Merge ../linux-2.6

.gitignore

@@ -30,6 +30,11 @@ include/config
 include/linux/autoconf.h
 include/linux/compile.h
 include/linux/version.h
+include/linux/utsrelease.h
 
 # stgit generated dirs
 patches-*
+
+# quilt's files
+patches
+series

CREDITS

@@ -2209,7 +2209,7 @@ S: (address available on request)
 S: USA
 
 N: Ian McDonald
-E: iam4@cs.waikato.ac.nz
+E: ian.mcdonald@jandi.co.nz
 E: imcdnzl@gmail.com
 W: http://wand.net.nz/~iam4
 W: http://imcdnzl.blogspot.com

Documentation/DocBook/kernel-api.tmpl

@@ -58,6 +58,9 @@
 !Iinclude/linux/ktime.h
 !Iinclude/linux/hrtimer.h
 !Ekernel/hrtimer.c
+     </sect1>
+     <sect1><title>Workqueues and Kevents</title>
+!Ekernel/workqueue.c
      </sect1>
      <sect1><title>Internal Functions</title>
 !Ikernel/exit.c
@@ -300,7 +303,7 @@ X!Ekernel/module.c
      </sect1>
 
      <sect1><title>Resources Management</title>
-!Ekernel/resource.c
+!Ikernel/resource.c
      </sect1>
 
      <sect1><title>MTRR Handling</title>
@@ -312,9 +315,7 @@ X!Ekernel/module.c
 !Edrivers/pci/pci-driver.c
 !Edrivers/pci/remove.c
 !Edrivers/pci/pci-acpi.c
-<!-- kerneldoc does not understand __devinit
+!Edrivers/pci/search.c
-X!Edrivers/pci/search.c
- -->
 !Edrivers/pci/msi.c
 !Edrivers/pci/bus.c
 <!-- FIXME: Removed for now since no structured comments in source

Documentation/SubmittingPatches

@@ -10,7 +10,9 @@ kernel, the process can sometimes be daunting if you're not familiar
 with "the system."  This text is a collection of suggestions which
 can greatly increase the chances of your change being accepted.
 
-If you are submitting a driver, also read Documentation/SubmittingDrivers.
+Read Documentation/SubmitChecklist for a list of items to check
+before submitting code.  If you are submitting a driver, also read
+Documentation/SubmittingDrivers.
 
 
 
@@ -74,9 +76,6 @@ There are a number of scripts which can aid in this:
 Quilt:
 http://savannah.nongnu.org/projects/quilt
 
-Randy Dunlap's patch scripts:
-http://www.xenotime.net/linux/scripts/patching-scripts-002.tar.gz
-
 Andrew Morton's patch scripts:
 http://www.zip.com.au/~akpm/linux/patches/
 Instead of these scripts, quilt is the recommended patch management
@@ -484,7 +483,7 @@ Greg Kroah-Hartman "How to piss off a kernel subsystem maintainer".
   <http://www.kroah.com/log/2005/10/19/>
   <http://www.kroah.com/log/2006/01/11/>
 
-NO!!!! No more huge patch bombs to linux-kernel@vger.kernel.org people!.
+NO!!!! No more huge patch bombs to linux-kernel@vger.kernel.org people!
   <http://marc.theaimsgroup.com/?l=linux-kernel&m=112112749912944&w=2>
 
 Kernel Documentation/CodingStyle
@@ -493,4 +492,3 @@ Kernel Documentation/CodingStyle
 Linus Torvald's mail on the canonical patch format:
   <http://lkml.org/lkml/2005/4/7/183>
 --
-Last updated on 17 Nov 2005.

Documentation/accounting/delay-accounting.txt

@@ -64,11 +64,13 @@ Compile the kernel with
 	CONFIG_TASK_DELAY_ACCT=y
 	CONFIG_TASKSTATS=y
 
-Enable the accounting at boot time by adding
+Delay accounting is enabled by default at boot up.
-the following to the kernel boot options
+To disable, add
-	delayacct
+   nodelayacct
+to the kernel boot options. The rest of the instructions
+below assume this has not been done.
 
-and after the system has booted up, use a utility
+After the system has booted up, use a utility
 similar to  getdelays.c to access the delays
 seen by a given task or a task group (tgid).
 The utility also allows a given command to be

Documentation/connector/ucon.c

@@ -0,0 +1,206 @@
+/*
+ * 	ucon.c
+ *
+ * Copyright (c) 2004+ Evgeniy Polyakov <johnpol@2ka.mipt.ru>
+ *
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#include <asm/types.h>
+
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <sys/poll.h>
+
+#include <linux/netlink.h>
+#include <linux/rtnetlink.h>
+
+#include <arpa/inet.h>
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <string.h>
+#include <errno.h>
+#include <time.h>
+
+#include <linux/connector.h>
+
+#define DEBUG
+#define NETLINK_CONNECTOR 	11
+
+#ifdef DEBUG
+#define ulog(f, a...) fprintf(stdout, f, ##a)
+#else
+#define ulog(f, a...) do {} while (0)
+#endif
+
+static int need_exit;
+static __u32 seq;
+
+static int netlink_send(int s, struct cn_msg *msg)
+{
+	struct nlmsghdr *nlh;
+	unsigned int size;
+	int err;
+	char buf[128];
+	struct cn_msg *m;
+
+	size = NLMSG_SPACE(sizeof(struct cn_msg) + msg->len);
+
+	nlh = (struct nlmsghdr *)buf;
+	nlh->nlmsg_seq = seq++;
+	nlh->nlmsg_pid = getpid();
+	nlh->nlmsg_type = NLMSG_DONE;
+	nlh->nlmsg_len = NLMSG_LENGTH(size - sizeof(*nlh));
+	nlh->nlmsg_flags = 0;
+
+	m = NLMSG_DATA(nlh);
+#if 0
+	ulog("%s: [%08x.%08x] len=%u, seq=%u, ack=%u.\n",
+	       __func__, msg->id.idx, msg->id.val, msg->len, msg->seq, msg->ack);
+#endif
+	memcpy(m, msg, sizeof(*m) + msg->len);
+
+	err = send(s, nlh, size, 0);
+	if (err == -1)
+		ulog("Failed to send: %s [%d].\n",
+			strerror(errno), errno);
+
+	return err;
+}
+
+int main(int argc, char *argv[])
+{
+	int s;
+	char buf[1024];
+	int len;
+	struct nlmsghdr *reply;
+	struct sockaddr_nl l_local;
+	struct cn_msg *data;
+	FILE *out;
+	time_t tm;
+	struct pollfd pfd;
+
+	if (argc < 2)
+		out = stdout;
+	else {
+		out = fopen(argv[1], "a+");
+		if (!out) {
+			ulog("Unable to open %s for writing: %s\n",
+				argv[1], strerror(errno));
+			out = stdout;
+		}
+	}
+
+	memset(buf, 0, sizeof(buf));
+
+	s = socket(PF_NETLINK, SOCK_DGRAM, NETLINK_CONNECTOR);
+	if (s == -1) {
+		perror("socket");
+		return -1;
+	}
+
+	l_local.nl_family = AF_NETLINK;
+	l_local.nl_groups = 0x123; /* bitmask of requested groups */
+	l_local.nl_pid = 0;
+
+	if (bind(s, (struct sockaddr *)&l_local, sizeof(struct sockaddr_nl)) == -1) {
+		perror("bind");
+		close(s);
+		return -1;
+	}
+
+#if 0
+	{
+		int on = 0x57; /* Additional group number */
+		setsockopt(s, SOL_NETLINK, NETLINK_ADD_MEMBERSHIP, &on, sizeof(on));
+	}
+#endif
+	if (0) {
+		int i, j;
+
+		memset(buf, 0, sizeof(buf));
+
+		data = (struct cn_msg *)buf;
+
+		data->id.idx = 0x123;
+		data->id.val = 0x456;
+		data->seq = seq++;
+		data->ack = 0;
+		data->len = 0;
+
+		for (j=0; j<10; ++j) {
+			for (i=0; i<1000; ++i) {
+				len = netlink_send(s, data);
+			}
+
+			ulog("%d messages have been sent to %08x.%08x.\n", i, data->id.idx, data->id.val);
+		}
+
+		return 0;
+	}
+
+
+	pfd.fd = s;
+
+	while (!need_exit) {
+		pfd.events = POLLIN;
+		pfd.revents = 0;
+		switch (poll(&pfd, 1, -1)) {
+			case 0:
+				need_exit = 1;
+				break;
+			case -1:
+				if (errno != EINTR) {
+					need_exit = 1;
+					break;
+				}
+				continue;
+		}
+		if (need_exit)
+			break;
+
+		memset(buf, 0, sizeof(buf));
+		len = recv(s, buf, sizeof(buf), 0);
+		if (len == -1) {
+			perror("recv buf");
+			close(s);
+			return -1;
+		}
+		reply = (struct nlmsghdr *)buf;
+
+		switch (reply->nlmsg_type) {
+		case NLMSG_ERROR:
+			fprintf(out, "Error message received.\n");
+			fflush(out);
+			break;
+		case NLMSG_DONE:
+			data = (struct cn_msg *)NLMSG_DATA(reply);
+
+			time(&tm);
+			fprintf(out, "%.24s : [%x.%x] [%08u.%08u].\n",
+				ctime(&tm), data->id.idx, data->id.val, data->seq, data->ack);
+			fflush(out);
+			break;
+		default:
+			break;
+		}
+	}
+
+	close(s);
+	return 0;
+}

Documentation/cpu-freq/user-guide.txt

@@ -153,10 +153,13 @@ scaling_governor,		and by "echoing" the name of another
 				that some governors won't load - they only
 				work on some specific architectures or
 				processors.
-scaling_min_freq and 
+scaling_min_freq and
 scaling_max_freq		show the current "policy limits" (in
 				kHz). By echoing new values into these
 				files, you can change these limits.
+				NOTE: when setting a policy you need to
+				first set scaling_max_freq, then
+				scaling_min_freq.
 
 
 If you have selected the "userspace" governor which allows you to

Documentation/cpu-hotplug.txt

@@ -251,16 +251,24 @@ A: This is what you would need in your kernel code to receive notifications.
 		return NOTIFY_OK;
 	}
 
-	static struct notifier_block foobar_cpu_notifer =
+	static struct notifier_block __cpuinitdata foobar_cpu_notifer =
 	{
 	   .notifier_call = foobar_cpu_callback,
 	};
 
+You need to call register_cpu_notifier() from your init function.
+Init functions could be of two types:
+1. early init (init function called when only the boot processor is online).
+2. late init (init function called _after_ all the CPUs are online).
 
-In your init function,
+For the first case, you should add the following to your init function
 
 	register_cpu_notifier(&foobar_cpu_notifier);
 
+For the second case, you should add the following to your init function
+
+	register_hotcpu_notifier(&foobar_cpu_notifier);
+
 You can fail PREPARE notifiers if something doesn't work to prepare resources.
 This will stop the activity and send a following CANCELED event back.
 

Documentation/cpusets.txt

@@ -217,6 +217,12 @@ exclusive cpuset.  Also, the use of a Linux virtual file system (vfs)
 to represent the cpuset hierarchy provides for a familiar permission
 and name space for cpusets, with a minimum of additional kernel code.
 
+The cpus file in the root (top_cpuset) cpuset is read-only.
+It automatically tracks the value of cpu_online_map, using a CPU
+hotplug notifier.  If and when memory nodes can be hotplugged,
+we expect to make the mems file in the root cpuset read-only
+as well, and have it track the value of node_online_map.
+
 
 1.4 What are exclusive cpusets ?
 --------------------------------

Documentation/devices.txt

@@ -2565,10 +2565,10 @@ Your cooperation is appreciated.
 		243 = /dev/usb/dabusb3	Fourth dabusb device
 
 180 block	USB block devices
-		0 = /dev/uba		First USB block device
+		  0 = /dev/uba		First USB block device
-		8 = /dev/ubb		Second USB block device
+		  8 = /dev/ubb		Second USB block device
-		16 = /dev/ubc		Thrid USB block device
+		 16 = /dev/ubc		Third USB block device
-		...
+		    ...
 
 181 char	Conrad Electronic parallel port radio clocks
 		  0 = /dev/pcfclock0	First Conrad radio clock

Documentation/fb/imacfb.txt

@@ -0,0 +1,31 @@
+
+What is imacfb?
+===============
+
+This is a generic EFI platform driver for Intel based Apple computers.
+Imacfb is only for EFI booted Intel Macs.
+
+Supported Hardware
+==================
+
+iMac 17"/20"
+Macbook
+Macbook Pro 15"/17"
+MacMini
+
+How to use it?
+==============
+
+Imacfb does not have any kind of autodetection of your machine.
+You have to add the fillowing kernel parameters in your elilo.conf:
+	Macbook :
+		video=imacfb:macbook
+	MacMini :
+		video=imacfb:mini
+	Macbook Pro 15", iMac 17" :
+		video=imacfb:i17
+	Macbook Pro 17", iMac 20" :
+		video=imacfb:i20
+
+--
+Edgar Hucek <gimli@dark-green.com>

Documentation/filesystems/00-INDEX

@@ -62,8 +62,8 @@ ramfs-rootfs-initramfs.txt
 	- info on the 'in memory' filesystems ramfs, rootfs and initramfs.
 reiser4.txt
 	- info on the Reiser4 filesystem based on dancing tree algorithms.
-relayfs.txt
+relay.txt
-	- info on relayfs, for efficient streaming from kernel to user space.
+	- info on relay, for efficient streaming from kernel to user space.
 romfs.txt
 	- description of the ROMFS filesystem.
 smbfs.txt

Documentation/filesystems/relay.txt

@@ -0,0 +1,479 @@
+relay interface (formerly relayfs)
+==================================
+
+The relay interface provides a means for kernel applications to
+efficiently log and transfer large quantities of data from the kernel
+to userspace via user-defined 'relay channels'.
+
+A 'relay channel' is a kernel->user data relay mechanism implemented
+as a set of per-cpu kernel buffers ('channel buffers'), each
+represented as a regular file ('relay file') in user space.  Kernel
+clients write into the channel buffers using efficient write
+functions; these automatically log into the current cpu's channel
+buffer.  User space applications mmap() or read() from the relay files
+and retrieve the data as it becomes available.  The relay files
+themselves are files created in a host filesystem, e.g. debugfs, and
+are associated with the channel buffers using the API described below.
+
+The format of the data logged into the channel buffers is completely
+up to the kernel client; the relay interface does however provide
+hooks which allow kernel clients to impose some structure on the
+buffer data.  The relay interface doesn't implement any form of data
+filtering - this also is left to the kernel client.  The purpose is to
+keep things as simple as possible.
+
+This document provides an overview of the relay interface API.  The
+details of the function parameters are documented along with the
+functions in the relay interface code - please see that for details.
+
+Semantics
+=========
+
+Each relay channel has one buffer per CPU, each buffer has one or more
+sub-buffers.  Messages are written to the first sub-buffer until it is
+too full to contain a new message, in which case it it is written to
+the next (if available).  Messages are never split across sub-buffers.
+At this point, userspace can be notified so it empties the first
+sub-buffer, while the kernel continues writing to the next.
+
+When notified that a sub-buffer is full, the kernel knows how many
+bytes of it are padding i.e. unused space occurring because a complete
+message couldn't fit into a sub-buffer.  Userspace can use this
+knowledge to copy only valid data.
+
+After copying it, userspace can notify the kernel that a sub-buffer
+has been consumed.
+
+A relay channel can operate in a mode where it will overwrite data not
+yet collected by userspace, and not wait for it to be consumed.
+
+The relay channel itself does not provide for communication of such
+data between userspace and kernel, allowing the kernel side to remain
+simple and not impose a single interface on userspace.  It does
+provide a set of examples and a separate helper though, described
+below.
+
+The read() interface both removes padding and internally consumes the
+read sub-buffers; thus in cases where read(2) is being used to drain
+the channel buffers, special-purpose communication between kernel and
+user isn't necessary for basic operation.
+
+One of the major goals of the relay interface is to provide a low
+overhead mechanism for conveying kernel data to userspace.  While the
+read() interface is easy to use, it's not as efficient as the mmap()
+approach; the example code attempts to make the tradeoff between the
+two approaches as small as possible.
+
+klog and relay-apps example code
+================================
+
+The relay interface itself is ready to use, but to make things easier,
+a couple simple utility functions and a set of examples are provided.
+
+The relay-apps example tarball, available on the relay sourceforge
+site, contains a set of self-contained examples, each consisting of a
+pair of .c files containing boilerplate code for each of the user and
+kernel sides of a relay application.  When combined these two sets of
+boilerplate code provide glue to easily stream data to disk, without
+having to bother with mundane housekeeping chores.
+
+The 'klog debugging functions' patch (klog.patch in the relay-apps
+tarball) provides a couple of high-level logging functions to the
+kernel which allow writing formatted text or raw data to a channel,
+regardless of whether a channel to write into exists or not, or even
+whether the relay interface is compiled into the kernel or not.  These
+functions allow you to put unconditional 'trace' statements anywhere
+in the kernel or kernel modules; only when there is a 'klog handler'
+registered will data actually be logged (see the klog and kleak
+examples for details).
+
+It is of course possible to use the relay interface from scratch,
+i.e. without using any of the relay-apps example code or klog, but
+you'll have to implement communication between userspace and kernel,
+allowing both to convey the state of buffers (full, empty, amount of
+padding).  The read() interface both removes padding and internally
+consumes the read sub-buffers; thus in cases where read(2) is being
+used to drain the channel buffers, special-purpose communication
+between kernel and user isn't necessary for basic operation.  Things
+such as buffer-full conditions would still need to be communicated via
+some channel though.
+
+klog and the relay-apps examples can be found in the relay-apps
+tarball on http://relayfs.sourceforge.net
+
+The relay interface user space API
+==================================
+
+The relay interface implements basic file operations for user space
+access to relay channel buffer data.  Here are the file operations
+that are available and some comments regarding their behavior:
+
+open()	    enables user to open an _existing_ channel buffer.
+
+mmap()      results in channel buffer being mapped into the caller's
+	    memory space. Note that you can't do a partial mmap - you
+	    must map the entire file, which is NRBUF * SUBBUFSIZE.
+
+read()      read the contents of a channel buffer.  The bytes read are
+	    'consumed' by the reader, i.e. they won't be available
+	    again to subsequent reads.  If the channel is being used
+	    in no-overwrite mode (the default), it can be read at any
+	    time even if there's an active kernel writer.  If the
+	    channel is being used in overwrite mode and there are
+	    active channel writers, results may be unpredictable -
+	    users should make sure that all logging to the channel has
+	    ended before using read() with overwrite mode.  Sub-buffer
+	    padding is automatically removed and will not be seen by
+	    the reader.
+
+sendfile()  transfer data from a channel buffer to an output file
+	    descriptor. Sub-buffer padding is automatically removed
+	    and will not be seen by the reader.
+
+poll()      POLLIN/POLLRDNORM/POLLERR supported.  User applications are
+	    notified when sub-buffer boundaries are crossed.
+
+close()     decrements the channel buffer's refcount.  When the refcount
+	    reaches 0, i.e. when no process or kernel client has the
+	    buffer open, the channel buffer is freed.
+
+In order for a user application to make use of relay files, the
+host filesystem must be mounted.  For example,
+
+	mount -t debugfs debugfs /debug
+
+NOTE:   the host filesystem doesn't need to be mounted for kernel
+	clients to create or use channels - it only needs to be
+	mounted when user space applications need access to the buffer
+	data.
+
+
+The relay interface kernel API
+==============================
+
+Here's a summary of the API the relay interface provides to in-kernel clients:
+
+TBD(curr. line MT:/API/)
+  channel management functions:
+
+    relay_open(base_filename, parent, subbuf_size, n_subbufs,
+               callbacks)
+    relay_close(chan)
+    relay_flush(chan)
+    relay_reset(chan)
+
+  channel management typically called on instigation of userspace:
+
+    relay_subbufs_consumed(chan, cpu, subbufs_consumed)
+
+  write functions:
+
+    relay_write(chan, data, length)
+    __relay_write(chan, data, length)
+    relay_reserve(chan, length)
+
+  callbacks:
+
+    subbuf_start(buf, subbuf, prev_subbuf, prev_padding)
+    buf_mapped(buf, filp)
+    buf_unmapped(buf, filp)
+    create_buf_file(filename, parent, mode, buf, is_global)
+    remove_buf_file(dentry)
+
+  helper functions:
+
+    relay_buf_full(buf)
+    subbuf_start_reserve(buf, length)
+
+
+Creating a channel
+------------------
+
+relay_open() is used to create a channel, along with its per-cpu
+channel buffers.  Each channel buffer will have an associated file
+created for it in the host filesystem, which can be and mmapped or
+read from in user space.  The files are named basename0...basenameN-1
+where N is the number of online cpus, and by default will be created
+in the root of the filesystem (if the parent param is NULL).  If you
+want a directory structure to contain your relay files, you should
+create it using the host filesystem's directory creation function,
+e.g. debugfs_create_dir(), and pass the parent directory to
+relay_open().  Users are responsible for cleaning up any directory
+structure they create, when the channel is closed - again the host
+filesystem's directory removal functions should be used for that,
+e.g. debugfs_remove().
+
+In order for a channel to be created and the host filesystem's files
+associated with its channel buffers, the user must provide definitions
+for two callback functions, create_buf_file() and remove_buf_file().
+create_buf_file() is called once for each per-cpu buffer from
+relay_open() and allows the user to create the file which will be used
+to represent the corresponding channel buffer.  The callback should
+return the dentry of the file created to represent the channel buffer.
+remove_buf_file() must also be defined; it's responsible for deleting
+the file(s) created in create_buf_file() and is called during
+relay_close().
+
+Here are some typical definitions for these callbacks, in this case
+using debugfs:
+
+/*
+ * create_buf_file() callback.  Creates relay file in debugfs.
+ */
+static struct dentry *create_buf_file_handler(const char *filename,
+                                              struct dentry *parent,
+                                              int mode,
+                                              struct rchan_buf *buf,
+                                              int *is_global)
+{
+        return debugfs_create_file(filename, mode, parent, buf,
+	                           &relay_file_operations);
+}
+
+/*
+ * remove_buf_file() callback.  Removes relay file from debugfs.
+ */
+static int remove_buf_file_handler(struct dentry *dentry)
+{
+        debugfs_remove(dentry);
+
+        return 0;
+}
+
+/*
+ * relay interface callbacks
+ */
+static struct rchan_callbacks relay_callbacks =
+{
+        .create_buf_file = create_buf_file_handler,
+        .remove_buf_file = remove_buf_file_handler,
+};
+
+And an example relay_open() invocation using them:
+
+  chan = relay_open("cpu", NULL, SUBBUF_SIZE, N_SUBBUFS, &relay_callbacks);
+
+If the create_buf_file() callback fails, or isn't defined, channel
+creation and thus relay_open() will fail.
+
+The total size of each per-cpu buffer is calculated by multiplying the
+number of sub-buffers by the sub-buffer size passed into relay_open().
+The idea behind sub-buffers is that they're basically an extension of
+double-buffering to N buffers, and they also allow applications to
+easily implement random-access-on-buffer-boundary schemes, which can
+be important for some high-volume applications.  The number and size
+of sub-buffers is completely dependent on the application and even for
+the same application, different conditions will warrant different
+values for these parameters at different times.  Typically, the right
+values to use are best decided after some experimentation; in general,
+though, it's safe to assume that having only 1 sub-buffer is a bad
+idea - you're guaranteed to either overwrite data or lose events
+depending on the channel mode being used.
+
+The create_buf_file() implementation can also be defined in such a way
+as to allow the creation of a single 'global' buffer instead of the
+default per-cpu set.  This can be useful for applications interested
+mainly in seeing the relative ordering of system-wide events without
+the need to bother with saving explicit timestamps for the purpose of
+merging/sorting per-cpu files in a postprocessing step.
+
+To have relay_open() create a global buffer, the create_buf_file()
+implementation should set the value of the is_global outparam to a
+non-zero value in addition to creating the file that will be used to
+represent the single buffer.  In the case of a global buffer,
+create_buf_file() and remove_buf_file() will be called only once.  The
+normal channel-writing functions, e.g. relay_write(), can still be
+used - writes from any cpu will transparently end up in the global
+buffer - but since it is a global buffer, callers should make sure
+they use the proper locking for such a buffer, either by wrapping
+writes in a spinlock, or by copying a write function from relay.h and
+creating a local version that internally does the proper locking.
+
+Channel 'modes'
+---------------
+
+relay channels can be used in either of two modes - 'overwrite' or
+'no-overwrite'.  The mode is entirely determined by the implementation
+of the subbuf_start() callback, as described below.  The default if no
+subbuf_start() callback is defined is 'no-overwrite' mode.  If the
+default mode suits your needs, and you plan to use the read()
+interface to retrieve channel data, you can ignore the details of this
+section, as it pertains mainly to mmap() implementations.
+
+In 'overwrite' mode, also known as 'flight recorder' mode, writes
+continuously cycle around the buffer and will never fail, but will
+unconditionally overwrite old data regardless of whether it's actually
+been consumed.  In no-overwrite mode, writes will fail, i.e. data will
+be lost, if the number of unconsumed sub-buffers equals the total
+number of sub-buffers in the channel.  It should be clear that if
+there is no consumer or if the consumer can't consume sub-buffers fast
+enough, data will be lost in either case; the only difference is
+whether data is lost from the beginning or the end of a buffer.
+
+As explained above, a relay channel is made of up one or more
+per-cpu channel buffers, each implemented as a circular buffer
+subdivided into one or more sub-buffers.  Messages are written into
+the current sub-buffer of the channel's current per-cpu buffer via the
+write functions described below.  Whenever a message can't fit into
+the current sub-buffer, because there's no room left for it, the
+client is notified via the subbuf_start() callback that a switch to a
+new sub-buffer is about to occur.  The client uses this callback to 1)
+initialize the next sub-buffer if appropriate 2) finalize the previous
+sub-buffer if appropriate and 3) return a boolean value indicating
+whether or not to actually move on to the next sub-buffer.
+
+To implement 'no-overwrite' mode, the userspace client would provide
+an implementation of the subbuf_start() callback something like the
+following:
+
+static int subbuf_start(struct rchan_buf *buf,
+                        void *subbuf,
+			void *prev_subbuf,
+			unsigned int prev_padding)
+{
+	if (prev_subbuf)
+		*((unsigned *)prev_subbuf) = prev_padding;
+
+	if (relay_buf_full(buf))
+		return 0;
+
+	subbuf_start_reserve(buf, sizeof(unsigned int));
+
+	return 1;
+}
+
+If the current buffer is full, i.e. all sub-buffers remain unconsumed,
+the callback returns 0 to indicate that the buffer switch should not
+occur yet, i.e. until the consumer has had a chance to read the
+current set of ready sub-buffers.  For the relay_buf_full() function
+to make sense, the consumer is reponsible for notifying the relay
+interface when sub-buffers have been consumed via
+relay_subbufs_consumed().  Any subsequent attempts to write into the
+buffer will again invoke the subbuf_start() callback with the same
+parameters; only when the consumer has consumed one or more of the
+ready sub-buffers will relay_buf_full() return 0, in which case the
+buffer switch can continue.
+
+The implementation of the subbuf_start() callback for 'overwrite' mode
+would be very similar:
+
+static int subbuf_start(struct rchan_buf *buf,
+                        void *subbuf,
+			void *prev_subbuf,
+			unsigned int prev_padding)
+{
+	if (prev_subbuf)
+		*((unsigned *)prev_subbuf) = prev_padding;
+
+	subbuf_start_reserve(buf, sizeof(unsigned int));
+
+	return 1;
+}
+
+In this case, the relay_buf_full() check is meaningless and the
+callback always returns 1, causing the buffer switch to occur
+unconditionally.  It's also meaningless for the client to use the
+relay_subbufs_consumed() function in this mode, as it's never
+consulted.
+
+The default subbuf_start() implementation, used if the client doesn't
+define any callbacks, or doesn't define the subbuf_start() callback,
+implements the simplest possible 'no-overwrite' mode, i.e. it does
+nothing but return 0.
+
+Header information can be reserved at the beginning of each sub-buffer
+by calling the subbuf_start_reserve() helper function from within the
+subbuf_start() callback.  This reserved area can be used to store
+whatever information the client wants.  In the example above, room is
+reserved in each sub-buffer to store the padding count for that
+sub-buffer.  This is filled in for the previous sub-buffer in the
+subbuf_start() implementation; the padding value for the previous
+sub-buffer is passed into the subbuf_start() callback along with a
+pointer to the previous sub-buffer, since the padding value isn't
+known until a sub-buffer is filled.  The subbuf_start() callback is
+also called for the first sub-buffer when the channel is opened, to
+give the client a chance to reserve space in it.  In this case the
+previous sub-buffer pointer passed into the callback will be NULL, so
+the client should check the value of the prev_subbuf pointer before
+writing into the previous sub-buffer.
+
+Writing to a channel
+--------------------
+
+Kernel clients write data into the current cpu's channel buffer using
+relay_write() or __relay_write().  relay_write() is the main logging
+function - it uses local_irqsave() to protect the buffer and should be
+used if you might be logging from interrupt context.  If you know
+you'll never be logging from interrupt context, you can use
+__relay_write(), which only disables preemption.  These functions
+don't return a value, so you can't determine whether or not they
+failed - the assumption is that you wouldn't want to check a return
+value in the fast logging path anyway, and that they'll always succeed
+unless the buffer is full and no-overwrite mode is being used, in
+which case you can detect a failed write in the subbuf_start()
+callback by calling the relay_buf_full() helper function.
+
+relay_reserve() is used to reserve a slot in a channel buffer which
+can be written to later.  This would typically be used in applications
+that need to write directly into a channel buffer without having to
+stage data in a temporary buffer beforehand.  Because the actual write
+may not happen immediately after the slot is reserved, applications
+using relay_reserve() can keep a count of the number of bytes actually
+written, either in space reserved in the sub-buffers themselves or as
+a separate array.  See the 'reserve' example in the relay-apps tarball
+at http://relayfs.sourceforge.net for an example of how this can be
+done.  Because the write is under control of the client and is
+separated from the reserve, relay_reserve() doesn't protect the buffer
+at all - it's up to the client to provide the appropriate
+synchronization when using relay_reserve().
+
+Closing a channel
+-----------------
+
+The client calls relay_close() when it's finished using the channel.
+The channel and its associated buffers are destroyed when there are no
+longer any references to any of the channel buffers.  relay_flush()
+forces a sub-buffer switch on all the channel buffers, and can be used
+to finalize and process the last sub-buffers before the channel is
+closed.
+
+Misc
+----
+
+Some applications may want to keep a channel around and re-use it
+rather than open and close a new channel for each use.  relay_reset()
+can be used for this purpose - it resets a channel to its initial
+state without reallocating channel buffer memory or destroying
+existing mappings.  It should however only be called when it's safe to
+do so, i.e. when the channel isn't currently being written to.
+
+Finally, there are a couple of utility callbacks that can be used for
+different purposes.  buf_mapped() is called whenever a channel buffer
+is mmapped from user space and buf_unmapped() is called when it's
+unmapped.  The client can use this notification to trigger actions
+within the kernel application, such as enabling/disabling logging to
+the channel.
+
+
+Resources
+=========
+
+For news, example code, mailing list, etc. see the relay interface homepage:
+
+    http://relayfs.sourceforge.net
+
+
+Credits
+=======
+
+The ideas and specs for the relay interface came about as a result of
+discussions on tracing involving the following:
+
+Michel Dagenais		<michel.dagenais@polymtl.ca>
+Richard Moore		<richardj_moore@uk.ibm.com>
+Bob Wisniewski		<bob@watson.ibm.com>
+Karim Yaghmour		<karim@opersys.com>
+Tom Zanussi		<zanussi@us.ibm.com>
+
+Also thanks to Hubertus Franke for a lot of useful suggestions and bug
+reports.

Documentation/filesystems/relayfs.txt

@@ -1,442 +0,0 @@
-
-relayfs - a high-speed data relay filesystem
-============================================
-
-relayfs is a filesystem designed to provide an efficient mechanism for
-tools and facilities to relay large and potentially sustained streams
-of data from kernel space to user space.
-
-The main abstraction of relayfs is the 'channel'.  A channel consists
-of a set of per-cpu kernel buffers each represented by a file in the
-relayfs filesystem.  Kernel clients write into a channel using
-efficient write functions which automatically log to the current cpu's
-channel buffer.  User space applications mmap() the per-cpu files and
-retrieve the data as it becomes available.
-
-The format of the data logged into the channel buffers is completely
-up to the relayfs client; relayfs does however provide hooks which
-allow clients to impose some structure on the buffer data.  Nor does
-relayfs implement any form of data filtering - this also is left to
-the client.  The purpose is to keep relayfs as simple as possible.
-
-This document provides an overview of the relayfs API.  The details of
-the function parameters are documented along with the functions in the
-filesystem code - please see that for details.
-
-Semantics
-=========
-
-Each relayfs channel has one buffer per CPU, each buffer has one or
-more sub-buffers. Messages are written to the first sub-buffer until
-it is too full to contain a new message, in which case it it is
-written to the next (if available).  Messages are never split across
-sub-buffers.  At this point, userspace can be notified so it empties
-the first sub-buffer, while the kernel continues writing to the next.
-
-When notified that a sub-buffer is full, the kernel knows how many
-bytes of it are padding i.e. unused.  Userspace can use this knowledge
-to copy only valid data.
-
-After copying it, userspace can notify the kernel that a sub-buffer
-has been consumed.
-
-relayfs can operate in a mode where it will overwrite data not yet
-collected by userspace, and not wait for it to consume it.
-
-relayfs itself does not provide for communication of such data between
-userspace and kernel, allowing the kernel side to remain simple and
-not impose a single interface on userspace. It does provide a set of
-examples and a separate helper though, described below.
-
-klog and relay-apps example code
-================================
-
-relayfs itself is ready to use, but to make things easier, a couple
-simple utility functions and a set of examples are provided.
-
-The relay-apps example tarball, available on the relayfs sourceforge
-site, contains a set of self-contained examples, each consisting of a
-pair of .c files containing boilerplate code for each of the user and
-kernel sides of a relayfs application; combined these two sets of
-boilerplate code provide glue to easily stream data to disk, without
-having to bother with mundane housekeeping chores.
-
-The 'klog debugging functions' patch (klog.patch in the relay-apps
-tarball) provides a couple of high-level logging functions to the
-kernel which allow writing formatted text or raw data to a channel,
-regardless of whether a channel to write into exists or not, or
-whether relayfs is compiled into the kernel or is configured as a
-module.  These functions allow you to put unconditional 'trace'
-statements anywhere in the kernel or kernel modules; only when there
-is a 'klog handler' registered will data actually be logged (see the
-klog and kleak examples for details).
-
-It is of course possible to use relayfs from scratch i.e. without
-using any of the relay-apps example code or klog, but you'll have to
-implement communication between userspace and kernel, allowing both to
-convey the state of buffers (full, empty, amount of padding).
-
-klog and the relay-apps examples can be found in the relay-apps
-tarball on http://relayfs.sourceforge.net
-
-
-The relayfs user space API
-==========================
-
-relayfs implements basic file operations for user space access to
-relayfs channel buffer data.  Here are the file operations that are
-available and some comments regarding their behavior:
-
-open()	 enables user to open an _existing_ buffer.
-
-mmap()	 results in channel buffer being mapped into the caller's
-	 memory space. Note that you can't do a partial mmap - you must
-	 map the entire file, which is NRBUF * SUBBUFSIZE.
-
-read()	 read the contents of a channel buffer.  The bytes read are
-	 'consumed' by the reader i.e. they won't be available again
-	 to subsequent reads.  If the channel is being used in
-	 no-overwrite mode (the default), it can be read at any time
-	 even if there's an active kernel writer.  If the channel is
-	 being used in overwrite mode and there are active channel
-	 writers, results may be unpredictable - users should make
-	 sure that all logging to the channel has ended before using
-	 read() with overwrite mode.
-
-poll()	 POLLIN/POLLRDNORM/POLLERR supported.  User applications are
-	 notified when sub-buffer boundaries are crossed.
-
-close() decrements the channel buffer's refcount.  When the refcount
-	reaches 0 i.e. when no process or kernel client has the buffer
-	open, the channel buffer is freed.
-
-
-In order for a user application to make use of relayfs files, the
-relayfs filesystem must be mounted.  For example,
-
-	mount -t relayfs relayfs /mnt/relay
-
-NOTE:	relayfs doesn't need to be mounted for kernel clients to create
-	or use channels - it only needs to be mounted when user space
-	applications need access to the buffer data.
-
-
-The relayfs kernel API
-======================
-
-Here's a summary of the API relayfs provides to in-kernel clients:
-
-
-  channel management functions:
-
-    relay_open(base_filename, parent, subbuf_size, n_subbufs,
-               callbacks)
-    relay_close(chan)
-    relay_flush(chan)
-    relay_reset(chan)
-    relayfs_create_dir(name, parent)
-    relayfs_remove_dir(dentry)
-    relayfs_create_file(name, parent, mode, fops, data)
-    relayfs_remove_file(dentry)
-
-  channel management typically called on instigation of userspace:
-
-    relay_subbufs_consumed(chan, cpu, subbufs_consumed)
-
-  write functions:
-
-    relay_write(chan, data, length)
-    __relay_write(chan, data, length)
-    relay_reserve(chan, length)
-
-  callbacks:
-
-    subbuf_start(buf, subbuf, prev_subbuf, prev_padding)
-    buf_mapped(buf, filp)
-    buf_unmapped(buf, filp)
-    create_buf_file(filename, parent, mode, buf, is_global)
-    remove_buf_file(dentry)
-
-  helper functions:
-
-    relay_buf_full(buf)
-    subbuf_start_reserve(buf, length)
-
-
-Creating a channel
-------------------
-
-relay_open() is used to create a channel, along with its per-cpu
-channel buffers.  Each channel buffer will have an associated file
-created for it in the relayfs filesystem, which can be opened and
-mmapped from user space if desired.  The files are named
-basename0...basenameN-1 where N is the number of online cpus, and by
-default will be created in the root of the filesystem.  If you want a
-directory structure to contain your relayfs files, you can create it
-with relayfs_create_dir() and pass the parent directory to
-relay_open().  Clients are responsible for cleaning up any directory
-structure they create when the channel is closed - use
-relayfs_remove_dir() for that.
-
-The total size of each per-cpu buffer is calculated by multiplying the
-number of sub-buffers by the sub-buffer size passed into relay_open().
-The idea behind sub-buffers is that they're basically an extension of
-double-buffering to N buffers, and they also allow applications to
-easily implement random-access-on-buffer-boundary schemes, which can
-be important for some high-volume applications.  The number and size
-of sub-buffers is completely dependent on the application and even for
-the same application, different conditions will warrant different
-values for these parameters at different times.  Typically, the right
-values to use are best decided after some experimentation; in general,
-though, it's safe to assume that having only 1 sub-buffer is a bad
-idea - you're guaranteed to either overwrite data or lose events
-depending on the channel mode being used.
-
-Channel 'modes'
----------------
-
-relayfs channels can be used in either of two modes - 'overwrite' or
-'no-overwrite'.  The mode is entirely determined by the implementation
-of the subbuf_start() callback, as described below.  In 'overwrite'
-mode, also known as 'flight recorder' mode, writes continuously cycle
-around the buffer and will never fail, but will unconditionally
-overwrite old data regardless of whether it's actually been consumed.
-In no-overwrite mode, writes will fail i.e. data will be lost, if the
-number of unconsumed sub-buffers equals the total number of
-sub-buffers in the channel.  It should be clear that if there is no
-consumer or if the consumer can't consume sub-buffers fast enought,
-data will be lost in either case; the only difference is whether data
-is lost from the beginning or the end of a buffer.
-
-As explained above, a relayfs channel is made of up one or more
-per-cpu channel buffers, each implemented as a circular buffer
-subdivided into one or more sub-buffers.  Messages are written into
-the current sub-buffer of the channel's current per-cpu buffer via the
-write functions described below.  Whenever a message can't fit into
-the current sub-buffer, because there's no room left for it, the
-client is notified via the subbuf_start() callback that a switch to a
-new sub-buffer is about to occur.  The client uses this callback to 1)
-initialize the next sub-buffer if appropriate 2) finalize the previous
-sub-buffer if appropriate and 3) return a boolean value indicating
-whether or not to actually go ahead with the sub-buffer switch.
-
-To implement 'no-overwrite' mode, the userspace client would provide
-an implementation of the subbuf_start() callback something like the
-following:
-
-static int subbuf_start(struct rchan_buf *buf,
-                        void *subbuf,
-			void *prev_subbuf,
-			unsigned int prev_padding)
-{
-	if (prev_subbuf)
-		*((unsigned *)prev_subbuf) = prev_padding;
-
-	if (relay_buf_full(buf))
-		return 0;
-
-	subbuf_start_reserve(buf, sizeof(unsigned int));
-
-	return 1;
-}
-
-If the current buffer is full i.e. all sub-buffers remain unconsumed,
-the callback returns 0 to indicate that the buffer switch should not
-occur yet i.e. until the consumer has had a chance to read the current
-set of ready sub-buffers.  For the relay_buf_full() function to make
-sense, the consumer is reponsible for notifying relayfs when
-sub-buffers have been consumed via relay_subbufs_consumed().  Any
-subsequent attempts to write into the buffer will again invoke the
-subbuf_start() callback with the same parameters; only when the
-consumer has consumed one or more of the ready sub-buffers will
-relay_buf_full() return 0, in which case the buffer switch can
-continue.
-
-The implementation of the subbuf_start() callback for 'overwrite' mode
-would be very similar:
-
-static int subbuf_start(struct rchan_buf *buf,
-                        void *subbuf,
-			void *prev_subbuf,
-			unsigned int prev_padding)
-{
-	if (prev_subbuf)
-		*((unsigned *)prev_subbuf) = prev_padding;
-
-	subbuf_start_reserve(buf, sizeof(unsigned int));
-
-	return 1;
-}
-
-In this case, the relay_buf_full() check is meaningless and the
-callback always returns 1, causing the buffer switch to occur
-unconditionally.  It's also meaningless for the client to use the
-relay_subbufs_consumed() function in this mode, as it's never
-consulted.
-
-The default subbuf_start() implementation, used if the client doesn't
-define any callbacks, or doesn't define the subbuf_start() callback,
-implements the simplest possible 'no-overwrite' mode i.e. it does
-nothing but return 0.
-
-Header information can be reserved at the beginning of each sub-buffer
-by calling the subbuf_start_reserve() helper function from within the
-subbuf_start() callback.  This reserved area can be used to store
-whatever information the client wants.  In the example above, room is
-reserved in each sub-buffer to store the padding count for that
-sub-buffer.  This is filled in for the previous sub-buffer in the
-subbuf_start() implementation; the padding value for the previous
-sub-buffer is passed into the subbuf_start() callback along with a
-pointer to the previous sub-buffer, since the padding value isn't
-known until a sub-buffer is filled.  The subbuf_start() callback is
-also called for the first sub-buffer when the channel is opened, to
-give the client a chance to reserve space in it.  In this case the
-previous sub-buffer pointer passed into the callback will be NULL, so
-the client should check the value of the prev_subbuf pointer before
-writing into the previous sub-buffer.
-
-Writing to a channel
---------------------
-
-kernel clients write data into the current cpu's channel buffer using
-relay_write() or __relay_write().  relay_write() is the main logging
-function - it uses local_irqsave() to protect the buffer and should be
-used if you might be logging from interrupt context.  If you know
-you'll never be logging from interrupt context, you can use
-__relay_write(), which only disables preemption.  These functions
-don't return a value, so you can't determine whether or not they
-failed - the assumption is that you wouldn't want to check a return
-value in the fast logging path anyway, and that they'll always succeed
-unless the buffer is full and no-overwrite mode is being used, in
-which case you can detect a failed write in the subbuf_start()
-callback by calling the relay_buf_full() helper function.
-
-relay_reserve() is used to reserve a slot in a channel buffer which
-can be written to later.  This would typically be used in applications
-that need to write directly into a channel buffer without having to
-stage data in a temporary buffer beforehand.  Because the actual write
-may not happen immediately after the slot is reserved, applications
-using relay_reserve() can keep a count of the number of bytes actually
-written, either in space reserved in the sub-buffers themselves or as
-a separate array.  See the 'reserve' example in the relay-apps tarball
-at http://relayfs.sourceforge.net for an example of how this can be
-done.  Because the write is under control of the client and is
-separated from the reserve, relay_reserve() doesn't protect the buffer
-at all - it's up to the client to provide the appropriate
-synchronization when using relay_reserve().
-
-Closing a channel
------------------
-
-The client calls relay_close() when it's finished using the channel.
-The channel and its associated buffers are destroyed when there are no
-longer any references to any of the channel buffers.  relay_flush()
-forces a sub-buffer switch on all the channel buffers, and can be used
-to finalize and process the last sub-buffers before the channel is
-closed.
-
-Creating non-relay files
-------------------------
-
-relay_open() automatically creates files in the relayfs filesystem to
-represent the per-cpu kernel buffers; it's often useful for
-applications to be able to create their own files alongside the relay
-files in the relayfs filesystem as well e.g. 'control' files much like
-those created in /proc or debugfs for similar purposes, used to
-communicate control information between the kernel and user sides of a
-relayfs application.  For this purpose the relayfs_create_file() and
-relayfs_remove_file() API functions exist.  For relayfs_create_file(),
-the caller passes in a set of user-defined file operations to be used
-for the file and an optional void * to a user-specified data item,
-which will be accessible via inode->u.generic_ip (see the relay-apps
-tarball for examples).  The file_operations are a required parameter
-to relayfs_create_file() and thus the semantics of these files are
-completely defined by the caller.
-
-See the relay-apps tarball at http://relayfs.sourceforge.net for
-examples of how these non-relay files are meant to be used.
-
-Creating relay files in other filesystems
------------------------------------------
-
-By default of course, relay_open() creates relay files in the relayfs
-filesystem.  Because relay_file_operations is exported, however, it's
-also possible to create and use relay files in other pseudo-filesytems
-such as debugfs.
-
-For this purpose, two callback functions are provided,
-create_buf_file() and remove_buf_file().  create_buf_file() is called
-once for each per-cpu buffer from relay_open() to allow the client to
-create a file to be used to represent the corresponding buffer; if
-this callback is not defined, the default implementation will create
-and return a file in the relayfs filesystem to represent the buffer.
-The callback should return the dentry of the file created to represent
-the relay buffer.  Note that the parent directory passed to
-relay_open() (and passed along to the callback), if specified, must
-exist in the same filesystem the new relay file is created in.  If
-create_buf_file() is defined, remove_buf_file() must also be defined;
-it's responsible for deleting the file(s) created in create_buf_file()
-and is called during relay_close().
-
-The create_buf_file() implementation can also be defined in such a way
-as to allow the creation of a single 'global' buffer instead of the
-default per-cpu set.  This can be useful for applications interested
-mainly in seeing the relative ordering of system-wide events without
-the need to bother with saving explicit timestamps for the purpose of
-merging/sorting per-cpu files in a postprocessing step.
-
-To have relay_open() create a global buffer, the create_buf_file()
-implementation should set the value of the is_global outparam to a
-non-zero value in addition to creating the file that will be used to
-represent the single buffer.  In the case of a global buffer,
-create_buf_file() and remove_buf_file() will be called only once.  The
-normal channel-writing functions e.g. relay_write() can still be used
-- writes from any cpu will transparently end up in the global buffer -
-but since it is a global buffer, callers should make sure they use the
-proper locking for such a buffer, either by wrapping writes in a
-spinlock, or by copying a write function from relayfs_fs.h and
-creating a local version that internally does the proper locking.
-
-See the 'exported-relayfile' examples in the relay-apps tarball for
-examples of creating and using relay files in debugfs.
-
-Misc
-----
-
-Some applications may want to keep a channel around and re-use it
-rather than open and close a new channel for each use.  relay_reset()
-can be used for this purpose - it resets a channel to its initial
-state without reallocating channel buffer memory or destroying
-existing mappings.  It should however only be called when it's safe to
-do so i.e. when the channel isn't currently being written to.
-
-Finally, there are a couple of utility callbacks that can be used for
-different purposes.  buf_mapped() is called whenever a channel buffer
-is mmapped from user space and buf_unmapped() is called when it's
-unmapped.  The client can use this notification to trigger actions
-within the kernel application, such as enabling/disabling logging to
-the channel.
-
-
-Resources
-=========
-
-For news, example code, mailing list, etc. see the relayfs homepage:
-
-    http://relayfs.sourceforge.net
-
-
-Credits
-=======
-
-The ideas and specs for relayfs came about as a result of discussions
-on tracing involving the following:
-
-Michel Dagenais		<michel.dagenais@polymtl.ca>
-Richard Moore		<richardj_moore@uk.ibm.com>
-Bob Wisniewski		<bob@watson.ibm.com>
-Karim Yaghmour		<karim@opersys.com>
-Tom Zanussi		<zanussi@us.ibm.com>
-
-Also thanks to Hubertus Franke for a lot of useful suggestions and bug
-reports.

Documentation/infiniband/ipoib.txt

@@ -51,8 +51,6 @@ Debugging Information
 
 References
 
-  IETF IP over InfiniBand (ipoib) Working Group
-    http://ietf.org/html.charters/ipoib-charter.html
   Transmission of IP over InfiniBand (IPoIB) (RFC 4391)
     http://ietf.org/rfc/rfc4391.txt 
   IP over InfiniBand (IPoIB) Architecture (RFC 4392)

Documentation/initrd.txt

@@ -72,6 +72,22 @@ initrd adds the following new options:
     initrd is mounted as root, and the normal boot procedure is followed,
     with the RAM disk still mounted as root.
 
+Compressed cpio images
+----------------------
+
+Recent kernels have support for populating a ramdisk from a compressed cpio
+archive, on such systems, the creation of a ramdisk image doesn't need to
+involve special block devices or loopbacks, you merely create a directory on
+disk with the desired initrd content, cd to that directory, and run (as an
+example):
+
+find . | cpio --quiet -c -o | gzip -9 -n > /boot/imagefile.img
+
+Examining the contents of an existing image file is just as simple:
+
+mkdir /tmp/imagefile
+cd /tmp/imagefile
+gzip -cd /boot/imagefile.img | cpio -imd --quiet
 
 Installation
 ------------

Documentation/input/joystick.txt

@@ -39,7 +39,6 @@ them. Bug reports and success stories are also welcome.
 
   The input project website is at:
 
-	http://www.suse.cz/development/input/
 	http://atrey.karlin.mff.cuni.cz/~vojtech/input/
 
   There is also a mailing list for the driver at:

Documentation/kbuild/makefiles.txt

@@ -407,6 +407,20 @@ more details, with real examples.
 	The second argument is optional, and if supplied will be used
 	if first argument is not supported.
 
+    ld-option
+    	ld-option is used to check if $(CC) when used to link object files
+	supports the given option.  An optional second option may be
+	specified if first option are not supported.
+
+	Example:
+		#arch/i386/kernel/Makefile
+		vsyscall-flags += $(call ld-option, -Wl$(comma)--hash-style=sysv)
+
+	In the above example vsyscall-flags will be assigned the option
+	-Wl$(comma)--hash-style=sysv if it is supported by $(CC).
+	The second argument is optional, and if supplied will be used
+	if first argument is not supported.
+
     cc-option
 	cc-option is used to check if $(CC) support a given option, and not
 	supported to use an optional second option.

Documentation/kernel-parameters.txt

@@ -448,8 +448,6 @@ running once the system is up.
 			Format: <area>[,<node>]
 			See also Documentation/networking/decnet.txt.
 
-	delayacct	[KNL] Enable per-task delay accounting
-
 	dhash_entries=	[KNL]
 			Set number of hash buckets for dentry cache.
 
@@ -1031,6 +1029,8 @@ running once the system is up.
 
 	nocache		[ARM]
 
+	nodelayacct	[KNL] Disable per-task delay accounting
+
 	nodisconnect	[HW,SCSI,M68K] Disables SCSI disconnects.
 
 	noexec		[IA-64]

Documentation/kobject.txt

@@ -247,7 +247,7 @@ the object-specific fields, which include:
 - default_attrs: Default attributes to be exported via sysfs when the
   object is registered.Note that the last attribute has to be
   initialized to NULL ! You can find a complete implementation
-  in drivers/block/genhd.c
+  in block/genhd.c
 
 
 Instances of struct kobj_type are not registered; only referenced by

Documentation/networking/ip-sysctl.txt

@@ -294,15 +294,15 @@ tcp_rmem - vector of 3 INTEGERs: min, default, max
 	Default: 87380*2 bytes.
 
 tcp_mem - vector of 3 INTEGERs: min, pressure, max
-	low: below this number of pages TCP is not bothered about its
+	min: below this number of pages TCP is not bothered about its
 	memory appetite.
 
 	pressure: when amount of memory allocated by TCP exceeds this number
 	of pages, TCP moderates its memory consumption and enters memory
 	pressure mode, which is exited when memory consumption falls
-	under "low".
+	under "min".
 
-	high: number of pages allowed for queueing by all TCP sockets.
+	max: number of pages allowed for queueing by all TCP sockets.
 
 	Defaults are calculated at boot time from amount of available
 	memory.

Documentation/powerpc/booting-without-of.txt

@@ -1196,7 +1196,7 @@ platforms are moved over to use the flattened-device-tree model.
     - model : Model of the device.  Can be "TSEC", "eTSEC", or "FEC"
     - compatible : Should be "gianfar"
     - reg : Offset and length of the register set for the device
-    - address : List of bytes representing the ethernet address of
+    - mac-address : List of bytes representing the ethernet address of
       this controller
     - interrupts : <a b> where a is the interrupt number and b is a
       field that represents an encoding of the sense and level
@@ -1216,7 +1216,7 @@ platforms are moved over to use the flattened-device-tree model.
 		model = "TSEC";
 		compatible = "gianfar";
 		reg = <24000 1000>;
-		address = [ 00 E0 0C 00 73 00 ];
+		mac-address = [ 00 E0 0C 00 73 00 ];
 		interrupts = <d 3 e 3 12 3>;
 		interrupt-parent = <40000>;
 		phy-handle = <2452000>
@@ -1498,7 +1498,7 @@ not necessary as they are usually the same as the root node.
 			model = "TSEC";
 			compatible = "gianfar";
 			reg = <24000 1000>;
-			address = [ 00 E0 0C 00 73 00 ];
+			mac-address = [ 00 E0 0C 00 73 00 ];
 			interrupts = <d 3 e 3 12 3>;
 			interrupt-parent = <40000>;
 			phy-handle = <2452000>;
@@ -1511,7 +1511,7 @@ not necessary as they are usually the same as the root node.
 			model = "TSEC";
 			compatible = "gianfar";
 			reg = <25000 1000>;
-			address = [ 00 E0 0C 00 73 01 ];
+			mac-address = [ 00 E0 0C 00 73 01 ];
 			interrupts = <13 3 14 3 18 3>;
 			interrupt-parent = <40000>;
 			phy-handle = <2452001>;
@@ -1524,7 +1524,7 @@ not necessary as they are usually the same as the root node.
 			model = "FEC";
 			compatible = "gianfar";
 			reg = <26000 1000>;
-			address = [ 00 E0 0C 00 73 02 ];
+			mac-address = [ 00 E0 0C 00 73 02 ];
 			interrupts = <19 3>;
 			interrupt-parent = <40000>;
 			phy-handle = <2452002>;

Documentation/scsi/ChangeLog.megaraid

@@ -1,3 +1,126 @@
+Release Date	: Fri May 19 09:31:45 EST 2006 - Seokmann Ju <sju@lsil.com>
+Current Version : 2.20.4.9 (scsi module), 2.20.2.6 (cmm module)
+Older Version	: 2.20.4.8 (scsi module), 2.20.2.6 (cmm module)
+
+1.	Fixed a bug in megaraid_init_mbox().
+	Customer reported "garbage in file on x86_64 platform".
+	Root Cause: the driver registered controllers as 64-bit DMA capable
+	for those which are not support it.
+	Fix: Made change in the function inserting identification machanism
+	identifying 64-bit DMA capable controllers.
+
+	> -----Original Message-----
+	> From: Vasily Averin [mailto:vvs@sw.ru]
+	> Sent: Thursday, May 04, 2006 2:49 PM
+	> To: linux-scsi@vger.kernel.org; Kolli, Neela; Mukker, Atul;
+	> Ju, Seokmann; Bagalkote, Sreenivas;
+	> James.Bottomley@SteelEye.com; devel@openvz.org
+	> Subject: megaraid_mbox: garbage in file
+	>
+	> Hello all,
+	>
+	> I've investigated customers claim on the unstable work of
+	> their node and found a
+	> strange effect: reading from some files leads to the
+	>  "attempt to access beyond end of device" messages.
+	>
+	> I've checked filesystem, memory on the node, motherboard BIOS
+	> version, but it
+	> does not help and issue still has been reproduced by simple
+	> file reading.
+	>
+	> Reproducer is simple:
+	>
+	> echo 0xffffffff >/proc/sys/dev/scsi/logging_level ;
+	> cat /vz/private/101/root/etc/ld.so.cache >/tmp/ttt  ;
+	> echo 0 >/proc/sys/dev/scsi/logging
+	>
+	> It leads to the following messages in dmesg
+	>
+	> sd_init_command: disk=sda, block=871769260, count=26
+	> sda : block=871769260
+	> sda : reading 26/26 512 byte blocks.
+	> scsi_add_timer: scmd: f79ed980, time: 7500, (c02b1420)
+	> sd 0:1:0:0: send 0xf79ed980                  sd 0:1:0:0:
+	>         command: Read (10): 28 00 33 f6 24 ac 00 00 1a 00
+	> buffer = 0xf7cfb540, bufflen = 13312, done = 0xc0366b40,
+	> queuecommand 0xc0344010
+	> leaving scsi_dispatch_cmnd()
+	> scsi_delete_timer: scmd: f79ed980, rtn: 1
+	> sd 0:1:0:0: done 0xf79ed980 SUCCESS        0 sd 0:1:0:0:
+	>         command: Read (10): 28 00 33 f6 24 ac 00 00 1a 00
+	> scsi host busy 1 failed 0
+	> sd 0:1:0:0: Notifying upper driver of completion (result 0)
+	> sd_rw_intr: sda: res=0x0
+	> 26 sectors total, 13312 bytes done.
+	> use_sg is 4
+	> attempt to access beyond end of device
+	> sda6: rw=0, want=1044134458, limit=951401367
+	> Buffer I/O error on device sda6, logical block 522067228
+	> attempt to access beyond end of device
+
+2.	When INQUIRY with EVPD bit set issued to the MegaRAID controller,
+	system memory gets corrupted.
+	Root Cause: MegaRAID F/W handle the INQUIRY with EVPD bit set
+	incorrectly.
+	Fix: MegaRAID F/W has fixed the problem and being process of release,
+	soon. Meanwhile, driver will filter out the request.
+
+3.	One of member in the data structure of the driver leads unaligne
+	issue on 64-bit platform.
+	Customer reporeted "kernel unaligned access addrss" issue when
+	application communicates with MegaRAID HBA driver.
+	Root Cause: in uioc_t structure, one of member had misaligned and it
+	led system to display the error message.
+	Fix: A patch submitted to community from following folk.
+
+	> -----Original Message-----
+	> From: linux-scsi-owner@vger.kernel.org
+	> [mailto:linux-scsi-owner@vger.kernel.org] On Behalf Of Sakurai Hiroomi
+	> Sent: Wednesday, July 12, 2006 4:20 AM
+	> To: linux-scsi@vger.kernel.org; linux-kernel@vger.kernel.org
+	> Subject: Re: Help: strange messages from kernel on IA64 platform
+	>
+	> Hi,
+	>
+	> I saw same message.
+	>
+	> When GAM(Global Array Manager) is started, The following
+	> message output.
+	> kernel: kernel unaligned access to 0xe0000001fe1080d4,
+	> ip=0xa000000200053371
+	>
+	> The uioc structure used by ioctl is defined by packed,
+	> the allignment of each member are disturbed.
+	> In a 64 bit structure, the allignment of member doesn't fit 64 bit
+	> boundary. this causes this messages.
+	> In a 32 bit structure, we don't see the message because the allinment
+	> of member fit 32 bit boundary even if packed is specified.
+	>
+	> patch
+	> I Add 32 bit dummy member to fit 64 bit boundary. I tested.
+	> We confirmed this patch fix the problem by IA64 server.
+	>
+	> **************************************************************
+	> ****************
+	> --- linux-2.6.9/drivers/scsi/megaraid/megaraid_ioctl.h.orig
+	> 2006-04-03 17:13:03.000000000 +0900
+	> +++ linux-2.6.9/drivers/scsi/megaraid/megaraid_ioctl.h
+	> 2006-04-03 17:14:09.000000000 +0900
+	> @@ -132,6 +132,10 @@
+	>  /* Driver Data: */
+	>          void __user *           user_data;
+	>          uint32_t                user_data_len;
+	> +
+	> +        /* 64bit alignment */
+	> +        uint32_t                pad_0xBC;
+	> +
+	>          mraid_passthru_t        __user *user_pthru;
+	>
+	>          mraid_passthru_t        *pthru32;
+	> **************************************************************
+	> ****************
+
 Release Date	: Mon Apr 11 12:27:22 EST 2006 - Seokmann Ju <sju@lsil.com>
 Current Version : 2.20.4.8 (scsi module), 2.20.2.6 (cmm module)
 Older Version	: 2.20.4.7 (scsi module), 2.20.2.6 (cmm module)

Documentation/sysctl/fs.txt

@@ -25,6 +25,7 @@ Currently, these files are in /proc/sys/fs:
 - inode-state
 - overflowuid
 - overflowgid
+- suid_dumpable
 - super-max
 - super-nr
 
@@ -131,6 +132,25 @@ The default is 65534.
 
 ==============================================================
 
+suid_dumpable:
+
+This value can be used to query and set the core dump mode for setuid
+or otherwise protected/tainted binaries. The modes are
+
+0 - (default) - traditional behaviour. Any process which has changed
+	privilege levels or is execute only will not be dumped
+1 - (debug) - all processes dump core when possible. The core dump is
+	owned by the current user and no security is applied. This is
+	intended for system debugging situations only. Ptrace is unchecked.
+2 - (suidsafe) - any binary which normally would not be dumped is dumped
+	readable by root only. This allows the end user to remove
+	such a dump but not access it directly. For security reasons
+	core dumps in this mode will not overwrite one another or
+	other files. This mode is appropriate when adminstrators are
+	attempting to debug problems in a normal environment.
+
+==============================================================
+
 super-max & super-nr:
 
 These numbers control the maximum number of superblocks, and

Documentation/sysctl/kernel.txt

@@ -50,7 +50,6 @@ show up in /proc/sys/kernel:
 - shmmax                      [ sysv ipc ]
 - shmmni
 - stop-a                      [ SPARC only ]
-- suid_dumpable
 - sysrq                       ==> Documentation/sysrq.txt
 - tainted
 - threads-max
@@ -211,9 +210,8 @@ Controls the kernel's behaviour when an oops or BUG is encountered.
 
 0: try to continue operation
 
-1: delay a few seconds (to give klogd time to record the oops output) and
+1: panic immediatly.  If the `panic' sysctl is also non-zero then the
-   then panic.  If the `panic' sysctl is also non-zero then the machine will
+   machine will be rebooted.
-   be rebooted.
 
 ==============================================================
 
@@ -311,25 +309,6 @@ kernel.  This value defaults to SHMMAX.
 
 ==============================================================
 
-suid_dumpable:
-
-This value can be used to query and set the core dump mode for setuid
-or otherwise protected/tainted binaries. The modes are
-
-0 - (default) - traditional behaviour. Any process which has changed
-	privilege levels or is execute only will not be dumped
-1 - (debug) - all processes dump core when possible. The core dump is
-	owned by the current user and no security is applied. This is
-	intended for system debugging situations only. Ptrace is unchecked.
-2 - (suidsafe) - any binary which normally would not be dumped is dumped
-	readable by root only. This allows the end user to remove
-	such a dump but not access it directly. For security reasons
-	core dumps in this mode will not overwrite one another or
-	other files. This mode is appropriate when adminstrators are
-	attempting to debug problems in a normal environment.
-
-==============================================================
-
 tainted: 
 
 Non-zero if the kernel has been tainted.  Numeric values, which

Documentation/usb/proc_usb_info.txt

@@ -59,7 +59,7 @@ bind to an interface (or perhaps several) using an ioctl call.  You
 would issue more ioctls to the device to communicate to it using
 control, bulk, or other kinds of USB transfers.  The IOCTLs are
 listed in the <linux/usbdevice_fs.h> file, and at this writing the
-source code (linux/drivers/usb/devio.c) is the primary reference
+source code (linux/drivers/usb/core/devio.c) is the primary reference
 for how to access devices through those files.
 
 Note that since by default these BBB/DDD files are writable only by

Documentation/usb/usb-help.txt

@@ -5,8 +5,7 @@ For USB help other than the readme files that are located in
 Documentation/usb/*, see the following:
 
 Linux-USB project:  http://www.linux-usb.org
-  mirrors at        http://www.suse.cz/development/linux-usb/
+  mirrors at        http://usb.in.tum.de/linux-usb/
-         and        http://usb.in.tum.de/linux-usb/
          and        http://it.linux-usb.org
 Linux USB Guide:    http://linux-usb.sourceforge.net
 Linux-USB device overview (working devices and drivers):

Documentation/x86_64/boot-options.txt

@@ -238,6 +238,13 @@ Debugging
   pagefaulttrace Dump all page faults. Only useful for extreme debugging
 		and will create a lot of output.
 
+  call_trace=[old|both|newfallback|new]
+		old: use old inexact backtracer
+		new: use new exact dwarf2 unwinder
+ 		both: print entries from both
+		newfallback: use new unwinder but fall back to old if it gets
+			stuck (default)
+
 Misc
 
   noreplacement  Don't replace instructions with more appropriate ones

MAINTAINERS

@@ -214,6 +214,12 @@ W:	http://acpi.sourceforge.net/
 T:	git kernel.org:/pub/scm/linux/kernel/git/lenb/linux-acpi-2.6.git
 S:	Maintained
 
+ACPI PCI HOTPLUG DRIVER
+P:	Kristen Carlson Accardi
+M:	kristen.c.accardi@intel.com
+L:	pcihpd-discuss@lists.sourceforge.net
+S:	Maintained
+
 AD1816 SOUND DRIVER
 P:	Thorsten Knabe
 M:	Thorsten Knabe <linux@thorsten-knabe.de>
@@ -292,6 +298,13 @@ L:	info-linux@geode.amd.com
 W:	http://www.amd.com/us-en/ConnectivitySolutions/TechnicalResources/0,,50_2334_2452_11363,00.html
 S:	Supported
 
+AOA (Apple Onboard Audio) ALSA DRIVER
+P:	Johannes Berg
+M:	johannes@sipsolutions.net
+L:	linuxppc-dev@ozlabs.org
+L:	alsa-devel@alsa-project.org
+S:	Maintained
+
 APM DRIVER
 P:	Stephen Rothwell
 M:	sfr@canb.auug.org.au
@@ -876,6 +889,12 @@ M:	rdunlap@xenotime.net
 T:	git http://tali.admingilde.org/git/linux-docbook.git
 S:	Maintained
 
+DOCKING STATION DRIVER
+P:	Kristen Carlson Accardi
+M:	kristen.c.accardi@intel.com
+L:	linux-acpi@vger.kernel.org
+S:	Maintained
+
 DOUBLETALK DRIVER
 P:	James R. Van Zandt
 M:	jrv@vanzandt.mv.com
@@ -968,6 +987,10 @@ P:	Andrey V. Savochkin
 M:	saw@saw.sw.com.sg
 S:	Maintained
 
+EFS FILESYSTEM
+W:	http://aeschi.ch.eu.org/efs/
+S:	Orphan
+
 EMU10K1 SOUND DRIVER
 P:	James Courtier-Dutton
 M:	James@superbug.demon.co.uk
@@ -1598,7 +1621,7 @@ W:	http://jfs.sourceforge.net/
 T:	git kernel.org:/pub/scm/linux/kernel/git/shaggy/jfs-2.6.git
 S:	Supported
 
-JOURNALLING LAYER FOR BLOCK DEVICS (JBD)
+JOURNALLING LAYER FOR BLOCK DEVICES (JBD)
 P:	Stephen Tweedie, Andrew Morton
 M:	sct@redhat.com, akpm@osdl.org
 L:	ext2-devel@lists.sourceforge.net
@@ -1642,9 +1665,8 @@ S:	Maintained
 
 KERNEL JANITORS
 P:	Several
-L:	kernel-janitors@osdl.org
+L:	kernel-janitors@lists.osdl.org
 W:	http://www.kerneljanitors.org/
-W:	http://sf.net/projects/kernel-janitor/
 S:	Maintained
 
 KERNEL NFSD
@@ -1882,6 +1904,12 @@ S:     linux-scsi@vger.kernel.org
 W:     http://megaraid.lsilogic.com
 S:     Maintained
 
+MEMORY MANAGEMENT
+L:	linux-mm@kvack.org
+L:	linux-kernel@vger.kernel.org
+W:	http://www.linux-mm.org
+S:	Maintained
+
 MEMORY TECHNOLOGY DEVICES (MTD)
 P:	David Woodhouse
 M:	dwmw2@infradead.org
@@ -2626,6 +2654,22 @@ M:	dbrownell@users.sourceforge.net
 L:	spi-devel-general@lists.sourceforge.net
 S:	Maintained
 
+STABLE BRANCH:
+P:	Greg Kroah-Hartman
+M:	greg@kroah.com
+P:	Chris Wright
+M:	chrisw@sous-sol.org
+L:	stable@kernel.org
+S:	Maintained
+
+STABLE BRANCH:
+P:	Greg Kroah-Hartman
+M:	greg@kroah.com
+P:	Chris Wright
+M:	chrisw@sous-sol.org
+L:	stable@kernel.org
+S:	Maintained
+
 TPM DEVICE DRIVER
 P:	Kylene Hall
 M:	kjhall@us.ibm.com

Makefile

@@ -1,7 +1,7 @@
 VERSION = 2
 PATCHLEVEL = 6
 SUBLEVEL = 18
-EXTRAVERSION = -rc2
+EXTRAVERSION = -rc4
 NAME=Crazed Snow-Weasel
 
 # *DOCUMENTATION*
@@ -309,9 +309,6 @@ CPPFLAGS        := -D__KERNEL__ $(LINUXINCLUDE)
 
 CFLAGS          := -Wall -Wundef -Wstrict-prototypes -Wno-trigraphs \
                    -fno-strict-aliasing -fno-common
-# Force gcc to behave correct even for buggy distributions
-CFLAGS          += $(call cc-option, -fno-stack-protector-all \
-                                     -fno-stack-protector)
 AFLAGS          := -D__ASSEMBLY__
 
 # Read KERNELRELEASE from include/config/kernel.release (if it exists)
@@ -368,6 +365,7 @@ endif
 
 no-dot-config-targets := clean mrproper distclean \
 			 cscope TAGS tags help %docs check% \
+			 include/linux/version.h headers_% \
 			 kernelrelease kernelversion
 
 config-targets := 0
@@ -435,12 +433,13 @@ core-y		:= usr/
 endif # KBUILD_EXTMOD
 
 ifeq ($(dot-config),1)
-# In this section, we need .config
+# Read in config
+-include include/config/auto.conf
 
+ifeq ($(KBUILD_EXTMOD),)
 # Read in dependencies to all Kconfig* files, make sure to run
 # oldconfig if changes are detected.
 -include include/config/auto.conf.cmd
--include include/config/auto.conf
 
 # To avoid any implicit rule to kick in, define an empty command
 $(KCONFIG_CONFIG) include/config/auto.conf.cmd: ;
@@ -450,16 +449,27 @@ $(KCONFIG_CONFIG) include/config/auto.conf.cmd: ;
 # if auto.conf.cmd is missing then we are probably in a cleaned tree so
 # we execute the config step to be sure to catch updated Kconfig files
 include/config/auto.conf: $(KCONFIG_CONFIG) include/config/auto.conf.cmd
-ifeq ($(KBUILD_EXTMOD),)
 	$(Q)$(MAKE) -f $(srctree)/Makefile silentoldconfig
 else
-	$(error kernel configuration not valid - run 'make prepare' in $(srctree) to update it)
+# external modules needs include/linux/autoconf.h and include/config/auto.conf
-endif
+# but do not care if they are up-to-date. Use auto.conf to trigger the test
+PHONY += include/config/auto.conf
+
+include/config/auto.conf:
+	$(Q)test -e include/linux/autoconf.h -a -e $@ || (		\
+	echo;								\
+	echo "  ERROR: Kernel configuration is invalid.";		\
+	echo "         include/linux/autoconf.h or $@ are missing.";	\
+	echo "         Run 'make oldconfig && make prepare' on kernel src to fix it.";	\
+	echo;								\
+	/bin/false)
+
+endif # KBUILD_EXTMOD
 
 else
 # Dummy target needed, because used as prerequisite
 include/config/auto.conf: ;
-endif
+endif # $(dot-config)
 
 # The all: target is the default when no target is given on the
 # command line.
@@ -473,6 +483,8 @@ else
 CFLAGS		+= -O2
 endif
 
+include $(srctree)/arch/$(ARCH)/Makefile
+
 ifdef CONFIG_FRAME_POINTER
 CFLAGS		+= -fno-omit-frame-pointer $(call cc-option,-fno-optimize-sibling-calls,)
 else
@@ -487,7 +499,8 @@ ifdef CONFIG_DEBUG_INFO
 CFLAGS		+= -g
 endif
 
-include $(srctree)/arch/$(ARCH)/Makefile
+# Force gcc to behave correct even for buggy distributions
+CFLAGS          += $(call cc-option, -fno-stack-protector)
 
 # arch Makefile may override CC so keep this after arch Makefile is included
 NOSTDINC_FLAGS += -nostdinc -isystem $(shell $(CC) -print-file-name=include)

arch/alpha/kernel/err_ev7.c

@@ -274,16 +274,14 @@ ev7_process_pal_subpacket(struct el_subpacket *header)
 struct el_subpacket_handler ev7_pal_subpacket_handler =
 	SUBPACKET_HANDLER_INIT(EL_CLASS__PAL, ev7_process_pal_subpacket);
 
-void 
+void
 ev7_register_error_handlers(void)
 {
 	int i;
 
-	for(i = 0;
+	for (i = 0; i < ARRAY_SIZE(el_ev7_pal_annotations); i++)
-	    i<sizeof(el_ev7_pal_annotations)/sizeof(el_ev7_pal_annotations[1]);
-	    i++) {
 		cdl_register_subpacket_annotation(&el_ev7_pal_annotations[i]);
-	}	
+
 	cdl_register_subpacket_handler(&ev7_pal_subpacket_handler);
 }
 

arch/alpha/kernel/osf_sys.c

@@ -623,12 +623,12 @@ osf_sysinfo(int command, char __user *buf, long count)
 	long len, err = -EINVAL;
 
 	offset = command-1;
-	if (offset >= sizeof(sysinfo_table)/sizeof(char *)) {
+	if (offset >= ARRAY_SIZE(sysinfo_table)) {
 		/* Digital UNIX has a few unpublished interfaces here */
 		printk("sysinfo(%d)", command);
 		goto out;
 	}
-	
+
 	down_read(&uts_sem);
 	res = sysinfo_table[offset];
 	len = strlen(res)+1;

arch/alpha/kernel/setup.c

@@ -114,8 +114,6 @@ struct alpha_machine_vector alpha_mv;
 int alpha_using_srm;
 #endif
 
-#define N(a) (sizeof(a)/sizeof(a[0]))
-
 static struct alpha_machine_vector *get_sysvec(unsigned long, unsigned long,
 					       unsigned long);
 static struct alpha_machine_vector *get_sysvec_byname(const char *);
@@ -240,7 +238,7 @@ reserve_std_resources(void)
 	standard_io_resources[0].start = RTC_PORT(0);
 	standard_io_resources[0].end = RTC_PORT(0) + 0x10;
 
-	for (i = 0; i < N(standard_io_resources); ++i)
+	for (i = 0; i < ARRAY_SIZE(standard_io_resources); ++i)
 		request_resource(io, standard_io_resources+i);
 }
 
@@ -918,13 +916,13 @@ get_sysvec(unsigned long type, unsigned long variation, unsigned long cpu)
 
 	/* Search the system tables first... */
 	vec = NULL;
-	if (type < N(systype_vecs)) {
+	if (type < ARRAY_SIZE(systype_vecs)) {
 		vec = systype_vecs[type];
 	} else if ((type > ST_API_BIAS) &&
-		   (type - ST_API_BIAS) < N(api_vecs)) {
+		   (type - ST_API_BIAS) < ARRAY_SIZE(api_vecs)) {
 		vec = api_vecs[type - ST_API_BIAS];
 	} else if ((type > ST_UNOFFICIAL_BIAS) &&
-		   (type - ST_UNOFFICIAL_BIAS) < N(unofficial_vecs)) {
+		   (type - ST_UNOFFICIAL_BIAS) < ARRAY_SIZE(unofficial_vecs)) {
 		vec = unofficial_vecs[type - ST_UNOFFICIAL_BIAS];
 	}
 
@@ -938,11 +936,11 @@ get_sysvec(unsigned long type, unsigned long variation, unsigned long cpu)
 
 		switch (type) {
 		case ST_DEC_ALCOR:
-			if (member < N(alcor_indices))
+			if (member < ARRAY_SIZE(alcor_indices))
 				vec = alcor_vecs[alcor_indices[member]];
 			break;
 		case ST_DEC_EB164:
-			if (member < N(eb164_indices))
+			if (member < ARRAY_SIZE(eb164_indices))
 				vec = eb164_vecs[eb164_indices[member]];
 			/* PC164 may show as EB164 variation with EV56 CPU,
 			   but, since no true EB164 had anything but EV5... */
@@ -950,24 +948,24 @@ get_sysvec(unsigned long type, unsigned long variation, unsigned long cpu)
 				vec = &pc164_mv;
 			break;
 		case ST_DEC_EB64P:
-			if (member < N(eb64p_indices))
+			if (member < ARRAY_SIZE(eb64p_indices))
 				vec = eb64p_vecs[eb64p_indices[member]];
 			break;
 		case ST_DEC_EB66:
-			if (member < N(eb66_indices))
+			if (member < ARRAY_SIZE(eb66_indices))
 				vec = eb66_vecs[eb66_indices[member]];
 			break;
 		case ST_DEC_MARVEL:
-			if (member < N(marvel_indices))
+			if (member < ARRAY_SIZE(marvel_indices))
 				vec = marvel_vecs[marvel_indices[member]];
 			break;
 		case ST_DEC_TITAN:
 			vec = titan_vecs[0];	/* default */
-			if (member < N(titan_indices))
+			if (member < ARRAY_SIZE(titan_indices))
 				vec = titan_vecs[titan_indices[member]];
 			break;
 		case ST_DEC_TSUNAMI:
-			if (member < N(tsunami_indices))
+			if (member < ARRAY_SIZE(tsunami_indices))
 				vec = tsunami_vecs[tsunami_indices[member]];
 			break;
 		case ST_DEC_1000:
@@ -1039,7 +1037,7 @@ get_sysvec_byname(const char *name)
 
 	size_t i;
 
-	for (i = 0; i < N(all_vecs); ++i) {
+	for (i = 0; i < ARRAY_SIZE(all_vecs); ++i) {
 		struct alpha_machine_vector *mv = all_vecs[i];
 		if (strcasecmp(mv->vector_name, name) == 0)
 			return mv;
@@ -1055,13 +1053,13 @@ get_sysnames(unsigned long type, unsigned long variation, unsigned long cpu,
 
 	/* If not in the tables, make it UNKNOWN,
 	   else set type name to family */
-	if (type < N(systype_names)) {
+	if (type < ARRAY_SIZE(systype_names)) {
 		*type_name = systype_names[type];
 	} else if ((type > ST_API_BIAS) &&
-		   (type - ST_API_BIAS) < N(api_names)) {
+		   (type - ST_API_BIAS) < ARRAY_SIZE(api_names)) {
 		*type_name = api_names[type - ST_API_BIAS];
 	} else if ((type > ST_UNOFFICIAL_BIAS) &&
-		   (type - ST_UNOFFICIAL_BIAS) < N(unofficial_names)) {
+		   (type - ST_UNOFFICIAL_BIAS) < ARRAY_SIZE(unofficial_names)) {
 		*type_name = unofficial_names[type - ST_UNOFFICIAL_BIAS];
 	} else {
 		*type_name = sys_unknown;
@@ -1083,7 +1081,7 @@ get_sysnames(unsigned long type, unsigned long variation, unsigned long cpu,
 	default: /* default to variation "0" for now */
 		break;
 	case ST_DEC_EB164:
-		if (member < N(eb164_indices))
+		if (member < ARRAY_SIZE(eb164_indices))
 			*variation_name = eb164_names[eb164_indices[member]];
 		/* PC164 may show as EB164 variation, but with EV56 CPU,
 		   so, since no true EB164 had anything but EV5... */
@@ -1091,32 +1089,32 @@ get_sysnames(unsigned long type, unsigned long variation, unsigned long cpu,
 			*variation_name = eb164_names[1]; /* make it PC164 */
 		break;
 	case ST_DEC_ALCOR:
-		if (member < N(alcor_indices))
+		if (member < ARRAY_SIZE(alcor_indices))
 			*variation_name = alcor_names[alcor_indices[member]];
 		break;
 	case ST_DEC_EB64P:
-		if (member < N(eb64p_indices))
+		if (member < ARRAY_SIZE(eb64p_indices))
 			*variation_name = eb64p_names[eb64p_indices[member]];
 		break;
 	case ST_DEC_EB66:
-		if (member < N(eb66_indices))
+		if (member < ARRAY_SIZE(eb66_indices))
 			*variation_name = eb66_names[eb66_indices[member]];
 		break;
 	case ST_DEC_MARVEL:
-		if (member < N(marvel_indices))
+		if (member < ARRAY_SIZE(marvel_indices))
 			*variation_name = marvel_names[marvel_indices[member]];
 		break;
 	case ST_DEC_RAWHIDE:
-		if (member < N(rawhide_indices))
+		if (member < ARRAY_SIZE(rawhide_indices))
 			*variation_name = rawhide_names[rawhide_indices[member]];
 		break;
 	case ST_DEC_TITAN:
 		*variation_name = titan_names[0];	/* default */
-		if (member < N(titan_indices))
+		if (member < ARRAY_SIZE(titan_indices))
 			*variation_name = titan_names[titan_indices[member]];
 		break;
 	case ST_DEC_TSUNAMI:
-		if (member < N(tsunami_indices))
+		if (member < ARRAY_SIZE(tsunami_indices))
 			*variation_name = tsunami_names[tsunami_indices[member]];
 		break;
 	}
@@ -1211,7 +1209,7 @@ show_cpuinfo(struct seq_file *f, void *slot)
 
 	cpu_index = (unsigned) (cpu->type - 1);
 	cpu_name = "Unknown";
-	if (cpu_index < N(cpu_names))
+	if (cpu_index < ARRAY_SIZE(cpu_names))
 		cpu_name = cpu_names[cpu_index];
 
 	get_sysnames(hwrpb->sys_type, hwrpb->sys_variation,

arch/alpha/kernel/sys_ruffian.c

@@ -182,16 +182,16 @@ static unsigned long __init
 ruffian_get_bank_size(unsigned long offset)
 {
 	unsigned long bank_addr, bank, ret = 0;
-  
+
 	/* Valid offsets are: 0x800, 0x840 and 0x880
 	   since Ruffian only uses three banks.  */
 	bank_addr = (unsigned long)PYXIS_MCR + offset;
 	bank = *(vulp)bank_addr;
-    
+
 	/* Check BANK_ENABLE */
 	if (bank & 0x01) {
 		static unsigned long size[] __initdata = {
-			0x40000000UL, /* 0x00,   1G */ 
+			0x40000000UL, /* 0x00,   1G */
 			0x20000000UL, /* 0x02, 512M */
 			0x10000000UL, /* 0x04, 256M */
 			0x08000000UL, /* 0x06, 128M */
@@ -203,7 +203,7 @@ ruffian_get_bank_size(unsigned long offset)
 		};
 
 		bank = (bank & 0x1e) >> 1;
-		if (bank < sizeof(size)/sizeof(*size))
+		if (bank < ARRAY_SIZE(size))
 			ret = size[bank];
 	}
 

arch/alpha/kernel/time.c

@@ -233,7 +233,7 @@ validate_cc_value(unsigned long cc)
 	index = cpu->type & 0xffffffff;
 
 	/* If index out of bounds, no way to validate.  */
-	if (index >= sizeof(cpu_hz)/sizeof(cpu_hz[0]))
+	if (index >= ARRAY_SIZE(cpu_hz))
 		return cc;
 
 	/* If index contains no data, no way to validate.  */

arch/arm/common/dmabounce.c

@@ -179,17 +179,19 @@ alloc_safe_buffer(struct dmabounce_device_info *device_info, void *ptr,
 static inline struct safe_buffer *
 find_safe_buffer(struct dmabounce_device_info *device_info, dma_addr_t safe_dma_addr)
 {
-	struct safe_buffer *b = NULL;
+	struct safe_buffer *b, *rb = NULL;
 	unsigned long flags;
 
 	read_lock_irqsave(&device_info->lock, flags);
 
 	list_for_each_entry(b, &device_info->safe_buffers, node)
-		if (b->safe_dma_addr == safe_dma_addr)
+		if (b->safe_dma_addr == safe_dma_addr) {
+			rb = b;
 			break;
+		}
 
 	read_unlock_irqrestore(&device_info->lock, flags);
-	return b;
+	return rb;
 }
 
 static inline void

arch/arm/common/gic.c

@@ -95,7 +95,8 @@ static void gic_set_cpu(unsigned int irq, cpumask_t mask_val)
 }
 #endif
 
-static struct irqchip gic_chip = {
+static struct irq_chip gic_chip = {
+	.name		= "GIC",
 	.ack		= gic_ack_irq,
 	.mask		= gic_mask_irq,
 	.unmask		= gic_unmask_irq,

arch/arm/common/locomo.c

@@ -204,7 +204,8 @@ static void locomo_unmask_irq(unsigned int irq)
 	locomo_writel(r, mapbase + LOCOMO_ICR);
 }
 
-static struct irqchip locomo_chip = {
+static struct irq_chip locomo_chip = {
+	.name	= "LOCOMO",
 	.ack	= locomo_ack_irq,
 	.mask	= locomo_mask_irq,
 	.unmask	= locomo_unmask_irq,
@@ -249,7 +250,8 @@ static void locomo_key_unmask_irq(unsigned int irq)
 	locomo_writel(r, mapbase + LOCOMO_KEYBOARD + LOCOMO_KIC);
 }
 
-static struct irqchip locomo_key_chip = {
+static struct irq_chip locomo_key_chip = {
+	.name	= "LOCOMO-key",
 	.ack	= locomo_key_ack_irq,
 	.mask	= locomo_key_mask_irq,
 	.unmask	= locomo_key_unmask_irq,
@@ -312,7 +314,8 @@ static void locomo_gpio_unmask_irq(unsigned int irq)
 	locomo_writel(r, mapbase + LOCOMO_GIE);
 }
 
-static struct irqchip locomo_gpio_chip = {
+static struct irq_chip locomo_gpio_chip = {
+	.name	= "LOCOMO-gpio",
 	.ack	= locomo_gpio_ack_irq,
 	.mask	= locomo_gpio_mask_irq,
 	.unmask	= locomo_gpio_unmask_irq,
@@ -357,7 +360,8 @@ static void locomo_lt_unmask_irq(unsigned int irq)
 	locomo_writel(r, mapbase + LOCOMO_LTINT);
 }
 
-static struct irqchip locomo_lt_chip = {
+static struct irq_chip locomo_lt_chip = {
+	.name	= "LOCOMO-lt",
 	.ack	= locomo_lt_ack_irq,
 	.mask	= locomo_lt_mask_irq,
 	.unmask	= locomo_lt_unmask_irq,
@@ -418,7 +422,8 @@ static void locomo_spi_unmask_irq(unsigned int irq)
 	locomo_writel(r, mapbase + LOCOMO_SPIIE);
 }
 
-static struct irqchip locomo_spi_chip = {
+static struct irq_chip locomo_spi_chip = {
+	.name	= "LOCOMO-spi",
 	.ack	= locomo_spi_ack_irq,
 	.mask	= locomo_spi_mask_irq,
 	.unmask	= locomo_spi_unmask_irq,

arch/arm/common/rtctime.c

@@ -68,6 +68,7 @@ void rtc_next_alarm_time(struct rtc_time *next, struct rtc_time *now, struct rtc
 		rtc_time_to_tm(next_time, next);
 	}
 }
+EXPORT_SYMBOL(rtc_next_alarm_time);
 
 static inline int rtc_arm_read_time(struct rtc_ops *ops, struct rtc_time *tm)
 {

arch/arm/common/sa1111.c

@@ -272,7 +272,8 @@ static int sa1111_wake_lowirq(unsigned int irq, unsigned int on)
 	return 0;
 }
 
-static struct irqchip sa1111_low_chip = {
+static struct irq_chip sa1111_low_chip = {
+	.name		= "SA1111-l",
 	.ack		= sa1111_ack_irq,
 	.mask		= sa1111_mask_lowirq,
 	.unmask		= sa1111_unmask_lowirq,
@@ -368,7 +369,8 @@ static int sa1111_wake_highirq(unsigned int irq, unsigned int on)
 	return 0;
 }
 
-static struct irqchip sa1111_high_chip = {
+static struct irq_chip sa1111_high_chip = {
+	.name		= "SA1111-h",
 	.ack		= sa1111_ack_irq,
 	.mask		= sa1111_mask_highirq,
 	.unmask		= sa1111_unmask_highirq,

arch/arm/common/vic.c

@@ -39,7 +39,8 @@ static void vic_unmask_irq(unsigned int irq)
 	writel(1 << irq, base + VIC_INT_ENABLE);
 }
 
-static struct irqchip vic_chip = {
+static struct irq_chip vic_chip = {
+	.name	= "VIC",
 	.ack	= vic_mask_irq,
 	.mask	= vic_mask_irq,
 	.unmask	= vic_unmask_irq,

arch/arm/configs/ep93xx_defconfig

@@ -1,7 +1,7 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.18-rc1
+# Linux kernel version: 2.6.18-rc1-git9
-# Sun Jul  9 15:21:30 2006
+# Sat Jul 15 15:08:10 2006
 #
 CONFIG_ARM=y
 CONFIG_MMU=y
@@ -30,6 +30,7 @@ CONFIG_SWAP=y
 CONFIG_SYSVIPC=y
 # CONFIG_POSIX_MQUEUE is not set
 # CONFIG_BSD_PROCESS_ACCT is not set
+# CONFIG_TASKSTATS is not set
 CONFIG_SYSCTL=y
 # CONFIG_AUDIT is not set
 CONFIG_IKCONFIG=y
@@ -749,7 +750,7 @@ CONFIG_VIDEO_V4L2=y
 # USB support
 #
 CONFIG_USB_ARCH_HAS_HCD=y
-# CONFIG_USB_ARCH_HAS_OHCI is not set
+CONFIG_USB_ARCH_HAS_OHCI=y
 # CONFIG_USB_ARCH_HAS_EHCI is not set
 CONFIG_USB=y
 CONFIG_USB_DEBUG=y
@@ -766,6 +767,9 @@ CONFIG_USB_DYNAMIC_MINORS=y
 # USB Host Controller Drivers
 #
 # CONFIG_USB_ISP116X_HCD is not set
+CONFIG_USB_OHCI_HCD=y
+# CONFIG_USB_OHCI_BIG_ENDIAN is not set
+CONFIG_USB_OHCI_LITTLE_ENDIAN=y
 # CONFIG_USB_SL811_HCD is not set
 
 #
@@ -855,6 +859,7 @@ CONFIG_USB_SERIAL_CONSOLE=y
 CONFIG_USB_SERIAL_PL2303=y
 # CONFIG_USB_SERIAL_HP4X is not set
 # CONFIG_USB_SERIAL_SAFE is not set
+# CONFIG_USB_SERIAL_SIERRAWIRELESS is not set
 # CONFIG_USB_SERIAL_TI is not set
 # CONFIG_USB_SERIAL_CYBERJACK is not set
 # CONFIG_USB_SERIAL_XIRCOM is not set
@@ -871,7 +876,7 @@ CONFIG_USB_SERIAL_PL2303=y
 # CONFIG_USB_LEGOTOWER is not set
 # CONFIG_USB_LCD is not set
 # CONFIG_USB_LED is not set
-# CONFIG_USB_CY7C63 is not set
+# CONFIG_USB_CYPRESS_CY7C63 is not set
 # CONFIG_USB_CYTHERM is not set
 # CONFIG_USB_PHIDGETKIT is not set
 # CONFIG_USB_PHIDGETSERVO is not set
@@ -916,6 +921,7 @@ CONFIG_RTC_INTF_DEV=y
 # CONFIG_RTC_DRV_X1205 is not set
 # CONFIG_RTC_DRV_DS1307 is not set
 # CONFIG_RTC_DRV_DS1553 is not set
+# CONFIG_RTC_DRV_ISL1208 is not set
 # CONFIG_RTC_DRV_DS1672 is not set
 # CONFIG_RTC_DRV_DS1742 is not set
 # CONFIG_RTC_DRV_PCF8563 is not set
@@ -1023,7 +1029,6 @@ CONFIG_SUNRPC=y
 # CONFIG_RPCSEC_GSS_SPKM3 is not set
 # CONFIG_SMB_FS is not set
 # CONFIG_CIFS is not set
-# CONFIG_CIFS_DEBUG2 is not set
 # CONFIG_NCP_FS is not set
 # CONFIG_CODA_FS is not set
 # CONFIG_AFS_FS is not set

arch/arm/kernel/ecard.c

@@ -470,7 +470,8 @@ static void ecard_irq_mask(unsigned int irqnr)
 	}
 }
 
-static struct irqchip ecard_chip = {
+static struct irq_chip ecard_chip = {
+	.name	= "ECARD",
 	.ack	= ecard_irq_mask,
 	.mask	= ecard_irq_mask,
 	.unmask = ecard_irq_unmask,

arch/arm/kernel/entry-armv.S

@@ -634,6 +634,14 @@ ENTRY(__switch_to)
  * purpose.
  */
 
+	.macro	usr_ret, reg
+#ifdef CONFIG_ARM_THUMB
+	bx	\reg
+#else
+	mov	pc, \reg
+#endif
+	.endm
+
 	.align	5
 	.globl	__kuser_helper_start
 __kuser_helper_start:
@@ -675,7 +683,7 @@ __kuser_memory_barrier:				@ 0xffff0fa0
 #if __LINUX_ARM_ARCH__ >= 6 && defined(CONFIG_SMP)
 	mcr	p15, 0, r0, c7, c10, 5	@ dmb
 #endif
-	mov	pc, lr
+	usr_ret	lr
 
 	.align	5
 
@@ -778,7 +786,7 @@ __kuser_cmpxchg:				@ 0xffff0fc0
 	mov	r0, #-1
 	adds	r0, r0, #0
 #endif
-	mov	pc, lr
+	usr_ret	lr
 
 #else
 
@@ -792,7 +800,7 @@ __kuser_cmpxchg:				@ 0xffff0fc0
 #ifdef CONFIG_SMP
 	mcr	p15, 0, r0, c7, c10, 5	@ dmb
 #endif
-	mov	pc, lr
+	usr_ret	lr
 
 #endif
 
@@ -834,16 +842,11 @@ __kuser_cmpxchg:				@ 0xffff0fc0
 __kuser_get_tls:				@ 0xffff0fe0
 
 #if !defined(CONFIG_HAS_TLS_REG) && !defined(CONFIG_TLS_REG_EMUL)
-
 	ldr	r0, [pc, #(16 - 8)]		@ TLS stored at 0xffff0ff0
-	mov	pc, lr
-
 #else
-
 	mrc	p15, 0, r0, c13, c0, 3		@ read TLS register
-	mov	pc, lr
-
 #endif
+	usr_ret	lr
 
 	.rep	5
 	.word	0			@ pad up to __kuser_helper_version

arch/arm/kernel/head.S

@@ -114,18 +114,18 @@ ENTRY(secondary_startup)
 	 * Use the page tables supplied from  __cpu_up.
 	 */
 	adr	r4, __secondary_data
-	ldmia	r4, {r5, r6, r13}		@ address to jump to after
+	ldmia	r4, {r5, r7, r13}		@ address to jump to after
 	sub	r4, r4, r5			@ mmu has been enabled
-	ldr	r4, [r6, r4]			@ get secondary_data.pgdir
+	ldr	r4, [r7, r4]			@ get secondary_data.pgdir
 	adr	lr, __enable_mmu		@ return address
-	add	pc, r10, #12			@ initialise processor
+	add	pc, r10, #PROCINFO_INITFUNC	@ initialise processor
 						@ (return control reg)
 
 	/*
 	 * r6  = &secondary_data
 	 */
 ENTRY(__secondary_switched)
-	ldr	sp, [r6, #4]			@ get secondary_data.stack
+	ldr	sp, [r7, #4]			@ get secondary_data.stack
 	mov	fp, #0
 	b	secondary_start_kernel
 

arch/arm/kernel/irq.c

@@ -77,6 +77,7 @@ int show_interrupts(struct seq_file *p, void *v)
 		seq_printf(p, "%3d: ", i);
 		for_each_present_cpu(cpu)
 			seq_printf(p, "%10u ", kstat_cpu(cpu).irqs[i]);
+		seq_printf(p, " %10s", irq_desc[i].chip->name ? : "-");
 		seq_printf(p, "  %s", action->name);
 		for (action = action->next; action; action = action->next)
 			seq_printf(p, ", %s", action->name);

arch/arm/kernel/traps.c

@@ -232,11 +232,8 @@ NORET_TYPE void die(const char *str, struct pt_regs *regs, int err)
 	bust_spinlocks(0);
 	spin_unlock_irq(&die_lock);
 
-	if (panic_on_oops) {
+	if (panic_on_oops)
-		printk(KERN_EMERG "Fatal exception: panic in 5 seconds\n");
-		ssleep(5);
 		panic("Fatal exception");
-	}
 
 	do_exit(SIGSEGV);
 }

arch/arm/mach-at91rm9200/gpio.c

@@ -327,7 +327,8 @@ static int gpio_irq_type(unsigned pin, unsigned type)
 	return (type == IRQT_BOTHEDGE) ? 0 : -EINVAL;
 }
 
-static struct irqchip gpio_irqchip = {
+static struct irq_chip gpio_irqchip = {
+	.name		= "GPIO",
 	.mask		= gpio_irq_mask,
 	.unmask		= gpio_irq_unmask,
 	.set_type	= gpio_irq_type,

arch/arm/mach-at91rm9200/irq.c

@@ -114,7 +114,8 @@ void at91_irq_resume(void)
 #define at91_aic_set_wake	NULL
 #endif
 
-static struct irqchip at91_aic_chip = {
+static struct irq_chip at91_aic_chip = {
+	.name		= "AIC",
 	.ack		= at91_aic_mask_irq,
 	.mask		= at91_aic_mask_irq,
 	.unmask		= at91_aic_unmask_irq,

arch/arm/mach-footbridge/cats-hw.c

@@ -8,7 +8,7 @@
 #include <linux/ioport.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
-#include <linux/tty.h>
+#include <linux/screen_info.h>
 
 #include <asm/hardware/dec21285.h>
 #include <asm/io.h>

arch/arm/mach-imx/irq.c

@@ -204,13 +204,15 @@ imx_gpiod_demux_handler(unsigned int irq_unused, struct irqdesc *desc,
 	imx_gpio_handler(mask, irq, desc, regs);
 }
 
-static struct irqchip imx_internal_chip = {
+static struct irq_chip imx_internal_chip = {
+	.name = "MPU",
 	.ack = imx_mask_irq,
 	.mask = imx_mask_irq,
 	.unmask = imx_unmask_irq,
 };
 
-static struct irqchip imx_gpio_chip = {
+static struct irq_chip imx_gpio_chip = {
+	.name = "GPIO",
 	.ack = imx_gpio_ack_irq,
 	.mask = imx_gpio_mask_irq,
 	.unmask = imx_gpio_unmask_irq,

arch/arm/mach-integrator/integrator_ap.c

@@ -161,7 +161,8 @@ static void sc_unmask_irq(unsigned int irq)
 	writel(1 << irq, VA_IC_BASE + IRQ_ENABLE_SET);
 }
 
-static struct irqchip sc_chip = {
+static struct irq_chip sc_chip = {
+	.name	= "SC",
 	.ack	= sc_mask_irq,
 	.mask	= sc_mask_irq,
 	.unmask = sc_unmask_irq,

arch/arm/mach-integrator/integrator_cp.c

@@ -156,7 +156,8 @@ static void cic_unmask_irq(unsigned int irq)
 	cic_writel(1 << irq, INTCP_VA_CIC_BASE + IRQ_ENABLE_SET);
 }
 
-static struct irqchip cic_chip = {
+static struct irq_chip cic_chip = {
+	.name	= "CIC",
 	.ack	= cic_mask_irq,
 	.mask	= cic_mask_irq,
 	.unmask	= cic_unmask_irq,
@@ -174,7 +175,8 @@ static void pic_unmask_irq(unsigned int irq)
 	pic_writel(1 << irq, INTCP_VA_PIC_BASE + IRQ_ENABLE_SET);
 }
 
-static struct irqchip pic_chip = {
+static struct irq_chip pic_chip = {
+	.name	= "PIC",
 	.ack	= pic_mask_irq,
 	.mask	= pic_mask_irq,
 	.unmask = pic_unmask_irq,
@@ -192,7 +194,8 @@ static void sic_unmask_irq(unsigned int irq)
 	sic_writel(1 << irq, INTCP_VA_SIC_BASE + IRQ_ENABLE_SET);
 }
 
-static struct irqchip sic_chip = {
+static struct irq_chip sic_chip = {
+	.name	= "SIC",
 	.ack	= sic_mask_irq,
 	.mask	= sic_mask_irq,
 	.unmask	= sic_unmask_irq,

arch/arm/mach-iop3xx/iop321-irq.c

@@ -52,7 +52,8 @@ iop321_irq_unmask (unsigned int irq)
 	intctl_write(iop321_mask);
 }
 
-struct irqchip ext_chip = {
+struct irq_chip ext_chip = {
+	.name	= "IOP",
 	.ack    = iop321_irq_mask,
 	.mask   = iop321_irq_mask,
 	.unmask = iop321_irq_unmask,

arch/arm/mach-iop3xx/iop331-irq.c

@@ -77,13 +77,15 @@ iop331_irq_unmask2(unsigned int irq)
         intctl_write1(iop331_mask1);
 }
 
-struct irqchip iop331_irqchip1 = {
+struct irq_chip iop331_irqchip1 = {
+	.name	= "IOP-1",
 	.ack    = iop331_irq_mask1,
 	.mask   = iop331_irq_mask1,
 	.unmask = iop331_irq_unmask1,
 };
 
-struct irqchip iop331_irqchip2 = {
+struct irq_chip iop331_irqchip2 = {
+	.name	= "IOP-2",
 	.ack    = iop331_irq_mask2,
 	.mask   = iop331_irq_mask2,
 	.unmask = iop331_irq_unmask2,

arch/arm/mach-ixp4xx/common-pci.c

@@ -532,8 +532,6 @@ pci_set_consistent_dma_mask(struct pci_dev *dev, u64 mask)
 	return -EIO;
 }
 
-EXPORT_SYMBOL(pci_set_dma_mask);
-EXPORT_SYMBOL(pci_set_consistent_dma_mask);
 EXPORT_SYMBOL(ixp4xx_pci_read);
 EXPORT_SYMBOL(ixp4xx_pci_write);
 

arch/arm/mach-ixp4xx/gtwx5715-setup.c

@@ -107,9 +107,9 @@ static struct flash_platform_data gtwx5715_flash_data = {
 	.width		= 2,
 };
 
-static struct gtw5715_flash_resource = {
+static struct resource gtwx5715_flash_resource = {
 	.flags		= IORESOURCE_MEM,
-}
+};
 
 static struct platform_device gtwx5715_flash = {
 	.name		= "IXP4XX-Flash",
@@ -130,9 +130,6 @@ static void __init gtwx5715_init(void)
 {
 	ixp4xx_sys_init();
 
-	if (!flash_resource)
-		printk(KERN_ERR "Could not allocate flash resource\n");
-
 	gtwx5715_flash_resource.start = IXP4XX_EXP_BUS_BASE(0);
 	gtwx5715_flash_resource.end = IXP4XX_EXP_BUS_BASE(0) + SZ_8M - 1;
 

arch/arm/mach-lh7a40x/arch-kev7a400.c

@@ -63,7 +63,8 @@ static void kev7a400_unmask_cpld_irq (u32 irq)
 	CPLD_WR_PB_INT_MASK = CPLD_IRQ_mask;
 }
 
-static struct irqchip kev7a400_cpld_chip = {
+static struct irq_chip kev7a400_cpld_chip = {
+	.name	= "CPLD",
 	.ack	= kev7a400_ack_cpld_irq,
 	.mask	= kev7a400_mask_cpld_irq,
 	.unmask	= kev7a400_unmask_cpld_irq,

arch/arm/mach-lh7a40x/arch-lpd7a40x.c

@@ -200,7 +200,8 @@ static void lh7a40x_unmask_cpld_irq (u32 irq)
 	}
 }
 
-static struct irqchip lpd7a40x_cpld_chip = {
+static struct irq_chip lpd7a40x_cpld_chip = {
+	.name	= "CPLD",
 	.ack	= lh7a40x_ack_cpld_irq,
 	.mask	= lh7a40x_mask_cpld_irq,
 	.unmask	= lh7a40x_unmask_cpld_irq,

arch/arm/mach-lh7a40x/irq-kev7a400.c

@@ -43,7 +43,8 @@ lh7a400_unmask_cpld_irq (u32 irq)
 }
 
 static struct
-irqchip lh7a400_cpld_chip = {
+irq_chip lh7a400_cpld_chip = {
+	.name	= "CPLD",
 	.ack	= lh7a400_ack_cpld_irq,
 	.mask	= lh7a400_mask_cpld_irq,
 	.unmask	= lh7a400_unmask_cpld_irq,

arch/arm/mach-lh7a40x/irq-lh7a400.c

@@ -38,13 +38,15 @@ static void lh7a400_ack_gpio_irq (u32 irq)
 	INTC_INTENC = (1 << irq);
 }
 
-static struct irqchip lh7a400_internal_chip = {
+static struct irq_chip lh7a400_internal_chip = {
+	.name	= "MPU",
 	.ack	= lh7a400_mask_irq, /* Level triggering -> mask is ack */
 	.mask	= lh7a400_mask_irq,
 	.unmask	= lh7a400_unmask_irq,
 };
 
-static struct irqchip lh7a400_gpio_chip = {
+static struct irq_chip lh7a400_gpio_chip = {
+	.name	= "GPIO",
 	.ack	= lh7a400_ack_gpio_irq,
 	.mask	= lh7a400_mask_irq,
 	.unmask	= lh7a400_unmask_irq,

arch/arm/mach-lh7a40x/irq-lh7a404.c

@@ -76,25 +76,29 @@ static void lh7a404_vic2_ack_gpio_irq (u32 irq)
 	VIC2_INTENCLR = (1 << irq);
 }
 
-static struct irqchip lh7a404_vic1_chip = {
+static struct irq_chip lh7a404_vic1_chip = {
+	.name	= "VIC1",
 	.ack	= lh7a404_vic1_mask_irq, /* Because level-triggered */
 	.mask	= lh7a404_vic1_mask_irq,
 	.unmask	= lh7a404_vic1_unmask_irq,
 };
 
-static struct irqchip lh7a404_vic2_chip = {
+static struct irq_chip lh7a404_vic2_chip = {
+	.name	= "VIC2",
 	.ack	= lh7a404_vic2_mask_irq, /* Because level-triggered */
 	.mask	= lh7a404_vic2_mask_irq,
 	.unmask	= lh7a404_vic2_unmask_irq,
 };
 
-static struct irqchip lh7a404_gpio_vic1_chip = {
+static struct irq_chip lh7a404_gpio_vic1_chip = {
+	.name	= "GPIO-VIC1",
 	.ack	= lh7a404_vic1_ack_gpio_irq,
 	.mask	= lh7a404_vic1_mask_irq,
 	.unmask	= lh7a404_vic1_unmask_irq,
 };
 
-static struct irqchip lh7a404_gpio_vic2_chip = {
+static struct irq_chip lh7a404_gpio_vic2_chip = {
+	.name	= "GPIO-VIC2",
 	.ack	= lh7a404_vic2_ack_gpio_irq,
 	.mask	= lh7a404_vic2_mask_irq,
 	.unmask	= lh7a404_vic2_unmask_irq,

arch/arm/mach-lh7a40x/irq-lpd7a40x.c

@@ -50,7 +50,8 @@ static void lh7a40x_unmask_cpld_irq (u32 irq)
 	}
 }
 
-static struct irqchip lh7a40x_cpld_chip = {
+static struct irq_chip lh7a40x_cpld_chip = {
+	.name	= "CPLD",
 	.ack	= lh7a40x_ack_cpld_irq,
 	.mask	= lh7a40x_mask_cpld_irq,
 	.unmask	= lh7a40x_unmask_cpld_irq,

arch/arm/mach-omap1/fpga.c

@@ -106,14 +106,16 @@ void innovator_fpga_IRQ_demux(unsigned int irq, struct irqdesc *desc,
 	}
 }
 
-static struct irqchip omap_fpga_irq_ack = {
+static struct irq_chip omap_fpga_irq_ack = {
+	.name		= "FPGA-ack",
 	.ack		= fpga_mask_ack_irq,
 	.mask		= fpga_mask_irq,
 	.unmask		= fpga_unmask_irq,
 };
 
 
-static struct irqchip omap_fpga_irq = {
+static struct irq_chip omap_fpga_irq = {
+	.name		= "FPGA",
 	.ack		= fpga_ack_irq,
 	.mask		= fpga_mask_irq,
 	.unmask		= fpga_unmask_irq,

arch/arm/mach-omap1/irq.c

@@ -168,7 +168,8 @@ static struct omap_irq_bank omap1610_irq_banks[] = {
 };
 #endif
 
-static struct irqchip omap_irq_chip = {
+static struct irq_chip omap_irq_chip = {
+	.name		= "MPU",
 	.ack		= omap_mask_ack_irq,
 	.mask		= omap_mask_irq,
 	.unmask		= omap_unmask_irq,

arch/arm/mach-omap2/irq.c

@@ -94,7 +94,8 @@ static void omap_mask_ack_irq(unsigned int irq)
 	omap_ack_irq(irq);
 }
 
-static struct irqchip omap_irq_chip = {
+static struct irq_chip omap_irq_chip = {
+	.name	= "INTC",
 	.ack	= omap_mask_ack_irq,
 	.mask	= omap_mask_irq,
 	.unmask	= omap_unmask_irq,

arch/arm/mach-pxa/irq.c

@@ -39,7 +39,8 @@ static void pxa_unmask_low_irq(unsigned int irq)
 	ICMR |= (1 << (irq + PXA_IRQ_SKIP));
 }
 
-static struct irqchip pxa_internal_chip_low = {
+static struct irq_chip pxa_internal_chip_low = {
+	.name		= "SC",
 	.ack		= pxa_mask_low_irq,
 	.mask		= pxa_mask_low_irq,
 	.unmask		= pxa_unmask_low_irq,
@@ -61,7 +62,8 @@ static void pxa_unmask_high_irq(unsigned int irq)
 	ICMR2 |= (1 << (irq - 32 + PXA_IRQ_SKIP));
 }
 
-static struct irqchip pxa_internal_chip_high = {
+static struct irq_chip pxa_internal_chip_high = {
+	.name		= "SC-hi",
 	.ack		= pxa_mask_high_irq,
 	.mask		= pxa_mask_high_irq,
 	.unmask		= pxa_unmask_high_irq,
@@ -129,7 +131,8 @@ static void pxa_ack_low_gpio(unsigned int irq)
 	GEDR0 = (1 << (irq - IRQ_GPIO0));
 }
 
-static struct irqchip pxa_low_gpio_chip = {
+static struct irq_chip pxa_low_gpio_chip = {
+	.name		= "GPIO-l",
 	.ack		= pxa_ack_low_gpio,
 	.mask		= pxa_mask_low_irq,
 	.unmask		= pxa_unmask_low_irq,
@@ -237,7 +240,8 @@ static void pxa_unmask_muxed_gpio(unsigned int irq)
 	GFER(gpio) = GPIO_IRQ_falling_edge[idx] & GPIO_IRQ_mask[idx];
 }
 
-static struct irqchip pxa_muxed_gpio_chip = {
+static struct irq_chip pxa_muxed_gpio_chip = {
+	.name		= "GPIO",
 	.ack		= pxa_ack_muxed_gpio,
 	.mask		= pxa_mask_muxed_gpio,
 	.unmask		= pxa_unmask_muxed_gpio,

arch/arm/mach-pxa/lpd270.c

@@ -68,7 +68,8 @@ static void lpd270_unmask_irq(unsigned int irq)
 	__raw_writew(lpd270_irq_enabled, LPD270_INT_MASK);
 }
 
-static struct irqchip lpd270_irq_chip = {
+static struct irq_chip lpd270_irq_chip = {
+	.name		= "CPLD",
 	.ack		= lpd270_mask_irq,
 	.mask		= lpd270_mask_irq,
 	.unmask		= lpd270_unmask_irq,

arch/arm/mach-pxa/lubbock.c

@@ -78,7 +78,8 @@ static void lubbock_unmask_irq(unsigned int irq)
 	LUB_IRQ_MASK_EN = (lubbock_irq_enabled |= (1 << lubbock_irq));
 }
 
-static struct irqchip lubbock_irq_chip = {
+static struct irq_chip lubbock_irq_chip = {
+	.name		= "FPGA",
 	.ack		= lubbock_mask_irq,
 	.mask		= lubbock_mask_irq,
 	.unmask		= lubbock_unmask_irq,

arch/arm/mach-pxa/mainstone.c

@@ -64,7 +64,8 @@ static void mainstone_unmask_irq(unsigned int irq)
 	MST_INTMSKENA = (mainstone_irq_enabled |= (1 << mainstone_irq));
 }
 
-static struct irqchip mainstone_irq_chip = {
+static struct irq_chip mainstone_irq_chip = {
+	.name		= "FPGA",
 	.ack		= mainstone_mask_irq,
 	.mask		= mainstone_mask_irq,
 	.unmask		= mainstone_unmask_irq,

arch/arm/mach-s3c2410/Makefile

@@ -10,45 +10,47 @@ obj-m			:=
 obj-n			:=
 obj-			:=
 
+# DMA
+obj-$(CONFIG_S3C2410_DMA)	+= dma.o
+
 # S3C2400 support files
-obj-$(CONFIG_CPU_S3C2400)  += s3c2400-gpio.o
+obj-$(CONFIG_CPU_S3C2400)	+= s3c2400-gpio.o
 
 # S3C2410 support files
 
-obj-$(CONFIG_CPU_S3C2410)  += s3c2410.o
+obj-$(CONFIG_CPU_S3C2410)	+= s3c2410.o
-obj-$(CONFIG_CPU_S3C2410)  += s3c2410-gpio.o
+obj-$(CONFIG_CPU_S3C2410)	+= s3c2410-gpio.o
-obj-$(CONFIG_S3C2410_DMA)  += dma.o
 
 # Power Management support
 
-obj-$(CONFIG_PM)	   += pm.o sleep.o
+obj-$(CONFIG_PM)		+= pm.o sleep.o
-obj-$(CONFIG_PM_SIMTEC)	   += pm-simtec.o
+obj-$(CONFIG_PM_SIMTEC)		+= pm-simtec.o
 
 # S3C2412 support
-obj-$(CONFIG_CPU_S3C2412)  += s3c2412.o
+obj-$(CONFIG_CPU_S3C2412)	+= s3c2412.o
-obj-$(CONFIG_CPU_S3C2412)  += s3c2412-clock.o
+obj-$(CONFIG_CPU_S3C2412)	+= s3c2412-clock.o
 
 #
 # S3C244X support
 
-obj-$(CONFIG_CPU_S3C244X)  += s3c244x.o
+obj-$(CONFIG_CPU_S3C244X)	+= s3c244x.o
-obj-$(CONFIG_CPU_S3C244X)  += s3c244x-irq.o
+obj-$(CONFIG_CPU_S3C244X)	+= s3c244x-irq.o
 
 # Clock control
 
-obj-$(CONFIG_S3C2410_CLOCK) += s3c2410-clock.o
+obj-$(CONFIG_S3C2410_CLOCK)	+= s3c2410-clock.o
 
 # S3C2440 support
 
-obj-$(CONFIG_CPU_S3C2440)  += s3c2440.o s3c2440-dsc.o
+obj-$(CONFIG_CPU_S3C2440)	+= s3c2440.o s3c2440-dsc.o
-obj-$(CONFIG_CPU_S3C2440)  += s3c2440-irq.o
+obj-$(CONFIG_CPU_S3C2440)	+= s3c2440-irq.o
-obj-$(CONFIG_CPU_S3C2440)  += s3c2440-clock.o
+obj-$(CONFIG_CPU_S3C2440)	+= s3c2440-clock.o
-obj-$(CONFIG_CPU_S3C2440)  += s3c2410-gpio.o
+obj-$(CONFIG_CPU_S3C2440)	+= s3c2410-gpio.o
 
 # S3C2442 support
 
-obj-$(CONFIG_CPU_S3C2442)  += s3c2442.o
+obj-$(CONFIG_CPU_S3C2442)	+= s3c2442.o
-obj-$(CONFIG_CPU_S3C2442)  += s3c2442-clock.o
+obj-$(CONFIG_CPU_S3C2442)	+= s3c2442-clock.o
 
 # bast extras
 

arch/arm/mach-s3c2410/dma.c

@@ -112,7 +112,7 @@ dmadbg_capture(s3c2410_dma_chan_t *chan, struct s3c2410_dma_regstate *regs)
 }
 
 static void
-dmadbg_showregs(const char *fname, int line, s3c2410_dma_chan_t *chan,
+dmadbg_dumpregs(const char *fname, int line, s3c2410_dma_chan_t *chan,
 		 struct s3c2410_dma_regstate *regs)
 {
 	printk(KERN_DEBUG "dma%d: %s:%d: DCSRC=%08lx, DISRC=%08lx, DSTAT=%08lx DMT=%02lx, DCON=%08lx\n",
@@ -132,7 +132,16 @@ dmadbg_showchan(const char *fname, int line, s3c2410_dma_chan_t *chan)
 	       chan->number, fname, line, chan->load_state,
 	       chan->curr, chan->next, chan->end);
 
-	dmadbg_showregs(fname, line, chan, &state);
+	dmadbg_dumpregs(fname, line, chan, &state);
+}
+
+static void
+dmadbg_showregs(const char *fname, int line, s3c2410_dma_chan_t *chan)
+{
+	struct s3c2410_dma_regstate state;
+
+	dmadbg_capture(chan, &state);
+	dmadbg_dumpregs(fname, line, chan, &state);
 }
 
 #define dbg_showregs(chan) dmadbg_showregs(__FUNCTION__, __LINE__, (chan))
@@ -253,10 +262,14 @@ s3c2410_dma_loadbuffer(s3c2410_dma_chan_t *chan,
 			 buf->next);
 		reload = (buf->next == NULL) ? S3C2410_DCON_NORELOAD : 0;
 	} else {
-		pr_debug("load_state is %d => autoreload\n", chan->load_state);
+		//pr_debug("load_state is %d => autoreload\n", chan->load_state);
 		reload = S3C2410_DCON_AUTORELOAD;
 	}
 
+	if ((buf->data & 0xf0000000) != 0x30000000) {
+		dmawarn("dmaload: buffer is %p\n", (void *)buf->data);
+	}
+
 	writel(buf->data, chan->addr_reg);
 
 	dma_wrreg(chan, S3C2410_DMA_DCON,
@@ -370,7 +383,7 @@ static int s3c2410_dma_start(s3c2410_dma_chan_t *chan)
 	tmp |= S3C2410_DMASKTRIG_ON;
 	dma_wrreg(chan, S3C2410_DMA_DMASKTRIG, tmp);
 
-	pr_debug("wrote %08lx to DMASKTRIG\n", tmp);
+	pr_debug("dma%d: %08lx to DMASKTRIG\n", chan->number, tmp);
 
 #if 0
 	/* the dma buffer loads should take care of clearing the AUTO
@@ -384,7 +397,30 @@ static int s3c2410_dma_start(s3c2410_dma_chan_t *chan)
 
 	dbg_showchan(chan);
 
+	/* if we've only loaded one buffer onto the channel, then chec
+	 * to see if we have another, and if so, try and load it so when
+	 * the first buffer is finished, the new one will be loaded onto
+	 * the channel */
+
+	if (chan->next != NULL) {
+		if (chan->load_state == S3C2410_DMALOAD_1LOADED) {
+
+			if (s3c2410_dma_waitforload(chan, __LINE__) == 0) {
+				pr_debug("%s: buff not yet loaded, no more todo\n",
+					 __FUNCTION__);
+			} else {
+				chan->load_state = S3C2410_DMALOAD_1RUNNING;
+				s3c2410_dma_loadbuffer(chan, chan->next);
+			}
+
+		} else if (chan->load_state == S3C2410_DMALOAD_1RUNNING) {
+			s3c2410_dma_loadbuffer(chan, chan->next);
+		}
+	}
+
+
 	local_irq_restore(flags);
+
 	return 0;
 }
 
@@ -436,12 +472,11 @@ int s3c2410_dma_enqueue(unsigned int channel, void *id,
 	buf = kmem_cache_alloc(dma_kmem, GFP_ATOMIC);
 	if (buf == NULL) {
 		pr_debug("%s: out of memory (%ld alloc)\n",
-			 __FUNCTION__, sizeof(*buf));
+			 __FUNCTION__, (long)sizeof(*buf));
 		return -ENOMEM;
 	}
 
-	pr_debug("%s: new buffer %p\n", __FUNCTION__, buf);
+	//pr_debug("%s: new buffer %p\n", __FUNCTION__, buf);
-
 	//dbg_showchan(chan);
 
 	buf->next  = NULL;
@@ -537,14 +572,20 @@ s3c2410_dma_lastxfer(s3c2410_dma_chan_t *chan)
 	case S3C2410_DMALOAD_1LOADED:
 		if (s3c2410_dma_waitforload(chan, __LINE__) == 0) {
 				/* flag error? */
-			printk(KERN_ERR "dma%d: timeout waiting for load\n",
+			printk(KERN_ERR "dma%d: timeout waiting for load (%s)\n",
-			       chan->number);
+			       chan->number, __FUNCTION__);
 			return;
 		}
 		break;
 
+	case S3C2410_DMALOAD_1LOADED_1RUNNING:
+		/* I belive in this case we do not have anything to do
+		 * until the next buffer comes along, and we turn off the
+		 * reload */
+		return;
+
 	default:
-		pr_debug("dma%d: lastxfer: unhandled load_state %d with no next",
+		pr_debug("dma%d: lastxfer: unhandled load_state %d with no next\n",
 			 chan->number, chan->load_state);
 		return;
 
@@ -629,7 +670,14 @@ s3c2410_dma_irq(int irq, void *devpw, struct pt_regs *regs)
 	} else {
 	}
 
-	if (chan->next != NULL) {
+	/* only reload if the channel is still running... our buffer done
+	 * routine may have altered the state by requesting the dma channel
+	 * to stop or shutdown... */
+
+	/* todo: check that when the channel is shut-down from inside this
+	 * function, we cope with unsetting reload, etc */
+
+	if (chan->next != NULL && chan->state != S3C2410_DMA_IDLE) {
 		unsigned long flags;
 
 		switch (chan->load_state) {
@@ -644,8 +692,8 @@ s3c2410_dma_irq(int irq, void *devpw, struct pt_regs *regs)
 		case S3C2410_DMALOAD_1LOADED:
 			if (s3c2410_dma_waitforload(chan, __LINE__) == 0) {
 				/* flag error? */
-				printk(KERN_ERR "dma%d: timeout waiting for load\n",
+				printk(KERN_ERR "dma%d: timeout waiting for load (%s)\n",
-				       chan->number);
+				       chan->number, __FUNCTION__);
 				return IRQ_HANDLED;
 			}
 
@@ -678,8 +726,6 @@ s3c2410_dma_irq(int irq, void *devpw, struct pt_regs *regs)
 	return IRQ_HANDLED;
 }
 
-
-
 /* s3c2410_request_dma
  *
  * get control of an dma channel
@@ -718,11 +764,17 @@ int s3c2410_dma_request(unsigned int channel, s3c2410_dma_client_t *client,
 		pr_debug("dma%d: %s : requesting irq %d\n",
 			 channel, __FUNCTION__, chan->irq);
 
+		chan->irq_claimed = 1;
+		local_irq_restore(flags);
+
 		err = request_irq(chan->irq, s3c2410_dma_irq, IRQF_DISABLED,
 				  client->name, (void *)chan);
 
+		local_irq_save(flags);
+
 		if (err) {
 			chan->in_use = 0;
+			chan->irq_claimed = 0;
 			local_irq_restore(flags);
 
 			printk(KERN_ERR "%s: cannot get IRQ %d for DMA %d\n",
@@ -730,7 +782,6 @@ int s3c2410_dma_request(unsigned int channel, s3c2410_dma_client_t *client,
 			return err;
 		}
 
-		chan->irq_claimed = 1;
 		chan->irq_enabled = 1;
 	}
 
@@ -810,6 +861,7 @@ static int s3c2410_dma_dostop(s3c2410_dma_chan_t *chan)
 
 	tmp = dma_rdreg(chan, S3C2410_DMA_DMASKTRIG);
 	tmp |= S3C2410_DMASKTRIG_STOP;
+	//tmp &= ~S3C2410_DMASKTRIG_ON;
 	dma_wrreg(chan, S3C2410_DMA_DMASKTRIG, tmp);
 
 #if 0
@@ -819,6 +871,7 @@ static int s3c2410_dma_dostop(s3c2410_dma_chan_t *chan)
 	dma_wrreg(chan, S3C2410_DMA_DCON, tmp);
 #endif
 
+	/* should stop do this, or should we wait for flush? */
 	chan->state      = S3C2410_DMA_IDLE;
 	chan->load_state = S3C2410_DMALOAD_NONE;
 
@@ -827,6 +880,22 @@ static int s3c2410_dma_dostop(s3c2410_dma_chan_t *chan)
 	return 0;
 }
 
+void s3c2410_dma_waitforstop(s3c2410_dma_chan_t *chan)
+{
+	unsigned long tmp;
+	unsigned int timeout = 0x10000;
+
+	while (timeout-- > 0) {
+		tmp = dma_rdreg(chan, S3C2410_DMA_DMASKTRIG);
+
+		if (!(tmp & S3C2410_DMASKTRIG_ON))
+			return;
+	}
+
+	pr_debug("dma%d: failed to stop?\n", chan->number);
+}
+
+
 /* s3c2410_dma_flush
  *
  * stop the channel, and remove all current and pending transfers
@@ -837,7 +906,9 @@ static int s3c2410_dma_flush(s3c2410_dma_chan_t *chan)
 	s3c2410_dma_buf_t *buf, *next;
 	unsigned long flags;
 
-	pr_debug("%s:\n", __FUNCTION__);
+	pr_debug("%s: chan %p (%d)\n", __FUNCTION__, chan, chan->number);
+
+	dbg_showchan(chan);
 
 	local_irq_save(flags);
 
@@ -864,11 +935,64 @@ static int s3c2410_dma_flush(s3c2410_dma_chan_t *chan)
 		}
 	}
 
+	dbg_showregs(chan);
+
+	s3c2410_dma_waitforstop(chan);
+
+#if 0
+	/* should also clear interrupts, according to WinCE BSP */
+	{
+		unsigned long tmp;
+
+		tmp = dma_rdreg(chan, S3C2410_DMA_DCON);
+		tmp |= S3C2410_DCON_NORELOAD;
+		dma_wrreg(chan, S3C2410_DMA_DCON, tmp);
+	}
+#endif
+
+	dbg_showregs(chan);
+
 	local_irq_restore(flags);
 
 	return 0;
 }
 
+int
+s3c2410_dma_started(s3c2410_dma_chan_t *chan)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+
+	dbg_showchan(chan);
+
+	/* if we've only loaded one buffer onto the channel, then chec
+	 * to see if we have another, and if so, try and load it so when
+	 * the first buffer is finished, the new one will be loaded onto
+	 * the channel */
+
+	if (chan->next != NULL) {
+		if (chan->load_state == S3C2410_DMALOAD_1LOADED) {
+
+			if (s3c2410_dma_waitforload(chan, __LINE__) == 0) {
+				pr_debug("%s: buff not yet loaded, no more todo\n",
+					 __FUNCTION__);
+			} else {
+				chan->load_state = S3C2410_DMALOAD_1RUNNING;
+				s3c2410_dma_loadbuffer(chan, chan->next);
+			}
+
+		} else if (chan->load_state == S3C2410_DMALOAD_1RUNNING) {
+			s3c2410_dma_loadbuffer(chan, chan->next);
+		}
+	}
+
+
+	local_irq_restore(flags);
+
+	return 0;
+
+}
 
 int
 s3c2410_dma_ctrl(dmach_t channel, s3c2410_chan_op_t op)
@@ -885,14 +1009,15 @@ s3c2410_dma_ctrl(dmach_t channel, s3c2410_chan_op_t op)
 		return s3c2410_dma_dostop(chan);
 
 	case S3C2410_DMAOP_PAUSE:
-		return -ENOENT;
-
 	case S3C2410_DMAOP_RESUME:
 		return -ENOENT;
 
 	case S3C2410_DMAOP_FLUSH:
 		return s3c2410_dma_flush(chan);
 
+	case S3C2410_DMAOP_STARTED:
+		return s3c2410_dma_started(chan);
+
 	case S3C2410_DMAOP_TIMEOUT:
 		return 0;
 

arch/arm/mach-s3c2410/mach-anubis.c

@@ -60,11 +60,12 @@ static struct map_desc anubis_iodesc[] __initdata = {
 	.virtual	= (u32)S3C24XX_VA_ISA_BYTE,
 	.pfn		= __phys_to_pfn(0x0),
 	.length		= SZ_4M,
-	.type		= MT_DEVICE
+	.type		= MT_DEVICE,
   }, {
 	.virtual	= (u32)S3C24XX_VA_ISA_WORD,
 	.pfn		= __phys_to_pfn(0x0),
-	.length 	= SZ_4M, MT_DEVICE
+	.length 	= SZ_4M,
+	.type		= MT_DEVICE,
   },
 
   /* we could possibly compress the next set down into a set of smaller tables
@@ -78,36 +79,12 @@ static struct map_desc anubis_iodesc[] __initdata = {
 	.virtual	= (u32)ANUBIS_VA_CTRL1,
 	.pfn		= __phys_to_pfn(ANUBIS_PA_CTRL1),
 	.length		= SZ_4K,
-	.type		= MT_DEVICE
+	.type		= MT_DEVICE,
   }, {
 	.virtual	= (u32)ANUBIS_VA_CTRL2,
 	.pfn		= __phys_to_pfn(ANUBIS_PA_CTRL2),
 	.length		= SZ_4K,
-	.type		=MT_DEVICE
+	.type		= MT_DEVICE,
-  },
-
-  /* IDE drives */
-
-  {
-	.virtual	= (u32)ANUBIS_IDEPRI,
-	.pfn		= __phys_to_pfn(S3C2410_CS3),
-	.length		= SZ_1M,
-	.type		= MT_DEVICE
-  }, {
-	.virtual	= (u32)ANUBIS_IDEPRIAUX,
-	.pfn		= __phys_to_pfn(S3C2410_CS3+(1<<26)),
-	.length		= SZ_1M,
-	.type		= MT_DEVICE
-  }, {
-	.virtual	= (u32)ANUBIS_IDESEC,
-	.pfn		= __phys_to_pfn(S3C2410_CS4),
-	.length		= SZ_1M,
-	.type		= MT_DEVICE
-  }, {
-	.virtual	= (u32)ANUBIS_IDESECAUX,
-	.pfn		= __phys_to_pfn(S3C2410_CS4+(1<<26)),
-	.length		= SZ_1M,
-	.type		= MT_DEVICE
   },
 };
 
@@ -126,7 +103,7 @@ static struct s3c24xx_uart_clksrc anubis_serial_clocks[] = {
 		.name		= "pclk",
 		.divisor	= 1,
 		.min_baud	= 0,
-		.max_baud	= 0.
+		.max_baud	= 0,
 	}
 };
 
@@ -139,7 +116,7 @@ static struct s3c2410_uartcfg anubis_uartcfgs[] __initdata = {
 		.ulcon	     = ULCON,
 		.ufcon	     = UFCON,
 		.clocks	     = anubis_serial_clocks,
-		.clocks_size = ARRAY_SIZE(anubis_serial_clocks)
+		.clocks_size = ARRAY_SIZE(anubis_serial_clocks),
 	},
 	[1] = {
 		.hwport	     = 2,
@@ -148,7 +125,7 @@ static struct s3c2410_uartcfg anubis_uartcfgs[] __initdata = {
 		.ulcon	     = ULCON,
 		.ufcon	     = UFCON,
 		.clocks	     = anubis_serial_clocks,
-		.clocks_size = ARRAY_SIZE(anubis_serial_clocks)
+		.clocks_size = ARRAY_SIZE(anubis_serial_clocks),
 	},
 };
 
@@ -162,7 +139,7 @@ static struct mtd_partition anubis_default_nand_part[] = {
 	[0] = {
 		.name	= "Boot Agent",
 		.size	= SZ_16K,
-		.offset	= 0
+		.offset	= 0,
 	},
 	[1] = {
 		.name	= "/boot",
@@ -194,21 +171,21 @@ static struct s3c2410_nand_set anubis_nand_sets[] = {
 		.nr_chips	= 1,
 		.nr_map		= external_map,
 		.nr_partitions	= ARRAY_SIZE(anubis_default_nand_part),
-		.partitions	= anubis_default_nand_part
+		.partitions	= anubis_default_nand_part,
 	},
 	[0] = {
 		.name		= "chip0",
 		.nr_chips	= 1,
 		.nr_map		= chip0_map,
 		.nr_partitions	= ARRAY_SIZE(anubis_default_nand_part),
-		.partitions	= anubis_default_nand_part
+		.partitions	= anubis_default_nand_part,
 	},
 	[2] = {
 		.name		= "chip1",
 		.nr_chips	= 1,
 		.nr_map		= chip1_map,
 		.nr_partitions	= ARRAY_SIZE(anubis_default_nand_part),
-		.partitions	= anubis_default_nand_part
+		.partitions	= anubis_default_nand_part,
 	},
 };
 
@@ -313,7 +290,7 @@ static struct s3c24xx_board anubis_board __initdata = {
 	.devices       = anubis_devices,
 	.devices_count = ARRAY_SIZE(anubis_devices),
 	.clocks	       = anubis_clocks,
-	.clocks_count  = ARRAY_SIZE(anubis_clocks)
+	.clocks_count  = ARRAY_SIZE(anubis_clocks),
 };
 
 static void __init anubis_map_io(void)

arch/arm/mach-s3c2410/mach-osiris.c

@@ -67,12 +67,12 @@ static struct map_desc osiris_iodesc[] __initdata = {
 	  .virtual	= (u32)OSIRIS_VA_CTRL1,
 	  .pfn		= __phys_to_pfn(OSIRIS_PA_CTRL1),
 	  .length	= SZ_16K,
-	  .type		= MT_DEVICE
+	  .type		= MT_DEVICE,
   }, {
 	  .virtual	= (u32)OSIRIS_VA_CTRL2,
 	  .pfn		= __phys_to_pfn(OSIRIS_PA_CTRL2),
 	  .length	= SZ_16K,
-	  .type		= MT_DEVICE
+	  .type		= MT_DEVICE,
   },
 };
 
@@ -91,7 +91,7 @@ static struct s3c24xx_uart_clksrc osiris_serial_clocks[] = {
 		.name		= "pclk",
 		.divisor	= 1,
 		.min_baud	= 0,
-		.max_baud	= 0.
+		.max_baud	= 0,
 	}
 };
 
@@ -103,7 +103,7 @@ static struct s3c2410_uartcfg osiris_uartcfgs[] __initdata = {
 		.ulcon	     = ULCON,
 		.ufcon	     = UFCON,
 		.clocks	     = osiris_serial_clocks,
-		.clocks_size = ARRAY_SIZE(osiris_serial_clocks)
+		.clocks_size = ARRAY_SIZE(osiris_serial_clocks),
 	},
 	[1] = {
 		.hwport	     = 1,
@@ -112,7 +112,7 @@ static struct s3c2410_uartcfg osiris_uartcfgs[] __initdata = {
 		.ulcon	     = ULCON,
 		.ufcon	     = UFCON,
 		.clocks	     = osiris_serial_clocks,
-		.clocks_size = ARRAY_SIZE(osiris_serial_clocks)
+		.clocks_size = ARRAY_SIZE(osiris_serial_clocks),
 	},
 };
 
@@ -126,7 +126,7 @@ static struct mtd_partition osiris_default_nand_part[] = {
 	[0] = {
 		.name	= "Boot Agent",
 		.size	= SZ_16K,
-		.offset	= 0
+		.offset	= 0,
 	},
 	[1] = {
 		.name	= "/boot",
@@ -158,21 +158,21 @@ static struct s3c2410_nand_set osiris_nand_sets[] = {
 		.nr_chips	= 1,
 		.nr_map		= external_map,
 		.nr_partitions	= ARRAY_SIZE(osiris_default_nand_part),
-		.partitions	= osiris_default_nand_part
+		.partitions	= osiris_default_nand_part,
 	},
 	[0] = {
 		.name		= "chip0",
 		.nr_chips	= 1,
 		.nr_map		= chip0_map,
 		.nr_partitions	= ARRAY_SIZE(osiris_default_nand_part),
-		.partitions	= osiris_default_nand_part
+		.partitions	= osiris_default_nand_part,
 	},
 	[2] = {
 		.name		= "chip1",
 		.nr_chips	= 1,
 		.nr_map		= chip1_map,
 		.nr_partitions	= ARRAY_SIZE(osiris_default_nand_part),
-		.partitions	= osiris_default_nand_part
+		.partitions	= osiris_default_nand_part,
 	},
 };
 
@@ -245,7 +245,7 @@ static struct s3c24xx_board osiris_board __initdata = {
 	.devices       = osiris_devices,
 	.devices_count = ARRAY_SIZE(osiris_devices),
 	.clocks	       = osiris_clocks,
-	.clocks_count  = ARRAY_SIZE(osiris_clocks)
+	.clocks_count  = ARRAY_SIZE(osiris_clocks),
 };
 
 static void __init osiris_map_io(void)

arch/arm/mach-sa1100/irq.c

@@ -95,7 +95,8 @@ static int sa1100_low_gpio_wake(unsigned int irq, unsigned int on)
 	return 0;
 }
 
-static struct irqchip sa1100_low_gpio_chip = {
+static struct irq_chip sa1100_low_gpio_chip = {
+	.name		= "GPIO-l",
 	.ack		= sa1100_low_gpio_ack,
 	.mask		= sa1100_low_gpio_mask,
 	.unmask		= sa1100_low_gpio_unmask,
@@ -178,7 +179,8 @@ static int sa1100_high_gpio_wake(unsigned int irq, unsigned int on)
 	return 0;
 }
 
-static struct irqchip sa1100_high_gpio_chip = {
+static struct irq_chip sa1100_high_gpio_chip = {
+	.name		= "GPIO-h",
 	.ack		= sa1100_high_gpio_ack,
 	.mask		= sa1100_high_gpio_mask,
 	.unmask		= sa1100_high_gpio_unmask,
@@ -215,7 +217,8 @@ static int sa1100_set_wake(unsigned int irq, unsigned int on)
 	return -EINVAL;
 }
 
-static struct irqchip sa1100_normal_chip = {
+static struct irq_chip sa1100_normal_chip = {
+	.name		= "SC",
 	.ack		= sa1100_mask_irq,
 	.mask		= sa1100_mask_irq,
 	.unmask		= sa1100_unmask_irq,

arch/arm/mach-shark/irq.c

@@ -69,7 +69,8 @@ static irqreturn_t bogus_int(int irq, void *dev_id, struct pt_regs *regs)
 
 static struct irqaction cascade;
 
-static struct irqchip fb_chip = {
+static struct irq_chip fb_chip = {
+	.name	= "XT-PIC",
 	.ack	= shark_ack_8259A_irq,
 	.mask	= shark_disable_8259A_irq,
 	.unmask = shark_enable_8259A_irq,

arch/arm/mach-versatile/core.c

@@ -69,7 +69,8 @@ static void sic_unmask_irq(unsigned int irq)
 	writel(1 << irq, VA_SIC_BASE + SIC_IRQ_ENABLE_SET);
 }
 
-static struct irqchip sic_chip = {
+static struct irq_chip sic_chip = {
+	.name	= "SIC",
 	.ack	= sic_mask_irq,
 	.mask	= sic_mask_irq,
 	.unmask	= sic_unmask_irq,
@@ -284,7 +285,7 @@ static struct flash_platform_data versatile_flash_data = {
 
 static struct resource versatile_flash_resource = {
 	.start			= VERSATILE_FLASH_BASE,
-	.end			= VERSATILE_FLASH_BASE + VERSATILE_FLASH_SIZE,
+	.end			= VERSATILE_FLASH_BASE + VERSATILE_FLASH_SIZE - 1,
 	.flags			= IORESOURCE_MEM,
 };
 

arch/arm/mm/ioremap.c

@@ -363,7 +363,9 @@ EXPORT_SYMBOL(__ioremap);
 
 void __iounmap(void __iomem *addr)
 {
+#ifndef CONFIG_SMP
 	struct vm_struct **p, *tmp;
+#endif
 	unsigned int section_mapping = 0;
 
 	addr = (void __iomem *)(PAGE_MASK & (unsigned long)addr);

arch/arm/mm/proc-syms.c

@@ -13,6 +13,7 @@
 #include <asm/cacheflush.h>
 #include <asm/proc-fns.h>
 #include <asm/tlbflush.h>
+#include <asm/page.h>
 
 #ifndef MULTI_CPU
 EXPORT_SYMBOL(cpu_dcache_clean_area);
@@ -30,6 +31,13 @@ EXPORT_SYMBOL(__cpuc_coherent_kern_range);
 EXPORT_SYMBOL(cpu_cache);
 #endif
 
+#ifndef MULTI_USER
+EXPORT_SYMBOL(__cpu_clear_user_page);
+EXPORT_SYMBOL(__cpu_copy_user_page);
+#else
+EXPORT_SYMBOL(cpu_user);
+#endif
+
 /*
  * No module should need to touch the TLB (and currently
  * no modules do.  We export this for "loadkernel" support

arch/arm/mm/proc-xscale.S

@@ -536,6 +536,11 @@ cpu_80200_name:
 	.asciz	"XScale-80200"
 	.size	cpu_80200_name, . - cpu_80200_name
 
+	.type	cpu_80219_name, #object
+cpu_80219_name:
+	.asciz	"XScale-80219"
+	.size	cpu_80219_name, . - cpu_80219_name
+
 	.type	cpu_8032x_name, #object
 cpu_8032x_name:
 	.asciz	"XScale-IOP8032x Family"
@@ -613,10 +618,33 @@ __80200_proc_info:
 	.long	xscale_cache_fns
 	.size	__80200_proc_info, . - __80200_proc_info
 
+	.type	__80219_proc_info,#object
+__80219_proc_info:
+	.long	0x69052e20
+	.long	0xffffffe0
+	.long   PMD_TYPE_SECT | \
+		PMD_SECT_BUFFERABLE | \
+		PMD_SECT_CACHEABLE | \
+		PMD_SECT_AP_WRITE | \
+		PMD_SECT_AP_READ
+	.long   PMD_TYPE_SECT | \
+		PMD_SECT_AP_WRITE | \
+		PMD_SECT_AP_READ
+	b	__xscale_setup
+	.long	cpu_arch_name
+	.long	cpu_elf_name
+	.long	HWCAP_SWP|HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT|HWCAP_EDSP
+	.long	cpu_80219_name
+	.long	xscale_processor_functions
+	.long	v4wbi_tlb_fns
+	.long	xscale_mc_user_fns
+	.long	xscale_cache_fns
+	.size	__80219_proc_info, . - __80219_proc_info
+
 	.type	__8032x_proc_info,#object
 __8032x_proc_info:
 	.long	0x69052420
-	.long	0xfffff5e0      @ mask should accomodate IOP80219 also
+	.long	0xffffffe0
 	.long   PMD_TYPE_SECT | \
 		PMD_SECT_BUFFERABLE | \
 		PMD_SECT_CACHEABLE | \

arch/arm/plat-omap/gpio.c

@@ -944,7 +944,8 @@ static void mpuio_unmask_irq(unsigned int irq)
 	_set_gpio_irqenable(bank, gpio, 1);
 }
 
-static struct irqchip gpio_irq_chip = {
+static struct irq_chip gpio_irq_chip = {
+	.name		= "GPIO",
 	.ack		= gpio_ack_irq,
 	.mask		= gpio_mask_irq,
 	.unmask		= gpio_unmask_irq,
@@ -952,10 +953,11 @@ static struct irqchip gpio_irq_chip = {
 	.set_wake	= gpio_wake_enable,
 };
 
-static struct irqchip mpuio_irq_chip = {
+static struct irq_chip mpuio_irq_chip = {
+	.name	= "MPUIO",
 	.ack	= mpuio_ack_irq,
 	.mask	= mpuio_mask_irq,
-	.unmask = mpuio_unmask_irq
+	.unmask	= mpuio_unmask_irq
 };
 
 static int initialized;

arch/i386/Kconfig

@@ -142,6 +142,7 @@ config X86_SUMMIT
 	  In particular, it is needed for the x440.
 
 	  If you don't have one of these computers, you should say N here.
+	  If you want to build a NUMA kernel, you must select ACPI.
 
 config X86_BIGSMP
 	bool "Support for other sub-arch SMP systems with more than 8 CPUs"
@@ -169,6 +170,7 @@ config X86_GENERICARCH
        help
           This option compiles in the Summit, bigsmp, ES7000, default subarchitectures.
 	  It is intended for a generic binary kernel.
+	  If you want a NUMA kernel, select ACPI.   We need SRAT for NUMA.
 
 config X86_ES7000
 	bool "Support for Unisys ES7000 IA32 series"
@@ -542,7 +544,7 @@ config X86_PAE
 # Common NUMA Features
 config NUMA
 	bool "Numa Memory Allocation and Scheduler Support"
-	depends on SMP && HIGHMEM64G && (X86_NUMAQ || X86_GENERICARCH || (X86_SUMMIT && ACPI))
+	depends on SMP && HIGHMEM64G && (X86_NUMAQ || (X86_SUMMIT || X86_GENERICARCH) && ACPI)
 	default n if X86_PC
 	default y if (X86_NUMAQ || X86_SUMMIT)
 
@@ -672,7 +674,7 @@ config MTRR
 	  See <file:Documentation/mtrr.txt> for more information.
 
 config EFI
-	bool "Boot from EFI support (EXPERIMENTAL)"
+	bool "Boot from EFI support"
 	depends on ACPI
 	default n
 	---help---

arch/i386/kernel/Makefile

@@ -59,7 +59,8 @@ quiet_cmd_syscall = SYSCALL $@
 
 export CPPFLAGS_vsyscall.lds += -P -C -U$(ARCH)
 
-vsyscall-flags = -shared -s -Wl,-soname=linux-gate.so.1
+vsyscall-flags = -shared -s -Wl,-soname=linux-gate.so.1 \
+		 $(call ld-option, -Wl$(comma)--hash-style=sysv)
 SYSCFLAGS_vsyscall-sysenter.so	= $(vsyscall-flags)
 SYSCFLAGS_vsyscall-int80.so	= $(vsyscall-flags)
 

arch/i386/kernel/acpi/boot.c

@@ -59,7 +59,7 @@ static inline int gsi_irq_sharing(int gsi) { return gsi; }
 
 #define BAD_MADT_ENTRY(entry, end) (					    \
 		(!entry) || (unsigned long)entry + sizeof(*entry) > end ||  \
-		((acpi_table_entry_header *)entry)->length != sizeof(*entry))
+		((acpi_table_entry_header *)entry)->length < sizeof(*entry))
 
 #define PREFIX			"ACPI: "
 

arch/i386/kernel/acpi/wakeup.S

@@ -292,7 +292,10 @@ ENTRY(do_suspend_lowlevel)
 	pushl	$3
 	call	acpi_enter_sleep_state
 	addl	$4, %esp
-	ret
+
+#	In case of S3 failure, we'll emerge here.  Jump
+# 	to ret_point to recover
+	jmp	ret_point
 	.p2align 4,,7
 ret_point:
 	call	restore_registers

arch/i386/kernel/cpu/cpufreq/Kconfig

@@ -96,6 +96,7 @@ config X86_POWERNOW_K8_ACPI
 
 config X86_GX_SUSPMOD
 	tristate "Cyrix MediaGX/NatSemi Geode Suspend Modulation"
+	depends on PCI
 	help
 	 This add the CPUFreq driver for NatSemi Geode processors which
 	 support suspend modulation.
@@ -202,7 +203,7 @@ config X86_LONGRUN
 config X86_LONGHAUL
 	tristate "VIA Cyrix III Longhaul"
 	select CPU_FREQ_TABLE
-	depends on BROKEN
+	depends on ACPI_PROCESSOR
 	help
 	  This adds the CPUFreq driver for VIA Samuel/CyrixIII,
 	  VIA Cyrix Samuel/C3, VIA Cyrix Ezra and VIA Cyrix Ezra-T

arch/i386/kernel/cpu/cpufreq/acpi-cpufreq.c

@@ -384,8 +384,7 @@ static int acpi_cpufreq_early_init_acpi(void)
 	}
 
 	/* Do initialization in ACPI core */
-	acpi_processor_preregister_performance(acpi_perf_data);
+	return acpi_processor_preregister_performance(acpi_perf_data);
-	return 0;
 }
 
 static int
@@ -568,16 +567,11 @@ static struct cpufreq_driver acpi_cpufreq_driver = {
 static int __init
 acpi_cpufreq_init (void)
 {
-	int                     result = 0;
-
 	dprintk("acpi_cpufreq_init\n");
 
-	result = acpi_cpufreq_early_init_acpi();
+	acpi_cpufreq_early_init_acpi();
 
-	if (!result)
+ 	return cpufreq_register_driver(&acpi_cpufreq_driver);
- 		result = cpufreq_register_driver(&acpi_cpufreq_driver);
-	
-	return (result);
 }
 
 

arch/i386/kernel/cpu/cpufreq/longhaul.c

@@ -29,11 +29,13 @@
 #include <linux/cpufreq.h>
 #include <linux/slab.h>
 #include <linux/string.h>
-#include <linux/pci.h>
 
 #include <asm/msr.h>
 #include <asm/timex.h>
 #include <asm/io.h>
+#include <asm/acpi.h>
+#include <linux/acpi.h>
+#include <acpi/processor.h>
 
 #include "longhaul.h"
 
@@ -56,6 +58,8 @@ static int minvid, maxvid;
 static unsigned int minmult, maxmult;
 static int can_scale_voltage;
 static int vrmrev;
+static struct acpi_processor *pr = NULL;
+static struct acpi_processor_cx *cx = NULL;
 
 /* Module parameters */
 static int dont_scale_voltage;
@@ -118,84 +122,65 @@ static int longhaul_get_cpu_mult(void)
 	return eblcr_table[invalue];
 }
 
+/* For processor with BCR2 MSR */
 
-static void do_powersaver(union msr_longhaul *longhaul,
+static void do_longhaul1(int cx_address, unsigned int clock_ratio_index)
-			unsigned int clock_ratio_index)
 {
-	struct pci_dev *dev;
+	union msr_bcr2 bcr2;
-	unsigned long flags;
+	u32 t;
-	unsigned int tmp_mask;
-	int version;
-	int i;
-	u16 pci_cmd;
-	u16 cmd_state[64];
 
-	switch (cpu_model) {
+	rdmsrl(MSR_VIA_BCR2, bcr2.val);
-	case CPU_EZRA_T:
+	/* Enable software clock multiplier */
-		version = 3;
+	bcr2.bits.ESOFTBF = 1;
-		break;
+	bcr2.bits.CLOCKMUL = clock_ratio_index;
-	case CPU_NEHEMIAH:
-		version = 0xf;
-		break;
-	default:
-		return;
-	}
-
-	rdmsrl(MSR_VIA_LONGHAUL, longhaul->val);
-	longhaul->bits.SoftBusRatio = clock_ratio_index & 0xf;
-	longhaul->bits.SoftBusRatio4 = (clock_ratio_index & 0x10) >> 4;
-	longhaul->bits.EnableSoftBusRatio = 1;
-	longhaul->bits.RevisionKey = 0;
-
-	preempt_disable();
-	local_irq_save(flags);
-
-	/*
-	 * get current pci bus master state for all devices
-	 * and clear bus master bit
-	 */
-	dev = NULL;
-	i = 0;
-	do {
-		dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev);
-		if (dev != NULL) {
-			pci_read_config_word(dev, PCI_COMMAND, &pci_cmd);
-			cmd_state[i++] = pci_cmd;
-			pci_cmd &= ~PCI_COMMAND_MASTER;
-			pci_write_config_word(dev, PCI_COMMAND, pci_cmd);
-		}
-	} while (dev != NULL);
-
-	tmp_mask=inb(0x21);	/* works on C3. save mask. */
-	outb(0xFE,0x21);	/* TMR0 only */
-	outb(0xFF,0x80);	/* delay */
 
+	/* Sync to timer tick */
 	safe_halt();
-	wrmsrl(MSR_VIA_LONGHAUL, longhaul->val);
+	ACPI_FLUSH_CPU_CACHE();
-	halt();
+	/* Change frequency on next halt or sleep */
+	wrmsrl(MSR_VIA_BCR2, bcr2.val);
+	/* Invoke C3 */
+	inb(cx_address);
+	/* Dummy op - must do something useless after P_LVL3 read */
+	t = inl(acpi_fadt.xpm_tmr_blk.address);
 
+	/* Disable software clock multiplier */
 	local_irq_disable();
+	rdmsrl(MSR_VIA_BCR2, bcr2.val);
+	bcr2.bits.ESOFTBF = 0;
+	wrmsrl(MSR_VIA_BCR2, bcr2.val);
+}
 
-	outb(tmp_mask,0x21);	/* restore mask */
+/* For processor with Longhaul MSR */
 
-	/* restore pci bus master state for all devices */
+static void do_powersaver(int cx_address, unsigned int clock_ratio_index)
-	dev = NULL;
+{
-	i = 0;
+	union msr_longhaul longhaul;
-	do {
+	u32 t;
-		dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev);
-		if (dev != NULL) {
-			pci_cmd = cmd_state[i++];
-			pci_write_config_byte(dev, PCI_COMMAND, pci_cmd);
-		}
-	} while (dev != NULL);
-	local_irq_restore(flags);
-	preempt_enable();
 
-	/* disable bus ratio bit */
+	rdmsrl(MSR_VIA_LONGHAUL, longhaul.val);
-	rdmsrl(MSR_VIA_LONGHAUL, longhaul->val);
+	longhaul.bits.RevisionKey = longhaul.bits.RevisionID;
-	longhaul->bits.EnableSoftBusRatio = 0;
+	longhaul.bits.SoftBusRatio = clock_ratio_index & 0xf;
-	longhaul->bits.RevisionKey = version;
+	longhaul.bits.SoftBusRatio4 = (clock_ratio_index & 0x10) >> 4;
-	wrmsrl(MSR_VIA_LONGHAUL, longhaul->val);
+	longhaul.bits.EnableSoftBusRatio = 1;
+
+	/* Sync to timer tick */
+	safe_halt();
+	ACPI_FLUSH_CPU_CACHE();
+	/* Change frequency on next halt or sleep */
+	wrmsrl(MSR_VIA_LONGHAUL, longhaul.val);
+	/* Invoke C3 */
+	inb(cx_address);
+	/* Dummy op - must do something useless after P_LVL3 read */
+	t = inl(acpi_fadt.xpm_tmr_blk.address);
+
+	/* Disable bus ratio bit */
+	local_irq_disable();
+	longhaul.bits.RevisionKey = longhaul.bits.RevisionID;
+	longhaul.bits.EnableSoftBusRatio = 0;
+	longhaul.bits.EnableSoftBSEL = 0;
+	longhaul.bits.EnableSoftVID = 0;
+	wrmsrl(MSR_VIA_LONGHAUL, longhaul.val);
 }
 
 /**
@@ -209,9 +194,9 @@ static void longhaul_setstate(unsigned int clock_ratio_index)
 {
 	int speed, mult;
 	struct cpufreq_freqs freqs;
-	union msr_longhaul longhaul;
-	union msr_bcr2 bcr2;
 	static unsigned int old_ratio=-1;
+	unsigned long flags;
+	unsigned int pic1_mask, pic2_mask;
 
 	if (old_ratio == clock_ratio_index)
 		return;
@@ -234,6 +219,20 @@ static void longhaul_setstate(unsigned int clock_ratio_index)
 	dprintk ("Setting to FSB:%dMHz Mult:%d.%dx (%s)\n",
 			fsb, mult/10, mult%10, print_speed(speed/1000));
 
+	preempt_disable();
+	local_irq_save(flags);
+
+	pic2_mask = inb(0xA1);
+	pic1_mask = inb(0x21);	/* works on C3. save mask. */
+	outb(0xFF,0xA1);	/* Overkill */
+	outb(0xFE,0x21);	/* TMR0 only */
+
+	/* Disable bus master arbitration */
+	if (pr->flags.bm_check) {
+		acpi_set_register(ACPI_BITREG_ARB_DISABLE, 1,
+				  ACPI_MTX_DO_NOT_LOCK);
+	}
+
 	switch (longhaul_version) {
 
 	/*
@@ -245,20 +244,7 @@ static void longhaul_setstate(unsigned int clock_ratio_index)
 	 */
 	case TYPE_LONGHAUL_V1:
 	case TYPE_LONGHAUL_V2:
-		rdmsrl (MSR_VIA_BCR2, bcr2.val);
+		do_longhaul1(cx->address, clock_ratio_index);
-		/* Enable software clock multiplier */
-		bcr2.bits.ESOFTBF = 1;
-		bcr2.bits.CLOCKMUL = clock_ratio_index;
-		local_irq_disable();
-		wrmsrl (MSR_VIA_BCR2, bcr2.val);
-		safe_halt();
-
-		/* Disable software clock multiplier */
-		rdmsrl (MSR_VIA_BCR2, bcr2.val);
-		bcr2.bits.ESOFTBF = 0;
-		local_irq_disable();
-		wrmsrl (MSR_VIA_BCR2, bcr2.val);
-		local_irq_enable();
 		break;
 
 	/*
@@ -273,10 +259,22 @@ static void longhaul_setstate(unsigned int clock_ratio_index)
 	 * to work in practice.
 	 */
 	case TYPE_POWERSAVER:
-		do_powersaver(&longhaul, clock_ratio_index);
+		do_powersaver(cx->address, clock_ratio_index);
 		break;
 	}
 
+	/* Enable bus master arbitration */
+	if (pr->flags.bm_check) {
+		acpi_set_register(ACPI_BITREG_ARB_DISABLE, 0,
+				  ACPI_MTX_DO_NOT_LOCK);
+	}
+
+	outb(pic2_mask,0xA1);	/* restore mask */
+	outb(pic1_mask,0x21);
+
+	local_irq_restore(flags);
+	preempt_enable();
+
 	cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
 }
 
@@ -324,9 +322,11 @@ static int guess_fsb(void)
 static int __init longhaul_get_ranges(void)
 {
 	unsigned long invalue;
-	unsigned int multipliers[32]= {
+	unsigned int ezra_t_multipliers[32]= {
-		50,30,40,100,55,35,45,95,90,70,80,60,120,75,85,65,
+			90,  30,  40, 100,  55,  35,  45,  95,
-		-1,110,120,-1,135,115,125,105,130,150,160,140,-1,155,-1,145 };
+			50,  70,  80,  60, 120,  75,  85,  65,
+			-1, 110, 120,  -1, 135, 115, 125, 105,
+			130, 150, 160, 140,  -1, 155,  -1, 145 };
 	unsigned int j, k = 0;
 	union msr_longhaul longhaul;
 	unsigned long lo, hi;
@@ -355,13 +355,13 @@ static int __init longhaul_get_ranges(void)
 			invalue = longhaul.bits.MaxMHzBR;
 			if (longhaul.bits.MaxMHzBR4)
 				invalue += 16;
-			maxmult=multipliers[invalue];
+			maxmult=ezra_t_multipliers[invalue];
 
 			invalue = longhaul.bits.MinMHzBR;
 			if (longhaul.bits.MinMHzBR4 == 1)
 				minmult = 30;
 			else
-				minmult = multipliers[invalue];
+				minmult = ezra_t_multipliers[invalue];
 			fsb = eblcr_fsb_table_v2[longhaul.bits.MaxMHzFSB];
 			break;
 		}
@@ -527,6 +527,18 @@ static unsigned int longhaul_get(unsigned int cpu)
 	return calc_speed(longhaul_get_cpu_mult());
 }
 
+static acpi_status longhaul_walk_callback(acpi_handle obj_handle,
+					  u32 nesting_level,
+					  void *context, void **return_value)
+{
+	struct acpi_device *d;
+
+	if ( acpi_bus_get_device(obj_handle, &d) ) {
+		return 0;
+	}
+	*return_value = (void *)acpi_driver_data(d);
+	return 1;
+}
 
 static int __init longhaul_cpu_init(struct cpufreq_policy *policy)
 {
@@ -534,6 +546,15 @@ static int __init longhaul_cpu_init(struct cpufreq_policy *policy)
 	char *cpuname=NULL;
 	int ret;
 
+	/* Check ACPI support for C3 state */
+	acpi_walk_namespace(ACPI_TYPE_PROCESSOR, ACPI_ROOT_OBJECT, ACPI_UINT32_MAX,
+			 &longhaul_walk_callback, NULL, (void *)&pr);
+	if (pr == NULL) goto err_acpi;
+
+	cx = &pr->power.states[ACPI_STATE_C3];
+	if (cx->address == 0 || cx->latency > 1000) goto err_acpi;
+
+	/* Now check what we have on this motherboard */
 	switch (c->x86_model) {
 	case 6:
 		cpu_model = CPU_SAMUEL;
@@ -634,6 +655,10 @@ static int __init longhaul_cpu_init(struct cpufreq_policy *policy)
 	cpufreq_frequency_table_get_attr(longhaul_table, policy->cpu);
 
 	return 0;
+
+err_acpi:
+	printk(KERN_ERR PFX "No ACPI support for CPU frequency changes.\n");
+	return -ENODEV;
 }
 
 static int __devexit longhaul_cpu_exit(struct cpufreq_policy *policy)
@@ -666,6 +691,18 @@ static int __init longhaul_init(void)
 	if (c->x86_vendor != X86_VENDOR_CENTAUR || c->x86 != 6)
 		return -ENODEV;
 
+#ifdef CONFIG_SMP
+	if (num_online_cpus() > 1) {
+		return -ENODEV;
+		printk(KERN_ERR PFX "More than 1 CPU detected, longhaul disabled.\n");
+	}
+#endif
+#ifdef CONFIG_X86_IO_APIC
+	if (cpu_has_apic) {
+		printk(KERN_ERR PFX "APIC detected. Longhaul is currently broken in this configuration.\n");
+		return -ENODEV;
+	}
+#endif
 	switch (c->x86_model) {
 	case 6 ... 9:
 		return cpufreq_register_driver(&longhaul_driver);
@@ -699,6 +736,6 @@ MODULE_AUTHOR ("Dave Jones <davej@codemonkey.org.uk>");
 MODULE_DESCRIPTION ("Longhaul driver for VIA Cyrix processors.");
 MODULE_LICENSE ("GPL");
 
-module_init(longhaul_init);
+late_initcall(longhaul_init);
 module_exit(longhaul_exit);
 

arch/i386/kernel/cpu/intel_cacheinfo.c

@@ -759,7 +759,7 @@ static int __cpuinit cache_sysfs_init(void)
 	if (num_cache_leaves == 0)
 		return 0;
 
-	register_cpu_notifier(&cacheinfo_cpu_notifier);
+	register_hotcpu_notifier(&cacheinfo_cpu_notifier);
 
 	for_each_online_cpu(i) {
 		cacheinfo_cpu_callback(&cacheinfo_cpu_notifier, CPU_ONLINE,

arch/i386/kernel/cpu/mcheck/mce.h

@@ -9,6 +9,6 @@ void winchip_mcheck_init(struct cpuinfo_x86 *c);
 /* Call the installed machine check handler for this CPU setup. */
 extern fastcall void (*machine_check_vector)(struct pt_regs *, long error_code);
 
-extern int mce_disabled __initdata;
+extern int mce_disabled;
 extern int nr_mce_banks;
 

arch/i386/kernel/entry.S

@@ -204,7 +204,7 @@ VM_MASK		= 0x00020000
 ENTRY(ret_from_fork)
 	CFI_STARTPROC
 	pushl %eax
-	CFI_ADJUST_CFA_OFFSET -4
+	CFI_ADJUST_CFA_OFFSET 4
 	call schedule_tail
 	GET_THREAD_INFO(%ebp)
 	popl %eax

arch/i386/kernel/kprobes.c

@@ -256,11 +256,6 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
 	int ret = 0;
 	kprobe_opcode_t *addr;
 	struct kprobe_ctlblk *kcb;
-#ifdef CONFIG_PREEMPT
-	unsigned pre_preempt_count = preempt_count();
-#else
-	unsigned pre_preempt_count = 1;
-#endif
 
 	addr = (kprobe_opcode_t *)(regs->eip - sizeof(kprobe_opcode_t));
 
@@ -338,13 +333,15 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
 		return 1;
 
 ss_probe:
-	if (pre_preempt_count && p->ainsn.boostable == 1 && !p->post_handler){
+#ifndef CONFIG_PREEMPT
+	if (p->ainsn.boostable == 1 && !p->post_handler){
 		/* Boost up -- we can execute copied instructions directly */
 		reset_current_kprobe();
 		regs->eip = (unsigned long)p->ainsn.insn;
 		preempt_enable_no_resched();
 		return 1;
 	}
+#endif
 	prepare_singlestep(p, regs);
 	kcb->kprobe_status = KPROBE_HIT_SS;
 	return 1;

arch/i386/kernel/machine_kexec.c

@@ -189,14 +189,11 @@ NORET_TYPE void machine_kexec(struct kimage *image)
 	memcpy((void *)reboot_code_buffer, relocate_new_kernel,
 						relocate_new_kernel_size);
 
-	/* The segment registers are funny things, they are
+	/* The segment registers are funny things, they have both a
-	 * automatically loaded from a table, in memory wherever you
+	 * visible and an invisible part.  Whenever the visible part is
-	 * set them to a specific selector, but this table is never
+	 * set to a specific selector, the invisible part is loaded
-	 * accessed again you set the segment to a different selector.
+	 * with from a table in memory.  At no other time is the
-	 *
+	 * descriptor table in memory accessed.
-	 * The more common model is are caches where the behide
-	 * the scenes work is done, but is also dropped at arbitrary
-	 * times.
 	 *
 	 * I take advantage of this here by force loading the
 	 * segments, before I zap the gdt with an invalid value.

arch/i386/kernel/nmi.c

@@ -575,6 +575,7 @@ void touch_nmi_watchdog (void)
 	 */
 	touch_softlockup_watchdog();
 }
+EXPORT_SYMBOL(touch_nmi_watchdog);
 
 extern void die_nmi(struct pt_regs *, const char *msg);
 

arch/i386/kernel/process.c

@@ -690,8 +690,8 @@ struct task_struct fastcall * __switch_to(struct task_struct *prev_p, struct tas
 	/*
 	 * Now maybe handle debug registers and/or IO bitmaps
 	 */
-	if (unlikely((task_thread_info(next_p)->flags & _TIF_WORK_CTXSW))
+	if (unlikely((task_thread_info(next_p)->flags & _TIF_WORK_CTXSW)
-	    || test_tsk_thread_flag(prev_p, TIF_IO_BITMAP))
+	    || test_tsk_thread_flag(prev_p, TIF_IO_BITMAP)))
 		__switch_to_xtra(next_p, tss);
 
 	disable_tsc(prev_p, next_p);

arch/i386/kernel/smpboot.c

@@ -212,14 +212,20 @@ valid_k7:
  * then we print a warning if not, and always resync.
  */
 
-static atomic_t tsc_start_flag = ATOMIC_INIT(0);
+static struct {
-static atomic_t tsc_count_start = ATOMIC_INIT(0);
+	atomic_t start_flag;
-static atomic_t tsc_count_stop = ATOMIC_INIT(0);
+	atomic_t count_start;
-static unsigned long long tsc_values[NR_CPUS];
+	atomic_t count_stop;
+	unsigned long long values[NR_CPUS];
+} tsc __initdata = {
+	.start_flag = ATOMIC_INIT(0),
+	.count_start = ATOMIC_INIT(0),
+	.count_stop = ATOMIC_INIT(0),
+};
 
 #define NR_LOOPS 5
 
-static void __init synchronize_tsc_bp (void)
+static void __init synchronize_tsc_bp(void)
 {
 	int i;
 	unsigned long long t0;
@@ -233,7 +239,7 @@ static void __init synchronize_tsc_bp (void)
 	/* convert from kcyc/sec to cyc/usec */
 	one_usec = cpu_khz / 1000;
 
-	atomic_set(&tsc_start_flag, 1);
+	atomic_set(&tsc.start_flag, 1);
 	wmb();
 
 	/*
@@ -250,16 +256,16 @@ static void __init synchronize_tsc_bp (void)
 		/*
 		 * all APs synchronize but they loop on '== num_cpus'
 		 */
-		while (atomic_read(&tsc_count_start) != num_booting_cpus()-1)
+		while (atomic_read(&tsc.count_start) != num_booting_cpus()-1)
 			cpu_relax();
-		atomic_set(&tsc_count_stop, 0);
+		atomic_set(&tsc.count_stop, 0);
 		wmb();
 		/*
 		 * this lets the APs save their current TSC:
 		 */
-		atomic_inc(&tsc_count_start);
+		atomic_inc(&tsc.count_start);
 
-		rdtscll(tsc_values[smp_processor_id()]);
+		rdtscll(tsc.values[smp_processor_id()]);
 		/*
 		 * We clear the TSC in the last loop:
 		 */
@@ -269,56 +275,54 @@ static void __init synchronize_tsc_bp (void)
 		/*
 		 * Wait for all APs to leave the synchronization point:
 		 */
-		while (atomic_read(&tsc_count_stop) != num_booting_cpus()-1)
+		while (atomic_read(&tsc.count_stop) != num_booting_cpus()-1)
 			cpu_relax();
-		atomic_set(&tsc_count_start, 0);
+		atomic_set(&tsc.count_start, 0);
 		wmb();
-		atomic_inc(&tsc_count_stop);
+		atomic_inc(&tsc.count_stop);
 	}
 
 	sum = 0;
 	for (i = 0; i < NR_CPUS; i++) {
 		if (cpu_isset(i, cpu_callout_map)) {
-			t0 = tsc_values[i];
+			t0 = tsc.values[i];
 			sum += t0;
 		}
 	}
 	avg = sum;
 	do_div(avg, num_booting_cpus());
 
-	sum = 0;
 	for (i = 0; i < NR_CPUS; i++) {
 		if (!cpu_isset(i, cpu_callout_map))
 			continue;
-		delta = tsc_values[i] - avg;
+		delta = tsc.values[i] - avg;
 		if (delta < 0)
 			delta = -delta;
 		/*
 		 * We report bigger than 2 microseconds clock differences.
 		 */
 		if (delta > 2*one_usec) {
-			long realdelta;
+			long long realdelta;
+
 			if (!buggy) {
 				buggy = 1;
 				printk("\n");
 			}
 			realdelta = delta;
 			do_div(realdelta, one_usec);
-			if (tsc_values[i] < avg)
+			if (tsc.values[i] < avg)
 				realdelta = -realdelta;
 
-			if (realdelta > 0)
+			if (realdelta)
-				printk(KERN_INFO "CPU#%d had %ld usecs TSC "
+				printk(KERN_INFO "CPU#%d had %Ld usecs TSC "
 					"skew, fixed it up.\n", i, realdelta);
 		}
-
-		sum += delta;
 	}
 	if (!buggy)
 		printk("passed.\n");
 }
 
-static void __init synchronize_tsc_ap (void)
+static void __init synchronize_tsc_ap(void)
 {
 	int i;
 
@@ -327,20 +331,20 @@ static void __init synchronize_tsc_ap (void)
 	 * this gets called, so we first wait for the BP to
 	 * finish SMP initialization:
 	 */
-	while (!atomic_read(&tsc_start_flag))
+	while (!atomic_read(&tsc.start_flag))
 		cpu_relax();
 
 	for (i = 0; i < NR_LOOPS; i++) {
-		atomic_inc(&tsc_count_start);
+		atomic_inc(&tsc.count_start);
-		while (atomic_read(&tsc_count_start) != num_booting_cpus())
+		while (atomic_read(&tsc.count_start) != num_booting_cpus())
 			cpu_relax();
 
-		rdtscll(tsc_values[smp_processor_id()]);
+		rdtscll(tsc.values[smp_processor_id()]);
 		if (i == NR_LOOPS-1)
 			write_tsc(0, 0);
 
-		atomic_inc(&tsc_count_stop);
+		atomic_inc(&tsc.count_stop);
-		while (atomic_read(&tsc_count_stop) != num_booting_cpus())
+		while (atomic_read(&tsc.count_stop) != num_booting_cpus())
 			cpu_relax();
 	}
 }

arch/i386/kernel/time.c

@@ -135,7 +135,7 @@ unsigned long profile_pc(struct pt_regs *regs)
 {
 	unsigned long pc = instruction_pointer(regs);
 
-	if (in_lock_functions(pc))
+	if (!user_mode_vm(regs) && in_lock_functions(pc))
 		return *(unsigned long *)(regs->ebp + 4);
 
 	return pc;

arch/i386/kernel/traps.c

@@ -187,10 +187,21 @@ static void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
 			if (unwind_init_blocked(&info, task) == 0)
 				unw_ret = show_trace_unwind(&info, log_lvl);
 		}
-		if (unw_ret > 0) {
+		if (unw_ret > 0 && !arch_unw_user_mode(&info)) {
-			if (call_trace > 0)
+#ifdef CONFIG_STACK_UNWIND
+			print_symbol("DWARF2 unwinder stuck at %s\n",
+				     UNW_PC(&info));
+			if (call_trace == 1) {
+				printk("Leftover inexact backtrace:\n");
+				if (UNW_SP(&info))
+					stack = (void *)UNW_SP(&info);
+			} else if (call_trace > 1)
 				return;
-			printk("%sLegacy call trace:\n", log_lvl);
+			else
+				printk("Full inexact backtrace again:\n");
+#else
+			printk("Inexact backtrace:\n");
+#endif
 		}
 	}
 
@@ -442,11 +453,9 @@ void die(const char * str, struct pt_regs * regs, long err)
 	if (in_interrupt())
 		panic("Fatal exception in interrupt");
 
-	if (panic_on_oops) {
+	if (panic_on_oops)
-		printk(KERN_EMERG "Fatal exception: panic in 5 seconds\n");
-		ssleep(5);
 		panic("Fatal exception");
-	}
+
 	oops_exit();
 	do_exit(SIGSEGV);
 }
@@ -1238,8 +1247,10 @@ static int __init call_trace_setup(char *s)
 		call_trace = -1;
 	else if (strcmp(s, "both") == 0)
 		call_trace = 0;
-	else if (strcmp(s, "new") == 0)
+	else if (strcmp(s, "newfallback") == 0)
 		call_trace = 1;
+	else if (strcmp(s, "new") == 2)
+		call_trace = 2;
 	return 1;
 }
 __setup("call_trace=", call_trace_setup);

arch/i386/kernel/vsyscall.lds.S

@@ -10,6 +10,7 @@ SECTIONS
   . = VDSO_PRELINK + SIZEOF_HEADERS;
 
   .hash           : { *(.hash) }		:text
+  .gnu.hash       : { *(.gnu.hash) }
   .dynsym         : { *(.dynsym) }
   .dynstr         : { *(.dynstr) }
   .gnu.version    : { *(.gnu.version) }

arch/i386/pci/init.c

@@ -14,8 +14,12 @@ static __init int pci_access_init(void)
 #ifdef CONFIG_PCI_BIOS
 	pci_pcbios_init();
 #endif
-	if (raw_pci_ops)
+	/*
-		return 0;
+	 * don't check for raw_pci_ops here because we want pcbios as last
+	 * fallback, yet it's needed to run first to set pcibios_last_bus
+	 * in case legacy PCI probing is used. otherwise detecting peer busses
+	 * fails.
+	 */
 #ifdef CONFIG_PCI_DIRECT
 	pci_direct_init();
 #endif