Merge with /home/shaggy/git/linus-clean/

Signed-off-by: Dave Kleikamp <shaggy@austin.ibm.com>

17 files changed, 601 insertions, 107 deletions

diff --git a/mm/Makefile b/mm/Makefile
index 8f70ffd763c..4cd69e3ce42 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -19,3 +19,4 @@ obj-$(CONFIG_SPARSEMEM)	+= sparse.o
 obj-$(CONFIG_SHMEM) += shmem.o
 obj-$(CONFIG_TINY_SHMEM) += tiny-shmem.o
 
+obj-$(CONFIG_FS_XIP) += filemap_xip.o
diff --git a/mm/bootmem.c b/mm/bootmem.c
index f82f7aebbee..c1330cc1978 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -33,6 +33,14 @@ EXPORT_SYMBOL(max_pfn);		/* This is exported so
 				 * dma_get_required_mask(), which uses
 				 * it, can be an inline function */
 
+#ifdef CONFIG_CRASH_DUMP
+/*
+ * If we have booted due to a crash, max_pfn will be a very low value. We need
+ * to know the amount of memory that the previous kernel used.
+ */
+unsigned long saved_max_pfn;
+#endif
+
 /* return the number of _pages_ that will be allocated for the boot bitmap */
 unsigned long __init bootmem_bootmap_pages (unsigned long pages)
 {
@@ -57,7 +65,7 @@ static unsigned long __init init_bootmem_core (pg_data_t *pgdat,
 	pgdat->pgdat_next = pgdat_list;
 	pgdat_list = pgdat;
 
-	mapsize = (mapsize + (sizeof(long) - 1UL)) & ~(sizeof(long) - 1UL);
+	mapsize = ALIGN(mapsize, sizeof(long));
 	bdata->node_bootmem_map = phys_to_virt(mapstart << PAGE_SHIFT);
 	bdata->node_boot_start = (start << PAGE_SHIFT);
 	bdata->node_low_pfn = end;
@@ -178,7 +186,7 @@ __alloc_bootmem_core(struct bootmem_data *bdata, unsigned long size,
 	} else
 		preferred = 0;
 
-	preferred = ((preferred + align - 1) & ~(align - 1)) >> PAGE_SHIFT;
+	preferred = ALIGN(preferred, align) >> PAGE_SHIFT;
 	preferred += offset;
 	areasize = (size+PAGE_SIZE-1)/PAGE_SIZE;
 	incr = align >> PAGE_SHIFT ? : 1;
@@ -219,7 +227,7 @@ found:
 	 */
 	if (align < PAGE_SIZE &&
 	    bdata->last_offset && bdata->last_pos+1 == start) {
-		offset = (bdata->last_offset+align-1) & ~(align-1);
+		offset = ALIGN(bdata->last_offset, align);
 		BUG_ON(offset > PAGE_SIZE);
 		remaining_size = PAGE_SIZE-offset;
 		if (size < remaining_size) {
diff --git a/mm/fadvise.c b/mm/fadvise.c
index 57264d74b8b..5f19e87bc5a 100644
--- a/mm/fadvise.c
+++ b/mm/fadvise.c
@@ -43,6 +43,10 @@ asmlinkage long sys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice)
 		goto out;
 	}
 
+	if (mapping->a_ops->get_xip_page)
+		/* no bad return value, but ignore advice */
+		goto out;
+
 	/* Careful about overflows. Len == 0 means "as much as possible" */
 	endbyte = offset + len;
 	if (!len || endbyte < len)
diff --git a/mm/filemap.c b/mm/filemap.c
index a3598b542a3..c11418dd94e 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -28,6 +28,7 @@
 #include <linux/blkdev.h>
 #include <linux/security.h>
 #include <linux/syscalls.h>
+#include "filemap.h"
 /*
  * FIXME: remove all knowledge of the buffer layer from the core VM
  */
@@ -1714,32 +1715,7 @@ int remove_suid(struct dentry *dentry)
 }
 EXPORT_SYMBOL(remove_suid);
 
-/*
- * Copy as much as we can into the page and return the number of bytes which
- * were sucessfully copied.  If a fault is encountered then clear the page
- * out to (offset+bytes) and return the number of bytes which were copied.
- */
-static inline size_t
-filemap_copy_from_user(struct page *page, unsigned long offset,
-			const char __user *buf, unsigned bytes)
-{
-	char *kaddr;
-	int left;
-
-	kaddr = kmap_atomic(page, KM_USER0);
-	left = __copy_from_user_inatomic(kaddr + offset, buf, bytes);
-	kunmap_atomic(kaddr, KM_USER0);
-
-	if (left != 0) {
-		/* Do it the slow way */
-		kaddr = kmap(page);
-		left = __copy_from_user(kaddr + offset, buf, bytes);
-		kunmap(page);
-	}
-	return bytes - left;
-}
-
-static size_t
+size_t
 __filemap_copy_from_user_iovec(char *vaddr, 
 			const struct iovec *iov, size_t base, size_t bytes)
 {
@@ -1767,52 +1743,6 @@ __filemap_copy_from_user_iovec(char *vaddr,
 }
 
 /*
- * This has the same sideeffects and return value as filemap_copy_from_user().
- * The difference is that on a fault we need to memset the remainder of the
- * page (out to offset+bytes), to emulate filemap_copy_from_user()'s
- * single-segment behaviour.
- */
-static inline size_t
-filemap_copy_from_user_iovec(struct page *page, unsigned long offset,
-			const struct iovec *iov, size_t base, size_t bytes)
-{
-	char *kaddr;
-	size_t copied;
-
-	kaddr = kmap_atomic(page, KM_USER0);
-	copied = __filemap_copy_from_user_iovec(kaddr + offset, iov,
-						base, bytes);
-	kunmap_atomic(kaddr, KM_USER0);
-	if (copied != bytes) {
-		kaddr = kmap(page);
-		copied = __filemap_copy_from_user_iovec(kaddr + offset, iov,
-							base, bytes);
-		kunmap(page);
-	}
-	return copied;
-}
-
-static inline void
-filemap_set_next_iovec(const struct iovec **iovp, size_t *basep, size_t bytes)
-{
-	const struct iovec *iov = *iovp;
-	size_t base = *basep;
-
-	while (bytes) {
-		int copy = min(bytes, iov->iov_len - base);
-
-		bytes -= copy;
-		base += copy;
-		if (iov->iov_len == base) {
-			iov++;
-			base = 0;
-		}
-	}
-	*iovp = iov;
-	*basep = base;
-}
-
-/*
  * Performs necessary checks before doing a write
  *
  * Can adjust writing position aor amount of bytes to write.
@@ -1921,8 +1851,11 @@ generic_file_direct_write(struct kiocb *iocb, const struct iovec *iov,
 	 * i_sem is held, which protects generic_osync_inode() from
 	 * livelocking.
 	 */
-	if (written >= 0 && file->f_flags & O_SYNC)
-		generic_osync_inode(inode, mapping, OSYNC_METADATA);
+	if (written >= 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) {
+		int err = generic_osync_inode(inode, mapping, OSYNC_METADATA);
+		if (err < 0)
+			written = err;
+	}
 	if (written == count && !is_sync_kiocb(iocb))
 		written = -EIOCBQUEUED;
 	return written;
@@ -2021,7 +1954,9 @@ generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov,
 				if (unlikely(nr_segs > 1)) {
 					filemap_set_next_iovec(&cur_iov,
 							&iov_base, status);
-					buf = cur_iov->iov_base + iov_base;
+					if (count)
+						buf = cur_iov->iov_base +
+							iov_base;
 				} else {
 					iov_base += status;
 				}
diff --git a/mm/filemap.h b/mm/filemap.h
new file mode 100644
index 00000000000..13793ba0ce1
--- /dev/null
+++ b/mm/filemap.h
@@ -0,0 +1,94 @@
+/*
+ *	linux/mm/filemap.h
+ *
+ * Copyright (C) 1994-1999  Linus Torvalds
+ */
+
+#ifndef __FILEMAP_H
+#define __FILEMAP_H
+
+#include <linux/types.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/highmem.h>
+#include <linux/uio.h>
+#include <linux/config.h>
+#include <asm/uaccess.h>
+
+size_t
+__filemap_copy_from_user_iovec(char *vaddr,
+			       const struct iovec *iov,
+			       size_t base,
+			       size_t bytes);
+
+/*
+ * Copy as much as we can into the page and return the number of bytes which
+ * were sucessfully copied.  If a fault is encountered then clear the page
+ * out to (offset+bytes) and return the number of bytes which were copied.
+ */
+static inline size_t
+filemap_copy_from_user(struct page *page, unsigned long offset,
+			const char __user *buf, unsigned bytes)
+{
+	char *kaddr;
+	int left;
+
+	kaddr = kmap_atomic(page, KM_USER0);
+	left = __copy_from_user_inatomic(kaddr + offset, buf, bytes);
+	kunmap_atomic(kaddr, KM_USER0);
+
+	if (left != 0) {
+		/* Do it the slow way */
+		kaddr = kmap(page);
+		left = __copy_from_user(kaddr + offset, buf, bytes);
+		kunmap(page);
+	}
+	return bytes - left;
+}
+
+/*
+ * This has the same sideeffects and return value as filemap_copy_from_user().
+ * The difference is that on a fault we need to memset the remainder of the
+ * page (out to offset+bytes), to emulate filemap_copy_from_user()'s
+ * single-segment behaviour.
+ */
+static inline size_t
+filemap_copy_from_user_iovec(struct page *page, unsigned long offset,
+			const struct iovec *iov, size_t base, size_t bytes)
+{
+	char *kaddr;
+	size_t copied;
+
+	kaddr = kmap_atomic(page, KM_USER0);
+	copied = __filemap_copy_from_user_iovec(kaddr + offset, iov,
+						base, bytes);
+	kunmap_atomic(kaddr, KM_USER0);
+	if (copied != bytes) {
+		kaddr = kmap(page);
+		copied = __filemap_copy_from_user_iovec(kaddr + offset, iov,
+							base, bytes);
+		kunmap(page);
+	}
+	return copied;
+}
+
+static inline void
+filemap_set_next_iovec(const struct iovec **iovp, size_t *basep, size_t bytes)
+{
+	const struct iovec *iov = *iovp;
+	size_t base = *basep;
+
+	while (bytes) {
+		int copy = min(bytes, iov->iov_len - base);
+
+		bytes -= copy;
+		base += copy;
+		if (iov->iov_len == base) {
+			iov++;
+			base = 0;
+		}
+	}
+	*iovp = iov;
+	*basep = base;
+}
+#endif
diff --git a/mm/filemap_xip.c b/mm/filemap_xip.c
new file mode 100644
index 00000000000..4553b2c5aab
--- /dev/null
+++ b/mm/filemap_xip.c
@@ -0,0 +1,447 @@
+/*
+ *	linux/mm/filemap_xip.c
+ *
+ * Copyright (C) 2005 IBM Corporation
+ * Author: Carsten Otte <cotte@de.ibm.com>
+ *
+ * derived from linux/mm/filemap.c - Copyright (C) Linus Torvalds
+ *
+ */
+
+#include <linux/fs.h>
+#include <linux/pagemap.h>
+#include <linux/module.h>
+#include <linux/uio.h>
+#include <linux/rmap.h>
+#include <asm/tlbflush.h>
+#include "filemap.h"
+
+/*
+ * This is a file read routine for execute in place files, and uses
+ * the mapping->a_ops->get_xip_page() function for the actual low-level
+ * stuff.
+ *
+ * Note the struct file* is not used at all.  It may be NULL.
+ */
+static void
+do_xip_mapping_read(struct address_space *mapping,
+		    struct file_ra_state *_ra,
+		    struct file *filp,
+		    loff_t *ppos,
+		    read_descriptor_t *desc,
+		    read_actor_t actor)
+{
+	struct inode *inode = mapping->host;
+	unsigned long index, end_index, offset;
+	loff_t isize;
+
+	BUG_ON(!mapping->a_ops->get_xip_page);
+
+	index = *ppos >> PAGE_CACHE_SHIFT;
+	offset = *ppos & ~PAGE_CACHE_MASK;
+
+	isize = i_size_read(inode);
+	if (!isize)
+		goto out;
+
+	end_index = (isize - 1) >> PAGE_CACHE_SHIFT;
+	for (;;) {
+		struct page *page;
+		unsigned long nr, ret;
+
+		/* nr is the maximum number of bytes to copy from this page */
+		nr = PAGE_CACHE_SIZE;
+		if (index >= end_index) {
+			if (index > end_index)
+				goto out;
+			nr = ((isize - 1) & ~PAGE_CACHE_MASK) + 1;
+			if (nr <= offset) {
+				goto out;
+			}
+		}
+		nr = nr - offset;
+
+		page = mapping->a_ops->get_xip_page(mapping,
+			index*(PAGE_SIZE/512), 0);
+		if (!page)
+			goto no_xip_page;
+		if (unlikely(IS_ERR(page))) {
+			if (PTR_ERR(page) == -ENODATA) {
+				/* sparse */
+				page = virt_to_page(empty_zero_page);
+			} 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
+		 * before reading the page on the kernel side.
+		 */
+		if (mapping_writably_mapped(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...
+		 *
+		 * The actor routine returns how many bytes were actually used..
+		 * NOTE! This may not be the same as how much of a user buffer
+		 * we filled up (we may be padding etc), so we can only update
+		 * "pos" here (the actor routine has to update the user buffer
+		 * pointers and the remaining count).
+		 */
+		ret = actor(desc, page, offset, nr);
+		offset += ret;
+		index += offset >> PAGE_CACHE_SHIFT;
+		offset &= ~PAGE_CACHE_MASK;
+
+		if (ret == nr && desc->count)
+			continue;
+		goto out;
+
+no_xip_page:
+		/* Did not get the page. Report it */
+		desc->error = -EIO;
+		goto out;
+	}
+
+out:
+	*ppos = ((loff_t) index << PAGE_CACHE_SHIFT) + offset;
+	if (filp)
+		file_accessed(filp);
+}
+
+ssize_t
+xip_file_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos)
+{
+	read_descriptor_t desc;
+
+	if (!access_ok(VERIFY_WRITE, buf, len))
+		return -EFAULT;
+
+	desc.written = 0;
+	desc.arg.buf = buf;
+	desc.count = len;
+	desc.error = 0;
+
+	do_xip_mapping_read(filp->f_mapping, &filp->f_ra, filp,
+			    ppos, &desc, file_read_actor);
+
+	if (desc.written)
+		return desc.written;
+	else
+		return desc.error;
+}
+EXPORT_SYMBOL_GPL(xip_file_read);
+
+ssize_t
+xip_file_sendfile(struct file *in_file, loff_t *ppos,
+	     size_t count, read_actor_t actor, void *target)
+{
+	read_descriptor_t desc;
+
+	if (!count)
+		return 0;
+
+	desc.written = 0;
+	desc.count = count;
+	desc.arg.data = target;
+	desc.error = 0;
+
+	do_xip_mapping_read(in_file->f_mapping, &in_file->f_ra, in_file,
+			    ppos, &desc, actor);
+	if (desc.written)
+		return desc.written;
+	return desc.error;
+}
+EXPORT_SYMBOL_GPL(xip_file_sendfile);
+
+/*
+ * __xip_unmap is invoked from xip_unmap and
+ * 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?
+ */
+static void
+__xip_unmap (struct address_space * mapping,
+		     unsigned long pgoff)
+{
+	struct vm_area_struct *vma;
+	struct mm_struct *mm;
+	struct prio_tree_iter iter;
+	unsigned long address;
+	pte_t *pte;
+	pte_t pteval;
+
+	spin_lock(&mapping->i_mmap_lock);
+	vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) {
+		mm = vma->vm_mm;
+		address = vma->vm_start +
+			((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
+		BUG_ON(address < vma->vm_start || address >= vma->vm_end);
+		/*
+		 * 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,
+					 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);
+			BUG_ON(pte_dirty(pteval));
+			pte_unmap(pte);
+			spin_unlock(&mm->page_table_lock);
+		}
+	}
+	spin_unlock(&mapping->i_mmap_lock);
+}
+
+/*
+ * xip_nopage() is invoked via the vma operations vector for a
+ * mapped memory region to read in file data during a page fault.
+ *
+ * This function is derived from filemap_nopage, but used for execute in place
+ */
+static struct page *
+xip_file_nopage(struct vm_area_struct * area,
+		   unsigned long address,
+		   int *type)
+{
+	struct file *file = area->vm_file;
+	struct address_space *mapping = file->f_mapping;
+	struct inode *inode = mapping->host;
+	struct page *page;
+	unsigned long size, pgoff, endoff;
+
+	pgoff = ((address - area->vm_start) >> PAGE_CACHE_SHIFT)
+		+ area->vm_pgoff;
+	endoff = ((area->vm_end - area->vm_start) >> PAGE_CACHE_SHIFT)
+		+ area->vm_pgoff;
+
+	size = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+	if (pgoff >= size) {
+		return NULL;
+	}
+
+	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)
+		return NULL;
+
+	/* sparse block */
+	if ((area->vm_flags & (VM_WRITE | VM_MAYWRITE)) &&
+	    (area->vm_flags & (VM_SHARED| VM_MAYSHARE)) &&
+	    (!(mapping->host->i_sb->s_flags & MS_RDONLY))) {
+		/* maybe shared writable, allocate new block */
+		page = mapping->a_ops->get_xip_page (mapping,
+			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);
+	}
+
+	return page;
+}
+
+static struct vm_operations_struct xip_file_vm_ops = {
+	.nopage         = xip_file_nopage,
+};
+
+int xip_file_mmap(struct file * file, struct vm_area_struct * vma)
+{
+	BUG_ON(!file->f_mapping->a_ops->get_xip_page);
+
+	file_accessed(file);
+	vma->vm_ops = &xip_file_vm_ops;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(xip_file_mmap);
+
+static ssize_t
+__xip_file_write(struct file *filp, const char __user *buf,
+		  size_t count, loff_t pos, loff_t *ppos)
+{
+	struct address_space * mapping = filp->f_mapping;
+	struct address_space_operations *a_ops = mapping->a_ops;
+	struct inode 	*inode = mapping->host;
+	long		status = 0;
+	struct page	*page;
+	size_t		bytes;
+	ssize_t		written = 0;
+
+	BUG_ON(!mapping->a_ops->get_xip_page);
+
+	do {
+		unsigned long index;
+		unsigned long offset;
+		size_t copied;
+
+		offset = (pos & (PAGE_CACHE_SIZE -1)); /* Within page */
+		index = pos >> PAGE_CACHE_SHIFT;
+		bytes = PAGE_CACHE_SIZE - offset;
+		if (bytes > count)
+			bytes = count;
+
+		/*
+		 * Bring in the user page that we will copy from _first_.
+		 * Otherwise there's a nasty deadlock on copying from the
+		 * same page as we're writing to, without it being marked
+		 * up-to-date.
+		 */
+		fault_in_pages_readable(buf, bytes);
+
+		page = a_ops->get_xip_page(mapping,
+					   index*(PAGE_SIZE/512), 0);
+		if (IS_ERR(page) && (PTR_ERR(page) == -ENODATA)) {
+			/* we allocate a new page unmap it */
+			page = a_ops->get_xip_page(mapping,
+						   index*(PAGE_SIZE/512), 1);
+			if (!IS_ERR(page))
+				/* unmap page at pgoff from all other vmas */
+				__xip_unmap(mapping, index);
+		}
+
+		if (IS_ERR(page)) {
+			status = PTR_ERR(page);
+			break;
+		}
+
+		BUG_ON(!PageUptodate(page));
+
+		copied = filemap_copy_from_user(page, offset, buf, bytes);
+		flush_dcache_page(page);
+		if (likely(copied > 0)) {
+			status = copied;
+
+			if (status >= 0) {
+				written += status;
+				count -= status;
+				pos += status;
+				buf += status;
+			}
+		}
+		if (unlikely(copied != bytes))
+			if (status >= 0)
+				status = -EFAULT;
+		if (status < 0)
+			break;
+	} while (count);
+	*ppos = pos;
+	/*
+	 * No need to use i_size_read() here, the i_size
+	 * cannot change under us because we hold i_sem.
+	 */
+	if (pos > inode->i_size) {
+		i_size_write(inode, pos);
+		mark_inode_dirty(inode);
+	}
+
+	return written ? written : status;
+}
+
+ssize_t
+xip_file_write(struct file *filp, const char __user *buf, size_t len,
+	       loff_t *ppos)
+{
+	struct address_space *mapping = filp->f_mapping;
+	struct inode *inode = mapping->host;
+	size_t count;
+	loff_t pos;
+	ssize_t ret;
+
+	down(&inode->i_sem);
+
+	if (!access_ok(VERIFY_READ, buf, len)) {
+		ret=-EFAULT;
+		goto out_up;
+	}
+
+	pos = *ppos;
+	count = len;
+
+	vfs_check_frozen(inode->i_sb, SB_FREEZE_WRITE);
+
+	/* We can write back this queue in page reclaim */
+	current->backing_dev_info = mapping->backing_dev_info;
+
+	ret = generic_write_checks(filp, &pos, &count, S_ISBLK(inode->i_mode));
+	if (ret)
+		goto out_backing;
+	if (count == 0)
+		goto out_backing;
+
+	ret = remove_suid(filp->f_dentry);
+	if (ret)
+		goto out_backing;
+
+	inode_update_time(inode, 1);
+
+	ret = __xip_file_write (filp, buf, count, pos, ppos);
+
+ out_backing:
+	current->backing_dev_info = NULL;
+ out_up:
+	up(&inode->i_sem);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(xip_file_write);
+
+/*
+ * truncate a page used for execute in place
+ * functionality is analog to block_truncate_page but does use get_xip_page
+ * to get the page instead of page cache
+ */
+int
+xip_truncate_page(struct address_space *mapping, loff_t from)
+{
+	pgoff_t index = from >> PAGE_CACHE_SHIFT;
+	unsigned offset = from & (PAGE_CACHE_SIZE-1);
+	unsigned blocksize;
+	unsigned length;
+	struct page *page;
+	void *kaddr;
+
+	BUG_ON(!mapping->a_ops->get_xip_page);
+
+	blocksize = 1 << mapping->host->i_blkbits;
+	length = offset & (blocksize - 1);
+
+	/* Block boundary? Nothing to do */
+	if (!length)
+		return 0;
+
+	length = blocksize - length;
+
+	page = mapping->a_ops->get_xip_page(mapping,
+					    index*(PAGE_SIZE/512), 0);
+	if (!page)
+		return -ENOMEM;
+	if (unlikely(IS_ERR(page))) {
+		if (PTR_ERR(page) == -ENODATA)
+			/* Hole? No need to truncate */
+			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);
+
+	flush_dcache_page(page);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(xip_truncate_page);
diff --git a/mm/madvise.c b/mm/madvise.c
index 54a5d3bc55d..73180a22877 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -86,6 +86,11 @@ static long madvise_willneed(struct vm_area_struct * vma,
 	if (!file)
 		return -EBADF;
 
+	if (file->f_mapping->a_ops->get_xip_page) {
+		/* no bad return value, but ignore advice */
+		return 0;
+	}
+
 	*prev = vma;
 	start = ((start - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
 	if (end > vma->vm_end)
diff --git a/mm/memory.c b/mm/memory.c
index 30975ef4872..beabdefa625 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1139,7 +1139,7 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
 {
 	pgd_t *pgd;
 	unsigned long next;
-	unsigned long end = addr + size;
+	unsigned long end = addr + PAGE_ALIGN(size);
 	struct mm_struct *mm = vma->vm_mm;
 	int err;
 
@@ -1458,7 +1458,7 @@ restart:
  * unmap_mapping_range - unmap the portion of all mmaps
  * in the specified address_space corresponding to the specified
  * page range in the underlying file.
- * @address_space: the address space containing mmaps to be unmapped.
+ * @mapping: the address space containing mmaps to be unmapped.
  * @holebegin: byte in first page to unmap, relative to the start of
  * the underlying file.  This will be rounded down to a PAGE_SIZE
  * boundary.  Note that this is different from vmtruncate(), which
diff --git a/mm/mempool.c b/mm/mempool.c
index 9a72f7d918f..65f2957b8d5 100644
--- a/mm/mempool.c
+++ b/mm/mempool.c
@@ -205,7 +205,7 @@ void * mempool_alloc(mempool_t *pool, unsigned int __nocast gfp_mask)
 	void *element;
 	unsigned long flags;
 	wait_queue_t wait;
-	int gfp_temp;
+	unsigned int gfp_temp;
 
 	might_sleep_if(gfp_mask & __GFP_WAIT);
 
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 59666d905f1..1e56076672f 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -253,14 +253,16 @@ static struct mm_struct *oom_kill_process(struct task_struct *p)
  * OR try to be smart about which process to kill. Note that we
  * don't have to be perfect here, we just have to be good.
  */
-void out_of_memory(unsigned int __nocast gfp_mask)
+void out_of_memory(unsigned int __nocast gfp_mask, int order)
 {
 	struct mm_struct *mm = NULL;
 	task_t * p;
 
-	printk("oom-killer: gfp_mask=0x%x\n", gfp_mask);
-	/* print memory stats */
-	show_mem();
+	if (printk_ratelimit()) {
+		printk("oom-killer: gfp_mask=0x%x, order=%d\n",
+			gfp_mask, order);
+		show_mem();
+	}
 
 	read_lock(&tasklist_lock);
 retry:
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 613b99a5591..a6329fa8f86 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -354,7 +354,7 @@ static void background_writeout(unsigned long _min_pages)
  * the whole world.  Returns 0 if a pdflush thread was dispatched.  Returns
  * -1 if all pdflush threads were busy.
  */
-int wakeup_bdflush(long nr_pages)
+int wakeup_pdflush(long nr_pages)
 {
 	if (nr_pages == 0) {
 		struct writeback_state wbs;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 7ee675ad101..1d6ba6a4b59 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -897,12 +897,6 @@ rebalance:
 	cond_resched();
 
 	if (likely(did_some_progress)) {
-		/*
-		 * Go through the zonelist yet one more time, keep
-		 * very high watermark here, this is only to catch
-		 * a parallel oom killing, we must fail if we're still
-		 * under heavy pressure.
-		 */
 		for (i = 0; (z = zones[i]) != NULL; i++) {
 			if (!zone_watermark_ok(z, order, z->pages_min,
 					       classzone_idx, can_try_harder,
@@ -936,7 +930,7 @@ rebalance:
 				goto got_pg;
 		}
 
-		out_of_memory(gfp_mask);
+		out_of_memory(gfp_mask, order);
 		goto restart;
 	}
 
@@ -1667,9 +1661,8 @@ void __init memmap_init_zone(unsigned long size, int nid, unsigned long zone,
 #ifdef WANT_PAGE_VIRTUAL
 		/* The shift won't overflow because ZONE_NORMAL is below 4G. */
 		if (!is_highmem_idx(zone))
-			set_page_address(page, __va(start_pfn << PAGE_SHIFT));
+			set_page_address(page, __va(pfn << PAGE_SHIFT));
 #endif
-		start_pfn++;
 	}
 }
 
diff --git a/mm/page_io.c b/mm/page_io.c
index 667c76df1ec..2e605a19ce5 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -127,7 +127,7 @@ out:
 	return ret;
 }
 
-#if defined(CONFIG_SOFTWARE_SUSPEND) || defined(CONFIG_PM_DISK)
+#ifdef CONFIG_SOFTWARE_SUSPEND
 /*
  * A scruffy utility function to read or write an arbitrary swap page
  * and wait on the I/O.  The caller must have a ref on the page.
diff --git a/mm/pdflush.c b/mm/pdflush.c
index 38ce279cc8c..d6781951267 100644
--- a/mm/pdflush.c
+++ b/mm/pdflush.c
@@ -105,7 +105,7 @@ static int __pdflush(struct pdflush_work *my_work)
 		spin_unlock_irq(&pdflush_lock);
 
 		schedule();
-		if (try_to_freeze(PF_FREEZE)) {
+		if (try_to_freeze()) {
 			spin_lock_irq(&pdflush_lock);
 			continue;
 		}
diff --git a/mm/rmap.c b/mm/rmap.c
index 89770bd25f3..08ac5c7fa91 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -247,8 +247,8 @@ unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma)
  *
  * On success returns with mapped pte and locked mm->page_table_lock.
  */
-static pte_t *page_check_address(struct page *page, struct mm_struct *mm,
-					unsigned long address)
+pte_t *page_check_address(struct page *page, struct mm_struct *mm,
+			  unsigned long address)
 {
 	pgd_t *pgd;
 	pud_t *pud;
diff --git a/mm/slab.c b/mm/slab.c
index 122d031baab..c9e706db463 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -584,7 +584,8 @@ static inline struct array_cache *ac_data(kmem_cache_t *cachep)
 	return cachep->array[smp_processor_id()];
 }
 
-static inline kmem_cache_t *__find_general_cachep(size_t size, int gfpflags)
+static inline kmem_cache_t *__find_general_cachep(size_t size,
+						unsigned int __nocast gfpflags)
 {
 	struct cache_sizes *csizep = malloc_sizes;
 
@@ -608,7 +609,8 @@ static inline kmem_cache_t *__find_general_cachep(size_t size, int gfpflags)
 	return csizep->cs_cachep;
 }
 
-kmem_cache_t *kmem_find_general_cachep(size_t size, int gfpflags)
+kmem_cache_t *kmem_find_general_cachep(size_t size,
+		unsigned int __nocast gfpflags)
 {
 	return __find_general_cachep(size, gfpflags);
 }
@@ -2100,7 +2102,7 @@ cache_alloc_debugcheck_before(kmem_cache_t *cachep, unsigned int __nocast flags)
 #if DEBUG
 static void *
 cache_alloc_debugcheck_after(kmem_cache_t *cachep,
-			unsigned long flags, void *objp, void *caller)
+			unsigned int __nocast flags, void *objp, void *caller)
 {
 	if (!objp)	
 		return objp;
@@ -2372,6 +2374,9 @@ void *kmem_cache_alloc_node(kmem_cache_t *cachep, int flags, int nodeid)
 	struct slab *slabp;
 	kmem_bufctl_t next;
 
+	if (nodeid == -1)
+		return kmem_cache_alloc(cachep, flags);
+
 	for (loop = 0;;loop++) {
 		struct list_head *q;
 
@@ -2439,7 +2444,7 @@ got_slabp:
 }
 EXPORT_SYMBOL(kmem_cache_alloc_node);
 
-void *kmalloc_node(size_t size, int flags, int node)
+void *kmalloc_node(size_t size, unsigned int __nocast flags, int node)
 {
 	kmem_cache_t *cachep;
 
@@ -3091,7 +3096,7 @@ unsigned int ksize(const void *objp)
  * @s: the string to duplicate
  * @gfp: the GFP mask used in the kmalloc() call when allocating memory
  */
-char *kstrdup(const char *s, int gfp)
+char *kstrdup(const char *s, unsigned int __nocast gfp)
 {
 	size_t len;
 	char *buf;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 4b8e62a1937..cfffe5098d5 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -972,7 +972,7 @@ int try_to_free_pages(struct zone **zones, unsigned int gfp_mask)
 		 * writeout.  So in laptop mode, write out the whole world.
 		 */
 		if (total_scanned > sc.swap_cluster_max + sc.swap_cluster_max/2) {
-			wakeup_bdflush(laptop_mode ? 0 : total_scanned);
+			wakeup_pdflush(laptop_mode ? 0 : total_scanned);
 			sc.may_writepage = 1;
 		}
 
@@ -1216,8 +1216,8 @@ static int kswapd(void *p)
 	order = 0;
 	for ( ; ; ) {
 		unsigned long new_order;
-		if (current->flags & PF_FREEZE)
-			refrigerator(PF_FREEZE);
+
+		try_to_freeze();
 
 		prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE);
 		new_order = pgdat->kswapd_max_order;