Merge remote branch 'gcl/next' into next

13 files changed, 174 insertions, 176 deletions

diff --git a/Documentation/ABI/testing/sysfs-bus-rbd b/Documentation/ABI/testing/sysfs-bus-rbd
new file mode 100644
index 000000000000..90a87e2a572b
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-bus-rbd
@@ -0,0 +1,83 @@
+What:           /sys/bus/rbd/
+Date:           November 2010
+Contact:        Yehuda Sadeh <yehuda@hq.newdream.net>,
+                Sage Weil <sage@newdream.net>
+Description:
+
+Being used for adding and removing rbd block devices.
+
+Usage: <mon ip addr> <options> <pool name> <rbd image name> [snap name]
+
+ $ echo "192.168.0.1 name=admin rbd foo" > /sys/bus/rbd/add
+
+The snapshot name can be "-" or omitted to map the image read/write. A <dev-id>
+will be assigned for any registered block device. If snapshot is used, it will
+be mapped read-only.
+
+Removal of a device:
+
+  $ echo <dev-id> > /sys/bus/rbd/remove
+
+Entries under /sys/bus/rbd/devices/<dev-id>/
+--------------------------------------------
+
+client_id
+
+        The ceph unique client id that was assigned for this specific session.
+
+major
+
+        The block device major number.
+
+name
+
+        The name of the rbd image.
+
+pool
+
+        The pool where this rbd image resides. The pool-name pair is unique
+        per rados system.
+
+size
+
+        The size (in bytes) of the mapped block device.
+
+refresh
+
+        Writing to this file will reread the image header data and set
+        all relevant datastructures accordingly.
+
+current_snap
+
+        The current snapshot for which the device is mapped.
+
+create_snap
+
+        Create a snapshot:
+
+         $ echo <snap-name> > /sys/bus/rbd/devices/<dev-id>/snap_create
+
+rollback_snap
+
+        Rolls back data to the specified snapshot. This goes over the entire
+        list of rados blocks and sends a rollback command to each.
+
+         $ echo <snap-name> > /sys/bus/rbd/devices/<dev-id>/snap_rollback
+
+snap_*
+
+        A directory per each snapshot
+
+
+Entries under /sys/bus/rbd/devices/<dev-id>/snap_<snap-name>
+-------------------------------------------------------------
+
+id
+
+        The rados internal snapshot id assigned for this snapshot
+
+size
+
+        The size of the image when this snapshot was taken.
+
+
diff --git a/Documentation/ABI/testing/sysfs-platform-asus-laptop b/Documentation/ABI/testing/sysfs-platform-asus-laptop
index 1d775390e856..41ff8ae4dee0 100644
--- a/Documentation/ABI/testing/sysfs-platform-asus-laptop
+++ b/Documentation/ABI/testing/sysfs-platform-asus-laptop
@@ -47,6 +47,20 @@ Date:		January 2007
 KernelVersion:  2.6.20
 Contact:        "Corentin Chary" <corentincj@iksaif.net>
 Description:
-                Control the bluetooth device. 1 means on, 0 means off.
+                Control the wlan device. 1 means on, 0 means off.
                 This may control the led, the device or both.
 Users:          Lapsus
+
+What:           /sys/devices/platform/asus_laptop/wimax
+Date:           October 2010
+KernelVersion:  2.6.37
+Contact:        "Corentin Chary" <corentincj@iksaif.net>
+Description:
+                Control the wimax device. 1 means on, 0 means off.
+
+What:           /sys/devices/platform/asus_laptop/wwan
+Date:           October 2010
+KernelVersion:  2.6.37
+Contact:        "Corentin Chary" <corentincj@iksaif.net>
+Description:
+                Control the wwan (3G) device. 1 means on, 0 means off.
diff --git a/Documentation/ABI/testing/sysfs-platform-eeepc-wmi b/Documentation/ABI/testing/sysfs-platform-eeepc-wmi
new file mode 100644
index 000000000000..e4b5fef5fadd
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-platform-eeepc-wmi
@@ -0,0 +1,10 @@
+What:           /sys/devices/platform/eeepc-wmi/cpufv
+Date:           Oct 2010
+KernelVersion:  2.6.37
+Contact:        "Corentin Chary" <corentincj@iksaif.net>
+Description:
+                Change CPU clock configuration (write-only).
+                There are three available clock configuration:
+                    * 0 -> Super Performance Mode
+                    * 1 -> High Performance Mode
+                    * 2 -> Power Saving Mode
diff --git a/Documentation/accounting/getdelays.c b/Documentation/accounting/getdelays.c
index a2976a6de033..e9c77788a39d 100644
--- a/Documentation/accounting/getdelays.c
+++ b/Documentation/accounting/getdelays.c
@@ -516,6 +516,7 @@ int main(int argc, char *argv[])
                         default:
                                 fprintf(stderr, "Unknown nla_type %d\n",
                                         na->nla_type);
+                        case TASKSTATS_TYPE_NULL:
                                 break;
                         }
                         na = (struct nlattr *) (GENLMSG_DATA(&msg) + len);
diff --git a/Documentation/driver-model/interface.txt b/Documentation/driver-model/interface.txt
deleted file mode 100644
index c66912bfe866..000000000000
--- a/Documentation/driver-model/interface.txt
+++ /dev/null
@@ -1,129 +0,0 @@
-
-Device Interfaces
-
-Introduction
-~~~~~~~~~~~~
-
-Device interfaces are the logical interfaces of device classes that correlate
-directly to userspace interfaces, like device nodes. 
-   
-Each device class may have multiple interfaces through which you can 
-access the same device. An input device may support the mouse interface, 
-the 'evdev' interface, and the touchscreen interface. A SCSI disk would 
-support the disk interface, the SCSI generic interface, and possibly a raw 
-device interface. 
-
-Device interfaces are registered with the class they belong to. As devices
-are added to the class, they are added to each interface registered with
-the class. The interface is responsible for determining whether the device
-supports the interface or not. 
-
-
-Programming Interface
-~~~~~~~~~~~~~~~~~~~~~
-
-struct device_interface {
-        char                    * name;
-        rwlock_t                lock;
-        u32                     devnum;
-        struct device_class     * devclass;
-
-        struct list_head        node;
-        struct driver_dir_entry dir;
-
-        int (*add_device)(struct device *);
-        int (*add_device)(struct intf_data *);
-};
-
-int interface_register(struct device_interface *);
-void interface_unregister(struct device_interface *);
-
-
-An interface must specify the device class it belongs to. It is added
-to that class's list of interfaces on registration.
-
-
-Interfaces can be added to a device class at any time. Whenever it is
-added, each device in the class is passed to the interface's
-add_device callback. When an interface is removed, each device is
-removed from the interface.
-
-
-Devices
-~~~~~~~
-Once a device is added to a device class, it is added to each
-interface that is registered with the device class. The class
-is expected to place a class-specific data structure in 
-struct device::class_data. The interface can use that (along with
-other fields of struct device) to determine whether or not the driver
-and/or device support that particular interface.
-
-
-Data
-~~~~
-
-struct intf_data {
-        struct list_head        node;
-        struct device_interface * intf;
-        struct device           * dev;
-        u32                     intf_num;
-};
-
-int interface_add_data(struct interface_data *);
-
-The interface is responsible for allocating and initializing a struct 
-intf_data and calling interface_add_data() to add it to the device's list
-of interfaces it belongs to. This list will be iterated over when the device
-is removed from the class (instead of all possible interfaces for a class).
-This structure should probably be embedded in whatever per-device data 
-structure the interface is allocating anyway.
-   
-Devices are enumerated within the interface. This happens in interface_add_data()
-and the enumerated value is stored in the struct intf_data for that device. 
-
-sysfs
-~~~~~
-Each interface is given a directory in the directory of the device
-class it belongs to:
-
-Interfaces get a directory in the class's directory as well:
-
-   class/
-   `-- input
-       |-- devices
-       |-- drivers
-       |-- mouse
-       `-- evdev
-
-When a device is added to the interface, a symlink is created that points 
-to the device's directory in the physical hierarchy:
-
-   class/
-   `-- input
-       |-- devices
-       |   `-- 1 -> ../../../root/pci0/00:1f.0/usb_bus/00:1f.2-1:0/
-       |-- drivers
-       |   `-- usb:usb_mouse -> ../../../bus/drivers/usb_mouse/
-       |-- mouse
-       |   `-- 1 -> ../../../root/pci0/00:1f.0/usb_bus/00:1f.2-1:0/
-       `-- evdev
-           `-- 1 -> ../../../root/pci0/00:1f.0/usb_bus/00:1f.2-1:0/
-
-
-Future Plans
-~~~~~~~~~~~~
-A device interface is correlated directly with a userspace interface
-for a device, specifically a device node. For instance, a SCSI disk
-exposes at least two interfaces to userspace: the standard SCSI disk
-interface and the SCSI generic interface. It might also export a raw
-device interface. 
-
-Many interfaces have a major number associated with them and each
-device gets a minor number. Or, multiple interfaces might share one
-major number, and each will receive a range of minor numbers (like in
-the case of input devices).
-
-These major and minor numbers could be stored in the interface
-structure. Major and minor allocations could happen when the interface
-is registered with the class, or via a helper function. 
-
diff --git a/Documentation/edac.txt b/Documentation/edac.txt
index 0b875e8da969..9ee774de57cd 100644
--- a/Documentation/edac.txt
+++ b/Documentation/edac.txt
@@ -196,7 +196,7 @@ csrow3.
 The representation of the above is reflected in the directory tree
 in EDAC's sysfs interface. Starting in directory
 /sys/devices/system/edac/mc each memory controller will be represented
-by its own 'mcX' directory, where 'X" is the index of the MC.
+by its own 'mcX' directory, where 'X' is the index of the MC.
 
 
         ..../edac/mc/
@@ -207,7 +207,7 @@ by its own 'mcX' directory, where 'X" is the index of the MC.
                    ....
 
 Under each 'mcX' directory each 'csrowX' is again represented by a
-'csrowX', where 'X" is the csrow index:
+'csrowX', where 'X' is the csrow index:
 
 
         .../mc/mc0/
@@ -232,7 +232,7 @@ EDAC control and attribute files.
 
 
 In 'mcX' directories are EDAC control and attribute files for
-this 'X" instance of the memory controllers:
+this 'X' instance of the memory controllers:
 
 
 Counter reset control file:
@@ -343,7 +343,7 @@ Sdram memory scrubbing rate:
 'csrowX' DIRECTORIES
 
 In the 'csrowX' directories are EDAC control and attribute files for
-this 'X" instance of csrow:
+this 'X' instance of csrow:
 
 
 Total Uncorrectable Errors count attribute file:
diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index a91f30890011..b6426f15b4ae 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -173,12 +173,13 @@ prototypes:
         sector_t (*bmap)(struct address_space *, sector_t);
         int (*invalidatepage) (struct page *, unsigned long);
         int (*releasepage) (struct page *, int);
+        void (*freepage)(struct page *);
         int (*direct_IO)(int, struct kiocb *, const struct iovec *iov,
                         loff_t offset, unsigned long nr_segs);
         int (*launder_page) (struct page *);
 
 locking rules:
-        All except set_page_dirty may block
+        All except set_page_dirty and freepage may block
 
                         BKL     PageLocked(page)        i_mutex
 writepage:              no      yes, unlocks (see below)
@@ -193,6 +194,7 @@ perform_write:		no	n/a			yes
 bmap:                   no
 invalidatepage:         no      yes
 releasepage:            no      yes
+freepage:               no      yes
 direct_IO:              no
 launder_page:           no      yes
 
@@ -288,6 +290,9 @@ buffers from the page in preparation for freeing it.  It returns zero to
 indicate that the buffers are (or may be) freeable.  If ->releasepage is zero,
 the kernel assumes that the fs has no private interest in the buffers.
 
+        ->freepage() is called when the kernel is done dropping the page
+from the page cache.
+
         ->launder_page() may be called prior to releasing a page if
 it is still found to be dirty. It returns zero if the page was successfully
 cleaned, or an error value if not. Note that in order to prevent the page
diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index ed7e5efc06d8..20899e095e7e 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/Documentation/filesystems/vfs.txt
@@ -534,6 +534,7 @@ struct address_space_operations {
         sector_t (*bmap)(struct address_space *, sector_t);
         int (*invalidatepage) (struct page *, unsigned long);
         int (*releasepage) (struct page *, int);
+        void (*freepage)(struct page *);
         ssize_t (*direct_IO)(int, struct kiocb *, const struct iovec *iov,
                         loff_t offset, unsigned long nr_segs);
         struct page* (*get_xip_page)(struct address_space *, sector_t,
@@ -660,11 +661,10 @@ struct address_space_operations {
   releasepage: releasepage is called on PagePrivate pages to indicate
         that the page should be freed if possible.  ->releasepage
         should remove any private data from the page and clear the
-        PagePrivate flag.  It may also remove the page from the
-        address_space.  If this fails for some reason, it may indicate
-        failure with a 0 return value.
-        This is used in two distinct though related cases.  The first
-        is when the VM finds a clean page with no active users and
+        PagePrivate flag. If releasepage() fails for some reason, it must
+        indicate failure with a 0 return value.
+        releasepage() is used in two distinct though related cases.  The
+        first is when the VM finds a clean page with no active users and
         wants to make it a free page.  If ->releasepage succeeds, the
         page will be removed from the address_space and become free.
 
@@ -679,6 +679,12 @@ struct address_space_operations {
         need to ensure this.  Possibly it can clear the PageUptodate
         bit if it cannot free private data yet.
 
+  freepage: freepage is called once the page is no longer visible in
+        the page cache in order to allow the cleanup of any private
+        data. Since it may be called by the memory reclaimer, it
+        should not assume that the original address_space mapping still
+        exists, and it should not block.
+
   direct_IO: called by the generic read/write routines to perform
         direct_IO - that is IO requests which bypass the page cache
         and transfer data directly between the storage and the
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 69bb6a9c871a..e51fbd88661d 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -2183,11 +2183,6 @@ and is between 256 and 4096 characters. It is defined in the file
         reset_devices   [KNL] Force drivers to reset the underlying device
                         during initialization.
 
-        resource_alloc_from_bottom
-                        Allocate new resources from the beginning of available
-                        space, not the end.  If you need to use this, please
-                        report a bug.
-
         resume=         [SWSUSP]
                         Specify the partition device for software suspend
 
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index fe95105992c5..3c5e465296e1 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -144,6 +144,7 @@ tcp_adv_win_scale - INTEGER
         Count buffering overhead as bytes/2^tcp_adv_win_scale
         (if tcp_adv_win_scale > 0) or bytes-bytes/2^(-tcp_adv_win_scale),
         if it is <= 0.
+        Possible values are [-31, 31], inclusive.
         Default: 2
 
 tcp_allowed_congestion_control - STRING
diff --git a/Documentation/power/runtime_pm.txt b/Documentation/power/runtime_pm.txt
index 489e9bacd165..41cc7b30d7dd 100644
--- a/Documentation/power/runtime_pm.txt
+++ b/Documentation/power/runtime_pm.txt
@@ -379,8 +379,8 @@ drivers/base/power/runtime.c and include/linux/pm_runtime.h:
       zero)
 
   bool pm_runtime_suspended(struct device *dev);
-    - return true if the device's runtime PM status is 'suspended', or false
-      otherwise
+    - return true if the device's runtime PM status is 'suspended' and its
+      'power.disable_depth' field is equal to zero, or false otherwise
 
   void pm_runtime_allow(struct device *dev);
     - set the power.runtime_auto flag for the device and decrease its usage
diff --git a/Documentation/scsi/scsi_mid_low_api.txt b/Documentation/scsi/scsi_mid_low_api.txt
index 570ef2b3d79b..df322c103466 100644
--- a/Documentation/scsi/scsi_mid_low_api.txt
+++ b/Documentation/scsi/scsi_mid_low_api.txt
@@ -1044,9 +1044,9 @@ Details:
 
 
 /**
- *      queuecommand - queue scsi command, invoke 'done' on completion
+ *      queuecommand - queue scsi command, invoke scp->scsi_done on completion
+ *      @shost: pointer to the scsi host object
  *      @scp: pointer to scsi command object
- *      @done: function pointer to be invoked on completion
  *
  *      Returns 0 on success.
  *
@@ -1074,42 +1074,45 @@ Details:
  *
  *      Other types of errors that are detected immediately may be
  *      flagged by setting scp->result to an appropriate value,
- *      invoking the 'done' callback, and then returning 0 from this
- *      function. If the command is not performed immediately (and the
- *      LLD is starting (or will start) the given command) then this
- *      function should place 0 in scp->result and return 0.
+ *      invoking the scp->scsi_done callback, and then returning 0
+ *      from this function. If the command is not performed
+ *      immediately (and the LLD is starting (or will start) the given
+ *      command) then this function should place 0 in scp->result and
+ *      return 0.
  *
  *      Command ownership.  If the driver returns zero, it owns the
- *      command and must take responsibility for ensuring the 'done'
- *      callback is executed.  Note: the driver may call done before
- *      returning zero, but after it has called done, it may not
- *      return any value other than zero.  If the driver makes a
- *      non-zero return, it must not execute the command's done
- *      callback at any time.
- *
- *      Locks: struct Scsi_Host::host_lock held on entry (with "irqsave")
- *             and is expected to be held on return.
+ *      command and must take responsibility for ensuring the
+ *      scp->scsi_done callback is executed.  Note: the driver may
+ *      call scp->scsi_done before returning zero, but after it has
+ *      called scp->scsi_done, it may not return any value other than
+ *      zero.  If the driver makes a non-zero return, it must not
+ *      execute the command's scsi_done callback at any time.
+ *
+ *      Locks: up to and including 2.6.36, struct Scsi_Host::host_lock
+ *             held on entry (with "irqsave") and is expected to be
+ *             held on return. From 2.6.37 onwards, queuecommand is
+ *             called without any locks held.
  *
  *      Calling context: in interrupt (soft irq) or process context
  *
- *      Notes: This function should be relatively fast. Normally it will
- *      not wait for IO to complete. Hence the 'done' callback is invoked 
- *      (often directly from an interrupt service routine) some time after
- *      this function has returned. In some cases (e.g. pseudo adapter 
- *      drivers that manufacture the response to a SCSI INQUIRY)
- *      the 'done' callback may be invoked before this function returns.
- *      If the 'done' callback is not invoked within a certain period
- *      the SCSI mid level will commence error processing.
- *      If a status of CHECK CONDITION is placed in "result" when the
- *      'done' callback is invoked, then the LLD driver should 
- *      perform autosense and fill in the struct scsi_cmnd::sense_buffer
+ *      Notes: This function should be relatively fast. Normally it
+ *      will not wait for IO to complete. Hence the scp->scsi_done
+ *      callback is invoked (often directly from an interrupt service
+ *      routine) some time after this function has returned. In some
+ *      cases (e.g. pseudo adapter drivers that manufacture the
+ *      response to a SCSI INQUIRY) the scp->scsi_done callback may be
+ *      invoked before this function returns.  If the scp->scsi_done
+ *      callback is not invoked within a certain period the SCSI mid
+ *      level will commence error processing.  If a status of CHECK
+ *      CONDITION is placed in "result" when the scp->scsi_done
+ *      callback is invoked, then the LLD driver should perform
+ *      autosense and fill in the struct scsi_cmnd::sense_buffer
  *      array. The scsi_cmnd::sense_buffer array is zeroed prior to
  *      the mid level queuing a command to an LLD.
  *
  *      Defined in: LLD
  **/
-    int queuecommand(struct scsi_cmnd * scp, 
-                     void (*done)(struct scsi_cmnd *))
+    int queuecommand(struct Scsi_Host *shost, struct scsi_cmnd * scp)
 
 
 /**
diff --git a/Documentation/trace/postprocess/trace-vmscan-postprocess.pl b/Documentation/trace/postprocess/trace-vmscan-postprocess.pl
index b3e73ddb1567..12cecc83cd91 100644
--- a/Documentation/trace/postprocess/trace-vmscan-postprocess.pl
+++ b/Documentation/trace/postprocess/trace-vmscan-postprocess.pl
@@ -373,9 +373,18 @@ EVENT_PROCESS:
                                 print "         $regex_lru_isolate/o\n";
                                 next;
                         }
+                        my $isolate_mode = $1;
                         my $nr_scanned = $4;
                         my $nr_contig_dirty = $7;
-                        $perprocesspid{$process_pid}->{HIGH_NR_SCANNED} += $nr_scanned;
+
+                        # To closer match vmstat scanning statistics, only count isolate_both
+                        # and isolate_inactive as scanning. isolate_active is rotation
+                        # isolate_inactive == 0
+                        # isolate_active   == 1
+                        # isolate_both     == 2
+                        if ($isolate_mode != 1) {
+                                $perprocesspid{$process_pid}->{HIGH_NR_SCANNED} += $nr_scanned;
+                        }
                         $perprocesspid{$process_pid}->{HIGH_NR_CONTIG_DIRTY} += $nr_contig_dirty;
                 } elsif ($tracepoint eq "mm_vmscan_lru_shrink_inactive") {
                         $details = $5;