summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorCarsten Otte <cotte@de.ibm.com>2005-06-23 22:05:25 -0700
committerLinus Torvalds <torvalds@ppc970.osdl.org>2005-06-24 00:06:41 -0700
commitceffc078528befc008c6f2c2c4decda79eabd534 (patch)
treea289e10162bdef0c0d9f6533f1a647b0fe1ed7a9
parent420edbcc09008342c7b2665453f6b370739aadb0 (diff)
downloadlinux-3.10-ceffc078528befc008c6f2c2c4decda79eabd534.tar.gz
linux-3.10-ceffc078528befc008c6f2c2c4decda79eabd534.tar.bz2
linux-3.10-ceffc078528befc008c6f2c2c4decda79eabd534.zip
[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>
-rw-r--r--fs/open.c4
-rw-r--r--include/linux/fs.h18
-rw-r--r--include/linux/rmap.h6
-rw-r--r--mm/Makefile1
-rw-r--r--mm/filemap.c74
-rw-r--r--mm/filemap.h94
-rw-r--r--mm/filemap_xip.c581
-rw-r--r--mm/rmap.c4
8 files changed, 707 insertions, 75 deletions
diff --git a/fs/open.c b/fs/open.c
index 8ec63f73591..3f4a4286fdc 100644
--- a/fs/open.c
+++ b/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);
}
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 929bf8d20c8..79c0fafc021 100644
--- a/include/linux/fs.h
+++ b/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)
diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index 11b484e37ac..e80fb7ee6ef 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -93,6 +93,12 @@ 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.
*/
unsigned long page_address_in_vma(struct page *, struct vm_area_struct *);
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/filemap.c b/mm/filemap.c
index a3598b542a3..7332194d7af 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.
diff --git a/mm/filemap.h b/mm/filemap.h
new file mode 100644
index 00000000000..c2d0546a57e
--- /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>
+
+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
diff --git a/mm/filemap_xip.c b/mm/filemap_xip.c
new file mode 100644
index 00000000000..7d63acd4881
--- /dev/null
+++ b/mm/filemap_xip.c
@@ -0,0 +1,581 @@
+/*
+ * 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);
+}
+
+/*
+ * This is the "read()" routine for all filesystems
+ * that uses the get_xip_page address space operation.
+ */
+static ssize_t
+__xip_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
+ unsigned long nr_segs, loff_t *ppos)
+{
+ struct file *filp = iocb->ki_filp;
+ ssize_t retval;
+ unsigned long seg;
+ size_t count;
+
+ count = 0;
+ for (seg = 0; seg < nr_segs; seg++) {
+ const struct iovec *iv = &iov[seg];
+
+ /*
+ * If any segment has a negative length, or the cumulative
+ * length ever wraps negative then return -EINVAL.
+ */
+ count += iv->iov_len;
+ if (unlikely((ssize_t)(count|iv->iov_len) < 0))
+ return -EINVAL;
+ if (access_ok(VERIFY_WRITE, iv->iov_base, iv->iov_len))
+ continue;
+ if (seg == 0)
+ return -EFAULT;
+ nr_segs = seg;
+ count -= iv->iov_len; /* This segment is no good */
+ break;
+ }
+
+ retval = 0;
+ if (count) {
+ for (seg = 0; seg < nr_segs; seg++) {
+ read_descriptor_t desc;
+
+ desc.written = 0;
+ desc.arg.buf = iov[seg].iov_base;
+ desc.count = iov[seg].iov_len;
+ if (desc.count == 0)
+ continue;
+ desc.error = 0;
+ do_xip_mapping_read(filp->f_mapping, &filp->f_ra, filp,
+ ppos, &desc, file_read_actor);
+ retval += desc.written;
+ if (!retval) {
+ retval = desc.error;
+ break;
+ }
+ }
+ }
+ return retval;
+}
+
+ssize_t
+xip_file_aio_read(struct kiocb *iocb, char __user *buf, size_t count,
+ loff_t pos)
+{
+ struct iovec local_iov = { .iov_base = buf, .iov_len = count };
+
+ BUG_ON(iocb->ki_pos != pos);
+ return __xip_file_aio_read(iocb, &local_iov, 1, &iocb->ki_pos);
+}
+EXPORT_SYMBOL_GPL(xip_file_aio_read);
+
+ssize_t
+xip_file_readv(struct file *filp, const struct iovec *iov,
+ unsigned long nr_segs, loff_t *ppos)
+{
+ struct kiocb kiocb;
+
+ init_sync_kiocb(&kiocb, filp);
+ return __xip_file_aio_read(&kiocb, iov, nr_segs, ppos);
+}
+EXPORT_SYMBOL_GPL(xip_file_readv);
+
+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
+do_xip_file_write(struct kiocb *iocb, const struct iovec *iov,
+ unsigned long nr_segs, loff_t pos, loff_t *ppos,
+ size_t count)
+{
+ struct file *file = iocb->ki_filp;
+ struct address_space * mapping = file->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;
+ const struct iovec *cur_iov = iov; /* current iovec */
+ size_t iov_base = 0; /* offset in the current iovec */
+ char __user *buf;
+ ssize_t written = 0;
+
+ BUG_ON(!mapping->a_ops->get_xip_page);
+
+ buf = iov->iov_base;
+ 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));
+
+ if (likely(nr_segs == 1))
+ copied = filemap_copy_from_user(page, offset,
+ buf, bytes);
+ else
+ copied = filemap_copy_from_user_iovec(page, offset,
+ cur_iov, iov_base, bytes);
+ flush_dcache_page(page);
+ if (likely(copied > 0)) {
+ status = copied;
+
+ if (status >= 0) {
+ written += status;
+ count -= status;
+ pos += status;
+ buf += status;
+ if (unlikely(nr_segs > 1))
+ filemap_set_next_iovec(&cur_iov,
+ &iov_base, 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;
+}
+
+static ssize_t
+xip_file_aio_write_nolock(struct kiocb *iocb, const struct iovec *iov,
+ unsigned long nr_segs, loff_t *ppos)
+{
+ struct file *file = iocb->ki_filp;
+ struct address_space * mapping = file->f_mapping;
+ size_t ocount; /* original count */
+ size_t count; /* after file limit checks */
+ struct inode *inode = mapping->host;
+ unsigned long seg;
+ loff_t pos;
+ ssize_t written;
+ ssize_t err;
+
+ ocount = 0;
+ for (seg = 0; seg < nr_segs; seg++) {
+ const struct iovec *iv = &iov[seg];
+
+ /*
+ * If any segment has a negative length, or the cumulative
+ * length ever wraps negative then return -EINVAL.
+ */
+ ocount += iv->iov_len;
+ if (unlikely((ssize_t)(ocount|iv->iov_len) < 0))
+ return -EINVAL;
+ if (access_ok(VERIFY_READ, iv->iov_base, iv->iov_len))
+ continue;
+ if (seg == 0)
+ return -EFAULT;
+ nr_segs = seg;
+ ocount -= iv->iov_len; /* This segment is no good */
+ break;
+ }
+
+ count = ocount;
+ pos = *ppos;
+
+ vfs_check_frozen(inode->i_sb, SB_FREEZE_WRITE);
+
+ written = 0;
+
+ err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode));
+ if (err)
+ goto out;
+
+ if (count == 0)
+ goto out;
+
+ err = remove_suid(file->f_dentry);
+ if (err)
+ goto out;
+
+ inode_update_time(inode, 1);
+
+ /* use execute in place to copy directly to disk */
+ written = do_xip_file_write (iocb, iov,
+ nr_segs, pos, ppos, count);
+ out:
+ return written ? written : err;
+}
+
+static ssize_t
+__xip_file_write_nolock(struct file *file, const struct iovec *iov,
+ unsigned long nr_segs, loff_t *ppos)
+{
+ struct kiocb kiocb;
+
+ init_sync_kiocb(&kiocb, file);
+ return xip_file_aio_write_nolock(&kiocb, iov, nr_segs, ppos);
+}
+
+ssize_t
+xip_file_aio_write(struct kiocb *iocb, const char __user *buf,
+ size_t count, loff_t pos)
+{
+ struct file *file = iocb->ki_filp;
+ struct address_space *mapping = file->f_mapping;
+ struct inode *inode = mapping->host;
+ ssize_t ret;
+ struct iovec local_iov = { .iov_base = (void __user *)buf,
+ .iov_len = count };
+
+ BUG_ON(iocb->ki_pos != pos);
+
+ down(&inode->i_sem);
+ ret = xip_file_aio_write_nolock(iocb, &local_iov, 1, &iocb->ki_pos);
+ up(&inode->i_sem);
+ return ret;
+}
+EXPORT_SYMBOL_GPL(xip_file_aio_write);
+
+ssize_t xip_file_writev(struct file *file, const struct iovec *iov,
+ unsigned long nr_segs, loff_t *ppos)
+{
+ struct address_space *mapping = file->f_mapping;
+ struct inode *inode = mapping->host;
+ ssize_t ret;
+
+ down(&inode->i_sem);
+ ret = __xip_file_write_nolock(file, iov, nr_segs, ppos);
+ up(&inode->i_sem);
+ return ret;
+}
+EXPORT_SYMBOL_GPL(xip_file_writev);
+
+/*
+ * 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;
+ int err;
+
+ 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);
+ err = -ENOMEM;
+ if (!page)
+ goto out;
+ if (unlikely(IS_ERR(page))) {
+ if (PTR_ERR(page) == -ENODATA) {
+ /* Hole? No need to truncate */
+ return 0;
+ } else {
+ err = PTR_ERR(page);
+ goto out;
+ }
+ } 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);
+ err = 0;
+out:
+ return err;
+}
+EXPORT_SYMBOL_GPL(xip_truncate_page);
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;