Merge tag 'drm-xe-fixes-2024-12-04' of https://gitlab.freedesktop.org/drm/xe/kernel into drm-fixes

Driver Changes:
- Missing init value and 64-bit write-order check (Zhanjung)
- Fix a memory allocation issue causing lockdep violation (John)

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

From: Thomas Hellstrom <thomas.hellstrom@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/Z1BidZBFQOLjz__J@fedora

Author: airlied

drivers/gpu/drm/xe/xe_devcoredump.c

@@ -155,36 +155,6 @@ static void xe_devcoredump_snapshot_free(struct xe_devcoredump_snapshot *ss)
 	ss->vm = NULL;
 }
 
-static void xe_devcoredump_deferred_snap_work(struct work_struct *work)
-{
-	struct xe_devcoredump_snapshot *ss = container_of(work, typeof(*ss), work);
-	struct xe_devcoredump *coredump = container_of(ss, typeof(*coredump), snapshot);
-	struct xe_device *xe = coredump_to_xe(coredump);
-	unsigned int fw_ref;
-
-	xe_pm_runtime_get(xe);
-
-	/* keep going if fw fails as we still want to save the memory and SW data */
-	fw_ref = xe_force_wake_get(gt_to_fw(ss->gt), XE_FORCEWAKE_ALL);
-	if (!xe_force_wake_ref_has_domain(fw_ref, XE_FORCEWAKE_ALL))
-		xe_gt_info(ss->gt, "failed to get forcewake for coredump capture\n");
-	xe_vm_snapshot_capture_delayed(ss->vm);
-	xe_guc_exec_queue_snapshot_capture_delayed(ss->ge);
-	xe_force_wake_put(gt_to_fw(ss->gt), fw_ref);
-
-	xe_pm_runtime_put(xe);
-
-	/* Calculate devcoredump size */
-	ss->read.size = __xe_devcoredump_read(NULL, INT_MAX, coredump);
-
-	ss->read.buffer = kvmalloc(ss->read.size, GFP_USER);
-	if (!ss->read.buffer)
-		return;
-
-	__xe_devcoredump_read(ss->read.buffer, ss->read.size, coredump);
-	xe_devcoredump_snapshot_free(ss);
-}
-
 static ssize_t xe_devcoredump_read(char *buffer, loff_t offset,
 				   size_t count, void *data, size_t datalen)
 {
@@ -234,6 +204,45 @@ static void xe_devcoredump_free(void *data)
 		 "Xe device coredump has been deleted.\n");
 }
 
+static void xe_devcoredump_deferred_snap_work(struct work_struct *work)
+{
+	struct xe_devcoredump_snapshot *ss = container_of(work, typeof(*ss), work);
+	struct xe_devcoredump *coredump = container_of(ss, typeof(*coredump), snapshot);
+	struct xe_device *xe = coredump_to_xe(coredump);
+	unsigned int fw_ref;
+
+	/*
+	 * NB: Despite passing a GFP_ flags parameter here, more allocations are done
+	 * internally using GFP_KERNEL expliictly. Hence this call must be in the worker
+	 * thread and not in the initial capture call.
+	 */
+	dev_coredumpm_timeout(gt_to_xe(ss->gt)->drm.dev, THIS_MODULE, coredump, 0, GFP_KERNEL,
+			      xe_devcoredump_read, xe_devcoredump_free,
+			      XE_COREDUMP_TIMEOUT_JIFFIES);
+
+	xe_pm_runtime_get(xe);
+
+	/* keep going if fw fails as we still want to save the memory and SW data */
+	fw_ref = xe_force_wake_get(gt_to_fw(ss->gt), XE_FORCEWAKE_ALL);
+	if (!xe_force_wake_ref_has_domain(fw_ref, XE_FORCEWAKE_ALL))
+		xe_gt_info(ss->gt, "failed to get forcewake for coredump capture\n");
+	xe_vm_snapshot_capture_delayed(ss->vm);
+	xe_guc_exec_queue_snapshot_capture_delayed(ss->ge);
+	xe_force_wake_put(gt_to_fw(ss->gt), fw_ref);
+
+	xe_pm_runtime_put(xe);
+
+	/* Calculate devcoredump size */
+	ss->read.size = __xe_devcoredump_read(NULL, INT_MAX, coredump);
+
+	ss->read.buffer = kvmalloc(ss->read.size, GFP_USER);
+	if (!ss->read.buffer)
+		return;
+
+	__xe_devcoredump_read(ss->read.buffer, ss->read.size, coredump);
+	xe_devcoredump_snapshot_free(ss);
+}
+
 static void devcoredump_snapshot(struct xe_devcoredump *coredump,
 				 struct xe_sched_job *job)
 {
@@ -310,10 +319,6 @@ void xe_devcoredump(struct xe_sched_job *job)
 	drm_info(&xe->drm, "Xe device coredump has been created\n");
 	drm_info(&xe->drm, "Check your /sys/class/drm/card%d/device/devcoredump/data\n",
 		 xe->drm.primary->index);
-
-	dev_coredumpm_timeout(xe->drm.dev, THIS_MODULE, coredump, 0, GFP_KERNEL,
-			      xe_devcoredump_read, xe_devcoredump_free,
-			      XE_COREDUMP_TIMEOUT_JIFFIES);
 }
 
 static void xe_driver_devcoredump_fini(void *arg)

drivers/gpu/drm/xe/xe_guc_capture.c

@@ -102,6 +102,7 @@ struct __guc_capture_parsed_output {
  *                   A 64 bit register define requires 2 consecutive entries,
  *                   with low dword first and hi dword the second.
  *     2. Register name: null for incompleted define
+ *     3. Incorrect order will trigger XE_WARN.
  */
 #define COMMON_XELP_BASE_GLOBAL \
 	{ FORCEWAKE_GT,			REG_32BIT,	0,	0,	"FORCEWAKE_GT"}
@@ -1675,10 +1676,10 @@ snapshot_print_by_list_order(struct xe_hw_engine_snapshot *snapshot, struct drm_
 	struct xe_devcoredump *devcoredump = &xe->devcoredump;
 	struct xe_devcoredump_snapshot *devcore_snapshot = &devcoredump->snapshot;
 	struct gcap_reg_list_info *reginfo = NULL;
-	u32 last_value, i;
-	bool is_ext;
+	u32 i, last_value = 0;
+	bool is_ext, low32_ready = false;
 
-	if (!list || list->num_regs == 0)
+	if (!list || !list->list || list->num_regs == 0)
 		return;
 	XE_WARN_ON(!devcore_snapshot->matched_node);
 
@@ -1701,29 +1702,75 @@ snapshot_print_by_list_order(struct xe_hw_engine_snapshot *snapshot, struct drm_
 			continue;
 
 		value = reg->value;
-		if (reg_desc->data_type == REG_64BIT_LOW_DW) {
+		switch (reg_desc->data_type) {
+		case REG_64BIT_LOW_DW:
 			last_value = value;
+
+			/*
+			 * A 64 bit register define requires 2 consecutive
+			 * entries in register list, with low dword first
+			 * and hi dword the second, like:
+			 *  { XXX_REG_LO(0), REG_64BIT_LOW_DW, 0, 0, NULL},
+			 *  { XXX_REG_HI(0), REG_64BIT_HI_DW,  0, 0, "XXX_REG"},
+			 *
+			 * Incorrect order will trigger XE_WARN.
+			 *
+			 * Possible double low here, for example:
+			 *  { XXX_REG_LO(0), REG_64BIT_LOW_DW, 0, 0, NULL},
+			 *  { XXX_REG_LO(0), REG_64BIT_LOW_DW, 0, 0, NULL},
+			 */
+			XE_WARN_ON(low32_ready);
+			low32_ready = true;
 			/* Low 32 bit dword saved, continue for high 32 bit */
-			continue;
-		} else if (reg_desc->data_type == REG_64BIT_HI_DW) {
+			break;
+
+		case REG_64BIT_HI_DW: {
 			u64 value_qw = ((u64)value << 32) | last_value;
 
+			/*
+			 * Incorrect 64bit register order. Possible missing low.
+			 * for example:
+			 *  { XXX_REG(0), REG_32BIT, 0, 0, NULL},
+			 *  { XXX_REG_HI(0), REG_64BIT_HI_DW, 0, 0, NULL},
+			 */
+			XE_WARN_ON(!low32_ready);
+			low32_ready = false;
+
 			drm_printf(p, "\t%s: 0x%016llx\n", reg_desc->regname, value_qw);
-			continue;
+			break;
 		}
 
-		if (is_ext) {
-			int dss, group, instance;
+		case REG_32BIT:
+			/*
+			 * Incorrect 64bit register order. Possible missing high.
+			 * for example:
+			 *  { XXX_REG_LO(0), REG_64BIT_LOW_DW, 0, 0, NULL},
+			 *  { XXX_REG(0), REG_32BIT, 0, 0, "XXX_REG"},
+			 */
+			XE_WARN_ON(low32_ready);
+
+			if (is_ext) {
+				int dss, group, instance;
 
-			group = FIELD_GET(GUC_REGSET_STEERING_GROUP, reg_desc->flags);
-			instance = FIELD_GET(GUC_REGSET_STEERING_INSTANCE, reg_desc->flags);
-			dss = xe_gt_mcr_steering_info_to_dss_id(gt, group, instance);
+				group = FIELD_GET(GUC_REGSET_STEERING_GROUP, reg_desc->flags);
+				instance = FIELD_GET(GUC_REGSET_STEERING_INSTANCE, reg_desc->flags);
+				dss = xe_gt_mcr_steering_info_to_dss_id(gt, group, instance);
 
-			drm_printf(p, "\t%s[%u]: 0x%08x\n", reg_desc->regname, dss, value);
-		} else {
-			drm_printf(p, "\t%s: 0x%08x\n", reg_desc->regname, value);
+				drm_printf(p, "\t%s[%u]: 0x%08x\n", reg_desc->regname, dss, value);
+			} else {
+				drm_printf(p, "\t%s: 0x%08x\n", reg_desc->regname, value);
+			}
+			break;
 		}
 	}
+
+	/*
+	 * Incorrect 64bit register order. Possible missing high.
+	 * for example:
+	 *  { XXX_REG_LO(0), REG_64BIT_LOW_DW, 0, 0, NULL},
+	 *  } // <- Register list end
+	 */
+	XE_WARN_ON(low32_ready);
 }
 
 /**