/*
* Clear a page's dirty flag, while caring for dirty memory accounting.
* Returns true if the page was previously dirty.
*
* This is for preparing to put the page under writeout. We leave the page
* tagged as dirty in the radix tree so that a concurrent write-for-sync
* can discover it via a PAGECACHE_TAG_DIRTY walk. The ->writepage
* implementation will run either set_page_writeback() or set_page_dirty(),
* at which stage we bring the page's dirty flag and radix-tree dirty tag
* back into sync.
*
* This incoherency between the page's dirty flag and radix-tree tag is
* unfortunate, but it only exists while the page is locked.
*/
static int tux3_clear_page_dirty_for_io(struct page *page)
{
if(DEBUG_MODE_K==1)
{
printf("\t\t\t\t%25s[K] %25s %4d #in\n",__FILE__,__func__,__LINE__);
}
struct address_space *mapping = page->mapping;
BUG_ON(!PageLocked(page));
if (mapping && mapping_cap_account_dirty(mapping)) {
/*
* Yes, Virginia, this is indeed insane.
*
* We use this sequence to make sure that
* (a) we account for dirty stats properly
* (b) we tell the low-level filesystem to
* mark the whole page dirty if it was
* dirty in a pagetable. Only to then
* (c) clean the page again and return 1 to
* cause the writeback.
*
* This way we avoid all nasty races with the
* dirty bit in multiple places and clearing
* them concurrently from different threads.
*
* Note! Normally the "set_page_dirty(page)"
* has no effect on the actual dirty bit - since
* that will already usually be set. But we
* need the side effects, and it can help us
* avoid races.
*
* We basically use the page "master dirty bit"
* as a serialization point for all the different
* threads doing their things.
*/
/* If PageForked(), don't touch PTE and don't dirty */
if (!PageForked(page) && page_mkclean(page))
set_page_dirty(page);
/*
* We carefully synchronise fault handlers against
* installing a dirty pte and marking the page dirty
* at this point. We do this by having them hold the
* page lock at some point after installing their
* pte, but before marking the page dirty.
* Pages are always locked coming in here, so we get
* the desired exclusion. See mm/memory.c:do_wp_page()
* for more comments.
*/
if (TestClearPageDirty(page)) {
dec_zone_page_state(page, NR_FILE_DIRTY);
dec_bdi_stat(mapping->backing_dev_info,
BDI_RECLAIMABLE);
return 1;
}
return 0;
}
return TestClearPageDirty(page);
}
static int
nfs_clear_request_commit(struct nfs_page *req)
{
struct page *page = req->wb_page;
if (test_and_clear_bit(PG_CLEAN, &(req)->wb_flags)) {
dec_zone_page_state(page, NR_UNSTABLE_NFS);
dec_bdi_stat(page->mapping->backing_dev_info, BDI_RECLAIMABLE);
return 1;
}
return 0;
}
/*
* This cancels just the dirty bit on the kernel page itself, it
* does NOT actually remove dirty bits on any mmap's that may be
* around. It also leaves the page tagged dirty, so any sync
* activity will still find it on the dirty lists, and in particular,
* clear_page_dirty_for_io() will still look at the dirty bits in
* the VM.
*
* Doing this should *normally* only ever be done when a page
* is truncated, and is not actually mapped anywhere at all. However,
* fs/buffer.c does this when it notices that somebody has cleaned
* out all the buffers on a page without actually doing it through
* the VM. Can you say "ext3 is horribly ugly"? Tought you could.
*/
void cancel_dirty_page(struct page *page, unsigned int account_size)
{
if (TestClearPageDirty(page)) {
struct address_space *mapping = page->mapping;
if (mapping && mapping_cap_account_dirty(mapping)) {
dec_zone_page_state(page, NR_FILE_DIRTY);
dec_bdi_stat(mapping->backing_dev_info,
BDI_RECLAIMABLE);
if (account_size)
task_io_account_cancelled_write(account_size);
}
}
}
void __delete_from_page_cache(struct page *page)
{
struct address_space *mapping = page->mapping;
if (PageUptodate(page) && PageMappedToDisk(page))
cleancache_put_page(page);
else
cleancache_invalidate_page(mapping, page);
radix_tree_delete(&mapping->page_tree, page->index);
page->mapping = NULL;
mapping->nrpages--;
__dec_zone_page_state(page, NR_FILE_PAGES);
if (PageSwapBacked(page))
__dec_zone_page_state(page, NR_SHMEM);
BUG_ON(page_mapped(page));
if (PageDirty(page) && mapping_cap_account_dirty(mapping)) {
dec_zone_page_state(page, NR_FILE_DIRTY);
dec_bdi_stat(mapping->backing_dev_info, BDI_RECLAIMABLE);
}
}
/*
* Set up the argument/result storage required for the RPC call.
*/
static int nfs_commit_rpcsetup(struct list_head *head,
struct nfs_write_data *data,
int how)
{
struct nfs_page *first = nfs_list_entry(head->next);
struct inode *inode = first->wb_context->path.dentry->d_inode;
int flags = (how & FLUSH_SYNC) ? 0 : RPC_TASK_ASYNC;
int priority = flush_task_priority(how);
struct rpc_task *task;
struct rpc_message msg = {
.rpc_argp = &data->args,
.rpc_resp = &data->res,
.rpc_cred = first->wb_context->cred,
};
struct rpc_task_setup task_setup_data = {
.task = &data->task,
.rpc_client = NFS_CLIENT(inode),
.rpc_message = &msg,
.callback_ops = &nfs_commit_ops,
.callback_data = data,
.workqueue = nfsiod_workqueue,
.flags = flags,
.priority = priority,
};
/* Set up the RPC argument and reply structs
* NB: take care not to mess about with data->commit et al. */
list_splice_init(head, &data->pages);
data->inode = inode;
data->cred = msg.rpc_cred;
data->args.fh = NFS_FH(data->inode);
/* Note: we always request a commit of the entire inode */
data->args.offset = 0;
data->args.count = 0;
data->args.context = get_nfs_open_context(first->wb_context);
data->res.count = 0;
data->res.fattr = &data->fattr;
data->res.verf = &data->verf;
nfs_fattr_init(&data->fattr);
/* Set up the initial task struct. */
NFS_PROTO(inode)->commit_setup(data, &msg);
dprintk("NFS: %5u initiated commit call\n", data->task.tk_pid);
task = rpc_run_task(&task_setup_data);
if (IS_ERR(task))
return PTR_ERR(task);
rpc_put_task(task);
return 0;
}
/*
* Commit dirty pages
*/
static int
nfs_commit_list(struct inode *inode, struct list_head *head, int how)
{
struct nfs_write_data *data;
struct nfs_page *req;
data = nfs_commitdata_alloc();
if (!data)
goto out_bad;
/* Set up the argument struct */
return nfs_commit_rpcsetup(head, data, how);
out_bad:
while (!list_empty(head)) {
req = nfs_list_entry(head->next);
nfs_list_remove_request(req);
nfs_mark_request_commit(req);
dec_zone_page_state(req->wb_page, NR_UNSTABLE_NFS);
dec_bdi_stat(req->wb_page->mapping->backing_dev_info,
BDI_RECLAIMABLE);
nfs_clear_page_tag_locked(req);
}
return -ENOMEM;
}
/*
* COMMIT call returned
*/
static void nfs_commit_done(struct rpc_task *task, void *calldata)
{
struct nfs_write_data *data = calldata;
dprintk("NFS: %5u nfs_commit_done (status %d)\n",
task->tk_pid, task->tk_status);
/* Call the NFS version-specific code */
if (NFS_PROTO(data->inode)->commit_done(task, data) != 0)
return;
}
static void nfs_commit_release(void *calldata)
{
struct nfs_write_data *data = calldata;
struct nfs_page *req;
int status = data->task.tk_status;
while (!list_empty(&data->pages)) {
req = nfs_list_entry(data->pages.next);
nfs_list_remove_request(req);
nfs_clear_request_commit(req);
dprintk("NFS: commit (%s/%lld %d@%lld)",
req->wb_context->path.dentry->d_inode->i_sb->s_id,
(long long)NFS_FILEID(req->wb_context->path.dentry->d_inode),
req->wb_bytes,
(long long)req_offset(req));
if (status < 0) {
nfs_context_set_write_error(req->wb_context, status);
nfs_inode_remove_request(req);
dprintk(", error = %d\n", status);
goto next;
}
/* Okay, COMMIT succeeded, apparently. Check the verifier
* returned by the server against all stored verfs. */
if (!memcmp(req->wb_verf.verifier, data->verf.verifier, sizeof(data->verf.verifier))) {
/* We have a match */
nfs_inode_remove_request(req);
dprintk(" OK\n");
goto next;
}
/* We have a mismatch. Write the page again */
dprintk(" mismatch\n");
nfs_mark_request_dirty(req);
next:
nfs_clear_page_tag_locked(req);
}
nfs_commitdata_release(calldata);
}
static const struct rpc_call_ops nfs_commit_ops = {
#if defined(CONFIG_NFS_V4_1)
.rpc_call_prepare = nfs_write_prepare,
#endif /* CONFIG_NFS_V4_1 */
.rpc_call_done = nfs_commit_done,
.rpc_release = nfs_commit_release,
};
int nfs_commit_inode(struct inode *inode, int how)
{
LIST_HEAD(head);
int res;
spin_lock(&inode->i_lock);
res = nfs_scan_commit(inode, &head, 0, 0);
spin_unlock(&inode->i_lock);
if (res) {
int error = nfs_commit_list(inode, &head, how);
if (error < 0)
return error;
}
return res;
}
#else
static inline int nfs_commit_list(struct inode *inode, struct list_head *head, int how)
{
return 0;
}
#endif
long nfs_sync_mapping_wait(struct address_space *mapping, struct writeback_control *wbc, int how)
{
struct inode *inode = mapping->host;
pgoff_t idx_start, idx_end;
unsigned int npages = 0;
LIST_HEAD(head);
int nocommit = how & FLUSH_NOCOMMIT;
long pages, ret;
/* FIXME */
if (wbc->range_cyclic)
idx_start = 0;
else {
idx_start = wbc->range_start >> PAGE_CACHE_SHIFT;
idx_end = wbc->range_end >> PAGE_CACHE_SHIFT;
if (idx_end > idx_start) {
pgoff_t l_npages = 1 + idx_end - idx_start;
npages = l_npages;
if (sizeof(npages) != sizeof(l_npages) &&
(pgoff_t)npages != l_npages)
npages = 0;
}
}
how &= ~FLUSH_NOCOMMIT;
spin_lock(&inode->i_lock);
do {
ret = nfs_wait_on_requests_locked(inode, idx_start, npages);
if (ret != 0)
continue;
if (nocommit)
break;
pages = nfs_scan_commit(inode, &head, idx_start, npages);
if (pages == 0)
break;
if (how & FLUSH_INVALIDATE) {
spin_unlock(&inode->i_lock);
nfs_cancel_commit_list(&head);
ret = pages;
spin_lock(&inode->i_lock);
continue;
}
pages += nfs_scan_commit(inode, &head, 0, 0);
spin_unlock(&inode->i_lock);
ret = nfs_commit_list(inode, &head, how);
spin_lock(&inode->i_lock);
} while (ret >= 0);
spin_unlock(&inode->i_lock);
return ret;
}
static int __nfs_write_mapping(struct address_space *mapping, struct writeback_control *wbc, int how)
{
int ret;
ret = nfs_writepages(mapping, wbc);
if (ret < 0)
goto out;
ret = nfs_sync_mapping_wait(mapping, wbc, how);
if (ret < 0)
goto out;
return 0;
out:
__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
return ret;
}