Merge ../linux-2.6/

5 files changed, 33 insertions, 36 deletions

diff --git a/mm/filemap_xip.c b/mm/filemap_xip.c
index 3b6e384..8c199f5 100644
--- a/mm/filemap_xip.c
+++ b/mm/filemap_xip.c
@@ -68,13 +68,12 @@ do_xip_mapping_read(struct address_space *mapping,
 		if (unlikely(IS_ERR(page))) {
 			if (PTR_ERR(page) == -ENODATA) {
 				/* sparse */
-				page = virt_to_page(empty_zero_page);
+				page = ZERO_PAGE(0);
 			} else {
 				desc->error = PTR_ERR(page);
 				goto out;
 			}
-		} else
-			BUG_ON(!PageUptodate(page));
+		}
 
 		/* If users can be writing to this page using arbitrary
 		 * virtual addresses, take care about potential aliasing
@@ -84,8 +83,7 @@ do_xip_mapping_read(struct address_space *mapping,
 			flush_dcache_page(page);
 
 		/*
-		 * Ok, we have the page, and it's up-to-date, so
-		 * now we can copy it to user space...
+		 * Ok, we have the page, so now we can copy it to user space...
 		 *
 		 * The actor routine returns how many bytes were actually used..
 		 * NOTE! This may not be the same as how much of a user buffer
@@ -164,7 +162,7 @@ EXPORT_SYMBOL_GPL(xip_file_sendfile);
  * xip_write
  *
  * This function walks all vmas of the address_space and unmaps the
- * empty_zero_page when found at pgoff. Should it go in rmap.c?
+ * ZERO_PAGE when found at pgoff. Should it go in rmap.c?
  */
 static void
 __xip_unmap (struct address_space * mapping,
@@ -187,11 +185,11 @@ __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(virt_to_page(empty_zero_page), mm,
+		pte = page_check_address(ZERO_PAGE(address), mm,
 					 address);
 		if (!IS_ERR(pte)) {
 			/* Nuke the page table entry. */
-			flush_cache_page(vma, address, pte_pfn(pte));
+			flush_cache_page(vma, address, pte_pfn(*pte));
 			pteval = ptep_clear_flush(vma, address, pte);
 			BUG_ON(pte_dirty(pteval));
 			pte_unmap(pte);
@@ -230,7 +228,6 @@ 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)) {
-		BUG_ON(!PageUptodate(page));
 		return page;
 	}
 	if (PTR_ERR(page) != -ENODATA)
@@ -245,12 +242,11 @@ xip_file_nopage(struct vm_area_struct * area,
 			pgoff*(PAGE_SIZE/512), 1);
 		if (IS_ERR(page))
 			return NULL;
-		BUG_ON(!PageUptodate(page));
 		/* unmap page at pgoff from all other vmas */
 		__xip_unmap(mapping, pgoff);
 	} else {
-		/* not shared and writable, use empty_zero_page */
-		page = virt_to_page(empty_zero_page);
+		/* not shared and writable, use ZERO_PAGE() */
+		page = ZERO_PAGE(address);
 	}
 
 	return page;
@@ -319,8 +315,6 @@ __xip_file_write(struct file *filp, const char __user *buf,
 			break;
 		}
 
-		BUG_ON(!PageUptodate(page));
-
 		copied = filemap_copy_from_user(page, offset, buf, bytes);
 		flush_dcache_page(page);
 		if (likely(copied > 0)) {
@@ -435,8 +429,7 @@ xip_truncate_page(struct address_space *mapping, loff_t from)
 			return 0;
 		else
 			return PTR_ERR(page);
-	} else
-		BUG_ON(!PageUptodate(page));
+	}
 	kaddr = kmap_atomic(page, KM_USER0);
 	memset(kaddr + offset, 0, length);
 	kunmap_atomic(kaddr, KM_USER0);
diff --git a/mm/madvise.c b/mm/madvise.c
index 73180a2..c8c01a1 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -83,9 +83,6 @@ static long madvise_willneed(struct vm_area_struct * vma,
 {
 	struct file *file = vma->vm_file;
 
-	if (!file)
-		return -EBADF;
-
 	if (file->f_mapping->a_ops->get_xip_page) {
 		/* no bad return value, but ignore advice */
 		return 0;
@@ -140,11 +137,16 @@ static long madvise_dontneed(struct vm_area_struct * vma,
 	return 0;
 }
 
-static long madvise_vma(struct vm_area_struct *vma, struct vm_area_struct **prev,
-			unsigned long start, unsigned long end, int behavior)
+static long
+madvise_vma(struct vm_area_struct *vma, struct vm_area_struct **prev,
+		unsigned long start, unsigned long end, int behavior)
 {
+	struct file *filp = vma->vm_file;
 	long error = -EBADF;
 
+	if (!filp)
+		goto  out;
+
 	switch (behavior) {
 	case MADV_NORMAL:
 	case MADV_SEQUENTIAL:
@@ -165,6 +167,7 @@ static long madvise_vma(struct vm_area_struct *vma, struct vm_area_struct **prev
 		break;
 	}
 		
+out:
 	return error;
 }
 
diff --git a/mm/memory.c b/mm/memory.c
index beabdef..6fe77ac 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -776,8 +776,8 @@ unsigned long zap_page_range(struct vm_area_struct *vma, unsigned long address,
  * Do a quick page-table lookup for a single page.
  * mm->page_table_lock must be held.
  */
-static struct page *
-__follow_page(struct mm_struct *mm, unsigned long address, int read, int write)
+static struct page *__follow_page(struct mm_struct *mm, unsigned long address,
+			int read, int write, int accessed)
 {
 	pgd_t *pgd;
 	pud_t *pud;
@@ -818,9 +818,11 @@ __follow_page(struct mm_struct *mm, unsigned long address, int read, int write)
 		pfn = pte_pfn(pte);
 		if (pfn_valid(pfn)) {
 			page = pfn_to_page(pfn);
-			if (write && !pte_dirty(pte) && !PageDirty(page))
-				set_page_dirty(page);
-			mark_page_accessed(page);
+			if (accessed) {
+				if (write && !pte_dirty(pte) &&!PageDirty(page))
+					set_page_dirty(page);
+				mark_page_accessed(page);
+			}
 			return page;
 		}
 	}
@@ -829,16 +831,19 @@ out:
 	return NULL;
 }
 
-struct page *
+inline struct page *
 follow_page(struct mm_struct *mm, unsigned long address, int write)
 {
-	return __follow_page(mm, address, /*read*/0, write);
+	return __follow_page(mm, address, 0, write, 1);
 }
 
-int
-check_user_page_readable(struct mm_struct *mm, unsigned long address)
+/*
+ * check_user_page_readable() can be called frm niterrupt context by oprofile,
+ * so we need to avoid taking any non-irq-safe locks
+ */
+int check_user_page_readable(struct mm_struct *mm, unsigned long address)
 {
-	return __follow_page(mm, address, /*read*/1, /*write*/0) != NULL;
+	return __follow_page(mm, address, 1, 0, 0) != NULL;
 }
 EXPORT_SYMBOL(check_user_page_readable);
 
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index cb41c31..1694845 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1138,11 +1138,11 @@ void mpol_free_shared_policy(struct shared_policy *p)
 	while (next) {
 		n = rb_entry(next, struct sp_node, nd);
 		next = rb_next(&n->nd);
+		rb_erase(&n->nd, &p->root);
 		mpol_free(n->policy);
 		kmem_cache_free(sn_cache, n);
 	}
 	spin_unlock(&p->lock);
-	p->root = RB_ROOT;
 }
 
 /* assumes fs == KERNEL_DS */
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 1d6ba6a..42bccfb 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1861,7 +1861,6 @@ static void __init free_area_init_core(struct pglist_data *pgdat,
 		unsigned long *zones_size, unsigned long *zholes_size)
 {
 	unsigned long i, j;
-	const unsigned long zone_required_alignment = 1UL << (MAX_ORDER-1);
 	int cpu, nid = pgdat->node_id;
 	unsigned long zone_start_pfn = pgdat->node_start_pfn;
 
@@ -1934,9 +1933,6 @@ static void __init free_area_init_core(struct pglist_data *pgdat,
 		zone->zone_mem_map = pfn_to_page(zone_start_pfn);
 		zone->zone_start_pfn = zone_start_pfn;
 
-		if ((zone_start_pfn) & (zone_required_alignment-1))
-			printk(KERN_CRIT "BUG: wrong zone alignment, it will crash\n");
-
 		memmap_init(size, nid, j, zone_start_pfn);
 
 		zonetable_add(zone, nid, j, zone_start_pfn, size);