[PATCH v2] nfsd: more robust allocation failure handling in nfsd_reply_cache_init

[PATCH v2] nfsd: more robust allocation failure handling in nfsd_reply_cache_init

[Jeff Layton]

Currently, we try to allocate the cache as a single, large chunk, which
can fail if no big chunks of memory are available. We _do_ try to size
it according to the amount of memory in the box, but if the server is
started well after boot time, then the allocation can fail due to memory
fragmentation.

Fall back to doing a vzalloc if the kcalloc fails, and switch the
shutdown code to do a kvfree to handle freeing correctly.

Reported-by: Olaf Hering <olaf@aepfle.de>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Jeff Layton <jlayton@redhat.com>
---
 fs/nfsd/nfscache.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c
index 54cde9a5864e..d6b97b424ad1 100644
--- a/fs/nfsd/nfscache.c
+++ b/fs/nfsd/nfscache.c
@@ -9,6 +9,7 @@
  */
 
 #include <linux/slab.h>
+#include <linux/vmalloc.h>
 #include <linux/sunrpc/addr.h>
 #include <linux/highmem.h>
 #include <linux/log2.h>
@@ -174,8 +175,12 @@ int nfsd_reply_cache_init(void)
 		goto out_nomem;
 
 	drc_hashtbl = kcalloc(hashsize, sizeof(*drc_hashtbl), GFP_KERNEL);
-	if (!drc_hashtbl)
-		goto out_nomem;
+	if (!drc_hashtbl) {
+		drc_hashtbl = vzalloc(hashsize * sizeof(*drc_hashtbl));
+		if (!drc_hashtbl)
+			goto out_nomem;
+	}
+
 	for (i = 0; i < hashsize; i++) {
 		INIT_LIST_HEAD(&drc_hashtbl[i].lru_head);
 		spin_lock_init(&drc_hashtbl[i].cache_lock);
@@ -204,7 +209,7 @@ void nfsd_reply_cache_shutdown(void)
 		}
 	}
 
-	kfree (drc_hashtbl);
+	kvfree(drc_hashtbl);
 	drc_hashtbl = NULL;
 	drc_hashsize = 0;
 
-- 
2.7.4

Re: [PATCH v2] nfsd: more robust allocation failure handling in nfsd_reply_cache_init

[J. Bruce Fields]

On Wed, Oct 26, 2016 at 07:26:40AM -0400, Jeff Layton wrote:
> Currently, we try to allocate the cache as a single, large chunk, which
> can fail if no big chunks of memory are available. We _do_ try to size
> it according to the amount of memory in the box, but if the server is
> started well after boot time, then the allocation can fail due to memory
> fragmentation.
> 
> Fall back to doing a vzalloc if the kcalloc fails, and switch the
> shutdown code to do a kvfree to handle freeing correctly.

Thanks, applying for 4.10.--b.

> 
> Reported-by: Olaf Hering <olaf@aepfle.de>
> Cc: Linus Torvalds <torvalds@linux-foundation.org>
> Signed-off-by: Jeff Layton <jlayton@redhat.com>
> ---
>  fs/nfsd/nfscache.c | 11 ++++++++---
>  1 file changed, 8 insertions(+), 3 deletions(-)
> 
> diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c
> index 54cde9a5864e..d6b97b424ad1 100644
> --- a/fs/nfsd/nfscache.c
> +++ b/fs/nfsd/nfscache.c
> @@ -9,6 +9,7 @@
>   */
>  
>  #include <linux/slab.h>
> +#include <linux/vmalloc.h>
>  #include <linux/sunrpc/addr.h>
>  #include <linux/highmem.h>
>  #include <linux/log2.h>
> @@ -174,8 +175,12 @@ int nfsd_reply_cache_init(void)
>  		goto out_nomem;
>  
>  	drc_hashtbl = kcalloc(hashsize, sizeof(*drc_hashtbl), GFP_KERNEL);
> -	if (!drc_hashtbl)
> -		goto out_nomem;
> +	if (!drc_hashtbl) {
> +		drc_hashtbl = vzalloc(hashsize * sizeof(*drc_hashtbl));
> +		if (!drc_hashtbl)
> +			goto out_nomem;
> +	}
> +
>  	for (i = 0; i < hashsize; i++) {
>  		INIT_LIST_HEAD(&drc_hashtbl[i].lru_head);
>  		spin_lock_init(&drc_hashtbl[i].cache_lock);
> @@ -204,7 +209,7 @@ void nfsd_reply_cache_shutdown(void)
>  		}
>  	}
>  
> -	kfree (drc_hashtbl);
> +	kvfree(drc_hashtbl);
>  	drc_hashtbl = NULL;
>  	drc_hashsize = 0;
>  
> -- 
> 2.7.4