linux/fs/ceph/file.c

2120 lines
54 KiB
C
Raw Normal View History

License cleanup: add SPDX GPL-2.0 license identifier to files with no license Many source files in the tree are missing licensing information, which makes it harder for compliance tools to determine the correct license. By default all files without license information are under the default license of the kernel, which is GPL version 2. Update the files which contain no license information with the 'GPL-2.0' SPDX license identifier. The SPDX identifier is a legally binding shorthand, which can be used instead of the full boiler plate text. This patch is based on work done by Thomas Gleixner and Kate Stewart and Philippe Ombredanne. How this work was done: Patches were generated and checked against linux-4.14-rc6 for a subset of the use cases: - file had no licensing information it it. - file was a */uapi/* one with no licensing information in it, - file was a */uapi/* one with existing licensing information, Further patches will be generated in subsequent months to fix up cases where non-standard license headers were used, and references to license had to be inferred by heuristics based on keywords. The analysis to determine which SPDX License Identifier to be applied to a file was done in a spreadsheet of side by side results from of the output of two independent scanners (ScanCode & Windriver) producing SPDX tag:value files created by Philippe Ombredanne. Philippe prepared the base worksheet, and did an initial spot review of a few 1000 files. The 4.13 kernel was the starting point of the analysis with 60,537 files assessed. Kate Stewart did a file by file comparison of the scanner results in the spreadsheet to determine which SPDX license identifier(s) to be applied to the file. She confirmed any determination that was not immediately clear with lawyers working with the Linux Foundation. Criteria used to select files for SPDX license identifier tagging was: - Files considered eligible had to be source code files. - Make and config files were included as candidates if they contained >5 lines of source - File already had some variant of a license header in it (even if <5 lines). All documentation files were explicitly excluded. The following heuristics were used to determine which SPDX license identifiers to apply. - when both scanners couldn't find any license traces, file was considered to have no license information in it, and the top level COPYING file license applied. For non */uapi/* files that summary was: SPDX license identifier # files ---------------------------------------------------|------- GPL-2.0 11139 and resulted in the first patch in this series. If that file was a */uapi/* path one, it was "GPL-2.0 WITH Linux-syscall-note" otherwise it was "GPL-2.0". Results of that was: SPDX license identifier # files ---------------------------------------------------|------- GPL-2.0 WITH Linux-syscall-note 930 and resulted in the second patch in this series. - if a file had some form of licensing information in it, and was one of the */uapi/* ones, it was denoted with the Linux-syscall-note if any GPL family license was found in the file or had no licensing in it (per prior point). Results summary: SPDX license identifier # files ---------------------------------------------------|------ GPL-2.0 WITH Linux-syscall-note 270 GPL-2.0+ WITH Linux-syscall-note 169 ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) 21 ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) 17 LGPL-2.1+ WITH Linux-syscall-note 15 GPL-1.0+ WITH Linux-syscall-note 14 ((GPL-2.0+ WITH Linux-syscall-note) OR BSD-3-Clause) 5 LGPL-2.0+ WITH Linux-syscall-note 4 LGPL-2.1 WITH Linux-syscall-note 3 ((GPL-2.0 WITH Linux-syscall-note) OR MIT) 3 ((GPL-2.0 WITH Linux-syscall-note) AND MIT) 1 and that resulted in the third patch in this series. - when the two scanners agreed on the detected license(s), that became the concluded license(s). - when there was disagreement between the two scanners (one detected a license but the other didn't, or they both detected different licenses) a manual inspection of the file occurred. - In most cases a manual inspection of the information in the file resulted in a clear resolution of the license that should apply (and which scanner probably needed to revisit its heuristics). - When it was not immediately clear, the license identifier was confirmed with lawyers working with the Linux Foundation. - If there was any question as to the appropriate license identifier, the file was flagged for further research and to be revisited later in time. In total, over 70 hours of logged manual review was done on the spreadsheet to determine the SPDX license identifiers to apply to the source files by Kate, Philippe, Thomas and, in some cases, confirmation by lawyers working with the Linux Foundation. Kate also obtained a third independent scan of the 4.13 code base from FOSSology, and compared selected files where the other two scanners disagreed against that SPDX file, to see if there was new insights. The Windriver scanner is based on an older version of FOSSology in part, so they are related. Thomas did random spot checks in about 500 files from the spreadsheets for the uapi headers and agreed with SPDX license identifier in the files he inspected. For the non-uapi files Thomas did random spot checks in about 15000 files. In initial set of patches against 4.14-rc6, 3 files were found to have copy/paste license identifier errors, and have been fixed to reflect the correct identifier. Additionally Philippe spent 10 hours this week doing a detailed manual inspection and review of the 12,461 patched files from the initial patch version early this week with: - a full scancode scan run, collecting the matched texts, detected license ids and scores - reviewing anything where there was a license detected (about 500+ files) to ensure that the applied SPDX license was correct - reviewing anything where there was no detection but the patch license was not GPL-2.0 WITH Linux-syscall-note to ensure that the applied SPDX license was correct This produced a worksheet with 20 files needing minor correction. This worksheet was then exported into 3 different .csv files for the different types of files to be modified. These .csv files were then reviewed by Greg. Thomas wrote a script to parse the csv files and add the proper SPDX tag to the file, in the format that the file expected. This script was further refined by Greg based on the output to detect more types of files automatically and to distinguish between header and source .c files (which need different comment types.) Finally Greg ran the script using the .csv files to generate the patches. Reviewed-by: Kate Stewart <kstewart@linuxfoundation.org> Reviewed-by: Philippe Ombredanne <pombredanne@nexb.com> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2017-11-01 22:07:57 +08:00
// SPDX-License-Identifier: GPL-2.0
#include <linux/ceph/ceph_debug.h>
#include <linux/ceph/striper.h>
#include <linux/module.h>
#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>
#include <linux/file.h>
#include <linux/mount.h>
#include <linux/namei.h>
#include <linux/writeback.h>
#include <linux/falloc.h>
#include "super.h"
#include "mds_client.h"
#include "cache.h"
static __le32 ceph_flags_sys2wire(u32 flags)
{
u32 wire_flags = 0;
switch (flags & O_ACCMODE) {
case O_RDONLY:
wire_flags |= CEPH_O_RDONLY;
break;
case O_WRONLY:
wire_flags |= CEPH_O_WRONLY;
break;
case O_RDWR:
wire_flags |= CEPH_O_RDWR;
break;
}
flags &= ~O_ACCMODE;
#define ceph_sys2wire(a) if (flags & a) { wire_flags |= CEPH_##a; flags &= ~a; }
ceph_sys2wire(O_CREAT);
ceph_sys2wire(O_EXCL);
ceph_sys2wire(O_TRUNC);
ceph_sys2wire(O_DIRECTORY);
ceph_sys2wire(O_NOFOLLOW);
#undef ceph_sys2wire
if (flags)
dout("unused open flags: %x\n", flags);
return cpu_to_le32(wire_flags);
}
/*
* 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.
*/
/*
* How many pages to get in one call to iov_iter_get_pages(). This
* determines the size of the on-stack array used as a buffer.
*/
#define ITER_GET_BVECS_PAGES 64
static ssize_t __iter_get_bvecs(struct iov_iter *iter, size_t maxsize,
struct bio_vec *bvecs)
{
size_t size = 0;
int bvec_idx = 0;
if (maxsize > iov_iter_count(iter))
maxsize = iov_iter_count(iter);
while (size < maxsize) {
struct page *pages[ITER_GET_BVECS_PAGES];
ssize_t bytes;
size_t start;
int idx = 0;
bytes = iov_iter_get_pages(iter, pages, maxsize - size,
ITER_GET_BVECS_PAGES, &start);
if (bytes < 0)
return size ?: bytes;
iov_iter_advance(iter, bytes);
size += bytes;
for ( ; bytes; idx++, bvec_idx++) {
struct bio_vec bv = {
.bv_page = pages[idx],
.bv_len = min_t(int, bytes, PAGE_SIZE - start),
.bv_offset = start,
};
bvecs[bvec_idx] = bv;
bytes -= bv.bv_len;
start = 0;
}
}
return size;
}
/*
* iov_iter_get_pages() only considers one iov_iter segment, no matter
* what maxsize or maxpages are given. For ITER_BVEC that is a single
* page.
*
* Attempt to get up to @maxsize bytes worth of pages from @iter.
* Return the number of bytes in the created bio_vec array, or an error.
*/
static ssize_t iter_get_bvecs_alloc(struct iov_iter *iter, size_t maxsize,
struct bio_vec **bvecs, int *num_bvecs)
{
struct bio_vec *bv;
size_t orig_count = iov_iter_count(iter);
ssize_t bytes;
int npages;
iov_iter_truncate(iter, maxsize);
npages = iov_iter_npages(iter, INT_MAX);
iov_iter_reexpand(iter, orig_count);
/*
* __iter_get_bvecs() may populate only part of the array -- zero it
* out.
*/
bv = kvmalloc_array(npages, sizeof(*bv), GFP_KERNEL | __GFP_ZERO);
if (!bv)
return -ENOMEM;
bytes = __iter_get_bvecs(iter, maxsize, bv);
if (bytes < 0) {
/*
* No pages were pinned -- just free the array.
*/
kvfree(bv);
return bytes;
}
*bvecs = bv;
*num_bvecs = npages;
return bytes;
}
static void put_bvecs(struct bio_vec *bvecs, int num_bvecs, bool should_dirty)
{
int i;
for (i = 0; i < num_bvecs; i++) {
if (bvecs[i].bv_page) {
if (should_dirty)
set_page_dirty_lock(bvecs[i].bv_page);
put_page(bvecs[i].bv_page);
}
}
kvfree(bvecs);
}
/*
* 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)
{
struct ceph_fs_client *fsc = ceph_sb_to_client(sb);
struct ceph_mds_client *mdsc = fsc->mdsc;
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 = ceph_flags_sys2wire(flags);
req->r_args.open.mode = cpu_to_le32(create_mode);
out:
return req;
}
static int ceph_init_file_info(struct inode *inode, struct file *file,
int fmode, bool isdir)
{
struct ceph_file_info *fi;
dout("%s %p %p 0%o (%s)\n", __func__, inode, file,
inode->i_mode, isdir ? "dir" : "regular");
BUG_ON(inode->i_fop->release != ceph_release);
if (isdir) {
struct ceph_dir_file_info *dfi =
kmem_cache_zalloc(ceph_dir_file_cachep, GFP_KERNEL);
if (!dfi) {
ceph_put_fmode(ceph_inode(inode), fmode); /* clean up */
return -ENOMEM;
}
file->private_data = dfi;
fi = &dfi->file_info;
dfi->next_offset = 2;
dfi->readdir_cache_idx = -1;
} else {
fi = kmem_cache_zalloc(ceph_file_cachep, GFP_KERNEL);
if (!fi) {
ceph_put_fmode(ceph_inode(inode), fmode); /* clean up */
return -ENOMEM;
}
file->private_data = fi;
}
fi->fmode = fmode;
spin_lock_init(&fi->rw_contexts_lock);
INIT_LIST_HEAD(&fi->rw_contexts);
return 0;
}
/*
* 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)
{
int ret = 0;
switch (inode->i_mode & S_IFMT) {
case S_IFREG:
ceph_fscache_register_inode_cookie(inode);
ceph_fscache_file_set_cookie(inode, file);
fs: mark expected switch fall-throughs In preparation to enabling -Wimplicit-fallthrough, mark switch cases where we are expecting to fall through. This patch fixes the following warnings: fs/affs/affs.h:124:38: warning: this statement may fall through [-Wimplicit-fallthrough=] fs/configfs/dir.c:1692:11: warning: this statement may fall through [-Wimplicit-fallthrough=] fs/configfs/dir.c:1694:7: warning: this statement may fall through [-Wimplicit-fallthrough=] fs/ceph/file.c:249:3: warning: this statement may fall through [-Wimplicit-fallthrough=] fs/ext4/hash.c:233:15: warning: this statement may fall through [-Wimplicit-fallthrough=] fs/ext4/hash.c:246:15: warning: this statement may fall through [-Wimplicit-fallthrough=] fs/ext2/inode.c:1237:7: warning: this statement may fall through [-Wimplicit-fallthrough=] fs/ext2/inode.c:1244:7: warning: this statement may fall through [-Wimplicit-fallthrough=] fs/ext4/indirect.c:1182:6: warning: this statement may fall through [-Wimplicit-fallthrough=] fs/ext4/indirect.c:1188:6: warning: this statement may fall through [-Wimplicit-fallthrough=] fs/ext4/indirect.c:1432:6: warning: this statement may fall through [-Wimplicit-fallthrough=] fs/ext4/indirect.c:1440:6: warning: this statement may fall through [-Wimplicit-fallthrough=] fs/f2fs/node.c:618:8: warning: this statement may fall through [-Wimplicit-fallthrough=] fs/f2fs/node.c:620:8: warning: this statement may fall through [-Wimplicit-fallthrough=] fs/btrfs/ref-verify.c:522:15: warning: this statement may fall through [-Wimplicit-fallthrough=] fs/gfs2/bmap.c:711:7: warning: this statement may fall through [-Wimplicit-fallthrough=] fs/gfs2/bmap.c:722:7: warning: this statement may fall through [-Wimplicit-fallthrough=] fs/jffs2/fs.c:339:6: warning: this statement may fall through [-Wimplicit-fallthrough=] fs/nfsd/nfs4proc.c:429:12: warning: this statement may fall through [-Wimplicit-fallthrough=] fs/ufs/util.h:62:6: warning: this statement may fall through [-Wimplicit-fallthrough=] fs/ufs/util.h:43:6: warning: this statement may fall through [-Wimplicit-fallthrough=] fs/fcntl.c:770:7: warning: this statement may fall through [-Wimplicit-fallthrough=] fs/seq_file.c:319:10: warning: this statement may fall through [-Wimplicit-fallthrough=] fs/libfs.c:148:11: warning: this statement may fall through [-Wimplicit-fallthrough=] fs/libfs.c:150:7: warning: this statement may fall through [-Wimplicit-fallthrough=] fs/signalfd.c:178:7: warning: this statement may fall through [-Wimplicit-fallthrough=] fs/locks.c:1473:16: warning: this statement may fall through [-Wimplicit-fallthrough=] Warning level 3 was used: -Wimplicit-fallthrough=3 This patch is part of the ongoing efforts to enabling -Wimplicit-fallthrough. Reviewed-by: Kees Cook <keescook@chromium.org> Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
2019-01-23 16:48:28 +08:00
/* fall through */
case S_IFDIR:
ret = ceph_init_file_info(inode, file, fmode,
S_ISDIR(inode->i_mode));
if (ret)
return ret;
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;
}
/*
* try renew caps after session gets killed.
*/
int ceph_renew_caps(struct inode *inode)
{
struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_mds_request *req;
int err, flags, wanted;
spin_lock(&ci->i_ceph_lock);
wanted = __ceph_caps_file_wanted(ci);
if (__ceph_is_any_real_caps(ci) &&
(!(wanted & CEPH_CAP_ANY_WR) || ci->i_auth_cap)) {
int issued = __ceph_caps_issued(ci, NULL);
spin_unlock(&ci->i_ceph_lock);
dout("renew caps %p want %s issued %s updating mds_wanted\n",
inode, ceph_cap_string(wanted), ceph_cap_string(issued));
ceph_check_caps(ci, 0, NULL);
return 0;
}
spin_unlock(&ci->i_ceph_lock);
flags = 0;
if ((wanted & CEPH_CAP_FILE_RD) && (wanted & CEPH_CAP_FILE_WR))
flags = O_RDWR;
else if (wanted & CEPH_CAP_FILE_RD)
flags = O_RDONLY;
else if (wanted & CEPH_CAP_FILE_WR)
flags = O_WRONLY;
#ifdef O_LAZY
if (wanted & CEPH_CAP_FILE_LAZYIO)
flags |= O_LAZY;
#endif
req = prepare_open_request(inode->i_sb, flags, 0);
if (IS_ERR(req)) {
err = PTR_ERR(req);
goto out;
}
req->r_inode = inode;
ihold(inode);
req->r_num_caps = 1;
req->r_fmode = -1;
err = ceph_mdsc_do_request(mdsc, NULL, req);
ceph_mdsc_put_request(req);
out:
dout("renew caps %p open result=%d\n", inode, err);
return err < 0 ? err : 0;
}
/*
* 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);
struct ceph_fs_client *fsc = ceph_sb_to_client(inode->i_sb);
struct ceph_mds_client *mdsc = fsc->mdsc;
struct ceph_mds_request *req;
struct ceph_file_info *fi = file->private_data;
int err;
int flags, fmode, wanted;
if (fi) {
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) {
spin_lock(&ci->i_ceph_lock);
__ceph_get_fmode(ci, fmode);
spin_unlock(&ci->i_ceph_lock);
return ceph_init_file(inode, file, fmode);
}
/*
* No need to block if we have caps on the auth MDS (for
* write) or any MDS (for read). Update wanted set
* asynchronously.
*/
spin_lock(&ci->i_ceph_lock);
if (__ceph_is_any_real_caps(ci) &&
(((fmode & CEPH_FILE_MODE_WR) == 0) || ci->i_auth_cap)) {
int mds_wanted = __ceph_caps_mds_wanted(ci, true);
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);
spin_unlock(&ci->i_ceph_lock);
/* 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);
spin_unlock(&ci->i_ceph_lock);
return ceph_init_file(inode, file, fmode);
}
spin_unlock(&ci->i_ceph_lock);
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;
}
req->r_inode = inode;
ihold(inode);
req->r_num_caps = 1;
err = ceph_mdsc_do_request(mdsc, NULL, req);
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;
}
/*
* Do a lookup + open with a single request. If we get a non-existent
* file or symlink, return 1 so the VFS can retry.
*/
int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
struct file *file, unsigned flags, umode_t mode)
{
struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb);
struct ceph_mds_client *mdsc = fsc->mdsc;
struct ceph_mds_request *req;
struct dentry *dn;
struct ceph_acls_info acls = {};
int mask;
int err;
dout("atomic_open %p dentry %p '%pd' %s flags %d mode 0%o\n",
dir, dentry, dentry,
d_unhashed(dentry) ? "unhashed" : "hashed", flags, mode);
if (dentry->d_name.len > NAME_MAX)
return -ENAMETOOLONG;
if (flags & O_CREAT) {
if (ceph_quota_is_max_files_exceeded(dir))
return -EDQUOT;
err = ceph_pre_init_acls(dir, &mode, &acls);
if (err < 0)
return err;
}
/* do the open */
req = prepare_open_request(dir->i_sb, flags, mode);
if (IS_ERR(req)) {
err = PTR_ERR(req);
goto out_acl;
}
req->r_dentry = dget(dentry);
req->r_num_caps = 2;
if (flags & O_CREAT) {
req->r_dentry_drop = CEPH_CAP_FILE_SHARED | CEPH_CAP_AUTH_EXCL;
req->r_dentry_unless = CEPH_CAP_FILE_EXCL;
if (acls.pagelist) {
req->r_pagelist = acls.pagelist;
acls.pagelist = NULL;
}
}
mask = CEPH_STAT_CAP_INODE | CEPH_CAP_AUTH_SHARED;
if (ceph_security_xattr_wanted(dir))
mask |= CEPH_CAP_XATTR_SHARED;
req->r_args.open.mask = cpu_to_le32(mask);
req->r_parent = dir;
set_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags);
err = ceph_mdsc_do_request(mdsc,
(flags & (O_CREAT|O_TRUNC)) ? dir : NULL,
req);
err = ceph_handle_snapdir(req, dentry, err);
if (err)
goto out_req;
if ((flags & O_CREAT) && !req->r_reply_info.head->is_dentry)
err = ceph_handle_notrace_create(dir, dentry);
if (d_in_lookup(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_req;
if (dn || d_really_is_negative(dentry) || d_is_symlink(dentry)) {
/* 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);
if (req->r_op == CEPH_MDS_OP_CREATE && req->r_reply_info.has_create_ino) {
ceph_init_inode_acls(d_inode(dentry), &acls);
file->f_mode |= FMODE_CREATED;
}
err = finish_open(file, dentry, ceph_open);
}
out_req:
if (!req->r_err && req->r_target_inode)
ceph_put_fmode(ceph_inode(req->r_target_inode), req->r_fmode);
ceph_mdsc_put_request(req);
out_acl:
ceph_release_acls_info(&acls);
dout("atomic_open result=%d\n", err);
return err;
}
int ceph_release(struct inode *inode, struct file *file)
{
struct ceph_inode_info *ci = ceph_inode(inode);
if (S_ISDIR(inode->i_mode)) {
struct ceph_dir_file_info *dfi = file->private_data;
dout("release inode %p dir file %p\n", inode, file);
WARN_ON(!list_empty(&dfi->file_info.rw_contexts));
ceph_put_fmode(ci, dfi->file_info.fmode);
if (dfi->last_readdir)
ceph_mdsc_put_request(dfi->last_readdir);
kfree(dfi->last_name);
kfree(dfi->dir_info);
kmem_cache_free(ceph_dir_file_cachep, dfi);
} else {
struct ceph_file_info *fi = file->private_data;
dout("release inode %p regular file %p\n", inode, file);
WARN_ON(!list_empty(&fi->rw_contexts));
ceph_put_fmode(ci, fi->fmode);
kmem_cache_free(ceph_file_cachep, fi);
}
/* wake up anyone waiting for caps on this inode */
wake_up_all(&ci->i_cap_wq);
return 0;
}
enum {
HAVE_RETRIED = 1,
CHECK_EOF = 2,
READ_INLINE = 3,
};
/*
* 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. (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 ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *to,
int *retry_op)
{
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_osd_client *osdc = &fsc->client->osdc;
ssize_t ret;
u64 off = iocb->ki_pos;
u64 len = iov_iter_count(to);
dout("sync_read on file %p %llu~%u %s\n", file, off, (unsigned)len,
(file->f_flags & O_DIRECT) ? "O_DIRECT" : "");
if (!len)
return 0;
/*
* 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.
*/
ret = filemap_write_and_wait_range(inode->i_mapping,
off, off + len - 1);
if (ret < 0)
return ret;
ret = 0;
while ((len = iov_iter_count(to)) > 0) {
struct ceph_osd_request *req;
struct page **pages;
int num_pages;
size_t page_off;
u64 i_size;
bool more;
req = ceph_osdc_new_request(osdc, &ci->i_layout,
ci->i_vino, off, &len, 0, 1,
CEPH_OSD_OP_READ, CEPH_OSD_FLAG_READ,
NULL, ci->i_truncate_seq,
ci->i_truncate_size, false);
if (IS_ERR(req)) {
ret = PTR_ERR(req);
break;
}
more = len < iov_iter_count(to);
if (unlikely(iov_iter_is_pipe(to))) {
ret = iov_iter_get_pages_alloc(to, &pages, len,
&page_off);
if (ret <= 0) {
ceph_osdc_put_request(req);
ret = -ENOMEM;
break;
}
num_pages = DIV_ROUND_UP(ret + page_off, PAGE_SIZE);
if (ret < len) {
len = ret;
osd_req_op_extent_update(req, 0, len);
more = false;
}
} else {
num_pages = calc_pages_for(off, len);
page_off = off & ~PAGE_MASK;
pages = ceph_alloc_page_vector(num_pages, GFP_KERNEL);
if (IS_ERR(pages)) {
ceph_osdc_put_request(req);
ret = PTR_ERR(pages);
break;
}
}
osd_req_op_extent_osd_data_pages(req, 0, pages, len, page_off,
false, false);
ret = ceph_osdc_start_request(osdc, req, false);
if (!ret)
ret = ceph_osdc_wait_request(osdc, req);
ceph_osdc_put_request(req);
i_size = i_size_read(inode);
dout("sync_read %llu~%llu got %zd i_size %llu%s\n",
off, len, ret, i_size, (more ? " MORE" : ""));
if (ret == -ENOENT)
ret = 0;
if (ret >= 0 && ret < len && (off + ret < i_size)) {
int zlen = min(len - ret, i_size - off - ret);
int zoff = page_off + ret;
dout("sync_read zero gap %llu~%llu\n",
off + ret, off + ret + zlen);
ceph_zero_page_vector_range(zoff, zlen, pages);
ret += zlen;
}
if (unlikely(iov_iter_is_pipe(to))) {
if (ret > 0) {
iov_iter_advance(to, ret);
off += ret;
} else {
iov_iter_advance(to, 0);
}
ceph_put_page_vector(pages, num_pages, false);
} else {
int idx = 0;
size_t left = ret > 0 ? ret : 0;
while (left > 0) {
size_t len, copied;
page_off = off & ~PAGE_MASK;
len = min_t(size_t, left, PAGE_SIZE - page_off);
copied = copy_page_to_iter(pages[idx++],
page_off, len, to);
off += copied;
left -= copied;
if (copied < len) {
ret = -EFAULT;
break;
}
}
ceph_release_page_vector(pages, num_pages);
}
if (ret <= 0 || off >= i_size || !more)
break;
}
if (off > iocb->ki_pos) {
if (ret >= 0 &&
iov_iter_count(to) > 0 && off >= i_size_read(inode))
*retry_op = CHECK_EOF;
ret = off - iocb->ki_pos;
iocb->ki_pos = off;
}
dout("sync_read result %zd retry_op %d\n", ret, *retry_op);
return ret;
}
struct ceph_aio_request {
struct kiocb *iocb;
size_t total_len;
bool write;
bool should_dirty;
int error;
struct list_head osd_reqs;
unsigned num_reqs;
atomic_t pending_reqs;
struct timespec64 mtime;
struct ceph_cap_flush *prealloc_cf;
};
struct ceph_aio_work {
struct work_struct work;
struct ceph_osd_request *req;
};
static void ceph_aio_retry_work(struct work_struct *work);
static void ceph_aio_complete(struct inode *inode,
struct ceph_aio_request *aio_req)
{
struct ceph_inode_info *ci = ceph_inode(inode);
int ret;
if (!atomic_dec_and_test(&aio_req->pending_reqs))
return;
ret = aio_req->error;
if (!ret)
ret = aio_req->total_len;
dout("ceph_aio_complete %p rc %d\n", inode, ret);
if (ret >= 0 && aio_req->write) {
int dirty;
loff_t endoff = aio_req->iocb->ki_pos + aio_req->total_len;
if (endoff > i_size_read(inode)) {
if (ceph_inode_set_size(inode, endoff))
ceph_check_caps(ci, CHECK_CAPS_AUTHONLY, NULL);
}
spin_lock(&ci->i_ceph_lock);
ci->i_inline_version = CEPH_INLINE_NONE;
dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_FILE_WR,
&aio_req->prealloc_cf);
spin_unlock(&ci->i_ceph_lock);
if (dirty)
__mark_inode_dirty(inode, dirty);
}
ceph_put_cap_refs(ci, (aio_req->write ? CEPH_CAP_FILE_WR :
CEPH_CAP_FILE_RD));
aio_req->iocb->ki_complete(aio_req->iocb, ret, 0);
ceph_free_cap_flush(aio_req->prealloc_cf);
kfree(aio_req);
}
static void ceph_aio_complete_req(struct ceph_osd_request *req)
{
int rc = req->r_result;
struct inode *inode = req->r_inode;
struct ceph_aio_request *aio_req = req->r_priv;
struct ceph_osd_data *osd_data = osd_req_op_extent_osd_data(req, 0);
BUG_ON(osd_data->type != CEPH_OSD_DATA_TYPE_BVECS);
BUG_ON(!osd_data->num_bvecs);
dout("ceph_aio_complete_req %p rc %d bytes %u\n",
inode, rc, osd_data->bvec_pos.iter.bi_size);
if (rc == -EOLDSNAPC) {
struct ceph_aio_work *aio_work;
BUG_ON(!aio_req->write);
aio_work = kmalloc(sizeof(*aio_work), GFP_NOFS);
if (aio_work) {
INIT_WORK(&aio_work->work, ceph_aio_retry_work);
aio_work->req = req;
queue_work(ceph_inode_to_client(inode)->wb_wq,
&aio_work->work);
return;
}
rc = -ENOMEM;
} else if (!aio_req->write) {
if (rc == -ENOENT)
rc = 0;
if (rc >= 0 && osd_data->bvec_pos.iter.bi_size > rc) {
struct iov_iter i;
int zlen = osd_data->bvec_pos.iter.bi_size - rc;
/*
* If read is satisfied by single OSD request,
* it can pass EOF. Otherwise read is within
* i_size.
*/
if (aio_req->num_reqs == 1) {
loff_t i_size = i_size_read(inode);
loff_t endoff = aio_req->iocb->ki_pos + rc;
if (endoff < i_size)
zlen = min_t(size_t, zlen,
i_size - endoff);
aio_req->total_len = rc + zlen;
}
iov_iter_bvec(&i, READ, osd_data->bvec_pos.bvecs,
osd_data->num_bvecs,
osd_data->bvec_pos.iter.bi_size);
iov_iter_advance(&i, rc);
iov_iter_zero(zlen, &i);
}
}
put_bvecs(osd_data->bvec_pos.bvecs, osd_data->num_bvecs,
aio_req->should_dirty);
ceph_osdc_put_request(req);
if (rc < 0)
cmpxchg(&aio_req->error, 0, rc);
ceph_aio_complete(inode, aio_req);
return;
}
static void ceph_aio_retry_work(struct work_struct *work)
{
struct ceph_aio_work *aio_work =
container_of(work, struct ceph_aio_work, work);
struct ceph_osd_request *orig_req = aio_work->req;
struct ceph_aio_request *aio_req = orig_req->r_priv;
struct inode *inode = orig_req->r_inode;
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_snap_context *snapc;
struct ceph_osd_request *req;
int ret;
spin_lock(&ci->i_ceph_lock);
if (__ceph_have_pending_cap_snap(ci)) {
struct ceph_cap_snap *capsnap =
list_last_entry(&ci->i_cap_snaps,
struct ceph_cap_snap,
ci_item);
snapc = ceph_get_snap_context(capsnap->context);
} else {
BUG_ON(!ci->i_head_snapc);
snapc = ceph_get_snap_context(ci->i_head_snapc);
}
spin_unlock(&ci->i_ceph_lock);
req = ceph_osdc_alloc_request(orig_req->r_osdc, snapc, 1,
false, GFP_NOFS);
if (!req) {
ret = -ENOMEM;
req = orig_req;
goto out;
}
req->r_flags = /* CEPH_OSD_FLAG_ORDERSNAP | */ CEPH_OSD_FLAG_WRITE;
ceph_oloc_copy(&req->r_base_oloc, &orig_req->r_base_oloc);
ceph_oid_copy(&req->r_base_oid, &orig_req->r_base_oid);
req->r_ops[0] = orig_req->r_ops[0];
req->r_mtime = aio_req->mtime;
req->r_data_offset = req->r_ops[0].extent.offset;
ret = ceph_osdc_alloc_messages(req, GFP_NOFS);
if (ret) {
ceph_osdc_put_request(req);
req = orig_req;
goto out;
}
ceph_osdc_put_request(orig_req);
req->r_callback = ceph_aio_complete_req;
req->r_inode = inode;
req->r_priv = aio_req;
ret = ceph_osdc_start_request(req->r_osdc, req, false);
out:
if (ret < 0) {
req->r_result = ret;
ceph_aio_complete_req(req);
}
ceph_put_snap_context(snapc);
kfree(aio_work);
}
static ssize_t
ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
struct ceph_snap_context *snapc,
struct ceph_cap_flush **pcf)
{
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_vino vino;
struct ceph_osd_request *req;
struct bio_vec *bvecs;
struct ceph_aio_request *aio_req = NULL;
int num_pages = 0;
int flags;
int ret;
struct timespec64 mtime = current_time(inode);
size_t count = iov_iter_count(iter);
loff_t pos = iocb->ki_pos;
bool write = iov_iter_rw(iter) == WRITE;
bool should_dirty = !write && iter_is_iovec(iter);
if (write && ceph_snap(file_inode(file)) != CEPH_NOSNAP)
return -EROFS;
dout("sync_direct_%s on file %p %lld~%u snapc %p seq %lld\n",
(write ? "write" : "read"), file, pos, (unsigned)count,
snapc, snapc ? snapc->seq : 0);
ret = filemap_write_and_wait_range(inode->i_mapping,
pos, pos + count - 1);
if (ret < 0)
return ret;
if (write) {
int ret2 = invalidate_inode_pages2_range(inode->i_mapping,
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
pos >> PAGE_SHIFT,
(pos + count - 1) >> PAGE_SHIFT);
if (ret2 < 0)
dout("invalidate_inode_pages2_range returned %d\n", ret2);
flags = /* CEPH_OSD_FLAG_ORDERSNAP | */ CEPH_OSD_FLAG_WRITE;
} else {
flags = CEPH_OSD_FLAG_READ;
}
while (iov_iter_count(iter) > 0) {
u64 size = iov_iter_count(iter);
ssize_t len;
if (write)
size = min_t(u64, size, fsc->mount_options->wsize);
else
size = min_t(u64, size, fsc->mount_options->rsize);
vino = ceph_vino(inode);
req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout,
vino, pos, &size, 0,
1,
write ? CEPH_OSD_OP_WRITE :
CEPH_OSD_OP_READ,
flags, snapc,
ci->i_truncate_seq,
ci->i_truncate_size,
false);
if (IS_ERR(req)) {
ret = PTR_ERR(req);
break;
}
len = iter_get_bvecs_alloc(iter, size, &bvecs, &num_pages);
if (len < 0) {
ceph_osdc_put_request(req);
ret = len;
break;
}
if (len != size)
osd_req_op_extent_update(req, 0, len);
/*
* To simplify error handling, allow AIO when IO within i_size
* or IO can be satisfied by single OSD request.
*/
if (pos == iocb->ki_pos && !is_sync_kiocb(iocb) &&
(len == count || pos + count <= i_size_read(inode))) {
aio_req = kzalloc(sizeof(*aio_req), GFP_KERNEL);
if (aio_req) {
aio_req->iocb = iocb;
aio_req->write = write;
aio_req->should_dirty = should_dirty;
INIT_LIST_HEAD(&aio_req->osd_reqs);
if (write) {
aio_req->mtime = mtime;
swap(aio_req->prealloc_cf, *pcf);
}
}
/* ignore error */
}
if (write) {
/*
* throw out any page cache pages in this range. this
* may block.
*/
truncate_inode_pages_range(inode->i_mapping, pos,
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
(pos+len) | (PAGE_SIZE - 1));
req->r_mtime = mtime;
}
osd_req_op_extent_osd_data_bvecs(req, 0, bvecs, num_pages, len);
if (aio_req) {
aio_req->total_len += len;
aio_req->num_reqs++;
atomic_inc(&aio_req->pending_reqs);
req->r_callback = ceph_aio_complete_req;
req->r_inode = inode;
req->r_priv = aio_req;
list_add_tail(&req->r_unsafe_item, &aio_req->osd_reqs);
pos += len;
continue;
}
ret = ceph_osdc_start_request(req->r_osdc, req, false);
if (!ret)
ret = ceph_osdc_wait_request(&fsc->client->osdc, req);
size = i_size_read(inode);
if (!write) {
if (ret == -ENOENT)
ret = 0;
if (ret >= 0 && ret < len && pos + ret < size) {
struct iov_iter i;
int zlen = min_t(size_t, len - ret,
size - pos - ret);
iov_iter_bvec(&i, READ, bvecs, num_pages, len);
iov_iter_advance(&i, ret);
iov_iter_zero(zlen, &i);
ret += zlen;
}
if (ret >= 0)
len = ret;
}
put_bvecs(bvecs, num_pages, should_dirty);
ceph_osdc_put_request(req);
if (ret < 0)
break;
pos += len;
if (!write && pos >= size)
break;
if (write && pos > size) {
if (ceph_inode_set_size(inode, pos))
ceph_check_caps(ceph_inode(inode),
CHECK_CAPS_AUTHONLY,
NULL);
}
}
if (aio_req) {
LIST_HEAD(osd_reqs);
if (aio_req->num_reqs == 0) {
kfree(aio_req);
return ret;
}
ceph_get_cap_refs(ci, write ? CEPH_CAP_FILE_WR :
CEPH_CAP_FILE_RD);
list_splice(&aio_req->osd_reqs, &osd_reqs);
while (!list_empty(&osd_reqs)) {
req = list_first_entry(&osd_reqs,
struct ceph_osd_request,
r_unsafe_item);
list_del_init(&req->r_unsafe_item);
if (ret >= 0)
ret = ceph_osdc_start_request(req->r_osdc,
req, false);
if (ret < 0) {
req->r_result = ret;
ceph_aio_complete_req(req);
}
}
return -EIOCBQUEUED;
}
if (ret != -EOLDSNAPC && pos > iocb->ki_pos) {
ret = pos - iocb->ki_pos;
iocb->ki_pos = pos;
}
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, struct iov_iter *from, loff_t pos,
struct ceph_snap_context *snapc)
{
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_vino vino;
struct ceph_osd_request *req;
struct page **pages;
u64 len;
int num_pages;
int written = 0;
int flags;
int ret;
bool check_caps = false;
struct timespec64 mtime = current_time(inode);
size_t count = iov_iter_count(from);
if (ceph_snap(file_inode(file)) != CEPH_NOSNAP)
return -EROFS;
dout("sync_write on file %p %lld~%u snapc %p seq %lld\n",
file, pos, (unsigned)count, snapc, snapc->seq);
ret = filemap_write_and_wait_range(inode->i_mapping,
pos, pos + count - 1);
if (ret < 0)
return ret;
ret = invalidate_inode_pages2_range(inode->i_mapping,
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
pos >> PAGE_SHIFT,
(pos + count - 1) >> PAGE_SHIFT);
if (ret < 0)
dout("invalidate_inode_pages2_range returned %d\n", ret);
flags = /* CEPH_OSD_FLAG_ORDERSNAP | */ CEPH_OSD_FLAG_WRITE;
while ((len = iov_iter_count(from)) > 0) {
size_t left;
int n;
vino = ceph_vino(inode);
req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout,
vino, pos, &len, 0, 1,
CEPH_OSD_OP_WRITE, flags, snapc,
ci->i_truncate_seq,
ci->i_truncate_size,
false);
if (IS_ERR(req)) {
ret = PTR_ERR(req);
break;
}
/*
* write from beginning of first page,
* regardless of io alignment
*/
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
num_pages = (len + PAGE_SIZE - 1) >> PAGE_SHIFT;
pages = ceph_alloc_page_vector(num_pages, GFP_KERNEL);
if (IS_ERR(pages)) {
ret = PTR_ERR(pages);
goto out;
}
left = len;
for (n = 0; n < num_pages; n++) {
size_t plen = min_t(size_t, left, PAGE_SIZE);
ret = copy_page_from_iter(pages[n], 0, plen, from);
if (ret != plen) {
ret = -EFAULT;
break;
}
left -= ret;
}
if (ret < 0) {
ceph_release_page_vector(pages, num_pages);
goto out;
}
req->r_inode = inode;
osd_req_op_extent_osd_data_pages(req, 0, pages, len, 0,
false, true);
req->r_mtime = mtime;
ret = ceph_osdc_start_request(&fsc->client->osdc, req, false);
if (!ret)
ret = ceph_osdc_wait_request(&fsc->client->osdc, req);
out:
ceph_osdc_put_request(req);
if (ret != 0) {
ceph_set_error_write(ci);
break;
}
ceph_clear_error_write(ci);
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);
}
}
if (ret != -EOLDSNAPC && written > 0) {
ret = written;
iocb->ki_pos = pos;
}
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_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
struct file *filp = iocb->ki_filp;
struct ceph_file_info *fi = filp->private_data;
size_t len = iov_iter_count(to);
struct inode *inode = file_inode(filp);
struct ceph_inode_info *ci = ceph_inode(inode);
struct page *pinned_page = NULL;
ssize_t ret;
int want, got = 0;
int retry_op = 0, read = 0;
again:
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);
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, -1, &got, &pinned_page);
if (ret < 0)
return ret;
if ((got & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)) == 0 ||
(iocb->ki_flags & IOCB_DIRECT) ||
(fi->flags & CEPH_F_SYNC)) {
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 (ci->i_inline_version == CEPH_INLINE_NONE) {
if (!retry_op && (iocb->ki_flags & IOCB_DIRECT)) {
ret = ceph_direct_read_write(iocb, to,
NULL, NULL);
if (ret >= 0 && ret < len)
retry_op = CHECK_EOF;
} else {
ret = ceph_sync_read(iocb, to, &retry_op);
}
} else {
retry_op = READ_INLINE;
}
} else {
CEPH_DEFINE_RW_CONTEXT(rw_ctx, got);
dout("aio_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));
ceph_add_rw_context(fi, &rw_ctx);
ret = generic_file_read_iter(iocb, to);
ceph_del_rw_context(fi, &rw_ctx);
}
dout("aio_read %p %llx.%llx dropping cap refs on %s = %d\n",
inode, ceph_vinop(inode), ceph_cap_string(got), (int)ret);
if (pinned_page) {
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
put_page(pinned_page);
pinned_page = NULL;
}
ceph_put_cap_refs(ci, got);
if (retry_op > HAVE_RETRIED && ret >= 0) {
int statret;
struct page *page = NULL;
loff_t i_size;
if (retry_op == READ_INLINE) {
page = __page_cache_alloc(GFP_KERNEL);
if (!page)
return -ENOMEM;
}
statret = __ceph_do_getattr(inode, page,
CEPH_STAT_CAP_INLINE_DATA, !!page);
if (statret < 0) {
if (page)
__free_page(page);
if (statret == -ENODATA) {
BUG_ON(retry_op != READ_INLINE);
goto again;
}
return statret;
}
i_size = i_size_read(inode);
if (retry_op == READ_INLINE) {
BUG_ON(ret > 0 || read > 0);
if (iocb->ki_pos < i_size &&
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
iocb->ki_pos < PAGE_SIZE) {
loff_t end = min_t(loff_t, i_size,
iocb->ki_pos + len);
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
end = min_t(loff_t, end, PAGE_SIZE);
if (statret < end)
zero_user_segment(page, statret, end);
ret = copy_page_to_iter(page,
iocb->ki_pos & ~PAGE_MASK,
end - iocb->ki_pos, to);
iocb->ki_pos += ret;
read += ret;
}
if (iocb->ki_pos < i_size && read < len) {
size_t zlen = min_t(size_t, len - read,
i_size - iocb->ki_pos);
ret = iov_iter_zero(zlen, to);
iocb->ki_pos += ret;
read += ret;
}
__free_pages(page, 0);
return read;
}
/* hit EOF or hole? */
if (retry_op == CHECK_EOF && iocb->ki_pos < i_size &&
ret < len) {
dout("sync_read hit hole, ppos %lld < size %lld"
", reading more\n", iocb->ki_pos, i_size);
read += ret;
len -= ret;
retry_op = HAVE_RETRIED;
goto again;
}
}
if (ret >= 0)
ret += read;
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_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
struct ceph_file_info *fi = file->private_data;
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_cap_flush *prealloc_cf;
ssize_t count, written = 0;
int err, want, got;
loff_t pos;
loff_t limit = max(i_size_read(inode), fsc->max_file_size);
if (ceph_snap(inode) != CEPH_NOSNAP)
return -EROFS;
prealloc_cf = ceph_alloc_cap_flush();
if (!prealloc_cf)
return -ENOMEM;
retry_snap:
inode_lock(inode);
/* We can write back this queue in page reclaim */
current->backing_dev_info = inode_to_bdi(inode);
if (iocb->ki_flags & IOCB_APPEND) {
err = ceph_do_getattr(inode, CEPH_STAT_CAP_SIZE, false);
if (err < 0)
goto out;
}
err = generic_write_checks(iocb, from);
if (err <= 0)
goto out;
pos = iocb->ki_pos;
if (unlikely(pos >= limit)) {
err = -EFBIG;
goto out;
} else {
iov_iter_truncate(from, limit - pos);
}
count = iov_iter_count(from);
if (ceph_quota_is_max_bytes_exceeded(inode, pos + count)) {
err = -EDQUOT;
goto out;
}
err = file_remove_privs(file);
if (err)
goto out;
err = file_update_time(file);
if (err)
goto out;
if (ci->i_inline_version != CEPH_INLINE_NONE) {
err = ceph_uninline_data(file, NULL);
if (err < 0)
goto out;
}
/* FIXME: not complete since it doesn't account for being at quota */
if (ceph_osdmap_flag(&fsc->client->osdc, CEPH_OSDMAP_FULL)) {
err = -ENOSPC;
goto out;
}
dout("aio_write %p %llx.%llx %llu~%zd getting caps. i_size %llu\n",
inode, ceph_vinop(inode), pos, count, i_size_read(inode));
if (fi->fmode & CEPH_FILE_MODE_LAZY)
want = CEPH_CAP_FILE_BUFFER | CEPH_CAP_FILE_LAZYIO;
else
want = CEPH_CAP_FILE_BUFFER;
got = 0;
err = ceph_get_caps(ci, CEPH_CAP_FILE_WR, want, pos + count,
&got, NULL);
if (err < 0)
goto out;
dout("aio_write %p %llx.%llx %llu~%zd got cap refs on %s\n",
inode, ceph_vinop(inode), pos, count, ceph_cap_string(got));
if ((got & (CEPH_CAP_FILE_BUFFER|CEPH_CAP_FILE_LAZYIO)) == 0 ||
(iocb->ki_flags & IOCB_DIRECT) || (fi->flags & CEPH_F_SYNC) ||
(ci->i_ceph_flags & CEPH_I_ERROR_WRITE)) {
struct ceph_snap_context *snapc;
struct iov_iter data;
inode_unlock(inode);
spin_lock(&ci->i_ceph_lock);
if (__ceph_have_pending_cap_snap(ci)) {
struct ceph_cap_snap *capsnap =
list_last_entry(&ci->i_cap_snaps,
struct ceph_cap_snap,
ci_item);
snapc = ceph_get_snap_context(capsnap->context);
} else {
BUG_ON(!ci->i_head_snapc);
snapc = ceph_get_snap_context(ci->i_head_snapc);
}
spin_unlock(&ci->i_ceph_lock);
/* we might need to revert back to that point */
data = *from;
if (iocb->ki_flags & IOCB_DIRECT)
written = ceph_direct_read_write(iocb, &data, snapc,
&prealloc_cf);
else
written = ceph_sync_write(iocb, &data, pos, snapc);
if (written > 0)
iov_iter_advance(from, written);
ceph_put_snap_context(snapc);
} else {
/*
* 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
*/
written = generic_perform_write(file, from, pos);
if (likely(written >= 0))
iocb->ki_pos = pos + written;
inode_unlock(inode);
}
if (written >= 0) {
int dirty;
spin_lock(&ci->i_ceph_lock);
ci->i_inline_version = CEPH_INLINE_NONE;
dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_FILE_WR,
&prealloc_cf);
spin_unlock(&ci->i_ceph_lock);
if (dirty)
__mark_inode_dirty(inode, dirty);
if (ceph_quota_is_max_bytes_approaching(inode, iocb->ki_pos))
ceph_check_caps(ci, CHECK_CAPS_NODELAY, NULL);
}
dout("aio_write %p %llx.%llx %llu~%u dropping cap refs on %s\n",
inode, ceph_vinop(inode), pos, (unsigned)count,
ceph_cap_string(got));
ceph_put_cap_refs(ci, got);
if (written == -EOLDSNAPC) {
dout("aio_write %p %llx.%llx %llu~%u" "got EOLDSNAPC, retrying\n",
inode, ceph_vinop(inode), pos, (unsigned)count);
goto retry_snap;
}
if (written >= 0) {
if (ceph_osdmap_flag(&fsc->client->osdc, CEPH_OSDMAP_NEARFULL))
iocb->ki_flags |= IOCB_DSYNC;
written = generic_write_sync(iocb, written);
}
goto out_unlocked;
out:
inode_unlock(inode);
out_unlocked:
ceph_free_cap_flush(prealloc_cf);
current->backing_dev_info = NULL;
return written ? written : err;
}
/*
* llseek. be sure to verify file size on SEEK_END.
*/
static loff_t ceph_llseek(struct file *file, loff_t offset, int whence)
{
struct inode *inode = file->f_mapping->host;
struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
loff_t i_size;
loff_t ret;
inode_lock(inode);
if (whence == SEEK_END || whence == SEEK_DATA || whence == SEEK_HOLE) {
ret = ceph_do_getattr(inode, CEPH_STAT_CAP_SIZE, false);
if (ret < 0)
goto out;
}
i_size = i_size_read(inode);
switch (whence) {
case SEEK_END:
offset += 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) {
ret = file->f_pos;
goto out;
}
offset += file->f_pos;
break;
case SEEK_DATA:
if (offset < 0 || offset >= i_size) {
ret = -ENXIO;
goto out;
}
break;
case SEEK_HOLE:
if (offset < 0 || offset >= i_size) {
ret = -ENXIO;
goto out;
}
offset = i_size;
break;
}
ret = vfs_setpos(file, offset, max(i_size, fsc->max_file_size));
out:
inode_unlock(inode);
return ret;
}
static inline void ceph_zero_partial_page(
struct inode *inode, loff_t offset, unsigned size)
{
struct page *page;
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
pgoff_t index = offset >> PAGE_SHIFT;
page = find_lock_page(inode->i_mapping, index);
if (page) {
wait_on_page_writeback(page);
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
zero_user(page, offset & (PAGE_SIZE - 1), size);
unlock_page(page);
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
put_page(page);
}
}
static void ceph_zero_pagecache_range(struct inode *inode, loff_t offset,
loff_t length)
{
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
loff_t nearly = round_up(offset, PAGE_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;
}
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
if (length >= PAGE_SIZE) {
loff_t size = round_down(length, PAGE_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,
0, 1, op,
CEPH_OSD_FLAG_WRITE,
NULL, 0, 0, false);
if (IS_ERR(req)) {
ret = PTR_ERR(req);
goto out;
}
req->r_mtime = 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);
s32 stripe_unit = ci->i_layout.stripe_unit;
s32 stripe_count = ci->i_layout.stripe_count;
s32 object_size = ci->i_layout.object_size;
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);
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;
struct inode *inode = file_inode(file);
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_cap_flush *prealloc_cf;
int want, got = 0;
int dirty;
int ret = 0;
loff_t endoff = 0;
loff_t size;
if (mode != (FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE))
return -EOPNOTSUPP;
if (!S_ISREG(inode->i_mode))
return -EOPNOTSUPP;
prealloc_cf = ceph_alloc_cap_flush();
if (!prealloc_cf)
return -ENOMEM;
inode_lock(inode);
if (ceph_snap(inode) != CEPH_NOSNAP) {
ret = -EROFS;
goto unlock;
}
if (ci->i_inline_version != CEPH_INLINE_NONE) {
ret = ceph_uninline_data(file, NULL);
if (ret < 0)
goto unlock;
}
size = i_size_read(inode);
/* Are we punching a hole beyond EOF? */
if (offset >= size)
goto unlock;
if ((offset + length) > size)
length = size - offset;
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, endoff, &got, NULL);
if (ret < 0)
goto unlock;
ceph_zero_pagecache_range(inode, offset, length);
ret = ceph_zero_objects(inode, offset, length);
if (!ret) {
spin_lock(&ci->i_ceph_lock);
ci->i_inline_version = CEPH_INLINE_NONE;
dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_FILE_WR,
&prealloc_cf);
spin_unlock(&ci->i_ceph_lock);
if (dirty)
__mark_inode_dirty(inode, dirty);
}
ceph_put_cap_refs(ci, got);
unlock:
inode_unlock(inode);
ceph_free_cap_flush(prealloc_cf);
return ret;
}
/*
* This function tries to get FILE_WR capabilities for dst_ci and FILE_RD for
* src_ci. Two attempts are made to obtain both caps, and an error is return if
* this fails; zero is returned on success.
*/
static int get_rd_wr_caps(struct ceph_inode_info *src_ci,
loff_t src_endoff, int *src_got,
struct ceph_inode_info *dst_ci,
loff_t dst_endoff, int *dst_got)
{
int ret = 0;
bool retrying = false;
retry_caps:
ret = ceph_get_caps(dst_ci, CEPH_CAP_FILE_WR, CEPH_CAP_FILE_BUFFER,
dst_endoff, dst_got, NULL);
if (ret < 0)
return ret;
/*
* Since we're already holding the FILE_WR capability for the dst file,
* we would risk a deadlock by using ceph_get_caps. Thus, we'll do some
* retry dance instead to try to get both capabilities.
*/
ret = ceph_try_get_caps(src_ci, CEPH_CAP_FILE_RD, CEPH_CAP_FILE_SHARED,
false, src_got);
if (ret <= 0) {
/* Start by dropping dst_ci caps and getting src_ci caps */
ceph_put_cap_refs(dst_ci, *dst_got);
if (retrying) {
if (!ret)
/* ceph_try_get_caps masks EAGAIN */
ret = -EAGAIN;
return ret;
}
ret = ceph_get_caps(src_ci, CEPH_CAP_FILE_RD,
CEPH_CAP_FILE_SHARED, src_endoff,
src_got, NULL);
if (ret < 0)
return ret;
/*... drop src_ci caps too, and retry */
ceph_put_cap_refs(src_ci, *src_got);
retrying = true;
goto retry_caps;
}
return ret;
}
static void put_rd_wr_caps(struct ceph_inode_info *src_ci, int src_got,
struct ceph_inode_info *dst_ci, int dst_got)
{
ceph_put_cap_refs(src_ci, src_got);
ceph_put_cap_refs(dst_ci, dst_got);
}
/*
* This function does several size-related checks, returning an error if:
* - source file is smaller than off+len
* - destination file size is not OK (inode_newsize_ok())
* - max bytes quotas is exceeded
*/
static int is_file_size_ok(struct inode *src_inode, struct inode *dst_inode,
loff_t src_off, loff_t dst_off, size_t len)
{
loff_t size, endoff;
size = i_size_read(src_inode);
/*
* Don't copy beyond source file EOF. Instead of simply setting length
* to (size - src_off), just drop to VFS default implementation, as the
* local i_size may be stale due to other clients writing to the source
* inode.
*/
if (src_off + len > size) {
dout("Copy beyond EOF (%llu + %zu > %llu)\n",
src_off, len, size);
return -EOPNOTSUPP;
}
size = i_size_read(dst_inode);
endoff = dst_off + len;
if (inode_newsize_ok(dst_inode, endoff))
return -EOPNOTSUPP;
if (ceph_quota_is_max_bytes_exceeded(dst_inode, endoff))
return -EDQUOT;
return 0;
}
static ssize_t ceph_copy_file_range(struct file *src_file, loff_t src_off,
struct file *dst_file, loff_t dst_off,
size_t len, unsigned int flags)
{
struct inode *src_inode = file_inode(src_file);
struct inode *dst_inode = file_inode(dst_file);
struct ceph_inode_info *src_ci = ceph_inode(src_inode);
struct ceph_inode_info *dst_ci = ceph_inode(dst_inode);
struct ceph_cap_flush *prealloc_cf;
struct ceph_object_locator src_oloc, dst_oloc;
struct ceph_object_id src_oid, dst_oid;
loff_t endoff = 0, size;
ssize_t ret = -EIO;
u64 src_objnum, dst_objnum, src_objoff, dst_objoff;
u32 src_objlen, dst_objlen, object_size;
int src_got = 0, dst_got = 0, err, dirty;
bool do_final_copy = false;
if (src_inode == dst_inode)
return -EINVAL;
if (ceph_snap(dst_inode) != CEPH_NOSNAP)
return -EROFS;
/*
* Some of the checks below will return -EOPNOTSUPP, which will force a
* fallback to the default VFS copy_file_range implementation. This is
* desirable in several cases (for ex, the 'len' is smaller than the
* size of the objects, or in cases where that would be more
* efficient).
*/
if (ceph_test_mount_opt(ceph_inode_to_client(src_inode), NOCOPYFROM))
return -EOPNOTSUPP;
if ((src_ci->i_layout.stripe_unit != dst_ci->i_layout.stripe_unit) ||
(src_ci->i_layout.stripe_count != dst_ci->i_layout.stripe_count) ||
(src_ci->i_layout.object_size != dst_ci->i_layout.object_size))
return -EOPNOTSUPP;
if (len < src_ci->i_layout.object_size)
return -EOPNOTSUPP; /* no remote copy will be done */
prealloc_cf = ceph_alloc_cap_flush();
if (!prealloc_cf)
return -ENOMEM;
/* Start by sync'ing the source and destination files */
ret = file_write_and_wait_range(src_file, src_off, (src_off + len));
if (ret < 0) {
dout("failed to write src file (%zd)\n", ret);
goto out;
}
ret = file_write_and_wait_range(dst_file, dst_off, (dst_off + len));
if (ret < 0) {
dout("failed to write dst file (%zd)\n", ret);
goto out;
}
/*
* We need FILE_WR caps for dst_ci and FILE_RD for src_ci as other
* clients may have dirty data in their caches. And OSDs know nothing
* about caps, so they can't safely do the remote object copies.
*/
err = get_rd_wr_caps(src_ci, (src_off + len), &src_got,
dst_ci, (dst_off + len), &dst_got);
if (err < 0) {
dout("get_rd_wr_caps returned %d\n", err);
ret = -EOPNOTSUPP;
goto out;
}
ret = is_file_size_ok(src_inode, dst_inode, src_off, dst_off, len);
if (ret < 0)
goto out_caps;
size = i_size_read(dst_inode);
endoff = dst_off + len;
/* Drop dst file cached pages */
ret = invalidate_inode_pages2_range(dst_inode->i_mapping,
dst_off >> PAGE_SHIFT,
endoff >> PAGE_SHIFT);
if (ret < 0) {
dout("Failed to invalidate inode pages (%zd)\n", ret);
ret = 0; /* XXX */
}
src_oloc.pool = src_ci->i_layout.pool_id;
src_oloc.pool_ns = ceph_try_get_string(src_ci->i_layout.pool_ns);
dst_oloc.pool = dst_ci->i_layout.pool_id;
dst_oloc.pool_ns = ceph_try_get_string(dst_ci->i_layout.pool_ns);
ceph_calc_file_object_mapping(&src_ci->i_layout, src_off,
src_ci->i_layout.object_size,
&src_objnum, &src_objoff, &src_objlen);
ceph_calc_file_object_mapping(&dst_ci->i_layout, dst_off,
dst_ci->i_layout.object_size,
&dst_objnum, &dst_objoff, &dst_objlen);
/* object-level offsets need to the same */
if (src_objoff != dst_objoff) {
ret = -EOPNOTSUPP;
goto out_caps;
}
/*
* Do a manual copy if the object offset isn't object aligned.
* 'src_objlen' contains the bytes left until the end of the object,
* starting at the src_off
*/
if (src_objoff) {
/*
* we need to temporarily drop all caps as we'll be calling
* {read,write}_iter, which will get caps again.
*/
put_rd_wr_caps(src_ci, src_got, dst_ci, dst_got);
ret = do_splice_direct(src_file, &src_off, dst_file,
&dst_off, src_objlen, flags);
if (ret < 0) {
dout("do_splice_direct returned %d\n", err);
goto out;
}
len -= ret;
err = get_rd_wr_caps(src_ci, (src_off + len),
&src_got, dst_ci,
(dst_off + len), &dst_got);
if (err < 0)
goto out;
err = is_file_size_ok(src_inode, dst_inode,
src_off, dst_off, len);
if (err < 0)
goto out_caps;
}
object_size = src_ci->i_layout.object_size;
while (len >= object_size) {
ceph_calc_file_object_mapping(&src_ci->i_layout, src_off,
object_size, &src_objnum,
&src_objoff, &src_objlen);
ceph_calc_file_object_mapping(&dst_ci->i_layout, dst_off,
object_size, &dst_objnum,
&dst_objoff, &dst_objlen);
ceph_oid_init(&src_oid);
ceph_oid_printf(&src_oid, "%llx.%08llx",
src_ci->i_vino.ino, src_objnum);
ceph_oid_init(&dst_oid);
ceph_oid_printf(&dst_oid, "%llx.%08llx",
dst_ci->i_vino.ino, dst_objnum);
/* Do an object remote copy */
err = ceph_osdc_copy_from(
&ceph_inode_to_client(src_inode)->client->osdc,
src_ci->i_vino.snap, 0,
&src_oid, &src_oloc,
CEPH_OSD_OP_FLAG_FADVISE_SEQUENTIAL |
CEPH_OSD_OP_FLAG_FADVISE_NOCACHE,
&dst_oid, &dst_oloc,
CEPH_OSD_OP_FLAG_FADVISE_SEQUENTIAL |
CEPH_OSD_OP_FLAG_FADVISE_DONTNEED, 0);
if (err) {
dout("ceph_osdc_copy_from returned %d\n", err);
if (!ret)
ret = err;
goto out_caps;
}
len -= object_size;
src_off += object_size;
dst_off += object_size;
ret += object_size;
}
if (len)
/* We still need one final local copy */
do_final_copy = true;
file_update_time(dst_file);
if (endoff > size) {
int caps_flags = 0;
/* Let the MDS know about dst file size change */
if (ceph_quota_is_max_bytes_approaching(dst_inode, endoff))
caps_flags |= CHECK_CAPS_NODELAY;
if (ceph_inode_set_size(dst_inode, endoff))
caps_flags |= CHECK_CAPS_AUTHONLY;
if (caps_flags)
ceph_check_caps(dst_ci, caps_flags, NULL);
}
/* Mark Fw dirty */
spin_lock(&dst_ci->i_ceph_lock);
dst_ci->i_inline_version = CEPH_INLINE_NONE;
dirty = __ceph_mark_dirty_caps(dst_ci, CEPH_CAP_FILE_WR, &prealloc_cf);
spin_unlock(&dst_ci->i_ceph_lock);
if (dirty)
__mark_inode_dirty(dst_inode, dirty);
out_caps:
put_rd_wr_caps(src_ci, src_got, dst_ci, dst_got);
if (do_final_copy) {
err = do_splice_direct(src_file, &src_off, dst_file,
&dst_off, len, flags);
if (err < 0) {
dout("do_splice_direct returned %d\n", err);
goto out;
}
len -= err;
ret += err;
}
out:
ceph_free_cap_flush(prealloc_cf);
return ret;
}
const struct file_operations ceph_file_fops = {
.open = ceph_open,
.release = ceph_release,
.llseek = ceph_llseek,
.read_iter = ceph_read_iter,
.write_iter = ceph_write_iter,
.mmap = ceph_mmap,
.fsync = ceph_fsync,
.lock = ceph_lock,
.flock = ceph_flock,
.splice_read = generic_file_splice_read,
.splice_write = iter_file_splice_write,
.unlocked_ioctl = ceph_ioctl,
.compat_ioctl = ceph_ioctl,
.fallocate = ceph_fallocate,
.copy_file_range = ceph_copy_file_range,
};