RE: [PATCH v2 09/10] drm/xe/vsec: Support late bind fw information

>-----Original Message-----
>From: Intel-xe <[email protected]> On Behalf Of Michael
>J. Ruhl
>Sent: Wednesday, August 12, 2026 3:38 PM
>To: [email protected]; [email protected];
>[email protected]; [email protected]; Brost, Matthew
><[email protected]>; Vivi, Rodrigo <[email protected]>;
>[email protected]; [email protected]; [email protected];
>[email protected]; Vijay, Anoop C <[email protected]>;
>Nilawar, Badal <[email protected]>; Roper, Matthew D
><[email protected]>; Ausmus, James <[email protected]>
>Subject: [PATCH v2 09/10] drm/xe/vsec: Support late bind fw information
>
>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.
>
>Signed-off-by: Michael J. Ruhl <[email protected]>
>---
> drivers/gpu/drm/xe/xe_device.c       |   4 +-
> drivers/gpu/drm/xe/xe_device_types.h |   4 +
> drivers/gpu/drm/xe/xe_vsec.c         | 142 +++++++++++++++++++++++++--
> drivers/gpu/drm/xe/xe_vsec.h         |   2 +-
> 4 files changed, 144 insertions(+), 8 deletions(-)
>
>diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
>index 71111ad32465..df6716a975fb 100644
>--- a/drivers/gpu/drm/xe/xe_device.c
>+++ b/drivers/gpu/drm/xe/xe_device.c
>@@ -1139,7 +1139,9 @@ int xe_device_probe(struct xe_device *xe)
> 	for_each_gt(gt, xe, id)
> 		xe_gt_sanitize_freq(gt);
>
>-	xe_vsec_init(xe);
>+	err = xe_vsec_init(xe);
>+	if (err)
>+		goto err_unregister_display;
>
> 	err = xe_sriov_init_late(xe);
> 	if (err)
>diff --git a/drivers/gpu/drm/xe/xe_device_types.h
>b/drivers/gpu/drm/xe/xe_device_types.h
>index 3f1a70813a99..5d9e6e66c665 100644
>--- a/drivers/gpu/drm/xe/xe_device_types.h
>+++ b/drivers/gpu/drm/xe/xe_device_types.h
>@@ -468,6 +468,10 @@ 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 578d59048b39..bed5103dac19 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>
>@@ -17,6 +18,7 @@
> #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"
>@@ -162,6 +164,14 @@ 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);
>@@ -272,6 +282,56 @@ static int xe_guid_decode(u32 guid, int *index, u32
>*offset)
> 	return -ENODEV;
> }
>
>+#define WAITING_FOR_SYCTLR
>+#ifdef WAITING_FOR_SYCTLR
>+static bool xe_is_oobmsm_fw_ready(struct xe_device *xe)
>+{
>+	return true;
>+}
>+#endif
>+
>+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_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 (!schedule_delayed_work(&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_is_oobmsm_fw_ready(xe))
>+			return true;
>+
>+		msleep(VSEC_LATE_BIND_DELAY_MSEC);
>+	}
>+
>+	drm_warn(&xe->drm, "Late Binding failed to complete\n");
>+
>+	return false;
>+}
>+
> /*
>  * xe_pmt_telem_read is a callback API.  I.e this can be accessed external to
>  * XE driver (PMT driver scope).  Because of this, DRM hotplug needs to be
>@@ -318,6 +378,11 @@ 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;
>+	}
>+
> 	mutex_lock(&xe->pmt.lock);
>
> 	/* set SoC re-mapper index register based on GUID memory region */
>@@ -327,6 +392,7 @@ int xe_pmt_telem_read(struct device *dev, u32 guid,
>u64 *data, loff_t user_offse
>
> 	mutex_unlock(&xe->pmt.lock);
>
>+runtime_exit:
> 	xe_pm_runtime_put(xe);
>
> dev_exit:
>@@ -374,6 +440,10 @@ static int xe_pmt_read_reg(struct device *dev, u32
>guid, u32 *reg, u32 offset)
> 	disc_addr += CRI_DISCOVERY_OFFSET + inst + offset;
>
> 	xe_pm_runtime_get(xe);
>+	if (!wait_for_fw(xe)) {
>+		ret = -ENODATA;
>+		goto runtime_exit;
>+	}
> 	mutex_lock(&xe->pmt.lock);
>
> 	xe->soc_remapper.set_telem_region(xe, CRI_IDX_TELEM_DISCOVERY);
>@@ -381,6 +451,8 @@ static int xe_pmt_read_reg(struct device *dev, u32
>guid, u32 *reg, u32 offset)
> 	memcpy_fromio(reg, disc_addr, sizeof(*reg));
>
> 	mutex_unlock(&xe->pmt.lock);
>+
>+runtime_exit:
> 	xe_pm_runtime_put(xe);
>
> dev_exit:
>@@ -416,6 +488,10 @@ static int xe_pmt_write_reg(struct device *dev, u32
>guid, u32 reg, u32 offset)
> 	disc_addr += CRI_DISCOVERY_OFFSET + inst + offset;
>
> 	xe_pm_runtime_get(xe);
>+	if (!wait_for_fw(xe)) {
>+		ret = -ENODATA;
>+		goto runtime_exit;
>+	}
> 	mutex_lock(&xe->pmt.lock);
>
> 	xe->soc_remapper.set_telem_region(xe, CRI_IDX_TELEM_DISCOVERY);
>@@ -425,6 +501,9 @@ static int xe_pmt_write_reg(struct device *dev, u32
>guid, u32 reg, u32 offset)
> 	mutex_unlock(&xe->pmt.lock);
> 	xe_pm_runtime_put(xe);

The above _put should have been removed.

This will be fixed.

m

>+runtime_exit:
>+	xe_pm_runtime_put(xe);
>+
> dev_exit:
> 	drm_dev_exit(idx);
>
>@@ -454,12 +533,44 @@ 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;
>+
>+	info->priv_data = &xe_cri_pmt_cb;
>+	xe->soc_remapper.set_telem_region(xe, CRI_IDX_TELEM_DISCOVERY);
>+
>+	intel_vsec_register(dev, info);
>+}
>+
>+static void vsec_disable_late_bind_work(void *arg)
>+{
>+	struct xe_device *xe = arg;
>+
>+	/*
>+	 * If was work was cancelled while it was still pending, we need to
>+	 * take care of releasing the runtime reference
>+	 */
>+	if (disable_delayed_work_sync(&xe->pmt.work))
>+		xe_pm_runtime_put(xe);
>+}
>+
> /**
>  * xe_vsec_init - Initialize resources and add intel_vsec auxiliary
>  * interface
>  * @xe: valid xe instance
>  */
>-void xe_vsec_init(struct xe_device *xe)
>+int xe_vsec_init(struct xe_device *xe)
> {
> 	struct intel_vsec_platform_info *info;
> 	struct device *dev = xe->drm.dev;
>@@ -467,30 +578,44 @@ void xe_vsec_init(struct xe_device *xe)
>
> 	platform = get_platform_info(xe);
> 	if (platform == XE_VSEC_UNKNOWN)
>-		return;
>+		return 0;
>
> 	info = &xe_vsec_info[platform];
> 	if (!info->headers)
>-		return;
>+		return 0;
>
> 	switch (platform) {
> 	case XE_VSEC_BMG:
> 		if (!xe->soc_remapper.set_telem_region)
>-			return;
>+			return 0;
> 		xe->pmt.base_offset = BMG_TELEMETRY_OFFSET;
> 		info->priv_data = &xe_bmg_pmt_cb;
> 		break;
>
> 	case XE_VSEC_CRI:
> 		if (!xe->soc_remapper.set_telem_region)
>-			return;
>+			return 0;
> 		xe->pmt.base_offset = CRI_TELEMETRY_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_is_oobmsm_fw_ready(xe)) {
>+			schedule_delayed_work(&xe->pmt.work,
>+
>msecs_to_jiffies(VSEC_LATE_BIND_DELAY_MSEC));
>+			return devm_add_action_or_reset(xe->drm.dev,
>+
>	vsec_disable_late_bind_work,
>+							xe);
>+		}
>+
> 		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 0;
> 	}
>
> 	/*
>@@ -498,5 +623,10 @@ void xe_vsec_init(struct xe_device *xe)
> 	 * resources.
> 	 */
> 	intel_vsec_register(dev, info);
>+
>+	if (platform == XE_VSEC_CRI)
>+		xe_pm_runtime_put(xe);
>+
>+	return 0;
> }
> 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..c4a1e2fc67d8 100644
>--- a/drivers/gpu/drm/xe/xe_vsec.h
>+++ b/drivers/gpu/drm/xe/xe_vsec.h
>@@ -9,7 +9,7 @@
> struct device;
> struct xe_device;
>
>-void xe_vsec_init(struct xe_device *xe);
>+int xe_vsec_init(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