exit
fi
done
-From 29183a70b0b828500816bd794b3fe192fce89f73 Mon Sep 17 00:00:00 2001
-From: John Stultz <john.stultz@linaro.org>
-Date: Mon, 9 Feb 2015 23:30:36 -0800
-Subject: ntp: Fixup adjtimex freq validation on 32-bit systems
+From e820d55cb99dd93ac2dc949cf486bb187e5cd70d Mon Sep 17 00:00:00 2001
+From: Guoqing Jiang <gqjiang@suse.com>
+Date: Wed, 19 Dec 2018 14:19:25 +0800
+Subject: md: fix raid10 hang issue caused by barrier
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
-Additional validation of adjtimex freq values to avoid
-potential multiplication overflows were added in commit
-5e5aeb4367b (time: adjtimex: Validate the ADJ_FREQUENCY values)
+When both regular IO and resync IO happen at the same time,
+and if we also need to split regular. Then we can see tasks
+hang due to barrier.
-Unfortunately the patch used LONG_MAX/MIN instead of
-LLONG_MAX/MIN, which was fine on 64-bit systems, but being
-much smaller on 32-bit systems caused false positives
-resulting in most direct frequency adjustments to fail w/
-EINVAL.
+1. resync thread
+[ 1463.757205] INFO: task md1_resync:5215 blocked for more than 480 seconds.
+[ 1463.757207] Not tainted 4.19.5-1-default #1
+[ 1463.757209] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
+[ 1463.757212] md1_resync D 0 5215 2 0x80000000
+[ 1463.757216] Call Trace:
+[ 1463.757223] ? __schedule+0x29a/0x880
+[ 1463.757231] ? raise_barrier+0x8d/0x140 [raid10]
+[ 1463.757236] schedule+0x78/0x110
+[ 1463.757243] raise_barrier+0x8d/0x140 [raid10]
+[ 1463.757248] ? wait_woken+0x80/0x80
+[ 1463.757257] raid10_sync_request+0x1f6/0x1e30 [raid10]
+[ 1463.757265] ? _raw_spin_unlock_irq+0x22/0x40
+[ 1463.757284] ? is_mddev_idle+0x125/0x137 [md_mod]
+[ 1463.757302] md_do_sync.cold.78+0x404/0x969 [md_mod]
+[ 1463.757311] ? wait_woken+0x80/0x80
+[ 1463.757336] ? md_rdev_init+0xb0/0xb0 [md_mod]
+[ 1463.757351] md_thread+0xe9/0x140 [md_mod]
+[ 1463.757358] ? _raw_spin_unlock_irqrestore+0x2e/0x60
+[ 1463.757364] ? __kthread_parkme+0x4c/0x70
+[ 1463.757369] kthread+0x112/0x130
+[ 1463.757374] ? kthread_create_worker_on_cpu+0x40/0x40
+[ 1463.757380] ret_from_fork+0x3a/0x50
-ntpd only does direct frequency adjustments at startup, so
-the issue was not as easily observed there, but other time
-sync applications like ptpd and chrony were more effected by
-the bug.
+2. regular IO
+[ 1463.760679] INFO: task kworker/0:8:5367 blocked for more than 480 seconds.
+[ 1463.760683] Not tainted 4.19.5-1-default #1
+[ 1463.760684] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
+[ 1463.760687] kworker/0:8 D 0 5367 2 0x80000000
+[ 1463.760718] Workqueue: md submit_flushes [md_mod]
+[ 1463.760721] Call Trace:
+[ 1463.760731] ? __schedule+0x29a/0x880
+[ 1463.760741] ? wait_barrier+0xdd/0x170 [raid10]
+[ 1463.760746] schedule+0x78/0x110
+[ 1463.760753] wait_barrier+0xdd/0x170 [raid10]
+[ 1463.760761] ? wait_woken+0x80/0x80
+[ 1463.760768] raid10_write_request+0xf2/0x900 [raid10]
+[ 1463.760774] ? wait_woken+0x80/0x80
+[ 1463.760778] ? mempool_alloc+0x55/0x160
+[ 1463.760795] ? md_write_start+0xa9/0x270 [md_mod]
+[ 1463.760801] ? try_to_wake_up+0x44/0x470
+[ 1463.760810] raid10_make_request+0xc1/0x120 [raid10]
+[ 1463.760816] ? wait_woken+0x80/0x80
+[ 1463.760831] md_handle_request+0x121/0x190 [md_mod]
+[ 1463.760851] md_make_request+0x78/0x190 [md_mod]
+[ 1463.760860] generic_make_request+0x1c6/0x470
+[ 1463.760870] raid10_write_request+0x77a/0x900 [raid10]
+[ 1463.760875] ? wait_woken+0x80/0x80
+[ 1463.760879] ? mempool_alloc+0x55/0x160
+[ 1463.760895] ? md_write_start+0xa9/0x270 [md_mod]
+[ 1463.760904] raid10_make_request+0xc1/0x120 [raid10]
+[ 1463.760910] ? wait_woken+0x80/0x80
+[ 1463.760926] md_handle_request+0x121/0x190 [md_mod]
+[ 1463.760931] ? _raw_spin_unlock_irq+0x22/0x40
+[ 1463.760936] ? finish_task_switch+0x74/0x260
+[ 1463.760954] submit_flushes+0x21/0x40 [md_mod]
-See bugs:
+So resync io is waiting for regular write io to complete to
+decrease nr_pending (conf->barrier++ is called before waiting).
+The regular write io splits another bio after call wait_barrier
+which call nr_pending++, then the splitted bio would continue
+with raid10_write_request -> wait_barrier, so the splitted bio
+has to wait for barrier to be zero, then deadlock happens as
+follows.
- https://bugzilla.kernel.org/show_bug.cgi?id=92481
- https://bugzilla.redhat.com/show_bug.cgi?id=1188074
+ resync io regular io
-This patch changes the checks to use LLONG_MAX for
-clarity, and additionally the checks are disabled
-on 32-bit systems since LLONG_MAX/PPM_SCALE is always
-larger then the 32-bit long freq value, so multiplication
-overflows aren't possible there.
+ raise_barrier
+ wait_barrier
+ generic_make_request
+ wait_barrier
-Reported-by: Josh Boyer <jwboyer@fedoraproject.org>
-Reported-by: George Joseph <george.joseph@fairview5.com>
-Tested-by: George Joseph <george.joseph@fairview5.com>
-Signed-off-by: John Stultz <john.stultz@linaro.org>
-Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
-Cc: <stable@vger.kernel.org> # v3.19+
-Cc: Linus Torvalds <torvalds@linux-foundation.org>
-Cc: Sasha Levin <sasha.levin@oracle.com>
-Link: http://lkml.kernel.org/r/1423553436-29747-1-git-send-email-john.stultz@linaro.org
-[ Prettified the changelog and the comments a bit. ]
-Signed-off-by: Ingo Molnar <mingo@kernel.org>
+To resolve the issue, we need to call allow_barrier to decrease
+nr_pending before generic_make_request since regular IO is not
+issued to underlying devices, and wait_barrier is called again
+to ensure no internal IO happening.
-diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
-index 4b585e0..0f60b08 100644
---- a/kernel/time/ntp.c
-+++ b/kernel/time/ntp.c
-@@ -633,10 +633,14 @@ int ntp_validate_timex(struct timex *txc)
- if ((txc->modes & ADJ_SETOFFSET) && (!capable(CAP_SYS_TIME)))
- return -EPERM;
-
-- if (txc->modes & ADJ_FREQUENCY) {
-- if (LONG_MIN / PPM_SCALE > txc->freq)
-+ /*
-+ * Check for potential multiplication overflows that can
-+ * only happen on 64-bit systems:
-+ */
-+ if ((txc->modes & ADJ_FREQUENCY) && (BITS_PER_LONG == 64)) {
-+ if (LLONG_MIN / PPM_SCALE > txc->freq)
- return -EINVAL;
-- if (LONG_MAX / PPM_SCALE < txc->freq)
-+ if (LLONG_MAX / PPM_SCALE < txc->freq)
- return -EINVAL;
+Fixes: fc9977dd069e ("md/raid10: simplify the splitting of requests.")
+Reported-and-tested-by: SiniĊĦa Bandin <sinisa@4net.rs>
+Signed-off-by: Guoqing Jiang <gqjiang@suse.com>
+Signed-off-by: Shaohua Li <shli@fb.com>
+---
+ drivers/md/raid10.c | 4 ++++
+ 1 file changed, 4 insertions(+)
+
+diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
+index 76c92e31afc0..abb5d382f64d 100644
+--- a/drivers/md/raid10.c
++++ b/drivers/md/raid10.c
+@@ -1209,7 +1209,9 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio,
+ struct bio *split = bio_split(bio, max_sectors,
+ gfp, &conf->bio_split);
+ bio_chain(split, bio);
++ allow_barrier(conf);
+ generic_make_request(bio);
++ wait_barrier(conf);
+ bio = split;
+ r10_bio->master_bio = bio;
+ r10_bio->sectors = max_sectors;
+@@ -1492,7 +1494,9 @@ retry_write:
+ struct bio *split = bio_split(bio, r10_bio->sectors,
+ GFP_NOIO, &conf->bio_split);
+ bio_chain(split, bio);
++ allow_barrier(conf);
+ generic_make_request(bio);
++ wait_barrier(conf);
+ bio = split;
+ r10_bio->master_bio = bio;
}
-
--
-cgit v0.10.2
+cgit 1.2-0.3.lf.el7
+--- linux-4.14/security/selinux/include/classmap.h 2017-11-12 19:46:13.000000000 +0100
++++ linux-4.20/security/selinux/include/classmap.h 2018-12-24 00:55:59.000000000 +0100
+@@ -238,9 +238,11 @@
+ { "access", NULL } },
+ { "infiniband_endport",
+ { "manage_subnet", NULL } },
++ { "xdp_socket",
++ { COMMON_SOCK_PERMS, NULL } },
+ { NULL }
+ };
+
+-#if PF_MAX > 44
++#if PF_MAX > 45
+ #error New address family defined, please update secclass_map.
+ #endif
projects / packages / kernel.git / blobdiff