Merge tag 'ceph-for-5.3-rc1' of git://github.com/ceph/ceph-client

Pull ceph updates from Ilya Dryomov:
 "Lots of exciting things this time!

   - support for rbd object-map and fast-diff features (myself). This
     will speed up reads, discards and things like snap diffs on sparse
     images.

   - ceph.snap.btime vxattr to expose snapshot creation time (David
     Disseldorp). This will be used to integrate with "Restore Previous
     Versions" feature added in Windows 7 for folks who reexport ceph
     through SMB.

   - security xattrs for ceph (Zheng Yan). Only selinux is supported for
     now due to the limitations of ->dentry_init_security().

   - support for MSG_ADDR2, FS_BTIME and FS_CHANGE_ATTR features (Jeff
     Layton). This is actually a single feature bit which was missing
     because of the filesystem pieces. With this in, the kernel client
     will finally be reported as "luminous" by "ceph features" -- it is
     still being reported as "jewel" even though all required Luminous
     features were implemented in 4.13.

   - stop NULL-terminating ceph vxattrs (Jeff Layton). The convention
     with xattrs is to not terminate and this was causing
     inconsistencies with ceph-fuse.

   - change filesystem time granularity from 1 us to 1 ns, again fixing
     an inconsistency with ceph-fuse (Luis Henriques).

  On top of this there are some additional dentry name handling and cap
  flushing fixes from Zheng. Finally, Jeff is formally taking over for
  Zheng as the filesystem maintainer"

* tag 'ceph-for-5.3-rc1' of git://github.com/ceph/ceph-client: (71 commits)
  ceph: fix end offset in truncate_inode_pages_range call
  ceph: use generic_delete_inode() for ->drop_inode
  ceph: use ceph_evict_inode to cleanup inode's resource
  ceph: initialize superblock s_time_gran to 1
  MAINTAINERS: take over for Zheng as CephFS kernel client maintainer
  rbd: setallochint only if object doesn't exist
  rbd: support for object-map and fast-diff
  rbd: call rbd_dev_mapping_set() from rbd_dev_image_probe()
  libceph: export osd_req_op_data() macro
  libceph: change ceph_osdc_call() to take page vector for response
  libceph: bump CEPH_MSG_MAX_DATA_LEN (again)
  rbd: new exclusive lock wait/wake code
  rbd: quiescing lock should wait for image requests
  rbd: lock should be quiesced on reacquire
  rbd: introduce copyup state machine
  rbd: rename rbd_obj_setup_*() to rbd_obj_init_*()
  rbd: move OSD request allocation into object request state machines
  rbd: factor out __rbd_osd_setup_discard_ops()
  rbd: factor out rbd_osd_setup_copyup()
  rbd: introduce obj_req->osd_reqs list
  ...

1 files changed, 77 insertions, 43 deletions

diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 0176241eaea7..d98dcd976c80 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -8,6 +8,7 @@
 #include <linux/vmalloc.h>
 #include <linux/wait.h>
 #include <linux/writeback.h>
+#include <linux/iversion.h>
 
 #include "super.h"
 #include "mds_client.h"
@@ -1138,8 +1139,9 @@ struct cap_msg_args {
 	u64			ino, cid, follows;
 	u64			flush_tid, oldest_flush_tid, size, max_size;
 	u64			xattr_version;
+	u64			change_attr;
 	struct ceph_buffer	*xattr_buf;
-	struct timespec64	atime, mtime, ctime;
+	struct timespec64	atime, mtime, ctime, btime;
 	int			op, caps, wanted, dirty;
 	u32			seq, issue_seq, mseq, time_warp_seq;
 	u32			flags;
@@ -1160,7 +1162,6 @@ static int send_cap_msg(struct cap_msg_args *arg)
 	struct ceph_msg *msg;
 	void *p;
 	size_t extra_len;
-	struct timespec64 zerotime = {0};
 	struct ceph_osd_client *osdc = &arg->session->s_mdsc->fsc->client->osdc;
 
 	dout("send_cap_msg %s %llx %llx caps %s wanted %s dirty %s"
@@ -1245,15 +1246,10 @@ static int send_cap_msg(struct cap_msg_args *arg)
 	/* pool namespace (version 8) (mds always ignores this) */
 	ceph_encode_32(&p, 0);
 
-	/*
-	 * btime and change_attr (version 9)
-	 *
-	 * We just zero these out for now, as the MDS ignores them unless
-	 * the requisite feature flags are set (which we don't do yet).
-	 */
-	ceph_encode_timespec64(p, &zerotime);
+	/* btime and change_attr (version 9) */
+	ceph_encode_timespec64(p, &arg->btime);
 	p += sizeof(struct ceph_timespec);
-	ceph_encode_64(&p, 0);
+	ceph_encode_64(&p, arg->change_attr);
 
 	/* Advisory flags (version 10) */
 	ceph_encode_32(&p, arg->flags);
@@ -1263,20 +1259,22 @@ static int send_cap_msg(struct cap_msg_args *arg)
 }
 
 /*
- * Queue cap releases when an inode is dropped from our cache.  Since
- * inode is about to be destroyed, there is no need for i_ceph_lock.
+ * Queue cap releases when an inode is dropped from our cache.
  */
-void __ceph_remove_caps(struct inode *inode)
+void __ceph_remove_caps(struct ceph_inode_info *ci)
 {
-	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct rb_node *p;
 
+	/* lock i_ceph_lock, because ceph_d_revalidate(..., LOOKUP_RCU)
+	 * may call __ceph_caps_issued_mask() on a freeing inode. */
+	spin_lock(&ci->i_ceph_lock);
 	p = rb_first(&ci->i_caps);
 	while (p) {
 		struct ceph_cap *cap = rb_entry(p, struct ceph_cap, ci_node);
 		p = rb_next(p);
 		__ceph_remove_cap(cap, true);
 	}
+	spin_unlock(&ci->i_ceph_lock);
 }
 
 /*
@@ -1297,7 +1295,7 @@ void __ceph_remove_caps(struct inode *inode)
  * caller should hold snap_rwsem (read), s_mutex.
  */
 static int __send_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap,
-		      int op, bool sync, int used, int want, int retain,
+		      int op, int flags, int used, int want, int retain,
 		      int flushing, u64 flush_tid, u64 oldest_flush_tid)
 	__releases(cap->ci->i_ceph_lock)
 {
@@ -1377,6 +1375,8 @@ static int __send_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap,
 	arg.mtime = inode->i_mtime;
 	arg.atime = inode->i_atime;
 	arg.ctime = inode->i_ctime;
+	arg.btime = ci->i_btime;
+	arg.change_attr = inode_peek_iversion_raw(inode);
 
 	arg.op = op;
 	arg.caps = cap->implemented;
@@ -1393,12 +1393,19 @@ static int __send_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap,
 	arg.mode = inode->i_mode;
 
 	arg.inline_data = ci->i_inline_version != CEPH_INLINE_NONE;
-	if (list_empty(&ci->i_cap_snaps))
-		arg.flags = CEPH_CLIENT_CAPS_NO_CAPSNAP;
-	else
-		arg.flags = CEPH_CLIENT_CAPS_PENDING_CAPSNAP;
-	if (sync)
-		arg.flags |= CEPH_CLIENT_CAPS_SYNC;
+	if (!(flags & CEPH_CLIENT_CAPS_PENDING_CAPSNAP) &&
+	    !list_empty(&ci->i_cap_snaps)) {
+		struct ceph_cap_snap *capsnap;
+		list_for_each_entry_reverse(capsnap, &ci->i_cap_snaps, ci_item) {
+			if (capsnap->cap_flush.tid)
+				break;
+			if (capsnap->need_flush) {
+				flags |= CEPH_CLIENT_CAPS_PENDING_CAPSNAP;
+				break;
+			}
+		}
+	}
+	arg.flags = flags;
 
 	spin_unlock(&ci->i_ceph_lock);
 
@@ -1436,6 +1443,8 @@ static inline int __send_flush_snap(struct inode *inode,
 	arg.atime = capsnap->atime;
 	arg.mtime = capsnap->mtime;
 	arg.ctime = capsnap->ctime;
+	arg.btime = capsnap->btime;
+	arg.change_attr = capsnap->change_attr;
 
 	arg.op = CEPH_CAP_OP_FLUSHSNAP;
 	arg.caps = capsnap->issued;
@@ -1603,10 +1612,8 @@ retry:
 	}
 
 	// make sure flushsnap messages are sent in proper order.
-	if (ci->i_ceph_flags & CEPH_I_KICK_FLUSH) {
+	if (ci->i_ceph_flags & CEPH_I_KICK_FLUSH)
 		__kick_flushing_caps(mdsc, session, ci, 0);
-		ci->i_ceph_flags &= ~CEPH_I_KICK_FLUSH;
-	}
 
 	__ceph_flush_snaps(ci, session);
 out:
@@ -2048,10 +2055,8 @@ ack:
 		if (cap == ci->i_auth_cap &&
 		    (ci->i_ceph_flags &
 		     (CEPH_I_KICK_FLUSH | CEPH_I_FLUSH_SNAPS))) {
-			if (ci->i_ceph_flags & CEPH_I_KICK_FLUSH) {
+			if (ci->i_ceph_flags & CEPH_I_KICK_FLUSH)
 				__kick_flushing_caps(mdsc, session, ci, 0);
-				ci->i_ceph_flags &= ~CEPH_I_KICK_FLUSH;
-			}
 			if (ci->i_ceph_flags & CEPH_I_FLUSH_SNAPS)
 				__ceph_flush_snaps(ci, session);
 
@@ -2087,7 +2092,7 @@ ack:
 		sent++;
 
 		/* __send_cap drops i_ceph_lock */
-		delayed += __send_cap(mdsc, cap, CEPH_CAP_OP_UPDATE, false,
+		delayed += __send_cap(mdsc, cap, CEPH_CAP_OP_UPDATE, 0,
 				cap_used, want, retain, flushing,
 				flush_tid, oldest_flush_tid);
 		goto retry; /* retake i_ceph_lock and restart our cap scan. */
@@ -2121,6 +2126,7 @@ static int try_flush_caps(struct inode *inode, u64 *ptid)
 
 retry:
 	spin_lock(&ci->i_ceph_lock);
+retry_locked:
 	if (ci->i_ceph_flags & CEPH_I_NOFLUSH) {
 		spin_unlock(&ci->i_ceph_lock);
 		dout("try_flush_caps skipping %p I_NOFLUSH set\n", inode);
@@ -2128,8 +2134,6 @@ retry:
 	}
 	if (ci->i_dirty_caps && ci->i_auth_cap) {
 		struct ceph_cap *cap = ci->i_auth_cap;
-		int used = __ceph_caps_used(ci);
-		int want = __ceph_caps_wanted(ci);
 		int delayed;
 
 		if (!session || session != cap->session) {
@@ -2145,13 +2149,25 @@ retry:
 			goto out;
 		}
 
+		if (ci->i_ceph_flags &
+		    (CEPH_I_KICK_FLUSH | CEPH_I_FLUSH_SNAPS)) {
+			if (ci->i_ceph_flags & CEPH_I_KICK_FLUSH)
+				__kick_flushing_caps(mdsc, session, ci, 0);
+			if (ci->i_ceph_flags & CEPH_I_FLUSH_SNAPS)
+				__ceph_flush_snaps(ci, session);
+			goto retry_locked;
+		}
+
 		flushing = __mark_caps_flushing(inode, session, true,
 						&flush_tid, &oldest_flush_tid);
 
 		/* __send_cap drops i_ceph_lock */
-		delayed = __send_cap(mdsc, cap, CEPH_CAP_OP_FLUSH, true,
-				used, want, (cap->issued | cap->implemented),
-				flushing, flush_tid, oldest_flush_tid);
+		delayed = __send_cap(mdsc, cap, CEPH_CAP_OP_FLUSH,
+				     CEPH_CLIENT_CAPS_SYNC,
+				     __ceph_caps_used(ci),
+				     __ceph_caps_wanted(ci),
+				     (cap->issued | cap->implemented),
+				     flushing, flush_tid, oldest_flush_tid);
 
 		if (delayed) {
 			spin_lock(&ci->i_ceph_lock);
@@ -2320,6 +2336,16 @@ static void __kick_flushing_caps(struct ceph_mds_client *mdsc,
 	struct ceph_cap_flush *cf;
 	int ret;
 	u64 first_tid = 0;
+	u64 last_snap_flush = 0;
+
+	ci->i_ceph_flags &= ~CEPH_I_KICK_FLUSH;
+
+	list_for_each_entry_reverse(cf, &ci->i_cap_flush_list, i_list) {
+		if (!cf->caps) {
+			last_snap_flush = cf->tid;
+			break;
+		}
+	}
 
 	list_for_each_entry(cf, &ci->i_cap_flush_list, i_list) {
 		if (cf->tid < first_tid)
@@ -2338,10 +2364,13 @@ static void __kick_flushing_caps(struct ceph_mds_client *mdsc,
 			dout("kick_flushing_caps %p cap %p tid %llu %s\n",
 			     inode, cap, cf->tid, ceph_cap_string(cf->caps));
 			ci->i_ceph_flags |= CEPH_I_NODELAY;
+
 			ret = __send_cap(mdsc, cap, CEPH_CAP_OP_FLUSH,
-					  false, __ceph_caps_used(ci),
+					 (cf->tid < last_snap_flush ?
+					  CEPH_CLIENT_CAPS_PENDING_CAPSNAP : 0),
+					  __ceph_caps_used(ci),
 					  __ceph_caps_wanted(ci),
-					  cap->issued | cap->implemented,
+					  (cap->issued | cap->implemented),
 					  cf->caps, cf->tid, oldest_flush_tid);
 			if (ret) {
 				pr_err("kick_flushing_caps: error sending "
@@ -2410,7 +2439,6 @@ void ceph_early_kick_flushing_caps(struct ceph_mds_client *mdsc,
 		 */
 		if ((cap->issued & ci->i_flushing_caps) !=
 		    ci->i_flushing_caps) {
-			ci->i_ceph_flags &= ~CEPH_I_KICK_FLUSH;
 			/* encode_caps_cb() also will reset these sequence
 			 * numbers. make sure sequence numbers in cap flush
 			 * message match later reconnect message */
@@ -2450,7 +2478,6 @@ void ceph_kick_flushing_caps(struct ceph_mds_client *mdsc,
 			continue;
 		}
 		if (ci->i_ceph_flags & CEPH_I_KICK_FLUSH) {
-			ci->i_ceph_flags &= ~CEPH_I_KICK_FLUSH;
 			__kick_flushing_caps(mdsc, session, ci,
 					     oldest_flush_tid);
 		}
@@ -2478,7 +2505,6 @@ static void kick_flushing_inode_caps(struct ceph_mds_client *mdsc,
 		oldest_flush_tid = __get_oldest_flush_tid(mdsc);
 		spin_unlock(&mdsc->cap_dirty_lock);
 
-		ci->i_ceph_flags &= ~CEPH_I_KICK_FLUSH;
 		__kick_flushing_caps(mdsc, session, ci, oldest_flush_tid);
 		spin_unlock(&ci->i_ceph_lock);
 	} else {
@@ -3040,8 +3066,10 @@ struct cap_extra_info {
 	bool dirstat_valid;
 	u64 nfiles;
 	u64 nsubdirs;
+	u64 change_attr;
 	/* currently issued */
 	int issued;
+	struct timespec64 btime;
 };
 
 /*
@@ -3123,11 +3151,14 @@ static void handle_cap_grant(struct inode *inode,
 
 	__check_cap_issue(ci, cap, newcaps);
 
+	inode_set_max_iversion_raw(inode, extra_info->change_attr);
+
 	if ((newcaps & CEPH_CAP_AUTH_SHARED) &&
 	    (extra_info->issued & CEPH_CAP_AUTH_EXCL) == 0) {
 		inode->i_mode = le32_to_cpu(grant->mode);
 		inode->i_uid = make_kuid(&init_user_ns, le32_to_cpu(grant->uid));
 		inode->i_gid = make_kgid(&init_user_ns, le32_to_cpu(grant->gid));
+		ci->i_btime = extra_info->btime;
 		dout("%p mode 0%o uid.gid %d.%d\n", inode, inode->i_mode,
 		     from_kuid(&init_user_ns, inode->i_uid),
 		     from_kgid(&init_user_ns, inode->i_gid));
@@ -3154,6 +3185,7 @@ static void handle_cap_grant(struct inode *inode,
 			ci->i_xattrs.blob = ceph_buffer_get(xattr_buf);
 			ci->i_xattrs.version = version;
 			ceph_forget_all_cached_acls(inode);
+			ceph_security_invalidate_secctx(inode);
 		}
 	}
 
@@ -3848,17 +3880,19 @@ void ceph_handle_caps(struct ceph_mds_session *session,
 		}
 	}
 
-	if (msg_version >= 11) {
+	if (msg_version >= 9) {
 		struct ceph_timespec *btime;
-		u64 change_attr;
-		u32 flags;
 
-		/* version >= 9 */
 		if (p + sizeof(*btime) > end)
 			goto bad;
 		btime = p;
+		ceph_decode_timespec64(&extra_info.btime, btime);
 		p += sizeof(*btime);
-		ceph_decode_64_safe(&p, end, change_attr, bad);
+		ceph_decode_64_safe(&p, end, extra_info.change_attr, bad);
+	}
+
+	if (msg_version >= 11) {
+		u32 flags;
 		/* version >= 10 */
 		ceph_decode_32_safe(&p, end, flags, bad);
 		/* version >= 11 */