Commit cc8362b1 authored by Linus Torvalds's avatar Linus Torvalds
Browse files

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

Pull Ceph changes from Sage Weil:
 "Lots of stuff this time around:

   - lots of cleanup and refactoring in the libceph messenger code, and
     many hard to hit races and bugs closed as a result.
   - lots of cleanup and refactoring in the rbd code from Alex Elder,
     mostly in preparation for the layering functionality that will be
     coming in 3.7.
   - some misc rbd cleanups from Josh Durgin that are finally going
     upstream
   - support for CRUSH tunables (used by newer clusters to improve the
     data placement)
   - some cleanup in our use of d_parent that Al brought up a while back
   - a random collection of fixes across the tree

  There is another patch coming that fixes up our ->atomic_open()
  behavior, but I'm going to hammer on it a bit more before sending it."

Fix up conflicts due to commits that were already committed earlier in
drivers/block/rbd.c, net/ceph/{messenger.c, osd_client.c}

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client: (132 commits)
  rbd: create rbd_refresh_helper()
  rbd: return obj version in __rbd_refresh_header()
  rbd: fixes in rbd_header_from_disk()
  rbd: always pass ops array to rbd_req_sync_op()
  rbd: pass null version pointer in add_snap()
  rbd: make rbd_create_rw_ops() return a pointer
  rbd: have __rbd_add_snap_dev() return a pointer
  libceph: recheck con state after allocating incoming message
  libceph: change ceph_con_in_msg_alloc convention to be less weird
  libceph: avoid dropping con mutex before fault
  libceph: verify state after retaking con lock after dispatch
  libceph: revoke mon_client messages on session restart
  libceph: fix handling of immediate socket connect failure
  ceph: update MAINTAINERS file
  libceph: be less chatty about stray replies
  libceph: clear all flags on con_close
  libceph: clean up con flags
  libceph: replace connection state bits with states
  libceph: drop unnecessary CLOSED check in socket state change callback
  libceph: close socket directly from ceph_con_close()
  ...
parents 2e3ee613 1fe5e993
......@@ -35,8 +35,14 @@ name
pool
The pool where this rbd image resides. The pool-name pair is unique
per rados system.
The name of the storage pool where this rbd image resides.
An rbd image name is unique within its pool.
pool_id
The unique identifier for the rbd image's pool. This is
a permanent attribute of the pool. A pool's id will never
change.
size
......
......@@ -1789,15 +1789,16 @@ F: arch/powerpc/oprofile/*cell*
F: arch/powerpc/platforms/cell/
CEPH DISTRIBUTED FILE SYSTEM CLIENT
M: Sage Weil <sage@newdream.net>
M: Sage Weil <sage@inktank.com>
L: ceph-devel@vger.kernel.org
W: http://ceph.newdream.net/
W: http://ceph.com/
T: git git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client.git
S: Supported
F: Documentation/filesystems/ceph.txt
F: fs/ceph
F: net/ceph
F: include/linux/ceph
F: include/linux/crush
CERTIFIED WIRELESS USB (WUSB) SUBSYSTEM:
L: linux-usb@vger.kernel.org
......@@ -5639,10 +5640,12 @@ S: Supported
F: arch/hexagon/
RADOS BLOCK DEVICE (RBD)
F: include/linux/qnxtypes.h
M: Yehuda Sadeh <yehuda@hq.newdream.net>
M: Sage Weil <sage@newdream.net>
M: Yehuda Sadeh <yehuda@inktank.com>
M: Sage Weil <sage@inktank.com>
M: Alex Elder <elder@inktank.com>
M: ceph-devel@vger.kernel.org
W: http://ceph.com/
T: git git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client.git
S: Supported
F: drivers/block/rbd.c
F: drivers/block/rbd_types.h
......
This diff is collapsed.
......@@ -31,7 +31,6 @@
#define RBD_MIN_OBJ_ORDER 16
#define RBD_MAX_OBJ_ORDER 30
#define RBD_MAX_OBJ_NAME_LEN 96
#define RBD_MAX_SEG_NAME_LEN 128
#define RBD_COMP_NONE 0
......
......@@ -51,8 +51,7 @@ int ceph_init_dentry(struct dentry *dentry)
goto out_unlock;
}
if (dentry->d_parent == NULL || /* nfs fh_to_dentry */
ceph_snap(dentry->d_parent->d_inode) == CEPH_NOSNAP)
if (ceph_snap(dentry->d_parent->d_inode) == CEPH_NOSNAP)
d_set_d_op(dentry, &ceph_dentry_ops);
else if (ceph_snap(dentry->d_parent->d_inode) == CEPH_SNAPDIR)
d_set_d_op(dentry, &ceph_snapdir_dentry_ops);
......@@ -79,7 +78,7 @@ struct inode *ceph_get_dentry_parent_inode(struct dentry *dentry)
return NULL;
spin_lock(&dentry->d_lock);
if (dentry->d_parent) {
if (!IS_ROOT(dentry)) {
inode = dentry->d_parent->d_inode;
ihold(inode);
}
......@@ -1154,7 +1153,7 @@ static void ceph_d_prune(struct dentry *dentry)
dout("ceph_d_prune %p\n", dentry);
/* do we have a valid parent? */
if (!dentry->d_parent || IS_ROOT(dentry))
if (IS_ROOT(dentry))
return;
/* if we are not hashed, we don't affect D_COMPLETE */
......
......@@ -10,6 +10,7 @@
#include "super.h"
#include "mds_client.h"
#include <linux/ceph/ceph_features.h>
#include <linux/ceph/messenger.h>
#include <linux/ceph/decode.h>
#include <linux/ceph/pagelist.h>
......@@ -394,11 +395,7 @@ static struct ceph_mds_session *register_session(struct ceph_mds_client *mdsc,
s->s_seq = 0;
mutex_init(&s->s_mutex);
ceph_con_init(mdsc->fsc->client->msgr, &s->s_con);
s->s_con.private = s;
s->s_con.ops = &mds_con_ops;
s->s_con.peer_name.type = CEPH_ENTITY_TYPE_MDS;
s->s_con.peer_name.num = cpu_to_le64(mds);
ceph_con_init(&s->s_con, s, &mds_con_ops, &mdsc->fsc->client->msgr);
spin_lock_init(&s->s_gen_ttl_lock);
s->s_cap_gen = 0;
......@@ -440,7 +437,8 @@ static struct ceph_mds_session *register_session(struct ceph_mds_client *mdsc,
mdsc->sessions[mds] = s;
atomic_inc(&s->s_ref); /* one ref to sessions[], one to caller */
ceph_con_open(&s->s_con, ceph_mdsmap_get_addr(mdsc->mdsmap, mds));
ceph_con_open(&s->s_con, CEPH_ENTITY_TYPE_MDS, mds,
ceph_mdsmap_get_addr(mdsc->mdsmap, mds));
return s;
......@@ -1472,11 +1470,6 @@ retry:
else
len += 1 + temp->d_name.len;
temp = temp->d_parent;
if (temp == NULL) {
rcu_read_unlock();
pr_err("build_path corrupt dentry %p\n", dentry);
return ERR_PTR(-EINVAL);
}
}
rcu_read_unlock();
if (len)
......@@ -1513,12 +1506,6 @@ retry:
if (pos)
path[--pos] = '/';
temp = temp->d_parent;
if (temp == NULL) {
rcu_read_unlock();
pr_err("build_path corrupt dentry\n");
kfree(path);
return ERR_PTR(-EINVAL);
}
}
rcu_read_unlock();
if (pos != 0 || read_seqretry(&rename_lock, seq)) {
......@@ -2531,7 +2518,9 @@ static void send_mds_reconnect(struct ceph_mds_client *mdsc,
session->s_state = CEPH_MDS_SESSION_RECONNECTING;
session->s_seq = 0;
ceph_con_close(&session->s_con);
ceph_con_open(&session->s_con,
CEPH_ENTITY_TYPE_MDS, mds,
ceph_mdsmap_get_addr(mdsc->mdsmap, mds));
/* replay unsafe requests */
......
......@@ -296,8 +296,7 @@ static int build_snap_context(struct ceph_snap_realm *realm)
struct ceph_snap_realm *parent = realm->parent;
struct ceph_snap_context *snapc;
int err = 0;
int i;
int num = realm->num_prior_parent_snaps + realm->num_snaps;
u32 num = realm->num_prior_parent_snaps + realm->num_snaps;
/*
* build parent context, if it hasn't been built.
......@@ -321,11 +320,11 @@ static int build_snap_context(struct ceph_snap_realm *realm)
realm->cached_context->seq == realm->seq &&
(!parent ||
realm->cached_context->seq >= parent->cached_context->seq)) {
dout("build_snap_context %llx %p: %p seq %lld (%d snaps)"
dout("build_snap_context %llx %p: %p seq %lld (%u snaps)"
" (unchanged)\n",
realm->ino, realm, realm->cached_context,
realm->cached_context->seq,
realm->cached_context->num_snaps);
(unsigned int) realm->cached_context->num_snaps);
return 0;
}
......@@ -342,6 +341,8 @@ static int build_snap_context(struct ceph_snap_realm *realm)
num = 0;
snapc->seq = realm->seq;
if (parent) {
u32 i;
/* include any of parent's snaps occurring _after_ my
parent became my parent */
for (i = 0; i < parent->cached_context->num_snaps; i++)
......@@ -361,8 +362,9 @@ static int build_snap_context(struct ceph_snap_realm *realm)
sort(snapc->snaps, num, sizeof(u64), cmpu64_rev, NULL);
snapc->num_snaps = num;
dout("build_snap_context %llx %p: %p seq %lld (%d snaps)\n",
realm->ino, realm, snapc, snapc->seq, snapc->num_snaps);
dout("build_snap_context %llx %p: %p seq %lld (%u snaps)\n",
realm->ino, realm, snapc, snapc->seq,
(unsigned int) snapc->num_snaps);
if (realm->cached_context)
ceph_put_snap_context(realm->cached_context);
......@@ -402,9 +404,9 @@ static void rebuild_snap_realms(struct ceph_snap_realm *realm)
* helper to allocate and decode an array of snapids. free prior
* instance, if any.
*/
static int dup_array(u64 **dst, __le64 *src, int num)
static int dup_array(u64 **dst, __le64 *src, u32 num)
{
int i;
u32 i;
kfree(*dst);
if (num) {
......
......@@ -18,6 +18,7 @@
#include "super.h"
#include "mds_client.h"
#include <linux/ceph/ceph_features.h>
#include <linux/ceph/decode.h>
#include <linux/ceph/mon_client.h>
#include <linux/ceph/auth.h>
......
......@@ -612,9 +612,9 @@ struct ceph_snap_realm {
u64 parent_since; /* snapid when our current parent became so */
u64 *prior_parent_snaps; /* snaps inherited from any parents we */
int num_prior_parent_snaps; /* had prior to parent_since */
u32 num_prior_parent_snaps; /* had prior to parent_since */
u64 *snaps; /* snaps specific to this realm */
int num_snaps;
u32 num_snaps;
struct ceph_snap_realm *parent;
struct list_head children; /* list of child realms */
......
......@@ -457,6 +457,7 @@ start:
for (i = 0; i < numattr; i++)
kfree(xattrs[i]);
kfree(xattrs);
xattrs = NULL;
goto start;
}
err = -EIO;
......
#ifndef __CEPH_FEATURES
#define __CEPH_FEATURES
/*
* feature bits
*/
#define CEPH_FEATURE_UID (1<<0)
#define CEPH_FEATURE_NOSRCADDR (1<<1)
#define CEPH_FEATURE_MONCLOCKCHECK (1<<2)
#define CEPH_FEATURE_FLOCK (1<<3)
#define CEPH_FEATURE_SUBSCRIBE2 (1<<4)
#define CEPH_FEATURE_MONNAMES (1<<5)
#define CEPH_FEATURE_RECONNECT_SEQ (1<<6)
#define CEPH_FEATURE_DIRLAYOUTHASH (1<<7)
/* bits 8-17 defined by user-space; not supported yet here */
#define CEPH_FEATURE_CRUSH_TUNABLES (1<<18)
/*
* Features supported.
*/
#define CEPH_FEATURES_SUPPORTED_DEFAULT \
(CEPH_FEATURE_NOSRCADDR | \
CEPH_FEATURE_CRUSH_TUNABLES)
#define CEPH_FEATURES_REQUIRED_DEFAULT \
(CEPH_FEATURE_NOSRCADDR)
#endif
......@@ -35,20 +35,6 @@
/* arbitrary limit on max # of monitors (cluster of 3 is typical) */
#define CEPH_MAX_MON 31
/*
* feature bits
*/
#define CEPH_FEATURE_UID (1<<0)
#define CEPH_FEATURE_NOSRCADDR (1<<1)
#define CEPH_FEATURE_MONCLOCKCHECK (1<<2)
#define CEPH_FEATURE_FLOCK (1<<3)
#define CEPH_FEATURE_SUBSCRIBE2 (1<<4)
#define CEPH_FEATURE_MONNAMES (1<<5)
#define CEPH_FEATURE_RECONNECT_SEQ (1<<6)
#define CEPH_FEATURE_DIRLAYOUTHASH (1<<7)
/*
* ceph_file_layout - describe data layout for a file/inode
*/
......
#ifndef __CEPH_DECODE_H
#define __CEPH_DECODE_H
#include <linux/err.h>
#include <linux/bug.h>
#include <linux/time.h>
#include <asm/unaligned.h>
......@@ -84,6 +85,52 @@ static inline int ceph_has_room(void **p, void *end, size_t n)
ceph_decode_copy(p, pv, n); \
} while (0)
/*
* Allocate a buffer big enough to hold the wire-encoded string, and
* decode the string into it. The resulting string will always be
* terminated with '\0'. If successful, *p will be advanced
* past the decoded data. Also, if lenp is not a null pointer, the
* length (not including the terminating '\0') will be recorded in
* *lenp. Note that a zero-length string is a valid return value.
*
* Returns a pointer to the newly-allocated string buffer, or a
* pointer-coded errno if an error occurs. Neither *p nor *lenp
* will have been updated if an error is returned.
*
* There are two possible failures:
* - converting the string would require accessing memory at or
* beyond the "end" pointer provided (-E
* - memory could not be allocated for the result
*/
static inline char *ceph_extract_encoded_string(void **p, void *end,
size_t *lenp, gfp_t gfp)
{
u32 len;
void *sp = *p;
char *buf;
ceph_decode_32_safe(&sp, end, len, bad);
if (!ceph_has_room(&sp, end, len))
goto bad;
buf = kmalloc(len + 1, gfp);
if (!buf)
return ERR_PTR(-ENOMEM);
if (len)
memcpy(buf, sp, len);
buf[len] = '\0';
*p = (char *) *p + sizeof (u32) + len;
if (lenp)
*lenp = (size_t) len;
return buf;
bad:
return ERR_PTR(-ERANGE);
}
/*
* struct ceph_timespec <-> struct timespec
*/
......@@ -151,7 +198,7 @@ static inline void ceph_encode_filepath(void **p, void *end,
u64 ino, const char *path)
{
u32 len = path ? strlen(path) : 0;
BUG_ON(*p + sizeof(ino) + sizeof(len) + len > end);
BUG_ON(*p + 1 + sizeof(ino) + sizeof(len) + len > end);
ceph_encode_8(p, 1);
ceph_encode_64(p, ino);
ceph_encode_32(p, len);
......
......@@ -22,12 +22,6 @@
#include "osd_client.h"
#include "ceph_fs.h"
/*
* Supported features
*/
#define CEPH_FEATURE_SUPPORTED_DEFAULT CEPH_FEATURE_NOSRCADDR
#define CEPH_FEATURE_REQUIRED_DEFAULT CEPH_FEATURE_NOSRCADDR
/*
* mount options
*/
......@@ -132,7 +126,7 @@ struct ceph_client {
u32 supported_features;
u32 required_features;
struct ceph_messenger *msgr; /* messenger instance */
struct ceph_messenger msgr; /* messenger instance */
struct ceph_mon_client monc;
struct ceph_osd_client osdc;
......@@ -160,7 +154,7 @@ struct ceph_client {
struct ceph_snap_context {
atomic_t nref;
u64 seq;
int num_snaps;
u32 num_snaps;
u64 snaps[];
};
......
......@@ -31,9 +31,6 @@ struct ceph_connection_operations {
int (*verify_authorizer_reply) (struct ceph_connection *con, int len);
int (*invalidate_authorizer)(struct ceph_connection *con);
/* protocol version mismatch */
void (*bad_proto) (struct ceph_connection *con);
/* there was some error on the socket (disconnect, whatever) */
void (*fault) (struct ceph_connection *con);
......@@ -53,6 +50,7 @@ struct ceph_messenger {
struct ceph_entity_inst inst; /* my name+address */
struct ceph_entity_addr my_enc_addr;
atomic_t stopping;
bool nocrc;
/*
......@@ -80,7 +78,10 @@ struct ceph_msg {
unsigned nr_pages; /* size of page array */
unsigned page_alignment; /* io offset in first page */
struct ceph_pagelist *pagelist; /* instead of pages */
struct ceph_connection *con;
struct list_head list_head;
struct kref kref;
struct bio *bio; /* instead of pages/pagelist */
struct bio *bio_iter; /* bio iterator */
......@@ -105,23 +106,6 @@ struct ceph_msg_pos {
#define BASE_DELAY_INTERVAL (HZ/2)
#define MAX_DELAY_INTERVAL (5 * 60 * HZ)
/*
* ceph_connection state bit flags
*/
#define LOSSYTX 0 /* we can close channel or drop messages on errors */
#define CONNECTING 1
#define NEGOTIATING 2
#define KEEPALIVE_PENDING 3
#define WRITE_PENDING 4 /* we have data ready to send */
#define STANDBY 8 /* no outgoing messages, socket closed. we keep
* the ceph_connection around to maintain shared
* state with the peer. */
#define CLOSED 10 /* we've closed the connection */
#define SOCK_CLOSED 11 /* socket state changed to closed */
#define OPENING 13 /* open connection w/ (possibly new) peer */
#define DEAD 14 /* dead, about to kfree */
#define BACKOFF 15
/*
* A single connection with another host.
*
......@@ -131,18 +115,22 @@ struct ceph_msg_pos {
*/
struct ceph_connection {
void *private;
atomic_t nref;
const struct ceph_connection_operations *ops;
struct ceph_messenger *msgr;
atomic_t sock_state;
struct socket *sock;
unsigned long state; /* connection state (see flags above) */
struct ceph_entity_addr peer_addr; /* peer address */
struct ceph_entity_addr peer_addr_for_me;
unsigned long flags;
unsigned long state;
const char *error_msg; /* error message, if any */
struct ceph_entity_addr peer_addr; /* peer address */
struct ceph_entity_name peer_name; /* peer name */
struct ceph_entity_addr peer_addr_for_me;
unsigned peer_features;
u32 connect_seq; /* identify the most recent connection
attempt for this connection, client */
......@@ -207,24 +195,26 @@ extern int ceph_msgr_init(void);
extern void ceph_msgr_exit(void);
extern void ceph_msgr_flush(void);
extern struct ceph_messenger *ceph_messenger_create(
struct ceph_entity_addr *myaddr,
u32 features, u32 required);
extern void ceph_messenger_destroy(struct ceph_messenger *);
extern void ceph_messenger_init(struct ceph_messenger *msgr,
struct ceph_entity_addr *myaddr,
u32 supported_features,
u32 required_features,
bool nocrc);
extern void ceph_con_init(struct ceph_messenger *msgr,
struct ceph_connection *con);
extern void ceph_con_init(struct ceph_connection *con, void *private,
const struct ceph_connection_operations *ops,
struct ceph_messenger *msgr);
extern void ceph_con_open(struct ceph_connection *con,
__u8 entity_type, __u64 entity_num,
struct ceph_entity_addr *addr);
extern bool ceph_con_opened(struct ceph_connection *con);
extern void ceph_con_close(struct ceph_connection *con);
extern void ceph_con_send(struct ceph_connection *con, struct ceph_msg *msg);
extern void ceph_con_revoke(struct ceph_connection *con, struct ceph_msg *msg);
extern void ceph_con_revoke_message(struct ceph_connection *con,
struct ceph_msg *msg);
extern void ceph_msg_revoke(struct ceph_msg *msg);
extern void ceph_msg_revoke_incoming(struct ceph_msg *msg);
extern void ceph_con_keepalive(struct ceph_connection *con);
extern struct ceph_connection *ceph_con_get(struct ceph_connection *con);
extern void ceph_con_put(struct ceph_connection *con);
extern struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags,
bool can_fail);
......
......@@ -70,7 +70,7 @@ struct ceph_mon_client {
bool hunting;
int cur_mon; /* last monitor i contacted */
unsigned long sub_sent, sub_renew_after;
struct ceph_connection *con;
struct ceph_connection con;
bool have_fsid;
/* pending generic requests */
......
......@@ -11,10 +11,11 @@
struct ceph_msgpool {
const char *name;
mempool_t *pool;
int type; /* preallocated message type */
int front_len; /* preallocated payload size */
};
extern int ceph_msgpool_init(struct ceph_msgpool *pool,
extern int ceph_msgpool_init(struct ceph_msgpool *pool, int type,
int front_len, int size, bool blocking,
const char *name);
extern void ceph_msgpool_destroy(struct ceph_msgpool *pool);
......
......@@ -154,6 +154,14 @@ struct crush_map {
__s32 max_buckets;
__u32 max_rules;
__s32 max_devices;
/* choose local retries before re-descent */
__u32 choose_local_tries;
/* choose local attempts using a fallback permutation before
* re-descent */
__u32 choose_local_fallback_tries;
/* choose attempts before giving up */
__u32 choose_total_tries;
};
......
......@@ -17,6 +17,7 @@
#include <linux/string.h>
#include <linux/ceph/ceph_features.h>
#include <linux/ceph/libceph.h>
#include <linux/ceph/debugfs.h>
#include <linux/ceph/decode.h>
......@@ -460,27 +461,23 @@ struct ceph_client *ceph_create_client(struct ceph_options *opt, void *private,
client->auth_err = 0;
client->extra_mon_dispatch = NULL;
client->supported_features = CEPH_FEATURE_SUPPORTED_DEFAULT |
client->supported_features = CEPH_FEATURES_SUPPORTED_DEFAULT |
supported_features;
client->required_features = CEPH_FEATURE_REQUIRED_DEFAULT |
client->required_features = CEPH_FEATURES_REQUIRED_DEFAULT |
required_features;
/* msgr */
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)) {
err = PTR_ERR(client->msgr);
goto fail;
}
client->msgr->nocrc = ceph_test_opt(client, NOCRC);
ceph_messenger_init(&client->msgr, myaddr,
client->supported_features,
client->required_features,
ceph_test_opt(client, NOCRC));
/* subsystems */
err = ceph_monc_init(&client->monc, client);
if (err < 0)
goto fail_msgr;
goto fail;
err = ceph_osdc_init(&client->osdc, client);
if (err < 0)
goto fail_monc;
......@@ -489,8 +486,6 @@ struct ceph_client *ceph_create_client(struct ceph_options *opt, void *private,
fail_monc:
ceph_monc_stop(&client->monc);
fail_msgr:
ceph_messenger_destroy(client->msgr);
fail:
kfree(client);
return ERR_PTR(err);
......@@ -501,6 +496,8 @@ void ceph_destroy_client(struct ceph_client *client)
{
dout("destroy_client %p\n", client);
atomic_set(&client->msgr.stopping, 1);
/* unmount */
ceph_osdc_stop(&client->osdc);
......@@ -508,8 +505,6 @@ void ceph_destroy_client(struct ceph_client *client)
ceph_debugfs_client_cleanup(client);
ceph_messenger_destroy(client->msgr);
ceph_destroy_options(client->options);
kfree(client);
......
......@@ -306,7 +306,6 @@ static int crush_choose(const struct crush_map *map,
int item = 0;
int itemtype;
int collide, reject;
const unsigned int orig_tries = 5; /* attempts before we fall back to search */
dprintk("CHOOSE%s bucket %d x %d outpos %d numrep