Intel-XE Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Matthew Brost <matthew.brost@intel.com>
To: intel-xe@lists.freedesktop.org
Subject: [PATCH 10/28] drm/xe/vf: Add xe_gt_sriov_vf_recovery_inprogress helper
Date: Tue, 16 Sep 2025 20:45:57 -0700	[thread overview]
Message-ID: <20250917034615.3977603-11-matthew.brost@intel.com> (raw)
In-Reply-To: <20250917034615.3977603-1-matthew.brost@intel.com>

Add xe_gt_sriov_vf_recovery_inprogress helper.

This helper serves as the singular point to determine whether a VF
post-migration recovery is currently in progress. Expected callers
include the GuC CT layer and the GuC submission layer. Atomically
visable as soon as vCPU are unhalted until VF recovery completes.

Signed-off-by: Matthew Brost <matthew.brost@intel.com>
---
 drivers/gpu/drm/xe/xe_gt_sriov_vf.c       | 17 ++++++++
 drivers/gpu/drm/xe/xe_gt_sriov_vf.h       |  2 +
 drivers/gpu/drm/xe/xe_gt_sriov_vf_types.h | 10 +++++
 drivers/gpu/drm/xe/xe_memirq.c            | 48 ++++++++++++++++++++++-
 drivers/gpu/drm/xe/xe_memirq.h            |  3 ++
 5 files changed, 79 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_vf.c b/drivers/gpu/drm/xe/xe_gt_sriov_vf.c
index 016c867e5e2b..c9d0e32e7a15 100644
--- a/drivers/gpu/drm/xe/xe_gt_sriov_vf.c
+++ b/drivers/gpu/drm/xe/xe_gt_sriov_vf.c
@@ -26,6 +26,7 @@
 #include "xe_guc_hxg_helpers.h"
 #include "xe_guc_relay.h"
 #include "xe_lrc.h"
+#include "xe_memirq.h"
 #include "xe_mmio.h"
 #include "xe_sriov.h"
 #include "xe_sriov_vf.h"
@@ -828,6 +829,7 @@ void xe_gt_sriov_vf_migrated_event_handler(struct xe_gt *gt)
 	struct xe_device *xe = gt_to_xe(gt);
 
 	xe_gt_assert(gt, IS_SRIOV_VF(xe));
+	xe_gt_assert(gt, xe_gt_sriov_vf_recovery_inprogress(gt));
 
 	set_bit(gt->info.id, &xe->sriov.vf.migration.gt_flags);
 	/*
@@ -1172,3 +1174,18 @@ void xe_gt_sriov_vf_print_version(struct xe_gt *gt, struct drm_printer *p)
 	drm_printf(p, "\thandshake:\t%u.%u\n",
 		   pf_version->major, pf_version->minor);
 }
+
+/**
+ * xe_gt_sriov_vf_recovery_inprogress() - VF post migration recovery in progress
+ * @gt: the &xe_gt
+ *
+ * Return: True if VF post migration recovery in progress, False otherwise
+ */
+bool xe_gt_sriov_vf_recovery_inprogress(struct xe_gt *gt)
+{
+	struct xe_memirq *memirq = &gt_to_tile(gt)->memirq;
+
+	return IS_SRIOV_VF(gt_to_xe(gt)) &&
+		(xe_memirq_vf_recovery_irq_pending(memirq, &gt->uc.guc) ||
+		 READ_ONCE(gt->sriov.vf.migration.recovery_inprogress));
+}
diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_vf.h b/drivers/gpu/drm/xe/xe_gt_sriov_vf.h
index 0af1dc769fe0..bb5f8eace19b 100644
--- a/drivers/gpu/drm/xe/xe_gt_sriov_vf.h
+++ b/drivers/gpu/drm/xe/xe_gt_sriov_vf.h
@@ -25,6 +25,8 @@ void xe_gt_sriov_vf_default_lrcs_hwsp_rebase(struct xe_gt *gt);
 int xe_gt_sriov_vf_notify_resfix_done(struct xe_gt *gt);
 void xe_gt_sriov_vf_migrated_event_handler(struct xe_gt *gt);
 
+bool xe_gt_sriov_vf_recovery_inprogress(struct xe_gt *gt);
+
 u32 xe_gt_sriov_vf_gmdid(struct xe_gt *gt);
 u16 xe_gt_sriov_vf_guc_ids(struct xe_gt *gt);
 u64 xe_gt_sriov_vf_lmem(struct xe_gt *gt);
diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_vf_types.h b/drivers/gpu/drm/xe/xe_gt_sriov_vf_types.h
index d95857bd789b..7b10b8e1e10e 100644
--- a/drivers/gpu/drm/xe/xe_gt_sriov_vf_types.h
+++ b/drivers/gpu/drm/xe/xe_gt_sriov_vf_types.h
@@ -49,6 +49,14 @@ struct xe_gt_sriov_vf_runtime {
 	} *regs;
 };
 
+/**
+ * xe_gt_sriov_vf_migration - VF migration data.
+ */
+struct xe_gt_sriov_vf_migration {
+	/** @recovery_inprogress: VF post migration recovery in progress */
+	bool recovery_inprogress;
+};
+
 /**
  * struct xe_gt_sriov_vf - GT level VF virtualization data.
  */
@@ -61,6 +69,8 @@ struct xe_gt_sriov_vf {
 	struct xe_gt_sriov_vf_selfconfig self_config;
 	/** @runtime: runtime data retrieved from the PF. */
 	struct xe_gt_sriov_vf_runtime runtime;
+	/** @migration: migration data for the VF. */
+	struct xe_gt_sriov_vf_migration migration;
 };
 
 #endif
diff --git a/drivers/gpu/drm/xe/xe_memirq.c b/drivers/gpu/drm/xe/xe_memirq.c
index 49c45ec3e83c..94d5d6859aab 100644
--- a/drivers/gpu/drm/xe/xe_memirq.c
+++ b/drivers/gpu/drm/xe/xe_memirq.c
@@ -398,6 +398,23 @@ void xe_memirq_postinstall(struct xe_memirq *memirq)
 		memirq_set_enable(memirq, true);
 }
 
+static bool memirq_received_noclear(struct xe_memirq *memirq,
+				    struct iosys_map *vector,
+				    u16 offset, const char *name)
+{
+	u8 value;
+
+	value = iosys_map_rd(vector, offset, u8);
+	if (value) {
+		if (value != 0xff)
+			memirq_err_ratelimited(memirq,
+					       "Unexpected memirq value %#x from %s at %u\n",
+					       value, name, offset);
+	}
+
+	return value;
+}
+
 static bool memirq_received(struct xe_memirq *memirq, struct iosys_map *vector,
 			    u16 offset, const char *name)
 {
@@ -434,8 +451,16 @@ static void memirq_dispatch_guc(struct xe_memirq *memirq, struct iosys_map *stat
 	if (memirq_received(memirq, status, ilog2(GUC_INTR_GUC2HOST), name))
 		xe_guc_irq_handler(guc, GUC_INTR_GUC2HOST);
 
-	if (memirq_received(memirq, status, ilog2(GUC_INTR_SW_INT_0), name))
+	/*
+	 * We must wait to perform the clear operation until after
+	 * xe_gt_sriov_vf_start_migration_recovery() runs, to avoid race
+	 * conditions where xe_gt_sriov_vf_recovery_inprogress() returns false.
+	 */
+	if (memirq_received_noclear(memirq, status, ilog2(GUC_INTR_SW_INT_0),
+				    name)) {
 		xe_guc_irq_handler(guc, GUC_INTR_SW_INT_0);
+		iosys_map_wr(status, ilog2(GUC_INTR_SW_INT_0), u8, 0x00);
+	}
 }
 
 /**
@@ -460,6 +485,27 @@ void xe_memirq_hwe_handler(struct xe_memirq *memirq, struct xe_hw_engine *hwe)
 	}
 }
 
+/**
+ * xe_memirq_vf_recovery_irq_pending() - VF recovery IRQ is pending
+ * @memirq: the &xe_memirq
+ * @guc: the &xe_guc to check for IRQ
+ *
+ * Return: True if VF recovery IRQ is pending on @guc, False otherwise
+ */
+bool xe_memirq_vf_recovery_irq_pending(struct xe_memirq *memirq,
+				       struct xe_guc *guc)
+{
+	struct xe_gt *gt = guc_to_gt(guc);
+	struct iosys_map map;
+
+	if (xe_gt_is_media_type(gt))
+		map = IOSYS_MAP_INIT_OFFSET(&memirq->status, ilog2(INTR_MGUC) * SZ_16);
+	else
+		map = IOSYS_MAP_INIT_OFFSET(&memirq->status, ilog2(INTR_GUC) * SZ_16);
+
+	return iosys_map_rd(&map, ilog2(GUC_INTR_SW_INT_0), u8);
+}
+
 /**
  * xe_memirq_handler - The `Memory Based Interrupts`_ Handler.
  * @memirq: the &xe_memirq
diff --git a/drivers/gpu/drm/xe/xe_memirq.h b/drivers/gpu/drm/xe/xe_memirq.h
index 06130650e9d6..476b8cba179d 100644
--- a/drivers/gpu/drm/xe/xe_memirq.h
+++ b/drivers/gpu/drm/xe/xe_memirq.h
@@ -25,4 +25,7 @@ void xe_memirq_handler(struct xe_memirq *memirq);
 
 int xe_memirq_init_guc(struct xe_memirq *memirq, struct xe_guc *guc);
 
+bool xe_memirq_vf_recovery_irq_pending(struct xe_memirq *memirq,
+				       struct xe_guc *guc);
+
 #endif
-- 
2.34.1


  parent reply	other threads:[~2025-09-17  3:46 UTC|newest]

Thread overview: 33+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-09-17  3:45 [PATCH 00/28] VF migration redesign Matthew Brost
2025-09-17  3:45 ` [PATCH 01/28] drm/xe/vf: Lock querying GGTT config during driver init Matthew Brost
2025-09-17  3:45 ` [PATCH 02/28] Revert "drm/xe/vf: Rebase exec queue parallel commands during migration recovery" Matthew Brost
2025-09-17  3:45 ` [PATCH 03/28] Revert "drm/xe/vf: Post migration, repopulate ring area for pending request" Matthew Brost
2025-09-17  3:45 ` [PATCH 04/28] Revert "drm/xe/vf: Fixup CTB send buffer messages after migration" Matthew Brost
2025-09-17  3:45 ` [PATCH 05/28] drm/xe: Save off position in ring in which a job was programmed Matthew Brost
2025-09-17  3:45 ` [PATCH 06/28] drm/xe/guc: Track pending-enable source in submission state Matthew Brost
2025-09-17  3:45 ` [PATCH 07/28] drm/xe: Track LR jobs in DRM scheduler pending list Matthew Brost
2025-09-17  3:45 ` [PATCH 08/28] drm/xe: Don't change LRC ring head on job resubmission Matthew Brost
2025-09-17  3:45 ` [PATCH 09/28] drm/xe/guc: Document GuC submission backend Matthew Brost
2025-09-17  3:45 ` Matthew Brost [this message]
2025-09-17  3:45 ` [PATCH 11/28] drm/xe/vf: Make VF recovery run on per-GT worker Matthew Brost
2025-09-17  3:45 ` [PATCH 12/28] drm/xe/vf: Abort H2G sends during VF post-migration recovery Matthew Brost
2025-09-17  3:46 ` [PATCH 13/28] drm/xe/vf: Remove memory allocations from VF post migration recovery Matthew Brost
2025-09-17  3:46 ` [PATCH 14/28] drm/xe/vf: Close multi-GT GGTT shift race Matthew Brost
2025-09-17  3:46 ` [PATCH 15/28] drm/xe/vf: Teardown VF post migration worker on driver unload Matthew Brost
2025-09-17  3:46 ` [PATCH 16/28] drm/xe/vf: Don't allow GT reset to be queued during VF post migration recovery Matthew Brost
2025-09-17  3:46 ` [PATCH 17/28] drm/xe/vf: Wakeup in GuC backend on " Matthew Brost
2025-09-17  3:46 ` [PATCH 18/28] drm/xe/vf: Extra debug on GGTT shift Matthew Brost
2025-09-17  3:46 ` [PATCH 19/28] drm/xe/vf: Use GUC_HXG_TYPE_EVENT for GuC context register Matthew Brost
2025-09-17  3:46 ` [PATCH 20/28] drm/xe/vf: Stop and flush CTs in VF post migration recovery Matthew Brost
2025-09-17  3:46 ` [PATCH 21/28] drm/xe/vf: Reset TLB invalidations during " Matthew Brost
2025-09-17  3:46 ` [PATCH 22/28] drm/xe/vf: Kickstart after resfix in " Matthew Brost
2025-09-17  3:46 ` [PATCH 23/28] drm/xe/vf: Start CTs before resfix " Matthew Brost
2025-09-17  3:46 ` [PATCH 24/28] drm/xe/vf: Abort VF post migration recovery on failure Matthew Brost
2025-09-17  3:46 ` [PATCH 25/28] drm/xe/vf: Replay GuC submission state on pause / unpause Matthew Brost
2025-09-17  3:46 ` [PATCH 26/28] drm/xe: Move queue init before LRC creation Matthew Brost
2025-09-17  3:46 ` [PATCH 27/28] drm/xe/vf: Add debug prints for GuC replaying state during VF recovery Matthew Brost
2025-09-17  3:46 ` [PATCH 28/28] drm/xe/vf: Workaround for race condition in GuC firmware during VF pause Matthew Brost
2025-09-17  3:55 ` ✗ CI.checkpatch: warning for VF migration redesign Patchwork
2025-09-17  3:56 ` ✓ CI.KUnit: success " Patchwork
2025-09-17  4:39 ` ✗ Xe.CI.BAT: failure " Patchwork
2025-09-17  6:38 ` ✗ Xe.CI.Full: " 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=20250917034615.3977603-11-matthew.brost@intel.com \
    --to=matthew.brost@intel.com \
    --cc=intel-xe@lists.freedesktop.org \
    /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