summaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
Diffstat (limited to 'net')
-rw-r--r--net/ceph/ceph_common.c27
-rw-r--r--net/ceph/cls_lock_client.c51
-rw-r--r--net/ceph/debugfs.c7
-rw-r--r--net/ceph/osd_client.c139
-rw-r--r--net/ceph/pagelist.c2
-rw-r--r--net/ceph/snapshot.c6
6 files changed, 198 insertions, 34 deletions
diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c
index 4eb773ccce11..4fd02831beed 100644
--- a/net/ceph/ceph_common.c
+++ b/net/ceph/ceph_common.c
@@ -45,6 +45,17 @@ bool libceph_compatible(void *data)
}
EXPORT_SYMBOL(libceph_compatible);
+static int param_get_supported_features(char *buffer,
+ const struct kernel_param *kp)
+{
+ return sprintf(buffer, "0x%llx", CEPH_FEATURES_SUPPORTED_DEFAULT);
+}
+static const struct kernel_param_ops param_ops_supported_features = {
+ .get = param_get_supported_features,
+};
+module_param_cb(supported_features, &param_ops_supported_features, NULL,
+ S_IRUGO);
+
/*
* find filename portion of a path (/foo/bar/baz -> baz)
*/
@@ -596,9 +607,7 @@ EXPORT_SYMBOL(ceph_client_gid);
/*
* create a fresh client instance
*/
-struct ceph_client *ceph_create_client(struct ceph_options *opt, void *private,
- u64 supported_features,
- u64 required_features)
+struct ceph_client *ceph_create_client(struct ceph_options *opt, void *private)
{
struct ceph_client *client;
struct ceph_entity_addr *myaddr = NULL;
@@ -615,14 +624,12 @@ struct ceph_client *ceph_create_client(struct ceph_options *opt, void *private,
init_waitqueue_head(&client->auth_wq);
client->auth_err = 0;
- if (!ceph_test_opt(client, NOMSGAUTH))
- required_features |= CEPH_FEATURE_MSG_AUTH;
-
client->extra_mon_dispatch = NULL;
- client->supported_features = CEPH_FEATURES_SUPPORTED_DEFAULT |
- supported_features;
- client->required_features = CEPH_FEATURES_REQUIRED_DEFAULT |
- required_features;
+ client->supported_features = CEPH_FEATURES_SUPPORTED_DEFAULT;
+ client->required_features = CEPH_FEATURES_REQUIRED_DEFAULT;
+
+ if (!ceph_test_opt(client, NOMSGAUTH))
+ client->required_features |= CEPH_FEATURE_MSG_AUTH;
/* msgr */
if (ceph_test_opt(client, MYIP))
diff --git a/net/ceph/cls_lock_client.c b/net/ceph/cls_lock_client.c
index b9233b990399..08ada893f01e 100644
--- a/net/ceph/cls_lock_client.c
+++ b/net/ceph/cls_lock_client.c
@@ -179,6 +179,57 @@ int ceph_cls_break_lock(struct ceph_osd_client *osdc,
}
EXPORT_SYMBOL(ceph_cls_break_lock);
+int ceph_cls_set_cookie(struct ceph_osd_client *osdc,
+ struct ceph_object_id *oid,
+ struct ceph_object_locator *oloc,
+ char *lock_name, u8 type, char *old_cookie,
+ char *tag, char *new_cookie)
+{
+ int cookie_op_buf_size;
+ int name_len = strlen(lock_name);
+ int old_cookie_len = strlen(old_cookie);
+ int tag_len = strlen(tag);
+ int new_cookie_len = strlen(new_cookie);
+ void *p, *end;
+ struct page *cookie_op_page;
+ int ret;
+
+ cookie_op_buf_size = name_len + sizeof(__le32) +
+ old_cookie_len + sizeof(__le32) +
+ tag_len + sizeof(__le32) +
+ new_cookie_len + sizeof(__le32) +
+ sizeof(u8) + CEPH_ENCODING_START_BLK_LEN;
+ if (cookie_op_buf_size > PAGE_SIZE)
+ return -E2BIG;
+
+ cookie_op_page = alloc_page(GFP_NOIO);
+ if (!cookie_op_page)
+ return -ENOMEM;
+
+ p = page_address(cookie_op_page);
+ end = p + cookie_op_buf_size;
+
+ /* encode cls_lock_set_cookie_op struct */
+ ceph_start_encoding(&p, 1, 1,
+ cookie_op_buf_size - CEPH_ENCODING_START_BLK_LEN);
+ ceph_encode_string(&p, end, lock_name, name_len);
+ ceph_encode_8(&p, type);
+ ceph_encode_string(&p, end, old_cookie, old_cookie_len);
+ ceph_encode_string(&p, end, tag, tag_len);
+ ceph_encode_string(&p, end, new_cookie, new_cookie_len);
+
+ dout("%s lock_name %s type %d old_cookie %s tag %s new_cookie %s\n",
+ __func__, lock_name, type, old_cookie, tag, new_cookie);
+ ret = ceph_osdc_call(osdc, oid, oloc, "lock", "set_cookie",
+ CEPH_OSD_FLAG_WRITE, cookie_op_page,
+ cookie_op_buf_size, NULL, NULL);
+
+ dout("%s: status %d\n", __func__, ret);
+ __free_page(cookie_op_page);
+ return ret;
+}
+EXPORT_SYMBOL(ceph_cls_set_cookie);
+
void ceph_free_lockers(struct ceph_locker *lockers, u32 num_lockers)
{
int i;
diff --git a/net/ceph/debugfs.c b/net/ceph/debugfs.c
index c62b2b029a6e..71ba13927b3d 100644
--- a/net/ceph/debugfs.c
+++ b/net/ceph/debugfs.c
@@ -62,7 +62,8 @@ static int osdmap_show(struct seq_file *s, void *p)
return 0;
down_read(&osdc->lock);
- seq_printf(s, "epoch %d flags 0x%x\n", map->epoch, map->flags);
+ seq_printf(s, "epoch %u barrier %u flags 0x%x\n", map->epoch,
+ osdc->epoch_barrier, map->flags);
for (n = rb_first(&map->pg_pools); n; n = rb_next(n)) {
struct ceph_pg_pool_info *pi =
@@ -177,9 +178,7 @@ static void dump_request(struct seq_file *s, struct ceph_osd_request *req)
seq_printf(s, "%llu\t", req->r_tid);
dump_target(s, &req->r_t);
- seq_printf(s, "\t%d\t%u'%llu", req->r_attempts,
- le32_to_cpu(req->r_replay_version.epoch),
- le64_to_cpu(req->r_replay_version.version));
+ seq_printf(s, "\t%d", req->r_attempts);
for (i = 0; i < req->r_num_ops; i++) {
struct ceph_osd_req_op *op = &req->r_ops[i];
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 242d7c0d92f8..924f07c36ddb 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -961,6 +961,7 @@ struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc,
truncate_size, truncate_seq);
}
+ req->r_abort_on_full = true;
req->r_flags = flags;
req->r_base_oloc.pool = layout->pool_id;
req->r_base_oloc.pool_ns = ceph_try_get_string(layout->pool_ns);
@@ -1005,7 +1006,7 @@ static bool osd_registered(struct ceph_osd *osd)
*/
static void osd_init(struct ceph_osd *osd)
{
- atomic_set(&osd->o_ref, 1);
+ refcount_set(&osd->o_ref, 1);
RB_CLEAR_NODE(&osd->o_node);
osd->o_requests = RB_ROOT;
osd->o_linger_requests = RB_ROOT;
@@ -1050,9 +1051,9 @@ static struct ceph_osd *create_osd(struct ceph_osd_client *osdc, int onum)
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));
+ 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));
return osd;
} else {
dout("get_osd %p FAIL\n", osd);
@@ -1062,9 +1063,9 @@ 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, atomic_read(&osd->o_ref),
- atomic_read(&osd->o_ref) - 1);
- if (atomic_dec_and_test(&osd->o_ref)) {
+ dout("put_osd %p %d -> %d\n", osd, refcount_read(&osd->o_ref),
+ refcount_read(&osd->o_ref) - 1);
+ if (refcount_dec_and_test(&osd->o_ref)) {
osd_cleanup(osd);
kfree(osd);
}
@@ -1297,8 +1298,9 @@ static bool target_should_be_paused(struct ceph_osd_client *osdc,
__pool_full(pi);
WARN_ON(pi->id != t->base_oloc.pool);
- return (t->flags & CEPH_OSD_FLAG_READ && pauserd) ||
- (t->flags & CEPH_OSD_FLAG_WRITE && pausewr);
+ return ((t->flags & CEPH_OSD_FLAG_READ) && pauserd) ||
+ ((t->flags & CEPH_OSD_FLAG_WRITE) && pausewr) ||
+ (osdc->osdmap->epoch < osdc->epoch_barrier);
}
enum calc_target_result {
@@ -1503,9 +1505,10 @@ static void encode_request(struct ceph_osd_request *req, struct ceph_msg *msg)
ceph_encode_32(&p, req->r_flags);
ceph_encode_timespec(p, &req->r_mtime);
p += sizeof(struct ceph_timespec);
- /* aka reassert_version */
- memcpy(p, &req->r_replay_version, sizeof(req->r_replay_version));
- p += sizeof(req->r_replay_version);
+
+ /* reassert_version */
+ memset(p, 0, sizeof(struct ceph_eversion));
+ p += sizeof(struct ceph_eversion);
/* oloc */
ceph_start_encoding(&p, 5, 4,
@@ -1626,6 +1629,7 @@ static void maybe_request_map(struct ceph_osd_client *osdc)
ceph_monc_renew_subs(&osdc->client->monc);
}
+static void complete_request(struct ceph_osd_request *req, int err);
static void send_map_check(struct ceph_osd_request *req);
static void __submit_request(struct ceph_osd_request *req, bool wrlocked)
@@ -1635,6 +1639,7 @@ static void __submit_request(struct ceph_osd_request *req, bool wrlocked)
enum calc_target_result ct_res;
bool need_send = false;
bool promoted = false;
+ bool need_abort = false;
WARN_ON(req->r_tid);
dout("%s req %p wrlocked %d\n", __func__, req, wrlocked);
@@ -1650,8 +1655,13 @@ again:
goto promote;
}
- if ((req->r_flags & CEPH_OSD_FLAG_WRITE) &&
- ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSEWR)) {
+ if (osdc->osdmap->epoch < osdc->epoch_barrier) {
+ dout("req %p epoch %u barrier %u\n", req, osdc->osdmap->epoch,
+ osdc->epoch_barrier);
+ req->r_t.paused = true;
+ maybe_request_map(osdc);
+ } else if ((req->r_flags & CEPH_OSD_FLAG_WRITE) &&
+ ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSEWR)) {
dout("req %p pausewr\n", req);
req->r_t.paused = true;
maybe_request_map(osdc);
@@ -1669,6 +1679,8 @@ again:
pr_warn_ratelimited("FULL or reached pool quota\n");
req->r_t.paused = true;
maybe_request_map(osdc);
+ if (req->r_abort_on_full)
+ need_abort = true;
} else if (!osd_homeless(osd)) {
need_send = true;
} else {
@@ -1685,6 +1697,8 @@ again:
link_request(osd, req);
if (need_send)
send_request(req);
+ else if (need_abort)
+ complete_request(req, -ENOSPC);
mutex_unlock(&osd->lock);
if (ct_res == CALC_TARGET_POOL_DNE)
@@ -1799,6 +1813,97 @@ static void abort_request(struct ceph_osd_request *req, int err)
complete_request(req, err);
}
+static void update_epoch_barrier(struct ceph_osd_client *osdc, u32 eb)
+{
+ if (likely(eb > osdc->epoch_barrier)) {
+ dout("updating epoch_barrier from %u to %u\n",
+ osdc->epoch_barrier, eb);
+ osdc->epoch_barrier = eb;
+ /* Request map if we're not to the barrier yet */
+ if (eb > osdc->osdmap->epoch)
+ maybe_request_map(osdc);
+ }
+}
+
+void ceph_osdc_update_epoch_barrier(struct ceph_osd_client *osdc, u32 eb)
+{
+ down_read(&osdc->lock);
+ if (unlikely(eb > osdc->epoch_barrier)) {
+ up_read(&osdc->lock);
+ down_write(&osdc->lock);
+ update_epoch_barrier(osdc, eb);
+ up_write(&osdc->lock);
+ } else {
+ up_read(&osdc->lock);
+ }
+}
+EXPORT_SYMBOL(ceph_osdc_update_epoch_barrier);
+
+/*
+ * Drop all pending requests that are stalled waiting on a full condition to
+ * clear, and complete them with ENOSPC as the return code. Set the
+ * osdc->epoch_barrier to the latest map epoch that we've seen if any were
+ * cancelled.
+ */
+static void ceph_osdc_abort_on_full(struct ceph_osd_client *osdc)
+{
+ struct rb_node *n;
+ bool victims = false;
+
+ dout("enter abort_on_full\n");
+
+ if (!ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL) && !have_pool_full(osdc))
+ goto out;
+
+ /* Scan list and see if there is anything to abort */
+ for (n = rb_first(&osdc->osds); n; n = rb_next(n)) {
+ struct ceph_osd *osd = rb_entry(n, struct ceph_osd, o_node);
+ struct rb_node *m;
+
+ m = rb_first(&osd->o_requests);
+ while (m) {
+ struct ceph_osd_request *req = rb_entry(m,
+ struct ceph_osd_request, r_node);
+ m = rb_next(m);
+
+ if (req->r_abort_on_full) {
+ victims = true;
+ break;
+ }
+ }
+ if (victims)
+ break;
+ }
+
+ if (!victims)
+ goto out;
+
+ /*
+ * Update the barrier to current epoch if it's behind that point,
+ * since we know we have some calls to be aborted in the tree.
+ */
+ update_epoch_barrier(osdc, osdc->osdmap->epoch);
+
+ for (n = rb_first(&osdc->osds); n; n = rb_next(n)) {
+ struct ceph_osd *osd = rb_entry(n, struct ceph_osd, o_node);
+ struct rb_node *m;
+
+ m = rb_first(&osd->o_requests);
+ while (m) {
+ struct ceph_osd_request *req = rb_entry(m,
+ struct ceph_osd_request, r_node);
+ m = rb_next(m);
+
+ if (req->r_abort_on_full &&
+ (ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL) ||
+ pool_full(osdc, req->r_t.target_oloc.pool)))
+ abort_request(req, -ENOSPC);
+ }
+ }
+out:
+ dout("return abort_on_full barrier=%u\n", osdc->epoch_barrier);
+}
+
static void check_pool_dne(struct ceph_osd_request *req)
{
struct ceph_osd_client *osdc = req->r_osdc;
@@ -3252,11 +3357,13 @@ done:
pausewr = ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSEWR) ||
ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL) ||
have_pool_full(osdc);
- if (was_pauserd || was_pausewr || pauserd || pausewr)
+ if (was_pauserd || was_pausewr || pauserd || pausewr ||
+ osdc->osdmap->epoch < osdc->epoch_barrier)
maybe_request_map(osdc);
kick_requests(osdc, &need_resend, &need_resend_linger);
+ ceph_osdc_abort_on_full(osdc);
ceph_monc_got_map(&osdc->client->monc, CEPH_SUB_OSDMAP,
osdc->osdmap->epoch);
up_write(&osdc->lock);
@@ -4126,7 +4233,7 @@ void ceph_osdc_stop(struct ceph_osd_client *osdc)
close_osd(osd);
}
up_write(&osdc->lock);
- WARN_ON(atomic_read(&osdc->homeless_osd.o_ref) != 1);
+ WARN_ON(refcount_read(&osdc->homeless_osd.o_ref) != 1);
osd_cleanup(&osdc->homeless_osd);
WARN_ON(!list_empty(&osdc->osd_lru));
diff --git a/net/ceph/pagelist.c b/net/ceph/pagelist.c
index 6864007e64fc..ce09f73be759 100644
--- a/net/ceph/pagelist.c
+++ b/net/ceph/pagelist.c
@@ -16,7 +16,7 @@ static void ceph_pagelist_unmap_tail(struct ceph_pagelist *pl)
void ceph_pagelist_release(struct ceph_pagelist *pl)
{
- if (!atomic_dec_and_test(&pl->refcnt))
+ if (!refcount_dec_and_test(&pl->refcnt))
return;
ceph_pagelist_unmap_tail(pl);
while (!list_empty(&pl->head)) {
diff --git a/net/ceph/snapshot.c b/net/ceph/snapshot.c
index 705414e78ae0..e14a5d038656 100644
--- a/net/ceph/snapshot.c
+++ b/net/ceph/snapshot.c
@@ -49,7 +49,7 @@ struct ceph_snap_context *ceph_create_snap_context(u32 snap_count,
if (!snapc)
return NULL;
- atomic_set(&snapc->nref, 1);
+ refcount_set(&snapc->nref, 1);
snapc->num_snaps = snap_count;
return snapc;
@@ -59,7 +59,7 @@ EXPORT_SYMBOL(ceph_create_snap_context);
struct ceph_snap_context *ceph_get_snap_context(struct ceph_snap_context *sc)
{
if (sc)
- atomic_inc(&sc->nref);
+ refcount_inc(&sc->nref);
return sc;
}
EXPORT_SYMBOL(ceph_get_snap_context);
@@ -68,7 +68,7 @@ void ceph_put_snap_context(struct ceph_snap_context *sc)
{
if (!sc)
return;
- if (atomic_dec_and_test(&sc->nref)) {
+ if (refcount_dec_and_test(&sc->nref)) {
/*printk(" deleting snap_context %p\n", sc);*/
kfree(sc);
}
generated by cgit v1.2.3 (git 2.39.1) at 2024-11-25 10:33:36 +0000