summaryrefslogtreecommitdiffstats
path: root/net/ceph
diff options
context:
space:
mode:
Diffstat (limited to 'net/ceph')
-rw-r--r--net/ceph/auth_x.c49
-rw-r--r--net/ceph/auth_x.h2
-rw-r--r--net/ceph/crush/mapper.c33
-rw-r--r--net/ceph/messenger.c105
-rw-r--r--net/ceph/mon_client.c4
-rw-r--r--net/ceph/osd_client.c10
-rw-r--r--net/ceph/osdmap.c19
7 files changed, 159 insertions, 63 deletions
diff --git a/net/ceph/auth_x.c b/net/ceph/auth_x.c
index 10d87753ed87..9e43a315e662 100644
--- a/net/ceph/auth_x.c
+++ b/net/ceph/auth_x.c
@@ -152,7 +152,6 @@ static int process_one_ticket(struct ceph_auth_client *ac,
void *ticket_buf = NULL;
void *tp, *tpend;
void **ptp;
- 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;
@@ -193,8 +192,8 @@ static int process_one_ticket(struct ceph_auth_client *ac,
if (ret)
goto out;
- ceph_decode_copy(&dp, &new_validity, sizeof(new_validity));
- ceph_decode_timespec(&validity, &new_validity);
+ ceph_decode_timespec(&validity, dp);
+ dp += sizeof(struct ceph_timespec);
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,
@@ -233,10 +232,10 @@ static int process_one_ticket(struct ceph_auth_client *ac,
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;
+ th->have_key = true;
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);
@@ -384,6 +383,24 @@ bad:
return -ERANGE;
}
+static bool need_key(struct ceph_x_ticket_handler *th)
+{
+ if (!th->have_key)
+ return true;
+
+ return get_seconds() >= th->renew_after;
+}
+
+static bool have_key(struct ceph_x_ticket_handler *th)
+{
+ if (th->have_key) {
+ if (get_seconds() >= th->expires)
+ th->have_key = false;
+ }
+
+ return th->have_key;
+}
+
static void ceph_x_validate_tickets(struct ceph_auth_client *ac, int *pneed)
{
int want = ac->want_keys;
@@ -402,20 +419,18 @@ static void ceph_x_validate_tickets(struct ceph_auth_client *ac, int *pneed)
continue;
th = get_ticket_handler(ac, service);
-
if (IS_ERR(th)) {
*pneed |= service;
continue;
}
- if (get_seconds() >= th->renew_after)
+ if (need_key(th))
*pneed |= service;
- if (get_seconds() >= th->expires)
+ if (!have_key(th))
xi->have_keys &= ~service;
}
}
-
static int ceph_x_build_request(struct ceph_auth_client *ac,
void *buf, void *end)
{
@@ -667,14 +682,26 @@ static void ceph_x_destroy(struct ceph_auth_client *ac)
ac->private = NULL;
}
-static void ceph_x_invalidate_authorizer(struct ceph_auth_client *ac,
- int peer_type)
+static void invalidate_ticket(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))
- memset(&th->validity, 0, sizeof(th->validity));
+ th->have_key = false;
+}
+
+static void ceph_x_invalidate_authorizer(struct ceph_auth_client *ac,
+ int peer_type)
+{
+ /*
+ * We are to invalidate a service ticket in the hopes of
+ * getting a new, hopefully more valid, one. But, we won't get
+ * it unless our AUTH ticket is good, so invalidate AUTH ticket
+ * as well, just in case.
+ */
+ invalidate_ticket(ac, peer_type);
+ invalidate_ticket(ac, CEPH_ENTITY_TYPE_AUTH);
}
static int calcu_signature(struct ceph_x_authorizer *au,
diff --git a/net/ceph/auth_x.h b/net/ceph/auth_x.h
index e8b7c6917d47..40b1a3cf7397 100644
--- a/net/ceph/auth_x.h
+++ b/net/ceph/auth_x.h
@@ -16,7 +16,7 @@ struct ceph_x_ticket_handler {
unsigned int service;
struct ceph_crypto_key session_key;
- struct ceph_timespec validity;
+ bool have_key;
u64 secret_id;
struct ceph_buffer *ticket_blob;
diff --git a/net/ceph/crush/mapper.c b/net/ceph/crush/mapper.c
index 393bfb22d5bb..5fcfb98f309e 100644
--- a/net/ceph/crush/mapper.c
+++ b/net/ceph/crush/mapper.c
@@ -403,6 +403,7 @@ static int is_out(const struct crush_map *map,
* @local_retries: localized retries
* @local_fallback_retries: localized fallback retries
* @recurse_to_leaf: true if we want one device under each item of given type (chooseleaf instead of choose)
+ * @stable: stable mode starts rep=0 in the recursive call for all replicas
* @vary_r: pass r to recursive calls
* @out2: second output vector for leaf items (if @recurse_to_leaf)
* @parent_r: r value passed from the parent
@@ -419,6 +420,7 @@ static int crush_choose_firstn(const struct crush_map *map,
unsigned int local_fallback_retries,
int recurse_to_leaf,
unsigned int vary_r,
+ unsigned int stable,
int *out2,
int parent_r)
{
@@ -433,13 +435,13 @@ static int crush_choose_firstn(const struct crush_map *map,
int collide, reject;
int count = out_size;
- dprintk("CHOOSE%s bucket %d x %d outpos %d numrep %d tries %d recurse_tries %d local_retries %d local_fallback_retries %d parent_r %d\n",
+ dprintk("CHOOSE%s bucket %d x %d outpos %d numrep %d tries %d recurse_tries %d local_retries %d local_fallback_retries %d parent_r %d stable %d\n",
recurse_to_leaf ? "_LEAF" : "",
bucket->id, x, outpos, numrep,
tries, recurse_tries, local_retries, local_fallback_retries,
- parent_r);
+ parent_r, stable);
- for (rep = outpos; rep < numrep && count > 0 ; rep++) {
+ for (rep = stable ? 0 : outpos; rep < numrep && count > 0 ; rep++) {
/* keep trying until we get a non-out, non-colliding item */
ftotal = 0;
skip_rep = 0;
@@ -512,13 +514,14 @@ static int crush_choose_firstn(const struct crush_map *map,
if (crush_choose_firstn(map,
map->buckets[-1-item],
weight, weight_max,
- x, outpos+1, 0,
+ x, stable ? 1 : outpos+1, 0,
out2, outpos, count,
recurse_tries, 0,
local_retries,
local_fallback_retries,
0,
vary_r,
+ stable,
NULL,
sub_r) <= outpos)
/* didn't get leaf */
@@ -816,6 +819,7 @@ int crush_do_rule(const struct crush_map *map,
int choose_local_fallback_retries = map->choose_local_fallback_tries;
int vary_r = map->chooseleaf_vary_r;
+ int stable = map->chooseleaf_stable;
if ((__u32)ruleno >= map->max_rules) {
dprintk(" bad ruleno %d\n", ruleno);
@@ -835,7 +839,8 @@ int crush_do_rule(const struct crush_map *map,
case CRUSH_RULE_TAKE:
if ((curstep->arg1 >= 0 &&
curstep->arg1 < map->max_devices) ||
- (-1-curstep->arg1 < map->max_buckets &&
+ (-1-curstep->arg1 >= 0 &&
+ -1-curstep->arg1 < map->max_buckets &&
map->buckets[-1-curstep->arg1])) {
w[0] = curstep->arg1;
wsize = 1;
@@ -869,6 +874,11 @@ int crush_do_rule(const struct crush_map *map,
vary_r = curstep->arg1;
break;
+ case CRUSH_RULE_SET_CHOOSELEAF_STABLE:
+ if (curstep->arg1 >= 0)
+ stable = curstep->arg1;
+ break;
+
case CRUSH_RULE_CHOOSELEAF_FIRSTN:
case CRUSH_RULE_CHOOSE_FIRSTN:
firstn = 1;
@@ -888,6 +898,7 @@ int crush_do_rule(const struct crush_map *map,
osize = 0;
for (i = 0; i < wsize; i++) {
+ int bno;
/*
* see CRUSH_N, CRUSH_N_MINUS macros.
* basically, numrep <= 0 means relative to
@@ -900,6 +911,13 @@ int crush_do_rule(const struct crush_map *map,
continue;
}
j = 0;
+ /* make sure bucket id is valid */
+ bno = -1 - w[i];
+ if (bno < 0 || bno >= map->max_buckets) {
+ /* w[i] is probably CRUSH_ITEM_NONE */
+ dprintk(" bad w[i] %d\n", w[i]);
+ continue;
+ }
if (firstn) {
int recurse_tries;
if (choose_leaf_tries)
@@ -911,7 +929,7 @@ int crush_do_rule(const struct crush_map *map,
recurse_tries = choose_tries;
osize += crush_choose_firstn(
map,
- map->buckets[-1-w[i]],
+ map->buckets[bno],
weight, weight_max,
x, numrep,
curstep->arg2,
@@ -923,6 +941,7 @@ int crush_do_rule(const struct crush_map *map,
choose_local_fallback_retries,
recurse_to_leaf,
vary_r,
+ stable,
c+osize,
0);
} else {
@@ -930,7 +949,7 @@ int crush_do_rule(const struct crush_map *map,
numrep : (result_max-osize));
crush_choose_indep(
map,
- map->buckets[-1-w[i]],
+ map->buckets[bno],
weight, weight_max,
x, out_size, numrep,
curstep->arg2,
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 9981039ef4ff..9cfedf565f5b 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -23,9 +23,6 @@
#include <linux/ceph/pagelist.h>
#include <linux/export.h>
-#define list_entry_next(pos, member) \
- list_entry(pos->member.next, typeof(*pos), member)
-
/*
* Ceph uses the messenger to exchange ceph_msg messages with other
* hosts in the system. The messenger provides ordered and reliable
@@ -672,6 +669,8 @@ static void reset_connection(struct ceph_connection *con)
}
con->in_seq = 0;
con->in_seq_acked = 0;
+
+ con->out_skip = 0;
}
/*
@@ -771,6 +770,8 @@ static u32 get_global_seq(struct ceph_messenger *msgr, u32 gt)
static void con_out_kvec_reset(struct ceph_connection *con)
{
+ BUG_ON(con->out_skip);
+
con->out_kvec_left = 0;
con->out_kvec_bytes = 0;
con->out_kvec_cur = &con->out_kvec[0];
@@ -779,9 +780,9 @@ static void con_out_kvec_reset(struct ceph_connection *con)
static void con_out_kvec_add(struct ceph_connection *con,
size_t size, void *data)
{
- int index;
+ int index = con->out_kvec_left;
- index = con->out_kvec_left;
+ BUG_ON(con->out_skip);
BUG_ON(index >= ARRAY_SIZE(con->out_kvec));
con->out_kvec[index].iov_len = size;
@@ -790,6 +791,27 @@ static void con_out_kvec_add(struct ceph_connection *con,
con->out_kvec_bytes += size;
}
+/*
+ * Chop off a kvec from the end. Return residual number of bytes for
+ * that kvec, i.e. how many bytes would have been written if the kvec
+ * hadn't been nuked.
+ */
+static int con_out_kvec_skip(struct ceph_connection *con)
+{
+ int off = con->out_kvec_cur - con->out_kvec;
+ int skip = 0;
+
+ if (con->out_kvec_bytes > 0) {
+ skip = con->out_kvec[off + con->out_kvec_left - 1].iov_len;
+ BUG_ON(con->out_kvec_bytes < skip);
+ BUG_ON(!con->out_kvec_left);
+ con->out_kvec_bytes -= skip;
+ con->out_kvec_left--;
+ }
+
+ return skip;
+}
+
#ifdef CONFIG_BLOCK
/*
@@ -1042,7 +1064,7 @@ static bool ceph_msg_data_pagelist_advance(struct ceph_msg_data_cursor *cursor,
/* Move on to the next page */
BUG_ON(list_is_last(&cursor->page->lru, &pagelist->head));
- cursor->page = list_entry_next(cursor->page, lru);
+ cursor->page = list_next_entry(cursor->page, lru);
cursor->last_piece = cursor->resid <= PAGE_SIZE;
return true;
@@ -1166,7 +1188,7 @@ static bool ceph_msg_data_advance(struct ceph_msg_data_cursor *cursor,
if (!cursor->resid && cursor->total_resid) {
WARN_ON(!cursor->last_piece);
BUG_ON(list_is_last(&cursor->data->links, cursor->data_head));
- cursor->data = list_entry_next(cursor->data, links);
+ cursor->data = list_next_entry(cursor->data, links);
__ceph_msg_data_cursor_init(cursor);
new_piece = true;
}
@@ -1197,7 +1219,6 @@ static void prepare_write_message_footer(struct ceph_connection *con)
m->footer.flags |= CEPH_MSG_FOOTER_COMPLETE;
dout("prepare_write_message_footer %p\n", con);
- con->out_kvec_is_msg = true;
con->out_kvec[v].iov_base = &m->footer;
if (con->peer_features & CEPH_FEATURE_MSG_AUTH) {
if (con->ops->sign_message)
@@ -1225,7 +1246,6 @@ static void prepare_write_message(struct ceph_connection *con)
u32 crc;
con_out_kvec_reset(con);
- 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
@@ -1265,18 +1285,19 @@ static void prepare_write_message(struct ceph_connection *con)
/* tag + hdr + front + middle */
con_out_kvec_add(con, sizeof (tag_msg), &tag_msg);
- con_out_kvec_add(con, sizeof (m->hdr), &m->hdr);
+ con_out_kvec_add(con, sizeof(con->out_hdr), &con->out_hdr);
con_out_kvec_add(con, m->front.iov_len, m->front.iov_base);
if (m->middle)
con_out_kvec_add(con, m->middle->vec.iov_len,
m->middle->vec.iov_base);
- /* fill in crc (except data pages), footer */
+ /* fill in hdr crc and finalize hdr */
crc = crc32c(0, &m->hdr, offsetof(struct ceph_msg_header, crc));
con->out_msg->hdr.crc = cpu_to_le32(crc);
- con->out_msg->footer.flags = 0;
+ memcpy(&con->out_hdr, &con->out_msg->hdr, sizeof(con->out_hdr));
+ /* fill in front and middle crc, footer */
crc = crc32c(0, m->front.iov_base, m->front.iov_len);
con->out_msg->footer.front_crc = cpu_to_le32(crc);
if (m->middle) {
@@ -1288,6 +1309,7 @@ static void prepare_write_message(struct ceph_connection *con)
dout("%s front_crc %u middle_crc %u\n", __func__,
le32_to_cpu(con->out_msg->footer.front_crc),
le32_to_cpu(con->out_msg->footer.middle_crc));
+ con->out_msg->footer.flags = 0;
/* is there a data payload? */
con->out_msg->footer.data_crc = 0;
@@ -1492,7 +1514,6 @@ static int write_partial_kvec(struct ceph_connection *con)
}
}
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,
@@ -1584,6 +1605,7 @@ static int write_partial_skip(struct ceph_connection *con)
{
int ret;
+ dout("%s %p %d left\n", __func__, con, con->out_skip);
while (con->out_skip > 0) {
size_t size = min(con->out_skip, (int) PAGE_CACHE_SIZE);
@@ -2506,13 +2528,13 @@ more:
more_kvec:
/* kvec data queued? */
- if (con->out_skip) {
- ret = write_partial_skip(con);
+ if (con->out_kvec_left) {
+ ret = write_partial_kvec(con);
if (ret <= 0)
goto out;
}
- if (con->out_kvec_left) {
- ret = write_partial_kvec(con);
+ if (con->out_skip) {
+ ret = write_partial_skip(con);
if (ret <= 0)
goto out;
}
@@ -2805,13 +2827,17 @@ static bool con_backoff(struct ceph_connection *con)
static void con_fault_finish(struct ceph_connection *con)
{
+ dout("%s %p\n", __func__, con);
+
/*
* 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->auth_retry) {
+ dout("auth_retry %d, invalidating\n", con->auth_retry);
+ if (con->ops->invalidate_authorizer)
+ con->ops->invalidate_authorizer(con);
+ con->auth_retry = 0;
}
if (con->ops->fault)
@@ -3050,16 +3076,31 @@ void ceph_msg_revoke(struct ceph_msg *msg)
ceph_msg_put(msg);
}
if (con->out_msg == msg) {
- dout("%s %p msg %p - was sending\n", __func__, 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;
+ BUG_ON(con->out_skip);
+ /* footer */
+ if (con->out_msg_done) {
+ con->out_skip += con_out_kvec_skip(con);
+ } else {
+ BUG_ON(!msg->data_length);
+ if (con->peer_features & CEPH_FEATURE_MSG_AUTH)
+ con->out_skip += sizeof(msg->footer);
+ else
+ con->out_skip += sizeof(msg->old_footer);
}
+ /* data, middle, front */
+ if (msg->data_length)
+ con->out_skip += msg->cursor.total_resid;
+ if (msg->middle)
+ con->out_skip += con_out_kvec_skip(con);
+ con->out_skip += con_out_kvec_skip(con);
+
+ dout("%s %p msg %p - was sending, will write %d skip %d\n",
+ __func__, con, msg, con->out_kvec_bytes, con->out_skip);
msg->hdr.seq = 0;
-
+ con->out_msg = NULL;
ceph_msg_put(msg);
}
+
mutex_unlock(&con->mutex);
}
@@ -3361,9 +3402,7 @@ static void ceph_msg_free(struct ceph_msg *m)
static void ceph_msg_release(struct kref *kref)
{
struct ceph_msg *m = container_of(kref, struct ceph_msg, kref);
- LIST_HEAD(data);
- struct list_head *links;
- struct list_head *next;
+ struct ceph_msg_data *data, *next;
dout("%s %p\n", __func__, m);
WARN_ON(!list_empty(&m->list_head));
@@ -3376,12 +3415,8 @@ static void ceph_msg_release(struct kref *kref)
m->middle = NULL;
}
- list_splice_init(&m->data, &data);
- list_for_each_safe(links, next, &data) {
- struct ceph_msg_data *data;
-
- data = list_entry(links, struct ceph_msg_data, links);
- list_del_init(links);
+ list_for_each_entry_safe(data, next, &m->data, links) {
+ list_del_init(&data->links);
ceph_msg_data_destroy(data);
}
m->data_length = 0;
diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c
index edda01626a45..de85dddc3dc0 100644
--- a/net/ceph/mon_client.c
+++ b/net/ceph/mon_client.c
@@ -364,10 +364,6 @@ static bool have_debugfs_info(struct ceph_mon_client *monc)
return monc->client->have_fsid && monc->auth->global_id > 0;
}
-/*
- * The monitor responds with mount ack indicate mount success. The
- * included client ticket allows the client to talk to MDSs and OSDs.
- */
static void ceph_monc_handle_map(struct ceph_mon_client *monc,
struct ceph_msg *msg)
{
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index f8f235930d88..3534e12683d3 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -1770,6 +1770,7 @@ static void handle_reply(struct ceph_osd_client *osdc, struct ceph_msg *msg)
u32 osdmap_epoch;
int already_completed;
u32 bytes;
+ u8 decode_redir;
unsigned int i;
tid = le64_to_cpu(msg->hdr.tid);
@@ -1841,6 +1842,15 @@ static void handle_reply(struct ceph_osd_client *osdc, struct ceph_msg *msg)
p += 8 + 4; /* skip replay_version */
p += 8; /* skip user_version */
+ if (le16_to_cpu(msg->hdr.version) >= 7)
+ ceph_decode_8_safe(&p, end, decode_redir, bad_put);
+ else
+ decode_redir = 1;
+ } else {
+ decode_redir = 0;
+ }
+
+ if (decode_redir) {
err = ceph_redirect_decode(&p, end, &redir);
if (err)
goto bad_put;
diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index 7d8f581d9f1f..243574c8cf33 100644
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -342,23 +342,32 @@ static struct crush_map *crush_decode(void *pbyval, void *end)
c->choose_local_tries = ceph_decode_32(p);
c->choose_local_fallback_tries = ceph_decode_32(p);
c->choose_total_tries = ceph_decode_32(p);
- dout("crush decode tunable choose_local_tries = %d",
+ dout("crush decode tunable choose_local_tries = %d\n",
c->choose_local_tries);
- dout("crush decode tunable choose_local_fallback_tries = %d",
+ dout("crush decode tunable choose_local_fallback_tries = %d\n",
c->choose_local_fallback_tries);
- dout("crush decode tunable choose_total_tries = %d",
+ dout("crush decode tunable choose_total_tries = %d\n",
c->choose_total_tries);
ceph_decode_need(p, end, sizeof(u32), done);
c->chooseleaf_descend_once = ceph_decode_32(p);
- dout("crush decode tunable chooseleaf_descend_once = %d",
+ dout("crush decode tunable chooseleaf_descend_once = %d\n",
c->chooseleaf_descend_once);
ceph_decode_need(p, end, sizeof(u8), done);
c->chooseleaf_vary_r = ceph_decode_8(p);
- dout("crush decode tunable chooseleaf_vary_r = %d",
+ dout("crush decode tunable chooseleaf_vary_r = %d\n",
c->chooseleaf_vary_r);
+ /* skip straw_calc_version, allowed_bucket_algs */
+ ceph_decode_need(p, end, sizeof(u8) + sizeof(u32), done);
+ *p += sizeof(u8) + sizeof(u32);
+
+ ceph_decode_need(p, end, sizeof(u8), done);
+ c->chooseleaf_stable = ceph_decode_8(p);
+ dout("crush decode tunable chooseleaf_stable = %d\n",
+ c->chooseleaf_stable);
+
done:
dout("crush_decode success\n");
return c;
OpenPOWER on IntegriCloud