aboutsummaryrefslogtreecommitdiff
path: root/fs/select.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/select.c')
-rw-r--r--fs/select.c304
1 files changed, 225 insertions, 79 deletions
diff --git a/fs/select.c b/fs/select.c
index 87df51eadcf..467bb1cb3ea 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -15,8 +15,9 @@
*/
#include <linux/kernel.h>
+#include <linux/sched.h>
#include <linux/syscalls.h>
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/slab.h>
#include <linux/poll.h>
#include <linux/personality.h> /* for STICKY_TIMEOUTS */
@@ -25,6 +26,9 @@
#include <linux/fs.h>
#include <linux/rcupdate.h>
#include <linux/hrtimer.h>
+#include <linux/sched/rt.h>
+#include <linux/freezer.h>
+#include <net/busy_poll.h>
#include <asm/uaccess.h>
@@ -41,26 +45,32 @@
* better solutions..
*/
+#define MAX_SLACK (100 * NSEC_PER_MSEC)
+
static long __estimate_accuracy(struct timespec *tv)
{
long slack;
int divfactor = 1000;
+ if (tv->tv_sec < 0)
+ return 0;
+
if (task_nice(current) > 0)
divfactor = divfactor / 5;
+ if (tv->tv_sec > MAX_SLACK / (NSEC_PER_SEC/divfactor))
+ return MAX_SLACK;
+
slack = tv->tv_nsec / divfactor;
slack += tv->tv_sec * (NSEC_PER_SEC/divfactor);
- if (slack > 100 * NSEC_PER_MSEC)
- slack = 100 * NSEC_PER_MSEC;
+ if (slack > MAX_SLACK)
+ return MAX_SLACK;
- if (slack < 0)
- slack = 0;
return slack;
}
-static long estimate_accuracy(struct timespec *tv)
+long select_estimate_accuracy(struct timespec *tv)
{
unsigned long ret;
struct timespec now;
@@ -109,11 +119,12 @@ static void __pollwait(struct file *filp, wait_queue_head_t *wait_address,
void poll_initwait(struct poll_wqueues *pwq)
{
init_poll_funcptr(&pwq->pt, __pollwait);
+ pwq->polling_task = current;
+ pwq->triggered = 0;
pwq->error = 0;
pwq->table = NULL;
pwq->inline_index = 0;
}
-
EXPORT_SYMBOL(poll_initwait);
static void free_poll_entry(struct poll_table_entry *entry)
@@ -142,12 +153,10 @@ void poll_freewait(struct poll_wqueues *pwq)
free_page((unsigned long) old);
}
}
-
EXPORT_SYMBOL(poll_freewait);
-static struct poll_table_entry *poll_get_entry(poll_table *_p)
+static struct poll_table_entry *poll_get_entry(struct poll_wqueues *p)
{
- struct poll_wqueues *p = container_of(_p, struct poll_wqueues, pt);
struct poll_table_page *table = p->table;
if (p->inline_index < N_INLINE_POLL_ENTRIES)
@@ -159,7 +168,6 @@ static struct poll_table_entry *poll_get_entry(poll_table *_p)
new_table = (struct poll_table_page *) __get_free_page(GFP_KERNEL);
if (!new_table) {
p->error = -ENOMEM;
- __set_current_state(TASK_RUNNING);
return NULL;
}
new_table->entry = new_table->entries;
@@ -171,20 +179,85 @@ static struct poll_table_entry *poll_get_entry(poll_table *_p)
return table->entry++;
}
+static int __pollwake(wait_queue_t *wait, unsigned mode, int sync, void *key)
+{
+ struct poll_wqueues *pwq = wait->private;
+ DECLARE_WAITQUEUE(dummy_wait, pwq->polling_task);
+
+ /*
+ * Although this function is called under waitqueue lock, LOCK
+ * doesn't imply write barrier and the users expect write
+ * barrier semantics on wakeup functions. The following
+ * smp_wmb() is equivalent to smp_wmb() in try_to_wake_up()
+ * and is paired with set_mb() in poll_schedule_timeout.
+ */
+ smp_wmb();
+ pwq->triggered = 1;
+
+ /*
+ * Perform the default wake up operation using a dummy
+ * waitqueue.
+ *
+ * TODO: This is hacky but there currently is no interface to
+ * pass in @sync. @sync is scheduled to be removed and once
+ * that happens, wake_up_process() can be used directly.
+ */
+ return default_wake_function(&dummy_wait, mode, sync, key);
+}
+
+static int pollwake(wait_queue_t *wait, unsigned mode, int sync, void *key)
+{
+ struct poll_table_entry *entry;
+
+ entry = container_of(wait, struct poll_table_entry, wait);
+ if (key && !((unsigned long)key & entry->key))
+ return 0;
+ return __pollwake(wait, mode, sync, key);
+}
+
/* Add a new entry */
static void __pollwait(struct file *filp, wait_queue_head_t *wait_address,
poll_table *p)
{
- struct poll_table_entry *entry = poll_get_entry(p);
+ struct poll_wqueues *pwq = container_of(p, struct poll_wqueues, pt);
+ struct poll_table_entry *entry = poll_get_entry(pwq);
if (!entry)
return;
- get_file(filp);
- entry->filp = filp;
+ entry->filp = get_file(filp);
entry->wait_address = wait_address;
- init_waitqueue_entry(&entry->wait, current);
+ entry->key = p->_key;
+ init_waitqueue_func_entry(&entry->wait, pollwake);
+ entry->wait.private = pwq;
add_wait_queue(wait_address, &entry->wait);
}
+int poll_schedule_timeout(struct poll_wqueues *pwq, int state,
+ ktime_t *expires, unsigned long slack)
+{
+ int rc = -EINTR;
+
+ set_current_state(state);
+ if (!pwq->triggered)
+ rc = schedule_hrtimeout_range(expires, slack, HRTIMER_MODE_ABS);
+ __set_current_state(TASK_RUNNING);
+
+ /*
+ * Prepare for the next iteration.
+ *
+ * The following set_mb() serves two purposes. First, it's
+ * the counterpart rmb of the wmb in pollwake() such that data
+ * written before wake up is always visible after wake up.
+ * Second, the full barrier guarantees that triggered clearing
+ * doesn't pass event check of the next iteration. Note that
+ * this problem doesn't exist for the first iteration as
+ * add_wait_queue() has full barrier semantics.
+ */
+ set_mb(pwq->triggered, 0);
+
+ return rc;
+}
+EXPORT_SYMBOL(poll_schedule_timeout);
+
/**
* poll_select_set_timeout - helper function to setup the timeout value
* @to: pointer to timespec variable for the final timeout
@@ -235,6 +308,8 @@ static int poll_select_copy_remaining(struct timespec *end_time, void __user *p,
rts.tv_sec = rts.tv_nsec = 0;
if (timeval) {
+ if (sizeof(rtv) > sizeof(rtv.tv_sec) + sizeof(rtv.tv_usec))
+ memset(&rtv, 0, sizeof(rtv));
rtv.tv_sec = rts.tv_sec;
rtv.tv_usec = rts.tv_nsec / NSEC_PER_USEC;
@@ -272,10 +347,10 @@ static int max_select_fd(unsigned long n, fd_set_bits *fds)
struct fdtable *fdt;
/* handle last in-complete long-word first */
- set = ~(~0UL << (n & (__NFDBITS-1)));
- n /= __NFDBITS;
+ set = ~(~0UL << (n & (BITS_PER_LONG-1)));
+ n /= BITS_PER_LONG;
fdt = files_fdtable(current->files);
- open_fds = fdt->open_fds->fds_bits+n;
+ open_fds = fdt->open_fds + n;
max = 0;
if (set) {
set &= BITS(fds, n);
@@ -300,7 +375,7 @@ get_max:
max++;
set >>= 1;
} while (set);
- max += n * __NFDBITS;
+ max += n * BITS_PER_LONG;
}
return max;
@@ -310,6 +385,17 @@ get_max:
#define POLLOUT_SET (POLLWRBAND | POLLWRNORM | POLLOUT | POLLERR)
#define POLLEX_SET (POLLPRI)
+static inline void wait_key_set(poll_table *wait, unsigned long in,
+ unsigned long out, unsigned long bit,
+ unsigned int ll_flag)
+{
+ wait->_key = POLLEX_SET | ll_flag;
+ if (in & bit)
+ wait->_key |= POLLIN_SET;
+ if (out & bit)
+ wait->_key |= POLLOUT_SET;
+}
+
int do_select(int n, fd_set_bits *fds, struct timespec *end_time)
{
ktime_t expire, *to = NULL;
@@ -317,6 +403,8 @@ 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);
@@ -329,18 +417,17 @@ int do_select(int n, fd_set_bits *fds, struct timespec *end_time)
poll_initwait(&table);
wait = &table.pt;
if (end_time && !end_time->tv_sec && !end_time->tv_nsec) {
- wait = NULL;
+ wait->_qproc = NULL;
timed_out = 1;
}
if (end_time && !timed_out)
- slack = estimate_accuracy(end_time);
+ slack = select_estimate_accuracy(end_time);
retval = 0;
for (;;) {
unsigned long *rinp, *routp, *rexp, *inp, *outp, *exp;
-
- set_current_state(TASK_INTERRUPTIBLE);
+ 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;
@@ -348,41 +435,58 @@ int do_select(int n, fd_set_bits *fds, struct timespec *end_time)
for (i = 0; i < n; ++rinp, ++routp, ++rexp) {
unsigned long in, out, ex, all_bits, bit = 1, mask, j;
unsigned long res_in = 0, res_out = 0, res_ex = 0;
- const struct file_operations *f_op = NULL;
- struct file *file = NULL;
in = *inp++; out = *outp++; ex = *exp++;
all_bits = in | out | ex;
if (all_bits == 0) {
- i += __NFDBITS;
+ i += BITS_PER_LONG;
continue;
}
- for (j = 0; j < __NFDBITS; ++j, ++i, bit <<= 1) {
- int fput_needed;
+ for (j = 0; j < BITS_PER_LONG; ++j, ++i, bit <<= 1) {
+ struct fd f;
if (i >= n)
break;
if (!(bit & all_bits))
continue;
- file = fget_light(i, &fput_needed);
- if (file) {
- f_op = file->f_op;
+ f = fdget(i);
+ if (f.file) {
+ const struct file_operations *f_op;
+ f_op = f.file->f_op;
mask = DEFAULT_POLLMASK;
- if (f_op && f_op->poll)
- mask = (*f_op->poll)(file, retval ? NULL : wait);
- fput_light(file, fput_needed);
+ if (f_op->poll) {
+ wait_key_set(wait, in, out,
+ bit, busy_flag);
+ mask = (*f_op->poll)(f.file, wait);
+ }
+ fdput(f);
if ((mask & POLLIN_SET) && (in & bit)) {
res_in |= bit;
retval++;
+ wait->_qproc = NULL;
}
if ((mask & POLLOUT_SET) && (out & bit)) {
res_out |= bit;
retval++;
+ wait->_qproc = NULL;
}
if ((mask & POLLEX_SET) && (ex & bit)) {
res_ex |= bit;
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)
@@ -393,7 +497,7 @@ int do_select(int n, fd_set_bits *fds, struct timespec *end_time)
*rexp = res_ex;
cond_resched();
}
- wait = NULL;
+ wait->_qproc = NULL;
if (retval || timed_out || signal_pending(current))
break;
if (table.error) {
@@ -401,6 +505,17 @@ 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
@@ -411,10 +526,10 @@ int do_select(int n, fd_set_bits *fds, struct timespec *end_time)
to = &expire;
}
- if (!schedule_hrtimeout_range(to, slack, HRTIMER_MODE_ABS))
+ if (!poll_schedule_timeout(&table, TASK_INTERRUPTIBLE,
+ to, slack))
timed_out = 1;
}
- __set_current_state(TASK_RUNNING);
poll_freewait(&table);
@@ -429,9 +544,6 @@ int do_select(int n, fd_set_bits *fds, struct timespec *end_time)
* Update: ERESTARTSYS breaks at least the xview clock binary, so
* I'm trying ERESTARTNOHAND which restart only when you want to.
*/
-#define MAX_SELECT_SECONDS \
- ((unsigned long) (MAX_SCHEDULE_TIMEOUT / HZ)-1)
-
int core_sys_select(int n, fd_set __user *inp, fd_set __user *outp,
fd_set __user *exp, struct timespec *end_time)
{
@@ -507,8 +619,8 @@ out_nofds:
return ret;
}
-asmlinkage long sys_select(int n, fd_set __user *inp, fd_set __user *outp,
- fd_set __user *exp, struct timeval __user *tvp)
+SYSCALL_DEFINE5(select, int, n, fd_set __user *, inp, fd_set __user *, outp,
+ fd_set __user *, exp, struct timeval __user *, tvp)
{
struct timespec end_time, *to = NULL;
struct timeval tv;
@@ -531,10 +643,9 @@ asmlinkage long sys_select(int n, fd_set __user *inp, fd_set __user *outp,
return ret;
}
-#ifdef HAVE_SET_RESTORE_SIGMASK
-asmlinkage long sys_pselect7(int n, fd_set __user *inp, fd_set __user *outp,
- fd_set __user *exp, struct timespec __user *tsp,
- const sigset_t __user *sigmask, size_t sigsetsize)
+static long do_pselect(int n, fd_set __user *inp, fd_set __user *outp,
+ fd_set __user *exp, struct timespec __user *tsp,
+ const sigset_t __user *sigmask, size_t sigsetsize)
{
sigset_t ksigmask, sigsaved;
struct timespec ts, end_time, *to = NULL;
@@ -560,7 +671,7 @@ asmlinkage long sys_pselect7(int n, fd_set __user *inp, fd_set __user *outp,
sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved);
}
- ret = core_sys_select(n, inp, outp, exp, &end_time);
+ ret = core_sys_select(n, inp, outp, exp, to);
ret = poll_select_copy_remaining(&end_time, tsp, 0, ret);
if (ret == -ERESTARTNOHAND) {
@@ -586,8 +697,9 @@ asmlinkage long sys_pselect7(int n, fd_set __user *inp, fd_set __user *outp,
* which has a pointer to the sigset_t itself followed by a size_t containing
* the sigset size.
*/
-asmlinkage long sys_pselect6(int n, fd_set __user *inp, fd_set __user *outp,
- fd_set __user *exp, struct timespec __user *tsp, void __user *sig)
+SYSCALL_DEFINE6(pselect6, int, n, fd_set __user *, inp, fd_set __user *, outp,
+ fd_set __user *, exp, struct timespec __user *, tsp,
+ void __user *, sig)
{
size_t sigsetsize = 0;
sigset_t __user *up = NULL;
@@ -600,9 +712,25 @@ asmlinkage long sys_pselect6(int n, fd_set __user *inp, fd_set __user *outp,
return -EFAULT;
}
- return sys_pselect7(n, inp, outp, exp, tsp, up, sigsetsize);
+ return do_pselect(n, inp, outp, exp, tsp, up, sigsetsize);
}
-#endif /* HAVE_SET_RESTORE_SIGMASK */
+
+#ifdef __ARCH_WANT_SYS_OLD_SELECT
+struct sel_arg_struct {
+ unsigned long n;
+ fd_set __user *inp, *outp, *exp;
+ struct timeval __user *tvp;
+};
+
+SYSCALL_DEFINE1(old_select, struct sel_arg_struct __user *, arg)
+{
+ struct sel_arg_struct a;
+
+ if (copy_from_user(&a, arg, sizeof(a)))
+ return -EFAULT;
+ return sys_select(a.n, a.inp, a.outp, a.exp, a.tvp);
+}
+#endif
struct poll_list {
struct poll_list *next;
@@ -617,9 +745,11 @@ struct poll_list {
* interested in events matching the pollfd->events mask, and the result
* matching that mask is both recorded in pollfd->revents and returned. The
* pwait poll_table will be used by the fd-provided poll handler for waiting,
- * if non-NULL.
+ * 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;
@@ -627,18 +757,20 @@ static inline unsigned int do_pollfd(struct pollfd *pollfd, poll_table *pwait)
mask = 0;
fd = pollfd->fd;
if (fd >= 0) {
- int fput_needed;
- struct file * file;
-
- file = fget_light(fd, &fput_needed);
+ struct fd f = fdget(fd);
mask = POLLNVAL;
- if (file != NULL) {
+ if (f.file) {
mask = DEFAULT_POLLMASK;
- if (file->f_op && file->f_op->poll)
- mask = file->f_op->poll(file, pwait);
+ if (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;
- fput_light(file, fput_needed);
+ fdput(f);
}
}
pollfd->revents = mask;
@@ -653,20 +785,22 @@ 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) {
- pt = NULL;
+ pt->_qproc = NULL;
timed_out = 1;
}
if (end_time && !timed_out)
- slack = estimate_accuracy(end_time);
+ slack = select_estimate_accuracy(end_time);
for (;;) {
struct poll_list *walk;
+ bool can_busy_loop = false;
- set_current_state(TASK_INTERRUPTIBLE);
for (walk = list; walk != NULL; walk = walk->next) {
struct pollfd * pfd, * pfd_end;
@@ -675,22 +809,26 @@ static int do_poll(unsigned int nfds, struct poll_list *list,
for (; pfd != pfd_end; pfd++) {
/*
* Fish for events. If we found one, record it
- * and kill the poll_table, so we don't
+ * and kill poll_table->_qproc, so we don't
* needlessly register any other waiters after
* 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 = NULL;
+ pt->_qproc = NULL;
+ /* found something, stop busy polling */
+ busy_flag = 0;
+ can_busy_loop = false;
}
}
}
/*
* All waiters have already been registered, so don't provide
- * a poll_table to them on the next loop iteration.
+ * a poll_table->_qproc to them on the next loop iteration.
*/
- pt = NULL;
+ pt->_qproc = NULL;
if (!count) {
count = wait->error;
if (signal_pending(current))
@@ -699,6 +837,17 @@ 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
@@ -709,10 +858,9 @@ static int do_poll(unsigned int nfds, struct poll_list *list,
to = &expire;
}
- if (!schedule_hrtimeout_range(to, slack, HRTIMER_MODE_ABS))
+ if (!poll_schedule_timeout(wait, TASK_INTERRUPTIBLE, to, slack))
timed_out = 1;
}
- __set_current_state(TASK_RUNNING);
return count;
}
@@ -732,7 +880,7 @@ int do_sys_poll(struct pollfd __user *ufds, unsigned int nfds,
struct poll_list *walk = head;
unsigned long todo = nfds;
- if (nfds > current->signal->rlim[RLIMIT_NOFILE].rlim_cur)
+ if (nfds > rlimit(RLIMIT_NOFILE))
return -EINVAL;
len = min_t(unsigned int, nfds, N_STACK_PPS);
@@ -806,8 +954,8 @@ static long do_restart_poll(struct restart_block *restart_block)
return ret;
}
-asmlinkage long sys_poll(struct pollfd __user *ufds, unsigned int nfds,
- long timeout_msecs)
+SYSCALL_DEFINE3(poll, struct pollfd __user *, ufds, unsigned int, nfds,
+ int, timeout_msecs)
{
struct timespec end_time, *to = NULL;
int ret;
@@ -840,10 +988,9 @@ asmlinkage long sys_poll(struct pollfd __user *ufds, unsigned int nfds,
return ret;
}
-#ifdef HAVE_SET_RESTORE_SIGMASK
-asmlinkage long sys_ppoll(struct pollfd __user *ufds, unsigned int nfds,
- struct timespec __user *tsp, const sigset_t __user *sigmask,
- size_t sigsetsize)
+SYSCALL_DEFINE5(ppoll, struct pollfd __user *, ufds, unsigned int, nfds,
+ struct timespec __user *, tsp, const sigset_t __user *, sigmask,
+ size_t, sigsetsize)
{
sigset_t ksigmask, sigsaved;
struct timespec ts, end_time, *to = NULL;
@@ -891,4 +1038,3 @@ asmlinkage long sys_ppoll(struct pollfd __user *ufds, unsigned int nfds,
return ret;
}
-#endif /* HAVE_SET_RESTORE_SIGMASK */
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-12-08 13:14:18 +0000