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 <[email protected]>
---
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(-)
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/core/subdev.h b/drivers/gpu/drm/nouveau/include/nvkm/core/subdev.h
index 1665738948fb..96113c8bee8c 100644
--- 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 53a6651ac225..80b5aaceeaad 100644
--- 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 ad8da523bb22..c75e463f3501 100644
--- 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 3a1e45adeedc..2055d0b100d3 100644
--- 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);
--
2.35.1
not able to hit any error on my machine, but regardless:
Reviewed-by: Karol Herbst <[email protected]>
I suspect there are more places where we could put it, but we can add
those later.
Anyway, I think it's valuable to push it through fixes, not sure how
far back we want to CC stable though.
On Fri, Apr 29, 2022 at 9:54 PM Lyude Paul <[email protected]> wrote:
>
> 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 <[email protected]>
> ---
> 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(-)
>
> diff --git a/drivers/gpu/drm/nouveau/include/nvkm/core/subdev.h b/drivers/gpu/drm/nouveau/include/nvkm/core/subdev.h
> index 1665738948fb..96113c8bee8c 100644
> --- 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 53a6651ac225..80b5aaceeaad 100644
> --- 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 ad8da523bb22..c75e463f3501 100644
> --- 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 3a1e45adeedc..2055d0b100d3 100644
> --- 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);
> --
> 2.35.1
>
Actually, there is another place we have to put this, we can spam
"SCHED_ERROR" things which are triggered within multiple
drivers/gpu/drm/nouveau/nvkm/engine/fifo/ files.
On Tue, May 3, 2022 at 9:23 PM Karol Herbst <[email protected]> wrote:
>
> not able to hit any error on my machine, but regardless:
>
> Reviewed-by: Karol Herbst <[email protected]>
>
> I suspect there are more places where we could put it, but we can add
> those later.
>
> Anyway, I think it's valuable to push it through fixes, not sure how
> far back we want to CC stable though.
>
> On Fri, Apr 29, 2022 at 9:54 PM Lyude Paul <[email protected]> wrote:
> >
> > 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 <[email protected]>
> > ---
> > 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(-)
> >
> > diff --git a/drivers/gpu/drm/nouveau/include/nvkm/core/subdev.h b/drivers/gpu/drm/nouveau/include/nvkm/core/subdev.h
> > index 1665738948fb..96113c8bee8c 100644
> > --- 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 53a6651ac225..80b5aaceeaad 100644
> > --- 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 ad8da523bb22..c75e463f3501 100644
> > --- 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 3a1e45adeedc..2055d0b100d3 100644
> > --- 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);
> > --
> > 2.35.1
> >
On Tue, 2022-05-03 at 21:23 +0200, Karol Herbst wrote:
> not able to hit any error on my machine, but regardless:
>
> Reviewed-by: Karol Herbst <[email protected]>
>
> I suspect there are more places where we could put it, but we can add
> those later.
>
> Anyway, I think it's valuable to push it through fixes, not sure how
> far back we want to CC stable though.
JFYI - dim fixes can figure this out if you just give it the commit that
introduced the issue.
Anyway, will push this upstream in a moment
>
> On Fri, Apr 29, 2022 at 9:54 PM Lyude Paul <[email protected]> wrote:
> >
> > 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 <[email protected]>
> > ---
> > 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(-)
> >
> > diff --git a/drivers/gpu/drm/nouveau/include/nvkm/core/subdev.h
> > b/drivers/gpu/drm/nouveau/include/nvkm/core/subdev.h
> > index 1665738948fb..96113c8bee8c 100644
> > --- 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 53a6651ac225..80b5aaceeaad 100644
> > --- 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 ad8da523bb22..c75e463f3501 100644
> > --- 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 3a1e45adeedc..2055d0b100d3 100644
> > --- 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);
> > --
> > 2.35.1
> >
>
--
Cheers,
Lyude Paul (she/her)
Software Engineer at Red Hat
Mhhh - looks like it goes far back enough I probably should just Cc it without
a version tag and see how far it applies for greg. Will do that
On Wed, 2022-05-04 at 14:49 -0400, Lyude Paul wrote:
> On Tue, 2022-05-03 at 21:23 +0200, Karol Herbst wrote:
> > not able to hit any error on my machine, but regardless:
> >
> > Reviewed-by: Karol Herbst <[email protected]>
> >
> > I suspect there are more places where we could put it, but we can add
> > those later.
> >
> > Anyway, I think it's valuable to push it through fixes, not sure how
> > far back we want to CC stable though.
>
> JFYI - dim fixes can figure this out if you just give it the commit that
> introduced the issue.
>
> Anyway, will push this upstream in a moment
>
> >
> > On Fri, Apr 29, 2022 at 9:54 PM Lyude Paul <[email protected]> wrote:
> > >
> > > 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 <[email protected]>
> > > ---
> > > 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(-)
> > >
> > > diff --git a/drivers/gpu/drm/nouveau/include/nvkm/core/subdev.h
> > > b/drivers/gpu/drm/nouveau/include/nvkm/core/subdev.h
> > > index 1665738948fb..96113c8bee8c 100644
> > > --- 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 53a6651ac225..80b5aaceeaad 100644
> > > --- 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 ad8da523bb22..c75e463f3501 100644
> > > --- 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 3a1e45adeedc..2055d0b100d3 100644
> > > --- 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);
> > > --
> > > 2.35.1
> > >
> >
>
--
Cheers,
Lyude Paul (she/her)
Software Engineer at Red Hat