[PATCH v6 7/9] drm/xe/guc: Dump entire CTB on errors

[John.C.Harrison@Intel.com]

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

The dump of the CT buffers was only showing the unprocessed data which
is not generally useful for saying why a hang occurred - because it
was probably caused by the commands that were just processed. So save
and dump the entire buffer but in a more compact dump format. Also
zero fill it on allocation to avoid confusion over uninitialised data
in the dump.

v2: Add kerneldoc - review feedback from Michal W.
v3: Fix kerneldoc.
v4: Use ascii85 instead of hexdump (review feedback from Matthew B).

Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
---
 drivers/gpu/drm/xe/xe_guc_ct.c       | 85 ++++++++++++----------------
 drivers/gpu/drm/xe/xe_guc_ct.h       |  8 +--
 drivers/gpu/drm/xe/xe_guc_ct_types.h |  2 +
 3 files changed, 41 insertions(+), 54 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_guc_ct.c b/drivers/gpu/drm/xe/xe_guc_ct.c
index f51fc0d9e648..e41f2e4fbe6b 100644
--- a/drivers/gpu/drm/xe/xe_guc_ct.c
+++ b/drivers/gpu/drm/xe/xe_guc_ct.c
@@ -17,6 +17,7 @@
 #include "abi/guc_actions_sriov_abi.h"
 #include "abi/guc_klvs_abi.h"
 #include "xe_bo.h"
+#include "xe_devcoredump.h"
 #include "xe_device.h"
 #include "xe_gt.h"
 #include "xe_gt_pagefault.h"
@@ -444,6 +445,7 @@ int xe_guc_ct_enable(struct xe_guc_ct *ct)
 
 	xe_gt_assert(gt, !xe_guc_ct_enabled(ct));
 
+	xe_map_memset(xe, &ct->bo->vmap, 0, 0, ct->bo->size);
 	guc_ct_ctb_h2g_init(xe, &ct->ctbs.h2g, &ct->bo->vmap);
 	guc_ct_ctb_g2h_init(xe, &ct->ctbs.g2h, &ct->bo->vmap);
 
@@ -1571,49 +1573,42 @@ static void g2h_worker_func(struct work_struct *w)
 	receive_g2h(ct);
 }
 
-static void guc_ctb_snapshot_capture(struct xe_device *xe, struct guc_ctb *ctb,
-				     struct guc_ctb_snapshot *snapshot,
-				     bool atomic)
+static void guc_ctb_snapshot_alloc(struct guc_ctb *ctb, struct guc_ctb_snapshot *snapshot,
+				   bool atomic)
+{
+	snapshot->size = ctb->info.size * sizeof(u32);
+	snapshot->cmds = kmalloc(snapshot->size, atomic ? GFP_ATOMIC : GFP_KERNEL);
+}
+
+struct xe_guc_ct_snapshot *xe_guc_ct_snapshot_alloc(struct xe_guc_ct *ct, bool atomic)
 {
-	u32 head, tail;
+	struct xe_guc_ct_snapshot *snapshot;
+
+	snapshot = kzalloc(sizeof(*snapshot), atomic ? GFP_ATOMIC : GFP_KERNEL);
+	if (!snapshot)
+		return NULL;
+
+	/* Don't give up if the CTB storage fails to allocate */
+	guc_ctb_snapshot_alloc(&ct->ctbs.h2g, &snapshot->h2g, atomic);
+	guc_ctb_snapshot_alloc(&ct->ctbs.g2h, &snapshot->g2h, atomic);
 
+	return snapshot;
+}
+
+static void guc_ctb_snapshot_capture(struct xe_device *xe, struct guc_ctb *ctb,
+				     struct guc_ctb_snapshot *snapshot)
+{
 	xe_map_memcpy_from(xe, &snapshot->desc, &ctb->desc, 0,
 			   sizeof(struct guc_ct_buffer_desc));
 	memcpy(&snapshot->info, &ctb->info, sizeof(struct guc_ctb_info));
 
-	snapshot->cmds = kmalloc_array(ctb->info.size, sizeof(u32),
-				       atomic ? GFP_ATOMIC : GFP_KERNEL);
-
-	if (!snapshot->cmds) {
-		drm_err(&xe->drm, "Skipping CTB commands snapshot. Only CT info will be available.\n");
-		return;
-	}
-
-	head = snapshot->desc.head;
-	tail = snapshot->desc.tail;
-
-	if (head != tail) {
-		struct iosys_map map =
-			IOSYS_MAP_INIT_OFFSET(&ctb->cmds, head * sizeof(u32));
-
-		while (head != tail) {
-			snapshot->cmds[head] = xe_map_rd(xe, &map, 0, u32);
-			++head;
-			if (head == ctb->info.size) {
-				head = 0;
-				map = ctb->cmds;
-			} else {
-				iosys_map_incr(&map, sizeof(u32));
-			}
-		}
-	}
+	if (snapshot->cmds)
+		xe_map_memcpy_from(xe, snapshot->cmds, &ctb->cmds, 0, snapshot->size);
 }
 
 static void guc_ctb_snapshot_print(struct guc_ctb_snapshot *snapshot,
 				   struct drm_printer *p)
 {
-	u32 head, tail;
-
 	drm_printf(p, "\tsize: %d\n", snapshot->info.size);
 	drm_printf(p, "\tresv_space: %d\n", snapshot->info.resv_space);
 	drm_printf(p, "\thead: %d\n", snapshot->info.head);
@@ -1624,19 +1619,13 @@ static void guc_ctb_snapshot_print(struct guc_ctb_snapshot *snapshot,
 	drm_printf(p, "\ttail (memory): %d\n", snapshot->desc.tail);
 	drm_printf(p, "\tstatus (memory): 0x%x\n", snapshot->desc.status);
 
-	if (!snapshot->cmds)
+	if (!snapshot->cmds) {
+		drm_printf(p, "CT buffer allocation missing!\n");
 		return;
-
-	head = snapshot->desc.head;
-	tail = snapshot->desc.tail;
-
-	while (head != tail) {
-		drm_printf(p, "\tcmd[%d]: 0x%08x\n", head,
-			   snapshot->cmds[head]);
-		++head;
-		if (head == snapshot->info.size)
-			head = 0;
 	}
+
+	drm_printf(p, "CT buffer:\n");
+	xe_print_blob_ascii85(p, snapshot->cmds, 0, snapshot->size);
 }
 
 static void guc_ctb_snapshot_free(struct guc_ctb_snapshot *snapshot)
@@ -1662,9 +1651,7 @@ struct xe_guc_ct_snapshot *xe_guc_ct_snapshot_capture(struct xe_guc_ct *ct,
 	struct xe_device *xe = ct_to_xe(ct);
 	struct xe_guc_ct_snapshot *snapshot;
 
-	snapshot = kzalloc(sizeof(*snapshot),
-			   atomic ? GFP_ATOMIC : GFP_KERNEL);
-
+	snapshot = xe_guc_ct_snapshot_alloc(ct, atomic);
 	if (!snapshot) {
 		drm_err(&xe->drm, "Skipping CTB snapshot entirely.\n");
 		return NULL;
@@ -1673,10 +1660,8 @@ struct xe_guc_ct_snapshot *xe_guc_ct_snapshot_capture(struct xe_guc_ct *ct,
 	if (xe_guc_ct_enabled(ct) || ct->state == XE_GUC_CT_STATE_STOPPED) {
 		snapshot->ct_enabled = true;
 		snapshot->g2h_outstanding = READ_ONCE(ct->g2h_outstanding);
-		guc_ctb_snapshot_capture(xe, &ct->ctbs.h2g,
-					 &snapshot->h2g, atomic);
-		guc_ctb_snapshot_capture(xe, &ct->ctbs.g2h,
-					 &snapshot->g2h, atomic);
+		guc_ctb_snapshot_capture(xe, &ct->ctbs.h2g, &snapshot->h2g);
+		guc_ctb_snapshot_capture(xe, &ct->ctbs.g2h, &snapshot->g2h);
 	}
 
 	return snapshot;
diff --git a/drivers/gpu/drm/xe/xe_guc_ct.h b/drivers/gpu/drm/xe/xe_guc_ct.h
index 293041bed7ed..338f0b75d29f 100644
--- a/drivers/gpu/drm/xe/xe_guc_ct.h
+++ b/drivers/gpu/drm/xe/xe_guc_ct.h
@@ -9,6 +9,7 @@
 #include "xe_guc_ct_types.h"
 
 struct drm_printer;
+struct xe_device;
 
 int xe_guc_ct_init(struct xe_guc_ct *ct);
 int xe_guc_ct_enable(struct xe_guc_ct *ct);
@@ -16,10 +17,9 @@ void xe_guc_ct_disable(struct xe_guc_ct *ct);
 void xe_guc_ct_stop(struct xe_guc_ct *ct);
 void xe_guc_ct_fast_path(struct xe_guc_ct *ct);
 
-struct xe_guc_ct_snapshot *
-xe_guc_ct_snapshot_capture(struct xe_guc_ct *ct, bool atomic);
-void xe_guc_ct_snapshot_print(struct xe_guc_ct_snapshot *snapshot,
-			      struct drm_printer *p);
+struct xe_guc_ct_snapshot *xe_guc_ct_snapshot_alloc(struct xe_guc_ct *ct, bool atomic);
+struct xe_guc_ct_snapshot *xe_guc_ct_snapshot_capture(struct xe_guc_ct *ct, bool atomic);
+void xe_guc_ct_snapshot_print(struct xe_guc_ct_snapshot *snapshot, struct drm_printer *p);
 void xe_guc_ct_snapshot_free(struct xe_guc_ct_snapshot *snapshot);
 void xe_guc_ct_print(struct xe_guc_ct *ct, struct drm_printer *p);
 
diff --git a/drivers/gpu/drm/xe/xe_guc_ct_types.h b/drivers/gpu/drm/xe/xe_guc_ct_types.h
index 85e127ec91d7..c2a2a2831e82 100644
--- a/drivers/gpu/drm/xe/xe_guc_ct_types.h
+++ b/drivers/gpu/drm/xe/xe_guc_ct_types.h
@@ -52,6 +52,8 @@ struct guc_ctb {
 struct guc_ctb_snapshot {
 	/** @desc: snapshot of the CTB descriptor */
 	struct guc_ct_buffer_desc desc;
+	/** @size: size of the snapshot of the CTB commands */
+	size_t size;
 	/** @cmds: snapshot of the CTB commands */
 	u32 *cmds;
 	/** @info: snapshot of the CTB info */
-- 
2.46.0