diff options
author | Guillaume Nault <gnault@redhat.com> | 2022-12-16 07:45:26 -0500 |
---|---|---|
committer | Jakub Kicinski <kuba@kernel.org> | 2022-12-19 17:28:49 -0800 |
commit | fb87bd47516d9a26b6d549231aa743b20fd4a569 (patch) | |
tree | edbb3a64442ad35a911801f9c1a4f723a0fc73b2 | |
parent | b389a902dd5be4ece505a2e0463b9b034de04bf5 (diff) | |
download | linux-fb87bd47516d9a26b6d549231aa743b20fd4a569.tar.gz linux-fb87bd47516d9a26b6d549231aa743b20fd4a569.tar.bz2 linux-fb87bd47516d9a26b6d549231aa743b20fd4a569.zip |
net: Introduce sk_use_task_frag in struct sock.
Sockets that can be used while recursing into memory reclaim, like
those used by network block devices and file systems, mustn't use
current->task_frag: if the current process is already using it, then
the inner memory reclaim call would corrupt the task_frag structure.
To avoid this, sk_page_frag() uses ->sk_allocation to detect sockets
that mustn't use current->task_frag, assuming that those used during
memory reclaim had their allocation constraints reflected in
->sk_allocation.
This unfortunately doesn't cover all cases: in an attempt to remove all
usage of GFP_NOFS and GFP_NOIO, sunrpc stopped setting these flags in
->sk_allocation, and used memalloc_nofs critical sections instead.
This breaks the sk_page_frag() heuristic since the allocation
constraints are now stored in current->flags, which sk_page_frag()
can't read without risking triggering a cache miss and slowing down
TCP's fast path.
This patch creates a new field in struct sock, named sk_use_task_frag,
which sockets with memory reclaim constraints can set to false if they
can't safely use current->task_frag. In such cases, sk_page_frag() now
always returns the socket's page_frag (->sk_frag). The first user is
sunrpc, which needs to avoid using current->task_frag but can keep
->sk_allocation set to GFP_KERNEL otherwise.
Eventually, it might be possible to simplify sk_page_frag() by only
testing ->sk_use_task_frag and avoid relying on the ->sk_allocation
heuristic entirely (assuming other sockets will set ->sk_use_task_frag
according to their constraints in the future).
The new ->sk_use_task_frag field is placed in a hole in struct sock and
belongs to a cache line shared with ->sk_shutdown. Therefore it should
be hot and shouldn't have negative performance impacts on TCP's fast
path (sk_shutdown is tested just before the while() loop in
tcp_sendmsg_locked()).
Link: https://lore.kernel.org/netdev/b4d8cb09c913d3e34f853736f3f5628abfd7f4b6.1656699567.git.gnault@redhat.com/
Signed-off-by: Guillaume Nault <gnault@redhat.com>
Reviewed-by: Benjamin Coddington <bcodding@redhat.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
-rw-r--r-- | include/net/sock.h | 11 | ||||
-rw-r--r-- | net/core/sock.c | 1 |
2 files changed, 10 insertions, 2 deletions
diff --git a/include/net/sock.h b/include/net/sock.h index ecea3dcc2217..fefe1f4abf19 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -318,6 +318,9 @@ struct sk_filter; * @sk_stamp: time stamp of last packet received * @sk_stamp_seq: lock for accessing sk_stamp on 32 bit architectures only * @sk_tsflags: SO_TIMESTAMPING flags + * @sk_use_task_frag: allow sk_page_frag() to use current->task_frag. + * Sockets that can be used under memory reclaim should + * set this to false. * @sk_bind_phc: SO_TIMESTAMPING bind PHC index of PTP virtual clock * for timestamping * @sk_tskey: counter to disambiguate concurrent tstamp requests @@ -512,6 +515,7 @@ struct sock { u8 sk_txtime_deadline_mode : 1, sk_txtime_report_errors : 1, sk_txtime_unused : 6; + bool sk_use_task_frag; struct socket *sk_socket; void *sk_user_data; @@ -2561,14 +2565,17 @@ static inline void sk_stream_moderate_sndbuf(struct sock *sk) * socket operations and end up recursing into sk_page_frag() * while it's already in use: explicitly avoid task page_frag * usage if the caller is potentially doing any of them. - * This assumes that page fault handlers use the GFP_NOFS flags. + * This assumes that page fault handlers use the GFP_NOFS flags or + * explicitly disable sk_use_task_frag. * * Return: a per task page_frag if context allows that, * otherwise a per socket one. */ static inline struct page_frag *sk_page_frag(struct sock *sk) { - if ((sk->sk_allocation & (__GFP_DIRECT_RECLAIM | __GFP_MEMALLOC | __GFP_FS)) == + if (sk->sk_use_task_frag && + (sk->sk_allocation & (__GFP_DIRECT_RECLAIM | __GFP_MEMALLOC | + __GFP_FS)) == (__GFP_DIRECT_RECLAIM | __GFP_FS)) return ¤t->task_frag; diff --git a/net/core/sock.c b/net/core/sock.c index d2587d8712db..f954d5893e79 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -3390,6 +3390,7 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk->sk_rcvbuf = READ_ONCE(sysctl_rmem_default); sk->sk_sndbuf = READ_ONCE(sysctl_wmem_default); sk->sk_state = TCP_CLOSE; + sk->sk_use_task_frag = true; sk_set_socket(sk, sock); sock_set_flag(sk, SOCK_ZAPPED); |