kfree(req->r_pages);
}
+ static void ceph_unlock_page_vector(struct page **pages, int num_pages)
+ {
+ int i;
+
+ for (i = 0; i < num_pages; i++)
+ unlock_page(pages[i]);
+ }
+
/*
* start an async read(ahead) operation. return nr_pages we submitted
* a read for on success, or negative error code.
return nr_pages;
out_pages:
+ ceph_unlock_page_vector(pages, nr_pages);
ceph_release_page_vector(pages, nr_pages);
out:
ceph_osdc_put_request(req);
struct page **pagep, void **fsdata)
{
struct inode *inode = file->f_dentry->d_inode;
+ struct ceph_inode_info *ci = ceph_inode(inode);
+ struct ceph_file_info *fi = file->private_data;
struct page *page;
pgoff_t index = pos >> PAGE_CACHE_SHIFT;
- int r;
+ int r, want, got = 0;
+
+ if (fi->fmode & CEPH_FILE_MODE_LAZY)
+ want = CEPH_CAP_FILE_BUFFER | CEPH_CAP_FILE_LAZYIO;
+ else
+ want = CEPH_CAP_FILE_BUFFER;
+
+ dout("write_begin %p %llx.%llx %llu~%u getting caps. i_size %llu\n",
+ inode, ceph_vinop(inode), pos, len, inode->i_size);
+ r = ceph_get_caps(ci, CEPH_CAP_FILE_WR, want, &got, pos+len);
+ if (r < 0)
+ return r;
+ dout("write_begin %p %llx.%llx %llu~%u got cap refs on %s\n",
+ inode, ceph_vinop(inode), pos, len, ceph_cap_string(got));
+ if (!(got & (CEPH_CAP_FILE_BUFFER|CEPH_CAP_FILE_LAZYIO))) {
+ ceph_put_cap_refs(ci, got);
+ return -EAGAIN;
+ }
do {
/* get a page */
page = grab_cache_page_write_begin(mapping, index, 0);
- if (!page)
- return -ENOMEM;
- *pagep = page;
+ if (!page) {
+ r = -ENOMEM;
+ break;
+ }
dout("write_begin file %p inode %p page %p %d~%d\n", file,
inode, page, (int)pos, (int)len);
r = ceph_update_writeable_page(file, pos, len, page);
+ if (r)
+ page_cache_release(page);
} while (r == -EAGAIN);
+ if (r) {
+ ceph_put_cap_refs(ci, got);
+ } else {
+ *pagep = page;
+ *(int *)fsdata = got;
+ }
return r;
}
struct page *page, void *fsdata)
{
struct inode *inode = file->f_dentry->d_inode;
+ struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
struct ceph_mds_client *mdsc = fsc->mdsc;
unsigned from = pos & (PAGE_CACHE_SIZE - 1);
int check_cap = 0;
+ int got = (unsigned long)fsdata;
dout("write_end file %p inode %p page %p %d~%d (%d)\n", file,
inode, page, (int)pos, (int)copied, (int)len);
up_read(&mdsc->snap_rwsem);
page_cache_release(page);
+ if (copied > 0) {
+ int dirty;
+ 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);
+ }
+
+ dout("write_end %p %llx.%llx %llu~%u dropping cap refs on %s\n",
+ inode, ceph_vinop(inode), pos, len, ceph_cap_string(got));
+ ceph_put_cap_refs(ci, got);
+
if (check_cap)
ceph_check_caps(ceph_inode(inode), CHECK_CAPS_AUTHONLY, NULL);
static struct vm_operations_struct ceph_vmops = {
.fault = filemap_fault,
.page_mkwrite = ceph_page_mkwrite,
+ .remap_pages = generic_file_remap_pages,
};
int ceph_mmap(struct file *file, struct vm_area_struct *vma)
return -ENOEXEC;
file_accessed(file);
vma->vm_ops = &ceph_vmops;
- vma->vm_flags |= VM_CAN_NONLINEAR;
return 0;
}
struct ceph_osd_client *osdc =
&ceph_sb_to_client(inode->i_sb)->client->osdc;
loff_t endoff = pos + iov->iov_len;
- int want, got = 0;
- int ret, err;
+ int got = 0;
+ int ret, err, written;
if (ceph_snap(inode) != CEPH_NOSNAP)
return -EROFS;
retry_snap:
+ written = 0;
if (ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL))
return -ENOSPC;
__ceph_do_pending_vmtruncate(inode);
- dout("aio_write %p %llx.%llx %llu~%u getting caps. i_size %llu\n",
- inode, ceph_vinop(inode), pos, (unsigned)iov->iov_len,
- inode->i_size);
- 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 out_put;
-
- dout("aio_write %p %llx.%llx %llu~%u got cap refs on %s\n",
- inode, ceph_vinop(inode), pos, (unsigned)iov->iov_len,
- ceph_cap_string(got));
-
- if ((got & (CEPH_CAP_FILE_BUFFER|CEPH_CAP_FILE_LAZYIO)) == 0 ||
- (iocb->ki_filp->f_flags & O_DIRECT) ||
- (inode->i_sb->s_flags & MS_SYNCHRONOUS) ||
- (fi->flags & CEPH_F_SYNC)) {
- ret = ceph_sync_write(file, iov->iov_base, iov->iov_len,
- &iocb->ki_pos);
- } else {
- /*
- * buffered write; drop Fw early to avoid slow
- * revocation if we get stuck on balance_dirty_pages
- */
- int dirty;
-
- spin_lock(&ci->i_ceph_lock);
- dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_FILE_WR);
- spin_unlock(&ci->i_ceph_lock);
- ceph_put_cap_refs(ci, got);
+ /*
+ * try to do a buffered write. if we don't have sufficient
+ * caps, we'll get -EAGAIN from generic_file_aio_write, or a
+ * short write if we only get caps for some pages.
+ */
+ if (!(iocb->ki_filp->f_flags & O_DIRECT) &&
+ !(inode->i_sb->s_flags & MS_SYNCHRONOUS) &&
+ !(fi->flags & CEPH_F_SYNC)) {
ret = generic_file_aio_write(iocb, iov, nr_segs, pos);
+ if (ret >= 0)
+ written = ret;
+
if ((ret >= 0 || ret == -EIOCBQUEUED) &&
((file->f_flags & O_SYNC) || IS_SYNC(file->f_mapping->host)
|| ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_NEARFULL))) {
- err = vfs_fsync_range(file, pos, pos + ret - 1, 1);
+ err = vfs_fsync_range(file, pos, pos + written - 1, 1);
if (err < 0)
ret = err;
}
+ if ((ret < 0 && ret != -EAGAIN) || pos + written >= endoff)
+ goto out;
+ }
- if (dirty)
- __mark_inode_dirty(inode, dirty);
+ dout("aio_write %p %llx.%llx %llu~%u getting caps. i_size %llu\n",
+ inode, ceph_vinop(inode), pos + written,
+ (unsigned)iov->iov_len - written, inode->i_size);
+ ret = ceph_get_caps(ci, CEPH_CAP_FILE_WR, 0, &got, endoff);
+ if (ret < 0)
goto out;
- }
+ dout("aio_write %p %llx.%llx %llu~%u got cap refs on %s\n",
+ inode, ceph_vinop(inode), pos + written,
+ (unsigned)iov->iov_len - written, ceph_cap_string(got));
+ ret = ceph_sync_write(file, iov->iov_base + written,
+ iov->iov_len - written, &iocb->ki_pos);
if (ret >= 0) {
int dirty;
spin_lock(&ci->i_ceph_lock);
if (dirty)
__mark_inode_dirty(inode, dirty);
}
-
- out_put:
dout("aio_write %p %llx.%llx %llu~%u dropping cap refs on %s\n",
- inode, ceph_vinop(inode), pos, (unsigned)iov->iov_len,
- ceph_cap_string(got));
+ inode, ceph_vinop(inode), pos + written,
+ (unsigned)iov->iov_len - written, ceph_cap_string(got));
ceph_put_cap_refs(ci, got);
-
out:
if (ret == -EOLDSNAPC) {
dout("aio_write %p %llx.%llx %llu~%u got EOLDSNAPC, retrying\n",
/*
* llseek. be sure to verify file size on SEEK_END.
*/
-static loff_t ceph_llseek(struct file *file, loff_t offset, int origin)
+static loff_t ceph_llseek(struct file *file, loff_t offset, int whence)
{
struct inode *inode = file->f_mapping->host;
int ret;
mutex_lock(&inode->i_mutex);
__ceph_do_pending_vmtruncate(inode);
- if (origin == SEEK_END || origin == SEEK_DATA || origin == SEEK_HOLE) {
+ if (whence == SEEK_END || whence == SEEK_DATA || whence == SEEK_HOLE) {
ret = ceph_do_getattr(inode, CEPH_STAT_CAP_SIZE);
if (ret < 0) {
offset = ret;
}
}
- switch (origin) {
+ switch (whence) {
case SEEK_END:
offset += inode->i_size;
break;
pr_err("fill_trace bad get_inode "
"%llx.%llx\n", vino.ino, vino.snap);
err = PTR_ERR(in);
- d_delete(dn);
+ d_drop(dn);
goto done;
}
dn = splice_dentry(dn, in, &have_lease, true);
in = ceph_get_inode(parent->d_sb, vino);
if (IS_ERR(in)) {
dout("new_inode badness\n");
- d_delete(dn);
+ d_drop(dn);
dput(dn);
err = PTR_ERR(in);
goto out;
{
struct ceph_inode_info *ci = ceph_inode(inode);
u64 to;
- int wrbuffer_refs, wake = 0;
+ int wrbuffer_refs, finish = 0;
retry:
spin_lock(&ci->i_ceph_lock);
truncate_inode_pages(inode->i_mapping, to);
spin_lock(&ci->i_ceph_lock);
- ci->i_truncate_pending--;
- if (ci->i_truncate_pending == 0)
- wake = 1;
+ if (to == ci->i_truncate_size) {
+ ci->i_truncate_pending = 0;
+ finish = 1;
+ }
spin_unlock(&ci->i_ceph_lock);
+ if (!finish)
+ goto retry;
if (wrbuffer_refs == 0)
ceph_check_caps(ci, CHECK_CAPS_AUTHONLY, NULL);
- if (wake)
- wake_up_all(&ci->i_cap_wq);
+
+ wake_up_all(&ci->i_cap_wq);
}
seq_printf(m, ",mount_timeout=%d", opt->mount_timeout);
if (opt->osd_idle_ttl != CEPH_OSD_IDLE_TTL_DEFAULT)
seq_printf(m, ",osd_idle_ttl=%d", opt->osd_idle_ttl);
- if (opt->osd_timeout != CEPH_OSD_TIMEOUT_DEFAULT)
- seq_printf(m, ",osdtimeout=%d", opt->osd_timeout);
if (opt->osd_keepalive_timeout != CEPH_OSD_KEEPALIVE_DEFAULT)
seq_printf(m, ",osdkeepalivetimeout=%d",
opt->osd_keepalive_timeout);
static void destroy_caches(void)
{
+ /*
+ * Make sure all delayed rcu free inodes are flushed before we
+ * destroy cache.
+ */
+ rcu_barrier();
kmem_cache_destroy(ceph_inode_cachep);
kmem_cache_destroy(ceph_cap_cachep);
kmem_cache_destroy(ceph_dentry_cachep);
fsc->backing_dev_info.ra_pages =
default_backing_dev_info.ra_pages;
- err = bdi_register(&fsc->backing_dev_info, NULL, "ceph-%d",
+ err = bdi_register(&fsc->backing_dev_info, NULL, "ceph-%ld",
atomic_long_inc_return(&bdi_seq));
if (!err)
sb->s_bdi = &fsc->backing_dev_info;
#ifndef _FS_CEPH_LIBCEPH_H
#define _FS_CEPH_LIBCEPH_H
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
#include <asm/unaligned.h>
#include <linux/backing-dev.h>
#include <linux/writeback.h>
#include <linux/slab.h>
-#include "types.h"
-#include "messenger.h"
-#include "msgpool.h"
-#include "mon_client.h"
-#include "osd_client.h"
-#include "ceph_fs.h"
+#include <linux/ceph/types.h>
+#include <linux/ceph/messenger.h>
+#include <linux/ceph/msgpool.h>
+#include <linux/ceph/mon_client.h>
+#include <linux/ceph/osd_client.h>
+#include <linux/ceph/ceph_fs.h>
/*
* mount options
struct ceph_entity_addr my_addr;
int mount_timeout;
int osd_idle_ttl;
- int osd_timeout;
int osd_keepalive_timeout;
/*
* defaults
*/
#define CEPH_MOUNT_TIMEOUT_DEFAULT 60
- #define CEPH_OSD_TIMEOUT_DEFAULT 60 /* seconds */
#define CEPH_OSD_KEEPALIVE_DEFAULT 5
#define CEPH_OSD_IDLE_TTL_DEFAULT 60
#define _FS_CEPH_OSDMAP_H
#include <linux/rbtree.h>
-#include "types.h"
-#include "ceph_fs.h"
+#include <linux/ceph/types.h>
+#include <linux/ceph/ceph_fs.h>
#include <linux/crush/crush.h>
/*
extern int ceph_calc_pg_primary(struct ceph_osdmap *osdmap,
struct ceph_pg pgid);
+ extern const char *ceph_pg_pool_name_by_id(struct ceph_osdmap *map, u64 id);
extern int ceph_pg_poolid_by_name(struct ceph_osdmap *map, const char *name);
#endif
* (Reliable Autonomic Distributed Object Store).
*/
-#include "msgr.h"
+#include <linux/ceph/msgr.h>
/*
* osdmap encoding versions
*
* lpgp_num -- as above.
*/
+ #define CEPH_NOPOOL ((__u64) (-1)) /* pool id not defined */
+
#define CEPH_PG_TYPE_REP 1
#define CEPH_PG_TYPE_RAID4 2
#define CEPH_PG_POOL_VERSION 2