From ab50b8ed818016cfecd747d6d4bb9139986bc029 Mon Sep 17 00:00:00 2001
From: Hugh Dickins <hugh@veritas.com>
Date: Sat, 29 Oct 2005 18:15:56 -0700
Subject: [PATCH] mm: vm_stat_account unshackled

The original vm_stat_account has fallen into disuse, with only one user, and
only one user of vm_stat_unaccount.  It's easier to keep track if we convert
them all to __vm_stat_account, then free it from its __shackles.

Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
---
 mm/mprotect.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'mm/mprotect.c')

diff --git a/mm/mprotect.c b/mm/mprotect.c
index 57577f63b30..b426f01c5e9 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -168,8 +168,8 @@ success:
 	vma->vm_flags = newflags;
 	vma->vm_page_prot = newprot;
 	change_protection(vma, start, end, newprot);
-	__vm_stat_account(mm, oldflags, vma->vm_file, -nrpages);
-	__vm_stat_account(mm, newflags, vma->vm_file, nrpages);
+	vm_stat_account(mm, oldflags, vma->vm_file, -nrpages);
+	vm_stat_account(mm, newflags, vma->vm_file, nrpages);
 	return 0;
 
 fail:
-- 
cgit v1.2.3-70-g09d2


From b5810039a54e5babf428e9a1e89fc1940fabff11 Mon Sep 17 00:00:00 2001
From: Nick Piggin <nickpiggin@yahoo.com.au>
Date: Sat, 29 Oct 2005 18:16:12 -0700
Subject: [PATCH] core remove PageReserved

Remove PageReserved() calls from core code by tightening VM_RESERVED
handling in mm/ to cover PageReserved functionality.

PageReserved special casing is removed from get_page and put_page.

All setting and clearing of PageReserved is retained, and it is now flagged
in the page_alloc checks to help ensure we don't introduce any refcount
based freeing of Reserved pages.

MAP_PRIVATE, PROT_WRITE of VM_RESERVED regions is tentatively being
deprecated.  We never completely handled it correctly anyway, and is be
reintroduced in future if required (Hugh has a proof of concept).

Once PageReserved() calls are removed from kernel/power/swsusp.c, and all
arch/ and driver code, the Set and Clear calls, and the PG_reserved bit can
be trivially removed.

Last real user of PageReserved is swsusp, which uses PageReserved to
determine whether a struct page points to valid memory or not.  This still
needs to be addressed (a generic page_is_ram() should work).

A last caveat: the ZERO_PAGE is now refcounted and managed with rmap (and
thus mapcounted and count towards shared rss).  These writes to the struct
page could cause excessive cacheline bouncing on big systems.  There are a
number of ways this could be addressed if it is an issue.

Signed-off-by: Nick Piggin <npiggin@suse.de>

Refcount bug fix for filemap_xip.c

Signed-off-by: Carsten Otte <cotte@de.ibm.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
---
 arch/ppc64/kernel/vdso.c  |  12 +++--
 arch/sparc/mm/generic.c   |   3 ++
 arch/sparc64/mm/generic.c |   3 ++
 drivers/scsi/sg.c         |  12 +++--
 drivers/scsi/st.c         |  10 ++--
 fs/direct-io.c            |   4 +-
 include/linux/mm.h        |   5 +-
 kernel/power/swsusp.c     |  25 +++++----
 mm/bootmem.c              |   1 +
 mm/filemap_xip.c          |  11 ++--
 mm/fremap.c               |  23 ++++----
 mm/madvise.c              |   2 +-
 mm/memory.c               | 131 ++++++++++++++++++++++++++++------------------
 mm/mempolicy.c            |  29 +++++-----
 mm/mmap.c                 |  11 ++++
 mm/mprotect.c             |   8 +++
 mm/msync.c                |  17 +++---
 mm/page_alloc.c           |  14 ++---
 mm/rmap.c                 |  14 ++---
 mm/shmem.c                |   4 +-
 mm/swap.c                 |   4 +-
 sound/core/pcm_native.c   |   9 ++--
 22 files changed, 218 insertions(+), 134 deletions(-)

(limited to 'mm/mprotect.c')

diff --git a/arch/ppc64/kernel/vdso.c b/arch/ppc64/kernel/vdso.c
index efa985f05ac..4aacf521e3e 100644
--- a/arch/ppc64/kernel/vdso.c
+++ b/arch/ppc64/kernel/vdso.c
@@ -176,13 +176,13 @@ static struct page * vdso_vma_nopage(struct vm_area_struct * vma,
 		return NOPAGE_SIGBUS;
 
 	/*
-	 * Last page is systemcfg, special handling here, no get_page() a
-	 * this is a reserved page
+	 * Last page is systemcfg.
 	 */
 	if ((vma->vm_end - address) <= PAGE_SIZE)
-		return virt_to_page(systemcfg);
+		pg = virt_to_page(systemcfg);
+	else
+		pg = virt_to_page(vbase + offset);
 
-	pg = virt_to_page(vbase + offset);
 	get_page(pg);
 	DBG(" ->page count: %d\n", page_count(pg));
 
@@ -259,7 +259,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int executable_stack)
 	 * gettimeofday will be totally dead. It's fine to use that for setting
 	 * breakpoints in the vDSO code pages though
 	 */
-	vma->vm_flags = VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC;
+	vma->vm_flags = VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC | VM_RESERVED;
 	vma->vm_flags |= mm->def_flags;
 	vma->vm_page_prot = protection_map[vma->vm_flags & 0x7];
 	vma->vm_ops = &vdso_vmops;
@@ -603,6 +603,8 @@ void __init vdso_init(void)
 		ClearPageReserved(pg);
 		get_page(pg);
 	}
+
+	get_page(virt_to_page(systemcfg));
 }
 
 int in_gate_area_no_task(unsigned long addr)
diff --git a/arch/sparc/mm/generic.c b/arch/sparc/mm/generic.c
index 20ccb957fb7..659c9a71f86 100644
--- a/arch/sparc/mm/generic.c
+++ b/arch/sparc/mm/generic.c
@@ -73,6 +73,9 @@ int io_remap_pfn_range(struct vm_area_struct *vma, unsigned long from,
 	int space = GET_IOSPACE(pfn);
 	unsigned long offset = GET_PFN(pfn) << PAGE_SHIFT;
 
+	/* See comment in mm/memory.c remap_pfn_range */
+	vma->vm_flags |= VM_IO | VM_RESERVED;
+
 	prot = __pgprot(pg_iobits);
 	offset -= from;
 	dir = pgd_offset(mm, from);
diff --git a/arch/sparc64/mm/generic.c b/arch/sparc64/mm/generic.c
index c954d91f01d..afc01cec701 100644
--- a/arch/sparc64/mm/generic.c
+++ b/arch/sparc64/mm/generic.c
@@ -127,6 +127,9 @@ int io_remap_pfn_range(struct vm_area_struct *vma, unsigned long from,
 	int space = GET_IOSPACE(pfn);
 	unsigned long offset = GET_PFN(pfn) << PAGE_SHIFT;
 
+	/* See comment in mm/memory.c remap_pfn_range */
+	vma->vm_flags |= VM_IO | VM_RESERVED;
+
 	prot = __pgprot(pg_iobits);
 	offset -= from;
 	dir = pgd_offset(mm, from);
diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index 861e51375d7..2d30b46806b 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -1886,13 +1886,17 @@ st_unmap_user_pages(struct scatterlist *sgl, const unsigned int nr_pages,
 	int i;
 
 	for (i=0; i < nr_pages; i++) {
-		if (dirtied && !PageReserved(sgl[i].page))
-			SetPageDirty(sgl[i].page);
-		/* unlock_page(sgl[i].page); */
+		struct page *page = sgl[i].page;
+
+		/* XXX: just for debug. Remove when PageReserved is removed */
+		BUG_ON(PageReserved(page));
+		if (dirtied)
+			SetPageDirty(page);
+		/* unlock_page(page); */
 		/* FIXME: cache flush missing for rw==READ
 		 * FIXME: call the correct reference counting function
 		 */
-		page_cache_release(sgl[i].page);
+		page_cache_release(page);
 	}
 
 	return 0;
diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c
index 5eb54d8019b..da9766283bd 100644
--- a/drivers/scsi/st.c
+++ b/drivers/scsi/st.c
@@ -4526,12 +4526,16 @@ static int sgl_unmap_user_pages(struct scatterlist *sgl, const unsigned int nr_p
 	int i;
 
 	for (i=0; i < nr_pages; i++) {
-		if (dirtied && !PageReserved(sgl[i].page))
-			SetPageDirty(sgl[i].page);
+		struct page *page = sgl[i].page;
+
+		/* XXX: just for debug. Remove when PageReserved is removed */
+		BUG_ON(PageReserved(page));
+		if (dirtied)
+			SetPageDirty(page);
 		/* FIXME: cache flush missing for rw==READ
 		 * FIXME: call the correct reference counting function
 		 */
-		page_cache_release(sgl[i].page);
+		page_cache_release(page);
 	}
 
 	return 0;
diff --git a/fs/direct-io.c b/fs/direct-io.c
index 0d06097bc99..3931e7f1e6b 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -162,6 +162,7 @@ static int dio_refill_pages(struct dio *dio)
 	up_read(&current->mm->mmap_sem);
 
 	if (ret < 0 && dio->blocks_available && (dio->rw == WRITE)) {
+		struct page *page = ZERO_PAGE(dio->curr_user_address);
 		/*
 		 * A memory fault, but the filesystem has some outstanding
 		 * mapped blocks.  We need to use those blocks up to avoid
@@ -169,7 +170,8 @@ static int dio_refill_pages(struct dio *dio)
 		 */
 		if (dio->page_errors == 0)
 			dio->page_errors = ret;
-		dio->pages[0] = ZERO_PAGE(dio->curr_user_address);
+		page_cache_get(page);
+		dio->pages[0] = page;
 		dio->head = 0;
 		dio->tail = 1;
 		ret = 0;
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 0c64484d8ae..da42093250c 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -157,7 +157,7 @@ extern unsigned int kobjsize(const void *objp);
 
 #define VM_DONTCOPY	0x00020000      /* Do not copy this vma on fork */
 #define VM_DONTEXPAND	0x00040000	/* Cannot expand with mremap() */
-#define VM_RESERVED	0x00080000	/* Don't unmap it from swap_out */
+#define VM_RESERVED	0x00080000	/* Pages managed in a special way */
 #define VM_ACCOUNT	0x00100000	/* Is a VM accounted object */
 #define VM_HUGETLB	0x00400000	/* Huge TLB Page VM */
 #define VM_NONLINEAR	0x00800000	/* Is non-linear (remap_file_pages) */
@@ -338,7 +338,7 @@ static inline void get_page(struct page *page)
 
 static inline void put_page(struct page *page)
 {
-	if (!PageReserved(page) && put_page_testzero(page))
+	if (put_page_testzero(page))
 		__page_cache_release(page);
 }
 
@@ -723,6 +723,7 @@ void install_arg_page(struct vm_area_struct *, struct page *, unsigned long);
 
 int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, unsigned long start,
 		int len, int write, int force, struct page **pages, struct vm_area_struct **vmas);
+void print_bad_pte(struct vm_area_struct *, pte_t, unsigned long);
 
 int __set_page_dirty_buffers(struct page *page);
 int __set_page_dirty_nobuffers(struct page *page);
diff --git a/kernel/power/swsusp.c b/kernel/power/swsusp.c
index 10bc5ec496d..016504ccfcc 100644
--- a/kernel/power/swsusp.c
+++ b/kernel/power/swsusp.c
@@ -578,15 +578,23 @@ static int save_highmem_zone(struct zone *zone)
 			continue;
 		page = pfn_to_page(pfn);
 		/*
-		 * This condition results from rvmalloc() sans vmalloc_32()
-		 * and architectural memory reservations. This should be
-		 * corrected eventually when the cases giving rise to this
-		 * are better understood.
+		 * PageReserved results from rvmalloc() sans vmalloc_32()
+		 * and architectural memory reservations.
+		 *
+		 * rvmalloc should not cause this, because all implementations
+		 * appear to always be using vmalloc_32 on architectures with
+		 * highmem. This is a good thing, because we would like to save
+		 * rvmalloc pages.
+		 *
+		 * It appears to be triggered by pages which do not point to
+		 * valid memory (see arch/i386/mm/init.c:one_highpage_init(),
+		 * which sets PageReserved if the page does not point to valid
+		 * RAM.
+		 *
+		 * XXX: must remove usage of PageReserved!
 		 */
-		if (PageReserved(page)) {
-			printk("highmem reserved page?!\n");
+		if (PageReserved(page))
 			continue;
-		}
 		BUG_ON(PageNosave(page));
 		if (PageNosaveFree(page))
 			continue;
@@ -672,10 +680,9 @@ static int saveable(struct zone * zone, unsigned long * zone_pfn)
 		return 0;
 
 	page = pfn_to_page(pfn);
-	BUG_ON(PageReserved(page) && PageNosave(page));
 	if (PageNosave(page))
 		return 0;
-	if (PageReserved(page) && pfn_is_nosave(pfn)) {
+	if (pfn_is_nosave(pfn)) {
 		pr_debug("[nosave pfn 0x%lx]", pfn);
 		return 0;
 	}
diff --git a/mm/bootmem.c b/mm/bootmem.c
index a58699b6579..e8c567177dc 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -305,6 +305,7 @@ static unsigned long __init free_all_bootmem_core(pg_data_t *pgdat)
 				if (j + 16 < BITS_PER_LONG)
 					prefetchw(page + j + 16);
 				__ClearPageReserved(page + j);
+				set_page_count(page + j, 0);
 			}
 			__free_pages(page, order);
 			i += BITS_PER_LONG;
diff --git a/mm/filemap_xip.c b/mm/filemap_xip.c
index 8c199f53773..9354ee279b1 100644
--- a/mm/filemap_xip.c
+++ b/mm/filemap_xip.c
@@ -174,6 +174,7 @@ __xip_unmap (struct address_space * mapping,
 	unsigned long address;
 	pte_t *pte;
 	pte_t pteval;
+	struct page *page = ZERO_PAGE(address);
 
 	spin_lock(&mapping->i_mmap_lock);
 	vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) {
@@ -185,15 +186,17 @@ __xip_unmap (struct address_space * mapping,
 		 * We need the page_table_lock to protect us from page faults,
 		 * munmap, fork, etc...
 		 */
-		pte = page_check_address(ZERO_PAGE(address), mm,
-					 address);
+		pte = page_check_address(page, mm, address);
 		if (!IS_ERR(pte)) {
 			/* Nuke the page table entry. */
 			flush_cache_page(vma, address, pte_pfn(*pte));
 			pteval = ptep_clear_flush(vma, address, pte);
+			page_remove_rmap(page);
+			dec_mm_counter(mm, file_rss);
 			BUG_ON(pte_dirty(pteval));
 			pte_unmap(pte);
 			spin_unlock(&mm->page_table_lock);
+			page_cache_release(page);
 		}
 	}
 	spin_unlock(&mapping->i_mmap_lock);
@@ -228,7 +231,7 @@ xip_file_nopage(struct vm_area_struct * area,
 
 	page = mapping->a_ops->get_xip_page(mapping, pgoff*(PAGE_SIZE/512), 0);
 	if (!IS_ERR(page)) {
-		return page;
+		goto out;
 	}
 	if (PTR_ERR(page) != -ENODATA)
 		return NULL;
@@ -249,6 +252,8 @@ xip_file_nopage(struct vm_area_struct * area,
 		page = ZERO_PAGE(address);
 	}
 
+out:
+	page_cache_get(page);
 	return page;
 }
 
diff --git a/mm/fremap.c b/mm/fremap.c
index fd7f2a17ff3..224cc1598b3 100644
--- a/mm/fremap.c
+++ b/mm/fremap.c
@@ -29,19 +29,20 @@ static inline void zap_pte(struct mm_struct *mm, struct vm_area_struct *vma,
 		return;
 	if (pte_present(pte)) {
 		unsigned long pfn = pte_pfn(pte);
+		struct page *page;
 
 		flush_cache_page(vma, addr, pfn);
 		pte = ptep_clear_flush(vma, addr, ptep);
-		if (pfn_valid(pfn)) {
-			struct page *page = pfn_to_page(pfn);
-			if (!PageReserved(page)) {
-				if (pte_dirty(pte))
-					set_page_dirty(page);
-				page_remove_rmap(page);
-				page_cache_release(page);
-				dec_mm_counter(mm, file_rss);
-			}
+		if (unlikely(!pfn_valid(pfn))) {
+			print_bad_pte(vma, pte, addr);
+			return;
 		}
+		page = pfn_to_page(pfn);
+		if (pte_dirty(pte))
+			set_page_dirty(page);
+		page_remove_rmap(page);
+		page_cache_release(page);
+		dec_mm_counter(mm, file_rss);
 	} else {
 		if (!pte_file(pte))
 			free_swap_and_cache(pte_to_swp_entry(pte));
@@ -65,6 +66,8 @@ int install_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	pgd_t *pgd;
 	pte_t pte_val;
 
+	BUG_ON(vma->vm_flags & VM_RESERVED);
+
 	pgd = pgd_offset(mm, addr);
 	spin_lock(&mm->page_table_lock);
 	
@@ -125,6 +128,8 @@ int install_file_pte(struct mm_struct *mm, struct vm_area_struct *vma,
 	pgd_t *pgd;
 	pte_t pte_val;
 
+	BUG_ON(vma->vm_flags & VM_RESERVED);
+
 	pgd = pgd_offset(mm, addr);
 	spin_lock(&mm->page_table_lock);
 	
diff --git a/mm/madvise.c b/mm/madvise.c
index 20e075d1c64..17aaf3e1644 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -126,7 +126,7 @@ static long madvise_dontneed(struct vm_area_struct * vma,
 			     unsigned long start, unsigned long end)
 {
 	*prev = vma;
-	if ((vma->vm_flags & VM_LOCKED) || is_vm_hugetlb_page(vma))
+	if (vma->vm_flags & (VM_LOCKED|VM_HUGETLB|VM_RESERVED))
 		return -EINVAL;
 
 	if (unlikely(vma->vm_flags & VM_NONLINEAR)) {
diff --git a/mm/memory.c b/mm/memory.c
index da642b5528f..e83f9440bb6 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -342,6 +342,23 @@ static inline void add_mm_rss(struct mm_struct *mm, int file_rss, int anon_rss)
 
 #define NO_RSS 2	/* Increment neither file_rss nor anon_rss */
 
+/*
+ * This function is called to print an error when a pte in a
+ * !VM_RESERVED region is found pointing to an invalid pfn (which
+ * is an error.
+ *
+ * The calling function must still handle the error.
+ */
+void print_bad_pte(struct vm_area_struct *vma, pte_t pte, unsigned long vaddr)
+{
+	printk(KERN_ERR "Bad pte = %08llx, process = %s, "
+			"vm_flags = %lx, vaddr = %lx\n",
+		(long long)pte_val(pte),
+		(vma->vm_mm == current->mm ? current->comm : "???"),
+		vma->vm_flags, vaddr);
+	dump_stack();
+}
+
 /*
  * copy one vm_area from one task to the other. Assumes the page tables
  * already present in the new task to be cleared in the whole range
@@ -353,9 +370,10 @@ static inline void add_mm_rss(struct mm_struct *mm, int file_rss, int anon_rss)
 
 static inline int
 copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
-		pte_t *dst_pte, pte_t *src_pte, unsigned long vm_flags,
+		pte_t *dst_pte, pte_t *src_pte, struct vm_area_struct *vma,
 		unsigned long addr)
 {
+	unsigned long vm_flags = vma->vm_flags;
 	pte_t pte = *src_pte;
 	struct page *page;
 	unsigned long pfn;
@@ -375,18 +393,22 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		goto out_set_pte;
 	}
 
+	/* If the region is VM_RESERVED, the mapping is not
+	 * mapped via rmap - duplicate the pte as is.
+	 */
+	if (vm_flags & VM_RESERVED)
+		goto out_set_pte;
+
 	pfn = pte_pfn(pte);
-	/* the pte points outside of valid memory, the
-	 * mapping is assumed to be good, meaningful
-	 * and not mapped via rmap - duplicate the
-	 * mapping as is.
+	/* If the pte points outside of valid memory but
+	 * the region is not VM_RESERVED, we have a problem.
 	 */
-	page = NULL;
-	if (pfn_valid(pfn))
-		page = pfn_to_page(pfn);
+	if (unlikely(!pfn_valid(pfn))) {
+		print_bad_pte(vma, pte, addr);
+		goto out_set_pte; /* try to do something sane */
+	}
 
-	if (!page || PageReserved(page))
-		goto out_set_pte;
+	page = pfn_to_page(pfn);
 
 	/*
 	 * If it's a COW mapping, write protect it both
@@ -418,7 +440,6 @@ static int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		unsigned long addr, unsigned long end)
 {
 	pte_t *src_pte, *dst_pte;
-	unsigned long vm_flags = vma->vm_flags;
 	int progress = 0;
 	int rss[NO_RSS+1], anon;
 
@@ -446,8 +467,7 @@ again:
 			progress++;
 			continue;
 		}
-		anon = copy_one_pte(dst_mm, src_mm, dst_pte, src_pte,
-							vm_flags, addr);
+		anon = copy_one_pte(dst_mm, src_mm, dst_pte, src_pte, vma,addr);
 		rss[anon]++;
 		progress += 8;
 	} while (dst_pte++, src_pte++, addr += PAGE_SIZE, addr != end);
@@ -541,10 +561,12 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 	return 0;
 }
 
-static void zap_pte_range(struct mmu_gather *tlb, pmd_t *pmd,
+static void zap_pte_range(struct mmu_gather *tlb,
+				struct vm_area_struct *vma, pmd_t *pmd,
 				unsigned long addr, unsigned long end,
 				struct zap_details *details)
 {
+	struct mm_struct *mm = tlb->mm;
 	pte_t *pte;
 	int file_rss = 0;
 	int anon_rss = 0;
@@ -556,11 +578,12 @@ static void zap_pte_range(struct mmu_gather *tlb, pmd_t *pmd,
 			continue;
 		if (pte_present(ptent)) {
 			struct page *page = NULL;
-			unsigned long pfn = pte_pfn(ptent);
-			if (pfn_valid(pfn)) {
-				page = pfn_to_page(pfn);
-				if (PageReserved(page))
-					page = NULL;
+			if (!(vma->vm_flags & VM_RESERVED)) {
+				unsigned long pfn = pte_pfn(ptent);
+				if (unlikely(!pfn_valid(pfn)))
+					print_bad_pte(vma, ptent, addr);
+				else
+					page = pfn_to_page(pfn);
 			}
 			if (unlikely(details) && page) {
 				/*
@@ -580,7 +603,7 @@ static void zap_pte_range(struct mmu_gather *tlb, pmd_t *pmd,
 				     page->index > details->last_index))
 					continue;
 			}
-			ptent = ptep_get_and_clear_full(tlb->mm, addr, pte,
+			ptent = ptep_get_and_clear_full(mm, addr, pte,
 							tlb->fullmm);
 			tlb_remove_tlb_entry(tlb, pte, addr);
 			if (unlikely(!page))
@@ -588,7 +611,7 @@ static void zap_pte_range(struct mmu_gather *tlb, pmd_t *pmd,
 			if (unlikely(details) && details->nonlinear_vma
 			    && linear_page_index(details->nonlinear_vma,
 						addr) != page->index)
-				set_pte_at(tlb->mm, addr, pte,
+				set_pte_at(mm, addr, pte,
 					   pgoff_to_pte(page->index));
 			if (PageAnon(page))
 				anon_rss++;
@@ -611,14 +634,15 @@ static void zap_pte_range(struct mmu_gather *tlb, pmd_t *pmd,
 			continue;
 		if (!pte_file(ptent))
 			free_swap_and_cache(pte_to_swp_entry(ptent));
-		pte_clear_full(tlb->mm, addr, pte, tlb->fullmm);
+		pte_clear_full(mm, addr, pte, tlb->fullmm);
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 
-	add_mm_rss(tlb->mm, -file_rss, -anon_rss);
+	add_mm_rss(mm, -file_rss, -anon_rss);
 	pte_unmap(pte - 1);
 }
 
-static inline void zap_pmd_range(struct mmu_gather *tlb, pud_t *pud,
+static inline void zap_pmd_range(struct mmu_gather *tlb,
+				struct vm_area_struct *vma, pud_t *pud,
 				unsigned long addr, unsigned long end,
 				struct zap_details *details)
 {
@@ -630,11 +654,12 @@ static inline void zap_pmd_range(struct mmu_gather *tlb, pud_t *pud,
 		next = pmd_addr_end(addr, end);
 		if (pmd_none_or_clear_bad(pmd))
 			continue;
-		zap_pte_range(tlb, pmd, addr, next, details);
+		zap_pte_range(tlb, vma, pmd, addr, next, details);
 	} while (pmd++, addr = next, addr != end);
 }
 
-static inline void zap_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
+static inline void zap_pud_range(struct mmu_gather *tlb,
+				struct vm_area_struct *vma, pgd_t *pgd,
 				unsigned long addr, unsigned long end,
 				struct zap_details *details)
 {
@@ -646,7 +671,7 @@ static inline void zap_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
 		next = pud_addr_end(addr, end);
 		if (pud_none_or_clear_bad(pud))
 			continue;
-		zap_pmd_range(tlb, pud, addr, next, details);
+		zap_pmd_range(tlb, vma, pud, addr, next, details);
 	} while (pud++, addr = next, addr != end);
 }
 
@@ -667,7 +692,7 @@ static void unmap_page_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
 		next = pgd_addr_end(addr, end);
 		if (pgd_none_or_clear_bad(pgd))
 			continue;
-		zap_pud_range(tlb, pgd, addr, next, details);
+		zap_pud_range(tlb, vma, pgd, addr, next, details);
 	} while (pgd++, addr = next, addr != end);
 	tlb_end_vma(tlb, vma);
 }
@@ -967,7 +992,7 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 			continue;
 		}
 
-		if (!vma || (vma->vm_flags & VM_IO)
+		if (!vma || (vma->vm_flags & (VM_IO | VM_RESERVED))
 				|| !(flags & vma->vm_flags))
 			return i ? : -EFAULT;
 
@@ -1027,8 +1052,7 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 			if (pages) {
 				pages[i] = page;
 				flush_dcache_page(page);
-				if (!PageReserved(page))
-					page_cache_get(page);
+				page_cache_get(page);
 			}
 			if (vmas)
 				vmas[i] = vma;
@@ -1051,7 +1075,11 @@ static int zeromap_pte_range(struct mm_struct *mm, pmd_t *pmd,
 	if (!pte)
 		return -ENOMEM;
 	do {
-		pte_t zero_pte = pte_wrprotect(mk_pte(ZERO_PAGE(addr), prot));
+		struct page *page = ZERO_PAGE(addr);
+		pte_t zero_pte = pte_wrprotect(mk_pte(page, prot));
+		page_cache_get(page);
+		page_add_file_rmap(page);
+		inc_mm_counter(mm, file_rss);
 		BUG_ON(!pte_none(*pte));
 		set_pte_at(mm, addr, pte, zero_pte);
 	} while (pte++, addr += PAGE_SIZE, addr != end);
@@ -1132,8 +1160,7 @@ static int remap_pte_range(struct mm_struct *mm, pmd_t *pmd,
 		return -ENOMEM;
 	do {
 		BUG_ON(!pte_none(*pte));
-		if (!pfn_valid(pfn) || PageReserved(pfn_to_page(pfn)))
-			set_pte_at(mm, addr, pte, pfn_pte(pfn, prot));
+		set_pte_at(mm, addr, pte, pfn_pte(pfn, prot));
 		pfn++;
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 	pte_unmap(pte - 1);
@@ -1195,8 +1222,8 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
 	 * rest of the world about it:
 	 *   VM_IO tells people not to look at these pages
 	 *	(accesses can have side effects).
-	 *   VM_RESERVED tells swapout not to try to touch
-	 *	this region.
+	 *   VM_RESERVED tells the core MM not to "manage" these pages
+         *	(e.g. refcount, mapcount, try to swap them out).
 	 */
 	vma->vm_flags |= VM_IO | VM_RESERVED;
 
@@ -1256,11 +1283,13 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	pte_t entry;
 	int ret = VM_FAULT_MINOR;
 
+	BUG_ON(vma->vm_flags & VM_RESERVED);
+
 	if (unlikely(!pfn_valid(pfn))) {
 		/*
 		 * Page table corrupted: show pte and kill process.
 		 */
-		pte_ERROR(orig_pte);
+		print_bad_pte(vma, orig_pte, address);
 		ret = VM_FAULT_OOM;
 		goto unlock;
 	}
@@ -1284,8 +1313,7 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	/*
 	 * Ok, we need to copy. Oh, well..
 	 */
-	if (!PageReserved(old_page))
-		page_cache_get(old_page);
+	page_cache_get(old_page);
 	pte_unmap(page_table);
 	spin_unlock(&mm->page_table_lock);
 
@@ -1308,14 +1336,10 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	spin_lock(&mm->page_table_lock);
 	page_table = pte_offset_map(pmd, address);
 	if (likely(pte_same(*page_table, orig_pte))) {
-		if (PageReserved(old_page))
+		page_remove_rmap(old_page);
+		if (!PageAnon(old_page)) {
 			inc_mm_counter(mm, anon_rss);
-		else {
-			page_remove_rmap(old_page);
-			if (!PageAnon(old_page)) {
-				inc_mm_counter(mm, anon_rss);
-				dec_mm_counter(mm, file_rss);
-			}
+			dec_mm_counter(mm, file_rss);
 		}
 		flush_cache_page(vma, address, pfn);
 		entry = mk_pte(new_page, vma->vm_page_prot);
@@ -1769,14 +1793,13 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		unsigned long address, pte_t *page_table, pmd_t *pmd,
 		int write_access)
 {
+	struct page *page = ZERO_PAGE(addr);
 	pte_t entry;
 
 	/* Mapping of ZERO_PAGE - vm_page_prot is readonly */
-	entry = mk_pte(ZERO_PAGE(addr), vma->vm_page_prot);
+	entry = mk_pte(page, vma->vm_page_prot);
 
 	if (write_access) {
-		struct page *page;
-
 		/* Allocate our own private page. */
 		pte_unmap(page_table);
 		spin_unlock(&mm->page_table_lock);
@@ -1800,6 +1823,10 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		lru_cache_add_active(page);
 		SetPageReferenced(page);
 		page_add_anon_rmap(page, vma, address);
+	} else {
+		inc_mm_counter(mm, file_rss);
+		page_add_file_rmap(page);
+		page_cache_get(page);
 	}
 
 	set_pte_at(mm, address, page_table, entry);
@@ -1916,7 +1943,7 @@ retry:
 			inc_mm_counter(mm, anon_rss);
 			lru_cache_add_active(new_page);
 			page_add_anon_rmap(new_page, vma, address);
-		} else if (!PageReserved(new_page)) {
+		} else if (!(vma->vm_flags & VM_RESERVED)) {
 			inc_mm_counter(mm, file_rss);
 			page_add_file_rmap(new_page);
 		}
@@ -1957,7 +1984,7 @@ static int do_file_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		/*
 		 * Page table corrupted: show pte and kill process.
 		 */
-		pte_ERROR(orig_pte);
+		print_bad_pte(vma, orig_pte, address);
 		return VM_FAULT_OOM;
 	}
 	/* We can then assume vm->vm_ops && vma->vm_ops->populate */
@@ -2232,7 +2259,7 @@ static int __init gate_vma_init(void)
 	gate_vma.vm_start = FIXADDR_USER_START;
 	gate_vma.vm_end = FIXADDR_USER_END;
 	gate_vma.vm_page_prot = PAGE_READONLY;
-	gate_vma.vm_flags = 0;
+	gate_vma.vm_flags = VM_RESERVED;
 	return 0;
 }
 __initcall(gate_vma_init);
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 43b1199af59..11d824f282f 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -223,13 +223,13 @@ static struct mempolicy *mpol_new(int mode, nodemask_t *nodes)
 }
 
 /* Ensure all existing pages follow the policy. */
-static int check_pte_range(struct mm_struct *mm, pmd_t *pmd,
+static int check_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 		unsigned long addr, unsigned long end, nodemask_t *nodes)
 {
 	pte_t *orig_pte;
 	pte_t *pte;
 
-	spin_lock(&mm->page_table_lock);
+	spin_lock(&vma->vm_mm->page_table_lock);
 	orig_pte = pte = pte_offset_map(pmd, addr);
 	do {
 		unsigned long pfn;
@@ -238,18 +238,20 @@ static int check_pte_range(struct mm_struct *mm, pmd_t *pmd,
 		if (!pte_present(*pte))
 			continue;
 		pfn = pte_pfn(*pte);
-		if (!pfn_valid(pfn))
+		if (!pfn_valid(pfn)) {
+			print_bad_pte(vma, *pte, addr);
 			continue;
+		}
 		nid = pfn_to_nid(pfn);
 		if (!node_isset(nid, *nodes))
 			break;
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 	pte_unmap(orig_pte);
-	spin_unlock(&mm->page_table_lock);
+	spin_unlock(&vma->vm_mm->page_table_lock);
 	return addr != end;
 }
 
-static inline int check_pmd_range(struct mm_struct *mm, pud_t *pud,
+static inline int check_pmd_range(struct vm_area_struct *vma, pud_t *pud,
 		unsigned long addr, unsigned long end, nodemask_t *nodes)
 {
 	pmd_t *pmd;
@@ -260,13 +262,13 @@ static inline int check_pmd_range(struct mm_struct *mm, pud_t *pud,
 		next = pmd_addr_end(addr, end);
 		if (pmd_none_or_clear_bad(pmd))
 			continue;
-		if (check_pte_range(mm, pmd, addr, next, nodes))
+		if (check_pte_range(vma, pmd, addr, next, nodes))
 			return -EIO;
 	} while (pmd++, addr = next, addr != end);
 	return 0;
 }
 
-static inline int check_pud_range(struct mm_struct *mm, pgd_t *pgd,
+static inline int check_pud_range(struct vm_area_struct *vma, pgd_t *pgd,
 		unsigned long addr, unsigned long end, nodemask_t *nodes)
 {
 	pud_t *pud;
@@ -277,24 +279,24 @@ static inline int check_pud_range(struct mm_struct *mm, pgd_t *pgd,
 		next = pud_addr_end(addr, end);
 		if (pud_none_or_clear_bad(pud))
 			continue;
-		if (check_pmd_range(mm, pud, addr, next, nodes))
+		if (check_pmd_range(vma, pud, addr, next, nodes))
 			return -EIO;
 	} while (pud++, addr = next, addr != end);
 	return 0;
 }
 
-static inline int check_pgd_range(struct mm_struct *mm,
+static inline int check_pgd_range(struct vm_area_struct *vma,
 		unsigned long addr, unsigned long end, nodemask_t *nodes)
 {
 	pgd_t *pgd;
 	unsigned long next;
 
-	pgd = pgd_offset(mm, addr);
+	pgd = pgd_offset(vma->vm_mm, addr);
 	do {
 		next = pgd_addr_end(addr, end);
 		if (pgd_none_or_clear_bad(pgd))
 			continue;
-		if (check_pud_range(mm, pgd, addr, next, nodes))
+		if (check_pud_range(vma, pgd, addr, next, nodes))
 			return -EIO;
 	} while (pgd++, addr = next, addr != end);
 	return 0;
@@ -311,6 +313,8 @@ check_range(struct mm_struct *mm, unsigned long start, unsigned long end,
 	first = find_vma(mm, start);
 	if (!first)
 		return ERR_PTR(-EFAULT);
+	if (first->vm_flags & VM_RESERVED)
+		return ERR_PTR(-EACCES);
 	prev = NULL;
 	for (vma = first; vma && vma->vm_start < end; vma = vma->vm_next) {
 		if (!vma->vm_next && vma->vm_end < end)
@@ -323,8 +327,7 @@ check_range(struct mm_struct *mm, unsigned long start, unsigned long end,
 				endvma = end;
 			if (vma->vm_start > start)
 				start = vma->vm_start;
-			err = check_pgd_range(vma->vm_mm,
-					   start, endvma, nodes);
+			err = check_pgd_range(vma, start, endvma, nodes);
 			if (err) {
 				first = ERR_PTR(err);
 				break;
diff --git a/mm/mmap.c b/mm/mmap.c
index 459b9f068ad..8a111792b8d 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1088,6 +1088,17 @@ munmap_back:
 		error = file->f_op->mmap(file, vma);
 		if (error)
 			goto unmap_and_free_vma;
+		if ((vma->vm_flags & (VM_SHARED | VM_WRITE | VM_RESERVED))
+						== (VM_WRITE | VM_RESERVED)) {
+			printk(KERN_WARNING "program %s is using MAP_PRIVATE, "
+				"PROT_WRITE mmap of VM_RESERVED memory, which "
+				"is deprecated. Please report this to "
+				"linux-kernel@vger.kernel.org\n",current->comm);
+			if (vma->vm_ops && vma->vm_ops->close)
+				vma->vm_ops->close(vma);
+			error = -EACCES;
+			goto unmap_and_free_vma;
+		}
 	} else if (vm_flags & VM_SHARED) {
 		error = shmem_zero_setup(vma);
 		if (error)
diff --git a/mm/mprotect.c b/mm/mprotect.c
index b426f01c5e9..672a76fddd5 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -125,6 +125,14 @@ mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev,
 	 * a MAP_NORESERVE private mapping to writable will now reserve.
 	 */
 	if (newflags & VM_WRITE) {
+		if (oldflags & VM_RESERVED) {
+			BUG_ON(oldflags & VM_WRITE);
+			printk(KERN_WARNING "program %s is using MAP_PRIVATE, "
+				"PROT_WRITE mprotect of VM_RESERVED memory, "
+				"which is deprecated. Please report this to "
+				"linux-kernel@vger.kernel.org\n",current->comm);
+			return -EACCES;
+		}
 		if (!(oldflags & (VM_ACCOUNT|VM_WRITE|VM_SHARED|VM_HUGETLB))) {
 			charged = nrpages;
 			if (security_vm_enough_memory(charged))
diff --git a/mm/msync.c b/mm/msync.c
index 3b5f1c521d4..86039548606 100644
--- a/mm/msync.c
+++ b/mm/msync.c
@@ -25,6 +25,7 @@
 static void msync_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 				unsigned long addr, unsigned long end)
 {
+	struct mm_struct *mm = vma->vm_mm;
 	pte_t *pte;
 	int progress = 0;
 
@@ -37,7 +38,7 @@ again:
 		if (progress >= 64) {
 			progress = 0;
 			if (need_resched() ||
-			    need_lockbreak(&vma->vm_mm->page_table_lock))
+			    need_lockbreak(&mm->page_table_lock))
 				break;
 		}
 		progress++;
@@ -46,11 +47,11 @@ again:
 		if (!pte_maybe_dirty(*pte))
 			continue;
 		pfn = pte_pfn(*pte);
-		if (!pfn_valid(pfn))
+		if (unlikely(!pfn_valid(pfn))) {
+			print_bad_pte(vma, *pte, addr);
 			continue;
+		}
 		page = pfn_to_page(pfn);
-		if (PageReserved(page))
-			continue;
 
 		if (ptep_clear_flush_dirty(vma, addr, pte) ||
 		    page_test_and_clear_dirty(page))
@@ -58,7 +59,7 @@ again:
 		progress += 3;
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 	pte_unmap(pte - 1);
-	cond_resched_lock(&vma->vm_mm->page_table_lock);
+	cond_resched_lock(&mm->page_table_lock);
 	if (addr != end)
 		goto again;
 }
@@ -102,8 +103,10 @@ static void msync_page_range(struct vm_area_struct *vma,
 
 	/* For hugepages we can't go walking the page table normally,
 	 * but that's ok, hugetlbfs is memory based, so we don't need
-	 * to do anything more on an msync() */
-	if (is_vm_hugetlb_page(vma))
+	 * to do anything more on an msync().
+	 * Can't do anything with VM_RESERVED regions either.
+	 */
+	if (vma->vm_flags & (VM_HUGETLB|VM_RESERVED))
 		return;
 
 	BUG_ON(addr >= end);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 60663232fbb..0541288ebf4 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -114,7 +114,8 @@ static void bad_page(const char *function, struct page *page)
 			1 << PG_reclaim |
 			1 << PG_slab    |
 			1 << PG_swapcache |
-			1 << PG_writeback);
+			1 << PG_writeback |
+			1 << PG_reserved );
 	set_page_count(page, 0);
 	reset_page_mapcount(page);
 	page->mapping = NULL;
@@ -244,7 +245,6 @@ static inline int page_is_buddy(struct page *page, int order)
 {
        if (PagePrivate(page)           &&
            (page_order(page) == order) &&
-           !PageReserved(page)         &&
             page_count(page) == 0)
                return 1;
        return 0;
@@ -327,7 +327,8 @@ static inline void free_pages_check(const char *function, struct page *page)
 			1 << PG_reclaim	|
 			1 << PG_slab	|
 			1 << PG_swapcache |
-			1 << PG_writeback )))
+			1 << PG_writeback |
+			1 << PG_reserved )))
 		bad_page(function, page);
 	if (PageDirty(page))
 		__ClearPageDirty(page);
@@ -455,7 +456,8 @@ static void prep_new_page(struct page *page, int order)
 			1 << PG_reclaim	|
 			1 << PG_slab    |
 			1 << PG_swapcache |
-			1 << PG_writeback )))
+			1 << PG_writeback |
+			1 << PG_reserved )))
 		bad_page(__FUNCTION__, page);
 
 	page->flags &= ~(1 << PG_uptodate | 1 << PG_error |
@@ -1016,7 +1018,7 @@ void __pagevec_free(struct pagevec *pvec)
 
 fastcall void __free_pages(struct page *page, unsigned int order)
 {
-	if (!PageReserved(page) && put_page_testzero(page)) {
+	if (put_page_testzero(page)) {
 		if (order == 0)
 			free_hot_page(page);
 		else
@@ -1674,7 +1676,7 @@ void __init memmap_init_zone(unsigned long size, int nid, unsigned long zone,
 			continue;
 		page = pfn_to_page(pfn);
 		set_page_links(page, zone, nid, pfn);
-		set_page_count(page, 0);
+		set_page_count(page, 1);
 		reset_page_mapcount(page);
 		SetPageReserved(page);
 		INIT_LIST_HEAD(&page->lru);
diff --git a/mm/rmap.c b/mm/rmap.c
index 504757624cc..f69d5342ce7 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -443,8 +443,6 @@ int page_referenced(struct page *page, int is_locked, int ignore_token)
 void page_add_anon_rmap(struct page *page,
 	struct vm_area_struct *vma, unsigned long address)
 {
-	BUG_ON(PageReserved(page));
-
 	if (atomic_inc_and_test(&page->_mapcount)) {
 		struct anon_vma *anon_vma = vma->anon_vma;
 
@@ -468,8 +466,7 @@ void page_add_anon_rmap(struct page *page,
 void page_add_file_rmap(struct page *page)
 {
 	BUG_ON(PageAnon(page));
-	if (!pfn_valid(page_to_pfn(page)) || PageReserved(page))
-		return;
+	BUG_ON(!pfn_valid(page_to_pfn(page)));
 
 	if (atomic_inc_and_test(&page->_mapcount))
 		inc_page_state(nr_mapped);
@@ -483,8 +480,6 @@ void page_add_file_rmap(struct page *page)
  */
 void page_remove_rmap(struct page *page)
 {
-	BUG_ON(PageReserved(page));
-
 	if (atomic_add_negative(-1, &page->_mapcount)) {
 		BUG_ON(page_mapcount(page) < 0);
 		/*
@@ -640,13 +635,13 @@ static void try_to_unmap_cluster(unsigned long cursor,
 			continue;
 
 		pfn = pte_pfn(*pte);
-		if (!pfn_valid(pfn))
+		if (unlikely(!pfn_valid(pfn))) {
+			print_bad_pte(vma, *pte, address);
 			continue;
+		}
 
 		page = pfn_to_page(pfn);
 		BUG_ON(PageAnon(page));
-		if (PageReserved(page))
-			continue;
 
 		if (ptep_clear_flush_young(vma, address, pte))
 			continue;
@@ -808,7 +803,6 @@ int try_to_unmap(struct page *page)
 {
 	int ret;
 
-	BUG_ON(PageReserved(page));
 	BUG_ON(!PageLocked(page));
 
 	if (PageAnon(page))
diff --git a/mm/shmem.c b/mm/shmem.c
index 6796311a23e..37777f4c11f 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1506,8 +1506,10 @@ static void do_shmem_file_read(struct file *filp, loff_t *ppos, read_descriptor_
 			 */
 			if (!offset)
 				mark_page_accessed(page);
-		} else
+		} else {
 			page = ZERO_PAGE(0);
+			page_cache_get(page);
+		}
 
 		/*
 		 * Ok, we have the page, and it's up-to-date, so
diff --git a/mm/swap.c b/mm/swap.c
index 7771d2803f6..21d15f99805 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -48,7 +48,7 @@ void put_page(struct page *page)
 		}
 		return;
 	}
-	if (!PageReserved(page) && put_page_testzero(page))
+	if (put_page_testzero(page))
 		__page_cache_release(page);
 }
 EXPORT_SYMBOL(put_page);
@@ -215,7 +215,7 @@ void release_pages(struct page **pages, int nr, int cold)
 		struct page *page = pages[i];
 		struct zone *pagezone;
 
-		if (PageReserved(page) || !put_page_testzero(page))
+		if (!put_page_testzero(page))
 			continue;
 
 		pagezone = page_zone(page);
diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c
index 67abebabf83..e97b2d162cc 100644
--- a/sound/core/pcm_native.c
+++ b/sound/core/pcm_native.c
@@ -2949,8 +2949,7 @@ static struct page * snd_pcm_mmap_status_nopage(struct vm_area_struct *area, uns
 		return NOPAGE_OOM;
 	runtime = substream->runtime;
 	page = virt_to_page(runtime->status);
-	if (!PageReserved(page))
-		get_page(page);
+	get_page(page);
 	if (type)
 		*type = VM_FAULT_MINOR;
 	return page;
@@ -2992,8 +2991,7 @@ static struct page * snd_pcm_mmap_control_nopage(struct vm_area_struct *area, un
 		return NOPAGE_OOM;
 	runtime = substream->runtime;
 	page = virt_to_page(runtime->control);
-	if (!PageReserved(page))
-		get_page(page);
+	get_page(page);
 	if (type)
 		*type = VM_FAULT_MINOR;
 	return page;
@@ -3066,8 +3064,7 @@ static struct page *snd_pcm_mmap_data_nopage(struct vm_area_struct *area, unsign
 		vaddr = runtime->dma_area + offset;
 		page = virt_to_page(vaddr);
 	}
-	if (!PageReserved(page))
-		get_page(page);
+	get_page(page);
 	if (type)
 		*type = VM_FAULT_MINOR;
 	return page;
-- 
cgit v1.2.3-70-g09d2


From 705e87c0c3c38424f7f30556c85bc20e808d2f59 Mon Sep 17 00:00:00 2001
From: Hugh Dickins <hugh@veritas.com>
Date: Sat, 29 Oct 2005 18:16:27 -0700
Subject: [PATCH] mm: pte_offset_map_lock loops

Convert those common loops using page_table_lock on the outside and
pte_offset_map within to use just pte_offset_map_lock within instead.

These all hold mmap_sem (some exclusively, some not), so at no level can a
page table be whipped away from beneath them.  But whereas pte_alloc loops
tested with the "atomic" pmd_present, these loops are testing with pmd_none,
which on i386 PAE tests both lower and upper halves.

That's now unsafe, so add a cast into pmd_none to test only the vital lower
half: we lose a little sensitivity to a corrupt middle directory, but not
enough to worry about.  It appears that i386 and UML were the only
architectures vulnerable in this way, and pgd and pud no problem.

Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
---
 fs/proc/task_mmu.c         | 17 ++++++-----------
 include/asm-i386/pgtable.h |  3 ++-
 include/asm-um/pgtable.h   |  2 +-
 mm/mempolicy.c             |  7 +++----
 mm/mprotect.c              |  7 +++----
 mm/msync.c                 | 21 ++++++---------------
 mm/swapfile.c              | 20 +++++++++-----------
 7 files changed, 30 insertions(+), 47 deletions(-)

(limited to 'mm/mprotect.c')

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 7c89b454904..7e5e7ec2e36 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -203,13 +203,14 @@ static void smaps_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 				struct mem_size_stats *mss)
 {
 	pte_t *pte, ptent;
+	spinlock_t *ptl;
 	unsigned long pfn;
 	struct page *page;
 
-	pte = pte_offset_map(pmd, addr);
+	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
 	do {
 		ptent = *pte;
-		if (pte_none(ptent) || !pte_present(ptent))
+		if (!pte_present(ptent))
 			continue;
 
 		mss->resident += PAGE_SIZE;
@@ -230,8 +231,8 @@ static void smaps_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 				mss->private_clean += PAGE_SIZE;
 		}
 	} while (pte++, addr += PAGE_SIZE, addr != end);
-	pte_unmap(pte - 1);
-	cond_resched_lock(&vma->vm_mm->page_table_lock);
+	pte_unmap_unlock(pte - 1, ptl);
+	cond_resched();
 }
 
 static inline void smaps_pmd_range(struct vm_area_struct *vma, pud_t *pud,
@@ -285,17 +286,11 @@ static inline void smaps_pgd_range(struct vm_area_struct *vma,
 static int show_smap(struct seq_file *m, void *v)
 {
 	struct vm_area_struct *vma = v;
-	struct mm_struct *mm = vma->vm_mm;
 	struct mem_size_stats mss;
 
 	memset(&mss, 0, sizeof mss);
-
-	if (mm) {
-		spin_lock(&mm->page_table_lock);
+	if (vma->vm_mm)
 		smaps_pgd_range(vma, vma->vm_start, vma->vm_end, &mss);
-		spin_unlock(&mm->page_table_lock);
-	}
-
 	return show_map_internal(m, v, &mss);
 }
 
diff --git a/include/asm-i386/pgtable.h b/include/asm-i386/pgtable.h
index d101ac414f0..0e3ec809352 100644
--- a/include/asm-i386/pgtable.h
+++ b/include/asm-i386/pgtable.h
@@ -203,7 +203,8 @@ extern unsigned long pg0[];
 #define pte_present(x)	((x).pte_low & (_PAGE_PRESENT | _PAGE_PROTNONE))
 #define pte_clear(mm,addr,xp)	do { set_pte_at(mm, addr, xp, __pte(0)); } while (0)
 
-#define pmd_none(x)	(!pmd_val(x))
+/* To avoid harmful races, pmd_none(x) should check only the lower when PAE */
+#define pmd_none(x)	(!(unsigned long)pmd_val(x))
 #define pmd_present(x)	(pmd_val(x) & _PAGE_PRESENT)
 #define pmd_clear(xp)	do { set_pmd(xp, __pmd(0)); } while (0)
 #define	pmd_bad(x)	((pmd_val(x) & (~PAGE_MASK & ~_PAGE_USER)) != _KERNPG_TABLE)
diff --git a/include/asm-um/pgtable.h b/include/asm-um/pgtable.h
index 616d02b57ea..ac64eb95586 100644
--- a/include/asm-um/pgtable.h
+++ b/include/asm-um/pgtable.h
@@ -138,7 +138,7 @@ extern unsigned long pg0[1024];
 
 #define pte_clear(mm,addr,xp) pte_set_val(*(xp), (phys_t) 0, __pgprot(_PAGE_NEWPAGE))
 
-#define pmd_none(x)	(!(pmd_val(x) & ~_PAGE_NEWPAGE))
+#define pmd_none(x)	(!((unsigned long)pmd_val(x) & ~_PAGE_NEWPAGE))
 #define	pmd_bad(x)	((pmd_val(x) & (~PAGE_MASK & ~_PAGE_USER)) != _KERNPG_TABLE)
 #define pmd_present(x)	(pmd_val(x) & _PAGE_PRESENT)
 #define pmd_clear(xp)	do { pmd_val(*(xp)) = _PAGE_NEWPAGE; } while (0)
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 11d824f282f..902d4c9eccd 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -228,9 +228,9 @@ static int check_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 {
 	pte_t *orig_pte;
 	pte_t *pte;
+	spinlock_t *ptl;
 
-	spin_lock(&vma->vm_mm->page_table_lock);
-	orig_pte = pte = pte_offset_map(pmd, addr);
+	orig_pte = pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
 	do {
 		unsigned long pfn;
 		unsigned int nid;
@@ -246,8 +246,7 @@ static int check_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 		if (!node_isset(nid, *nodes))
 			break;
 	} while (pte++, addr += PAGE_SIZE, addr != end);
-	pte_unmap(orig_pte);
-	spin_unlock(&vma->vm_mm->page_table_lock);
+	pte_unmap_unlock(orig_pte, ptl);
 	return addr != end;
 }
 
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 672a76fddd5..17a2b52b753 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -29,8 +29,9 @@ static void change_pte_range(struct mm_struct *mm, pmd_t *pmd,
 		unsigned long addr, unsigned long end, pgprot_t newprot)
 {
 	pte_t *pte;
+	spinlock_t *ptl;
 
-	pte = pte_offset_map(pmd, addr);
+	pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
 	do {
 		if (pte_present(*pte)) {
 			pte_t ptent;
@@ -44,7 +45,7 @@ static void change_pte_range(struct mm_struct *mm, pmd_t *pmd,
 			lazy_mmu_prot_update(ptent);
 		}
 	} while (pte++, addr += PAGE_SIZE, addr != end);
-	pte_unmap(pte - 1);
+	pte_unmap_unlock(pte - 1, ptl);
 }
 
 static inline void change_pmd_range(struct mm_struct *mm, pud_t *pud,
@@ -88,7 +89,6 @@ static void change_protection(struct vm_area_struct *vma,
 	BUG_ON(addr >= end);
 	pgd = pgd_offset(mm, addr);
 	flush_cache_range(vma, addr, end);
-	spin_lock(&mm->page_table_lock);
 	do {
 		next = pgd_addr_end(addr, end);
 		if (pgd_none_or_clear_bad(pgd))
@@ -96,7 +96,6 @@ static void change_protection(struct vm_area_struct *vma,
 		change_pud_range(mm, pgd, addr, next, newprot);
 	} while (pgd++, addr = next, addr != end);
 	flush_tlb_range(vma, start, end);
-	spin_unlock(&mm->page_table_lock);
 }
 
 static int
diff --git a/mm/msync.c b/mm/msync.c
index 86039548606..0e040e9c39d 100644
--- a/mm/msync.c
+++ b/mm/msync.c
@@ -17,28 +17,22 @@
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
 
-/*
- * Called with mm->page_table_lock held to protect against other
- * threads/the swapper from ripping pte's out from under us.
- */
-
 static void msync_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 				unsigned long addr, unsigned long end)
 {
-	struct mm_struct *mm = vma->vm_mm;
 	pte_t *pte;
+	spinlock_t *ptl;
 	int progress = 0;
 
 again:
-	pte = pte_offset_map(pmd, addr);
+	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
 	do {
 		unsigned long pfn;
 		struct page *page;
 
 		if (progress >= 64) {
 			progress = 0;
-			if (need_resched() ||
-			    need_lockbreak(&mm->page_table_lock))
+			if (need_resched() || need_lockbreak(ptl))
 				break;
 		}
 		progress++;
@@ -58,8 +52,8 @@ again:
 			set_page_dirty(page);
 		progress += 3;
 	} while (pte++, addr += PAGE_SIZE, addr != end);
-	pte_unmap(pte - 1);
-	cond_resched_lock(&mm->page_table_lock);
+	pte_unmap_unlock(pte - 1, ptl);
+	cond_resched();
 	if (addr != end)
 		goto again;
 }
@@ -97,7 +91,6 @@ static inline void msync_pud_range(struct vm_area_struct *vma, pgd_t *pgd,
 static void msync_page_range(struct vm_area_struct *vma,
 				unsigned long addr, unsigned long end)
 {
-	struct mm_struct *mm = vma->vm_mm;
 	pgd_t *pgd;
 	unsigned long next;
 
@@ -110,16 +103,14 @@ static void msync_page_range(struct vm_area_struct *vma,
 		return;
 
 	BUG_ON(addr >= end);
-	pgd = pgd_offset(mm, addr);
+	pgd = pgd_offset(vma->vm_mm, addr);
 	flush_cache_range(vma, addr, end);
-	spin_lock(&mm->page_table_lock);
 	do {
 		next = pgd_addr_end(addr, end);
 		if (pgd_none_or_clear_bad(pgd))
 			continue;
 		msync_pud_range(vma, pgd, addr, next);
 	} while (pgd++, addr = next, addr != end);
-	spin_unlock(&mm->page_table_lock);
 }
 
 /*
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 296e0bbf783..510f0039b00 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -401,8 +401,6 @@ void free_swap_and_cache(swp_entry_t entry)
  * No need to decide whether this PTE shares the swap entry with others,
  * just let do_wp_page work it out if a write is requested later - to
  * force COW, vm_page_prot omits write permission from any private vma.
- *
- * vma->vm_mm->page_table_lock is held.
  */
 static void unuse_pte(struct vm_area_struct *vma, pte_t *pte,
 		unsigned long addr, swp_entry_t entry, struct page *page)
@@ -424,23 +422,25 @@ static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 				unsigned long addr, unsigned long end,
 				swp_entry_t entry, struct page *page)
 {
-	pte_t *pte;
 	pte_t swp_pte = swp_entry_to_pte(entry);
+	pte_t *pte;
+	spinlock_t *ptl;
+	int found = 0;
 
-	pte = pte_offset_map(pmd, addr);
+	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
 	do {
 		/*
 		 * swapoff spends a _lot_ of time in this loop!
 		 * Test inline before going to call unuse_pte.
 		 */
 		if (unlikely(pte_same(*pte, swp_pte))) {
-			unuse_pte(vma, pte, addr, entry, page);
-			pte_unmap(pte);
-			return 1;
+			unuse_pte(vma, pte++, addr, entry, page);
+			found = 1;
+			break;
 		}
 	} while (pte++, addr += PAGE_SIZE, addr != end);
-	pte_unmap(pte - 1);
-	return 0;
+	pte_unmap_unlock(pte - 1, ptl);
+	return found;
 }
 
 static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud,
@@ -522,12 +522,10 @@ static int unuse_mm(struct mm_struct *mm,
 		down_read(&mm->mmap_sem);
 		lock_page(page);
 	}
-	spin_lock(&mm->page_table_lock);
 	for (vma = mm->mmap; vma; vma = vma->vm_next) {
 		if (vma->anon_vma && unuse_vma(vma, entry, page))
 			break;
 	}
-	spin_unlock(&mm->page_table_lock);
 	up_read(&mm->mmap_sem);
 	/*
 	 * Currently unuse_mm cannot fail, but leave error handling
-- 
cgit v1.2.3-70-g09d2