X86 platform drivers
 help / color / mirror / Atom feed
From: "Michael J. Ruhl" <michael.j.ruhl@intel.com>
To: platform-driver-x86@vger.kernel.org,
	intel-xe@lists.freedesktop.org, hansg@kernel.org,
	ilpo.jarvinen@linux.intel.com, 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,
	karthik.poosa@intel.com
Subject: [PATCH v4 15/18] drm/xe/vsec: Support late bind fw information
Date: Tue,  1 Sep 2026 12:27:50 -0700	[thread overview]
Message-ID: <20260901192736.626777-35-michael.j.ruhl@intel.com> (raw)
In-Reply-To: <20260901192736.626777-20-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.

Signed-off-by: Michael J. Ruhl <michael.j.ruhl@intel.com>
---
 drivers/gpu/drm/xe/xe_device.c       |   4 +-
 drivers/gpu/drm/xe/xe_device_types.h |   5 +
 drivers/gpu/drm/xe/xe_vsec.c         | 136 +++++++++++++++++++++++++--
 drivers/gpu/drm/xe/xe_vsec.h         |   2 +-
 4 files changed, 138 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
index 396d02eb2af8..0dffabed2e99 100644
--- a/drivers/gpu/drm/xe/xe_device.c
+++ b/drivers/gpu/drm/xe/xe_device.c
@@ -1140,7 +1140,9 @@ 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..69e052ac5a82 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>
@@ -468,6 +469,10 @@ 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 e58fea788ace..8284977377bd 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"
@@ -162,7 +164,15 @@ enum capability {
 	WATCHER,
 };
 
-static int xe_guid_decode(u32 guid, int *index, u32 *offset)
+/*
+ * 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);
 	u32 cap_type  = FIELD_GET(GUID_CAP_TYPE, guid);
@@ -270,6 +280,48 @@ 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_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
@@ -316,6 +368,11 @@ 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 */
@@ -325,6 +382,7 @@ 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:
@@ -367,6 +425,10 @@ 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;
+	}
 	mutex_lock(&xe->pmt.lock);
 
 	xe->soc_remapper.set_telem_region(xe, CRI_IDX_TELEM_DISCOVERY);
@@ -374,6 +436,8 @@ 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:
@@ -404,6 +468,10 @@ 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;
+	}
 	mutex_lock(&xe->pmt.lock);
 
 	xe->soc_remapper.set_telem_region(xe, CRI_IDX_TELEM_DISCOVERY);
@@ -411,6 +479,8 @@ static int xe_pmt_write_reg(struct device *dev, u32 guid, u32 reg, u32 offset)
 	memcpy_toio(disc_addr, &reg, sizeof(reg));
 
 	mutex_unlock(&xe->pmt.lock);
+
+runtime_exit:
 	xe_pm_runtime_put(xe);
 
 dev_exit:
@@ -442,12 +512,44 @@ 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 the queued work is canceled, the runtime reference needs to be
+	 * released here.
+	 */
+	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;
@@ -455,30 +557,45 @@ 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 (IS_SRIOV_VF(xe))
-			return;
+			return 0;
 		xe->pmt.base_offset = BMG_TELEMETRY_OFFSET;
 		info->priv_data = &xe_bmg_pmt_cb;
 		break;
 
 	case XE_VSEC_CRI:
 		if (IS_SRIOV_VF(xe))
-			return;
+			return 0;
+
 		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_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;
 	}
 
 	/*
@@ -486,5 +603,10 @@ 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


  parent reply	other threads:[~2026-09-01 19:28 UTC|newest]

Thread overview: 24+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-09-01 19:27 [PATCH v4 00/18] Crescent Island PMT support Michael J. Ruhl
2026-09-01 19:27 ` [PATCH v4 01/18] platform/x86/intel/pmt: complete pcidev to device update Michael J. Ruhl
2026-09-01 19:27 ` [PATCH v4 02/18] platform/x86/intel/pmt: refactor rmw with a return value Michael J. Ruhl
2026-09-02  9:05   ` Ilpo Järvinen
2026-09-02  9:07   ` Ilpo Järvinen
2026-09-01 19:27 ` [PATCH v4 03/18] platform/x86/intel/pmt: refactor rc " Michael J. Ruhl
2026-09-02  9:08   ` Ilpo Järvinen
2026-09-01 19:27 ` [PATCH v4 04/18] platform/x86/intel/pmt: Add register access callbacks Michael J. Ruhl
2026-09-01 19:27 ` [PATCH v4 05/18] platform/x86/intel/pmt: Add helpers for callback info Michael J. Ruhl
2026-09-02  9:10   ` Ilpo Järvinen
2026-09-01 19:27 ` [PATCH v4 06/18] platform/x86/intel/pmt: Do not remap when using callbacks Michael J. Ruhl
2026-09-02  9:18   ` Ilpo Järvinen
2026-09-01 19:27 ` [PATCH v4 07/18] drm/xe/vsec: Do not register BMG PMT for VF Michael J. Ruhl
2026-09-01 19:27 ` [PATCH v4 08/18] drm/xe/vsec: Correct locking order Michael J. Ruhl
2026-09-01 19:27 ` [PATCH v4 09/18] drm/xe/vsec: Use correct pm state get Michael J. Ruhl
2026-09-01 19:27 ` [PATCH v4 10/18] drm/xe/vsec: Support possible hotplug exit Michael J. Ruhl
2026-09-01 19:27 ` [PATCH v4 11/18] drm/xe/vsec: Support Crescent Island PMT Michael J. Ruhl
2026-09-01 19:27 ` [PATCH v4 12/18] drm/xe/vsec: Refactor BattleMage PMT defines Michael J. Ruhl
2026-09-01 19:27 ` [PATCH v4 13/18] drm/xe/vsec: Crescent Island PMT decode Michael J. Ruhl
2026-09-01 19:27 ` [PATCH v4 14/18] drm/xe/vsec: Crescent Island PMT callbacks Michael J. Ruhl
2026-09-01 19:27 ` Michael J. Ruhl [this message]
2026-09-01 19:27 ` [PATCH v4 16/18] drm/xe/vsec: Add PMT GUID internal access Michael J. Ruhl
2026-09-01 19:27 ` [PATCH v4 17/18] drm/xe/vsec: Update PMT " Michael J. Ruhl
2026-09-01 19:27 ` [PATCH v4 18/18] drm/xe/vsec: Refactor platform check Michael J. Ruhl

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=20260901192736.626777-35-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=hansg@kernel.org \
    --cc=ilpo.jarvinen@linux.intel.com \
    --cc=intel-xe@lists.freedesktop.org \
    --cc=james.ausmus@intel.com \
    --cc=karthik.poosa@intel.com \
    --cc=matthew.brost@intel.com \
    --cc=matthew.d.roper@intel.com \
    --cc=platform-driver-x86@vger.kernel.org \
    --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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox