Re: [PATCH] mm: take memory hotplug lock within numa_zonelist_order_handler()

From: Thomas Gleixner
Date: Wed Jul 26 2017 - 09:34:41 EST


On Wed, 26 Jul 2017, Heiko Carstens wrote:
> Andre Wild reported the folling warning:
>
> WARNING: CPU: 2 PID: 1205 at kernel/cpu.c:240 lockdep_assert_cpus_held+0x4c/0x60
> Modules linked in:
> CPU: 2 PID: 1205 Comm: bash Not tainted 4.13.0-rc2-00022-gfd2b2c57ec20 #10
> Hardware name: IBM 2964 N96 702 (z/VM 6.4.0)
> task: 00000000701d8100 task.stack: 0000000073594000
> Krnl PSW : 0704f00180000000 0000000000145e24 (lockdep_assert_cpus_held+0x4c/0x60)
> ...
> Call Trace:
> lockdep_assert_cpus_held+0x42/0x60)
> stop_machine_cpuslocked+0x62/0xf0
> build_all_zonelists+0x92/0x150
> numa_zonelist_order_handler+0x102/0x150
> proc_sys_call_handler.isra.12+0xda/0x118
> proc_sys_write+0x34/0x48
> __vfs_write+0x3c/0x178
> vfs_write+0xbc/0x1a0
> SyS_write+0x66/0xc0
> system_call+0xc4/0x2b0
> locks held by bash/1205:
> #0: (sb_writers#4){.+.+.+}, at: [<000000000037b29e>] vfs_write+0xa6/0x1a0
> #1: (zl_order_mutex){+.+...}, at: [<00000000002c8e4c>] numa_zonelist_order_handler+0x44/0x150
> #2: (zonelists_mutex){+.+...}, at: [<00000000002c8efc>] numa_zonelist_order_handler+0xf4/0x150
> Last Breaking-Event-Address:
> [<0000000000145e20>] lockdep_assert_cpus_held+0x48/0x60
>
> This can be easily triggered with e.g.
>
> >echo n > /proc/sys/vm/numa_zonelist_order
>
> With commit 3f906ba23689a ("mm/memory-hotplug: switch locking to a
> percpu rwsem") memory hotplug locking was changed to fix a potential
> deadlock. This also switched the stop_machine() invocation within
> build_all_zonelists() to stop_machine_cpuslocked() which now expects
> that online cpus are locked when being called.
>
> This assumption is not true if build_all_zonelists() is being called
> from numa_zonelist_order_handler(). In order to fix this simply add a
> mem_hotplug_begin()/mem_hotplug_done() pair to numa_zonelist_order_handler().

Sorry, I missed that call path when I did the conversion. So yes, that
needs some protection....

Thanks,

tglx