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: (22 commits)
  ceph: do not carry i_lock for readdir from dcache
  fs/ceph/xattr.c: Use kmemdup
  rbd: passing wrong variable to bvec_kunmap_irq()
  rbd: null vs ERR_PTR
  ceph: fix num_pages_free accounting in pagelist
  ceph: add CEPH_MDS_OP_SETDIRLAYOUT and associated ioctl.
  ceph: don't crash when passed bad mount options
  ceph: fix debugfs warnings
  block: rbd: removing unnecessary test
  block: rbd: fixed may leaks
  ceph: switch from BKL to lock_flocks()
  ceph: preallocate flock state without locks held
  ceph: add pagelist_reserve, pagelist_truncate, pagelist_set_cursor
  ceph: use mapping->nrpages to determine if mapping is empty
  ceph: only invalidate on check_caps if we actually have pages
  ceph: do not hide .snap in root directory
  rbd: introduce rados block device (rbd), based on libceph
  ceph: factor out libceph from Ceph file system
  ceph-rbd: osdc support for osd call and rollback operations
  ceph: messenger and osdc changes for rbd
  ...

29 files changed, 10750 insertions, 0 deletions

diff --git a/net/Kconfig b/net/Kconfig
index e926884c167..55fd82e9ffd 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -293,6 +293,7 @@ source "net/wimax/Kconfig"
 source "net/rfkill/Kconfig"
 source "net/9p/Kconfig"
 source "net/caif/Kconfig"
+source "net/ceph/Kconfig"
 
 
 endif   # if NET
diff --git a/net/Makefile b/net/Makefile
index ea60fbce9b1..6b7bfd7f141 100644
--- a/net/Makefile
+++ b/net/Makefile
@@ -68,3 +68,4 @@ obj-$(CONFIG_SYSCTL)		+= sysctl_net.o
 endif
 obj-$(CONFIG_WIMAX)		+= wimax/
 obj-$(CONFIG_DNS_RESOLVER)	+= dns_resolver/
+obj-$(CONFIG_CEPH_LIB)		+= ceph/
diff --git a/net/ceph/Kconfig b/net/ceph/Kconfig
new file mode 100644
index 00000000000..ad424049b0c
--- /dev/null
+++ b/net/ceph/Kconfig
@@ -0,0 +1,28 @@
+config CEPH_LIB
+        tristate "Ceph core library (EXPERIMENTAL)"
+	depends on INET && EXPERIMENTAL
+	select LIBCRC32C
+	select CRYPTO_AES
+	select CRYPTO
+	default n
+	help
+	  Choose Y or M here to include cephlib, which provides the
+	  common functionality to both the Ceph filesystem and
+	  to the rados block device (rbd).
+
+	  More information at http://ceph.newdream.net/.
+
+	  If unsure, say N.
+
+config CEPH_LIB_PRETTYDEBUG
+	bool "Include file:line in ceph debug output"
+	depends on CEPH_LIB
+	default n
+	help
+	  If you say Y here, debug output will include a filename and
+	  line to aid debugging.  This increases kernel size and slows
+	  execution slightly when debug call sites are enabled (e.g.,
+	  via CONFIG_DYNAMIC_DEBUG).
+
+	  If unsure, say N.
+
diff --git a/net/ceph/Makefile b/net/ceph/Makefile
new file mode 100644
index 00000000000..aab1cabb803
--- /dev/null
+++ b/net/ceph/Makefile
@@ -0,0 +1,37 @@
+#
+# Makefile for CEPH filesystem.
+#
+
+ifneq ($(KERNELRELEASE),)
+
+obj-$(CONFIG_CEPH_LIB) += libceph.o
+
+libceph-objs := ceph_common.o messenger.o msgpool.o buffer.o pagelist.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 \
+	pagevec.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_LIB=m modules
+
+modules_install:
+	$(MAKE) -C $(KERNELDIR) M=$(PWD) CONFIG_CEPH_LIB=m modules_install
+
+clean:
+	$(MAKE) -C $(KERNELDIR) M=$(PWD) clean
+
+endif
diff --git a/net/ceph/armor.c b/net/ceph/armor.c
new file mode 100644
index 00000000000..eb2a666b0be
--- /dev/null
+++ b/net/ceph/armor.c
@@ -0,0 +1,103 @@
+
+#include <linux/errno.h>
+
+int ceph_armor(char *dst, const char *src, const char *end);
+int ceph_unarmor(char *dst, const char *src, const char *end);
+
+/*
+ * base64 encode/decode.
+ */
+
+static 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;
+}
diff --git a/net/ceph/auth.c b/net/ceph/auth.c
new file mode 100644
index 00000000000..549c1f43e1d
--- /dev/null
+++ b/net/ceph/auth.c
@@ -0,0 +1,259 @@
+#include <linux/ceph/ceph_debug.h>
+
+#include <linux/module.h>
+#include <linux/err.h>
+#include <linux/slab.h>
+
+#include <linux/ceph/types.h>
+#include <linux/ceph/decode.h>
+#include <linux/ceph/libceph.h>
+#include <linux/ceph/messenger.h>
+#include "auth_none.h"
+#include "auth_x.h"
+
+
+/*
+ * get protocol handler
+ */
+static u32 supported_protocols[] = {
+	CEPH_AUTH_NONE,
+	CEPH_AUTH_CEPHX
+};
+
+static 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;
+}
+
+static 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 auth method %s request\n", ret,
+		       ac->ops->name);
+		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("auth method '%s' error %d\n", ac->ops->name, 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->should_authenticate(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);
+}
diff --git a/net/ceph/auth_none.c b/net/ceph/auth_none.c
new file mode 100644
index 00000000000..214c2bb43d6
--- /dev/null
+++ b/net/ceph/auth_none.c
@@ -0,0 +1,132 @@
+
+#include <linux/ceph/ceph_debug.h>
+
+#include <linux/err.h>
+#include <linux/module.h>
+#include <linux/random.h>
+#include <linux/slab.h>
+
+#include <linux/ceph/decode.h>
+#include <linux/ceph/auth.h>
+
+#include "auth_none.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;
+}
+
+static int should_authenticate(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 = {
+	.name = "none",
+	.reset = reset,
+	.destroy = destroy,
+	.is_authenticated = is_authenticated,
+	.should_authenticate = should_authenticate,
+	.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;
+}
+
diff --git a/net/ceph/auth_none.h b/net/ceph/auth_none.h
new file mode 100644
index 00000000000..ed7d088b1bc
--- /dev/null
+++ b/net/ceph/auth_none.h
@@ -0,0 +1,29 @@
+#ifndef _FS_CEPH_AUTH_NONE_H
+#define _FS_CEPH_AUTH_NONE_H
+
+#include <linux/slab.h>
+#include <linux/ceph/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
+
diff --git a/net/ceph/auth_x.c b/net/ceph/auth_x.c
new file mode 100644
index 00000000000..7fd5dfcf6e1
--- /dev/null
+++ b/net/ceph/auth_x.c
@@ -0,0 +1,688 @@
+
+#include <linux/ceph/ceph_debug.h>
+
+#include <linux/err.h>
+#include <linux/module.h>
+#include <linux/random.h>
+#include <linux/slab.h>
+
+#include <linux/ceph/decode.h>
+#include <linux/ceph/auth.h>
+
+#include "crypto.h"
+#include "auth_x.h"
+#include "auth_x_protocol.h"
+
+#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_should_authenticate(struct ceph_auth_client *ac)
+{
+	struct ceph_x_info *xi = ac->private;
+	int need;
+
+	ceph_x_validate_tickets(ac, &need);
+	dout("ceph_x_should_authenticate want=%d need=%d have=%d\n",
+	     ac->want_keys, need, xi->have_keys);
+	return need != 0;
+}
+
+static int ceph_x_encrypt_buflen(int ilen)
+{
+	return sizeof(struct ceph_x_encrypt_header) + ilen + 16 +
+		sizeof(u32);
+}
+
+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
+ */
+static 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 reply_struct_v;
+
+	dbuf = kmalloc(TEMP_TICKET_BUF_LEN, GFP_NOFS);
+	if (!dbuf)
+		return -ENOMEM;
+
+	ret = -ENOMEM;
+	ticket_buf = kmalloc(TEMP_TICKET_BUF_LEN, GFP_NOFS);
+	if (!ticket_buf)
+		goto out_dbuf;
+
+	ceph_decode_need(&p, end, 1 + sizeof(u32), bad);
+	reply_struct_v = ceph_decode_8(&p);
+	if (reply_struct_v != 1)
+		goto bad;
+	num = ceph_decode_32(&p);
+	dout("%d tickets\n", num);
+	while (num--) {
+		int type;
+		u8 tkt_struct_v, blob_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;
+		struct ceph_timespec new_validity;
+		struct ceph_crypto_key new_session_key;
+		struct ceph_buffer *new_ticket_blob;
+		unsigned long new_expires, new_renew_after;
+		u64 new_secret_id;
+
+		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));
+
+		tkt_struct_v = ceph_decode_8(&p);
+		if (tkt_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;
+
+		tkt_struct_v = ceph_decode_8(&dp);
+		if (tkt_struct_v != 1)
+			goto bad;
+
+		memcpy(&old_key, &th->session_key, sizeof(old_key));
+		ret = ceph_crypto_key_decode(&new_session_key, &dp, dend);
+		if (ret)
+			goto out;
+
+		ceph_decode_copy(&dp, &new_validity, sizeof(new_validity));
+		ceph_decode_timespec(&validity, &new_validity);
+		new_expires = get_seconds() + validity.tv_sec;
+		new_renew_after = new_expires - (validity.tv_sec / 4);
+		dout(" expires=%lu renew_after=%lu\n", new_expires,
+		     new_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);
+		blob_struct_v = ceph_decode_8(&tp);
+		new_secret_id = ceph_decode_64(&tp);
+		ret = ceph_decode_buffer(&new_ticket_blob, &tp, tpend);
+		if (ret)
+			goto out;
+
+		/* all is well, update our ticket */
+		ceph_crypto_key_destroy(&th->session_key);
+		if (th->ticket_blob)
+			ceph_buffer_put(th->ticket_blob);
+		th->session_key = new_session_key;
+		th->ticket_blob = new_ticket_blob;
+		th->validity = new_validity;
+		th->secret_id = new_secret_id;
+		th->expires = new_expires;
+		th->renew_after = new_renew_after;
+		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:
+	kfree(ticket_buf);
+out_dbuf:
+	kfree(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 maxlen;
+	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);
+
+	maxlen = sizeof(*msg_a) + sizeof(msg_b) +
+		ceph_x_encrypt_buflen(ticket_blob_len);
+	dout("  need len %d\n", maxlen);
+	if (au->buf && au->buf->alloc_len < maxlen) {
+		ceph_buffer_put(au->buf);
+		au->buf = NULL;
+	}
+	if (!au->buf) {
+		au->buf = ceph_buffer_new(maxlen, 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);
+	BUG_ON(au->buf->vec.iov_len > maxlen);
+	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 (IS_ERR(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);
+
+	if (IS_ERR(th))
+		return PTR_ERR(th);
+
+	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 ^= *(__le64 *)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);
+
+		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 = le16_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);
+		if (IS_ERR(th))
+			return PTR_ERR(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 (IS_ERR(th))
+		return PTR_ERR(th);
+	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);
+	}
+
+	if (xi->auth_authorizer.buf)
+		ceph_buffer_put(xi->auth_authorizer.buf);
+
+	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 (!IS_ERR(th))
+		remove_ticket_handler(ac, th);
+}
+
+
+static const struct ceph_auth_client_ops ceph_x_ops = {
+	.name = "x",
+	.is_authenticated = ceph_x_is_authenticated,
+	.should_authenticate = ceph_x_should_authenticate,
+	.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);
+	ret = -ENOMEM;
+	xi = kzalloc(sizeof(*xi), GFP_NOFS);
+	if (!xi)
+		goto out;
+
+	ret = -EINVAL;
+	if (!ac->secret) {
+		pr_err("no secret set (for auth_x protocol)\n");
+		goto out_nomem;
+	}
+
+	ret = ceph_crypto_key_unarmor(&xi->secret, ac->secret);
+	if (ret)
+		goto out_nomem;
+
+	xi->starting = true;
+	xi->ticket_handlers = RB_ROOT;
+
+	ac->protocol = CEPH_AUTH_CEPHX;
+	ac->private = xi;
+	ac->ops = &ceph_x_ops;
+	return 0;
+
+out_nomem:
+	kfree(xi);
+out:
+	return ret;
+}
+
+
diff --git a/net/ceph/auth_x.h b/net/ceph/auth_x.h
new file mode 100644
index 00000000000..e02da7a5c5a
--- /dev/null
+++ b/net/ceph/auth_x.h
@@ -0,0 +1,50 @@
+#ifndef _FS_CEPH_AUTH_X_H
+#define _FS_CEPH_AUTH_X_H
+
+#include <linux/rbtree.h>
+
+#include <linux/ceph/auth.h>
+
+#include "crypto.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
+
diff --git a/net/ceph/auth_x_protocol.h b/net/ceph/auth_x_protocol.h
new file mode 100644
index 00000000000..671d30576c4
--- /dev/null
+++ b/net/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
diff --git a/net/ceph/buffer.c b/net/ceph/buffer.c
new file mode 100644
index 00000000000..53d8abfa25d
--- /dev/null
+++ b/net/ceph/buffer.c
@@ -0,0 +1,68 @@
+
+#include <linux/ceph/ceph_debug.h>
+
+#include <linux/module.h>
+#include <linux/slab.h>
+
+#include <linux/ceph/buffer.h>
+#include <linux/ceph/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;
+}
+EXPORT_SYMBOL(ceph_buffer_new);
+
+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);
+}
+EXPORT_SYMBOL(ceph_buffer_release);
+
+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;
+}
diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c
new file mode 100644
index 00000000000..f3e4a13fea0
--- /dev/null
+++ b/net/ceph/ceph_common.c
@@ -0,0 +1,529 @@
+
+#include <linux/ceph/ceph_debug.h>
+#include <linux/backing-dev.h>
+#include <linux/ctype.h>
+#include <linux/fs.h>
+#include <linux/inet.h>
+#include <linux/in6.h>
+#include <linux/module.h>
+#include <linux/mount.h>
+#include <linux/parser.h>
+#include <linux/sched.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <linux/statfs.h>
+#include <linux/string.h>
+
+
+#include <linux/ceph/libceph.h>
+#include <linux/ceph/debugfs.h>
+#include <linux/ceph/decode.h>
+#include <linux/ceph/mon_client.h>
+#include <linux/ceph/auth.h>
+
+
+
+/*
+ * find filename portion of a path (/foo/bar/baz -> baz)
+ */
+const char *ceph_file_part(const char *s, int len)
+{
+	const char *e = s + len;
+
+	while (e != s && *(e-1) != '/')
+		e--;
+	return e;
+}
+EXPORT_SYMBOL(ceph_file_part);
+
+const char *ceph_msg_type_name(int type)
+{
+	switch (type) {
+	case CEPH_MSG_SHUTDOWN: return "shutdown";
+	case CEPH_MSG_PING: return "ping";
+	case CEPH_MSG_AUTH: return "auth";
+	case CEPH_MSG_AUTH_REPLY: return "auth_reply";
+	case CEPH_MSG_MON_MAP: return "mon_map";
+	case CEPH_MSG_MON_GET_MAP: return "mon_get_map";
+	case CEPH_MSG_MON_SUBSCRIBE: return "mon_subscribe";
+	case CEPH_MSG_MON_SUBSCRIBE_ACK: return "mon_subscribe_ack";
+	case CEPH_MSG_STATFS: return "statfs";
+	case CEPH_MSG_STATFS_REPLY: return "statfs_reply";
+	case CEPH_MSG_MDS_MAP: return "mds_map";
+	case CEPH_MSG_CLIENT_SESSION: return "client_session";
+	case CEPH_MSG_CLIENT_RECONNECT: return "client_reconnect";
+	case CEPH_MSG_CLIENT_REQUEST: return "client_request";
+	case CEPH_MSG_CLIENT_REQUEST_FORWARD: return "client_request_forward";
+	case CEPH_MSG_CLIENT_REPLY: return "client_reply";
+	case CEPH_MSG_CLIENT_CAPS: return "client_caps";
+	case CEPH_MSG_CLIENT_CAPRELEASE: return "client_cap_release";
+	case CEPH_MSG_CLIENT_SNAP: return "client_snap";
+	case CEPH_MSG_CLIENT_LEASE: return "client_lease";
+	case CEPH_MSG_OSD_MAP: return "osd_map";
+	case CEPH_MSG_OSD_OP: return "osd_op";
+	case CEPH_MSG_OSD_OPREPLY: return "osd_opreply";
+	default: return "unknown";
+	}
+}
+EXPORT_SYMBOL(ceph_msg_type_name);
+
+/*
+ * Initially learn our fsid, or verify an fsid matches.
+ */
+int ceph_check_fsid(struct ceph_client *client, struct ceph_fsid *fsid)
+{
+	if (client->have_fsid) {
+		if (ceph_fsid_compare(&client->fsid, fsid)) {
+			pr_err("bad fsid, had %pU got %pU",
+			       &client->fsid, fsid);
+			return -1;
+		}
+	} else {
+		pr_info("client%lld fsid %pU\n", ceph_client_id(client), fsid);
+		memcpy(&client->fsid, fsid, sizeof(*fsid));
+		ceph_debugfs_client_init(client);
+		client->have_fsid = true;
+	}
+	return 0;
+}
+EXPORT_SYMBOL(ceph_check_fsid);
+
+static int strcmp_null(const char *s1, const char *s2)
+{
+	if (!s1 && !s2)
+		return 0;
+	if (s1 && !s2)
+		return -1;
+	if (!s1 && s2)
+		return 1;
+	return strcmp(s1, s2);
+}
+
+int ceph_compare_options(struct ceph_options *new_opt,
+			 struct ceph_client *client)
+{
+	struct ceph_options *opt1 = new_opt;
+	struct ceph_options *opt2 = client->options;
+	int ofs = offsetof(struct ceph_options, mon_addr);
+	int i;
+	int ret;
+
+	ret = memcmp(opt1, opt2, ofs);
+	if (ret)
+		return ret;
+
+	ret = strcmp_null(opt1->name, opt2->name);
+	if (ret)
+		return ret;
+
+	ret = strcmp_null(opt1->secret, opt2->secret);
+	if (ret)
+		return ret;
+
+	/* any matching mon ip implies a match */
+	for (i = 0; i < opt1->num_mon; i++) {
+		if (ceph_monmap_contains(client->monc.monmap,
+				 &opt1->mon_addr[i]))
+			return 0;
+	}
+	return -1;
+}
+EXPORT_SYMBOL(ceph_compare_options);
+
+
+static int parse_fsid(const char *str, struct ceph_fsid *fsid)
+{
+	int i = 0;
+	char tmp[3];
+	int err = -EINVAL;
+	int d;
+
+	dout("parse_fsid '%s'\n", str);
+	tmp[2] = 0;
+	while (*str && i < 16) {
+		if (ispunct(*str)) {
+			str++;
+			continue;
+		}
+		if (!isxdigit(str[0]) || !isxdigit(str[1]))
+			break;
+		tmp[0] = str[0];
+		tmp[1] = str[1];
+		if (sscanf(tmp, "%x", &d) < 1)
+			break;
+		fsid->fsid[i] = d & 0xff;
+		i++;
+		str += 2;
+	}
+
+	if (i == 16)
+		err = 0;
+	dout("parse_fsid ret %d got fsid %pU", err, fsid);
+	return err;
+}
+
+/*
+ * ceph options
+ */
+enum {
+	Opt_osdtimeout,
+	Opt_osdkeepalivetimeout,
+	Opt_mount_timeout,
+	Opt_osd_idle_ttl,
+	Opt_last_int,
+	/* int args above */
+	Opt_fsid,
+	Opt_name,
+	Opt_secret,
+	Opt_ip,
+	Opt_last_string,
+	/* string args above */
+	Opt_noshare,
+	Opt_nocrc,
+};
+
+static match_table_t opt_tokens = {
+	{Opt_osdtimeout, "osdtimeout=%d"},
+	{Opt_osdkeepalivetimeout, "osdkeepalive=%d"},
+	{Opt_mount_timeout, "mount_timeout=%d"},
+	{Opt_osd_idle_ttl, "osd_idle_ttl=%d"},
+	/* int args above */
+	{Opt_fsid, "fsid=%s"},
+	{Opt_name, "name=%s"},
+	{Opt_secret, "secret=%s"},
+	{Opt_ip, "ip=%s"},
+	/* string args above */
+	{Opt_noshare, "noshare"},
+	{Opt_nocrc, "nocrc"},
+	{-1, NULL}
+};
+
+void ceph_destroy_options(struct ceph_options *opt)
+{
+	dout("destroy_options %p\n", opt);
+	kfree(opt->name);
+	kfree(opt->secret);
+	kfree(opt);
+}
+EXPORT_SYMBOL(ceph_destroy_options);
+
+int ceph_parse_options(struct ceph_options **popt, char *options,
+		       const char *dev_name, const char *dev_name_end,
+		       int (*parse_extra_token)(char *c, void *private),
+		       void *private)
+{
+	struct ceph_options *opt;
+	const char *c;
+	int err = -ENOMEM;
+	substring_t argstr[MAX_OPT_ARGS];
+
+	opt = kzalloc(sizeof(*opt), GFP_KERNEL);
+	if (!opt)
+		return err;
+	opt->mon_addr = kcalloc(CEPH_MAX_MON, sizeof(*opt->mon_addr),
+				GFP_KERNEL);
+	if (!opt->mon_addr)
+		goto out;
+
+	dout("parse_options %p options '%s' dev_name '%s'\n", opt, options,
+	     dev_name);
+
+	/* start with defaults */
+	opt->flags = CEPH_OPT_DEFAULT;
+	opt->osd_timeout = CEPH_OSD_TIMEOUT_DEFAULT;
+	opt->osd_keepalive_timeout = CEPH_OSD_KEEPALIVE_DEFAULT;
+	opt->mount_timeout = CEPH_MOUNT_TIMEOUT_DEFAULT; /* seconds */
+	opt->osd_idle_ttl = CEPH_OSD_IDLE_TTL_DEFAULT;   /* seconds */
+
+	/* get mon ip(s) */
+	/* ip1[:port1][,ip2[:port2]...] */
+	err = ceph_parse_ips(dev_name, dev_name_end, opt->mon_addr,
+			     CEPH_MAX_MON, &opt->num_mon);
+	if (err < 0)
+		goto out;
+
+	/* parse mount options */
+	while ((c = strsep(&options, ",")) != NULL) {
+		int token, intval, ret;
+		if (!*c)
+			continue;
+		err = -EINVAL;
+		token = match_token((char *)c, opt_tokens, argstr);
+		if (token < 0 && parse_extra_token) {
+			/* extra? */
+			err = parse_extra_token((char *)c, private);
+			if (err < 0) {
+				pr_err("bad option at '%s'\n", c);
+				goto out;
+			}
+			continue;
+		}
+		if (token < Opt_last_int) {
+			ret = match_int(&argstr[0], &intval);
+			if (ret < 0) {
+				pr_err("bad mount option arg (not int) "
+				       "at '%s'\n", c);
+				continue;
+			}
+			dout("got int token %d val %d\n", token, intval);
+		} else if (token > Opt_last_int && token < Opt_last_string) {
+			dout("got string token %d val %s\n", token,
+			     argstr[0].from);
+		} else {
+			dout("got token %d\n", token);
+		}
+		switch (token) {
+		case Opt_ip:
+			err = ceph_parse_ips(argstr[0].from,
+					     argstr[0].to,
+					     &opt->my_addr,
+					     1, NULL);
+			if (err < 0)
+				goto out;
+			opt->flags |= CEPH_OPT_MYIP;
+			break;
+
+		case Opt_fsid:
+			err = parse_fsid(argstr[0].from, &opt->fsid);
+			if (err == 0)
+				opt->flags |= CEPH_OPT_FSID;
+			break;
+		case Opt_name:
+			opt->name = kstrndup(argstr[0].from,
+					      argstr[0].to-argstr[0].from,
+					      GFP_KERNEL);
+			break;
+		case Opt_secret:
+			opt->secret = kstrndup(argstr[0].from,
+						argstr[0].to-argstr[0].from,
+						GFP_KERNEL);
+			break;
+
+			/* misc */
+		case Opt_osdtimeout:
+			opt->osd_timeout = intval;
+			break;
+		case Opt_osdkeepalivetimeout:
+			opt->osd_keepalive_timeout = intval;
+			break;
+		case Opt_osd_idle_ttl:
+			opt->osd_idle_ttl = intval;
+			break;
+		case Opt_mount_timeout:
+			opt->mount_timeout = intval;
+			break;
+
+		case Opt_noshare:
+			opt->flags |= CEPH_OPT_NOSHARE;
+			break;
+
+		case Opt_nocrc:
+			opt->flags |= CEPH_OPT_NOCRC;
+			break;
+
+		default:
+			BUG_ON(token);
+		}
+	}
+
+	/* success */
+	*popt = opt;
+	return 0;
+
+out:
+	ceph_destroy_options(opt);
+	return err;
+}
+EXPORT_SYMBOL(ceph_parse_options);
+
+u64 ceph_client_id(struct ceph_client *client)
+{
+	return client->monc.auth->global_id;
+}
+EXPORT_SYMBOL(ceph_client_id);
+
+/*
+ * create a fresh client instance
+ */
+struct ceph_client *ceph_create_client(struct ceph_options *opt, void *private)
+{
+	struct ceph_client *client;
+	int err = -ENOMEM;
+
+	client = kzalloc(sizeof(*client), GFP_KERNEL);
+	if (client == NULL)
+		return ERR_PTR(-ENOMEM);
+
+	client->private = private;
+	client->options = opt;
+
+	mutex_init(&client->mount_mutex);
+	init_waitqueue_head(&client->auth_wq);
+	client->auth_err = 0;
+
+	client->extra_mon_dispatch = NULL;
+	client->supported_features = CEPH_FEATURE_SUPPORTED_DEFAULT;
+	client->required_features = CEPH_FEATURE_REQUIRED_DEFAULT;
+
+	client->msgr = NULL;
+
+	/* subsystems */
+	err = ceph_monc_init(&client->monc, client);
+	if (err < 0)
+		goto fail;
+	err = ceph_osdc_init(&client->osdc, client);
+	if (err < 0)
+		goto fail_monc;
+
+	return client;
+
+fail_monc:
+	ceph_monc_stop(&client->monc);
+fail:
+	kfree(client);
+	return ERR_PTR(err);
+}
+EXPORT_SYMBOL(ceph_create_client);
+
+void ceph_destroy_client(struct ceph_client *client)
+{
+	dout("destroy_client %p\n", client);
+
+	/* unmount */
+	ceph_osdc_stop(&client->osdc);
+
+	/*
+	 * make sure mds and osd connections close out before destroying
+	 * the auth module, which is needed to free those connections'
+	 * ceph_authorizers.
+	 */
+	ceph_msgr_flush();
+
+	ceph_monc_stop(&client->monc);
+
+	ceph_debugfs_client_cleanup(client);
+
+	if (client->msgr)
+		ceph_messenger_destroy(client->msgr);
+
+	ceph_destroy_options(client->options);
+
+	kfree(client);
+	dout("destroy_client %p done\n", client);
+}
+EXPORT_SYMBOL(ceph_destroy_client);
+
+/*
+ * true if we have the mon map (and have thus joined the cluster)
+ */
+static int have_mon_and_osd_map(struct ceph_client *client)
+{
+	return client->monc.monmap && client->monc.monmap->epoch &&
+	       client->osdc.osdmap && client->osdc.osdmap->epoch;
+}
+
+/*
+ * mount: join the ceph cluster, and open root directory.
+ */
+int __ceph_open_session(struct ceph_client *client, unsigned long started)
+{
+	struct ceph_entity_addr *myaddr = NULL;
+	int err;
+	unsigned long timeout = client->options->mount_timeout * HZ;
+
+	/* initialize the messenger */
+	if (client->msgr == NULL) {
+		if (ceph_test_opt(client, MYIP))
+			myaddr = &client->options->my_addr;
+		client->msgr = ceph_messenger_create(myaddr,
+					client->supported_features,
+					client->required_features);
+		if (IS_ERR(client->msgr)) {
+			client->msgr = NULL;
+			return PTR_ERR(client->msgr);
+		}
+		client->msgr->nocrc = ceph_test_opt(client, NOCRC);
+	}
+
+	/* open session, and wait for mon and osd maps */
+	err = ceph_monc_open_session(&client->monc);
+	if (err < 0)
+		return err;
+
+	while (!have_mon_and_osd_map(client)) {
+		err = -EIO;
+		if (timeout && time_after_eq(jiffies, started + timeout))
+			return err;
+
+		/* wait */
+		dout("mount waiting for mon_map\n");
+		err = wait_event_interruptible_timeout(client->auth_wq,
+			have_mon_and_osd_map(client) || (client->auth_err < 0),
+			timeout);
+		if (err == -EINTR || err == -ERESTARTSYS)
+			return err;
+		if (client->auth_err < 0)
+			return client->auth_err;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(__ceph_open_session);
+
+
+int ceph_open_session(struct ceph_client *client)
+{
+	int ret;
+	unsigned long started = jiffies;  /* note the start time */
+
+	dout("open_session start\n");
+	mutex_lock(&client->mount_mutex);
+
+	ret = __ceph_open_session(client, started);
+
+	mutex_unlock(&client->mount_mutex);
+	return ret;
+}
+EXPORT_SYMBOL(ceph_open_session);
+
+
+static int __init init_ceph_lib(void)
+{
+	int ret = 0;
+
+	ret = ceph_debugfs_init();
+	if (ret < 0)
+		goto out;
+
+	ret = ceph_msgr_init();
+	if (ret < 0)
+		goto out_debugfs;
+
+	pr_info("loaded (mon/osd proto %d/%d, osdmap %d/%d %d/%d)\n",
+		CEPH_MONC_PROTOCOL, CEPH_OSDC_PROTOCOL,
+		CEPH_OSDMAP_VERSION, CEPH_OSDMAP_VERSION_EXT,
+		CEPH_OSDMAP_INC_VERSION, CEPH_OSDMAP_INC_VERSION_EXT);
+
+	return 0;
+
+out_debugfs:
+	ceph_debugfs_cleanup();
+out:
+	return ret;
+}
+
+static void __exit exit_ceph_lib(void)
+{
+	dout("exit_ceph_lib\n");
+	ceph_msgr_exit();
+	ceph_debugfs_cleanup();
+}
+
+module_init(init_ceph_lib);
+module_exit(exit_ceph_lib);
+
+MODULE_AUTHOR("Sage Weil <sage@newdream.net>");
+MODULE_AUTHOR("Yehuda Sadeh <yehuda@hq.newdream.net>");
+MODULE_AUTHOR("Patience Warnick <patience@newdream.net>");
+MODULE_DESCRIPTION("Ceph filesystem for Linux");
+MODULE_LICENSE("GPL");
diff --git a/net/ceph/ceph_fs.c b/net/ceph/ceph_fs.c
new file mode 100644
index 00000000000..a3a3a31d3c3
--- /dev/null
+++ b/net/ceph/ceph_fs.c
@@ -0,0 +1,75 @@
+/*
+ * Some non-inline ceph helpers
+ */
+#include <linux/module.h>
+#include <linux/ceph/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)
+{
+	int mode;
+
+#ifdef O_DIRECTORY  /* fixme */
+	if ((flags & O_DIRECTORY) == O_DIRECTORY)
+		return CEPH_FILE_MODE_PIN;
+#endif
+	if ((flags & O_APPEND) == O_APPEND)
+		flags |= O_WRONLY;
+
+	if ((flags & O_ACCMODE) == O_RDWR)
+		mode = CEPH_FILE_MODE_RDWR;
+	else if ((flags & O_ACCMODE) == O_WRONLY)
+		mode = CEPH_FILE_MODE_WR;
+	else
+		mode = CEPH_FILE_MODE_RD;
+
+#ifdef O_LAZY
+	if (flags & O_LAZY)
+		mode |= CEPH_FILE_MODE_LAZY;
+#endif
+
+	return mode;
+}
+EXPORT_SYMBOL(ceph_flags_to_mode);
+
+int ceph_caps_for_mode(int mode)
+{
+	int caps = CEPH_CAP_PIN;
+
+	if (mode & CEPH_FILE_MODE_RD)
+		caps |= CEPH_CAP_FILE_SHARED |
+			CEPH_CAP_FILE_RD | CEPH_CAP_FILE_CACHE;
+	if (mode & CEPH_FILE_MODE_WR)
+		caps |= 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;
+	if (mode & CEPH_FILE_MODE_LAZY)
+		caps |= CEPH_CAP_FILE_LAZYIO;
+
+	return caps;
+}
+EXPORT_SYMBOL(ceph_caps_for_mode);
diff --git a/net/ceph/ceph_hash.c b/net/ceph/ceph_hash.c
new file mode 100644
index 00000000000..815ef882679
--- /dev/null
+++ b/net/ceph/ceph_hash.c
@@ -0,0 +1,118 @@
+
+#include <linux/ceph/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";
+	}
+}
diff --git a/net/ceph/ceph_strings.c b/net/ceph/ceph_strings.c
new file mode 100644
index 00000000000..3fbda04de29
--- /dev/null
+++ b/net/ceph/ceph_strings.c
@@ -0,0 +1,84 @@
+/*
+ * Ceph string constants
+ */
+#include <linux/module.h>
+#include <linux/ceph/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_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_ROLLBACK: return "rollback";
+
+	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_CMPXATTR: return "cmpxattr";
+
+	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_pool_op_name(int op)
+{
+	switch (op) {
+	case POOL_OP_CREATE: return "create";
+	case POOL_OP_DELETE: return "delete";
+	case POOL_OP_AUID_CHANGE: return "auid change";
+	case POOL_OP_CREATE_SNAP: return "create snap";
+	case POOL_OP_DELETE_SNAP: return "delete snap";
+	case POOL_OP_CREATE_UNMANAGED_SNAP: return "create unmanaged snap";
+	case POOL_OP_DELETE_UNMANAGED_SNAP: return "delete unmanaged snap";
+	}
+	return "???";
+}
diff --git a/net/ceph/crush/crush.c b/net/ceph/crush/crush.c
new file mode 100644
index 00000000000..d6ebb13a18a
--- /dev/null
+++ b/net/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 <linux/crush/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);
+}
+
+
diff --git a/net/ceph/crush/hash.c b/net/ceph/crush/hash.c
new file mode 100644
index 00000000000..5bb63e37a8a
--- /dev/null
+++ b/net/ceph/crush/hash.c
@@ -0,0 +1,149 @@
+
+#include <linux/types.h>
+#include <linux/crush/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";
+	}
+}
diff --git a/net/ceph/crush/mapper.c b/net/ceph/crush/mapper.c
new file mode 100644
index 00000000000..42599e31dca
--- /dev/null
+++ b/net/ceph/crush/mapper.c
@@ -0,0 +1,609 @@
+
+#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 <linux/crush/crush.h>
+#include <linux/crush/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(" crush_bucket_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] >= 0x10000)
+		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%s bucket %d x %d outpos %d numrep %d\n", recurse_to_leaf ? "_LEAF" : "",
+		bucket->id, x, outpos, numrep);
+
+	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];
+					retry_bucket = 1;
+					continue;
+				}
+
+				/* collision? */
+				for (i = 0; i < outpos; i++) {
+					if (out[i] == item) {
+						collide = 1;
+						break;
+					}
+				}
+
+				reject = 0;
+				if (recurse_to_leaf) {
+					if (item < 0) {
+						if (crush_choose(map,
+							 map->buckets[-1-item],
+							 weight,
+							 x, outpos+1, 0,
+							 out2, outpos,
+							 firstn, 0,
+							 NULL) <= outpos)
+							/* didn't get leaf */
+							reject = 1;
+					} else {
+						/* we already have a leaf! */
+						out2[outpos] = item;
+					}
+				}
+
+				if (!reject) {
+					/* 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;
+}
+
+
diff --git a/net/ceph/crypto.c b/net/ceph/crypto.c
new file mode 100644
index 00000000000..7b505b0c983
--- /dev/null
+++ b/net/ceph/crypto.c
@@ -0,0 +1,412 @@
+
+#include <linux/ceph/ceph_debug.h>
+
+#include <linux/err.h>
+#include <linux/scatterlist.h>
+#include <linux/slab.h>
+#include <crypto/hash.h>
+
+#include <linux/ceph/decode.h>
+#include "crypto.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);
+}
+
+static const u8 *aes_iv = (u8 *)CEPH_AES_IV;
+
+static 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;
+}
+
+static 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;
+}
+
+static 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;
+}
+
+static 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;
+	}
+}
diff --git a/net/ceph/crypto.h b/net/ceph/crypto.h
new file mode 100644
index 00000000000..f9eccace592
--- /dev/null
+++ b/net/ceph/crypto.h
@@ -0,0 +1,48 @@
+#ifndef _FS_CEPH_CRYPTO_H
+#define _FS_CEPH_CRYPTO_H
+
+#include <linux/ceph/types.h>
+#include <linux/ceph/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 char *src, const char *end);
+extern int ceph_unarmor(char *dst, const char *src, const char *end);
+
+#endif
diff --git a/net/ceph/debugfs.c b/net/ceph/debugfs.c
new file mode 100644
index 00000000000..27d4ea315d1
--- /dev/null
+++ b/net/ceph/debugfs.c
@@ -0,0 +1,267 @@
+#include <linux/ceph/ceph_debug.h>
+
+#include <linux/device.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/ctype.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+
+#include <linux/ceph/libceph.h>
+#include <linux/ceph/mon_client.h>
+#include <linux/ceph/auth.h>
+#include <linux/ceph/debugfs.h>
+
+#ifdef CONFIG_DEBUG_FS
+
+/*
+ * Implement /sys/kernel/debug/ceph fun
+ *
+ * /sys/kernel/debug/ceph/client*  - an instance of the ceph client
+ *      .../osdmap      - current osdmap
+ *      .../monmap      - current monmap
+ *      .../osdc        - active osd 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),
+			   ceph_pr_addr(&inst->addr.in_addr));
+	}
+	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, ceph_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_generic_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->generic_request_tree); rp; rp = rb_next(rp)) {
+		__u16 op;
+		req = rb_entry(rp, struct ceph_mon_generic_request, node);
+		op = le16_to_cpu(req->request->hdr.type);
+		if (op == CEPH_MSG_STATFS)
+			seq_printf(s, "%lld statfs\n", req->tid);
+		else
+			seq_printf(s, "%lld unknown\n", req->tid);
+	}
+
+	mutex_unlock(&monc->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;
+}
+
+CEPH_DEFINE_SHOW_FUNC(monmap_show)
+CEPH_DEFINE_SHOW_FUNC(osdmap_show)
+CEPH_DEFINE_SHOW_FUNC(monc_show)
+CEPH_DEFINE_SHOW_FUNC(osdc_show)
+
+int 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 = -ENOMEM;
+	char name[80];
+
+	snprintf(name, sizeof(name), "%pU.client%lld", &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->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_osdmap = debugfs_create_file("osdmap",
+					0600,
+					client->debugfs_dir,
+					client,
+					&osdmap_show_fops);
+	if (!client->debugfs_osdmap)
+		goto out;
+
+	return 0;
+
+out:
+	ceph_debugfs_client_cleanup(client);
+	return ret;
+}
+
+void ceph_debugfs_client_cleanup(struct ceph_client *client)
+{
+	debugfs_remove(client->debugfs_osdmap);
+	debugfs_remove(client->debugfs_monmap);
+	debugfs_remove(client->osdc.debugfs_file);
+	debugfs_remove(client->monc.debugfs_file);
+	debugfs_remove(client->debugfs_dir);
+}
+
+#else  /* CONFIG_DEBUG_FS */
+
+int 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 */
+
+EXPORT_SYMBOL(ceph_debugfs_init);
+EXPORT_SYMBOL(ceph_debugfs_cleanup);
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
new file mode 100644
index 00000000000..0e8157ee5d4
--- /dev/null
+++ b/net/ceph/messenger.c
@@ -0,0 +1,2453 @@
+#include <linux/ceph/ceph_debug.h>
+
+#include <linux/crc32c.h>
+#include <linux/ctype.h>
+#include <linux/highmem.h>
+#include <linux/inet.h>
+#include <linux/kthread.h>
+#include <linux/net.h>
+#include <linux/slab.h>
+#include <linux/socket.h>
+#include <linux/string.h>
+#include <linux/bio.h>
+#include <linux/blkdev.h>
+#include <net/tcp.h>
+
+#include <linux/ceph/libceph.h>
+#include <linux/ceph/messenger.h>
+#include <linux/ceph/decode.h>
+#include <linux/ceph/pagelist.h>
+
+/*
+ * Ceph uses the messenger to exchange ceph_msg messages with other
+ * hosts in the system.  The messenger provides ordered and reliable
+ * delivery.  We tolerate TCP disconnects by reconnecting (with
+ * exponential backoff) in the case of a fault (disconnection, bad
+ * crc, protocol error).  Acks allow sent messages to be discarded by
+ * the sender.
+ */
+
+/* static tag bytes (protocol control messages) */
+static char tag_msg = CEPH_MSGR_TAG_MSG;
+static char tag_ack = CEPH_MSGR_TAG_ACK;
+static char tag_keepalive = CEPH_MSGR_TAG_KEEPALIVE;
+
+#ifdef CONFIG_LOCKDEP
+static struct lock_class_key socket_class;
+#endif
+
+
+static void queue_con(struct ceph_connection *con);
+static void con_work(struct work_struct *);
+static void ceph_fault(struct ceph_connection *con);
+
+/*
+ * nicely render a sockaddr as a string.
+ */
+#define MAX_ADDR_STR 20
+#define MAX_ADDR_STR_LEN 60
+static char addr_str[MAX_ADDR_STR][MAX_ADDR_STR_LEN];
+static DEFINE_SPINLOCK(addr_str_lock);
+static int last_addr_str;
+
+const char *ceph_pr_addr(const struct sockaddr_storage *ss)
+{
+	int i;
+	char *s;
+	struct sockaddr_in *in4 = (void *)ss;
+	struct sockaddr_in6 *in6 = (void *)ss;
+
+	spin_lock(&addr_str_lock);
+	i = last_addr_str++;
+	if (last_addr_str == MAX_ADDR_STR)
+		last_addr_str = 0;
+	spin_unlock(&addr_str_lock);
+	s = addr_str[i];
+
+	switch (ss->ss_family) {
+	case AF_INET:
+		snprintf(s, MAX_ADDR_STR_LEN, "%pI4:%u", &in4->sin_addr,
+			 (unsigned int)ntohs(in4->sin_port));
+		break;
+
+	case AF_INET6:
+		snprintf(s, MAX_ADDR_STR_LEN, "[%pI6c]:%u", &in6->sin6_addr,
+			 (unsigned int)ntohs(in6->sin6_port));
+		break;
+
+	default:
+		sprintf(s, "(unknown sockaddr family %d)", (int)ss->ss_family);
+	}
+
+	return s;
+}
+EXPORT_SYMBOL(ceph_pr_addr);
+
+static void encode_my_addr(struct ceph_messenger *msgr)
+{
+	memcpy(&msgr->my_enc_addr, &msgr->inst.addr, sizeof(msgr->my_enc_addr));
+	ceph_encode_addr(&msgr->my_enc_addr);
+}
+
+/*
+ * work queue for all reading and writing to/from the socket.
+ */
+struct workqueue_struct *ceph_msgr_wq;
+
+int ceph_msgr_init(void)
+{
+	ceph_msgr_wq = create_workqueue("ceph-msgr");
+	if (IS_ERR(ceph_msgr_wq)) {
+		int ret = PTR_ERR(ceph_msgr_wq);
+		pr_err("msgr_init failed to create workqueue: %d\n", ret);
+		ceph_msgr_wq = NULL;
+		return ret;
+	}
+	return 0;
+}
+EXPORT_SYMBOL(ceph_msgr_init);
+
+void ceph_msgr_exit(void)
+{
+	destroy_workqueue(ceph_msgr_wq);
+}
+EXPORT_SYMBOL(ceph_msgr_exit);
+
+void ceph_msgr_flush(void)
+{
+	flush_workqueue(ceph_msgr_wq);
+}
+EXPORT_SYMBOL(ceph_msgr_flush);
+
+
+/*
+ * socket callback functions
+ */
+
+/* data available on socket, or listen socket received a connect */
+static void ceph_data_ready(struct sock *sk, int count_unused)
+{
+	struct ceph_connection *con =
+		(struct ceph_connection *)sk->sk_user_data;
+	if (sk->sk_state != TCP_CLOSE_WAIT) {
+		dout("ceph_data_ready on %p state = %lu, queueing work\n",
+		     con, con->state);
+		queue_con(con);
+	}
+}
+
+/* socket has buffer space for writing */
+static void ceph_write_space(struct sock *sk)
+{
+	struct ceph_connection *con =
+		(struct ceph_connection *)sk->sk_user_data;
+
+	/* only queue to workqueue if there is data we want to write. */
+	if (test_bit(WRITE_PENDING, &con->state)) {
+		dout("ceph_write_space %p queueing write work\n", con);
+		queue_con(con);
+	} else {
+		dout("ceph_write_space %p nothing to write\n", con);
+	}
+
+	/* since we have our own write_space, clear the SOCK_NOSPACE flag */
+	clear_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
+}
+
+/* socket's state has changed */
+static void ceph_state_change(struct sock *sk)
+{
+	struct ceph_connection *con =
+		(struct ceph_connection *)sk->sk_user_data;
+
+	dout("ceph_state_change %p state = %lu sk_state = %u\n",
+	     con, con->state, sk->sk_state);
+
+	if (test_bit(CLOSED, &con->state))
+		return;
+
+	switch (sk->sk_state) {
+	case TCP_CLOSE:
+		dout("ceph_state_change TCP_CLOSE\n");
+	case TCP_CLOSE_WAIT:
+		dout("ceph_state_change TCP_CLOSE_WAIT\n");
+		if (test_and_set_bit(SOCK_CLOSED, &con->state) == 0) {
+			if (test_bit(CONNECTING, &con->state))
+				con->error_msg = "connection failed";
+			else
+				con->error_msg = "socket closed";
+			queue_con(con);
+		}
+		break;
+	case TCP_ESTABLISHED:
+		dout("ceph_state_change TCP_ESTABLISHED\n");
+		queue_con(con);
+		break;
+	}
+}
+
+/*
+ * set up socket callbacks
+ */
+static void set_sock_callbacks(struct socket *sock,
+			       struct ceph_connection *con)
+{
+	struct sock *sk = sock->sk;
+	sk->sk_user_data = (void *)con;
+	sk->sk_data_ready = ceph_data_ready;
+	sk->sk_write_space = ceph_write_space;
+	sk->sk_state_change = ceph_state_change;
+}
+
+
+/*
+ * socket helpers
+ */
+
+/*
+ * initiate connection to a remote socket.
+ */
+static struct socket *ceph_tcp_connect(struct ceph_connection *con)
+{
+	struct sockaddr_storage *paddr = &con->peer_addr.in_addr;
+	struct socket *sock;
+	int ret;
+
+	BUG_ON(con->sock);
+	ret = sock_create_kern(con->peer_addr.in_addr.ss_family, SOCK_STREAM,
+			       IPPROTO_TCP, &sock);
+	if (ret)
+		return ERR_PTR(ret);
+	con->sock = sock;
+	sock->sk->sk_allocation = GFP_NOFS;
+
+#ifdef CONFIG_LOCKDEP
+	lockdep_set_class(&sock->sk->sk_lock, &socket_class);
+#endif
+
+	set_sock_callbacks(sock, con);
+
+	dout("connect %s\n", ceph_pr_addr(&con->peer_addr.in_addr));
+
+	ret = sock->ops->connect(sock, (struct sockaddr *)paddr, sizeof(*paddr),
+				 O_NONBLOCK);
+	if (ret == -EINPROGRESS) {
+		dout("connect %s EINPROGRESS sk_state = %u\n",
+		     ceph_pr_addr(&con->peer_addr.in_addr),
+		     sock->sk->sk_state);
+		ret = 0;
+	}
+	if (ret < 0) {
+		pr_err("connect %s error %d\n",
+		       ceph_pr_addr(&con->peer_addr.in_addr), ret);
+		sock_release(sock);
+		con->sock = NULL;
+		con->error_msg = "connect error";
+	}
+
+	if (ret < 0)
+		return ERR_PTR(ret);
+	return sock;
+}
+
+static int ceph_tcp_recvmsg(struct socket *sock, void *buf, size_t len)
+{
+	struct kvec iov = {buf, len};
+	struct msghdr msg = { .msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL };
+
+	return kernel_recvmsg(sock, &msg, &iov, 1, len, msg.msg_flags);
+}
+
+/*
+ * write something.  @more is true if caller will be sending more data
+ * shortly.
+ */
+static int ceph_tcp_sendmsg(struct socket *sock, struct kvec *iov,
+		     size_t kvlen, size_t len, int more)
+{
+	struct msghdr msg = { .msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL };
+
+	if (more)
+		msg.msg_flags |= MSG_MORE;
+	else
+		msg.msg_flags |= MSG_EOR;  /* superfluous, but what the hell */
+
+	return kernel_sendmsg(sock, &msg, iov, kvlen, len);
+}
+
+
+/*
+ * Shutdown/close the socket for the given connection.
+ */
+static int con_close_socket(struct ceph_connection *con)
+{
+	int rc;
+
+	dout("con_close_socket on %p sock %p\n", con, con->sock);
+	if (!con->sock)
+		return 0;
+	set_bit(SOCK_CLOSED, &con->state);
+	rc = con->sock->ops->shutdown(con->sock, SHUT_RDWR);
+	sock_release(con->sock);
+	con->sock = NULL;
+	clear_bit(SOCK_CLOSED, &con->state);
+	return rc;
+}
+
+/*
+ * Reset a connection.  Discard all incoming and outgoing messages
+ * and clear *_seq state.
+ */
+static void ceph_msg_remove(struct ceph_msg *msg)
+{
+	list_del_init(&msg->list_head);
+	ceph_msg_put(msg);
+}
+static void ceph_msg_remove_list(struct list_head *head)
+{
+	while (!list_empty(head)) {
+		struct ceph_msg *msg = list_first_entry(head, struct ceph_msg,
+							list_head);
+		ceph_msg_remove(msg);
+	}
+}
+
+static void reset_connection(struct ceph_connection *con)
+{
+	/* reset connection, out_queue, msg_ and connect_seq */
+	/* discard existing out_queue and msg_seq */
+	ceph_msg_remove_list(&con->out_queue);
+	ceph_msg_remove_list(&con->out_sent);
+
+	if (con->in_msg) {
+		ceph_msg_put(con->in_msg);
+		con->in_msg = NULL;
+	}
+
+	con->connect_seq = 0;
+	con->out_seq = 0;
+	if (con->out_msg) {
+		ceph_msg_put(con->out_msg);
+		con->out_msg = NULL;
+	}
+	con->out_keepalive_pending = false;
+	con->in_seq = 0;
+	con->in_seq_acked = 0;
+}
+
+/*
+ * mark a peer down.  drop any open connections.
+ */
+void ceph_con_close(struct ceph_connection *con)
+{
+	dout("con_close %p peer %s\n", con,
+	     ceph_pr_addr(&con->peer_addr.in_addr));
+	set_bit(CLOSED, &con->state);  /* in case there's queued work */
+	clear_bit(STANDBY, &con->state);  /* avoid connect_seq bump */
+	clear_bit(LOSSYTX, &con->state);  /* so we retry next connect */
+	clear_bit(KEEPALIVE_PENDING, &con->state);
+	clear_bit(WRITE_PENDING, &con->state);
+	mutex_lock(&con->mutex);
+	reset_connection(con);
+	con->peer_global_seq = 0;
+	cancel_delayed_work(&con->work);
+	mutex_unlock(&con->mutex);
+	queue_con(con);
+}
+EXPORT_SYMBOL(ceph_con_close);
+
+/*
+ * Reopen a closed connection, with a new peer address.
+ */
+void ceph_con_open(struct ceph_connection *con, struct ceph_entity_addr *addr)
+{
+	dout("con_open %p %s\n", con, ceph_pr_addr(&addr->in_addr));
+	set_bit(OPENING, &con->state);
+	clear_bit(CLOSED, &con->state);
+	memcpy(&con->peer_addr, addr, sizeof(*addr));
+	con->delay = 0;      /* reset backoff memory */
+	queue_con(con);
+}
+EXPORT_SYMBOL(ceph_con_open);
+
+/*
+ * return true if this connection ever successfully opened
+ */
+bool ceph_con_opened(struct ceph_connection *con)
+{
+	return con->connect_seq > 0;
+}
+
+/*
+ * generic get/put
+ */
+struct ceph_connection *ceph_con_get(struct ceph_connection *con)
+{
+	dout("con_get %p nref = %d -> %d\n", con,
+	     atomic_read(&con->nref), atomic_read(&con->nref) + 1);
+	if (atomic_inc_not_zero(&con->nref))
+		return con;
+	return NULL;
+}
+
+void ceph_con_put(struct ceph_connection *con)
+{
+	dout("con_put %p nref = %d -> %d\n", con,
+	     atomic_read(&con->nref), atomic_read(&con->nref) - 1);
+	BUG_ON(atomic_read(&con->nref) == 0);
+	if (atomic_dec_and_test(&con->nref)) {
+		BUG_ON(con->sock);
+		kfree(con);
+	}
+}
+
+/*
+ * initialize a new connection.
+ */
+void ceph_con_init(struct ceph_messenger *msgr, struct ceph_connection *con)
+{
+	dout("con_init %p\n", con);
+	memset(con, 0, sizeof(*con));
+	atomic_set(&con->nref, 1);
+	con->msgr = msgr;
+	mutex_init(&con->mutex);
+	INIT_LIST_HEAD(&con->out_queue);
+	INIT_LIST_HEAD(&con->out_sent);
+	INIT_DELAYED_WORK(&con->work, con_work);
+}
+EXPORT_SYMBOL(ceph_con_init);
+
+
+/*
+ * We maintain a global counter to order connection attempts.  Get
+ * a unique seq greater than @gt.
+ */
+static u32 get_global_seq(struct ceph_messenger *msgr, u32 gt)
+{
+	u32 ret;
+
+	spin_lock(&msgr->global_seq_lock);
+	if (msgr->global_seq < gt)
+		msgr->global_seq = gt;
+	ret = ++msgr->global_seq;
+	spin_unlock(&msgr->global_seq_lock);
+	return ret;
+}
+
+
+/*
+ * Prepare footer for currently outgoing message, and finish things
+ * off.  Assumes out_kvec* are already valid.. we just add on to the end.
+ */
+static void prepare_write_message_footer(struct ceph_connection *con, int v)
+{
+	struct ceph_msg *m = con->out_msg;
+
+	dout("prepare_write_message_footer %p\n", con);
+	con->out_kvec_is_msg = true;
+	con->out_kvec[v].iov_base = &m->footer;
+	con->out_kvec[v].iov_len = sizeof(m->footer);
+	con->out_kvec_bytes += sizeof(m->footer);
+	con->out_kvec_left++;
+	con->out_more = m->more_to_follow;
+	con->out_msg_done = true;
+}
+
+/*
+ * Prepare headers for the next outgoing message.
+ */
+static void prepare_write_message(struct ceph_connection *con)
+{
+	struct ceph_msg *m;
+	int v = 0;
+
+	con->out_kvec_bytes = 0;
+	con->out_kvec_is_msg = true;
+	con->out_msg_done = false;
+
+	/* Sneak an ack in there first?  If we can get it into the same
+	 * TCP packet that's a good thing. */
+	if (con->in_seq > con->in_seq_acked) {
+		con->in_seq_acked = con->in_seq;
+		con->out_kvec[v].iov_base = &tag_ack;
+		con->out_kvec[v++].iov_len = 1;
+		con->out_temp_ack = cpu_to_le64(con->in_seq_acked);
+		con->out_kvec[v].iov_base = &con->out_temp_ack;
+		con->out_kvec[v++].iov_len = sizeof(con->out_temp_ack);
+		con->out_kvec_bytes = 1 + sizeof(con->out_temp_ack);
+	}
+
+	m = list_first_entry(&con->out_queue,
+		       struct ceph_msg, list_head);
+	con->out_msg = m;
+	if (test_bit(LOSSYTX, &con->state)) {
+		list_del_init(&m->list_head);
+	} else {
+		/* put message on sent list */
+		ceph_msg_get(m);
+		list_move_tail(&m->list_head, &con->out_sent);
+	}
+
+	/*
+	 * only assign outgoing seq # if we haven't sent this message
+	 * yet.  if it is requeued, resend with it's original seq.
+	 */
+	if (m->needs_out_seq) {
+		m->hdr.seq = cpu_to_le64(++con->out_seq);
+		m->needs_out_seq = false;
+	}
+
+	dout("prepare_write_message %p seq %lld type %d len %d+%d+%d %d pgs\n",
+	     m, con->out_seq, le16_to_cpu(m->hdr.type),
+	     le32_to_cpu(m->hdr.front_len), le32_to_cpu(m->hdr.middle_len),
+	     le32_to_cpu(m->hdr.data_len),
+	     m->nr_pages);
+	BUG_ON(le32_to_cpu(m->hdr.front_len) != m->front.iov_len);
+
+	/* tag + hdr + front + middle */
+	con->out_kvec[v].iov_base = &tag_msg;
+	con->out_kvec[v++].iov_len = 1;
+	con->out_kvec[v].iov_base = &m->hdr;
+	con->out_kvec[v++].iov_len = sizeof(m->hdr);
+	con->out_kvec[v++] = m->front;
+	if (m->middle)
+		con->out_kvec[v++] = m->middle->vec;
+	con->out_kvec_left = v;
+	con->out_kvec_bytes += 1 + sizeof(m->hdr) + m->front.iov_len +
+		(m->middle ? m->middle->vec.iov_len : 0);
+	con->out_kvec_cur = con->out_kvec;
+
+	/* fill in crc (except data pages), footer */
+	con->out_msg->hdr.crc =
+		cpu_to_le32(crc32c(0, (void *)&m->hdr,
+				      sizeof(m->hdr) - sizeof(m->hdr.crc)));
+	con->out_msg->footer.flags = CEPH_MSG_FOOTER_COMPLETE;
+	con->out_msg->footer.front_crc =
+		cpu_to_le32(crc32c(0, m->front.iov_base, m->front.iov_len));
+	if (m->middle)
+		con->out_msg->footer.middle_crc =
+			cpu_to_le32(crc32c(0, m->middle->vec.iov_base,
+					   m->middle->vec.iov_len));
+	else
+		con->out_msg->footer.middle_crc = 0;
+	con->out_msg->footer.data_crc = 0;
+	dout("prepare_write_message front_crc %u data_crc %u\n",
+	     le32_to_cpu(con->out_msg->footer.front_crc),
+	     le32_to_cpu(con->out_msg->footer.middle_crc));
+
+	/* is there a data payload? */
+	if (le32_to_cpu(m->hdr.data_len) > 0) {
+		/* initialize page iterator */
+		con->out_msg_pos.page = 0;
+		if (m->pages)
+			con->out_msg_pos.page_pos =
+				le16_to_cpu(m->hdr.data_off) & ~PAGE_MASK;
+		else
+			con->out_msg_pos.page_pos = 0;
+		con->out_msg_pos.data_pos = 0;
+		con->out_msg_pos.did_page_crc = 0;
+		con->out_more = 1;  /* data + footer will follow */
+	} else {
+		/* no, queue up footer too and be done */
+		prepare_write_message_footer(con, v);
+	}
+
+	set_bit(WRITE_PENDING, &con->state);
+}
+
+/*
+ * Prepare an ack.
+ */
+static void prepare_write_ack(struct ceph_connection *con)
+{
+	dout("prepare_write_ack %p %llu -> %llu\n", con,
+	     con->in_seq_acked, con->in_seq);
+	con->in_seq_acked = con->in_seq;
+
+	con->out_kvec[0].iov_base = &tag_ack;
+	con->out_kvec[0].iov_len = 1;
+	con->out_temp_ack = cpu_to_le64(con->in_seq_acked);
+	con->out_kvec[1].iov_base = &con->out_temp_ack;
+	con->out_kvec[1].iov_len = sizeof(con->out_temp_ack);
+	con->out_kvec_left = 2;
+	con->out_kvec_bytes = 1 + sizeof(con->out_temp_ack);
+	con->out_kvec_cur = con->out_kvec;
+	con->out_more = 1;  /* more will follow.. eventually.. */
+	set_bit(WRITE_PENDING, &con->state);
+}
+
+/*
+ * Prepare to write keepalive byte.
+ */
+static void prepare_write_keepalive(struct ceph_connection *con)
+{
+	dout("prepare_write_keepalive %p\n", con);
+	con->out_kvec[0].iov_base = &tag_keepalive;
+	con->out_kvec[0].iov_len = 1;
+	con->out_kvec_left = 1;
+	con->out_kvec_bytes = 1;
+	con->out_kvec_cur = con->out_kvec;
+	set_bit(WRITE_PENDING, &con->state);
+}
+
+/*
+ * Connection negotiation.
+ */
+
+static void prepare_connect_authorizer(struct ceph_connection *con)
+{
+	void *auth_buf;
+	int auth_len = 0;
+	int auth_protocol = 0;
+
+	mutex_unlock(&con->mutex);
+	if (con->ops->get_authorizer)
+		con->ops->get_authorizer(con, &auth_buf, &auth_len,
+					 &auth_protocol, &con->auth_reply_buf,
+					 &con->auth_reply_buf_len,
+					 con->auth_retry);
+	mutex_lock(&con->mutex);
+
+	con->out_connect.authorizer_protocol = cpu_to_le32(auth_protocol);
+	con->out_connect.authorizer_len = cpu_to_le32(auth_len);
+
+	con->out_kvec[con->out_kvec_left].iov_base = auth_buf;
+	con->out_kvec[con->out_kvec_left].iov_len = auth_len;
+	con->out_kvec_left++;
+	con->out_kvec_bytes += auth_len;
+}
+
+/*
+ * We connected to a peer and are saying hello.
+ */
+static void prepare_write_banner(struct ceph_messenger *msgr,
+				 struct ceph_connection *con)
+{
+	int len = strlen(CEPH_BANNER);
+
+	con->out_kvec[0].iov_base = CEPH_BANNER;
+	con->out_kvec[0].iov_len = len;
+	con->out_kvec[1].iov_base = &msgr->my_enc_addr;
+	con->out_kvec[1].iov_len = sizeof(msgr->my_enc_addr);
+	con->out_kvec_left = 2;
+	con->out_kvec_bytes = len + sizeof(msgr->my_enc_addr);
+	con->out_kvec_cur = con->out_kvec;
+	con->out_more = 0;
+	set_bit(WRITE_PENDING, &con->state);
+}
+
+static void prepare_write_connect(struct ceph_messenger *msgr,
+				  struct ceph_connection *con,
+				  int after_banner)
+{
+	unsigned global_seq = get_global_seq(con->msgr, 0);
+	int proto;
+
+	switch (con->peer_name.type) {
+	case CEPH_ENTITY_TYPE_MON:
+		proto = CEPH_MONC_PROTOCOL;
+		break;
+	case CEPH_ENTITY_TYPE_OSD:
+		proto = CEPH_OSDC_PROTOCOL;
+		break;
+	case CEPH_ENTITY_TYPE_MDS:
+		proto = CEPH_MDSC_PROTOCOL;
+		break;
+	default:
+		BUG();
+	}
+
+	dout("prepare_write_connect %p cseq=%d gseq=%d proto=%d\n", con,
+	     con->connect_seq, global_seq, proto);
+
+	con->out_connect.features = cpu_to_le64(msgr->supported_features);
+	con->out_connect.host_type = cpu_to_le32(CEPH_ENTITY_TYPE_CLIENT);
+	con->out_connect.connect_seq = cpu_to_le32(con->connect_seq);
+	con->out_connect.global_seq = cpu_to_le32(global_seq);
+	con->out_connect.protocol_version = cpu_to_le32(proto);
+	con->out_connect.flags = 0;
+
+	if (!after_banner) {
+		con->out_kvec_left = 0;
+		con->out_kvec_bytes = 0;
+	}
+	con->out_kvec[con->out_kvec_left].iov_base = &con->out_connect;
+	con->out_kvec[con->out_kvec_left].iov_len = sizeof(con->out_connect);
+	con->out_kvec_left++;
+	con->out_kvec_bytes += sizeof(con->out_connect);
+	con->out_kvec_cur = con->out_kvec;
+	con->out_more = 0;
+	set_bit(WRITE_PENDING, &con->state);
+
+	prepare_connect_authorizer(con);
+}
+
+
+/*
+ * write as much of pending kvecs to the socket as we can.
+ *  1 -> done
+ *  0 -> socket full, but more to do
+ * <0 -> error
+ */
+static int write_partial_kvec(struct ceph_connection *con)
+{
+	int ret;
+
+	dout("write_partial_kvec %p %d left\n", con, con->out_kvec_bytes);
+	while (con->out_kvec_bytes > 0) {
+		ret = ceph_tcp_sendmsg(con->sock, con->out_kvec_cur,
+				       con->out_kvec_left, con->out_kvec_bytes,
+				       con->out_more);
+		if (ret <= 0)
+			goto out;
+		con->out_kvec_bytes -= ret;
+		if (con->out_kvec_bytes == 0)
+			break;            /* done */
+		while (ret > 0) {
+			if (ret >= con->out_kvec_cur->iov_len) {
+				ret -= con->out_kvec_cur->iov_len;
+				con->out_kvec_cur++;
+				con->out_kvec_left--;
+			} else {
+				con->out_kvec_cur->iov_len -= ret;
+				con->out_kvec_cur->iov_base += ret;
+				ret = 0;
+				break;
+			}
+		}
+	}
+	con->out_kvec_left = 0;
+	con->out_kvec_is_msg = false;
+	ret = 1;
+out:
+	dout("write_partial_kvec %p %d left in %d kvecs ret = %d\n", con,
+	     con->out_kvec_bytes, con->out_kvec_left, ret);
+	return ret;  /* done! */
+}
+
+#ifdef CONFIG_BLOCK
+static void init_bio_iter(struct bio *bio, struct bio **iter, int *seg)
+{
+	if (!bio) {
+		*iter = NULL;
+		*seg = 0;
+		return;
+	}
+	*iter = bio;
+	*seg = bio->bi_idx;
+}
+
+static void iter_bio_next(struct bio **bio_iter, int *seg)
+{
+	if (*bio_iter == NULL)
+		return;
+
+	BUG_ON(*seg >= (*bio_iter)->bi_vcnt);
+
+	(*seg)++;
+	if (*seg == (*bio_iter)->bi_vcnt)
+		init_bio_iter((*bio_iter)->bi_next, bio_iter, seg);
+}
+#endif
+
+/*
+ * Write as much message data payload as we can.  If we finish, queue
+ * up the footer.
+ *  1 -> done, footer is now queued in out_kvec[].
+ *  0 -> socket full, but more to do
+ * <0 -> error
+ */
+static int write_partial_msg_pages(struct ceph_connection *con)
+{
+	struct ceph_msg *msg = con->out_msg;
+	unsigned data_len = le32_to_cpu(msg->hdr.data_len);
+	size_t len;
+	int crc = con->msgr->nocrc;
+	int ret;
+	int total_max_write;
+	int in_trail = 0;
+	size_t trail_len = (msg->trail ? msg->trail->length : 0);
+
+	dout("write_partial_msg_pages %p msg %p page %d/%d offset %d\n",
+	     con, con->out_msg, con->out_msg_pos.page, con->out_msg->nr_pages,
+	     con->out_msg_pos.page_pos);
+
+#ifdef CONFIG_BLOCK
+	if (msg->bio && !msg->bio_iter)
+		init_bio_iter(msg->bio, &msg->bio_iter, &msg->bio_seg);
+#endif
+
+	while (data_len > con->out_msg_pos.data_pos) {
+		struct page *page = NULL;
+		void *kaddr = NULL;
+		int max_write = PAGE_SIZE;
+		int page_shift = 0;
+
+		total_max_write = data_len - trail_len -
+			con->out_msg_pos.data_pos;
+
+		/*
+		 * if we are calculating the data crc (the default), we need
+		 * to map the page.  if our pages[] has been revoked, use the
+		 * zero page.
+		 */
+
+		/* have we reached the trail part of the data? */
+		if (con->out_msg_pos.data_pos >= data_len - trail_len) {
+			in_trail = 1;
+
+			total_max_write = data_len - con->out_msg_pos.data_pos;
+
+			page = list_first_entry(&msg->trail->head,
+						struct page, lru);
+			if (crc)
+				kaddr = kmap(page);
+			max_write = PAGE_SIZE;
+		} else if (msg->pages) {
+			page = msg->pages[con->out_msg_pos.page];
+			if (crc)
+				kaddr = kmap(page);
+		} else if (msg->pagelist) {
+			page = list_first_entry(&msg->pagelist->head,
+						struct page, lru);
+			if (crc)
+				kaddr = kmap(page);
+#ifdef CONFIG_BLOCK
+		} else if (msg->bio) {
+			struct bio_vec *bv;
+
+			bv = bio_iovec_idx(msg->bio_iter, msg->bio_seg);
+			page = bv->bv_page;
+			page_shift = bv->bv_offset;
+			if (crc)
+				kaddr = kmap(page) + page_shift;
+			max_write = bv->bv_len;
+#endif
+		} else {
+			page = con->msgr->zero_page;
+			if (crc)
+				kaddr = page_address(con->msgr->zero_page);
+		}
+		len = min_t(int, max_write - con->out_msg_pos.page_pos,
+			    total_max_write);
+
+		if (crc && !con->out_msg_pos.did_page_crc) {
+			void *base = kaddr + con->out_msg_pos.page_pos;
+			u32 tmpcrc = le32_to_cpu(con->out_msg->footer.data_crc);
+
+			BUG_ON(kaddr == NULL);
+			con->out_msg->footer.data_crc =
+				cpu_to_le32(crc32c(tmpcrc, base, len));
+			con->out_msg_pos.did_page_crc = 1;
+		}
+		ret = kernel_sendpage(con->sock, page,
+				      con->out_msg_pos.page_pos + page_shift,
+				      len,
+				      MSG_DONTWAIT | MSG_NOSIGNAL |
+				      MSG_MORE);
+
+		if (crc &&
+		    (msg->pages || msg->pagelist || msg->bio || in_trail))
+			kunmap(page);
+
+		if (ret <= 0)
+			goto out;
+
+		con->out_msg_pos.data_pos += ret;
+		con->out_msg_pos.page_pos += ret;
+		if (ret == len) {
+			con->out_msg_pos.page_pos = 0;
+			con->out_msg_pos.page++;
+			con->out_msg_pos.did_page_crc = 0;
+			if (in_trail)
+				list_move_tail(&page->lru,
+					       &msg->trail->head);
+			else if (msg->pagelist)
+				list_move_tail(&page->lru,
+					       &msg->pagelist->head);
+#ifdef CONFIG_BLOCK
+			else if (msg->bio)
+				iter_bio_next(&msg->bio_iter, &msg->bio_seg);
+#endif
+		}
+	}
+
+	dout("write_partial_msg_pages %p msg %p done\n", con, msg);
+
+	/* prepare and queue up footer, too */
+	if (!crc)
+		con->out_msg->footer.flags |= CEPH_MSG_FOOTER_NOCRC;
+	con->out_kvec_bytes = 0;
+	con->out_kvec_left = 0;
+	con->out_kvec_cur = con->out_kvec;
+	prepare_write_message_footer(con, 0);
+	ret = 1;
+out:
+	return ret;
+}
+
+/*
+ * write some zeros
+ */
+static int write_partial_skip(struct ceph_connection *con)
+{
+	int ret;
+
+	while (con->out_skip > 0) {
+		struct kvec iov = {
+			.iov_base = page_address(con->msgr->zero_page),
+			.iov_len = min(con->out_skip, (int)PAGE_CACHE_SIZE)
+		};
+
+		ret = ceph_tcp_sendmsg(con->sock, &iov, 1, iov.iov_len, 1);
+		if (ret <= 0)
+			goto out;
+		con->out_skip -= ret;
+	}
+	ret = 1;
+out:
+	return ret;
+}
+
+/*
+ * Prepare to read connection handshake, or an ack.
+ */
+static void prepare_read_banner(struct ceph_connection *con)
+{
+	dout("prepare_read_banner %p\n", con);
+	con->in_base_pos = 0;
+}
+
+static void prepare_read_connect(struct ceph_connection *con)
+{
+	dout("prepare_read_connect %p\n", con);
+	con->in_base_pos = 0;
+}
+
+static void prepare_read_ack(struct ceph_connection *con)
+{
+	dout("prepare_read_ack %p\n", con);
+	con->in_base_pos = 0;
+}
+
+static void prepare_read_tag(struct ceph_connection *con)
+{
+	dout("prepare_read_tag %p\n", con);
+	con->in_base_pos = 0;
+	con->in_tag = CEPH_MSGR_TAG_READY;
+}
+
+/*
+ * Prepare to read a message.
+ */
+static int prepare_read_message(struct ceph_connection *con)
+{
+	dout("prepare_read_message %p\n", con);
+	BUG_ON(con->in_msg != NULL);
+	con->in_base_pos = 0;
+	con->in_front_crc = con->in_middle_crc = con->in_data_crc = 0;
+	return 0;
+}
+
+
+static int read_partial(struct ceph_connection *con,
+			int *to, int size, void *object)
+{
+	*to += size;
+	while (con->in_base_pos < *to) {
+		int left = *to - con->in_base_pos;
+		int have = size - left;
+		int ret = ceph_tcp_recvmsg(con->sock, object + have, left);
+		if (ret <= 0)
+			return ret;
+		con->in_base_pos += ret;
+	}
+	return 1;
+}
+
+
+/*
+ * Read all or part of the connect-side handshake on a new connection
+ */
+static int read_partial_banner(struct ceph_connection *con)
+{
+	int ret, to = 0;
+
+	dout("read_partial_banner %p at %d\n", con, con->in_base_pos);
+
+	/* peer's banner */
+	ret = read_partial(con, &to, strlen(CEPH_BANNER), con->in_banner);
+	if (ret <= 0)
+		goto out;
+	ret = read_partial(con, &to, sizeof(con->actual_peer_addr),
+			   &con->actual_peer_addr);
+	if (ret <= 0)
+		goto out;
+	ret = read_partial(con, &to, sizeof(con->peer_addr_for_me),
+			   &con->peer_addr_for_me);
+	if (ret <= 0)
+		goto out;
+out:
+	return ret;
+}
+
+static int read_partial_connect(struct ceph_connection *con)
+{
+	int ret, to = 0;
+
+	dout("read_partial_connect %p at %d\n", con, con->in_base_pos);
+
+	ret = read_partial(con, &to, sizeof(con->in_reply), &con->in_reply);
+	if (ret <= 0)
+		goto out;
+	ret = read_partial(con, &to, le32_to_cpu(con->in_reply.authorizer_len),
+			   con->auth_reply_buf);
+	if (ret <= 0)
+		goto out;
+
+	dout("read_partial_connect %p tag %d, con_seq = %u, g_seq = %u\n",
+	     con, (int)con->in_reply.tag,
+	     le32_to_cpu(con->in_reply.connect_seq),
+	     le32_to_cpu(con->in_reply.global_seq));
+out:
+	return ret;
+
+}
+
+/*
+ * Verify the hello banner looks okay.
+ */
+static int verify_hello(struct ceph_connection *con)
+{
+	if (memcmp(con->in_banner, CEPH_BANNER, strlen(CEPH_BANNER))) {
+		pr_err("connect to %s got bad banner\n",
+		       ceph_pr_addr(&con->peer_addr.in_addr));
+		con->error_msg = "protocol error, bad banner";
+		return -1;
+	}
+	return 0;
+}
+
+static bool addr_is_blank(struct sockaddr_storage *ss)
+{
+	switch (ss->ss_family) {
+	case AF_INET:
+		return ((struct sockaddr_in *)ss)->sin_addr.s_addr == 0;
+	case AF_INET6:
+		return
+		     ((struct sockaddr_in6 *)ss)->sin6_addr.s6_addr32[0] == 0 &&
+		     ((struct sockaddr_in6 *)ss)->sin6_addr.s6_addr32[1] == 0 &&
+		     ((struct sockaddr_in6 *)ss)->sin6_addr.s6_addr32[2] == 0 &&
+		     ((struct sockaddr_in6 *)ss)->sin6_addr.s6_addr32[3] == 0;
+	}
+	return false;
+}
+
+static int addr_port(struct sockaddr_storage *ss)
+{
+	switch (ss->ss_family) {
+	case AF_INET:
+		return ntohs(((struct sockaddr_in *)ss)->sin_port);
+	case AF_INET6:
+		return ntohs(((struct sockaddr_in6 *)ss)->sin6_port);
+	}
+	return 0;
+}
+
+static void addr_set_port(struct sockaddr_storage *ss, int p)
+{
+	switch (ss->ss_family) {
+	case AF_INET:
+		((struct sockaddr_in *)ss)->sin_port = htons(p);
+	case AF_INET6:
+		((struct sockaddr_in6 *)ss)->sin6_port = htons(p);
+	}
+}
+
+/*
+ * Parse an ip[:port] list into an addr array.  Use the default
+ * monitor port if a port isn't specified.
+ */
+int ceph_parse_ips(const char *c, const char *end,
+		   struct ceph_entity_addr *addr,
+		   int max_count, int *count)
+{
+	int i;
+	const char *p = c;
+
+	dout("parse_ips on '%.*s'\n", (int)(end-c), c);
+	for (i = 0; i < max_count; i++) {
+		const char *ipend;
+		struct sockaddr_storage *ss = &addr[i].in_addr;
+		struct sockaddr_in *in4 = (void *)ss;
+		struct sockaddr_in6 *in6 = (void *)ss;
+		int port;
+		char delim = ',';
+
+		if (*p == '[') {
+			delim = ']';
+			p++;
+		}
+
+		memset(ss, 0, sizeof(*ss));
+		if (in4_pton(p, end - p, (u8 *)&in4->sin_addr.s_addr,
+			     delim, &ipend))
+			ss->ss_family = AF_INET;
+		else if (in6_pton(p, end - p, (u8 *)&in6->sin6_addr.s6_addr,
+				  delim, &ipend))
+			ss->ss_family = AF_INET6;
+		else
+			goto bad;
+		p = ipend;
+
+		if (delim == ']') {
+			if (*p != ']') {
+				dout("missing matching ']'\n");
+				goto bad;
+			}
+			p++;
+		}
+
+		/* port? */
+		if (p < end && *p == ':') {
+			port = 0;
+			p++;
+			while (p < end && *p >= '0' && *p <= '9') {
+				port = (port * 10) + (*p - '0');
+				p++;
+			}
+			if (port > 65535 || port == 0)
+				goto bad;
+		} else {
+			port = CEPH_MON_PORT;
+		}
+
+		addr_set_port(ss, port);
+
+		dout("parse_ips got %s\n", ceph_pr_addr(ss));
+
+		if (p == end)
+			break;
+		if (*p != ',')
+			goto bad;
+		p++;
+	}
+
+	if (p != end)
+		goto bad;
+
+	if (count)
+		*count = i + 1;
+	return 0;
+
+bad:
+	pr_err("parse_ips bad ip '%.*s'\n", (int)(end - c), c);
+	return -EINVAL;
+}
+EXPORT_SYMBOL(ceph_parse_ips);
+
+static int process_banner(struct ceph_connection *con)
+{
+	dout("process_banner on %p\n", con);
+
+	if (verify_hello(con) < 0)
+		return -1;
+
+	ceph_decode_addr(&con->actual_peer_addr);
+	ceph_decode_addr(&con->peer_addr_for_me);
+
+	/*
+	 * Make sure the other end is who we wanted.  note that the other
+	 * end may not yet know their ip address, so if it's 0.0.0.0, give
+	 * them the benefit of the doubt.
+	 */
+	if (memcmp(&con->peer_addr, &con->actual_peer_addr,
+		   sizeof(con->peer_addr)) != 0 &&
+	    !(addr_is_blank(&con->actual_peer_addr.in_addr) &&
+	      con->actual_peer_addr.nonce == con->peer_addr.nonce)) {
+		pr_warning("wrong peer, want %s/%d, got %s/%d\n",
+			   ceph_pr_addr(&con->peer_addr.in_addr),
+			   (int)le32_to_cpu(con->peer_addr.nonce),
+			   ceph_pr_addr(&con->actual_peer_addr.in_addr),
+			   (int)le32_to_cpu(con->actual_peer_addr.nonce));
+		con->error_msg = "wrong peer at address";
+		return -1;
+	}
+
+	/*
+	 * did we learn our address?
+	 */
+	if (addr_is_blank(&con->msgr->inst.addr.in_addr)) {
+		int port = addr_port(&con->msgr->inst.addr.in_addr);
+
+		memcpy(&con->msgr->inst.addr.in_addr,
+		       &con->peer_addr_for_me.in_addr,
+		       sizeof(con->peer_addr_for_me.in_addr));
+		addr_set_port(&con->msgr->inst.addr.in_addr, port);
+		encode_my_addr(con->msgr);
+		dout("process_banner learned my addr is %s\n",
+		     ceph_pr_addr(&con->msgr->inst.addr.in_addr));
+	}
+
+	set_bit(NEGOTIATING, &con->state);
+	prepare_read_connect(con);
+	return 0;
+}
+
+static void fail_protocol(struct ceph_connection *con)
+{
+	reset_connection(con);
+	set_bit(CLOSED, &con->state);  /* in case there's queued work */
+
+	mutex_unlock(&con->mutex);
+	if (con->ops->bad_proto)
+		con->ops->bad_proto(con);
+	mutex_lock(&con->mutex);
+}
+
+static int process_connect(struct ceph_connection *con)
+{
+	u64 sup_feat = con->msgr->supported_features;
+	u64 req_feat = con->msgr->required_features;
+	u64 server_feat = le64_to_cpu(con->in_reply.features);
+
+	dout("process_connect on %p tag %d\n", con, (int)con->in_tag);
+
+	switch (con->in_reply.tag) {
+	case CEPH_MSGR_TAG_FEATURES:
+		pr_err("%s%lld %s feature set mismatch,"
+		       " my %llx < server's %llx, missing %llx\n",
+		       ENTITY_NAME(con->peer_name),
+		       ceph_pr_addr(&con->peer_addr.in_addr),
+		       sup_feat, server_feat, server_feat & ~sup_feat);
+		con->error_msg = "missing required protocol features";
+		fail_protocol(con);
+		return -1;
+
+	case CEPH_MSGR_TAG_BADPROTOVER:
+		pr_err("%s%lld %s protocol version mismatch,"
+		       " my %d != server's %d\n",
+		       ENTITY_NAME(con->peer_name),
+		       ceph_pr_addr(&con->peer_addr.in_addr),
+		       le32_to_cpu(con->out_connect.protocol_version),
+		       le32_to_cpu(con->in_reply.protocol_version));
+		con->error_msg = "protocol version mismatch";
+		fail_protocol(con);
+		return -1;
+
+	case CEPH_MSGR_TAG_BADAUTHORIZER:
+		con->auth_retry++;
+		dout("process_connect %p got BADAUTHORIZER attempt %d\n", con,
+		     con->auth_retry);
+		if (con->auth_retry == 2) {
+			con->error_msg = "connect authorization failure";
+			reset_connection(con);
+			set_bit(CLOSED, &con->state);
+			return -1;
+		}
+		con->auth_retry = 1;
+		prepare_write_connect(con->msgr, con, 0);
+		prepare_read_connect(con);
+		break;
+
+	case CEPH_MSGR_TAG_RESETSESSION:
+		/*
+		 * If we connected with a large connect_seq but the peer
+		 * has no record of a session with us (no connection, or
+		 * connect_seq == 0), they will send RESETSESION to indicate
+		 * that they must have reset their session, and may have
+		 * dropped messages.
+		 */
+		dout("process_connect got RESET peer seq %u\n",
+		     le32_to_cpu(con->in_connect.connect_seq));
+		pr_err("%s%lld %s connection reset\n",
+		       ENTITY_NAME(con->peer_name),
+		       ceph_pr_addr(&con->peer_addr.in_addr));
+		reset_connection(con);
+		prepare_write_connect(con->msgr, con, 0);
+		prepare_read_connect(con);
+
+		/* Tell ceph about it. */
+		mutex_unlock(&con->mutex);
+		pr_info("reset on %s%lld\n", ENTITY_NAME(con->peer_name));
+		if (con->ops->peer_reset)
+			con->ops->peer_reset(con);
+		mutex_lock(&con->mutex);
+		break;
+
+	case CEPH_MSGR_TAG_RETRY_SESSION:
+		/*
+		 * If we sent a smaller connect_seq than the peer has, try
+		 * again with a larger value.
+		 */
+		dout("process_connect got RETRY my seq = %u, peer_seq = %u\n",
+		     le32_to_cpu(con->out_connect.connect_seq),
+		     le32_to_cpu(con->in_connect.connect_seq));
+		con->connect_seq = le32_to_cpu(con->in_connect.connect_seq);
+		prepare_write_connect(con->msgr, con, 0);
+		prepare_read_connect(con);
+		break;
+
+	case CEPH_MSGR_TAG_RETRY_GLOBAL:
+		/*
+		 * If we sent a smaller global_seq than the peer has, try
+		 * again with a larger value.
+		 */
+		dout("process_connect got RETRY_GLOBAL my %u peer_gseq %u\n",
+		     con->peer_global_seq,
+		     le32_to_cpu(con->in_connect.global_seq));
+		get_global_seq(con->msgr,
+			       le32_to_cpu(con->in_connect.global_seq));
+		prepare_write_connect(con->msgr, con, 0);
+		prepare_read_connect(con);
+		break;
+
+	case CEPH_MSGR_TAG_READY:
+		if (req_feat & ~server_feat) {
+			pr_err("%s%lld %s protocol feature mismatch,"
+			       " my required %llx > server's %llx, need %llx\n",
+			       ENTITY_NAME(con->peer_name),
+			       ceph_pr_addr(&con->peer_addr.in_addr),
+			       req_feat, server_feat, req_feat & ~server_feat);
+			con->error_msg = "missing required protocol features";
+			fail_protocol(con);
+			return -1;
+		}
+		clear_bit(CONNECTING, &con->state);
+		con->peer_global_seq = le32_to_cpu(con->in_reply.global_seq);
+		con->connect_seq++;
+		con->peer_features = server_feat;
+		dout("process_connect got READY gseq %d cseq %d (%d)\n",
+		     con->peer_global_seq,
+		     le32_to_cpu(con->in_reply.connect_seq),
+		     con->connect_seq);
+		WARN_ON(con->connect_seq !=
+			le32_to_cpu(con->in_reply.connect_seq));
+
+		if (con->in_reply.flags & CEPH_MSG_CONNECT_LOSSY)
+			set_bit(LOSSYTX, &con->state);
+
+		prepare_read_tag(con);
+		break;
+
+	case CEPH_MSGR_TAG_WAIT:
+		/*
+		 * If there is a connection race (we are opening
+		 * connections to each other), one of us may just have
+		 * to WAIT.  This shouldn't happen if we are the
+		 * client.
+		 */
+		pr_err("process_connect peer connecting WAIT\n");
+
+	default:
+		pr_err("connect protocol error, will retry\n");
+		con->error_msg = "protocol error, garbage tag during connect";
+		return -1;
+	}
+	return 0;
+}
+
+
+/*
+ * read (part of) an ack
+ */
+static int read_partial_ack(struct ceph_connection *con)
+{
+	int to = 0;
+
+	return read_partial(con, &to, sizeof(con->in_temp_ack),
+			    &con->in_temp_ack);
+}
+
+
+/*
+ * We can finally discard anything that's been acked.
+ */
+static void process_ack(struct ceph_connection *con)
+{
+	struct ceph_msg *m;
+	u64 ack = le64_to_cpu(con->in_temp_ack);
+	u64 seq;
+
+	while (!list_empty(&con->out_sent)) {
+		m = list_first_entry(&con->out_sent, struct ceph_msg,
+				     list_head);
+		seq = le64_to_cpu(m->hdr.seq);
+		if (seq > ack)
+			break;
+		dout("got ack for seq %llu type %d at %p\n", seq,
+		     le16_to_cpu(m->hdr.type), m);
+		ceph_msg_remove(m);
+	}
+	prepare_read_tag(con);
+}
+
+
+
+
+static int read_partial_message_section(struct ceph_connection *con,
+					struct kvec *section,
+					unsigned int sec_len, u32 *crc)
+{
+	int ret, left;
+
+	BUG_ON(!section);
+
+	while (section->iov_len < sec_len) {
+		BUG_ON(section->iov_base == NULL);
+		left = sec_len - section->iov_len;
+		ret = ceph_tcp_recvmsg(con->sock, (char *)section->iov_base +
+				       section->iov_len, left);
+		if (ret <= 0)
+			return ret;
+		section->iov_len += ret;
+		if (section->iov_len == sec_len)
+			*crc = crc32c(0, section->iov_base,
+				      section->iov_len);
+	}
+
+	return 1;
+}
+
+static struct ceph_msg *ceph_alloc_msg(struct ceph_connection *con,
+				struct ceph_msg_header *hdr,
+				int *skip);
+
+
+static int read_partial_message_pages(struct ceph_connection *con,
+				      struct page **pages,
+				      unsigned data_len, int datacrc)
+{
+	void *p;
+	int ret;
+	int left;
+
+	left = min((int)(data_len - con->in_msg_pos.data_pos),
+		   (int)(PAGE_SIZE - con->in_msg_pos.page_pos));
+	/* (page) data */
+	BUG_ON(pages == NULL);
+	p = kmap(pages[con->in_msg_pos.page]);
+	ret = ceph_tcp_recvmsg(con->sock, p + con->in_msg_pos.page_pos,
+			       left);
+	if (ret > 0 && datacrc)
+		con->in_data_crc =
+			crc32c(con->in_data_crc,
+				  p + con->in_msg_pos.page_pos, ret);
+	kunmap(pages[con->in_msg_pos.page]);
+	if (ret <= 0)
+		return ret;
+	con->in_msg_pos.data_pos += ret;
+	con->in_msg_pos.page_pos += ret;
+	if (con->in_msg_pos.page_pos == PAGE_SIZE) {
+		con->in_msg_pos.page_pos = 0;
+		con->in_msg_pos.page++;
+	}
+
+	return ret;
+}
+
+#ifdef CONFIG_BLOCK
+static int read_partial_message_bio(struct ceph_connection *con,
+				    struct bio **bio_iter, int *bio_seg,
+				    unsigned data_len, int datacrc)
+{
+	struct bio_vec *bv = bio_iovec_idx(*bio_iter, *bio_seg);
+	void *p;
+	int ret, left;
+
+	if (IS_ERR(bv))
+		return PTR_ERR(bv);
+
+	left = min((int)(data_len - con->in_msg_pos.data_pos),
+		   (int)(bv->bv_len - con->in_msg_pos.page_pos));
+
+	p = kmap(bv->bv_page) + bv->bv_offset;
+
+	ret = ceph_tcp_recvmsg(con->sock, p + con->in_msg_pos.page_pos,
+			       left);
+	if (ret > 0 && datacrc)
+		con->in_data_crc =
+			crc32c(con->in_data_crc,
+				  p + con->in_msg_pos.page_pos, ret);
+	kunmap(bv->bv_page);
+	if (ret <= 0)
+		return ret;
+	con->in_msg_pos.data_pos += ret;
+	con->in_msg_pos.page_pos += ret;
+	if (con->in_msg_pos.page_pos == bv->bv_len) {
+		con->in_msg_pos.page_pos = 0;
+		iter_bio_next(bio_iter, bio_seg);
+	}
+
+	return ret;
+}
+#endif
+
+/*
+ * read (part of) a message.
+ */
+static int read_partial_message(struct ceph_connection *con)
+{
+	struct ceph_msg *m = con->in_msg;
+	int ret;
+	int to, left;
+	unsigned front_len, middle_len, data_len, data_off;
+	int datacrc = con->msgr->nocrc;
+	int skip;
+	u64 seq;
+
+	dout("read_partial_message con %p msg %p\n", con, m);
+
+	/* header */
+	while (con->in_base_pos < sizeof(con->in_hdr)) {
+		left = sizeof(con->in_hdr) - con->in_base_pos;
+		ret = ceph_tcp_recvmsg(con->sock,
+				       (char *)&con->in_hdr + con->in_base_pos,
+				       left);
+		if (ret <= 0)
+			return ret;
+		con->in_base_pos += ret;
+		if (con->in_base_pos == sizeof(con->in_hdr)) {
+			u32 crc = crc32c(0, (void *)&con->in_hdr,
+				 sizeof(con->in_hdr) - sizeof(con->in_hdr.crc));
+			if (crc != le32_to_cpu(con->in_hdr.crc)) {
+				pr_err("read_partial_message bad hdr "
+				       " crc %u != expected %u\n",
+				       crc, con->in_hdr.crc);
+				return -EBADMSG;
+			}
+		}
+	}
+	front_len = le32_to_cpu(con->in_hdr.front_len);
+	if (front_len > CEPH_MSG_MAX_FRONT_LEN)
+		return -EIO;
+	middle_len = le32_to_cpu(con->in_hdr.middle_len);
+	if (middle_len > CEPH_MSG_MAX_DATA_LEN)
+		return -EIO;
+	data_len = le32_to_cpu(con->in_hdr.data_len);
+	if (data_len > CEPH_MSG_MAX_DATA_LEN)
+		return -EIO;
+	data_off = le16_to_cpu(con->in_hdr.data_off);
+
+	/* verify seq# */
+	seq = le64_to_cpu(con->in_hdr.seq);
+	if ((s64)seq - (s64)con->in_seq < 1) {
+		pr_info("skipping %s%lld %s seq %lld, expected %lld\n",
+			ENTITY_NAME(con->peer_name),
+			ceph_pr_addr(&con->peer_addr.in_addr),
+			seq, con->in_seq + 1);
+		con->in_base_pos = -front_len - middle_len - data_len -
+			sizeof(m->footer);
+		con->in_tag = CEPH_MSGR_TAG_READY;
+		con->in_seq++;
+		return 0;
+	} else if ((s64)seq - (s64)con->in_seq > 1) {
+		pr_err("read_partial_message bad seq %lld expected %lld\n",
+		       seq, con->in_seq + 1);
+		con->error_msg = "bad message sequence # for incoming message";
+		return -EBADMSG;
+	}
+
+	/* allocate message? */
+	if (!con->in_msg) {
+		dout("got hdr type %d front %d data %d\n", con->in_hdr.type,
+		     con->in_hdr.front_len, con->in_hdr.data_len);
+		skip = 0;
+		con->in_msg = ceph_alloc_msg(con, &con->in_hdr, &skip);
+		if (skip) {
+			/* skip this message */
+			dout("alloc_msg said skip message\n");
+			BUG_ON(con->in_msg);
+			con->in_base_pos = -front_len - middle_len - data_len -
+				sizeof(m->footer);
+			con->in_tag = CEPH_MSGR_TAG_READY;
+			con->in_seq++;
+			return 0;
+		}
+		if (!con->in_msg) {
+			con->error_msg =
+				"error allocating memory for incoming message";
+			return -ENOMEM;
+		}
+		m = con->in_msg;
+		m->front.iov_len = 0;    /* haven't read it yet */
+		if (m->middle)
+			m->middle->vec.iov_len = 0;
+
+		con->in_msg_pos.page = 0;
+		if (m->pages)
+			con->in_msg_pos.page_pos = data_off & ~PAGE_MASK;
+		else
+			con->in_msg_pos.page_pos = 0;
+		con->in_msg_pos.data_pos = 0;
+	}
+
+	/* front */
+	ret = read_partial_message_section(con, &m->front, front_len,
+					   &con->in_front_crc);
+	if (ret <= 0)
+		return ret;
+
+	/* middle */
+	if (m->middle) {
+		ret = read_partial_message_section(con, &m->middle->vec,
+						   middle_len,
+						   &con->in_middle_crc);
+		if (ret <= 0)
+			return ret;
+	}
+#ifdef CONFIG_BLOCK
+	if (m->bio && !m->bio_iter)
+		init_bio_iter(m->bio, &m->bio_iter, &m->bio_seg);
+#endif
+
+	/* (page) data */
+	while (con->in_msg_pos.data_pos < data_len) {
+		if (m->pages) {
+			ret = read_partial_message_pages(con, m->pages,
+						 data_len, datacrc);
+			if (ret <= 0)
+				return ret;
+#ifdef CONFIG_BLOCK
+		} else if (m->bio) {
+
+			ret = read_partial_message_bio(con,
+						 &m->bio_iter, &m->bio_seg,
+						 data_len, datacrc);
+			if (ret <= 0)
+				return ret;
+#endif
+		} else {
+			BUG_ON(1);
+		}
+	}
+
+	/* footer */
+	to = sizeof(m->hdr) + sizeof(m->footer);
+	while (con->in_base_pos < to) {
+		left = to - con->in_base_pos;
+		ret = ceph_tcp_recvmsg(con->sock, (char *)&m->footer +
+				       (con->in_base_pos - sizeof(m->hdr)),
+				       left);
+		if (ret <= 0)
+			return ret;
+		con->in_base_pos += ret;
+	}
+	dout("read_partial_message got msg %p %d (%u) + %d (%u) + %d (%u)\n",
+	     m, front_len, m->footer.front_crc, middle_len,
+	     m->footer.middle_crc, data_len, m->footer.data_crc);
+
+	/* crc ok? */
+	if (con->in_front_crc != le32_to_cpu(m->footer.front_crc)) {
+		pr_err("read_partial_message %p front crc %u != exp. %u\n",
+		       m, con->in_front_crc, m->footer.front_crc);
+		return -EBADMSG;
+	}
+	if (con->in_middle_crc != le32_to_cpu(m->footer.middle_crc)) {
+		pr_err("read_partial_message %p middle crc %u != exp %u\n",
+		       m, con->in_middle_crc, m->footer.middle_crc);
+		return -EBADMSG;
+	}
+	if (datacrc &&
+	    (m->footer.flags & CEPH_MSG_FOOTER_NOCRC) == 0 &&
+	    con->in_data_crc != le32_to_cpu(m->footer.data_crc)) {
+		pr_err("read_partial_message %p data crc %u != exp. %u\n", m,
+		       con->in_data_crc, le32_to_cpu(m->footer.data_crc));
+		return -EBADMSG;
+	}
+
+	return 1; /* done! */
+}
+
+/*
+ * Process message.  This happens in the worker thread.  The callback should
+ * be careful not to do anything that waits on other incoming messages or it
+ * may deadlock.
+ */
+static void process_message(struct ceph_connection *con)
+{
+	struct ceph_msg *msg;
+
+	msg = con->in_msg;
+	con->in_msg = NULL;
+
+	/* if first message, set peer_name */
+	if (con->peer_name.type == 0)
+		con->peer_name = msg->hdr.src;
+
+	con->in_seq++;
+	mutex_unlock(&con->mutex);
+
+	dout("===== %p %llu from %s%lld %d=%s len %d+%d (%u %u %u) =====\n",
+	     msg, le64_to_cpu(msg->hdr.seq),
+	     ENTITY_NAME(msg->hdr.src),
+	     le16_to_cpu(msg->hdr.type),
+	     ceph_msg_type_name(le16_to_cpu(msg->hdr.type)),
+	     le32_to_cpu(msg->hdr.front_len),
+	     le32_to_cpu(msg->hdr.data_len),
+	     con->in_front_crc, con->in_middle_crc, con->in_data_crc);
+	con->ops->dispatch(con, msg);
+
+	mutex_lock(&con->mutex);
+	prepare_read_tag(con);
+}
+
+
+/*
+ * Write something to the socket.  Called in a worker thread when the
+ * socket appears to be writeable and we have something ready to send.
+ */
+static int try_write(struct ceph_connection *con)
+{
+	struct ceph_messenger *msgr = con->msgr;
+	int ret = 1;
+
+	dout("try_write start %p state %lu nref %d\n", con, con->state,
+	     atomic_read(&con->nref));
+
+more:
+	dout("try_write out_kvec_bytes %d\n", con->out_kvec_bytes);
+
+	/* open the socket first? */
+	if (con->sock == NULL) {
+		/*
+		 * if we were STANDBY and are reconnecting _this_
+		 * connection, bump connect_seq now.  Always bump
+		 * global_seq.
+		 */
+		if (test_and_clear_bit(STANDBY, &con->state))
+			con->connect_seq++;
+
+		prepare_write_banner(msgr, con);
+		prepare_write_connect(msgr, con, 1);
+		prepare_read_banner(con);
+		set_bit(CONNECTING, &con->state);
+		clear_bit(NEGOTIATING, &con->state);
+
+		BUG_ON(con->in_msg);
+		con->in_tag = CEPH_MSGR_TAG_READY;
+		dout("try_write initiating connect on %p new state %lu\n",
+		     con, con->state);
+		con->sock = ceph_tcp_connect(con);
+		if (IS_ERR(con->sock)) {
+			con->sock = NULL;
+			con->error_msg = "connect error";
+			ret = -1;
+			goto out;
+		}
+	}
+
+more_kvec:
+	/* kvec data queued? */
+	if (con->out_skip) {
+		ret = write_partial_skip(con);
+		if (ret <= 0)
+			goto done;
+		if (ret < 0) {
+			dout("try_write write_partial_skip err %d\n", ret);
+			goto done;
+		}
+	}
+	if (con->out_kvec_left) {
+		ret = write_partial_kvec(con);
+		if (ret <= 0)
+			goto done;
+	}
+
+	/* msg pages? */
+	if (con->out_msg) {
+		if (con->out_msg_done) {
+			ceph_msg_put(con->out_msg);
+			con->out_msg = NULL;   /* we're done with this one */
+			goto do_next;
+		}
+
+		ret = write_partial_msg_pages(con);
+		if (ret == 1)
+			goto more_kvec;  /* we need to send the footer, too! */
+		if (ret == 0)
+			goto done;
+		if (ret < 0) {
+			dout("try_write write_partial_msg_pages err %d\n",
+			     ret);
+			goto done;
+		}
+	}
+
+do_next:
+	if (!test_bit(CONNECTING, &con->state)) {
+		/* is anything else pending? */
+		if (!list_empty(&con->out_queue)) {
+			prepare_write_message(con);
+			goto more;
+		}
+		if (con->in_seq > con->in_seq_acked) {
+			prepare_write_ack(con);
+			goto more;
+		}
+		if (test_and_clear_bit(KEEPALIVE_PENDING, &con->state)) {
+			prepare_write_keepalive(con);
+			goto more;
+		}
+	}
+
+	/* Nothing to do! */
+	clear_bit(WRITE_PENDING, &con->state);
+	dout("try_write nothing else to write.\n");
+done:
+	ret = 0;
+out:
+	dout("try_write done on %p\n", con);
+	return ret;
+}
+
+
+
+/*
+ * Read what we can from the socket.
+ */
+static int try_read(struct ceph_connection *con)
+{
+	int ret = -1;
+
+	if (!con->sock)
+		return 0;
+
+	if (test_bit(STANDBY, &con->state))
+		return 0;
+
+	dout("try_read start on %p\n", con);
+
+more:
+	dout("try_read tag %d in_base_pos %d\n", (int)con->in_tag,
+	     con->in_base_pos);
+	if (test_bit(CONNECTING, &con->state)) {
+		if (!test_bit(NEGOTIATING, &con->state)) {
+			dout("try_read connecting\n");
+			ret = read_partial_banner(con);
+			if (ret <= 0)
+				goto done;
+			if (process_banner(con) < 0) {
+				ret = -1;
+				goto out;
+			}
+		}
+		ret = read_partial_connect(con);
+		if (ret <= 0)
+			goto done;
+		if (process_connect(con) < 0) {
+			ret = -1;
+			goto out;
+		}
+		goto more;
+	}
+
+	if (con->in_base_pos < 0) {
+		/*
+		 * skipping + discarding content.
+		 *
+		 * FIXME: there must be a better way to do this!
+		 */
+		static char buf[1024];
+		int skip = min(1024, -con->in_base_pos);
+		dout("skipping %d / %d bytes\n", skip, -con->in_base_pos);
+		ret = ceph_tcp_recvmsg(con->sock, buf, skip);
+		if (ret <= 0)
+			goto done;
+		con->in_base_pos += ret;
+		if (con->in_base_pos)
+			goto more;
+	}
+	if (con->in_tag == CEPH_MSGR_TAG_READY) {
+		/*
+		 * what's next?
+		 */
+		ret = ceph_tcp_recvmsg(con->sock, &con->in_tag, 1);
+		if (ret <= 0)
+			goto done;
+		dout("try_read got tag %d\n", (int)con->in_tag);
+		switch (con->in_tag) {
+		case CEPH_MSGR_TAG_MSG:
+			prepare_read_message(con);
+			break;
+		case CEPH_MSGR_TAG_ACK:
+			prepare_read_ack(con);
+			break;
+		case CEPH_MSGR_TAG_CLOSE:
+			set_bit(CLOSED, &con->state);   /* fixme */
+			goto done;
+		default:
+			goto bad_tag;
+		}
+	}
+	if (con->in_tag == CEPH_MSGR_TAG_MSG) {
+		ret = read_partial_message(con);
+		if (ret <= 0) {
+			switch (ret) {
+			case -EBADMSG:
+				con->error_msg = "bad crc";
+				ret = -EIO;
+				goto out;
+			case -EIO:
+				con->error_msg = "io error";
+				goto out;
+			default:
+				goto done;
+			}
+		}
+		if (con->in_tag == CEPH_MSGR_TAG_READY)
+			goto more;
+		process_message(con);
+		goto more;
+	}
+	if (con->in_tag == CEPH_MSGR_TAG_ACK) {
+		ret = read_partial_ack(con);
+		if (ret <= 0)
+			goto done;
+		process_ack(con);
+		goto more;
+	}
+
+done:
+	ret = 0;
+out:
+	dout("try_read done on %p\n", con);
+	return ret;
+
+bad_tag:
+	pr_err("try_read bad con->in_tag = %d\n", (int)con->in_tag);
+	con->error_msg = "protocol error, garbage tag";
+	ret = -1;
+	goto out;
+}
+
+
+/*
+ * Atomically queue work on a connection.  Bump @con reference to
+ * avoid races with connection teardown.
+ *
+ * There is some trickery going on with QUEUED and BUSY because we
+ * only want a _single_ thread operating on each connection at any
+ * point in time, but we want to use all available CPUs.
+ *
+ * The worker thread only proceeds if it can atomically set BUSY.  It
+ * clears QUEUED and does it's thing.  When it thinks it's done, it
+ * clears BUSY, then rechecks QUEUED.. if it's set again, it loops
+ * (tries again to set BUSY).
+ *
+ * To queue work, we first set QUEUED, _then_ if BUSY isn't set, we
+ * try to queue work.  If that fails (work is already queued, or BUSY)
+ * we give up (work also already being done or is queued) but leave QUEUED
+ * set so that the worker thread will loop if necessary.
+ */
+static void queue_con(struct ceph_connection *con)
+{
+	if (test_bit(DEAD, &con->state)) {
+		dout("queue_con %p ignoring: DEAD\n",
+		     con);
+		return;
+	}
+
+	if (!con->ops->get(con)) {
+		dout("queue_con %p ref count 0\n", con);
+		return;
+	}
+
+	set_bit(QUEUED, &con->state);
+	if (test_bit(BUSY, &con->state)) {
+		dout("queue_con %p - already BUSY\n", con);
+		con->ops->put(con);
+	} else if (!queue_work(ceph_msgr_wq, &con->work.work)) {
+		dout("queue_con %p - already queued\n", con);
+		con->ops->put(con);
+	} else {
+		dout("queue_con %p\n", con);
+	}
+}
+
+/*
+ * Do some work on a connection.  Drop a connection ref when we're done.
+ */
+static void con_work(struct work_struct *work)
+{
+	struct ceph_connection *con = container_of(work, struct ceph_connection,
+						   work.work);
+	int backoff = 0;
+
+more:
+	if (test_and_set_bit(BUSY, &con->state) != 0) {
+		dout("con_work %p BUSY already set\n", con);
+		goto out;
+	}
+	dout("con_work %p start, clearing QUEUED\n", con);
+	clear_bit(QUEUED, &con->state);
+
+	mutex_lock(&con->mutex);
+
+	if (test_bit(CLOSED, &con->state)) { /* e.g. if we are replaced */
+		dout("con_work CLOSED\n");
+		con_close_socket(con);
+		goto done;
+	}
+	if (test_and_clear_bit(OPENING, &con->state)) {
+		/* reopen w/ new peer */
+		dout("con_work OPENING\n");
+		con_close_socket(con);
+	}
+
+	if (test_and_clear_bit(SOCK_CLOSED, &con->state) ||
+	    try_read(con) < 0 ||
+	    try_write(con) < 0) {
+		mutex_unlock(&con->mutex);
+		backoff = 1;
+		ceph_fault(con);     /* error/fault path */
+		goto done_unlocked;
+	}
+
+done:
+	mutex_unlock(&con->mutex);
+
+done_unlocked:
+	clear_bit(BUSY, &con->state);
+	dout("con->state=%lu\n", con->state);
+	if (test_bit(QUEUED, &con->state)) {
+		if (!backoff || test_bit(OPENING, &con->state)) {
+			dout("con_work %p QUEUED reset, looping\n", con);
+			goto more;
+		}
+		dout("con_work %p QUEUED reset, but just faulted\n", con);
+		clear_bit(QUEUED, &con->state);
+	}
+	dout("con_work %p done\n", con);
+
+out:
+	con->ops->put(con);
+}
+
+
+/*
+ * Generic error/fault handler.  A retry mechanism is used with
+ * exponential backoff
+ */
+static void ceph_fault(struct ceph_connection *con)
+{
+	pr_err("%s%lld %s %s\n", ENTITY_NAME(con->peer_name),
+	       ceph_pr_addr(&con->peer_addr.in_addr), con->error_msg);
+	dout("fault %p state %lu to peer %s\n",
+	     con, con->state, ceph_pr_addr(&con->peer_addr.in_addr));
+
+	if (test_bit(LOSSYTX, &con->state)) {
+		dout("fault on LOSSYTX channel\n");
+		goto out;
+	}
+
+	mutex_lock(&con->mutex);
+	if (test_bit(CLOSED, &con->state))
+		goto out_unlock;
+
+	con_close_socket(con);
+
+	if (con->in_msg) {
+		ceph_msg_put(con->in_msg);
+		con->in_msg = NULL;
+	}
+
+	/* Requeue anything that hasn't been acked */
+	list_splice_init(&con->out_sent, &con->out_queue);
+
+	/* If there are no messages in the queue, place the connection
+	 * in a STANDBY state (i.e., don't try to reconnect just yet). */
+	if (list_empty(&con->out_queue) && !con->out_keepalive_pending) {
+		dout("fault setting STANDBY\n");
+		set_bit(STANDBY, &con->state);
+	} else {
+		/* retry after a delay. */
+		if (con->delay == 0)
+			con->delay = BASE_DELAY_INTERVAL;
+		else if (con->delay < MAX_DELAY_INTERVAL)
+			con->delay *= 2;
+		dout("fault queueing %p delay %lu\n", con, con->delay);
+		con->ops->get(con);
+		if (queue_delayed_work(ceph_msgr_wq, &con->work,
+				       round_jiffies_relative(con->delay)) == 0)
+			con->ops->put(con);
+	}
+
+out_unlock:
+	mutex_unlock(&con->mutex);
+out:
+	/*
+	 * in case we faulted due to authentication, invalidate our
+	 * current tickets so that we can get new ones.
+	 */
+	if (con->auth_retry && con->ops->invalidate_authorizer) {
+		dout("calling invalidate_authorizer()\n");
+		con->ops->invalidate_authorizer(con);
+	}
+
+	if (con->ops->fault)
+		con->ops->fault(con);
+}
+
+
+
+/*
+ * create a new messenger instance
+ */
+struct ceph_messenger *ceph_messenger_create(struct ceph_entity_addr *myaddr,
+					     u32 supported_features,
+					     u32 required_features)
+{
+	struct ceph_messenger *msgr;
+
+	msgr = kzalloc(sizeof(*msgr), GFP_KERNEL);
+	if (msgr == NULL)
+		return ERR_PTR(-ENOMEM);
+
+	msgr->supported_features = supported_features;
+	msgr->required_features = required_features;
+
+	spin_lock_init(&msgr->global_seq_lock);
+
+	/* the zero page is needed if a request is "canceled" while the message
+	 * is being written over the socket */
+	msgr->zero_page = __page_cache_alloc(GFP_KERNEL | __GFP_ZERO);
+	if (!msgr->zero_page) {
+		kfree(msgr);
+		return ERR_PTR(-ENOMEM);
+	}
+	kmap(msgr->zero_page);
+
+	if (myaddr)
+		msgr->inst.addr = *myaddr;
+
+	/* select a random nonce */
+	msgr->inst.addr.type = 0;
+	get_random_bytes(&msgr->inst.addr.nonce, sizeof(msgr->inst.addr.nonce));
+	encode_my_addr(msgr);
+
+	dout("messenger_create %p\n", msgr);
+	return msgr;
+}
+EXPORT_SYMBOL(ceph_messenger_create);
+
+void ceph_messenger_destroy(struct ceph_messenger *msgr)
+{
+	dout("destroy %p\n", msgr);
+	kunmap(msgr->zero_page);
+	__free_page(msgr->zero_page);
+	kfree(msgr);
+	dout("destroyed messenger %p\n", msgr);
+}
+EXPORT_SYMBOL(ceph_messenger_destroy);
+
+/*
+ * Queue up an outgoing message on the given connection.
+ */
+void ceph_con_send(struct ceph_connection *con, struct ceph_msg *msg)
+{
+	if (test_bit(CLOSED, &con->state)) {
+		dout("con_send %p closed, dropping %p\n", con, msg);
+		ceph_msg_put(msg);
+		return;
+	}
+
+	/* set src+dst */
+	msg->hdr.src = con->msgr->inst.name;
+
+	BUG_ON(msg->front.iov_len != le32_to_cpu(msg->hdr.front_len));
+
+	msg->needs_out_seq = true;
+
+	/* queue */
+	mutex_lock(&con->mutex);
+	BUG_ON(!list_empty(&msg->list_head));
+	list_add_tail(&msg->list_head, &con->out_queue);
+	dout("----- %p to %s%lld %d=%s len %d+%d+%d -----\n", msg,
+	     ENTITY_NAME(con->peer_name), le16_to_cpu(msg->hdr.type),
+	     ceph_msg_type_name(le16_to_cpu(msg->hdr.type)),
+	     le32_to_cpu(msg->hdr.front_len),
+	     le32_to_cpu(msg->hdr.middle_len),
+	     le32_to_cpu(msg->hdr.data_len));
+	mutex_unlock(&con->mutex);
+
+	/* if there wasn't anything waiting to send before, queue
+	 * new work */
+	if (test_and_set_bit(WRITE_PENDING, &con->state) == 0)
+		queue_con(con);
+}
+EXPORT_SYMBOL(ceph_con_send);
+
+/*
+ * Revoke a message that was previously queued for send
+ */
+void ceph_con_revoke(struct ceph_connection *con, struct ceph_msg *msg)
+{
+	mutex_lock(&con->mutex);
+	if (!list_empty(&msg->list_head)) {
+		dout("con_revoke %p msg %p - was on queue\n", con, msg);
+		list_del_init(&msg->list_head);
+		ceph_msg_put(msg);
+		msg->hdr.seq = 0;
+	}
+	if (con->out_msg == msg) {
+		dout("con_revoke %p msg %p - was sending\n", con, msg);
+		con->out_msg = NULL;
+		if (con->out_kvec_is_msg) {
+			con->out_skip = con->out_kvec_bytes;
+			con->out_kvec_is_msg = false;
+		}
+		ceph_msg_put(msg);
+		msg->hdr.seq = 0;
+	}
+	mutex_unlock(&con->mutex);
+}
+
+/*
+ * Revoke a message that we may be reading data into
+ */
+void ceph_con_revoke_message(struct ceph_connection *con, struct ceph_msg *msg)
+{
+	mutex_lock(&con->mutex);
+	if (con->in_msg && con->in_msg == msg) {
+		unsigned front_len = le32_to_cpu(con->in_hdr.front_len);
+		unsigned middle_len = le32_to_cpu(con->in_hdr.middle_len);
+		unsigned data_len = le32_to_cpu(con->in_hdr.data_len);
+
+		/* skip rest of message */
+		dout("con_revoke_pages %p msg %p revoked\n", con, msg);
+			con->in_base_pos = con->in_base_pos -
+				sizeof(struct ceph_msg_header) -
+				front_len -
+				middle_len -
+				data_len -
+				sizeof(struct ceph_msg_footer);
+		ceph_msg_put(con->in_msg);
+		con->in_msg = NULL;
+		con->in_tag = CEPH_MSGR_TAG_READY;
+		con->in_seq++;
+	} else {
+		dout("con_revoke_pages %p msg %p pages %p no-op\n",
+		     con, con->in_msg, msg);
+	}
+	mutex_unlock(&con->mutex);
+}
+
+/*
+ * Queue a keepalive byte to ensure the tcp connection is alive.
+ */
+void ceph_con_keepalive(struct ceph_connection *con)
+{
+	if (test_and_set_bit(KEEPALIVE_PENDING, &con->state) == 0 &&
+	    test_and_set_bit(WRITE_PENDING, &con->state) == 0)
+		queue_con(con);
+}
+EXPORT_SYMBOL(ceph_con_keepalive);
+
+
+/*
+ * construct a new message with given type, size
+ * the new msg has a ref count of 1.
+ */
+struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags)
+{
+	struct ceph_msg *m;
+
+	m = kmalloc(sizeof(*m), flags);
+	if (m == NULL)
+		goto out;
+	kref_init(&m->kref);
+	INIT_LIST_HEAD(&m->list_head);
+
+	m->hdr.tid = 0;
+	m->hdr.type = cpu_to_le16(type);
+	m->hdr.priority = cpu_to_le16(CEPH_MSG_PRIO_DEFAULT);
+	m->hdr.version = 0;
+	m->hdr.front_len = cpu_to_le32(front_len);
+	m->hdr.middle_len = 0;
+	m->hdr.data_len = 0;
+	m->hdr.data_off = 0;
+	m->hdr.reserved = 0;
+	m->footer.front_crc = 0;
+	m->footer.middle_crc = 0;
+	m->footer.data_crc = 0;
+	m->footer.flags = 0;
+	m->front_max = front_len;
+	m->front_is_vmalloc = false;
+	m->more_to_follow = false;
+	m->pool = NULL;
+
+	/* front */
+	if (front_len) {
+		if (front_len > PAGE_CACHE_SIZE) {
+			m->front.iov_base = __vmalloc(front_len, flags,
+						      PAGE_KERNEL);
+			m->front_is_vmalloc = true;
+		} else {
+			m->front.iov_base = kmalloc(front_len, flags);
+		}
+		if (m->front.iov_base == NULL) {
+			pr_err("msg_new can't allocate %d bytes\n",
+			     front_len);
+			goto out2;
+		}
+	} else {
+		m->front.iov_base = NULL;
+	}
+	m->front.iov_len = front_len;
+
+	/* middle */
+	m->middle = NULL;
+
+	/* data */
+	m->nr_pages = 0;
+	m->pages = NULL;
+	m->pagelist = NULL;
+	m->bio = NULL;
+	m->bio_iter = NULL;
+	m->bio_seg = 0;
+	m->trail = NULL;
+
+	dout("ceph_msg_new %p front %d\n", m, front_len);
+	return m;
+
+out2:
+	ceph_msg_put(m);
+out:
+	pr_err("msg_new can't create type %d front %d\n", type, front_len);
+	return NULL;
+}
+EXPORT_SYMBOL(ceph_msg_new);
+
+/*
+ * Allocate "middle" portion of a message, if it is needed and wasn't
+ * allocated by alloc_msg.  This allows us to read a small fixed-size
+ * per-type header in the front and then gracefully fail (i.e.,
+ * propagate the error to the caller based on info in the front) when
+ * the middle is too large.
+ */
+static int ceph_alloc_middle(struct ceph_connection *con, struct ceph_msg *msg)
+{
+	int type = le16_to_cpu(msg->hdr.type);
+	int middle_len = le32_to_cpu(msg->hdr.middle_len);
+
+	dout("alloc_middle %p type %d %s middle_len %d\n", msg, type,
+	     ceph_msg_type_name(type), middle_len);
+	BUG_ON(!middle_len);
+	BUG_ON(msg->middle);
+
+	msg->middle = ceph_buffer_new(middle_len, GFP_NOFS);
+	if (!msg->middle)
+		return -ENOMEM;
+	return 0;
+}
+
+/*
+ * Generic message allocator, for incoming messages.
+ */
+static struct ceph_msg *ceph_alloc_msg(struct ceph_connection *con,
+				struct ceph_msg_header *hdr,
+				int *skip)
+{
+	int type = le16_to_cpu(hdr->type);
+	int front_len = le32_to_cpu(hdr->front_len);
+	int middle_len = le32_to_cpu(hdr->middle_len);
+	struct ceph_msg *msg = NULL;
+	int ret;
+
+	if (con->ops->alloc_msg) {
+		mutex_unlock(&con->mutex);
+		msg = con->ops->alloc_msg(con, hdr, skip);
+		mutex_lock(&con->mutex);
+		if (!msg || *skip)
+			return NULL;
+	}
+	if (!msg) {
+		*skip = 0;
+		msg = ceph_msg_new(type, front_len, GFP_NOFS);
+		if (!msg) {
+			pr_err("unable to allocate msg type %d len %d\n",
+			       type, front_len);
+			return NULL;
+		}
+	}
+	memcpy(&msg->hdr, &con->in_hdr, sizeof(con->in_hdr));
+
+	if (middle_len && !msg->middle) {
+		ret = ceph_alloc_middle(con, msg);
+		if (ret < 0) {
+			ceph_msg_put(msg);
+			return NULL;
+		}
+	}
+
+	return msg;
+}
+
+
+/*
+ * Free a generically kmalloc'd message.
+ */
+void ceph_msg_kfree(struct ceph_msg *m)
+{
+	dout("msg_kfree %p\n", m);
+	if (m->front_is_vmalloc)
+		vfree(m->front.iov_base);
+	else
+		kfree(m->front.iov_base);
+	kfree(m);
+}
+
+/*
+ * Drop a msg ref.  Destroy as needed.
+ */
+void ceph_msg_last_put(struct kref *kref)
+{
+	struct ceph_msg *m = container_of(kref, struct ceph_msg, kref);
+
+	dout("ceph_msg_put last one on %p\n", m);
+	WARN_ON(!list_empty(&m->list_head));
+
+	/* drop middle, data, if any */
+	if (m->middle) {
+		ceph_buffer_put(m->middle);
+		m->middle = NULL;
+	}
+	m->nr_pages = 0;
+	m->pages = NULL;
+
+	if (m->pagelist) {
+		ceph_pagelist_release(m->pagelist);
+		kfree(m->pagelist);
+		m->pagelist = NULL;
+	}
+
+	m->trail = NULL;
+
+	if (m->pool)
+		ceph_msgpool_put(m->pool, m);
+	else
+		ceph_msg_kfree(m);
+}
+EXPORT_SYMBOL(ceph_msg_last_put);
+
+void ceph_msg_dump(struct ceph_msg *msg)
+{
+	pr_debug("msg_dump %p (front_max %d nr_pages %d)\n", msg,
+		 msg->front_max, msg->nr_pages);
+	print_hex_dump(KERN_DEBUG, "header: ",
+		       DUMP_PREFIX_OFFSET, 16, 1,
+		       &msg->hdr, sizeof(msg->hdr), true);
+	print_hex_dump(KERN_DEBUG, " front: ",
+		       DUMP_PREFIX_OFFSET, 16, 1,
+		       msg->front.iov_base, msg->front.iov_len, true);
+	if (msg->middle)
+		print_hex_dump(KERN_DEBUG, "middle: ",
+			       DUMP_PREFIX_OFFSET, 16, 1,
+			       msg->middle->vec.iov_base,
+			       msg->middle->vec.iov_len, true);
+	print_hex_dump(KERN_DEBUG, "footer: ",
+		       DUMP_PREFIX_OFFSET, 16, 1,
+		       &msg->footer, sizeof(msg->footer), true);
+}
+EXPORT_SYMBOL(ceph_msg_dump);
diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c
new file mode 100644
index 00000000000..8a079399174
--- /dev/null
+++ b/net/ceph/mon_client.c
@@ -0,0 +1,1027 @@
+#include <linux/ceph/ceph_debug.h>
+
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/random.h>
+#include <linux/sched.h>
+
+#include <linux/ceph/mon_client.h>
+#include <linux/ceph/libceph.h>
+#include <linux/ceph/decode.h>
+
+#include <linux/ceph/auth.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.
+ */
+
+static const 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,
+		     ceph_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_con_revoke(monc->con, monc->m_auth);
+	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 = monc->m_subscribe;
+		struct ceph_mon_subscribe_item *i;
+		void *p, *end;
+		int num;
+
+		p = msg->front.iov_base;
+		end = p + msg->front_max;
+
+		num = 1 + !!monc->want_next_osdmap + !!monc->want_mdsmap;
+		ceph_encode_32(&p, num);
+
+		if (monc->want_next_osdmap) {
+			dout("__send_subscribe to 'osdmap' %u\n",
+			     (unsigned)monc->have_osdmap);
+			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 */
+		}
+		if (monc->want_mdsmap) {
+			dout("__send_subscribe to 'mdsmap' %u+\n",
+			     (unsigned)monc->have_mdsmap);
+			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_revoke(monc->con, msg);
+		ceph_con_send(monc->con, ceph_msg_get(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,
+			ceph_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;
+}
+EXPORT_SYMBOL(ceph_monc_got_mdsmap);
+
+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;
+}
+EXPORT_SYMBOL(ceph_monc_open_session);
+
+/*
+ * 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_all(&client->auth_wq);
+}
+
+/*
+ * generic requests (e.g., statfs, poolop)
+ */
+static struct ceph_mon_generic_request *__lookup_generic_req(
+	struct ceph_mon_client *monc, u64 tid)
+{
+	struct ceph_mon_generic_request *req;
+	struct rb_node *n = monc->generic_request_tree.rb_node;
+
+	while (n) {
+		req = rb_entry(n, struct ceph_mon_generic_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_generic_request(struct ceph_mon_client *monc,
+			    struct ceph_mon_generic_request *new)
+{
+	struct rb_node **p = &monc->generic_request_tree.rb_node;
+	struct rb_node *parent = NULL;
+	struct ceph_mon_generic_request *req = NULL;
+
+	while (*p) {
+		parent = *p;
+		req = rb_entry(parent, struct ceph_mon_generic_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->generic_request_tree);
+}
+
+static void release_generic_request(struct kref *kref)
+{
+	struct ceph_mon_generic_request *req =
+		container_of(kref, struct ceph_mon_generic_request, kref);
+
+	if (req->reply)
+		ceph_msg_put(req->reply);
+	if (req->request)
+		ceph_msg_put(req->request);
+
+	kfree(req);
+}
+
+static void put_generic_request(struct ceph_mon_generic_request *req)
+{
+	kref_put(&req->kref, release_generic_request);
+}
+
+static void get_generic_request(struct ceph_mon_generic_request *req)
+{
+	kref_get(&req->kref);
+}
+
+static struct ceph_msg *get_generic_reply(struct ceph_connection *con,
+					 struct ceph_msg_header *hdr,
+					 int *skip)
+{
+	struct ceph_mon_client *monc = con->private;
+	struct ceph_mon_generic_request *req;
+	u64 tid = le64_to_cpu(hdr->tid);
+	struct ceph_msg *m;
+
+	mutex_lock(&monc->mutex);
+	req = __lookup_generic_req(monc, tid);
+	if (!req) {
+		dout("get_generic_reply %lld dne\n", tid);
+		*skip = 1;
+		m = NULL;
+	} else {
+		dout("get_generic_reply %lld got %p\n", tid, req->reply);
+		m = ceph_msg_get(req->reply);
+		/*
+		 * we don't need to track the connection reading into
+		 * this reply because we only have one open connection
+		 * at a time, ever.
+		 */
+	}
+	mutex_unlock(&monc->mutex);
+	return m;
+}
+
+static int do_generic_request(struct ceph_mon_client *monc,
+			      struct ceph_mon_generic_request *req)
+{
+	int err;
+
+	/* register request */
+	mutex_lock(&monc->mutex);
+	req->tid = ++monc->last_tid;
+	req->request->hdr.tid = cpu_to_le64(req->tid);
+	__insert_generic_request(monc, req);
+	monc->num_generic_requests++;
+	ceph_con_send(monc->con, ceph_msg_get(req->request));
+	mutex_unlock(&monc->mutex);
+
+	err = wait_for_completion_interruptible(&req->completion);
+
+	mutex_lock(&monc->mutex);
+	rb_erase(&req->node, &monc->generic_request_tree);
+	monc->num_generic_requests--;
+	mutex_unlock(&monc->mutex);
+
+	if (!err)
+		err = req->result;
+	return err;
+}
+
+/*
+ * statfs
+ */
+static void handle_statfs_reply(struct ceph_mon_client *monc,
+				struct ceph_msg *msg)
+{
+	struct ceph_mon_generic_request *req;
+	struct ceph_mon_statfs_reply *reply = msg->front.iov_base;
+	u64 tid = le64_to_cpu(msg->hdr.tid);
+
+	if (msg->front.iov_len != sizeof(*reply))
+		goto bad;
+	dout("handle_statfs_reply %p tid %llu\n", msg, tid);
+
+	mutex_lock(&monc->mutex);
+	req = __lookup_generic_req(monc, tid);
+	if (req) {
+		*(struct ceph_statfs *)req->buf = reply->st;
+		req->result = 0;
+		get_generic_request(req);
+	}
+	mutex_unlock(&monc->mutex);
+	if (req) {
+		complete_all(&req->completion);
+		put_generic_request(req);
+	}
+	return;
+
+bad:
+	pr_err("corrupt generic reply, tid %llu\n", tid);
+	ceph_msg_dump(msg);
+}
+
+/*
+ * Do a synchronous statfs().
+ */
+int ceph_monc_do_statfs(struct ceph_mon_client *monc, struct ceph_statfs *buf)
+{
+	struct ceph_mon_generic_request *req;
+	struct ceph_mon_statfs *h;
+	int err;
+
+	req = kzalloc(sizeof(*req), GFP_NOFS);
+	if (!req)
+		return -ENOMEM;
+
+	kref_init(&req->kref);
+	req->buf = buf;
+	req->buf_len = sizeof(*buf);
+	init_completion(&req->completion);
+
+	err = -ENOMEM;
+	req->request = ceph_msg_new(CEPH_MSG_STATFS, sizeof(*h), GFP_NOFS);
+	if (!req->request)
+		goto out;
+	req->reply = ceph_msg_new(CEPH_MSG_STATFS_REPLY, 1024, GFP_NOFS);
+	if (!req->reply)
+		goto out;
+
+	/* fill out request */
+	h = req->request->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;
+
+	err = do_generic_request(monc, req);
+
+out:
+	kref_put(&req->kref, release_generic_request);
+	return err;
+}
+EXPORT_SYMBOL(ceph_monc_do_statfs);
+
+/*
+ * pool ops
+ */
+static int get_poolop_reply_buf(const char *src, size_t src_len,
+				char *dst, size_t dst_len)
+{
+	u32 buf_len;
+
+	if (src_len != sizeof(u32) + dst_len)
+		return -EINVAL;
+
+	buf_len = le32_to_cpu(*(u32 *)src);
+	if (buf_len != dst_len)
+		return -EINVAL;
+
+	memcpy(dst, src + sizeof(u32), dst_len);
+	return 0;
+}
+
+static void handle_poolop_reply(struct ceph_mon_client *monc,
+				struct ceph_msg *msg)
+{
+	struct ceph_mon_generic_request *req;
+	struct ceph_mon_poolop_reply *reply = msg->front.iov_base;
+	u64 tid = le64_to_cpu(msg->hdr.tid);
+
+	if (msg->front.iov_len < sizeof(*reply))
+		goto bad;
+	dout("handle_poolop_reply %p tid %llu\n", msg, tid);
+
+	mutex_lock(&monc->mutex);
+	req = __lookup_generic_req(monc, tid);
+	if (req) {
+		if (req->buf_len &&
+		    get_poolop_reply_buf(msg->front.iov_base + sizeof(*reply),
+				     msg->front.iov_len - sizeof(*reply),
+				     req->buf, req->buf_len) < 0) {
+			mutex_unlock(&monc->mutex);
+			goto bad;
+		}
+		req->result = le32_to_cpu(reply->reply_code);
+		get_generic_request(req);
+	}
+	mutex_unlock(&monc->mutex);
+	if (req) {
+		complete(&req->completion);
+		put_generic_request(req);
+	}
+	return;
+
+bad:
+	pr_err("corrupt generic reply, tid %llu\n", tid);
+	ceph_msg_dump(msg);
+}
+
+/*
+ * Do a synchronous pool op.
+ */
+int ceph_monc_do_poolop(struct ceph_mon_client *monc, u32 op,
+			u32 pool, u64 snapid,
+			char *buf, int len)
+{
+	struct ceph_mon_generic_request *req;
+	struct ceph_mon_poolop *h;
+	int err;
+
+	req = kzalloc(sizeof(*req), GFP_NOFS);
+	if (!req)
+		return -ENOMEM;
+
+	kref_init(&req->kref);
+	req->buf = buf;
+	req->buf_len = len;
+	init_completion(&req->completion);
+
+	err = -ENOMEM;
+	req->request = ceph_msg_new(CEPH_MSG_POOLOP, sizeof(*h), GFP_NOFS);
+	if (!req->request)
+		goto out;
+	req->reply = ceph_msg_new(CEPH_MSG_POOLOP_REPLY, 1024, GFP_NOFS);
+	if (!req->reply)
+		goto out;
+
+	/* fill out request */
+	req->request->hdr.version = cpu_to_le16(2);
+	h = req->request->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;
+	h->pool = cpu_to_le32(pool);
+	h->op = cpu_to_le32(op);
+	h->auid = 0;
+	h->snapid = cpu_to_le64(snapid);
+	h->name_len = 0;
+
+	err = do_generic_request(monc, req);
+
+out:
+	kref_put(&req->kref, release_generic_request);
+	return err;
+}
+
+int ceph_monc_create_snapid(struct ceph_mon_client *monc,
+			    u32 pool, u64 *snapid)
+{
+	return ceph_monc_do_poolop(monc,  POOL_OP_CREATE_UNMANAGED_SNAP,
+				   pool, 0, (char *)snapid, sizeof(*snapid));
+
+}
+EXPORT_SYMBOL(ceph_monc_create_snapid);
+
+int ceph_monc_delete_snapid(struct ceph_mon_client *monc,
+			    u32 pool, u64 snapid)
+{
+	return ceph_monc_do_poolop(monc,  POOL_OP_CREATE_UNMANAGED_SNAP,
+				   pool, snapid, 0, 0);
+
+}
+
+/*
+ * Resend pending generic requests.
+ */
+static void __resend_generic_request(struct ceph_mon_client *monc)
+{
+	struct ceph_mon_generic_request *req;
+	struct rb_node *p;
+
+	for (p = rb_first(&monc->generic_request_tree); p; p = rb_next(p)) {
+		req = rb_entry(p, struct ceph_mon_generic_request, node);
+		ceph_con_revoke(monc->con, req->request);
+		ceph_con_send(monc->con, ceph_msg_get(req->request));
+	}
+}
+
+/*
+ * 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_options *opt = monc->client->options;
+	struct ceph_entity_addr *mon_addr = opt->mon_addr;
+	int num_mon = opt->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;
+	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->options->name,
+				    cl->options->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;
+
+	/* msgs */
+	err = -ENOMEM;
+	monc->m_subscribe_ack = ceph_msg_new(CEPH_MSG_MON_SUBSCRIBE_ACK,
+				     sizeof(struct ceph_mon_subscribe_ack),
+				     GFP_NOFS);
+	if (!monc->m_subscribe_ack)
+		goto out_monmap;
+
+	monc->m_subscribe = ceph_msg_new(CEPH_MSG_MON_SUBSCRIBE, 96, GFP_NOFS);
+	if (!monc->m_subscribe)
+		goto out_subscribe_ack;
+
+	monc->m_auth_reply = ceph_msg_new(CEPH_MSG_AUTH_REPLY, 4096, GFP_NOFS);
+	if (!monc->m_auth_reply)
+		goto out_subscribe;
+
+	monc->m_auth = ceph_msg_new(CEPH_MSG_AUTH, 4096, GFP_NOFS);
+	monc->pending_auth = 0;
+	if (!monc->m_auth)
+		goto out_auth_reply;
+
+	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->generic_request_tree = RB_ROOT;
+	monc->num_generic_requests = 0;
+	monc->last_tid = 0;
+
+	monc->have_mdsmap = 0;
+	monc->have_osdmap = 0;
+	monc->want_next_osdmap = 1;
+	return 0;
+
+out_auth_reply:
+	ceph_msg_put(monc->m_auth_reply);
+out_subscribe:
+	ceph_msg_put(monc->m_subscribe);
+out_subscribe_ack:
+	ceph_msg_put(monc->m_subscribe_ack);
+out_monmap:
+	kfree(monc->monmap);
+out:
+	return err;
+}
+EXPORT_SYMBOL(ceph_monc_init);
+
+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_msg_put(monc->m_auth_reply);
+	ceph_msg_put(monc->m_subscribe);
+	ceph_msg_put(monc->m_subscribe_ack);
+
+	kfree(monc->monmap);
+}
+EXPORT_SYMBOL(ceph_monc_stop);
+
+static void handle_auth_reply(struct ceph_mon_client *monc,
+			      struct ceph_msg *msg)
+{
+	int ret;
+	int was_auth = 0;
+
+	mutex_lock(&monc->mutex);
+	if (monc->auth->ops)
+		was_auth = monc->auth->ops->is_authenticated(monc->auth);
+	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_all(&monc->client->auth_wq);
+	} else if (ret > 0) {
+		__send_prepared_auth_request(monc, ret);
+	} else if (!was_auth && 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 =
+					cpu_to_le64(monc->auth->global_id);
+
+		__send_subscribe(monc);
+		__resend_generic_request(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;
+}
+EXPORT_SYMBOL(ceph_monc_validate_auth);
+
+/*
+ * 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_POOLOP_REPLY:
+		handle_poolop_reply(monc, msg);
+		break;
+
+	case CEPH_MSG_MON_MAP:
+		ceph_monc_handle_map(monc, msg);
+		break;
+
+	case CEPH_MSG_OSD_MAP:
+		ceph_osdc_handle_map(&monc->client->osdc, msg);
+		break;
+
+	default:
+		/* can the chained handler handle it? */
+		if (monc->client->extra_mon_dispatch &&
+		    monc->client->extra_mon_dispatch(monc->client, msg) == 0)
+			break;
+			
+		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_msg_get(monc->m_subscribe_ack);
+		break;
+	case CEPH_MSG_POOLOP_REPLY:
+	case CEPH_MSG_STATFS_REPLY:
+		return get_generic_reply(con, hdr, skip);
+	case CEPH_MSG_AUTH_REPLY:
+		m = ceph_msg_get(monc->m_auth_reply);
+		break;
+	case CEPH_MSG_MON_MAP:
+	case CEPH_MSG_MDS_MAP:
+	case CEPH_MSG_OSD_MAP:
+		m = ceph_msg_new(type, front_len, GFP_NOFS);
+		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,
+			ceph_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);
+}
+
+static const 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,
+};
diff --git a/net/ceph/msgpool.c b/net/ceph/msgpool.c
new file mode 100644
index 00000000000..d5f2d97ac05
--- /dev/null
+++ b/net/ceph/msgpool.c
@@ -0,0 +1,64 @@
+#include <linux/ceph/ceph_debug.h>
+
+#include <linux/err.h>
+#include <linux/sched.h>
+#include <linux/types.h>
+#include <linux/vmalloc.h>
+
+#include <linux/ceph/msgpool.h>
+
+static void *alloc_fn(gfp_t gfp_mask, void *arg)
+{
+	struct ceph_msgpool *pool = arg;
+	void *p;
+
+	p = ceph_msg_new(0, pool->front_len, gfp_mask);
+	if (!p)
+		pr_err("msgpool %s alloc failed\n", pool->name);
+	return p;
+}
+
+static void free_fn(void *element, void *arg)
+{
+	ceph_msg_put(element);
+}
+
+int ceph_msgpool_init(struct ceph_msgpool *pool,
+		      int front_len, int size, bool blocking, const char *name)
+{
+	pool->front_len = front_len;
+	pool->pool = mempool_create(size, alloc_fn, free_fn, pool);
+	if (!pool->pool)
+		return -ENOMEM;
+	pool->name = name;
+	return 0;
+}
+
+void ceph_msgpool_destroy(struct ceph_msgpool *pool)
+{
+	mempool_destroy(pool->pool);
+}
+
+struct ceph_msg *ceph_msgpool_get(struct ceph_msgpool *pool,
+				  int front_len)
+{
+	if (front_len > pool->front_len) {
+		pr_err("msgpool_get pool %s need front %d, pool size is %d\n",
+		       pool->name, front_len, pool->front_len);
+		WARN_ON(1);
+
+		/* try to alloc a fresh message */
+		return ceph_msg_new(0, front_len, GFP_NOFS);
+	}
+
+	return mempool_alloc(pool->pool, GFP_NOFS);
+}
+
+void ceph_msgpool_put(struct ceph_msgpool *pool, struct ceph_msg *msg)
+{
+	/* 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_init(&msg->kref);  /* retake single ref */
+}
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
new file mode 100644
index 00000000000..79391994b3e
--- /dev/null
+++ b/net/ceph/osd_client.c
@@ -0,0 +1,1773 @@
+#include <linux/ceph/ceph_debug.h>
+
+#include <linux/module.h>
+#include <linux/err.h>
+#include <linux/highmem.h>
+#include <linux/mm.h>
+#include <linux/pagemap.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+#ifdef CONFIG_BLOCK
+#include <linux/bio.h>
+#endif
+
+#include <linux/ceph/libceph.h>
+#include <linux/ceph/osd_client.h>
+#include <linux/ceph/messenger.h>
+#include <linux/ceph/decode.h>
+#include <linux/ceph/auth.h>
+#include <linux/ceph/pagelist.h>
+
+#define OSD_OP_FRONT_LEN	4096
+#define OSD_OPREPLY_FRONT_LEN	512
+
+static const struct ceph_connection_operations osd_con_ops;
+static int __kick_requests(struct ceph_osd_client *osdc,
+			  struct ceph_osd *kickosd);
+
+static void kick_requests(struct ceph_osd_client *osdc, struct ceph_osd *osd);
+
+static int op_needs_trail(int op)
+{
+	switch (op) {
+	case CEPH_OSD_OP_GETXATTR:
+	case CEPH_OSD_OP_SETXATTR:
+	case CEPH_OSD_OP_CMPXATTR:
+	case CEPH_OSD_OP_CALL:
+		return 1;
+	default:
+		return 0;
+	}
+}
+
+static int op_has_extent(int op)
+{
+	return (op == CEPH_OSD_OP_READ ||
+		op == CEPH_OSD_OP_WRITE);
+}
+
+void ceph_calc_raw_layout(struct ceph_osd_client *osdc,
+			struct ceph_file_layout *layout,
+			u64 snapid,
+			u64 off, u64 *plen, u64 *bno,
+			struct ceph_osd_request *req,
+			struct ceph_osd_req_op *op)
+{
+	struct ceph_osd_request_head *reqhead = req->r_request->front.iov_base;
+	u64 orig_len = *plen;
+	u64 objoff, objlen;    /* extent in object */
+
+	reqhead->snapid = cpu_to_le64(snapid);
+
+	/* object extent? */
+	ceph_calc_file_object_mapping(layout, off, plen, bno,
+				      &objoff, &objlen);
+	if (*plen < orig_len)
+		dout(" skipping last %llu, final file extent %llu~%llu\n",
+		     orig_len - *plen, off, *plen);
+
+	if (op_has_extent(op->op)) {
+		op->extent.offset = objoff;
+		op->extent.length = objlen;
+	}
+	req->r_num_pages = calc_pages_for(off, *plen);
+	if (op->op == CEPH_OSD_OP_WRITE)
+		op->payload_len = *plen;
+
+	dout("calc_layout bno=%llx %llu~%llu (%d pages)\n",
+	     *bno, objoff, objlen, req->r_num_pages);
+
+}
+EXPORT_SYMBOL(ceph_calc_raw_layout);
+
+/*
+ * Implement client access to distributed object storage cluster.
+ *
+ * All data objects are stored within a cluster/cloud of OSDs, or
+ * "object storage devices."  (Note that Ceph OSDs have _nothing_ to
+ * do with the T10 OSD extensions to SCSI.)  Ceph OSDs are simply
+ * remote daemons serving up and coordinating consistent and safe
+ * access to storage.
+ *
+ * Cluster membership and the mapping of data objects onto storage devices
+ * are described by the osd map.
+ *
+ * We keep track of pending OSD requests (read, write), resubmit
+ * requests to different OSDs when the cluster topology/data layout
+ * change, or retry the affected requests when the communications
+ * channel with an OSD is reset.
+ */
+
+/*
+ * calculate the mapping of a file extent onto an object, and fill out the
+ * request accordingly.  shorten extent as necessary if it crosses an
+ * object boundary.
+ *
+ * fill osd op in request message.
+ */
+static void calc_layout(struct ceph_osd_client *osdc,
+			struct ceph_vino vino,
+			struct ceph_file_layout *layout,
+			u64 off, u64 *plen,
+			struct ceph_osd_request *req,
+			struct ceph_osd_req_op *op)
+{
+	u64 bno;
+
+	ceph_calc_raw_layout(osdc, layout, vino.snap, off,
+			     plen, &bno, req, op);
+
+	sprintf(req->r_oid, "%llx.%08llx", vino.ino, bno);
+	req->r_oid_len = strlen(req->r_oid);
+}
+
+/*
+ * requests
+ */
+void ceph_osdc_release_request(struct kref *kref)
+{
+	struct ceph_osd_request *req = container_of(kref,
+						    struct ceph_osd_request,
+						    r_kref);
+
+	if (req->r_request)
+		ceph_msg_put(req->r_request);
+	if (req->r_reply)
+		ceph_msg_put(req->r_reply);
+	if (req->r_con_filling_msg) {
+		dout("release_request revoking pages %p from con %p\n",
+		     req->r_pages, req->r_con_filling_msg);
+		ceph_con_revoke_message(req->r_con_filling_msg,
+				      req->r_reply);
+		ceph_con_put(req->r_con_filling_msg);
+	}
+	if (req->r_own_pages)
+		ceph_release_page_vector(req->r_pages,
+					 req->r_num_pages);
+#ifdef CONFIG_BLOCK
+	if (req->r_bio)
+		bio_put(req->r_bio);
+#endif
+	ceph_put_snap_context(req->r_snapc);
+	if (req->r_trail) {
+		ceph_pagelist_release(req->r_trail);
+		kfree(req->r_trail);
+	}
+	if (req->r_mempool)
+		mempool_free(req, req->r_osdc->req_mempool);
+	else
+		kfree(req);
+}
+EXPORT_SYMBOL(ceph_osdc_release_request);
+
+static int get_num_ops(struct ceph_osd_req_op *ops, int *needs_trail)
+{
+	int i = 0;
+
+	if (needs_trail)
+		*needs_trail = 0;
+	while (ops[i].op) {
+		if (needs_trail && op_needs_trail(ops[i].op))
+			*needs_trail = 1;
+		i++;
+	}
+
+	return i;
+}
+
+struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc,
+					       int flags,
+					       struct ceph_snap_context *snapc,
+					       struct ceph_osd_req_op *ops,
+					       bool use_mempool,
+					       gfp_t gfp_flags,
+					       struct page **pages,
+					       struct bio *bio)
+{
+	struct ceph_osd_request *req;
+	struct ceph_msg *msg;
+	int needs_trail;
+	int num_op = get_num_ops(ops, &needs_trail);
+	size_t msg_size = sizeof(struct ceph_osd_request_head);
+
+	msg_size += num_op*sizeof(struct ceph_osd_op);
+
+	if (use_mempool) {
+		req = mempool_alloc(osdc->req_mempool, gfp_flags);
+		memset(req, 0, sizeof(*req));
+	} else {
+		req = kzalloc(sizeof(*req), gfp_flags);
+	}
+	if (req == NULL)
+		return NULL;
+
+	req->r_osdc = osdc;
+	req->r_mempool = use_mempool;
+
+	kref_init(&req->r_kref);
+	init_completion(&req->r_completion);
+	init_completion(&req->r_safe_completion);
+	INIT_LIST_HEAD(&req->r_unsafe_item);
+	req->r_flags = flags;
+
+	WARN_ON((flags & (CEPH_OSD_FLAG_READ|CEPH_OSD_FLAG_WRITE)) == 0);
+
+	/* create reply message */
+	if (use_mempool)
+		msg = ceph_msgpool_get(&osdc->msgpool_op_reply, 0);
+	else
+		msg = ceph_msg_new(CEPH_MSG_OSD_OPREPLY,
+				   OSD_OPREPLY_FRONT_LEN, gfp_flags);
+	if (!msg) {
+		ceph_osdc_put_request(req);
+		return NULL;
+	}
+	req->r_reply = msg;
+
+	/* allocate space for the trailing data */
+	if (needs_trail) {
+		req->r_trail = kmalloc(sizeof(struct ceph_pagelist), gfp_flags);
+		if (!req->r_trail) {
+			ceph_osdc_put_request(req);
+			return NULL;
+		}
+		ceph_pagelist_init(req->r_trail);
+	}
+	/* create request message; allow space for oid */
+	msg_size += 40;
+	if (snapc)
+		msg_size += sizeof(u64) * snapc->num_snaps;
+	if (use_mempool)
+		msg = ceph_msgpool_get(&osdc->msgpool_op, 0);
+	else
+		msg = ceph_msg_new(CEPH_MSG_OSD_OP, msg_size, gfp_flags);
+	if (!msg) {
+		ceph_osdc_put_request(req);
+		return NULL;
+	}
+
+	msg->hdr.type = cpu_to_le16(CEPH_MSG_OSD_OP);
+	memset(msg->front.iov_base, 0, msg->front.iov_len);
+
+	req->r_request = msg;
+	req->r_pages = pages;
+#ifdef CONFIG_BLOCK
+	if (bio) {
+		req->r_bio = bio;
+		bio_get(req->r_bio);
+	}
+#endif
+
+	return req;
+}
+EXPORT_SYMBOL(ceph_osdc_alloc_request);
+
+static void osd_req_encode_op(struct ceph_osd_request *req,
+			      struct ceph_osd_op *dst,
+			      struct ceph_osd_req_op *src)
+{
+	dst->op = cpu_to_le16(src->op);
+
+	switch (dst->op) {
+	case CEPH_OSD_OP_READ:
+	case CEPH_OSD_OP_WRITE:
+		dst->extent.offset =
+			cpu_to_le64(src->extent.offset);
+		dst->extent.length =
+			cpu_to_le64(src->extent.length);
+		dst->extent.truncate_size =
+			cpu_to_le64(src->extent.truncate_size);
+		dst->extent.truncate_seq =
+			cpu_to_le32(src->extent.truncate_seq);
+		break;
+
+	case CEPH_OSD_OP_GETXATTR:
+	case CEPH_OSD_OP_SETXATTR:
+	case CEPH_OSD_OP_CMPXATTR:
+		BUG_ON(!req->r_trail);
+
+		dst->xattr.name_len = cpu_to_le32(src->xattr.name_len);
+		dst->xattr.value_len = cpu_to_le32(src->xattr.value_len);
+		dst->xattr.cmp_op = src->xattr.cmp_op;
+		dst->xattr.cmp_mode = src->xattr.cmp_mode;
+		ceph_pagelist_append(req->r_trail, src->xattr.name,
+				     src->xattr.name_len);
+		ceph_pagelist_append(req->r_trail, src->xattr.val,
+				     src->xattr.value_len);
+		break;
+	case CEPH_OSD_OP_CALL:
+		BUG_ON(!req->r_trail);
+
+		dst->cls.class_len = src->cls.class_len;
+		dst->cls.method_len = src->cls.method_len;
+		dst->cls.indata_len = cpu_to_le32(src->cls.indata_len);
+
+		ceph_pagelist_append(req->r_trail, src->cls.class_name,
+				     src->cls.class_len);
+		ceph_pagelist_append(req->r_trail, src->cls.method_name,
+				     src->cls.method_len);
+		ceph_pagelist_append(req->r_trail, src->cls.indata,
+				     src->cls.indata_len);
+		break;
+	case CEPH_OSD_OP_ROLLBACK:
+		dst->snap.snapid = cpu_to_le64(src->snap.snapid);
+		break;
+	case CEPH_OSD_OP_STARTSYNC:
+		break;
+	default:
+		pr_err("unrecognized osd opcode %d\n", dst->op);
+		WARN_ON(1);
+		break;
+	}
+	dst->payload_len = cpu_to_le32(src->payload_len);
+}
+
+/*
+ * build new request AND message
+ *
+ */
+void ceph_osdc_build_request(struct ceph_osd_request *req,
+			     u64 off, u64 *plen,
+			     struct ceph_osd_req_op *src_ops,
+			     struct ceph_snap_context *snapc,
+			     struct timespec *mtime,
+			     const char *oid,
+			     int oid_len)
+{
+	struct ceph_msg *msg = req->r_request;
+	struct ceph_osd_request_head *head;
+	struct ceph_osd_req_op *src_op;
+	struct ceph_osd_op *op;
+	void *p;
+	int num_op = get_num_ops(src_ops, NULL);
+	size_t msg_size = sizeof(*head) + num_op*sizeof(*op);
+	int flags = req->r_flags;
+	u64 data_len = 0;
+	int i;
+
+	head = msg->front.iov_base;
+	op = (void *)(head + 1);
+	p = (void *)(op + num_op);
+
+	req->r_snapc = ceph_get_snap_context(snapc);
+
+	head->client_inc = cpu_to_le32(1); /* always, for now. */
+	head->flags = cpu_to_le32(flags);
+	if (flags & CEPH_OSD_FLAG_WRITE)
+		ceph_encode_timespec(&head->mtime, mtime);
+	head->num_ops = cpu_to_le16(num_op);
+
+
+	/* fill in oid */
+	head->object_len = cpu_to_le32(oid_len);
+	memcpy(p, oid, oid_len);
+	p += oid_len;
+
+	src_op = src_ops;
+	while (src_op->op) {
+		osd_req_encode_op(req, op, src_op);
+		src_op++;
+		op++;
+	}
+
+	if (req->r_trail)
+		data_len += req->r_trail->length;
+
+	if (snapc) {
+		head->snap_seq = cpu_to_le64(snapc->seq);
+		head->num_snaps = cpu_to_le32(snapc->num_snaps);
+		for (i = 0; i < snapc->num_snaps; i++) {
+			put_unaligned_le64(snapc->snaps[i], p);
+			p += sizeof(u64);
+		}
+	}
+
+	if (flags & CEPH_OSD_FLAG_WRITE) {
+		req->r_request->hdr.data_off = cpu_to_le16(off);
+		req->r_request->hdr.data_len = cpu_to_le32(*plen + data_len);
+	} else if (data_len) {
+		req->r_request->hdr.data_off = 0;
+		req->r_request->hdr.data_len = cpu_to_le32(data_len);
+	}
+
+	BUG_ON(p > msg->front.iov_base + msg->front.iov_len);
+	msg_size = p - msg->front.iov_base;
+	msg->front.iov_len = msg_size;
+	msg->hdr.front_len = cpu_to_le32(msg_size);
+	return;
+}
+EXPORT_SYMBOL(ceph_osdc_build_request);
+
+/*
+ * build new request AND message, calculate layout, and adjust file
+ * extent as needed.
+ *
+ * if the file was recently truncated, we include information about its
+ * old and new size so that the object can be updated appropriately.  (we
+ * avoid synchronously deleting truncated objects because it's slow.)
+ *
+ * if @do_sync, include a 'startsync' command so that the osd will flush
+ * data quickly.
+ */
+struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc,
+					       struct ceph_file_layout *layout,
+					       struct ceph_vino vino,
+					       u64 off, u64 *plen,
+					       int opcode, 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)
+{
+	struct ceph_osd_req_op ops[3];
+	struct ceph_osd_request *req;
+
+	ops[0].op = opcode;
+	ops[0].extent.truncate_seq = truncate_seq;
+	ops[0].extent.truncate_size = truncate_size;
+	ops[0].payload_len = 0;
+
+	if (do_sync) {
+		ops[1].op = CEPH_OSD_OP_STARTSYNC;
+		ops[1].payload_len = 0;
+		ops[2].op = 0;
+	} else
+		ops[1].op = 0;
+
+	req = ceph_osdc_alloc_request(osdc, flags,
+					 snapc, ops,
+					 use_mempool,
+					 GFP_NOFS, NULL, NULL);
+	if (IS_ERR(req))
+		return req;
+
+	/* calculate max write size */
+	calc_layout(osdc, vino, layout, off, plen, req, ops);
+	req->r_file_layout = *layout;  /* keep a copy */
+
+	ceph_osdc_build_request(req, off, plen, ops,
+				snapc,
+				mtime,
+				req->r_oid, req->r_oid_len);
+
+	return req;
+}
+EXPORT_SYMBOL(ceph_osdc_new_request);
+
+/*
+ * We keep osd requests in an rbtree, sorted by ->r_tid.
+ */
+static void __insert_request(struct ceph_osd_client *osdc,
+			     struct ceph_osd_request *new)
+{
+	struct rb_node **p = &osdc->requests.rb_node;
+	struct rb_node *parent = NULL;
+	struct ceph_osd_request *req = NULL;
+
+	while (*p) {
+		parent = *p;
+		req = rb_entry(parent, struct ceph_osd_request, r_node);
+		if (new->r_tid < req->r_tid)
+			p = &(*p)->rb_left;
+		else if (new->r_tid > req->r_tid)
+			p = &(*p)->rb_right;
+		else
+			BUG();
+	}
+
+	rb_link_node(&new->r_node, parent, p);
+	rb_insert_color(&new->r_node, &osdc->requests);
+}
+
+static struct ceph_osd_request *__lookup_request(struct ceph_osd_client *osdc,
+						 u64 tid)
+{
+	struct ceph_osd_request *req;
+	struct rb_node *n = osdc->requests.rb_node;
+
+	while (n) {
+		req = rb_entry(n, struct ceph_osd_request, r_node);
+		if (tid < req->r_tid)
+			n = n->rb_left;
+		else if (tid > req->r_tid)
+			n = n->rb_right;
+		else
+			return req;
+	}
+	return NULL;
+}
+
+static struct ceph_osd_request *
+__lookup_request_ge(struct ceph_osd_client *osdc,
+		    u64 tid)
+{
+	struct ceph_osd_request *req;
+	struct rb_node *n = osdc->requests.rb_node;
+
+	while (n) {
+		req = rb_entry(n, struct ceph_osd_request, r_node);
+		if (tid < req->r_tid) {
+			if (!n->rb_left)
+				return req;
+			n = n->rb_left;
+		} else if (tid > req->r_tid) {
+			n = n->rb_right;
+		} else {
+			return req;
+		}
+	}
+	return NULL;
+}
+
+
+/*
+ * If the osd connection drops, we need to resubmit all requests.
+ */
+static void osd_reset(struct ceph_connection *con)
+{
+	struct ceph_osd *osd = con->private;
+	struct ceph_osd_client *osdc;
+
+	if (!osd)
+		return;
+	dout("osd_reset osd%d\n", osd->o_osd);
+	osdc = osd->o_osdc;
+	down_read(&osdc->map_sem);
+	kick_requests(osdc, osd);
+	up_read(&osdc->map_sem);
+}
+
+/*
+ * Track open sessions with osds.
+ */
+static struct ceph_osd *create_osd(struct ceph_osd_client *osdc)
+{
+	struct ceph_osd *osd;
+
+	osd = kzalloc(sizeof(*osd), GFP_NOFS);
+	if (!osd)
+		return NULL;
+
+	atomic_set(&osd->o_ref, 1);
+	osd->o_osdc = osdc;
+	INIT_LIST_HEAD(&osd->o_requests);
+	INIT_LIST_HEAD(&osd->o_osd_lru);
+	osd->o_incarnation = 1;
+
+	ceph_con_init(osdc->client->msgr, &osd->o_con);
+	osd->o_con.private = osd;
+	osd->o_con.ops = &osd_con_ops;
+	osd->o_con.peer_name.type = CEPH_ENTITY_TYPE_OSD;
+
+	INIT_LIST_HEAD(&osd->o_keepalive_item);
+	return osd;
+}
+
+static struct ceph_osd *get_osd(struct ceph_osd *osd)
+{
+	if (atomic_inc_not_zero(&osd->o_ref)) {
+		dout("get_osd %p %d -> %d\n", osd, atomic_read(&osd->o_ref)-1,
+		     atomic_read(&osd->o_ref));
+		return osd;
+	} else {
+		dout("get_osd %p FAIL\n", osd);
+		return NULL;
+	}
+}
+
+static void put_osd(struct ceph_osd *osd)
+{
+	dout("put_osd %p %d -> %d\n", osd, atomic_read(&osd->o_ref),
+	     atomic_read(&osd->o_ref) - 1);
+	if (atomic_dec_and_test(&osd->o_ref)) {
+		struct ceph_auth_client *ac = osd->o_osdc->client->monc.auth;
+
+		if (osd->o_authorizer)
+			ac->ops->destroy_authorizer(ac, osd->o_authorizer);
+		kfree(osd);
+	}
+}
+
+/*
+ * remove an osd from our map
+ */
+static void __remove_osd(struct ceph_osd_client *osdc, struct ceph_osd *osd)
+{
+	dout("__remove_osd %p\n", osd);
+	BUG_ON(!list_empty(&osd->o_requests));
+	rb_erase(&osd->o_node, &osdc->osds);
+	list_del_init(&osd->o_osd_lru);
+	ceph_con_close(&osd->o_con);
+	put_osd(osd);
+}
+
+static void __move_osd_to_lru(struct ceph_osd_client *osdc,
+			      struct ceph_osd *osd)
+{
+	dout("__move_osd_to_lru %p\n", osd);
+	BUG_ON(!list_empty(&osd->o_osd_lru));
+	list_add_tail(&osd->o_osd_lru, &osdc->osd_lru);
+	osd->lru_ttl = jiffies + osdc->client->options->osd_idle_ttl * HZ;
+}
+
+static void __remove_osd_from_lru(struct ceph_osd *osd)
+{
+	dout("__remove_osd_from_lru %p\n", osd);
+	if (!list_empty(&osd->o_osd_lru))
+		list_del_init(&osd->o_osd_lru);
+}
+
+static void remove_old_osds(struct ceph_osd_client *osdc, int remove_all)
+{
+	struct ceph_osd *osd, *nosd;
+
+	dout("__remove_old_osds %p\n", osdc);
+	mutex_lock(&osdc->request_mutex);
+	list_for_each_entry_safe(osd, nosd, &osdc->osd_lru, o_osd_lru) {
+		if (!remove_all && time_before(jiffies, osd->lru_ttl))
+			break;
+		__remove_osd(osdc, osd);
+	}
+	mutex_unlock(&osdc->request_mutex);
+}
+
+/*
+ * reset osd connect
+ */
+static int __reset_osd(struct ceph_osd_client *osdc, struct ceph_osd *osd)
+{
+	struct ceph_osd_request *req;
+	int ret = 0;
+
+	dout("__reset_osd %p osd%d\n", osd, osd->o_osd);
+	if (list_empty(&osd->o_requests)) {
+		__remove_osd(osdc, osd);
+	} else if (memcmp(&osdc->osdmap->osd_addr[osd->o_osd],
+			  &osd->o_con.peer_addr,
+			  sizeof(osd->o_con.peer_addr)) == 0 &&
+		   !ceph_con_opened(&osd->o_con)) {
+		dout(" osd addr hasn't changed and connection never opened,"
+		     " letting msgr retry");
+		/* touch each r_stamp for handle_timeout()'s benfit */
+		list_for_each_entry(req, &osd->o_requests, r_osd_item)
+			req->r_stamp = jiffies;
+		ret = -EAGAIN;
+	} else {
+		ceph_con_close(&osd->o_con);
+		ceph_con_open(&osd->o_con, &osdc->osdmap->osd_addr[osd->o_osd]);
+		osd->o_incarnation++;
+	}
+	return ret;
+}
+
+static void __insert_osd(struct ceph_osd_client *osdc, struct ceph_osd *new)
+{
+	struct rb_node **p = &osdc->osds.rb_node;
+	struct rb_node *parent = NULL;
+	struct ceph_osd *osd = NULL;
+
+	while (*p) {
+		parent = *p;
+		osd = rb_entry(parent, struct ceph_osd, o_node);
+		if (new->o_osd < osd->o_osd)
+			p = &(*p)->rb_left;
+		else if (new->o_osd > osd->o_osd)
+			p = &(*p)->rb_right;
+		else
+			BUG();
+	}
+
+	rb_link_node(&new->o_node, parent, p);
+	rb_insert_color(&new->o_node, &osdc->osds);
+}
+
+static struct ceph_osd *__lookup_osd(struct ceph_osd_client *osdc, int o)
+{
+	struct ceph_osd *osd;
+	struct rb_node *n = osdc->osds.rb_node;
+
+	while (n) {
+		osd = rb_entry(n, struct ceph_osd, o_node);
+		if (o < osd->o_osd)
+			n = n->rb_left;
+		else if (o > osd->o_osd)
+			n = n->rb_right;
+		else
+			return osd;
+	}
+	return NULL;
+}
+
+static void __schedule_osd_timeout(struct ceph_osd_client *osdc)
+{
+	schedule_delayed_work(&osdc->timeout_work,
+			osdc->client->options->osd_keepalive_timeout * HZ);
+}
+
+static void __cancel_osd_timeout(struct ceph_osd_client *osdc)
+{
+	cancel_delayed_work(&osdc->timeout_work);
+}
+
+/*
+ * Register request, assign tid.  If this is the first request, set up
+ * the timeout event.
+ */
+static void register_request(struct ceph_osd_client *osdc,
+			     struct ceph_osd_request *req)
+{
+	mutex_lock(&osdc->request_mutex);
+	req->r_tid = ++osdc->last_tid;
+	req->r_request->hdr.tid = cpu_to_le64(req->r_tid);
+	INIT_LIST_HEAD(&req->r_req_lru_item);
+
+	dout("register_request %p tid %lld\n", req, req->r_tid);
+	__insert_request(osdc, req);
+	ceph_osdc_get_request(req);
+	osdc->num_requests++;
+
+	if (osdc->num_requests == 1) {
+		dout(" first request, scheduling timeout\n");
+		__schedule_osd_timeout(osdc);
+	}
+	mutex_unlock(&osdc->request_mutex);
+}
+
+/*
+ * called under osdc->request_mutex
+ */
+static void __unregister_request(struct ceph_osd_client *osdc,
+				 struct ceph_osd_request *req)
+{
+	dout("__unregister_request %p tid %lld\n", req, req->r_tid);
+	rb_erase(&req->r_node, &osdc->requests);
+	osdc->num_requests--;
+
+	if (req->r_osd) {
+		/* make sure the original request isn't in flight. */
+		ceph_con_revoke(&req->r_osd->o_con, req->r_request);
+
+		list_del_init(&req->r_osd_item);
+		if (list_empty(&req->r_osd->o_requests))
+			__move_osd_to_lru(osdc, req->r_osd);
+		req->r_osd = NULL;
+	}
+
+	ceph_osdc_put_request(req);
+
+	list_del_init(&req->r_req_lru_item);
+	if (osdc->num_requests == 0) {
+		dout(" no requests, canceling timeout\n");
+		__cancel_osd_timeout(osdc);
+	}
+}
+
+/*
+ * Cancel a previously queued request message
+ */
+static void __cancel_request(struct ceph_osd_request *req)
+{
+	if (req->r_sent && req->r_osd) {
+		ceph_con_revoke(&req->r_osd->o_con, req->r_request);
+		req->r_sent = 0;
+	}
+	list_del_init(&req->r_req_lru_item);
+}
+
+/*
+ * Pick an osd (the first 'up' osd in the pg), allocate the osd struct
+ * (as needed), and set the request r_osd appropriately.  If there is
+ * no up osd, set r_osd to NULL.
+ *
+ * Return 0 if unchanged, 1 if changed, or negative on error.
+ *
+ * Caller should hold map_sem for read and request_mutex.
+ */
+static int __map_osds(struct ceph_osd_client *osdc,
+		      struct ceph_osd_request *req)
+{
+	struct ceph_osd_request_head *reqhead = req->r_request->front.iov_base;
+	struct ceph_pg pgid;
+	int acting[CEPH_PG_MAX_SIZE];
+	int o = -1, num = 0;
+	int err;
+
+	dout("map_osds %p tid %lld\n", req, req->r_tid);
+	err = ceph_calc_object_layout(&reqhead->layout, req->r_oid,
+				      &req->r_file_layout, osdc->osdmap);
+	if (err)
+		return err;
+	pgid = reqhead->layout.ol_pgid;
+	req->r_pgid = pgid;
+
+	err = ceph_calc_pg_acting(osdc->osdmap, pgid, acting);
+	if (err > 0) {
+		o = acting[0];
+		num = err;
+	}
+
+	if ((req->r_osd && req->r_osd->o_osd == o &&
+	     req->r_sent >= req->r_osd->o_incarnation &&
+	     req->r_num_pg_osds == num &&
+	     memcmp(req->r_pg_osds, acting, sizeof(acting[0])*num) == 0) ||
+	    (req->r_osd == NULL && o == -1))
+		return 0;  /* no change */
+
+	dout("map_osds tid %llu pgid %d.%x osd%d (was osd%d)\n",
+	     req->r_tid, le32_to_cpu(pgid.pool), le16_to_cpu(pgid.ps), o,
+	     req->r_osd ? req->r_osd->o_osd : -1);
+
+	/* record full pg acting set */
+	memcpy(req->r_pg_osds, acting, sizeof(acting[0]) * num);
+	req->r_num_pg_osds = num;
+
+	if (req->r_osd) {
+		__cancel_request(req);
+		list_del_init(&req->r_osd_item);
+		req->r_osd = NULL;
+	}
+
+	req->r_osd = __lookup_osd(osdc, o);
+	if (!req->r_osd && o >= 0) {
+		err = -ENOMEM;
+		req->r_osd = create_osd(osdc);
+		if (!req->r_osd)
+			goto out;
+
+		dout("map_osds osd %p is osd%d\n", req->r_osd, o);
+		req->r_osd->o_osd = o;
+		req->r_osd->o_con.peer_name.num = cpu_to_le64(o);
+		__insert_osd(osdc, req->r_osd);
+
+		ceph_con_open(&req->r_osd->o_con, &osdc->osdmap->osd_addr[o]);
+	}
+
+	if (req->r_osd) {
+		__remove_osd_from_lru(req->r_osd);
+		list_add(&req->r_osd_item, &req->r_osd->o_requests);
+	}
+	err = 1;   /* osd or pg changed */
+
+out:
+	return err;
+}
+
+/*
+ * caller should hold map_sem (for read) and request_mutex
+ */
+static int __send_request(struct ceph_osd_client *osdc,
+			  struct ceph_osd_request *req)
+{
+	struct ceph_osd_request_head *reqhead;
+	int err;
+
+	err = __map_osds(osdc, req);
+	if (err < 0)
+		return err;
+	if (req->r_osd == NULL) {
+		dout("send_request %p no up osds in pg\n", req);
+		ceph_monc_request_next_osdmap(&osdc->client->monc);
+		return 0;
+	}
+
+	dout("send_request %p tid %llu to osd%d flags %d\n",
+	     req, req->r_tid, req->r_osd->o_osd, req->r_flags);
+
+	reqhead = req->r_request->front.iov_base;
+	reqhead->osdmap_epoch = cpu_to_le32(osdc->osdmap->epoch);
+	reqhead->flags |= cpu_to_le32(req->r_flags);  /* e.g., RETRY */
+	reqhead->reassert_version = req->r_reassert_version;
+
+	req->r_stamp = jiffies;
+	list_move_tail(&req->r_req_lru_item, &osdc->req_lru);
+
+	ceph_msg_get(req->r_request); /* send consumes a ref */
+	ceph_con_send(&req->r_osd->o_con, req->r_request);
+	req->r_sent = req->r_osd->o_incarnation;
+	return 0;
+}
+
+/*
+ * Timeout callback, called every N seconds when 1 or more osd
+ * requests has been active for more than N seconds.  When this
+ * happens, we ping all OSDs with requests who have timed out to
+ * ensure any communications channel reset is detected.  Reset the
+ * request timeouts another N seconds in the future as we go.
+ * Reschedule the timeout event another N seconds in future (unless
+ * there are no open requests).
+ */
+static void handle_timeout(struct work_struct *work)
+{
+	struct ceph_osd_client *osdc =
+		container_of(work, struct ceph_osd_client, timeout_work.work);
+	struct ceph_osd_request *req, *last_req = NULL;
+	struct ceph_osd *osd;
+	unsigned long timeout = osdc->client->options->osd_timeout * HZ;
+	unsigned long keepalive =
+		osdc->client->options->osd_keepalive_timeout * HZ;
+	unsigned long last_stamp = 0;
+	struct rb_node *p;
+	struct list_head slow_osds;
+
+	dout("timeout\n");
+	down_read(&osdc->map_sem);
+
+	ceph_monc_request_next_osdmap(&osdc->client->monc);
+
+	mutex_lock(&osdc->request_mutex);
+	for (p = rb_first(&osdc->requests); p; p = rb_next(p)) {
+		req = rb_entry(p, struct ceph_osd_request, r_node);
+
+		if (req->r_resend) {
+			int err;
+
+			dout("osdc resending prev failed %lld\n", req->r_tid);
+			err = __send_request(osdc, req);
+			if (err)
+				dout("osdc failed again on %lld\n", req->r_tid);
+			else
+				req->r_resend = false;
+			continue;
+		}
+	}
+
+	/*
+	 * reset osds that appear to be _really_ unresponsive.  this
+	 * is a failsafe measure.. we really shouldn't be getting to
+	 * this point if the system is working properly.  the monitors
+	 * should mark the osd as failed and we should find out about
+	 * it from an updated osd map.
+	 */
+	while (timeout && !list_empty(&osdc->req_lru)) {
+		req = list_entry(osdc->req_lru.next, struct ceph_osd_request,
+				 r_req_lru_item);
+
+		if (time_before(jiffies, req->r_stamp + timeout))
+			break;
+
+		BUG_ON(req == last_req && req->r_stamp == last_stamp);
+		last_req = req;
+		last_stamp = req->r_stamp;
+
+		osd = req->r_osd;
+		BUG_ON(!osd);
+		pr_warning(" tid %llu timed out on osd%d, will reset osd\n",
+			   req->r_tid, osd->o_osd);
+		__kick_requests(osdc, osd);
+	}
+
+	/*
+	 * ping osds that are a bit slow.  this ensures that if there
+	 * is a break in the TCP connection we will notice, and reopen
+	 * a connection with that osd (from the fault callback).
+	 */
+	INIT_LIST_HEAD(&slow_osds);
+	list_for_each_entry(req, &osdc->req_lru, r_req_lru_item) {
+		if (time_before(jiffies, req->r_stamp + keepalive))
+			break;
+
+		osd = req->r_osd;
+		BUG_ON(!osd);
+		dout(" tid %llu is slow, will send keepalive on osd%d\n",
+		     req->r_tid, osd->o_osd);
+		list_move_tail(&osd->o_keepalive_item, &slow_osds);
+	}
+	while (!list_empty(&slow_osds)) {
+		osd = list_entry(slow_osds.next, struct ceph_osd,
+				 o_keepalive_item);
+		list_del_init(&osd->o_keepalive_item);
+		ceph_con_keepalive(&osd->o_con);
+	}
+
+	__schedule_osd_timeout(osdc);
+	mutex_unlock(&osdc->request_mutex);
+
+	up_read(&osdc->map_sem);
+}
+
+static void handle_osds_timeout(struct work_struct *work)
+{
+	struct ceph_osd_client *osdc =
+		container_of(work, struct ceph_osd_client,
+			     osds_timeout_work.work);
+	unsigned long delay =
+		osdc->client->options->osd_idle_ttl * HZ >> 2;
+
+	dout("osds timeout\n");
+	down_read(&osdc->map_sem);
+	remove_old_osds(osdc, 0);
+	up_read(&osdc->map_sem);
+
+	schedule_delayed_work(&osdc->osds_timeout_work,
+			      round_jiffies_relative(delay));
+}
+
+/*
+ * handle osd op reply.  either call the callback if it is specified,
+ * or do the completion to wake up the waiting thread.
+ */
+static void handle_reply(struct ceph_osd_client *osdc, struct ceph_msg *msg,
+			 struct ceph_connection *con)
+{
+	struct ceph_osd_reply_head *rhead = msg->front.iov_base;
+	struct ceph_osd_request *req;
+	u64 tid;
+	int numops, object_len, flags;
+	s32 result;
+
+	tid = le64_to_cpu(msg->hdr.tid);
+	if (msg->front.iov_len < sizeof(*rhead))
+		goto bad;
+	numops = le32_to_cpu(rhead->num_ops);
+	object_len = le32_to_cpu(rhead->object_len);
+	result = le32_to_cpu(rhead->result);
+	if (msg->front.iov_len != sizeof(*rhead) + object_len +
+	    numops * sizeof(struct ceph_osd_op))
+		goto bad;
+	dout("handle_reply %p tid %llu result %d\n", msg, tid, (int)result);
+
+	/* lookup */
+	mutex_lock(&osdc->request_mutex);
+	req = __lookup_request(osdc, tid);
+	if (req == NULL) {
+		dout("handle_reply tid %llu dne\n", tid);
+		mutex_unlock(&osdc->request_mutex);
+		return;
+	}
+	ceph_osdc_get_request(req);
+	flags = le32_to_cpu(rhead->flags);
+
+	/*
+	 * if this connection filled our message, drop our reference now, to
+	 * avoid a (safe but slower) revoke later.
+	 */
+	if (req->r_con_filling_msg == con && req->r_reply == msg) {
+		dout(" dropping con_filling_msg ref %p\n", con);
+		req->r_con_filling_msg = NULL;
+		ceph_con_put(con);
+	}
+
+	if (!req->r_got_reply) {
+		unsigned bytes;
+
+		req->r_result = le32_to_cpu(rhead->result);
+		bytes = le32_to_cpu(msg->hdr.data_len);
+		dout("handle_reply result %d bytes %d\n", req->r_result,
+		     bytes);
+		if (req->r_result == 0)
+			req->r_result = bytes;
+
+		/* in case this is a write and we need to replay, */
+		req->r_reassert_version = rhead->reassert_version;
+
+		req->r_got_reply = 1;
+	} else if ((flags & CEPH_OSD_FLAG_ONDISK) == 0) {
+		dout("handle_reply tid %llu dup ack\n", tid);
+		mutex_unlock(&osdc->request_mutex);
+		goto done;
+	}
+
+	dout("handle_reply tid %llu flags %d\n", tid, flags);
+
+	/* either this is a read, or we got the safe response */
+	if (result < 0 ||
+	    (flags & CEPH_OSD_FLAG_ONDISK) ||
+	    ((flags & CEPH_OSD_FLAG_WRITE) == 0))
+		__unregister_request(osdc, req);
+
+	mutex_unlock(&osdc->request_mutex);
+
+	if (req->r_callback)
+		req->r_callback(req, msg);
+	else
+		complete_all(&req->r_completion);
+
+	if (flags & CEPH_OSD_FLAG_ONDISK) {
+		if (req->r_safe_callback)
+			req->r_safe_callback(req, msg);
+		complete_all(&req->r_safe_completion);  /* fsync waiter */
+	}
+
+done:
+	ceph_osdc_put_request(req);
+	return;
+
+bad:
+	pr_err("corrupt osd_op_reply got %d %d expected %d\n",
+	       (int)msg->front.iov_len, le32_to_cpu(msg->hdr.front_len),
+	       (int)sizeof(*rhead));
+	ceph_msg_dump(msg);
+}
+
+
+static int __kick_requests(struct ceph_osd_client *osdc,
+			  struct ceph_osd *kickosd)
+{
+	struct ceph_osd_request *req;
+	struct rb_node *p, *n;
+	int needmap = 0;
+	int err;
+
+	dout("kick_requests osd%d\n", kickosd ? kickosd->o_osd : -1);
+	if (kickosd) {
+		err = __reset_osd(osdc, kickosd);
+		if (err == -EAGAIN)
+			return 1;
+	} else {
+		for (p = rb_first(&osdc->osds); p; p = n) {
+			struct ceph_osd *osd =
+				rb_entry(p, struct ceph_osd, o_node);
+
+			n = rb_next(p);
+			if (!ceph_osd_is_up(osdc->osdmap, osd->o_osd) ||
+			    memcmp(&osd->o_con.peer_addr,
+				   ceph_osd_addr(osdc->osdmap,
+						 osd->o_osd),
+				   sizeof(struct ceph_entity_addr)) != 0)
+				__reset_osd(osdc, osd);
+		}
+	}
+
+	for (p = rb_first(&osdc->requests); p; p = rb_next(p)) {
+		req = rb_entry(p, struct ceph_osd_request, r_node);
+
+		if (req->r_resend) {
+			dout(" r_resend set on tid %llu\n", req->r_tid);
+			__cancel_request(req);
+			goto kick;
+		}
+		if (req->r_osd && kickosd == req->r_osd) {
+			__cancel_request(req);
+			goto kick;
+		}
+
+		err = __map_osds(osdc, req);
+		if (err == 0)
+			continue;  /* no change */
+		if (err < 0) {
+			/*
+			 * FIXME: really, we should set the request
+			 * error and fail if this isn't a 'nofail'
+			 * request, but that's a fair bit more
+			 * complicated to do.  So retry!
+			 */
+			dout(" setting r_resend on %llu\n", req->r_tid);
+			req->r_resend = true;
+			continue;
+		}
+		if (req->r_osd == NULL) {
+			dout("tid %llu maps to no valid osd\n", req->r_tid);
+			needmap++;  /* request a newer map */
+			continue;
+		}
+
+kick:
+		dout("kicking %p tid %llu osd%d\n", req, req->r_tid,
+		     req->r_osd ? req->r_osd->o_osd : -1);
+		req->r_flags |= CEPH_OSD_FLAG_RETRY;
+		err = __send_request(osdc, req);
+		if (err) {
+			dout(" setting r_resend on %llu\n", req->r_tid);
+			req->r_resend = true;
+		}
+	}
+
+	return needmap;
+}
+
+/*
+ * Resubmit osd requests whose osd or osd address has changed.  Request
+ * a new osd map if osds are down, or we are otherwise unable to determine
+ * how to direct a request.
+ *
+ * Close connections to down osds.
+ *
+ * If @who is specified, resubmit requests for that specific osd.
+ *
+ * Caller should hold map_sem for read and request_mutex.
+ */
+static void kick_requests(struct ceph_osd_client *osdc,
+			  struct ceph_osd *kickosd)
+{
+	int needmap;
+
+	mutex_lock(&osdc->request_mutex);
+	needmap = __kick_requests(osdc, kickosd);
+	mutex_unlock(&osdc->request_mutex);
+
+	if (needmap) {
+		dout("%d requests for down osds, need new map\n", needmap);
+		ceph_monc_request_next_osdmap(&osdc->client->monc);
+	}
+
+}
+/*
+ * Process updated osd map.
+ *
+ * The message contains any number of incremental and full maps, normally
+ * indicating some sort of topology change in the cluster.  Kick requests
+ * off to different OSDs as needed.
+ */
+void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg)
+{
+	void *p, *end, *next;
+	u32 nr_maps, maplen;
+	u32 epoch;
+	struct ceph_osdmap *newmap = NULL, *oldmap;
+	int err;
+	struct ceph_fsid fsid;
+
+	dout("handle_map have %u\n", osdc->osdmap ? osdc->osdmap->epoch : 0);
+	p = msg->front.iov_base;
+	end = p + msg->front.iov_len;
+
+	/* verify fsid */
+	ceph_decode_need(&p, end, sizeof(fsid), bad);
+	ceph_decode_copy(&p, &fsid, sizeof(fsid));
+	if (ceph_check_fsid(osdc->client, &fsid) < 0)
+		return;
+
+	down_write(&osdc->map_sem);
+
+	/* incremental maps */
+	ceph_decode_32_safe(&p, end, nr_maps, bad);
+	dout(" %d inc maps\n", nr_maps);
+	while (nr_maps > 0) {
+		ceph_decode_need(&p, end, 2*sizeof(u32), bad);
+		epoch = ceph_decode_32(&p);
+		maplen = ceph_decode_32(&p);
+		ceph_decode_need(&p, end, maplen, bad);
+		next = p + maplen;
+		if (osdc->osdmap && osdc->osdmap->epoch+1 == epoch) {
+			dout("applying incremental map %u len %d\n",
+			     epoch, maplen);
+			newmap = osdmap_apply_incremental(&p, next,
+							  osdc->osdmap,
+							  osdc->client->msgr);
+			if (IS_ERR(newmap)) {
+				err = PTR_ERR(newmap);
+				goto bad;
+			}
+			BUG_ON(!newmap);
+			if (newmap != osdc->osdmap) {
+				ceph_osdmap_destroy(osdc->osdmap);
+				osdc->osdmap = newmap;
+			}
+		} else {
+			dout("ignoring incremental map %u len %d\n",
+			     epoch, maplen);
+		}
+		p = next;
+		nr_maps--;
+	}
+	if (newmap)
+		goto done;
+
+	/* full maps */
+	ceph_decode_32_safe(&p, end, nr_maps, bad);
+	dout(" %d full maps\n", nr_maps);
+	while (nr_maps) {
+		ceph_decode_need(&p, end, 2*sizeof(u32), bad);
+		epoch = ceph_decode_32(&p);
+		maplen = ceph_decode_32(&p);
+		ceph_decode_need(&p, end, maplen, bad);
+		if (nr_maps > 1) {
+			dout("skipping non-latest full map %u len %d\n",
+			     epoch, maplen);
+		} else if (osdc->osdmap && osdc->osdmap->epoch >= epoch) {
+			dout("skipping full map %u len %d, "
+			     "older than our %u\n", epoch, maplen,
+			     osdc->osdmap->epoch);
+		} else {
+			dout("taking full map %u len %d\n", epoch, maplen);
+			newmap = osdmap_decode(&p, p+maplen);
+			if (IS_ERR(newmap)) {
+				err = PTR_ERR(newmap);
+				goto bad;
+			}
+			BUG_ON(!newmap);
+			oldmap = osdc->osdmap;
+			osdc->osdmap = newmap;
+			if (oldmap)
+				ceph_osdmap_destroy(oldmap);
+		}
+		p += maplen;
+		nr_maps--;
+	}
+
+done:
+	downgrade_write(&osdc->map_sem);
+	ceph_monc_got_osdmap(&osdc->client->monc, osdc->osdmap->epoch);
+	if (newmap)
+		kick_requests(osdc, NULL);
+	up_read(&osdc->map_sem);
+	wake_up_all(&osdc->client->auth_wq);
+	return;
+
+bad:
+	pr_err("osdc handle_map corrupt msg\n");
+	ceph_msg_dump(msg);
+	up_write(&osdc->map_sem);
+	return;
+}
+
+/*
+ * Register request, send initial attempt.
+ */
+int ceph_osdc_start_request(struct ceph_osd_client *osdc,
+			    struct ceph_osd_request *req,
+			    bool nofail)
+{
+	int rc = 0;
+
+	req->r_request->pages = req->r_pages;
+	req->r_request->nr_pages = req->r_num_pages;
+#ifdef CONFIG_BLOCK
+	req->r_request->bio = req->r_bio;
+#endif
+	req->r_request->trail = req->r_trail;
+
+	register_request(osdc, req);
+
+	down_read(&osdc->map_sem);
+	mutex_lock(&osdc->request_mutex);
+	/*
+	 * a racing kick_requests() may have sent the message for us
+	 * while we dropped request_mutex above, so only send now if
+	 * the request still han't been touched yet.
+	 */
+	if (req->r_sent == 0) {
+		rc = __send_request(osdc, req);
+		if (rc) {
+			if (nofail) {
+				dout("osdc_start_request failed send, "
+				     " marking %lld\n", req->r_tid);
+				req->r_resend = true;
+				rc = 0;
+			} else {
+				__unregister_request(osdc, req);
+			}
+		}
+	}
+	mutex_unlock(&osdc->request_mutex);
+	up_read(&osdc->map_sem);
+	return rc;
+}
+EXPORT_SYMBOL(ceph_osdc_start_request);
+
+/*
+ * wait for a request to complete
+ */
+int ceph_osdc_wait_request(struct ceph_osd_client *osdc,
+			   struct ceph_osd_request *req)
+{
+	int rc;
+
+	rc = wait_for_completion_interruptible(&req->r_completion);
+	if (rc < 0) {
+		mutex_lock(&osdc->request_mutex);
+		__cancel_request(req);
+		__unregister_request(osdc, req);
+		mutex_unlock(&osdc->request_mutex);
+		dout("wait_request tid %llu canceled/timed out\n", req->r_tid);
+		return rc;
+	}
+
+	dout("wait_request tid %llu result %d\n", req->r_tid, req->r_result);
+	return req->r_result;
+}
+EXPORT_SYMBOL(ceph_osdc_wait_request);
+
+/*
+ * sync - wait for all in-flight requests to flush.  avoid starvation.
+ */
+void ceph_osdc_sync(struct ceph_osd_client *osdc)
+{
+	struct ceph_osd_request *req;
+	u64 last_tid, next_tid = 0;
+
+	mutex_lock(&osdc->request_mutex);
+	last_tid = osdc->last_tid;
+	while (1) {
+		req = __lookup_request_ge(osdc, next_tid);
+		if (!req)
+			break;
+		if (req->r_tid > last_tid)
+			break;
+
+		next_tid = req->r_tid + 1;
+		if ((req->r_flags & CEPH_OSD_FLAG_WRITE) == 0)
+			continue;
+
+		ceph_osdc_get_request(req);
+		mutex_unlock(&osdc->request_mutex);
+		dout("sync waiting on tid %llu (last is %llu)\n",
+		     req->r_tid, last_tid);
+		wait_for_completion(&req->r_safe_completion);
+		mutex_lock(&osdc->request_mutex);
+		ceph_osdc_put_request(req);
+	}
+	mutex_unlock(&osdc->request_mutex);
+	dout("sync done (thru tid %llu)\n", last_tid);
+}
+EXPORT_SYMBOL(ceph_osdc_sync);
+
+/*
+ * init, shutdown
+ */
+int ceph_osdc_init(struct ceph_osd_client *osdc, struct ceph_client *client)
+{
+	int err;
+
+	dout("init\n");
+	osdc->client = client;
+	osdc->osdmap = NULL;
+	init_rwsem(&osdc->map_sem);
+	init_completion(&osdc->map_waiters);
+	osdc->last_requested_map = 0;
+	mutex_init(&osdc->request_mutex);
+	osdc->last_tid = 0;
+	osdc->osds = RB_ROOT;
+	INIT_LIST_HEAD(&osdc->osd_lru);
+	osdc->requests = RB_ROOT;
+	INIT_LIST_HEAD(&osdc->req_lru);
+	osdc->num_requests = 0;
+	INIT_DELAYED_WORK(&osdc->timeout_work, handle_timeout);
+	INIT_DELAYED_WORK(&osdc->osds_timeout_work, handle_osds_timeout);
+
+	schedule_delayed_work(&osdc->osds_timeout_work,
+	   round_jiffies_relative(osdc->client->options->osd_idle_ttl * HZ));
+
+	err = -ENOMEM;
+	osdc->req_mempool = mempool_create_kmalloc_pool(10,
+					sizeof(struct ceph_osd_request));
+	if (!osdc->req_mempool)
+		goto out;
+
+	err = ceph_msgpool_init(&osdc->msgpool_op, OSD_OP_FRONT_LEN, 10, true,
+				"osd_op");
+	if (err < 0)
+		goto out_mempool;
+	err = ceph_msgpool_init(&osdc->msgpool_op_reply,
+				OSD_OPREPLY_FRONT_LEN, 10, true,
+				"osd_op_reply");
+	if (err < 0)
+		goto out_msgpool;
+	return 0;
+
+out_msgpool:
+	ceph_msgpool_destroy(&osdc->msgpool_op);
+out_mempool:
+	mempool_destroy(osdc->req_mempool);
+out:
+	return err;
+}
+EXPORT_SYMBOL(ceph_osdc_init);
+
+void ceph_osdc_stop(struct ceph_osd_client *osdc)
+{
+	cancel_delayed_work_sync(&osdc->timeout_work);
+	cancel_delayed_work_sync(&osdc->osds_timeout_work);
+	if (osdc->osdmap) {
+		ceph_osdmap_destroy(osdc->osdmap);
+		osdc->osdmap = NULL;
+	}
+	remove_old_osds(osdc, 1);
+	mempool_destroy(osdc->req_mempool);
+	ceph_msgpool_destroy(&osdc->msgpool_op);
+	ceph_msgpool_destroy(&osdc->msgpool_op_reply);
+}
+EXPORT_SYMBOL(ceph_osdc_stop);
+
+/*
+ * Read some contiguous pages.  If we cross a stripe boundary, shorten
+ * *plen.  Return number of bytes read, or error.
+ */
+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 num_pages)
+{
+	struct ceph_osd_request *req;
+	int rc = 0;
+
+	dout("readpages on ino %llx.%llx on %llu~%llu\n", vino.ino,
+	     vino.snap, off, *plen);
+	req = ceph_osdc_new_request(osdc, layout, vino, off, plen,
+				    CEPH_OSD_OP_READ, CEPH_OSD_FLAG_READ,
+				    NULL, 0, truncate_seq, truncate_size, NULL,
+				    false, 1);
+	if (!req)
+		return -ENOMEM;
+
+	/* it may be a short read due to an object boundary */
+	req->r_pages = pages;
+
+	dout("readpages  final extent is %llu~%llu (%d pages)\n",
+	     off, *plen, req->r_num_pages);
+
+	rc = ceph_osdc_start_request(osdc, req, false);
+	if (!rc)
+		rc = ceph_osdc_wait_request(osdc, req);
+
+	ceph_osdc_put_request(req);
+	dout("readpages result %d\n", rc);
+	return rc;
+}
+EXPORT_SYMBOL(ceph_osdc_readpages);
+
+/*
+ * do a synchronous write on N pages
+ */
+int ceph_osdc_writepages(struct ceph_osd_client *osdc, struct ceph_vino vino,
+			 struct ceph_file_layout *layout,
+			 struct ceph_snap_context *snapc,
+			 u64 off, u64 len,
+			 u32 truncate_seq, u64 truncate_size,
+			 struct timespec *mtime,
+			 struct page **pages, int num_pages,
+			 int flags, int do_sync, bool nofail)
+{
+	struct ceph_osd_request *req;
+	int rc = 0;
+
+	BUG_ON(vino.snap != CEPH_NOSNAP);
+	req = ceph_osdc_new_request(osdc, layout, vino, off, &len,
+				    CEPH_OSD_OP_WRITE,
+				    flags | CEPH_OSD_FLAG_ONDISK |
+					    CEPH_OSD_FLAG_WRITE,
+				    snapc, do_sync,
+				    truncate_seq, truncate_size, mtime,
+				    nofail, 1);
+	if (!req)
+		return -ENOMEM;
+
+	/* it may be a short write due to an object boundary */
+	req->r_pages = pages;
+	dout("writepages %llu~%llu (%d pages)\n", off, len,
+	     req->r_num_pages);
+
+	rc = ceph_osdc_start_request(osdc, req, nofail);
+	if (!rc)
+		rc = ceph_osdc_wait_request(osdc, req);
+
+	ceph_osdc_put_request(req);
+	if (rc == 0)
+		rc = len;
+	dout("writepages result %d\n", rc);
+	return rc;
+}
+EXPORT_SYMBOL(ceph_osdc_writepages);
+
+/*
+ * handle incoming message
+ */
+static void dispatch(struct ceph_connection *con, struct ceph_msg *msg)
+{
+	struct ceph_osd *osd = con->private;
+	struct ceph_osd_client *osdc;
+	int type = le16_to_cpu(msg->hdr.type);
+
+	if (!osd)
+		goto out;
+	osdc = osd->o_osdc;
+
+	switch (type) {
+	case CEPH_MSG_OSD_MAP:
+		ceph_osdc_handle_map(osdc, msg);
+		break;
+	case CEPH_MSG_OSD_OPREPLY:
+		handle_reply(osdc, msg, con);
+		break;
+
+	default:
+		pr_err("received unknown message type %d %s\n", type,
+		       ceph_msg_type_name(type));
+	}
+out:
+	ceph_msg_put(msg);
+}
+
+/*
+ * lookup and return message for incoming reply.  set up reply message
+ * pages.
+ */
+static struct ceph_msg *get_reply(struct ceph_connection *con,
+				  struct ceph_msg_header *hdr,
+				  int *skip)
+{
+	struct ceph_osd *osd = con->private;
+	struct ceph_osd_client *osdc = osd->o_osdc;
+	struct ceph_msg *m;
+	struct ceph_osd_request *req;
+	int front = le32_to_cpu(hdr->front_len);
+	int data_len = le32_to_cpu(hdr->data_len);
+	u64 tid;
+
+	tid = le64_to_cpu(hdr->tid);
+	mutex_lock(&osdc->request_mutex);
+	req = __lookup_request(osdc, tid);
+	if (!req) {
+		*skip = 1;
+		m = NULL;
+		pr_info("get_reply unknown tid %llu from osd%d\n", tid,
+			osd->o_osd);
+		goto out;
+	}
+
+	if (req->r_con_filling_msg) {
+		dout("get_reply revoking msg %p from old con %p\n",
+		     req->r_reply, req->r_con_filling_msg);
+		ceph_con_revoke_message(req->r_con_filling_msg, req->r_reply);
+		ceph_con_put(req->r_con_filling_msg);
+		req->r_con_filling_msg = NULL;
+	}
+
+	if (front > req->r_reply->front.iov_len) {
+		pr_warning("get_reply front %d > preallocated %d\n",
+			   front, (int)req->r_reply->front.iov_len);
+		m = ceph_msg_new(CEPH_MSG_OSD_OPREPLY, front, GFP_NOFS);
+		if (!m)
+			goto out;
+		ceph_msg_put(req->r_reply);
+		req->r_reply = m;
+	}
+	m = ceph_msg_get(req->r_reply);
+
+	if (data_len > 0) {
+		unsigned data_off = le16_to_cpu(hdr->data_off);
+		int want = calc_pages_for(data_off & ~PAGE_MASK, data_len);
+
+		if (unlikely(req->r_num_pages < want)) {
+			pr_warning("tid %lld reply %d > expected %d pages\n",
+				   tid, want, m->nr_pages);
+			*skip = 1;
+			ceph_msg_put(m);
+			m = NULL;
+			goto out;
+		}
+		m->pages = req->r_pages;
+		m->nr_pages = req->r_num_pages;
+#ifdef CONFIG_BLOCK
+		m->bio = req->r_bio;
+#endif
+	}
+	*skip = 0;
+	req->r_con_filling_msg = ceph_con_get(con);
+	dout("get_reply tid %lld %p\n", tid, m);
+
+out:
+	mutex_unlock(&osdc->request_mutex);
+	return m;
+
+}
+
+static struct ceph_msg *alloc_msg(struct ceph_connection *con,
+				  struct ceph_msg_header *hdr,
+				  int *skip)
+{
+	struct ceph_osd *osd = con->private;
+	int type = le16_to_cpu(hdr->type);
+	int front = le32_to_cpu(hdr->front_len);
+
+	switch (type) {
+	case CEPH_MSG_OSD_MAP:
+		return ceph_msg_new(type, front, GFP_NOFS);
+	case CEPH_MSG_OSD_OPREPLY:
+		return get_reply(con, hdr, skip);
+	default:
+		pr_info("alloc_msg unexpected msg type %d from osd%d\n", type,
+			osd->o_osd);
+		*skip = 1;
+		return NULL;
+	}
+}
+
+/*
+ * Wrappers to refcount containing ceph_osd struct
+ */
+static struct ceph_connection *get_osd_con(struct ceph_connection *con)
+{
+	struct ceph_osd *osd = con->private;
+	if (get_osd(osd))
+		return con;
+	return NULL;
+}
+
+static void put_osd_con(struct ceph_connection *con)
+{
+	struct ceph_osd *osd = con->private;
+	put_osd(osd);
+}
+
+/*
+ * authentication
+ */
+static int get_authorizer(struct ceph_connection *con,
+			  void **buf, int *len, int *proto,
+			  void **reply_buf, int *reply_len, int force_new)
+{
+	struct ceph_osd *o = con->private;
+	struct ceph_osd_client *osdc = o->o_osdc;
+	struct ceph_auth_client *ac = osdc->client->monc.auth;
+	int ret = 0;
+
+	if (force_new && o->o_authorizer) {
+		ac->ops->destroy_authorizer(ac, o->o_authorizer);
+		o->o_authorizer = NULL;
+	}
+	if (o->o_authorizer == NULL) {
+		ret = ac->ops->create_authorizer(
+			ac, CEPH_ENTITY_TYPE_OSD,
+			&o->o_authorizer,
+			&o->o_authorizer_buf,
+			&o->o_authorizer_buf_len,
+			&o->o_authorizer_reply_buf,
+			&o->o_authorizer_reply_buf_len);
+		if (ret)
+			return ret;
+	}
+
+	*proto = ac->protocol;
+	*buf = o->o_authorizer_buf;
+	*len = o->o_authorizer_buf_len;
+	*reply_buf = o->o_authorizer_reply_buf;
+	*reply_len = o->o_authorizer_reply_buf_len;
+	return 0;
+}
+
+
+static int verify_authorizer_reply(struct ceph_connection *con, int len)
+{
+	struct ceph_osd *o = con->private;
+	struct ceph_osd_client *osdc = o->o_osdc;
+	struct ceph_auth_client *ac = osdc->client->monc.auth;
+
+	return ac->ops->verify_authorizer_reply(ac, o->o_authorizer, len);
+}
+
+static int invalidate_authorizer(struct ceph_connection *con)
+{
+	struct ceph_osd *o = con->private;
+	struct ceph_osd_client *osdc = o->o_osdc;
+	struct ceph_auth_client *ac = osdc->client->monc.auth;
+
+	if (ac->ops->invalidate_authorizer)
+		ac->ops->invalidate_authorizer(ac, CEPH_ENTITY_TYPE_OSD);
+
+	return ceph_monc_validate_auth(&osdc->client->monc);
+}
+
+static const struct ceph_connection_operations osd_con_ops = {
+	.get = get_osd_con,
+	.put = put_osd_con,
+	.dispatch = dispatch,
+	.get_authorizer = get_authorizer,
+	.verify_authorizer_reply = verify_authorizer_reply,
+	.invalidate_authorizer = invalidate_authorizer,
+	.alloc_msg = alloc_msg,
+	.fault = osd_reset,
+};
diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
new file mode 100644
index 00000000000..d73f3f6efa3
--- /dev/null
+++ b/net/ceph/osdmap.c
@@ -0,0 +1,1128 @@
+
+#include <linux/ceph/ceph_debug.h>
+
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <asm/div64.h>
+
+#include <linux/ceph/libceph.h>
+#include <linux/ceph/osdmap.h>
+#include <linux/ceph/decode.h>
+#include <linux/crush/hash.h>
+#include <linux/crush/mapper.h>
+
+char *ceph_osdmap_state_str(char *str, int len, int state)
+{
+	int flag = 0;
+
+	if (!len)
+		goto done;
+
+	*str = '\0';
+	if (state) {
+		if (state & CEPH_OSD_EXISTS) {
+			snprintf(str, len, "exists");
+			flag = 1;
+		}
+		if (state & CEPH_OSD_UP) {
+			snprintf(str, len, "%s%s%s", str, (flag ? ", " : ""),
+				 "up");
+			flag = 1;
+		}
+	} else {
+		snprintf(str, len, "doesn't exist");
+	}
+done:
+	return str;
+}
+
+/* maps */
+
+static int calc_bits_of(unsigned t)
+{
+	int b = 0;
+	while (t) {
+		t = t >> 1;
+		b++;
+	}
+	return b;
+}
+
+/*
+ * the foo_mask is the smallest value 2^n-1 that is >= foo.
+ */
+static void calc_pg_masks(struct ceph_pg_pool_info *pi)
+{
+	pi->pg_num_mask = (1 << calc_bits_of(le32_to_cpu(pi->v.pg_num)-1)) - 1;
+	pi->pgp_num_mask =
+		(1 << calc_bits_of(le32_to_cpu(pi->v.pgp_num)-1)) - 1;
+	pi->lpg_num_mask =
+		(1 << calc_bits_of(le32_to_cpu(pi->v.lpg_num)-1)) - 1;
+	pi->lpgp_num_mask =
+		(1 << calc_bits_of(le32_to_cpu(pi->v.lpgp_num)-1)) - 1;
+}
+
+/*
+ * decode crush map
+ */
+static int crush_decode_uniform_bucket(void **p, void *end,
+				       struct crush_bucket_uniform *b)
+{
+	dout("crush_decode_uniform_bucket %p to %p\n", *p, end);
+	ceph_decode_need(p, end, (1+b->h.size) * sizeof(u32), bad);
+	b->item_weight = ceph_decode_32(p);
+	return 0;
+bad:
+	return -EINVAL;
+}
+
+static int crush_decode_list_bucket(void **p, void *end,
+				    struct crush_bucket_list *b)
+{
+	int j;
+	dout("crush_decode_list_bucket %p to %p\n", *p, end);
+	b->item_weights = kcalloc(b->h.size, sizeof(u32), GFP_NOFS);
+	if (b->item_weights == NULL)
+		return -ENOMEM;
+	b->sum_weights = kcalloc(b->h.size, sizeof(u32), GFP_NOFS);
+	if (b->sum_weights == NULL)
+		return -ENOMEM;
+	ceph_decode_need(p, end, 2 * b->h.size * sizeof(u32), bad);
+	for (j = 0; j < b->h.size; j++) {
+		b->item_weights[j] = ceph_decode_32(p);
+		b->sum_weights[j] = ceph_decode_32(p);
+	}
+	return 0;
+bad:
+	return -EINVAL;
+}
+
+static int crush_decode_tree_bucket(void **p, void *end,
+				    struct crush_bucket_tree *b)
+{
+	int j;
+	dout("crush_decode_tree_bucket %p to %p\n", *p, end);
+	ceph_decode_32_safe(p, end, b->num_nodes, bad);
+	b->node_weights = kcalloc(b->num_nodes, sizeof(u32), GFP_NOFS);
+	if (b->node_weights == NULL)
+		return -ENOMEM;
+	ceph_decode_need(p, end, b->num_nodes * sizeof(u32), bad);
+	for (j = 0; j < b->num_nodes; j++)
+		b->node_weights[j] = ceph_decode_32(p);
+	return 0;
+bad:
+	return -EINVAL;
+}
+
+static int crush_decode_straw_bucket(void **p, void *end,
+				     struct crush_bucket_straw *b)
+{
+	int j;
+	dout("crush_decode_straw_bucket %p to %p\n", *p, end);
+	b->item_weights = kcalloc(b->h.size, sizeof(u32), GFP_NOFS);
+	if (b->item_weights == NULL)
+		return -ENOMEM;
+	b->straws = kcalloc(b->h.size, sizeof(u32), GFP_NOFS);
+	if (b->straws == NULL)
+		return -ENOMEM;
+	ceph_decode_need(p, end, 2 * b->h.size * sizeof(u32), bad);
+	for (j = 0; j < b->h.size; j++) {
+		b->item_weights[j] = ceph_decode_32(p);
+		b->straws[j] = ceph_decode_32(p);
+	}
+	return 0;
+bad:
+	return -EINVAL;
+}
+
+static struct crush_map *crush_decode(void *pbyval, void *end)
+{
+	struct crush_map *c;
+	int err = -EINVAL;
+	int i, j;
+	void **p = &pbyval;
+	void *start = pbyval;
+	u32 magic;
+
+	dout("crush_decode %p to %p len %d\n", *p, end, (int)(end - *p));
+
+	c = kzalloc(sizeof(*c), GFP_NOFS);
+	if (c == NULL)
+		return ERR_PTR(-ENOMEM);
+
+	ceph_decode_need(p, end, 4*sizeof(u32), bad);
+	magic = ceph_decode_32(p);
+	if (magic != CRUSH_MAGIC) {
+		pr_err("crush_decode magic %x != current %x\n",
+		       (unsigned)magic, (unsigned)CRUSH_MAGIC);
+		goto bad;
+	}
+	c->max_buckets = ceph_decode_32(p);
+	c->max_rules = ceph_decode_32(p);
+	c->max_devices = ceph_decode_32(p);
+
+	c->device_parents = kcalloc(c->max_devices, sizeof(u32), GFP_NOFS);
+	if (c->device_parents == NULL)
+		goto badmem;
+	c->bucket_parents = kcalloc(c->max_buckets, sizeof(u32), GFP_NOFS);
+	if (c->bucket_parents == NULL)
+		goto badmem;
+
+	c->buckets = kcalloc(c->max_buckets, sizeof(*c->buckets), GFP_NOFS);
+	if (c->buckets == NULL)
+		goto badmem;
+	c->rules = kcalloc(c->max_rules, sizeof(*c->rules), GFP_NOFS);
+	if (c->rules == NULL)
+		goto badmem;
+
+	/* buckets */
+	for (i = 0; i < c->max_buckets; i++) {
+		int size = 0;
+		u32 alg;
+		struct crush_bucket *b;
+
+		ceph_decode_32_safe(p, end, alg, bad);
+		if (alg == 0) {
+			c->buckets[i] = NULL;
+			continue;
+		}
+		dout("crush_decode bucket %d off %x %p to %p\n",
+		     i, (int)(*p-start), *p, end);
+
+		switch (alg) {
+		case CRUSH_BUCKET_UNIFORM:
+			size = sizeof(struct crush_bucket_uniform);
+			break;
+		case CRUSH_BUCKET_LIST:
+			size = sizeof(struct crush_bucket_list);
+			break;
+		case CRUSH_BUCKET_TREE:
+			size = sizeof(struct crush_bucket_tree);
+			break;
+		case CRUSH_BUCKET_STRAW:
+			size = sizeof(struct crush_bucket_straw);
+			break;
+		default:
+			err = -EINVAL;
+			goto bad;
+		}
+		BUG_ON(size == 0);
+		b = c->buckets[i] = kzalloc(size, GFP_NOFS);
+		if (b == NULL)
+			goto badmem;
+
+		ceph_decode_need(p, end, 4*sizeof(u32), bad);
+		b->id = ceph_decode_32(p);
+		b->type = ceph_decode_16(p);
+		b->alg = ceph_decode_8(p);
+		b->hash = ceph_decode_8(p);
+		b->weight = ceph_decode_32(p);
+		b->size = ceph_decode_32(p);
+
+		dout("crush_decode bucket size %d off %x %p to %p\n",
+		     b->size, (int)(*p-start), *p, end);
+
+		b->items = kcalloc(b->size, sizeof(__s32), GFP_NOFS);
+		if (b->items == NULL)
+			goto badmem;
+		b->perm = kcalloc(b->size, sizeof(u32), GFP_NOFS);
+		if (b->perm == NULL)
+			goto badmem;
+		b->perm_n = 0;
+
+		ceph_decode_need(p, end, b->size*sizeof(u32), bad);
+		for (j = 0; j < b->size; j++)
+			b->items[j] = ceph_decode_32(p);
+
+		switch (b->alg) {
+		case CRUSH_BUCKET_UNIFORM:
+			err = crush_decode_uniform_bucket(p, end,
+				  (struct crush_bucket_uniform *)b);
+			if (err < 0)
+				goto bad;
+			break;
+		case CRUSH_BUCKET_LIST:
+			err = crush_decode_list_bucket(p, end,
+			       (struct crush_bucket_list *)b);
+			if (err < 0)
+				goto bad;
+			break;
+		case CRUSH_BUCKET_TREE:
+			err = crush_decode_tree_bucket(p, end,
+				(struct crush_bucket_tree *)b);
+			if (err < 0)
+				goto bad;
+			break;
+		case CRUSH_BUCKET_STRAW:
+			err = crush_decode_straw_bucket(p, end,
+				(struct crush_bucket_straw *)b);
+			if (err < 0)
+				goto bad;
+			break;
+		}
+	}
+
+	/* rules */
+	dout("rule vec is %p\n", c->rules);
+	for (i = 0; i < c->max_rules; i++) {
+		u32 yes;
+		struct crush_rule *r;
+
+		ceph_decode_32_safe(p, end, yes, bad);
+		if (!yes) {
+			dout("crush_decode NO rule %d off %x %p to %p\n",
+			     i, (int)(*p-start), *p, end);
+			c->rules[i] = NULL;
+			continue;
+		}
+
+		dout("crush_decode rule %d off %x %p to %p\n",
+		     i, (int)(*p-start), *p, end);
+
+		/* len */
+		ceph_decode_32_safe(p, end, yes, bad);
+#if BITS_PER_LONG == 32
+		err = -EINVAL;
+		if (yes > ULONG_MAX / sizeof(struct crush_rule_step))
+			goto bad;
+#endif
+		r = c->rules[i] = kmalloc(sizeof(*r) +
+					  yes*sizeof(struct crush_rule_step),
+					  GFP_NOFS);
+		if (r == NULL)
+			goto badmem;
+		dout(" rule %d is at %p\n", i, r);
+		r->len = yes;
+		ceph_decode_copy_safe(p, end, &r->mask, 4, bad); /* 4 u8's */
+		ceph_decode_need(p, end, r->len*3*sizeof(u32), bad);
+		for (j = 0; j < r->len; j++) {
+			r->steps[j].op = ceph_decode_32(p);
+			r->steps[j].arg1 = ceph_decode_32(p);
+			r->steps[j].arg2 = ceph_decode_32(p);
+		}
+	}
+
+	/* ignore trailing name maps. */
+
+	dout("crush_decode success\n");
+	return c;
+
+badmem:
+	err = -ENOMEM;
+bad:
+	dout("crush_decode fail %d\n", err);
+	crush_destroy(c);
+	return ERR_PTR(err);
+}
+
+/*
+ * rbtree of pg_mapping for handling pg_temp (explicit mapping of pgid
+ * to a set of osds)
+ */
+static int pgid_cmp(struct ceph_pg l, struct ceph_pg r)
+{
+	u64 a = *(u64 *)&l;
+	u64 b = *(u64 *)&r;
+
+	if (a < b)
+		return -1;
+	if (a > b)
+		return 1;
+	return 0;
+}
+
+static int __insert_pg_mapping(struct ceph_pg_mapping *new,
+			       struct rb_root *root)
+{
+	struct rb_node **p = &root->rb_node;
+	struct rb_node *parent = NULL;
+	struct ceph_pg_mapping *pg = NULL;
+	int c;
+
+	while (*p) {
+		parent = *p;
+		pg = rb_entry(parent, struct ceph_pg_mapping, node);
+		c = pgid_cmp(new->pgid, pg->pgid);
+		if (c < 0)
+			p = &(*p)->rb_left;
+		else if (c > 0)
+			p = &(*p)->rb_right;
+		else
+			return -EEXIST;
+	}
+
+	rb_link_node(&new->node, parent, p);
+	rb_insert_color(&new->node, root);
+	return 0;
+}
+
+static struct ceph_pg_mapping *__lookup_pg_mapping(struct rb_root *root,
+						   struct ceph_pg pgid)
+{
+	struct rb_node *n = root->rb_node;
+	struct ceph_pg_mapping *pg;
+	int c;
+
+	while (n) {
+		pg = rb_entry(n, struct ceph_pg_mapping, node);
+		c = pgid_cmp(pgid, pg->pgid);
+		if (c < 0)
+			n = n->rb_left;
+		else if (c > 0)
+			n = n->rb_right;
+		else
+			return pg;
+	}
+	return NULL;
+}
+
+/*
+ * rbtree of pg pool info
+ */
+static int __insert_pg_pool(struct rb_root *root, struct ceph_pg_pool_info *new)
+{
+	struct rb_node **p = &root->rb_node;
+	struct rb_node *parent = NULL;
+	struct ceph_pg_pool_info *pi = NULL;
+
+	while (*p) {
+		parent = *p;
+		pi = rb_entry(parent, struct ceph_pg_pool_info, node);
+		if (new->id < pi->id)
+			p = &(*p)->rb_left;
+		else if (new->id > pi->id)
+			p = &(*p)->rb_right;
+		else
+			return -EEXIST;
+	}
+
+	rb_link_node(&new->node, parent, p);
+	rb_insert_color(&new->node, root);
+	return 0;
+}
+
+static struct ceph_pg_pool_info *__lookup_pg_pool(struct rb_root *root, int id)
+{
+	struct ceph_pg_pool_info *pi;
+	struct rb_node *n = root->rb_node;
+
+	while (n) {
+		pi = rb_entry(n, struct ceph_pg_pool_info, node);
+		if (id < pi->id)
+			n = n->rb_left;
+		else if (id > pi->id)
+			n = n->rb_right;
+		else
+			return pi;
+	}
+	return NULL;
+}
+
+int ceph_pg_poolid_by_name(struct ceph_osdmap *map, const char *name)
+{
+	struct rb_node *rbp;
+
+	for (rbp = rb_first(&map->pg_pools); rbp; rbp = rb_next(rbp)) {
+		struct ceph_pg_pool_info *pi =
+			rb_entry(rbp, struct ceph_pg_pool_info, node);
+		if (pi->name && strcmp(pi->name, name) == 0)
+			return pi->id;
+	}
+	return -ENOENT;
+}
+EXPORT_SYMBOL(ceph_pg_poolid_by_name);
+
+static void __remove_pg_pool(struct rb_root *root, struct ceph_pg_pool_info *pi)
+{
+	rb_erase(&pi->node, root);
+	kfree(pi->name);
+	kfree(pi);
+}
+
+static int __decode_pool(void **p, void *end, struct ceph_pg_pool_info *pi)
+{
+	unsigned n, m;
+
+	ceph_decode_copy(p, &pi->v, sizeof(pi->v));
+	calc_pg_masks(pi);
+
+	/* num_snaps * snap_info_t */
+	n = le32_to_cpu(pi->v.num_snaps);
+	while (n--) {
+		ceph_decode_need(p, end, sizeof(u64) + 1 + sizeof(u64) +
+				 sizeof(struct ceph_timespec), bad);
+		*p += sizeof(u64) +       /* key */
+			1 + sizeof(u64) + /* u8, snapid */
+			sizeof(struct ceph_timespec);
+		m = ceph_decode_32(p);    /* snap name */
+		*p += m;
+	}
+
+	*p += le32_to_cpu(pi->v.num_removed_snap_intervals) * sizeof(u64) * 2;
+	return 0;
+
+bad:
+	return -EINVAL;
+}
+
+static int __decode_pool_names(void **p, void *end, struct ceph_osdmap *map)
+{
+	struct ceph_pg_pool_info *pi;
+	u32 num, len, pool;
+
+	ceph_decode_32_safe(p, end, num, bad);
+	dout(" %d pool names\n", num);
+	while (num--) {
+		ceph_decode_32_safe(p, end, pool, bad);
+		ceph_decode_32_safe(p, end, len, bad);
+		dout("  pool %d len %d\n", pool, len);
+		pi = __lookup_pg_pool(&map->pg_pools, pool);
+		if (pi) {
+			kfree(pi->name);
+			pi->name = kmalloc(len + 1, GFP_NOFS);
+			if (pi->name) {
+				memcpy(pi->name, *p, len);
+				pi->name[len] = '\0';
+				dout("  name is %s\n", pi->name);
+			}
+		}
+		*p += len;
+	}
+	return 0;
+
+bad:
+	return -EINVAL;
+}
+
+/*
+ * osd map
+ */
+void ceph_osdmap_destroy(struct ceph_osdmap *map)
+{
+	dout("osdmap_destroy %p\n", map);
+	if (map->crush)
+		crush_destroy(map->crush);
+	while (!RB_EMPTY_ROOT(&map->pg_temp)) {
+		struct ceph_pg_mapping *pg =
+			rb_entry(rb_first(&map->pg_temp),
+				 struct ceph_pg_mapping, node);
+		rb_erase(&pg->node, &map->pg_temp);
+		kfree(pg);
+	}
+	while (!RB_EMPTY_ROOT(&map->pg_pools)) {
+		struct ceph_pg_pool_info *pi =
+			rb_entry(rb_first(&map->pg_pools),
+				 struct ceph_pg_pool_info, node);
+		__remove_pg_pool(&map->pg_pools, pi);
+	}
+	kfree(map->osd_state);
+	kfree(map->osd_weight);
+	kfree(map->osd_addr);
+	kfree(map);
+}
+
+/*
+ * adjust max osd value.  reallocate arrays.
+ */
+static int osdmap_set_max_osd(struct ceph_osdmap *map, int max)
+{
+	u8 *state;
+	struct ceph_entity_addr *addr;
+	u32 *weight;
+
+	state = kcalloc(max, sizeof(*state), GFP_NOFS);
+	addr = kcalloc(max, sizeof(*addr), GFP_NOFS);
+	weight = kcalloc(max, sizeof(*weight), GFP_NOFS);
+	if (state == NULL || addr == NULL || weight == NULL) {
+		kfree(state);
+		kfree(addr);
+		kfree(weight);
+		return -ENOMEM;
+	}
+
+	/* copy old? */
+	if (map->osd_state) {
+		memcpy(state, map->osd_state, map->max_osd*sizeof(*state));
+		memcpy(addr, map->osd_addr, map->max_osd*sizeof(*addr));
+		memcpy(weight, map->osd_weight, map->max_osd*sizeof(*weight));
+		kfree(map->osd_state);
+		kfree(map->osd_addr);
+		kfree(map->osd_weight);
+	}
+
+	map->osd_state = state;
+	map->osd_weight = weight;
+	map->osd_addr = addr;
+	map->max_osd = max;
+	return 0;
+}
+
+/*
+ * decode a full map.
+ */
+struct ceph_osdmap *osdmap_decode(void **p, void *end)
+{
+	struct ceph_osdmap *map;
+	u16 version;
+	u32 len, max, i;
+	u8 ev;
+	int err = -EINVAL;
+	void *start = *p;
+	struct ceph_pg_pool_info *pi;
+
+	dout("osdmap_decode %p to %p len %d\n", *p, end, (int)(end - *p));
+
+	map = kzalloc(sizeof(*map), GFP_NOFS);
+	if (map == NULL)
+		return ERR_PTR(-ENOMEM);
+	map->pg_temp = RB_ROOT;
+
+	ceph_decode_16_safe(p, end, version, bad);
+	if (version > CEPH_OSDMAP_VERSION) {
+		pr_warning("got unknown v %d > %d of osdmap\n", version,
+			   CEPH_OSDMAP_VERSION);
+		goto bad;
+	}
+
+	ceph_decode_need(p, end, 2*sizeof(u64)+6*sizeof(u32), bad);
+	ceph_decode_copy(p, &map->fsid, sizeof(map->fsid));
+	map->epoch = ceph_decode_32(p);
+	ceph_decode_copy(p, &map->created, sizeof(map->created));
+	ceph_decode_copy(p, &map->modified, sizeof(map->modified));
+
+	ceph_decode_32_safe(p, end, max, bad);
+	while (max--) {
+		ceph_decode_need(p, end, 4 + 1 + sizeof(pi->v), bad);
+		pi = kzalloc(sizeof(*pi), GFP_NOFS);
+		if (!pi)
+			goto bad;
+		pi->id = ceph_decode_32(p);
+		ev = ceph_decode_8(p); /* encoding version */
+		if (ev > CEPH_PG_POOL_VERSION) {
+			pr_warning("got unknown v %d > %d of ceph_pg_pool\n",
+				   ev, CEPH_PG_POOL_VERSION);
+			kfree(pi);
+			goto bad;
+		}
+		err = __decode_pool(p, end, pi);
+		if (err < 0)
+			goto bad;
+		__insert_pg_pool(&map->pg_pools, pi);
+	}
+
+	if (version >= 5 && __decode_pool_names(p, end, map) < 0)
+		goto bad;
+
+	ceph_decode_32_safe(p, end, map->pool_max, bad);
+
+	ceph_decode_32_safe(p, end, map->flags, bad);
+
+	max = ceph_decode_32(p);
+
+	/* (re)alloc osd arrays */
+	err = osdmap_set_max_osd(map, max);
+	if (err < 0)
+		goto bad;
+	dout("osdmap_decode max_osd = %d\n", map->max_osd);
+
+	/* osds */
+	err = -EINVAL;
+	ceph_decode_need(p, end, 3*sizeof(u32) +
+			 map->max_osd*(1 + sizeof(*map->osd_weight) +
+				       sizeof(*map->osd_addr)), bad);
+	*p += 4; /* skip length field (should match max) */
+	ceph_decode_copy(p, map->osd_state, map->max_osd);
+
+	*p += 4; /* skip length field (should match max) */
+	for (i = 0; i < map->max_osd; i++)
+		map->osd_weight[i] = ceph_decode_32(p);
+
+	*p += 4; /* skip length field (should match max) */
+	ceph_decode_copy(p, map->osd_addr, map->max_osd*sizeof(*map->osd_addr));
+	for (i = 0; i < map->max_osd; i++)
+		ceph_decode_addr(&map->osd_addr[i]);
+
+	/* pg_temp */
+	ceph_decode_32_safe(p, end, len, bad);
+	for (i = 0; i < len; i++) {
+		int n, j;
+		struct ceph_pg pgid;
+		struct ceph_pg_mapping *pg;
+
+		ceph_decode_need(p, end, sizeof(u32) + sizeof(u64), bad);
+		ceph_decode_copy(p, &pgid, sizeof(pgid));
+		n = ceph_decode_32(p);
+		ceph_decode_need(p, end, n * sizeof(u32), bad);
+		err = -ENOMEM;
+		pg = kmalloc(sizeof(*pg) + n*sizeof(u32), GFP_NOFS);
+		if (!pg)
+			goto bad;
+		pg->pgid = pgid;
+		pg->len = n;
+		for (j = 0; j < n; j++)
+			pg->osds[j] = ceph_decode_32(p);
+
+		err = __insert_pg_mapping(pg, &map->pg_temp);
+		if (err)
+			goto bad;
+		dout(" added pg_temp %llx len %d\n", *(u64 *)&pgid, len);
+	}
+
+	/* crush */
+	ceph_decode_32_safe(p, end, len, bad);
+	dout("osdmap_decode crush len %d from off 0x%x\n", len,
+	     (int)(*p - start));
+	ceph_decode_need(p, end, len, bad);
+	map->crush = crush_decode(*p, end);
+	*p += len;
+	if (IS_ERR(map->crush)) {
+		err = PTR_ERR(map->crush);
+		map->crush = NULL;
+		goto bad;
+	}
+
+	/* ignore the rest of the map */
+	*p = end;
+
+	dout("osdmap_decode done %p %p\n", *p, end);
+	return map;
+
+bad:
+	dout("osdmap_decode fail\n");
+	ceph_osdmap_destroy(map);
+	return ERR_PTR(err);
+}
+
+/*
+ * decode and apply an incremental map update.
+ */
+struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end,
+					     struct ceph_osdmap *map,
+					     struct ceph_messenger *msgr)
+{
+	struct crush_map *newcrush = NULL;
+	struct ceph_fsid fsid;
+	u32 epoch = 0;
+	struct ceph_timespec modified;
+	u32 len, pool;
+	__s32 new_pool_max, new_flags, max;
+	void *start = *p;
+	int err = -EINVAL;
+	u16 version;
+	struct rb_node *rbp;
+
+	ceph_decode_16_safe(p, end, version, bad);
+	if (version > CEPH_OSDMAP_INC_VERSION) {
+		pr_warning("got unknown v %d > %d of inc osdmap\n", version,
+			   CEPH_OSDMAP_INC_VERSION);
+		goto bad;
+	}
+
+	ceph_decode_need(p, end, sizeof(fsid)+sizeof(modified)+2*sizeof(u32),
+			 bad);
+	ceph_decode_copy(p, &fsid, sizeof(fsid));
+	epoch = ceph_decode_32(p);
+	BUG_ON(epoch != map->epoch+1);
+	ceph_decode_copy(p, &modified, sizeof(modified));
+	new_pool_max = ceph_decode_32(p);
+	new_flags = ceph_decode_32(p);
+
+	/* full map? */
+	ceph_decode_32_safe(p, end, len, bad);
+	if (len > 0) {
+		dout("apply_incremental full map len %d, %p to %p\n",
+		     len, *p, end);
+		return osdmap_decode(p, min(*p+len, end));
+	}
+
+	/* new crush? */
+	ceph_decode_32_safe(p, end, len, bad);
+	if (len > 0) {
+		dout("apply_incremental new crush map len %d, %p to %p\n",
+		     len, *p, end);
+		newcrush = crush_decode(*p, min(*p+len, end));
+		if (IS_ERR(newcrush))
+			return ERR_CAST(newcrush);
+		*p += len;
+	}
+
+	/* new flags? */
+	if (new_flags >= 0)
+		map->flags = new_flags;
+	if (new_pool_max >= 0)
+		map->pool_max = new_pool_max;
+
+	ceph_decode_need(p, end, 5*sizeof(u32), bad);
+
+	/* new max? */
+	max = ceph_decode_32(p);
+	if (max >= 0) {
+		err = osdmap_set_max_osd(map, max);
+		if (err < 0)
+			goto bad;
+	}
+
+	map->epoch++;
+	map->modified = map->modified;
+	if (newcrush) {
+		if (map->crush)
+			crush_destroy(map->crush);
+		map->crush = newcrush;
+		newcrush = NULL;
+	}
+
+	/* new_pool */
+	ceph_decode_32_safe(p, end, len, bad);
+	while (len--) {
+		__u8 ev;
+		struct ceph_pg_pool_info *pi;
+
+		ceph_decode_32_safe(p, end, pool, bad);
+		ceph_decode_need(p, end, 1 + sizeof(pi->v), bad);
+		ev = ceph_decode_8(p);  /* encoding version */
+		if (ev > CEPH_PG_POOL_VERSION) {
+			pr_warning("got unknown v %d > %d of ceph_pg_pool\n",
+				   ev, CEPH_PG_POOL_VERSION);
+			goto bad;
+		}
+		pi = __lookup_pg_pool(&map->pg_pools, pool);
+		if (!pi) {
+			pi = kzalloc(sizeof(*pi), GFP_NOFS);
+			if (!pi) {
+				err = -ENOMEM;
+				goto bad;
+			}
+			pi->id = pool;
+			__insert_pg_pool(&map->pg_pools, pi);
+		}
+		err = __decode_pool(p, end, pi);
+		if (err < 0)
+			goto bad;
+	}
+	if (version >= 5 && __decode_pool_names(p, end, map) < 0)
+		goto bad;
+
+	/* old_pool */
+	ceph_decode_32_safe(p, end, len, bad);
+	while (len--) {
+		struct ceph_pg_pool_info *pi;
+
+		ceph_decode_32_safe(p, end, pool, bad);
+		pi = __lookup_pg_pool(&map->pg_pools, pool);
+		if (pi)
+			__remove_pg_pool(&map->pg_pools, pi);
+	}
+
+	/* new_up */
+	err = -EINVAL;
+	ceph_decode_32_safe(p, end, len, bad);
+	while (len--) {
+		u32 osd;
+		struct ceph_entity_addr addr;
+		ceph_decode_32_safe(p, end, osd, bad);
+		ceph_decode_copy_safe(p, end, &addr, sizeof(addr), bad);
+		ceph_decode_addr(&addr);
+		pr_info("osd%d up\n", osd);
+		BUG_ON(osd >= map->max_osd);
+		map->osd_state[osd] |= CEPH_OSD_UP;
+		map->osd_addr[osd] = addr;
+	}
+
+	/* new_down */
+	ceph_decode_32_safe(p, end, len, bad);
+	while (len--) {
+		u32 osd;
+		ceph_decode_32_safe(p, end, osd, bad);
+		(*p)++;  /* clean flag */
+		pr_info("osd%d down\n", osd);
+		if (osd < map->max_osd)
+			map->osd_state[osd] &= ~CEPH_OSD_UP;
+	}
+
+	/* new_weight */
+	ceph_decode_32_safe(p, end, len, bad);
+	while (len--) {
+		u32 osd, off;
+		ceph_decode_need(p, end, sizeof(u32)*2, bad);
+		osd = ceph_decode_32(p);
+		off = ceph_decode_32(p);
+		pr_info("osd%d weight 0x%x %s\n", osd, off,
+		     off == CEPH_OSD_IN ? "(in)" :
+		     (off == CEPH_OSD_OUT ? "(out)" : ""));
+		if (osd < map->max_osd)
+			map->osd_weight[osd] = off;
+	}
+
+	/* new_pg_temp */
+	rbp = rb_first(&map->pg_temp);
+	ceph_decode_32_safe(p, end, len, bad);
+	while (len--) {
+		struct ceph_pg_mapping *pg;
+		int j;
+		struct ceph_pg pgid;
+		u32 pglen;
+		ceph_decode_need(p, end, sizeof(u64) + sizeof(u32), bad);
+		ceph_decode_copy(p, &pgid, sizeof(pgid));
+		pglen = ceph_decode_32(p);
+
+		/* remove any? */
+		while (rbp && pgid_cmp(rb_entry(rbp, struct ceph_pg_mapping,
+						node)->pgid, pgid) <= 0) {
+			struct ceph_pg_mapping *cur =
+				rb_entry(rbp, struct ceph_pg_mapping, node);
+
+			rbp = rb_next(rbp);
+			dout(" removed pg_temp %llx\n", *(u64 *)&cur->pgid);
+			rb_erase(&cur->node, &map->pg_temp);
+			kfree(cur);
+		}
+
+		if (pglen) {
+			/* insert */
+			ceph_decode_need(p, end, pglen*sizeof(u32), bad);
+			pg = kmalloc(sizeof(*pg) + sizeof(u32)*pglen, GFP_NOFS);
+			if (!pg) {
+				err = -ENOMEM;
+				goto bad;
+			}
+			pg->pgid = pgid;
+			pg->len = pglen;
+			for (j = 0; j < pglen; j++)
+				pg->osds[j] = ceph_decode_32(p);
+			err = __insert_pg_mapping(pg, &map->pg_temp);
+			if (err) {
+				kfree(pg);
+				goto bad;
+			}
+			dout(" added pg_temp %llx len %d\n", *(u64 *)&pgid,
+			     pglen);
+		}
+	}
+	while (rbp) {
+		struct ceph_pg_mapping *cur =
+			rb_entry(rbp, struct ceph_pg_mapping, node);
+
+		rbp = rb_next(rbp);
+		dout(" removed pg_temp %llx\n", *(u64 *)&cur->pgid);
+		rb_erase(&cur->node, &map->pg_temp);
+		kfree(cur);
+	}
+
+	/* ignore the rest */
+	*p = end;
+	return map;
+
+bad:
+	pr_err("corrupt inc osdmap epoch %d off %d (%p of %p-%p)\n",
+	       epoch, (int)(*p - start), *p, start, end);
+	print_hex_dump(KERN_DEBUG, "osdmap: ",
+		       DUMP_PREFIX_OFFSET, 16, 1,
+		       start, end - start, true);
+	if (newcrush)
+		crush_destroy(newcrush);
+	return ERR_PTR(err);
+}
+
+
+
+
+/*
+ * calculate file layout from given offset, length.
+ * fill in correct oid, logical length, and object extent
+ * offset, length.
+ *
+ * for now, we write only a single su, until we can
+ * pass a stride back to the caller.
+ */
+void ceph_calc_file_object_mapping(struct ceph_file_layout *layout,
+				   u64 off, u64 *plen,
+				   u64 *ono,
+				   u64 *oxoff, u64 *oxlen)
+{
+	u32 osize = le32_to_cpu(layout->fl_object_size);
+	u32 su = le32_to_cpu(layout->fl_stripe_unit);
+	u32 sc = le32_to_cpu(layout->fl_stripe_count);
+	u32 bl, stripeno, stripepos, objsetno;
+	u32 su_per_object;
+	u64 t, su_offset;
+
+	dout("mapping %llu~%llu  osize %u fl_su %u\n", off, *plen,
+	     osize, su);
+	su_per_object = osize / su;
+	dout("osize %u / su %u = su_per_object %u\n", osize, su,
+	     su_per_object);
+
+	BUG_ON((su & ~PAGE_MASK) != 0);
+	/* bl = *off / su; */
+	t = off;
+	do_div(t, su);
+	bl = t;
+	dout("off %llu / su %u = bl %u\n", off, su, bl);
+
+	stripeno = bl / sc;
+	stripepos = bl % sc;
+	objsetno = stripeno / su_per_object;
+
+	*ono = objsetno * sc + stripepos;
+	dout("objset %u * sc %u = ono %u\n", objsetno, sc, (unsigned)*ono);
+
+	/* *oxoff = *off % layout->fl_stripe_unit;  # offset in su */
+	t = off;
+	su_offset = do_div(t, su);
+	*oxoff = su_offset + (stripeno % su_per_object) * su;
+
+	/*
+	 * Calculate the length of the extent being written to the selected
+	 * object. This is the minimum of the full length requested (plen) or
+	 * the remainder of the current stripe being written to.
+	 */
+	*oxlen = min_t(u64, *plen, su - su_offset);
+	*plen = *oxlen;
+
+	dout(" obj extent %llu~%llu\n", *oxoff, *oxlen);
+}
+EXPORT_SYMBOL(ceph_calc_file_object_mapping);
+
+/*
+ * calculate an object layout (i.e. pgid) from an oid,
+ * file_layout, and osdmap
+ */
+int ceph_calc_object_layout(struct ceph_object_layout *ol,
+			    const char *oid,
+			    struct ceph_file_layout *fl,
+			    struct ceph_osdmap *osdmap)
+{
+	unsigned num, num_mask;
+	struct ceph_pg pgid;
+	s32 preferred = (s32)le32_to_cpu(fl->fl_pg_preferred);
+	int poolid = le32_to_cpu(fl->fl_pg_pool);
+	struct ceph_pg_pool_info *pool;
+	unsigned ps;
+
+	BUG_ON(!osdmap);
+
+	pool = __lookup_pg_pool(&osdmap->pg_pools, poolid);
+	if (!pool)
+		return -EIO;
+	ps = ceph_str_hash(pool->v.object_hash, oid, strlen(oid));
+	if (preferred >= 0) {
+		ps += preferred;
+		num = le32_to_cpu(pool->v.lpg_num);
+		num_mask = pool->lpg_num_mask;
+	} else {
+		num = le32_to_cpu(pool->v.pg_num);
+		num_mask = pool->pg_num_mask;
+	}
+
+	pgid.ps = cpu_to_le16(ps);
+	pgid.preferred = cpu_to_le16(preferred);
+	pgid.pool = fl->fl_pg_pool;
+	if (preferred >= 0)
+		dout("calc_object_layout '%s' pgid %d.%xp%d\n", oid, poolid, ps,
+		     (int)preferred);
+	else
+		dout("calc_object_layout '%s' pgid %d.%x\n", oid, poolid, ps);
+
+	ol->ol_pgid = pgid;
+	ol->ol_stripe_unit = fl->fl_object_stripe_unit;
+	return 0;
+}
+EXPORT_SYMBOL(ceph_calc_object_layout);
+
+/*
+ * Calculate raw osd vector for the given pgid.  Return pointer to osd
+ * array, or NULL on failure.
+ */
+static int *calc_pg_raw(struct ceph_osdmap *osdmap, struct ceph_pg pgid,
+			int *osds, int *num)
+{
+	struct ceph_pg_mapping *pg;
+	struct ceph_pg_pool_info *pool;
+	int ruleno;
+	unsigned poolid, ps, pps;
+	int preferred;
+
+	/* pg_temp? */
+	pg = __lookup_pg_mapping(&osdmap->pg_temp, pgid);
+	if (pg) {
+		*num = pg->len;
+		return pg->osds;
+	}
+
+	/* crush */
+	poolid = le32_to_cpu(pgid.pool);
+	ps = le16_to_cpu(pgid.ps);
+	preferred = (s16)le16_to_cpu(pgid.preferred);
+
+	/* don't forcefeed bad device ids to crush */
+	if (preferred >= osdmap->max_osd ||
+	    preferred >= osdmap->crush->max_devices)
+		preferred = -1;
+
+	pool = __lookup_pg_pool(&osdmap->pg_pools, poolid);
+	if (!pool)
+		return NULL;
+	ruleno = crush_find_rule(osdmap->crush, pool->v.crush_ruleset,
+				 pool->v.type, pool->v.size);
+	if (ruleno < 0) {
+		pr_err("no crush rule pool %d ruleset %d type %d size %d\n",
+		       poolid, pool->v.crush_ruleset, pool->v.type,
+		       pool->v.size);
+		return NULL;
+	}
+
+	if (preferred >= 0)
+		pps = ceph_stable_mod(ps,
+				      le32_to_cpu(pool->v.lpgp_num),
+				      pool->lpgp_num_mask);
+	else
+		pps = ceph_stable_mod(ps,
+				      le32_to_cpu(pool->v.pgp_num),
+				      pool->pgp_num_mask);
+	pps += poolid;
+	*num = crush_do_rule(osdmap->crush, ruleno, pps, osds,
+			     min_t(int, pool->v.size, *num),
+			     preferred, osdmap->osd_weight);
+	return osds;
+}
+
+/*
+ * Return acting set for given pgid.
+ */
+int ceph_calc_pg_acting(struct ceph_osdmap *osdmap, struct ceph_pg pgid,
+			int *acting)
+{
+	int rawosds[CEPH_PG_MAX_SIZE], *osds;
+	int i, o, num = CEPH_PG_MAX_SIZE;
+
+	osds = calc_pg_raw(osdmap, pgid, rawosds, &num);
+	if (!osds)
+		return -1;
+
+	/* primary is first up osd */
+	o = 0;
+	for (i = 0; i < num; i++)
+		if (ceph_osd_is_up(osdmap, osds[i]))
+			acting[o++] = osds[i];
+	return o;
+}
+
+/*
+ * Return primary osd for given pgid, or -1 if none.
+ */
+int ceph_calc_pg_primary(struct ceph_osdmap *osdmap, struct ceph_pg pgid)
+{
+	int rawosds[CEPH_PG_MAX_SIZE], *osds;
+	int i, num = CEPH_PG_MAX_SIZE;
+
+	osds = calc_pg_raw(osdmap, pgid, rawosds, &num);
+	if (!osds)
+		return -1;
+
+	/* primary is first up osd */
+	for (i = 0; i < num; i++)
+		if (ceph_osd_is_up(osdmap, osds[i]))
+			return osds[i];
+	return -1;
+}
+EXPORT_SYMBOL(ceph_calc_pg_primary);
diff --git a/net/ceph/pagelist.c b/net/ceph/pagelist.c
new file mode 100644
index 00000000000..13cb409a7bb
--- /dev/null
+++ b/net/ceph/pagelist.c
@@ -0,0 +1,154 @@
+
+#include <linux/module.h>
+#include <linux/gfp.h>
+#include <linux/pagemap.h>
+#include <linux/highmem.h>
+#include <linux/ceph/pagelist.h>
+
+static void ceph_pagelist_unmap_tail(struct ceph_pagelist *pl)
+{
+	if (pl->mapped_tail) {
+		struct page *page = list_entry(pl->head.prev, struct page, lru);
+		kunmap(page);
+		pl->mapped_tail = NULL;
+	}
+}
+
+int ceph_pagelist_release(struct ceph_pagelist *pl)
+{
+	ceph_pagelist_unmap_tail(pl);
+	while (!list_empty(&pl->head)) {
+		struct page *page = list_first_entry(&pl->head, struct page,
+						     lru);
+		list_del(&page->lru);
+		__free_page(page);
+	}
+	ceph_pagelist_free_reserve(pl);
+	return 0;
+}
+EXPORT_SYMBOL(ceph_pagelist_release);
+
+static int ceph_pagelist_addpage(struct ceph_pagelist *pl)
+{
+	struct page *page;
+
+	if (!pl->num_pages_free) {
+		page = __page_cache_alloc(GFP_NOFS);
+	} else {
+		page = list_first_entry(&pl->free_list, struct page, lru);
+		list_del(&page->lru);
+		--pl->num_pages_free;
+	}
+	if (!page)
+		return -ENOMEM;
+	pl->room += PAGE_SIZE;
+	ceph_pagelist_unmap_tail(pl);
+	list_add_tail(&page->lru, &pl->head);
+	pl->mapped_tail = kmap(page);
+	return 0;
+}
+
+int ceph_pagelist_append(struct ceph_pagelist *pl, const 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;
+}
+EXPORT_SYMBOL(ceph_pagelist_append);
+
+/**
+ * Allocate enough pages for a pagelist to append the given amount
+ * of data without without allocating.
+ * Returns: 0 on success, -ENOMEM on error.
+ */
+int ceph_pagelist_reserve(struct ceph_pagelist *pl, size_t space)
+{
+	if (space <= pl->room)
+		return 0;
+	space -= pl->room;
+	space = (space + PAGE_SIZE - 1) >> PAGE_SHIFT;   /* conv to num pages */
+
+	while (space > pl->num_pages_free) {
+		struct page *page = __page_cache_alloc(GFP_NOFS);
+		if (!page)
+			return -ENOMEM;
+		list_add_tail(&page->lru, &pl->free_list);
+		++pl->num_pages_free;
+	}
+	return 0;
+}
+EXPORT_SYMBOL(ceph_pagelist_reserve);
+
+/**
+ * Free any pages that have been preallocated.
+ */
+int ceph_pagelist_free_reserve(struct ceph_pagelist *pl)
+{
+	while (!list_empty(&pl->free_list)) {
+		struct page *page = list_first_entry(&pl->free_list,
+						     struct page, lru);
+		list_del(&page->lru);
+		__free_page(page);
+		--pl->num_pages_free;
+	}
+	BUG_ON(pl->num_pages_free);
+	return 0;
+}
+EXPORT_SYMBOL(ceph_pagelist_free_reserve);
+
+/**
+ * Create a truncation point.
+ */
+void ceph_pagelist_set_cursor(struct ceph_pagelist *pl,
+			      struct ceph_pagelist_cursor *c)
+{
+	c->pl = pl;
+	c->page_lru = pl->head.prev;
+	c->room = pl->room;
+}
+EXPORT_SYMBOL(ceph_pagelist_set_cursor);
+
+/**
+ * Truncate a pagelist to the given point. Move extra pages to reserve.
+ * This won't sleep.
+ * Returns: 0 on success,
+ *          -EINVAL if the pagelist doesn't match the trunc point pagelist
+ */
+int ceph_pagelist_truncate(struct ceph_pagelist *pl,
+			   struct ceph_pagelist_cursor *c)
+{
+	struct page *page;
+
+	if (pl != c->pl)
+		return -EINVAL;
+	ceph_pagelist_unmap_tail(pl);
+	while (pl->head.prev != c->page_lru) {
+		page = list_entry(pl->head.prev, struct page, lru);
+		list_del(&page->lru);                /* remove from pagelist */
+		list_add_tail(&page->lru, &pl->free_list); /* add to reserve */
+		++pl->num_pages_free;
+	}
+	pl->room = c->room;
+	if (!list_empty(&pl->head)) {
+		page = list_entry(pl->head.prev, struct page, lru);
+		pl->mapped_tail = kmap(page);
+	}
+	return 0;
+}
+EXPORT_SYMBOL(ceph_pagelist_truncate);
diff --git a/net/ceph/pagevec.c b/net/ceph/pagevec.c
new file mode 100644
index 00000000000..54caf068715
--- /dev/null
+++ b/net/ceph/pagevec.c
@@ -0,0 +1,223 @@
+#include <linux/ceph/ceph_debug.h>
+
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/file.h>
+#include <linux/namei.h>
+#include <linux/writeback.h>
+
+#include <linux/ceph/libceph.h>
+
+/*
+ * build a vector of user pages
+ */
+struct page **ceph_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);
+}
+EXPORT_SYMBOL(ceph_get_direct_page_vector);
+
+void ceph_put_page_vector(struct page **pages, int num_pages)
+{
+	int i;
+
+	for (i = 0; i < num_pages; i++)
+		put_page(pages[i]);
+	kfree(pages);
+}
+EXPORT_SYMBOL(ceph_put_page_vector);
+
+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);
+}
+EXPORT_SYMBOL(ceph_release_page_vector);
+
+/*
+ * allocate a vector new pages
+ */
+struct page **ceph_alloc_page_vector(int num_pages, gfp_t flags)
+{
+	struct page **pages;
+	int i;
+
+	pages = kmalloc(sizeof(*pages) * num_pages, flags);
+	if (!pages)
+		return ERR_PTR(-ENOMEM);
+	for (i = 0; i < num_pages; i++) {
+		pages[i] = __page_cache_alloc(flags);
+		if (pages[i] == NULL) {
+			ceph_release_page_vector(pages, i);
+			return ERR_PTR(-ENOMEM);
+		}
+	}
+	return pages;
+}
+EXPORT_SYMBOL(ceph_alloc_page_vector);
+
+/*
+ * copy user data into a page vector
+ */
+int ceph_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;
+}
+EXPORT_SYMBOL(ceph_copy_user_to_page_vector);
+
+int ceph_copy_to_page_vector(struct page **pages,
+				    const char *data,
+				    loff_t off, size_t len)
+{
+	int i = 0;
+	size_t po = off & ~PAGE_CACHE_MASK;
+	size_t left = len;
+	size_t l;
+
+	while (left > 0) {
+		l = min_t(size_t, PAGE_CACHE_SIZE-po, left);
+		memcpy(page_address(pages[i]) + po, data, l);
+		data += l;
+		left -= l;
+		po += l;
+		if (po == PAGE_CACHE_SIZE) {
+			po = 0;
+			i++;
+		}
+	}
+	return len;
+}
+EXPORT_SYMBOL(ceph_copy_to_page_vector);
+
+int ceph_copy_from_page_vector(struct page **pages,
+				    char *data,
+				    loff_t off, size_t len)
+{
+	int i = 0;
+	size_t po = off & ~PAGE_CACHE_MASK;
+	size_t left = len;
+	size_t l;
+
+	while (left > 0) {
+		l = min_t(size_t, PAGE_CACHE_SIZE-po, left);
+		memcpy(data, page_address(pages[i]) + po, l);
+		data += l;
+		left -= l;
+		po += l;
+		if (po == PAGE_CACHE_SIZE) {
+			po = 0;
+			i++;
+		}
+	}
+	return len;
+}
+EXPORT_SYMBOL(ceph_copy_from_page_vector);
+
+/*
+ * copy user data from a page vector into a user pointer
+ */
+int ceph_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;
+}
+EXPORT_SYMBOL(ceph_copy_page_vector_to_user);
+
+/*
+ * Zero an extent within a page vector.  Offset is relative to the
+ * start of the first page.
+ */
+void ceph_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);
+	}
+}
+EXPORT_SYMBOL(ceph_zero_page_vector_range);
+