summaryrefslogtreecommitdiff
path: root/fs/read_write.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/read_write.c')
-rw-r--r--fs/read_write.c655
1 files changed, 459 insertions, 196 deletions
diff --git a/fs/read_write.c b/fs/read_write.c
index c20614f86c01..122a3846d9e1 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -9,17 +9,23 @@
#include <linux/fcntl.h>
#include <linux/file.h>
#include <linux/uio.h>
+#include <linux/aio.h>
#include <linux/fsnotify.h>
#include <linux/security.h>
#include <linux/export.h>
#include <linux/syscalls.h>
#include <linux/pagemap.h>
#include <linux/splice.h>
-#include "read_write.h"
+#include <linux/compat.h>
+#include "internal.h"
#include <asm/uaccess.h>
#include <asm/unistd.h>
+typedef ssize_t (*io_fn_t)(struct file *, char __user *, size_t, loff_t *);
+typedef ssize_t (*iov_fn_t)(struct kiocb *, const struct iovec *,
+ unsigned long, loff_t);
+
const struct file_operations generic_ro_fops = {
.llseek = generic_file_llseek,
.read = do_sync_read,
@@ -35,8 +41,19 @@ static inline int unsigned_offsets(struct file *file)
return file->f_mode & FMODE_UNSIGNED_OFFSET;
}
-static loff_t lseek_execute(struct file *file, struct inode *inode,
- loff_t offset, loff_t maxsize)
+/**
+ * vfs_setpos - update the file offset for lseek
+ * @file: file structure in question
+ * @offset: file offset to seek to
+ * @maxsize: maximum file size
+ *
+ * This is a low-level filesystem helper for updating the file offset to
+ * the value specified by @offset if the given offset is valid and it is
+ * not equal to the current file offset.
+ *
+ * Return the specified offset on success and -EINVAL on invalid offset.
+ */
+loff_t vfs_setpos(struct file *file, loff_t offset, loff_t maxsize)
{
if (offset < 0 && !unsigned_offsets(file))
return -EINVAL;
@@ -49,16 +66,18 @@ static loff_t lseek_execute(struct file *file, struct inode *inode,
}
return offset;
}
+EXPORT_SYMBOL(vfs_setpos);
/**
* generic_file_llseek_size - generic llseek implementation for regular files
* @file: file structure to seek on
* @offset: file offset to seek to
- * @origin: type of seek
- * @size: max size of file system
+ * @whence: type of seek
+ * @size: max size of this file in file system
+ * @eof: offset used for SEEK_END position
*
* This is a variant of generic_file_llseek that allows passing in a custom
- * file size.
+ * maximum file size and a custom EOF position, for e.g. hashed directories
*
* Synchronization:
* SEEK_SET and SEEK_END are unsynchronized (but atomic on 64bit platforms)
@@ -66,14 +85,12 @@ static loff_t lseek_execute(struct file *file, struct inode *inode,
* read/writes behave like SEEK_SET against seeks.
*/
loff_t
-generic_file_llseek_size(struct file *file, loff_t offset, int origin,
- loff_t maxsize)
+generic_file_llseek_size(struct file *file, loff_t offset, int whence,
+ loff_t maxsize, loff_t eof)
{
- struct inode *inode = file->f_mapping->host;
-
- switch (origin) {
+ switch (whence) {
case SEEK_END:
- offset += i_size_read(inode);
+ offset += eof;
break;
case SEEK_CUR:
/*
@@ -90,8 +107,7 @@ generic_file_llseek_size(struct file *file, loff_t offset, int origin,
* like SEEK_SET.
*/
spin_lock(&file->f_lock);
- offset = lseek_execute(file, inode, file->f_pos + offset,
- maxsize);
+ offset = vfs_setpos(file, file->f_pos + offset, maxsize);
spin_unlock(&file->f_lock);
return offset;
case SEEK_DATA:
@@ -99,7 +115,7 @@ generic_file_llseek_size(struct file *file, loff_t offset, int origin,
* In the generic case the entire file is data, so as long as
* offset isn't at the end of the file then the offset is data.
*/
- if (offset >= i_size_read(inode))
+ if (offset >= eof)
return -ENXIO;
break;
case SEEK_HOLE:
@@ -107,13 +123,13 @@ generic_file_llseek_size(struct file *file, loff_t offset, int origin,
* There is a virtual hole at the end of the file, so as long as
* offset isn't i_size or larger, return i_size.
*/
- if (offset >= i_size_read(inode))
+ if (offset >= eof)
return -ENXIO;
- offset = i_size_read(inode);
+ offset = eof;
break;
}
- return lseek_execute(file, inode, offset, maxsize);
+ return vfs_setpos(file, offset, maxsize);
}
EXPORT_SYMBOL(generic_file_llseek_size);
@@ -121,51 +137,72 @@ EXPORT_SYMBOL(generic_file_llseek_size);
* generic_file_llseek - generic llseek implementation for regular files
* @file: file structure to seek on
* @offset: file offset to seek to
- * @origin: type of seek
+ * @whence: type of seek
*
* This is a generic implemenation of ->llseek useable for all normal local
* filesystems. It just updates the file offset to the value specified by
- * @offset and @origin under i_mutex.
+ * @offset and @whence.
*/
-loff_t generic_file_llseek(struct file *file, loff_t offset, int origin)
+loff_t generic_file_llseek(struct file *file, loff_t offset, int whence)
{
struct inode *inode = file->f_mapping->host;
- return generic_file_llseek_size(file, offset, origin,
- inode->i_sb->s_maxbytes);
+ return generic_file_llseek_size(file, offset, whence,
+ inode->i_sb->s_maxbytes,
+ i_size_read(inode));
}
EXPORT_SYMBOL(generic_file_llseek);
/**
+ * fixed_size_llseek - llseek implementation for fixed-sized devices
+ * @file: file structure to seek on
+ * @offset: file offset to seek to
+ * @whence: type of seek
+ * @size: size of the file
+ *
+ */
+loff_t fixed_size_llseek(struct file *file, loff_t offset, int whence, loff_t size)
+{
+ switch (whence) {
+ case SEEK_SET: case SEEK_CUR: case SEEK_END:
+ return generic_file_llseek_size(file, offset, whence,
+ size, size);
+ default:
+ return -EINVAL;
+ }
+}
+EXPORT_SYMBOL(fixed_size_llseek);
+
+/**
* noop_llseek - No Operation Performed llseek implementation
* @file: file structure to seek on
* @offset: file offset to seek to
- * @origin: type of seek
+ * @whence: type of seek
*
* This is an implementation of ->llseek useable for the rare special case when
* userspace expects the seek to succeed but the (device) file is actually not
* able to perform the seek. In this case you use noop_llseek() instead of
* falling back to the default implementation of ->llseek.
*/
-loff_t noop_llseek(struct file *file, loff_t offset, int origin)
+loff_t noop_llseek(struct file *file, loff_t offset, int whence)
{
return file->f_pos;
}
EXPORT_SYMBOL(noop_llseek);
-loff_t no_llseek(struct file *file, loff_t offset, int origin)
+loff_t no_llseek(struct file *file, loff_t offset, int whence)
{
return -ESPIPE;
}
EXPORT_SYMBOL(no_llseek);
-loff_t default_llseek(struct file *file, loff_t offset, int origin)
+loff_t default_llseek(struct file *file, loff_t offset, int whence)
{
- struct inode *inode = file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(file);
loff_t retval;
mutex_lock(&inode->i_mutex);
- switch (origin) {
+ switch (whence) {
case SEEK_END:
offset += i_size_read(inode);
break;
@@ -214,7 +251,7 @@ out:
}
EXPORT_SYMBOL(default_llseek);
-loff_t vfs_llseek(struct file *file, loff_t offset, int origin)
+loff_t vfs_llseek(struct file *file, loff_t offset, int whence)
{
loff_t (*fn)(struct file *, loff_t, int);
@@ -223,54 +260,53 @@ loff_t vfs_llseek(struct file *file, loff_t offset, int origin)
if (file->f_op && file->f_op->llseek)
fn = file->f_op->llseek;
}
- return fn(file, offset, origin);
+ return fn(file, offset, whence);
}
EXPORT_SYMBOL(vfs_llseek);
-SYSCALL_DEFINE3(lseek, unsigned int, fd, off_t, offset, unsigned int, origin)
+SYSCALL_DEFINE3(lseek, unsigned int, fd, off_t, offset, unsigned int, whence)
{
off_t retval;
- struct file * file;
- int fput_needed;
-
- retval = -EBADF;
- file = fget_light(fd, &fput_needed);
- if (!file)
- goto bad;
+ struct fd f = fdget(fd);
+ if (!f.file)
+ return -EBADF;
retval = -EINVAL;
- if (origin <= SEEK_MAX) {
- loff_t res = vfs_llseek(file, offset, origin);
+ if (whence <= SEEK_MAX) {
+ loff_t res = vfs_llseek(f.file, offset, whence);
retval = res;
if (res != (loff_t)retval)
retval = -EOVERFLOW; /* LFS: should only happen on 32 bit platforms */
}
- fput_light(file, fput_needed);
-bad:
+ fdput(f);
return retval;
}
+#ifdef CONFIG_COMPAT
+COMPAT_SYSCALL_DEFINE3(lseek, unsigned int, fd, compat_off_t, offset, unsigned int, whence)
+{
+ return sys_lseek(fd, offset, whence);
+}
+#endif
+
#ifdef __ARCH_WANT_SYS_LLSEEK
SYSCALL_DEFINE5(llseek, unsigned int, fd, unsigned long, offset_high,
unsigned long, offset_low, loff_t __user *, result,
- unsigned int, origin)
+ unsigned int, whence)
{
int retval;
- struct file * file;
+ struct fd f = fdget(fd);
loff_t offset;
- int fput_needed;
- retval = -EBADF;
- file = fget_light(fd, &fput_needed);
- if (!file)
- goto bad;
+ if (!f.file)
+ return -EBADF;
retval = -EINVAL;
- if (origin > SEEK_MAX)
+ if (whence > SEEK_MAX)
goto out_putf;
- offset = vfs_llseek(file, ((loff_t) offset_high << 32) | offset_low,
- origin);
+ offset = vfs_llseek(f.file, ((loff_t) offset_high << 32) | offset_low,
+ whence);
retval = (int)offset;
if (offset >= 0) {
@@ -279,25 +315,23 @@ SYSCALL_DEFINE5(llseek, unsigned int, fd, unsigned long, offset_high,
retval = 0;
}
out_putf:
- fput_light(file, fput_needed);
-bad:
+ fdput(f);
return retval;
}
#endif
-
/*
* rw_verify_area doesn't like huge counts. We limit
* them to something that fits in "int" so that others
* won't have to do range checks all the time.
*/
-int rw_verify_area(int read_write, struct file *file, loff_t *ppos, size_t count)
+int rw_verify_area(int read_write, struct file *file, const loff_t *ppos, size_t count)
{
struct inode *inode;
loff_t pos;
int retval = -EINVAL;
- inode = file->f_path.dentry->d_inode;
+ inode = file_inode(file);
if (unlikely((ssize_t) count < 0))
return retval;
pos = *ppos;
@@ -325,16 +359,6 @@ int rw_verify_area(int read_write, struct file *file, loff_t *ppos, size_t count
return count > MAX_RW_COUNT ? MAX_RW_COUNT : count;
}
-static void wait_on_retry_sync_kiocb(struct kiocb *iocb)
-{
- set_current_state(TASK_UNINTERRUPTIBLE);
- if (!kiocbIsKicked(iocb))
- schedule();
- else
- kiocbClearKicked(iocb);
- __set_current_state(TASK_RUNNING);
-}
-
ssize_t do_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos)
{
struct iovec iov = { .iov_base = buf, .iov_len = len };
@@ -346,13 +370,7 @@ ssize_t do_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *pp
kiocb.ki_left = len;
kiocb.ki_nbytes = len;
- for (;;) {
- ret = filp->f_op->aio_read(&kiocb, &iov, 1, kiocb.ki_pos);
- if (ret != -EIOCBRETRY)
- break;
- wait_on_retry_sync_kiocb(&kiocb);
- }
-
+ ret = filp->f_op->aio_read(&kiocb, &iov, 1, kiocb.ki_pos);
if (-EIOCBQUEUED == ret)
ret = wait_on_sync_kiocb(&kiocb);
*ppos = kiocb.ki_pos;
@@ -402,13 +420,7 @@ ssize_t do_sync_write(struct file *filp, const char __user *buf, size_t len, lof
kiocb.ki_left = len;
kiocb.ki_nbytes = len;
- for (;;) {
- ret = filp->f_op->aio_write(&kiocb, &iov, 1, kiocb.ki_pos);
- if (ret != -EIOCBRETRY)
- break;
- wait_on_retry_sync_kiocb(&kiocb);
- }
-
+ ret = filp->f_op->aio_write(&kiocb, &iov, 1, kiocb.ki_pos);
if (-EIOCBQUEUED == ret)
ret = wait_on_sync_kiocb(&kiocb);
*ppos = kiocb.ki_pos;
@@ -417,6 +429,33 @@ ssize_t do_sync_write(struct file *filp, const char __user *buf, size_t len, lof
EXPORT_SYMBOL(do_sync_write);
+ssize_t __kernel_write(struct file *file, const char *buf, size_t count, loff_t *pos)
+{
+ mm_segment_t old_fs;
+ const char __user *p;
+ ssize_t ret;
+
+ if (!file->f_op || (!file->f_op->write && !file->f_op->aio_write))
+ return -EINVAL;
+
+ old_fs = get_fs();
+ set_fs(get_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
+ ret = do_sync_write(file, p, count, pos);
+ set_fs(old_fs);
+ if (ret > 0) {
+ fsnotify_modify(file);
+ add_wchar(current, ret);
+ }
+ inc_syscw(current);
+ return ret;
+}
+
ssize_t vfs_write(struct file *file, const char __user *buf, size_t count, loff_t *pos)
{
ssize_t ret;
@@ -431,6 +470,7 @@ ssize_t vfs_write(struct file *file, const char __user *buf, size_t count, loff_
ret = rw_verify_area(WRITE, file, pos, count);
if (ret >= 0) {
count = ret;
+ file_start_write(file);
if (file->f_op->write)
ret = file->f_op->write(file, buf, count, pos);
else
@@ -440,6 +480,7 @@ ssize_t vfs_write(struct file *file, const char __user *buf, size_t count, loff_
add_wchar(current, ret);
}
inc_syscw(current);
+ file_end_write(file);
}
return ret;
@@ -459,96 +500,75 @@ static inline void file_pos_write(struct file *file, loff_t pos)
SYSCALL_DEFINE3(read, unsigned int, fd, char __user *, buf, size_t, count)
{
- struct file *file;
+ struct fd f = fdget(fd);
ssize_t ret = -EBADF;
- int fput_needed;
- file = fget_light(fd, &fput_needed);
- if (file) {
- loff_t pos = file_pos_read(file);
- ret = vfs_read(file, buf, count, &pos);
- file_pos_write(file, pos);
- fput_light(file, fput_needed);
+ if (f.file) {
+ loff_t pos = file_pos_read(f.file);
+ ret = vfs_read(f.file, buf, count, &pos);
+ if (ret >= 0)
+ file_pos_write(f.file, pos);
+ fdput(f);
}
-
return ret;
}
SYSCALL_DEFINE3(write, unsigned int, fd, const char __user *, buf,
size_t, count)
{
- struct file *file;
+ struct fd f = fdget(fd);
ssize_t ret = -EBADF;
- int fput_needed;
- file = fget_light(fd, &fput_needed);
- if (file) {
- loff_t pos = file_pos_read(file);
- ret = vfs_write(file, buf, count, &pos);
- file_pos_write(file, pos);
- fput_light(file, fput_needed);
+ if (f.file) {
+ loff_t pos = file_pos_read(f.file);
+ ret = vfs_write(f.file, buf, count, &pos);
+ if (ret >= 0)
+ file_pos_write(f.file, pos);
+ fdput(f);
}
return ret;
}
-SYSCALL_DEFINE(pread64)(unsigned int fd, char __user *buf,
- size_t count, loff_t pos)
+SYSCALL_DEFINE4(pread64, unsigned int, fd, char __user *, buf,
+ size_t, count, loff_t, pos)
{
- struct file *file;
+ struct fd f;
ssize_t ret = -EBADF;
- int fput_needed;
if (pos < 0)
return -EINVAL;
- file = fget_light(fd, &fput_needed);
- if (file) {
+ f = fdget(fd);
+ if (f.file) {
ret = -ESPIPE;
- if (file->f_mode & FMODE_PREAD)
- ret = vfs_read(file, buf, count, &pos);
- fput_light(file, fput_needed);
+ if (f.file->f_mode & FMODE_PREAD)
+ ret = vfs_read(f.file, buf, count, &pos);
+ fdput(f);
}
return ret;
}
-#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS
-asmlinkage long SyS_pread64(long fd, long buf, long count, loff_t pos)
-{
- return SYSC_pread64((unsigned int) fd, (char __user *) buf,
- (size_t) count, pos);
-}
-SYSCALL_ALIAS(sys_pread64, SyS_pread64);
-#endif
-SYSCALL_DEFINE(pwrite64)(unsigned int fd, const char __user *buf,
- size_t count, loff_t pos)
+SYSCALL_DEFINE4(pwrite64, unsigned int, fd, const char __user *, buf,
+ size_t, count, loff_t, pos)
{
- struct file *file;
+ struct fd f;
ssize_t ret = -EBADF;
- int fput_needed;
if (pos < 0)
return -EINVAL;
- file = fget_light(fd, &fput_needed);
- if (file) {
+ f = fdget(fd);
+ if (f.file) {
ret = -ESPIPE;
- if (file->f_mode & FMODE_PWRITE)
- ret = vfs_write(file, buf, count, &pos);
- fput_light(file, fput_needed);
+ if (f.file->f_mode & FMODE_PWRITE)
+ ret = vfs_write(f.file, buf, count, &pos);
+ fdput(f);
}
return ret;
}
-#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS
-asmlinkage long SyS_pwrite64(long fd, long buf, long count, loff_t pos)
-{
- return SYSC_pwrite64((unsigned int) fd, (const char __user *) buf,
- (size_t) count, pos);
-}
-SYSCALL_ALIAS(sys_pwrite64, SyS_pwrite64);
-#endif
/*
* Reduce an iovec's length in-place. Return the resulting number of segments
@@ -571,7 +591,7 @@ unsigned long iov_shorten(struct iovec *iov, unsigned long nr_segs, size_t to)
}
EXPORT_SYMBOL(iov_shorten);
-ssize_t do_sync_readv_writev(struct file *filp, const struct iovec *iov,
+static ssize_t do_sync_readv_writev(struct file *filp, const struct iovec *iov,
unsigned long nr_segs, size_t len, loff_t *ppos, iov_fn_t fn)
{
struct kiocb kiocb;
@@ -582,13 +602,7 @@ ssize_t do_sync_readv_writev(struct file *filp, const struct iovec *iov,
kiocb.ki_left = len;
kiocb.ki_nbytes = len;
- for (;;) {
- ret = fn(&kiocb, iov, nr_segs, kiocb.ki_pos);
- if (ret != -EIOCBRETRY)
- break;
- wait_on_retry_sync_kiocb(&kiocb);
- }
-
+ ret = fn(&kiocb, iov, nr_segs, kiocb.ki_pos);
if (ret == -EIOCBQUEUED)
ret = wait_on_sync_kiocb(&kiocb);
*ppos = kiocb.ki_pos;
@@ -596,7 +610,7 @@ ssize_t do_sync_readv_writev(struct file *filp, const struct iovec *iov,
}
/* Do it by hand, with file-ops */
-ssize_t do_loop_readv_writev(struct file *filp, struct iovec *iov,
+static ssize_t do_loop_readv_writev(struct file *filp, struct iovec *iov,
unsigned long nr_segs, loff_t *ppos, io_fn_t fn)
{
struct iovec *vector = iov;
@@ -738,6 +752,7 @@ static ssize_t do_readv_writev(int type, struct file *file,
} else {
fn = (io_fn_t)file->f_op->write;
fnv = file->f_op->aio_write;
+ file_start_write(file);
}
if (fnv)
@@ -746,6 +761,9 @@ static ssize_t do_readv_writev(int type, struct file *file,
else
ret = do_loop_readv_writev(file, iov, nr_segs, pos, fn);
+ if (type != READ)
+ file_end_write(file);
+
out:
if (iov != iovstack)
kfree(iov);
@@ -787,16 +805,15 @@ EXPORT_SYMBOL(vfs_writev);
SYSCALL_DEFINE3(readv, unsigned long, fd, const struct iovec __user *, vec,
unsigned long, vlen)
{
- struct file *file;
+ struct fd f = fdget(fd);
ssize_t ret = -EBADF;
- int fput_needed;
- file = fget_light(fd, &fput_needed);
- if (file) {
- loff_t pos = file_pos_read(file);
- ret = vfs_readv(file, vec, vlen, &pos);
- file_pos_write(file, pos);
- fput_light(file, fput_needed);
+ if (f.file) {
+ loff_t pos = file_pos_read(f.file);
+ ret = vfs_readv(f.file, vec, vlen, &pos);
+ if (ret >= 0)
+ file_pos_write(f.file, pos);
+ fdput(f);
}
if (ret > 0)
@@ -808,16 +825,15 @@ SYSCALL_DEFINE3(readv, unsigned long, fd, const struct iovec __user *, vec,
SYSCALL_DEFINE3(writev, unsigned long, fd, const struct iovec __user *, vec,
unsigned long, vlen)
{
- struct file *file;
+ struct fd f = fdget(fd);
ssize_t ret = -EBADF;
- int fput_needed;
- file = fget_light(fd, &fput_needed);
- if (file) {
- loff_t pos = file_pos_read(file);
- ret = vfs_writev(file, vec, vlen, &pos);
- file_pos_write(file, pos);
- fput_light(file, fput_needed);
+ if (f.file) {
+ loff_t pos = file_pos_read(f.file);
+ ret = vfs_writev(f.file, vec, vlen, &pos);
+ if (ret >= 0)
+ file_pos_write(f.file, pos);
+ fdput(f);
}
if (ret > 0)
@@ -836,19 +852,18 @@ SYSCALL_DEFINE5(preadv, unsigned long, fd, const struct iovec __user *, vec,
unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h)
{
loff_t pos = pos_from_hilo(pos_h, pos_l);
- struct file *file;
+ struct fd f;
ssize_t ret = -EBADF;
- int fput_needed;
if (pos < 0)
return -EINVAL;
- file = fget_light(fd, &fput_needed);
- if (file) {
+ f = fdget(fd);
+ if (f.file) {
ret = -ESPIPE;
- if (file->f_mode & FMODE_PREAD)
- ret = vfs_readv(file, vec, vlen, &pos);
- fput_light(file, fput_needed);
+ if (f.file->f_mode & FMODE_PREAD)
+ ret = vfs_readv(f.file, vec, vlen, &pos);
+ fdput(f);
}
if (ret > 0)
@@ -861,52 +876,251 @@ SYSCALL_DEFINE5(pwritev, unsigned long, fd, const struct iovec __user *, vec,
unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h)
{
loff_t pos = pos_from_hilo(pos_h, pos_l);
- struct file *file;
+ struct fd f;
ssize_t ret = -EBADF;
- int fput_needed;
if (pos < 0)
return -EINVAL;
- file = fget_light(fd, &fput_needed);
- if (file) {
+ f = fdget(fd);
+ if (f.file) {
ret = -ESPIPE;
- if (file->f_mode & FMODE_PWRITE)
- ret = vfs_writev(file, vec, vlen, &pos);
- fput_light(file, fput_needed);
+ if (f.file->f_mode & FMODE_PWRITE)
+ ret = vfs_writev(f.file, vec, vlen, &pos);
+ fdput(f);
+ }
+
+ if (ret > 0)
+ add_wchar(current, ret);
+ inc_syscw(current);
+ return ret;
+}
+
+#ifdef CONFIG_COMPAT
+
+static ssize_t compat_do_readv_writev(int type, struct file *file,
+ const struct compat_iovec __user *uvector,
+ unsigned long nr_segs, loff_t *pos)
+{
+ compat_ssize_t tot_len;
+ struct iovec iovstack[UIO_FASTIOV];
+ struct iovec *iov = iovstack;
+ ssize_t ret;
+ io_fn_t fn;
+ iov_fn_t fnv;
+
+ ret = -EINVAL;
+ if (!file->f_op)
+ goto out;
+
+ ret = -EFAULT;
+ if (!access_ok(VERIFY_READ, uvector, nr_segs*sizeof(*uvector)))
+ goto out;
+
+ ret = compat_rw_copy_check_uvector(type, uvector, nr_segs,
+ UIO_FASTIOV, iovstack, &iov);
+ if (ret <= 0)
+ goto out;
+
+ tot_len = ret;
+ ret = rw_verify_area(type, file, pos, tot_len);
+ if (ret < 0)
+ goto out;
+
+ fnv = NULL;
+ if (type == READ) {
+ fn = file->f_op->read;
+ fnv = file->f_op->aio_read;
+ } else {
+ fn = (io_fn_t)file->f_op->write;
+ fnv = file->f_op->aio_write;
+ file_start_write(file);
+ }
+
+ if (fnv)
+ ret = do_sync_readv_writev(file, iov, nr_segs, tot_len,
+ pos, fnv);
+ else
+ ret = do_loop_readv_writev(file, iov, nr_segs, pos, fn);
+
+ if (type != READ)
+ file_end_write(file);
+
+out:
+ if (iov != iovstack)
+ kfree(iov);
+ if ((ret + (type == READ)) > 0) {
+ if (type == READ)
+ fsnotify_access(file);
+ else
+ fsnotify_modify(file);
}
+ return ret;
+}
+
+static size_t compat_readv(struct file *file,
+ const struct compat_iovec __user *vec,
+ unsigned long vlen, loff_t *pos)
+{
+ ssize_t ret = -EBADF;
+ if (!(file->f_mode & FMODE_READ))
+ goto out;
+
+ ret = -EINVAL;
+ if (!file->f_op || (!file->f_op->aio_read && !file->f_op->read))
+ goto out;
+
+ ret = compat_do_readv_writev(READ, file, vec, vlen, pos);
+
+out:
+ if (ret > 0)
+ add_rchar(current, ret);
+ inc_syscr(current);
+ return ret;
+}
+
+COMPAT_SYSCALL_DEFINE3(readv, unsigned long, fd,
+ const struct compat_iovec __user *,vec,
+ unsigned long, vlen)
+{
+ struct fd f = fdget(fd);
+ ssize_t ret;
+ loff_t pos;
+
+ if (!f.file)
+ return -EBADF;
+ pos = f.file->f_pos;
+ ret = compat_readv(f.file, vec, vlen, &pos);
+ if (ret >= 0)
+ f.file->f_pos = pos;
+ fdput(f);
+ return ret;
+}
+
+COMPAT_SYSCALL_DEFINE4(preadv64, unsigned long, fd,
+ const struct compat_iovec __user *,vec,
+ unsigned long, vlen, loff_t, pos)
+{
+ struct fd f;
+ ssize_t ret;
+
+ if (pos < 0)
+ return -EINVAL;
+ f = fdget(fd);
+ if (!f.file)
+ return -EBADF;
+ ret = -ESPIPE;
+ if (f.file->f_mode & FMODE_PREAD)
+ ret = compat_readv(f.file, vec, vlen, &pos);
+ fdput(f);
+ return ret;
+}
+
+COMPAT_SYSCALL_DEFINE5(preadv, unsigned long, fd,
+ const struct compat_iovec __user *,vec,
+ unsigned long, vlen, u32, pos_low, u32, pos_high)
+{
+ loff_t pos = ((loff_t)pos_high << 32) | pos_low;
+ return compat_sys_preadv64(fd, vec, vlen, pos);
+}
+
+static size_t compat_writev(struct file *file,
+ const struct compat_iovec __user *vec,
+ unsigned long vlen, loff_t *pos)
+{
+ ssize_t ret = -EBADF;
+
+ if (!(file->f_mode & FMODE_WRITE))
+ goto out;
+
+ ret = -EINVAL;
+ if (!file->f_op || (!file->f_op->aio_write && !file->f_op->write))
+ goto out;
+
+ ret = compat_do_readv_writev(WRITE, file, vec, vlen, pos);
+
+out:
if (ret > 0)
add_wchar(current, ret);
inc_syscw(current);
return ret;
}
+COMPAT_SYSCALL_DEFINE3(writev, unsigned long, fd,
+ const struct compat_iovec __user *, vec,
+ unsigned long, vlen)
+{
+ struct fd f = fdget(fd);
+ ssize_t ret;
+ loff_t pos;
+
+ if (!f.file)
+ return -EBADF;
+ pos = f.file->f_pos;
+ ret = compat_writev(f.file, vec, vlen, &pos);
+ if (ret >= 0)
+ f.file->f_pos = pos;
+ fdput(f);
+ return ret;
+}
+
+COMPAT_SYSCALL_DEFINE4(pwritev64, unsigned long, fd,
+ const struct compat_iovec __user *,vec,
+ unsigned long, vlen, loff_t, pos)
+{
+ struct fd f;
+ ssize_t ret;
+
+ if (pos < 0)
+ return -EINVAL;
+ f = fdget(fd);
+ if (!f.file)
+ return -EBADF;
+ ret = -ESPIPE;
+ if (f.file->f_mode & FMODE_PWRITE)
+ ret = compat_writev(f.file, vec, vlen, &pos);
+ fdput(f);
+ return ret;
+}
+
+COMPAT_SYSCALL_DEFINE5(pwritev, unsigned long, fd,
+ const struct compat_iovec __user *,vec,
+ unsigned long, vlen, u32, pos_low, u32, pos_high)
+{
+ loff_t pos = ((loff_t)pos_high << 32) | pos_low;
+ return compat_sys_pwritev64(fd, vec, vlen, pos);
+}
+#endif
+
static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos,
- size_t count, loff_t max)
+ size_t count, loff_t max)
{
- struct file * in_file, * out_file;
- struct inode * in_inode, * out_inode;
+ struct fd in, out;
+ struct inode *in_inode, *out_inode;
loff_t pos;
+ loff_t out_pos;
ssize_t retval;
- int fput_needed_in, fput_needed_out, fl;
+ int fl;
/*
* Get input file, and verify that it is ok..
*/
retval = -EBADF;
- in_file = fget_light(in_fd, &fput_needed_in);
- if (!in_file)
+ in = fdget(in_fd);
+ if (!in.file)
goto out;
- if (!(in_file->f_mode & FMODE_READ))
+ if (!(in.file->f_mode & FMODE_READ))
goto fput_in;
retval = -ESPIPE;
- if (!ppos)
- ppos = &in_file->f_pos;
- else
- if (!(in_file->f_mode & FMODE_PREAD))
+ if (!ppos) {
+ pos = in.file->f_pos;
+ } else {
+ pos = *ppos;
+ if (!(in.file->f_mode & FMODE_PREAD))
goto fput_in;
- retval = rw_verify_area(READ, in_file, ppos, count);
+ }
+ retval = rw_verify_area(READ, in.file, &pos, count);
if (retval < 0)
goto fput_in;
count = retval;
@@ -915,15 +1129,16 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos,
* Get output file, and verify that it is ok..
*/
retval = -EBADF;
- out_file = fget_light(out_fd, &fput_needed_out);
- if (!out_file)
+ out = fdget(out_fd);
+ if (!out.file)
goto fput_in;
- if (!(out_file->f_mode & FMODE_WRITE))
+ if (!(out.file->f_mode & FMODE_WRITE))
goto fput_out;
retval = -EINVAL;
- in_inode = in_file->f_path.dentry->d_inode;
- out_inode = out_file->f_path.dentry->d_inode;
- retval = rw_verify_area(WRITE, out_file, &out_file->f_pos, count);
+ in_inode = file_inode(in.file);
+ out_inode = file_inode(out.file);
+ out_pos = out.file->f_pos;
+ retval = rw_verify_area(WRITE, out.file, &out_pos, count);
if (retval < 0)
goto fput_out;
count = retval;
@@ -931,7 +1146,6 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos,
if (!max)
max = min(in_inode->i_sb->s_maxbytes, out_inode->i_sb->s_maxbytes);
- pos = *ppos;
if (unlikely(pos + count > max)) {
retval = -EOVERFLOW;
if (pos >= max)
@@ -947,25 +1161,34 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos,
* and the application is arguably buggy if it doesn't expect
* EAGAIN on a non-blocking file descriptor.
*/
- if (in_file->f_flags & O_NONBLOCK)
+ if (in.file->f_flags & O_NONBLOCK)
fl = SPLICE_F_NONBLOCK;
#endif
- retval = do_splice_direct(in_file, ppos, out_file, count, fl);
+ file_start_write(out.file);
+ retval = do_splice_direct(in.file, &pos, out.file, &out_pos, count, fl);
+ file_end_write(out.file);
if (retval > 0) {
add_rchar(current, retval);
add_wchar(current, retval);
+ fsnotify_access(in.file);
+ fsnotify_modify(out.file);
+ out.file->f_pos = out_pos;
+ if (ppos)
+ *ppos = pos;
+ else
+ in.file->f_pos = pos;
}
inc_syscr(current);
inc_syscw(current);
- if (*ppos > max)
+ if (pos > max)
retval = -EOVERFLOW;
fput_out:
- fput_light(out_file, fput_needed_out);
+ fdput(out);
fput_in:
- fput_light(in_file, fput_needed_in);
+ fdput(in);
out:
return retval;
}
@@ -1005,3 +1228,43 @@ SYSCALL_DEFINE4(sendfile64, int, out_fd, int, in_fd, loff_t __user *, offset, si
return do_sendfile(out_fd, in_fd, NULL, count, 0);
}
+
+#ifdef CONFIG_COMPAT
+COMPAT_SYSCALL_DEFINE4(sendfile, int, out_fd, int, in_fd,
+ compat_off_t __user *, offset, compat_size_t, count)
+{
+ loff_t pos;
+ off_t off;
+ ssize_t ret;
+
+ if (offset) {
+ if (unlikely(get_user(off, offset)))
+ return -EFAULT;
+ pos = off;
+ ret = do_sendfile(out_fd, in_fd, &pos, count, MAX_NON_LFS);
+ if (unlikely(put_user(pos, offset)))
+ return -EFAULT;
+ return ret;
+ }
+
+ return do_sendfile(out_fd, in_fd, NULL, count, 0);
+}
+
+COMPAT_SYSCALL_DEFINE4(sendfile64, int, out_fd, int, in_fd,
+ compat_loff_t __user *, offset, compat_size_t, count)
+{
+ loff_t pos;
+ ssize_t ret;
+
+ if (offset) {
+ if (unlikely(copy_from_user(&pos, offset, sizeof(loff_t))))
+ return -EFAULT;
+ ret = do_sendfile(out_fd, in_fd, &pos, count, 0);
+ if (unlikely(put_user(pos, offset)))
+ return -EFAULT;
+ return ret;
+ }
+
+ return do_sendfile(out_fd, in_fd, NULL, count, 0);
+}
+#endif