// 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/compat.h> #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 … static long __estimate_accuracy(struct timespec64 *tv) { … } u64 select_estimate_accuracy(struct timespec64 *tv) { … } struct poll_table_page { … }; #define POLL_TABLE_FULL(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) { … } EXPORT_SYMBOL(…); static void free_poll_entry(struct poll_table_entry *entry) { … } void poll_freewait(struct poll_wqueues *pwq) { … } EXPORT_SYMBOL(…); static struct poll_table_entry *poll_get_entry(struct poll_wqueues *p) { … } static int __pollwake(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) { … } static int pollwake(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) { … } /* Add a new entry */ static void __pollwait(struct file *filp, wait_queue_head_t *wait_address, poll_table *p) { … } static int poll_schedule_timeout(struct poll_wqueues *pwq, int state, ktime_t *expires, unsigned long slack) { … } /** * 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) { … } enum poll_time_type { … }; static int poll_select_finish(struct timespec64 *end_time, void __user *p, enum poll_time_type pt_type, int ret) { … } /* * Scalable version of the fd_set. */ fd_set_bits; /* * How many longwords for "nr" bits? */ #define FDS_BITPERLONG … #define FDS_LONGS(nr) … #define FDS_BYTES(nr) … /* * 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) { … } static inline unsigned long __must_check set_fd_set(unsigned long nr, void __user *ufdset, unsigned long *fdset) { … } static inline void zero_fd_set(unsigned long nr, unsigned long *fdset) { … } #define FDS_IN(fds, n) … #define FDS_OUT(fds, n) … #define FDS_EX(fds, n) … #define BITS(fds, n) … static int max_select_fd(unsigned long n, fd_set_bits *fds) { … } #define POLLIN_SET … #define POLLOUT_SET … #define POLLEX_SET … static inline void wait_key_set(poll_table *wait, unsigned long in, unsigned long out, unsigned long bit, __poll_t ll_flag) { … } static noinline_for_stack int do_select(int n, fd_set_bits *fds, struct timespec64 *end_time) { … } /* * 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) { … } static int kern_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, struct __kernel_old_timeval __user *tvp) { … } SYSCALL_DEFINE5(select, int, n, fd_set __user *, inp, fd_set __user *, outp, fd_set __user *, exp, struct __kernel_old_timeval __user *, tvp) { … } static long do_pselect(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, void __user *tsp, const sigset_t __user *sigmask, size_t sigsetsize, enum poll_time_type type) { … } /* * Most architectures can't handle 7-argument syscalls. So we provide a * 6-argument version where the sixth argument is a pointer to a structure * which has a pointer to the sigset_t itself followed by a size_t containing * the sigset size. */ struct sigset_argpack { … }; static inline int get_sigset_argpack(struct sigset_argpack *to, struct sigset_argpack __user *from) { … } SYSCALL_DEFINE6(pselect6, int, n, fd_set __user *, inp, fd_set __user *, outp, fd_set __user *, exp, struct __kernel_timespec __user *, tsp, void __user *, sig) { … } #if defined(CONFIG_COMPAT_32BIT_TIME) && !defined(CONFIG_64BIT) SYSCALL_DEFINE6(pselect6_time32, int, n, fd_set __user *, inp, fd_set __user *, outp, fd_set __user *, exp, struct old_timespec32 __user *, tsp, void __user *, sig) { struct sigset_argpack x = {NULL, 0}; if (get_sigset_argpack(&x, sig)) return -EFAULT; return do_pselect(n, inp, outp, exp, tsp, x.p, x.size, PT_OLD_TIMESPEC); } #endif #ifdef __ARCH_WANT_SYS_OLD_SELECT struct sel_arg_struct { unsigned long n; fd_set __user *inp, *outp, *exp; struct __kernel_old_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 kern_select(a.n, a.inp, a.outp, a.exp, a.tvp); } #endif struct poll_list { … }; #define POLLFD_PER_PAGE … /* * Fish for pollable events on the pollfd->fd file descriptor. We're only * 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 pwait->_qproc is non-NULL. */ static inline __poll_t do_pollfd(struct pollfd *pollfd, poll_table *pwait, bool *can_busy_poll, __poll_t busy_flag) { … } static int do_poll(struct poll_list *list, struct poll_wqueues *wait, struct timespec64 *end_time) { … } #define N_STACK_PPS … static int do_sys_poll(struct pollfd __user *ufds, unsigned int nfds, struct timespec64 *end_time) { … } static long do_restart_poll(struct restart_block *restart_block) { … } SYSCALL_DEFINE3(poll, struct pollfd __user *, ufds, unsigned int, nfds, int, timeout_msecs) { … } SYSCALL_DEFINE5(ppoll, struct pollfd __user *, ufds, unsigned int, nfds, struct __kernel_timespec __user *, tsp, const sigset_t __user *, sigmask, size_t, sigsetsize) { … } #if defined(CONFIG_COMPAT_32BIT_TIME) && !defined(CONFIG_64BIT) SYSCALL_DEFINE5(ppoll_time32, struct pollfd __user *, ufds, unsigned int, nfds, struct old_timespec32 __user *, tsp, const sigset_t __user *, sigmask, size_t, sigsetsize) { struct timespec64 ts, end_time, *to = NULL; int ret; if (tsp) { if (get_old_timespec32(&ts, tsp)) return -EFAULT; to = &end_time; if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec)) return -EINVAL; } ret = set_user_sigmask(sigmask, sigsetsize); if (ret) return ret; ret = do_sys_poll(ufds, nfds, to); return poll_select_finish(&end_time, tsp, PT_OLD_TIMESPEC, ret); } #endif #ifdef CONFIG_COMPAT #define __COMPAT_NFDBITS … /* * Ooo, nasty. We need here to frob 32-bit unsigned longs to * 64-bit unsigned longs. */ static int compat_get_fd_set(unsigned long nr, compat_ulong_t __user *ufdset, unsigned long *fdset) { … } static int compat_set_fd_set(unsigned long nr, compat_ulong_t __user *ufdset, unsigned long *fdset) { … } /* * This is a virtual copy of sys_select from fs/select.c and probably * should be compared to it from time to time */ /* * 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. */ static int compat_core_sys_select(int n, compat_ulong_t __user *inp, compat_ulong_t __user *outp, compat_ulong_t __user *exp, struct timespec64 *end_time) { … } static int do_compat_select(int n, compat_ulong_t __user *inp, compat_ulong_t __user *outp, compat_ulong_t __user *exp, struct old_timeval32 __user *tvp) { … } COMPAT_SYSCALL_DEFINE5(select, int, n, compat_ulong_t __user *, inp, compat_ulong_t __user *, outp, compat_ulong_t __user *, exp, struct old_timeval32 __user *, tvp) { … } struct compat_sel_arg_struct { … }; COMPAT_SYSCALL_DEFINE1(old_select, struct compat_sel_arg_struct __user *, arg) { … } static long do_compat_pselect(int n, compat_ulong_t __user *inp, compat_ulong_t __user *outp, compat_ulong_t __user *exp, void __user *tsp, compat_sigset_t __user *sigmask, compat_size_t sigsetsize, enum poll_time_type type) { … } struct compat_sigset_argpack { … }; static inline int get_compat_sigset_argpack(struct compat_sigset_argpack *to, struct compat_sigset_argpack __user *from) { … } COMPAT_SYSCALL_DEFINE6(pselect6_time64, int, n, compat_ulong_t __user *, inp, compat_ulong_t __user *, outp, compat_ulong_t __user *, exp, struct __kernel_timespec __user *, tsp, void __user *, sig) { … } #if defined(CONFIG_COMPAT_32BIT_TIME) COMPAT_SYSCALL_DEFINE6(pselect6_time32, int, n, compat_ulong_t __user *, inp, compat_ulong_t __user *, outp, compat_ulong_t __user *, exp, struct old_timespec32 __user *, tsp, void __user *, sig) { … } #endif #if defined(CONFIG_COMPAT_32BIT_TIME) COMPAT_SYSCALL_DEFINE5(ppoll_time32, struct pollfd __user *, ufds, unsigned int, nfds, struct old_timespec32 __user *, tsp, const compat_sigset_t __user *, sigmask, compat_size_t, sigsetsize) { … } #endif /* New compat syscall for 64 bit time_t*/ COMPAT_SYSCALL_DEFINE5(ppoll_time64, struct pollfd __user *, ufds, unsigned int, nfds, struct __kernel_timespec __user *, tsp, const compat_sigset_t __user *, sigmask, compat_size_t, sigsetsize) { … } #endif
Codebase Browser
linux