From e9959f0f37160e1f5351af828cc981712b5066c1 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Wed, 24 Nov 2010 12:57:09 -0800 Subject: mm/page_alloc.c: fix build_all_zonelist() where percpu_alloc() is wrongly called under stop_machine_run() During memory hotplug, build_allzonelists() may be called under stop_machine_run(). In this function, setup_zone_pageset() is called. But it's bug because it will do page allocation under stop_machine_run(). Here is a report from Alok Kataria. BUG: sleeping function called from invalid context at kernel/mutex.c:94 in_atomic(): 0, irqs_disabled(): 1, pid: 4, name: migration/0 Pid: 4, comm: migration/0 Not tainted 2.6.35.6-45.fc14.x86_64 #1 Call Trace: [] __might_sleep+0xeb/0xf0 [] mutex_lock+0x24/0x50 [] pcpu_alloc+0x6d/0x7ee [] ? load_balance+0xbe/0x60e [] ? rt_se_boosted+0x21/0x2f [] ? dequeue_rt_stack+0x18b/0x1ed [] __alloc_percpu+0x10/0x12 [] setup_zone_pageset+0x38/0xbe [] ? build_zonelists_node.clone.58+0x79/0x8c [] __build_all_zonelists+0x419/0x46c [] ? cpu_stopper_thread+0xb2/0x198 [] stop_machine_cpu_stop+0x8e/0xc5 [] ? stop_machine_cpu_stop+0x0/0xc5 [] cpu_stopper_thread+0x108/0x198 [] ? schedule+0x5b2/0x5cc [] ? cpu_stopper_thread+0x0/0x198 [] kthread+0x7f/0x87 [] kernel_thread_helper+0x4/0x10 [] ? kthread+0x0/0x87 [] ? kernel_thread_helper+0x0/0x10 Built 5 zonelists in Node order, mobility grouping on. Total pages: 289456 Policy zone: Normal This patch tries to fix the issue by moving setup_zone_pageset() out from stop_machine_run(). It's obviously not necessary to be called under stop_machine_run(). [akpm@linux-foundation.org: remove unneeded local] Reported-by: Alok Kataria Signed-off-by: KAMEZAWA Hiroyuki Cc: Tejun Heo Cc: Petr Vandrovec Cc: Pekka Enberg Reviewed-by: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 14 +++++--------- 1 file changed, 5 insertions(+), 9 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 07a654486f75..e4092704c1a9 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -3008,14 +3008,6 @@ static __init_refok int __build_all_zonelists(void *data) build_zonelist_cache(pgdat); } -#ifdef CONFIG_MEMORY_HOTPLUG - /* Setup real pagesets for the new zone */ - if (data) { - struct zone *zone = data; - setup_zone_pageset(zone); - } -#endif - /* * Initialize the boot_pagesets that are going to be used * for bootstrapping processors. The real pagesets for @@ -3064,7 +3056,11 @@ void build_all_zonelists(void *data) } else { /* we have to stop all cpus to guarantee there is no user of zonelist */ - stop_machine(__build_all_zonelists, data, NULL); +#ifdef CONFIG_MEMORY_HOTPLUG + if (data) + setup_zone_pageset((struct zone *)data); +#endif + stop_machine(__build_all_zonelists, NULL, NULL); /* cpuset refresh routine should be here */ } vm_total_pages = nr_free_pagecache_pages(); -- cgit v1.2.2 From c9e664f1fdf34aa8cede047b206deaa8f1945af0 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Fri, 3 Dec 2010 22:57:45 +0100 Subject: PM / Hibernate: Fix memory corruption related to swap There is a problem that swap pages allocated before the creation of a hibernation image can be released and used for storing the contents of different memory pages while the image is being saved. Since the kernel stored in the image doesn't know of that, it causes memory corruption to occur after resume from hibernation, especially on systems with relatively small RAM that need to swap often. This issue can be addressed by keeping the GFP_IOFS bits clear in gfp_allowed_mask during the entire hibernation, including the saving of the image, until the system is finally turned off or the hibernation is aborted. Unfortunately, for this purpose it's necessary to rework the way in which the hibernate and suspend code manipulates gfp_allowed_mask. This change is based on an earlier patch from Hugh Dickins. Signed-off-by: Rafael J. Wysocki Reported-by: Ondrej Zary Acked-by: Hugh Dickins Reviewed-by: KAMEZAWA Hiroyuki Cc: stable@kernel.org --- mm/page_alloc.c | 19 ++++++++++++------- 1 file changed, 12 insertions(+), 7 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index e4092704c1a9..ff7e15872398 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -104,19 +104,24 @@ gfp_t gfp_allowed_mask __read_mostly = GFP_BOOT_MASK; * only be modified with pm_mutex held, unless the suspend/hibernate code is * guaranteed not to run in parallel with that modification). */ -void set_gfp_allowed_mask(gfp_t mask) + +static gfp_t saved_gfp_mask; + +void pm_restore_gfp_mask(void) { WARN_ON(!mutex_is_locked(&pm_mutex)); - gfp_allowed_mask = mask; + if (saved_gfp_mask) { + gfp_allowed_mask = saved_gfp_mask; + saved_gfp_mask = 0; + } } -gfp_t clear_gfp_allowed_mask(gfp_t mask) +void pm_restrict_gfp_mask(void) { - gfp_t ret = gfp_allowed_mask; - WARN_ON(!mutex_is_locked(&pm_mutex)); - gfp_allowed_mask &= ~mask; - return ret; + WARN_ON(saved_gfp_mask); + saved_gfp_mask = gfp_allowed_mask; + gfp_allowed_mask &= ~GFP_IOFS; } #endif /* CONFIG_PM_SLEEP */ -- cgit v1.2.2