Initial commit; kernel source import

fs/ceph/Kconfig

@@ -0,0 +1,18 @@
+config CEPH_FS
+	tristate "Ceph distributed file system"
+	depends on INET
+	select CEPH_LIB
+	select LIBCRC32C
+	select CRYPTO_AES
+	select CRYPTO
+	default n
+	help
+	  Choose Y or M here to include support for mounting the
+	  experimental Ceph distributed file system.  Ceph is an extremely
+	  scalable file system designed to provide high performance,
+	  reliable access to petabytes of storage.
+
+	  More information at http://ceph.newdream.net/.
+
+	  If unsure, say N.
+

fs/ceph/Makefile

@@ -0,0 +1,11 @@
+#
+# Makefile for CEPH filesystem.
+#
+
+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 \
+	mds_client.o mdsmap.o strings.o ceph_frag.o \
+	debugfs.o
+

fs/ceph/ceph_frag.c

@@ -0,0 +1,22 @@
+/*
+ * Ceph 'frag' type
+ */
+#include <linux/module.h>
+#include <linux/ceph/types.h>
+
+int ceph_frag_compare(__u32 a, __u32 b)
+{
+	unsigned va = ceph_frag_value(a);
+	unsigned vb = ceph_frag_value(b);
+	if (va < vb)
+		return -1;
+	if (va > vb)
+		return 1;
+	va = ceph_frag_bits(a);
+	vb = ceph_frag_bits(b);
+	if (va < vb)
+		return -1;
+	if (va > vb)
+		return 1;
+	return 0;
+}

fs/ceph/debugfs.c

@@ -0,0 +1,274 @@
+#include <linux/ceph/ceph_debug.h>
+
+#include <linux/device.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/ctype.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+
+#include <linux/ceph/libceph.h>
+#include <linux/ceph/mon_client.h>
+#include <linux/ceph/auth.h>
+#include <linux/ceph/debugfs.h>
+
+#include "super.h"
+
+#ifdef CONFIG_DEBUG_FS
+
+#include "mds_client.h"
+
+static int mdsmap_show(struct seq_file *s, void *p)
+{
+	int i;
+	struct ceph_fs_client *fsc = s->private;
+
+	if (fsc->mdsc == NULL || fsc->mdsc->mdsmap == NULL)
+		return 0;
+	seq_printf(s, "epoch %d\n", fsc->mdsc->mdsmap->m_epoch);
+	seq_printf(s, "root %d\n", fsc->mdsc->mdsmap->m_root);
+	seq_printf(s, "session_timeout %d\n",
+		       fsc->mdsc->mdsmap->m_session_timeout);
+	seq_printf(s, "session_autoclose %d\n",
+		       fsc->mdsc->mdsmap->m_session_autoclose);
+	for (i = 0; i < fsc->mdsc->mdsmap->m_max_mds; i++) {
+		struct ceph_entity_addr *addr =
+			&fsc->mdsc->mdsmap->m_info[i].addr;
+		int state = fsc->mdsc->mdsmap->m_info[i].state;
+
+		seq_printf(s, "\tmds%d\t%s\t(%s)\n", i,
+			       ceph_pr_addr(&addr->in_addr),
+			       ceph_mds_state_name(state));
+	}
+	return 0;
+}
+
+/*
+ * mdsc debugfs
+ */
+static int mdsc_show(struct seq_file *s, void *p)
+{
+	struct ceph_fs_client *fsc = s->private;
+	struct ceph_mds_client *mdsc = fsc->mdsc;
+	struct ceph_mds_request *req;
+	struct rb_node *rp;
+	int pathlen;
+	u64 pathbase;
+	char *path;
+
+	mutex_lock(&mdsc->mutex);
+	for (rp = rb_first(&mdsc->request_tree); rp; rp = rb_next(rp)) {
+		req = rb_entry(rp, struct ceph_mds_request, r_node);
+
+		if (req->r_request && req->r_session)
+			seq_printf(s, "%lld\tmds%d\t", req->r_tid,
+				   req->r_session->s_mds);
+		else if (!req->r_request)
+			seq_printf(s, "%lld\t(no request)\t", req->r_tid);
+		else
+			seq_printf(s, "%lld\t(no session)\t", req->r_tid);
+
+		seq_printf(s, "%s", ceph_mds_op_name(req->r_op));
+
+		if (req->r_got_unsafe)
+			seq_printf(s, "\t(unsafe)");
+		else
+			seq_printf(s, "\t");
+
+		if (req->r_inode) {
+			seq_printf(s, " #%llx", ceph_ino(req->r_inode));
+		} else if (req->r_dentry) {
+			path = ceph_mdsc_build_path(req->r_dentry, &pathlen,
+						    &pathbase, 0);
+			if (IS_ERR(path))
+				path = NULL;
+			spin_lock(&req->r_dentry->d_lock);
+			seq_printf(s, " #%llx/%.*s (%s)",
+				   ceph_ino(req->r_dentry->d_parent->d_inode),
+				   req->r_dentry->d_name.len,
+				   req->r_dentry->d_name.name,
+				   path ? path : "");
+			spin_unlock(&req->r_dentry->d_lock);
+			kfree(path);
+		} else if (req->r_path1) {
+			seq_printf(s, " #%llx/%s", req->r_ino1.ino,
+				   req->r_path1);
+		}
+
+		if (req->r_old_dentry) {
+			path = ceph_mdsc_build_path(req->r_old_dentry, &pathlen,
+						    &pathbase, 0);
+			if (IS_ERR(path))
+				path = NULL;
+			spin_lock(&req->r_old_dentry->d_lock);
+			seq_printf(s, " #%llx/%.*s (%s)",
+			   ceph_ino(req->r_old_dentry_dir),
+				   req->r_old_dentry->d_name.len,
+				   req->r_old_dentry->d_name.name,
+				   path ? path : "");
+			spin_unlock(&req->r_old_dentry->d_lock);
+			kfree(path);
+		} else if (req->r_path2) {
+			if (req->r_ino2.ino)
+				seq_printf(s, " #%llx/%s", req->r_ino2.ino,
+					   req->r_path2);
+			else
+				seq_printf(s, " %s", req->r_path2);
+		}
+
+		seq_printf(s, "\n");
+	}
+	mutex_unlock(&mdsc->mutex);
+
+	return 0;
+}
+
+static int caps_show(struct seq_file *s, void *p)
+{
+	struct ceph_fs_client *fsc = s->private;
+	int total, avail, used, reserved, min;
+
+	ceph_reservation_status(fsc, &total, &avail, &used, &reserved, &min);
+	seq_printf(s, "total\t\t%d\n"
+		   "avail\t\t%d\n"
+		   "used\t\t%d\n"
+		   "reserved\t%d\n"
+		   "min\t%d\n",
+		   total, avail, used, reserved, min);
+	return 0;
+}
+
+static int dentry_lru_show(struct seq_file *s, void *ptr)
+{
+	struct ceph_fs_client *fsc = s->private;
+	struct ceph_mds_client *mdsc = fsc->mdsc;
+	struct ceph_dentry_info *di;
+
+	spin_lock(&mdsc->dentry_lru_lock);
+	list_for_each_entry(di, &mdsc->dentry_lru, lru) {
+		struct dentry *dentry = di->dentry;
+		seq_printf(s, "%p %p\t%.*s\n",
+			   di, dentry, dentry->d_name.len, dentry->d_name.name);
+	}
+	spin_unlock(&mdsc->dentry_lru_lock);
+
+	return 0;
+}
+
+CEPH_DEFINE_SHOW_FUNC(mdsmap_show)
+CEPH_DEFINE_SHOW_FUNC(mdsc_show)
+CEPH_DEFINE_SHOW_FUNC(caps_show)
+CEPH_DEFINE_SHOW_FUNC(dentry_lru_show)
+
+
+/*
+ * debugfs
+ */
+static int congestion_kb_set(void *data, u64 val)
+{
+	struct ceph_fs_client *fsc = (struct ceph_fs_client *)data;
+
+	fsc->mount_options->congestion_kb = (int)val;
+	return 0;
+}
+
+static int congestion_kb_get(void *data, u64 *val)
+{
+	struct ceph_fs_client *fsc = (struct ceph_fs_client *)data;
+
+	*val = (u64)fsc->mount_options->congestion_kb;
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(congestion_kb_fops, congestion_kb_get,
+			congestion_kb_set, "%llu\n");
+
+
+void ceph_fs_debugfs_cleanup(struct ceph_fs_client *fsc)
+{
+	dout("ceph_fs_debugfs_cleanup\n");
+	debugfs_remove(fsc->debugfs_bdi);
+	debugfs_remove(fsc->debugfs_congestion_kb);
+	debugfs_remove(fsc->debugfs_mdsmap);
+	debugfs_remove(fsc->debugfs_caps);
+	debugfs_remove(fsc->debugfs_mdsc);
+	debugfs_remove(fsc->debugfs_dentry_lru);
+}
+
+int ceph_fs_debugfs_init(struct ceph_fs_client *fsc)
+{
+	char name[100];
+	int err = -ENOMEM;
+
+	dout("ceph_fs_debugfs_init\n");
+	BUG_ON(!fsc->client->debugfs_dir);
+	fsc->debugfs_congestion_kb =
+		debugfs_create_file("writeback_congestion_kb",
+				    0600,
+				    fsc->client->debugfs_dir,
+				    fsc,
+				    &congestion_kb_fops);
+	if (!fsc->debugfs_congestion_kb)
+		goto out;
+
+	snprintf(name, sizeof(name), "../../bdi/%s",
+		 dev_name(fsc->backing_dev_info.dev));
+	fsc->debugfs_bdi =
+		debugfs_create_symlink("bdi",
+				       fsc->client->debugfs_dir,
+				       name);
+	if (!fsc->debugfs_bdi)
+		goto out;
+
+	fsc->debugfs_mdsmap = debugfs_create_file("mdsmap",
+					0600,
+					fsc->client->debugfs_dir,
+					fsc,
+					&mdsmap_show_fops);
+	if (!fsc->debugfs_mdsmap)
+		goto out;
+
+	fsc->debugfs_mdsc = debugfs_create_file("mdsc",
+						0600,
+						fsc->client->debugfs_dir,
+						fsc,
+						&mdsc_show_fops);
+	if (!fsc->debugfs_mdsc)
+		goto out;
+
+	fsc->debugfs_caps = debugfs_create_file("caps",
+						   0400,
+						   fsc->client->debugfs_dir,
+						   fsc,
+						   &caps_show_fops);
+	if (!fsc->debugfs_caps)
+		goto out;
+
+	fsc->debugfs_dentry_lru = debugfs_create_file("dentry_lru",
+					0600,
+					fsc->client->debugfs_dir,
+					fsc,
+					&dentry_lru_show_fops);
+	if (!fsc->debugfs_dentry_lru)
+		goto out;
+
+	return 0;
+
+out:
+	ceph_fs_debugfs_cleanup(fsc);
+	return err;
+}
+
+
+#else  /* CONFIG_DEBUG_FS */
+
+int ceph_fs_debugfs_init(struct ceph_fs_client *fsc)
+{
+	return 0;
+}
+
+void ceph_fs_debugfs_cleanup(struct ceph_fs_client *fsc)
+{
+}
+
+#endif  /* CONFIG_DEBUG_FS */

fs/ceph/export.c

@@ -0,0 +1,277 @@
+#include <linux/ceph/ceph_debug.h>
+
+#include <linux/exportfs.h>
+#include <linux/slab.h>
+#include <asm/unaligned.h>
+
+#include "super.h"
+#include "mds_client.h"
+
+/*
+ * NFS export support
+ *
+ * NFS re-export of a ceph mount is, at present, only semireliable.
+ * The basic issue is that the Ceph architectures doesn't lend itself
+ * well to generating filehandles that will remain valid forever.
+ *
+ * So, we do our best.  If you're lucky, your inode will be in the
+ * client's cache.  If it's not, and you have a connectable fh, then
+ * the MDS server may be able to find it for you.  Otherwise, you get
+ * ESTALE.
+ *
+ * There are ways to this more reliable, but in the non-connectable fh
+ * case, we won't every work perfectly, and in the connectable case,
+ * some changes are needed on the MDS side to work better.
+ */
+
+/*
+ * Basic fh
+ */
+struct ceph_nfs_fh {
+	u64 ino;
+} __attribute__ ((packed));
+
+/*
+ * Larger 'connectable' fh that includes parent ino and name hash.
+ * Use this whenever possible, as it works more reliably.
+ */
+struct ceph_nfs_confh {
+	u64 ino, parent_ino;
+	u32 parent_name_hash;
+} __attribute__ ((packed));
+
+/*
+ * The presence of @parent_inode here tells us whether NFS wants a
+ * connectable file handle.  However, we want to make a connectionable
+ * file handle unconditionally so that the MDS gets as much of a hint
+ * as possible.  That means we only use @parent_dentry to indicate
+ * whether nfsd wants a connectable fh, and whether we should indicate
+ * failure from a too-small @max_len.
+ */
+static int ceph_encode_fh(struct inode *inode, u32 *rawfh, int *max_len,
+			  struct inode *parent_inode)
+{
+	int type;
+	struct ceph_nfs_fh *fh = (void *)rawfh;
+	struct ceph_nfs_confh *cfh = (void *)rawfh;
+	int connected_handle_length = sizeof(*cfh)/4;
+	int handle_length = sizeof(*fh)/4;
+	struct dentry *dentry;
+	struct dentry *parent;
+
+	/* don't re-export snaps */
+	if (ceph_snap(inode) != CEPH_NOSNAP)
+		return -EINVAL;
+
+	dentry = d_find_alias(inode);
+
+	/* if we found an alias, generate a connectable fh */
+	if (*max_len >= connected_handle_length && dentry) {
+		dout("encode_fh %p connectable\n", dentry);
+		spin_lock(&dentry->d_lock);
+		parent = dentry->d_parent;
+		cfh->ino = ceph_ino(inode);
+		cfh->parent_ino = ceph_ino(parent->d_inode);
+		cfh->parent_name_hash = ceph_dentry_hash(parent->d_inode,
+							 dentry);
+		*max_len = connected_handle_length;
+		type = 2;
+		spin_unlock(&dentry->d_lock);
+	} else if (*max_len >= handle_length) {
+		if (parent_inode) {
+			/* nfsd wants connectable */
+			*max_len = connected_handle_length;
+			type = FILEID_INVALID;
+		} else {
+			dout("encode_fh %p\n", dentry);
+			fh->ino = ceph_ino(inode);
+			*max_len = handle_length;
+			type = 1;
+		}
+	} else {
+		*max_len = handle_length;
+		type = FILEID_INVALID;
+	}
+	if (dentry)
+		dput(dentry);
+	return type;
+}
+
+/*
+ * convert regular fh to dentry
+ *
+ * FIXME: we should try harder by querying the mds for the ino.
+ */
+static struct dentry *__fh_to_dentry(struct super_block *sb,
+				     struct ceph_nfs_fh *fh, int fh_len)
+{
+	struct ceph_mds_client *mdsc = ceph_sb_to_client(sb)->mdsc;
+	struct inode *inode;
+	struct dentry *dentry;
+	struct ceph_vino vino;
+	int err;
+
+	if (fh_len < sizeof(*fh) / 4)
+		return ERR_PTR(-ESTALE);
+
+	dout("__fh_to_dentry %llx\n", fh->ino);
+	vino.ino = fh->ino;
+	vino.snap = CEPH_NOSNAP;
+	inode = ceph_find_inode(sb, vino);
+	if (!inode) {
+		struct ceph_mds_request *req;
+
+		req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_LOOKUPINO,
+					       USE_ANY_MDS);
+		if (IS_ERR(req))
+			return ERR_CAST(req);
+
+		req->r_ino1 = vino;
+		req->r_num_caps = 1;
+		err = ceph_mdsc_do_request(mdsc, NULL, req);
+		inode = req->r_target_inode;
+		if (inode)
+			ihold(inode);
+		ceph_mdsc_put_request(req);
+		if (!inode)
+			return ERR_PTR(-ESTALE);
+	}
+
+	dentry = d_obtain_alias(inode);
+	if (IS_ERR(dentry)) {
+		pr_err("fh_to_dentry %llx -- inode %p but ENOMEM\n",
+		       fh->ino, inode);
+		iput(inode);
+		return dentry;
+	}
+	err = ceph_init_dentry(dentry);
+	if (err < 0) {
+		iput(inode);
+		return ERR_PTR(err);
+	}
+	dout("__fh_to_dentry %llx %p dentry %p\n", fh->ino, inode, dentry);
+	return dentry;
+}
+
+/*
+ * convert connectable fh to dentry
+ */
+static struct dentry *__cfh_to_dentry(struct super_block *sb,
+				      struct ceph_nfs_confh *cfh, int fh_len)
+{
+	struct ceph_mds_client *mdsc = ceph_sb_to_client(sb)->mdsc;
+	struct inode *inode;
+	struct dentry *dentry;
+	struct ceph_vino vino;
+	int err;
+
+	if (fh_len < sizeof(*cfh) / 4)
+		return ERR_PTR(-ESTALE);
+
+	dout("__cfh_to_dentry %llx (%llx/%x)\n",
+	     cfh->ino, cfh->parent_ino, cfh->parent_name_hash);
+
+	vino.ino = cfh->ino;
+	vino.snap = CEPH_NOSNAP;
+	inode = ceph_find_inode(sb, vino);
+	if (!inode) {
+		struct ceph_mds_request *req;
+
+		req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_LOOKUPHASH,
+					       USE_ANY_MDS);
+		if (IS_ERR(req))
+			return ERR_CAST(req);
+
+		req->r_ino1 = vino;
+		req->r_ino2.ino = cfh->parent_ino;
+		req->r_ino2.snap = CEPH_NOSNAP;
+		req->r_path2 = kmalloc(16, GFP_NOFS);
+		snprintf(req->r_path2, 16, "%d", cfh->parent_name_hash);
+		req->r_num_caps = 1;
+		err = ceph_mdsc_do_request(mdsc, NULL, req);
+		inode = req->r_target_inode;
+		if (inode)
+			ihold(inode);
+		ceph_mdsc_put_request(req);
+		if (!inode)
+			return ERR_PTR(err ? err : -ESTALE);
+	}
+
+	dentry = d_obtain_alias(inode);
+	if (IS_ERR(dentry)) {
+		pr_err("cfh_to_dentry %llx -- inode %p but ENOMEM\n",
+		       cfh->ino, inode);
+		iput(inode);
+		return dentry;
+	}
+	err = ceph_init_dentry(dentry);
+	if (err < 0) {
+		iput(inode);
+		return ERR_PTR(err);
+	}
+	dout("__cfh_to_dentry %llx %p dentry %p\n", cfh->ino, inode, dentry);
+	return dentry;
+}
+
+static struct dentry *ceph_fh_to_dentry(struct super_block *sb, struct fid *fid,
+					int fh_len, int fh_type)
+{
+	if (fh_type == 1)
+		return __fh_to_dentry(sb, (struct ceph_nfs_fh *)fid->raw,
+								fh_len);
+	else
+		return __cfh_to_dentry(sb, (struct ceph_nfs_confh *)fid->raw,
+								fh_len);
+}
+
+/*
+ * get parent, if possible.
+ *
+ * FIXME: we could do better by querying the mds to discover the
+ * parent.
+ */
+static struct dentry *ceph_fh_to_parent(struct super_block *sb,
+					 struct fid *fid,
+					int fh_len, int fh_type)
+{
+	struct ceph_nfs_confh *cfh = (void *)fid->raw;
+	struct ceph_vino vino;
+	struct inode *inode;
+	struct dentry *dentry;
+	int err;
+
+	if (fh_type == 1)
+		return ERR_PTR(-ESTALE);
+	if (fh_len < sizeof(*cfh) / 4)
+		return ERR_PTR(-ESTALE);
+
+	pr_debug("fh_to_parent %llx/%d\n", cfh->parent_ino,
+		 cfh->parent_name_hash);
+
+	vino.ino = cfh->ino;
+	vino.snap = CEPH_NOSNAP;
+	inode = ceph_find_inode(sb, vino);
+	if (!inode)
+		return ERR_PTR(-ESTALE);
+
+	dentry = d_obtain_alias(inode);
+	if (IS_ERR(dentry)) {
+		pr_err("fh_to_parent %llx -- inode %p but ENOMEM\n",
+		       cfh->ino, inode);
+		iput(inode);
+		return dentry;
+	}
+	err = ceph_init_dentry(dentry);
+	if (err < 0) {
+		iput(inode);
+		return ERR_PTR(err);
+	}
+	dout("fh_to_parent %llx %p dentry %p\n", cfh->ino, inode, dentry);
+	return dentry;
+}
+
+const struct export_operations ceph_export_ops = {
+	.encode_fh = ceph_encode_fh,
+	.fh_to_dentry = ceph_fh_to_dentry,
+	.fh_to_parent = ceph_fh_to_parent,
+};

fs/ceph/file.c

@@ -0,0 +1,902 @@
+#include <linux/ceph/ceph_debug.h>
+
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/file.h>
+#include <linux/mount.h>
+#include <linux/namei.h>
+#include <linux/writeback.h>
+#include <linux/aio.h>
+
+#include "super.h"
+#include "mds_client.h"
+
+/*
+ * Ceph file operations
+ *
+ * Implement basic open/close functionality, and implement
+ * read/write.
+ *
+ * We implement three modes of file I/O:
+ *  - buffered uses the generic_file_aio_{read,write} helpers
+ *
+ *  - synchronous is used when there is multi-client read/write
+ *    sharing, avoids the page cache, and synchronously waits for an
+ *    ack from the OSD.
+ *
+ *  - direct io takes the variant of the sync path that references
+ *    user pages directly.
+ *
+ * fsync() flushes and waits on dirty pages, but just queues metadata
+ * for writeback: since the MDS can recover size and mtime there is no
+ * need to wait for MDS acknowledgement.
+ */
+
+
+/*
+ * Prepare an open request.  Preallocate ceph_cap to avoid an
+ * inopportune ENOMEM later.
+ */
+static struct ceph_mds_request *
+prepare_open_request(struct super_block *sb, int flags, int create_mode)
+{
+	struct ceph_fs_client *fsc = ceph_sb_to_client(sb);
+	struct ceph_mds_client *mdsc = fsc->mdsc;
+	struct ceph_mds_request *req;
+	int want_auth = USE_ANY_MDS;
+	int op = (flags & O_CREAT) ? CEPH_MDS_OP_CREATE : CEPH_MDS_OP_OPEN;
+
+	if (flags & (O_WRONLY|O_RDWR|O_CREAT|O_TRUNC))
+		want_auth = USE_AUTH_MDS;
+
+	req = ceph_mdsc_create_request(mdsc, op, want_auth);
+	if (IS_ERR(req))
+		goto out;
+	req->r_fmode = ceph_flags_to_mode(flags);
+	req->r_args.open.flags = cpu_to_le32(flags);
+	req->r_args.open.mode = cpu_to_le32(create_mode);
+out:
+	return req;
+}
+
+/*
+ * initialize private struct file data.
+ * if we fail, clean up by dropping fmode reference on the ceph_inode
+ */
+static int ceph_init_file(struct inode *inode, struct file *file, int fmode)
+{
+	struct ceph_file_info *cf;
+	int ret = 0;
+
+	switch (inode->i_mode & S_IFMT) {
+	case S_IFREG:
+	case S_IFDIR:
+		dout("init_file %p %p 0%o (regular)\n", inode, file,
+		     inode->i_mode);
+		cf = kmem_cache_alloc(ceph_file_cachep, GFP_NOFS | __GFP_ZERO);
+		if (cf == NULL) {
+			ceph_put_fmode(ceph_inode(inode), fmode); /* clean up */
+			return -ENOMEM;
+		}
+		cf->fmode = fmode;
+		cf->next_offset = 2;
+		file->private_data = cf;
+		BUG_ON(inode->i_fop->release != ceph_release);
+		break;
+
+	case S_IFLNK:
+		dout("init_file %p %p 0%o (symlink)\n", inode, file,
+		     inode->i_mode);
+		ceph_put_fmode(ceph_inode(inode), fmode); /* clean up */
+		break;
+
+	default:
+		dout("init_file %p %p 0%o (special)\n", inode, file,
+		     inode->i_mode);
+		/*
+		 * we need to drop the open ref now, since we don't
+		 * have .release set to ceph_release.
+		 */
+		ceph_put_fmode(ceph_inode(inode), fmode); /* clean up */
+		BUG_ON(inode->i_fop->release == ceph_release);
+
+		/* call the proper open fop */
+		ret = inode->i_fop->open(inode, file);
+	}
+	return ret;
+}
+
+/*
+ * If we already have the requisite capabilities, we can satisfy
+ * the open request locally (no need to request new caps from the
+ * MDS).  We do, however, need to inform the MDS (asynchronously)
+ * if our wanted caps set expands.
+ */
+int ceph_open(struct inode *inode, struct file *file)
+{
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct ceph_fs_client *fsc = ceph_sb_to_client(inode->i_sb);
+	struct ceph_mds_client *mdsc = fsc->mdsc;
+	struct ceph_mds_request *req;
+	struct ceph_file_info *cf = file->private_data;
+	struct inode *parent_inode = NULL;
+	int err;
+	int flags, fmode, wanted;
+
+	if (cf) {
+		dout("open file %p is already opened\n", file);
+		return 0;
+	}
+
+	/* filter out O_CREAT|O_EXCL; vfs did that already.  yuck. */
+	flags = file->f_flags & ~(O_CREAT|O_EXCL);
+	if (S_ISDIR(inode->i_mode))
+		flags = O_DIRECTORY;  /* mds likes to know */
+
+	dout("open inode %p ino %llx.%llx file %p flags %d (%d)\n", inode,
+	     ceph_vinop(inode), file, flags, file->f_flags);
+	fmode = ceph_flags_to_mode(flags);
+	wanted = ceph_caps_for_mode(fmode);
+
+	/* snapped files are read-only */
+	if (ceph_snap(inode) != CEPH_NOSNAP && (file->f_mode & FMODE_WRITE))
+		return -EROFS;
+
+	/* trivially open snapdir */
+	if (ceph_snap(inode) == CEPH_SNAPDIR) {
+		spin_lock(&ci->i_ceph_lock);
+		__ceph_get_fmode(ci, fmode);
+		spin_unlock(&ci->i_ceph_lock);
+		return ceph_init_file(inode, file, fmode);
+	}
+
+	/*
+	 * No need to block if we have caps on the auth MDS (for
+	 * write) or any MDS (for read).  Update wanted set
+	 * asynchronously.
+	 */
+	spin_lock(&ci->i_ceph_lock);
+	if (__ceph_is_any_real_caps(ci) &&
+	    (((fmode & CEPH_FILE_MODE_WR) == 0) || ci->i_auth_cap)) {
+		int mds_wanted = __ceph_caps_mds_wanted(ci);
+		int issued = __ceph_caps_issued(ci, NULL);
+
+		dout("open %p fmode %d want %s issued %s using existing\n",
+		     inode, fmode, ceph_cap_string(wanted),
+		     ceph_cap_string(issued));
+		__ceph_get_fmode(ci, fmode);
+		spin_unlock(&ci->i_ceph_lock);
+
+		/* adjust wanted? */
+		if ((issued & wanted) != wanted &&
+		    (mds_wanted & wanted) != wanted &&
+		    ceph_snap(inode) != CEPH_SNAPDIR)
+			ceph_check_caps(ci, 0, NULL);
+
+		return ceph_init_file(inode, file, fmode);
+	} else if (ceph_snap(inode) != CEPH_NOSNAP &&
+		   (ci->i_snap_caps & wanted) == wanted) {
+		__ceph_get_fmode(ci, fmode);
+		spin_unlock(&ci->i_ceph_lock);
+		return ceph_init_file(inode, file, fmode);
+	}
+	spin_unlock(&ci->i_ceph_lock);
+
+	dout("open fmode %d wants %s\n", fmode, ceph_cap_string(wanted));
+	req = prepare_open_request(inode->i_sb, flags, 0);
+	if (IS_ERR(req)) {
+		err = PTR_ERR(req);
+		goto out;
+	}
+	req->r_inode = inode;
+	ihold(inode);
+	req->r_num_caps = 1;
+	if (flags & (O_CREAT|O_TRUNC))
+		parent_inode = ceph_get_dentry_parent_inode(file->f_dentry);
+	err = ceph_mdsc_do_request(mdsc, parent_inode, req);
+	iput(parent_inode);
+	if (!err)
+		err = ceph_init_file(inode, file, req->r_fmode);
+	ceph_mdsc_put_request(req);
+	dout("open result=%d on %llx.%llx\n", err, ceph_vinop(inode));
+out:
+	return err;
+}
+
+
+/*
+ * Do a lookup + open with a single request.  If we get a non-existent
+ * file or symlink, return 1 so the VFS can retry.
+ */
+int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
+		     struct file *file, unsigned flags, umode_t mode,
+		     int *opened)
+{
+	struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb);
+	struct ceph_mds_client *mdsc = fsc->mdsc;
+	struct ceph_mds_request *req;
+	struct dentry *dn;
+	int err;
+
+	dout("atomic_open %p dentry %p '%.*s' %s flags %d mode 0%o\n",
+	     dir, dentry, dentry->d_name.len, dentry->d_name.name,
+	     d_unhashed(dentry) ? "unhashed" : "hashed", flags, mode);
+
+	if (dentry->d_name.len > NAME_MAX)
+		return -ENAMETOOLONG;
+
+	err = ceph_init_dentry(dentry);
+	if (err < 0)
+		return err;
+
+	/* do the open */
+	req = prepare_open_request(dir->i_sb, flags, mode);
+	if (IS_ERR(req))
+		return PTR_ERR(req);
+	req->r_dentry = dget(dentry);
+	req->r_num_caps = 2;
+	if (flags & O_CREAT) {
+		req->r_dentry_drop = CEPH_CAP_FILE_SHARED;
+		req->r_dentry_unless = CEPH_CAP_FILE_EXCL;
+	}
+	req->r_locked_dir = dir;           /* caller holds dir->i_mutex */
+	err = ceph_mdsc_do_request(mdsc,
+				   (flags & (O_CREAT|O_TRUNC)) ? dir : NULL,
+				   req);
+	if (err)
+		goto out_err;
+
+	err = ceph_handle_snapdir(req, dentry, err);
+	if (err == 0 && (flags & O_CREAT) && !req->r_reply_info.head->is_dentry)
+		err = ceph_handle_notrace_create(dir, dentry);
+
+	if (d_unhashed(dentry)) {
+		dn = ceph_finish_lookup(req, dentry, err);
+		if (IS_ERR(dn))
+			err = PTR_ERR(dn);
+	} else {
+		/* we were given a hashed negative dentry */
+		dn = NULL;
+	}
+	if (err)
+		goto out_err;
+	if (dn || dentry->d_inode == NULL || S_ISLNK(dentry->d_inode->i_mode)) {
+		/* make vfs retry on splice, ENOENT, or symlink */
+		dout("atomic_open finish_no_open on dn %p\n", dn);
+		err = finish_no_open(file, dn);
+	} else {
+		dout("atomic_open finish_open on dn %p\n", dn);
+		if (req->r_op == CEPH_MDS_OP_CREATE && req->r_reply_info.has_create_ino) {
+			*opened |= FILE_CREATED;
+		}
+		err = finish_open(file, dentry, ceph_open, opened);
+	}
+
+out_err:
+	ceph_mdsc_put_request(req);
+	dout("atomic_open result=%d\n", err);
+	return err;
+}
+
+int ceph_release(struct inode *inode, struct file *file)
+{
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct ceph_file_info *cf = file->private_data;
+
+	dout("release inode %p file %p\n", inode, file);
+	ceph_put_fmode(ci, cf->fmode);
+	if (cf->last_readdir)
+		ceph_mdsc_put_request(cf->last_readdir);
+	kfree(cf->last_name);
+	kfree(cf->dir_info);
+	dput(cf->dentry);
+	kmem_cache_free(ceph_file_cachep, cf);
+
+	/* wake up anyone waiting for caps on this inode */
+	wake_up_all(&ci->i_cap_wq);
+	return 0;
+}
+
+/*
+ * Read a range of bytes striped over one or more objects.  Iterate over
+ * objects we stripe over.  (That's not atomic, but good enough for now.)
+ *
+ * If we get a short result from the OSD, check against i_size; we need to
+ * only return a short read to the caller if we hit EOF.
+ */
+static int striped_read(struct inode *inode,
+			u64 off, u64 len,
+			struct page **pages, int num_pages,
+			int *checkeof, bool o_direct,
+			unsigned long buf_align)
+{
+	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	u64 pos, this_len;
+	int io_align, page_align;
+	int left, pages_left;
+	int read;
+	struct page **page_pos;
+	int ret;
+	bool hit_stripe, was_short;
+
+	/*
+	 * we may need to do multiple reads.  not atomic, unfortunately.
+	 */
+	pos = off;
+	left = len;
+	page_pos = pages;
+	pages_left = num_pages;
+	read = 0;
+	io_align = off & ~PAGE_MASK;
+
+more:
+	if (o_direct)
+		page_align = (pos - io_align + buf_align) & ~PAGE_MASK;
+	else
+		page_align = pos & ~PAGE_MASK;
+	this_len = left;
+	ret = ceph_osdc_readpages(&fsc->client->osdc, ceph_vino(inode),
+				  &ci->i_layout, pos, &this_len,
+				  ci->i_truncate_seq,
+				  ci->i_truncate_size,
+				  page_pos, pages_left, page_align);
+	if (ret == -ENOENT)
+		ret = 0;
+	hit_stripe = this_len < left;
+	was_short = ret >= 0 && ret < this_len;
+	dout("striped_read %llu~%u (read %u) got %d%s%s\n", pos, left, read,
+	     ret, hit_stripe ? " HITSTRIPE" : "", was_short ? " SHORT" : "");
+
+	if (ret > 0) {
+		int didpages = (page_align + ret) >> PAGE_CACHE_SHIFT;
+
+		if (read < pos - off) {
+			dout(" zero gap %llu to %llu\n", off + read, pos);
+			ceph_zero_page_vector_range(page_align + read,
+						    pos - off - read, pages);
+		}
+		pos += ret;
+		read = pos - off;
+		left -= ret;
+		page_pos += didpages;
+		pages_left -= didpages;
+
+		/* hit stripe? */
+		if (left && hit_stripe)
+			goto more;
+	}
+
+	if (was_short) {
+		/* did we bounce off eof? */
+		if (pos + left > inode->i_size)
+			*checkeof = 1;
+
+		/* zero trailing bytes (inside i_size) */
+		if (left > 0 && pos < inode->i_size) {
+			if (pos + left > inode->i_size)
+				left = inode->i_size - pos;
+
+			dout("zero tail %d\n", left);
+			ceph_zero_page_vector_range(page_align + read, left,
+						    pages);
+			read += left;
+		}
+	}
+
+	if (ret >= 0)
+		ret = read;
+	dout("striped_read returns %d\n", ret);
+	return ret;
+}
+
+/*
+ * Completely synchronous read and write methods.  Direct from __user
+ * buffer to osd, or directly to user pages (if O_DIRECT).
+ *
+ * If the read spans object boundary, just do multiple reads.
+ */
+static ssize_t ceph_sync_read(struct file *file, char __user *data,
+			      unsigned len, loff_t *poff, int *checkeof)
+{
+	struct inode *inode = file_inode(file);
+	struct page **pages;
+	u64 off = *poff;
+	int num_pages, ret;
+
+	dout("sync_read on file %p %llu~%u %s\n", file, off, len,
+	     (file->f_flags & O_DIRECT) ? "O_DIRECT" : "");
+
+	if (file->f_flags & O_DIRECT) {
+		num_pages = calc_pages_for((unsigned long)data, len);
+		pages = ceph_get_direct_page_vector(data, num_pages, true);
+	} else {
+		num_pages = calc_pages_for(off, len);
+		pages = ceph_alloc_page_vector(num_pages, GFP_NOFS);
+	}
+	if (IS_ERR(pages))
+		return PTR_ERR(pages);
+
+	/*
+	 * flush any page cache pages in this range.  this
+	 * will make concurrent normal and sync io slow,
+	 * but it will at least behave sensibly when they are
+	 * in sequence.
+	 */
+	ret = filemap_write_and_wait(inode->i_mapping);
+	if (ret < 0)
+		goto done;
+
+	ret = striped_read(inode, off, len, pages, num_pages, checkeof,
+			   file->f_flags & O_DIRECT,
+			   (unsigned long)data & ~PAGE_MASK);
+
+	if (ret >= 0 && (file->f_flags & O_DIRECT) == 0)
+		ret = ceph_copy_page_vector_to_user(pages, data, off, ret);
+	if (ret >= 0)
+		*poff = off + ret;
+
+done:
+	if (file->f_flags & O_DIRECT)
+		ceph_put_page_vector(pages, num_pages, true);
+	else
+		ceph_release_page_vector(pages, num_pages);
+	dout("sync_read result %d\n", ret);
+	return ret;
+}
+
+/*
+ * Write commit request unsafe callback, called to tell us when a
+ * request is unsafe (that is, in flight--has been handed to the
+ * messenger to send to its target osd).  It is called again when
+ * we've received a response message indicating the request is
+ * "safe" (its CEPH_OSD_FLAG_ONDISK flag is set), or when a request
+ * is completed early (and unsuccessfully) due to a timeout or
+ * interrupt.
+ *
+ * This is used if we requested both an ACK and ONDISK commit reply
+ * from the OSD.
+ */
+static void ceph_sync_write_unsafe(struct ceph_osd_request *req, bool unsafe)
+{
+	struct ceph_inode_info *ci = ceph_inode(req->r_inode);
+
+	dout("%s %p tid %llu %ssafe\n", __func__, req, req->r_tid,
+		unsafe ? "un" : "");
+	if (unsafe) {
+		ceph_get_cap_refs(ci, CEPH_CAP_FILE_WR);
+		spin_lock(&ci->i_unsafe_lock);
+		list_add_tail(&req->r_unsafe_item,
+			      &ci->i_unsafe_writes);
+		spin_unlock(&ci->i_unsafe_lock);
+	} else {
+		spin_lock(&ci->i_unsafe_lock);
+		list_del_init(&req->r_unsafe_item);
+		spin_unlock(&ci->i_unsafe_lock);
+		ceph_put_cap_refs(ci, CEPH_CAP_FILE_WR);
+	}
+}
+
+/*
+ * Synchronous write, straight from __user pointer or user pages (if
+ * O_DIRECT).
+ *
+ * If write spans object boundary, just do multiple writes.  (For a
+ * correct atomic write, we should e.g. take write locks on all
+ * objects, rollback on failure, etc.)
+ */
+static ssize_t ceph_sync_write(struct file *file, const char __user *data,
+			       size_t left, loff_t pos, loff_t *ppos)
+{
+	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_snap_context *snapc;
+	struct ceph_vino vino;
+	struct ceph_osd_request *req;
+	int num_ops = 1;
+	struct page **pages;
+	int num_pages;
+	u64 len;
+	int written = 0;
+	int flags;
+	int check_caps = 0;
+	int page_align, io_align;
+	unsigned long buf_align;
+	int ret;
+	struct timespec mtime = CURRENT_TIME;
+	bool own_pages = false;
+
+	if (ceph_snap(file_inode(file)) != CEPH_NOSNAP)
+		return -EROFS;
+
+	dout("sync_write on file %p %lld~%u %s\n", file, pos,
+	     (unsigned)left, (file->f_flags & O_DIRECT) ? "O_DIRECT" : "");
+
+	ret = filemap_write_and_wait_range(inode->i_mapping, pos, pos + left);
+	if (ret < 0)
+		return ret;
+
+	ret = invalidate_inode_pages2_range(inode->i_mapping,
+					    pos >> PAGE_CACHE_SHIFT,
+					    (pos + left) >> PAGE_CACHE_SHIFT);
+	if (ret < 0)
+		dout("invalidate_inode_pages2_range returned %d\n", ret);
+
+	flags = CEPH_OSD_FLAG_ORDERSNAP |
+		CEPH_OSD_FLAG_ONDISK |
+		CEPH_OSD_FLAG_WRITE;
+	if ((file->f_flags & (O_SYNC|O_DIRECT)) == 0)
+		flags |= CEPH_OSD_FLAG_ACK;
+	else
+		num_ops++;	/* Also include a 'startsync' command. */
+
+	/*
+	 * we may need to do multiple writes here if we span an object
+	 * boundary.  this isn't atomic, unfortunately.  :(
+	 */
+more:
+	io_align = pos & ~PAGE_MASK;
+	buf_align = (unsigned long)data & ~PAGE_MASK;
+	len = left;
+
+	snapc = ci->i_snap_realm->cached_context;
+	vino = ceph_vino(inode);
+	req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout,
+				    vino, pos, &len, num_ops,
+				    CEPH_OSD_OP_WRITE, flags, snapc,
+				    ci->i_truncate_seq, ci->i_truncate_size,
+				    false);
+	if (IS_ERR(req))
+		return PTR_ERR(req);
+
+	/* write from beginning of first page, regardless of io alignment */
+	page_align = file->f_flags & O_DIRECT ? buf_align : io_align;
+	num_pages = calc_pages_for(page_align, len);
+	if (file->f_flags & O_DIRECT) {
+		pages = ceph_get_direct_page_vector(data, num_pages, false);
+		if (IS_ERR(pages)) {
+			ret = PTR_ERR(pages);
+			goto out;
+		}
+
+		/*
+		 * throw out any page cache pages in this range. this
+		 * may block.
+		 */
+		truncate_inode_pages_range(inode->i_mapping, pos,
+					   (pos+len) | (PAGE_CACHE_SIZE-1));
+	} else {
+		pages = ceph_alloc_page_vector(num_pages, GFP_NOFS);
+		if (IS_ERR(pages)) {
+			ret = PTR_ERR(pages);
+			goto out;
+		}
+		ret = ceph_copy_user_to_page_vector(pages, data, pos, len);
+		if (ret < 0) {
+			ceph_release_page_vector(pages, num_pages);
+			goto out;
+		}
+
+		if ((file->f_flags & O_SYNC) == 0) {
+			/* get a second commit callback */
+			req->r_unsafe_callback = ceph_sync_write_unsafe;
+			req->r_inode = inode;
+			own_pages = true;
+		}
+	}
+	osd_req_op_extent_osd_data_pages(req, 0, pages, len, page_align,
+					false, own_pages);
+
+	/* BUG_ON(vino.snap != CEPH_NOSNAP); */
+	ceph_osdc_build_request(req, pos, snapc, vino.snap, &mtime);
+
+	ret = ceph_osdc_start_request(&fsc->client->osdc, req, false);
+	if (!ret)
+		ret = ceph_osdc_wait_request(&fsc->client->osdc, req);
+
+	if (file->f_flags & O_DIRECT)
+		ceph_put_page_vector(pages, num_pages, false);
+	else if (file->f_flags & O_SYNC)
+		ceph_release_page_vector(pages, num_pages);
+
+out:
+	ceph_osdc_put_request(req);
+	if (ret == 0) {
+		pos += len;
+		written += len;
+		left -= len;
+		data += len;
+		if (left)
+			goto more;
+
+		ret = written;
+		*ppos = pos;
+		if (pos > i_size_read(inode))
+			check_caps = ceph_inode_set_size(inode, pos);
+		if (check_caps)
+			ceph_check_caps(ceph_inode(inode), CHECK_CAPS_AUTHONLY,
+					NULL);
+	}
+	return ret;
+}
+
+/*
+ * Wrap generic_file_aio_read with checks for cap bits on the inode.
+ * Atomically grab references, so that those bits are not released
+ * back to the MDS mid-read.
+ *
+ * Hmm, the sync read case isn't actually async... should it be?
+ */
+static ssize_t ceph_aio_read(struct kiocb *iocb, const struct iovec *iov,
+			     unsigned long nr_segs, loff_t pos)
+{
+	struct file *filp = iocb->ki_filp;
+	struct ceph_file_info *fi = filp->private_data;
+	loff_t *ppos = &iocb->ki_pos;
+	size_t len = iov->iov_len;
+	struct inode *inode = file_inode(filp);
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	void __user *base = iov->iov_base;
+	ssize_t ret;
+	int want, got = 0;
+	int checkeof = 0, read = 0;
+
+	dout("aio_read %p %llx.%llx %llu~%u trying to get caps on %p\n",
+	     inode, ceph_vinop(inode), pos, (unsigned)len, inode);
+again:
+	if (fi->fmode & CEPH_FILE_MODE_LAZY)
+		want = CEPH_CAP_FILE_CACHE | CEPH_CAP_FILE_LAZYIO;
+	else
+		want = CEPH_CAP_FILE_CACHE;
+	ret = ceph_get_caps(ci, CEPH_CAP_FILE_RD, want, &got, -1);
+	if (ret < 0)
+		goto out;
+	dout("aio_read %p %llx.%llx %llu~%u got cap refs on %s\n",
+	     inode, ceph_vinop(inode), pos, (unsigned)len,
+	     ceph_cap_string(got));
+
+	if ((got & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)) == 0 ||
+	    (iocb->ki_filp->f_flags & O_DIRECT) ||
+	    (inode->i_sb->s_flags & MS_SYNCHRONOUS) ||
+	    (fi->flags & CEPH_F_SYNC))
+		/* hmm, this isn't really async... */
+		ret = ceph_sync_read(filp, base, len, ppos, &checkeof);
+	else
+		ret = generic_file_aio_read(iocb, iov, nr_segs, pos);
+
+out:
+	dout("aio_read %p %llx.%llx dropping cap refs on %s = %d\n",
+	     inode, ceph_vinop(inode), ceph_cap_string(got), (int)ret);
+	ceph_put_cap_refs(ci, got);
+
+	if (checkeof && ret >= 0) {
+		int statret = ceph_do_getattr(inode, CEPH_STAT_CAP_SIZE);
+
+		/* hit EOF or hole? */
+		if (statret == 0 && *ppos < inode->i_size) {
+			dout("aio_read sync_read hit hole, ppos %lld < size %lld, reading more\n", *ppos, inode->i_size);
+			read += ret;
+			base += ret;
+			len -= ret;
+			checkeof = 0;
+			goto again;
+		}
+	}
+	if (ret >= 0)
+		ret += read;
+
+	return ret;
+}
+
+/*
+ * Take cap references to avoid releasing caps to MDS mid-write.
+ *
+ * If we are synchronous, and write with an old snap context, the OSD
+ * may return EOLDSNAPC.  In that case, retry the write.. _after_
+ * dropping our cap refs and allowing the pending snap to logically
+ * complete _before_ this write occurs.
+ *
+ * If we are near ENOSPC, write synchronously.
+ */
+static ssize_t ceph_aio_write(struct kiocb *iocb, const struct iovec *iov,
+		       unsigned long nr_segs, loff_t pos)
+{
+	struct file *file = iocb->ki_filp;
+	struct ceph_file_info *fi = file->private_data;
+	struct inode *inode = file_inode(file);
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct ceph_osd_client *osdc =
+		&ceph_sb_to_client(inode->i_sb)->client->osdc;
+	ssize_t count, written = 0;
+	int err, want, got;
+	bool hold_mutex;
+
+	if (ceph_snap(inode) != CEPH_NOSNAP)
+		return -EROFS;
+
+	sb_start_write(inode->i_sb);
+	mutex_lock(&inode->i_mutex);
+	hold_mutex = true;
+
+	err = generic_segment_checks(iov, &nr_segs, &count, VERIFY_READ);
+	if (err)
+		goto out;
+
+	/* We can write back this queue in page reclaim */
+	current->backing_dev_info = file->f_mapping->backing_dev_info;
+
+	err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode));
+	if (err)
+		goto out;
+
+	if (count == 0)
+		goto out;
+
+	err = file_remove_suid(file);
+	if (err)
+		goto out;
+
+	err = file_update_time(file);
+	if (err)
+		goto out;
+
+retry_snap:
+	if (ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL)) {
+		err = -ENOSPC;
+		goto out;
+	}
+
+	dout("aio_write %p %llx.%llx %llu~%zd getting caps. i_size %llu\n",
+	     inode, ceph_vinop(inode), pos, count, 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;
+	got = 0;
+	err = ceph_get_caps(ci, CEPH_CAP_FILE_WR, want, &got, pos + count);
+	if (err < 0)
+		goto out;
+
+	dout("aio_write %p %llx.%llx %llu~%zd got cap refs on %s\n",
+	     inode, ceph_vinop(inode), pos, count, 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)) {
+		mutex_unlock(&inode->i_mutex);
+		written = ceph_sync_write(file, iov->iov_base, count,
+					  pos, &iocb->ki_pos);
+	} else {
+		written = generic_file_buffered_write(iocb, iov, nr_segs,
+						      pos, &iocb->ki_pos,
+						      count, 0);
+		mutex_unlock(&inode->i_mutex);
+	}
+	hold_mutex = false;
+
+	if (written >= 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("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));
+	ceph_put_cap_refs(ci, got);
+
+	if (written >= 0 &&
+	    ((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 + written - 1, 1);
+		if (err < 0)
+			written = err;
+	}
+
+	if (written == -EOLDSNAPC) {
+		dout("aio_write %p %llx.%llx %llu~%u got EOLDSNAPC, retrying\n",
+		     inode, ceph_vinop(inode), pos, (unsigned)iov->iov_len);
+		mutex_lock(&inode->i_mutex);
+		hold_mutex = true;
+		goto retry_snap;
+	}
+out:
+	if (hold_mutex)
+		mutex_unlock(&inode->i_mutex);
+	sb_end_write(inode->i_sb);
+	current->backing_dev_info = NULL;
+
+	return written ? written : err;
+}
+
+/*
+ * llseek.  be sure to verify file size on SEEK_END.
+ */
+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, false);
+
+	if (whence == SEEK_END || whence == SEEK_DATA || whence == SEEK_HOLE) {
+		ret = ceph_do_getattr(inode, CEPH_STAT_CAP_SIZE);
+		if (ret < 0) {
+			offset = ret;
+			goto out;
+		}
+	}
+
+	switch (whence) {
+	case SEEK_END:
+		offset += inode->i_size;
+		break;
+	case SEEK_CUR:
+		/*
+		 * Here we special-case the lseek(fd, 0, SEEK_CUR)
+		 * position-querying operation.  Avoid rewriting the "same"
+		 * f_pos value back to the file because a concurrent read(),
+		 * write() or lseek() might have altered it
+		 */
+		if (offset == 0) {
+			offset = file->f_pos;
+			goto out;
+		}
+		offset += file->f_pos;
+		break;
+	case SEEK_DATA:
+		if (offset >= inode->i_size) {
+			ret = -ENXIO;
+			goto out;
+		}
+		break;
+	case SEEK_HOLE:
+		if (offset >= inode->i_size) {
+			ret = -ENXIO;
+			goto out;
+		}
+		offset = inode->i_size;
+		break;
+	}
+
+	if (offset < 0 || offset > inode->i_sb->s_maxbytes) {
+		offset = -EINVAL;
+		goto out;
+	}
+
+	/* Special lock needed here? */
+	if (offset != file->f_pos) {
+		file->f_pos = offset;
+		file->f_version = 0;
+	}
+
+out:
+	mutex_unlock(&inode->i_mutex);
+	return offset;
+}
+
+const struct file_operations ceph_file_fops = {
+	.open = ceph_open,
+	.release = ceph_release,
+	.llseek = ceph_llseek,
+	.read = do_sync_read,
+	.write = do_sync_write,
+	.aio_read = ceph_aio_read,
+	.aio_write = ceph_aio_write,
+	.mmap = ceph_mmap,
+	.fsync = ceph_fsync,
+	.lock = ceph_lock,
+	.flock = ceph_flock,
+	.splice_read = generic_file_splice_read,
+	.splice_write = generic_file_splice_write,
+	.unlocked_ioctl = ceph_ioctl,
+	.compat_ioctl	= ceph_ioctl,
+};
+

fs/ceph/ioctl.c

@@ -0,0 +1,288 @@
+#include <linux/in.h>
+
+#include "super.h"
+#include "mds_client.h"
+#include <linux/ceph/ceph_debug.h>
+
+#include "ioctl.h"
+
+
+/*
+ * ioctls
+ */
+
+/*
+ * get and set the file layout
+ */
+static long ceph_ioctl_get_layout(struct file *file, void __user *arg)
+{
+	struct ceph_inode_info *ci = ceph_inode(file_inode(file));
+	struct ceph_ioctl_layout l;
+	int err;
+
+	err = ceph_do_getattr(file_inode(file), CEPH_STAT_CAP_LAYOUT);
+	if (!err) {
+		l.stripe_unit = ceph_file_layout_su(ci->i_layout);
+		l.stripe_count = ceph_file_layout_stripe_count(ci->i_layout);
+		l.object_size = ceph_file_layout_object_size(ci->i_layout);
+		l.data_pool = le32_to_cpu(ci->i_layout.fl_pg_pool);
+		l.preferred_osd = (s32)-1;
+		if (copy_to_user(arg, &l, sizeof(l)))
+			return -EFAULT;
+	}
+
+	return err;
+}
+
+static long __validate_layout(struct ceph_mds_client *mdsc,
+			      struct ceph_ioctl_layout *l)
+{
+	int i, err;
+
+	/* validate striping parameters */
+	if ((l->object_size & ~PAGE_MASK) ||
+	    (l->stripe_unit & ~PAGE_MASK) ||
+	    (l->stripe_unit != 0 &&
+	     ((unsigned)l->object_size % (unsigned)l->stripe_unit)))
+		return -EINVAL;
+
+	/* make sure it's a valid data pool */
+	mutex_lock(&mdsc->mutex);
+	err = -EINVAL;
+	for (i = 0; i < mdsc->mdsmap->m_num_data_pg_pools; i++)
+		if (mdsc->mdsmap->m_data_pg_pools[i] == l->data_pool) {
+			err = 0;
+			break;
+		}
+	mutex_unlock(&mdsc->mutex);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+static long ceph_ioctl_set_layout(struct file *file, void __user *arg)
+{
+	struct inode *inode = file_inode(file);
+	struct inode *parent_inode;
+	struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
+	struct ceph_mds_request *req;
+	struct ceph_ioctl_layout l;
+	struct ceph_inode_info *ci = ceph_inode(file_inode(file));
+	struct ceph_ioctl_layout nl;
+	int err;
+
+	if (copy_from_user(&l, arg, sizeof(l)))
+		return -EFAULT;
+
+	/* validate changed params against current layout */
+	err = ceph_do_getattr(file_inode(file), CEPH_STAT_CAP_LAYOUT);
+	if (err)
+		return err;
+
+	memset(&nl, 0, sizeof(nl));
+	if (l.stripe_count)
+		nl.stripe_count = l.stripe_count;
+	else
+		nl.stripe_count = ceph_file_layout_stripe_count(ci->i_layout);
+	if (l.stripe_unit)
+		nl.stripe_unit = l.stripe_unit;
+	else
+		nl.stripe_unit = ceph_file_layout_su(ci->i_layout);
+	if (l.object_size)
+		nl.object_size = l.object_size;
+	else
+		nl.object_size = ceph_file_layout_object_size(ci->i_layout);
+	if (l.data_pool)
+		nl.data_pool = l.data_pool;
+	else
+		nl.data_pool = ceph_file_layout_pg_pool(ci->i_layout);
+
+	/* this is obsolete, and always -1 */
+	nl.preferred_osd = le64_to_cpu(-1);
+
+	err = __validate_layout(mdsc, &nl);
+	if (err)
+		return err;
+
+	req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_SETLAYOUT,
+				       USE_AUTH_MDS);
+	if (IS_ERR(req))
+		return PTR_ERR(req);
+	req->r_inode = inode;
+	ihold(inode);
+	req->r_inode_drop = CEPH_CAP_FILE_SHARED | CEPH_CAP_FILE_EXCL;
+
+	req->r_args.setlayout.layout.fl_stripe_unit =
+		cpu_to_le32(l.stripe_unit);
+	req->r_args.setlayout.layout.fl_stripe_count =
+		cpu_to_le32(l.stripe_count);
+	req->r_args.setlayout.layout.fl_object_size =
+		cpu_to_le32(l.object_size);
+	req->r_args.setlayout.layout.fl_pg_pool = cpu_to_le32(l.data_pool);
+
+	parent_inode = ceph_get_dentry_parent_inode(file->f_dentry);
+	err = ceph_mdsc_do_request(mdsc, parent_inode, req);
+	iput(parent_inode);
+	ceph_mdsc_put_request(req);
+	return err;
+}
+
+/*
+ * Set a layout policy on a directory inode. All items in the tree
+ * rooted at this inode will inherit this layout on creation,
+ * (It doesn't apply retroactively )
+ * unless a subdirectory has its own layout policy.
+ */
+static long ceph_ioctl_set_layout_policy (struct file *file, void __user *arg)
+{
+	struct inode *inode = file_inode(file);
+	struct ceph_mds_request *req;
+	struct ceph_ioctl_layout l;
+	int err;
+	struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
+
+	/* copy and validate */
+	if (copy_from_user(&l, arg, sizeof(l)))
+		return -EFAULT;
+
+	err = __validate_layout(mdsc, &l);
+	if (err)
+		return err;
+
+	req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_SETDIRLAYOUT,
+				       USE_AUTH_MDS);
+
+	if (IS_ERR(req))
+		return PTR_ERR(req);
+	req->r_inode = inode;
+	ihold(inode);
+
+	req->r_args.setlayout.layout.fl_stripe_unit =
+			cpu_to_le32(l.stripe_unit);
+	req->r_args.setlayout.layout.fl_stripe_count =
+			cpu_to_le32(l.stripe_count);
+	req->r_args.setlayout.layout.fl_object_size =
+			cpu_to_le32(l.object_size);
+	req->r_args.setlayout.layout.fl_pg_pool =
+			cpu_to_le32(l.data_pool);
+
+	err = ceph_mdsc_do_request(mdsc, inode, req);
+	ceph_mdsc_put_request(req);
+	return err;
+}
+
+/*
+ * Return object name, size/offset information, and location (OSD
+ * number, network address) for a given file offset.
+ */
+static long ceph_ioctl_get_dataloc(struct file *file, void __user *arg)
+{
+	struct ceph_ioctl_dataloc dl;
+	struct inode *inode = file_inode(file);
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct ceph_osd_client *osdc =
+		&ceph_sb_to_client(inode->i_sb)->client->osdc;
+	u64 len = 1, olen;
+	u64 tmp;
+	struct ceph_pg pgid;
+	int r;
+
+	/* copy and validate */
+	if (copy_from_user(&dl, arg, sizeof(dl)))
+		return -EFAULT;
+
+	down_read(&osdc->map_sem);
+	r = ceph_calc_file_object_mapping(&ci->i_layout, dl.file_offset, len,
+					  &dl.object_no, &dl.object_offset,
+					  &olen);
+	if (r < 0) {
+		up_read(&osdc->map_sem);
+		return -EIO;
+	}
+	dl.file_offset -= dl.object_offset;
+	dl.object_size = ceph_file_layout_object_size(ci->i_layout);
+	dl.block_size = ceph_file_layout_su(ci->i_layout);
+
+	/* block_offset = object_offset % block_size */
+	tmp = dl.object_offset;
+	dl.block_offset = do_div(tmp, dl.block_size);
+
+	snprintf(dl.object_name, sizeof(dl.object_name), "%llx.%08llx",
+		 ceph_ino(inode), dl.object_no);
+
+	ceph_calc_ceph_pg(&pgid, dl.object_name, osdc->osdmap,
+		ceph_file_layout_pg_pool(ci->i_layout));
+
+	dl.osd = ceph_calc_pg_primary(osdc->osdmap, pgid);
+	if (dl.osd >= 0) {
+		struct ceph_entity_addr *a =
+			ceph_osd_addr(osdc->osdmap, dl.osd);
+		if (a)
+			memcpy(&dl.osd_addr, &a->in_addr, sizeof(dl.osd_addr));
+	} else {
+		memset(&dl.osd_addr, 0, sizeof(dl.osd_addr));
+	}
+	up_read(&osdc->map_sem);
+
+	/* send result back to user */
+	if (copy_to_user(arg, &dl, sizeof(dl)))
+		return -EFAULT;
+
+	return 0;
+}
+
+static long ceph_ioctl_lazyio(struct file *file)
+{
+	struct ceph_file_info *fi = file->private_data;
+	struct inode *inode = file_inode(file);
+	struct ceph_inode_info *ci = ceph_inode(inode);
+
+	if ((fi->fmode & CEPH_FILE_MODE_LAZY) == 0) {
+		spin_lock(&ci->i_ceph_lock);
+		ci->i_nr_by_mode[fi->fmode]--;
+		fi->fmode |= CEPH_FILE_MODE_LAZY;
+		ci->i_nr_by_mode[fi->fmode]++;
+		spin_unlock(&ci->i_ceph_lock);
+		dout("ioctl_layzio: file %p marked lazy\n", file);
+
+		ceph_check_caps(ci, 0, NULL);
+	} else {
+		dout("ioctl_layzio: file %p already lazy\n", file);
+	}
+	return 0;
+}
+
+static long ceph_ioctl_syncio(struct file *file)
+{
+	struct ceph_file_info *fi = file->private_data;
+
+	fi->flags |= CEPH_F_SYNC;
+	return 0;
+}
+
+long ceph_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	dout("ioctl file %p cmd %u arg %lu\n", file, cmd, arg);
+	switch (cmd) {
+	case CEPH_IOC_GET_LAYOUT:
+		return ceph_ioctl_get_layout(file, (void __user *)arg);
+
+	case CEPH_IOC_SET_LAYOUT:
+		return ceph_ioctl_set_layout(file, (void __user *)arg);
+
+	case CEPH_IOC_SET_LAYOUT_POLICY:
+		return ceph_ioctl_set_layout_policy(file, (void __user *)arg);
+
+	case CEPH_IOC_GET_DATALOC:
+		return ceph_ioctl_get_dataloc(file, (void __user *)arg);
+
+	case CEPH_IOC_LAZYIO:
+		return ceph_ioctl_lazyio(file);
+
+	case CEPH_IOC_SYNCIO:
+		return ceph_ioctl_syncio(file);
+	}
+
+	return -ENOTTY;
+}

fs/ceph/ioctl.h

@@ -0,0 +1,100 @@
+#ifndef FS_CEPH_IOCTL_H
+#define FS_CEPH_IOCTL_H
+
+#include <linux/ioctl.h>
+#include <linux/types.h>
+
+#define CEPH_IOCTL_MAGIC 0x97
+
+/*
+ * CEPH_IOC_GET_LAYOUT - get file layout or dir layout policy
+ * CEPH_IOC_SET_LAYOUT - set file layout
+ * CEPH_IOC_SET_LAYOUT_POLICY - set dir layout policy
+ *
+ * The file layout specifies how file data is striped over objects in
+ * the distributed object store, which object pool they belong to (if
+ * it differs from the default), and an optional 'preferred osd' to
+ * store them on.
+ *
+ * Files get a new layout based on the policy set on the containing
+ * directory or one of its ancestors.  The GET_LAYOUT ioctl will let
+ * you examine the layout for a file or the policy on a directory.
+ *
+ * SET_LAYOUT will let you set a layout on a newly created file.  This
+ * only works immediately after the file is created and before any
+ * data is written to it.
+ *
+ * SET_LAYOUT_POLICY will let you set a layout policy (default layout)
+ * on a directory that will apply to any new files created in that
+ * directory (or any child directory that doesn't specify a layout of
+ * its own).
+ */
+
+/* use u64 to align sanely on all archs */
+struct ceph_ioctl_layout {
+	__u64 stripe_unit, stripe_count, object_size;
+	__u64 data_pool;
+
+	/* obsolete.  new values ignored, always return -1 */
+	__s64 preferred_osd;
+};
+
+#define CEPH_IOC_GET_LAYOUT _IOR(CEPH_IOCTL_MAGIC, 1,		\
+				   struct ceph_ioctl_layout)
+#define CEPH_IOC_SET_LAYOUT _IOW(CEPH_IOCTL_MAGIC, 2,		\
+				   struct ceph_ioctl_layout)
+#define CEPH_IOC_SET_LAYOUT_POLICY _IOW(CEPH_IOCTL_MAGIC, 5,	\
+				   struct ceph_ioctl_layout)
+
+/*
+ * CEPH_IOC_GET_DATALOC - get location of file data in the cluster
+ *
+ * Extract identity, address of the OSD and object storing a given
+ * file offset.
+ */
+struct ceph_ioctl_dataloc {
+	__u64 file_offset;           /* in+out: file offset */
+	__u64 object_offset;         /* out: offset in object */
+	__u64 object_no;             /* out: object # */
+	__u64 object_size;           /* out: object size */
+	char object_name[64];        /* out: object name */
+	__u64 block_offset;          /* out: offset in block */
+	__u64 block_size;            /* out: block length */
+	__s64 osd;                   /* out: osd # */
+	struct sockaddr_storage osd_addr; /* out: osd address */
+};
+
+#define CEPH_IOC_GET_DATALOC _IOWR(CEPH_IOCTL_MAGIC, 3,	\
+				   struct ceph_ioctl_dataloc)
+
+/*
+ * CEPH_IOC_LAZYIO - relax consistency
+ *
+ * Normally Ceph switches to synchronous IO when multiple clients have
+ * the file open (and or more for write).  Reads and writes bypass the
+ * page cache and go directly to the OSD.  Setting this flag on a file
+ * descriptor will allow buffered IO for this file in cases where the
+ * application knows it won't interfere with other nodes (or doesn't
+ * care).
+ */
+#define CEPH_IOC_LAZYIO _IO(CEPH_IOCTL_MAGIC, 4)
+
+/*
+ * CEPH_IOC_SYNCIO - force synchronous IO
+ *
+ * This ioctl sets a file flag that forces the synchronous IO that
+ * bypasses the page cache, even if it is not necessary.  This is
+ * essentially the opposite behavior of IOC_LAZYIO.  This forces the
+ * same read/write path as a file opened by multiple clients when one
+ * or more of those clients is opened for write.
+ *
+ * Note that this type of sync IO takes a different path than a file
+ * opened with O_SYNC/D_SYNC (writes hit the page cache and are
+ * immediately flushed on page boundaries).  It is very similar to
+ * O_DIRECT (writes bypass the page cache) excep that O_DIRECT writes
+ * are not copied (user page must remain stable) and O_DIRECT writes
+ * have alignment restrictions (on the buffer and file offset).
+ */
+#define CEPH_IOC_SYNCIO _IO(CEPH_IOCTL_MAGIC, 5)
+
+#endif

fs/ceph/locks.c

@@ -0,0 +1,307 @@
+#include <linux/ceph/ceph_debug.h>
+
+#include <linux/file.h>
+#include <linux/namei.h>
+
+#include "super.h"
+#include "mds_client.h"
+#include <linux/ceph/pagelist.h>
+
+/**
+ * Implement fcntl and flock locking functions.
+ */
+static int ceph_lock_message(u8 lock_type, u16 operation, struct file *file,
+			     int cmd, u8 wait, struct file_lock *fl)
+{
+	struct inode *inode = file_inode(file);
+	struct ceph_mds_client *mdsc =
+		ceph_sb_to_client(inode->i_sb)->mdsc;
+	struct ceph_mds_request *req;
+	int err;
+	u64 length = 0;
+
+	req = ceph_mdsc_create_request(mdsc, operation, USE_AUTH_MDS);
+	if (IS_ERR(req))
+		return PTR_ERR(req);
+	req->r_inode = inode;
+	ihold(inode);
+
+	/* mds requires start and length rather than start and end */
+	if (LLONG_MAX == fl->fl_end)
+		length = 0;
+	else
+		length = fl->fl_end - fl->fl_start + 1;
+
+	dout("ceph_lock_message: rule: %d, op: %d, pid: %llu, start: %llu, "
+	     "length: %llu, wait: %d, type: %d", (int)lock_type,
+	     (int)operation, (u64)fl->fl_pid, fl->fl_start,
+	     length, wait, fl->fl_type);
+
+	req->r_args.filelock_change.rule = lock_type;
+	req->r_args.filelock_change.type = cmd;
+	req->r_args.filelock_change.pid = cpu_to_le64((u64)fl->fl_pid);
+	/* This should be adjusted, but I'm not sure if
+	   namespaces actually get id numbers*/
+	req->r_args.filelock_change.pid_namespace =
+		cpu_to_le64((u64)(unsigned long)fl->fl_nspid);
+	req->r_args.filelock_change.start = cpu_to_le64(fl->fl_start);
+	req->r_args.filelock_change.length = cpu_to_le64(length);
+	req->r_args.filelock_change.wait = wait;
+
+	err = ceph_mdsc_do_request(mdsc, inode, req);
+
+	if ( operation == CEPH_MDS_OP_GETFILELOCK){
+		fl->fl_pid = le64_to_cpu(req->r_reply_info.filelock_reply->pid);
+		if (CEPH_LOCK_SHARED == req->r_reply_info.filelock_reply->type)
+			fl->fl_type = F_RDLCK;
+		else if (CEPH_LOCK_EXCL == req->r_reply_info.filelock_reply->type)
+			fl->fl_type = F_WRLCK;
+		else
+			fl->fl_type = F_UNLCK;
+
+		fl->fl_start = le64_to_cpu(req->r_reply_info.filelock_reply->start);
+		length = le64_to_cpu(req->r_reply_info.filelock_reply->start) +
+						 le64_to_cpu(req->r_reply_info.filelock_reply->length);
+		if (length >= 1)
+			fl->fl_end = length -1;
+		else
+			fl->fl_end = 0;
+
+	}
+	ceph_mdsc_put_request(req);
+	dout("ceph_lock_message: rule: %d, op: %d, pid: %llu, start: %llu, "
+	     "length: %llu, wait: %d, type: %d, err code %d", (int)lock_type,
+	     (int)operation, (u64)fl->fl_pid, fl->fl_start,
+	     length, wait, fl->fl_type, err);
+	return err;
+}
+
+/**
+ * Attempt to set an fcntl lock.
+ * For now, this just goes away to the server. Later it may be more awesome.
+ */
+int ceph_lock(struct file *file, int cmd, struct file_lock *fl)
+{
+	u8 lock_cmd;
+	int err;
+	u8 wait = 0;
+	u16 op = CEPH_MDS_OP_SETFILELOCK;
+
+	fl->fl_nspid = get_pid(task_tgid(current));
+	dout("ceph_lock, fl_pid:%d", fl->fl_pid);
+
+	/* set wait bit as appropriate, then make command as Ceph expects it*/
+	if (F_SETLKW == cmd)
+		wait = 1;
+	if (F_GETLK == cmd)
+		op = CEPH_MDS_OP_GETFILELOCK;
+
+	if (F_RDLCK == fl->fl_type)
+		lock_cmd = CEPH_LOCK_SHARED;
+	else if (F_WRLCK == fl->fl_type)
+		lock_cmd = CEPH_LOCK_EXCL;
+	else
+		lock_cmd = CEPH_LOCK_UNLOCK;
+
+	err = ceph_lock_message(CEPH_LOCK_FCNTL, op, file, lock_cmd, wait, fl);
+	if (!err) {
+		if ( op != CEPH_MDS_OP_GETFILELOCK ){
+			dout("mds locked, locking locally");
+			err = posix_lock_file(file, fl, NULL);
+			if (err && (CEPH_MDS_OP_SETFILELOCK == op)) {
+				/* undo! This should only happen if
+				 * the kernel detects local
+				 * deadlock. */
+				ceph_lock_message(CEPH_LOCK_FCNTL, op, file,
+						  CEPH_LOCK_UNLOCK, 0, fl);
+				dout("got %d on posix_lock_file, undid lock",
+				     err);
+			}
+		}
+
+	} else if (err == -ERESTARTSYS) {
+		dout("undoing lock\n");
+		ceph_lock_message(CEPH_LOCK_FCNTL, op, file,
+				  CEPH_LOCK_UNLOCK, 0, fl);
+	}
+	return err;
+}
+
+int ceph_flock(struct file *file, int cmd, struct file_lock *fl)
+{
+	u8 lock_cmd;
+	int err;
+	u8 wait = 1;
+
+	fl->fl_nspid = get_pid(task_tgid(current));
+	dout("ceph_flock, fl_pid:%d", fl->fl_pid);
+
+	/* set wait bit, then clear it out of cmd*/
+	if (cmd & LOCK_NB)
+		wait = 0;
+	cmd = cmd & (LOCK_SH | LOCK_EX | LOCK_UN);
+	/* set command sequence that Ceph wants to see:
+	   shared lock, exclusive lock, or unlock */
+	if (LOCK_SH == cmd)
+		lock_cmd = CEPH_LOCK_SHARED;
+	else if (LOCK_EX == cmd)
+		lock_cmd = CEPH_LOCK_EXCL;
+	else
+		lock_cmd = CEPH_LOCK_UNLOCK;
+
+	err = ceph_lock_message(CEPH_LOCK_FLOCK, CEPH_MDS_OP_SETFILELOCK,
+				file, lock_cmd, wait, fl);
+	if (!err) {
+		err = flock_lock_file_wait(file, fl);
+		if (err) {
+			ceph_lock_message(CEPH_LOCK_FLOCK,
+					  CEPH_MDS_OP_SETFILELOCK,
+					  file, CEPH_LOCK_UNLOCK, 0, fl);
+			dout("got %d on flock_lock_file_wait, undid lock", err);
+		}
+	} else if (err == -ERESTARTSYS) {
+		dout("undoing lock\n");
+		ceph_lock_message(CEPH_LOCK_FLOCK,
+				  CEPH_MDS_OP_SETFILELOCK,
+				  file, CEPH_LOCK_UNLOCK, 0, fl);
+	}
+	return err;
+}
+
+/**
+ * Must be called with BKL already held. Fills in the passed
+ * counter variables, so you can prepare pagelist metadata before calling
+ * ceph_encode_locks.
+ */
+void ceph_count_locks(struct inode *inode, int *fcntl_count, int *flock_count)
+{
+	struct file_lock *lock;
+
+	*fcntl_count = 0;
+	*flock_count = 0;
+
+	for (lock = inode->i_flock; lock != NULL; lock = lock->fl_next) {
+		if (lock->fl_flags & FL_POSIX)
+			++(*fcntl_count);
+		else if (lock->fl_flags & FL_FLOCK)
+			++(*flock_count);
+	}
+	dout("counted %d flock locks and %d fcntl locks",
+	     *flock_count, *fcntl_count);
+}
+
+/**
+ * Encode the flock and fcntl locks for the given inode into the ceph_filelock
+ * array. Must be called with lock_flocks() already held.
+ * If we encounter more of a specific lock type than expected, return -ENOSPC.
+ */
+int ceph_encode_locks_to_buffer(struct inode *inode,
+				struct ceph_filelock *flocks,
+				int num_fcntl_locks, int num_flock_locks)
+{
+	struct file_lock *lock;
+	int err = 0;
+	int seen_fcntl = 0;
+	int seen_flock = 0;
+	int l = 0;
+
+	dout("encoding %d flock and %d fcntl locks", num_flock_locks,
+	     num_fcntl_locks);
+
+	for (lock = inode->i_flock; lock != NULL; lock = lock->fl_next) {
+		if (lock->fl_flags & FL_POSIX) {
+			++seen_fcntl;
+			if (seen_fcntl > num_fcntl_locks) {
+				err = -ENOSPC;
+				goto fail;
+			}
+			err = lock_to_ceph_filelock(lock, &flocks[l]);
+			if (err)
+				goto fail;
+			++l;
+		}
+	}
+	for (lock = inode->i_flock; lock != NULL; lock = lock->fl_next) {
+		if (lock->fl_flags & FL_FLOCK) {
+			++seen_flock;
+			if (seen_flock > num_flock_locks) {
+				err = -ENOSPC;
+				goto fail;
+			}
+			err = lock_to_ceph_filelock(lock, &flocks[l]);
+			if (err)
+				goto fail;
+			++l;
+		}
+	}
+fail:
+	return err;
+}
+
+/**
+ * Copy the encoded flock and fcntl locks into the pagelist.
+ * Format is: #fcntl locks, sequential fcntl locks, #flock locks,
+ * sequential flock locks.
+ * Returns zero on success.
+ */
+int ceph_locks_to_pagelist(struct ceph_filelock *flocks,
+			   struct ceph_pagelist *pagelist,
+			   int num_fcntl_locks, int num_flock_locks)
+{
+	int err = 0;
+	__le32 nlocks;
+
+	nlocks = cpu_to_le32(num_fcntl_locks);
+	err = ceph_pagelist_append(pagelist, &nlocks, sizeof(nlocks));
+	if (err)
+		goto out_fail;
+
+	err = ceph_pagelist_append(pagelist, flocks,
+				   num_fcntl_locks * sizeof(*flocks));
+	if (err)
+		goto out_fail;
+
+	nlocks = cpu_to_le32(num_flock_locks);
+	err = ceph_pagelist_append(pagelist, &nlocks, sizeof(nlocks));
+	if (err)
+		goto out_fail;
+
+	err = ceph_pagelist_append(pagelist,
+				   &flocks[num_fcntl_locks],
+				   num_flock_locks * sizeof(*flocks));
+out_fail:
+	return err;
+}
+
+/*
+ * Given a pointer to a lock, convert it to a ceph filelock
+ */
+int lock_to_ceph_filelock(struct file_lock *lock,
+			  struct ceph_filelock *cephlock)
+{
+	int err = 0;
+
+	cephlock->start = cpu_to_le64(lock->fl_start);
+	cephlock->length = cpu_to_le64(lock->fl_end - lock->fl_start + 1);
+	cephlock->client = cpu_to_le64(0);
+	cephlock->pid = cpu_to_le64(lock->fl_pid);
+	cephlock->pid_namespace =
+	        cpu_to_le64((u64)(unsigned long)lock->fl_nspid);
+
+	switch (lock->fl_type) {
+	case F_RDLCK:
+		cephlock->type = CEPH_LOCK_SHARED;
+		break;
+	case F_WRLCK:
+		cephlock->type = CEPH_LOCK_EXCL;
+		break;
+	case F_UNLCK:
+		cephlock->type = CEPH_LOCK_UNLOCK;
+		break;
+	default:
+		dout("Have unknown lock type %d", lock->fl_type);
+		err = -EINVAL;
+	}
+
+	return err;
+}

fs/ceph/mds_client.h

@@ -0,0 +1,388 @@
+#ifndef _FS_CEPH_MDS_CLIENT_H
+#define _FS_CEPH_MDS_CLIENT_H
+
+#include <linux/completion.h>
+#include <linux/kref.h>
+#include <linux/list.h>
+#include <linux/mutex.h>
+#include <linux/rbtree.h>
+#include <linux/spinlock.h>
+
+#include <linux/ceph/types.h>
+#include <linux/ceph/messenger.h>
+#include <linux/ceph/mdsmap.h>
+#include <linux/ceph/auth.h>
+
+/*
+ * Some lock dependencies:
+ *
+ * session->s_mutex
+ *         mdsc->mutex
+ *
+ *         mdsc->snap_rwsem
+ *
+ *         ci->i_ceph_lock
+ *                 mdsc->snap_flush_lock
+ *                 mdsc->cap_delay_lock
+ *
+ */
+
+struct ceph_fs_client;
+struct ceph_cap;
+
+/*
+ * parsed info about a single inode.  pointers are into the encoded
+ * on-wire structures within the mds reply message payload.
+ */
+struct ceph_mds_reply_info_in {
+	struct ceph_mds_reply_inode *in;
+	struct ceph_dir_layout dir_layout;
+	u32 symlink_len;
+	char *symlink;
+	u32 xattr_len;
+	char *xattr_data;
+};
+
+/*
+ * parsed info about an mds reply, including information about
+ * either: 1) the target inode and/or its parent directory and dentry,
+ * and directory contents (for readdir results), or
+ * 2) the file range lock info (for fcntl F_GETLK results).
+ */
+struct ceph_mds_reply_info_parsed {
+	struct ceph_mds_reply_head    *head;
+
+	/* trace */
+	struct ceph_mds_reply_info_in diri, targeti;
+	struct ceph_mds_reply_dirfrag *dirfrag;
+	char                          *dname;
+	u32                           dname_len;
+	struct ceph_mds_reply_lease   *dlease;
+
+	/* extra */
+	union {
+		/* for fcntl F_GETLK results */
+		struct ceph_filelock *filelock_reply;
+
+		/* for readdir results */
+		struct {
+			struct ceph_mds_reply_dirfrag *dir_dir;
+			int                           dir_nr;
+			char                          **dir_dname;
+			u32                           *dir_dname_len;
+			struct ceph_mds_reply_lease   **dir_dlease;
+			struct ceph_mds_reply_info_in *dir_in;
+			u8                            dir_complete, dir_end;
+		};
+
+		/* for create results */
+		struct {
+			bool has_create_ino;
+			u64 ino;
+		};
+	};
+
+	/* encoded blob describing snapshot contexts for certain
+	   operations (e.g., open) */
+	void *snapblob;
+	int snapblob_len;
+};
+
+
+/*
+ * cap releases are batched and sent to the MDS en masse.
+ */
+#define CEPH_CAPS_PER_RELEASE ((PAGE_CACHE_SIZE -			\
+				sizeof(struct ceph_mds_cap_release)) /	\
+			       sizeof(struct ceph_mds_cap_item))
+
+
+/*
+ * state associated with each MDS<->client session
+ */
+enum {
+	CEPH_MDS_SESSION_NEW = 1,
+	CEPH_MDS_SESSION_OPENING = 2,
+	CEPH_MDS_SESSION_OPEN = 3,
+	CEPH_MDS_SESSION_HUNG = 4,
+	CEPH_MDS_SESSION_CLOSING = 5,
+	CEPH_MDS_SESSION_RESTARTING = 6,
+	CEPH_MDS_SESSION_RECONNECTING = 7,
+};
+
+struct ceph_mds_session {
+	struct ceph_mds_client *s_mdsc;
+	int               s_mds;
+	int               s_state;
+	unsigned long     s_ttl;      /* time until mds kills us */
+	u64               s_seq;      /* incoming msg seq # */
+	struct mutex      s_mutex;    /* serialize session messages */
+
+	struct ceph_connection s_con;
+
+	struct ceph_auth_handshake s_auth;
+
+	/* protected by s_gen_ttl_lock */
+	spinlock_t        s_gen_ttl_lock;
+	u32               s_cap_gen;  /* inc each time we get mds stale msg */
+	unsigned long     s_cap_ttl;  /* when session caps expire */
+
+	/* protected by s_cap_lock */
+	spinlock_t        s_cap_lock;
+	struct list_head  s_caps;     /* all caps issued by this session */
+	int               s_nr_caps, s_trim_caps;
+	int               s_num_cap_releases;
+	struct list_head  s_cap_releases; /* waiting cap_release messages */
+	struct list_head  s_cap_releases_done; /* ready to send */
+	struct ceph_cap  *s_cap_iterator;
+
+	/* protected by mutex */
+	struct list_head  s_cap_flushing;     /* inodes w/ flushing caps */
+	struct list_head  s_cap_snaps_flushing;
+	unsigned long     s_renew_requested; /* last time we sent a renew req */
+	u64               s_renew_seq;
+
+	atomic_t          s_ref;
+	struct list_head  s_waiting;  /* waiting requests */
+	struct list_head  s_unsafe;   /* unsafe requests */
+};
+
+/*
+ * modes of choosing which MDS to send a request to
+ */
+enum {
+	USE_ANY_MDS,
+	USE_RANDOM_MDS,
+	USE_AUTH_MDS,   /* prefer authoritative mds for this metadata item */
+};
+
+struct ceph_mds_request;
+struct ceph_mds_client;
+
+/*
+ * request completion callback
+ */
+typedef void (*ceph_mds_request_callback_t) (struct ceph_mds_client *mdsc,
+					     struct ceph_mds_request *req);
+
+/*
+ * an in-flight mds request
+ */
+struct ceph_mds_request {
+	u64 r_tid;                   /* transaction id */
+	struct rb_node r_node;
+	struct ceph_mds_client *r_mdsc;
+
+	int r_op;                    /* mds op code */
+
+	/* operation on what? */
+	struct inode *r_inode;              /* arg1 */
+	struct dentry *r_dentry;            /* arg1 */
+	struct dentry *r_old_dentry;        /* arg2: rename from or link from */
+	struct inode *r_old_dentry_dir;     /* arg2: old dentry's parent dir */
+	char *r_path1, *r_path2;
+	struct ceph_vino r_ino1, r_ino2;
+
+	struct inode *r_locked_dir; /* dir (if any) i_mutex locked by vfs */
+	struct inode *r_target_inode;       /* resulting inode */
+
+	struct mutex r_fill_mutex;
+
+	union ceph_mds_request_args r_args;
+	int r_fmode;        /* file mode, if expecting cap */
+	kuid_t r_uid;
+	kgid_t r_gid;
+
+	/* for choosing which mds to send this request to */
+	int r_direct_mode;
+	u32 r_direct_hash;      /* choose dir frag based on this dentry hash */
+	bool r_direct_is_hash;  /* true if r_direct_hash is valid */
+
+	/* data payload is used for xattr ops */
+	struct page **r_pages;
+	int r_num_pages;
+	int r_data_len;
+
+	/* what caps shall we drop? */
+	int r_inode_drop, r_inode_unless;
+	int r_dentry_drop, r_dentry_unless;
+	int r_old_dentry_drop, r_old_dentry_unless;
+	struct inode *r_old_inode;
+	int r_old_inode_drop, r_old_inode_unless;
+
+	struct ceph_msg  *r_request;  /* original request */
+	int r_request_release_offset;
+	struct ceph_msg  *r_reply;
+	struct ceph_mds_reply_info_parsed r_reply_info;
+	int r_err;
+	bool r_aborted;
+
+	unsigned long r_timeout;  /* optional.  jiffies */
+	unsigned long r_started;  /* start time to measure timeout against */
+	unsigned long r_request_started; /* start time for mds request only,
+					    used to measure lease durations */
+
+	/* link unsafe requests to parent directory, for fsync */
+	struct inode	*r_unsafe_dir;
+	struct list_head r_unsafe_dir_item;
+
+	struct ceph_mds_session *r_session;
+
+	int               r_attempts;   /* resend attempts */
+	int               r_num_fwd;    /* number of forward attempts */
+	int               r_resend_mds; /* mds to resend to next, if any*/
+	u32               r_sent_on_mseq; /* cap mseq request was sent at*/
+
+	struct kref       r_kref;
+	struct list_head  r_wait;
+	struct completion r_completion;
+	struct completion r_safe_completion;
+	ceph_mds_request_callback_t r_callback;
+	struct list_head  r_unsafe_item;  /* per-session unsafe list item */
+	bool		  r_got_unsafe, r_got_safe, r_got_result;
+
+	bool              r_did_prepopulate;
+	u32               r_readdir_offset;
+
+	struct ceph_cap_reservation r_caps_reservation;
+	int r_num_caps;
+};
+
+/*
+ * mds client state
+ */
+struct ceph_mds_client {
+	struct ceph_fs_client  *fsc;
+	struct mutex            mutex;         /* all nested structures */
+
+	struct ceph_mdsmap      *mdsmap;
+	struct completion       safe_umount_waiters;
+	wait_queue_head_t       session_close_wq;
+	struct list_head        waiting_for_map;
+
+	struct ceph_mds_session **sessions;    /* NULL for mds if no session */
+	int                     max_sessions;  /* len of s_mds_sessions */
+	int                     stopping;      /* true if shutting down */
+
+	/*
+	 * snap_rwsem will cover cap linkage into snaprealms, and
+	 * realm snap contexts.  (later, we can do per-realm snap
+	 * contexts locks..)  the empty list contains realms with no
+	 * references (implying they contain no inodes with caps) that
+	 * should be destroyed.
+	 */
+	struct rw_semaphore     snap_rwsem;
+	struct rb_root          snap_realms;
+	struct list_head        snap_empty;
+	spinlock_t              snap_empty_lock;  /* protect snap_empty */
+
+	u64                    last_tid;      /* most recent mds request */
+	struct rb_root         request_tree;  /* pending mds requests */
+	struct delayed_work    delayed_work;  /* delayed work */
+	unsigned long    last_renew_caps;  /* last time we renewed our caps */
+	struct list_head cap_delay_list;   /* caps with delayed release */
+	spinlock_t       cap_delay_lock;   /* protects cap_delay_list */
+	struct list_head snap_flush_list;  /* cap_snaps ready to flush */
+	spinlock_t       snap_flush_lock;
+
+	u64               cap_flush_seq;
+	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 */
+	wait_queue_head_t cap_flushing_wq;
+
+	/*
+	 * Cap reservations
+	 *
+	 * Maintain a global pool of preallocated struct ceph_caps, referenced
+	 * by struct ceph_caps_reservations.  This ensures that we preallocate
+	 * memory needed to successfully process an MDS response.  (If an MDS
+	 * sends us cap information and we fail to process it, we will have
+	 * problems due to the client and MDS being out of sync.)
+	 *
+	 * Reservations are 'owned' by a ceph_cap_reservation context.
+	 */
+	spinlock_t	caps_list_lock;
+	struct		list_head caps_list; /* unused (reserved or
+						unreserved) */
+	int		caps_total_count;    /* total caps allocated */
+	int		caps_use_count;      /* in use */
+	int		caps_reserve_count;  /* unused, reserved */
+	int		caps_avail_count;    /* unused, unreserved */
+	int		caps_min_count;      /* keep at least this many
+						(unreserved) */
+	spinlock_t	  dentry_lru_lock;
+	struct list_head  dentry_lru;
+	int		  num_dentry;
+};
+
+extern const char *ceph_mds_op_name(int op);
+
+extern struct ceph_mds_session *
+__ceph_lookup_mds_session(struct ceph_mds_client *, int mds);
+
+static inline struct ceph_mds_session *
+ceph_get_mds_session(struct ceph_mds_session *s)
+{
+	atomic_inc(&s->s_ref);
+	return s;
+}
+
+extern void ceph_put_mds_session(struct ceph_mds_session *s);
+
+extern int ceph_send_msg_mds(struct ceph_mds_client *mdsc,
+			     struct ceph_msg *msg, int mds);
+
+extern int ceph_mdsc_init(struct ceph_fs_client *fsc);
+extern void ceph_mdsc_close_sessions(struct ceph_mds_client *mdsc);
+extern void ceph_mdsc_destroy(struct ceph_fs_client *fsc);
+
+extern void ceph_mdsc_sync(struct ceph_mds_client *mdsc);
+
+extern void ceph_mdsc_lease_release(struct ceph_mds_client *mdsc,
+				    struct inode *inode,
+				    struct dentry *dn);
+
+extern void ceph_invalidate_dir_request(struct ceph_mds_request *req);
+
+extern struct ceph_mds_request *
+ceph_mdsc_create_request(struct ceph_mds_client *mdsc, int op, int mode);
+extern void ceph_mdsc_submit_request(struct ceph_mds_client *mdsc,
+				     struct ceph_mds_request *req);
+extern int ceph_mdsc_do_request(struct ceph_mds_client *mdsc,
+				struct inode *dir,
+				struct ceph_mds_request *req);
+static inline void ceph_mdsc_get_request(struct ceph_mds_request *req)
+{
+	kref_get(&req->r_kref);
+}
+extern void ceph_mdsc_release_request(struct kref *kref);
+static inline void ceph_mdsc_put_request(struct ceph_mds_request *req)
+{
+	kref_put(&req->r_kref, ceph_mdsc_release_request);
+}
+
+extern int ceph_add_cap_releases(struct ceph_mds_client *mdsc,
+				 struct ceph_mds_session *session);
+extern void ceph_send_cap_releases(struct ceph_mds_client *mdsc,
+				   struct ceph_mds_session *session);
+
+extern void ceph_mdsc_pre_umount(struct ceph_mds_client *mdsc);
+
+extern char *ceph_mdsc_build_path(struct dentry *dentry, int *plen, u64 *base,
+				  int stop_on_nosnap);
+
+extern void __ceph_mdsc_drop_dentry_lease(struct dentry *dentry);
+extern void ceph_mdsc_lease_send_msg(struct ceph_mds_session *session,
+				     struct inode *inode,
+				     struct dentry *dentry, char action,
+				     u32 seq);
+
+extern void ceph_mdsc_handle_map(struct ceph_mds_client *mdsc,
+				 struct ceph_msg *msg);
+
+extern void ceph_mdsc_open_export_target_sessions(struct ceph_mds_client *mdsc,
+					  struct ceph_mds_session *session);
+
+#endif

fs/ceph/mdsmap.c

@@ -0,0 +1,185 @@
+#include <linux/ceph/ceph_debug.h>
+
+#include <linux/bug.h>
+#include <linux/err.h>
+#include <linux/random.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+
+#include <linux/ceph/mdsmap.h>
+#include <linux/ceph/messenger.h>
+#include <linux/ceph/decode.h>
+
+#include "super.h"
+
+
+/*
+ * choose a random mds that is "up" (i.e. has a state > 0), or -1.
+ */
+int ceph_mdsmap_get_random_mds(struct ceph_mdsmap *m)
+{
+	int n = 0;
+	int i;
+
+	/* special case for one mds */
+	if (1 == m->m_max_mds && m->m_info[0].state > 0)
+		return 0;
+
+	/* count */
+	for (i = 0; i < m->m_max_mds; i++)
+		if (m->m_info[i].state > 0)
+			n++;
+	if (n == 0)
+		return -1;
+
+	/* pick */
+	n = prandom_u32() % n;
+	i = 0;
+	for (i = 0; n > 0; i++, n--)
+		while (m->m_info[i].state <= 0)
+			i++;
+
+	return i;
+}
+
+/*
+ * Decode an MDS map
+ *
+ * Ignore any fields we don't care about (there are quite a few of
+ * them).
+ */
+struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end)
+{
+	struct ceph_mdsmap *m;
+	const void *start = *p;
+	int i, j, n;
+	int err = -EINVAL;
+	u16 version;
+
+	m = kzalloc(sizeof(*m), GFP_NOFS);
+	if (m == NULL)
+		return ERR_PTR(-ENOMEM);
+
+	ceph_decode_16_safe(p, end, version, bad);
+	if (version > 3) {
+		pr_warning("got mdsmap version %d > 3, failing", version);
+		goto bad;
+	}
+
+	ceph_decode_need(p, end, 8*sizeof(u32) + sizeof(u64), bad);
+	m->m_epoch = ceph_decode_32(p);
+	m->m_client_epoch = ceph_decode_32(p);
+	m->m_last_failure = ceph_decode_32(p);
+	m->m_root = ceph_decode_32(p);
+	m->m_session_timeout = ceph_decode_32(p);
+	m->m_session_autoclose = ceph_decode_32(p);
+	m->m_max_file_size = ceph_decode_64(p);
+	m->m_max_mds = ceph_decode_32(p);
+
+	m->m_info = kcalloc(m->m_max_mds, sizeof(*m->m_info), GFP_NOFS);
+	if (m->m_info == NULL)
+		goto badmem;
+
+	/* pick out active nodes from mds_info (state > 0) */
+	n = ceph_decode_32(p);
+	for (i = 0; i < n; i++) {
+		u64 global_id;
+		u32 namelen;
+		s32 mds, inc, state;
+		u64 state_seq;
+		u8 infoversion;
+		struct ceph_entity_addr addr;
+		u32 num_export_targets;
+		void *pexport_targets = NULL;
+		struct ceph_timespec laggy_since;
+
+		ceph_decode_need(p, end, sizeof(u64)*2 + 1 + sizeof(u32), bad);
+		global_id = ceph_decode_64(p);
+		infoversion = ceph_decode_8(p);
+		*p += sizeof(u64);
+		namelen = ceph_decode_32(p);  /* skip mds name */
+		*p += namelen;
+
+		ceph_decode_need(p, end,
+				 4*sizeof(u32) + sizeof(u64) +
+				 sizeof(addr) + sizeof(struct ceph_timespec),
+				 bad);
+		mds = ceph_decode_32(p);
+		inc = ceph_decode_32(p);
+		state = ceph_decode_32(p);
+		state_seq = ceph_decode_64(p);
+		ceph_decode_copy(p, &addr, sizeof(addr));
+		ceph_decode_addr(&addr);
+		ceph_decode_copy(p, &laggy_since, sizeof(laggy_since));
+		*p += sizeof(u32);
+		ceph_decode_32_safe(p, end, namelen, bad);
+		*p += namelen;
+		if (infoversion >= 2) {
+			ceph_decode_32_safe(p, end, num_export_targets, bad);
+			pexport_targets = *p;
+			*p += num_export_targets * sizeof(u32);
+		} else {
+			num_export_targets = 0;
+		}
+
+		dout("mdsmap_decode %d/%d %lld mds%d.%d %s %s\n",
+		     i+1, n, global_id, mds, inc,
+		     ceph_pr_addr(&addr.in_addr),
+		     ceph_mds_state_name(state));
+		if (mds >= 0 && mds < m->m_max_mds && state > 0) {
+			m->m_info[mds].global_id = global_id;
+			m->m_info[mds].state = state;
+			m->m_info[mds].addr = addr;
+			m->m_info[mds].laggy =
+				(laggy_since.tv_sec != 0 ||
+				 laggy_since.tv_nsec != 0);
+			m->m_info[mds].num_export_targets = num_export_targets;
+			if (num_export_targets) {
+				m->m_info[mds].export_targets =
+					kcalloc(num_export_targets, sizeof(u32),
+						GFP_NOFS);
+				for (j = 0; j < num_export_targets; j++)
+					m->m_info[mds].export_targets[j] =
+					       ceph_decode_32(&pexport_targets);
+			} else {
+				m->m_info[mds].export_targets = NULL;
+			}
+		}
+	}
+
+	/* pg_pools */
+	ceph_decode_32_safe(p, end, n, bad);
+	m->m_num_data_pg_pools = n;
+	m->m_data_pg_pools = kcalloc(n, sizeof(u64), GFP_NOFS);
+	if (!m->m_data_pg_pools)
+		goto badmem;
+	ceph_decode_need(p, end, sizeof(u64)*(n+1), bad);
+	for (i = 0; i < n; i++)
+		m->m_data_pg_pools[i] = ceph_decode_64(p);
+	m->m_cas_pg_pool = ceph_decode_64(p);
+
+	/* ok, we don't care about the rest. */
+	dout("mdsmap_decode success epoch %u\n", m->m_epoch);
+	return m;
+
+badmem:
+	err = -ENOMEM;
+bad:
+	pr_err("corrupt mdsmap\n");
+	print_hex_dump(KERN_DEBUG, "mdsmap: ",
+		       DUMP_PREFIX_OFFSET, 16, 1,
+		       start, end - start, true);
+	ceph_mdsmap_destroy(m);
+	return ERR_PTR(-EINVAL);
+}
+
+void ceph_mdsmap_destroy(struct ceph_mdsmap *m)
+{
+	int i;
+
+	for (i = 0; i < m->m_max_mds; i++)
+		kfree(m->m_info[i].export_targets);
+	kfree(m->m_info);
+	kfree(m->m_data_pg_pools);
+	kfree(m);
+}

fs/ceph/snap.c

@@ -0,0 +1,932 @@
+#include <linux/ceph/ceph_debug.h>
+
+#include <linux/sort.h>
+#include <linux/slab.h>
+
+#include "super.h"
+#include "mds_client.h"
+
+#include <linux/ceph/decode.h>
+
+/*
+ * Snapshots in ceph are driven in large part by cooperation from the
+ * client.  In contrast to local file systems or file servers that
+ * implement snapshots at a single point in the system, ceph's
+ * distributed access to storage requires clients to help decide
+ * whether a write logically occurs before or after a recently created
+ * snapshot.
+ *
+ * This provides a perfect instantanous client-wide snapshot.  Between
+ * clients, however, snapshots may appear to be applied at slightly
+ * different points in time, depending on delays in delivering the
+ * snapshot notification.
+ *
+ * Snapshots are _not_ file system-wide.  Instead, each snapshot
+ * applies to the subdirectory nested beneath some directory.  This
+ * effectively divides the hierarchy into multiple "realms," where all
+ * of the files contained by each realm share the same set of
+ * snapshots.  An individual realm's snap set contains snapshots
+ * explicitly created on that realm, as well as any snaps in its
+ * parent's snap set _after_ the point at which the parent became it's
+ * parent (due to, say, a rename).  Similarly, snaps from prior parents
+ * during the time intervals during which they were the parent are included.
+ *
+ * The client is spared most of this detail, fortunately... it must only
+ * maintains a hierarchy of realms reflecting the current parent/child
+ * realm relationship, and for each realm has an explicit list of snaps
+ * inherited from prior parents.
+ *
+ * A snap_realm struct is maintained for realms containing every inode
+ * with an open cap in the system.  (The needed snap realm information is
+ * provided by the MDS whenever a cap is issued, i.e., on open.)  A 'seq'
+ * version number is used to ensure that as realm parameters change (new
+ * snapshot, new parent, etc.) the client's realm hierarchy is updated.
+ *
+ * The realm hierarchy drives the generation of a 'snap context' for each
+ * realm, which simply lists the resulting set of snaps for the realm.  This
+ * is attached to any writes sent to OSDs.
+ */
+/*
+ * Unfortunately error handling is a bit mixed here.  If we get a snap
+ * update, but don't have enough memory to update our realm hierarchy,
+ * it's not clear what we can do about it (besides complaining to the
+ * console).
+ */
+
+
+/*
+ * increase ref count for the realm
+ *
+ * caller must hold snap_rwsem for write.
+ */
+void ceph_get_snap_realm(struct ceph_mds_client *mdsc,
+			 struct ceph_snap_realm *realm)
+{
+	dout("get_realm %p %d -> %d\n", realm,
+	     atomic_read(&realm->nref), atomic_read(&realm->nref)+1);
+	/*
+	 * since we _only_ increment realm refs or empty the empty
+	 * list with snap_rwsem held, adjusting the empty list here is
+	 * safe.  we do need to protect against concurrent empty list
+	 * additions, however.
+	 */
+	if (atomic_read(&realm->nref) == 0) {
+		spin_lock(&mdsc->snap_empty_lock);
+		list_del_init(&realm->empty_item);
+		spin_unlock(&mdsc->snap_empty_lock);
+	}
+
+	atomic_inc(&realm->nref);
+}
+
+static void __insert_snap_realm(struct rb_root *root,
+				struct ceph_snap_realm *new)
+{
+	struct rb_node **p = &root->rb_node;
+	struct rb_node *parent = NULL;
+	struct ceph_snap_realm *r = NULL;
+
+	while (*p) {
+		parent = *p;
+		r = rb_entry(parent, struct ceph_snap_realm, node);
+		if (new->ino < r->ino)
+			p = &(*p)->rb_left;
+		else if (new->ino > r->ino)
+			p = &(*p)->rb_right;
+		else
+			BUG();
+	}
+
+	rb_link_node(&new->node, parent, p);
+	rb_insert_color(&new->node, root);
+}
+
+/*
+ * create and get the realm rooted at @ino and bump its ref count.
+ *
+ * caller must hold snap_rwsem for write.
+ */
+static struct ceph_snap_realm *ceph_create_snap_realm(
+	struct ceph_mds_client *mdsc,
+	u64 ino)
+{
+	struct ceph_snap_realm *realm;
+
+	realm = kzalloc(sizeof(*realm), GFP_NOFS);
+	if (!realm)
+		return ERR_PTR(-ENOMEM);
+
+	atomic_set(&realm->nref, 0);    /* tree does not take a ref */
+	realm->ino = ino;
+	INIT_LIST_HEAD(&realm->children);
+	INIT_LIST_HEAD(&realm->child_item);
+	INIT_LIST_HEAD(&realm->empty_item);
+	INIT_LIST_HEAD(&realm->dirty_item);
+	INIT_LIST_HEAD(&realm->inodes_with_caps);
+	spin_lock_init(&realm->inodes_with_caps_lock);
+	__insert_snap_realm(&mdsc->snap_realms, realm);
+	dout("create_snap_realm %llx %p\n", realm->ino, realm);
+	return realm;
+}
+
+/*
+ * lookup the realm rooted at @ino.
+ *
+ * caller must hold snap_rwsem for write.
+ */
+struct ceph_snap_realm *ceph_lookup_snap_realm(struct ceph_mds_client *mdsc,
+					       u64 ino)
+{
+	struct rb_node *n = mdsc->snap_realms.rb_node;
+	struct ceph_snap_realm *r;
+
+	while (n) {
+		r = rb_entry(n, struct ceph_snap_realm, node);
+		if (ino < r->ino)
+			n = n->rb_left;
+		else if (ino > r->ino)
+			n = n->rb_right;
+		else {
+			dout("lookup_snap_realm %llx %p\n", r->ino, r);
+			return r;
+		}
+	}
+	return NULL;
+}
+
+static void __put_snap_realm(struct ceph_mds_client *mdsc,
+			     struct ceph_snap_realm *realm);
+
+/*
+ * called with snap_rwsem (write)
+ */
+static void __destroy_snap_realm(struct ceph_mds_client *mdsc,
+				 struct ceph_snap_realm *realm)
+{
+	dout("__destroy_snap_realm %p %llx\n", realm, realm->ino);
+
+	rb_erase(&realm->node, &mdsc->snap_realms);
+
+	if (realm->parent) {
+		list_del_init(&realm->child_item);
+		__put_snap_realm(mdsc, realm->parent);
+	}
+
+	kfree(realm->prior_parent_snaps);
+	kfree(realm->snaps);
+	ceph_put_snap_context(realm->cached_context);
+	kfree(realm);
+}
+
+/*
+ * caller holds snap_rwsem (write)
+ */
+static void __put_snap_realm(struct ceph_mds_client *mdsc,
+			     struct ceph_snap_realm *realm)
+{
+	dout("__put_snap_realm %llx %p %d -> %d\n", realm->ino, realm,
+	     atomic_read(&realm->nref), atomic_read(&realm->nref)-1);
+	if (atomic_dec_and_test(&realm->nref))
+		__destroy_snap_realm(mdsc, realm);
+}
+
+/*
+ * caller needn't hold any locks
+ */
+void ceph_put_snap_realm(struct ceph_mds_client *mdsc,
+			 struct ceph_snap_realm *realm)
+{
+	dout("put_snap_realm %llx %p %d -> %d\n", realm->ino, realm,
+	     atomic_read(&realm->nref), atomic_read(&realm->nref)-1);
+	if (!atomic_dec_and_test(&realm->nref))
+		return;
+
+	if (down_write_trylock(&mdsc->snap_rwsem)) {
+		__destroy_snap_realm(mdsc, realm);
+		up_write(&mdsc->snap_rwsem);
+	} else {
+		spin_lock(&mdsc->snap_empty_lock);
+		list_add(&realm->empty_item, &mdsc->snap_empty);
+		spin_unlock(&mdsc->snap_empty_lock);
+	}
+}
+
+/*
+ * Clean up any realms whose ref counts have dropped to zero.  Note
+ * that this does not include realms who were created but not yet
+ * used.
+ *
+ * Called under snap_rwsem (write)
+ */
+static void __cleanup_empty_realms(struct ceph_mds_client *mdsc)
+{
+	struct ceph_snap_realm *realm;
+
+	spin_lock(&mdsc->snap_empty_lock);
+	while (!list_empty(&mdsc->snap_empty)) {
+		realm = list_first_entry(&mdsc->snap_empty,
+				   struct ceph_snap_realm, empty_item);
+		list_del(&realm->empty_item);
+		spin_unlock(&mdsc->snap_empty_lock);
+		__destroy_snap_realm(mdsc, realm);
+		spin_lock(&mdsc->snap_empty_lock);
+	}
+	spin_unlock(&mdsc->snap_empty_lock);
+}
+
+void ceph_cleanup_empty_realms(struct ceph_mds_client *mdsc)
+{
+	down_write(&mdsc->snap_rwsem);
+	__cleanup_empty_realms(mdsc);
+	up_write(&mdsc->snap_rwsem);
+}
+
+/*
+ * adjust the parent realm of a given @realm.  adjust child list, and parent
+ * pointers, and ref counts appropriately.
+ *
+ * return true if parent was changed, 0 if unchanged, <0 on error.
+ *
+ * caller must hold snap_rwsem for write.
+ */
+static int adjust_snap_realm_parent(struct ceph_mds_client *mdsc,
+				    struct ceph_snap_realm *realm,
+				    u64 parentino)
+{
+	struct ceph_snap_realm *parent;
+
+	if (realm->parent_ino == parentino)
+		return 0;
+
+	parent = ceph_lookup_snap_realm(mdsc, parentino);
+	if (!parent) {
+		parent = ceph_create_snap_realm(mdsc, parentino);
+		if (IS_ERR(parent))
+			return PTR_ERR(parent);
+	}
+	dout("adjust_snap_realm_parent %llx %p: %llx %p -> %llx %p\n",
+	     realm->ino, realm, realm->parent_ino, realm->parent,
+	     parentino, parent);
+	if (realm->parent) {
+		list_del_init(&realm->child_item);
+		ceph_put_snap_realm(mdsc, realm->parent);
+	}
+	realm->parent_ino = parentino;
+	realm->parent = parent;
+	ceph_get_snap_realm(mdsc, parent);
+	list_add(&realm->child_item, &parent->children);
+	return 1;
+}
+
+
+static int cmpu64_rev(const void *a, const void *b)
+{
+	if (*(u64 *)a < *(u64 *)b)
+		return 1;
+	if (*(u64 *)a > *(u64 *)b)
+		return -1;
+	return 0;
+}
+
+/*
+ * build the snap context for a given realm.
+ */
+static int build_snap_context(struct ceph_snap_realm *realm)
+{
+	struct ceph_snap_realm *parent = realm->parent;
+	struct ceph_snap_context *snapc;
+	int err = 0;
+	u32 num = realm->num_prior_parent_snaps + realm->num_snaps;
+
+	/*
+	 * build parent context, if it hasn't been built.
+	 * conservatively estimate that all parent snaps might be
+	 * included by us.
+	 */
+	if (parent) {
+		if (!parent->cached_context) {
+			err = build_snap_context(parent);
+			if (err)
+				goto fail;
+		}
+		num += parent->cached_context->num_snaps;
+	}
+
+	/* do i actually need to update?  not if my context seq
+	   matches realm seq, and my parents' does to.  (this works
+	   because we rebuild_snap_realms() works _downward_ in
+	   hierarchy after each update.) */
+	if (realm->cached_context &&
+	    realm->cached_context->seq == realm->seq &&
+	    (!parent ||
+	     realm->cached_context->seq >= parent->cached_context->seq)) {
+		dout("build_snap_context %llx %p: %p seq %lld (%u snaps)"
+		     " (unchanged)\n",
+		     realm->ino, realm, realm->cached_context,
+		     realm->cached_context->seq,
+		     (unsigned int) realm->cached_context->num_snaps);
+		return 0;
+	}
+
+	/* alloc new snap context */
+	err = -ENOMEM;
+	if (num > (SIZE_MAX - sizeof(*snapc)) / sizeof(u64))
+		goto fail;
+	snapc = ceph_create_snap_context(num, GFP_NOFS);
+	if (!snapc)
+		goto fail;
+
+	/* build (reverse sorted) snap vector */
+	num = 0;
+	snapc->seq = realm->seq;
+	if (parent) {
+		u32 i;
+
+		/* include any of parent's snaps occurring _after_ my
+		   parent became my parent */
+		for (i = 0; i < parent->cached_context->num_snaps; i++)
+			if (parent->cached_context->snaps[i] >=
+			    realm->parent_since)
+				snapc->snaps[num++] =
+					parent->cached_context->snaps[i];
+		if (parent->cached_context->seq > snapc->seq)
+			snapc->seq = parent->cached_context->seq;
+	}
+	memcpy(snapc->snaps + num, realm->snaps,
+	       sizeof(u64)*realm->num_snaps);
+	num += realm->num_snaps;
+	memcpy(snapc->snaps + num, realm->prior_parent_snaps,
+	       sizeof(u64)*realm->num_prior_parent_snaps);
+	num += realm->num_prior_parent_snaps;
+
+	sort(snapc->snaps, num, sizeof(u64), cmpu64_rev, NULL);
+	snapc->num_snaps = num;
+	dout("build_snap_context %llx %p: %p seq %lld (%u snaps)\n",
+	     realm->ino, realm, snapc, snapc->seq,
+	     (unsigned int) snapc->num_snaps);
+
+	if (realm->cached_context)
+		ceph_put_snap_context(realm->cached_context);
+	realm->cached_context = snapc;
+	return 0;
+
+fail:
+	/*
+	 * if we fail, clear old (incorrect) cached_context... hopefully
+	 * we'll have better luck building it later
+	 */
+	if (realm->cached_context) {
+		ceph_put_snap_context(realm->cached_context);
+		realm->cached_context = NULL;
+	}
+	pr_err("build_snap_context %llx %p fail %d\n", realm->ino,
+	       realm, err);
+	return err;
+}
+
+/*
+ * rebuild snap context for the given realm and all of its children.
+ */
+static void rebuild_snap_realms(struct ceph_snap_realm *realm)
+{
+	struct ceph_snap_realm *child;
+
+	dout("rebuild_snap_realms %llx %p\n", realm->ino, realm);
+	build_snap_context(realm);
+
+	list_for_each_entry(child, &realm->children, child_item)
+		rebuild_snap_realms(child);
+}
+
+
+/*
+ * helper to allocate and decode an array of snapids.  free prior
+ * instance, if any.
+ */
+static int dup_array(u64 **dst, __le64 *src, u32 num)
+{
+	u32 i;
+
+	kfree(*dst);
+	if (num) {
+		*dst = kcalloc(num, sizeof(u64), GFP_NOFS);
+		if (!*dst)
+			return -ENOMEM;
+		for (i = 0; i < num; i++)
+			(*dst)[i] = get_unaligned_le64(src + i);
+	} else {
+		*dst = NULL;
+	}
+	return 0;
+}
+
+
+/*
+ * When a snapshot is applied, the size/mtime inode metadata is queued
+ * in a ceph_cap_snap (one for each snapshot) until writeback
+ * completes and the metadata can be flushed back to the MDS.
+ *
+ * However, if a (sync) write is currently in-progress when we apply
+ * the snapshot, we have to wait until the write succeeds or fails
+ * (and a final size/mtime is known).  In this case the
+ * cap_snap->writing = 1, and is said to be "pending."  When the write
+ * finishes, we __ceph_finish_cap_snap().
+ *
+ * Caller must hold snap_rwsem for read (i.e., the realm topology won't
+ * change).
+ */
+void ceph_queue_cap_snap(struct ceph_inode_info *ci)
+{
+	struct inode *inode = &ci->vfs_inode;
+	struct ceph_cap_snap *capsnap;
+	int used, dirty;
+
+	capsnap = kzalloc(sizeof(*capsnap), GFP_NOFS);
+	if (!capsnap) {
+		pr_err("ENOMEM allocating ceph_cap_snap on %p\n", inode);
+		return;
+	}
+
+	spin_lock(&ci->i_ceph_lock);
+	used = __ceph_caps_used(ci);
+	dirty = __ceph_caps_dirty(ci);
+
+	/*
+	 * If there is a write in progress, treat that as a dirty Fw,
+	 * even though it hasn't completed yet; by the time we finish
+	 * up this capsnap it will be.
+	 */
+	if (used & CEPH_CAP_FILE_WR)
+		dirty |= CEPH_CAP_FILE_WR;
+
+	if (__ceph_have_pending_cap_snap(ci)) {
+		/* there is no point in queuing multiple "pending" cap_snaps,
+		   as no new writes are allowed to start when pending, so any
+		   writes in progress now were started before the previous
+		   cap_snap.  lucky us. */
+		dout("queue_cap_snap %p already pending\n", inode);
+		kfree(capsnap);
+	} else if (dirty & (CEPH_CAP_AUTH_EXCL|CEPH_CAP_XATTR_EXCL|
+			    CEPH_CAP_FILE_EXCL|CEPH_CAP_FILE_WR)) {
+		struct ceph_snap_context *snapc = ci->i_head_snapc;
+
+		/*
+		 * if we are a sync write, we may need to go to the snaprealm
+		 * to get the current snapc.
+		 */
+		if (!snapc)
+			snapc = ci->i_snap_realm->cached_context;
+
+		dout("queue_cap_snap %p cap_snap %p queuing under %p %s\n",
+		     inode, capsnap, snapc, ceph_cap_string(dirty));
+		ihold(inode);
+
+		atomic_set(&capsnap->nref, 1);
+		capsnap->ci = ci;
+		INIT_LIST_HEAD(&capsnap->ci_item);
+		INIT_LIST_HEAD(&capsnap->flushing_item);
+
+		capsnap->follows = snapc->seq;
+		capsnap->issued = __ceph_caps_issued(ci, NULL);
+		capsnap->dirty = dirty;
+
+		capsnap->mode = inode->i_mode;
+		capsnap->uid = inode->i_uid;
+		capsnap->gid = inode->i_gid;
+
+		if (dirty & CEPH_CAP_XATTR_EXCL) {
+			__ceph_build_xattrs_blob(ci);
+			capsnap->xattr_blob =
+				ceph_buffer_get(ci->i_xattrs.blob);
+			capsnap->xattr_version = ci->i_xattrs.version;
+		} else {
+			capsnap->xattr_blob = NULL;
+			capsnap->xattr_version = 0;
+		}
+
+		/* dirty page count moved from _head to this cap_snap;
+		   all subsequent writes page dirties occur _after_ this
+		   snapshot. */
+		capsnap->dirty_pages = ci->i_wrbuffer_ref_head;
+		ci->i_wrbuffer_ref_head = 0;
+		capsnap->context = snapc;
+		ci->i_head_snapc =
+			ceph_get_snap_context(ci->i_snap_realm->cached_context);
+		dout(" new snapc is %p\n", ci->i_head_snapc);
+		list_add_tail(&capsnap->ci_item, &ci->i_cap_snaps);
+
+		if (used & CEPH_CAP_FILE_WR) {
+			dout("queue_cap_snap %p cap_snap %p snapc %p"
+			     " seq %llu used WR, now pending\n", inode,
+			     capsnap, snapc, snapc->seq);
+			capsnap->writing = 1;
+		} else {
+			/* note mtime, size NOW. */
+			__ceph_finish_cap_snap(ci, capsnap);
+		}
+	} else {
+		dout("queue_cap_snap %p nothing dirty|writing\n", inode);
+		kfree(capsnap);
+	}
+
+	spin_unlock(&ci->i_ceph_lock);
+}
+
+/*
+ * Finalize the size, mtime for a cap_snap.. that is, settle on final values
+ * to be used for the snapshot, to be flushed back to the mds.
+ *
+ * If capsnap can now be flushed, add to snap_flush list, and return 1.
+ *
+ * Caller must hold i_ceph_lock.
+ */
+int __ceph_finish_cap_snap(struct ceph_inode_info *ci,
+			    struct ceph_cap_snap *capsnap)
+{
+	struct inode *inode = &ci->vfs_inode;
+	struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
+
+	BUG_ON(capsnap->writing);
+	capsnap->size = inode->i_size;
+	capsnap->mtime = inode->i_mtime;
+	capsnap->atime = inode->i_atime;
+	capsnap->ctime = inode->i_ctime;
+	capsnap->time_warp_seq = ci->i_time_warp_seq;
+	if (capsnap->dirty_pages) {
+		dout("finish_cap_snap %p cap_snap %p snapc %p %llu %s s=%llu "
+		     "still has %d dirty pages\n", inode, capsnap,
+		     capsnap->context, capsnap->context->seq,
+		     ceph_cap_string(capsnap->dirty), capsnap->size,
+		     capsnap->dirty_pages);
+		return 0;
+	}
+	dout("finish_cap_snap %p cap_snap %p snapc %p %llu %s s=%llu\n",
+	     inode, capsnap, capsnap->context,
+	     capsnap->context->seq, ceph_cap_string(capsnap->dirty),
+	     capsnap->size);
+
+	spin_lock(&mdsc->snap_flush_lock);
+	list_add_tail(&ci->i_snap_flush_item, &mdsc->snap_flush_list);
+	spin_unlock(&mdsc->snap_flush_lock);
+	return 1;  /* caller may want to ceph_flush_snaps */
+}
+
+/*
+ * Queue cap_snaps for snap writeback for this realm and its children.
+ * Called under snap_rwsem, so realm topology won't change.
+ */
+static void queue_realm_cap_snaps(struct ceph_snap_realm *realm)
+{
+	struct ceph_inode_info *ci;
+	struct inode *lastinode = NULL;
+	struct ceph_snap_realm *child;
+
+	dout("queue_realm_cap_snaps %p %llx inodes\n", realm, realm->ino);
+
+	spin_lock(&realm->inodes_with_caps_lock);
+	list_for_each_entry(ci, &realm->inodes_with_caps,
+			    i_snap_realm_item) {
+		struct inode *inode = igrab(&ci->vfs_inode);
+		if (!inode)
+			continue;
+		spin_unlock(&realm->inodes_with_caps_lock);
+		if (lastinode)
+			iput(lastinode);
+		lastinode = inode;
+		ceph_queue_cap_snap(ci);
+		spin_lock(&realm->inodes_with_caps_lock);
+	}
+	spin_unlock(&realm->inodes_with_caps_lock);
+	if (lastinode)
+		iput(lastinode);
+
+	list_for_each_entry(child, &realm->children, child_item) {
+		dout("queue_realm_cap_snaps %p %llx queue child %p %llx\n",
+		     realm, realm->ino, child, child->ino);
+		list_del_init(&child->dirty_item);
+		list_add(&child->dirty_item, &realm->dirty_item);
+	}
+
+	list_del_init(&realm->dirty_item);
+	dout("queue_realm_cap_snaps %p %llx done\n", realm, realm->ino);
+}
+
+/*
+ * Parse and apply a snapblob "snap trace" from the MDS.  This specifies
+ * the snap realm parameters from a given realm and all of its ancestors,
+ * up to the root.
+ *
+ * Caller must hold snap_rwsem for write.
+ */
+int ceph_update_snap_trace(struct ceph_mds_client *mdsc,
+			   void *p, void *e, bool deletion)
+{
+	struct ceph_mds_snap_realm *ri;    /* encoded */
+	__le64 *snaps;                     /* encoded */
+	__le64 *prior_parent_snaps;        /* encoded */
+	struct ceph_snap_realm *realm;
+	int invalidate = 0;
+	int err = -ENOMEM;
+	LIST_HEAD(dirty_realms);
+
+	dout("update_snap_trace deletion=%d\n", deletion);
+more:
+	ceph_decode_need(&p, e, sizeof(*ri), bad);
+	ri = p;
+	p += sizeof(*ri);
+	ceph_decode_need(&p, e, sizeof(u64)*(le32_to_cpu(ri->num_snaps) +
+			    le32_to_cpu(ri->num_prior_parent_snaps)), bad);
+	snaps = p;
+	p += sizeof(u64) * le32_to_cpu(ri->num_snaps);
+	prior_parent_snaps = p;
+	p += sizeof(u64) * le32_to_cpu(ri->num_prior_parent_snaps);
+
+	realm = ceph_lookup_snap_realm(mdsc, le64_to_cpu(ri->ino));
+	if (!realm) {
+		realm = ceph_create_snap_realm(mdsc, le64_to_cpu(ri->ino));
+		if (IS_ERR(realm)) {
+			err = PTR_ERR(realm);
+			goto fail;
+		}
+	}
+
+	/* ensure the parent is correct */
+	err = adjust_snap_realm_parent(mdsc, realm, le64_to_cpu(ri->parent));
+	if (err < 0)
+		goto fail;
+	invalidate += err;
+
+	if (le64_to_cpu(ri->seq) > realm->seq) {
+		dout("update_snap_trace updating %llx %p %lld -> %lld\n",
+		     realm->ino, realm, realm->seq, le64_to_cpu(ri->seq));
+		/* update realm parameters, snap lists */
+		realm->seq = le64_to_cpu(ri->seq);
+		realm->created = le64_to_cpu(ri->created);
+		realm->parent_since = le64_to_cpu(ri->parent_since);
+
+		realm->num_snaps = le32_to_cpu(ri->num_snaps);
+		err = dup_array(&realm->snaps, snaps, realm->num_snaps);
+		if (err < 0)
+			goto fail;
+
+		realm->num_prior_parent_snaps =
+			le32_to_cpu(ri->num_prior_parent_snaps);
+		err = dup_array(&realm->prior_parent_snaps, prior_parent_snaps,
+				realm->num_prior_parent_snaps);
+		if (err < 0)
+			goto fail;
+
+		/* queue realm for cap_snap creation */
+		list_add(&realm->dirty_item, &dirty_realms);
+
+		invalidate = 1;
+	} else if (!realm->cached_context) {
+		dout("update_snap_trace %llx %p seq %lld new\n",
+		     realm->ino, realm, realm->seq);
+		invalidate = 1;
+	} else {
+		dout("update_snap_trace %llx %p seq %lld unchanged\n",
+		     realm->ino, realm, realm->seq);
+	}
+
+	dout("done with %llx %p, invalidated=%d, %p %p\n", realm->ino,
+	     realm, invalidate, p, e);
+
+	if (p < e)
+		goto more;
+
+	/* invalidate when we reach the _end_ (root) of the trace */
+	if (invalidate)
+		rebuild_snap_realms(realm);
+
+	/*
+	 * queue cap snaps _after_ we've built the new snap contexts,
+	 * so that i_head_snapc can be set appropriately.
+	 */
+	while (!list_empty(&dirty_realms)) {
+		realm = list_first_entry(&dirty_realms, struct ceph_snap_realm,
+					 dirty_item);
+		queue_realm_cap_snaps(realm);
+	}
+
+	__cleanup_empty_realms(mdsc);
+	return 0;
+
+bad:
+	err = -EINVAL;
+fail:
+	pr_err("update_snap_trace error %d\n", err);
+	return err;
+}
+
+
+/*
+ * Send any cap_snaps that are queued for flush.  Try to carry
+ * s_mutex across multiple snap flushes to avoid locking overhead.
+ *
+ * Caller holds no locks.
+ */
+static void flush_snaps(struct ceph_mds_client *mdsc)
+{
+	struct ceph_inode_info *ci;
+	struct inode *inode;
+	struct ceph_mds_session *session = NULL;
+
+	dout("flush_snaps\n");
+	spin_lock(&mdsc->snap_flush_lock);
+	while (!list_empty(&mdsc->snap_flush_list)) {
+		ci = list_first_entry(&mdsc->snap_flush_list,
+				struct ceph_inode_info, i_snap_flush_item);
+		inode = &ci->vfs_inode;
+		ihold(inode);
+		spin_unlock(&mdsc->snap_flush_lock);
+		spin_lock(&ci->i_ceph_lock);
+		__ceph_flush_snaps(ci, &session, 0);
+		spin_unlock(&ci->i_ceph_lock);
+		iput(inode);
+		spin_lock(&mdsc->snap_flush_lock);
+	}
+	spin_unlock(&mdsc->snap_flush_lock);
+
+	if (session) {
+		mutex_unlock(&session->s_mutex);
+		ceph_put_mds_session(session);
+	}
+	dout("flush_snaps done\n");
+}
+
+
+/*
+ * Handle a snap notification from the MDS.
+ *
+ * This can take two basic forms: the simplest is just a snap creation
+ * or deletion notification on an existing realm.  This should update the
+ * realm and its children.
+ *
+ * The more difficult case is realm creation, due to snap creation at a
+ * new point in the file hierarchy, or due to a rename that moves a file or
+ * directory into another realm.
+ */
+void ceph_handle_snap(struct ceph_mds_client *mdsc,
+		      struct ceph_mds_session *session,
+		      struct ceph_msg *msg)
+{
+	struct super_block *sb = mdsc->fsc->sb;
+	int mds = session->s_mds;
+	u64 split;
+	int op;
+	int trace_len;
+	struct ceph_snap_realm *realm = NULL;
+	void *p = msg->front.iov_base;
+	void *e = p + msg->front.iov_len;
+	struct ceph_mds_snap_head *h;
+	int num_split_inos, num_split_realms;
+	__le64 *split_inos = NULL, *split_realms = NULL;
+	int i;
+	int locked_rwsem = 0;
+
+	/* decode */
+	if (msg->front.iov_len < sizeof(*h))
+		goto bad;
+	h = p;
+	op = le32_to_cpu(h->op);
+	split = le64_to_cpu(h->split);   /* non-zero if we are splitting an
+					  * existing realm */
+	num_split_inos = le32_to_cpu(h->num_split_inos);
+	num_split_realms = le32_to_cpu(h->num_split_realms);
+	trace_len = le32_to_cpu(h->trace_len);
+	p += sizeof(*h);
+
+	dout("handle_snap from mds%d op %s split %llx tracelen %d\n", mds,
+	     ceph_snap_op_name(op), split, trace_len);
+
+	mutex_lock(&session->s_mutex);
+	session->s_seq++;
+	mutex_unlock(&session->s_mutex);
+
+	down_write(&mdsc->snap_rwsem);
+	locked_rwsem = 1;
+
+	if (op == CEPH_SNAP_OP_SPLIT) {
+		struct ceph_mds_snap_realm *ri;
+
+		/*
+		 * A "split" breaks part of an existing realm off into
+		 * a new realm.  The MDS provides a list of inodes
+		 * (with caps) and child realms that belong to the new
+		 * child.
+		 */
+		split_inos = p;
+		p += sizeof(u64) * num_split_inos;
+		split_realms = p;
+		p += sizeof(u64) * num_split_realms;
+		ceph_decode_need(&p, e, sizeof(*ri), bad);
+		/* we will peek at realm info here, but will _not_
+		 * advance p, as the realm update will occur below in
+		 * ceph_update_snap_trace. */
+		ri = p;
+
+		realm = ceph_lookup_snap_realm(mdsc, split);
+		if (!realm) {
+			realm = ceph_create_snap_realm(mdsc, split);
+			if (IS_ERR(realm))
+				goto out;
+		}
+		ceph_get_snap_realm(mdsc, realm);
+
+		dout("splitting snap_realm %llx %p\n", realm->ino, realm);
+		for (i = 0; i < num_split_inos; i++) {
+			struct ceph_vino vino = {
+				.ino = le64_to_cpu(split_inos[i]),
+				.snap = CEPH_NOSNAP,
+			};
+			struct inode *inode = ceph_find_inode(sb, vino);
+			struct ceph_inode_info *ci;
+			struct ceph_snap_realm *oldrealm;
+
+			if (!inode)
+				continue;
+			ci = ceph_inode(inode);
+
+			spin_lock(&ci->i_ceph_lock);
+			if (!ci->i_snap_realm)
+				goto skip_inode;
+			/*
+			 * If this inode belongs to a realm that was
+			 * created after our new realm, we experienced
+			 * a race (due to another split notifications
+			 * arriving from a different MDS).  So skip
+			 * this inode.
+			 */
+			if (ci->i_snap_realm->created >
+			    le64_to_cpu(ri->created)) {
+				dout(" leaving %p in newer realm %llx %p\n",
+				     inode, ci->i_snap_realm->ino,
+				     ci->i_snap_realm);
+				goto skip_inode;
+			}
+			dout(" will move %p to split realm %llx %p\n",
+			     inode, realm->ino, realm);
+			/*
+			 * Move the inode to the new realm
+			 */
+			spin_lock(&realm->inodes_with_caps_lock);
+			list_del_init(&ci->i_snap_realm_item);
+			list_add(&ci->i_snap_realm_item,
+				 &realm->inodes_with_caps);
+			oldrealm = ci->i_snap_realm;
+			ci->i_snap_realm = realm;
+			spin_unlock(&realm->inodes_with_caps_lock);
+			spin_unlock(&ci->i_ceph_lock);
+
+			ceph_get_snap_realm(mdsc, realm);
+			ceph_put_snap_realm(mdsc, oldrealm);
+
+			iput(inode);
+			continue;
+
+skip_inode:
+			spin_unlock(&ci->i_ceph_lock);
+			iput(inode);
+		}
+
+		/* we may have taken some of the old realm's children. */
+		for (i = 0; i < num_split_realms; i++) {
+			struct ceph_snap_realm *child =
+				ceph_lookup_snap_realm(mdsc,
+					   le64_to_cpu(split_realms[i]));
+			if (!child)
+				continue;
+			adjust_snap_realm_parent(mdsc, child, realm->ino);
+		}
+	}
+
+	/*
+	 * update using the provided snap trace. if we are deleting a
+	 * snap, we can avoid queueing cap_snaps.
+	 */
+	ceph_update_snap_trace(mdsc, p, e,
+			       op == CEPH_SNAP_OP_DESTROY);
+
+	if (op == CEPH_SNAP_OP_SPLIT)
+		/* we took a reference when we created the realm, above */
+		ceph_put_snap_realm(mdsc, realm);
+
+	__cleanup_empty_realms(mdsc);
+
+	up_write(&mdsc->snap_rwsem);
+
+	flush_snaps(mdsc);
+	return;
+
+bad:
+	pr_err("corrupt snap message from mds%d\n", mds);
+	ceph_msg_dump(msg);
+out:
+	if (locked_rwsem)
+		up_write(&mdsc->snap_rwsem);
+	return;
+}
+
+
+

fs/ceph/strings.c

@@ -0,0 +1,121 @@
+/*
+ * Ceph fs string constants
+ */
+#include <linux/module.h>
+#include <linux/ceph/types.h>
+
+
+const char *ceph_mds_state_name(int s)
+{
+	switch (s) {
+		/* down and out */
+	case CEPH_MDS_STATE_DNE:        return "down:dne";
+	case CEPH_MDS_STATE_STOPPED:    return "down:stopped";
+		/* up and out */
+	case CEPH_MDS_STATE_BOOT:       return "up:boot";
+	case CEPH_MDS_STATE_STANDBY:    return "up:standby";
+	case CEPH_MDS_STATE_STANDBY_REPLAY:    return "up:standby-replay";
+	case CEPH_MDS_STATE_REPLAYONCE: return "up:oneshot-replay";
+	case CEPH_MDS_STATE_CREATING:   return "up:creating";
+	case CEPH_MDS_STATE_STARTING:   return "up:starting";
+		/* up and in */
+	case CEPH_MDS_STATE_REPLAY:     return "up:replay";
+	case CEPH_MDS_STATE_RESOLVE:    return "up:resolve";
+	case CEPH_MDS_STATE_RECONNECT:  return "up:reconnect";
+	case CEPH_MDS_STATE_REJOIN:     return "up:rejoin";
+	case CEPH_MDS_STATE_CLIENTREPLAY: return "up:clientreplay";
+	case CEPH_MDS_STATE_ACTIVE:     return "up:active";
+	case CEPH_MDS_STATE_STOPPING:   return "up:stopping";
+	}
+	return "???";
+}
+
+const char *ceph_session_op_name(int op)
+{
+	switch (op) {
+	case CEPH_SESSION_REQUEST_OPEN: return "request_open";
+	case CEPH_SESSION_OPEN: return "open";
+	case CEPH_SESSION_REQUEST_CLOSE: return "request_close";
+	case CEPH_SESSION_CLOSE: return "close";
+	case CEPH_SESSION_REQUEST_RENEWCAPS: return "request_renewcaps";
+	case CEPH_SESSION_RENEWCAPS: return "renewcaps";
+	case CEPH_SESSION_STALE: return "stale";
+	case CEPH_SESSION_RECALL_STATE: return "recall_state";
+	}
+	return "???";
+}
+
+const char *ceph_mds_op_name(int op)
+{
+	switch (op) {
+	case CEPH_MDS_OP_LOOKUP:  return "lookup";
+	case CEPH_MDS_OP_LOOKUPHASH:  return "lookuphash";
+	case CEPH_MDS_OP_LOOKUPPARENT:  return "lookupparent";
+	case CEPH_MDS_OP_LOOKUPINO:  return "lookupino";
+	case CEPH_MDS_OP_GETATTR:  return "getattr";
+	case CEPH_MDS_OP_SETXATTR: return "setxattr";
+	case CEPH_MDS_OP_SETATTR: return "setattr";
+	case CEPH_MDS_OP_RMXATTR: return "rmxattr";
+	case CEPH_MDS_OP_SETLAYOUT: return "setlayou";
+	case CEPH_MDS_OP_SETDIRLAYOUT: return "setdirlayout";
+	case CEPH_MDS_OP_READDIR: return "readdir";
+	case CEPH_MDS_OP_MKNOD: return "mknod";
+	case CEPH_MDS_OP_LINK: return "link";
+	case CEPH_MDS_OP_UNLINK: return "unlink";
+	case CEPH_MDS_OP_RENAME: return "rename";
+	case CEPH_MDS_OP_MKDIR: return "mkdir";
+	case CEPH_MDS_OP_RMDIR: return "rmdir";
+	case CEPH_MDS_OP_SYMLINK: return "symlink";
+	case CEPH_MDS_OP_CREATE: return "create";
+	case CEPH_MDS_OP_OPEN: return "open";
+	case CEPH_MDS_OP_LOOKUPSNAP: return "lookupsnap";
+	case CEPH_MDS_OP_LSSNAP: return "lssnap";
+	case CEPH_MDS_OP_MKSNAP: return "mksnap";
+	case CEPH_MDS_OP_RMSNAP: return "rmsnap";
+	case CEPH_MDS_OP_SETFILELOCK: return "setfilelock";
+	case CEPH_MDS_OP_GETFILELOCK: return "getfilelock";
+	}
+	return "???";
+}
+
+const char *ceph_cap_op_name(int op)
+{
+	switch (op) {
+	case CEPH_CAP_OP_GRANT: return "grant";
+	case CEPH_CAP_OP_REVOKE: return "revoke";
+	case CEPH_CAP_OP_TRUNC: return "trunc";
+	case CEPH_CAP_OP_EXPORT: return "export";
+	case CEPH_CAP_OP_IMPORT: return "import";
+	case CEPH_CAP_OP_UPDATE: return "update";
+	case CEPH_CAP_OP_DROP: return "drop";
+	case CEPH_CAP_OP_FLUSH: return "flush";
+	case CEPH_CAP_OP_FLUSH_ACK: return "flush_ack";
+	case CEPH_CAP_OP_FLUSHSNAP: return "flushsnap";
+	case CEPH_CAP_OP_FLUSHSNAP_ACK: return "flushsnap_ack";
+	case CEPH_CAP_OP_RELEASE: return "release";
+	case CEPH_CAP_OP_RENEW: return "renew";
+	}
+	return "???";
+}
+
+const char *ceph_lease_op_name(int o)
+{
+	switch (o) {
+	case CEPH_MDS_LEASE_REVOKE: return "revoke";
+	case CEPH_MDS_LEASE_RELEASE: return "release";
+	case CEPH_MDS_LEASE_RENEW: return "renew";
+	case CEPH_MDS_LEASE_REVOKE_ACK: return "revoke_ack";
+	}
+	return "???";
+}
+
+const char *ceph_snap_op_name(int o)
+{
+	switch (o) {
+	case CEPH_SNAP_OP_UPDATE: return "update";
+	case CEPH_SNAP_OP_CREATE: return "create";
+	case CEPH_SNAP_OP_DESTROY: return "destroy";
+	case CEPH_SNAP_OP_SPLIT: return "split";
+	}
+	return "???";
+}

fs/ceph/super.h

@@ -0,0 +1,838 @@
+#ifndef _FS_CEPH_SUPER_H
+#define _FS_CEPH_SUPER_H
+
+#include <linux/ceph/ceph_debug.h>
+
+#include <asm/unaligned.h>
+#include <linux/backing-dev.h>
+#include <linux/completion.h>
+#include <linux/exportfs.h>
+#include <linux/fs.h>
+#include <linux/mempool.h>
+#include <linux/pagemap.h>
+#include <linux/wait.h>
+#include <linux/writeback.h>
+#include <linux/slab.h>
+
+#include <linux/ceph/libceph.h>
+
+/* f_type in struct statfs */
+#define CEPH_SUPER_MAGIC 0x00c36400
+
+/* large granularity for statfs utilization stats to facilitate
+ * large volume sizes on 32-bit machines. */
+#define CEPH_BLOCK_SHIFT   22  /* 4 MB */
+#define CEPH_BLOCK         (1 << CEPH_BLOCK_SHIFT)
+
+#define CEPH_MOUNT_OPT_DIRSTAT         (1<<4) /* `cat dirname` for stats */
+#define CEPH_MOUNT_OPT_RBYTES          (1<<5) /* dir st_bytes = rbytes */
+#define CEPH_MOUNT_OPT_NOASYNCREADDIR  (1<<7) /* no dcache readdir */
+#define CEPH_MOUNT_OPT_INO32           (1<<8) /* 32 bit inos */
+#define CEPH_MOUNT_OPT_DCACHE          (1<<9) /* use dcache for readdir etc */
+
+#define CEPH_MOUNT_OPT_DEFAULT    (CEPH_MOUNT_OPT_RBYTES)
+
+#define ceph_set_mount_opt(fsc, opt) \
+	(fsc)->mount_options->flags |= CEPH_MOUNT_OPT_##opt;
+#define ceph_test_mount_opt(fsc, opt) \
+	(!!((fsc)->mount_options->flags & CEPH_MOUNT_OPT_##opt))
+
+#define CEPH_RSIZE_DEFAULT             0           /* max read size */
+#define CEPH_RASIZE_DEFAULT            (8192*1024) /* readahead */
+#define CEPH_MAX_READDIR_DEFAULT        1024
+#define CEPH_MAX_READDIR_BYTES_DEFAULT  (512*1024)
+#define CEPH_SNAPDIRNAME_DEFAULT        ".snap"
+
+struct ceph_mount_options {
+	int flags;
+	int sb_flags;
+
+	int wsize;            /* max write size */
+	int rsize;            /* max read size */
+	int rasize;           /* max readahead */
+	int congestion_kb;    /* max writeback in flight */
+	int caps_wanted_delay_min, caps_wanted_delay_max;
+	int cap_release_safety;
+	int max_readdir;       /* max readdir result (entires) */
+	int max_readdir_bytes; /* max readdir result (bytes) */
+
+	/*
+	 * everything above this point can be memcmp'd; everything below
+	 * is handled in compare_mount_options()
+	 */
+
+	char *snapdir_name;   /* default ".snap" */
+};
+
+struct ceph_fs_client {
+	struct super_block *sb;
+
+	struct ceph_mount_options *mount_options;
+	struct ceph_client *client;
+
+	unsigned long mount_state;
+	int min_caps;                  /* min caps i added */
+
+	struct ceph_mds_client *mdsc;
+
+	/* writeback */
+	mempool_t *wb_pagevec_pool;
+	struct workqueue_struct *wb_wq;
+	struct workqueue_struct *pg_inv_wq;
+	struct workqueue_struct *trunc_wq;
+	atomic_long_t writeback_count;
+
+	struct backing_dev_info backing_dev_info;
+
+#ifdef CONFIG_DEBUG_FS
+	struct dentry *debugfs_dentry_lru, *debugfs_caps;
+	struct dentry *debugfs_congestion_kb;
+	struct dentry *debugfs_bdi;
+	struct dentry *debugfs_mdsc, *debugfs_mdsmap;
+#endif
+};
+
+
+/*
+ * File i/o capability.  This tracks shared state with the metadata
+ * server that allows us to cache or writeback attributes or to read
+ * and write data.  For any given inode, we should have one or more
+ * capabilities, one issued by each metadata server, and our
+ * cumulative access is the OR of all issued capabilities.
+ *
+ * Each cap is referenced by the inode's i_caps rbtree and by per-mds
+ * session capability lists.
+ */
+struct ceph_cap {
+	struct ceph_inode_info *ci;
+	struct rb_node ci_node;          /* per-ci cap tree */
+	struct ceph_mds_session *session;
+	struct list_head session_caps;   /* per-session caplist */
+	int mds;
+	u64 cap_id;       /* unique cap id (mds provided) */
+	int issued;       /* latest, from the mds */
+	int implemented;  /* implemented superset of issued (for revocation) */
+	int mds_wanted;
+	u32 seq, issue_seq, mseq;
+	u32 cap_gen;      /* active/stale cycle */
+	unsigned long last_used;
+	struct list_head caps_item;
+};
+
+#define CHECK_CAPS_NODELAY    1  /* do not delay any further */
+#define CHECK_CAPS_AUTHONLY   2  /* only check auth cap */
+#define CHECK_CAPS_FLUSH      4  /* flush any dirty caps */
+
+/*
+ * Snapped cap state that is pending flush to mds.  When a snapshot occurs,
+ * we first complete any in-process sync writes and writeback any dirty
+ * data before flushing the snapped state (tracked here) back to the MDS.
+ */
+struct ceph_cap_snap {
+	atomic_t nref;
+	struct ceph_inode_info *ci;
+	struct list_head ci_item, flushing_item;
+
+	u64 follows, flush_tid;
+	int issued, dirty;
+	struct ceph_snap_context *context;
+
+	umode_t mode;
+	kuid_t uid;
+	kgid_t gid;
+
+	struct ceph_buffer *xattr_blob;
+	u64 xattr_version;
+
+	u64 size;
+	struct timespec mtime, atime, ctime;
+	u64 time_warp_seq;
+	int writing;   /* a sync write is still in progress */
+	int dirty_pages;     /* dirty pages awaiting writeback */
+};
+
+static inline void ceph_put_cap_snap(struct ceph_cap_snap *capsnap)
+{
+	if (atomic_dec_and_test(&capsnap->nref)) {
+		if (capsnap->xattr_blob)
+			ceph_buffer_put(capsnap->xattr_blob);
+		kfree(capsnap);
+	}
+}
+
+/*
+ * The frag tree describes how a directory is fragmented, potentially across
+ * multiple metadata servers.  It is also used to indicate points where
+ * metadata authority is delegated, and whether/where metadata is replicated.
+ *
+ * A _leaf_ frag will be present in the i_fragtree IFF there is
+ * delegation info.  That is, if mds >= 0 || ndist > 0.
+ */
+#define CEPH_MAX_DIRFRAG_REP 4
+
+struct ceph_inode_frag {
+	struct rb_node node;
+
+	/* fragtree state */
+	u32 frag;
+	int split_by;         /* i.e. 2^(split_by) children */
+
+	/* delegation and replication info */
+	int mds;              /* -1 if same authority as parent */
+	int ndist;            /* >0 if replicated */
+	int dist[CEPH_MAX_DIRFRAG_REP];
+};
+
+/*
+ * We cache inode xattrs as an encoded blob until they are first used,
+ * at which point we parse them into an rbtree.
+ */
+struct ceph_inode_xattr {
+	struct rb_node node;
+
+	const char *name;
+	int name_len;
+	const char *val;
+	int val_len;
+	int dirty;
+
+	int should_free_name;
+	int should_free_val;
+};
+
+/*
+ * Ceph dentry state
+ */
+struct ceph_dentry_info {
+	struct ceph_mds_session *lease_session;
+	u32 lease_gen, lease_shared_gen;
+	u32 lease_seq;
+	unsigned long lease_renew_after, lease_renew_from;
+	struct list_head lru;
+	struct dentry *dentry;
+	u64 time;
+	u64 offset;
+};
+
+struct ceph_inode_xattrs_info {
+	/*
+	 * (still encoded) xattr blob. we avoid the overhead of parsing
+	 * this until someone actually calls getxattr, etc.
+	 *
+	 * blob->vec.iov_len == 4 implies there are no xattrs; blob ==
+	 * NULL means we don't know.
+	*/
+	struct ceph_buffer *blob, *prealloc_blob;
+
+	struct rb_root index;
+	bool dirty;
+	int count;
+	int names_size;
+	int vals_size;
+	u64 version, index_version;
+};
+
+/*
+ * Ceph inode.
+ */
+struct ceph_inode_info {
+	struct ceph_vino i_vino;   /* ceph ino + snap */
+
+	spinlock_t i_ceph_lock;
+
+	u64 i_version;
+	u32 i_time_warp_seq;
+
+	unsigned i_ceph_flags;
+	atomic_t i_release_count;
+	atomic_t i_complete_count;
+
+	struct ceph_dir_layout i_dir_layout;
+	struct ceph_file_layout i_layout;
+	char *i_symlink;
+
+	/* for dirs */
+	struct timespec i_rctime;
+	u64 i_rbytes, i_rfiles, i_rsubdirs;
+	u64 i_files, i_subdirs;
+	u64 i_max_offset;  /* largest readdir offset, set with complete dir */
+
+	struct rb_root i_fragtree;
+	struct mutex i_fragtree_mutex;
+
+	struct ceph_inode_xattrs_info i_xattrs;
+
+	/* capabilities.  protected _both_ by i_ceph_lock and cap->session's
+	 * s_mutex. */
+	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;
+	u64 i_cap_flush_seq;
+	/* 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. */
+	u16 i_cap_flush_last_tid, i_cap_flush_tid[CEPH_CAP_BITS];
+	wait_queue_head_t i_cap_wq;      /* threads waiting on a capability */
+	unsigned long i_hold_caps_min; /* jiffies */
+	unsigned long i_hold_caps_max; /* jiffies */
+	struct list_head i_cap_delay_list;  /* for delayed cap release to mds */
+	int i_cap_exporting_mds;         /* to handle cap migration between */
+	unsigned i_cap_exporting_mseq;   /*  mds's. */
+	unsigned i_cap_exporting_issued;
+	struct ceph_cap_reservation i_cap_migration_resv;
+	struct list_head i_cap_snaps;   /* snapped state pending flush to mds */
+	struct ceph_snap_context *i_head_snapc;  /* set if wr_buffer_head > 0 or
+						    dirty|flushing caps */
+	unsigned i_snap_caps;           /* cap bits for snapped files */
+
+	int i_nr_by_mode[CEPH_FILE_MODE_NUM];  /* open file counts */
+
+	u32 i_truncate_seq;        /* last truncate to smaller size */
+	u64 i_truncate_size;       /*  and the size we last truncated down to */
+	int i_truncate_pending;    /*  still need to call vmtruncate */
+
+	u64 i_max_size;            /* max file size authorized by mds */
+	u64 i_reported_size; /* (max_)size reported to or requested of mds */
+	u64 i_wanted_max_size;     /* offset we'd like to write too */
+	u64 i_requested_max_size;  /* max_size we've requested */
+
+	/* held references to caps */
+	int i_pin_ref;
+	int i_rd_ref, i_rdcache_ref, i_wr_ref, i_wb_ref;
+	int i_wrbuffer_ref, i_wrbuffer_ref_head;
+	u32 i_shared_gen;       /* increment each time we get FILE_SHARED */
+	u32 i_rdcache_gen;      /* incremented each time we get FILE_CACHE. */
+	u32 i_rdcache_revoking; /* RDCACHE gen to async invalidate, if any */
+
+	struct list_head i_unsafe_writes; /* uncommitted sync writes */
+	struct list_head i_unsafe_dirops; /* uncommitted mds dir ops */
+	spinlock_t i_unsafe_lock;
+
+	struct ceph_snap_realm *i_snap_realm; /* snap realm (if caps) */
+	int i_snap_realm_counter; /* snap realm (if caps) */
+	struct list_head i_snap_realm_item;
+	struct list_head i_snap_flush_item;
+
+	struct work_struct i_wb_work;  /* writeback work */
+	struct work_struct i_pg_inv_work;  /* page invalidation work */
+
+	struct work_struct i_vmtruncate_work;
+
+	struct inode vfs_inode; /* at end */
+};
+
+static inline struct ceph_inode_info *ceph_inode(struct inode *inode)
+{
+	return container_of(inode, struct ceph_inode_info, vfs_inode);
+}
+
+static inline struct ceph_fs_client *ceph_inode_to_client(struct inode *inode)
+{
+	return (struct ceph_fs_client *)inode->i_sb->s_fs_info;
+}
+
+static inline struct ceph_fs_client *ceph_sb_to_client(struct super_block *sb)
+{
+	return (struct ceph_fs_client *)sb->s_fs_info;
+}
+
+static inline struct ceph_vino ceph_vino(struct inode *inode)
+{
+	return ceph_inode(inode)->i_vino;
+}
+
+/*
+ * ino_t is <64 bits on many architectures, blech.
+ *
+ *               i_ino (kernel inode)   st_ino (userspace)
+ * i386          32                     32
+ * x86_64+ino32  64                     32
+ * x86_64        64                     64
+ */
+static inline u32 ceph_ino_to_ino32(__u64 vino)
+{
+	u32 ino = vino & 0xffffffff;
+	ino ^= vino >> 32;
+	if (!ino)
+		ino = 2;
+	return ino;
+}
+
+/*
+ * kernel i_ino value
+ */
+static inline ino_t ceph_vino_to_ino(struct ceph_vino vino)
+{
+#if BITS_PER_LONG == 32
+	return ceph_ino_to_ino32(vino.ino);
+#else
+	return (ino_t)vino.ino;
+#endif
+}
+
+/*
+ * user-visible ino (stat, filldir)
+ */
+#if BITS_PER_LONG == 32
+static inline ino_t ceph_translate_ino(struct super_block *sb, ino_t ino)
+{
+	return ino;
+}
+#else
+static inline ino_t ceph_translate_ino(struct super_block *sb, ino_t ino)
+{
+	if (ceph_test_mount_opt(ceph_sb_to_client(sb), INO32))
+		ino = ceph_ino_to_ino32(ino);
+	return ino;
+}
+#endif
+
+
+/* for printf-style formatting */
+#define ceph_vinop(i) ceph_inode(i)->i_vino.ino, ceph_inode(i)->i_vino.snap
+
+static inline u64 ceph_ino(struct inode *inode)
+{
+	return ceph_inode(inode)->i_vino.ino;
+}
+static inline u64 ceph_snap(struct inode *inode)
+{
+	return ceph_inode(inode)->i_vino.snap;
+}
+
+static inline int ceph_ino_compare(struct inode *inode, void *data)
+{
+	struct ceph_vino *pvino = (struct ceph_vino *)data;
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	return ci->i_vino.ino == pvino->ino &&
+		ci->i_vino.snap == pvino->snap;
+}
+
+static inline struct inode *ceph_find_inode(struct super_block *sb,
+					    struct ceph_vino vino)
+{
+	ino_t t = ceph_vino_to_ino(vino);
+	return ilookup5(sb, t, ceph_ino_compare, &vino);
+}
+
+
+/*
+ * Ceph inode.
+ */
+#define CEPH_I_NODELAY   4  /* do not delay cap release */
+#define CEPH_I_FLUSH     8  /* do not delay flush of dirty metadata */
+#define CEPH_I_NOFLUSH  16  /* do not flush dirty caps */
+
+static inline void __ceph_dir_set_complete(struct ceph_inode_info *ci,
+					   int release_count)
+{
+	atomic_set(&ci->i_complete_count, release_count);
+}
+
+static inline void __ceph_dir_clear_complete(struct ceph_inode_info *ci)
+{
+	atomic_inc(&ci->i_release_count);
+}
+
+static inline bool __ceph_dir_is_complete(struct ceph_inode_info *ci)
+{
+	return atomic_read(&ci->i_complete_count) ==
+		atomic_read(&ci->i_release_count);
+}
+
+static inline void ceph_dir_clear_complete(struct inode *inode)
+{
+	__ceph_dir_clear_complete(ceph_inode(inode));
+}
+
+static inline bool ceph_dir_is_complete(struct inode *inode)
+{
+	return __ceph_dir_is_complete(ceph_inode(inode));
+}
+
+
+/* find a specific frag @f */
+extern struct ceph_inode_frag *__ceph_find_frag(struct ceph_inode_info *ci,
+						u32 f);
+
+/*
+ * choose fragment for value @v.  copy frag content to pfrag, if leaf
+ * exists
+ */
+extern u32 ceph_choose_frag(struct ceph_inode_info *ci, u32 v,
+			    struct ceph_inode_frag *pfrag,
+			    int *found);
+
+static inline struct ceph_dentry_info *ceph_dentry(struct dentry *dentry)
+{
+	return (struct ceph_dentry_info *)dentry->d_fsdata;
+}
+
+static inline loff_t ceph_make_fpos(unsigned frag, unsigned off)
+{
+	return ((loff_t)frag << 32) | (loff_t)off;
+}
+
+/*
+ * caps helpers
+ */
+static inline bool __ceph_is_any_real_caps(struct ceph_inode_info *ci)
+{
+	return !RB_EMPTY_ROOT(&ci->i_caps);
+}
+
+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_other(struct ceph_inode_info *ci,
+				    struct ceph_cap *cap);
+
+static inline int ceph_caps_issued(struct ceph_inode_info *ci)
+{
+	int issued;
+	spin_lock(&ci->i_ceph_lock);
+	issued = __ceph_caps_issued(ci, NULL);
+	spin_unlock(&ci->i_ceph_lock);
+	return issued;
+}
+
+static inline int ceph_caps_issued_mask(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);
+	spin_unlock(&ci->i_ceph_lock);
+	return r;
+}
+
+static inline int __ceph_caps_dirty(struct ceph_inode_info *ci)
+{
+	return ci->i_dirty_caps | ci->i_flushing_caps;
+}
+extern int __ceph_mark_dirty_caps(struct ceph_inode_info *ci, int mask);
+
+extern int ceph_caps_revoking(struct ceph_inode_info *ci, int mask);
+extern int __ceph_caps_used(struct ceph_inode_info *ci);
+
+extern int __ceph_caps_file_wanted(struct ceph_inode_info *ci);
+
+/*
+ * wanted, by virtue of open file modes AND cap refs (buffered/cached data)
+ */
+static inline int __ceph_caps_wanted(struct ceph_inode_info *ci)
+{
+	int w = __ceph_caps_file_wanted(ci) | __ceph_caps_used(ci);
+	if (w & CEPH_CAP_FILE_BUFFER)
+		w |= CEPH_CAP_FILE_EXCL;  /* we want EXCL if dirty data */
+	return w;
+}
+
+/* what the mds thinks we want */
+extern int __ceph_caps_mds_wanted(struct ceph_inode_info *ci);
+
+extern void ceph_caps_init(struct ceph_mds_client *mdsc);
+extern void ceph_caps_finalize(struct ceph_mds_client *mdsc);
+extern void ceph_adjust_min_caps(struct ceph_mds_client *mdsc, int delta);
+extern int ceph_reserve_caps(struct ceph_mds_client *mdsc,
+			     struct ceph_cap_reservation *ctx, int need);
+extern int ceph_unreserve_caps(struct ceph_mds_client *mdsc,
+			       struct ceph_cap_reservation *ctx);
+extern void ceph_reservation_status(struct ceph_fs_client *client,
+				    int *total, int *avail, int *used,
+				    int *reserved, int *min);
+
+
+
+/*
+ * we keep buffered readdir results attached to file->private_data
+ */
+#define CEPH_F_SYNC     1
+#define CEPH_F_ATEND    2
+
+struct ceph_file_info {
+	short fmode;     /* initialized on open */
+	short flags;     /* CEPH_F_* */
+
+	/* readdir: position within the dir */
+	u32 frag;
+	struct ceph_mds_request *last_readdir;
+
+	/* readdir: position within a frag */
+	unsigned offset;       /* offset of last chunk, adjusted for . and .. */
+	u64 next_offset;       /* offset of next chunk (last_name's + 1) */
+	char *last_name;       /* last entry in previous chunk */
+	struct dentry *dentry; /* next dentry (for dcache readdir) */
+	int dir_release_count;
+
+	/* used for -o dirstat read() on directory thing */
+	char *dir_info;
+	int dir_info_len;
+};
+
+
+
+/*
+ * A "snap realm" describes a subset of the file hierarchy sharing
+ * the same set of snapshots that apply to it.  The realms themselves
+ * are organized into a hierarchy, such that children inherit (some of)
+ * the snapshots of their parents.
+ *
+ * All inodes within the realm that have capabilities are linked into a
+ * per-realm list.
+ */
+struct ceph_snap_realm {
+	u64 ino;
+	atomic_t nref;
+	struct rb_node node;
+
+	u64 created, seq;
+	u64 parent_ino;
+	u64 parent_since;   /* snapid when our current parent became so */
+
+	u64 *prior_parent_snaps;      /* snaps inherited from any parents we */
+	u32 num_prior_parent_snaps;   /*  had prior to parent_since */
+	u64 *snaps;                   /* snaps specific to this realm */
+	u32 num_snaps;
+
+	struct ceph_snap_realm *parent;
+	struct list_head children;       /* list of child realms */
+	struct list_head child_item;
+
+	struct list_head empty_item;     /* if i have ref==0 */
+
+	struct list_head dirty_item;     /* if realm needs new context */
+
+	/* the current set of snaps for this realm */
+	struct ceph_snap_context *cached_context;
+
+	struct list_head inodes_with_caps;
+	spinlock_t inodes_with_caps_lock;
+};
+
+static inline int default_congestion_kb(void)
+{
+	int congestion_kb;
+
+	/*
+	 * Copied from NFS
+	 *
+	 * congestion size, scale with available memory.
+	 *
+	 *  64MB:    8192k
+	 * 128MB:   11585k
+	 * 256MB:   16384k
+	 * 512MB:   23170k
+	 *   1GB:   32768k
+	 *   2GB:   46340k
+	 *   4GB:   65536k
+	 *   8GB:   92681k
+	 *  16GB:  131072k
+	 *
+	 * This allows larger machines to have larger/more transfers.
+	 * Limit the default to 256M
+	 */
+	congestion_kb = (16*int_sqrt(totalram_pages)) << (PAGE_SHIFT-10);
+	if (congestion_kb > 256*1024)
+		congestion_kb = 256*1024;
+
+	return congestion_kb;
+}
+
+
+
+/* snap.c */
+struct ceph_snap_realm *ceph_lookup_snap_realm(struct ceph_mds_client *mdsc,
+					       u64 ino);
+extern void ceph_get_snap_realm(struct ceph_mds_client *mdsc,
+				struct ceph_snap_realm *realm);
+extern void ceph_put_snap_realm(struct ceph_mds_client *mdsc,
+				struct ceph_snap_realm *realm);
+extern int ceph_update_snap_trace(struct ceph_mds_client *m,
+				  void *p, void *e, bool deletion);
+extern void ceph_handle_snap(struct ceph_mds_client *mdsc,
+			     struct ceph_mds_session *session,
+			     struct ceph_msg *msg);
+extern void ceph_queue_cap_snap(struct ceph_inode_info *ci);
+extern int __ceph_finish_cap_snap(struct ceph_inode_info *ci,
+				  struct ceph_cap_snap *capsnap);
+extern void ceph_cleanup_empty_realms(struct ceph_mds_client *mdsc);
+
+/*
+ * a cap_snap is "pending" if it is still awaiting an in-progress
+ * sync write (that may/may not still update size, mtime, etc.).
+ */
+static inline bool __ceph_have_pending_cap_snap(struct ceph_inode_info *ci)
+{
+	return !list_empty(&ci->i_cap_snaps) &&
+		list_entry(ci->i_cap_snaps.prev, struct ceph_cap_snap,
+			   ci_item)->writing;
+}
+
+/* inode.c */
+extern const struct inode_operations ceph_file_iops;
+
+extern struct inode *ceph_alloc_inode(struct super_block *sb);
+extern void ceph_destroy_inode(struct inode *inode);
+
+extern struct inode *ceph_get_inode(struct super_block *sb,
+				    struct ceph_vino vino);
+extern struct inode *ceph_get_snapdir(struct inode *parent);
+extern int ceph_fill_file_size(struct inode *inode, int issued,
+			       u32 truncate_seq, u64 truncate_size, u64 size);
+extern void ceph_fill_file_time(struct inode *inode, int issued,
+				u64 time_warp_seq, struct timespec *ctime,
+				struct timespec *mtime, struct timespec *atime);
+extern int ceph_fill_trace(struct super_block *sb,
+			   struct ceph_mds_request *req,
+			   struct ceph_mds_session *session);
+extern int ceph_readdir_prepopulate(struct ceph_mds_request *req,
+				    struct ceph_mds_session *session);
+
+extern int ceph_inode_holds_cap(struct inode *inode, int mask);
+
+extern int ceph_inode_set_size(struct inode *inode, loff_t size);
+extern void __ceph_do_pending_vmtruncate(struct inode *inode, bool needlock);
+extern void ceph_queue_vmtruncate(struct inode *inode);
+
+extern void ceph_queue_invalidate(struct inode *inode);
+extern void ceph_queue_writeback(struct inode *inode);
+
+extern int ceph_do_getattr(struct inode *inode, int mask);
+extern int ceph_permission(struct inode *inode, int mask);
+extern int ceph_setattr(struct dentry *dentry, struct iattr *attr);
+extern int ceph_getattr(struct vfsmount *mnt, struct dentry *dentry,
+			struct kstat *stat);
+
+/* xattr.c */
+extern int ceph_setxattr(struct dentry *, const char *, const void *,
+			 size_t, int);
+extern ssize_t ceph_getxattr(struct dentry *, const char *, void *, size_t);
+extern ssize_t ceph_listxattr(struct dentry *, char *, size_t);
+extern int ceph_removexattr(struct dentry *, const char *);
+extern void __ceph_build_xattrs_blob(struct ceph_inode_info *ci);
+extern void __ceph_destroy_xattrs(struct ceph_inode_info *ci);
+extern void __init ceph_xattr_init(void);
+extern void ceph_xattr_exit(void);
+
+/* caps.c */
+extern const char *ceph_cap_string(int c);
+extern void ceph_handle_caps(struct ceph_mds_session *session,
+			     struct ceph_msg *msg);
+extern int ceph_add_cap(struct inode *inode,
+			struct ceph_mds_session *session, u64 cap_id,
+			int fmode, unsigned issued, unsigned wanted,
+			unsigned cap, unsigned seq, u64 realmino, int flags,
+			struct ceph_cap_reservation *caps_reservation);
+extern void __ceph_remove_cap(struct ceph_cap *cap);
+static inline void ceph_remove_cap(struct ceph_cap *cap)
+{
+	spin_lock(&cap->ci->i_ceph_lock);
+	__ceph_remove_cap(cap);
+	spin_unlock(&cap->ci->i_ceph_lock);
+}
+extern void ceph_put_cap(struct ceph_mds_client *mdsc,
+			 struct ceph_cap *cap);
+
+extern void __queue_cap_release(struct ceph_mds_session *session, u64 ino,
+				u64 cap_id, u32 migrate_seq, u32 issue_seq);
+extern void ceph_queue_caps_release(struct inode *inode);
+extern int ceph_write_inode(struct inode *inode, struct writeback_control *wbc);
+extern int ceph_fsync(struct file *file, loff_t start, loff_t end,
+		      int datasync);
+extern void ceph_kick_flushing_caps(struct ceph_mds_client *mdsc,
+				    struct ceph_mds_session *session);
+extern struct ceph_cap *ceph_get_cap_for_mds(struct ceph_inode_info *ci,
+					     int mds);
+extern int ceph_get_cap_mds(struct inode *inode);
+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_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,
+			       struct ceph_mds_session **psession,
+			       int again);
+extern void ceph_check_caps(struct ceph_inode_info *ci, int flags,
+			    struct ceph_mds_session *session);
+extern void ceph_check_delayed_caps(struct ceph_mds_client *mdsc);
+extern void ceph_flush_dirty_caps(struct ceph_mds_client *mdsc);
+
+extern int ceph_encode_inode_release(void **p, struct inode *inode,
+				     int mds, int drop, int unless, int force);
+extern int ceph_encode_dentry_release(void **p, struct dentry *dn,
+				      int mds, int drop, int unless);
+
+extern int ceph_get_caps(struct ceph_inode_info *ci, int need, int want,
+			 int *got, loff_t endoff);
+
+/* for counting open files by mode */
+static inline void __ceph_get_fmode(struct ceph_inode_info *ci, int mode)
+{
+	ci->i_nr_by_mode[mode]++;
+}
+extern void ceph_put_fmode(struct ceph_inode_info *ci, int mode);
+
+/* addr.c */
+extern const struct address_space_operations ceph_aops;
+extern int ceph_mmap(struct file *file, struct vm_area_struct *vma);
+
+/* file.c */
+extern const struct file_operations ceph_file_fops;
+extern const struct address_space_operations ceph_aops;
+
+extern int ceph_open(struct inode *inode, struct file *file);
+extern int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
+			    struct file *file, unsigned flags, umode_t mode,
+			    int *opened);
+extern int ceph_release(struct inode *inode, struct file *filp);
+
+/* dir.c */
+extern const struct file_operations ceph_dir_fops;
+extern const struct inode_operations ceph_dir_iops;
+extern const struct dentry_operations ceph_dentry_ops, ceph_snap_dentry_ops,
+	ceph_snapdir_dentry_ops;
+
+extern int ceph_handle_notrace_create(struct inode *dir, struct dentry *dentry);
+extern int ceph_handle_snapdir(struct ceph_mds_request *req,
+			       struct dentry *dentry, int err);
+extern struct dentry *ceph_finish_lookup(struct ceph_mds_request *req,
+					 struct dentry *dentry, int err);
+
+extern void ceph_dentry_lru_add(struct dentry *dn);
+extern void ceph_dentry_lru_touch(struct dentry *dn);
+extern void ceph_dentry_lru_del(struct dentry *dn);
+extern void ceph_invalidate_dentry_lease(struct dentry *dentry);
+extern unsigned ceph_dentry_hash(struct inode *dir, struct dentry *dn);
+extern struct inode *ceph_get_dentry_parent_inode(struct dentry *dentry);
+
+/*
+ * our d_ops vary depending on whether the inode is live,
+ * snapshotted (read-only), or a virtual ".snap" directory.
+ */
+int ceph_init_dentry(struct dentry *dentry);
+
+
+/* ioctl.c */
+extern long ceph_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
+
+/* export.c */
+extern const struct export_operations ceph_export_ops;
+
+/* locks.c */
+extern int ceph_lock(struct file *file, int cmd, struct file_lock *fl);
+extern int ceph_flock(struct file *file, int cmd, struct file_lock *fl);
+extern void ceph_count_locks(struct inode *inode, int *p_num, int *f_num);
+extern int ceph_encode_locks_to_buffer(struct inode *inode,
+				       struct ceph_filelock *flocks,
+				       int num_fcntl_locks,
+				       int num_flock_locks);
+extern int ceph_locks_to_pagelist(struct ceph_filelock *flocks,
+				  struct ceph_pagelist *pagelist,
+				  int num_fcntl_locks, int num_flock_locks);
+extern int lock_to_ceph_filelock(struct file_lock *fl, struct ceph_filelock *c);
+
+/* debugfs.c */
+extern int ceph_fs_debugfs_init(struct ceph_fs_client *client);
+extern void ceph_fs_debugfs_cleanup(struct ceph_fs_client *client);
+
+#endif /* _FS_CEPH_SUPER_H */