cregit-Linux how code gets into the kernel

Release 4.18 fs/select.c

Directory: fs
// SPDX-License-Identifier: GPL-2.0
/*
 * This file contains the procedures for the handling of select and poll
 *
 * Created for Linux based loosely upon Mathius Lattner's minix
 * patches by Peter MacDonald. Heavily edited by Linus.
 *
 *  4 February 1994
 *     COFF/ELF binary emulation. If the process has the STICKY_TIMEOUTS
 *     flag set in its personality we do *not* modify the given timeout
 *     parameter to reflect time remaining.
 *
 *  24 January 2000
 *     Changed sys_poll()/do_poll() to use PAGE_SIZE chunk-based allocation 
 *     of fds to overcome nfds < 16390 descriptors limit (Tigran Aivazian).
 */

#include <linux/kernel.h>
#include <linux/sched/signal.h>
#include <linux/sched/rt.h>
#include <linux/syscalls.h>
#include <linux/export.h>
#include <linux/slab.h>
#include <linux/poll.h>
#include <linux/personality.h> /* for STICKY_TIMEOUTS */
#include <linux/file.h>
#include <linux/fdtable.h>
#include <linux/fs.h>
#include <linux/rcupdate.h>
#include <linux/hrtimer.h>
#include <linux/freezer.h>
#include <net/busy_poll.h>
#include <linux/vmalloc.h>

#include <linux/uaccess.h>


/*
 * Estimate expected accuracy in ns from a timeval.
 *
 * After quite a bit of churning around, we've settled on
 * a simple thing of taking 0.1% of the timeout as the
 * slack, with a cap of 100 msec.
 * "nice" tasks get a 0.5% slack instead.
 *
 * Consider this comment an open invitation to come up with even
 * better solutions..
 */


#define MAX_SLACK	(100 * NSEC_PER_MSEC)


static long __estimate_accuracy(struct timespec64 *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 > MAX_SLACK) return MAX_SLACK; return slack; }

Contributors

PersonTokensPropCommitsCommitProp
Arjan van de Ven6164.89%360.00%
Guillaume Knispel3234.04%120.00%
Deepa Dinamani11.06%120.00%
Total94100.00%5100.00%


u64 select_estimate_accuracy(struct timespec64 *tv) { u64 ret; struct timespec64 now; /* * Realtime tasks get a slack of 0 for obvious reasons. */ if (rt_task(current)) return 0; ktime_get_ts64(&now); now = timespec64_sub(*tv, now); ret = __estimate_accuracy(&now); if (ret < current->timer_slack_ns) return current->timer_slack_ns; return ret; }

Contributors

PersonTokensPropCommitsCommitProp
Arjan van de Ven6189.71%240.00%
Deepa Dinamani45.88%120.00%
John Stultz22.94%120.00%
Andrew Morton11.47%120.00%
Total68100.00%5100.00%

struct poll_table_page { struct poll_table_page * next; struct poll_table_entry * entry; struct poll_table_entry entries[0]; }; #define POLL_TABLE_FULL(table) \ ((unsigned long)((table)->entry+1) > PAGE_SIZE + (unsigned long)(table)) /* * Ok, Peter made a complicated, but straightforward multiple_wait() function. * I have rewritten this, taking some shortcuts: This code may not be easy to * follow, but it should be free of race-conditions, and it's practical. If you * understand what I'm doing here, then you understand how the linux * sleep/wakeup mechanism works. * * Two very simple procedures, poll_wait() and poll_freewait() make all the * work. poll_wait() is an inline-function defined in <linux/poll.h>, * as all select/poll functions have to call it to add an entry to the * poll table. */ static void __pollwait(struct file *filp, wait_queue_head_t *wait_address, poll_table *p);
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; }

Contributors

PersonTokensPropCommitsCommitProp
Manfred Spraul3162.00%120.00%
Andi Kleen612.00%120.00%
Tejun Heo612.00%120.00%
Guillaume Knispel612.00%120.00%
Linus Torvalds (pre-git)12.00%120.00%
Total50100.00%5100.00%

EXPORT_SYMBOL(poll_initwait);
static void free_poll_entry(struct poll_table_entry *entry) { remove_wait_queue(entry->wait_address, &entry->wait); fput(entry->filp); }

Contributors

PersonTokensPropCommitsCommitProp
Andi Kleen30100.00%1100.00%
Total30100.00%1100.00%


void poll_freewait(struct poll_wqueues *pwq) { struct poll_table_page * p = pwq->table; int i; for (i = 0; i < pwq->inline_index; i++) free_poll_entry(pwq->inline_entries + i); while (p) { struct poll_table_entry * entry; struct poll_table_page *old; entry = p->entry; do { entry--; free_poll_entry(entry); } while (entry > p->entries); old = p; p = p->next; free_page((unsigned long) old); } }

Contributors

PersonTokensPropCommitsCommitProp
Linus Torvalds (pre-git)7166.36%1184.62%
Andi Kleen2826.17%17.69%
Manfred Spraul87.48%17.69%
Total107100.00%13100.00%

EXPORT_SYMBOL(poll_freewait);
static struct poll_table_entry *poll_get_entry(struct poll_wqueues *p) { struct poll_table_page *table = p->table; if (p->inline_index < N_INLINE_POLL_ENTRIES) return p->inline_entries + p->inline_index++; if (!table || POLL_TABLE_FULL(table)) { struct poll_table_page *new_table; new_table = (struct poll_table_page *) __get_free_page(GFP_KERNEL); if (!new_table) { p->error = -ENOMEM; return NULL; } new_table->entry = new_table->entries; new_table->next = table; p->table = new_table; table = new_table; } return table->entry++; }

Contributors

PersonTokensPropCommitsCommitProp
Linus Torvalds (pre-git)7867.24%342.86%
Andi Kleen3126.72%114.29%
Manfred Spraul43.45%114.29%
Tejun Heo21.72%114.29%
Adrian Bunk10.86%114.29%
Total116100.00%7100.00%


static int __pollwake(wait_queue_entry_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 smp_store_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); }

Contributors

PersonTokensPropCommitsCommitProp
Tejun Heo5995.16%125.00%
Peter Zijlstra11.61%125.00%
Eric Dumazet11.61%125.00%
Ingo Molnar11.61%125.00%
Total62100.00%4100.00%


static int pollwake(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) { struct poll_table_entry *entry; entry = container_of(wait, struct poll_table_entry, wait); if (key && !(key_to_poll(key) & entry->key)) return 0; return __pollwake(wait, mode, sync, key); }

Contributors

PersonTokensPropCommitsCommitProp
Eric Dumazet6494.12%133.33%
Al Viro34.41%133.33%
Ingo Molnar11.47%133.33%
Total68100.00%3100.00%

/* Add a new entry */
static void __pollwait(struct file *filp, wait_queue_head_t *wait_address, poll_table *p) { struct poll_wqueues *pwq = container_of(p, struct poll_wqueues, pt); struct poll_table_entry *entry = poll_get_entry(pwq); if (!entry) return; entry->filp = get_file(filp); entry->wait_address = wait_address; entry->key = p->_key; init_waitqueue_func_entry(&entry->wait, pollwake); entry->wait.private = pwq; add_wait_queue(wait_address, &entry->wait); }

Contributors

PersonTokensPropCommitsCommitProp
Linus Torvalds (pre-git)3938.61%444.44%
Tejun Heo2625.74%111.11%
Andi Kleen2524.75%111.11%
Eric Dumazet76.93%111.11%
Al Viro32.97%111.11%
Hans Verkuil10.99%111.11%
Total101100.00%9100.00%


static 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 smp_store_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. */ smp_store_mb(pwq->triggered, 0); return rc; }

Contributors

PersonTokensPropCommitsCommitProp
Tejun Heo6594.20%125.00%
Peter Zijlstra22.90%125.00%
Rafael J. Wysocki11.45%125.00%
Christoph Hellwig11.45%125.00%
Total69100.00%4100.00%

/** * poll_select_set_timeout - helper function to setup the timeout value * @to: pointer to timespec64 variable for the final timeout * @sec: seconds (from user space) * @nsec: nanoseconds (from user space) * * Note, we do not use a timespec for the user space value here, That * way we can use the function for timeval and compat interfaces as well. * * Returns -EINVAL if sec/nsec are not normalized. Otherwise 0. */
int poll_select_set_timeout(struct timespec64 *to, time64_t sec, long nsec) { struct timespec64 ts = {.tv_sec = sec, .tv_nsec = nsec}; if (!timespec64_valid(&ts)) return -EINVAL; /* Optimize for the zero timeout value here */ if (!sec && !nsec) { to->tv_sec = to->tv_nsec = 0; } else { ktime_get_ts64(to); *to = timespec64_add_safe(*to, ts); } return 0; }

Contributors

PersonTokensPropCommitsCommitProp
Thomas Gleixner8293.18%150.00%
Deepa Dinamani66.82%150.00%
Total88100.00%2100.00%


static int poll_select_copy_remaining(struct timespec64 *end_time, void __user *p, int timeval, int ret) { struct timespec64 rts; struct timeval rtv; if (!p) return ret; if (current->personality & STICKY_TIMEOUTS) goto sticky; /* No update for zero timeout */ if (!end_time->tv_sec && !end_time->tv_nsec) return ret; ktime_get_ts64(&rts); rts = timespec64_sub(*end_time, rts); if (rts.tv_sec < 0) 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; if (!copy_to_user(p, &rtv, sizeof(rtv))) return ret; } else if (!put_timespec64(&rts, p)) return ret; /* * If an application puts its timeval in read-only memory, we * don't want the Linux-specific update to the timeval to * cause a fault after the select has completed * successfully. However, because we're not updating the * timeval, we can't restart the system call. */ sticky: if (ret == -ERESTARTNOHAND) ret = -EINTR; return ret; }

Contributors

PersonTokensPropCommitsCommitProp
Thomas Gleixner16177.03%125.00%
Vasiliy Kulikov3416.27%125.00%
Deepa Dinamani146.70%250.00%
Total209100.00%4100.00%

/* * Scalable version of the fd_set. */ typedef struct { unsigned long *in, *out, *ex; unsigned long *res_in, *res_out, *res_ex; } fd_set_bits; /* * How many longwords for "nr" bits? */ #define FDS_BITPERLONG (8*sizeof(long)) #define FDS_LONGS(nr) (((nr)+FDS_BITPERLONG-1)/FDS_BITPERLONG) #define FDS_BYTES(nr) (FDS_LONGS(nr)*sizeof(long)) /* * We do a VERIFY_WRITE here even though we are only reading this time: * we'll write to it eventually.. * * Use "unsigned long" accesses to let user-mode fd_set's be long-aligned. */
static inline int get_fd_set(unsigned long nr, void __user *ufdset, unsigned long *fdset) { nr = FDS_BYTES(nr); if (ufdset) return copy_from_user(fdset, ufdset, nr) ? -EFAULT : 0; memset(fdset, 0, nr); return 0; }

Contributors

PersonTokensPropCommitsCommitProp
Al Viro59100.00%1100.00%
Total59100.00%1100.00%


static inline unsigned long __must_check set_fd_set(unsigned long nr, void __user *ufdset, unsigned long *fdset) { if (ufdset) return __copy_to_user(ufdset, fdset, FDS_BYTES(nr)); return 0; }

Contributors

PersonTokensPropCommitsCommitProp
Al Viro43100.00%1100.00%
Total43100.00%1100.00%


static inline void zero_fd_set(unsigned long nr, unsigned long *fdset) { memset(fdset, 0, FDS_BYTES(nr)); }

Contributors

PersonTokensPropCommitsCommitProp
Al Viro28100.00%1100.00%
Total28100.00%1100.00%

#define FDS_IN(fds, n) (fds->in + n) #define FDS_OUT(fds, n) (fds->out + n) #define FDS_EX(fds, n) (fds->ex + n) #define BITS(fds, n) (*FDS_IN(fds, n)|*FDS_OUT(fds, n)|*FDS_EX(fds, n))
static int max_select_fd(unsigned long n, fd_set_bits *fds) { unsigned long *open_fds; unsigned long set; int max; struct fdtable *fdt; /* handle last in-complete long-word first */ set = ~(~0UL << (n & (BITS_PER_LONG-1))); n /= BITS_PER_LONG; fdt = files_fdtable(current->files); open_fds = fdt->open_fds + n; max = 0; if (set) { set &= BITS(fds, n); if (set) { if (!(set & ~*open_fds)) goto get_max; return -EBADF; } } while (n) { open_fds--; n--; set = BITS(fds, n); if (!set) continue; if (set & ~*open_fds) return -EBADF; if (max) continue; get_max: do { max++; set >>= 1; } while (set); max += n * BITS_PER_LONG; } return max; }

Contributors

PersonTokensPropCommitsCommitProp
Linus Torvalds (pre-git)16891.30%777.78%
Dipankar Sarma137.07%111.11%
Josh Boyer31.63%111.11%
Total184100.00%9100.00%

#define POLLIN_SET (EPOLLRDNORM | EPOLLRDBAND | EPOLLIN | EPOLLHUP | EPOLLERR) #define POLLOUT_SET (EPOLLWRBAND | EPOLLWRNORM | EPOLLOUT | EPOLLERR) #define POLLEX_SET (EPOLLPRI)
static inline void wait_key_set(poll_table *wait, unsigned long in, unsigned long out, unsigned long bit, __poll_t ll_flag) { wait->_key = POLLEX_SET | ll_flag; if (in & bit) wait->_key |= POLLIN_SET; if (out & bit) wait->_key |= POLLOUT_SET; }

Contributors

PersonTokensPropCommitsCommitProp
Eric Dumazet5086.21%125.00%
Eliezer Tamir46.90%125.00%
Hans Verkuil35.17%125.00%
Al Viro11.72%125.00%
Total58100.00%4100.00%


static int do_select(int n, fd_set_bits *fds, struct timespec64 *end_time) { ktime_t expire, *to = NULL; struct poll_wqueues table; poll_table *wait; int retval, i, timed_out = 0; u64 slack = 0; __poll_t busy_flag = net_busy_loop_on() ? POLL_BUSY_LOOP : 0; unsigned long busy_start = 0; rcu_read_lock(); retval = max_select_fd(n, fds); rcu_read_unlock(); if (retval < 0) return retval; n = retval; poll_initwait(&table); wait = &table.pt; if (end_time && !end_time->tv_sec && !end_time->tv_nsec) { wait->_qproc = NULL; timed_out = 1; } if (end_time && !timed_out) slack = select_estimate_accuracy(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; for (i = 0; i < n; ++rinp, ++routp, ++rexp) { unsigned long in, out, ex, all_bits, bit = 1, j; unsigned long res_in = 0, res_out = 0, res_ex = 0; __poll_t mask; in = *inp++; out = *outp++; ex = *exp++; all_bits = in | out | ex; if (all_bits == 0) { i += BITS_PER_LONG; continue; } for (j = 0; j < BITS_PER_LONG; ++j, ++i, bit <<= 1) { struct fd f; if (i >= n) break; if (!(bit & all_bits)) continue; f = fdget(i); if (f.file) { wait_key_set(wait, in, out, bit, busy_flag); mask = vfs_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) *rinp = res_in; if (res_out) *routp = res_out; if (res_ex) *rexp = res_ex; cond_resched(); } wait->_qproc = NULL; if (retval || timed_out || signal_pending(current)) break; if (table.error) { retval = table.error; break; } /* only if found POLL_BUSY_LOOP sockets && not out of time */ if (can_busy_loop && !need_resched()) { if (!busy_start) { busy_start = busy_loop_current_time(); continue; } if (!busy_loop_timeout(busy_start)) 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 * pointer to the expiry value. */ if (end_time && !to) { expire = timespec64_to_ktime(*end_time); to = &expire; } if (!poll_schedule_timeout(&table, TASK_INTERRUPTIBLE, to, slack)) timed_out = 1; } poll_freewait(&table); return retval; }

Contributors

PersonTokensPropCommitsCommitProp
Linus Torvalds (pre-git)22233.53%2144.68%
Andrew Morton19629.61%24.26%
Eliezer Tamir8112.24%48.51%
Arjan van de Ven6710.12%36.38%
Eric Dumazet243.63%24.26%
David Woodhouse162.42%12.13%
Al Viro162.42%48.51%
Hans Verkuil101.51%12.13%
Manfred Spraul60.91%12.13%
Tejun Heo60.91%12.13%
Alexander Duyck50.76%12.13%
Dipankar Sarma40.60%12.13%
Linus Torvalds30.45%12.13%
Deepa Dinamani20.30%12.13%
Josh Boyer20.30%12.13%
Christoph Hellwig10.15%12.13%
John Stultz10.15%12.13%
Total662100.00%47100.00%

/* * We can actually return ERESTARTSYS instead of EINTR, but I'd * like to be certain this leads to no problems. So I return * EINTR just for safety. * * Update: ERESTARTSYS breaks at least the xview clock binary, so * I'm trying ERESTARTNOHAND which restart only when you want to. */
int core_sys_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, struct timespec64 *end_time) { fd_set_bits fds; void *bits; int ret, max_fds; size_t size, alloc_size; struct fdtable *fdt; /* Allocate small arguments on the stack to save memory and be faster */ long stack_fds[SELECT_STACK_ALLOC/sizeof(long)]; ret = -EINVAL; if (n < 0) goto out_nofds; /* max_fds can increase, so grab it once to avoid race */ rcu_read_lock(); fdt = files_fdtable(current->files); max_fds = fdt->max_fds; rcu_read_unlock(); if (n > max_fds) n = max_fds; /* * We need 6 bitmaps (in/out/ex for both incoming and outgoing), * since we used fdset we need to allocate memory in units of * long-words. */ size = FDS_BYTES(n); bits = stack_fds; if (size > sizeof(stack_fds) / 6) { /* Not enough space in on-stack array; must use kmalloc */ ret = -ENOMEM; if (size > (SIZE_MAX / 6)) goto out_nofds; alloc_size = 6 * size; bits = kvmalloc(alloc_size, GFP_KERNEL); if (!bits) goto out_nofds; } fds.in = bits; fds.out = bits + size; fds.ex = bits + 2*size; fds.res_in = bits + 3*size; fds.res_out = bits + 4*size; fds.res_ex = bits + 5*size; if ((ret = get_fd_set(n, inp, fds.in)) || (ret = get_fd_set(n, outp, fds.out)) || (ret = get_fd_set(n, exp, fds.ex))) goto out; zero_fd_set(n, fds.res_in); zero_fd_set(n, fds.res_out); zero_fd_set(n, fds.res_ex); ret = do_select(n, &fds, end_time); if (ret < 0) goto out; if (!ret) { ret = -ERESTARTNOHAND; if (signal_pending(current)) goto out; ret = 0; } if (set_fd_set(n, inp, fds.res_in) || set_fd_set(n, outp, fds.res_out) || set_fd_set(n, exp, fds.res_ex)) ret = -EFAULT; out: if (bits != stack_fds) kvfree(bits); out_nofds: return ret; }

Contributors

PersonTokensPropCommitsCommitProp
Linus Torvalds (pre-git)26664.72%1448.28%
David Woodhouse297.06%13.45%
Vlastimil Babka235.60%13.45%
Andi Kleen225.35%13.45%
Mitchell Blank Jr.194.62%13.45%
Dipankar Sarma184.38%26.90%
Linus Torvalds92.19%26.90%
Andrew Morton81.95%26.90%
Vadim Lobanov61.46%13.45%
Jes Sorensen61.46%13.45%
Arjan van de Ven30.73%13.45%
Deepa Dinamani10.24%13.45%
Michal Hocko10.24%13.45%
Total411100.00%29100.00%


static int kern_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, struct timeval __user *tvp) { struct timespec64 end_time, *to = NULL; struct timeval tv; int ret; if (tvp) { if (copy_from_user(&tv, tvp, sizeof(tv