public inbox for intel-gfx@lists.freedesktop.org
 help / color / mirror / Atom feed
From: John.C.Harrison@Intel.com
To: Intel-GFX@Lists.FreeDesktop.Org
Cc: DRI-Devel@Lists.FreeDesktop.Org
Subject: [Intel-gfx] [PATCH 4/7] drm/i915/guc: Record CTB info in error logs
Date: Wed, 27 Jul 2022 19:20:25 -0700	[thread overview]
Message-ID: <20220728022028.2190627-5-John.C.Harrison@Intel.com> (raw)
In-Reply-To: <20220728022028.2190627-1-John.C.Harrison@Intel.com>

From: John Harrison <John.C.Harrison@Intel.com>

When debugging GuC communication issues, it is useful to have the CTB
info available. So add the state and buffer contents to the error
capture log.

Also, add a sub-structure for the GuC specific error capture info as
it is now becoming numerous.

Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
---
 drivers/gpu/drm/i915/i915_gpu_error.c | 59 +++++++++++++++++++++++----
 drivers/gpu/drm/i915/i915_gpu_error.h | 20 +++++++--
 2 files changed, 67 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index addba75252343..543ba63f958ea 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -671,6 +671,18 @@ static void err_print_pciid(struct drm_i915_error_state_buf *m,
 		   pdev->subsystem_device);
 }
 
+static void err_print_guc_ctb(struct drm_i915_error_state_buf *m,
+			      const char *name,
+			      const struct intel_ctb_coredump *ctb)
+{
+	if (!ctb->size)
+		return;
+
+	err_printf(m, "GuC %s CTB: raw: 0x%08X, 0x%08X/%08X, cached: 0x%08X/%08X, desc = 0x%08X, buf = 0x%08X x 0x%08X\n",
+		   name, ctb->raw_status, ctb->raw_head, ctb->raw_tail,
+		   ctb->head, ctb->tail, ctb->desc_offset, ctb->cmds_offset, ctb->size);
+}
+
 static void err_print_uc(struct drm_i915_error_state_buf *m,
 			 const struct intel_uc_coredump *error_uc)
 {
@@ -678,8 +690,12 @@ static void err_print_uc(struct drm_i915_error_state_buf *m,
 
 	intel_uc_fw_dump(&error_uc->guc_fw, &p);
 	intel_uc_fw_dump(&error_uc->huc_fw, &p);
-	err_printf(m, "GuC timestamp: 0x%08x\n", error_uc->timestamp);
-	intel_gpu_error_print_vma(m, NULL, error_uc->guc_log);
+	err_printf(m, "GuC timestamp: 0x%08x\n", error_uc->guc.timestamp);
+	intel_gpu_error_print_vma(m, NULL, error_uc->guc.vma_log);
+	err_printf(m, "GuC CTB fence: %d\n", error_uc->guc.last_fence);
+	err_print_guc_ctb(m, "Send", error_uc->guc.ctb + 0);
+	err_print_guc_ctb(m, "Recv", error_uc->guc.ctb + 1);
+	intel_gpu_error_print_vma(m, NULL, error_uc->guc.vma_ctb);
 }
 
 static void err_free_sgl(struct scatterlist *sgl)
@@ -854,7 +870,7 @@ static void __err_print_to_sgl(struct drm_i915_error_state_buf *m,
 	if (error->gt) {
 		bool print_guc_capture = false;
 
-		if (error->gt->uc && error->gt->uc->is_guc_capture)
+		if (error->gt->uc && error->gt->uc->guc.is_guc_capture)
 			print_guc_capture = true;
 
 		err_print_gt_display(m, error->gt);
@@ -1009,7 +1025,8 @@ static void cleanup_uc(struct intel_uc_coredump *uc)
 {
 	kfree(uc->guc_fw.path);
 	kfree(uc->huc_fw.path);
-	i915_vma_coredump_free(uc->guc_log);
+	i915_vma_coredump_free(uc->guc.vma_log);
+	i915_vma_coredump_free(uc->guc.vma_ctb);
 
 	kfree(uc);
 }
@@ -1658,6 +1675,23 @@ gt_record_engines(struct intel_gt_coredump *gt,
 	}
 }
 
+static void gt_record_guc_ctb(struct intel_ctb_coredump *saved,
+			      const struct intel_guc_ct_buffer *ctb,
+			      const void *blob_ptr, struct intel_guc *guc)
+{
+	if (!ctb || !ctb->desc)
+		return;
+
+	saved->raw_status = ctb->desc->status;
+	saved->raw_head = ctb->desc->head;
+	saved->raw_tail = ctb->desc->tail;
+	saved->head = ctb->head;
+	saved->tail = ctb->tail;
+	saved->size = ctb->size;
+	saved->desc_offset = ((void *)ctb->desc) - blob_ptr;
+	saved->cmds_offset = ((void *)ctb->cmds) - blob_ptr;
+}
+
 static struct intel_uc_coredump *
 gt_record_uc(struct intel_gt_coredump *gt,
 	     struct i915_vma_compress *compress)
@@ -1684,9 +1718,16 @@ gt_record_uc(struct intel_gt_coredump *gt,
 	 * log times to system times (in conjunction with the error->boottime and
 	 * gt->clock_frequency fields saved elsewhere).
 	 */
-	error_uc->timestamp = intel_uncore_read(gt->_gt->uncore, GUCPMTIMESTAMP);
-	error_uc->guc_log = create_vma_coredump(gt->_gt, uc->guc.log.vma,
-						"GuC log buffer", compress);
+	error_uc->guc.timestamp = intel_uncore_read(gt->_gt->uncore, GUCPMTIMESTAMP);
+	error_uc->guc.vma_log = create_vma_coredump(gt->_gt, uc->guc.log.vma,
+						    "GuC log buffer", compress);
+	error_uc->guc.vma_ctb = create_vma_coredump(gt->_gt, uc->guc.ct.vma,
+						    "GuC CT buffer", compress);
+	error_uc->guc.last_fence = uc->guc.ct.requests.last_fence;
+	gt_record_guc_ctb(error_uc->guc.ctb + 0, &uc->guc.ct.ctbs.send,
+			  uc->guc.ct.ctbs.send.desc, (struct intel_guc *)&uc->guc);
+	gt_record_guc_ctb(error_uc->guc.ctb + 1, &uc->guc.ct.ctbs.recv,
+			  uc->guc.ct.ctbs.send.desc, (struct intel_guc *)&uc->guc);
 
 	return error_uc;
 }
@@ -2039,9 +2080,9 @@ __i915_gpu_coredump(struct intel_gt *gt, intel_engine_mask_t engine_mask, u32 du
 			error->gt->uc = gt_record_uc(error->gt, compress);
 			if (error->gt->uc) {
 				if (dump_flags & CORE_DUMP_FLAG_IS_GUC_CAPTURE)
-					error->gt->uc->is_guc_capture = true;
+					error->gt->uc->guc.is_guc_capture = true;
 				else
-					GEM_BUG_ON(error->gt->uc->is_guc_capture);
+					GEM_BUG_ON(error->gt->uc->guc.is_guc_capture);
 			}
 		}
 
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.h b/drivers/gpu/drm/i915/i915_gpu_error.h
index d8a8b3d529e09..efc75cc2ffdb9 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.h
+++ b/drivers/gpu/drm/i915/i915_gpu_error.h
@@ -125,6 +125,15 @@ struct intel_engine_coredump {
 	struct intel_engine_coredump *next;
 };
 
+struct intel_ctb_coredump {
+	u32 raw_head, head;
+	u32 raw_tail, tail;
+	u32 raw_status;
+	u32 desc_offset;
+	u32 cmds_offset;
+	u32 size;
+};
+
 struct intel_gt_coredump {
 	const struct intel_gt *_gt;
 	bool awake;
@@ -165,9 +174,14 @@ struct intel_gt_coredump {
 	struct intel_uc_coredump {
 		struct intel_uc_fw guc_fw;
 		struct intel_uc_fw huc_fw;
-		struct i915_vma_coredump *guc_log;
-		u32 timestamp;
-		bool is_guc_capture;
+		struct guc_info {
+			struct intel_ctb_coredump ctb[2];
+			struct i915_vma_coredump *vma_ctb;
+			struct i915_vma_coredump *vma_log;
+			u32 timestamp;
+			u16 last_fence;
+			bool is_guc_capture;
+		} guc;
 	} *uc;
 
 	struct intel_gt_coredump *next;
-- 
2.37.1


  parent reply	other threads:[~2022-07-28  2:21 UTC|newest]

Thread overview: 34+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-07-28  2:20 [Intel-gfx] [PATCH 0/7] Fixes and improvements to GuC logging and error capture John.C.Harrison
2022-07-28  2:20 ` [Intel-gfx] [PATCH 1/7] drm/i915/guc: Add a helper for log buffer size John.C.Harrison
2022-08-02 17:37   ` Teres Alexis, Alan Previn
2022-08-03  0:29     ` John Harrison
2022-07-28  2:20 ` [Intel-gfx] [PATCH 2/7] drm/i915/guc: Fix capture size warning and bump the size John.C.Harrison
2022-08-02 17:46   ` Teres Alexis, Alan Previn
2022-07-28  2:20 ` [Intel-gfx] [PATCH 3/7] drm/i915/guc: Add GuC <-> kernel time stamp translation information John.C.Harrison
2022-08-05  0:40   ` Teres Alexis, Alan Previn
2022-08-08 18:43     ` John Harrison
2022-08-15  4:55       ` Teres Alexis, Alan Previn
2022-08-19 10:45   ` Jani Nikula
2022-08-19 21:02     ` John Harrison
2022-08-23 10:09       ` Jani Nikula
2022-07-28  2:20 ` John.C.Harrison [this message]
2022-08-02 18:27   ` [Intel-gfx] [PATCH 4/7] drm/i915/guc: Record CTB info in error logs Teres Alexis, Alan Previn
2022-08-03  0:20     ` John Harrison
2022-07-28  2:20 ` [Intel-gfx] [PATCH 5/7] drm/i915/guc: Use streaming loads to speed up dumping the guc log John.C.Harrison
2022-08-02 18:48   ` Teres Alexis, Alan Previn
2022-08-03  0:14     ` John Harrison
2022-07-28  2:20 ` [Intel-gfx] [PATCH 6/7] drm/i915/guc: Make GuC log sizes runtime configurable John.C.Harrison
2022-08-15  5:43   ` Teres Alexis, Alan Previn
2022-08-24  9:01   ` Joonas Lahtinen
     [not found]     ` <4bd7b51a-caf0-d987-c7df-6cfb24f36597@intel.com>
2022-08-25  7:15       ` Joonas Lahtinen
2022-08-25 16:31         ` John Harrison
2022-08-26  6:23           ` Joonas Lahtinen
2022-09-12  7:12             ` Joonas Lahtinen
2022-09-12 23:46               ` John Harrison
2022-07-28  2:20 ` [Intel-gfx] [PATCH 7/7] drm/i915/guc: Reduce spam from error capture John.C.Harrison
2022-08-02 18:54   ` Teres Alexis, Alan Previn
2022-07-28  2:37 ` [Intel-gfx] ✗ Fi.CI.CHECKPATCH: warning for Fixes and improvements to GuC logging and " Patchwork
2022-07-28  2:37 ` [Intel-gfx] ✗ Fi.CI.SPARSE: " Patchwork
2022-07-28  2:57 ` [Intel-gfx] ✓ Fi.CI.BAT: success " Patchwork
2022-07-28  9:31 ` [Intel-gfx] ✗ Fi.CI.IGT: failure " Patchwork
2022-08-16  0:53   ` John Harrison

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20220728022028.2190627-5-John.C.Harrison@Intel.com \
    --to=john.c.harrison@intel.com \
    --cc=DRI-Devel@Lists.FreeDesktop.Org \
    --cc=Intel-GFX@Lists.FreeDesktop.Org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox