linux-kernel - [PATCH 5.15 589/667] drm/nouveau/subdev/bus: Ratelimit logging for fault errors

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: <20220607164952.350301524@linuxfoundation.org>
Date:   Tue,  7 Jun 2022 19:04:14 +0200
From:   Greg Kroah-Hartman <gregkh@...uxfoundation.org>
To:     linux-kernel@...r.kernel.org
Cc:     Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
        stable@...r.kernel.org, Lyude Paul <lyude@...hat.com>,
        Karol Herbst <kherbst@...hat.com>
Subject: [PATCH 5.15 589/667] drm/nouveau/subdev/bus: Ratelimit logging for fault errors

From: Lyude Paul <lyude@...hat.com>

commit 9887bda0c831df0c044d6de147d002e48024fb4a upstream.

There's plenty of ways to fudge the GPU when developing on nouveau by
mistake, some of which can result in nouveau seriously spamming dmesg with
fault errors. This can be somewhat annoying, as it can quickly overrun the
message buffer (or your terminal emulator's buffer) and get rid of actually
useful feedback from the driver. While working on my new atomic only MST
branch, I ran into this issue a couple of times.

So, let's fix this by adding nvkm_error_ratelimited(), and using it to
ratelimit errors from faults. This should be fine for developers, since
it's nearly always only the first few faults that we care about seeing.
Plus, you can turn off rate limiting in the kernel if you really need to.

Signed-off-by: Lyude Paul <lyude@...hat.com>
Reviewed-by: Karol Herbst <kherbst@...hat.com>
Cc: stable@...r.kernel.org
Link: https://patchwork.freedesktop.org/patch/msgid/20220429195350.85620-1-lyude@redhat.com
Signed-off-by: Greg Kroah-Hartman <gregkh@...uxfoundation.org>
---
 drivers/gpu/drm/nouveau/include/nvkm/core/subdev.h |    2 ++
 drivers/gpu/drm/nouveau/nvkm/subdev/bus/gf100.c    |   14 +++++++-------
 drivers/gpu/drm/nouveau/nvkm/subdev/bus/nv31.c     |    6 +++---
 drivers/gpu/drm/nouveau/nvkm/subdev/bus/nv50.c     |    6 +++---
 4 files changed, 15 insertions(+), 13 deletions(-)

--- a/drivers/gpu/drm/nouveau/include/nvkm/core/subdev.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/core/subdev.h
@@ -62,4 +62,6 @@ void nvkm_subdev_intr(struct nvkm_subdev
 #define nvkm_debug(s,f,a...) nvkm_printk((s), DEBUG,   info, f, ##a)
 #define nvkm_trace(s,f,a...) nvkm_printk((s), TRACE,   info, f, ##a)
 #define nvkm_spam(s,f,a...)  nvkm_printk((s),  SPAM,    dbg, f, ##a)
+
+#define nvkm_error_ratelimited(s,f,a...) nvkm_printk((s), ERROR, err_ratelimited, f, ##a)
 #endif
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/bus/gf100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bus/gf100.c
@@ -35,13 +35,13 @@ gf100_bus_intr(struct nvkm_bus *bus)
 		u32 addr = nvkm_rd32(device, 0x009084);
 		u32 data = nvkm_rd32(device, 0x009088);
 
-		nvkm_error(subdev,
-			   "MMIO %s of %08x FAULT at %06x [ %s%s%s]\n",
-			   (addr & 0x00000002) ? "write" : "read", data,
-			   (addr & 0x00fffffc),
-			   (stat & 0x00000002) ? "!ENGINE " : "",
-			   (stat & 0x00000004) ? "PRIVRING " : "",
-			   (stat & 0x00000008) ? "TIMEOUT " : "");
+		nvkm_error_ratelimited(subdev,
+				       "MMIO %s of %08x FAULT at %06x [ %s%s%s]\n",
+				       (addr & 0x00000002) ? "write" : "read", data,
+				       (addr & 0x00fffffc),
+				       (stat & 0x00000002) ? "!ENGINE " : "",
+				       (stat & 0x00000004) ? "PRIVRING " : "",
+				       (stat & 0x00000008) ? "TIMEOUT " : "");
 
 		nvkm_wr32(device, 0x009084, 0x00000000);
 		nvkm_wr32(device, 0x001100, (stat & 0x0000000e));
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/bus/nv31.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bus/nv31.c
@@ -45,9 +45,9 @@ nv31_bus_intr(struct nvkm_bus *bus)
 		u32 addr = nvkm_rd32(device, 0x009084);
 		u32 data = nvkm_rd32(device, 0x009088);
 
-		nvkm_error(subdev, "MMIO %s of %08x FAULT at %06x\n",
-			   (addr & 0x00000002) ? "write" : "read", data,
-			   (addr & 0x00fffffc));
+		nvkm_error_ratelimited(subdev, "MMIO %s of %08x FAULT at %06x\n",
+				       (addr & 0x00000002) ? "write" : "read", data,
+				       (addr & 0x00fffffc));
 
 		stat &= ~0x00000008;
 		nvkm_wr32(device, 0x001100, 0x00000008);
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/bus/nv50.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bus/nv50.c
@@ -60,9 +60,9 @@ nv50_bus_intr(struct nvkm_bus *bus)
 		u32 addr = nvkm_rd32(device, 0x009084);
 		u32 data = nvkm_rd32(device, 0x009088);
 
-		nvkm_error(subdev, "MMIO %s of %08x FAULT at %06x\n",
-			   (addr & 0x00000002) ? "write" : "read", data,
-			   (addr & 0x00fffffc));
+		nvkm_error_ratelimited(subdev, "MMIO %s of %08x FAULT at %06x\n",
+				       (addr & 0x00000002) ? "write" : "read", data,
+				       (addr & 0x00fffffc));
 
 		stat &= ~0x00000008;
 		nvkm_wr32(device, 0x001100, 0x00000008);