From 102a0743326a03cd1a1202ceda21e175b7d3575c Mon Sep 17 00:00:00 2001 From: hc <hc@nodka.com> Date: Tue, 20 Feb 2024 01:20:52 +0000 Subject: [PATCH] add new system file --- kernel/fs/select.c | 505 +++++++++++++++++++++++++++++-------------------------- 1 files changed, 264 insertions(+), 241 deletions(-) diff --git a/kernel/fs/select.c b/kernel/fs/select.c index 1c3985d..5edffee 100644 --- a/kernel/fs/select.c +++ b/kernel/fs/select.c @@ -97,7 +97,7 @@ struct poll_table_page { struct poll_table_page * next; struct poll_table_entry * entry; - struct poll_table_entry entries[0]; + struct poll_table_entry entries[]; }; #define POLL_TABLE_FULL(table) \ @@ -287,12 +287,20 @@ return 0; } -static int poll_select_copy_remaining(struct timespec64 *end_time, - void __user *p, - int timeval, int ret) +enum poll_time_type { + PT_TIMEVAL = 0, + PT_OLD_TIMEVAL = 1, + PT_TIMESPEC = 2, + PT_OLD_TIMESPEC = 3, +}; + +static int poll_select_finish(struct timespec64 *end_time, + void __user *p, + enum poll_time_type pt_type, int ret) { struct timespec64 rts; - struct timeval rtv; + + restore_saved_sigmask_unless(ret == -ERESTARTNOHAND); if (!p) return ret; @@ -310,18 +318,40 @@ 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; + switch (pt_type) { + case PT_TIMEVAL: + { + struct __kernel_old_timeval rtv; - if (!copy_to_user(p, &rtv, sizeof(rtv))) + 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; + } + break; + case PT_OLD_TIMEVAL: + { + struct old_timeval32 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; + } + break; + case PT_TIMESPEC: + if (!put_timespec64(&rts, p)) return ret; - - } else if (!put_timespec64(&rts, p)) - return ret; - + break; + case PT_OLD_TIMESPEC: + if (!put_old_timespec32(&rts, p)) + return ret; + break; + default: + BUG(); + } /* * If an application puts its timeval in read-only memory, we * don't want the Linux-specific update to the timeval to @@ -353,9 +383,6 @@ #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 @@ -674,10 +701,10 @@ } static int kern_select(int n, fd_set __user *inp, fd_set __user *outp, - fd_set __user *exp, struct timeval __user *tvp) + fd_set __user *exp, struct __kernel_old_timeval __user *tvp) { struct timespec64 end_time, *to = NULL; - struct timeval tv; + struct __kernel_old_timeval tv; int ret; if (tvp) { @@ -692,63 +719,48 @@ } ret = core_sys_select(n, inp, outp, exp, to); - ret = poll_select_copy_remaining(&end_time, tvp, 1, ret); - - return ret; + return poll_select_finish(&end_time, tvp, PT_TIMEVAL, ret); } SYSCALL_DEFINE5(select, int, n, fd_set __user *, inp, fd_set __user *, outp, - fd_set __user *, exp, struct timeval __user *, tvp) + fd_set __user *, exp, struct __kernel_old_timeval __user *, tvp) { return kern_select(n, inp, outp, exp, tvp); } 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) + fd_set __user *exp, void __user *tsp, + const sigset_t __user *sigmask, size_t sigsetsize, + enum poll_time_type type) { - sigset_t ksigmask, sigsaved; struct timespec64 ts, end_time, *to = NULL; int ret; if (tsp) { - if (get_timespec64(&ts, tsp)) - return -EFAULT; + switch (type) { + case PT_TIMESPEC: + if (get_timespec64(&ts, tsp)) + return -EFAULT; + break; + case PT_OLD_TIMESPEC: + if (get_old_timespec32(&ts, tsp)) + return -EFAULT; + break; + default: + BUG(); + } to = &end_time; if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec)) return -EINVAL; } - if (sigmask) { - /* XXX: Don't preclude handling different sized sigset_t's. */ - if (sigsetsize != sizeof(sigset_t)) - return -EINVAL; - if (copy_from_user(&ksigmask, sigmask, sizeof(ksigmask))) - return -EFAULT; - - sigdelsetmask(&ksigmask, sigmask(SIGKILL)|sigmask(SIGSTOP)); - sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved); - } + ret = set_user_sigmask(sigmask, sigsetsize); + if (ret) + return ret; ret = core_sys_select(n, inp, outp, exp, to); - ret = poll_select_copy_remaining(&end_time, tsp, 0, ret); - - if (ret == -ERESTARTNOHAND) { - /* - * Don't restore the signal mask yet. Let do_signal() deliver - * the signal on the way back to userspace, before the signal - * mask is restored. - */ - if (sigmask) { - memcpy(¤t->saved_sigmask, &sigsaved, - sizeof(sigsaved)); - set_restore_sigmask(); - } - } else if (sigmask) - sigprocmask(SIG_SETMASK, &sigsaved, NULL); - - return ret; + return poll_select_finish(&end_time, tsp, type, ret); } /* @@ -757,29 +769,61 @@ * which has a pointer to the sigset_t itself followed by a size_t containing * the sigset size. */ +struct sigset_argpack { + sigset_t __user *p; + size_t size; +}; + +static inline int get_sigset_argpack(struct sigset_argpack *to, + struct sigset_argpack __user *from) +{ + // the path is hot enough for overhead of copy_from_user() to matter + if (from) { + if (!user_read_access_begin(from, sizeof(*from))) + return -EFAULT; + unsafe_get_user(to->p, &from->p, Efault); + unsafe_get_user(to->size, &from->size, Efault); + user_read_access_end(); + } + return 0; +Efault: + user_access_end(); + return -EFAULT; +} + SYSCALL_DEFINE6(pselect6, int, n, fd_set __user *, inp, fd_set __user *, outp, - fd_set __user *, exp, struct timespec __user *, tsp, + fd_set __user *, exp, struct __kernel_timespec __user *, tsp, void __user *, sig) { - size_t sigsetsize = 0; - sigset_t __user *up = NULL; + struct sigset_argpack x = {NULL, 0}; - if (sig) { - if (!access_ok(VERIFY_READ, sig, sizeof(void *)+sizeof(size_t)) - || __get_user(up, (sigset_t __user * __user *)sig) - || __get_user(sigsetsize, - (size_t __user *)(sig+sizeof(void *)))) - return -EFAULT; - } + if (get_sigset_argpack(&x, sig)) + return -EFAULT; - return do_pselect(n, inp, outp, exp, tsp, up, sigsetsize); + return do_pselect(n, inp, outp, exp, tsp, x.p, x.size, PT_TIMESPEC); } + +#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 timeval __user *tvp; + struct __kernel_old_timeval __user *tvp; }; SYSCALL_DEFINE1(old_select, struct sel_arg_struct __user *, arg) @@ -795,7 +839,7 @@ struct poll_list { struct poll_list *next; int len; - struct pollfd entries[0]; + struct pollfd entries[]; }; #define POLLFD_PER_PAGE ((PAGE_SIZE-sizeof(struct poll_list)) / sizeof(struct pollfd)) @@ -891,7 +935,7 @@ if (!count) { count = wait->error; if (signal_pending(current)) - count = -EINTR; + count = -ERESTARTNOHAND; } if (count || timed_out) break; @@ -930,7 +974,7 @@ struct timespec64 *end_time) { struct poll_wqueues table; - int err = -EFAULT, fdcount, len, size; + int err = -EFAULT, fdcount, len; /* Allocate small arguments on the stack to save memory and be faster - use long to make sure the buffer is aligned properly on 64 bit archs to avoid unaligned access */ @@ -958,8 +1002,8 @@ break; len = min(todo, POLLFD_PER_PAGE); - size = sizeof(struct poll_list) + sizeof(struct pollfd) * len; - walk = walk->next = kmalloc(size, GFP_KERNEL); + walk = walk->next = kmalloc(struct_size(walk, entries, len), + GFP_KERNEL); if (!walk) { err = -ENOMEM; goto out_fds; @@ -970,14 +1014,17 @@ fdcount = do_poll(head, &table, end_time); poll_freewait(&table); + if (!user_write_access_begin(ufds, nfds * sizeof(*ufds))) + goto out_fds; + for (walk = head; walk; walk = walk->next) { struct pollfd *fds = walk->entries; int j; - for (j = 0; j < walk->len; j++, ufds++) - if (__put_user(fds[j].revents, &ufds->revents)) - goto out_fds; + for (j = walk->len; j; fds++, ufds++, j--) + unsafe_put_user(fds->revents, &ufds->revents, Efault); } + user_write_access_end(); err = fdcount; out_fds: @@ -989,6 +1036,11 @@ } return err; + +Efault: + user_write_access_end(); + err = -EFAULT; + goto out_fds; } static long do_restart_poll(struct restart_block *restart_block) @@ -1006,7 +1058,7 @@ ret = do_sys_poll(ufds, nfds, to); - if (ret == -EINTR) + if (ret == -ERESTARTNOHAND) ret = set_restart_fn(restart_block, do_restart_poll); return ret; @@ -1026,7 +1078,7 @@ ret = do_sys_poll(ufds, nfds, to); - if (ret == -EINTR) { + if (ret == -ERESTARTNOHAND) { struct restart_block *restart_block; restart_block = ¤t->restart_block; @@ -1046,10 +1098,9 @@ } SYSCALL_DEFINE5(ppoll, struct pollfd __user *, ufds, unsigned int, nfds, - struct timespec __user *, tsp, const sigset_t __user *, sigmask, + struct __kernel_timespec __user *, tsp, const sigset_t __user *, sigmask, size_t, sigsetsize) { - sigset_t ksigmask, sigsaved; struct timespec64 ts, end_time, *to = NULL; int ret; @@ -1062,89 +1113,43 @@ return -EINVAL; } - if (sigmask) { - /* XXX: Don't preclude handling different sized sigset_t's. */ - if (sigsetsize != sizeof(sigset_t)) - return -EINVAL; - if (copy_from_user(&ksigmask, sigmask, sizeof(ksigmask))) - return -EFAULT; - - sigdelsetmask(&ksigmask, sigmask(SIGKILL)|sigmask(SIGSTOP)); - sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved); - } + ret = set_user_sigmask(sigmask, sigsetsize); + if (ret) + return ret; ret = do_sys_poll(ufds, nfds, to); - - /* We can restart this syscall, usually */ - if (ret == -EINTR) { - /* - * Don't restore the signal mask yet. Let do_signal() deliver - * the signal on the way back to userspace, before the signal - * mask is restored. - */ - if (sigmask) { - memcpy(¤t->saved_sigmask, &sigsaved, - sizeof(sigsaved)); - set_restore_sigmask(); - } - ret = -ERESTARTNOHAND; - } else if (sigmask) - sigprocmask(SIG_SETMASK, &sigsaved, NULL); - - ret = poll_select_copy_remaining(&end_time, tsp, 0, ret); - - return ret; + return poll_select_finish(&end_time, tsp, PT_TIMESPEC, ret); } + +#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 (8 * sizeof(compat_ulong_t)) - -static -int compat_poll_select_copy_remaining(struct timespec64 *end_time, void __user *p, - int timeval, int ret) -{ - struct timespec64 ts; - - 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(&ts); - ts = timespec64_sub(*end_time, ts); - if (ts.tv_sec < 0) - ts.tv_sec = ts.tv_nsec = 0; - - if (timeval) { - struct compat_timeval rtv; - - rtv.tv_sec = ts.tv_sec; - rtv.tv_usec = ts.tv_nsec / NSEC_PER_USEC; - - if (!copy_to_user(p, &rtv, sizeof(rtv))) - return ret; - } else { - if (!compat_put_timespec64(&ts, 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; -} /* * Ooo, nasty. We need here to frob 32-bit unsigned longs to @@ -1258,10 +1263,10 @@ static int do_compat_select(int n, compat_ulong_t __user *inp, compat_ulong_t __user *outp, compat_ulong_t __user *exp, - struct compat_timeval __user *tvp) + struct old_timeval32 __user *tvp) { struct timespec64 end_time, *to = NULL; - struct compat_timeval tv; + struct old_timeval32 tv; int ret; if (tvp) { @@ -1276,14 +1281,12 @@ } ret = compat_core_sys_select(n, inp, outp, exp, to); - ret = compat_poll_select_copy_remaining(&end_time, tvp, 1, ret); - - return ret; + return poll_select_finish(&end_time, tvp, PT_OLD_TIMEVAL, ret); } COMPAT_SYSCALL_DEFINE5(select, int, n, compat_ulong_t __user *, inp, compat_ulong_t __user *, outp, compat_ulong_t __user *, exp, - struct compat_timeval __user *, tvp) + struct old_timeval32 __user *, tvp) { return do_compat_select(n, inp, outp, exp, tvp); } @@ -1308,81 +1311,99 @@ static long do_compat_pselect(int n, compat_ulong_t __user *inp, compat_ulong_t __user *outp, compat_ulong_t __user *exp, - struct compat_timespec __user *tsp, compat_sigset_t __user *sigmask, - compat_size_t sigsetsize) + void __user *tsp, compat_sigset_t __user *sigmask, + compat_size_t sigsetsize, enum poll_time_type type) { - sigset_t ksigmask, sigsaved; struct timespec64 ts, end_time, *to = NULL; int ret; if (tsp) { - if (compat_get_timespec64(&ts, tsp)) - return -EFAULT; + switch (type) { + case PT_OLD_TIMESPEC: + if (get_old_timespec32(&ts, tsp)) + return -EFAULT; + break; + case PT_TIMESPEC: + if (get_timespec64(&ts, tsp)) + return -EFAULT; + break; + default: + BUG(); + } to = &end_time; if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec)) return -EINVAL; } - if (sigmask) { - if (sigsetsize != sizeof(compat_sigset_t)) - return -EINVAL; - if (get_compat_sigset(&ksigmask, sigmask)) - return -EFAULT; - - sigdelsetmask(&ksigmask, sigmask(SIGKILL)|sigmask(SIGSTOP)); - sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved); - } + ret = set_compat_user_sigmask(sigmask, sigsetsize); + if (ret) + return ret; ret = compat_core_sys_select(n, inp, outp, exp, to); - ret = compat_poll_select_copy_remaining(&end_time, tsp, 0, ret); - - if (ret == -ERESTARTNOHAND) { - /* - * Don't restore the signal mask yet. Let do_signal() deliver - * the signal on the way back to userspace, before the signal - * mask is restored. - */ - if (sigmask) { - memcpy(¤t->saved_sigmask, &sigsaved, - sizeof(sigsaved)); - set_restore_sigmask(); - } - } else if (sigmask) - sigprocmask(SIG_SETMASK, &sigsaved, NULL); - - return ret; + return poll_select_finish(&end_time, tsp, type, ret); } -COMPAT_SYSCALL_DEFINE6(pselect6, int, n, compat_ulong_t __user *, inp, - compat_ulong_t __user *, outp, compat_ulong_t __user *, exp, - struct compat_timespec __user *, tsp, void __user *, sig) +struct compat_sigset_argpack { + compat_uptr_t p; + compat_size_t size; +}; +static inline int get_compat_sigset_argpack(struct compat_sigset_argpack *to, + struct compat_sigset_argpack __user *from) { - compat_size_t sigsetsize = 0; - compat_uptr_t up = 0; - - if (sig) { - if (!access_ok(VERIFY_READ, sig, - sizeof(compat_uptr_t)+sizeof(compat_size_t)) || - __get_user(up, (compat_uptr_t __user *)sig) || - __get_user(sigsetsize, - (compat_size_t __user *)(sig+sizeof(up)))) + if (from) { + if (!user_read_access_begin(from, sizeof(*from))) return -EFAULT; + unsafe_get_user(to->p, &from->p, Efault); + unsafe_get_user(to->size, &from->size, Efault); + user_read_access_end(); } - return do_compat_pselect(n, inp, outp, exp, tsp, compat_ptr(up), - sigsetsize); + return 0; +Efault: + user_access_end(); + return -EFAULT; } -COMPAT_SYSCALL_DEFINE5(ppoll, struct pollfd __user *, ufds, - unsigned int, nfds, struct compat_timespec __user *, tsp, +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) +{ + struct compat_sigset_argpack x = {0, 0}; + + if (get_compat_sigset_argpack(&x, sig)) + return -EFAULT; + + return do_compat_pselect(n, inp, outp, exp, tsp, compat_ptr(x.p), + x.size, PT_TIMESPEC); +} + +#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) +{ + struct compat_sigset_argpack x = {0, 0}; + + if (get_compat_sigset_argpack(&x, sig)) + return -EFAULT; + + return do_compat_pselect(n, inp, outp, exp, tsp, compat_ptr(x.p), + x.size, PT_OLD_TIMESPEC); +} + +#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) { - sigset_t ksigmask, sigsaved; struct timespec64 ts, end_time, *to = NULL; int ret; if (tsp) { - if (compat_get_timespec64(&ts, tsp)) + if (get_old_timespec32(&ts, tsp)) return -EFAULT; to = &end_time; @@ -1390,36 +1411,38 @@ return -EINVAL; } - if (sigmask) { - if (sigsetsize != sizeof(compat_sigset_t)) - return -EINVAL; - if (get_compat_sigset(&ksigmask, sigmask)) - return -EFAULT; - - sigdelsetmask(&ksigmask, sigmask(SIGKILL)|sigmask(SIGSTOP)); - sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved); - } + ret = set_compat_user_sigmask(sigmask, sigsetsize); + if (ret) + return ret; ret = do_sys_poll(ufds, nfds, to); - - /* We can restart this syscall, usually */ - if (ret == -EINTR) { - /* - * Don't restore the signal mask yet. Let do_signal() deliver - * the signal on the way back to userspace, before the signal - * mask is restored. - */ - if (sigmask) { - memcpy(¤t->saved_sigmask, &sigsaved, - sizeof(sigsaved)); - set_restore_sigmask(); - } - ret = -ERESTARTNOHAND; - } else if (sigmask) - sigprocmask(SIG_SETMASK, &sigsaved, NULL); - - ret = compat_poll_select_copy_remaining(&end_time, tsp, 0, ret); - - return ret; + return poll_select_finish(&end_time, tsp, PT_OLD_TIMESPEC, ret); } #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) +{ + struct timespec64 ts, end_time, *to = NULL; + int ret; + + if (tsp) { + if (get_timespec64(&ts, tsp)) + return -EFAULT; + + to = &end_time; + if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec)) + return -EINVAL; + } + + ret = set_compat_user_sigmask(sigmask, sigsetsize); + if (ret) + return ret; + + ret = do_sys_poll(ufds, nfds, to); + return poll_select_finish(&end_time, tsp, PT_TIMESPEC, ret); +} + +#endif -- Gitblit v1.6.2