linux-kernel - [PATCH 5.15 54/73] drm/nouveau: wait for the exclusive fence after the shared ones v2

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20220103142058.666219405@linuxfoundation.org>
Date:   Mon,  3 Jan 2022 15:24:15 +0100
From:   Greg Kroah-Hartman <gregkh@...uxfoundation.org>
To:     linux-kernel@...r.kernel.org
Cc:     Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
        stable@...r.kernel.org,
        Christian König <christian.koenig@....com>,
        Stefan Fritsch <sf@...itsch.de>,
        Dan Moulding <dmoulding@...com>,
        Ben Skeggs <bskeggs@...hat.com>
Subject: [PATCH 5.15 54/73] drm/nouveau: wait for the exclusive fence after the shared ones v2

From: Christian König <christian.koenig@....com>

commit 67f74302f45d5d862f22ced3297624e50ac352f0 upstream.

Always waiting for the exclusive fence resulted on some performance
regressions. So try to wait for the shared fences first, then the
exclusive fence should always be signaled already.

v2: fix incorrectly placed "(", add some comment why we do this.

Signed-off-by: Christian König <christian.koenig@....com>
Tested-by: Stefan Fritsch <sf@...itsch.de>
Tested-by: Dan Moulding <dmoulding@...com>
Acked-by: Ben Skeggs <bskeggs@...hat.com>
Signed-off-by: Christian König <christian.koenig@....com>
Cc: <stable@...r.kernel.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20211209102335.18321-1-christian.koenig@amd.com
Signed-off-by: Greg Kroah-Hartman <gregkh@...uxfoundation.org>
---
 drivers/gpu/drm/nouveau/nouveau_fence.c |   28 +++++++++++++++-------------
 1 file changed, 15 insertions(+), 13 deletions(-)

--- a/drivers/gpu/drm/nouveau/nouveau_fence.c
+++ b/drivers/gpu/drm/nouveau/nouveau_fence.c
@@ -353,15 +353,22 @@ nouveau_fence_sync(struct nouveau_bo *nv
 
 		if (ret)
 			return ret;
-	}
 
-	fobj = dma_resv_shared_list(resv);
-	fence = dma_resv_excl_fence(resv);
+		fobj = NULL;
+	} else {
+		fobj = dma_resv_shared_list(resv);
+	}
 
-	if (fence) {
+	/* Waiting for the exclusive fence first causes performance regressions
+	 * under some circumstances. So manually wait for the shared ones first.
+	 */
+	for (i = 0; i < (fobj ? fobj->shared_count : 0) && !ret; ++i) {
 		struct nouveau_channel *prev = NULL;
 		bool must_wait = true;
 
+		fence = rcu_dereference_protected(fobj->shared[i],
+						dma_resv_held(resv));
+
 		f = nouveau_local_fence(fence, chan->drm);
 		if (f) {
 			rcu_read_lock();
@@ -373,20 +380,13 @@ nouveau_fence_sync(struct nouveau_bo *nv
 
 		if (must_wait)
 			ret = dma_fence_wait(fence, intr);
-
-		return ret;
 	}
 
-	if (!exclusive || !fobj)
-		return ret;
-
-	for (i = 0; i < fobj->shared_count && !ret; ++i) {
+	fence = dma_resv_excl_fence(resv);
+	if (fence) {
 		struct nouveau_channel *prev = NULL;
 		bool must_wait = true;
 
-		fence = rcu_dereference_protected(fobj->shared[i],
-						dma_resv_held(resv));
-
 		f = nouveau_local_fence(fence, chan->drm);
 		if (f) {
 			rcu_read_lock();
@@ -398,6 +398,8 @@ nouveau_fence_sync(struct nouveau_bo *nv
 
 		if (must_wait)
 			ret = dma_fence_wait(fence, intr);
+
+		return ret;
 	}
 
 	return ret;