static int gfs2_write_cache_jdata(struct address_space *mapping, struct writeback_control *wbc) { struct backing_dev_info *bdi = mapping->backing_dev_info; int ret = 0; int done = 0; struct pagevec pvec; int nr_pages; pgoff_t index; pgoff_t end; int scanned = 0; int range_whole = 0; if (wbc->nonblocking && bdi_write_congested(bdi)) { wbc->encountered_congestion = 1; return 0; } pagevec_init(&pvec, 0); if (wbc->range_cyclic) { index = mapping->writeback_index; /* Start from prev offset */ end = -1; } else { index = wbc->range_start >> PAGE_CACHE_SHIFT; end = wbc->range_end >> PAGE_CACHE_SHIFT; if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX) range_whole = 1; scanned = 1; } retry: while (!done && (index <= end) && (nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, PAGECACHE_TAG_DIRTY, min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1))) { scanned = 1; ret = gfs2_write_jdata_pagevec(mapping, wbc, &pvec, nr_pages, end); if (ret) done = 1; if (ret > 0) ret = 0; pagevec_release(&pvec); cond_resched(); } if (!scanned && !done) { /* * We hit the last page and there is more work to be done: wrap * back to the start of the file */ scanned = 1; index = 0; goto retry; } if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0)) mapping->writeback_index = index; return ret; }
/* * Attempt to release the private state associated with a page * - Called if either PG_private or PG_fscache is set on the page * - Caller holds page lock * - Return true (may release page) or false (may not) */ static int nfs_release_page(struct page *page, gfp_t gfp) { struct address_space *mapping = page->mapping; dfprintk(PAGECACHE, "NFS: release_page(%p)\n", page); /* Always try to initiate a 'commit' if relevant, but only * wait for it if __GFP_WAIT is set. Even then, only wait 1 * second and only if the 'bdi' is not congested. * Waiting indefinitely can cause deadlocks when the NFS * server is on this machine, when a new TCP connection is * needed and in other rare cases. There is no particular * need to wait extensively here. A short wait has the * benefit that someone else can worry about the freezer. */ if (mapping) { struct nfs_server *nfss = NFS_SERVER(mapping->host); nfs_commit_inode(mapping->host, 0); if ((gfp & __GFP_WAIT) && !bdi_write_congested(&nfss->backing_dev_info)) { wait_on_page_bit_killable_timeout(page, PG_private, HZ); if (PagePrivate(page)) set_bdi_congested(&nfss->backing_dev_info, BLK_RW_ASYNC); } } /* If PagePrivate() is set, then the page is not freeable */ if (PagePrivate(page)) return 0; return nfs_fscache_release_page(page, gfp); }
static int gfs2_write_jdata_pagevec(struct address_space *mapping, struct writeback_control *wbc, struct pagevec *pvec, int nr_pages, pgoff_t end) { struct inode *inode = mapping->host; struct gfs2_sbd *sdp = GFS2_SB(inode); loff_t i_size = i_size_read(inode); pgoff_t end_index = i_size >> PAGE_CACHE_SHIFT; unsigned offset = i_size & (PAGE_CACHE_SIZE-1); unsigned nrblocks = nr_pages * (PAGE_CACHE_SIZE/inode->i_sb->s_blocksize); struct backing_dev_info *bdi = mapping->backing_dev_info; int i; int ret; ret = gfs2_trans_begin(sdp, nrblocks, nrblocks); if (ret < 0) return ret; for(i = 0; i < nr_pages; i++) { struct page *page = pvec->pages[i]; lock_page(page); if (unlikely(page->mapping != mapping)) { unlock_page(page); continue; } if (!wbc->range_cyclic && page->index > end) { ret = 1; unlock_page(page); continue; } if (wbc->sync_mode != WB_SYNC_NONE) wait_on_page_writeback(page); if (PageWriteback(page) || !clear_page_dirty_for_io(page)) { unlock_page(page); continue; } /* Is the page fully outside i_size? (truncate in progress) */ if (page->index > end_index || (page->index == end_index && !offset)) { page->mapping->a_ops->invalidatepage(page, 0); unlock_page(page); continue; } ret = __gfs2_jdata_writepage(page, wbc); if (ret || (--(wbc->nr_to_write) <= 0)) ret = 1; if (wbc->nonblocking && bdi_write_congested(bdi)) { wbc->encountered_congestion = 1; ret = 1; } } gfs2_trans_end(sdp); return ret; }
/** * write_cache_pages - walk the list of dirty pages of the given address space and write all of them. * @mapping: address space structure to write * @wbc: subtract the number of written pages from *@wbc->nr_to_write * @writepage: function called for each page * @data: data passed to writepage function * * If a page is already under I/O, write_cache_pages() skips it, even * if it's dirty. This is desirable behaviour for memory-cleaning writeback, * but it is INCORRECT for data-integrity system calls such as fsync(). fsync() * and msync() need to guarantee that all the data which was dirty at the time * the call was made get new I/O started against them. If wbc->sync_mode is * WB_SYNC_ALL then we were called for data integrity and we must wait for * existing IO to complete. */ int write_cache_pages(struct address_space *mapping, struct writeback_control *wbc, writepage_t writepage, void *data) { struct backing_dev_info *bdi = mapping->backing_dev_info; int ret = 0; int done = 0; struct pagevec pvec; int nr_pages; pgoff_t uninitialized_var(writeback_index); pgoff_t index; pgoff_t end; /* Inclusive */ pgoff_t done_index; int cycled; int range_whole = 0; if (wbc->nonblocking && bdi_write_congested(bdi)) { wbc->encountered_congestion = 1; return 0; } pagevec_init(&pvec, 0); if (wbc->range_cyclic) { writeback_index = mapping->writeback_index; /* prev offset */ index = writeback_index; if (index == 0) cycled = 1; else cycled = 0; end = -1; } else { index = wbc->range_start >> PAGE_CACHE_SHIFT; end = wbc->range_end >> PAGE_CACHE_SHIFT; if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX) range_whole = 1; cycled = 1; /* ignore range_cyclic tests */ } retry: done_index = index; while (!done && (index <= end)) { int i; nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, PAGECACHE_TAG_DIRTY, min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1); if (nr_pages == 0) break; for (i = 0; i < nr_pages; i++) { struct page *page = pvec.pages[i]; /* * At this point, the page may be truncated or * invalidated (changing page->mapping to NULL), or * even swizzled back from swapper_space to tmpfs file * mapping. However, page->index will not change * because we have a reference on the page. */ if (page->index > end) { /* * can't be range_cyclic (1st pass) because * end == -1 in that case. */ done = 1; break; } done_index = page->index + 1; lock_page(page); /* * Page truncated or invalidated. We can freely skip it * then, even for data integrity operations: the page * has disappeared concurrently, so there could be no * real expectation of this data interity operation * even if there is now a new, dirty page at the same * pagecache address. */ if (unlikely(page->mapping != mapping)) { continue_unlock: unlock_page(page); continue; } if (!PageDirty(page)) { /* someone wrote it for us */ goto continue_unlock; } if (PageWriteback(page)) { if (wbc->sync_mode != WB_SYNC_NONE) wait_on_page_writeback(page); else goto continue_unlock; } BUG_ON(PageWriteback(page)); if (!clear_page_dirty_for_io(page)) goto continue_unlock; ret = (*writepage)(page, wbc, data); if (unlikely(ret)) { if (ret == AOP_WRITEPAGE_ACTIVATE) { unlock_page(page); ret = 0; } else { /* * done_index is set past this page, * so media errors will not choke * background writeout for the entire * file. This has consequences for * range_cyclic semantics (ie. it may * not be suitable for data integrity * writeout). */ done = 1; break; } } if (wbc->nr_to_write > 0) { wbc->nr_to_write--; if (wbc->nr_to_write == 0 && wbc->sync_mode == WB_SYNC_NONE) { /* * We stop writing back only if we are * not doing integrity sync. In case of * integrity sync we have to keep going * because someone may be concurrently * dirtying pages, and we might have * synced a lot of newly appeared dirty * pages, but have not synced all of the * old dirty pages. */ done = 1; break; } } if (wbc->nonblocking && bdi_write_congested(bdi)) { wbc->encountered_congestion = 1; done = 1; break; } } pagevec_release(&pvec); cond_resched(); } if (!cycled && !done) { /* * range_cyclic: * We hit the last page and there is more work to be done: wrap * back to the start of the file */ cycled = 1; index = 0; end = writeback_index - 1; goto retry; } if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0)) mapping->writeback_index = done_index; return ret; }
/** * write_cache_pages - walk the list of dirty pages of the given address space and write all of them. * @mapping: address space structure to write * @wbc: subtract the number of written pages from *@wbc->nr_to_write * @writepage: function called for each page * @data: data passed to writepage function * * If a page is already under I/O, write_cache_pages() skips it, even * if it's dirty. This is desirable behaviour for memory-cleaning writeback, * but it is INCORRECT for data-integrity system calls such as fsync(). fsync() * and msync() need to guarantee that all the data which was dirty at the time * the call was made get new I/O started against them. If wbc->sync_mode is * WB_SYNC_ALL then we were called for data integrity and we must wait for * existing IO to complete. */ int write_cache_pages(struct address_space *mapping, struct writeback_control *wbc, writepage_t writepage, void *data) { struct backing_dev_info *bdi = mapping->backing_dev_info; int ret = 0; int done = 0; struct pagevec pvec; int nr_pages; pgoff_t index; pgoff_t end; /* Inclusive */ int scanned = 0; int range_whole = 0; long nr_to_write = wbc->nr_to_write; if (wbc->nonblocking && bdi_write_congested(bdi)) { wbc->encountered_congestion = 1; return 0; } pagevec_init(&pvec, 0); if (wbc->range_cyclic) { index = mapping->writeback_index; /* Start from prev offset */ end = -1; } else { index = wbc->range_start >> PAGE_CACHE_SHIFT; end = wbc->range_end >> PAGE_CACHE_SHIFT; if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX) range_whole = 1; scanned = 1; } retry: while (!done && (index <= end) && (nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, PAGECACHE_TAG_DIRTY, min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1))) { unsigned i; scanned = 1; for (i = 0; i < nr_pages; i++) { struct page *page = pvec.pages[i]; /* * At this point we hold neither mapping->tree_lock nor * lock on the page itself: the page may be truncated or * invalidated (changing page->mapping to NULL), or even * swizzled back from swapper_space to tmpfs file * mapping */ lock_page(page); if (unlikely(page->mapping != mapping)) { unlock_page(page); continue; } if (!wbc->range_cyclic && page->index > end) { done = 1; unlock_page(page); continue; } if (wbc->sync_mode != WB_SYNC_NONE) wait_on_page_writeback(page); if (PageWriteback(page) || !clear_page_dirty_for_io(page)) { unlock_page(page); continue; } ret = (*writepage)(page, wbc, data); if (unlikely(ret == AOP_WRITEPAGE_ACTIVATE)) { unlock_page(page); ret = 0; } if (ret || (--nr_to_write <= 0)) done = 1; if (wbc->nonblocking && bdi_write_congested(bdi)) { wbc->encountered_congestion = 1; done = 1; } } pagevec_release(&pvec); cond_resched(); } if (!scanned && !done) { /* * We hit the last page and there is more work to be done: wrap * back to the start of the file */ scanned = 1; index = 0; goto retry; } if (!wbc->no_nrwrite_index_update) { if (wbc->range_cyclic || (range_whole && nr_to_write > 0)) mapping->writeback_index = index; wbc->nr_to_write = nr_to_write; } return ret; }