#include <linux/mm.h>
#include <linux/pagemap.h>
#include <linux/writeback.h> /* generic_writepages */
+#include <linux/slab.h>
#include <linux/pagevec.h>
#include <linux/task_io_accounting_ops.h>
*/
static void ceph_invalidatepage(struct page *page, unsigned long offset)
{
- struct inode *inode = page->mapping->host;
+ struct inode *inode;
struct ceph_inode_info *ci;
struct ceph_snap_context *snapc = (void *)page->private;
BUG_ON(!PagePrivate(page));
BUG_ON(!page->mapping);
+ inode = page->mapping->host;
+
/*
* We can get non-dirty pages here due to races between
* set_page_dirty and truncate_complete_page; just spit out a
struct ceph_osd_op *op;
struct ceph_inode_info *ci = ceph_inode(inode);
unsigned wrote;
- loff_t offset = req->r_pages[0]->index << PAGE_CACHE_SHIFT;
struct page *page;
int i;
struct ceph_snap_context *snapc = req->r_snapc;
u64 bytes = 0;
struct ceph_client *client = ceph_inode_to_client(inode);
long writeback_stat;
+ unsigned issued = __ceph_caps_issued(ci, NULL);
/* parse reply */
replyhead = msg->front.iov_base;
bytes = le64_to_cpu(op->extent.length);
if (rc >= 0) {
- wrote = (bytes + (offset & ~PAGE_CACHE_MASK) + ~PAGE_CACHE_MASK)
- >> PAGE_CACHE_SHIFT;
- WARN_ON(wrote != req->r_num_pages);
+ /*
+ * Assume we wrote the pages we originally sent. The
+ * osd might reply with fewer pages if our writeback
+ * raced with a truncation and was adjusted at the osd,
+ * so don't believe the reply.
+ */
+ wrote = req->r_num_pages;
} else {
wrote = 0;
mapping_set_error(mapping, rc);
ceph_put_snap_context(snapc);
dout("unlocking %d %p\n", i, page);
end_page_writeback(page);
+
+ /*
+ * We lost the cache cap, need to truncate the page before
+ * it is unlocked, otherwise we'd truncate it later in the
+ * page truncation thread, possibly losing some data that
+ * raced its way in
+ */
+ if ((issued & CEPH_CAP_FILE_CACHE) == 0)
+ generic_error_remove_page(inode->i_mapping, page);
+
unlock_page(page);
}
dout("%p wrote+cleaned %d pages\n", inode, wrote);
struct inode *inode = mapping->host;
struct backing_dev_info *bdi = mapping->backing_dev_info;
struct ceph_inode_info *ci = ceph_inode(inode);
- struct ceph_client *client = ceph_inode_to_client(inode);
+ struct ceph_client *client;
pgoff_t index, start, end;
int range_whole = 0;
int should_loop = 1;
/*
* We are only allowed to write into/dirty the page if the page is
* clean, or already dirty within the same snap context.
+ *
+ * called with page locked.
+ * return success with page locked,
+ * or any failure (incl -EAGAIN) with page unlocked.
*/
-static int ceph_write_begin(struct file *file, struct address_space *mapping,
- loff_t pos, unsigned len, unsigned flags,
- struct page **pagep, void **fsdata)
+static int ceph_update_writeable_page(struct file *file,
+ loff_t pos, unsigned len,
+ struct page *page)
{
struct inode *inode = file->f_dentry->d_inode;
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_mds_client *mdsc = &ceph_inode_to_client(inode)->mdsc;
- struct page *page;
- pgoff_t index = pos >> PAGE_CACHE_SHIFT;
loff_t page_off = pos & PAGE_CACHE_MASK;
int pos_in_page = pos & ~PAGE_CACHE_MASK;
int end_in_page = pos_in_page + len;
struct ceph_snap_context *snapc;
int r;
- /* get a page*/
-retry:
- page = grab_cache_page_write_begin(mapping, index, 0);
- if (!page)
- return -ENOMEM;
- *pagep = page;
-
- dout("write_begin file %p inode %p page %p %d~%d\n", file,
- inode, page, (int)pos, (int)len);
-
retry_locked:
/* writepages currently holds page lock, but if we change that later, */
wait_on_page_writeback(page);
*/
snapc = ceph_get_snap_context((void *)page->private);
unlock_page(page);
- if (ceph_queue_writeback(inode))
- igrab(inode);
- wait_event_interruptible(ci->i_cap_wq,
+ ceph_queue_writeback(inode);
+ r = wait_event_interruptible(ci->i_cap_wq,
context_is_writeable_or_written(inode, snapc));
ceph_put_snap_context(snapc);
- goto retry;
+ if (r == -ERESTARTSYS)
+ return r;
+ return -EAGAIN;
}
/* yay, writeable, do it now (without dropping page lock) */
}
/*
+ * We are only allowed to write into/dirty the page if the page is
+ * clean, or already dirty within the same snap context.
+ */
+static int ceph_write_begin(struct file *file, struct address_space *mapping,
+ loff_t pos, unsigned len, unsigned flags,
+ struct page **pagep, void **fsdata)
+{
+ struct inode *inode = file->f_dentry->d_inode;
+ struct page *page;
+ pgoff_t index = pos >> PAGE_CACHE_SHIFT;
+ int r;
+
+ do {
+ /* get a page */
+ page = grab_cache_page_write_begin(mapping, index, 0);
+ if (!page)
+ return -ENOMEM;
+ *pagep = page;
+
+ dout("write_begin file %p inode %p page %p %d~%d\n", file,
+ inode, page, (int)pos, (int)len);
+
+ r = ceph_update_writeable_page(file, pos, len, page);
+ } while (r == -EAGAIN);
+
+ return r;
+}
+
+/*
* we don't do anything in here that simple_write_end doesn't do
* except adjust dirty page accounting and drop read lock on
* mdsc->snap_rwsem.
struct ceph_mds_client *mdsc = &ceph_inode_to_client(inode)->mdsc;
loff_t off = page->index << PAGE_CACHE_SHIFT;
loff_t size, len;
- struct page *locked_page = NULL;
- void *fsdata = NULL;
int ret;
size = i_size_read(inode);
dout("page_mkwrite %p %llu~%llu page %p idx %lu\n", inode,
off, len, page, page->index);
- ret = ceph_write_begin(vma->vm_file, inode->i_mapping, off, len, 0,
- &locked_page, &fsdata);
- WARN_ON(page != locked_page);
- if (!ret) {
- /*
- * doing the following, instead of calling
- * ceph_write_end. Note that we keep the
- * page locked
- */
+
+ lock_page(page);
+
+ ret = VM_FAULT_NOPAGE;
+ if ((off > size) ||
+ (page->mapping != inode->i_mapping))
+ goto out;
+
+ ret = ceph_update_writeable_page(vma->vm_file, off, len, page);
+ if (ret == 0) {
+ /* success. we'll keep the page locked. */
set_page_dirty(page);
up_read(&mdsc->snap_rwsem);
- page_cache_release(page);
ret = VM_FAULT_LOCKED;
} else {
- ret = VM_FAULT_SIGBUS;
+ if (ret == -ENOMEM)
+ ret = VM_FAULT_OOM;
+ else
+ ret = VM_FAULT_SIGBUS;
}
+out:
dout("page_mkwrite %p %llu~%llu = %d\n", inode, off, len, ret);
+ if (ret != VM_FAULT_LOCKED)
+ unlock_page(page);
return ret;
}
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff