Merge tag 'ceph-for-5.8-rc1' of git://github.com/ceph/ceph-client

Pull ceph updates from Ilya Dryomov:
 "The highlights are:

   - OSD/MDS latency and caps cache metrics infrastructure for the
     filesytem (Xiubo Li). Currently available through debugfs and will
     be periodically sent to the MDS in the future.

   - support for replica reads (balanced and localized reads) for rbd
     and the filesystem (myself). The default remains to always read
     from primary, users can opt-in with the new crush_location and
     read_from_replica options. Note that reading from replica is safe
     for general use only since Octopus.

   - support for RADOS allocation hint flags (myself). Currently used by
     rbd to propagate the compressible/incompressible hint given with
     the new compression_hint map option and ready for passing on more
     advanced hints, e.g. based on fadvise() from the filesystem.

   - support for efficient cross-quota-realm renames (Luis Henriques)

   - assorted cap handling improvements and cleanups, particularly
     untangling some of the locking (Jeff Layton)"

* tag 'ceph-for-5.8-rc1' of git://github.com/ceph/ceph-client: (29 commits)
  rbd: compression_hint option
  libceph: support for alloc hint flags
  libceph: read_from_replica option
  libceph: support for balanced and localized reads
  libceph: crush_location infrastructure
  libceph: decode CRUSH device/bucket types and names
  libceph: add non-asserting rbtree insertion helper
  ceph: skip checking caps when session reconnecting and releasing reqs
  ceph: make sure mdsc->mutex is nested in s->s_mutex to fix dead lock
  ceph: don't return -ESTALE if there's still an open file
  libceph, rbd: replace zero-length array with flexible-array
  ceph: allow rename operation under different quota realms
  ceph: normalize 'delta' parameter usage in check_quota_exceeded
  ceph: ceph_kick_flushing_caps needs the s_mutex
  ceph: request expedited service on session's last cap flush
  ceph: convert mdsc->cap_dirty to a per-session list
  ceph: reset i_requested_max_size if file write is not wanted
  ceph: throw a warning if we destroy session with mutex still locked
  ceph: fix potential race in ceph_check_caps
  ceph: document what protects i_dirty_item and i_flushing_item
  ...

drivers/block/rbd.c

@@ -836,6 +836,7 @@ enum {
 	Opt_lock_timeout,
 	/* int args above */
 	Opt_pool_ns,
+	Opt_compression_hint,
 	/* string args above */
 	Opt_read_only,
 	Opt_read_write,
@@ -844,8 +845,23 @@ enum {
 	Opt_notrim,
 };
 
+enum {
+	Opt_compression_hint_none,
+	Opt_compression_hint_compressible,
+	Opt_compression_hint_incompressible,
+};
+
+static const struct constant_table rbd_param_compression_hint[] = {
+	{"none",		Opt_compression_hint_none},
+	{"compressible",	Opt_compression_hint_compressible},
+	{"incompressible",	Opt_compression_hint_incompressible},
+	{}
+};
+
 static const struct fs_parameter_spec rbd_parameters[] = {
 	fsparam_u32	("alloc_size",			Opt_alloc_size),
+	fsparam_enum	("compression_hint",		Opt_compression_hint,
+			 rbd_param_compression_hint),
 	fsparam_flag	("exclusive",			Opt_exclusive),
 	fsparam_flag	("lock_on_read",		Opt_lock_on_read),
 	fsparam_u32	("lock_timeout",		Opt_lock_timeout),
@@ -867,6 +883,8 @@ struct rbd_options {
 	bool	lock_on_read;
 	bool	exclusive;
 	bool	trim;
+
+	u32 alloc_hint_flags;  /* CEPH_OSD_OP_ALLOC_HINT_FLAG_* */
 };
 
 #define RBD_QUEUE_DEPTH_DEFAULT	BLKDEV_MAX_RQ
@@ -2253,7 +2271,8 @@ static void __rbd_osd_setup_write_ops(struct ceph_osd_request *osd_req,
 	    !(obj_req->flags & RBD_OBJ_FLAG_MAY_EXIST)) {
 		osd_req_op_alloc_hint_init(osd_req, which++,
 					   rbd_dev->layout.object_size,
-					   rbd_dev->layout.object_size);
+					   rbd_dev->layout.object_size,
+					   rbd_dev->opts->alloc_hint_flags);
 	}
 
 	if (rbd_obj_is_entire(obj_req))
@@ -6331,6 +6350,29 @@ static int rbd_parse_param(struct fs_parameter *param,
 		pctx->spec->pool_ns = param->string;
 		param->string = NULL;
 		break;
+	case Opt_compression_hint:
+		switch (result.uint_32) {
+		case Opt_compression_hint_none:
+			opt->alloc_hint_flags &=
+			    ~(CEPH_OSD_ALLOC_HINT_FLAG_COMPRESSIBLE |
+			      CEPH_OSD_ALLOC_HINT_FLAG_INCOMPRESSIBLE);
+			break;
+		case Opt_compression_hint_compressible:
+			opt->alloc_hint_flags |=
+			    CEPH_OSD_ALLOC_HINT_FLAG_COMPRESSIBLE;
+			opt->alloc_hint_flags &=
+			    ~CEPH_OSD_ALLOC_HINT_FLAG_INCOMPRESSIBLE;
+			break;
+		case Opt_compression_hint_incompressible:
+			opt->alloc_hint_flags |=
+			    CEPH_OSD_ALLOC_HINT_FLAG_INCOMPRESSIBLE;
+			opt->alloc_hint_flags &=
+			    ~CEPH_OSD_ALLOC_HINT_FLAG_COMPRESSIBLE;
+			break;
+		default:
+			BUG();
+		}
+		break;
 	case Opt_read_only:
 		opt->read_only = true;
 		break;

drivers/block/rbd_types.h

@@ -93,7 +93,7 @@ struct rbd_image_header_ondisk {
 	__le32 snap_count;
 	__le32 reserved;
 	__le64 snap_names_len;
-	struct rbd_image_snap_ondisk snaps[0];
+	struct rbd_image_snap_ondisk snaps[];
 } __attribute__((packed));
 
 

fs/ceph/Makefile

@@ -8,7 +8,7 @@ obj-$(CONFIG_CEPH_FS) += ceph.o
 ceph-y := super.o inode.o dir.o file.o locks.o addr.o ioctl.o \
 	export.o caps.o snap.o xattr.o quota.o io.o \
 	mds_client.o mdsmap.o strings.o ceph_frag.o \
-	debugfs.o util.o
+	debugfs.o util.o metric.o
 
 ceph-$(CONFIG_CEPH_FSCACHE) += cache.o
 ceph-$(CONFIG_CEPH_FS_POSIX_ACL) += acl.o

fs/ceph/acl.c

@@ -22,7 +22,7 @@ static inline void ceph_set_cached_acl(struct inode *inode,
 	struct ceph_inode_info *ci = ceph_inode(inode);
 
 	spin_lock(&ci->i_ceph_lock);
-	if (__ceph_caps_issued_mask(ci, CEPH_CAP_XATTR_SHARED, 0))
+	if (__ceph_caps_issued_mask_metric(ci, CEPH_CAP_XATTR_SHARED, 0))
 		set_cached_acl(inode, type, acl);
 	else
 		forget_cached_acl(inode, type);

fs/ceph/addr.c

@@ -11,10 +11,12 @@
 #include <linux/task_io_accounting_ops.h>
 #include <linux/signal.h>
 #include <linux/iversion.h>
+#include <linux/ktime.h>
 
 #include "super.h"
 #include "mds_client.h"
 #include "cache.h"
+#include "metric.h"
 #include <linux/ceph/osd_client.h>
 #include <linux/ceph/striper.h>
 
@@ -216,6 +218,9 @@ static int ceph_sync_readpages(struct ceph_fs_client *fsc,
 	if (!rc)
 		rc = ceph_osdc_wait_request(osdc, req);
 
+	ceph_update_read_latency(&fsc->mdsc->metric, req->r_start_latency,
+				 req->r_end_latency, rc);
+
 	ceph_osdc_put_request(req);
 	dout("readpages result %d\n", rc);
 	return rc;
@@ -299,6 +304,7 @@ static int ceph_readpage(struct file *filp, struct page *page)
 static void finish_read(struct ceph_osd_request *req)
 {
 	struct inode *inode = req->r_inode;
+	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
 	struct ceph_osd_data *osd_data;
 	int rc = req->r_result <= 0 ? req->r_result : 0;
 	int bytes = req->r_result >= 0 ? req->r_result : 0;
@@ -336,6 +342,10 @@ unlock:
 		put_page(page);
 		bytes -= PAGE_SIZE;
 	}
+
+	ceph_update_read_latency(&fsc->mdsc->metric, req->r_start_latency,
+				 req->r_end_latency, rc);
+
 	kfree(osd_data->pages);
 }
 
@@ -643,6 +653,9 @@ static int ceph_sync_writepages(struct ceph_fs_client *fsc,
 	if (!rc)
 		rc = ceph_osdc_wait_request(osdc, req);
 
+	ceph_update_write_latency(&fsc->mdsc->metric, req->r_start_latency,
+				  req->r_end_latency, rc);
+
 	ceph_osdc_put_request(req);
 	if (rc == 0)
 		rc = len;
@@ -794,6 +807,9 @@ static void writepages_finish(struct ceph_osd_request *req)
 		ceph_clear_error_write(ci);
 	}
 
+	ceph_update_write_latency(&fsc->mdsc->metric, req->r_start_latency,
+				  req->r_end_latency, rc);
+
 	/*
 	 * We lost the cache cap, need to truncate the page before
 	 * it is unlocked, otherwise we'd truncate it later in the
@@ -1852,6 +1868,10 @@ int ceph_uninline_data(struct file *filp, struct page *locked_page)
 	err = ceph_osdc_start_request(&fsc->client->osdc, req, false);
 	if (!err)
 		err = ceph_osdc_wait_request(&fsc->client->osdc, req);
+
+	ceph_update_write_latency(&fsc->mdsc->metric, req->r_start_latency,
+				  req->r_end_latency, err);
+
 out_put:
 	ceph_osdc_put_request(req);
 	if (err == -ECANCELED)

fs/ceph/debugfs.c

@@ -7,6 +7,8 @@
 #include <linux/ctype.h>
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
+#include <linux/math64.h>
+#include <linux/ktime.h>
 
 #include <linux/ceph/libceph.h>
 #include <linux/ceph/mon_client.h>
@@ -18,6 +20,7 @@
 #ifdef CONFIG_DEBUG_FS
 
 #include "mds_client.h"
+#include "metric.h"
 
 static int mdsmap_show(struct seq_file *s, void *p)
 {
@@ -124,6 +127,87 @@ static int mdsc_show(struct seq_file *s, void *p)
 	return 0;
 }
 
+#define CEPH_METRIC_SHOW(name, total, avg, min, max, sq) {		\
+	s64 _total, _avg, _min, _max, _sq, _st;				\
+	_avg = ktime_to_us(avg);					\
+	_min = ktime_to_us(min == KTIME_MAX ? 0 : min);			\
+	_max = ktime_to_us(max);					\
+	_total = total - 1;						\
+	_sq = _total > 0 ? DIV64_U64_ROUND_CLOSEST(sq, _total) : 0;	\
+	_st = int_sqrt64(_sq);						\
+	_st = ktime_to_us(_st);						\
+	seq_printf(s, "%-14s%-12lld%-16lld%-16lld%-16lld%lld\n",	\
+		   name, total, _avg, _min, _max, _st);			\
+}
+
+static int metric_show(struct seq_file *s, void *p)
+{
+	struct ceph_fs_client *fsc = s->private;
+	struct ceph_mds_client *mdsc = fsc->mdsc;
+	struct ceph_client_metric *m = &mdsc->metric;
+	int i, nr_caps = 0;
+	s64 total, sum, avg, min, max, sq;
+
+	seq_printf(s, "item          total       avg_lat(us)     min_lat(us)     max_lat(us)     stdev(us)\n");
+	seq_printf(s, "-----------------------------------------------------------------------------------\n");
+
+	spin_lock(&m->read_latency_lock);
+	total = m->total_reads;
+	sum = m->read_latency_sum;
+	avg = total > 0 ? DIV64_U64_ROUND_CLOSEST(sum, total) : 0;
+	min = m->read_latency_min;
+	max = m->read_latency_max;
+	sq = m->read_latency_sq_sum;
+	spin_unlock(&m->read_latency_lock);
+	CEPH_METRIC_SHOW("read", total, avg, min, max, sq);
+
+	spin_lock(&m->write_latency_lock);
+	total = m->total_writes;
+	sum = m->write_latency_sum;
+	avg = total > 0 ? DIV64_U64_ROUND_CLOSEST(sum, total) : 0;
+	min = m->write_latency_min;
+	max = m->write_latency_max;
+	sq = m->write_latency_sq_sum;
+	spin_unlock(&m->write_latency_lock);
+	CEPH_METRIC_SHOW("write", total, avg, min, max, sq);
+
+	spin_lock(&m->metadata_latency_lock);
+	total = m->total_metadatas;
+	sum = m->metadata_latency_sum;
+	avg = total > 0 ? DIV64_U64_ROUND_CLOSEST(sum, total) : 0;
+	min = m->metadata_latency_min;
+	max = m->metadata_latency_max;
+	sq = m->metadata_latency_sq_sum;
+	spin_unlock(&m->metadata_latency_lock);
+	CEPH_METRIC_SHOW("metadata", total, avg, min, max, sq);
+
+	seq_printf(s, "\n");
+	seq_printf(s, "item          total           miss            hit\n");
+	seq_printf(s, "-------------------------------------------------\n");
+
+	seq_printf(s, "%-14s%-16lld%-16lld%lld\n", "d_lease",
+		   atomic64_read(&m->total_dentries),
+		   percpu_counter_sum(&m->d_lease_mis),
+		   percpu_counter_sum(&m->d_lease_hit));
+
+	mutex_lock(&mdsc->mutex);
+	for (i = 0; i < mdsc->max_sessions; i++) {
+		struct ceph_mds_session *s;
+
+		s = __ceph_lookup_mds_session(mdsc, i);
+		if (!s)
+			continue;
+		nr_caps += s->s_nr_caps;
+		ceph_put_mds_session(s);
+	}
+	mutex_unlock(&mdsc->mutex);
+	seq_printf(s, "%-14s%-16d%-16lld%lld\n", "caps", nr_caps,
+		   percpu_counter_sum(&m->i_caps_mis),
+		   percpu_counter_sum(&m->i_caps_hit));
+
+	return 0;
+}
+
 static int caps_show_cb(struct inode *inode, struct ceph_cap *cap, void *p)
 {
 	struct seq_file *s = p;
@@ -222,6 +306,7 @@ DEFINE_SHOW_ATTRIBUTE(mdsmap);
 DEFINE_SHOW_ATTRIBUTE(mdsc);
 DEFINE_SHOW_ATTRIBUTE(caps);
 DEFINE_SHOW_ATTRIBUTE(mds_sessions);
+DEFINE_SHOW_ATTRIBUTE(metric);
 
 
 /*
@@ -255,6 +340,7 @@ void ceph_fs_debugfs_cleanup(struct ceph_fs_client *fsc)
 	debugfs_remove(fsc->debugfs_mdsmap);
 	debugfs_remove(fsc->debugfs_mds_sessions);
 	debugfs_remove(fsc->debugfs_caps);
+	debugfs_remove(fsc->debugfs_metric);
 	debugfs_remove(fsc->debugfs_mdsc);
 }
 
@@ -295,11 +381,17 @@ void ceph_fs_debugfs_init(struct ceph_fs_client *fsc)
 						fsc,
 						&mdsc_fops);
 
+	fsc->debugfs_metric = debugfs_create_file("metrics",
+						  0400,
+						  fsc->client->debugfs_dir,
+						  fsc,
+						  &metric_fops);
+
 	fsc->debugfs_caps = debugfs_create_file("caps",
-						   0400,
-						   fsc->client->debugfs_dir,
-						   fsc,
-						   &caps_fops);
+						0400,
+						fsc->client->debugfs_dir,
+						fsc,
+						&caps_fops);
 }
 
 

fs/ceph/dir.c

@@ -38,6 +38,8 @@ static int __dir_lease_try_check(const struct dentry *dentry);
 static int ceph_d_init(struct dentry *dentry)
 {
 	struct ceph_dentry_info *di;
+	struct ceph_fs_client *fsc = ceph_sb_to_client(dentry->d_sb);
+	struct ceph_mds_client *mdsc = fsc->mdsc;
 
 	di = kmem_cache_zalloc(ceph_dentry_cachep, GFP_KERNEL);
 	if (!di)
@@ -48,6 +50,9 @@ static int ceph_d_init(struct dentry *dentry)
 	di->time = jiffies;
 	dentry->d_fsdata = di;
 	INIT_LIST_HEAD(&di->lease_list);
+
+	atomic64_inc(&mdsc->metric.total_dentries);
+
 	return 0;
 }
 
@@ -344,8 +349,9 @@ static int ceph_readdir(struct file *file, struct dir_context *ctx)
 	    !ceph_test_mount_opt(fsc, NOASYNCREADDIR) &&
 	    ceph_snap(inode) != CEPH_SNAPDIR &&
 	    __ceph_dir_is_complete_ordered(ci) &&
-	    __ceph_caps_issued_mask(ci, CEPH_CAP_FILE_SHARED, 1)) {
+	    __ceph_caps_issued_mask_metric(ci, CEPH_CAP_FILE_SHARED, 1)) {
 		int shared_gen = atomic_read(&ci->i_shared_gen);
+
 		spin_unlock(&ci->i_ceph_lock);
 		err = __dcache_readdir(file, ctx, shared_gen);
 		if (err != -EAGAIN)
@@ -762,7 +768,7 @@ static struct dentry *ceph_lookup(struct inode *dir, struct dentry *dentry,
 		    !is_root_ceph_dentry(dir, dentry) &&
 		    ceph_test_mount_opt(fsc, DCACHE) &&
 		    __ceph_dir_is_complete(ci) &&
-		    (__ceph_caps_issued_mask(ci, CEPH_CAP_FILE_SHARED, 1))) {
+		    __ceph_caps_issued_mask_metric(ci, CEPH_CAP_FILE_SHARED, 1)) {
 			__ceph_touch_fmode(ci, mdsc, CEPH_FILE_MODE_RD);
 			spin_unlock(&ci->i_ceph_lock);
 			dout(" dir %p complete, -ENOENT\n", dir);
@@ -1203,11 +1209,12 @@ static int ceph_rename(struct inode *old_dir, struct dentry *old_dentry,
 			op = CEPH_MDS_OP_RENAMESNAP;
 		else
 			return -EROFS;
+	} else if (old_dir != new_dir) {
+		err = ceph_quota_check_rename(mdsc, d_inode(old_dentry),
+					      new_dir);
+		if (err)
+			return err;
 	}
-	/* don't allow cross-quota renames */
-	if ((old_dir != new_dir) &&
-	    (!ceph_quota_is_same_realm(old_dir, new_dir)))
-		return -EXDEV;
 
 	dout("rename dir %p dentry %p to dir %p dentry %p\n",
 	     old_dir, old_dentry, new_dir, new_dentry);
@@ -1709,6 +1716,8 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags)
 		if (flags & LOOKUP_RCU)
 			return -ECHILD;
 
+		percpu_counter_inc(&mdsc->metric.d_lease_mis);
+
 		op = ceph_snap(dir) == CEPH_SNAPDIR ?
 			CEPH_MDS_OP_LOOKUPSNAP : CEPH_MDS_OP_LOOKUP;
 		req = ceph_mdsc_create_request(mdsc, op, USE_ANY_MDS);
@@ -1740,6 +1749,8 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags)
 			dout("d_revalidate %p lookup result=%d\n",
 			     dentry, err);
 		}
+	} else {
+		percpu_counter_inc(&mdsc->metric.d_lease_hit);
 	}
 
 	dout("d_revalidate %p %s\n", dentry, valid ? "valid" : "invalid");
@@ -1782,9 +1793,12 @@ static int ceph_d_delete(const struct dentry *dentry)
 static void ceph_d_release(struct dentry *dentry)
 {
 	struct ceph_dentry_info *di = ceph_dentry(dentry);
+	struct ceph_fs_client *fsc = ceph_sb_to_client(dentry->d_sb);
 
 	dout("d_release %p\n", dentry);
 
+	atomic64_dec(&fsc->mdsc->metric.total_dentries);
+
 	spin_lock(&dentry->d_lock);
 	__dentry_lease_unlist(di);
 	dentry->d_fsdata = NULL;

fs/ceph/export.c

@@ -172,9 +172,16 @@ struct inode *ceph_lookup_inode(struct super_block *sb, u64 ino)
 static struct dentry *__fh_to_dentry(struct super_block *sb, u64 ino)
 {
 	struct inode *inode = __lookup_inode(sb, ino);
+	int err;
+
 	if (IS_ERR(inode))
 		return ERR_CAST(inode);
-	if (inode->i_nlink == 0) {
+	/* We need LINK caps to reliably check i_nlink */
+	err = ceph_do_getattr(inode, CEPH_CAP_LINK_SHARED, false);
+	if (err)
+		return ERR_PTR(err);
+	/* -ESTALE if inode as been unlinked and no file is open */
+	if ((inode->i_nlink == 0) && (atomic_read(&inode->i_count) == 1)) {
 		iput(inode);
 		return ERR_PTR(-ESTALE);
 	}

fs/ceph/file.c

@@ -11,11 +11,13 @@
 #include <linux/writeback.h>
 #include <linux/falloc.h>
 #include <linux/iversion.h>
+#include <linux/ktime.h>
 
 #include "super.h"
 #include "mds_client.h"
 #include "cache.h"
 #include "io.h"
+#include "metric.h"
 
 static __le32 ceph_flags_sys2wire(u32 flags)
 {
@@ -906,6 +908,12 @@ static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *to,
 		ret = ceph_osdc_start_request(osdc, req, false);
 		if (!ret)
 			ret = ceph_osdc_wait_request(osdc, req);
+
+		ceph_update_read_latency(&fsc->mdsc->metric,
+					 req->r_start_latency,
+					 req->r_end_latency,
+					 ret);
+
 		ceph_osdc_put_request(req);
 
 		i_size = i_size_read(inode);
@@ -1044,6 +1052,8 @@ static void ceph_aio_complete_req(struct ceph_osd_request *req)
 	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);
+	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
+	struct ceph_client_metric *metric = &fsc->mdsc->metric;
 
 	BUG_ON(osd_data->type != CEPH_OSD_DATA_TYPE_BVECS);
 	BUG_ON(!osd_data->num_bvecs);
@@ -1051,6 +1061,16 @@ static void ceph_aio_complete_req(struct ceph_osd_request *req)
 	dout("ceph_aio_complete_req %p rc %d bytes %u\n",
 	     inode, rc, osd_data->bvec_pos.iter.bi_size);
 
+	/* r_start_latency == 0 means the request was not submitted */
+	if (req->r_start_latency) {
+		if (aio_req->write)
+			ceph_update_write_latency(metric, req->r_start_latency,
+						  req->r_end_latency, rc);
+		else
+			ceph_update_read_latency(metric, req->r_start_latency,
+						 req->r_end_latency, rc);
+	}
+
 	if (rc == -EOLDSNAPC) {
 		struct ceph_aio_work *aio_work;
 		BUG_ON(!aio_req->write);
@@ -1179,6 +1199,7 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
 	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_client_metric *metric = &fsc->mdsc->metric;
 	struct ceph_vino vino;
 	struct ceph_osd_request *req;
 	struct bio_vec *bvecs;
@@ -1295,6 +1316,13 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
 		if (!ret)
 			ret = ceph_osdc_wait_request(&fsc->client->osdc, req);
 
+		if (write)
+			ceph_update_write_latency(metric, req->r_start_latency,
+						  req->r_end_latency, ret);
+		else
+			ceph_update_read_latency(metric, req->r_start_latency,
+						 req->r_end_latency, ret);
+
 		size = i_size_read(inode);
 		if (!write) {
 			if (ret == -ENOENT)
@@ -1466,6 +1494,8 @@ ceph_sync_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos,
 		if (!ret)
 			ret = ceph_osdc_wait_request(&fsc->client->osdc, req);
 
+		ceph_update_write_latency(&fsc->mdsc->metric, req->r_start_latency,
+					  req->r_end_latency, ret);
 out:
 		ceph_osdc_put_request(req);
 		if (ret != 0) {

fs/ceph/inode.c

@@ -2288,8 +2288,8 @@ int __ceph_do_getattr(struct inode *inode, struct page *locked_page,
 
 	dout("do_getattr inode %p mask %s mode 0%o\n",
 	     inode, ceph_cap_string(mask), inode->i_mode);
-	if (!force && ceph_caps_issued_mask(ceph_inode(inode), mask, 1))
-		return 0;
+	if (!force && ceph_caps_issued_mask_metric(ceph_inode(inode), mask, 1))
+			return 0;
 
 	mode = (mask & CEPH_STAT_RSTAT) ? USE_AUTH_MDS : USE_ANY_MDS;
 	req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_GETATTR, mode);

fs/ceph/mds_client.c

@@ -10,6 +10,7 @@
 #include <linux/seq_file.h>
 #include <linux/ratelimit.h>
 #include <linux/bits.h>
+#include <linux/ktime.h>
 
 #include "super.h"
 #include "mds_client.h"
@@ -658,6 +659,7 @@ void ceph_put_mds_session(struct ceph_mds_session *s)
 	if (refcount_dec_and_test(&s->s_ref)) {
 		if (s->s_auth.authorizer)
 			ceph_auth_destroy_authorizer(s->s_auth.authorizer);
+		WARN_ON(mutex_is_locked(&s->s_mutex));
 		xa_destroy(&s->s_delegated_inos);
 		kfree(s);
 	}
@@ -753,6 +755,7 @@ static struct ceph_mds_session *register_session(struct ceph_mds_client *mdsc,
 	INIT_LIST_HEAD(&s->s_cap_releases);
 	INIT_WORK(&s->s_cap_release_work, ceph_cap_release_work);
 
+	INIT_LIST_HEAD(&s->s_cap_dirty);
 	INIT_LIST_HEAD(&s->s_cap_flushing);
 
 	mdsc->sessions[mds] = s;
@@ -801,7 +804,7 @@ void ceph_mdsc_release_request(struct kref *kref)
 	struct ceph_mds_request *req = container_of(kref,
 						    struct ceph_mds_request,
 						    r_kref);
-	ceph_mdsc_release_dir_caps(req);
+	ceph_mdsc_release_dir_caps_no_check(req);
 	destroy_reply_info(&req->r_reply_info);
 	if (req->r_request)
 		ceph_msg_put(req->r_request);
@@ -2201,6 +2204,7 @@ ceph_mdsc_create_request(struct ceph_mds_client *mdsc, int op, int mode)
 	mutex_init(&req->r_fill_mutex);
 	req->r_mdsc = mdsc;
 	req->r_started = jiffies;
+	req->r_start_latency = ktime_get();
 	req->r_resend_mds = -1;
 	INIT_LIST_HEAD(&req->r_unsafe_dir_item);
 	INIT_LIST_HEAD(&req->r_unsafe_target_item);
@@ -2547,6 +2551,8 @@ out:
 static void complete_request(struct ceph_mds_client *mdsc,
 			     struct ceph_mds_request *req)
 {
+	req->r_end_latency = ktime_get();
+
 	if (req->r_callback)
 		req->r_callback(mdsc, req);
 	complete_all(&req->r_completion);
@@ -3155,6 +3161,9 @@ out_err:
 
 	/* kick calling process */
 	complete_request(mdsc, req);
+
+	ceph_update_metadata_latency(&mdsc->metric, req->r_start_latency,
+				     req->r_end_latency, err);
 out:
 	ceph_mdsc_put_request(req);
 	return;
@@ -3393,6 +3402,18 @@ void ceph_mdsc_release_dir_caps(struct ceph_mds_request *req)
 	}
 }
 
+void ceph_mdsc_release_dir_caps_no_check(struct ceph_mds_request *req)
+{
+	int dcaps;
+
+	dcaps = xchg(&req->r_dir_caps, 0);
+	if (dcaps) {
+		dout("releasing r_dir_caps=%s\n", ceph_cap_string(dcaps));
+		ceph_put_cap_refs_no_check_caps(ceph_inode(req->r_parent),
+						dcaps);
+	}
+}
+
 /*
  * called under session->mutex.
  */
@@ -3425,7 +3446,7 @@ static void replay_unsafe_requests(struct ceph_mds_client *mdsc,
 		if (req->r_session->s_mds != session->s_mds)
 			continue;
 
-		ceph_mdsc_release_dir_caps(req);
+		ceph_mdsc_release_dir_caps_no_check(req);
 
 		__send_request(mdsc, session, req, true);
 	}
@@ -3760,8 +3781,6 @@ fail:
  * recovering MDS might have.
  *
  * This is a relatively heavyweight operation, but it's rare.
- *
- * called with mdsc->mutex held.
  */
 static void send_mds_reconnect(struct ceph_mds_client *mdsc,
 			       struct ceph_mds_session *session)
@@ -4015,7 +4034,11 @@ static void check_new_map(struct ceph_mds_client *mdsc,
 			    oldstate != CEPH_MDS_STATE_STARTING)
 				pr_info("mds%d recovery completed\n", s->s_mds);
 			kick_requests(mdsc, i);
+			mutex_unlock(&mdsc->mutex);
+			mutex_lock(&s->s_mutex);
+			mutex_lock(&mdsc->mutex);
 			ceph_kick_flushing_caps(mdsc, s);
+			mutex_unlock(&s->s_mutex);
 			wake_up_session_caps(s, RECONNECT);
 		}
 	}
@@ -4323,6 +4346,7 @@ int ceph_mdsc_init(struct ceph_fs_client *fsc)
 
 {
 	struct ceph_mds_client *mdsc;
+	int err;
 
 	mdsc = kzalloc(sizeof(struct ceph_mds_client), GFP_NOFS);
 	if (!mdsc)
@@ -4331,8 +4355,8 @@ int ceph_mdsc_init(struct ceph_fs_client *fsc)
 	mutex_init(&mdsc->mutex);
 	mdsc->mdsmap = kzalloc(sizeof(*mdsc->mdsmap), GFP_NOFS);
 	if (!mdsc->mdsmap) {
-		kfree(mdsc);
-		return -ENOMEM;
+		err = -ENOMEM;
+		goto err_mdsc;
 	}
 
 	fsc->mdsc = mdsc;
@@ -4364,13 +4388,15 @@ int ceph_mdsc_init(struct ceph_fs_client *fsc)
 	spin_lock_init(&mdsc->snap_flush_lock);
 	mdsc->last_cap_flush_tid = 1;
 	INIT_LIST_HEAD(&mdsc->cap_flush_list);
-	INIT_LIST_HEAD(&mdsc->cap_dirty);
 	INIT_LIST_HEAD(&mdsc->cap_dirty_migrating);
 	mdsc->num_cap_flushing = 0;
 	spin_lock_init(&mdsc->cap_dirty_lock);
 	init_waitqueue_head(&mdsc->cap_flushing_wq);
 	INIT_WORK(&mdsc->cap_reclaim_work, ceph_cap_reclaim_work);
 	atomic_set(&mdsc->cap_reclaim_pending, 0);
+	err = ceph_metric_init(&mdsc->metric);
+	if (err)
+		goto err_mdsmap;
 
 	spin_lock_init(&mdsc->dentry_list_lock);
 	INIT_LIST_HEAD(&mdsc->dentry_leases);
@@ -4389,6 +4415,12 @@ int ceph_mdsc_init(struct ceph_fs_client *fsc)
 	strscpy(mdsc->nodename, utsname()->nodename,
 		sizeof(mdsc->nodename));
 	return 0;
+
+err_mdsmap:
+	kfree(mdsc->mdsmap);
+err_mdsc:
+	kfree(mdsc);
+	return err;
 }
 
 /*
@@ -4646,6 +4678,8 @@ void ceph_mdsc_destroy(struct ceph_fs_client *fsc)
 
 	ceph_mdsc_stop(mdsc);
 
+	ceph_metric_destroy(&mdsc->metric);
+
 	fsc->mdsc = NULL;
 	kfree(mdsc);
 	dout("mdsc_destroy %p done\n", mdsc);

fs/ceph/mds_client.h

@@ -10,12 +10,15 @@
 #include <linux/spinlock.h>
 #include <linux/refcount.h>
 #include <linux/utsname.h>
+#include <linux/ktime.h>
 
 #include <linux/ceph/types.h>
 #include <linux/ceph/messenger.h>
 #include <linux/ceph/mdsmap.h>
 #include <linux/ceph/auth.h>
 
+#include "metric.h"
+
 /* The first 8 bits are reserved for old ceph releases */
 enum ceph_feature_type {
 	CEPHFS_FEATURE_MIMIC = 8,
@@ -196,8 +199,12 @@ struct ceph_mds_session {
 	struct list_head  s_cap_releases; /* waiting cap_release messages */
 	struct work_struct s_cap_release_work;
 
-	/* protected by mutex */
+	/* See ceph_inode_info->i_dirty_item. */
+	struct list_head  s_cap_dirty;	      /* inodes w/ dirty caps */
+
+	/* See ceph_inode_info->i_flushing_item. */
 	struct list_head  s_cap_flushing;     /* inodes w/ flushing caps */
+
 	unsigned long     s_renew_requested; /* last time we sent a renew req */
 	u64               s_renew_seq;
 
@@ -297,6 +304,8 @@ struct ceph_mds_request {
 
 	unsigned long r_timeout;  /* optional.  jiffies, 0 is "wait forever" */
 	unsigned long r_started;  /* start time to measure timeout against */
+	unsigned long r_start_latency;  /* start time to measure latency */
+	unsigned long r_end_latency;    /* finish time to measure latency */
 	unsigned long r_request_started; /* start time for mds request only,
 					    used to measure lease durations */
 
@@ -419,7 +428,6 @@ struct ceph_mds_client {
 
 	u64               last_cap_flush_tid;
 	struct list_head  cap_flush_list;
-	struct list_head  cap_dirty;        /* inodes with dirty caps */
 	struct list_head  cap_dirty_migrating; /* ...that are migration... */
 	int               num_cap_flushing; /* # caps we are flushing */
 	spinlock_t        cap_dirty_lock;   /* protects above items */
@@ -454,6 +462,8 @@ struct ceph_mds_client {
 	struct list_head  dentry_leases;     /* fifo list */
 	struct list_head  dentry_dir_leases; /* lru list */
 
+	struct ceph_client_metric metric;
+
 	spinlock_t		snapid_map_lock;
 	struct rb_root		snapid_map_tree;
 	struct list_head	snapid_map_lru;
@@ -497,6 +507,7 @@ extern int ceph_mdsc_do_request(struct ceph_mds_client *mdsc,
 				struct inode *dir,
 				struct ceph_mds_request *req);
 extern void ceph_mdsc_release_dir_caps(struct ceph_mds_request *req);
+extern void ceph_mdsc_release_dir_caps_no_check(struct ceph_mds_request *req);
 static inline void ceph_mdsc_get_request(struct ceph_mds_request *req)
 {
 	kref_get(&req->r_kref);

fs/ceph/metric.c

@@ -0,0 +1,148 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#include <linux/types.h>
+#include <linux/percpu_counter.h>
+#include <linux/math64.h>
+
+#include "metric.h"
+
+int ceph_metric_init(struct ceph_client_metric *m)
+{
+	int ret;
+
+	if (!m)
+		return -EINVAL;
+
+	atomic64_set(&m->total_dentries, 0);
+	ret = percpu_counter_init(&m->d_lease_hit, 0, GFP_KERNEL);
+	if (ret)
+		return ret;
+
+	ret = percpu_counter_init(&m->d_lease_mis, 0, GFP_KERNEL);
+	if (ret)
+		goto err_d_lease_mis;
+
+	ret = percpu_counter_init(&m->i_caps_hit, 0, GFP_KERNEL);
+	if (ret)
+		goto err_i_caps_hit;
+
+	ret = percpu_counter_init(&m->i_caps_mis, 0, GFP_KERNEL);
+	if (ret)
+		goto err_i_caps_mis;
+
+	spin_lock_init(&m->read_latency_lock);
+	m->read_latency_sq_sum = 0;
+	m->read_latency_min = KTIME_MAX;
+	m->read_latency_max = 0;
+	m->total_reads = 0;
+	m->read_latency_sum = 0;
+
+	spin_lock_init(&m->write_latency_lock);
+	m->write_latency_sq_sum = 0;
+	m->write_latency_min = KTIME_MAX;
+	m->write_latency_max = 0;
+	m->total_writes = 0;
+	m->write_latency_sum = 0;
+
+	spin_lock_init(&m->metadata_latency_lock);
+	m->metadata_latency_sq_sum = 0;
+	m->metadata_latency_min = KTIME_MAX;
+	m->metadata_latency_max = 0;
+	m->total_metadatas = 0;
+	m->metadata_latency_sum = 0;
+
+	return 0;
+
+err_i_caps_mis:
+	percpu_counter_destroy(&m->i_caps_hit);
+err_i_caps_hit:
+	percpu_counter_destroy(&m->d_lease_mis);
+err_d_lease_mis:
+	percpu_counter_destroy(&m->d_lease_hit);
+
+	return ret;
+}
+
+void ceph_metric_destroy(struct ceph_client_metric *m)
+{
+	if (!m)
+		return;
+
+	percpu_counter_destroy(&m->i_caps_mis);
+	percpu_counter_destroy(&m->i_caps_hit);
+	percpu_counter_destroy(&m->d_lease_mis);
+	percpu_counter_destroy(&m->d_lease_hit);
+}
+
+static inline void __update_latency(ktime_t *totalp, ktime_t *lsump,
+				    ktime_t *min, ktime_t *max,
+				    ktime_t *sq_sump, ktime_t lat)
+{
+	ktime_t total, avg, sq, lsum;
+
+	total = ++(*totalp);
+	lsum = (*lsump += lat);
+
+	if (unlikely(lat < *min))
+		*min = lat;
+	if (unlikely(lat > *max))
+		*max = lat;
+
+	if (unlikely(total == 1))
+		return;
+
+	/* the sq is (lat - old_avg) * (lat - new_avg) */
+	avg = DIV64_U64_ROUND_CLOSEST((lsum - lat), (total - 1));
+	sq = lat - avg;
+	avg = DIV64_U64_ROUND_CLOSEST(lsum, total);
+	sq = sq * (lat - avg);
+	*sq_sump += sq;
+}
+
+void ceph_update_read_latency(struct ceph_client_metric *m,
+			      ktime_t r_start, ktime_t r_end,
+			      int rc)
+{
+	ktime_t lat = ktime_sub(r_end, r_start);
+
+	if (unlikely(rc < 0 && rc != -ENOENT && rc != -ETIMEDOUT))
+		return;
+
+	spin_lock(&m->read_latency_lock);
+	__update_latency(&m->total_reads, &m->read_latency_sum,
+			 &m->read_latency_min, &m->read_latency_max,
+			 &m->read_latency_sq_sum, lat);
+	spin_unlock(&m->read_latency_lock);
+}
+
+void ceph_update_write_latency(struct ceph_client_metric *m,
+			       ktime_t r_start, ktime_t r_end,
+			       int rc)
+{
+	ktime_t lat = ktime_sub(r_end, r_start);
+
+	if (unlikely(rc && rc != -ETIMEDOUT))
+		return;
+
+	spin_lock(&m->write_latency_lock);
+	__update_latency(&m->total_writes, &m->write_latency_sum,
+			 &m->write_latency_min, &m->write_latency_max,
+			 &m->write_latency_sq_sum, lat);
+	spin_unlock(&m->write_latency_lock);
+}
+
+void ceph_update_metadata_latency(struct ceph_client_metric *m,
+				  ktime_t r_start, ktime_t r_end,
+				  int rc)
+{
+	ktime_t lat = ktime_sub(r_end, r_start);
+
+	if (unlikely(rc && rc != -ENOENT))
+		return;
+
+	spin_lock(&m->metadata_latency_lock);
+	__update_latency(&m->total_metadatas, &m->metadata_latency_sum,
+			 &m->metadata_latency_min, &m->metadata_latency_max,
+			 &m->metadata_latency_sq_sum, lat);
+	spin_unlock(&m->metadata_latency_lock);
+}

fs/ceph/metric.h

@@ -0,0 +1,62 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _FS_CEPH_MDS_METRIC_H
+#define _FS_CEPH_MDS_METRIC_H
+
+#include <linux/types.h>
+#include <linux/percpu_counter.h>
+#include <linux/ktime.h>
+
+/* This is the global metrics */
+struct ceph_client_metric {
+	atomic64_t            total_dentries;
+	struct percpu_counter d_lease_hit;
+	struct percpu_counter d_lease_mis;
+
+	struct percpu_counter i_caps_hit;
+	struct percpu_counter i_caps_mis;
+
+	spinlock_t read_latency_lock;
+	u64 total_reads;
+	ktime_t read_latency_sum;
+	ktime_t read_latency_sq_sum;
+	ktime_t read_latency_min;
+	ktime_t read_latency_max;
+
+	spinlock_t write_latency_lock;
+	u64 total_writes;
+	ktime_t write_latency_sum;
+	ktime_t write_latency_sq_sum;
+	ktime_t write_latency_min;
+	ktime_t write_latency_max;
+
+	spinlock_t metadata_latency_lock;
+	u64 total_metadatas;
+	ktime_t metadata_latency_sum;
+	ktime_t metadata_latency_sq_sum;
+	ktime_t metadata_latency_min;
+	ktime_t metadata_latency_max;
+};
+
+extern int ceph_metric_init(struct ceph_client_metric *m);
+extern void ceph_metric_destroy(struct ceph_client_metric *m);
+
+static inline void ceph_update_cap_hit(struct ceph_client_metric *m)
+{
+	percpu_counter_inc(&m->i_caps_hit);
+}
+
+static inline void ceph_update_cap_mis(struct ceph_client_metric *m)
+{
+	percpu_counter_inc(&m->i_caps_mis);
+}
+
+extern void ceph_update_read_latency(struct ceph_client_metric *m,
+				     ktime_t r_start, ktime_t r_end,
+				     int rc);
+extern void ceph_update_write_latency(struct ceph_client_metric *m,
+				      ktime_t r_start, ktime_t r_end,
+				      int rc);
+extern void ceph_update_metadata_latency(struct ceph_client_metric *m,
+				         ktime_t r_start, ktime_t r_end,
+					 int rc);
+#endif /* _FS_CEPH_MDS_METRIC_H */

fs/ceph/quota.c

@@ -264,7 +264,7 @@ restart:
 	return NULL;
 }
 
-bool ceph_quota_is_same_realm(struct inode *old, struct inode *new)
+static bool ceph_quota_is_same_realm(struct inode *old, struct inode *new)
 {
 	struct ceph_mds_client *mdsc = ceph_inode_to_client(old)->mdsc;
 	struct ceph_snap_realm *old_realm, *new_realm;
@@ -361,8 +361,6 @@ restart:
 		spin_unlock(&ci->i_ceph_lock);
 		switch (op) {
 		case QUOTA_CHECK_MAX_FILES_OP:
-			exceeded = (max && (rvalue >= max));
-			break;
 		case QUOTA_CHECK_MAX_BYTES_OP:
 			exceeded = (max && (rvalue + delta > max));
 			break;
@@ -417,7 +415,7 @@ bool ceph_quota_is_max_files_exceeded(struct inode *inode)
 
 	WARN_ON(!S_ISDIR(inode->i_mode));
 
-	return check_quota_exceeded(inode, QUOTA_CHECK_MAX_FILES_OP, 0);
+	return check_quota_exceeded(inode, QUOTA_CHECK_MAX_FILES_OP, 1);
 }
 
 /*
@@ -518,3 +516,59 @@ bool ceph_quota_update_statfs(struct ceph_fs_client *fsc, struct kstatfs *buf)
 	return is_updated;
 }
 
+/*
+ * ceph_quota_check_rename - check if a rename can be executed
+ * @mdsc:	MDS client instance
+ * @old:	inode to be copied
+ * @new:	destination inode (directory)
+ *
+ * This function verifies if a rename (e.g. moving a file or directory) can be
+ * executed.  It forces an rstat update in the @new target directory (and in the
+ * source @old as well, if it's a directory).  The actual check is done both for
+ * max_files and max_bytes.
+ *
+ * This function returns 0 if it's OK to do the rename, or, if quotas are
+ * exceeded, -EXDEV (if @old is a directory) or -EDQUOT.
+ */
+int ceph_quota_check_rename(struct ceph_mds_client *mdsc,
+			    struct inode *old, struct inode *new)
+{
+	struct ceph_inode_info *ci_old = ceph_inode(old);
+	int ret = 0;
+
+	if (ceph_quota_is_same_realm(old, new))
+		return 0;
+
+	/*
+	 * Get the latest rstat for target directory (and for source, if a
+	 * directory)
+	 */
+	ret = ceph_do_getattr(new, CEPH_STAT_RSTAT, false);
+	if (ret)
+		return ret;
+
+	if (S_ISDIR(old->i_mode)) {
+		ret = ceph_do_getattr(old, CEPH_STAT_RSTAT, false);
+		if (ret)
+			return ret;
+		ret = check_quota_exceeded(new, QUOTA_CHECK_MAX_BYTES_OP,
+					   ci_old->i_rbytes);
+		if (!ret)
+			ret = check_quota_exceeded(new,
+						   QUOTA_CHECK_MAX_FILES_OP,
+						   ci_old->i_rfiles +
+						   ci_old->i_rsubdirs);
+		if (ret)
+			ret = -EXDEV;
+	} else {
+		ret = check_quota_exceeded(new, QUOTA_CHECK_MAX_BYTES_OP,
+					   i_size_read(old));
+		if (!ret)
+			ret = check_quota_exceeded(new,
+						   QUOTA_CHECK_MAX_FILES_OP, 1);
+		if (ret)
+			ret = -EDQUOT;
+	}
+
+	return ret;
+}

fs/ceph/super.h

@@ -128,6 +128,7 @@ struct ceph_fs_client {
 	struct dentry *debugfs_congestion_kb;
 	struct dentry *debugfs_bdi;
 	struct dentry *debugfs_mdsc, *debugfs_mdsmap;
+	struct dentry *debugfs_metric;
 	struct dentry *debugfs_mds_sessions;
 #endif
 
@@ -350,7 +351,25 @@ struct ceph_inode_info {
 	struct rb_root i_caps;           /* cap list */
 	struct ceph_cap *i_auth_cap;     /* authoritative cap, if any */
 	unsigned i_dirty_caps, i_flushing_caps;     /* mask of dirtied fields */
-	struct list_head i_dirty_item, i_flushing_item;
+
+	/*
+	 * Link to the the auth cap's session's s_cap_dirty list. s_cap_dirty
+	 * is protected by the mdsc->cap_dirty_lock, but each individual item
+	 * is also protected by the inode's i_ceph_lock. Walking s_cap_dirty
+	 * requires the mdsc->cap_dirty_lock. List presence for an item can
+	 * be tested under the i_ceph_lock. Changing anything requires both.
+	 */
+	struct list_head i_dirty_item;
+
+	/*
+	 * Link to session's s_cap_flushing list. Protected in a similar
+	 * fashion to i_dirty_item, but also by the s_mutex for changes. The
+	 * s_cap_flushing list can be walked while holding either the s_mutex
+	 * or msdc->cap_dirty_lock. List presence can also be checked while
+	 * holding the i_ceph_lock for this inode.
+	 */
+	struct list_head i_flushing_item;
+
 	/* we need to track cap writeback on a per-cap-bit basis, to allow
 	 * overlapping, pipelined cap flushes to the mds.  we can probably
 	 * reduce the tid to 8 bits if we're concerned about inode size. */
@@ -644,6 +663,8 @@ static inline bool __ceph_is_any_real_caps(struct ceph_inode_info *ci)
 
 extern int __ceph_caps_issued(struct ceph_inode_info *ci, int *implemented);
 extern int __ceph_caps_issued_mask(struct ceph_inode_info *ci, int mask, int t);
+extern int __ceph_caps_issued_mask_metric(struct ceph_inode_info *ci, int mask,
+					  int t);
 extern int __ceph_caps_issued_other(struct ceph_inode_info *ci,
 				    struct ceph_cap *cap);
 
@@ -656,12 +677,12 @@ static inline int ceph_caps_issued(struct ceph_inode_info *ci)
 	return issued;
 }
 
-static inline int ceph_caps_issued_mask(struct ceph_inode_info *ci, int mask,
-					int touch)
+static inline int ceph_caps_issued_mask_metric(struct ceph_inode_info *ci,
+					       int mask, int touch)
 {
 	int r;
 	spin_lock(&ci->i_ceph_lock);
-	r = __ceph_caps_issued_mask(ci, mask, touch);
+	r = __ceph_caps_issued_mask_metric(ci, mask, touch);
 	spin_unlock(&ci->i_ceph_lock);
 	return r;
 }
@@ -1074,6 +1095,8 @@ extern void ceph_take_cap_refs(struct ceph_inode_info *ci, int caps,
 				bool snap_rwsem_locked);
 extern void ceph_get_cap_refs(struct ceph_inode_info *ci, int caps);
 extern void ceph_put_cap_refs(struct ceph_inode_info *ci, int had);
+extern void ceph_put_cap_refs_no_check_caps(struct ceph_inode_info *ci,
+					    int had);
 extern void ceph_put_wrbuffer_cap_refs(struct ceph_inode_info *ci, int nr,
 				       struct ceph_snap_context *snapc);
 extern void ceph_flush_snaps(struct ceph_inode_info *ci,
@@ -1189,13 +1212,14 @@ extern void ceph_handle_quota(struct ceph_mds_client *mdsc,
 			      struct ceph_mds_session *session,
 			      struct ceph_msg *msg);
 extern bool ceph_quota_is_max_files_exceeded(struct inode *inode);
-extern bool ceph_quota_is_same_realm(struct inode *old, struct inode *new);
 extern bool ceph_quota_is_max_bytes_exceeded(struct inode *inode,
 					     loff_t newlen);
 extern bool ceph_quota_is_max_bytes_approaching(struct inode *inode,
 						loff_t newlen);
 extern bool ceph_quota_update_statfs(struct ceph_fs_client *fsc,
 				     struct kstatfs *buf);
+extern int ceph_quota_check_rename(struct ceph_mds_client *mdsc,
+				   struct inode *old, struct inode *new);
 extern void ceph_cleanup_quotarealms_inodes(struct ceph_mds_client *mdsc);
 
 #endif /* _FS_CEPH_SUPER_H */

fs/ceph/xattr.c

@@ -856,7 +856,7 @@ ssize_t __ceph_getxattr(struct inode *inode, const char *name, void *value,
 
 	if (ci->i_xattrs.version == 0 ||
 	    !((req_mask & CEPH_CAP_XATTR_SHARED) ||
-	      __ceph_caps_issued_mask(ci, CEPH_CAP_XATTR_SHARED, 1))) {
+	      __ceph_caps_issued_mask_metric(ci, CEPH_CAP_XATTR_SHARED, 1))) {
 		spin_unlock(&ci->i_ceph_lock);
 
 		/* security module gets xattr while filling trace */
@@ -914,7 +914,7 @@ ssize_t ceph_listxattr(struct dentry *dentry, char *names, size_t size)
 	     ci->i_xattrs.version, ci->i_xattrs.index_version);
 
 	if (ci->i_xattrs.version == 0 ||
-	    !__ceph_caps_issued_mask(ci, CEPH_CAP_XATTR_SHARED, 1)) {
+	    !__ceph_caps_issued_mask_metric(ci, CEPH_CAP_XATTR_SHARED, 1)) {
 		spin_unlock(&ci->i_ceph_lock);
 		err = ceph_do_getattr(inode, CEPH_STAT_CAP_XATTR, true);
 		if (err)

include/linux/ceph/libceph.h

@@ -53,6 +53,8 @@ struct ceph_options {
 	unsigned long osd_keepalive_timeout;	/* jiffies */
 	unsigned long osd_request_timeout;	/* jiffies */
 
+	u32 osd_req_flags;  /* CEPH_OSD_FLAG_*, applied to each OSD request */
+
 	/*
 	 * any type that can't be simply compared or doesn't need
 	 * to be compared should go beyond this point,
@@ -64,6 +66,7 @@ struct ceph_options {
 	int num_mon;
 	char *name;
 	struct ceph_crypto_key *key;
+	struct rb_root crush_locs;
 };
 
 /*
@@ -188,7 +191,7 @@ static inline int calc_pages_for(u64 off, u64 len)
 #define RB_CMP3WAY(a, b) ((a) < (b) ? -1 : (a) > (b))
 
 #define DEFINE_RB_INSDEL_FUNCS2(name, type, keyfld, cmpexp, keyexp, nodefld) \
-static void insert_##name(struct rb_root *root, type *t)		\
+static bool __insert_##name(struct rb_root *root, type *t)		\
 {									\
 	struct rb_node **n = &root->rb_node;				\
 	struct rb_node *parent = NULL;					\
@@ -206,11 +209,17 @@ static void insert_##name(struct rb_root *root, type *t)		\
 		else if (cmp > 0)					\
 			n = &(*n)->rb_right;				\
 		else							\
-			BUG();						\
+			return false;					\
 	}								\
 									\
 	rb_link_node(&t->nodefld, parent, n);				\
 	rb_insert_color(&t->nodefld, root);				\
+	return true;							\
+}									\
+static void __maybe_unused insert_##name(struct rb_root *root, type *t)	\
+{									\
+	if (!__insert_##name(root, t))					\
+		BUG();							\
 }									\
 static void erase_##name(struct rb_root *root, type *t)			\
 {									\

include/linux/ceph/mon_client.h

@@ -19,7 +19,7 @@ struct ceph_monmap {
 	struct ceph_fsid fsid;
 	u32 epoch;
 	u32 num_mon;
-	struct ceph_entity_inst mon_inst[0];
+	struct ceph_entity_inst mon_inst[];
 };
 
 struct ceph_mon_client;