summaryrefslogtreecommitdiff
path: root/net/ceph
diff options
context:
space:
mode:
Diffstat (limited to 'net/ceph')
-rw-r--r--net/ceph/auth_x.c2
-rw-r--r--net/ceph/ceph_common.c58
-rw-r--r--net/ceph/debugfs.c14
-rw-r--r--net/ceph/messenger.c2
-rw-r--r--net/ceph/messenger_v2.c17
-rw-r--r--net/ceph/osd_client.c6
-rw-r--r--net/ceph/osdmap.c138
7 files changed, 123 insertions, 114 deletions
diff --git a/net/ceph/auth_x.c b/net/ceph/auth_x.c
index b71b1635916e..a21c157daf7d 100644
--- a/net/ceph/auth_x.c
+++ b/net/ceph/auth_x.c
@@ -631,6 +631,7 @@ static int handle_auth_session_key(struct ceph_auth_client *ac, u64 global_id,
/* connection secret */
ceph_decode_32_safe(p, end, len, e_inval);
+ ceph_decode_need(p, end, len, e_inval);
dout("%s connection secret blob len %d\n", __func__, len);
if (len > 0) {
dp = *p + ceph_x_encrypt_offset();
@@ -648,6 +649,7 @@ static int handle_auth_session_key(struct ceph_auth_client *ac, u64 global_id,
/* service tickets */
ceph_decode_32_safe(p, end, len, e_inval);
+ ceph_decode_need(p, end, len, e_inval);
dout("%s service tickets blob len %d\n", __func__, len);
if (len > 0) {
ret = ceph_x_proc_ticket_reply(ac, &th->session_key,
diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c
index 4c6441536d55..e734e57be083 100644
--- a/net/ceph/ceph_common.c
+++ b/net/ceph/ceph_common.c
@@ -786,41 +786,52 @@ void ceph_reset_client_addr(struct ceph_client *client)
EXPORT_SYMBOL(ceph_reset_client_addr);
/*
- * true if we have the mon map (and have thus joined the cluster)
- */
-static bool 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)
+int __ceph_open_session(struct ceph_client *client)
{
- unsigned long timeout = client->options->mount_timeout;
- long err;
+ DEFINE_WAIT_FUNC(wait, woken_wake_function);
+ long timeout = ceph_timeout_jiffies(client->options->mount_timeout);
+ bool have_monmap, have_osdmap;
+ int err;
/* 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)) {
- if (timeout && time_after_eq(jiffies, started + timeout))
- return -ETIMEDOUT;
+ add_wait_queue(&client->auth_wq, &wait);
+ for (;;) {
+ mutex_lock(&client->monc.mutex);
+ err = client->auth_err;
+ have_monmap = client->monc.monmap && client->monc.monmap->epoch;
+ mutex_unlock(&client->monc.mutex);
+
+ down_read(&client->osdc.lock);
+ have_osdmap = client->osdc.osdmap && client->osdc.osdmap->epoch;
+ up_read(&client->osdc.lock);
+
+ if (err || (have_monmap && have_osdmap))
+ break;
+
+ if (signal_pending(current)) {
+ err = -ERESTARTSYS;
+ break;
+ }
+
+ if (!timeout) {
+ err = -ETIMEDOUT;
+ break;
+ }
/* 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),
- ceph_timeout_jiffies(timeout));
- if (err < 0)
- return err;
- if (client->auth_err < 0)
- return client->auth_err;
+ timeout = wait_woken(&wait, TASK_INTERRUPTIBLE, timeout);
}
+ remove_wait_queue(&client->auth_wq, &wait);
+
+ if (err)
+ return err;
pr_info("client%llu fsid %pU\n", ceph_client_gid(client),
&client->fsid);
@@ -833,12 +844,11 @@ 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);
+ ret = __ceph_open_session(client);
mutex_unlock(&client->mount_mutex);
return ret;
diff --git a/net/ceph/debugfs.c b/net/ceph/debugfs.c
index 2110439f8a24..83c270bce63c 100644
--- a/net/ceph/debugfs.c
+++ b/net/ceph/debugfs.c
@@ -36,8 +36,9 @@ static int monmap_show(struct seq_file *s, void *p)
int i;
struct ceph_client *client = s->private;
+ mutex_lock(&client->monc.mutex);
if (client->monc.monmap == NULL)
- return 0;
+ goto out_unlock;
seq_printf(s, "epoch %d\n", client->monc.monmap->epoch);
for (i = 0; i < client->monc.monmap->num_mon; i++) {
@@ -48,6 +49,9 @@ static int monmap_show(struct seq_file *s, void *p)
ENTITY_NAME(inst->name),
ceph_pr_addr(&inst->addr));
}
+
+out_unlock:
+ mutex_unlock(&client->monc.mutex);
return 0;
}
@@ -56,13 +60,14 @@ static int osdmap_show(struct seq_file *s, void *p)
int i;
struct ceph_client *client = s->private;
struct ceph_osd_client *osdc = &client->osdc;
- struct ceph_osdmap *map = osdc->osdmap;
+ struct ceph_osdmap *map;
struct rb_node *n;
+ down_read(&osdc->lock);
+ map = osdc->osdmap;
if (map == NULL)
- return 0;
+ goto out_unlock;
- down_read(&osdc->lock);
seq_printf(s, "epoch %u barrier %u flags 0x%x\n", map->epoch,
osdc->epoch_barrier, map->flags);
@@ -131,6 +136,7 @@ static int osdmap_show(struct seq_file *s, void *p)
seq_printf(s, "]\n");
}
+out_unlock:
up_read(&osdc->lock);
return 0;
}
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index f8181acaf870..70b25f4ecba6 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -460,7 +460,7 @@ int ceph_tcp_connect(struct ceph_connection *con)
set_sock_callbacks(sock, con);
con_sock_state_connecting(con);
- ret = kernel_connect(sock, (struct sockaddr *)&ss, sizeof(ss),
+ ret = kernel_connect(sock, (struct sockaddr_unsized *)&ss, sizeof(ss),
O_NONBLOCK);
if (ret == -EINPROGRESS) {
dout("connect %s EINPROGRESS sk_state = %u\n",
diff --git a/net/ceph/messenger_v2.c b/net/ceph/messenger_v2.c
index 9e39378eda00..833e57849c1d 100644
--- a/net/ceph/messenger_v2.c
+++ b/net/ceph/messenger_v2.c
@@ -1061,13 +1061,16 @@ static int decrypt_control_remainder(struct ceph_connection *con)
static int process_v2_sparse_read(struct ceph_connection *con,
struct page **pages, int spos)
{
- struct ceph_msg_data_cursor *cursor = &con->v2.in_cursor;
+ struct ceph_msg_data_cursor cursor;
int ret;
+ ceph_msg_data_cursor_init(&cursor, con->in_msg,
+ con->in_msg->sparse_read_total);
+
for (;;) {
char *buf = NULL;
- ret = con->ops->sparse_read(con, cursor, &buf);
+ ret = con->ops->sparse_read(con, &cursor, &buf);
if (ret <= 0)
return ret;
@@ -1085,11 +1088,11 @@ static int process_v2_sparse_read(struct ceph_connection *con,
} else {
struct bio_vec bv;
- get_bvec_at(cursor, &bv);
+ get_bvec_at(&cursor, &bv);
len = min_t(int, len, bv.bv_len);
memcpy_page(bv.bv_page, bv.bv_offset,
spage, soff, len);
- ceph_msg_data_advance(cursor, len);
+ ceph_msg_data_advance(&cursor, len);
}
spos += len;
ret -= len;
@@ -1535,8 +1538,7 @@ static int prepare_keepalive2(struct ceph_connection *con)
struct timespec64 now;
ktime_get_real_ts64(&now);
- dout("%s con %p timestamp %lld.%09ld\n", __func__, con, now.tv_sec,
- now.tv_nsec);
+ dout("%s con %p timestamp %ptSp\n", __func__, con, &now);
ceph_encode_timespec64(ts, &now);
@@ -2729,8 +2731,7 @@ static int process_keepalive2_ack(struct ceph_connection *con,
ceph_decode_need(&p, end, sizeof(struct ceph_timespec), bad);
ceph_decode_timespec64(&con->last_keepalive_ack, p);
- dout("%s con %p timestamp %lld.%09ld\n", __func__, con,
- con->last_keepalive_ack.tv_sec, con->last_keepalive_ack.tv_nsec);
+ dout("%s con %p timestamp %ptSp\n", __func__, con, &con->last_keepalive_ack);
return 0;
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 6664ea73ccf8..3667319b949d 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -1280,8 +1280,7 @@ static struct ceph_osd *create_osd(struct ceph_osd_client *osdc, int onum)
static struct ceph_osd *get_osd(struct ceph_osd *osd)
{
if (refcount_inc_not_zero(&osd->o_ref)) {
- dout("get_osd %p %d -> %d\n", osd, refcount_read(&osd->o_ref)-1,
- refcount_read(&osd->o_ref));
+ dout("get_osd %p -> %d\n", osd, refcount_read(&osd->o_ref));
return osd;
} else {
dout("get_osd %p FAIL\n", osd);
@@ -1291,8 +1290,7 @@ static struct ceph_osd *get_osd(struct ceph_osd *osd)
static void put_osd(struct ceph_osd *osd)
{
- dout("put_osd %p %d -> %d\n", osd, refcount_read(&osd->o_ref),
- refcount_read(&osd->o_ref) - 1);
+ dout("put_osd %p -> %d\n", osd, refcount_read(&osd->o_ref) - 1);
if (refcount_dec_and_test(&osd->o_ref)) {
osd_cleanup(osd);
kfree(osd);
diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index 295098873861..34b3ab59602f 100644
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -806,51 +806,49 @@ static int decode_pool(void **p, void *end, struct ceph_pg_pool_info *pi)
ceph_decode_need(p, end, len, bad);
pool_end = *p + len;
+ ceph_decode_need(p, end, 4 + 4 + 4, bad);
pi->type = ceph_decode_8(p);
pi->size = ceph_decode_8(p);
pi->crush_ruleset = ceph_decode_8(p);
pi->object_hash = ceph_decode_8(p);
-
pi->pg_num = ceph_decode_32(p);
pi->pgp_num = ceph_decode_32(p);
- *p += 4 + 4; /* skip lpg* */
- *p += 4; /* skip last_change */
- *p += 8 + 4; /* skip snap_seq, snap_epoch */
+ /* lpg*, last_change, snap_seq, snap_epoch */
+ ceph_decode_skip_n(p, end, 8 + 4 + 8 + 4, bad);
/* skip snaps */
- num = ceph_decode_32(p);
+ ceph_decode_32_safe(p, end, num, bad);
while (num--) {
- *p += 8; /* snapid key */
- *p += 1 + 1; /* versions */
- len = ceph_decode_32(p);
- *p += len;
+ /* snapid key, pool snap (with versions) */
+ ceph_decode_skip_n(p, end, 8 + 2, bad);
+ ceph_decode_skip_string(p, end, bad);
}
- /* skip removed_snaps */
- num = ceph_decode_32(p);
- *p += num * (8 + 8);
+ /* removed_snaps */
+ ceph_decode_skip_map(p, end, 64, 64, bad);
+ ceph_decode_need(p, end, 8 + 8 + 4, bad);
*p += 8; /* skip auid */
pi->flags = ceph_decode_64(p);
*p += 4; /* skip crash_replay_interval */
if (ev >= 7)
- pi->min_size = ceph_decode_8(p);
+ ceph_decode_8_safe(p, end, pi->min_size, bad);
else
pi->min_size = pi->size - pi->size / 2;
if (ev >= 8)
- *p += 8 + 8; /* skip quota_max_* */
+ /* quota_max_* */
+ ceph_decode_skip_n(p, end, 8 + 8, bad);
if (ev >= 9) {
- /* skip tiers */
- num = ceph_decode_32(p);
- *p += num * 8;
+ /* tiers */
+ ceph_decode_skip_set(p, end, 64, bad);
+ ceph_decode_need(p, end, 8 + 1 + 8 + 8, bad);
*p += 8; /* skip tier_of */
*p += 1; /* skip cache_mode */
-
pi->read_tier = ceph_decode_64(p);
pi->write_tier = ceph_decode_64(p);
} else {
@@ -858,86 +856,76 @@ static int decode_pool(void **p, void *end, struct ceph_pg_pool_info *pi)
pi->write_tier = -1;
}
- if (ev >= 10) {
- /* skip properties */
- num = ceph_decode_32(p);
- while (num--) {
- len = ceph_decode_32(p);
- *p += len; /* key */
- len = ceph_decode_32(p);
- *p += len; /* val */
- }
- }
+ if (ev >= 10)
+ /* properties */
+ ceph_decode_skip_map(p, end, string, string, bad);
if (ev >= 11) {
- /* skip hit_set_params */
- *p += 1 + 1; /* versions */
- len = ceph_decode_32(p);
- *p += len;
+ /* hit_set_params (with versions) */
+ ceph_decode_skip_n(p, end, 2, bad);
+ ceph_decode_skip_string(p, end, bad);
- *p += 4; /* skip hit_set_period */
- *p += 4; /* skip hit_set_count */
+ /* hit_set_period, hit_set_count */
+ ceph_decode_skip_n(p, end, 4 + 4, bad);
}
if (ev >= 12)
- *p += 4; /* skip stripe_width */
+ /* stripe_width */
+ ceph_decode_skip_32(p, end, bad);
- if (ev >= 13) {
- *p += 8; /* skip target_max_bytes */
- *p += 8; /* skip target_max_objects */
- *p += 4; /* skip cache_target_dirty_ratio_micro */
- *p += 4; /* skip cache_target_full_ratio_micro */
- *p += 4; /* skip cache_min_flush_age */
- *p += 4; /* skip cache_min_evict_age */
- }
+ if (ev >= 13)
+ /* target_max_*, cache_target_*, cache_min_* */
+ ceph_decode_skip_n(p, end, 16 + 8 + 8, bad);
- if (ev >= 14) {
- /* skip erasure_code_profile */
- len = ceph_decode_32(p);
- *p += len;
- }
+ if (ev >= 14)
+ /* erasure_code_profile */
+ ceph_decode_skip_string(p, end, bad);
/*
* last_force_op_resend_preluminous, will be overridden if the
* map was encoded with RESEND_ON_SPLIT
*/
if (ev >= 15)
- pi->last_force_request_resend = ceph_decode_32(p);
+ ceph_decode_32_safe(p, end, pi->last_force_request_resend, bad);
else
pi->last_force_request_resend = 0;
if (ev >= 16)
- *p += 4; /* skip min_read_recency_for_promote */
+ /* min_read_recency_for_promote */
+ ceph_decode_skip_32(p, end, bad);
if (ev >= 17)
- *p += 8; /* skip expected_num_objects */
+ /* expected_num_objects */
+ ceph_decode_skip_64(p, end, bad);
if (ev >= 19)
- *p += 4; /* skip cache_target_dirty_high_ratio_micro */
+ /* cache_target_dirty_high_ratio_micro */
+ ceph_decode_skip_32(p, end, bad);
if (ev >= 20)
- *p += 4; /* skip min_write_recency_for_promote */
+ /* min_write_recency_for_promote */
+ ceph_decode_skip_32(p, end, bad);
if (ev >= 21)
- *p += 1; /* skip use_gmt_hitset */
+ /* use_gmt_hitset */
+ ceph_decode_skip_8(p, end, bad);
if (ev >= 22)
- *p += 1; /* skip fast_read */
+ /* fast_read */
+ ceph_decode_skip_8(p, end, bad);
- if (ev >= 23) {
- *p += 4; /* skip hit_set_grade_decay_rate */
- *p += 4; /* skip hit_set_search_last_n */
- }
+ if (ev >= 23)
+ /* hit_set_grade_decay_rate, hit_set_search_last_n */
+ ceph_decode_skip_n(p, end, 4 + 4, bad);
if (ev >= 24) {
- /* skip opts */
- *p += 1 + 1; /* versions */
- len = ceph_decode_32(p);
- *p += len;
+ /* opts (with versions) */
+ ceph_decode_skip_n(p, end, 2, bad);
+ ceph_decode_skip_string(p, end, bad);
}
if (ev >= 25)
- pi->last_force_request_resend = ceph_decode_32(p);
+ ceph_decode_32_safe(p, end, pi->last_force_request_resend, bad);
/* ignore the rest */
@@ -1438,7 +1426,7 @@ static struct ceph_pg_mapping *__decode_pg_temp(void **p, void *end,
ceph_decode_32_safe(p, end, len, e_inval);
if (len == 0 && incremental)
return NULL; /* new_pg_temp: [] to remove */
- if (len > (SIZE_MAX - sizeof(*pg)) / sizeof(u32))
+ if ((size_t)len > (SIZE_MAX - sizeof(*pg)) / sizeof(u32))
return ERR_PTR(-EINVAL);
ceph_decode_need(p, end, len * sizeof(u32), e_inval);
@@ -1504,8 +1492,6 @@ static int decode_new_primary_temp(void **p, void *end,
u32 ceph_get_primary_affinity(struct ceph_osdmap *map, int osd)
{
- BUG_ON(osd >= map->max_osd);
-
if (!map->osd_primary_affinity)
return CEPH_OSD_DEFAULT_PRIMARY_AFFINITY;
@@ -1514,8 +1500,6 @@ u32 ceph_get_primary_affinity(struct ceph_osdmap *map, int osd)
static int set_primary_affinity(struct ceph_osdmap *map, int osd, u32 aff)
{
- BUG_ON(osd >= map->max_osd);
-
if (!map->osd_primary_affinity) {
int i;
@@ -1577,6 +1561,8 @@ static int decode_new_primary_affinity(void **p, void *end,
ceph_decode_32_safe(p, end, osd, e_inval);
ceph_decode_32_safe(p, end, aff, e_inval);
+ if (osd >= map->max_osd)
+ goto e_inval;
ret = set_primary_affinity(map, osd, aff);
if (ret)
@@ -1621,7 +1607,7 @@ static struct ceph_pg_mapping *__decode_pg_upmap_items(void **p, void *end,
u32 len, i;
ceph_decode_32_safe(p, end, len, e_inval);
- if (len > (SIZE_MAX - sizeof(*pg)) / (2 * sizeof(u32)))
+ if ((size_t)len > (SIZE_MAX - sizeof(*pg)) / (2 * sizeof(u32)))
return ERR_PTR(-EINVAL);
ceph_decode_need(p, end, 2 * len * sizeof(u32), e_inval);
@@ -1879,7 +1865,9 @@ static int decode_new_up_state_weight(void **p, void *end, u8 struct_v,
ceph_decode_need(p, end, 2*sizeof(u32), e_inval);
osd = ceph_decode_32(p);
w = ceph_decode_32(p);
- BUG_ON(osd >= map->max_osd);
+ if (osd >= map->max_osd)
+ goto e_inval;
+
osdmap_info(map, "osd%d weight 0x%x %s\n", osd, w,
w == CEPH_OSD_IN ? "(in)" :
(w == CEPH_OSD_OUT ? "(out)" : ""));
@@ -1905,13 +1893,15 @@ static int decode_new_up_state_weight(void **p, void *end, u8 struct_v,
u32 xorstate;
osd = ceph_decode_32(p);
+ if (osd >= map->max_osd)
+ goto e_inval;
+
if (struct_v >= 5)
xorstate = ceph_decode_32(p);
else
xorstate = ceph_decode_8(p);
if (xorstate == 0)
xorstate = CEPH_OSD_UP;
- BUG_ON(osd >= map->max_osd);
if ((map->osd_state[osd] & CEPH_OSD_UP) &&
(xorstate & CEPH_OSD_UP))
osdmap_info(map, "osd%d down\n", osd);
@@ -1937,7 +1927,9 @@ static int decode_new_up_state_weight(void **p, void *end, u8 struct_v,
struct ceph_entity_addr addr;
osd = ceph_decode_32(p);
- BUG_ON(osd >= map->max_osd);
+ if (osd >= map->max_osd)
+ goto e_inval;
+
if (struct_v >= 7)
ret = ceph_decode_entity_addrvec(p, end, msgr2, &addr);
else
generated by cgit v1.2.3 (git 2.0.4) at 2025-12-14 04:45:49 +0000