From 42dbfc8649737cb622b2a7e02045401c4c09561c Mon Sep 17 00:00:00 2001 From: Li Zhong Date: Thu, 10 Apr 2014 16:25:31 +0800 Subject: [PATCH] powerpc/pseries: Protect remove_memory() with device hotplug lock While testing memory hot-remove, I found following dead lock: Process #1141 is drmgr, trying to remove some memory, i.e. memory499. It holds the memory_hotplug_mutex, and blocks when trying to remove file "online" under dir memory499, in kernfs_drain(), at wait_event(root->deactivate_waitq, atomic_read(&kn->active) == KN_DEACTIVATED_BIAS); Process #1120 is trying to online memory499 by echo 1 > memory499/online In .kernfs_fop_write, it uses kernfs_get_active() to increase &kn->active, thus blocking process #1141. While itself is blocked later when trying to acquire memory_hotplug_mutex, which is held by process The backtrace of both processes are shown below: [] 0xc000000001b18600 [] .__switch_to+0x144/0x200 [] .online_pages+0x74/0x7b0 [] .memory_subsys_online+0x9c/0x150 [] .device_online+0xb8/0x120 [] .online_store+0xb4/0xc0 [] .dev_attr_store+0x64/0xa0 [] .sysfs_kf_write+0x7c/0xb0 [] .kernfs_fop_write+0x154/0x1e0 [] .vfs_write+0xe0/0x260 [] .SyS_write+0x64/0x110 [] syscall_exit+0x0/0x7c [] 0xc000000001b18600 [] .__switch_to+0x144/0x200 [] .__kernfs_remove+0x204/0x300 [] .kernfs_remove_by_name_ns+0x68/0xf0 [] .sysfs_remove_file_ns+0x38/0x60 [] .device_remove_attrs+0x54/0xc0 [] .device_del+0x158/0x250 [] .device_unregister+0x34/0xa0 [] .unregister_memory_section+0x164/0x170 [] .__remove_pages+0x108/0x4c0 [] .arch_remove_memory+0x60/0xc0 [] .remove_memory+0x8c/0xe0 [] .pseries_remove_memblock+0xd4/0x160 [] .pseries_memory_notifier+0x27c/0x290 [] .notifier_call_chain+0x8c/0x100 [] .__blocking_notifier_call_chain+0x6c/0xe0 [] .of_property_notify+0x7c/0xc0 [] .of_update_property+0x3c/0x1b0 [] .ofdt_write+0x3dc/0x740 [] .proc_reg_write+0xac/0x110 [] .vfs_write+0xe0/0x260 [] .SyS_write+0x64/0x110 [] syscall_exit+0x0/0x7c This patch uses lock_device_hotplug() to protect remove_memory() called in pseries_remove_memblock(), which is also stated before function remove_memory(): * NOTE: The caller must call lock_device_hotplug() to serialize hotplug * and online/offline operations before this call, as required by * try_offline_node(). */ void __ref remove_memory(int nid, u64 start, u64 size) With this lock held, the other process(#1120 above) trying to online the memory block will retry the system call when calling lock_device_hotplug_sysfs(), and finally find No such device error. Signed-off-by: Li Zhong Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/platforms/pseries/hotplug-memory.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index 573b488..7f75c94 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -100,10 +100,10 @@ static int pseries_remove_memblock(unsigned long base, unsigned int memblock_siz start_pfn = base >> PAGE_SHIFT; - if (!pfn_valid(start_pfn)) { - memblock_remove(base, memblock_size); - return 0; - } + lock_device_hotplug(); + + if (!pfn_valid(start_pfn)) + goto out; block_sz = memory_block_size_bytes(); sections_per_block = block_sz / MIN_MEMORY_BLOCK_SIZE; @@ -114,8 +114,10 @@ static int pseries_remove_memblock(unsigned long base, unsigned int memblock_siz base += MIN_MEMORY_BLOCK_SIZE; } +out: /* Update memory regions for memory remove */ memblock_remove(base, memblock_size); + unlock_device_hotplug(); return 0; } -- 2.7.4