Merge commit 'v2.6.28-rc2' into core/locking

Conflicts:
	arch/um/include/asm/system.h

38 files changed, 3890 insertions, 1166 deletions

diff --git a/mm/Kconfig b/mm/Kconfig
index 0bd9c2dbb2a..5b5790f8a81 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -101,7 +101,7 @@ config HAVE_MEMORY_PRESENT
 # with gcc 3.4 and later.
 #
 config SPARSEMEM_STATIC
-	def_bool n
+	bool
 
 #
 # Architecture platforms which require a two level mem_section in SPARSEMEM
@@ -113,7 +113,7 @@ config SPARSEMEM_EXTREME
 	depends on SPARSEMEM && !SPARSEMEM_STATIC
 
 config SPARSEMEM_VMEMMAP_ENABLE
-	def_bool n
+	bool
 
 config SPARSEMEM_VMEMMAP
 	bool "Sparse Memory virtual memmap"
@@ -187,6 +187,9 @@ config RESOURCES_64BIT
 	help
 	  This option allows memory and IO resources to be 64 bit.
 
+config PHYS_ADDR_T_64BIT
+	def_bool 64BIT || ARCH_PHYS_ADDR_T_64BIT
+
 config ZONE_DMA_FLAG
 	int
 	default "0" if !ZONE_DMA
@@ -206,5 +209,16 @@ config VIRT_TO_BUS
 	def_bool y
 	depends on !ARCH_NO_VIRT_TO_BUS
 
+config UNEVICTABLE_LRU
+	bool "Add LRU list to track non-evictable pages"
+	default y
+	depends on MMU
+	help
+	  Keeps unevictable pages off of the active and inactive pageout
+	  lists, so kswapd will not waste CPU time or have its balancing
+	  algorithms thrown off by scanning these pages.  Selecting this
+	  will use one page flag and increase the code size a little,
+	  say Y unless you know what you are doing.
+
 config MMU_NOTIFIER
 	bool
diff --git a/mm/Makefile b/mm/Makefile
index da4ccf015ae..c06b45a1ff5 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -33,5 +33,4 @@ obj-$(CONFIG_FS_XIP) += filemap_xip.o
 obj-$(CONFIG_MIGRATION) += migrate.o
 obj-$(CONFIG_SMP) += allocpercpu.o
 obj-$(CONFIG_QUICKLIST) += quicklist.o
-obj-$(CONFIG_CGROUP_MEM_RES_CTLR) += memcontrol.o
-
+obj-$(CONFIG_CGROUP_MEM_RES_CTLR) += memcontrol.o page_cgroup.o
diff --git a/mm/bootmem.c b/mm/bootmem.c
index ad8eec6e44a..ac5a891f142 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -48,7 +48,7 @@ early_param("bootmem_debug", bootmem_debug_setup);
 	if (unlikely(bootmem_debug))			\
 		printk(KERN_INFO			\
 			"bootmem::%s " fmt,		\
-			__FUNCTION__, ## args);		\
+			__func__, ## args);		\
 })
 
 static unsigned long __init bootmap_bytes(unsigned long pages)
diff --git a/mm/bounce.c b/mm/bounce.c
index b6d2d0f1019..06722c40305 100644
--- a/mm/bounce.c
+++ b/mm/bounce.c
@@ -267,7 +267,7 @@ void blk_queue_bounce(struct request_queue *q, struct bio **bio_orig)
 	/*
 	 * Data-less bio, nothing to bounce
 	 */
-	if (bio_empty_barrier(*bio_orig))
+	if (!bio_has_data(*bio_orig))
 		return;
 
 	/*
diff --git a/mm/fadvise.c b/mm/fadvise.c
index 343cfdfebd9..a1da969bd98 100644
--- a/mm/fadvise.c
+++ b/mm/fadvise.c
@@ -3,7 +3,7 @@
  *
  * Copyright (C) 2002, Linus Torvalds
  *
- * 11Jan2003	akpm@digeo.com
+ * 11Jan2003	Andrew Morton
  *		Initial version.
  */
 
diff --git a/mm/filemap.c b/mm/filemap.c
index 876bc595d0f..ab8553658af 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -33,6 +33,7 @@
 #include <linux/cpuset.h>
 #include <linux/hardirq.h> /* for BUG_ON(!in_atomic()) only */
 #include <linux/memcontrol.h>
+#include <linux/mm_inline.h> /* for page_is_file_cache() */
 #include "internal.h"
 
 /*
@@ -115,12 +116,12 @@ void __remove_from_page_cache(struct page *page)
 {
 	struct address_space *mapping = page->mapping;
 
-	mem_cgroup_uncharge_cache_page(page);
 	radix_tree_delete(&mapping->page_tree, page->index);
 	page->mapping = NULL;
 	mapping->nrpages--;
 	__dec_zone_page_state(page, NR_FILE_PAGES);
 	BUG_ON(page_mapped(page));
+	mem_cgroup_uncharge_cache_page(page);
 
 	/*
 	 * Some filesystems seem to re-dirty the page even after
@@ -492,9 +493,24 @@ EXPORT_SYMBOL(add_to_page_cache_locked);
 int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
 				pgoff_t offset, gfp_t gfp_mask)
 {
-	int ret = add_to_page_cache(page, mapping, offset, gfp_mask);
-	if (ret == 0)
-		lru_cache_add(page);
+	int ret;
+
+	/*
+	 * Splice_read and readahead add shmem/tmpfs pages into the page cache
+	 * before shmem_readpage has a chance to mark them as SwapBacked: they
+	 * need to go on the active_anon lru below, and mem_cgroup_cache_charge
+	 * (called in add_to_page_cache) needs to know where they're going too.
+	 */
+	if (mapping_cap_swap_backed(mapping))
+		SetPageSwapBacked(page);
+
+	ret = add_to_page_cache(page, mapping, offset, gfp_mask);
+	if (ret == 0) {
+		if (page_is_file_cache(page))
+			lru_cache_add_file(page);
+		else
+			lru_cache_add_active_anon(page);
+	}
 	return ret;
 }
 
@@ -557,17 +573,14 @@ EXPORT_SYMBOL(wait_on_page_bit);
  * mechananism between PageLocked pages and PageWriteback pages is shared.
  * But that's OK - sleepers in wait_on_page_writeback() just go back to sleep.
  *
- * The first mb is necessary to safely close the critical section opened by the
- * test_and_set_bit() to lock the page; the second mb is necessary to enforce
- * ordering between the clear_bit and the read of the waitqueue (to avoid SMP
- * races with a parallel wait_on_page_locked()).
+ * The mb is necessary to enforce ordering between the clear_bit and the read
+ * of the waitqueue (to avoid SMP races with a parallel wait_on_page_locked()).
  */
 void unlock_page(struct page *page)
 {
-	smp_mb__before_clear_bit();
-	if (!test_and_clear_bit(PG_locked, &page->flags))
-		BUG();
-	smp_mb__after_clear_bit(); 
+	VM_BUG_ON(!PageLocked(page));
+	clear_bit_unlock(PG_locked, &page->flags);
+	smp_mb__after_clear_bit();
 	wake_up_page(page, PG_locked);
 }
 EXPORT_SYMBOL(unlock_page);
@@ -1100,8 +1113,9 @@ page_ok:
 
 page_not_up_to_date:
 		/* Get exclusive access to the page ... */
-		if (lock_page_killable(page))
-			goto readpage_eio;
+		error = lock_page_killable(page);
+		if (unlikely(error))
+			goto readpage_error;
 
 page_not_up_to_date_locked:
 		/* Did it get truncated before we got the lock? */
@@ -1130,8 +1144,9 @@ readpage:
 		}
 
 		if (!PageUptodate(page)) {
-			if (lock_page_killable(page))
-				goto readpage_eio;
+			error = lock_page_killable(page);
+			if (unlikely(error))
+				goto readpage_error;
 			if (!PageUptodate(page)) {
 				if (page->mapping == NULL) {
 					/*
@@ -1143,15 +1158,14 @@ readpage:
 				}
 				unlock_page(page);
 				shrink_readahead_size_eio(filp, ra);
-				goto readpage_eio;
+				error = -EIO;
+				goto readpage_error;
 			}
 			unlock_page(page);
 		}
 
 		goto page_ok;
 
-readpage_eio:
-		error = -EIO;
 readpage_error:
 		/* UHHUH! A synchronous read error occurred. Report it */
 		desc->error = error;
@@ -1186,8 +1200,7 @@ out:
 	ra->prev_pos |= prev_offset;
 
 	*ppos = ((loff_t)index << PAGE_CACHE_SHIFT) + offset;
-	if (filp)
-		file_accessed(filp);
+	file_accessed(filp);
 }
 
 int file_read_actor(read_descriptor_t *desc, struct page *page,
diff --git a/mm/fremap.c b/mm/fremap.c
index 7881638e4a1..7d12ca70ef7 100644
--- a/mm/fremap.c
+++ b/mm/fremap.c
@@ -21,6 +21,8 @@
 #include <asm/cacheflush.h>
 #include <asm/tlbflush.h>
 
+#include "internal.h"
+
 static void zap_pte(struct mm_struct *mm, struct vm_area_struct *vma,
 			unsigned long addr, pte_t *ptep)
 {
@@ -215,15 +217,31 @@ asmlinkage long sys_remap_file_pages(unsigned long start, unsigned long size,
 		spin_unlock(&mapping->i_mmap_lock);
 	}
 
+	if (vma->vm_flags & VM_LOCKED) {
+		/*
+		 * drop PG_Mlocked flag for over-mapped range
+		 */
+		unsigned int saved_flags = vma->vm_flags;
+		munlock_vma_pages_range(vma, start, start + size);
+		vma->vm_flags = saved_flags;
+	}
+
 	mmu_notifier_invalidate_range_start(mm, start, start + size);
 	err = populate_range(mm, vma, start, size, pgoff);
 	mmu_notifier_invalidate_range_end(mm, start, start + size);
 	if (!err && !(flags & MAP_NONBLOCK)) {
-		if (unlikely(has_write_lock)) {
-			downgrade_write(&mm->mmap_sem);
-			has_write_lock = 0;
+		if (vma->vm_flags & VM_LOCKED) {
+			/*
+			 * might be mapping previously unmapped range of file
+			 */
+			mlock_vma_pages_range(vma, start, start + size);
+		} else {
+			if (unlikely(has_write_lock)) {
+				downgrade_write(&mm->mmap_sem);
+				has_write_lock = 0;
+			}
+			make_pages_present(start, start+size);
 		}
-		make_pages_present(start, start+size);
 	}
 
 	/*
@@ -240,4 +258,3 @@ out:
 
 	return err;
 }
-
diff --git a/mm/highmem.c b/mm/highmem.c
index e16e1523b68..b36b83b920f 100644
--- a/mm/highmem.c
+++ b/mm/highmem.c
@@ -70,6 +70,7 @@ static DECLARE_WAIT_QUEUE_HEAD(pkmap_map_wait);
 static void flush_all_zero_pkmaps(void)
 {
 	int i;
+	int need_flush = 0;
 
 	flush_cache_kmaps();
 
@@ -101,8 +102,10 @@ static void flush_all_zero_pkmaps(void)
 			  &pkmap_page_table[i]);
 
 		set_page_address(page, NULL);
+		need_flush = 1;
 	}
-	flush_tlb_kernel_range(PKMAP_ADDR(0), PKMAP_ADDR(LAST_PKMAP));
+	if (need_flush)
+		flush_tlb_kernel_range(PKMAP_ADDR(0), PKMAP_ADDR(LAST_PKMAP));
 }
 
 /**
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 67a71191136..421aee99b84 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -7,6 +7,7 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/mm.h>
+#include <linux/seq_file.h>
 #include <linux/sysctl.h>
 #include <linux/highmem.h>
 #include <linux/mmu_notifier.h>
@@ -262,7 +263,7 @@ struct resv_map {
 	struct list_head regions;
 };
 
-struct resv_map *resv_map_alloc(void)
+static struct resv_map *resv_map_alloc(void)
 {
 	struct resv_map *resv_map = kmalloc(sizeof(*resv_map), GFP_KERNEL);
 	if (!resv_map)
@@ -274,7 +275,7 @@ struct resv_map *resv_map_alloc(void)
 	return resv_map;
 }
 
-void resv_map_release(struct kref *ref)
+static void resv_map_release(struct kref *ref)
 {
 	struct resv_map *resv_map = container_of(ref, struct resv_map, refs);
 
@@ -289,7 +290,7 @@ static struct resv_map *vma_resv_map(struct vm_area_struct *vma)
 	if (!(vma->vm_flags & VM_SHARED))
 		return (struct resv_map *)(get_vma_private_data(vma) &
 							~HPAGE_RESV_MASK);
-	return 0;
+	return NULL;
 }
 
 static void set_vma_resv_map(struct vm_area_struct *vma, struct resv_map *map)
@@ -1455,15 +1456,15 @@ int hugetlb_overcommit_handler(struct ctl_table *table, int write,
 
 #endif /* CONFIG_SYSCTL */
 
-int hugetlb_report_meminfo(char *buf)
+void hugetlb_report_meminfo(struct seq_file *m)
 {
 	struct hstate *h = &default_hstate;
-	return sprintf(buf,
-			"HugePages_Total: %5lu\n"
-			"HugePages_Free:  %5lu\n"
-			"HugePages_Rsvd:  %5lu\n"
-			"HugePages_Surp:  %5lu\n"
-			"Hugepagesize:    %5lu kB\n",
+	seq_printf(m,
+			"HugePages_Total:   %5lu\n"
+			"HugePages_Free:    %5lu\n"
+			"HugePages_Rsvd:    %5lu\n"
+			"HugePages_Surp:    %5lu\n"
+			"Hugepagesize:   %8lu kB\n",
 			h->nr_huge_pages,
 			h->free_huge_pages,
 			h->resv_huge_pages,
@@ -1747,10 +1748,8 @@ void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
  * from other VMAs and let the children be SIGKILLed if they are faulting the
  * same region.
  */
-int unmap_ref_private(struct mm_struct *mm,
-					struct vm_area_struct *vma,
-					struct page *page,
-					unsigned long address)
+static int unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma,
+				struct page *page, unsigned long address)
 {
 	struct vm_area_struct *iter_vma;
 	struct address_space *mapping;
@@ -2008,7 +2007,7 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	entry = huge_ptep_get(ptep);
 	if (huge_pte_none(entry)) {
 		ret = hugetlb_no_page(mm, vma, address, ptep, write_access);
-		goto out_unlock;
+		goto out_mutex;
 	}
 
 	ret = 0;
@@ -2024,7 +2023,7 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (write_access && !pte_write(entry)) {
 		if (vma_needs_reservation(h, vma, address) < 0) {
 			ret = VM_FAULT_OOM;
-			goto out_unlock;
+			goto out_mutex;
 		}
 
 		if (!(vma->vm_flags & VM_SHARED))
@@ -2034,10 +2033,23 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 
 	spin_lock(&mm->page_table_lock);
 	/* Check for a racing update before calling hugetlb_cow */
-	if (likely(pte_same(entry, huge_ptep_get(ptep))))
-		if (write_access && !pte_write(entry))
+	if (unlikely(!pte_same(entry, huge_ptep_get(ptep))))
+		goto out_page_table_lock;
+
+
+	if (write_access) {
+		if (!pte_write(entry)) {
 			ret = hugetlb_cow(mm, vma, address, ptep, entry,
 							pagecache_page);
+			goto out_page_table_lock;
+		}
+		entry = pte_mkdirty(entry);
+	}
+	entry = pte_mkyoung(entry);
+	if (huge_ptep_set_access_flags(vma, address, ptep, entry, write_access))
+		update_mmu_cache(vma, address, entry);
+
+out_page_table_lock:
 	spin_unlock(&mm->page_table_lock);
 
 	if (pagecache_page) {
@@ -2045,7 +2057,7 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 		put_page(pagecache_page);
 	}
 
-out_unlock:
+out_mutex:
 	mutex_unlock(&hugetlb_instantiation_mutex);
 
 	return ret;
@@ -2060,6 +2072,14 @@ follow_huge_pud(struct mm_struct *mm, unsigned long address,
 	return NULL;
 }
 
+static int huge_zeropage_ok(pte_t *ptep, int write, int shared)
+{
+	if (!ptep || write || shared)
+		return 0;
+	else
+		return huge_pte_none(huge_ptep_get(ptep));
+}
+
 int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 			struct page **pages, struct vm_area_struct **vmas,
 			unsigned long *position, int *length, int i,
@@ -2069,6 +2089,8 @@ int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	unsigned long vaddr = *position;
 	int remainder = *length;
 	struct hstate *h = hstate_vma(vma);
+	int zeropage_ok = 0;
+	int shared = vma->vm_flags & VM_SHARED;
 
 	spin_lock(&mm->page_table_lock);
 	while (vaddr < vma->vm_end && remainder) {
@@ -2081,8 +2103,11 @@ int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		 * first, for the page indexing below to work.
 		 */
 		pte = huge_pte_offset(mm, vaddr & huge_page_mask(h));
+		if (huge_zeropage_ok(pte, write, shared))
+			zeropage_ok = 1;
 
-		if (!pte || huge_pte_none(huge_ptep_get(pte)) ||
+		if (!pte ||
+		    (huge_pte_none(huge_ptep_get(pte)) && !zeropage_ok) ||
 		    (write && !pte_write(huge_ptep_get(pte)))) {
 			int ret;
 
@@ -2102,8 +2127,11 @@ int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		page = pte_page(huge_ptep_get(pte));
 same_page:
 		if (pages) {
-			get_page(page);
-			pages[i] = page + pfn_offset;
+			if (zeropage_ok)
+				pages[i] = ZERO_PAGE(0);
+			else
+				pages[i] = page + pfn_offset;
+			get_page(pages[i]);
 		}
 
 		if (vmas)
diff --git a/mm/internal.h b/mm/internal.h
index 1f43f741697..e4e728bdf32 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -39,6 +39,15 @@ static inline void __put_page(struct page *page)
 	atomic_dec(&page->_count);
 }
 
+/*
+ * in mm/vmscan.c:
+ */
+extern int isolate_lru_page(struct page *page);
+extern void putback_lru_page(struct page *page);
+
+/*
+ * in mm/page_alloc.c
+ */
 extern void __free_pages_bootmem(struct page *page, unsigned int order);
 
 /*
@@ -52,6 +61,120 @@ static inline unsigned long page_order(struct page *page)
 	return page_private(page);
 }
 
+extern long mlock_vma_pages_range(struct vm_area_struct *vma,
+			unsigned long start, unsigned long end);
+extern void munlock_vma_pages_range(struct vm_area_struct *vma,
+			unsigned long start, unsigned long end);
+static inline void munlock_vma_pages_all(struct vm_area_struct *vma)
+{
+	munlock_vma_pages_range(vma, vma->vm_start, vma->vm_end);
+}
+
+#ifdef CONFIG_UNEVICTABLE_LRU
+/*
+ * unevictable_migrate_page() called only from migrate_page_copy() to
+ * migrate unevictable flag to new page.
+ * Note that the old page has been isolated from the LRU lists at this
+ * point so we don't need to worry about LRU statistics.
+ */
+static inline void unevictable_migrate_page(struct page *new, struct page *old)
+{
+	if (TestClearPageUnevictable(old))
+		SetPageUnevictable(new);
+}
+#else
+static inline void unevictable_migrate_page(struct page *new, struct page *old)
+{
+}
+#endif
+
+#ifdef CONFIG_UNEVICTABLE_LRU
+/*
+ * Called only in fault path via page_evictable() for a new page
+ * to determine if it's being mapped into a LOCKED vma.
+ * If so, mark page as mlocked.
+ */
+static inline int is_mlocked_vma(struct vm_area_struct *vma, struct page *page)
+{
+	VM_BUG_ON(PageLRU(page));
+
+	if (likely((vma->vm_flags & (VM_LOCKED | VM_SPECIAL)) != VM_LOCKED))
+		return 0;
+
+	if (!TestSetPageMlocked(page)) {
+		inc_zone_page_state(page, NR_MLOCK);
+		count_vm_event(UNEVICTABLE_PGMLOCKED);
+	}
+	return 1;
+}
+
+/*
+ * must be called with vma's mmap_sem held for read, and page locked.
+ */
+extern void mlock_vma_page(struct page *page);
+
+/*
+ * Clear the page's PageMlocked().  This can be useful in a situation where
+ * we want to unconditionally remove a page from the pagecache -- e.g.,
+ * on truncation or freeing.
+ *
+ * It is legal to call this function for any page, mlocked or not.
+ * If called for a page that is still mapped by mlocked vmas, all we do
+ * is revert to lazy LRU behaviour -- semantics are not broken.
+ */
+extern void __clear_page_mlock(struct page *page);
+static inline void clear_page_mlock(struct page *page)
+{
+	if (unlikely(TestClearPageMlocked(page)))
+		__clear_page_mlock(page);
+}
+
+/*
+ * mlock_migrate_page - called only from migrate_page_copy() to
+ * migrate the Mlocked page flag; update statistics.
+ */
+static inline void mlock_migrate_page(struct page *newpage, struct page *page)
+{
+	if (TestClearPageMlocked(page)) {
+		unsigned long flags;
+
+		local_irq_save(flags);
+		__dec_zone_page_state(page, NR_MLOCK);
+		SetPageMlocked(newpage);
+		__inc_zone_page_state(newpage, NR_MLOCK);
+		local_irq_restore(flags);
+	}
+}
+
+/*
+ * free_page_mlock() -- clean up attempts to free and mlocked() page.
+ * Page should not be on lru, so no need to fix that up.
+ * free_pages_check() will verify...
+ */
+static inline void free_page_mlock(struct page *page)
+{
+	if (unlikely(TestClearPageMlocked(page))) {
+		unsigned long flags;
+
+		local_irq_save(flags);
+		__dec_zone_page_state(page, NR_MLOCK);
+		__count_vm_event(UNEVICTABLE_MLOCKFREED);
+		local_irq_restore(flags);
+	}
+}
+
+#else /* CONFIG_UNEVICTABLE_LRU */
+static inline int is_mlocked_vma(struct vm_area_struct *v, struct page *p)
+{
+	return 0;
+}
+static inline void clear_page_mlock(struct page *page) { }
+static inline void mlock_vma_page(struct page *page) { }
+static inline void mlock_migrate_page(struct page *new, struct page *old) { }
+static inline void free_page_mlock(struct page *page) { }
+
+#endif /* CONFIG_UNEVICTABLE_LRU */
+
 /*
  * FLATMEM and DISCONTIGMEM configurations use alloc_bootmem_node,
  * so all functions starting at paging_init should be marked __init
@@ -120,4 +243,12 @@ static inline void mminit_validate_memmodel_limits(unsigned long *start_pfn,
 }
 #endif /* CONFIG_SPARSEMEM */
 
+#define GUP_FLAGS_WRITE                  0x1
+#define GUP_FLAGS_FORCE                  0x2
+#define GUP_FLAGS_IGNORE_VMA_PERMISSIONS 0x4
+
+int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
+		     unsigned long start, int len, int flags,
+		     struct page **pages, struct vm_area_struct **vmas);
+
 #endif
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 0f1f7a7374b..866dcc7eeb0 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -32,11 +32,12 @@
 #include <linux/fs.h>
 #include <linux/seq_file.h>
 #include <linux/vmalloc.h>
+#include <linux/mm_inline.h>
+#include <linux/page_cgroup.h>
 
 #include <asm/uaccess.h>
 
 struct cgroup_subsys mem_cgroup_subsys __read_mostly;
-static struct kmem_cache *page_cgroup_cache __read_mostly;
 #define MEM_CGROUP_RECLAIM_RETRIES	5
 
 /*
@@ -65,11 +66,10 @@ struct mem_cgroup_stat {
 /*
  * For accounting under irq disable, no need for increment preempt count.
  */
-static void __mem_cgroup_stat_add_safe(struct mem_cgroup_stat *stat,
+static inline void __mem_cgroup_stat_add_safe(struct mem_cgroup_stat_cpu *stat,
 		enum mem_cgroup_stat_index idx, int val)
 {
-	int cpu = smp_processor_id();
-	stat->cpustat[cpu].count[idx] += val;
+	stat->count[idx] += val;
 }
 
 static s64 mem_cgroup_read_stat(struct mem_cgroup_stat *stat,
@@ -85,22 +85,13 @@ static s64 mem_cgroup_read_stat(struct mem_cgroup_stat *stat,
 /*
  * per-zone information in memory controller.
  */
-
-enum mem_cgroup_zstat_index {
-	MEM_CGROUP_ZSTAT_ACTIVE,
-	MEM_CGROUP_ZSTAT_INACTIVE,
-
-	NR_MEM_CGROUP_ZSTAT,
-};
-
 struct mem_cgroup_per_zone {
 	/*
 	 * spin_lock to protect the per cgroup LRU
 	 */
 	spinlock_t		lru_lock;
-	struct list_head	active_list;
-	struct list_head	inactive_list;
-	unsigned long count[NR_MEM_CGROUP_ZSTAT];
+	struct list_head	lists[NR_LRU_LISTS];
+	unsigned long		count[NR_LRU_LISTS];
 };
 /* Macro for accessing counter */
 #define MEM_CGROUP_ZSTAT(mz, idx)	((mz)->count[(idx)])
@@ -144,69 +135,52 @@ struct mem_cgroup {
 };
 static struct mem_cgroup init_mem_cgroup;
 
-/*
- * We use the lower bit of the page->page_cgroup pointer as a bit spin
- * lock.  We need to ensure that page->page_cgroup is at least two
- * byte aligned (based on comments from Nick Piggin).  But since
- * bit_spin_lock doesn't actually set that lock bit in a non-debug
- * uniprocessor kernel, we should avoid setting it here too.
- */
-#define PAGE_CGROUP_LOCK_BIT 	0x0
-#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK)
-#define PAGE_CGROUP_LOCK 	(1 << PAGE_CGROUP_LOCK_BIT)
-#else
-#define PAGE_CGROUP_LOCK	0x0
-#endif
-
-/*
- * A page_cgroup page is associated with every page descriptor. The
- * page_cgroup helps us identify information about the cgroup
- */
-struct page_cgroup {
-	struct list_head lru;		/* per cgroup LRU list */
-	struct page *page;
-	struct mem_cgroup *mem_cgroup;
-	int flags;
-};
-#define PAGE_CGROUP_FLAG_CACHE	(0x1)	/* charged as cache */
-#define PAGE_CGROUP_FLAG_ACTIVE (0x2)	/* page is active in this cgroup */
-
-static int page_cgroup_nid(struct page_cgroup *pc)
-{
-	return page_to_nid(pc->page);
-}
-
-static enum zone_type page_cgroup_zid(struct page_cgroup *pc)
-{
-	return page_zonenum(pc->page);
-}
-
 enum charge_type {
 	MEM_CGROUP_CHARGE_TYPE_CACHE = 0,
 	MEM_CGROUP_CHARGE_TYPE_MAPPED,
+	MEM_CGROUP_CHARGE_TYPE_SHMEM,	/* used by page migration of shmem */
 	MEM_CGROUP_CHARGE_TYPE_FORCE,	/* used by force_empty */
+	NR_CHARGE_TYPE,
+};
+
+/* only for here (for easy reading.) */
+#define PCGF_CACHE	(1UL << PCG_CACHE)
+#define PCGF_USED	(1UL << PCG_USED)
+#define PCGF_ACTIVE	(1UL << PCG_ACTIVE)
+#define PCGF_LOCK	(1UL << PCG_LOCK)
+#define PCGF_FILE	(1UL << PCG_FILE)
+static const unsigned long
+pcg_default_flags[NR_CHARGE_TYPE] = {
+	PCGF_CACHE | PCGF_FILE | PCGF_USED | PCGF_LOCK, /* File Cache */
+	PCGF_ACTIVE | PCGF_USED | PCGF_LOCK, /* Anon */
+	PCGF_ACTIVE | PCGF_CACHE | PCGF_USED | PCGF_LOCK, /* Shmem */
+	0, /* FORCE */
 };
 
 /*
  * Always modified under lru lock. Then, not necessary to preempt_disable()
  */
-static void mem_cgroup_charge_statistics(struct mem_cgroup *mem, int flags,
-					bool charge)
+static void mem_cgroup_charge_statistics(struct mem_cgroup *mem,
+					 struct page_cgroup *pc,
+					 bool charge)
 {
 	int val = (charge)? 1 : -1;
 	struct mem_cgroup_stat *stat = &mem->stat;
+	struct mem_cgroup_stat_cpu *cpustat;
 
 	VM_BUG_ON(!irqs_disabled());
-	if (flags & PAGE_CGROUP_FLAG_CACHE)
-		__mem_cgroup_stat_add_safe(stat, MEM_CGROUP_STAT_CACHE, val);
+
+	cpustat = &stat->cpustat[smp_processor_id()];
+	if (PageCgroupCache(pc))
+		__mem_cgroup_stat_add_safe(cpustat, MEM_CGROUP_STAT_CACHE, val);
 	else
-		__mem_cgroup_stat_add_safe(stat, MEM_CGROUP_STAT_RSS, val);
+		__mem_cgroup_stat_add_safe(cpustat, MEM_CGROUP_STAT_RSS, val);
 
 	if (charge)
-		__mem_cgroup_stat_add_safe(stat,
+		__mem_cgroup_stat_add_safe(cpustat,
 				MEM_CGROUP_STAT_PGPGIN_COUNT, 1);
 	else
-		__mem_cgroup_stat_add_safe(stat,
+		__mem_cgroup_stat_add_safe(cpustat,
 				MEM_CGROUP_STAT_PGPGOUT_COUNT, 1);
 }
 
@@ -227,7 +201,7 @@ page_cgroup_zoneinfo(struct page_cgroup *pc)
 }
 
 static unsigned long mem_cgroup_get_all_zonestat(struct mem_cgroup *mem,
-					enum mem_cgroup_zstat_index idx)
+					enum lru_list idx)
 {
 	int nid, zid;
 	struct mem_cgroup_per_zone *mz;
@@ -250,89 +224,89 @@ static struct mem_cgroup *mem_cgroup_from_cont(struct cgroup *cont)
 
 struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p)
 {
+	/*
+	 * mm_update_next_owner() may clear mm->owner to NULL
+	 * if it races with swapoff, page migration, etc.
+	 * So this can be called with p == NULL.
+	 */
+	if (unlikely(!p))
+		return NULL;
+
 	return container_of(task_subsys_state(p, mem_cgroup_subsys_id),
 				struct mem_cgroup, css);
 }
 
-static inline int page_cgroup_locked(struct page *page)
-{
-	return bit_spin_is_locked(PAGE_CGROUP_LOCK_BIT, &page->page_cgroup);
-}
-
-static void page_assign_page_cgroup(struct pa