From: Al Viro <viro@ZenIV.linux.org.uk>
To: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Dave Chinner <david@fromorbit.com>, CAI Qian <caiqian@redhat.com>,
linux-xfs <linux-xfs@vger.kernel.org>,
xfs@oss.sgi.com, Jens Axboe <axboe@kernel.dk>,
Nick Piggin <npiggin@gmail.com>,
linux-fsdevel <linux-fsdevel@vger.kernel.org>
Subject: [PATCH 11/12] switch generic_file_splice_read() to use of ->read_iter()
Date: Sat, 24 Sep 2016 05:01:50 +0100 [thread overview]
Message-ID: <20160924040150.GQ2356@ZenIV.linux.org.uk> (raw)
In-Reply-To: <CA+55aFyr-X_6FcWkSXBUcxV0p1BUZw8d=46wawv2x+8y7f8YcQ@mail.gmail.com>
... and kill the ->splice_read() instances that can be switched to it
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
drivers/staging/lustre/lustre/llite/file.c | 70 ++----
.../staging/lustre/lustre/llite/llite_internal.h | 15 +-
drivers/staging/lustre/lustre/llite/vvp_internal.h | 14 --
drivers/staging/lustre/lustre/llite/vvp_io.c | 45 +---
fs/coda/file.c | 23 +-
fs/gfs2/file.c | 28 +--
fs/nfs/file.c | 25 +--
fs/nfs/internal.h | 2 -
fs/nfs/nfs4file.c | 2 +-
fs/ocfs2/file.c | 34 +--
fs/ocfs2/ocfs2_trace.h | 2 -
fs/splice.c | 244 +++------------------
fs/xfs/xfs_file.c | 41 +---
fs/xfs/xfs_trace.h | 1 -
include/linux/fs.h | 2 -
mm/shmem.c | 115 +---------
16 files changed, 58 insertions(+), 605 deletions(-)
diff --git a/drivers/staging/lustre/lustre/llite/file.c b/drivers/staging/lustre/lustre/llite/file.c
index 57281b9..2567b09 100644
--- a/drivers/staging/lustre/lustre/llite/file.c
+++ b/drivers/staging/lustre/lustre/llite/file.c
@@ -1153,36 +1153,21 @@ restart:
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,
diff --git a/drivers/staging/lustre/lustre/llite/llite_internal.h b/drivers/staging/lustre/lustre/llite/llite_internal.h
index 4d6d589..0e738c8 100644
--- a/drivers/staging/lustre/lustre/llite/llite_internal.h
+++ b/drivers/staging/lustre/lustre/llite/llite_internal.h
@@ -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);
diff --git a/drivers/staging/lustre/lustre/llite/vvp_internal.h b/drivers/staging/lustre/lustre/llite/vvp_internal.h
index 79fc428..2fa49cc 100644
--- a/drivers/staging/lustre/lustre/llite/vvp_internal.h
+++ b/drivers/staging/lustre/lustre/llite/vvp_internal.h
@@ -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.
*/
@@ -99,10 +91,6 @@ 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;
int vui_from;
@@ -110,8 +98,6 @@ struct vvp_io {
} write;
} u;
- enum vvp_io_subtype vui_io_subtype;
-
/**
* Layout version when this IO is initialized
*/
diff --git a/drivers/staging/lustre/lustre/llite/vvp_io.c b/drivers/staging/lustre/lustre/llite/vvp_io.c
index 94916dc..4864600 100644
--- a/drivers/staging/lustre/lustre/llite/vvp_io.c
+++ b/drivers/staging/lustre/lustre/llite/vvp_io.c
@@ -55,18 +55,6 @@ static struct vvp_io *cl2vvp_io(const struct lu_env *env,
}
/**
- * 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
* correctness of layout. It works because swapping layout processes
@@ -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) {
diff --git a/fs/coda/file.c b/fs/coda/file.c
index f47c748..8415d4f 100644
--- a/fs/coda/file.c
+++ b/fs/coda/file.c
@@ -38,27 +38,6 @@ coda_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
}
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)
{
struct file *coda_file = iocb->ki_filp;
@@ -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,
};
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index 320e65e..7016a6a7 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -954,30 +954,6 @@ out_uninit:
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,
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 7d62097..5048585 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -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)
{
@@ -868,7 +845,7 @@ 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,
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 74935a1..d7b062b 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -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 *);
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index d085ad7..89a7795 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -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,
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 4e7b0dc..6596e41 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -2307,36 +2307,6 @@ out_mutex:
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)
{
@@ -2495,7 +2465,7 @@ 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,
};
@@ -2540,7 +2510,7 @@ 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,
};
diff --git a/fs/ocfs2/ocfs2_trace.h b/fs/ocfs2/ocfs2_trace.h
index f8f5fc5..0b58abc 100644
--- a/fs/ocfs2/ocfs2_trace.h
+++ b/fs/ocfs2/ocfs2_trace.h
@@ -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);
diff --git a/fs/splice.c b/fs/splice.c
index 589a1d5..58c322a 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -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 @@ fill_it:
*
* 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);
+ } else if (ret < 0) {
+ if (WARN_ON(to.idx != idx || to.iov_offset)) {
+ /*
+ * a bogus ->read_iter() has copied something and still
+ * returned an error instead of a short read.
+ */
+ to.idx = idx;
+ to.iov_offset = 0;
+ iov_iter_advance(&to, 0); /* to free what was emitted */
+ }
+ /*
+ * callers of ->splice_read() expect -EAGAIN on
+ * "can't put anything in there", rather than -EFAULT.
+ */
+ if (ret == -EFAULT)
+ ret = -EAGAIN;
}
return ret;
@@ -580,7 +393,7 @@ ssize_t kernel_write(struct file *file, const char *buf, size_t count,
}
EXPORT_SYMBOL(kernel_write);
-ssize_t default_file_splice_read(struct file *in, loff_t *ppos,
+static ssize_t default_file_splice_read(struct file *in, loff_t *ppos,
struct pipe_inode_info *pipe, size_t len,
unsigned int flags)
{
@@ -675,7 +488,6 @@ err:
res = error;
goto shrink_ret;
}
-EXPORT_SYMBOL(default_file_splice_read);
/*
* Send 'sd->len' bytes to socket from 'sd->file' at position 'sd->pos'
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index e612a02..92f16cf 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -399,45 +399,6 @@ xfs_file_read_iter(
return ret;
}
-STATIC ssize_t
-xfs_file_splice_read(
- struct file *infilp,
- loff_t *ppos,
- struct pipe_inode_info *pipe,
- size_t count,
- unsigned int flags)
-{
- struct xfs_inode *ip = XFS_I(infilp->f_mapping->host);
- ssize_t ret;
-
- XFS_STATS_INC(ip->i_mount, xs_read_calls);
-
- if (XFS_FORCED_SHUTDOWN(ip->i_mount))
- return -EIO;
-
- trace_xfs_file_splice_read(ip, count, *ppos);
-
- /*
- * DAX inodes cannot ues the page cache for splice, so we have to push
- * them through the VFS IO path. This means it goes through
- * ->read_iter, which for us takes the XFS_IOLOCK_SHARED. Hence we
- * cannot lock the splice operation at this level for DAX inodes.
- */
- if (IS_DAX(VFS_I(ip))) {
- ret = default_file_splice_read(infilp, ppos, pipe, count,
- flags);
- goto out;
- }
-
- xfs_rw_ilock(ip, XFS_IOLOCK_SHARED);
- ret = generic_file_splice_read(infilp, ppos, pipe, count, flags);
- xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
-out:
- if (ret > 0)
- XFS_STATS_ADD(ip->i_mount, xs_read_bytes, ret);
- return ret;
-}
-
/*
* Zero any on disk space between the current EOF and the new, larger EOF.
*
@@ -1652,7 +1613,7 @@ const struct file_operations xfs_file_operations = {
.llseek = xfs_file_llseek,
.read_iter = xfs_file_read_iter,
.write_iter = xfs_file_write_iter,
- .splice_read = xfs_file_splice_read,
+ .splice_read = generic_file_splice_read,
.splice_write = iter_file_splice_write,
.unlocked_ioctl = xfs_file_ioctl,
#ifdef CONFIG_COMPAT
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index d303a66..f31db44 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -1170,7 +1170,6 @@ DEFINE_RW_EVENT(xfs_file_dax_read);
DEFINE_RW_EVENT(xfs_file_buffered_write);
DEFINE_RW_EVENT(xfs_file_direct_write);
DEFINE_RW_EVENT(xfs_file_dax_write);
-DEFINE_RW_EVENT(xfs_file_splice_read);
DECLARE_EVENT_CLASS(xfs_page_class,
TP_PROTO(struct inode *inode, struct page *page, unsigned long off,
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 901e25d..b04883e 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2794,8 +2794,6 @@ extern void block_sync_page(struct page *page);
/* fs/splice.c */
extern ssize_t generic_file_splice_read(struct file *, loff_t *,
struct pipe_inode_info *, size_t, unsigned int);
-extern ssize_t default_file_splice_read(struct file *, loff_t *,
- struct pipe_inode_info *, size_t, unsigned int);
extern ssize_t iter_file_splice_write(struct pipe_inode_info *,
struct file *, loff_t *, size_t, unsigned int);
extern ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe,
diff --git a/mm/shmem.c b/mm/shmem.c
index fd8b2b5..84d7077 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -2310,119 +2310,6 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
return retval ? retval : error;
}
-static ssize_t shmem_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;
- struct inode *inode = mapping->host;
- 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, left;
- 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,
- };
-
- isize = i_size_read(inode);
- if (unlikely(*ppos >= isize))
- return 0;
-
- left = isize - *ppos;
- if (unlikely(left < len))
- len = left;
-
- 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);
-
- spd.nr_pages = find_get_pages_contig(mapping, index,
- nr_pages, spd.pages);
- index += spd.nr_pages;
- error = 0;
-
- while (spd.nr_pages < nr_pages) {
- error = shmem_getpage(inode, index, &page, SGP_CACHE);
- if (error)
- break;
- unlock_page(page);
- spd.pages[spd.nr_pages++] = page;
- index++;
- }
-
- 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 = min_t(unsigned long, len, PAGE_SIZE - loff);
- page = spd.pages[page_nr];
-
- if (!PageUptodate(page) || page->mapping != mapping) {
- error = shmem_getpage(inode, index, &page, SGP_CACHE);
- if (error)
- break;
- unlock_page(page);
- put_page(spd.pages[page_nr]);
- spd.pages[page_nr] = page;
- }
-
- isize = i_size_read(inode);
- end_index = (isize - 1) >> PAGE_SHIFT;
- if (unlikely(!isize || index > end_index))
- break;
-
- if (end_index == index) {
- unsigned int plen;
-
- plen = ((isize - 1) & ~PAGE_MASK) + 1;
- if (plen <= loff)
- break;
-
- 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++;
- }
-
- while (page_nr < nr_pages)
- put_page(spd.pages[page_nr++]);
-
- if (spd.nr_pages)
- error = splice_to_pipe(pipe, &spd);
-
- splice_shrink_spd(&spd);
-
- if (error > 0) {
- *ppos += error;
- file_accessed(in);
- }
- return error;
-}
-
/*
* llseek SEEK_DATA or SEEK_HOLE through the radix_tree.
*/
@@ -3785,7 +3672,7 @@ static const struct file_operations shmem_file_operations = {
.read_iter = shmem_file_read_iter,
.write_iter = generic_file_write_iter,
.fsync = noop_fsync,
- .splice_read = shmem_file_splice_read,
+ .splice_read = generic_file_splice_read,
.splice_write = iter_file_splice_write,
.fallocate = shmem_fallocate,
#endif
--
2.9.3
next prev parent reply other threads:[~2016-09-24 4:01 UTC|newest]
Thread overview: 151+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <723420070.1340881.1472835555274.JavaMail.zimbra@redhat.com>
[not found] ` <1832555471.1341372.1472835736236.JavaMail.zimbra@redhat.com>
2016-09-03 0:39 ` xfs_file_splice_read: possible circular locking dependency detected Dave Chinner
2016-09-03 0:57 ` Linus Torvalds
2016-09-03 1:45 ` Al Viro
2016-09-06 23:59 ` Dave Chinner
2016-09-08 20:35 ` Al Viro
2016-09-06 21:53 ` CAI Qian
2016-09-06 23:34 ` Dave Chinner
2016-09-08 15:29 ` CAI Qian
2016-09-08 17:56 ` Al Viro
2016-09-08 18:12 ` Linus Torvalds
2016-09-08 18:18 ` Linus Torvalds
2016-09-08 20:44 ` Al Viro
2016-09-08 20:57 ` Al Viro
2016-09-08 21:23 ` Al Viro
2016-09-08 21:38 ` Dave Chinner
2016-09-08 23:55 ` Al Viro
2016-09-09 1:53 ` Dave Chinner
2016-09-09 2:22 ` Linus Torvalds
2016-09-09 2:26 ` Linus Torvalds
2016-09-09 2:34 ` Al Viro
2016-09-09 2:50 ` Linus Torvalds
2016-09-09 22:19 ` Al Viro
2016-09-10 2:06 ` Linus Torvalds
2016-09-14 3:16 ` Al Viro
2016-09-14 3:39 ` Nicholas Piggin
2016-09-14 4:01 ` Linus Torvalds
2016-09-18 5:33 ` Al Viro
2016-09-19 3:08 ` Nicholas Piggin
2016-09-19 6:11 ` Al Viro
2016-09-19 7:26 ` Nicholas Piggin
2016-09-14 3:49 ` Linus Torvalds
2016-09-14 4:26 ` Al Viro
2016-09-17 8:20 ` Al Viro
2016-09-17 19:00 ` Al Viro
2016-09-17 20:15 ` Linus Torvalds
2016-09-18 19:31 ` skb_splice_bits() and large chunks in pipe (was " Al Viro
2016-09-18 20:12 ` Linus Torvalds
2016-09-18 22:31 ` Al Viro
2016-09-19 0:18 ` Linus Torvalds
2016-09-19 0:22 ` Al Viro
2016-09-20 9:51 ` Herbert Xu
2016-09-23 19:00 ` [RFC][CFT] splice_read reworked Al Viro
2016-09-23 19:01 ` [PATCH 01/11] fix memory leaks in tracing_buffers_splice_read() Al Viro
2016-09-23 19:02 ` [PATCH 02/11] splice_to_pipe(): don't open-code wakeup_pipe_readers() Al Viro
2016-09-23 19:02 ` [PATCH 03/11] splice: switch get_iovec_page_array() to iov_iter Al Viro
2016-09-23 19:02 ` Al Viro
2016-09-23 19:03 ` [PATCH 04/11] splice: lift pipe_lock out of splice_to_pipe() Al Viro
2016-09-23 19:45 ` Linus Torvalds
2016-09-23 20:10 ` Al Viro
2016-09-23 20:36 ` Linus Torvalds
2016-09-24 3:59 ` Al Viro
2016-09-24 17:29 ` Al Viro
2016-09-27 15:38 ` Nicholas Piggin
2016-09-27 15:53 ` Chuck Lever
2016-09-27 15:53 ` Chuck Lever
2016-09-24 3:59 ` [PATCH 04/12] " Al Viro
2016-09-26 13:35 ` Miklos Szeredi
2016-09-26 13:35 ` Miklos Szeredi
2016-09-27 4:14 ` Al Viro
2016-09-27 4:14 ` Al Viro
2016-12-17 19:54 ` Andreas Schwab
2016-12-18 19:28 ` Linus Torvalds
2016-12-18 19:57 ` Andreas Schwab
2016-12-18 20:12 ` Al Viro
2016-12-18 20:30 ` Al Viro
2016-12-18 22:10 ` Linus Torvalds
2016-12-18 22:18 ` Al Viro
2016-12-18 22:22 ` Linus Torvalds
2016-12-18 22:49 ` Andreas Schwab
2016-12-21 18:56 ` Andreas Schwab
2016-12-21 19:12 ` Linus Torvalds
2016-09-24 4:00 ` [PATCH 06/12] new helper: add_to_pipe() Al Viro
2016-09-26 13:49 ` Miklos Szeredi
2016-09-24 4:01 ` [PATCH 10/12] new iov_iter flavour: pipe-backed Al Viro
2016-09-29 20:53 ` Miklos Szeredi
2016-09-29 22:50 ` Al Viro
2016-09-29 22:50 ` Al Viro
2016-09-30 7:30 ` Miklos Szeredi
2016-10-03 3:34 ` [RFC] O_DIRECT vs EFAULT (was Re: [PATCH 10/12] new iov_iter flavour: pipe-backed) Al Viro
2016-10-03 17:07 ` Linus Torvalds
2016-10-03 18:54 ` Al Viro
2016-09-24 4:01 ` Al Viro [this message]
2016-09-24 4:02 ` [PATCH 12/12] switch default_file_splice_read() to use of pipe-backed iov_iter Al Viro
2016-09-23 19:03 ` [PATCH 05/11] skb_splice_bits(): get rid of callback Al Viro
2016-09-23 19:03 ` Al Viro
2016-09-23 19:04 ` [PATCH 06/11] new helper: add_to_pipe() Al Viro
2016-09-23 19:04 ` [PATCH 07/11] fuse_dev_splice_read(): switch to add_to_pipe() Al Viro
2016-09-23 19:06 ` [PATCH 08/11] cifs: don't use memcpy() to copy struct iov_iter Al Viro
2016-09-23 19:08 ` [PATCH 09/11] fuse_ioctl_copy_user(): don't open-code copy_page_{to,from}_iter() Al Viro
2016-09-26 9:31 ` Miklos Szeredi
2016-09-23 19:09 ` [PATCH 10/11] new iov_iter flavour: pipe-backed Al Viro
2016-09-23 19:10 ` [PATCH 11/11] switch generic_file_splice_read() to use of ->read_iter() Al Viro
2016-09-30 13:32 ` [RFC][CFT] splice_read reworked CAI Qian
2016-09-30 17:42 ` CAI Qian
2016-09-30 18:33 ` CAI Qian
2016-09-30 18:33 ` CAI Qian
2016-10-03 1:37 ` Al Viro
2016-10-03 17:49 ` CAI Qian
2016-10-04 17:39 ` local DoS - systemd hang or timeout (WAS: Re: [RFC][CFT] splice_read reworked) CAI Qian
2016-10-04 21:42 ` tj
2016-10-05 14:09 ` CAI Qian
2016-10-05 15:30 ` tj
2016-10-05 15:54 ` CAI Qian
2016-10-05 18:57 ` CAI Qian
2016-10-05 20:05 ` Al Viro
2016-10-06 12:20 ` CAI Qian
2016-10-06 12:25 ` CAI Qian
2016-10-06 16:11 ` CAI Qian
2016-10-06 17:00 ` Linus Torvalds
2016-10-06 18:12 ` CAI Qian
2016-10-07 9:57 ` Dave Chinner
2016-10-07 15:25 ` Linus Torvalds
2016-10-07 7:08 ` Jan Kara
2016-10-07 14:43 ` CAI Qian
2016-10-07 15:27 ` CAI Qian
2016-10-07 18:56 ` CAI Qian
2016-10-09 21:54 ` Dave Chinner
2016-10-10 14:10 ` CAI Qian
2016-10-10 20:14 ` CAI Qian
2016-10-10 21:57 ` Dave Chinner
2016-10-12 19:50 ` [bisected] " CAI Qian
2016-10-12 20:59 ` Dave Chinner
2016-10-13 16:25 ` CAI Qian
2016-10-13 20:49 ` Dave Chinner
2016-10-13 20:56 ` CAI Qian
2016-10-09 21:51 ` Dave Chinner
2016-10-21 15:38 ` [4.9-rc1+] overlayfs lockdep CAI Qian
2016-10-24 12:57 ` Miklos Szeredi
2016-10-07 9:27 ` local DoS - systemd hang or timeout (WAS: Re: [RFC][CFT] splice_read reworked) Dave Chinner
2016-10-27 12:52 ` local DoS - systemd hang or timeout with cgroup traces CAI Qian
2016-10-03 1:42 ` [RFC][CFT] splice_read reworked Al Viro
2016-10-03 14:06 ` CAI Qian
2016-10-03 15:20 ` CAI Qian
2016-10-03 21:12 ` Dave Chinner
2016-10-04 13:57 ` CAI Qian
2016-10-03 20:32 ` CAI Qian
2016-10-03 20:35 ` Al Viro
2016-10-04 13:29 ` CAI Qian
2016-10-04 14:28 ` Al Viro
2016-10-04 16:21 ` CAI Qian
2016-10-04 20:12 ` Al Viro
2016-10-05 14:30 ` CAI Qian
2016-10-05 16:07 ` Al Viro
2016-09-09 2:31 ` xfs_file_splice_read: possible circular locking dependency detected Al Viro
2016-09-09 2:39 ` Linus Torvalds
2016-09-09 2:26 ` Al Viro
2016-09-09 2:19 ` Al Viro
2016-09-08 18:01 ` Linus Torvalds
2016-09-08 20:39 ` CAI Qian
2016-09-08 21:19 ` Dave Chinner
2016-09-08 21:30 ` Al Viro
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20160924040150.GQ2356@ZenIV.linux.org.uk \
--to=viro@zeniv.linux.org.uk \
--cc=axboe@kernel.dk \
--cc=caiqian@redhat.com \
--cc=david@fromorbit.com \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-xfs@vger.kernel.org \
--cc=npiggin@gmail.com \
--cc=torvalds@linux-foundation.org \
--cc=xfs@oss.sgi.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.