Merge tag 'drm-xe-fixes-2025-02-06' of https://gitlab.freedesktop.org/drm/xe/kernel into drm-fixes

UAPI Changes:
 - OA uAPI related fixes (Ashutosh)

Driver Changes:
 - Fix SRIOV migration initialization (Michal)
 - Restore devcoredump to a sane state (Lucas)

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

From: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/Z6S9rI1ScT_5Aw6_@intel.com

9 files changed, 61 insertions, 39 deletions

diff --git a/drivers/gpu/drm/xe/regs/xe_oa_regs.h b/drivers/gpu/drm/xe/regs/xe_oa_regs.h
index a49561e9f3c3..a79ad2da070c 100644
--- a/drivers/gpu/drm/xe/regs/xe_oa_regs.h
+++ b/drivers/gpu/drm/xe/regs/xe_oa_regs.h
@@ -51,6 +51,10 @@
 /* Common to all OA units */
 #define  OA_OACONTROL_REPORT_BC_MASK		REG_GENMASK(9, 9)
 #define  OA_OACONTROL_COUNTER_SIZE_MASK		REG_GENMASK(8, 8)
+#define  OAG_OACONTROL_USED_BITS \
+	(OAG_OACONTROL_OA_PES_DISAG_EN | OAG_OACONTROL_OA_CCS_SELECT_MASK | \
+	 OAG_OACONTROL_OA_COUNTER_SEL_MASK | OAG_OACONTROL_OA_COUNTER_ENABLE | \
+	 OA_OACONTROL_REPORT_BC_MASK | OA_OACONTROL_COUNTER_SIZE_MASK)
 
 #define OAG_OA_DEBUG XE_REG(0xdaf8, XE_REG_OPTION_MASKED)
 #define  OAG_OA_DEBUG_DISABLE_MMIO_TRG			REG_BIT(14)
@@ -78,6 +82,8 @@
 #define OAM_CONTEXT_CONTROL_OFFSET		(0x1bc)
 #define OAM_CONTROL_OFFSET			(0x194)
 #define  OAM_CONTROL_COUNTER_SEL_MASK		REG_GENMASK(3, 1)
+#define  OAM_OACONTROL_USED_BITS \
+	(OAM_CONTROL_COUNTER_SEL_MASK | OAG_OACONTROL_OA_COUNTER_ENABLE)
 #define OAM_DEBUG_OFFSET			(0x198)
 #define OAM_STATUS_OFFSET			(0x19c)
 #define OAM_MMIO_TRG_OFFSET			(0x1d0)
diff --git a/drivers/gpu/drm/xe/xe_devcoredump.c b/drivers/gpu/drm/xe/xe_devcoredump.c
index 81dc7795c065..39fe485d2085 100644
--- a/drivers/gpu/drm/xe/xe_devcoredump.c
+++ b/drivers/gpu/drm/xe/xe_devcoredump.c
@@ -119,11 +119,7 @@ static ssize_t __xe_devcoredump_read(char *buffer, size_t count,
 	drm_puts(&p, "\n**** GuC CT ****\n");
 	xe_guc_ct_snapshot_print(ss->guc.ct, &p);
 
-	/*
-	 * Don't add a new section header here because the mesa debug decoder
-	 * tool expects the context information to be in the 'GuC CT' section.
-	 */
-	/* drm_puts(&p, "\n**** Contexts ****\n"); */
+	drm_puts(&p, "\n**** Contexts ****\n");
 	xe_guc_exec_queue_snapshot_print(ss->ge, &p);
 
 	drm_puts(&p, "\n**** Job ****\n");
@@ -395,42 +391,34 @@ int xe_devcoredump_init(struct xe_device *xe)
 /**
  * xe_print_blob_ascii85 - print a BLOB to some useful location in ASCII85
  *
- * The output is split to multiple lines because some print targets, e.g. dmesg
- * cannot handle arbitrarily long lines. Note also that printing to dmesg in
- * piece-meal fashion is not possible, each separate call to drm_puts() has a
- * line-feed automatically added! Therefore, the entire output line must be
- * constructed in a local buffer first, then printed in one atomic output call.
+ * The output is split into multiple calls to drm_puts() because some print
+ * targets, e.g. dmesg, cannot handle arbitrarily long lines. These targets may
+ * add newlines, as is the case with dmesg: each drm_puts() call creates a
+ * separate line.
  *
  * There is also a scheduler yield call to prevent the 'task has been stuck for
  * 120s' kernel hang check feature from firing when printing to a slow target
  * such as dmesg over a serial port.
  *
- * TODO: Add compression prior to the ASCII85 encoding to shrink huge buffers down.
- *
  * @p: the printer object to output to
  * @prefix: optional prefix to add to output string
+ * @suffix: optional suffix to add at the end. 0 disables it and is
+ *          not added to the output, which is useful when using multiple calls
+ *          to dump data to @p
  * @blob: the Binary Large OBject to dump out
  * @offset: offset in bytes to skip from the front of the BLOB, must be a multiple of sizeof(u32)
  * @size: the size in bytes of the BLOB, must be a multiple of sizeof(u32)
  */
-void xe_print_blob_ascii85(struct drm_printer *p, const char *prefix,
+void xe_print_blob_ascii85(struct drm_printer *p, const char *prefix, char suffix,
 			   const void *blob, size_t offset, size_t size)
 {
 	const u32 *blob32 = (const u32 *)blob;
 	char buff[ASCII85_BUFSZ], *line_buff;
 	size_t line_pos = 0;
 
-	/*
-	 * Splitting blobs across multiple lines is not compatible with the mesa
-	 * debug decoder tool. Note that even dropping the explicit '\n' below
-	 * doesn't help because the GuC log is so big some underlying implementation
-	 * still splits the lines at 512K characters. So just bail completely for
-	 * the moment.
-	 */
-	return;
-
 #define DMESG_MAX_LINE_LEN	800
-#define MIN_SPACE		(ASCII85_BUFSZ + 2)		/* 85 + "\n\0" */
+	/* Always leave space for the suffix char and the \0 */
+#define MIN_SPACE		(ASCII85_BUFSZ + 2)	/* 85 + "<suffix>\0" */
 
 	if (size & 3)
 		drm_printf(p, "Size not word aligned: %zu", size);
@@ -462,7 +450,6 @@ void xe_print_blob_ascii85(struct drm_printer *p, const char *prefix,
 		line_pos += strlen(line_buff + line_pos);
 
 		if ((line_pos + MIN_SPACE) >= DMESG_MAX_LINE_LEN) {
-			line_buff[line_pos++] = '\n';
 			line_buff[line_pos++] = 0;
 
 			drm_puts(p, line_buff);
@@ -474,10 +461,11 @@ void xe_print_blob_ascii85(struct drm_printer *p, const char *prefix,
 		}
 	}
 
+	if (suffix)
+		line_buff[line_pos++] = suffix;
+
 	if (line_pos) {
-		line_buff[line_pos++] = '\n';
 		line_buff[line_pos++] = 0;
-
 		drm_puts(p, line_buff);
 	}
 
diff --git a/drivers/gpu/drm/xe/xe_devcoredump.h b/drivers/gpu/drm/xe/xe_devcoredump.h
index 6a17e6d60102..5391a80a4d1b 100644
--- a/drivers/gpu/drm/xe/xe_devcoredump.h
+++ b/drivers/gpu/drm/xe/xe_devcoredump.h
@@ -29,7 +29,7 @@ static inline int xe_devcoredump_init(struct xe_device *xe)
 }
 #endif
 
-void xe_print_blob_ascii85(struct drm_printer *p, const char *prefix,
+void xe_print_blob_ascii85(struct drm_printer *p, const char *prefix, char suffix,
 			   const void *blob, size_t offset, size_t size);
 
 #endif
diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c
index 26e64530ada2..5d6fb79957b6 100644
--- a/drivers/gpu/drm/xe/xe_gt.c
+++ b/drivers/gpu/drm/xe/xe_gt.c
@@ -532,8 +532,10 @@ static int all_fw_domain_init(struct xe_gt *gt)
 	if (IS_SRIOV_PF(gt_to_xe(gt)) && !xe_gt_is_media_type(gt))
 		xe_lmtt_init_hw(&gt_to_tile(gt)->sriov.pf.lmtt);
 
-	if (IS_SRIOV_PF(gt_to_xe(gt)))
+	if (IS_SRIOV_PF(gt_to_xe(gt))) {
+		xe_gt_sriov_pf_init(gt);
 		xe_gt_sriov_pf_init_hw(gt);
+	}
 
 	xe_force_wake_put(gt_to_fw(gt), fw_ref);
 
diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf.c b/drivers/gpu/drm/xe/xe_gt_sriov_pf.c
index e71fc3d2bda2..6f906c8e8108 100644
--- a/drivers/gpu/drm/xe/xe_gt_sriov_pf.c
+++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf.c
@@ -68,6 +68,19 @@ int xe_gt_sriov_pf_init_early(struct xe_gt *gt)
 	return 0;
 }
 
+/**
+ * xe_gt_sriov_pf_init - Prepare SR-IOV PF data structures on PF.
+ * @gt: the &xe_gt to initialize
+ *
+ * Late one-time initialization of the PF data.
+ *
+ * Return: 0 on success or a negative error code on failure.
+ */
+int xe_gt_sriov_pf_init(struct xe_gt *gt)
+{
+	return xe_gt_sriov_pf_migration_init(gt);
+}
+
 static bool pf_needs_enable_ggtt_guest_update(struct xe_device *xe)
 {
 	return GRAPHICS_VERx100(xe) == 1200;
@@ -90,7 +103,6 @@ void xe_gt_sriov_pf_init_hw(struct xe_gt *gt)
 		pf_enable_ggtt_guest_update(gt);
 
 	xe_gt_sriov_pf_service_update(gt);
-	xe_gt_sriov_pf_migration_init(gt);
 }
 
 static u32 pf_get_vf_regs_stride(struct xe_device *xe)
diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf.h b/drivers/gpu/drm/xe/xe_gt_sriov_pf.h
index 96fab779a906..f474509411c0 100644
--- a/drivers/gpu/drm/xe/xe_gt_sriov_pf.h
+++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf.h
@@ -10,6 +10,7 @@ struct xe_gt;
 
 #ifdef CONFIG_PCI_IOV
 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_restart(struct xe_gt *gt);
@@ -19,6 +20,11 @@ static inline int xe_gt_sriov_pf_init_early(struct xe_gt *gt)
 	return 0;
 }
 
+static inline int xe_gt_sriov_pf_init(struct xe_gt *gt)
+{
+	return 0;
+}
+
 static inline void xe_gt_sriov_pf_init_hw(struct xe_gt *gt)
 {
 }
diff --git a/drivers/gpu/drm/xe/xe_guc_ct.c b/drivers/gpu/drm/xe/xe_guc_ct.c
index 8b65c5e959cc..50c8076b5158 100644
--- a/drivers/gpu/drm/xe/xe_guc_ct.c
+++ b/drivers/gpu/drm/xe/xe_guc_ct.c
@@ -1724,7 +1724,8 @@ void xe_guc_ct_snapshot_print(struct xe_guc_ct_snapshot *snapshot,
 			   snapshot->g2h_outstanding);
 
 		if (snapshot->ctb)
-			xe_print_blob_ascii85(p, "CTB data", snapshot->ctb, 0, snapshot->ctb_size);
+			xe_print_blob_ascii85(p, "CTB data", '\n',
+					      snapshot->ctb, 0, snapshot->ctb_size);
 	} else {
 		drm_puts(p, "CT disabled\n");
 	}
diff --git a/drivers/gpu/drm/xe/xe_guc_log.c b/drivers/gpu/drm/xe/xe_guc_log.c
index df4cfb698cdb..2baa4d95571f 100644
--- a/drivers/gpu/drm/xe/xe_guc_log.c
+++ b/drivers/gpu/drm/xe/xe_guc_log.c
@@ -211,8 +211,10 @@ void xe_guc_log_snapshot_print(struct xe_guc_log_snapshot *snapshot, struct drm_
 	remain = snapshot->size;
 	for (i = 0; i < snapshot->num_chunks; i++) {
 		size_t size = min(GUC_LOG_CHUNK_SIZE, remain);
+		const char *prefix = i ? NULL : "Log data";
+		char suffix = i == snapshot->num_chunks - 1 ? '\n' : 0;
 
-		xe_print_blob_ascii85(p, i ? NULL : "Log data", snapshot->copy[i], 0, size);
+		xe_print_blob_ascii85(p, prefix, suffix, snapshot->copy[i], 0, size);
 		remain -= size;
 	}
 }
diff --git a/drivers/gpu/drm/xe/xe_oa.c b/drivers/gpu/drm/xe/xe_oa.c
index eeb96b5f49e2..fa873f3d0a9d 100644
--- a/drivers/gpu/drm/xe/xe_oa.c
+++ b/drivers/gpu/drm/xe/xe_oa.c
@@ -237,7 +237,6 @@ static bool xe_oa_buffer_check_unlocked(struct xe_oa_stream *stream)
 	u32 tail, hw_tail, partial_report_size, available;
 	int report_size = stream->oa_buffer.format->size;
 	unsigned long flags;
-	bool pollin;
 
 	spin_lock_irqsave(&stream->oa_buffer.ptr_lock, flags);
 
@@ -282,11 +281,11 @@ static bool xe_oa_buffer_check_unlocked(struct xe_oa_stream *stream)
 	stream->oa_buffer.tail = tail;
 
 	available = xe_oa_circ_diff(stream, stream->oa_buffer.tail, stream->oa_buffer.head);
-	pollin = available >= stream->wait_num_reports * report_size;
+	stream->pollin = available >= stream->wait_num_reports * report_size;
 
 	spin_unlock_irqrestore(&stream->oa_buffer.ptr_lock, flags);
 
-	return pollin;
+	return stream->pollin;
 }
 
 static enum hrtimer_restart xe_oa_poll_check_timer_cb(struct hrtimer *hrtimer)
@@ -294,10 +293,8 @@ static enum hrtimer_restart xe_oa_poll_check_timer_cb(struct hrtimer *hrtimer)
 	struct xe_oa_stream *stream =
 		container_of(hrtimer, typeof(*stream), poll_check_timer);
 
-	if (xe_oa_buffer_check_unlocked(stream)) {
-		stream->pollin = true;
+	if (xe_oa_buffer_check_unlocked(stream))
 		wake_up(&stream->poll_wq);
-	}
 
 	hrtimer_forward_now(hrtimer, ns_to_ktime(stream->poll_period_ns));
 
@@ -452,6 +449,12 @@ static u32 __oa_ccs_select(struct xe_oa_stream *stream)
 	return val;
 }
 
+static u32 __oactrl_used_bits(struct xe_oa_stream *stream)
+{
+	return stream->hwe->oa_unit->type == DRM_XE_OA_UNIT_TYPE_OAG ?
+		OAG_OACONTROL_USED_BITS : OAM_OACONTROL_USED_BITS;
+}
+
 static void xe_oa_enable(struct xe_oa_stream *stream)
 {
 	const struct xe_oa_format *format = stream->oa_buffer.format;
@@ -472,14 +475,14 @@ static void xe_oa_enable(struct xe_oa_stream *stream)
 	    stream->hwe->oa_unit->type == DRM_XE_OA_UNIT_TYPE_OAG)
 		val |= OAG_OACONTROL_OA_PES_DISAG_EN;
 
-	xe_mmio_write32(&stream->gt->mmio, regs->oa_ctrl, val);
+	xe_mmio_rmw32(&stream->gt->mmio, regs->oa_ctrl, __oactrl_used_bits(stream), val);
 }
 
 static void xe_oa_disable(struct xe_oa_stream *stream)
 {
 	struct xe_mmio *mmio = &stream->gt->mmio;
 
-	xe_mmio_write32(mmio, __oa_regs(stream)->oa_ctrl, 0);
+	xe_mmio_rmw32(mmio, __oa_regs(stream)->oa_ctrl, __oactrl_used_bits(stream), 0);
 	if (xe_mmio_wait32(mmio, __oa_regs(stream)->oa_ctrl,
 			   OAG_OACONTROL_OA_COUNTER_ENABLE, 0, 50000, NULL, false))
 		drm_err(&stream->oa->xe->drm,
@@ -2534,6 +2537,8 @@ static void __xe_oa_init_oa_units(struct xe_gt *gt)
 			u->type = DRM_XE_OA_UNIT_TYPE_OAM;
 		}
 
+		xe_mmio_write32(&gt->mmio, u->regs.oa_ctrl, 0);
+
 		/* Ensure MMIO trigger remains disabled till there is a stream */
 		xe_mmio_write32(&gt->mmio, u->regs.oa_debug,
 				oag_configure_mmio_trigger(NULL, false));