Merge tag 'drm-xe-fixes-2025-07-11' of https://gitlab.freedesktop.org/drm/xe/kernel into drm-fixes

danvet · danvet · commit 14e85fabee2b · 2025-07-11T11:35:39.000+02:00
Driver Changes: - Clear LMTT page to avoid leaking data from one VF to another - Align PF queue size to power of 2 - Disable Indirect Ring State to avoid intermittent issues on context switch: feature is not currently needed, so can be disabled for now. - Fix compression handling when the BO pages are very fragmented - Restore display pm on error path - Fix runtime pm handling in xe devcoredump - Fix xe_pm_set_vram_threshold() doc - Recommend new minor versions of GuC firmware - Drop some workarounds on VF - Do not use verbose GuC logging by default: it should be only for debugging Signed-off-by: Simona Vetter <simona.vetter@ffwll.ch> From: Lucas De Marchi <lucas.demarchi@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/s6jyd24mimbzb4vxtgc5vupvbyqplfep2c6eupue7znnlbhuxy@lmvzexfzhrnn
diff --git a/drivers/gpu/drm/xe/xe_devcoredump.c b/drivers/gpu/drm/xe/xe_devcoredump.c
@@ -171,14 +171,32 @@ static void xe_devcoredump_snapshot_free(struct xe_devcoredump_snapshot *ss)
 
 #define XE_DEVCOREDUMP_CHUNK_MAX	(SZ_512M + SZ_1G)
 
+/**
+ * xe_devcoredump_read() - Read data from the Xe device coredump snapshot
+ * @buffer: Destination buffer to copy the coredump data into
+ * @offset: Offset in the coredump data to start reading from
+ * @count: Number of bytes to read
+ * @data: Pointer to the xe_devcoredump structure
+ * @datalen: Length of the data (unused)
+ *
+ * Reads a chunk of the coredump snapshot data into the provided buffer.
+ * If the devcoredump is smaller than 1.5 GB (XE_DEVCOREDUMP_CHUNK_MAX),
+ * it is read directly from a pre-written buffer. For larger devcoredumps,
+ * the pre-written buffer must be periodically repopulated from the snapshot
+ * state due to kmalloc size limitations.
+ *
+ * Return: Number of bytes copied on success, or a negative error code on failure.
+ */
 static ssize_t xe_devcoredump_read(char *buffer, loff_t offset,
 				   size_t count, void *data, size_t datalen)
 {
 	struct xe_devcoredump *coredump = data;
 	struct xe_devcoredump_snapshot *ss;
-	ssize_t byte_copied;
+	ssize_t byte_copied = 0;
 	u32 chunk_offset;
 	ssize_t new_chunk_position;
+	bool pm_needed = false;
+	int ret = 0;
 
 	if (!coredump)
 		return -ENODEV;
@@ -188,20 +206,19 @@ static ssize_t xe_devcoredump_read(char *buffer, loff_t offset,
 	/* Ensure delayed work is captured before continuing */
 	flush_work(&ss->work);
 
-	if (ss->read.size > XE_DEVCOREDUMP_CHUNK_MAX)
+	pm_needed = ss->read.size > XE_DEVCOREDUMP_CHUNK_MAX;
+	if (pm_needed)
 		xe_pm_runtime_get(gt_to_xe(ss->gt));
 
 	mutex_lock(&coredump->lock);
 
 	if (!ss->read.buffer) {
-		mutex_unlock(&coredump->lock);
-		return -ENODEV;
+		ret = -ENODEV;
+		goto unlock;
 	}
 
-	if (offset >= ss->read.size) {
-		mutex_unlock(&coredump->lock);
-		return 0;
-	}
+	if (offset >= ss->read.size)
+		goto unlock;
 
 	new_chunk_position = div_u64_rem(offset,
 					 XE_DEVCOREDUMP_CHUNK_MAX,
@@ -221,12 +238,13 @@ static ssize_t xe_devcoredump_read(char *buffer, loff_t offset,
 		ss->read.size - offset;
 	memcpy(buffer, ss->read.buffer + chunk_offset, byte_copied);
 
+unlock:
 	mutex_unlock(&coredump->lock);
 
-	if (ss->read.size > XE_DEVCOREDUMP_CHUNK_MAX)
+	if (pm_needed)
 		xe_pm_runtime_put(gt_to_xe(ss->gt));
 
-	return byte_copied;
+	return byte_copied ? byte_copied : ret;
 }
 
 static void xe_devcoredump_free(void *data)
diff --git a/drivers/gpu/drm/xe/xe_gt_pagefault.c b/drivers/gpu/drm/xe/xe_gt_pagefault.c
@@ -444,6 +444,7 @@ static int xe_alloc_pf_queue(struct xe_gt *gt, struct pf_queue *pf_queue)
 #define PF_MULTIPLIER	8
 	pf_queue->num_dw =
 		(num_eus + XE_NUM_HW_ENGINES) * PF_MSG_LEN_DW * PF_MULTIPLIER;
+	pf_queue->num_dw = roundup_pow_of_two(pf_queue->num_dw);
 #undef PF_MULTIPLIER
 
 	pf_queue->gt = gt;
diff --git a/drivers/gpu/drm/xe/xe_lmtt.c b/drivers/gpu/drm/xe/xe_lmtt.c
@@ -78,6 +78,9 @@ static struct xe_lmtt_pt *lmtt_pt_alloc(struct xe_lmtt *lmtt, unsigned int level
 	}
 
 	lmtt_assert(lmtt, xe_bo_is_vram(bo));
+	lmtt_debug(lmtt, "level=%u addr=%#llx\n", level, (u64)xe_bo_main_addr(bo, XE_PAGE_SIZE));
+
+	xe_map_memset(lmtt_to_xe(lmtt), &bo->vmap, 0, 0, bo->size);
 
 	pt->level = level;
 	pt->bo = bo;
@@ -91,6 +94,9 @@ static struct xe_lmtt_pt *lmtt_pt_alloc(struct xe_lmtt *lmtt, unsigned int level
 
 static void lmtt_pt_free(struct xe_lmtt_pt *pt)
 {
+	lmtt_debug(&pt->bo->tile->sriov.pf.lmtt, "level=%u addr=%llx\n",
+		   pt->level, (u64)xe_bo_main_addr(pt->bo, XE_PAGE_SIZE));
+
 	xe_bo_unpin_map_no_vm(pt->bo);
 	kfree(pt);
 }
@@ -226,9 +232,14 @@ static void lmtt_write_pte(struct xe_lmtt *lmtt, struct xe_lmtt_pt *pt,
 
 	switch (lmtt->ops->lmtt_pte_size(level)) {
 	case sizeof(u32):
+		lmtt_assert(lmtt, !overflows_type(pte, u32));
+		lmtt_assert(lmtt, !pte || !iosys_map_rd(&pt->bo->vmap, idx * sizeof(u32), u32));
+
 		xe_map_wr(lmtt_to_xe(lmtt), &pt->bo->vmap, idx * sizeof(u32), u32, pte);
 		break;
 	case sizeof(u64):
+		lmtt_assert(lmtt, !pte || !iosys_map_rd(&pt->bo->vmap, idx * sizeof(u64), u64));
+
 		xe_map_wr(lmtt_to_xe(lmtt), &pt->bo->vmap, idx * sizeof(u64), u64, pte);
 		break;
 	default:
diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c
@@ -863,7 +863,7 @@ struct dma_fence *xe_migrate_copy(struct xe_migrate *m,
 		if (src_is_vram && xe_migrate_allow_identity(src_L0, &src_it))
 			xe_res_next(&src_it, src_L0);
 		else
-			emit_pte(m, bb, src_L0_pt, src_is_vram, copy_system_ccs,
+			emit_pte(m, bb, src_L0_pt, src_is_vram, copy_system_ccs || use_comp_pat,
 				 &src_it, src_L0, src);
 
 		if (dst_is_vram && xe_migrate_allow_identity(src_L0, &dst_it))
diff --git a/drivers/gpu/drm/xe/xe_module.c b/drivers/gpu/drm/xe/xe_module.c
@@ -20,7 +20,7 @@
 
 struct xe_modparam xe_modparam = {
 	.probe_display = true,
-	.guc_log_level = 3,
+	.guc_log_level = IS_ENABLED(CONFIG_DRM_XE_DEBUG) ? 3 : 1,
 	.force_probe = CONFIG_DRM_XE_FORCE_PROBE,
 	.wedged_mode = 1,
 	.svm_notifier_size = 512,
diff --git a/drivers/gpu/drm/xe/xe_pci.c b/drivers/gpu/drm/xe/xe_pci.c
@@ -140,7 +140,6 @@ static const struct xe_graphics_desc graphics_xelpg = {
 	.has_asid = 1, \
 	.has_atomic_enable_pte_bit = 1, \
 	.has_flat_ccs = 1, \
-	.has_indirect_ring_state = 1, \
 	.has_range_tlb_invalidation = 1, \
 	.has_usm = 1, \
 	.has_64bit_timestamp = 1, \
diff --git a/drivers/gpu/drm/xe/xe_pm.c b/drivers/gpu/drm/xe/xe_pm.c
@@ -134,7 +134,7 @@ int xe_pm_suspend(struct xe_device *xe)
 	/* FIXME: Super racey... */
 	err = xe_bo_evict_all(xe);
 	if (err)
-		goto err_pxp;
+		goto err_display;
 
 	for_each_gt(gt, xe, id) {
 		err = xe_gt_suspend(gt);
@@ -151,7 +151,6 @@ int xe_pm_suspend(struct xe_device *xe)
 
 err_display:
 	xe_display_pm_resume(xe);
-err_pxp:
 	xe_pxp_pm_resume(xe->pxp);
 err:
 	drm_dbg(&xe->drm, "Device suspend failed %d\n", err);
@@ -753,11 +752,13 @@ void xe_pm_assert_unbounded_bridge(struct xe_device *xe)
 }
 
 /**
- * xe_pm_set_vram_threshold - Set a vram threshold for allowing/blocking D3Cold
+ * xe_pm_set_vram_threshold - Set a VRAM threshold for allowing/blocking D3Cold
  * @xe: xe device instance
- * @threshold: VRAM size in bites for the D3cold threshold
+ * @threshold: VRAM size in MiB for the D3cold threshold
  *
- * Returns 0 for success, negative error code otherwise.
+ * Return:
+ * * 0		- success
+ * * -EINVAL	- invalid argument
  */
 int xe_pm_set_vram_threshold(struct xe_device *xe, u32 threshold)
 {
diff --git a/drivers/gpu/drm/xe/xe_uc_fw.c b/drivers/gpu/drm/xe/xe_uc_fw.c
@@ -114,10 +114,10 @@ struct fw_blobs_by_type {
 #define XE_GT_TYPE_ANY XE_GT_TYPE_UNINITIALIZED
 
 #define XE_GUC_FIRMWARE_DEFS(fw_def, mmp_ver, major_ver)					\
-	fw_def(BATTLEMAGE,	GT_TYPE_ANY,	major_ver(xe,	guc,	bmg,	70, 44, 1))	\
-	fw_def(LUNARLAKE,	GT_TYPE_ANY,	major_ver(xe,	guc,	lnl,	70, 44, 1))	\
+	fw_def(BATTLEMAGE,	GT_TYPE_ANY,	major_ver(xe,	guc,	bmg,	70, 45, 2))	\
+	fw_def(LUNARLAKE,	GT_TYPE_ANY,	major_ver(xe,	guc,	lnl,	70, 45, 2))	\
 	fw_def(METEORLAKE,	GT_TYPE_ANY,	major_ver(i915,	guc,	mtl,	70, 44, 1))	\
-	fw_def(DG2,		GT_TYPE_ANY,	major_ver(i915,	guc,	dg2,	70, 44, 1))	\
+	fw_def(DG2,		GT_TYPE_ANY,	major_ver(i915,	guc,	dg2,	70, 45, 2))	\
 	fw_def(DG1,		GT_TYPE_ANY,	major_ver(i915,	guc,	dg1,	70, 44, 1))	\
 	fw_def(ALDERLAKE_N,	GT_TYPE_ANY,	major_ver(i915,	guc,	tgl,	70, 44, 1))	\
 	fw_def(ALDERLAKE_P,	GT_TYPE_ANY,	major_ver(i915,	guc,	adlp,	70, 44, 1))	\
diff --git a/drivers/gpu/drm/xe/xe_wa_oob.rules b/drivers/gpu/drm/xe/xe_wa_oob.rules
@@ -38,10 +38,10 @@
 		GRAPHICS_VERSION(2004)
 		GRAPHICS_VERSION_RANGE(3000, 3001)
 22019338487	MEDIA_VERSION(2000)
-		GRAPHICS_VERSION(2001)
+		GRAPHICS_VERSION(2001), FUNC(xe_rtp_match_not_sriov_vf)
 		MEDIA_VERSION(3000), MEDIA_STEP(A0, B0), FUNC(xe_rtp_match_not_sriov_vf)
 22019338487_display	PLATFORM(LUNARLAKE)
-16023588340	GRAPHICS_VERSION(2001)
+16023588340	GRAPHICS_VERSION(2001), FUNC(xe_rtp_match_not_sriov_vf)
 14019789679	GRAPHICS_VERSION(1255)
 		GRAPHICS_VERSION_RANGE(1270, 2004)
 no_media_l3	MEDIA_VERSION(3000)
