Commit e1a1cd59 authored by Balbir Singh's avatar Balbir Singh Committed by Linus Torvalds
Browse files

Memory controller: make charging gfp mask aware 



Nick Piggin pointed out that swap cache and page cache addition routines
could be called from non GFP_KERNEL contexts.  This patch makes the
charging routine aware of the gfp context.  Charging might fail if the
cgroup is over it's limit, in which case a suitable error is returned.

This patch was tested on a Powerpc box.  I am still looking at being able
to test the path, through which allocations happen in non GFP_KERNEL
contexts.

[kamezawa.hiroyu@jp.fujitsu.com: problem with ZONE_MOVABLE]
Signed-off-by: default avatarBalbir Singh <balbir@linux.vnet.ibm.com>
Cc: Pavel Emelianov <xemul@openvz.org>
Cc: Paul Menage <menage@google.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Kirill Korotaev <dev@sw.ru>
Cc: Herbert Poetzl <herbert@13thfloor.at>
Cc: David Rientjes <rientjes@google.com>
Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com>
Signed-off-by: default avatarKAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent bed7161a

include/linux/memcontrol.h

+8 −4
Original line number Diff line number Diff line
@@ -32,7 +32,8 @@ extern void mm_free_cgroup(struct mm_struct *mm); 
extern void page_assign_page_cgroup(struct page *page,

					struct page_cgroup *pc);

extern struct page_cgroup *page_get_page_cgroup(struct page *page);

extern int mem_cgroup_charge(struct page *page, struct mm_struct *mm);

extern int mem_cgroup_charge(struct page *page, struct mm_struct *mm,

				gfp_t gfp_mask);

extern void mem_cgroup_uncharge(struct page_cgroup *pc);

extern void mem_cgroup_move_lists(struct page_cgroup *pc, bool active);

extern unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
@@ -42,7 +43,8 @@ extern unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan, 
					struct mem_cgroup *mem_cont,

					int active);

extern void mem_cgroup_out_of_memory(struct mem_cgroup *mem, gfp_t gfp_mask);

extern int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm);

extern int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,

					gfp_t gfp_mask);

extern struct mem_cgroup *mm_cgroup(struct mm_struct *mm);



static inline void mem_cgroup_uncharge_page(struct page *page)
@@ -70,7 +72,8 @@ static inline struct page_cgroup *page_get_page_cgroup(struct page *page) 
	return NULL;

}



static inline int mem_cgroup_charge(struct page *page, struct mm_struct *mm)

static inline int mem_cgroup_charge(struct page *page, struct mm_struct *mm,

					gfp_t gfp_mask)

{

	return 0;

}
@@ -89,7 +92,8 @@ static inline void mem_cgroup_move_lists(struct page_cgroup *pc, 
}



static inline int mem_cgroup_cache_charge(struct page *page,

						struct mm_struct *mm)

						struct mm_struct *mm,

						gfp_t gfp_mask)

{

	return 0;

}

include/linux/swap.h

+2 −1
Original line number Diff line number Diff line
@@ -183,7 +183,8 @@ extern void swap_setup(void); 
/* linux/mm/vmscan.c */

extern unsigned long try_to_free_pages(struct zone **zones, int order,

					gfp_t gfp_mask);

extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem);

extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem,

							gfp_t gfp_mask);

extern int __isolate_lru_page(struct page *page, int mode);

extern unsigned long shrink_all_memory(unsigned long nr_pages);

extern int vm_swappiness;

mm/filemap.c

+1 −1
Original line number Diff line number Diff line
@@ -464,7 +464,7 @@ int add_to_page_cache(struct page *page, struct address_space *mapping, 


	if (error == 0) {



		error = mem_cgroup_cache_charge(page, current->mm);

		error = mem_cgroup_cache_charge(page, current->mm, gfp_mask);

		if (error)

			goto out;

mm/memcontrol.c

+17 −7
Original line number Diff line number Diff line
@@ -261,7 +261,8 @@ unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan, 
 * 0 if the charge was successful

 * < 0 if the cgroup is over its limit

 */

int mem_cgroup_charge(struct page *page, struct mm_struct *mm)

int mem_cgroup_charge(struct page *page, struct mm_struct *mm,

				gfp_t gfp_mask)

{

	struct mem_cgroup *mem;

	struct page_cgroup *pc, *race_pc;
@@ -293,7 +294,7 @@ retry: 


	unlock_page_cgroup(page);



	pc = kzalloc(sizeof(struct page_cgroup), GFP_KERNEL);

	pc = kzalloc(sizeof(struct page_cgroup), gfp_mask);

	if (pc == NULL)

		goto err;
@@ -320,7 +321,14 @@ retry: 
	 * the cgroup limit.

	 */

	while (res_counter_charge(&mem->res, PAGE_SIZE)) {

		if (try_to_free_mem_cgroup_pages(mem))

		bool is_atomic = gfp_mask & GFP_ATOMIC;

		/*

		 * We cannot reclaim under GFP_ATOMIC, fail the charge

		 */

		if (is_atomic)

			goto noreclaim;



		if (try_to_free_mem_cgroup_pages(mem, gfp_mask))

			continue;



		/*
@@ -344,8 +352,9 @@ retry: 
			congestion_wait(WRITE, HZ/10);

			continue;

		}



noreclaim:

		css_put(&mem->css);

		if (!is_atomic)

			mem_cgroup_out_of_memory(mem, GFP_KERNEL);

		goto free_pc;

	}
@@ -385,7 +394,8 @@ err: 
/*

 * See if the cached pages should be charged at all?

 */

int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm)

int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,

				gfp_t gfp_mask)

{

	struct mem_cgroup *mem;

	if (!mm)
@@ -393,7 +403,7 @@ int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm) 


	mem = rcu_dereference(mm->mem_cgroup);

	if (mem->control_type == MEM_CGROUP_TYPE_ALL)

		return mem_cgroup_charge(page, mm);

		return mem_cgroup_charge(page, mm, gfp_mask);

	else

		return 0;

}

mm/memory.c

+5 −5
Original line number Diff line number Diff line
@@ -1147,7 +1147,7 @@ static int insert_page(struct mm_struct *mm, unsigned long addr, struct page *pa 
	pte_t *pte;

	spinlock_t *ptl;



	retval = mem_cgroup_charge(page, mm);

	retval = mem_cgroup_charge(page, mm, GFP_KERNEL);

	if (retval)

		goto out;
@@ -1650,7 +1650,7 @@ gotten: 
	cow_user_page(new_page, old_page, address, vma);

	__SetPageUptodate(new_page);



	if (mem_cgroup_charge(new_page, mm))

	if (mem_cgroup_charge(new_page, mm, GFP_KERNEL))

		goto oom_free_new;



	/*
@@ -2052,7 +2052,7 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, 
		count_vm_event(PGMAJFAULT);

	}



	if (mem_cgroup_charge(page, mm)) {

	if (mem_cgroup_charge(page, mm, GFP_KERNEL)) {

		delayacct_clear_flag(DELAYACCT_PF_SWAPIN);

		ret = VM_FAULT_OOM;

		goto out;
@@ -2139,7 +2139,7 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, 
		goto oom;

	__SetPageUptodate(page);



	if (mem_cgroup_charge(page, mm))

	if (mem_cgroup_charge(page, mm, GFP_KERNEL))

		goto oom_free_page;



	entry = mk_pte(page, vma->vm_page_prot);
@@ -2277,7 +2277,7 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma, 


	}



	if (mem_cgroup_charge(page, mm)) {

	if (mem_cgroup_charge(page, mm, GFP_KERNEL)) {

		ret = VM_FAULT_OOM;

		goto out;

	}

CRA Git | Maintained and supported by SUSTech CRA and CCSE