nouveau: fix disabling the nonstall irq due to storm code

[ Upstream commit 0ef5c4e4dbbfcebaa9b2eca18097b43016727dfe ]

Nouveau has code that when it gets an IRQ with no allowed handler
it disables it to avoid storms.

However with nonstall interrupts, we often disable them from
the drm driver, but still request their emission via the push submission.

Just don't disable nonstall irqs ever in normal operation, the
event handling code will filter them out, and the driver will
just enable/disable them at load time.

This fixes timeouts we've been seeing on/off for a long time,
but they became a lot more noticeable on Blackwell.

This doesn't fix all of them, there is a subsequent fence emission
fix to fix the last few.

Fixes: 3ebd64aa3c4f ("drm/nouveau/intr: support multiple trees, and explicit interfaces")
Cc: stable@vger.kernel.org
Signed-off-by: Dave Airlie <airlied@redhat.com>
Link: https://lore.kernel.org/r/20250829021633.1674524-1-airlied@gmail.com
[ Fix a typo and a minor checkpatch.pl warning; remove "v2" from commit
  subject. - Danilo ]
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
[ File renames + drop r535 changes ]
Signed-off-by: Sasha Levin <sashal@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/base.c
index 5db37247dc29b2f1f9062981b2bf535fe2632c69..572c54a3709139e82fc0c20d572e6f86078040c7 100644 (file)
--- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/base.c
@@ -348,6 +348,8 @@ nvkm_fifo_dtor(struct nvkm_engine *engine)
        nvkm_chid_unref(&fifo->chid);
 
        nvkm_event_fini(&fifo->nonstall.event);
+       if (fifo->func->nonstall_dtor)
+               fifo->func->nonstall_dtor(fifo);
        mutex_destroy(&fifo->mutex);
        return fifo;
 }

diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga100.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga100.c
index c56d2a839efbaffdb6c0a01843973863b56c30de..686a2c9fec46d8a85f21b677da5473f44255cdba 100644 (file)
--- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga100.c
@@ -516,19 +516,11 @@ ga100_fifo_nonstall_intr(struct nvkm_inth *inth)
 static void
 ga100_fifo_nonstall_block(struct nvkm_event *event, int type, int index)
 {
-       struct nvkm_fifo *fifo = container_of(event, typeof(*fifo), nonstall.event);
-       struct nvkm_runl *runl = nvkm_runl_get(fifo, index, 0);
-
-       nvkm_inth_block(&runl->nonstall.inth);
 }
 
 static void
 ga100_fifo_nonstall_allow(struct nvkm_event *event, int type, int index)
 {
-       struct nvkm_fifo *fifo = container_of(event, typeof(*fifo), nonstall.event);
-       struct nvkm_runl *runl = nvkm_runl_get(fifo, index, 0);
-
-       nvkm_inth_allow(&runl->nonstall.inth);
 }
 
 const struct nvkm_event_func
@@ -559,12 +551,26 @@ ga100_fifo_nonstall_ctor(struct nvkm_fifo *fifo)
                if (ret)
                        return ret;
 
+               nvkm_inth_allow(&runl->nonstall.inth);
+
                nr = max(nr, runl->id + 1);
        }
 
        return nr;
 }
 
+void
+ga100_fifo_nonstall_dtor(struct nvkm_fifo *fifo)
+{
+       struct nvkm_runl *runl;
+
+       nvkm_runl_foreach(runl, fifo) {
+               if (runl->nonstall.vector < 0)
+                       continue;
+               nvkm_inth_block(&runl->nonstall.inth);
+       }
+}
+
 int
 ga100_fifo_runl_ctor(struct nvkm_fifo *fifo)
 {
@@ -594,6 +600,7 @@ ga100_fifo = {
        .runl_ctor = ga100_fifo_runl_ctor,
        .mmu_fault = &tu102_fifo_mmu_fault,
        .nonstall_ctor = ga100_fifo_nonstall_ctor,
+       .nonstall_dtor = ga100_fifo_nonstall_dtor,
        .nonstall = &ga100_fifo_nonstall,
        .runl = &ga100_runl,
        .runq = &ga100_runq,

diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga102.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga102.c
index 2cdf5da339b60bc609a8ebd1d45160dd2722430b..dccf38101fd9e7a573361e8224dbad2e491e3ed2 100644 (file)
--- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga102.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga102.c
@@ -28,6 +28,7 @@ ga102_fifo = {
        .runl_ctor = ga100_fifo_runl_ctor,
        .mmu_fault = &tu102_fifo_mmu_fault,
        .nonstall_ctor = ga100_fifo_nonstall_ctor,
+       .nonstall_dtor = ga100_fifo_nonstall_dtor,
        .nonstall = &ga100_fifo_nonstall,
        .runl = &ga100_runl,
        .runq = &ga100_runq,

diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/priv.h b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/priv.h
index 4d448be19224a8a0f86e7bfe08eaa66b3a70e117..b4ccf6b8bd21a1563939494d8f7d82ff6eb75ece 100644 (file)
--- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/priv.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/priv.h
@@ -38,6 +38,7 @@ struct nvkm_fifo_func {
        void (*start)(struct nvkm_fifo *, unsigned long *);
 
        int (*nonstall_ctor)(struct nvkm_fifo *);
+       void (*nonstall_dtor)(struct nvkm_fifo *);
        const struct nvkm_event_func *nonstall;
 
        const struct nvkm_runl_func *runl;
@@ -194,6 +195,7 @@ extern const struct nvkm_fifo_func_mmu_fault tu102_fifo_mmu_fault;
 
 int ga100_fifo_runl_ctor(struct nvkm_fifo *);
 int ga100_fifo_nonstall_ctor(struct nvkm_fifo *);
+void ga100_fifo_nonstall_dtor(struct nvkm_fifo *);
 extern const struct nvkm_event_func ga100_fifo_nonstall;
 extern const struct nvkm_runl_func ga100_runl;
 extern const struct nvkm_runq_func ga100_runq;