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@xxxxxxxxxx/
Fixes: a1231fda7e94 ("SUNRPC: Set memalloc_nofs_save() on all
rpciod/xprtiod jobs")
Signed-off-by: Guillaume Nault <gnault@xxxxxxxxxx>
Looks good, and thanks for looking through all the options.
Reviewed-by: Benjamin Coddington <bcodding@xxxxxxxxxx>
Ben
