drm/nouveau/subdev/bus: Ratelimit logging for fault errors

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@redhat.com>
Reviewed-by: Karol Herbst <kherbst@redhat.com>
Cc: stable@vger.kernel.org
Link: https://patchwork.freedesktop.org/patch/msgid/20220429195350.85620-1-lyude@redhat.com

diff --git a/drivers/gpu/drm/nouveau/include/nvkm/core/subdev.h b/drivers/gpu/drm/nouveau/include/nvkm/core/subdev.h
index 1665738..96113c8 100644 (file)
--- 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

diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bus/gf100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bus/gf100.c
index 53a6651..80b5aac 100644 (file)
--- 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));

diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bus/nv31.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bus/nv31.c
index ad8da52..c75e463 100644 (file)
--- 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);

diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bus/nv50.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bus/nv50.c
index 3a1e45a..2055d0b 100644 (file)
--- 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);