Commit a1231fda7e94 ("SUNRPC: Set memalloc_nofs_save() on all
rpciod/xprtiod jobs") stopped setting sk->sk_allocation explicitly in
favor of using memalloc_nofs_save()/memalloc_nofs_restore() critical
sections.
However, ->sk_allocation isn't used just by the memory allocator.
In particular, sk_page_frag() uses it to figure out if it can return
the page_frag from current or if it has to use the socket one.
With ->sk_allocation set to the default GFP_KERNEL, sk_page_frag() now
returns current->page_frag, which might already be in use in the
current context if the call happens during memory reclaim.
Fix this by setting ->sk_allocation to GFP_NOFS.
Note that we can't just instruct sk_page_frag() to look at
current->flags, because it could generate a cache miss, thus slowing
down the TCP fast path.
This is similar to the problems fixed by the following two commits:
* cifs: commit dacb5d8875cc ("tcp: fix page frag corruption on page
fault").
* nbd: commit 20eb4f29b602 ("net: fix sk_page_frag() recursion from
memory reclaim").
Link: https://lore.kernel.org/netdev/b4d8cb09c913d3e34f853736f3f5628abfd7f4b6.1656699567.git.gnault@redhat.com/
Fixes: a1231fda7e94 ("SUNRPC: Set memalloc_nofs_save() on all rpciod/xprtiod jobs")
Signed-off-by: Guillaume Nault <[email protected]>
---
net/sunrpc/xprtsock.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index e976007f4fd0..1bd3048d43ae 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -1882,6 +1882,7 @@ static int xs_local_finish_connecting(struct rpc_xprt *xprt,
sk->sk_write_space = xs_udp_write_space;
sk->sk_state_change = xs_local_state_change;
sk->sk_error_report = xs_error_report;
+ sk->sk_allocation = GFP_NOFS;
xprt_clear_connected(xprt);
@@ -2083,6 +2084,7 @@ static void xs_udp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
sk->sk_user_data = xprt;
sk->sk_data_ready = xs_data_ready;
sk->sk_write_space = xs_udp_write_space;
+ sk->sk_allocation = GFP_NOFS;
xprt_set_connected(xprt);
@@ -2250,6 +2252,7 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
sk->sk_state_change = xs_tcp_state_change;
sk->sk_write_space = xs_tcp_write_space;
sk->sk_error_report = xs_error_report;
+ sk->sk_allocation = GFP_NOFS;
/* socket options */
sock_reset_flag(sk, SOCK_LINGER);
--
2.21.3
On Wed, 2022-09-21 at 14:16 +0200, Guillaume Nault wrote:
> Commit a1231fda7e94 ("SUNRPC: Set memalloc_nofs_save() on all
> rpciod/xprtiod jobs") stopped setting sk->sk_allocation explicitly in
> favor of using memalloc_nofs_save()/memalloc_nofs_restore() critical
> sections.
>
> However, ->sk_allocation isn't used just by the memory allocator.
> In particular, sk_page_frag() uses it to figure out if it can return
> the page_frag from current or if it has to use the socket one.
> With ->sk_allocation set to the default GFP_KERNEL, sk_page_frag() now
> returns current->page_frag, which might already be in use in the
> current context if the call happens during memory reclaim.
>
> Fix this by setting ->sk_allocation to GFP_NOFS.
> Note that we can't just instruct sk_page_frag() to look at
> current->flags, because it could generate a cache miss, thus slowing
> down the TCP fast path.
>
> This is similar to the problems fixed by the following two commits:
> * cifs: commit dacb5d8875cc ("tcp: fix page frag corruption on page
> fault").
> * nbd: commit 20eb4f29b602 ("net: fix sk_page_frag() recursion from
> memory reclaim").
>
> Link: https://lore.kernel.org/netdev/b4d8cb09c913d3e34f853736f3f5628abfd7f4b6.1656699567.git.gnault@redhat.com/
> Fixes: a1231fda7e94 ("SUNRPC: Set memalloc_nofs_save() on all rpciod/xprtiod jobs")
> Signed-off-by: Guillaume Nault <[email protected]>
It's unfortunate, but I think we need to keep both memalloc_nofs_save()
and sk_allocation for the time being.
Thanks Guillaume, patch LGTM.
Acked-by: Paolo Abeni <[email protected]>
On 21 Sep 2022, at 8:16, Guillaume Nault wrote:
> Commit a1231fda7e94 ("SUNRPC: Set memalloc_nofs_save() on all
> rpciod/xprtiod jobs") stopped setting sk->sk_allocation explicitly in
> favor of using memalloc_nofs_save()/memalloc_nofs_restore() critical
> sections.
>
> However, ->sk_allocation isn't used just by the memory allocator.
> In particular, sk_page_frag() uses it to figure out if it can return
> the page_frag from current or if it has to use the socket one.
> With ->sk_allocation set to the default GFP_KERNEL, sk_page_frag() now
> returns current->page_frag, which might already be in use in the
> current context if the call happens during memory reclaim.
>
> Fix this by setting ->sk_allocation to GFP_NOFS.
> Note that we can't just instruct sk_page_frag() to look at
> current->flags, because it could generate a cache miss, thus slowing
> down the TCP fast path.
>
> This is similar to the problems fixed by the following two commits:
> * cifs: commit dacb5d8875cc ("tcp: fix page frag corruption on page
> fault").
> * nbd: commit 20eb4f29b602 ("net: fix sk_page_frag() recursion from
> memory reclaim").
>
> Link:
> https://lore.kernel.org/netdev/b4d8cb09c913d3e34f853736f3f5628abfd7f4b6.1656699567.git.gnault@redhat.com/
> Fixes: a1231fda7e94 ("SUNRPC: Set memalloc_nofs_save() on all
> rpciod/xprtiod jobs")
> Signed-off-by: Guillaume Nault <[email protected]>
Looks good, and thanks for looking through all the options.
Reviewed-by: Benjamin Coddington <[email protected]>
Ben
On Wed, 2022-09-21 at 14:16 +0200, Guillaume Nault wrote:
> Commit a1231fda7e94 ("SUNRPC: Set memalloc_nofs_save() on all
> rpciod/xprtiod jobs") stopped setting sk->sk_allocation explicitly in
> favor of using memalloc_nofs_save()/memalloc_nofs_restore() critical
> sections.
>
> However, ->sk_allocation isn't used just by the memory allocator.
> In particular, sk_page_frag() uses it to figure out if it can return
> the page_frag from current or if it has to use the socket one.
> With ->sk_allocation set to the default GFP_KERNEL, sk_page_frag() now
> returns current->page_frag, which might already be in use in the
> current context if the call happens during memory reclaim.
>
> Fix this by setting ->sk_allocation to GFP_NOFS.
> Note that we can't just instruct sk_page_frag() to look at
> current->flags, because it could generate a cache miss, thus slowing
> down the TCP fast path.
>
> This is similar to the problems fixed by the following two commits:
> * cifs: commit dacb5d8875cc ("tcp: fix page frag corruption on page
> fault").
> * nbd: commit 20eb4f29b602 ("net: fix sk_page_frag() recursion from
> memory reclaim").
>
> Link: https://lore.kernel.org/netdev/b4d8cb09c913d3e34f853736f3f5628abfd7f4b6.1656699567.git.gnault@redhat.com/
> Fixes: a1231fda7e94 ("SUNRPC: Set memalloc_nofs_save() on all rpciod/xprtiod jobs")
> Signed-off-by: Guillaume Nault <[email protected]>
@Trond, @Anna, @Chuck: are you ok with this patch? Should we take it
via the net tree or will you merge it?
Thanks!
Paolo