Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6

Conflicts:

	Documentation/kernel-parameters.txt
	arch/sh/include/asm/elf.h

20 files changed, 114 insertions, 59 deletions

diff --git a/mm/Kconfig b/mm/Kconfig
index 0bd9c2dbb2a..1a501a4de95 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
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..903bf316912 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1100,8 +1100,9 @@ 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 +1131,9 @@ 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 +1145,14 @@ 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 +1187,7 @@ 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/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..38633864a93 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2008,7 +2008,7 @@ 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 +2024,7 @@ 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 +2034,23 @@ 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 +2058,7 @@ 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;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 0f1f7a7374b..36896f3eb7f 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -250,6 +250,14 @@ 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);
 }
@@ -549,6 +557,11 @@ static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm,
 	if (likely(!memcg)) {
 		rcu_read_lock();
 		mem = mem_cgroup_from_task(rcu_dereference(mm->owner));
+		if (unlikely(!mem)) {
+			rcu_read_unlock();
+			kmem_cache_free(page_cgroup_cache, pc);
+			return 0;
+		}
 		/*
 		 * For every charge from the cgroup, increment reference count
 		 */
@@ -801,11 +814,16 @@ int mem_cgroup_shrink_usage(struct mm_struct *mm, gfp_t gfp_mask)
 
 	rcu_read_lock();
 	mem = mem_cgroup_from_task(rcu_dereference(mm->owner));
+	if (unlikely(!mem)) {
+		rcu_read_unlock();
+		return 0;
+	}
 	css_get(&mem->css);
 	rcu_read_unlock();
 
 	do {
 		progress = try_to_free_mem_cgroup_pages(mem, gfp_mask);
+		progress += res_counter_check_under_limit(&mem->res);
 	} while (!progress && --retry);
 
 	css_put(&mem->css);
diff --git a/mm/mmzone.c b/mm/mmzone.c
index 486ed595ee6..16ce8b955dc 100644
--- a/mm/mmzone.c
+++ b/mm/mmzone.c
@@ -69,6 +69,6 @@ struct zoneref *next_zones_zonelist(struct zoneref *z,
 				(z->zone && !zref_in_nodemask(z, nodes)))
 			z++;
 
-	*zone = zonelist_zone(z++);
+	*zone = zonelist_zone(z);
 	return z;
 }
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 24de8b65fdb..b40f6d5f8fe 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -7,7 +7,7 @@
  * Contains functions related to writing back dirty pages at the
  * address_space level.
  *
- * 10Apr2002	akpm@zip.com.au
+ * 10Apr2002	Andrew Morton
  *		Initial version
  */
 
@@ -876,6 +876,7 @@ int write_cache_pages(struct address_space *mapping,
 	pgoff_t end;		/* Inclusive */
 	int scanned = 0;
 	int range_whole = 0;
+	long nr_to_write = wbc->nr_to_write;
 
 	if (wbc->nonblocking && bdi_write_congested(bdi)) {
 		wbc->encountered_congestion = 1;
@@ -939,7 +940,7 @@ retry:
 				unlock_page(page);
 				ret = 0;
 			}
-			if (ret || (--(wbc->nr_to_write) <= 0))
+			if (ret || (--nr_to_write <= 0))
 				done = 1;
 			if (wbc->nonblocking && bdi_write_congested(bdi)) {
 				wbc->encountered_congestion = 1;
@@ -958,11 +959,12 @@ retry:
 		index = 0;
 		goto retry;
 	}
-	if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
-		mapping->writeback_index = index;
+	if (!wbc->no_nrwrite_index_update) {
+		if (wbc->range_cyclic || (range_whole && nr_to_write > 0))
+			mapping->writeback_index = index;
+		wbc->nr_to_write = nr_to_write;
+	}
 
-	if (wbc->range_cont)
-		wbc->range_start = index << PAGE_CACHE_SHIFT;
 	return ret;
 }
 EXPORT_SYMBOL(write_cache_pages);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index e293c58bea5..9eb9eb92828 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -268,13 +268,14 @@ void prep_compound_page(struct page *page, unsigned long order)
 {
 	int i;
 	int nr_pages = 1 << order;
+	struct page *p = page + 1;
 
 	set_compound_page_dtor(page, free_compound_page);
 	set_compound_order(page, order);
 	__SetPageHead(page);
-	for (i = 1; i < nr_pages; i++) {
-		struct page *p = page + i;
-
+	for (i = 1; i < nr_pages; i++, p++) {
+		if (unlikely((i & (MAX_ORDER_NR_PAGES - 1)) == 0))
+			p = pfn_to_page(page_to_pfn(page) + i);
 		__SetPageTail(p);
 		p->first_page = page;
 	}
@@ -284,6 +285,7 @@ static void destroy_compound_page(struct page *page, unsigned long order)
 {
 	int i;
 	int nr_pages = 1 << order;
+	struct page *p = page + 1;
 
 	if (unlikely(compound_order(page) != order))
 		bad_page(page);
@@ -291,8 +293,9 @@ static void destroy_compound_page(struct page *page, unsigned long order)
 	if (unlikely(!PageHead(page)))
 			bad_page(page);
 	__ClearPageHead(page);
-	for (i = 1; i < nr_pages; i++) {
-		struct page *p = page + i;
+	for (i = 1; i < nr_pages; i++, p++) {
+		if (unlikely((i & (MAX_ORDER_NR_PAGES - 1)) == 0))
+			p = pfn_to_page(page_to_pfn(page) + i);
 
 		if (unlikely(!PageTail(p) |
 				(p->first_page != page)))
@@ -3949,7 +3952,7 @@ static void check_for_regular_memory(pg_data_t *pgdat)
 void __init free_area_init_nodes(unsigned long *max_zone_pfn)
 {
 	unsigned long nid;
-	enum zone_type i;
+	int i;
 
 	/* Sort early_node_map as initialisation assumes it is sorted */
 	sort_node_map();
diff --git a/mm/page_isolation.c b/mm/page_isolation.c
index c69f84fe038..b70a7fec1ff 100644
--- a/mm/page_isolation.c
+++ b/mm/page_isolation.c
@@ -114,8 +114,10 @@ __test_page_isolated_in_pageblock(unsigned long pfn, unsigned long end_pfn)
 
 int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn)
 {
-	unsigned long pfn;
+	unsigned long pfn, flags;
 	struct page *page;
+	struct zone *zone;
+	int ret;
 
 	pfn = start_pfn;
 	/*
@@ -131,7 +133,9 @@ int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn)
 	if (pfn < end_pfn)
 		return -EBUSY;
 	/* Check all pages are free or Marked as ISOLATED */
-	if (__test_page_isolated_in_pageblock(start_pfn, end_pfn))
-		return 0;
-	return -EBUSY;
+	zone = page_zone(pfn_to_page(pfn));
+	spin_lock_irqsave(&zone->lock, flags);
+	ret = __test_page_isolated_in_pageblock(start_pfn, end_pfn);
+	spin_unlock_irqrestore(&zone->lock, flags);
+	return ret ? 0 : -EBUSY;
 }
diff --git a/mm/pdflush.c b/mm/pdflush.c
index 0cbe0c60c6b..a0a14c4d507 100644
--- a/mm/pdflush.c
+++ b/mm/pdflush.c
@@ -3,7 +3,7 @@
  *
  * Copyright (C) 2002, Linus Torvalds.
  *
- * 09Apr2002	akpm@zip.com.au
+ * 09Apr2002	Andrew Morton
  *		Initial version
  * 29Feb2004	kaos@sgi.com
  *		Move worker thread creation to kthread to avoid chewing
diff --git a/mm/readahead.c b/mm/readahead.c
index 77e8ddf945e..6cbd9a72fde 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -3,7 +3,7 @@
  *
  * Copyright (C) 2002, Linus Torvalds
  *
- * 09Apr2002	akpm@zip.com.au
+ * 09Apr2002	Andrew Morton
  *		Initial version.
  */
 
diff --git a/mm/shmem.c b/mm/shmem.c
index 04fb4f1ab88..d87958a5f03 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -50,14 +50,12 @@
 #include <linux/migrate.h>
 #include <linux/highmem.h>
 #include <linux/seq_file.h>
+#include <linux/magic.h>
 
 #include <asm/uaccess.h>
 #include <asm/div64.h>
 #include <asm/pgtable.h>
 
-/* This magic number is used in glibc for posix shared memory */
-#define TMPFS_MAGIC	0x01021994
-
 #define ENTRIES_PER_PAGE (PAGE_CACHE_SIZE/sizeof(unsigned long))
 #define ENTRIES_PER_PAGEPAGE (ENTRIES_PER_PAGE*ENTRIES_PER_PAGE)
 #define BLOCKS_PER_PAGE  (PAGE_CACHE_SIZE/512)
@@ -2582,6 +2580,7 @@ put_memory:
 	shmem_unacct_size(flags, size);
 	return ERR_PTR(error);
 }
+EXPORT_SYMBOL_GPL(shmem_file_setup);
 
 /**
  * shmem_zero_setup - setup a shared anonymous mapping
diff --git a/mm/slob.c b/mm/slob.c
index 4c82dd41f32..cb675d12679 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -514,9 +514,11 @@ size_t ksize(const void *block)
 		return 0;
 
 	sp = (struct slob_page *)virt_to_page(block);
-	if (slob_page(sp))
-		return ((slob_t *)block - 1)->units + SLOB_UNIT;
-	else
+	if (slob_page(sp)) {
+		int align = max(ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN);
+		unsigned int *m = (unsigned int *)(block - align);
+		return SLOB_UNITS(*m) * SLOB_UNIT;
+	} else
 		return sp->page.private;
 }
 
diff --git a/mm/slub.c b/mm/slub.c
index fb486d5540f..0c83e6afe7b 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1932,6 +1932,7 @@ init_kmem_cache_node(struct kmem_cache_node *n, struct kmem_cache *s)
 	INIT_LIST_HEAD(&n->partial);
 #ifdef CONFIG_SLUB_DEBUG
 	atomic_long_set(&n->nr_slabs, 0);
+	atomic_long_set(&n->total_objects, 0);
 	INIT_LIST_HEAD(&n->full);
 #endif
 }
diff --git a/mm/tiny-shmem.c b/mm/tiny-shmem.c
index ae532f50194..8d7a27a6335 100644
--- a/mm/tiny-shmem.c
+++ b/mm/tiny-shmem.c
@@ -65,31 +65,31 @@ struct file *shmem_file_setup(char *name, loff_t size, unsigned long flags)
 	if (!dentry)
 		goto put_memory;
 
+	error = -ENFILE;
+	file = get_empty_filp();
+	if (!file)
+		goto put_dentry;
+
 	error = -ENOSPC;
 	inode = ramfs_get_inode(root->d_sb, S_IFREG | S_IRWXUGO, 0);
 	if (!inode)
-		goto put_dentry;
+		goto close_file;
 
 	d_instantiate(dentry, inode);
-	error = -ENFILE;
-	file = alloc_file(shm_mnt, dentry, FMODE_WRITE | FMODE_READ,
-			&ramfs_file_operations);
-	if (!file)
-		goto put_dentry;
-
+	inode->i_size = size;
 	inode->i_nlink = 0;	/* It is unlinked */
+	init_file(file, shm_mnt, dentry, FMODE_WRITE | FMODE_READ,
+			&ramfs_file_operations);
 
-	/* notify everyone as to the change of file size */
-	error = do_truncate(dentry, size, 0, file);
-	if (error < 0)
+#ifndef CONFIG_MMU
+	error = ramfs_nommu_expand_for_mapping(inode, size);
+	if (error)
 		goto close_file;
-
+#endif
 	return file;
 
 close_file:
 	put_filp(file);
-	return ERR_PTR(error);
-
 put_dentry:
 	dput(dentry);
 put_memory:
diff --git a/mm/truncate.c b/mm/truncate.c
index 6650c1d878b..e83e4b114ef 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -3,7 +3,7 @@
  *
  * Copyright (C) 2002, Linus Torvalds
  *
- * 10Sep2002	akpm@zip.com.au
+ * 10Sep2002	Andrew Morton
  *		Initial version.
  */
 
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 85b9a0d2c87..bba06c41fc5 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -180,6 +180,13 @@ struct page *vmalloc_to_page(const void *vmalloc_addr)
 	pmd_t *pmd;
 	pte_t *ptep, pte;
 
+	/*
+	 * XXX we might need to change this if we add VIRTUAL_BUG_ON for
+	 * architectures that do not vmalloc module space
+	 */
+	VIRTUAL_BUG_ON(!is_vmalloc_addr(vmalloc_addr) &&
+			!is_module_address(addr));
+
 	if (!pgd_none(*pgd)) {
 		pud = pud_offset(pgd, addr);
 		if (!pud_none(*pud)) {