summaryrefslogtreecommitdiff
path: root/fs/ceph/inode.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/ceph/inode.c')
-rw-r--r--fs/ceph/inode.c95
1 files changed, 76 insertions, 19 deletions
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index f3a2abf28a77..9a8e396aed89 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -12,6 +12,7 @@
#include "super.h"
#include "mds_client.h"
+#include "cache.h"
#include <linux/ceph/decode.h>
/*
@@ -344,6 +345,7 @@ struct inode *ceph_alloc_inode(struct super_block *sb)
for (i = 0; i < CEPH_FILE_MODE_NUM; i++)
ci->i_nr_by_mode[i] = 0;
+ mutex_init(&ci->i_truncate_mutex);
ci->i_truncate_seq = 0;
ci->i_truncate_size = 0;
ci->i_truncate_pending = 0;
@@ -377,6 +379,8 @@ struct inode *ceph_alloc_inode(struct super_block *sb)
INIT_WORK(&ci->i_vmtruncate_work, ceph_vmtruncate_work);
+ ceph_fscache_inode_init(ci);
+
return &ci->vfs_inode;
}
@@ -396,6 +400,8 @@ void ceph_destroy_inode(struct inode *inode)
dout("destroy_inode %p ino %llx.%llx\n", inode, ceph_vinop(inode));
+ ceph_fscache_unregister_inode_cookie(ci);
+
ceph_queue_caps_release(inode);
/*
@@ -430,7 +436,6 @@ void ceph_destroy_inode(struct inode *inode)
call_rcu(&inode->i_rcu, ceph_i_callback);
}
-
/*
* Helpers to fill in size, ctime, mtime, and atime. We have to be
* careful because either the client or MDS may have more up to date
@@ -455,16 +460,20 @@ int ceph_fill_file_size(struct inode *inode, int issued,
dout("truncate_seq %u -> %u\n",
ci->i_truncate_seq, truncate_seq);
ci->i_truncate_seq = truncate_seq;
+
+ /* the MDS should have revoked these caps */
+ WARN_ON_ONCE(issued & (CEPH_CAP_FILE_EXCL |
+ CEPH_CAP_FILE_RD |
+ CEPH_CAP_FILE_WR |
+ CEPH_CAP_FILE_LAZYIO));
/*
* If we hold relevant caps, or in the case where we're
* not the only client referencing this file and we
* don't hold those caps, then we need to check whether
* the file is either opened or mmaped
*/
- if ((issued & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_RD|
- CEPH_CAP_FILE_WR|CEPH_CAP_FILE_BUFFER|
- CEPH_CAP_FILE_EXCL|
- CEPH_CAP_FILE_LAZYIO)) ||
+ if ((issued & (CEPH_CAP_FILE_CACHE|
+ CEPH_CAP_FILE_BUFFER)) ||
mapping_mapped(inode->i_mapping) ||
__ceph_caps_file_wanted(ci)) {
ci->i_truncate_pending++;
@@ -478,6 +487,10 @@ int ceph_fill_file_size(struct inode *inode, int issued,
truncate_size);
ci->i_truncate_size = truncate_size;
}
+
+ if (queue_trunc)
+ ceph_fscache_invalidate(inode);
+
return queue_trunc;
}
@@ -564,6 +577,8 @@ static int fill_inode(struct inode *inode,
int issued = 0, implemented;
struct timespec mtime, atime, ctime;
u32 nsplits;
+ struct ceph_inode_frag *frag;
+ struct rb_node *rb_node;
struct ceph_buffer *xattr_blob = NULL;
int err = 0;
int queue_trunc = 0;
@@ -738,15 +753,38 @@ no_change:
/* FIXME: move me up, if/when version reflects fragtree changes */
nsplits = le32_to_cpu(info->fragtree.nsplits);
mutex_lock(&ci->i_fragtree_mutex);
+ rb_node = rb_first(&ci->i_fragtree);
for (i = 0; i < nsplits; i++) {
u32 id = le32_to_cpu(info->fragtree.splits[i].frag);
- struct ceph_inode_frag *frag = __get_or_create_frag(ci, id);
-
- if (IS_ERR(frag))
- continue;
+ frag = NULL;
+ while (rb_node) {
+ frag = rb_entry(rb_node, struct ceph_inode_frag, node);
+ if (ceph_frag_compare(frag->frag, id) >= 0) {
+ if (frag->frag != id)
+ frag = NULL;
+ else
+ rb_node = rb_next(rb_node);
+ break;
+ }
+ rb_node = rb_next(rb_node);
+ rb_erase(&frag->node, &ci->i_fragtree);
+ kfree(frag);
+ frag = NULL;
+ }
+ if (!frag) {
+ frag = __get_or_create_frag(ci, id);
+ if (IS_ERR(frag))
+ continue;
+ }
frag->split_by = le32_to_cpu(info->fragtree.splits[i].by);
dout(" frag %x split by %d\n", frag->frag, frag->split_by);
}
+ while (rb_node) {
+ frag = rb_entry(rb_node, struct ceph_inode_frag, node);
+ rb_node = rb_next(rb_node);
+ rb_erase(&frag->node, &ci->i_fragtree);
+ kfree(frag);
+ }
mutex_unlock(&ci->i_fragtree_mutex);
/* were we issued a capability? */
@@ -1066,7 +1104,7 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
* complete.
*/
ceph_set_dentry_offset(req->r_old_dentry);
- dout("dn %p gets new offset %lld\n", req->r_old_dentry,
+ dout("dn %p gets new offset %lld\n", req->r_old_dentry,
ceph_dentry(req->r_old_dentry)->offset);
dn = req->r_old_dentry; /* use old_dentry */
@@ -1237,8 +1275,20 @@ int ceph_readdir_prepopulate(struct ceph_mds_request *req,
int err = 0, i;
struct inode *snapdir = NULL;
struct ceph_mds_request_head *rhead = req->r_request->front.iov_base;
- u64 frag = le32_to_cpu(rhead->args.readdir.frag);
struct ceph_dentry_info *di;
+ u64 r_readdir_offset = req->r_readdir_offset;
+ u32 frag = le32_to_cpu(rhead->args.readdir.frag);
+
+ if (rinfo->dir_dir &&
+ le32_to_cpu(rinfo->dir_dir->frag) != frag) {
+ dout("readdir_prepopulate got new frag %x -> %x\n",
+ frag, le32_to_cpu(rinfo->dir_dir->frag));
+ frag = le32_to_cpu(rinfo->dir_dir->frag);
+ if (ceph_frag_is_leftmost(frag))
+ r_readdir_offset = 2;
+ else
+ r_readdir_offset = 0;
+ }
if (req->r_aborted)
return readdir_prepopulate_inodes_only(req, session);
@@ -1302,7 +1352,7 @@ retry_lookup:
}
di = dn->d_fsdata;
- di->offset = ceph_make_fpos(frag, i + req->r_readdir_offset);
+ di->offset = ceph_make_fpos(frag, i + r_readdir_offset);
/* inode */
if (dn->d_inode) {
@@ -1419,18 +1469,20 @@ static void ceph_invalidate_work(struct work_struct *work)
u32 orig_gen;
int check = 0;
+ mutex_lock(&ci->i_truncate_mutex);
spin_lock(&ci->i_ceph_lock);
dout("invalidate_pages %p gen %d revoking %d\n", inode,
ci->i_rdcache_gen, ci->i_rdcache_revoking);
if (ci->i_rdcache_revoking != ci->i_rdcache_gen) {
/* nevermind! */
spin_unlock(&ci->i_ceph_lock);
+ mutex_unlock(&ci->i_truncate_mutex);
goto out;
}
orig_gen = ci->i_rdcache_gen;
spin_unlock(&ci->i_ceph_lock);
- truncate_inode_pages(&inode->i_data, 0);
+ truncate_inode_pages(inode->i_mapping, 0);
spin_lock(&ci->i_ceph_lock);
if (orig_gen == ci->i_rdcache_gen &&
@@ -1445,6 +1497,7 @@ static void ceph_invalidate_work(struct work_struct *work)
ci->i_rdcache_revoking);
}
spin_unlock(&ci->i_ceph_lock);
+ mutex_unlock(&ci->i_truncate_mutex);
if (check)
ceph_check_caps(ci, 0, NULL);
@@ -1465,9 +1518,7 @@ static void ceph_vmtruncate_work(struct work_struct *work)
struct inode *inode = &ci->vfs_inode;
dout("vmtruncate_work %p\n", inode);
- mutex_lock(&inode->i_mutex);
__ceph_do_pending_vmtruncate(inode);
- mutex_unlock(&inode->i_mutex);
iput(inode);
}
@@ -1480,6 +1531,7 @@ void ceph_queue_vmtruncate(struct inode *inode)
struct ceph_inode_info *ci = ceph_inode(inode);
ihold(inode);
+
if (queue_work(ceph_sb_to_client(inode->i_sb)->trunc_wq,
&ci->i_vmtruncate_work)) {
dout("ceph_queue_vmtruncate %p\n", inode);
@@ -1500,11 +1552,13 @@ void __ceph_do_pending_vmtruncate(struct inode *inode)
u64 to;
int wrbuffer_refs, finish = 0;
+ mutex_lock(&ci->i_truncate_mutex);
retry:
spin_lock(&ci->i_ceph_lock);
if (ci->i_truncate_pending == 0) {
dout("__do_pending_vmtruncate %p none pending\n", inode);
spin_unlock(&ci->i_ceph_lock);
+ mutex_unlock(&ci->i_truncate_mutex);
return;
}
@@ -1521,6 +1575,9 @@ retry:
goto retry;
}
+ /* there should be no reader or writer */
+ WARN_ON_ONCE(ci->i_rd_ref || ci->i_wr_ref);
+
to = ci->i_truncate_size;
wrbuffer_refs = ci->i_wrbuffer_ref;
dout("__do_pending_vmtruncate %p (%d) to %lld\n", inode,
@@ -1538,13 +1595,14 @@ retry:
if (!finish)
goto retry;
+ mutex_unlock(&ci->i_truncate_mutex);
+
if (wrbuffer_refs == 0)
ceph_check_caps(ci, CHECK_CAPS_AUTHONLY, NULL);
wake_up_all(&ci->i_cap_wq);
}
-
/*
* symlinks
*/
@@ -1586,8 +1644,6 @@ int ceph_setattr(struct dentry *dentry, struct iattr *attr)
if (ceph_snap(inode) != CEPH_NOSNAP)
return -EROFS;
- __ceph_do_pending_vmtruncate(inode);
-
err = inode_change_ok(inode, attr);
if (err != 0)
return err;
@@ -1768,7 +1824,8 @@ int ceph_setattr(struct dentry *dentry, struct iattr *attr)
ceph_cap_string(dirtied), mask);
ceph_mdsc_put_request(req);
- __ceph_do_pending_vmtruncate(inode);
+ if (mask & CEPH_SETATTR_SIZE)
+ __ceph_do_pending_vmtruncate(inode);
return err;
out:
spin_unlock(&ci->i_ceph_lock);
generated by cgit v1.2.3 (git 2.25.1) at 2025-10-23 15:03:33 +0000