xip: support non-struct page backed memory
Convert XIP to support non-struct page backed memory, using VM_MIXEDMAP for
the user mappings.
This requires the get_xip_page API to be changed to an address based one.
Improve the API layering a little bit too, while we're here.
This is required in order to support XIP filesystems on memory that isn't
backed with struct page (but memory with struct page is still supported too).
Signed-off-by: Nick Piggin <npiggin@suse.de>
Acked-by: Carsten Otte <cotte@de.ibm.com>
Cc: Jared Hulbert <jaredeh@gmail.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/mm/fadvise.c b/mm/fadvise.c
index 3c0f1e9..343cfdf 100644
--- a/mm/fadvise.c
+++ b/mm/fadvise.c
@@ -49,7 +49,7 @@
goto out;
}
- if (mapping->a_ops->get_xip_page) {
+ if (mapping->a_ops->get_xip_mem) {
switch (advice) {
case POSIX_FADV_NORMAL:
case POSIX_FADV_RANDOM:
diff --git a/mm/filemap_xip.c b/mm/filemap_xip.c
index 5e598c4..3e744ab 100644
--- a/mm/filemap_xip.c
+++ b/mm/filemap_xip.c
@@ -15,6 +15,7 @@
#include <linux/rmap.h>
#include <linux/sched.h>
#include <asm/tlbflush.h>
+#include <asm/io.h>
/*
* We do use our own empty page to avoid interference with other users
@@ -42,37 +43,41 @@
/*
* 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
+ * the mapping->a_ops->get_xip_mem() function for the actual low-level
* stuff.
*
* Note the struct file* is not used at all. It may be NULL.
*/
-static void
+static ssize_t
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)
+ char __user *buf,
+ size_t len,
+ loff_t *ppos)
{
struct inode *inode = mapping->host;
pgoff_t index, end_index;
unsigned long offset;
- loff_t isize;
+ loff_t isize, pos;
+ size_t copied = 0, error = 0;
- BUG_ON(!mapping->a_ops->get_xip_page);
+ BUG_ON(!mapping->a_ops->get_xip_mem);
- index = *ppos >> PAGE_CACHE_SHIFT;
- offset = *ppos & ~PAGE_CACHE_MASK;
+ pos = *ppos;
+ index = pos >> PAGE_CACHE_SHIFT;
+ offset = pos & ~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;
+ do {
+ unsigned long nr, left;
+ void *xip_mem;
+ unsigned long xip_pfn;
+ int zero = 0;
/* nr is the maximum number of bytes to copy from this page */
nr = PAGE_CACHE_SIZE;
@@ -85,19 +90,17 @@
}
}
nr = nr - offset;
+ if (nr > len)
+ nr = len;
- 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) {
+ error = mapping->a_ops->get_xip_mem(mapping, index, 0,
+ &xip_mem, &xip_pfn);
+ if (unlikely(error)) {
+ if (error == -ENODATA) {
/* sparse */
- page = ZERO_PAGE(0);
- } else {
- desc->error = PTR_ERR(page);
+ zero = 1;
+ } else
goto out;
- }
}
/* If users can be writing to this page using arbitrary
@@ -105,10 +108,10 @@
* before reading the page on the kernel side.
*/
if (mapping_writably_mapped(mapping))
- flush_dcache_page(page);
+ /* address based flush */ ;
/*
- * Ok, we have the page, so now we can copy it to user space...
+ * Ok, we have the mem, 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
@@ -116,47 +119,38 @@
* "pos" here (the actor routine has to update the user buffer
* pointers and the remaining count).
*/
- ret = actor(desc, page, offset, nr);
- offset += ret;
+ if (!zero)
+ left = __copy_to_user(buf+copied, xip_mem+offset, nr);
+ else
+ left = __clear_user(buf + copied, nr);
+
+ if (left) {
+ error = -EFAULT;
+ goto out;
+ }
+
+ copied += (nr - left);
+ offset += (nr - left);
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;
- }
+ } while (copied < len);
out:
- *ppos = ((loff_t) index << PAGE_CACHE_SHIFT) + offset;
+ *ppos = pos + copied;
if (filp)
file_accessed(filp);
+
+ return (copied ? copied : error);
}
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;
+ return do_xip_mapping_read(filp->f_mapping, &filp->f_ra, filp,
+ buf, len, ppos);
}
EXPORT_SYMBOL_GPL(xip_file_read);
@@ -211,13 +205,16 @@
*
* This function is derived from filemap_fault, but used for execute in place
*/
-static int xip_file_fault(struct vm_area_struct *area, struct vm_fault *vmf)
+static int xip_file_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
{
- struct file *file = area->vm_file;
+ struct file *file = vma->vm_file;
struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
- struct page *page;
pgoff_t size;
+ void *xip_mem;
+ unsigned long xip_pfn;
+ struct page *page;
+ int error;
/* XXX: are VM_FAULT_ codes OK? */
@@ -225,35 +222,44 @@
if (vmf->pgoff >= size)
return VM_FAULT_SIGBUS;
- page = mapping->a_ops->get_xip_page(mapping,
- vmf->pgoff*(PAGE_SIZE/512), 0);
- if (!IS_ERR(page))
- goto out;
- if (PTR_ERR(page) != -ENODATA)
+ error = mapping->a_ops->get_xip_mem(mapping, vmf->pgoff, 0,
+ &xip_mem, &xip_pfn);
+ if (likely(!error))
+ goto found;
+ if (error != -ENODATA)
return VM_FAULT_OOM;
/* sparse block */
- if ((area->vm_flags & (VM_WRITE | VM_MAYWRITE)) &&
- (area->vm_flags & (VM_SHARED| VM_MAYSHARE)) &&
+ if ((vma->vm_flags & (VM_WRITE | VM_MAYWRITE)) &&
+ (vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) &&
(!(mapping->host->i_sb->s_flags & MS_RDONLY))) {
+ int err;
+
/* maybe shared writable, allocate new block */
- page = mapping->a_ops->get_xip_page(mapping,
- vmf->pgoff*(PAGE_SIZE/512), 1);
- if (IS_ERR(page))
+ error = mapping->a_ops->get_xip_mem(mapping, vmf->pgoff, 1,
+ &xip_mem, &xip_pfn);
+ if (error)
return VM_FAULT_SIGBUS;
- /* unmap page at pgoff from all other vmas */
+ /* unmap sparse mappings at pgoff from all other vmas */
__xip_unmap(mapping, vmf->pgoff);
+
+found:
+ err = vm_insert_mixed(vma, (unsigned long)vmf->virtual_address,
+ xip_pfn);
+ if (err == -ENOMEM)
+ return VM_FAULT_OOM;
+ BUG_ON(err);
+ return VM_FAULT_NOPAGE;
} else {
/* not shared and writable, use xip_sparse_page() */
page = xip_sparse_page();
if (!page)
return VM_FAULT_OOM;
- }
-out:
- page_cache_get(page);
- vmf->page = page;
- return 0;
+ page_cache_get(page);
+ vmf->page = page;
+ return 0;
+ }
}
static struct vm_operations_struct xip_file_vm_ops = {
@@ -262,11 +268,11 @@
int xip_file_mmap(struct file * file, struct vm_area_struct * vma)
{
- BUG_ON(!file->f_mapping->a_ops->get_xip_page);
+ BUG_ON(!file->f_mapping->a_ops->get_xip_mem);
file_accessed(file);
vma->vm_ops = &xip_file_vm_ops;
- vma->vm_flags |= VM_CAN_NONLINEAR;
+ vma->vm_flags |= VM_CAN_NONLINEAR | VM_MIXEDMAP;
return 0;
}
EXPORT_SYMBOL_GPL(xip_file_mmap);
@@ -279,17 +285,17 @@
const 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);
+ BUG_ON(!mapping->a_ops->get_xip_mem);
do {
unsigned long index;
unsigned long offset;
size_t copied;
- char *kaddr;
+ void *xip_mem;
+ unsigned long xip_pfn;
offset = (pos & (PAGE_CACHE_SIZE -1)); /* Within page */
index = pos >> PAGE_CACHE_SHIFT;
@@ -297,28 +303,22 @@
if (bytes > count)
bytes = count;
- page = a_ops->get_xip_page(mapping,
- index*(PAGE_SIZE/512), 0);
- if (IS_ERR(page) && (PTR_ERR(page) == -ENODATA)) {
+ status = a_ops->get_xip_mem(mapping, index, 0,
+ &xip_mem, &xip_pfn);
+ if (status == -ENODATA) {
/* we allocate a new page unmap it */
- page = a_ops->get_xip_page(mapping,
- index*(PAGE_SIZE/512), 1);
- if (!IS_ERR(page))
+ status = a_ops->get_xip_mem(mapping, index, 1,
+ &xip_mem, &xip_pfn);
+ if (!status)
/* unmap page at pgoff from all other vmas */
__xip_unmap(mapping, index);
}
- if (IS_ERR(page)) {
- status = PTR_ERR(page);
+ if (status)
break;
- }
- fault_in_pages_readable(buf, bytes);
- kaddr = kmap_atomic(page, KM_USER0);
copied = bytes -
- __copy_from_user_inatomic_nocache(kaddr + offset, buf, bytes);
- kunmap_atomic(kaddr, KM_USER0);
- flush_dcache_page(page);
+ __copy_from_user_nocache(xip_mem + offset, buf, bytes);
if (likely(copied > 0)) {
status = copied;
@@ -398,7 +398,7 @@
/*
* truncate a page used for execute in place
- * functionality is analog to block_truncate_page but does use get_xip_page
+ * functionality is analog to block_truncate_page but does use get_xip_mem
* to get the page instead of page cache
*/
int
@@ -408,9 +408,11 @@
unsigned offset = from & (PAGE_CACHE_SIZE-1);
unsigned blocksize;
unsigned length;
- struct page *page;
+ void *xip_mem;
+ unsigned long xip_pfn;
+ int err;
- BUG_ON(!mapping->a_ops->get_xip_page);
+ BUG_ON(!mapping->a_ops->get_xip_mem);
blocksize = 1 << mapping->host->i_blkbits;
length = offset & (blocksize - 1);
@@ -421,18 +423,16 @@
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)
+ err = mapping->a_ops->get_xip_mem(mapping, index, 0,
+ &xip_mem, &xip_pfn);
+ if (unlikely(err)) {
+ if (err == -ENODATA)
/* Hole? No need to truncate */
return 0;
else
- return PTR_ERR(page);
+ return err;
}
- zero_user(page, offset, length);
+ memset(xip_mem + offset, 0, length);
return 0;
}
EXPORT_SYMBOL_GPL(xip_truncate_page);
diff --git a/mm/madvise.c b/mm/madvise.c
index 93ee375..23a0ec3 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -112,7 +112,7 @@
if (!file)
return -EBADF;
- if (file->f_mapping->a_ops->get_xip_page) {
+ if (file->f_mapping->a_ops->get_xip_mem) {
/* no bad return value, but ignore advice */
return 0;
}
