Commit 82c156f8 authored by Al Viro's avatar Al Viro

switch generic_file_splice_read() to use of ->read_iter()

... and kill the ->splice_read() instances that can be switched to it
Signed-off-by: default avatarAl Viro <viro@zeniv.linux.org.uk>
parent 241699cd
......@@ -1153,36 +1153,21 @@ ll_file_io_generic(const struct lu_env *env, struct vvp_io_args *args,
int write_mutex_locked = 0;
vio->vui_fd = LUSTRE_FPRIVATE(file);
vio->vui_io_subtype = args->via_io_subtype;
switch (vio->vui_io_subtype) {
case IO_NORMAL:
vio->vui_iter = args->u.normal.via_iter;
vio->vui_iocb = args->u.normal.via_iocb;
if ((iot == CIT_WRITE) &&
!(vio->vui_fd->fd_flags & LL_FILE_GROUP_LOCKED)) {
if (mutex_lock_interruptible(&lli->
lli_write_mutex)) {
result = -ERESTARTSYS;
goto out;
}
write_mutex_locked = 1;
vio->vui_iter = args->u.normal.via_iter;
vio->vui_iocb = args->u.normal.via_iocb;
if ((iot == CIT_WRITE) &&
!(vio->vui_fd->fd_flags & LL_FILE_GROUP_LOCKED)) {
if (mutex_lock_interruptible(&lli->lli_write_mutex)) {
result = -ERESTARTSYS;
goto out;
}
down_read(&lli->lli_trunc_sem);
break;
case IO_SPLICE:
vio->u.splice.vui_pipe = args->u.splice.via_pipe;
vio->u.splice.vui_flags = args->u.splice.via_flags;
break;
default:
CERROR("Unknown IO type - %u\n", vio->vui_io_subtype);
LBUG();
write_mutex_locked = 1;
}
down_read(&lli->lli_trunc_sem);
ll_cl_add(file, env, io);
result = cl_io_loop(env, io);
ll_cl_remove(file, env);
if (args->via_io_subtype == IO_NORMAL)
up_read(&lli->lli_trunc_sem);
up_read(&lli->lli_trunc_sem);
if (write_mutex_locked)
mutex_unlock(&lli->lli_write_mutex);
} else {
......@@ -1237,7 +1222,7 @@ static ssize_t ll_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
if (IS_ERR(env))
return PTR_ERR(env);
args = ll_env_args(env, IO_NORMAL);
args = ll_env_args(env);
args->u.normal.via_iter = to;
args->u.normal.via_iocb = iocb;
......@@ -1261,7 +1246,7 @@ static ssize_t ll_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
if (IS_ERR(env))
return PTR_ERR(env);
args = ll_env_args(env, IO_NORMAL);
args = ll_env_args(env);
args->u.normal.via_iter = from;
args->u.normal.via_iocb = iocb;
......@@ -1271,31 +1256,6 @@ static ssize_t ll_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
return result;
}
/*
* Send file content (through pagecache) somewhere with helper
*/
static ssize_t ll_file_splice_read(struct file *in_file, loff_t *ppos,
struct pipe_inode_info *pipe, size_t count,
unsigned int flags)
{
struct lu_env *env;
struct vvp_io_args *args;
ssize_t result;
int refcheck;
env = cl_env_get(&refcheck);
if (IS_ERR(env))
return PTR_ERR(env);
args = ll_env_args(env, IO_SPLICE);
args->u.splice.via_pipe = pipe;
args->u.splice.via_flags = flags;
result = ll_file_io_generic(env, args, in_file, CIT_READ, ppos, count);
cl_env_put(env, &refcheck);
return result;
}
static int ll_lov_recreate(struct inode *inode, struct ost_id *oi, u32 ost_idx)
{
struct obd_export *exp = ll_i2dtexp(inode);
......@@ -3173,7 +3133,7 @@ struct file_operations ll_file_operations = {
.release = ll_file_release,
.mmap = ll_file_mmap,
.llseek = ll_file_seek,
.splice_read = ll_file_splice_read,
.splice_read = generic_file_splice_read,
.fsync = ll_fsync,
.flush = ll_flush
};
......@@ -3186,7 +3146,7 @@ struct file_operations ll_file_operations_flock = {
.release = ll_file_release,
.mmap = ll_file_mmap,
.llseek = ll_file_seek,
.splice_read = ll_file_splice_read,
.splice_read = generic_file_splice_read,
.fsync = ll_fsync,
.flush = ll_flush,
.flock = ll_file_flock,
......@@ -3202,7 +3162,7 @@ struct file_operations ll_file_operations_noflock = {
.release = ll_file_release,
.mmap = ll_file_mmap,
.llseek = ll_file_seek,
.splice_read = ll_file_splice_read,
.splice_read = generic_file_splice_read,
.fsync = ll_fsync,
.flush = ll_flush,
.flock = ll_file_noflock,
......
......@@ -800,17 +800,11 @@ void vvp_write_complete(struct vvp_object *club, struct vvp_page *page);
*/
struct vvp_io_args {
/** normal/splice */
enum vvp_io_subtype via_io_subtype;
union {
struct {
struct kiocb *via_iocb;
struct iov_iter *via_iter;
} normal;
struct {
struct pipe_inode_info *via_pipe;
unsigned int via_flags;
} splice;
} u;
};
......@@ -838,14 +832,9 @@ static inline struct ll_thread_info *ll_env_info(const struct lu_env *env)
return lti;
}
static inline struct vvp_io_args *ll_env_args(const struct lu_env *env,
enum vvp_io_subtype type)
static inline struct vvp_io_args *ll_env_args(const struct lu_env *env)
{
struct vvp_io_args *via = &ll_env_info(env)->lti_args;
via->via_io_subtype = type;
return via;
return &ll_env_info(env)->lti_args;
}
void ll_queue_done_writing(struct inode *inode, unsigned long flags);
......
......@@ -49,14 +49,6 @@ struct obd_device;
struct obd_export;
struct page;
/* specific architecture can implement only part of this list */
enum vvp_io_subtype {
/** normal IO */
IO_NORMAL,
/** io started from splice_{read|write} */
IO_SPLICE
};
/**
* IO state private to IO state private to VVP layer.
*/
......@@ -98,10 +90,6 @@ struct vvp_io {
*/
bool ft_flags_valid;
} fault;
struct {
struct pipe_inode_info *vui_pipe;
unsigned int vui_flags;
} splice;
struct {
struct cl_page_list vui_queue;
unsigned long vui_written;
......@@ -110,8 +98,6 @@ struct vvp_io {
} write;
} u;
enum vvp_io_subtype vui_io_subtype;
/**
* Layout version when this IO is initialized
*/
......
......@@ -54,18 +54,6 @@ static struct vvp_io *cl2vvp_io(const struct lu_env *env,
return vio;
}
/**
* True, if \a io is a normal io, False for splice_{read,write}
*/
static int cl_is_normalio(const struct lu_env *env, const struct cl_io *io)
{
struct vvp_io *vio = vvp_env_io(env);
LASSERT(io->ci_type == CIT_READ || io->ci_type == CIT_WRITE);
return vio->vui_io_subtype == IO_NORMAL;
}
/**
* For swapping layout. The file's layout may have changed.
* To avoid populating pages to a wrong stripe, we have to verify the
......@@ -391,9 +379,6 @@ static int vvp_mmap_locks(const struct lu_env *env,
LASSERT(io->ci_type == CIT_READ || io->ci_type == CIT_WRITE);
if (!cl_is_normalio(env, io))
return 0;
if (!vio->vui_iter) /* nfs or loop back device write */
return 0;
......@@ -462,15 +447,10 @@ static void vvp_io_advance(const struct lu_env *env,
const struct cl_io_slice *ios,
size_t nob)
{
struct vvp_io *vio = cl2vvp_io(env, ios);
struct cl_io *io = ios->cis_io;
struct cl_object *obj = ios->cis_io->ci_obj;
struct vvp_io *vio = cl2vvp_io(env, ios);
CLOBINVRNT(env, obj, vvp_object_invariant(obj));
if (!cl_is_normalio(env, io))
return;
iov_iter_reexpand(vio->vui_iter, vio->vui_tot_count -= nob);
}
......@@ -479,7 +459,7 @@ static void vvp_io_update_iov(const struct lu_env *env,
{
size_t size = io->u.ci_rw.crw_count;
if (!cl_is_normalio(env, io) || !vio->vui_iter)
if (!vio->vui_iter)
return;
iov_iter_truncate(vio->vui_iter, size);
......@@ -716,25 +696,8 @@ static int vvp_io_read_start(const struct lu_env *env,
/* BUG: 5972 */
file_accessed(file);
switch (vio->vui_io_subtype) {
case IO_NORMAL:
LASSERT(vio->vui_iocb->ki_pos == pos);
result = generic_file_read_iter(vio->vui_iocb, vio->vui_iter);
break;
case IO_SPLICE:
result = generic_file_splice_read(file, &pos,
vio->u.splice.vui_pipe, cnt,
vio->u.splice.vui_flags);
/* LU-1109: do splice read stripe by stripe otherwise if it
* may make nfsd stuck if this read occupied all internal pipe
* buffers.
*/
io->ci_continue = 0;
break;
default:
CERROR("Wrong IO type %u\n", vio->vui_io_subtype);
LBUG();
}
LASSERT(vio->vui_iocb->ki_pos == pos);
result = generic_file_read_iter(vio->vui_iocb, vio->vui_iter);
out:
if (result >= 0) {
......
......@@ -37,27 +37,6 @@ coda_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
return vfs_iter_read(cfi->cfi_container, to, &iocb->ki_pos);
}
static ssize_t
coda_file_splice_read(struct file *coda_file, loff_t *ppos,
struct pipe_inode_info *pipe, size_t count,
unsigned int flags)
{
ssize_t (*splice_read)(struct file *, loff_t *,
struct pipe_inode_info *, size_t, unsigned int);
struct coda_file_info *cfi;
struct file *host_file;
cfi = CODA_FTOC(coda_file);
BUG_ON(!cfi || cfi->cfi_magic != CODA_MAGIC);
host_file = cfi->cfi_container;
splice_read = host_file->f_op->splice_read;
if (!splice_read)
splice_read = default_file_splice_read;
return splice_read(host_file, ppos, pipe, count, flags);
}
static ssize_t
coda_file_write_iter(struct kiocb *iocb, struct iov_iter *to)
{
......@@ -225,6 +204,6 @@ const struct file_operations coda_file_operations = {
.open = coda_open,
.release = coda_release,
.fsync = coda_fsync,
.splice_read = coda_file_splice_read,
.splice_read = generic_file_splice_read,
};
......@@ -954,30 +954,6 @@ static long gfs2_fallocate(struct file *file, int mode, loff_t offset, loff_t le
return ret;
}
static ssize_t gfs2_file_splice_read(struct file *in, loff_t *ppos,
struct pipe_inode_info *pipe, size_t len,
unsigned int flags)
{
struct inode *inode = in->f_mapping->host;
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_holder gh;
int ret;
inode_lock(inode);
ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, 0, &gh);
if (ret) {
inode_unlock(inode);
return ret;
}
gfs2_glock_dq_uninit(&gh);
inode_unlock(inode);
return generic_file_splice_read(in, ppos, pipe, len, flags);
}
static ssize_t gfs2_file_splice_write(struct pipe_inode_info *pipe,
struct file *out, loff_t *ppos,
size_t len, unsigned int flags)
......@@ -1140,7 +1116,7 @@ const struct file_operations gfs2_file_fops = {
.fsync = gfs2_fsync,
.lock = gfs2_lock,
.flock = gfs2_flock,
.splice_read = gfs2_file_splice_read,
.splice_read = generic_file_splice_read,
.splice_write = gfs2_file_splice_write,
.setlease = simple_nosetlease,
.fallocate = gfs2_fallocate,
......@@ -1168,7 +1144,7 @@ const struct file_operations gfs2_file_fops_nolock = {
.open = gfs2_open,
.release = gfs2_release,
.fsync = gfs2_fsync,
.splice_read = gfs2_file_splice_read,
.splice_read = generic_file_splice_read,
.splice_write = gfs2_file_splice_write,
.setlease = generic_setlease,
.fallocate = gfs2_fallocate,
......
......@@ -182,29 +182,6 @@ nfs_file_read(struct kiocb *iocb, struct iov_iter *to)
}
EXPORT_SYMBOL_GPL(nfs_file_read);
ssize_t
nfs_file_splice_read(struct file *filp, loff_t *ppos,
struct pipe_inode_info *pipe, size_t count,
unsigned int flags)
{
struct inode *inode = file_inode(filp);
ssize_t res;
dprintk("NFS: splice_read(%pD2, %lu@%Lu)\n",
filp, (unsigned long) count, (unsigned long long) *ppos);
nfs_start_io_read(inode);
res = nfs_revalidate_mapping(inode, filp->f_mapping);
if (!res) {
res = generic_file_splice_read(filp, ppos, pipe, count, flags);
if (res > 0)
nfs_add_stats(inode, NFSIOS_NORMALREADBYTES, res);
}
nfs_end_io_read(inode);
return res;
}
EXPORT_SYMBOL_GPL(nfs_file_splice_read);
int
nfs_file_mmap(struct file * file, struct vm_area_struct * vma)
{
......@@ -871,7 +848,7 @@ const struct file_operations nfs_file_operations = {
.fsync = nfs_file_fsync,
.lock = nfs_lock,
.flock = nfs_flock,
.splice_read = nfs_file_splice_read,
.splice_read = generic_file_splice_read,
.splice_write = iter_file_splice_write,
.check_flags = nfs_check_flags,
.setlease = simple_nosetlease,
......
......@@ -365,8 +365,6 @@ int nfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *)
int nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync);
loff_t nfs_file_llseek(struct file *, loff_t, int);
ssize_t nfs_file_read(struct kiocb *, struct iov_iter *);
ssize_t nfs_file_splice_read(struct file *, loff_t *, struct pipe_inode_info *,
size_t, unsigned int);
int nfs_file_mmap(struct file *, struct vm_area_struct *);
ssize_t nfs_file_write(struct kiocb *, struct iov_iter *);
int nfs_file_release(struct inode *, struct file *);
......
......@@ -248,7 +248,7 @@ const struct file_operations nfs4_file_operations = {
.fsync = nfs_file_fsync,
.lock = nfs_lock,
.flock = nfs_flock,
.splice_read = nfs_file_splice_read,
.splice_read = generic_file_splice_read,
.splice_write = iter_file_splice_write,
.check_flags = nfs_check_flags,
.setlease = simple_nosetlease,
......
......@@ -2321,36 +2321,6 @@ static ssize_t ocfs2_file_write_iter(struct kiocb *iocb,
return ret;
}
static ssize_t ocfs2_file_splice_read(struct file *in,
loff_t *ppos,
struct pipe_inode_info *pipe,
size_t len,
unsigned int flags)
{
int ret = 0, lock_level = 0;
struct inode *inode = file_inode(in);
trace_ocfs2_file_splice_read(inode, in, in->f_path.dentry,
(unsigned long long)OCFS2_I(inode)->ip_blkno,
in->f_path.dentry->d_name.len,
in->f_path.dentry->d_name.name, len);
/*
* See the comment in ocfs2_file_read_iter()
*/
ret = ocfs2_inode_lock_atime(inode, in->f_path.mnt, &lock_level);
if (ret < 0) {
mlog_errno(ret);
goto bail;
}
ocfs2_inode_unlock(inode, lock_level);
ret = generic_file_splice_read(in, ppos, pipe, len, flags);
bail:
return ret;
}
static ssize_t ocfs2_file_read_iter(struct kiocb *iocb,
struct iov_iter *to)
{
......@@ -2509,7 +2479,7 @@ const struct file_operations ocfs2_fops = {
#endif
.lock = ocfs2_lock,
.flock = ocfs2_flock,
.splice_read = ocfs2_file_splice_read,
.splice_read = generic_file_splice_read,
.splice_write = iter_file_splice_write,
.fallocate = ocfs2_fallocate,
};
......@@ -2554,7 +2524,7 @@ const struct file_operations ocfs2_fops_no_plocks = {
.compat_ioctl = ocfs2_compat_ioctl,
#endif
.flock = ocfs2_flock,
.splice_read = ocfs2_file_splice_read,
.splice_read = generic_file_splice_read,
.splice_write = iter_file_splice_write,
.fallocate = ocfs2_fallocate,
};
......
......@@ -1314,8 +1314,6 @@ DEFINE_OCFS2_FILE_OPS(ocfs2_file_aio_write);
DEFINE_OCFS2_FILE_OPS(ocfs2_file_splice_write);
DEFINE_OCFS2_FILE_OPS(ocfs2_file_splice_read);
DEFINE_OCFS2_FILE_OPS(ocfs2_file_aio_read);
DEFINE_OCFS2_ULL_ULL_ULL_EVENT(ocfs2_truncate_file);
......
......@@ -281,207 +281,6 @@ void splice_shrink_spd(struct splice_pipe_desc *spd)
kfree(spd->partial);
}
static int
__generic_file_splice_read(struct file *in, loff_t *ppos,
struct pipe_inode_info *pipe, size_t len,
unsigned int flags)
{
struct address_space *mapping = in->f_mapping;
unsigned int loff, nr_pages, req_pages;
struct page *pages[PIPE_DEF_BUFFERS];
struct partial_page partial[PIPE_DEF_BUFFERS];
struct page *page;
pgoff_t index, end_index;
loff_t isize;
int error, page_nr;
struct splice_pipe_desc spd = {
.pages = pages,
.partial = partial,
.nr_pages_max = PIPE_DEF_BUFFERS,
.flags = flags,
.ops = &page_cache_pipe_buf_ops,
.spd_release = spd_release_page,
};
if (splice_grow_spd(pipe, &spd))
return -ENOMEM;
index = *ppos >> PAGE_SHIFT;
loff = *ppos & ~PAGE_MASK;
req_pages = (len + loff + PAGE_SIZE - 1) >> PAGE_SHIFT;
nr_pages = min(req_pages, spd.nr_pages_max);
/*
* Lookup the (hopefully) full range of pages we need.
*/
spd.nr_pages = find_get_pages_contig(mapping, index, nr_pages, spd.pages);
index += spd.nr_pages;
/*
* If find_get_pages_contig() returned fewer pages than we needed,
* readahead/allocate the rest and fill in the holes.
*/
if (spd.nr_pages < nr_pages)
page_cache_sync_readahead(mapping, &in->f_ra, in,
index, req_pages - spd.nr_pages);
error = 0;
while (spd.nr_pages < nr_pages) {
/*
* Page could be there, find_get_pages_contig() breaks on
* the first hole.
*/
page = find_get_page(mapping, index);
if (!page) {
/*
* page didn't exist, allocate one.
*/
page = page_cache_alloc_cold(mapping);
if (!page)
break;
error = add_to_page_cache_lru(page, mapping, index,
mapping_gfp_constraint(mapping, GFP_KERNEL));
if (unlikely(error)) {
put_page(page);
if (error == -EEXIST)
continue;
break;
}
/*
* add_to_page_cache() locks the page, unlock it
* to avoid convoluting the logic below even more.
*/
unlock_page(page);
}
spd.pages[spd.nr_pages++] = page;
index++;
}
/*
* Now loop over the map and see if we need to start IO on any
* pages, fill in the partial map, etc.
*/
index = *ppos >> PAGE_SHIFT;
nr_pages = spd.nr_pages;
spd.nr_pages = 0;
for (page_nr = 0; page_nr < nr_pages; page_nr++) {
unsigned int this_len;
if (!len)
break;
/*
* this_len is the max we'll use from this page
*/
this_len = min_t(unsigned long, len, PAGE_SIZE - loff);
page = spd.pages[page_nr];
if (PageReadahead(page))
page_cache_async_readahead(mapping, &in->f_ra, in,
page, index, req_pages - page_nr);
/*
* If the page isn't uptodate, we may need to start io on it
*/
if (!PageUptodate(page)) {
lock_page(page);
/*
* Page was truncated, or invalidated by the
* filesystem. Redo the find/create, but this time the
* page is kept locked, so there's no chance of another
* race with truncate/invalidate.
*/
if (!page->mapping) {
unlock_page(page);
retry_lookup:
page = find_or_create_page(mapping, index,
mapping_gfp_mask(mapping));
if (!page) {
error = -ENOMEM;
break;
}
put_page(spd.pages[page_nr]);
spd.pages[page_nr] = page;
}
/*
* page was already under io and is now done, great
*/
if (PageUptodate(page)) {
unlock_page(page);
goto fill_it;
}
/*
* need to read in the page
*/
error = mapping->a_ops->readpage(in, page);
if (unlikely(error)) {
/*
* Re-lookup the page
*/
if (error == AOP_TRUNCATED_PAGE)
goto retry_lookup;
break;
}
}
fill_it:
/*
* i_size must be checked after PageUptodate.
*/
isize = i_size_read(mapping->host);
end_index = (isize - 1) >> PAGE_SHIFT;
if (unlikely(!isize || index > end_index))
break;
/*
* if this is the last page, see if we need to shrink
* the length and stop
*/
if (end_index == index) {
unsigned int plen;
/*
* max good bytes in this page
*/
plen = ((isize - 1) & ~PAGE_MASK) + 1;
if (plen <= loff)
break;
/*
* force quit after adding this page
*/
this_len = min(this_len, plen - loff);
len = this_len;
}
spd.partial[page_nr].offset = loff;
spd.partial[page_nr].len = this_len;
len -= this_len;
loff = 0;
spd.nr_pages++;
index++;
}
/*
* Release any pages at the end, if we quit early. 'page_nr' is how far
* we got, 'nr_pages' is how many pages are in the map.
*/
while (page_nr < nr_pages)
put_page(spd.pages[page_nr++]);
in->f_ra.prev_pos = (loff_t)index << PAGE_SHIFT;
if (spd.nr_pages)
error = splice_to_pipe(pipe, &spd);
splice_shrink_spd(&spd);
return error;
}
/**
* generic_file_splice_read - splice data from file to a pipe
* @in: file to splice from
......@@ -492,32 +291,46 @@ __generic_file_splice_read(struct file *in, loff_t *ppos,
*
* Description:
* Will read pages from given file and fill them into a pipe. Can be
* used as long as the address_space operations for the source implements
* a readpage() hook.
* used as long as it has more or less sane ->read_iter().
*
*/
ssize_t generic_file_splice_read(struct file *in, loff_t *ppos,
struct pipe_inode_info *pipe, size_t len,
unsigned int flags)
{
loff_t isize, left;
int ret;
if (IS_DAX(in->f_mapping->host))
return default_file_splice_read(in, ppos, pipe, len, flags);
struct iov_iter to;
struct kiocb kiocb;
loff_t isize;
int idx, ret;
isize = i_size_read(in->f_mapping->host);
if (unlikely(*ppos >= isize))
return 0;
left = isize - *ppos;
if (unlikely(left < len))
len = left;
ret = __generic_file_splice_read(in, ppos, pipe, len, flags);
iov_iter_pipe(&to, ITER_PIPE | READ, pipe, len);
idx = to.idx;
init_sync_kiocb(&kiocb, in);
kiocb.ki_pos = *ppos;
ret = in->f_op->read_iter(&kiocb, &to);
if (ret > 0) {
*ppos += ret;
*ppos = kiocb.ki_pos;
file_accessed(in);