The patch titled
Subject: mm: change cpuhotplug lock order in lru_add_drain_all()
has been added to the -mm tree. Its filename is
mm-change-cpuhotplug-lock-order-in-lru_add_drain_all.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/mm-change-cpuhotplug-lock-order-in-lru_add_drain_all.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/mm-change-cpuhotplug-lock-order-in-lru_add_drain_all.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Subject: mm: change cpuhotplug lock order in lru_add_drain_all()
[ 131.022567] ============================================
[ 131.023034] WARNING: possible recursive locking detected
[ 131.023034] 4.12.0-rc7-next-20170630 #10 Not tainted
[ 131.023034] --------------------------------------------
[ 131.023034] bash/2266 is trying to acquire lock:
[ 131.023034] (cpu_hotplug_lock.rw_sem){++++++}, at: [<ffffffff8117fcd2>] lru_add_drain_all+0x42/0x190
[ 131.023034]
but task is already holding lock:
[ 131.023034] (cpu_hotplug_lock.rw_sem){++++++}, at: [<ffffffff811d5489>] mem_hotplug_begin+0x9/0x20
[ 131.023034]
other info that might help us debug this:
[ 131.023034] Possible unsafe locking scenario:
[ 131.023034] CPU0
[ 131.023034] ----
[ 131.023034] lock(cpu_hotplug_lock.rw_sem);
[ 131.023034] lock(cpu_hotplug_lock.rw_sem);
[ 131.023034]
*** DEADLOCK ***
[ 131.023034] May be due to missing lock nesting notation
[ 131.023034] 8 locks held by bash/2266:
[ 131.023034] #0: (sb_writers#8){.+.+.+}, at: [<ffffffff811e81f8>] vfs_write+0x1a8/0x1d0
[ 131.023034] #1: (&of->mutex){+.+.+.}, at: [<ffffffff81274b2c>] kernfs_fop_write+0xfc/0x1b0
[ 131.023034] #2: (s_active#48){.+.+.+}, at: [<ffffffff81274b34>] kernfs_fop_write+0x104/0x1b0
[ 131.023034] #3: (device_hotplug_lock){+.+.+.}, at: [<ffffffff816d4810>] lock_device_hotplug_sysfs+0x10/0x40
[ 131.023034] #4: (cpu_hotplug_lock.rw_sem){++++++}, at: [<ffffffff811d5489>] mem_hotplug_begin+0x9/0x20
[ 131.023034] #5: (mem_hotplug_lock.rw_sem){++++++}, at: [<ffffffff810ada81>] percpu_down_write+0x21/0x110
[ 131.023034] #6: (&dev->mutex){......}, at: [<ffffffff816d5bd5>] device_offline+0x45/0xb0
[ 131.023034] #7: (lock#3){+.+...}, at: [<ffffffff8117fccd>] lru_add_drain_all+0x3d/0x190
[ 131.023034]
stack backtrace:
[ 131.023034] CPU: 0 PID: 2266 Comm: bash Not tainted 4.12.0-rc7-next-20170630 #10
[ 131.023034] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.10.2-0-g5f4c7b1-prebuilt.qemu-project.org 04/01/2014
[ 131.023034] Call Trace:
[ 131.023034] dump_stack+0x85/0xc7
[ 131.023034] __lock_acquire+0x1747/0x17a0
[ 131.023034] ? lru_add_drain_all+0x3d/0x190
[ 131.023034] ? __mutex_lock+0x218/0x940
[ 131.023034] ? trace_hardirqs_on+0xd/0x10
[ 131.023034] lock_acquire+0x103/0x200
[ 131.023034] ? lock_acquire+0x103/0x200
[ 131.023034] ? lru_add_drain_all+0x42/0x190
[ 131.023034] cpus_read_lock+0x3d/0x80
[ 131.023034] ? lru_add_drain_all+0x42/0x190
[ 131.023034] lru_add_drain_all+0x42/0x190
[ 131.023034] __offline_pages.constprop.25+0x5de/0x870
[ 131.023034] offline_pages+0xc/0x10
[ 131.023034] memory_subsys_offline+0x43/0x70
[ 131.023034] device_offline+0x83/0xb0
[ 131.023034] store_mem_state+0xdb/0xe0
[ 131.023034] dev_attr_store+0x13/0x20
[ 131.023034] sysfs_kf_write+0x40/0x50
[ 131.023034] kernfs_fop_write+0x130/0x1b0
[ 131.023034] __vfs_write+0x23/0x130
[ 131.023034] ? rcu_read_lock_sched_held+0x6d/0x80
[ 131.023034] ? rcu_sync_lockdep_assert+0x2a/0x50
[ 131.023034] ? __sb_start_write+0xd4/0x1c0
[ 131.023034] ? vfs_write+0x1a8/0x1d0
[ 131.023034] vfs_write+0xc8/0x1d0
[ 131.023034] SyS_write+0x44/0xa0
[ 131.023034] entry_SYSCALL_64_fastpath+0x1f/0xbe
Reported-by: Andrey Ryabinin <aryabinin@xxxxxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxxxx>
Cc: Vlastimil Babka <vbabka@xxxxxxx>
Cc: Daniel Kiper <dkiper@xxxxxxxxxxxx>
Cc: Vladimir Davydov <vdavydov.dev@xxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/swap.h | 1 +
mm/memory_hotplug.c | 4 ++--
mm/swap.c | 11 ++++++++---
3 files changed, 11 insertions(+), 5 deletions(-)
diff -puN include/linux/swap.h~mm-change-cpuhotplug-lock-order-in-lru_add_drain_all include/linux/swap.h
--- a/include/linux/swap.h~mm-change-cpuhotplug-lock-order-in-lru_add_drain_all
+++ a/include/linux/swap.h
@@ -277,6 +277,7 @@ extern void mark_page_accessed(struct pa
extern void lru_add_drain(void);
extern void lru_add_drain_cpu(int cpu);
extern void lru_add_drain_all(void);
+extern void lru_add_drain_all_cpuslocked(void);
extern void rotate_reclaimable_page(struct page *page);
extern void deactivate_file_page(struct page *page);
extern void mark_page_lazyfree(struct page *page);
diff -puN mm/memory_hotplug.c~mm-change-cpuhotplug-lock-order-in-lru_add_drain_all mm/memory_hotplug.c
--- a/mm/memory_hotplug.c~mm-change-cpuhotplug-lock-order-in-lru_add_drain_all
+++ a/mm/memory_hotplug.c
@@ -1670,7 +1670,7 @@ repeat:
goto failed_removal;
ret = 0;
if (drain) {
- lru_add_drain_all();
+ lru_add_drain_all_cpuslocked();
cond_resched();
drain_all_pages(zone);
}
@@ -1691,7 +1691,7 @@ repeat:
}
}
/* drain all zone's lru pagevec, this is asynchronous... */
- lru_add_drain_all();
+ lru_add_drain_all_cpuslocked();
yield();
/* drain pcp pages, this is synchronous. */
drain_all_pages(zone);
diff -puN mm/swap.c~mm-change-cpuhotplug-lock-order-in-lru_add_drain_all mm/swap.c
--- a/mm/swap.c~mm-change-cpuhotplug-lock-order-in-lru_add_drain_all
+++ a/mm/swap.c
@@ -688,7 +688,7 @@ static void lru_add_drain_per_cpu(struct
static DEFINE_PER_CPU(struct work_struct, lru_add_drain_work);
-void lru_add_drain_all(void)
+void lru_add_drain_all_cpuslocked(void)
{
static DEFINE_MUTEX(lock);
static struct cpumask has_work;
@@ -702,7 +702,6 @@ void lru_add_drain_all(void)
return;
mutex_lock(&lock);
- get_online_cpus();
cpumask_clear(&has_work);
for_each_online_cpu(cpu) {
@@ -722,10 +721,16 @@ void lru_add_drain_all(void)
for_each_cpu(cpu, &has_work)
flush_work(&per_cpu(lru_add_drain_work, cpu));
- put_online_cpus();
mutex_unlock(&lock);
}
+void lru_add_drain_all(void)
+{
+ get_online_cpus();
+ lru_add_drain_all_cpuslocked();
+ put_online_cpus();
+}
+
/**
* release_pages - batched put_page()
* @pages: array of pages to release
_
Patches currently in -mm which might be from tglx@xxxxxxxxxxxxx are
mm-memory-hotplug-switch-locking-to-a-percpu-rwsem.patch
mm-change-cpuhotplug-lock-order-in-lru_add_drain_all.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
