Intel-XE Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Brian Nguyen <brian3.nguyen@intel.com>
To: intel-xe@lists.freedesktop.org
Cc: tejas.upadhyay@intel.com, matthew.brost@intel.com,
	shuicheng.lin@intel.com, stuart.summers@intel.com,
	Brian Nguyen <brian3.nguyen@intel.com>
Subject: [PATCH 03/11] drm/xe/xe_tlb_inval: Modify fence interface to support PPC flush
Date: Tue, 18 Nov 2025 17:05:44 +0800	[thread overview]
Message-ID: <20251118090552.246243-4-brian3.nguyen@intel.com> (raw)
In-Reply-To: <20251118090552.246243-1-brian3.nguyen@intel.com>

Allow for tlb_invalidation to configure when driver wants to flush the
Private Physical Cache (PPC) as a process of the tlb invalidation
process.

Default behavior is still to always flush the PPC but driver now has the
option to disable it.

Signed-off-by: Brian Nguyen <brian3.nguyen@intel.com>
---
 drivers/gpu/drm/xe/xe_guc_tlb_inval.c   | 11 +++++++----
 drivers/gpu/drm/xe/xe_tlb_inval.c       | 21 ++++++++++++++++++---
 drivers/gpu/drm/xe/xe_tlb_inval.h       |  5 +++--
 drivers/gpu/drm/xe/xe_tlb_inval_job.c   |  2 +-
 drivers/gpu/drm/xe/xe_tlb_inval_types.h |  5 ++++-
 drivers/gpu/drm/xe/xe_vm.c              |  4 ++--
 6 files changed, 35 insertions(+), 13 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_guc_tlb_inval.c b/drivers/gpu/drm/xe/xe_guc_tlb_inval.c
index cd126c53faab..c05709a5bc98 100644
--- a/drivers/gpu/drm/xe/xe_guc_tlb_inval.c
+++ b/drivers/gpu/drm/xe/xe_guc_tlb_inval.c
@@ -34,9 +34,12 @@ static int send_tlb_inval(struct xe_guc *guc, const u32 *action, int len)
 			      G2H_LEN_DW_TLB_INVALIDATE, 1);
 }
 
-#define MAKE_INVAL_OP(type)	((type << XE_GUC_TLB_INVAL_TYPE_SHIFT) | \
+#define MAKE_INVAL_OP_FLUSH(type, flush_cache)	((type << XE_GUC_TLB_INVAL_TYPE_SHIFT) | \
 		XE_GUC_TLB_INVAL_MODE_HEAVY << XE_GUC_TLB_INVAL_MODE_SHIFT | \
-		XE_GUC_TLB_INVAL_FLUSH_CACHE)
+		(flush_cache ? \
+		XE_GUC_TLB_INVAL_FLUSH_CACHE : 0))
+
+#define MAKE_INVAL_OP(type)	MAKE_INVAL_OP_FLUSH(type, true)
 
 static int send_tlb_inval_all(struct xe_tlb_inval *tlb_inval, u32 seqno)
 {
@@ -100,7 +103,7 @@ static int send_tlb_inval_ggtt(struct xe_tlb_inval *tlb_inval, u32 seqno)
 #define MAX_RANGE_TLB_INVALIDATION_LENGTH (rounddown_pow_of_two(ULONG_MAX))
 
 static int send_tlb_inval_ppgtt(struct xe_tlb_inval *tlb_inval, u32 seqno,
-				u64 start, u64 end, u32 asid)
+				u64 start, u64 end, u32 asid, bool flush_cache)
 {
 #define MAX_TLB_INVALIDATION_LEN	7
 	struct xe_guc *guc = tlb_inval->private;
@@ -154,7 +157,7 @@ static int send_tlb_inval_ppgtt(struct xe_tlb_inval *tlb_inval, u32 seqno,
 						    ilog2(SZ_2M) + 1)));
 		xe_gt_assert(gt, IS_ALIGNED(start, length));
 
-		action[len++] = MAKE_INVAL_OP(XE_GUC_TLB_INVAL_PAGE_SELECTIVE);
+		action[len++] = MAKE_INVAL_OP_FLUSH(XE_GUC_TLB_INVAL_PAGE_SELECTIVE, flush_cache);
 		action[len++] = asid;
 		action[len++] = lower_32_bits(start);
 		action[len++] = upper_32_bits(start);
diff --git a/drivers/gpu/drm/xe/xe_tlb_inval.c b/drivers/gpu/drm/xe/xe_tlb_inval.c
index 50f05d6b5672..de275759743c 100644
--- a/drivers/gpu/drm/xe/xe_tlb_inval.c
+++ b/drivers/gpu/drm/xe/xe_tlb_inval.c
@@ -324,10 +324,10 @@ int xe_tlb_inval_ggtt(struct xe_tlb_inval *tlb_inval)
  */
 int xe_tlb_inval_range(struct xe_tlb_inval *tlb_inval,
 		       struct xe_tlb_inval_fence *fence, u64 start, u64 end,
-		       u32 asid)
+		       u32 asid, bool flush_cache)
 {
 	return xe_tlb_inval_issue(tlb_inval, fence, tlb_inval->ops->ppgtt,
-				  start, end, asid);
+				  start, end, asid, flush_cache);
 }
 
 /**
@@ -343,7 +343,7 @@ void xe_tlb_inval_vm(struct xe_tlb_inval *tlb_inval, struct xe_vm *vm)
 	u64 range = 1ull << vm->xe->info.va_bits;
 
 	xe_tlb_inval_fence_init(tlb_inval, &fence, true);
-	xe_tlb_inval_range(tlb_inval, &fence, 0, range, vm->usm.asid);
+	xe_tlb_inval_range(tlb_inval, &fence, 0, range, vm->usm.asid, true);
 	xe_tlb_inval_fence_wait(&fence);
 }
 
@@ -420,6 +420,20 @@ static const struct dma_fence_ops inval_fence_ops = {
 	.get_timeline_name = xe_inval_fence_get_timeline_name,
 };
 
+/**
+ * xe_tlb_inval_fence_flush_cache - Control PPC flush at invalidation
+ * @fence: TLB inval fence
+ * @flush_cache: whether to perform PPC cache flush
+ *
+ * Helper function to modify the tlb_inval fence to control the PPC flush.
+ * Other components shouldn't modify fence directly.
+ */
+void xe_tlb_inval_fence_flush_cache(struct xe_tlb_inval_fence *fence,
+				    bool flush_cache)
+{
+	fence->flush_cache = flush_cache;
+}
+
 /**
  * xe_tlb_inval_fence_init() - Initialize TLB invalidation fence
  * @tlb_inval: TLB invalidation client
@@ -446,4 +460,5 @@ void xe_tlb_inval_fence_init(struct xe_tlb_inval *tlb_inval,
 	else
 		dma_fence_get(&fence->base);
 	fence->tlb_inval = tlb_inval;
+	fence->flush_cache = true;
 }
diff --git a/drivers/gpu/drm/xe/xe_tlb_inval.h b/drivers/gpu/drm/xe/xe_tlb_inval.h
index 9dbddc310eb9..b84ce3e6f294 100644
--- a/drivers/gpu/drm/xe/xe_tlb_inval.h
+++ b/drivers/gpu/drm/xe/xe_tlb_inval.h
@@ -24,8 +24,9 @@ int xe_tlb_inval_ggtt(struct xe_tlb_inval *tlb_inval);
 void xe_tlb_inval_vm(struct xe_tlb_inval *tlb_inval, struct xe_vm *vm);
 int xe_tlb_inval_range(struct xe_tlb_inval *tlb_inval,
 		       struct xe_tlb_inval_fence *fence,
-		       u64 start, u64 end, u32 asid);
-
+		       u64 start, u64 end, u32 asid, bool flush_cache);
+void xe_tlb_inval_fence_flush_cache(struct xe_tlb_inval_fence *fence,
+				    bool flush_cache);
 void xe_tlb_inval_fence_init(struct xe_tlb_inval *tlb_inval,
 			     struct xe_tlb_inval_fence *fence,
 			     bool stack);
diff --git a/drivers/gpu/drm/xe/xe_tlb_inval_job.c b/drivers/gpu/drm/xe/xe_tlb_inval_job.c
index 1ae0dec2cf31..6248f90323a9 100644
--- a/drivers/gpu/drm/xe/xe_tlb_inval_job.c
+++ b/drivers/gpu/drm/xe/xe_tlb_inval_job.c
@@ -49,7 +49,7 @@ static struct dma_fence *xe_tlb_inval_job_run(struct xe_dep_job *dep_job)
 		container_of(job->fence, typeof(*ifence), base);
 
 	xe_tlb_inval_range(job->tlb_inval, ifence, job->start,
-			   job->end, job->vm->usm.asid);
+			   job->end, job->vm->usm.asid, ifence->flush_cache);
 
 	return job->fence;
 }
diff --git a/drivers/gpu/drm/xe/xe_tlb_inval_types.h b/drivers/gpu/drm/xe/xe_tlb_inval_types.h
index 7a6967ce3b76..c3c3943fb07e 100644
--- a/drivers/gpu/drm/xe/xe_tlb_inval_types.h
+++ b/drivers/gpu/drm/xe/xe_tlb_inval_types.h
@@ -40,12 +40,13 @@ struct xe_tlb_inval_ops {
 	 * @start: Start address
 	 * @end: End address
 	 * @asid: Address space ID
+	 * @flush_cache: PPC flush control
 	 *
 	 * Return 0 on success, -ECANCELED if backend is mid-reset, error on
 	 * failure
 	 */
 	int (*ppgtt)(struct xe_tlb_inval *tlb_inval, u32 seqno, u64 start,
-		     u64 end, u32 asid);
+		     u64 end, u32 asid, bool flush_cache);
 
 	/**
 	 * @initialized: Backend is initialized
@@ -126,6 +127,8 @@ struct xe_tlb_inval_fence {
 	int seqno;
 	/** @inval_time: time of TLB invalidation */
 	ktime_t inval_time;
+	/** @flush_cache: bool for PPC flush, default is true */
+	bool flush_cache;
 };
 
 #endif
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index 7cac646bdf1c..5fb5226574c5 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -3907,7 +3907,7 @@ int xe_vm_range_tilemask_tlb_inval(struct xe_vm *vm, u64 start,
 
 		err = xe_tlb_inval_range(&tile->primary_gt->tlb_inval,
 					 &fence[fence_id], start, end,
-					 vm->usm.asid);
+					 vm->usm.asid, true);
 		if (err)
 			goto wait;
 		++fence_id;
@@ -3920,7 +3920,7 @@ int xe_vm_range_tilemask_tlb_inval(struct xe_vm *vm, u64 start,
 
 		err = xe_tlb_inval_range(&tile->media_gt->tlb_inval,
 					 &fence[fence_id], start, end,
-					 vm->usm.asid);
+					 vm->usm.asid, true);
 		if (err)
 			goto wait;
 		++fence_id;
-- 
2.51.2


  parent reply	other threads:[~2025-11-18  9:06 UTC|newest]

Thread overview: 51+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-11-18  9:05 [PATCH 00/11] Page Reclamation Support for Xe3p Platforms Brian Nguyen
2025-11-18  9:05 ` [PATCH 01/11] [DO, NOT, REVIEW] drm/xe: Do not forward invalid TLB invalidation seqnos to upper layers Brian Nguyen
2025-11-18  9:05 ` [PATCH 02/11] drm/xe: Reset tlb fence timeout on invalid seqno received Brian Nguyen
2025-11-21 17:23   ` Lin, Shuicheng
2025-11-22  1:53     ` Nguyen, Brian3
2025-11-22 18:25   ` Matthew Brost
2025-11-25 11:01     ` Nguyen, Brian3
2025-11-18  9:05 ` Brian Nguyen [this message]
2025-11-21 18:02   ` [PATCH 03/11] drm/xe/xe_tlb_inval: Modify fence interface to support PPC flush Lin, Shuicheng
2025-11-22  1:54     ` Nguyen, Brian3
2025-11-22 19:32   ` Matthew Brost
2025-11-25 11:07     ` Nguyen, Brian3
2025-11-18  9:05 ` [PATCH 04/11] drm/xe: Add page reclamation info to device info Brian Nguyen
2025-11-21 18:15   ` Lin, Shuicheng
2025-11-22 18:31   ` Matthew Brost
2025-11-18  9:05 ` [PATCH 05/11] drm/xe/guc: Add page reclamation interface to GuC Brian Nguyen
2025-11-21 18:32   ` Lin, Shuicheng
2025-11-22  1:56     ` Nguyen, Brian3
2025-11-22 18:39       ` Matthew Brost
2025-11-25 11:13         ` Nguyen, Brian3
2025-11-18  9:05 ` [PATCH 06/11] drm/xe: Create page reclaim list on unbind Brian Nguyen
2025-11-21 21:29   ` Lin, Shuicheng
2025-11-22  1:57     ` Nguyen, Brian3
2025-11-22 19:18   ` Matthew Brost
2025-11-25 11:18     ` Nguyen, Brian3
2025-11-25 18:34       ` Matthew Brost
2025-11-25 19:01         ` Nguyen, Brian3
2025-11-25 19:07           ` Matthew Brost
2025-11-25 19:46             ` Nguyen, Brian3
2025-11-25 22:35               ` Matthew Brost
2025-11-26  2:33                 ` Nguyen, Brian3
2025-11-18  9:05 ` [PATCH 07/11] drm/xe: Suballocate BO for page reclaim Brian Nguyen
2025-11-22 19:42   ` Matthew Brost
2025-11-25 11:20     ` Nguyen, Brian3
2025-11-18  9:05 ` [PATCH 08/11] drm/xe: Prep page reclaim in tlb inval job Brian Nguyen
2025-11-22 13:52   ` Michal Wajdeczko
2025-11-25 11:20     ` Nguyen, Brian3
2025-11-18  9:05 ` [PATCH 09/11] drm/xe: Append page reclamation action to tlb inval Brian Nguyen
2025-11-18  9:05 ` [PATCH 10/11] drm/xe: Optimize flushing of L2$ by skipping unnecessary page reclaim Brian Nguyen
2025-11-24 12:29   ` Matthew Auld
2025-11-25  6:12     ` Nguyen, Brian3
2025-11-25 11:48     ` Upadhyay, Tejas
2025-11-25 13:05       ` Upadhyay, Tejas
2025-11-18  9:05 ` [PATCH 11/11] drm/xe: Add debugfs support for page reclamation Brian Nguyen
2025-11-21 22:32   ` Lin, Shuicheng
2025-11-22  1:57     ` Nguyen, Brian3
2025-11-22 14:18   ` Michal Wajdeczko
2025-11-25 11:21     ` Nguyen, Brian3
2025-11-18  9:52 ` ✗ CI.checkpatch: warning for Page Reclamation Support for Xe3p Platforms Patchwork
2025-11-18  9:53 ` ✓ CI.KUnit: success " Patchwork
2025-11-18 13:02 ` ✗ 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=20251118090552.246243-4-brian3.nguyen@intel.com \
    --to=brian3.nguyen@intel.com \
    --cc=intel-xe@lists.freedesktop.org \
    --cc=matthew.brost@intel.com \
    --cc=shuicheng.lin@intel.com \
    --cc=stuart.summers@intel.com \
    --cc=tejas.upadhyay@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