Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client

Pull ceph updates from Sage Weil:
 "This includes both the first pile of Ceph patches (which I sent to
  torvalds@vger, sigh) and a few new patches that add support for
  fscache for Ceph.  That includes a few fscache core fixes that David
  Howells asked go through the Ceph tree.  (Thanks go to Milosz Tanski
  for putting this feature together)

  This first batch of patches (included here) had (has) several
  important RBD bug fixes, hole punch support, several different
  cleanups in the page cache interactions, improvements in the truncate
  code (new truncate mutex to avoid shenanigans with i_mutex), and a
  series of fixes in the synchronous striping read/write code.

  On top of that is a random collection of small fixes all across the
  tree (error code checks and error path cleanup, obsolete wq flags,
  etc)"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client: (43 commits)
  ceph: use d_invalidate() to invalidate aliases
  ceph: remove ceph_lookup_inode()
  ceph: trivial buildbot warnings fix
  ceph: Do not do invalidate if the filesystem is mounted nofsc
  ceph: page still marked private_2
  ceph: ceph_readpage_to_fscache didn't check if marked
  ceph: clean PgPrivate2 on returning from readpages
  ceph: use fscache as a local presisent cache
  fscache: Netfs function for cleanup post readpages
  FS-Cache: Fix heading in documentation
  CacheFiles: Implement interface to check cache consistency
  FS-Cache: Add interface to check consistency of a cached object
  rbd: fix null dereference in dout
  rbd: fix buffer size for writes to images with snapshots
  libceph: use pg_num_mask instead of pgp_num_mask for pg.seed calc
  rbd: fix I/O error propagation for reads
  ceph: use vfs __set_page_dirty_nobuffers interface instead of doing it inside filesystem
  ceph: allow sync_read/write return partial successed size of read/write.
  ceph: fix bugs about handling short-read for sync read mode.
  ceph: remove useless variable revoked_rdcache
  ...

1 files changed, 33 insertions, 13 deletions

diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index f3a2abf28a77..8549a48115f7 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;
 }
 
@@ -1066,7 +1079,7 @@ 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 */
@@ -1419,18 +1432,20 @@ 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 +1460,7 @@ 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 +1481,7 @@ 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 +1494,7 @@ 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 +1515,13 @@ 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 +1538,9 @@ 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 +1558,14 @@ 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 +1607,6 @@ 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 +1787,8 @@ 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);