11 files changed, 261 insertions, 53 deletions

diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt
index 21272e4b4a5c..495858b236b6 100644
--- a/Documentation/feature-removal-schedule.txt
+++ b/Documentation/feature-removal-schedule.txt
@@ -176,6 +176,18 @@ Who:	Richard Knutsson <ricknu-0@student.ltu.se> and Greg Kroah-Hartman <gregkh@s
 
 ---------------------------
 
+What:   Usage of invalid timevals in setitimer
+When:   March 2007
+Why:    POSIX requires to validate timevals in the setitimer call. This
+        was never done by Linux. The invalid (e.g. negative timevals) were
+        silently converted to more or less random timeouts and intervals.
+        Until the removal a per boot limited number of warnings is printed
+        and the timevals are sanitized.
+
+Who:    Thomas Gleixner <tglx@linutronix.de>
+
+---------------------------
+
 What:   I2C interface of the it87 driver
 When:   January 2007
 Why:    The ISA interface is faster and should be always available. The I2C
diff --git a/Documentation/filesystems/v9fs.txt b/Documentation/filesystems/9p.txt
index 24c7a9c41f0d..43b89c214d20 100644
--- a/Documentation/filesystems/v9fs.txt
+++ b/Documentation/filesystems/9p.txt
@@ -1,5 +1,5 @@
-                        V9FS: 9P2000 for Linux
-                        ======================
+                    v9fs: Plan 9 Resource Sharing for Linux
+                    =======================================
 
 ABOUT
 =====
@@ -9,18 +9,19 @@ v9fs is a Unix implementation of the Plan 9 9p remote filesystem protocol.
 This software was originally developed by Ron Minnich <rminnich@lanl.gov>
 and Maya Gokhale <maya@lanl.gov>.  Additional development by Greg Watson
 <gwatson@lanl.gov> and most recently Eric Van Hensbergen
-<ericvh@gmail.com> and Latchesar Ionkov <lucho@ionkov.net>.
+<ericvh@gmail.com>, Latchesar Ionkov <lucho@ionkov.net> and Russ Cox
+<rsc@swtch.com>.
 
 USAGE
 =====
 
 For remote file server:
 
-        mount -t 9P 10.10.1.2 /mnt/9
+        mount -t 9p 10.10.1.2 /mnt/9
 
 For Plan 9 From User Space applications (http://swtch.com/plan9)
 
-        mount -t 9P `namespace`/acme /mnt/9 -o proto=unix,name=$USER
+        mount -t 9p `namespace`/acme /mnt/9 -o proto=unix,uname=$USER
 
 OPTIONS
 =======
@@ -32,7 +33,7 @@ OPTIONS
                         fd   - used passed file descriptors for connection
                                 (see rfdno and wfdno)
 
-  name=name     user name to attempt mount as on the remote server.  The
+  uname=name    user name to attempt mount as on the remote server.  The
                 server may override or ignore this value.  Certain user
                 names may require authentication.
 
@@ -42,7 +43,7 @@ OPTIONS
   debug=n       specifies debug level.  The debug level is a bitmask.
                         0x01 = display verbose error messages
                         0x02 = developer debug (DEBUG_CURRENT)
-                        0x04 = display 9P trace
+                        0x04 = display 9p trace
                         0x08 = display VFS trace
                         0x10 = display Marshalling debug
                         0x20 = display RPC debug
@@ -53,11 +54,11 @@ OPTIONS
 
   wfdno=n       the file descriptor for writing with proto=fd
 
-  maxdata=n     the number of bytes to use for 9P packet payload (msize)
+  maxdata=n     the number of bytes to use for 9p packet payload (msize)
 
   port=n        port to connect to on the remote server
 
-  noextend      force legacy mode (no 9P2000.u semantics)
+  noextend      force legacy mode (no 9p2000.u semantics)
 
   uid           attempt to mount as a particular uid
 
@@ -72,7 +73,7 @@ OPTIONS
 RESOURCES
 =========
 
-The Linux version of the 9P server is now maintained under the npfs project
+The Linux version of the 9p server is now maintained under the npfs project
 on sourceforge (http://sourceforge.net/projects/npfs).
 
 There are user and developer mailing lists available through the v9fs project
diff --git a/Documentation/filesystems/udf.txt b/Documentation/filesystems/udf.txt
index e5213bc301f7..511b4230c053 100644
--- a/Documentation/filesystems/udf.txt
+++ b/Documentation/filesystems/udf.txt
@@ -26,6 +26,20 @@ The following mount options are supported:
         nostrict        Unset strict conformance
         iocharset=      Set the NLS character set
 
+The uid= and gid= options need a bit more explaining.  They will accept a
+decimal numeric value which will be used as the default ID for that mount.
+They will also accept the string "ignore" and "forget".  For files on the disk
+that are owned by nobody ( -1 ), they will instead look as if they are owned
+by the default ID.  The ignore option causes the default ID to override all
+IDs on the disk, not just -1.  The forget option causes all IDs to be written
+to disk as -1, so when the media is later remounted, they will appear to be
+owned by whatever default ID it is mounted with at that time.
+
+For typical desktop use of removable media, you should set the ID to that
+of the interactively logged on user, and also specify both the forget and
+ignore options.  This way the interactive user will always see the files
+on the disk as belonging to him.
+
 The remaining are for debugging and disaster recovery:
 
         novrs           Skip volume sequence recognition 
diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index e56e842847d3..adaa899e5c90 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/Documentation/filesystems/vfs.txt
@@ -230,10 +230,15 @@ only called from a process context (i.e. not from an interrupt handler
 or bottom half).
 
   alloc_inode: this method is called by inode_alloc() to allocate memory
-        for struct inode and initialize it.
+        for struct inode and initialize it.  If this function is not
+        defined, a simple 'struct inode' is allocated.  Normally
+        alloc_inode will be used to allocate a larger structure which
+        contains a 'struct inode' embedded within it.
 
   destroy_inode: this method is called by destroy_inode() to release
-        resources allocated for struct inode.
+        resources allocated for struct inode.  It is only required if
+        ->alloc_inode was defined and simply undoes anything done by
+        ->alloc_inode.
 
   read_inode: this method is called to read a specific inode from the
         mounted filesystem.  The i_ino member in the struct inode is
@@ -443,14 +448,81 @@ otherwise noted.
 The Address Space Object
 ========================
 
-The address space object is used to identify pages in the page cache.
-
+The address space object is used to group and manage pages in the page
+cache.  It can be used to keep track of the pages in a file (or
+anything else) and also track the mapping of sections of the file into
+process address spaces.
+
+There are a number of distinct yet related services that an
+address-space can provide.  These include communicating memory
+pressure, page lookup by address, and keeping track of pages tagged as
+Dirty or Writeback.
+
+The first can be used independently to the others.  The VM can try to
+either write dirty pages in order to clean them, or release clean
+pages in order to reuse them.  To do this it can call the ->writepage
+method on dirty pages, and ->releasepage on clean pages with
+PagePrivate set. Clean pages without PagePrivate and with no external
+references will be released without notice being given to the
+address_space.
+
+To achieve this functionality, pages need to be placed on an LRU with
+lru_cache_add and mark_page_active needs to be called whenever the
+page is used.
+
+Pages are normally kept in a radix tree index by ->index. This tree
+maintains information about the PG_Dirty and PG_Writeback status of
+each page, so that pages with either of these flags can be found
+quickly.
+
+The Dirty tag is primarily used by mpage_writepages - the default
+->writepages method.  It uses the tag to find dirty pages to call
+->writepage on.  If mpage_writepages is not used (i.e. the address
+provides its own ->writepages) , the PAGECACHE_TAG_DIRTY tag is
+almost unused.  write_inode_now and sync_inode do use it (through
+__sync_single_inode) to check if ->writepages has been successful in
+writing out the whole address_space.
+
+The Writeback tag is used by filemap*wait* and sync_page* functions,
+via wait_on_page_writeback_range, to wait for all writeback to
+complete.  While waiting ->sync_page (if defined) will be called on
+each page that is found to require writeback.
+
+An address_space handler may attach extra information to a page,
+typically using the 'private' field in the 'struct page'.  If such
+information is attached, the PG_Private flag should be set.  This will
+cause various VM routines to make extra calls into the address_space
+handler to deal with that data.
+
+An address space acts as an intermediate between storage and
+application.  Data is read into the address space a whole page at a
+time, and provided to the application either by copying of the page,
+or by memory-mapping the page.
+Data is written into the address space by the application, and then
+written-back to storage typically in whole pages, however the
+address_space has finer control of write sizes.
+
+The read process essentially only requires 'readpage'.  The write
+process is more complicated and uses prepare_write/commit_write or
+set_page_dirty to write data into the address_space, and writepage,
+sync_page, and writepages to writeback data to storage.
+
+Adding and removing pages to/from an address_space is protected by the
+inode's i_mutex.
+
+When data is written to a page, the PG_Dirty flag should be set.  It
+typically remains set until writepage asks for it to be written.  This
+should clear PG_Dirty and set PG_Writeback.  It can be actually
+written at any point after PG_Dirty is clear.  Once it is known to be
+safe, PG_Writeback is cleared.
+
+Writeback makes use of a writeback_control structure...
 
 struct address_space_operations
 -------------------------------
 
 This describes how the VFS can manipulate mapping of a file to page cache in
-your filesystem. As of kernel 2.6.13, the following members are defined:
+your filesystem. As of kernel 2.6.16, the following members are defined:
 
 struct address_space_operations {
         int (*writepage)(struct page *page, struct writeback_control *wbc);
@@ -469,47 +541,148 @@ struct address_space_operations {
                         loff_t offset, unsigned long nr_segs);
         struct page* (*get_xip_page)(struct address_space *, sector_t,
                         int);
+        /* migrate the contents of a page to the specified target */
+        int (*migratepage) (struct page *, struct page *);
 };
 
-  writepage: called by the VM write a dirty page to backing store.
+  writepage: called by the VM to write a dirty page to backing store.
+      This may happen for data integrity reasons (i.e. 'sync'), or
+      to free up memory (flush).  The difference can be seen in
+      wbc->sync_mode.
+      The PG_Dirty flag has been cleared and PageLocked is true.
+      writepage should start writeout, should set PG_Writeback,
+      and should make sure the page is unlocked, either synchronously
+      or asynchronously when the write operation completes.
+
+      If wbc->sync_mode is WB_SYNC_NONE, ->writepage doesn't have to
+      try too hard if there are problems, and may choose to write out
+      other pages from the mapping if that is easier (e.g. due to
+      internal dependencies).  If it chooses not to start writeout, it
+      should return AOP_WRITEPAGE_ACTIVATE so that the VM will not keep
+      calling ->writepage on that page.
+
+      See the file "Locking" for more details.
 
   readpage: called by the VM to read a page from backing store.
+       The page will be Locked when readpage is called, and should be
+       unlocked and marked uptodate once the read completes.
+       If ->readpage discovers that it needs to unlock the page for
+       some reason, it can do so, and then return AOP_TRUNCATED_PAGE.
+       In this case, the page will be relocated, relocked and if
+       that all succeeds, ->readpage will be called again.
 
   sync_page: called by the VM to notify the backing store to perform all
         queued I/O operations for a page. I/O operations for other pages
         associated with this address_space object may also be performed.
 
+        This function is optional and is called only for pages with
+        PG_Writeback set while waiting for the writeback to complete.
+
   writepages: called by the VM to write out pages associated with the
-        address_space object.
+        address_space object.  If wbc->sync_mode is WBC_SYNC_ALL, then
+        the writeback_control will specify a range of pages that must be
+        written out.  If it is WBC_SYNC_NONE, then a nr_to_write is given
+        and that many pages should be written if possible.
+        If no ->writepages is given, then mpage_writepages is used
+        instead.  This will choose pages from the address space that are
+        tagged as DIRTY and will pass them to ->writepage.
 
   set_page_dirty: called by the VM to set a page dirty.
+        This is particularly needed if an address space attaches
+        private data to a page, and that data needs to be updated when
+        a page is dirtied.  This is called, for example, when a memory
+        mapped page gets modified.
+        If defined, it should set the PageDirty flag, and the
+        PAGECACHE_TAG_DIRTY tag in the radix tree.
 
   readpages: called by the VM to read pages associated with the address_space
-        object.
+        object. This is essentially just a vector version of
+        readpage.  Instead of just one page, several pages are
+        requested.
+        readpages is only used for read-ahead, so read errors are
+        ignored.  If anything goes wrong, feel free to give up.
 
   prepare_write: called by the generic write path in VM to set up a write
-        request for a page.
-
-  commit_write: called by the generic write path in VM to write page to
-        its backing store.
+        request for a page.  This indicates to the address space that
+        the given range of bytes is about to be written.  The
+        address_space should check that the write will be able to
+        complete, by allocating space if necessary and doing any other
+        internal housekeeping.  If the write will update parts of
+        any basic-blocks on storage, then those blocks should be
+        pre-read (if they haven't been read already) so that the
+        updated blocks can be written out properly.
+        The page will be locked.  If prepare_write wants to unlock the
+        page it, like readpage, may do so and return
+        AOP_TRUNCATED_PAGE.
+        In this case the prepare_write will be retried one the lock is
+        regained.
+
+  commit_write: If prepare_write succeeds, new data will be copied
+        into the page and then commit_write will be called.  It will
+        typically update the size of the file (if appropriate) and
+        mark the inode as dirty, and do any other related housekeeping
+        operations.  It should avoid returning an error if possible -
+        errors should have been handled by prepare_write.
 
   bmap: called by the VFS to map a logical block offset within object to
-        physical block number. This method is use by for the legacy FIBMAP
-        ioctl. Other uses are discouraged.
-
-  invalidatepage: called by the VM on truncate to disassociate a page from its
-        address_space mapping.
-
-  releasepage: called by the VFS to release filesystem specific metadata from
-        a page.
-
-  direct_IO: called by the VM for direct I/O writes and reads.
+        physical block number. This method is used by the FIBMAP
+        ioctl and for working with swap-files.  To be able to swap to
+        a file, the file must have a stable mapping to a block
+        device.  The swap system does not go through the filesystem
+        but instead uses bmap to find out where the blocks in the file
+        are and uses those addresses directly.
+
+
+  invalidatepage: If a page has PagePrivate set, then invalidatepage
+        will be called when part or all of the page is to be removed
+        from the address space.  This generally corresponds to either a
+        truncation or a complete invalidation of the address space
+        (in the latter case 'offset' will always be 0).
+        Any private data associated with the page should be updated
+        to reflect this truncation.  If offset is 0, then
+        the private data should be released, because the page
+        must be able to be completely discarded.  This may be done by
+        calling the ->releasepage function, but in this case the
+        release MUST succeed.
+
+  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
+        wants to make it a free page.  If ->releasepage succeeds, the
+        page will be removed from the address_space and become free.
+
+        The second case if when a request has been made to invalidate
+        some or all pages in an address_space.  This can happen
+        through the fadvice(POSIX_FADV_DONTNEED) system call or by the
+        filesystem explicitly requesting it as nfs and 9fs do (when
+        they believe the cache may be out of date with storage) by
+        calling invalidate_inode_pages2().
+        If the filesystem makes such a call, and needs to be certain
+        that all pages are invalidated, then its releasepage will
+        need to ensure this.  Possibly it can clear the PageUptodate
+        bit if it cannot free private data yet.
+
+  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
+        application's address space.
 
   get_xip_page: called by the VM to translate a block number to a page.
         The page is valid until the corresponding filesystem is unmounted.
         Filesystems that want to use execute-in-place (XIP) need to implement
         it.  An example implementation can be found in fs/ext2/xip.c.
 
+  migrate_page:  This is used to compact the physical memory usage.
+        If the VM wants to relocate a page (maybe off a memory card
+        that is signalling imminent failure) it will pass a new page
+        and an old page to this function.  migrate_page should
+        transfer any private data across and update any references
+        that it has to the page.
 
 The File Object
 ===============
diff --git a/Documentation/firmware_class/firmware_sample_driver.c b/Documentation/firmware_class/firmware_sample_driver.c
index d3ad2c24490a..ad3edaba4533 100644
--- a/Documentation/firmware_class/firmware_sample_driver.c
+++ b/Documentation/firmware_class/firmware_sample_driver.c
@@ -23,7 +23,6 @@ char __init inkernel_firmware[] = "let's say that this is firmware\n";
 #endif
 
 static struct device ghost_device = {
-        .name      = "Ghost Device",
         .bus_id    = "ghost0",
 };
 
@@ -92,7 +91,7 @@ static void sample_probe_async(void)
 {
         /* Let's say that I can't sleep */
         int error;
-        error = request_firmware_nowait (THIS_MODULE,
+        error = request_firmware_nowait (THIS_MODULE, FW_ACTION_NOHOTPLUG,
                                          "sample_driver_fw", &ghost_device,
                                          "my device pointer",
                                          sample_probe_async_cont);
diff --git a/Documentation/firmware_class/firmware_sample_firmware_class.c b/Documentation/firmware_class/firmware_sample_firmware_class.c
index 57b956aecbc5..9e1b0e4051cd 100644
--- a/Documentation/firmware_class/firmware_sample_firmware_class.c
+++ b/Documentation/firmware_class/firmware_sample_firmware_class.c
@@ -172,7 +172,6 @@ static void fw_remove_class_device(struct class_device *class_dev)
 static struct class_device *class_dev;
 
 static struct device my_device = {
-        .name      = "Sample Device",
         .bus_id    = "my_dev0",
 };
 
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 44a25f3f51d1..f8cb55c30b0f 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -367,12 +367,17 @@ running once the system is up.
                 tty<n>  Use the virtual console device <n>.
 
                 ttyS<n>[,options]
+                ttyUSB0[,options]
                         Use the specified serial port.  The options are of
-                        the form "bbbbpn", where "bbbb" is the baud rate,
-                        "p" is parity ("n", "o", or "e"), and "n" is bits.
-                        Default is "9600n8".
-
-                        See also Documentation/serial-console.txt.
+                        the form "bbbbpnf", where "bbbb" is the baud rate,
+                        "p" is parity ("n", "o", or "e"), "n" is number of
+                        bits, and "f" is flow control ("r" for RTS or
+                        omit it).  Default is "9600n8".
+
+                        See Documentation/serial-console.txt for more
+                        information.  See
+                        Documentation/networking/netconsole.txt for an
+                        alternative.
 
                 uart,io,<addr>[,options]
                 uart,mmio,<addr>[,options]
diff --git a/Documentation/networking/ray_cs.txt b/Documentation/networking/ray_cs.txt
index 5427f8c7df95..145d27a52395 100644
--- a/Documentation/networking/ray_cs.txt
+++ b/Documentation/networking/ray_cs.txt
@@ -25,7 +25,7 @@ the essid= string parameter is available via the kernel command line.
 This will change after the method of sorting out parameters for all
 the PCMCIA drivers is agreed upon.  If you must have a built in driver
 with nondefault parameters, they can be edited in
-/usr/src/linux/drivers/net/pcmcia/ray_cs.c.  Searching for MODULE_PARM
+/usr/src/linux/drivers/net/pcmcia/ray_cs.c.  Searching for module_param
 will find them all.
 
 Information on card services is available at:
diff --git a/Documentation/serial-console.txt b/Documentation/serial-console.txt
index 6c689b0df2b8..9a7bc8b3f479 100644
--- a/Documentation/serial-console.txt
+++ b/Documentation/serial-console.txt
@@ -17,11 +17,13 @@ The format of this option is:
                         ttyX for any other virtual console
                         ttySx for a serial port
                         lp0 for the first parallel port
+                        ttyUSB0 for the first USB serial device
 
         options:        depend on the driver. For the serial port this
-                        defines the baudrate/parity/bits of the port,
-                        in the format BBBBPN, where BBBB is the speed,
-                        P is parity (n/o/e), and N is bits. Default is
+                        defines the baudrate/parity/bits/flow control of
+                        the port, in the format BBBBPNF, where BBBB is the
+                        speed, P is parity (n/o/e), N is number of bits,
+                        and F is flow control ('r' for RTS). Default is
                         9600n8. The maximum baudrate is 115200.
 
 You can specify multiple console= options on the kernel command line.
@@ -45,6 +47,9 @@ become the console.
 You will need to create a new device to use /dev/console. The official
 /dev/console is now character device 5,1.
 
+(You can also use a network device as a console.  See
+Documentation/networking/netconsole.txt for information on that.)
+
 Here's an example that will use /dev/ttyS1 (COM2) as the console.
 Replace the sample values as needed.
 
diff --git a/Documentation/sound/oss/Introduction b/Documentation/sound/oss/Introduction
index 15d4fb975ac0..f04ba6bb7395 100644
--- a/Documentation/sound/oss/Introduction
+++ b/Documentation/sound/oss/Introduction
@@ -69,7 +69,7 @@ are available, for example IRQ, address, DMA.
 
 Warning, the options for different cards sometime use different names 
 for the same or a similar feature (dma1= versus dma16=).  As a last 
-resort, inspect the code (search for MODULE_PARM).
+resort, inspect the code (search for module_param).
 
 Notes:
 
diff --git a/Documentation/sound/oss/cs46xx b/Documentation/sound/oss/cs46xx
index 88d6cf8b39f3..b54432709863 100644
--- a/Documentation/sound/oss/cs46xx
+++ b/Documentation/sound/oss/cs46xx
@@ -88,7 +88,7 @@ parameters.  for a copy email: twoller@crystal.cirrus.com
 
 MODULE_PARMS definitions
 ------------------------
-MODULE_PARM(defaultorder, "i");
+module_param(defaultorder, ulong, 0);
 defaultorder=N
 where N is a value from 1 to 12
 The buffer order determines the size of the dma buffer for the driver.
@@ -98,18 +98,18 @@ to not underrun the dma buffer as easily.  As default, use 32k (order=3)
 rather than 64k as some of the games work more responsively.
 (2^N) * PAGE_SIZE = allocated buffer size
 
-MODULE_PARM(cs_debuglevel, "i");
-MODULE_PARM(cs_debugmask, "i");
+module_param(cs_debuglevel, ulong, 0644);
+module_param(cs_debugmask, ulong, 0644);
 cs_debuglevel=N
 cs_debugmask=0xMMMMMMMM
 where N is a value from 0 (no debug printfs), to 9 (maximum)
 0xMMMMMMMM is a debug mask corresponding to the CS_xxx bits (see driver source).
 
-MODULE_PARM(hercules_egpio_disable, "i");
+module_param(hercules_egpio_disable, ulong, 0);
 hercules_egpio_disable=N
 where N is a 0 (enable egpio), or a 1 (disable egpio support)
 
-MODULE_PARM(initdelay, "i");
+module_param(initdelay, ulong, 0);
 initdelay=N
 This value is used to determine the millescond delay during the initialization
 code prior to powering up the PLL.  On laptops this value can be used to
@@ -118,19 +118,19 @@ system is booted under battery power then the mdelay()/udelay() functions fail t
 properly delay the required time.  Also, if the system is booted under AC power
 and then the power removed, the mdelay()/udelay() functions will not delay properly.
  
-MODULE_PARM(powerdown, "i");
+module_param(powerdown, ulong, 0);
 powerdown=N
 where N is 0 (disable any powerdown of the internal blocks) or 1 (enable powerdown)
 
 
-MODULE_PARM(external_amp, "i");
+module_param(external_amp, bool, 0);
 external_amp=1
 if N is set to 1, then force enabling the EAPD support in the primary AC97 codec.
 override the detection logic and force the external amp bit in the AC97 0x26 register
 to be reset (0).  EAPD should be 0 for powerup, and 1 for powerdown.  The VTB Santa Cruz
 card has inverted logic, so there is a special function for these cards.
 
-MODULE_PARM(thinkpad, "i");
+module_param(thinkpad, bool, 0);
 thinkpad=1
 if N is set to 1, then force enabling the clkrun functionality.
 Currently, when the part is being used, then clkrun is disabled for the entire system,