summaryrefslogtreecommitdiff
path: root/fs/select.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2013-07-09 18:24:39 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2013-07-09 18:24:39 -0700
commit496322bc91e35007ed754184dcd447a02b6dd685 (patch)
treef5298d0a74c0a6e65c0e98050b594b8d020904c1 /fs/select.c
parent2e17c5a97e231f3cb426f4b7895eab5be5c5442e (diff)
parent56e0ef527b184b3de2d7f88c6190812b2b2ac6bf (diff)
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller: "This is a re-do of the net-next pull request for the current merge window. The only difference from the one I made the other day is that this has Eliezer's interface renames and the timeout handling changes made based upon your feedback, as well as a few bug fixes that have trickeled in. Highlights: 1) Low latency device polling, eliminating the cost of interrupt handling and context switches. Allows direct polling of a network device from socket operations, such as recvmsg() and poll(). Currently ixgbe, mlx4, and bnx2x support this feature. Full high level description, performance numbers, and design in commit 0a4db187a999 ("Merge branch 'll_poll'") From Eliezer Tamir. 2) With the routing cache removed, ip_check_mc_rcu() gets exercised more than ever before in the case where we have lots of multicast addresses. Use a hash table instead of a simple linked list, from Eric Dumazet. 3) Add driver for Atheros CQA98xx 802.11ac wireless devices, from Bartosz Markowski, Janusz Dziedzic, Kalle Valo, Marek Kwaczynski, Marek Puzyniak, Michal Kazior, and Sujith Manoharan. 4) Support reporting the TUN device persist flag to userspace, from Pavel Emelyanov. 5) Allow controlling network device VF link state using netlink, from Rony Efraim. 6) Support GRE tunneling in openvswitch, from Pravin B Shelar. 7) Adjust SOCK_MIN_RCVBUF and SOCK_MIN_SNDBUF for modern times, from Daniel Borkmann and Eric Dumazet. 8) Allow controlling of TCP quickack behavior on a per-route basis, from Cong Wang. 9) Several bug fixes and improvements to vxlan from Stephen Hemminger, Pravin B Shelar, and Mike Rapoport. In particular, support receiving on multiple UDP ports. 10) Major cleanups, particular in the area of debugging and cookie lifetime handline, to the SCTP protocol code. From Daniel Borkmann. 11) Allow packets to cross network namespaces when traversing tunnel devices. From Nicolas Dichtel. 12) Allow monitoring netlink traffic via AF_PACKET sockets, in a manner akin to how we monitor real network traffic via ptype_all. From Daniel Borkmann. 13) Several bug fixes and improvements for the new alx device driver, from Johannes Berg. 14) Fix scalability issues in the netem packet scheduler's time queue, by using an rbtree. From Eric Dumazet. 15) Several bug fixes in TCP loss recovery handling, from Yuchung Cheng. 16) Add support for GSO segmentation of MPLS packets, from Simon Horman. 17) Make network notifiers have a real data type for the opaque pointer that's passed into them. Use this to properly handle network device flag changes in arp_netdev_event(). From Jiri Pirko and Timo Teräs. 18) Convert several drivers over to module_pci_driver(), from Peter Huewe. 19) tcp_fixup_rcvbuf() can loop 500 times over loopback, just use a O(1) calculation instead. From Eric Dumazet. 20) Support setting of explicit tunnel peer addresses in ipv6, just like ipv4. From Nicolas Dichtel. 21) Protect x86 BPF JIT against spraying attacks, from Eric Dumazet. 22) Prevent a single high rate flow from overruning an individual cpu during RX packet processing via selective flow shedding. From Willem de Bruijn. 23) Don't use spinlocks in TCP md5 signing fast paths, from Eric Dumazet. 24) Don't just drop GSO packets which are above the TBF scheduler's burst limit, chop them up so they are in-bounds instead. Also from Eric Dumazet. 25) VLAN offloads are missed when configured on top of a bridge, fix from Vlad Yasevich. 26) Support IPV6 in ping sockets. From Lorenzo Colitti. 27) Receive flow steering targets should be updated at poll() time too, from David Majnemer. 28) Fix several corner case regressions in PMTU/redirect handling due to the routing cache removal, from Timo Teräs. 29) We have to be mindful of ipv4 mapped ipv6 sockets in upd_v6_push_pending_frames(). From Hannes Frederic Sowa. 30) Fix L2TP sequence number handling bugs, from James Chapman." * git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1214 commits) drivers/net: caif: fix wrong rtnl_is_locked() usage drivers/net: enic: release rtnl_lock on error-path vhost-net: fix use-after-free in vhost_net_flush net: mv643xx_eth: do not use port number as platform device id net: sctp: confirm route during forward progress virtio_net: fix race in RX VQ processing virtio: support unlocked queue poll net/cadence/macb: fix bug/typo in extracting gem_irq_read_clear bit Documentation: Fix references to defunct linux-net@vger.kernel.org net/fs: change busy poll time accounting net: rename low latency sockets functions to busy poll bridge: fix some kernel warning in multicast timer sfc: Fix memory leak when discarding scattered packets sit: fix tunnel update via netlink dt:net:stmmac: Add dt specific phy reset callback support. dt:net:stmmac: Add support to dwmac version 3.610 and 3.710 dt:net:stmmac: Allocate platform data only if its NULL. net:stmmac: fix memleak in the open method ipv6: rt6_check_neigh should successfully verify neigh if no NUD information are available net: ipv6: fix wrong ping_v6_sendmsg return value ...
Diffstat (limited to 'fs/select.c')
-rw-r--r--fs/select.c62
1 files changed, 57 insertions, 5 deletions
diff --git a/fs/select.c b/fs/select.c
index 6b14dc7df3a4..f9f49c40cfd4 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -28,6 +28,7 @@
#include <linux/hrtimer.h>
#include <linux/sched/rt.h>
#include <linux/freezer.h>
+#include <net/ll_poll.h>
#include <asm/uaccess.h>
@@ -386,9 +387,10 @@ get_max:
#define POLLEX_SET (POLLPRI)
static inline void wait_key_set(poll_table *wait, unsigned long in,
- unsigned long out, unsigned long bit)
+ unsigned long out, unsigned long bit,
+ unsigned int ll_flag)
{
- wait->_key = POLLEX_SET;
+ wait->_key = POLLEX_SET | ll_flag;
if (in & bit)
wait->_key |= POLLIN_SET;
if (out & bit)
@@ -402,6 +404,8 @@ int do_select(int n, fd_set_bits *fds, struct timespec *end_time)
poll_table *wait;
int retval, i, timed_out = 0;
unsigned long slack = 0;
+ unsigned int busy_flag = net_busy_loop_on() ? POLL_BUSY_LOOP : 0;
+ unsigned long busy_end = 0;
rcu_read_lock();
retval = max_select_fd(n, fds);
@@ -424,6 +428,7 @@ int do_select(int n, fd_set_bits *fds, struct timespec *end_time)
retval = 0;
for (;;) {
unsigned long *rinp, *routp, *rexp, *inp, *outp, *exp;
+ bool can_busy_loop = false;
inp = fds->in; outp = fds->out; exp = fds->ex;
rinp = fds->res_in; routp = fds->res_out; rexp = fds->res_ex;
@@ -451,7 +456,8 @@ int do_select(int n, fd_set_bits *fds, struct timespec *end_time)
f_op = f.file->f_op;
mask = DEFAULT_POLLMASK;
if (f_op && f_op->poll) {
- wait_key_set(wait, in, out, bit);
+ wait_key_set(wait, in, out,
+ bit, busy_flag);
mask = (*f_op->poll)(f.file, wait);
}
fdput(f);
@@ -470,6 +476,18 @@ int do_select(int n, fd_set_bits *fds, struct timespec *end_time)
retval++;
wait->_qproc = NULL;
}
+ /* got something, stop busy polling */
+ if (retval) {
+ can_busy_loop = false;
+ busy_flag = 0;
+
+ /*
+ * only remember a returned
+ * POLL_BUSY_LOOP if we asked for it
+ */
+ } else if (busy_flag & mask)
+ can_busy_loop = true;
+
}
}
if (res_in)
@@ -488,6 +506,17 @@ int do_select(int n, fd_set_bits *fds, struct timespec *end_time)
break;
}
+ /* only if found POLL_BUSY_LOOP sockets && not out of time */
+ if (can_busy_loop && !need_resched()) {
+ if (!busy_end) {
+ busy_end = busy_loop_end_time();
+ continue;
+ }
+ if (!busy_loop_timeout(busy_end))
+ continue;
+ }
+ busy_flag = 0;
+
/*
* If this is the first loop and we have a timeout
* given, then we convert to ktime_t and set the to
@@ -719,7 +748,9 @@ struct poll_list {
* pwait poll_table will be used by the fd-provided poll handler for waiting,
* if pwait->_qproc is non-NULL.
*/
-static inline unsigned int do_pollfd(struct pollfd *pollfd, poll_table *pwait)
+static inline unsigned int do_pollfd(struct pollfd *pollfd, poll_table *pwait,
+ bool *can_busy_poll,
+ unsigned int busy_flag)
{
unsigned int mask;
int fd;
@@ -733,7 +764,10 @@ static inline unsigned int do_pollfd(struct pollfd *pollfd, poll_table *pwait)
mask = DEFAULT_POLLMASK;
if (f.file->f_op && f.file->f_op->poll) {
pwait->_key = pollfd->events|POLLERR|POLLHUP;
+ pwait->_key |= busy_flag;
mask = f.file->f_op->poll(f.file, pwait);
+ if (mask & busy_flag)
+ *can_busy_poll = true;
}
/* Mask out unneeded events. */
mask &= pollfd->events | POLLERR | POLLHUP;
@@ -752,6 +786,8 @@ static int do_poll(unsigned int nfds, struct poll_list *list,
ktime_t expire, *to = NULL;
int timed_out = 0, count = 0;
unsigned long slack = 0;
+ unsigned int busy_flag = net_busy_loop_on() ? POLL_BUSY_LOOP : 0;
+ unsigned long busy_end = 0;
/* Optimise the no-wait case */
if (end_time && !end_time->tv_sec && !end_time->tv_nsec) {
@@ -764,6 +800,7 @@ static int do_poll(unsigned int nfds, struct poll_list *list,
for (;;) {
struct poll_list *walk;
+ bool can_busy_loop = false;
for (walk = list; walk != NULL; walk = walk->next) {
struct pollfd * pfd, * pfd_end;
@@ -778,9 +815,13 @@ static int do_poll(unsigned int nfds, struct poll_list *list,
* this. They'll get immediately deregistered
* when we break out and return.
*/
- if (do_pollfd(pfd, pt)) {
+ if (do_pollfd(pfd, pt, &can_busy_loop,
+ busy_flag)) {
count++;
pt->_qproc = NULL;
+ /* found something, stop busy polling */
+ busy_flag = 0;
+ can_busy_loop = false;
}
}
}
@@ -797,6 +838,17 @@ static int do_poll(unsigned int nfds, struct poll_list *list,
if (count || timed_out)
break;
+ /* only if found POLL_BUSY_LOOP sockets && not out of time */
+ if (can_busy_loop && !need_resched()) {
+ if (!busy_end) {
+ busy_end = busy_loop_end_time();
+ continue;
+ }
+ if (!busy_loop_timeout(busy_end))
+ continue;
+ }
+ busy_flag = 0;
+
/*
* If this is the first loop and we have a timeout
* given, then we convert to ktime_t and set the to