nouveau: fix fence hang

If there is not enough space in pushbuffer for fence emission
(nouveau_fence_emit -> nv50_screen_fence_emit -> MARK_RING),
the pushbuffer is flushed, which through flush_notify ->
nv50_default_flush_notify -> nouveau_fence_update marks currently
emitting fence as flushed. But actual emission is done after this mark.
So later when there is a need to wait on this fence and pushbuffer
was not flushed in between, fence wait will never finish causing
application to hang.

To fix this, introduce new fence state between AVAILABLE and EMITTED,
set it before emission and handle it everywhere.

Additionally obtain fence sequence numbers after possible flush in
MARK_RING, because we want to emit fences in correct order.

Reviewed-by: Christoph Bumiller <[email protected]>

Note: This is a candidate for the 7.11 branch.

5 files changed, 28 insertions, 14 deletions

diff --git a/src/gallium/drivers/nouveau/nouveau_fence.c b/src/gallium/drivers/nouveau/nouveau_fence.c
index 26e4775b12d..a2fcafef4a7 100644
--- a/src/gallium/drivers/nouveau/nouveau_fence.c
+++ b/src/gallium/drivers/nouveau/nouveau_fence.c
@@ -86,12 +86,10 @@ nouveau_fence_emit(struct nouveau_fence *fence)
 {
    struct nouveau_screen *screen = fence->screen;
 
-   fence->sequence = ++screen->fence.sequence;
-
    assert(fence->state == NOUVEAU_FENCE_STATE_AVAILABLE);
 
    /* set this now, so that if fence.emit triggers a flush we don't recurse */
-   fence->state = NOUVEAU_FENCE_STATE_EMITTED;
+   fence->state = NOUVEAU_FENCE_STATE_EMITTING;
 
    ++fence->ref;
 
@@ -102,7 +100,10 @@ nouveau_fence_emit(struct nouveau_fence *fence)
 
    screen->fence.tail = fence;
 
-   screen->fence.emit(&screen->base, fence->sequence);
+   screen->fence.emit(&screen->base, &fence->sequence);
+
+   assert(fence->state == NOUVEAU_FENCE_STATE_EMITTING);
+   fence->state = NOUVEAU_FENCE_STATE_EMITTED;
 }
 
 void
@@ -162,7 +163,8 @@ nouveau_fence_update(struct nouveau_screen *screen, boolean flushed)
 
    if (flushed) {
       for (fence = next; fence; fence = fence->next)
-         fence->state = NOUVEAU_FENCE_STATE_FLUSHED;
+         if (fence->state == NOUVEAU_FENCE_STATE_EMITTED)
+            fence->state = NOUVEAU_FENCE_STATE_FLUSHED;
    }
 }
 
@@ -185,6 +187,9 @@ nouveau_fence_wait(struct nouveau_fence *fence)
    struct nouveau_screen *screen = fence->screen;
    uint32_t spins = 0;
 
+   /* wtf, someone is waiting on a fence in flush_notify handler? */
+   assert(fence->state != NOUVEAU_FENCE_STATE_EMITTING);
+
    if (fence->state < NOUVEAU_FENCE_STATE_EMITTED) {
       nouveau_fence_emit(fence);
 
@@ -216,7 +221,7 @@ nouveau_fence_wait(struct nouveau_fence *fence)
 void
 nouveau_fence_next(struct nouveau_screen *screen)
 {
-   if (screen->fence.current->state < NOUVEAU_FENCE_STATE_EMITTED)
+   if (screen->fence.current->state < NOUVEAU_FENCE_STATE_EMITTING)
       nouveau_fence_emit(screen->fence.current);
 
    nouveau_fence_ref(NULL, &screen->fence.current);
diff --git a/src/gallium/drivers/nouveau/nouveau_fence.h b/src/gallium/drivers/nouveau/nouveau_fence.h
index 680c75e99f9..3984a9a942d 100644
--- a/src/gallium/drivers/nouveau/nouveau_fence.h
+++ b/src/gallium/drivers/nouveau/nouveau_fence.h
@@ -6,9 +6,10 @@
 #include "util/u_double_list.h"
 
 #define NOUVEAU_FENCE_STATE_AVAILABLE 0
-#define NOUVEAU_FENCE_STATE_EMITTED   1
-#define NOUVEAU_FENCE_STATE_FLUSHED   2
-#define NOUVEAU_FENCE_STATE_SIGNALLED 3
+#define NOUVEAU_FENCE_STATE_EMITTING  1
+#define NOUVEAU_FENCE_STATE_EMITTED   2
+#define NOUVEAU_FENCE_STATE_FLUSHED   3
+#define NOUVEAU_FENCE_STATE_SIGNALLED 4
 
 struct nouveau_fence_work {
    struct list_head list;
diff --git a/src/gallium/drivers/nouveau/nouveau_screen.h b/src/gallium/drivers/nouveau/nouveau_screen.h
index cf291c6c595..808500f3002 100644
--- a/src/gallium/drivers/nouveau/nouveau_screen.h
+++ b/src/gallium/drivers/nouveau/nouveau_screen.h
@@ -24,7 +24,7 @@ struct nouveau_screen {
 		struct nouveau_fence *current;
 		u32 sequence;
 		u32 sequence_ack;
-		void (*emit)(struct pipe_screen *, u32 sequence);
+		void (*emit)(struct pipe_screen *, u32 *sequence);
 		u32  (*update)(struct pipe_screen *);
 	} fence;
 
diff --git a/src/gallium/drivers/nv50/nv50_screen.c b/src/gallium/drivers/nv50/nv50_screen.c
index c36f3cd4a04..7ff11ea4b0b 100644
--- a/src/gallium/drivers/nv50/nv50_screen.c
+++ b/src/gallium/drivers/nv50/nv50_screen.c
@@ -261,16 +261,20 @@ nv50_screen_destroy(struct pipe_screen *pscreen)
 }
 
 static void
-nv50_screen_fence_emit(struct pipe_screen *pscreen, u32 sequence)
+nv50_screen_fence_emit(struct pipe_screen *pscreen, u32 *sequence)
 {
    struct nv50_screen *screen = nv50_screen(pscreen);
    struct nouveau_channel *chan = screen->base.channel;
 
    MARK_RING (chan, 5, 2);
+
+   /* we need to do it after possible flush in MARK_RING */
+   *sequence = ++screen->base.fence.sequence;
+
    BEGIN_RING(chan, RING_3D(QUERY_ADDRESS_HIGH), 4);
    OUT_RELOCh(chan, screen->fence.bo, 0, NOUVEAU_BO_WR);
    OUT_RELOCl(chan, screen->fence.bo, 0, NOUVEAU_BO_WR);
-   OUT_RING  (chan, sequence);
+   OUT_RING  (chan, *sequence);
    OUT_RING  (chan, NV50_3D_QUERY_GET_MODE_WRITE_UNK0 |
                     NV50_3D_QUERY_GET_UNK4 |
                     NV50_3D_QUERY_GET_UNIT_CROP |
diff --git a/src/gallium/drivers/nvc0/nvc0_screen.c b/src/gallium/drivers/nvc0/nvc0_screen.c
index cc6e6830af2..292cbddcc0c 100644
--- a/src/gallium/drivers/nvc0/nvc0_screen.c
+++ b/src/gallium/drivers/nvc0/nvc0_screen.c
@@ -334,16 +334,20 @@ nvc0_magic_3d_init(struct nouveau_channel *chan)
 }
 
 static void
-nvc0_screen_fence_emit(struct pipe_screen *pscreen, u32 sequence)
+nvc0_screen_fence_emit(struct pipe_screen *pscreen, u32 *sequence)
 {
    struct nvc0_screen *screen = nvc0_screen(pscreen);
    struct nouveau_channel *chan = screen->base.channel;
 
    MARK_RING (chan, 5, 2);
+
+   /* we need to do it after possible flush in MARK_RING */
+   *sequence = ++screen->base.fence.sequence;
+
    BEGIN_RING(chan, RING_3D(QUERY_ADDRESS_HIGH), 4);
    OUT_RELOCh(chan, screen->fence.bo, 0, NOUVEAU_BO_WR);
    OUT_RELOCl(chan, screen->fence.bo, 0, NOUVEAU_BO_WR);
-   OUT_RING  (chan, sequence);
+   OUT_RING  (chan, *sequence);
    OUT_RING  (chan, NVC0_3D_QUERY_GET_FENCE | NVC0_3D_QUERY_GET_SHORT |
               (0xf << NVC0_3D_QUERY_GET_UNIT__SHIFT));
 }