ceph: adapt ceph to the fscache rewrite

index e53c8541f5b2..0ffc4c8d7c10 100644
@@ -126,7 +126,7 @@ static int ceph_set_page_dirty(struct page *page)
 	BUG_ON(PagePrivate(page));
 	attach_page_private(page, snapc);
 
-	return __set_page_dirty_nobuffers(page);
+	return ceph_fscache_set_page_dirty(page);
 }
 
 /*

@@ -141,8 +141,6 @@ static void ceph_invalidatepage(struct page *page, unsigned int offset,
 	struct ceph_inode_info *ci;
 	struct ceph_snap_context *snapc;
 
-	wait_on_page_fscache(page);
-
 	inode = page->mapping->host;
 	ci = ceph_inode(inode);
 

@@ -153,28 +151,36 @@ static void ceph_invalidatepage(struct page *page, unsigned int offset,
 	}
 
 	WARN_ON(!PageLocked(page));
-	if (!PagePrivate(page))
-		return;
+	if (PagePrivate(page)) {
+		dout("%p invalidatepage %p idx %lu full dirty page\n",
+		     inode, page, page->index);
 
-	dout("%p invalidatepage %p idx %lu full dirty page\n",
-	     inode, page, page->index);
+		snapc = detach_page_private(page);
+		ceph_put_wrbuffer_cap_refs(ci, 1, snapc);
+		ceph_put_snap_context(snapc);
+	}
 
-	snapc = detach_page_private(page);
-	ceph_put_wrbuffer_cap_refs(ci, 1, snapc);
-	ceph_put_snap_context(snapc);
+	wait_on_page_fscache(page);
 }
 
 static int ceph_releasepage(struct page *page, gfp_t gfp)
 {
-	dout("%p releasepage %p idx %lu (%sdirty)\n", page->mapping->host,
-	     page, page->index, PageDirty(page) ? "" : "not ");
+	struct inode *inode = page->mapping->host;
+
+	dout("%llx:%llx releasepage %p idx %lu (%sdirty)\n",
+	     ceph_vinop(inode), page,
+	     page->index, PageDirty(page) ? "" : "not ");
+
+	if (PagePrivate(page))
+		return 0;
 
 	if (PageFsCache(page)) {
-		if (!(gfp & __GFP_DIRECT_RECLAIM) || !(gfp & __GFP_FS))
+		if (!gfpflags_allow_blocking(gfp) || !(gfp & __GFP_FS))
 			return 0;
 		wait_on_page_fscache(page);
 	}
-	return !PagePrivate(page);
+	ceph_fscache_note_page_release(inode);
+	return 1;
 }
 
 static void ceph_netfs_expand_readahead(struct netfs_read_request *rreq)

258 lines not on this page · raw message

158 lines not on this page · raw message

index b9460b6fb76f..0bc0e6c157df 100644
@@ -1856,7 +1856,7 @@ static int try_nonblocking_invalidate(struct inode *inode)
 	u32 invalidating_gen = ci->i_rdcache_gen;
 
 	spin_unlock(&ci->i_ceph_lock);
-	ceph_fscache_invalidate(inode);
+	ceph_fscache_invalidate(inode, false);
 	invalidate_mapping_pages(&inode->i_data, 0, -1);
 	spin_lock(&ci->i_ceph_lock);
 

@@ -2388,6 +2388,7 @@ int ceph_write_inode(struct inode *inode, struct writeback_control *wbc)
 	int wait = (wbc->sync_mode == WB_SYNC_ALL && !wbc->for_sync);
 
 	dout("write_inode %p wait=%d\n", inode, wait);
+	ceph_fscache_unpin_writeback(inode, wbc);
 	if (wait) {
 		dirty = try_flush_caps(inode, &flush_tid);
 		if (dirty)

index 02a0a0fd9ccd..bf1017682d09 100644
@@ -248,8 +248,7 @@ static int ceph_init_file(struct inode *inode, struct file *file, int fmode)
 
 	switch (inode->i_mode & S_IFMT) {
 	case S_IFREG:
-		ceph_fscache_register_inode_cookie(inode);
-		ceph_fscache_file_set_cookie(inode, file);
+		ceph_fscache_use_cookie(inode, file->f_mode & FMODE_WRITE);
 		fallthrough;
 	case S_IFDIR:
 		ret = ceph_init_file_info(inode, file, fmode,

@@ -810,6 +809,7 @@ int ceph_release(struct inode *inode, struct file *file)
 		dout("release inode %p regular file %p\n", inode, file);
 		WARN_ON(!list_empty(&fi->rw_contexts));
 
+		ceph_fscache_unuse_cookie(inode, file->f_mode & FMODE_WRITE);
 		ceph_put_fmode(ci, fi->fmode, 1);
 
 		kmem_cache_free(ceph_file_cachep, fi);

@@ -1206,7 +1206,11 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
 	     snapc, snapc ? snapc->seq : 0);
 
 	if (write) {
-		int ret2 = invalidate_inode_pages2_range(inode->i_mapping,
+		int ret2;
+
+		ceph_fscache_invalidate(inode, true);
+
+		ret2 = invalidate_inode_pages2_range(inode->i_mapping,
 					pos >> PAGE_SHIFT,
 					(pos + count - 1) >> PAGE_SHIFT);
 		if (ret2 < 0)

@@ -1417,6 +1421,7 @@ ceph_sync_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos,
 	if (ret < 0)
 		return ret;
 
+	ceph_fscache_invalidate(inode, false);
 	ret = invalidate_inode_pages2_range(inode->i_mapping,
 					    pos >> PAGE_SHIFT,
 					    (pos + count - 1) >> PAGE_SHIFT);

@@ -2101,6 +2106,7 @@ static long ceph_fallocate(struct file *file, int mode,
 		goto unlock;
 
 	filemap_invalidate_lock(inode->i_mapping);
+	ceph_fscache_invalidate(inode, false);
 	ceph_zero_pagecache_range(inode, offset, length);
 	ret = ceph_zero_objects(inode, offset, length);
 

@@ -2425,6 +2431,7 @@ static ssize_t __ceph_copy_file_range(struct file *src_file, loff_t src_off,
 		goto out_caps;
 
 	/* Drop dst file cached pages */
+	ceph_fscache_invalidate(dst_inode, false);
 	ret = invalidate_inode_pages2_range(dst_inode->i_mapping,
 					    dst_off >> PAGE_SHIFT,
 					    (dst_off + len) >> PAGE_SHIFT);

index e3322fcb2e8d..ef4a980a7bf3 100644
@@ -564,6 +564,8 @@ void ceph_evict_inode(struct inode *inode)
 	percpu_counter_dec(&mdsc->metric.total_inodes);
 
 	truncate_inode_pages_final(&inode->i_data);
+	if (inode->i_state & I_PINNING_FSCACHE_WB)
+		ceph_fscache_unuse_cookie(inode, true);
 	clear_inode(inode);
 
 	ceph_fscache_unregister_inode_cookie(ci);

@@ -634,6 +636,12 @@ int ceph_fill_file_size(struct inode *inode, int issued,
 		}
 		i_size_write(inode, size);
 		inode->i_blocks = calc_inode_blocks(size);
+		/*
+		 * If we're expanding, then we should be able to just update
+		 * the existing cookie.
+		 */
+		if (size > isize)
+			ceph_fscache_update(inode);
 		ci->i_reported_size = size;
 		if (truncate_seq != ci->i_truncate_seq) {
 			dout("truncate_seq %u -> %u\n",

@@ -666,10 +674,6 @@ int ceph_fill_file_size(struct inode *inode, int issued,
 		     truncate_size);
 		ci->i_truncate_size = truncate_size;
 	}
-
-	if (queue_trunc)
-		ceph_fscache_invalidate(inode);
-
 	return queue_trunc;
 }
 

@@ -1053,6 +1057,8 @@ int ceph_fill_inode(struct inode *inode, struct page *locked_page,
 
 	spin_unlock(&ci->i_ceph_lock);
 
+	ceph_fscache_register_inode_cookie(inode);
+
 	if (fill_inline)
 		ceph_fill_inline_data(inode, locked_page,
 				      iinfo->inline_data, iinfo->inline_len);

@@ -1814,11 +1820,13 @@ bool ceph_inode_set_size(struct inode *inode, loff_t size)
 	spin_lock(&ci->i_ceph_lock);
 	dout("set_size %p %llu -> %llu\n", inode, i_size_read(inode), size);
 	i_size_write(inode, size);
+	ceph_fscache_update(inode);
 	inode->i_blocks = calc_inode_blocks(size);
 
 	ret = __ceph_should_report_size(ci);
 
 	spin_unlock(&ci->i_ceph_lock);
+
 	return ret;
 }
 

@@ -1844,6 +1852,8 @@ static void ceph_do_invalidate_pages(struct inode *inode)
 	u32 orig_gen;
 	int check = 0;
 
+	ceph_fscache_invalidate(inode, false);
+
 	mutex_lock(&ci->i_truncate_mutex);
 
 	if (ceph_inode_is_shutdown(inode)) {

@@ -1868,7 +1878,7 @@ static void ceph_do_invalidate_pages(struct inode *inode)
 	orig_gen = ci->i_rdcache_gen;
 	spin_unlock(&ci->i_ceph_lock);
 
-	ceph_fscache_invalidate(inode);
+	ceph_fscache_invalidate(inode, false);
 	if (invalidate_inode_pages2(inode->i_mapping) < 0) {
 		pr_err("invalidate_inode_pages2 %llx.%llx failed\n",
 		       ceph_vinop(inode));

@@ -1937,6 +1947,7 @@ void __ceph_do_pending_vmtruncate(struct inode *inode)
 	     ci->i_truncate_pending, to);
 	spin_unlock(&ci->i_ceph_lock);
 
+	ceph_fscache_resize(inode, to);
 	truncate_pagecache(inode, to);
 
 	spin_lock(&ci->i_ceph_lock);

@@ -2184,7 +2195,6 @@ int __ceph_setattr(struct inode *inode, struct iattr *attr)
 	if (inode_dirty_flags)
 		__mark_inode_dirty(inode, inode_dirty_flags);
 
-
 	if (mask) {
 		req->r_inode = inode;
 		ihold(inode);

index bab61232dc5a..bea89bdb534a 100644
@@ -787,16 +787,10 @@ static int __init init_caches(void)
 	if (!ceph_wb_pagevec_pool)
 		goto bad_pagevec_pool;
 
-	error = ceph_fscache_register();
-	if (error)
-		goto bad_fscache;
-
 	return 0;
 
-bad_fscache:
-	kmem_cache_destroy(ceph_mds_request_cachep);
 bad_pagevec_pool:
-	mempool_destroy(ceph_wb_pagevec_pool);
+	kmem_cache_destroy(ceph_mds_request_cachep);
 bad_mds_req:
 	kmem_cache_destroy(ceph_dir_file_cachep);
 bad_dir_file:

@@ -828,8 +822,6 @@ static void destroy_caches(void)
 	kmem_cache_destroy(ceph_dir_file_cachep);
 	kmem_cache_destroy(ceph_mds_request_cachep);
 	mempool_destroy(ceph_wb_pagevec_pool);
-
-	ceph_fscache_unregister();
 }
 
 static void __ceph_umount_begin(struct ceph_fs_client *fsc)

index ac331aa07cfa..d0142cc5c41b 100644
@@ -21,7 +21,6 @@
 #include <linux/ceph/libceph.h>
 
 #ifdef CONFIG_CEPH_FSCACHE
-#define FSCACHE_USE_NEW_IO_API
 #include <linux/fscache.h>
 #endif
 

@@ -135,7 +134,7 @@ struct ceph_fs_client {
 #endif
 
 #ifdef CONFIG_CEPH_FSCACHE
-	struct fscache_cookie *fscache;
+	struct fscache_volume *fscache;
 #endif
 };
 

index 0ffc4c8d7c10..e836f8f1d4f8 100644
@@ -5,7 +5,6 @@
 #include <linux/fs.h>
 #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>

@@ -384,6 +383,38 @@ static void ceph_readahead(struct readahead_control *ractl)
 	netfs_readahead(ractl, &ceph_netfs_read_ops, (void *)(uintptr_t)got);
 }
 
+#ifdef CONFIG_CEPH_FSCACHE
+static void ceph_set_page_fscache(struct page *page)
+{
+	set_page_fscache(page);
+}
+
+static void ceph_fscache_write_terminated(void *priv, ssize_t error, bool was_async)
+{
+	struct inode *inode = priv;
+
+	if (IS_ERR_VALUE(error) && error != -ENOBUFS)
+		ceph_fscache_invalidate(inode, false);
+}
+
+static void ceph_fscache_write_to_cache(struct inode *inode, u64 off, u64 len, bool caching)
+{
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct fscache_cookie *cookie = ceph_fscache_cookie(ci);
+
+	fscache_write_to_cache(cookie, inode->i_mapping, off, len, i_size_read(inode),
+			       ceph_fscache_write_terminated, inode, caching);
+}
+#else
+static inline void ceph_set_page_fscache(struct page *page)
+{
+}
+
+static inline void ceph_fscache_write_to_cache(struct inode *inode, u64 off, u64 len, bool caching)
+{
+}
+#endif /* CONFIG_CEPH_FSCACHE */
+
 struct ceph_writeback_ctl
 {
 	loff_t i_size;

@@ -499,6 +530,7 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
 	struct ceph_writeback_ctl ceph_wbc;
 	struct ceph_osd_client *osdc = &fsc->client->osdc;
 	struct ceph_osd_request *req;
+	bool caching = ceph_is_cache_enabled(inode);
 
 	dout("writepage %p idx %lu\n", page, page->index);
 

@@ -537,16 +569,17 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
 	    CONGESTION_ON_THRESH(fsc->mount_options->congestion_kb))
 		set_bdi_congested(inode_to_bdi(inode), BLK_RW_ASYNC);
 
-	set_page_writeback(page);
 	req = ceph_osdc_new_request(osdc, &ci->i_layout, ceph_vino(inode), page_off, &len, 0, 1,
 				    CEPH_OSD_OP_WRITE, CEPH_OSD_FLAG_WRITE, snapc,
 				    ceph_wbc.truncate_seq, ceph_wbc.truncate_size,
 				    true);
-	if (IS_ERR(req)) {
-		redirty_page_for_writepage(wbc, page);
-		end_page_writeback(page);
+	if (IS_ERR(req))
 		return PTR_ERR(req);
-	}
+
+	set_page_writeback(page);
+	if (caching)
+		ceph_set_page_fscache(page);
+	ceph_fscache_write_to_cache(inode, page_off, len, caching);
 
 	/* it may be a short write due to an object boundary */
 	WARN_ON_ONCE(len > thp_size(page));

@@ -605,6 +638,9 @@ static int ceph_writepage(struct page *page, struct writeback_control *wbc)
 	struct inode *inode = page->mapping->host;
 	BUG_ON(!inode);
 	ihold(inode);
+
+	wait_on_page_fscache(page);
+
 	err = writepage_nounlock(page, wbc);
 	if (err == -ERESTARTSYS) {
 		/* direct memory reclaimer was killed by SIGKILL. return 0

@@ -726,6 +762,7 @@ static int ceph_writepages_start(struct address_space *mapping,
 	struct ceph_writeback_ctl ceph_wbc;
 	bool should_loop, range_whole = false;
 	bool done = false;
+	bool caching = ceph_is_cache_enabled(inode);
 
 	dout("writepages_start %p (mode=%s)\n", inode,
 	     wbc->sync_mode == WB_SYNC_NONE ? "NONE" :

@@ -849,7 +886,7 @@ static int ceph_writepages_start(struct address_space *mapping,
 				unlock_page(page);
 				break;
 			}
-			if (PageWriteback(page)) {
+			if (PageWriteback(page) || PageFsCache(page)) {
 				if (wbc->sync_mode == WB_SYNC_NONE) {
 					dout("%p under writeback\n", page);
 					unlock_page(page);

@@ -857,6 +894,7 @@ static int ceph_writepages_start(struct address_space *mapping,
 				}
 				dout("waiting on writeback %p\n", page);
 				wait_on_page_writeback(page);
+				wait_on_page_fscache(page);
 			}
 
 			if (!clear_page_dirty_for_io(page)) {

@@ -989,9 +1027,19 @@ static int ceph_writepages_start(struct address_space *mapping,
 		op_idx = 0;
 		for (i = 0; i < locked_pages; i++) {
 			u64 cur_offset = page_offset(pages[i]);
+			/*
+			 * Discontinuity in page range? Ceph can handle that by just passing
+			 * multiple extents in the write op.
+			 */
 			if (offset + len != cur_offset) {
+				/* If it's full, stop here */
 				if (op_idx + 1 == req->r_num_ops)
 					break;
+
+				/* Kick off an fscache write with what we have so far. */
+				ceph_fscache_write_to_cache(inode, offset, len, caching);
+
+				/* Start a new extent */
 				osd_req_op_extent_dup_last(req, op_idx,
 							   cur_offset - offset);
 				dout("writepages got pages at %llu~%llu\n",

@@ -1002,14 +1050,17 @@ static int ceph_writepages_start(struct address_space *mapping,
 				osd_req_op_extent_update(req, op_idx, len);
 
 				len = 0;
-				offset = cur_offset; 
+				offset = cur_offset;
 				data_pages = pages + i;
 				op_idx++;
 			}
 
 			set_page_writeback(pages[i]);
+			if (caching)
+				ceph_set_page_fscache(pages[i]);
 			len += thp_size(page);
 		}
+		ceph_fscache_write_to_cache(inode, offset, len, caching);
 
 		if (ceph_wbc.size_stable) {
 			len = min(len, ceph_wbc.i_size - offset);