#include <linux/file.h>
#include <linux/uio.h>
#include <linux/smp_lock.h>
-#include <linux/dnotify.h>
+#include <linux/fsnotify.h>
#include <linux/security.h>
#include <linux/module.h>
#include <linux/syscalls.h>
+#include <linux/pagemap.h>
+#include "read_write.h"
#include <asm/uaccess.h>
#include <asm/unistd.h>
-struct file_operations generic_ro_fops = {
+const struct file_operations generic_ro_fops = {
.llseek = generic_file_llseek,
- .read = generic_file_read,
+ .read = do_sync_read,
+ .aio_read = generic_file_aio_read,
.mmap = generic_file_readonly_mmap,
.sendfile = generic_file_sendfile,
};
long long retval;
struct inode *inode = file->f_mapping->host;
- down(&inode->i_sem);
+ mutex_lock(&inode->i_mutex);
switch (origin) {
case 2:
offset += inode->i_size;
}
retval = offset;
}
- up(&inode->i_sem);
+ mutex_unlock(&inode->i_mutex);
return retval;
}
lock_kernel();
switch (origin) {
case 2:
- offset += i_size_read(file->f_dentry->d_inode);
+ offset += i_size_read(file->f_path.dentry->d_inode);
break;
case 1:
offset += file->f_pos;
}
retval = -EINVAL;
- if (offset>=0 && offset<=file->f_dentry->d_inode->i_sb->s_maxbytes) {
+ if (offset>=0 && offset<=file->f_path.dentry->d_inode->i_sb->s_maxbytes) {
if (offset != file->f_pos) {
file->f_pos = offset;
file->f_version = 0;
lock_kernel();
switch (origin) {
case 2:
- offset += i_size_read(file->f_dentry->d_inode);
+ offset += i_size_read(file->f_path.dentry->d_inode);
break;
case 1:
offset += file->f_pos;
}
#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.
+ */
+#define MAX_RW_COUNT (INT_MAX & PAGE_CACHE_MASK)
int rw_verify_area(int read_write, struct file *file, loff_t *ppos, size_t count)
{
struct inode *inode;
loff_t pos;
- if (unlikely(count > file->f_maxcount))
+ if (unlikely((ssize_t) count < 0))
goto Einval;
pos = *ppos;
if (unlikely((pos < 0) || (loff_t) (pos + count) < 0))
goto Einval;
- inode = file->f_dentry->d_inode;
- if (inode->i_flock && MANDATORY_LOCK(inode))
- return locks_mandatory_area(read_write == READ ? FLOCK_VERIFY_READ : FLOCK_VERIFY_WRITE, inode, file, pos, count);
- return 0;
+ inode = file->f_path.dentry->d_inode;
+ if (unlikely(inode->i_flock && MANDATORY_LOCK(inode))) {
+ int retval = locks_mandatory_area(
+ read_write == READ ? FLOCK_VERIFY_READ : FLOCK_VERIFY_WRITE,
+ inode, file, pos, count);
+ if (retval < 0)
+ return retval;
+ }
+ return count > MAX_RW_COUNT ? MAX_RW_COUNT : count;
Einval:
return -EINVAL;
}
+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 };
struct kiocb kiocb;
ssize_t ret;
init_sync_kiocb(&kiocb, filp);
kiocb.ki_pos = *ppos;
- ret = filp->f_op->aio_read(&kiocb, buf, len, kiocb.ki_pos);
+ kiocb.ki_left = len;
+
+ for (;;) {
+ ret = filp->f_op->aio_read(&kiocb, &iov, 1, kiocb.ki_pos);
+ if (ret != -EIOCBRETRY)
+ break;
+ wait_on_retry_sync_kiocb(&kiocb);
+ }
+
if (-EIOCBQUEUED == ret)
ret = wait_on_sync_kiocb(&kiocb);
*ppos = kiocb.ki_pos;
return -EFAULT;
ret = rw_verify_area(READ, file, pos, count);
- if (!ret) {
+ if (ret >= 0) {
+ count = ret;
ret = security_file_permission (file, MAY_READ);
if (!ret) {
if (file->f_op->read)
else
ret = do_sync_read(file, buf, count, pos);
if (ret > 0) {
- dnotify_parent(file->f_dentry, DN_ACCESS);
+ fsnotify_access(file->f_path.dentry);
current->rchar += ret;
}
current->syscr++;
ssize_t do_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos)
{
+ struct iovec iov = { .iov_base = (void __user *)buf, .iov_len = len };
struct kiocb kiocb;
ssize_t ret;
init_sync_kiocb(&kiocb, filp);
kiocb.ki_pos = *ppos;
- ret = filp->f_op->aio_write(&kiocb, buf, len, kiocb.ki_pos);
+ kiocb.ki_left = len;
+
+ for (;;) {
+ ret = filp->f_op->aio_write(&kiocb, &iov, 1, kiocb.ki_pos);
+ if (ret != -EIOCBRETRY)
+ break;
+ wait_on_retry_sync_kiocb(&kiocb);
+ }
+
if (-EIOCBQUEUED == ret)
ret = wait_on_sync_kiocb(&kiocb);
*ppos = kiocb.ki_pos;
return -EFAULT;
ret = rw_verify_area(WRITE, file, pos, count);
- if (!ret) {
+ if (ret >= 0) {
+ count = ret;
ret = security_file_permission (file, MAY_WRITE);
if (!ret) {
if (file->f_op->write)
else
ret = do_sync_write(file, buf, count, pos);
if (ret > 0) {
- dnotify_parent(file->f_dentry, DN_MODIFY);
+ fsnotify_modify(file->f_path.dentry);
current->wchar += ret;
}
current->syscw++;
return ret;
}
-EXPORT_SYMBOL_GPL(sys_write);
-
asmlinkage ssize_t sys_pread64(unsigned int fd, char __user *buf,
size_t count, loff_t pos)
{
return seg;
}
-EXPORT_SYMBOL(iov_shorten);
+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;
+ ssize_t ret;
+
+ init_sync_kiocb(&kiocb, filp);
+ kiocb.ki_pos = *ppos;
+ 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);
+ }
+
+ if (ret == -EIOCBQUEUED)
+ ret = wait_on_sync_kiocb(&kiocb);
+ *ppos = kiocb.ki_pos;
+ return ret;
+}
+
+/* Do it by hand, with file-ops */
+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;
+ ssize_t ret = 0;
+
+ while (nr_segs > 0) {
+ void __user *base;
+ size_t len;
+ ssize_t nr;
+
+ base = vector->iov_base;
+ len = vector->iov_len;
+ vector++;
+ nr_segs--;
+
+ nr = fn(filp, base, len, ppos);
+
+ if (nr < 0) {
+ if (!ret)
+ ret = nr;
+ break;
+ }
+ ret += nr;
+ if (nr != len)
+ break;
+ }
+
+ return ret;
+}
/* A write operation does a read from user space and vice versa */
#define vrfy_dir(type) ((type) == READ ? VERIFY_WRITE : VERIFY_READ)
+ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector,
+ unsigned long nr_segs, unsigned long fast_segs,
+ struct iovec *fast_pointer,
+ struct iovec **ret_pointer)
+ {
+ unsigned long seg;
+ ssize_t ret;
+ struct iovec *iov = fast_pointer;
+
+ /*
+ * SuS says "The readv() function *may* fail if the iovcnt argument
+ * was less than or equal to 0, or greater than {IOV_MAX}. Linux has
+ * traditionally returned zero for zero segments, so...
+ */
+ if (nr_segs == 0) {
+ ret = 0;
+ goto out;
+ }
+
+ /*
+ * First get the "struct iovec" from user memory and
+ * verify all the pointers
+ */
+ if (nr_segs > UIO_MAXIOV) {
+ ret = -EINVAL;
+ goto out;
+ }
+ if (nr_segs > fast_segs) {
+ iov = kmalloc(nr_segs*sizeof(struct iovec), GFP_KERNEL);
+ if (iov == NULL) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ }
+ if (copy_from_user(iov, uvector, nr_segs*sizeof(*uvector))) {
+ ret = -EFAULT;
+ goto out;
+ }
+
+ /*
+ * According to the Single Unix Specification we should return EINVAL
+ * if an element length is < 0 when cast to ssize_t or if the
+ * total length would overflow the ssize_t return value of the
+ * system call.
+ */
+ ret = 0;
+ for (seg = 0; seg < nr_segs; seg++) {
+ void __user *buf = iov[seg].iov_base;
+ ssize_t len = (ssize_t)iov[seg].iov_len;
+
+ /* see if we we're about to use an invalid len or if
+ * it's about to overflow ssize_t */
+ if (len < 0 || (ret + len < ret)) {
+ ret = -EINVAL;
+ goto out;
+ }
+ if (unlikely(!access_ok(vrfy_dir(type), buf, len))) {
+ ret = -EFAULT;
+ goto out;
+ }
+
+ ret += len;
+ }
+out:
+ *ret_pointer = iov;
+ return ret;
+}
+
static ssize_t do_readv_writev(int type, struct file *file,
const struct iovec __user * uvector,
unsigned long nr_segs, loff_t *pos)
{
- typedef ssize_t (*io_fn_t)(struct file *, char __user *, size_t, loff_t *);
- typedef ssize_t (*iov_fn_t)(struct file *, const struct iovec *, unsigned long, loff_t *);
-
size_t tot_len;
struct iovec iovstack[UIO_FASTIOV];
- struct iovec *iov=iovstack, *vector;
+ struct iovec *iov = iovstack;
ssize_t ret;
- int seg;
io_fn_t fn;
iov_fn_t fnv;
- /*
- * SuS says "The readv() function *may* fail if the iovcnt argument
- * was less than or equal to 0, or greater than {IOV_MAX}. Linux has
- * traditionally returned zero for zero segments, so...
- */
- ret = 0;
- if (nr_segs == 0)
- goto out;
-
- /*
- * First get the "struct iovec" from user memory and
- * verify all the pointers
- */
- ret = -EINVAL;
- if ((nr_segs > UIO_MAXIOV) || (nr_segs <= 0))
- goto out;
- if (!file->f_op)
- goto out;
- if (nr_segs > UIO_FASTIOV) {
- ret = -ENOMEM;
- iov = kmalloc(nr_segs*sizeof(struct iovec), GFP_KERNEL);
- if (!iov)
- goto out;
- }
- ret = -EFAULT;
- if (copy_from_user(iov, uvector, nr_segs*sizeof(*uvector)))
+ if (!file->f_op) {
+ ret = -EINVAL;
goto out;
+ }
- /*
- * Single unix specification:
- * We should -EINVAL if an element length is not >= 0 and fitting an
- * ssize_t. The total length is fitting an ssize_t
- *
- * Be careful here because iov_len is a size_t not an ssize_t
- */
- tot_len = 0;
- ret = -EINVAL;
- for (seg = 0; seg < nr_segs; seg++) {
- void __user *buf = iov[seg].iov_base;
- ssize_t len = (ssize_t)iov[seg].iov_len;
-
- if (len < 0) /* size_t not fitting an ssize_t .. */
- goto out;
- if (unlikely(!access_ok(vrfy_dir(type), buf, len)))
- goto Efault;
- tot_len += len;
- if ((ssize_t)tot_len < 0) /* maths overflow on the ssize_t */
- goto out;
- }
- if (tot_len == 0) {
- ret = 0;
+ ret = rw_copy_check_uvector(type, uvector, nr_segs,
+ ARRAY_SIZE(iovstack), iovstack, &iov);
+ if (ret <= 0)
goto out;
- }
+ tot_len = ret;
ret = rw_verify_area(type, file, pos, tot_len);
+ if (ret < 0)
+ goto out;
+ ret = security_file_permission(file, type == READ ? MAY_READ : MAY_WRITE);
if (ret)
goto out;
fnv = NULL;
if (type == READ) {
fn = file->f_op->read;
- fnv = file->f_op->readv;
+ fnv = file->f_op->aio_read;
} else {
fn = (io_fn_t)file->f_op->write;
- fnv = file->f_op->writev;
- }
- if (fnv) {
- ret = fnv(file, iov, nr_segs, pos);
- goto out;
+ fnv = file->f_op->aio_write;
}
- /* Do it by hand, with file-ops */
- ret = 0;
- vector = iov;
- while (nr_segs > 0) {
- void __user * base;
- size_t len;
- ssize_t nr;
-
- base = vector->iov_base;
- len = vector->iov_len;
- vector++;
- nr_segs--;
-
- nr = fn(file, base, len, pos);
+ 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 (nr < 0) {
- if (!ret) ret = nr;
- break;
- }
- ret += nr;
- if (nr != len)
- break;
- }
out:
if (iov != iovstack)
kfree(iov);
- if ((ret + (type == READ)) > 0)
- dnotify_parent(file->f_dentry,
- (type == READ) ? DN_ACCESS : DN_MODIFY);
+ if ((ret + (type == READ)) > 0) {
+ if (type == READ)
+ fsnotify_access(file->f_path.dentry);
+ else
+ fsnotify_modify(file->f_path.dentry);
+ }
return ret;
-Efault:
- ret = -EFAULT;
- goto out;
}
ssize_t vfs_readv(struct file *file, const struct iovec __user *vec,
{
if (!(file->f_mode & FMODE_READ))
return -EBADF;
- if (!file->f_op || (!file->f_op->readv && !file->f_op->read))
+ if (!file->f_op || (!file->f_op->aio_read && !file->f_op->read))
return -EINVAL;
return do_readv_writev(READ, file, vec, vlen, pos);
{
if (!(file->f_mode & FMODE_WRITE))
return -EBADF;
- if (!file->f_op || (!file->f_op->writev && !file->f_op->write))
+ if (!file->f_op || (!file->f_op->aio_write && !file->f_op->write))
return -EINVAL;
return do_readv_writev(WRITE, file, vec, vlen, pos);
return ret;
}
+ssize_t vfs_sendfile(struct file *out_file, struct file *in_file, loff_t *ppos,
+ size_t count, loff_t max)
+{
+ struct inode * in_inode, * out_inode;
+ loff_t pos;
+ ssize_t ret;
+
+ /* verify in_file */
+ in_inode = in_file->f_path.dentry->d_inode;
+ if (!in_inode)
+ return -EINVAL;
+ if (!in_file->f_op || !in_file->f_op->sendfile)
+ return -EINVAL;
+
+ if (!ppos)
+ ppos = &in_file->f_pos;
+ else
+ if (!(in_file->f_mode & FMODE_PREAD))
+ return -ESPIPE;
+
+ ret = rw_verify_area(READ, in_file, ppos, count);
+ if (ret < 0)
+ return ret;
+ count = ret;
+
+ /* verify out_file */
+ out_inode = out_file->f_path.dentry->d_inode;
+ if (!out_inode)
+ return -EINVAL;
+ if (!out_file->f_op || !out_file->f_op->sendpage)
+ return -EINVAL;
+
+ ret = rw_verify_area(WRITE, out_file, &out_file->f_pos, count);
+ if (ret < 0)
+ return ret;
+ count = ret;
+
+ ret = security_file_permission (out_file, MAY_WRITE);
+ if (ret)
+ return ret;
+
+ if (!max)
+ max = min(in_inode->i_sb->s_maxbytes, out_inode->i_sb->s_maxbytes);
+
+ pos = *ppos;
+ if (unlikely(pos < 0))
+ return -EINVAL;
+ if (unlikely(pos + count > max)) {
+ if (pos >= max)
+ return -EOVERFLOW;
+ count = max - pos;
+ }
+
+ ret = in_file->f_op->sendfile(in_file, ppos, count, file_send_actor, out_file);
+
+ if (ret > 0) {
+ current->rchar += ret;
+ current->wchar += ret;
+ }
+
+ if (*ppos > max)
+ return -EOVERFLOW;
+ return ret;
+}
+
+EXPORT_SYMBOL(vfs_sendfile);
+
static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos,
size_t count, loff_t max)
{
struct file * in_file, * out_file;
- struct inode * in_inode, * out_inode;
- loff_t pos;
ssize_t retval;
int fput_needed_in, fput_needed_out;
goto out;
if (!(in_file->f_mode & FMODE_READ))
goto fput_in;
- retval = -EINVAL;
- in_inode = in_file->f_dentry->d_inode;
- if (!in_inode)
- goto fput_in;
- if (!in_file->f_op || !in_file->f_op->sendfile)
- goto fput_in;
- retval = -ESPIPE;
- if (!ppos)
- ppos = &in_file->f_pos;
- else
- if (!(in_file->f_mode & FMODE_PREAD))
- goto fput_in;
- retval = rw_verify_area(READ, in_file, ppos, count);
- if (retval)
- goto fput_in;
retval = security_file_permission (in_file, MAY_READ);
if (retval)
goto fput_in;
if (!(out_file->f_mode & FMODE_WRITE))
goto fput_out;
- retval = -EINVAL;
- if (!out_file->f_op || !out_file->f_op->sendpage)
- goto fput_out;
- out_inode = out_file->f_dentry->d_inode;
- retval = rw_verify_area(WRITE, out_file, &out_file->f_pos, count);
- if (retval)
- goto fput_out;
-
- retval = security_file_permission (out_file, MAY_WRITE);
- if (retval)
- goto fput_out;
- if (!max)
- max = min(in_inode->i_sb->s_maxbytes, out_inode->i_sb->s_maxbytes);
+ retval = vfs_sendfile(out_file, in_file, ppos, count, max);
- pos = *ppos;
- retval = -EINVAL;
- if (unlikely(pos < 0))
- goto fput_out;
- if (unlikely(pos + count > max)) {
- retval = -EOVERFLOW;
- if (pos >= max)
- goto fput_out;
- count = max - pos;
- }
-
- retval = in_file->f_op->sendfile(in_file, ppos, count, file_send_actor, out_file);
-
- if (retval > 0) {
- current->rchar += retval;
- current->wchar += retval;
- }
current->syscr++;
current->syscw++;
- if (*ppos > max)
- retval = -EOVERFLOW;
-
fput_out:
fput_light(out_file, fput_needed_out);
fput_in: