* Copyright (C) 2006 Jaya Kumar
*
* This file is subject to the terms and conditions of the GNU General Public
- * License. See the file COPYING in the main directory of this archive
+ * License. See the file COPYING in the main directory of this archive
* for more details.
*/
#include <linux/errno.h>
#include <linux/string.h>
#include <linux/mm.h>
-#include <linux/slab.h>
#include <linux/vmalloc.h>
#include <linux/delay.h>
#include <linux/interrupt.h>
#include <linux/fb.h>
#include <linux/list.h>
-#include <asm/uaccess.h>
/* to support deferred IO */
#include <linux/rmap.h>
#include <linux/pagemap.h>
+struct page *fb_deferred_io_page(struct fb_info *info, unsigned long offs)
+{
+ void *screen_base = (void __force *) info->screen_base;
+ struct page *page;
+
+ if (is_vmalloc_addr(screen_base + offs))
+ page = vmalloc_to_page(screen_base + offs);
+ else
+ page = pfn_to_page((info->fix.smem_start + offs) >> PAGE_SHIFT);
+
+ return page;
+}
+
/* this is to find and return the vmalloc-ed fb pages */
-static struct page* fb_deferred_io_nopage(struct vm_area_struct *vma,
- unsigned long vaddr, int *type)
+static int fb_deferred_io_fault(struct vm_area_struct *vma,
+ struct vm_fault *vmf)
{
unsigned long offset;
struct page *page;
struct fb_info *info = vma->vm_private_data;
- offset = (vaddr - vma->vm_start) + (vma->vm_pgoff << PAGE_SHIFT);
+ offset = vmf->pgoff << PAGE_SHIFT;
if (offset >= info->fix.smem_len)
- return NOPAGE_SIGBUS;
+ return VM_FAULT_SIGBUS;
- page = vmalloc_to_page(info->screen_base + offset);
+ page = fb_deferred_io_page(info, offset);
if (!page)
- return NOPAGE_OOM;
+ return VM_FAULT_SIGBUS;
get_page(page);
- if (type)
- *type = VM_FAULT_MINOR;
- return page;
+
+ if (vma->vm_file)
+ page->mapping = vma->vm_file->f_mapping;
+ else
+ printk(KERN_ERR "no mapping available\n");
+
+ BUG_ON(!page->mapping);
+ page->index = vmf->pgoff;
+
+ vmf->page = page;
+ return 0;
}
+int fb_deferred_io_fsync(struct file *file, int datasync)
+{
+ struct fb_info *info = file->private_data;
+
+ /* Skip if deferred io is compiled-in but disabled on this fbdev */
+ if (!info->fbdefio)
+ return 0;
+
+ /* Kill off the delayed work */
+ cancel_rearming_delayed_work(&info->deferred_work);
+
+ /* Run it immediately */
+ return schedule_delayed_work(&info->deferred_work, 0);
+}
+EXPORT_SYMBOL_GPL(fb_deferred_io_fsync);
+
/* vm_ops->page_mkwrite handler */
-int fb_deferred_io_mkwrite(struct vm_area_struct *vma,
- struct page *page)
+static int fb_deferred_io_mkwrite(struct vm_area_struct *vma,
+ struct vm_fault *vmf)
{
+ struct page *page = vmf->page;
struct fb_info *info = vma->vm_private_data;
struct fb_deferred_io *fbdefio = info->fbdefio;
+ struct page *cur;
/* this is a callback we get when userspace first tries to
write to the page. we schedule a workqueue. that workqueue
/* protect against the workqueue changing the page list */
mutex_lock(&fbdefio->lock);
- list_add(&page->lru, &fbdefio->pagelist);
+
+ /* we loop through the pagelist before adding in order
+ to keep the pagelist sorted */
+ list_for_each_entry(cur, &fbdefio->pagelist, lru) {
+ /* this check is to catch the case where a new
+ process could start writing to the same page
+ through a new pte. this new access can cause the
+ mkwrite even when the original ps's pte is marked
+ writable */
+ if (unlikely(cur == page))
+ goto page_already_added;
+ else if (cur->index > page->index)
+ break;
+ }
+
+ list_add_tail(&page->lru, &cur->lru);
+
+page_already_added:
mutex_unlock(&fbdefio->lock);
/* come back after delay to process the deferred IO */
return 0;
}
-static struct vm_operations_struct fb_deferred_io_vm_ops = {
- .nopage = fb_deferred_io_nopage,
+static const struct vm_operations_struct fb_deferred_io_vm_ops = {
+ .fault = fb_deferred_io_fault,
.page_mkwrite = fb_deferred_io_mkwrite,
};
+static int fb_deferred_io_set_page_dirty(struct page *page)
+{
+ if (!PageDirty(page))
+ SetPageDirty(page);
+ return 0;
+}
+
+static const struct address_space_operations fb_deferred_io_aops = {
+ .set_page_dirty = fb_deferred_io_set_page_dirty,
+};
+
static int fb_deferred_io_mmap(struct fb_info *info, struct vm_area_struct *vma)
{
vma->vm_ops = &fb_deferred_io_vm_ops;
- vma->vm_flags |= ( VM_IO | VM_RESERVED | VM_DONTEXPAND );
+ vma->vm_flags |= ( VM_RESERVED | VM_DONTEXPAND );
+ if (!(info->flags & FBINFO_VIRTFB))
+ vma->vm_flags |= VM_IO;
vma->vm_private_data = info;
return 0;
}
{
struct fb_info *info = container_of(work, struct fb_info,
deferred_work.work);
- struct list_head *node, *next;
- struct page *cur;
struct fb_deferred_io *fbdefio = info->fbdefio;
+ struct page *page, *tmp_page;
+ struct list_head *node, *tmp_node;
+ struct list_head non_dirty;
+
+ INIT_LIST_HEAD(&non_dirty);
/* here we mkclean the pages, then do all deferred IO */
mutex_lock(&fbdefio->lock);
- list_for_each_entry(cur, &fbdefio->pagelist, lru) {
- lock_page(cur);
- page_mkclean(cur);
- unlock_page(cur);
+ list_for_each_entry_safe(page, tmp_page, &fbdefio->pagelist, lru) {
+ lock_page(page);
+ /*
+ * The workqueue callback can be triggered after a
+ * ->page_mkwrite() call but before the PTE has been marked
+ * dirty. In this case page_mkclean() won't "rearm" the page.
+ *
+ * To avoid this, remove those "non-dirty" pages from the
+ * pagelist before calling the driver's callback, then add
+ * them back to get processed on the next work iteration.
+ * At that time, their PTEs will hopefully be dirty for real.
+ */
+ if (!page_mkclean(page))
+ list_move_tail(&page->lru, &non_dirty);
+ unlock_page(page);
}
/* driver's callback with pagelist */
fbdefio->deferred_io(info, &fbdefio->pagelist);
- /* clear the list */
- list_for_each_safe(node, next, &fbdefio->pagelist) {
+ /* clear the list... */
+ list_for_each_safe(node, tmp_node, &fbdefio->pagelist) {
list_del(node);
}
+ /* ... and add back the "non-dirty" pages to the list */
+ list_splice_tail(&non_dirty, &fbdefio->pagelist);
mutex_unlock(&fbdefio->lock);
}
}
EXPORT_SYMBOL_GPL(fb_deferred_io_init);
+void fb_deferred_io_open(struct fb_info *info,
+ struct inode *inode,
+ struct file *file)
+{
+ file->f_mapping->a_ops = &fb_deferred_io_aops;
+}
+EXPORT_SYMBOL_GPL(fb_deferred_io_open);
+
void fb_deferred_io_cleanup(struct fb_info *info)
{
struct fb_deferred_io *fbdefio = info->fbdefio;
+ struct list_head *node, *tmp_node;
+ struct page *page;
+ int i;
BUG_ON(!fbdefio);
cancel_delayed_work(&info->deferred_work);
flush_scheduled_work();
+
+ /* the list may have still some non-dirty pages at this point */
+ mutex_lock(&fbdefio->lock);
+ list_for_each_safe(node, tmp_node, &fbdefio->pagelist) {
+ list_del(node);
+ }
+ mutex_unlock(&fbdefio->lock);
+
+ /* clear out the mapping that we setup */
+ for (i = 0 ; i < info->fix.smem_len; i += PAGE_SIZE) {
+ page = fb_deferred_io_page(info, i);
+ page->mapping = NULL;
+ }
+
+ info->fbops->fb_mmap = NULL;
+ mutex_destroy(&fbdefio->lock);
}
EXPORT_SYMBOL_GPL(fb_deferred_io_cleanup);