[Intel-gfx] [CI 11/13] drm/i915: add a new perf configuration execbuf parameter
We want the ability to dispatch a set of command buffer to the
hardware, each with a different OA configuration. To achieve this, we
reuse a couple of fields from the execbuf2 struct (I CAN HAZ
execbuf3?) to notify what OA configuration should be used for a batch
buffer. This requires the process making the execbuf with this flag to
also own the perf fd at the time of execbuf.
v2: Add a emit_oa_config() vfunc in the intel_engine_cs (Chris)
Move oa_config vma to active (Chris)
v3: Don't drop the lock for engine lookup (Chris)
Move OA config vma to active before writing the ringbuffer (Chris)
v4: Reuse i915_user_extension_fn
Serialize requests with OA config updates
v5: Check that the chained extension is only present once (Chris)
Unpin oa_vma in main path (Chris)
v6: Use BIT_ULL (Chris)
v7: Hold drm.struct_mutex when serializing the request with OA config (Chris)
v8: Remove active request from engine (Lionel)
v9: Move fetching OA configuration pass engine pinning (Lionel)
Lock VMA before moving to active (Chris)
v10: Fix leak on perf_fd (Lionel)
Signed-off-by: Lionel Landwerlin
---
.../gpu/drm/i915/gem/i915_gem_execbuffer.c| 147 +-
drivers/gpu/drm/i915/i915_getparam.c | 4 +
include/uapi/drm/i915_drm.h | 39 +
3 files changed, 188 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index 46ad8d9642d1..d416b60c94bb 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -24,6 +24,7 @@
#include "i915_gem_clflush.h"
#include "i915_gem_context.h"
#include "i915_gem_ioctls.h"
+#include "i915_perf.h"
#include "i915_trace.h"
#include "i915_user_extensions.h"
@@ -284,7 +285,12 @@ struct i915_execbuffer {
struct {
u64 flags; /** Available extensions parameters */
struct drm_i915_gem_execbuffer_ext_timeline_fences
timeline_fences;
+ struct drm_i915_gem_execbuffer_ext_perf perf_config;
} extensions;
+
+ struct file *perf_file;
+ struct i915_oa_config *oa_config; /** HW configuration for OA, NULL is
not needed. */
+ struct i915_vma *oa_vma;
};
#define exec_entry(EB, VMA) (&(EB)->exec[(VMA)->exec_flags - (EB)->flags])
@@ -1152,6 +1158,58 @@ static int reloc_move_to_gpu(struct i915_request *rq,
struct i915_vma *vma)
return err;
}
+
+static int
+eb_get_oa_config(struct i915_execbuffer *eb)
+{
+ struct drm_i915_gem_object *oa_bo;
+ int err = 0;
+
+ eb->perf_file = NULL;
+ eb->oa_config = NULL;
+ eb->oa_vma = NULL;
+
+ if ((eb->extensions.flags & BIT_ULL(DRM_I915_GEM_EXECBUFFER_EXT_PERF))
== 0)
+ return 0;
+
+ eb->perf_file = fget(eb->extensions.perf_config.perf_fd);
+ if (!eb->perf_file)
+ return -EINVAL;
+
+ err = i915_mutex_lock_interruptible(&eb->i915->drm);
+ if (err)
+ return err;
+
+ if (eb->perf_file->private_data != eb->i915->perf.exclusive_stream)
+ err = -EINVAL;
+
+ mutex_unlock(&eb->i915->drm.struct_mutex);
+
+ if (err)
+ return err;
+
+ if (eb->i915->perf.exclusive_stream->engine != eb->engine)
+ return -EINVAL;
+
+ err = i915_perf_get_oa_config_and_bo(
+ eb->i915->perf.exclusive_stream,
+ eb->extensions.perf_config.oa_config,
+ &eb->oa_config, &oa_bo);
+ if (err)
+ return err;
+
+ eb->oa_vma = i915_vma_instance(oa_bo,
+ &eb->engine->gt->ggtt->vm, NULL);
+ i915_gem_object_put(oa_bo);
+ if (IS_ERR(eb->oa_vma)) {
+ err = PTR_ERR(eb->oa_vma);
+ eb->oa_vma = NULL;
+ return err;
+ }
+
+ return 0;
+}
+
static int __reloc_gpu_alloc(struct i915_execbuffer *eb,
struct i915_vma *vma,
unsigned int len)
@@ -2051,6 +2109,54 @@ add_to_client(struct i915_request *rq, struct drm_file
*file)
spin_unlock(&file_priv->mm.lock);
}
+static int eb_oa_config(struct i915_execbuffer *eb)
+{
+ struct i915_perf_stream *perf_stream;
+ int err;
+
+ if (!eb->oa_config)
+ return 0;
+
+ perf_stream = eb->perf_file->private_data;
+
+ err = mutex_lock_interruptible(&perf_stream->config_mutex);
+ if (err)
+ return err;
+
+ err = i915_active_request_set(&perf_stream->active_config_rq,
+ eb->request);
+ if (err)
+ goto out;
+
+ /*
+* If the config hasn't changed, skip reconfiguring the HW (this is
+* subject to a delay we want to avoid has much as possible).
+*/
+ if (eb->oa_config == perf_stream->oa_config)
+ goto out;
+
+ i
[Intel-gfx] [CI 11/13] drm/i915: add a new perf configuration execbuf parameter
We want the ability to dispatch a set of command buffer to the
hardware, each with a different OA configuration. To achieve this, we
reuse a couple of fields from the execbuf2 struct (I CAN HAZ
execbuf3?) to notify what OA configuration should be used for a batch
buffer. This requires the process making the execbuf with this flag to
also own the perf fd at the time of execbuf.
v2: Add a emit_oa_config() vfunc in the intel_engine_cs (Chris)
Move oa_config vma to active (Chris)
v3: Don't drop the lock for engine lookup (Chris)
Move OA config vma to active before writing the ringbuffer (Chris)
v4: Reuse i915_user_extension_fn
Serialize requests with OA config updates
v5: Check that the chained extension is only present once (Chris)
Unpin oa_vma in main path (Chris)
v6: Use BIT_ULL (Chris)
v7: Hold drm.struct_mutex when serializing the request with OA config (Chris)
v8: Remove active request from engine (Lionel)
v9: Move fetching OA configuration pass engine pinning (Lionel)
Lock VMA before moving to active (Chris)
v10: Fix leak on perf_fd (Lionel)
Signed-off-by: Lionel Landwerlin
---
.../gpu/drm/i915/gem/i915_gem_execbuffer.c| 147 +-
drivers/gpu/drm/i915/i915_getparam.c | 4 +
include/uapi/drm/i915_drm.h | 39 +
3 files changed, 188 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index 46ad8d9642d1..d416b60c94bb 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -24,6 +24,7 @@
#include "i915_gem_clflush.h"
#include "i915_gem_context.h"
#include "i915_gem_ioctls.h"
+#include "i915_perf.h"
#include "i915_trace.h"
#include "i915_user_extensions.h"
@@ -284,7 +285,12 @@ struct i915_execbuffer {
struct {
u64 flags; /** Available extensions parameters */
struct drm_i915_gem_execbuffer_ext_timeline_fences
timeline_fences;
+ struct drm_i915_gem_execbuffer_ext_perf perf_config;
} extensions;
+
+ struct file *perf_file;
+ struct i915_oa_config *oa_config; /** HW configuration for OA, NULL is
not needed. */
+ struct i915_vma *oa_vma;
};
#define exec_entry(EB, VMA) (&(EB)->exec[(VMA)->exec_flags - (EB)->flags])
@@ -1152,6 +1158,58 @@ static int reloc_move_to_gpu(struct i915_request *rq,
struct i915_vma *vma)
return err;
}
+
+static int
+eb_get_oa_config(struct i915_execbuffer *eb)
+{
+ struct drm_i915_gem_object *oa_bo;
+ int err = 0;
+
+ eb->perf_file = NULL;
+ eb->oa_config = NULL;
+ eb->oa_vma = NULL;
+
+ if ((eb->extensions.flags & BIT_ULL(DRM_I915_GEM_EXECBUFFER_EXT_PERF))
== 0)
+ return 0;
+
+ eb->perf_file = fget(eb->extensions.perf_config.perf_fd);
+ if (!eb->perf_file)
+ return -EINVAL;
+
+ err = i915_mutex_lock_interruptible(&eb->i915->drm);
+ if (err)
+ return err;
+
+ if (eb->perf_file->private_data != eb->i915->perf.exclusive_stream)
+ err = -EINVAL;
+
+ mutex_unlock(&eb->i915->drm.struct_mutex);
+
+ if (err)
+ return err;
+
+ if (eb->i915->perf.exclusive_stream->engine != eb->engine)
+ return -EINVAL;
+
+ err = i915_perf_get_oa_config_and_bo(
+ eb->i915->perf.exclusive_stream,
+ eb->extensions.perf_config.oa_config,
+ &eb->oa_config, &oa_bo);
+ if (err)
+ return err;
+
+ eb->oa_vma = i915_vma_instance(oa_bo,
+ &eb->engine->gt->ggtt->vm, NULL);
+ i915_gem_object_put(oa_bo);
+ if (IS_ERR(eb->oa_vma)) {
+ err = PTR_ERR(eb->oa_vma);
+ eb->oa_vma = NULL;
+ return err;
+ }
+
+ return 0;
+}
+
static int __reloc_gpu_alloc(struct i915_execbuffer *eb,
struct i915_vma *vma,
unsigned int len)
@@ -2051,6 +2109,54 @@ add_to_client(struct i915_request *rq, struct drm_file
*file)
spin_unlock(&file_priv->mm.lock);
}
+static int eb_oa_config(struct i915_execbuffer *eb)
+{
+ struct i915_perf_stream *perf_stream;
+ int err;
+
+ if (!eb->oa_config)
+ return 0;
+
+ perf_stream = eb->perf_file->private_data;
+
+ err = mutex_lock_interruptible(&perf_stream->config_mutex);
+ if (err)
+ return err;
+
+ err = i915_active_request_set(&perf_stream->active_config_rq,
+ eb->request);
+ if (err)
+ goto out;
+
+ /*
+* If the config hasn't changed, skip reconfiguring the HW (this is
+* subject to a delay we want to avoid has much as possible).
+*/
+ if (eb->oa_config == perf_stream->oa_config)
+ goto out;
+
+ i
