From: Stuart Summers <stuart.summers@intel.com>
Cc: rodrigo.vivi@intel.com, riana.tauro@intel.com,
anoop.c.vijay@intel.com, matthew.d.roper@intel.com,
fei.yang@intel.com, intel-xe@lists.freedesktop.org,
Stuart Summers <stuart.summers@intel.com>
Subject: [PATCH 17/17] drm/xe: Don't error on failed media defeature
Date: Sat, 21 Nov 2026 18:23:33 +0000 [thread overview]
Message-ID: <20261121182317.48981-36-stuart.summers@intel.com> (raw)
In-Reply-To: <20261121182317.48981-19-stuart.summers@intel.com>
Right now there isn't an easy way to get the version of the
GFSP firmware that will be replying to this command. For testing
purposes, don't print an error to avoid flagging CI for some
early testing.
Note this patch is not intended to be merged...
Signed-off-by: Stuart Summers <stuart.summers@intel.com>
---
drivers/gpu/drm/xe/xe_ras.c | 18 +++++++++---------
drivers/gpu/drm/xe/xe_sysctrl.c | 10 +++++-----
drivers/gpu/drm/xe/xe_sysctrl_debugfs.c | 6 +++---
drivers/gpu/drm/xe/xe_sysctrl_event.c | 2 +-
drivers/gpu/drm/xe/xe_sysctrl_mailbox.c | 25 +++++++++++++++----------
drivers/gpu/drm/xe/xe_sysctrl_mailbox.h | 3 ++-
6 files changed, 35 insertions(+), 29 deletions(-)
diff --git a/drivers/gpu/drm/xe/xe_ras.c b/drivers/gpu/drm/xe/xe_ras.c
index 0fb891d00b36..ac7898bfa456 100644
--- a/drivers/gpu/drm/xe/xe_ras.c
+++ b/drivers/gpu/drm/xe/xe_ras.c
@@ -282,7 +282,7 @@ static int send_page_offline_cmd(struct xe_device *xe, u64 page_address,
xe_sysctrl_create_command(&command, XE_SYSCTRL_GROUP_GFSP, XE_SYSCTRL_CMD_PAGE_OFFLINE,
&request, sizeof(request), &response, sizeof(response));
- ret = xe_sysctrl_send_command(&xe->sc, &command, &rlen);
+ ret = xe_sysctrl_send_command(&xe->sc, &command, &rlen, true);
if (ret) {
xe_log_err(xe, SYSCTRL, ret, "failed to send page offline command\n");
return ret;
@@ -435,7 +435,7 @@ static void process_offline_pages(struct xe_device *xe, u32 cmd, void *req, size
if (list_req)
list_req->index = count;
- ret = xe_sysctrl_send_command(&xe->sc, &command, &rlen);
+ ret = xe_sysctrl_send_command(&xe->sc, &command, &rlen, true);
if (ret) {
xe_log_err(xe, SYSCTRL, ret, "failed to get page offline data, cmd=%#x\n",
cmd);
@@ -792,7 +792,7 @@ int xe_ras_get_counter_response(struct xe_device *xe, const struct xe_ras_error_
xe_sysctrl_create_command(&command, XE_SYSCTRL_GROUP_GFSP, XE_SYSCTRL_CMD_GET_COUNTER,
&request, sizeof(request), response, sizeof(*response));
- ret = xe_sysctrl_send_command(&xe->sc, &command, &rlen);
+ ret = xe_sysctrl_send_command(&xe->sc, &command, &rlen, true);
if (ret) {
xe_err(xe, "sysctrl: failed to get counter %d\n", ret);
return ret;
@@ -860,7 +860,7 @@ enum xe_ras_recovery_action xe_ras_process_errors(struct xe_device *xe)
do {
memset(&response, 0, sizeof(response));
- ret = xe_sysctrl_send_command(&xe->sc, &command, &rlen);
+ ret = xe_sysctrl_send_command(&xe->sc, &command, &rlen, true);
if (ret) {
xe_err(xe, "sysctrl: failed to get soc error %d\n", ret);
goto err;
@@ -983,7 +983,7 @@ int xe_ras_clear_counter(struct xe_device *xe, u8 severity, u8 component)
&request, sizeof(request), &response, sizeof(response));
guard(xe_pm_runtime)(xe);
- ret = xe_sysctrl_send_command(&xe->sc, &command, &rlen);
+ ret = xe_sysctrl_send_command(&xe->sc, &command, &rlen, true);
if (ret) {
xe_err(xe, "sysctrl: failed to clear counter %d\n", ret);
return ret;
@@ -1042,7 +1042,7 @@ int xe_ras_get_threshold(struct xe_device *xe, u8 severity, u8 component, u32 *t
&request, sizeof(request), &response, sizeof(response));
guard(xe_pm_runtime)(xe);
- ret = xe_sysctrl_send_command(&xe->sc, &command, &len);
+ ret = xe_sysctrl_send_command(&xe->sc, &command, &len, true);
if (ret) {
xe_err(xe, "sysctrl: failed to get threshold %d\n", ret);
return ret;
@@ -1095,7 +1095,7 @@ int xe_ras_set_threshold(struct xe_device *xe, u8 severity, u8 component, u32 th
&request, sizeof(request), &response, sizeof(response));
guard(xe_pm_runtime)(xe);
- ret = xe_sysctrl_send_command(&xe->sc, &command, &len);
+ ret = xe_sysctrl_send_command(&xe->sc, &command, &len, true);
if (ret) {
xe_err(xe, "sysctrl: failed to set threshold %d\n", ret);
return ret;
@@ -1137,7 +1137,7 @@ static ssize_t gpu_health_show(struct device *dev, struct device_attribute *attr
xe_sysctrl_create_command(&command, XE_SYSCTRL_GROUP_GFSP, XE_SYSCTRL_CMD_GET_HEALTH,
&request, sizeof(request), &response, sizeof(response));
guard(xe_pm_runtime)(xe);
- ret = xe_sysctrl_send_command(&xe->sc, &command, &rlen);
+ ret = xe_sysctrl_send_command(&xe->sc, &command, &rlen, true);
if (ret) {
xe_err(xe, "sysctrl: failed to get health %d\n", ret);
return ret;
@@ -1182,7 +1182,7 @@ static ssize_t gpu_health_store(struct device *dev, struct device_attribute *att
xe_sysctrl_create_command(&command, XE_SYSCTRL_GROUP_GFSP, XE_SYSCTRL_CMD_SET_HEALTH,
&request, sizeof(request), &response, sizeof(response));
guard(xe_pm_runtime)(xe);
- ret = xe_sysctrl_send_command(&xe->sc, &command, &rlen);
+ ret = xe_sysctrl_send_command(&xe->sc, &command, &rlen, true);
if (ret) {
xe_err(xe, "sysctrl: failed to set health %d\n", ret);
return ret;
diff --git a/drivers/gpu/drm/xe/xe_sysctrl.c b/drivers/gpu/drm/xe/xe_sysctrl.c
index a7f8c8edd012..66b4e519d29c 100644
--- a/drivers/gpu/drm/xe/xe_sysctrl.c
+++ b/drivers/gpu/drm/xe/xe_sysctrl.c
@@ -166,7 +166,7 @@ xe_sysctrl_check_app_status(struct xe_device *xe, enum xe_sysctrl_app_id app_id)
xe_sysctrl_create_command(&cmd, XE_SYSCTRL_GROUP_CORE, XE_SYSCTRL_CMD_GET_APP_STATUS_BY_ID,
&req, sizeof(req), &resp, sizeof(resp));
- ret = xe_sysctrl_send_command(&xe->sc, &cmd, &out_len);
+ ret = xe_sysctrl_send_command(&xe->sc, &cmd, &out_len, true);
if (ret)
return XE_SYSCTRL_FIRMWARE_COMM_FAILURE;
@@ -243,7 +243,7 @@ int xe_sysctrl_sdk_api_version(struct xe_device *xe, u16 *version)
xe_sysctrl_create_command(&cmd, XE_SYSCTRL_GROUP_CORE, XE_SYSCTRL_CMD_SDK_API_VERSION,
0, 0, &resp, sizeof(resp));
- ret = xe_sysctrl_send_command(&xe->sc, &cmd, &out_len);
+ ret = xe_sysctrl_send_command(&xe->sc, &cmd, &out_len, true);
if (ret)
return ret;
@@ -270,7 +270,7 @@ static int sysctrl_media_defeature(struct xe_device *xe, u8 feature)
XE_SYSCTRL_CMD_MEDIA_DEFEATURE,
&req, sizeof(req), &resp, sizeof(resp));
- ret = xe_sysctrl_send_command(&xe->sc, &cmd, &out_len);
+ ret = xe_sysctrl_send_command(&xe->sc, &cmd, &out_len, false);
if (ret)
return ret;
@@ -308,8 +308,8 @@ static int sysctrl_media_defeature_send(struct xe_device *xe, u8 feature)
ret = sysctrl_media_defeature(xe, feature);
if (ret) {
- xe_err(xe, "sysctrl: failed to defeature media (0x%02x): %pe\n",
- feature, ERR_PTR(ret));
+ xe_info(xe, "sysctrl: failed to defeature media (0x%02x): %pe\n",
+ feature, ERR_PTR(ret));
return ret;
}
diff --git a/drivers/gpu/drm/xe/xe_sysctrl_debugfs.c b/drivers/gpu/drm/xe/xe_sysctrl_debugfs.c
index e0db099ef0ad..510c48ebd0ba 100644
--- a/drivers/gpu/drm/xe/xe_sysctrl_debugfs.c
+++ b/drivers/gpu/drm/xe/xe_sysctrl_debugfs.c
@@ -85,7 +85,7 @@ static ssize_t xe_sysctrl_loopback_write(struct file *file, const char __user *u
scoped_guard(mutex, &entry->lock) {
guard(xe_pm_runtime)(xe);
- entry->status = xe_sysctrl_send_command(entry->sc, &cmd, &out_len);
+ entry->status = xe_sysctrl_send_command(entry->sc, &cmd, &out_len, true);
entry->response_len = entry->status ? 0 : out_len;
status = entry->status;
}
@@ -227,7 +227,7 @@ static ssize_t xe_sysctrl_ras_error_inject_write(struct file *file, const char _
scoped_guard(mutex, &entry->lock) {
guard(xe_pm_runtime)(xe);
- status = xe_sysctrl_send_command(entry->sc, &cmd, &out_len);
+ status = xe_sysctrl_send_command(entry->sc, &cmd, &out_len, true);
entry->status = status;
}
@@ -420,7 +420,7 @@ static ssize_t xe_sysctrl_mailbox_write(struct file *file, const char __user *ub
cmd.timeout_ms = timeout_ms;
guard(xe_pm_runtime)(xe);
- status = xe_sysctrl_send_command(entry->sc, &cmd, &out_len);
+ status = xe_sysctrl_send_command(entry->sc, &cmd, &out_len, true);
entry->status = status;
entry->response_len = status ? 0 : out_len;
}
diff --git a/drivers/gpu/drm/xe/xe_sysctrl_event.c b/drivers/gpu/drm/xe/xe_sysctrl_event.c
index 3239c110a66a..9ef34e0c48f9 100644
--- a/drivers/gpu/drm/xe/xe_sysctrl_event.c
+++ b/drivers/gpu/drm/xe/xe_sysctrl_event.c
@@ -24,7 +24,7 @@ static void get_pending_event(struct xe_sysctrl *sc, struct xe_sysctrl_mailbox_c
do {
memset(response, 0, sizeof(*response));
- ret = xe_sysctrl_send_command(sc, command, &len);
+ ret = xe_sysctrl_send_command(sc, command, &len, true);
if (ret) {
xe_log_err(xe, SYSCTRL, ret, "Failed to get pending event\n");
return;
diff --git a/drivers/gpu/drm/xe/xe_sysctrl_mailbox.c b/drivers/gpu/drm/xe/xe_sysctrl_mailbox.c
index 2af73c62d32d..0da7831c7157 100644
--- a/drivers/gpu/drm/xe/xe_sysctrl_mailbox.c
+++ b/drivers/gpu/drm/xe/xe_sysctrl_mailbox.c
@@ -216,7 +216,8 @@ static int sysctrl_process_frame(struct xe_sysctrl *sc,
static int sysctrl_receive_frames(struct xe_sysctrl *sc,
const struct xe_sysctrl_mailbox_msg_hdr *req,
void *data_out, size_t data_out_len,
- size_t *rdata_len, unsigned int timeout_ms)
+ size_t *rdata_len, unsigned int timeout_ms,
+ bool print_on_error)
{
struct xe_sysctrl_mailbox_msg_hdr *hdr;
struct xe_device *xe = sc_to_xe(sc);
@@ -248,16 +249,17 @@ static int sysctrl_receive_frames(struct xe_sysctrl *sc,
hdr = (struct xe_sysctrl_mailbox_msg_hdr *)buffer;
- if (!XE_SYSCTRL_HDR_IS_RESPONSE(hdr) ||
- XE_SYSCTRL_HDR_GROUP_ID(hdr) != XE_SYSCTRL_HDR_GROUP_ID(req) ||
- XE_SYSCTRL_HDR_COMMAND(hdr) != XE_SYSCTRL_HDR_COMMAND(req)) {
+ if ((!XE_SYSCTRL_HDR_IS_RESPONSE(hdr) ||
+ XE_SYSCTRL_HDR_GROUP_ID(hdr) != XE_SYSCTRL_HDR_GROUP_ID(req) ||
+ XE_SYSCTRL_HDR_COMMAND(hdr) != XE_SYSCTRL_HDR_COMMAND(req)) &&
+ print_on_error) {
xe_log_err(xe, SYSCTRL, -EPROTO,
"Response header mismatch: %#x != %#x\n",
hdr->data, req->data);
return -EPROTO;
}
- if (XE_SYSCTRL_HDR_RESULT(hdr) != 0) {
+ if (XE_SYSCTRL_HDR_RESULT(hdr) != 0 && print_on_error) {
xe_log_err(xe, SYSCTRL, -EIO, "Firmware error: %#04x %#x.%#x\n",
XE_SYSCTRL_HDR_RESULT(hdr),
XE_SYSCTRL_HDR_GROUP_ID(req), XE_SYSCTRL_HDR_COMMAND(req));
@@ -273,7 +275,8 @@ static int sysctrl_receive_frames(struct xe_sysctrl *sc,
static int sysctrl_send_command(struct xe_sysctrl *sc,
const u8 *mbox_cmd, size_t cmd_size,
void *data_out, size_t data_out_len,
- size_t *rdata_len, unsigned int timeout_ms)
+ size_t *rdata_len, unsigned int timeout_ms,
+ bool print_on_error)
{
const struct xe_sysctrl_mailbox_msg_hdr *hdr;
size_t received;
@@ -289,7 +292,8 @@ static int sysctrl_send_command(struct xe_sysctrl *sc,
hdr = (const struct xe_sysctrl_mailbox_msg_hdr *)mbox_cmd;
ret = sysctrl_receive_frames(sc, hdr, data_out, data_out_len,
- &received, timeout_ms);
+ &received, timeout_ms,
+ print_on_error);
if (ret)
return ret;
@@ -349,7 +353,8 @@ void xe_sysctrl_create_command(struct xe_sysctrl_mailbox_command *command, u8 gr
*/
int xe_sysctrl_send_command(struct xe_sysctrl *sc,
struct xe_sysctrl_mailbox_command *cmd,
- size_t *rdata_len)
+ size_t *rdata_len,
+ bool print_on_error)
{
struct xe_device *xe = sc_to_xe(sc);
u8 group_id, command_code;
@@ -379,8 +384,8 @@ int xe_sysctrl_send_command(struct xe_sysctrl *sc,
ret = sysctrl_send_command(sc, sc->cmd_buf, cmd_size,
cmd->data_out, cmd->data_out_len, rdata_len,
- timeout_ms);
- if (ret)
+ timeout_ms, print_on_error);
+ if (ret && print_on_error)
xe_log_err(xe, SYSCTRL, ret, "Mailbox command failed to send %#x.%#x\n",
group_id, command_code);
diff --git a/drivers/gpu/drm/xe/xe_sysctrl_mailbox.h b/drivers/gpu/drm/xe/xe_sysctrl_mailbox.h
index 5a3dd14e3a11..165155aba297 100644
--- a/drivers/gpu/drm/xe/xe_sysctrl_mailbox.h
+++ b/drivers/gpu/drm/xe/xe_sysctrl_mailbox.h
@@ -28,6 +28,7 @@ void xe_sysctrl_create_command(struct xe_sysctrl_mailbox_command *command, u8 gr
size_t response_len);
int xe_sysctrl_send_command(struct xe_sysctrl *sc,
struct xe_sysctrl_mailbox_command *cmd,
- size_t *rdata_len);
+ size_t *rdata_len,
+ bool print_on_error);
#endif
--
2.43.0
prev parent reply other threads:[~2026-11-21 18:24 UTC|newest]
Thread overview: 18+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-11-21 18:23 [PATCH 00/17] Work around media 52-bit limitation on CRI Stuart Summers
2026-11-21 18:23 ` [PATCH 01/17] drm/xe/sysctrl: Use preallocated mailbox staging buffers Stuart Summers
2026-11-21 18:23 ` [PATCH 02/17] drm/xe: Process device OOB workarounds during early info init Stuart Summers
2026-11-21 18:23 ` [PATCH 03/17] drm/xe/sysctrl: Restore the SoC remapper on every runtime resume Stuart Summers
2026-11-21 18:23 ` [PATCH 04/17] drm/xe: Add enable_media module parameter Stuart Summers
2026-11-21 18:23 ` [PATCH 05/17] drm/xe: Detect each GMD_ID IP in a loop Stuart Summers
2026-11-21 18:23 ` [PATCH 06/17] drm/xe: Tolerate a missing graphics IP in xe_info_init() Stuart Summers
2026-11-21 18:23 ` [PATCH 07/17] drm/xe: Verify IP presence against GU_CNTL Stuart Summers
2026-11-21 18:23 ` [PATCH 08/17] drm/xe: Guard per-tile primary GT accesses Stuart Summers
2026-11-21 18:23 ` [PATCH 09/17] drm/xe: Stop assuming the root tile has a primary GT Stuart Summers
2026-11-21 18:23 ` [PATCH 10/17] drm/xe: Do not claim flat CCS without a graphics IP Stuart Summers
2026-11-21 18:23 ` [PATCH 11/17] drm/xe: Run page table updates on the media GT when there is no primary Stuart Summers
2026-11-21 18:23 ` [PATCH 12/17] drm/xe: Document that gt_types_allowed=media now probes Stuart Summers
2026-11-21 18:23 ` [PATCH 13/17] drm/xe: Fall back to CPU copies when the tile cannot blit Stuart Summers
2026-11-21 18:23 ` [PATCH 14/17] drm/xe: Require a fully visible VRAM BAR without a primary GT Stuart Summers
2026-11-21 18:23 ` [PATCH 15/17] drm/xe: Allow probe " Stuart Summers
2026-11-21 18:23 ` [PATCH 16/17] drm/xe: Work around media 52-bit limitation on CRI Stuart Summers
2026-11-21 18:23 ` Stuart Summers [this message]
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=20261121182317.48981-36-stuart.summers@intel.com \
--to=stuart.summers@intel.com \
--cc=anoop.c.vijay@intel.com \
--cc=fei.yang@intel.com \
--cc=intel-xe@lists.freedesktop.org \
--cc=matthew.d.roper@intel.com \
--cc=riana.tauro@intel.com \
--cc=rodrigo.vivi@intel.com \
/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