[PATCH v5 7/8] drm/xe/guc: Dump entire CTB on errors
John.C.Harrison at Intel.com
John.C.Harrison at Intel.com
Mon Jul 29 23:17:51 UTC 2024
From: John Harrison <John.C.Harrison at 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.
Signed-off-by: John Harrison <John.C.Harrison at Intel.com>
---
drivers/gpu/drm/xe/xe_devcoredump.c | 2 +-
drivers/gpu/drm/xe/xe_guc_ct.c | 101 ++++++++++++---------------
drivers/gpu/drm/xe/xe_guc_ct.h | 9 +--
drivers/gpu/drm/xe/xe_guc_ct_types.h | 2 +
drivers/gpu/drm/xe/xe_guc_log.c | 12 +++-
drivers/gpu/drm/xe/xe_guc_log.h | 2 +
6 files changed, 63 insertions(+), 65 deletions(-)
diff --git a/drivers/gpu/drm/xe/xe_devcoredump.c b/drivers/gpu/drm/xe/xe_devcoredump.c
index d8d8ca2c19d3..08a0bb3ee7c0 100644
--- a/drivers/gpu/drm/xe/xe_devcoredump.c
+++ b/drivers/gpu/drm/xe/xe_devcoredump.c
@@ -117,7 +117,7 @@ static ssize_t xe_devcoredump_read(char *buffer, loff_t offset,
xe_device_snapshot_print(xe, &p);
drm_printf(&p, "\n**** GuC CT ****\n");
- xe_guc_ct_snapshot_print(coredump->snapshot.ct, &p);
+ xe_guc_ct_snapshot_print(xe, coredump->snapshot.ct, &p, false);
xe_guc_exec_queue_snapshot_print(coredump->snapshot.ge, &p);
drm_printf(&p, "\n**** Job ****\n");
diff --git a/drivers/gpu/drm/xe/xe_guc_ct.c b/drivers/gpu/drm/xe/xe_guc_ct.c
index 21c88a0cdfd3..ad393d22db28 100644
--- a/drivers/gpu/drm/xe/xe_guc_ct.c
+++ b/drivers/gpu/drm/xe/xe_guc_ct.c
@@ -436,6 +436,7 @@ 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);
@@ -1563,49 +1564,43 @@ 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)
{
- u32 head, tail;
+ snapshot->size = ctb->info.size * sizeof(u32);
+ snapshot->cmds = kmalloc(snapshot->size, atomic ? GFP_ATOMIC : GFP_KERNEL);
+}
- 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));
+struct xe_guc_ct_snapshot *xe_guc_ct_snapshot_alloc(struct xe_guc_ct *ct, bool atomic)
+{
+ struct xe_guc_ct_snapshot *snapshot;
- snapshot->cmds = kmalloc_array(ctb->info.size, sizeof(u32),
- atomic ? GFP_ATOMIC : GFP_KERNEL);
+ snapshot = kzalloc(sizeof(*snapshot), atomic ? GFP_ATOMIC : GFP_KERNEL);
+ if (!snapshot)
+ return NULL;
- if (!snapshot->cmds) {
- drm_err(&xe->drm, "Skipping CTB commands snapshot. Only CT info will be available.\n");
- return;
- }
+ /* 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);
- 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));
- }
- }
- }
+ return snapshot;
}
-static void guc_ctb_snapshot_print(struct guc_ctb_snapshot *snapshot,
- struct drm_printer *p)
+static void guc_ctb_snapshot_capture(struct xe_device *xe, struct guc_ctb *ctb,
+ struct guc_ctb_snapshot *snapshot)
{
- u32 head, tail;
+ 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));
+
+ if (snapshot->cmds)
+ xe_map_memcpy_from(xe, snapshot->cmds, &ctb->cmds, 0, snapshot->size);
+}
+static void guc_ctb_snapshot_print(struct xe_device *xe,
+ struct guc_ctb_snapshot *snapshot,
+ struct drm_printer *p, bool atomic)
+{
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);
@@ -1616,19 +1611,13 @@ 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_hexdump_blob(xe, snapshot->cmds, snapshot->size, p, atomic);
}
static void guc_ctb_snapshot_free(struct guc_ctb_snapshot *snapshot)
@@ -1654,9 +1643,7 @@ 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;
@@ -1665,10 +1652,8 @@ 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;
@@ -1681,18 +1666,18 @@ struct xe_guc_ct_snapshot *xe_guc_ct_snapshot_capture(struct xe_guc_ct *ct,
*
* This function prints out a given GuC CT snapshot object.
*/
-void xe_guc_ct_snapshot_print(struct xe_guc_ct_snapshot *snapshot,
- struct drm_printer *p)
+void xe_guc_ct_snapshot_print(struct xe_device *xe, struct xe_guc_ct_snapshot *snapshot,
+ struct drm_printer *p, bool atomic)
{
if (!snapshot)
return;
if (snapshot->ct_enabled) {
drm_puts(p, "H2G CTB (all sizes in DW):\n");
- guc_ctb_snapshot_print(&snapshot->h2g, p);
+ guc_ctb_snapshot_print(xe, &snapshot->h2g, p, atomic);
drm_puts(p, "G2H CTB (all sizes in DW):\n");
- guc_ctb_snapshot_print(&snapshot->g2h, p);
+ guc_ctb_snapshot_print(xe, &snapshot->g2h, p, atomic);
drm_printf(p, "\tg2h outstanding: %d\n",
snapshot->g2h_outstanding);
@@ -1732,7 +1717,7 @@ void xe_guc_ct_print(struct xe_guc_ct *ct, struct drm_printer *p, bool atomic)
struct xe_guc_ct_snapshot *snapshot;
snapshot = xe_guc_ct_snapshot_capture(ct, atomic);
- xe_guc_ct_snapshot_print(snapshot, p);
+ xe_guc_ct_snapshot_print(ct_to_xe(ct), snapshot, p, atomic);
xe_guc_ct_snapshot_free(snapshot);
}
@@ -1753,7 +1738,7 @@ static void ct_dead_print(struct xe_dead_ct *dead)
drm_printf(&lp, "CTB is dead - reason=0x%X\n", dead->reason);
xe_guc_log_snapshot_print(ct_to_xe(ct), dead->snapshot_log, &lp, false);
- xe_guc_ct_snapshot_print(dead->snapshot_ct, &lp);
+ xe_guc_ct_snapshot_print(ct_to_xe(ct), dead->snapshot_ct, &lp, false);
drm_printf(&lp, "Done.\n");
}
diff --git a/drivers/gpu/drm/xe/xe_guc_ct.h b/drivers/gpu/drm/xe/xe_guc_ct.h
index 190202fce2d0..4336865fcedc 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 +17,10 @@ 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_device *xe, struct xe_guc_ct_snapshot *snapshot,
+ struct drm_printer *p, bool atomic);
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, bool atomic);
diff --git a/drivers/gpu/drm/xe/xe_guc_ct_types.h b/drivers/gpu/drm/xe/xe_guc_ct_types.h
index 9eb2f1a6dcfe..e2a984f0df81 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;
+ /** @cmds: 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 */
diff --git a/drivers/gpu/drm/xe/xe_guc_log.c b/drivers/gpu/drm/xe/xe_guc_log.c
index 2f0a7607941d..82f862b9ad25 100644
--- a/drivers/gpu/drm/xe/xe_guc_log.c
+++ b/drivers/gpu/drm/xe/xe_guc_log.c
@@ -65,8 +65,16 @@ static size_t guc_log_size(void)
#define WORDS_PER_READ (WORDS_PER_DUMP * DUMPS_PER_LINE * LINES_PER_READ)
#define ASCII_LENGTH_PER_WORD 9 /* ' 00000000' */
-static void xe_hexdump_blob(struct xe_device *xe, const void *blob, size_t size,
- struct drm_printer *p, bool atomic)
+/**
+ * xe_hexdump_blob - dump a BLOB to some useful location
+ * @xe: an Xe device structure
+ * @blob: the Binary Large OBject to dump out
+ * @size: the size in bytes of the BLOB
+ * @p: the printer object to output to
+ * @atomic: is the call inside an atomic section of some kind?
+ */
+void xe_hexdump_blob(struct xe_device *xe, const void *blob, size_t size,
+ struct drm_printer *p, bool atomic)
{
char line_buff[DUMPS_PER_LINE * WORDS_PER_DUMP * ASCII_LENGTH_PER_WORD + 1];
int i, j, k;
diff --git a/drivers/gpu/drm/xe/xe_guc_log.h b/drivers/gpu/drm/xe/xe_guc_log.h
index 959a33af23f5..111be8bbaade 100644
--- a/drivers/gpu/drm/xe/xe_guc_log.h
+++ b/drivers/gpu/drm/xe/xe_guc_log.h
@@ -44,6 +44,8 @@ struct xe_guc_log_snapshot *xe_guc_log_snapshot_capture(struct xe_guc_log *log,
void xe_guc_log_snapshot_print(struct xe_device *xe, struct xe_guc_log_snapshot *snapshot,
struct drm_printer *p, bool atomic);
void xe_guc_log_snapshot_free(struct xe_guc_log_snapshot *snapshot);
+void xe_hexdump_blob(struct xe_device *xe, const void *blob, size_t size,
+ struct drm_printer *p, bool atomic);
static inline u32
xe_guc_log_get_level(struct xe_guc_log *log)
--
2.43.2
More information about the Intel-xe
mailing list