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.c2
-rw-r--r--drivers/gpu/drm/amd/amdkfd/kfd_device.c7
-rw-r--r--drivers/gpu/drm/amd/amdkfd/kfd_events.c24
-rw-r--r--drivers/gpu/drm/amd/amdkfd/kfd_priv.h2
-rw-r--r--drivers/gpu/drm/amd/amdkfd/kfd_svm.c17
-rw-r--r--drivers/gpu/drm/amd/amdkfd/kfd_svm.h1
-rw-r--r--drivers/gpu/drm/amd/amdkfd/kfd_topology.c11
7 files changed, 34 insertions, 30 deletions
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index 2b3d8bc8f0aa..dc774ddf3445 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -874,7 +874,7 @@ static int kfd_ioctl_wait_events(struct file *filp, struct kfd_process *p,
err = kfd_wait_on_events(p, args->num_events,
(void __user *)args->events_ptr,
(args->wait_for_all != 0),
- args->timeout, &args->wait_result);
+ &args->timeout, &args->wait_result);
return err;
}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index f5853835f03a..357298e69495 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -102,13 +102,18 @@ static void kfd_device_info_set_sdma_info(struct kfd_dev *kfd)
switch (sdma_version) {
case IP_VERSION(6, 0, 0):
- case IP_VERSION(6, 0, 1):
case IP_VERSION(6, 0, 2):
/* Reserve 1 for paging and 1 for gfx */
kfd->device_info.num_reserved_sdma_queues_per_engine = 2;
/* BIT(0)=engine-0 queue-0; BIT(1)=engine-1 queue-0; BIT(2)=engine-0 queue-1; ... */
kfd->device_info.reserved_sdma_queues_bitmap = 0xFULL;
break;
+ case IP_VERSION(6, 0, 1):
+ /* Reserve 1 for paging and 1 for gfx */
+ kfd->device_info.num_reserved_sdma_queues_per_engine = 2;
+ /* BIT(0)=engine-0 queue-0; BIT(1)=engine-0 queue-1; ... */
+ kfd->device_info.reserved_sdma_queues_bitmap = 0x3ULL;
+ break;
default:
break;
}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
index 3942a56c28bb..83e3ce9f6049 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_events.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
@@ -894,7 +894,8 @@ static long user_timeout_to_jiffies(uint32_t user_timeout_ms)
return msecs_to_jiffies(user_timeout_ms) + 1;
}
-static void free_waiters(uint32_t num_events, struct kfd_event_waiter *waiters)
+static void free_waiters(uint32_t num_events, struct kfd_event_waiter *waiters,
+ bool undo_auto_reset)
{
uint32_t i;
@@ -903,6 +904,9 @@ static void free_waiters(uint32_t num_events, struct kfd_event_waiter *waiters)
spin_lock(&waiters[i].event->lock);
remove_wait_queue(&waiters[i].event->wq,
&waiters[i].wait);
+ if (undo_auto_reset && waiters[i].activated &&
+ waiters[i].event && waiters[i].event->auto_reset)
+ set_event(waiters[i].event);
spin_unlock(&waiters[i].event->lock);
}
@@ -911,7 +915,7 @@ static void free_waiters(uint32_t num_events, struct kfd_event_waiter *waiters)
int kfd_wait_on_events(struct kfd_process *p,
uint32_t num_events, void __user *data,
- bool all, uint32_t user_timeout_ms,
+ bool all, uint32_t *user_timeout_ms,
uint32_t *wait_result)
{
struct kfd_event_data __user *events =
@@ -920,7 +924,7 @@ int kfd_wait_on_events(struct kfd_process *p,
int ret = 0;
struct kfd_event_waiter *event_waiters = NULL;
- long timeout = user_timeout_to_jiffies(user_timeout_ms);
+ long timeout = user_timeout_to_jiffies(*user_timeout_ms);
event_waiters = alloc_event_waiters(num_events);
if (!event_waiters) {
@@ -970,15 +974,11 @@ int kfd_wait_on_events(struct kfd_process *p,
}
if (signal_pending(current)) {
- /*
- * This is wrong when a nonzero, non-infinite timeout
- * is specified. We need to use
- * ERESTARTSYS_RESTARTBLOCK, but struct restart_block
- * contains a union with data for each user and it's
- * in generic kernel code that I don't want to
- * touch yet.
- */
ret = -ERESTARTSYS;
+ if (*user_timeout_ms != KFD_EVENT_TIMEOUT_IMMEDIATE &&
+ *user_timeout_ms != KFD_EVENT_TIMEOUT_INFINITE)
+ *user_timeout_ms = jiffies_to_msecs(
+ max(0l, timeout-1));
break;
}
@@ -1019,7 +1019,7 @@ int kfd_wait_on_events(struct kfd_process *p,
event_waiters, events);
out_unlock:
- free_waiters(num_events, event_waiters);
+ free_waiters(num_events, event_waiters, ret == -ERESTARTSYS);
mutex_unlock(&p->event_mutex);
out:
if (ret)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index d03a3b9c9c5d..bf610e3b683b 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -1317,7 +1317,7 @@ void kfd_event_free_process(struct kfd_process *p);
int kfd_event_mmap(struct kfd_process *process, struct vm_area_struct *vma);
int kfd_wait_on_events(struct kfd_process *p,
uint32_t num_events, void __user *data,
- bool all, uint32_t user_timeout_ms,
+ bool all, uint32_t *user_timeout_ms,
uint32_t *wait_result);
void kfd_signal_event_interrupt(u32 pasid, uint32_t partial_id,
uint32_t valid_id_bits);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index a67ba8879a56..11074cc8c333 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -541,7 +541,6 @@ svm_range_vram_node_new(struct amdgpu_device *adev, struct svm_range *prange,
kfree(svm_bo);
return -ESRCH;
}
- svm_bo->svms = prange->svms;
svm_bo->eviction_fence =
amdgpu_amdkfd_fence_create(dma_fence_context_alloc(1),
mm,
@@ -3273,7 +3272,6 @@ int svm_range_schedule_evict_svm_bo(struct amdgpu_amdkfd_fence *fence)
static void svm_range_evict_svm_bo_worker(struct work_struct *work)
{
struct svm_range_bo *svm_bo;
- struct kfd_process *p;
struct mm_struct *mm;
int r = 0;
@@ -3281,13 +3279,12 @@ static void svm_range_evict_svm_bo_worker(struct work_struct *work)
if (!svm_bo_ref_unless_zero(svm_bo))
return; /* svm_bo was freed while eviction was pending */
- /* svm_range_bo_release destroys this worker thread. So during
- * the lifetime of this thread, kfd_process and mm will be valid.
- */
- p = container_of(svm_bo->svms, struct kfd_process, svms);
- mm = p->mm;
- if (!mm)
+ if (mmget_not_zero(svm_bo->eviction_fence->mm)) {
+ mm = svm_bo->eviction_fence->mm;
+ } else {
+ svm_range_bo_unref(svm_bo);
return;
+ }
mmap_read_lock(mm);
spin_lock(&svm_bo->list_lock);
@@ -3305,8 +3302,7 @@ static void svm_range_evict_svm_bo_worker(struct work_struct *work)
mutex_lock(&prange->migrate_mutex);
do {
- r = svm_migrate_vram_to_ram(prange,
- svm_bo->eviction_fence->mm,
+ r = svm_migrate_vram_to_ram(prange, mm,
KFD_MIGRATE_TRIGGER_TTM_EVICTION);
} while (!r && prange->actual_loc && --retries);
@@ -3324,6 +3320,7 @@ static void svm_range_evict_svm_bo_worker(struct work_struct *work)
}
spin_unlock(&svm_bo->list_lock);
mmap_read_unlock(mm);
+ mmput(mm);
dma_fence_signal(&svm_bo->eviction_fence->base);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.h b/drivers/gpu/drm/amd/amdkfd/kfd_svm.h
index 9156b041ef17..cfac13ad06ef 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.h
@@ -46,7 +46,6 @@ struct svm_range_bo {
spinlock_t list_lock;
struct amdgpu_amdkfd_fence *eviction_fence;
struct work_struct eviction_work;
- struct svm_range_list *svms;
uint32_t evicting;
struct work_struct release_work;
};
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
index 25990bec600d..3f0a4a415907 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
@@ -1392,8 +1392,8 @@ static int kfd_build_p2p_node_entry(struct kfd_topology_device *dev,
static int kfd_create_indirect_link_prop(struct kfd_topology_device *kdev, int gpu_node)
{
+ struct kfd_iolink_properties *gpu_link, *tmp_link, *cpu_link;
struct kfd_iolink_properties *props = NULL, *props2 = NULL;
- struct kfd_iolink_properties *gpu_link, *cpu_link;
struct kfd_topology_device *cpu_dev;
int ret = 0;
int i, num_cpu;
@@ -1416,16 +1416,19 @@ static int kfd_create_indirect_link_prop(struct kfd_topology_device *kdev, int g
continue;
/* find CPU <--> CPU links */
+ cpu_link = NULL;
cpu_dev = kfd_topology_device_by_proximity_domain(i);
if (cpu_dev) {
- list_for_each_entry(cpu_link,
+ list_for_each_entry(tmp_link,
&cpu_dev->io_link_props, list) {
- if (cpu_link->node_to == gpu_link->node_to)
+ if (tmp_link->node_to == gpu_link->node_to) {
+ cpu_link = tmp_link;
break;
+ }
}
}
- if (cpu_link->node_to != gpu_link->node_to)
+ if (!cpu_link)
return -ENOMEM;
/* CPU <--> CPU <--> GPU, GPU node*/
generated by cgit v1.2.3 (git 2.39.0) at 2025-01-31 01:07:44 +0300