dax: make sure inodes are flushed before destroy cache
PATCH 1/1 dax: make sure inodes are flushed before destroy cache
A bug can be triggered by following command
$ modprobe nd_pmem && modprobe -r nd_pmem
[ 10.060014] BUG dax_cache (Not tainted): Objects remaining in dax_cache on __kmem_cache_shutdown() [ 10.060938] Slab 0x0000000085b729ac objects=9 used=1 fp=0x000000004f5ae469 flags=0x200000000010200(slab|head|node) [ 10.062433] Call Trace: [ 10.062673] dump_stack_lvl+0x34/0x44 [ 10.062865] slab_err+0x90/0xd0 [ 10.063619] __kmem_cache_shutdown+0x13b/0x2f0 [ 10.063848] kmem_cache_destroy+0x4a/0x110 [ 10.064058] __x64_sys_delete_module+0x265/0x300
This is caused by dax_fs_exit() not flushing inodes before destroy cache. To fix this issue, call rcu_barrier() before destroy cache.
--- drivers/dax/super.c | 1 + 1 file changed, 1 insertion(+)
drivers/dax/super.c +1 -0
@@ -476,6 +476,7 @@ static int dax_fs_init(void)static void dax_fs_exit (void ) {kern_unmount (dax_mnt); +rcu_barrier ();kmem_cache_destroy (dax_cache); }
Signature · 1 line
2.25.1
Looks good,
Quoted 13 lines · Tong Zhang
A bug can be triggered by following command
$ modprobe nd_pmem && modprobe -r nd_pmem[ 10.060014] BUG dax_cache (Not tainted): Objects remaining in dax_cache on __kmem_cache_shutdown() [ 10.060938] Slab 0x0000000085b729ac objects=9 used=1 fp=0x000000004f5ae469 flags=0x200000000010200(slab|head|node) [ 10.062433] Call Trace: [ 10.062673] dump_stack_lvl+0x34/0x44 [ 10.062865] slab_err+0x90/0xd0 [ 10.063619] __kmem_cache_shutdown+0x13b/0x2f0 [ 10.063848] kmem_cache_destroy+0x4a/0x110 [ 10.064058] __x64_sys_delete_module+0x265/0x300
Quoted 2 lines
This is caused by
dax_fs_exit()not flushing inodes before destroy cache. To fix this issue, callrcu_barrier()before destroy cache.
I don't doubt that this fixes the bug. However, I can't help but think this is hiding a bug, or perhaps a missing step, in the kmem_cache layer? As far as I can see dax does not call call_rcu() and only uses srcu not rcu? I was tempted to suggest srcu_barrier() but dax does not call call_srcu() either.
So I'm not clear about what is really going on and why this fixes it. I know that dax is not using srcu is a standard way so perhaps this helps in a way I don't quite grok? If so perhaps a comment here would be in order?
Ira
Quoted 22 lines
Signed-off-by Tong Zhang <[email protected]>--- drivers/dax/super.c | 1 + 1 file changed, 1 insertion(+)drivers/dax/super.c +1
-0@@ -476,6 +476,7 @@ static int dax_fs_init(void)static void dax_fs_exit (void ) {kern_unmount (dax_mnt); +rcu_barrier ();kmem_cache_destroy (dax_cache); }Signature · 1 line
2.25.1
Quoted 15 lines · Ira Weiny
Quoted 13 lines · Tong Zhang
A bug can be triggered by following command
$ modprobe nd_pmem && modprobe -r nd_pmem[ 10.060014] BUG dax_cache (Not tainted): Objects remaining in dax_cache on __kmem_cache_shutdown() [ 10.060938] Slab 0x0000000085b729ac objects=9 used=1 fp=0x000000004f5ae469 flags=0x200000000010200(slab|head|node) [ 10.062433] Call Trace: [ 10.062673] dump_stack_lvl+0x34/0x44 [ 10.062865] slab_err+0x90/0xd0 [ 10.063619] __kmem_cache_shutdown+0x13b/0x2f0 [ 10.063848] kmem_cache_destroy+0x4a/0x110 [ 10.064058] __x64_sys_delete_module+0x265/0x300
Quoted 7 lines
Quoted 2 lines
This is caused by
dax_fs_exit()not flushing inodes before destroy cache. To fix this issue, callrcu_barrier()before destroy cache.I don't doubt that this fixes the bug. However, I can't help but think this is hiding a bug, or perhaps a missing step, in the
kmem_cachelayer? As far as I can see dax does not callcall_rcu()and only uses srcu not rcu? I was tempted to suggestsrcu_barrier()but dax does not callcall_srcu()either.
This rcu_barrier() is associated with the call_rcu() in destroy_inode().
While kern_unmount() does a full sycnrhonize_rcu() after clearing ->mnt_ns. Any pending destroy_inode() callbacks need to be flushed before the kmem_cache is destroyed.
Quoted 3 lines
So I'm not clear about what is really going on and why this fixes it. I know that dax is not using srcu is a standard way so perhaps this helps in a way I don't quite grok? If so perhaps a comment here would be in order?
Looks like a common pattern I missed that all filesystem exit paths implement.
Ira Weiny
Reviewed-byQuoted 19 lines · Dan Williams
Quoted 18 lines · Ira Weiny
Quoted 15 lines · Tong Zhang
A bug can be triggered by following command
$ modprobe nd_pmem && modprobe -r nd_pmem[ 10.060014] BUG dax_cache (Not tainted): Objects remaining in dax_cache on __kmem_cache_shutdown() [ 10.060938] Slab 0x0000000085b729ac objects=9 used=1 fp=0x000000004f5ae469 flags=0x200000000010200(slab|head|node) [ 10.062433] Call Trace: [ 10.062673] dump_stack_lvl+0x34/0x44 [ 10.062865] slab_err+0x90/0xd0 [ 10.063619] __kmem_cache_shutdown+0x13b/0x2f0 [ 10.063848] kmem_cache_destroy+0x4a/0x110 [ 10.064058] __x64_sys_delete_module+0x265/0x300This is caused by
dax_fs_exit()not flushing inodes before destroy cache. To fix this issue, callrcu_barrier()before destroy cache.
Quoted 6 lines
Quoted 4 lines
I don't doubt that this fixes the bug. However, I can't help but think this is hiding a bug, or perhaps a missing step, in the
kmem_cachelayer? As far as I can see dax does not callcall_rcu()and only uses srcu not rcu? I was tempted to suggestsrcu_barrier()but dax does not callcall_srcu()either.This
rcu_barrier()is associated with thecall_rcu()indestroy_inode().
Ok yea.
Quoted 10 lines
While
kern_unmount()does a fullsycnrhonize_rcu()after clearing ->mnt_ns. Any pendingdestroy_inode()callbacks need to be flushed before thekmem_cacheis destroyed.Quoted 3 lines
So I'm not clear about what is really going on and why this fixes it. I know that dax is not using srcu is a standard way so perhaps this helps in a way I don't quite grok? If so perhaps a comment here would be in order?
Looks like a common pattern I missed that all filesystem exit paths implement.
I think a comment would be in order, especially since since it looks like every other FS has one:
fs/ext4/super.c:
...
/*
* Make sure all delayed rcu free inodes are flushed before we
* destroy cache.
*/
rcu_barrier(); ...
Anyway ok.
Thanks for looking Dan,
Ira