diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2020-10-22 09:59:21 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2020-10-22 09:59:21 -0700 |
commit | f56e65dff6ad52395ef45738799b4fb70ff43376 (patch) | |
tree | 230e0ac39888f219a6859fb15ef548fb2bd6511c /fs/read_write.c | |
parent | 24717cfbbbbfa415d1e3dca0f21c417e5faf8208 (diff) | |
parent | 7b84b665c874f60d84547635341e418f20cbbab2 (diff) |
Merge branch 'work.set_fs' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs
Pull initial set_fs() removal from Al Viro:
"Christoph's set_fs base series + fixups"
* 'work.set_fs' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
fs: Allow a NULL pos pointer to __kernel_read
fs: Allow a NULL pos pointer to __kernel_write
powerpc: remove address space overrides using set_fs()
powerpc: use non-set_fs based maccess routines
x86: remove address space overrides using set_fs()
x86: make TASK_SIZE_MAX usable from assembly code
x86: move PAGE_OFFSET, TASK_SIZE & friends to page_{32,64}_types.h
lkdtm: remove set_fs-based tests
test_bitmap: remove user bitmap tests
uaccess: add infrastructure for kernel builds with set_fs()
fs: don't allow splice read/write without explicit ops
fs: don't allow kernel reads and writes without iter ops
sysctl: Convert to iter interfaces
proc: add a read_iter method to proc proc_ops
proc: cleanup the compat vs no compat file ops
proc: remove a level of indentation in proc_get_inode
Diffstat (limited to 'fs/read_write.c')
-rw-r--r-- | fs/read_write.c | 71 |
1 files changed, 45 insertions, 26 deletions
diff --git a/fs/read_write.c b/fs/read_write.c index 19f5c4bf75aa..a669fb049b84 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -419,27 +419,42 @@ static ssize_t new_sync_read(struct file *filp, char __user *buf, size_t len, lo return ret; } +static int warn_unsupported(struct file *file, const char *op) +{ + pr_warn_ratelimited( + "kernel %s not supported for file %pD4 (pid: %d comm: %.20s)\n", + op, file, current->pid, current->comm); + return -EINVAL; +} + ssize_t __kernel_read(struct file *file, void *buf, size_t count, loff_t *pos) { - mm_segment_t old_fs = get_fs(); + struct kvec iov = { + .iov_base = buf, + .iov_len = min_t(size_t, count, MAX_RW_COUNT), + }; + struct kiocb kiocb; + struct iov_iter iter; ssize_t ret; if (WARN_ON_ONCE(!(file->f_mode & FMODE_READ))) return -EINVAL; if (!(file->f_mode & FMODE_CAN_READ)) return -EINVAL; + /* + * Also fail if ->read_iter and ->read are both wired up as that + * implies very convoluted semantics. + */ + if (unlikely(!file->f_op->read_iter || file->f_op->read)) + return warn_unsupported(file, "read"); - if (count > MAX_RW_COUNT) - count = MAX_RW_COUNT; - set_fs(KERNEL_DS); - if (file->f_op->read) - ret = file->f_op->read(file, (void __user *)buf, count, pos); - else if (file->f_op->read_iter) - ret = new_sync_read(file, (void __user *)buf, count, pos); - else - ret = -EINVAL; - set_fs(old_fs); + init_sync_kiocb(&kiocb, file); + kiocb.ki_pos = pos ? *pos : 0; + iov_iter_kvec(&iter, READ, &iov, 1, iov.iov_len); + ret = file->f_op->read_iter(&kiocb, &iter); if (ret > 0) { + if (pos) + *pos = kiocb.ki_pos; fsnotify_access(file); add_rchar(current, ret); } @@ -510,28 +525,32 @@ static ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t /* caller is responsible for file_start_write/file_end_write */ ssize_t __kernel_write(struct file *file, const void *buf, size_t count, loff_t *pos) { - mm_segment_t old_fs; - const char __user *p; + struct kvec iov = { + .iov_base = (void *)buf, + .iov_len = min_t(size_t, count, MAX_RW_COUNT), + }; + struct kiocb kiocb; + struct iov_iter iter; ssize_t ret; if (WARN_ON_ONCE(!(file->f_mode & FMODE_WRITE))) return -EBADF; if (!(file->f_mode & FMODE_CAN_WRITE)) return -EINVAL; + /* + * Also fail if ->write_iter and ->write are both wired up as that + * implies very convoluted semantics. + */ + if (unlikely(!file->f_op->write_iter || file->f_op->write)) + return warn_unsupported(file, "write"); - old_fs = get_fs(); - set_fs(KERNEL_DS); - p = (__force const char __user *)buf; - if (count > MAX_RW_COUNT) - count = MAX_RW_COUNT; - if (file->f_op->write) - ret = file->f_op->write(file, p, count, pos); - else if (file->f_op->write_iter) - ret = new_sync_write(file, p, count, pos); - else - ret = -EINVAL; - set_fs(old_fs); + init_sync_kiocb(&kiocb, file); + kiocb.ki_pos = pos ? *pos : 0; + iov_iter_kvec(&iter, WRITE, &iov, 1, iov.iov_len); + ret = file->f_op->write_iter(&kiocb, &iter); if (ret > 0) { + if (pos) + *pos = kiocb.ki_pos; fsnotify_modify(file); add_wchar(current, ret); } @@ -889,7 +908,7 @@ ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos, } EXPORT_SYMBOL(vfs_iter_write); -ssize_t vfs_readv(struct file *file, const struct iovec __user *vec, +static ssize_t vfs_readv(struct file *file, const struct iovec __user *vec, unsigned long vlen, loff_t *pos, rwf_t flags) { struct iovec iovstack[UIO_FASTIOV]; |