static void check_iovecs(struct iovec *vec, int cnt,
struct iovec *avec, int acnt, uint32_t off_in_head)
{
char *s1, *s2;
uint32_t size, asize;
size = iov_length(vec, cnt);
asize = iov_length(avec, acnt) - off_in_head;
if (size != asize) {
gf_log("crypt", GF_LOG_DEBUG, "size %d is not eq asize %d",
size, asize);
return;
}
s1 = GF_CALLOC(1, size, gf_crypt_mt_data);
if (!s1) {
gf_log("crypt", GF_LOG_DEBUG, "Can not allocate stream ");
return;
}
s2 = GF_CALLOC(1, asize, gf_crypt_mt_data);
if (!s2) {
GF_FREE(s1);
gf_log("crypt", GF_LOG_DEBUG, "Can not allocate stream ");
return;
}
compound_stream(vec, cnt, s1, 0);
compound_stream(avec, acnt, s2, off_in_head);
if (memcmp(s1, s2, size))
gf_log("crypt", GF_LOG_DEBUG, "chunks of different data");
GF_FREE(s1);
GF_FREE(s2);
}
int32_t ida_buffer_combine(ida_local_t * local, ida_buffer_t * dst, ida_buffer_t * src)
{
if (iov_length(dst->vectors, dst->count) == iov_length(src->vectors, src->count))
{
return 0;
}
return EIO;
}
/*
* Transfer an interrupt request to userspace
*
* Unlike other requests this is assembled on demand, without a need
* to allocate a separate fuse_req structure.
*
* Called with fc->lock held, releases it
*/
static int fuse_read_interrupt(struct fuse_conn *fc, struct fuse_req *req,
const struct iovec *iov, unsigned long nr_segs)
{
struct fuse_copy_state cs;
struct fuse_in_header ih;
struct fuse_interrupt_in arg;
unsigned reqsize = sizeof(ih) + sizeof(arg);
int err;
list_del_init(&req->intr_entry);
req->intr_unique = fuse_get_unique(fc);
memset(&ih, 0, sizeof(ih));
memset(&arg, 0, sizeof(arg));
ih.len = reqsize;
ih.opcode = FUSE_INTERRUPT;
ih.unique = req->intr_unique;
arg.unique = req->in.h.unique;
spin_unlock(&fc->lock);
if (iov_length(iov, nr_segs) < reqsize)
return -EINVAL;
fuse_copy_init(&cs, fc, 1, NULL, iov, nr_segs);
err = fuse_copy_one(&cs, &ih, sizeof(ih));
if (!err)
err = fuse_copy_one(&cs, &arg, sizeof(arg));
fuse_copy_finish(&cs);
return err ? err : reqsize;
}
static ssize_t
nilfs_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
loff_t offset, unsigned long nr_segs)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
ssize_t size;
if (rw == WRITE)
return 0;
size = blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs,
nilfs_get_block);
if (unlikely((rw & WRITE) && size < 0)) {
loff_t isize = i_size_read(inode);
loff_t end = offset + iov_length(iov, nr_segs);
if (end > isize)
vmtruncate(inode, isize);
}
return size;
}
static int send_reply(fuse_req_t req, int error, const void *arg,
size_t argsize)
{
struct fuse_out_header out;
struct iovec iov[2];
size_t count;
int res;
if (error <= -1000 || error > 0) {
fprintf(stderr, "fuse: bad error value: %i\n", error);
error = -ERANGE;
}
out.unique = req->unique;
out.error = error;
count = 1;
iov[0].iov_base = &out;
iov[0].iov_len = sizeof(struct fuse_out_header);
if (argsize && !error) {
count++;
iov[1].iov_base = (void *) arg;
iov[1].iov_len = argsize;
}
out.len = iov_length(iov, count);
if (req->f->debug) {
printf(" unique: %llu, error: %i (%s), outsize: %i\n",
out.unique, out.error, strerror(-out.error), out.len);
fflush(stdout);
}
res = fuse_chan_send(req->ch, iov, count);
free_req(req);
return res;
}
ssize_t rawfs_block_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
unsigned long nr_segs, loff_t pos)
{
struct file *filp = iocb->ki_filp;
// struct super_block *sb = filp->f_path.dentry->d_sb;
// struct rawfs_sb_info *rawfs_sb = RAWFS_SB(sb);
// struct address_space *mapping=filp->f_mapping;
struct inode *inode = filp->f_mapping->host;
struct rawfs_inode_info *inode_info = RAWFS_I(inode);
ssize_t retval;
// unsigned long seg = 0;
loff_t *ppos = &iocb->ki_pos;
// loff_t size;
retval=iov_length(iov, nr_segs);
RAWFS_PRINT(RAWFS_DBG_FILE, "rawfs_block_file_aio_write %s, pos %lld, "
"len %d\n", inode_info->i_name, pos, retval);
if (retval > 0)
*ppos = pos + retval;
file_accessed(filp);
/* This function is not supported, data will not write to the device */
return retval;
}
static int send_reply_iov(fuse_req_t req, int error, struct iovec *iov,
int count)
{
struct fuse_out_header out;
int res;
if (error <= -1000 || error > 0) {
fprintf(stderr, "fuse: bad error value: %i\n", error);
error = -ERANGE;
}
out.unique = req->unique;
out.error = error;
iov[0].iov_base = &out;
iov[0].iov_len = sizeof(struct fuse_out_header);
out.len = iov_length(iov, count);
/* Foxconn removed start pling 06/19/2009 */
#if 0
if (req->f->debug)
fprintf(stderr, " unique: %llu, error: %i (%s), outsize: %i\n",
(unsigned long long) out.unique, out.error,
strerror(-out.error), out.len);
#endif
/* Foxconn removed end pling 06/19/2009 */
res = fuse_chan_send(req->ch, iov, count);
free_req(req);
return res;
}
static ssize_t gfs2_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
unsigned long nr_segs, loff_t pos)
{
struct file *file = iocb->ki_filp;
size_t writesize = iov_length(iov, nr_segs);
struct dentry *dentry = file->f_dentry;
struct gfs2_inode *ip = GFS2_I(dentry->d_inode);
struct gfs2_sbd *sdp;
int ret;
sdp = GFS2_SB(file->f_mapping->host);
ret = gfs2_rs_alloc(ip);
if (ret)
return ret;
atomic_set(&ip->i_res->rs_sizehint, writesize >> sdp->sd_sb.sb_bsize_shift);
if (file->f_flags & O_APPEND) {
struct gfs2_holder gh;
ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, 0, &gh);
if (ret)
return ret;
gfs2_glock_dq_uninit(&gh);
}
return generic_file_aio_write(iocb, iov, nr_segs, pos);
}
static ssize_t jfs_direct_IO(int rw, struct kiocb *iocb,
const struct iovec *iov, loff_t offset, unsigned long nr_segs)
{
struct file *file = iocb->ki_filp;
struct address_space *mapping = file->f_mapping;
struct inode *inode = file->f_mapping->host;
ssize_t ret;
ret = blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs,
jfs_get_block);
/*
* In case of error extending write may have instantiated a few
* blocks outside i_size. Trim these off again.
*/
if (unlikely((rw & WRITE) && ret < 0)) {
loff_t isize = i_size_read(inode);
loff_t end = offset + iov_length(iov, nr_segs);
if (end > isize)
jfs_write_failed(mapping, end);
}
return ret;
}
static ssize_t gfs2_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
unsigned long nr_segs, loff_t pos)
{
struct file *file = iocb->ki_filp;
size_t writesize = iov_length(iov, nr_segs);
struct dentry *dentry = file->f_dentry;
struct gfs2_inode *ip = GFS2_I(dentry->d_inode);
int ret;
ret = gfs2_rs_alloc(ip);
if (ret)
return ret;
gfs2_size_hint(file, pos, writesize);
if (file->f_flags & O_APPEND) {
struct gfs2_holder gh;
ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, 0, &gh);
if (ret)
return ret;
gfs2_glock_dq_uninit(&gh);
}
return generic_file_aio_write(iocb, iov, nr_segs, pos);
}
static ssize_t
nilfs_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
loff_t offset, unsigned long nr_segs)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
ssize_t size;
if (rw == WRITE)
return 0;
/* Needs synchronization with the cleaner */
size = blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs,
nilfs_get_block);
/*
* In case of error extending write may have instantiated a few
* blocks outside i_size. Trim these off again.
*/
if (unlikely((rw & WRITE) && size < 0)) {
loff_t isize = i_size_read(inode);
loff_t end = offset + iov_length(iov, nr_segs);
if (end > isize)
vmtruncate(inode, isize);
}
return size;
}
int fuse_send_reply_iov_nofree(fuse_req_t req, int error, struct iovec *iov,
int count)
{
struct fuse_out_header out;
if (error <= -1000 || error > 0) {
fprintf(stderr, "fuse: bad error value: %i\n", error);
error = -ERANGE;
}
out.unique = req->unique;
out.error = error;
iov[0].iov_base = &out;
iov[0].iov_len = sizeof(struct fuse_out_header);
out.len = iov_length(iov, count);
if (req->f->debug) {
if (out.error) {
fprintf(stderr,
" unique: %llu, error: %i (%s), outsize: %i\n",
(unsigned long long) out.unique, out.error,
strerror(-out.error), out.len);
} else {
fprintf(stderr,
" unique: %llu, success, outsize: %i\n",
(unsigned long long) out.unique, out.len);
}
}
return fuse_chan_send(req->ch, iov, count);
}
static ssize_t
ext4_file_write(struct kiocb *iocb, const struct iovec *iov,
unsigned long nr_segs, loff_t pos)
{
struct inode *inode = iocb->ki_filp->f_path.dentry->d_inode;
/*
* If we have encountered a bitmap-format file, the size limit
* is smaller than s_maxbytes, which is for extent-mapped files.
*/
if (!(ext4_test_inode_state(inode, EXT4_STATE_DA_ALLOC_CLOSE))) {
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
size_t length = iov_length(iov, nr_segs);
if (pos > sbi->s_bitmap_maxbytes)
return -EFBIG;
if (pos + length > sbi->s_bitmap_maxbytes) {
nr_segs = iov_shorten((struct iovec *)iov, nr_segs,
sbi->s_bitmap_maxbytes - pos);
}
}
return generic_file_aio_write(iocb, iov, nr_segs, pos);
}
/**
* rawfs_block_file_aio_read - read routine for block files
* @iocb: kernel I/O control block
* @iov: io vector request
* @nr_segs: number of segments in the iovec
* @pos: current file position
*/
ssize_t
rawfs_block_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
unsigned long nr_segs, loff_t pos)
{
struct file *filp = iocb->ki_filp;
struct super_block *sb = filp->f_path.dentry->d_sb;
struct rawfs_sb_info *rawfs_sb = RAWFS_SB(sb);
// struct address_space *mapping=filp->f_mapping;
struct inode *inode = filp->f_mapping->host;
struct rawfs_inode_info *inode_info = RAWFS_I(inode);
ssize_t retval;
// unsigned long seg = 0;
size_t count;
loff_t *ppos = &iocb->ki_pos;
// Always use direct I/O
loff_t size;
int block_no;
retval = generic_segment_checks(iov, &nr_segs, &count, VERIFY_WRITE);
if (retval)
return retval;
retval=iov_length(iov, nr_segs);
mutex_lock(&rawfs_sb->rawfs_lock);
RAWFS_PRINT(RAWFS_DBG_FILE, "rawfs_block_file_aio_read %s, pos %lld, "
"len %d\n", inode_info->i_name, pos, retval);
size = i_size_read(inode);
// Get inode ID
block_no = filp->f_path.dentry->d_inode->i_ino - RAWFS_BLOCK0_INO;
if ((retval + pos) >= size)
retval = size - pos;
if (pos < size) {
rawfs_sb->dev.read_page_user(filp->f_path.dentry->d_inode->i_sb,
block_no, pos, iov, nr_segs, retval);
if (retval > 0)
*ppos = pos + retval;
if (retval < 0 || *ppos >= size) {
file_accessed(filp);
goto out;
}
}
out:
mutex_unlock(&rawfs_sb->rawfs_lock);
return retval;
}
static ssize_t
ext4_file_write(struct kiocb *iocb, const struct iovec *iov,
unsigned long nr_segs, loff_t pos)
{
struct inode *inode = iocb->ki_filp->f_path.dentry->d_inode;
int unaligned_aio = 0;
int ret;
trace_ext4_file_write(iocb->ki_filp->f_path.dentry, iocb->ki_left);
/*
* If we have encountered a bitmap-format file, the size limit
* is smaller than s_maxbytes, which is for extent-mapped files.
*/
if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
size_t length = iov_length(iov, nr_segs);
if ((pos > sbi->s_bitmap_maxbytes ||
(pos == sbi->s_bitmap_maxbytes && length > 0)))
return -EFBIG;
if (pos + length > sbi->s_bitmap_maxbytes) {
nr_segs = iov_shorten((struct iovec *)iov, nr_segs,
sbi->s_bitmap_maxbytes - pos);
}
} else if (unlikely((iocb->ki_filp->f_flags & O_DIRECT) &&
!is_sync_kiocb(iocb))) {
unaligned_aio = ext4_unaligned_aio(inode, iov, nr_segs, pos);
}
/* Unaligned direct AIO must be serialized; see comment above */
if (unaligned_aio) {
static unsigned long unaligned_warn_time;
/* Warn about this once per day */
if (printk_timed_ratelimit(&unaligned_warn_time, 60*60*24*HZ))
ext4_msg(inode->i_sb, KERN_WARNING,
"Unaligned AIO/DIO on inode %ld by %s; "
"performance will be poor.",
inode->i_ino, current->comm);
mutex_lock(ext4_aio_mutex(inode));
ext4_aiodio_wait(inode);
}
ret = generic_file_aio_write(iocb, iov, nr_segs, pos);
if (unaligned_aio)
mutex_unlock(ext4_aio_mutex(inode));
trace_file_write_done(iocb->ki_filp);
return ret;
}
ssize_t nfs_file_write(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;
unsigned long written = 0;
ssize_t result;
size_t count = iov_length(iov, nr_segs);
if (iocb->ki_filp->f_flags & O_DIRECT)
return nfs_file_direct_write(iocb, iov, nr_segs, pos, true);
dprintk("NFS: write(%s/%s, %lu@%Ld)\n",
dentry->d_parent->d_name.name, dentry->d_name.name,
(unsigned long) count, (long long) pos);
result = -EBUSY;
if (IS_SWAPFILE(inode))
goto out_swapfile;
/*
* O_APPEND implies that we must revalidate the file length.
*/
if (iocb->ki_filp->f_flags & O_APPEND) {
result = nfs_revalidate_file_size(inode, iocb->ki_filp);
if (result)
goto out;
}
result = count;
if (!count)
goto out;
result = generic_file_aio_write(iocb, iov, nr_segs, pos);
if (result > 0)
written = result;
/* Return error values for O_DSYNC and IS_SYNC() */
if (result >= 0 && nfs_need_sync_write(iocb->ki_filp, inode)) {
int err = vfs_fsync(iocb->ki_filp, 0);
if (err < 0)
result = err;
}
if (result > 0)
nfs_add_stats(inode, NFSIOS_NORMALWRITTENBYTES, written);
out:
return result;
out_swapfile:
printk(KERN_INFO "NFS: attempt to write to active swap file!\n");
goto out;
}
static ssize_t
ext4_file_write(struct kiocb *iocb, const struct iovec *iov,
unsigned long nr_segs, loff_t pos)
{
struct inode *inode = iocb->ki_filp->f_path.dentry->d_inode;
int unaligned_aio = 0;
int ret;
trace_ext4_file_write(iocb->ki_filp->f_path.dentry, iocb->ki_left);
if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
size_t length = iov_length(iov, nr_segs);
if ((pos > sbi->s_bitmap_maxbytes ||
(pos == sbi->s_bitmap_maxbytes && length > 0)))
return -EFBIG;
if (pos + length > sbi->s_bitmap_maxbytes) {
nr_segs = iov_shorten((struct iovec *)iov, nr_segs,
sbi->s_bitmap_maxbytes - pos);
}
} else if (unlikely((iocb->ki_filp->f_flags & O_DIRECT) &&
!is_sync_kiocb(iocb))) {
unaligned_aio = ext4_unaligned_aio(inode, iov, nr_segs, pos);
}
if (unaligned_aio) {
static unsigned long unaligned_warn_time;
if (printk_timed_ratelimit(&unaligned_warn_time, 60*60*24*HZ))
ext4_msg(inode->i_sb, KERN_WARNING,
"Unaligned AIO/DIO on inode %ld by %s; "
"performance will be poor.",
inode->i_ino, current->comm);
mutex_lock(ext4_aio_mutex(inode));
ext4_aiodio_wait(inode);
}
ret = generic_file_aio_write(iocb, iov, nr_segs, pos);
if (unaligned_aio)
mutex_unlock(ext4_aio_mutex(inode));
return ret;
}
static ssize_t nfs_file_write(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);
#ifdef CONFIG_NFS_DIRECTIO
if (iocb->ki_filp->f_flags & O_DIRECT)
return nfs_file_direct_write(iocb, iov, nr_segs, pos);
#endif
dfprintk(VFS, "nfs: write(%s/%s(%ld), %lu@%Ld)\n",
dentry->d_parent->d_name.name, dentry->d_name.name,
inode->i_ino, (unsigned long) count, (long long) pos);
result = -EBUSY;
if (IS_SWAPFILE(inode))
goto out_swapfile;
/*
* O_APPEND implies that we must revalidate the file length.
*/
if (iocb->ki_filp->f_flags & O_APPEND) {
result = nfs_revalidate_file_size(inode, iocb->ki_filp);
if (result)
goto out;
}
result = count;
if (!count)
goto out;
nfs_add_stats(inode, NFSIOS_NORMALWRITTENBYTES, count);
result = generic_file_aio_write(iocb, iov, nr_segs, pos);
/* Return error values for O_SYNC and IS_SYNC() */
if (result >= 0 && (IS_SYNC(inode) || (iocb->ki_filp->f_flags & O_SYNC))) {
int err = nfs_fsync(iocb->ki_filp, dentry, 1);
if (err < 0)
result = err;
}
out:
return result;
out_swapfile:
printk(KERN_INFO "NFS: attempt to write to active swap file!\n");
goto out;
}
static int send_notify_iov(struct fuse_ll *f, struct fuse_chan *ch,
int notify_code, struct iovec *iov, int count)
{
struct fuse_out_header out;
out.unique = 0;
out.error = notify_code;
iov[0].iov_base = &out;
iov[0].iov_len = sizeof(struct fuse_out_header);
out.len = iov_length(iov, count);
if (f->debug)
fprintf(stderr, "NOTIFY: code=%d count=%d length=%u\n",
notify_code, count, out.len);
return fuse_chan_send(ch, iov, count);
}
int32_t ida_buffer_assign(ida_local_t * local, ida_buffer_t * dst, struct iobref * buffers, struct iovec * vectors, uint32_t count)
{
char * ptr;
int32_t i, error;
if (unlikely(count > 1))
{
error = ida_buffer_new(local, dst, iov_length(vectors, count));
if (unlikely(error != 0))
{
return error;
}
ptr = dst->vectors->iov_base;
for (i = 0; i < count; i++)
{
memcpy(ptr, vectors[i].iov_base, vectors[i].iov_len);
ptr += vectors[i].iov_len;
}
}
else
{
SYS_PTR(
&dst->buffers, iobref_ref, (buffers),
ENOMEM,
E(),
RETERR()
);
SYS_PTR(
&dst->vectors, iov_dup, (vectors, count),
ENOMEM,
E(),
GOTO(failed)
);
}
dst->count = 1;
return 0;
failed:
iobref_unref(dst->buffers);
dst->buffers = NULL;
return -ENOMEM;
}
/*
* This tests whether the IO in question is block-aligned or not.
* Ext4 utilizes unwritten extents when hole-filling during direct IO, and they
* are converted to written only after the IO is complete. Until they are
* mapped, these blocks appear as holes, so dio_zero_block() will assume that
* it needs to zero out portions of the start and/or end block. If 2 AIO
* threads are at work on the same unwritten block, they must be synchronized
* or one thread will zero the other's data, causing corruption.
*/
static int
ext4_unaligned_aio(struct inode *inode, const struct iovec *iov,
unsigned long nr_segs, loff_t pos)
{
struct super_block *sb = inode->i_sb;
int blockmask = sb->s_blocksize - 1;
size_t count = iov_length(iov, nr_segs);
loff_t final_size = pos + count;
if (pos >= inode->i_size)
return 0;
if ((pos & blockmask) || (final_size & blockmask))
return 1;
return 0;
}
static ssize_t f2fs_direct_IO(int rw, struct kiocb *iocb,
const struct iovec *iov, loff_t offset,
unsigned long nr_segs)
{
struct file *file = iocb->ki_filp;
struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
size_t count = iov_length(iov, nr_segs);
int err;
/* we don't need to use inline_data strictly */
if (f2fs_has_inline_data(inode)) {
err = f2fs_convert_inline_inode(inode);
if (err)
return err;
}
if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))
return 0;
err = check_direct_IO(inode, rw, iov, offset, nr_segs);
if (err)
return err;
trace_f2fs_direct_IO_enter(inode, offset, count, rw);
if (rw & WRITE) {
__allocate_data_blocks(inode, offset, count);
if (unlikely(f2fs_cp_error(F2FS_I_SB(inode)))) {
err = -EIO;
goto out;
}
}
err = blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs,
get_data_block_dio);
out:
if (err < 0 && (rw & WRITE))
f2fs_write_failed(mapping, offset + count);
trace_f2fs_direct_IO_exit(inode, offset, count, rw, err);
return err;
}
static ssize_t hypfs_aio_write(struct kiocb *iocb, const struct iovec *iov,
unsigned long nr_segs, loff_t offset)
{
int rc;
struct super_block *sb;
struct hypfs_sb_info *fs_info;
size_t count = iov_length(iov, nr_segs);
sb = iocb->ki_filp->f_path.dentry->d_inode->i_sb;
fs_info = sb->s_fs_info;
/*
* Currently we only allow one update per second for two reasons:
* 1. diag 204 is VERY expensive
* 2. If several processes do updates in parallel and then read the
* hypfs data, the likelihood of collisions is reduced, if we restrict
* the minimum update interval. A collision occurs, if during the
* data gathering of one process another process triggers an update
* If the first process wants to ensure consistent data, it has
* to restart data collection in this case.
*/
mutex_lock(&fs_info->lock);
if (fs_info->last_update == get_seconds()) {
rc = -EBUSY;
goto out;
}
hypfs_delete_tree(sb->s_root);
if (MACHINE_IS_VM)
rc = hypfs_vm_create_files(sb, sb->s_root);
else
rc = hypfs_diag_create_files(sb, sb->s_root);
if (rc) {
pr_err("Updating the hypfs tree failed\n");
hypfs_delete_tree(sb->s_root);
goto out;
}
hypfs_update_update(sb);
rc = count;
out:
mutex_unlock(&fs_info->lock);
return rc;
}
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 gfs2_direct_IO(int rw, struct kiocb *iocb,
const struct iovec *iov, loff_t offset,
unsigned long nr_segs)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
struct address_space *mapping = inode->i_mapping;
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_holder gh;
int rv;
/*
* Deferred lock, even if its a write, since we do no allocation
* on this path. All we need change is atime, and this lock mode
* ensures that other nodes have flushed their buffered read caches
* (i.e. their page cache entries for this inode). We do not,
* unfortunately have the option of only flushing a range like
* the VFS does.
*/
gfs2_holder_init(ip->i_gl, LM_ST_DEFERRED, 0, &gh);
rv = gfs2_glock_nq(&gh);
if (rv)
return rv;
rv = gfs2_ok_for_dio(ip, rw, offset);
if (rv != 1)
goto out; /* dio not valid, fall back to buffered i/o */
/*
* Now since we are holding a deferred (CW) lock at this point, you
* might be wondering why this is ever needed. There is a case however
* where we've granted a deferred local lock against a cached exclusive
* glock. That is ok provided all granted local locks are deferred, but
* it also means that it is possible to encounter pages which are
* cached and possibly also mapped. So here we check for that and sort
* them out ahead of the dio. The glock state machine will take care of
* everything else.
*
* If in fact the cached glock state (gl->gl_state) is deferred (CW) in
* the first place, mapping->nr_pages will always be zero.
*/
if (mapping->nrpages) {
loff_t lstart = offset & (PAGE_CACHE_SIZE - 1);
loff_t len = iov_length(iov, nr_segs);
loff_t end = PAGE_ALIGN(offset + len) - 1;
rv = 0;
if (len == 0)
goto out;
if (test_and_clear_bit(GIF_SW_PAGED, &ip->i_flags))
unmap_shared_mapping_range(ip->i_inode.i_mapping, offset, len);
rv = filemap_write_and_wait_range(mapping, lstart, end);
if (rv)
goto out;
if (rw == WRITE)
truncate_inode_pages_range(mapping, lstart, end);
}
rv = __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov,
offset, nr_segs, gfs2_get_block_direct,
NULL, NULL, 0);
out:
gfs2_glock_dq(&gh);
gfs2_holder_uninit(&gh);
return rv;
}
static int gfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
{
struct page *page = vmf->page;
struct inode *inode = vma->vm_file->f_path.dentry->d_inode;
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_sbd *sdp = GFS2_SB(inode);
struct gfs2_alloc_parms ap = { .aflags = 0, };
unsigned long last_index;
u64 pos = page->index << PAGE_CACHE_SHIFT;
unsigned int data_blocks, ind_blocks, rblocks;
int alloc_required = 0;
struct gfs2_holder gh;
loff_t size;
int ret;
sb_start_pagefault(inode->i_sb);
/* Update file times before taking page lock */
file_update_time(vma->vm_file);
ret = get_write_access(inode);
if (ret)
goto out;
ret = gfs2_rs_alloc(ip);
if (ret)
goto out_write_access;
gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
ret = gfs2_glock_nq(&gh);
if (ret)
goto out_uninit;
set_bit(GLF_DIRTY, &ip->i_gl->gl_flags);
set_bit(GIF_SW_PAGED, &ip->i_flags);
gfs2_size_hint(inode, pos, PAGE_CACHE_SIZE);
ret = gfs2_write_alloc_required(ip, pos, PAGE_CACHE_SIZE, &alloc_required);
if (ret)
goto out_unlock;
if (!alloc_required) {
lock_page(page);
if (!PageUptodate(page) || page->mapping != inode->i_mapping) {
ret = -EAGAIN;
unlock_page(page);
}
goto out_unlock;
}
ret = gfs2_rindex_update(sdp);
if (ret)
goto out_unlock;
ret = gfs2_quota_lock_check(ip);
if (ret)
goto out_unlock;
gfs2_write_calc_reserv(ip, PAGE_CACHE_SIZE, &data_blocks, &ind_blocks);
ap.target = data_blocks + ind_blocks;
ret = gfs2_inplace_reserve(ip, &ap);
if (ret)
goto out_quota_unlock;
rblocks = RES_DINODE + ind_blocks;
if (gfs2_is_jdata(ip))
rblocks += data_blocks ? data_blocks : 1;
if (ind_blocks || data_blocks) {
rblocks += RES_STATFS + RES_QUOTA;
rblocks += gfs2_rg_blocks(ip, data_blocks + ind_blocks);
}
ret = gfs2_trans_begin(sdp, rblocks, 0);
if (ret)
goto out_trans_fail;
lock_page(page);
ret = -EINVAL;
size = i_size_read(inode);
last_index = (size - 1) >> PAGE_CACHE_SHIFT;
/* Check page index against inode size */
if (size == 0 || (page->index > last_index))
goto out_trans_end;
ret = -EAGAIN;
/* If truncated, we must retry the operation, we may have raced
* with the glock demotion code.
*/
if (!PageUptodate(page) || page->mapping != inode->i_mapping)
goto out_trans_end;
/* Unstuff, if required, and allocate backing blocks for page */
ret = 0;
if (gfs2_is_stuffed(ip))
ret = gfs2_unstuff_dinode(ip, page);
if (ret == 0)
ret = gfs2_allocate_page_backing(page);
out_trans_end:
if (ret)
unlock_page(page);
gfs2_trans_end(sdp);
out_trans_fail:
gfs2_inplace_release(ip);
out_quota_unlock:
gfs2_quota_unlock(ip);
out_unlock:
gfs2_glock_dq(&gh);
out_uninit:
gfs2_holder_uninit(&gh);
if (ret == 0) {
set_page_dirty(page);
wait_for_stable_page(page);
}
out_write_access:
put_write_access(inode);
out:
sb_end_pagefault(inode->i_sb);
return block_page_mkwrite_return(ret);
}
static const struct vm_operations_struct gfs2_vm_ops = {
.fault = filemap_fault,
.page_mkwrite = gfs2_page_mkwrite,
};
/**
* gfs2_mmap -
* @file: The file to map
* @vma: The VMA which described the mapping
*
* There is no need to get a lock here unless we should be updating
* atime. We ignore any locking errors since the only consequence is
* a missed atime update (which will just be deferred until later).
*
* Returns: 0
*/
static int gfs2_mmap(struct file *file, struct vm_area_struct *vma)
{
struct gfs2_inode *ip = GFS2_I(file->f_mapping->host);
if (!(file->f_flags & O_NOATIME) &&
!IS_NOATIME(&ip->i_inode)) {
struct gfs2_holder i_gh;
int error;
error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY,
&i_gh);
if (error)
return error;
/* grab lock to update inode */
gfs2_glock_dq_uninit(&i_gh);
file_accessed(file);
}
vma->vm_ops = &gfs2_vm_ops;
vma->vm_flags |= VM_CAN_NONLINEAR;
return 0;
}
/**
* gfs2_open - open a file
* @inode: the inode to open
* @file: the struct file for this opening
*
* Returns: errno
*/
static int gfs2_open(struct inode *inode, struct file *file)
{
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_holder i_gh;
struct gfs2_file *fp;
int error;
fp = kzalloc(sizeof(struct gfs2_file), GFP_KERNEL);
if (!fp)
return -ENOMEM;
mutex_init(&fp->f_fl_mutex);
gfs2_assert_warn(GFS2_SB(inode), !file->private_data);
file->private_data = fp;
if (S_ISREG(ip->i_inode.i_mode)) {
error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY,
&i_gh);
if (error)
goto fail;
if (!(file->f_flags & O_LARGEFILE) &&
i_size_read(inode) > MAX_NON_LFS) {
error = -EOVERFLOW;
goto fail_gunlock;
}
gfs2_glock_dq_uninit(&i_gh);
}
return 0;
fail_gunlock:
gfs2_glock_dq_uninit(&i_gh);
fail:
file->private_data = NULL;
kfree(fp);
return error;
}
/**
* gfs2_release - called to close a struct file
* @inode: the inode the struct file belongs to
* @file: the struct file being closed
*
* Returns: errno
*/
static int gfs2_release(struct inode *inode, struct file *file)
{
struct gfs2_inode *ip = GFS2_I(inode);
kfree(file->private_data);
file->private_data = NULL;
if (!(file->f_mode & FMODE_WRITE))
return 0;
gfs2_rs_delete(ip);
return 0;
}
/**
* gfs2_fsync - sync the dirty data for a file (across the cluster)
* @file: the file that points to the dentry
* @start: the start position in the file to sync
* @end: the end position in the file to sync
* @datasync: set if we can ignore timestamp changes
*
* The VFS will flush data for us. We only need to worry
* about metadata here.
*
* Returns: errno
*/
static int gfs2_fsync(struct file *file, struct dentry *dentry, int datasync)
{
struct inode *inode = dentry->d_inode;
int sync_state = inode->i_state & I_DIRTY;
struct gfs2_inode *ip = GFS2_I(inode);
int ret;
if (!gfs2_is_jdata(ip))
sync_state &= ~I_DIRTY_PAGES;
if (datasync)
sync_state &= ~I_DIRTY_SYNC;
if (sync_state) {
ret = sync_inode_metadata(inode, 1);
if (ret)
return ret;
if (gfs2_is_jdata(ip))
filemap_write_and_wait(inode->i_mapping);
gfs2_ail_flush(ip->i_gl, 1);
}
return 0;
}
/**
* gfs2_file_aio_write - Perform a write to a file
* @iocb: The io context
* @iov: The data to write
* @nr_segs: Number of @iov segments
* @pos: The file position
*
* We have to do a lock/unlock here to refresh the inode size for
* O_APPEND writes, otherwise we can land up writing at the wrong
* offset. There is still a race, but provided the app is using its
* own file locking, this will make O_APPEND work as expected.
*
*/
static ssize_t gfs2_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
unsigned long nr_segs, loff_t pos)
{
struct file *file = iocb->ki_filp;
size_t writesize = iov_length(iov, nr_segs);
struct dentry *dentry = file->f_dentry;
struct gfs2_inode *ip = GFS2_I(dentry->d_inode);
struct gfs2_sbd *sdp;
int ret;
sdp = GFS2_SB(file->f_mapping->host);
ret = gfs2_rs_alloc(ip);
if (ret)
return ret;
gfs2_size_hint(file->f_dentry->d_inode, pos, writesize);
if (file->f_flags & O_APPEND) {
struct gfs2_holder gh;
ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, 0, &gh);
if (ret)
return ret;
gfs2_glock_dq_uninit(&gh);
}
return generic_file_aio_write(iocb, iov, nr_segs, pos);
}
static ssize_t gfs2_file_splice_write(struct pipe_inode_info *pipe,
struct file *out, loff_t *ppos,
size_t len, unsigned int flags)
{
int error;
struct inode *inode = out->f_mapping->host;
struct gfs2_inode *ip = GFS2_I(inode);
error = gfs2_rs_alloc(ip);
if (error)
return (ssize_t)error;
gfs2_size_hint(inode, *ppos, len);
return generic_file_splice_write(pipe, out, ppos, len, flags);
}
static ssize_t
pipe_write(struct kiocb *iocb, const struct iovec *_iov,
unsigned long nr_segs, loff_t ppos)
{
struct file *filp = iocb->ki_filp;
struct inode *inode = filp->f_path.dentry->d_inode;
struct pipe_inode_info *pipe;
ssize_t ret;
int do_wakeup;
struct iovec *iov = (struct iovec *)_iov;
size_t total_len;
ssize_t chars;
total_len = iov_length(iov, nr_segs);
/* Null write succeeds. */
if (unlikely(total_len == 0))
return 0;
do_wakeup = 0;
ret = 0;
mutex_lock(&inode->i_mutex);
pipe = inode->i_pipe;
if (!pipe->readers) {
send_sig(SIGPIPE, current, 0);
ret = -EPIPE;
goto out;
}
/* We try to merge small writes */
chars = total_len & (PAGE_SIZE-1); /* size of the last buffer */
if (pipe->nrbufs && chars != 0) {
int lastbuf = (pipe->curbuf + pipe->nrbufs - 1) &
(pipe->buffers - 1);
struct pipe_buffer *buf = pipe->bufs + lastbuf;
const struct pipe_buf_operations *ops = buf->ops;
int offset = buf->offset + buf->len;
if (ops->can_merge && offset + chars <= PAGE_SIZE) {
int error, atomic = 1;
void *addr;
error = ops->confirm(pipe, buf);
if (error)
goto out;
iov_fault_in_pages_read(iov, chars);
redo1:
addr = ops->map(pipe, buf, atomic);
error = pipe_iov_copy_from_user(offset + addr, iov,
chars, atomic);
ops->unmap(pipe, buf, addr);
ret = error;
do_wakeup = 1;
if (error) {
if (atomic) {
atomic = 0;
goto redo1;
}
goto out;
}
buf->len += chars;
total_len -= chars;
ret = chars;
if (!total_len)
goto out;
}
}
for (;;) {
int bufs;
if (!pipe->readers) {
send_sig(SIGPIPE, current, 0);
if (!ret)
ret = -EPIPE;
break;
}
bufs = pipe->nrbufs;
if (bufs < pipe->buffers) {
int newbuf = (pipe->curbuf + bufs) & (pipe->buffers-1);
struct pipe_buffer *buf = pipe->bufs + newbuf;
struct page *page = pipe->tmp_page;
char *src;
int error, atomic = 1;
if (!page) {
page = alloc_page(GFP_HIGHUSER);
if (unlikely(!page)) {
ret = ret ? : -ENOMEM;
break;
}
pipe->tmp_page = page;
}
static ssize_t
pipe_read(struct kiocb *iocb, const struct iovec *_iov,
unsigned long nr_segs, loff_t pos)
{
struct file *filp = iocb->ki_filp;
struct inode *inode = filp->f_path.dentry->d_inode;
struct pipe_inode_info *pipe;
int do_wakeup;
ssize_t ret;
struct iovec *iov = (struct iovec *)_iov;
size_t total_len;
total_len = iov_length(iov, nr_segs);
/* Null read succeeds. */
if (unlikely(total_len == 0))
return 0;
do_wakeup = 0;
ret = 0;
mutex_lock(&inode->i_mutex);
pipe = inode->i_pipe;
for (;;) {
int bufs = pipe->nrbufs;
if (bufs) {
int curbuf = pipe->curbuf;
struct pipe_buffer *buf = pipe->bufs + curbuf;
const struct pipe_buf_operations *ops = buf->ops;
void *addr;
size_t chars = buf->len;
int error, atomic;
if (chars > total_len)
chars = total_len;
error = ops->confirm(pipe, buf);
if (error) {
if (!ret)
error = ret;
break;
}
atomic = !iov_fault_in_pages_write(iov, chars);
redo:
addr = ops->map(pipe, buf, atomic);
error = pipe_iov_copy_to_user(iov, addr + buf->offset, chars, atomic);
ops->unmap(pipe, buf, addr);
if (unlikely(error)) {
/*
* Just retry with the slow path if we failed.
*/
if (atomic) {
atomic = 0;
goto redo;
}
if (!ret)
ret = error;
break;
}
ret += chars;
buf->offset += chars;
buf->len -= chars;
if (!buf->len) {
buf->ops = NULL;
ops->release(pipe, buf);
curbuf = (curbuf + 1) & (pipe->buffers - 1);
pipe->curbuf = curbuf;
pipe->nrbufs = --bufs;
do_wakeup = 1;
}
total_len -= chars;
if (!total_len)
break; /* common path: read succeeded */
}
if (bufs) /* More to do? */
continue;
if (!pipe->writers)
break;
if (!pipe->waiting_writers) {
/* syscall merging: Usually we must not sleep
* if O_NONBLOCK is set, or if we got some data.
* But if a writer sleeps in kernel space, then
* we can wait for that data without violating POSIX.
*/
if (ret)
break;
if (filp->f_flags & O_NONBLOCK) {
ret = -EAGAIN;
break;
}
}
if (signal_pending(current)) {
if (!ret)
ret = -ERESTARTSYS;
break;
}
if (do_wakeup) {
wake_up_interruptible_sync(&pipe->wait);
kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT);
}
pipe_wait(pipe);
}
mutex_unlock(&inode->i_mutex);
/* Signal writers asynchronously that there is more room. */
if (do_wakeup) {
wake_up_interruptible_sync(&pipe->wait);
kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT);
}
if (ret > 0)
file_accessed(filp);
return ret;
}
/* Expects to be always run from workqueue - which acts as
* read-size critical section for our kind of RCU. */
static void handle_tx(struct vhost_net *net)
{
struct vhost_net_virtqueue *nvq = &net->vqs[VHOST_NET_VQ_TX];
struct vhost_virtqueue *vq = &nvq->vq;
unsigned out, in, s;
int head;
struct msghdr msg = {
.msg_name = NULL,
.msg_namelen = 0,
.msg_control = NULL,
.msg_controllen = 0,
.msg_flags = MSG_DONTWAIT,
};
size_t len, total_len = 0;
int err;
size_t hdr_size;
struct socket *sock;
struct vhost_net_ubuf_ref *uninitialized_var(ubufs);
bool zcopy, zcopy_used;
mutex_lock(&vq->mutex);
sock = vq->private_data;
if (!sock)
goto out;
vhost_disable_notify(&net->dev, vq);
hdr_size = nvq->vhost_hlen;
zcopy = nvq->ubufs;
for (;;) {
/* Release DMAs done buffers first */
if (zcopy)
vhost_zerocopy_signal_used(net, vq);
/* If more outstanding DMAs, queue the work.
* Handle upend_idx wrap around
*/
if (unlikely((nvq->upend_idx + vq->num - VHOST_MAX_PEND)
% UIO_MAXIOV == nvq->done_idx))
break;
head = vhost_get_vq_desc(vq, vq->iov,
ARRAY_SIZE(vq->iov),
&out, &in,
NULL, NULL);
/* On error, stop handling until the next kick. */
if (unlikely(head < 0))
break;
/* Nothing new? Wait for eventfd to tell us they refilled. */
if (head == vq->num) {
if (unlikely(vhost_enable_notify(&net->dev, vq))) {
vhost_disable_notify(&net->dev, vq);
continue;
}
break;
}
if (in) {
vq_err(vq, "Unexpected descriptor format for TX: "
"out %d, int %d\n", out, in);
break;
}
/* Skip header. TODO: support TSO. */
s = move_iovec_hdr(vq->iov, nvq->hdr, hdr_size, out);
len = iov_length(vq->iov, out);
iov_iter_init(&msg.msg_iter, WRITE, vq->iov, out, len);
/* Sanity check */
if (!len) {
vq_err(vq, "Unexpected header len for TX: "
"%zd expected %zd\n",
iov_length(nvq->hdr, s), hdr_size);
break;
}
zcopy_used = zcopy && len >= VHOST_GOODCOPY_LEN
&& (nvq->upend_idx + 1) % UIO_MAXIOV !=
nvq->done_idx
&& vhost_net_tx_select_zcopy(net);
/* use msg_control to pass vhost zerocopy ubuf info to skb */
if (zcopy_used) {
struct ubuf_info *ubuf;
ubuf = nvq->ubuf_info + nvq->upend_idx;
vq->heads[nvq->upend_idx].id = cpu_to_vhost32(vq, head);
vq->heads[nvq->upend_idx].len = VHOST_DMA_IN_PROGRESS;
ubuf->callback = vhost_zerocopy_callback;
ubuf->ctx = nvq->ubufs;
ubuf->desc = nvq->upend_idx;
msg.msg_control = ubuf;
msg.msg_controllen = sizeof(ubuf);
ubufs = nvq->ubufs;
atomic_inc(&ubufs->refcount);
nvq->upend_idx = (nvq->upend_idx + 1) % UIO_MAXIOV;
} else {
msg.msg_control = NULL;
ubufs = NULL;
}
/* TODO: Check specific error and bomb out unless ENOBUFS? */
err = sock->ops->sendmsg(NULL, sock, &msg, len);
if (unlikely(err < 0)) {
if (zcopy_used) {
vhost_net_ubuf_put(ubufs);
nvq->upend_idx = ((unsigned)nvq->upend_idx - 1)
% UIO_MAXIOV;
}
vhost_discard_vq_desc(vq, 1);
break;
}
if (err != len)
pr_debug("Truncated TX packet: "
" len %d != %zd\n", err, len);
if (!zcopy_used)
vhost_add_used_and_signal(&net->dev, vq, head, 0);
else
vhost_zerocopy_signal_used(net, vq);
total_len += len;
vhost_net_tx_packet(net);
if (unlikely(total_len >= VHOST_NET_WEIGHT)) {
vhost_poll_queue(&vq->poll);
break;
}
}
out:
mutex_unlock(&vq->mutex);
}
static int peek_head_len(struct sock *sk)
{
struct sk_buff *head;
int len = 0;
unsigned long flags;
spin_lock_irqsave(&sk->sk_receive_queue.lock, flags);
head = skb_peek(&sk->sk_receive_queue);
if (likely(head)) {
len = head->len;
if (vlan_tx_tag_present(head))
len += VLAN_HLEN;
}
spin_unlock_irqrestore(&sk->sk_receive_queue.lock, flags);
return len;
}
/* This is a multi-buffer version of vhost_get_desc, that works if
* vq has read descriptors only.
* @vq - the relevant virtqueue
* @datalen - data length we'll be reading
* @iovcount - returned count of io vectors we fill
* @log - vhost log
* @log_num - log offset
* @quota - headcount quota, 1 for big buffer
* returns number of buffer heads allocated, negative on error
*/
static int get_rx_bufs(struct vhost_virtqueue *vq,
struct vring_used_elem *heads,
int datalen,
unsigned *iovcount,
struct vhost_log *log,
unsigned *log_num,
unsigned int quota)
{
unsigned int out, in;
int seg = 0;
int headcount = 0;
unsigned d;
int r, nlogs = 0;
/* len is always initialized before use since we are always called with
* datalen > 0.
*/
u32 uninitialized_var(len);
while (datalen > 0 && headcount < quota) {
if (unlikely(seg >= UIO_MAXIOV)) {
r = -ENOBUFS;
goto err;
}
r = vhost_get_vq_desc(vq, vq->iov + seg,
ARRAY_SIZE(vq->iov) - seg, &out,
&in, log, log_num);
if (unlikely(r < 0))
goto err;
d = r;
if (d == vq->num) {
r = 0;
goto err;
}
if (unlikely(out || in <= 0)) {
vq_err(vq, "unexpected descriptor format for RX: "
"out %d, in %d\n", out, in);
r = -EINVAL;
goto err;
}
if (unlikely(log)) {
nlogs += *log_num;
log += *log_num;
}
heads[headcount].id = cpu_to_vhost32(vq, d);
len = iov_length(vq->iov + seg, in);
heads[headcount].len = cpu_to_vhost32(vq, len);
datalen -= len;
++headcount;
seg += in;
}
heads[headcount - 1].len = cpu_to_vhost32(vq, len - datalen);
*iovcount = seg;
if (unlikely(log))
*log_num = nlogs;
/* Detect overrun */
if (unlikely(datalen > 0)) {
r = UIO_MAXIOV + 1;
goto err;
}
return headcount;
err:
vhost_discard_vq_desc(vq, headcount);
return r;
}
static ssize_t
ll_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
loff_t file_offset, unsigned long nr_segs)
{
struct ll_cl_context *lcc;
const struct lu_env *env;
struct cl_io *io;
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
ssize_t count = iov_length(iov, nr_segs);
ssize_t tot_bytes = 0, result = 0;
unsigned long seg = 0;
size_t size = MAX_DIO_SIZE;
ENTRY;
/* FIXME: io smaller than PAGE_SIZE is broken on ia64 ??? */
if ((file_offset & ~PAGE_MASK) || (count & ~PAGE_MASK))
RETURN(-EINVAL);
CDEBUG(D_VFSTRACE, "VFS Op:inode="DFID"(%p), size=%zd (max %lu), "
"offset=%lld=%llx, pages %zd (max %lu)\n",
PFID(ll_inode2fid(inode)), inode, count, MAX_DIO_SIZE,
file_offset, file_offset, count >> PAGE_SHIFT,
MAX_DIO_SIZE >> PAGE_SHIFT);
/* Check that all user buffers are aligned as well */
for (seg = 0; seg < nr_segs; seg++) {
if (((unsigned long)iov[seg].iov_base & ~PAGE_MASK) ||
(iov[seg].iov_len & ~PAGE_MASK))
RETURN(-EINVAL);
}
lcc = ll_cl_find(file);
if (lcc == NULL)
RETURN(-EIO);
env = lcc->lcc_env;
LASSERT(!IS_ERR(env));
io = lcc->lcc_io;
LASSERT(io != NULL);
for (seg = 0; seg < nr_segs; seg++) {
size_t iov_left = iov[seg].iov_len;
unsigned long user_addr = (unsigned long)iov[seg].iov_base;
if (rw == READ) {
if (file_offset >= i_size_read(inode))
break;
if (file_offset + iov_left > i_size_read(inode))
iov_left = i_size_read(inode) - file_offset;
}
while (iov_left > 0) {
struct page **pages;
int page_count, max_pages = 0;
size_t bytes;
bytes = min(size, iov_left);
page_count = ll_get_user_pages(rw, user_addr, bytes,
&pages, &max_pages);
if (likely(page_count > 0)) {
if (unlikely(page_count < max_pages))
bytes = page_count << PAGE_SHIFT;
result = ll_direct_IO_seg(env, io, rw, inode,
bytes, file_offset,
pages, page_count);
ll_free_user_pages(pages, max_pages, rw==READ);
} else if (page_count == 0) {
GOTO(out, result = -EFAULT);
} else {
result = page_count;
}
if (unlikely(result <= 0)) {
/* If we can't allocate a large enough buffer
* for the request, shrink it to a smaller
* PAGE_SIZE multiple and try again.
* We should always be able to kmalloc for a
* page worth of page pointers = 4MB on i386. */
if (result == -ENOMEM &&
size > (PAGE_SIZE / sizeof(*pages)) *
PAGE_SIZE) {
size = ((((size / 2) - 1) |
~PAGE_MASK) + 1) &
PAGE_MASK;
CDEBUG(D_VFSTRACE, "DIO size now %zu\n",
size);
continue;
}
GOTO(out, result);
}
tot_bytes += result;
file_offset += result;
iov_left -= result;
user_addr += result;
}
}
out:
if (tot_bytes > 0) {
struct vvp_io *vio = vvp_env_io(env);
/* no commit async for direct IO */
vio->u.write.vui_written += tot_bytes;
}
RETURN(tot_bytes ? tot_bytes : result);
}
