#include <linux/module.h>
#include <linux/uio.h>
#include <linux/rmap.h>
+#include <linux/mmu_notifier.h>
+#include <linux/sched.h>
+#include <linux/seqlock.h>
+#include <linux/mutex.h>
#include <asm/tlbflush.h>
-#include "filemap.h"
+#include <asm/io.h>
+
+/*
+ * We do use our own empty page to avoid interference with other users
+ * of ZERO_PAGE(), such as /dev/zero
+ */
+static DEFINE_MUTEX(xip_sparse_mutex);
+static seqcount_t xip_sparse_seq = SEQCNT_ZERO;
+static struct page *__xip_sparse_page;
+
+/* called under xip_sparse_mutex */
+static struct page *xip_sparse_page(void)
+{
+ if (!__xip_sparse_page) {
+ struct page *page = alloc_page(GFP_HIGHUSER | __GFP_ZERO);
+
+ if (page)
+ __xip_sparse_page = page;
+ }
+ return __xip_sparse_page;
+}
/*
* 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;
- unsigned long index, end_index, offset;
- loff_t isize;
+ pgoff_t index, end_index;
+ unsigned long offset;
+ 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;
}
}
nr = nr - offset;
+ if (nr > len - copied)
+ nr = len - copied;
- 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
* 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
* "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 (!zero)
+ left = __copy_to_user(buf+copied, xip_mem+offset, nr);
+ else
+ left = __clear_user(buf + copied, nr);
- if (ret == nr && desc->count)
- continue;
- goto out;
+ if (left) {
+ error = -EFAULT;
+ goto out;
+ }
-no_xip_page:
- /* Did not get the page. Report it */
- desc->error = -EIO;
- goto out;
- }
+ copied += (nr - left);
+ offset += (nr - left);
+ index += offset >> PAGE_CACHE_SHIFT;
+ offset &= ~PAGE_CACHE_MASK;
+ } 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);
-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
- * ZERO_PAGE when found at pgoff. Should it go in rmap.c?
+ * __xip_sparse_page when found at pgoff.
*/
static void
__xip_unmap (struct address_space * mapping,
unsigned long address;
pte_t *pte;
pte_t pteval;
- struct page *page = ZERO_PAGE(address);
+ spinlock_t *ptl;
+ struct page *page;
+ unsigned count;
+ int locked = 0;
+
+ count = read_seqcount_begin(&xip_sparse_seq);
+
+ page = __xip_sparse_page;
+ if (!page)
+ return;
+retry:
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(page, mm, address);
- if (!IS_ERR(pte)) {
+ pte = page_check_address(page, mm, address, &ptl, 1);
+ if (pte) {
/* Nuke the page table entry. */
flush_cache_page(vma, address, pte_pfn(*pte));
- pteval = ptep_clear_flush(vma, address, pte);
+ pteval = ptep_clear_flush_notify(vma, address, pte);
page_remove_rmap(page);
dec_mm_counter(mm, file_rss);
BUG_ON(pte_dirty(pteval));
- pte_unmap(pte);
- spin_unlock(&mm->page_table_lock);
+ pte_unmap_unlock(pte, ptl);
page_cache_release(page);
}
}
spin_unlock(&mapping->i_mmap_lock);
+
+ if (locked) {
+ mutex_unlock(&xip_sparse_mutex);
+ } else if (read_seqcount_retry(&xip_sparse_seq, count)) {
+ mutex_lock(&xip_sparse_mutex);
+ locked = 1;
+ goto retry;
+ }
}
/*
- * xip_nopage() is invoked via the vma operations vector for a
+ * xip_fault() 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
+ * This function is derived from filemap_fault, but used for execute in place
*/
-static struct page *
-xip_file_nopage(struct vm_area_struct * area,
- unsigned long address,
- int *type)
+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;
+ pgoff_t size;
+ void *xip_mem;
+ unsigned long xip_pfn;
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;
+ int error;
+ /* XXX: are VM_FAULT_ codes OK? */
+again:
size = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
- if (pgoff >= size) {
- return NULL;
- }
+ if (vmf->pgoff >= size)
+ return VM_FAULT_SIGBUS;
- page = mapping->a_ops->get_xip_page(mapping, pgoff*(PAGE_SIZE/512), 0);
- if (!IS_ERR(page)) {
- goto out;
- }
- if (PTR_ERR(page) != -ENODATA)
- return NULL;
+ 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,
- pgoff*(PAGE_SIZE/512), 1);
- if (IS_ERR(page))
- return NULL;
- /* unmap page at pgoff from all other vmas */
- __xip_unmap(mapping, pgoff);
+ mutex_lock(&xip_sparse_mutex);
+ error = mapping->a_ops->get_xip_mem(mapping, vmf->pgoff, 1,
+ &xip_mem, &xip_pfn);
+ mutex_unlock(&xip_sparse_mutex);
+ if (error)
+ return VM_FAULT_SIGBUS;
+ /* 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 ZERO_PAGE() */
- page = ZERO_PAGE(address);
- }
+ int err, ret = VM_FAULT_OOM;
+
+ mutex_lock(&xip_sparse_mutex);
+ write_seqcount_begin(&xip_sparse_seq);
+ error = mapping->a_ops->get_xip_mem(mapping, vmf->pgoff, 0,
+ &xip_mem, &xip_pfn);
+ if (unlikely(!error)) {
+ write_seqcount_end(&xip_sparse_seq);
+ mutex_unlock(&xip_sparse_mutex);
+ goto again;
+ }
+ if (error != -ENODATA)
+ goto out;
+ /* not shared and writable, use xip_sparse_page() */
+ page = xip_sparse_page();
+ if (!page)
+ goto out;
+ err = vm_insert_page(vma, (unsigned long)vmf->virtual_address,
+ page);
+ if (err == -ENOMEM)
+ goto out;
+ ret = VM_FAULT_NOPAGE;
out:
- page_cache_get(page);
- return page;
+ write_seqcount_end(&xip_sparse_seq);
+ mutex_unlock(&xip_sparse_mutex);
+
+ return ret;
+ }
}
static struct vm_operations_struct xip_file_vm_ops = {
- .nopage = xip_file_nopage,
+ .fault = xip_file_fault,
};
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 | VM_MIXEDMAP;
return 0;
}
EXPORT_SYMBOL_GPL(xip_file_mmap);
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;
+ 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;
+ void *xip_mem;
+ unsigned long xip_pfn;
offset = (pos & (PAGE_CACHE_SIZE -1)); /* Within page */
index = pos >> PAGE_CACHE_SHIFT;
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)) {
+ 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))
+ mutex_lock(&xip_sparse_mutex);
+ status = a_ops->get_xip_mem(mapping, index, 1,
+ &xip_mem, &xip_pfn);
+ mutex_unlock(&xip_sparse_mutex);
+ 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;
- }
- copied = filemap_copy_from_user(page, offset, buf, bytes);
- flush_dcache_page(page);
+ copied = bytes -
+ __copy_from_user_nocache(xip_mem + offset, buf, bytes);
+
if (likely(copied > 0)) {
status = copied;
*ppos = pos;
/*
* No need to use i_size_read() here, the i_size
- * cannot change under us because we hold i_sem.
+ * cannot change under us because we hold i_mutex.
*/
if (pos > inode->i_size) {
i_size_write(inode, pos);
loff_t pos;
ssize_t ret;
- down(&inode->i_sem);
+ mutex_lock(&inode->i_mutex);
if (!access_ok(VERIFY_READ, buf, len)) {
ret=-EFAULT;
if (count == 0)
goto out_backing;
- ret = remove_suid(filp->f_dentry);
+ ret = file_remove_suid(filp);
if (ret)
goto out_backing;
- inode_update_time(inode, 1);
+ file_update_time(filp);
ret = __xip_file_write (filp, buf, count, pos, ppos);
out_backing:
current->backing_dev_info = NULL;
out_up:
- up(&inode->i_sem);
+ mutex_unlock(&inode->i_mutex);
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
+ * functionality is analog to block_truncate_page but does use get_xip_mem
* to get the page instead of page cache
*/
int
unsigned offset = from & (PAGE_CACHE_SIZE-1);
unsigned blocksize;
unsigned length;
- struct page *page;
- void *kaddr;
+ 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);
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;
}
- kaddr = kmap_atomic(page, KM_USER0);
- memset(kaddr + offset, 0, length);
- kunmap_atomic(kaddr, KM_USER0);
-
- flush_dcache_page(page);
+ memset(xip_mem + offset, 0, length);
return 0;
}
EXPORT_SYMBOL_GPL(xip_truncate_page);