Something went wrong. Try again.
Linux kernel mirror (for testing) git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
Something went wrong. Try again.
123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574// SPDX-License-Identifier: GPL-2.0/* * linux/fs/readdir.c * * Copyright (C) 1995 Linus Torvalds */
#include <linux/stddef.h>#include <linux/kernel.h>#include <linux/export.h>#include <linux/time.h>#include <linux/mm.h>#include <linux/errno.h>#include <linux/stat.h>#include <linux/file.h>#include <linux/fs.h>#include <linux/fsnotify.h>#include <linux/dirent.h>#include <linux/security.h>#include <linux/syscalls.h>#include <linux/unistd.h>#include <linux/compat.h>#include <linux/uaccess.h>
#define dirent_size(dirent, len) offsetof(typeof(*(dirent)), d_name[len])
/* * Some filesystems were never converted to '->iterate_shared()' * and their directory iterators want the inode lock held for * writing. This wrapper allows for converting from the shared * semantics to the exclusive inode use. */int wrap_directory_iterator(struct file *file, struct dir_context *ctx, int (*iter)(struct file *, struct dir_context *)){ struct inode *inode = file_inode(file); int ret;
/* * We'd love to have an 'inode_upgrade_trylock()' operation, * see the comment in mmap_upgrade_trylock() in mm/memory.c. * * But considering this is for "filesystems that never got * converted", it really doesn't matter. * * Also note that since we have to return with the lock held * for reading, we can't use the "killable()" locking here, * since we do need to get the lock even if we're dying. * * We could do the write part killably and then get the read * lock unconditionally if it mattered, but see above on why * this does the very simplistic conversion. */ up_read(&inode->i_rwsem); down_write(&inode->i_rwsem);
/* * Since we dropped the inode lock, we should do the * DEADDIR test again. See 'iterate_dir()' below. * * Note that we don't need to re-do the f_pos games, * since the file must be locked wrt f_pos anyway. */ ret = -ENOENT; if (!IS_DEADDIR(inode)) ret = iter(file, ctx);
downgrade_write(&inode->i_rwsem); return ret;}EXPORT_SYMBOL(wrap_directory_iterator);
/* * Note the "unsafe_put_user()" semantics: we goto a * label for errors. */#define unsafe_copy_dirent_name(_dst, _src, _len, label) do { \ char __user *dst = (_dst); \ const char *src = (_src); \ size_t len = (_len); \ unsafe_put_user(0, dst+len, label); \ unsafe_copy_to_user(dst, src, len, label); \} while (0)
int iterate_dir(struct file *file, struct dir_context *ctx){ struct inode *inode = file_inode(file); int res = -ENOTDIR;
if (!file->f_op->iterate_shared) goto out;
res = security_file_permission(file, MAY_READ); if (res) goto out;
res = fsnotify_file_perm(file, MAY_READ); if (res) goto out;
res = down_read_killable(&inode->i_rwsem); if (res) goto out;
res = -ENOENT; if (!IS_DEADDIR(inode)) { ctx->pos = file->f_pos; res = file->f_op->iterate_shared(file, ctx); file->f_pos = ctx->pos; fsnotify_access(file); file_accessed(file); } inode_unlock_shared(inode);out: return res;}EXPORT_SYMBOL(iterate_dir);
/* * POSIX says that a dirent name cannot contain NULL or a '/'. * * It's not 100% clear what we should really do in this case. * The filesystem is clearly corrupted, but returning a hard * error means that you now don't see any of the other names * either, so that isn't a perfect alternative. * * And if you return an error, what error do you use? Several * filesystems seem to have decided on EUCLEAN being the error * code for EFSCORRUPTED, and that may be the error to use. Or * just EIO, which is perhaps more obvious to users. * * In order to see the other file names in the directory, the * caller might want to make this a "soft" error: skip the * entry, and return the error at the end instead. * * Note that this should likely do a "memchr(name, 0, len)" * check too, since that would be filesystem corruption as * well. However, that case can't actually confuse user space, * which has to do a strlen() on the name anyway to find the * filename length, and the above "soft error" worry means * that it's probably better left alone until we have that * issue clarified. * * Note the PATH_MAX check - it's arbitrary but the real * kernel limit on a possible path component, not NAME_MAX, * which is the technical standard limit. */static int verify_dirent_name(const char *name, int len){ if (len <= 0 || len >= PATH_MAX) return -EIO; if (memchr(name, '/', len)) return -EIO; return 0;}
/* * Traditional linux readdir() handling.. * * "count=1" is a special case, meaning that the buffer is one * dirent-structure in size and that the code can't handle more * anyway. Thus the special "fillonedir()" function for that * case (the low-level handlers don't need to care about this). */
#ifdef __ARCH_WANT_OLD_READDIR
struct old_linux_dirent { unsigned long d_ino; unsigned long d_offset; unsigned short d_namlen; char d_name[];};
struct readdir_callback { struct dir_context ctx; struct old_linux_dirent __user * dirent; int result;};
static bool fillonedir(struct dir_context *ctx, const char *name, int namlen, loff_t offset, u64 ino, unsigned int d_type){ struct readdir_callback *buf = container_of(ctx, struct readdir_callback, ctx); struct old_linux_dirent __user * dirent; unsigned long d_ino;
if (buf->result) return false; buf->result = verify_dirent_name(name, namlen); if (buf->result) return false; d_ino = ino; if (sizeof(d_ino) < sizeof(ino) && d_ino != ino) { buf->result = -EOVERFLOW; return false; } buf->result++; dirent = buf->dirent; scoped_user_write_access_size(dirent, dirent_size(dirent, namlen + 1), efault) { unsafe_put_user(d_ino, &dirent->d_ino, efault); unsafe_put_user(offset, &dirent->d_offset, efault); unsafe_put_user(namlen, &dirent->d_namlen, efault); unsafe_copy_dirent_name(dirent->d_name, name, namlen, efault); } return true;efault: buf->result = -EFAULT; return false;}
SYSCALL_DEFINE3(old_readdir, unsigned int, fd, struct old_linux_dirent __user *, dirent, unsigned int, count){ int error; CLASS(fd_pos, f)(fd); struct readdir_callback buf = { .ctx.actor = fillonedir, .ctx.count = 1, /* Hint to fs: just one entry. */ .dirent = dirent };
if (fd_empty(f)) return -EBADF;
error = iterate_dir(fd_file(f), &buf.ctx); if (buf.result) error = buf.result;
return error;}
#endif /* __ARCH_WANT_OLD_READDIR */
/* * New, all-improved, singing, dancing, iBCS2-compliant getdents() * interface. */struct linux_dirent { unsigned long d_ino; unsigned long d_off; unsigned short d_reclen; char d_name[];};
struct getdents_callback { struct dir_context ctx; struct linux_dirent __user * current_dir; int prev_reclen; int error;};
static bool filldir(struct dir_context *ctx, const char *name, int namlen, loff_t offset, u64 ino, unsigned int d_type){ struct linux_dirent __user *dirent, *prev; struct getdents_callback *buf = container_of(ctx, struct getdents_callback, ctx); unsigned long d_ino; int reclen = ALIGN(dirent_size(dirent, namlen + 2), sizeof(long)); int prev_reclen; unsigned int flags = d_type;
BUILD_BUG_ON(FILLDIR_FLAG_NOINTR & S_DT_MASK); d_type &= S_DT_MASK;
buf->error = verify_dirent_name(name, namlen); if (unlikely(buf->error)) return false; buf->error = -EINVAL; /* only used if we fail.. */ if (reclen > ctx->count) return false; d_ino = ino; if (sizeof(d_ino) < sizeof(ino) && d_ino != ino) { buf->error = -EOVERFLOW; return false; } prev_reclen = buf->prev_reclen; if (!(flags & FILLDIR_FLAG_NOINTR) && prev_reclen && signal_pending(current)) return false; dirent = buf->current_dir; prev = (void __user *) dirent - prev_reclen; scoped_user_write_access_size(prev, reclen + prev_reclen, efault) { /* This might be 'dirent->d_off', but if so it will get overwritten */ unsafe_put_user(offset, &prev->d_off, efault); unsafe_put_user(d_ino, &dirent->d_ino, efault); unsafe_put_user(reclen, &dirent->d_reclen, efault); unsafe_put_user(d_type, (char __user *)dirent + reclen - 1, efault); unsafe_copy_dirent_name(dirent->d_name, name, namlen, efault); }
buf->current_dir = (void __user *)dirent + reclen; buf->prev_reclen = reclen; ctx->count -= reclen; return true;efault: buf->error = -EFAULT; return false;}
SYSCALL_DEFINE3(getdents, unsigned int, fd, struct linux_dirent __user *, dirent, unsigned int, count){ CLASS(fd_pos, f)(fd); struct getdents_callback buf = { .ctx.actor = filldir, .ctx.count = count, .ctx.dt_flags_mask = FILLDIR_FLAG_NOINTR, .current_dir = dirent }; int error;
if (fd_empty(f)) return -EBADF;
error = iterate_dir(fd_file(f), &buf.ctx); if (error >= 0) error = buf.error; if (buf.prev_reclen) { struct linux_dirent __user * lastdirent; lastdirent = (void __user *)buf.current_dir - buf.prev_reclen;
if (put_user(buf.ctx.pos, &lastdirent->d_off)) error = -EFAULT; else error = count - buf.ctx.count; } return error;}
struct getdents_callback64 { struct dir_context ctx; struct linux_dirent64 __user * current_dir; int prev_reclen; int error;};
static bool filldir64(struct dir_context *ctx, const char *name, int namlen, loff_t offset, u64 ino, unsigned int d_type){ struct linux_dirent64 __user *dirent, *prev; struct getdents_callback64 *buf = container_of(ctx, struct getdents_callback64, ctx); int reclen = ALIGN(dirent_size(dirent, namlen + 1), sizeof(u64)); int prev_reclen; unsigned int flags = d_type;
BUILD_BUG_ON(FILLDIR_FLAG_NOINTR & S_DT_MASK); d_type &= S_DT_MASK;
buf->error = verify_dirent_name(name, namlen); if (unlikely(buf->error)) return false; buf->error = -EINVAL; /* only used if we fail.. */ if (reclen > ctx->count) return false; prev_reclen = buf->prev_reclen; if (!(flags & FILLDIR_FLAG_NOINTR) && prev_reclen && signal_pending(current)) return false; dirent = buf->current_dir; prev = (void __user *)dirent - prev_reclen; scoped_user_write_access_size(prev, reclen + prev_reclen, efault) { /* This might be 'dirent->d_off', but if so it will get overwritten */ unsafe_put_user(offset, &prev->d_off, efault); unsafe_put_user(ino, &dirent->d_ino, efault); unsafe_put_user(reclen, &dirent->d_reclen, efault); unsafe_put_user(d_type, &dirent->d_type, efault); unsafe_copy_dirent_name(dirent->d_name, name, namlen, efault); }
buf->prev_reclen = reclen; buf->current_dir = (void __user *)dirent + reclen; ctx->count -= reclen; return true;
efault: buf->error = -EFAULT; return false;}
SYSCALL_DEFINE3(getdents64, unsigned int, fd, struct linux_dirent64 __user *, dirent, unsigned int, count){ CLASS(fd_pos, f)(fd); struct getdents_callback64 buf = { .ctx.actor = filldir64, .ctx.count = count, .ctx.dt_flags_mask = FILLDIR_FLAG_NOINTR, .current_dir = dirent }; int error;
if (fd_empty(f)) return -EBADF;
error = iterate_dir(fd_file(f), &buf.ctx); if (error >= 0) error = buf.error; if (buf.prev_reclen) { struct linux_dirent64 __user * lastdirent; typeof(lastdirent->d_off) d_off = buf.ctx.pos;
lastdirent = (void __user *) buf.current_dir - buf.prev_reclen; if (put_user(d_off, &lastdirent->d_off)) error = -EFAULT; else error = count - buf.ctx.count; } return error;}
#ifdef CONFIG_COMPATstruct compat_old_linux_dirent { compat_ulong_t d_ino; compat_ulong_t d_offset; unsigned short d_namlen; char d_name[];};
struct compat_readdir_callback { struct dir_context ctx; struct compat_old_linux_dirent __user *dirent; int result;};
static bool compat_fillonedir(struct dir_context *ctx, const char *name, int namlen, loff_t offset, u64 ino, unsigned int d_type){ struct compat_readdir_callback *buf = container_of(ctx, struct compat_readdir_callback, ctx); struct compat_old_linux_dirent __user *dirent; compat_ulong_t d_ino;
if (buf->result) return false; buf->result = verify_dirent_name(name, namlen); if (buf->result) return false; d_ino = ino; if (sizeof(d_ino) < sizeof(ino) && d_ino != ino) { buf->result = -EOVERFLOW; return false; } buf->result++; dirent = buf->dirent; scoped_user_write_access_size(dirent, dirent_size(dirent, namlen + 1), efault) { unsafe_put_user(d_ino, &dirent->d_ino, efault); unsafe_put_user(offset, &dirent->d_offset, efault); unsafe_put_user(namlen, &dirent->d_namlen, efault); unsafe_copy_dirent_name(dirent->d_name, name, namlen, efault); } return true;efault: buf->result = -EFAULT; return false;}
COMPAT_SYSCALL_DEFINE3(old_readdir, unsigned int, fd, struct compat_old_linux_dirent __user *, dirent, unsigned int, count){ int error; CLASS(fd_pos, f)(fd); struct compat_readdir_callback buf = { .ctx.actor = compat_fillonedir, .ctx.count = 1, /* Hint to fs: just one entry. */ .dirent = dirent };
if (fd_empty(f)) return -EBADF;
error = iterate_dir(fd_file(f), &buf.ctx); if (buf.result) error = buf.result;
return error;}
struct compat_linux_dirent { compat_ulong_t d_ino; compat_ulong_t d_off; unsigned short d_reclen; char d_name[];};
struct compat_getdents_callback { struct dir_context ctx; struct compat_linux_dirent __user *current_dir; int prev_reclen; int error;};
static bool compat_filldir(struct dir_context *ctx, const char *name, int namlen, loff_t offset, u64 ino, unsigned int d_type){ struct compat_linux_dirent __user *dirent, *prev; struct compat_getdents_callback *buf = container_of(ctx, struct compat_getdents_callback, ctx); compat_ulong_t d_ino; int reclen = ALIGN(dirent_size(dirent, namlen + 2), sizeof(compat_long_t)); int prev_reclen; unsigned int flags = d_type;
BUILD_BUG_ON(FILLDIR_FLAG_NOINTR & S_DT_MASK); d_type &= S_DT_MASK;
buf->error = verify_dirent_name(name, namlen); if (unlikely(buf->error)) return false; buf->error = -EINVAL; /* only used if we fail.. */ if (reclen > ctx->count) return false; d_ino = ino; if (sizeof(d_ino) < sizeof(ino) && d_ino != ino) { buf->error = -EOVERFLOW; return false; } prev_reclen = buf->prev_reclen; if (!(flags & FILLDIR_FLAG_NOINTR) && prev_reclen && signal_pending(current)) return false; dirent = buf->current_dir; prev = (void __user *) dirent - prev_reclen; scoped_user_write_access_size(prev, reclen + prev_reclen, efault) { unsafe_put_user(offset, &prev->d_off, efault); unsafe_put_user(d_ino, &dirent->d_ino, efault); unsafe_put_user(reclen, &dirent->d_reclen, efault); unsafe_put_user(d_type, (char __user *)dirent + reclen - 1, efault); unsafe_copy_dirent_name(dirent->d_name, name, namlen, efault); }
buf->prev_reclen = reclen; buf->current_dir = (void __user *)dirent + reclen; ctx->count -= reclen; return true;efault: buf->error = -EFAULT; return false;}
COMPAT_SYSCALL_DEFINE3(getdents, unsigned int, fd, struct compat_linux_dirent __user *, dirent, unsigned int, count){ CLASS(fd_pos, f)(fd); struct compat_getdents_callback buf = { .ctx.actor = compat_filldir, .ctx.count = count, .ctx.dt_flags_mask = FILLDIR_FLAG_NOINTR, .current_dir = dirent, }; int error;
if (fd_empty(f)) return -EBADF;
error = iterate_dir(fd_file(f), &buf.ctx); if (error >= 0) error = buf.error; if (buf.prev_reclen) { struct compat_linux_dirent __user * lastdirent; lastdirent = (void __user *)buf.current_dir - buf.prev_reclen;
if (put_user(buf.ctx.pos, &lastdirent->d_off)) error = -EFAULT; else error = count - buf.ctx.count; } return error;}#endif