summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/amd/amdkfd
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/gpu/drm/amd/amdkfd')
-rw-r--r--drivers/gpu/drm/amd/amdkfd/kfd_chardev.c8
-rw-r--r--drivers/gpu/drm/amd/amdkfd/kfd_device.c17
-rw-r--r--drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c1
-rw-r--r--drivers/gpu/drm/amd/amdkfd/kfd_int_process_v10.c3
-rw-r--r--drivers/gpu/drm/amd/amdkfd/kfd_int_process_v11.c3
-rw-r--r--drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c3
-rw-r--r--drivers/gpu/drm/amd/amdkfd/kfd_migrate.c16
-rw-r--r--drivers/gpu/drm/amd/amdkfd/kfd_priv.h2
-rw-r--r--drivers/gpu/drm/amd/amdkfd/kfd_process.c19
-rw-r--r--drivers/gpu/drm/amd/amdkfd/kfd_svm.c2
10 files changed, 44 insertions, 30 deletions
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index dfa8c69532d4..55aa74cbc532 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -779,8 +779,8 @@ static int kfd_ioctl_get_process_apertures_new(struct file *filp,
* nodes, but not more than args->num_of_nodes as that is
* the amount of memory allocated by user
*/
- pa = kzalloc((sizeof(struct kfd_process_device_apertures) *
- args->num_of_nodes), GFP_KERNEL);
+ pa = kcalloc(args->num_of_nodes, sizeof(struct kfd_process_device_apertures),
+ GFP_KERNEL);
if (!pa)
return -ENOMEM;
@@ -1523,7 +1523,7 @@ static int kfd_ioctl_get_dmabuf_info(struct file *filep,
/* Find a KFD GPU device that supports the get_dmabuf_info query */
for (i = 0; kfd_topology_enum_kfd_devices(i, &dev) == 0; i++)
- if (dev)
+ if (dev && !kfd_devcgroup_check_permission(dev))
break;
if (!dev)
return -EINVAL;
@@ -1545,7 +1545,7 @@ static int kfd_ioctl_get_dmabuf_info(struct file *filep,
if (xcp_id >= 0)
args->gpu_id = dmabuf_adev->kfd.dev->nodes[xcp_id]->id;
else
- args->gpu_id = dmabuf_adev->kfd.dev->nodes[0]->id;
+ args->gpu_id = dev->id;
args->flags = flags;
/* Copy metadata buffer to user mode */
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index 041ec3de55e7..719d6d365e15 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -960,7 +960,6 @@ void kgd2kfd_suspend(struct kfd_dev *kfd, bool run_pm)
{
struct kfd_node *node;
int i;
- int count;
if (!kfd->init_complete)
return;
@@ -968,12 +967,10 @@ void kgd2kfd_suspend(struct kfd_dev *kfd, bool run_pm)
/* for runtime suspend, skip locking kfd */
if (!run_pm) {
mutex_lock(&kfd_processes_mutex);
- count = ++kfd_locked;
- mutex_unlock(&kfd_processes_mutex);
-
/* For first KFD device suspend all the KFD processes */
- if (count == 1)
+ if (++kfd_locked == 1)
kfd_suspend_all_processes();
+ mutex_unlock(&kfd_processes_mutex);
}
for (i = 0; i < kfd->num_nodes; i++) {
@@ -984,7 +981,7 @@ void kgd2kfd_suspend(struct kfd_dev *kfd, bool run_pm)
int kgd2kfd_resume(struct kfd_dev *kfd, bool run_pm)
{
- int ret, count, i;
+ int ret, i;
if (!kfd->init_complete)
return 0;
@@ -998,12 +995,10 @@ int kgd2kfd_resume(struct kfd_dev *kfd, bool run_pm)
/* for runtime resume, skip unlocking kfd */
if (!run_pm) {
mutex_lock(&kfd_processes_mutex);
- count = --kfd_locked;
- mutex_unlock(&kfd_processes_mutex);
-
- WARN_ONCE(count < 0, "KFD suspend / resume ref. error");
- if (count == 0)
+ if (--kfd_locked == 0)
ret = kfd_resume_all_processes();
+ WARN_ONCE(kfd_locked < 0, "KFD suspend / resume ref. error");
+ mutex_unlock(&kfd_processes_mutex);
}
return ret;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index f4d395e38683..0b655555e167 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -2001,6 +2001,7 @@ static int unmap_queues_cpsch(struct device_queue_manager *dqm,
dev_err(dev, "HIQ MQD's queue_doorbell_id0 is not 0, Queue preemption time out\n");
while (halt_if_hws_hang)
schedule();
+ kfd_hws_hang(dqm);
return -ETIME;
}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v10.c b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v10.c
index 9a06c6fb6605..40a21be6c07c 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v10.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v10.c
@@ -339,7 +339,8 @@ static void event_interrupt_wq_v10(struct kfd_node *dev,
break;
}
kfd_signal_event_interrupt(pasid, context_id0 & 0x7fffff, 23);
- } else if (source_id == SOC15_INTSRC_CP_BAD_OPCODE) {
+ } else if (source_id == SOC15_INTSRC_CP_BAD_OPCODE &&
+ KFD_DBG_EC_TYPE_IS_PACKET(KFD_DEBUG_CP_BAD_OP_ECODE(context_id0))) {
kfd_set_dbg_ev_from_interrupt(dev, pasid,
KFD_DEBUG_DOORBELL_ID(context_id0),
KFD_EC_MASK(KFD_DEBUG_CP_BAD_OP_ECODE(context_id0)),
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v11.c b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v11.c
index 7e2859736a55..fe2ad0c0de95 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v11.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v11.c
@@ -328,7 +328,8 @@ static void event_interrupt_wq_v11(struct kfd_node *dev,
/* CP */
if (source_id == SOC15_INTSRC_CP_END_OF_PIPE)
kfd_signal_event_interrupt(pasid, context_id0, 32);
- else if (source_id == SOC15_INTSRC_CP_BAD_OPCODE)
+ else if (source_id == SOC15_INTSRC_CP_BAD_OPCODE &&
+ KFD_DBG_EC_TYPE_IS_PACKET(KFD_CTXID0_CP_BAD_OP_ECODE(context_id0)))
kfd_set_dbg_ev_from_interrupt(dev, pasid,
KFD_CTXID0_DOORBELL_ID(context_id0),
KFD_EC_MASK(KFD_CTXID0_CP_BAD_OP_ECODE(context_id0)),
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c
index 91dd5e045b51..c4c6a29052ac 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c
@@ -388,7 +388,8 @@ static void event_interrupt_wq_v9(struct kfd_node *dev,
break;
}
kfd_signal_event_interrupt(pasid, sq_int_data, 24);
- } else if (source_id == SOC15_INTSRC_CP_BAD_OPCODE) {
+ } else if (source_id == SOC15_INTSRC_CP_BAD_OPCODE &&
+ KFD_DBG_EC_TYPE_IS_PACKET(KFD_DEBUG_CP_BAD_OP_ECODE(context_id0))) {
kfd_set_dbg_ev_from_interrupt(dev, pasid,
KFD_DEBUG_DOORBELL_ID(context_id0),
KFD_EC_MASK(KFD_DEBUG_CP_BAD_OP_ECODE(context_id0)),
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
index bdc01ca9609a..5c8d81bfce7a 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
@@ -509,10 +509,19 @@ svm_migrate_ram_to_vram(struct svm_range *prange, uint32_t best_loc,
start = start_mgr << PAGE_SHIFT;
end = (last_mgr + 1) << PAGE_SHIFT;
+ r = amdgpu_amdkfd_reserve_mem_limit(node->adev,
+ prange->npages * PAGE_SIZE,
+ KFD_IOC_ALLOC_MEM_FLAGS_VRAM,
+ node->xcp ? node->xcp->id : 0);
+ if (r) {
+ dev_dbg(node->adev->dev, "failed to reserve VRAM, r: %ld\n", r);
+ return -ENOSPC;
+ }
+
r = svm_range_vram_node_new(node, prange, true);
if (r) {
dev_dbg(node->adev->dev, "fail %ld to alloc vram\n", r);
- return r;
+ goto out;
}
ttm_res_offset = (start_mgr - prange->start + prange->offset) << PAGE_SHIFT;
@@ -545,6 +554,11 @@ svm_migrate_ram_to_vram(struct svm_range *prange, uint32_t best_loc,
svm_range_vram_node_free(prange);
}
+out:
+ amdgpu_amdkfd_unreserve_mem_limit(node->adev,
+ prange->npages * PAGE_SIZE,
+ KFD_IOC_ALLOC_MEM_FLAGS_VRAM,
+ node->xcp ? node->xcp->id : 0);
return r < 0 ? r : 0;
}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 42d40560cd30..a81ef232fdef 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -1473,7 +1473,7 @@ static inline void kfd_flush_tlb(struct kfd_process_device *pdd,
static inline bool kfd_flush_tlb_after_unmap(struct kfd_dev *dev)
{
- return KFD_GC_VERSION(dev) > IP_VERSION(9, 4, 2) ||
+ return KFD_GC_VERSION(dev) >= IP_VERSION(9, 4, 2) ||
(KFD_GC_VERSION(dev) == IP_VERSION(9, 4, 1) && dev->sdma_fw_version >= 18) ||
KFD_GC_VERSION(dev) == IP_VERSION(9, 4, 0);
}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index 717a60d7a4ea..58c1fe542193 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -819,9 +819,9 @@ struct kfd_process *kfd_create_process(struct task_struct *thread)
mutex_lock(&kfd_processes_mutex);
if (kfd_is_locked()) {
- mutex_unlock(&kfd_processes_mutex);
pr_debug("KFD is locked! Cannot create process");
- return ERR_PTR(-EINVAL);
+ process = ERR_PTR(-EINVAL);
+ goto out;
}
/* A prior open of /dev/kfd could have already created the process. */
@@ -1922,6 +1922,8 @@ static int signal_eviction_fence(struct kfd_process *p)
rcu_read_lock();
ef = dma_fence_get_rcu_safe(&p->ef);
rcu_read_unlock();
+ if (!ef)
+ return -EINVAL;
ret = dma_fence_signal(ef);
dma_fence_put(ef);
@@ -1949,10 +1951,9 @@ static void evict_process_worker(struct work_struct *work)
* they are responsible stopping the queues and scheduling
* the restore work.
*/
- if (!signal_eviction_fence(p))
- queue_delayed_work(kfd_restore_wq, &p->restore_work,
- msecs_to_jiffies(PROCESS_RESTORE_TIME_MS));
- else
+ if (signal_eviction_fence(p) ||
+ mod_delayed_work(kfd_restore_wq, &p->restore_work,
+ msecs_to_jiffies(PROCESS_RESTORE_TIME_MS)))
kfd_process_restore_queues(p);
pr_debug("Finished evicting pasid 0x%x\n", p->pasid);
@@ -2011,9 +2012,9 @@ static void restore_process_worker(struct work_struct *work)
if (ret) {
pr_debug("Failed to restore BOs of pasid 0x%x, retry after %d ms\n",
p->pasid, PROCESS_BACK_OFF_TIME_MS);
- ret = queue_delayed_work(kfd_restore_wq, &p->restore_work,
- msecs_to_jiffies(PROCESS_BACK_OFF_TIME_MS));
- WARN(!ret, "reschedule restore work failed\n");
+ if (mod_delayed_work(kfd_restore_wq, &p->restore_work,
+ msecs_to_jiffies(PROCESS_RESTORE_TIME_MS)))
+ kfd_process_restore_queues(p);
}
}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index f0f7f48af413..386875e6eb96 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -3426,7 +3426,7 @@ svm_range_trigger_migration(struct mm_struct *mm, struct svm_range *prange,
mm, KFD_MIGRATE_TRIGGER_PREFETCH);
*migrated = !r;
- return r;
+ return 0;
}
int svm_range_schedule_evict_svm_bo(struct amdgpu_amdkfd_fence *fence)
generated by cgit v1.2.3 (git 2.39.0) at 2024-09-28 11:16:38 +0300