net: poll/select low latency socket support

select/poll busy-poll support.

Split sysctl value into two separate ones, one for read and one for poll.
updated Documentation/sysctl/net.txt

Add a new poll flag POLL_LL. When this flag is set, sock_poll will call
sk_poll_ll if possible. sock_poll sets this flag in its return value
to indicate to select/poll when a socket that can busy poll is found.

When poll/select have nothing to report, call the low-level
sock_poll again until we are out of time or we find something.

Once the system call finds something, it stops setting POLL_LL, so it can
return the result to the user ASAP.

Signed-off-by: Eliezer Tamir <eliezer.tamir@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

7 files changed, 91 insertions, 22 deletions

diff --git a/Documentation/sysctl/net.txt b/Documentation/sysctl/net.txt
index 5369879eafe2..e658bbfb641f 100644
--- a/Documentation/sysctl/net.txt
+++ b/Documentation/sysctl/net.txt
@@ -50,13 +50,27 @@ The maximum number of packets that kernel can handle on a NAPI interrupt,
 it's a Per-CPU variable.
 Default: 64
 
-low_latency_poll
+low_latency_read
 ----------------
-Low latency busy poll timeout. (needs CONFIG_NET_LL_RX_POLL)
+Low latency busy poll timeout for socket reads. (needs CONFIG_NET_LL_RX_POLL)
 Approximate time in us to spin waiting for packets on the device queue.
+This sets the default value of the SO_LL socket option.
+Can be set or overridden per socket by setting socket option SO_LL.
 Recommended value is 50. May increase power usage.
 Default: 0 (off)
 
+low_latency_poll
+----------------
+Low latency busy poll timeout for poll and select. (needs CONFIG_NET_LL_RX_POLL)
+Approximate time in us to spin waiting for packets on the device queue.
+Recommended value depends on the number of sockets you poll on.
+For several sockets 50, for several hundreds 100.
+For more than that you probably want to use epoll.
+Note that only sockets with SO_LL set will be busy polled, so you want to either
+selectively set SO_LL on those sockets or set sysctl.net.low_latency_read globally.
+May increase power usage.
+Default: 0 (off)
+
 rmem_default
 ------------
 
diff --git a/fs/select.c b/fs/select.c
index 8c1c96c27062..79b876eb91da 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -27,6 +27,7 @@
 #include <linux/rcupdate.h>
 #include <linux/hrtimer.h>
 #include <linux/sched/rt.h>
+#include <net/ll_poll.h>
 
 #include <asm/uaccess.h>
 
@@ -384,9 +385,10 @@ 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)
@@ -400,6 +402,8 @@ 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 ll_flag = POLL_LL;
+        u64 ll_time = ll_end_time();
 
         rcu_read_lock();
         retval = max_select_fd(n, fds);
@@ -422,6 +426,7 @@ 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_ll = false;
 
                 inp = fds->in; outp = fds->out; exp = fds->ex;
                 rinp = fds->res_in; routp = fds->res_out; rexp = fds->res_ex;
@@ -449,7 +454,8 @@ 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, ll_flag);
                                                 mask = (*f_op->poll)(f.file, wait);
                                         }
                                         fdput(f);
@@ -468,6 +474,11 @@ int do_select(int n, fd_set_bits *fds, struct timespec *end_time)
                                                 retval++;
                                                 wait->_qproc = NULL;
                                         }
+                                        if (mask & POLL_LL)
+                                                can_ll = true;
+                                        /* got something, stop busy polling */
+                                        if (retval)
+                                                ll_flag = 0;
                                 }
                         }
                         if (res_in)
@@ -486,6 +497,9 @@ int do_select(int n, fd_set_bits *fds, struct timespec *end_time)
                         break;
                 }
 
+                if (can_ll && can_poll_ll(ll_time))
+                        continue;
+
                 /*
                  * If this is the first loop and we have a timeout
                  * given, then we convert to ktime_t and set the to
@@ -717,7 +731,8 @@ 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_ll, unsigned int ll_flag)
 {
         unsigned int mask;
         int fd;
@@ -731,7 +746,10 @@ 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 |= ll_flag;
                                 mask = f.file->f_op->poll(f.file, pwait);
+                                if (mask & POLL_LL)
+                                        *can_ll = true;
                         }
                         /* Mask out unneeded events. */
                         mask &= pollfd->events | POLLERR | POLLHUP;
@@ -750,6 +768,8 @@ 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 ll_flag = POLL_LL;
+        u64 ll_time = ll_end_time();
 
         /* Optimise the no-wait case */
         if (end_time && !end_time->tv_sec && !end_time->tv_nsec) {
@@ -762,6 +782,7 @@ static int do_poll(unsigned int nfds,  struct poll_list *list,
 
         for (;;) {
                 struct poll_list *walk;
+                bool can_ll = false;
 
                 for (walk = list; walk != NULL; walk = walk->next) {
                         struct pollfd * pfd, * pfd_end;
@@ -776,9 +797,10 @@ 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_ll, ll_flag)) {
                                         count++;
                                         pt->_qproc = NULL;
+                                        ll_flag = 0;
                                 }