---- linux-2.6.33/scripts/mod/modpost.c~ 2010-02-24 19:52:17.000000000 +0100
-+++ linux-2.6.33/scripts/mod/modpost.c 2010-03-07 14:26:47.242168558 +0100
-@@ -15,7 +15,8 @@
- #include <stdio.h>
- #include <ctype.h>
- #include "modpost.h"
--#include "../../include/generated/autoconf.h"
-+// PLD architectures don't use CONFIG_SYMBOL_PREFIX
-+//#include "../../include/generated/autoconf.h"
- #include "../../include/linux/license.h"
+From: Shaohua Li <shli@fb.com>
+
+Basically this is a copy of commit 001e4a8775f6(ext4: implement cgroup
+writeback support). Tested with a fio test, verified writeback is
+throttled against cgroup io.max write bandwidth, also verified moving
+the fio test to another cgroup and the writeback is throttled against
+new cgroup setting.
+
+Cc: Tejun Heo <tj@kernel.org>
+Signed-off-by: Shaohua Li <shli@fb.com>
+---
+ fs/xfs/xfs_aops.c | 2 ++
+ fs/xfs/xfs_super.c | 1 +
+ 2 files changed, 3 insertions(+)
+
+--- linux-4.19/fs/xfs/xfs_aops.c.org 2018-11-21 10:31:12.348955352 +0100
++++ linux-4.19/fs/xfs/xfs_aops.c 2018-11-21 10:34:35.241764742 +0100
+@@ -613,8 +613,10 @@ xfs_add_to_ioend(
+ list_add(&wpc->ioend->io_list, iolist);
+ wpc->ioend = xfs_alloc_ioend(inode, wpc->io_type, offset,
+ bdev, sector);
++ wbc_init_bio(wbc, wpc->ioend->io_bio);
+ }
+
++ wbc_account_io(wbc, page, len);
+ if (!__bio_try_merge_page(wpc->ioend->io_bio, page, len, poff)) {
+ if (iop)
+ atomic_inc(&iop->write_count);
+diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
+index 584cf2d..aea3bc2 100644
+--- a/fs/xfs/xfs_super.c
++++ b/fs/xfs/xfs_super.c
+@@ -1634,6 +1634,7 @@ xfs_fs_fill_super(
+ sb->s_max_links = XFS_MAXLINK;
+ sb->s_time_gran = 1;
+ set_posix_acl_flag(sb);
++ sb->s_iflags |= SB_I_CGROUPWB;
- /* Some toolchains use a `_' prefix for all user symbols. */
+ /* version 5 superblocks support inode version counters. */
+ if (XFS_SB_VERSION_NUM(&mp->m_sb) == XFS_SB_VERSION_5)
+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
---- linux-3.0/scripts/kconfig/lxdialog/check-lxdialog.sh~ 2011-07-22 04:17:23.000000000 +0200
-+++ linux-3.0/scripts/kconfig/lxdialog/check-lxdialog.sh 2011-08-25 21:26:04.799150642 +0200
-@@ -9,6 +9,12 @@
- $cc -print-file-name=lib${lib}.${ext} | grep -q /
- if [ $? -eq 0 ]; then
- echo "-l${lib}"
-+ for libt in tinfow tinfo ; do
-+ $cc -print-file-name=lib${libt}.${ext} | grep -q /
-+ if [ $? -eq 0 ]; then
-+ echo "-l${libt}"
-+ fi
-+ done
- exit
- fi
- done
-From 8358b02bf67d3a5d8a825070e1aa73f25fb2e4c7 Mon Sep 17 00:00:00 2001
-From: Jann Horn <jannh@google.com>
-Date: Tue, 26 Apr 2016 22:26:26 +0200
-Subject: bpf: fix double-fdput in replace_map_fd_with_map_ptr()
+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.
-When bpf(BPF_PROG_LOAD, ...) was invoked with a BPF program whose bytecode
-references a non-map file descriptor as a map file descriptor, the error
-handling code called fdput() twice instead of once (in __bpf_map_get() and
-in replace_map_fd_with_map_ptr()). If the file descriptor table of the
-current task is shared, this causes f_count to be decremented too much,
-allowing the struct file to be freed while it is still in use
-(use-after-free). This can be exploited to gain root privileges by an
-unprivileged user.
+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
-This bug was introduced in
-commit 0246e64d9a5f ("bpf: handle pseudo BPF_LD_IMM64 insn"), but is only
-exploitable since
-commit 1be7f75d1668 ("bpf: enable non-root eBPF programs") because
-previously, CAP_SYS_ADMIN was required to reach the vulnerable code.
+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]
-(posted publicly according to request by maintainer)
+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.
-Signed-off-by: Jann Horn <jannh@google.com>
-Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-Acked-by: Alexei Starovoitov <ast@kernel.org>
-Acked-by: Daniel Borkmann <daniel@iogearbox.net>
-Signed-off-by: David S. Miller <davem@davemloft.net>
+ resync io regular io
+
+ raise_barrier
+ wait_barrier
+ generic_make_request
+ wait_barrier
+
+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.
+
+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>
---
- kernel/bpf/verifier.c | 1 -
- 1 file changed, 1 deletion(-)
+ drivers/md/raid10.c | 4 ++++
+ 1 file changed, 4 insertions(+)
-diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
-index 618ef77..db2574e 100644
---- a/kernel/bpf/verifier.c
-+++ b/kernel/bpf/verifier.c
-@@ -2030,7 +2030,6 @@ static int replace_map_fd_with_map_ptr(struct verifier_env *env)
- if (IS_ERR(map)) {
- verbose("fd %d is not pointing to valid bpf_map\n",
- insn->imm);
-- fdput(f);
- return PTR_ERR(map);
- }
-
+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 v0.12
+cgit 1.2-0.3.lf.el7
+
projects / packages / kernel.git / blobdiff