Memory controller: memory accounting

Add the accounting hooks.  The accounting is carried out for RSS and Page
Cache (unmapped) pages.  There is now a common limit and accounting for both.
The RSS accounting is accounted at page_add_*_rmap() and page_remove_rmap()
time.  Page cache is accounted at add_to_page_cache(),
__delete_from_page_cache().  Swap cache is also accounted for.

Each page's page_cgroup is protected with the last bit of the
page_cgroup pointer, this makes handling of race conditions involving
simultaneous mappings of a page easier.  A reference count is kept in the
page_cgroup to deal with cases where a page might be unmapped from the RSS
of all tasks, but still lives in the page cache.

Credits go to Vaidyanathan Srinivasan for helping with reference counting work
of the page cgroup.  Almost all of the page cache accounting code has help
from Vaidyanathan Srinivasan.

[hugh@veritas.com: fix swapoff breakage]
[akpm@linux-foundation.org: fix locking]
Signed-off-by: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com>
Signed-off-by: Balbir 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: <Valdis.Kletnieks@vt.edu>
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 42 insertions, 5 deletions

diff --git a/mm/memory.c b/mm/memory.c
index 9d073fa0a2d..0ba224ea6ba 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -50,6 +50,7 @@
 #include <linux/delayacct.h>
 #include <linux/init.h>
 #include <linux/writeback.h>
+#include <linux/memcontrol.h>
 
 #include <asm/pgalloc.h>
 #include <asm/uaccess.h>
@@ -1144,16 +1145,20 @@ static int insert_page(struct mm_struct *mm, unsigned long addr, struct page *pa
 {
 	int retval;
 	pte_t *pte;
-	spinlock_t *ptl;  
+	spinlock_t *ptl;
+
+	retval = mem_cgroup_charge(page, mm);
+	if (retval)
+		goto out;
 
 	retval = -EINVAL;
 	if (PageAnon(page))
-		goto out;
+		goto out_uncharge;
 	retval = -ENOMEM;
 	flush_dcache_page(page);
 	pte = get_locked_pte(mm, addr, &ptl);
 	if (!pte)
-		goto out;
+		goto out_uncharge;
 	retval = -EBUSY;
 	if (!pte_none(*pte))
 		goto out_unlock;
@@ -1165,8 +1170,12 @@ static int insert_page(struct mm_struct *mm, unsigned long addr, struct page *pa
 	set_pte_at(mm, addr, pte, mk_pte(page, prot));
 
 	retval = 0;
+	pte_unmap_unlock(pte, ptl);
+	return retval;
 out_unlock:
 	pte_unmap_unlock(pte, ptl);
+out_uncharge:
+	mem_cgroup_uncharge_page(page);
 out:
 	return retval;
 }
@@ -1641,6 +1650,9 @@ gotten:
 	cow_user_page(new_page, old_page, address, vma);
 	__SetPageUptodate(new_page);
 
+	if (mem_cgroup_charge(new_page, mm))
+		goto oom_free_new;
+
 	/*
 	 * Re-check the pte - we dropped the lock
 	 */
@@ -1672,7 +1684,9 @@ gotten:
 		/* Free the old page.. */
 		new_page = old_page;
 		ret |= VM_FAULT_WRITE;
-	}
+	} else
+		mem_cgroup_uncharge_page(new_page);
+
 	if (new_page)
 		page_cache_release(new_page);
 	if (old_page)
@@ -1696,6 +1710,8 @@ unlock:
 		put_page(dirty_page);
 	}
 	return ret;
+oom_free_new:
+	__free_page(new_page);
 oom:
 	if (old_page)
 		page_cache_release(old_page);
@@ -2036,6 +2052,12 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		count_vm_event(PGMAJFAULT);
 	}
 
+	if (mem_cgroup_charge(page, mm)) {
+		delayacct_clear_flag(DELAYACCT_PF_SWAPIN);
+		ret = VM_FAULT_OOM;
+		goto out;
+	}
+
 	mark_page_accessed(page);
 	lock_page(page);
 	delayacct_clear_flag(DELAYACCT_PF_SWAPIN);
@@ -2073,8 +2095,10 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (write_access) {
 		/* XXX: We could OR the do_wp_page code with this one? */
 		if (do_wp_page(mm, vma, address,
-				page_table, pmd, ptl, pte) & VM_FAULT_OOM)
+				page_table, pmd, ptl, pte) & VM_FAULT_OOM) {
+			mem_cgroup_uncharge_page(page);
 			ret = VM_FAULT_OOM;
+		}
 		goto out;
 	}
 
@@ -2085,6 +2109,7 @@ unlock:
 out:
 	return ret;
 out_nomap:
+	mem_cgroup_uncharge_page(page);
 	pte_unmap_unlock(page_table, ptl);
 	unlock_page(page);
 	page_cache_release(page);
@@ -2114,6 +2139,9 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		goto oom;
 	__SetPageUptodate(page);
 
+	if (mem_cgroup_charge(page, mm))
+		goto oom_free_page;
+
 	entry = mk_pte(page, vma->vm_page_prot);
 	entry = maybe_mkwrite(pte_mkdirty(entry), vma);
 
@@ -2131,8 +2159,11 @@ unlock:
 	pte_unmap_unlock(page_table, ptl);
 	return 0;
 release:
+	mem_cgroup_uncharge_page(page);
 	page_cache_release(page);
 	goto unlock;
+oom_free_page:
+	__free_page(page);
 oom:
 	return VM_FAULT_OOM;
 }
@@ -2246,6 +2277,11 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 
 	}
 
+	if (mem_cgroup_charge(page, mm)) {
+		ret = VM_FAULT_OOM;
+		goto out;
+	}
+
 	page_table = pte_offset_map_lock(mm, pmd, address, &ptl);
 
 	/*
@@ -2281,6 +2317,7 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 		/* no need to invalidate: a not-present page won't be cached */
 		update_mmu_cache(vma, address, entry);
 	} else {
+		mem_cgroup_uncharge_page(page);
 		if (anon)
 			page_cache_release(page);
 		else