[PATCH] xip: fs/mm: execute in place

- generic_file* file operations do no longer have a xip/non-xip split
- filemap_xip.c implements a new set of fops that require get_xip_page
  aop to work proper. all new fops are exported GPL-only (don't like to
  see whatever code use those except GPL modules)
- __xip_unmap now uses page_check_address, which is no longer static
  in rmap.c, and defined in linux/rmap.h
- mm/filemap.h is now much more clean, plainly having just Linus'
  inline funcs moved here from filemap.c
- fix includes in filemap_xip to make it build cleanly on i386
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>

fs/open.c

@@ -808,7 +808,9 @@ struct file *dentry_open(struct dentry *dentry, struct vfsmount *mnt, int flags)
 
 	/* NB: we're sure to have correct a_ops only after f_op->open */
 	if (f->f_flags & O_DIRECT) {
-		if (!f->f_mapping->a_ops || !f->f_mapping->a_ops->direct_IO) {
+		if (!f->f_mapping->a_ops ||
+		    ((!f->f_mapping->a_ops->direct_IO) &&
+		    (!f->f_mapping->a_ops->get_xip_page))) {
 			fput(f);
 			f = ERR_PTR(-EINVAL);
 		}

include/linux/fs.h

@@ -330,6 +330,8 @@ struct address_space_operations {
 	int (*releasepage) (struct page *, int);
 	ssize_t (*direct_IO)(int, struct kiocb *, const struct iovec *iov,
 			loff_t offset, unsigned long nr_segs);
+	struct page* (*get_xip_page)(struct address_space *, sector_t,
+			int);
 };
 
 struct backing_dev_info;
@@ -1497,6 +1499,22 @@ extern loff_t remote_llseek(struct file *file, loff_t offset, int origin);
 extern int generic_file_open(struct inode * inode, struct file * filp);
 extern int nonseekable_open(struct inode * inode, struct file * filp);
 
+#ifdef CONFIG_FS_XIP
+extern ssize_t xip_file_aio_read(struct kiocb *iocb, char __user *buf,
+				 size_t count, loff_t pos);
+extern ssize_t xip_file_readv(struct file *filp, const struct iovec *iov,
+			      unsigned long nr_segs, loff_t *ppos);
+extern ssize_t xip_file_sendfile(struct file *in_file, loff_t *ppos,
+				 size_t count, read_actor_t actor,
+				 void *target);
+extern int xip_file_mmap(struct file * file, struct vm_area_struct * vma);
+extern ssize_t xip_file_aio_write(struct kiocb *iocb, const char __user *buf,
+				  size_t count, loff_t pos);
+extern ssize_t xip_file_writev(struct file *file, const struct iovec *iov,
+			       unsigned long nr_segs, loff_t *ppos);
+extern int xip_truncate_page(struct address_space *mapping, loff_t from);
+#endif
+
 static inline void do_generic_file_read(struct file * filp, loff_t *ppos,
 					read_descriptor_t * desc,
 					read_actor_t actor)

include/linux/rmap.h

@@ -92,6 +92,12 @@ static inline void page_dup_rmap(struct page *page)
 int page_referenced(struct page *, int is_locked, int ignore_token);
 int try_to_unmap(struct page *);
 
+/*
+ * Called from mm/filemap_xip.c to unmap empty zero page
+ */
+pte_t *page_check_address(struct page *, struct mm_struct *, unsigned long);
+
+
 /*
  * Used by swapoff to help locate where page is expected in vma.
  */

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

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)
 {
@@ -1766,52 +1742,6 @@ __filemap_copy_from_user_iovec(char *vaddr,
 	return copied - 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;
-}
-
 /*
  * Performs necessary checks before doing a write
  *

mm/filemap.h

+/*
+ *	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>
+
+extern 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

mm/rmap.c

@@ -247,7 +247,7 @@ 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,
+pte_t *page_check_address(struct page *page, struct mm_struct *mm,
 			  unsigned long address)
 {
 	pgd_t *pgd;