dm: add bufio

The dm-bufio interface allows you to do cached I/O on devices,
holding recently-read blocks in memory and performing delayed writes.

We don't use buffer cache or page cache already present in the kernel, because:
* we need to handle block sizes larger than a page
* we can't allocate memory to perform reads or we'd have deadlocks

Currently, when a cache is required, we limit its size to a fraction of
available memory.  Usage can be viewed and changed in
/sys/module/dm_bufio/parameters/ .

The first user is thin provisioning, but more dm users are planned.

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>

1 files changed, 112 insertions, 0 deletions

diff --git a/drivers/md/dm-bufio.h b/drivers/md/dm-bufio.h
new file mode 100644
index 000000000000..5c4c3a04e381
--- /dev/null
+++ b/drivers/md/dm-bufio.h
@@ -0,0 +1,112 @@
+/*
+ * Copyright (C) 2009-2011 Red Hat, Inc.
+ *
+ * Author: Mikulas Patocka <mpatocka@redhat.com>
+ *
+ * This file is released under the GPL.
+ */
+
+#ifndef DM_BUFIO_H
+#define DM_BUFIO_H
+
+#include <linux/blkdev.h>
+#include <linux/types.h>
+
+/*----------------------------------------------------------------*/
+
+struct dm_bufio_client;
+struct dm_buffer;
+
+/*
+ * Create a buffered IO cache on a given device
+ */
+struct dm_bufio_client *
+dm_bufio_client_create(struct block_device *bdev, unsigned block_size,
+                       unsigned reserved_buffers, unsigned aux_size,
+                       void (*alloc_callback)(struct dm_buffer *),
+                       void (*write_callback)(struct dm_buffer *));
+
+/*
+ * Release a buffered IO cache.
+ */
+void dm_bufio_client_destroy(struct dm_bufio_client *c);
+
+/*
+ * WARNING: to avoid deadlocks, these conditions are observed:
+ *
+ * - At most one thread can hold at most "reserved_buffers" simultaneously.
+ * - Each other threads can hold at most one buffer.
+ * - Threads which call only dm_bufio_get can hold unlimited number of
+ *   buffers.
+ */
+
+/*
+ * Read a given block from disk. Returns pointer to data.  Returns a
+ * pointer to dm_buffer that can be used to release the buffer or to make
+ * it dirty.
+ */
+void *dm_bufio_read(struct dm_bufio_client *c, sector_t block,
+                    struct dm_buffer **bp);
+
+/*
+ * Like dm_bufio_read, but return buffer from cache, don't read
+ * it. If the buffer is not in the cache, return NULL.
+ */
+void *dm_bufio_get(struct dm_bufio_client *c, sector_t block,
+                   struct dm_buffer **bp);
+
+/*
+ * Like dm_bufio_read, but don't read anything from the disk.  It is
+ * expected that the caller initializes the buffer and marks it dirty.
+ */
+void *dm_bufio_new(struct dm_bufio_client *c, sector_t block,
+                   struct dm_buffer **bp);
+
+/*
+ * Release a reference obtained with dm_bufio_{read,get,new}. The data
+ * pointer and dm_buffer pointer is no longer valid after this call.
+ */
+void dm_bufio_release(struct dm_buffer *b);
+
+/*
+ * Mark a buffer dirty. It should be called after the buffer is modified.
+ *
+ * In case of memory pressure, the buffer may be written after
+ * dm_bufio_mark_buffer_dirty, but before dm_bufio_write_dirty_buffers.  So
+ * dm_bufio_write_dirty_buffers guarantees that the buffer is on-disk but
+ * the actual writing may occur earlier.
+ */
+void dm_bufio_mark_buffer_dirty(struct dm_buffer *b);
+
+/*
+ * Initiate writing of dirty buffers, without waiting for completion.
+ */
+void dm_bufio_write_dirty_buffers_async(struct dm_bufio_client *c);
+
+/*
+ * Write all dirty buffers. Guarantees that all dirty buffers created prior
+ * to this call are on disk when this call exits.
+ */
+int dm_bufio_write_dirty_buffers(struct dm_bufio_client *c);
+
+/*
+ * Send an empty write barrier to the device to flush hardware disk cache.
+ */
+int dm_bufio_issue_flush(struct dm_bufio_client *c);
+
+/*
+ * Like dm_bufio_release but also move the buffer to the new
+ * block. dm_bufio_write_dirty_buffers is needed to commit the new block.
+ */
+void dm_bufio_release_move(struct dm_buffer *b, sector_t new_block);
+
+unsigned dm_bufio_get_block_size(struct dm_bufio_client *c);
+sector_t dm_bufio_get_device_size(struct dm_bufio_client *c);
+sector_t dm_bufio_get_block_number(struct dm_buffer *b);
+void *dm_bufio_get_block_data(struct dm_buffer *b);
+void *dm_bufio_get_aux_data(struct dm_buffer *b);
+struct dm_bufio_client *dm_bufio_get_client(struct dm_buffer *b);
+
+/*----------------------------------------------------------------*/
+
+#endif