pqn->kq, false); + pqn->kq =NULL ; }if (pqn->q) {@@ -396,6 +397,7 @@ int pqm_destroy_queue(struct process_queue_manager *pqm, unsigned int qid)kfree (pqn->q->properties.cu_mask); pqn->q->properties.cu_mask =NULL ;uninit_queue (pqn->q); + pqn->q =NULL ; }
Quoted 4 lines
Quoted 4 lines
Quoted 4 lines
drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c +0
-0list_del (&pqn->process_queue_list);Signature · 1 line
2.25.1
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx