From: "Michael J. Ruhl" <michael.j.ruhl@intel.com>
To: intel-xe@lists.freedesktop.org, matthew.brost@intel.com,
rodrigo.vivi@intel.com, thomas.hellstrom@linux.intel.com,
airlied@gmail.com, simona@ffwll.ch, david.e.box@linux.intel.com,
anoop.c.vijay@intel.com, badal.nilawar@intel.com,
matthew.d.roper@intel.com, james.ausmus@intel.com
Subject: [PATCH v16 13/17] drm/xe/vsec: Support late bind fw information
Date: Mon, 16 Nov 2026 07:07:02 -0800 [thread overview]
Message-ID: <20261116150649.368686-32-michael.j.ruhl@intel.com> (raw)
In-Reply-To: <20261116150649.368686-19-michael.j.ruhl@intel.com>
CRI FW is loaded on power on. Because of this, access to the FW cannot
be done until it is running.
Update the XE PMT probe and access to check for late bind devices,
verify, and wait for the appropriate FW state before probe or access.
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Michael J. Ruhl <michael.j.ruhl@intel.com>
---
drivers/gpu/drm/xe/xe_device.c | 3 +
drivers/gpu/drm/xe/xe_device_types.h | 5 ++
drivers/gpu/drm/xe/xe_vsec.c | 126 ++++++++++++++++++++++++++-
drivers/gpu/drm/xe/xe_vsec.h | 1 +
4 files changed, 134 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
index c3cd98244d4c..76e401ae5878 100644
--- a/drivers/gpu/drm/xe/xe_device.c
+++ b/drivers/gpu/drm/xe/xe_device.c
@@ -1111,6 +1111,7 @@ int xe_device_probe(struct xe_device *xe)
return 0;
err_unregister_display:
+ xe_vsec_remove(xe);
xe_display_unregister(xe);
drm_dev_unregister(&xe->drm);
@@ -1119,6 +1120,8 @@ int xe_device_probe(struct xe_device *xe)
void xe_device_remove(struct xe_device *xe)
{
+ xe_vsec_remove(xe);
+
xe_display_unregister(xe);
drm_dev_unplug(&xe->drm);
diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h
index 28b1669a14d8..d1bdd3a872a8 100644
--- a/drivers/gpu/drm/xe/xe_device_types.h
+++ b/drivers/gpu/drm/xe/xe_device_types.h
@@ -7,6 +7,7 @@
#define _XE_DEVICE_TYPES_H_
#include <linux/pci.h>
+#include <linux/workqueue.h>
#include <drm/drm_device.h>
#include <drm/drm_file.h>
@@ -487,6 +488,10 @@ struct xe_device {
struct mutex lock;
/** @pmt.base_offset: device specific base offset */
u64 base_offset;
+ /** @pmt.work: support late-bind probe */
+ struct delayed_work work;
+ /** @pmt.retry_count: late-bind probe retry */
+ u32 retry_count;
} pmt;
/** @soc_remapper: SoC remapper object */
diff --git a/drivers/gpu/drm/xe/xe_vsec.c b/drivers/gpu/drm/xe/xe_vsec.c
index 4ca41a5ef502..fe3d8338cfc9 100644
--- a/drivers/gpu/drm/xe/xe_vsec.c
+++ b/drivers/gpu/drm/xe/xe_vsec.c
@@ -3,6 +3,7 @@
#include <linux/bitfield.h>
#include <linux/bits.h>
#include <linux/cleanup.h>
+#include <linux/delay.h>
#include <linux/errno.h>
#include <linux/intel_vsec.h>
#include <linux/module.h>
@@ -18,6 +19,7 @@
#include "xe_mmio.h"
#include "xe_platform_types.h"
#include "xe_pm.h"
+#include "xe_sysctrl.h"
#include "xe_vsec.h"
#include "regs/xe_pmt.h"
@@ -173,6 +175,14 @@ enum capability {
WATCHER,
};
+/*
+ * Late bind will delay 100msec for up to 20 seconds
+ */
+#define VSEC_LATE_BIND_DELAY_MSEC 100
+#define VSEC_LATE_BIND_RETRY 200
+
+static void cri_late_bind_probe(struct xe_device *xe);
+
static int bmg_guid_decode(u32 guid, int *index, u32 *offset)
{
u32 record_id = FIELD_GET(GUID_RECORD_ID, guid);
@@ -281,6 +291,53 @@ static int xe_guid_decode(u32 guid, int *index, u32 *offset)
return -ENODEV;
}
+static void cri_late_bind_probe_work(struct work_struct *work)
+{
+ struct xe_device *xe = container_of(work, struct xe_device, pmt.work.work);
+
+ if (xe_sysctrl_is_oobmsm_fw_ready(xe)) {
+ cri_late_bind_probe(xe);
+ xe_pm_runtime_put(xe);
+ return;
+ }
+
+ xe->pmt.retry_count++;
+
+ /* wait up to 20 seconds */
+ if (xe->pmt.retry_count == VSEC_LATE_BIND_RETRY) {
+ drm_warn(&xe->drm, "PMT probe: Late Binding failed to complete\n");
+ xe_pm_runtime_put(xe);
+ return;
+ }
+
+ if (!queue_delayed_work(system_freezable_wq, &xe->pmt.work,
+ msecs_to_jiffies(VSEC_LATE_BIND_DELAY_MSEC)))
+ xe_pm_runtime_put(xe);
+}
+
+static bool wait_for_fw(struct xe_device *xe)
+{
+ int retries = VSEC_LATE_BIND_RETRY; /* wait up to 20 secs */
+
+ if (xe->info.platform != XE_CRESCENTISLAND)
+ return true;
+
+ while (retries--) {
+ if (xe_sysctrl_is_oobmsm_fw_ready(xe))
+ return true;
+
+ msleep(VSEC_LATE_BIND_DELAY_MSEC);
+ if (signal_pending(current)) {
+ drm_warn(&xe->drm, "Late Binding interrupted\n");
+ return false;
+ }
+ }
+
+ drm_warn(&xe->drm, "Late Binding failed to complete\n");
+
+ return false;
+}
+
/**
* xe_pmt_telem_read - Given a device and a PMT GUID, read data into a buffer
* @dev: valid Xe device
@@ -343,6 +400,11 @@ int xe_pmt_telem_read(struct device *dev, u32 guid, u64 *data, loff_t user_offse
goto dev_exit;
}
+ if (!wait_for_fw(xe)) {
+ ret = -ENODATA;
+ goto runtime_exit;
+ }
+
scoped_guard(mutex, &xe->pmt.lock) {
u32 device_id = FIELD_GET(GUID_DEVICE_ID, guid);
@@ -355,6 +417,7 @@ int xe_pmt_telem_read(struct device *dev, u32 guid, u64 *data, loff_t user_offse
xe->soc_remapper.set_telem_region(xe, CRI_IDX_TELEM_DISCOVERY);
}
+runtime_exit:
xe_pm_runtime_put(xe);
dev_exit:
@@ -400,6 +463,10 @@ static int xe_pmt_read_reg(struct device *dev, u32 guid, u32 *reg, u32 offset)
disc_addr += inst + offset;
xe_pm_runtime_get(xe);
+ if (!wait_for_fw(xe)) {
+ ret = -ENODATA;
+ goto runtime_exit;
+ }
scoped_guard(mutex, &xe->pmt.lock) {
xe->soc_remapper.set_telem_region(xe, CRI_IDX_TELEM_DISCOVERY);
@@ -407,6 +474,7 @@ static int xe_pmt_read_reg(struct device *dev, u32 guid, u32 *reg, u32 offset)
*reg = readl(disc_addr);
}
+runtime_exit:
xe_pm_runtime_put(xe);
drm_dev_exit(idx);
@@ -434,6 +502,10 @@ static int xe_pmt_write_reg(struct device *dev, u32 guid, u32 reg, u32 offset)
disc_addr += inst + offset;
xe_pm_runtime_get(xe);
+ if (!wait_for_fw(xe)) {
+ ret = -ENODATA;
+ goto runtime_exit;
+ }
scoped_guard(mutex, &xe->pmt.lock) {
xe->soc_remapper.set_telem_region(xe, CRI_IDX_TELEM_DISCOVERY);
@@ -441,6 +513,7 @@ static int xe_pmt_write_reg(struct device *dev, u32 guid, u32 reg, u32 offset)
writel(reg, disc_addr);
}
+runtime_exit:
xe_pm_runtime_put(xe);
drm_dev_exit(idx);
@@ -476,6 +549,28 @@ static enum xe_vsec get_platform_info(struct xe_device *xe)
return vsec_platforms[xe->info.platform];
}
+static void cri_late_bind_probe(struct xe_device *xe)
+{
+ struct intel_vsec_platform_info *info;
+ struct device *dev = xe->drm.dev;
+ enum xe_vsec platform;
+
+ platform = get_platform_info(xe);
+ if (platform != XE_VSEC_CRI)
+ return;
+
+ info = &xe_vsec_info[platform];
+ if (!info->headers)
+ return;
+
+ guard(mutex)(&xe->pmt.lock);
+
+ info->priv_data = &xe_cri_pmt_cb;
+ xe->soc_remapper.set_telem_region(xe, CRI_IDX_TELEM_DISCOVERY);
+
+ intel_vsec_register(dev, info);
+}
+
/**
* xe_vsec_init - Initialize resources and add intel_vsec auxiliary
* interface
@@ -503,12 +598,24 @@ void xe_vsec_init(struct xe_device *xe)
case XE_VSEC_CRI:
xe->pmt.base_offset = CRI_PMT_OFFSET;
+
+ xe->pmt.retry_count = 0;
+ INIT_DELAYED_WORK(&xe->pmt.work, cri_late_bind_probe_work);
+
+ xe_pm_runtime_get_noresume(xe);
+ if (!xe_sysctrl_is_oobmsm_fw_ready(xe)) {
+ queue_delayed_work(system_freezable_wq, &xe->pmt.work,
+ msecs_to_jiffies(VSEC_LATE_BIND_DELAY_MSEC));
+ return;
+ }
+
info->priv_data = &xe_cri_pmt_cb;
xe->soc_remapper.set_telem_region(xe, CRI_IDX_TELEM_DISCOVERY);
break;
default:
- break;
+ drm_err(&xe->drm, "Unsupported platform: %u\n", platform);
+ return;
}
/*
@@ -516,5 +623,22 @@ void xe_vsec_init(struct xe_device *xe)
* resources.
*/
intel_vsec_register(dev, info);
+
+ if (platform == XE_VSEC_CRI)
+ xe_pm_runtime_put(xe);
+}
+
+/**
+ * xe_vsec_remove - cleanup any outstanding resources
+ * @xe: valid xe instance
+ */
+void xe_vsec_remove(struct xe_device *xe)
+{
+ /* Cleanup on Crescent Isle */
+ if (xe->info.platform == XE_CRESCENTISLAND &&
+ xe->pmt.base_offset == CRI_PMT_OFFSET &&
+ disable_delayed_work_sync(&xe->pmt.work))
+ xe_pm_runtime_put(xe);
+
}
MODULE_IMPORT_NS("INTEL_VSEC");
diff --git a/drivers/gpu/drm/xe/xe_vsec.h b/drivers/gpu/drm/xe/xe_vsec.h
index a25b4e6e681b..e925dba4158b 100644
--- a/drivers/gpu/drm/xe/xe_vsec.h
+++ b/drivers/gpu/drm/xe/xe_vsec.h
@@ -10,6 +10,7 @@ struct device;
struct xe_device;
void xe_vsec_init(struct xe_device *xe);
+void xe_vsec_remove(struct xe_device *xe);
int xe_pmt_telem_read(struct device *dev, u32 guid, u64 *data, loff_t user_offset, u32 count);
#endif
--
2.43.0
next prev parent reply other threads:[~2026-11-16 15:07 UTC|newest]
Thread overview: 26+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-11-16 15:06 [PATCH v16 00/17] Crescent Island PMT support Michael J. Ruhl
2026-11-16 15:06 ` [PATCH v16 01/17] drm/xe/vsec: VSEC requires soc-remapper Michael J. Ruhl
2026-11-16 15:06 ` [PATCH v16 02/17] drm/xe/vsec: Do not register BMG PMT for VF Michael J. Ruhl
2026-11-16 15:06 ` [PATCH v16 03/17] drm/xe/vsec: Correct locking order Michael J. Ruhl
2026-11-16 15:06 ` [PATCH v16 04/17] drm/xe/vsec: Use correct pm state get Michael J. Ruhl
2026-11-16 15:06 ` [PATCH v16 05/17] drm/xe/vsec: Add DOC text for VSEC Michael J. Ruhl
2026-11-16 15:06 ` [PATCH v16 06/17] drm/xe/vsec: Support possible hotplug exit Michael J. Ruhl
2026-11-16 15:06 ` [PATCH v16 07/17] drm/xe/vsec: Refactor BattleMage PMT defines Michael J. Ruhl
2026-11-16 15:06 ` [PATCH v16 08/17] drm/xe/vsec: Update VSEC probe order Michael J. Ruhl
2026-11-16 15:06 ` [PATCH v16 09/17] drm/xe/vsec: Add base_offset to allow for more flexibilty Michael J. Ruhl
2026-11-16 15:06 ` [PATCH v16 10/17] drm/xe/vsec: Support Crescent Island PMT Michael J. Ruhl
2026-11-16 15:07 ` [PATCH v16 11/17] drm/xe/vsec: Crescent Island PMT decode Michael J. Ruhl
2026-11-16 15:07 ` [PATCH v16 12/17] drm/xe/vsec: Crescent Island PMT callbacks Michael J. Ruhl
2026-11-16 15:07 ` Michael J. Ruhl [this message]
2026-11-16 15:39 ` [PATCH v16 13/17] drm/xe/vsec: Support late bind fw information sashiko-bot
2026-11-16 16:35 ` Ruhl, Michael J
2026-11-16 15:07 ` [PATCH v16 14/17] drm/xe/vsec: Add PMT GUID internal access Michael J. Ruhl
2026-11-16 15:31 ` sashiko-bot
2026-11-16 16:39 ` Ruhl, Michael J
2026-11-16 15:07 ` [PATCH v16 15/17] drm/xe/vsec: Update PMT " Michael J. Ruhl
2026-11-16 15:07 ` [PATCH v16 16/17] drm/xe/vsec: Refactor platform check Michael J. Ruhl
2026-11-16 15:07 ` [PATCH v16 17/17] drm/xe/vsec: Support survivability mode for CRI Michael J. Ruhl
2026-11-16 18:36 ` ✗ CI.checkpatch: warning for Crescent Island PMT support (rev18) Patchwork
2026-11-16 18:38 ` ✓ CI.KUnit: success " Patchwork
2026-11-16 19:10 ` ✓ Xe.CI.BAT: " Patchwork
2026-11-17 5:52 ` ✗ Xe.CI.FULL: failure " Patchwork
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=20261116150649.368686-32-michael.j.ruhl@intel.com \
--to=michael.j.ruhl@intel.com \
--cc=airlied@gmail.com \
--cc=anoop.c.vijay@intel.com \
--cc=badal.nilawar@intel.com \
--cc=david.e.box@linux.intel.com \
--cc=intel-xe@lists.freedesktop.org \
--cc=james.ausmus@intel.com \
--cc=matthew.brost@intel.com \
--cc=matthew.d.roper@intel.com \
--cc=rodrigo.vivi@intel.com \
--cc=simona@ffwll.ch \
--cc=thomas.hellstrom@linux.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.