// SPDX-License-Identifier: GPL-2.0/* * linux/fs/file.c * * Copyright (C) 1998-1999, Stephen Tweedie and Bill Hawes * * Manage the dynamic fd arrays in the process files_struct. */ #include <linux/syscalls.h>#include <linux/export.h>#include <linux/fs.h>#include <linux/kernel.h>#include <linux/mm.h>#include <linux/sched/signal.h>#include <linux/slab.h>#include <linux/file.h>#include <linux/fdtable.h>#include <linux/bitops.h>#include <linux/spinlock.h>#include <linux/rcupdate.h>#include <linux/close_range.h>#include <linux/file_ref.h>#include <net/sock.h>#include <linux/init_task.h> #include "internal.h" static noinline bool __file_ref_put_badval(file_ref_t *ref, unsigned long cnt){ /* * If the reference count was already in the dead zone, then this * put() operation is imbalanced. Warn, put the reference count back to * DEAD and tell the caller to not deconstruct the object. */ if (WARN_ONCE(cnt >= FILE_REF_RELEASED, "imbalanced put on file reference count")) { atomic_long_set(&ref->refcnt, FILE_REF_DEAD); return false; } /* * This is a put() operation on a saturated refcount. Restore the * mean saturation value and tell the caller to not deconstruct the * object. */ if (cnt > FILE_REF_MAXREF) atomic_long_set(&ref->refcnt, FILE_REF_SATURATED); return false;} /** * __file_ref_put - Slowpath of file_ref_put() * @ref: Pointer to the reference count * @cnt: Current reference count * * Invoked when the reference count is outside of the valid zone. * * Return: * True if this was the last reference with no future references * possible. This signals the caller that it can safely schedule the * object, which is protected by the reference counter, for * deconstruction. * * False if there are still active references or the put() raced * with a concurrent get()/put() pair. Caller is not allowed to * deconstruct the protected object. */bool __file_ref_put(file_ref_t *ref, unsigned long cnt){ /* Did this drop the last reference? */ if (likely(cnt == FILE_REF_NOREF)) { /* * Carefully try to set the reference count to FILE_REF_DEAD. * * This can fail if a concurrent get() operation has * elevated it again or the corresponding put() even marked * it dead already. Both are valid situations and do not * require a retry. If this fails the caller is not * allowed to deconstruct the object. */ if (!atomic_long_try_cmpxchg_release(&ref->refcnt, &cnt, FILE_REF_DEAD)) return false; /* * The caller can safely schedule the object for * deconstruction. Provide acquire ordering. */ smp_acquire__after_ctrl_dep(); return true; } return __file_ref_put_badval(ref, cnt);}EXPORT_SYMBOL_GPL(__file_ref_put); unsigned int sysctl_nr_open __read_mostly = 1024*1024;unsigned int sysctl_nr_open_min = BITS_PER_LONG;/* our min() is unusable in constant expressions ;-/ */#define __const_min(x, y) ((x) < (y) ? (x) : (y))unsigned int sysctl_nr_open_max = __const_min(INT_MAX, ~(size_t)0/sizeof(void *)) & -BITS_PER_LONG; static void __free_fdtable(struct fdtable *fdt){ kvfree(fdt->fd); kvfree(fdt->open_fds); kfree(fdt);} static void free_fdtable_rcu(struct rcu_head *rcu){ __free_fdtable(container_of(rcu, struct fdtable, rcu));} #define BITBIT_NR(nr) BITS_TO_LONGS(BITS_TO_LONGS(nr))#define BITBIT_SIZE(nr) (BITBIT_NR(nr) * sizeof(long)) #define fdt_words(fdt) ((fdt)->max_fds / BITS_PER_LONG) // words in ->open_fds/* * Copy 'count' fd bits from the old table to the new table and clear the extra * space if any. This does not copy the file pointers. Called with the files * spinlock held for write. */static inline void copy_fd_bitmaps(struct fdtable *nfdt, struct fdtable *ofdt, unsigned int copy_words){ unsigned int nwords = fdt_words(nfdt); bitmap_copy_and_extend(nfdt->open_fds, ofdt->open_fds, copy_words * BITS_PER_LONG, nwords * BITS_PER_LONG); bitmap_copy_and_extend(nfdt->close_on_exec, ofdt->close_on_exec, copy_words * BITS_PER_LONG, nwords * BITS_PER_LONG); bitmap_copy_and_extend(nfdt->full_fds_bits, ofdt->full_fds_bits, copy_words, nwords);} /* * Copy all file descriptors from the old table to the new, expanded table and * clear the extra space. Called with the files spinlock held for write. */static void copy_fdtable(struct fdtable *nfdt, struct fdtable *ofdt){ size_t cpy, set; BUG_ON(nfdt->max_fds < ofdt->max_fds); cpy = ofdt->max_fds * sizeof(struct file *); set = (nfdt->max_fds - ofdt->max_fds) * sizeof(struct file *); memcpy(nfdt->fd, ofdt->fd, cpy); memset((char *)nfdt->fd + cpy, 0, set); copy_fd_bitmaps(nfdt, ofdt, fdt_words(ofdt));} /* * Note how the fdtable bitmap allocations very much have to be a multiple of * BITS_PER_LONG. This is not only because we walk those things in chunks of * 'unsigned long' in some places, but simply because that is how the Linux * kernel bitmaps are defined to work: they are not "bits in an array of bytes", * they are very much "bits in an array of unsigned long". */static struct fdtable *alloc_fdtable(unsigned int slots_wanted){ struct fdtable *fdt; unsigned int nr; void *data; /* * Figure out how many fds we actually want to support in this fdtable. * Allocation steps are keyed to the size of the fdarray, since it * grows far faster than any of the other dynamic data. We try to fit * the fdarray into comfortable page-tuned chunks: starting at 1024B * and growing in powers of two from there on. Since we called only * with slots_wanted > BITS_PER_LONG (embedded instance in files->fdtab * already gives BITS_PER_LONG slots), the above boils down to * 1. use the smallest power of two large enough to give us that many * slots. * 2. on 32bit skip 64 and 128 - the minimal capacity we want there is * 256 slots (i.e. 1Kb fd array). * 3. on 64bit don't skip anything, 1Kb fd array means 128 slots there * and we are never going to be asked for 64 or less. */ if (IS_ENABLED(CONFIG_32BIT) && slots_wanted < 256) nr = 256; else nr = roundup_pow_of_two(slots_wanted); /* * Note that this can drive nr *below* what we had passed if sysctl_nr_open * had been set lower between the check in expand_files() and here. * * We make sure that nr remains a multiple of BITS_PER_LONG - otherwise * bitmaps handling below becomes unpleasant, to put it mildly... */ if (unlikely(nr > sysctl_nr_open)) { nr = round_down(sysctl_nr_open, BITS_PER_LONG); if (nr < slots_wanted) return ERR_PTR(-EMFILE); } /* * Check if the allocation size would exceed INT_MAX. kvmalloc_array() * and kvmalloc() will warn if the allocation size is greater than * INT_MAX, as filp_cache objects are not __GFP_NOWARN. * * This can happen when sysctl_nr_open is set to a very high value and * a process tries to use a file descriptor near that limit. For example, * if sysctl_nr_open is set to 1073741816 (0x3ffffff8) - which is what * systemd typically sets it to - then trying to use a file descriptor * close to that value will require allocating a file descriptor table * that exceeds 8GB in size. */ if (unlikely(nr > INT_MAX / sizeof(struct file *))) return ERR_PTR(-EMFILE); fdt = kmalloc_obj(struct fdtable, GFP_KERNEL_ACCOUNT); if (!fdt) goto out; fdt->max_fds = nr; data = kvmalloc_objs(struct file *, nr, GFP_KERNEL_ACCOUNT); if (!data) goto out_fdt; fdt->fd = data; data = kvmalloc(max_t(size_t, 2 * nr / BITS_PER_BYTE + BITBIT_SIZE(nr), L1_CACHE_BYTES), GFP_KERNEL_ACCOUNT); if (!data) goto out_arr; fdt->open_fds = data; data += nr / BITS_PER_BYTE; fdt->close_on_exec = data; data += nr / BITS_PER_BYTE; fdt->full_fds_bits = data; return fdt; out_arr: kvfree(fdt->fd);out_fdt: kfree(fdt);out: return ERR_PTR(-ENOMEM);} /* * Expand the file descriptor table. * This function will allocate a new fdtable and both fd array and fdset, of * the given size. * Return <0 error code on error; 0 on successful completion. * The files->file_lock should be held on entry, and will be held on exit. */static int expand_fdtable(struct files_struct *files, unsigned int nr) __releases(files->file_lock) __acquires(files->file_lock){ struct fdtable *new_fdt, *cur_fdt; spin_unlock(&files->file_lock); new_fdt = alloc_fdtable(nr + 1); /* make sure all fd_install() have seen resize_in_progress * or have finished their rcu_read_lock_sched() section. */ if (atomic_read(&files->count) > 1) synchronize_rcu(); spin_lock(&files->file_lock); if (IS_ERR(new_fdt)) return PTR_ERR(new_fdt); cur_fdt = files_fdtable(files); BUG_ON(nr < cur_fdt->max_fds); copy_fdtable(new_fdt, cur_fdt); rcu_assign_pointer(files->fdt, new_fdt); if (cur_fdt != &files->fdtab) call_rcu(&cur_fdt->rcu, free_fdtable_rcu); /* coupled with smp_rmb() in fd_install() */ smp_wmb(); return 0;} /* * Expand files. * This function will expand the file structures, if the requested size exceeds * the current capacity and there is room for expansion. * Return <0 error code on error; 0 on success. * The files->file_lock should be held on entry, and will be held on exit. */static int expand_files(struct files_struct *files, unsigned int nr) __releases(files->file_lock) __acquires(files->file_lock){ struct fdtable *fdt; int error; repeat: fdt = files_fdtable(files); /* Do we need to expand? */ if (nr < fdt->max_fds) return 0; if (unlikely(files->resize_in_progress)) { spin_unlock(&files->file_lock); wait_event(files->resize_wait, !files->resize_in_progress); spin_lock(&files->file_lock); goto repeat; } /* Can we expand? */ if (unlikely(nr >= sysctl_nr_open)) return -EMFILE; /* All good, so we try */ files->resize_in_progress = true; error = expand_fdtable(files, nr); files->resize_in_progress = false; wake_up_all(&files->resize_wait); return error;} static inline void __set_close_on_exec(unsigned int fd, struct fdtable *fdt, bool set){ if (set) { __set_bit(fd, fdt->close_on_exec); } else { if (test_bit(fd, fdt->close_on_exec)) __clear_bit(fd, fdt->close_on_exec); }} static inline void __set_open_fd(unsigned int fd, struct fdtable *fdt, bool set){ __set_bit(fd, fdt->open_fds); __set_close_on_exec(fd, fdt, set); fd /= BITS_PER_LONG; if (!~fdt->open_fds[fd]) __set_bit(fd, fdt->full_fds_bits);} static inline void __clear_open_fd(unsigned int fd, struct fdtable *fdt){ __clear_bit(fd, fdt->open_fds); fd /= BITS_PER_LONG; if (test_bit(fd, fdt->full_fds_bits)) __clear_bit(fd, fdt->full_fds_bits);} static inline bool fd_is_open(unsigned int fd, const struct fdtable *fdt){ return test_bit(fd, fdt->open_fds);} /* * Note that a sane fdtable size always has to be a multiple of * BITS_PER_LONG, since we have bitmaps that are sized by this. * * punch_hole is optional - when close_range() is asked to unshare * and close, we don't need to copy descriptors in that range, so * a smaller cloned descriptor table might suffice if the last * currently opened descriptor falls into that range. */static unsigned int sane_fdtable_size(struct fdtable *fdt, struct fd_range *punch_hole){ unsigned int last = find_last_bit(fdt->open_fds, fdt->max_fds); if (last == fdt->max_fds) return NR_OPEN_DEFAULT; if (punch_hole && punch_hole->to >= last && punch_hole->from <= last) { last = find_last_bit(fdt->open_fds, punch_hole->from); if (last == punch_hole->from) return NR_OPEN_DEFAULT; } return ALIGN(last + 1, BITS_PER_LONG);} /* * Allocate a new descriptor table and copy contents from the passed in * instance. Returns a pointer to cloned table on success, ERR_PTR() * on failure. For 'punch_hole' see sane_fdtable_size(). */struct files_struct *dup_fd(struct files_struct *oldf, struct fd_range *punch_hole){ struct files_struct *newf; struct file **old_fds, **new_fds; unsigned int open_files, i; struct fdtable *old_fdt, *new_fdt; newf = kmem_cache_alloc(files_cachep, GFP_KERNEL); if (!newf) return ERR_PTR(-ENOMEM); atomic_set(&newf->count, 1); spin_lock_init(&newf->file_lock); newf->resize_in_progress = false; init_waitqueue_head(&newf->resize_wait); newf->next_fd = 0; new_fdt = &newf->fdtab; new_fdt->max_fds = NR_OPEN_DEFAULT; new_fdt->close_on_exec = newf->close_on_exec_init; new_fdt->open_fds = newf->open_fds_init; new_fdt->full_fds_bits = newf->full_fds_bits_init; new_fdt->fd = &newf->fd_array[0]; spin_lock(&oldf->file_lock); old_fdt = files_fdtable(oldf); open_files = sane_fdtable_size(old_fdt, punch_hole); /* * Check whether we need to allocate a larger fd array and fd set. */ while (unlikely(open_files > new_fdt->max_fds)) { spin_unlock(&oldf->file_lock); if (new_fdt != &newf->fdtab) __free_fdtable(new_fdt); new_fdt = alloc_fdtable(open_files); if (IS_ERR(new_fdt)) { kmem_cache_free(files_cachep, newf); return ERR_CAST(new_fdt); } /* * Reacquire the oldf lock and a pointer to its fd table * who knows it may have a new bigger fd table. We need * the latest pointer. */ spin_lock(&oldf->file_lock); old_fdt = files_fdtable(oldf); open_files = sane_fdtable_size(old_fdt, punch_hole); } copy_fd_bitmaps(new_fdt, old_fdt, open_files / BITS_PER_LONG); old_fds = old_fdt->fd; new_fds = new_fdt->fd; /* * We may be racing against fd allocation from other threads using this * files_struct, despite holding ->file_lock. * * alloc_fd() might have already claimed a slot, while fd_install() * did not populate it yet. Note the latter operates locklessly, so * the file can show up as we are walking the array below. * * At the same time we know no files will disappear as all other * operations take the lock. * * Instead of trying to placate userspace racing with itself, we * ref the file if we see it and mark the fd slot as unused otherwise. */ for (i = open_files; i != 0; i--) { struct file *f = rcu_dereference_raw(*old_fds++); if (f) { get_file(f); } else { __clear_open_fd(open_files - i, new_fdt); } rcu_assign_pointer(*new_fds++, f); } spin_unlock(&oldf->file_lock); /* clear the remainder */ memset(new_fds, 0, (new_fdt->max_fds - open_files) * sizeof(struct file *)); rcu_assign_pointer(newf->fdt, new_fdt); return newf;} static struct fdtable *close_files(struct files_struct * files){ /* * It is safe to dereference the fd table without RCU or * ->file_lock because this is the last reference to the * files structure. */ struct fdtable *fdt = rcu_dereference_raw(files->fdt); unsigned int i, j = 0; for (;;) { unsigned long set; i = j * BITS_PER_LONG; if (i >= fdt->max_fds) break; set = fdt->open_fds[j++]; while (set) { if (set & 1) { struct file *file = fdt->fd[i]; if (file) { filp_close(file, files); cond_resched(); } } i++; set >>= 1; }Lines 1–500 of 1531. Load more
// SPDX-License-Identifier: GPL-2.0 /* * linux/fs/file.c * * Copyright (C) 1998-1999, Stephen Tweedie and Bill Hawes * * Manage the dynamic fd arrays in the process files_struct. */ #include <linux/syscalls.h> #include <linux/export.h> #include <linux/fs.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/sched/signal.h> #include <linux/slab.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/bitops.h> #include <linux/spinlock.h> #include <linux/rcupdate.h> #include <linux/close_range.h> #include <linux/file_ref.h> #include <net/sock.h> #include <linux/init_task.h> #include "internal.h" static noinline bool __file_ref_put_badval(file_ref_t *ref, unsigned long cnt) { /* * If the reference count was already in the dead zone, then this * put() operation is imbalanced. Warn, put the reference count back to * DEAD and tell the caller to not deconstruct the object. */ if (WARN_ONCE(cnt >= FILE_REF_RELEASED, "imbalanced put on file reference count")) { atomic_long_set(&ref->refcnt, FILE_REF_DEAD); return false; } /* * This is a put() operation on a saturated refcount. Restore the * mean saturation value and tell the caller to not deconstruct the * object. */ if (cnt > FILE_REF_MAXREF) atomic_long_set(&ref->refcnt, FILE_REF_SATURATED); return false; } /** * __file_ref_put - Slowpath of file_ref_put() * @ref: Pointer to the reference count * @cnt: Current reference count * * Invoked when the reference count is outside of the valid zone. * * Return: * True if this was the last reference with no future references * possible. This signals the caller that it can safely schedule the * object, which is protected by the reference counter, for * deconstruction. * * False if there are still active references or the put() raced * with a concurrent get()/put() pair. Caller is not allowed to * deconstruct the protected object. */ bool __file_ref_put(file_ref_t *ref, unsigned long cnt) { /* Did this drop the last reference? */ if (likely(cnt == FILE_REF_NOREF)) { /* * Carefully try to set the reference count to FILE_REF_DEAD. * * This can fail if a concurrent get() operation has * elevated it again or the corresponding put() even marked * it dead already. Both are valid situations and do not * require a retry. If this fails the caller is not * allowed to deconstruct the object. */ if (!atomic_long_try_cmpxchg_release(&ref->refcnt, &cnt, FILE_REF_DEAD)) return false; /* * The caller can safely schedule the object for * deconstruction. Provide acquire ordering. */ smp_acquire__after_ctrl_dep(); return true; } return __file_ref_put_badval(ref, cnt); } EXPORT_SYMBOL_GPL(__file_ref_put); unsigned int sysctl_nr_open __read_mostly = 1024*1024; unsigned int sysctl_nr_open_min = BITS_PER_LONG; /* our min() is unusable in constant expressions ;-/ */ #define __const_min(x, y) ((x) < (y) ? (x) : (y)) unsigned int sysctl_nr_open_max = __const_min(INT_MAX, ~(size_t)0/sizeof(void *)) & -BITS_PER_LONG; static void __free_fdtable(struct fdtable *fdt) { kvfree(fdt->fd); kvfree(fdt->open_fds); kfree(fdt); } static void free_fdtable_rcu(struct rcu_head *rcu) { __free_fdtable(container_of(rcu, struct fdtable, rcu)); } #define BITBIT_NR(nr) BITS_TO_LONGS(BITS_TO_LONGS(nr)) #define BITBIT_SIZE(nr) (BITBIT_NR(nr) * sizeof(long)) #define fdt_words(fdt) ((fdt)->max_fds / BITS_PER_LONG) // words in ->open_fds /* * Copy 'count' fd bits from the old table to the new table and clear the extra * space if any. This does not copy the file pointers. Called with the files * spinlock held for write. */ static inline void copy_fd_bitmaps(struct fdtable *nfdt, struct fdtable *ofdt, unsigned int copy_words) { unsigned int nwords = fdt_words(nfdt); bitmap_copy_and_extend(nfdt->open_fds, ofdt->open_fds, copy_words * BITS_PER_LONG, nwords * BITS_PER_LONG); bitmap_copy_and_extend(nfdt->close_on_exec, ofdt->close_on_exec, copy_words * BITS_PER_LONG, nwords * BITS_PER_LONG); bitmap_copy_and_extend(nfdt->full_fds_bits, ofdt->full_fds_bits, copy_words, nwords); } /* * Copy all file descriptors from the old table to the new, expanded table and * clear the extra space. Called with the files spinlock held for write. */ static void copy_fdtable(struct fdtable *nfdt, struct fdtable *ofdt) { size_t cpy, set; BUG_ON(nfdt->max_fds < ofdt->max_fds); cpy = ofdt->max_fds * sizeof(struct file *); set = (nfdt->max_fds - ofdt->max_fds) * sizeof(struct file *); memcpy(nfdt->fd, ofdt->fd, cpy); memset((char *)nfdt->fd + cpy, 0, set); copy_fd_bitmaps(nfdt, ofdt, fdt_words(ofdt)); } /* * Note how the fdtable bitmap allocations very much have to be a multiple of * BITS_PER_LONG. This is not only because we walk those things in chunks of * 'unsigned long' in some places, but simply because that is how the Linux * kernel bitmaps are defined to work: they are not "bits in an array of bytes", * they are very much "bits in an array of unsigned long". */ static struct fdtable *alloc_fdtable(unsigned int slots_wanted) { struct fdtable *fdt; unsigned int nr; void *data; /* * Figure out how many fds we actually want to support in this fdtable. * Allocation steps are keyed to the size of the fdarray, since it * grows far faster than any of the other dynamic data. We try to fit * the fdarray into comfortable page-tuned chunks: starting at 1024B * and growing in powers of two from there on. Since we called only * with slots_wanted > BITS_PER_LONG (embedded instance in files->fdtab * already gives BITS_PER_LONG slots), the above boils down to * 1. use the smallest power of two large enough to give us that many * slots. * 2. on 32bit skip 64 and 128 - the minimal capacity we want there is * 256 slots (i.e. 1Kb fd array). * 3. on 64bit don't skip anything, 1Kb fd array means 128 slots there * and we are never going to be asked for 64 or less. */ if (IS_ENABLED(CONFIG_32BIT) && slots_wanted < 256) nr = 256; else nr = roundup_pow_of_two(slots_wanted); /* * Note that this can drive nr *below* what we had passed if sysctl_nr_open * had been set lower between the check in expand_files() and here. * * We make sure that nr remains a multiple of BITS_PER_LONG - otherwise * bitmaps handling below becomes unpleasant, to put it mildly... */ if (unlikely(nr > sysctl_nr_open)) { nr = round_down(sysctl_nr_open, BITS_PER_LONG); if (nr < slots_wanted) return ERR_PTR(-EMFILE); } /* * Check if the allocation size would exceed INT_MAX. kvmalloc_array() * and kvmalloc() will warn if the allocation size is greater than * INT_MAX, as filp_cache objects are not __GFP_NOWARN. * * This can happen when sysctl_nr_open is set to a very high value and * a process tries to use a file descriptor near that limit. For example, * if sysctl_nr_open is set to 1073741816 (0x3ffffff8) - which is what * systemd typically sets it to - then trying to use a file descriptor * close to that value will require allocating a file descriptor table * that exceeds 8GB in size. */ if (unlikely(nr > INT_MAX / sizeof(struct file *))) return ERR_PTR(-EMFILE); fdt = kmalloc_obj(struct fdtable, GFP_KERNEL_ACCOUNT); if (!fdt) goto out; fdt->max_fds = nr; data = kvmalloc_objs(struct file *, nr, GFP_KERNEL_ACCOUNT); if (!data) goto out_fdt; fdt->fd = data; data = kvmalloc(max_t(size_t, 2 * nr / BITS_PER_BYTE + BITBIT_SIZE(nr), L1_CACHE_BYTES), GFP_KERNEL_ACCOUNT); if (!data) goto out_arr; fdt->open_fds = data; data += nr / BITS_PER_BYTE; fdt->close_on_exec = data; data += nr / BITS_PER_BYTE; fdt->full_fds_bits = data; return fdt; out_arr: kvfree(fdt->fd); out_fdt: kfree(fdt); out: return ERR_PTR(-ENOMEM); } /* * Expand the file descriptor table. * This function will allocate a new fdtable and both fd array and fdset, of * the given size. * Return <0 error code on error; 0 on successful completion. * The files->file_lock should be held on entry, and will be held on exit. */ static int expand_fdtable(struct files_struct *files, unsigned int nr) __releases(files->file_lock) __acquires(files->file_lock) { struct fdtable *new_fdt, *cur_fdt; spin_unlock(&files->file_lock); new_fdt = alloc_fdtable(nr + 1); /* make sure all fd_install() have seen resize_in_progress * or have finished their rcu_read_lock_sched() section. */ if (atomic_read(&files->count) > 1) synchronize_rcu(); spin_lock(&files->file_lock); if (IS_ERR(new_fdt)) return PTR_ERR(new_fdt); cur_fdt = files_fdtable(files); BUG_ON(nr < cur_fdt->max_fds); copy_fdtable(new_fdt, cur_fdt); rcu_assign_pointer(files->fdt, new_fdt); if (cur_fdt != &files->fdtab) call_rcu(&cur_fdt->rcu, free_fdtable_rcu); /* coupled with smp_rmb() in fd_install() */ smp_wmb(); return 0; } /* * Expand files. * This function will expand the file structures, if the requested size exceeds * the current capacity and there is room for expansion. * Return <0 error code on error; 0 on success. * The files->file_lock should be held on entry, and will be held on exit. */ static int expand_files(struct files_struct *files, unsigned int nr) __releases(files->file_lock) __acquires(files->file_lock) { struct fdtable *fdt; int error; repeat: fdt = files_fdtable(files); /* Do we need to expand? */ if (nr < fdt->max_fds) return 0; if (unlikely(files->resize_in_progress)) { spin_unlock(&files->file_lock); wait_event(files->resize_wait, !files->resize_in_progress); spin_lock(&files->file_lock); goto repeat; } /* Can we expand? */ if (unlikely(nr >= sysctl_nr_open)) return -EMFILE; /* All good, so we try */ files->resize_in_progress = true; error = expand_fdtable(files, nr); files->resize_in_progress = false; wake_up_all(&files->resize_wait); return error; } static inline void __set_close_on_exec(unsigned int fd, struct fdtable *fdt, bool set) { if (set) { __set_bit(fd, fdt->close_on_exec); } else { if (test_bit(fd, fdt->close_on_exec)) __clear_bit(fd, fdt->close_on_exec); } } static inline void __set_open_fd(unsigned int fd, struct fdtable *fdt, bool set) { __set_bit(fd, fdt->open_fds); __set_close_on_exec(fd, fdt, set); fd /= BITS_PER_LONG; if (!~fdt->open_fds[fd]) __set_bit(fd, fdt->full_fds_bits); } static inline void __clear_open_fd(unsigned int fd, struct fdtable *fdt) { __clear_bit(fd, fdt->open_fds); fd /= BITS_PER_LONG; if (test_bit(fd, fdt->full_fds_bits)) __clear_bit(fd, fdt->full_fds_bits); } static inline bool fd_is_open(unsigned int fd, const struct fdtable *fdt) { return test_bit(fd, fdt->open_fds); } /* * Note that a sane fdtable size always has to be a multiple of * BITS_PER_LONG, since we have bitmaps that are sized by this. * * punch_hole is optional - when close_range() is asked to unshare * and close, we don't need to copy descriptors in that range, so * a smaller cloned descriptor table might suffice if the last * currently opened descriptor falls into that range. */ static unsigned int sane_fdtable_size(struct fdtable *fdt, struct fd_range *punch_hole) { unsigned int last = find_last_bit(fdt->open_fds, fdt->max_fds); if (last == fdt->max_fds) return NR_OPEN_DEFAULT; if (punch_hole && punch_hole->to >= last && punch_hole->from <= last) { last = find_last_bit(fdt->open_fds, punch_hole->from); if (last == punch_hole->from) return NR_OPEN_DEFAULT; } return ALIGN(last + 1, BITS_PER_LONG); } /* * Allocate a new descriptor table and copy contents from the passed in * instance. Returns a pointer to cloned table on success, ERR_PTR() * on failure. For 'punch_hole' see sane_fdtable_size(). */ struct files_struct *dup_fd(struct files_struct *oldf, struct fd_range *punch_hole) { struct files_struct *newf; struct file **old_fds, **new_fds; unsigned int open_files, i; struct fdtable *old_fdt, *new_fdt; newf = kmem_cache_alloc(files_cachep, GFP_KERNEL); if (!newf) return ERR_PTR(-ENOMEM); atomic_set(&newf->count, 1); spin_lock_init(&newf->file_lock); newf->resize_in_progress = false; init_waitqueue_head(&newf->resize_wait); newf->next_fd = 0; new_fdt = &newf->fdtab; new_fdt->max_fds = NR_OPEN_DEFAULT; new_fdt->close_on_exec = newf->close_on_exec_init; new_fdt->open_fds = newf->open_fds_init; new_fdt->full_fds_bits = newf->full_fds_bits_init; new_fdt->fd = &newf->fd_array[0]; spin_lock(&oldf->file_lock); old_fdt = files_fdtable(oldf); open_files = sane_fdtable_size(old_fdt, punch_hole); /* * Check whether we need to allocate a larger fd array and fd set. */ while (unlikely(open_files > new_fdt->max_fds)) { spin_unlock(&oldf->file_lock); if (new_fdt != &newf->fdtab) __free_fdtable(new_fdt); new_fdt = alloc_fdtable(open_files); if (IS_ERR(new_fdt)) { kmem_cache_free(files_cachep, newf); return ERR_CAST(new_fdt); } /* * Reacquire the oldf lock and a pointer to its fd table * who knows it may have a new bigger fd table. We need * the latest pointer. */ spin_lock(&oldf->file_lock); old_fdt = files_fdtable(oldf); open_files = sane_fdtable_size(old_fdt, punch_hole); } copy_fd_bitmaps(new_fdt, old_fdt, open_files / BITS_PER_LONG); old_fds = old_fdt->fd; new_fds = new_fdt->fd; /* * We may be racing against fd allocation from other threads using this * files_struct, despite holding ->file_lock. * * alloc_fd() might have already claimed a slot, while fd_install() * did not populate it yet. Note the latter operates locklessly, so * the file can show up as we are walking the array below. * * At the same time we know no files will disappear as all other * operations take the lock. * * Instead of trying to placate userspace racing with itself, we * ref the file if we see it and mark the fd slot as unused otherwise. */ for (i = open_files; i != 0; i--) { struct file *f = rcu_dereference_raw(*old_fds++); if (f) { get_file(f); } else { __clear_open_fd(open_files - i, new_fdt); } rcu_assign_pointer(*new_fds++, f); } spin_unlock(&oldf->file_lock); /* clear the remainder */ memset(new_fds, 0, (new_fdt->max_fds - open_files) * sizeof(struct file *)); rcu_assign_pointer(newf->fdt, new_fdt); return newf; } static struct fdtable *close_files(struct files_struct * files) { /* * It is safe to dereference the fd table without RCU or * ->file_lock because this is the last reference to the * files structure. */ struct fdtable *fdt = rcu_dereference_raw(files->fdt); unsigned int i, j = 0; for (;;) { unsigned long set; i = j * BITS_PER_LONG; if (i >= fdt->max_fds) break; set = fdt->open_fds[j++]; while (set) { if (set & 1) { struct file *file = fdt->fd[i]; if (file) { filp_close(file, files); cond_resched(); } } i++; set >>= 1; }