static ssize_t
HgfsAioRead(struct kiocb *iocb, // IN: I/O control block
const struct iovec *iov, // OUT: Array of I/O buffers
unsigned long numSegs, // IN: Number of buffers
loff_t offset) // IN: Offset at which to read
{
int result;
ASSERT(iocb);
ASSERT(iocb->ki_filp);
ASSERT(iocb->ki_filp->f_dentry);
ASSERT(iov);
LOG(6, (KERN_DEBUG "VMware hgfs: HgfsAioRead: was called\n"));
result = HgfsRevalidate(iocb->ki_filp->f_dentry);
if (result) {
LOG(4, (KERN_DEBUG "VMware hgfs: HgfsAioRead: invalid dentry\n"));
goto out;
}
result = generic_file_aio_read(iocb, iov, numSegs, offset);
out:
return result;
}
static ssize_t
smb_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
unsigned long nr_segs, loff_t pos)
{
struct file * file = iocb->ki_filp;
struct dentry * dentry = file->f_path.dentry;
ssize_t status;
VERBOSE("file %s/%s, count=%lu@%lu\n", DENTRY_PATH(dentry),
(unsigned long) iocb->ki_left, (unsigned long) pos);
status = smb_revalidate_inode(dentry);
if (status) {
PARANOIA("%s/%s validation failed, error=%Zd\n",
DENTRY_PATH(dentry), status);
goto out;
}
VERBOSE("before read, size=%ld, flags=%x, atime=%ld\n",
(long)dentry->d_inode->i_size,
dentry->d_inode->i_flags, dentry->d_inode->i_atime.tv_sec);
status = generic_file_aio_read(iocb, iov, nr_segs, pos);
out:
return status;
}
ssize_t testfs_aio_read(struct kiocb *iocb, const struct iovec *iov, unsigned long nr_segs, loff_t pos)
{
int ret = 0;
printk(KERN_INFO "testfs: testfs_aio_read\n");
ret = generic_file_aio_read(iocb, iov, nr_segs, pos);
return ret;
}
ssize_t
xixfs_file_aio_read(
struct kiocb *iocb,
#if LINUX_VERSION_2_6_19_REPLACE_INTERFACE
const struct iovec *iov,
unsigned long count,
#else
char __user *buf,
size_t count,
#endif
loff_t pos
)
{
struct address_space *mapping = iocb->ki_filp->f_mapping;
struct inode *inode = mapping->host;
PXIXFS_LINUX_FCB pFCB = NULL;
ssize_t ret = 0;
XIXCORE_ASSERT(inode);
pFCB = XIXFS_I(inode);
XIXFS_ASSERT_FCB(pFCB);
if(XIXCORE_TEST_FLAGS( pFCB->XixcoreFcb.FCBFlags, XIXCORE_FCB_CHANGE_DELETED )){
DebugTrace(DEBUG_LEVEL_ERROR, DEBUG_TARGET_ALL,
("ERROR DELETED FILE \n"));
//printk(KERN_DEBUG "xixfs_file_aio_read ERROR\n");
return -EPERM;
}
DebugTrace(DEBUG_LEVEL_ERROR, (DEBUG_TARGET_FCB|DEBUG_TARGET_VFSAPIT),
("ENTER xixfs_file_aio_read .\n"));
#if LINUX_VERSION_2_6_19_REPLACE_INTERFACE
ret = generic_file_aio_read(iocb, iov, count, pos);
#else
ret = generic_file_aio_read(iocb, buf, count, pos);
#endif
//printk(KERN_DEBUG "xixfs_file_aio_read ret (0x%x)\n", ret);
return ret;
}
ssize_t my_aio_read(struct kiocb *iocb, const struct iovec *iov, unsigned long nr_segs, loff_t pos) {
ssize_t r;
printk("OSDI: custom read\n");
r = generic_file_aio_read(iocb, iov, nr_segs, pos);
if(ramfs_flag) {
size_t i;
char *ib = (char *)iov->iov_base;
for( i=0 ; i<iov->iov_len ; i++ ) ib[i] ^= ENCODE_KEY;
printk("ramfs_flag is up\n");
}
return r;
}
/**
* ecryptfs_read_update_atime
*
* generic_file_read updates the atime of upper layer inode. But, it
* doesn't give us a chance to update the atime of the lower layer
* inode. This function is a wrapper to generic_file_read. It
* updates the atime of the lower level inode if generic_file_read
* returns without any errors. This is to be used only for file reads.
* The function to be used for directory reads is ecryptfs_read.
*/
static ssize_t ecryptfs_read_update_atime(struct kiocb *iocb,
const struct iovec *iov,
unsigned long nr_segs, loff_t pos)
{
ssize_t rc;
struct path *path;
struct file *file = iocb->ki_filp;
rc = generic_file_aio_read(iocb, iov, nr_segs, pos);
/*
* Even though this is a async interface, we need to wait
* for IO to finish to update atime
*/
if (-EIOCBQUEUED == rc)
rc = wait_on_sync_kiocb(iocb);
if (rc >= 0) {
path = ecryptfs_dentry_to_lower_path(file->f_path.dentry);
touch_atime(path);
}
return rc;
}
static ssize_t
nfs_file_read(struct kiocb *iocb, char __user * buf, size_t count, loff_t pos)
{
struct dentry * dentry = iocb->ki_filp->f_dentry;
struct inode * inode = dentry->d_inode;
ssize_t result;
#ifdef CONFIG_NFS_DIRECTIO
if (iocb->ki_filp->f_flags & O_DIRECT)
return nfs_file_direct_read(iocb, buf, count, pos);
#endif
dfprintk(VFS, "nfs: read(%s/%s, %lu@%lu)\n",
dentry->d_parent->d_name.name, dentry->d_name.name,
(unsigned long) count, (unsigned long) pos);
result = nfs_revalidate_file(inode, iocb->ki_filp);
if (!result)
result = generic_file_aio_read(iocb, buf, count, pos);
return result;
}
static ssize_t
nfs_file_read(struct kiocb *iocb, const struct iovec *iov,
unsigned long nr_segs, loff_t pos)
{
struct dentry * dentry = iocb->ki_filp->f_path.dentry;
struct inode * inode = dentry->d_inode;
ssize_t result;
size_t count = iov_length(iov, nr_segs);
if (iocb->ki_filp->f_flags & O_DIRECT)
return nfs_file_direct_read(iocb, iov, nr_segs, pos);
dprintk("NFS: read(%s/%s, %lu@%lu)\n",
dentry->d_parent->d_name.name, dentry->d_name.name,
(unsigned long) count, (unsigned long) pos);
result = nfs_revalidate_mapping(inode, iocb->ki_filp->f_mapping);
nfs_add_stats(inode, NFSIOS_NORMALREADBYTES, count);
if (!result)
result = generic_file_aio_read(iocb, iov, nr_segs, pos);
return result;
}
STATIC ssize_t
xfs_file_aio_read(
struct kiocb *iocb,
const struct iovec *iovp,
unsigned long nr_segs,
loff_t pos)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
size_t size = 0;
ssize_t ret = 0;
int ioflags = 0;
xfs_fsize_t n;
XFS_STATS_INC(xs_read_calls);
BUG_ON(iocb->ki_pos != pos);
if (unlikely(file->f_flags & O_DIRECT))
ioflags |= IO_ISDIRECT;
if (file->f_mode & FMODE_NOCMTIME)
ioflags |= IO_INVIS;
ret = generic_segment_checks(iovp, &nr_segs, &size, VERIFY_WRITE);
if (ret < 0)
return ret;
if (unlikely(ioflags & IO_ISDIRECT)) {
xfs_buftarg_t *target =
XFS_IS_REALTIME_INODE(ip) ?
mp->m_rtdev_targp : mp->m_ddev_targp;
if ((iocb->ki_pos & target->bt_smask) ||
(size & target->bt_smask)) {
if (iocb->ki_pos == i_size_read(inode))
return 0;
return -XFS_ERROR(EINVAL);
}
}
n = mp->m_super->s_maxbytes - iocb->ki_pos;
if (n <= 0 || size == 0)
return 0;
if (n < size)
size = n;
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
/*
* Locking is a bit tricky here. If we take an exclusive lock
* for direct IO, we effectively serialise all new concurrent
* read IO to this file and block it behind IO that is currently in
* progress because IO in progress holds the IO lock shared. We only
* need to hold the lock exclusive to blow away the page cache, so
* only take lock exclusively if the page cache needs invalidation.
* This allows the normal direct IO case of no page cache pages to
* proceeed concurrently without serialisation.
*/
xfs_rw_ilock(ip, XFS_IOLOCK_SHARED);
if ((ioflags & IO_ISDIRECT) && inode->i_mapping->nrpages) {
xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
xfs_rw_ilock(ip, XFS_IOLOCK_EXCL);
if (inode->i_mapping->nrpages) {
ret = -xfs_flushinval_pages(ip,
(iocb->ki_pos & PAGE_CACHE_MASK),
-1, FI_REMAPF_LOCKED);
if (ret) {
xfs_rw_iunlock(ip, XFS_IOLOCK_EXCL);
return ret;
}
}
xfs_rw_ilock_demote(ip, XFS_IOLOCK_EXCL);
}
trace_xfs_file_read(ip, size, iocb->ki_pos, ioflags);
ret = generic_file_aio_read(iocb, iovp, nr_segs, iocb->ki_pos);
if (ret > 0)
XFS_STATS_ADD(xs_read_bytes, ret);
xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
return ret;
}
STATIC ssize_t
xfs_file_aio_read(
struct kiocb *iocb,
const struct iovec *iovp,
unsigned long nr_segs,
loff_t pos)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
size_t size = 0;
ssize_t ret = 0;
int ioflags = 0;
xfs_fsize_t n;
unsigned long seg;
XFS_STATS_INC(xs_read_calls);
BUG_ON(iocb->ki_pos != pos);
if (unlikely(file->f_flags & O_DIRECT))
ioflags |= IO_ISDIRECT;
if (file->f_mode & FMODE_NOCMTIME)
ioflags |= IO_INVIS;
/* START copy & waste from filemap.c */
for (seg = 0; seg < nr_segs; seg++) {
const struct iovec *iv = &iovp[seg];
/*
* If any segment has a negative length, or the cumulative
* length ever wraps negative then return -EINVAL.
*/
size += iv->iov_len;
if (unlikely((ssize_t)(size|iv->iov_len) < 0))
return XFS_ERROR(-EINVAL);
}
/* END copy & waste from filemap.c */
if (unlikely(ioflags & IO_ISDIRECT)) {
xfs_buftarg_t *target =
XFS_IS_REALTIME_INODE(ip) ?
mp->m_rtdev_targp : mp->m_ddev_targp;
if ((iocb->ki_pos & target->bt_smask) ||
(size & target->bt_smask)) {
if (iocb->ki_pos == ip->i_size)
return 0;
return -XFS_ERROR(EINVAL);
}
}
n = XFS_MAXIOFFSET(mp) - iocb->ki_pos;
if (n <= 0 || size == 0)
return 0;
if (n < size)
size = n;
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
if (unlikely(ioflags & IO_ISDIRECT))
mutex_lock(&inode->i_mutex);
xfs_ilock(ip, XFS_IOLOCK_SHARED);
if (DM_EVENT_ENABLED(ip, DM_EVENT_READ) && !(ioflags & IO_INVIS)) {
int dmflags = FILP_DELAY_FLAG(file) | DM_SEM_FLAG_RD(ioflags);
int iolock = XFS_IOLOCK_SHARED;
ret = -XFS_SEND_DATA(mp, DM_EVENT_READ, ip, iocb->ki_pos, size,
dmflags, &iolock);
if (ret) {
xfs_iunlock(ip, XFS_IOLOCK_SHARED);
if (unlikely(ioflags & IO_ISDIRECT))
mutex_unlock(&inode->i_mutex);
return ret;
}
}
if (unlikely(ioflags & IO_ISDIRECT)) {
if (inode->i_mapping->nrpages) {
ret = -xfs_flushinval_pages(ip,
(iocb->ki_pos & PAGE_CACHE_MASK),
-1, FI_REMAPF_LOCKED);
}
mutex_unlock(&inode->i_mutex);
if (ret) {
xfs_iunlock(ip, XFS_IOLOCK_SHARED);
return ret;
}
}
trace_xfs_file_read(ip, size, iocb->ki_pos, ioflags);
ret = generic_file_aio_read(iocb, iovp, nr_segs, iocb->ki_pos);
if (ret > 0)
XFS_STATS_ADD(xs_read_bytes, ret);
xfs_iunlock(ip, XFS_IOLOCK_SHARED);
return ret;
}
static ssize_t lustre_generic_file_read(struct file *file,
struct ccc_io *vio, loff_t *ppos)
{
return generic_file_aio_read(vio->cui_iocb, vio->cui_iov,
vio->cui_nrsegs, *ppos);
}
STATIC ssize_t
xfs_file_aio_read(
struct kiocb *iocb,
const struct iovec *iovp,
unsigned long nr_segs,
loff_t pos)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
size_t size = 0;
ssize_t ret = 0;
int ioflags = 0;
xfs_fsize_t n;
unsigned long seg;
XFS_STATS_INC(xs_read_calls);
BUG_ON(iocb->ki_pos != pos);
if (unlikely(file->f_flags & O_DIRECT))
ioflags |= IO_ISDIRECT;
if (file->f_mode & FMODE_NOCMTIME)
ioflags |= IO_INVIS;
for (seg = 0; seg < nr_segs; seg++) {
const struct iovec *iv = &iovp[seg];
size += iv->iov_len;
if (unlikely((ssize_t)(size|iv->iov_len) < 0))
return XFS_ERROR(-EINVAL);
}
if (unlikely(ioflags & IO_ISDIRECT)) {
xfs_buftarg_t *target =
XFS_IS_REALTIME_INODE(ip) ?
mp->m_rtdev_targp : mp->m_ddev_targp;
if ((iocb->ki_pos & target->bt_smask) ||
(size & target->bt_smask)) {
if (iocb->ki_pos == i_size_read(inode))
return 0;
return -XFS_ERROR(EINVAL);
}
}
n = XFS_MAXIOFFSET(mp) - iocb->ki_pos;
if (n <= 0 || size == 0)
return 0;
if (n < size)
size = n;
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
xfs_rw_ilock(ip, XFS_IOLOCK_SHARED);
if ((ioflags & IO_ISDIRECT) && inode->i_mapping->nrpages) {
xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
xfs_rw_ilock(ip, XFS_IOLOCK_EXCL);
if (inode->i_mapping->nrpages) {
ret = -xfs_flushinval_pages(ip,
(iocb->ki_pos & PAGE_CACHE_MASK),
-1, FI_REMAPF_LOCKED);
if (ret) {
xfs_rw_iunlock(ip, XFS_IOLOCK_EXCL);
return ret;
}
}
xfs_rw_ilock_demote(ip, XFS_IOLOCK_EXCL);
}
trace_xfs_file_read(ip, size, iocb->ki_pos, ioflags);
ret = generic_file_aio_read(iocb, iovp, nr_segs, iocb->ki_pos);
if (ret > 0)
XFS_STATS_ADD(xs_read_bytes, ret);
xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
return ret;
}
static ssize_t ocfs2_file_aio_read(struct kiocb *iocb,
const struct iovec *iov,
unsigned long nr_segs,
loff_t pos)
{
int ret = 0, rw_level = -1, have_alloc_sem = 0, lock_level = 0;
struct file *filp = iocb->ki_filp;
struct inode *inode = filp->f_path.dentry->d_inode;
mlog_entry("(0x%p, %u, '%.*s')\n", filp,
(unsigned int)nr_segs,
filp->f_path.dentry->d_name.len,
filp->f_path.dentry->d_name.name);
if (!inode) {
ret = -EINVAL;
mlog_errno(ret);
goto bail;
}
/*
* buffered reads protect themselves in ->readpage(). O_DIRECT reads
* need locks to protect pending reads from racing with truncate.
*/
if (filp->f_flags & O_DIRECT) {
down_read(&inode->i_alloc_sem);
have_alloc_sem = 1;
ret = ocfs2_rw_lock(inode, 0);
if (ret < 0) {
mlog_errno(ret);
goto bail;
}
rw_level = 0;
/* communicate with ocfs2_dio_end_io */
ocfs2_iocb_set_rw_locked(iocb, rw_level);
}
/*
* We're fine letting folks race truncates and extending
* writes with read across the cluster, just like they can
* locally. Hence no rw_lock during read.
*
* Take and drop the meta data lock to update inode fields
* like i_size. This allows the checks down below
* generic_file_aio_read() a chance of actually working.
*/
ret = ocfs2_meta_lock_atime(inode, filp->f_vfsmnt, &lock_level);
if (ret < 0) {
mlog_errno(ret);
goto bail;
}
ocfs2_meta_unlock(inode, lock_level);
ret = generic_file_aio_read(iocb, iov, nr_segs, iocb->ki_pos);
if (ret == -EINVAL)
mlog(ML_ERROR, "generic_file_aio_read returned -EINVAL\n");
/* buffered aio wouldn't have proper lock coverage today */
BUG_ON(ret == -EIOCBQUEUED && !(filp->f_flags & O_DIRECT));
/* see ocfs2_file_aio_write */
if (ret == -EIOCBQUEUED || !ocfs2_iocb_is_rw_locked(iocb)) {
rw_level = -1;
have_alloc_sem = 0;
}
bail:
if (have_alloc_sem)
up_read(&inode->i_alloc_sem);
if (rw_level != -1)
ocfs2_rw_unlock(inode, rw_level);
mlog_exit(ret);
return ret;
}
ssize_t /* bytes read, or (-) error */
xfs_read(
bhv_desc_t *bdp,
struct kiocb *iocb,
const struct iovec *iovp,
unsigned int segs,
loff_t *offset,
int ioflags,
cred_t *credp)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
size_t size = 0;
ssize_t ret;
xfs_fsize_t n;
xfs_inode_t *ip;
xfs_mount_t *mp;
bhv_vnode_t *vp;
unsigned long seg;
ip = XFS_BHVTOI(bdp);
vp = BHV_TO_VNODE(bdp);
mp = ip->i_mount;
XFS_STATS_INC(xs_read_calls);
/* START copy & waste from filemap.c */
for (seg = 0; seg < segs; seg++) {
const struct iovec *iv = &iovp[seg];
/*
* If any segment has a negative length, or the cumulative
* length ever wraps negative then return -EINVAL.
*/
size += iv->iov_len;
if (unlikely((ssize_t)(size|iv->iov_len) < 0))
return XFS_ERROR(-EINVAL);
}
/* END copy & waste from filemap.c */
if (unlikely(ioflags & IO_ISDIRECT)) {
xfs_buftarg_t *target =
(ip->i_d.di_flags & XFS_DIFLAG_REALTIME) ?
mp->m_rtdev_targp : mp->m_ddev_targp;
if ((*offset & target->bt_smask) ||
(size & target->bt_smask)) {
if (*offset == ip->i_d.di_size) {
return (0);
}
return -XFS_ERROR(EINVAL);
}
}
n = XFS_MAXIOFFSET(mp) - *offset;
if ((n <= 0) || (size == 0))
return 0;
if (n < size)
size = n;
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
if (unlikely(ioflags & IO_ISDIRECT))
mutex_lock(&inode->i_mutex);
xfs_ilock(ip, XFS_IOLOCK_SHARED);
if (DM_EVENT_ENABLED(vp->v_vfsp, ip, DM_EVENT_READ) &&
!(ioflags & IO_INVIS)) {
bhv_vrwlock_t locktype = VRWLOCK_READ;
int dmflags = FILP_DELAY_FLAG(file) | DM_SEM_FLAG_RD(ioflags);
ret = -XFS_SEND_DATA(mp, DM_EVENT_READ,
BHV_TO_VNODE(bdp), *offset, size,
dmflags, &locktype);
if (ret) {
xfs_iunlock(ip, XFS_IOLOCK_SHARED);
if (unlikely(ioflags & IO_ISDIRECT))
mutex_unlock(&inode->i_mutex);
return ret;
}
}
if (unlikely(ioflags & IO_ISDIRECT)) {
if (VN_CACHED(vp))
bhv_vop_flushinval_pages(vp, ctooff(offtoct(*offset)),
-1, FI_REMAPF_LOCKED);
mutex_unlock(&inode->i_mutex);
}
xfs_rw_enter_trace(XFS_READ_ENTER, &ip->i_iocore,
(void *)iovp, segs, *offset, ioflags);
iocb->ki_pos = *offset;
ret = generic_file_aio_read(iocb, iovp, segs, *offset);
if (ret == -EIOCBQUEUED && !(ioflags & IO_ISAIO))
ret = wait_on_sync_kiocb(iocb);
if (ret > 0)
XFS_STATS_ADD(xs_read_bytes, ret);
xfs_iunlock(ip, XFS_IOLOCK_SHARED);
return ret;
}
static ssize_t ccfs_generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov, unsigned long nr_segs, loff_t pos) {
ssize_t res;
res = generic_file_aio_read(iocb, iov, nr_segs, pos);
mdbg(INFO3,"Async Read ... Pos: %lld, Res: %ld",(long long) pos, res);
return res;
}
