2010-04-07 06:14:15 +08:00
|
|
|
#include <linux/ceph/ceph_debug.h>
|
2009-10-07 02:31:08 +08:00
|
|
|
|
2010-04-07 06:14:15 +08:00
|
|
|
#include <linux/module.h>
|
2009-10-07 02:31:08 +08:00
|
|
|
#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 16:04:11 +08:00
|
|
|
#include <linux/slab.h>
|
2009-10-07 02:31:08 +08:00
|
|
|
#include <linux/file.h>
|
2012-08-01 02:27:36 +08:00
|
|
|
#include <linux/mount.h>
|
2009-10-07 02:31:08 +08:00
|
|
|
#include <linux/namei.h>
|
|
|
|
#include <linux/writeback.h>
|
2013-05-08 07:19:08 +08:00
|
|
|
#include <linux/aio.h>
|
2013-08-15 11:51:44 +08:00
|
|
|
#include <linux/falloc.h>
|
2009-10-07 02:31:08 +08:00
|
|
|
|
|
|
|
#include "super.h"
|
|
|
|
#include "mds_client.h"
|
2013-08-22 05:29:54 +08:00
|
|
|
#include "cache.h"
|
2009-10-07 02:31:08 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* 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 06:14:15 +08:00
|
|
|
struct ceph_fs_client *fsc = ceph_sb_to_client(sb);
|
|
|
|
struct ceph_mds_client *mdsc = fsc->mdsc;
|
2009-10-07 02:31:08 +08:00
|
|
|
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;
|
2013-08-22 05:29:54 +08:00
|
|
|
struct ceph_inode_info *ci = ceph_inode(inode);
|
|
|
|
struct ceph_fs_client *fsc = ceph_sb_to_client(inode->i_sb);
|
|
|
|
struct ceph_mds_client *mdsc = fsc->mdsc;
|
2009-10-07 02:31:08 +08:00
|
|
|
|
|
|
|
switch (inode->i_mode & S_IFMT) {
|
|
|
|
case S_IFREG:
|
2013-08-22 05:29:54 +08:00
|
|
|
/* First file open request creates the cookie, we want to keep
|
|
|
|
* this cookie around for the filetime of the inode as not to
|
|
|
|
* have to worry about fscache register / revoke / operation
|
|
|
|
* races.
|
|
|
|
*
|
|
|
|
* Also, if we know the operation is going to invalidate data
|
|
|
|
* (non readonly) just nuke the cache right away.
|
|
|
|
*/
|
|
|
|
ceph_fscache_register_inode_cookie(mdsc->fsc, ci);
|
|
|
|
if ((fmode & CEPH_FILE_MODE_WR))
|
|
|
|
ceph_fscache_invalidate(inode);
|
2009-10-07 02:31:08 +08:00
|
|
|
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 06:14:15 +08:00
|
|
|
struct ceph_fs_client *fsc = ceph_sb_to_client(inode->i_sb);
|
|
|
|
struct ceph_mds_client *mdsc = fsc->mdsc;
|
2009-10-07 02:31:08 +08:00
|
|
|
struct ceph_mds_request *req;
|
|
|
|
struct ceph_file_info *cf = file->private_data;
|
2011-07-27 02:30:29 +08:00
|
|
|
struct inode *parent_inode = NULL;
|
2009-10-07 02:31:08 +08:00
|
|
|
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) {
|
2011-12-01 01:47:09 +08:00
|
|
|
spin_lock(&ci->i_ceph_lock);
|
2009-10-07 02:31:08 +08:00
|
|
|
__ceph_get_fmode(ci, fmode);
|
2011-12-01 01:47:09 +08:00
|
|
|
spin_unlock(&ci->i_ceph_lock);
|
2009-10-07 02:31:08 +08:00
|
|
|
return ceph_init_file(inode, file, fmode);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
2010-11-08 01:07:15 +08:00
|
|
|
* No need to block if we have caps on the auth MDS (for
|
|
|
|
* write) or any MDS (for read). Update wanted set
|
2009-10-07 02:31:08 +08:00
|
|
|
* asynchronously.
|
|
|
|
*/
|
2011-12-01 01:47:09 +08:00
|
|
|
spin_lock(&ci->i_ceph_lock);
|
2010-11-08 01:07:15 +08:00
|
|
|
if (__ceph_is_any_real_caps(ci) &&
|
|
|
|
(((fmode & CEPH_FILE_MODE_WR) == 0) || ci->i_auth_cap)) {
|
2009-10-07 02:31:08 +08:00
|
|
|
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);
|
2011-12-01 01:47:09 +08:00
|
|
|
spin_unlock(&ci->i_ceph_lock);
|
2009-10-07 02:31:08 +08:00
|
|
|
|
|
|
|
/* 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);
|
2011-12-01 01:47:09 +08:00
|
|
|
spin_unlock(&ci->i_ceph_lock);
|
2009-10-07 02:31:08 +08:00
|
|
|
return ceph_init_file(inode, file, fmode);
|
|
|
|
}
|
2013-08-22 05:29:54 +08:00
|
|
|
|
2011-12-01 01:47:09 +08:00
|
|
|
spin_unlock(&ci->i_ceph_lock);
|
2009-10-07 02:31:08 +08:00
|
|
|
|
|
|
|
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;
|
|
|
|
}
|
2011-05-28 00:24:26 +08:00
|
|
|
req->r_inode = inode;
|
|
|
|
ihold(inode);
|
2013-08-22 05:29:54 +08:00
|
|
|
|
2009-10-07 02:31:08 +08:00
|
|
|
req->r_num_caps = 1;
|
2013-02-06 05:52:29 +08:00
|
|
|
if (flags & O_CREAT)
|
2011-07-27 02:30:29 +08:00
|
|
|
parent_inode = ceph_get_dentry_parent_inode(file->f_dentry);
|
2009-10-07 02:31:08 +08:00
|
|
|
err = ceph_mdsc_do_request(mdsc, parent_inode, req);
|
2011-07-27 02:30:29 +08:00
|
|
|
iput(parent_inode);
|
2009-10-07 02:31:08 +08:00
|
|
|
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;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
/*
|
2012-08-01 02:27:36 +08:00
|
|
|
* Do a lookup + open with a single request. If we get a non-existent
|
|
|
|
* file or symlink, return 1 so the VFS can retry.
|
2009-10-07 02:31:08 +08:00
|
|
|
*/
|
2012-08-01 02:27:36 +08:00
|
|
|
int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
|
2012-06-22 16:40:19 +08:00
|
|
|
struct file *file, unsigned flags, umode_t mode,
|
2012-06-22 16:39:14 +08:00
|
|
|
int *opened)
|
2009-10-07 02:31:08 +08:00
|
|
|
{
|
2010-04-07 06:14:15 +08:00
|
|
|
struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb);
|
|
|
|
struct ceph_mds_client *mdsc = fsc->mdsc;
|
2009-10-07 02:31:08 +08:00
|
|
|
struct ceph_mds_request *req;
|
2012-08-01 02:27:36 +08:00
|
|
|
struct dentry *dn;
|
2009-10-07 02:31:08 +08:00
|
|
|
int err;
|
|
|
|
|
2012-08-01 02:27:36 +08:00
|
|
|
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;
|
2009-10-07 02:31:08 +08:00
|
|
|
|
|
|
|
/* do the open */
|
|
|
|
req = prepare_open_request(dir->i_sb, flags, mode);
|
|
|
|
if (IS_ERR(req))
|
2012-06-22 16:39:14 +08:00
|
|
|
return PTR_ERR(req);
|
2009-10-07 02:31:08 +08:00
|
|
|
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 */
|
2011-07-27 02:27:48 +08:00
|
|
|
err = ceph_mdsc_do_request(mdsc,
|
|
|
|
(flags & (O_CREAT|O_TRUNC)) ? dir : NULL,
|
|
|
|
req);
|
2012-12-20 03:44:23 +08:00
|
|
|
if (err)
|
|
|
|
goto out_err;
|
|
|
|
|
2011-07-27 02:28:11 +08:00
|
|
|
err = ceph_handle_snapdir(req, dentry, err);
|
2012-08-01 02:27:36 +08:00
|
|
|
if (err == 0 && (flags & O_CREAT) && !req->r_reply_info.head->is_dentry)
|
2009-10-07 02:31:08 +08:00
|
|
|
err = ceph_handle_notrace_create(dir, dentry);
|
2012-06-05 21:10:25 +08:00
|
|
|
|
2012-08-01 02:27:36 +08:00
|
|
|
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);
|
2012-12-29 01:56:46 +08:00
|
|
|
if (req->r_op == CEPH_MDS_OP_CREATE && req->r_reply_info.has_create_ino) {
|
2014-02-11 12:55:05 +08:00
|
|
|
ceph_init_acl(dentry, dentry->d_inode, dir);
|
2012-12-29 01:56:46 +08:00
|
|
|
*opened |= FILE_CREATED;
|
|
|
|
}
|
2012-08-01 02:27:36 +08:00
|
|
|
err = finish_open(file, dentry, ceph_open, opened);
|
|
|
|
}
|
|
|
|
out_err:
|
2014-04-01 20:20:17 +08:00
|
|
|
if (!req->r_err && req->r_target_inode)
|
|
|
|
ceph_put_fmode(ceph_inode(req->r_target_inode), req->r_fmode);
|
2012-08-01 02:27:36 +08:00
|
|
|
ceph_mdsc_put_request(req);
|
|
|
|
dout("atomic_open result=%d\n", err);
|
2012-06-22 16:39:14 +08:00
|
|
|
return err;
|
2009-10-07 02:31:08 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
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);
|
2010-03-02 01:57:54 +08:00
|
|
|
|
|
|
|
/* wake up anyone waiting for caps on this inode */
|
2010-07-28 04:11:08 +08:00
|
|
|
wake_up_all(&ci->i_cap_wq);
|
2009-10-07 02:31:08 +08:00
|
|
|
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,
|
2010-02-10 06:04:02 +08:00
|
|
|
struct page **pages, int num_pages,
|
2011-06-02 07:08:44 +08:00
|
|
|
int *checkeof, bool o_direct,
|
2010-12-16 12:41:54 +08:00
|
|
|
unsigned long buf_align)
|
2009-10-07 02:31:08 +08:00
|
|
|
{
|
2010-04-07 06:14:15 +08:00
|
|
|
struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
|
2009-10-07 02:31:08 +08:00
|
|
|
struct ceph_inode_info *ci = ceph_inode(inode);
|
2013-07-23 21:48:01 +08:00
|
|
|
u64 pos, this_len, left;
|
2010-11-10 04:43:12 +08:00
|
|
|
int io_align, page_align;
|
2013-07-23 21:48:01 +08:00
|
|
|
int pages_left;
|
2009-10-07 02:31:08 +08:00
|
|
|
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;
|
2010-11-10 04:43:12 +08:00
|
|
|
io_align = off & ~PAGE_MASK;
|
2009-10-07 02:31:08 +08:00
|
|
|
|
|
|
|
more:
|
2011-06-02 07:08:44 +08:00
|
|
|
if (o_direct)
|
2010-12-16 12:41:54 +08:00
|
|
|
page_align = (pos - io_align + buf_align) & ~PAGE_MASK;
|
2010-11-10 04:43:12 +08:00
|
|
|
else
|
|
|
|
page_align = pos & ~PAGE_MASK;
|
2009-10-07 02:31:08 +08:00
|
|
|
this_len = left;
|
2010-04-07 06:14:15 +08:00
|
|
|
ret = ceph_osdc_readpages(&fsc->client->osdc, ceph_vino(inode),
|
2009-10-07 02:31:08 +08:00
|
|
|
&ci->i_layout, pos, &this_len,
|
|
|
|
ci->i_truncate_seq,
|
|
|
|
ci->i_truncate_size,
|
2010-11-10 04:43:12 +08:00
|
|
|
page_pos, pages_left, page_align);
|
2009-10-07 02:31:08 +08:00
|
|
|
if (ret == -ENOENT)
|
|
|
|
ret = 0;
|
2011-06-08 11:40:35 +08:00
|
|
|
hit_stripe = this_len < left;
|
|
|
|
was_short = ret >= 0 && ret < this_len;
|
2013-07-23 21:48:01 +08:00
|
|
|
dout("striped_read %llu~%llu (read %u) got %d%s%s\n", pos, left, read,
|
2009-10-07 02:31:08 +08:00
|
|
|
ret, hit_stripe ? " HITSTRIPE" : "", was_short ? " SHORT" : "");
|
|
|
|
|
2013-08-06 16:20:38 +08:00
|
|
|
if (ret >= 0) {
|
|
|
|
int didpages;
|
|
|
|
if (was_short && (pos + ret < inode->i_size)) {
|
|
|
|
u64 tmp = min(this_len - ret,
|
|
|
|
inode->i_size - pos - ret);
|
|
|
|
dout(" zero gap %llu to %llu\n",
|
|
|
|
pos + ret, pos + ret + tmp);
|
|
|
|
ceph_zero_page_vector_range(page_align + read + ret,
|
|
|
|
tmp, pages);
|
|
|
|
ret += tmp;
|
2009-10-07 02:31:08 +08:00
|
|
|
}
|
2013-08-06 16:20:38 +08:00
|
|
|
|
|
|
|
didpages = (page_align + ret) >> PAGE_CACHE_SHIFT;
|
2009-10-07 02:31:08 +08:00
|
|
|
pos += ret;
|
|
|
|
read = pos - off;
|
|
|
|
left -= ret;
|
|
|
|
page_pos += didpages;
|
|
|
|
pages_left -= didpages;
|
|
|
|
|
2013-08-06 16:20:38 +08:00
|
|
|
/* hit stripe and need continue*/
|
|
|
|
if (left && hit_stripe && pos < inode->i_size)
|
2009-10-07 02:31:08 +08:00
|
|
|
goto more;
|
|
|
|
}
|
|
|
|
|
2013-08-21 15:02:51 +08:00
|
|
|
if (read > 0) {
|
2013-08-06 16:20:38 +08:00
|
|
|
ret = read;
|
2011-06-02 07:08:44 +08:00
|
|
|
/* did we bounce off eof? */
|
|
|
|
if (pos + left > inode->i_size)
|
|
|
|
*checkeof = 1;
|
2009-10-07 02:31:08 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
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.
|
|
|
|
*/
|
2013-09-26 14:42:17 +08:00
|
|
|
static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *i,
|
|
|
|
int *checkeof)
|
2009-10-07 02:31:08 +08:00
|
|
|
{
|
2013-09-26 14:42:17 +08:00
|
|
|
struct file *file = iocb->ki_filp;
|
2013-01-24 06:07:38 +08:00
|
|
|
struct inode *inode = file_inode(file);
|
2009-10-07 02:31:08 +08:00
|
|
|
struct page **pages;
|
2013-09-26 14:42:17 +08:00
|
|
|
u64 off = iocb->ki_pos;
|
2010-12-16 12:41:54 +08:00
|
|
|
int num_pages, ret;
|
2013-09-26 14:42:17 +08:00
|
|
|
size_t len = i->count;
|
2009-10-07 02:31:08 +08:00
|
|
|
|
2013-09-26 14:42:17 +08:00
|
|
|
dout("sync_read on file %p %llu~%u %s\n", file, off,
|
|
|
|
(unsigned)len,
|
2009-10-07 02:31:08 +08:00
|
|
|
(file->f_flags & O_DIRECT) ? "O_DIRECT" : "");
|
2010-11-10 04:24:53 +08:00
|
|
|
/*
|
|
|
|
* 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.
|
|
|
|
*/
|
2013-09-26 14:42:17 +08:00
|
|
|
ret = filemap_write_and_wait_range(inode->i_mapping, off,
|
|
|
|
off + len);
|
2010-02-10 03:14:41 +08:00
|
|
|
if (ret < 0)
|
2013-09-26 14:42:17 +08:00
|
|
|
return ret;
|
2010-02-10 03:14:41 +08:00
|
|
|
|
2013-09-26 14:42:17 +08:00
|
|
|
if (file->f_flags & O_DIRECT) {
|
|
|
|
while (iov_iter_count(i)) {
|
|
|
|
void __user *data = i->iov[0].iov_base + i->iov_offset;
|
|
|
|
size_t len = i->iov[0].iov_len - i->iov_offset;
|
|
|
|
|
|
|
|
num_pages = calc_pages_for((unsigned long)data, len);
|
|
|
|
pages = ceph_get_direct_page_vector(data,
|
|
|
|
num_pages, true);
|
|
|
|
if (IS_ERR(pages))
|
|
|
|
return PTR_ERR(pages);
|
|
|
|
|
|
|
|
ret = striped_read(inode, off, len,
|
|
|
|
pages, num_pages, checkeof,
|
|
|
|
1, (unsigned long)data & ~PAGE_MASK);
|
|
|
|
ceph_put_page_vector(pages, num_pages, true);
|
|
|
|
|
|
|
|
if (ret <= 0)
|
|
|
|
break;
|
|
|
|
off += ret;
|
|
|
|
iov_iter_advance(i, ret);
|
|
|
|
if (ret < len)
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
} else {
|
|
|
|
num_pages = calc_pages_for(off, len);
|
|
|
|
pages = ceph_alloc_page_vector(num_pages, GFP_NOFS);
|
|
|
|
if (IS_ERR(pages))
|
|
|
|
return PTR_ERR(pages);
|
|
|
|
ret = striped_read(inode, off, len, pages,
|
|
|
|
num_pages, checkeof, 0, 0);
|
|
|
|
if (ret > 0) {
|
|
|
|
int l, k = 0;
|
|
|
|
size_t left = len = ret;
|
|
|
|
|
|
|
|
while (left) {
|
|
|
|
void __user *data = i->iov[0].iov_base
|
|
|
|
+ i->iov_offset;
|
|
|
|
l = min(i->iov[0].iov_len - i->iov_offset,
|
|
|
|
left);
|
|
|
|
|
|
|
|
ret = ceph_copy_page_vector_to_user(&pages[k],
|
|
|
|
data, off,
|
|
|
|
l);
|
|
|
|
if (ret > 0) {
|
|
|
|
iov_iter_advance(i, ret);
|
|
|
|
left -= ret;
|
|
|
|
off += ret;
|
|
|
|
k = calc_pages_for(iocb->ki_pos,
|
|
|
|
len - left + 1) - 1;
|
|
|
|
BUG_ON(k >= num_pages && left);
|
|
|
|
} else
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
ceph_release_page_vector(pages, num_pages);
|
|
|
|
}
|
2009-10-07 02:31:08 +08:00
|
|
|
|
2013-09-26 14:42:17 +08:00
|
|
|
if (off > iocb->ki_pos) {
|
|
|
|
ret = off - iocb->ki_pos;
|
|
|
|
iocb->ki_pos = off;
|
|
|
|
}
|
2009-10-07 02:31:08 +08:00
|
|
|
|
|
|
|
dout("sync_read result %d\n", ret);
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
libceph: change how "safe" callback is used
An osd request currently has two callbacks. They inform the
initiator of the request when we've received confirmation for the
target osd that a request was received, and when the osd indicates
all changes described by the request are durable.
The only time the second callback is used is in the ceph file system
for a synchronous write. There's a race that makes some handling of
this case unsafe. This patch addresses this problem. The error
handling for this callback is also kind of gross, and this patch
changes that as well.
In ceph_sync_write(), if a safe callback is requested we want to add
the request on the ceph inode's unsafe items list. Because items on
this list must have their tid set (by ceph_osd_start_request()), the
request added *after* the call to that function returns. The
problem with this is that there's a race between starting the
request and adding it to the unsafe items list; the request may
already be complete before ceph_sync_write() even begins to put it
on the list.
To address this, we change the way the "safe" callback is used.
Rather than just calling it when the request is "safe", we use it to
notify the initiator the bounds (start and end) of the period during
which the request is *unsafe*. So the initiator gets notified just
before the request gets sent to the osd (when it is "unsafe"), and
again when it's known the results are durable (it's no longer
unsafe). The first call will get made in __send_request(), just
before the request message gets sent to the messenger for the first
time. That function is only called by __send_queued(), which is
always called with the osd client's request mutex held.
We then have this callback function insert the request on the ceph
inode's unsafe list when we're told the request is unsafe. This
will avoid the race because this call will be made under protection
of the osd client's request mutex. It also nicely groups the setup
and cleanup of the state associated with managing unsafe requests.
The name of the "safe" callback field is changed to "unsafe" to
better reflect its new purpose. It has a Boolean "unsafe" parameter
to indicate whether the request is becoming unsafe or is now safe.
Because the "msg" parameter wasn't used, we drop that.
This resolves the original problem reportedin:
http://tracker.ceph.com/issues/4706
Reported-by: Yan, Zheng <zheng.z.yan@intel.com>
Signed-off-by: Alex Elder <elder@inktank.com>
Reviewed-by: Yan, Zheng <zheng.z.yan@intel.com>
Reviewed-by: Sage Weil <sage@inktank.com>
2013-04-16 00:20:42 +08:00
|
|
|
* Write commit request unsafe callback, called to tell us when a
|
|
|
|
* request is unsafe (that is, in flight--has been handed to the
|
|
|
|
* messenger to send to its target osd). It is called again when
|
|
|
|
* we've received a response message indicating the request is
|
|
|
|
* "safe" (its CEPH_OSD_FLAG_ONDISK flag is set), or when a request
|
|
|
|
* is completed early (and unsuccessfully) due to a timeout or
|
|
|
|
* interrupt.
|
|
|
|
*
|
|
|
|
* This is used if we requested both an ACK and ONDISK commit reply
|
|
|
|
* from the OSD.
|
2009-10-07 02:31:08 +08:00
|
|
|
*/
|
libceph: change how "safe" callback is used
An osd request currently has two callbacks. They inform the
initiator of the request when we've received confirmation for the
target osd that a request was received, and when the osd indicates
all changes described by the request are durable.
The only time the second callback is used is in the ceph file system
for a synchronous write. There's a race that makes some handling of
this case unsafe. This patch addresses this problem. The error
handling for this callback is also kind of gross, and this patch
changes that as well.
In ceph_sync_write(), if a safe callback is requested we want to add
the request on the ceph inode's unsafe items list. Because items on
this list must have their tid set (by ceph_osd_start_request()), the
request added *after* the call to that function returns. The
problem with this is that there's a race between starting the
request and adding it to the unsafe items list; the request may
already be complete before ceph_sync_write() even begins to put it
on the list.
To address this, we change the way the "safe" callback is used.
Rather than just calling it when the request is "safe", we use it to
notify the initiator the bounds (start and end) of the period during
which the request is *unsafe*. So the initiator gets notified just
before the request gets sent to the osd (when it is "unsafe"), and
again when it's known the results are durable (it's no longer
unsafe). The first call will get made in __send_request(), just
before the request message gets sent to the messenger for the first
time. That function is only called by __send_queued(), which is
always called with the osd client's request mutex held.
We then have this callback function insert the request on the ceph
inode's unsafe list when we're told the request is unsafe. This
will avoid the race because this call will be made under protection
of the osd client's request mutex. It also nicely groups the setup
and cleanup of the state associated with managing unsafe requests.
The name of the "safe" callback field is changed to "unsafe" to
better reflect its new purpose. It has a Boolean "unsafe" parameter
to indicate whether the request is becoming unsafe or is now safe.
Because the "msg" parameter wasn't used, we drop that.
This resolves the original problem reportedin:
http://tracker.ceph.com/issues/4706
Reported-by: Yan, Zheng <zheng.z.yan@intel.com>
Signed-off-by: Alex Elder <elder@inktank.com>
Reviewed-by: Yan, Zheng <zheng.z.yan@intel.com>
Reviewed-by: Sage Weil <sage@inktank.com>
2013-04-16 00:20:42 +08:00
|
|
|
static void ceph_sync_write_unsafe(struct ceph_osd_request *req, bool unsafe)
|
2009-10-07 02:31:08 +08:00
|
|
|
{
|
|
|
|
struct ceph_inode_info *ci = ceph_inode(req->r_inode);
|
|
|
|
|
libceph: change how "safe" callback is used
An osd request currently has two callbacks. They inform the
initiator of the request when we've received confirmation for the
target osd that a request was received, and when the osd indicates
all changes described by the request are durable.
The only time the second callback is used is in the ceph file system
for a synchronous write. There's a race that makes some handling of
this case unsafe. This patch addresses this problem. The error
handling for this callback is also kind of gross, and this patch
changes that as well.
In ceph_sync_write(), if a safe callback is requested we want to add
the request on the ceph inode's unsafe items list. Because items on
this list must have their tid set (by ceph_osd_start_request()), the
request added *after* the call to that function returns. The
problem with this is that there's a race between starting the
request and adding it to the unsafe items list; the request may
already be complete before ceph_sync_write() even begins to put it
on the list.
To address this, we change the way the "safe" callback is used.
Rather than just calling it when the request is "safe", we use it to
notify the initiator the bounds (start and end) of the period during
which the request is *unsafe*. So the initiator gets notified just
before the request gets sent to the osd (when it is "unsafe"), and
again when it's known the results are durable (it's no longer
unsafe). The first call will get made in __send_request(), just
before the request message gets sent to the messenger for the first
time. That function is only called by __send_queued(), which is
always called with the osd client's request mutex held.
We then have this callback function insert the request on the ceph
inode's unsafe list when we're told the request is unsafe. This
will avoid the race because this call will be made under protection
of the osd client's request mutex. It also nicely groups the setup
and cleanup of the state associated with managing unsafe requests.
The name of the "safe" callback field is changed to "unsafe" to
better reflect its new purpose. It has a Boolean "unsafe" parameter
to indicate whether the request is becoming unsafe or is now safe.
Because the "msg" parameter wasn't used, we drop that.
This resolves the original problem reportedin:
http://tracker.ceph.com/issues/4706
Reported-by: Yan, Zheng <zheng.z.yan@intel.com>
Signed-off-by: Alex Elder <elder@inktank.com>
Reviewed-by: Yan, Zheng <zheng.z.yan@intel.com>
Reviewed-by: Sage Weil <sage@inktank.com>
2013-04-16 00:20:42 +08:00
|
|
|
dout("%s %p tid %llu %ssafe\n", __func__, req, req->r_tid,
|
|
|
|
unsafe ? "un" : "");
|
|
|
|
if (unsafe) {
|
|
|
|
ceph_get_cap_refs(ci, CEPH_CAP_FILE_WR);
|
|
|
|
spin_lock(&ci->i_unsafe_lock);
|
|
|
|
list_add_tail(&req->r_unsafe_item,
|
|
|
|
&ci->i_unsafe_writes);
|
|
|
|
spin_unlock(&ci->i_unsafe_lock);
|
|
|
|
} else {
|
|
|
|
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);
|
|
|
|
}
|
2009-10-07 02:31:08 +08:00
|
|
|
}
|
|
|
|
|
2013-09-12 13:54:26 +08:00
|
|
|
|
2009-10-07 02:31:08 +08:00
|
|
|
/*
|
2013-09-12 13:54:26 +08:00
|
|
|
* Synchronous write, straight from __user pointer or user pages.
|
2009-10-07 02:31:08 +08:00
|
|
|
*
|
|
|
|
* 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.)
|
|
|
|
*/
|
2013-09-12 13:54:26 +08:00
|
|
|
static ssize_t
|
|
|
|
ceph_sync_direct_write(struct kiocb *iocb, const struct iovec *iov,
|
|
|
|
unsigned long nr_segs, size_t count)
|
2009-10-07 02:31:08 +08:00
|
|
|
{
|
2013-09-12 13:54:26 +08:00
|
|
|
struct file *file = iocb->ki_filp;
|
2013-01-24 06:07:38 +08:00
|
|
|
struct inode *inode = file_inode(file);
|
2009-10-07 02:31:08 +08:00
|
|
|
struct ceph_inode_info *ci = ceph_inode(inode);
|
2010-04-07 06:14:15 +08:00
|
|
|
struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
|
2013-03-15 03:09:05 +08:00
|
|
|
struct ceph_snap_context *snapc;
|
|
|
|
struct ceph_vino vino;
|
2009-10-07 02:31:08 +08:00
|
|
|
struct ceph_osd_request *req;
|
|
|
|
struct page **pages;
|
|
|
|
int num_pages;
|
|
|
|
int written = 0;
|
|
|
|
int flags;
|
|
|
|
int check_caps = 0;
|
2013-09-12 13:54:26 +08:00
|
|
|
int page_align;
|
2009-10-07 02:31:08 +08:00
|
|
|
int ret;
|
|
|
|
struct timespec mtime = CURRENT_TIME;
|
2013-09-12 13:54:26 +08:00
|
|
|
loff_t pos = iocb->ki_pos;
|
|
|
|
struct iov_iter i;
|
2009-10-07 02:31:08 +08:00
|
|
|
|
2013-01-24 06:07:38 +08:00
|
|
|
if (ceph_snap(file_inode(file)) != CEPH_NOSNAP)
|
2009-10-07 02:31:08 +08:00
|
|
|
return -EROFS;
|
|
|
|
|
2013-09-12 13:54:26 +08:00
|
|
|
dout("sync_direct_write on file %p %lld~%u\n", file, pos,
|
|
|
|
(unsigned)count);
|
2009-10-07 02:31:08 +08:00
|
|
|
|
2013-09-12 13:54:26 +08:00
|
|
|
ret = filemap_write_and_wait_range(inode->i_mapping, pos, pos + count);
|
2010-02-10 03:14:41 +08:00
|
|
|
if (ret < 0)
|
|
|
|
return ret;
|
|
|
|
|
|
|
|
ret = invalidate_inode_pages2_range(inode->i_mapping,
|
|
|
|
pos >> PAGE_CACHE_SHIFT,
|
2013-09-12 13:54:26 +08:00
|
|
|
(pos + count) >> PAGE_CACHE_SHIFT);
|
2010-02-10 03:14:41 +08:00
|
|
|
if (ret < 0)
|
|
|
|
dout("invalidate_inode_pages2_range returned %d\n", ret);
|
|
|
|
|
2009-10-07 02:31:08 +08:00
|
|
|
flags = CEPH_OSD_FLAG_ORDERSNAP |
|
|
|
|
CEPH_OSD_FLAG_ONDISK |
|
|
|
|
CEPH_OSD_FLAG_WRITE;
|
|
|
|
|
2013-09-12 13:54:26 +08:00
|
|
|
iov_iter_init(&i, iov, nr_segs, count, 0);
|
|
|
|
|
|
|
|
while (iov_iter_count(&i) > 0) {
|
|
|
|
void __user *data = i.iov->iov_base + i.iov_offset;
|
|
|
|
u64 len = i.iov->iov_len - i.iov_offset;
|
|
|
|
|
|
|
|
page_align = (unsigned long)data & ~PAGE_MASK;
|
|
|
|
|
|
|
|
snapc = ci->i_snap_realm->cached_context;
|
|
|
|
vino = ceph_vino(inode);
|
|
|
|
req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout,
|
|
|
|
vino, pos, &len,
|
|
|
|
2,/*include a 'startsync' command*/
|
|
|
|
CEPH_OSD_OP_WRITE, flags, snapc,
|
|
|
|
ci->i_truncate_seq,
|
|
|
|
ci->i_truncate_size,
|
|
|
|
false);
|
|
|
|
if (IS_ERR(req)) {
|
|
|
|
ret = PTR_ERR(req);
|
2014-04-04 10:44:19 +08:00
|
|
|
break;
|
2013-09-12 13:54:26 +08:00
|
|
|
}
|
2009-10-07 02:31:08 +08:00
|
|
|
|
2013-09-12 13:54:26 +08:00
|
|
|
num_pages = calc_pages_for(page_align, len);
|
2010-12-16 12:45:41 +08:00
|
|
|
pages = ceph_get_direct_page_vector(data, num_pages, false);
|
2009-10-07 02:31:08 +08:00
|
|
|
if (IS_ERR(pages)) {
|
|
|
|
ret = PTR_ERR(pages);
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* throw out any page cache pages in this range. this
|
|
|
|
* may block.
|
|
|
|
*/
|
2010-08-04 01:25:11 +08:00
|
|
|
truncate_inode_pages_range(inode->i_mapping, pos,
|
2013-09-12 13:54:26 +08:00
|
|
|
(pos+len) | (PAGE_CACHE_SIZE-1));
|
|
|
|
osd_req_op_extent_osd_data_pages(req, 0, pages, len, page_align,
|
|
|
|
false, false);
|
|
|
|
|
|
|
|
/* BUG_ON(vino.snap != CEPH_NOSNAP); */
|
|
|
|
ceph_osdc_build_request(req, pos, snapc, vino.snap, &mtime);
|
|
|
|
|
|
|
|
ret = ceph_osdc_start_request(&fsc->client->osdc, req, false);
|
|
|
|
if (!ret)
|
|
|
|
ret = ceph_osdc_wait_request(&fsc->client->osdc, req);
|
|
|
|
|
|
|
|
ceph_put_page_vector(pages, num_pages, false);
|
|
|
|
|
|
|
|
out:
|
|
|
|
ceph_osdc_put_request(req);
|
|
|
|
if (ret == 0) {
|
|
|
|
pos += len;
|
|
|
|
written += len;
|
|
|
|
iov_iter_advance(&i, (size_t)len);
|
|
|
|
|
|
|
|
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);
|
|
|
|
}
|
|
|
|
} else
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (ret != -EOLDSNAPC && written > 0) {
|
|
|
|
iocb->ki_pos = pos;
|
|
|
|
ret = written;
|
|
|
|
}
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Synchronous write, straight from __user pointer or user pages.
|
|
|
|
*
|
|
|
|
* 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 kiocb *iocb, const struct iovec *iov,
|
|
|
|
unsigned long nr_segs, size_t count)
|
|
|
|
{
|
|
|
|
struct file *file = iocb->ki_filp;
|
|
|
|
struct inode *inode = file_inode(file);
|
|
|
|
struct ceph_inode_info *ci = ceph_inode(inode);
|
|
|
|
struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
|
|
|
|
struct ceph_snap_context *snapc;
|
|
|
|
struct ceph_vino vino;
|
|
|
|
struct ceph_osd_request *req;
|
|
|
|
struct page **pages;
|
|
|
|
u64 len;
|
|
|
|
int num_pages;
|
|
|
|
int written = 0;
|
|
|
|
int flags;
|
|
|
|
int check_caps = 0;
|
|
|
|
int ret;
|
|
|
|
struct timespec mtime = CURRENT_TIME;
|
|
|
|
loff_t pos = iocb->ki_pos;
|
|
|
|
struct iov_iter i;
|
|
|
|
|
|
|
|
if (ceph_snap(file_inode(file)) != CEPH_NOSNAP)
|
|
|
|
return -EROFS;
|
|
|
|
|
|
|
|
dout("sync_write on file %p %lld~%u\n", file, pos, (unsigned)count);
|
|
|
|
|
|
|
|
ret = filemap_write_and_wait_range(inode->i_mapping, pos, pos + count);
|
|
|
|
if (ret < 0)
|
|
|
|
return ret;
|
|
|
|
|
|
|
|
ret = invalidate_inode_pages2_range(inode->i_mapping,
|
|
|
|
pos >> PAGE_CACHE_SHIFT,
|
|
|
|
(pos + count) >> PAGE_CACHE_SHIFT);
|
|
|
|
if (ret < 0)
|
|
|
|
dout("invalidate_inode_pages2_range returned %d\n", ret);
|
|
|
|
|
|
|
|
flags = CEPH_OSD_FLAG_ORDERSNAP |
|
|
|
|
CEPH_OSD_FLAG_ONDISK |
|
|
|
|
CEPH_OSD_FLAG_WRITE |
|
|
|
|
CEPH_OSD_FLAG_ACK;
|
|
|
|
|
|
|
|
iov_iter_init(&i, iov, nr_segs, count, 0);
|
|
|
|
|
|
|
|
while ((len = iov_iter_count(&i)) > 0) {
|
|
|
|
size_t left;
|
|
|
|
int n;
|
|
|
|
|
|
|
|
snapc = ci->i_snap_realm->cached_context;
|
|
|
|
vino = ceph_vino(inode);
|
|
|
|
req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout,
|
|
|
|
vino, pos, &len, 1,
|
|
|
|
CEPH_OSD_OP_WRITE, flags, snapc,
|
|
|
|
ci->i_truncate_seq,
|
|
|
|
ci->i_truncate_size,
|
|
|
|
false);
|
|
|
|
if (IS_ERR(req)) {
|
|
|
|
ret = PTR_ERR(req);
|
2014-04-04 10:44:19 +08:00
|
|
|
break;
|
2013-09-12 13:54:26 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* write from beginning of first page,
|
|
|
|
* regardless of io alignment
|
|
|
|
*/
|
|
|
|
num_pages = (len + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
|
|
|
|
|
2010-04-07 05:33:58 +08:00
|
|
|
pages = ceph_alloc_page_vector(num_pages, GFP_NOFS);
|
2009-10-07 02:31:08 +08:00
|
|
|
if (IS_ERR(pages)) {
|
|
|
|
ret = PTR_ERR(pages);
|
|
|
|
goto out;
|
|
|
|
}
|
2013-09-12 13:54:26 +08:00
|
|
|
|
|
|
|
left = len;
|
|
|
|
for (n = 0; n < num_pages; n++) {
|
2014-01-29 01:16:18 +08:00
|
|
|
size_t plen = min_t(size_t, left, PAGE_SIZE);
|
2013-09-12 13:54:26 +08:00
|
|
|
ret = iov_iter_copy_from_user(pages[n], &i, 0, plen);
|
|
|
|
if (ret != plen) {
|
|
|
|
ret = -EFAULT;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
left -= ret;
|
|
|
|
iov_iter_advance(&i, ret);
|
|
|
|
}
|
|
|
|
|
2009-10-07 02:31:08 +08:00
|
|
|
if (ret < 0) {
|
|
|
|
ceph_release_page_vector(pages, num_pages);
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
2013-09-12 13:54:26 +08:00
|
|
|
/* get a second commit callback */
|
|
|
|
req->r_unsafe_callback = ceph_sync_write_unsafe;
|
|
|
|
req->r_inode = inode;
|
2009-10-07 02:31:08 +08:00
|
|
|
|
2013-09-12 13:54:26 +08:00
|
|
|
osd_req_op_extent_osd_data_pages(req, 0, pages, len, 0,
|
|
|
|
false, true);
|
2013-03-15 03:09:06 +08:00
|
|
|
|
2013-09-12 13:54:26 +08:00
|
|
|
/* BUG_ON(vino.snap != CEPH_NOSNAP); */
|
|
|
|
ceph_osdc_build_request(req, pos, snapc, vino.snap, &mtime);
|
2009-10-07 02:31:08 +08:00
|
|
|
|
2013-09-12 13:54:26 +08:00
|
|
|
ret = ceph_osdc_start_request(&fsc->client->osdc, req, false);
|
|
|
|
if (!ret)
|
|
|
|
ret = ceph_osdc_wait_request(&fsc->client->osdc, req);
|
2009-10-07 02:31:08 +08:00
|
|
|
|
|
|
|
out:
|
2013-09-12 13:54:26 +08:00
|
|
|
ceph_osdc_put_request(req);
|
|
|
|
if (ret == 0) {
|
|
|
|
pos += len;
|
|
|
|
written += len;
|
|
|
|
|
|
|
|
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);
|
|
|
|
}
|
|
|
|
} else
|
|
|
|
break;
|
|
|
|
}
|
2009-10-07 02:31:08 +08:00
|
|
|
|
2013-09-12 13:54:26 +08:00
|
|
|
if (ret != -EOLDSNAPC && written > 0) {
|
2009-10-07 02:31:08 +08:00
|
|
|
ret = written;
|
2013-09-12 13:54:26 +08:00
|
|
|
iocb->ki_pos = pos;
|
2009-10-07 02:31:08 +08:00
|
|
|
}
|
|
|
|
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;
|
2010-05-28 01:40:43 +08:00
|
|
|
struct ceph_file_info *fi = filp->private_data;
|
2013-09-26 14:42:17 +08:00
|
|
|
size_t len = iocb->ki_nbytes;
|
2013-01-24 06:07:38 +08:00
|
|
|
struct inode *inode = file_inode(filp);
|
2009-10-07 02:31:08 +08:00
|
|
|
struct ceph_inode_info *ci = ceph_inode(inode);
|
|
|
|
ssize_t ret;
|
2010-05-28 01:40:43 +08:00
|
|
|
int want, got = 0;
|
2010-02-10 06:04:02 +08:00
|
|
|
int checkeof = 0, read = 0;
|
2009-10-07 02:31:08 +08:00
|
|
|
|
2010-02-10 06:04:02 +08:00
|
|
|
again:
|
2013-09-26 14:42:17 +08:00
|
|
|
dout("aio_read %p %llx.%llx %llu~%u trying to get caps on %p\n",
|
|
|
|
inode, ceph_vinop(inode), iocb->ki_pos, (unsigned)len, inode);
|
|
|
|
|
2010-05-28 01:40:43 +08:00
|
|
|
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);
|
2009-10-07 02:31:08 +08:00
|
|
|
if (ret < 0)
|
2013-09-26 14:42:17 +08:00
|
|
|
return ret;
|
2009-10-07 02:31:08 +08:00
|
|
|
|
2010-05-28 01:40:43 +08:00
|
|
|
if ((got & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)) == 0 ||
|
2009-10-07 02:31:08 +08:00
|
|
|
(iocb->ki_filp->f_flags & O_DIRECT) ||
|
2013-09-26 14:42:17 +08:00
|
|
|
(fi->flags & CEPH_F_SYNC)) {
|
|
|
|
struct iov_iter i;
|
|
|
|
|
|
|
|
dout("aio_sync_read %p %llx.%llx %llu~%u got cap refs on %s\n",
|
|
|
|
inode, ceph_vinop(inode), iocb->ki_pos, (unsigned)len,
|
|
|
|
ceph_cap_string(got));
|
|
|
|
|
|
|
|
if (!read) {
|
|
|
|
ret = generic_segment_checks(iov, &nr_segs,
|
|
|
|
&len, VERIFY_WRITE);
|
|
|
|
if (ret)
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
iov_iter_init(&i, iov, nr_segs, len, read);
|
|
|
|
|
2009-10-07 02:31:08 +08:00
|
|
|
/* hmm, this isn't really async... */
|
2013-09-26 14:42:17 +08:00
|
|
|
ret = ceph_sync_read(iocb, &i, &checkeof);
|
|
|
|
} else {
|
|
|
|
/*
|
|
|
|
* We can't modify the content of iov,
|
|
|
|
* so we only read from beginning.
|
|
|
|
*/
|
|
|
|
if (read) {
|
|
|
|
iocb->ki_pos = pos;
|
|
|
|
len = iocb->ki_nbytes;
|
|
|
|
read = 0;
|
|
|
|
}
|
|
|
|
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));
|
2009-10-07 02:31:08 +08:00
|
|
|
|
2013-09-26 14:42:17 +08:00
|
|
|
ret = generic_file_aio_read(iocb, iov, nr_segs, pos);
|
|
|
|
}
|
2009-10-07 02:31:08 +08:00
|
|
|
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);
|
2010-02-10 06:04:02 +08:00
|
|
|
|
|
|
|
if (checkeof && ret >= 0) {
|
2013-09-26 14:42:17 +08:00
|
|
|
int statret = ceph_do_getattr(inode,
|
|
|
|
CEPH_STAT_CAP_SIZE);
|
2010-02-10 06:04:02 +08:00
|
|
|
|
|
|
|
/* hit EOF or hole? */
|
2013-09-26 14:42:17 +08:00
|
|
|
if (statret == 0 && iocb->ki_pos < inode->i_size &&
|
|
|
|
ret < len) {
|
|
|
|
dout("sync_read hit hole, ppos %lld < size %lld"
|
|
|
|
", reading more\n", iocb->ki_pos,
|
|
|
|
inode->i_size);
|
|
|
|
|
2010-02-10 06:04:02 +08:00
|
|
|
read += ret;
|
|
|
|
len -= ret;
|
|
|
|
checkeof = 0;
|
|
|
|
goto again;
|
|
|
|
}
|
|
|
|
}
|
2013-09-26 14:42:17 +08:00
|
|
|
|
2010-02-10 06:04:02 +08:00
|
|
|
if (ret >= 0)
|
|
|
|
ret += read;
|
|
|
|
|
2009-10-07 02:31:08 +08:00
|
|
|
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;
|
2010-05-27 05:31:27 +08:00
|
|
|
struct ceph_file_info *fi = file->private_data;
|
2013-01-24 06:07:38 +08:00
|
|
|
struct inode *inode = file_inode(file);
|
2009-10-07 02:31:08 +08:00
|
|
|
struct ceph_inode_info *ci = ceph_inode(inode);
|
2010-04-07 06:14:15 +08:00
|
|
|
struct ceph_osd_client *osdc =
|
|
|
|
&ceph_sb_to_client(inode->i_sb)->client->osdc;
|
2013-04-12 16:11:13 +08:00
|
|
|
ssize_t count, written = 0;
|
|
|
|
int err, want, got;
|
2009-10-07 02:31:08 +08:00
|
|
|
|
|
|
|
if (ceph_snap(inode) != CEPH_NOSNAP)
|
|
|
|
return -EROFS;
|
|
|
|
|
2013-04-12 16:11:13 +08:00
|
|
|
mutex_lock(&inode->i_mutex);
|
|
|
|
|
|
|
|
err = generic_segment_checks(iov, &nr_segs, &count, VERIFY_READ);
|
|
|
|
if (err)
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
/* We can write back this queue in page reclaim */
|
|
|
|
current->backing_dev_info = file->f_mapping->backing_dev_info;
|
|
|
|
|
|
|
|
err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode));
|
|
|
|
if (err)
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
if (count == 0)
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
err = file_remove_suid(file);
|
|
|
|
if (err)
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
err = file_update_time(file);
|
|
|
|
if (err)
|
|
|
|
goto out;
|
|
|
|
|
2009-10-07 02:31:08 +08:00
|
|
|
retry_snap:
|
2013-03-01 10:55:39 +08:00
|
|
|
if (ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL)) {
|
2013-04-12 16:11:13 +08:00
|
|
|
err = -ENOSPC;
|
2013-03-01 10:55:39 +08:00
|
|
|
goto out;
|
|
|
|
}
|
2013-04-12 16:11:13 +08:00
|
|
|
|
2013-04-20 05:20:07 +08:00
|
|
|
dout("aio_write %p %llx.%llx %llu~%zd getting caps. i_size %llu\n",
|
2013-04-12 16:11:13 +08:00
|
|
|
inode, ceph_vinop(inode), pos, count, inode->i_size);
|
2013-05-02 12:15:58 +08:00
|
|
|
if (fi->fmode & CEPH_FILE_MODE_LAZY)
|
|
|
|
want = CEPH_CAP_FILE_BUFFER | CEPH_CAP_FILE_LAZYIO;
|
|
|
|
else
|
|
|
|
want = CEPH_CAP_FILE_BUFFER;
|
2013-04-12 16:11:13 +08:00
|
|
|
got = 0;
|
|
|
|
err = ceph_get_caps(ci, CEPH_CAP_FILE_WR, want, &got, pos + count);
|
|
|
|
if (err < 0)
|
2013-04-12 16:11:10 +08:00
|
|
|
goto out;
|
2009-10-07 02:31:08 +08:00
|
|
|
|
2013-04-20 05:20:07 +08:00
|
|
|
dout("aio_write %p %llx.%llx %llu~%zd got cap refs on %s\n",
|
2013-04-12 16:11:13 +08:00
|
|
|
inode, ceph_vinop(inode), pos, count, ceph_cap_string(got));
|
2013-05-02 12:15:58 +08:00
|
|
|
|
|
|
|
if ((got & (CEPH_CAP_FILE_BUFFER|CEPH_CAP_FILE_LAZYIO)) == 0 ||
|
2013-09-12 13:54:26 +08:00
|
|
|
(file->f_flags & O_DIRECT) || (fi->flags & CEPH_F_SYNC)) {
|
2013-04-12 16:11:10 +08:00
|
|
|
mutex_unlock(&inode->i_mutex);
|
2013-09-12 13:54:26 +08:00
|
|
|
if (file->f_flags & O_DIRECT)
|
|
|
|
written = ceph_sync_direct_write(iocb, iov,
|
|
|
|
nr_segs, count);
|
|
|
|
else
|
|
|
|
written = ceph_sync_write(iocb, iov, nr_segs, count);
|
2013-08-08 15:32:19 +08:00
|
|
|
if (written == -EOLDSNAPC) {
|
|
|
|
dout("aio_write %p %llx.%llx %llu~%u"
|
|
|
|
"got EOLDSNAPC, retrying\n",
|
|
|
|
inode, ceph_vinop(inode),
|
|
|
|
pos, (unsigned)iov->iov_len);
|
|
|
|
mutex_lock(&inode->i_mutex);
|
|
|
|
goto retry_snap;
|
|
|
|
}
|
2013-05-02 12:15:58 +08:00
|
|
|
} else {
|
2013-12-26 22:29:27 +08:00
|
|
|
loff_t old_size = inode->i_size;
|
2014-02-12 11:28:43 +08:00
|
|
|
struct iov_iter from;
|
2013-08-13 12:42:15 +08:00
|
|
|
/*
|
|
|
|
* No need to acquire the i_truncate_mutex. Because
|
|
|
|
* the MDS revokes Fwb caps before sending truncate
|
|
|
|
* message to us. We can't get Fwb cap while there
|
|
|
|
* are pending vmtruncate. So write and vmtruncate
|
|
|
|
* can not run at the same time
|
|
|
|
*/
|
2014-02-12 11:28:43 +08:00
|
|
|
iov_iter_init(&from, iov, nr_segs, count, 0);
|
|
|
|
written = generic_perform_write(file, &from, pos);
|
|
|
|
if (likely(written >= 0))
|
|
|
|
iocb->ki_pos = pos + written;
|
2013-12-26 22:29:27 +08:00
|
|
|
if (inode->i_size > old_size)
|
|
|
|
ceph_fscache_update_objectsize(inode);
|
2013-03-01 10:55:39 +08:00
|
|
|
mutex_unlock(&inode->i_mutex);
|
2013-05-02 12:15:58 +08:00
|
|
|
}
|
2011-07-27 02:27:34 +08:00
|
|
|
|
2013-04-12 16:11:13 +08:00
|
|
|
if (written >= 0) {
|
2011-05-05 02:33:47 +08:00
|
|
|
int dirty;
|
2011-12-01 01:47:09 +08:00
|
|
|
spin_lock(&ci->i_ceph_lock);
|
2011-05-05 02:33:47 +08:00
|
|
|
dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_FILE_WR);
|
2011-12-01 01:47:09 +08:00
|
|
|
spin_unlock(&ci->i_ceph_lock);
|
2011-05-05 02:33:47 +08:00
|
|
|
if (dirty)
|
|
|
|
__mark_inode_dirty(inode, dirty);
|
2009-10-07 02:31:08 +08:00
|
|
|
}
|
2013-05-02 12:15:58 +08:00
|
|
|
|
2009-10-07 02:31:08 +08:00
|
|
|
dout("aio_write %p %llx.%llx %llu~%u dropping cap refs on %s\n",
|
2013-05-02 12:15:58 +08:00
|
|
|
inode, ceph_vinop(inode), pos, (unsigned)iov->iov_len,
|
|
|
|
ceph_cap_string(got));
|
2009-10-07 02:31:08 +08:00
|
|
|
ceph_put_cap_refs(ci, got);
|
2013-05-02 12:15:58 +08:00
|
|
|
|
2013-04-12 16:11:13 +08:00
|
|
|
if (written >= 0 &&
|
2013-03-01 10:55:39 +08:00
|
|
|
((file->f_flags & O_SYNC) || IS_SYNC(file->f_mapping->host) ||
|
|
|
|
ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_NEARFULL))) {
|
2013-04-12 16:11:13 +08:00
|
|
|
err = vfs_fsync_range(file, pos, pos + written - 1, 1);
|
2013-03-01 10:55:39 +08:00
|
|
|
if (err < 0)
|
2013-04-12 16:11:13 +08:00
|
|
|
written = err;
|
2013-03-01 10:55:39 +08:00
|
|
|
}
|
2013-04-12 16:11:13 +08:00
|
|
|
|
2013-08-10 00:57:58 +08:00
|
|
|
goto out_unlocked;
|
|
|
|
|
2013-04-12 16:11:13 +08:00
|
|
|
out:
|
2013-08-10 00:57:58 +08:00
|
|
|
mutex_unlock(&inode->i_mutex);
|
|
|
|
out_unlocked:
|
2013-04-12 16:11:13 +08:00
|
|
|
current->backing_dev_info = NULL;
|
|
|
|
return written ? written : err;
|
2009-10-07 02:31:08 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* llseek. be sure to verify file size on SEEK_END.
|
|
|
|
*/
|
2012-12-18 07:59:39 +08:00
|
|
|
static loff_t ceph_llseek(struct file *file, loff_t offset, int whence)
|
2009-10-07 02:31:08 +08:00
|
|
|
{
|
|
|
|
struct inode *inode = file->f_mapping->host;
|
|
|
|
int ret;
|
|
|
|
|
|
|
|
mutex_lock(&inode->i_mutex);
|
2011-12-14 01:19:26 +08:00
|
|
|
|
2012-12-18 07:59:39 +08:00
|
|
|
if (whence == SEEK_END || whence == SEEK_DATA || whence == SEEK_HOLE) {
|
2009-10-07 02:31:08 +08:00
|
|
|
ret = ceph_do_getattr(inode, CEPH_STAT_CAP_SIZE);
|
|
|
|
if (ret < 0) {
|
|
|
|
offset = ret;
|
|
|
|
goto out;
|
|
|
|
}
|
2011-07-19 01:21:38 +08:00
|
|
|
}
|
|
|
|
|
2012-12-18 07:59:39 +08:00
|
|
|
switch (whence) {
|
2011-07-19 01:21:38 +08:00
|
|
|
case SEEK_END:
|
2009-10-07 02:31:08 +08:00
|
|
|
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;
|
2011-07-19 01:21:38 +08:00
|
|
|
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;
|
2009-10-07 02:31:08 +08:00
|
|
|
}
|
|
|
|
|
2013-06-25 12:02:13 +08:00
|
|
|
offset = vfs_setpos(file, offset, inode->i_sb->s_maxbytes);
|
2009-10-07 02:31:08 +08:00
|
|
|
|
|
|
|
out:
|
|
|
|
mutex_unlock(&inode->i_mutex);
|
|
|
|
return offset;
|
|
|
|
}
|
|
|
|
|
2013-08-15 11:51:44 +08:00
|
|
|
static inline void ceph_zero_partial_page(
|
|
|
|
struct inode *inode, loff_t offset, unsigned size)
|
|
|
|
{
|
|
|
|
struct page *page;
|
|
|
|
pgoff_t index = offset >> PAGE_CACHE_SHIFT;
|
|
|
|
|
|
|
|
page = find_lock_page(inode->i_mapping, index);
|
|
|
|
if (page) {
|
|
|
|
wait_on_page_writeback(page);
|
|
|
|
zero_user(page, offset & (PAGE_CACHE_SIZE - 1), size);
|
|
|
|
unlock_page(page);
|
|
|
|
page_cache_release(page);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
static void ceph_zero_pagecache_range(struct inode *inode, loff_t offset,
|
|
|
|
loff_t length)
|
|
|
|
{
|
|
|
|
loff_t nearly = round_up(offset, PAGE_CACHE_SIZE);
|
|
|
|
if (offset < nearly) {
|
|
|
|
loff_t size = nearly - offset;
|
|
|
|
if (length < size)
|
|
|
|
size = length;
|
|
|
|
ceph_zero_partial_page(inode, offset, size);
|
|
|
|
offset += size;
|
|
|
|
length -= size;
|
|
|
|
}
|
|
|
|
if (length >= PAGE_CACHE_SIZE) {
|
|
|
|
loff_t size = round_down(length, PAGE_CACHE_SIZE);
|
|
|
|
truncate_pagecache_range(inode, offset, offset + size - 1);
|
|
|
|
offset += size;
|
|
|
|
length -= size;
|
|
|
|
}
|
|
|
|
if (length)
|
|
|
|
ceph_zero_partial_page(inode, offset, length);
|
|
|
|
}
|
|
|
|
|
|
|
|
static int ceph_zero_partial_object(struct inode *inode,
|
|
|
|
loff_t offset, loff_t *length)
|
|
|
|
{
|
|
|
|
struct ceph_inode_info *ci = ceph_inode(inode);
|
|
|
|
struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
|
|
|
|
struct ceph_osd_request *req;
|
|
|
|
int ret = 0;
|
|
|
|
loff_t zero = 0;
|
|
|
|
int op;
|
|
|
|
|
|
|
|
if (!length) {
|
|
|
|
op = offset ? CEPH_OSD_OP_DELETE : CEPH_OSD_OP_TRUNCATE;
|
|
|
|
length = &zero;
|
|
|
|
} else {
|
|
|
|
op = CEPH_OSD_OP_ZERO;
|
|
|
|
}
|
|
|
|
|
|
|
|
req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout,
|
|
|
|
ceph_vino(inode),
|
|
|
|
offset, length,
|
|
|
|
1, op,
|
|
|
|
CEPH_OSD_FLAG_WRITE |
|
|
|
|
CEPH_OSD_FLAG_ONDISK,
|
|
|
|
NULL, 0, 0, false);
|
|
|
|
if (IS_ERR(req)) {
|
|
|
|
ret = PTR_ERR(req);
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
ceph_osdc_build_request(req, offset, NULL, ceph_vino(inode).snap,
|
|
|
|
&inode->i_mtime);
|
|
|
|
|
|
|
|
ret = ceph_osdc_start_request(&fsc->client->osdc, req, false);
|
|
|
|
if (!ret) {
|
|
|
|
ret = ceph_osdc_wait_request(&fsc->client->osdc, req);
|
|
|
|
if (ret == -ENOENT)
|
|
|
|
ret = 0;
|
|
|
|
}
|
|
|
|
ceph_osdc_put_request(req);
|
|
|
|
|
|
|
|
out:
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int ceph_zero_objects(struct inode *inode, loff_t offset, loff_t length)
|
|
|
|
{
|
|
|
|
int ret = 0;
|
|
|
|
struct ceph_inode_info *ci = ceph_inode(inode);
|
2013-08-28 03:15:16 +08:00
|
|
|
s32 stripe_unit = ceph_file_layout_su(ci->i_layout);
|
|
|
|
s32 stripe_count = ceph_file_layout_stripe_count(ci->i_layout);
|
|
|
|
s32 object_size = ceph_file_layout_object_size(ci->i_layout);
|
|
|
|
u64 object_set_size = object_size * stripe_count;
|
|
|
|
u64 nearly, t;
|
|
|
|
|
|
|
|
/* round offset up to next period boundary */
|
|
|
|
nearly = offset + object_set_size - 1;
|
|
|
|
t = nearly;
|
|
|
|
nearly -= do_div(t, object_set_size);
|
2013-08-15 11:51:44 +08:00
|
|
|
|
|
|
|
while (length && offset < nearly) {
|
|
|
|
loff_t size = length;
|
|
|
|
ret = ceph_zero_partial_object(inode, offset, &size);
|
|
|
|
if (ret < 0)
|
|
|
|
return ret;
|
|
|
|
offset += size;
|
|
|
|
length -= size;
|
|
|
|
}
|
|
|
|
while (length >= object_set_size) {
|
|
|
|
int i;
|
|
|
|
loff_t pos = offset;
|
|
|
|
for (i = 0; i < stripe_count; ++i) {
|
|
|
|
ret = ceph_zero_partial_object(inode, pos, NULL);
|
|
|
|
if (ret < 0)
|
|
|
|
return ret;
|
|
|
|
pos += stripe_unit;
|
|
|
|
}
|
|
|
|
offset += object_set_size;
|
|
|
|
length -= object_set_size;
|
|
|
|
}
|
|
|
|
while (length) {
|
|
|
|
loff_t size = length;
|
|
|
|
ret = ceph_zero_partial_object(inode, offset, &size);
|
|
|
|
if (ret < 0)
|
|
|
|
return ret;
|
|
|
|
offset += size;
|
|
|
|
length -= size;
|
|
|
|
}
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
static long ceph_fallocate(struct file *file, int mode,
|
|
|
|
loff_t offset, loff_t length)
|
|
|
|
{
|
|
|
|
struct ceph_file_info *fi = file->private_data;
|
2013-12-11 13:49:11 +08:00
|
|
|
struct inode *inode = file_inode(file);
|
2013-08-15 11:51:44 +08:00
|
|
|
struct ceph_inode_info *ci = ceph_inode(inode);
|
|
|
|
struct ceph_osd_client *osdc =
|
|
|
|
&ceph_inode_to_client(inode)->client->osdc;
|
|
|
|
int want, got = 0;
|
|
|
|
int dirty;
|
|
|
|
int ret = 0;
|
|
|
|
loff_t endoff = 0;
|
|
|
|
loff_t size;
|
|
|
|
|
|
|
|
if (!S_ISREG(inode->i_mode))
|
|
|
|
return -EOPNOTSUPP;
|
|
|
|
|
|
|
|
mutex_lock(&inode->i_mutex);
|
|
|
|
|
|
|
|
if (ceph_snap(inode) != CEPH_NOSNAP) {
|
|
|
|
ret = -EROFS;
|
|
|
|
goto unlock;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL) &&
|
|
|
|
!(mode & FALLOC_FL_PUNCH_HOLE)) {
|
|
|
|
ret = -ENOSPC;
|
|
|
|
goto unlock;
|
|
|
|
}
|
|
|
|
|
|
|
|
size = i_size_read(inode);
|
|
|
|
if (!(mode & FALLOC_FL_KEEP_SIZE))
|
|
|
|
endoff = offset + length;
|
|
|
|
|
|
|
|
if (fi->fmode & CEPH_FILE_MODE_LAZY)
|
|
|
|
want = CEPH_CAP_FILE_BUFFER | CEPH_CAP_FILE_LAZYIO;
|
|
|
|
else
|
|
|
|
want = CEPH_CAP_FILE_BUFFER;
|
|
|
|
|
|
|
|
ret = ceph_get_caps(ci, CEPH_CAP_FILE_WR, want, &got, endoff);
|
|
|
|
if (ret < 0)
|
|
|
|
goto unlock;
|
|
|
|
|
|
|
|
if (mode & FALLOC_FL_PUNCH_HOLE) {
|
|
|
|
if (offset < size)
|
|
|
|
ceph_zero_pagecache_range(inode, offset, length);
|
|
|
|
ret = ceph_zero_objects(inode, offset, length);
|
|
|
|
} else if (endoff > size) {
|
|
|
|
truncate_pagecache_range(inode, size, -1);
|
|
|
|
if (ceph_inode_set_size(inode, endoff))
|
|
|
|
ceph_check_caps(ceph_inode(inode),
|
|
|
|
CHECK_CAPS_AUTHONLY, NULL);
|
|
|
|
}
|
|
|
|
|
|
|
|
if (!ret) {
|
|
|
|
spin_lock(&ci->i_ceph_lock);
|
|
|
|
dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_FILE_WR);
|
|
|
|
spin_unlock(&ci->i_ceph_lock);
|
|
|
|
if (dirty)
|
|
|
|
__mark_inode_dirty(inode, dirty);
|
|
|
|
}
|
|
|
|
|
|
|
|
ceph_put_cap_refs(ci, got);
|
|
|
|
unlock:
|
|
|
|
mutex_unlock(&inode->i_mutex);
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2009-10-07 02:31:08 +08:00
|
|
|
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 06:34:23 +08:00
|
|
|
.lock = ceph_lock,
|
|
|
|
.flock = ceph_flock,
|
2009-10-07 02:31:08 +08:00
|
|
|
.splice_read = generic_file_splice_read,
|
|
|
|
.splice_write = generic_file_splice_write,
|
|
|
|
.unlocked_ioctl = ceph_ioctl,
|
|
|
|
.compat_ioctl = ceph_ioctl,
|
2013-08-15 11:51:44 +08:00
|
|
|
.fallocate = ceph_fallocate,
|
2009-10-07 02:31:08 +08:00
|
|
|
};
|
|
|
|
|