Merge tag 'drm-xe-next-fixes-2024-09-19' of https://gitlab.freedesktop.org/drm/xe/kernel into drm-next

Driver Changes:
- Fix macro for checking minimum GuC version (Michal Wajdeczko)
- Fix CCS offset calculation for some BMG SKUs (Matthew Auld)
- Fix locking on memory usage reporting via fdinfo and BO destroy (Matthew Auld)
- Fix GPU page fault handler on a closed VM (Matthew Brost)
- Fix overflow in oa batch buffer (José)

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

From: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/lr6vhd7x5eb7gubd7utfmnwzvfqfslji4kssxyqisynzlvqjni@svgm6jot7r66

7 files changed, 69 insertions, 17 deletions

diff --git a/drivers/gpu/drm/xe/xe_bb.c b/drivers/gpu/drm/xe/xe_bb.c
index a13e0b3a169e..ef777dbdf4ec 100644
--- a/drivers/gpu/drm/xe/xe_bb.c
+++ b/drivers/gpu/drm/xe/xe_bb.c
@@ -65,7 +65,8 @@ __xe_bb_create_job(struct xe_exec_queue *q, struct xe_bb *bb, u64 *addr)
 {
 	u32 size = drm_suballoc_size(bb->bo);
 
-	bb->cs[bb->len++] = MI_BATCH_BUFFER_END;
+	if (bb->len == 0 || bb->cs[bb->len - 1] != MI_BATCH_BUFFER_END)
+		bb->cs[bb->len++] = MI_BATCH_BUFFER_END;
 
 	xe_gt_assert(q->gt, bb->len * 4 + bb_prefetch(q->gt) <= size);
 
diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c
index 06911e9a3bf5..f379df3a12bf 100644
--- a/drivers/gpu/drm/xe/xe_bo.c
+++ b/drivers/gpu/drm/xe/xe_bo.c
@@ -2320,6 +2320,20 @@ void xe_bo_put_commit(struct llist_head *deferred)
 		drm_gem_object_free(&bo->ttm.base.refcount);
 }
 
+void xe_bo_put(struct xe_bo *bo)
+{
+	might_sleep();
+	if (bo) {
+#ifdef CONFIG_PROC_FS
+		if (bo->client)
+			might_lock(&bo->client->bos_lock);
+#endif
+		if (bo->ggtt_node && bo->ggtt_node->ggtt)
+			might_lock(&bo->ggtt_node->ggtt->lock);
+		drm_gem_object_put(&bo->ttm.base);
+	}
+}
+
 /**
  * xe_bo_dumb_create - Create a dumb bo as backing for a fb
  * @file_priv: ...
diff --git a/drivers/gpu/drm/xe/xe_bo.h b/drivers/gpu/drm/xe/xe_bo.h
index dbfb3209615d..6e4be52306df 100644
--- a/drivers/gpu/drm/xe/xe_bo.h
+++ b/drivers/gpu/drm/xe/xe_bo.h
@@ -126,11 +126,7 @@ static inline struct xe_bo *xe_bo_get(struct xe_bo *bo)
 	return bo;
 }
 
-static inline void xe_bo_put(struct xe_bo *bo)
-{
-	if (bo)
-		drm_gem_object_put(&bo->ttm.base);
-}
+void xe_bo_put(struct xe_bo *bo);
 
 static inline void __xe_bo_unset_bulk_move(struct xe_bo *bo)
 {
diff --git a/drivers/gpu/drm/xe/xe_drm_client.c b/drivers/gpu/drm/xe/xe_drm_client.c
index e64f4b645e2e..c4add8b38bbd 100644
--- a/drivers/gpu/drm/xe/xe_drm_client.c
+++ b/drivers/gpu/drm/xe/xe_drm_client.c
@@ -10,6 +10,7 @@
 #include <linux/slab.h>
 #include <linux/types.h>
 
+#include "xe_assert.h"
 #include "xe_bo.h"
 #include "xe_bo_types.h"
 #include "xe_device_types.h"
@@ -151,10 +152,13 @@ void xe_drm_client_add_bo(struct xe_drm_client *client,
  */
 void xe_drm_client_remove_bo(struct xe_bo *bo)
 {
+	struct xe_device *xe = ttm_to_xe_device(bo->ttm.bdev);
 	struct xe_drm_client *client = bo->client;
 
+	xe_assert(xe, !kref_read(&bo->ttm.base.refcount));
+
 	spin_lock(&client->bos_lock);
-	list_del(&bo->client_link);
+	list_del_init(&bo->client_link);
 	spin_unlock(&client->bos_lock);
 
 	xe_drm_client_put(client);
@@ -164,12 +168,9 @@ static void bo_meminfo(struct xe_bo *bo,
 		       struct drm_memory_stats stats[TTM_NUM_MEM_TYPES])
 {
 	u64 sz = bo->size;
-	u32 mem_type;
+	u32 mem_type = bo->ttm.resource->mem_type;
 
-	if (bo->placement.placement)
-		mem_type = bo->placement.placement->mem_type;
-	else
-		mem_type = XE_PL_TT;
+	xe_bo_assert_held(bo);
 
 	if (drm_gem_object_is_shared_for_memory_stats(&bo->ttm.base))
 		stats[mem_type].shared += sz;
@@ -196,6 +197,7 @@ static void show_meminfo(struct drm_printer *p, struct drm_file *file)
 	struct xe_drm_client *client;
 	struct drm_gem_object *obj;
 	struct xe_bo *bo;
+	LLIST_HEAD(deferred);
 	unsigned int id;
 	u32 mem_type;
 
@@ -206,7 +208,20 @@ static void show_meminfo(struct drm_printer *p, struct drm_file *file)
 	idr_for_each_entry(&file->object_idr, obj, id) {
 		struct xe_bo *bo = gem_to_xe_bo(obj);
 
-		bo_meminfo(bo, stats);
+		if (dma_resv_trylock(bo->ttm.base.resv)) {
+			bo_meminfo(bo, stats);
+			xe_bo_unlock(bo);
+		} else {
+			xe_bo_get(bo);
+			spin_unlock(&file->table_lock);
+
+			xe_bo_lock(bo, false);
+			bo_meminfo(bo, stats);
+			xe_bo_unlock(bo);
+
+			xe_bo_put(bo);
+			spin_lock(&file->table_lock);
+		}
 	}
 	spin_unlock(&file->table_lock);
 
@@ -215,11 +230,28 @@ static void show_meminfo(struct drm_printer *p, struct drm_file *file)
 	list_for_each_entry(bo, &client->bos_list, client_link) {
 		if (!kref_get_unless_zero(&bo->ttm.base.refcount))
 			continue;
-		bo_meminfo(bo, stats);
-		xe_bo_put(bo);
+
+		if (dma_resv_trylock(bo->ttm.base.resv)) {
+			bo_meminfo(bo, stats);
+			xe_bo_unlock(bo);
+		} else {
+			spin_unlock(&client->bos_lock);
+
+			xe_bo_lock(bo, false);
+			bo_meminfo(bo, stats);
+			xe_bo_unlock(bo);
+
+			spin_lock(&client->bos_lock);
+			/* The bo ref will prevent this bo from being removed from the list */
+			xe_assert(xef->xe, !list_empty(&bo->client_link));
+		}
+
+		xe_bo_put_deferred(bo, &deferred);
 	}
 	spin_unlock(&client->bos_lock);
 
+	xe_bo_put_commit(&deferred);
+
 	for (mem_type = XE_PL_SYSTEM; mem_type < TTM_NUM_MEM_TYPES; ++mem_type) {
 		if (!xe_mem_type_to_name[mem_type])
 			continue;
diff --git a/drivers/gpu/drm/xe/xe_gt_pagefault.c b/drivers/gpu/drm/xe/xe_gt_pagefault.c
index 730eec07795e..00af059a8971 100644
--- a/drivers/gpu/drm/xe/xe_gt_pagefault.c
+++ b/drivers/gpu/drm/xe/xe_gt_pagefault.c
@@ -212,6 +212,12 @@ static int handle_pagefault(struct xe_gt *gt, struct pagefault *pf)
 	 * TODO: Change to read lock? Using write lock for simplicity.
 	 */
 	down_write(&vm->lock);
+
+	if (xe_vm_is_closed(vm)) {
+		err = -ENOENT;
+		goto unlock_vm;
+	}
+
 	vma = lookup_vma(vm, pf->page_addr);
 	if (!vma) {
 		err = -EINVAL;
diff --git a/drivers/gpu/drm/xe/xe_guc.h b/drivers/gpu/drm/xe/xe_guc.h
index c3e6b51f7a09..42116b167c98 100644
--- a/drivers/gpu/drm/xe/xe_guc.h
+++ b/drivers/gpu/drm/xe/xe_guc.h
@@ -18,8 +18,10 @@
  */
 #define MAKE_GUC_VER(maj, min, pat)	(((maj) << 16) | ((min) << 8) | (pat))
 #define MAKE_GUC_VER_STRUCT(ver)	MAKE_GUC_VER((ver).major, (ver).minor, (ver).patch)
-#define GUC_SUBMIT_VER(guc)		MAKE_VER_STRUCT((guc)->fw.versions.found[XE_UC_FW_VER_COMPATIBILITY])
-#define GUC_FIRMWARE_VER(guc)		MAKE_VER_STRUCT((guc)->fw.versions.found[XE_UC_FW_VER_RELEASE])
+#define GUC_SUBMIT_VER(guc) \
+	MAKE_GUC_VER_STRUCT((guc)->fw.versions.found[XE_UC_FW_VER_COMPATIBILITY])
+#define GUC_FIRMWARE_VER(guc) \
+	MAKE_GUC_VER_STRUCT((guc)->fw.versions.found[XE_UC_FW_VER_RELEASE])
 
 struct drm_printer;
 
diff --git a/drivers/gpu/drm/xe/xe_vram.c b/drivers/gpu/drm/xe/xe_vram.c
index 5bcd59190353..80ba2fc78837 100644
--- a/drivers/gpu/drm/xe/xe_vram.c
+++ b/drivers/gpu/drm/xe/xe_vram.c
@@ -182,6 +182,7 @@ static inline u64 get_flat_ccs_offset(struct xe_gt *gt, u64 tile_size)
 		offset = offset_hi << 32; /* HW view bits 39:32 */
 		offset |= offset_lo << 6; /* HW view bits 31:6 */
 		offset *= num_enabled; /* convert to SW view */
+		offset = round_up(offset, SZ_128K); /* SW must round up to nearest 128K */
 
 		/* We don't expect any holes */
 		xe_assert_msg(xe, offset == (xe_mmio_read64_2x32(gt, GSMBASE) - ccs_size),