[PATCH 4/9] exofs: address_space_operations

[Boaz Harrosh <bharrosh@panasas.com>]

OK Now we start to read and write from osd-objects, page-by-page.
The page index is the object's offset.

Signed-off-by: Boaz Harrosh <bharrosh@panasas.com>
---
 fs/exofs/exofs.h |    6 +
 fs/exofs/inode.c |  315 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 321 insertions(+), 0 deletions(-)

diff --git a/fs/exofs/exofs.h b/fs/exofs/exofs.h
index 6f9b56c..a094cd7 100644
--- a/fs/exofs/exofs.h
+++ b/fs/exofs/exofs.h
@@ -183,6 +183,9 @@ void free_osd_req(struct osd_request *req);
 /* inode.c               */
 void exofs_truncate(struct inode *inode);
 int exofs_setattr(struct dentry *, struct iattr *);
+int exofs_write_begin(struct file *file, struct address_space *mapping,
+		loff_t pos, unsigned len, unsigned flags,
+		struct page **pagep, void **fsdata);
 
 /*********************
  * operation vectors *
@@ -191,6 +194,9 @@ int exofs_setattr(struct dentry *, struct iattr *);
 extern struct inode_operations exofs_file_inode_operations;
 extern struct file_operations exofs_file_operations;
 
+/* inode.c           */
+extern struct address_space_operations exofs_aops;
+
 /* symlink.c         */
 extern struct inode_operations exofs_symlink_inode_operations;
 extern struct inode_operations exofs_fast_symlink_inode_operations;
diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c
index 931025b..b904e97 100644
--- a/fs/exofs/inode.c
+++ b/fs/exofs/inode.c
@@ -36,6 +36,8 @@
 
 #include "exofs.h"
 
+static int __readpage_filler(struct page *page, bool is_async_unlock);
+
 /*
  * Test whether an inode is a fast symlink.
  */
@@ -60,6 +62,319 @@ int exofs_get_block(struct inode *inode, sector_t iblock,
 	return 0;
 }
 
+int exofs_write_begin(struct file *file, struct address_space *mapping,
+		loff_t pos, unsigned len, unsigned flags,
+		struct page **pagep, void **fsdata)
+{
+	int ret = 0;
+	struct page *page;
+
+	page = *pagep;
+	if (page == NULL) {
+		ret = simple_write_begin(file, mapping, pos, len, flags, pagep,
+					 fsdata);
+		page = *pagep;
+	}
+
+	 /* read modify write */
+	if (!PageUptodate(page) && (len != PAGE_CACHE_SIZE))
+			ret = __readpage_filler(page, false);
+
+	return ret;
+}
+
+int exofs_write_begin_export(struct file *file, struct address_space *mapping,
+		loff_t pos, unsigned len, unsigned flags,
+		struct page **pagep, void **fsdata)
+{
+	*pagep = NULL;
+
+	return exofs_write_begin(file, mapping, pos, len, flags, pagep,
+					fsdata);
+}
+
+/*
+ * Callback function when writepage finishes.  Check for errors, unlock, clean
+ * up, etc.
+ */
+void writepage_done(struct osd_request *req, void *p)
+{
+	int ret;
+	struct page *page = (struct page *)p;
+	struct inode *inode = page->mapping->host;
+	struct exofs_sb_info *sbi = inode->i_sb->s_fs_info;
+
+	ret = check_ok(req);
+	free_osd_req(req);
+	atomic_dec(&sbi->s_curr_pending);
+
+	if (ret) {
+		if (ret == -ENOSPC)
+			set_bit(AS_ENOSPC, &page->mapping->flags);
+		else
+			set_bit(AS_EIO, &page->mapping->flags);
+
+		SetPageError(page);
+	}
+
+	end_page_writeback(page);
+	unlock_page(page);
+}
+
+/*
+ * Write a page to disk.  page->index gives us the page number.  The page is
+ * locked before this function is called.  We write asynchronously and then the
+ * callback function (writepage_done) is called.  We signify that the operation
+ * has completed by unlocking the page and calling end_page_writeback().
+ */
+static int exofs_writepage(struct page *page, struct writeback_control *wbc)
+{
+	struct inode *inode = page->mapping->host;
+	struct exofs_i_info *oi = EXOFS_I(inode);
+	loff_t i_size = i_size_read(inode);
+	unsigned long end_index = i_size >> PAGE_CACHE_SHIFT;
+	unsigned offset = 0;
+	struct osd_request *req = NULL;
+	struct exofs_sb_info *sbi;
+	uint64_t start;
+	uint64_t len = PAGE_CACHE_SIZE;
+	unsigned char *kaddr;
+	int ret = 0;
+
+	if (!PageLocked(page))
+		BUG();
+
+	/* if the object has not been created, and we are not in sync mode,
+	 * just return.  otherwise, wait. */
+	if (!ObjCreated(oi)) {
+		if (!Obj2BCreated(oi))
+			BUG();
+
+		if (wbc->sync_mode == WB_SYNC_NONE) {
+			redirty_page_for_writepage(wbc, page);
+			unlock_page(page);
+			ret = 0;
+			goto out;
+		} else {
+			wait_event(oi->i_wq, ObjCreated(oi));
+		}
+	}
+
+	/* in this case, the page is within the limits of the file */
+	if (page->index < end_index)
+		goto do_it;
+
+	offset = i_size & (PAGE_CACHE_SIZE - 1);
+	len = offset;
+
+	/*in this case, the page is outside the limits (truncate in progress)*/
+	if (page->index >= end_index + 1 || !offset) {
+		unlock_page(page);
+		goto out;
+	}
+
+do_it:
+	BUG_ON(PageWriteback(page));
+	set_page_writeback(page);
+	start = page->index << PAGE_CACHE_SHIFT;
+	sbi = inode->i_sb->s_fs_info;
+
+	kaddr = page_address(page);
+
+	req = prepare_osd_write(sbi->s_dev, sbi->s_pid,
+			      inode->i_ino + EXOFS_OBJ_OFF, len, start, 0,
+			      kaddr);
+	if (!req) {
+		printk(KERN_ERR "ERROR: writepage failed.\n");
+		ret = -ENOMEM;
+		goto fail;
+	}
+
+	oi->i_commit_size = min_t(uint64_t, oi->i_commit_size, len + start);
+
+	ret = exofs_async_op(req, writepage_done, (void *)page, oi->i_cred);
+	if (ret) {
+		free_osd_req(req);
+		goto fail;
+	}
+	atomic_inc(&sbi->s_curr_pending);
+out:
+	return ret;
+fail:
+	set_bit(AS_EIO, &page->mapping->flags);
+	end_page_writeback(page);
+	unlock_page(page);
+	goto out;
+}
+
+/*
+ * Callback for readpage
+ */
+int __readpage_done(struct osd_request *req, void *p, int unlock)
+{
+	struct page *page = (struct page *)p;
+	struct inode *inode = page->mapping->host;
+	struct exofs_sb_info *sbi = inode->i_sb->s_fs_info;
+	int ret;
+
+	ret = check_ok(req);
+	free_osd_req(req);
+	atomic_dec(&sbi->s_curr_pending);
+
+	if (ret == 0) {
+
+		/* Everything is OK */
+		SetPageUptodate(page);
+		if (PageError(page))
+			ClearPageError(page);
+	} else if (ret == -EFAULT) {
+		char *kaddr;
+
+		/* In this case we were trying to read something that wasn't on
+		 * disk yet - return a page full of zeroes.  This should be OK,
+		 * because the object should be empty (if there was a write
+		 * before this read, the read would be waiting with the page
+		 * locked */
+		kaddr = page_address(page);
+		memset(kaddr, 0, PAGE_CACHE_SIZE);
+
+		SetPageUptodate(page);
+		if (PageError(page))
+			ClearPageError(page);
+	} else /* Error */
+		SetPageError(page);
+
+	if (unlock)
+		unlock_page(page);
+
+	return ret;
+}
+
+void readpage_done(struct osd_request *req, void *p)
+{
+	__readpage_done(req, p, true);
+}
+
+/*
+ * Read a page from the OSD
+ */
+static int __readpage_filler(struct page *page, bool is_async_unlock)
+{
+	struct osd_request *req = NULL;
+	struct inode *inode = page->mapping->host;
+	struct exofs_i_info *oi = EXOFS_I(inode);
+	ino_t ino = inode->i_ino;
+	loff_t i_size = i_size_read(inode);
+	loff_t i_start = page->index << PAGE_CACHE_SHIFT;
+	unsigned long end_index = i_size >> PAGE_CACHE_SHIFT;
+	struct super_block *sb = inode->i_sb;
+	struct exofs_sb_info *sbi = sb->s_fs_info;
+	uint64_t amount;
+	unsigned char *kaddr;
+	int ret = 0;
+
+	if (!PageLocked(page))
+		BUG();
+
+	if (PageUptodate(page))
+		goto out;
+
+	if (page->index < end_index)
+		amount = PAGE_CACHE_SIZE;
+	else
+		amount = i_size & (PAGE_CACHE_SIZE - 1);
+
+	/* this will be out of bounds, or doesn't exist yet */
+	if ((page->index >= end_index + 1) || !ObjCreated(oi) || !amount
+	    /*|| (i_start >= oi->i_commit_size)*/) {
+		kaddr = kmap_atomic(page, KM_USER0);
+		memset(kaddr, 0, PAGE_CACHE_SIZE);
+		flush_dcache_page(page);
+		kunmap_atomic(page, KM_USER0);
+		SetPageUptodate(page);
+		if (PageError(page))
+			ClearPageError(page);
+		if (is_async_unlock)
+			unlock_page(page);
+		goto out;
+	}
+
+	if (amount != PAGE_CACHE_SIZE) {
+		kaddr = kmap_atomic(page, KM_USER0);
+		memset(kaddr + amount, 0, PAGE_CACHE_SIZE - amount);
+		flush_dcache_page(page);
+		kunmap_atomic(page, KM_USER0);
+	}
+
+	kaddr = page_address(page);
+
+	req = prepare_osd_read(sbi->s_dev, sbi->s_pid, ino + EXOFS_OBJ_OFF,
+			       amount, i_start, 0, kaddr);
+	if (!req) {
+		printk(KERN_ERR "ERROR: readpage failed.\n");
+		ret = -ENOMEM;
+		unlock_page(page);
+		goto out;
+	}
+
+	atomic_inc(&sbi->s_curr_pending);
+	if (!is_async_unlock) {
+		exofs_sync_op(req, sbi->s_timeout, oi->i_cred);
+		ret = __readpage_done(req, page, false);
+	} else {
+		ret = exofs_async_op(req, readpage_done, page, oi->i_cred);
+		if (ret) {
+			free_osd_req(req);
+			unlock_page(page);
+			atomic_dec(&sbi->s_curr_pending);
+		}
+	}
+
+out:
+	return ret;
+}
+
+static int readpage_filler(struct page *page)
+{
+	int ret = __readpage_filler(page, true);
+
+	return ret;
+}
+
+/*
+ * We don't need the file
+ */
+static int exofs_readpage(struct file *file, struct page *page)
+{
+	return readpage_filler(page);
+}
+
+/*
+ * We don't need the data
+ */
+static int readpage_strip(void *data, struct page *page)
+{
+	return readpage_filler(page);
+}
+
+/*
+ * read a bunch of pages - usually for readahead
+ */
+static int exofs_readpages(struct file *file, struct address_space *mapping,
+			   struct list_head *pages, unsigned nr_pages)
+{
+	return read_cache_pages(mapping, pages, readpage_strip, NULL);
+}
+
+struct address_space_operations exofs_aops = {
+	.readpage	= exofs_readpage,
+	.readpages	= exofs_readpages,
+	.writepage	= exofs_writepage,
+	.write_begin	= exofs_write_begin_export,
+	.write_end	= simple_write_end,
+	.writepages	= generic_writepages,
+};
+
 /******************************************************************************
  * INODE OPERATIONS
  *****************************************************************************/
-- 
1.6.0.1