--- /dev/null
+From 182b1917109892ab9f26d66bfdcbc4ba6f0a0a65 Mon Sep 17 00:00:00 2001
+From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= <toke@toke.dk>
+Date: Tue, 27 Feb 2018 19:09:44 +0200
+Subject: ath9k: Protect queue draining by rcu_read_lock()
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+From: Toke Høiland-Jørgensen <toke@toke.dk>
+
+commit 182b1917109892ab9f26d66bfdcbc4ba6f0a0a65 upstream.
+
+When ath9k was switched over to use the mac80211 intermediate queues,
+node cleanup now drains the mac80211 queues. However, this call path is
+not protected by rcu_read_lock() as it was previously entirely internal
+to the driver which uses its own locking.
+
+This leads to a possible rcu_dereference() without holding
+rcu_read_lock(); but only if a station is cleaned up while having
+packets queued on the TXQ. Fix this by adding the rcu_read_lock() to the
+caller in ath9k.
+
+Fixes: 50f08edf9809 ("ath9k: Switch to using mac80211 intermediate software queues.")
+Cc: stable@vger.kernel.org
+Reported-by: Ben Greear <greearb@candelatech.com>
+Signed-off-by: Toke Høiland-Jørgensen <toke@toke.dk>
+Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ drivers/net/wireless/ath/ath9k/xmit.c | 4 ++++
+ 1 file changed, 4 insertions(+)
+
+--- a/drivers/net/wireless/ath/ath9k/xmit.c
++++ b/drivers/net/wireless/ath/ath9k/xmit.c
+@@ -2892,6 +2892,8 @@ void ath_tx_node_cleanup(struct ath_soft
+ struct ath_txq *txq;
+ int tidno;
+
++ rcu_read_lock();
++
+ for (tidno = 0; tidno < IEEE80211_NUM_TIDS; tidno++) {
+ tid = ath_node_to_tid(an, tidno);
+ txq = tid->txq;
+@@ -2909,6 +2911,8 @@ void ath_tx_node_cleanup(struct ath_soft
+ if (!an->sta)
+ break; /* just one multicast ath_atx_tid */
+ }
++
++ rcu_read_unlock();
+ }
+
+ #ifdef CONFIG_ATH9K_TX99
--- /dev/null
+From bc6d65e6dc89c3b7ff78e4ad797117c122ffde8e Mon Sep 17 00:00:00 2001
+From: Tejun Heo <tj@kernel.org>
+Date: Mon, 2 Apr 2018 15:04:58 -0700
+Subject: blk-mq: Directly schedule q->timeout_work when aborting a request
+
+From: Tejun Heo <tj@kernel.org>
+
+commit bc6d65e6dc89c3b7ff78e4ad797117c122ffde8e upstream.
+
+Request abortion is performed by overriding deadline to now and
+scheduling timeout handling immediately. For the latter part, the
+code was using mod_timer(timeout, 0) which can't guarantee that the
+timer runs afterwards. Let's schedule the underlying work item
+directly instead.
+
+This fixes the hangs during probing reported by Sitsofe but it isn't
+yet clear to me how the failure can happen reliably if it's just the
+above described race condition.
+
+Signed-off-by: Tejun Heo <tj@kernel.org>
+Reported-by: Sitsofe Wheeler <sitsofe@gmail.com>
+Reported-by: Meelis Roos <mroos@linux.ee>
+Fixes: 358f70da49d7 ("blk-mq: make blk_abort_request() trigger timeout path")
+Cc: stable@vger.kernel.org # v4.16
+Link: http://lkml.kernel.org/r/CALjAwxh-PVYFnYFCJpGOja+m5SzZ8Sa4J7ohxdK=r8NyOF-EMA@mail.gmail.com
+Link: http://lkml.kernel.org/r/alpine.LRH.2.21.1802261049140.4893@math.ut.ee
+Signed-off-by: Jens Axboe <axboe@kernel.dk>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ block/blk-timeout.c | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+--- a/block/blk-timeout.c
++++ b/block/blk-timeout.c
+@@ -165,7 +165,7 @@ void blk_abort_request(struct request *r
+ * No need for fancy synchronizations.
+ */
+ blk_rq_set_deadline(req, jiffies);
+- mod_timer(&req->q->timeout, 0);
++ kblockd_schedule_work(&req->q->timeout_work);
+ } else {
+ if (blk_mark_rq_complete(req))
+ return;
--- /dev/null
+From bffa9909a6b48d8ca3398dec601bc9162a4020c4 Mon Sep 17 00:00:00 2001
+From: Ming Lei <ming.lei@redhat.com>
+Date: Sun, 8 Apr 2018 17:48:08 +0800
+Subject: blk-mq: don't keep offline CPUs mapped to hctx 0
+
+From: Ming Lei <ming.lei@redhat.com>
+
+commit bffa9909a6b48d8ca3398dec601bc9162a4020c4 upstream.
+
+From commit 4b855ad37194 ("blk-mq: Create hctx for each present CPU),
+blk-mq doesn't remap queue after CPU topo is changed, that said when
+some of these offline CPUs become online, they are still mapped to
+hctx 0, then hctx 0 may become the bottleneck of IO dispatch and
+completion.
+
+This patch sets up the mapping from the beginning, and aligns to
+queue mapping for PCI device (blk_mq_pci_map_queues()).
+
+Cc: Stefan Haberland <sth@linux.vnet.ibm.com>
+Cc: Keith Busch <keith.busch@intel.com>
+Cc: stable@vger.kernel.org
+Fixes: 4b855ad37194 ("blk-mq: Create hctx for each present CPU)
+Tested-by: Christian Borntraeger <borntraeger@de.ibm.com>
+Reviewed-by: Christoph Hellwig <hch@lst.de>
+Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
+Signed-off-by: Ming Lei <ming.lei@redhat.com>
+Signed-off-by: Jens Axboe <axboe@kernel.dk>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ block/blk-mq-cpumap.c | 5 -----
+ 1 file changed, 5 deletions(-)
+
+--- a/block/blk-mq-cpumap.c
++++ b/block/blk-mq-cpumap.c
+@@ -16,11 +16,6 @@
+
+ static int cpu_to_queue_index(unsigned int nr_queues, const int cpu)
+ {
+- /*
+- * Non present CPU will be mapped to queue index 0.
+- */
+- if (!cpu_present(cpu))
+- return 0;
+ return cpu % nr_queues;
+ }
+
--- /dev/null
+From a1c735fb790745f94a359df45c11df4a69760389 Mon Sep 17 00:00:00 2001
+From: Ming Lei <ming.lei@redhat.com>
+Date: Sun, 8 Apr 2018 17:48:07 +0800
+Subject: blk-mq: make sure that correct hctx->next_cpu is set
+
+From: Ming Lei <ming.lei@redhat.com>
+
+commit a1c735fb790745f94a359df45c11df4a69760389 upstream.
+
+From commit 20e4d81393196 (blk-mq: simplify queue mapping & schedule
+with each possisble CPU), one hctx can be mapped from all offline CPUs,
+then hctx->next_cpu can be set as wrong.
+
+This patch fixes this issue by making hctx->next_cpu pointing to the
+first CPU in hctx->cpumask if all CPUs in hctx->cpumask are offline.
+
+Cc: Stefan Haberland <sth@linux.vnet.ibm.com>
+Tested-by: Christian Borntraeger <borntraeger@de.ibm.com>
+Reviewed-by: Christoph Hellwig <hch@lst.de>
+Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
+Fixes: 20e4d81393196 ("blk-mq: simplify queue mapping & schedule with each possisble CPU")
+Cc: stable@vger.kernel.org
+Signed-off-by: Ming Lei <ming.lei@redhat.com>
+Signed-off-by: Jens Axboe <axboe@kernel.dk>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ block/blk-mq.c | 2 ++
+ 1 file changed, 2 insertions(+)
+
+--- a/block/blk-mq.c
++++ b/block/blk-mq.c
+@@ -2439,6 +2439,8 @@ static void blk_mq_map_swqueue(struct re
+ */
+ hctx->next_cpu = cpumask_first_and(hctx->cpumask,
+ cpu_online_mask);
++ if (hctx->next_cpu >= nr_cpu_ids)
++ hctx->next_cpu = cpumask_first(hctx->cpumask);
+ hctx->next_cpu_batch = BLK_MQ_CPU_WORK_BATCH;
+ }
+ }
--- /dev/null
+From 0bca799b92807ee9be0890690f5dde7d8c6a8e25 Mon Sep 17 00:00:00 2001
+From: Ming Lei <ming.lei@redhat.com>
+Date: Thu, 5 Apr 2018 00:35:21 +0800
+Subject: blk-mq: order getting budget and driver tag
+
+From: Ming Lei <ming.lei@redhat.com>
+
+commit 0bca799b92807ee9be0890690f5dde7d8c6a8e25 upstream.
+
+This patch orders getting budget and driver tag by making sure to acquire
+driver tag after budget is got, this way can help to avoid the following
+race:
+
+1) before dispatch request from scheduler queue, get one budget first, then
+dequeue a request, call it request A.
+
+2) in another IO path for dispatching request B which is from hctx->dispatch,
+driver tag is got, then try to get budget in blk_mq_dispatch_rq_list(),
+unfortunately the budget is held by request A.
+
+3) meantime blk_mq_dispatch_rq_list() is called for dispatching request
+A, and try to get driver tag first, unfortunately no driver tag is
+available because the driver tag is held by request B
+
+4) both two IO pathes can't move on, and IO stall is caused.
+
+This issue can be observed when running dbench on USB storage.
+
+This patch fixes this issue by always getting budget before getting
+driver tag.
+
+Cc: stable@vger.kernel.org
+Fixes: de1482974080ec9e ("blk-mq: introduce .get_budget and .put_budget in blk_mq_ops")
+Cc: Christoph Hellwig <hch@lst.de>
+Cc: Bart Van Assche <bart.vanassche@wdc.com>
+Cc: Omar Sandoval <osandov@fb.com>
+Signed-off-by: Ming Lei <ming.lei@redhat.com>
+Signed-off-by: Jens Axboe <axboe@kernel.dk>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ block/blk-mq.c | 21 ++++++++++-----------
+ 1 file changed, 10 insertions(+), 11 deletions(-)
+
+--- a/block/blk-mq.c
++++ b/block/blk-mq.c
+@@ -1188,7 +1188,12 @@ bool blk_mq_dispatch_rq_list(struct requ
+ struct blk_mq_queue_data bd;
+
+ rq = list_first_entry(list, struct request, queuelist);
+- if (!blk_mq_get_driver_tag(rq, &hctx, false)) {
++
++ hctx = blk_mq_map_queue(rq->q, rq->mq_ctx->cpu);
++ if (!got_budget && !blk_mq_get_dispatch_budget(hctx))
++ break;
++
++ if (!blk_mq_get_driver_tag(rq, NULL, false)) {
+ /*
+ * The initial allocation attempt failed, so we need to
+ * rerun the hardware queue when a tag is freed. The
+@@ -1197,8 +1202,7 @@ bool blk_mq_dispatch_rq_list(struct requ
+ * we'll re-run it below.
+ */
+ if (!blk_mq_mark_tag_wait(&hctx, rq)) {
+- if (got_budget)
+- blk_mq_put_dispatch_budget(hctx);
++ blk_mq_put_dispatch_budget(hctx);
+ /*
+ * For non-shared tags, the RESTART check
+ * will suffice.
+@@ -1209,11 +1213,6 @@ bool blk_mq_dispatch_rq_list(struct requ
+ }
+ }
+
+- if (!got_budget && !blk_mq_get_dispatch_budget(hctx)) {
+- blk_mq_put_driver_tag(rq);
+- break;
+- }
+-
+ list_del_init(&rq->queuelist);
+
+ bd.rq = rq;
+@@ -1812,11 +1811,11 @@ static blk_status_t __blk_mq_try_issue_d
+ if (q->elevator && !bypass_insert)
+ goto insert;
+
+- if (!blk_mq_get_driver_tag(rq, NULL, false))
++ if (!blk_mq_get_dispatch_budget(hctx))
+ goto insert;
+
+- if (!blk_mq_get_dispatch_budget(hctx)) {
+- blk_mq_put_driver_tag(rq);
++ if (!blk_mq_get_driver_tag(rq, NULL, false)) {
++ blk_mq_put_dispatch_budget(hctx);
+ goto insert;
+ }
+
--- /dev/null
+From 818e0fa293ca836eba515615c64680ea916fd7cd Mon Sep 17 00:00:00 2001
+From: Bart Van Assche <bart.vanassche@wdc.com>
+Date: Mon, 19 Mar 2018 11:46:13 -0700
+Subject: block: Change a rcu_read_{lock,unlock}_sched() pair into rcu_read_{lock,unlock}()
+
+From: Bart Van Assche <bart.vanassche@wdc.com>
+
+commit 818e0fa293ca836eba515615c64680ea916fd7cd upstream.
+
+scsi_device_quiesce() uses synchronize_rcu() to guarantee that the
+effect of blk_set_preempt_only() will be visible for percpu_ref_tryget()
+calls that occur after the queue unfreeze by using the approach
+explained in https://lwn.net/Articles/573497/. The rcu read lock and
+unlock calls in blk_queue_enter() form a pair with the synchronize_rcu()
+call in scsi_device_quiesce(). Both scsi_device_quiesce() and
+blk_queue_enter() must either use regular RCU or RCU-sched.
+Since neither the RCU-protected code in blk_queue_enter() nor
+blk_queue_usage_counter_release() sleeps, regular RCU protection
+is sufficient. Note: scsi_device_quiesce() does not have to be
+modified since it already uses synchronize_rcu().
+
+Reported-by: Tejun Heo <tj@kernel.org>
+Fixes: 3a0a529971ec ("block, scsi: Make SCSI quiesce and resume work reliably")
+Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
+Acked-by: Tejun Heo <tj@kernel.org>
+Cc: Tejun Heo <tj@kernel.org>
+Cc: Hannes Reinecke <hare@suse.com>
+Cc: Ming Lei <ming.lei@redhat.com>
+Cc: Christoph Hellwig <hch@lst.de>
+Cc: Johannes Thumshirn <jthumshirn@suse.de>
+Cc: Oleksandr Natalenko <oleksandr@natalenko.name>
+Cc: Martin Steigerwald <martin@lichtvoll.de>
+Cc: stable@vger.kernel.org # v4.15
+Signed-off-by: Jens Axboe <axboe@kernel.dk>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ block/blk-core.c | 4 ++--
+ 1 file changed, 2 insertions(+), 2 deletions(-)
+
+--- a/block/blk-core.c
++++ b/block/blk-core.c
+@@ -827,7 +827,7 @@ int blk_queue_enter(struct request_queue
+ bool success = false;
+ int ret;
+
+- rcu_read_lock_sched();
++ rcu_read_lock();
+ if (percpu_ref_tryget_live(&q->q_usage_counter)) {
+ /*
+ * The code that sets the PREEMPT_ONLY flag is
+@@ -840,7 +840,7 @@ int blk_queue_enter(struct request_queue
+ percpu_ref_put(&q->q_usage_counter);
+ }
+ }
+- rcu_read_unlock_sched();
++ rcu_read_unlock();
+
+ if (success)
+ return 0;
--- /dev/null
+From b94929d975c8423defc9aededb0f499ff936b509 Mon Sep 17 00:00:00 2001
+From: Yunlong Song <yunlong.song@huawei.com>
+Date: Mon, 29 Jan 2018 11:37:45 +0800
+Subject: f2fs: fix heap mode to reset it back
+
+From: Yunlong Song <yunlong.song@huawei.com>
+
+commit b94929d975c8423defc9aededb0f499ff936b509 upstream.
+
+Commit 7a20b8a61eff81bdb7097a578752a74860e9d142 ("f2fs: allocate node
+and hot data in the beginning of partition") introduces another mount
+option, heap, to reset it back. But it does not do anything for heap
+mode, so fix it.
+
+Cc: stable@vger.kernel.org
+Signed-off-by: Yunlong Song <yunlong.song@huawei.com>
+Reviewed-by: Chao Yu <yuchao0@huawei.com>
+Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ fs/f2fs/gc.c | 5 +++--
+ fs/f2fs/segment.c | 3 ++-
+ 2 files changed, 5 insertions(+), 3 deletions(-)
+
+--- a/fs/f2fs/gc.c
++++ b/fs/f2fs/gc.c
+@@ -191,8 +191,9 @@ static void select_policy(struct f2fs_sb
+ if (gc_type != FG_GC && p->max_search > sbi->max_victim_search)
+ p->max_search = sbi->max_victim_search;
+
+- /* let's select beginning hot/small space first */
+- if (type == CURSEG_HOT_DATA || IS_NODESEG(type))
++ /* let's select beginning hot/small space first in no_heap mode*/
++ if (test_opt(sbi, NOHEAP) &&
++ (type == CURSEG_HOT_DATA || IS_NODESEG(type)))
+ p->offset = 0;
+ else
+ p->offset = SIT_I(sbi)->last_victim[p->gc_mode];
+--- a/fs/f2fs/segment.c
++++ b/fs/f2fs/segment.c
+@@ -2164,7 +2164,8 @@ static unsigned int __get_next_segno(str
+ if (sbi->segs_per_sec != 1)
+ return CURSEG_I(sbi, type)->segno;
+
+- if (type == CURSEG_HOT_DATA || IS_NODESEG(type))
++ if (test_opt(sbi, NOHEAP) &&
++ (type == CURSEG_HOT_DATA || IS_NODESEG(type)))
+ return 0;
+
+ if (SIT_I(sbi)->last_victim[ALLOC_NEXT])
--- /dev/null
+From 5df63c2a149ae65a9ec239e7c2af44efa6f79beb Mon Sep 17 00:00:00 2001
+From: Mike Kravetz <mike.kravetz@oracle.com>
+Date: Thu, 5 Apr 2018 16:18:21 -0700
+Subject: hugetlbfs: fix bug in pgoff overflow checking
+
+From: Mike Kravetz <mike.kravetz@oracle.com>
+
+commit 5df63c2a149ae65a9ec239e7c2af44efa6f79beb upstream.
+
+This is a fix for a regression in 32 bit kernels caused by an invalid
+check for pgoff overflow in hugetlbfs mmap setup. The check incorrectly
+specified that the size of a loff_t was the same as the size of a long.
+The regression prevents mapping hugetlbfs files at offsets greater than
+4GB on 32 bit kernels.
+
+On 32 bit kernels conversion from a page based unsigned long can not
+overflow a loff_t byte offset. Therefore, skip this check if
+sizeof(unsigned long) != sizeof(loff_t).
+
+Link: http://lkml.kernel.org/r/20180330145402.5053-1-mike.kravetz@oracle.com
+Fixes: 63489f8e8211 ("hugetlbfs: check for pgoff value overflow")
+Reported-by: Dan Rue <dan.rue@linaro.org>
+Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com>
+Tested-by: Anders Roxell <anders.roxell@linaro.org>
+Cc: Michal Hocko <mhocko@kernel.org>
+Cc: Yisheng Xie <xieyisheng1@huawei.com>
+Cc: "Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>
+Cc: Nic Losby <blurbdust@gmail.com>
+Cc: <stable@vger.kernel.org>
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
+Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ fs/hugetlbfs/inode.c | 10 +++++++---
+ 1 file changed, 7 insertions(+), 3 deletions(-)
+
+--- a/fs/hugetlbfs/inode.c
++++ b/fs/hugetlbfs/inode.c
+@@ -138,10 +138,14 @@ static int hugetlbfs_file_mmap(struct fi
+
+ /*
+ * page based offset in vm_pgoff could be sufficiently large to
+- * overflow a (l)off_t when converted to byte offset.
++ * overflow a loff_t when converted to byte offset. This can
++ * only happen on architectures where sizeof(loff_t) ==
++ * sizeof(unsigned long). So, only check in those instances.
+ */
+- if (vma->vm_pgoff & PGOFF_LOFFT_MAX)
+- return -EINVAL;
++ if (sizeof(unsigned long) == sizeof(loff_t)) {
++ if (vma->vm_pgoff & PGOFF_LOFFT_MAX)
++ return -EINVAL;
++ }
+
+ /* must be huge page aligned */
+ if (vma->vm_pgoff & (~huge_page_mask(h) >> PAGE_SHIFT))
--- /dev/null
+From 8351760ff5b2042039554b4948ddabaac644a976 Mon Sep 17 00:00:00 2001
+From: Yury Norov <ynorov@caviumnetworks.com>
+Date: Thu, 5 Apr 2018 16:18:25 -0700
+Subject: lib: fix stall in __bitmap_parselist()
+
+From: Yury Norov <ynorov@caviumnetworks.com>
+
+commit 8351760ff5b2042039554b4948ddabaac644a976 upstream.
+
+syzbot is catching stalls at __bitmap_parselist()
+(https://syzkaller.appspot.com/bug?id=ad7e0351fbc90535558514a71cd3edc11681997a).
+The trigger is
+
+ unsigned long v = 0;
+ bitmap_parselist("7:,", &v, BITS_PER_LONG);
+
+which results in hitting infinite loop at
+
+ while (a <= b) {
+ off = min(b - a + 1, used_size);
+ bitmap_set(maskp, a, off);
+ a += group_size;
+ }
+
+due to used_size == group_size == 0.
+
+Link: http://lkml.kernel.org/r/20180404162647.15763-1-ynorov@caviumnetworks.com
+Fixes: 0a5ce0831d04382a ("lib/bitmap.c: make bitmap_parselist() thread-safe and much faster")
+Signed-off-by: Yury Norov <ynorov@caviumnetworks.com>
+Reported-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
+Reported-by: syzbot <syzbot+6887cbb011c8054e8a3d@syzkaller.appspotmail.com>
+Cc: Noam Camus <noamca@mellanox.com>
+Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk>
+Cc: Matthew Wilcox <mawilcox@microsoft.com>
+Cc: Mauro Carvalho Chehab <mchehab@kernel.org>
+Cc: <stable@vger.kernel.org>
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
+Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ lib/bitmap.c | 2 +-
+ lib/test_bitmap.c | 4 ++++
+ 2 files changed, 5 insertions(+), 1 deletion(-)
+
+--- a/lib/bitmap.c
++++ b/lib/bitmap.c
+@@ -607,7 +607,7 @@ static int __bitmap_parselist(const char
+ /* if no digit is after '-', it's wrong*/
+ if (at_start && in_range)
+ return -EINVAL;
+- if (!(a <= b) || !(used_size <= group_size))
++ if (!(a <= b) || group_size == 0 || !(used_size <= group_size))
+ return -EINVAL;
+ if (b >= nmaskbits)
+ return -ERANGE;
+--- a/lib/test_bitmap.c
++++ b/lib/test_bitmap.c
+@@ -255,6 +255,10 @@ static const struct test_bitmap_parselis
+ {-EINVAL, "-1", NULL, 8, 0},
+ {-EINVAL, "-0", NULL, 8, 0},
+ {-EINVAL, "10-1", NULL, 8, 0},
++ {-EINVAL, "0-31:", NULL, 8, 0},
++ {-EINVAL, "0-31:0", NULL, 8, 0},
++ {-EINVAL, "0-31:0/0", NULL, 8, 0},
++ {-EINVAL, "0-31:1/0", NULL, 8, 0},
+ {-EINVAL, "0-31:10/1", NULL, 8, 0},
+ };
+
--- /dev/null
+From 880a3a5325489a143269a8e172e7563ebf9897bc Mon Sep 17 00:00:00 2001
+From: "J. Bruce Fields" <bfields@redhat.com>
+Date: Wed, 21 Mar 2018 17:19:02 -0400
+Subject: nfsd: fix incorrect umasks
+
+From: J. Bruce Fields <bfields@redhat.com>
+
+commit 880a3a5325489a143269a8e172e7563ebf9897bc upstream.
+
+We're neglecting to clear the umask after it's set, which can cause a
+later unrelated rpc to (incorrectly) use the same umask if it happens to
+be processed by the same thread.
+
+There's a more subtle problem here too:
+
+An NFSv4 compound request is decoded all in one pass before any
+operations are executed.
+
+Currently we're setting current->fs->umask at the time we decode the
+compound. In theory a single compound could contain multiple creates
+each setting a umask. In that case we'd end up using whichever umask
+was passed in the *last* operation as the umask for all the creates,
+whether that was correct or not.
+
+So, we should just be saving the umask at decode time and waiting to set
+it until we actually process the corresponding operation.
+
+In practice it's unlikely any client would do multiple creates in a
+single compound. And even if it did they'd likely be from the same
+process (hence carry the same umask). So this is a little academic, but
+we should get it right anyway.
+
+Fixes: 47057abde515 (nfsd: add support for the umask attribute)
+Cc: stable@vger.kernel.org
+Reported-by: Lucash Stach <l.stach@pengutronix.de>
+Signed-off-by: J. Bruce Fields <bfields@redhat.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ fs/nfsd/nfs4proc.c | 12 ++++++++++--
+ fs/nfsd/nfs4xdr.c | 8 +++-----
+ fs/nfsd/xdr4.h | 2 ++
+ 3 files changed, 15 insertions(+), 7 deletions(-)
+
+--- a/fs/nfsd/nfs4proc.c
++++ b/fs/nfsd/nfs4proc.c
+@@ -32,6 +32,7 @@
+ * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
++#include <linux/fs_struct.h>
+ #include <linux/file.h>
+ #include <linux/falloc.h>
+ #include <linux/slab.h>
+@@ -252,11 +253,13 @@ do_open_lookup(struct svc_rqst *rqstp, s
+ * Note: create modes (UNCHECKED,GUARDED...) are the same
+ * in NFSv4 as in v3 except EXCLUSIVE4_1.
+ */
++ current->fs->umask = open->op_umask;
+ status = do_nfsd_create(rqstp, current_fh, open->op_fname.data,
+ open->op_fname.len, &open->op_iattr,
+ *resfh, open->op_createmode,
+ (u32 *)open->op_verf.data,
+ &open->op_truncate, &open->op_created);
++ current->fs->umask = 0;
+
+ if (!status && open->op_label.len)
+ nfsd4_security_inode_setsecctx(*resfh, &open->op_label, open->op_bmval);
+@@ -603,6 +606,7 @@ nfsd4_create(struct svc_rqst *rqstp, str
+ if (status)
+ return status;
+
++ current->fs->umask = create->cr_umask;
+ switch (create->cr_type) {
+ case NF4LNK:
+ status = nfsd_symlink(rqstp, &cstate->current_fh,
+@@ -611,20 +615,22 @@ nfsd4_create(struct svc_rqst *rqstp, str
+ break;
+
+ case NF4BLK:
++ status = nfserr_inval;
+ rdev = MKDEV(create->cr_specdata1, create->cr_specdata2);
+ if (MAJOR(rdev) != create->cr_specdata1 ||
+ MINOR(rdev) != create->cr_specdata2)
+- return nfserr_inval;
++ goto out_umask;
+ status = nfsd_create(rqstp, &cstate->current_fh,
+ create->cr_name, create->cr_namelen,
+ &create->cr_iattr, S_IFBLK, rdev, &resfh);
+ break;
+
+ case NF4CHR:
++ status = nfserr_inval;
+ rdev = MKDEV(create->cr_specdata1, create->cr_specdata2);
+ if (MAJOR(rdev) != create->cr_specdata1 ||
+ MINOR(rdev) != create->cr_specdata2)
+- return nfserr_inval;
++ goto out_umask;
+ status = nfsd_create(rqstp, &cstate->current_fh,
+ create->cr_name, create->cr_namelen,
+ &create->cr_iattr,S_IFCHR, rdev, &resfh);
+@@ -668,6 +674,8 @@ nfsd4_create(struct svc_rqst *rqstp, str
+ fh_dup2(&cstate->current_fh, &resfh);
+ out:
+ fh_put(&resfh);
++out_umask:
++ current->fs->umask = 0;
+ return status;
+ }
+
+--- a/fs/nfsd/nfs4xdr.c
++++ b/fs/nfsd/nfs4xdr.c
+@@ -33,7 +33,6 @@
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+-#include <linux/fs_struct.h>
+ #include <linux/file.h>
+ #include <linux/slab.h>
+ #include <linux/namei.h>
+@@ -682,7 +681,7 @@ nfsd4_decode_create(struct nfsd4_compoun
+
+ status = nfsd4_decode_fattr(argp, create->cr_bmval, &create->cr_iattr,
+ &create->cr_acl, &create->cr_label,
+- ¤t->fs->umask);
++ &create->cr_umask);
+ if (status)
+ goto out;
+
+@@ -927,7 +926,6 @@ nfsd4_decode_open(struct nfsd4_compounda
+ case NFS4_OPEN_NOCREATE:
+ break;
+ case NFS4_OPEN_CREATE:
+- current->fs->umask = 0;
+ READ_BUF(4);
+ open->op_createmode = be32_to_cpup(p++);
+ switch (open->op_createmode) {
+@@ -935,7 +933,7 @@ nfsd4_decode_open(struct nfsd4_compounda
+ case NFS4_CREATE_GUARDED:
+ status = nfsd4_decode_fattr(argp, open->op_bmval,
+ &open->op_iattr, &open->op_acl, &open->op_label,
+- ¤t->fs->umask);
++ &open->op_umask);
+ if (status)
+ goto out;
+ break;
+@@ -950,7 +948,7 @@ nfsd4_decode_open(struct nfsd4_compounda
+ COPYMEM(open->op_verf.data, NFS4_VERIFIER_SIZE);
+ status = nfsd4_decode_fattr(argp, open->op_bmval,
+ &open->op_iattr, &open->op_acl, &open->op_label,
+- ¤t->fs->umask);
++ &open->op_umask);
+ if (status)
+ goto out;
+ break;
+--- a/fs/nfsd/xdr4.h
++++ b/fs/nfsd/xdr4.h
+@@ -118,6 +118,7 @@ struct nfsd4_create {
+ } u;
+ u32 cr_bmval[3]; /* request */
+ struct iattr cr_iattr; /* request */
++ int cr_umask; /* request */
+ struct nfsd4_change_info cr_cinfo; /* response */
+ struct nfs4_acl *cr_acl;
+ struct xdr_netobj cr_label;
+@@ -228,6 +229,7 @@ struct nfsd4_open {
+ u32 op_why_no_deleg; /* response - DELEG_NONE_EXT only */
+ u32 op_create; /* request */
+ u32 op_createmode; /* request */
++ int op_umask; /* request */
+ u32 op_bmval[3]; /* request */
+ struct iattr op_iattr; /* UNCHECKED4, GUARDED4, EXCLUSIVE4_1 */
+ nfs4_verifier op_verf __attribute__((aligned(32)));
--- /dev/null
+From 2079699c10c8c60a9572540c2f77d045abf036eb Mon Sep 17 00:00:00 2001
+From: Keith Busch <keith.busch@intel.com>
+Date: Mon, 19 Mar 2018 10:53:50 -0600
+Subject: nvme: Skip checking heads without namespaces
+
+From: Keith Busch <keith.busch@intel.com>
+
+commit 2079699c10c8c60a9572540c2f77d045abf036eb upstream.
+
+If a task is holding a reference to a namespace on a removed controller,
+the head will not be released. If the same controller is added again
+later, its namespaces may not be successfully added. Instead, the user
+will see kernel message "Duplicate IDs for nsid <X>".
+
+This patch fixes that by skipping heads that don't have namespaces when
+considering if a new namespace is safe to add.
+
+Reported-by: Alex Gagniuc <Alex_Gagniuc@Dellteam.com>
+Cc: stable@vger.kernel.org
+Signed-off-by: Keith Busch <keith.busch@intel.com>
+Reviewed-by: Max Gurtovoy <maxg@mellanox.com>
+Reviewed-by: Christoph Hellwig <hch@lst.de>
+Signed-off-by: Jens Axboe <axboe@kernel.dk>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ drivers/nvme/host/core.c | 1 +
+ 1 file changed, 1 insertion(+)
+
+--- a/drivers/nvme/host/core.c
++++ b/drivers/nvme/host/core.c
+@@ -2793,6 +2793,7 @@ static int __nvme_check_ids(struct nvme_
+
+ list_for_each_entry(h, &subsys->nsheads, entry) {
+ if (nvme_ns_ids_valid(&new->ids) &&
++ !list_empty(&h->list) &&
+ nvme_ns_ids_equal(&new->ids, &h->ids))
+ return -EINVAL;
+ }
--- /dev/null
+From 3ec9b3fafcaf441cc4d46b9742cd6ec0c79f8df0 Mon Sep 17 00:00:00 2001
+From: Amir Goldstein <amir73il@gmail.com>
+Date: Mon, 12 Mar 2018 10:30:41 -0400
+Subject: ovl: fix lookup with middle layer opaque dir and absolute path redirects
+
+From: Amir Goldstein <amir73il@gmail.com>
+
+commit 3ec9b3fafcaf441cc4d46b9742cd6ec0c79f8df0 upstream.
+
+As of now if we encounter an opaque dir while looking for a dentry, we set
+d->last=true. This means that there is no need to look further in any of
+the lower layers. This works fine as long as there are no redirets or
+relative redircts. But what if there is an absolute redirect on the
+children dentry of opaque directory. We still need to continue to look into
+next lower layer. This patch fixes it.
+
+Here is an example to demonstrate the issue. Say you have following setup.
+
+upper: /redirect (redirect=/a/b/c)
+lower1: /a/[b]/c ([b] is opaque) (c has absolute redirect=/a/b/d/)
+lower0: /a/b/d/foo
+
+Now "redirect" dir should merge with lower1:/a/b/c/ and lower0:/a/b/d.
+Note, despite the fact lower1:/a/[b] is opaque, we need to continue to look
+into lower0 because children c has an absolute redirect.
+
+Following is a reproducer.
+
+Watch me make foo disappear:
+
+ $ mkdir lower middle upper work work2 merged
+ $ mkdir lower/origin
+ $ touch lower/origin/foo
+ $ mount -t overlay none merged/ \
+ -olowerdir=lower,upperdir=middle,workdir=work2
+ $ mkdir merged/pure
+ $ mv merged/origin merged/pure/redirect
+ $ umount merged
+ $ mount -t overlay none merged/ \
+ -olowerdir=middle:lower,upperdir=upper,workdir=work
+ $ mv merged/pure/redirect merged/redirect
+
+Now you see foo inside a twice redirected merged dir:
+
+ $ ls merged/redirect
+ foo
+ $ umount merged
+ $ mount -t overlay none merged/ \
+ -olowerdir=middle:lower,upperdir=upper,workdir=work
+
+After mount cycle you don't see foo inside the same dir:
+
+ $ ls merged/redirect
+
+During middle layer lookup, the opaqueness of middle/pure is left in
+the lookup state and then middle/pure/redirect is wrongly treated as
+opaque.
+
+Fixes: 02b69b284cd7 ("ovl: lookup redirects")
+Cc: <stable@vger.kernel.org> #v4.10
+Signed-off-by: Amir Goldstein <amir73il@gmail.com>
+Signed-off-by: Vivek Goyal <vgoyal@redhat.com>
+Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ fs/overlayfs/namei.c | 9 +++++++++
+ 1 file changed, 9 insertions(+)
+
+--- a/fs/overlayfs/namei.c
++++ b/fs/overlayfs/namei.c
+@@ -56,6 +56,15 @@ static int ovl_check_redirect(struct den
+ if (s == next)
+ goto invalid;
+ }
++ /*
++ * One of the ancestor path elements in an absolute path
++ * lookup in ovl_lookup_layer() could have been opaque and
++ * that will stop further lookup in lower layers (d->stop=true)
++ * But we have found an absolute redirect in decendant path
++ * element and that should force continue lookup in lower
++ * layers (reset d->stop).
++ */
++ d->stop = false;
+ } else {
+ if (strchr(buf, '/') != NULL)
+ goto invalid;
--- /dev/null
+From 452061fd4521b2bf3225fc391dbe536e5f9c05e2 Mon Sep 17 00:00:00 2001
+From: Vivek Goyal <vgoyal@redhat.com>
+Date: Fri, 9 Mar 2018 15:44:41 -0500
+Subject: ovl: Set d->last properly during lookup
+
+From: Vivek Goyal <vgoyal@redhat.com>
+
+commit 452061fd4521b2bf3225fc391dbe536e5f9c05e2 upstream.
+
+d->last signifies that this is the last layer we are looking into and there
+is no more. And that means this allows for some optimzation opportunities
+during lookup. For example, in ovl_lookup_single() we don't have to check
+for opaque xattr of a directory is this is the last layer we are looking
+into (d->last = true).
+
+But knowing for sure whether we are looking into last layer can be very
+tricky. If redirects are not enabled, then we can look at poe->numlower and
+figure out if the lookup we are about to is last layer or not. But if
+redircts are enabled then it is possible poe->numlower suggests that we are
+looking in last layer, but there is an absolute redirect present in found
+element and that redirects us to a layer in root and that means lookup will
+continue in lower layers further.
+
+For example, consider following.
+
+/upperdir/pure (opaque=y)
+/upperdir/pure/foo (opaque=y,redirect=/bar)
+/lowerdir/bar
+
+In this case pure is "pure upper". When we look for "foo", that time
+poe->numlower=0. But that alone does not mean that we will not search for a
+merge candidate in /lowerdir. Absolute redirect changes that.
+
+IOW, d->last should not be set just based on poe->numlower if redirects are
+enabled. That can lead to setting d->last while it should not have and that
+means we will not check for opaque xattr while we should have.
+
+So do this.
+
+ - If redirects are not enabled, then continue to rely on poe->numlower
+ information to determine if it is last layer or not.
+
+ - If redirects are enabled, then set d->last = true only if this is the
+ last layer in root ovl_entry (roe).
+
+Suggested-by: Amir Goldstein <amir73il@gmail.com>
+Reviewed-by: Amir Goldstein <amir73il@gmail.com>
+Signed-off-by: Vivek Goyal <vgoyal@redhat.com>
+Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
+Fixes: 02b69b284cd7 ("ovl: lookup redirects")
+Cc: <stable@vger.kernel.org> #v4.10
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ fs/overlayfs/namei.c | 8 ++++++--
+ 1 file changed, 6 insertions(+), 2 deletions(-)
+
+--- a/fs/overlayfs/namei.c
++++ b/fs/overlayfs/namei.c
+@@ -815,7 +815,7 @@ struct dentry *ovl_lookup(struct inode *
+ .is_dir = false,
+ .opaque = false,
+ .stop = false,
+- .last = !poe->numlower,
++ .last = ofs->config.redirect_follow ? false : !poe->numlower,
+ .redirect = NULL,
+ };
+
+@@ -873,7 +873,11 @@ struct dentry *ovl_lookup(struct inode *
+ for (i = 0; !d.stop && i < poe->numlower; i++) {
+ struct ovl_path lower = poe->lowerstack[i];
+
+- d.last = i == poe->numlower - 1;
++ if (!ofs->config.redirect_follow)
++ d.last = i == poe->numlower - 1;
++ else
++ d.last = lower.layer->idx == roe->numlower;
++
+ err = ovl_lookup_layer(lower.dentry, &d, &this);
+ if (err)
+ goto out_put;
--- /dev/null
+From 695b46e76b62447e506cddc87e088236498008e5 Mon Sep 17 00:00:00 2001
+From: Amir Goldstein <amir73il@gmail.com>
+Date: Thu, 15 Mar 2018 23:39:01 +0200
+Subject: ovl: set i_ino to the value of st_ino for NFS export
+
+From: Amir Goldstein <amir73il@gmail.com>
+
+commit 695b46e76b62447e506cddc87e088236498008e5 upstream.
+
+Eddie Horng reported that readdir of an overlayfs directory that
+was exported via NFSv3 returns entries with d_type set to DT_UNKNOWN.
+The reason is that while preparing the response for readdirplus, nfsd
+checks inside encode_entryplus_baggage() that a child dentry's inode
+number matches the value of d_ino returns by overlayfs readdir iterator.
+
+Because the overlayfs inodes use arbitrary inode numbers that are not
+correlated with the values of st_ino/d_ino, NFSv3 falls back to not
+encoding d_type. Although this is an allowed behavior, we can fix it for
+the case of all overlayfs layers on the same underlying filesystem.
+
+When NFS export is enabled and d_ino is consistent with st_ino
+(samefs), set the same value also to i_ino in ovl_fill_inode() for all
+overlayfs inodes, nfsd readdirplus sanity checks will pass.
+ovl_fill_inode() may be called from ovl_new_inode(), before real inode
+was created with ino arg 0. In that case, i_ino will be updated to real
+upper inode i_ino on ovl_inode_init() or ovl_inode_update().
+
+Reported-by: Eddie Horng <eddiehorng.tw@gmail.com>
+Tested-by: Eddie Horng <eddiehorng.tw@gmail.com>
+Signed-off-by: Amir Goldstein <amir73il@gmail.com>
+Fixes: 8383f1748829 ("ovl: wire up NFS export operations")
+Cc: <stable@vger.kernel.org> #v4.16
+Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ fs/overlayfs/inode.c | 21 +++++++++++++++++----
+ fs/overlayfs/util.c | 8 +++++++-
+ 2 files changed, 24 insertions(+), 5 deletions(-)
+
+--- a/fs/overlayfs/inode.c
++++ b/fs/overlayfs/inode.c
+@@ -459,9 +459,20 @@ static inline void ovl_lockdep_annotate_
+ #endif
+ }
+
+-static void ovl_fill_inode(struct inode *inode, umode_t mode, dev_t rdev)
++static void ovl_fill_inode(struct inode *inode, umode_t mode, dev_t rdev,
++ unsigned long ino)
+ {
+- inode->i_ino = get_next_ino();
++ /*
++ * When NFS export is enabled and d_ino is consistent with st_ino
++ * (samefs), set the same value to i_ino, because nfsd readdirplus
++ * compares d_ino values to i_ino values of child entries. When called
++ * from ovl_new_inode(), ino arg is 0, so i_ino will be updated to real
++ * upper inode i_ino on ovl_inode_init() or ovl_inode_update().
++ */
++ if (inode->i_sb->s_export_op && ovl_same_sb(inode->i_sb))
++ inode->i_ino = ino;
++ else
++ inode->i_ino = get_next_ino();
+ inode->i_mode = mode;
+ inode->i_flags |= S_NOCMTIME;
+ #ifdef CONFIG_FS_POSIX_ACL
+@@ -597,7 +608,7 @@ struct inode *ovl_new_inode(struct super
+
+ inode = new_inode(sb);
+ if (inode)
+- ovl_fill_inode(inode, mode, rdev);
++ ovl_fill_inode(inode, mode, rdev, 0);
+
+ return inode;
+ }
+@@ -710,6 +721,7 @@ struct inode *ovl_get_inode(struct super
+ struct inode *inode;
+ bool bylower = ovl_hash_bylower(sb, upperdentry, lowerdentry, index);
+ bool is_dir;
++ unsigned long ino = 0;
+
+ if (!realinode)
+ realinode = d_inode(lowerdentry);
+@@ -748,13 +760,14 @@ struct inode *ovl_get_inode(struct super
+ if (!is_dir)
+ nlink = ovl_get_nlink(lowerdentry, upperdentry, nlink);
+ set_nlink(inode, nlink);
++ ino = key->i_ino;
+ } else {
+ /* Lower hardlink that will be broken on copy up */
+ inode = new_inode(sb);
+ if (!inode)
+ goto out_nomem;
+ }
+- ovl_fill_inode(inode, realinode->i_mode, realinode->i_rdev);
++ ovl_fill_inode(inode, realinode->i_mode, realinode->i_rdev, ino);
+ ovl_inode_init(inode, upperdentry, lowerdentry);
+
+ if (upperdentry && ovl_is_impuredir(upperdentry))
+--- a/fs/overlayfs/util.c
++++ b/fs/overlayfs/util.c
+@@ -279,12 +279,16 @@ void ovl_dentry_set_redirect(struct dent
+ void ovl_inode_init(struct inode *inode, struct dentry *upperdentry,
+ struct dentry *lowerdentry)
+ {
++ struct inode *realinode = d_inode(upperdentry ?: lowerdentry);
++
+ if (upperdentry)
+ OVL_I(inode)->__upperdentry = upperdentry;
+ if (lowerdentry)
+ OVL_I(inode)->lower = igrab(d_inode(lowerdentry));
+
+- ovl_copyattr(d_inode(upperdentry ?: lowerdentry), inode);
++ ovl_copyattr(realinode, inode);
++ if (!inode->i_ino)
++ inode->i_ino = realinode->i_ino;
+ }
+
+ void ovl_inode_update(struct inode *inode, struct dentry *upperdentry)
+@@ -299,6 +303,8 @@ void ovl_inode_update(struct inode *inod
+ smp_wmb();
+ OVL_I(inode)->__upperdentry = upperdentry;
+ if (inode_unhashed(inode)) {
++ if (!inode->i_ino)
++ inode->i_ino = upperinode->i_ino;
+ inode->i_private = upperinode;
+ __insert_inode_hash(inode, (unsigned long) upperinode);
+ }
--- /dev/null
+From 9f99e50d460ac7fd5f6c9b97aad0088c28c8656d Mon Sep 17 00:00:00 2001
+From: Amir Goldstein <amir73il@gmail.com>
+Date: Wed, 11 Apr 2018 20:09:29 +0300
+Subject: ovl: set lower layer st_dev only if setting lower st_ino
+
+From: Amir Goldstein <amir73il@gmail.com>
+
+commit 9f99e50d460ac7fd5f6c9b97aad0088c28c8656d upstream.
+
+For broken hardlinks, we do not return lower st_ino, so we should
+also not return lower pseudo st_dev.
+
+Fixes: a0c5ad307ac0 ("ovl: relax same fs constraint for constant st_ino")
+Cc: <stable@vger.kernel.org> #v4.15
+Signed-off-by: Amir Goldstein <amir73il@gmail.com>
+Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ fs/overlayfs/inode.c | 7 ++-----
+ 1 file changed, 2 insertions(+), 5 deletions(-)
+
+--- a/fs/overlayfs/inode.c
++++ b/fs/overlayfs/inode.c
+@@ -118,13 +118,10 @@ int ovl_getattr(const struct path *path,
+ */
+ if (ovl_test_flag(OVL_INDEX, d_inode(dentry)) ||
+ (!ovl_verify_lower(dentry->d_sb) &&
+- (is_dir || lowerstat.nlink == 1)))
++ (is_dir || lowerstat.nlink == 1))) {
+ stat->ino = lowerstat.ino;
+-
+- if (samefs)
+- WARN_ON_ONCE(stat->dev != lowerstat.dev);
+- else
+ stat->dev = ovl_get_pseudo_dev(dentry);
++ }
+ }
+ if (samefs) {
+ /*
x86-mce-amd-pass-the-bank-number-to-smca_get_bank_type.patch
x86-mce-amd-edac-mce_amd-enumerate-reserved-smca-bank-type.patch
x86-mce-amd-get-address-from-already-initialized-block.patch
+ath9k-protect-queue-draining-by-rcu_read_lock.patch
+x86-uapi-fix-asm-bootparam.h-userspace-compilation-errors.patch
+x86-apic-fix-signedness-bug-in-apic-id-validity-checks.patch
+sunrpc-remove-incorrect-hmac-request-initialization.patch
+f2fs-fix-heap-mode-to-reset-it-back.patch
+block-change-a-rcu_read_-lock-unlock-_sched-pair-into-rcu_read_-lock-unlock.patch
+nvme-skip-checking-heads-without-namespaces.patch
+lib-fix-stall-in-__bitmap_parselist.patch
+zboot-fix-stack-protector-in-compressed-boot-phase.patch
+blk-mq-directly-schedule-q-timeout_work-when-aborting-a-request.patch
+blk-mq-order-getting-budget-and-driver-tag.patch
+blk-mq-make-sure-that-correct-hctx-next_cpu-is-set.patch
+blk-mq-don-t-keep-offline-cpus-mapped-to-hctx-0.patch
+ovl-set-d-last-properly-during-lookup.patch
+ovl-fix-lookup-with-middle-layer-opaque-dir-and-absolute-path-redirects.patch
+ovl-set-i_ino-to-the-value-of-st_ino-for-nfs-export.patch
+ovl-set-lower-layer-st_dev-only-if-setting-lower-st_ino.patch
+xen-xenbus_dev_frontend-fix-xs_transaction_end-handling.patch
+hugetlbfs-fix-bug-in-pgoff-overflow-checking.patch
+nfsd-fix-incorrect-umasks.patch
--- /dev/null
+From f3aefb6a7066e24bfea7fcf1b07907576de69d63 Mon Sep 17 00:00:00 2001
+From: Eric Biggers <ebiggers@google.com>
+Date: Wed, 28 Mar 2018 10:57:22 -0700
+Subject: sunrpc: remove incorrect HMAC request initialization
+
+From: Eric Biggers <ebiggers@google.com>
+
+commit f3aefb6a7066e24bfea7fcf1b07907576de69d63 upstream.
+
+make_checksum_hmac_md5() is allocating an HMAC transform and doing
+crypto API calls in the following order:
+
+ crypto_ahash_init()
+ crypto_ahash_setkey()
+ crypto_ahash_digest()
+
+This is wrong because it makes no sense to init() the request before a
+key has been set, given that the initial state depends on the key. And
+digest() is short for init() + update() + final(), so in this case
+there's no need to explicitly call init() at all.
+
+Before commit 9fa68f620041 ("crypto: hash - prevent using keyed hashes
+without setting key") the extra init() had no real effect, at least for
+the software HMAC implementation. (There are also hardware drivers that
+implement HMAC-MD5, and it's not immediately obvious how gracefully they
+handle init() before setkey().) But now the crypto API detects this
+incorrect initialization and returns -ENOKEY. This is breaking NFS
+mounts in some cases.
+
+Fix it by removing the incorrect call to crypto_ahash_init().
+
+Reported-by: Michael Young <m.a.young@durham.ac.uk>
+Fixes: 9fa68f620041 ("crypto: hash - prevent using keyed hashes without setting key")
+Fixes: fffdaef2eb4a ("gss_krb5: Add support for rc4-hmac encryption")
+Cc: stable@vger.kernel.org
+Signed-off-by: Eric Biggers <ebiggers@google.com>
+Signed-off-by: J. Bruce Fields <bfields@redhat.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ net/sunrpc/auth_gss/gss_krb5_crypto.c | 3 ---
+ 1 file changed, 3 deletions(-)
+
+--- a/net/sunrpc/auth_gss/gss_krb5_crypto.c
++++ b/net/sunrpc/auth_gss/gss_krb5_crypto.c
+@@ -237,9 +237,6 @@ make_checksum_hmac_md5(struct krb5_ctx *
+
+ ahash_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP, NULL, NULL);
+
+- err = crypto_ahash_init(req);
+- if (err)
+- goto out;
+ err = crypto_ahash_setkey(hmac_md5, cksumkey, kctx->gk5e->keylength);
+ if (err)
+ goto out;
--- /dev/null
+From a774635db5c430cbf21fa5d2f2df3d23aaa8e782 Mon Sep 17 00:00:00 2001
+From: Li RongQing <lirongqing@baidu.com>
+Date: Tue, 10 Apr 2018 09:16:06 +0800
+Subject: x86/apic: Fix signedness bug in APIC ID validity checks
+
+From: Li RongQing <lirongqing@baidu.com>
+
+commit a774635db5c430cbf21fa5d2f2df3d23aaa8e782 upstream.
+
+The APIC ID as parsed from ACPI MADT is validity checked with the
+apic->apic_id_valid() callback, which depends on the selected APIC type.
+
+For non X2APIC types APIC IDs >= 0xFF are invalid, but values > 0x7FFFFFFF
+are detected as valid. This happens because the 'apicid' argument of the
+apic_id_valid() callback is type 'int'. So the resulting comparison
+
+ apicid < 0xFF
+
+evaluates to true for all unsigned int values > 0x7FFFFFFF which are handed
+to default_apic_id_valid(). As a consequence, invalid APIC IDs in !X2APIC
+mode are considered valid and accounted as possible CPUs.
+
+Change the apicid argument type of the apic_id_valid() callback to u32 so
+the evaluation is unsigned and returns the correct result.
+
+[ tglx: Massaged changelog ]
+
+Signed-off-by: Li RongQing <lirongqing@baidu.com>
+Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
+Cc: stable@vger.kernel.org
+Cc: jgross@suse.com
+Cc: Dou Liyang <douly.fnst@cn.fujitsu.com>
+Cc: Peter Zijlstra <peterz@infradead.org>
+Cc: hpa@zytor.com
+Link: https://lkml.kernel.org/r/1523322966-10296-1-git-send-email-lirongqing@baidu.com
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ arch/x86/include/asm/apic.h | 4 ++--
+ arch/x86/kernel/acpi/boot.c | 13 ++++++++-----
+ arch/x86/kernel/apic/apic_common.c | 2 +-
+ arch/x86/kernel/apic/apic_numachip.c | 2 +-
+ arch/x86/kernel/apic/x2apic.h | 2 +-
+ arch/x86/kernel/apic/x2apic_phys.c | 2 +-
+ arch/x86/kernel/apic/x2apic_uv_x.c | 2 +-
+ arch/x86/xen/apic.c | 2 +-
+ 8 files changed, 16 insertions(+), 13 deletions(-)
+
+--- a/arch/x86/include/asm/apic.h
++++ b/arch/x86/include/asm/apic.h
+@@ -319,7 +319,7 @@ struct apic {
+ /* Probe, setup and smpboot functions */
+ int (*probe)(void);
+ int (*acpi_madt_oem_check)(char *oem_id, char *oem_table_id);
+- int (*apic_id_valid)(int apicid);
++ int (*apic_id_valid)(u32 apicid);
+ int (*apic_id_registered)(void);
+
+ bool (*check_apicid_used)(physid_mask_t *map, int apicid);
+@@ -492,7 +492,7 @@ static inline unsigned int read_apic_id(
+ return apic->get_apic_id(reg);
+ }
+
+-extern int default_apic_id_valid(int apicid);
++extern int default_apic_id_valid(u32 apicid);
+ extern int default_acpi_madt_oem_check(char *, char *);
+ extern void default_setup_apic_routing(void);
+
+--- a/arch/x86/kernel/acpi/boot.c
++++ b/arch/x86/kernel/acpi/boot.c
+@@ -200,7 +200,7 @@ acpi_parse_x2apic(struct acpi_subtable_h
+ {
+ struct acpi_madt_local_x2apic *processor = NULL;
+ #ifdef CONFIG_X86_X2APIC
+- int apic_id;
++ u32 apic_id;
+ u8 enabled;
+ #endif
+
+@@ -222,10 +222,13 @@ acpi_parse_x2apic(struct acpi_subtable_h
+ * to not preallocating memory for all NR_CPUS
+ * when we use CPU hotplug.
+ */
+- if (!apic->apic_id_valid(apic_id) && enabled)
+- printk(KERN_WARNING PREFIX "x2apic entry ignored\n");
+- else
+- acpi_register_lapic(apic_id, processor->uid, enabled);
++ if (!apic->apic_id_valid(apic_id)) {
++ if (enabled)
++ pr_warn(PREFIX "x2apic entry ignored\n");
++ return 0;
++ }
++
++ acpi_register_lapic(apic_id, processor->uid, enabled);
+ #else
+ printk(KERN_WARNING PREFIX "x2apic entry ignored\n");
+ #endif
+--- a/arch/x86/kernel/apic/apic_common.c
++++ b/arch/x86/kernel/apic/apic_common.c
+@@ -40,7 +40,7 @@ int default_check_phys_apicid_present(in
+ return physid_isset(phys_apicid, phys_cpu_present_map);
+ }
+
+-int default_apic_id_valid(int apicid)
++int default_apic_id_valid(u32 apicid)
+ {
+ return (apicid < 255);
+ }
+--- a/arch/x86/kernel/apic/apic_numachip.c
++++ b/arch/x86/kernel/apic/apic_numachip.c
+@@ -56,7 +56,7 @@ static u32 numachip2_set_apic_id(unsigne
+ return id << 24;
+ }
+
+-static int numachip_apic_id_valid(int apicid)
++static int numachip_apic_id_valid(u32 apicid)
+ {
+ /* Trust what bootloader passes in MADT */
+ return 1;
+--- a/arch/x86/kernel/apic/x2apic.h
++++ b/arch/x86/kernel/apic/x2apic.h
+@@ -1,6 +1,6 @@
+ /* Common bits for X2APIC cluster/physical modes. */
+
+-int x2apic_apic_id_valid(int apicid);
++int x2apic_apic_id_valid(u32 apicid);
+ int x2apic_apic_id_registered(void);
+ void __x2apic_send_IPI_dest(unsigned int apicid, int vector, unsigned int dest);
+ unsigned int x2apic_get_apic_id(unsigned long id);
+--- a/arch/x86/kernel/apic/x2apic_phys.c
++++ b/arch/x86/kernel/apic/x2apic_phys.c
+@@ -101,7 +101,7 @@ static int x2apic_phys_probe(void)
+ }
+
+ /* Common x2apic functions, also used by x2apic_cluster */
+-int x2apic_apic_id_valid(int apicid)
++int x2apic_apic_id_valid(u32 apicid)
+ {
+ return 1;
+ }
+--- a/arch/x86/kernel/apic/x2apic_uv_x.c
++++ b/arch/x86/kernel/apic/x2apic_uv_x.c
+@@ -557,7 +557,7 @@ static void uv_send_IPI_all(int vector)
+ uv_send_IPI_mask(cpu_online_mask, vector);
+ }
+
+-static int uv_apic_id_valid(int apicid)
++static int uv_apic_id_valid(u32 apicid)
+ {
+ return 1;
+ }
+--- a/arch/x86/xen/apic.c
++++ b/arch/x86/xen/apic.c
+@@ -112,7 +112,7 @@ static int xen_madt_oem_check(char *oem_
+ return xen_pv_domain();
+ }
+
+-static int xen_id_always_valid(int apicid)
++static int xen_id_always_valid(u32 apicid)
+ {
+ return 1;
+ }
--- /dev/null
+From 9820e1c3376c641299624dd24646aed3167ad5b1 Mon Sep 17 00:00:00 2001
+From: "Dmitry V. Levin" <ldv@altlinux.org>
+Date: Thu, 5 Apr 2018 07:32:10 +0300
+Subject: x86/uapi: Fix asm/bootparam.h userspace compilation errors
+
+From: Dmitry V. Levin <ldv@altlinux.org>
+
+commit 9820e1c3376c641299624dd24646aed3167ad5b1 upstream.
+
+Consistently use types provided by <linux/types.h> to fix the following
+asm/bootparam.h userspace compilation errors:
+
+ /usr/include/asm/bootparam.h:140:2: error: unknown type name 'u16'
+ u16 version;
+ /usr/include/asm/bootparam.h:141:2: error: unknown type name 'u16'
+ u16 compatible_version;
+ /usr/include/asm/bootparam.h:142:2: error: unknown type name 'u16'
+ u16 pm_timer_address;
+ /usr/include/asm/bootparam.h:143:2: error: unknown type name 'u16'
+ u16 num_cpus;
+ /usr/include/asm/bootparam.h:144:2: error: unknown type name 'u64'
+ u64 pci_mmconfig_base;
+ /usr/include/asm/bootparam.h:145:2: error: unknown type name 'u32'
+ u32 tsc_khz;
+ /usr/include/asm/bootparam.h:146:2: error: unknown type name 'u32'
+ u32 apic_khz;
+ /usr/include/asm/bootparam.h:147:2: error: unknown type name 'u8'
+ u8 standard_ioapic;
+ /usr/include/asm/bootparam.h:148:2: error: unknown type name 'u8'
+ u8 cpu_ids[255];
+
+Signed-off-by: Dmitry V. Levin <ldv@altlinux.org>
+Acked-by: Jan Kiszka <jan.kiszka@siemens.com>
+Cc: <stable@vger.kernel.org> # v4.16
+Cc: Linus Torvalds <torvalds@linux-foundation.org>
+Cc: Peter Zijlstra <peterz@infradead.org>
+Cc: Thomas Gleixner <tglx@linutronix.de>
+Fixes: 4a362601baa6 ("x86/jailhouse: Add infrastructure for running in non-root cell")
+Link: http://lkml.kernel.org/r/20180405043210.GA13254@altlinux.org
+Signed-off-by: Ingo Molnar <mingo@kernel.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ arch/x86/include/uapi/asm/bootparam.h | 18 +++++++++---------
+ 1 file changed, 9 insertions(+), 9 deletions(-)
+
+--- a/arch/x86/include/uapi/asm/bootparam.h
++++ b/arch/x86/include/uapi/asm/bootparam.h
+@@ -137,15 +137,15 @@ struct boot_e820_entry {
+ * setup data structure.
+ */
+ struct jailhouse_setup_data {
+- u16 version;
+- u16 compatible_version;
+- u16 pm_timer_address;
+- u16 num_cpus;
+- u64 pci_mmconfig_base;
+- u32 tsc_khz;
+- u32 apic_khz;
+- u8 standard_ioapic;
+- u8 cpu_ids[255];
++ __u16 version;
++ __u16 compatible_version;
++ __u16 pm_timer_address;
++ __u16 num_cpus;
++ __u64 pci_mmconfig_base;
++ __u32 tsc_khz;
++ __u32 apic_khz;
++ __u8 standard_ioapic;
++ __u8 cpu_ids[255];
+ } __attribute__((packed));
+
+ /* The so-called "zeropage" */
--- /dev/null
+From 2a22ee6c3ab1d761bc9c04f1e4117edd55b82f09 Mon Sep 17 00:00:00 2001
+From: Simon Gaiser <simon@invisiblethingslab.com>
+Date: Thu, 15 Mar 2018 03:43:20 +0100
+Subject: xen: xenbus_dev_frontend: Fix XS_TRANSACTION_END handling
+
+From: Simon Gaiser <simon@invisiblethingslab.com>
+
+commit 2a22ee6c3ab1d761bc9c04f1e4117edd55b82f09 upstream.
+
+Commit fd8aa9095a95 ("xen: optimize xenbus driver for multiple
+concurrent xenstore accesses") made a subtle change to the semantic of
+xenbus_dev_request_and_reply() and xenbus_transaction_end().
+
+Before on an error response to XS_TRANSACTION_END
+xenbus_dev_request_and_reply() would not decrement the active
+transaction counter. But xenbus_transaction_end() has always counted the
+transaction as finished regardless of the response.
+
+The new behavior is that xenbus_dev_request_and_reply() and
+xenbus_transaction_end() will always count the transaction as finished
+regardless the response code (handled in xs_request_exit()).
+
+But xenbus_dev_frontend tries to end a transaction on closing of the
+device if the XS_TRANSACTION_END failed before. Trying to close the
+transaction twice corrupts the reference count. So fix this by also
+considering a transaction closed if we have sent XS_TRANSACTION_END once
+regardless of the return code.
+
+Cc: <stable@vger.kernel.org> # 4.11
+Fixes: fd8aa9095a95 ("xen: optimize xenbus driver for multiple concurrent xenstore accesses")
+Signed-off-by: Simon Gaiser <simon@invisiblethingslab.com>
+Reviewed-by: Juergen Gross <jgross@suse.com>
+Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ drivers/xen/xenbus/xenbus_dev_frontend.c | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+--- a/drivers/xen/xenbus/xenbus_dev_frontend.c
++++ b/drivers/xen/xenbus/xenbus_dev_frontend.c
+@@ -365,7 +365,7 @@ void xenbus_dev_queue_reply(struct xb_re
+ if (WARN_ON(rc))
+ goto out;
+ }
+- } else if (req->msg.type == XS_TRANSACTION_END) {
++ } else if (req->type == XS_TRANSACTION_END) {
+ trans = xenbus_get_transaction(u, req->msg.tx_id);
+ if (WARN_ON(!trans))
+ goto out;
--- /dev/null
+From 7bbaf27d9c83037b6e60a818e57bdbedf6bc15be Mon Sep 17 00:00:00 2001
+From: Huacai Chen <chenhc@lemote.com>
+Date: Thu, 5 Apr 2018 16:18:18 -0700
+Subject: zboot: fix stack protector in compressed boot phase
+
+From: Huacai Chen <chenhc@lemote.com>
+
+commit 7bbaf27d9c83037b6e60a818e57bdbedf6bc15be upstream.
+
+Calling __stack_chk_guard_setup() in decompress_kernel() is too late
+that stack checking always fails for decompress_kernel() itself. So
+remove __stack_chk_guard_setup() and initialize __stack_chk_guard before
+we call decompress_kernel().
+
+Original code comes from ARM but also used for MIPS and SH, so fix them
+together. If without this fix, compressed booting of these archs will
+fail because stack checking is enabled by default (>=4.16).
+
+Link: http://lkml.kernel.org/r/1522226933-29317-1-git-send-email-chenhc@lemote.com
+Fixes: 8779657d29c0 ("stackprotector: Introduce CONFIG_CC_STACKPROTECTOR_STRONG")
+Signed-off-by: Huacai Chen <chenhc@lemote.com>
+Acked-by: James Hogan <jhogan@kernel.org>
+Acked-by: Kees Cook <keescook@chromium.org>
+Acked-by: Rich Felker <dalias@libc.org>
+Cc: Ralf Baechle <ralf@linux-mips.org>
+Cc: Russell King <linux@arm.linux.org.uk>
+Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
+Cc: Ingo Molnar <mingo@elte.hu>
+Cc: <stable@vger.kernel.org>
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
+Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ arch/arm/boot/compressed/misc.c | 9 +--------
+ arch/mips/boot/compressed/decompress.c | 9 +--------
+ arch/sh/boot/compressed/misc.c | 9 +--------
+ 3 files changed, 3 insertions(+), 24 deletions(-)
+
+--- a/arch/arm/boot/compressed/misc.c
++++ b/arch/arm/boot/compressed/misc.c
+@@ -128,12 +128,7 @@ asmlinkage void __div0(void)
+ error("Attempting division by 0!");
+ }
+
+-unsigned long __stack_chk_guard;
+-
+-void __stack_chk_guard_setup(void)
+-{
+- __stack_chk_guard = 0x000a0dff;
+-}
++const unsigned long __stack_chk_guard = 0x000a0dff;
+
+ void __stack_chk_fail(void)
+ {
+@@ -150,8 +145,6 @@ decompress_kernel(unsigned long output_s
+ {
+ int ret;
+
+- __stack_chk_guard_setup();
+-
+ output_data = (unsigned char *)output_start;
+ free_mem_ptr = free_mem_ptr_p;
+ free_mem_end_ptr = free_mem_ptr_end_p;
+--- a/arch/mips/boot/compressed/decompress.c
++++ b/arch/mips/boot/compressed/decompress.c
+@@ -76,12 +76,7 @@ void error(char *x)
+ #include "../../../../lib/decompress_unxz.c"
+ #endif
+
+-unsigned long __stack_chk_guard;
+-
+-void __stack_chk_guard_setup(void)
+-{
+- __stack_chk_guard = 0x000a0dff;
+-}
++const unsigned long __stack_chk_guard = 0x000a0dff;
+
+ void __stack_chk_fail(void)
+ {
+@@ -92,8 +87,6 @@ void decompress_kernel(unsigned long boo
+ {
+ unsigned long zimage_start, zimage_size;
+
+- __stack_chk_guard_setup();
+-
+ zimage_start = (unsigned long)(&__image_begin);
+ zimage_size = (unsigned long)(&__image_end) -
+ (unsigned long)(&__image_begin);
+--- a/arch/sh/boot/compressed/misc.c
++++ b/arch/sh/boot/compressed/misc.c
+@@ -104,12 +104,7 @@ static void error(char *x)
+ while(1); /* Halt */
+ }
+
+-unsigned long __stack_chk_guard;
+-
+-void __stack_chk_guard_setup(void)
+-{
+- __stack_chk_guard = 0x000a0dff;
+-}
++const unsigned long __stack_chk_guard = 0x000a0dff;
+
+ void __stack_chk_fail(void)
+ {
+@@ -130,8 +125,6 @@ void decompress_kernel(void)
+ {
+ unsigned long output_addr;
+
+- __stack_chk_guard_setup();
+-
+ #ifdef CONFIG_SUPERH64
+ output_addr = (CONFIG_MEMORY_START + 0x2000);
+ #else
projects / thirdparty / kernel / stable-queue.git / commitdiff
