Merge tag 'drm-xe-fixes-2024-12-23' of https://gitlab.freedesktop.org…

…/drm/xe/kernel into drm-fixes

UAPI Changes:
- Revert some devcoredump file format changes
  breaking a mesa debug tool (John)

Driver Changes:
- Fixes around waits when moving to system (Nirmoy)
- Fix a typo when checking for LMEM provisioning (Michal)
- Fix a fault on fd close after unbind (Lucas)

Signed-off-by: Dave Airlie <[email protected]>

From: Thomas Hellstrom <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/Z2mjt7OTfH76cgua@fedora

drivers/gpu/drm/xe/xe_bo.c

@@ -724,7 +724,7 @@ static int xe_bo_move(struct ttm_buffer_object *ttm_bo, bool evict,
 	    new_mem->mem_type == XE_PL_SYSTEM) {
 		long timeout = dma_resv_wait_timeout(ttm_bo->base.resv,
 						     DMA_RESV_USAGE_BOOKKEEP,
-						     true,
+						     false,
 						     MAX_SCHEDULE_TIMEOUT);
 		if (timeout < 0) {
 			ret = timeout;
@@ -848,8 +848,16 @@ static int xe_bo_move(struct ttm_buffer_object *ttm_bo, bool evict,
 
 out:
 	if ((!ttm_bo->resource || ttm_bo->resource->mem_type == XE_PL_SYSTEM) &&
-	    ttm_bo->ttm)
+	    ttm_bo->ttm) {
+		long timeout = dma_resv_wait_timeout(ttm_bo->base.resv,
+						     DMA_RESV_USAGE_KERNEL,
+						     false,
+						     MAX_SCHEDULE_TIMEOUT);
+		if (timeout < 0)
+			ret = timeout;
+
 		xe_tt_unmap_sg(ttm_bo->ttm);
+	}
 
 	return ret;
 }

drivers/gpu/drm/xe/xe_devcoredump.c

@@ -109,7 +109,11 @@ static ssize_t __xe_devcoredump_read(char *buffer, size_t count,
 	drm_puts(&p, "\n**** GuC CT ****\n");
 	xe_guc_ct_snapshot_print(ss->guc.ct, &p);
 
-	drm_puts(&p, "\n**** Contexts ****\n");
+	/*
+	 * Don't add a new section header here because the mesa debug decoder
+	 * tool expects the context information to be in the 'GuC CT' section.
+	 */
+	/* drm_puts(&p, "\n**** Contexts ****\n"); */
 	xe_guc_exec_queue_snapshot_print(ss->ge, &p);
 
 	drm_puts(&p, "\n**** Job ****\n");
@@ -363,6 +367,15 @@ void xe_print_blob_ascii85(struct drm_printer *p, const char *prefix,
 	char buff[ASCII85_BUFSZ], *line_buff;
 	size_t line_pos = 0;
 
+	/*
+	 * Splitting blobs across multiple lines is not compatible with the mesa
+	 * debug decoder tool. Note that even dropping the explicit '\n' below
+	 * doesn't help because the GuC log is so big some underlying implementation
+	 * still splits the lines at 512K characters. So just bail completely for
+	 * the moment.
+	 */
+	return;
+
 #define DMESG_MAX_LINE_LEN	800
 #define MIN_SPACE		(ASCII85_BUFSZ + 2)		/* 85 + "\n\0" */
 

drivers/gpu/drm/xe/xe_exec_queue.c

@@ -8,6 +8,7 @@
 #include <linux/nospec.h>
 
 #include <drm/drm_device.h>
+#include <drm/drm_drv.h>
 #include <drm/drm_file.h>
 #include <uapi/drm/xe_drm.h>
 
@@ -762,9 +763,11 @@ bool xe_exec_queue_is_idle(struct xe_exec_queue *q)
  */
 void xe_exec_queue_update_run_ticks(struct xe_exec_queue *q)
 {
+	struct xe_device *xe = gt_to_xe(q->gt);
 	struct xe_file *xef;
 	struct xe_lrc *lrc;
 	u32 old_ts, new_ts;
+	int idx;
 
 	/*
 	 * Jobs that are run during driver load may use an exec_queue, but are
@@ -774,6 +777,10 @@ void xe_exec_queue_update_run_ticks(struct xe_exec_queue *q)
 	if (!q->vm || !q->vm->xef)
 		return;
 
+	/* Synchronize with unbind while holding the xe file open */
+	if (!drm_dev_enter(&xe->drm, &idx))
+		return;
+
 	xef = q->vm->xef;
 
 	/*
@@ -787,6 +794,8 @@ void xe_exec_queue_update_run_ticks(struct xe_exec_queue *q)
 	lrc = q->lrc[0];
 	new_ts = xe_lrc_update_timestamp(lrc, &old_ts);
 	xef->run_ticks[q->class] += (new_ts - old_ts) * q->width;
+
+	drm_dev_exit(idx);
 }
 
 /**

drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c

@@ -2046,7 +2046,7 @@ static int pf_validate_vf_config(struct xe_gt *gt, unsigned int vfid)
 	valid_any = valid_any || (valid_ggtt && is_primary);
 
 	if (IS_DGFX(xe)) {
-		bool valid_lmem = pf_get_vf_config_ggtt(primary_gt, vfid);
+		bool valid_lmem = pf_get_vf_config_lmem(primary_gt, vfid);
 
 		valid_any = valid_any || (valid_lmem && is_primary);
 		valid_all = valid_all && valid_lmem;