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

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client: (205 commits)
  ceph: update for write_inode API change
  ceph: reset osd after relevant messages timed out
  ceph: fix flush_dirty_caps race with caps migration
  ceph: include migrating caps in issued set
  ceph: fix osdmap decoding when pools include (removed) snaps
  ceph: return EBADF if waiting for caps on closed file
  ceph: set osd request message front length correctly
  ceph: reset front len on return to msgpool; BUG on mismatched front iov
  ceph: fix snaptrace decoding on cap migration between mds
  ceph: use single osd op reply msg
  ceph: reset bits on connection close
  ceph: remove bogus mds forward warning
  ceph: remove fragile __map_osds optimization
  ceph: fix connection fault STANDBY check
  ceph: invalidate_authorizer without con->mutex held
  ceph: don't clobber write return value when using O_SYNC
  ceph: fix client_request_forward decoding
  ceph: drop messages on unregistered mds sessions; cleanup
  ceph: fix comments, locking in destroy_inode
  ceph: move dereference after NULL test
  ...

Fix trivial conflicts in Documentation/ioctl/ioctl-number.txt

Documentation/filesystems/ceph.txt

@@ -0,0 +1,139 @@
+Ceph Distributed File System
+============================
+
+Ceph is a distributed network file system designed to provide good
+performance, reliability, and scalability.
+
+Basic features include:
+
+ * POSIX semantics
+ * Seamless scaling from 1 to many thousands of nodes
+ * High availability and reliability.  No single points of failure.
+ * N-way replication of data across storage nodes
+ * Fast recovery from node failures
+ * Automatic rebalancing of data on node addition/removal
+ * Easy deployment: most FS components are userspace daemons
+
+Also,
+ * Flexible snapshots (on any directory)
+ * Recursive accounting (nested files, directories, bytes)
+
+In contrast to cluster filesystems like GFS, OCFS2, and GPFS that rely
+on symmetric access by all clients to shared block devices, Ceph
+separates data and metadata management into independent server
+clusters, similar to Lustre.  Unlike Lustre, however, metadata and
+storage nodes run entirely as user space daemons.  Storage nodes
+utilize btrfs to store data objects, leveraging its advanced features
+(checksumming, metadata replication, etc.).  File data is striped
+across storage nodes in large chunks to distribute workload and
+facilitate high throughputs.  When storage nodes fail, data is
+re-replicated in a distributed fashion by the storage nodes themselves
+(with some minimal coordination from a cluster monitor), making the
+system extremely efficient and scalable.
+
+Metadata servers effectively form a large, consistent, distributed
+in-memory cache above the file namespace that is extremely scalable,
+dynamically redistributes metadata in response to workload changes,
+and can tolerate arbitrary (well, non-Byzantine) node failures.  The
+metadata server takes a somewhat unconventional approach to metadata
+storage to significantly improve performance for common workloads.  In
+particular, inodes with only a single link are embedded in
+directories, allowing entire directories of dentries and inodes to be
+loaded into its cache with a single I/O operation.  The contents of
+extremely large directories can be fragmented and managed by
+independent metadata servers, allowing scalable concurrent access.
+
+The system offers automatic data rebalancing/migration when scaling
+from a small cluster of just a few nodes to many hundreds, without
+requiring an administrator carve the data set into static volumes or
+go through the tedious process of migrating data between servers.
+When the file system approaches full, new nodes can be easily added
+and things will "just work."
+
+Ceph includes flexible snapshot mechanism that allows a user to create
+a snapshot on any subdirectory (and its nested contents) in the
+system.  Snapshot creation and deletion are as simple as 'mkdir
+.snap/foo' and 'rmdir .snap/foo'.
+
+Ceph also provides some recursive accounting on directories for nested
+files and bytes.  That is, a 'getfattr -d foo' on any directory in the
+system will reveal the total number of nested regular files and
+subdirectories, and a summation of all nested file sizes.  This makes
+the identification of large disk space consumers relatively quick, as
+no 'du' or similar recursive scan of the file system is required.
+
+
+Mount Syntax
+============
+
+The basic mount syntax is:
+
+ # mount -t ceph monip[:port][,monip2[:port]...]:/[subdir] mnt
+
+You only need to specify a single monitor, as the client will get the
+full list when it connects.  (However, if the monitor you specify
+happens to be down, the mount won't succeed.)  The port can be left
+off if the monitor is using the default.  So if the monitor is at
+1.2.3.4,
+
+ # mount -t ceph 1.2.3.4:/ /mnt/ceph
+
+is sufficient.  If /sbin/mount.ceph is installed, a hostname can be
+used instead of an IP address.
+
+
+
+Mount Options
+=============
+
+  ip=A.B.C.D[:N]
+	Specify the IP and/or port the client should bind to locally.
+	There is normally not much reason to do this.  If the IP is not
+	specified, the client's IP address is determined by looking at the
+	address it's connection to the monitor originates from.
+
+  wsize=X
+	Specify the maximum write size in bytes.  By default there is no
+	maximu.  Ceph will normally size writes based on the file stripe
+	size.
+
+  rsize=X
+	Specify the maximum readahead.
+
+  mount_timeout=X
+	Specify the timeout value for mount (in seconds), in the case
+	of a non-responsive Ceph file system.  The default is 30
+	seconds.
+
+  rbytes
+	When stat() is called on a directory, set st_size to 'rbytes',
+	the summation of file sizes over all files nested beneath that
+	directory.  This is the default.
+
+  norbytes
+	When stat() is called on a directory, set st_size to the
+	number of entries in that directory.
+
+  nocrc
+	Disable CRC32C calculation for data writes.  If set, the OSD
+	must rely on TCP's error correction to detect data corruption
+	in the data payload.
+
+  noasyncreaddir
+	Disable client's use its local cache to satisfy	readdir
+	requests.  (This does not change correctness; the client uses
+	cached metadata only when a lease or capability ensures it is
+	valid.)
+
+
+More Information
+================
+
+For more information on Ceph, see the home page at
+	http://ceph.newdream.net/
+
+The Linux kernel client source tree is available at
+	git://ceph.newdream.net/linux-ceph-client.git
+
+and the source for the full system is at
+	git://ceph.newdream.net/ceph.git

Documentation/ioctl/ioctl-number.txt

@@ -291,6 +291,7 @@ Code  Seq#(hex)	Include File		Comments
 0x92	00-0F	drivers/usb/mon/mon_bin.c
 0x93	60-7F	linux/auto_fs.h
 0x94	all	fs/btrfs/ioctl.h
+0x97	00-7F	fs/ceph/ioctl.h		Ceph file system
 0x99	00-0F				537-Addinboard driver
 					<mailto:buk@buks.ipn.de>
 0xA0	all	linux/sdp/sdp.h		Industrial Device Project

MAINTAINERS

@@ -1441,6 +1441,15 @@ F:	arch/powerpc/include/asm/spu*.h
 F:	arch/powerpc/oprofile/*cell*
 F:	arch/powerpc/platforms/cell/
 
+CEPH DISTRIBUTED FILE SYSTEM CLIENT
+M:	Sage Weil <sage@newdream.net>
+L:	ceph-devel@lists.sourceforge.net
+W:	http://ceph.newdream.net/
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client.git
+S:	Supported
+F:	Documentation/filesystems/ceph.txt
+F:	fs/ceph
+
 CERTIFIED WIRELESS USB (WUSB) SUBSYSTEM:
 M:	David Vrabel <david.vrabel@csr.com>
 L:	linux-usb@vger.kernel.org

fs/Kconfig

@@ -235,6 +235,7 @@ config NFS_COMMON
 
 source "net/sunrpc/Kconfig"
 source "fs/smbfs/Kconfig"
+source "fs/ceph/Kconfig"
 source "fs/cifs/Kconfig"
 source "fs/ncpfs/Kconfig"
 source "fs/coda/Kconfig"

fs/Makefile

@@ -125,3 +125,4 @@ obj-$(CONFIG_OCFS2_FS)		+= ocfs2/
 obj-$(CONFIG_BTRFS_FS)		+= btrfs/
 obj-$(CONFIG_GFS2_FS)           += gfs2/
 obj-$(CONFIG_EXOFS_FS)          += exofs/
+obj-$(CONFIG_CEPH_FS)		+= ceph/

fs/ceph/Kconfig

@@ -0,0 +1,27 @@
+config CEPH_FS
+        tristate "Ceph distributed file system (EXPERIMENTAL)"
+	depends on INET && EXPERIMENTAL
+	select LIBCRC32C
+	select CONFIG_CRYPTO_AES
+	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.
+
+config CEPH_FS_PRETTYDEBUG
+	bool "Include file:line in ceph debug output"
+	depends on CEPH_FS
+	default n
+	help
+	  If you say Y here, debug output will include a filename and
+	  line to aid debugging.  This icnreases kernel size and slows
+	  execution slightly when debug call sites are enabled (e.g.,
+	  via CONFIG_DYNAMIC_DEBUG).
+
+	  If unsure, say N.
+

fs/ceph/Makefile

@@ -0,0 +1,39 @@
+#
+# Makefile for CEPH filesystem.
+#
+
+ifneq ($(KERNELRELEASE),)
+
+obj-$(CONFIG_CEPH_FS) += ceph.o
+
+ceph-objs := super.o inode.o dir.o file.o addr.o ioctl.o \
+	export.o caps.o snap.o xattr.o \
+	messenger.o msgpool.o buffer.o pagelist.o \
+	mds_client.o mdsmap.o \
+	mon_client.o \
+	osd_client.o osdmap.o crush/crush.o crush/mapper.o crush/hash.o \
+	debugfs.o \
+	auth.o auth_none.o \
+	crypto.o armor.o \
+	auth_x.o \
+	ceph_fs.o ceph_strings.o ceph_hash.o ceph_frag.o
+
+else
+#Otherwise we were called directly from the command
+# line; invoke the kernel build system.
+
+KERNELDIR ?= /lib/modules/$(shell uname -r)/build
+PWD := $(shell pwd)
+
+default: all
+
+all:
+	$(MAKE) -C $(KERNELDIR) M=$(PWD) CONFIG_CEPH_FS=m modules
+
+modules_install:
+	$(MAKE) -C $(KERNELDIR) M=$(PWD) CONFIG_CEPH_FS=m modules_install
+
+clean:
+	$(MAKE) -C $(KERNELDIR) M=$(PWD) clean
+
+endif

fs/ceph/README

@@ -0,0 +1,20 @@
+#
+# The following files are shared by (and manually synchronized
+# between) the Ceph userland and kernel client.
+#
+# userland                  kernel
+src/include/ceph_fs.h	    fs/ceph/ceph_fs.h
+src/include/ceph_fs.cc	    fs/ceph/ceph_fs.c
+src/include/msgr.h	    fs/ceph/msgr.h
+src/include/rados.h	    fs/ceph/rados.h
+src/include/ceph_strings.cc fs/ceph/ceph_strings.c
+src/include/ceph_frag.h	    fs/ceph/ceph_frag.h
+src/include/ceph_frag.cc    fs/ceph/ceph_frag.c
+src/include/ceph_hash.h	    fs/ceph/ceph_hash.h
+src/include/ceph_hash.cc    fs/ceph/ceph_hash.c
+src/crush/crush.c	    fs/ceph/crush/crush.c
+src/crush/crush.h	    fs/ceph/crush/crush.h
+src/crush/mapper.c	    fs/ceph/crush/mapper.c
+src/crush/mapper.h	    fs/ceph/crush/mapper.h
+src/crush/hash.h	    fs/ceph/crush/hash.h
+src/crush/hash.c	    fs/ceph/crush/hash.c

fs/ceph/armor.c

@@ -0,0 +1,99 @@
+
+#include <linux/errno.h>
+
+/*
+ * base64 encode/decode.
+ */
+
+const char *pem_key = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/";
+
+static int encode_bits(int c)
+{
+	return pem_key[c];
+}
+
+static int decode_bits(char c)
+{
+	if (c >= 'A' && c <= 'Z')
+		return c - 'A';
+	if (c >= 'a' && c <= 'z')
+		return c - 'a' + 26;
+	if (c >= '0' && c <= '9')
+		return c - '0' + 52;
+	if (c == '+')
+		return 62;
+	if (c == '/')
+		return 63;
+	if (c == '=')
+		return 0; /* just non-negative, please */
+	return -EINVAL;
+}
+
+int ceph_armor(char *dst, const char *src, const char *end)
+{
+	int olen = 0;
+	int line = 0;
+
+	while (src < end) {
+		unsigned char a, b, c;
+
+		a = *src++;
+		*dst++ = encode_bits(a >> 2);
+		if (src < end) {
+			b = *src++;
+			*dst++ = encode_bits(((a & 3) << 4) | (b >> 4));
+			if (src < end) {
+				c = *src++;
+				*dst++ = encode_bits(((b & 15) << 2) |
+						     (c >> 6));
+				*dst++ = encode_bits(c & 63);
+			} else {
+				*dst++ = encode_bits((b & 15) << 2);
+				*dst++ = '=';
+			}
+		} else {
+			*dst++ = encode_bits(((a & 3) << 4));
+			*dst++ = '=';
+			*dst++ = '=';
+		}
+		olen += 4;
+		line += 4;
+		if (line == 64) {
+			line = 0;
+			*(dst++) = '\n';
+			olen++;
+		}
+	}
+	return olen;
+}
+
+int ceph_unarmor(char *dst, const char *src, const char *end)
+{
+	int olen = 0;
+
+	while (src < end) {
+		int a, b, c, d;
+
+		if (src < end && src[0] == '\n')
+			src++;
+		if (src + 4 > end)
+			return -EINVAL;
+		a = decode_bits(src[0]);
+		b = decode_bits(src[1]);
+		c = decode_bits(src[2]);
+		d = decode_bits(src[3]);
+		if (a < 0 || b < 0 || c < 0 || d < 0)
+			return -EINVAL;
+
+		*dst++ = (a << 2) | (b >> 4);
+		if (src[2] == '=')
+			return olen + 1;
+		*dst++ = ((b & 15) << 4) | (c >> 2);
+		if (src[3] == '=')
+			return olen + 2;
+		*dst++ = ((c & 3) << 6) | d;
+		olen += 3;
+		src += 4;
+	}
+	return olen;
+}

fs/ceph/auth.c

@@ -0,0 +1,257 @@
+#include "ceph_debug.h"
+
+#include <linux/module.h>
+#include <linux/err.h>
+
+#include "types.h"
+#include "auth_none.h"
+#include "auth_x.h"
+#include "decode.h"
+#include "super.h"
+
+#include "messenger.h"
+
+/*
+ * get protocol handler
+ */
+static u32 supported_protocols[] = {
+	CEPH_AUTH_NONE,
+	CEPH_AUTH_CEPHX
+};
+
+int ceph_auth_init_protocol(struct ceph_auth_client *ac, int protocol)
+{
+	switch (protocol) {
+	case CEPH_AUTH_NONE:
+		return ceph_auth_none_init(ac);
+	case CEPH_AUTH_CEPHX:
+		return ceph_x_init(ac);
+	default:
+		return -ENOENT;
+	}
+}
+
+/*
+ * setup, teardown.
+ */
+struct ceph_auth_client *ceph_auth_init(const char *name, const char *secret)
+{
+	struct ceph_auth_client *ac;
+	int ret;
+
+	dout("auth_init name '%s' secret '%s'\n", name, secret);
+
+	ret = -ENOMEM;
+	ac = kzalloc(sizeof(*ac), GFP_NOFS);
+	if (!ac)
+		goto out;
+
+	ac->negotiating = true;
+	if (name)
+		ac->name = name;
+	else
+		ac->name = CEPH_AUTH_NAME_DEFAULT;
+	dout("auth_init name %s secret %s\n", ac->name, secret);
+	ac->secret = secret;
+	return ac;
+
+out:
+	return ERR_PTR(ret);
+}
+
+void ceph_auth_destroy(struct ceph_auth_client *ac)
+{
+	dout("auth_destroy %p\n", ac);
+	if (ac->ops)
+		ac->ops->destroy(ac);
+	kfree(ac);
+}
+
+/*
+ * Reset occurs when reconnecting to the monitor.
+ */
+void ceph_auth_reset(struct ceph_auth_client *ac)
+{
+	dout("auth_reset %p\n", ac);
+	if (ac->ops && !ac->negotiating)
+		ac->ops->reset(ac);
+	ac->negotiating = true;
+}
+
+int ceph_entity_name_encode(const char *name, void **p, void *end)
+{
+	int len = strlen(name);
+
+	if (*p + 2*sizeof(u32) + len > end)
+		return -ERANGE;
+	ceph_encode_32(p, CEPH_ENTITY_TYPE_CLIENT);
+	ceph_encode_32(p, len);
+	ceph_encode_copy(p, name, len);
+	return 0;
+}
+
+/*
+ * Initiate protocol negotiation with monitor.  Include entity name
+ * and list supported protocols.
+ */
+int ceph_auth_build_hello(struct ceph_auth_client *ac, void *buf, size_t len)
+{
+	struct ceph_mon_request_header *monhdr = buf;
+	void *p = monhdr + 1, *end = buf + len, *lenp;
+	int i, num;
+	int ret;
+
+	dout("auth_build_hello\n");
+	monhdr->have_version = 0;
+	monhdr->session_mon = cpu_to_le16(-1);
+	monhdr->session_mon_tid = 0;
+
+	ceph_encode_32(&p, 0);  /* no protocol, yet */
+
+	lenp = p;
+	p += sizeof(u32);
+
+	ceph_decode_need(&p, end, 1 + sizeof(u32), bad);
+	ceph_encode_8(&p, 1);
+	num = ARRAY_SIZE(supported_protocols);
+	ceph_encode_32(&p, num);
+	ceph_decode_need(&p, end, num * sizeof(u32), bad);
+	for (i = 0; i < num; i++)
+		ceph_encode_32(&p, supported_protocols[i]);
+
+	ret = ceph_entity_name_encode(ac->name, &p, end);
+	if (ret < 0)
+		return ret;
+	ceph_decode_need(&p, end, sizeof(u64), bad);
+	ceph_encode_64(&p, ac->global_id);
+
+	ceph_encode_32(&lenp, p - lenp - sizeof(u32));
+	return p - buf;
+
+bad:
+	return -ERANGE;
+}
+
+int ceph_build_auth_request(struct ceph_auth_client *ac,
+			   void *msg_buf, size_t msg_len)
+{
+	struct ceph_mon_request_header *monhdr = msg_buf;
+	void *p = monhdr + 1;
+	void *end = msg_buf + msg_len;
+	int ret;
+
+	monhdr->have_version = 0;
+	monhdr->session_mon = cpu_to_le16(-1);
+	monhdr->session_mon_tid = 0;
+
+	ceph_encode_32(&p, ac->protocol);
+
+	ret = ac->ops->build_request(ac, p + sizeof(u32), end);
+	if (ret < 0) {
+		pr_err("error %d building request\n", ret);
+		return ret;
+	}
+	dout(" built request %d bytes\n", ret);
+	ceph_encode_32(&p, ret);
+	return p + ret - msg_buf;
+}
+
+/*
+ * Handle auth message from monitor.
+ */
+int ceph_handle_auth_reply(struct ceph_auth_client *ac,
+			   void *buf, size_t len,
+			   void *reply_buf, size_t reply_len)
+{
+	void *p = buf;
+	void *end = buf + len;
+	int protocol;
+	s32 result;
+	u64 global_id;
+	void *payload, *payload_end;
+	int payload_len;
+	char *result_msg;
+	int result_msg_len;
+	int ret = -EINVAL;
+
+	dout("handle_auth_reply %p %p\n", p, end);
+	ceph_decode_need(&p, end, sizeof(u32) * 3 + sizeof(u64), bad);
+	protocol = ceph_decode_32(&p);
+	result = ceph_decode_32(&p);
+	global_id = ceph_decode_64(&p);
+	payload_len = ceph_decode_32(&p);
+	payload = p;
+	p += payload_len;
+	ceph_decode_need(&p, end, sizeof(u32), bad);
+	result_msg_len = ceph_decode_32(&p);
+	result_msg = p;
+	p += result_msg_len;
+	if (p != end)
+		goto bad;
+
+	dout(" result %d '%.*s' gid %llu len %d\n", result, result_msg_len,
+	     result_msg, global_id, payload_len);
+
+	payload_end = payload + payload_len;
+
+	if (global_id && ac->global_id != global_id) {
+		dout(" set global_id %lld -> %lld\n", ac->global_id, global_id);
+		ac->global_id = global_id;
+	}
+
+	if (ac->negotiating) {
+		/* server does not support our protocols? */
+		if (!protocol && result < 0) {
+			ret = result;
+			goto out;
+		}
+		/* set up (new) protocol handler? */
+		if (ac->protocol && ac->protocol != protocol) {
+			ac->ops->destroy(ac);
+			ac->protocol = 0;
+			ac->ops = NULL;
+		}
+		if (ac->protocol != protocol) {
+			ret = ceph_auth_init_protocol(ac, protocol);
+			if (ret) {
+				pr_err("error %d on auth protocol %d init\n",
+				       ret, protocol);
+				goto out;
+			}
+		}
+
+		ac->negotiating = false;
+	}
+
+	ret = ac->ops->handle_reply(ac, result, payload, payload_end);
+	if (ret == -EAGAIN) {
+		return ceph_build_auth_request(ac, reply_buf, reply_len);
+	} else if (ret) {
+		pr_err("authentication error %d\n", ret);
+		return ret;
+	}
+	return 0;
+
+bad:
+	pr_err("failed to decode auth msg\n");
+out:
+	return ret;
+}
+
+int ceph_build_auth(struct ceph_auth_client *ac,
+		    void *msg_buf, size_t msg_len)
+{
+	if (!ac->protocol)
+		return ceph_auth_build_hello(ac, msg_buf, msg_len);
+	BUG_ON(!ac->ops);
+	if (!ac->ops->is_authenticated(ac))
+		return ceph_build_auth_request(ac, msg_buf, msg_len);
+	return 0;
+}
+
+int ceph_auth_is_authenticated(struct ceph_auth_client *ac)
+{
+	if (!ac->ops)
+		return 0;
+	return ac->ops->is_authenticated(ac);
+}

fs/ceph/auth.h

@@ -0,0 +1,84 @@
+#ifndef _FS_CEPH_AUTH_H
+#define _FS_CEPH_AUTH_H
+
+#include "types.h"
+#include "buffer.h"
+
+/*
+ * Abstract interface for communicating with the authenticate module.
+ * There is some handshake that takes place between us and the monitor
+ * to acquire the necessary keys.  These are used to generate an
+ * 'authorizer' that we use when connecting to a service (mds, osd).
+ */
+
+struct ceph_auth_client;
+struct ceph_authorizer;
+
+struct ceph_auth_client_ops {
+	/*
+	 * true if we are authenticated and can connect to
+	 * services.
+	 */
+	int (*is_authenticated)(struct ceph_auth_client *ac);
+
+	/*
+	 * build requests and process replies during monitor
+	 * handshake.  if handle_reply returns -EAGAIN, we build
+	 * another request.
+	 */
+	int (*build_request)(struct ceph_auth_client *ac, void *buf, void *end);
+	int (*handle_reply)(struct ceph_auth_client *ac, int result,
+			    void *buf, void *end);
+
+	/*
+	 * Create authorizer for connecting to a service, and verify
+	 * the response to authenticate the service.
+	 */
+	int (*create_authorizer)(struct ceph_auth_client *ac, int peer_type,
+				 struct ceph_authorizer **a,
+				 void **buf, size_t *len,
+				 void **reply_buf, size_t *reply_len);
+	int (*verify_authorizer_reply)(struct ceph_auth_client *ac,
+				       struct ceph_authorizer *a, size_t len);
+	void (*destroy_authorizer)(struct ceph_auth_client *ac,
+				   struct ceph_authorizer *a);
+	void (*invalidate_authorizer)(struct ceph_auth_client *ac,
+				      int peer_type);
+
+	/* reset when we (re)connect to a monitor */
+	void (*reset)(struct ceph_auth_client *ac);
+
+	void (*destroy)(struct ceph_auth_client *ac);
+};
+
+struct ceph_auth_client {
+	u32 protocol;           /* CEPH_AUTH_* */
+	void *private;          /* for use by protocol implementation */
+	const struct ceph_auth_client_ops *ops;  /* null iff protocol==0 */
+
+	bool negotiating;       /* true if negotiating protocol */
+	const char *name;       /* entity name */
+	u64 global_id;          /* our unique id in system */
+	const char *secret;     /* our secret key */
+	unsigned want_keys;     /* which services we want */
+};
+
+extern struct ceph_auth_client *ceph_auth_init(const char *name,
+					       const char *secret);
+extern void ceph_auth_destroy(struct ceph_auth_client *ac);
+
+extern void ceph_auth_reset(struct ceph_auth_client *ac);
+
+extern int ceph_auth_build_hello(struct ceph_auth_client *ac,
+				 void *buf, size_t len);
+extern int ceph_handle_auth_reply(struct ceph_auth_client *ac,
+				  void *buf, size_t len,
+				  void *reply_buf, size_t reply_len);
+extern int ceph_entity_name_encode(const char *name, void **p, void *end);
+
+extern int ceph_build_auth(struct ceph_auth_client *ac,
+		    void *msg_buf, size_t msg_len);
+
+extern int ceph_auth_is_authenticated(struct ceph_auth_client *ac);
+
+#endif

fs/ceph/auth_none.c

@@ -0,0 +1,121 @@
+
+#include "ceph_debug.h"
+
+#include <linux/err.h>
+#include <linux/module.h>
+#include <linux/random.h>
+
+#include "auth_none.h"
+#include "auth.h"
+#include "decode.h"
+
+static void reset(struct ceph_auth_client *ac)
+{
+	struct ceph_auth_none_info *xi = ac->private;
+
+	xi->starting = true;
+	xi->built_authorizer = false;
+}
+
+static void destroy(struct ceph_auth_client *ac)
+{
+	kfree(ac->private);
+	ac->private = NULL;
+}
+
+static int is_authenticated(struct ceph_auth_client *ac)
+{
+	struct ceph_auth_none_info *xi = ac->private;
+
+	return !xi->starting;
+}
+
+/*
+ * the generic auth code decode the global_id, and we carry no actual
+ * authenticate state, so nothing happens here.
+ */
+static int handle_reply(struct ceph_auth_client *ac, int result,
+			void *buf, void *end)
+{
+	struct ceph_auth_none_info *xi = ac->private;
+
+	xi->starting = false;
+	return result;
+}
+
+/*
+ * build an 'authorizer' with our entity_name and global_id.  we can
+ * reuse a single static copy since it is identical for all services
+ * we connect to.
+ */
+static int ceph_auth_none_create_authorizer(
+	struct ceph_auth_client *ac, int peer_type,
+	struct ceph_authorizer **a,
+	void **buf, size_t *len,
+	void **reply_buf, size_t *reply_len)
+{
+	struct ceph_auth_none_info *ai = ac->private;
+	struct ceph_none_authorizer *au = &ai->au;
+	void *p, *end;
+	int ret;
+
+	if (!ai->built_authorizer) {
+		p = au->buf;
+		end = p + sizeof(au->buf);
+		ceph_encode_8(&p, 1);
+		ret = ceph_entity_name_encode(ac->name, &p, end - 8);
+		if (ret < 0)
+			goto bad;
+		ceph_decode_need(&p, end, sizeof(u64), bad2);
+		ceph_encode_64(&p, ac->global_id);
+		au->buf_len = p - (void *)au->buf;
+		ai->built_authorizer = true;
+		dout("built authorizer len %d\n", au->buf_len);
+	}
+
+	*a = (struct ceph_authorizer *)au;
+	*buf = au->buf;
+	*len = au->buf_len;
+	*reply_buf = au->reply_buf;
+	*reply_len = sizeof(au->reply_buf);
+	return 0;
+
+bad2:
+	ret = -ERANGE;
+bad:
+	return ret;
+}
+
+static void ceph_auth_none_destroy_authorizer(struct ceph_auth_client *ac,
+				      struct ceph_authorizer *a)
+{
+	/* nothing to do */
+}
+
+static const struct ceph_auth_client_ops ceph_auth_none_ops = {
+	.reset = reset,
+	.destroy = destroy,
+	.is_authenticated = is_authenticated,
+	.handle_reply = handle_reply,
+	.create_authorizer = ceph_auth_none_create_authorizer,
+	.destroy_authorizer = ceph_auth_none_destroy_authorizer,
+};
+
+int ceph_auth_none_init(struct ceph_auth_client *ac)
+{
+	struct ceph_auth_none_info *xi;
+
+	dout("ceph_auth_none_init %p\n", ac);
+	xi = kzalloc(sizeof(*xi), GFP_NOFS);
+	if (!xi)
+		return -ENOMEM;
+
+	xi->starting = true;
+	xi->built_authorizer = false;
+
+	ac->protocol = CEPH_AUTH_NONE;
+	ac->private = xi;
+	ac->ops = &ceph_auth_none_ops;
+	return 0;
+}
+

fs/ceph/auth_none.h

@@ -0,0 +1,28 @@
+#ifndef _FS_CEPH_AUTH_NONE_H
+#define _FS_CEPH_AUTH_NONE_H
+
+#include "auth.h"
+
+/*
+ * null security mode.
+ *
+ * we use a single static authorizer that simply encodes our entity name
+ * and global id.
+ */
+
+struct ceph_none_authorizer {
+	char buf[128];
+	int buf_len;
+	char reply_buf[0];
+};
+
+struct ceph_auth_none_info {
+	bool starting;
+	bool built_authorizer;
+	struct ceph_none_authorizer au;   /* we only need one; it's static */
+};
+
+extern int ceph_auth_none_init(struct ceph_auth_client *ac);
+
+#endif
+

fs/ceph/auth_x.c

@@ -0,0 +1,656 @@
+
+#include "ceph_debug.h"
+
+#include <linux/err.h>
+#include <linux/module.h>
+#include <linux/random.h>
+
+#include "auth_x.h"
+#include "auth_x_protocol.h"
+#include "crypto.h"
+#include "auth.h"
+#include "decode.h"
+
+struct kmem_cache *ceph_x_ticketbuf_cachep;
+
+#define TEMP_TICKET_BUF_LEN	256
+
+static void ceph_x_validate_tickets(struct ceph_auth_client *ac, int *pneed);
+
+static int ceph_x_is_authenticated(struct ceph_auth_client *ac)
+{
+	struct ceph_x_info *xi = ac->private;
+	int need;
+
+	ceph_x_validate_tickets(ac, &need);
+	dout("ceph_x_is_authenticated want=%d need=%d have=%d\n",
+	     ac->want_keys, need, xi->have_keys);
+	return (ac->want_keys & xi->have_keys) == ac->want_keys;
+}
+
+static int ceph_x_encrypt(struct ceph_crypto_key *secret,
+			  void *ibuf, int ilen, void *obuf, size_t olen)
+{
+	struct ceph_x_encrypt_header head = {
+		.struct_v = 1,
+		.magic = cpu_to_le64(CEPHX_ENC_MAGIC)
+	};
+	size_t len = olen - sizeof(u32);
+	int ret;
+
+	ret = ceph_encrypt2(secret, obuf + sizeof(u32), &len,
+			    &head, sizeof(head), ibuf, ilen);
+	if (ret)
+		return ret;
+	ceph_encode_32(&obuf, len);
+	return len + sizeof(u32);
+}
+
+static int ceph_x_decrypt(struct ceph_crypto_key *secret,
+			  void **p, void *end, void *obuf, size_t olen)
+{
+	struct ceph_x_encrypt_header head;
+	size_t head_len = sizeof(head);
+	int len, ret;
+
+	len = ceph_decode_32(p);
+	if (*p + len > end)
+		return -EINVAL;
+
+	dout("ceph_x_decrypt len %d\n", len);
+	ret = ceph_decrypt2(secret, &head, &head_len, obuf, &olen,
+			    *p, len);
+	if (ret)
+		return ret;
+	if (head.struct_v != 1 || le64_to_cpu(head.magic) != CEPHX_ENC_MAGIC)
+		return -EPERM;
+	*p += len;
+	return olen;
+}
+
+/*
+ * get existing (or insert new) ticket handler
+ */
+struct ceph_x_ticket_handler *get_ticket_handler(struct ceph_auth_client *ac,
+						 int service)
+{
+	struct ceph_x_ticket_handler *th;
+	struct ceph_x_info *xi = ac->private;
+	struct rb_node *parent = NULL, **p = &xi->ticket_handlers.rb_node;
+
+	while (*p) {
+		parent = *p;
+		th = rb_entry(parent, struct ceph_x_ticket_handler, node);
+		if (service < th->service)
+			p = &(*p)->rb_left;
+		else if (service > th->service)
+			p = &(*p)->rb_right;
+		else
+			return th;
+	}
+
+	/* add it */
+	th = kzalloc(sizeof(*th), GFP_NOFS);
+	if (!th)
+		return ERR_PTR(-ENOMEM);
+	th->service = service;
+	rb_link_node(&th->node, parent, p);
+	rb_insert_color(&th->node, &xi->ticket_handlers);
+	return th;
+}
+
+static void remove_ticket_handler(struct ceph_auth_client *ac,
+				  struct ceph_x_ticket_handler *th)
+{
+	struct ceph_x_info *xi = ac->private;
+
+	dout("remove_ticket_handler %p %d\n", th, th->service);
+	rb_erase(&th->node, &xi->ticket_handlers);
+	ceph_crypto_key_destroy(&th->session_key);
+	if (th->ticket_blob)
+		ceph_buffer_put(th->ticket_blob);
+	kfree(th);
+}
+
+static int ceph_x_proc_ticket_reply(struct ceph_auth_client *ac,
+				    struct ceph_crypto_key *secret,
+				    void *buf, void *end)
+{
+	struct ceph_x_info *xi = ac->private;
+	int num;
+	void *p = buf;
+	int ret;
+	char *dbuf;
+	char *ticket_buf;
+	u8 struct_v;
+
+	dbuf = kmem_cache_alloc(ceph_x_ticketbuf_cachep, GFP_NOFS | GFP_ATOMIC);
+	if (!dbuf)
+		return -ENOMEM;
+
+	ret = -ENOMEM;
+	ticket_buf = kmem_cache_alloc(ceph_x_ticketbuf_cachep,
+				      GFP_NOFS | GFP_ATOMIC);
+	if (!ticket_buf)
+		goto out_dbuf;
+
+	ceph_decode_need(&p, end, 1 + sizeof(u32), bad);
+	struct_v = ceph_decode_8(&p);
+	if (struct_v != 1)
+		goto bad;
+	num = ceph_decode_32(&p);
+	dout("%d tickets\n", num);
+	while (num--) {
+		int type;
+		u8 struct_v;
+		struct ceph_x_ticket_handler *th;
+		void *dp, *dend;
+		int dlen;
+		char is_enc;
+		struct timespec validity;
+		struct ceph_crypto_key old_key;
+		void *tp, *tpend;
+
+		ceph_decode_need(&p, end, sizeof(u32) + 1, bad);
+
+		type = ceph_decode_32(&p);
+		dout(" ticket type %d %s\n", type, ceph_entity_type_name(type));
+
+		struct_v = ceph_decode_8(&p);
+		if (struct_v != 1)
+			goto bad;
+
+		th = get_ticket_handler(ac, type);
+		if (IS_ERR(th)) {
+			ret = PTR_ERR(th);
+			goto out;
+		}
+
+		/* blob for me */
+		dlen = ceph_x_decrypt(secret, &p, end, dbuf,
+				      TEMP_TICKET_BUF_LEN);
+		if (dlen <= 0) {
+			ret = dlen;
+			goto out;
+		}
+		dout(" decrypted %d bytes\n", dlen);
+		dend = dbuf + dlen;
+		dp = dbuf;
+
+		struct_v = ceph_decode_8(&dp);
+		if (struct_v != 1)
+			goto bad;
+
+		memcpy(&old_key, &th->session_key, sizeof(old_key));
+		ret = ceph_crypto_key_decode(&th->session_key, &dp, dend);
+		if (ret)
+			goto out;
+
+		ceph_decode_copy(&dp, &th->validity, sizeof(th->validity));
+		ceph_decode_timespec(&validity, &th->validity);
+		th->expires = get_seconds() + validity.tv_sec;
+		th->renew_after = th->expires - (validity.tv_sec / 4);
+		dout(" expires=%lu renew_after=%lu\n", th->expires,
+		     th->renew_after);
+
+		/* ticket blob for service */
+		ceph_decode_8_safe(&p, end, is_enc, bad);
+		tp = ticket_buf;
+		if (is_enc) {
+			/* encrypted */
+			dout(" encrypted ticket\n");
+			dlen = ceph_x_decrypt(&old_key, &p, end, ticket_buf,
+					      TEMP_TICKET_BUF_LEN);
+			if (dlen < 0) {
+				ret = dlen;
+				goto out;
+			}
+			dlen = ceph_decode_32(&tp);
+		} else {
+			/* unencrypted */
+			ceph_decode_32_safe(&p, end, dlen, bad);
+			ceph_decode_need(&p, end, dlen, bad);
+			ceph_decode_copy(&p, ticket_buf, dlen);
+		}
+		tpend = tp + dlen;
+		dout(" ticket blob is %d bytes\n", dlen);
+		ceph_decode_need(&tp, tpend, 1 + sizeof(u64), bad);
+		struct_v = ceph_decode_8(&tp);
+		th->secret_id = ceph_decode_64(&tp);
+		ret = ceph_decode_buffer(&th->ticket_blob, &tp, tpend);
+		if (ret)
+			goto out;
+		dout(" got ticket service %d (%s) secret_id %lld len %d\n",
+		     type, ceph_entity_type_name(type), th->secret_id,
+		     (int)th->ticket_blob->vec.iov_len);
+		xi->have_keys |= th->service;
+	}
+
+	ret = 0;
+out:
+	kmem_cache_free(ceph_x_ticketbuf_cachep, ticket_buf);
+out_dbuf:
+	kmem_cache_free(ceph_x_ticketbuf_cachep, dbuf);
+	return ret;
+
+bad:
+	ret = -EINVAL;
+	goto out;
+}
+
+static int ceph_x_build_authorizer(struct ceph_auth_client *ac,
+				   struct ceph_x_ticket_handler *th,
+				   struct ceph_x_authorizer *au)
+{
+	int len;
+	struct ceph_x_authorize_a *msg_a;
+	struct ceph_x_authorize_b msg_b;
+	void *p, *end;
+	int ret;
+	int ticket_blob_len =
+		(th->ticket_blob ? th->ticket_blob->vec.iov_len : 0);
+
+	dout("build_authorizer for %s %p\n",
+	     ceph_entity_type_name(th->service), au);
+
+	len = sizeof(*msg_a) + sizeof(msg_b) + sizeof(u32) +
+		ticket_blob_len + 16;
+	dout("  need len %d\n", len);
+	if (au->buf && au->buf->alloc_len < len) {
+		ceph_buffer_put(au->buf);
+		au->buf = NULL;
+	}
+	if (!au->buf) {
+		au->buf = ceph_buffer_new(len, GFP_NOFS);
+		if (!au->buf)
+			return -ENOMEM;
+	}
+	au->service = th->service;
+
+	msg_a = au->buf->vec.iov_base;
+	msg_a->struct_v = 1;
+	msg_a->global_id = cpu_to_le64(ac->global_id);
+	msg_a->service_id = cpu_to_le32(th->service);
+	msg_a->ticket_blob.struct_v = 1;
+	msg_a->ticket_blob.secret_id = cpu_to_le64(th->secret_id);
+	msg_a->ticket_blob.blob_len = cpu_to_le32(ticket_blob_len);
+	if (ticket_blob_len) {
+		memcpy(msg_a->ticket_blob.blob, th->ticket_blob->vec.iov_base,
+		       th->ticket_blob->vec.iov_len);
+	}
+	dout(" th %p secret_id %lld %lld\n", th, th->secret_id,
+	     le64_to_cpu(msg_a->ticket_blob.secret_id));
+
+	p = msg_a + 1;
+	p += ticket_blob_len;
+	end = au->buf->vec.iov_base + au->buf->vec.iov_len;
+
+	get_random_bytes(&au->nonce, sizeof(au->nonce));
+	msg_b.struct_v = 1;
+	msg_b.nonce = cpu_to_le64(au->nonce);
+	ret = ceph_x_encrypt(&th->session_key, &msg_b, sizeof(msg_b),
+			     p, end - p);
+	if (ret < 0)
+		goto out_buf;
+	p += ret;
+	au->buf->vec.iov_len = p - au->buf->vec.iov_base;
+	dout(" built authorizer nonce %llx len %d\n", au->nonce,
+	     (int)au->buf->vec.iov_len);
+	return 0;
+
+out_buf:
+	ceph_buffer_put(au->buf);
+	au->buf = NULL;
+	return ret;
+}
+
+static int ceph_x_encode_ticket(struct ceph_x_ticket_handler *th,
+				void **p, void *end)
+{
+	ceph_decode_need(p, end, 1 + sizeof(u64), bad);
+	ceph_encode_8(p, 1);
+	ceph_encode_64(p, th->secret_id);
+	if (th->ticket_blob) {
+		const char *buf = th->ticket_blob->vec.iov_base;
+		u32 len = th->ticket_blob->vec.iov_len;
+
+		ceph_encode_32_safe(p, end, len, bad);
+		ceph_encode_copy_safe(p, end, buf, len, bad);
+	} else {
+		ceph_encode_32_safe(p, end, 0, bad);
+	}
+
+	return 0;
+bad:
+	return -ERANGE;
+}
+
+static void ceph_x_validate_tickets(struct ceph_auth_client *ac, int *pneed)
+{
+	int want = ac->want_keys;
+	struct ceph_x_info *xi = ac->private;
+	int service;
+
+	*pneed = ac->want_keys & ~(xi->have_keys);
+
+	for (service = 1; service <= want; service <<= 1) {
+		struct ceph_x_ticket_handler *th;
+
+		if (!(ac->want_keys & service))
+			continue;
+
+		if (*pneed & service)
+			continue;
+
+		th = get_ticket_handler(ac, service);
+
+		if (!th) {
+			*pneed |= service;
+			continue;
+		}
+
+		if (get_seconds() >= th->renew_after)
+			*pneed |= service;
+		if (get_seconds() >= th->expires)
+			xi->have_keys &= ~service;
+	}
+}
+
+
+static int ceph_x_build_request(struct ceph_auth_client *ac,
+				void *buf, void *end)
+{
+	struct ceph_x_info *xi = ac->private;
+	int need;
+	struct ceph_x_request_header *head = buf;
+	int ret;
+	struct ceph_x_ticket_handler *th =
+		get_ticket_handler(ac, CEPH_ENTITY_TYPE_AUTH);
+
+	ceph_x_validate_tickets(ac, &need);
+
+	dout("build_request want %x have %x need %x\n",
+	     ac->want_keys, xi->have_keys, need);
+
+	if (need & CEPH_ENTITY_TYPE_AUTH) {
+		struct ceph_x_authenticate *auth = (void *)(head + 1);
+		void *p = auth + 1;
+		struct ceph_x_challenge_blob tmp;
+		char tmp_enc[40];
+		u64 *u;
+
+		if (p > end)
+			return -ERANGE;
+
+		dout(" get_auth_session_key\n");
+		head->op = cpu_to_le16(CEPHX_GET_AUTH_SESSION_KEY);
+
+		/* encrypt and hash */
+		get_random_bytes(&auth->client_challenge, sizeof(u64));
+		tmp.client_challenge = auth->client_challenge;
+		tmp.server_challenge = cpu_to_le64(xi->server_challenge);
+		ret = ceph_x_encrypt(&xi->secret, &tmp, sizeof(tmp),
+				     tmp_enc, sizeof(tmp_enc));
+		if (ret < 0)
+			return ret;
+
+		auth->struct_v = 1;
+		auth->key = 0;
+		for (u = (u64 *)tmp_enc; u + 1 <= (u64 *)(tmp_enc + ret); u++)
+			auth->key ^= *u;
+		dout(" server_challenge %llx client_challenge %llx key %llx\n",
+		     xi->server_challenge, le64_to_cpu(auth->client_challenge),
+		     le64_to_cpu(auth->key));
+
+		/* now encode the old ticket if exists */
+		ret = ceph_x_encode_ticket(th, &p, end);
+		if (ret < 0)
+			return ret;
+
+		return p - buf;
+	}
+
+	if (need) {
+		void *p = head + 1;
+		struct ceph_x_service_ticket_request *req;
+
+		if (p > end)
+			return -ERANGE;
+		head->op = cpu_to_le16(CEPHX_GET_PRINCIPAL_SESSION_KEY);
+
+		BUG_ON(!th);
+		ret = ceph_x_build_authorizer(ac, th, &xi->auth_authorizer);
+		if (ret)
+			return ret;
+		ceph_encode_copy(&p, xi->auth_authorizer.buf->vec.iov_base,
+				 xi->auth_authorizer.buf->vec.iov_len);
+
+		req = p;
+		req->keys = cpu_to_le32(need);
+		p += sizeof(*req);
+		return p - buf;
+	}
+
+	return 0;
+}
+
+static int ceph_x_handle_reply(struct ceph_auth_client *ac, int result,
+			       void *buf, void *end)
+{
+	struct ceph_x_info *xi = ac->private;
+	struct ceph_x_reply_header *head = buf;
+	struct ceph_x_ticket_handler *th;
+	int len = end - buf;
+	int op;
+	int ret;
+
+	if (result)
+		return result;  /* XXX hmm? */
+
+	if (xi->starting) {
+		/* it's a hello */
+		struct ceph_x_server_challenge *sc = buf;
+
+		if (len != sizeof(*sc))
+			return -EINVAL;
+		xi->server_challenge = le64_to_cpu(sc->server_challenge);
+		dout("handle_reply got server challenge %llx\n",
+		     xi->server_challenge);
+		xi->starting = false;
+		xi->have_keys &= ~CEPH_ENTITY_TYPE_AUTH;
+		return -EAGAIN;
+	}
+
+	op = le32_to_cpu(head->op);
+	result = le32_to_cpu(head->result);
+	dout("handle_reply op %d result %d\n", op, result);
+	switch (op) {
+	case CEPHX_GET_AUTH_SESSION_KEY:
+		/* verify auth key */
+		ret = ceph_x_proc_ticket_reply(ac, &xi->secret,
+					       buf + sizeof(*head), end);
+		break;
+
+	case CEPHX_GET_PRINCIPAL_SESSION_KEY:
+		th = get_ticket_handler(ac, CEPH_ENTITY_TYPE_AUTH);
+		BUG_ON(!th);
+		ret = ceph_x_proc_ticket_reply(ac, &th->session_key,
+					       buf + sizeof(*head), end);
+		break;
+
+	default:
+		return -EINVAL;
+	}
+	if (ret)
+		return ret;
+	if (ac->want_keys == xi->have_keys)
+		return 0;
+	return -EAGAIN;
+}
+
+static int ceph_x_create_authorizer(
+	struct ceph_auth_client *ac, int peer_type,
+	struct ceph_authorizer **a,
+	void **buf, size_t *len,
+	void **reply_buf, size_t *reply_len)
+{
+	struct ceph_x_authorizer *au;
+	struct ceph_x_ticket_handler *th;
+	int ret;
+
+	th = get_ticket_handler(ac, peer_type);
+	if (IS_ERR(th))
+		return PTR_ERR(th);
+
+	au = kzalloc(sizeof(*au), GFP_NOFS);
+	if (!au)
+		return -ENOMEM;
+
+	ret = ceph_x_build_authorizer(ac, th, au);
+	if (ret) {
+		kfree(au);
+		return ret;
+	}
+
+	*a = (struct ceph_authorizer *)au;
+	*buf = au->buf->vec.iov_base;
+	*len = au->buf->vec.iov_len;
+	*reply_buf = au->reply_buf;
+	*reply_len = sizeof(au->reply_buf);
+	return 0;
+}
+
+static int ceph_x_verify_authorizer_reply(struct ceph_auth_client *ac,
+					  struct ceph_authorizer *a, size_t len)
+{
+	struct ceph_x_authorizer *au = (void *)a;
+	struct ceph_x_ticket_handler *th;
+	int ret = 0;
+	struct ceph_x_authorize_reply reply;
+	void *p = au->reply_buf;
+	void *end = p + sizeof(au->reply_buf);
+
+	th = get_ticket_handler(ac, au->service);
+	if (!th)
+		return -EIO;  /* hrm! */
+	ret = ceph_x_decrypt(&th->session_key, &p, end, &reply, sizeof(reply));
+	if (ret < 0)
+		return ret;
+	if (ret != sizeof(reply))
+		return -EPERM;
+
+	if (au->nonce + 1 != le64_to_cpu(reply.nonce_plus_one))
+		ret = -EPERM;
+	else
+		ret = 0;
+	dout("verify_authorizer_reply nonce %llx got %llx ret %d\n",
+	     au->nonce, le64_to_cpu(reply.nonce_plus_one), ret);
+	return ret;
+}
+
+static void ceph_x_destroy_authorizer(struct ceph_auth_client *ac,
+				      struct ceph_authorizer *a)
+{
+	struct ceph_x_authorizer *au = (void *)a;
+
+	ceph_buffer_put(au->buf);
+	kfree(au);
+}
+
+
+static void ceph_x_reset(struct ceph_auth_client *ac)
+{
+	struct ceph_x_info *xi = ac->private;
+
+	dout("reset\n");
+	xi->starting = true;
+	xi->server_challenge = 0;
+}
+
+static void ceph_x_destroy(struct ceph_auth_client *ac)
+{
+	struct ceph_x_info *xi = ac->private;
+	struct rb_node *p;
+
+	dout("ceph_x_destroy %p\n", ac);
+	ceph_crypto_key_destroy(&xi->secret);
+
+	while ((p = rb_first(&xi->ticket_handlers)) != NULL) {
+		struct ceph_x_ticket_handler *th =
+			rb_entry(p, struct ceph_x_ticket_handler, node);
+		remove_ticket_handler(ac, th);
+	}
+
+	kmem_cache_destroy(ceph_x_ticketbuf_cachep);
+
+	kfree(ac->private);
+	ac->private = NULL;
+}
+
+static void ceph_x_invalidate_authorizer(struct ceph_auth_client *ac,
+				   int peer_type)
+{
+	struct ceph_x_ticket_handler *th;
+
+	th = get_ticket_handler(ac, peer_type);
+	if (th && !IS_ERR(th))
+		remove_ticket_handler(ac, th);
+}
+
+
+static const struct ceph_auth_client_ops ceph_x_ops = {
+	.is_authenticated = ceph_x_is_authenticated,
+	.build_request = ceph_x_build_request,
+	.handle_reply = ceph_x_handle_reply,
+	.create_authorizer = ceph_x_create_authorizer,
+	.verify_authorizer_reply = ceph_x_verify_authorizer_reply,
+	.destroy_authorizer = ceph_x_destroy_authorizer,
+	.invalidate_authorizer = ceph_x_invalidate_authorizer,
+	.reset =  ceph_x_reset,
+	.destroy = ceph_x_destroy,
+};
+
+
+int ceph_x_init(struct ceph_auth_client *ac)
+{
+	struct ceph_x_info *xi;
+	int ret;
+
+	dout("ceph_x_init %p\n", ac);
+	xi = kzalloc(sizeof(*xi), GFP_NOFS);
+	if (!xi)
+		return -ENOMEM;
+
+	ret = -ENOMEM;
+	ceph_x_ticketbuf_cachep = kmem_cache_create("ceph_x_ticketbuf",
+				      TEMP_TICKET_BUF_LEN, 8,
+				      (SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD),
+				      NULL);
+	if (!ceph_x_ticketbuf_cachep)
+		goto done_nomem;
+	ret = -EINVAL;
+	if (!ac->secret) {
+		pr_err("no secret set (for auth_x protocol)\n");
+		goto done_nomem;
+	}
+
+	ret = ceph_crypto_key_unarmor(&xi->secret, ac->secret);
+	if (ret)
+		goto done_nomem;
+
+	xi->starting = true;
+	xi->ticket_handlers = RB_ROOT;
+
+	ac->protocol = CEPH_AUTH_CEPHX;
+	ac->private = xi;
+	ac->ops = &ceph_x_ops;
+	return 0;
+
+done_nomem:
+	kfree(xi);
+	if (ceph_x_ticketbuf_cachep)
+		kmem_cache_destroy(ceph_x_ticketbuf_cachep);
+	return ret;
+}
+
+

fs/ceph/auth_x.h

@@ -0,0 +1,49 @@
+#ifndef _FS_CEPH_AUTH_X_H
+#define _FS_CEPH_AUTH_X_H
+
+#include <linux/rbtree.h>
+
+#include "crypto.h"
+#include "auth.h"
+#include "auth_x_protocol.h"
+
+/*
+ * Handle ticket for a single service.
+ */
+struct ceph_x_ticket_handler {
+	struct rb_node node;
+	unsigned service;
+
+	struct ceph_crypto_key session_key;
+	struct ceph_timespec validity;
+
+	u64 secret_id;
+	struct ceph_buffer *ticket_blob;
+
+	unsigned long renew_after, expires;
+};
+
+
+struct ceph_x_authorizer {
+	struct ceph_buffer *buf;
+	unsigned service;
+	u64 nonce;
+	char reply_buf[128];  /* big enough for encrypted blob */
+};
+
+struct ceph_x_info {
+	struct ceph_crypto_key secret;
+
+	bool starting;
+	u64 server_challenge;
+
+	unsigned have_keys;
+	struct rb_root ticket_handlers;
+
+	struct ceph_x_authorizer auth_authorizer;
+};
+
+extern int ceph_x_init(struct ceph_auth_client *ac);
+
+#endif
+

fs/ceph/auth_x_protocol.h

@@ -0,0 +1,90 @@
+#ifndef __FS_CEPH_AUTH_X_PROTOCOL
+#define __FS_CEPH_AUTH_X_PROTOCOL
+
+#define CEPHX_GET_AUTH_SESSION_KEY      0x0100
+#define CEPHX_GET_PRINCIPAL_SESSION_KEY 0x0200
+#define CEPHX_GET_ROTATING_KEY          0x0400
+
+/* common bits */
+struct ceph_x_ticket_blob {
+	__u8 struct_v;
+	__le64 secret_id;
+	__le32 blob_len;
+	char blob[];
+} __attribute__ ((packed));
+
+
+/* common request/reply headers */
+struct ceph_x_request_header {
+	__le16 op;
+} __attribute__ ((packed));
+
+struct ceph_x_reply_header {
+	__le16 op;
+	__le32 result;
+} __attribute__ ((packed));
+
+
+/* authenticate handshake */
+
+/* initial hello (no reply header) */
+struct ceph_x_server_challenge {
+	__u8 struct_v;
+	__le64 server_challenge;
+} __attribute__ ((packed));
+
+struct ceph_x_authenticate {
+	__u8 struct_v;
+	__le64 client_challenge;
+	__le64 key;
+	/* ticket blob */
+} __attribute__ ((packed));
+
+struct ceph_x_service_ticket_request {
+	__u8 struct_v;
+	__le32 keys;
+} __attribute__ ((packed));
+
+struct ceph_x_challenge_blob {
+	__le64 server_challenge;
+	__le64 client_challenge;
+} __attribute__ ((packed));
+
+
+
+/* authorize handshake */
+
+/*
+ * The authorizer consists of two pieces:
+ *  a - service id, ticket blob
+ *  b - encrypted with session key
+ */
+struct ceph_x_authorize_a {
+	__u8 struct_v;
+	__le64 global_id;
+	__le32 service_id;
+	struct ceph_x_ticket_blob ticket_blob;
+} __attribute__ ((packed));
+
+struct ceph_x_authorize_b {
+	__u8 struct_v;
+	__le64 nonce;
+} __attribute__ ((packed));
+
+struct ceph_x_authorize_reply {
+	__u8 struct_v;
+	__le64 nonce_plus_one;
+} __attribute__ ((packed));
+
+
+/*
+ * encyption bundle
+ */
+#define CEPHX_ENC_MAGIC 0xff009cad8826aa55ull
+
+struct ceph_x_encrypt_header {
+	__u8 struct_v;
+	__le64 magic;
+} __attribute__ ((packed));
+
+#endif

fs/ceph/buffer.c

@@ -0,0 +1,78 @@
+
+#include "ceph_debug.h"
+#include "buffer.h"
+#include "decode.h"
+
+struct ceph_buffer *ceph_buffer_new(size_t len, gfp_t gfp)
+{
+	struct ceph_buffer *b;
+
+	b = kmalloc(sizeof(*b), gfp);
+	if (!b)
+		return NULL;
+
+	b->vec.iov_base = kmalloc(len, gfp | __GFP_NOWARN);
+	if (b->vec.iov_base) {
+		b->is_vmalloc = false;
+	} else {
+		b->vec.iov_base = __vmalloc(len, gfp, PAGE_KERNEL);
+		if (!b->vec.iov_base) {
+			kfree(b);
+			return NULL;
+		}
+		b->is_vmalloc = true;
+	}
+
+	kref_init(&b->kref);
+	b->alloc_len = len;
+	b->vec.iov_len = len;
+	dout("buffer_new %p\n", b);
+	return b;
+}
+
+void ceph_buffer_release(struct kref *kref)
+{
+	struct ceph_buffer *b = container_of(kref, struct ceph_buffer, kref);
+
+	dout("buffer_release %p\n", b);
+	if (b->vec.iov_base) {
+		if (b->is_vmalloc)
+			vfree(b->vec.iov_base);
+		else
+			kfree(b->vec.iov_base);
+	}
+	kfree(b);
+}
+
+int ceph_buffer_alloc(struct ceph_buffer *b, int len, gfp_t gfp)
+{
+	b->vec.iov_base = kmalloc(len, gfp | __GFP_NOWARN);
+	if (b->vec.iov_base) {
+		b->is_vmalloc = false;
+	} else {
+		b->vec.iov_base = __vmalloc(len, gfp, PAGE_KERNEL);
+		b->is_vmalloc = true;
+	}
+	if (!b->vec.iov_base)
+		return -ENOMEM;
+	b->alloc_len = len;
+	b->vec.iov_len = len;
+	return 0;
+}
+
+int ceph_decode_buffer(struct ceph_buffer **b, void **p, void *end)
+{
+	size_t len;
+
+	ceph_decode_need(p, end, sizeof(u32), bad);
+	len = ceph_decode_32(p);
+	dout("decode_buffer len %d\n", (int)len);
+	ceph_decode_need(p, end, len, bad);
+	*b = ceph_buffer_new(len, GFP_NOFS);
+	if (!*b)
+		return -ENOMEM;
+	ceph_decode_copy(p, (*b)->vec.iov_base, len);
+	return 0;
+bad:
+	return -EINVAL;
+}

fs/ceph/buffer.h

@@ -0,0 +1,39 @@
+#ifndef __FS_CEPH_BUFFER_H
+#define __FS_CEPH_BUFFER_H
+
+#include <linux/kref.h>
+#include <linux/mm.h>
+#include <linux/vmalloc.h>
+#include <linux/types.h>
+#include <linux/uio.h>
+
+/*
+ * a simple reference counted buffer.
+ *
+ * use kmalloc for small sizes (<= one page), vmalloc for larger
+ * sizes.
+ */
+struct ceph_buffer {
+	struct kref kref;
+	struct kvec vec;
+	size_t alloc_len;
+	bool is_vmalloc;
+};
+
+extern struct ceph_buffer *ceph_buffer_new(size_t len, gfp_t gfp);
+extern void ceph_buffer_release(struct kref *kref);
+
+static inline struct ceph_buffer *ceph_buffer_get(struct ceph_buffer *b)
+{
+	kref_get(&b->kref);
+	return b;
+}
+
+static inline void ceph_buffer_put(struct ceph_buffer *b)
+{
+	kref_put(&b->kref, ceph_buffer_release);
+}
+
+extern int ceph_decode_buffer(struct ceph_buffer **b, void **p, void *end);
+
+#endif

fs/ceph/ceph_debug.h

@@ -0,0 +1,37 @@
+#ifndef _FS_CEPH_DEBUG_H
+#define _FS_CEPH_DEBUG_H
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#ifdef CONFIG_CEPH_FS_PRETTYDEBUG
+
+/*
+ * wrap pr_debug to include a filename:lineno prefix on each line.
+ * this incurs some overhead (kernel size and execution time) due to
+ * the extra function call at each call site.
+ */
+
+# if defined(DEBUG) || defined(CONFIG_DYNAMIC_DEBUG)
+extern const char *ceph_file_part(const char *s, int len);
+#  define dout(fmt, ...)						\
+	pr_debug(" %12.12s:%-4d : " fmt,				\
+		 ceph_file_part(__FILE__, sizeof(__FILE__)),		\
+		 __LINE__, ##__VA_ARGS__)
+# else
+/* faux printk call just to see any compiler warnings. */
+#  define dout(fmt, ...)	do {				\
+		if (0)						\
+			printk(KERN_DEBUG fmt, ##__VA_ARGS__);	\
+	} while (0)
+# endif
+
+#else
+
+/*
+ * or, just wrap pr_debug
+ */
+# define dout(fmt, ...)	pr_debug(" " fmt, ##__VA_ARGS__)
+
+#endif
+
+#endif

fs/ceph/ceph_frag.c

@@ -0,0 +1,21 @@
+/*
+ * Ceph 'frag' type
+ */
+#include "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/ceph_frag.h

@@ -0,0 +1,109 @@
+#ifndef _FS_CEPH_FRAG_H
+#define _FS_CEPH_FRAG_H
+
+/*
+ * "Frags" are a way to describe a subset of a 32-bit number space,
+ * using a mask and a value to match against that mask.  Any given frag
+ * (subset of the number space) can be partitioned into 2^n sub-frags.
+ *
+ * Frags are encoded into a 32-bit word:
+ *   8 upper bits = "bits"
+ *  24 lower bits = "value"
+ * (We could go to 5+27 bits, but who cares.)
+ *
+ * We use the _most_ significant bits of the 24 bit value.  This makes
+ * values logically sort.
+ *
+ * Unfortunately, because the "bits" field is still in the high bits, we
+ * can't sort encoded frags numerically.  However, it does allow you
+ * to feed encoded frags as values into frag_contains_value.
+ */
+static inline __u32 ceph_frag_make(__u32 b, __u32 v)
+{
+	return (b << 24) |
+		(v & (0xffffffu << (24-b)) & 0xffffffu);
+}
+static inline __u32 ceph_frag_bits(__u32 f)
+{
+	return f >> 24;
+}
+static inline __u32 ceph_frag_value(__u32 f)
+{
+	return f & 0xffffffu;
+}
+static inline __u32 ceph_frag_mask(__u32 f)
+{
+	return (0xffffffu << (24-ceph_frag_bits(f))) & 0xffffffu;
+}
+static inline __u32 ceph_frag_mask_shift(__u32 f)
+{
+	return 24 - ceph_frag_bits(f);
+}
+
+static inline int ceph_frag_contains_value(__u32 f, __u32 v)
+{
+	return (v & ceph_frag_mask(f)) == ceph_frag_value(f);
+}
+static inline int ceph_frag_contains_frag(__u32 f, __u32 sub)
+{
+	/* is sub as specific as us, and contained by us? */
+	return ceph_frag_bits(sub) >= ceph_frag_bits(f) &&
+	       (ceph_frag_value(sub) & ceph_frag_mask(f)) == ceph_frag_value(f);
+}
+
+static inline __u32 ceph_frag_parent(__u32 f)
+{
+	return ceph_frag_make(ceph_frag_bits(f) - 1,
+			 ceph_frag_value(f) & (ceph_frag_mask(f) << 1));
+}
+static inline int ceph_frag_is_left_child(__u32 f)
+{
+	return ceph_frag_bits(f) > 0 &&
+		(ceph_frag_value(f) & (0x1000000 >> ceph_frag_bits(f))) == 0;
+}
+static inline int ceph_frag_is_right_child(__u32 f)
+{
+	return ceph_frag_bits(f) > 0 &&
+		(ceph_frag_value(f) & (0x1000000 >> ceph_frag_bits(f))) == 1;
+}
+static inline __u32 ceph_frag_sibling(__u32 f)
+{
+	return ceph_frag_make(ceph_frag_bits(f),
+		      ceph_frag_value(f) ^ (0x1000000 >> ceph_frag_bits(f)));
+}
+static inline __u32 ceph_frag_left_child(__u32 f)
+{
+	return ceph_frag_make(ceph_frag_bits(f)+1, ceph_frag_value(f));
+}
+static inline __u32 ceph_frag_right_child(__u32 f)
+{
+	return ceph_frag_make(ceph_frag_bits(f)+1,
+	      ceph_frag_value(f) | (0x1000000 >> (1+ceph_frag_bits(f))));
+}
+static inline __u32 ceph_frag_make_child(__u32 f, int by, int i)
+{
+	int newbits = ceph_frag_bits(f) + by;
+	return ceph_frag_make(newbits,
+			 ceph_frag_value(f) | (i << (24 - newbits)));
+}
+static inline int ceph_frag_is_leftmost(__u32 f)
+{
+	return ceph_frag_value(f) == 0;
+}
+static inline int ceph_frag_is_rightmost(__u32 f)
+{
+	return ceph_frag_value(f) == ceph_frag_mask(f);
+}
+static inline __u32 ceph_frag_next(__u32 f)
+{
+	return ceph_frag_make(ceph_frag_bits(f),
+			 ceph_frag_value(f) + (0x1000000 >> ceph_frag_bits(f)));
+}
+
+/*
+ * comparator to sort frags logically, as when traversing the
+ * number space in ascending order...
+ */
+int ceph_frag_compare(__u32 a, __u32 b);
+
+#endif

fs/ceph/ceph_fs.c

@@ -0,0 +1,74 @@
+/*
+ * Some non-inline ceph helpers
+ */
+#include "types.h"
+
+/*
+ * return true if @layout appears to be valid
+ */
+int ceph_file_layout_is_valid(const struct ceph_file_layout *layout)
+{
+	__u32 su = le32_to_cpu(layout->fl_stripe_unit);
+	__u32 sc = le32_to_cpu(layout->fl_stripe_count);
+	__u32 os = le32_to_cpu(layout->fl_object_size);
+
+	/* stripe unit, object size must be non-zero, 64k increment */
+	if (!su || (su & (CEPH_MIN_STRIPE_UNIT-1)))
+		return 0;
+	if (!os || (os & (CEPH_MIN_STRIPE_UNIT-1)))
+		return 0;
+	/* object size must be a multiple of stripe unit */
+	if (os < su || os % su)
+		return 0;
+	/* stripe count must be non-zero */
+	if (!sc)
+		return 0;
+	return 1;
+}
+
+
+int ceph_flags_to_mode(int flags)
+{
+#ifdef O_DIRECTORY  /* fixme */
+	if ((flags & O_DIRECTORY) == O_DIRECTORY)
+		return CEPH_FILE_MODE_PIN;
+#endif
+#ifdef O_LAZY
+	if (flags & O_LAZY)
+		return CEPH_FILE_MODE_LAZY;
+#endif
+	if ((flags & O_APPEND) == O_APPEND)
+		flags |= O_WRONLY;
+
+	flags &= O_ACCMODE;
+	if ((flags & O_RDWR) == O_RDWR)
+		return CEPH_FILE_MODE_RDWR;
+	if ((flags & O_WRONLY) == O_WRONLY)
+		return CEPH_FILE_MODE_WR;
+	return CEPH_FILE_MODE_RD;
+}
+
+int ceph_caps_for_mode(int mode)
+{
+	switch (mode) {
+	case CEPH_FILE_MODE_PIN:
+		return CEPH_CAP_PIN;
+	case CEPH_FILE_MODE_RD:
+		return CEPH_CAP_PIN | CEPH_CAP_FILE_SHARED |
+			CEPH_CAP_FILE_RD | CEPH_CAP_FILE_CACHE;
+	case CEPH_FILE_MODE_RDWR:
+		return CEPH_CAP_PIN | CEPH_CAP_FILE_SHARED |
+			CEPH_CAP_FILE_EXCL |
+			CEPH_CAP_FILE_RD | CEPH_CAP_FILE_CACHE |
+			CEPH_CAP_FILE_WR | CEPH_CAP_FILE_BUFFER |
+			CEPH_CAP_AUTH_SHARED | CEPH_CAP_AUTH_EXCL |
+			CEPH_CAP_XATTR_SHARED | CEPH_CAP_XATTR_EXCL;
+	case CEPH_FILE_MODE_WR:
+		return CEPH_CAP_PIN | CEPH_CAP_FILE_SHARED |
+			CEPH_CAP_FILE_EXCL |
+			CEPH_CAP_FILE_WR | CEPH_CAP_FILE_BUFFER |
+			CEPH_CAP_AUTH_SHARED | CEPH_CAP_AUTH_EXCL |
+			CEPH_CAP_XATTR_SHARED | CEPH_CAP_XATTR_EXCL;
+	}
+	return 0;
+}

fs/ceph/ceph_fs.h

@@ -0,0 +1,650 @@
+/*
+ * ceph_fs.h - Ceph constants and data types to share between kernel and
+ * user space.
+ *
+ * Most types in this file are defined as little-endian, and are
+ * primarily intended to describe data structures that pass over the
+ * wire or that are stored on disk.
+ *
+ * LGPL2
+ */
+
+#ifndef _FS_CEPH_CEPH_FS_H
+#define _FS_CEPH_CEPH_FS_H
+
+#include "msgr.h"
+#include "rados.h"
+
+/*
+ * Ceph release version
+ */
+#define CEPH_VERSION_MAJOR 0
+#define CEPH_VERSION_MINOR 19
+#define CEPH_VERSION_PATCH 0
+
+#define _CEPH_STRINGIFY(x) #x
+#define CEPH_STRINGIFY(x) _CEPH_STRINGIFY(x)
+#define CEPH_MAKE_VERSION(x, y, z) CEPH_STRINGIFY(x) "." CEPH_STRINGIFY(y) \
+	"." CEPH_STRINGIFY(z)
+#define CEPH_VERSION CEPH_MAKE_VERSION(CEPH_VERSION_MAJOR, \
+				       CEPH_VERSION_MINOR, CEPH_VERSION_PATCH)
+
+/*
+ * subprotocol versions.  when specific messages types or high-level
+ * protocols change, bump the affected components.  we keep rev
+ * internal cluster protocols separately from the public,
+ * client-facing protocol.
+ */
+#define CEPH_OSD_PROTOCOL     8 /* cluster internal */
+#define CEPH_MDS_PROTOCOL     9 /* cluster internal */
+#define CEPH_MON_PROTOCOL     5 /* cluster internal */
+#define CEPH_OSDC_PROTOCOL   24 /* server/client */
+#define CEPH_MDSC_PROTOCOL   32 /* server/client */
+#define CEPH_MONC_PROTOCOL   15 /* server/client */
+
+
+#define CEPH_INO_ROOT  1
+#define CEPH_INO_CEPH  2        /* hidden .ceph dir */
+
+/* arbitrary limit on max # of monitors (cluster of 3 is typical) */
+#define CEPH_MAX_MON   31
+
+
+/*
+ * feature bits
+ */
+#define CEPH_FEATURE_SUPPORTED  0
+#define CEPH_FEATURE_REQUIRED   0
+
+
+/*
+ * ceph_file_layout - describe data layout for a file/inode
+ */
+struct ceph_file_layout {
+	/* file -> object mapping */
+	__le32 fl_stripe_unit;     /* stripe unit, in bytes.  must be multiple
+				      of page size. */
+	__le32 fl_stripe_count;    /* over this many objects */
+	__le32 fl_object_size;     /* until objects are this big, then move to
+				      new objects */
+	__le32 fl_cas_hash;        /* 0 = none; 1 = sha256 */
+
+	/* pg -> disk layout */
+	__le32 fl_object_stripe_unit;  /* for per-object parity, if any */
+
+	/* object -> pg layout */
+	__le32 fl_pg_preferred; /* preferred primary for pg (-1 for none) */
+	__le32 fl_pg_pool;      /* namespace, crush ruleset, rep level */
+} __attribute__ ((packed));
+
+#define CEPH_MIN_STRIPE_UNIT 65536
+
+int ceph_file_layout_is_valid(const struct ceph_file_layout *layout);
+
+
+/* crypto algorithms */
+#define CEPH_CRYPTO_NONE 0x0
+#define CEPH_CRYPTO_AES  0x1
+
+/* security/authentication protocols */
+#define CEPH_AUTH_UNKNOWN	0x0
+#define CEPH_AUTH_NONE	 	0x1
+#define CEPH_AUTH_CEPHX	 	0x2
+
+
+/*********************************************
+ * message layer
+ */
+
+/*
+ * message types
+ */
+
+/* misc */
+#define CEPH_MSG_SHUTDOWN               1
+#define CEPH_MSG_PING                   2
+
+/* client <-> monitor */
+#define CEPH_MSG_MON_MAP                4
+#define CEPH_MSG_MON_GET_MAP            5
+#define CEPH_MSG_STATFS                 13
+#define CEPH_MSG_STATFS_REPLY           14
+#define CEPH_MSG_MON_SUBSCRIBE          15
+#define CEPH_MSG_MON_SUBSCRIBE_ACK      16
+#define CEPH_MSG_AUTH			17
+#define CEPH_MSG_AUTH_REPLY		18
+
+/* client <-> mds */
+#define CEPH_MSG_MDS_MAP                21
+
+#define CEPH_MSG_CLIENT_SESSION         22
+#define CEPH_MSG_CLIENT_RECONNECT       23
+
+#define CEPH_MSG_CLIENT_REQUEST         24
+#define CEPH_MSG_CLIENT_REQUEST_FORWARD 25
+#define CEPH_MSG_CLIENT_REPLY           26
+#define CEPH_MSG_CLIENT_CAPS            0x310
+#define CEPH_MSG_CLIENT_LEASE           0x311
+#define CEPH_MSG_CLIENT_SNAP            0x312
+#define CEPH_MSG_CLIENT_CAPRELEASE      0x313
+
+/* osd */
+#define CEPH_MSG_OSD_MAP          41
+#define CEPH_MSG_OSD_OP           42
+#define CEPH_MSG_OSD_OPREPLY      43
+
+struct ceph_mon_request_header {
+	__le64 have_version;
+	__le16 session_mon;
+	__le64 session_mon_tid;
+} __attribute__ ((packed));
+
+struct ceph_mon_statfs {
+	struct ceph_mon_request_header monhdr;
+	struct ceph_fsid fsid;
+} __attribute__ ((packed));
+
+struct ceph_statfs {
+	__le64 kb, kb_used, kb_avail;
+	__le64 num_objects;
+} __attribute__ ((packed));
+
+struct ceph_mon_statfs_reply {
+	struct ceph_fsid fsid;
+	__le64 version;
+	struct ceph_statfs st;
+} __attribute__ ((packed));
+
+struct ceph_osd_getmap {
+	struct ceph_mon_request_header monhdr;
+	struct ceph_fsid fsid;
+	__le32 start;
+} __attribute__ ((packed));
+
+struct ceph_mds_getmap {
+	struct ceph_mon_request_header monhdr;
+	struct ceph_fsid fsid;
+} __attribute__ ((packed));
+
+struct ceph_client_mount {
+	struct ceph_mon_request_header monhdr;
+} __attribute__ ((packed));
+
+struct ceph_mon_subscribe_item {
+	__le64 have_version;	__le64 have;
+	__u8 onetime;
+} __attribute__ ((packed));
+
+struct ceph_mon_subscribe_ack {
+	__le32 duration;         /* seconds */
+	struct ceph_fsid fsid;
+} __attribute__ ((packed));
+
+/*
+ * mds states
+ *   > 0 -> in
+ *  <= 0 -> out
+ */
+#define CEPH_MDS_STATE_DNE          0  /* down, does not exist. */
+#define CEPH_MDS_STATE_STOPPED     -1  /* down, once existed, but no subtrees.
+					  empty log. */
+#define CEPH_MDS_STATE_BOOT        -4  /* up, boot announcement. */
+#define CEPH_MDS_STATE_STANDBY     -5  /* up, idle.  waiting for assignment. */
+#define CEPH_MDS_STATE_CREATING    -6  /* up, creating MDS instance. */
+#define CEPH_MDS_STATE_STARTING    -7  /* up, starting previously stopped mds */
+#define CEPH_MDS_STATE_STANDBY_REPLAY -8 /* up, tailing active node's journal */
+
+#define CEPH_MDS_STATE_REPLAY       8  /* up, replaying journal. */
+#define CEPH_MDS_STATE_RESOLVE      9  /* up, disambiguating distributed
+					  operations (import, rename, etc.) */
+#define CEPH_MDS_STATE_RECONNECT    10 /* up, reconnect to clients */
+#define CEPH_MDS_STATE_REJOIN       11 /* up, rejoining distributed cache */
+#define CEPH_MDS_STATE_CLIENTREPLAY 12 /* up, replaying client operations */
+#define CEPH_MDS_STATE_ACTIVE       13 /* up, active */
+#define CEPH_MDS_STATE_STOPPING     14 /* up, but exporting metadata */
+
+extern const char *ceph_mds_state_name(int s);
+
+
+/*
+ * metadata lock types.
+ *  - these are bitmasks.. we can compose them
+ *  - they also define the lock ordering by the MDS
+ *  - a few of these are internal to the mds
+ */
+#define CEPH_LOCK_DN          1
+#define CEPH_LOCK_ISNAP       2
+#define CEPH_LOCK_IVERSION    4     /* mds internal */
+#define CEPH_LOCK_IFILE       8     /* mds internal */
+#define CEPH_LOCK_IAUTH       32
+#define CEPH_LOCK_ILINK       64
+#define CEPH_LOCK_IDFT        128   /* dir frag tree */
+#define CEPH_LOCK_INEST       256   /* mds internal */
+#define CEPH_LOCK_IXATTR      512
+#define CEPH_LOCK_INO         2048  /* immutable inode bits; not a lock */
+
+/* client_session ops */
+enum {
+	CEPH_SESSION_REQUEST_OPEN,
+	CEPH_SESSION_OPEN,
+	CEPH_SESSION_REQUEST_CLOSE,
+	CEPH_SESSION_CLOSE,
+	CEPH_SESSION_REQUEST_RENEWCAPS,
+	CEPH_SESSION_RENEWCAPS,
+	CEPH_SESSION_STALE,
+	CEPH_SESSION_RECALL_STATE,
+};
+
+extern const char *ceph_session_op_name(int op);
+
+struct ceph_mds_session_head {
+	__le32 op;
+	__le64 seq;
+	struct ceph_timespec stamp;
+	__le32 max_caps, max_leases;
+} __attribute__ ((packed));
+
+/* client_request */
+/*
+ * metadata ops.
+ *  & 0x001000 -> write op
+ *  & 0x010000 -> follow symlink (e.g. stat(), not lstat()).
+ &  & 0x100000 -> use weird ino/path trace
+ */
+#define CEPH_MDS_OP_WRITE        0x001000
+enum {
+	CEPH_MDS_OP_LOOKUP     = 0x00100,
+	CEPH_MDS_OP_GETATTR    = 0x00101,
+	CEPH_MDS_OP_LOOKUPHASH = 0x00102,
+	CEPH_MDS_OP_LOOKUPPARENT = 0x00103,
+
+	CEPH_MDS_OP_SETXATTR   = 0x01105,
+	CEPH_MDS_OP_RMXATTR    = 0x01106,
+	CEPH_MDS_OP_SETLAYOUT  = 0x01107,
+	CEPH_MDS_OP_SETATTR    = 0x01108,
+
+	CEPH_MDS_OP_MKNOD      = 0x01201,
+	CEPH_MDS_OP_LINK       = 0x01202,
+	CEPH_MDS_OP_UNLINK     = 0x01203,
+	CEPH_MDS_OP_RENAME     = 0x01204,
+	CEPH_MDS_OP_MKDIR      = 0x01220,
+	CEPH_MDS_OP_RMDIR      = 0x01221,
+	CEPH_MDS_OP_SYMLINK    = 0x01222,
+
+	CEPH_MDS_OP_CREATE     = 0x01301,
+	CEPH_MDS_OP_OPEN       = 0x00302,
+	CEPH_MDS_OP_READDIR    = 0x00305,
+
+	CEPH_MDS_OP_LOOKUPSNAP = 0x00400,
+	CEPH_MDS_OP_MKSNAP     = 0x01400,
+	CEPH_MDS_OP_RMSNAP     = 0x01401,
+	CEPH_MDS_OP_LSSNAP     = 0x00402,
+};
+
+extern const char *ceph_mds_op_name(int op);
+
+
+#define CEPH_SETATTR_MODE   1
+#define CEPH_SETATTR_UID    2
+#define CEPH_SETATTR_GID    4
+#define CEPH_SETATTR_MTIME  8
+#define CEPH_SETATTR_ATIME 16
+#define CEPH_SETATTR_SIZE  32
+#define CEPH_SETATTR_CTIME 64
+
+union ceph_mds_request_args {
+	struct {
+		__le32 mask;                 /* CEPH_CAP_* */
+	} __attribute__ ((packed)) getattr;
+	struct {
+		__le32 mode;
+		__le32 uid;
+		__le32 gid;
+		struct ceph_timespec mtime;
+		struct ceph_timespec atime;
+		__le64 size, old_size;       /* old_size needed by truncate */
+		__le32 mask;                 /* CEPH_SETATTR_* */
+	} __attribute__ ((packed)) setattr;
+	struct {
+		__le32 frag;                 /* which dir fragment */
+		__le32 max_entries;          /* how many dentries to grab */
+	} __attribute__ ((packed)) readdir;
+	struct {
+		__le32 mode;
+		__le32 rdev;
+	} __attribute__ ((packed)) mknod;
+	struct {
+		__le32 mode;
+	} __attribute__ ((packed)) mkdir;
+	struct {
+		__le32 flags;
+		__le32 mode;
+		__le32 stripe_unit;          /* layout for newly created file */
+		__le32 stripe_count;         /* ... */
+		__le32 object_size;
+		__le32 file_replication;
+		__le32 preferred;
+	} __attribute__ ((packed)) open;
+	struct {
+		__le32 flags;
+	} __attribute__ ((packed)) setxattr;
+	struct {
+		struct ceph_file_layout layout;
+	} __attribute__ ((packed)) setlayout;
+} __attribute__ ((packed));
+
+#define CEPH_MDS_FLAG_REPLAY        1  /* this is a replayed op */
+#define CEPH_MDS_FLAG_WANT_DENTRY   2  /* want dentry in reply */
+
+struct ceph_mds_request_head {
+	__le64 oldest_client_tid;
+	__le32 mdsmap_epoch;           /* on client */
+	__le32 flags;                  /* CEPH_MDS_FLAG_* */
+	__u8 num_retry, num_fwd;       /* count retry, fwd attempts */
+	__le16 num_releases;           /* # include cap/lease release records */
+	__le32 op;                     /* mds op code */
+	__le32 caller_uid, caller_gid;
+	__le64 ino;                    /* use this ino for openc, mkdir, mknod,
+					  etc. (if replaying) */
+	union ceph_mds_request_args args;
+} __attribute__ ((packed));
+
+/* cap/lease release record */
+struct ceph_mds_request_release {
+	__le64 ino, cap_id;            /* ino and unique cap id */
+	__le32 caps, wanted;           /* new issued, wanted */
+	__le32 seq, issue_seq, mseq;
+	__le32 dname_seq;              /* if releasing a dentry lease, a */
+	__le32 dname_len;              /* string follows. */
+} __attribute__ ((packed));
+
+/* client reply */
+struct ceph_mds_reply_head {
+	__le32 op;
+	__le32 result;
+	__le32 mdsmap_epoch;
+	__u8 safe;                     /* true if committed to disk */
+	__u8 is_dentry, is_target;     /* true if dentry, target inode records
+					  are included with reply */
+} __attribute__ ((packed));
+
+/* one for each node split */
+struct ceph_frag_tree_split {
+	__le32 frag;                   /* this frag splits... */
+	__le32 by;                     /* ...by this many bits */
+} __attribute__ ((packed));
+
+struct ceph_frag_tree_head {
+	__le32 nsplits;                /* num ceph_frag_tree_split records */
+	struct ceph_frag_tree_split splits[];
+} __attribute__ ((packed));
+
+/* capability issue, for bundling with mds reply */
+struct ceph_mds_reply_cap {
+	__le32 caps, wanted;           /* caps issued, wanted */
+	__le64 cap_id;
+	__le32 seq, mseq;
+	__le64 realm;                  /* snap realm */
+	__u8 flags;                    /* CEPH_CAP_FLAG_* */
+} __attribute__ ((packed));
+
+#define CEPH_CAP_FLAG_AUTH  1          /* cap is issued by auth mds */
+
+/* inode record, for bundling with mds reply */
+struct ceph_mds_reply_inode {
+	__le64 ino;
+	__le64 snapid;
+	__le32 rdev;
+	__le64 version;                /* inode version */
+	__le64 xattr_version;          /* version for xattr blob */
+	struct ceph_mds_reply_cap cap; /* caps issued for this inode */
+	struct ceph_file_layout layout;
+	struct ceph_timespec ctime, mtime, atime;
+	__le32 time_warp_seq;
+	__le64 size, max_size, truncate_size;
+	__le32 truncate_seq;
+	__le32 mode, uid, gid;
+	__le32 nlink;
+	__le64 files, subdirs, rbytes, rfiles, rsubdirs;  /* dir stats */
+	struct ceph_timespec rctime;
+	struct ceph_frag_tree_head fragtree;  /* (must be at end of struct) */
+} __attribute__ ((packed));
+/* followed by frag array, then symlink string, then xattr blob */
+
+/* reply_lease follows dname, and reply_inode */
+struct ceph_mds_reply_lease {
+	__le16 mask;            /* lease type(s) */
+	__le32 duration_ms;     /* lease duration */
+	__le32 seq;
+} __attribute__ ((packed));
+
+struct ceph_mds_reply_dirfrag {
+	__le32 frag;            /* fragment */
+	__le32 auth;            /* auth mds, if this is a delegation point */
+	__le32 ndist;           /* number of mds' this is replicated on */
+	__le32 dist[];
+} __attribute__ ((packed));
+
+/* file access modes */
+#define CEPH_FILE_MODE_PIN        0
+#define CEPH_FILE_MODE_RD         1
+#define CEPH_FILE_MODE_WR         2
+#define CEPH_FILE_MODE_RDWR       3  /* RD | WR */
+#define CEPH_FILE_MODE_LAZY       4  /* lazy io */
+#define CEPH_FILE_MODE_NUM        8  /* bc these are bit fields.. mostly */
+
+int ceph_flags_to_mode(int flags);
+
+
+/* capability bits */
+#define CEPH_CAP_PIN         1  /* no specific capabilities beyond the pin */
+
+/* generic cap bits */
+#define CEPH_CAP_GSHARED     1  /* client can reads */
+#define CEPH_CAP_GEXCL       2  /* client can read and update */
+#define CEPH_CAP_GCACHE      4  /* (file) client can cache reads */
+#define CEPH_CAP_GRD         8  /* (file) client can read */
+#define CEPH_CAP_GWR        16  /* (file) client can write */
+#define CEPH_CAP_GBUFFER    32  /* (file) client can buffer writes */
+#define CEPH_CAP_GWREXTEND  64  /* (file) client can extend EOF */
+#define CEPH_CAP_GLAZYIO   128  /* (file) client can perform lazy io */
+
+/* per-lock shift */
+#define CEPH_CAP_SAUTH      2
+#define CEPH_CAP_SLINK      4
+#define CEPH_CAP_SXATTR     6
+#define CEPH_CAP_SFILE      8   /* goes at the end (uses >2 cap bits) */
+
+#define CEPH_CAP_BITS       16
+
+/* composed values */
+#define CEPH_CAP_AUTH_SHARED  (CEPH_CAP_GSHARED  << CEPH_CAP_SAUTH)
+#define CEPH_CAP_AUTH_EXCL     (CEPH_CAP_GEXCL     << CEPH_CAP_SAUTH)
+#define CEPH_CAP_LINK_SHARED  (CEPH_CAP_GSHARED  << CEPH_CAP_SLINK)
+#define CEPH_CAP_LINK_EXCL     (CEPH_CAP_GEXCL     << CEPH_CAP_SLINK)
+#define CEPH_CAP_XATTR_SHARED (CEPH_CAP_GSHARED  << CEPH_CAP_SXATTR)
+#define CEPH_CAP_XATTR_EXCL    (CEPH_CAP_GEXCL     << CEPH_CAP_SXATTR)
+#define CEPH_CAP_FILE(x)    (x << CEPH_CAP_SFILE)
+#define CEPH_CAP_FILE_SHARED   (CEPH_CAP_GSHARED   << CEPH_CAP_SFILE)
+#define CEPH_CAP_FILE_EXCL     (CEPH_CAP_GEXCL     << CEPH_CAP_SFILE)
+#define CEPH_CAP_FILE_CACHE    (CEPH_CAP_GCACHE    << CEPH_CAP_SFILE)
+#define CEPH_CAP_FILE_RD       (CEPH_CAP_GRD       << CEPH_CAP_SFILE)
+#define CEPH_CAP_FILE_WR       (CEPH_CAP_GWR       << CEPH_CAP_SFILE)
+#define CEPH_CAP_FILE_BUFFER   (CEPH_CAP_GBUFFER   << CEPH_CAP_SFILE)
+#define CEPH_CAP_FILE_WREXTEND (CEPH_CAP_GWREXTEND << CEPH_CAP_SFILE)
+#define CEPH_CAP_FILE_LAZYIO   (CEPH_CAP_GLAZYIO   << CEPH_CAP_SFILE)
+
+/* cap masks (for getattr) */
+#define CEPH_STAT_CAP_INODE    CEPH_CAP_PIN
+#define CEPH_STAT_CAP_TYPE     CEPH_CAP_PIN  /* mode >> 12 */
+#define CEPH_STAT_CAP_SYMLINK  CEPH_CAP_PIN
+#define CEPH_STAT_CAP_UID      CEPH_CAP_AUTH_SHARED
+#define CEPH_STAT_CAP_GID      CEPH_CAP_AUTH_SHARED
+#define CEPH_STAT_CAP_MODE     CEPH_CAP_AUTH_SHARED
+#define CEPH_STAT_CAP_NLINK    CEPH_CAP_LINK_SHARED
+#define CEPH_STAT_CAP_LAYOUT   CEPH_CAP_FILE_SHARED
+#define CEPH_STAT_CAP_MTIME    CEPH_CAP_FILE_SHARED
+#define CEPH_STAT_CAP_SIZE     CEPH_CAP_FILE_SHARED
+#define CEPH_STAT_CAP_ATIME    CEPH_CAP_FILE_SHARED  /* fixme */
+#define CEPH_STAT_CAP_XATTR    CEPH_CAP_XATTR_SHARED
+#define CEPH_STAT_CAP_INODE_ALL (CEPH_CAP_PIN |			\
+				 CEPH_CAP_AUTH_SHARED |	\
+				 CEPH_CAP_LINK_SHARED |	\
+				 CEPH_CAP_FILE_SHARED |	\
+				 CEPH_CAP_XATTR_SHARED)
+
+#define CEPH_CAP_ANY_SHARED (CEPH_CAP_AUTH_SHARED |			\
+			      CEPH_CAP_LINK_SHARED |			\
+			      CEPH_CAP_XATTR_SHARED |			\
+			      CEPH_CAP_FILE_SHARED)
+#define CEPH_CAP_ANY_RD   (CEPH_CAP_ANY_SHARED | CEPH_CAP_FILE_RD |	\
+			   CEPH_CAP_FILE_CACHE)
+
+#define CEPH_CAP_ANY_EXCL (CEPH_CAP_AUTH_EXCL |		\
+			   CEPH_CAP_LINK_EXCL |		\
+			   CEPH_CAP_XATTR_EXCL |	\
+			   CEPH_CAP_FILE_EXCL)
+#define CEPH_CAP_ANY_FILE_WR (CEPH_CAP_FILE_WR | CEPH_CAP_FILE_BUFFER |	\
+			      CEPH_CAP_FILE_EXCL)
+#define CEPH_CAP_ANY_WR   (CEPH_CAP_ANY_EXCL | CEPH_CAP_ANY_FILE_WR)
+#define CEPH_CAP_ANY      (CEPH_CAP_ANY_RD | CEPH_CAP_ANY_EXCL | \
+			   CEPH_CAP_ANY_FILE_WR | CEPH_CAP_PIN)
+
+#define CEPH_CAP_LOCKS (CEPH_LOCK_IFILE | CEPH_LOCK_IAUTH | CEPH_LOCK_ILINK | \
+			CEPH_LOCK_IXATTR)
+
+int ceph_caps_for_mode(int mode);
+
+enum {
+	CEPH_CAP_OP_GRANT,         /* mds->client grant */
+	CEPH_CAP_OP_REVOKE,        /* mds->client revoke */
+	CEPH_CAP_OP_TRUNC,         /* mds->client trunc notify */
+	CEPH_CAP_OP_EXPORT,        /* mds has exported the cap */
+	CEPH_CAP_OP_IMPORT,        /* mds has imported the cap */
+	CEPH_CAP_OP_UPDATE,        /* client->mds update */
+	CEPH_CAP_OP_DROP,          /* client->mds drop cap bits */
+	CEPH_CAP_OP_FLUSH,         /* client->mds cap writeback */
+	CEPH_CAP_OP_FLUSH_ACK,     /* mds->client flushed */
+	CEPH_CAP_OP_FLUSHSNAP,     /* client->mds flush snapped metadata */
+	CEPH_CAP_OP_FLUSHSNAP_ACK, /* mds->client flushed snapped metadata */
+	CEPH_CAP_OP_RELEASE,       /* client->mds release (clean) cap */
+	CEPH_CAP_OP_RENEW,         /* client->mds renewal request */
+};
+
+extern const char *ceph_cap_op_name(int op);
+
+/*
+ * caps message, used for capability callbacks, acks, requests, etc.
+ */
+struct ceph_mds_caps {
+	__le32 op;                  /* CEPH_CAP_OP_* */
+	__le64 ino, realm;
+	__le64 cap_id;
+	__le32 seq, issue_seq;
+	__le32 caps, wanted, dirty; /* latest issued/wanted/dirty */
+	__le32 migrate_seq;
+	__le64 snap_follows;
+	__le32 snap_trace_len;
+
+	/* authlock */
+	__le32 uid, gid, mode;
+
+	/* linklock */
+	__le32 nlink;
+
+	/* xattrlock */
+	__le32 xattr_len;
+	__le64 xattr_version;
+
+	/* filelock */
+	__le64 size, max_size, truncate_size;
+	__le32 truncate_seq;
+	struct ceph_timespec mtime, atime, ctime;
+	struct ceph_file_layout layout;
+	__le32 time_warp_seq;
+} __attribute__ ((packed));
+
+/* cap release msg head */
+struct ceph_mds_cap_release {
+	__le32 num;                /* number of cap_items that follow */
+} __attribute__ ((packed));
+
+struct ceph_mds_cap_item {
+	__le64 ino;
+	__le64 cap_id;
+	__le32 migrate_seq, seq;
+} __attribute__ ((packed));
+
+#define CEPH_MDS_LEASE_REVOKE           1  /*    mds  -> client */
+#define CEPH_MDS_LEASE_RELEASE          2  /* client  -> mds    */
+#define CEPH_MDS_LEASE_RENEW            3  /* client <-> mds    */
+#define CEPH_MDS_LEASE_REVOKE_ACK       4  /* client  -> mds    */
+
+extern const char *ceph_lease_op_name(int o);
+
+/* lease msg header */
+struct ceph_mds_lease {
+	__u8 action;            /* CEPH_MDS_LEASE_* */
+	__le16 mask;            /* which lease */
+	__le64 ino;
+	__le64 first, last;     /* snap range */
+	__le32 seq;
+	__le32 duration_ms;     /* duration of renewal */
+} __attribute__ ((packed));
+/* followed by a __le32+string for dname */
+
+/* client reconnect */
+struct ceph_mds_cap_reconnect {
+	__le64 cap_id;
+	__le32 wanted;
+	__le32 issued;
+	__le64 size;
+	struct ceph_timespec mtime, atime;
+	__le64 snaprealm;
+	__le64 pathbase;        /* base ino for our path to this ino */
+} __attribute__ ((packed));
+/* followed by encoded string */
+
+struct ceph_mds_snaprealm_reconnect {
+	__le64 ino;     /* snap realm base */
+	__le64 seq;     /* snap seq for this snap realm */
+	__le64 parent;  /* parent realm */
+} __attribute__ ((packed));
+
+/*
+ * snaps
+ */
+enum {
+	CEPH_SNAP_OP_UPDATE,  /* CREATE or DESTROY */
+	CEPH_SNAP_OP_CREATE,
+	CEPH_SNAP_OP_DESTROY,
+	CEPH_SNAP_OP_SPLIT,
+};
+
+extern const char *ceph_snap_op_name(int o);
+
+/* snap msg header */
+struct ceph_mds_snap_head {
+	__le32 op;                /* CEPH_SNAP_OP_* */
+	__le64 split;             /* ino to split off, if any */
+	__le32 num_split_inos;    /* # inos belonging to new child realm */
+	__le32 num_split_realms;  /* # child realms udner new child realm */
+	__le32 trace_len;         /* size of snap trace blob */
+} __attribute__ ((packed));
+/* followed by split ino list, then split realms, then the trace blob */
+
+/*
+ * encode info about a snaprealm, as viewed by a client
+ */
+struct ceph_mds_snap_realm {
+	__le64 ino;           /* ino */
+	__le64 created;       /* snap: when created */
+	__le64 parent;        /* ino: parent realm */
+	__le64 parent_since;  /* snap: same parent since */
+	__le64 seq;           /* snap: version */
+	__le32 num_snaps;
+	__le32 num_prior_parent_snaps;
+} __attribute__ ((packed));
+/* followed by my snap list, then prior parent snap list */
+
+#endif

fs/ceph/ceph_hash.c

@@ -0,0 +1,118 @@
+
+#include "types.h"
+
+/*
+ * Robert Jenkin's hash function.
+ * http://burtleburtle.net/bob/hash/evahash.html
+ * This is in the public domain.
+ */
+#define mix(a, b, c)						\
+	do {							\
+		a = a - b;  a = a - c;  a = a ^ (c >> 13);	\
+		b = b - c;  b = b - a;  b = b ^ (a << 8);	\
+		c = c - a;  c = c - b;  c = c ^ (b >> 13);	\
+		a = a - b;  a = a - c;  a = a ^ (c >> 12);	\
+		b = b - c;  b = b - a;  b = b ^ (a << 16);	\
+		c = c - a;  c = c - b;  c = c ^ (b >> 5);	\
+		a = a - b;  a = a - c;  a = a ^ (c >> 3);	\
+		b = b - c;  b = b - a;  b = b ^ (a << 10);	\
+		c = c - a;  c = c - b;  c = c ^ (b >> 15);	\
+	} while (0)
+
+unsigned ceph_str_hash_rjenkins(const char *str, unsigned length)
+{
+	const unsigned char *k = (const unsigned char *)str;
+	__u32 a, b, c;  /* the internal state */
+	__u32 len;      /* how many key bytes still need mixing */
+
+	/* Set up the internal state */
+	len = length;
+	a = 0x9e3779b9;      /* the golden ratio; an arbitrary value */
+	b = a;
+	c = 0;               /* variable initialization of internal state */
+
+	/* handle most of the key */
+	while (len >= 12) {
+		a = a + (k[0] + ((__u32)k[1] << 8) + ((__u32)k[2] << 16) +
+			 ((__u32)k[3] << 24));
+		b = b + (k[4] + ((__u32)k[5] << 8) + ((__u32)k[6] << 16) +
+			 ((__u32)k[7] << 24));
+		c = c + (k[8] + ((__u32)k[9] << 8) + ((__u32)k[10] << 16) +
+			 ((__u32)k[11] << 24));
+		mix(a, b, c);
+		k = k + 12;
+		len = len - 12;
+	}
+
+	/* handle the last 11 bytes */
+	c = c + length;
+	switch (len) {            /* all the case statements fall through */
+	case 11:
+		c = c + ((__u32)k[10] << 24);
+	case 10:
+		c = c + ((__u32)k[9] << 16);
+	case 9:
+		c = c + ((__u32)k[8] << 8);
+		/* the first byte of c is reserved for the length */
+	case 8:
+		b = b + ((__u32)k[7] << 24);
+	case 7:
+		b = b + ((__u32)k[6] << 16);
+	case 6:
+		b = b + ((__u32)k[5] << 8);
+	case 5:
+		b = b + k[4];
+	case 4:
+		a = a + ((__u32)k[3] << 24);
+	case 3:
+		a = a + ((__u32)k[2] << 16);
+	case 2:
+		a = a + ((__u32)k[1] << 8);
+	case 1:
+		a = a + k[0];
+		/* case 0: nothing left to add */
+	}
+	mix(a, b, c);
+
+	return c;
+}
+
+/*
+ * linux dcache hash
+ */
+unsigned ceph_str_hash_linux(const char *str, unsigned length)
+{
+	unsigned long hash = 0;
+	unsigned char c;
+
+	while (length--) {
+		c = *str++;
+		hash = (hash + (c << 4) + (c >> 4)) * 11;
+	}
+	return hash;
+}
+
+
+unsigned ceph_str_hash(int type, const char *s, unsigned len)
+{
+	switch (type) {
+	case CEPH_STR_HASH_LINUX:
+		return ceph_str_hash_linux(s, len);
+	case CEPH_STR_HASH_RJENKINS:
+		return ceph_str_hash_rjenkins(s, len);
+	default:
+		return -1;
+	}
+}
+
+const char *ceph_str_hash_name(int type)
+{
+	switch (type) {
+	case CEPH_STR_HASH_LINUX:
+		return "linux";
+	case CEPH_STR_HASH_RJENKINS:
+		return "rjenkins";
+	default:
+		return "unknown";
+	}
+}

fs/ceph/ceph_hash.h

@@ -0,0 +1,13 @@
+#ifndef _FS_CEPH_HASH_H
+#define _FS_CEPH_HASH_H
+
+#define CEPH_STR_HASH_LINUX      0x1  /* linux dcache hash */
+#define CEPH_STR_HASH_RJENKINS   0x2  /* robert jenkins' */
+
+extern unsigned ceph_str_hash_linux(const char *s, unsigned len);
+extern unsigned ceph_str_hash_rjenkins(const char *s, unsigned len);
+
+extern unsigned ceph_str_hash(int type, const char *s, unsigned len);
+extern const char *ceph_str_hash_name(int type);
+
+#endif

fs/ceph/ceph_strings.c

@@ -0,0 +1,176 @@
+/*
+ * Ceph string constants
+ */
+#include "types.h"
+
+const char *ceph_entity_type_name(int type)
+{
+	switch (type) {
+	case CEPH_ENTITY_TYPE_MDS: return "mds";
+	case CEPH_ENTITY_TYPE_OSD: return "osd";
+	case CEPH_ENTITY_TYPE_MON: return "mon";
+	case CEPH_ENTITY_TYPE_CLIENT: return "client";
+	case CEPH_ENTITY_TYPE_ADMIN: return "admin";
+	case CEPH_ENTITY_TYPE_AUTH: return "auth";
+	default: return "unknown";
+	}
+}
+
+const char *ceph_osd_op_name(int op)
+{
+	switch (op) {
+	case CEPH_OSD_OP_READ: return "read";
+	case CEPH_OSD_OP_STAT: return "stat";
+
+	case CEPH_OSD_OP_MASKTRUNC: return "masktrunc";
+
+	case CEPH_OSD_OP_WRITE: return "write";
+	case CEPH_OSD_OP_DELETE: return "delete";
+	case CEPH_OSD_OP_TRUNCATE: return "truncate";
+	case CEPH_OSD_OP_ZERO: return "zero";
+	case CEPH_OSD_OP_WRITEFULL: return "writefull";
+
+	case CEPH_OSD_OP_APPEND: return "append";
+	case CEPH_OSD_OP_STARTSYNC: return "startsync";
+	case CEPH_OSD_OP_SETTRUNC: return "settrunc";
+	case CEPH_OSD_OP_TRIMTRUNC: return "trimtrunc";
+
+	case CEPH_OSD_OP_TMAPUP: return "tmapup";
+	case CEPH_OSD_OP_TMAPGET: return "tmapget";
+	case CEPH_OSD_OP_TMAPPUT: return "tmapput";
+
+	case CEPH_OSD_OP_GETXATTR: return "getxattr";
+	case CEPH_OSD_OP_GETXATTRS: return "getxattrs";
+	case CEPH_OSD_OP_SETXATTR: return "setxattr";
+	case CEPH_OSD_OP_SETXATTRS: return "setxattrs";
+	case CEPH_OSD_OP_RESETXATTRS: return "resetxattrs";
+	case CEPH_OSD_OP_RMXATTR: return "rmxattr";
+
+	case CEPH_OSD_OP_PULL: return "pull";
+	case CEPH_OSD_OP_PUSH: return "push";
+	case CEPH_OSD_OP_BALANCEREADS: return "balance-reads";
+	case CEPH_OSD_OP_UNBALANCEREADS: return "unbalance-reads";
+	case CEPH_OSD_OP_SCRUB: return "scrub";
+
+	case CEPH_OSD_OP_WRLOCK: return "wrlock";
+	case CEPH_OSD_OP_WRUNLOCK: return "wrunlock";
+	case CEPH_OSD_OP_RDLOCK: return "rdlock";
+	case CEPH_OSD_OP_RDUNLOCK: return "rdunlock";
+	case CEPH_OSD_OP_UPLOCK: return "uplock";
+	case CEPH_OSD_OP_DNLOCK: return "dnlock";
+
+	case CEPH_OSD_OP_CALL: return "call";
+
+	case CEPH_OSD_OP_PGLS: return "pgls";
+	}
+	return "???";
+}
+
+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_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_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_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";
+	}
+	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/crush/crush.c

@@ -0,0 +1,151 @@
+
+#ifdef __KERNEL__
+# include <linux/slab.h>
+#else
+# include <stdlib.h>
+# include <assert.h>
+# define kfree(x) do { if (x) free(x); } while (0)
+# define BUG_ON(x) assert(!(x))
+#endif
+
+#include "crush.h"
+
+const char *crush_bucket_alg_name(int alg)
+{
+	switch (alg) {
+	case CRUSH_BUCKET_UNIFORM: return "uniform";
+	case CRUSH_BUCKET_LIST: return "list";
+	case CRUSH_BUCKET_TREE: return "tree";
+	case CRUSH_BUCKET_STRAW: return "straw";
+	default: return "unknown";
+	}
+}
+
+/**
+ * crush_get_bucket_item_weight - Get weight of an item in given bucket
+ * @b: bucket pointer
+ * @p: item index in bucket
+ */
+int crush_get_bucket_item_weight(struct crush_bucket *b, int p)
+{
+	if (p >= b->size)
+		return 0;
+
+	switch (b->alg) {
+	case CRUSH_BUCKET_UNIFORM:
+		return ((struct crush_bucket_uniform *)b)->item_weight;
+	case CRUSH_BUCKET_LIST:
+		return ((struct crush_bucket_list *)b)->item_weights[p];
+	case CRUSH_BUCKET_TREE:
+		if (p & 1)
+			return ((struct crush_bucket_tree *)b)->node_weights[p];
+		return 0;
+	case CRUSH_BUCKET_STRAW:
+		return ((struct crush_bucket_straw *)b)->item_weights[p];
+	}
+	return 0;
+}
+
+/**
+ * crush_calc_parents - Calculate parent vectors for the given crush map.
+ * @map: crush_map pointer
+ */
+void crush_calc_parents(struct crush_map *map)
+{
+	int i, b, c;
+
+	for (b = 0; b < map->max_buckets; b++) {
+		if (map->buckets[b] == NULL)
+			continue;
+		for (i = 0; i < map->buckets[b]->size; i++) {
+			c = map->buckets[b]->items[i];
+			BUG_ON(c >= map->max_devices ||
+			       c < -map->max_buckets);
+			if (c >= 0)
+				map->device_parents[c] = map->buckets[b]->id;
+			else
+				map->bucket_parents[-1-c] = map->buckets[b]->id;
+		}
+	}
+}
+
+void crush_destroy_bucket_uniform(struct crush_bucket_uniform *b)
+{
+	kfree(b->h.perm);
+	kfree(b->h.items);
+	kfree(b);
+}
+
+void crush_destroy_bucket_list(struct crush_bucket_list *b)
+{
+	kfree(b->item_weights);
+	kfree(b->sum_weights);
+	kfree(b->h.perm);
+	kfree(b->h.items);
+	kfree(b);
+}
+
+void crush_destroy_bucket_tree(struct crush_bucket_tree *b)
+{
+	kfree(b->node_weights);
+	kfree(b);
+}
+
+void crush_destroy_bucket_straw(struct crush_bucket_straw *b)
+{
+	kfree(b->straws);
+	kfree(b->item_weights);
+	kfree(b->h.perm);
+	kfree(b->h.items);
+	kfree(b);
+}
+
+void crush_destroy_bucket(struct crush_bucket *b)
+{
+	switch (b->alg) {
+	case CRUSH_BUCKET_UNIFORM:
+		crush_destroy_bucket_uniform((struct crush_bucket_uniform *)b);
+		break;
+	case CRUSH_BUCKET_LIST:
+		crush_destroy_bucket_list((struct crush_bucket_list *)b);
+		break;
+	case CRUSH_BUCKET_TREE:
+		crush_destroy_bucket_tree((struct crush_bucket_tree *)b);
+		break;
+	case CRUSH_BUCKET_STRAW:
+		crush_destroy_bucket_straw((struct crush_bucket_straw *)b);
+		break;
+	}
+}
+
+/**
+ * crush_destroy - Destroy a crush_map
+ * @map: crush_map pointer
+ */
+void crush_destroy(struct crush_map *map)
+{
+	int b;
+
+	/* buckets */
+	if (map->buckets) {
+		for (b = 0; b < map->max_buckets; b++) {
+			if (map->buckets[b] == NULL)
+				continue;
+			crush_destroy_bucket(map->buckets[b]);
+		}
+		kfree(map->buckets);
+	}
+
+	/* rules */
+	if (map->rules) {
+		for (b = 0; b < map->max_rules; b++)
+			kfree(map->rules[b]);
+		kfree(map->rules);
+	}
+
+	kfree(map->bucket_parents);
+	kfree(map->device_parents);
+	kfree(map);
+}
+
+

fs/ceph/crush/crush.h

@@ -0,0 +1,180 @@
+#ifndef _CRUSH_CRUSH_H
+#define _CRUSH_CRUSH_H
+
+#include <linux/types.h>
+
+/*
+ * CRUSH is a pseudo-random data distribution algorithm that
+ * efficiently distributes input values (typically, data objects)
+ * across a heterogeneous, structured storage cluster.
+ *
+ * The algorithm was originally described in detail in this paper
+ * (although the algorithm has evolved somewhat since then):
+ *
+ *     http://www.ssrc.ucsc.edu/Papers/weil-sc06.pdf
+ *
+ * LGPL2
+ */
+
+
+#define CRUSH_MAGIC 0x00010000ul   /* for detecting algorithm revisions */
+
+
+#define CRUSH_MAX_DEPTH 10  /* max crush hierarchy depth */
+#define CRUSH_MAX_SET   10  /* max size of a mapping result */
+
+
+/*
+ * CRUSH uses user-defined "rules" to describe how inputs should be
+ * mapped to devices.  A rule consists of sequence of steps to perform
+ * to generate the set of output devices.
+ */
+struct crush_rule_step {
+	__u32 op;
+	__s32 arg1;
+	__s32 arg2;
+};
+
+/* step op codes */
+enum {
+	CRUSH_RULE_NOOP = 0,
+	CRUSH_RULE_TAKE = 1,          /* arg1 = value to start with */
+	CRUSH_RULE_CHOOSE_FIRSTN = 2, /* arg1 = num items to pick */
+				      /* arg2 = type */
+	CRUSH_RULE_CHOOSE_INDEP = 3,  /* same */
+	CRUSH_RULE_EMIT = 4,          /* no args */
+	CRUSH_RULE_CHOOSE_LEAF_FIRSTN = 6,
+	CRUSH_RULE_CHOOSE_LEAF_INDEP = 7,
+};
+
+/*
+ * for specifying choose num (arg1) relative to the max parameter
+ * passed to do_rule
+ */
+#define CRUSH_CHOOSE_N            0
+#define CRUSH_CHOOSE_N_MINUS(x)   (-(x))
+
+/*
+ * The rule mask is used to describe what the rule is intended for.
+ * Given a ruleset and size of output set, we search through the
+ * rule list for a matching rule_mask.
+ */
+struct crush_rule_mask {
+	__u8 ruleset;
+	__u8 type;
+	__u8 min_size;
+	__u8 max_size;
+};
+
+struct crush_rule {
+	__u32 len;
+	struct crush_rule_mask mask;
+	struct crush_rule_step steps[0];
+};
+
+#define crush_rule_size(len) (sizeof(struct crush_rule) + \
+			      (len)*sizeof(struct crush_rule_step))
+
+
+
+/*
+ * A bucket is a named container of other items (either devices or
+ * other buckets).  Items within a bucket are chosen using one of a
+ * few different algorithms.  The table summarizes how the speed of
+ * each option measures up against mapping stability when items are
+ * added or removed.
+ *
+ *  Bucket Alg     Speed       Additions    Removals
+ *  ------------------------------------------------
+ *  uniform         O(1)       poor         poor
+ *  list            O(n)       optimal      poor
+ *  tree            O(log n)   good         good
+ *  straw           O(n)       optimal      optimal
+ */
+enum {
+	CRUSH_BUCKET_UNIFORM = 1,
+	CRUSH_BUCKET_LIST = 2,
+	CRUSH_BUCKET_TREE = 3,
+	CRUSH_BUCKET_STRAW = 4
+};
+extern const char *crush_bucket_alg_name(int alg);
+
+struct crush_bucket {
+	__s32 id;        /* this'll be negative */
+	__u16 type;      /* non-zero; type=0 is reserved for devices */
+	__u8 alg;        /* one of CRUSH_BUCKET_* */
+	__u8 hash;       /* which hash function to use, CRUSH_HASH_* */
+	__u32 weight;    /* 16-bit fixed point */
+	__u32 size;      /* num items */
+	__s32 *items;
+
+	/*
+	 * cached random permutation: used for uniform bucket and for
+	 * the linear search fallback for the other bucket types.
+	 */
+	__u32 perm_x;  /* @x for which *perm is defined */
+	__u32 perm_n;  /* num elements of *perm that are permuted/defined */
+	__u32 *perm;
+};
+
+struct crush_bucket_uniform {
+	struct crush_bucket h;
+	__u32 item_weight;  /* 16-bit fixed point; all items equally weighted */
+};
+
+struct crush_bucket_list {
+	struct crush_bucket h;
+	__u32 *item_weights;  /* 16-bit fixed point */
+	__u32 *sum_weights;   /* 16-bit fixed point.  element i is sum
+				 of weights 0..i, inclusive */
+};
+
+struct crush_bucket_tree {
+	struct crush_bucket h;  /* note: h.size is _tree_ size, not number of
+				   actual items */
+	__u8 num_nodes;
+	__u32 *node_weights;
+};
+
+struct crush_bucket_straw {
+	struct crush_bucket h;
+	__u32 *item_weights;   /* 16-bit fixed point */
+	__u32 *straws;         /* 16-bit fixed point */
+};
+
+
+
+/*
+ * CRUSH map includes all buckets, rules, etc.
+ */
+struct crush_map {
+	struct crush_bucket **buckets;
+	struct crush_rule **rules;
+
+	/*
+	 * Parent pointers to identify the parent bucket a device or
+	 * bucket in the hierarchy.  If an item appears more than
+	 * once, this is the _last_ time it appeared (where buckets
+	 * are processed in bucket id order, from -1 on down to
+	 * -max_buckets.
+	 */
+	__u32 *bucket_parents;
+	__u32 *device_parents;
+
+	__s32 max_buckets;
+	__u32 max_rules;
+	__s32 max_devices;
+};
+
+
+/* crush.c */
+extern int crush_get_bucket_item_weight(struct crush_bucket *b, int pos);
+extern void crush_calc_parents(struct crush_map *map);
+extern void crush_destroy_bucket_uniform(struct crush_bucket_uniform *b);
+extern void crush_destroy_bucket_list(struct crush_bucket_list *b);
+extern void crush_destroy_bucket_tree(struct crush_bucket_tree *b);
+extern void crush_destroy_bucket_straw(struct crush_bucket_straw *b);
+extern void crush_destroy_bucket(struct crush_bucket *b);
+extern void crush_destroy(struct crush_map *map);
+
+#endif

fs/ceph/crush/hash.c

@@ -0,0 +1,149 @@
+
+#include <linux/types.h>
+#include "hash.h"
+
+/*
+ * Robert Jenkins' function for mixing 32-bit values
+ * http://burtleburtle.net/bob/hash/evahash.html
+ * a, b = random bits, c = input and output
+ */
+#define crush_hashmix(a, b, c) do {			\
+		a = a-b;  a = a-c;  a = a^(c>>13);	\
+		b = b-c;  b = b-a;  b = b^(a<<8);	\
+		c = c-a;  c = c-b;  c = c^(b>>13);	\
+		a = a-b;  a = a-c;  a = a^(c>>12);	\
+		b = b-c;  b = b-a;  b = b^(a<<16);	\
+		c = c-a;  c = c-b;  c = c^(b>>5);	\
+		a = a-b;  a = a-c;  a = a^(c>>3);	\
+		b = b-c;  b = b-a;  b = b^(a<<10);	\
+		c = c-a;  c = c-b;  c = c^(b>>15);	\
+	} while (0)
+
+#define crush_hash_seed 1315423911
+
+static __u32 crush_hash32_rjenkins1(__u32 a)
+{
+	__u32 hash = crush_hash_seed ^ a;
+	__u32 b = a;
+	__u32 x = 231232;
+	__u32 y = 1232;
+	crush_hashmix(b, x, hash);
+	crush_hashmix(y, a, hash);
+	return hash;
+}
+
+static __u32 crush_hash32_rjenkins1_2(__u32 a, __u32 b)
+{
+	__u32 hash = crush_hash_seed ^ a ^ b;
+	__u32 x = 231232;
+	__u32 y = 1232;
+	crush_hashmix(a, b, hash);
+	crush_hashmix(x, a, hash);
+	crush_hashmix(b, y, hash);
+	return hash;
+}
+
+static __u32 crush_hash32_rjenkins1_3(__u32 a, __u32 b, __u32 c)
+{
+	__u32 hash = crush_hash_seed ^ a ^ b ^ c;
+	__u32 x = 231232;
+	__u32 y = 1232;
+	crush_hashmix(a, b, hash);
+	crush_hashmix(c, x, hash);
+	crush_hashmix(y, a, hash);
+	crush_hashmix(b, x, hash);
+	crush_hashmix(y, c, hash);
+	return hash;
+}
+
+static __u32 crush_hash32_rjenkins1_4(__u32 a, __u32 b, __u32 c, __u32 d)
+{
+	__u32 hash = crush_hash_seed ^ a ^ b ^ c ^ d;
+	__u32 x = 231232;
+	__u32 y = 1232;
+	crush_hashmix(a, b, hash);
+	crush_hashmix(c, d, hash);
+	crush_hashmix(a, x, hash);
+	crush_hashmix(y, b, hash);
+	crush_hashmix(c, x, hash);
+	crush_hashmix(y, d, hash);
+	return hash;
+}
+
+static __u32 crush_hash32_rjenkins1_5(__u32 a, __u32 b, __u32 c, __u32 d,
+				      __u32 e)
+{
+	__u32 hash = crush_hash_seed ^ a ^ b ^ c ^ d ^ e;
+	__u32 x = 231232;
+	__u32 y = 1232;
+	crush_hashmix(a, b, hash);
+	crush_hashmix(c, d, hash);
+	crush_hashmix(e, x, hash);
+	crush_hashmix(y, a, hash);
+	crush_hashmix(b, x, hash);
+	crush_hashmix(y, c, hash);
+	crush_hashmix(d, x, hash);
+	crush_hashmix(y, e, hash);
+	return hash;
+}
+
+
+__u32 crush_hash32(int type, __u32 a)
+{
+	switch (type) {
+	case CRUSH_HASH_RJENKINS1:
+		return crush_hash32_rjenkins1(a);
+	default:
+		return 0;
+	}
+}
+
+__u32 crush_hash32_2(int type, __u32 a, __u32 b)
+{
+	switch (type) {
+	case CRUSH_HASH_RJENKINS1:
+		return crush_hash32_rjenkins1_2(a, b);
+	default:
+		return 0;
+	}
+}
+
+__u32 crush_hash32_3(int type, __u32 a, __u32 b, __u32 c)
+{
+	switch (type) {
+	case CRUSH_HASH_RJENKINS1:
+		return crush_hash32_rjenkins1_3(a, b, c);
+	default:
+		return 0;
+	}
+}
+
+__u32 crush_hash32_4(int type, __u32 a, __u32 b, __u32 c, __u32 d)
+{
+	switch (type) {
+	case CRUSH_HASH_RJENKINS1:
+		return crush_hash32_rjenkins1_4(a, b, c, d);
+	default:
+		return 0;
+	}
+}
+
+__u32 crush_hash32_5(int type, __u32 a, __u32 b, __u32 c, __u32 d, __u32 e)
+{
+	switch (type) {
+	case CRUSH_HASH_RJENKINS1:
+		return crush_hash32_rjenkins1_5(a, b, c, d, e);
+	default:
+		return 0;
+	}
+}
+
+const char *crush_hash_name(int type)
+{
+	switch (type) {
+	case CRUSH_HASH_RJENKINS1:
+		return "rjenkins1";
+	default:
+		return "unknown";
+	}
+}

fs/ceph/crush/hash.h

@@ -0,0 +1,17 @@
+#ifndef _CRUSH_HASH_H
+#define _CRUSH_HASH_H
+
+#define CRUSH_HASH_RJENKINS1   0
+
+#define CRUSH_HASH_DEFAULT CRUSH_HASH_RJENKINS1
+
+extern const char *crush_hash_name(int type);
+
+extern __u32 crush_hash32(int type, __u32 a);
+extern __u32 crush_hash32_2(int type, __u32 a, __u32 b);
+extern __u32 crush_hash32_3(int type, __u32 a, __u32 b, __u32 c);
+extern __u32 crush_hash32_4(int type, __u32 a, __u32 b, __u32 c, __u32 d);
+extern __u32 crush_hash32_5(int type, __u32 a, __u32 b, __u32 c, __u32 d,
+			    __u32 e);
+
+#endif

fs/ceph/crush/mapper.c

@@ -0,0 +1,596 @@
+
+#ifdef __KERNEL__
+# include <linux/string.h>
+# include <linux/slab.h>
+# include <linux/bug.h>
+# include <linux/kernel.h>
+# ifndef dprintk
+#  define dprintk(args...)
+# endif
+#else
+# include <string.h>
+# include <stdio.h>
+# include <stdlib.h>
+# include <assert.h>
+# define BUG_ON(x) assert(!(x))
+# define dprintk(args...) /* printf(args) */
+# define kmalloc(x, f) malloc(x)
+# define kfree(x) free(x)
+#endif
+
+#include "crush.h"
+#include "hash.h"
+
+/*
+ * Implement the core CRUSH mapping algorithm.
+ */
+
+/**
+ * crush_find_rule - find a crush_rule id for a given ruleset, type, and size.
+ * @map: the crush_map
+ * @ruleset: the storage ruleset id (user defined)
+ * @type: storage ruleset type (user defined)
+ * @size: output set size
+ */
+int crush_find_rule(struct crush_map *map, int ruleset, int type, int size)
+{
+	int i;
+
+	for (i = 0; i < map->max_rules; i++) {
+		if (map->rules[i] &&
+		    map->rules[i]->mask.ruleset == ruleset &&
+		    map->rules[i]->mask.type == type &&
+		    map->rules[i]->mask.min_size <= size &&
+		    map->rules[i]->mask.max_size >= size)
+			return i;
+	}
+	return -1;
+}
+
+
+/*
+ * bucket choose methods
+ *
+ * For each bucket algorithm, we have a "choose" method that, given a
+ * crush input @x and replica position (usually, position in output set) @r,
+ * will produce an item in the bucket.
+ */
+
+/*
+ * Choose based on a random permutation of the bucket.
+ *
+ * We used to use some prime number arithmetic to do this, but it
+ * wasn't very random, and had some other bad behaviors.  Instead, we
+ * calculate an actual random permutation of the bucket members.
+ * Since this is expensive, we optimize for the r=0 case, which
+ * captures the vast majority of calls.
+ */
+static int bucket_perm_choose(struct crush_bucket *bucket,
+			      int x, int r)
+{
+	unsigned pr = r % bucket->size;
+	unsigned i, s;
+
+	/* start a new permutation if @x has changed */
+	if (bucket->perm_x != x || bucket->perm_n == 0) {
+		dprintk("bucket %d new x=%d\n", bucket->id, x);
+		bucket->perm_x = x;
+
+		/* optimize common r=0 case */
+		if (pr == 0) {
+			s = crush_hash32_3(bucket->hash, x, bucket->id, 0) %
+				bucket->size;
+			bucket->perm[0] = s;
+			bucket->perm_n = 0xffff;   /* magic value, see below */
+			goto out;
+		}
+
+		for (i = 0; i < bucket->size; i++)
+			bucket->perm[i] = i;
+		bucket->perm_n = 0;
+	} else if (bucket->perm_n == 0xffff) {
+		/* clean up after the r=0 case above */
+		for (i = 1; i < bucket->size; i++)
+			bucket->perm[i] = i;
+		bucket->perm[bucket->perm[0]] = 0;
+		bucket->perm_n = 1;
+	}
+
+	/* calculate permutation up to pr */
+	for (i = 0; i < bucket->perm_n; i++)
+		dprintk(" perm_choose have %d: %d\n", i, bucket->perm[i]);
+	while (bucket->perm_n <= pr) {
+		unsigned p = bucket->perm_n;
+		/* no point in swapping the final entry */
+		if (p < bucket->size - 1) {
+			i = crush_hash32_3(bucket->hash, x, bucket->id, p) %
+				(bucket->size - p);
+			if (i) {
+				unsigned t = bucket->perm[p + i];
+				bucket->perm[p + i] = bucket->perm[p];
+				bucket->perm[p] = t;
+			}
+			dprintk(" perm_choose swap %d with %d\n", p, p+i);
+		}
+		bucket->perm_n++;
+	}
+	for (i = 0; i < bucket->size; i++)
+		dprintk(" perm_choose  %d: %d\n", i, bucket->perm[i]);
+
+	s = bucket->perm[pr];
+out:
+	dprintk(" perm_choose %d sz=%d x=%d r=%d (%d) s=%d\n", bucket->id,
+		bucket->size, x, r, pr, s);
+	return bucket->items[s];
+}
+
+/* uniform */
+static int bucket_uniform_choose(struct crush_bucket_uniform *bucket,
+				 int x, int r)
+{
+	return bucket_perm_choose(&bucket->h, x, r);
+}
+
+/* list */
+static int bucket_list_choose(struct crush_bucket_list *bucket,
+			      int x, int r)
+{
+	int i;
+
+	for (i = bucket->h.size-1; i >= 0; i--) {
+		__u64 w = crush_hash32_4(bucket->h.hash,x, bucket->h.items[i],
+					 r, bucket->h.id);
+		w &= 0xffff;
+		dprintk("list_choose i=%d x=%d r=%d item %d weight %x "
+			"sw %x rand %llx",
+			i, x, r, bucket->h.items[i], bucket->item_weights[i],
+			bucket->sum_weights[i], w);
+		w *= bucket->sum_weights[i];
+		w = w >> 16;
+		/*dprintk(" scaled %llx\n", w);*/
+		if (w < bucket->item_weights[i])
+			return bucket->h.items[i];
+	}
+
+	BUG_ON(1);
+	return 0;
+}
+
+
+/* (binary) tree */
+static int height(int n)
+{
+	int h = 0;
+	while ((n & 1) == 0) {
+		h++;
+		n = n >> 1;
+	}
+	return h;
+}
+
+static int left(int x)
+{
+	int h = height(x);
+	return x - (1 << (h-1));
+}
+
+static int right(int x)
+{
+	int h = height(x);
+	return x + (1 << (h-1));
+}
+
+static int terminal(int x)
+{
+	return x & 1;
+}
+
+static int bucket_tree_choose(struct crush_bucket_tree *bucket,
+			      int x, int r)
+{
+	int n, l;
+	__u32 w;
+	__u64 t;
+
+	/* start at root */
+	n = bucket->num_nodes >> 1;
+
+	while (!terminal(n)) {
+		/* pick point in [0, w) */
+		w = bucket->node_weights[n];
+		t = (__u64)crush_hash32_4(bucket->h.hash, x, n, r,
+					  bucket->h.id) * (__u64)w;
+		t = t >> 32;
+
+		/* descend to the left or right? */
+		l = left(n);
+		if (t < bucket->node_weights[l])
+			n = l;
+		else
+			n = right(n);
+	}
+
+	return bucket->h.items[n >> 1];
+}
+
+
+/* straw */
+
+static int bucket_straw_choose(struct crush_bucket_straw *bucket,
+			       int x, int r)
+{
+	int i;
+	int high = 0;
+	__u64 high_draw = 0;
+	__u64 draw;
+
+	for (i = 0; i < bucket->h.size; i++) {
+		draw = crush_hash32_3(bucket->h.hash, x, bucket->h.items[i], r);
+		draw &= 0xffff;
+		draw *= bucket->straws[i];
+		if (i == 0 || draw > high_draw) {
+			high = i;
+			high_draw = draw;
+		}
+	}
+	return bucket->h.items[high];
+}
+
+static int crush_bucket_choose(struct crush_bucket *in, int x, int r)
+{
+	dprintk("choose %d x=%d r=%d\n", in->id, x, r);
+	switch (in->alg) {
+	case CRUSH_BUCKET_UNIFORM:
+		return bucket_uniform_choose((struct crush_bucket_uniform *)in,
+					  x, r);
+	case CRUSH_BUCKET_LIST:
+		return bucket_list_choose((struct crush_bucket_list *)in,
+					  x, r);
+	case CRUSH_BUCKET_TREE:
+		return bucket_tree_choose((struct crush_bucket_tree *)in,
+					  x, r);
+	case CRUSH_BUCKET_STRAW:
+		return bucket_straw_choose((struct crush_bucket_straw *)in,
+					   x, r);
+	default:
+		BUG_ON(1);
+		return in->items[0];
+	}
+}
+
+/*
+ * true if device is marked "out" (failed, fully offloaded)
+ * of the cluster
+ */
+static int is_out(struct crush_map *map, __u32 *weight, int item, int x)
+{
+	if (weight[item] >= 0x1000)
+		return 0;
+	if (weight[item] == 0)
+		return 1;
+	if ((crush_hash32_2(CRUSH_HASH_RJENKINS1, x, item) & 0xffff)
+	    < weight[item])
+		return 0;
+	return 1;
+}
+
+/**
+ * crush_choose - choose numrep distinct items of given type
+ * @map: the crush_map
+ * @bucket: the bucket we are choose an item from
+ * @x: crush input value
+ * @numrep: the number of items to choose
+ * @type: the type of item to choose
+ * @out: pointer to output vector
+ * @outpos: our position in that vector
+ * @firstn: true if choosing "first n" items, false if choosing "indep"
+ * @recurse_to_leaf: true if we want one device under each item of given type
+ * @out2: second output vector for leaf items (if @recurse_to_leaf)
+ */
+static int crush_choose(struct crush_map *map,
+			struct crush_bucket *bucket,
+			__u32 *weight,
+			int x, int numrep, int type,
+			int *out, int outpos,
+			int firstn, int recurse_to_leaf,
+			int *out2)
+{
+	int rep;
+	int ftotal, flocal;
+	int retry_descent, retry_bucket, skip_rep;
+	struct crush_bucket *in = bucket;
+	int r;
+	int i;
+	int item = 0;
+	int itemtype;
+	int collide, reject;
+	const int orig_tries = 5; /* attempts before we fall back to search */
+	dprintk("choose bucket %d x %d outpos %d\n", bucket->id, x, outpos);
+
+	for (rep = outpos; rep < numrep; rep++) {
+		/* keep trying until we get a non-out, non-colliding item */
+		ftotal = 0;
+		skip_rep = 0;
+		do {
+			retry_descent = 0;
+			in = bucket;               /* initial bucket */
+
+			/* choose through intervening buckets */
+			flocal = 0;
+			do {
+				collide = 0;
+				retry_bucket = 0;
+				r = rep;
+				if (in->alg == CRUSH_BUCKET_UNIFORM) {
+					/* be careful */
+					if (firstn || numrep >= in->size)
+						/* r' = r + f_total */
+						r += ftotal;
+					else if (in->size % numrep == 0)
+						/* r'=r+(n+1)*f_local */
+						r += (numrep+1) *
+							(flocal+ftotal);
+					else
+						/* r' = r + n*f_local */
+						r += numrep * (flocal+ftotal);
+				} else {
+					if (firstn)
+						/* r' = r + f_total */
+						r += ftotal;
+					else
+						/* r' = r + n*f_local */
+						r += numrep * (flocal+ftotal);
+				}
+
+				/* bucket choose */
+				if (in->size == 0) {
+					reject = 1;
+					goto reject;
+				}
+				if (flocal >= (in->size>>1) &&
+				    flocal > orig_tries)
+					item = bucket_perm_choose(in, x, r);
+				else
+					item = crush_bucket_choose(in, x, r);
+				BUG_ON(item >= map->max_devices);
+
+				/* desired type? */
+				if (item < 0)
+					itemtype = map->buckets[-1-item]->type;
+				else
+					itemtype = 0;
+				dprintk("  item %d type %d\n", item, itemtype);
+
+				/* keep going? */
+				if (itemtype != type) {
+					BUG_ON(item >= 0 ||
+					       (-1-item) >= map->max_buckets);
+					in = map->buckets[-1-item];
+					continue;
+				}
+
+				/* collision? */
+				for (i = 0; i < outpos; i++) {
+					if (out[i] == item) {
+						collide = 1;
+						break;
+					}
+				}
+
+				if (recurse_to_leaf &&
+				    item < 0 &&
+				    crush_choose(map, map->buckets[-1-item],
+						 weight,
+						 x, outpos+1, 0,
+						 out2, outpos,
+						 firstn, 0, NULL) <= outpos) {
+					reject = 1;
+				} else {
+					/* out? */
+					if (itemtype == 0)
+						reject = is_out(map, weight,
+								item, x);
+					else
+						reject = 0;
+				}
+
+reject:
+				if (reject || collide) {
+					ftotal++;
+					flocal++;
+
+					if (collide && flocal < 3)
+						/* retry locally a few times */
+						retry_bucket = 1;
+					else if (flocal < in->size + orig_tries)
+						/* exhaustive bucket search */
+						retry_bucket = 1;
+					else if (ftotal < 20)
+						/* then retry descent */
+						retry_descent = 1;
+					else
+						/* else give up */
+						skip_rep = 1;
+					dprintk("  reject %d  collide %d  "
+						"ftotal %d  flocal %d\n",
+						reject, collide, ftotal,
+						flocal);
+				}
+			} while (retry_bucket);
+		} while (retry_descent);
+
+		if (skip_rep) {
+			dprintk("skip rep\n");
+			continue;
+		}
+
+		dprintk("choose got %d\n", item);
+		out[outpos] = item;
+		outpos++;
+	}
+
+	dprintk("choose returns %d\n", outpos);
+	return outpos;
+}
+
+
+/**
+ * crush_do_rule - calculate a mapping with the given input and rule
+ * @map: the crush_map
+ * @ruleno: the rule id
+ * @x: hash input
+ * @result: pointer to result vector
+ * @result_max: maximum result size
+ * @force: force initial replica choice; -1 for none
+ */
+int crush_do_rule(struct crush_map *map,
+		  int ruleno, int x, int *result, int result_max,
+		  int force, __u32 *weight)
+{
+	int result_len;
+	int force_context[CRUSH_MAX_DEPTH];
+	int force_pos = -1;
+	int a[CRUSH_MAX_SET];
+	int b[CRUSH_MAX_SET];
+	int c[CRUSH_MAX_SET];
+	int recurse_to_leaf;
+	int *w;
+	int wsize = 0;
+	int *o;
+	int osize;
+	int *tmp;
+	struct crush_rule *rule;
+	int step;
+	int i, j;
+	int numrep;
+	int firstn;
+	int rc = -1;
+
+	BUG_ON(ruleno >= map->max_rules);
+
+	rule = map->rules[ruleno];
+	result_len = 0;
+	w = a;
+	o = b;
+
+	/*
+	 * determine hierarchical context of force, if any.  note
+	 * that this may or may not correspond to the specific types
+	 * referenced by the crush rule.
+	 */
+	if (force >= 0) {
+		if (force >= map->max_devices ||
+		    map->device_parents[force] == 0) {
+			/*dprintk("CRUSH: forcefed device dne\n");*/
+			rc = -1;  /* force fed device dne */
+			goto out;
+		}
+		if (!is_out(map, weight, force, x)) {
+			while (1) {
+				force_context[++force_pos] = force;
+				if (force >= 0)
+					force = map->device_parents[force];
+				else
+					force = map->bucket_parents[-1-force];
+				if (force == 0)
+					break;
+			}
+		}
+	}
+
+	for (step = 0; step < rule->len; step++) {
+		firstn = 0;
+		switch (rule->steps[step].op) {
+		case CRUSH_RULE_TAKE:
+			w[0] = rule->steps[step].arg1;
+			if (force_pos >= 0) {
+				BUG_ON(force_context[force_pos] != w[0]);
+				force_pos--;
+			}
+			wsize = 1;
+			break;
+
+		case CRUSH_RULE_CHOOSE_LEAF_FIRSTN:
+		case CRUSH_RULE_CHOOSE_FIRSTN:
+			firstn = 1;
+		case CRUSH_RULE_CHOOSE_LEAF_INDEP:
+		case CRUSH_RULE_CHOOSE_INDEP:
+			BUG_ON(wsize == 0);
+
+			recurse_to_leaf =
+				rule->steps[step].op ==
+				 CRUSH_RULE_CHOOSE_LEAF_FIRSTN ||
+				rule->steps[step].op ==
+				CRUSH_RULE_CHOOSE_LEAF_INDEP;
+
+			/* reset output */
+			osize = 0;
+
+			for (i = 0; i < wsize; i++) {
+				/*
+				 * see CRUSH_N, CRUSH_N_MINUS macros.
+				 * basically, numrep <= 0 means relative to
+				 * the provided result_max
+				 */
+				numrep = rule->steps[step].arg1;
+				if (numrep <= 0) {
+					numrep += result_max;
+					if (numrep <= 0)
+						continue;
+				}
+				j = 0;
+				if (osize == 0 && force_pos >= 0) {
+					/* skip any intermediate types */
+					while (force_pos &&
+					       force_context[force_pos] < 0 &&
+					       rule->steps[step].arg2 !=
+					       map->buckets[-1 -
+					       force_context[force_pos]]->type)
+						force_pos--;
+					o[osize] = force_context[force_pos];
+					if (recurse_to_leaf)
+						c[osize] = force_context[0];
+					j++;
+					force_pos--;
+				}
+				osize += crush_choose(map,
+						      map->buckets[-1-w[i]],
+						      weight,
+						      x, numrep,
+						      rule->steps[step].arg2,
+						      o+osize, j,
+						      firstn,
+						      recurse_to_leaf, c+osize);
+			}
+
+			if (recurse_to_leaf)
+				/* copy final _leaf_ values to output set */
+				memcpy(o, c, osize*sizeof(*o));
+
+			/* swap t and w arrays */
+			tmp = o;
+			o = w;
+			w = tmp;
+			wsize = osize;
+			break;
+
+
+		case CRUSH_RULE_EMIT:
+			for (i = 0; i < wsize && result_len < result_max; i++) {
+				result[result_len] = w[i];
+				result_len++;
+			}
+			wsize = 0;
+			break;
+
+		default:
+			BUG_ON(1);
+		}
+	}
+	rc = result_len;
+
+out:
+	return rc;
+}
+
+

fs/ceph/crush/mapper.h

@@ -0,0 +1,20 @@
+#ifndef _CRUSH_MAPPER_H
+#define _CRUSH_MAPPER_H
+
+/*
+ * CRUSH functions for find rules and then mapping an input to an
+ * output set.
+ *
+ * LGPL2
+ */
+
+#include "crush.h"
+
+extern int crush_find_rule(struct crush_map *map, int pool, int type, int size);
+extern int crush_do_rule(struct crush_map *map,
+			 int ruleno,
+			 int x, int *result, int result_max,
+			 int forcefeed,    /* -1 for none */
+			 __u32 *weights);
+
+#endif

fs/ceph/crypto.c

@@ -0,0 +1,408 @@
+
+#include "ceph_debug.h"
+
+#include <linux/err.h>
+#include <linux/scatterlist.h>
+#include <crypto/hash.h>
+
+#include "crypto.h"
+#include "decode.h"
+
+int ceph_crypto_key_encode(struct ceph_crypto_key *key, void **p, void *end)
+{
+	if (*p + sizeof(u16) + sizeof(key->created) +
+	    sizeof(u16) + key->len > end)
+		return -ERANGE;
+	ceph_encode_16(p, key->type);
+	ceph_encode_copy(p, &key->created, sizeof(key->created));
+	ceph_encode_16(p, key->len);
+	ceph_encode_copy(p, key->key, key->len);
+	return 0;
+}
+
+int ceph_crypto_key_decode(struct ceph_crypto_key *key, void **p, void *end)
+{
+	ceph_decode_need(p, end, 2*sizeof(u16) + sizeof(key->created), bad);
+	key->type = ceph_decode_16(p);
+	ceph_decode_copy(p, &key->created, sizeof(key->created));
+	key->len = ceph_decode_16(p);
+	ceph_decode_need(p, end, key->len, bad);
+	key->key = kmalloc(key->len, GFP_NOFS);
+	if (!key->key)
+		return -ENOMEM;
+	ceph_decode_copy(p, key->key, key->len);
+	return 0;
+
+bad:
+	dout("failed to decode crypto key\n");
+	return -EINVAL;
+}
+
+int ceph_crypto_key_unarmor(struct ceph_crypto_key *key, const char *inkey)
+{
+	int inlen = strlen(inkey);
+	int blen = inlen * 3 / 4;
+	void *buf, *p;
+	int ret;
+
+	dout("crypto_key_unarmor %s\n", inkey);
+	buf = kmalloc(blen, GFP_NOFS);
+	if (!buf)
+		return -ENOMEM;
+	blen = ceph_unarmor(buf, inkey, inkey+inlen);
+	if (blen < 0) {
+		kfree(buf);
+		return blen;
+	}
+
+	p = buf;
+	ret = ceph_crypto_key_decode(key, &p, p + blen);
+	kfree(buf);
+	if (ret)
+		return ret;
+	dout("crypto_key_unarmor key %p type %d len %d\n", key,
+	     key->type, key->len);
+	return 0;
+}
+
+
+
+#define AES_KEY_SIZE 16
+
+static struct crypto_blkcipher *ceph_crypto_alloc_cipher(void)
+{
+	return crypto_alloc_blkcipher("cbc(aes)", 0, CRYPTO_ALG_ASYNC);
+}
+
+const u8 *aes_iv = "cephsageyudagreg";
+
+int ceph_aes_encrypt(const void *key, int key_len, void *dst, size_t *dst_len,
+		     const void *src, size_t src_len)
+{
+	struct scatterlist sg_in[2], sg_out[1];
+	struct crypto_blkcipher *tfm = ceph_crypto_alloc_cipher();
+	struct blkcipher_desc desc = { .tfm = tfm, .flags = 0 };
+	int ret;
+	void *iv;
+	int ivsize;
+	size_t zero_padding = (0x10 - (src_len & 0x0f));
+	char pad[16];
+
+	if (IS_ERR(tfm))
+		return PTR_ERR(tfm);
+
+	memset(pad, zero_padding, zero_padding);
+
+	*dst_len = src_len + zero_padding;
+
+	crypto_blkcipher_setkey((void *)tfm, key, key_len);
+	sg_init_table(sg_in, 2);
+	sg_set_buf(&sg_in[0], src, src_len);
+	sg_set_buf(&sg_in[1], pad, zero_padding);
+	sg_init_table(sg_out, 1);
+	sg_set_buf(sg_out, dst, *dst_len);
+	iv = crypto_blkcipher_crt(tfm)->iv;
+	ivsize = crypto_blkcipher_ivsize(tfm);
+
+	memcpy(iv, aes_iv, ivsize);
+	/*
+	print_hex_dump(KERN_ERR, "enc key: ", DUMP_PREFIX_NONE, 16, 1,
+		       key, key_len, 1);
+	print_hex_dump(KERN_ERR, "enc src: ", DUMP_PREFIX_NONE, 16, 1,
+			src, src_len, 1);
+	print_hex_dump(KERN_ERR, "enc pad: ", DUMP_PREFIX_NONE, 16, 1,
+			pad, zero_padding, 1);
+	*/
+	ret = crypto_blkcipher_encrypt(&desc, sg_out, sg_in,
+				     src_len + zero_padding);
+	crypto_free_blkcipher(tfm);
+	if (ret < 0)
+		pr_err("ceph_aes_crypt failed %d\n", ret);
+	/*
+	print_hex_dump(KERN_ERR, "enc out: ", DUMP_PREFIX_NONE, 16, 1,
+		       dst, *dst_len, 1);
+	*/
+	return 0;
+}
+
+int ceph_aes_encrypt2(const void *key, int key_len, void *dst, size_t *dst_len,
+		      const void *src1, size_t src1_len,
+		      const void *src2, size_t src2_len)
+{
+	struct scatterlist sg_in[3], sg_out[1];
+	struct crypto_blkcipher *tfm = ceph_crypto_alloc_cipher();
+	struct blkcipher_desc desc = { .tfm = tfm, .flags = 0 };
+	int ret;
+	void *iv;
+	int ivsize;
+	size_t zero_padding = (0x10 - ((src1_len + src2_len) & 0x0f));
+	char pad[16];
+
+	if (IS_ERR(tfm))
+		return PTR_ERR(tfm);
+
+	memset(pad, zero_padding, zero_padding);
+
+	*dst_len = src1_len + src2_len + zero_padding;
+
+	crypto_blkcipher_setkey((void *)tfm, key, key_len);
+	sg_init_table(sg_in, 3);
+	sg_set_buf(&sg_in[0], src1, src1_len);
+	sg_set_buf(&sg_in[1], src2, src2_len);
+	sg_set_buf(&sg_in[2], pad, zero_padding);
+	sg_init_table(sg_out, 1);
+	sg_set_buf(sg_out, dst, *dst_len);
+	iv = crypto_blkcipher_crt(tfm)->iv;
+	ivsize = crypto_blkcipher_ivsize(tfm);
+
+	memcpy(iv, aes_iv, ivsize);
+	/*
+	print_hex_dump(KERN_ERR, "enc  key: ", DUMP_PREFIX_NONE, 16, 1,
+		       key, key_len, 1);
+	print_hex_dump(KERN_ERR, "enc src1: ", DUMP_PREFIX_NONE, 16, 1,
+			src1, src1_len, 1);
+	print_hex_dump(KERN_ERR, "enc src2: ", DUMP_PREFIX_NONE, 16, 1,
+			src2, src2_len, 1);
+	print_hex_dump(KERN_ERR, "enc  pad: ", DUMP_PREFIX_NONE, 16, 1,
+			pad, zero_padding, 1);
+	*/
+	ret = crypto_blkcipher_encrypt(&desc, sg_out, sg_in,
+				     src1_len + src2_len + zero_padding);
+	crypto_free_blkcipher(tfm);
+	if (ret < 0)
+		pr_err("ceph_aes_crypt2 failed %d\n", ret);
+	/*
+	print_hex_dump(KERN_ERR, "enc  out: ", DUMP_PREFIX_NONE, 16, 1,
+		       dst, *dst_len, 1);
+	*/
+	return 0;
+}
+
+int ceph_aes_decrypt(const void *key, int key_len, void *dst, size_t *dst_len,
+		     const void *src, size_t src_len)
+{
+	struct scatterlist sg_in[1], sg_out[2];
+	struct crypto_blkcipher *tfm = ceph_crypto_alloc_cipher();
+	struct blkcipher_desc desc = { .tfm = tfm };
+	char pad[16];
+	void *iv;
+	int ivsize;
+	int ret;
+	int last_byte;
+
+	if (IS_ERR(tfm))
+		return PTR_ERR(tfm);
+
+	crypto_blkcipher_setkey((void *)tfm, key, key_len);
+	sg_init_table(sg_in, 1);
+	sg_init_table(sg_out, 2);
+	sg_set_buf(sg_in, src, src_len);
+	sg_set_buf(&sg_out[0], dst, *dst_len);
+	sg_set_buf(&sg_out[1], pad, sizeof(pad));
+
+	iv = crypto_blkcipher_crt(tfm)->iv;
+	ivsize = crypto_blkcipher_ivsize(tfm);
+
+	memcpy(iv, aes_iv, ivsize);
+
+	/*
+	print_hex_dump(KERN_ERR, "dec key: ", DUMP_PREFIX_NONE, 16, 1,
+		       key, key_len, 1);
+	print_hex_dump(KERN_ERR, "dec  in: ", DUMP_PREFIX_NONE, 16, 1,
+		       src, src_len, 1);
+	*/
+
+	ret = crypto_blkcipher_decrypt(&desc, sg_out, sg_in, src_len);
+	crypto_free_blkcipher(tfm);
+	if (ret < 0) {
+		pr_err("ceph_aes_decrypt failed %d\n", ret);
+		return ret;
+	}
+
+	if (src_len <= *dst_len)
+		last_byte = ((char *)dst)[src_len - 1];
+	else
+		last_byte = pad[src_len - *dst_len - 1];
+	if (last_byte <= 16 && src_len >= last_byte) {
+		*dst_len = src_len - last_byte;
+	} else {
+		pr_err("ceph_aes_decrypt got bad padding %d on src len %d\n",
+		       last_byte, (int)src_len);
+		return -EPERM;  /* bad padding */
+	}
+	/*
+	print_hex_dump(KERN_ERR, "dec out: ", DUMP_PREFIX_NONE, 16, 1,
+		       dst, *dst_len, 1);
+	*/
+	return 0;
+}
+
+int ceph_aes_decrypt2(const void *key, int key_len,
+		      void *dst1, size_t *dst1_len,
+		      void *dst2, size_t *dst2_len,
+		      const void *src, size_t src_len)
+{
+	struct scatterlist sg_in[1], sg_out[3];
+	struct crypto_blkcipher *tfm = ceph_crypto_alloc_cipher();
+	struct blkcipher_desc desc = { .tfm = tfm };
+	char pad[16];
+	void *iv;
+	int ivsize;
+	int ret;
+	int last_byte;
+
+	if (IS_ERR(tfm))
+		return PTR_ERR(tfm);
+
+	sg_init_table(sg_in, 1);
+	sg_set_buf(sg_in, src, src_len);
+	sg_init_table(sg_out, 3);
+	sg_set_buf(&sg_out[0], dst1, *dst1_len);
+	sg_set_buf(&sg_out[1], dst2, *dst2_len);
+	sg_set_buf(&sg_out[2], pad, sizeof(pad));
+
+	crypto_blkcipher_setkey((void *)tfm, key, key_len);
+	iv = crypto_blkcipher_crt(tfm)->iv;
+	ivsize = crypto_blkcipher_ivsize(tfm);
+
+	memcpy(iv, aes_iv, ivsize);
+
+	/*
+	print_hex_dump(KERN_ERR, "dec  key: ", DUMP_PREFIX_NONE, 16, 1,
+		       key, key_len, 1);
+	print_hex_dump(KERN_ERR, "dec   in: ", DUMP_PREFIX_NONE, 16, 1,
+		       src, src_len, 1);
+	*/
+
+	ret = crypto_blkcipher_decrypt(&desc, sg_out, sg_in, src_len);
+	crypto_free_blkcipher(tfm);
+	if (ret < 0) {
+		pr_err("ceph_aes_decrypt failed %d\n", ret);
+		return ret;
+	}
+
+	if (src_len <= *dst1_len)
+		last_byte = ((char *)dst1)[src_len - 1];
+	else if (src_len <= *dst1_len + *dst2_len)
+		last_byte = ((char *)dst2)[src_len - *dst1_len - 1];
+	else
+		last_byte = pad[src_len - *dst1_len - *dst2_len - 1];
+	if (last_byte <= 16 && src_len >= last_byte) {
+		src_len -= last_byte;
+	} else {
+		pr_err("ceph_aes_decrypt got bad padding %d on src len %d\n",
+		       last_byte, (int)src_len);
+		return -EPERM;  /* bad padding */
+	}
+
+	if (src_len < *dst1_len) {
+		*dst1_len = src_len;
+		*dst2_len = 0;
+	} else {
+		*dst2_len = src_len - *dst1_len;
+	}
+	/*
+	print_hex_dump(KERN_ERR, "dec  out1: ", DUMP_PREFIX_NONE, 16, 1,
+		       dst1, *dst1_len, 1);
+	print_hex_dump(KERN_ERR, "dec  out2: ", DUMP_PREFIX_NONE, 16, 1,
+		       dst2, *dst2_len, 1);
+	*/
+
+	return 0;
+}
+
+
+int ceph_decrypt(struct ceph_crypto_key *secret, void *dst, size_t *dst_len,
+		 const void *src, size_t src_len)
+{
+	switch (secret->type) {
+	case CEPH_CRYPTO_NONE:
+		if (*dst_len < src_len)
+			return -ERANGE;
+		memcpy(dst, src, src_len);
+		*dst_len = src_len;
+		return 0;
+
+	case CEPH_CRYPTO_AES:
+		return ceph_aes_decrypt(secret->key, secret->len, dst,
+					dst_len, src, src_len);
+
+	default:
+		return -EINVAL;
+	}
+}
+
+int ceph_decrypt2(struct ceph_crypto_key *secret,
+			void *dst1, size_t *dst1_len,
+			void *dst2, size_t *dst2_len,
+			const void *src, size_t src_len)
+{
+	size_t t;
+
+	switch (secret->type) {
+	case CEPH_CRYPTO_NONE:
+		if (*dst1_len + *dst2_len < src_len)
+			return -ERANGE;
+		t = min(*dst1_len, src_len);
+		memcpy(dst1, src, t);
+		*dst1_len = t;
+		src += t;
+		src_len -= t;
+		if (src_len) {
+			t = min(*dst2_len, src_len);
+			memcpy(dst2, src, t);
+			*dst2_len = t;
+		}
+		return 0;
+
+	case CEPH_CRYPTO_AES:
+		return ceph_aes_decrypt2(secret->key, secret->len,
+					 dst1, dst1_len, dst2, dst2_len,
+					 src, src_len);
+
+	default:
+		return -EINVAL;
+	}
+}
+
+int ceph_encrypt(struct ceph_crypto_key *secret, void *dst, size_t *dst_len,
+		 const void *src, size_t src_len)
+{
+	switch (secret->type) {
+	case CEPH_CRYPTO_NONE:
+		if (*dst_len < src_len)
+			return -ERANGE;
+		memcpy(dst, src, src_len);
+		*dst_len = src_len;
+		return 0;
+
+	case CEPH_CRYPTO_AES:
+		return ceph_aes_encrypt(secret->key, secret->len, dst,
+					dst_len, src, src_len);
+
+	default:
+		return -EINVAL;
+	}
+}
+
+int ceph_encrypt2(struct ceph_crypto_key *secret, void *dst, size_t *dst_len,
+		  const void *src1, size_t src1_len,
+		  const void *src2, size_t src2_len)
+{
+	switch (secret->type) {
+	case CEPH_CRYPTO_NONE:
+		if (*dst_len < src1_len + src2_len)
+			return -ERANGE;
+		memcpy(dst, src1, src1_len);
+		memcpy(dst + src1_len, src2, src2_len);
+		*dst_len = src1_len + src2_len;
+		return 0;
+
+	case CEPH_CRYPTO_AES:
+		return ceph_aes_encrypt2(secret->key, secret->len, dst, dst_len,
+					 src1, src1_len, src2, src2_len);
+
+	default:
+		return -EINVAL;
+	}
+}

fs/ceph/crypto.h

@@ -0,0 +1,48 @@
+#ifndef _FS_CEPH_CRYPTO_H
+#define _FS_CEPH_CRYPTO_H
+
+#include "types.h"
+#include "buffer.h"
+
+/*
+ * cryptographic secret
+ */
+struct ceph_crypto_key {
+	int type;
+	struct ceph_timespec created;
+	int len;
+	void *key;
+};
+
+static inline void ceph_crypto_key_destroy(struct ceph_crypto_key *key)
+{
+	kfree(key->key);
+}
+
+extern int ceph_crypto_key_encode(struct ceph_crypto_key *key,
+				  void **p, void *end);
+extern int ceph_crypto_key_decode(struct ceph_crypto_key *key,
+				  void **p, void *end);
+extern int ceph_crypto_key_unarmor(struct ceph_crypto_key *key, const char *in);
+
+/* crypto.c */
+extern int ceph_decrypt(struct ceph_crypto_key *secret,
+			void *dst, size_t *dst_len,
+			const void *src, size_t src_len);
+extern int ceph_encrypt(struct ceph_crypto_key *secret,
+			void *dst, size_t *dst_len,
+			const void *src, size_t src_len);
+extern int ceph_decrypt2(struct ceph_crypto_key *secret,
+			void *dst1, size_t *dst1_len,
+			void *dst2, size_t *dst2_len,
+			const void *src, size_t src_len);
+extern int ceph_encrypt2(struct ceph_crypto_key *secret,
+			 void *dst, size_t *dst_len,
+			 const void *src1, size_t src1_len,
+			 const void *src2, size_t src2_len);
+
+/* armor.c */
+extern int ceph_armor(char *dst, const void *src, const void *end);
+extern int ceph_unarmor(void *dst, const char *src, const char *end);
+
+#endif

fs/ceph/debugfs.c

@@ -0,0 +1,483 @@
+#include "ceph_debug.h"
+
+#include <linux/device.h>
+#include <linux/module.h>
+#include <linux/ctype.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+
+#include "super.h"
+#include "mds_client.h"
+#include "mon_client.h"
+#include "auth.h"
+
+#ifdef CONFIG_DEBUG_FS
+
+/*
+ * Implement /sys/kernel/debug/ceph fun
+ *
+ * /sys/kernel/debug/ceph/client*  - an instance of the ceph client
+ *      .../osdmap      - current osdmap
+ *      .../mdsmap      - current mdsmap
+ *      .../monmap      - current monmap
+ *      .../osdc        - active osd requests
+ *      .../mdsc        - active mds requests
+ *      .../monc        - mon client state
+ *      .../dentry_lru  - dump contents of dentry lru
+ *      .../caps        - expose cap (reservation) stats
+ *      .../bdi         - symlink to ../../bdi/something
+ */
+
+static struct dentry *ceph_debugfs_dir;
+
+static int monmap_show(struct seq_file *s, void *p)
+{
+	int i;
+	struct ceph_client *client = s->private;
+
+	if (client->monc.monmap == NULL)
+		return 0;
+
+	seq_printf(s, "epoch %d\n", client->monc.monmap->epoch);
+	for (i = 0; i < client->monc.monmap->num_mon; i++) {
+		struct ceph_entity_inst *inst =
+			&client->monc.monmap->mon_inst[i];
+
+		seq_printf(s, "\t%s%lld\t%s\n",
+			   ENTITY_NAME(inst->name),
+			   pr_addr(&inst->addr.in_addr));
+	}
+	return 0;
+}
+
+static int mdsmap_show(struct seq_file *s, void *p)
+{
+	int i;
+	struct ceph_client *client = s->private;
+
+	if (client->mdsc.mdsmap == NULL)
+		return 0;
+	seq_printf(s, "epoch %d\n", client->mdsc.mdsmap->m_epoch);
+	seq_printf(s, "root %d\n", client->mdsc.mdsmap->m_root);
+	seq_printf(s, "session_timeout %d\n",
+		       client->mdsc.mdsmap->m_session_timeout);
+	seq_printf(s, "session_autoclose %d\n",
+		       client->mdsc.mdsmap->m_session_autoclose);
+	for (i = 0; i < client->mdsc.mdsmap->m_max_mds; i++) {
+		struct ceph_entity_addr *addr =
+			&client->mdsc.mdsmap->m_info[i].addr;
+		int state = client->mdsc.mdsmap->m_info[i].state;
+
+		seq_printf(s, "\tmds%d\t%s\t(%s)\n", i, pr_addr(&addr->in_addr),
+			       ceph_mds_state_name(state));
+	}
+	return 0;
+}
+
+static int osdmap_show(struct seq_file *s, void *p)
+{
+	int i;
+	struct ceph_client *client = s->private;
+	struct rb_node *n;
+
+	if (client->osdc.osdmap == NULL)
+		return 0;
+	seq_printf(s, "epoch %d\n", client->osdc.osdmap->epoch);
+	seq_printf(s, "flags%s%s\n",
+		   (client->osdc.osdmap->flags & CEPH_OSDMAP_NEARFULL) ?
+		   " NEARFULL" : "",
+		   (client->osdc.osdmap->flags & CEPH_OSDMAP_FULL) ?
+		   " FULL" : "");
+	for (n = rb_first(&client->osdc.osdmap->pg_pools); n; n = rb_next(n)) {
+		struct ceph_pg_pool_info *pool =
+			rb_entry(n, struct ceph_pg_pool_info, node);
+		seq_printf(s, "pg_pool %d pg_num %d / %d, lpg_num %d / %d\n",
+			   pool->id, pool->v.pg_num, pool->pg_num_mask,
+			   pool->v.lpg_num, pool->lpg_num_mask);
+	}
+	for (i = 0; i < client->osdc.osdmap->max_osd; i++) {
+		struct ceph_entity_addr *addr =
+			&client->osdc.osdmap->osd_addr[i];
+		int state = client->osdc.osdmap->osd_state[i];
+		char sb[64];
+
+		seq_printf(s, "\tosd%d\t%s\t%3d%%\t(%s)\n",
+			   i, pr_addr(&addr->in_addr),
+			   ((client->osdc.osdmap->osd_weight[i]*100) >> 16),
+			   ceph_osdmap_state_str(sb, sizeof(sb), state));
+	}
+	return 0;
+}
+
+static int monc_show(struct seq_file *s, void *p)
+{
+	struct ceph_client *client = s->private;
+	struct ceph_mon_statfs_request *req;
+	struct ceph_mon_client *monc = &client->monc;
+	struct rb_node *rp;
+
+	mutex_lock(&monc->mutex);
+
+	if (monc->have_mdsmap)
+		seq_printf(s, "have mdsmap %u\n", (unsigned)monc->have_mdsmap);
+	if (monc->have_osdmap)
+		seq_printf(s, "have osdmap %u\n", (unsigned)monc->have_osdmap);
+	if (monc->want_next_osdmap)
+		seq_printf(s, "want next osdmap\n");
+
+	for (rp = rb_first(&monc->statfs_request_tree); rp; rp = rb_next(rp)) {
+		req = rb_entry(rp, struct ceph_mon_statfs_request, node);
+		seq_printf(s, "%lld statfs\n", req->tid);
+	}
+
+	mutex_unlock(&monc->mutex);
+	return 0;
+}
+
+static int mdsc_show(struct seq_file *s, void *p)
+{
+	struct ceph_client *client = s->private;
+	struct ceph_mds_client *mdsc = &client->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)
+			seq_printf(s, "%lld\tmds%d\t", req->r_tid, req->r_mds);
+		else
+			seq_printf(s, "%lld\t(no request)\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);
+			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);
+			spin_lock(&req->r_old_dentry->d_lock);
+			seq_printf(s, " #%llx/%.*s (%s)",
+			   ceph_ino(req->r_old_dentry->d_parent->d_inode),
+				   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 osdc_show(struct seq_file *s, void *pp)
+{
+	struct ceph_client *client = s->private;
+	struct ceph_osd_client *osdc = &client->osdc;
+	struct rb_node *p;
+
+	mutex_lock(&osdc->request_mutex);
+	for (p = rb_first(&osdc->requests); p; p = rb_next(p)) {
+		struct ceph_osd_request *req;
+		struct ceph_osd_request_head *head;
+		struct ceph_osd_op *op;
+		int num_ops;
+		int opcode, olen;
+		int i;
+
+		req = rb_entry(p, struct ceph_osd_request, r_node);
+
+		seq_printf(s, "%lld\tosd%d\t%d.%x\t", req->r_tid,
+			   req->r_osd ? req->r_osd->o_osd : -1,
+			   le32_to_cpu(req->r_pgid.pool),
+			   le16_to_cpu(req->r_pgid.ps));
+
+		head = req->r_request->front.iov_base;
+		op = (void *)(head + 1);
+
+		num_ops = le16_to_cpu(head->num_ops);
+		olen = le32_to_cpu(head->object_len);
+		seq_printf(s, "%.*s", olen,
+			   (const char *)(head->ops + num_ops));
+
+		if (req->r_reassert_version.epoch)
+			seq_printf(s, "\t%u'%llu",
+			   (unsigned)le32_to_cpu(req->r_reassert_version.epoch),
+			   le64_to_cpu(req->r_reassert_version.version));
+		else
+			seq_printf(s, "\t");
+
+		for (i = 0; i < num_ops; i++) {
+			opcode = le16_to_cpu(op->op);
+			seq_printf(s, "\t%s", ceph_osd_op_name(opcode));
+			op++;
+		}
+
+		seq_printf(s, "\n");
+	}
+	mutex_unlock(&osdc->request_mutex);
+	return 0;
+}
+
+static int caps_show(struct seq_file *s, void *p)
+{
+	struct ceph_client *client = p;
+	int total, avail, used, reserved, min;
+
+	ceph_reservation_status(client, &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_client *client = s->private;
+	struct ceph_mds_client *mdsc = &client->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;
+}
+
+#define DEFINE_SHOW_FUNC(name) 						\
+static int name##_open(struct inode *inode, struct file *file)		\
+{									\
+	struct seq_file *sf;						\
+	int ret;							\
+									\
+	ret = single_open(file, name, NULL);				\
+	sf = file->private_data;					\
+	sf->private = inode->i_private;					\
+	return ret;							\
+}									\
+									\
+static const struct file_operations name##_fops = {			\
+	.open		= name##_open,					\
+	.read		= seq_read,					\
+	.llseek		= seq_lseek,					\
+	.release	= single_release,				\
+};
+
+DEFINE_SHOW_FUNC(monmap_show)
+DEFINE_SHOW_FUNC(mdsmap_show)
+DEFINE_SHOW_FUNC(osdmap_show)
+DEFINE_SHOW_FUNC(monc_show)
+DEFINE_SHOW_FUNC(mdsc_show)
+DEFINE_SHOW_FUNC(osdc_show)
+DEFINE_SHOW_FUNC(dentry_lru_show)
+DEFINE_SHOW_FUNC(caps_show)
+
+static int congestion_kb_set(void *data, u64 val)
+{
+	struct ceph_client *client = (struct ceph_client *)data;
+
+	if (client)
+		client->mount_args->congestion_kb = (int)val;
+
+	return 0;
+}
+
+static int congestion_kb_get(void *data, u64 *val)
+{
+	struct ceph_client *client = (struct ceph_client *)data;
+
+	if (client)
+		*val = (u64)client->mount_args->congestion_kb;
+
+	return 0;
+}
+
+
+DEFINE_SIMPLE_ATTRIBUTE(congestion_kb_fops, congestion_kb_get,
+			congestion_kb_set, "%llu\n");
+
+int __init ceph_debugfs_init(void)
+{
+	ceph_debugfs_dir = debugfs_create_dir("ceph", NULL);
+	if (!ceph_debugfs_dir)
+		return -ENOMEM;
+	return 0;
+}
+
+void ceph_debugfs_cleanup(void)
+{
+	debugfs_remove(ceph_debugfs_dir);
+}
+
+int ceph_debugfs_client_init(struct ceph_client *client)
+{
+	int ret = 0;
+	char name[80];
+
+	snprintf(name, sizeof(name), FSID_FORMAT ".client%lld",
+		 PR_FSID(&client->fsid), client->monc.auth->global_id);
+
+	client->debugfs_dir = debugfs_create_dir(name, ceph_debugfs_dir);
+	if (!client->debugfs_dir)
+		goto out;
+
+	client->monc.debugfs_file = debugfs_create_file("monc",
+						      0600,
+						      client->debugfs_dir,
+						      client,
+						      &monc_show_fops);
+	if (!client->monc.debugfs_file)
+		goto out;
+
+	client->mdsc.debugfs_file = debugfs_create_file("mdsc",
+						      0600,
+						      client->debugfs_dir,
+						      client,
+						      &mdsc_show_fops);
+	if (!client->mdsc.debugfs_file)
+		goto out;
+
+	client->osdc.debugfs_file = debugfs_create_file("osdc",
+						      0600,
+						      client->debugfs_dir,
+						      client,
+						      &osdc_show_fops);
+	if (!client->osdc.debugfs_file)
+		goto out;
+
+	client->debugfs_monmap = debugfs_create_file("monmap",
+					0600,
+					client->debugfs_dir,
+					client,
+					&monmap_show_fops);
+	if (!client->debugfs_monmap)
+		goto out;
+
+	client->debugfs_mdsmap = debugfs_create_file("mdsmap",
+					0600,
+					client->debugfs_dir,
+					client,
+					&mdsmap_show_fops);
+	if (!client->debugfs_mdsmap)
+		goto out;
+
+	client->debugfs_osdmap = debugfs_create_file("osdmap",
+					0600,
+					client->debugfs_dir,
+					client,
+					&osdmap_show_fops);
+	if (!client->debugfs_osdmap)
+		goto out;
+
+	client->debugfs_dentry_lru = debugfs_create_file("dentry_lru",
+					0600,
+					client->debugfs_dir,
+					client,
+					&dentry_lru_show_fops);
+	if (!client->debugfs_dentry_lru)
+		goto out;
+
+	client->debugfs_caps = debugfs_create_file("caps",
+						   0400,
+						   client->debugfs_dir,
+						   client,
+						   &caps_show_fops);
+	if (!client->debugfs_caps)
+		goto out;
+
+	client->debugfs_congestion_kb = debugfs_create_file("writeback_congestion_kb",
+						   0600,
+						   client->debugfs_dir,
+						   client,
+						   &congestion_kb_fops);
+	if (!client->debugfs_congestion_kb)
+		goto out;
+
+	sprintf(name, "../../bdi/%s", dev_name(client->sb->s_bdi->dev));
+	client->debugfs_bdi = debugfs_create_symlink("bdi", client->debugfs_dir,
+						     name);
+
+	return 0;
+
+out:
+	ceph_debugfs_client_cleanup(client);
+	return ret;
+}
+
+void ceph_debugfs_client_cleanup(struct ceph_client *client)
+{
+	debugfs_remove(client->debugfs_bdi);
+	debugfs_remove(client->debugfs_caps);
+	debugfs_remove(client->debugfs_dentry_lru);
+	debugfs_remove(client->debugfs_osdmap);
+	debugfs_remove(client->debugfs_mdsmap);
+	debugfs_remove(client->debugfs_monmap);
+	debugfs_remove(client->osdc.debugfs_file);
+	debugfs_remove(client->mdsc.debugfs_file);
+	debugfs_remove(client->monc.debugfs_file);
+	debugfs_remove(client->debugfs_congestion_kb);
+	debugfs_remove(client->debugfs_dir);
+}
+
+#else  // CONFIG_DEBUG_FS
+
+int __init ceph_debugfs_init(void)
+{
+	return 0;
+}
+
+void ceph_debugfs_cleanup(void)
+{
+}
+
+int ceph_debugfs_client_init(struct ceph_client *client)
+{
+	return 0;
+}
+
+void ceph_debugfs_client_cleanup(struct ceph_client *client)
+{
+}
+
+#endif  // CONFIG_DEBUG_FS

fs/ceph/decode.h

@@ -0,0 +1,194 @@
+#ifndef __CEPH_DECODE_H
+#define __CEPH_DECODE_H
+
+#include <asm/unaligned.h>
+#include <linux/time.h>
+
+#include "types.h"
+
+/*
+ * in all cases,
+ *   void **p     pointer to position pointer
+ *   void *end    pointer to end of buffer (last byte + 1)
+ */
+
+static inline u64 ceph_decode_64(void **p)
+{
+	u64 v = get_unaligned_le64(*p);
+	*p += sizeof(u64);
+	return v;
+}
+static inline u32 ceph_decode_32(void **p)
+{
+	u32 v = get_unaligned_le32(*p);
+	*p += sizeof(u32);
+	return v;
+}
+static inline u16 ceph_decode_16(void **p)
+{
+	u16 v = get_unaligned_le16(*p);
+	*p += sizeof(u16);
+	return v;
+}
+static inline u8 ceph_decode_8(void **p)
+{
+	u8 v = *(u8 *)*p;
+	(*p)++;
+	return v;
+}
+static inline void ceph_decode_copy(void **p, void *pv, size_t n)
+{
+	memcpy(pv, *p, n);
+	*p += n;
+}
+
+/*
+ * bounds check input.
+ */
+#define ceph_decode_need(p, end, n, bad)		\
+	do {						\
+		if (unlikely(*(p) + (n) > (end))) 	\
+			goto bad;			\
+	} while (0)
+
+#define ceph_decode_64_safe(p, end, v, bad)			\
+	do {							\
+		ceph_decode_need(p, end, sizeof(u64), bad);	\
+		v = ceph_decode_64(p);				\
+	} while (0)
+#define ceph_decode_32_safe(p, end, v, bad)			\
+	do {							\
+		ceph_decode_need(p, end, sizeof(u32), bad);	\
+		v = ceph_decode_32(p);				\
+	} while (0)
+#define ceph_decode_16_safe(p, end, v, bad)			\
+	do {							\
+		ceph_decode_need(p, end, sizeof(u16), bad);	\
+		v = ceph_decode_16(p);				\
+	} while (0)
+#define ceph_decode_8_safe(p, end, v, bad)			\
+	do {							\
+		ceph_decode_need(p, end, sizeof(u8), bad);	\
+		v = ceph_decode_8(p);				\
+	} while (0)
+
+#define ceph_decode_copy_safe(p, end, pv, n, bad)		\
+	do {							\
+		ceph_decode_need(p, end, n, bad);		\
+		ceph_decode_copy(p, pv, n);			\
+	} while (0)
+
+/*
+ * struct ceph_timespec <-> struct timespec
+ */
+static inline void ceph_decode_timespec(struct timespec *ts,
+					const struct ceph_timespec *tv)
+{
+	ts->tv_sec = le32_to_cpu(tv->tv_sec);
+	ts->tv_nsec = le32_to_cpu(tv->tv_nsec);
+}
+static inline void ceph_encode_timespec(struct ceph_timespec *tv,
+					const struct timespec *ts)
+{
+	tv->tv_sec = cpu_to_le32(ts->tv_sec);
+	tv->tv_nsec = cpu_to_le32(ts->tv_nsec);
+}
+
+/*
+ * sockaddr_storage <-> ceph_sockaddr
+ */
+static inline void ceph_encode_addr(struct ceph_entity_addr *a)
+{
+	a->in_addr.ss_family = htons(a->in_addr.ss_family);
+}
+static inline void ceph_decode_addr(struct ceph_entity_addr *a)
+{
+	a->in_addr.ss_family = ntohs(a->in_addr.ss_family);
+	WARN_ON(a->in_addr.ss_family == 512);
+}
+
+/*
+ * encoders
+ */
+static inline void ceph_encode_64(void **p, u64 v)
+{
+	put_unaligned_le64(v, (__le64 *)*p);
+	*p += sizeof(u64);
+}
+static inline void ceph_encode_32(void **p, u32 v)
+{
+	put_unaligned_le32(v, (__le32 *)*p);
+	*p += sizeof(u32);
+}
+static inline void ceph_encode_16(void **p, u16 v)
+{
+	put_unaligned_le16(v, (__le16 *)*p);
+	*p += sizeof(u16);
+}
+static inline void ceph_encode_8(void **p, u8 v)
+{
+	*(u8 *)*p = v;
+	(*p)++;
+}
+static inline void ceph_encode_copy(void **p, const void *s, int len)
+{
+	memcpy(*p, s, len);
+	*p += len;
+}
+
+/*
+ * filepath, string encoders
+ */
+static inline void ceph_encode_filepath(void **p, void *end,
+					u64 ino, const char *path)
+{
+	u32 len = path ? strlen(path) : 0;
+	BUG_ON(*p + sizeof(ino) + sizeof(len) + len > end);
+	ceph_encode_8(p, 1);
+	ceph_encode_64(p, ino);
+	ceph_encode_32(p, len);
+	if (len)
+		memcpy(*p, path, len);
+	*p += len;
+}
+
+static inline void ceph_encode_string(void **p, void *end,
+				      const char *s, u32 len)
+{
+	BUG_ON(*p + sizeof(len) + len > end);
+	ceph_encode_32(p, len);
+	if (len)
+		memcpy(*p, s, len);
+	*p += len;
+}
+
+#define ceph_encode_need(p, end, n, bad)		\
+	do {						\
+		if (unlikely(*(p) + (n) > (end))) 	\
+			goto bad;			\
+	} while (0)
+
+#define ceph_encode_64_safe(p, end, v, bad)			\
+	do {							\
+		ceph_encode_need(p, end, sizeof(u64), bad);	\
+		ceph_encode_64(p, v);				\
+	} while (0)
+#define ceph_encode_32_safe(p, end, v, bad)			\
+	do {							\
+		ceph_encode_need(p, end, sizeof(u32), bad);	\
+		ceph_encode_32(p, v);			\
+	} while (0)
+#define ceph_encode_16_safe(p, end, v, bad)			\
+	do {							\
+		ceph_encode_need(p, end, sizeof(u16), bad);	\
+		ceph_encode_16(p, v);			\
+	} while (0)
+
+#define ceph_encode_copy_safe(p, end, pv, n, bad)		\
+	do {							\
+		ceph_encode_need(p, end, n, bad);		\
+		ceph_encode_copy(p, pv, n);			\
+	} while (0)
+
+
+#endif

fs/ceph/export.c

@@ -0,0 +1,223 @@
+#include "ceph_debug.h"
+
+#include <linux/exportfs.h>
+#include <asm/unaligned.h>
+
+#include "super.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));
+
+static int ceph_encode_fh(struct dentry *dentry, u32 *rawfh, int *max_len,
+			  int connectable)
+{
+	struct ceph_nfs_fh *fh = (void *)rawfh;
+	struct ceph_nfs_confh *cfh = (void *)rawfh;
+	struct dentry *parent = dentry->d_parent;
+	struct inode *inode = dentry->d_inode;
+	int type;
+
+	/* don't re-export snaps */
+	if (ceph_snap(inode) != CEPH_NOSNAP)
+		return -EINVAL;
+
+	if (*max_len >= sizeof(*cfh)) {
+		dout("encode_fh %p connectable\n", dentry);
+		cfh->ino = ceph_ino(dentry->d_inode);
+		cfh->parent_ino = ceph_ino(parent->d_inode);
+		cfh->parent_name_hash = parent->d_name.hash;
+		*max_len = sizeof(*cfh);
+		type = 2;
+	} else if (*max_len > sizeof(*fh)) {
+		if (connectable)
+			return -ENOSPC;
+		dout("encode_fh %p\n", dentry);
+		fh->ino = ceph_ino(dentry->d_inode);
+		*max_len = sizeof(*fh);
+		type = 1;
+	} else {
+		return -ENOSPC;
+	}
+	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)
+{
+	struct inode *inode;
+	struct dentry *dentry;
+	struct ceph_vino vino;
+	int err;
+
+	dout("__fh_to_dentry %llx\n", fh->ino);
+	vino.ino = fh->ino;
+	vino.snap = CEPH_NOSNAP;
+	inode = ceph_find_inode(sb, vino);
+	if (!inode)
+		return ERR_PTR(-ESTALE);
+
+	dentry = d_obtain_alias(inode);
+	if (!dentry) {
+		pr_err("fh_to_dentry %llx -- inode %p but ENOMEM\n",
+		       fh->ino, inode);
+		iput(inode);
+		return ERR_PTR(-ENOMEM);
+	}
+	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)
+{
+	struct ceph_mds_client *mdsc = &ceph_client(sb)->mdsc;
+	struct inode *inode;
+	struct dentry *dentry;
+	struct ceph_vino vino;
+	int err;
+
+	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_PTR(PTR_ERR(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);
+		ceph_mdsc_put_request(req);
+		inode = ceph_find_inode(sb, vino);
+		if (!inode)
+			return ERR_PTR(err ? err : -ESTALE);
+	}
+
+	dentry = d_obtain_alias(inode);
+	if (!dentry) {
+		pr_err("cfh_to_dentry %llx -- inode %p but ENOMEM\n",
+		       cfh->ino, inode);
+		iput(inode);
+		return ERR_PTR(-ENOMEM);
+	}
+	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);
+	else
+		return __cfh_to_dentry(sb, (struct ceph_nfs_confh *)fid->raw);
+}
+
+/*
+ * 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);
+
+	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 (!dentry) {
+		pr_err("fh_to_parent %llx -- inode %p but ENOMEM\n",
+		       cfh->ino, inode);
+		iput(inode);
+		return ERR_PTR(-ENOMEM);
+	}
+	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 +1,937 @@
+#include "ceph_debug.h"
+
+#include <linux/sched.h>
+#include <linux/file.h>
+#include <linux/namei.h>
+#include <linux/writeback.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_client *client = ceph_sb_to_client(sb);
+	struct ceph_mds_client *mdsc = &client->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);
+	req->r_args.open.preferred = cpu_to_le32(-1);
+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 the filp already has private_data, that means the file was
+ * already opened by intent during lookup, and we do nothing.
+ *
+ * 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_client *client = ceph_sb_to_client(inode->i_sb);
+	struct ceph_mds_client *mdsc = &client->mdsc;
+	struct ceph_mds_request *req;
+	struct ceph_file_info *cf = file->private_data;
+	struct inode *parent_inode = file->f_dentry->d_parent->d_inode;
+	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(&inode->i_lock);
+		__ceph_get_fmode(ci, fmode);
+		spin_unlock(&inode->i_lock);
+		return ceph_init_file(inode, file, fmode);
+	}
+
+	/*
+	 * No need to block if we have any caps.  Update wanted set
+	 * asynchronously.
+	 */
+	spin_lock(&inode->i_lock);
+	if (__ceph_is_any_real_caps(ci)) {
+		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(&inode->i_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(&inode->i_lock);
+		return ceph_init_file(inode, file, fmode);
+	}
+	spin_unlock(&inode->i_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 = igrab(inode);
+	req->r_num_caps = 1;
+	err = ceph_mdsc_do_request(mdsc, parent_inode, req);
+	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 this succeeds, but some subsequent check in the vfs
+ * may_open() fails, the struct *file gets cleaned up (i.e.
+ * ceph_release gets called).  So fear not!
+ */
+/*
+ * flags
+ *  path_lookup_open   -> LOOKUP_OPEN
+ *  path_lookup_create -> LOOKUP_OPEN|LOOKUP_CREATE
+ */
+struct dentry *ceph_lookup_open(struct inode *dir, struct dentry *dentry,
+				struct nameidata *nd, int mode,
+				int locked_dir)
+{
+	struct ceph_client *client = ceph_sb_to_client(dir->i_sb);
+	struct ceph_mds_client *mdsc = &client->mdsc;
+	struct file *file = nd->intent.open.file;
+	struct inode *parent_inode = get_dentry_parent_inode(file->f_dentry);
+	struct ceph_mds_request *req;
+	int err;
+	int flags = nd->intent.open.flags - 1;  /* silly vfs! */
+
+	dout("ceph_lookup_open dentry %p '%.*s' flags %d mode 0%o\n",
+	     dentry, dentry->d_name.len, dentry->d_name.name, flags, mode);
+
+	/* do the open */
+	req = prepare_open_request(dir->i_sb, flags, mode);
+	if (IS_ERR(req))
+		return ERR_PTR(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, parent_inode, req);
+	dentry = ceph_finish_lookup(req, dentry, err);
+	if (!err && (flags & O_CREAT) && !req->r_reply_info.head->is_dentry)
+		err = ceph_handle_notrace_create(dir, dentry);
+	if (!err)
+		err = ceph_init_file(req->r_dentry->d_inode, file,
+				     req->r_fmode);
+	ceph_mdsc_put_request(req);
+	dout("ceph_lookup_open result=%p\n", dentry);
+	return dentry;
+}
+
+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(&ci->i_cap_wq);
+	return 0;
+}
+
+/*
+ * build a vector of user pages
+ */
+static struct page **get_direct_page_vector(const char __user *data,
+					    int num_pages,
+					    loff_t off, size_t len)
+{
+	struct page **pages;
+	int rc;
+
+	pages = kmalloc(sizeof(*pages) * num_pages, GFP_NOFS);
+	if (!pages)
+		return ERR_PTR(-ENOMEM);
+
+	down_read(&current->mm->mmap_sem);
+	rc = get_user_pages(current, current->mm, (unsigned long)data,
+			    num_pages, 0, 0, pages, NULL);
+	up_read(&current->mm->mmap_sem);
+	if (rc < 0)
+		goto fail;
+	return pages;
+
+fail:
+	kfree(pages);
+	return ERR_PTR(rc);
+}
+
+static void put_page_vector(struct page **pages, int num_pages)
+{
+	int i;
+
+	for (i = 0; i < num_pages; i++)
+		put_page(pages[i]);
+	kfree(pages);
+}
+
+void ceph_release_page_vector(struct page **pages, int num_pages)
+{
+	int i;
+
+	for (i = 0; i < num_pages; i++)
+		__free_pages(pages[i], 0);
+	kfree(pages);
+}
+
+/*
+ * allocate a vector new pages
+ */
+static struct page **alloc_page_vector(int num_pages)
+{
+	struct page **pages;
+	int i;
+
+	pages = kmalloc(sizeof(*pages) * num_pages, GFP_NOFS);
+	if (!pages)
+		return ERR_PTR(-ENOMEM);
+	for (i = 0; i < num_pages; i++) {
+		pages[i] = alloc_page(GFP_NOFS);
+		if (pages[i] == NULL) {
+			ceph_release_page_vector(pages, i);
+			return ERR_PTR(-ENOMEM);
+		}
+	}
+	return pages;
+}
+
+/*
+ * copy user data into a page vector
+ */
+static int copy_user_to_page_vector(struct page **pages,
+				    const char __user *data,
+				    loff_t off, size_t len)
+{
+	int i = 0;
+	int po = off & ~PAGE_CACHE_MASK;
+	int left = len;
+	int l, bad;
+
+	while (left > 0) {
+		l = min_t(int, PAGE_CACHE_SIZE-po, left);
+		bad = copy_from_user(page_address(pages[i]) + po, data, l);
+		if (bad == l)
+			return -EFAULT;
+		data += l - bad;
+		left -= l - bad;
+		po += l - bad;
+		if (po == PAGE_CACHE_SIZE) {
+			po = 0;
+			i++;
+		}
+	}
+	return len;
+}
+
+/*
+ * copy user data from a page vector into a user pointer
+ */
+static int copy_page_vector_to_user(struct page **pages, char __user *data,
+				    loff_t off, size_t len)
+{
+	int i = 0;
+	int po = off & ~PAGE_CACHE_MASK;
+	int left = len;
+	int l, bad;
+
+	while (left > 0) {
+		l = min_t(int, left, PAGE_CACHE_SIZE-po);
+		bad = copy_to_user(data, page_address(pages[i]) + po, l);
+		if (bad == l)
+			return -EFAULT;
+		data += l - bad;
+		left -= l - bad;
+		if (po) {
+			po += l - bad;
+			if (po == PAGE_CACHE_SIZE)
+				po = 0;
+		}
+		i++;
+	}
+	return len;
+}
+
+/*
+ * Zero an extent within a page vector.  Offset is relative to the
+ * start of the first page.
+ */
+static void zero_page_vector_range(int off, int len, struct page **pages)
+{
+	int i = off >> PAGE_CACHE_SHIFT;
+
+	off &= ~PAGE_CACHE_MASK;
+
+	dout("zero_page_vector_page %u~%u\n", off, len);
+
+	/* leading partial page? */
+	if (off) {
+		int end = min((int)PAGE_CACHE_SIZE, off + len);
+		dout("zeroing %d %p head from %d\n", i, pages[i],
+		     (int)off);
+		zero_user_segment(pages[i], off, end);
+		len -= (end - off);
+		i++;
+	}
+	while (len >= PAGE_CACHE_SIZE) {
+		dout("zeroing %d %p len=%d\n", i, pages[i], len);
+		zero_user_segment(pages[i], 0, PAGE_CACHE_SIZE);
+		len -= PAGE_CACHE_SIZE;
+		i++;
+	}
+	/* trailing partial page? */
+	if (len) {
+		dout("zeroing %d %p tail to %d\n", i, pages[i], (int)len);
+		zero_user_segment(pages[i], 0, len);
+	}
+}
+
+
+/*
+ * 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)
+{
+	struct ceph_client *client = ceph_inode_to_client(inode);
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	u64 pos, this_len;
+	int page_off = off & ~PAGE_CACHE_MASK; /* first byte's offset in page */
+	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;
+
+more:
+	this_len = left;
+	ret = ceph_osdc_readpages(&client->osdc, ceph_vino(inode),
+				  &ci->i_layout, pos, &this_len,
+				  ci->i_truncate_seq,
+				  ci->i_truncate_size,
+				  page_pos, pages_left);
+	hit_stripe = this_len < left;
+	was_short = ret >= 0 && ret < this_len;
+	if (ret == -ENOENT)
+		ret = 0;
+	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 =
+			((pos & ~PAGE_CACHE_MASK) + ret) >> PAGE_CACHE_SHIFT;
+
+		if (read < pos - off) {
+			dout(" zero gap %llu to %llu\n", off + read, pos);
+			zero_page_vector_range(page_off + 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) {
+		/* was original extent fully inside i_size? */
+		if (pos + left <= inode->i_size) {
+			dout("zero tail\n");
+			zero_page_vector_range(page_off + read, len - read,
+					       pages);
+			read = len;
+			goto out;
+		}
+
+		/* check i_size */
+		*checkeof = 1;
+	}
+
+out:
+	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->f_dentry->d_inode;
+	struct page **pages;
+	u64 off = *poff;
+	int num_pages = calc_pages_for(off, len);
+	int 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) {
+		pages = get_direct_page_vector(data, num_pages, off, len);
+
+		/*
+		 * flush any page cache pages in this range.  this
+		 * will make concurrent normal and O_DIRECT io slow,
+		 * but it will at least behave sensibly when they are
+		 * in sequence.
+		 */
+	} else {
+		pages = alloc_page_vector(num_pages);
+	}
+	if (IS_ERR(pages))
+		return PTR_ERR(pages);
+
+	ret = filemap_write_and_wait(inode->i_mapping);
+	if (ret < 0)
+		goto done;
+
+	ret = striped_read(inode, off, len, pages, num_pages, checkeof);
+
+	if (ret >= 0 && (file->f_flags & O_DIRECT) == 0)
+		ret = copy_page_vector_to_user(pages, data, off, ret);
+	if (ret >= 0)
+		*poff = off + ret;
+
+done:
+	if (file->f_flags & O_DIRECT)
+		put_page_vector(pages, num_pages);
+	else
+		ceph_release_page_vector(pages, num_pages);
+	dout("sync_read result %d\n", ret);
+	return ret;
+}
+
+/*
+ * Write commit callback, called if we requested both an ACK and
+ * ONDISK commit reply from the OSD.
+ */
+static void sync_write_commit(struct ceph_osd_request *req,
+			      struct ceph_msg *msg)
+{
+	struct ceph_inode_info *ci = ceph_inode(req->r_inode);
+
+	dout("sync_write_commit %p tid %llu\n", req, req->r_tid);
+	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 *offset)
+{
+	struct inode *inode = file->f_dentry->d_inode;
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct ceph_client *client = ceph_inode_to_client(inode);
+	struct ceph_osd_request *req;
+	struct page **pages;
+	int num_pages;
+	long long unsigned pos;
+	u64 len;
+	int written = 0;
+	int flags;
+	int do_sync = 0;
+	int check_caps = 0;
+	int ret;
+	struct timespec mtime = CURRENT_TIME;
+
+	if (ceph_snap(file->f_dentry->d_inode) != CEPH_NOSNAP)
+		return -EROFS;
+
+	dout("sync_write on file %p %lld~%u %s\n", file, *offset,
+	     (unsigned)left, (file->f_flags & O_DIRECT) ? "O_DIRECT" : "");
+
+	if (file->f_flags & O_APPEND)
+		pos = i_size_read(inode);
+	else
+		pos = *offset;
+
+	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
+		do_sync = 1;
+
+	/*
+	 * we may need to do multiple writes here if we span an object
+	 * boundary.  this isn't atomic, unfortunately.  :(
+	 */
+more:
+	len = left;
+	req = ceph_osdc_new_request(&client->osdc, &ci->i_layout,
+				    ceph_vino(inode), pos, &len,
+				    CEPH_OSD_OP_WRITE, flags,
+				    ci->i_snap_realm->cached_context,
+				    do_sync,
+				    ci->i_truncate_seq, ci->i_truncate_size,
+				    &mtime, false, 2);
+	if (IS_ERR(req))
+		return PTR_ERR(req);
+
+	num_pages = calc_pages_for(pos, len);
+
+	if (file->f_flags & O_DIRECT) {
+		pages = get_direct_page_vector(data, num_pages, pos, len);
+		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);
+	} else {
+		pages = alloc_page_vector(num_pages);
+		if (IS_ERR(pages)) {
+			ret = PTR_ERR(pages);
+			goto out;
+		}
+		ret = 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_safe_callback = sync_write_commit;
+			req->r_own_pages = 1;
+		}
+	}
+	req->r_pages = pages;
+	req->r_num_pages = num_pages;
+	req->r_inode = inode;
+
+	ret = ceph_osdc_start_request(&client->osdc, req, false);
+	if (!ret) {
+		if (req->r_safe_callback) {
+			/*
+			 * Add to inode unsafe list only after we
+			 * start_request so that a tid has been assigned.
+			 */
+			spin_lock(&ci->i_unsafe_lock);
+			list_add(&ci->i_unsafe_writes, &req->r_unsafe_item);
+			spin_unlock(&ci->i_unsafe_lock);
+			ceph_get_cap_refs(ci, CEPH_CAP_FILE_WR);
+		}
+		ret = ceph_osdc_wait_request(&client->osdc, req);
+	}
+
+	if (file->f_flags & O_DIRECT)
+		put_page_vector(pages, num_pages);
+	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;
+		if (left)
+			goto more;
+
+		ret = written;
+		*offset = 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;
+	loff_t *ppos = &iocb->ki_pos;
+	size_t len = iov->iov_len;
+	struct inode *inode = filp->f_dentry->d_inode;
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	void *base = iov->iov_base;
+	ssize_t ret;
+	int 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:
+	__ceph_do_pending_vmtruncate(inode);
+	ret = ceph_get_caps(ci, CEPH_CAP_FILE_RD, CEPH_CAP_FILE_CACHE,
+			    &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) == 0 ||
+	    (iocb->ki_filp->f_flags & O_DIRECT) ||
+	    (inode->i_sb->s_flags & MS_SYNCHRONOUS))
+		/* 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, reading more\n");
+			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 inode *inode = file->f_dentry->d_inode;
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct ceph_osd_client *osdc = &ceph_client(inode->i_sb)->osdc;
+	loff_t endoff = pos + iov->iov_len;
+	int got = 0;
+	int ret, err;
+
+	if (ceph_snap(inode) != CEPH_NOSNAP)
+		return -EROFS;
+
+retry_snap:
+	if (ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL))
+		return -ENOSPC;
+	__ceph_do_pending_vmtruncate(inode);
+	dout("aio_write %p %llx.%llx %llu~%u getting caps. i_size %llu\n",
+	     inode, ceph_vinop(inode), pos, (unsigned)iov->iov_len,
+	     inode->i_size);
+	ret = ceph_get_caps(ci, CEPH_CAP_FILE_WR, CEPH_CAP_FILE_BUFFER,
+			    &got, endoff);
+	if (ret < 0)
+		goto out;
+
+	dout("aio_write %p %llx.%llx %llu~%u  got cap refs on %s\n",
+	     inode, ceph_vinop(inode), pos, (unsigned)iov->iov_len,
+	     ceph_cap_string(got));
+
+	if ((got & CEPH_CAP_FILE_BUFFER) == 0 ||
+	    (iocb->ki_filp->f_flags & O_DIRECT) ||
+	    (inode->i_sb->s_flags & MS_SYNCHRONOUS)) {
+		ret = ceph_sync_write(file, iov->iov_base, iov->iov_len,
+			&iocb->ki_pos);
+	} else {
+		ret = generic_file_aio_write(iocb, iov, nr_segs, pos);
+
+		if ((ret >= 0 || ret == -EIOCBQUEUED) &&
+		    ((file->f_flags & O_SYNC) || IS_SYNC(file->f_mapping->host)
+		     || ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_NEARFULL))) {
+			err = vfs_fsync_range(file, file->f_path.dentry,
+					      pos, pos + ret - 1, 1);
+			if (err < 0)
+				ret = err;
+		}
+	}
+	if (ret >= 0) {
+		spin_lock(&inode->i_lock);
+		__ceph_mark_dirty_caps(ci, CEPH_CAP_FILE_WR);
+		spin_unlock(&inode->i_lock);
+	}
+
+out:
+	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 (ret == -EOLDSNAPC) {
+		dout("aio_write %p %llx.%llx %llu~%u got EOLDSNAPC, retrying\n",
+		     inode, ceph_vinop(inode), pos, (unsigned)iov->iov_len);
+		goto retry_snap;
+	}
+
+	return ret;
+}
+
+/*
+ * llseek.  be sure to verify file size on SEEK_END.
+ */
+static loff_t ceph_llseek(struct file *file, loff_t offset, int origin)
+{
+	struct inode *inode = file->f_mapping->host;
+	int ret;
+
+	mutex_lock(&inode->i_mutex);
+	__ceph_do_pending_vmtruncate(inode);
+	switch (origin) {
+	case SEEK_END:
+		ret = ceph_do_getattr(inode, CEPH_STAT_CAP_SIZE);
+		if (ret < 0) {
+			offset = ret;
+			goto out;
+		}
+		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;
+	}
+
+	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,
+	.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 +1,160 @@
+#include <linux/in.h>
+
+#include "ioctl.h"
+#include "super.h"
+#include "ceph_debug.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->f_dentry->d_inode);
+	struct ceph_ioctl_layout l;
+	int err;
+
+	err = ceph_do_getattr(file->f_dentry->d_inode, 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)le32_to_cpu(ci->i_layout.fl_pg_preferred);
+		if (copy_to_user(arg, &l, sizeof(l)))
+			return -EFAULT;
+	}
+
+	return err;
+}
+
+static long ceph_ioctl_set_layout(struct file *file, void __user *arg)
+{
+	struct inode *inode = file->f_dentry->d_inode;
+	struct inode *parent_inode = file->f_dentry->d_parent->d_inode;
+	struct ceph_mds_client *mdsc = &ceph_sb_to_client(inode->i_sb)->mdsc;
+	struct ceph_mds_request *req;
+	struct ceph_ioctl_layout l;
+	int err, i;
+
+	/* copy and validate */
+	if (copy_from_user(&l, arg, sizeof(l)))
+		return -EFAULT;
+
+	if ((l.object_size & ~PAGE_MASK) ||
+	    (l.stripe_unit & ~PAGE_MASK) ||
+	    !l.stripe_unit ||
+	    (l.object_size &&
+	     (unsigned)l.object_size % (unsigned)l.stripe_unit))
+		return -EINVAL;
+
+	/* make sure it's a valid data pool */
+	if (l.data_pool > 0) {
+		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;
+	}
+
+	req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_SETLAYOUT,
+				       USE_AUTH_MDS);
+	if (IS_ERR(req))
+		return PTR_ERR(req);
+	req->r_inode = igrab(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);
+	req->r_args.setlayout.layout.fl_pg_preferred =
+		cpu_to_le32(l.preferred_osd);
+
+	err = ceph_mdsc_do_request(mdsc, parent_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->f_dentry->d_inode;
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct ceph_osd_client *osdc = &ceph_client(inode->i_sb)->osdc;
+	u64 len = 1, olen;
+	u64 tmp;
+	struct ceph_object_layout ol;
+	struct ceph_pg pgid;
+
+	/* copy and validate */
+	if (copy_from_user(&dl, arg, sizeof(dl)))
+		return -EFAULT;
+
+	down_read(&osdc->map_sem);
+	ceph_calc_file_object_mapping(&ci->i_layout, dl.file_offset, &len,
+				      &dl.object_no, &dl.object_offset, &olen);
+	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_object_layout(&ol, dl.object_name, &ci->i_layout,
+				osdc->osdmap);
+
+	pgid = ol.ol_pgid;
+	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;
+}
+
+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_GET_DATALOC:
+		return ceph_ioctl_get_dataloc(file, (void __user *)arg);
+	}
+	return -ENOTTY;
+}

fs/ceph/ioctl.h

@@ -0,0 +1,40 @@
+#ifndef FS_CEPH_IOCTL_H
+#define FS_CEPH_IOCTL_H
+
+#include <linux/ioctl.h>
+#include <linux/types.h>
+
+#define CEPH_IOCTL_MAGIC 0x97
+
+/* just use u64 to align sanely on all archs */
+struct ceph_ioctl_layout {
+	__u64 stripe_unit, stripe_count, object_size;
+	__u64 data_pool;
+	__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)
+
+/*
+ * 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)
+
+#endif

fs/ceph/mds_client.h

@@ -0,0 +1,335 @@
+#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 "types.h"
+#include "messenger.h"
+#include "mdsmap.h"
+
+/*
+ * Some lock dependencies:
+ *
+ * session->s_mutex
+ *         mdsc->mutex
+ *
+ *         mdsc->snap_rwsem
+ *
+ *         inode->i_lock
+ *                 mdsc->snap_flush_lock
+ *                 mdsc->cap_delay_lock
+ *
+ */
+
+struct ceph_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;
+	u32 symlink_len;
+	char *symlink;
+	u32 xattr_len;
+	char *xattr_data;
+};
+
+/*
+ * parsed info about an mds reply, including information about the
+ * target inode and/or its parent directory and dentry, and directory
+ * contents (for readdir results).
+ */
+struct ceph_mds_reply_info_parsed {
+	struct ceph_mds_reply_head    *head;
+
+	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;
+
+	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;
+
+	/* 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_authorizer *s_authorizer;
+	void             *s_authorizer_buf, *s_authorizer_reply_buf;
+	size_t            s_authorizer_buf_len, s_authorizer_reply_buf_len;
+
+	/* protected by s_cap_lock */
+	spinlock_t        s_cap_lock;
+	u32               s_cap_gen;  /* inc each time we get mds stale msg */
+	unsigned long     s_cap_ttl;  /* when session caps expire */
+	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;
+
+	int r_op;                    /* mds op code */
+	int r_mds;
+
+	/* operation on what? */
+	struct inode *r_inode;              /* arg1 */
+	struct dentry *r_dentry;            /* arg1 */
+	struct dentry *r_old_dentry;        /* arg2: rename from or link from */
+	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 */
+
+	union ceph_mds_request_args r_args;
+	int r_fmode;        /* file mode, if expecting cap */
+
+	/* 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 */
+	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_num_stale;
+	int               r_resend_mds; /* mds to resend to next, if any*/
+
+	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;
+
+	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_client      *client;
+	struct mutex            mutex;         /* all nested structures */
+
+	struct ceph_mdsmap      *mdsmap;
+	struct completion       safe_umount_waiters, session_close_waiters;
+	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 */
+	int               num_cap_flushing; /* # caps we are flushing */
+	spinlock_t        cap_dirty_lock;   /* protects above items */
+	wait_queue_head_t cap_flushing_wq;
+
+#ifdef CONFIG_DEBUG_FS
+	struct dentry 	  *debugfs_file;
+#endif
+
+	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_mds_client *mdsc,
+			   struct ceph_client *client);
+extern void ceph_mdsc_close_sessions(struct ceph_mds_client *mdsc);
+extern void ceph_mdsc_stop(struct ceph_mds_client *mdsc);
+
+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, int mask);
+
+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 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);
+
+#endif

fs/ceph/mdsmap.c

@@ -0,0 +1,174 @@
+#include "ceph_debug.h"
+
+#include <linux/bug.h>
+#include <linux/err.h>
+#include <linux/random.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+
+#include "mdsmap.h"
+#include "messenger.h"
+#include "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;
+	char r;
+
+	/* count */
+	for (i = 0; i < m->m_max_mds; i++)
+		if (m->m_info[i].state > 0)
+			n++;
+	if (n == 0)
+		return -1;
+
+	/* pick */
+	get_random_bytes(&r, 1);
+	n = r % 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);
+
+	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;
+
+		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);
+		*p += sizeof(struct ceph_timespec);
+		*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, 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].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(u32), GFP_NOFS);
+	if (!m->m_data_pg_pools)
+		goto badmem;
+	ceph_decode_need(p, end, sizeof(u32)*(n+1), bad);
+	for (i = 0; i < n; i++)
+		m->m_data_pg_pools[i] = ceph_decode_32(p);
+	m->m_cas_pg_pool = ceph_decode_32(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/mdsmap.h

@@ -0,0 +1,54 @@
+#ifndef _FS_CEPH_MDSMAP_H
+#define _FS_CEPH_MDSMAP_H
+
+#include "types.h"
+
+/*
+ * mds map - describe servers in the mds cluster.
+ *
+ * we limit fields to those the client actually xcares about
+ */
+struct ceph_mds_info {
+	u64 global_id;
+	struct ceph_entity_addr addr;
+	s32 state;
+	int num_export_targets;
+	u32 *export_targets;
+};
+
+struct ceph_mdsmap {
+	u32 m_epoch, m_client_epoch, m_last_failure;
+	u32 m_root;
+	u32 m_session_timeout;          /* seconds */
+	u32 m_session_autoclose;        /* seconds */
+	u64 m_max_file_size;
+	u32 m_max_mds;                  /* size of m_addr, m_state arrays */
+	struct ceph_mds_info *m_info;
+
+	/* which object pools file data can be stored in */
+	int m_num_data_pg_pools;
+	u32 *m_data_pg_pools;
+	u32 m_cas_pg_pool;
+};
+
+static inline struct ceph_entity_addr *
+ceph_mdsmap_get_addr(struct ceph_mdsmap *m, int w)
+{
+	if (w >= m->m_max_mds)
+		return NULL;
+	return &m->m_info[w].addr;
+}
+
+static inline int ceph_mdsmap_get_state(struct ceph_mdsmap *m, int w)
+{
+	BUG_ON(w < 0);
+	if (w >= m->m_max_mds)
+		return CEPH_MDS_STATE_DNE;
+	return m->m_info[w].state;
+}
+
+extern int ceph_mdsmap_get_random_mds(struct ceph_mdsmap *m);
+extern struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end);
+extern void ceph_mdsmap_destroy(struct ceph_mdsmap *m);
+
+#endif

fs/ceph/messenger.h

@@ -0,0 +1,254 @@
+#ifndef __FS_CEPH_MESSENGER_H
+#define __FS_CEPH_MESSENGER_H
+
+#include <linux/kref.h>
+#include <linux/mutex.h>
+#include <linux/net.h>
+#include <linux/radix-tree.h>
+#include <linux/uio.h>
+#include <linux/version.h>
+#include <linux/workqueue.h>
+
+#include "types.h"
+#include "buffer.h"
+
+struct ceph_msg;
+struct ceph_connection;
+
+extern struct workqueue_struct *ceph_msgr_wq;       /* receive work queue */
+
+/*
+ * Ceph defines these callbacks for handling connection events.
+ */
+struct ceph_connection_operations {
+	struct ceph_connection *(*get)(struct ceph_connection *);
+	void (*put)(struct ceph_connection *);
+
+	/* handle an incoming message. */
+	void (*dispatch) (struct ceph_connection *con, struct ceph_msg *m);
+
+	/* authorize an outgoing connection */
+	int (*get_authorizer) (struct ceph_connection *con,
+			       void **buf, int *len, int *proto,
+			       void **reply_buf, int *reply_len, int force_new);
+	int (*verify_authorizer_reply) (struct ceph_connection *con, int len);
+	int (*invalidate_authorizer)(struct ceph_connection *con);
+
+	/* protocol version mismatch */
+	void (*bad_proto) (struct ceph_connection *con);
+
+	/* there was some error on the socket (disconnect, whatever) */
+	void (*fault) (struct ceph_connection *con);
+
+	/* a remote host as terminated a message exchange session, and messages
+	 * we sent (or they tried to send us) may be lost. */
+	void (*peer_reset) (struct ceph_connection *con);
+
+	struct ceph_msg * (*alloc_msg) (struct ceph_connection *con,
+					struct ceph_msg_header *hdr,
+					int *skip);
+};
+
+extern const char *ceph_name_type_str(int t);
+
+/* use format string %s%d */
+#define ENTITY_NAME(n) ceph_name_type_str((n).type), le64_to_cpu((n).num)
+
+struct ceph_messenger {
+	struct ceph_entity_inst inst;    /* my name+address */
+	struct ceph_entity_addr my_enc_addr;
+	struct page *zero_page;          /* used in certain error cases */
+
+	bool nocrc;
+
+	/*
+	 * the global_seq counts connections i (attempt to) initiate
+	 * in order to disambiguate certain connect race conditions.
+	 */
+	u32 global_seq;
+	spinlock_t global_seq_lock;
+};
+
+/*
+ * a single message.  it contains a header (src, dest, message type, etc.),
+ * footer (crc values, mainly), a "front" message body, and possibly a
+ * data payload (stored in some number of pages).
+ */
+struct ceph_msg {
+	struct ceph_msg_header hdr;	/* header */
+	struct ceph_msg_footer footer;	/* footer */
+	struct kvec front;              /* unaligned blobs of message */
+	struct ceph_buffer *middle;
+	struct page **pages;            /* data payload.  NOT OWNER. */
+	unsigned nr_pages;              /* size of page array */
+	struct ceph_pagelist *pagelist; /* instead of pages */
+	struct list_head list_head;
+	struct kref kref;
+	bool front_is_vmalloc;
+	bool more_to_follow;
+	int front_max;
+
+	struct ceph_msgpool *pool;
+};
+
+struct ceph_msg_pos {
+	int page, page_pos;  /* which page; offset in page */
+	int data_pos;        /* offset in data payload */
+	int did_page_crc;    /* true if we've calculated crc for current page */
+};
+
+/* ceph connection fault delay defaults, for exponential backoff */
+#define BASE_DELAY_INTERVAL	(HZ/2)
+#define MAX_DELAY_INTERVAL	(5 * 60 * HZ)
+
+/*
+ * ceph_connection state bit flags
+ *
+ * QUEUED and BUSY are used together to ensure that only a single
+ * thread is currently opening, reading or writing data to the socket.
+ */
+#define LOSSYTX         0  /* we can close channel or drop messages on errors */
+#define CONNECTING	1
+#define NEGOTIATING	2
+#define KEEPALIVE_PENDING      3
+#define WRITE_PENDING	4  /* we have data ready to send */
+#define QUEUED          5  /* there is work queued on this connection */
+#define BUSY            6  /* work is being done */
+#define STANDBY		8  /* no outgoing messages, socket closed.  we keep
+			    * the ceph_connection around to maintain shared
+			    * state with the peer. */
+#define CLOSED		10 /* we've closed the connection */
+#define SOCK_CLOSED	11 /* socket state changed to closed */
+#define OPENING         13 /* open connection w/ (possibly new) peer */
+#define DEAD            14 /* dead, about to kfree */
+
+/*
+ * A single connection with another host.
+ *
+ * We maintain a queue of outgoing messages, and some session state to
+ * ensure that we can preserve the lossless, ordered delivery of
+ * messages in the case of a TCP disconnect.
+ */
+struct ceph_connection {
+	void *private;
+	atomic_t nref;
+
+	const struct ceph_connection_operations *ops;
+
+	struct ceph_messenger *msgr;
+	struct socket *sock;
+	unsigned long state;	/* connection state (see flags above) */
+	const char *error_msg;  /* error message, if any */
+
+	struct ceph_entity_addr peer_addr; /* peer address */
+	struct ceph_entity_name peer_name; /* peer name */
+	struct ceph_entity_addr peer_addr_for_me;
+	u32 connect_seq;      /* identify the most recent connection
+				 attempt for this connection, client */
+	u32 peer_global_seq;  /* peer's global seq for this connection */
+
+	int auth_retry;       /* true if we need a newer authorizer */
+	void *auth_reply_buf;   /* where to put the authorizer reply */
+	int auth_reply_buf_len;
+
+	struct mutex mutex;
+
+	/* out queue */
+	struct list_head out_queue;
+	struct list_head out_sent;   /* sending or sent but unacked */
+	u64 out_seq;		     /* last message queued for send */
+	u64 out_seq_sent;            /* last message sent */
+	bool out_keepalive_pending;
+
+	u64 in_seq, in_seq_acked;  /* last message received, acked */
+
+	/* connection negotiation temps */
+	char in_banner[CEPH_BANNER_MAX_LEN];
+	union {
+		struct {  /* outgoing connection */
+			struct ceph_msg_connect out_connect;
+			struct ceph_msg_connect_reply in_reply;
+		};
+		struct {  /* incoming */
+			struct ceph_msg_connect in_connect;
+			struct ceph_msg_connect_reply out_reply;
+		};
+	};
+	struct ceph_entity_addr actual_peer_addr;
+
+	/* message out temps */
+	struct ceph_msg *out_msg;        /* sending message (== tail of
+					    out_sent) */
+	bool out_msg_done;
+	struct ceph_msg_pos out_msg_pos;
+
+	struct kvec out_kvec[8],         /* sending header/footer data */
+		*out_kvec_cur;
+	int out_kvec_left;   /* kvec's left in out_kvec */
+	int out_skip;        /* skip this many bytes */
+	int out_kvec_bytes;  /* total bytes left */
+	bool out_kvec_is_msg; /* kvec refers to out_msg */
+	int out_more;        /* there is more data after the kvecs */
+	__le64 out_temp_ack; /* for writing an ack */
+
+	/* message in temps */
+	struct ceph_msg_header in_hdr;
+	struct ceph_msg *in_msg;
+	struct ceph_msg_pos in_msg_pos;
+	u32 in_front_crc, in_middle_crc, in_data_crc;  /* calculated crc */
+
+	char in_tag;         /* protocol control byte */
+	int in_base_pos;     /* bytes read */
+	__le64 in_temp_ack;  /* for reading an ack */
+
+	struct delayed_work work;	    /* send|recv work */
+	unsigned long       delay;          /* current delay interval */
+};
+
+
+extern const char *pr_addr(const struct sockaddr_storage *ss);
+extern int ceph_parse_ips(const char *c, const char *end,
+			  struct ceph_entity_addr *addr,
+			  int max_count, int *count);
+
+
+extern int ceph_msgr_init(void);
+extern void ceph_msgr_exit(void);
+
+extern struct ceph_messenger *ceph_messenger_create(
+	struct ceph_entity_addr *myaddr);
+extern void ceph_messenger_destroy(struct ceph_messenger *);
+
+extern void ceph_con_init(struct ceph_messenger *msgr,
+			  struct ceph_connection *con);
+extern void ceph_con_open(struct ceph_connection *con,
+			  struct ceph_entity_addr *addr);
+extern void ceph_con_close(struct ceph_connection *con);
+extern void ceph_con_send(struct ceph_connection *con, struct ceph_msg *msg);
+extern void ceph_con_revoke(struct ceph_connection *con, struct ceph_msg *msg);
+extern void ceph_con_revoke_message(struct ceph_connection *con,
+				  struct ceph_msg *msg);
+extern void ceph_con_keepalive(struct ceph_connection *con);
+extern struct ceph_connection *ceph_con_get(struct ceph_connection *con);
+extern void ceph_con_put(struct ceph_connection *con);
+
+extern struct ceph_msg *ceph_msg_new(int type, int front_len,
+				     int page_len, int page_off,
+				     struct page **pages);
+extern void ceph_msg_kfree(struct ceph_msg *m);
+
+
+static inline struct ceph_msg *ceph_msg_get(struct ceph_msg *msg)
+{
+	kref_get(&msg->kref);
+	return msg;
+}
+extern void ceph_msg_last_put(struct kref *kref);
+static inline void ceph_msg_put(struct ceph_msg *msg)
+{
+	kref_put(&msg->kref, ceph_msg_last_put);
+}
+
+extern void ceph_msg_dump(struct ceph_msg *msg);
+
+#endif

fs/ceph/mon_client.c

@@ -0,0 +1,834 @@
+#include "ceph_debug.h"
+
+#include <linux/types.h>
+#include <linux/random.h>
+#include <linux/sched.h>
+
+#include "mon_client.h"
+#include "super.h"
+#include "auth.h"
+#include "decode.h"
+
+/*
+ * Interact with Ceph monitor cluster.  Handle requests for new map
+ * versions, and periodically resend as needed.  Also implement
+ * statfs() and umount().
+ *
+ * A small cluster of Ceph "monitors" are responsible for managing critical
+ * cluster configuration and state information.  An odd number (e.g., 3, 5)
+ * of cmon daemons use a modified version of the Paxos part-time parliament
+ * algorithm to manage the MDS map (mds cluster membership), OSD map, and
+ * list of clients who have mounted the file system.
+ *
+ * We maintain an open, active session with a monitor at all times in order to
+ * receive timely MDSMap updates.  We periodically send a keepalive byte on the
+ * TCP socket to ensure we detect a failure.  If the connection does break, we
+ * randomly hunt for a new monitor.  Once the connection is reestablished, we
+ * resend any outstanding requests.
+ */
+
+const static struct ceph_connection_operations mon_con_ops;
+
+static int __validate_auth(struct ceph_mon_client *monc);
+
+/*
+ * Decode a monmap blob (e.g., during mount).
+ */
+struct ceph_monmap *ceph_monmap_decode(void *p, void *end)
+{
+	struct ceph_monmap *m = NULL;
+	int i, err = -EINVAL;
+	struct ceph_fsid fsid;
+	u32 epoch, num_mon;
+	u16 version;
+	u32 len;
+
+	ceph_decode_32_safe(&p, end, len, bad);
+	ceph_decode_need(&p, end, len, bad);
+
+	dout("monmap_decode %p %p len %d\n", p, end, (int)(end-p));
+
+	ceph_decode_16_safe(&p, end, version, bad);
+
+	ceph_decode_need(&p, end, sizeof(fsid) + 2*sizeof(u32), bad);
+	ceph_decode_copy(&p, &fsid, sizeof(fsid));
+	epoch = ceph_decode_32(&p);
+
+	num_mon = ceph_decode_32(&p);
+	ceph_decode_need(&p, end, num_mon*sizeof(m->mon_inst[0]), bad);
+
+	if (num_mon >= CEPH_MAX_MON)
+		goto bad;
+	m = kmalloc(sizeof(*m) + sizeof(m->mon_inst[0])*num_mon, GFP_NOFS);
+	if (m == NULL)
+		return ERR_PTR(-ENOMEM);
+	m->fsid = fsid;
+	m->epoch = epoch;
+	m->num_mon = num_mon;
+	ceph_decode_copy(&p, m->mon_inst, num_mon*sizeof(m->mon_inst[0]));
+	for (i = 0; i < num_mon; i++)
+		ceph_decode_addr(&m->mon_inst[i].addr);
+
+	dout("monmap_decode epoch %d, num_mon %d\n", m->epoch,
+	     m->num_mon);
+	for (i = 0; i < m->num_mon; i++)
+		dout("monmap_decode  mon%d is %s\n", i,
+		     pr_addr(&m->mon_inst[i].addr.in_addr));
+	return m;
+
+bad:
+	dout("monmap_decode failed with %d\n", err);
+	kfree(m);
+	return ERR_PTR(err);
+}
+
+/*
+ * return true if *addr is included in the monmap.
+ */
+int ceph_monmap_contains(struct ceph_monmap *m, struct ceph_entity_addr *addr)
+{
+	int i;
+
+	for (i = 0; i < m->num_mon; i++)
+		if (memcmp(addr, &m->mon_inst[i].addr, sizeof(*addr)) == 0)
+			return 1;
+	return 0;
+}
+
+/*
+ * Send an auth request.
+ */
+static void __send_prepared_auth_request(struct ceph_mon_client *monc, int len)
+{
+	monc->pending_auth = 1;
+	monc->m_auth->front.iov_len = len;
+	monc->m_auth->hdr.front_len = cpu_to_le32(len);
+	ceph_msg_get(monc->m_auth);  /* keep our ref */
+	ceph_con_send(monc->con, monc->m_auth);
+}
+
+/*
+ * Close monitor session, if any.
+ */
+static void __close_session(struct ceph_mon_client *monc)
+{
+	if (monc->con) {
+		dout("__close_session closing mon%d\n", monc->cur_mon);
+		ceph_con_revoke(monc->con, monc->m_auth);
+		ceph_con_close(monc->con);
+		monc->cur_mon = -1;
+		monc->pending_auth = 0;
+		ceph_auth_reset(monc->auth);
+	}
+}
+
+/*
+ * Open a session with a (new) monitor.
+ */
+static int __open_session(struct ceph_mon_client *monc)
+{
+	char r;
+	int ret;
+
+	if (monc->cur_mon < 0) {
+		get_random_bytes(&r, 1);
+		monc->cur_mon = r % monc->monmap->num_mon;
+		dout("open_session num=%d r=%d -> mon%d\n",
+		     monc->monmap->num_mon, r, monc->cur_mon);
+		monc->sub_sent = 0;
+		monc->sub_renew_after = jiffies;  /* i.e., expired */
+		monc->want_next_osdmap = !!monc->want_next_osdmap;
+
+		dout("open_session mon%d opening\n", monc->cur_mon);
+		monc->con->peer_name.type = CEPH_ENTITY_TYPE_MON;
+		monc->con->peer_name.num = cpu_to_le64(monc->cur_mon);
+		ceph_con_open(monc->con,
+			      &monc->monmap->mon_inst[monc->cur_mon].addr);
+
+		/* initiatiate authentication handshake */
+		ret = ceph_auth_build_hello(monc->auth,
+					    monc->m_auth->front.iov_base,
+					    monc->m_auth->front_max);
+		__send_prepared_auth_request(monc, ret);
+	} else {
+		dout("open_session mon%d already open\n", monc->cur_mon);
+	}
+	return 0;
+}
+
+static bool __sub_expired(struct ceph_mon_client *monc)
+{
+	return time_after_eq(jiffies, monc->sub_renew_after);
+}
+
+/*
+ * Reschedule delayed work timer.
+ */
+static void __schedule_delayed(struct ceph_mon_client *monc)
+{
+	unsigned delay;
+
+	if (monc->cur_mon < 0 || __sub_expired(monc))
+		delay = 10 * HZ;
+	else
+		delay = 20 * HZ;
+	dout("__schedule_delayed after %u\n", delay);
+	schedule_delayed_work(&monc->delayed_work, delay);
+}
+
+/*
+ * Send subscribe request for mdsmap and/or osdmap.
+ */
+static void __send_subscribe(struct ceph_mon_client *monc)
+{
+	dout("__send_subscribe sub_sent=%u exp=%u want_osd=%d\n",
+	     (unsigned)monc->sub_sent, __sub_expired(monc),
+	     monc->want_next_osdmap);
+	if ((__sub_expired(monc) && !monc->sub_sent) ||
+	    monc->want_next_osdmap == 1) {
+		struct ceph_msg *msg;
+		struct ceph_mon_subscribe_item *i;
+		void *p, *end;
+
+		msg = ceph_msg_new(CEPH_MSG_MON_SUBSCRIBE, 96, 0, 0, NULL);
+		if (!msg)
+			return;
+
+		p = msg->front.iov_base;
+		end = p + msg->front.iov_len;
+
+		dout("__send_subscribe to 'mdsmap' %u+\n",
+		     (unsigned)monc->have_mdsmap);
+		if (monc->want_next_osdmap) {
+			dout("__send_subscribe to 'osdmap' %u\n",
+			     (unsigned)monc->have_osdmap);
+			ceph_encode_32(&p, 3);
+			ceph_encode_string(&p, end, "osdmap", 6);
+			i = p;
+			i->have = cpu_to_le64(monc->have_osdmap);
+			i->onetime = 1;
+			p += sizeof(*i);
+			monc->want_next_osdmap = 2;  /* requested */
+		} else {
+			ceph_encode_32(&p, 2);
+		}
+		ceph_encode_string(&p, end, "mdsmap", 6);
+		i = p;
+		i->have = cpu_to_le64(monc->have_mdsmap);
+		i->onetime = 0;
+		p += sizeof(*i);
+		ceph_encode_string(&p, end, "monmap", 6);
+		i = p;
+		i->have = 0;
+		i->onetime = 0;
+		p += sizeof(*i);
+
+		msg->front.iov_len = p - msg->front.iov_base;
+		msg->hdr.front_len = cpu_to_le32(msg->front.iov_len);
+		ceph_con_send(monc->con, msg);
+
+		monc->sub_sent = jiffies | 1;  /* never 0 */
+	}
+}
+
+static void handle_subscribe_ack(struct ceph_mon_client *monc,
+				 struct ceph_msg *msg)
+{
+	unsigned seconds;
+	struct ceph_mon_subscribe_ack *h = msg->front.iov_base;
+
+	if (msg->front.iov_len < sizeof(*h))
+		goto bad;
+	seconds = le32_to_cpu(h->duration);
+
+	mutex_lock(&monc->mutex);
+	if (monc->hunting) {
+		pr_info("mon%d %s session established\n",
+			monc->cur_mon, pr_addr(&monc->con->peer_addr.in_addr));
+		monc->hunting = false;
+	}
+	dout("handle_subscribe_ack after %d seconds\n", seconds);
+	monc->sub_renew_after = monc->sub_sent + (seconds >> 1)*HZ - 1;
+	monc->sub_sent = 0;
+	mutex_unlock(&monc->mutex);
+	return;
+bad:
+	pr_err("got corrupt subscribe-ack msg\n");
+	ceph_msg_dump(msg);
+}
+
+/*
+ * Keep track of which maps we have
+ */
+int ceph_monc_got_mdsmap(struct ceph_mon_client *monc, u32 got)
+{
+	mutex_lock(&monc->mutex);
+	monc->have_mdsmap = got;
+	mutex_unlock(&monc->mutex);
+	return 0;
+}
+
+int ceph_monc_got_osdmap(struct ceph_mon_client *monc, u32 got)
+{
+	mutex_lock(&monc->mutex);
+	monc->have_osdmap = got;
+	monc->want_next_osdmap = 0;
+	mutex_unlock(&monc->mutex);
+	return 0;
+}
+
+/*
+ * Register interest in the next osdmap
+ */
+void ceph_monc_request_next_osdmap(struct ceph_mon_client *monc)
+{
+	dout("request_next_osdmap have %u\n", monc->have_osdmap);
+	mutex_lock(&monc->mutex);
+	if (!monc->want_next_osdmap)
+		monc->want_next_osdmap = 1;
+	if (monc->want_next_osdmap < 2)
+		__send_subscribe(monc);
+	mutex_unlock(&monc->mutex);
+}
+
+/*
+ *
+ */
+int ceph_monc_open_session(struct ceph_mon_client *monc)
+{
+	if (!monc->con) {
+		monc->con = kmalloc(sizeof(*monc->con), GFP_KERNEL);
+		if (!monc->con)
+			return -ENOMEM;
+		ceph_con_init(monc->client->msgr, monc->con);
+		monc->con->private = monc;
+		monc->con->ops = &mon_con_ops;
+	}
+
+	mutex_lock(&monc->mutex);
+	__open_session(monc);
+	__schedule_delayed(monc);
+	mutex_unlock(&monc->mutex);
+	return 0;
+}
+
+/*
+ * The monitor responds with mount ack indicate mount success.  The
+ * included client ticket allows the client to talk to MDSs and OSDs.
+ */
+static void ceph_monc_handle_map(struct ceph_mon_client *monc,
+				 struct ceph_msg *msg)
+{
+	struct ceph_client *client = monc->client;
+	struct ceph_monmap *monmap = NULL, *old = monc->monmap;
+	void *p, *end;
+
+	mutex_lock(&monc->mutex);
+
+	dout("handle_monmap\n");
+	p = msg->front.iov_base;
+	end = p + msg->front.iov_len;
+
+	monmap = ceph_monmap_decode(p, end);
+	if (IS_ERR(monmap)) {
+		pr_err("problem decoding monmap, %d\n",
+		       (int)PTR_ERR(monmap));
+		goto out;
+	}
+
+	if (ceph_check_fsid(monc->client, &monmap->fsid) < 0) {
+		kfree(monmap);
+		goto out;
+	}
+
+	client->monc.monmap = monmap;
+	kfree(old);
+
+out:
+	mutex_unlock(&monc->mutex);
+	wake_up(&client->auth_wq);
+}
+
+/*
+ * statfs
+ */
+static struct ceph_mon_statfs_request *__lookup_statfs(
+	struct ceph_mon_client *monc, u64 tid)
+{
+	struct ceph_mon_statfs_request *req;
+	struct rb_node *n = monc->statfs_request_tree.rb_node;
+
+	while (n) {
+		req = rb_entry(n, struct ceph_mon_statfs_request, node);
+		if (tid < req->tid)
+			n = n->rb_left;
+		else if (tid > req->tid)
+			n = n->rb_right;
+		else
+			return req;
+	}
+	return NULL;
+}
+
+static void __insert_statfs(struct ceph_mon_client *monc,
+			    struct ceph_mon_statfs_request *new)
+{
+	struct rb_node **p = &monc->statfs_request_tree.rb_node;
+	struct rb_node *parent = NULL;
+	struct ceph_mon_statfs_request *req = NULL;
+
+	while (*p) {
+		parent = *p;
+		req = rb_entry(parent, struct ceph_mon_statfs_request, node);
+		if (new->tid < req->tid)
+			p = &(*p)->rb_left;
+		else if (new->tid > req->tid)
+			p = &(*p)->rb_right;
+		else
+			BUG();
+	}
+
+	rb_link_node(&new->node, parent, p);
+	rb_insert_color(&new->node, &monc->statfs_request_tree);
+}
+
+static void handle_statfs_reply(struct ceph_mon_client *monc,
+				struct ceph_msg *msg)
+{
+	struct ceph_mon_statfs_request *req;
+	struct ceph_mon_statfs_reply *reply = msg->front.iov_base;
+	u64 tid;
+
+	if (msg->front.iov_len != sizeof(*reply))
+		goto bad;
+	tid = le64_to_cpu(msg->hdr.tid);
+	dout("handle_statfs_reply %p tid %llu\n", msg, tid);
+
+	mutex_lock(&monc->mutex);
+	req = __lookup_statfs(monc, tid);
+	if (req) {
+		*req->buf = reply->st;
+		req->result = 0;
+	}
+	mutex_unlock(&monc->mutex);
+	if (req)
+		complete(&req->completion);
+	return;
+
+bad:
+	pr_err("corrupt statfs reply, no tid\n");
+	ceph_msg_dump(msg);
+}
+
+/*
+ * (re)send a statfs request
+ */
+static int send_statfs(struct ceph_mon_client *monc,
+		       struct ceph_mon_statfs_request *req)
+{
+	struct ceph_msg *msg;
+	struct ceph_mon_statfs *h;
+
+	dout("send_statfs tid %llu\n", req->tid);
+	msg = ceph_msg_new(CEPH_MSG_STATFS, sizeof(*h), 0, 0, NULL);
+	if (IS_ERR(msg))
+		return PTR_ERR(msg);
+	req->request = msg;
+	msg->hdr.tid = cpu_to_le64(req->tid);
+	h = msg->front.iov_base;
+	h->monhdr.have_version = 0;
+	h->monhdr.session_mon = cpu_to_le16(-1);
+	h->monhdr.session_mon_tid = 0;
+	h->fsid = monc->monmap->fsid;
+	ceph_con_send(monc->con, msg);
+	return 0;
+}
+
+/*
+ * Do a synchronous statfs().
+ */
+int ceph_monc_do_statfs(struct ceph_mon_client *monc, struct ceph_statfs *buf)
+{
+	struct ceph_mon_statfs_request req;
+	int err;
+
+	req.buf = buf;
+	init_completion(&req.completion);
+
+	/* allocate memory for reply */
+	err = ceph_msgpool_resv(&monc->msgpool_statfs_reply, 1);
+	if (err)
+		return err;
+
+	/* register request */
+	mutex_lock(&monc->mutex);
+	req.tid = ++monc->last_tid;
+	req.last_attempt = jiffies;
+	req.delay = BASE_DELAY_INTERVAL;
+	__insert_statfs(monc, &req);
+	monc->num_statfs_requests++;
+	mutex_unlock(&monc->mutex);
+
+	/* send request and wait */
+	err = send_statfs(monc, &req);
+	if (!err)
+		err = wait_for_completion_interruptible(&req.completion);
+
+	mutex_lock(&monc->mutex);
+	rb_erase(&req.node, &monc->statfs_request_tree);
+	monc->num_statfs_requests--;
+	ceph_msgpool_resv(&monc->msgpool_statfs_reply, -1);
+	mutex_unlock(&monc->mutex);
+
+	if (!err)
+		err = req.result;
+	return err;
+}
+
+/*
+ * Resend pending statfs requests.
+ */
+static void __resend_statfs(struct ceph_mon_client *monc)
+{
+	struct ceph_mon_statfs_request *req;
+	struct rb_node *p;
+
+	for (p = rb_first(&monc->statfs_request_tree); p; p = rb_next(p)) {
+		req = rb_entry(p, struct ceph_mon_statfs_request, node);
+		send_statfs(monc, req);
+	}
+}
+
+/*
+ * Delayed work.  If we haven't mounted yet, retry.  Otherwise,
+ * renew/retry subscription as needed (in case it is timing out, or we
+ * got an ENOMEM).  And keep the monitor connection alive.
+ */
+static void delayed_work(struct work_struct *work)
+{
+	struct ceph_mon_client *monc =
+		container_of(work, struct ceph_mon_client, delayed_work.work);
+
+	dout("monc delayed_work\n");
+	mutex_lock(&monc->mutex);
+	if (monc->hunting) {
+		__close_session(monc);
+		__open_session(monc);  /* continue hunting */
+	} else {
+		ceph_con_keepalive(monc->con);
+
+		__validate_auth(monc);
+
+		if (monc->auth->ops->is_authenticated(monc->auth))
+			__send_subscribe(monc);
+	}
+	__schedule_delayed(monc);
+	mutex_unlock(&monc->mutex);
+}
+
+/*
+ * On startup, we build a temporary monmap populated with the IPs
+ * provided by mount(2).
+ */
+static int build_initial_monmap(struct ceph_mon_client *monc)
+{
+	struct ceph_mount_args *args = monc->client->mount_args;
+	struct ceph_entity_addr *mon_addr = args->mon_addr;
+	int num_mon = args->num_mon;
+	int i;
+
+	/* build initial monmap */
+	monc->monmap = kzalloc(sizeof(*monc->monmap) +
+			       num_mon*sizeof(monc->monmap->mon_inst[0]),
+			       GFP_KERNEL);
+	if (!monc->monmap)
+		return -ENOMEM;
+	for (i = 0; i < num_mon; i++) {
+		monc->monmap->mon_inst[i].addr = mon_addr[i];
+		monc->monmap->mon_inst[i].addr.nonce = 0;
+		monc->monmap->mon_inst[i].name.type =
+			CEPH_ENTITY_TYPE_MON;
+		monc->monmap->mon_inst[i].name.num = cpu_to_le64(i);
+	}
+	monc->monmap->num_mon = num_mon;
+	monc->have_fsid = false;
+
+	/* release addr memory */
+	kfree(args->mon_addr);
+	args->mon_addr = NULL;
+	args->num_mon = 0;
+	return 0;
+}
+
+int ceph_monc_init(struct ceph_mon_client *monc, struct ceph_client *cl)
+{
+	int err = 0;
+
+	dout("init\n");
+	memset(monc, 0, sizeof(*monc));
+	monc->client = cl;
+	monc->monmap = NULL;
+	mutex_init(&monc->mutex);
+
+	err = build_initial_monmap(monc);
+	if (err)
+		goto out;
+
+	monc->con = NULL;
+
+	/* authentication */
+	monc->auth = ceph_auth_init(cl->mount_args->name,
+				    cl->mount_args->secret);
+	if (IS_ERR(monc->auth))
+		return PTR_ERR(monc->auth);
+	monc->auth->want_keys =
+		CEPH_ENTITY_TYPE_AUTH | CEPH_ENTITY_TYPE_MON |
+		CEPH_ENTITY_TYPE_OSD | CEPH_ENTITY_TYPE_MDS;
+
+	/* msg pools */
+	err = ceph_msgpool_init(&monc->msgpool_subscribe_ack,
+			       sizeof(struct ceph_mon_subscribe_ack), 1, false);
+	if (err < 0)
+		goto out_monmap;
+	err = ceph_msgpool_init(&monc->msgpool_statfs_reply,
+				sizeof(struct ceph_mon_statfs_reply), 0, false);
+	if (err < 0)
+		goto out_pool1;
+	err = ceph_msgpool_init(&monc->msgpool_auth_reply, 4096, 1, false);
+	if (err < 0)
+		goto out_pool2;
+
+	monc->m_auth = ceph_msg_new(CEPH_MSG_AUTH, 4096, 0, 0, NULL);
+	monc->pending_auth = 0;
+	if (IS_ERR(monc->m_auth)) {
+		err = PTR_ERR(monc->m_auth);
+		monc->m_auth = NULL;
+		goto out_pool3;
+	}
+
+	monc->cur_mon = -1;
+	monc->hunting = true;
+	monc->sub_renew_after = jiffies;
+	monc->sub_sent = 0;
+
+	INIT_DELAYED_WORK(&monc->delayed_work, delayed_work);
+	monc->statfs_request_tree = RB_ROOT;
+	monc->num_statfs_requests = 0;
+	monc->last_tid = 0;
+
+	monc->have_mdsmap = 0;
+	monc->have_osdmap = 0;
+	monc->want_next_osdmap = 1;
+	return 0;
+
+out_pool3:
+	ceph_msgpool_destroy(&monc->msgpool_auth_reply);
+out_pool2:
+	ceph_msgpool_destroy(&monc->msgpool_subscribe_ack);
+out_pool1:
+	ceph_msgpool_destroy(&monc->msgpool_statfs_reply);
+out_monmap:
+	kfree(monc->monmap);
+out:
+	return err;
+}
+
+void ceph_monc_stop(struct ceph_mon_client *monc)
+{
+	dout("stop\n");
+	cancel_delayed_work_sync(&monc->delayed_work);
+
+	mutex_lock(&monc->mutex);
+	__close_session(monc);
+	if (monc->con) {
+		monc->con->private = NULL;
+		monc->con->ops->put(monc->con);
+		monc->con = NULL;
+	}
+	mutex_unlock(&monc->mutex);
+
+	ceph_auth_destroy(monc->auth);
+
+	ceph_msg_put(monc->m_auth);
+	ceph_msgpool_destroy(&monc->msgpool_subscribe_ack);
+	ceph_msgpool_destroy(&monc->msgpool_statfs_reply);
+	ceph_msgpool_destroy(&monc->msgpool_auth_reply);
+
+	kfree(monc->monmap);
+}
+
+static void handle_auth_reply(struct ceph_mon_client *monc,
+			      struct ceph_msg *msg)
+{
+	int ret;
+
+	mutex_lock(&monc->mutex);
+	monc->pending_auth = 0;
+	ret = ceph_handle_auth_reply(monc->auth, msg->front.iov_base,
+				     msg->front.iov_len,
+				     monc->m_auth->front.iov_base,
+				     monc->m_auth->front_max);
+	if (ret < 0) {
+		monc->client->auth_err = ret;
+		wake_up(&monc->client->auth_wq);
+	} else if (ret > 0) {
+		__send_prepared_auth_request(monc, ret);
+	} else if (monc->auth->ops->is_authenticated(monc->auth)) {
+		dout("authenticated, starting session\n");
+
+		monc->client->msgr->inst.name.type = CEPH_ENTITY_TYPE_CLIENT;
+		monc->client->msgr->inst.name.num = monc->auth->global_id;
+
+		__send_subscribe(monc);
+		__resend_statfs(monc);
+	}
+	mutex_unlock(&monc->mutex);
+}
+
+static int __validate_auth(struct ceph_mon_client *monc)
+{
+	int ret;
+
+	if (monc->pending_auth)
+		return 0;
+
+	ret = ceph_build_auth(monc->auth, monc->m_auth->front.iov_base,
+			      monc->m_auth->front_max);
+	if (ret <= 0)
+		return ret; /* either an error, or no need to authenticate */
+	__send_prepared_auth_request(monc, ret);
+	return 0;
+}
+
+int ceph_monc_validate_auth(struct ceph_mon_client *monc)
+{
+	int ret;
+
+	mutex_lock(&monc->mutex);
+	ret = __validate_auth(monc);
+	mutex_unlock(&monc->mutex);
+	return ret;
+}
+
+/*
+ * handle incoming message
+ */
+static void dispatch(struct ceph_connection *con, struct ceph_msg *msg)
+{
+	struct ceph_mon_client *monc = con->private;
+	int type = le16_to_cpu(msg->hdr.type);
+
+	if (!monc)
+		return;
+
+	switch (type) {
+	case CEPH_MSG_AUTH_REPLY:
+		handle_auth_reply(monc, msg);
+		break;
+
+	case CEPH_MSG_MON_SUBSCRIBE_ACK:
+		handle_subscribe_ack(monc, msg);
+		break;
+
+	case CEPH_MSG_STATFS_REPLY:
+		handle_statfs_reply(monc, msg);
+		break;
+
+	case CEPH_MSG_MON_MAP:
+		ceph_monc_handle_map(monc, msg);
+		break;
+
+	case CEPH_MSG_MDS_MAP:
+		ceph_mdsc_handle_map(&monc->client->mdsc, msg);
+		break;
+
+	case CEPH_MSG_OSD_MAP:
+		ceph_osdc_handle_map(&monc->client->osdc, msg);
+		break;
+
+	default:
+		pr_err("received unknown message type %d %s\n", type,
+		       ceph_msg_type_name(type));
+	}
+	ceph_msg_put(msg);
+}
+
+/*
+ * Allocate memory for incoming message
+ */
+static struct ceph_msg *mon_alloc_msg(struct ceph_connection *con,
+				      struct ceph_msg_header *hdr,
+				      int *skip)
+{
+	struct ceph_mon_client *monc = con->private;
+	int type = le16_to_cpu(hdr->type);
+	int front_len = le32_to_cpu(hdr->front_len);
+	struct ceph_msg *m = NULL;
+
+	*skip = 0;
+
+	switch (type) {
+	case CEPH_MSG_MON_SUBSCRIBE_ACK:
+		m = ceph_msgpool_get(&monc->msgpool_subscribe_ack, front_len);
+		break;
+	case CEPH_MSG_STATFS_REPLY:
+		m = ceph_msgpool_get(&monc->msgpool_statfs_reply, front_len);
+		break;
+	case CEPH_MSG_AUTH_REPLY:
+		m = ceph_msgpool_get(&monc->msgpool_auth_reply, front_len);
+		break;
+	case CEPH_MSG_MON_MAP:
+	case CEPH_MSG_MDS_MAP:
+	case CEPH_MSG_OSD_MAP:
+		m = ceph_msg_new(type, front_len, 0, 0, NULL);
+		break;
+	}
+
+	if (!m) {
+		pr_info("alloc_msg unknown type %d\n", type);
+		*skip = 1;
+	}
+	return m;
+}
+
+/*
+ * If the monitor connection resets, pick a new monitor and resubmit
+ * any pending requests.
+ */
+static void mon_fault(struct ceph_connection *con)
+{
+	struct ceph_mon_client *monc = con->private;
+
+	if (!monc)
+		return;
+
+	dout("mon_fault\n");
+	mutex_lock(&monc->mutex);
+	if (!con->private)
+		goto out;
+
+	if (monc->con && !monc->hunting)
+		pr_info("mon%d %s session lost, "
+			"hunting for new mon\n", monc->cur_mon,
+			pr_addr(&monc->con->peer_addr.in_addr));
+
+	__close_session(monc);
+	if (!monc->hunting) {
+		/* start hunting */
+		monc->hunting = true;
+		__open_session(monc);
+	} else {
+		/* already hunting, let's wait a bit */
+		__schedule_delayed(monc);
+	}
+out:
+	mutex_unlock(&monc->mutex);
+}
+
+const static struct ceph_connection_operations mon_con_ops = {
+	.get = ceph_con_get,
+	.put = ceph_con_put,
+	.dispatch = dispatch,
+	.fault = mon_fault,
+	.alloc_msg = mon_alloc_msg,
+};

fs/ceph/mon_client.h

@@ -0,0 +1,119 @@
+#ifndef _FS_CEPH_MON_CLIENT_H
+#define _FS_CEPH_MON_CLIENT_H
+
+#include <linux/completion.h>
+#include <linux/rbtree.h>
+
+#include "messenger.h"
+#include "msgpool.h"
+
+struct ceph_client;
+struct ceph_mount_args;
+struct ceph_auth_client;
+
+/*
+ * The monitor map enumerates the set of all monitors.
+ */
+struct ceph_monmap {
+	struct ceph_fsid fsid;
+	u32 epoch;
+	u32 num_mon;
+	struct ceph_entity_inst mon_inst[0];
+};
+
+struct ceph_mon_client;
+struct ceph_mon_statfs_request;
+
+
+/*
+ * Generic mechanism for resending monitor requests.
+ */
+typedef void (*ceph_monc_request_func_t)(struct ceph_mon_client *monc,
+					 int newmon);
+
+/* a pending monitor request */
+struct ceph_mon_request {
+	struct ceph_mon_client *monc;
+	struct delayed_work delayed_work;
+	unsigned long delay;
+	ceph_monc_request_func_t do_request;
+};
+
+/*
+ * statfs() is done a bit differently because we need to get data back
+ * to the caller
+ */
+struct ceph_mon_statfs_request {
+	u64 tid;
+	struct rb_node node;
+	int result;
+	struct ceph_statfs *buf;
+	struct completion completion;
+	unsigned long last_attempt, delay; /* jiffies */
+	struct ceph_msg *request;  /* original request */
+};
+
+struct ceph_mon_client {
+	struct ceph_client *client;
+	struct ceph_monmap *monmap;
+
+	struct mutex mutex;
+	struct delayed_work delayed_work;
+
+	struct ceph_auth_client *auth;
+	struct ceph_msg *m_auth;
+	int pending_auth;
+
+	bool hunting;
+	int cur_mon;                       /* last monitor i contacted */
+	unsigned long sub_sent, sub_renew_after;
+	struct ceph_connection *con;
+	bool have_fsid;
+
+	/* msg pools */
+	struct ceph_msgpool msgpool_subscribe_ack;
+	struct ceph_msgpool msgpool_statfs_reply;
+	struct ceph_msgpool msgpool_auth_reply;
+
+	/* pending statfs requests */
+	struct rb_root statfs_request_tree;
+	int num_statfs_requests;
+	u64 last_tid;
+
+	/* mds/osd map */
+	int want_next_osdmap; /* 1 = want, 2 = want+asked */
+	u32 have_osdmap, have_mdsmap;
+
+#ifdef CONFIG_DEBUG_FS
+	struct dentry *debugfs_file;
+#endif
+};
+
+extern struct ceph_monmap *ceph_monmap_decode(void *p, void *end);
+extern int ceph_monmap_contains(struct ceph_monmap *m,
+				struct ceph_entity_addr *addr);
+
+extern int ceph_monc_init(struct ceph_mon_client *monc, struct ceph_client *cl);
+extern void ceph_monc_stop(struct ceph_mon_client *monc);
+
+/*
+ * The model here is to indicate that we need a new map of at least
+ * epoch @want, and also call in when we receive a map.  We will
+ * periodically rerequest the map from the monitor cluster until we
+ * get what we want.
+ */
+extern int ceph_monc_got_mdsmap(struct ceph_mon_client *monc, u32 have);
+extern int ceph_monc_got_osdmap(struct ceph_mon_client *monc, u32 have);
+
+extern void ceph_monc_request_next_osdmap(struct ceph_mon_client *monc);
+
+extern int ceph_monc_do_statfs(struct ceph_mon_client *monc,
+			       struct ceph_statfs *buf);
+
+extern int ceph_monc_open_session(struct ceph_mon_client *monc);
+
+extern int ceph_monc_validate_auth(struct ceph_mon_client *monc);
+
+
+
+#endif

fs/ceph/msgpool.c

@@ -0,0 +1,186 @@
+#include "ceph_debug.h"
+
+#include <linux/err.h>
+#include <linux/sched.h>
+#include <linux/types.h>
+#include <linux/vmalloc.h>
+
+#include "msgpool.h"
+
+/*
+ * We use msg pools to preallocate memory for messages we expect to
+ * receive over the wire, to avoid getting ourselves into OOM
+ * conditions at unexpected times.  We take use a few different
+ * strategies:
+ *
+ *  - for request/response type interactions, we preallocate the
+ * memory needed for the response when we generate the request.
+ *
+ *  - for messages we can receive at any time from the MDS, we preallocate
+ * a pool of messages we can re-use.
+ *
+ *  - for writeback, we preallocate some number of messages to use for
+ * requests and their replies, so that we always make forward
+ * progress.
+ *
+ * The msgpool behaves like a mempool_t, but keeps preallocated
+ * ceph_msgs strung together on a list_head instead of using a pointer
+ * vector.  This avoids vector reallocation when we adjust the number
+ * of preallocated items (which happens frequently).
+ */
+
+
+/*
+ * Allocate or release as necessary to meet our target pool size.
+ */
+static int __fill_msgpool(struct ceph_msgpool *pool)
+{
+	struct ceph_msg *msg;
+
+	while (pool->num < pool->min) {
+		dout("fill_msgpool %p %d/%d allocating\n", pool, pool->num,
+		     pool->min);
+		spin_unlock(&pool->lock);
+		msg = ceph_msg_new(0, pool->front_len, 0, 0, NULL);
+		spin_lock(&pool->lock);
+		if (IS_ERR(msg))
+			return PTR_ERR(msg);
+		msg->pool = pool;
+		list_add(&msg->list_head, &pool->msgs);
+		pool->num++;
+	}
+	while (pool->num > pool->min) {
+		msg = list_first_entry(&pool->msgs, struct ceph_msg, list_head);
+		dout("fill_msgpool %p %d/%d releasing %p\n", pool, pool->num,
+		     pool->min, msg);
+		list_del_init(&msg->list_head);
+		pool->num--;
+		ceph_msg_kfree(msg);
+	}
+	return 0;
+}
+
+int ceph_msgpool_init(struct ceph_msgpool *pool,
+		      int front_len, int min, bool blocking)
+{
+	int ret;
+
+	dout("msgpool_init %p front_len %d min %d\n", pool, front_len, min);
+	spin_lock_init(&pool->lock);
+	pool->front_len = front_len;
+	INIT_LIST_HEAD(&pool->msgs);
+	pool->num = 0;
+	pool->min = min;
+	pool->blocking = blocking;
+	init_waitqueue_head(&pool->wait);
+
+	spin_lock(&pool->lock);
+	ret = __fill_msgpool(pool);
+	spin_unlock(&pool->lock);
+	return ret;
+}
+
+void ceph_msgpool_destroy(struct ceph_msgpool *pool)
+{
+	dout("msgpool_destroy %p\n", pool);
+	spin_lock(&pool->lock);
+	pool->min = 0;
+	__fill_msgpool(pool);
+	spin_unlock(&pool->lock);
+}
+
+int ceph_msgpool_resv(struct ceph_msgpool *pool, int delta)
+{
+	int ret;
+
+	spin_lock(&pool->lock);
+	dout("msgpool_resv %p delta %d\n", pool, delta);
+	pool->min += delta;
+	ret = __fill_msgpool(pool);
+	spin_unlock(&pool->lock);
+	return ret;
+}
+
+struct ceph_msg *ceph_msgpool_get(struct ceph_msgpool *pool, int front_len)
+{
+	wait_queue_t wait;
+	struct ceph_msg *msg;
+
+	if (front_len && front_len > pool->front_len) {
+		pr_err("msgpool_get pool %p need front %d, pool size is %d\n",
+		       pool, front_len, pool->front_len);
+		WARN_ON(1);
+
+		/* try to alloc a fresh message */
+		msg = ceph_msg_new(0, front_len, 0, 0, NULL);
+		if (!IS_ERR(msg))
+			return msg;
+	}
+
+	if (!front_len)
+		front_len = pool->front_len;
+
+	if (pool->blocking) {
+		/* mempool_t behavior; first try to alloc */
+		msg = ceph_msg_new(0, front_len, 0, 0, NULL);
+		if (!IS_ERR(msg))
+			return msg;
+	}
+
+	while (1) {
+		spin_lock(&pool->lock);
+		if (likely(pool->num)) {
+			msg = list_entry(pool->msgs.next, struct ceph_msg,
+					 list_head);
+			list_del_init(&msg->list_head);
+			pool->num--;
+			dout("msgpool_get %p got %p, now %d/%d\n", pool, msg,
+			     pool->num, pool->min);
+			spin_unlock(&pool->lock);
+			return msg;
+		}
+		pr_err("msgpool_get %p now %d/%d, %s\n", pool, pool->num,
+		       pool->min, pool->blocking ? "waiting" : "may fail");
+		spin_unlock(&pool->lock);
+
+		if (!pool->blocking) {
+			WARN_ON(1);
+
+			/* maybe we can allocate it now? */
+			msg = ceph_msg_new(0, front_len, 0, 0, NULL);
+			if (!IS_ERR(msg))
+				return msg;
+
+			pr_err("msgpool_get %p empty + alloc failed\n", pool);
+			return ERR_PTR(-ENOMEM);
+		}
+
+		init_wait(&wait);
+		prepare_to_wait(&pool->wait, &wait, TASK_UNINTERRUPTIBLE);
+		schedule();
+		finish_wait(&pool->wait, &wait);
+	}
+}
+
+void ceph_msgpool_put(struct ceph_msgpool *pool, struct ceph_msg *msg)
+{
+	spin_lock(&pool->lock);
+	if (pool->num < pool->min) {
+		/* reset msg front_len; user may have changed it */
+		msg->front.iov_len = pool->front_len;
+		msg->hdr.front_len = cpu_to_le32(pool->front_len);
+
+		kref_set(&msg->kref, 1);  /* retake a single ref */
+		list_add(&msg->list_head, &pool->msgs);
+		pool->num++;
+		dout("msgpool_put %p reclaim %p, now %d/%d\n", pool, msg,
+		     pool->num, pool->min);
+		spin_unlock(&pool->lock);
+		wake_up(&pool->wait);
+	} else {
+		dout("msgpool_put %p drop %p, at %d/%d\n", pool, msg,
+		     pool->num, pool->min);
+		spin_unlock(&pool->lock);
+		ceph_msg_kfree(msg);
+	}
+}

fs/ceph/msgpool.h

@@ -0,0 +1,27 @@
+#ifndef _FS_CEPH_MSGPOOL
+#define _FS_CEPH_MSGPOOL
+
+#include "messenger.h"
+
+/*
+ * we use memory pools for preallocating messages we may receive, to
+ * avoid unexpected OOM conditions.
+ */
+struct ceph_msgpool {
+	spinlock_t lock;
+	int front_len;          /* preallocated payload size */
+	struct list_head msgs;  /* msgs in the pool; each has 1 ref */
+	int num, min;           /* cur, min # msgs in the pool */
+	bool blocking;
+	wait_queue_head_t wait;
+};
+
+extern int ceph_msgpool_init(struct ceph_msgpool *pool,
+			     int front_len, int size, bool blocking);
+extern void ceph_msgpool_destroy(struct ceph_msgpool *pool);
+extern int ceph_msgpool_resv(struct ceph_msgpool *, int delta);
+extern struct ceph_msg *ceph_msgpool_get(struct ceph_msgpool *,
+					 int front_len);
+extern void ceph_msgpool_put(struct ceph_msgpool *, struct ceph_msg *);
+
+#endif

fs/ceph/msgr.h

@@ -0,0 +1,158 @@
+#ifndef __MSGR_H
+#define __MSGR_H
+
+/*
+ * Data types for message passing layer used by Ceph.
+ */
+
+#define CEPH_MON_PORT    6789  /* default monitor port */
+
+/*
+ * client-side processes will try to bind to ports in this
+ * range, simply for the benefit of tools like nmap or wireshark
+ * that would like to identify the protocol.
+ */
+#define CEPH_PORT_FIRST  6789
+#define CEPH_PORT_START  6800  /* non-monitors start here */
+#define CEPH_PORT_LAST   6900
+
+/*
+ * tcp connection banner.  include a protocol version. and adjust
+ * whenever the wire protocol changes.  try to keep this string length
+ * constant.
+ */
+#define CEPH_BANNER "ceph v027"
+#define CEPH_BANNER_MAX_LEN 30
+
+
+/*
+ * Rollover-safe type and comparator for 32-bit sequence numbers.
+ * Comparator returns -1, 0, or 1.
+ */
+typedef __u32 ceph_seq_t;
+
+static inline __s32 ceph_seq_cmp(__u32 a, __u32 b)
+{
+       return (__s32)a - (__s32)b;
+}
+
+
+/*
+ * entity_name -- logical name for a process participating in the
+ * network, e.g. 'mds0' or 'osd3'.
+ */
+struct ceph_entity_name {
+	__u8 type;      /* CEPH_ENTITY_TYPE_* */
+	__le64 num;
+} __attribute__ ((packed));
+
+#define CEPH_ENTITY_TYPE_MON    0x01
+#define CEPH_ENTITY_TYPE_MDS    0x02
+#define CEPH_ENTITY_TYPE_OSD    0x04
+#define CEPH_ENTITY_TYPE_CLIENT 0x08
+#define CEPH_ENTITY_TYPE_ADMIN  0x10
+#define CEPH_ENTITY_TYPE_AUTH   0x20
+
+#define CEPH_ENTITY_TYPE_ANY    0xFF
+
+extern const char *ceph_entity_type_name(int type);
+
+/*
+ * entity_addr -- network address
+ */
+struct ceph_entity_addr {
+	__le32 type;
+	__le32 nonce;  /* unique id for process (e.g. pid) */
+	struct sockaddr_storage in_addr;
+} __attribute__ ((packed));
+
+struct ceph_entity_inst {
+	struct ceph_entity_name name;
+	struct ceph_entity_addr addr;
+} __attribute__ ((packed));
+
+
+/* used by message exchange protocol */
+#define CEPH_MSGR_TAG_READY         1  /* server->client: ready for messages */
+#define CEPH_MSGR_TAG_RESETSESSION  2  /* server->client: reset, try again */
+#define CEPH_MSGR_TAG_WAIT          3  /* server->client: wait for racing
+					  incoming connection */
+#define CEPH_MSGR_TAG_RETRY_SESSION 4  /* server->client + cseq: try again
+					  with higher cseq */
+#define CEPH_MSGR_TAG_RETRY_GLOBAL  5  /* server->client + gseq: try again
+					  with higher gseq */
+#define CEPH_MSGR_TAG_CLOSE         6  /* closing pipe */
+#define CEPH_MSGR_TAG_MSG           7  /* message */
+#define CEPH_MSGR_TAG_ACK           8  /* message ack */
+#define CEPH_MSGR_TAG_KEEPALIVE     9  /* just a keepalive byte! */
+#define CEPH_MSGR_TAG_BADPROTOVER  10  /* bad protocol version */
+#define CEPH_MSGR_TAG_BADAUTHORIZER 11 /* bad authorizer */
+#define CEPH_MSGR_TAG_FEATURES      12 /* insufficient features */
+
+
+/*
+ * connection negotiation
+ */
+struct ceph_msg_connect {
+	__le64 features;     /* supported feature bits */
+	__le32 host_type;    /* CEPH_ENTITY_TYPE_* */
+	__le32 global_seq;   /* count connections initiated by this host */
+	__le32 connect_seq;  /* count connections initiated in this session */
+	__le32 protocol_version;
+	__le32 authorizer_protocol;
+	__le32 authorizer_len;
+	__u8  flags;         /* CEPH_MSG_CONNECT_* */
+} __attribute__ ((packed));
+
+struct ceph_msg_connect_reply {
+	__u8 tag;
+	__le64 features;     /* feature bits for this session */
+	__le32 global_seq;
+	__le32 connect_seq;
+	__le32 protocol_version;
+	__le32 authorizer_len;
+	__u8 flags;
+} __attribute__ ((packed));
+
+#define CEPH_MSG_CONNECT_LOSSY  1  /* messages i send may be safely dropped */
+
+
+/*
+ * message header
+ */
+struct ceph_msg_header {
+	__le64 seq;       /* message seq# for this session */
+	__le64 tid;       /* transaction id */
+	__le16 type;      /* message type */
+	__le16 priority;  /* priority.  higher value == higher priority */
+	__le16 version;   /* version of message encoding */
+
+	__le32 front_len; /* bytes in main payload */
+	__le32 middle_len;/* bytes in middle payload */
+	__le32 data_len;  /* bytes of data payload */
+	__le16 data_off;  /* sender: include full offset;
+			     receiver: mask against ~PAGE_MASK */
+
+	struct ceph_entity_inst src, orig_src;
+	__le32 reserved;
+	__le32 crc;       /* header crc32c */
+} __attribute__ ((packed));
+
+#define CEPH_MSG_PRIO_LOW     64
+#define CEPH_MSG_PRIO_DEFAULT 127
+#define CEPH_MSG_PRIO_HIGH    196
+#define CEPH_MSG_PRIO_HIGHEST 255
+
+/*
+ * follows data payload
+ */
+struct ceph_msg_footer {
+	__le32 front_crc, middle_crc, data_crc;
+	__u8 flags;
+} __attribute__ ((packed));
+
+#define CEPH_MSG_FOOTER_COMPLETE  (1<<0)   /* msg wasn't aborted */
+#define CEPH_MSG_FOOTER_NOCRC     (1<<1)   /* no data crc */
+
+
+#endif

fs/ceph/osd_client.h

@@ -0,0 +1,166 @@
+#ifndef _FS_CEPH_OSD_CLIENT_H
+#define _FS_CEPH_OSD_CLIENT_H
+
+#include <linux/completion.h>
+#include <linux/kref.h>
+#include <linux/mempool.h>
+#include <linux/rbtree.h>
+
+#include "types.h"
+#include "osdmap.h"
+#include "messenger.h"
+
+struct ceph_msg;
+struct ceph_snap_context;
+struct ceph_osd_request;
+struct ceph_osd_client;
+struct ceph_authorizer;
+
+/*
+ * completion callback for async writepages
+ */
+typedef void (*ceph_osdc_callback_t)(struct ceph_osd_request *,
+				     struct ceph_msg *);
+
+/* a given osd we're communicating with */
+struct ceph_osd {
+	atomic_t o_ref;
+	struct ceph_osd_client *o_osdc;
+	int o_osd;
+	int o_incarnation;
+	struct rb_node o_node;
+	struct ceph_connection o_con;
+	struct list_head o_requests;
+	struct list_head o_osd_lru;
+	struct ceph_authorizer *o_authorizer;
+	void *o_authorizer_buf, *o_authorizer_reply_buf;
+	size_t o_authorizer_buf_len, o_authorizer_reply_buf_len;
+	unsigned long lru_ttl;
+	int o_marked_for_keepalive;
+	struct list_head o_keepalive_item;
+};
+
+/* an in-flight request */
+struct ceph_osd_request {
+	u64             r_tid;              /* unique for this client */
+	struct rb_node  r_node;
+	struct list_head r_req_lru_item;
+	struct list_head r_osd_item;
+	struct ceph_osd *r_osd;
+	struct ceph_pg   r_pgid;
+
+	struct ceph_connection *r_con_filling_msg;
+
+	struct ceph_msg  *r_request, *r_reply;
+	int               r_result;
+	int               r_flags;     /* any additional flags for the osd */
+	u32               r_sent;      /* >0 if r_request is sending/sent */
+	int               r_got_reply;
+
+	struct ceph_osd_client *r_osdc;
+	struct kref       r_kref;
+	bool              r_mempool;
+	struct completion r_completion, r_safe_completion;
+	ceph_osdc_callback_t r_callback, r_safe_callback;
+	struct ceph_eversion r_reassert_version;
+	struct list_head  r_unsafe_item;
+
+	struct inode *r_inode;         	      /* for use by callbacks */
+	struct writeback_control *r_wbc;      /* ditto */
+
+	char              r_oid[40];          /* object name */
+	int               r_oid_len;
+	unsigned long     r_sent_stamp;
+	bool              r_resend;           /* msg send failed, needs retry */
+
+	struct ceph_file_layout r_file_layout;
+	struct ceph_snap_context *r_snapc;    /* snap context for writes */
+	unsigned          r_num_pages;        /* size of page array (follows) */
+	struct page     **r_pages;            /* pages for data payload */
+	int               r_pages_from_pool;
+	int               r_own_pages;        /* if true, i own page list */
+};
+
+struct ceph_osd_client {
+	struct ceph_client     *client;
+
+	struct ceph_osdmap     *osdmap;       /* current map */
+	struct rw_semaphore    map_sem;
+	struct completion      map_waiters;
+	u64                    last_requested_map;
+
+	struct mutex           request_mutex;
+	struct rb_root         osds;          /* osds */
+	struct list_head       osd_lru;       /* idle osds */
+	u64                    timeout_tid;   /* tid of timeout triggering rq */
+	u64                    last_tid;      /* tid of last request */
+	struct rb_root         requests;      /* pending requests */
+	struct list_head       req_lru;	      /* pending requests lru */
+	int                    num_requests;
+	struct delayed_work    timeout_work;
+	struct delayed_work    osds_timeout_work;
+#ifdef CONFIG_DEBUG_FS
+	struct dentry 	       *debugfs_file;
+#endif
+
+	mempool_t              *req_mempool;
+
+	struct ceph_msgpool	msgpool_op;
+	struct ceph_msgpool	msgpool_op_reply;
+};
+
+extern int ceph_osdc_init(struct ceph_osd_client *osdc,
+			  struct ceph_client *client);
+extern void ceph_osdc_stop(struct ceph_osd_client *osdc);
+
+extern void ceph_osdc_handle_reply(struct ceph_osd_client *osdc,
+				   struct ceph_msg *msg);
+extern void ceph_osdc_handle_map(struct ceph_osd_client *osdc,
+				 struct ceph_msg *msg);
+
+extern struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *,
+				      struct ceph_file_layout *layout,
+				      struct ceph_vino vino,
+				      u64 offset, u64 *len, int op, int flags,
+				      struct ceph_snap_context *snapc,
+				      int do_sync, u32 truncate_seq,
+				      u64 truncate_size,
+				      struct timespec *mtime,
+				      bool use_mempool, int num_reply);
+
+static inline void ceph_osdc_get_request(struct ceph_osd_request *req)
+{
+	kref_get(&req->r_kref);
+}
+extern void ceph_osdc_release_request(struct kref *kref);
+static inline void ceph_osdc_put_request(struct ceph_osd_request *req)
+{
+	kref_put(&req->r_kref, ceph_osdc_release_request);
+}
+
+extern int ceph_osdc_start_request(struct ceph_osd_client *osdc,
+				   struct ceph_osd_request *req,
+				   bool nofail);
+extern int ceph_osdc_wait_request(struct ceph_osd_client *osdc,
+				  struct ceph_osd_request *req);
+extern void ceph_osdc_sync(struct ceph_osd_client *osdc);
+
+extern int ceph_osdc_readpages(struct ceph_osd_client *osdc,
+			       struct ceph_vino vino,
+			       struct ceph_file_layout *layout,
+			       u64 off, u64 *plen,
+			       u32 truncate_seq, u64 truncate_size,
+			       struct page **pages, int nr_pages);
+
+extern int ceph_osdc_writepages(struct ceph_osd_client *osdc,
+				struct ceph_vino vino,
+				struct ceph_file_layout *layout,
+				struct ceph_snap_context *sc,
+				u64 off, u64 len,
+				u32 truncate_seq, u64 truncate_size,
+				struct timespec *mtime,
+				struct page **pages, int nr_pages,
+				int flags, int do_sync, bool nofail);
+
+#endif
+

fs/ceph/osdmap.h

@@ -0,0 +1,125 @@
+#ifndef _FS_CEPH_OSDMAP_H
+#define _FS_CEPH_OSDMAP_H
+
+#include <linux/rbtree.h>
+#include "types.h"
+#include "ceph_fs.h"
+#include "crush/crush.h"
+
+/*
+ * The osd map describes the current membership of the osd cluster and
+ * specifies the mapping of objects to placement groups and placement
+ * groups to (sets of) osds.  That is, it completely specifies the
+ * (desired) distribution of all data objects in the system at some
+ * point in time.
+ *
+ * Each map version is identified by an epoch, which increases monotonically.
+ *
+ * The map can be updated either via an incremental map (diff) describing
+ * the change between two successive epochs, or as a fully encoded map.
+ */
+struct ceph_pg_pool_info {
+	struct rb_node node;
+	int id;
+	struct ceph_pg_pool v;
+	int pg_num_mask, pgp_num_mask, lpg_num_mask, lpgp_num_mask;
+};
+
+struct ceph_pg_mapping {
+	struct rb_node node;
+	struct ceph_pg pgid;
+	int len;
+	int osds[];
+};
+
+struct ceph_osdmap {
+	struct ceph_fsid fsid;
+	u32 epoch;
+	u32 mkfs_epoch;
+	struct ceph_timespec created, modified;
+
+	u32 flags;         /* CEPH_OSDMAP_* */
+
+	u32 max_osd;       /* size of osd_state, _offload, _addr arrays */
+	u8 *osd_state;     /* CEPH_OSD_* */
+	u32 *osd_weight;   /* 0 = failed, 0x10000 = 100% normal */
+	struct ceph_entity_addr *osd_addr;
+
+	struct rb_root pg_temp;
+	struct rb_root pg_pools;
+	u32 pool_max;
+
+	/* the CRUSH map specifies the mapping of placement groups to
+	 * the list of osds that store+replicate them. */
+	struct crush_map *crush;
+};
+
+/*
+ * file layout helpers
+ */
+#define ceph_file_layout_su(l) ((__s32)le32_to_cpu((l).fl_stripe_unit))
+#define ceph_file_layout_stripe_count(l) \
+	((__s32)le32_to_cpu((l).fl_stripe_count))
+#define ceph_file_layout_object_size(l) ((__s32)le32_to_cpu((l).fl_object_size))
+#define ceph_file_layout_cas_hash(l) ((__s32)le32_to_cpu((l).fl_cas_hash))
+#define ceph_file_layout_object_su(l) \
+	((__s32)le32_to_cpu((l).fl_object_stripe_unit))
+#define ceph_file_layout_pg_preferred(l) \
+	((__s32)le32_to_cpu((l).fl_pg_preferred))
+#define ceph_file_layout_pg_pool(l) \
+	((__s32)le32_to_cpu((l).fl_pg_pool))
+
+static inline unsigned ceph_file_layout_stripe_width(struct ceph_file_layout *l)
+{
+	return le32_to_cpu(l->fl_stripe_unit) *
+		le32_to_cpu(l->fl_stripe_count);
+}
+
+/* "period" == bytes before i start on a new set of objects */
+static inline unsigned ceph_file_layout_period(struct ceph_file_layout *l)
+{
+	return le32_to_cpu(l->fl_object_size) *
+		le32_to_cpu(l->fl_stripe_count);
+}
+
+
+static inline int ceph_osd_is_up(struct ceph_osdmap *map, int osd)
+{
+	return (osd < map->max_osd) && (map->osd_state[osd] & CEPH_OSD_UP);
+}
+
+static inline bool ceph_osdmap_flag(struct ceph_osdmap *map, int flag)
+{
+	return map && (map->flags & flag);
+}
+
+extern char *ceph_osdmap_state_str(char *str, int len, int state);
+
+static inline struct ceph_entity_addr *ceph_osd_addr(struct ceph_osdmap *map,
+						     int osd)
+{
+	if (osd >= map->max_osd)
+		return NULL;
+	return &map->osd_addr[osd];
+}
+
+extern struct ceph_osdmap *osdmap_decode(void **p, void *end);
+extern struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end,
+					    struct ceph_osdmap *map,
+					    struct ceph_messenger *msgr);
+extern void ceph_osdmap_destroy(struct ceph_osdmap *map);
+
+/* calculate mapping of a file extent to an object */
+extern void ceph_calc_file_object_mapping(struct ceph_file_layout *layout,
+					  u64 off, u64 *plen,
+					  u64 *bno, u64 *oxoff, u64 *oxlen);
+
+/* calculate mapping of object to a placement group */
+extern int ceph_calc_object_layout(struct ceph_object_layout *ol,
+				   const char *oid,
+				   struct ceph_file_layout *fl,
+				   struct ceph_osdmap *osdmap);
+extern int ceph_calc_pg_primary(struct ceph_osdmap *osdmap,
+				struct ceph_pg pgid);
+
+#endif

fs/ceph/pagelist.c

@@ -0,0 +1,54 @@
+
+#include <linux/pagemap.h>
+#include <linux/highmem.h>
+
+#include "pagelist.h"
+
+int ceph_pagelist_release(struct ceph_pagelist *pl)
+{
+	if (pl->mapped_tail)
+		kunmap(pl->mapped_tail);
+	while (!list_empty(&pl->head)) {
+		struct page *page = list_first_entry(&pl->head, struct page,
+						     lru);
+		list_del(&page->lru);
+		__free_page(page);
+	}
+	return 0;
+}
+
+static int ceph_pagelist_addpage(struct ceph_pagelist *pl)
+{
+	struct page *page = alloc_page(GFP_NOFS);
+	if (!page)
+		return -ENOMEM;
+	pl->room += PAGE_SIZE;
+	list_add_tail(&page->lru, &pl->head);
+	if (pl->mapped_tail)
+		kunmap(pl->mapped_tail);
+	pl->mapped_tail = kmap(page);
+	return 0;
+}
+
+int ceph_pagelist_append(struct ceph_pagelist *pl, void *buf, size_t len)
+{
+	while (pl->room < len) {
+		size_t bit = pl->room;
+		int ret;
+
+		memcpy(pl->mapped_tail + (pl->length & ~PAGE_CACHE_MASK),
+		       buf, bit);
+		pl->length += bit;
+		pl->room -= bit;
+		buf += bit;
+		len -= bit;
+		ret = ceph_pagelist_addpage(pl);
+		if (ret)
+			return ret;
+	}
+
+	memcpy(pl->mapped_tail + (pl->length & ~PAGE_CACHE_MASK), buf, len);
+	pl->length += len;
+	pl->room -= len;
+	return 0;
+}

fs/ceph/pagelist.h

@@ -0,0 +1,54 @@
+#ifndef __FS_CEPH_PAGELIST_H
+#define __FS_CEPH_PAGELIST_H
+
+#include <linux/list.h>
+
+struct ceph_pagelist {
+	struct list_head head;
+	void *mapped_tail;
+	size_t length;
+	size_t room;
+};
+
+static inline void ceph_pagelist_init(struct ceph_pagelist *pl)
+{
+	INIT_LIST_HEAD(&pl->head);
+	pl->mapped_tail = NULL;
+	pl->length = 0;
+	pl->room = 0;
+}
+extern int ceph_pagelist_release(struct ceph_pagelist *pl);
+
+extern int ceph_pagelist_append(struct ceph_pagelist *pl, void *d, size_t l);
+
+static inline int ceph_pagelist_encode_64(struct ceph_pagelist *pl, u64 v)
+{
+	__le64 ev = cpu_to_le64(v);
+	return ceph_pagelist_append(pl, &ev, sizeof(ev));
+}
+static inline int ceph_pagelist_encode_32(struct ceph_pagelist *pl, u32 v)
+{
+	__le32 ev = cpu_to_le32(v);
+	return ceph_pagelist_append(pl, &ev, sizeof(ev));
+}
+static inline int ceph_pagelist_encode_16(struct ceph_pagelist *pl, u16 v)
+{
+	__le16 ev = cpu_to_le16(v);
+	return ceph_pagelist_append(pl, &ev, sizeof(ev));
+}
+static inline int ceph_pagelist_encode_8(struct ceph_pagelist *pl, u8 v)
+{
+	return ceph_pagelist_append(pl, &v, 1);
+}
+static inline int ceph_pagelist_encode_string(struct ceph_pagelist *pl,
+					      char *s, size_t len)
+{
+	int ret = ceph_pagelist_encode_32(pl, len);
+	if (ret)
+		return ret;
+	if (len)
+		return ceph_pagelist_append(pl, s, len);
+	return 0;
+}
+
+#endif

fs/ceph/rados.h

@@ -0,0 +1,374 @@
+#ifndef __RADOS_H
+#define __RADOS_H
+
+/*
+ * Data types for the Ceph distributed object storage layer RADOS
+ * (Reliable Autonomic Distributed Object Store).
+ */
+
+#include "msgr.h"
+
+/*
+ * osdmap encoding versions
+ */
+#define CEPH_OSDMAP_INC_VERSION 4
+#define CEPH_OSDMAP_VERSION     4
+
+/*
+ * fs id
+ */
+struct ceph_fsid {
+	unsigned char fsid[16];
+};
+
+static inline int ceph_fsid_compare(const struct ceph_fsid *a,
+				    const struct ceph_fsid *b)
+{
+	return memcmp(a, b, sizeof(*a));
+}
+
+/*
+ * ino, object, etc.
+ */
+typedef __le64 ceph_snapid_t;
+#define CEPH_SNAPDIR ((__u64)(-1))  /* reserved for hidden .snap dir */
+#define CEPH_NOSNAP  ((__u64)(-2))  /* "head", "live" revision */
+#define CEPH_MAXSNAP ((__u64)(-3))  /* largest valid snapid */
+
+struct ceph_timespec {
+	__le32 tv_sec;
+	__le32 tv_nsec;
+} __attribute__ ((packed));
+
+
+/*
+ * object layout - how objects are mapped into PGs
+ */
+#define CEPH_OBJECT_LAYOUT_HASH     1
+#define CEPH_OBJECT_LAYOUT_LINEAR   2
+#define CEPH_OBJECT_LAYOUT_HASHINO  3
+
+/*
+ * pg layout -- how PGs are mapped onto (sets of) OSDs
+ */
+#define CEPH_PG_LAYOUT_CRUSH  0
+#define CEPH_PG_LAYOUT_HASH   1
+#define CEPH_PG_LAYOUT_LINEAR 2
+#define CEPH_PG_LAYOUT_HYBRID 3
+
+
+/*
+ * placement group.
+ * we encode this into one __le64.
+ */
+struct ceph_pg {
+	__le16 preferred; /* preferred primary osd */
+	__le16 ps;        /* placement seed */
+	__le32 pool;      /* object pool */
+} __attribute__ ((packed));
+
+/*
+ * pg_pool is a set of pgs storing a pool of objects
+ *
+ *  pg_num -- base number of pseudorandomly placed pgs
+ *
+ *  pgp_num -- effective number when calculating pg placement.  this
+ * is used for pg_num increases.  new pgs result in data being "split"
+ * into new pgs.  for this to proceed smoothly, new pgs are intiially
+ * colocated with their parents; that is, pgp_num doesn't increase
+ * until the new pgs have successfully split.  only _then_ are the new
+ * pgs placed independently.
+ *
+ *  lpg_num -- localized pg count (per device).  replicas are randomly
+ * selected.
+ *
+ *  lpgp_num -- as above.
+ */
+#define CEPH_PG_TYPE_REP     1
+#define CEPH_PG_TYPE_RAID4   2
+#define CEPH_PG_POOL_VERSION 2
+struct ceph_pg_pool {
+	__u8 type;                /* CEPH_PG_TYPE_* */
+	__u8 size;                /* number of osds in each pg */
+	__u8 crush_ruleset;       /* crush placement rule */
+	__u8 object_hash;         /* hash mapping object name to ps */
+	__le32 pg_num, pgp_num;   /* number of pg's */
+	__le32 lpg_num, lpgp_num; /* number of localized pg's */
+	__le32 last_change;       /* most recent epoch changed */
+	__le64 snap_seq;          /* seq for per-pool snapshot */
+	__le32 snap_epoch;        /* epoch of last snap */
+	__le32 num_snaps;
+	__le32 num_removed_snap_intervals;
+	__le64 uid;
+} __attribute__ ((packed));
+
+/*
+ * stable_mod func is used to control number of placement groups.
+ * similar to straight-up modulo, but produces a stable mapping as b
+ * increases over time.  b is the number of bins, and bmask is the
+ * containing power of 2 minus 1.
+ *
+ * b <= bmask and bmask=(2**n)-1
+ * e.g., b=12 -> bmask=15, b=123 -> bmask=127
+ */
+static inline int ceph_stable_mod(int x, int b, int bmask)
+{
+	if ((x & bmask) < b)
+		return x & bmask;
+	else
+		return x & (bmask >> 1);
+}
+
+/*
+ * object layout - how a given object should be stored.
+ */
+struct ceph_object_layout {
+	struct ceph_pg ol_pgid;   /* raw pg, with _full_ ps precision. */
+	__le32 ol_stripe_unit;    /* for per-object parity, if any */
+} __attribute__ ((packed));
+
+/*
+ * compound epoch+version, used by storage layer to serialize mutations
+ */
+struct ceph_eversion {
+	__le32 epoch;
+	__le64 version;
+} __attribute__ ((packed));
+
+/*
+ * osd map bits
+ */
+
+/* status bits */
+#define CEPH_OSD_EXISTS 1
+#define CEPH_OSD_UP     2
+
+/* osd weights.  fixed point value: 0x10000 == 1.0 ("in"), 0 == "out" */
+#define CEPH_OSD_IN  0x10000
+#define CEPH_OSD_OUT 0
+
+
+/*
+ * osd map flag bits
+ */
+#define CEPH_OSDMAP_NEARFULL (1<<0)  /* sync writes (near ENOSPC) */
+#define CEPH_OSDMAP_FULL     (1<<1)  /* no data writes (ENOSPC) */
+#define CEPH_OSDMAP_PAUSERD  (1<<2)  /* pause all reads */
+#define CEPH_OSDMAP_PAUSEWR  (1<<3)  /* pause all writes */
+#define CEPH_OSDMAP_PAUSEREC (1<<4)  /* pause recovery */
+
+/*
+ * osd ops
+ */
+#define CEPH_OSD_OP_MODE       0xf000
+#define CEPH_OSD_OP_MODE_RD    0x1000
+#define CEPH_OSD_OP_MODE_WR    0x2000
+#define CEPH_OSD_OP_MODE_RMW   0x3000
+#define CEPH_OSD_OP_MODE_SUB   0x4000
+
+#define CEPH_OSD_OP_TYPE       0x0f00
+#define CEPH_OSD_OP_TYPE_LOCK  0x0100
+#define CEPH_OSD_OP_TYPE_DATA  0x0200
+#define CEPH_OSD_OP_TYPE_ATTR  0x0300
+#define CEPH_OSD_OP_TYPE_EXEC  0x0400
+#define CEPH_OSD_OP_TYPE_PG    0x0500
+
+enum {
+	/** data **/
+	/* read */
+	CEPH_OSD_OP_READ      = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 1,
+	CEPH_OSD_OP_STAT      = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 2,
+
+	/* fancy read */
+	CEPH_OSD_OP_MASKTRUNC = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 4,
+
+	/* write */
+	CEPH_OSD_OP_WRITE     = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 1,
+	CEPH_OSD_OP_WRITEFULL = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 2,
+	CEPH_OSD_OP_TRUNCATE  = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 3,
+	CEPH_OSD_OP_ZERO      = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 4,
+	CEPH_OSD_OP_DELETE    = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 5,
+
+	/* fancy write */
+	CEPH_OSD_OP_APPEND    = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 6,
+	CEPH_OSD_OP_STARTSYNC = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 7,
+	CEPH_OSD_OP_SETTRUNC  = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 8,
+	CEPH_OSD_OP_TRIMTRUNC = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 9,
+
+	CEPH_OSD_OP_TMAPUP  = CEPH_OSD_OP_MODE_RMW | CEPH_OSD_OP_TYPE_DATA | 10,
+	CEPH_OSD_OP_TMAPPUT = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 11,
+	CEPH_OSD_OP_TMAPGET = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 12,
+
+	CEPH_OSD_OP_CREATE  = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 13,
+
+	/** attrs **/
+	/* read */
+	CEPH_OSD_OP_GETXATTR  = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_ATTR | 1,
+	CEPH_OSD_OP_GETXATTRS = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_ATTR | 2,
+
+	/* write */
+	CEPH_OSD_OP_SETXATTR  = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_ATTR | 1,
+	CEPH_OSD_OP_SETXATTRS = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_ATTR | 2,
+	CEPH_OSD_OP_RESETXATTRS = CEPH_OSD_OP_MODE_WR|CEPH_OSD_OP_TYPE_ATTR | 3,
+	CEPH_OSD_OP_RMXATTR   = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_ATTR | 4,
+
+	/** subop **/
+	CEPH_OSD_OP_PULL           = CEPH_OSD_OP_MODE_SUB | 1,
+	CEPH_OSD_OP_PUSH           = CEPH_OSD_OP_MODE_SUB | 2,
+	CEPH_OSD_OP_BALANCEREADS   = CEPH_OSD_OP_MODE_SUB | 3,
+	CEPH_OSD_OP_UNBALANCEREADS = CEPH_OSD_OP_MODE_SUB | 4,
+	CEPH_OSD_OP_SCRUB          = CEPH_OSD_OP_MODE_SUB | 5,
+
+	/** lock **/
+	CEPH_OSD_OP_WRLOCK    = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_LOCK | 1,
+	CEPH_OSD_OP_WRUNLOCK  = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_LOCK | 2,
+	CEPH_OSD_OP_RDLOCK    = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_LOCK | 3,
+	CEPH_OSD_OP_RDUNLOCK  = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_LOCK | 4,
+	CEPH_OSD_OP_UPLOCK    = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_LOCK | 5,
+	CEPH_OSD_OP_DNLOCK    = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_LOCK | 6,
+
+	/** exec **/
+	CEPH_OSD_OP_CALL    = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_EXEC | 1,
+
+	/** pg **/
+	CEPH_OSD_OP_PGLS      = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_PG | 1,
+};
+
+static inline int ceph_osd_op_type_lock(int op)
+{
+	return (op & CEPH_OSD_OP_TYPE) == CEPH_OSD_OP_TYPE_LOCK;
+}
+static inline int ceph_osd_op_type_data(int op)
+{
+	return (op & CEPH_OSD_OP_TYPE) == CEPH_OSD_OP_TYPE_DATA;
+}
+static inline int ceph_osd_op_type_attr(int op)
+{
+	return (op & CEPH_OSD_OP_TYPE) == CEPH_OSD_OP_TYPE_ATTR;
+}
+static inline int ceph_osd_op_type_exec(int op)
+{
+	return (op & CEPH_OSD_OP_TYPE) == CEPH_OSD_OP_TYPE_EXEC;
+}
+static inline int ceph_osd_op_type_pg(int op)
+{
+	return (op & CEPH_OSD_OP_TYPE) == CEPH_OSD_OP_TYPE_PG;
+}
+
+static inline int ceph_osd_op_mode_subop(int op)
+{
+	return (op & CEPH_OSD_OP_MODE) == CEPH_OSD_OP_MODE_SUB;
+}
+static inline int ceph_osd_op_mode_read(int op)
+{
+	return (op & CEPH_OSD_OP_MODE) == CEPH_OSD_OP_MODE_RD;
+}
+static inline int ceph_osd_op_mode_modify(int op)
+{
+	return (op & CEPH_OSD_OP_MODE) == CEPH_OSD_OP_MODE_WR;
+}
+
+#define CEPH_OSD_TMAP_HDR 'h'
+#define CEPH_OSD_TMAP_SET 's'
+#define CEPH_OSD_TMAP_RM  'r'
+
+extern const char *ceph_osd_op_name(int op);
+
+
+/*
+ * osd op flags
+ *
+ * An op may be READ, WRITE, or READ|WRITE.
+ */
+enum {
+	CEPH_OSD_FLAG_ACK = 1,          /* want (or is) "ack" ack */
+	CEPH_OSD_FLAG_ONNVRAM = 2,      /* want (or is) "onnvram" ack */
+	CEPH_OSD_FLAG_ONDISK = 4,       /* want (or is) "ondisk" ack */
+	CEPH_OSD_FLAG_RETRY = 8,        /* resend attempt */
+	CEPH_OSD_FLAG_READ = 16,        /* op may read */
+	CEPH_OSD_FLAG_WRITE = 32,       /* op may write */
+	CEPH_OSD_FLAG_ORDERSNAP = 64,   /* EOLDSNAP if snapc is out of order */
+	CEPH_OSD_FLAG_PEERSTAT = 128,   /* msg includes osd_peer_stat */
+	CEPH_OSD_FLAG_BALANCE_READS = 256,
+	CEPH_OSD_FLAG_PARALLELEXEC = 512, /* execute op in parallel */
+	CEPH_OSD_FLAG_PGOP = 1024,      /* pg op, no object */
+	CEPH_OSD_FLAG_EXEC = 2048,      /* op may exec */
+};
+
+enum {
+	CEPH_OSD_OP_FLAG_EXCL = 1,      /* EXCL object create */
+};
+
+#define EOLDSNAPC    ERESTART  /* ORDERSNAP flag set; writer has old snapc*/
+#define EBLACKLISTED ESHUTDOWN /* blacklisted */
+
+/*
+ * an individual object operation.  each may be accompanied by some data
+ * payload
+ */
+struct ceph_osd_op {
+	__le16 op;           /* CEPH_OSD_OP_* */
+	__le32 flags;        /* CEPH_OSD_FLAG_* */
+	union {
+		struct {
+			__le64 offset, length;
+			__le64 truncate_size;
+			__le32 truncate_seq;
+		} __attribute__ ((packed)) extent;
+		struct {
+			__le32 name_len;
+			__le32 value_len;
+		} __attribute__ ((packed)) xattr;
+		struct {
+			__u8 class_len;
+			__u8 method_len;
+			__u8 argc;
+			__le32 indata_len;
+		} __attribute__ ((packed)) cls;
+		struct {
+			__le64 cookie, count;
+		} __attribute__ ((packed)) pgls;
+	};
+	__le32 payload_len;
+} __attribute__ ((packed));
+
+/*
+ * osd request message header.  each request may include multiple
+ * ceph_osd_op object operations.
+ */
+struct ceph_osd_request_head {
+	__le32 client_inc;                 /* client incarnation */
+	struct ceph_object_layout layout;  /* pgid */
+	__le32 osdmap_epoch;               /* client's osdmap epoch */
+
+	__le32 flags;
+
+	struct ceph_timespec mtime;        /* for mutations only */
+	struct ceph_eversion reassert_version; /* if we are replaying op */
+
+	__le32 object_len;     /* length of object name */
+
+	__le64 snapid;         /* snapid to read */
+	__le64 snap_seq;       /* writer's snap context */
+	__le32 num_snaps;
+
+	__le16 num_ops;
+	struct ceph_osd_op ops[];  /* followed by ops[], obj, ticket, snaps */
+} __attribute__ ((packed));
+
+struct ceph_osd_reply_head {
+	__le32 client_inc;                /* client incarnation */
+	__le32 flags;
+	struct ceph_object_layout layout;
+	__le32 osdmap_epoch;
+	struct ceph_eversion reassert_version; /* for replaying uncommitted */
+
+	__le32 result;                    /* result code */
+
+	__le32 object_len;                /* length of object name */
+	__le32 num_ops;
+	struct ceph_osd_op ops[0];  /* ops[], object */
+} __attribute__ ((packed));
+
+
+#endif

fs/ceph/snap.c

@@ -0,0 +1,904 @@
+#include "ceph_debug.h"
+
+#include <linux/sort.h>
+
+#include "super.h"
+#include "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->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(&mdsc->snap_empty, &realm->empty_item);
+		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;
+	int i;
+	int 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 (%d snaps)"
+		     " (unchanged)\n",
+		     realm->ino, realm, realm->cached_context,
+		     realm->cached_context->seq,
+		     realm->cached_context->num_snaps);
+		return 0;
+	}
+
+	/* alloc new snap context */
+	err = -ENOMEM;
+	if (num > ULONG_MAX / sizeof(u64) - sizeof(*snapc))
+		goto fail;
+	snapc = kzalloc(sizeof(*snapc) + num*sizeof(u64), GFP_NOFS);
+	if (!snapc)
+		goto fail;
+	atomic_set(&snapc->nref, 1);
+
+	/* build (reverse sorted) snap vector */
+	num = 0;
+	snapc->seq = realm->seq;
+	if (parent) {
+		/* include any of parent's snaps occuring _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 (%d snaps)\n",
+	     realm->ino, realm, snapc, snapc->seq, 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, int num)
+{
+	int 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 ceph_snap_context *snapc)
+{
+	struct inode *inode = &ci->vfs_inode;
+	struct ceph_cap_snap *capsnap;
+	int used;
+
+	capsnap = kzalloc(sizeof(*capsnap), GFP_NOFS);
+	if (!capsnap) {
+		pr_err("ENOMEM allocating ceph_cap_snap on %p\n", inode);
+		return;
+	}
+
+	spin_lock(&inode->i_lock);
+	used = __ceph_caps_used(ci);
+	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 snapc %p seq %llu used %d"
+		     " already pending\n", inode, snapc, snapc->seq, used);
+		kfree(capsnap);
+	} else if (ci->i_wrbuffer_ref_head || (used & CEPH_CAP_FILE_WR)) {
+		igrab(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 - 1;
+		capsnap->context = ceph_get_snap_context(snapc);
+		capsnap->issued = __ceph_caps_issued(ci, NULL);
+		capsnap->dirty = __ceph_caps_dirty(ci);
+
+		capsnap->mode = inode->i_mode;
+		capsnap->uid = inode->i_uid;
+		capsnap->gid = inode->i_gid;
+
+		/* fixme? */
+		capsnap->xattr_blob = NULL;
+		capsnap->xattr_len = 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;
+		ceph_put_snap_context(ci->i_head_snapc);
+		ci->i_head_snapc = NULL;
+		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(&inode->i_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_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_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=%llu "
+		     "still has %d dirty pages\n", inode, capsnap,
+		     capsnap->context, capsnap->context->seq,
+		     capsnap->size, capsnap->dirty_pages);
+		return 0;
+	}
+	dout("finish_cap_snap %p cap_snap %p snapc %p %llu s=%llu clean\n",
+	     inode, capsnap, capsnap->context,
+	     capsnap->context->seq, 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 */
+}
+
+
+/*
+ * 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;
+
+	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;
+		}
+	}
+
+	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));
+		/*
+		 * if the realm seq has changed, queue a cap_snap for every
+		 * inode with open caps.  we do this _before_ we update
+		 * the realm info so that we prepare for writeback under the
+		 * _previous_ snap context.
+		 *
+		 * ...unless it's a snap deletion!
+		 */
+		if (!deletion) {
+			struct ceph_inode_info *ci;
+			struct inode *lastinode = NULL;
+
+			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, realm->cached_context);
+				spin_lock(&realm->inodes_with_caps_lock);
+			}
+			spin_unlock(&realm->inodes_with_caps_lock);
+			if (lastinode)
+				iput(lastinode);
+			dout("update_snap_trace cap_snaps queued\n");
+		}
+
+	} else {
+		dout("update_snap_trace %llx %p seq %lld unchanged\n",
+		     realm->ino, realm, realm->seq);
+	}
+
+	/* 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) {
+		/* 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;
+
+		invalidate = 1;
+	} else if (!realm->cached_context) {
+		invalidate = 1;
+	}
+
+	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);
+
+	__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;
+		igrab(inode);
+		spin_unlock(&mdsc->snap_flush_lock);
+		spin_lock(&inode->i_lock);
+		__ceph_flush_snaps(ci, &session);
+		spin_unlock(&inode->i_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->client->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;
+
+			if (!inode)
+				continue;
+			ci = ceph_inode(inode);
+
+			spin_lock(&inode->i_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);
+			/*
+			 * Remove the inode from the realm's inode
+			 * list, but don't add it to the new realm
+			 * yet.  We don't want the cap_snap to be
+			 * queued (again) by ceph_update_snap_trace()
+			 * below.  Queue it _now_, under the old context.
+			 */
+			list_del_init(&ci->i_snap_realm_item);
+			spin_unlock(&inode->i_lock);
+
+			ceph_queue_cap_snap(ci,
+					    ci->i_snap_realm->cached_context);
+
+			iput(inode);
+			continue;
+
+skip_inode:
+			spin_unlock(&inode->i_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) {
+		/*
+		 * ok, _now_ add the inodes into the new 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;
+
+			if (!inode)
+				continue;
+			ci = ceph_inode(inode);
+			spin_lock(&inode->i_lock);
+			if (!ci->i_snap_realm)
+				goto split_skip_inode;
+			ceph_put_snap_realm(mdsc, ci->i_snap_realm);
+			spin_lock(&realm->inodes_with_caps_lock);
+			list_add(&ci->i_snap_realm_item,
+				 &realm->inodes_with_caps);
+			ci->i_snap_realm = realm;
+			spin_unlock(&realm->inodes_with_caps_lock);
+			ceph_get_snap_realm(mdsc, realm);
+split_skip_inode:
+			spin_unlock(&inode->i_lock);
+			iput(inode);
+		}
+
+		/* 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/super.h

@@ -0,0 +1,901 @@
+#ifndef _FS_CEPH_SUPER_H
+#define _FS_CEPH_SUPER_H
+
+#include "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 "types.h"
+#include "messenger.h"
+#include "msgpool.h"
+#include "mon_client.h"
+#include "mds_client.h"
+#include "osd_client.h"
+#include "ceph_fs.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   20  /* 1 MB */
+#define CEPH_BLOCK         (1 << CEPH_BLOCK_SHIFT)
+
+/*
+ * mount options
+ */
+#define CEPH_OPT_FSID             (1<<0)
+#define CEPH_OPT_NOSHARE          (1<<1) /* don't share client with other sbs */
+#define CEPH_OPT_MYIP             (1<<2) /* specified my ip */
+#define CEPH_OPT_DIRSTAT          (1<<4) /* funky `cat dirname` for stats */
+#define CEPH_OPT_RBYTES           (1<<5) /* dir st_bytes = rbytes */
+#define CEPH_OPT_NOCRC            (1<<6) /* no data crc on writes */
+#define CEPH_OPT_NOASYNCREADDIR   (1<<7) /* no dcache readdir */
+
+#define CEPH_OPT_DEFAULT   (CEPH_OPT_RBYTES)
+
+#define ceph_set_opt(client, opt) \
+	(client)->mount_args->flags |= CEPH_OPT_##opt;
+#define ceph_test_opt(client, opt) \
+	(!!((client)->mount_args->flags & CEPH_OPT_##opt))
+
+
+struct ceph_mount_args {
+	int sb_flags;
+	int num_mon;
+	struct ceph_entity_addr *mon_addr;
+	int flags;
+	int mount_timeout;
+	int osd_idle_ttl;
+	int caps_wanted_delay_min, caps_wanted_delay_max;
+	struct ceph_fsid fsid;
+	struct ceph_entity_addr my_addr;
+	int wsize;
+	int rsize;            /* max readahead */
+	int max_readdir;      /* max readdir size */
+	int congestion_kb;      /* max readdir size */
+	int osd_timeout;
+	int osd_keepalive_timeout;
+	char *snapdir_name;   /* default ".snap" */
+	char *name;
+	char *secret;
+	int cap_release_safety;
+};
+
+/*
+ * defaults
+ */
+#define CEPH_MOUNT_TIMEOUT_DEFAULT  60
+#define CEPH_OSD_TIMEOUT_DEFAULT    60  /* seconds */
+#define CEPH_OSD_KEEPALIVE_DEFAULT  5
+#define CEPH_OSD_IDLE_TTL_DEFAULT    60
+#define CEPH_MOUNT_RSIZE_DEFAULT    (512*1024) /* readahead */
+
+#define CEPH_MSG_MAX_FRONT_LEN	(16*1024*1024)
+#define CEPH_MSG_MAX_DATA_LEN	(16*1024*1024)
+
+#define CEPH_SNAPDIRNAME_DEFAULT ".snap"
+#define CEPH_AUTH_NAME_DEFAULT   "guest"
+
+/*
+ * Delay telling the MDS we no longer want caps, in case we reopen
+ * the file.  Delay a minimum amount of time, even if we send a cap
+ * message for some other reason.  Otherwise, take the oppotunity to
+ * update the mds to avoid sending another message later.
+ */
+#define CEPH_CAPS_WANTED_DELAY_MIN_DEFAULT      5  /* cap release delay */
+#define CEPH_CAPS_WANTED_DELAY_MAX_DEFAULT     60  /* cap release delay */
+
+
+/* mount state */
+enum {
+	CEPH_MOUNT_MOUNTING,
+	CEPH_MOUNT_MOUNTED,
+	CEPH_MOUNT_UNMOUNTING,
+	CEPH_MOUNT_UNMOUNTED,
+	CEPH_MOUNT_SHUTDOWN,
+};
+
+/*
+ * subtract jiffies
+ */
+static inline unsigned long time_sub(unsigned long a, unsigned long b)
+{
+	BUG_ON(time_after(b, a));
+	return (long)a - (long)b;
+}
+
+/*
+ * per-filesystem client state
+ *
+ * possibly shared by multiple mount points, if they are
+ * mounting the same ceph filesystem/cluster.
+ */
+struct ceph_client {
+	struct ceph_fsid fsid;
+	bool have_fsid;
+
+	struct mutex mount_mutex;       /* serialize mount attempts */
+	struct ceph_mount_args *mount_args;
+
+	struct super_block *sb;
+
+	unsigned long mount_state;
+	wait_queue_head_t auth_wq;
+
+	int auth_err;
+
+	int min_caps;                  /* min caps i added */
+
+	struct ceph_messenger *msgr;   /* messenger instance */
+	struct ceph_mon_client monc;
+	struct ceph_mds_client mdsc;
+	struct ceph_osd_client osdc;
+
+	/* 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_monmap;
+	struct dentry *debugfs_mdsmap, *debugfs_osdmap;
+	struct dentry *debugfs_dir, *debugfs_dentry_lru, *debugfs_caps;
+	struct dentry *debugfs_congestion_kb;
+	struct dentry *debugfs_bdi;
+#endif
+};
+
+static inline struct ceph_client *ceph_client(struct super_block *sb)
+{
+	return sb->s_fs_info;
+}
+
+
+/*
+ * 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;
+
+	mode_t mode;
+	uid_t uid;
+	gid_t gid;
+
+	void *xattr_blob;
+	int xattr_len;
+	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))
+		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;
+};
+
+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.
+ */
+#define CEPH_I_COMPLETE  1  /* we have complete directory cached */
+#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 */
+
+struct ceph_inode_info {
+	struct ceph_vino i_vino;   /* ceph ino + snap */
+
+	u64 i_version;
+	u32 i_time_warp_seq;
+
+	unsigned i_ceph_flags;
+	unsigned long i_release_count;
+
+	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 I_COMPLETE */
+
+	struct rb_root i_fragtree;
+	struct mutex i_fragtree_mutex;
+
+	struct ceph_inode_xattrs_info i_xattrs;
+
+	/* capabilities.  protected _both_ by i_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 */
+	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;
+	int i_wrbuffer_ref, i_wrbuffer_ref_head;
+	u32 i_shared_gen;       /* increment each time we get FILE_SHARED */
+	u32 i_rdcache_gen;      /* we increment this each time we get
+				   FILE_CACHE.  If it's non-zero, we
+				   _may_ have cached pages. */
+	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 void ceph_i_clear(struct inode *inode, unsigned mask)
+{
+	struct ceph_inode_info *ci = ceph_inode(inode);
+
+	spin_lock(&inode->i_lock);
+	ci->i_ceph_flags &= ~mask;
+	spin_unlock(&inode->i_lock);
+}
+
+static inline void ceph_i_set(struct inode *inode, unsigned mask)
+{
+	struct ceph_inode_info *ci = ceph_inode(inode);
+
+	spin_lock(&inode->i_lock);
+	ci->i_ceph_flags |= mask;
+	spin_unlock(&inode->i_lock);
+}
+
+static inline bool ceph_i_test(struct inode *inode, unsigned mask)
+{
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	bool r;
+
+	smp_mb();
+	r = (ci->i_ceph_flags & mask) == mask;
+	return r;
+}
+
+
+/* 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);
+
+/*
+ * 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;
+};
+
+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;
+}
+
+/*
+ * ino_t is <64 bits on many architectures, blech.
+ *
+ * don't include snap in ino hash, at least for now.
+ */
+static inline ino_t ceph_vino_to_ino(struct ceph_vino vino)
+{
+	ino_t ino = (ino_t)vino.ino;  /* ^ (vino.snap << 20); */
+#if BITS_PER_LONG == 32
+	ino ^= vino.ino >> (sizeof(u64)-sizeof(ino_t)) * 8;
+	if (!ino)
+		ino = 1;
+#endif
+	return ino;
+}
+
+static inline int ceph_set_ino_cb(struct inode *inode, void *data)
+{
+	ceph_inode(inode)->i_vino = *(struct ceph_vino *)data;
+	inode->i_ino = ceph_vino_to_ino(*(struct ceph_vino *)data);
+	return 0;
+}
+
+static inline struct ceph_vino ceph_vino(struct inode *inode)
+{
+	return ceph_inode(inode)->i_vino;
+}
+
+/* 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);
+}
+
+
+/*
+ * 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->vfs_inode.i_lock);
+	issued = __ceph_caps_issued(ci, NULL);
+	spin_unlock(&ci->vfs_inode.i_lock);
+	return issued;
+}
+
+static inline int ceph_caps_issued_mask(struct ceph_inode_info *ci, int mask,
+					int touch)
+{
+	int r;
+	spin_lock(&ci->vfs_inode.i_lock);
+	r = __ceph_caps_issued_mask(ci, mask, touch);
+	spin_unlock(&ci->vfs_inode.i_lock);
+	return r;
+}
+
+static inline int __ceph_caps_dirty(struct ceph_inode_info *ci)
+{
+	return ci->i_dirty_caps | ci->i_flushing_caps;
+}
+extern void __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(void);
+extern void ceph_caps_finalize(void);
+extern void ceph_adjust_min_caps(int delta);
+extern int ceph_reserve_caps(struct ceph_cap_reservation *ctx, int need);
+extern int ceph_unreserve_caps(struct ceph_cap_reservation *ctx);
+extern void ceph_reservation_status(struct ceph_client *client,
+				    int *total, int *avail, int *used,
+				    int *reserved, int *min);
+
+static inline struct ceph_client *ceph_inode_to_client(struct inode *inode)
+{
+	return (struct ceph_client *)inode->i_sb->s_fs_info;
+}
+
+static inline struct ceph_client *ceph_sb_to_client(struct super_block *sb)
+{
+	return (struct ceph_client *)sb->s_fs_info;
+}
+
+
+/*
+ * we keep buffered readdir results attached to file->private_data
+ */
+struct ceph_file_info {
+	int fmode;     /* initialized on open */
+
+	/* readdir: position within the dir */
+	u32 frag;
+	struct ceph_mds_request *last_readdir;
+	int at_end;
+
+	/* 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) */
+	unsigned long dir_release_count;
+
+	/* used for -o dirstat read() on directory thing */
+	char *dir_info;
+	int dir_info_len;
+};
+
+
+
+/*
+ * snapshots
+ */
+
+/*
+ * A "snap context" is the set of existing snapshots when we
+ * write data.  It is used by the OSD to guide its COW behavior.
+ *
+ * The ceph_snap_context is refcounted, and attached to each dirty
+ * page, indicating which context the dirty data belonged when it was
+ * dirtied.
+ */
+struct ceph_snap_context {
+	atomic_t nref;
+	u64 seq;
+	int num_snaps;
+	u64 snaps[];
+};
+
+static inline struct ceph_snap_context *
+ceph_get_snap_context(struct ceph_snap_context *sc)
+{
+	/*
+	printk("get_snap_context %p %d -> %d\n", sc, atomic_read(&sc->nref),
+	       atomic_read(&sc->nref)+1);
+	*/
+	if (sc)
+		atomic_inc(&sc->nref);
+	return sc;
+}
+
+static inline void ceph_put_snap_context(struct ceph_snap_context *sc)
+{
+	if (!sc)
+		return;
+	/*
+	printk("put_snap_context %p %d -> %d\n", sc, atomic_read(&sc->nref),
+	       atomic_read(&sc->nref)-1);
+	*/
+	if (atomic_dec_and_test(&sc->nref)) {
+		/*printk(" deleting snap_context %p\n", sc);*/
+		kfree(sc);
+	}
+}
+
+/*
+ * 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 */
+	int num_prior_parent_snaps;   /*  had prior to parent_since */
+	u64 *snaps;                   /* snaps specific to this realm */
+	int 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 */
+
+	/* 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;
+};
+
+
+
+/*
+ * calculate the number of pages a given length and offset map onto,
+ * if we align the data.
+ */
+static inline int calc_pages_for(u64 off, u64 len)
+{
+	return ((off+len+PAGE_CACHE_SIZE-1) >> PAGE_CACHE_SHIFT) -
+		(off >> PAGE_CACHE_SHIFT);
+}
+
+
+
+/* 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,
+				struct ceph_snap_context *snapc);
+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;
+}
+
+
+/* super.c */
+extern struct kmem_cache *ceph_inode_cachep;
+extern struct kmem_cache *ceph_cap_cachep;
+extern struct kmem_cache *ceph_dentry_cachep;
+extern struct kmem_cache *ceph_file_cachep;
+
+extern const char *ceph_msg_type_name(int type);
+extern int ceph_check_fsid(struct ceph_client *client, struct ceph_fsid *fsid);
+
+#define FSID_FORMAT "%02x%02x%02x%02x-%02x%02x-%02x%02x-%02x%02x-" \
+	"%02x%02x%02x%02x%02x%02x"
+#define PR_FSID(f) (f)->fsid[0], (f)->fsid[1], (f)->fsid[2], (f)->fsid[3], \
+		(f)->fsid[4], (f)->fsid[5], (f)->fsid[6], (f)->fsid[7],    \
+		(f)->fsid[8], (f)->fsid[9], (f)->fsid[10], (f)->fsid[11],  \
+		(f)->fsid[12], (f)->fsid[13], (f)->fsid[14], (f)->fsid[15]
+
+/* 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);
+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);
+
+/* 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)
+{
+	struct inode *inode = &cap->ci->vfs_inode;
+	spin_lock(&inode->i_lock);
+	__ceph_remove_cap(cap);
+	spin_unlock(&inode->i_lock);
+}
+extern void ceph_put_cap(struct ceph_cap *cap);
+
+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, struct dentry *dentry, int datasync);
+extern void ceph_kick_flushing_caps(struct ceph_mds_client *mdsc,
+				    struct ceph_mds_session *session);
+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);
+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 struct dentry *ceph_lookup_open(struct inode *dir, struct dentry *dentry,
+				       struct nameidata *nd, int mode,
+				       int locked_dir);
+extern int ceph_release(struct inode *inode, struct file *filp);
+extern void ceph_release_page_vector(struct page **pages, int num_pages);
+
+/* dir.c */
+extern const struct file_operations ceph_dir_fops;
+extern const struct inode_operations ceph_dir_iops;
+extern 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 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);
+
+/*
+ * 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;
+
+/* debugfs.c */
+extern int ceph_debugfs_init(void);
+extern void ceph_debugfs_cleanup(void);
+extern int ceph_debugfs_client_init(struct ceph_client *client);
+extern void ceph_debugfs_client_cleanup(struct ceph_client *client);
+
+static inline struct inode *get_dentry_parent_inode(struct dentry *dentry)
+{
+	if (dentry && dentry->d_parent)
+		return dentry->d_parent->d_inode;
+
+	return NULL;
+}
+
+#endif /* _FS_CEPH_SUPER_H */

fs/ceph/types.h

@@ -0,0 +1,29 @@
+#ifndef _FS_CEPH_TYPES_H
+#define _FS_CEPH_TYPES_H
+
+/* needed before including ceph_fs.h */
+#include <linux/in.h>
+#include <linux/types.h>
+#include <linux/fcntl.h>
+#include <linux/string.h>
+
+#include "ceph_fs.h"
+#include "ceph_frag.h"
+#include "ceph_hash.h"
+
+/*
+ * Identify inodes by both their ino AND snapshot id (a u64).
+ */
+struct ceph_vino {
+	u64 ino;
+	u64 snap;
+};
+
+
+/* context for the caps reservation mechanism */
+struct ceph_cap_reservation {
+	int count;
+};
+
+
+#endif

fs/ceph/xattr.c

@@ -0,0 +1,844 @@
+#include "ceph_debug.h"
+#include "super.h"
+#include "decode.h"
+
+#include <linux/xattr.h>
+
+static bool ceph_is_valid_xattr(const char *name)
+{
+	return !strncmp(name, XATTR_SECURITY_PREFIX,
+			XATTR_SECURITY_PREFIX_LEN) ||
+	       !strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN) ||
+	       !strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN);
+}
+
+/*
+ * These define virtual xattrs exposing the recursive directory
+ * statistics and layout metadata.
+ */
+struct ceph_vxattr_cb {
+	bool readonly;
+	char *name;
+	size_t (*getxattr_cb)(struct ceph_inode_info *ci, char *val,
+			      size_t size);
+};
+
+/* directories */
+
+static size_t ceph_vxattrcb_entries(struct ceph_inode_info *ci, char *val,
+					size_t size)
+{
+	return snprintf(val, size, "%lld", ci->i_files + ci->i_subdirs);
+}
+
+static size_t ceph_vxattrcb_files(struct ceph_inode_info *ci, char *val,
+				      size_t size)
+{
+	return snprintf(val, size, "%lld", ci->i_files);
+}
+
+static size_t ceph_vxattrcb_subdirs(struct ceph_inode_info *ci, char *val,
+					size_t size)
+{
+	return snprintf(val, size, "%lld", ci->i_subdirs);
+}
+
+static size_t ceph_vxattrcb_rentries(struct ceph_inode_info *ci, char *val,
+					 size_t size)
+{
+	return snprintf(val, size, "%lld", ci->i_rfiles + ci->i_rsubdirs);
+}
+
+static size_t ceph_vxattrcb_rfiles(struct ceph_inode_info *ci, char *val,
+				       size_t size)
+{
+	return snprintf(val, size, "%lld", ci->i_rfiles);
+}
+
+static size_t ceph_vxattrcb_rsubdirs(struct ceph_inode_info *ci, char *val,
+					 size_t size)
+{
+	return snprintf(val, size, "%lld", ci->i_rsubdirs);
+}
+
+static size_t ceph_vxattrcb_rbytes(struct ceph_inode_info *ci, char *val,
+				       size_t size)
+{
+	return snprintf(val, size, "%lld", ci->i_rbytes);
+}
+
+static size_t ceph_vxattrcb_rctime(struct ceph_inode_info *ci, char *val,
+				       size_t size)
+{
+	return snprintf(val, size, "%ld.%ld", (long)ci->i_rctime.tv_sec,
+			(long)ci->i_rctime.tv_nsec);
+}
+
+static struct ceph_vxattr_cb ceph_dir_vxattrs[] = {
+	{ true, "user.ceph.dir.entries", ceph_vxattrcb_entries},
+	{ true, "user.ceph.dir.files", ceph_vxattrcb_files},
+	{ true, "user.ceph.dir.subdirs", ceph_vxattrcb_subdirs},
+	{ true, "user.ceph.dir.rentries", ceph_vxattrcb_rentries},
+	{ true, "user.ceph.dir.rfiles", ceph_vxattrcb_rfiles},
+	{ true, "user.ceph.dir.rsubdirs", ceph_vxattrcb_rsubdirs},
+	{ true, "user.ceph.dir.rbytes", ceph_vxattrcb_rbytes},
+	{ true, "user.ceph.dir.rctime", ceph_vxattrcb_rctime},
+	{ true, NULL, NULL }
+};
+
+/* files */
+
+static size_t ceph_vxattrcb_layout(struct ceph_inode_info *ci, char *val,
+				   size_t size)
+{
+	int ret;
+
+	ret = snprintf(val, size,
+		"chunk_bytes=%lld\nstripe_count=%lld\nobject_size=%lld\n",
+		(unsigned long long)ceph_file_layout_su(ci->i_layout),
+		(unsigned long long)ceph_file_layout_stripe_count(ci->i_layout),
+		(unsigned long long)ceph_file_layout_object_size(ci->i_layout));
+	if (ceph_file_layout_pg_preferred(ci->i_layout))
+		ret += snprintf(val + ret, size, "preferred_osd=%lld\n",
+			    (unsigned long long)ceph_file_layout_pg_preferred(
+				    ci->i_layout));
+	return ret;
+}
+
+static struct ceph_vxattr_cb ceph_file_vxattrs[] = {
+	{ true, "user.ceph.layout", ceph_vxattrcb_layout},
+	{ NULL, NULL }
+};
+
+static struct ceph_vxattr_cb *ceph_inode_vxattrs(struct inode *inode)
+{
+	if (S_ISDIR(inode->i_mode))
+		return ceph_dir_vxattrs;
+	else if (S_ISREG(inode->i_mode))
+		return ceph_file_vxattrs;
+	return NULL;
+}
+
+static struct ceph_vxattr_cb *ceph_match_vxattr(struct ceph_vxattr_cb *vxattr,
+						const char *name)
+{
+	do {
+		if (strcmp(vxattr->name, name) == 0)
+			return vxattr;
+		vxattr++;
+	} while (vxattr->name);
+	return NULL;
+}
+
+static int __set_xattr(struct ceph_inode_info *ci,
+			   const char *name, int name_len,
+			   const char *val, int val_len,
+			   int dirty,
+			   int should_free_name, int should_free_val,
+			   struct ceph_inode_xattr **newxattr)
+{
+	struct rb_node **p;
+	struct rb_node *parent = NULL;
+	struct ceph_inode_xattr *xattr = NULL;
+	int c;
+	int new = 0;
+
+	p = &ci->i_xattrs.index.rb_node;
+	while (*p) {
+		parent = *p;
+		xattr = rb_entry(parent, struct ceph_inode_xattr, node);
+		c = strncmp(name, xattr->name, min(name_len, xattr->name_len));
+		if (c < 0)
+			p = &(*p)->rb_left;
+		else if (c > 0)
+			p = &(*p)->rb_right;
+		else {
+			if (name_len == xattr->name_len)
+				break;
+			else if (name_len < xattr->name_len)
+				p = &(*p)->rb_left;
+			else
+				p = &(*p)->rb_right;
+		}
+		xattr = NULL;
+	}
+
+	if (!xattr) {
+		new = 1;
+		xattr = *newxattr;
+		xattr->name = name;
+		xattr->name_len = name_len;
+		xattr->should_free_name = should_free_name;
+
+		ci->i_xattrs.count++;
+		dout("__set_xattr count=%d\n", ci->i_xattrs.count);
+	} else {
+		kfree(*newxattr);
+		*newxattr = NULL;
+		if (xattr->should_free_val)
+			kfree((void *)xattr->val);
+
+		if (should_free_name) {
+			kfree((void *)name);
+			name = xattr->name;
+		}
+		ci->i_xattrs.names_size -= xattr->name_len;
+		ci->i_xattrs.vals_size -= xattr->val_len;
+	}
+	if (!xattr) {
+		pr_err("__set_xattr ENOMEM on %p %llx.%llx xattr %s=%s\n",
+		       &ci->vfs_inode, ceph_vinop(&ci->vfs_inode), name,
+		       xattr->val);
+		return -ENOMEM;
+	}
+	ci->i_xattrs.names_size += name_len;
+	ci->i_xattrs.vals_size += val_len;
+	if (val)
+		xattr->val = val;
+	else
+		xattr->val = "";
+
+	xattr->val_len = val_len;
+	xattr->dirty = dirty;
+	xattr->should_free_val = (val && should_free_val);
+
+	if (new) {
+		rb_link_node(&xattr->node, parent, p);
+		rb_insert_color(&xattr->node, &ci->i_xattrs.index);
+		dout("__set_xattr_val p=%p\n", p);
+	}
+
+	dout("__set_xattr_val added %llx.%llx xattr %p %s=%.*s\n",
+	     ceph_vinop(&ci->vfs_inode), xattr, name, val_len, val);
+
+	return 0;
+}
+
+static struct ceph_inode_xattr *__get_xattr(struct ceph_inode_info *ci,
+			   const char *name)
+{
+	struct rb_node **p;
+	struct rb_node *parent = NULL;
+	struct ceph_inode_xattr *xattr = NULL;
+	int c;
+
+	p = &ci->i_xattrs.index.rb_node;
+	while (*p) {
+		parent = *p;
+		xattr = rb_entry(parent, struct ceph_inode_xattr, node);
+		c = strncmp(name, xattr->name, xattr->name_len);
+		if (c < 0)
+			p = &(*p)->rb_left;
+		else if (c > 0)
+			p = &(*p)->rb_right;
+		else {
+			dout("__get_xattr %s: found %.*s\n", name,
+			     xattr->val_len, xattr->val);
+			return xattr;
+		}
+	}
+
+	dout("__get_xattr %s: not found\n", name);
+
+	return NULL;
+}
+
+static void __free_xattr(struct ceph_inode_xattr *xattr)
+{
+	BUG_ON(!xattr);
+
+	if (xattr->should_free_name)
+		kfree((void *)xattr->name);
+	if (xattr->should_free_val)
+		kfree((void *)xattr->val);
+
+	kfree(xattr);
+}
+
+static int __remove_xattr(struct ceph_inode_info *ci,
+			  struct ceph_inode_xattr *xattr)
+{
+	if (!xattr)
+		return -EOPNOTSUPP;
+
+	rb_erase(&xattr->node, &ci->i_xattrs.index);
+
+	if (xattr->should_free_name)
+		kfree((void *)xattr->name);
+	if (xattr->should_free_val)
+		kfree((void *)xattr->val);
+
+	ci->i_xattrs.names_size -= xattr->name_len;
+	ci->i_xattrs.vals_size -= xattr->val_len;
+	ci->i_xattrs.count--;
+	kfree(xattr);
+
+	return 0;
+}
+
+static int __remove_xattr_by_name(struct ceph_inode_info *ci,
+			   const char *name)
+{
+	struct rb_node **p;
+	struct ceph_inode_xattr *xattr;
+	int err;
+
+	p = &ci->i_xattrs.index.rb_node;
+	xattr = __get_xattr(ci, name);
+	err = __remove_xattr(ci, xattr);
+	return err;
+}
+
+static char *__copy_xattr_names(struct ceph_inode_info *ci,
+				char *dest)
+{
+	struct rb_node *p;
+	struct ceph_inode_xattr *xattr = NULL;
+
+	p = rb_first(&ci->i_xattrs.index);
+	dout("__copy_xattr_names count=%d\n", ci->i_xattrs.count);
+
+	while (p) {
+		xattr = rb_entry(p, struct ceph_inode_xattr, node);
+		memcpy(dest, xattr->name, xattr->name_len);
+		dest[xattr->name_len] = '\0';
+
+		dout("dest=%s %p (%s) (%d/%d)\n", dest, xattr, xattr->name,
+		     xattr->name_len, ci->i_xattrs.names_size);
+
+		dest += xattr->name_len + 1;
+		p = rb_next(p);
+	}
+
+	return dest;
+}
+
+void __ceph_destroy_xattrs(struct ceph_inode_info *ci)
+{
+	struct rb_node *p, *tmp;
+	struct ceph_inode_xattr *xattr = NULL;
+
+	p = rb_first(&ci->i_xattrs.index);
+
+	dout("__ceph_destroy_xattrs p=%p\n", p);
+
+	while (p) {
+		xattr = rb_entry(p, struct ceph_inode_xattr, node);
+		tmp = p;
+		p = rb_next(tmp);
+		dout("__ceph_destroy_xattrs next p=%p (%.*s)\n", p,
+		     xattr->name_len, xattr->name);
+		rb_erase(tmp, &ci->i_xattrs.index);
+
+		__free_xattr(xattr);
+	}
+
+	ci->i_xattrs.names_size = 0;
+	ci->i_xattrs.vals_size = 0;
+	ci->i_xattrs.index_version = 0;
+	ci->i_xattrs.count = 0;
+	ci->i_xattrs.index = RB_ROOT;
+}
+
+static int __build_xattrs(struct inode *inode)
+{
+	u32 namelen;
+	u32 numattr = 0;
+	void *p, *end;
+	u32 len;
+	const char *name, *val;
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	int xattr_version;
+	struct ceph_inode_xattr **xattrs = NULL;
+	int err = 0;
+	int i;
+
+	dout("__build_xattrs() len=%d\n",
+	     ci->i_xattrs.blob ? (int)ci->i_xattrs.blob->vec.iov_len : 0);
+
+	if (ci->i_xattrs.index_version >= ci->i_xattrs.version)
+		return 0; /* already built */
+
+	__ceph_destroy_xattrs(ci);
+
+start:
+	/* updated internal xattr rb tree */
+	if (ci->i_xattrs.blob && ci->i_xattrs.blob->vec.iov_len > 4) {
+		p = ci->i_xattrs.blob->vec.iov_base;
+		end = p + ci->i_xattrs.blob->vec.iov_len;
+		ceph_decode_32_safe(&p, end, numattr, bad);
+		xattr_version = ci->i_xattrs.version;
+		spin_unlock(&inode->i_lock);
+
+		xattrs = kcalloc(numattr, sizeof(struct ceph_xattr *),
+				 GFP_NOFS);
+		err = -ENOMEM;
+		if (!xattrs)
+			goto bad_lock;
+		memset(xattrs, 0, numattr*sizeof(struct ceph_xattr *));
+		for (i = 0; i < numattr; i++) {
+			xattrs[i] = kmalloc(sizeof(struct ceph_inode_xattr),
+					    GFP_NOFS);
+			if (!xattrs[i])
+				goto bad_lock;
+		}
+
+		spin_lock(&inode->i_lock);
+		if (ci->i_xattrs.version != xattr_version) {
+			/* lost a race, retry */
+			for (i = 0; i < numattr; i++)
+				kfree(xattrs[i]);
+			kfree(xattrs);
+			goto start;
+		}
+		err = -EIO;
+		while (numattr--) {
+			ceph_decode_32_safe(&p, end, len, bad);
+			namelen = len;
+			name = p;
+			p += len;
+			ceph_decode_32_safe(&p, end, len, bad);
+			val = p;
+			p += len;
+
+			err = __set_xattr(ci, name, namelen, val, len,
+					  0, 0, 0, &xattrs[numattr]);
+
+			if (err < 0)
+				goto bad;
+		}
+		kfree(xattrs);
+	}
+	ci->i_xattrs.index_version = ci->i_xattrs.version;
+	ci->i_xattrs.dirty = false;
+
+	return err;
+bad_lock:
+	spin_lock(&inode->i_lock);
+bad:
+	if (xattrs) {
+		for (i = 0; i < numattr; i++)
+			kfree(xattrs[i]);
+		kfree(xattrs);
+	}
+	ci->i_xattrs.names_size = 0;
+	return err;
+}
+
+static int __get_required_blob_size(struct ceph_inode_info *ci, int name_size,
+				    int val_size)
+{
+	/*
+	 * 4 bytes for the length, and additional 4 bytes per each xattr name,
+	 * 4 bytes per each value
+	 */
+	int size = 4 + ci->i_xattrs.count*(4 + 4) +
+			     ci->i_xattrs.names_size +
+			     ci->i_xattrs.vals_size;
+	dout("__get_required_blob_size c=%d names.size=%d vals.size=%d\n",
+	     ci->i_xattrs.count, ci->i_xattrs.names_size,
+	     ci->i_xattrs.vals_size);
+
+	if (name_size)
+		size += 4 + 4 + name_size + val_size;
+
+	return size;
+}
+
+/*
+ * If there are dirty xattrs, reencode xattrs into the prealloc_blob
+ * and swap into place.
+ */
+void __ceph_build_xattrs_blob(struct ceph_inode_info *ci)
+{
+	struct rb_node *p;
+	struct ceph_inode_xattr *xattr = NULL;
+	void *dest;
+
+	dout("__build_xattrs_blob %p\n", &ci->vfs_inode);
+	if (ci->i_xattrs.dirty) {
+		int need = __get_required_blob_size(ci, 0, 0);
+
+		BUG_ON(need > ci->i_xattrs.prealloc_blob->alloc_len);
+
+		p = rb_first(&ci->i_xattrs.index);
+		dest = ci->i_xattrs.prealloc_blob->vec.iov_base;
+
+		ceph_encode_32(&dest, ci->i_xattrs.count);
+		while (p) {
+			xattr = rb_entry(p, struct ceph_inode_xattr, node);
+
+			ceph_encode_32(&dest, xattr->name_len);
+			memcpy(dest, xattr->name, xattr->name_len);
+			dest += xattr->name_len;
+			ceph_encode_32(&dest, xattr->val_len);
+			memcpy(dest, xattr->val, xattr->val_len);
+			dest += xattr->val_len;
+
+			p = rb_next(p);
+		}
+
+		/* adjust buffer len; it may be larger than we need */
+		ci->i_xattrs.prealloc_blob->vec.iov_len =
+			dest - ci->i_xattrs.prealloc_blob->vec.iov_base;
+
+		if (ci->i_xattrs.blob)
+			ceph_buffer_put(ci->i_xattrs.blob);
+		ci->i_xattrs.blob = ci->i_xattrs.prealloc_blob;
+		ci->i_xattrs.prealloc_blob = NULL;
+		ci->i_xattrs.dirty = false;
+	}
+}
+
+ssize_t ceph_getxattr(struct dentry *dentry, const char *name, void *value,
+		      size_t size)
+{
+	struct inode *inode = dentry->d_inode;
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct ceph_vxattr_cb *vxattrs = ceph_inode_vxattrs(inode);
+	int err;
+	struct ceph_inode_xattr *xattr;
+	struct ceph_vxattr_cb *vxattr = NULL;
+
+	if (!ceph_is_valid_xattr(name))
+		return -ENODATA;
+
+	/* let's see if a virtual xattr was requested */
+	if (vxattrs)
+		vxattr = ceph_match_vxattr(vxattrs, name);
+
+	spin_lock(&inode->i_lock);
+	dout("getxattr %p ver=%lld index_ver=%lld\n", inode,
+	     ci->i_xattrs.version, ci->i_xattrs.index_version);
+
+	if (__ceph_caps_issued_mask(ci, CEPH_CAP_XATTR_SHARED, 1) &&
+	    (ci->i_xattrs.index_version >= ci->i_xattrs.version)) {
+		goto get_xattr;
+	} else {
+		spin_unlock(&inode->i_lock);
+		/* get xattrs from mds (if we don't already have them) */
+		err = ceph_do_getattr(inode, CEPH_STAT_CAP_XATTR);
+		if (err)
+			return err;
+	}
+
+	spin_lock(&inode->i_lock);
+
+	if (vxattr && vxattr->readonly) {
+		err = vxattr->getxattr_cb(ci, value, size);
+		goto out;
+	}
+
+	err = __build_xattrs(inode);
+	if (err < 0)
+		goto out;
+
+get_xattr:
+	err = -ENODATA;  /* == ENOATTR */
+	xattr = __get_xattr(ci, name);
+	if (!xattr) {
+		if (vxattr)
+			err = vxattr->getxattr_cb(ci, value, size);
+		goto out;
+	}
+
+	err = -ERANGE;
+	if (size && size < xattr->val_len)
+		goto out;
+
+	err = xattr->val_len;
+	if (size == 0)
+		goto out;
+
+	memcpy(value, xattr->val, xattr->val_len);
+
+out:
+	spin_unlock(&inode->i_lock);
+	return err;
+}
+
+ssize_t ceph_listxattr(struct dentry *dentry, char *names, size_t size)
+{
+	struct inode *inode = dentry->d_inode;
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct ceph_vxattr_cb *vxattrs = ceph_inode_vxattrs(inode);
+	u32 vir_namelen = 0;
+	u32 namelen;
+	int err;
+	u32 len;
+	int i;
+
+	spin_lock(&inode->i_lock);
+	dout("listxattr %p ver=%lld index_ver=%lld\n", inode,
+	     ci->i_xattrs.version, ci->i_xattrs.index_version);
+
+	if (__ceph_caps_issued_mask(ci, CEPH_CAP_XATTR_SHARED, 1) &&
+	    (ci->i_xattrs.index_version > ci->i_xattrs.version)) {
+		goto list_xattr;
+	} else {
+		spin_unlock(&inode->i_lock);
+		err = ceph_do_getattr(inode, CEPH_STAT_CAP_XATTR);
+		if (err)
+			return err;
+	}
+
+	spin_lock(&inode->i_lock);
+
+	err = __build_xattrs(inode);
+	if (err < 0)
+		goto out;
+
+list_xattr:
+	vir_namelen = 0;
+	/* include virtual dir xattrs */
+	if (vxattrs)
+		for (i = 0; vxattrs[i].name; i++)
+			vir_namelen += strlen(vxattrs[i].name) + 1;
+	/* adding 1 byte per each variable due to the null termination */
+	namelen = vir_namelen + ci->i_xattrs.names_size + ci->i_xattrs.count;
+	err = -ERANGE;
+	if (size && namelen > size)
+		goto out;
+
+	err = namelen;
+	if (size == 0)
+		goto out;
+
+	names = __copy_xattr_names(ci, names);
+
+	/* virtual xattr names, too */
+	if (vxattrs)
+		for (i = 0; vxattrs[i].name; i++) {
+			len = sprintf(names, "%s", vxattrs[i].name);
+			names += len + 1;
+		}
+
+out:
+	spin_unlock(&inode->i_lock);
+	return err;
+}
+
+static int ceph_sync_setxattr(struct dentry *dentry, const char *name,
+			      const char *value, size_t size, int flags)
+{
+	struct ceph_client *client = ceph_client(dentry->d_sb);
+	struct inode *inode = dentry->d_inode;
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct inode *parent_inode = dentry->d_parent->d_inode;
+	struct ceph_mds_request *req;
+	struct ceph_mds_client *mdsc = &client->mdsc;
+	int err;
+	int i, nr_pages;
+	struct page **pages = NULL;
+	void *kaddr;
+
+	/* copy value into some pages */
+	nr_pages = calc_pages_for(0, size);
+	if (nr_pages) {
+		pages = kmalloc(sizeof(pages[0])*nr_pages, GFP_NOFS);
+		if (!pages)
+			return -ENOMEM;
+		err = -ENOMEM;
+		for (i = 0; i < nr_pages; i++) {
+			pages[i] = alloc_page(GFP_NOFS);
+			if (!pages[i]) {
+				nr_pages = i;
+				goto out;
+			}
+			kaddr = kmap(pages[i]);
+			memcpy(kaddr, value + i*PAGE_CACHE_SIZE,
+			       min(PAGE_CACHE_SIZE, size-i*PAGE_CACHE_SIZE));
+		}
+	}
+
+	dout("setxattr value=%.*s\n", (int)size, value);
+
+	/* do request */
+	req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_SETXATTR,
+				       USE_AUTH_MDS);
+	if (IS_ERR(req)) {
+		err = PTR_ERR(req);
+		goto out;
+	}
+	req->r_inode = igrab(inode);
+	req->r_inode_drop = CEPH_CAP_XATTR_SHARED;
+	req->r_num_caps = 1;
+	req->r_args.setxattr.flags = cpu_to_le32(flags);
+	req->r_path2 = kstrdup(name, GFP_NOFS);
+
+	req->r_pages = pages;
+	req->r_num_pages = nr_pages;
+	req->r_data_len = size;
+
+	dout("xattr.ver (before): %lld\n", ci->i_xattrs.version);
+	err = ceph_mdsc_do_request(mdsc, parent_inode, req);
+	ceph_mdsc_put_request(req);
+	dout("xattr.ver (after): %lld\n", ci->i_xattrs.version);
+
+out:
+	if (pages) {
+		for (i = 0; i < nr_pages; i++)
+			__free_page(pages[i]);
+		kfree(pages);
+	}
+	return err;
+}
+
+int ceph_setxattr(struct dentry *dentry, const char *name,
+		  const void *value, size_t size, int flags)
+{
+	struct inode *inode = dentry->d_inode;
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct ceph_vxattr_cb *vxattrs = ceph_inode_vxattrs(inode);
+	int err;
+	int name_len = strlen(name);
+	int val_len = size;
+	char *newname = NULL;
+	char *newval = NULL;
+	struct ceph_inode_xattr *xattr = NULL;
+	int issued;
+	int required_blob_size;
+
+	if (ceph_snap(inode) != CEPH_NOSNAP)
+		return -EROFS;
+
+	if (!ceph_is_valid_xattr(name))
+		return -EOPNOTSUPP;
+
+	if (vxattrs) {
+		struct ceph_vxattr_cb *vxattr =
+			ceph_match_vxattr(vxattrs, name);
+		if (vxattr && vxattr->readonly)
+			return -EOPNOTSUPP;
+	}
+
+	/* preallocate memory for xattr name, value, index node */
+	err = -ENOMEM;
+	newname = kmalloc(name_len + 1, GFP_NOFS);
+	if (!newname)
+		goto out;
+	memcpy(newname, name, name_len + 1);
+
+	if (val_len) {
+		newval = kmalloc(val_len + 1, GFP_NOFS);
+		if (!newval)
+			goto out;
+		memcpy(newval, value, val_len);
+		newval[val_len] = '\0';
+	}
+
+	xattr = kmalloc(sizeof(struct ceph_inode_xattr), GFP_NOFS);
+	if (!xattr)
+		goto out;
+
+	spin_lock(&inode->i_lock);
+retry:
+	issued = __ceph_caps_issued(ci, NULL);
+	if (!(issued & CEPH_CAP_XATTR_EXCL))
+		goto do_sync;
+	__build_xattrs(inode);
+
+	required_blob_size = __get_required_blob_size(ci, name_len, val_len);
+
+	if (!ci->i_xattrs.prealloc_blob ||
+	    required_blob_size > ci->i_xattrs.prealloc_blob->alloc_len) {
+		struct ceph_buffer *blob = NULL;
+
+		spin_unlock(&inode->i_lock);
+		dout(" preaallocating new blob size=%d\n", required_blob_size);
+		blob = ceph_buffer_new(required_blob_size, GFP_NOFS);
+		if (!blob)
+			goto out;
+		spin_lock(&inode->i_lock);
+		if (ci->i_xattrs.prealloc_blob)
+			ceph_buffer_put(ci->i_xattrs.prealloc_blob);
+		ci->i_xattrs.prealloc_blob = blob;
+		goto retry;
+	}
+
+	dout("setxattr %p issued %s\n", inode, ceph_cap_string(issued));
+	err = __set_xattr(ci, newname, name_len, newval,
+			  val_len, 1, 1, 1, &xattr);
+	__ceph_mark_dirty_caps(ci, CEPH_CAP_XATTR_EXCL);
+	ci->i_xattrs.dirty = true;
+	inode->i_ctime = CURRENT_TIME;
+	spin_unlock(&inode->i_lock);
+
+	return err;
+
+do_sync:
+	spin_unlock(&inode->i_lock);
+	err = ceph_sync_setxattr(dentry, name, value, size, flags);
+out:
+	kfree(newname);
+	kfree(newval);
+	kfree(xattr);
+	return err;
+}
+
+static int ceph_send_removexattr(struct dentry *dentry, const char *name)
+{
+	struct ceph_client *client = ceph_client(dentry->d_sb);
+	struct ceph_mds_client *mdsc = &client->mdsc;
+	struct inode *inode = dentry->d_inode;
+	struct inode *parent_inode = dentry->d_parent->d_inode;
+	struct ceph_mds_request *req;
+	int err;
+
+	req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_RMXATTR,
+				       USE_AUTH_MDS);
+	if (IS_ERR(req))
+		return PTR_ERR(req);
+	req->r_inode = igrab(inode);
+	req->r_inode_drop = CEPH_CAP_XATTR_SHARED;
+	req->r_num_caps = 1;
+	req->r_path2 = kstrdup(name, GFP_NOFS);
+
+	err = ceph_mdsc_do_request(mdsc, parent_inode, req);
+	ceph_mdsc_put_request(req);
+	return err;
+}
+
+int ceph_removexattr(struct dentry *dentry, const char *name)
+{
+	struct inode *inode = dentry->d_inode;
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct ceph_vxattr_cb *vxattrs = ceph_inode_vxattrs(inode);
+	int issued;
+	int err;
+
+	if (ceph_snap(inode) != CEPH_NOSNAP)
+		return -EROFS;
+
+	if (!ceph_is_valid_xattr(name))
+		return -EOPNOTSUPP;
+
+	if (vxattrs) {
+		struct ceph_vxattr_cb *vxattr =
+			ceph_match_vxattr(vxattrs, name);
+		if (vxattr && vxattr->readonly)
+			return -EOPNOTSUPP;
+	}
+
+	spin_lock(&inode->i_lock);
+	__build_xattrs(inode);
+	issued = __ceph_caps_issued(ci, NULL);
+	dout("removexattr %p issued %s\n", inode, ceph_cap_string(issued));
+
+	if (!(issued & CEPH_CAP_XATTR_EXCL))
+		goto do_sync;
+
+	err = __remove_xattr_by_name(ceph_inode(inode), name);
+	__ceph_mark_dirty_caps(ci, CEPH_CAP_XATTR_EXCL);
+	ci->i_xattrs.dirty = true;
+	inode->i_ctime = CURRENT_TIME;
+
+	spin_unlock(&inode->i_lock);
+
+	return err;
+do_sync:
+	spin_unlock(&inode->i_lock);
+	err = ceph_send_removexattr(dentry, name);
+	return err;
+}
+