Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6

Conflicts: arch/microblaze/include/asm/socket.h
author: David S. Miller <davem@davemloft.net> 2009-08-13 02:44:53 +0200
committer: David S. Miller <davem@davemloft.net> 2009-08-13 02:44:53 +0200
commit: aa11d958d1a6572eda08214d7c6a735804fe48a5 (patch)
tree: d025b05270ad1e010660d17eeadc6ac3c1abbd7d /Documentation
parent: net,pppoe: fixup module init/exit subsequent calls (diff)
parent: Revert "libertas: Read buffer overflow" (diff)
download: linux-aa11d958d1a6572eda08214d7c6a735804fe48a5.tar.xz
linux-aa11d958d1a6572eda08214d7c6a735804fe48a5.zip
17 files changed, 732 insertions, 499 deletions
diff --git a/Documentation/ABI/testing/sysfs-block b/Documentation/ABI/testing/sysfs-block
index cbbd3e069945..5f3bedaf8e35 100644
--- a/Documentation/ABI/testing/sysfs-block
+++ b/Documentation/ABI/testing/sysfs-block
@@ -94,28 +94,37 @@ What:		/sys/block/<disk>/queue/physical_block_size
 Date:		May 2009
 Contact:	Martin K. Petersen <martin.petersen@oracle.com>
 Description:
-		This is the smallest unit the storage device can write
-		without resorting to read-modify-write operation.  It is
-		usually the same as the logical block size but may be
-		bigger.  One example is SATA drives with 4KB sectors
-		that expose a 512-byte logical block size to the
-		operating system.
+		This is the smallest unit a physical storage device can
+		write atomically.  It is usually the same as the logical
+		block size but may be bigger.  One example is SATA
+		drives with 4KB sectors that expose a 512-byte logical
+		block size to the operating system.  For stacked block
+		devices the physical_block_size variable contains the
+		maximum physical_block_size of the component devices.
 
 What:		/sys/block/<disk>/queue/minimum_io_size
 Date:		April 2009
 Contact:	Martin K. Petersen <martin.petersen@oracle.com>
 Description:
-		Storage devices may report a preferred minimum I/O size,
-		which is the smallest request the device can perform
-		without incurring a read-modify-write penalty.  For disk
-		drives this is often the physical block size.  For RAID
-		arrays it is often the stripe chunk size.
+		Storage devices may report a granularity or preferred
+		minimum I/O size which is the smallest request the
+		device can perform without incurring a performance
+		penalty.  For disk drives this is often the physical
+		block size.  For RAID arrays it is often the stripe
+		chunk size.  A properly aligned multiple of
+		minimum_io_size is the preferred request size for
+		workloads where a high number of I/O operations is
+		desired.
 
 What:		/sys/block/<disk>/queue/optimal_io_size
 Date:		April 2009
 Contact:	Martin K. Petersen <martin.petersen@oracle.com>
 Description:
 		Storage devices may report an optimal I/O size, which is
-		the device's preferred unit of receiving I/O.  This is
-		rarely reported for disk drives.  For RAID devices it is
-		usually the stripe width or the internal block size.
+		the device's preferred unit for sustained I/O.  This is
+		rarely reported for disk drives.  For RAID arrays it is
+		usually the stripe width or the internal track size.  A
+		properly aligned multiple of optimal_io_size is the
+		preferred request size for workloads where sustained
+		throughput is desired.  If no optimal I/O size is
+		reported this file contains 0.
diff --git a/Documentation/arm/memory.txt b/Documentation/arm/memory.txt
index 43cb1004d35f..9d58c7c5eddd 100644
--- a/Documentation/arm/memory.txt
+++ b/Documentation/arm/memory.txt
@@ -21,6 +21,8 @@ ffff8000	ffffffff	copy_user_page / clear_user_page use.
 				For SA11xx and Xscale, this is used to
 				setup a minicache mapping.
 
+ffff4000	ffffffff	cache aliasing on ARMv6 and later CPUs.
+
 ffff1000	ffff7fff	Reserved.
 				Platforms must not use this address range.
 
diff --git a/Documentation/driver-model/driver.txt b/Documentation/driver-model/driver.txt
index 82132169d47a..60120fb3b961 100644
--- a/Documentation/driver-model/driver.txt
+++ b/Documentation/driver-model/driver.txt
@@ -207,8 +207,8 @@ Attributes
 ~~~~~~~~~~
 struct driver_attribute {
         struct attribute        attr;
-        ssize_t (*show)(struct device_driver *, char * buf, size_t count, loff_t off);
-        ssize_t (*store)(struct device_driver *, const char * buf, size_t count, loff_t off);
+        ssize_t (*show)(struct device_driver *driver, char *buf);
+        ssize_t (*store)(struct device_driver *, const char * buf, size_t count);
 };
 
 Device drivers can export attributes via their sysfs directories. 
diff --git a/Documentation/dvb/get_dvb_firmware b/Documentation/dvb/get_dvb_firmware
index a52adfc9a57f..3d1b0ab70c8e 100644
--- a/Documentation/dvb/get_dvb_firmware
+++ b/Documentation/dvb/get_dvb_firmware
@@ -25,7 +25,7 @@ use IO::Handle;
 		"tda10046lifeview", "av7110", "dec2000t", "dec2540t",
 		"dec3000s", "vp7041", "dibusb", "nxt2002", "nxt2004",
 		"or51211", "or51132_qam", "or51132_vsb", "bluebird",
-		"opera1", "cx231xx", "cx18", "cx23885", "pvrusb2" );
+		"opera1", "cx231xx", "cx18", "cx23885", "pvrusb2", "mpc718" );
 
 # Check args
 syntax() if (scalar(@ARGV) != 1);
@@ -381,6 +381,57 @@ sub cx18 {
     $allfiles;
 }
 
+sub mpc718 {
+    my $archive = 'Yuan MPC718 TV Tuner Card 2.13.10.1016.zip';
+    my $url = "ftp://ftp.work.acer-euro.com/desktop/aspire_idea510/vista/Drivers/$archive";
+    my $fwfile = "dvb-cx18-mpc718-mt352.fw";
+    my $tmpdir = tempdir(DIR => "/tmp", CLEANUP => 1);
+
+    checkstandard();
+    wgetfile($archive, $url);
+    unzip($archive, $tmpdir);
+
+    my $sourcefile = "$tmpdir/Yuan MPC718 TV Tuner Card 2.13.10.1016/mpc718_32bit/yuanrap.sys";
+    my $found = 0;
+
+    open IN, '<', $sourcefile or die "Couldn't open $sourcefile to extract $fwfile data\n";
+    binmode IN;
+    open OUT, '>', $fwfile;
+    binmode OUT;
+    {
+	# Block scope because we change the line terminator variable $/
+	my $prevlen = 0;
+	my $currlen;
+
+	# Buried in the data segment are 3 runs of almost identical
+	# register-value pairs that end in 0x5d 0x01 which is a "TUNER GO"
+	# command for the MT352.
+	# Pull out the middle run (because it's easy) of register-value
+	# pairs to make the "firmware" file.
+
+	local $/ = "\x5d\x01"; # MT352 "TUNER GO"
+
+	while (<IN>) {
+	    $currlen = length($_);
+	    if ($prevlen == $currlen && $currlen <= 64) {
+		chop; chop; # Get rid of "TUNER GO"
+		s/^\0\0//;  # get rid of leading 00 00 if it's there
+		printf OUT "$_";
+		$found = 1;
+		last;
+	    }
+	    $prevlen = $currlen;
+	}
+    }
+    close OUT;
+    close IN;
+    if (!$found) {
+	unlink $fwfile;
+	die "Couldn't find valid register-value sequence in $sourcefile for $fwfile\n";
+    }
+    $fwfile;
+}
+
 sub cx23885 {
     my $url = "http://linuxtv.org/downloads/firmware/";
 
diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt
index f8cd450be9aa..09e031c55887 100644
--- a/Documentation/feature-removal-schedule.txt
+++ b/Documentation/feature-removal-schedule.txt
@@ -458,3 +458,13 @@ Why:	Remove the old legacy 32bit machine check code. This has been
 	but the old version has been kept around for easier testing. Note this
 	doesn't impact the old P5 and WinChip machine check handlers.
 Who:	Andi Kleen <andi@firstfloor.org>
+
+----------------------------
+
+What:	lock_policy_rwsem_* and unlock_policy_rwsem_* will not be
+	exported interface anymore.
+When:	2.6.33
+Why:	cpu_policy_rwsem has a new cleaner definition making it local to
+	cpufreq core and contained inside cpufreq.c. Other dependent
+	drivers should not use it in order to safely avoid lockdep issues.
+Who:	Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
diff --git a/Documentation/filesystems/sysfs.txt b/Documentation/filesystems/sysfs.txt
index 7e81e37c0b1e..b245d524d568 100644
--- a/Documentation/filesystems/sysfs.txt
+++ b/Documentation/filesystems/sysfs.txt
@@ -23,7 +23,8 @@ interface.
 Using sysfs
 ~~~~~~~~~~~
 
-sysfs is always compiled in. You can access it by doing:
+sysfs is always compiled in if CONFIG_SYSFS is defined. You can access
+it by doing:
 
     mount -t sysfs sysfs /sys 
 
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 9347f4ad4342..3fe614d405e0 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -1725,8 +1725,8 @@ and is between 256 and 4096 characters. It is defined in the file
 	oprofile.cpu_type=	Force an oprofile cpu type
 			This might be useful if you have an older oprofile
 			userland or if you want common events.
-			Format: { archperfmon }
-			archperfmon: [X86] Force use of architectural
+			Format: { arch_perfmon }
+			arch_perfmon: [X86] Force use of architectural
 				perfmon on Intel CPUs instead of the
 				CPU specific event set.
 
diff --git a/Documentation/laptops/thinkpad-acpi.txt b/Documentation/laptops/thinkpad-acpi.txt
index f2296ecedb89..e2ddcdeb61b6 100644
--- a/Documentation/laptops/thinkpad-acpi.txt
+++ b/Documentation/laptops/thinkpad-acpi.txt
@@ -36,8 +36,6 @@ detailed description):
 	- Bluetooth enable and disable
 	- video output switching, expansion control
 	- ThinkLight on and off
-	- limited docking and undocking
-	- UltraBay eject
 	- CMOS/UCMS control
 	- LED control
 	- ACPI sounds
@@ -729,131 +727,6 @@ cannot be read or if it is unknown, thinkpad-acpi will report it as "off".
 It is impossible to know if the status returned through sysfs is valid.
 
 
-Docking / undocking -- /proc/acpi/ibm/dock
-------------------------------------------
-
-Docking and undocking (e.g. with the X4 UltraBase) requires some
-actions to be taken by the operating system to safely make or break
-the electrical connections with the dock.
-
-The docking feature of this driver generates the following ACPI events:
-
-	ibm/dock GDCK 00000003 00000001 -- eject request
-	ibm/dock GDCK 00000003 00000002 -- undocked
-	ibm/dock GDCK 00000000 00000003 -- docked
-
-NOTE: These events will only be generated if the laptop was docked
-when originally booted. This is due to the current lack of support for
-hot plugging of devices in the Linux ACPI framework. If the laptop was
-booted while not in the dock, the following message is shown in the
-logs:
-
-	Mar 17 01:42:34 aero kernel: thinkpad_acpi: dock device not present
-
-In this case, no dock-related events are generated but the dock and
-undock commands described below still work. They can be executed
-manually or triggered by Fn key combinations (see the example acpid
-configuration files included in the driver tarball package available
-on the web site).
-
-When the eject request button on the dock is pressed, the first event
-above is generated. The handler for this event should issue the
-following command:
-
-	echo undock > /proc/acpi/ibm/dock
-
-After the LED on the dock goes off, it is safe to eject the laptop.
-Note: if you pressed this key by mistake, go ahead and eject the
-laptop, then dock it back in. Otherwise, the dock may not function as
-expected.
-
-When the laptop is docked, the third event above is generated. The
-handler for this event should issue the following command to fully
-enable the dock:
-
-	echo dock > /proc/acpi/ibm/dock
-
-The contents of the /proc/acpi/ibm/dock file shows the current status
-of the dock, as provided by the ACPI framework.
-
-The docking support in this driver does not take care of enabling or
-disabling any other devices you may have attached to the dock. For
-example, a CD drive plugged into the UltraBase needs to be disabled or
-enabled separately. See the provided example acpid configuration files
-for how this can be accomplished.
-
-There is no support yet for PCI devices that may be attached to a
-docking station, e.g. in the ThinkPad Dock II. The driver currently
-does not recognize, enable or disable such devices. This means that
-the only docking stations currently supported are the X-series
-UltraBase docks and "dumb" port replicators like the Mini Dock (the
-latter don't need any ACPI support, actually).
-
-
-UltraBay eject -- /proc/acpi/ibm/bay
-------------------------------------
-
-Inserting or ejecting an UltraBay device requires some actions to be
-taken by the operating system to safely make or break the electrical
-connections with the device.
-
-This feature generates the following ACPI events:
-
-	ibm/bay MSTR 00000003 00000000 -- eject request
-	ibm/bay MSTR 00000001 00000000 -- eject lever inserted
-
-NOTE: These events will only be generated if the UltraBay was present
-when the laptop was originally booted (on the X series, the UltraBay
-is in the dock, so it may not be present if the laptop was undocked).
-This is due to the current lack of support for hot plugging of devices
-in the Linux ACPI framework. If the laptop was booted without the
-UltraBay, the following message is shown in the logs:
-
-	Mar 17 01:42:34 aero kernel: thinkpad_acpi: bay device not present
-
-In this case, no bay-related events are generated but the eject
-command described below still works. It can be executed manually or
-triggered by a hot key combination.
-
-Sliding the eject lever generates the first event shown above. The
-handler for this event should take whatever actions are necessary to
-shut down the device in the UltraBay (e.g. call idectl), then issue
-the following command:
-
-	echo eject > /proc/acpi/ibm/bay
-
-After the LED on the UltraBay goes off, it is safe to pull out the
-device.
-
-When the eject lever is inserted, the second event above is
-generated. The handler for this event should take whatever actions are
-necessary to enable the UltraBay device (e.g. call idectl).
-
-The contents of the /proc/acpi/ibm/bay file shows the current status
-of the UltraBay, as provided by the ACPI framework.
-
-EXPERIMENTAL warm eject support on the 600e/x, A22p and A3x (To use
-this feature, you need to supply the experimental=1 parameter when
-loading the module):
-
-These models do not have a button near the UltraBay device to request
-a hot eject but rather require the laptop to be put to sleep
-(suspend-to-ram) before the bay device is ejected or inserted).
-The sequence of steps to eject the device is as follows:
-
-	echo eject > /proc/acpi/ibm/bay
-	put the ThinkPad to sleep
-	remove the drive
-	resume from sleep
-	cat /proc/acpi/ibm/bay should show that the drive was removed
-
-On the A3x, both the UltraBay 2000 and UltraBay Plus devices are
-supported. Use "eject2" instead of "eject" for the second bay.
-
-Note: the UltraBay eject support on the 600e/x, A22p and A3x is
-EXPERIMENTAL and may not work as expected. USE WITH CAUTION!
-
-
 CMOS/UCMS control
 -----------------
 
diff --git a/Documentation/lguest/lguest.c b/Documentation/lguest/lguest.c
index 9ebcd6ef361b..950cde6d6e58 100644
--- a/Documentation/lguest/lguest.c
+++ b/Documentation/lguest/lguest.c
@@ -1,7 +1,9 @@
-/*P:100 This is the Launcher code, a simple program which lays out the
- * "physical" memory for the new Guest by mapping the kernel image and
- * the virtual devices, then opens /dev/lguest to tell the kernel
- * about the Guest and control it. :*/
+/*P:100
+ * This is the Launcher code, a simple program which lays out the "physical"
+ * memory for the new Guest by mapping the kernel image and the virtual
+ * devices, then opens /dev/lguest to tell the kernel about the Guest and
+ * control it.
+:*/
 #define _LARGEFILE64_SOURCE
 #define _GNU_SOURCE
 #include <stdio.h>
@@ -46,13 +48,15 @@
 #include "linux/virtio_rng.h"
 #include "linux/virtio_ring.h"
 #include "asm/bootparam.h"
-/*L:110 We can ignore the 39 include files we need for this program, but I do
- * want to draw attention to the use of kernel-style types.
+/*L:110
+ * We can ignore the 42 include files we need for this program, but I do want
+ * to draw attention to the use of kernel-style types.
  *
  * As Linus said, "C is a Spartan language, and so should your naming be."  I
  * like these abbreviations, so we define them here.  Note that u64 is always
  * unsigned long long, which works on all Linux systems: this means that we can
- * use %llu in printf for any u64. */
+ * use %llu in printf for any u64.
+ */
 typedef unsigned long long u64;
 typedef uint32_t u32;
 typedef uint16_t u16;
@@ -69,8 +73,10 @@ typedef uint8_t u8;
 /* This will occupy 3 pages: it must be a power of 2. */
 #define VIRTQUEUE_NUM 256
 
-/*L:120 verbose is both a global flag and a macro.  The C preprocessor allows
- * this, and although I wouldn't recommend it, it works quite nicely here. */
+/*L:120
+ * verbose is both a global flag and a macro.  The C preprocessor allows
+ * this, and although I wouldn't recommend it, it works quite nicely here.
+ */
 static bool verbose;
 #define verbose(args...) \
 	do { if (verbose) printf(args); } while(0)
@@ -87,8 +93,7 @@ static int lguest_fd;
 static unsigned int __thread cpu_id;
 
 /* This is our list of devices. */
-struct device_list
-{
+struct device_list {
 	/* Counter to assign interrupt numbers. */
 	unsigned int next_irq;
 
@@ -100,8 +105,7 @@ struct device_list
 
 	/* A single linked list of devices. */
 	struct device *dev;
-	/* And a pointer to the last device for easy append and also for
-	 * configuration appending. */
+	/* And a pointer to the last device for easy append. */
 	struct device *lastdev;
 };
 
@@ -109,8 +113,7 @@ struct device_list
 static struct device_list devices;
 
 /* The device structure describes a single device. */
-struct device
-{
+struct device {
 	/* The linked-list pointer. */
 	struct device *next;
 
@@ -135,8 +138,7 @@ struct device
 };
 
 /* The virtqueue structure describes a queue attached to a device. */
-struct virtqueue
-{
+struct virtqueue {
 	struct virtqueue *next;
 
 	/* Which device owns me. */
@@ -168,20 +170,24 @@ static char **main_args;
 /* The original tty settings to restore on exit. */
 static struct termios orig_term;
 
-/* We have to be careful with barriers: our devices are all run in separate
+/*
+ * We have to be careful with barriers: our devices are all run in separate
  * threads and so we need to make sure that changes visible to the Guest happen
- * in precise order. */
+ * in precise order.
+ */
 #define wmb() __asm__ __volatile__("" : : : "memory")
 #define mb() __asm__ __volatile__("" : : : "memory")
 
-/* Convert an iovec element to the given type.
+/*
+ * Convert an iovec element to the given type.
  *
  * This is a fairly ugly trick: we need to know the size of the type and
  * alignment requirement to check the pointer is kosher.  It's also nice to
  * have the name of the type in case we report failure.
  *
  * Typing those three things all the time is cumbersome and error prone, so we
- * have a macro which sets them all up and passes to the real function. */
+ * have a macro which sets them all up and passes to the real function.
+ */
 #define convert(iov, type) \
 	((type *)_convert((iov), sizeof(type), __alignof__(type), #type))
 
@@ -198,8 +204,10 @@ static void *_convert(struct iovec *iov, size_t size, size_t align,
 /* Wrapper for the last available index.  Makes it easier to change. */
 #define lg_last_avail(vq)	((vq)->last_avail_idx)
 
-/* The virtio configuration space is defined to be little-endian.  x86 is
- * little-endian too, but it's nice to be explicit so we have these helpers. */
+/*
+ * The virtio configuration space is defined to be little-endian.  x86 is
+ * little-endian too, but it's nice to be explicit so we have these helpers.
+ */
 #define cpu_to_le16(v16) (v16)
 #define cpu_to_le32(v32) (v32)
 #define cpu_to_le64(v64) (v64)
@@ -241,11 +249,12 @@ static u8 *get_feature_bits(struct device *dev)
 		+ dev->num_vq * sizeof(struct lguest_vqconfig);
 }
 
-/*L:100 The Launcher code itself takes us out into userspace, that scary place
- * where pointers run wild and free!  Unfortunately, like most userspace
- * programs, it's quite boring (which is why everyone likes to hack on the
- * kernel!).  Perhaps if you make up an Lguest Drinking Game at this point, it
- * will get you through this section.  Or, maybe not.
+/*L:100
+ * The Launcher code itself takes us out into userspace, that scary place where
+ * pointers run wild and free!  Unfortunately, like most userspace programs,
+ * it's quite boring (which is why everyone likes to hack on the kernel!).
+ * Perhaps if you make up an Lguest Drinking Game at this point, it will get
+ * you through this section.  Or, maybe not.
  *
  * The Launcher sets up a big chunk of memory to be the Guest's "physical"
  * memory and stores it in "guest_base".  In other words, Guest physical ==
@@ -253,7 +262,8 @@ static u8 *get_feature_bits(struct device *dev)
  *
  * This can be tough to get your head around, but usually it just means that we
  * use these trivial conversion functions when the Guest gives us it's
- * "physical" addresses: */
+ * "physical" addresses:
+ */
 static void *from_guest_phys(unsigned long addr)
 {
 	return guest_base + addr;
@@ -268,7 +278,8 @@ static unsigned long to_guest_phys(const void *addr)
  * Loading the Kernel.
  *
  * We start with couple of simple helper routines.  open_or_die() avoids
- * error-checking code cluttering the callers: */
+ * error-checking code cluttering the callers:
+ */
 static int open_or_die(const char *name, int flags)
 {
 	int fd = open(name, flags);
@@ -283,12 +294,19 @@ static void *map_zeroed_pages(unsigned int num)
 	int fd = open_or_die("/dev/zero", O_RDONLY);
 	void *addr;
 
-	/* We use a private mapping (ie. if we write to the page, it will be
-	 * copied). */
+	/*
+	 * We use a private mapping (ie. if we write to the page, it will be
+	 * copied).
+	 */
 	addr = mmap(NULL, getpagesize() * num,
 		    PROT_READ|PROT_WRITE|PROT_EXEC, MAP_PRIVATE, fd, 0);
 	if (addr == MAP_FAILED)
 		err(1, "Mmaping %u pages of /dev/zero", num);
+
+	/*
+	 * One neat mmap feature is that you can close the fd, and it
+	 * stays mapped.
+	 */
 	close(fd);
 
 	return addr;
@@ -305,20 +323,24 @@ static void *get_pages(unsigned int num)
 	return addr;
 }
 
-/* This routine is used to load the kernel or initrd.  It tries mmap, but if
+/*
+ * This routine is used to load the kernel or initrd.  It tries mmap, but if
  * that fails (Plan 9's kernel file isn't nicely aligned on page boundaries),
- * it falls back to reading the memory in. */
+ * it falls back to reading the memory in.
+ */
 static void map_at(int fd, void *addr, unsigned long offset, unsigned long len)
 {
 	ssize_t r;
 
-	/* We map writable even though for some segments are marked read-only.
+	/*
+	 * We map writable even though for some segments are marked read-only.
 	 * The kernel really wants to be writable: it patches its own
 	 * instructions.
 	 *
 	 * MAP_PRIVATE means that the page won't be copied until a write is
 	 * done to it.  This allows us to share untouched memory between
-	 * Guests. */
+	 * Guests.
+	 */
 	if (mmap(addr, len, PROT_READ|PROT_WRITE|PROT_EXEC,
 		 MAP_FIXED|MAP_PRIVATE, fd, offset) != MAP_FAILED)
 		return;
@@ -329,7 +351,8 @@ static void map_at(int fd, void *addr, unsigned long offset, unsigned long len)
 		err(1, "Reading offset %lu len %lu gave %zi", offset, len, r);
 }
 
-/* This routine takes an open vmlinux image, which is in ELF, and maps it into
+/*
+ * This routine takes an open vmlinux image, which is in ELF, and maps it into
  * the Guest memory.  ELF = Embedded Linking Format, which is the format used
  * by all modern binaries on Linux including the kernel.
  *
@@ -337,23 +360,28 @@ static void map_at(int fd, void *addr, unsigned long offset, unsigned long len)
  * address.  We use the physical address; the Guest will map itself to the
  * virtual address.
  *
- * We return the starting address. */
+ * We return the starting address.
+ */
 static unsigned long map_elf(int elf_fd, const Elf32_Ehdr *ehdr)
 {
 	Elf32_Phdr phdr[ehdr->e_phnum];
 	unsigned int i;
 
-	/* Sanity checks on the main ELF header: an x86 executable with a
-	 * reasonable number of correctly-sized program headers. */
+	/*
+	 * Sanity checks on the main ELF header: an x86 executable with a
+	 * reasonable number of correctly-sized program headers.
+	 */
 	if (ehdr->e_type != ET_EXEC
 	    || ehdr->e_machine != EM_386
 	    || ehdr->e_phentsize != sizeof(Elf32_Phdr)
 	    || ehdr->e_phnum < 1 || ehdr->e_phnum > 65536U/sizeof(Elf32_Phdr))
 		errx(1, "Malformed elf header");
 
-	/* An ELF executable contains an ELF header and a number of "program"
+	/*
+	 * An ELF executable contains an ELF header and a number of "program"
 	 * headers which indicate which parts ("segments") of the program to
-	 * load where. */
+	 * load where.
+	 */
 
 	/* We read in all the program headers at once: */
 	if (lseek(elf_fd, ehdr->e_phoff, SEEK_SET) < 0)
@@ -361,8 +389,10 @@ static unsigned long map_elf(int elf_fd, const Elf32_Ehdr *ehdr)
 	if (read(elf_fd, phdr, sizeof(phdr)) != sizeof(phdr))
 		err(1, "Reading program headers");
 
-	/* Try all the headers: there are usually only three.  A read-only one,
-	 * a read-write one, and a "note" section which we don't load. */
+	/*
+	 * Try all the headers: there are usually only three.  A read-only one,
+	 * a read-write one, and a "note" section which we don't load.
+	 */
 	for (i = 0; i < ehdr->e_phnum; i++) {
 		/* If this isn't a loadable segment, we ignore it */
 		if (phdr[i].p_type != PT_LOAD)
@@ -380,13 +410,15 @@ static unsigned long map_elf(int elf_fd, const Elf32_Ehdr *ehdr)
 	return ehdr->e_entry;
 }
 
-/*L:150 A bzImage, unlike an ELF file, is not meant to be loaded.  You're
- * supposed to jump into it and it will unpack itself.  We used to have to
- * perform some hairy magic because the unpacking code scared me.
+/*L:150
+ * A bzImage, unlike an ELF file, is not meant to be loaded.  You're supposed
+ * to jump into it and it will unpack itself.  We used to have to perform some
+ * hairy magic because the unpacking code scared me.
  *
  * Fortunately, Jeremy Fitzhardinge convinced me it wasn't that hard and wrote
  * a small patch to jump over the tricky bits in the Guest, so now we just read
- * the funky header so we know where in the file to load, and away we go! */
+ * the funky header so we know where in the file to load, and away we go!
+ */
 static unsigned long load_bzimage(int fd)
 {
 	struct boot_params boot;
@@ -394,8 +426,10 @@ static unsigned long load_bzimage(int fd)
 	/* Modern bzImages get loaded at 1M. */
 	void *p = from_guest_phys(0x100000);
 
-	/* Go back to the start of the file and read the header.  It should be
-	 * a Linux boot header (see Documentation/x86/i386/boot.txt) */
+	/*
+	 * Go back to the start of the file and read the header.  It should be
+	 * a Linux boot header (see Documentation/x86/i386/boot.txt)
+	 */
 	lseek(fd, 0, SEEK_SET);
 	read(fd, &boot, sizeof(boot));
 
@@ -414,9 +448,11 @@ static unsigned long load_bzimage(int fd)
 	return boot.hdr.code32_start;
 }
 
-/*L:140 Loading the kernel is easy when it's a "vmlinux", but most kernels
+/*L:140
+ * Loading the kernel is easy when it's a "vmlinux", but most kernels
  * come wrapped up in the self-decompressing "bzImage" format.  With a little
- * work, we can load those, too. */
+ * work, we can load those, too.
+ */
 static unsigned long load_kernel(int fd)
 {
 	Elf32_Ehdr hdr;
@@ -433,24 +469,28 @@ static unsigned long load_kernel(int fd)
 	return load_bzimage(fd);
 }
 
-/* This is a trivial little helper to align pages.  Andi Kleen hated it because
+/*
+ * This is a trivial little helper to align pages.  Andi Kleen hated it because
  * it calls getpagesize() twice: "it's dumb code."
  *
  * Kernel guys get really het up about optimization, even when it's not
- * necessary.  I leave this code as a reaction against that. */
+ * necessary.  I leave this code as a reaction against that.
+ */
 static inline unsigned long page_align(unsigned long addr)
 {
 	/* Add upwards and truncate downwards. */
 	return ((addr + getpagesize()-1) & ~(getpagesize()-1));
 }
 
-/*L:180 An "initial ram disk" is a disk image loaded into memory along with
- * the kernel which the kernel can use to boot from without needing any
- * drivers.  Most distributions now use this as standard: the initrd contains
- * the code to load the appropriate driver modules for the current machine.
+/*L:180
+ * An "initial ram disk" is a disk image loaded into memory along with the
+ * kernel which the kernel can use to boot from without needing any drivers.
+ * Most distributions now use this as standard: the initrd contains the code to
+ * load the appropriate driver modules for the current machine.
  *
  * Importantly, James Morris works for RedHat, and Fedora uses initrds for its
- * kernels.  He sent me this (and tells me when I break it). */
+ * kernels.  He sent me this (and tells me when I break it).
+ */
 static unsigned long load_initrd(const char *name, unsigned long mem)
 {
 	int ifd;
@@ -462,12 +502,16 @@ static unsigned long load_initrd(const char *name, unsigned long mem)
 	if (fstat(ifd, &st) < 0)
 		err(1, "fstat() on initrd '%s'", name);
 
-	/* We map the initrd at the top of memory, but mmap wants it to be
-	 * page-aligned, so we round the size up for that. */
+	/*
+	 * We map the initrd at the top of memory, but mmap wants it to be
+	 * page-aligned, so we round the size up for that.
+	 */
 	len = page_align(st.st_size);
 	map_at(ifd, from_guest_phys(mem - len), 0, st.st_size);
-	/* Once a file is mapped, you can close the file descriptor.  It's a
-	 * little odd, but quite useful. */
+	/*
+	 * Once a file is mapped, you can close the file descriptor.  It's a
+	 * little odd, but quite useful.
+	 */
 	close(ifd);
 	verbose("mapped initrd %s size=%lu @ %p\n", name, len, (void*)mem-len);
 
@@ -476,8 +520,10 @@ static unsigned long load_initrd(const char *name, unsigned long mem)
 }
 /*:*/
 
-/* Simple routine to roll all the commandline arguments together with spaces
- * between them. */
+/*
+ * Simple routine to roll all the commandline arguments together with spaces
+ * between them.
+ */
 static void concat(char *dst, char *args[])
 {
 	unsigned int i, len = 0;
@@ -494,10 +540,12 @@ static void concat(char *dst, char *args[])
 	dst[len] = '\0';
 }
 
-/*L:185 This is where we actually tell the kernel to initialize the Guest.  We
+/*L:185
+ * This is where we actually tell the kernel to initialize the Guest.  We
  * saw the arguments it expects when we looked at initialize() in lguest_user.c:
  * the base of Guest "physical" memory, the top physical page to allow and the
- * entry point for the Guest. */
+ * entry point for the Guest.
+ */
 static void tell_kernel(unsigned long start)
 {
 	unsigned long args[] = { LHREQ_INITIALIZE,
@@ -511,7 +559,7 @@ static void tell_kernel(unsigned long start)
 }
 /*:*/
 
-/*
+/*L:200
  * Device Handling.
  *
  * When the Guest gives us a buffer, it sends an array of addresses and sizes.
@@ -522,20 +570,26 @@ static void tell_kernel(unsigned long start)
 static void *_check_pointer(unsigned long addr, unsigned int size,
 			    unsigned int line)
 {
-	/* We have to separately check addr and addr+size, because size could
-	 * be huge and addr + size might wrap around. */
+	/*
+	 * We have to separately check addr and addr+size, because size could
+	 * be huge and addr + size might wrap around.
+	 */
 	if (addr >= guest_limit || addr + size >= guest_limit)
 		errx(1, "%s:%i: Invalid address %#lx", __FILE__, line, addr);
-	/* We return a pointer for the caller's convenience, now we know it's
-	 * safe to use. */
+	/*
+	 * We return a pointer for the caller's convenience, now we know it's
+	 * safe to use.
+	 */
 	return from_guest_phys(addr);
 }
 /* A macro which transparently hands the line number to the real function. */
 #define check_pointer(addr,size) _check_pointer(addr, size, __LINE__)
 
-/* Each buffer in the virtqueues is actually a chain of descriptors.  This
+/*
+ * Each buffer in the virtqueues is actually a chain of descriptors.  This
  * function returns the next descriptor in the chain, or vq->vring.num if we're
- * at the end. */
+ * at the end.
+ */
 static unsigned next_desc(struct vring_desc *desc,
 			  unsigned int i, unsigned int max)
 {
@@ -556,7 +610,10 @@ static unsigned next_desc(struct vring_desc *desc,
 	return next;
 }
 
-/* This actually sends the interrupt for this virtqueue */
+/*
+ * This actually sends the interrupt for this virtqueue, if we've used a
+ * buffer.
+ */
 static void trigger_irq(struct virtqueue *vq)
 {
 	unsigned long buf[] = { LHREQ_IRQ, vq->config.irq };
@@ -576,12 +633,14 @@ static void trigger_irq(struct virtqueue *vq)
 		err(1, "Triggering irq %i", vq->config.irq);
 }
 
-/* This looks in the virtqueue and for the first available buffer, and converts
+/*
+ * This looks in the virtqueue for the first available buffer, and converts
  * it to an iovec for convenient access.  Since descriptors consist of some
  * number of output then some number of input descriptors, it's actually two
  * iovecs, but we pack them into one and note how many of each there were.
  *
- * This function returns the descriptor number found. */
+ * This function waits if necessary, and returns the descriptor number found.
+ */
 static unsigned wait_for_vq_desc(struct virtqueue *vq,
 				 struct iovec iov[],
 				 unsigned int *out_num, unsigned int *in_num)
@@ -590,17 +649,23 @@ static unsigned wait_for_vq_desc(struct virtqueue *vq,
 	struct vring_desc *desc;
 	u16 last_avail = lg_last_avail(vq);
 
+	/* There's nothing available? */
 	while (last_avail == vq->vring.avail->idx) {
 		u64 event;
 
-		/* OK, tell Guest about progress up to now. */
+		/*
+		 * Since we're about to sleep, now is a good time to tell the
+		 * Guest about what we've used up to now.
+		 */
 		trigger_irq(vq);
 
 		/* OK, now we need to know about added descriptors. */
 		vq->vring.used->flags &= ~VRING_USED_F_NO_NOTIFY;
 
-		/* They could have slipped one in as we were doing that: make
-		 * sure it's written, then check again. */
+		/*
+		 * They could have slipped one in as we were doing that: make
+		 * sure it's written, then check again.
+		 */
 		mb();
 		if (last_avail != vq->vring.avail->idx) {
 			vq->vring.used->flags |= VRING_USED_F_NO_NOTIFY;
@@ -620,8 +685,10 @@ static unsigned wait_for_vq_desc(struct virtqueue *vq,
 		errx(1, "Guest moved used index from %u to %u",
 		     last_avail, vq->vring.avail->idx);
 
-	/* Grab the next descriptor number they're advertising, and increment
-	 * the index we've seen. */
+	/*
+	 * Grab the next descriptor number they're advertising, and increment
+	 * the index we've seen.
+	 */
 	head = vq->vring.avail->ring[last_avail % vq->vring.num];
 	lg_last_avail(vq)++;
 
@@ -636,8 +703,10 @@ static unsigned wait_for_vq_desc(struct virtqueue *vq,
 	desc = vq->vring.desc;
 	i = head;
 
-	/* If this is an indirect entry, then this buffer contains a descriptor
-	 * table which we handle as if it's any normal descriptor chain. */
+	/*
+	 * If this is an indirect entry, then this buffer contains a descriptor
+	 * table which we handle as if it's any normal descriptor chain.
+	 */
 	if (desc[i].flags & VRING_DESC_F_INDIRECT) {
 		if (desc[i].len % sizeof(struct vring_desc))
 			errx(1, "Invalid size for indirect buffer table");
@@ -656,8 +725,10 @@ static unsigned wait_for_vq_desc(struct virtqueue *vq,
 		if (desc[i].flags & VRING_DESC_F_WRITE)
 			(*in_num)++;
 		else {
-			/* If it's an output descriptor, they're all supposed
-			 * to come before any input descriptors. */
+			/*
+			 * If it's an output descriptor, they're all supposed
+			 * to come before any input descriptors.
+			 */
 			if (*in_num)
 				errx(1, "Descriptor has out after in");
 			(*out_num)++;
@@ -671,14 +742,19 @@ static unsigned wait_for_vq_desc(struct virtqueue *vq,
 	return head;
 }
 
-/* After we've used one of their buffers, we tell them about it.  We'll then
- * want to send them an interrupt, using trigger_irq(). */
+/*
+ * After we've used one of their buffers, we tell the Guest about it.  Sometime
+ * later we'll want to send them an interrupt using trigger_irq(); note that
+ * wait_for_vq_desc() does that for us if it has to wait.
+ */
 static void add_used(struct virtqueue *vq, unsigned int head, int len)
 {
 	struct vring_used_elem *used;
 
-	/* The virtqueue contains a ring of used buffers.  Get a pointer to the
-	 * next entry in that used ring. */
+	/*
+	 * The virtqueue contains a ring of used buffers.  Get a pointer to the
+	 * next entry in that used ring.
+	 */
 	used = &vq->vring.used->ring[vq->vring.used->idx % vq->vring.num];
 	used->id = head;
 	used->len = len;
@@ -698,9 +774,9 @@ static void add_used_and_trigger(struct virtqueue *vq, unsigned head, int len)
 /*
  * The Console
  *
- * We associate some data with the console for our exit hack. */
-struct console_abort
-{
+ * We associate some data with the console for our exit hack.
+ */
+struct console_abort {
 	/* How many times have they hit ^C? */
 	int count;
 	/* When did they start? */
@@ -715,30 +791,35 @@ static void console_input(struct virtqueue *vq)
 	struct console_abort *abort = vq->dev->priv;
 	struct iovec iov[vq->vring.num];
 
-	/* Make sure there's a descriptor waiting. */
+	/* Make sure there's a descriptor available. */
 	head = wait_for_vq_desc(vq, iov, &out_num, &in_num);
 	if (out_num)
 		errx(1, "Output buffers in console in queue?");
 
-	/* Read it in. */
+	/* Read into it.  This is where we usually wait. */
 	len = readv(STDIN_FILENO, iov, in_num);
 	if (len <= 0) {
 		/* Ran out of input? */
 		warnx("Failed to get console input, ignoring console.");
-		/* For simplicity, dying threads kill the whole Launcher.  So
-		 * just nap here. */
+		/*
+		 * For simplicity, dying threads kill the whole Launcher.  So
+		 * just nap here.
+		 */
 		for (;;)
 			pause();
 	}
 
+	/* Tell the Guest we used a buffer. */
 	add_used_and_trigger(vq, head, len);
 
-	/* Three ^C within one second?  Exit.
+	/*
+	 * Three ^C within one second?  Exit.
 	 *
 	 * This is such a hack, but works surprisingly well.  Each ^C has to
 	 * be in a buffer by itself, so they can't be too fast.  But we check
 	 * that we get three within about a second, so they can't be too
-	 * slow. */
+	 * slow.
+	 */
 	if (len != 1 || ((char *)iov[0].iov_base)[0] != 3) {
 		abort->count = 0;
 		return;
@@ -763,15 +844,23 @@ static void console_output(struct virtqueue *vq)
 	unsigned int head, out, in;
 	struct iovec iov[vq->vring.num];
 
+	/* We usually wait in here, for the Guest to give us something. */
 	head = wait_for_vq_desc(vq, iov, &out, &in);
 	if (in)
 		errx(1, "Input buffers in console output queue?");
+
+	/* writev can return a partial write, so we loop here. */
 	while (!iov_empty(iov, out)) {
 		int len = writev(STDOUT_FILENO, iov, out);
 		if (len <= 0)
 			err(1, "Write to stdout gave %i", len);
 		iov_consume(iov, out, len);
 	}
+
+	/*
+	 * We're finished with that buffer: if we're going to sleep,
+	 * wait_for_vq_desc() will prod the Guest with an interrupt.
+	 */
 	add_used(vq, head, 0);
 }
 
@@ -791,15 +880,30 @@ static void net_output(struct virtqueue *vq)
 	unsigned int head, out, in;
 	struct iovec iov[vq->vring.num];
 
+	/* We usually wait in here for the Guest to give us a packet. */
 	head = wait_for_vq_desc(vq, iov, &out, &in);
 	if (in)
 		errx(1, "Input buffers in net output queue?");
+	/*
+	 * Send the whole thing through to /dev/net/tun.  It expects the exact
+	 * same format: what a coincidence!
+	 */
 	if (writev(net_info->tunfd, iov, out) < 0)
 		errx(1, "Write to tun failed?");
+
+	/*
+	 * Done with that one; wait_for_vq_desc() will send the interrupt if
+	 * all packets are processed.
+	 */
 	add_used(vq, head, 0);
 }
 
-/* Will reading from this file descriptor block? */
+/*
+ * Handling network input is a bit trickier, because I've tried to optimize it.
+ *
+ * First we have a helper routine which tells is if from this file descriptor
+ * (ie. the /dev/net/tun device) will block:
+ */
 static bool will_block(int fd)
 {
 	fd_set fdset;
@@ -809,8 +913,11 @@ static bool will_block(int fd)
 	return select(fd+1, &fdset, NULL, NULL, &zero) != 1;
 }
 
-/* This is where we handle packets coming in from the tun device to our
- * Guest. */
+/*
+ * This handles packets coming in from the tun device to our Guest.  Like all
+ * service routines, it gets called again as soon as it returns, so you don't
+ * see a while(1) loop here.
+ */
 static void net_input(struct virtqueue *vq)
 {
 	int len;
@@ -818,21 +925,38 @@ static void net_input(struct virtqueue *vq)
 	struct iovec iov[vq->vring.num];
 	struct net_info *net_info = vq->dev->priv;
 
+	/*
+	 * Get a descriptor to write an incoming packet into.  This will also
+	 * send an interrupt if they're out of descriptors.
+	 */
 	head = wait_for_vq_desc(vq, iov, &out, &in);
 	if (out)
 		errx(1, "Output buffers in net input queue?");
 
-	/* Deliver interrupt now, since we're about to sleep. */
+	/*
+	 * If it looks like we'll block reading from the tun device, send them
+	 * an interrupt.
+	 */
 	if (vq->pending_used && will_block(net_info->tunfd))
 		trigger_irq(vq);
 
+	/*
+	 * Read in the packet.  This is where we normally wait (when there's no
+	 * incoming network traffic).
+	 */
 	len = readv(net_info->tunfd, iov, in);
 	if (len <= 0)
 		err(1, "Failed to read from tun.");
+
+	/*
+	 * Mark that packet buffer as used, but don't interrupt here.  We want
+	 * to wait until we've done as much work as we can.
+	 */
 	add_used(vq, head, len);
 }
+/*:*/
 
-/* This is the helper to create threads. */
+/* This is the helper to create threads: run the service routine in a loop. */
 static int do_thread(void *_vq)
 {
 	struct virtqueue *vq = _vq;
@@ -842,8 +966,10 @@ static int do_thread(void *_vq)
 	return 0;
 }
 
-/* When a child dies, we kill our entire process group with SIGTERM.  This
- * also has the side effect that the shell restores the console for us! */
+/*
+ * When a child dies, we kill our entire process group with SIGTERM.  This
+ * also has the side effect that the shell restores the console for us!
+ */
 static void kill_launcher(int signal)
 {
 	kill(0, SIGTERM);
@@ -878,11 +1004,15 @@ static void reset_device(struct device *dev)
 	signal(SIGCHLD, (void *)kill_launcher);
 }
 
+/*L:216
+ * This actually creates the thread which services the virtqueue for a device.
+ */
 static void create_thread(struct virtqueue *vq)
 {
-	/* Create stack for thread and run it.  Since stack grows
-	 * upwards, we point the stack pointer to the end of this
-	 * region. */
+	/*
+	 * Create stack for thread.  Since the stack grows upwards, we point
+	 * the stack pointer to the end of this region.
+	 */
 	char *stack = malloc(32768);
 	unsigned long args[] = { LHREQ_EVENTFD,
 				 vq->config.pfn*getpagesize(), 0 };
@@ -893,17 +1023,22 @@ static void create_thread(struct virtqueue *vq)
 		err(1, "Creating eventfd");
 	args[2] = vq->eventfd;
 
-	/* Attach an eventfd to this virtqueue: it will go off
-	 * when the Guest does an LHCALL_NOTIFY for this vq. */
+	/*
+	 * Attach an eventfd to this virtqueue: it will go off when the Guest
+	 * does an LHCALL_NOTIFY for this vq.
+	 */
 	if (write(lguest_fd, &args, sizeof(args)) != 0)
 		err(1, "Attaching eventfd");
 
-	/* CLONE_VM: because it has to access the Guest memory, and
-	 * SIGCHLD so we get a signal if it dies. */
+	/*
+	 * CLONE_VM: because it has to access the Guest memory, and SIGCHLD so
+	 * we get a signal if it dies.
+	 */
 	vq->thread = clone(do_thread, stack + 32768, CLONE_VM | SIGCHLD, vq);
 	if (vq->thread == (pid_t)-1)
 		err(1, "Creating clone");
-	/* We close our local copy, now the child has it. */
+
+	/* We close our local copy now the child has it. */
 	close(vq->eventfd);
 }
 
@@ -955,7 +1090,10 @@ static void update_device_status(struct device *dev)
 	}
 }
 
-/* This is the generic routine we call when the Guest uses LHCALL_NOTIFY. */
+/*L:215
+ * This is the generic routine we call when the Guest uses LHCALL_NOTIFY.  In
+ * particular, it's used to notify us of device status changes during boot.
+ */
 static void handle_output(unsigned long addr)
 {
 	struct device *i;
@@ -964,25 +1102,42 @@ static void handle_output(unsigned long addr)
 	for (i = devices.dev; i; i = i->next) {
 		struct virtqueue *vq;
 
-		/* Notifications to device descriptors update device status. */
+		/*
+		 * Notifications to device descriptors mean they updated the
+		 * device status.
+		 */
 		if (from_guest_phys(addr) == i->desc) {
 			update_device_status(i);
 			return;
 		}
 
-		/* Devices *can* be used before status is set to DRIVER_OK. */
+		/*
+		 * Devices *can* be used before status is set to DRIVER_OK.
+		 * The original plan was that they would never do this: they
+		 * would always finish setting up their status bits before
+		 * actually touching the virtqueues.  In practice, we allowed
+		 * them to, and they do (eg. the disk probes for partition
+		 * tables as part of initialization).
+		 *
+		 * If we see this, we start the device: once it's running, we
+		 * expect the device to catch all the notifications.
+		 */
 		for (vq = i->vq; vq; vq = vq->next) {
 			if (addr != vq->config.pfn*getpagesize())
 				continue;
 			if (i->running)
 				errx(1, "Notification on running %s", i->name);
+			/* This just calls create_thread() for each virtqueue */
 			start_device(i);
 			return;
 		}
 	}
 
-	/* Early console write is done using notify on a nul-terminated string
-	 * in Guest memory. */
+	/*
+	 * Early console write is done using notify on a nul-terminated string
+	 * in Guest memory.  It's also great for hacking debugging messages
+	 * into a Guest.
+	 */
 	if (addr >= guest_limit)
 		errx(1, "Bad NOTIFY %#lx", addr);
 
@@ -998,10 +1153,12 @@ static void handle_output(unsigned long addr)
  * routines to allocate and manage them.
  */
 
-/* The layout of the device page is a "struct lguest_device_desc" followed by a
+/*
+ * The layout of the device page is a "struct lguest_device_desc" followed by a
  * number of virtqueue descriptors, then two sets of feature bits, then an
  * array of configuration bytes.  This routine returns the configuration
- * pointer. */
+ * pointer.
+ */
 static u8 *device_config(const struct device *dev)
 {
 	return (void *)(dev->desc + 1)
@@ -1009,9 +1166,11 @@ static u8 *device_config(const struct device *dev)
 		+ dev->feature_len * 2;
 }
 
-/* This routine allocates a new "struct lguest_device_desc" from descriptor
+/*
+ * This routine allocates a new "struct lguest_device_desc" from descriptor
  * table page just above the Guest's normal memory.  It returns a pointer to
- * that descriptor. */
+ * that descriptor.
+ */
 static struct lguest_device_desc *new_dev_desc(u16 type)
 {
 	struct lguest_device_desc d = { .type = type };
@@ -1032,8 +1191,10 @@ static struct lguest_device_desc *new_dev_desc(u16 type)
 	return memcpy(p, &d, sizeof(d));
 }
 
-/* Each device descriptor is followed by the description of its virtqueues.  We
- * specify how many descriptors the virtqueue is to have. */
+/*
+ * Each device descriptor is followed by the description of its virtqueues.  We
+ * specify how many descriptors the virtqueue is to have.
+ */
 static void add_virtqueue(struct device *dev, unsigned int num_descs,
 			  void (*service)(struct virtqueue *))
 {
@@ -1050,6 +1211,11 @@ static void add_virtqueue(struct device *dev, unsigned int num_descs,
 	vq->next = NULL;
 	vq->last_avail_idx = 0;
 	vq->dev = dev;
+
+	/*
+	 * This is the routine the service thread will run, and its Process ID
+	 * once it's running.
+	 */
 	vq->service = service;
 	vq->thread = (pid_t)-1;
 
@@ -1061,10 +1227,12 @@ static void add_virtqueue(struct device *dev, unsigned int num_descs,
 	/* Initialize the vring. */
 	vring_init(&vq->vring, num_descs, p, LGUEST_VRING_ALIGN);
 
-	/* Append virtqueue to this device's descriptor.  We use
+	/*
+	 * Append virtqueue to this device's descriptor.  We use
 	 * device_config() to get the end of the device's current virtqueues;
 	 * we check that we haven't added any config or feature information
-	 * yet, otherwise we'd be overwriting them. */
+	 * yet, otherwise we'd be overwriting them.
+	 */
 	assert(dev->desc->config_len == 0 && dev->desc->feature_len == 0);
 	memcpy(device_config(dev), &vq->config, sizeof(vq->config));
 	dev->num_vq++;
@@ -1072,14 +1240,18 @@ static void add_virtqueue(struct device *dev, unsigned int num_descs,
 
 	verbose("Virtqueue page %#lx\n", to_guest_phys(p));
 
-	/* Add to tail of list, so dev->vq is first vq, dev->vq->next is
-	 * second.  */
+	/*
+	 * Add to tail of list, so dev->vq is first vq, dev->vq->next is
+	 * second.
+	 */
 	for (i = &dev->vq; *i; i = &(*i)->next);
 	*i = vq;
 }
 
-/* The first half of the feature bitmask is for us to advertise features.  The
- * second half is for the Guest to accept features. */
+/*
+ * The first half of the feature bitmask is for us to advertise features.  The
+ * second half is for the Guest to accept features.
+ */
 static void add_feature(struct device *dev, unsigned bit)
 {
 	u8 *features = get_feature_bits(dev);
@@ -1093,9 +1265,11 @@ static void add_feature(struct device *dev, unsigned bit)
 	features[bit / CHAR_BIT] |= (1 << (bit % CHAR_BIT));
 }
 
-/* This routine sets the configuration fields for an existing device's
+/*
+ * This routine sets the configuration fields for an existing device's
  * descriptor.  It only works for the last device, but that's OK because that's
- * how we use it. */
+ * how we use it.
+ */
 static void set_config(struct device *dev, unsigned len, const void *conf)
 {
 	/* Check we haven't overflowed our single page. */
@@ -1105,12 +1279,18 @@ static void set_config(struct device *dev, unsigned len, const void *conf)
 	/* Copy in the config information, and store the length. */
 	memcpy(device_config(dev), conf, len);
 	dev->desc->config_len = len;
+
+	/* Size must fit in config_len field (8 bits)! */
+	assert(dev->desc->config_len == len);
 }
 
-/* This routine does all the creation and setup of a new device, including
- * calling new_dev_desc() to allocate the descriptor and device memory.
+/*
+ * This routine does all the creation and setup of a new device, including
+ * calling new_dev_desc() to allocate the descriptor and device memory.  We
+ * don't actually start the service threads until later.
  *
- * See what I mean about userspace being boring? */
+ * See what I mean about userspace being boring?
+ */
 static struct device *new_device(const char *name, u16 type)
 {
 	struct device *dev = malloc(sizeof(*dev));
@@ -1123,10 +1303,12 @@ static struct device *new_device(const char *name, u16 type)
 	dev->num_vq = 0;
 	dev->running = false;
 
-	/* Append to device list.  Prepending to a single-linked list is
+	/*
+	 * Append to device list.  Prepending to a single-linked list is
 	 * easier, but the user expects the devices to be arranged on the bus
 	 * in command-line order.  The first network device on the command line
-	 * is eth0, the first block device /dev/vda, etc. */
+	 * is eth0, the first block device /dev/vda, etc.
+	 */
 	if (devices.lastdev)
 		devices.lastdev->next = dev;
 	else
@@ -1136,8 +1318,10 @@ static struct device *new_device(const char *name, u16 type)
 	return dev;
 }
 
-/* Our first setup routine is the console.  It's a fairly simple device, but
- * UNIX tty handling makes it uglier than it could be. */
+/*
+ * Our first setup routine is the console.  It's a fairly simple device, but
+ * UNIX tty handling makes it uglier than it could be.
+ */
 static void setup_console(void)
 {
 	struct device *dev;
@@ -1145,8 +1329,10 @@ static void setup_console(void)
 	/* If we can save the initial standard input settings... */
 	if (tcgetattr(STDIN_FILENO, &orig_term) == 0) {
 		struct termios term = orig_term;
-		/* Then we turn off echo, line buffering and ^C etc.  We want a
-		 * raw input stream to the Guest. */
+		/*
+		 * Then we turn off echo, line buffering and ^C etc: We want a
+		 * raw input stream to the Guest.
+		 */
 		term.c_lflag &= ~(ISIG|ICANON|ECHO);
 		tcsetattr(STDIN_FILENO, TCSANOW, &term);
 	}
@@ -1157,10 +1343,12 @@ static void setup_console(void)
 	dev->priv = malloc(sizeof(struct console_abort));
 	((struct console_abort *)dev->priv)->count = 0;
 
-	/* The console needs two virtqueues: the input then the output.  When
+	/*
+	 * The console needs two virtqueues: the input then the output.  When
 	 * they put something the input queue, we make sure we're listening to
 	 * stdin.  When they put something in the output queue, we write it to
-	 * stdout. */
+	 * stdout.
+	 */
 	add_virtqueue(dev, VIRTQUEUE_NUM, console_input);
 	add_virtqueue(dev, VIRTQUEUE_NUM, console_output);
 
@@ -1168,7 +1356,8 @@ static void setup_console(void)
 }
 /*:*/
 
-/*M:010 Inter-guest networking is an interesting area.  Simplest is to have a
+/*M:010
+ * Inter-guest networking is an interesting area.  Simplest is to have a
  * --sharenet=<name> option which opens or creates a named pipe.  This can be
  * used to send packets to another guest in a 1:1 manner.
  *
@@ -1182,7 +1371,8 @@ static void setup_console(void)
  * multiple inter-guest channels behind one interface, although it would
  * require some manner of hotplugging new virtio channels.
  *
- * Finally, we could implement a virtio network switch in the kernel. :*/
+ * Finally, we could implement a virtio network switch in the kernel.
+:*/
 
 static u32 str2ip(const char *ipaddr)
 {
@@ -1207,11 +1397,13 @@ static void str2mac(const char *macaddr, unsigned char mac[6])
 	mac[5] = m[5];
 }
 
-/* This code is "adapted" from libbridge: it attaches the Host end of the
+/*
+ * This code is "adapted" from libbridge: it attaches the Host end of the
  * network device to the bridge device specified by the command line.
  *
  * This is yet another James Morris contribution (I'm an IP-level guy, so I
- * dislike bridging), and I just try not to break it. */
+ * dislike bridging), and I just try not to break it.
+ */
 static void add_to_bridge(int fd, const char *if_name, const char *br_name)
 {
 	int ifidx;
@@ -1231,9 +1423,11 @@ static void add_to_bridge(int fd, const char *if_name, const char *br_name)
 		err(1, "can't add %s to bridge %s", if_name, br_name);
 }
 
-/* This sets up the Host end of the network device with an IP address, brings
+/*
+ * This sets up the Host end of the network device with an IP address, brings
  * it up so packets will flow, the copies the MAC address into the hwaddr
- * pointer. */
+ * pointer.
+ */
 static void configure_device(int fd, const char *tapif, u32 ipaddr)
 {
 	struct ifreq ifr;
@@ -1260,10 +1454,12 @@ static int get_tun_device(char tapif[IFNAMSIZ])
 	/* Start with this zeroed.  Messy but sure. */
 	memset(&ifr, 0, sizeof(ifr));
 
-	/* We open the /dev/net/tun device and tell it we want a tap device.  A
+	/*
+	 * We open the /dev/net/tun device and tell it we want a tap device.  A
 	 * tap device is like a tun device, only somehow different.  To tell
 	 * the truth, I completely blundered my way through this code, but it
-	 * works now! */
+	 * works now!
+	 */
 	netfd = open_or_die("/dev/net/tun", O_RDWR);
 	ifr.ifr_flags = IFF_TAP | IFF_NO_PI | IFF_VNET_HDR;
 	strcpy(ifr.ifr_name, "tap%d");
@@ -1274,18 +1470,22 @@ static int get_tun_device(char tapif[IFNAMSIZ])
 		  TUN_F_CSUM|TUN_F_TSO4|TUN_F_TSO6|TUN_F_TSO_ECN) != 0)
 		err(1, "Could not set features for tun device");
 
-	/* We don't need checksums calculated for packets coming in this
-	 * device: trust us! */
+	/*
+	 * We don't need checksums calculated for packets coming in this
+	 * device: trust us!
+	 */
 	ioctl(netfd, TUNSETNOCSUM, 1);
 
 	memcpy(tapif, ifr.ifr_name, IFNAMSIZ);
 	return netfd;
 }
 
-/*L:195 Our network is a Host<->Guest network.  This can either use bridging or
+/*L:195
+ * Our network is a Host<->Guest network.  This can either use bridging or
  * routing, but the principle is the same: it uses the "tun" device to inject
  * packets into the Host as if they came in from a normal network card.  We
- * just shunt packets between the Guest and the tun device. */
+ * just shunt packets between the Guest and the tun device.
+ */
 static void setup_tun_net(char *arg)
 {
 	struct device *dev;
@@ -1302,13 +1502,14 @@ static void setup_tun_net(char *arg)
 	dev = new_device("net", VIRTIO_ID_NET);
 	dev->priv = net_info;
 
-	/* Network devices need a receive and a send queue, just like
-	 * console. */
+	/* Network devices need a recv and a send queue, just like console. */
 	add_virtqueue(dev, VIRTQUEUE_NUM, net_input);
 	add_virtqueue(dev, VIRTQUEUE_NUM, net_output);
 
-	/* We need a socket to perform the magic network ioctls to bring up the
-	 * tap interface, connect to the bridge etc.  Any socket will do! */
+	/*
+	 * We need a socket to perform the magic network ioctls to bring up the
+	 * tap interface, connect to the bridge etc.  Any socket will do!
+	 */
 	ipfd = socket(PF_INET, SOCK_DGRAM, IPPROTO_IP);
 	if (ipfd < 0)
 		err(1, "opening IP socket");
@@ -1362,39 +1563,31 @@ static void setup_tun_net(char *arg)
 		verbose("device %u: tun %s: %s\n",
 			devices.device_num, tapif, arg);
 }
-
-/* Our block (disk) device should be really simple: the Guest asks for a block
- * number and we read or write that position in the file.  Unfortunately, that
- * was amazingly slow: the Guest waits until the read is finished before
- * running anything else, even if it could have been doing useful work.
- *
- * We could use async I/O, except it's reputed to suck so hard that characters
- * actually go missing from your code when you try to use it.
- *
- * So we farm the I/O out to thread, and communicate with it via a pipe. */
+/*:*/
 
 /* This hangs off device->priv. */
-struct vblk_info
-{
+struct vblk_info {
 	/* The size of the file. */
 	off64_t len;
 
 	/* The file descriptor for the file. */
 	int fd;
 
-	/* IO thread listens on this file descriptor [0]. */
-	int workpipe[2];
-
-	/* IO thread writes to this file descriptor to mark it done, then
-	 * Launcher triggers interrupt to Guest. */
-	int done_fd;
 };
 
 /*L:210
  * The Disk
  *
- * Remember that the block device is handled by a separate I/O thread.  We head
- * straight into the core of that thread here:
+ * The disk only has one virtqueue, so it only has one thread.  It is really
+ * simple: the Guest asks for a block number and we read or write that position
+ * in the file.
+ *
+ * Before we serviced each virtqueue in a separate thread, that was unacceptably
+ * slow: the Guest waits until the read is finished before running anything
+ * else, even if it could have been doing useful work.
+ *
+ * We could have used async I/O, except it's reputed to suck so hard that
+ * characters actually go missing from your code when you try to use it.
  */
 static void blk_request(struct virtqueue *vq)
 {
@@ -1406,47 +1599,64 @@ static void blk_request(struct virtqueue *vq)
 	struct iovec iov[vq->vring.num];
 	off64_t off;
 
-	/* Get the next request. */
+	/*
+	 * Get the next request, where we normally wait.  It triggers the
+	 * interrupt to acknowledge previously serviced requests (if any).
+	 */
 	head = wait_for_vq_desc(vq, iov, &out_num, &in_num);
 
-	/* Every block request should contain at least one output buffer
+	/*
+	 * Every block request should contain at least one output buffer
 	 * (detailing the location on disk and the type of request) and one
-	 * input buffer (to hold the result). */
+	 * input buffer (to hold the result).
+	 */
 	if (out_num == 0 || in_num == 0)
 		errx(1, "Bad virtblk cmd %u out=%u in=%u",
 		     head, out_num, in_num);
 
 	out = convert(&iov[0], struct virtio_blk_outhdr);
 	in = convert(&iov[out_num+in_num-1], u8);
+	/*
+	 * For historical reasons, block operations are expressed in 512 byte
+	 * "sectors".
+	 */
 	off = out->sector * 512;
 
-	/* The block device implements "barriers", where the Guest indicates
+	/*
+	 * The block device implements "barriers", where the Guest indicates
 	 * that it wants all previous writes to occur before this write.  We
 	 * don't have a way of asking our kernel to do a barrier, so we just
-	 * synchronize all the data in the file.  Pretty poor, no? */
+	 * synchronize all the data in the file.  Pretty poor, no?
+	 */
 	if (out->type & VIRTIO_BLK_T_BARRIER)
 		fdatasync(vblk->fd);
 
-	/* In general the virtio block driver is allowed to try SCSI commands.
-	 * It'd be nice if we supported eject, for example, but we don't. */
+	/*
+	 * In general the virtio block driver is allowed to try SCSI commands.
+	 * It'd be nice if we supported eject, for example, but we don't.
+	 */
 	if (out->type & VIRTIO_BLK_T_SCSI_CMD) {
 		fprintf(stderr, "Scsi commands unsupported\n");
 		*in = VIRTIO_BLK_S_UNSUPP;
 		wlen = sizeof(*in);
 	} else if (out->type & VIRTIO_BLK_T_OUT) {
-		/* Write */
-
-		/* Move to the right location in the block file.  This can fail
-		 * if they try to write past end. */
+		/*
+		 * Write
+		 *
+		 * Move to the right location in the block file.  This can fail
+		 * if they try to write past end.
+		 */
 		if (lseek64(vblk->fd, off, SEEK_SET) != off)
 			err(1, "Bad seek to sector %llu", out->sector);
 
 		ret = writev(vblk->fd, iov+1, out_num-1);
 		verbose("WRITE to sector %llu: %i\n", out->sector, ret);
 
-		/* Grr... Now we know how long the descriptor they sent was, we
+		/*
+		 * Grr... Now we know how long the descriptor they sent was, we
 		 * make sure they didn't try to write over the end of the block
-		 * file (possibly extending it). */
+		 * file (possibly extending it).
+		 */
 		if (ret > 0 && off + ret > vblk->len) {
 			/* Trim it back to the correct length */
 			ftruncate64(vblk->fd, vblk->len);
@@ -1456,10 +1666,12 @@ static void blk_request(struct virtqueue *vq)
 		wlen = sizeof(*in);
 		*in = (ret >= 0 ? VIRTIO_BLK_S_OK : VIRTIO_BLK_S_IOERR);
 	} else {
-		/* Read */
-
-		/* Move to the right location in the block file.  This can fail
-		 * if they try to read past end. */
+		/*
+		 * Read
+		 *
+		 * Move to the right location in the block file.  This can fail
+		 * if they try to read past end.
+		 */
 		if (lseek64(vblk->fd, off, SEEK_SET) != off)
 			err(1, "Bad seek to sector %llu", out->sector);
 
@@ -1474,13 +1686,16 @@ static void blk_request(struct virtqueue *vq)
 		}
 	}
 
-	/* OK, so we noted that it was pretty poor to use an fdatasync as a
+	/*
+	 * OK, so we noted that it was pretty poor to use an fdatasync as a
 	 * barrier.  But Christoph Hellwig points out that we need a sync
 	 * *afterwards* as well: "Barriers specify no reordering to the front
-	 * or the back."  And Jens Axboe confirmed it, so here we are: */
+	 * or the back."  And Jens Axboe confirmed it, so here we are:
+	 */
 	if (out->type & VIRTIO_BLK_T_BARRIER)
 		fdatasync(vblk->fd);
 
+	/* Finished that request. */
 	add_used(vq, head, wlen);
 }
 
@@ -1491,7 +1706,7 @@ static void setup_block_file(const char *filename)
 	struct vblk_info *vblk;
 	struct virtio_blk_config conf;
 
-	/* The device responds to return from I/O thread. */
+	/* Creat the device. */
 	dev = new_device("block", VIRTIO_ID_BLOCK);
 
 	/* The device has one virtqueue, where the Guest places requests. */
@@ -1510,27 +1725,32 @@ static void setup_block_file(const char *filename)
 	/* Tell Guest how many sectors this device has. */
 	conf.capacity = cpu_to_le64(vblk->len / 512);
 
-	/* Tell Guest not to put in too many descriptors at once: two are used
-	 * for the in and out elements. */
+	/*
+	 * Tell Guest not to put in too many descriptors at once: two are used
+	 * for the in and out elements.
+	 */
 	add_feature(dev, VIRTIO_BLK_F_SEG_MAX);
 	conf.seg_max = cpu_to_le32(VIRTQUEUE_NUM - 2);
 
-	set_config(dev, sizeof(conf), &conf);
+	/* Don't try to put whole struct: we have 8 bit limit. */
+	set_config(dev, offsetof(struct virtio_blk_config, geometry), &conf);
 
 	verbose("device %u: virtblock %llu sectors\n",
 		++devices.device_num, le64_to_cpu(conf.capacity));
 }
 
-struct rng_info {
-	int rfd;
-};
-
-/* Our random number generator device reads from /dev/random into the Guest's
+/*L:211
+ * Our random number generator device reads from /dev/random into the Guest's
  * input buffers.  The usual case is that the Guest doesn't want random numbers
  * and so has no buffers although /dev/random is still readable, whereas
  * console is the reverse.
  *
- * The same logic applies, however. */
+ * The same logic applies, however.
+ */
+struct rng_info {
+	int rfd;
+};
+
 static void rng_input(struct virtqueue *vq)
 {
 	int len;
@@ -1543,9 +1763,10 @@ static void rng_input(struct virtqueue *vq)
 	if (out_num)
 		errx(1, "Output buffers in rng?");
 
-	/* This is why we convert to iovecs: the readv() call uses them, and so
-	 * it reads straight into the Guest's buffer.  We loop to make sure we
-	 * fill it. */
+	/*
+	 * Just like the console write, we loop to cover the whole iovec.
+	 * In this case, short reads actually happen quite a bit.
+	 */
 	while (!iov_empty(iov, in_num)) {
 		len = readv(rng_info->rfd, iov, in_num);
 		if (len <= 0)
@@ -1558,15 +1779,18 @@ static void rng_input(struct virtqueue *vq)
 	add_used(vq, head, totlen);
 }
 
-/* And this creates a "hardware" random number device for the Guest. */
+/*L:199
+ * This creates a "hardware" random number device for the Guest.
+ */
 static void setup_rng(void)
 {
 	struct device *dev;
 	struct rng_info *rng_info = malloc(sizeof(*rng_info));
 
+	/* Our device's privat info simply contains the /dev/random fd. */
 	rng_info->rfd = open_or_die("/dev/random", O_RDONLY);
 
-	/* The device responds to return from I/O thread. */
+	/* Create the new device. */
 	dev = new_device("rng", VIRTIO_ID_RNG);
 	dev->priv = rng_info;
 
@@ -1582,8 +1806,10 @@ static void __attribute__((noreturn)) restart_guest(void)
 {
 	unsigned int i;
 
-	/* Since we don't track all open fds, we simply close everything beyond
-	 * stderr. */
+	/*
+	 * Since we don't track all open fds, we simply close everything beyond
+	 * stderr.
+	 */
 	for (i = 3; i < FD_SETSIZE; i++)
 		close(i);
 
@@ -1594,8 +1820,10 @@ static void __attribute__((noreturn)) restart_guest(void)
 	err(1, "Could not exec %s", main_args[0]);
 }
 
-/*L:220 Finally we reach the core of the Launcher which runs the Guest, serves
- * its input and output, and finally, lays it to rest. */
+/*L:220
+ * Finally we reach the core of the Launcher which runs the Guest, serves
+ * its input and output, and finally, lays it to rest.
+ */
 static void __attribute__((noreturn)) run_guest(void)
 {
 	for (;;) {
@@ -1630,7 +1858,7 @@ static void __attribute__((noreturn)) run_guest(void)
  *
  * Are you ready?  Take a deep breath and join me in the core of the Host, in
  * "make Host".
- :*/
+:*/
 
 static struct option opts[] = {
 	{ "verbose", 0, NULL, 'v' },
@@ -1651,8 +1879,7 @@ static void usage(void)
 /*L:105 The main routine is where the real work begins: */
 int main(int argc, char *argv[])
 {
-	/* Memory, top-level pagetable, code startpoint and size of the
-	 * (optional) initrd. */
+	/* Memory, code startpoint and size of the (optional) initrd. */
 	unsigned long mem = 0, start, initrd_size = 0;
 	/* Two temporaries. */
 	int i, c;
@@ -1664,24 +1891,32 @@ int main(int argc, char *argv[])
 	/* Save the args: we "reboot" by execing ourselves again. */
 	main_args = argv;
 
-	/* First we initialize the device list.  We keep a pointer to the last
+	/*
+	 * First we initialize the device list.  We keep a pointer to the last
 	 * device, and the next interrupt number to use for devices (1:
-	 * remember that 0 is used by the timer). */
+	 * remember that 0 is used by the timer).
+	 */
 	devices.lastdev = NULL;
 	devices.next_irq = 1;
 
+	/* We're CPU 0.  In fact, that's the only CPU possible right now. */
 	cpu_id = 0;
-	/* We need to know how much memory so we can set up the device
+
+	/*
+	 * We need to know how much memory so we can set up the device
 	 * descriptor and memory pages for the devices as we parse the command
 	 * line.  So we quickly look through the arguments to find the amount
-	 * of memory now. */
+	 * of memory now.
+	 */
 	for (i = 1; i < argc; i++) {
 		if (argv[i][0] != '-') {
 			mem = atoi(argv[i]) * 1024 * 1024;
-			/* We start by mapping anonymous pages over all of
+			/*
+			 * We start by mapping anonymous pages over all of
 			 * guest-physical memory range.  This fills it with 0,
 			 * and ensures that the Guest won't be killed when it
-			 * tries to access it. */
+			 * tries to access it.
+			 */
 			guest_base = map_zeroed_pages(mem / getpagesize()
 						      + DEVICE_PAGES);
 			guest_limit = mem;
@@ -1714,8 +1949,10 @@ int main(int argc, char *argv[])
 			usage();
 		}
 	}
-	/* After the other arguments we expect memory and kernel image name,
-	 * followed by command line arguments for the kernel. */
+	/*
+	 * After the other arguments we expect memory and kernel image name,
+	 * followed by command line arguments for the kernel.
+	 */
 	if (optind + 2 > argc)
 		usage();
 
@@ -1733,20 +1970,26 @@ int main(int argc, char *argv[])
 	/* Map the initrd image if requested (at top of physical memory) */
 	if (initrd_name) {
 		initrd_size = load_initrd(initrd_name, mem);
-		/* These are the location in the Linux boot header where the
-		 * start and size of the initrd are expected to be found. */
+		/*
+		 * These are the location in the Linux boot header where the
+		 * start and size of the initrd are expected to be found.
+		 */
 		boot->hdr.ramdisk_image = mem - initrd_size;
 		boot->hdr.ramdisk_size = initrd_size;
 		/* The bootloader type 0xFF means "unknown"; that's OK. */
 		boot->hdr.type_of_loader = 0xFF;
 	}
 
-	/* The Linux boot header contains an "E820" memory map: ours is a
-	 * simple, single region. */
+	/*
+	 * The Linux boot header contains an "E820" memory map: ours is a
+	 * simple, single region.
+	 */
 	boot->e820_entries = 1;
 	boot->e820_map[0] = ((struct e820entry) { 0, mem, E820_RAM });
-	/* The boot header contains a command line pointer: we put the command
-	 * line after the boot header. */
+	/*
+	 * The boot header contains a command line pointer: we put the command
+	 * line after the boot header.
+	 */
 	boot->hdr.cmd_line_ptr = to_guest_phys(boot + 1);
 	/* We use a simple helper to copy the arguments separated by spaces. */
 	concat((char *)(boot + 1), argv+optind+2);
@@ -1760,11 +2003,13 @@ int main(int argc, char *argv[])
 	/* Tell the entry path not to try to reload segment registers. */
 	boot->hdr.loadflags |= KEEP_SEGMENTS;
 
-	/* We tell the kernel to initialize the Guest: this returns the open
-	 * /dev/lguest file descriptor. */
+	/*
+	 * We tell the kernel to initialize the Guest: this returns the open
+	 * /dev/lguest file descriptor.
+	 */
 	tell_kernel(start);
 
-	/* Ensure that we terminate if a child dies. */
+	/* Ensure that we terminate if a device-servicing child dies. */
 	signal(SIGCHLD, kill_launcher);
 
 	/* If we exit via err(), this kills all the threads, restores tty. */
diff --git a/Documentation/lockdep-design.txt b/Documentation/lockdep-design.txt
index e20d913d5914..abf768c681e2 100644
--- a/Documentation/lockdep-design.txt
+++ b/Documentation/lockdep-design.txt
@@ -30,9 +30,9 @@ State
 The validator tracks lock-class usage history into 4n + 1 separate state bits:
 
 - 'ever held in STATE context'
-- 'ever head as readlock in STATE context'
-- 'ever head with STATE enabled'
-- 'ever head as readlock with STATE enabled'
+- 'ever held as readlock in STATE context'
+- 'ever held with STATE enabled'
+- 'ever held as readlock with STATE enabled'
 
 Where STATE can be either one of (kernel/lockdep_states.h)
  - hardirq
diff --git a/Documentation/scheduler/sched-rt-group.txt b/Documentation/scheduler/sched-rt-group.txt
index 1df7f9cdab05..86eabe6c3419 100644
--- a/Documentation/scheduler/sched-rt-group.txt
+++ b/Documentation/scheduler/sched-rt-group.txt
@@ -73,7 +73,7 @@ The remaining CPU time will be used for user input and other tasks. Because
 realtime tasks have explicitly allocated the CPU time they need to perform
 their tasks, buffer underruns in the graphics or audio can be eliminated.
 
-NOTE: the above example is not fully implemented as of yet (2.6.25). We still
+NOTE: the above example is not fully implemented yet. We still
 lack an EDF scheduler to make non-uniform periods usable.
 
 
@@ -140,14 +140,15 @@ The other option is:
 
 .o CONFIG_CGROUP_SCHED (aka "Basis for grouping tasks" = "Control groups")
 
-This uses the /cgroup virtual file system and "/cgroup/<cgroup>/cpu.rt_runtime_us"
-to control the CPU time reserved for each control group instead.
+This uses the /cgroup virtual file system and
+"/cgroup/<cgroup>/cpu.rt_runtime_us" to control the CPU time reserved for each
+control group instead.
 
 For more information on working with control groups, you should read
 Documentation/cgroups/cgroups.txt as well.
 
-Group settings are checked against the following limits in order to keep the configuration
-schedulable:
+Group settings are checked against the following limits in order to keep the
+configuration schedulable:
 
    \Sum_{i} runtime_{i} / global_period <= global_runtime / global_period
 
@@ -189,7 +190,7 @@ Implementing SCHED_EDF might take a while to complete. Priority Inheritance is
 the biggest challenge as the current linux PI infrastructure is geared towards
 the limited static priority levels 0-99. With deadline scheduling you need to
 do deadline inheritance (since priority is inversely proportional to the
-deadline delta (deadline - now).
+deadline delta (deadline - now)).
 
 This means the whole PI machinery will have to be reworked - and that is one of
 the most complex pieces of code we have.
diff --git a/Documentation/sound/alsa/Procfile.txt b/Documentation/sound/alsa/Procfile.txt
index 381908d8ca42..719a819f8cc2 100644
--- a/Documentation/sound/alsa/Procfile.txt
+++ b/Documentation/sound/alsa/Procfile.txt
@@ -101,6 +101,8 @@ card*/pcm*/xrun_debug
 	  bit 0 = Enable XRUN/jiffies debug messages
 	  bit 1 = Show stack trace at XRUN / jiffies check
 	  bit 2 = Enable additional jiffies check
+	  bit 3 = Log hwptr update at each period interrupt
+	  bit 4 = Log hwptr update at each snd_pcm_update_hw_ptr()
 
 	When the bit 0 is set, the driver will show the messages to
 	kernel log when an xrun is detected.  The debug message is
@@ -117,6 +119,9 @@ card*/pcm*/xrun_debug
 	buggy) hardware that doesn't give smooth pointer updates.
 	This feature is enabled via the bit 2.
 
+	Bits 3 and 4 are for logging the hwptr records.  Note that
+	these will give flood of kernel messages.
+
 card*/pcm*/sub*/info
 	The general information of this PCM sub-stream.
 
diff --git a/Documentation/sysrq.txt b/Documentation/sysrq.txt
index cf42b820ff9d..d56a01775423 100644
--- a/Documentation/sysrq.txt
+++ b/Documentation/sysrq.txt
@@ -66,7 +66,8 @@ On all -  write a character to /proc/sysrq-trigger.  e.g.:
 'b'     - Will immediately reboot the system without syncing or unmounting
           your disks.
 
-'c'	- Will perform a kexec reboot in order to take a crashdump.
+'c'	- Will perform a system crash by a NULL pointer dereference.
+          A crashdump will be taken if configured.
 
 'd'	- Shows all locks that are held.
 
@@ -141,8 +142,8 @@ useful when you want to exit a program that will not let you switch consoles.
 re'B'oot is good when you're unable to shut down. But you should also 'S'ync
 and 'U'mount first.
 
-'C'rashdump can be used to manually trigger a crashdump when the system is hung.
-The kernel needs to have been built with CONFIG_KEXEC enabled.
+'C'rash can be used to manually trigger a crashdump when the system is hung.
+Note that this just triggers a crash if there is no dump mechanism available.
 
 'S'ync is great when your system is locked up, it allows you to sync your
 disks and will certainly lessen the chance of data loss and fscking. Note
diff --git a/Documentation/video4linux/CARDLIST.em28xx b/Documentation/video4linux/CARDLIST.em28xx
index 873630e7e53e..68c236c01846 100644
--- a/Documentation/video4linux/CARDLIST.em28xx
+++ b/Documentation/video4linux/CARDLIST.em28xx
@@ -20,7 +20,7 @@
  19 -> EM2860/SAA711X Reference Design          (em2860)
  20 -> AMD ATI TV Wonder HD 600                 (em2880)        [0438:b002]
  21 -> eMPIA Technology, Inc. GrabBeeX+ Video Encoder (em2800)        [eb1a:2801]
- 22 -> Unknown EM2750/EM2751 webcam grabber     (em2750)        [eb1a:2750,eb1a:2751]
+ 22 -> EM2710/EM2750/EM2751 webcam grabber      (em2750)        [eb1a:2750,eb1a:2751]
  23 -> Huaqi DLCW-130                           (em2750)
  24 -> D-Link DUB-T210 TV Tuner                 (em2820/em2840) [2001:f112]
  25 -> Gadmei UTV310                            (em2820/em2840)
@@ -66,3 +66,4 @@
  68 -> Terratec AV350                           (em2860)        [0ccd:0084]
  69 -> KWorld ATSC 315U HDTV TV Box             (em2882)        [eb1a:a313]
  70 -> Evga inDtube                             (em2882)
+ 71 -> Silvercrest Webcam 1.3mpix               (em2820/em2840)
diff --git a/Documentation/video4linux/gspca.txt b/Documentation/video4linux/gspca.txt
index 2bcf78896e22..573f95b58807 100644
--- a/Documentation/video4linux/gspca.txt
+++ b/Documentation/video4linux/gspca.txt
@@ -44,7 +44,9 @@ zc3xx		0458:7007	Genius VideoCam V2
 zc3xx		0458:700c	Genius VideoCam V3
 zc3xx		0458:700f	Genius VideoCam Web V2
 sonixj		0458:7025	Genius Eye 311Q
+sn9c20x		0458:7029	Genius Look 320s
 sonixj		0458:702e	Genius Slim 310 NB
+sn9c20x		045e:00f4	LifeCam VX-6000 (SN9C20x + OV9650)
 sonixj		045e:00f5	MicroSoft VX3000
 sonixj		045e:00f7	MicroSoft VX1000
 ov519		045e:028c	Micro$oft xbox cam
@@ -282,6 +284,28 @@ sonixj		0c45:613a	Microdia Sonix PC Camera
 sonixj		0c45:613b	Surfer SN-206
 sonixj		0c45:613c	Sonix Pccam168
 sonixj		0c45:6143	Sonix Pccam168
+sn9c20x		0c45:6240	PC Camera (SN9C201 + MT9M001)
+sn9c20x		0c45:6242	PC Camera (SN9C201 + MT9M111)
+sn9c20x		0c45:6248	PC Camera (SN9C201 + OV9655)
+sn9c20x		0c45:624e	PC Camera (SN9C201 + SOI968)
+sn9c20x		0c45:624f	PC Camera (SN9C201 + OV9650)
+sn9c20x		0c45:6251	PC Camera (SN9C201 + OV9650)
+sn9c20x		0c45:6253	PC Camera (SN9C201 + OV9650)
+sn9c20x		0c45:6260	PC Camera (SN9C201 + OV7670)
+sn9c20x		0c45:6270	PC Camera (SN9C201 + MT9V011/MT9V111/MT9V112)
+sn9c20x		0c45:627b	PC Camera (SN9C201 + OV7660)
+sn9c20x		0c45:627c	PC Camera (SN9C201 + HV7131R)
+sn9c20x		0c45:627f	PC Camera (SN9C201 + OV9650)
+sn9c20x		0c45:6280	PC Camera (SN9C202 + MT9M001)
+sn9c20x		0c45:6282	PC Camera (SN9C202 + MT9M111)
+sn9c20x		0c45:6288	PC Camera (SN9C202 + OV9655)
+sn9c20x		0c45:628e	PC Camera (SN9C202 + SOI968)
+sn9c20x		0c45:628f	PC Camera (SN9C202 + OV9650)
+sn9c20x		0c45:62a0	PC Camera (SN9C202 + OV7670)
+sn9c20x		0c45:62b0	PC Camera (SN9C202 + MT9V011/MT9V111/MT9V112)
+sn9c20x		0c45:62b3	PC Camera (SN9C202 + OV9655)
+sn9c20x		0c45:62bb	PC Camera (SN9C202 + OV7660)
+sn9c20x		0c45:62bc	PC Camera (SN9C202 + HV7131R)
 sunplus		0d64:0303	Sunplus FashionCam DXG
 etoms		102c:6151	Qcam Sangha CIF
 etoms		102c:6251	Qcam xxxxxx VGA
@@ -290,6 +314,7 @@ spca561		10fd:7e50	FlyCam Usb 100
 zc3xx		10fd:8050	Typhoon Webshot II USB 300k
 ov534		1415:2000	Sony HD Eye for PS3 (SLEH 00201)
 pac207		145f:013a	Trust WB-1300N
+sn9c20x		145f:013d	Trust WB-3600R
 vc032x		15b8:6001	HP 2.0 Megapixel
 vc032x		15b8:6002	HP 2.0 Megapixel rz406aa
 spca501		1776:501c	Arowana 300K CMOS Camera
@@ -300,4 +325,11 @@ spca500		2899:012c	Toptro Industrial
 spca508		8086:0110	Intel Easy PC Camera
 spca500		8086:0630	Intel Pocket PC Camera
 spca506		99fa:8988	Grandtec V.cap
+sn9c20x		a168:0610	Dino-Lite Digital Microscope (SN9C201 + HV7131R)
+sn9c20x		a168:0611	Dino-Lite Digital Microscope (SN9C201 + HV7131R)
+sn9c20x		a168:0613	Dino-Lite Digital Microscope (SN9C201 + HV7131R)
+sn9c20x		a168:0618	Dino-Lite Digital Microscope (SN9C201 + HV7131R)
+sn9c20x		a168:0614	Dino-Lite Digital Microscope (SN9C201 + MT9M111)
+sn9c20x		a168:0615	Dino-Lite Digital Microscope (SN9C201 + MT9M111)
+sn9c20x		a168:0617	Dino-Lite Digital Microscope (SN9C201 + MT9M111)
 spca561		abcd:cdee	Petcam
diff --git a/Documentation/x86/00-INDEX b/Documentation/x86/00-INDEX
index dbe3377754af..f37b46d34861 100644
--- a/Documentation/x86/00-INDEX
+++ b/Documentation/x86/00-INDEX
@@ -2,3 +2,5 @@
 	- this file
 mtrr.txt
 	- how to use x86 Memory Type Range Registers to increase performance
+exception-tables.txt
+	- why and how Linux kernel uses exception tables on x86
diff --git a/Documentation/exception.txt b/Documentation/x86/exception-tables.txt
index 2d5aded64247..32901aa36f0a 100644
--- a/Documentation/exception.txt
+++ b/Documentation/x86/exception-tables.txt
@@ -1,123 +1,123 @@
-     Kernel level exception handling in Linux 2.1.8
+     Kernel level exception handling in Linux
   Commentary by Joerg Pommnitz <joerg@raleigh.ibm.com>
 
-When a process runs in kernel mode, it often has to access user 
-mode memory whose address has been passed by an untrusted program. 
+When a process runs in kernel mode, it often has to access user
+mode memory whose address has been passed by an untrusted program.
 To protect itself the kernel has to verify this address.
 
-In older versions of Linux this was done with the 
-int verify_area(int type, const void * addr, unsigned long size) 
+In older versions of Linux this was done with the
+int verify_area(int type, const void * addr, unsigned long size)
 function (which has since been replaced by access_ok()).
 
-This function verified that the memory area starting at address 
+This function verified that the memory area starting at address
 'addr' and of size 'size' was accessible for the operation specified
-in type (read or write). To do this, verify_read had to look up the 
-virtual memory area (vma) that contained the address addr. In the 
-normal case (correctly working program), this test was successful. 
+in type (read or write). To do this, verify_read had to look up the
+virtual memory area (vma) that contained the address addr. In the
+normal case (correctly working program), this test was successful.
 It only failed for a few buggy programs. In some kernel profiling
 tests, this normally unneeded verification used up a considerable
 amount of time.
 
-To overcome this situation, Linus decided to let the virtual memory 
+To overcome this situation, Linus decided to let the virtual memory
 hardware present in every Linux-capable CPU handle this test.
 
 How does this work?
 
-Whenever the kernel tries to access an address that is currently not 
-accessible, the CPU generates a page fault exception and calls the 
-page fault handler 
+Whenever the kernel tries to access an address that is currently not
+accessible, the CPU generates a page fault exception and calls the
+page fault handler
 
 void do_page_fault(struct pt_regs *regs, unsigned long error_code)
 
-in arch/i386/mm/fault.c. The parameters on the stack are set up by 
-the low level assembly glue in arch/i386/kernel/entry.S. The parameter
-regs is a pointer to the saved registers on the stack, error_code 
+in arch/x86/mm/fault.c. The parameters on the stack are set up by
+the low level assembly glue in arch/x86/kernel/entry_32.S. The parameter
+regs is a pointer to the saved registers on the stack, error_code
 contains a reason code for the exception.
 
-do_page_fault first obtains the unaccessible address from the CPU 
-control register CR2. If the address is within the virtual address 
-space of the process, the fault probably occurred, because the page 
-was not swapped in, write protected or something similar. However, 
-we are interested in the other case: the address is not valid, there 
-is no vma that contains this address. In this case, the kernel jumps 
-to the bad_area label. 
-
-There it uses the address of the instruction that caused the exception 
-(i.e. regs->eip) to find an address where the execution can continue 
-(fixup). If this search is successful, the fault handler modifies the 
-return address (again regs->eip) and returns. The execution will 
+do_page_fault first obtains the unaccessible address from the CPU
+control register CR2. If the address is within the virtual address
+space of the process, the fault probably occurred, because the page
+was not swapped in, write protected or something similar. However,
+we are interested in the other case: the address is not valid, there
+is no vma that contains this address. In this case, the kernel jumps
+to the bad_area label.
+
+There it uses the address of the instruction that caused the exception
+(i.e. regs->eip) to find an address where the execution can continue
+(fixup). If this search is successful, the fault handler modifies the
+return address (again regs->eip) and returns. The execution will
 continue at the address in fixup.
 
 Where does fixup point to?
 
-Since we jump to the contents of fixup, fixup obviously points 
-to executable code. This code is hidden inside the user access macros. 
-I have picked the get_user macro defined in include/asm/uaccess.h as an
-example. The definition is somewhat hard to follow, so let's peek at 
+Since we jump to the contents of fixup, fixup obviously points
+to executable code. This code is hidden inside the user access macros.
+I have picked the get_user macro defined in arch/x86/include/asm/uaccess.h
+as an example. The definition is somewhat hard to follow, so let's peek at
 the code generated by the preprocessor and the compiler. I selected
-the get_user call in drivers/char/console.c for a detailed examination.
+the get_user call in drivers/char/sysrq.c for a detailed examination.
 
-The original code in console.c line 1405:
+The original code in sysrq.c line 587:
         get_user(c, buf);
 
 The preprocessor output (edited to become somewhat readable):
 
 (
-  {        
-    long __gu_err = - 14 , __gu_val = 0;        
-    const __typeof__(*( (  buf ) )) *__gu_addr = ((buf));        
-    if (((((0 + current_set[0])->tss.segment) == 0x18 )  || 
-       (((sizeof(*(buf))) <= 0xC0000000UL) && 
-       ((unsigned long)(__gu_addr ) <= 0xC0000000UL - (sizeof(*(buf)))))))        
+  {
+    long __gu_err = - 14 , __gu_val = 0;
+    const __typeof__(*( (  buf ) )) *__gu_addr = ((buf));
+    if (((((0 + current_set[0])->tss.segment) == 0x18 )  ||
+       (((sizeof(*(buf))) <= 0xC0000000UL) &&
+       ((unsigned long)(__gu_addr ) <= 0xC0000000UL - (sizeof(*(buf)))))))
       do {
-        __gu_err  = 0;        
-        switch ((sizeof(*(buf)))) {        
-          case 1: 
-            __asm__ __volatile__(        
-              "1:      mov" "b" " %2,%" "b" "1\n"        
-              "2:\n"        
-              ".section .fixup,\"ax\"\n"        
-              "3:      movl %3,%0\n"        
-              "        xor" "b" " %" "b" "1,%" "b" "1\n"        
-              "        jmp 2b\n"        
-              ".section __ex_table,\"a\"\n"        
-              "        .align 4\n"        
-              "        .long 1b,3b\n"        
+        __gu_err  = 0;
+        switch ((sizeof(*(buf)))) {
+          case 1:
+            __asm__ __volatile__(
+              "1:      mov" "b" " %2,%" "b" "1\n"
+              "2:\n"
+              ".section .fixup,\"ax\"\n"
+              "3:      movl %3,%0\n"
+              "        xor" "b" " %" "b" "1,%" "b" "1\n"
+              "        jmp 2b\n"
+              ".section __ex_table,\"a\"\n"
+              "        .align 4\n"
+              "        .long 1b,3b\n"
               ".text"        : "=r"(__gu_err), "=q" (__gu_val): "m"((*(struct __large_struct *)
-                            (   __gu_addr   )) ), "i"(- 14 ), "0"(  __gu_err  )) ; 
-              break;        
-          case 2: 
+                            (   __gu_addr   )) ), "i"(- 14 ), "0"(  __gu_err  )) ;
+              break;
+          case 2:
             __asm__ __volatile__(
-              "1:      mov" "w" " %2,%" "w" "1\n"        
-              "2:\n"        
-              ".section .fixup,\"ax\"\n"        
-              "3:      movl %3,%0\n"        
-              "        xor" "w" " %" "w" "1,%" "w" "1\n"        
-              "        jmp 2b\n"        
-              ".section __ex_table,\"a\"\n"        
-              "        .align 4\n"        
-              "        .long 1b,3b\n"        
+              "1:      mov" "w" " %2,%" "w" "1\n"
+              "2:\n"
+              ".section .fixup,\"ax\"\n"
+              "3:      movl %3,%0\n"
+              "        xor" "w" " %" "w" "1,%" "w" "1\n"
+              "        jmp 2b\n"
+              ".section __ex_table,\"a\"\n"
+              "        .align 4\n"
+              "        .long 1b,3b\n"
               ".text"        : "=r"(__gu_err), "=r" (__gu_val) : "m"((*(struct __large_struct *)
-                            (   __gu_addr   )) ), "i"(- 14 ), "0"(  __gu_err  )); 
-              break;        
-          case 4: 
-            __asm__ __volatile__(        
-              "1:      mov" "l" " %2,%" "" "1\n"        
-              "2:\n"        
-              ".section .fixup,\"ax\"\n"        
-              "3:      movl %3,%0\n"        
-              "        xor" "l" " %" "" "1,%" "" "1\n"        
-              "        jmp 2b\n"        
-              ".section __ex_table,\"a\"\n"        
-              "        .align 4\n"        "        .long 1b,3b\n"        
+                            (   __gu_addr   )) ), "i"(- 14 ), "0"(  __gu_err  ));
+              break;
+          case 4:
+            __asm__ __volatile__(
+              "1:      mov" "l" " %2,%" "" "1\n"
+              "2:\n"
+              ".section .fixup,\"ax\"\n"
+              "3:      movl %3,%0\n"
+              "        xor" "l" " %" "" "1,%" "" "1\n"
+              "        jmp 2b\n"
+              ".section __ex_table,\"a\"\n"
+              "        .align 4\n"        "        .long 1b,3b\n"
               ".text"        : "=r"(__gu_err), "=r" (__gu_val) : "m"((*(struct __large_struct *)
-                            (   __gu_addr   )) ), "i"(- 14 ), "0"(__gu_err)); 
-              break;        
-          default: 
-            (__gu_val) = __get_user_bad();        
-        }        
-      } while (0) ;        
-    ((c)) = (__typeof__(*((buf))))__gu_val;        
+                            (   __gu_addr   )) ), "i"(- 14 ), "0"(__gu_err));
+              break;
+          default:
+            (__gu_val) = __get_user_bad();
+        }
+      } while (0) ;
+    ((c)) = (__typeof__(*((buf))))__gu_val;
     __gu_err;
   }
 );
@@ -127,12 +127,12 @@ see what code gcc generates:
 
  >         xorl %edx,%edx
  >         movl current_set,%eax
- >         cmpl $24,788(%eax)        
- >         je .L1424        
+ >         cmpl $24,788(%eax)
+ >         je .L1424
  >         cmpl $-1073741825,64(%esp)
- >         ja .L1423                
+ >         ja .L1423
  > .L1424:
- >         movl %edx,%eax                        
+ >         movl %edx,%eax
  >         movl 64(%esp),%ebx
  > #APP
  > 1:      movb (%ebx),%dl                /* this is the actual user access */
@@ -149,17 +149,17 @@ see what code gcc generates:
  > .L1423:
  >         movzbl %dl,%esi
 
-The optimizer does a good job and gives us something we can actually 
-understand. Can we? The actual user access is quite obvious. Thanks 
-to the unified address space we can just access the address in user 
+The optimizer does a good job and gives us something we can actually
+understand. Can we? The actual user access is quite obvious. Thanks
+to the unified address space we can just access the address in user
 memory. But what does the .section stuff do?????
 
 To understand this we have to look at the final kernel:
 
  > objdump --section-headers vmlinux
- > 
+ >
  > vmlinux:     file format elf32-i386
- > 
+ >
  > Sections:
  > Idx Name          Size      VMA       LMA       File off  Algn
  >   0 .text         00098f40  c0100000  c0100000  00001000  2**4
@@ -198,18 +198,18 @@ final kernel executable:
 
 The whole user memory access is reduced to 10 x86 machine instructions.
 The instructions bracketed in the .section directives are no longer
-in the normal execution path. They are located in a different section 
+in the normal execution path. They are located in a different section
 of the executable file:
 
  > objdump --disassemble --section=.fixup vmlinux
- > 
+ >
  > c0199ff5 <.fixup+10b5> movl   $0xfffffff2,%eax
  > c0199ffa <.fixup+10ba> xorb   %dl,%dl
  > c0199ffc <.fixup+10bc> jmp    c017e7a7 <do_con_write+e3>
 
 And finally:
  > objdump --full-contents --section=__ex_table vmlinux
- > 
+ >
  >  c01aa7c4 93c017c0 e09f19c0 97c017c0 99c017c0  ................
  >  c01aa7d4 f6c217c0 e99f19c0 a5e717c0 f59f19c0  ................
  >  c01aa7e4 080a18c0 01a019c0 0a0a18c0 04a019c0  ................
@@ -235,8 +235,8 @@ sections in the ELF object file. So the instructions
 ended up in the .fixup section of the object file and the addresses
         .long 1b,3b
 ended up in the __ex_table section of the object file. 1b and 3b
-are local labels. The local label 1b (1b stands for next label 1 
-backward) is the address of the instruction that might fault, i.e. 
+are local labels. The local label 1b (1b stands for next label 1
+backward) is the address of the instruction that might fault, i.e.
 in our case the address of the label 1 is c017e7a5:
 the original assembly code: > 1:      movb (%ebx),%dl
 and linked in vmlinux     : > c017e7a5 <do_con_write+e1> movb   (%ebx),%dl
@@ -254,7 +254,7 @@ The assembly code
 becomes the value pair
  >  c01aa7d4 c017c2f6 c0199fe9 c017e7a5 c0199ff5  ................
                                ^this is ^this is
-                               1b       3b 
+                               1b       3b
 c017e7a5,c0199ff5 in the exception table of the kernel.
 
 So, what actually happens if a fault from kernel mode with no suitable
@@ -266,9 +266,9 @@ vma occurs?
 3.) CPU calls do_page_fault
 4.) do page fault calls search_exception_table (regs->eip == c017e7a5);
 5.) search_exception_table looks up the address c017e7a5 in the
-    exception table (i.e. the contents of the ELF section __ex_table) 
+    exception table (i.e. the contents of the ELF section __ex_table)
     and returns the address of the associated fault handle code c0199ff5.
-6.) do_page_fault modifies its own return address to point to the fault 
+6.) do_page_fault modifies its own return address to point to the fault
     handle code and returns.
 7.) execution continues in the fault handling code.
 8.) 8a) EAX becomes -EFAULT (== -14)
author	David S. Miller <davem@davemloft.net>	2009-08-13 02:44:53 +0200
committer	David S. Miller <davem@davemloft.net>	2009-08-13 02:44:53 +0200
commit	aa11d958d1a6572eda08214d7c6a735804fe48a5 (patch)
tree	d025b05270ad1e010660d17eeadc6ac3c1abbd7d /Documentation
parent	net,pppoe: fixup module init/exit subsequent calls (diff)
parent	Revert "libertas: Read buffer overflow" (diff)
download	linux-aa11d958d1a6572eda08214d7c6a735804fe48a5.tar.xz linux-aa11d958d1a6572eda08214d7c6a735804fe48a5.zip