diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2009-07-10 03:33:18 (GMT) |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2009-07-10 03:33:18 (GMT) |
commit | e864561c12bc743789eab76242b8314d394daa52 (patch) | |
tree | 5f9bf951fd8e713b224062a37b2a0b24c14f17ce /include/net/sock.h | |
parent | 42359da44112565e12a5209befb36dc6b6d6cd9c (diff) | |
parent | e594e96e8a14101a6decabf6746bd5186287debc (diff) | |
download | linux-fsl-qoriq-e864561c12bc743789eab76242b8314d394daa52.tar.xz |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6: (29 commits)
cxgb3: Fix crash caused by stashing wrong netdev_queue
ixgbe: Fix coexistence of FCoE and Flow Director in 82599
memory barrier: adding smp_mb__after_lock
net: adding memory barrier to the poll and receive callbacks
netpoll: Fix carrier detection for drivers that are using phylib
includecheck fix: include/linux, rfkill.h
p54: tx refused but queue active
Atheros Kconfig needs to be dependent on WLAN_80211
mac80211: fix docbook
mac80211_hwsim: avoid NULL access
ssb: Add support for 4318E
b43: Add support for 4318E
zd1211rw: adding SONY IFU-WLM2 (054c:0257) as a zd1211b device
zd1211rw: 07b8:6001 is a ZD1211B
r6040: bump driver version to 0.24 and date to 08 July 2009
r6040: restore MIER register correctly when IRQ line is shared
ipv4: Fix fib_trie rebalancing, part 4 (root thresholds)
davinci_emac: fix kernel oops when changing MAC address while interface is down
igb: set lan id prior to configuring phy
mac80211: minstrel: avoid accessing negative indices in rix_to_ndx()
...
Diffstat (limited to 'include/net/sock.h')
-rw-r--r-- | include/net/sock.h | 69 |
1 files changed, 69 insertions, 0 deletions
diff --git a/include/net/sock.h b/include/net/sock.h index 352f06bb..2c0da92 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -54,6 +54,7 @@ #include <linux/filter.h> #include <linux/rculist_nulls.h> +#include <linux/poll.h> #include <asm/atomic.h> #include <net/dst.h> @@ -1241,6 +1242,74 @@ static inline int sk_has_allocations(const struct sock *sk) return sk_wmem_alloc_get(sk) || sk_rmem_alloc_get(sk); } +/** + * sk_has_sleeper - check if there are any waiting processes + * @sk: socket + * + * Returns true if socket has waiting processes + * + * The purpose of the sk_has_sleeper and sock_poll_wait is to wrap the memory + * barrier call. They were added due to the race found within the tcp code. + * + * Consider following tcp code paths: + * + * CPU1 CPU2 + * + * sys_select receive packet + * ... ... + * __add_wait_queue update tp->rcv_nxt + * ... ... + * tp->rcv_nxt check sock_def_readable + * ... { + * schedule ... + * if (sk->sk_sleep && waitqueue_active(sk->sk_sleep)) + * wake_up_interruptible(sk->sk_sleep) + * ... + * } + * + * The race for tcp fires when the __add_wait_queue changes done by CPU1 stay + * in its cache, and so does the tp->rcv_nxt update on CPU2 side. The CPU1 + * could then endup calling schedule and sleep forever if there are no more + * data on the socket. + * + * The sk_has_sleeper is always called right after a call to read_lock, so we + * can use smp_mb__after_lock barrier. + */ +static inline int sk_has_sleeper(struct sock *sk) +{ + /* + * We need to be sure we are in sync with the + * add_wait_queue modifications to the wait queue. + * + * This memory barrier is paired in the sock_poll_wait. + */ + smp_mb__after_lock(); + return sk->sk_sleep && waitqueue_active(sk->sk_sleep); +} + +/** + * sock_poll_wait - place memory barrier behind the poll_wait call. + * @filp: file + * @wait_address: socket wait queue + * @p: poll_table + * + * See the comments in the sk_has_sleeper function. + */ +static inline void sock_poll_wait(struct file *filp, + wait_queue_head_t *wait_address, poll_table *p) +{ + if (p && wait_address) { + poll_wait(filp, wait_address, p); + /* + * We need to be sure we are in sync with the + * socket flags modification. + * + * This memory barrier is paired in the sk_has_sleeper. + */ + smp_mb(); + } +} + /* * Queue a received datagram if it will fit. Stream and sequenced * protocols can't normally use this as they need to fit buffers in |