2010-04-07 00:14:15 +02:00
|
|
|
#include <linux/ceph/ceph_debug.h>
|
2009-10-06 20:31:08 +02:00
|
|
|
|
2010-04-07 00:14:15 +02:00
|
|
|
#include <linux/module.h>
|
2009-10-06 20:31:08 +02:00
|
|
|
#include <linux/sched.h>
|
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h
percpu.h is included by sched.h and module.h and thus ends up being
included when building most .c files. percpu.h includes slab.h which
in turn includes gfp.h making everything defined by the two files
universally available and complicating inclusion dependencies.
percpu.h -> slab.h dependency is about to be removed. Prepare for
this change by updating users of gfp and slab facilities include those
headers directly instead of assuming availability. As this conversion
needs to touch large number of source files, the following script is
used as the basis of conversion.
http://userweb.kernel.org/~tj/misc/slabh-sweep.py
The script does the followings.
* Scan files for gfp and slab usages and update includes such that
only the necessary includes are there. ie. if only gfp is used,
gfp.h, if slab is used, slab.h.
* When the script inserts a new include, it looks at the include
blocks and try to put the new include such that its order conforms
to its surrounding. It's put in the include block which contains
core kernel includes, in the same order that the rest are ordered -
alphabetical, Christmas tree, rev-Xmas-tree or at the end if there
doesn't seem to be any matching order.
* If the script can't find a place to put a new include (mostly
because the file doesn't have fitting include block), it prints out
an error message indicating which .h file needs to be added to the
file.
The conversion was done in the following steps.
1. The initial automatic conversion of all .c files updated slightly
over 4000 files, deleting around 700 includes and adding ~480 gfp.h
and ~3000 slab.h inclusions. The script emitted errors for ~400
files.
2. Each error was manually checked. Some didn't need the inclusion,
some needed manual addition while adding it to implementation .h or
embedding .c file was more appropriate for others. This step added
inclusions to around 150 files.
3. The script was run again and the output was compared to the edits
from #2 to make sure no file was left behind.
4. Several build tests were done and a couple of problems were fixed.
e.g. lib/decompress_*.c used malloc/free() wrappers around slab
APIs requiring slab.h to be added manually.
5. The script was run on all .h files but without automatically
editing them as sprinkling gfp.h and slab.h inclusions around .h
files could easily lead to inclusion dependency hell. Most gfp.h
inclusion directives were ignored as stuff from gfp.h was usually
wildly available and often used in preprocessor macros. Each
slab.h inclusion directive was examined and added manually as
necessary.
6. percpu.h was updated not to include slab.h.
7. Build test were done on the following configurations and failures
were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my
distributed build env didn't work with gcov compiles) and a few
more options had to be turned off depending on archs to make things
build (like ipr on powerpc/64 which failed due to missing writeq).
* x86 and x86_64 UP and SMP allmodconfig and a custom test config.
* powerpc and powerpc64 SMP allmodconfig
* sparc and sparc64 SMP allmodconfig
* ia64 SMP allmodconfig
* s390 SMP allmodconfig
* alpha SMP allmodconfig
* um on x86_64 SMP allmodconfig
8. percpu.h modifications were reverted so that it could be applied as
a separate patch and serve as bisection point.
Given the fact that I had only a couple of failures from tests on step
6, I'm fairly confident about the coverage of this conversion patch.
If there is a breakage, it's likely to be something in one of the arch
headers which should be easily discoverable easily on most builds of
the specific arch.
Signed-off-by: Tejun Heo <tj@kernel.org>
Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 09:04:11 +01:00
|
|
|
#include <linux/slab.h>
|
2009-10-06 20:31:08 +02:00
|
|
|
#include <linux/file.h>
|
2012-07-31 20:27:36 +02:00
|
|
|
#include <linux/mount.h>
|
2009-10-06 20:31:08 +02:00
|
|
|
#include <linux/namei.h>
|
|
|
|
#include <linux/writeback.h>
|
|
|
|
|
|
|
|
#include "super.h"
|
|
|
|
#include "mds_client.h"
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Ceph file operations
|
|
|
|
*
|
|
|
|
* Implement basic open/close functionality, and implement
|
|
|
|
* read/write.
|
|
|
|
*
|
|
|
|
* We implement three modes of file I/O:
|
|
|
|
* - buffered uses the generic_file_aio_{read,write} helpers
|
|
|
|
*
|
|
|
|
* - synchronous is used when there is multi-client read/write
|
|
|
|
* sharing, avoids the page cache, and synchronously waits for an
|
|
|
|
* ack from the OSD.
|
|
|
|
*
|
|
|
|
* - direct io takes the variant of the sync path that references
|
|
|
|
* user pages directly.
|
|
|
|
*
|
|
|
|
* fsync() flushes and waits on dirty pages, but just queues metadata
|
|
|
|
* for writeback: since the MDS can recover size and mtime there is no
|
|
|
|
* need to wait for MDS acknowledgement.
|
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Prepare an open request. Preallocate ceph_cap to avoid an
|
|
|
|
* inopportune ENOMEM later.
|
|
|
|
*/
|
|
|
|
static struct ceph_mds_request *
|
|
|
|
prepare_open_request(struct super_block *sb, int flags, int create_mode)
|
|
|
|
{
|
2010-04-07 00:14:15 +02:00
|
|
|
struct ceph_fs_client *fsc = ceph_sb_to_client(sb);
|
|
|
|
struct ceph_mds_client *mdsc = fsc->mdsc;
|
2009-10-06 20:31:08 +02:00
|
|
|
struct ceph_mds_request *req;
|
|
|
|
int want_auth = USE_ANY_MDS;
|
|
|
|
int op = (flags & O_CREAT) ? CEPH_MDS_OP_CREATE : CEPH_MDS_OP_OPEN;
|
|
|
|
|
|
|
|
if (flags & (O_WRONLY|O_RDWR|O_CREAT|O_TRUNC))
|
|
|
|
want_auth = USE_AUTH_MDS;
|
|
|
|
|
|
|
|
req = ceph_mdsc_create_request(mdsc, op, want_auth);
|
|
|
|
if (IS_ERR(req))
|
|
|
|
goto out;
|
|
|
|
req->r_fmode = ceph_flags_to_mode(flags);
|
|
|
|
req->r_args.open.flags = cpu_to_le32(flags);
|
|
|
|
req->r_args.open.mode = cpu_to_le32(create_mode);
|
|
|
|
out:
|
|
|
|
return req;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* initialize private struct file data.
|
|
|
|
* if we fail, clean up by dropping fmode reference on the ceph_inode
|
|
|
|
*/
|
|
|
|
static int ceph_init_file(struct inode *inode, struct file *file, int fmode)
|
|
|
|
{
|
|
|
|
struct ceph_file_info *cf;
|
|
|
|
int ret = 0;
|
|
|
|
|
|
|
|
switch (inode->i_mode & S_IFMT) {
|
|
|
|
case S_IFREG:
|
|
|
|
case S_IFDIR:
|
|
|
|
dout("init_file %p %p 0%o (regular)\n", inode, file,
|
|
|
|
inode->i_mode);
|
|
|
|
cf = kmem_cache_alloc(ceph_file_cachep, GFP_NOFS | __GFP_ZERO);
|
|
|
|
if (cf == NULL) {
|
|
|
|
ceph_put_fmode(ceph_inode(inode), fmode); /* clean up */
|
|
|
|
return -ENOMEM;
|
|
|
|
}
|
|
|
|
cf->fmode = fmode;
|
|
|
|
cf->next_offset = 2;
|
|
|
|
file->private_data = cf;
|
|
|
|
BUG_ON(inode->i_fop->release != ceph_release);
|
|
|
|
break;
|
|
|
|
|
|
|
|
case S_IFLNK:
|
|
|
|
dout("init_file %p %p 0%o (symlink)\n", inode, file,
|
|
|
|
inode->i_mode);
|
|
|
|
ceph_put_fmode(ceph_inode(inode), fmode); /* clean up */
|
|
|
|
break;
|
|
|
|
|
|
|
|
default:
|
|
|
|
dout("init_file %p %p 0%o (special)\n", inode, file,
|
|
|
|
inode->i_mode);
|
|
|
|
/*
|
|
|
|
* we need to drop the open ref now, since we don't
|
|
|
|
* have .release set to ceph_release.
|
|
|
|
*/
|
|
|
|
ceph_put_fmode(ceph_inode(inode), fmode); /* clean up */
|
|
|
|
BUG_ON(inode->i_fop->release == ceph_release);
|
|
|
|
|
|
|
|
/* call the proper open fop */
|
|
|
|
ret = inode->i_fop->open(inode, file);
|
|
|
|
}
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* If we already have the requisite capabilities, we can satisfy
|
|
|
|
* the open request locally (no need to request new caps from the
|
|
|
|
* MDS). We do, however, need to inform the MDS (asynchronously)
|
|
|
|
* if our wanted caps set expands.
|
|
|
|
*/
|
|
|
|
int ceph_open(struct inode *inode, struct file *file)
|
|
|
|
{
|
|
|
|
struct ceph_inode_info *ci = ceph_inode(inode);
|
2010-04-07 00:14:15 +02:00
|
|
|
struct ceph_fs_client *fsc = ceph_sb_to_client(inode->i_sb);
|
|
|
|
struct ceph_mds_client *mdsc = fsc->mdsc;
|
2009-10-06 20:31:08 +02:00
|
|
|
struct ceph_mds_request *req;
|
|
|
|
struct ceph_file_info *cf = file->private_data;
|
2011-07-26 20:30:29 +02:00
|
|
|
struct inode *parent_inode = NULL;
|
2009-10-06 20:31:08 +02:00
|
|
|
int err;
|
|
|
|
int flags, fmode, wanted;
|
|
|
|
|
|
|
|
if (cf) {
|
|
|
|
dout("open file %p is already opened\n", file);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* filter out O_CREAT|O_EXCL; vfs did that already. yuck. */
|
|
|
|
flags = file->f_flags & ~(O_CREAT|O_EXCL);
|
|
|
|
if (S_ISDIR(inode->i_mode))
|
|
|
|
flags = O_DIRECTORY; /* mds likes to know */
|
|
|
|
|
|
|
|
dout("open inode %p ino %llx.%llx file %p flags %d (%d)\n", inode,
|
|
|
|
ceph_vinop(inode), file, flags, file->f_flags);
|
|
|
|
fmode = ceph_flags_to_mode(flags);
|
|
|
|
wanted = ceph_caps_for_mode(fmode);
|
|
|
|
|
|
|
|
/* snapped files are read-only */
|
|
|
|
if (ceph_snap(inode) != CEPH_NOSNAP && (file->f_mode & FMODE_WRITE))
|
|
|
|
return -EROFS;
|
|
|
|
|
|
|
|
/* trivially open snapdir */
|
|
|
|
if (ceph_snap(inode) == CEPH_SNAPDIR) {
|
2011-11-30 18:47:09 +01:00
|
|
|
spin_lock(&ci->i_ceph_lock);
|
2009-10-06 20:31:08 +02:00
|
|
|
__ceph_get_fmode(ci, fmode);
|
2011-11-30 18:47:09 +01:00
|
|
|
spin_unlock(&ci->i_ceph_lock);
|
2009-10-06 20:31:08 +02:00
|
|
|
return ceph_init_file(inode, file, fmode);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
2010-11-07 18:07:15 +01:00
|
|
|
* No need to block if we have caps on the auth MDS (for
|
|
|
|
* write) or any MDS (for read). Update wanted set
|
2009-10-06 20:31:08 +02:00
|
|
|
* asynchronously.
|
|
|
|
*/
|
2011-11-30 18:47:09 +01:00
|
|
|
spin_lock(&ci->i_ceph_lock);
|
2010-11-07 18:07:15 +01:00
|
|
|
if (__ceph_is_any_real_caps(ci) &&
|
|
|
|
(((fmode & CEPH_FILE_MODE_WR) == 0) || ci->i_auth_cap)) {
|
2009-10-06 20:31:08 +02:00
|
|
|
int mds_wanted = __ceph_caps_mds_wanted(ci);
|
|
|
|
int issued = __ceph_caps_issued(ci, NULL);
|
|
|
|
|
|
|
|
dout("open %p fmode %d want %s issued %s using existing\n",
|
|
|
|
inode, fmode, ceph_cap_string(wanted),
|
|
|
|
ceph_cap_string(issued));
|
|
|
|
__ceph_get_fmode(ci, fmode);
|
2011-11-30 18:47:09 +01:00
|
|
|
spin_unlock(&ci->i_ceph_lock);
|
2009-10-06 20:31:08 +02:00
|
|
|
|
|
|
|
/* adjust wanted? */
|
|
|
|
if ((issued & wanted) != wanted &&
|
|
|
|
(mds_wanted & wanted) != wanted &&
|
|
|
|
ceph_snap(inode) != CEPH_SNAPDIR)
|
|
|
|
ceph_check_caps(ci, 0, NULL);
|
|
|
|
|
|
|
|
return ceph_init_file(inode, file, fmode);
|
|
|
|
} else if (ceph_snap(inode) != CEPH_NOSNAP &&
|
|
|
|
(ci->i_snap_caps & wanted) == wanted) {
|
|
|
|
__ceph_get_fmode(ci, fmode);
|
2011-11-30 18:47:09 +01:00
|
|
|
spin_unlock(&ci->i_ceph_lock);
|
2009-10-06 20:31:08 +02:00
|
|
|
return ceph_init_file(inode, file, fmode);
|
|
|
|
}
|
2011-11-30 18:47:09 +01:00
|
|
|
spin_unlock(&ci->i_ceph_lock);
|
2009-10-06 20:31:08 +02:00
|
|
|
|
|
|
|
dout("open fmode %d wants %s\n", fmode, ceph_cap_string(wanted));
|
|
|
|
req = prepare_open_request(inode->i_sb, flags, 0);
|
|
|
|
if (IS_ERR(req)) {
|
|
|
|
err = PTR_ERR(req);
|
|
|
|
goto out;
|
|
|
|
}
|
2011-05-27 18:24:26 +02:00
|
|
|
req->r_inode = inode;
|
|
|
|
ihold(inode);
|
2009-10-06 20:31:08 +02:00
|
|
|
req->r_num_caps = 1;
|
2011-07-26 20:30:29 +02:00
|
|
|
if (flags & (O_CREAT|O_TRUNC))
|
|
|
|
parent_inode = ceph_get_dentry_parent_inode(file->f_dentry);
|
2009-10-06 20:31:08 +02:00
|
|
|
err = ceph_mdsc_do_request(mdsc, parent_inode, req);
|
2011-07-26 20:30:29 +02:00
|
|
|
iput(parent_inode);
|
2009-10-06 20:31:08 +02:00
|
|
|
if (!err)
|
|
|
|
err = ceph_init_file(inode, file, req->r_fmode);
|
|
|
|
ceph_mdsc_put_request(req);
|
|
|
|
dout("open result=%d on %llx.%llx\n", err, ceph_vinop(inode));
|
|
|
|
out:
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
/*
|
2012-07-31 20:27:36 +02:00
|
|
|
* Do a lookup + open with a single request. If we get a non-existent
|
|
|
|
* file or symlink, return 1 so the VFS can retry.
|
2009-10-06 20:31:08 +02:00
|
|
|
*/
|
2012-07-31 20:27:36 +02:00
|
|
|
int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
|
2012-06-22 10:40:19 +02:00
|
|
|
struct file *file, unsigned flags, umode_t mode,
|
2012-06-22 10:39:14 +02:00
|
|
|
int *opened)
|
2009-10-06 20:31:08 +02:00
|
|
|
{
|
2010-04-07 00:14:15 +02:00
|
|
|
struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb);
|
|
|
|
struct ceph_mds_client *mdsc = fsc->mdsc;
|
2009-10-06 20:31:08 +02:00
|
|
|
struct ceph_mds_request *req;
|
2012-07-31 20:27:36 +02:00
|
|
|
struct dentry *dn;
|
2009-10-06 20:31:08 +02:00
|
|
|
int err;
|
|
|
|
|
2012-07-31 20:27:36 +02:00
|
|
|
dout("atomic_open %p dentry %p '%.*s' %s flags %d mode 0%o\n",
|
|
|
|
dir, dentry, dentry->d_name.len, dentry->d_name.name,
|
|
|
|
d_unhashed(dentry) ? "unhashed" : "hashed", flags, mode);
|
|
|
|
|
|
|
|
if (dentry->d_name.len > NAME_MAX)
|
|
|
|
return -ENAMETOOLONG;
|
|
|
|
|
|
|
|
err = ceph_init_dentry(dentry);
|
|
|
|
if (err < 0)
|
|
|
|
return err;
|
2009-10-06 20:31:08 +02:00
|
|
|
|
|
|
|
/* do the open */
|
|
|
|
req = prepare_open_request(dir->i_sb, flags, mode);
|
|
|
|
if (IS_ERR(req))
|
2012-06-22 10:39:14 +02:00
|
|
|
return PTR_ERR(req);
|
2009-10-06 20:31:08 +02:00
|
|
|
req->r_dentry = dget(dentry);
|
|
|
|
req->r_num_caps = 2;
|
|
|
|
if (flags & O_CREAT) {
|
|
|
|
req->r_dentry_drop = CEPH_CAP_FILE_SHARED;
|
|
|
|
req->r_dentry_unless = CEPH_CAP_FILE_EXCL;
|
|
|
|
}
|
|
|
|
req->r_locked_dir = dir; /* caller holds dir->i_mutex */
|
2011-07-26 20:27:48 +02:00
|
|
|
err = ceph_mdsc_do_request(mdsc,
|
|
|
|
(flags & (O_CREAT|O_TRUNC)) ? dir : NULL,
|
|
|
|
req);
|
2012-12-19 20:44:23 +01:00
|
|
|
if (err)
|
|
|
|
goto out_err;
|
|
|
|
|
2011-07-26 20:28:11 +02:00
|
|
|
err = ceph_handle_snapdir(req, dentry, err);
|
2012-07-31 20:27:36 +02:00
|
|
|
if (err == 0 && (flags & O_CREAT) && !req->r_reply_info.head->is_dentry)
|
2009-10-06 20:31:08 +02:00
|
|
|
err = ceph_handle_notrace_create(dir, dentry);
|
2012-06-05 15:10:25 +02:00
|
|
|
|
2012-07-31 20:27:36 +02:00
|
|
|
if (d_unhashed(dentry)) {
|
|
|
|
dn = ceph_finish_lookup(req, dentry, err);
|
|
|
|
if (IS_ERR(dn))
|
|
|
|
err = PTR_ERR(dn);
|
|
|
|
} else {
|
|
|
|
/* we were given a hashed negative dentry */
|
|
|
|
dn = NULL;
|
|
|
|
}
|
|
|
|
if (err)
|
|
|
|
goto out_err;
|
|
|
|
if (dn || dentry->d_inode == NULL || S_ISLNK(dentry->d_inode->i_mode)) {
|
|
|
|
/* make vfs retry on splice, ENOENT, or symlink */
|
|
|
|
dout("atomic_open finish_no_open on dn %p\n", dn);
|
|
|
|
err = finish_no_open(file, dn);
|
|
|
|
} else {
|
|
|
|
dout("atomic_open finish_open on dn %p\n", dn);
|
2012-12-28 18:56:46 +01:00
|
|
|
if (req->r_op == CEPH_MDS_OP_CREATE && req->r_reply_info.has_create_ino) {
|
|
|
|
*opened |= FILE_CREATED;
|
|
|
|
}
|
2012-07-31 20:27:36 +02:00
|
|
|
err = finish_open(file, dentry, ceph_open, opened);
|
|
|
|
}
|
2012-06-05 15:10:25 +02:00
|
|
|
|
2012-07-31 20:27:36 +02:00
|
|
|
out_err:
|
|
|
|
ceph_mdsc_put_request(req);
|
|
|
|
dout("atomic_open result=%d\n", err);
|
2012-06-22 10:39:14 +02:00
|
|
|
return err;
|
2009-10-06 20:31:08 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
int ceph_release(struct inode *inode, struct file *file)
|
|
|
|
{
|
|
|
|
struct ceph_inode_info *ci = ceph_inode(inode);
|
|
|
|
struct ceph_file_info *cf = file->private_data;
|
|
|
|
|
|
|
|
dout("release inode %p file %p\n", inode, file);
|
|
|
|
ceph_put_fmode(ci, cf->fmode);
|
|
|
|
if (cf->last_readdir)
|
|
|
|
ceph_mdsc_put_request(cf->last_readdir);
|
|
|
|
kfree(cf->last_name);
|
|
|
|
kfree(cf->dir_info);
|
|
|
|
dput(cf->dentry);
|
|
|
|
kmem_cache_free(ceph_file_cachep, cf);
|
2010-03-01 18:57:54 +01:00
|
|
|
|
|
|
|
/* wake up anyone waiting for caps on this inode */
|
2010-07-27 22:11:08 +02:00
|
|
|
wake_up_all(&ci->i_cap_wq);
|
2009-10-06 20:31:08 +02:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Read a range of bytes striped over one or more objects. Iterate over
|
|
|
|
* objects we stripe over. (That's not atomic, but good enough for now.)
|
|
|
|
*
|
|
|
|
* If we get a short result from the OSD, check against i_size; we need to
|
|
|
|
* only return a short read to the caller if we hit EOF.
|
|
|
|
*/
|
|
|
|
static int striped_read(struct inode *inode,
|
|
|
|
u64 off, u64 len,
|
2010-02-09 23:04:02 +01:00
|
|
|
struct page **pages, int num_pages,
|
2011-06-02 01:08:44 +02:00
|
|
|
int *checkeof, bool o_direct,
|
2010-12-16 05:41:54 +01:00
|
|
|
unsigned long buf_align)
|
2009-10-06 20:31:08 +02:00
|
|
|
{
|
2010-04-07 00:14:15 +02:00
|
|
|
struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
|
2009-10-06 20:31:08 +02:00
|
|
|
struct ceph_inode_info *ci = ceph_inode(inode);
|
|
|
|
u64 pos, this_len;
|
2010-11-09 21:43:12 +01:00
|
|
|
int io_align, page_align;
|
2009-10-06 20:31:08 +02:00
|
|
|
int left, pages_left;
|
|
|
|
int read;
|
|
|
|
struct page **page_pos;
|
|
|
|
int ret;
|
|
|
|
bool hit_stripe, was_short;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* we may need to do multiple reads. not atomic, unfortunately.
|
|
|
|
*/
|
|
|
|
pos = off;
|
|
|
|
left = len;
|
|
|
|
page_pos = pages;
|
|
|
|
pages_left = num_pages;
|
|
|
|
read = 0;
|
2010-11-09 21:43:12 +01:00
|
|
|
io_align = off & ~PAGE_MASK;
|
2009-10-06 20:31:08 +02:00
|
|
|
|
|
|
|
more:
|
2011-06-02 01:08:44 +02:00
|
|
|
if (o_direct)
|
2010-12-16 05:41:54 +01:00
|
|
|
page_align = (pos - io_align + buf_align) & ~PAGE_MASK;
|
2010-11-09 21:43:12 +01:00
|
|
|
else
|
|
|
|
page_align = pos & ~PAGE_MASK;
|
2009-10-06 20:31:08 +02:00
|
|
|
this_len = left;
|
2010-04-07 00:14:15 +02:00
|
|
|
ret = ceph_osdc_readpages(&fsc->client->osdc, ceph_vino(inode),
|
2009-10-06 20:31:08 +02:00
|
|
|
&ci->i_layout, pos, &this_len,
|
|
|
|
ci->i_truncate_seq,
|
|
|
|
ci->i_truncate_size,
|
2010-11-09 21:43:12 +01:00
|
|
|
page_pos, pages_left, page_align);
|
2009-10-06 20:31:08 +02:00
|
|
|
if (ret == -ENOENT)
|
|
|
|
ret = 0;
|
2011-06-08 05:40:35 +02:00
|
|
|
hit_stripe = this_len < left;
|
|
|
|
was_short = ret >= 0 && ret < this_len;
|
2009-10-06 20:31:08 +02:00
|
|
|
dout("striped_read %llu~%u (read %u) got %d%s%s\n", pos, left, read,
|
|
|
|
ret, hit_stripe ? " HITSTRIPE" : "", was_short ? " SHORT" : "");
|
|
|
|
|
|
|
|
if (ret > 0) {
|
2011-06-08 05:57:14 +02:00
|
|
|
int didpages = (page_align + ret) >> PAGE_CACHE_SHIFT;
|
2009-10-06 20:31:08 +02:00
|
|
|
|
|
|
|
if (read < pos - off) {
|
|
|
|
dout(" zero gap %llu to %llu\n", off + read, pos);
|
2011-06-08 05:57:14 +02:00
|
|
|
ceph_zero_page_vector_range(page_align + read,
|
2010-04-07 00:14:15 +02:00
|
|
|
pos - off - read, pages);
|
2009-10-06 20:31:08 +02:00
|
|
|
}
|
|
|
|
pos += ret;
|
|
|
|
read = pos - off;
|
|
|
|
left -= ret;
|
|
|
|
page_pos += didpages;
|
|
|
|
pages_left -= didpages;
|
|
|
|
|
|
|
|
/* hit stripe? */
|
|
|
|
if (left && hit_stripe)
|
|
|
|
goto more;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (was_short) {
|
2011-06-02 01:08:44 +02:00
|
|
|
/* did we bounce off eof? */
|
|
|
|
if (pos + left > inode->i_size)
|
|
|
|
*checkeof = 1;
|
|
|
|
|
|
|
|
/* zero trailing bytes (inside i_size) */
|
|
|
|
if (left > 0 && pos < inode->i_size) {
|
|
|
|
if (pos + left > inode->i_size)
|
|
|
|
left = inode->i_size - pos;
|
|
|
|
|
|
|
|
dout("zero tail %d\n", left);
|
2011-06-08 05:57:14 +02:00
|
|
|
ceph_zero_page_vector_range(page_align + read, left,
|
2010-04-07 00:14:15 +02:00
|
|
|
pages);
|
2011-06-02 01:08:44 +02:00
|
|
|
read += left;
|
2009-10-06 20:31:08 +02:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
if (ret >= 0)
|
|
|
|
ret = read;
|
|
|
|
dout("striped_read returns %d\n", ret);
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Completely synchronous read and write methods. Direct from __user
|
|
|
|
* buffer to osd, or directly to user pages (if O_DIRECT).
|
|
|
|
*
|
|
|
|
* If the read spans object boundary, just do multiple reads.
|
|
|
|
*/
|
|
|
|
static ssize_t ceph_sync_read(struct file *file, char __user *data,
|
2010-02-09 23:04:02 +01:00
|
|
|
unsigned len, loff_t *poff, int *checkeof)
|
2009-10-06 20:31:08 +02:00
|
|
|
{
|
|
|
|
struct inode *inode = file->f_dentry->d_inode;
|
|
|
|
struct page **pages;
|
|
|
|
u64 off = *poff;
|
2010-12-16 05:41:54 +01:00
|
|
|
int num_pages, ret;
|
2009-10-06 20:31:08 +02:00
|
|
|
|
|
|
|
dout("sync_read on file %p %llu~%u %s\n", file, off, len,
|
|
|
|
(file->f_flags & O_DIRECT) ? "O_DIRECT" : "");
|
|
|
|
|
2010-12-16 05:41:54 +01:00
|
|
|
if (file->f_flags & O_DIRECT) {
|
|
|
|
num_pages = calc_pages_for((unsigned long)data, len);
|
2010-12-16 05:45:41 +01:00
|
|
|
pages = ceph_get_direct_page_vector(data, num_pages, true);
|
2010-12-16 05:41:54 +01:00
|
|
|
} else {
|
|
|
|
num_pages = calc_pages_for(off, len);
|
2010-04-06 23:33:58 +02:00
|
|
|
pages = ceph_alloc_page_vector(num_pages, GFP_NOFS);
|
2010-12-16 05:41:54 +01:00
|
|
|
}
|
2009-10-06 20:31:08 +02:00
|
|
|
if (IS_ERR(pages))
|
|
|
|
return PTR_ERR(pages);
|
|
|
|
|
2010-11-09 21:24:53 +01:00
|
|
|
/*
|
|
|
|
* flush any page cache pages in this range. this
|
|
|
|
* will make concurrent normal and sync io slow,
|
|
|
|
* but it will at least behave sensibly when they are
|
|
|
|
* in sequence.
|
|
|
|
*/
|
2010-02-09 20:14:41 +01:00
|
|
|
ret = filemap_write_and_wait(inode->i_mapping);
|
|
|
|
if (ret < 0)
|
|
|
|
goto done;
|
|
|
|
|
2010-11-09 21:43:12 +01:00
|
|
|
ret = striped_read(inode, off, len, pages, num_pages, checkeof,
|
2010-12-16 05:41:54 +01:00
|
|
|
file->f_flags & O_DIRECT,
|
|
|
|
(unsigned long)data & ~PAGE_MASK);
|
2009-10-06 20:31:08 +02:00
|
|
|
|
|
|
|
if (ret >= 0 && (file->f_flags & O_DIRECT) == 0)
|
2010-04-07 00:14:15 +02:00
|
|
|
ret = ceph_copy_page_vector_to_user(pages, data, off, ret);
|
2009-10-06 20:31:08 +02:00
|
|
|
if (ret >= 0)
|
|
|
|
*poff = off + ret;
|
|
|
|
|
2010-02-09 20:14:41 +01:00
|
|
|
done:
|
2009-10-06 20:31:08 +02:00
|
|
|
if (file->f_flags & O_DIRECT)
|
2010-12-16 05:45:41 +01:00
|
|
|
ceph_put_page_vector(pages, num_pages, true);
|
2009-10-06 20:31:08 +02:00
|
|
|
else
|
|
|
|
ceph_release_page_vector(pages, num_pages);
|
|
|
|
dout("sync_read result %d\n", ret);
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Write commit callback, called if we requested both an ACK and
|
|
|
|
* ONDISK commit reply from the OSD.
|
|
|
|
*/
|
|
|
|
static void sync_write_commit(struct ceph_osd_request *req,
|
|
|
|
struct ceph_msg *msg)
|
|
|
|
{
|
|
|
|
struct ceph_inode_info *ci = ceph_inode(req->r_inode);
|
|
|
|
|
|
|
|
dout("sync_write_commit %p tid %llu\n", req, req->r_tid);
|
|
|
|
spin_lock(&ci->i_unsafe_lock);
|
|
|
|
list_del_init(&req->r_unsafe_item);
|
|
|
|
spin_unlock(&ci->i_unsafe_lock);
|
|
|
|
ceph_put_cap_refs(ci, CEPH_CAP_FILE_WR);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Synchronous write, straight from __user pointer or user pages (if
|
|
|
|
* O_DIRECT).
|
|
|
|
*
|
|
|
|
* If write spans object boundary, just do multiple writes. (For a
|
|
|
|
* correct atomic write, we should e.g. take write locks on all
|
|
|
|
* objects, rollback on failure, etc.)
|
|
|
|
*/
|
|
|
|
static ssize_t ceph_sync_write(struct file *file, const char __user *data,
|
|
|
|
size_t left, loff_t *offset)
|
|
|
|
{
|
|
|
|
struct inode *inode = file->f_dentry->d_inode;
|
|
|
|
struct ceph_inode_info *ci = ceph_inode(inode);
|
2010-04-07 00:14:15 +02:00
|
|
|
struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
|
2009-10-06 20:31:08 +02:00
|
|
|
struct ceph_osd_request *req;
|
|
|
|
struct page **pages;
|
|
|
|
int num_pages;
|
|
|
|
long long unsigned pos;
|
|
|
|
u64 len;
|
|
|
|
int written = 0;
|
|
|
|
int flags;
|
|
|
|
int do_sync = 0;
|
|
|
|
int check_caps = 0;
|
2010-11-09 21:43:12 +01:00
|
|
|
int page_align, io_align;
|
2010-12-16 05:41:54 +01:00
|
|
|
unsigned long buf_align;
|
2009-10-06 20:31:08 +02:00
|
|
|
int ret;
|
|
|
|
struct timespec mtime = CURRENT_TIME;
|
|
|
|
|
|
|
|
if (ceph_snap(file->f_dentry->d_inode) != CEPH_NOSNAP)
|
|
|
|
return -EROFS;
|
|
|
|
|
|
|
|
dout("sync_write on file %p %lld~%u %s\n", file, *offset,
|
|
|
|
(unsigned)left, (file->f_flags & O_DIRECT) ? "O_DIRECT" : "");
|
|
|
|
|
|
|
|
if (file->f_flags & O_APPEND)
|
|
|
|
pos = i_size_read(inode);
|
|
|
|
else
|
|
|
|
pos = *offset;
|
|
|
|
|
2010-02-09 20:14:41 +01:00
|
|
|
ret = filemap_write_and_wait_range(inode->i_mapping, pos, pos + left);
|
|
|
|
if (ret < 0)
|
|
|
|
return ret;
|
|
|
|
|
|
|
|
ret = invalidate_inode_pages2_range(inode->i_mapping,
|
|
|
|
pos >> PAGE_CACHE_SHIFT,
|
|
|
|
(pos + left) >> PAGE_CACHE_SHIFT);
|
|
|
|
if (ret < 0)
|
|
|
|
dout("invalidate_inode_pages2_range returned %d\n", ret);
|
|
|
|
|
2009-10-06 20:31:08 +02:00
|
|
|
flags = CEPH_OSD_FLAG_ORDERSNAP |
|
|
|
|
CEPH_OSD_FLAG_ONDISK |
|
|
|
|
CEPH_OSD_FLAG_WRITE;
|
|
|
|
if ((file->f_flags & (O_SYNC|O_DIRECT)) == 0)
|
|
|
|
flags |= CEPH_OSD_FLAG_ACK;
|
|
|
|
else
|
|
|
|
do_sync = 1;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* we may need to do multiple writes here if we span an object
|
|
|
|
* boundary. this isn't atomic, unfortunately. :(
|
|
|
|
*/
|
|
|
|
more:
|
2011-06-14 01:22:18 +02:00
|
|
|
io_align = pos & ~PAGE_MASK;
|
|
|
|
buf_align = (unsigned long)data & ~PAGE_MASK;
|
2009-10-06 20:31:08 +02:00
|
|
|
len = left;
|
2010-12-16 05:41:54 +01:00
|
|
|
if (file->f_flags & O_DIRECT) {
|
2010-11-09 21:43:12 +01:00
|
|
|
/* write from beginning of first page, regardless of
|
|
|
|
io alignment */
|
2010-12-16 05:41:54 +01:00
|
|
|
page_align = (pos - io_align + buf_align) & ~PAGE_MASK;
|
|
|
|
num_pages = calc_pages_for((unsigned long)data, len);
|
|
|
|
} else {
|
2010-11-09 21:43:12 +01:00
|
|
|
page_align = pos & ~PAGE_MASK;
|
2010-12-16 05:41:54 +01:00
|
|
|
num_pages = calc_pages_for(pos, len);
|
|
|
|
}
|
2010-04-07 00:14:15 +02:00
|
|
|
req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout,
|
2009-10-06 20:31:08 +02:00
|
|
|
ceph_vino(inode), pos, &len,
|
|
|
|
CEPH_OSD_OP_WRITE, flags,
|
|
|
|
ci->i_snap_realm->cached_context,
|
|
|
|
do_sync,
|
|
|
|
ci->i_truncate_seq, ci->i_truncate_size,
|
2010-11-09 21:43:12 +01:00
|
|
|
&mtime, false, 2, page_align);
|
2012-09-25 06:01:02 +02:00
|
|
|
if (IS_ERR(req))
|
|
|
|
return PTR_ERR(req);
|
2009-10-06 20:31:08 +02:00
|
|
|
|
|
|
|
if (file->f_flags & O_DIRECT) {
|
2010-12-16 05:45:41 +01:00
|
|
|
pages = ceph_get_direct_page_vector(data, num_pages, false);
|
2009-10-06 20:31:08 +02:00
|
|
|
if (IS_ERR(pages)) {
|
|
|
|
ret = PTR_ERR(pages);
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* throw out any page cache pages in this range. this
|
|
|
|
* may block.
|
|
|
|
*/
|
2010-08-03 19:25:11 +02:00
|
|
|
truncate_inode_pages_range(inode->i_mapping, pos,
|
2010-04-22 22:48:59 +02:00
|
|
|
(pos+len) | (PAGE_CACHE_SIZE-1));
|
2009-10-06 20:31:08 +02:00
|
|
|
} else {
|
2010-04-06 23:33:58 +02:00
|
|
|
pages = ceph_alloc_page_vector(num_pages, GFP_NOFS);
|
2009-10-06 20:31:08 +02:00
|
|
|
if (IS_ERR(pages)) {
|
|
|
|
ret = PTR_ERR(pages);
|
|
|
|
goto out;
|
|
|
|
}
|
2010-04-07 00:14:15 +02:00
|
|
|
ret = ceph_copy_user_to_page_vector(pages, data, pos, len);
|
2009-10-06 20:31:08 +02:00
|
|
|
if (ret < 0) {
|
|
|
|
ceph_release_page_vector(pages, num_pages);
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
if ((file->f_flags & O_SYNC) == 0) {
|
|
|
|
/* get a second commit callback */
|
|
|
|
req->r_safe_callback = sync_write_commit;
|
|
|
|
req->r_own_pages = 1;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
req->r_pages = pages;
|
|
|
|
req->r_num_pages = num_pages;
|
|
|
|
req->r_inode = inode;
|
|
|
|
|
2010-04-07 00:14:15 +02:00
|
|
|
ret = ceph_osdc_start_request(&fsc->client->osdc, req, false);
|
2009-10-06 20:31:08 +02:00
|
|
|
if (!ret) {
|
|
|
|
if (req->r_safe_callback) {
|
|
|
|
/*
|
|
|
|
* Add to inode unsafe list only after we
|
|
|
|
* start_request so that a tid has been assigned.
|
|
|
|
*/
|
|
|
|
spin_lock(&ci->i_unsafe_lock);
|
2011-03-15 10:18:02 +01:00
|
|
|
list_add_tail(&req->r_unsafe_item,
|
|
|
|
&ci->i_unsafe_writes);
|
2009-10-06 20:31:08 +02:00
|
|
|
spin_unlock(&ci->i_unsafe_lock);
|
|
|
|
ceph_get_cap_refs(ci, CEPH_CAP_FILE_WR);
|
|
|
|
}
|
2011-03-15 10:18:01 +01:00
|
|
|
|
2010-04-07 00:14:15 +02:00
|
|
|
ret = ceph_osdc_wait_request(&fsc->client->osdc, req);
|
2011-03-15 10:18:01 +01:00
|
|
|
if (ret < 0 && req->r_safe_callback) {
|
|
|
|
spin_lock(&ci->i_unsafe_lock);
|
|
|
|
list_del_init(&req->r_unsafe_item);
|
|
|
|
spin_unlock(&ci->i_unsafe_lock);
|
|
|
|
ceph_put_cap_refs(ci, CEPH_CAP_FILE_WR);
|
|
|
|
}
|
2009-10-06 20:31:08 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
if (file->f_flags & O_DIRECT)
|
2010-12-16 05:45:41 +01:00
|
|
|
ceph_put_page_vector(pages, num_pages, false);
|
2009-10-06 20:31:08 +02:00
|
|
|
else if (file->f_flags & O_SYNC)
|
|
|
|
ceph_release_page_vector(pages, num_pages);
|
|
|
|
|
|
|
|
out:
|
|
|
|
ceph_osdc_put_request(req);
|
|
|
|
if (ret == 0) {
|
|
|
|
pos += len;
|
|
|
|
written += len;
|
|
|
|
left -= len;
|
2011-06-14 01:22:18 +02:00
|
|
|
data += written;
|
2009-10-06 20:31:08 +02:00
|
|
|
if (left)
|
|
|
|
goto more;
|
|
|
|
|
|
|
|
ret = written;
|
|
|
|
*offset = pos;
|
|
|
|
if (pos > i_size_read(inode))
|
|
|
|
check_caps = ceph_inode_set_size(inode, pos);
|
|
|
|
if (check_caps)
|
|
|
|
ceph_check_caps(ceph_inode(inode), CHECK_CAPS_AUTHONLY,
|
|
|
|
NULL);
|
|
|
|
}
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Wrap generic_file_aio_read with checks for cap bits on the inode.
|
|
|
|
* Atomically grab references, so that those bits are not released
|
|
|
|
* back to the MDS mid-read.
|
|
|
|
*
|
|
|
|
* Hmm, the sync read case isn't actually async... should it be?
|
|
|
|
*/
|
|
|
|
static ssize_t ceph_aio_read(struct kiocb *iocb, const struct iovec *iov,
|
|
|
|
unsigned long nr_segs, loff_t pos)
|
|
|
|
{
|
|
|
|
struct file *filp = iocb->ki_filp;
|
2010-05-27 19:40:43 +02:00
|
|
|
struct ceph_file_info *fi = filp->private_data;
|
2009-10-06 20:31:08 +02:00
|
|
|
loff_t *ppos = &iocb->ki_pos;
|
|
|
|
size_t len = iov->iov_len;
|
|
|
|
struct inode *inode = filp->f_dentry->d_inode;
|
|
|
|
struct ceph_inode_info *ci = ceph_inode(inode);
|
2010-06-12 01:58:48 +02:00
|
|
|
void __user *base = iov->iov_base;
|
2009-10-06 20:31:08 +02:00
|
|
|
ssize_t ret;
|
2010-05-27 19:40:43 +02:00
|
|
|
int want, got = 0;
|
2010-02-09 23:04:02 +01:00
|
|
|
int checkeof = 0, read = 0;
|
2009-10-06 20:31:08 +02:00
|
|
|
|
|
|
|
dout("aio_read %p %llx.%llx %llu~%u trying to get caps on %p\n",
|
|
|
|
inode, ceph_vinop(inode), pos, (unsigned)len, inode);
|
2010-02-09 23:04:02 +01:00
|
|
|
again:
|
2009-10-06 20:31:08 +02:00
|
|
|
__ceph_do_pending_vmtruncate(inode);
|
2010-05-27 19:40:43 +02:00
|
|
|
if (fi->fmode & CEPH_FILE_MODE_LAZY)
|
|
|
|
want = CEPH_CAP_FILE_CACHE | CEPH_CAP_FILE_LAZYIO;
|
|
|
|
else
|
|
|
|
want = CEPH_CAP_FILE_CACHE;
|
|
|
|
ret = ceph_get_caps(ci, CEPH_CAP_FILE_RD, want, &got, -1);
|
2009-10-06 20:31:08 +02:00
|
|
|
if (ret < 0)
|
|
|
|
goto out;
|
|
|
|
dout("aio_read %p %llx.%llx %llu~%u got cap refs on %s\n",
|
|
|
|
inode, ceph_vinop(inode), pos, (unsigned)len,
|
|
|
|
ceph_cap_string(got));
|
|
|
|
|
2010-05-27 19:40:43 +02:00
|
|
|
if ((got & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)) == 0 ||
|
2009-10-06 20:31:08 +02:00
|
|
|
(iocb->ki_filp->f_flags & O_DIRECT) ||
|
2011-07-26 20:26:07 +02:00
|
|
|
(inode->i_sb->s_flags & MS_SYNCHRONOUS) ||
|
|
|
|
(fi->flags & CEPH_F_SYNC))
|
2009-10-06 20:31:08 +02:00
|
|
|
/* hmm, this isn't really async... */
|
2010-02-09 23:04:02 +01:00
|
|
|
ret = ceph_sync_read(filp, base, len, ppos, &checkeof);
|
2009-10-06 20:31:08 +02:00
|
|
|
else
|
|
|
|
ret = generic_file_aio_read(iocb, iov, nr_segs, pos);
|
|
|
|
|
|
|
|
out:
|
|
|
|
dout("aio_read %p %llx.%llx dropping cap refs on %s = %d\n",
|
|
|
|
inode, ceph_vinop(inode), ceph_cap_string(got), (int)ret);
|
|
|
|
ceph_put_cap_refs(ci, got);
|
2010-02-09 23:04:02 +01:00
|
|
|
|
|
|
|
if (checkeof && ret >= 0) {
|
|
|
|
int statret = ceph_do_getattr(inode, CEPH_STAT_CAP_SIZE);
|
|
|
|
|
|
|
|
/* hit EOF or hole? */
|
|
|
|
if (statret == 0 && *ppos < inode->i_size) {
|
2011-06-02 01:08:44 +02:00
|
|
|
dout("aio_read sync_read hit hole, ppos %lld < size %lld, reading more\n", *ppos, inode->i_size);
|
2010-02-09 23:04:02 +01:00
|
|
|
read += ret;
|
|
|
|
base += ret;
|
|
|
|
len -= ret;
|
|
|
|
checkeof = 0;
|
|
|
|
goto again;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
if (ret >= 0)
|
|
|
|
ret += read;
|
|
|
|
|
2009-10-06 20:31:08 +02:00
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Take cap references to avoid releasing caps to MDS mid-write.
|
|
|
|
*
|
|
|
|
* If we are synchronous, and write with an old snap context, the OSD
|
|
|
|
* may return EOLDSNAPC. In that case, retry the write.. _after_
|
|
|
|
* dropping our cap refs and allowing the pending snap to logically
|
|
|
|
* complete _before_ this write occurs.
|
|
|
|
*
|
|
|
|
* If we are near ENOSPC, write synchronously.
|
|
|
|
*/
|
|
|
|
static ssize_t ceph_aio_write(struct kiocb *iocb, const struct iovec *iov,
|
|
|
|
unsigned long nr_segs, loff_t pos)
|
|
|
|
{
|
|
|
|
struct file *file = iocb->ki_filp;
|
2010-05-26 23:31:27 +02:00
|
|
|
struct ceph_file_info *fi = file->private_data;
|
2009-10-06 20:31:08 +02:00
|
|
|
struct inode *inode = file->f_dentry->d_inode;
|
|
|
|
struct ceph_inode_info *ci = ceph_inode(inode);
|
2010-04-07 00:14:15 +02:00
|
|
|
struct ceph_osd_client *osdc =
|
|
|
|
&ceph_sb_to_client(inode->i_sb)->client->osdc;
|
2009-10-06 20:31:08 +02:00
|
|
|
loff_t endoff = pos + iov->iov_len;
|
2012-11-05 20:07:23 +01:00
|
|
|
int got = 0;
|
|
|
|
int ret, err, written;
|
2009-10-06 20:31:08 +02:00
|
|
|
|
|
|
|
if (ceph_snap(inode) != CEPH_NOSNAP)
|
|
|
|
return -EROFS;
|
|
|
|
|
|
|
|
retry_snap:
|
2012-11-05 20:07:23 +01:00
|
|
|
written = 0;
|
2009-10-06 20:31:08 +02:00
|
|
|
if (ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL))
|
|
|
|
return -ENOSPC;
|
|
|
|
__ceph_do_pending_vmtruncate(inode);
|
|
|
|
|
2012-11-05 20:07:23 +01:00
|
|
|
/*
|
|
|
|
* try to do a buffered write. if we don't have sufficient
|
|
|
|
* caps, we'll get -EAGAIN from generic_file_aio_write, or a
|
|
|
|
* short write if we only get caps for some pages.
|
|
|
|
*/
|
|
|
|
if (!(iocb->ki_filp->f_flags & O_DIRECT) &&
|
|
|
|
!(inode->i_sb->s_flags & MS_SYNCHRONOUS) &&
|
|
|
|
!(fi->flags & CEPH_F_SYNC)) {
|
2011-07-26 20:27:34 +02:00
|
|
|
ret = generic_file_aio_write(iocb, iov, nr_segs, pos);
|
2012-11-05 20:07:23 +01:00
|
|
|
if (ret >= 0)
|
|
|
|
written = ret;
|
|
|
|
|
2009-10-06 20:31:08 +02:00
|
|
|
if ((ret >= 0 || ret == -EIOCBQUEUED) &&
|
|
|
|
((file->f_flags & O_SYNC) || IS_SYNC(file->f_mapping->host)
|
2010-02-23 19:16:23 +01:00
|
|
|
|| ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_NEARFULL))) {
|
2012-11-05 20:07:23 +01:00
|
|
|
err = vfs_fsync_range(file, pos, pos + written - 1, 1);
|
2010-02-23 19:16:23 +01:00
|
|
|
if (err < 0)
|
|
|
|
ret = err;
|
|
|
|
}
|
2012-11-05 20:07:23 +01:00
|
|
|
if ((ret < 0 && ret != -EAGAIN) || pos + written >= endoff)
|
|
|
|
goto out;
|
|
|
|
}
|
2011-07-26 20:27:34 +02:00
|
|
|
|
2012-11-05 20:07:23 +01:00
|
|
|
dout("aio_write %p %llx.%llx %llu~%u getting caps. i_size %llu\n",
|
|
|
|
inode, ceph_vinop(inode), pos + written,
|
|
|
|
(unsigned)iov->iov_len - written, inode->i_size);
|
|
|
|
ret = ceph_get_caps(ci, CEPH_CAP_FILE_WR, 0, &got, endoff);
|
|
|
|
if (ret < 0)
|
2011-07-26 20:27:34 +02:00
|
|
|
goto out;
|
|
|
|
|
2012-11-05 20:07:23 +01:00
|
|
|
dout("aio_write %p %llx.%llx %llu~%u got cap refs on %s\n",
|
|
|
|
inode, ceph_vinop(inode), pos + written,
|
|
|
|
(unsigned)iov->iov_len - written, ceph_cap_string(got));
|
|
|
|
ret = ceph_sync_write(file, iov->iov_base + written,
|
|
|
|
iov->iov_len - written, &iocb->ki_pos);
|
2009-10-06 20:31:08 +02:00
|
|
|
if (ret >= 0) {
|
2011-05-04 20:33:47 +02:00
|
|
|
int dirty;
|
2011-11-30 18:47:09 +01:00
|
|
|
spin_lock(&ci->i_ceph_lock);
|
2011-05-04 20:33:47 +02:00
|
|
|
dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_FILE_WR);
|
2011-11-30 18:47:09 +01:00
|
|
|
spin_unlock(&ci->i_ceph_lock);
|
2011-05-04 20:33:47 +02:00
|
|
|
if (dirty)
|
|
|
|
__mark_inode_dirty(inode, dirty);
|
2009-10-06 20:31:08 +02:00
|
|
|
}
|
|
|
|
dout("aio_write %p %llx.%llx %llu~%u dropping cap refs on %s\n",
|
2012-11-05 20:07:23 +01:00
|
|
|
inode, ceph_vinop(inode), pos + written,
|
|
|
|
(unsigned)iov->iov_len - written, ceph_cap_string(got));
|
2009-10-06 20:31:08 +02:00
|
|
|
ceph_put_cap_refs(ci, got);
|
2011-07-26 20:27:34 +02:00
|
|
|
out:
|
2009-10-06 20:31:08 +02:00
|
|
|
if (ret == -EOLDSNAPC) {
|
|
|
|
dout("aio_write %p %llx.%llx %llu~%u got EOLDSNAPC, retrying\n",
|
|
|
|
inode, ceph_vinop(inode), pos, (unsigned)iov->iov_len);
|
|
|
|
goto retry_snap;
|
|
|
|
}
|
|
|
|
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* llseek. be sure to verify file size on SEEK_END.
|
|
|
|
*/
|
|
|
|
static loff_t ceph_llseek(struct file *file, loff_t offset, int origin)
|
|
|
|
{
|
|
|
|
struct inode *inode = file->f_mapping->host;
|
|
|
|
int ret;
|
|
|
|
|
|
|
|
mutex_lock(&inode->i_mutex);
|
|
|
|
__ceph_do_pending_vmtruncate(inode);
|
2011-12-13 18:19:26 +01:00
|
|
|
|
|
|
|
if (origin == SEEK_END || origin == SEEK_DATA || origin == SEEK_HOLE) {
|
2009-10-06 20:31:08 +02:00
|
|
|
ret = ceph_do_getattr(inode, CEPH_STAT_CAP_SIZE);
|
|
|
|
if (ret < 0) {
|
|
|
|
offset = ret;
|
|
|
|
goto out;
|
|
|
|
}
|
2011-07-18 19:21:38 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
switch (origin) {
|
|
|
|
case SEEK_END:
|
2009-10-06 20:31:08 +02:00
|
|
|
offset += inode->i_size;
|
|
|
|
break;
|
|
|
|
case SEEK_CUR:
|
|
|
|
/*
|
|
|
|
* Here we special-case the lseek(fd, 0, SEEK_CUR)
|
|
|
|
* position-querying operation. Avoid rewriting the "same"
|
|
|
|
* f_pos value back to the file because a concurrent read(),
|
|
|
|
* write() or lseek() might have altered it
|
|
|
|
*/
|
|
|
|
if (offset == 0) {
|
|
|
|
offset = file->f_pos;
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
offset += file->f_pos;
|
|
|
|
break;
|
2011-07-18 19:21:38 +02:00
|
|
|
case SEEK_DATA:
|
|
|
|
if (offset >= inode->i_size) {
|
|
|
|
ret = -ENXIO;
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
break;
|
|
|
|
case SEEK_HOLE:
|
|
|
|
if (offset >= inode->i_size) {
|
|
|
|
ret = -ENXIO;
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
offset = inode->i_size;
|
|
|
|
break;
|
2009-10-06 20:31:08 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
if (offset < 0 || offset > inode->i_sb->s_maxbytes) {
|
|
|
|
offset = -EINVAL;
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Special lock needed here? */
|
|
|
|
if (offset != file->f_pos) {
|
|
|
|
file->f_pos = offset;
|
|
|
|
file->f_version = 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
out:
|
|
|
|
mutex_unlock(&inode->i_mutex);
|
|
|
|
return offset;
|
|
|
|
}
|
|
|
|
|
|
|
|
const struct file_operations ceph_file_fops = {
|
|
|
|
.open = ceph_open,
|
|
|
|
.release = ceph_release,
|
|
|
|
.llseek = ceph_llseek,
|
|
|
|
.read = do_sync_read,
|
|
|
|
.write = do_sync_write,
|
|
|
|
.aio_read = ceph_aio_read,
|
|
|
|
.aio_write = ceph_aio_write,
|
|
|
|
.mmap = ceph_mmap,
|
|
|
|
.fsync = ceph_fsync,
|
2010-08-03 00:34:23 +02:00
|
|
|
.lock = ceph_lock,
|
|
|
|
.flock = ceph_flock,
|
2009-10-06 20:31:08 +02:00
|
|
|
.splice_read = generic_file_splice_read,
|
|
|
|
.splice_write = generic_file_splice_write,
|
|
|
|
.unlocked_ioctl = ceph_ioctl,
|
|
|
|
.compat_ioctl = ceph_ioctl,
|
|
|
|
};
|
|
|
|
|