14 files changed, 125 insertions, 43 deletions

diff --git a/drivers/gpu/drm/xe/xe_devcoredump.c b/drivers/gpu/drm/xe/xe_devcoredump.c
index 7a8af2311318..11e60d687572 100644
--- 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.c b/drivers/gpu/drm/xe/xe_gt.c
index 6c4cb9576fb6..e3517ce2e18c 100644
--- a/drivers/gpu/drm/xe/xe_gt.c
+++ b/drivers/gpu/drm/xe/xe_gt.c
@@ -417,6 +417,8 @@ int xe_gt_init_early(struct xe_gt *gt)
 	if (err)
 		return err;
 
+	xe_mocs_init_early(gt);
+
 	return 0;
 }
 
@@ -630,17 +632,15 @@ int xe_gt_init(struct xe_gt *gt)
 	if (err)
 		return err;
 
-	err = xe_gt_pagefault_init(gt);
+	err = xe_gt_sysfs_init(gt);
 	if (err)
 		return err;
 
-	xe_mocs_init_early(gt);
-
-	err = xe_gt_sysfs_init(gt);
+	err = gt_fw_domain_init(gt);
 	if (err)
 		return err;
 
-	err = gt_fw_domain_init(gt);
+	err = xe_gt_pagefault_init(gt);
 	if (err)
 		return err;
 
@@ -839,6 +839,9 @@ static int gt_reset(struct xe_gt *gt)
 		goto err_out;
 	}
 
+	if (IS_SRIOV_PF(gt_to_xe(gt)))
+		xe_gt_sriov_pf_stop_prepare(gt);
+
 	xe_uc_gucrc_disable(&gt->uc);
 	xe_uc_stop_prepare(&gt->uc);
 	xe_gt_pagefault_reset(gt);
diff --git a/drivers/gpu/drm/xe/xe_gt_pagefault.c b/drivers/gpu/drm/xe/xe_gt_pagefault.c
index 10622ca471a2..6717a636b1d9 100644
--- 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_gt_sriov_pf.c b/drivers/gpu/drm/xe/xe_gt_sriov_pf.c
index c08efca6420e..35489fa81825 100644
--- a/drivers/gpu/drm/xe/xe_gt_sriov_pf.c
+++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf.c
@@ -172,6 +172,25 @@ void xe_gt_sriov_pf_sanitize_hw(struct xe_gt *gt, unsigned int vfid)
 	pf_clear_vf_scratch_regs(gt, vfid);
 }
 
+static void pf_cancel_restart(struct xe_gt *gt)
+{
+	xe_gt_assert(gt, IS_SRIOV_PF(gt_to_xe(gt)));
+
+	if (cancel_work_sync(&gt->sriov.pf.workers.restart))
+		xe_gt_sriov_dbg_verbose(gt, "pending restart canceled!\n");
+}
+
+/**
+ * xe_gt_sriov_pf_stop_prepare() - Prepare to stop SR-IOV support.
+ * @gt: the &xe_gt
+ *
+ * This function can only be called on the PF.
+ */
+void xe_gt_sriov_pf_stop_prepare(struct xe_gt *gt)
+{
+	pf_cancel_restart(gt);
+}
+
 static void pf_restart(struct xe_gt *gt)
 {
 	struct xe_device *xe = gt_to_xe(gt);
diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf.h b/drivers/gpu/drm/xe/xe_gt_sriov_pf.h
index f474509411c0..e2b2ff8132dc 100644
--- a/drivers/gpu/drm/xe/xe_gt_sriov_pf.h
+++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf.h
@@ -13,6 +13,7 @@ int xe_gt_sriov_pf_init_early(struct xe_gt *gt);
 int xe_gt_sriov_pf_init(struct xe_gt *gt);
 void xe_gt_sriov_pf_init_hw(struct xe_gt *gt);
 void xe_gt_sriov_pf_sanitize_hw(struct xe_gt *gt, unsigned int vfid);
+void xe_gt_sriov_pf_stop_prepare(struct xe_gt *gt);
 void xe_gt_sriov_pf_restart(struct xe_gt *gt);
 #else
 static inline int xe_gt_sriov_pf_init_early(struct xe_gt *gt)
@@ -29,6 +30,10 @@ static inline void xe_gt_sriov_pf_init_hw(struct xe_gt *gt)
 {
 }
 
+static inline void xe_gt_sriov_pf_stop_prepare(struct xe_gt *gt)
+{
+}
+
 static inline void xe_gt_sriov_pf_restart(struct xe_gt *gt)
 {
 }
diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c
index 2420a548cacc..53a44702c04a 100644
--- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c
+++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c
@@ -2364,6 +2364,21 @@ int xe_gt_sriov_pf_config_restore(struct xe_gt *gt, unsigned int vfid,
 	return err;
 }
 
+static int pf_push_self_config(struct xe_gt *gt)
+{
+	int err;
+
+	err = pf_push_full_vf_config(gt, PFID);
+	if (err) {
+		xe_gt_sriov_err(gt, "Failed to push self configuration (%pe)\n",
+				ERR_PTR(err));
+		return err;
+	}
+
+	xe_gt_sriov_dbg_verbose(gt, "self configuration completed\n");
+	return 0;
+}
+
 static void fini_config(void *arg)
 {
 	struct xe_gt *gt = arg;
@@ -2387,9 +2402,17 @@ static void fini_config(void *arg)
 int xe_gt_sriov_pf_config_init(struct xe_gt *gt)
 {
 	struct xe_device *xe = gt_to_xe(gt);
+	int err;
 
 	xe_gt_assert(gt, IS_SRIOV_PF(xe));
 
+	mutex_lock(xe_gt_sriov_pf_master_mutex(gt));
+	err = pf_push_self_config(gt);
+	mutex_unlock(xe_gt_sriov_pf_master_mutex(gt));
+
+	if (err)
+		return err;
+
 	return devm_add_action_or_reset(xe->drm.dev, fini_config, gt);
 }
 
@@ -2407,6 +2430,10 @@ void xe_gt_sriov_pf_config_restart(struct xe_gt *gt)
 	unsigned int n, total_vfs = xe_sriov_pf_get_totalvfs(gt_to_xe(gt));
 	unsigned int fail = 0, skip = 0;
 
+	mutex_lock(xe_gt_sriov_pf_master_mutex(gt));
+	pf_push_self_config(gt);
+	mutex_unlock(xe_gt_sriov_pf_master_mutex(gt));
+
 	for (n = 1; n <= total_vfs; n++) {
 		if (xe_gt_sriov_pf_config_is_empty(gt, n))
 			skip++;
diff --git a/drivers/gpu/drm/xe/xe_lmtt.c b/drivers/gpu/drm/xe/xe_lmtt.c
index 63db66df064b..023ed6a6b49d 100644
--- 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 @@ out:
 
 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
index 7acdc4c78866..07a5161c7d5b 100644
--- 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))
@@ -1817,8 +1817,8 @@ int xe_migrate_access_memory(struct xe_migrate *m, struct xe_bo *bo,
 	xe_bo_assert_held(bo);
 
 	/* Use bounce buffer for small access and unaligned access */
-	if (len & XE_CACHELINE_MASK ||
-	    ((uintptr_t)buf | offset) & XE_CACHELINE_MASK) {
+	if (!IS_ALIGNED(len, XE_CACHELINE_BYTES) ||
+	    !IS_ALIGNED((unsigned long)buf + offset, XE_CACHELINE_BYTES)) {
 		int buf_offset = 0;
 
 		/*
@@ -1848,7 +1848,7 @@ int xe_migrate_access_memory(struct xe_migrate *m, struct xe_bo *bo,
 				err = xe_migrate_access_memory(m, bo,
 							       offset & ~XE_CACHELINE_MASK,
 							       (void *)ptr,
-							       sizeof(bounce), 0);
+							       sizeof(bounce), write);
 				if (err)
 					return err;
 			} else {
diff --git a/drivers/gpu/drm/xe/xe_module.c b/drivers/gpu/drm/xe/xe_module.c
index e4742e27e2cd..da6793c2f991 100644
--- 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
index ac4beaed58ff..278af53c74dc 100644
--- 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
index ff749edc005b..ad263de44111 100644
--- 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_ring_ops.c b/drivers/gpu/drm/xe/xe_ring_ops.c
index bc1689db4cd7..7b50c7c1ee21 100644
--- a/drivers/gpu/drm/xe/xe_ring_ops.c
+++ b/drivers/gpu/drm/xe/xe_ring_ops.c
@@ -110,13 +110,14 @@ static int emit_bb_start(u64 batch_addr, u32 ppgtt_flag, u32 *dw, int i)
 	return i;
 }
 
-static int emit_flush_invalidate(u32 *dw, int i)
+static int emit_flush_invalidate(u32 addr, u32 val, u32 *dw, int i)
 {
 	dw[i++] = MI_FLUSH_DW | MI_INVALIDATE_TLB | MI_FLUSH_DW_OP_STOREDW |
-		  MI_FLUSH_IMM_DW | MI_FLUSH_DW_STORE_INDEX;
-	dw[i++] = LRC_PPHWSP_FLUSH_INVAL_SCRATCH_ADDR;
-	dw[i++] = 0;
+		  MI_FLUSH_IMM_DW;
+
+	dw[i++] = addr | MI_FLUSH_DW_USE_GTT;
 	dw[i++] = 0;
+	dw[i++] = val;
 
 	return i;
 }
@@ -397,23 +398,20 @@ static void __emit_job_gen12_render_compute(struct xe_sched_job *job,
 static void emit_migration_job_gen12(struct xe_sched_job *job,
 				     struct xe_lrc *lrc, u32 seqno)
 {
+	u32 saddr = xe_lrc_start_seqno_ggtt_addr(lrc);
 	u32 dw[MAX_JOB_SIZE_DW], i = 0;
 
 	i = emit_copy_timestamp(lrc, dw, i);
 
-	i = emit_store_imm_ggtt(xe_lrc_start_seqno_ggtt_addr(lrc),
-				seqno, dw, i);
+	i = emit_store_imm_ggtt(saddr, seqno, dw, i);
 
 	dw[i++] = MI_ARB_ON_OFF | MI_ARB_DISABLE; /* Enabled again below */
 
 	i = emit_bb_start(job->ptrs[0].batch_addr, BIT(8), dw, i);
 
-	if (!IS_SRIOV_VF(gt_to_xe(job->q->gt))) {
-		/* XXX: Do we need this? Leaving for now. */
-		dw[i++] = preparser_disable(true);
-		i = emit_flush_invalidate(dw, i);
-		dw[i++] = preparser_disable(false);
-	}
+	dw[i++] = preparser_disable(true);
+	i = emit_flush_invalidate(saddr, seqno, dw, i);
+	dw[i++] = preparser_disable(false);
 
 	i = emit_bb_start(job->ptrs[1].batch_addr, BIT(8), dw, i);
 
diff --git a/drivers/gpu/drm/xe/xe_uc_fw.c b/drivers/gpu/drm/xe/xe_uc_fw.c
index 2741849bbf4d..a6612105201a 100644
--- 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
index 69c1d7fc695e..6d70109fcc43 100644
--- 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)