Merge tag 'ceph-for-4.11-rc2' of git://github.com/ceph/ceph-client

Pull ceph fixes from Ilya Dryomov:

 - a fix for the recently discovered misdirected requests bug present in
   jewel and later on the server side and all stable kernels

 - a fixup for -rc1 CRUSH changes

 - two usability enhancements: osd_request_timeout option and
   supported_features bus attribute.

* tag 'ceph-for-4.11-rc2' of git://github.com/ceph/ceph-client:
  libceph: osd_request_timeout option
  rbd: supported_features bus attribute
  libceph: don't set weight to IN when OSD is destroyed
  libceph: fix crush_decode() for older maps

Author: torvalds

drivers/block/rbd.c

@@ -120,10 +120,11 @@ static int atomic_dec_return_safe(atomic_t *v)
 
 /* Feature bits */
 
-#define RBD_FEATURE_LAYERING	(1<<0)
-#define RBD_FEATURE_STRIPINGV2	(1<<1)
-#define RBD_FEATURE_EXCLUSIVE_LOCK (1<<2)
-#define RBD_FEATURE_DATA_POOL (1<<7)
+#define RBD_FEATURE_LAYERING		(1ULL<<0)
+#define RBD_FEATURE_STRIPINGV2		(1ULL<<1)
+#define RBD_FEATURE_EXCLUSIVE_LOCK	(1ULL<<2)
+#define RBD_FEATURE_DATA_POOL		(1ULL<<7)
+
 #define RBD_FEATURES_ALL	(RBD_FEATURE_LAYERING |		\
 				 RBD_FEATURE_STRIPINGV2 |	\
 				 RBD_FEATURE_EXCLUSIVE_LOCK |	\
@@ -499,16 +500,23 @@ static bool rbd_is_lock_owner(struct rbd_device *rbd_dev)
 	return is_lock_owner;
 }
 
+static ssize_t rbd_supported_features_show(struct bus_type *bus, char *buf)
+{
+	return sprintf(buf, "0x%llx\n", RBD_FEATURES_SUPPORTED);
+}
+
 static BUS_ATTR(add, S_IWUSR, NULL, rbd_add);
 static BUS_ATTR(remove, S_IWUSR, NULL, rbd_remove);
 static BUS_ATTR(add_single_major, S_IWUSR, NULL, rbd_add_single_major);
 static BUS_ATTR(remove_single_major, S_IWUSR, NULL, rbd_remove_single_major);
+static BUS_ATTR(supported_features, S_IRUGO, rbd_supported_features_show, NULL);
 
 static struct attribute *rbd_bus_attrs[] = {
 	&bus_attr_add.attr,
 	&bus_attr_remove.attr,
 	&bus_attr_add_single_major.attr,
 	&bus_attr_remove_single_major.attr,
+	&bus_attr_supported_features.attr,
 	NULL,
 };
 

include/linux/ceph/libceph.h

@@ -48,6 +48,7 @@ struct ceph_options {
 	unsigned long mount_timeout;		/* jiffies */
 	unsigned long osd_idle_ttl;		/* jiffies */
 	unsigned long osd_keepalive_timeout;	/* jiffies */
+	unsigned long osd_request_timeout;	/* jiffies */
 
 	/*
 	 * any type that can't be simply compared or doesn't need need
@@ -68,6 +69,7 @@ struct ceph_options {
 #define CEPH_MOUNT_TIMEOUT_DEFAULT	msecs_to_jiffies(60 * 1000)
 #define CEPH_OSD_KEEPALIVE_DEFAULT	msecs_to_jiffies(5 * 1000)
 #define CEPH_OSD_IDLE_TTL_DEFAULT	msecs_to_jiffies(60 * 1000)
+#define CEPH_OSD_REQUEST_TIMEOUT_DEFAULT 0  /* no timeout */
 
 #define CEPH_MONC_HUNT_INTERVAL		msecs_to_jiffies(3 * 1000)
 #define CEPH_MONC_PING_INTERVAL		msecs_to_jiffies(10 * 1000)

include/linux/ceph/osd_client.h

@@ -189,6 +189,7 @@ struct ceph_osd_request {
 
 	/* internal */
 	unsigned long r_stamp;                /* jiffies, send or check time */
+	unsigned long r_start_stamp;          /* jiffies */
 	int r_attempts;
 	struct ceph_eversion r_replay_version; /* aka reassert_version */
 	u32 r_last_force_resend;

net/ceph/ceph_common.c

@@ -230,6 +230,7 @@ enum {
 	Opt_osdkeepalivetimeout,
 	Opt_mount_timeout,
 	Opt_osd_idle_ttl,
+	Opt_osd_request_timeout,
 	Opt_last_int,
 	/* int args above */
 	Opt_fsid,
@@ -256,6 +257,7 @@ static match_table_t opt_tokens = {
 	{Opt_osdkeepalivetimeout, "osdkeepalive=%d"},
 	{Opt_mount_timeout, "mount_timeout=%d"},
 	{Opt_osd_idle_ttl, "osd_idle_ttl=%d"},
+	{Opt_osd_request_timeout, "osd_request_timeout=%d"},
 	/* int args above */
 	{Opt_fsid, "fsid=%s"},
 	{Opt_name, "name=%s"},
@@ -361,6 +363,7 @@ ceph_parse_options(char *options, const char *dev_name,
 	opt->osd_keepalive_timeout = CEPH_OSD_KEEPALIVE_DEFAULT;
 	opt->mount_timeout = CEPH_MOUNT_TIMEOUT_DEFAULT;
 	opt->osd_idle_ttl = CEPH_OSD_IDLE_TTL_DEFAULT;
+	opt->osd_request_timeout = CEPH_OSD_REQUEST_TIMEOUT_DEFAULT;
 
 	/* get mon ip(s) */
 	/* ip1[:port1][,ip2[:port2]...] */
@@ -473,6 +476,15 @@ ceph_parse_options(char *options, const char *dev_name,
 			}
 			opt->mount_timeout = msecs_to_jiffies(intval * 1000);
 			break;
+		case Opt_osd_request_timeout:
+			/* 0 is "wait forever" (i.e. infinite timeout) */
+			if (intval < 0 || intval > INT_MAX / 1000) {
+				pr_err("osd_request_timeout out of range\n");
+				err = -EINVAL;
+				goto out;
+			}
+			opt->osd_request_timeout = msecs_to_jiffies(intval * 1000);
+			break;
 
 		case Opt_share:
 			opt->flags &= ~CEPH_OPT_NOSHARE;
@@ -557,6 +569,9 @@ int ceph_print_client_options(struct seq_file *m, struct ceph_client *client)
 	if (opt->osd_keepalive_timeout != CEPH_OSD_KEEPALIVE_DEFAULT)
 		seq_printf(m, "osdkeepalivetimeout=%d,",
 		    jiffies_to_msecs(opt->osd_keepalive_timeout) / 1000);
+	if (opt->osd_request_timeout != CEPH_OSD_REQUEST_TIMEOUT_DEFAULT)
+		seq_printf(m, "osd_request_timeout=%d,",
+			   jiffies_to_msecs(opt->osd_request_timeout) / 1000);
 
 	/* drop redundant comma */
 	if (m->count != pos)

net/ceph/osd_client.c

@@ -1709,6 +1709,8 @@ static void account_request(struct ceph_osd_request *req)
 
 	req->r_flags |= CEPH_OSD_FLAG_ONDISK;
 	atomic_inc(&req->r_osdc->num_requests);
+
+	req->r_start_stamp = jiffies;
 }
 
 static void submit_request(struct ceph_osd_request *req, bool wrlocked)
@@ -1789,6 +1791,14 @@ static void cancel_request(struct ceph_osd_request *req)
 	ceph_osdc_put_request(req);
 }
 
+static void abort_request(struct ceph_osd_request *req, int err)
+{
+	dout("%s req %p tid %llu err %d\n", __func__, req, req->r_tid, err);
+
+	cancel_map_check(req);
+	complete_request(req, err);
+}
+
 static void check_pool_dne(struct ceph_osd_request *req)
 {
 	struct ceph_osd_client *osdc = req->r_osdc;
@@ -2487,6 +2497,7 @@ static void handle_timeout(struct work_struct *work)
 		container_of(work, struct ceph_osd_client, timeout_work.work);
 	struct ceph_options *opts = osdc->client->options;
 	unsigned long cutoff = jiffies - opts->osd_keepalive_timeout;
+	unsigned long expiry_cutoff = jiffies - opts->osd_request_timeout;
 	LIST_HEAD(slow_osds);
 	struct rb_node *n, *p;
 
@@ -2502,15 +2513,23 @@ static void handle_timeout(struct work_struct *work)
 		struct ceph_osd *osd = rb_entry(n, struct ceph_osd, o_node);
 		bool found = false;
 
-		for (p = rb_first(&osd->o_requests); p; p = rb_next(p)) {
+		for (p = rb_first(&osd->o_requests); p; ) {
 			struct ceph_osd_request *req =
 			    rb_entry(p, struct ceph_osd_request, r_node);
 
+			p = rb_next(p); /* abort_request() */
+
 			if (time_before(req->r_stamp, cutoff)) {
 				dout(" req %p tid %llu on osd%d is laggy\n",
 				     req, req->r_tid, osd->o_osd);
 				found = true;
 			}
+			if (opts->osd_request_timeout &&
+			    time_before(req->r_start_stamp, expiry_cutoff)) {
+				pr_err_ratelimited("tid %llu on osd%d timeout\n",
+				       req->r_tid, osd->o_osd);
+				abort_request(req, -ETIMEDOUT);
+			}
 		}
 		for (p = rb_first(&osd->o_linger_requests); p; p = rb_next(p)) {
 			struct ceph_osd_linger_request *lreq =
@@ -2530,6 +2549,21 @@ static void handle_timeout(struct work_struct *work)
 			list_move_tail(&osd->o_keepalive_item, &slow_osds);
 	}
 
+	if (opts->osd_request_timeout) {
+		for (p = rb_first(&osdc->homeless_osd.o_requests); p; ) {
+			struct ceph_osd_request *req =
+			    rb_entry(p, struct ceph_osd_request, r_node);
+
+			p = rb_next(p); /* abort_request() */
+
+			if (time_before(req->r_start_stamp, expiry_cutoff)) {
+				pr_err_ratelimited("tid %llu on osd%d timeout\n",
+				       req->r_tid, osdc->homeless_osd.o_osd);
+				abort_request(req, -ETIMEDOUT);
+			}
+		}
+	}
+
 	if (atomic_read(&osdc->num_homeless) || !list_empty(&slow_osds))
 		maybe_request_map(osdc);
 

net/ceph/osdmap.c

@@ -390,9 +390,8 @@ static struct crush_map *crush_decode(void *pbyval, void *end)
 	dout("crush decode tunable chooseleaf_stable = %d\n",
 	     c->chooseleaf_stable);
 
-	crush_finalize(c);
-
 done:
+	crush_finalize(c);
 	dout("crush_decode success\n");
 	return c;
 
@@ -1380,7 +1379,6 @@ static int decode_new_up_state_weight(void **p, void *end,
 		if ((map->osd_state[osd] & CEPH_OSD_EXISTS) &&
 		    (xorstate & CEPH_OSD_EXISTS)) {
 			pr_info("osd%d does not exist\n", osd);
-			map->osd_weight[osd] = CEPH_OSD_IN;
 			ret = set_primary_affinity(map, osd,
 						   CEPH_OSD_DEFAULT_PRIMARY_AFFINITY);
 			if (ret)