4.18-stable patches

added patches:
	md-fix-invalid-stored-role-for-a-disk-try2.patch

diff --git a/queue-4.18/md-fix-invalid-stored-role-for-a-disk-try2.patch b/queue-4.18/md-fix-invalid-stored-role-for-a-disk-try2.patch
new file mode 100644 (file)
index 0000000..76b0060
--- /dev/null
+++ b/queue-4.18/md-fix-invalid-stored-role-for-a-disk-try2.patch
@@ -0,0 +1,58 @@
+From 9e753ba9b9b405e3902d9f08aec5f2ea58a0c317 Mon Sep 17 00:00:00 2001
+From: Shaohua Li <shli@fb.com>
+Date: Sun, 14 Oct 2018 17:05:07 -0700
+Subject: MD: fix invalid stored role for a disk - try2
+
+From: Shaohua Li <shli@fb.com>
+
+commit 9e753ba9b9b405e3902d9f08aec5f2ea58a0c317 upstream.
+
+Commit d595567dc4f0 (MD: fix invalid stored role for a disk) broke linear
+hotadd. Let's only fix the role for disks in raid1/10.
+Based on Guoqing's original patch.
+
+Reported-by: kernel test robot <rong.a.chen@intel.com>
+Cc: Gioh Kim <gi-oh.kim@profitbricks.com>
+Cc: Guoqing Jiang <gqjiang@suse.com>
+Signed-off-by: Shaohua Li <shli@fb.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ drivers/md/md.c     |    4 ----
+ drivers/md/raid1.c  |    1 +
+ drivers/md/raid10.c |    1 +
+ 3 files changed, 2 insertions(+), 4 deletions(-)
+
+--- a/drivers/md/md.c
++++ b/drivers/md/md.c
+@@ -1779,10 +1779,6 @@ static int super_1_validate(struct mddev
+                       } else
+                               set_bit(In_sync, &rdev->flags);
+                       rdev->raid_disk = role;
+-                      if (role >= mddev->raid_disks) {
+-                              rdev->saved_raid_disk = -1;
+-                              rdev->raid_disk = -1;
+-                      }
+                       break;
+               }
+               if (sb->devflags & WriteMostly1)
+--- a/drivers/md/raid1.c
++++ b/drivers/md/raid1.c
+@@ -1736,6 +1736,7 @@ static int raid1_add_disk(struct mddev *
+        */
+       if (rdev->saved_raid_disk >= 0 &&
+           rdev->saved_raid_disk >= first &&
++          rdev->saved_raid_disk < conf->raid_disks &&
+           conf->mirrors[rdev->saved_raid_disk].rdev == NULL)
+               first = last = rdev->saved_raid_disk;
+ 
+--- a/drivers/md/raid10.c
++++ b/drivers/md/raid10.c
+@@ -1808,6 +1808,7 @@ static int raid10_add_disk(struct mddev
+               first = last = rdev->raid_disk;
+ 
+       if (rdev->saved_raid_disk >= first &&
++          rdev->saved_raid_disk < conf->geo.raid_disks &&
+           conf->mirrors[rdev->saved_raid_disk].rdev == NULL)
+               mirror = rdev->saved_raid_disk;
+       else

diff --git a/queue-4.18/nvmet-rdma-use-a-private-workqueue-for-delete.patch b/queue-4.18/nvmet-rdma-use-a-private-workqueue-for-delete.patch
deleted file mode 100644 (file)
index 6347a06..0000000
--- a/queue-4.18/nvmet-rdma-use-a-private-workqueue-for-delete.patch
+++ /dev/null
@@ -1,158 +0,0 @@
-From foo@baz Sat Nov 10 10:48:43 PST 2018
-From: Sagi Grimberg <sagi@grimberg.me>
-Date: Thu, 27 Sep 2018 11:00:31 -0700
-Subject: nvmet-rdma: use a private workqueue for delete
-
-From: Sagi Grimberg <sagi@grimberg.me>
-
-[ Upstream commit 2acf70ade79d26b97611a8df52eb22aa33814cd4 ]
-
-Queue deletion is done asynchronous when the last reference on the queue
-is dropped.  Thus, in order to make sure we don't over allocate under a
-connect/disconnect storm, we let queue deletion complete before making
-forward progress.
-
-However, given that we flush the system_wq from rdma_cm context which
-runs from a workqueue context, we can have a circular locking complaint
-[1]. Fix that by using a private workqueue for queue deletion.
-
-[1]:
-======================================================
-WARNING: possible circular locking dependency detected
-4.19.0-rc4-dbg+ #3 Not tainted
-------------------------------------------------------
-kworker/5:0/39 is trying to acquire lock:
-00000000a10b6db9 (&id_priv->handler_mutex){+.+.}, at: rdma_destroy_id+0x6f/0x440 [rdma_cm]
-
-but task is already holding lock:
-00000000331b4e2c ((work_completion)(&queue->release_work)){+.+.}, at: process_one_work+0x3ed/0xa20
-
-which lock already depends on the new lock.
-
-the existing dependency chain (in reverse order) is:
-
--> #3 ((work_completion)(&queue->release_work)){+.+.}:
-       process_one_work+0x474/0xa20
-       worker_thread+0x63/0x5a0
-       kthread+0x1cf/0x1f0
-       ret_from_fork+0x24/0x30
-
--> #2 ((wq_completion)"events"){+.+.}:
-       flush_workqueue+0xf3/0x970
-       nvmet_rdma_cm_handler+0x133d/0x1734 [nvmet_rdma]
-       cma_ib_req_handler+0x72f/0xf90 [rdma_cm]
-       cm_process_work+0x2e/0x110 [ib_cm]
-       cm_req_handler+0x135b/0x1c30 [ib_cm]
-       cm_work_handler+0x2b7/0x38cd [ib_cm]
-       process_one_work+0x4ae/0xa20
-nvmet_rdma:nvmet_rdma_cm_handler: nvmet_rdma: disconnected (10): status 0 id 0000000040357082
-       worker_thread+0x63/0x5a0
-       kthread+0x1cf/0x1f0
-       ret_from_fork+0x24/0x30
-nvme nvme0: Reconnecting in 10 seconds...
-
--> #1 (&id_priv->handler_mutex/1){+.+.}:
-       __mutex_lock+0xfe/0xbe0
-       mutex_lock_nested+0x1b/0x20
-       cma_ib_req_handler+0x6aa/0xf90 [rdma_cm]
-       cm_process_work+0x2e/0x110 [ib_cm]
-       cm_req_handler+0x135b/0x1c30 [ib_cm]
-       cm_work_handler+0x2b7/0x38cd [ib_cm]
-       process_one_work+0x4ae/0xa20
-       worker_thread+0x63/0x5a0
-       kthread+0x1cf/0x1f0
-       ret_from_fork+0x24/0x30
-
--> #0 (&id_priv->handler_mutex){+.+.}:
-       lock_acquire+0xc5/0x200
-       __mutex_lock+0xfe/0xbe0
-       mutex_lock_nested+0x1b/0x20
-       rdma_destroy_id+0x6f/0x440 [rdma_cm]
-       nvmet_rdma_release_queue_work+0x8e/0x1b0 [nvmet_rdma]
-       process_one_work+0x4ae/0xa20
-       worker_thread+0x63/0x5a0
-       kthread+0x1cf/0x1f0
-       ret_from_fork+0x24/0x30
-
-Fixes: 777dc82395de ("nvmet-rdma: occasionally flush ongoing controller teardown")
-Reported-by: Bart Van Assche <bvanassche@acm.org>
-Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
-Tested-by: Bart Van Assche <bvanassche@acm.org>
-
-Signed-off-by: Christoph Hellwig <hch@lst.de>
-
-Signed-off-by: Sasha Levin <sashal@kernel.org>
-Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
----
- drivers/nvme/target/rdma.c |   19 +++++++++++++++----
- 1 file changed, 15 insertions(+), 4 deletions(-)
-
---- a/drivers/nvme/target/rdma.c
-+++ b/drivers/nvme/target/rdma.c
-@@ -119,6 +119,7 @@ struct nvmet_rdma_device {
-       struct list_head        entry;
- };
- 
-+struct workqueue_struct *nvmet_rdma_delete_wq;
- static bool nvmet_rdma_use_srq;
- module_param_named(use_srq, nvmet_rdma_use_srq, bool, 0444);
- MODULE_PARM_DESC(use_srq, "Use shared receive queue.");
-@@ -1169,12 +1170,12 @@ static int nvmet_rdma_queue_connect(stru
- 
-       if (queue->host_qid == 0) {
-               /* Let inflight controller teardown complete */
--              flush_scheduled_work();
-+              flush_workqueue(nvmet_rdma_delete_wq);
-       }
- 
-       ret = nvmet_rdma_cm_accept(cm_id, queue, &event->param.conn);
-       if (ret) {
--              schedule_work(&queue->release_work);
-+              queue_work(nvmet_rdma_delete_wq, &queue->release_work);
-               /* Destroying rdma_cm id is not needed here */
-               return 0;
-       }
-@@ -1239,7 +1240,7 @@ static void __nvmet_rdma_queue_disconnec
- 
-       if (disconnect) {
-               rdma_disconnect(queue->cm_id);
--              schedule_work(&queue->release_work);
-+              queue_work(nvmet_rdma_delete_wq, &queue->release_work);
-       }
- }
- 
-@@ -1269,7 +1270,7 @@ static void nvmet_rdma_queue_connect_fai
-       mutex_unlock(&nvmet_rdma_queue_mutex);
- 
-       pr_err("failed to connect queue %d\n", queue->idx);
--      schedule_work(&queue->release_work);
-+      queue_work(nvmet_rdma_delete_wq, &queue->release_work);
- }
- 
- /**
-@@ -1543,8 +1544,17 @@ static int __init nvmet_rdma_init(void)
-       if (ret)
-               goto err_ib_client;
- 
-+      nvmet_rdma_delete_wq = alloc_workqueue("nvmet-rdma-delete-wq",
-+                      WQ_UNBOUND | WQ_MEM_RECLAIM | WQ_SYSFS, 0);
-+      if (!nvmet_rdma_delete_wq) {
-+              ret = -ENOMEM;
-+              goto err_unreg_transport;
-+      }
-+
-       return 0;
- 
-+err_unreg_transport:
-+      nvmet_unregister_transport(&nvmet_rdma_ops);
- err_ib_client:
-       ib_unregister_client(&nvmet_rdma_ib_client);
-       return ret;
-@@ -1552,6 +1562,7 @@ err_ib_client:
- 
- static void __exit nvmet_rdma_exit(void)
- {
-+      destroy_workqueue(nvmet_rdma_delete_wq);
-       nvmet_unregister_transport(&nvmet_rdma_ops);
-       ib_unregister_client(&nvmet_rdma_ib_client);
-       WARN_ON_ONCE(!list_empty(&nvmet_rdma_queue_list));

diff --git a/queue-4.18/series b/queue-4.18/series
index 802e4583898cdbeb221ab49a71d36bd67817cbc2..9293ac6157a01621153a0aeaee5c136003c9ca45 100644 (file)
--- a/queue-4.18/series
+++ b/queue-4.18/series
@@ -87,7 +87,6 @@ iwlwifi-pcie-avoid-empty-free-rb-queue.patch
 iwlwifi-mvm-clear-hw_restart_requested-when-stopping-the-interface.patch
 iwlwifi-mvm-check-for-n_profiles-validity-in-ewrd-acpi.patch
 x86-olpc-indicate-that-legacy-pc-xo-1-platform-should-not-register-rtc.patch
-nvmet-rdma-use-a-private-workqueue-for-delete.patch
 acpi-pptt-handle-architecturally-unknown-cache-types.patch
 acpi-pm-lpit-register-sysfs-attributes-based-on-fadt.patch
 acpi-processor-fix-the-return-value-of-acpi_processor_ids_walk.patch
@@ -348,3 +347,4 @@ btrfs-fix-use-after-free-when-dumping-free-space.patch
 net-sched-remove-tca_options-from-policy.patch
 userns-also-map-extents-in-the-reverse-map-to-kernel-ids.patch
 bpf-wait-for-running-bpf-programs-when-updating-map-in-map.patch
+md-fix-invalid-stored-role-for-a-disk-try2.patch