[CI 1/4] drm/i915/perf: introduce a versioning of the i915-perf uapi

[CI 1/4] drm/i915/perf: introduce a versioning of the i915-perf uapi

[Chris Wilson]

From: Lionel Landwerlin <lionel.g.landwerlin@intel.com>

Reporting this version will help application figure out what level of
the support the running kernel provides.

v2: Add i915_perf_ioctl_version() (Chris)

Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_getparam.c |  4 ++++
 drivers/gpu/drm/i915/i915_perf.c     | 10 ++++++++++
 drivers/gpu/drm/i915/i915_perf.h     |  1 +
 include/uapi/drm/i915_drm.h          | 21 +++++++++++++++++++++
 4 files changed, 36 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_getparam.c b/drivers/gpu/drm/i915/i915_getparam.c
index f4b3cbb1adce..ad33fbe90a28 100644
--- a/drivers/gpu/drm/i915/i915_getparam.c
+++ b/drivers/gpu/drm/i915/i915_getparam.c
@@ -5,6 +5,7 @@
 #include "gt/intel_engine_user.h"
 
 #include "i915_drv.h"
+#include "i915_perf.h"
 
 int i915_getparam_ioctl(struct drm_device *dev, void *data,
 			struct drm_file *file_priv)
@@ -156,6 +157,9 @@ int i915_getparam_ioctl(struct drm_device *dev, void *data,
 	case I915_PARAM_MMAP_GTT_COHERENT:
 		value = INTEL_INFO(i915)->has_coherent_ggtt;
 		break;
+	case I915_PARAM_PERF_REVISION:
+		value = i915_perf_ioctl_version();
+		break;
 	default:
 		DRM_DEBUG("Unknown parameter %d\n", param->param);
 		return -EINVAL;
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 366580701ba2..220e3384af30 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -4017,6 +4017,16 @@ void i915_perf_fini(struct drm_i915_private *i915)
 	perf->i915 = NULL;
 }
 
+/**
+ * i915_perf_ioctl_version - Version of the i915-perf subsystem
+ *
+ * This version number is used by userspace to detect available features.
+ */
+int i915_perf_ioctl_version(void)
+{
+	return 1;
+}
+
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
 #include "selftests/i915_perf.c"
 #endif
diff --git a/drivers/gpu/drm/i915/i915_perf.h b/drivers/gpu/drm/i915/i915_perf.h
index 98e16be48a73..4ceebce72060 100644
--- a/drivers/gpu/drm/i915/i915_perf.h
+++ b/drivers/gpu/drm/i915/i915_perf.h
@@ -22,6 +22,7 @@ void i915_perf_init(struct drm_i915_private *i915);
 void i915_perf_fini(struct drm_i915_private *i915);
 void i915_perf_register(struct drm_i915_private *i915);
 void i915_perf_unregister(struct drm_i915_private *i915);
+int i915_perf_ioctl_version(void);
 
 int i915_perf_open_ioctl(struct drm_device *dev, void *data,
 			 struct drm_file *file);
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index 30c542144016..c50c712b3771 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -611,6 +611,13 @@ typedef struct drm_i915_irq_wait {
  * See I915_EXEC_FENCE_OUT and I915_EXEC_FENCE_SUBMIT.
  */
 #define I915_PARAM_HAS_EXEC_SUBMIT_FENCE 53
+
+/*
+ * Revision of the i915-perf uAPI. The value returned helps determine what
+ * i915-perf features are available. See drm_i915_perf_property_id.
+ */
+#define I915_PARAM_PERF_REVISION	54
+
 /* Must be kept compact -- no holes and well documented */
 
 typedef struct drm_i915_getparam {
@@ -1844,23 +1851,31 @@ enum drm_i915_perf_property_id {
 	 * Open the stream for a specific context handle (as used with
 	 * execbuffer2). A stream opened for a specific context this way
 	 * won't typically require root privileges.
+	 *
+	 * This property is available in perf revision 1.
 	 */
 	DRM_I915_PERF_PROP_CTX_HANDLE = 1,
 
 	/**
 	 * A value of 1 requests the inclusion of raw OA unit reports as
 	 * part of stream samples.
+	 *
+	 * This property is available in perf revision 1.
 	 */
 	DRM_I915_PERF_PROP_SAMPLE_OA,
 
 	/**
 	 * The value specifies which set of OA unit metrics should be
 	 * be configured, defining the contents of any OA unit reports.
+	 *
+	 * This property is available in perf revision 1.
 	 */
 	DRM_I915_PERF_PROP_OA_METRICS_SET,
 
 	/**
 	 * The value specifies the size and layout of OA unit reports.
+	 *
+	 * This property is available in perf revision 1.
 	 */
 	DRM_I915_PERF_PROP_OA_FORMAT,
 
@@ -1870,6 +1885,8 @@ enum drm_i915_perf_property_id {
 	 * from this exponent as follows:
 	 *
 	 *   80ns * 2^(period_exponent + 1)
+	 *
+	 * This property is available in perf revision 1.
 	 */
 	DRM_I915_PERF_PROP_OA_EXPONENT,
 
@@ -1901,6 +1918,8 @@ struct drm_i915_perf_open_param {
  * to close and re-open a stream with the same configuration.
  *
  * It's undefined whether any pending data for the stream will be lost.
+ *
+ * This ioctl is available in perf revision 1.
  */
 #define I915_PERF_IOCTL_ENABLE	_IO('i', 0x0)
 
@@ -1908,6 +1927,8 @@ struct drm_i915_perf_open_param {
  * Disable data capture for a stream.
  *
  * It is an error to try and read a stream that is disabled.
+ *
+ * This ioctl is available in perf revision 1.
  */
 #define I915_PERF_IOCTL_DISABLE	_IO('i', 0x1)
 
-- 
2.23.0

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[CI 2/4] drm/i915: add support for perf configuration queries

[Chris Wilson]

From: Lionel Landwerlin <lionel.g.landwerlin@intel.com>

Listing configurations at the moment is supported only through sysfs.
This might cause issues for applications wanting to list
configurations from a container where sysfs isn't available.

This change adds a way to query the number of configurations and their
content through the i915 query uAPI.

v2: Fix sparse warnings (Lionel)
    Add support to query configuration using uuid (Lionel)

v3: Fix some inconsistency in uapi header (Lionel)
    Fix unlocking when not locked issue (Lionel)
    Add debug messages (Lionel)

v4: Fix missing unlock (Dan)

v5: Drop lock when copying config content to userspace (Chris)

v6: Drop lock when copying config list to userspace (Chris)
    Fix deadlock when calling i915_perf_get_oa_config() under
    perf.metrics_lock (Lionel)
    Add i915_oa_config_get() (Chris)

Link: https://gitlab.freedesktop.org/mesa/mesa/merge_requests/932
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_perf.c  |   3 +-
 drivers/gpu/drm/i915/i915_query.c | 296 ++++++++++++++++++++++++++++++
 include/uapi/drm/i915_drm.h       |  62 ++++++-
 3 files changed, 358 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 220e3384af30..109782ea30ad 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -3806,8 +3806,7 @@ int i915_perf_remove_config_ioctl(struct drm_device *dev, void *data,
 
 	GEM_BUG_ON(*arg != oa_config->id);
 
-	sysfs_remove_group(perf->metrics_kobj,
-			   &oa_config->sysfs_metric);
+	sysfs_remove_group(perf->metrics_kobj, &oa_config->sysfs_metric);
 
 	idr_remove(&perf->metrics_idr, *arg);
 
diff --git a/drivers/gpu/drm/i915/i915_query.c b/drivers/gpu/drm/i915/i915_query.c
index abac5042da2b..c27cfef9281c 100644
--- a/drivers/gpu/drm/i915/i915_query.c
+++ b/drivers/gpu/drm/i915/i915_query.c
@@ -7,6 +7,7 @@
 #include <linux/nospec.h>
 
 #include "i915_drv.h"
+#include "i915_perf.h"
 #include "i915_query.h"
 #include <uapi/drm/i915_drm.h>
 
@@ -140,10 +141,305 @@ query_engine_info(struct drm_i915_private *i915,
 	return len;
 }
 
+static int can_copy_perf_config_registers_or_number(u32 user_n_regs,
+						    u64 user_regs_ptr,
+						    u32 kernel_n_regs)
+{
+	/*
+	 * We'll just put the number of registers, and won't copy the
+	 * register.
+	 */
+	if (user_n_regs == 0)
+		return 0;
+
+	if (user_n_regs < kernel_n_regs)
+		return -EINVAL;
+
+	if (!access_ok(u64_to_user_ptr(user_regs_ptr),
+		       2 * sizeof(u32) * kernel_n_regs))
+		return -EFAULT;
+
+	return 0;
+}
+
+static int copy_perf_config_registers_or_number(const struct i915_oa_reg *kernel_regs,
+						u32 kernel_n_regs,
+						u64 user_regs_ptr,
+						u32 *user_n_regs)
+{
+	u32 r;
+
+	if (*user_n_regs == 0) {
+		*user_n_regs = kernel_n_regs;
+		return 0;
+	}
+
+	*user_n_regs = kernel_n_regs;
+
+	for (r = 0; r < kernel_n_regs; r++) {
+		u32 __user *user_reg_ptr =
+			u64_to_user_ptr(user_regs_ptr + sizeof(u32) * r * 2);
+		u32 __user *user_val_ptr =
+			u64_to_user_ptr(user_regs_ptr + sizeof(u32) * r * 2 +
+					sizeof(u32));
+		int ret;
+
+		ret = __put_user(i915_mmio_reg_offset(kernel_regs[r].addr),
+				 user_reg_ptr);
+		if (ret)
+			return -EFAULT;
+
+		ret = __put_user(kernel_regs[r].value, user_val_ptr);
+		if (ret)
+			return -EFAULT;
+	}
+
+	return 0;
+}
+
+static int query_perf_config_data(struct drm_i915_private *i915,
+				  struct drm_i915_query_item *query_item,
+				  bool use_uuid)
+{
+	struct drm_i915_query_perf_config __user *user_query_config_ptr =
+		u64_to_user_ptr(query_item->data_ptr);
+	struct drm_i915_perf_oa_config __user *user_config_ptr =
+		u64_to_user_ptr(query_item->data_ptr +
+				sizeof(struct drm_i915_query_perf_config));
+	struct drm_i915_perf_oa_config user_config;
+	struct i915_perf *perf = &i915->perf;
+	struct i915_oa_config *oa_config;
+	char uuid[UUID_STRING_LEN + 1];
+	u64 config_id;
+	u32 flags, total_size;
+	int ret;
+
+	if (!perf->i915)
+		return -ENODEV;
+
+	total_size =
+		sizeof(struct drm_i915_query_perf_config) +
+		sizeof(struct drm_i915_perf_oa_config);
+
+	if (query_item->length == 0)
+		return total_size;
+
+	if (query_item->length < total_size) {
+		DRM_DEBUG("Invalid query config data item size=%u expected=%u\n",
+			  query_item->length, total_size);
+		return -EINVAL;
+	}
+
+	if (!access_ok(user_query_config_ptr, total_size))
+		return -EFAULT;
+
+	if (__get_user(flags, &user_query_config_ptr->flags))
+		return -EFAULT;
+
+	if (flags != 0)
+		return -EINVAL;
+
+	if (use_uuid) {
+		struct i915_oa_config *tmp;
+		int id;
+
+		BUILD_BUG_ON(sizeof(user_query_config_ptr->uuid) >= sizeof(uuid));
+
+		memset(&uuid, 0, sizeof(uuid));
+		if (__copy_from_user(uuid, user_query_config_ptr->uuid,
+				     sizeof(user_query_config_ptr->uuid)))
+			return -EFAULT;
+
+		oa_config = NULL;
+		rcu_read_lock();
+		idr_for_each_entry(&perf->metrics_idr, tmp, id) {
+			if (!strcmp(tmp->uuid, uuid)) {
+				oa_config = i915_oa_config_get(tmp);
+				break;
+			}
+		}
+		rcu_read_unlock();
+	} else {
+		if (__get_user(config_id, &user_query_config_ptr->config))
+			return -EFAULT;
+
+		oa_config = i915_perf_get_oa_config(perf, config_id);
+	}
+	if (!oa_config)
+		return -ENOENT;
+
+	if (__copy_from_user(&user_config, user_config_ptr,
+			     sizeof(user_config))) {
+		ret = -EFAULT;
+		goto out;
+	}
+
+	ret = can_copy_perf_config_registers_or_number(user_config.n_boolean_regs,
+						       user_config.boolean_regs_ptr,
+						       oa_config->b_counter_regs_len);
+	if (ret)
+		goto out;
+
+	ret = can_copy_perf_config_registers_or_number(user_config.n_flex_regs,
+						       user_config.flex_regs_ptr,
+						       oa_config->flex_regs_len);
+	if (ret)
+		goto out;
+
+	ret = can_copy_perf_config_registers_or_number(user_config.n_mux_regs,
+						       user_config.mux_regs_ptr,
+						       oa_config->mux_regs_len);
+	if (ret)
+		goto out;
+
+	ret = copy_perf_config_registers_or_number(oa_config->b_counter_regs,
+						   oa_config->b_counter_regs_len,
+						   user_config.boolean_regs_ptr,
+						   &user_config.n_boolean_regs);
+	if (ret)
+		goto out;
+
+	ret = copy_perf_config_registers_or_number(oa_config->flex_regs,
+						   oa_config->flex_regs_len,
+						   user_config.flex_regs_ptr,
+						   &user_config.n_flex_regs);
+	if (ret)
+		goto out;
+
+	ret = copy_perf_config_registers_or_number(oa_config->mux_regs,
+						   oa_config->mux_regs_len,
+						   user_config.mux_regs_ptr,
+						   &user_config.n_mux_regs);
+	if (ret)
+		goto out;
+
+	memcpy(user_config.uuid, oa_config->uuid, sizeof(user_config.uuid));
+
+	if (__copy_to_user(user_config_ptr, &user_config,
+			   sizeof(user_config))) {
+		ret = -EFAULT;
+		goto out;
+	}
+
+	ret = total_size;
+
+out:
+	i915_oa_config_put(oa_config);
+	return ret;
+}
+
+static size_t sizeof_perf_config_list(size_t count)
+{
+	return sizeof(struct drm_i915_query_perf_config) + sizeof(u64) * count;
+}
+
+static size_t sizeof_perf_metrics(struct i915_perf *perf)
+{
+	struct i915_oa_config *tmp;
+	size_t i;
+	int id;
+
+	i = 1;
+	rcu_read_lock();
+	idr_for_each_entry(&perf->metrics_idr, tmp, id)
+		i++;
+	rcu_read_unlock();
+
+	return sizeof_perf_config_list(i);
+}
+
+static int query_perf_config_list(struct drm_i915_private *i915,
+				  struct drm_i915_query_item *query_item)
+{
+	struct drm_i915_query_perf_config __user *user_query_config_ptr =
+		u64_to_user_ptr(query_item->data_ptr);
+	struct i915_perf *perf = &i915->perf;
+	u64 *oa_config_ids = NULL;
+	int alloc, n_configs;
+	u32 flags;
+	int ret;
+
+	if (!perf->i915)
+		return -ENODEV;
+
+	if (query_item->length == 0)
+		return sizeof_perf_metrics(perf);
+
+	if (get_user(flags, &user_query_config_ptr->flags))
+		return -EFAULT;
+
+	if (flags != 0)
+		return -EINVAL;
+
+	n_configs = 1;
+	do {
+		struct i915_oa_config *tmp;
+		u64 *ids;
+		int id;
+
+		ids = krealloc(oa_config_ids,
+			       n_configs * sizeof(*oa_config_ids),
+			       GFP_KERNEL);
+		if (!ids)
+			return -ENOMEM;
+
+		alloc = fetch_and_zero(&n_configs);
+
+		ids[n_configs++] = 1ull; /* reserved for test_config */
+		rcu_read_lock();
+		idr_for_each_entry(&perf->metrics_idr, tmp, id) {
+			if (n_configs < alloc)
+				ids[n_configs] = id;
+			n_configs++;
+		}
+		rcu_read_unlock();
+
+		oa_config_ids = ids;
+	} while (n_configs > alloc);
+
+	if (query_item->length < sizeof_perf_config_list(n_configs)) {
+		DRM_DEBUG("Invalid query config list item size=%u expected=%zu\n",
+			  query_item->length,
+			  sizeof_perf_config_list(n_configs));
+		kfree(oa_config_ids);
+		return -EINVAL;
+	}
+
+	if (put_user(n_configs, &user_query_config_ptr->config)) {
+		kfree(oa_config_ids);
+		return -EFAULT;
+	}
+
+	ret = copy_to_user(user_query_config_ptr + 1,
+			   oa_config_ids,
+			   n_configs * sizeof(*oa_config_ids));
+	kfree(oa_config_ids);
+	if (ret)
+		return -EFAULT;
+
+	return sizeof_perf_config_list(n_configs);
+}
+
+static int query_perf_config(struct drm_i915_private *i915,
+			     struct drm_i915_query_item *query_item)
+{
+	switch (query_item->flags) {
+	case DRM_I915_QUERY_PERF_CONFIG_LIST:
+		return query_perf_config_list(i915, query_item);
+	case DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_UUID:
+		return query_perf_config_data(i915, query_item, true);
+	case DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_ID:
+		return query_perf_config_data(i915, query_item, false);
+	default:
+		return -EINVAL;
+	}
+}
+
 static int (* const i915_query_funcs[])(struct drm_i915_private *dev_priv,
 					struct drm_i915_query_item *query_item) = {
 	query_topology_info,
 	query_engine_info,
+	query_perf_config,
 };
 
 int i915_query_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index c50c712b3771..0c7b2815fbf1 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -2005,6 +2005,7 @@ struct drm_i915_query_item {
 	__u64 query_id;
 #define DRM_I915_QUERY_TOPOLOGY_INFO    1
 #define DRM_I915_QUERY_ENGINE_INFO	2
+#define DRM_I915_QUERY_PERF_CONFIG      3
 /* Must be kept compact -- no holes and well documented */
 
 	/*
@@ -2016,9 +2017,18 @@ struct drm_i915_query_item {
 	__s32 length;
 
 	/*
-	 * Unused for now. Must be cleared to zero.
+	 * When query_id == DRM_I915_QUERY_TOPOLOGY_INFO, must be 0.
+	 *
+	 * When query_id == DRM_I915_QUERY_PERF_CONFIG, must be one of the
+	 * following :
+	 *         - DRM_I915_QUERY_PERF_CONFIG_LIST
+	 *         - DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_UUID
+	 *         - DRM_I915_QUERY_PERF_CONFIG_FOR_UUID
 	 */
 	__u32 flags;
+#define DRM_I915_QUERY_PERF_CONFIG_LIST          1
+#define DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_UUID 2
+#define DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_ID   3
 
 	/*
 	 * Data will be written at the location pointed by data_ptr when the
@@ -2146,6 +2156,56 @@ struct drm_i915_query_engine_info {
 	struct drm_i915_engine_info engines[];
 };
 
+/*
+ * Data written by the kernel with query DRM_I915_QUERY_PERF_CONFIG.
+ */
+struct drm_i915_query_perf_config {
+	union {
+		/*
+		 * When query_item.flags == DRM_I915_QUERY_PERF_CONFIG_LIST, i915 sets
+		 * this fields to the number of configurations available.
+		 */
+		__u64 n_configs;
+
+		/*
+		 * When query_id == DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_ID,
+		 * i915 will use the value in this field as configuration
+		 * identifier to decide what data to write into config_ptr.
+		 */
+		__u64 config;
+
+		/*
+		 * When query_id == DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_UUID,
+		 * i915 will use the value in this field as configuration
+		 * identifier to decide what data to write into config_ptr.
+		 *
+		 * String formatted like "%08x-%04x-%04x-%04x-%012x"
+		 */
+		char uuid[36];
+	};
+
+	/*
+	 * Unused for now. Must be cleared to zero.
+	 */
+	__u32 flags;
+
+	/*
+	 * When query_item.flags == DRM_I915_QUERY_PERF_CONFIG_LIST, i915 will
+	 * write an array of __u64 of configuration identifiers.
+	 *
+	 * When query_item.flags == DRM_I915_QUERY_PERF_CONFIG_DATA, i915 will
+	 * write a struct drm_i915_perf_oa_config. If the following fields of
+	 * drm_i915_perf_oa_config are set not set to 0, i915 will write into
+	 * the associated pointers the values of submitted when the
+	 * configuration was created :
+	 *
+	 *         - n_mux_regs
+	 *         - n_boolean_regs
+	 *         - n_flex_regs
+	 */
+	__u8 data[];
+};
+
 #if defined(__cplusplus)
 }
 #endif
-- 
2.23.0

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[CI 3/4] drm/i915/perf: Allow dynamic reconfiguration of the OA stream

[Chris Wilson]

Introduce a new perf_ioctl command to change the OA configuration of the
active stream. This allows the OA stream to be reconfigured between
batch buffers, giving greater flexibility in sampling. We inject a
request into the OA context to reconfigure the stream asynchronously on
the GPU in between and ordered with execbuffer calls.

Original patch for dynamic reconfiguration by Lionel Landwerlin.

Link: https://gitlab.freedesktop.org/mesa/mesa/merge_requests/932
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
---
 drivers/gpu/drm/i915/i915_perf.c | 46 +++++++++++++++++++++++++++++++-
 include/uapi/drm/i915_drm.h      | 13 +++++++++
 2 files changed, 58 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 109782ea30ad..372c91f6a28e 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -2862,6 +2862,40 @@ static void i915_perf_disable_locked(struct i915_perf_stream *stream)
 		stream->ops->disable(stream);
 }
 
+static long i915_perf_config_locked(struct i915_perf_stream *stream,
+				    unsigned long metrics_set)
+{
+	struct i915_oa_config *config;
+	long ret = stream->oa_config->id;
+
+	config = i915_perf_get_oa_config(stream->perf, metrics_set);
+	if (!config)
+		return -EINVAL;
+
+	if (config != stream->oa_config) {
+		int err;
+
+		/*
+		 * If OA is bound to a specific context, emit the
+		 * reconfiguration inline from that context. The update
+		 * will then be ordered with respect to submission on that
+		 * context.
+		 *
+		 * When set globally, we use a low priority kernel context,
+		 * so it will effectively take effect when idle.
+		 */
+		err = emit_oa_config(stream, oa_context(stream));
+		if (err == 0)
+			config = xchg(&stream->oa_config, config);
+		else
+			ret = err;
+	}
+
+	i915_oa_config_put(config);
+
+	return ret;
+}
+
 /**
  * i915_perf_ioctl - support ioctl() usage with i915 perf stream FDs
  * @stream: An i915 perf stream
@@ -2885,6 +2919,8 @@ static long i915_perf_ioctl_locked(struct i915_perf_stream *stream,
 	case I915_PERF_IOCTL_DISABLE:
 		i915_perf_disable_locked(stream);
 		return 0;
+	case I915_PERF_IOCTL_CONFIG:
+		return i915_perf_config_locked(stream, arg);
 	}
 
 	return -EINVAL;
@@ -4023,7 +4059,15 @@ void i915_perf_fini(struct drm_i915_private *i915)
  */
 int i915_perf_ioctl_version(void)
 {
-	return 1;
+	/*
+	 * 1: Initial version
+	 *   I915_PERF_IOCTL_ENABLE
+	 *   I915_PERF_IOCTL_DISABLE
+	 *
+	 * 2: Added runtime modification of OA config.
+	 *   I915_PERF_IOCTL_CONFIG
+	 */
+	return 2;
 }
 
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index 0c7b2815fbf1..b008ce8b4e6f 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -1932,6 +1932,19 @@ struct drm_i915_perf_open_param {
  */
 #define I915_PERF_IOCTL_DISABLE	_IO('i', 0x1)
 
+/**
+ * Change metrics_set captured by a stream.
+ *
+ * If the stream is bound to a specific context, the configuration change
+ * will performed inline with that context such that it takes effect before
+ * the next execbuf submission.
+ *
+ * Returns the previously bound metrics set id, or a negative error code.
+ *
+ * This ioctl is available in perf revision 2.
+ */
+#define I915_PERF_IOCTL_CONFIG	_IO('i', 0x2)
+
 /**
  * Common to all i915 perf records
  */
-- 
2.23.0

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[CI 4/4] drm/i915/perf: allow holding preemption on filtered ctx

[Chris Wilson]

From: Lionel Landwerlin <lionel.g.landwerlin@intel.com>

We would like to make use of perf in Vulkan. The Vulkan API is much
lower level than OpenGL, with applications directly exposed to the
concept of command buffers (pretty much equivalent to our batch
buffers). In Vulkan, queries are always limited in scope to a command
buffer. In OpenGL, the lack of command buffer concept meant that
queries' duration could span multiple command buffers.

With that restriction gone in Vulkan, we would like to simplify
measuring performance just by measuring the deltas between the counter
snapshots written by 2 MI_RECORD_PERF_COUNT commands, rather than the
more complex scheme we currently have in the GL driver, using 2
MI_RECORD_PERF_COUNT commands and doing some post processing on the
stream of OA reports, coming from the global OA buffer, to remove any
unrelated deltas in between the 2 MI_RECORD_PERF_COUNT.

Disabling preemption only apply to a single context with which want to
query performance counters for and is considered a privileged
operation, by default protected by CAP_SYS_ADMIN. It is possible to
enable it for a normal user by disabling the paranoid stream setting.

v2: Store preemption setting in intel_context (Chris)

v3: Use priorities to avoid preemption rather than the HW mechanism

v4: Just modify the port priority reporting function

v5: Add nopreempt flag on gem context and always flag requests
    appropriately, regarless of OA reconfiguration.

Link: https://gitlab.freedesktop.org/mesa/mesa/merge_requests/932
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/gem/i915_gem_context.h   | 18 ++++++++++
 .../gpu/drm/i915/gem/i915_gem_context_types.h |  1 +
 .../gpu/drm/i915/gem/i915_gem_execbuffer.c    |  3 ++
 drivers/gpu/drm/i915/i915_perf.c              | 34 +++++++++++++++++--
 drivers/gpu/drm/i915/i915_perf_types.h        |  8 +++++
 include/uapi/drm/i915_drm.h                   | 11 ++++++
 6 files changed, 72 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.h b/drivers/gpu/drm/i915/gem/i915_gem_context.h
index 9234586830d1..cfe80590f0ed 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.h
@@ -114,6 +114,24 @@ i915_gem_context_clear_user_engines(struct i915_gem_context *ctx)
 	clear_bit(CONTEXT_USER_ENGINES, &ctx->flags);
 }
 
+static inline bool
+i915_gem_context_nopreempt(const struct i915_gem_context *ctx)
+{
+	return test_bit(CONTEXT_NOPREEMPT, &ctx->flags);
+}
+
+static inline void
+i915_gem_context_set_nopreempt(struct i915_gem_context *ctx)
+{
+	set_bit(CONTEXT_NOPREEMPT, &ctx->flags);
+}
+
+static inline void
+i915_gem_context_clear_nopreempt(struct i915_gem_context *ctx)
+{
+	clear_bit(CONTEXT_NOPREEMPT, &ctx->flags);
+}
+
 static inline bool i915_gem_context_is_kernel(struct i915_gem_context *ctx)
 {
 	return !ctx->file_priv;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
index ab8e1367dfc8..fe97b8ba4fda 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
@@ -146,6 +146,7 @@ struct i915_gem_context {
 #define CONTEXT_CLOSED			1
 #define CONTEXT_FORCE_SINGLE_SUBMISSION	2
 #define CONTEXT_USER_ENGINES		3
+#define CONTEXT_NOPREEMPT		4
 
 	struct mutex mutex;
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index 98816c35ffc3..e96901888323 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -2077,6 +2077,9 @@ static int eb_submit(struct i915_execbuffer *eb)
 	if (err)
 		return err;
 
+	if (i915_gem_context_nopreempt(eb->gem_context))
+		eb->request->flags |= I915_REQUEST_NOPREEMPT;
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 372c91f6a28e..54ec1c4190ac 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -344,6 +344,8 @@ static const struct i915_oa_format gen8_plus_oa_formats[I915_OA_FORMAT_MAX] = {
  * struct perf_open_properties - for validated properties given to open a stream
  * @sample_flags: `DRM_I915_PERF_PROP_SAMPLE_*` properties are tracked as flags
  * @single_context: Whether a single or all gpu contexts should be monitored
+ * @hold_preemption: Whether the preemption is disabled for the filtered
+ *                   context
  * @ctx_handle: A gem ctx handle for use with @single_context
  * @metrics_set: An ID for an OA unit metric set advertised via sysfs
  * @oa_format: An OA unit HW report format
@@ -359,6 +361,7 @@ struct perf_open_properties {
 	u32 sample_flags;
 
 	u64 single_context:1;
+	u64 hold_preemption:1;
 	u64 ctx_handle;
 
 	/* OA sampling state */
@@ -2514,6 +2517,8 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 	if (WARN_ON(stream->oa_buffer.format_size == 0))
 		return -EINVAL;
 
+	stream->hold_preemption = props->hold_preemption;
+
 	stream->oa_buffer.format =
 		perf->oa_formats[props->oa_format].format;
 
@@ -2834,6 +2839,9 @@ static void i915_perf_enable_locked(struct i915_perf_stream *stream)
 
 	if (stream->ops->enable)
 		stream->ops->enable(stream);
+
+	if (stream->hold_preemption)
+		i915_gem_context_set_nopreempt(stream->ctx);
 }
 
 /**
@@ -2858,6 +2866,9 @@ static void i915_perf_disable_locked(struct i915_perf_stream *stream)
 	/* Allow stream->ops->disable() to refer to this */
 	stream->enabled = false;
 
+	if (stream->hold_preemption)
+		i915_gem_context_clear_nopreempt(stream->ctx);
+
 	if (stream->ops->disable)
 		stream->ops->disable(stream);
 }
@@ -3067,6 +3078,15 @@ i915_perf_open_ioctl_locked(struct i915_perf *perf,
 		}
 	}
 
+	if (props->hold_preemption) {
+		if (!props->single_context) {
+			DRM_DEBUG("preemption disable with no context\n");
+			ret = -EINVAL;
+			goto err;
+		}
+		privileged_op = true;
+	}
+
 	/*
 	 * On Haswell the OA unit supports clock gating off for a specific
 	 * context and in this mode there's no visibility of metrics for the
@@ -3081,7 +3101,7 @@ i915_perf_open_ioctl_locked(struct i915_perf *perf,
 	 * MI_REPORT_PERF_COUNT commands and so consider it a privileged op to
 	 * enable the OA unit by default.
 	 */
-	if (IS_HASWELL(perf->i915) && specific_ctx)
+	if (IS_HASWELL(perf->i915) && specific_ctx && !props->hold_preemption)
 		privileged_op = false;
 
 	/* Similar to perf's kernel.perf_paranoid_cpu sysctl option
@@ -3091,7 +3111,7 @@ i915_perf_open_ioctl_locked(struct i915_perf *perf,
 	 */
 	if (privileged_op &&
 	    i915_perf_stream_paranoid && !capable(CAP_SYS_ADMIN)) {
-		DRM_DEBUG("Insufficient privileges to open system-wide i915 perf stream\n");
+		DRM_DEBUG("Insufficient privileges to open i915 perf stream\n");
 		ret = -EACCES;
 		goto err_ctx;
 	}
@@ -3293,6 +3313,9 @@ static int read_properties_unlocked(struct i915_perf *perf,
 			props->oa_periodic = true;
 			props->oa_period_exponent = value;
 			break;
+		case DRM_I915_PERF_PROP_HOLD_PREEMPTION:
+			props->hold_preemption = !!value;
+			break;
 		case DRM_I915_PERF_PROP_MAX:
 			MISSING_CASE(id);
 			return -EINVAL;
@@ -4066,8 +4089,13 @@ int i915_perf_ioctl_version(void)
 	 *
 	 * 2: Added runtime modification of OA config.
 	 *   I915_PERF_IOCTL_CONFIG
+	 *
+	 * 3: Add DRM_I915_PERF_PROP_HOLD_PREEMPTION parameter to hold
+	 *    preemption on a particular context so that performance data is
+	 *    accessible from a delta of MI_RPC reports without looking at the
+	 *    OA buffer.
 	 */
-	return 2;
+	return 3;
 }
 
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
diff --git a/drivers/gpu/drm/i915/i915_perf_types.h b/drivers/gpu/drm/i915/i915_perf_types.h
index d35a3c1946c3..a1f733fc905a 100644
--- a/drivers/gpu/drm/i915/i915_perf_types.h
+++ b/drivers/gpu/drm/i915/i915_perf_types.h
@@ -170,6 +170,14 @@ struct i915_perf_stream {
 	 */
 	bool enabled;
 
+	/**
+	 * @hold_preemption: Whether preemption is put on hold for command
+	 * submissions done on the @ctx. This is useful for some drivers that
+	 * cannot easily post process the OA buffer context to subtract delta
+	 * of performance counters not associated with @ctx.
+	 */
+	bool hold_preemption;
+
 	/**
 	 * @ops: The callbacks providing the implementation of this specific
 	 * type of configured stream.
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index b008ce8b4e6f..63d40cba97e0 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -1890,6 +1890,17 @@ enum drm_i915_perf_property_id {
 	 */
 	DRM_I915_PERF_PROP_OA_EXPONENT,
 
+	/**
+	 * Specifying this property is only valid when specify a context to
+	 * filter with DRM_I915_PERF_PROP_CTX_HANDLE. Specifying this property
+	 * will hold preemption of the particular context we want to gather
+	 * performance data about. The execbuf2 submissions must include a
+	 * drm_i915_gem_execbuffer_ext_perf parameter for this to apply.
+	 *
+	 * This property is available in perf revision 3.
+	 */
+	DRM_I915_PERF_PROP_HOLD_PREEMPTION,
+
 	DRM_I915_PERF_PROP_MAX /* non-ABI */
 };
 
-- 
2.23.0

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

✗ Fi.CI.BUILD: failure for series starting with [CI,1/4] drm/i915/perf: introduce a versioning of the i915-perf uapi

[Patchwork]

== Series Details ==

Series: series starting with [CI,1/4] drm/i915/perf: introduce a versioning of the i915-perf uapi
URL   : https://patchwork.freedesktop.org/series/67990/
State : failure

== Summary ==

Applying: drm/i915/perf: introduce a versioning of the i915-perf uapi
Using index info to reconstruct a base tree...
M	drivers/gpu/drm/i915/i915_getparam.c
M	drivers/gpu/drm/i915/i915_perf.c
M	drivers/gpu/drm/i915/i915_perf.h
M	include/uapi/drm/i915_drm.h
Falling back to patching base and 3-way merge...
Auto-merging include/uapi/drm/i915_drm.h
Auto-merging drivers/gpu/drm/i915/i915_perf.c
CONFLICT (content): Merge conflict in drivers/gpu/drm/i915/i915_perf.c
error: Failed to merge in the changes.
hint: Use 'git am --show-current-patch' to see the failed patch
Patch failed at 0001 drm/i915/perf: introduce a versioning of the i915-perf uapi
When you have resolved this problem, run "git am --continue".
If you prefer to skip this patch, run "git am --skip" instead.
To restore the original branch and stop patching, run "git am --abort".

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx