Nouveau - Apr 2023 - [PATCH v3] drm/nouveau: fix incorrect conversion to dma_resv_wait_timeout()

Commit 41d351f29528 ("drm/nouveau: stop using ttm_bo_wait")
converted from ttm_bo_wait_ctx() to dma_resv_wait_timeout().
However, dma_resv_wait_timeout() returns greater than zero on
success as opposed to ttm_bo_wait_ctx(). As a result, relocs
will fail and log errors even when it was a success.

Change the return code handling to match that of
nouveau_gem_ioctl_cpu_prep(), which was already using
dma_resv_wait_timeout() correctly.

Fixes: 41d351f29528 ("drm/nouveau: stop using ttm_bo_wait")
Reported-by: Tanmay Bhushan <007047221b at gmail.com>
Link: https://lore.kernel.org/lkml/20230119225351.71657-1-007047221b at
gmail.com
Signed-off-by: John Ogness <john.ogness at linutronix.de>
---
 The original report was actually a patch that needed fixing.
 Since nobody has stepped up to fix this regression correctly,
 I'm posting the v2.

 This is a real regression introduced in 6.3-rc1.

 drivers/gpu/drm/nouveau/nouveau_gem.c | 18 ++++++++++++------
 1 file changed, 12 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c
b/drivers/gpu/drm/nouveau/nouveau_gem.c
index f77e44958037..346839c24273 100644
--- a/drivers/gpu/drm/nouveau/nouveau_gem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_gem.c
@@ -645,8 +645,9 @@ nouveau_gem_pushbuf_reloc_apply(struct nouveau_cli *cli,
 				struct drm_nouveau_gem_pushbuf_reloc *reloc,
 				struct drm_nouveau_gem_pushbuf_bo *bo)
 {
-	long ret = 0;
+	int ret = 0;
 	unsigned i;
+	long lret;
 
 	for (i = 0; i < req->nr_relocs; i++) {
 		struct drm_nouveau_gem_pushbuf_reloc *r = &reloc[i];
@@ -703,13 +704,18 @@ nouveau_gem_pushbuf_reloc_apply(struct nouveau_cli *cli,
 				data |= r->vor;
 		}
 
-		ret = dma_resv_wait_timeout(nvbo->bo.base.resv,
-					    DMA_RESV_USAGE_BOOKKEEP,
-					    false, 15 * HZ);
-		if (ret == 0)
+		lret = dma_resv_wait_timeout(nvbo->bo.base.resv,
+					     DMA_RESV_USAGE_BOOKKEEP,
+					     false, 15 * HZ);
+		if (!lret)
 			ret = -EBUSY;
+		else if (lret > 0)
+			ret = 0;
+		else
+			ret = lret;
+
 		if (ret) {
-			NV_PRINTK(err, cli, "reloc wait_idle failed: %ld\n",
+			NV_PRINTK(err, cli, "reloc wait_idle failed: %d\n",
 				  ret);
 			break;
 		}

base-commit: 09a9639e56c01c7a00d6c0ca63f4c7c41abe075d
-- 
2.30.2

Commit 41d351f29528 ("drm/nouveau: stop using ttm_bo_wait")
converted from ttm_bo_wait_ctx() to dma_resv_wait_timeout().
However, dma_resv_wait_timeout() returns greater than zero on
success as opposed to ttm_bo_wait_ctx(). As a result, relocs
will fail and log errors even when it was a success.

Change the return code handling to match that of
nouveau_gem_ioctl_cpu_prep(), which was already using
dma_resv_wait_timeout() correctly.

Fixes: 41d351f29528 ("drm/nouveau: stop using ttm_bo_wait")
Reported-by: Tanmay Bhushan <007047221b at gmail.com>
Link: https://lore.kernel.org/lkml/20230119225351.71657-1-007047221b at
gmail.com
Signed-off-by: John Ogness <john.ogness at linutronix.de>
---
 I just realized that the nouveau driver style prefers to scope
 variables used only in loops.

 v3: Define @lret within the for-loop.

 drivers/gpu/drm/nouveau/nouveau_gem.c | 18 ++++++++++++------
 1 file changed, 12 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c
b/drivers/gpu/drm/nouveau/nouveau_gem.c
index f77e44958037..ab9062e50977 100644
--- a/drivers/gpu/drm/nouveau/nouveau_gem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_gem.c
@@ -645,7 +645,7 @@ nouveau_gem_pushbuf_reloc_apply(struct nouveau_cli *cli,
 				struct drm_nouveau_gem_pushbuf_reloc *reloc,
 				struct drm_nouveau_gem_pushbuf_bo *bo)
 {
-	long ret = 0;
+	int ret = 0;
 	unsigned i;
 
 	for (i = 0; i < req->nr_relocs; i++) {
@@ -653,6 +653,7 @@ nouveau_gem_pushbuf_reloc_apply(struct nouveau_cli *cli,
 		struct drm_nouveau_gem_pushbuf_bo *b;
 		struct nouveau_bo *nvbo;
 		uint32_t data;
+		long lret;
 
 		if (unlikely(r->bo_index >= req->nr_buffers)) {
 			NV_PRINTK(err, cli, "reloc bo index invalid\n");
@@ -703,13 +704,18 @@ nouveau_gem_pushbuf_reloc_apply(struct nouveau_cli *cli,
 				data |= r->vor;
 		}
 
-		ret = dma_resv_wait_timeout(nvbo->bo.base.resv,
-					    DMA_RESV_USAGE_BOOKKEEP,
-					    false, 15 * HZ);
-		if (ret == 0)
+		lret = dma_resv_wait_timeout(nvbo->bo.base.resv,
+					     DMA_RESV_USAGE_BOOKKEEP,
+					     false, 15 * HZ);
+		if (!lret)
 			ret = -EBUSY;
+		else if (lret > 0)
+			ret = 0;
+		else
+			ret = lret;
+
 		if (ret) {
-			NV_PRINTK(err, cli, "reloc wait_idle failed: %ld\n",
+			NV_PRINTK(err, cli, "reloc wait_idle failed: %d\n",
 				  ret);
 			break;
 		}

base-commit: 09a9639e56c01c7a00d6c0ca63f4c7c41abe075d
-- 
2.30.2

Am 15.04.23 um 04:02 schrieb John Ogness:
> Commit 41d351f29528 ("drm/nouveau: stop using ttm_bo_wait")
> converted from ttm_bo_wait_ctx() to dma_resv_wait_timeout().
> However, dma_resv_wait_timeout() returns greater than zero on
> success as opposed to ttm_bo_wait_ctx(). As a result, relocs
> will fail and log errors even when it was a success.
>
> Change the return code handling to match that of
> nouveau_gem_ioctl_cpu_prep(), which was already using
> dma_resv_wait_timeout() correctly.
>
> Fixes: 41d351f29528 ("drm/nouveau: stop using ttm_bo_wait")
> Reported-by: Tanmay Bhushan <007047221b at gmail.com>
> Link: https://lore.kernel.org/lkml/20230119225351.71657-1-007047221b at
gmail.com
> Signed-off-by: John Ogness <john.ogness at linutronix.de>
Reviewed-by: Christian K?nig <christian.koenig at amd.com>
> ---
>   I just realized that the nouveau driver style prefers to scope
>   variables used only in loops.
>
>   v3: Define @lret within the for-loop.
>
>   drivers/gpu/drm/nouveau/nouveau_gem.c | 18 ++++++++++++------
>   1 file changed, 12 insertions(+), 6 deletions(-)
>
> diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c
b/drivers/gpu/drm/nouveau/nouveau_gem.c
> index f77e44958037..ab9062e50977 100644
> --- a/drivers/gpu/drm/nouveau/nouveau_gem.c
> +++ b/drivers/gpu/drm/nouveau/nouveau_gem.c
> @@ -645,7 +645,7 @@ nouveau_gem_pushbuf_reloc_apply(struct nouveau_cli
*cli,
>   				struct drm_nouveau_gem_pushbuf_reloc *reloc,
>   				struct drm_nouveau_gem_pushbuf_bo *bo)
>   {
> -	long ret = 0;
> +	int ret = 0;
>   	unsigned i;
>   
>   	for (i = 0; i < req->nr_relocs; i++) {
> @@ -653,6 +653,7 @@ nouveau_gem_pushbuf_reloc_apply(struct nouveau_cli
*cli,
>   		struct drm_nouveau_gem_pushbuf_bo *b;
>   		struct nouveau_bo *nvbo;
>   		uint32_t data;
> +		long lret;
>   
>   		if (unlikely(r->bo_index >= req->nr_buffers)) {
>   			NV_PRINTK(err, cli, "reloc bo index invalid\n");
> @@ -703,13 +704,18 @@ nouveau_gem_pushbuf_reloc_apply(struct nouveau_cli
*cli,
>   				data |= r->vor;
>   		}
>   
> -		ret = dma_resv_wait_timeout(nvbo->bo.base.resv,
> -					    DMA_RESV_USAGE_BOOKKEEP,
> -					    false, 15 * HZ);
> -		if (ret == 0)
> +		lret = dma_resv_wait_timeout(nvbo->bo.base.resv,
> +					     DMA_RESV_USAGE_BOOKKEEP,
> +					     false, 15 * HZ);
> +		if (!lret)
>   			ret = -EBUSY;
> +		else if (lret > 0)
> +			ret = 0;
> +		else
> +			ret = lret;
> +
>   		if (ret) {
> -			NV_PRINTK(err, cli, "reloc wait_idle failed: %ld\n",
> +			NV_PRINTK(err, cli, "reloc wait_idle failed: %d\n",
>   				  ret);
>   			break;
>   		}
>
> base-commit: 09a9639e56c01c7a00d6c0ca63f4c7c41abe075d