summaryrefslogtreecommitdiffstats
path: root/include
diff options
context:
space:
mode:
Diffstat (limited to 'include')
-rw-r--r--include/linux/async_tx.h9
-rw-r--r--include/linux/device-mapper.h3
-rw-r--r--include/linux/dm-dirty-log.h13
-rw-r--r--include/linux/dma_remapping.h1
-rw-r--r--include/linux/dmaengine.h30
-rw-r--r--include/linux/dw_dmac.h19
-rw-r--r--include/linux/ext3_fs.h1
-rw-r--r--include/linux/fscache-cache.h505
-rw-r--r--include/linux/fscache.h618
-rw-r--r--include/linux/hdreg.h66
-rw-r--r--include/linux/highmem.h29
-rw-r--r--include/linux/i2c/twl4030.h47
-rw-r--r--include/linux/intel-iommu.h2
-rw-r--r--include/linux/iommu.h13
-rw-r--r--include/linux/jbd.h5
-rw-r--r--include/linux/mmc/host.h5
-rw-r--r--include/linux/nfs_fs.h13
-rw-r--r--include/linux/nfs_fs_sb.h11
-rw-r--r--include/linux/nfs_iostat.h12
-rw-r--r--include/linux/page-flags.h40
-rw-r--r--include/linux/pagemap.h5
-rw-r--r--include/linux/raid/bitmap.h288
-rw-r--r--include/linux/raid/linear.h31
-rw-r--r--include/linux/raid/md.h81
-rw-r--r--include/linux/raid/md_k.h402
-rw-r--r--include/linux/raid/md_u.h35
-rw-r--r--include/linux/raid/multipath.h42
-rw-r--r--include/linux/raid/pq.h132
-rw-r--r--include/linux/raid/raid0.h30
-rw-r--r--include/linux/raid/raid1.h134
-rw-r--r--include/linux/raid/raid10.h123
-rw-r--r--include/linux/raid/raid5.h402
-rw-r--r--include/linux/raid/xor.h2
-rw-r--r--include/linux/regulator/bq24022.h3
-rw-r--r--include/linux/regulator/consumer.h6
-rw-r--r--include/linux/regulator/driver.h81
-rw-r--r--include/linux/regulator/fixed.h3
-rw-r--r--include/linux/regulator/machine.h12
-rw-r--r--include/linux/slow-work.h95
-rw-r--r--include/linux/timeriomem-rng.h2
40 files changed, 1715 insertions, 1636 deletions
diff --git a/include/linux/async_tx.h b/include/linux/async_tx.h
index 45f6297821b..5fc2ef8d97f 100644
--- a/include/linux/async_tx.h
+++ b/include/linux/async_tx.h
@@ -21,6 +21,15 @@
#include <linux/spinlock.h>
#include <linux/interrupt.h>
+/* on architectures without dma-mapping capabilities we need to ensure
+ * that the asynchronous path compiles away
+ */
+#ifdef CONFIG_HAS_DMA
+#define __async_inline
+#else
+#define __async_inline __always_inline
+#endif
+
/**
* dma_chan_ref - object used to manage dma channels received from the
* dmaengine core.
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index 8209e08969f..66ec05a5795 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -139,6 +139,9 @@ struct target_type {
dm_ioctl_fn ioctl;
dm_merge_fn merge;
dm_busy_fn busy;
+
+ /* For internal device-mapper use. */
+ struct list_head list;
};
struct io_restrictions {
diff --git a/include/linux/dm-dirty-log.h b/include/linux/dm-dirty-log.h
index 600c5fb2daa..5e8b11d88f6 100644
--- a/include/linux/dm-dirty-log.h
+++ b/include/linux/dm-dirty-log.h
@@ -28,6 +28,9 @@ struct dm_dirty_log_type {
const char *name;
struct module *module;
+ /* For internal device-mapper use */
+ struct list_head list;
+
int (*ctr)(struct dm_dirty_log *log, struct dm_target *ti,
unsigned argc, char **argv);
void (*dtr)(struct dm_dirty_log *log);
@@ -113,6 +116,16 @@ struct dm_dirty_log_type {
*/
int (*status)(struct dm_dirty_log *log, status_type_t status_type,
char *result, unsigned maxlen);
+
+ /*
+ * is_remote_recovering is necessary for cluster mirroring. It provides
+ * a way to detect recovery on another node, so we aren't writing
+ * concurrently. This function is likely to block (when a cluster log
+ * is used).
+ *
+ * Returns: 0, 1
+ */
+ int (*is_remote_recovering)(struct dm_dirty_log *log, region_t region);
};
int dm_dirty_log_type_register(struct dm_dirty_log_type *type);
diff --git a/include/linux/dma_remapping.h b/include/linux/dma_remapping.h
index af1dab41674..1a455f1f86d 100644
--- a/include/linux/dma_remapping.h
+++ b/include/linux/dma_remapping.h
@@ -11,6 +11,7 @@
#define DMA_PTE_READ (1)
#define DMA_PTE_WRITE (2)
+#define DMA_PTE_SNP (1 << 11)
struct intel_iommu;
struct dmar_domain;
diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index 1956c8d46d3..2e2aa3df170 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -23,9 +23,6 @@
#include <linux/device.h>
#include <linux/uio.h>
-#include <linux/kref.h>
-#include <linux/completion.h>
-#include <linux/rcupdate.h>
#include <linux/dma-mapping.h>
/**
@@ -205,6 +202,7 @@ struct dma_async_tx_descriptor {
/**
* struct dma_device - info on the entity supplying DMA services
* @chancnt: how many DMA channels are supported
+ * @privatecnt: how many DMA channels are requested by dma_request_channel
* @channels: the list of struct dma_chan
* @global_node: list_head for global dma_device_list
* @cap_mask: one or more dma_capability flags
@@ -227,6 +225,7 @@ struct dma_async_tx_descriptor {
struct dma_device {
unsigned int chancnt;
+ unsigned int privatecnt;
struct list_head channels;
struct list_head global_node;
dma_cap_mask_t cap_mask;
@@ -291,6 +290,24 @@ static inline void net_dmaengine_put(void)
}
#endif
+#ifdef CONFIG_ASYNC_TX_DMA
+#define async_dmaengine_get() dmaengine_get()
+#define async_dmaengine_put() dmaengine_put()
+#define async_dma_find_channel(type) dma_find_channel(type)
+#else
+static inline void async_dmaengine_get(void)
+{
+}
+static inline void async_dmaengine_put(void)
+{
+}
+static inline struct dma_chan *
+async_dma_find_channel(enum dma_transaction_type type)
+{
+ return NULL;
+}
+#endif
+
dma_cookie_t dma_async_memcpy_buf_to_buf(struct dma_chan *chan,
void *dest, void *src, size_t len);
dma_cookie_t dma_async_memcpy_buf_to_pg(struct dma_chan *chan,
@@ -337,6 +354,13 @@ __dma_cap_set(enum dma_transaction_type tx_type, dma_cap_mask_t *dstp)
set_bit(tx_type, dstp->bits);
}
+#define dma_cap_clear(tx, mask) __dma_cap_clear((tx), &(mask))
+static inline void
+__dma_cap_clear(enum dma_transaction_type tx_type, dma_cap_mask_t *dstp)
+{
+ clear_bit(tx_type, dstp->bits);
+}
+
#define dma_cap_zero(mask) __dma_cap_zero(&(mask))
static inline void __dma_cap_zero(dma_cap_mask_t *dstp)
{
diff --git a/include/linux/dw_dmac.h b/include/linux/dw_dmac.h
index d797dde247f..c8aad713a04 100644
--- a/include/linux/dw_dmac.h
+++ b/include/linux/dw_dmac.h
@@ -74,4 +74,23 @@ struct dw_dma_slave {
#define DWC_CFGL_HS_DST_POL (1 << 18) /* dst handshake active low */
#define DWC_CFGL_HS_SRC_POL (1 << 19) /* src handshake active low */
+/* DMA API extensions */
+struct dw_cyclic_desc {
+ struct dw_desc **desc;
+ unsigned long periods;
+ void (*period_callback)(void *param);
+ void *period_callback_param;
+};
+
+struct dw_cyclic_desc *dw_dma_cyclic_prep(struct dma_chan *chan,
+ dma_addr_t buf_addr, size_t buf_len, size_t period_len,
+ enum dma_data_direction direction);
+void dw_dma_cyclic_free(struct dma_chan *chan);
+int dw_dma_cyclic_start(struct dma_chan *chan);
+void dw_dma_cyclic_stop(struct dma_chan *chan);
+
+dma_addr_t dw_dma_get_src_addr(struct dma_chan *chan);
+
+dma_addr_t dw_dma_get_dst_addr(struct dma_chan *chan);
+
#endif /* DW_DMAC_H */
diff --git a/include/linux/ext3_fs.h b/include/linux/ext3_fs.h
index e263acaa405..634a5e5aba3 100644
--- a/include/linux/ext3_fs.h
+++ b/include/linux/ext3_fs.h
@@ -208,6 +208,7 @@ static inline __u32 ext3_mask_flags(umode_t mode, __u32 flags)
#define EXT3_STATE_JDATA 0x00000001 /* journaled data exists */
#define EXT3_STATE_NEW 0x00000002 /* inode is newly created */
#define EXT3_STATE_XATTR 0x00000004 /* has in-inode xattrs */
+#define EXT3_STATE_FLUSH_ON_CLOSE 0x00000008
/* Used to pass group descriptor data when online resize is done */
struct ext3_new_group_input {
diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h
new file mode 100644
index 00000000000..84d3532dd3e
--- /dev/null
+++ b/include/linux/fscache-cache.h
@@ -0,0 +1,505 @@
+/* General filesystem caching backing cache interface
+ *
+ * Copyright (C) 2004-2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * NOTE!!! See:
+ *
+ * Documentation/filesystems/caching/backend-api.txt
+ *
+ * for a description of the cache backend interface declared here.
+ */
+
+#ifndef _LINUX_FSCACHE_CACHE_H
+#define _LINUX_FSCACHE_CACHE_H
+
+#include <linux/fscache.h>
+#include <linux/sched.h>
+#include <linux/slow-work.h>
+
+#define NR_MAXCACHES BITS_PER_LONG
+
+struct fscache_cache;
+struct fscache_cache_ops;
+struct fscache_object;
+struct fscache_operation;
+
+/*
+ * cache tag definition
+ */
+struct fscache_cache_tag {
+ struct list_head link;
+ struct fscache_cache *cache; /* cache referred to by this tag */
+ unsigned long flags;
+#define FSCACHE_TAG_RESERVED 0 /* T if tag is reserved for a cache */
+ atomic_t usage;
+ char name[0]; /* tag name */
+};
+
+/*
+ * cache definition
+ */
+struct fscache_cache {
+ const struct fscache_cache_ops *ops;
+ struct fscache_cache_tag *tag; /* tag representing this cache */
+ struct kobject *kobj; /* system representation of this cache */
+ struct list_head link; /* link in list of caches */
+ size_t max_index_size; /* maximum size of index data */
+ char identifier[36]; /* cache label */
+
+ /* node management */
+ struct work_struct op_gc; /* operation garbage collector */
+ struct list_head object_list; /* list of data/index objects */
+ struct list_head op_gc_list; /* list of ops to be deleted */
+ spinlock_t object_list_lock;
+ spinlock_t op_gc_list_lock;
+ atomic_t object_count; /* no. of live objects in this cache */
+ struct fscache_object *fsdef; /* object for the fsdef index */
+ unsigned long flags;
+#define FSCACHE_IOERROR 0 /* cache stopped on I/O error */
+#define FSCACHE_CACHE_WITHDRAWN 1 /* cache has been withdrawn */
+};
+
+extern wait_queue_head_t fscache_cache_cleared_wq;
+
+/*
+ * operation to be applied to a cache object
+ * - retrieval initiation operations are done in the context of the process
+ * that issued them, and not in an async thread pool
+ */
+typedef void (*fscache_operation_release_t)(struct fscache_operation *op);
+typedef void (*fscache_operation_processor_t)(struct fscache_operation *op);
+
+struct fscache_operation {
+ union {
+ struct work_struct fast_work; /* record for fast ops */
+ struct slow_work slow_work; /* record for (very) slow ops */
+ };
+ struct list_head pend_link; /* link in object->pending_ops */
+ struct fscache_object *object; /* object to be operated upon */
+
+ unsigned long flags;
+#define FSCACHE_OP_TYPE 0x000f /* operation type */
+#define FSCACHE_OP_FAST 0x0001 /* - fast op, processor may not sleep for disk */
+#define FSCACHE_OP_SLOW 0x0002 /* - (very) slow op, processor may sleep for disk */
+#define FSCACHE_OP_MYTHREAD 0x0003 /* - processing is done be issuing thread, not pool */
+#define FSCACHE_OP_WAITING 4 /* cleared when op is woken */
+#define FSCACHE_OP_EXCLUSIVE 5 /* exclusive op, other ops must wait */
+#define FSCACHE_OP_DEAD 6 /* op is now dead */
+
+ atomic_t usage;
+ unsigned debug_id; /* debugging ID */
+
+ /* operation processor callback
+ * - can be NULL if FSCACHE_OP_WAITING is going to be used to perform
+ * the op in a non-pool thread */
+ fscache_operation_processor_t processor;
+
+ /* operation releaser */
+ fscache_operation_release_t release;
+};
+
+extern atomic_t fscache_op_debug_id;
+extern const struct slow_work_ops fscache_op_slow_work_ops;
+
+extern void fscache_enqueue_operation(struct fscache_operation *);
+extern void fscache_put_operation(struct fscache_operation *);
+
+/**
+ * fscache_operation_init - Do basic initialisation of an operation
+ * @op: The operation to initialise
+ * @release: The release function to assign
+ *
+ * Do basic initialisation of an operation. The caller must still set flags,
+ * object, either fast_work or slow_work if necessary, and processor if needed.
+ */
+static inline void fscache_operation_init(struct fscache_operation *op,
+ fscache_operation_release_t release)
+{
+ atomic_set(&op->usage, 1);
+ op->debug_id = atomic_inc_return(&fscache_op_debug_id);
+ op->release = release;
+ INIT_LIST_HEAD(&op->pend_link);
+}
+
+/**
+ * fscache_operation_init_slow - Do additional initialisation of a slow op
+ * @op: The operation to initialise
+ * @processor: The processor function to assign
+ *
+ * Do additional initialisation of an operation as required for slow work.
+ */
+static inline
+void fscache_operation_init_slow(struct fscache_operation *op,
+ fscache_operation_processor_t processor)
+{
+ op->processor = processor;
+ slow_work_init(&op->slow_work, &fscache_op_slow_work_ops);
+}
+
+/*
+ * data read operation
+ */
+struct fscache_retrieval {
+ struct fscache_operation op;
+ struct address_space *mapping; /* netfs pages */
+ fscache_rw_complete_t end_io_func; /* function to call on I/O completion */
+ void *context; /* netfs read context (pinned) */
+ struct list_head to_do; /* list of things to be done by the backend */
+ unsigned long start_time; /* time at which retrieval started */
+};
+
+typedef int (*fscache_page_retrieval_func_t)(struct fscache_retrieval *op,
+ struct page *page,
+ gfp_t gfp);
+
+typedef int (*fscache_pages_retrieval_func_t)(struct fscache_retrieval *op,
+ struct list_head *pages,
+ unsigned *nr_pages,
+ gfp_t gfp);
+
+/**
+ * fscache_get_retrieval - Get an extra reference on a retrieval operation
+ * @op: The retrieval operation to get a reference on
+ *
+ * Get an extra reference on a retrieval operation.
+ */
+static inline
+struct fscache_retrieval *fscache_get_retrieval(struct fscache_retrieval *op)
+{
+ atomic_inc(&op->op.usage);
+ return op;
+}
+
+/**
+ * fscache_enqueue_retrieval - Enqueue a retrieval operation for processing
+ * @op: The retrieval operation affected
+ *
+ * Enqueue a retrieval operation for processing by the FS-Cache thread pool.
+ */
+static inline void fscache_enqueue_retrieval(struct fscache_retrieval *op)
+{
+ fscache_enqueue_operation(&op->op);
+}
+
+/**
+ * fscache_put_retrieval - Drop a reference to a retrieval operation
+ * @op: The retrieval operation affected
+ *
+ * Drop a reference to a retrieval operation.
+ */
+static inline void fscache_put_retrieval(struct fscache_retrieval *op)
+{
+ fscache_put_operation(&op->op);
+}
+
+/*
+ * cached page storage work item
+ * - used to do three things:
+ * - batch writes to the cache
+ * - do cache writes asynchronously
+ * - defer writes until cache object lookup completion
+ */
+struct fscache_storage {
+ struct fscache_operation op;
+ pgoff_t store_limit; /* don't write more than this */
+};
+
+/*
+ * cache operations
+ */
+struct fscache_cache_ops {
+ /* name of cache provider */
+ const char *name;
+
+ /* allocate an object record for a cookie */
+ struct fscache_object *(*alloc_object)(struct fscache_cache *cache,
+ struct fscache_cookie *cookie);
+
+ /* look up the object for a cookie */
+ void (*lookup_object)(struct fscache_object *object);
+
+ /* finished looking up */
+ void (*lookup_complete)(struct fscache_object *object);
+
+ /* increment the usage count on this object (may fail if unmounting) */
+ struct fscache_object *(*grab_object)(struct fscache_object *object);
+
+ /* pin an object in the cache */
+ int (*pin_object)(struct fscache_object *object);
+
+ /* unpin an object in the cache */
+ void (*unpin_object)(struct fscache_object *object);
+
+ /* store the updated auxilliary data on an object */
+ void (*update_object)(struct fscache_object *object);
+
+ /* discard the resources pinned by an object and effect retirement if
+ * necessary */
+ void (*drop_object)(struct fscache_object *object);
+
+ /* dispose of a reference to an object */
+ void (*put_object)(struct fscache_object *object);
+
+ /* sync a cache */
+ void (*sync_cache)(struct fscache_cache *cache);
+
+ /* notification that the attributes of a non-index object (such as
+ * i_size) have changed */
+ int (*attr_changed)(struct fscache_object *object);
+
+ /* reserve space for an object's data and associated metadata */
+ int (*reserve_space)(struct fscache_object *object, loff_t i_size);
+
+ /* request a backing block for a page be read or allocated in the
+ * cache */
+ fscache_page_retrieval_func_t read_or_alloc_page;
+
+ /* request backing blocks for a list of pages be read or allocated in
+ * the cache */
+ fscache_pages_retrieval_func_t read_or_alloc_pages;
+
+ /* request a backing block for a page be allocated in the cache so that
+ * it can be written directly */
+ fscache_page_retrieval_func_t allocate_page;
+
+ /* request backing blocks for pages be allocated in the cache so that
+ * they can be written directly */
+ fscache_pages_retrieval_func_t allocate_pages;
+
+ /* write a page to its backing block in the cache */
+ int (*write_page)(struct fscache_storage *op, struct page *page);
+
+ /* detach backing block from a page (optional)
+ * - must release the cookie lock before returning
+ * - may sleep
+ */
+ void (*uncache_page)(struct fscache_object *object,
+ struct page *page);
+
+ /* dissociate a cache from all the pages it was backing */
+ void (*dissociate_pages)(struct fscache_cache *cache);
+};
+
+/*
+ * data file or index object cookie
+ * - a file will only appear in one cache
+ * - a request to cache a file may or may not be honoured, subject to
+ * constraints such as disk space
+ * - indices are created on disk just-in-time
+ */
+struct fscache_cookie {
+ atomic_t usage; /* number of users of this cookie */
+ atomic_t n_children; /* number of children of this cookie */
+ spinlock_t lock;
+ struct hlist_head backing_objects; /* object(s) backing this file/index */
+ const struct fscache_cookie_def *def; /* definition */
+ struct fscache_cookie *parent; /* parent of this entry */
+ void *netfs_data; /* back pointer to netfs */
+ struct radix_tree_root stores; /* pages to be stored on this cookie */
+#define FSCACHE_COOKIE_PENDING_TAG 0 /* pages tag: pending write to cache */
+
+ unsigned long flags;
+#define FSCACHE_COOKIE_LOOKING_UP 0 /* T if non-index cookie being looked up still */
+#define FSCACHE_COOKIE_CREATING 1 /* T if non-index object being created still */
+#define FSCACHE_COOKIE_NO_DATA_YET 2 /* T if new object with no cached data yet */
+#define FSCACHE_COOKIE_PENDING_FILL 3 /* T if pending initial fill on object */
+#define FSCACHE_COOKIE_FILLING 4 /* T if filling object incrementally */
+#define FSCACHE_COOKIE_UNAVAILABLE 5 /* T if cookie is unavailable (error, etc) */
+};
+
+extern struct fscache_cookie fscache_fsdef_index;
+
+/*
+ * on-disk cache file or index handle
+ */
+struct fscache_object {
+ enum fscache_object_state {
+ FSCACHE_OBJECT_INIT, /* object in initial unbound state */
+ FSCACHE_OBJECT_LOOKING_UP, /* looking up object */
+ FSCACHE_OBJECT_CREATING, /* creating object */
+
+ /* active states */
+ FSCACHE_OBJECT_AVAILABLE, /* cleaning up object after creation */
+ FSCACHE_OBJECT_ACTIVE, /* object is usable */
+ FSCACHE_OBJECT_UPDATING, /* object is updating */
+
+ /* terminal states */
+ FSCACHE_OBJECT_DYING, /* object waiting for accessors to finish */
+ FSCACHE_OBJECT_LC_DYING, /* object cleaning up after lookup/create */
+ FSCACHE_OBJECT_ABORT_INIT, /* abort the init state */
+ FSCACHE_OBJECT_RELEASING, /* releasing object */
+ FSCACHE_OBJECT_RECYCLING, /* retiring object */
+ FSCACHE_OBJECT_WITHDRAWING, /* withdrawing object */
+ FSCACHE_OBJECT_DEAD, /* object is now dead */
+ } state;
+
+ int debug_id; /* debugging ID */
+ int n_children; /* number of child objects */
+ int n_ops; /* number of ops outstanding on object */
+ int n_obj_ops; /* number of object ops outstanding on object */
+ int n_in_progress; /* number of ops in progress */
+ int n_exclusive; /* number of exclusive ops queued */
+ spinlock_t lock; /* state and operations lock */
+
+ unsigned long lookup_jif; /* time at which lookup started */
+ unsigned long event_mask; /* events this object is interested in */
+ unsigned long events; /* events to be processed by this object
+ * (order is important - using fls) */
+#define FSCACHE_OBJECT_EV_REQUEUE 0 /* T if object should be requeued */
+#define FSCACHE_OBJECT_EV_UPDATE 1 /* T if object should be updated */
+#define FSCACHE_OBJECT_EV_CLEARED 2 /* T if accessors all gone */
+#define FSCACHE_OBJECT_EV_ERROR 3 /* T if fatal error occurred during processing */
+#define FSCACHE_OBJECT_EV_RELEASE 4 /* T if netfs requested object release */
+#define FSCACHE_OBJECT_EV_RETIRE 5 /* T if netfs requested object retirement */
+#define FSCACHE_OBJECT_EV_WITHDRAW 6 /* T if cache requested object withdrawal */
+
+ unsigned long flags;
+#define FSCACHE_OBJECT_LOCK 0 /* T if object is busy being processed */
+#define FSCACHE_OBJECT_PENDING_WRITE 1 /* T if object has pending write */
+#define FSCACHE_OBJECT_WAITING 2 /* T if object is waiting on its parent */
+
+ struct list_head cache_link; /* link in cache->object_list */
+ struct hlist_node cookie_link; /* link in cookie->backing_objects */
+ struct fscache_cache *cache; /* cache that supplied this object */
+ struct fscache_cookie *cookie; /* netfs's file/index object */
+ struct fscache_object *parent; /* parent object */
+ struct slow_work work; /* attention scheduling record */
+ struct list_head dependents; /* FIFO of dependent objects */
+ struct list_head dep_link; /* link in parent's dependents list */
+ struct list_head pending_ops; /* unstarted operations on this object */
+ pgoff_t store_limit; /* current storage limit */
+};
+
+extern const char *fscache_object_states[];
+
+#define fscache_object_is_active(obj) \
+ (!test_bit(FSCACHE_IOERROR, &(obj)->cache->flags) && \
+ (obj)->state >= FSCACHE_OBJECT_AVAILABLE && \
+ (obj)->state < FSCACHE_OBJECT_DYING)
+
+extern const struct slow_work_ops fscache_object_slow_work_ops;
+
+/**
+ * fscache_object_init - Initialise a cache object description
+ * @object: Object description
+ *
+ * Initialise a cache object description to its basic values.
+ *
+ * See Documentation/filesystems/caching/backend-api.txt for a complete
+ * description.
+ */
+static inline
+void fscache_object_init(struct fscache_object *object,
+ struct fscache_cookie *cookie,
+ struct fscache_cache *cache)
+{
+ atomic_inc(&cache->object_count);
+
+ object->state = FSCACHE_OBJECT_INIT;
+ spin_lock_init(&object->lock);
+ INIT_LIST_HEAD(&object->cache_link);
+ INIT_HLIST_NODE(&object->cookie_link);
+ vslow_work_init(&object->work, &fscache_object_slow_work_ops);
+ INIT_LIST_HEAD(&object->dependents);
+ INIT_LIST_HEAD(&object->dep_link);
+ INIT_LIST_HEAD(&object->pending_ops);
+ object->n_children = 0;
+ object->n_ops = object->n_in_progress = object->n_exclusive = 0;
+ object->events = object->event_mask = 0;
+ object->flags = 0;
+ object->store_limit = 0;
+ object->cache = cache;
+ object->cookie = cookie;
+ object->parent = NULL;
+}
+
+extern void fscache_object_lookup_negative(struct fscache_object *object);
+extern void fscache_obtained_object(struct fscache_object *object);
+
+/**
+ * fscache_object_destroyed - Note destruction of an object in a cache
+ * @cache: The cache from which the object came
+ *
+ * Note the destruction and deallocation of an object record in a cache.
+ */
+static inline void fscache_object_destroyed(struct fscache_cache *cache)
+{
+ if (atomic_dec_and_test(&cache->object_count))
+ wake_up_all(&fscache_cache_cleared_wq);
+}
+
+/**
+ * fscache_object_lookup_error - Note an object encountered an error
+ * @object: The object on which the error was encountered
+ *
+ * Note that an object encountered a fatal error (usually an I/O error) and
+ * that it should be withdrawn as soon as possible.
+ */
+static inline void fscache_object_lookup_error(struct fscache_object *object)
+{
+ set_bit(FSCACHE_OBJECT_EV_ERROR, &object->events);
+}
+
+/**
+ * fscache_set_store_limit - Set the maximum size to be stored in an object
+ * @object: The object to set the maximum on
+ * @i_size: The limit to set in bytes
+ *
+ * Set the maximum size an object is permitted to reach, implying the highest
+ * byte that may be written. Intended to be called by the attr_changed() op.
+ *
+ * See Documentation/filesystems/caching/backend-api.txt for a complete
+ * description.
+ */
+static inline
+void fscache_set_store_limit(struct fscache_object *object, loff_t i_size)
+{
+ object->store_limit = i_size >> PAGE_SHIFT;
+ if (i_size & ~PAGE_MASK)
+ object->store_limit++;
+}
+
+/**
+ * fscache_end_io - End a retrieval operation on a page
+ * @op: The FS-Cache operation covering the retrieval
+ * @page: The page that was to be fetched
+ * @error: The error code (0 if successful)
+ *
+ * Note the end of an operation to retrieve a page, as covered by a particular
+ * operation record.
+ */
+static inline void fscache_end_io(struct fscache_retrieval *op,
+ struct page *page, int error)
+{
+ op->end_io_func(page, op->context, error);
+}
+
+/*
+ * out-of-line cache backend functions
+ */
+extern void fscache_init_cache(struct fscache_cache *cache,
+ const struct fscache_cache_ops *ops,
+ const char *idfmt,
+ ...) __attribute__ ((format (printf, 3, 4)));
+
+extern int fscache_add_cache(struct fscache_cache *cache,
+ struct fscache_object *fsdef,
+ const char *tagname);
+extern void fscache_withdraw_cache(struct fscache_cache *cache);
+
+extern void fscache_io_error(struct fscache_cache *cache);
+
+extern void fscache_mark_pages_cached(struct fscache_retrieval *op,
+ struct pagevec *pagevec);
+
+extern enum fscache_checkaux fscache_check_aux(struct fscache_object *object,
+ const void *data,
+ uint16_t datalen);
+
+#endif /* _LINUX_FSCACHE_CACHE_H */
diff --git a/include/linux/fscache.h b/include/linux/fscache.h
new file mode 100644
index 00000000000..6d8ee466e0a
--- /dev/null
+++ b/include/linux/fscache.h
@@ -0,0 +1,618 @@
+/* General filesystem caching interface
+ *
+ * Copyright (C) 2004-2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * NOTE!!! See:
+ *
+ * Documentation/filesystems/caching/netfs-api.txt
+ *
+ * for a description of the network filesystem interface declared here.
+ */
+
+#ifndef _LINUX_FSCACHE_H
+#define _LINUX_FSCACHE_H
+
+#include <linux/fs.h>
+#include <linux/list.h>
+#include <linux/pagemap.h>
+#include <linux/pagevec.h>
+
+#if defined(CONFIG_FSCACHE) || defined(CONFIG_FSCACHE_MODULE)
+#define fscache_available() (1)
+#define fscache_cookie_valid(cookie) (cookie)
+#else
+#define fscache_available() (0)
+#define fscache_cookie_valid(cookie) (0)
+#endif
+
+
+/*
+ * overload PG_private_2 to give us PG_fscache - this is used to indicate that
+ * a page is currently backed by a local disk cache
+ */
+#define PageFsCache(page) PagePrivate2((page))
+#define SetPageFsCache(page) SetPagePrivate2((page))
+#define ClearPageFsCache(page) ClearPagePrivate2((page))
+#define TestSetPageFsCache(page) TestSetPagePrivate2((page))
+#define TestClearPageFsCache(page) TestClearPagePrivate2((page))
+
+/* pattern used to fill dead space in an index entry */
+#define FSCACHE_INDEX_DEADFILL_PATTERN 0x79
+
+struct pagevec;
+struct fscache_cache_tag;
+struct fscache_cookie;
+struct fscache_netfs;
+
+typedef void (*fscache_rw_complete_t)(struct page *page,
+ void *context,
+ int error);
+
+/* result of index entry consultation */
+enum fscache_checkaux {
+ FSCACHE_CHECKAUX_OKAY, /* entry okay as is */
+ FSCACHE_CHECKAUX_NEEDS_UPDATE, /* entry requires update */
+ FSCACHE_CHECKAUX_OBSOLETE, /* entry requires deletion */
+};
+
+/*
+ * fscache cookie definition
+ */
+struct fscache_cookie_def {
+ /* name of cookie type */
+ char name[16];
+
+ /* cookie type */
+ uint8_t type;
+#define FSCACHE_COOKIE_TYPE_INDEX 0
+#define FSCACHE_COOKIE_TYPE_DATAFILE 1
+
+ /* select the cache into which to insert an entry in this index
+ * - optional
+ * - should return a cache identifier or NULL to cause the cache to be
+ * inherited from the parent if possible or the first cache picked
+ * for a non-index file if not
+ */
+ struct fscache_cache_tag *(*select_cache)(
+ const void *parent_netfs_data,
+ const void *cookie_netfs_data);
+
+ /* get an index key
+ * - should store the key data in the buffer
+ * - should return the amount of amount stored
+ * - not permitted to return an error
+ * - the netfs data from the cookie being used as the source is
+ * presented
+ */
+ uint16_t (*get_key)(const void *cookie_netfs_data,
+ void *buffer,
+ uint16_t bufmax);
+
+ /* get certain file attributes from the netfs data
+ * - this function can be absent for an index
+ * - not permitted to return an error
+ * - the netfs data from the cookie being used as the source is
+ * presented
+ */
+ void (*get_attr)(const void *cookie_netfs_data, uint64_t *size);
+
+ /* get the auxilliary data from netfs data
+ * - this function can be absent if the index carries no state data
+ * - should store the auxilliary data in the buffer
+ * - should return the amount of amount stored
+ * - not permitted to return an error
+ * - the netfs data from the cookie being used as the source is
+ * presented
+ */
+ uint16_t (*get_aux)(const void *cookie_netfs_data,
+ void *buffer,
+ uint16_t bufmax);
+
+ /* consult the netfs about the state of an object
+ * - this function can be absent if the index carries no state data
+ * - the netfs data from the cookie being used as the target is
+ * presented, as is the auxilliary data
+ */
+ enum fscache_checkaux (*check_aux)(void *cookie_netfs_data,
+ const void *data,
+ uint16_t datalen);
+
+ /* get an extra reference on a read context
+ * - this function can be absent if the completion function doesn't
+ * require a context
+ */
+ void (*get_context)(void *cookie_netfs_data, void *context);
+
+ /* release an extra reference on a read context
+ * - this function can be absent if the completion function doesn't
+ * require a context
+ */
+ void (*put_context)(void *cookie_netfs_data, void *context);
+
+ /* indicate pages that now have cache metadata retained
+ * - this function should mark the specified pages as now being cached
+ * - the pages will have been marked with PG_fscache before this is
+ * called, so this is optional
+ */
+ void (*mark_pages_cached)(void *cookie_netfs_data,
+ struct address_space *mapping,
+ struct pagevec *cached_pvec);
+
+ /* indicate the cookie is no longer cached
+ * - this function is called when the backing store currently caching
+ * a cookie is removed
+ * - the netfs should use this to clean up any markers indicating
+ * cached pages
+ * - this is mandatory for any object that may have data
+ */
+ void (*now_uncached)(void *cookie_netfs_data);
+};
+
+/*
+ * fscache cached network filesystem type
+ * - name, version and ops must be filled in before registration
+ * - all other fields will be set during registration
+ */
+struct fscache_netfs {
+ uint32_t version; /* indexing version */
+ const char *name; /* filesystem name */
+ struct fscache_cookie *primary_index;
+ struct list_head link; /* internal link */
+};
+
+/*
+ * slow-path functions for when there is actually caching available, and the
+ * netfs does actually have a valid token
+ * - these are not to be called directly
+ * - these are undefined symbols when FS-Cache is not configured and the
+ * optimiser takes care of not using them
+ */
+extern int __fscache_register_netfs(struct fscache_netfs *);
+extern void __fscache_unregister_netfs(struct fscache_netfs *);
+extern struct fscache_cache_tag *__fscache_lookup_cache_tag(const char *);
+extern void __fscache_release_cache_tag(struct fscache_cache_tag *);
+
+extern struct fscache_cookie *__fscache_acquire_cookie(
+ struct fscache_cookie *,
+ const struct fscache_cookie_def *,
+ void *);
+extern void __fscache_relinquish_cookie(struct fscache_cookie *, int);
+extern void __fscache_update_cookie(struct fscache_cookie *);
+extern int __fscache_attr_changed(struct fscache_cookie *);
+extern int __fscache_read_or_alloc_page(struct fscache_cookie *,
+ struct page *,
+ fscache_rw_complete_t,
+ void *,
+ gfp_t);
+extern int __fscache_read_or_alloc_pages(struct fscache_cookie *,
+ struct address_space *,
+ struct list_head *,
+ unsigned *,
+ fscache_rw_complete_t,
+ void *,
+ gfp_t);
+extern int __fscache_alloc_page(struct fscache_cookie *, struct page *, gfp_t);
+extern int __fscache_write_page(struct fscache_cookie *, struct page *, gfp_t);
+extern void __fscache_uncache_page(struct fscache_cookie *, struct page *);
+extern bool __fscache_check_page_write(struct fscache_cookie *, struct page *);
+extern void __fscache_wait_on_page_write(struct fscache_cookie *, struct page *);
+
+/**
+ * fscache_register_netfs - Register a filesystem as desiring caching services
+ * @netfs: The description of the filesystem
+ *
+ * Register a filesystem as desiring caching services if they're available.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+int fscache_register_netfs(struct fscache_netfs *netfs)
+{
+ if (fscache_available())
+ return __fscache_register_netfs(netfs);
+ else
+ return 0;
+}
+
+/**
+ * fscache_unregister_netfs - Indicate that a filesystem no longer desires
+ * caching services
+ * @netfs: The description of the filesystem
+ *
+ * Indicate that a filesystem no longer desires caching services for the
+ * moment.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+void fscache_unregister_netfs(struct fscache_netfs *netfs)
+{
+ if (fscache_available())
+ __fscache_unregister_netfs(netfs);
+}
+
+/**
+ * fscache_lookup_cache_tag - Look up a cache tag
+ * @name: The name of the tag to search for
+ *
+ * Acquire a specific cache referral tag that can be used to select a specific
+ * cache in which to cache an index.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+struct fscache_cache_tag *fscache_lookup_cache_tag(const char *name)
+{
+ if (fscache_available())
+ return __fscache_lookup_cache_tag(name);
+ else
+ return NULL;
+}
+
+/**
+ * fscache_release_cache_tag - Release a cache tag
+ * @tag: The tag to release
+ *
+ * Release a reference to a cache referral tag previously looked up.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+void fscache_release_cache_tag(struct fscache_cache_tag *tag)
+{
+ if (fscache_available())
+ __fscache_release_cache_tag(tag);
+}
+
+/**
+ * fscache_acquire_cookie - Acquire a cookie to represent a cache object
+ * @parent: The cookie that's to be the parent of this one
+ * @def: A description of the cache object, including callback operations
+ * @netfs_data: An arbitrary piece of data to be kept in the cookie to
+ * represent the cache object to the netfs
+ *
+ * This function is used to inform FS-Cache about part of an index hierarchy
+ * that can be used to locate files. This is done by requesting a cookie for
+ * each index in the path to the file.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+struct fscache_cookie *fscache_acquire_cookie(
+ struct fscache_cookie *parent,
+ const struct fscache_cookie_def *def,
+ void *netfs_data)
+{
+ if (fscache_cookie_valid(parent))
+ return __fscache_acquire_cookie(parent, def, netfs_data);
+ else
+ return NULL;
+}
+
+/**
+ * fscache_relinquish_cookie - Return the cookie to the cache, maybe discarding
+ * it
+ * @cookie: The cookie being returned
+ * @retire: True if the cache object the cookie represents is to be discarded
+ *
+ * This function returns a cookie to the cache, forcibly discarding the
+ * associated cache object if retire is set to true.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+void fscache_relinquish_cookie(struct fscache_cookie *cookie, int retire)
+{
+ if (fscache_cookie_valid(cookie))
+ __fscache_relinquish_cookie(cookie, retire);
+}
+
+/**
+ * fscache_update_cookie - Request that a cache object be updated
+ * @cookie: The cookie representing the cache object
+ *
+ * Request an update of the index data for the cache object associated with the
+ * cookie.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+void fscache_update_cookie(struct fscache_cookie *cookie)
+{
+ if (fscache_cookie_valid(cookie))
+ __fscache_update_cookie(cookie);
+}
+
+/**
+ * fscache_pin_cookie - Pin a data-storage cache object in its cache
+ * @cookie: The cookie representing the cache object
+ *
+ * Permit data-storage cache objects to be pinned in the cache.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+int fscache_pin_cookie(struct fscache_cookie *cookie)
+{
+ return -ENOBUFS;
+}
+
+/**
+ * fscache_pin_cookie - Unpin a data-storage cache object in its cache
+ * @cookie: The cookie representing the cache object
+ *
+ * Permit data-storage cache objects to be unpinned from the cache.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+void fscache_unpin_cookie(struct fscache_cookie *cookie)
+{
+}
+
+/**
+ * fscache_attr_changed - Notify cache that an object's attributes changed
+ * @cookie: The cookie representing the cache object
+ *
+ * Send a notification to the cache indicating that an object's attributes have
+ * changed. This includes the data size. These attributes will be obtained
+ * through the get_attr() cookie definition op.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+int fscache_attr_changed(struct fscache_cookie *cookie)
+{
+ if (fscache_cookie_valid(cookie))
+ return __fscache_attr_changed(cookie);
+ else
+ return -ENOBUFS;
+}
+
+/**
+ * fscache_reserve_space - Reserve data space for a cached object
+ * @cookie: The cookie representing the cache object
+ * @i_size: The amount of space to be reserved
+ *
+ * Reserve an amount of space in the cache for the cache object attached to a
+ * cookie so that a write to that object within the space can always be
+ * honoured.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+int fscache_reserve_space(struct fscache_cookie *cookie, loff_t size)
+{
+ return -ENOBUFS;
+}
+
+/**
+ * fscache_read_or_alloc_page - Read a page from the cache or allocate a block
+ * in which to store it
+ * @cookie: The cookie representing the cache object
+ * @page: The netfs page to fill if possible
+ * @end_io_func: The callback to invoke when and if the page is filled
+ * @context: An arbitrary piece of data to pass on to end_io_func()
+ * @gfp: The conditions under which memory allocation should be made
+ *
+ * Read a page from the cache, or if that's not possible make a potential
+ * one-block reservation in the cache into which the page may be stored once
+ * fetched from the server.
+ *
+ * If the page is not backed by the cache object, or if it there's some reason
+ * it can't be, -ENOBUFS will be returned and nothing more will be done for
+ * that page.
+ *
+ * Else, if that page is backed by the cache, a read will be initiated directly
+ * to the netfs's page and 0 will be returned by this function. The
+ * end_io_func() callback will be invoked when the operation terminates on a
+ * completion or failure. Note that the callback may be invoked before the
+ * return.
+ *
+ * Else, if the page is unbacked, -ENODATA is returned and a block may have
+ * been allocated in the cache.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+int fscache_read_or_alloc_page(struct fscache_cookie *cookie,
+ struct page *page,
+ fscache_rw_complete_t end_io_func,
+ void *context,
+ gfp_t gfp)
+{
+ if (fscache_cookie_valid(cookie))
+ return __fscache_read_or_alloc_page(cookie, page, end_io_func,
+ context, gfp);
+ else
+ return -ENOBUFS;
+}
+
+/**
+ * fscache_read_or_alloc_pages - Read pages from the cache and/or allocate
+ * blocks in which to store them
+ * @cookie: The cookie representing the cache object
+ * @mapping: The netfs inode mapping to which the pages will be attached
+ * @pages: A list of potential netfs pages to be filled
+ * @end_io_func: The callback to invoke when and if each page is filled
+ * @context: An arbitrary piece of data to pass on to end_io_func()
+ * @gfp: The conditions under which memory allocation should be made
+ *
+ * Read a set of pages from the cache, or if that's not possible, attempt to
+ * make a potential one-block reservation for each page in the cache into which
+ * that page may be stored once fetched from the server.
+ *
+ * If some pages are not backed by the cache object, or if it there's some
+ * reason they can't be, -ENOBUFS will be returned and nothing more will be
+ * done for that pages.
+ *
+ * Else, if some of the pages are backed by the cache, a read will be initiated
+ * directly to the netfs's page and 0 will be returned by this function. The
+ * end_io_func() callback will be invoked when the operation terminates on a
+ * completion or failure. Note that the callback may be invoked before the
+ * return.
+ *
+ * Else, if a page is unbacked, -ENODATA is returned and a block may have
+ * been allocated in the cache.
+ *
+ * Because the function may want to return all of -ENOBUFS, -ENODATA and 0 in
+ * regard to different pages, the return values are prioritised in that order.
+ * Any pages submitted for reading are removed from the pages list.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+int fscache_read_or_alloc_pages(struct fscache_cookie *cookie,
+ struct address_space *mapping,
+ struct list_head *pages,
+ unsigned *nr_pages,
+ fscache_rw_complete_t end_io_func,
+ void *context,
+ gfp_t gfp)
+{
+ if (fscache_cookie_valid(cookie))
+ return __fscache_read_or_alloc_pages(cookie, mapping, pages,
+ nr_pages, end_io_func,
+ context, gfp);
+ else
+ return -ENOBUFS;
+}
+
+/**
+ * fscache_alloc_page - Allocate a block in which to store a page
+ * @cookie: The cookie representing the cache object
+ * @page: The netfs page to allocate a page for
+ * @gfp: The conditions under which memory allocation should be made
+ *
+ * Request Allocation a block in the cache in which to store a netfs page
+ * without retrieving any contents from the cache.
+ *
+ * If the page is not backed by a file then -ENOBUFS will be returned and
+ * nothing more will be done, and no reservation will be made.
+ *
+ * Else, a block will be allocated if one wasn't already, and 0 will be
+ * returned
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+int fscache_alloc_page(struct fscache_cookie *cookie,
+ struct page *page,
+ gfp_t gfp)
+{
+ if (fscache_cookie_valid(cookie))
+ return __fscache_alloc_page(cookie, page, gfp);
+ else
+ return -ENOBUFS;
+}
+
+/**
+ * fscache_write_page - Request storage of a page in the cache
+ * @cookie: The cookie representing the cache object
+ * @page: The netfs page to store
+ * @gfp: The conditions under which memory allocation should be made
+ *
+ * Request the contents of the netfs page be written into the cache. This
+ * request may be ignored if no cache block is currently allocated, in which
+ * case it will return -ENOBUFS.
+ *
+ * If a cache block was already allocated, a write will be initiated and 0 will
+ * be returned. The PG_fscache_write page bit is set immediately and will then
+ * be cleared at the completion of the write to indicate the success or failure
+ * of the operation. Note that the completion may happen before the return.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+int fscache_write_page(struct fscache_cookie *cookie,
+ struct page *page,
+ gfp_t gfp)
+{
+ if (fscache_cookie_valid(cookie))
+ return __fscache_write_page(cookie, page, gfp);
+ else
+ return -ENOBUFS;
+}
+
+/**
+ * fscache_uncache_page - Indicate that caching is no longer required on a page
+ * @cookie: The cookie representing the cache object
+ * @page: The netfs page that was being cached.
+ *
+ * Tell the cache that we no longer want a page to be cached and that it should
+ * remove any knowledge of the netfs page it may have.
+ *
+ * Note that this cannot cancel any outstanding I/O operations between this
+ * page and the cache.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+void fscache_uncache_page(struct fscache_cookie *cookie,
+ struct page *page)
+{
+ if (fscache_cookie_valid(cookie))
+ __fscache_uncache_page(cookie, page);
+}
+
+/**
+ * fscache_check_page_write - Ask if a page is being writing to the cache
+ * @cookie: The cookie representing the cache object
+ * @page: The netfs page that is being cached.
+ *
+ * Ask the cache if a page is being written to the cache.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+bool fscache_check_page_write(struct fscache_cookie *cookie,
+ struct page *page)
+{
+ if (fscache_cookie_valid(cookie))
+ return __fscache_check_page_write(cookie, page);
+ return false;
+}
+
+/**
+ * fscache_wait_on_page_write - Wait for a page to complete writing to the cache
+ * @cookie: The cookie representing the cache object
+ * @page: The netfs page that is being cached.
+ *
+ * Ask the cache to wake us up when a page is no longer being written to the
+ * cache.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+void fscache_wait_on_page_write(struct fscache_cookie *cookie,
+ struct page *page)
+{
+ if (fscache_cookie_valid(cookie))
+ __fscache_wait_on_page_write(cookie, page);
+}
+
+#endif /* _LINUX_FSCACHE_H */
diff --git a/include/linux/hdreg.h b/include/linux/hdreg.h
index ed21bd3dbd2..29ee2873f4a 100644
--- a/include/linux/hdreg.h
+++ b/include/linux/hdreg.h
@@ -1,68 +1,6 @@
#ifndef _LINUX_HDREG_H
#define _LINUX_HDREG_H
-#ifdef __KERNEL__
-#include <linux/ata.h>
-
-/*
- * This file contains some defines for the AT-hd-controller.
- * Various sources.
- */
-
-/* ide.c has its own port definitions in "ide.h" */
-
-#define HD_IRQ 14
-
-/* Hd controller regs. Ref: IBM AT Bios-listing */
-#define HD_DATA 0x1f0 /* _CTL when writing */
-#define HD_ERROR 0x1f1 /* see err-bits */
-#define HD_NSECTOR 0x1f2 /* nr of sectors to read/write */
-#define HD_SECTOR 0x1f3 /* starting sector */
-#define HD_LCYL 0x1f4 /* starting cylinder */
-#define HD_HCYL 0x1f5 /* high byte of starting cyl */
-#define HD_CURRENT 0x1f6 /* 101dhhhh , d=drive, hhhh=head */
-#define HD_STATUS 0x1f7 /* see status-bits */
-#define HD_FEATURE HD_ERROR /* same io address, read=error, write=feature */
-#define HD_PRECOMP HD_FEATURE /* obsolete use of this port - predates IDE */
-#define HD_COMMAND HD_STATUS /* same io address, read=status, write=cmd */
-
-#define HD_CMD 0x3f6 /* used for resets */
-#define HD_ALTSTATUS 0x3f6 /* same as HD_STATUS but doesn't clear irq */
-
-/* remainder is shared between hd.c, ide.c, ide-cd.c, and the hdparm utility */
-
-/* Bits of HD_STATUS */
-#define ERR_STAT 0x01
-#define INDEX_STAT 0x02
-#define ECC_STAT 0x04 /* Corrected error */
-#define DRQ_STAT 0x08
-#define SEEK_STAT 0x10
-#define SRV_STAT 0x10
-#define WRERR_STAT 0x20
-#define READY_STAT 0x40
-#define BUSY_STAT 0x80
-
-/* Bits for HD_ERROR */
-#define MARK_ERR 0x01 /* Bad address mark */
-#define ILI_ERR 0x01 /* Illegal Length Indication (ATAPI) */
-#define TRK0_ERR 0x02 /* couldn't find track 0 */
-#define EOM_ERR 0x02 /* End Of Media (ATAPI) */
-#define ABRT_ERR 0x04 /* Command aborted */
-#define MCR_ERR 0x08 /* media change request */
-#define ID_ERR 0x10 /* ID field not found */
-#define MC_ERR 0x20 /* media changed */
-#define ECC_ERR 0x40 /* Uncorrectable ECC error */
-#define BBD_ERR 0x80 /* pre-EIDE meaning: block marked bad */
-#define ICRC_ERR 0x80 /* new meaning: CRC error during transfer */
-#define LFS_ERR 0xf0 /* Last Failed Sense (ATAPI) */
-
-/* Bits of HD_NSECTOR */
-#define CD 0x01
-#define IO 0x02
-#define REL 0x04
-#define TAG_MASK 0xf8
-#endif /* __KERNEL__ */
-
#include <linux/types.h>
/*
@@ -191,6 +129,7 @@ typedef struct hd_drive_hob_hdr {
#define TASKFILE_INVALID 0x7fff
#endif
+#ifndef __KERNEL__
/* ATA/ATAPI Commands pre T13 Spec */
#define WIN_NOP 0x00
/*
@@ -379,6 +318,7 @@ typedef struct hd_drive_hob_hdr {
#define SECURITY_ERASE_UNIT 0xBD
#define SECURITY_FREEZE_LOCK 0xBE
#define SECURITY_DISABLE_PASSWORD 0xBF
+#endif /* __KERNEL__ */
struct hd_geometry {
unsigned char heads;
@@ -448,6 +388,7 @@ enum {
#define __NEW_HD_DRIVE_ID
+#ifndef __KERNEL__
/*
* Structure returned by HDIO_GET_IDENTITY, as per ANSI NCITS ATA6 rev.1b spec.
*
@@ -699,6 +640,7 @@ struct hd_driveid {
* 7:0 Signature
*/
};
+#endif /* __KERNEL__ */
/*
* IDE "nice" flags. These are used on a per drive basis to determine
diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index 7ff5c55f9b5..1fcb7126a01 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -19,8 +19,21 @@ static inline void flush_kernel_dcache_page(struct page *page)
}
#endif
-#ifdef CONFIG_HIGHMEM
+#include <asm/kmap_types.h>
+
+#if defined(CONFIG_DEBUG_HIGHMEM) && defined(CONFIG_TRACE_IRQFLAGS_SUPPORT)
+
+void debug_kmap_atomic(enum km_type type);
+
+#else
+static inline void debug_kmap_atomic(enum km_type type)
+{
+}
+
+#endif
+
+#ifdef CONFIG_HIGHMEM
#include <asm/highmem.h>
/* declarations for linux/mm/highmem.c */
@@ -44,8 +57,6 @@ static inline void *kmap(struct page *page)
#define kunmap(page) do { (void) (page); } while (0)
-#include <asm/kmap_types.h>
-
static inline void *kmap_atomic(struct page *page, enum km_type idx)
{
pagefault_disable();
@@ -187,16 +198,4 @@ static inline void copy_highpage(struct page *to, struct page *from)
kunmap_atomic(vto, KM_USER1);
}
-#if defined(CONFIG_DEBUG_HIGHMEM) && defined(CONFIG_TRACE_IRQFLAGS_SUPPORT)
-
-void debug_kmap_atomic(enum km_type type);
-
-#else
-
-static inline void debug_kmap_atomic(enum km_type type)
-{
-}
-
-#endif
-
#endif /* _LINUX_HIGHMEM_H */
diff --git a/include/linux/i2c/twl4030.h b/include/linux/i2c/twl4030.h
index 8137f660a5c..0dc80ef2497 100644
--- a/include/linux/i2c/twl4030.h
+++ b/include/linux/i2c/twl4030.h
@@ -218,6 +218,53 @@ int twl4030_i2c_read(u8 mod_no, u8 *value, u8 reg, unsigned num_bytes);
/*----------------------------------------------------------------------*/
+/* Power bus message definitions */
+
+#define DEV_GRP_NULL 0x0
+#define DEV_GRP_P1 0x1
+#define DEV_GRP_P2 0x2
+#define DEV_GRP_P3 0x4
+
+#define RES_GRP_RES 0x0
+#define RES_GRP_PP 0x1
+#define RES_GRP_RC 0x2
+#define RES_GRP_PP_RC 0x3
+#define RES_GRP_PR 0x4
+#define RES_GRP_PP_PR 0x5
+#define RES_GRP_RC_PR 0x6
+#define RES_GRP_ALL 0x7
+
+#define RES_TYPE2_R0 0x0
+
+#define RES_TYPE_ALL 0x7
+
+#define RES_STATE_WRST 0xF
+#define RES_STATE_ACTIVE 0xE
+#define RES_STATE_SLEEP 0x8
+#define RES_STATE_OFF 0x0
+
+/*
+ * Power Bus Message Format ... these can be sent individually by Linux,
+ * but are usually part of downloaded scripts that are run when various
+ * power events are triggered.
+ *
+ * Broadcast Message (16 Bits):
+ * DEV_GRP[15:13] MT[12] RES_GRP[11:9] RES_TYPE2[8:7] RES_TYPE[6:4]
+ * RES_STATE[3:0]
+ *
+ * Singular Message (16 Bits):
+ * DEV_GRP[15:13] MT[12] RES_ID[11:4] RES_STATE[3:0]
+ */
+
+#define MSG_BROADCAST(devgrp, grp, type, type2, state) \
+ ( (devgrp) << 13 | 1 << 12 | (grp) << 9 | (type2) << 7 \
+ | (type) << 4 | (state))
+
+#define MSG_SINGULAR(devgrp, id, state) \
+ ((devgrp) << 13 | 0 << 12 | (id) << 4 | (state))
+
+/*----------------------------------------------------------------------*/
+
struct twl4030_bci_platform_data {
int *battery_tmp_tbl;
unsigned int tblsize;
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index 1d6c71d96ed..77214ead1a3 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -123,7 +123,7 @@ static inline void dmar_writeq(void __iomem *addr, u64 val)
#define ecap_eim_support(e) ((e >> 4) & 0x1)
#define ecap_ir_support(e) ((e >> 3) & 0x1)
#define ecap_max_handle_mask(e) ((e >> 20) & 0xf)
-
+#define ecap_sc_support(e) ((e >> 7) & 0x1) /* Snooping Control */
/* IOTLB_REG */
#define DMA_TLB_FLUSH_GRANU_OFFSET 60
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 8a7bfb1b6ca..3af4ffd591b 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -21,6 +21,7 @@
#define IOMMU_READ (1)
#define IOMMU_WRITE (2)
+#define IOMMU_CACHE (4) /* DMA cache coherency */
struct device;
@@ -28,6 +29,8 @@ struct iommu_domain {
void *priv;
};
+#define IOMMU_CAP_CACHE_COHERENCY 0x1
+
struct iommu_ops {
int (*domain_init)(struct iommu_domain *domain);
void (*domain_destroy)(struct iommu_domain *domain);
@@ -39,6 +42,8 @@ struct iommu_ops {
size_t size);
phys_addr_t (*iova_to_phys)(struct iommu_domain *domain,
unsigned long iova);
+ int (*domain_has_cap)(struct iommu_domain *domain,
+ unsigned long cap);
};
#ifdef CONFIG_IOMMU_API
@@ -57,6 +62,8 @@ extern void iommu_unmap_range(struct iommu_domain *domain, unsigned long iova,
size_t size);
extern phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain,
unsigned long iova);
+extern int iommu_domain_has_cap(struct iommu_domain *domain,
+ unsigned long cap);
#else /* CONFIG_IOMMU_API */
@@ -107,6 +114,12 @@ static inline phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain,
return 0;
}
+static inline int domain_has_cap(struct iommu_domain *domain,
+ unsigned long cap)
+{
+ return 0;
+}
+
#endif /* CONFIG_IOMMU_API */
#endif /* __LINUX_IOMMU_H */
diff --git a/include/linux/jbd.h b/include/linux/jbd.h
index 64246dce566..2c6943152c2 100644
--- a/include/linux/jbd.h
+++ b/include/linux/jbd.h
@@ -552,6 +552,11 @@ struct transaction_s
*/
int t_handle_count;
+ /*
+ * This transaction is being forced and some process is
+ * waiting for it to finish.
+ */
+ int t_synchronous_commit:1;
};
/**
diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h
index 4e457256bd3..3e7615e9087 100644
--- a/include/linux/mmc/host.h
+++ b/include/linux/mmc/host.h
@@ -192,5 +192,10 @@ static inline void mmc_signal_sdio_irq(struct mmc_host *host)
wake_up_process(host->sdio_irq_thread);
}
+struct regulator;
+
+int mmc_regulator_get_ocrmask(struct regulator *supply);
+int mmc_regulator_set_ocr(struct regulator *supply, unsigned short vdd_bit);
+
#endif
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index bde2557c2a9..fdffb413b19 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -185,6 +185,9 @@ struct nfs_inode {
fmode_t delegation_state;
struct rw_semaphore rwsem;
#endif /* CONFIG_NFS_V4*/
+#ifdef CONFIG_NFS_FSCACHE
+ struct fscache_cookie *fscache;
+#endif
struct inode vfs_inode;
};
@@ -207,6 +210,8 @@ struct nfs_inode {
#define NFS_INO_ACL_LRU_SET (2) /* Inode is on the LRU list */
#define NFS_INO_MOUNTPOINT (3) /* inode is remote mountpoint */
#define NFS_INO_FLUSHING (4) /* inode is flushing out data */
+#define NFS_INO_FSCACHE (5) /* inode can be cached by FS-Cache */
+#define NFS_INO_FSCACHE_LOCK (6) /* FS-Cache cookie management lock */
static inline struct nfs_inode *NFS_I(const struct inode *inode)
{
@@ -260,6 +265,11 @@ static inline int NFS_STALE(const struct inode *inode)
return test_bit(NFS_INO_STALE, &NFS_I(inode)->flags);
}
+static inline int NFS_FSCACHE(const struct inode *inode)
+{
+ return test_bit(NFS_INO_FSCACHE, &NFS_I(inode)->flags);
+}
+
static inline __u64 NFS_FILEID(const struct inode *inode)
{
return NFS_I(inode)->fileid;
@@ -506,6 +516,8 @@ extern int nfs_readpages(struct file *, struct address_space *,
struct list_head *, unsigned);
extern int nfs_readpage_result(struct rpc_task *, struct nfs_read_data *);
extern void nfs_readdata_release(void *data);
+extern int nfs_readpage_async(struct nfs_open_context *, struct inode *,
+ struct page *);
/*
* Allocate nfs_read_data structures
@@ -583,6 +595,7 @@ extern void * nfs_root_data(void);
#define NFSDBG_CALLBACK 0x0100
#define NFSDBG_CLIENT 0x0200
#define NFSDBG_MOUNT 0x0400
+#define NFSDBG_FSCACHE 0x0800
#define NFSDBG_ALL 0xFFFF
#ifdef __KERNEL__
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index 29b1e40dce9..6ad75948cbf 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -64,6 +64,10 @@ struct nfs_client {
char cl_ipaddr[48];
unsigned char cl_id_uniquifier;
#endif
+
+#ifdef CONFIG_NFS_FSCACHE
+ struct fscache_cookie *fscache; /* client index cache cookie */
+#endif
};
/*
@@ -96,12 +100,19 @@ struct nfs_server {
unsigned int acdirmin;
unsigned int acdirmax;
unsigned int namelen;
+ unsigned int options; /* extra options enabled by mount */
+#define NFS_OPTION_FSCACHE 0x00000001 /* - local caching enabled */
struct nfs_fsid fsid;
__u64 maxfilesize; /* maximum file size */
unsigned long mount_time; /* when this fs was mounted */
dev_t s_dev; /* superblock dev numbers */
+#ifdef CONFIG_NFS_FSCACHE
+ struct nfs_fscache_key *fscache_key; /* unique key for superblock */
+ struct fscache_cookie *fscache; /* superblock cookie */
+#endif
+
#ifdef CONFIG_NFS_V4
u32 attr_bitmask[2];/* V4 bitmask representing the set
of attributes supported on this
diff --git a/include/linux/nfs_iostat.h b/include/linux/nfs_iostat.h
index 1cb9a3fed2b..68b10f5f890 100644
--- a/include/linux/nfs_iostat.h
+++ b/include/linux/nfs_iostat.h
@@ -116,4 +116,16 @@ enum nfs_stat_eventcounters {
__NFSIOS_COUNTSMAX,
};
+/*
+ * NFS local caching servicing counters
+ */
+enum nfs_stat_fscachecounters {
+ NFSIOS_FSCACHE_PAGES_READ_OK,
+ NFSIOS_FSCACHE_PAGES_READ_FAIL,
+ NFSIOS_FSCACHE_PAGES_WRITTEN_OK,
+ NFSIOS_FSCACHE_PAGES_WRITTEN_FAIL,
+ NFSIOS_FSCACHE_PAGES_UNCACHED,
+ __NFSIOS_FSCACHEMAX,
+};
+
#endif /* _LINUX_NFS_IOSTAT */
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 61df1779b2a..62214c7d2d9 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -82,6 +82,7 @@ enum pageflags {
PG_arch_1,
PG_reserved,
PG_private, /* If pagecache, has fs-private data */
+ PG_private_2, /* If pagecache, has fs aux data */
PG_writeback, /* Page is under writeback */
#ifdef CONFIG_PAGEFLAGS_EXTENDED
PG_head, /* A head page */
@@ -108,6 +109,12 @@ enum pageflags {
/* Filesystems */
PG_checked = PG_owner_priv_1,
+ /* Two page bits are conscripted by FS-Cache to maintain local caching
+ * state. These bits are set on pages belonging to the netfs's inodes
+ * when those inodes are being locally cached.
+ */
+ PG_fscache = PG_private_2, /* page backed by cache */
+
/* XEN */
PG_pinned = PG_owner_priv_1,
PG_savepinned = PG_dirty,
@@ -182,7 +189,7 @@ static inline int TestClearPage##uname(struct page *page) { return 0; }
struct page; /* forward declaration */
-TESTPAGEFLAG(Locked, locked)
+TESTPAGEFLAG(Locked, locked) TESTSETFLAG(Locked, locked)
PAGEFLAG(Error, error)
PAGEFLAG(Referenced, referenced) TESTCLEARFLAG(Referenced, referenced)
PAGEFLAG(Dirty, dirty) TESTSCFLAG(Dirty, dirty) __CLEARPAGEFLAG(Dirty, dirty)
@@ -194,8 +201,6 @@ PAGEFLAG(Checked, checked) /* Used by some filesystems */
PAGEFLAG(Pinned, pinned) TESTSCFLAG(Pinned, pinned) /* Xen */
PAGEFLAG(SavePinned, savepinned); /* Xen */
PAGEFLAG(Reserved, reserved) __CLEARPAGEFLAG(Reserved, reserved)
-PAGEFLAG(Private, private) __CLEARPAGEFLAG(Private, private)
- __SETPAGEFLAG(Private, private)
PAGEFLAG(SwapBacked, swapbacked) __CLEARPAGEFLAG(SwapBacked, swapbacked)
__PAGEFLAG(SlobPage, slob_page)
@@ -205,6 +210,16 @@ __PAGEFLAG(SlubFrozen, slub_frozen)
__PAGEFLAG(SlubDebug, slub_debug)
/*
+ * Private page markings that may be used by the filesystem that owns the page
+ * for its own purposes.
+ * - PG_private and PG_private_2 cause releasepage() and co to be invoked
+ */
+PAGEFLAG(Private, private) __SETPAGEFLAG(Private, private)
+ __CLEARPAGEFLAG(Private, private)
+PAGEFLAG(Private2, private_2) TESTSCFLAG(Private2, private_2)
+PAGEFLAG(OwnerPriv1, owner_priv_1) TESTCLEARFLAG(OwnerPriv1, owner_priv_1)
+
+/*
* Only test-and-set exist for PG_writeback. The unconditional operators are
* risky: they bypass page accounting.
*/
@@ -384,9 +399,10 @@ static inline void __ClearPageTail(struct page *page)
* these flags set. It they are, there is a problem.
*/
#define PAGE_FLAGS_CHECK_AT_FREE \
- (1 << PG_lru | 1 << PG_private | 1 << PG_locked | \
- 1 << PG_buddy | 1 << PG_writeback | 1 << PG_reserved | \
- 1 << PG_slab | 1 << PG_swapcache | 1 << PG_active | \
+ (1 << PG_lru | 1 << PG_locked | \
+ 1 << PG_private | 1 << PG_private_2 | \
+ 1 << PG_buddy | 1 << PG_writeback | 1 << PG_reserved | \
+ 1 << PG_slab | 1 << PG_swapcache | 1 << PG_active | \
__PG_UNEVICTABLE | __PG_MLOCKED)
/*
@@ -397,4 +413,16 @@ static inline void __ClearPageTail(struct page *page)
#define PAGE_FLAGS_CHECK_AT_PREP ((1 << NR_PAGEFLAGS) - 1)
#endif /* !__GENERATING_BOUNDS_H */
+
+/**
+ * page_has_private - Determine if page has private stuff
+ * @page: The page to be checked
+ *
+ * Determine if a page has private stuff, indicating that release routines
+ * should be invoked upon it.
+ */
+#define page_has_private(page) \
+ ((page)->flags & ((1 << PG_private) | \
+ (1 << PG_private_2)))
+
#endif /* PAGE_FLAGS_H */
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 076a7dc67c2..34da5230faa 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -384,6 +384,11 @@ static inline void wait_on_page_writeback(struct page *page)
extern void end_page_writeback(struct page *page);
/*
+ * Add an arbitrary waiter to a page's wait queue
+ */
+extern void add_page_wait_queue(struct page *page, wait_queue_t *waiter);
+
+/*
* Fault a userspace page into pagetables. Return non-zero on a fault.
*
* This assumes that two userspace pages are always sufficient. That's
diff --git a/include/linux/raid/bitmap.h b/include/linux/raid/bitmap.h
deleted file mode 100644
index e98900671ca..00000000000
--- a/include/linux/raid/bitmap.h
+++ /dev/null
@@ -1,288 +0,0 @@
-/*
- * bitmap.h: Copyright (C) Peter T. Breuer (ptb@ot.uc3m.es) 2003
- *
- * additions: Copyright (C) 2003-2004, Paul Clements, SteelEye Technology, Inc.
- */
-#ifndef BITMAP_H
-#define BITMAP_H 1
-
-#define BITMAP_MAJOR_LO 3
-/* version 4 insists the bitmap is in little-endian order
- * with version 3, it is host-endian which is non-portable
- */
-#define BITMAP_MAJOR_HI 4
-#define BITMAP_MAJOR_HOSTENDIAN 3
-
-#define BITMAP_MINOR 39
-
-/*
- * in-memory bitmap:
- *
- * Use 16 bit block counters to track pending writes to each "chunk".
- * The 2 high order bits are special-purpose, the first is a flag indicating
- * whether a resync is needed. The second is a flag indicating whether a
- * resync is active.
- * This means that the counter is actually 14 bits:
- *
- * +--------+--------+------------------------------------------------+
- * | resync | resync | counter |
- * | needed | active | |
- * | (0-1) | (0-1) | (0-16383) |
- * +--------+--------+------------------------------------------------+
- *
- * The "resync needed" bit is set when:
- * a '1' bit is read from storage at startup.
- * a write request fails on some drives
- * a resync is aborted on a chunk with 'resync active' set
- * It is cleared (and resync-active set) when a resync starts across all drives
- * of the chunk.
- *
- *
- * The "resync active" bit is set when:
- * a resync is started on all drives, and resync_needed is set.
- * resync_needed will be cleared (as long as resync_active wasn't already set).
- * It is cleared when a resync completes.
- *
- * The counter counts pending write requests, plus the on-disk bit.
- * When the counter is '1' and the resync bits are clear, the on-disk
- * bit can be cleared aswell, thus setting the counter to 0.
- * When we set a bit, or in the counter (to start a write), if the fields is
- * 0, we first set the disk bit and set the counter to 1.
- *
- * If the counter is 0, the on-disk bit is clear and the stipe is clean
- * Anything that dirties the stipe pushes the counter to 2 (at least)
- * and sets the on-disk bit (lazily).
- * If a periodic sweep find the counter at 2, it is decremented to 1.
- * If the sweep find the counter at 1, the on-disk bit is cleared and the
- * counter goes to zero.
- *
- * Also, we'll hijack the "map" pointer itself and use it as two 16 bit block
- * counters as a fallback when "page" memory cannot be allocated:
- *
- * Normal case (page memory allocated):
- *
- * page pointer (32-bit)
- *
- * [ ] ------+
- * |
- * +-------> [ ][ ]..[ ] (4096 byte page == 2048 counters)
- * c1 c2 c2048
- *
- * Hijacked case (page memory allocation failed):
- *
- * hijacked page pointer (32-bit)
- *
- * [ ][ ] (no page memory allocated)
- * counter #1 (16-bit) counter #2 (16-bit)
- *
- */
-
-#ifdef __KERNEL__
-
-#define PAGE_BITS (PAGE_SIZE << 3)
-#define PAGE_BIT_SHIFT (PAGE_SHIFT + 3)
-
-typedef __u16 bitmap_counter_t;
-#define COUNTER_BITS 16
-#define COUNTER_BIT_SHIFT 4
-#define COUNTER_BYTE_RATIO (COUNTER_BITS / 8)
-#define COUNTER_BYTE_SHIFT (COUNTER_BIT_SHIFT - 3)
-
-#define NEEDED_MASK ((bitmap_counter_t) (1 << (COUNTER_BITS - 1)))
-#define RESYNC_MASK ((bitmap_counter_t) (1 << (COUNTER_BITS - 2)))
-#define COUNTER_MAX ((bitmap_counter_t) RESYNC_MASK - 1)
-#define NEEDED(x) (((bitmap_counter_t) x) & NEEDED_MASK)
-#define RESYNC(x) (((bitmap_counter_t) x) & RESYNC_MASK)
-#define COUNTER(x) (((bitmap_counter_t) x) & COUNTER_MAX)
-
-/* how many counters per page? */
-#define PAGE_COUNTER_RATIO (PAGE_BITS / COUNTER_BITS)
-/* same, except a shift value for more efficient bitops */
-#define PAGE_COUNTER_SHIFT (PAGE_BIT_SHIFT - COUNTER_BIT_SHIFT)
-/* same, except a mask value for more efficient bitops */
-#define PAGE_COUNTER_MASK (PAGE_COUNTER_RATIO - 1)
-
-#define BITMAP_BLOCK_SIZE 512
-#define BITMAP_BLOCK_SHIFT 9
-
-/* how many blocks per chunk? (this is variable) */
-#define CHUNK_BLOCK_RATIO(bitmap) ((bitmap)->chunksize >> BITMAP_BLOCK_SHIFT)
-#define CHUNK_BLOCK_SHIFT(bitmap) ((bitmap)->chunkshift - BITMAP_BLOCK_SHIFT)
-#define CHUNK_BLOCK_MASK(bitmap) (CHUNK_BLOCK_RATIO(bitmap) - 1)
-
-/* when hijacked, the counters and bits represent even larger "chunks" */
-/* there will be 1024 chunks represented by each counter in the page pointers */
-#define PAGEPTR_BLOCK_RATIO(bitmap) \
- (CHUNK_BLOCK_RATIO(bitmap) << PAGE_COUNTER_SHIFT >> 1)
-#define PAGEPTR_BLOCK_SHIFT(bitmap) \
- (CHUNK_BLOCK_SHIFT(bitmap) + PAGE_COUNTER_SHIFT - 1)
-#define PAGEPTR_BLOCK_MASK(bitmap) (PAGEPTR_BLOCK_RATIO(bitmap) - 1)
-
-/*
- * on-disk bitmap:
- *
- * Use one bit per "chunk" (block set). We do the disk I/O on the bitmap
- * file a page at a time. There's a superblock at the start of the file.
- */
-
-/* map chunks (bits) to file pages - offset by the size of the superblock */
-#define CHUNK_BIT_OFFSET(chunk) ((chunk) + (sizeof(bitmap_super_t) << 3))
-
-#endif
-
-/*
- * bitmap structures:
- */
-
-#define BITMAP_MAGIC 0x6d746962
-
-/* use these for bitmap->flags and bitmap->sb->state bit-fields */
-enum bitmap_state {
- BITMAP_STALE = 0x002, /* the bitmap file is out of date or had -EIO */
- BITMAP_WRITE_ERROR = 0x004, /* A write error has occurred */
- BITMAP_HOSTENDIAN = 0x8000,
-};
-
-/* the superblock at the front of the bitmap file -- little endian */
-typedef struct bitmap_super_s {
- __le32 magic; /* 0 BITMAP_MAGIC */
- __le32 version; /* 4 the bitmap major for now, could change... */
- __u8 uuid[16]; /* 8 128 bit uuid - must match md device uuid */
- __le64 events; /* 24 event counter for the bitmap (1)*/
- __le64 events_cleared;/*32 event counter when last bit cleared (2) */
- __le64 sync_size; /* 40 the size of the md device's sync range(3) */
- __le32 state; /* 48 bitmap state information */
- __le32 chunksize; /* 52 the bitmap chunk size in bytes */
- __le32 daemon_sleep; /* 56 seconds between disk flushes */
- __le32 write_behind; /* 60 number of outstanding write-behind writes */
-
- __u8 pad[256 - 64]; /* set to zero */
-} bitmap_super_t;
-
-/* notes:
- * (1) This event counter is updated before the eventcounter in the md superblock
- * When a bitmap is loaded, it is only accepted if this event counter is equal
- * to, or one greater than, the event counter in the superblock.
- * (2) This event counter is updated when the other one is *if*and*only*if* the
- * array is not degraded. As bits are not cleared when the array is degraded,
- * this represents the last time that any bits were cleared.
- * If a device is being added that has an event count with this value or
- * higher, it is accepted as conforming to the bitmap.
- * (3)This is the number of sectors represented by the bitmap, and is the range that
- * resync happens across. For raid1 and raid5/6 it is the size of individual
- * devices. For raid10 it is the size of the array.
- */
-
-#ifdef __KERNEL__
-
-/* the in-memory bitmap is represented by bitmap_pages */
-struct bitmap_page {
- /*
- * map points to the actual memory page
- */
- char *map;
- /*
- * in emergencies (when map cannot be alloced), hijack the map
- * pointer and use it as two counters itself
- */
- unsigned int hijacked:1;
- /*
- * count of dirty bits on the page
- */
- unsigned int count:31;
-};
-
-/* keep track of bitmap file pages that have pending writes on them */
-struct page_list {
- struct list_head list;
- struct page *page;
-};
-
-/* the main bitmap structure - one per mddev */
-struct bitmap {
- struct bitmap_page *bp;
- unsigned long pages; /* total number of pages in the bitmap */
- unsigned long missing_pages; /* number of pages not yet allocated */
-
- mddev_t *mddev; /* the md device that the bitmap is for */
-
- int counter_bits; /* how many bits per block counter */
-
- /* bitmap chunksize -- how much data does each bit represent? */
- unsigned long chunksize;
- unsigned long chunkshift; /* chunksize = 2^chunkshift (for bitops) */
- unsigned long chunks; /* total number of data chunks for the array */
-
- /* We hold a count on the chunk currently being synced, and drop
- * it when the last block is started. If the resync is aborted
- * midway, we need to be able to drop that count, so we remember
- * the counted chunk..
- */
- unsigned long syncchunk;
-
- __u64 events_cleared;
- int need_sync;
-
- /* bitmap spinlock */
- spinlock_t lock;
-
- long offset; /* offset from superblock if file is NULL */
- struct file *file; /* backing disk file */
- struct page *sb_page; /* cached copy of the bitmap file superblock */
- struct page **filemap; /* list of cache pages for the file */
- unsigned long *filemap_attr; /* attributes associated w/ filemap pages */
- unsigned long file_pages; /* number of pages in the file */
- int last_page_size; /* bytes in the last page */
-
- unsigned long flags;
-
- int allclean;
-
- unsigned long max_write_behind; /* write-behind mode */
- atomic_t behind_writes;
-
- /*
- * the bitmap daemon - periodically wakes up and sweeps the bitmap
- * file, cleaning up bits and flushing out pages to disk as necessary
- */
- unsigned long daemon_lastrun; /* jiffies of last run */
- unsigned long daemon_sleep; /* how many seconds between updates? */
- unsigned long last_end_sync; /* when we lasted called end_sync to
- * update bitmap with resync progress */
-
- atomic_t pending_writes; /* pending writes to the bitmap file */
- wait_queue_head_t write_wait;
- wait_queue_head_t overflow_wait;
-
-};
-
-/* the bitmap API */
-
-/* these are used only by md/bitmap */
-int bitmap_create(mddev_t *mddev);
-void bitmap_flush(mddev_t *mddev);
-void bitmap_destroy(mddev_t *mddev);
-
-void bitmap_print_sb(struct bitmap *bitmap);
-void bitmap_update_sb(struct bitmap *bitmap);
-
-int bitmap_setallbits(struct bitmap *bitmap);
-void bitmap_write_all(struct bitmap *bitmap);
-
-void bitmap_dirty_bits(struct bitmap *bitmap, unsigned long s, unsigned long e);
-
-/* these are exported */
-int bitmap_startwrite(struct bitmap *bitmap, sector_t offset,
- unsigned long sectors, int behind);
-void bitmap_endwrite(struct bitmap *bitmap, sector_t offset,
- unsigned long sectors, int success, int behind);
-int bitmap_start_sync(struct bitmap *bitmap, sector_t offset, int *blocks, int degraded);
-void bitmap_end_sync(struct bitmap *bitmap, sector_t offset, int *blocks, int aborted);
-void bitmap_close_sync(struct bitmap *bitmap);
-void bitmap_cond_end_sync(struct bitmap *bitmap, sector_t sector);
-
-void bitmap_unplug(struct bitmap *bitmap);
-void bitmap_daemon_work(struct bitmap *bitmap);
-#endif
-
-#endif
diff --git a/include/linux/raid/linear.h b/include/linux/raid/linear.h
deleted file mode 100644
index f38b9c586af..00000000000
--- a/include/linux/raid/linear.h
+++ /dev/null
@@ -1,31 +0,0 @@
-#ifndef _LINEAR_H
-#define _LINEAR_H
-
-#include <linux/raid/md.h>
-
-struct dev_info {
- mdk_rdev_t *rdev;
- sector_t num_sectors;
- sector_t start_sector;
-};
-
-typedef struct dev_info dev_info_t;
-
-struct linear_private_data
-{
- struct linear_private_data *prev; /* earlier version */
- dev_info_t **hash_table;
- sector_t spacing;
- sector_t array_sectors;
- int sector_shift; /* shift before dividing
- * by spacing
- */
- dev_info_t disks[0];
-};
-
-
-typedef struct linear_private_data linear_conf_t;
-
-#define mddev_to_conf(mddev) ((linear_conf_t *) mddev->private)
-
-#endif
diff --git a/include/linux/raid/md.h b/include/linux/raid/md.h
deleted file mode 100644
index 82bea14cae1..00000000000
--- a/include/linux/raid/md.h
+++ /dev/null
@@ -1,81 +0,0 @@
-/*
- md.h : Multiple Devices driver for Linux
- Copyright (C) 1996-98 Ingo Molnar, Gadi Oxman
- Copyright (C) 1994-96 Marc ZYNGIER
- <zyngier@ufr-info-p7.ibp.fr> or
- <maz@gloups.fdn.fr>
-
- This program is free software; you can redistribute it and/or modify
- it under the terms of the GNU General Public License as published by
- the Free Software Foundation; either version 2, or (at your option)
- any later version.
-
- You should have received a copy of the GNU General Public License
- (for example /usr/src/linux/COPYING); if not, write to the Free
- Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
-*/
-
-#ifndef _MD_H
-#define _MD_H
-
-#include <linux/blkdev.h>
-#include <linux/seq_file.h>
-
-/*
- * 'md_p.h' holds the 'physical' layout of RAID devices
- * 'md_u.h' holds the user <=> kernel API
- *
- * 'md_k.h' holds kernel internal definitions
- */
-
-#include <linux/raid/md_p.h>
-#include <linux/raid/md_u.h>
-#include <linux/raid/md_k.h>
-
-#ifdef CONFIG_MD
-
-/*
- * Different major versions are not compatible.
- * Different minor versions are only downward compatible.
- * Different patchlevel versions are downward and upward compatible.
- */
-#define MD_MAJOR_VERSION 0
-#define MD_MINOR_VERSION 90
-/*
- * MD_PATCHLEVEL_VERSION indicates kernel functionality.
- * >=1 means different superblock formats are selectable using SET_ARRAY_INFO
- * and major_version/minor_version accordingly
- * >=2 means that Internal bitmaps are supported by setting MD_SB_BITMAP_PRESENT
- * in the super status byte
- * >=3 means that bitmap superblock version 4 is supported, which uses
- * little-ending representation rather than host-endian
- */
-#define MD_PATCHLEVEL_VERSION 3
-
-extern int mdp_major;
-
-extern int register_md_personality(struct mdk_personality *p);
-extern int unregister_md_personality(struct mdk_personality *p);
-extern mdk_thread_t * md_register_thread(void (*run) (mddev_t *mddev),
- mddev_t *mddev, const char *name);
-extern void md_unregister_thread(mdk_thread_t *thread);
-extern void md_wakeup_thread(mdk_thread_t *thread);
-extern void md_check_recovery(mddev_t *mddev);
-extern void md_write_start(mddev_t *mddev, struct bio *bi);
-extern void md_write_end(mddev_t *mddev);
-extern void md_done_sync(mddev_t *mddev, int blocks, int ok);
-extern void md_error(mddev_t *mddev, mdk_rdev_t *rdev);
-
-extern void md_super_write(mddev_t *mddev, mdk_rdev_t *rdev,
- sector_t sector, int size, struct page *page);
-extern void md_super_wait(mddev_t *mddev);
-extern int sync_page_io(struct block_device *bdev, sector_t sector, int size,
- struct page *page, int rw);
-extern void md_do_sync(mddev_t *mddev);
-extern void md_new_event(mddev_t *mddev);
-extern int md_allow_write(mddev_t *mddev);
-extern void md_wait_for_blocked_rdev(mdk_rdev_t *rdev, mddev_t *mddev);
-
-#endif /* CONFIG_MD */
-#endif
-
diff --git a/include/linux/raid/md_k.h b/include/linux/raid/md_k.h
deleted file mode 100644
index 9743e4dbc91..00000000000
--- a/include/linux/raid/md_k.h
+++ /dev/null
@@ -1,402 +0,0 @@
-/*
- md_k.h : kernel internal structure of the Linux MD driver
- Copyright (C) 1996-98 Ingo Molnar, Gadi Oxman
-
- This program is free software; you can redistribute it and/or modify
- it under the terms of the GNU General Public License as published by
- the Free Software Foundation; either version 2, or (at your option)
- any later version.
-
- You should have received a copy of the GNU General Public License
- (for example /usr/src/linux/COPYING); if not, write to the Free
- Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
-*/
-
-#ifndef _MD_K_H
-#define _MD_K_H
-
-/* and dm-bio-list.h is not under include/linux because.... ??? */
-#include "../../../drivers/md/dm-bio-list.h"
-
-#ifdef CONFIG_BLOCK
-
-#define LEVEL_MULTIPATH (-4)
-#define LEVEL_LINEAR (-1)
-#define LEVEL_FAULTY (-5)
-
-/* we need a value for 'no level specified' and 0
- * means 'raid0', so we need something else. This is
- * for internal use only
- */
-#define LEVEL_NONE (-1000000)
-
-#define MaxSector (~(sector_t)0)
-
-typedef struct mddev_s mddev_t;
-typedef struct mdk_rdev_s mdk_rdev_t;
-
-/*
- * options passed in raidrun:
- */
-
-/* Currently this must fit in an 'int' */
-#define MAX_CHUNK_SIZE (1<<30)
-
-/*
- * MD's 'extended' device
- */
-struct mdk_rdev_s
-{
- struct list_head same_set; /* RAID devices within the same set */
-
- sector_t size; /* Device size (in blocks) */
- mddev_t *mddev; /* RAID array if running */
- long last_events; /* IO event timestamp */
-
- struct block_device *bdev; /* block device handle */
-
- struct page *sb_page;
- int sb_loaded;
- __u64 sb_events;
- sector_t data_offset; /* start of data in array */
- sector_t sb_start; /* offset of the super block (in 512byte sectors) */
- int sb_size; /* bytes in the superblock */
- int preferred_minor; /* autorun support */
-
- struct kobject kobj;
-
- /* A device can be in one of three states based on two flags:
- * Not working: faulty==1 in_sync==0
- * Fully working: faulty==0 in_sync==1
- * Working, but not
- * in sync with array
- * faulty==0 in_sync==0
- *
- * It can never have faulty==1, in_sync==1
- * This reduces the burden of testing multiple flags in many cases
- */
-
- unsigned long flags;
-#define Faulty 1 /* device is known to have a fault */
-#define In_sync 2 /* device is in_sync with rest of array */
-#define WriteMostly 4 /* Avoid reading if at all possible */
-#define BarriersNotsupp 5 /* BIO_RW_BARRIER is not supported */
-#define AllReserved 6 /* If whole device is reserved for
- * one array */
-#define AutoDetected 7 /* added by auto-detect */
-#define Blocked 8 /* An error occured on an externally
- * managed array, don't allow writes
- * until it is cleared */
-#define StateChanged 9 /* Faulty or Blocked has changed during
- * interrupt, so it needs to be
- * notified by the thread */
- wait_queue_head_t blocked_wait;
-
- int desc_nr; /* descriptor index in the superblock */
- int raid_disk; /* role of device in array */
- int saved_raid_disk; /* role that device used to have in the
- * array and could again if we did a partial
- * resync from the bitmap
- */
- sector_t recovery_offset;/* If this device has been partially
- * recovered, this is where we were
- * up to.
- */
-
- atomic_t nr_pending; /* number of pending requests.
- * only maintained for arrays that
- * support hot removal
- */
- atomic_t read_errors; /* number of consecutive read errors that
- * we have tried to ignore.
- */
- atomic_t corrected_errors; /* number of corrected read errors,
- * for reporting to userspace and storing
- * in superblock.
- */
- struct work_struct del_work; /* used for delayed sysfs removal */
-
- struct sysfs_dirent *sysfs_state; /* handle for 'state'
- * sysfs entry */
-};
-
-struct mddev_s
-{
- void *private;
- struct mdk_personality *pers;
- dev_t unit;
- int md_minor;
- struct list_head disks;
- unsigned long flags;
-#define MD_CHANGE_DEVS 0 /* Some device status has changed */
-#define MD_CHANGE_CLEAN 1 /* transition to or from 'clean' */
-#define MD_CHANGE_PENDING 2 /* superblock update in progress */
-
- int ro;
-
- struct gendisk *gendisk;
-
- struct kobject kobj;
- int hold_active;
-#define UNTIL_IOCTL 1
-#define UNTIL_STOP 2
-
- /* Superblock information */
- int major_version,
- minor_version,
- patch_version;
- int persistent;
- int external; /* metadata is
- * managed externally */
- char metadata_type[17]; /* externally set*/
- int chunk_size;
- time_t ctime, utime;
- int level, layout;
- char clevel[16];
- int raid_disks;
- int max_disks;
- sector_t size; /* used size of component devices */
- sector_t array_sectors; /* exported array size */
- __u64 events;
-
- char uuid[16];
-
- /* If the array is being reshaped, we need to record the
- * new shape and an indication of where we are up to.
- * This is written to the superblock.
- * If reshape_position is MaxSector, then no reshape is happening (yet).
- */
- sector_t reshape_position;
- int delta_disks, new_level, new_layout, new_chunk;
-
- struct mdk_thread_s *thread; /* management thread */
- struct mdk_thread_s *sync_thread; /* doing resync or reconstruct */
- sector_t curr_resync; /* last block scheduled */
- unsigned long resync_mark; /* a recent timestamp */
- sector_t resync_mark_cnt;/* blocks written at resync_mark */
- sector_t curr_mark_cnt; /* blocks scheduled now */
-
- sector_t resync_max_sectors; /* may be set by personality */
-
- sector_t resync_mismatches; /* count of sectors where
- * parity/replica mismatch found
- */
-
- /* allow user-space to request suspension of IO to regions of the array */
- sector_t suspend_lo;
- sector_t suspend_hi;
- /* if zero, use the system-wide default */
- int sync_speed_min;
- int sync_speed_max;
-
- /* resync even though the same disks are shared among md-devices */
- int parallel_resync;
-
- int ok_start_degraded;
- /* recovery/resync flags
- * NEEDED: we might need to start a resync/recover
- * RUNNING: a thread is running, or about to be started
- * SYNC: actually doing a resync, not a recovery
- * RECOVER: doing recovery, or need to try it.
- * INTR: resync needs to be aborted for some reason
- * DONE: thread is done and is waiting to be reaped
- * REQUEST: user-space has requested a sync (used with SYNC)
- * CHECK: user-space request for for check-only, no repair
- * RESHAPE: A reshape is happening
- *
- * If neither SYNC or RESHAPE are set, then it is a recovery.
- */
-#define MD_RECOVERY_RUNNING 0
-#define MD_RECOVERY_SYNC 1
-#define MD_RECOVERY_RECOVER 2
-#define MD_RECOVERY_INTR 3
-#define MD_RECOVERY_DONE 4
-#define MD_RECOVERY_NEEDED 5
-#define MD_RECOVERY_REQUESTED 6
-#define MD_RECOVERY_CHECK 7
-#define MD_RECOVERY_RESHAPE 8
-#define MD_RECOVERY_FROZEN 9
-
- unsigned long recovery;
- int recovery_disabled; /* if we detect that recovery
- * will always fail, set this
- * so we don't loop trying */
-
- int in_sync; /* know to not need resync */
- struct mutex reconfig_mutex;
- atomic_t active; /* general refcount */
- atomic_t openers; /* number of active opens */
-
- int changed; /* true if we might need to reread partition info */
- int degraded; /* whether md should consider
- * adding a spare
- */
- int barriers_work; /* initialised to true, cleared as soon
- * as a barrier request to slave
- * fails. Only supported
- */
- struct bio *biolist; /* bios that need to be retried
- * because BIO_RW_BARRIER is not supported
- */
-
- atomic_t recovery_active; /* blocks scheduled, but not written */
- wait_queue_head_t recovery_wait;
- sector_t recovery_cp;
- sector_t resync_min; /* user requested sync
- * starts here */
- sector_t resync_max; /* resync should pause
- * when it gets here */
-
- struct sysfs_dirent *sysfs_state; /* handle for 'array_state'
- * file in sysfs.
- */
- struct sysfs_dirent *sysfs_action; /* handle for 'sync_action' */
-
- struct work_struct del_work; /* used for delayed sysfs removal */
-
- spinlock_t write_lock;
- wait_queue_head_t sb_wait; /* for waiting on superblock updates */
- atomic_t pending_writes; /* number of active superblock writes */
-
- unsigned int safemode; /* if set, update "clean" superblock
- * when no writes pending.
- */
- unsigned int safemode_delay;
- struct timer_list safemode_timer;
- atomic_t writes_pending;
- struct request_queue *queue; /* for plugging ... */
-
- atomic_t write_behind; /* outstanding async IO */
- unsigned int max_write_behind; /* 0 = sync */
-
- struct bitmap *bitmap; /* the bitmap for the device */
- struct file *bitmap_file; /* the bitmap file */
- long bitmap_offset; /* offset from superblock of
- * start of bitmap. May be
- * negative, but not '0'
- */
- long default_bitmap_offset; /* this is the offset to use when
- * hot-adding a bitmap. It should
- * eventually be settable by sysfs.
- */
-
- struct list_head all_mddevs;
-};
-
-
-static inline void rdev_dec_pending(mdk_rdev_t *rdev, mddev_t *mddev)
-{
- int faulty = test_bit(Faulty, &rdev->flags);
- if (atomic_dec_and_test(&rdev->nr_pending) && faulty)
- set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
-}
-
-static inline void md_sync_acct(struct block_device *bdev, unsigned long nr_sectors)
-{
- atomic_add(nr_sectors, &bdev->bd_contains->bd_disk->sync_io);
-}
-
-struct mdk_personality
-{
- char *name;
- int level;
- struct list_head list;
- struct module *owner;
- int (*make_request)(struct request_queue *q, struct bio *bio);
- int (*run)(mddev_t *mddev);
- int (*stop)(mddev_t *mddev);
- void (*status)(struct seq_file *seq, mddev_t *mddev);
- /* error_handler must set ->faulty and clear ->in_sync
- * if appropriate, and should abort recovery if needed
- */
- void (*error_handler)(mddev_t *mddev, mdk_rdev_t *rdev);
- int (*hot_add_disk) (mddev_t *mddev, mdk_rdev_t *rdev);
- int (*hot_remove_disk) (mddev_t *mddev, int number);
- int (*spare_active) (mddev_t *mddev);
- sector_t (*sync_request)(mddev_t *mddev, sector_t sector_nr, int *skipped, int go_faster);
- int (*resize) (mddev_t *mddev, sector_t sectors);
- int (*check_reshape) (mddev_t *mddev);
- int (*start_reshape) (mddev_t *mddev);
- int (*reconfig) (mddev_t *mddev, int layout, int chunk_size);
- /* quiesce moves between quiescence states
- * 0 - fully active
- * 1 - no new requests allowed
- * others - reserved
- */
- void (*quiesce) (mddev_t *mddev, int state);
-};
-
-
-struct md_sysfs_entry {
- struct attribute attr;
- ssize_t (*show)(mddev_t *, char *);
- ssize_t (*store)(mddev_t *, const char *, size_t);
-};
-
-
-static inline char * mdname (mddev_t * mddev)
-{
- return mddev->gendisk ? mddev->gendisk->disk_name : "mdX";
-}
-
-/*
- * iterates through some rdev ringlist. It's safe to remove the
- * current 'rdev'. Dont touch 'tmp' though.
- */
-#define rdev_for_each_list(rdev, tmp, head) \
- list_for_each_entry_safe(rdev, tmp, head, same_set)
-
-/*
- * iterates through the 'same array disks' ringlist
- */
-#define rdev_for_each(rdev, tmp, mddev) \
- list_for_each_entry_safe(rdev, tmp, &((mddev)->disks), same_set)
-
-#define rdev_for_each_rcu(rdev, mddev) \
- list_for_each_entry_rcu(rdev, &((mddev)->disks), same_set)
-
-typedef struct mdk_thread_s {
- void (*run) (mddev_t *mddev);
- mddev_t *mddev;
- wait_queue_head_t wqueue;
- unsigned long flags;
- struct task_struct *tsk;
- unsigned long timeout;
-} mdk_thread_t;
-
-#define THREAD_WAKEUP 0
-
-#define __wait_event_lock_irq(wq, condition, lock, cmd) \
-do { \
- wait_queue_t __wait; \
- init_waitqueue_entry(&__wait, current); \
- \
- add_wait_queue(&wq, &__wait); \
- for (;;) { \
- set_current_state(TASK_UNINTERRUPTIBLE); \
- if (condition) \
- break; \
- spin_unlock_irq(&lock); \
- cmd; \
- schedule(); \
- spin_lock_irq(&lock); \
- } \
- current->state = TASK_RUNNING; \
- remove_wait_queue(&wq, &__wait); \
-} while (0)
-
-#define wait_event_lock_irq(wq, condition, lock, cmd) \
-do { \
- if (condition) \
- break; \
- __wait_event_lock_irq(wq, condition, lock, cmd); \
-} while (0)
-
-static inline void safe_put_page(struct page *p)
-{
- if (p) put_page(p);
-}
-
-#endif /* CONFIG_BLOCK */
-#endif
-
diff --git a/include/linux/raid/md_u.h b/include/linux/raid/md_u.h
index 7192035fc4b..fb1abb3367e 100644
--- a/include/linux/raid/md_u.h
+++ b/include/linux/raid/md_u.h
@@ -15,6 +15,24 @@
#ifndef _MD_U_H
#define _MD_U_H
+/*
+ * Different major versions are not compatible.
+ * Different minor versions are only downward compatible.
+ * Different patchlevel versions are downward and upward compatible.
+ */
+#define MD_MAJOR_VERSION 0
+#define MD_MINOR_VERSION 90
+/*
+ * MD_PATCHLEVEL_VERSION indicates kernel functionality.
+ * >=1 means different superblock formats are selectable using SET_ARRAY_INFO
+ * and major_version/minor_version accordingly
+ * >=2 means that Internal bitmaps are supported by setting MD_SB_BITMAP_PRESENT
+ * in the super status byte
+ * >=3 means that bitmap superblock version 4 is supported, which uses
+ * little-ending representation rather than host-endian
+ */
+#define MD_PATCHLEVEL_VERSION 3
+
/* ioctls */
/* status */
@@ -46,6 +64,12 @@
#define STOP_ARRAY_RO _IO (MD_MAJOR, 0x33)
#define RESTART_ARRAY_RW _IO (MD_MAJOR, 0x34)
+/* 63 partitions with the alternate major number (mdp) */
+#define MdpMinorShift 6
+#ifdef __KERNEL__
+extern int mdp_major;
+#endif
+
typedef struct mdu_version_s {
int major;
int minor;
@@ -85,6 +109,17 @@ typedef struct mdu_array_info_s {
} mdu_array_info_t;
+/* non-obvious values for 'level' */
+#define LEVEL_MULTIPATH (-4)
+#define LEVEL_LINEAR (-1)
+#define LEVEL_FAULTY (-5)
+
+/* we need a value for 'no level specified' and 0
+ * means 'raid0', so we need something else. This is
+ * for internal use only
+ */
+#define LEVEL_NONE (-1000000)
+
typedef struct mdu_disk_info_s {
/*
* configuration/status of one particular disk
diff --git a/include/linux/raid/multipath.h b/include/linux/raid/multipath.h
deleted file mode 100644
index 6f53fc177a4..00000000000
--- a/include/linux/raid/multipath.h
+++ /dev/null
@@ -1,42 +0,0 @@
-#ifndef _MULTIPATH_H
-#define _MULTIPATH_H
-
-#include <linux/raid/md.h>
-
-struct multipath_info {
- mdk_rdev_t *rdev;
-};
-
-struct multipath_private_data {
- mddev_t *mddev;
- struct multipath_info *multipaths;
- int raid_disks;
- int working_disks;
- spinlock_t device_lock;
- struct list_head retry_list;
-
- mempool_t *pool;
-};
-
-typedef struct multipath_private_data multipath_conf_t;
-
-/*
- * this is the only point in the RAID code where we violate
- * C type safety. mddev->private is an 'opaque' pointer.
- */
-#define mddev_to_conf(mddev) ((multipath_conf_t *) mddev->private)
-
-/*
- * this is our 'private' 'collective' MULTIPATH buffer head.
- * it contains information about what kind of IO operations were started
- * for this MULTIPATH operation, and about their status:
- */
-
-struct multipath_bh {
- mddev_t *mddev;
- struct bio *master_bio;
- struct bio bio;
- int path;
- struct list_head retry_list;
-};
-#endif
diff --git a/include/linux/raid/pq.h b/include/linux/raid/pq.h
new file mode 100644
index 00000000000..d92480f8285
--- /dev/null
+++ b/include/linux/raid/pq.h
@@ -0,0 +1,132 @@
+/* -*- linux-c -*- ------------------------------------------------------- *
+ *
+ * Copyright 2003 H. Peter Anvin - All Rights Reserved
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, Inc., 53 Temple Place Ste 330,
+ * Boston MA 02111-1307, USA; either version 2 of the License, or
+ * (at your option) any later version; incorporated herein by reference.
+ *
+ * ----------------------------------------------------------------------- */
+
+#ifndef LINUX_RAID_RAID6_H
+#define LINUX_RAID_RAID6_H
+
+#ifdef __KERNEL__
+
+/* Set to 1 to use kernel-wide empty_zero_page */
+#define RAID6_USE_EMPTY_ZERO_PAGE 0
+#include <linux/blkdev.h>
+
+/* We need a pre-zeroed page... if we don't want to use the kernel-provided
+ one define it here */
+#if RAID6_USE_EMPTY_ZERO_PAGE
+# define raid6_empty_zero_page empty_zero_page
+#else
+extern const char raid6_empty_zero_page[PAGE_SIZE];
+#endif
+
+#else /* ! __KERNEL__ */
+/* Used for testing in user space */
+
+#include <errno.h>
+#include <inttypes.h>
+#include <limits.h>
+#include <stddef.h>
+#include <sys/mman.h>
+#include <sys/types.h>
+
+/* Not standard, but glibc defines it */
+#define BITS_PER_LONG __WORDSIZE
+
+typedef uint8_t u8;
+typedef uint16_t u16;
+typedef uint32_t u32;
+typedef uint64_t u64;
+
+#ifndef PAGE_SIZE
+# define PAGE_SIZE 4096
+#endif
+extern const char raid6_empty_zero_page[PAGE_SIZE];
+
+#define __init
+#define __exit
+#define __attribute_const__ __attribute__((const))
+#define noinline __attribute__((noinline))
+
+#define preempt_enable()
+#define preempt_disable()
+#define cpu_has_feature(x) 1
+#define enable_kernel_altivec()
+#define disable_kernel_altivec()
+
+#define EXPORT_SYMBOL(sym)
+#define MODULE_LICENSE(licence)
+#define subsys_initcall(x)
+#define module_exit(x)
+#endif /* __KERNEL__ */
+
+/* Routine choices */
+struct raid6_calls {
+ void (*gen_syndrome)(int, size_t, void **);
+ int (*valid)(void); /* Returns 1 if this routine set is usable */
+ const char *name; /* Name of this routine set */
+ int prefer; /* Has special performance attribute */
+};
+
+/* Selected algorithm */
+extern struct raid6_calls raid6_call;
+
+/* Algorithm list */
+extern const struct raid6_calls * const raid6_algos[];
+int raid6_select_algo(void);
+
+/* Return values from chk_syndrome */
+#define RAID6_OK 0
+#define RAID6_P_BAD 1
+#define RAID6_Q_BAD 2
+#define RAID6_PQ_BAD 3
+
+/* Galois field tables */
+extern const u8 raid6_gfmul[256][256] __attribute__((aligned(256)));
+extern const u8 raid6_gfexp[256] __attribute__((aligned(256)));
+extern const u8 raid6_gfinv[256] __attribute__((aligned(256)));
+extern const u8 raid6_gfexi[256] __attribute__((aligned(256)));
+
+/* Recovery routines */
+void raid6_2data_recov(int disks, size_t bytes, int faila, int failb,
+ void **ptrs);
+void raid6_datap_recov(int disks, size_t bytes, int faila, void **ptrs);
+void raid6_dual_recov(int disks, size_t bytes, int faila, int failb,
+ void **ptrs);
+
+/* Some definitions to allow code to be compiled for testing in userspace */
+#ifndef __KERNEL__
+
+# define jiffies raid6_jiffies()
+# define printk printf
+# define GFP_KERNEL 0
+# define __get_free_pages(x, y) ((unsigned long)mmap(NULL, PAGE_SIZE << (y), \
+ PROT_READ|PROT_WRITE, \
+ MAP_PRIVATE|MAP_ANONYMOUS,\
+ 0, 0))
+# define free_pages(x, y) munmap((void *)(x), (y)*PAGE_SIZE)
+
+static inline void cpu_relax(void)
+{
+ /* Nothing */
+}
+
+#undef HZ
+#define HZ 1000
+static inline uint32_t raid6_jiffies(void)
+{
+ struct timeval tv;
+ gettimeofday(&tv, NULL);
+ return tv.tv_sec*1000 + tv.tv_usec/1000;
+}
+
+#endif /* ! __KERNEL__ */
+
+#endif /* LINUX_RAID_RAID6_H */
diff --git a/include/linux/raid/raid0.h b/include/linux/raid/raid0.h
deleted file mode 100644
index fd42aa87c39..00000000000
--- a/include/linux/raid/raid0.h
+++ /dev/null
@@ -1,30 +0,0 @@
-#ifndef _RAID0_H
-#define _RAID0_H
-
-#include <linux/raid/md.h>
-
-struct strip_zone
-{
- sector_t zone_start; /* Zone offset in md_dev (in sectors) */
- sector_t dev_start; /* Zone offset in real dev (in sectors) */
- sector_t sectors; /* Zone size in sectors */
- int nb_dev; /* # of devices attached to the zone */
- mdk_rdev_t **dev; /* Devices attached to the zone */
-};
-
-struct raid0_private_data
-{
- struct strip_zone **hash_table; /* Table of indexes into strip_zone */
- struct strip_zone *strip_zone;
- mdk_rdev_t **devlist; /* lists of rdevs, pointed to by strip_zone->dev */
- int nr_strip_zones;
-
- sector_t spacing;
- int sector_shift; /* shift this before divide by spacing */
-};
-
-typedef struct raid0_private_data raid0_conf_t;
-
-#define mddev_to_conf(mddev) ((raid0_conf_t *) mddev->private)
-
-#endif
diff --git a/include/linux/raid/raid1.h b/include/linux/raid/raid1.h
deleted file mode 100644
index 0a9ba7c3302..00000000000
--- a/include/linux/raid/raid1.h
+++ /dev/null
@@ -1,134 +0,0 @@
-#ifndef _RAID1_H
-#define _RAID1_H
-
-#include <linux/raid/md.h>
-
-typedef struct mirror_info mirror_info_t;
-
-struct mirror_info {
- mdk_rdev_t *rdev;
- sector_t head_position;
-};
-
-/*
- * memory pools need a pointer to the mddev, so they can force an unplug
- * when memory is tight, and a count of the number of drives that the
- * pool was allocated for, so they know how much to allocate and free.
- * mddev->raid_disks cannot be used, as it can change while a pool is active
- * These two datums are stored in a kmalloced struct.
- */
-
-struct pool_info {
- mddev_t *mddev;
- int raid_disks;
-};
-
-
-typedef struct r1bio_s r1bio_t;
-
-struct r1_private_data_s {
- mddev_t *mddev;
- mirror_info_t *mirrors;
- int raid_disks;
- int last_used;
- sector_t next_seq_sect;
- spinlock_t device_lock;
-
- struct list_head retry_list;
- /* queue pending writes and submit them on unplug */
- struct bio_list pending_bio_list;
- /* queue of writes that have been unplugged */
- struct bio_list flushing_bio_list;
-
- /* for use when syncing mirrors: */
-
- spinlock_t resync_lock;
- int nr_pending;
- int nr_waiting;
- int nr_queued;
- int barrier;
- sector_t next_resync;
- int fullsync; /* set to 1 if a full sync is needed,
- * (fresh device added).
- * Cleared when a sync completes.
- */
-
- wait_queue_head_t wait_barrier;
-
- struct pool_info *poolinfo;
-
- struct page *tmppage;
-
- mempool_t *r1bio_pool;
- mempool_t *r1buf_pool;
-};
-
-typedef struct r1_private_data_s conf_t;
-
-/*
- * this is the only point in the RAID code where we violate
- * C type safety. mddev->private is an 'opaque' pointer.
- */
-#define mddev_to_conf(mddev) ((conf_t *) mddev->private)
-
-/*
- * this is our 'private' RAID1 bio.
- *
- * it contains information about what kind of IO operations were started
- * for this RAID1 operation, and about their status:
- */
-
-struct r1bio_s {
- atomic_t remaining; /* 'have we finished' count,
- * used from IRQ handlers
- */
- atomic_t behind_remaining; /* number of write-behind ios remaining
- * in this BehindIO request
- */
- sector_t sector;
- int sectors;
- unsigned long state;
- mddev_t *mddev;
- /*
- * original bio going to /dev/mdx
- */
- struct bio *master_bio;
- /*
- * if the IO is in READ direction, then this is where we read
- */
- int read_disk;
-
- struct list_head retry_list;
- struct bitmap_update *bitmap_update;
- /*
- * if the IO is in WRITE direction, then multiple bios are used.
- * We choose the number when they are allocated.
- */
- struct bio *bios[0];
- /* DO NOT PUT ANY NEW FIELDS HERE - bios array is contiguously alloced*/
-};
-
-/* when we get a read error on a read-only array, we redirect to another
- * device without failing the first device, or trying to over-write to
- * correct the read error. To keep track of bad blocks on a per-bio
- * level, we store IO_BLOCKED in the appropriate 'bios' pointer
- */
-#define IO_BLOCKED ((struct bio*)1)
-
-/* bits for r1bio.state */
-#define R1BIO_Uptodate 0
-#define R1BIO_IsSync 1
-#define R1BIO_Degraded 2
-#define R1BIO_BehindIO 3
-#define R1BIO_Barrier 4
-#define R1BIO_BarrierRetry 5
-/* For write-behind requests, we call bi_end_io when
- * the last non-write-behind device completes, providing
- * any write was successful. Otherwise we call when
- * any write-behind write succeeds, otherwise we call
- * with failure when last write completes (and all failed).
- * Record that bi_end_io was called with this flag...
- */
-#define R1BIO_Returned 6
-
-#endif
diff --git a/include/linux/raid/raid10.h b/include/linux/raid/raid10.h
deleted file mode 100644
index e9091cfeb28..00000000000
--- a/include/linux/raid/raid10.h
+++ /dev/null
@@ -1,123 +0,0 @@
-#ifndef _RAID10_H
-#define _RAID10_H
-
-#include <linux/raid/md.h>
-
-typedef struct mirror_info mirror_info_t;
-
-struct mirror_info {
- mdk_rdev_t *rdev;
- sector_t head_position;
-};
-
-typedef struct r10bio_s r10bio_t;
-
-struct r10_private_data_s {
- mddev_t *mddev;
- mirror_info_t *mirrors;
- int raid_disks;
- spinlock_t device_lock;
-
- /* geometry */
- int near_copies; /* number of copies layed out raid0 style */
- int far_copies; /* number of copies layed out
- * at large strides across drives
- */
- int far_offset; /* far_copies are offset by 1 stripe
- * instead of many
- */
- int copies; /* near_copies * far_copies.
- * must be <= raid_disks
- */
- sector_t stride; /* distance between far copies.
- * This is size / far_copies unless
- * far_offset, in which case it is
- * 1 stripe.
- */
-
- int chunk_shift; /* shift from chunks to sectors */
- sector_t chunk_mask;
-
- struct list_head retry_list;
- /* queue pending writes and submit them on unplug */
- struct bio_list pending_bio_list;
-
-
- spinlock_t resync_lock;
- int nr_pending;
- int nr_waiting;
- int nr_queued;
- int barrier;
- sector_t next_resync;
- int fullsync; /* set to 1 if a full sync is needed,
- * (fresh device added).
- * Cleared when a sync completes.
- */
-
- wait_queue_head_t wait_barrier;
-
- mempool_t *r10bio_pool;
- mempool_t *r10buf_pool;
- struct page *tmppage;
-};
-
-typedef struct r10_private_data_s conf_t;
-
-/*
- * this is the only point in the RAID code where we violate
- * C type safety. mddev->private is an 'opaque' pointer.
- */
-#define mddev_to_conf(mddev) ((conf_t *) mddev->private)
-
-/*
- * this is our 'private' RAID10 bio.
- *
- * it contains information about what kind of IO operations were started
- * for this RAID10 operation, and about their status:
- */
-
-struct r10bio_s {
- atomic_t remaining; /* 'have we finished' count,
- * used from IRQ handlers
- */
- sector_t sector; /* virtual sector number */
- int sectors;
- unsigned long state;
- mddev_t *mddev;
- /*
- * original bio going to /dev/mdx
- */
- struct bio *master_bio;
- /*
- * if the IO is in READ direction, then this is where we read
- */
- int read_slot;
-
- struct list_head retry_list;
- /*
- * if the IO is in WRITE direction, then multiple bios are used,
- * one for each copy.
- * When resyncing we also use one for each copy.
- * When reconstructing, we use 2 bios, one for read, one for write.
- * We choose the number when they are allocated.
- */
- struct {
- struct bio *bio;
- sector_t addr;
- int devnum;
- } devs[0];
-};
-
-/* when we get a read error on a read-only array, we redirect to another
- * device without failing the first device, or trying to over-write to
- * correct the read error. To keep track of bad blocks on a per-bio
- * level, we store IO_BLOCKED in the appropriate 'bios' pointer
- */
-#define IO_BLOCKED ((struct bio*)1)
-
-/* bits for r10bio.state */
-#define R10BIO_Uptodate 0
-#define R10BIO_IsSync 1
-#define R10BIO_IsRecover 2
-#define R10BIO_Degraded 3
-#endif
diff --git a/include/linux/raid/raid5.h b/include/linux/raid/raid5.h
deleted file mode 100644
index 3b267279245..00000000000
--- a/include/linux/raid/raid5.h
+++ /dev/null
@@ -1,402 +0,0 @@
-#ifndef _RAID5_H
-#define _RAID5_H
-
-#include <linux/raid/md.h>
-#include <linux/raid/xor.h>
-
-/*
- *
- * Each stripe contains one buffer per disc. Each buffer can be in
- * one of a number of states stored in "flags". Changes between
- * these states happen *almost* exclusively under a per-stripe
- * spinlock. Some very specific changes can happen in bi_end_io, and
- * these are not protected by the spin lock.
- *
- * The flag bits that are used to represent these states are:
- * R5_UPTODATE and R5_LOCKED
- *
- * State Empty == !UPTODATE, !LOCK
- * We have no data, and there is no active request
- * State Want == !UPTODATE, LOCK
- * A read request is being submitted for this block
- * State Dirty == UPTODATE, LOCK
- * Some new data is in this buffer, and it is being written out
- * State Clean == UPTODATE, !LOCK
- * We have valid data which is the same as on disc
- *
- * The possible state transitions are:
- *
- * Empty -> Want - on read or write to get old data for parity calc
- * Empty -> Dirty - on compute_parity to satisfy write/sync request.(RECONSTRUCT_WRITE)
- * Empty -> Clean - on compute_block when computing a block for failed drive
- * Want -> Empty - on failed read
- * Want -> Clean - on successful completion of read request
- * Dirty -> Clean - on successful completion of write request
- * Dirty -> Clean - on failed write
- * Clean -> Dirty - on compute_parity to satisfy write/sync (RECONSTRUCT or RMW)
- *
- * The Want->Empty, Want->Clean, Dirty->Clean, transitions
- * all happen in b_end_io at interrupt time.
- * Each sets the Uptodate bit before releasing the Lock bit.
- * This leaves one multi-stage transition:
- * Want->Dirty->Clean
- * This is safe because thinking that a Clean buffer is actually dirty
- * will at worst delay some action, and the stripe will be scheduled
- * for attention after the transition is complete.
- *
- * There is one possibility that is not covered by these states. That
- * is if one drive has failed and there is a spare being rebuilt. We
- * can't distinguish between a clean block that has been generated
- * from parity calculations, and a clean block that has been
- * successfully written to the spare ( or to parity when resyncing).
- * To distingush these states we have a stripe bit STRIPE_INSYNC that
- * is set whenever a write is scheduled to the spare, or to the parity
- * disc if there is no spare. A sync request clears this bit, and
- * when we find it set with no buffers locked, we know the sync is
- * complete.
- *
- * Buffers for the md device that arrive via make_request are attached
- * to the appropriate stripe in one of two lists linked on b_reqnext.
- * One list (bh_read) for read requests, one (bh_write) for write.
- * There should never be more than one buffer on the two lists
- * together, but we are not guaranteed of that so we allow for more.
- *
- * If a buffer is on the read list when the associated cache buffer is
- * Uptodate, the data is copied into the read buffer and it's b_end_io
- * routine is called. This may happen in the end_request routine only
- * if the buffer has just successfully been read. end_request should
- * remove the buffers from the list and then set the Uptodate bit on
- * the buffer. Other threads may do this only if they first check
- * that the Uptodate bit is set. Once they have checked that they may
- * take buffers off the read queue.
- *
- * When a buffer on the write list is committed for write it is copied
- * into the cache buffer, which is then marked dirty, and moved onto a
- * third list, the written list (bh_written). Once both the parity
- * block and the cached buffer are successfully written, any buffer on
- * a written list can be returned with b_end_io.
- *
- * The write list and read list both act as fifos. The read list is
- * protected by the device_lock. The write and written lists are
- * protected by the stripe lock. The device_lock, which can be
- * claimed while the stipe lock is held, is only for list
- * manipulations and will only be held for a very short time. It can
- * be claimed from interrupts.
- *
- *
- * Stripes in the stripe cache can be on one of two lists (or on
- * neither). The "inactive_list" contains stripes which are not
- * currently being used for any request. They can freely be reused
- * for another stripe. The "handle_list" contains stripes that need
- * to be handled in some way. Both of these are fifo queues. Each
- * stripe is also (potentially) linked to a hash bucket in the hash
- * table so that it can be found by sector number. Stripes that are
- * not hashed must be on the inactive_list, and will normally be at
- * the front. All stripes start life this way.
- *
- * The inactive_list, handle_list and hash bucket lists are all protected by the
- * device_lock.
- * - stripes on the inactive_list never have their stripe_lock held.
- * - stripes have a reference counter. If count==0, they are on a list.
- * - If a stripe might need handling, STRIPE_HANDLE is set.
- * - When refcount reaches zero, then if STRIPE_HANDLE it is put on
- * handle_list else inactive_list
- *
- * This, combined with the fact that STRIPE_HANDLE is only ever
- * cleared while a stripe has a non-zero count means that if the
- * refcount is 0 and STRIPE_HANDLE is set, then it is on the
- * handle_list and if recount is 0 and STRIPE_HANDLE is not set, then
- * the stripe is on inactive_list.
- *
- * The possible transitions are:
- * activate an unhashed/inactive stripe (get_active_stripe())
- * lockdev check-hash unlink-stripe cnt++ clean-stripe hash-stripe unlockdev
- * activate a hashed, possibly active stripe (get_active_stripe())
- * lockdev check-hash if(!cnt++)unlink-stripe unlockdev
- * attach a request to an active stripe (add_stripe_bh())
- * lockdev attach-buffer unlockdev
- * handle a stripe (handle_stripe())
- * lockstripe clrSTRIPE_HANDLE ...
- * (lockdev check-buffers unlockdev) ..
- * change-state ..
- * record io/ops needed unlockstripe schedule io/ops
- * release an active stripe (release_stripe())
- * lockdev if (!--cnt) { if STRIPE_HANDLE, add to handle_list else add to inactive-list } unlockdev
- *
- * The refcount counts each thread that have activated the stripe,
- * plus raid5d if it is handling it, plus one for each active request
- * on a cached buffer, and plus one if the stripe is undergoing stripe
- * operations.
- *
- * Stripe operations are performed outside the stripe lock,
- * the stripe operations are:
- * -copying data between the stripe cache and user application buffers
- * -computing blocks to save a disk access, or to recover a missing block
- * -updating the parity on a write operation (reconstruct write and
- * read-modify-write)
- * -checking parity correctness
- * -running i/o to disk
- * These operations are carried out by raid5_run_ops which uses the async_tx
- * api to (optionally) offload operations to dedicated hardware engines.
- * When requesting an operation handle_stripe sets the pending bit for the
- * operation and increments the count. raid5_run_ops is then run whenever
- * the count is non-zero.
- * There are some critical dependencies between the operations that prevent some
- * from being requested while another is in flight.
- * 1/ Parity check operations destroy the in cache version of the parity block,
- * so we prevent parity dependent operations like writes and compute_blocks
- * from starting while a check is in progress. Some dma engines can perform
- * the check without damaging the parity block, in these cases the parity
- * block is re-marked up to date (assuming the check was successful) and is
- * not re-read from disk.
- * 2/ When a write operation is requested we immediately lock the affected
- * blocks, and mark them as not up to date. This causes new read requests
- * to be held off, as well as parity checks and compute block operations.
- * 3/ Once a compute block operation has been requested handle_stripe treats
- * that block as if it is up to date. raid5_run_ops guaruntees that any
- * operation that is dependent on the compute block result is initiated after
- * the compute block completes.
- */
-
-/*
- * Operations state - intermediate states that are visible outside of sh->lock
- * In general _idle indicates nothing is running, _run indicates a data
- * processing operation is active, and _result means the data processing result
- * is stable and can be acted upon. For simple operations like biofill and
- * compute that only have an _idle and _run state they are indicated with
- * sh->state flags (STRIPE_BIOFILL_RUN and STRIPE_COMPUTE_RUN)
- */
-/**
- * enum check_states - handles syncing / repairing a stripe
- * @check_state_idle - check operations are quiesced
- * @check_state_run - check operation is running
- * @check_state_result - set outside lock when check result is valid
- * @check_state_compute_run - check failed and we are repairing
- * @check_state_compute_result - set outside lock when compute result is valid
- */
-enum check_states {
- check_state_idle = 0,
- check_state_run, /* parity check */
- check_state_check_result,
- check_state_compute_run, /* parity repair */
- check_state_compute_result,
-};
-
-/**
- * enum reconstruct_states - handles writing or expanding a stripe
- */
-enum reconstruct_states {
- reconstruct_state_idle = 0,
- reconstruct_state_prexor_drain_run, /* prexor-write */
- reconstruct_state_drain_run, /* write */
- reconstruct_state_run, /* expand */
- reconstruct_state_prexor_drain_result,
- reconstruct_state_drain_result,
- reconstruct_state_result,
-};
-
-struct stripe_head {
- struct hlist_node hash;
- struct list_head lru; /* inactive_list or handle_list */
- struct raid5_private_data *raid_conf;
- sector_t sector; /* sector of this row */
- int pd_idx; /* parity disk index */
- unsigned long state; /* state flags */
- atomic_t count; /* nr of active thread/requests */
- spinlock_t lock;
- int bm_seq; /* sequence number for bitmap flushes */
- int disks; /* disks in stripe */
- enum check_states check_state;
- enum reconstruct_states reconstruct_state;
- /* stripe_operations
- * @target - STRIPE_OP_COMPUTE_BLK target
- */
- struct stripe_operations {
- int target;
- u32 zero_sum_result;
- } ops;
- struct r5dev {
- struct bio req;
- struct bio_vec vec;
- struct page *page;
- struct bio *toread, *read, *towrite, *written;
- sector_t sector; /* sector of this page */
- unsigned long flags;
- } dev[1]; /* allocated with extra space depending of RAID geometry */
-};
-
-/* stripe_head_state - collects and tracks the dynamic state of a stripe_head
- * for handle_stripe. It is only valid under spin_lock(sh->lock);
- */
-struct stripe_head_state {
- int syncing, expanding, expanded;
- int locked, uptodate, to_read, to_write, failed, written;
- int to_fill, compute, req_compute, non_overwrite;
- int failed_num;
- unsigned long ops_request;
-};
-
-/* r6_state - extra state data only relevant to r6 */
-struct r6_state {
- int p_failed, q_failed, qd_idx, failed_num[2];
-};
-
-/* Flags */
-#define R5_UPTODATE 0 /* page contains current data */
-#define R5_LOCKED 1 /* IO has been submitted on "req" */
-#define R5_OVERWRITE 2 /* towrite covers whole page */
-/* and some that are internal to handle_stripe */
-#define R5_Insync 3 /* rdev && rdev->in_sync at start */
-#define R5_Wantread 4 /* want to schedule a read */
-#define R5_Wantwrite 5
-#define R5_Overlap 7 /* There is a pending overlapping request on this block */
-#define R5_ReadError 8 /* seen a read error here recently */
-#define R5_ReWrite 9 /* have tried to over-write the readerror */
-
-#define R5_Expanded 10 /* This block now has post-expand data */
-#define R5_Wantcompute 11 /* compute_block in progress treat as
- * uptodate
- */
-#define R5_Wantfill 12 /* dev->toread contains a bio that needs
- * filling
- */
-#define R5_Wantdrain 13 /* dev->towrite needs to be drained */
-/*
- * Write method
- */
-#define RECONSTRUCT_WRITE 1
-#define READ_MODIFY_WRITE 2
-/* not a write method, but a compute_parity mode */
-#define CHECK_PARITY 3
-
-/*
- * Stripe state
- */
-#define STRIPE_HANDLE 2
-#define STRIPE_SYNCING 3
-#define STRIPE_INSYNC 4
-#define STRIPE_PREREAD_ACTIVE 5
-#define STRIPE_DELAYED 6
-#define STRIPE_DEGRADED 7
-#define STRIPE_BIT_DELAY 8
-#define STRIPE_EXPANDING 9
-#define STRIPE_EXPAND_SOURCE 10
-#define STRIPE_EXPAND_READY 11
-#define STRIPE_IO_STARTED 12 /* do not count towards 'bypass_count' */
-#define STRIPE_FULL_WRITE 13 /* all blocks are set to be overwritten */
-#define STRIPE_BIOFILL_RUN 14
-#define STRIPE_COMPUTE_RUN 15
-/*
- * Operation request flags
- */
-#define STRIPE_OP_BIOFILL 0
-#define STRIPE_OP_COMPUTE_BLK 1
-#define STRIPE_OP_PREXOR 2
-#define STRIPE_OP_BIODRAIN 3
-#define STRIPE_OP_POSTXOR 4
-#define STRIPE_OP_CHECK 5
-
-/*
- * Plugging:
- *
- * To improve write throughput, we need to delay the handling of some
- * stripes until there has been a chance that several write requests
- * for the one stripe have all been collected.
- * In particular, any write request that would require pre-reading
- * is put on a "delayed" queue until there are no stripes currently
- * in a pre-read phase. Further, if the "delayed" queue is empty when
- * a stripe is put on it then we "plug" the queue and do not process it
- * until an unplug call is made. (the unplug_io_fn() is called).
- *
- * When preread is initiated on a stripe, we set PREREAD_ACTIVE and add
- * it to the count of prereading stripes.
- * When write is initiated, or the stripe refcnt == 0 (just in case) we
- * clear the PREREAD_ACTIVE flag and decrement the count
- * Whenever the 'handle' queue is empty and the device is not plugged, we
- * move any strips from delayed to handle and clear the DELAYED flag and set
- * PREREAD_ACTIVE.
- * In stripe_handle, if we find pre-reading is necessary, we do it if
- * PREREAD_ACTIVE is set, else we set DELAYED which will send it to the delayed queue.
- * HANDLE gets cleared if stripe_handle leave nothing locked.
- */
-
-
-struct disk_info {
- mdk_rdev_t *rdev;
-};
-
-struct raid5_private_data {
- struct hlist_head *stripe_hashtbl;
- mddev_t *mddev;
- struct disk_info *spare;
- int chunk_size, level, algorithm;
- int max_degraded;
- int raid_disks;
- int max_nr_stripes;
-
- /* used during an expand */
- sector_t expand_progress; /* MaxSector when no expand happening */
- sector_t expand_lo; /* from here up to expand_progress it out-of-bounds
- * as we haven't flushed the metadata yet
- */
- int previous_raid_disks;
-
- struct list_head handle_list; /* stripes needing handling */
- struct list_head hold_list; /* preread ready stripes */
- struct list_head delayed_list; /* stripes that have plugged requests */
- struct list_head bitmap_list; /* stripes delaying awaiting bitmap update */
- struct bio *retry_read_aligned; /* currently retrying aligned bios */
- struct bio *retry_read_aligned_list; /* aligned bios retry list */
- atomic_t preread_active_stripes; /* stripes with scheduled io */
- atomic_t active_aligned_reads;
- atomic_t pending_full_writes; /* full write backlog */
- int bypass_count; /* bypassed prereads */
- int bypass_threshold; /* preread nice */
- struct list_head *last_hold; /* detect hold_list promotions */
-
- atomic_t reshape_stripes; /* stripes with pending writes for reshape */
- /* unfortunately we need two cache names as we temporarily have
- * two caches.
- */
- int active_name;
- char cache_name[2][20];
- struct kmem_cache *slab_cache; /* for allocating stripes */
-
- int seq_flush, seq_write;
- int quiesce;
-
- int fullsync; /* set to 1 if a full sync is needed,
- * (fresh device added).
- * Cleared when a sync completes.
- */
-
- struct page *spare_page; /* Used when checking P/Q in raid6 */
-
- /*
- * Free stripes pool
- */
- atomic_t active_stripes;
- struct list_head inactive_list;
- wait_queue_head_t wait_for_stripe;
- wait_queue_head_t wait_for_overlap;
- int inactive_blocked; /* release of inactive stripes blocked,
- * waiting for 25% to be free
- */
- int pool_size; /* number of disks in stripeheads in pool */
- spinlock_t device_lock;
- struct disk_info *disks;
-};
-
-typedef struct raid5_private_data raid5_conf_t;
-
-#define mddev_to_conf(mddev) ((raid5_conf_t *) mddev->private)
-
-/*
- * Our supported algorithms
- */
-#define ALGORITHM_LEFT_ASYMMETRIC 0
-#define ALGORITHM_RIGHT_ASYMMETRIC 1
-#define ALGORITHM_LEFT_SYMMETRIC 2
-#define ALGORITHM_RIGHT_SYMMETRIC 3
-
-#endif
diff --git a/include/linux/raid/xor.h b/include/linux/raid/xor.h
index 3e120587ead..5a210959e3f 100644
--- a/include/linux/raid/xor.h
+++ b/include/linux/raid/xor.h
@@ -1,8 +1,6 @@
#ifndef _XOR_H
#define _XOR_H
-#include <linux/raid/md.h>
-
#define MAX_XOR_BLOCKS 4
extern void xor_blocks(unsigned int count, unsigned int bytes,
diff --git a/include/linux/regulator/bq24022.h b/include/linux/regulator/bq24022.h
index e84b0a9feda..a6d014005d4 100644
--- a/include/linux/regulator/bq24022.h
+++ b/include/linux/regulator/bq24022.h
@@ -10,6 +10,8 @@
*
*/
+struct regulator_init_data;
+
/**
* bq24022_mach_info - platform data for bq24022
* @gpio_nce: GPIO line connected to the nCE pin, used to enable / disable charging
@@ -18,4 +20,5 @@
struct bq24022_mach_info {
int gpio_nce;
int gpio_iset2;
+ struct regulator_init_data *init_data;
};
diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h
index 801bf77ff4e..277f4b964df 100644
--- a/include/linux/regulator/consumer.h
+++ b/include/linux/regulator/consumer.h
@@ -3,7 +3,7 @@
*
* Copyright (C) 2007, 2008 Wolfson Microelectronics PLC.
*
- * Author: Liam Girdwood <lg@opensource.wolfsonmicro.com>
+ * Author: Liam Girdwood <lrg@slimlogic.co.uk>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
@@ -88,6 +88,7 @@
* FAIL Regulator output has failed.
* OVER_TEMP Regulator over temp.
* FORCE_DISABLE Regulator shut down by software.
+ * VOLTAGE_CHANGE Regulator voltage changed.
*
* NOTE: These events can be OR'ed together when passed into handler.
*/
@@ -98,6 +99,7 @@
#define REGULATOR_EVENT_FAIL 0x08
#define REGULATOR_EVENT_OVER_TEMP 0x10
#define REGULATOR_EVENT_FORCE_DISABLE 0x20
+#define REGULATOR_EVENT_VOLTAGE_CHANGE 0x40
struct regulator;
@@ -140,6 +142,8 @@ int regulator_bulk_disable(int num_consumers,
void regulator_bulk_free(int num_consumers,
struct regulator_bulk_data *consumers);
+int regulator_count_voltages(struct regulator *regulator);
+int regulator_list_voltage(struct regulator *regulator, unsigned selector);
int regulator_set_voltage(struct regulator *regulator, int min_uV, int max_uV);
int regulator_get_voltage(struct regulator *regulator);
int regulator_set_current_limit(struct regulator *regulator,
diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h
index 2dae05705f1..4848d8dacd9 100644
--- a/include/linux/regulator/driver.h
+++ b/include/linux/regulator/driver.h
@@ -3,7 +3,7 @@
*
* Copyright (C) 2007, 2008 Wolfson Microelectronics PLC.
*
- * Author: Liam Girdwood <lg@opensource.wolfsonmicro.com>
+ * Author: Liam Girdwood <lrg@slimlogic.co.uk>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
@@ -21,25 +21,38 @@
struct regulator_dev;
struct regulator_init_data;
+enum regulator_status {
+ REGULATOR_STATUS_OFF,
+ REGULATOR_STATUS_ON,
+ REGULATOR_STATUS_ERROR,
+ /* fast/normal/idle/standby are flavors of "on" */
+ REGULATOR_STATUS_FAST,
+ REGULATOR_STATUS_NORMAL,
+ REGULATOR_STATUS_IDLE,
+ REGULATOR_STATUS_STANDBY,
+};
+
/**
* struct regulator_ops - regulator operations.
*
- * This struct describes regulator operations which can be implemented by
- * regulator chip drivers.
- *
- * @enable: Enable the regulator.
- * @disable: Disable the regulator.
+ * @enable: Configure the regulator as enabled.
+ * @disable: Configure the regulator as disabled.
* @is_enabled: Return 1 if the regulator is enabled, 0 otherwise.
*
* @set_voltage: Set the voltage for the regulator within the range specified.
* The driver should select the voltage closest to min_uV.
* @get_voltage: Return the currently configured voltage for the regulator.
+ * @list_voltage: Return one of the supported voltages, in microvolts; zero
+ * if the selector indicates a voltage that is unusable on this system;
+ * or negative errno. Selectors range from zero to one less than
+ * regulator_desc.n_voltages. Voltages may be reported in any order.
*
* @set_current_limit: Configure a limit for a current-limited regulator.
- * @get_current_limit: Get the limit for a current-limited regulator.
+ * @get_current_limit: Get the configured limit for a current-limited regulator.
*
- * @set_mode: Set the operating mode for the regulator.
- * @get_mode: Get the current operating mode for the regulator.
+ * @get_mode: Get the configured operating mode for the regulator.
+ * @get_status: Return actual (not as-configured) status of regulator, as a
+ * REGULATOR_STATUS value (or negative errno)
* @get_optimum_mode: Get the most efficient operating mode for the regulator
* when running with the specified parameters.
*
@@ -51,9 +64,15 @@ struct regulator_init_data;
* suspended.
* @set_suspend_mode: Set the operating mode for the regulator when the
* system is suspended.
+ *
+ * This struct describes regulator operations which can be implemented by
+ * regulator chip drivers.
*/
struct regulator_ops {
+ /* enumerate supported voltages */
+ int (*list_voltage) (struct regulator_dev *, unsigned selector);
+
/* get/set regulator voltage */
int (*set_voltage) (struct regulator_dev *, int min_uV, int max_uV);
int (*get_voltage) (struct regulator_dev *);
@@ -72,6 +91,13 @@ struct regulator_ops {
int (*set_mode) (struct regulator_dev *, unsigned int mode);
unsigned int (*get_mode) (struct regulator_dev *);
+ /* report regulator status ... most other accessors report
+ * control inputs, this reports results of combining inputs
+ * from Linux (and other sources) with the actual load.
+ * returns REGULATOR_STATUS_* or negative errno.
+ */
+ int (*get_status)(struct regulator_dev *);
+
/* get most efficient regulator operating mode for load */
unsigned int (*get_optimum_mode) (struct regulator_dev *, int input_uV,
int output_uV, int load_uA);
@@ -106,6 +132,7 @@ enum regulator_type {
*
* @name: Identifying name for the regulator.
* @id: Numerical identifier for the regulator.
+ * @n_voltages: Number of selectors available for ops.list_voltage().
* @ops: Regulator operations table.
* @irq: Interrupt number for the regulator.
* @type: Indicates if the regulator is a voltage or current regulator.
@@ -114,14 +141,48 @@ enum regulator_type {
struct regulator_desc {
const char *name;
int id;
+ unsigned n_voltages;
struct regulator_ops *ops;
int irq;
enum regulator_type type;
struct module *owner;
};
+/*
+ * struct regulator_dev
+ *
+ * Voltage / Current regulator class device. One for each
+ * regulator.
+ *
+ * This should *not* be used directly by anything except the regulator
+ * core and notification injection (which should take the mutex and do
+ * no other direct access).
+ */
+struct regulator_dev {
+ struct regulator_desc *desc;
+ int use_count;
+
+ /* lists we belong to */
+ struct list_head list; /* list of all regulators */
+ struct list_head slist; /* list of supplied regulators */
+
+ /* lists we own */
+ struct list_head consumer_list; /* consumers we supply */
+ struct list_head supply_list; /* regulators we supply */
+
+ struct blocking_notifier_head notifier;
+ struct mutex mutex; /* consumer lock */
+ struct module *owner;
+ struct device dev;
+ struct regulation_constraints *constraints;
+ struct regulator_dev *supply; /* for tree */
+
+ void *reg_data; /* regulator_dev data */
+};
+
struct regulator_dev *regulator_register(struct regulator_desc *regulator_desc,
- struct device *dev, void *driver_data);
+ struct device *dev, struct regulator_init_data *init_data,
+ void *driver_data);
void regulator_unregister(struct regulator_dev *rdev);
int regulator_notifier_call_chain(struct regulator_dev *rdev,
diff --git a/include/linux/regulator/fixed.h b/include/linux/regulator/fixed.h
index 1387a5d2190..91b4da31f1b 100644
--- a/include/linux/regulator/fixed.h
+++ b/include/linux/regulator/fixed.h
@@ -14,9 +14,12 @@
#ifndef __REGULATOR_FIXED_H
#define __REGULATOR_FIXED_H
+struct regulator_init_data;
+
struct fixed_voltage_config {
const char *supply_name;
int microvolts;
+ struct regulator_init_data *init_data;
};
#endif
diff --git a/include/linux/regulator/machine.h b/include/linux/regulator/machine.h
index 3794773b23d..bac64fa390f 100644
--- a/include/linux/regulator/machine.h
+++ b/include/linux/regulator/machine.h
@@ -3,7 +3,7 @@
*
* Copyright (C) 2007, 2008 Wolfson Microelectronics PLC.
*
- * Author: Liam Girdwood <lg@opensource.wolfsonmicro.com>
+ * Author: Liam Girdwood <lrg@slimlogic.co.uk>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
@@ -73,7 +73,9 @@ struct regulator_state {
*
* @always_on: Set if the regulator should never be disabled.
* @boot_on: Set if the regulator is enabled when the system is initially
- * started.
+ * started. If the regulator is not enabled by the hardware or
+ * bootloader then it will be enabled when the constraints are
+ * applied.
* @apply_uV: Apply the voltage constraint when initialising.
*
* @input_uV: Input voltage for regulator when supplied by another regulator.
@@ -83,6 +85,7 @@ struct regulator_state {
* @state_standby: State for regulator when system is suspended in standby
* mode.
* @initial_state: Suspend state to set by default.
+ * @initial_mode: Mode to set at startup.
*/
struct regulation_constraints {
@@ -111,6 +114,9 @@ struct regulation_constraints {
struct regulator_state state_standby;
suspend_state_t initial_state; /* suspend state to set at init */
+ /* mode to set on startup */
+ unsigned int initial_mode;
+
/* constriant flags */
unsigned always_on:1; /* regulator never off when system is on */
unsigned boot_on:1; /* bootloader/firmware enabled regulator */
@@ -160,4 +166,6 @@ struct regulator_init_data {
int regulator_suspend_prepare(suspend_state_t state);
+void regulator_has_full_constraints(void);
+
#endif
diff --git a/include/linux/slow-work.h b/include/linux/slow-work.h
new file mode 100644
index 00000000000..85958277f83
--- /dev/null
+++ b/include/linux/slow-work.h
@@ -0,0 +1,95 @@
+/* Worker thread pool for slow items, such as filesystem lookups or mkdirs
+ *
+ * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ *
+ * See Documentation/slow-work.txt
+ */
+
+#ifndef _LINUX_SLOW_WORK_H
+#define _LINUX_SLOW_WORK_H
+
+#ifdef CONFIG_SLOW_WORK
+
+#include <linux/sysctl.h>
+
+struct slow_work;
+
+/*
+ * The operations used to support slow work items
+ */
+struct slow_work_ops {
+ /* get a ref on a work item
+ * - return 0 if successful, -ve if not
+ */
+ int (*get_ref)(struct slow_work *work);
+
+ /* discard a ref to a work item */
+ void (*put_ref)(struct slow_work *work);
+
+ /* execute a work item */
+ void (*execute)(struct slow_work *work);
+};
+
+/*
+ * A slow work item
+ * - A reference is held on the parent object by the thread pool when it is
+ * queued
+ */
+struct slow_work {
+ unsigned long flags;
+#define SLOW_WORK_PENDING 0 /* item pending (further) execution */
+#define SLOW_WORK_EXECUTING 1 /* item currently executing */
+#define SLOW_WORK_ENQ_DEFERRED 2 /* item enqueue deferred */
+#define SLOW_WORK_VERY_SLOW 3 /* item is very slow */
+ const struct slow_work_ops *ops; /* operations table for this item */
+ struct list_head link; /* link in queue */
+};
+
+/**
+ * slow_work_init - Initialise a slow work item
+ * @work: The work item to initialise
+ * @ops: The operations to use to handle the slow work item
+ *
+ * Initialise a slow work item.
+ */
+static inline void slow_work_init(struct slow_work *work,
+ const struct slow_work_ops *ops)
+{
+ work->flags = 0;
+ work->ops = ops;
+ INIT_LIST_HEAD(&work->link);
+}
+
+/**
+ * slow_work_init - Initialise a very slow work item
+ * @work: The work item to initialise
+ * @ops: The operations to use to handle the slow work item
+ *
+ * Initialise a very slow work item. This item will be restricted such that
+ * only a certain number of the pool threads will be able to execute items of
+ * this type.
+ */
+static inline void vslow_work_init(struct slow_work *work,
+ const struct slow_work_ops *ops)
+{
+ work->flags = 1 << SLOW_WORK_VERY_SLOW;
+ work->ops = ops;
+ INIT_LIST_HEAD(&work->link);
+}
+
+extern int slow_work_enqueue(struct slow_work *work);
+extern int slow_work_register_user(void);
+extern void slow_work_unregister_user(void);
+
+#ifdef CONFIG_SYSCTL
+extern ctl_table slow_work_sysctls[];
+#endif
+
+#endif /* CONFIG_SLOW_WORK */
+#endif /* _LINUX_SLOW_WORK_H */
diff --git a/include/linux/timeriomem-rng.h b/include/linux/timeriomem-rng.h
index dd253177f65..3e08a1c8683 100644
--- a/include/linux/timeriomem-rng.h
+++ b/include/linux/timeriomem-rng.h
@@ -14,7 +14,7 @@ struct timeriomem_rng_data {
struct completion completion;
unsigned int present:1;
- u32 __iomem *address;
+ void __iomem *address;
/* measures in usecs */
unsigned int period;