[PATCH 04/10] drm/i915/perf: allow for CS OA configs to be created lazily
Chris Wilson
chris at chris-wilson.co.uk
Tue Oct 8 20:35:07 UTC 2019
From: Lionel Landwerlin <lionel.g.landwerlin at intel.com>
Here we introduce a mechanism by which the execbuf part of the i915
driver will be able to request that a batch buffer containing the
programming for a particular OA config be created.
We'll execute these OA configuration buffers right before executing a
set of userspace commands so that a particular user batchbuffer be
executed with a given OA configuration.
This mechanism essentially allows the userspace driver to go through
several OA configuration without having to open/close the i915/perf
stream.
v2: No need for locking on object OA config object creation (Chris)
Flush cpu mapping of OA config (Chris)
v3: Properly deal with the perf_metric lock (Chris/Lionel)
v4: Fix oa config unref/put when not found (Lionel)
v5: Allocate BOs for configurations on the stream instead of globally
(Lionel)
v6: Fix 64bit division (Chris)
v7: Store allocated config BOs into the stream (Lionel)
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin at intel.com>
Reviewed-by: Chris Wilson <chris at chris-wilson.co.uk> (v4)
---
drivers/gpu/drm/i915/gt/intel_gpu_commands.h | 1 +
drivers/gpu/drm/i915/i915_perf.c | 266 ++++++++++++++++---
drivers/gpu/drm/i915/i915_perf.h | 31 +++
drivers/gpu/drm/i915/i915_perf_types.h | 24 +-
4 files changed, 277 insertions(+), 45 deletions(-)
diff --git a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
index b0227ab2fe1b..0987100c786b 100644
--- a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
+++ b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
@@ -138,6 +138,7 @@
/* Gen11+. addr = base + (ctx_restore ? offset & GENMASK(12,2) : offset) */
#define MI_LRI_CS_MMIO (1<<19)
#define MI_LRI_FORCE_POSTED (1<<12)
+#define MI_LOAD_REGISTER_IMM_MAX_REGS (126)
#define MI_STORE_REGISTER_MEM MI_INSTR(0x24, 1)
#define MI_STORE_REGISTER_MEM_GEN8 MI_INSTR(0x24, 2)
#define MI_SRM_LRM_GLOBAL_GTT (1<<22)
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 027a1d39f006..96f427bf17a9 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -369,52 +369,215 @@ struct perf_open_properties {
struct intel_engine_cs *engine;
};
+struct i915_oa_config_bo {
+ struct list_head link;
+
+ struct i915_oa_config *oa_config;
+ struct i915_vma *vma;
+};
+
static enum hrtimer_restart oa_poll_check_timer_cb(struct hrtimer *hrtimer);
-static void free_oa_config(struct i915_oa_config *oa_config)
+void i915_oa_config_release(struct kref *ref)
{
+ struct i915_oa_config *oa_config =
+ container_of(ref, typeof(*oa_config), ref);
+
if (!PTR_ERR(oa_config->flex_regs))
kfree(oa_config->flex_regs);
if (!PTR_ERR(oa_config->b_counter_regs))
kfree(oa_config->b_counter_regs);
if (!PTR_ERR(oa_config->mux_regs))
kfree(oa_config->mux_regs);
- kfree(oa_config);
+
+ kfree_rcu(oa_config, rcu);
}
-static void put_oa_config(struct i915_oa_config *oa_config)
+struct i915_oa_config *
+i915_perf_get_oa_config(struct i915_perf *perf, int metrics_set)
{
- if (!atomic_dec_and_test(&oa_config->ref_count))
- return;
+ struct i915_oa_config *oa_config;
- free_oa_config(oa_config);
+ rcu_read_lock();
+ if (metrics_set == 1)
+ oa_config = &perf->test_config;
+ else
+ oa_config = idr_find(&perf->metrics_idr, metrics_set);
+ if (oa_config)
+ oa_config = i915_oa_config_get(oa_config);
+ rcu_read_unlock();
+
+ return oa_config;
}
-static int get_oa_config(struct i915_perf *perf,
- int metrics_set,
- struct i915_oa_config **out_config)
+static u32 *write_cs_mi_lri(u32 *cs,
+ const struct i915_oa_reg *reg_data,
+ u32 n_regs)
{
- int ret;
+ u32 i;
- if (metrics_set == 1) {
- *out_config = &perf->test_config;
- atomic_inc(&perf->test_config.ref_count);
- return 0;
+ for (i = 0; i < n_regs; i++) {
+ if ((i % MI_LOAD_REGISTER_IMM_MAX_REGS) == 0) {
+ u32 n_lri = min_t(u32,
+ n_regs - i,
+ MI_LOAD_REGISTER_IMM_MAX_REGS);
+
+ *cs++ = MI_LOAD_REGISTER_IMM(n_lri);
+ }
+ *cs++ = i915_mmio_reg_offset(reg_data[i].addr);
+ *cs++ = reg_data[i].value;
}
- ret = mutex_lock_interruptible(&perf->metrics_lock);
- if (ret)
- return ret;
+ return cs;
+}
- *out_config = idr_find(&perf->metrics_idr, metrics_set);
- if (!*out_config)
- ret = -EINVAL;
- else
- atomic_inc(&(*out_config)->ref_count);
+static int num_lri_dwords(int num_regs)
+{
+ int count = 0;
- mutex_unlock(&perf->metrics_lock);
+ if (num_regs > 0) {
+ count += DIV_ROUND_UP(num_regs, MI_LOAD_REGISTER_IMM_MAX_REGS);
+ count += num_regs * 2;
+ }
- return ret;
+ return count;
+}
+
+static struct i915_oa_config_bo *
+alloc_oa_config_buffer(struct i915_perf_stream *stream,
+ struct i915_oa_config *oa_config)
+{
+ struct drm_i915_gem_object *obj;
+ struct i915_oa_config_bo *oa_bo;
+ size_t config_length = 0;
+ u32 *cs;
+ int err;
+
+ oa_bo = kzalloc(sizeof(*oa_bo), GFP_KERNEL);
+ if (!oa_bo)
+ return ERR_PTR(-ENOMEM);
+
+ oa_bo->oa_config = i915_oa_config_get(oa_config);
+
+ config_length += num_lri_dwords(oa_config->mux_regs_len);
+ config_length += num_lri_dwords(oa_config->b_counter_regs_len);
+ config_length += num_lri_dwords(oa_config->flex_regs_len);
+ config_length++; /* MI_BATCH_BUFFER_END */
+ config_length = ALIGN(sizeof(u32) * config_length, I915_GTT_PAGE_SIZE);
+
+ obj = i915_gem_object_create_shmem(stream->perf->i915, config_length);
+ if (IS_ERR(obj)) {
+ err = PTR_ERR(obj);
+ goto err_oa_config;
+ }
+
+ cs = i915_gem_object_pin_map(obj, I915_MAP_WB);
+ if (IS_ERR(cs)) {
+ err = PTR_ERR(cs);
+ goto err_oa_bo;
+ }
+
+ cs = write_cs_mi_lri(cs,
+ oa_config->mux_regs,
+ oa_config->mux_regs_len);
+ cs = write_cs_mi_lri(cs,
+ oa_config->b_counter_regs,
+ oa_config->b_counter_regs_len);
+ cs = write_cs_mi_lri(cs,
+ oa_config->flex_regs,
+ oa_config->flex_regs_len);
+
+ *cs++ = MI_BATCH_BUFFER_END;
+
+ i915_gem_object_flush_map(obj);
+ i915_gem_object_unpin_map(obj);
+
+ oa_bo->vma =
+ i915_vma_instance(obj, &stream->engine->gt->ggtt->vm, NULL);
+ if (IS_ERR(oa_bo->vma)) {
+ err = PTR_ERR(oa_bo->vma);
+ goto err_oa_bo;
+ }
+
+ return oa_bo;
+
+err_oa_bo:
+ i915_gem_object_put(obj);
+err_oa_config:
+ i915_oa_config_put(oa_bo->oa_config);
+ kfree(oa_bo);
+ return ERR_PTR(err);
+}
+
+static void free_oa_config_bo(struct i915_oa_config_bo *oa_bo)
+{
+ i915_oa_config_put(oa_bo->oa_config);
+ i915_vma_put(oa_bo->vma);
+ kfree(oa_bo);
+}
+
+int i915_perf_stream_get_oa_config(struct i915_perf_stream *stream,
+ int metrics_set,
+ struct i915_oa_config **out_config,
+ struct i915_vma **out_vma)
+{
+ struct i915_oa_config *oa_config;
+ int err = 0;
+
+ if (!stream->perf->i915)
+ return -ENODEV;
+
+ oa_config = i915_perf_get_oa_config(stream->perf, metrics_set);
+ if (!oa_config)
+ return -EINVAL;
+
+ if (out_vma) {
+ struct i915_oa_config_bo *oa_bo = NULL, *oa_bo_iter;
+
+ /* Look for the buffer in the already allocated BOs attached
+ * to the stream.
+ */
+ err = mutex_lock_interruptible(&stream->config_mutex);
+ if (err)
+ goto err;
+
+ list_for_each_entry(oa_bo_iter, &stream->oa_config_bos, link) {
+ if (oa_bo_iter->oa_config == oa_config &&
+ memcmp(oa_bo_iter->oa_config->uuid,
+ oa_config->uuid,
+ sizeof(oa_config->uuid)) == 0) {
+ oa_bo = oa_bo_iter;
+ break;
+ }
+ }
+
+ mutex_unlock(&stream->config_mutex);
+
+ if (!oa_bo) {
+ oa_bo = alloc_oa_config_buffer(stream, oa_config);
+ if (IS_ERR(oa_bo)) {
+ err = PTR_ERR(oa_bo);
+ goto err;
+ }
+
+ err = mutex_lock_interruptible(&stream->config_mutex);
+ if (err) {
+ free_oa_config_bo(oa_bo);
+ goto err;
+ }
+
+ list_add(&oa_bo->link, &stream->oa_config_bos);
+
+ mutex_unlock(&stream->config_mutex);
+ }
+
+ *out_vma = i915_vma_get(oa_bo->vma);
+ }
+
+err:
+ if (!err)
+ *out_config = oa_config;
+ return err;
}
static u32 gen8_oa_hw_tail_read(struct i915_perf_stream *stream)
@@ -1337,6 +1500,18 @@ free_oa_buffer(struct i915_perf_stream *stream)
stream->oa_buffer.vaddr = NULL;
}
+static void
+free_oa_configs(struct i915_perf_stream *stream)
+{
+ struct i915_oa_config_bo *oa_bo, *tmp;
+
+ i915_oa_config_put(stream->oa_config);
+ list_for_each_entry_safe(oa_bo, tmp, &stream->oa_config_bos, link) {
+ list_del(&oa_bo->link);
+ free_oa_config_bo(oa_bo);
+ }
+}
+
static void i915_oa_stream_destroy(struct i915_perf_stream *stream)
{
struct i915_perf *perf = stream->perf;
@@ -1358,7 +1533,7 @@ static void i915_oa_stream_destroy(struct i915_perf_stream *stream)
if (stream->ctx)
oa_put_render_ctx_id(stream);
- put_oa_config(stream->oa_config);
+ free_oa_configs(stream);
if (perf->spurious_report_rs.missed) {
DRM_NOTE("%d spurious OA report notices suppressed due to ratelimiting\n",
@@ -2171,6 +2346,8 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
return -EINVAL;
}
+ mutex_init(&stream->config_mutex);
+
stream->sample_size = sizeof(struct drm_i915_perf_record_header);
format_size = perf->oa_formats[props->oa_format].size;
@@ -2199,9 +2376,10 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
}
}
- ret = get_oa_config(perf, props->metrics_set, &stream->oa_config);
- if (ret) {
+ stream->oa_config = i915_perf_get_oa_config(perf, props->metrics_set);
+ if (!stream->oa_config) {
DRM_DEBUG("Invalid OA config id=%i\n", props->metrics_set);
+ ret = -EINVAL;
goto err_config;
}
@@ -2234,6 +2412,9 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
goto err_enable;
}
+ DRM_DEBUG("opening stream oa config uuid=%s\n",
+ stream->oa_config->uuid);
+
hrtimer_init(&stream->poll_check_timer,
CLOCK_MONOTONIC, HRTIMER_MODE_REL);
stream->poll_check_timer.function = oa_poll_check_timer_cb;
@@ -2249,11 +2430,11 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
free_oa_buffer(stream);
err_oa_buf_alloc:
- put_oa_config(stream->oa_config);
-
intel_uncore_forcewake_put(stream->gt->uncore, FORCEWAKE_ALL);
intel_runtime_pm_put(stream->gt->uncore->rpm, stream->wakeref);
+ free_oa_configs(stream);
+
err_config:
if (stream->ctx)
oa_put_render_ctx_id(stream);
@@ -2724,6 +2905,7 @@ i915_perf_open_ioctl_locked(struct i915_perf *perf,
goto err_ctx;
}
+ INIT_LIST_HEAD(&stream->oa_config_bos);
stream->perf = perf;
stream->gt = &perf->i915->gt;
stream->ctx = specific_ctx;
@@ -3058,7 +3240,8 @@ void i915_perf_register(struct drm_i915_private *i915)
if (ret)
goto sysfs_error;
- atomic_set(&perf->test_config.ref_count, 1);
+ perf->test_config.perf = perf;
+ kref_init(&perf->test_config.ref);
goto exit;
@@ -3316,7 +3499,8 @@ int i915_perf_add_config_ioctl(struct drm_device *dev, void *data,
return -ENOMEM;
}
- atomic_set(&oa_config->ref_count, 1);
+ oa_config->perf = perf;
+ kref_init(&oa_config->ref);
if (!uuid_is_valid(args->uuid)) {
DRM_DEBUG("Invalid uuid format for OA config\n");
@@ -3415,7 +3599,7 @@ int i915_perf_add_config_ioctl(struct drm_device *dev, void *data,
sysfs_err:
mutex_unlock(&perf->metrics_lock);
reg_err:
- put_oa_config(oa_config);
+ i915_oa_config_put(oa_config);
DRM_DEBUG("Failed to add new OA config\n");
return err;
}
@@ -3451,13 +3635,13 @@ int i915_perf_remove_config_ioctl(struct drm_device *dev, void *data,
ret = mutex_lock_interruptible(&perf->metrics_lock);
if (ret)
- goto lock_err;
+ return ret;
oa_config = idr_find(&perf->metrics_idr, *arg);
if (!oa_config) {
DRM_DEBUG("Failed to remove unknown OA config\n");
ret = -ENOENT;
- goto config_err;
+ goto err_unlock;
}
GEM_BUG_ON(*arg != oa_config->id);
@@ -3467,13 +3651,16 @@ int i915_perf_remove_config_ioctl(struct drm_device *dev, void *data,
idr_remove(&perf->metrics_idr, *arg);
+ mutex_unlock(&perf->metrics_lock);
+
DRM_DEBUG("Removed config %s id=%i\n", oa_config->uuid, oa_config->id);
- put_oa_config(oa_config);
+ i915_oa_config_put(oa_config);
+
+ return 0;
-config_err:
+err_unlock:
mutex_unlock(&perf->metrics_lock);
-lock_err:
return ret;
}
@@ -3643,7 +3830,7 @@ void i915_perf_init(struct drm_i915_private *i915)
static int destroy_config(int id, void *p, void *data)
{
- put_oa_config(p);
+ i915_oa_config_put(p);
return 0;
}
@@ -3655,9 +3842,6 @@ void i915_perf_fini(struct drm_i915_private *i915)
{
struct i915_perf *perf = &i915->perf;
- if (!perf->i915)
- return;
-
idr_for_each(&perf->metrics_idr, destroy_config, perf);
idr_destroy(&perf->metrics_idr);
diff --git a/drivers/gpu/drm/i915/i915_perf.h b/drivers/gpu/drm/i915/i915_perf.h
index 295e33e8eef7..2d1fcc94c518 100644
--- a/drivers/gpu/drm/i915/i915_perf.h
+++ b/drivers/gpu/drm/i915/i915_perf.h
@@ -7,12 +7,16 @@
#define __I915_PERF_H__
#include <linux/types.h>
+#include <linux/kref.h>
#include "i915_perf_types.h"
struct drm_device;
struct drm_file;
+struct drm_i915_gem_object;
struct drm_i915_private;
+struct i915_oa_config;
+struct i915_perf_stream;
struct intel_context;
struct intel_engine_cs;
@@ -28,7 +32,34 @@ int i915_perf_add_config_ioctl(struct drm_device *dev, void *data,
struct drm_file *file);
int i915_perf_remove_config_ioctl(struct drm_device *dev, void *data,
struct drm_file *file);
+
void i915_oa_init_reg_state(const struct intel_context *ce,
const struct intel_engine_cs *engine);
+struct i915_oa_config *
+i915_perf_get_oa_config(struct i915_perf *perf, int metrics_set);
+
+int i915_perf_stream_get_oa_config(struct i915_perf_stream *stream,
+ int metrics_set,
+ struct i915_oa_config **out_config,
+ struct i915_vma **out_vma);
+
+static inline struct i915_oa_config *
+i915_oa_config_get(struct i915_oa_config *oa_config)
+{
+ if (kref_get_unless_zero(&oa_config->ref))
+ return oa_config;
+ else
+ return NULL;
+}
+
+void i915_oa_config_release(struct kref *ref);
+static inline void i915_oa_config_put(struct i915_oa_config *oa_config)
+{
+ if (!oa_config)
+ return;
+
+ kref_put(&oa_config->ref, i915_oa_config_release);
+}
+
#endif /* __I915_PERF_H__ */
diff --git a/drivers/gpu/drm/i915/i915_perf_types.h b/drivers/gpu/drm/i915/i915_perf_types.h
index 82cd3b295037..5baee4f0fe91 100644
--- a/drivers/gpu/drm/i915/i915_perf_types.h
+++ b/drivers/gpu/drm/i915/i915_perf_types.h
@@ -22,6 +22,7 @@
struct drm_i915_private;
struct file;
struct i915_gem_context;
+struct i915_perf;
struct i915_vma;
struct intel_context;
struct intel_engine_cs;
@@ -37,6 +38,8 @@ struct i915_oa_reg {
};
struct i915_oa_config {
+ struct i915_perf *perf;
+
char uuid[UUID_STRING_LEN + 1];
int id;
@@ -51,7 +54,8 @@ struct i915_oa_config {
struct attribute *attrs[2];
struct device_attribute sysfs_metric_id;
- atomic_t ref_count;
+ struct kref ref;
+ struct rcu_head rcu;
};
struct i915_perf_stream;
@@ -178,13 +182,25 @@ struct i915_perf_stream {
*/
const struct i915_perf_stream_ops *ops;
+ /**
+ * @active_config_mutex: Protects access to @oa_config & @oa_config_bos.
+ */
+ struct mutex config_mutex;
+
/**
* @oa_config: The OA configuration used by the stream.
*/
struct i915_oa_config *oa_config;
+ /**
+ * @oa_config_bos: A list of struct i915_oa_config_bo allocated lazily
+ * each time @oa_config changes.
+ */
+ struct list_head oa_config_bos;
+
/**
* @pinned_ctx: The OA context specific information.
+ * The OA context specific information.
*/
struct intel_context *pinned_ctx;
u32 specific_ctx_id;
@@ -337,13 +353,13 @@ struct i915_perf {
/*
* Lock associated with adding/modifying/removing OA configs
- * in dev_priv->perf.metrics_idr.
+ * in perf->metrics_idr.
*/
struct mutex metrics_lock;
/*
- * List of dynamic configurations, you need to hold
- * dev_priv->perf.metrics_lock to access it.
+ * List of dynamic configurations (struct i915_oa_config), you
+ * need to hold perf->metrics_lock to access it.
*/
struct idr metrics_idr;
--
2.23.0
More information about the Intel-gfx-trybot
mailing list