diff mbox series

[v2,5/8] drm/shmem: Use mutex_trylock in drm_gem_shmem_purge

Message ID 20190823021216.5862-6-robh@kernel.org
State Accepted
Commit edbd7f318cd66cec4588a28ba6985b014456dbca
Headers show
Series [v2,1/8] drm/panfrost: Fix possible suspend in panfrost_remove | expand

Commit Message

Rob Herring Aug. 23, 2019, 2:12 a.m. UTC
Lockdep reports a circular locking dependency with pages_lock taken in
the shrinker callback. The deadlock can't actually happen with current
users at least as a BO will never be purgeable when pages_lock is held.
To be safe, let's use mutex_trylock() instead and bail if a BO is locked
already.

WARNING: possible circular locking dependency detected
5.3.0-rc1+ #100 Tainted: G             L
------------------------------------------------------
kswapd0/171 is trying to acquire lock:
000000009b9823fd (&shmem->pages_lock){+.+.}, at: drm_gem_shmem_purge+0x20/0x40

but task is already holding lock:
00000000f82369b6 (fs_reclaim){+.+.}, at: __fs_reclaim_acquire+0x0/0x40

which lock already depends on the new lock.

the existing dependency chain (in reverse order) is:

-> #1 (fs_reclaim){+.+.}:
       fs_reclaim_acquire.part.18+0x34/0x40
       fs_reclaim_acquire+0x20/0x28
       __kmalloc_node+0x6c/0x4c0
       kvmalloc_node+0x38/0xa8
       drm_gem_get_pages+0x80/0x1d0
       drm_gem_shmem_get_pages+0x58/0xa0
       drm_gem_shmem_get_pages_sgt+0x48/0xd0
       panfrost_mmu_map+0x38/0xf8 [panfrost]
       panfrost_gem_open+0xc0/0xe8 [panfrost]
       drm_gem_handle_create_tail+0xe8/0x198
       drm_gem_handle_create+0x3c/0x50
       panfrost_gem_create_with_handle+0x70/0xa0 [panfrost]
       panfrost_ioctl_create_bo+0x48/0x80 [panfrost]
       drm_ioctl_kernel+0xb8/0x110
       drm_ioctl+0x244/0x3f0
       do_vfs_ioctl+0xbc/0x910
       ksys_ioctl+0x78/0xa8
       __arm64_sys_ioctl+0x1c/0x28
       el0_svc_common.constprop.0+0x90/0x168
       el0_svc_handler+0x28/0x78
       el0_svc+0x8/0xc

-> #0 (&shmem->pages_lock){+.+.}:
       __lock_acquire+0xa2c/0x1d70
       lock_acquire+0xdc/0x228
       __mutex_lock+0x8c/0x800
       mutex_lock_nested+0x1c/0x28
       drm_gem_shmem_purge+0x20/0x40
       panfrost_gem_shrinker_scan+0xc0/0x180 [panfrost]
       do_shrink_slab+0x208/0x500
       shrink_slab+0x10c/0x2c0
       shrink_node+0x28c/0x4d8
       balance_pgdat+0x2c8/0x570
       kswapd+0x22c/0x638
       kthread+0x128/0x130
       ret_from_fork+0x10/0x18

other info that might help us debug this:

 Possible unsafe locking scenario:

       CPU0                    CPU1
       ----                    ----
  lock(fs_reclaim);
                               lock(&shmem->pages_lock);
                               lock(fs_reclaim);
  lock(&shmem->pages_lock);

 *** DEADLOCK ***

3 locks held by kswapd0/171:
 #0: 00000000f82369b6 (fs_reclaim){+.+.}, at: __fs_reclaim_acquire+0x0/0x40
 #1: 00000000ceb37808 (shrinker_rwsem){++++}, at: shrink_slab+0xbc/0x2c0
 #2: 00000000f31efa81 (&pfdev->shrinker_lock){+.+.}, at: panfrost_gem_shrinker_scan+0x34/0x180 [panfrost]

Fixes: 17acb9f35ed7 ("drm/shmem: Add madvise state and purge helpers")
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Maxime Ripard <maxime.ripard@bootlin.com>
Cc: Sean Paul <sean@poorly.run>
Cc: David Airlie <airlied@linux.ie>
Cc: Daniel Vetter <daniel@ffwll.ch>
Signed-off-by: Rob Herring <robh@kernel.org>
---
 drivers/gpu/drm/drm_gem_shmem_helper.c | 7 +++++--
 include/drm/drm_gem_shmem_helper.h     | 2 +-
 2 files changed, 6 insertions(+), 3 deletions(-)

Comments

Steven Price Aug. 23, 2019, 2:53 p.m. UTC | #1
On 23/08/2019 03:12, Rob Herring wrote:
> Lockdep reports a circular locking dependency with pages_lock taken in
> the shrinker callback. The deadlock can't actually happen with current
> users at least as a BO will never be purgeable when pages_lock is held.
> To be safe, let's use mutex_trylock() instead and bail if a BO is locked
> already.
> 
> WARNING: possible circular locking dependency detected
> 5.3.0-rc1+ #100 Tainted: G             L
> ------------------------------------------------------
> kswapd0/171 is trying to acquire lock:
> 000000009b9823fd (&shmem->pages_lock){+.+.}, at: drm_gem_shmem_purge+0x20/0x40
> 
> but task is already holding lock:
> 00000000f82369b6 (fs_reclaim){+.+.}, at: __fs_reclaim_acquire+0x0/0x40
> 
> which lock already depends on the new lock.
> 
> the existing dependency chain (in reverse order) is:
> 
> -> #1 (fs_reclaim){+.+.}:
>         fs_reclaim_acquire.part.18+0x34/0x40
>         fs_reclaim_acquire+0x20/0x28
>         __kmalloc_node+0x6c/0x4c0
>         kvmalloc_node+0x38/0xa8
>         drm_gem_get_pages+0x80/0x1d0
>         drm_gem_shmem_get_pages+0x58/0xa0
>         drm_gem_shmem_get_pages_sgt+0x48/0xd0
>         panfrost_mmu_map+0x38/0xf8 [panfrost]
>         panfrost_gem_open+0xc0/0xe8 [panfrost]
>         drm_gem_handle_create_tail+0xe8/0x198
>         drm_gem_handle_create+0x3c/0x50
>         panfrost_gem_create_with_handle+0x70/0xa0 [panfrost]
>         panfrost_ioctl_create_bo+0x48/0x80 [panfrost]
>         drm_ioctl_kernel+0xb8/0x110
>         drm_ioctl+0x244/0x3f0
>         do_vfs_ioctl+0xbc/0x910
>         ksys_ioctl+0x78/0xa8
>         __arm64_sys_ioctl+0x1c/0x28
>         el0_svc_common.constprop.0+0x90/0x168
>         el0_svc_handler+0x28/0x78
>         el0_svc+0x8/0xc
> 
> -> #0 (&shmem->pages_lock){+.+.}:
>         __lock_acquire+0xa2c/0x1d70
>         lock_acquire+0xdc/0x228
>         __mutex_lock+0x8c/0x800
>         mutex_lock_nested+0x1c/0x28
>         drm_gem_shmem_purge+0x20/0x40
>         panfrost_gem_shrinker_scan+0xc0/0x180 [panfrost]
>         do_shrink_slab+0x208/0x500
>         shrink_slab+0x10c/0x2c0
>         shrink_node+0x28c/0x4d8
>         balance_pgdat+0x2c8/0x570
>         kswapd+0x22c/0x638
>         kthread+0x128/0x130
>         ret_from_fork+0x10/0x18
> 
> other info that might help us debug this:
> 
>   Possible unsafe locking scenario:
> 
>         CPU0                    CPU1
>         ----                    ----
>    lock(fs_reclaim);
>                                 lock(&shmem->pages_lock);
>                                 lock(fs_reclaim);
>    lock(&shmem->pages_lock);
> 
>   *** DEADLOCK ***
> 
> 3 locks held by kswapd0/171:
>   #0: 00000000f82369b6 (fs_reclaim){+.+.}, at: __fs_reclaim_acquire+0x0/0x40
>   #1: 00000000ceb37808 (shrinker_rwsem){++++}, at: shrink_slab+0xbc/0x2c0
>   #2: 00000000f31efa81 (&pfdev->shrinker_lock){+.+.}, at: panfrost_gem_shrinker_scan+0x34/0x180 [panfrost]
> 
> Fixes: 17acb9f35ed7 ("drm/shmem: Add madvise state and purge helpers")
> Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
> Cc: Maxime Ripard <maxime.ripard@bootlin.com>
> Cc: Sean Paul <sean@poorly.run>
> Cc: David Airlie <airlied@linux.ie>
> Cc: Daniel Vetter <daniel@ffwll.ch>
> Signed-off-by: Rob Herring <robh@kernel.org>

I thought I'd already given my R-b for this one, but just in case:

Reviewed-by: Steven Price <steven.price@arm.com>

Steve

> ---
>   drivers/gpu/drm/drm_gem_shmem_helper.c | 7 +++++--
>   include/drm/drm_gem_shmem_helper.h     | 2 +-
>   2 files changed, 6 insertions(+), 3 deletions(-)
> 
> diff --git a/drivers/gpu/drm/drm_gem_shmem_helper.c b/drivers/gpu/drm/drm_gem_shmem_helper.c
> index 5423ec56b535..f5918707672f 100644
> --- a/drivers/gpu/drm/drm_gem_shmem_helper.c
> +++ b/drivers/gpu/drm/drm_gem_shmem_helper.c
> @@ -415,13 +415,16 @@ void drm_gem_shmem_purge_locked(struct drm_gem_object *obj)
>   }
>   EXPORT_SYMBOL(drm_gem_shmem_purge_locked);
>   
> -void drm_gem_shmem_purge(struct drm_gem_object *obj)
> +bool drm_gem_shmem_purge(struct drm_gem_object *obj)
>   {
>   	struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj);
>   
> -	mutex_lock(&shmem->pages_lock);
> +	if (!mutex_trylock(&shmem->pages_lock))
> +		return false;
>   	drm_gem_shmem_purge_locked(obj);
>   	mutex_unlock(&shmem->pages_lock);
> +
> +	return true;
>   }
>   EXPORT_SYMBOL(drm_gem_shmem_purge);
>   
> diff --git a/include/drm/drm_gem_shmem_helper.h b/include/drm/drm_gem_shmem_helper.h
> index ce1600fdfc3e..01f514521687 100644
> --- a/include/drm/drm_gem_shmem_helper.h
> +++ b/include/drm/drm_gem_shmem_helper.h
> @@ -134,7 +134,7 @@ static inline bool drm_gem_shmem_is_purgeable(struct drm_gem_shmem_object *shmem
>   }
>   
>   void drm_gem_shmem_purge_locked(struct drm_gem_object *obj);
> -void drm_gem_shmem_purge(struct drm_gem_object *obj);
> +bool drm_gem_shmem_purge(struct drm_gem_object *obj);
>   
>   struct drm_gem_shmem_object *
>   drm_gem_shmem_create_with_handle(struct drm_file *file_priv,
>
diff mbox series

Patch

diff --git a/drivers/gpu/drm/drm_gem_shmem_helper.c b/drivers/gpu/drm/drm_gem_shmem_helper.c
index 5423ec56b535..f5918707672f 100644
--- a/drivers/gpu/drm/drm_gem_shmem_helper.c
+++ b/drivers/gpu/drm/drm_gem_shmem_helper.c
@@ -415,13 +415,16 @@  void drm_gem_shmem_purge_locked(struct drm_gem_object *obj)
 }
 EXPORT_SYMBOL(drm_gem_shmem_purge_locked);
 
-void drm_gem_shmem_purge(struct drm_gem_object *obj)
+bool drm_gem_shmem_purge(struct drm_gem_object *obj)
 {
 	struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj);
 
-	mutex_lock(&shmem->pages_lock);
+	if (!mutex_trylock(&shmem->pages_lock))
+		return false;
 	drm_gem_shmem_purge_locked(obj);
 	mutex_unlock(&shmem->pages_lock);
+
+	return true;
 }
 EXPORT_SYMBOL(drm_gem_shmem_purge);
 
diff --git a/include/drm/drm_gem_shmem_helper.h b/include/drm/drm_gem_shmem_helper.h
index ce1600fdfc3e..01f514521687 100644
--- a/include/drm/drm_gem_shmem_helper.h
+++ b/include/drm/drm_gem_shmem_helper.h
@@ -134,7 +134,7 @@  static inline bool drm_gem_shmem_is_purgeable(struct drm_gem_shmem_object *shmem
 }
 
 void drm_gem_shmem_purge_locked(struct drm_gem_object *obj);
-void drm_gem_shmem_purge(struct drm_gem_object *obj);
+bool drm_gem_shmem_purge(struct drm_gem_object *obj);
 
 struct drm_gem_shmem_object *
 drm_gem_shmem_create_with_handle(struct drm_file *file_priv,