Merge tag 'drm-xe-fixes-2025-05-15-1' of https://gitlab.freedesktop.org/drm/xe/kernel into drm-fixes

Core Changes:
- Add timeslicing and allocation restriction for SVM

Driver Changes:
- Fix shrinker debugfs name
- Add HW workaround to Xe2
- Fix SVM when mixing GPU and CPU atomics
- Fix per client engine utilization due to active contexts
  not saving timestamp with lite restore enabled.

Signed-off-by: Dave Airlie <airlied@redhat.com>

From: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://lore.kernel.org/r/qil4scyn6ucnt43u5ju64bi7r7n5r36k4pz5rsh2maz7isle6g@lac3jpsjrrvs

Author: airlied

drivers/gpu/drm/drm_gpusvm.c

@@ -1118,6 +1118,10 @@ static void __drm_gpusvm_range_unmap_pages(struct drm_gpusvm *gpusvm,
 	lockdep_assert_held(&gpusvm->notifier_lock);
 
 	if (range->flags.has_dma_mapping) {
+		struct drm_gpusvm_range_flags flags = {
+			.__flags = range->flags.__flags,
+		};
+
 		for (i = 0, j = 0; i < npages; j++) {
 			struct drm_pagemap_device_addr *addr = &range->dma_addr[j];
 
@@ -1131,8 +1135,12 @@ static void __drm_gpusvm_range_unmap_pages(struct drm_gpusvm *gpusvm,
 							    dev, *addr);
 			i += 1 << addr->order;
 		}
-		range->flags.has_devmem_pages = false;
-		range->flags.has_dma_mapping = false;
+
+		/* WRITE_ONCE pairs with READ_ONCE for opportunistic checks */
+		flags.has_devmem_pages = false;
+		flags.has_dma_mapping = false;
+		WRITE_ONCE(range->flags.__flags, flags.__flags);
+
 		range->dpagemap = NULL;
 	}
 }
@@ -1334,6 +1342,7 @@ int drm_gpusvm_range_get_pages(struct drm_gpusvm *gpusvm,
 	int err = 0;
 	struct dev_pagemap *pagemap;
 	struct drm_pagemap *dpagemap;
+	struct drm_gpusvm_range_flags flags;
 
 retry:
 	hmm_range.notifier_seq = mmu_interval_read_begin(notifier);
@@ -1378,7 +1387,8 @@ int drm_gpusvm_range_get_pages(struct drm_gpusvm *gpusvm,
 	 */
 	drm_gpusvm_notifier_lock(gpusvm);
 
-	if (range->flags.unmapped) {
+	flags.__flags = range->flags.__flags;
+	if (flags.unmapped) {
 		drm_gpusvm_notifier_unlock(gpusvm);
 		err = -EFAULT;
 		goto err_free;
@@ -1454,6 +1464,11 @@ int drm_gpusvm_range_get_pages(struct drm_gpusvm *gpusvm,
 				goto err_unmap;
 			}
 
+			if (ctx->devmem_only) {
+				err = -EFAULT;
+				goto err_unmap;
+			}
+
 			addr = dma_map_page(gpusvm->drm->dev,
 					    page, 0,
 					    PAGE_SIZE << order,
@@ -1469,14 +1484,17 @@ int drm_gpusvm_range_get_pages(struct drm_gpusvm *gpusvm,
 		}
 		i += 1 << order;
 		num_dma_mapped = i;
-		range->flags.has_dma_mapping = true;
+		flags.has_dma_mapping = true;
 	}
 
 	if (zdd) {
-		range->flags.has_devmem_pages = true;
+		flags.has_devmem_pages = true;
 		range->dpagemap = dpagemap;
 	}
 
+	/* WRITE_ONCE pairs with READ_ONCE for opportunistic checks */
+	WRITE_ONCE(range->flags.__flags, flags.__flags);
+
 	drm_gpusvm_notifier_unlock(gpusvm);
 	kvfree(pfns);
 set_seqno:
@@ -1765,6 +1783,8 @@ int drm_gpusvm_migrate_to_devmem(struct drm_gpusvm *gpusvm,
 		goto err_finalize;
 
 	/* Upon success bind devmem allocation to range and zdd */
+	devmem_allocation->timeslice_expiration = get_jiffies_64() +
+		msecs_to_jiffies(ctx->timeslice_ms);
 	zdd->devmem_allocation = devmem_allocation;	/* Owns ref */
 
 err_finalize:
@@ -1985,6 +2005,13 @@ static int __drm_gpusvm_migrate_to_ram(struct vm_area_struct *vas,
 	void *buf;
 	int i, err = 0;
 
+	if (page) {
+		zdd = page->zone_device_data;
+		if (time_before64(get_jiffies_64(),
+				  zdd->devmem_allocation->timeslice_expiration))
+			return 0;
+	}
+
 	start = ALIGN_DOWN(fault_addr, size);
 	end = ALIGN(fault_addr + 1, size);
 

drivers/gpu/drm/xe/instructions/xe_mi_commands.h

@@ -47,6 +47,10 @@
 #define   MI_LRI_FORCE_POSTED		REG_BIT(12)
 #define   MI_LRI_LEN(x)			(((x) & 0xff) + 1)
 
+#define MI_STORE_REGISTER_MEM		(__MI_INSTR(0x24) | XE_INSTR_NUM_DW(4))
+#define   MI_SRM_USE_GGTT		REG_BIT(22)
+#define   MI_SRM_ADD_CS_OFFSET		REG_BIT(19)
+
 #define MI_FLUSH_DW			__MI_INSTR(0x26)
 #define   MI_FLUSH_DW_PROTECTED_MEM_EN	REG_BIT(22)
 #define   MI_FLUSH_DW_STORE_INDEX	REG_BIT(21)

drivers/gpu/drm/xe/regs/xe_engine_regs.h

@@ -43,6 +43,10 @@
 #define XEHPC_BCS8_RING_BASE			0x3ee000
 #define GSCCS_RING_BASE				0x11a000
 
+#define ENGINE_ID(base)				XE_REG((base) + 0x8c)
+#define   ENGINE_INSTANCE_ID			REG_GENMASK(9, 4)
+#define   ENGINE_CLASS_ID			REG_GENMASK(2, 0)
+
 #define RING_TAIL(base)				XE_REG((base) + 0x30)
 #define   TAIL_ADDR				REG_GENMASK(20, 3)
 
@@ -154,6 +158,7 @@
 #define   STOP_RING				REG_BIT(8)
 
 #define RING_CTX_TIMESTAMP(base)		XE_REG((base) + 0x3a8)
+#define RING_CTX_TIMESTAMP_UDW(base)		XE_REG((base) + 0x3ac)
 #define CSBE_DEBUG_STATUS(base)			XE_REG((base) + 0x3fc)
 
 #define RING_FORCE_TO_NONPRIV(base, i)		XE_REG(((base) + 0x4d0) + (i) * 4)

drivers/gpu/drm/xe/regs/xe_gt_regs.h

@@ -157,6 +157,7 @@
 #define XEHPG_SC_INSTDONE_EXTRA2		XE_REG_MCR(0x7108)
 
 #define COMMON_SLICE_CHICKEN4			XE_REG(0x7300, XE_REG_OPTION_MASKED)
+#define   SBE_PUSH_CONSTANT_BEHIND_FIX_ENABLE	REG_BIT(12)
 #define   DISABLE_TDC_LOAD_BALANCING_CALC	REG_BIT(6)
 
 #define COMMON_SLICE_CHICKEN3				XE_REG(0x7304, XE_REG_OPTION_MASKED)

drivers/gpu/drm/xe/regs/xe_lrc_layout.h

@@ -11,7 +11,9 @@
 #define CTX_RING_TAIL			(0x06 + 1)
 #define CTX_RING_START			(0x08 + 1)
 #define CTX_RING_CTL			(0x0a + 1)
+#define CTX_BB_PER_CTX_PTR		(0x12 + 1)
 #define CTX_TIMESTAMP			(0x22 + 1)
+#define CTX_TIMESTAMP_UDW		(0x24 + 1)
 #define CTX_INDIRECT_RING_STATE		(0x26 + 1)
 #define CTX_PDP0_UDW			(0x30 + 1)
 #define CTX_PDP0_LDW			(0x32 + 1)

drivers/gpu/drm/xe/xe_device_types.h

@@ -330,6 +330,8 @@ struct xe_device {
 		u8 has_sriov:1;
 		/** @info.has_usm: Device has unified shared memory support */
 		u8 has_usm:1;
+		/** @info.has_64bit_timestamp: Device supports 64-bit timestamps */
+		u8 has_64bit_timestamp:1;
 		/** @info.is_dgfx: is discrete device */
 		u8 is_dgfx:1;
 		/**

drivers/gpu/drm/xe/xe_exec_queue.c

@@ -830,7 +830,7 @@ void xe_exec_queue_update_run_ticks(struct xe_exec_queue *q)
 {
 	struct xe_device *xe = gt_to_xe(q->gt);
 	struct xe_lrc *lrc;
-	u32 old_ts, new_ts;
+	u64 old_ts, new_ts;
 	int idx;
 
 	/*

drivers/gpu/drm/xe/xe_guc_submit.c

@@ -941,7 +941,7 @@ static bool check_timeout(struct xe_exec_queue *q, struct xe_sched_job *job)
 		return xe_sched_invalidate_job(job, 2);
 	}
 
-	ctx_timestamp = xe_lrc_ctx_timestamp(q->lrc[0]);
+	ctx_timestamp = lower_32_bits(xe_lrc_ctx_timestamp(q->lrc[0]));
 	ctx_job_timestamp = xe_lrc_ctx_job_timestamp(q->lrc[0]);
 
 	/*