From 22098763a10d9c1340827fcf6edab66f153b27f0 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 13 Sep 2026 12:27:00 -0700 Subject: Merge tag 'trace-v7.3-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace Pull tracing fixes from Steven Rostedt: - Don't destroy user event fields when removal fails User event fields are destroyed before the event is removed from visibility. But that can fail leaving the still visible event with no fields. Move the destroying of the fields to after the event is successfully removed from visibility. - Initialize function graph state is fork before calling copy_exec_state() For non-CLONE_VM forks, copy_exec_state() allocates a new task_exec_state. If that allocation fails, ftrace_graph_exit_task() will free the tasks ret_stack pointer. Since that pointer is still using the parent's ret_stack, it mistakenly frees the parent's pointer too. Call ftrace_graph_init() on the task first which will NULL out the new tasks's ret_stack and if the copy fails, it will not free anything. - Remove FGRAPH_MAX_INDEX The macro FGRAPH_MAX_INDEX was added but never used. Remove it. - Save ent_size in function graph printing of nested functions The function graph tracer needs to look at the next event to see if the next event is the return of the current function entry. If it is, it prints a single line: ktime_get(); Otherwise it prints it like a nested function: tick_nohz_irq_exit() { ktime_get(); kcpustat_irq_exit(); } In order to look at the next event, it must save the current event so that it has the information to print from it. It saves the event in the iterator descriptor called "ent". What it doesn't save is the ent_size of the event which is now used to know if the function graph arguments are to be printed. The peek doesn't save the size so the size used happens to be that of the size of the last event that was seen. Save the entry event size in the iterator descriptor so that the correct size is used. - Fix several errors with freeing data in the histogram code The histogram code had a lot of leaked or or incorrect accounting when failures happen. Correct them. - Fix histogram regression of .percent and .graph modifiers Up until 6.3 histogram values could have "percent" or "graph" modifiers that changed how they were printed. But a change that added restricting histograms values from being strings, stack traces and other modifiers inadvertently prevented them from using the percent and graph modifiers, which were legal use cases for values. Put back the percent and graph modifiers. - Fix various typos in the comments - Set the trace_clock before initializing a histogram with clock argument The histogram API allows the user to specific which trace clock to use via a "clock=" string. The histogram is set up first before the clock is checked. If the passed in clock is not valid, it exits without fully fixing up the histogram leaving it on the list and a use-after-free can trigger. Update the clock argument first and if it fails then exit gracefully before the histogram trigger is placed on any lists. - Restore :mod: trailer after parsing in ftrace_set_clr_event The function ftrace_set_clr_event() modifies the parse string and needs to put it back to what was passed in. It searches for ":mod:" via a strsep() but fails to put back the first ':' in the string. Add back the ':' in the passed in string. - Take trace_array reference when opening a tracer options file The options files are dynamically created and some tracers add their own options. When a tracer adds their own list of options, the trace_array holding them has an array to hold the list of options for each tracer. This array increases in size via a krealloc(), and the new entry gets a newly allocated array to hold the options of the new tracer being added. The element in each entry of the tracer's option array holds a pointer back to the trace_array, a pointer to the tracer it is associated to, a pointer to the flags of the option. The issue is that these arrays are freed when the trace_array is freed when its instance it represents is removed from the instances directory. There's a race that an open of one of these options files can happen when the instance is being removed. Add a new helper function to be called by the open function of the options file to iterate all existing trace_arrays under a lock and find the one that has the given option element in one of it's tracer arrays. If found, then update the associated trace_array's reference counter to keep it from being freed. If not found, have the open call return -ENODEV. - Disable interrupts when acquiring the lock in rb_wake_up_waiters() The function rb_wake_up_waiters() assumes it will be called in interrupt context and does not disable irqs when taking cpu_buffer->reader_lock, which can be called in hard interrupt context. The issue is in PREEMPT_RT, this function is called in thread context leaving this lock open to a deadlock. Take the lock with interrupts disabled. - Use rcu_assign_pointer() for tmp_ops filter hash The tmp_ops used in update_ftrace_direct_mod() assigns its filter_hash field directly, but that field is annotated as __rcu and sparse complains. Assign it with rcu_assign_pointer() - Fix use-after-free in enable_trigger_private_data_free() The trace_event_call is accessed through the event_trigger_data's trace_event_file pointer to put the trace_event_call on freeing. The issue is that the trace_event_file data may have been freed already causing a use-after-free. Add a field to the event_trigger_data that points directly to the trace_event_call so that it can decrement its reference directly without needing to go through the trace_event_file. - Fix accounting of buffer data remote headers trace_buffer_desc_size() and trace_remote_alloc_buffer() undercount the number of pages is needed for the asked for size as it doesn't take into account the meta data on each page. Add a helper function to do the calculation properly and use that in these functions. - Catch nr_page_va overflow in ring_buffer_desc sizing The number of pages per remote ring buffer is capped by ring_buffer_desc::nr_page_va (32 bits). A buffer_size large enough to overflow that field would silently allocate a descriptor smaller than what was asked for. - Do not resize the subbuf order if any per_cpu buffer is disabled The mmapping of ring buffers disables resizing the subbuffers, but it is done per-cpu whereas the subbuf size change is done for all the per_cpu buffers under the buffer->mutex. It could change the size of some while the mapping is happening on others. Have the resize of the subbuf order check all the per_cpu buffers under the lock to see if any of them is disabled before starting and causing an inconsistency between buffers that are being mapped. * tag 'trace-v7.3-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace: (25 commits) ring-buffer: Check resize_disabled before publishing the new subbuf order tracing/remotes: Catch nr_page_va overflow in ring_buffer_desc sizing tracing/remotes: Account for ring buffer page header in size calculation tracing: Don't dereference trace_event_file in deferred trigger free ftrace: Use rcu_assign_pointer() for tmp_ops filter hash ring-buffer: Acquire the lock with irqsave in rb_wake_up_waiters() tracing: Take trace_array reference when opening a tracer options file tracing: Fix ring_buffer_read_page_size() kernel-doc tracing: Restore :mod: trailer after parsing in ftrace_set_clr_event() tracing: Fix memory corruption from a "STACKTRACE" histogram key tracing: Fix memory corruption from the histogram stacktrace modifier tracing: Undo the registration when enabling the histogram trigger fails tracing: Take the reference before publishing the named histogram trigger tracing: Set the trace clock before registering the histogram trigger tracing: Fix typo "preceeded" in comment tracing: Fix typo "availabe" in comment tracing: Let histogram values keep the percent and graph modifiers tracing: Keep the entry count when the histogram stats allocation fails tracing: Free histogram the field rejected for a bad modifier tracing: Free histogram the var ref when its initialization fails ... --- fs/select.c | 1438 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 1438 insertions(+) create mode 100644 fs/select.c (limited to 'fs/select.c') diff --git a/fs/select.c b/fs/select.c new file mode 100644 index 000000000..95d765310 --- /dev/null +++ b/fs/select.c @@ -0,0 +1,1438 @@ +// 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 +#include +#include +#include +#include +#include +#include +#include +#include /* for STICKY_TIMEOUTS */ +#include +#include +#include +#include +#include +#include +#include +#include + +#include + + +/* + * 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; +} + +u64 select_estimate_accuracy(struct timespec64 *tv) +{ + u64 ret; + struct timespec64 now; + u64 slack = current->timer_slack_ns; + + if (slack == 0) + return 0; + + ktime_get_ts64(&now); + now = timespec64_sub(*tv, now); + ret = __estimate_accuracy(&now); + if (ret < slack) + return slack; + return ret; +} + + + +struct poll_table_page { + struct poll_table_page * next; + struct poll_table_entry * entry; + struct poll_table_entry entries[]; +}; + +#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 , + * 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; +} +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); +} + +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; + kfree(old); + } +} +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 = kmalloc(PAGE_SIZE, 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++; +} + +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(); + WRITE_ONCE(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_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); +} + +/* 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); +} + +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 (!READ_ONCE(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; +} + +/** + * 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; +} + +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; + + restore_saved_sigmask_unless(ret == -ERESTARTNOHAND); + + 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; + + + switch (pt_type) { + case PT_TIMEVAL: + { + struct __kernel_old_timeval 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; + 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 + * 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; +} + +/* + * 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)) + +/* + * 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; +} + +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; +} + +static inline +void zero_fd_set(unsigned long nr, unsigned long *fdset) +{ + memset(fdset, 0, FDS_BYTES(nr)); +} + +#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; +} + +#define POLLIN_SET (EPOLLRDNORM | EPOLLRDBAND | EPOLLIN | EPOLLHUP | EPOLLERR |\ + EPOLLNVAL) +#define POLLOUT_SET (EPOLLWRBAND | EPOLLWRNORM | EPOLLOUT | EPOLLERR |\ + EPOLLNVAL) +#define POLLEX_SET (EPOLLPRI | EPOLLNVAL) + +static inline __poll_t select_poll_one(int fd, poll_table *wait, unsigned long in, + unsigned long out, unsigned long bit, + __poll_t ll_flag) +{ + CLASS(fd, f)(fd); + + if (fd_empty(f)) + return EPOLLNVAL; + + wait->_key = POLLEX_SET | ll_flag; + if (in & bit) + wait->_key |= POLLIN_SET; + if (out & bit) + wait->_key |= POLLOUT_SET; + + return vfs_poll(fd_file(f), wait); +} + +static noinline_for_stack 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) { + if (i >= n) + break; + if (!(bit & all_bits)) + continue; + mask = select_poll_one(i, wait, in, out, bit, + busy_flag); + 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; +} + +/* + * 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 (unlikely(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; +} + +static int kern_select(int n, fd_set __user *inp, fd_set __user *outp, + fd_set __user *exp, struct __kernel_old_timeval __user *tvp) +{ + struct timespec64 end_time, *to = NULL; + struct __kernel_old_timeval tv; + int ret; + + if (tvp) { + if (copy_from_user(&tv, tvp, sizeof(tv))) + return -EFAULT; + + /* + * Reject negative components before normalisation. The seconds + * sum below is performed in signed long and a crafted negative + * timeval can wrap to a positive value that passes + * timespec64_valid() and turns into an effectively-infinite + * deadline via timespec64_add_safe()'s saturation, instead of + * the -EINVAL POSIX requires for negative timeouts. + */ + if (tv.tv_sec < 0 || tv.tv_usec < 0) + return -EINVAL; + + to = &end_time; + if (poll_select_set_timeout(to, + tv.tv_sec + (tv.tv_usec / USEC_PER_SEC), + (tv.tv_usec % USEC_PER_SEC) * NSEC_PER_USEC)) + return -EINVAL; + } + + ret = core_sys_select(n, inp, outp, exp, to); + 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 __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, void __user *tsp, + const sigset_t __user *sigmask, size_t sigsetsize, + enum poll_time_type type) +{ + struct timespec64 ts, end_time, *to = NULL; + int ret; + + if (tsp) { + 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; + } + + ret = set_user_sigmask(sigmask, sigsetsize); + if (ret) + return ret; + + ret = core_sys_select(n, inp, outp, exp, to); + return poll_select_finish(&end_time, tsp, type, ret); +} + +/* + * 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 { + 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) { + scoped_user_read_access(from, Efault) { + unsafe_get_user(to->p, &from->p, Efault); + unsafe_get_user(to->size, &from->size, Efault); + } + } + return 0; +Efault: + return -EFAULT; +} + +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) +{ + 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_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 __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 { + struct poll_list *next; + unsigned int len; + struct pollfd entries[] __counted_by(len); +}; + +#define POLLFD_PER_PAGE ((PAGE_SIZE-sizeof(struct poll_list)) / sizeof(struct pollfd)) + +/* + * 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) +{ + int fd = pollfd->fd; + __poll_t mask, filter; + + if (unlikely(fd < 0)) + return 0; + + CLASS(fd, f)(fd); + if (fd_empty(f)) + return EPOLLNVAL; + + /* userland u16 ->events contains POLL... bitmap */ + filter = demangle_poll(pollfd->events) | EPOLLERR | EPOLLHUP; + pwait->_key = filter | busy_flag; + mask = vfs_poll(fd_file(f), pwait); + if (mask & busy_flag) + *can_busy_poll = true; + return mask & filter; /* Mask out unneeded events. */ +} + +static int do_poll(struct poll_list *list, struct poll_wqueues *wait, + struct timespec64 *end_time) +{ + poll_table* pt = &wait->pt; + ktime_t expire, *to = NULL; + int timed_out = 0, count = 0; + u64 slack = 0; + __poll_t busy_flag = net_busy_loop_on() ? POLL_BUSY_LOOP : 0; + unsigned long busy_start = 0; + + /* Optimise the no-wait case */ + if (end_time && !end_time->tv_sec && !end_time->tv_nsec) { + pt->_qproc = NULL; + timed_out = 1; + } + + if (end_time && !timed_out) + slack = select_estimate_accuracy(end_time); + + for (;;) { + struct poll_list *walk; + bool can_busy_loop = false; + + for (walk = list; walk != NULL; walk = walk->next) { + struct pollfd * pfd, * pfd_end; + + pfd = walk->entries; + pfd_end = pfd + walk->len; + for (; pfd != pfd_end; pfd++) { + __poll_t mask; + /* + * Fish for events. If we found one, record it + * 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. + */ + mask = do_pollfd(pfd, pt, &can_busy_loop, busy_flag); + pfd->revents = mangle_poll(mask); + if (mask) { + count++; + 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->_qproc to them on the next loop iteration. + */ + pt->_qproc = NULL; + if (!count) { + count = wait->error; + if (signal_pending(current)) + count = -ERESTARTNOHAND; + } + if (count || timed_out) + 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(wait, TASK_INTERRUPTIBLE, to, slack)) + timed_out = 1; + } + return count; +} + +#define N_STACK_PPS ((sizeof(stack_pps) - sizeof(struct poll_list)) / \ + sizeof(struct pollfd)) + +static int do_sys_poll(struct pollfd __user *ufds, unsigned int nfds, + struct timespec64 *end_time) +{ + struct poll_wqueues table; + int err = -EFAULT, fdcount; + /* 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 */ + long stack_pps[POLL_STACK_ALLOC/sizeof(long)]; + struct poll_list *const head = (struct poll_list *)stack_pps; + struct poll_list *walk = head; + unsigned int todo = nfds; + unsigned int len; + + if (nfds > rlimit(RLIMIT_NOFILE)) + return -EINVAL; + + len = min_t(unsigned int, nfds, N_STACK_PPS); + for (;;) { + walk->next = NULL; + walk->len = len; + if (!len) + break; + + if (copy_from_user(walk->entries, ufds + nfds-todo, + sizeof(struct pollfd) * walk->len)) + goto out_fds; + + if (walk->len >= todo) + break; + todo -= walk->len; + + len = min(todo, POLLFD_PER_PAGE); + walk = walk->next = kmalloc_flex(*walk, entries, len); + if (!walk) { + err = -ENOMEM; + goto out_fds; + } + } + + poll_initwait(&table); + fdcount = do_poll(head, &table, end_time); + poll_freewait(&table); + + scoped_user_write_access_size(ufds, nfds * sizeof(*ufds), out_fds) { + struct pollfd __user *_ufds = ufds; + + for (walk = head; walk; walk = walk->next) { + struct pollfd *fds = walk->entries; + unsigned int j; + + for (j = walk->len; j; fds++, _ufds++, j--) + unsafe_put_user(fds->revents, &_ufds->revents, out_fds); + } + } + + err = fdcount; +out_fds: + walk = head->next; + while (walk) { + struct poll_list *pos = walk; + walk = walk->next; + kfree(pos); + } + + return err; +} + +static long do_restart_poll(struct restart_block *restart_block) +{ + struct pollfd __user *ufds = restart_block->poll.ufds; + int nfds = restart_block->poll.nfds; + struct timespec64 *to = NULL; + int ret; + + if (restart_block->poll.has_timeout) + to = &restart_block->poll.end_time; + + ret = do_sys_poll(ufds, nfds, to); + + if (ret == -ERESTARTNOHAND) + ret = set_restart_fn(restart_block, do_restart_poll); + + return ret; +} + +SYSCALL_DEFINE3(poll, struct pollfd __user *, ufds, unsigned int, nfds, + int, timeout_msecs) +{ + struct timespec64 end_time, *to = NULL; + int ret; + + if (timeout_msecs >= 0) { + to = &end_time; + poll_select_set_timeout(to, timeout_msecs / MSEC_PER_SEC, + NSEC_PER_MSEC * (timeout_msecs % MSEC_PER_SEC)); + } + + ret = do_sys_poll(ufds, nfds, to); + + if (ret == -ERESTARTNOHAND) { + struct restart_block *restart_block; + + restart_block = ¤t->restart_block; + restart_block->poll.ufds = ufds; + restart_block->poll.nfds = nfds; + + if (timeout_msecs >= 0) { + restart_block->poll.end_time = end_time; + restart_block->poll.has_timeout = 1; + } else + restart_block->poll.has_timeout = 0; + + ret = set_restart_fn(restart_block, do_restart_poll); + } + return ret; +} + +SYSCALL_DEFINE5(ppoll, struct pollfd __user *, ufds, unsigned int, nfds, + struct __kernel_timespec __user *, tsp, const sigset_t __user *, sigmask, + 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_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); +} + +#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)) + +/* + * 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) +{ + if (ufdset) { + return compat_get_bitmap(fdset, ufdset, nr); + } else { + zero_fd_set(nr, fdset); + return 0; + } +} + +static +int compat_set_fd_set(unsigned long nr, compat_ulong_t __user *ufdset, + unsigned long *fdset) +{ + if (!ufdset) + return 0; + return compat_put_bitmap(ufdset, fdset, nr); +} + + +/* + * 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) +{ + fd_set_bits fds; + void *bits; + int size, max_fds, ret = -EINVAL; + struct fdtable *fdt; + long stack_fds[SELECT_STACK_ALLOC/sizeof(long)]; + + 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) { + bits = kmalloc_array(6, size, GFP_KERNEL); + ret = -ENOMEM; + if (!bits) + goto out_nofds; + } + fds.in = (unsigned long *) bits; + fds.out = (unsigned long *) (bits + size); + fds.ex = (unsigned long *) (bits + 2*size); + fds.res_in = (unsigned long *) (bits + 3*size); + fds.res_out = (unsigned long *) (bits + 4*size); + fds.res_ex = (unsigned long *) (bits + 5*size); + + if ((ret = compat_get_fd_set(n, inp, fds.in)) || + (ret = compat_get_fd_set(n, outp, fds.out)) || + (ret = compat_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 (compat_set_fd_set(n, inp, fds.res_in) || + compat_set_fd_set(n, outp, fds.res_out) || + compat_set_fd_set(n, exp, fds.res_ex)) + ret = -EFAULT; +out: + if (bits != stack_fds) + kfree(bits); +out_nofds: + return ret; +} + +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) +{ + struct timespec64 end_time, *to = NULL; + struct old_timeval32 tv; + int ret; + + if (tvp) { + if (copy_from_user(&tv, tvp, sizeof(tv))) + return -EFAULT; + + to = &end_time; + if (poll_select_set_timeout(to, + tv.tv_sec + (tv.tv_usec / USEC_PER_SEC), + (tv.tv_usec % USEC_PER_SEC) * NSEC_PER_USEC)) + return -EINVAL; + } + + ret = compat_core_sys_select(n, inp, outp, exp, to); + 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 old_timeval32 __user *, tvp) +{ + return do_compat_select(n, inp, outp, exp, tvp); +} + +struct compat_sel_arg_struct { + compat_ulong_t n; + compat_uptr_t inp; + compat_uptr_t outp; + compat_uptr_t exp; + compat_uptr_t tvp; +}; + +COMPAT_SYSCALL_DEFINE1(old_select, struct compat_sel_arg_struct __user *, arg) +{ + struct compat_sel_arg_struct a; + + if (copy_from_user(&a, arg, sizeof(a))) + return -EFAULT; + return do_compat_select(a.n, compat_ptr(a.inp), compat_ptr(a.outp), + compat_ptr(a.exp), compat_ptr(a.tvp)); +} + +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 timespec64 ts, end_time, *to = NULL; + int ret; + + if (tsp) { + 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; + } + + ret = set_compat_user_sigmask(sigmask, sigsetsize); + if (ret) + return ret; + + ret = compat_core_sys_select(n, inp, outp, exp, to); + return poll_select_finish(&end_time, tsp, type, ret); +} + +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) +{ + if (from) { + scoped_user_read_access(from, efault) { + unsafe_get_user(to->p, &from->p, efault); + unsafe_get_user(to->size, &from->size, efault); + } + } + return 0; +efault: + return -EFAULT; +} + +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) +{ + 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_compat_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 + +/* 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 -- cgit v1.3.1