diff options
| author | Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com> | 2022-10-26 22:20:53 +0000 |
|---|---|---|
| committer | John Harrison <John.C.Harrison@Intel.com> | 2022-10-27 12:36:30 -0700 |
| commit | 9677a9f3b1ad3537bc945e7c7e54778632ee2d0f (patch) | |
| tree | 150e3a2c148d3bffe73441577f1b3419e1872c97 /drivers/gpu/drm/i915/i915_perf.c | |
| parent | a5a6d92f77ffde188ce3aa4ccec21fac5b00c6e8 (diff) | |
| download | linux-9677a9f3b1ad3537bc945e7c7e54778632ee2d0f.tar.gz linux-9677a9f3b1ad3537bc945e7c7e54778632ee2d0f.tar.bz2 linux-9677a9f3b1ad3537bc945e7c7e54778632ee2d0f.zip | |
drm/i915/perf: Move gt-specific data from i915->perf to gt->perf
Make perf part of gt as the OAG buffer is specific to a gt. The refactor
eventually simplifies programming the right OA buffer and the right HW
registers when supporting multiple gts.
Signed-off-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20221026222102.5526-8-umesh.nerlige.ramappa@intel.com
Diffstat (limited to 'drivers/gpu/drm/i915/i915_perf.c')
| -rw-r--r-- | drivers/gpu/drm/i915/i915_perf.c | 75 |
1 files changed, 44 insertions, 31 deletions
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c index 75d320b2c1f8..83c5dc043261 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -1565,8 +1565,9 @@ free_noa_wait(struct i915_perf_stream *stream) static void i915_oa_stream_destroy(struct i915_perf_stream *stream) { struct i915_perf *perf = stream->perf; + struct intel_gt *gt = stream->engine->gt; - if (WARN_ON(stream != perf->exclusive_stream)) + if (WARN_ON(stream != gt->perf.exclusive_stream)) return; /* @@ -1575,7 +1576,7 @@ static void i915_oa_stream_destroy(struct i915_perf_stream *stream) * * See i915_oa_init_reg_state() and lrc_configure_all_contexts() */ - WRITE_ONCE(perf->exclusive_stream, NULL); + WRITE_ONCE(gt->perf.exclusive_stream, NULL); perf->ops.disable_metric_set(stream); free_oa_buffer(stream); @@ -2566,10 +2567,11 @@ oa_configure_all_contexts(struct i915_perf_stream *stream, { struct drm_i915_private *i915 = stream->perf->i915; struct intel_engine_cs *engine; + struct intel_gt *gt = stream->engine->gt; struct i915_gem_context *ctx, *cn; int err; - lockdep_assert_held(&stream->perf->lock); + lockdep_assert_held(>->perf.lock); /* * The OA register config is setup through the context image. This image @@ -3090,6 +3092,7 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream, { struct drm_i915_private *i915 = stream->perf->i915; struct i915_perf *perf = stream->perf; + struct intel_gt *gt; int format_size; int ret; @@ -3098,6 +3101,7 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream, "OA engine not specified\n"); return -EINVAL; } + gt = props->engine->gt; /* * If the sysfs metrics/ directory wasn't registered for some @@ -3128,7 +3132,7 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream, * counter reports and marshal to the appropriate client * we currently only allow exclusive access */ - if (perf->exclusive_stream) { + if (gt->perf.exclusive_stream) { drm_dbg(&stream->perf->i915->drm, "OA unit already in use\n"); return -EBUSY; @@ -3208,8 +3212,8 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream, stream->ops = &i915_oa_stream_ops; - perf->sseu = props->sseu; - WRITE_ONCE(perf->exclusive_stream, stream); + stream->engine->gt->perf.sseu = props->sseu; + WRITE_ONCE(gt->perf.exclusive_stream, stream); ret = i915_perf_stream_enable_sync(stream); if (ret) { @@ -3231,7 +3235,7 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream, return 0; err_enable: - WRITE_ONCE(perf->exclusive_stream, NULL); + WRITE_ONCE(gt->perf.exclusive_stream, NULL); perf->ops.disable_metric_set(stream); free_oa_buffer(stream); @@ -3261,7 +3265,7 @@ void i915_oa_init_reg_state(const struct intel_context *ce, return; /* perf.exclusive_stream serialised by lrc_configure_all_contexts() */ - stream = READ_ONCE(engine->i915->perf.exclusive_stream); + stream = READ_ONCE(engine->gt->perf.exclusive_stream); if (stream && GRAPHICS_VER(stream->perf->i915) < 12) gen8_update_reg_state_unlocked(ce, stream); } @@ -3290,7 +3294,7 @@ static ssize_t i915_perf_read(struct file *file, loff_t *ppos) { struct i915_perf_stream *stream = file->private_data; - struct i915_perf *perf = stream->perf; + struct intel_gt *gt = stream->engine->gt; size_t offset = 0; int ret; @@ -3314,14 +3318,14 @@ static ssize_t i915_perf_read(struct file *file, if (ret) return ret; - mutex_lock(&perf->lock); + mutex_lock(>->perf.lock); ret = stream->ops->read(stream, buf, count, &offset); - mutex_unlock(&perf->lock); + mutex_unlock(>->perf.lock); } while (!offset && !ret); } else { - mutex_lock(&perf->lock); + mutex_lock(>->perf.lock); ret = stream->ops->read(stream, buf, count, &offset); - mutex_unlock(&perf->lock); + mutex_unlock(>->perf.lock); } /* We allow the poll checking to sometimes report false positive EPOLLIN @@ -3368,7 +3372,7 @@ static enum hrtimer_restart oa_poll_check_timer_cb(struct hrtimer *hrtimer) * &i915_perf_stream_ops->poll_wait to call poll_wait() with a wait queue that * will be woken for new stream data. * - * Note: The &perf->lock mutex has been taken to serialize + * Note: The >->perf.lock mutex has been taken to serialize * with any non-file-operation driver hooks. * * Returns: any poll events that are ready without sleeping @@ -3409,12 +3413,12 @@ static __poll_t i915_perf_poll_locked(struct i915_perf_stream *stream, static __poll_t i915_perf_poll(struct file *file, poll_table *wait) { struct i915_perf_stream *stream = file->private_data; - struct i915_perf *perf = stream->perf; + struct intel_gt *gt = stream->engine->gt; __poll_t ret; - mutex_lock(&perf->lock); + mutex_lock(>->perf.lock); ret = i915_perf_poll_locked(stream, file, wait); - mutex_unlock(&perf->lock); + mutex_unlock(>->perf.lock); return ret; } @@ -3513,7 +3517,7 @@ static long i915_perf_config_locked(struct i915_perf_stream *stream, * @cmd: the ioctl request * @arg: the ioctl data * - * Note: The &perf->lock mutex has been taken to serialize + * Note: The >->perf.lock mutex has been taken to serialize * with any non-file-operation driver hooks. * * Returns: zero on success or a negative error code. Returns -EINVAL for @@ -3553,12 +3557,12 @@ static long i915_perf_ioctl(struct file *file, unsigned long arg) { struct i915_perf_stream *stream = file->private_data; - struct i915_perf *perf = stream->perf; + struct intel_gt *gt = stream->engine->gt; long ret; - mutex_lock(&perf->lock); + mutex_lock(>->perf.lock); ret = i915_perf_ioctl_locked(stream, cmd, arg); - mutex_unlock(&perf->lock); + mutex_unlock(>->perf.lock); return ret; } @@ -3570,7 +3574,7 @@ static long i915_perf_ioctl(struct file *file, * Frees all resources associated with the given i915 perf @stream, disabling * any associated data capture in the process. * - * Note: The &perf->lock mutex has been taken to serialize + * Note: The >->perf.lock mutex has been taken to serialize * with any non-file-operation driver hooks. */ static void i915_perf_destroy_locked(struct i915_perf_stream *stream) @@ -3602,10 +3606,11 @@ static int i915_perf_release(struct inode *inode, struct file *file) { struct i915_perf_stream *stream = file->private_data; struct i915_perf *perf = stream->perf; + struct intel_gt *gt = stream->engine->gt; - mutex_lock(&perf->lock); + mutex_lock(>->perf.lock); i915_perf_destroy_locked(stream); - mutex_unlock(&perf->lock); + mutex_unlock(>->perf.lock); /* Release the reference the perf stream kept on the driver. */ drm_dev_put(&perf->i915->drm); @@ -3638,7 +3643,7 @@ static const struct file_operations fops = { * See i915_perf_ioctl_open() for interface details. * * Implements further stream config validation and stream initialization on - * behalf of i915_perf_open_ioctl() with the &perf->lock mutex + * behalf of i915_perf_open_ioctl() with the >->perf.lock mutex * taken to serialize with any non-file-operation driver hooks. * * Note: at this point the @props have only been validated in isolation and @@ -4022,7 +4027,7 @@ static int read_properties_unlocked(struct i915_perf *perf, * mutex to avoid an awkward lockdep with mmap_lock. * * Most of the implementation details are handled by - * i915_perf_open_ioctl_locked() after taking the &perf->lock + * i915_perf_open_ioctl_locked() after taking the >->perf.lock * mutex for serializing with any non-file-operation driver hooks. * * Return: A newly opened i915 Perf stream file descriptor or negative @@ -4033,6 +4038,7 @@ int i915_perf_open_ioctl(struct drm_device *dev, void *data, { struct i915_perf *perf = &to_i915(dev)->perf; struct drm_i915_perf_open_param *param = data; + struct intel_gt *gt; struct perf_open_properties props; u32 known_open_flags; int ret; @@ -4059,9 +4065,11 @@ int i915_perf_open_ioctl(struct drm_device *dev, void *data, if (ret) return ret; - mutex_lock(&perf->lock); + gt = props.engine->gt; + + mutex_lock(>->perf.lock); ret = i915_perf_open_ioctl_locked(perf, param, &props, file); - mutex_unlock(&perf->lock); + mutex_unlock(>->perf.lock); return ret; } @@ -4077,6 +4085,7 @@ int i915_perf_open_ioctl(struct drm_device *dev, void *data, void i915_perf_register(struct drm_i915_private *i915) { struct i915_perf *perf = &i915->perf; + struct intel_gt *gt = to_gt(i915); if (!perf->i915) return; @@ -4085,13 +4094,13 @@ void i915_perf_register(struct drm_i915_private *i915) * i915_perf_open_ioctl(); considering that we register after * being exposed to userspace. */ - mutex_lock(&perf->lock); + mutex_lock(>->perf.lock); perf->metrics_kobj = kobject_create_and_add("metrics", &i915->drm.primary->kdev->kobj); - mutex_unlock(&perf->lock); + mutex_unlock(>->perf.lock); } /** @@ -4768,7 +4777,11 @@ void i915_perf_init(struct drm_i915_private *i915) } if (perf->ops.enable_metric_set) { - mutex_init(&perf->lock); + struct intel_gt *gt; + int i; + + for_each_gt(gt, i915, i) + mutex_init(>->perf.lock); /* Choose a representative limit */ oa_sample_rate_hard_limit = to_gt(i915)->clock_frequency / 2; |