Add a new context creation parameter to express a global context priority.
The priority ranking in descending order is as follows:
* AMDGPU_CTX_PRIORITY_HIGH_HW
* AMDGPU_CTX_PRIORITY_HIGH_SW
* AMDGPU_CTX_PRIORITY_NORMAL
* AMDGPU_CTX_PRIORITY_LOW_SW
* AMDGPU_CTX_PRIORITY_LOW_HW
The driver will attempt to schedule work to the hardware according to
the priorities. No latency or throughput guarantees are provided by
this patch.
This interface intends to service the EGL_IMG_context_priority
extension, and vulkan equivalents.
Setting a priority above NORMAL requires CAP_SYS_NICE or DRM_MASTER.
v2: Instead of using flags, repurpose __pad
v3: Swap enum values of _NORMAL _HIGH for backwards compatibility
v4: Validate usermode priority and store it
v5: Move priority validation into amdgpu_ctx_ioctl(), headline reword
v6: add UAPI note regarding priorities requiring CAP_SYS_ADMIN
v7: remove ctx->priority
v8: added AMDGPU_CTX_PRIORITY_LOW, s/CAP_SYS_ADMIN/CAP_SYS_NICE
v9: change the priority parameter to __s32
v10: split priorities into _SW and _HW
v11: Allow DRM_MASTER without CAP_SYS_NICE
Reviewed-by: Emil Velikov <emil.l.velikov at gmail.com>
Reviewed-by: Christian König <christian.koenig at amd.com>
Signed-off-by: Andres Rodriguez <andresx7 at gmail.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c | 60 +++++++++++++++++++++++++--
drivers/gpu/drm/amd/scheduler/gpu_scheduler.h | 5 ++-
include/uapi/drm/amdgpu_drm.h | 10 ++++-
3 files changed, 69 insertions(+), 6 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
index a11e443..68a852f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
@@ -13,57 +13,83 @@
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
* THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
* OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
* ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
* OTHER DEALINGS IN THE SOFTWARE.
*
* Authors: monk liu <monk.liu at amd.com>
*/
#include <drm/drmP.h>
#include "amdgpu.h"
-static int amdgpu_ctx_init(struct amdgpu_device *adev, struct amdgpu_ctx *ctx)
+static amdgpu_ctx_priority_permit(struct drm_file *filp,
+ enum amd_sched_priority priority)
+{
+ /* NORMAL and below are accessible by everyone */
+ if (priority <= AMD_SCHED_PRIORITY_NORMAL)
+ return 0;
+
+ if (capable(CAP_SYS_NICE))
+ return 0;
+
+ if (drm_is_current_master(filp))
+ return 0;
+
+ return -EACCES;
+}
+
+static int amdgpu_ctx_init(struct amdgpu_device *adev,
+ enum amd_sched_priority priority,
+ struct drm_file *filp,
+ struct amdgpu_ctx *ctx)
{
unsigned i, j;
int r;
+ if (priority < 0 || priority >= AMD_SCHED_PRIORITY_MAX)
+ return -EINVAL;
+
+ r = amdgpu_ctx_priority_permit(filp, priority);
+ if (r)
+ return r;
+
memset(ctx, 0, sizeof(*ctx));
ctx->adev = adev;
kref_init(&ctx->refcount);
spin_lock_init(&ctx->ring_lock);
ctx->fences = kcalloc(amdgpu_sched_jobs * AMDGPU_MAX_RINGS,
sizeof(struct dma_fence*), GFP_KERNEL);
if (!ctx->fences)
return -ENOMEM;
for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
ctx->rings[i].sequence = 1;
ctx->rings[i].fences = &ctx->fences[amdgpu_sched_jobs * i];
}
ctx->reset_counter = atomic_read(&adev->gpu_reset_counter);
/* create context entity for each ring */
for (i = 0; i < adev->num_rings; i++) {
struct amdgpu_ring *ring = adev->rings[i];
struct amd_sched_rq *rq;
- rq = &ring->sched.sched_rq[AMD_SCHED_PRIORITY_NORMAL];
+ rq = &ring->sched.sched_rq[priority];
if (ring == &adev->gfx.kiq.ring)
continue;
r = amd_sched_entity_init(&ring->sched, &ctx->rings[i].entity,
rq, amdgpu_sched_jobs);
if (r)
goto failed;
}
r = amdgpu_queue_mgr_init(adev, &ctx->queue_mgr);
if (r)
goto failed;
return 0;
@@ -88,49 +114,52 @@ static void amdgpu_ctx_fini(struct amdgpu_ctx *ctx)
for (i = 0; i < AMDGPU_MAX_RINGS; ++i)
for (j = 0; j < amdgpu_sched_jobs; ++j)
dma_fence_put(ctx->rings[i].fences[j]);
kfree(ctx->fences);
ctx->fences = NULL;
for (i = 0; i < adev->num_rings; i++)
amd_sched_entity_fini(&adev->rings[i]->sched,
&ctx->rings[i].entity);
amdgpu_queue_mgr_fini(adev, &ctx->queue_mgr);
}
static int amdgpu_ctx_alloc(struct amdgpu_device *adev,
struct amdgpu_fpriv *fpriv,
+ struct drm_file *filp,
+ enum amd_sched_priority priority,
uint32_t *id)
{
struct amdgpu_ctx_mgr *mgr = &fpriv->ctx_mgr;
struct amdgpu_ctx *ctx;
int r;
ctx = kmalloc(sizeof(*ctx), GFP_KERNEL);
if (!ctx)
return -ENOMEM;
mutex_lock(&mgr->lock);
r = idr_alloc(&mgr->ctx_handles, ctx, 1, 0, GFP_KERNEL);
if (r < 0) {
mutex_unlock(&mgr->lock);
kfree(ctx);
return r;
}
+
*id = (uint32_t)r;
- r = amdgpu_ctx_init(adev, ctx);
+ r = amdgpu_ctx_init(adev, priority, filp, ctx);
if (r) {
idr_remove(&mgr->ctx_handles, *id);
*id = 0;
kfree(ctx);
}
mutex_unlock(&mgr->lock);
return r;
}
static void amdgpu_ctx_do_release(struct kref *ref)
{
struct amdgpu_ctx *ctx;
ctx = container_of(ref, struct amdgpu_ctx, refcount);
@@ -176,46 +205,69 @@ static int amdgpu_ctx_query(struct amdgpu_device *adev,
out->state.hangs = 0x0;
/* determine if a GPU reset has occured since the last call */
reset_counter = atomic_read(&adev->gpu_reset_counter);
/* TODO: this should ideally return NO, GUILTY, or INNOCENT. */
if (ctx->reset_counter == reset_counter)
out->state.reset_status = AMDGPU_CTX_NO_RESET;
else
out->state.reset_status = AMDGPU_CTX_UNKNOWN_RESET;
ctx->reset_counter = reset_counter;
mutex_unlock(&mgr->lock);
return 0;
}
+static enum amd_sched_priority amdgpu_to_sched_priority(int amdgpu_priority)
+{
+ switch (amdgpu_priority) {
+ case AMDGPU_CTX_PRIORITY_HIGH_HW:
+ return AMD_SCHED_PRIORITY_HIGH_HW;
+ case AMDGPU_CTX_PRIORITY_HIGH_SW:
+ return AMD_SCHED_PRIORITY_HIGH_SW;
+ case AMDGPU_CTX_PRIORITY_NORMAL:
+ return AMD_SCHED_PRIORITY_NORMAL;
+ case AMDGPU_CTX_PRIORITY_LOW_SW:
+ case AMDGPU_CTX_PRIORITY_LOW_HW:
+ return AMD_SCHED_PRIORITY_LOW;
+ default:
+ WARN(1, "Invalid context priority %d\n", amdgpu_priority);
+ return AMD_SCHED_PRIORITY_NORMAL;
+ }
+}
+
int amdgpu_ctx_ioctl(struct drm_device *dev, void *data,
struct drm_file *filp)
{
int r;
uint32_t id;
+ enum amd_sched_priority priority;
union drm_amdgpu_ctx *args = data;
struct amdgpu_device *adev = dev->dev_private;
struct amdgpu_fpriv *fpriv = filp->driver_priv;
r = 0;
id = args->in.ctx_id;
+ priority = amdgpu_to_sched_priority(args->in.priority);
+
+ if (priority >= AMD_SCHED_PRIORITY_MAX)
+ return -EINVAL;
switch (args->in.op) {
case AMDGPU_CTX_OP_ALLOC_CTX:
- r = amdgpu_ctx_alloc(adev, fpriv, &id);
+ r = amdgpu_ctx_alloc(adev, fpriv, priority, filp, &id);
args->out.alloc.ctx_id = id;
break;
case AMDGPU_CTX_OP_FREE_CTX:
r = amdgpu_ctx_free(fpriv, id);
break;
case AMDGPU_CTX_OP_QUERY_STATE:
r = amdgpu_ctx_query(adev, fpriv, id, &args->out);
break;
default:
return -EINVAL;
}
return r;
}
diff --git a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h
index f9d8f28..38e622c 100644
--- a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h
+++ b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h
@@ -103,31 +103,34 @@ static inline bool amd_sched_invalidate_job(struct amd_sched_job *s_job, int thr
}
/**
* Define the backend operations called by the scheduler,
* these functions should be implemented in driver side
*/
struct amd_sched_backend_ops {
struct dma_fence *(*dependency)(struct amd_sched_job *sched_job);
struct dma_fence *(*run_job)(struct amd_sched_job *sched_job);
void (*timedout_job)(struct amd_sched_job *sched_job);
void (*free_job)(struct amd_sched_job *sched_job);
};
enum amd_sched_priority {
AMD_SCHED_PRIORITY_MIN,
- AMD_SCHED_PRIORITY_NORMAL = AMD_SCHED_PRIORITY_MIN,
+ AMD_SCHED_PRIORITY_LOW = AMD_SCHED_PRIORITY_MIN,
+ AMD_SCHED_PRIORITY_NORMAL,
+ AMD_SCHED_PRIORITY_HIGH_SW,
+ AMD_SCHED_PRIORITY_HIGH_HW,
AMD_SCHED_PRIORITY_KERNEL,
AMD_SCHED_PRIORITY_MAX
};
/**
* One scheduler is implemented for each hardware ring
*/
struct amd_gpu_scheduler {
const struct amd_sched_backend_ops *ops;
uint32_t hw_submission_limit;
long timeout;
const char *name;
struct amd_sched_rq sched_rq[AMD_SCHED_PRIORITY_MAX];
wait_queue_head_t wake_up_worker;
wait_queue_head_t job_scheduled;
diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h
index 34128f6..590fc2a 100644
--- a/include/uapi/drm/amdgpu_drm.h
+++ b/include/uapi/drm/amdgpu_drm.h
@@ -150,37 +150,45 @@ union drm_amdgpu_bo_list {
/* context related */
#define AMDGPU_CTX_OP_ALLOC_CTX 1
#define AMDGPU_CTX_OP_FREE_CTX 2
#define AMDGPU_CTX_OP_QUERY_STATE 3
/* GPU reset status */
#define AMDGPU_CTX_NO_RESET 0
/* this the context caused it */
#define AMDGPU_CTX_GUILTY_RESET 1
/* some other context caused it */
#define AMDGPU_CTX_INNOCENT_RESET 2
/* unknown cause */
#define AMDGPU_CTX_UNKNOWN_RESET 3
+/* Context priority level */
+#define AMDGPU_CTX_PRIORITY_LOW_HW -1023
+#define AMDGPU_CTX_PRIORITY_LOW_SW -512
+#define AMDGPU_CTX_PRIORITY_NORMAL 0
+/* Selecting a priority above NORMAL requires CAP_SYS_NICE or DRM_MASTER */
+#define AMDGPU_CTX_PRIORITY_HIGH_SW 512
+#define AMDGPU_CTX_PRIORITY_HIGH_HW 1023
+
struct drm_amdgpu_ctx_in {
/** AMDGPU_CTX_OP_* */
__u32 op;
/** For future use, no flags defined so far */
__u32 flags;
__u32 ctx_id;
- __u32 _pad;
+ __s32 priority;
};
union drm_amdgpu_ctx_out {
struct {
__u32 ctx_id;
__u32 _pad;
} alloc;
struct {
/** For future use, no flags defined so far */
__u64 flags;
/** Number of resets caused by this context so far. */
__u32 hangs;
/** Reset status since the last call of the ioctl. */
__u32 reset_status;
--
2.9.3
