From ca371c0d7e23d0d0afae65fc83a0e91cf7399573 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Fri, 12 Jun 2009 10:33:53 +0300 Subject: memcg: fix page_cgroup fatal error in FLATMEM Now, SLAB is configured in very early stage and it can be used in init routine now. But replacing alloc_bootmem() in FLAT/DISCONTIGMEM's page_cgroup() initialization breaks the allocation, now. (Works well in SPARSEMEM case...it supports MEMORY_HOTPLUG and size of page_cgroup is in reasonable size (< 1 << MAX_ORDER.) This patch revive FLATMEM+memory cgroup by using alloc_bootmem. In future, We stop to support FLATMEM (if no users) or rewrite codes for flatmem completely.But this will adds more messy codes and overheads. Reported-by: Li Zefan Tested-by: Li Zefan Tested-by: Ingo Molnar Signed-off-by: KAMEZAWA Hiroyuki Signed-off-by: Pekka Enberg --- init/main.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'init/main.c') diff --git a/init/main.c b/init/main.c index 5616661eac01..b3e8f14c568a 100644 --- a/init/main.c +++ b/init/main.c @@ -539,6 +539,11 @@ void __init __weak thread_info_cache_init(void) */ static void __init mm_init(void) { + /* + * page_cgroup requires countinous pages as memmap + * and it's bigger than MAX_ORDER unless SPARSEMEM. + */ + page_cgroup_init_flatmem(); mem_init(); kmem_cache_init(); vmalloc_init(); -- cgit v1.2.3-58-ga151 From 7e85ee0c1d15ca5f8bff0f514f158eba1742dd87 Mon Sep 17 00:00:00 2001 From: Pekka Enberg Date: Fri, 12 Jun 2009 14:03:06 +0300 Subject: slab,slub: don't enable interrupts during early boot As explained by Benjamin Herrenschmidt: Oh and btw, your patch alone doesn't fix powerpc, because it's missing a whole bunch of GFP_KERNEL's in the arch code... You would have to grep the entire kernel for things that check slab_is_available() and even then you'll be missing some. For example, slab_is_available() didn't always exist, and so in the early days on powerpc, we used a mem_init_done global that is set form mem_init() (not perfect but works in practice). And we still have code using that to do the test. Therefore, mask out __GFP_WAIT, __GFP_IO, and __GFP_FS in the slab allocators in early boot code to avoid enabling interrupts. Signed-off-by: Pekka Enberg --- include/linux/gfp.h | 3 +++ include/linux/slab.h | 2 ++ include/linux/slob_def.h | 5 +++++ include/linux/slub_def.h | 2 ++ init/main.c | 1 + mm/slab.c | 18 ++++++++++++++++++ mm/slub.c | 16 ++++++++++++++++ 7 files changed, 47 insertions(+) (limited to 'init/main.c') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 0bbc15f54536..3760e7c5de02 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -85,6 +85,9 @@ struct vm_area_struct; __GFP_NOWARN|__GFP_REPEAT|__GFP_NOFAIL|\ __GFP_NORETRY|__GFP_NOMEMALLOC) +/* Control slab gfp mask during early boot */ +#define SLAB_GFP_BOOT_MASK __GFP_BITS_MASK & ~(__GFP_WAIT|__GFP_IO|__GFP_FS) + /* Control allocation constraints */ #define GFP_CONSTRAINT_MASK (__GFP_HARDWALL|__GFP_THISNODE) diff --git a/include/linux/slab.h b/include/linux/slab.h index 48803064cedf..219b8fb4651d 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -319,4 +319,6 @@ static inline void *kzalloc_node(size_t size, gfp_t flags, int node) return kmalloc_node(size, flags | __GFP_ZERO, node); } +void __init kmem_cache_init_late(void); + #endif /* _LINUX_SLAB_H */ diff --git a/include/linux/slob_def.h b/include/linux/slob_def.h index 0ec00b39d006..bb5368df4be8 100644 --- a/include/linux/slob_def.h +++ b/include/linux/slob_def.h @@ -34,4 +34,9 @@ static __always_inline void *__kmalloc(size_t size, gfp_t flags) return kmalloc(size, flags); } +static inline void kmem_cache_init_late(void) +{ + /* Nothing to do */ +} + #endif /* __LINUX_SLOB_DEF_H */ diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index be5d40c43bd2..4dcbc2c71491 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -302,4 +302,6 @@ static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node) } #endif +void __init kmem_cache_init_late(void); + #endif /* _LINUX_SLUB_DEF_H */ diff --git a/init/main.c b/init/main.c index b3e8f14c568a..f6204f712e7c 100644 --- a/init/main.c +++ b/init/main.c @@ -640,6 +640,7 @@ asmlinkage void __init start_kernel(void) "enabled early\n"); early_boot_irqs_on(); local_irq_enable(); + kmem_cache_init_late(); /* * HACK ALERT! This is early. We're enabling the console before diff --git a/mm/slab.c b/mm/slab.c index cd76964b53bc..453efcb1c980 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -303,6 +303,12 @@ struct kmem_list3 { int free_touched; /* updated without locking */ }; +/* + * The slab allocator is initialized with interrupts disabled. Therefore, make + * sure early boot allocations don't accidentally enable interrupts. + */ +static gfp_t slab_gfp_mask __read_mostly = SLAB_GFP_BOOT_MASK; + /* * Need this for bootstrapping a per node allocator. */ @@ -1654,6 +1660,14 @@ void __init kmem_cache_init(void) */ } +void __init kmem_cache_init_late(void) +{ + /* + * Interrupts are enabled now so all GFP allocations are safe. + */ + slab_gfp_mask = __GFP_BITS_MASK; +} + static int __init cpucache_init(void) { int cpu; @@ -3354,6 +3368,8 @@ __cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid, unsigned long save_flags; void *ptr; + flags &= slab_gfp_mask; + lockdep_trace_alloc(flags); if (slab_should_failslab(cachep, flags)) @@ -3434,6 +3450,8 @@ __cache_alloc(struct kmem_cache *cachep, gfp_t flags, void *caller) unsigned long save_flags; void *objp; + flags &= slab_gfp_mask; + lockdep_trace_alloc(flags); if (slab_should_failslab(cachep, flags)) diff --git a/mm/slub.c b/mm/slub.c index 3964d3ce4c15..30354bfeb43d 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -178,6 +178,12 @@ static enum { SYSFS /* Sysfs up */ } slab_state = DOWN; +/* + * The slab allocator is initialized with interrupts disabled. Therefore, make + * sure early boot allocations don't accidentally enable interrupts. + */ +static gfp_t slab_gfp_mask __read_mostly = SLAB_GFP_BOOT_MASK; + /* A list of all slab caches on the system */ static DECLARE_RWSEM(slub_lock); static LIST_HEAD(slab_caches); @@ -1595,6 +1601,8 @@ static __always_inline void *slab_alloc(struct kmem_cache *s, unsigned long flags; unsigned int objsize; + gfpflags &= slab_gfp_mask; + lockdep_trace_alloc(gfpflags); might_sleep_if(gfpflags & __GFP_WAIT); @@ -3104,6 +3112,14 @@ void __init kmem_cache_init(void) nr_cpu_ids, nr_node_ids); } +void __init kmem_cache_init_late(void) +{ + /* + * Interrupts are enabled now so all GFP allocations are safe. + */ + slab_gfp_mask = __GFP_BITS_MASK; +} + /* * Find a mergeable slab cache */ -- cgit v1.2.3-58-ga151