drm/xe/uapi: Add a device query to get EU stall sampling information

User space can get the EU stall data record size, EU stall capabilities,
EU stall sampling rates, and per XeCore buffer size with query IOCTL
DRM_IOCTL_XE_DEVICE_QUERY with .query set to DRM_XE_DEVICE_QUERY_EU_STALL.
A struct drm_xe_query_eu_stall will be returned to the user space along
with an array of supported sampling rates sorted in the fastest sampling
rate first order. sampling_rates in struct drm_xe_query_eu_stall will
point to the array of sampling rates.

Any capabilities in EU stall sampling as of this patch are considered
as base capabilities. New capability bits will be added for any new
functionality added later.

v12: Rename has_eu_stall_sampling_support() to
     xe_eu_stall_supported_on_platform() and move it to header file.
v11: Check if EU stall sampling is supported on the platform.
v10: Change comments and variable names as per feedback
v9: Move reserved fields above num_sampling_rates in
    struct drm_xe_query_eu_stall.
v7: Change sampling_rates from a pointer to flexible array.
v6: Include EU stall sampling rates information and
    per XeCore buffer size in the query information.

Reviewed-by: Ashutosh Dixit <[email protected]>
Signed-off-by: Harish Chegondi <[email protected]>
Signed-off-by: Ashutosh Dixit <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/67ba42796a5a99d648239c315694cd222812a49b.1740533885.git.harish.chegondi@intel.com

Author: harishchegondi

drivers/gpu/drm/xe/xe_eu_stall.c

@@ -120,7 +120,46 @@ struct xe_eu_stall_data_xe2 {
 	__u64 unused[6];
 } __packed;
 
-static size_t xe_eu_stall_data_record_size(struct xe_device *xe)
+const u64 eu_stall_sampling_rates[] = {251, 251 * 2, 251 * 3, 251 * 4, 251 * 5, 251 * 6, 251 * 7};
+
+/**
+ * xe_eu_stall_get_sampling_rates - get EU stall sampling rates information.
+ *
+ * @num_rates: Pointer to a u32 to return the number of sampling rates.
+ * @rates: double u64 pointer to point to an array of sampling rates.
+ *
+ * Stores the number of sampling rates and pointer to the array of
+ * sampling rates in the input pointers.
+ *
+ * Returns: Size of the EU stall sampling rates array.
+ */
+size_t xe_eu_stall_get_sampling_rates(u32 *num_rates, const u64 **rates)
+{
+	*num_rates = ARRAY_SIZE(eu_stall_sampling_rates);
+	*rates = eu_stall_sampling_rates;
+
+	return sizeof(eu_stall_sampling_rates);
+}
+
+/**
+ * xe_eu_stall_get_per_xecore_buf_size - get per XeCore buffer size.
+ *
+ * Returns: The per XeCore buffer size used to allocate the per GT
+ *	    EU stall data buffer.
+ */
+size_t xe_eu_stall_get_per_xecore_buf_size(void)
+{
+	return per_xecore_buf_size;
+}
+
+/**
+ * xe_eu_stall_data_record_size - get EU stall data record size.
+ *
+ * @xe: Pointer to a Xe device.
+ *
+ * Returns: EU stall data record size.
+ */
+size_t xe_eu_stall_data_record_size(struct xe_device *xe)
 {
 	size_t record_size = 0;
 
@@ -812,11 +851,6 @@ static const struct file_operations fops_eu_stall = {
 	.compat_ioctl   = xe_eu_stall_stream_ioctl,
 };
 
-static inline bool has_eu_stall_sampling_support(struct xe_device *xe)
-{
-	return xe->info.platform == XE_PVC || GRAPHICS_VER(xe) >= 20;
-}
-
 static int xe_eu_stall_stream_open_locked(struct drm_device *dev,
 					  struct eu_stall_open_properties *props,
 					  struct drm_file *file)
@@ -885,7 +919,7 @@ int xe_eu_stall_stream_open(struct drm_device *dev, u64 data, struct drm_file *f
 	struct eu_stall_open_properties props = {};
 	int ret;
 
-	if (!has_eu_stall_sampling_support(xe)) {
+	if (!xe_eu_stall_supported_on_platform(xe)) {
 		drm_dbg(&xe->drm, "EU stall monitoring is not supported on this platform\n");
 		return -ENODEV;
 	}

drivers/gpu/drm/xe/xe_eu_stall.h

@@ -8,8 +8,17 @@
 
 #include "xe_gt_types.h"
 
+size_t xe_eu_stall_get_per_xecore_buf_size(void);
+size_t xe_eu_stall_data_record_size(struct xe_device *xe);
+size_t xe_eu_stall_get_sampling_rates(u32 *num_rates, const u64 **rates);
+
 int xe_eu_stall_init(struct xe_gt *gt);
 int xe_eu_stall_stream_open(struct drm_device *dev,
 			    u64 data,
 			    struct drm_file *file);
+
+static inline bool xe_eu_stall_supported_on_platform(struct xe_device *xe)
+{
+	return xe->info.platform == XE_PVC || GRAPHICS_VER(xe) >= 20;
+}
 #endif

drivers/gpu/drm/xe/xe_query.c

@@ -16,6 +16,7 @@
 #include "regs/xe_gt_regs.h"
 #include "xe_bo.h"
 #include "xe_device.h"
+#include "xe_eu_stall.h"
 #include "xe_exec_queue.h"
 #include "xe_force_wake.h"
 #include "xe_ggtt.h"
@@ -729,6 +730,47 @@ static int query_pxp_status(struct xe_device *xe, struct drm_xe_device_query *qu
 	return 0;
 }
 
+static int query_eu_stall(struct xe_device *xe,
+			  struct drm_xe_device_query *query)
+{
+	void __user *query_ptr = u64_to_user_ptr(query->data);
+	struct drm_xe_query_eu_stall *info;
+	size_t size, array_size;
+	const u64 *rates;
+	u32 num_rates;
+	int ret;
+
+	if (!xe_eu_stall_supported_on_platform(xe)) {
+		drm_dbg(&xe->drm, "EU stall monitoring is not supported on this platform\n");
+		return -ENODEV;
+	}
+
+	array_size = xe_eu_stall_get_sampling_rates(&num_rates, &rates);
+	size = sizeof(struct drm_xe_query_eu_stall) + array_size;
+
+	if (query->size == 0) {
+		query->size = size;
+		return 0;
+	} else if (XE_IOCTL_DBG(xe, query->size != size)) {
+		return -EINVAL;
+	}
+
+	info = kzalloc(size, GFP_KERNEL);
+	if (!info)
+		return -ENOMEM;
+
+	info->num_sampling_rates = num_rates;
+	info->capabilities = DRM_XE_EU_STALL_CAPS_BASE;
+	info->record_size = xe_eu_stall_data_record_size(xe);
+	info->per_xecore_buf_size = xe_eu_stall_get_per_xecore_buf_size();
+	memcpy(info->sampling_rates, rates, array_size);
+
+	ret = copy_to_user(query_ptr, info, size);
+	kfree(info);
+
+	return ret ? -EFAULT : 0;
+}
+
 static int (* const xe_query_funcs[])(struct xe_device *xe,
 				      struct drm_xe_device_query *query) = {
 	query_engines,
@@ -741,6 +783,7 @@ static int (* const xe_query_funcs[])(struct xe_device *xe,
 	query_uc_fw_version,
 	query_oa_units,
 	query_pxp_status,
+	query_eu_stall,
 };
 
 int xe_query_ioctl(struct drm_device *dev, void *data, struct drm_file *file)

include/uapi/drm/xe_drm.h

@@ -735,6 +735,7 @@ struct drm_xe_device_query {
 #define DRM_XE_DEVICE_QUERY_UC_FW_VERSION	7
 #define DRM_XE_DEVICE_QUERY_OA_UNITS		8
 #define DRM_XE_DEVICE_QUERY_PXP_STATUS		9
+#define DRM_XE_DEVICE_QUERY_EU_STALL		10
 	/** @query: The type of data to query */
 	__u32 query;
 
@@ -1873,8 +1874,8 @@ enum drm_xe_eu_stall_property_id {
 	DRM_XE_EU_STALL_PROP_GT_ID = 1,
 
 	/**
-	 * @DRM_XE_EU_STALL_PROP_SAMPLE_RATE: Sampling rate
-	 * in GPU cycles.
+	 * @DRM_XE_EU_STALL_PROP_SAMPLE_RATE: Sampling rate in
+	 * GPU cycles from @sampling_rates in struct @drm_xe_query_eu_stall
 	 */
 	DRM_XE_EU_STALL_PROP_SAMPLE_RATE,
 
@@ -1886,6 +1887,41 @@ enum drm_xe_eu_stall_property_id {
 	DRM_XE_EU_STALL_PROP_WAIT_NUM_REPORTS,
 };
 
+/**
+ * struct drm_xe_query_eu_stall - Information about EU stall sampling.
+ *
+ * If a query is made with a struct @drm_xe_device_query where .query
+ * is equal to @DRM_XE_DEVICE_QUERY_EU_STALL, then the reply uses
+ * struct @drm_xe_query_eu_stall in .data.
+ */
+struct drm_xe_query_eu_stall {
+	/** @extensions: Pointer to the first extension struct, if any */
+	__u64 extensions;
+
+	/** @capabilities: EU stall capabilities bit-mask */
+	__u64 capabilities;
+#define DRM_XE_EU_STALL_CAPS_BASE		(1 << 0)
+
+	/** @record_size: size of each EU stall data record */
+	__u64 record_size;
+
+	/** @per_xecore_buf_size: internal per XeCore buffer size */
+	__u64 per_xecore_buf_size;
+
+	/** @reserved: Reserved */
+	__u64 reserved[5];
+
+	/** @num_sampling_rates: Number of sampling rates in @sampling_rates array */
+	__u64 num_sampling_rates;
+
+	/**
+	 * @sampling_rates: Flexible array of sampling rates
+	 * sorted in the fastest to slowest order.
+	 * Sampling rates are specified in GPU clock cycles.
+	 */
+	__u64 sampling_rates[];
+};
+
 #if defined(__cplusplus)
 }
 #endif