drm/xe/oa/uapi: Define and parse OA sync properties

Now that we have laid the groundwork, introduce OA sync properties in the
uapi and parse the input xe_sync array as is done elsewhere in the
driver. Also add DRM_XE_OA_CAPS_SYNCS bit in OA capabilities for userspace.

v2: Fix and document DRM_XE_SYNC_TYPE_USER_FENCE for OA (Matt B)
    Add DRM_XE_OA_CAPS_SYNCS bit to OA capabilities (Jose)

Acked-by: José Roberto de Souza <jose.souza@intel.com>
Reviewed-by: Jonathan Cavitt <jonathan.cavitt@intel.com>
Signed-off-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20241022200352.1192560-3-ashutosh.dixit@intel.com

diff --git a/drivers/gpu/drm/xe/xe_oa.c b/drivers/gpu/drm/xe/xe_oa.c
index 15d952cf0cbd9038984a737baebbde72c98ec980..3f1de88c5f882c1088db08ccec8262ce3c87b99e 100644 (file)
--- a/drivers/gpu/drm/xe/xe_oa.c
+++ b/drivers/gpu/drm/xe/xe_oa.c
@@ -36,6 +36,7 @@
 #include "xe_pm.h"
 #include "xe_sched_job.h"
 #include "xe_sriov.h"
+#include "xe_sync.h"
 
 #define DEFAULT_POLL_FREQUENCY_HZ 200
 #define DEFAULT_POLL_PERIOD_NS (NSEC_PER_SEC / DEFAULT_POLL_FREQUENCY_HZ)
@@ -70,6 +71,7 @@ struct flex {
 };
 
 struct xe_oa_open_param {
+       struct xe_file *xef;
        u32 oa_unit_id;
        bool sample;
        u32 metric_set;
@@ -81,6 +83,9 @@ struct xe_oa_open_param {
        struct xe_exec_queue *exec_q;
        struct xe_hw_engine *hwe;
        bool no_preempt;
+       struct drm_xe_sync __user *syncs_user;
+       int num_syncs;
+       struct xe_sync_entry *syncs;
 };
 
 struct xe_oa_config_bo {
@@ -1398,6 +1403,9 @@ static int xe_oa_stream_init(struct xe_oa_stream *stream,
        stream->period_exponent = param->period_exponent;
        stream->no_preempt = param->no_preempt;
 
+       stream->num_syncs = param->num_syncs;
+       stream->syncs = param->syncs;
+
        /*
         * For Xe2+, when overrun mode is enabled, there are no partial reports at the end
         * of buffer, making the OA buffer effectively a non-power-of-2 size circular
@@ -1752,6 +1760,20 @@ static int xe_oa_set_no_preempt(struct xe_oa *oa, u64 value,
        return 0;
 }
 
+static int xe_oa_set_prop_num_syncs(struct xe_oa *oa, u64 value,
+                                   struct xe_oa_open_param *param)
+{
+       param->num_syncs = value;
+       return 0;
+}
+
+static int xe_oa_set_prop_syncs_user(struct xe_oa *oa, u64 value,
+                                    struct xe_oa_open_param *param)
+{
+       param->syncs_user = u64_to_user_ptr(value);
+       return 0;
+}
+
 typedef int (*xe_oa_set_property_fn)(struct xe_oa *oa, u64 value,
                                     struct xe_oa_open_param *param);
 static const xe_oa_set_property_fn xe_oa_set_property_funcs[] = {
@@ -1764,6 +1786,8 @@ static const xe_oa_set_property_fn xe_oa_set_property_funcs[] = {
        [DRM_XE_OA_PROPERTY_EXEC_QUEUE_ID] = xe_oa_set_prop_exec_queue_id,
        [DRM_XE_OA_PROPERTY_OA_ENGINE_INSTANCE] = xe_oa_set_prop_engine_instance,
        [DRM_XE_OA_PROPERTY_NO_PREEMPT] = xe_oa_set_no_preempt,
+       [DRM_XE_OA_PROPERTY_NUM_SYNCS] = xe_oa_set_prop_num_syncs,
+       [DRM_XE_OA_PROPERTY_SYNCS] = xe_oa_set_prop_syncs_user,
 };
 
 static int xe_oa_user_ext_set_property(struct xe_oa *oa, u64 extension,
@@ -1823,6 +1847,49 @@ static int xe_oa_user_extensions(struct xe_oa *oa, u64 extension, int ext_number
        return 0;
 }
 
+static int xe_oa_parse_syncs(struct xe_oa *oa, struct xe_oa_open_param *param)
+{
+       int ret, num_syncs, num_ufence = 0;
+
+       if (param->num_syncs && !param->syncs_user) {
+               drm_dbg(&oa->xe->drm, "num_syncs specified without sync array\n");
+               ret = -EINVAL;
+               goto exit;
+       }
+
+       if (param->num_syncs) {
+               param->syncs = kcalloc(param->num_syncs, sizeof(*param->syncs), GFP_KERNEL);
+               if (!param->syncs) {
+                       ret = -ENOMEM;
+                       goto exit;
+               }
+       }
+
+       for (num_syncs = 0; num_syncs < param->num_syncs; num_syncs++) {
+               ret = xe_sync_entry_parse(oa->xe, param->xef, &param->syncs[num_syncs],
+                                         &param->syncs_user[num_syncs], 0);
+               if (ret)
+                       goto err_syncs;
+
+               if (xe_sync_is_ufence(&param->syncs[num_syncs]))
+                       num_ufence++;
+       }
+
+       if (XE_IOCTL_DBG(oa->xe, num_ufence > 1)) {
+               ret = -EINVAL;
+               goto err_syncs;
+       }
+
+       return 0;
+
+err_syncs:
+       while (num_syncs--)
+               xe_sync_entry_cleanup(&param->syncs[num_syncs]);
+       kfree(param->syncs);
+exit:
+       return ret;
+}
+
 /**
  * xe_oa_stream_open_ioctl - Opens an OA stream
  * @dev: @drm_device
@@ -1848,6 +1915,7 @@ int xe_oa_stream_open_ioctl(struct drm_device *dev, u64 data, struct drm_file *f
                return -ENODEV;
        }
 
+       param.xef = xef;
        ret = xe_oa_user_extensions(oa, data, 0, &param);
        if (ret)
                return ret;
@@ -1916,11 +1984,24 @@ int xe_oa_stream_open_ioctl(struct drm_device *dev, u64 data, struct drm_file *f
                drm_dbg(&oa->xe->drm, "Using periodic sampling freq %lld Hz\n", oa_freq_hz);
        }
 
+       ret = xe_oa_parse_syncs(oa, &param);
+       if (ret)
+               goto err_exec_q;
+
        mutex_lock(&param.hwe->gt->oa.gt_lock);
        ret = xe_oa_stream_open_ioctl_locked(oa, &param);
        mutex_unlock(&param.hwe->gt->oa.gt_lock);
+       if (ret < 0)
+               goto err_sync_cleanup;
+
+       return ret;
+
+err_sync_cleanup:
+       while (param.num_syncs--)
+               xe_sync_entry_cleanup(&param.syncs[param.num_syncs]);
+       kfree(param.syncs);
 err_exec_q:
-       if (ret < 0 && param.exec_q)
+       if (param.exec_q)
                xe_exec_queue_put(param.exec_q);
        return ret;
 }

diff --git a/drivers/gpu/drm/xe/xe_oa_types.h b/drivers/gpu/drm/xe/xe_oa_types.h
index 8862eca73fbe3277977f2496a62a006ad837777d..99f4b2d4bdcf6a6d8e2de0cac7cfa62a471c1f89 100644 (file)
--- a/drivers/gpu/drm/xe/xe_oa_types.h
+++ b/drivers/gpu/drm/xe/xe_oa_types.h
@@ -238,5 +238,11 @@ struct xe_oa_stream {
 
        /** @no_preempt: Whether preemption and timeslicing is disabled for stream exec_q */
        u32 no_preempt;
+
+       /** @num_syncs: size of @syncs array */
+       u32 num_syncs;
+
+       /** @syncs: syncs to wait on and to signal */
+       struct xe_sync_entry *syncs;
 };
 #endif

diff --git a/drivers/gpu/drm/xe/xe_query.c b/drivers/gpu/drm/xe/xe_query.c
index dcd1291da057295da5bec1a78e817e4fb04f8911..170ae72d1a7bb7a111c1c869efeec6cfaf38ce3e 100644 (file)
--- a/drivers/gpu/drm/xe/xe_query.c
+++ b/drivers/gpu/drm/xe/xe_query.c
@@ -670,7 +670,7 @@ static int query_oa_units(struct xe_device *xe,
                        du->oa_unit_id = u->oa_unit_id;
                        du->oa_unit_type = u->type;
                        du->oa_timestamp_freq = xe_oa_timestamp_frequency(gt);
-                       du->capabilities = DRM_XE_OA_CAPS_BASE;
+                       du->capabilities = DRM_XE_OA_CAPS_BASE | DRM_XE_OA_CAPS_SYNCS;
 
                        j = 0;
                        for_each_hw_engine(hwe, gt, hwe_id) {

diff --git a/include/uapi/drm/xe_drm.h b/include/uapi/drm/xe_drm.h
index c4182e95a61955a85100a305af55b5a34a9bf4a2..4a8a4a63e99ca8fd84429fcdd292a503cfe9de20 100644 (file)
--- a/include/uapi/drm/xe_drm.h
+++ b/include/uapi/drm/xe_drm.h
@@ -1485,6 +1485,7 @@ struct drm_xe_oa_unit {
        /** @capabilities: OA capabilities bit-mask */
        __u64 capabilities;
 #define DRM_XE_OA_CAPS_BASE            (1 << 0)
+#define DRM_XE_OA_CAPS_SYNCS           (1 << 1)
 
        /** @oa_timestamp_freq: OA timestamp freq */
        __u64 oa_timestamp_freq;
@@ -1634,6 +1635,22 @@ enum drm_xe_oa_property_id {
         * to be disabled for the stream exec queue.
         */
        DRM_XE_OA_PROPERTY_NO_PREEMPT,
+
+       /**
+        * @DRM_XE_OA_PROPERTY_NUM_SYNCS: Number of syncs in the sync array
+        * specified in @DRM_XE_OA_PROPERTY_SYNCS
+        */
+       DRM_XE_OA_PROPERTY_NUM_SYNCS,
+
+       /**
+        * @DRM_XE_OA_PROPERTY_SYNCS: Pointer to struct @drm_xe_sync array
+        * with array size specified via @DRM_XE_OA_PROPERTY_NUM_SYNCS. OA
+        * configuration will wait till input fences signal. Output fences
+        * will signal after the new OA configuration takes effect. For
+        * @DRM_XE_SYNC_TYPE_USER_FENCE, @addr is a user pointer, similar
+        * to the VM bind case.
+        */
+       DRM_XE_OA_PROPERTY_SYNCS,
 };
 
 /**