Merge git://git.kernel.org/pub/scm/linux/kernel/git/agk/linux-2.6-dm

* git://git.kernel.org/pub/scm/linux/kernel/git/agk/linux-2.6-dm: (48 commits)
  dm mpath: change to be request based
  dm: disable interrupt when taking map_lock
  dm: do not set QUEUE_ORDERED_DRAIN if request based
  dm: enable request based option
  dm: prepare for request based option
  dm raid1: add userspace log
  dm: calculate queue limits during resume not load
  dm log: fix create_log_context to use logical_block_size of log device
  dm target:s introduce iterate devices fn
  dm table: establish queue limits by copying table limits
  dm table: replace struct io_restrictions with struct queue_limits
  dm table: validate device logical_block_size
  dm table: ensure targets are aligned to logical_block_size
  dm ioctl: support cookies for udev
  dm: sysfs add suspended attribute
  dm table: improve warning message when devices not freed before destruction
  dm mpath: add service time load balancer
  dm mpath: add queue length load balancer
  dm mpath: add start_io and nr_bytes to path selectors
  dm snapshot: use barrier when writing exception store
  ...

5 files changed, 432 insertions, 20 deletions

diff --git a/include/linux/Kbuild b/include/linux/Kbuild
index 03f22076381f..334a3593cdfd 100644
--- a/include/linux/Kbuild
+++ b/include/linux/Kbuild
@@ -57,6 +57,7 @@ header-y += dlmconstants.h
 header-y += dlm_device.h
 header-y += dlm_netlink.h
 header-y += dm-ioctl.h
+header-y += dm-log-userspace.h
 header-y += dn.h
 header-y += dqblk_xfs.h
 header-y += efs_fs_sb.h
diff --git a/include/linux/connector.h b/include/linux/connector.h
index b9966e64604e..b68d27850d51 100644
--- a/include/linux/connector.h
+++ b/include/linux/connector.h
@@ -41,8 +41,10 @@
 #define CN_IDX_BB                       0x5     /* BlackBoard, from the TSP GPL sampling framework */
 #define CN_DST_IDX                      0x6
 #define CN_DST_VAL                      0x1
+#define CN_IDX_DM                       0x7     /* Device Mapper */
+#define CN_VAL_DM_USERSPACE_LOG         0x1
 
-#define CN_NETLINK_USERS                7
+#define CN_NETLINK_USERS                8
 
 /*
  * Maximum connector's message size.
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index 49c2362977fd..0d6310657f32 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -11,6 +11,7 @@
 #include <linux/bio.h>
 #include <linux/blkdev.h>
 
+struct dm_dev;
 struct dm_target;
 struct dm_table;
 struct mapped_device;
@@ -21,6 +22,7 @@ typedef enum { STATUSTYPE_INFO, STATUSTYPE_TABLE } status_type_t;
 union map_info {
         void *ptr;
         unsigned long long ll;
+        unsigned flush_request;
 };
 
 /*
@@ -80,6 +82,15 @@ typedef int (*dm_ioctl_fn) (struct dm_target *ti, unsigned int cmd,
 typedef int (*dm_merge_fn) (struct dm_target *ti, struct bvec_merge_data *bvm,
                             struct bio_vec *biovec, int max_size);
 
+typedef int (*iterate_devices_callout_fn) (struct dm_target *ti,
+                                           struct dm_dev *dev,
+                                           sector_t physical_start,
+                                           void *data);
+
+typedef int (*dm_iterate_devices_fn) (struct dm_target *ti,
+                                      iterate_devices_callout_fn fn,
+                                      void *data);
+
 /*
  * Returns:
  *    0: The target can handle the next I/O immediately.
@@ -92,7 +103,8 @@ void dm_error(const char *message);
 /*
  * Combine device limits.
  */
-void dm_set_device_limits(struct dm_target *ti, struct block_device *bdev);
+int dm_set_device_limits(struct dm_target *ti, struct dm_dev *dev,
+                         sector_t start, void *data);
 
 struct dm_dev {
         struct block_device *bdev;
@@ -138,23 +150,12 @@ struct target_type {
         dm_ioctl_fn ioctl;
         dm_merge_fn merge;
         dm_busy_fn busy;
+        dm_iterate_devices_fn iterate_devices;
 
         /* For internal device-mapper use. */
         struct list_head list;
 };
 
-struct io_restrictions {
-        unsigned long bounce_pfn;
-        unsigned long seg_boundary_mask;
-        unsigned max_hw_sectors;
-        unsigned max_sectors;
-        unsigned max_segment_size;
-        unsigned short logical_block_size;
-        unsigned short max_hw_segments;
-        unsigned short max_phys_segments;
-        unsigned char no_cluster; /* inverted so that 0 is default */
-};
-
 struct dm_target {
         struct dm_table *table;
         struct target_type *type;
@@ -163,15 +164,18 @@ struct dm_target {
         sector_t begin;
         sector_t len;
 
-        /* FIXME: turn this into a mask, and merge with io_restrictions */
         /* Always a power of 2 */
         sector_t split_io;
 
         /*
-         * These are automatically filled in by
-         * dm_table_get_device.
+         * A number of zero-length barrier requests that will be submitted
+         * to the target for the purpose of flushing cache.
+         *
+         * The request number will be placed in union map_info->flush_request.
+         * It is a responsibility of the target driver to remap these requests
+         * to the real underlying devices.
          */
-        struct io_restrictions limits;
+        unsigned num_flush_requests;
 
         /* target specific data */
         void *private;
@@ -230,6 +234,7 @@ struct gendisk *dm_disk(struct mapped_device *md);
 int dm_suspended(struct mapped_device *md);
 int dm_noflush_suspending(struct dm_target *ti);
 union map_info *dm_get_mapinfo(struct bio *bio);
+union map_info *dm_get_rq_mapinfo(struct request *rq);
 
 /*
  * Geometry functions.
@@ -392,4 +397,12 @@ static inline unsigned long to_bytes(sector_t n)
         return (n << SECTOR_SHIFT);
 }
 
+/*-----------------------------------------------------------------
+ * Helper for block layer and dm core operations
+ *---------------------------------------------------------------*/
+void dm_dispatch_request(struct request *rq);
+void dm_requeue_unmapped_request(struct request *rq);
+void dm_kill_unmapped_request(struct request *rq, int error);
+int dm_underlying_device_busy(struct request_queue *q);
+
 #endif  /* _LINUX_DEVICE_MAPPER_H */
diff --git a/include/linux/dm-ioctl.h b/include/linux/dm-ioctl.h
index 48e44ee2b466..2ab84c83c31a 100644
--- a/include/linux/dm-ioctl.h
+++ b/include/linux/dm-ioctl.h
@@ -123,6 +123,16 @@ struct dm_ioctl {
         __u32 target_count;     /* in/out */
         __s32 open_count;       /* out */
         __u32 flags;            /* in/out */
+
+        /*
+         * event_nr holds either the event number (input and output) or the
+         * udev cookie value (input only).
+         * The DM_DEV_WAIT ioctl takes an event number as input.
+         * The DM_SUSPEND, DM_DEV_REMOVE and DM_DEV_RENAME ioctls
+         * use the field as a cookie to return in the DM_COOKIE
+         * variable with the uevents they issue.
+         * For output, the ioctls return the event number, not the cookie.
+         */
         __u32 event_nr;         /* in/out */
         __u32 padding;
 
@@ -256,9 +266,9 @@ enum {
 #define DM_DEV_SET_GEOMETRY     _IOWR(DM_IOCTL, DM_DEV_SET_GEOMETRY_CMD, struct dm_ioctl)
 
 #define DM_VERSION_MAJOR        4
-#define DM_VERSION_MINOR        14
+#define DM_VERSION_MINOR        15
 #define DM_VERSION_PATCHLEVEL   0
-#define DM_VERSION_EXTRA        "-ioctl (2008-04-23)"
+#define DM_VERSION_EXTRA        "-ioctl (2009-04-01)"
 
 /* Status bits */
 #define DM_READONLY_FLAG        (1 << 0) /* In/Out */
diff --git a/include/linux/dm-log-userspace.h b/include/linux/dm-log-userspace.h
new file mode 100644
index 000000000000..642e3017b51f
--- /dev/null
+++ b/include/linux/dm-log-userspace.h
@@ -0,0 +1,386 @@
+/*
+ * Copyright (C) 2006-2009 Red Hat, Inc.
+ *
+ * This file is released under the LGPL.
+ */
+
+#ifndef __DM_LOG_USERSPACE_H__
+#define __DM_LOG_USERSPACE_H__
+
+#include <linux/dm-ioctl.h> /* For DM_UUID_LEN */
+
+/*
+ * The device-mapper userspace log module consists of a kernel component and
+ * a user-space component.  The kernel component implements the API defined
+ * in dm-dirty-log.h.  Its purpose is simply to pass the parameters and
+ * return values of those API functions between kernel and user-space.
+ *
+ * Below are defined the 'request_types' - DM_ULOG_CTR, DM_ULOG_DTR, etc.
+ * These request types represent the different functions in the device-mapper
+ * dirty log API.  Each of these is described in more detail below.
+ *
+ * The user-space program must listen for requests from the kernel (representing
+ * the various API functions) and process them.
+ *
+ * User-space begins by setting up the communication link (error checking
+ * removed for clarity):
+ *      fd = socket(PF_NETLINK, SOCK_DGRAM, NETLINK_CONNECTOR);
+ *      addr.nl_family = AF_NETLINK;
+ *      addr.nl_groups = CN_IDX_DM;
+ *      addr.nl_pid = 0;
+ *      r = bind(fd, (struct sockaddr *) &addr, sizeof(addr));
+ *      opt = addr.nl_groups;
+ *      setsockopt(fd, SOL_NETLINK, NETLINK_ADD_MEMBERSHIP, &opt, sizeof(opt));
+ *
+ * User-space will then wait to receive requests form the kernel, which it
+ * will process as described below.  The requests are received in the form,
+ * ((struct dm_ulog_request) + (additional data)).  Depending on the request
+ * type, there may or may not be 'additional data'.  In the descriptions below,
+ * you will see 'Payload-to-userspace' and 'Payload-to-kernel'.  The
+ * 'Payload-to-userspace' is what the kernel sends in 'additional data' as
+ * necessary parameters to complete the request.  The 'Payload-to-kernel' is
+ * the 'additional data' returned to the kernel that contains the necessary
+ * results of the request.  The 'data_size' field in the dm_ulog_request
+ * structure denotes the availability and amount of payload data.
+ */
+
+/*
+ * DM_ULOG_CTR corresponds to (found in dm-dirty-log.h):
+ * int (*ctr)(struct dm_dirty_log *log, struct dm_target *ti,
+ *            unsigned argc, char **argv);
+ *
+ * Payload-to-userspace:
+ *      A single string containing all the argv arguments separated by ' 's
+ * Payload-to-kernel:
+ *      None.  ('data_size' in the dm_ulog_request struct should be 0.)
+ *
+ * The UUID contained in the dm_ulog_request structure is the reference that
+ * will be used by all request types to a specific log.  The constructor must
+ * record this assotiation with instance created.
+ *
+ * When the request has been processed, user-space must return the
+ * dm_ulog_request to the kernel - setting the 'error' field and
+ * 'data_size' appropriately.
+ */
+#define DM_ULOG_CTR                    1
+
+/*
+ * DM_ULOG_DTR corresponds to (found in dm-dirty-log.h):
+ * void (*dtr)(struct dm_dirty_log *log);
+ *
+ * Payload-to-userspace:
+ *      A single string containing all the argv arguments separated by ' 's
+ * Payload-to-kernel:
+ *      None.  ('data_size' in the dm_ulog_request struct should be 0.)
+ *
+ * The UUID contained in the dm_ulog_request structure is all that is
+ * necessary to identify the log instance being destroyed.  There is no
+ * payload data.
+ *
+ * When the request has been processed, user-space must return the
+ * dm_ulog_request to the kernel - setting the 'error' field and clearing
+ * 'data_size' appropriately.
+ */
+#define DM_ULOG_DTR                    2
+
+/*
+ * DM_ULOG_PRESUSPEND corresponds to (found in dm-dirty-log.h):
+ * int (*presuspend)(struct dm_dirty_log *log);
+ *
+ * Payload-to-userspace:
+ *      None.
+ * Payload-to-kernel:
+ *      None.
+ *
+ * The UUID contained in the dm_ulog_request structure is all that is
+ * necessary to identify the log instance being presuspended.  There is no
+ * payload data.
+ *
+ * When the request has been processed, user-space must return the
+ * dm_ulog_request to the kernel - setting the 'error' field and
+ * 'data_size' appropriately.
+ */
+#define DM_ULOG_PRESUSPEND             3
+
+/*
+ * DM_ULOG_POSTSUSPEND corresponds to (found in dm-dirty-log.h):
+ * int (*postsuspend)(struct dm_dirty_log *log);
+ *
+ * Payload-to-userspace:
+ *      None.
+ * Payload-to-kernel:
+ *      None.
+ *
+ * The UUID contained in the dm_ulog_request structure is all that is
+ * necessary to identify the log instance being postsuspended.  There is no
+ * payload data.
+ *
+ * When the request has been processed, user-space must return the
+ * dm_ulog_request to the kernel - setting the 'error' field and
+ * 'data_size' appropriately.
+ */
+#define DM_ULOG_POSTSUSPEND            4
+
+/*
+ * DM_ULOG_RESUME corresponds to (found in dm-dirty-log.h):
+ * int (*resume)(struct dm_dirty_log *log);
+ *
+ * Payload-to-userspace:
+ *      None.
+ * Payload-to-kernel:
+ *      None.
+ *
+ * The UUID contained in the dm_ulog_request structure is all that is
+ * necessary to identify the log instance being resumed.  There is no
+ * payload data.
+ *
+ * When the request has been processed, user-space must return the
+ * dm_ulog_request to the kernel - setting the 'error' field and
+ * 'data_size' appropriately.
+ */
+#define DM_ULOG_RESUME                 5
+
+/*
+ * DM_ULOG_GET_REGION_SIZE corresponds to (found in dm-dirty-log.h):
+ * uint32_t (*get_region_size)(struct dm_dirty_log *log);
+ *
+ * Payload-to-userspace:
+ *      None.
+ * Payload-to-kernel:
+ *      uint64_t - contains the region size
+ *
+ * The region size is something that was determined at constructor time.
+ * It is returned in the payload area and 'data_size' is set to
+ * reflect this.
+ *
+ * When the request has been processed, user-space must return the
+ * dm_ulog_request to the kernel - setting the 'error' field appropriately.
+ */
+#define DM_ULOG_GET_REGION_SIZE        6
+
+/*
+ * DM_ULOG_IS_CLEAN corresponds to (found in dm-dirty-log.h):
+ * int (*is_clean)(struct dm_dirty_log *log, region_t region);
+ *
+ * Payload-to-userspace:
+ *      uint64_t - the region to get clean status on
+ * Payload-to-kernel:
+ *      int64_t  - 1 if clean, 0 otherwise
+ *
+ * Payload is sizeof(uint64_t) and contains the region for which the clean
+ * status is being made.
+ *
+ * When the request has been processed, user-space must return the
+ * dm_ulog_request to the kernel - filling the payload with 0 (not clean) or
+ * 1 (clean), setting 'data_size' and 'error' appropriately.
+ */
+#define DM_ULOG_IS_CLEAN               7
+
+/*
+ * DM_ULOG_IN_SYNC corresponds to (found in dm-dirty-log.h):
+ * int (*in_sync)(struct dm_dirty_log *log, region_t region,
+ *                int can_block);
+ *
+ * Payload-to-userspace:
+ *      uint64_t - the region to get sync status on
+ * Payload-to-kernel:
+ *      int64_t - 1 if in-sync, 0 otherwise
+ *
+ * Exactly the same as 'is_clean' above, except this time asking "has the
+ * region been recovered?" vs. "is the region not being modified?"
+ */
+#define DM_ULOG_IN_SYNC                8
+
+/*
+ * DM_ULOG_FLUSH corresponds to (found in dm-dirty-log.h):
+ * int (*flush)(struct dm_dirty_log *log);
+ *
+ * Payload-to-userspace:
+ *      None.
+ * Payload-to-kernel:
+ *      None.
+ *
+ * No incoming or outgoing payload.  Simply flush log state to disk.
+ *
+ * When the request has been processed, user-space must return the
+ * dm_ulog_request to the kernel - setting the 'error' field and clearing
+ * 'data_size' appropriately.
+ */
+#define DM_ULOG_FLUSH                  9
+
+/*
+ * DM_ULOG_MARK_REGION corresponds to (found in dm-dirty-log.h):
+ * void (*mark_region)(struct dm_dirty_log *log, region_t region);
+ *
+ * Payload-to-userspace:
+ *      uint64_t [] - region(s) to mark
+ * Payload-to-kernel:
+ *      None.
+ *
+ * Incoming payload contains the one or more regions to mark dirty.
+ * The number of regions contained in the payload can be determined from
+ * 'data_size/sizeof(uint64_t)'.
+ *
+ * When the request has been processed, user-space must return the
+ * dm_ulog_request to the kernel - setting the 'error' field and clearing
+ * 'data_size' appropriately.
+ */
+#define DM_ULOG_MARK_REGION           10
+
+/*
+ * DM_ULOG_CLEAR_REGION corresponds to (found in dm-dirty-log.h):
+ * void (*clear_region)(struct dm_dirty_log *log, region_t region);
+ *
+ * Payload-to-userspace:
+ *      uint64_t [] - region(s) to clear
+ * Payload-to-kernel:
+ *      None.
+ *
+ * Incoming payload contains the one or more regions to mark clean.
+ * The number of regions contained in the payload can be determined from
+ * 'data_size/sizeof(uint64_t)'.
+ *
+ * When the request has been processed, user-space must return the
+ * dm_ulog_request to the kernel - setting the 'error' field and clearing
+ * 'data_size' appropriately.
+ */
+#define DM_ULOG_CLEAR_REGION          11
+
+/*
+ * DM_ULOG_GET_RESYNC_WORK corresponds to (found in dm-dirty-log.h):
+ * int (*get_resync_work)(struct dm_dirty_log *log, region_t *region);
+ *
+ * Payload-to-userspace:
+ *      None.
+ * Payload-to-kernel:
+ *      {
+ *              int64_t i; -- 1 if recovery necessary, 0 otherwise
+ *              uint64_t r; -- The region to recover if i=1
+ *      }
+ * 'data_size' should be set appropriately.
+ *
+ * When the request has been processed, user-space must return the
+ * dm_ulog_request to the kernel - setting the 'error' field appropriately.
+ */
+#define DM_ULOG_GET_RESYNC_WORK       12
+
+/*
+ * DM_ULOG_SET_REGION_SYNC corresponds to (found in dm-dirty-log.h):
+ * void (*set_region_sync)(struct dm_dirty_log *log,
+ *                         region_t region, int in_sync);
+ *
+ * Payload-to-userspace:
+ *      {
+ *              uint64_t - region to set sync state on
+ *              int64_t  - 0 if not-in-sync, 1 if in-sync
+ *      }
+ * Payload-to-kernel:
+ *      None.
+ *
+ * When the request has been processed, user-space must return the
+ * dm_ulog_request to the kernel - setting the 'error' field and clearing
+ * 'data_size' appropriately.
+ */
+#define DM_ULOG_SET_REGION_SYNC       13
+
+/*
+ * DM_ULOG_GET_SYNC_COUNT corresponds to (found in dm-dirty-log.h):
+ * region_t (*get_sync_count)(struct dm_dirty_log *log);
+ *
+ * Payload-to-userspace:
+ *      None.
+ * Payload-to-kernel:
+ *      uint64_t - the number of in-sync regions
+ *
+ * No incoming payload.  Kernel-bound payload contains the number of
+ * regions that are in-sync (in a size_t).
+ *
+ * When the request has been processed, user-space must return the
+ * dm_ulog_request to the kernel - setting the 'error' field and
+ * 'data_size' appropriately.
+ */
+#define DM_ULOG_GET_SYNC_COUNT        14
+
+/*
+ * DM_ULOG_STATUS_INFO corresponds to (found in dm-dirty-log.h):
+ * int (*status)(struct dm_dirty_log *log, STATUSTYPE_INFO,
+ *               char *result, unsigned maxlen);
+ *
+ * Payload-to-userspace:
+ *      None.
+ * Payload-to-kernel:
+ *      Character string containing STATUSTYPE_INFO
+ *
+ * When the request has been processed, user-space must return the
+ * dm_ulog_request to the kernel - setting the 'error' field and
+ * 'data_size' appropriately.
+ */
+#define DM_ULOG_STATUS_INFO           15
+
+/*
+ * DM_ULOG_STATUS_TABLE corresponds to (found in dm-dirty-log.h):
+ * int (*status)(struct dm_dirty_log *log, STATUSTYPE_TABLE,
+ *               char *result, unsigned maxlen);
+ *
+ * Payload-to-userspace:
+ *      None.
+ * Payload-to-kernel:
+ *      Character string containing STATUSTYPE_TABLE
+ *
+ * When the request has been processed, user-space must return the
+ * dm_ulog_request to the kernel - setting the 'error' field and
+ * 'data_size' appropriately.
+ */
+#define DM_ULOG_STATUS_TABLE          16
+
+/*
+ * DM_ULOG_IS_REMOTE_RECOVERING corresponds to (found in dm-dirty-log.h):
+ * int (*is_remote_recovering)(struct dm_dirty_log *log, region_t region);
+ *
+ * Payload-to-userspace:
+ *      uint64_t - region to determine recovery status on
+ * Payload-to-kernel:
+ *      {
+ *              int64_t is_recovering;  -- 0 if no, 1 if yes
+ *              uint64_t in_sync_hint;  -- lowest region still needing resync
+ *      }
+ *
+ * When the request has been processed, user-space must return the
+ * dm_ulog_request to the kernel - setting the 'error' field and
+ * 'data_size' appropriately.
+ */
+#define DM_ULOG_IS_REMOTE_RECOVERING  17
+
+/*
+ * (DM_ULOG_REQUEST_MASK & request_type) to get the request type
+ *
+ * Payload-to-userspace:
+ *      A single string containing all the argv arguments separated by ' 's
+ * Payload-to-kernel:
+ *      None.  ('data_size' in the dm_ulog_request struct should be 0.)
+ *
+ * We are reserving 8 bits of the 32-bit 'request_type' field for the
+ * various request types above.  The remaining 24-bits are currently
+ * set to zero and are reserved for future use and compatibility concerns.
+ *
+ * User-space should always use DM_ULOG_REQUEST_TYPE to aquire the
+ * request type from the 'request_type' field to maintain forward compatibility.
+ */
+#define DM_ULOG_REQUEST_MASK 0xFF
+#define DM_ULOG_REQUEST_TYPE(request_type) \
+        (DM_ULOG_REQUEST_MASK & (request_type))
+
+struct dm_ulog_request {
+        char uuid[DM_UUID_LEN]; /* Ties a request to a specific mirror log */
+        char padding[7];        /* Padding because DM_UUID_LEN = 129 */
+
+        int32_t error;          /* Used to report back processing errors */
+
+        uint32_t seq;           /* Sequence number for request */
+        uint32_t request_type;  /* DM_ULOG_* defined above */
+        uint32_t data_size;     /* How much data (not including this struct) */
+
+        char data[0];
+};
+
+#endif /* __DM_LOG_USERSPACE_H__ */