diff --git a/Documentation/cachetlb.txt b/Documentation/cachetlb.txt
index 73e794f..debf681 100644
--- a/Documentation/cachetlb.txt
+++ b/Documentation/cachetlb.txt
@@ -373,14 +373,15 @@
 	likely that you will need to flush the instruction cache
 	for copy_to_user_page().
 
-  void flush_anon_page(struct page *page, unsigned long vmaddr)
+  void flush_anon_page(struct vm_area_struct *vma, struct page *page,
+                       unsigned long vmaddr)
   	When the kernel needs to access the contents of an anonymous
 	page, it calls this function (currently only
 	get_user_pages()).  Note: flush_dcache_page() deliberately
 	doesn't work for an anonymous page.  The default
 	implementation is a nop (and should remain so for all coherent
 	architectures).  For incoherent architectures, it should flush
-	the cache of the page at vmaddr in the current user process.
+	the cache of the page at vmaddr.
 
   void flush_kernel_dcache_page(struct page *page)
 	When the kernel needs to modify a user page is has obtained
diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt
index 2ee16b49..fc53239 100644
--- a/Documentation/feature-removal-schedule.txt
+++ b/Documentation/feature-removal-schedule.txt
@@ -226,6 +226,23 @@
 
 ---------------------------
 
+What:	i2c_adapter.dev
+	i2c_adapter.list
+When:	July 2007
+Why:	Superfluous, given i2c_adapter.class_dev:
+	  * The "dev" was a stand-in for the physical device node that legacy
+	    drivers would not have; but now it's almost always present.  Any
+	    remaining legacy drivers must upgrade (they now trigger warnings).
+	  * The "list" duplicates class device children.
+	The delay in removing this is so upgraded lm_sensors and libsensors
+	can get deployed.  (Removal causes minor changes in the sysfs layout,
+	notably the location of the adapter type name and parenting the i2c
+	client hardware directly from their controller.)
+Who:	Jean Delvare <khali@linux-fr.org>,
+	David Brownell <dbrownell@users.sourceforge.net>
+
+---------------------------
+
 What:	IPv4 only connection tracking/NAT/helpers
 When:	2.6.22
 Why:	The new layer 3 independant connection tracking replaces the old
diff --git a/Documentation/powerpc/mpc52xx-device-tree-bindings.txt b/Documentation/powerpc/mpc52xx-device-tree-bindings.txt
index d077d76..7fb3b8a 100644
--- a/Documentation/powerpc/mpc52xx-device-tree-bindings.txt
+++ b/Documentation/powerpc/mpc52xx-device-tree-bindings.txt
@@ -157,8 +157,8 @@
 mscan@<addr>	mscan		*-mscan		CAN bus controller
 pci@<addr>	pci		*-pci		PCI bridge
 serial@<addr>	serial		*-psc-uart	PSC in serial mode
-i2s@<addr>	i2s		*-psc-i2s	PSC in i2s mode
-ac97@<addr>	ac97		*-psc-ac97	PSC in ac97 mode
+i2s@<addr>	sound		*-psc-i2s	PSC in i2s mode
+ac97@<addr>	sound		*-psc-ac97	PSC in ac97 mode
 spi@<addr>	spi		*-psc-spi	PSC in spi mode
 irda@<addr>	irda		*-psc-irda	PSC in IrDA mode
 spi@<addr>	spi		*-spi		MPC52xx spi device
diff --git a/Documentation/usb/acm.txt b/Documentation/usb/acm.txt
index 737d610..17f5c2e 100644
--- a/Documentation/usb/acm.txt
+++ b/Documentation/usb/acm.txt
@@ -46,6 +46,10 @@
 
 	3Com USR ISDN Pro TA
 
+  Some cell phones also connect via USB. I know the following phones work:
+
+	SonyEricsson K800i
+
   Unfortunately many modems and most ISDN TAs use proprietary interfaces and
 thus won't work with this drivers. Check for ACM compliance before buying.
 
diff --git a/Documentation/x86_64/boot-options.txt b/Documentation/x86_64/boot-options.txt
index dbdcaf6..5c86ed6 100644
--- a/Documentation/x86_64/boot-options.txt
+++ b/Documentation/x86_64/boot-options.txt
@@ -52,6 +52,10 @@
 		 apicmaintimer. Useful when your PIT timer is totally
 		 broken.
 
+   disable_8254_timer / enable_8254_timer
+		 Enable interrupt 0 timer routing over the 8254 in addition to over
+	         the IO-APIC. The kernel tries to set a sensible default.
+
 Early Console
 
    syntax: earlyprintk=vga
diff --git a/MAINTAINERS b/MAINTAINERS
index d1f454c..8e1d7da 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -441,20 +441,32 @@
 ARM/INTEL IOP32X ARM ARCHITECTURE
 P:	Lennert Buytenhek
 M:	kernel@wantstofly.org
+P:	Dan Williams
+M:	dan.j.williams@intel.com
 L:	linux-arm-kernel@lists.arm.linux.org.uk (subscribers-only)
-S:	Maintained
+S:	Supported
+
+ARM/INTEL IOP33X ARM ARCHITECTURE
+P:	Dan Williams
+M:	dan.j.williams@intel.com
+L:	linux-arm-kernel@lists.arm.linux.org.uk (subscribers-only)
+S:	Supported
 
 ARM/INTEL IOP13XX ARM ARCHITECTURE
 P:	Lennert Buytenhek
 M:	kernel@wantstofly.org
+P:	Dan Williams
+M:	dan.j.williams@intel.com
 L:	linux-arm-kernel@lists.arm.linux.org.uk (subscribers-only)
-S:	Maintained
+S:	Supported
 
 ARM/INTEL IQ81342EX MACHINE SUPPORT
 P:	Lennert Buytenhek
 M:	kernel@wantstofly.org
+P:	Dan Williams
+M:	dan.j.williams@intel.com
 L:	linux-arm-kernel@lists.arm.linux.org.uk (subscribers-only)
-S:	Maintained
+S:	Supported
 
 ARM/INTEL IXP2000 ARM ARCHITECTURE
 P:	Lennert Buytenhek
@@ -477,8 +489,10 @@
 ARM/INTEL XSC3 (MANZANO) ARM CORE
 P:	Lennert Buytenhek
 M:	kernel@wantstofly.org
+P:	Dan Williams
+M:	dan.j.williams@intel.com
 L:	linux-arm-kernel@lists.arm.linux.org.uk (subscribers-only)
-S:	Maintained
+S:	Supported
 
 ARM/IP FABRICS DOUBLE ESPRESSO MACHINE SUPPORT
 P:	Lennert Buytenhek
@@ -2608,6 +2622,12 @@
 M:	ambx1@neo.rr.com
 S:	Maintained
 
+PNXxxxx I2C DRIVER
+P:	Vitaly Wool
+M:	vitalywool@gmail.com
+L:	i2c@lm-sensors.org
+S:	Maintained
+
 PPP PROTOCOL DRIVERS AND COMPRESSORS
 P:	Paul Mackerras
 M:	paulus@samba.org
diff --git a/Makefile b/Makefile
index 0e9eee7..fb5b3ef 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 2
 PATCHLEVEL = 6
 SUBLEVEL = 20
-EXTRAVERSION =-rc3
+EXTRAVERSION =-rc4
 NAME = Homicidal Dwarf Hamster
 
 # *DOCUMENTATION*
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index 2db42b1..8517c3c 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -436,7 +436,7 @@
 	usr_entry
 
 	tst	r3, #PSR_T_BIT			@ Thumb mode?
-	bne	fpundefinstr			@ ignore FP
+	bne	__und_usr_unknown		@ ignore FP
 	sub	r4, r2, #4
 
 	@
@@ -448,7 +448,7 @@
 	@
 1:	ldrt	r0, [r4]
 	adr	r9, ret_from_exception
-	adr	lr, fpundefinstr
+	adr	lr, __und_usr_unknown
 	@
 	@ fallthrough to call_fpe
 	@
@@ -476,7 +476,9 @@
  * Emulators may wish to make use of the following registers:
  *  r0  = instruction opcode.
  *  r2  = PC+4
+ *  r9  = normal "successful" return address
  *  r10 = this threads thread_info structure.
+ *  lr  = unrecognised instruction return address
  */
 call_fpe:
 	tst	r0, #0x08000000			@ only CDP/CPRT/LDC/STC have bit 27
@@ -545,10 +547,12 @@
 
 	.data
 ENTRY(fp_enter)
-	.word	fpundefinstr
+	.word	no_fp
 	.text
 
-fpundefinstr:
+no_fp:	mov	pc, lr
+
+__und_usr_unknown:
 	mov	r0, sp
 	adr	lr, ret_from_exception
 	b	do_undefinstr
diff --git a/arch/arm/kernel/time.c b/arch/arm/kernel/time.c
index 6ff5e3f..3c8cdcf 100644
--- a/arch/arm/kernel/time.c
+++ b/arch/arm/kernel/time.c
@@ -29,6 +29,8 @@
 #include <linux/timer.h>
 #include <linux/irq.h>
 
+#include <linux/mc146818rtc.h>
+
 #include <asm/leds.h>
 #include <asm/thread_info.h>
 #include <asm/mach/time.h>
@@ -85,6 +87,17 @@
 	return (unsigned long long)jiffies * (1000000000 / HZ);
 }
 
+/*
+ * An implementation of printk_clock() independent from
+ * sched_clock().  This avoids non-bootable kernels when
+ * printk_clock is enabled.
+ */
+unsigned long long printk_clock(void)
+{
+	return (unsigned long long)(jiffies - INITIAL_JIFFIES) *
+			(1000000000 / HZ);
+}
+
 static unsigned long next_rtc_update;
 
 /*
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index 042a129..9089156 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -27,6 +27,7 @@
 #include <asm/uaccess.h>
 #include <asm/unistd.h>
 #include <asm/traps.h>
+#include <asm/io.h>
 
 #include "ptrace.h"
 #include "signal.h"
diff --git a/arch/arm/mm/flush.c b/arch/arm/mm/flush.c
index 628348c..9df507d 100644
--- a/arch/arm/mm/flush.c
+++ b/arch/arm/mm/flush.c
@@ -202,3 +202,42 @@
 	}
 }
 EXPORT_SYMBOL(flush_dcache_page);
+
+/*
+ * Flush an anonymous page so that users of get_user_pages()
+ * can safely access the data.  The expected sequence is:
+ *
+ *  get_user_pages()
+ *    -> flush_anon_page
+ *  memcpy() to/from page
+ *  if written to page, flush_dcache_page()
+ */
+void __flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned long vmaddr)
+{
+	unsigned long pfn;
+
+	/* VIPT non-aliasing caches need do nothing */
+	if (cache_is_vipt_nonaliasing())
+		return;
+
+	/*
+	 * Write back and invalidate userspace mapping.
+	 */
+	pfn = page_to_pfn(page);
+	if (cache_is_vivt()) {
+		flush_cache_page(vma, vmaddr, pfn);
+	} else {
+		/*
+		 * For aliasing VIPT, we can flush an alias of the
+		 * userspace address only.
+		 */
+		flush_pfn_alias(pfn, vmaddr);
+	}
+
+	/*
+	 * Invalidate kernel mapping.  No data should be contained
+	 * in this mapping of the page.  FIXME: this is overkill
+	 * since we actually ask for a write-back and invalidate.
+	 */
+	__cpuc_flush_dcache_page(page_address(page));
+}
diff --git a/arch/i386/Kconfig b/arch/i386/Kconfig
index 0d67a0a..0dfee81 100644
--- a/arch/i386/Kconfig
+++ b/arch/i386/Kconfig
@@ -777,6 +777,47 @@
           PHYSICAL_START.
 	  For more details see Documentation/kdump/kdump.txt
 
+config PHYSICAL_START
+	hex "Physical address where the kernel is loaded" if (EMBEDDED || CRASH_DUMP)
+	default "0x100000"
+	help
+	  This gives the physical address where the kernel is loaded.
+
+	  If kernel is a not relocatable (CONFIG_RELOCATABLE=n) then
+	  bzImage will decompress itself to above physical address and
+	  run from there. Otherwise, bzImage will run from the address where
+	  it has been loaded by the boot loader and will ignore above physical
+	  address.
+
+	  In normal kdump cases one does not have to set/change this option
+	  as now bzImage can be compiled as a completely relocatable image
+	  (CONFIG_RELOCATABLE=y) and be used to load and run from a different
+	  address. This option is mainly useful for the folks who don't want
+	  to use a bzImage for capturing the crash dump and want to use a
+	  vmlinux instead. vmlinux is not relocatable hence a kernel needs
+	  to be specifically compiled to run from a specific memory area
+	  (normally a reserved region) and this option comes handy.
+
+	  So if you are using bzImage for capturing the crash dump, leave
+	  the value here unchanged to 0x100000 and set CONFIG_RELOCATABLE=y.
+	  Otherwise if you plan to use vmlinux for capturing the crash dump
+	  change this value to start of the reserved region (Typically 16MB
+	  0x1000000). In other words, it can be set based on the "X" value as
+	  specified in the "crashkernel=YM@XM" command line boot parameter
+	  passed to the panic-ed kernel. Typically this parameter is set as
+	  crashkernel=64M@16M. Please take a look at
+	  Documentation/kdump/kdump.txt for more details about crash dumps.
+
+	  Usage of bzImage for capturing the crash dump is recommended as
+	  one does not have to build two kernels. Same kernel can be used
+	  as production kernel and capture kernel. Above option should have
+	  gone away after relocatable bzImage support is introduced. But it
+	  is present because there are users out there who continue to use
+	  vmlinux for dump capture. This option should go away down the
+	  line.
+
+	  Don't change this unless you know what you are doing.
+
 config RELOCATABLE
 	bool "Build a relocatable kernel(EXPERIMENTAL)"
 	depends on EXPERIMENTAL
diff --git a/arch/i386/kernel/cpu/common.c b/arch/i386/kernel/cpu/common.c
index 1b34c56..8689d62 100644
--- a/arch/i386/kernel/cpu/common.c
+++ b/arch/i386/kernel/cpu/common.c
@@ -54,7 +54,7 @@
 	.c_init	= default_init,
 	.c_vendor = "Unknown",
 };
-static struct cpu_dev * this_cpu = &default_cpu;
+static struct cpu_dev * this_cpu __cpuinitdata = &default_cpu;
 
 static int __init cachesize_setup(char *str)
 {
diff --git a/arch/i386/kernel/smpboot.c b/arch/i386/kernel/smpboot.c
index aef39be..300d9b3 100644
--- a/arch/i386/kernel/smpboot.c
+++ b/arch/i386/kernel/smpboot.c
@@ -227,7 +227,7 @@
 	atomic_t count_start;
 	atomic_t count_stop;
 	unsigned long long values[NR_CPUS];
-} tsc __initdata = {
+} tsc __cpuinitdata = {
 	.start_flag = ATOMIC_INIT(0),
 	.count_start = ATOMIC_INIT(0),
 	.count_stop = ATOMIC_INIT(0),
@@ -332,7 +332,7 @@
 		printk("passed.\n");
 }
 
-static void __init synchronize_tsc_ap(void)
+static void __cpuinit synchronize_tsc_ap(void)
 {
 	int i;
 
diff --git a/arch/i386/kernel/trampoline.S b/arch/i386/kernel/trampoline.S
index fcce0e6..2f1814c 100644
--- a/arch/i386/kernel/trampoline.S
+++ b/arch/i386/kernel/trampoline.S
@@ -38,6 +38,11 @@
 
 .data
 
+/* We can free up trampoline after bootup if cpu hotplug is not supported. */
+#ifndef CONFIG_HOTPLUG_CPU
+.section ".init.data","aw",@progbits
+#endif
+
 .code16
 
 ENTRY(trampoline_data)
diff --git a/arch/mips/kernel/mips_ksyms.c b/arch/mips/kernel/mips_ksyms.c
index f44a013..2ef857c 100644
--- a/arch/mips/kernel/mips_ksyms.c
+++ b/arch/mips/kernel/mips_ksyms.c
@@ -46,5 +46,7 @@
 EXPORT_SYMBOL(__strnlen_user_asm);
 
 EXPORT_SYMBOL(csum_partial);
+EXPORT_SYMBOL(csum_partial_copy_nocheck);
+EXPORT_SYMBOL(__csum_partial_copy_user);
 
 EXPORT_SYMBOL(invalid_pte_table);
diff --git a/arch/mips/kernel/time.c b/arch/mips/kernel/time.c
index 11aab6d..8aa544f7 100644
--- a/arch/mips/kernel/time.c
+++ b/arch/mips/kernel/time.c
@@ -94,10 +94,8 @@
 {
 	unsigned int count;
 
-#ifndef CONFIG_SOC_PNX8550	/* pnx8550 resets to zero */
 	/* Ack this timer interrupt and set the next one.  */
 	expirelo += cycles_per_jiffy;
-#endif
 	write_c0_compare(expirelo);
 
 	/* Check to see if we have missed any timer interrupts.  */
diff --git a/arch/mips/lib/Makefile b/arch/mips/lib/Makefile
index 888b61e..989c900 100644
--- a/arch/mips/lib/Makefile
+++ b/arch/mips/lib/Makefile
@@ -2,7 +2,7 @@
 # Makefile for MIPS-specific library files..
 #
 
-lib-y	+= csum_partial.o csum_partial_copy.o memcpy.o promlib.o \
+lib-y	+= csum_partial.o memcpy.o promlib.o \
 	   strlen_user.o strncpy_user.o strnlen_user.o uncached.o
 
 obj-y	+= iomap.o
diff --git a/arch/mips/lib/csum_partial.S b/arch/mips/lib/csum_partial.S
index 9db3572..c0a77fe 100644
--- a/arch/mips/lib/csum_partial.S
+++ b/arch/mips/lib/csum_partial.S
@@ -8,7 +8,9 @@
  * Copyright (C) 1998, 1999 Ralf Baechle
  * Copyright (C) 1999 Silicon Graphics, Inc.
  */
+#include <linux/errno.h>
 #include <asm/asm.h>
+#include <asm/asm-offsets.h>
 #include <asm/regdef.h>
 
 #ifdef CONFIG_64BIT
@@ -271,3 +273,443 @@
 	jr	ra
 	.set	noreorder
 	END(csum_partial)
+
+
+/*
+ * checksum and copy routines based on memcpy.S
+ *
+ *	csum_partial_copy_nocheck(src, dst, len, sum)
+ *	__csum_partial_copy_user(src, dst, len, sum, errp)
+ *
+ * See "Spec" in memcpy.S for details.  Unlike __copy_user, all
+ * function in this file use the standard calling convention.
+ */
+
+#define src a0
+#define dst a1
+#define len a2
+#define psum a3
+#define sum v0
+#define odd t8
+#define errptr t9
+
+/*
+ * The exception handler for loads requires that:
+ *  1- AT contain the address of the byte just past the end of the source
+ *     of the copy,
+ *  2- src_entry <= src < AT, and
+ *  3- (dst - src) == (dst_entry - src_entry),
+ * The _entry suffix denotes values when __copy_user was called.
+ *
+ * (1) is set up up by __csum_partial_copy_from_user and maintained by
+ *	not writing AT in __csum_partial_copy
+ * (2) is met by incrementing src by the number of bytes copied
+ * (3) is met by not doing loads between a pair of increments of dst and src
+ *
+ * The exception handlers for stores stores -EFAULT to errptr and return.
+ * These handlers do not need to overwrite any data.
+ */
+
+#define EXC(inst_reg,addr,handler)		\
+9:	inst_reg, addr;				\
+	.section __ex_table,"a";		\
+	PTR	9b, handler;			\
+	.previous
+
+#ifdef USE_DOUBLE
+
+#define LOAD   ld
+#define LOADL  ldl
+#define LOADR  ldr
+#define STOREL sdl
+#define STORER sdr
+#define STORE  sd
+#define ADD    daddu
+#define SUB    dsubu
+#define SRL    dsrl
+#define SLL    dsll
+#define SLLV   dsllv
+#define SRLV   dsrlv
+#define NBYTES 8
+#define LOG_NBYTES 3
+
+#else
+
+#define LOAD   lw
+#define LOADL  lwl
+#define LOADR  lwr
+#define STOREL swl
+#define STORER swr
+#define STORE  sw
+#define ADD    addu
+#define SUB    subu
+#define SRL    srl
+#define SLL    sll
+#define SLLV   sllv
+#define SRLV   srlv
+#define NBYTES 4
+#define LOG_NBYTES 2
+
+#endif /* USE_DOUBLE */
+
+#ifdef CONFIG_CPU_LITTLE_ENDIAN
+#define LDFIRST LOADR
+#define LDREST  LOADL
+#define STFIRST STORER
+#define STREST  STOREL
+#define SHIFT_DISCARD SLLV
+#define SHIFT_DISCARD_REVERT SRLV
+#else
+#define LDFIRST LOADL
+#define LDREST  LOADR
+#define STFIRST STOREL
+#define STREST  STORER
+#define SHIFT_DISCARD SRLV
+#define SHIFT_DISCARD_REVERT SLLV
+#endif
+
+#define FIRST(unit) ((unit)*NBYTES)
+#define REST(unit)  (FIRST(unit)+NBYTES-1)
+
+#define ADDRMASK (NBYTES-1)
+
+	.set	noat
+
+LEAF(__csum_partial_copy_user)
+	PTR_ADDU	AT, src, len	/* See (1) above. */
+#ifdef CONFIG_64BIT
+	move	errptr, a4
+#else
+	lw	errptr, 16(sp)
+#endif
+FEXPORT(csum_partial_copy_nocheck)
+	move	sum, zero
+	move	odd, zero
+	/*
+	 * Note: dst & src may be unaligned, len may be 0
+	 * Temps
+	 */
+	/*
+	 * The "issue break"s below are very approximate.
+	 * Issue delays for dcache fills will perturb the schedule, as will
+	 * load queue full replay traps, etc.
+	 *
+	 * If len < NBYTES use byte operations.
+	 */
+	sltu	t2, len, NBYTES
+	and	t1, dst, ADDRMASK
+	bnez	t2, copy_bytes_checklen
+	 and	t0, src, ADDRMASK
+	andi	odd, dst, 0x1			/* odd buffer? */
+	bnez	t1, dst_unaligned
+	 nop
+	bnez	t0, src_unaligned_dst_aligned
+	/*
+	 * use delay slot for fall-through
+	 * src and dst are aligned; need to compute rem
+	 */
+both_aligned:
+	 SRL	t0, len, LOG_NBYTES+3    # +3 for 8 units/iter
+	beqz	t0, cleanup_both_aligned # len < 8*NBYTES
+	 nop
+	SUB	len, 8*NBYTES		# subtract here for bgez loop
+	.align	4
+1:
+EXC(	LOAD	t0, UNIT(0)(src),	l_exc)
+EXC(	LOAD	t1, UNIT(1)(src),	l_exc_copy)
+EXC(	LOAD	t2, UNIT(2)(src),	l_exc_copy)
+EXC(	LOAD	t3, UNIT(3)(src),	l_exc_copy)
+EXC(	LOAD	t4, UNIT(4)(src),	l_exc_copy)
+EXC(	LOAD	t5, UNIT(5)(src),	l_exc_copy)
+EXC(	LOAD	t6, UNIT(6)(src),	l_exc_copy)
+EXC(	LOAD	t7, UNIT(7)(src),	l_exc_copy)
+	SUB	len, len, 8*NBYTES
+	ADD	src, src, 8*NBYTES
+EXC(	STORE	t0, UNIT(0)(dst),	s_exc)
+	ADDC(sum, t0)
+EXC(	STORE	t1, UNIT(1)(dst),	s_exc)
+	ADDC(sum, t1)
+EXC(	STORE	t2, UNIT(2)(dst),	s_exc)
+	ADDC(sum, t2)
+EXC(	STORE	t3, UNIT(3)(dst),	s_exc)
+	ADDC(sum, t3)
+EXC(	STORE	t4, UNIT(4)(dst),	s_exc)
+	ADDC(sum, t4)
+EXC(	STORE	t5, UNIT(5)(dst),	s_exc)
+	ADDC(sum, t5)
+EXC(	STORE	t6, UNIT(6)(dst),	s_exc)
+	ADDC(sum, t6)
+EXC(	STORE	t7, UNIT(7)(dst),	s_exc)
+	ADDC(sum, t7)
+	bgez	len, 1b
+	 ADD	dst, dst, 8*NBYTES
+	ADD	len, 8*NBYTES		# revert len (see above)
+
+	/*
+	 * len == the number of bytes left to copy < 8*NBYTES
+	 */
+cleanup_both_aligned:
+#define rem t7
+	beqz	len, done
+	 sltu	t0, len, 4*NBYTES
+	bnez	t0, less_than_4units
+	 and	rem, len, (NBYTES-1)	# rem = len % NBYTES
+	/*
+	 * len >= 4*NBYTES
+	 */
+EXC(	LOAD	t0, UNIT(0)(src),	l_exc)
+EXC(	LOAD	t1, UNIT(1)(src),	l_exc_copy)
+EXC(	LOAD	t2, UNIT(2)(src),	l_exc_copy)
+EXC(	LOAD	t3, UNIT(3)(src),	l_exc_copy)
+	SUB	len, len, 4*NBYTES
+	ADD	src, src, 4*NBYTES
+EXC(	STORE	t0, UNIT(0)(dst),	s_exc)
+	ADDC(sum, t0)
+EXC(	STORE	t1, UNIT(1)(dst),	s_exc)
+	ADDC(sum, t1)
+EXC(	STORE	t2, UNIT(2)(dst),	s_exc)
+	ADDC(sum, t2)
+EXC(	STORE	t3, UNIT(3)(dst),	s_exc)
+	ADDC(sum, t3)
+	beqz	len, done
+	 ADD	dst, dst, 4*NBYTES
+less_than_4units:
+	/*
+	 * rem = len % NBYTES
+	 */
+	beq	rem, len, copy_bytes
+	 nop
+1:
+EXC(	LOAD	t0, 0(src),		l_exc)
+	ADD	src, src, NBYTES
+	SUB	len, len, NBYTES
+EXC(	STORE	t0, 0(dst),		s_exc)
+	ADDC(sum, t0)
+	bne	rem, len, 1b
+	 ADD	dst, dst, NBYTES
+
+	/*
+	 * src and dst are aligned, need to copy rem bytes (rem < NBYTES)
+	 * A loop would do only a byte at a time with possible branch
+	 * mispredicts.  Can't do an explicit LOAD dst,mask,or,STORE
+	 * because can't assume read-access to dst.  Instead, use
+	 * STREST dst, which doesn't require read access to dst.
+	 *
+	 * This code should perform better than a simple loop on modern,
+	 * wide-issue mips processors because the code has fewer branches and
+	 * more instruction-level parallelism.
+	 */
+#define bits t2
+	beqz	len, done
+	 ADD	t1, dst, len	# t1 is just past last byte of dst
+	li	bits, 8*NBYTES
+	SLL	rem, len, 3	# rem = number of bits to keep
+EXC(	LOAD	t0, 0(src),		l_exc)
+	SUB	bits, bits, rem	# bits = number of bits to discard
+	SHIFT_DISCARD t0, t0, bits
+EXC(	STREST	t0, -1(t1),		s_exc)
+	SHIFT_DISCARD_REVERT t0, t0, bits
+	.set reorder
+	ADDC(sum, t0)
+	b	done
+	.set noreorder
+dst_unaligned:
+	/*
+	 * dst is unaligned
+	 * t0 = src & ADDRMASK
+	 * t1 = dst & ADDRMASK; T1 > 0
+	 * len >= NBYTES
+	 *
+	 * Copy enough bytes to align dst
+	 * Set match = (src and dst have same alignment)
+	 */
+#define match rem
+EXC(	LDFIRST	t3, FIRST(0)(src),	l_exc)
+	ADD	t2, zero, NBYTES
+EXC(	LDREST	t3, REST(0)(src),	l_exc_copy)
+	SUB	t2, t2, t1	# t2 = number of bytes copied
+	xor	match, t0, t1
+EXC(	STFIRST t3, FIRST(0)(dst),	s_exc)
+	SLL	t4, t1, 3		# t4 = number of bits to discard
+	SHIFT_DISCARD t3, t3, t4
+	/* no SHIFT_DISCARD_REVERT to handle odd buffer properly */
+	ADDC(sum, t3)
+	beq	len, t2, done
+	 SUB	len, len, t2
+	ADD	dst, dst, t2
+	beqz	match, both_aligned
+	 ADD	src, src, t2
+
+src_unaligned_dst_aligned:
+	SRL	t0, len, LOG_NBYTES+2    # +2 for 4 units/iter
+	beqz	t0, cleanup_src_unaligned
+	 and	rem, len, (4*NBYTES-1)   # rem = len % 4*NBYTES
+1:
+/*
+ * Avoid consecutive LD*'s to the same register since some mips
+ * implementations can't issue them in the same cycle.
+ * It's OK to load FIRST(N+1) before REST(N) because the two addresses
+ * are to the same unit (unless src is aligned, but it's not).
+ */
+EXC(	LDFIRST	t0, FIRST(0)(src),	l_exc)
+EXC(	LDFIRST	t1, FIRST(1)(src),	l_exc_copy)
+	SUB     len, len, 4*NBYTES
+EXC(	LDREST	t0, REST(0)(src),	l_exc_copy)
+EXC(	LDREST	t1, REST(1)(src),	l_exc_copy)
+EXC(	LDFIRST	t2, FIRST(2)(src),	l_exc_copy)
+EXC(	LDFIRST	t3, FIRST(3)(src),	l_exc_copy)
+EXC(	LDREST	t2, REST(2)(src),	l_exc_copy)
+EXC(	LDREST	t3, REST(3)(src),	l_exc_copy)
+	ADD	src, src, 4*NBYTES
+#ifdef CONFIG_CPU_SB1
+	nop				# improves slotting
+#endif
+EXC(	STORE	t0, UNIT(0)(dst),	s_exc)
+	ADDC(sum, t0)
+EXC(	STORE	t1, UNIT(1)(dst),	s_exc)
+	ADDC(sum, t1)
+EXC(	STORE	t2, UNIT(2)(dst),	s_exc)
+	ADDC(sum, t2)
+EXC(	STORE	t3, UNIT(3)(dst),	s_exc)
+	ADDC(sum, t3)
+	bne	len, rem, 1b
+	 ADD	dst, dst, 4*NBYTES
+
+cleanup_src_unaligned:
+	beqz	len, done
+	 and	rem, len, NBYTES-1  # rem = len % NBYTES
+	beq	rem, len, copy_bytes
+	 nop
+1:
+EXC(	LDFIRST t0, FIRST(0)(src),	l_exc)
+EXC(	LDREST	t0, REST(0)(src),	l_exc_copy)
+	ADD	src, src, NBYTES
+	SUB	len, len, NBYTES
+EXC(	STORE	t0, 0(dst),		s_exc)
+	ADDC(sum, t0)
+	bne	len, rem, 1b
+	 ADD	dst, dst, NBYTES
+
+copy_bytes_checklen:
+	beqz	len, done
+	 nop
+copy_bytes:
+	/* 0 < len < NBYTES  */
+#ifdef CONFIG_CPU_LITTLE_ENDIAN
+#define SHIFT_START 0
+#define SHIFT_INC 8
+#else
+#define SHIFT_START 8*(NBYTES-1)
+#define SHIFT_INC -8
+#endif
+	move	t2, zero	# partial word
+	li	t3, SHIFT_START	# shift
+/* use l_exc_copy here to return correct sum on fault */
+#define COPY_BYTE(N)			\
+EXC(	lbu	t0, N(src), l_exc_copy);	\
+	SUB	len, len, 1;		\
+EXC(	sb	t0, N(dst), s_exc);	\
+	SLLV	t0, t0, t3;		\
+	addu	t3, SHIFT_INC;		\
+	beqz	len, copy_bytes_done;	\
+	 or	t2, t0
+
+	COPY_BYTE(0)
+	COPY_BYTE(1)
+#ifdef USE_DOUBLE
+	COPY_BYTE(2)
+	COPY_BYTE(3)
+	COPY_BYTE(4)
+	COPY_BYTE(5)
+#endif
+EXC(	lbu	t0, NBYTES-2(src), l_exc_copy)
+	SUB	len, len, 1
+EXC(	sb	t0, NBYTES-2(dst), s_exc)
+	SLLV	t0, t0, t3
+	or	t2, t0
+copy_bytes_done:
+	ADDC(sum, t2)
+done:
+	/* fold checksum */
+#ifdef USE_DOUBLE
+	dsll32	v1, sum, 0
+	daddu	sum, v1
+	sltu	v1, sum, v1
+	dsra32	sum, sum, 0
+	addu	sum, v1
+#endif
+	sll	v1, sum, 16
+	addu	sum, v1
+	sltu	v1, sum, v1
+	srl	sum, sum, 16
+	addu	sum, v1
+
+	/* odd buffer alignment? */
+	beqz	odd, 1f
+	 nop
+	sll	v1, sum, 8
+	srl	sum, sum, 8
+	or	sum, v1
+	andi	sum, 0xffff
+1:
+	.set reorder
+	ADDC(sum, psum)
+	jr	ra
+	.set noreorder
+
+l_exc_copy:
+	/*
+	 * Copy bytes from src until faulting load address (or until a
+	 * lb faults)
+	 *
+	 * When reached by a faulting LDFIRST/LDREST, THREAD_BUADDR($28)
+	 * may be more than a byte beyond the last address.
+	 * Hence, the lb below may get an exception.
+	 *
+	 * Assumes src < THREAD_BUADDR($28)
+	 */
+	LOAD	t0, TI_TASK($28)
+	 li	t2, SHIFT_START
+	LOAD	t0, THREAD_BUADDR(t0)
+1:
+EXC(	lbu	t1, 0(src),	l_exc)
+	ADD	src, src, 1
+	sb	t1, 0(dst)	# can't fault -- we're copy_from_user
+	SLLV	t1, t1, t2
+	addu	t2, SHIFT_INC
+	ADDC(sum, t1)
+	bne	src, t0, 1b
+	 ADD	dst, dst, 1
+l_exc:
+	LOAD	t0, TI_TASK($28)
+	 nop
+	LOAD	t0, THREAD_BUADDR(t0)	# t0 is just past last good address
+	 nop
+	SUB	len, AT, t0		# len number of uncopied bytes
+	/*
+	 * Here's where we rely on src and dst being incremented in tandem,
+	 *   See (3) above.
+	 * dst += (fault addr - src) to put dst at first byte to clear
+	 */
+	ADD	dst, t0			# compute start address in a1
+	SUB	dst, src
+	/*
+	 * Clear len bytes starting at dst.  Can't call __bzero because it
+	 * might modify len.  An inefficient loop for these rare times...
+	 */
+	beqz	len, done
+	 SUB	src, len, 1
+1:	sb	zero, 0(dst)
+	ADD	dst, dst, 1
+	bnez	src, 1b
+	 SUB	src, src, 1
+	li	v1, -EFAULT
+	b	done
+	 sw	v1, (errptr)
+
+s_exc:
+	li	v0, -1 /* invalid checksum */
+	li	v1, -EFAULT
+	jr	ra
+	 sw	v1, (errptr)
+	END(__csum_partial_copy_user)
diff --git a/arch/mips/lib/csum_partial_copy.c b/arch/mips/lib/csum_partial_copy.c
deleted file mode 100644
index 0677104..0000000
--- a/arch/mips/lib/csum_partial_copy.c
+++ /dev/null
@@ -1,52 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 1994, 1995 Waldorf Electronics GmbH
- * Copyright (C) 1998, 1999 Ralf Baechle
- */
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/types.h>
-#include <asm/byteorder.h>
-#include <asm/string.h>
-#include <asm/uaccess.h>
-#include <net/checksum.h>
-
-/*
- * copy while checksumming, otherwise like csum_partial
- */
-__wsum csum_partial_copy_nocheck(const void *src,
-	void *dst, int len, __wsum sum)
-{
-	/*
-	 * It's 2:30 am and I don't feel like doing it real ...
-	 * This is lots slower than the real thing (tm)
-	 */
-	sum = csum_partial(src, len, sum);
-	memcpy(dst, src, len);
-
-	return sum;
-}
-
-EXPORT_SYMBOL(csum_partial_copy_nocheck);
-
-/*
- * Copy from userspace and compute checksum.  If we catch an exception
- * then zero the rest of the buffer.
- */
-__wsum csum_partial_copy_from_user (const void __user *src,
-	void *dst, int len, __wsum sum, int *err_ptr)
-{
-	int missing;
-
-	might_sleep();
-	missing = copy_from_user(dst, src, len);
-	if (missing) {
-		memset(dst + len - missing, 0, missing);
-		*err_ptr = -EFAULT;
-	}
-
-	return csum_partial(dst, len, sum);
-}
diff --git a/arch/mips/mips-boards/generic/time.c b/arch/mips/mips-boards/generic/time.c
index e4604c7..a3c3a1d 100644
--- a/arch/mips/mips-boards/generic/time.c
+++ b/arch/mips/mips-boards/generic/time.c
@@ -47,6 +47,9 @@
 #ifdef CONFIG_MIPS_MALTA
 #include <asm/mips-boards/maltaint.h>
 #endif
+#ifdef CONFIG_MIPS_SEAD
+#include <asm/mips-boards/seadint.h>
+#endif
 
 unsigned long cpu_khz;
 
@@ -263,11 +266,13 @@
 
 void __init plat_timer_setup(struct irqaction *irq)
 {
+#ifdef MSC01E_INT_BASE
 	if (cpu_has_veic) {
 		set_vi_handler (MSC01E_INT_CPUCTR, mips_timer_dispatch);
 		mips_cpu_timer_irq = MSC01E_INT_BASE + MSC01E_INT_CPUCTR;
-	}
-	else {
+	} else
+#endif
+	{
 		if (cpu_has_vint)
 			set_vi_handler (MIPSCPU_INT_CPUCTR, mips_timer_dispatch);
 		mips_cpu_timer_irq = MIPSCPU_INT_BASE + MIPSCPU_INT_CPUCTR;
diff --git a/arch/mips/mips-boards/malta/malta_mtd.c b/arch/mips/mips-boards/malta/malta_mtd.c
new file mode 100644
index 0000000..8ad9bdf
--- /dev/null
+++ b/arch/mips/mips-boards/malta/malta_mtd.c
@@ -0,0 +1,63 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2006 MIPS Technologies, Inc.
+ *     written by Ralf Baechle <ralf@linux-mips.org>
+ */
+
+#include <linux/init.h>
+#include <linux/platform_device.h>
+#include <linux/mtd/partitions.h>
+#include <linux/mtd/physmap.h>
+#include <mtd/mtd-abi.h>
+
+static struct mtd_partition malta_mtd_partitions[] = {
+	{
+		.name =		"YAMON",
+		.offset =	0x0,
+		.size =		0x100000,
+		.mask_flags =	MTD_WRITEABLE
+	}, {
+		.name =		"User FS",
+		.offset = 	0x100000,
+		.size =		0x2e0000
+	}, {
+		.name =		"Board Config",
+		.offset =	0x3e0000,
+		.size =		0x020000,
+		.mask_flags =	MTD_WRITEABLE
+	}
+};
+
+static struct physmap_flash_data malta_flash_data = {
+	.width		= 4,
+	.nr_parts	= ARRAY_SIZE(malta_mtd_partitions),
+	.parts		= malta_mtd_partitions
+};
+
+static struct resource malta_flash_resource = {
+	.start		= 0x1e000000,
+	.end		= 0x1e3fffff,
+	.flags		= IORESOURCE_MEM
+};
+
+static struct platform_device malta_flash = {
+	.name		= "physmap-flash",
+	.id		= 0,
+	.dev		= {
+		.platform_data	= &malta_flash_data,
+	},
+	.num_resources	= 1,
+	.resource	= &malta_flash_resource,
+};
+
+static int __init malta_mtd_init(void)
+{
+	platform_device_register(&malta_flash);
+
+	return 0;
+}
+
+module_init(malta_mtd_init)
diff --git a/arch/mips/mips-boards/sead/sead_int.c b/arch/mips/mips-boards/sead/sead_int.c
index f445fcd..874ccb0 100644
--- a/arch/mips/mips-boards/sead/sead_int.c
+++ b/arch/mips/mips-boards/sead/sead_int.c
@@ -21,7 +21,7 @@
  * Sead board.
  */
 #include <linux/init.h>
-#include <linux/irq.h>
+#include <linux/interrupt.h>
 
 #include <asm/irq_cpu.h>
 #include <asm/mipsregs.h>
@@ -108,7 +108,7 @@
 	if (irq >= 0)
 		do_IRQ(MIPSCPU_INT_BASE + irq);
 	else
-		spurious_interrupt(regs);
+		spurious_interrupt();
 }
 
 void __init arch_init_irq(void)
diff --git a/arch/mips/mm/pg-r4k.c b/arch/mips/mm/pg-r4k.c
index d41fc58..dc795be 100644
--- a/arch/mips/mm/pg-r4k.c
+++ b/arch/mips/mm/pg-r4k.c
@@ -243,11 +243,10 @@
 
 static inline void build_store_reg(int reg)
 {
-	if (cpu_has_prefetch)
-		if (reg)
-			build_dst_pref(pref_offset_copy);
-		else
-			build_dst_pref(pref_offset_clear);
+	int pref_off = cpu_has_prefetch ?
+		(reg ? pref_offset_copy : pref_offset_clear) : 0;
+	if (pref_off)
+		build_dst_pref(pref_off);
 	else if (cpu_has_cache_cdex_s)
 		build_cdex_s();
 	else if (cpu_has_cache_cdex_p)
diff --git a/arch/mips/pci/ops-pnx8550.c b/arch/mips/pci/ops-pnx8550.c
index 454b65c..f556b7a 100644
--- a/arch/mips/pci/ops-pnx8550.c
+++ b/arch/mips/pci/ops-pnx8550.c
@@ -202,7 +202,7 @@
 		break;
 	}
 
-	err = config_access(PCI_CMD_CONFIG_READ, bus, devfn, where, ~(1 << (where & 3)), &data);
+	err = config_access(PCI_CMD_CONFIG_WRITE, bus, devfn, where, ~(1 << (where & 3)), &data);
 
 	return err;
 }
diff --git a/arch/mips/philips/pnx8550/common/time.c b/arch/mips/philips/pnx8550/common/time.c
index 65c440e..f80acae 100644
--- a/arch/mips/philips/pnx8550/common/time.c
+++ b/arch/mips/philips/pnx8550/common/time.c
@@ -33,7 +33,17 @@
 #include <int.h>
 #include <cm.h>
 
-extern unsigned int mips_hpt_frequency;
+static unsigned long cpj;
+
+static cycle_t hpt_read(void)
+{
+	return read_c0_count2();
+}
+
+static void timer_ack(void)
+{
+	write_c0_compare(cpj);
+}
 
 /*
  * pnx8550_time_init() - it does the following things:
@@ -68,27 +78,47 @@
 	 * HZ timer interrupts per second.
 	 */
 	mips_hpt_frequency = 27UL * ((1000000UL * n)/(m * pow2p));
+	cpj = (mips_hpt_frequency + HZ / 2) / HZ;
+	timer_ack();
+
+	/* Setup Timer 2 */
+	write_c0_count2(0);
+	write_c0_compare2(0xffffffff);
+
+	clocksource_mips.read = hpt_read;
+	mips_timer_ack = timer_ack;
 }
 
+static irqreturn_t monotonic_interrupt(int irq, void *dev_id)
+{
+	/* Timer 2 clear interrupt */
+	write_c0_compare2(-1);
+	return IRQ_HANDLED;
+}
+
+static struct irqaction monotonic_irqaction = {
+	.handler = monotonic_interrupt,
+	.flags = IRQF_DISABLED,
+	.name = "Monotonic timer",
+};
+
 void __init plat_timer_setup(struct irqaction *irq)
 {
 	int configPR;
 
 	setup_irq(PNX8550_INT_TIMER1, irq);
+	setup_irq(PNX8550_INT_TIMER2, &monotonic_irqaction);
 
-	/* Start timer1 */
+	/* Timer 1 start */
 	configPR = read_c0_config7();
 	configPR &= ~0x00000008;
 	write_c0_config7(configPR);
 
-	/* Timer 2 stop */
+	/* Timer 2 start */
 	configPR = read_c0_config7();
-	configPR |= 0x00000010;
+	configPR &= ~0x00000010;
 	write_c0_config7(configPR);
 
-	write_c0_count2(0);
-	write_c0_compare2(0xffffffff);
-
 	/* Timer 3 stop */
 	configPR = read_c0_config7();
 	configPR |= 0x00000020;
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 8699dad..0855d55 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -436,7 +436,7 @@
 	select RTAS_PROC
 	select PPC_MPC52xx
 	select PPC_NATIVE
-	default y
+	default n
 
 config PPC_LITE5200
 	bool "Freescale Lite5200 Eval Board"
@@ -471,7 +471,7 @@
 	select PPC_INDIRECT_PCI
 	select PPC_UDBG_16550
 	select PPC_NATIVE
-	default y
+	default n
 
 config PPC_MAPLE
 	depends on PPC_MULTIPLATFORM && PPC64
diff --git a/arch/powerpc/boot/dts/lite5200.dts b/arch/powerpc/boot/dts/lite5200.dts
index 8bc0d25..a8efb59 100644
--- a/arch/powerpc/boot/dts/lite5200.dts
+++ b/arch/powerpc/boot/dts/lite5200.dts
@@ -238,7 +238,7 @@
 
 		// PSC3 in CODEC mode example
 		i2s@2400 {		// PSC3
-			device_type = "i2s";
+			device_type = "sound";
 			compatible = "mpc5200-psc-i2s\0mpc52xx-psc-i2s";
 			reg = <2400 100>;
 			interrupts = <2 3 0>;
@@ -265,7 +265,7 @@
 
 		// PSC6 in AC97 mode example
 		ac97@2c00 {		// PSC6
-			device_type = "ac97";
+			device_type = "sound";
 			compatible = "mpc5200-psc-ac97\0mpc52xx-psc-ac97";
 			reg = <2c00 100>;
 			interrupts = <2 4 0>;
diff --git a/arch/powerpc/boot/dts/lite5200b.dts b/arch/powerpc/boot/dts/lite5200b.dts
index 81cb764..1aabee4 100644
--- a/arch/powerpc/boot/dts/lite5200b.dts
+++ b/arch/powerpc/boot/dts/lite5200b.dts
@@ -243,7 +243,7 @@
 
 		// PSC3 in CODEC mode example
 		i2s@2400 {		// PSC3
-			device_type = "i2s";
+			device_type = "sound";
 			compatible = "mpc5200b-psc-i2s\0mpc52xx-psc-i2s";
 			reg = <2400 100>;
 			interrupts = <2 3 0>;
@@ -270,7 +270,7 @@
 
 		// PSC6 in AC97 mode example
 		ac97@2c00 {		// PSC6
-			device_type = "ac97";
+			device_type = "sound";
 			compatible = "mpc5200b-psc-ac97\0mpc52xx-psc-ac97";
 			reg = <2c00 100>;
 			interrupts = <2 4 0>;
diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig
index 1c00965..340376a 100644
--- a/arch/powerpc/configs/ppc64_defconfig
+++ b/arch/powerpc/configs/ppc64_defconfig
@@ -1,7 +1,7 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.18-rc6
-# Sun Sep 10 10:45:11 2006
+# Linux kernel version: 2.6.20-rc3
+# Tue Jan  2 15:32:44 2007
 #
 CONFIG_PPC64=y
 CONFIG_64BIT=y
@@ -10,6 +10,8 @@
 CONFIG_GENERIC_HARDIRQS=y
 CONFIG_IRQ_PER_CPU=y
 CONFIG_RWSEM_XCHGADD_ALGORITHM=y
+CONFIG_ARCH_HAS_ILOG2_U32=y
+CONFIG_ARCH_HAS_ILOG2_U64=y
 CONFIG_GENERIC_HWEIGHT=y
 CONFIG_GENERIC_CALIBRATE_DELAY=y
 CONFIG_GENERIC_FIND_NEXT_BIT=y
@@ -22,6 +24,8 @@
 CONFIG_PPC_OF=y
 CONFIG_PPC_UDBG_16550=y
 CONFIG_GENERIC_TBSYNC=y
+CONFIG_AUDIT_ARCH=y
+CONFIG_GENERIC_BUG=y
 # CONFIG_DEFAULT_UIMAGE is not set
 
 #
@@ -31,6 +35,10 @@
 CONFIG_POWER3=y
 CONFIG_POWER4=y
 CONFIG_PPC_FPU=y
+# CONFIG_PPC_DCR_NATIVE is not set
+CONFIG_PPC_DCR_MMIO=y
+CONFIG_PPC_DCR=y
+CONFIG_PPC_OF_PLATFORM_PCI=y
 CONFIG_ALTIVEC=y
 CONFIG_PPC_STD_MMU=y
 CONFIG_VIRT_CPU_ACCOUNTING=y
@@ -52,19 +60,24 @@
 CONFIG_LOCALVERSION_AUTO=y
 CONFIG_SWAP=y
 CONFIG_SYSVIPC=y
+# CONFIG_IPC_NS is not set
 CONFIG_POSIX_MQUEUE=y
 # CONFIG_BSD_PROCESS_ACCT is not set
 CONFIG_TASKSTATS=y
 CONFIG_TASK_DELAY_ACCT=y
-CONFIG_SYSCTL=y
+# CONFIG_UTS_NS is not set
 # CONFIG_AUDIT is not set
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
 CONFIG_CPUSETS=y
+CONFIG_SYSFS_DEPRECATED=y
 CONFIG_RELAY=y
 CONFIG_INITRAMFS_SOURCE=""
 CONFIG_CC_OPTIMIZE_FOR_SIZE=y
+# CONFIG_TASK_XACCT is not set
+CONFIG_SYSCTL=y
 # CONFIG_EMBEDDED is not set
+CONFIG_SYSCTL_SYSCALL=y
 CONFIG_KALLSYMS=y
 CONFIG_KALLSYMS_ALL=y
 # CONFIG_KALLSYMS_EXTRA_PASS is not set
@@ -73,12 +86,12 @@
 CONFIG_BUG=y
 CONFIG_ELF_CORE=y
 CONFIG_BASE_FULL=y
-CONFIG_RT_MUTEXES=y
 CONFIG_FUTEX=y
 CONFIG_EPOLL=y
 CONFIG_SHMEM=y
 CONFIG_SLAB=y
 CONFIG_VM_EVENT_COUNTERS=y
+CONFIG_RT_MUTEXES=y
 # CONFIG_TINY_SHMEM is not set
 CONFIG_BASE_SMALL=0
 # CONFIG_SLOB is not set
@@ -97,6 +110,7 @@
 #
 # Block layer
 #
+CONFIG_BLOCK=y
 CONFIG_BLK_DEV_IO_TRACE=y
 
 #
@@ -116,16 +130,20 @@
 # Platform support
 #
 CONFIG_PPC_MULTIPLATFORM=y
-# CONFIG_PPC_ISERIES is not set
 # CONFIG_EMBEDDED6xx is not set
 # CONFIG_APUS is not set
 CONFIG_PPC_PSERIES=y
+CONFIG_PPC_ISERIES=y
+# CONFIG_PPC_MPC52xx is not set
 CONFIG_PPC_PMAC=y
 CONFIG_PPC_PMAC64=y
 CONFIG_PPC_MAPLE=y
+# CONFIG_PPC_PASEMI is not set
 CONFIG_PPC_CELL=y
 CONFIG_PPC_CELL_NATIVE=y
 CONFIG_PPC_IBM_CELL_BLADE=y
+# CONFIG_PPC_PS3 is not set
+CONFIG_PPC_NATIVE=y
 CONFIG_UDBG_RTAS_CONSOLE=y
 CONFIG_XICS=y
 CONFIG_U3_DART=y
@@ -139,6 +157,8 @@
 # CONFIG_IBMEBUS is not set
 # CONFIG_PPC_MPC106 is not set
 CONFIG_PPC_970_NAP=y
+CONFIG_PPC_INDIRECT_IO=y
+CONFIG_GENERIC_IOMAP=y
 CONFIG_CPU_FREQ=y
 CONFIG_CPU_FREQ_TABLE=y
 # CONFIG_CPU_FREQ_DEBUG is not set
@@ -160,14 +180,16 @@
 #
 CONFIG_SPU_FS=m
 CONFIG_SPU_BASE=y
-CONFIG_SPUFS_MMAP=y
 CONFIG_CBE_RAS=y
+CONFIG_CBE_THERM=m
+CONFIG_CBE_CPUFREQ=m
 
 #
 # Kernel options
 #
 # CONFIG_HZ_100 is not set
 CONFIG_HZ_250=y
+# CONFIG_HZ_300 is not set
 # CONFIG_HZ_1000 is not set
 CONFIG_HZ=250
 CONFIG_PREEMPT_NONE=y
@@ -192,6 +214,7 @@
 CONFIG_ARCH_FLATMEM_ENABLE=y
 CONFIG_ARCH_SPARSEMEM_ENABLE=y
 CONFIG_ARCH_SPARSEMEM_DEFAULT=y
+CONFIG_ARCH_POPULATES_NODE_MAP=y
 CONFIG_SELECT_MEMORY_MODEL=y
 # CONFIG_FLATMEM_MANUAL is not set
 # CONFIG_DISCONTIGMEM_MANUAL is not set
@@ -201,6 +224,7 @@
 # CONFIG_SPARSEMEM_STATIC is not set
 CONFIG_SPARSEMEM_EXTREME=y
 CONFIG_MEMORY_HOTPLUG=y
+CONFIG_MEMORY_HOTPLUG_SPARSE=y
 CONFIG_SPLIT_PTLOCK_CPUS=4
 CONFIG_RESOURCES_64BIT=y
 CONFIG_ARCH_MEMORY_PROBE=y
@@ -222,6 +246,7 @@
 CONFIG_PCI=y
 CONFIG_PCI_DOMAINS=y
 # CONFIG_PCIEPORTBUS is not set
+# CONFIG_PCI_MULTITHREAD_PROBE is not set
 # CONFIG_PCI_DEBUG is not set
 
 #
@@ -254,6 +279,7 @@
 CONFIG_UNIX=y
 CONFIG_XFRM=y
 CONFIG_XFRM_USER=m
+# CONFIG_XFRM_SUB_POLICY is not set
 CONFIG_NET_KEY=m
 CONFIG_INET=y
 CONFIG_IP_MULTICAST=y
@@ -272,10 +298,13 @@
 CONFIG_INET_TUNNEL=y
 CONFIG_INET_XFRM_MODE_TRANSPORT=y
 CONFIG_INET_XFRM_MODE_TUNNEL=y
+CONFIG_INET_XFRM_MODE_BEET=y
 CONFIG_INET_DIAG=y
 CONFIG_INET_TCP_DIAG=y
 # CONFIG_TCP_CONG_ADVANCED is not set
-CONFIG_TCP_CONG_BIC=y
+CONFIG_TCP_CONG_CUBIC=y
+CONFIG_DEFAULT_TCP_CONG="cubic"
+# CONFIG_TCP_MD5SIG is not set
 
 #
 # IP: Virtual Server Configuration
@@ -294,25 +323,31 @@
 CONFIG_NETFILTER_NETLINK=y
 CONFIG_NETFILTER_NETLINK_QUEUE=m
 CONFIG_NETFILTER_NETLINK_LOG=m
+CONFIG_NF_CONNTRACK_ENABLED=m
+CONFIG_NF_CONNTRACK_SUPPORT=y
+# CONFIG_IP_NF_CONNTRACK_SUPPORT is not set
+CONFIG_NF_CONNTRACK=m
+CONFIG_NF_CT_ACCT=y
+CONFIG_NF_CONNTRACK_MARK=y
+CONFIG_NF_CONNTRACK_EVENTS=y
+CONFIG_NF_CT_PROTO_GRE=m
+CONFIG_NF_CT_PROTO_SCTP=m
+CONFIG_NF_CONNTRACK_AMANDA=m
+CONFIG_NF_CONNTRACK_FTP=m
+CONFIG_NF_CONNTRACK_H323=m
+CONFIG_NF_CONNTRACK_IRC=m
+CONFIG_NF_CONNTRACK_NETBIOS_NS=m
+CONFIG_NF_CONNTRACK_PPTP=m
+CONFIG_NF_CONNTRACK_SIP=m
+CONFIG_NF_CONNTRACK_TFTP=m
+CONFIG_NF_CT_NETLINK=m
 # CONFIG_NETFILTER_XTABLES is not set
 
 #
 # IP: Netfilter Configuration
 #
-CONFIG_IP_NF_CONNTRACK=m
-CONFIG_IP_NF_CT_ACCT=y
-CONFIG_IP_NF_CONNTRACK_MARK=y
-CONFIG_IP_NF_CONNTRACK_EVENTS=y
-CONFIG_IP_NF_CONNTRACK_NETLINK=m
-CONFIG_IP_NF_CT_PROTO_SCTP=m
-CONFIG_IP_NF_FTP=m
-CONFIG_IP_NF_IRC=m
-# CONFIG_IP_NF_NETBIOS_NS is not set
-CONFIG_IP_NF_TFTP=m
-CONFIG_IP_NF_AMANDA=m
-# CONFIG_IP_NF_PPTP is not set
-# CONFIG_IP_NF_H323 is not set
-CONFIG_IP_NF_SIP=m
+CONFIG_NF_CONNTRACK_IPV4=m
+CONFIG_NF_CONNTRACK_PROC_COMPAT=y
 CONFIG_IP_NF_QUEUE=m
 
 #
@@ -339,7 +374,6 @@
 # CONFIG_ATALK is not set
 # CONFIG_X25 is not set
 # CONFIG_LAPB is not set
-# CONFIG_NET_DIVERT is not set
 # CONFIG_ECONET is not set
 # CONFIG_WAN_ROUTER is not set
 
@@ -412,6 +446,12 @@
 # CONFIG_ATA_OVER_ETH is not set
 
 #
+# Misc devices
+#
+# CONFIG_SGI_IOC4 is not set
+# CONFIG_TIFM_CORE is not set
+
+#
 # ATA/ATAPI/MFM/RLL support
 #
 CONFIG_IDE=y
@@ -438,7 +478,6 @@
 # CONFIG_BLK_DEV_OFFBOARD is not set
 CONFIG_BLK_DEV_GENERIC=y
 # CONFIG_BLK_DEV_OPTI621 is not set
-CONFIG_BLK_DEV_SL82C105=y
 CONFIG_BLK_DEV_IDEDMA_PCI=y
 # CONFIG_BLK_DEV_IDEDMA_FORCED is not set
 CONFIG_IDEDMA_PCI_AUTO=y
@@ -453,6 +492,7 @@
 # CONFIG_BLK_DEV_CS5530 is not set
 # CONFIG_BLK_DEV_HPT34X is not set
 # CONFIG_BLK_DEV_HPT366 is not set
+# CONFIG_BLK_DEV_JMICRON is not set
 # CONFIG_BLK_DEV_SC1200 is not set
 # CONFIG_BLK_DEV_PIIX is not set
 # CONFIG_BLK_DEV_IT821X is not set
@@ -461,6 +501,7 @@
 # CONFIG_BLK_DEV_PDC202XX_NEW is not set
 # CONFIG_BLK_DEV_SVWKS is not set
 # CONFIG_BLK_DEV_SIIMAGE is not set
+CONFIG_BLK_DEV_SL82C105=y
 # CONFIG_BLK_DEV_SLC90E66 is not set
 # CONFIG_BLK_DEV_TRM290 is not set
 # CONFIG_BLK_DEV_VIA82CXXX is not set
@@ -478,6 +519,8 @@
 #
 # CONFIG_RAID_ATTRS is not set
 CONFIG_SCSI=y
+# CONFIG_SCSI_TGT is not set
+CONFIG_SCSI_NETLINK=y
 CONFIG_SCSI_PROC_FS=y
 
 #
@@ -497,14 +540,16 @@
 CONFIG_SCSI_MULTI_LUN=y
 CONFIG_SCSI_CONSTANTS=y
 # CONFIG_SCSI_LOGGING is not set
+# CONFIG_SCSI_SCAN_ASYNC is not set
 
 #
-# SCSI Transport Attributes
+# SCSI Transports
 #
 CONFIG_SCSI_SPI_ATTRS=y
 CONFIG_SCSI_FC_ATTRS=y
 CONFIG_SCSI_ISCSI_ATTRS=m
 # CONFIG_SCSI_SAS_ATTRS is not set
+# CONFIG_SCSI_SAS_LIBSAS is not set
 
 #
 # SCSI low-level drivers
@@ -517,26 +562,12 @@
 # CONFIG_SCSI_AIC7XXX is not set
 # CONFIG_SCSI_AIC7XXX_OLD is not set
 # CONFIG_SCSI_AIC79XX is not set
+# CONFIG_SCSI_AIC94XX is not set
+# CONFIG_SCSI_ARCMSR is not set
 # CONFIG_MEGARAID_NEWGEN is not set
 # CONFIG_MEGARAID_LEGACY is not set
 # CONFIG_MEGARAID_SAS is not set
-CONFIG_ATA=y
-# CONFIG_SATA_AHCI is not set
-CONFIG_SATA_SVW=y
-# CONFIG_SCSI_ATA_PIIX is not set
-# CONFIG_SATA_MV is not set
-# CONFIG_SATA_NV is not set
-# CONFIG_SCSI_PDC_ADMA is not set
 # CONFIG_SCSI_HPTIOP is not set
-# CONFIG_SATA_QSTOR is not set
-# CONFIG_SATA_PROMISE is not set
-# CONFIG_SATA_SX4 is not set
-# CONFIG_SATA_SIL is not set
-# CONFIG_SATA_SIL24 is not set
-# CONFIG_SATA_SIS is not set
-# CONFIG_SATA_ULI is not set
-# CONFIG_SATA_VIA is not set
-# CONFIG_SATA_VITESSE is not set
 # CONFIG_SCSI_BUSLOGIC is not set
 # CONFIG_SCSI_DMX3191D is not set
 # CONFIG_SCSI_EATA is not set
@@ -546,6 +577,7 @@
 CONFIG_SCSI_IBMVSCSI=y
 # CONFIG_SCSI_INITIO is not set
 # CONFIG_SCSI_INIA100 is not set
+# CONFIG_SCSI_STEX is not set
 CONFIG_SCSI_SYM53C8XX_2=y
 CONFIG_SCSI_SYM53C8XX_DMA_ADDRESSING_MODE=0
 CONFIG_SCSI_SYM53C8XX_DEFAULT_TAGS=16
@@ -556,10 +588,66 @@
 CONFIG_SCSI_IPR_DUMP=y
 # CONFIG_SCSI_QLOGIC_1280 is not set
 # CONFIG_SCSI_QLA_FC is not set
+# CONFIG_SCSI_QLA_ISCSI is not set
 CONFIG_SCSI_LPFC=m
 # CONFIG_SCSI_DC395x is not set
 # CONFIG_SCSI_DC390T is not set
 CONFIG_SCSI_DEBUG=m
+# CONFIG_SCSI_SRP is not set
+
+#
+# Serial ATA (prod) and Parallel ATA (experimental) drivers
+#
+CONFIG_ATA=y
+# CONFIG_SATA_AHCI is not set
+CONFIG_SATA_SVW=y
+# CONFIG_ATA_PIIX is not set
+# CONFIG_SATA_MV is not set
+# CONFIG_SATA_NV is not set
+# CONFIG_PDC_ADMA is not set
+# CONFIG_SATA_QSTOR is not set
+# CONFIG_SATA_PROMISE is not set
+# CONFIG_SATA_SX4 is not set
+# CONFIG_SATA_SIL is not set
+# CONFIG_SATA_SIL24 is not set
+# CONFIG_SATA_SIS is not set
+# CONFIG_SATA_ULI is not set
+# CONFIG_SATA_VIA is not set
+# CONFIG_SATA_VITESSE is not set
+# CONFIG_PATA_ALI is not set
+# CONFIG_PATA_AMD is not set
+# CONFIG_PATA_ARTOP is not set
+# CONFIG_PATA_ATIIXP is not set
+# CONFIG_PATA_CMD64X is not set
+# CONFIG_PATA_CS5520 is not set
+# CONFIG_PATA_CS5530 is not set
+# CONFIG_PATA_CYPRESS is not set
+# CONFIG_PATA_EFAR is not set
+# CONFIG_ATA_GENERIC is not set
+# CONFIG_PATA_HPT366 is not set
+# CONFIG_PATA_HPT37X is not set
+# CONFIG_PATA_HPT3X2N is not set
+# CONFIG_PATA_HPT3X3 is not set
+# CONFIG_PATA_IT821X is not set
+# CONFIG_PATA_JMICRON is not set
+# CONFIG_PATA_TRIFLEX is not set
+# CONFIG_PATA_MARVELL is not set
+# CONFIG_PATA_MPIIX is not set
+# CONFIG_PATA_OLDPIIX is not set
+# CONFIG_PATA_NETCELL is not set
+# CONFIG_PATA_NS87410 is not set
+# CONFIG_PATA_OPTI is not set
+# CONFIG_PATA_OPTIDMA is not set
+# CONFIG_PATA_PDC_OLD is not set
+# CONFIG_PATA_RADISYS is not set
+# CONFIG_PATA_RZ1000 is not set
+# CONFIG_PATA_SC1200 is not set
+# CONFIG_PATA_SERVERWORKS is not set
+# CONFIG_PATA_PDC2027X is not set
+# CONFIG_PATA_SIL680 is not set
+# CONFIG_PATA_SIS is not set
+# CONFIG_PATA_VIA is not set
+# CONFIG_PATA_WINBOND is not set
 
 #
 # Multi-device support (RAID and LVM)
@@ -575,6 +663,7 @@
 CONFIG_MD_MULTIPATH=m
 CONFIG_MD_FAULTY=m
 CONFIG_BLK_DEV_DM=y
+# CONFIG_DM_DEBUG is not set
 CONFIG_DM_CRYPT=m
 CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_MIRROR=m
@@ -630,11 +719,13 @@
 CONFIG_ADB_PMU=y
 # CONFIG_ADB_PMU_LED is not set
 CONFIG_PMAC_SMU=y
+# CONFIG_MAC_EMUMOUSEBTN is not set
 CONFIG_THERM_PM72=y
 CONFIG_WINDFARM=y
 CONFIG_WINDFARM_PM81=y
 CONFIG_WINDFARM_PM91=y
 CONFIG_WINDFARM_PM112=y
+# CONFIG_PMAC_RACKMETER is not set
 
 #
 # Network device support
@@ -675,6 +766,7 @@
 CONFIG_IBMVETH=m
 CONFIG_NET_PCI=y
 CONFIG_PCNET32=y
+# CONFIG_PCNET32_NAPI is not set
 # CONFIG_AMD8111_ETH is not set
 # CONFIG_ADAPTEC_STARFIRE is not set
 # CONFIG_B44 is not set
@@ -713,7 +805,7 @@
 CONFIG_TIGON3=y
 # CONFIG_BNX2 is not set
 CONFIG_SPIDER_NET=m
-# CONFIG_MV643XX_ETH is not set
+# CONFIG_QLA3XXX is not set
 
 #
 # Ethernet (10000 Mbit)
@@ -723,6 +815,7 @@
 # CONFIG_IXGB_NAPI is not set
 # CONFIG_S2IO is not set
 # CONFIG_MYRI10GE is not set
+# CONFIG_NETXEN_NIC is not set
 
 #
 # Token Ring devices
@@ -741,6 +834,7 @@
 # Wan interfaces
 #
 # CONFIG_WAN is not set
+CONFIG_ISERIES_VETH=m
 # CONFIG_FDDI is not set
 # CONFIG_HIPPI is not set
 CONFIG_PPP=m
@@ -753,6 +847,7 @@
 # CONFIG_PPP_MPPE is not set
 CONFIG_PPPOE=m
 # CONFIG_SLIP is not set
+CONFIG_SLHC=m
 # CONFIG_NET_FC is not set
 # CONFIG_SHAPER is not set
 CONFIG_NETCONSOLE=y
@@ -775,6 +870,7 @@
 # Input device support
 #
 CONFIG_INPUT=y
+# CONFIG_INPUT_FF_MEMLESS is not set
 
 #
 # Userland interfaces
@@ -797,6 +893,7 @@
 # CONFIG_KEYBOARD_LKKBD is not set
 # CONFIG_KEYBOARD_XTKBD is not set
 # CONFIG_KEYBOARD_NEWTON is not set
+# CONFIG_KEYBOARD_STOWAWAY is not set
 CONFIG_INPUT_MOUSE=y
 CONFIG_MOUSE_PS2=y
 # CONFIG_MOUSE_SERIAL is not set
@@ -850,6 +947,7 @@
 CONFIG_LEGACY_PTY_COUNT=256
 CONFIG_HVC_DRIVER=y
 CONFIG_HVC_CONSOLE=y
+CONFIG_HVC_ISERIES=y
 CONFIG_HVC_RTAS=y
 CONFIG_HVCS=m
 
@@ -868,10 +966,6 @@
 # CONFIG_DTLK is not set
 # CONFIG_R3964 is not set
 # CONFIG_APPLICOM is not set
-
-#
-# Ftape, the floppy tape device driver
-#
 # CONFIG_AGP is not set
 # CONFIG_DRM is not set
 CONFIG_RAW_DRIVER=y
@@ -882,7 +976,6 @@
 # TPM devices
 #
 # CONFIG_TCG_TPM is not set
-# CONFIG_TELCLOCK is not set
 
 #
 # I2C support
@@ -947,6 +1040,7 @@
 #
 # Dallas's 1-wire bus
 #
+# CONFIG_W1 is not set
 
 #
 # Hardware Monitoring support
@@ -955,14 +1049,9 @@
 # CONFIG_HWMON_VID is not set
 
 #
-# Misc devices
-#
-
-#
 # Multimedia devices
 #
 # CONFIG_VIDEO_DEV is not set
-CONFIG_VIDEO_V4L2=y
 
 #
 # Digital Video Broadcasting Devices
@@ -975,6 +1064,7 @@
 #
 CONFIG_FIRMWARE_EDID=y
 CONFIG_FB=y
+CONFIG_FB_DDC=y
 CONFIG_FB_CFB_FILLRECT=y
 CONFIG_FB_CFB_COPYAREA=y
 CONFIG_FB_CFB_IMAGEBLIT=y
@@ -1011,6 +1101,7 @@
 # CONFIG_FB_3DFX is not set
 # CONFIG_FB_VOODOO1 is not set
 # CONFIG_FB_TRIDENT is not set
+CONFIG_FB_IBM_GXT4500=y
 # CONFIG_FB_VIRTUAL is not set
 
 #
@@ -1159,6 +1250,11 @@
 # CONFIG_SOUND_PRIME is not set
 
 #
+# HID Devices
+#
+CONFIG_HID=y
+
+#
 # USB support
 #
 CONFIG_USB_ARCH_HAS_HCD=y
@@ -1173,6 +1269,7 @@
 CONFIG_USB_DEVICEFS=y
 # CONFIG_USB_BANDWIDTH is not set
 # CONFIG_USB_DYNAMIC_MINORS is not set
+# CONFIG_USB_MULTITHREAD_PROBE is not set
 # CONFIG_USB_OTG is not set
 
 #
@@ -1214,13 +1311,13 @@
 # CONFIG_USB_STORAGE_JUMPSHOT is not set
 # CONFIG_USB_STORAGE_ALAUDA is not set
 # CONFIG_USB_STORAGE_ONETOUCH is not set
+# CONFIG_USB_STORAGE_KARMA is not set
 # CONFIG_USB_LIBUSUAL is not set
 
 #
 # USB Input Devices
 #
 CONFIG_USB_HID=y
-CONFIG_USB_HIDINPUT=y
 # CONFIG_USB_HIDINPUT_POWERBOOK is not set
 # CONFIG_HID_FF is not set
 CONFIG_USB_HIDDEV=y
@@ -1250,6 +1347,7 @@
 # CONFIG_USB_KAWETH is not set
 # CONFIG_USB_PEGASUS is not set
 # CONFIG_USB_RTL8150 is not set
+# CONFIG_USB_USBNET_MII is not set
 # CONFIG_USB_USBNET is not set
 # CONFIG_USB_MON is not set
 
@@ -1267,6 +1365,7 @@
 #
 # CONFIG_USB_EMI62 is not set
 # CONFIG_USB_EMI26 is not set
+# CONFIG_USB_ADUTUX is not set
 # CONFIG_USB_AUERSWALD is not set
 # CONFIG_USB_RIO500 is not set
 # CONFIG_USB_LEGOTOWER is not set
@@ -1274,12 +1373,13 @@
 # CONFIG_USB_LED is not set
 # CONFIG_USB_CYPRESS_CY7C63 is not set
 # CONFIG_USB_CYTHERM is not set
-# CONFIG_USB_PHIDGETKIT is not set
-# CONFIG_USB_PHIDGETSERVO is not set
+# CONFIG_USB_PHIDGET is not set
 # CONFIG_USB_IDMOUSE is not set
+# CONFIG_USB_FTDI_ELAN is not set
 CONFIG_USB_APPLEDISPLAY=m
 # CONFIG_USB_SISUSBVGA is not set
 # CONFIG_USB_LD is not set
+# CONFIG_USB_TRANCEVIBRATOR is not set
 # CONFIG_USB_TEST is not set
 
 #
@@ -1318,6 +1418,7 @@
 CONFIG_INFINIBAND_ADDR_TRANS=y
 CONFIG_INFINIBAND_MTHCA=m
 CONFIG_INFINIBAND_MTHCA_DEBUG=y
+# CONFIG_INFINIBAND_AMSO1100 is not set
 CONFIG_INFINIBAND_IPOIB=m
 CONFIG_INFINIBAND_IPOIB_DEBUG=y
 # CONFIG_INFINIBAND_IPOIB_DEBUG_DATA is not set
@@ -1347,6 +1448,10 @@
 #
 
 #
+# Virtualization
+#
+
+#
 # File systems
 #
 CONFIG_EXT2_FS=y
@@ -1359,6 +1464,7 @@
 CONFIG_EXT3_FS_XATTR=y
 CONFIG_EXT3_FS_POSIX_ACL=y
 CONFIG_EXT3_FS_SECURITY=y
+# CONFIG_EXT4DEV_FS is not set
 CONFIG_JBD=y
 # CONFIG_JBD_DEBUG is not set
 CONFIG_FS_MBCACHE=y
@@ -1379,6 +1485,7 @@
 CONFIG_XFS_SECURITY=y
 CONFIG_XFS_POSIX_ACL=y
 # CONFIG_XFS_RT is not set
+# CONFIG_GFS2_FS is not set
 # CONFIG_OCFS2_FS is not set
 # CONFIG_MINIX_FS is not set
 # CONFIG_ROMFS_FS is not set
@@ -1414,8 +1521,10 @@
 #
 CONFIG_PROC_FS=y
 CONFIG_PROC_KCORE=y
+CONFIG_PROC_SYSCTL=y
 CONFIG_SYSFS=y
 CONFIG_TMPFS=y
+# CONFIG_TMPFS_POSIX_ACL is not set
 CONFIG_HUGETLBFS=y
 CONFIG_HUGETLB_PAGE=y
 CONFIG_RAMFS=y
@@ -1540,8 +1649,23 @@
 CONFIG_NLS_UTF8=m
 
 #
+# Distributed Lock Manager
+#
+# CONFIG_DLM is not set
+
+#
+# iSeries device drivers
+#
+# CONFIG_VIOCONS is not set
+CONFIG_VIODASD=y
+CONFIG_VIOCD=m
+CONFIG_VIOTAPE=m
+CONFIG_VIOPATH=y
+
+#
 # Library routines
 #
+CONFIG_BITREVERSE=y
 CONFIG_CRC_CCITT=m
 # CONFIG_CRC16 is not set
 CONFIG_CRC32=y
@@ -1551,6 +1675,7 @@
 CONFIG_TEXTSEARCH=y
 CONFIG_TEXTSEARCH_KMP=m
 CONFIG_PLIST=y
+CONFIG_IOMAP_COPY=y
 
 #
 # Instrumentation Support
@@ -1563,8 +1688,11 @@
 # Kernel hacking
 #
 # CONFIG_PRINTK_TIME is not set
+CONFIG_ENABLE_MUST_CHECK=y
 CONFIG_MAGIC_SYSRQ=y
 # CONFIG_UNUSED_SYMBOLS is not set
+CONFIG_DEBUG_FS=y
+# CONFIG_HEADERS_CHECK is not set
 CONFIG_DEBUG_KERNEL=y
 CONFIG_LOG_BUF_SHIFT=17
 CONFIG_DETECT_SOFTLOCKUP=y
@@ -1578,16 +1706,19 @@
 # CONFIG_DEBUG_SPINLOCK_SLEEP is not set
 # CONFIG_DEBUG_LOCKING_API_SELFTESTS is not set
 # CONFIG_DEBUG_KOBJECT is not set
+CONFIG_DEBUG_BUGVERBOSE=y
 # CONFIG_DEBUG_INFO is not set
-CONFIG_DEBUG_FS=y
 # CONFIG_DEBUG_VM is not set
+# CONFIG_DEBUG_LIST is not set
 CONFIG_FORCED_INLINING=y
 # CONFIG_RCU_TORTURE_TEST is not set
 CONFIG_DEBUG_STACKOVERFLOW=y
 CONFIG_DEBUG_STACK_USAGE=y
+# CONFIG_HCALL_STATS is not set
 CONFIG_DEBUGGER=y
 CONFIG_XMON=y
 # CONFIG_XMON_DEFAULT is not set
+CONFIG_XMON_DISASSEMBLY=y
 CONFIG_IRQSTACKS=y
 CONFIG_BOOTX_TEXT=y
 # CONFIG_PPC_EARLY_DEBUG is not set
@@ -1602,7 +1733,12 @@
 # Cryptographic options
 #
 CONFIG_CRYPTO=y
+CONFIG_CRYPTO_ALGAPI=y
+CONFIG_CRYPTO_BLKCIPHER=y
+CONFIG_CRYPTO_HASH=y
+CONFIG_CRYPTO_MANAGER=y
 CONFIG_CRYPTO_HMAC=y
+# CONFIG_CRYPTO_XCBC is not set
 CONFIG_CRYPTO_NULL=m
 CONFIG_CRYPTO_MD4=m
 CONFIG_CRYPTO_MD5=y
@@ -1611,9 +1747,14 @@
 CONFIG_CRYPTO_SHA512=m
 CONFIG_CRYPTO_WP512=m
 CONFIG_CRYPTO_TGR192=m
+# CONFIG_CRYPTO_GF128MUL is not set
+CONFIG_CRYPTO_ECB=m
+CONFIG_CRYPTO_CBC=y
+# CONFIG_CRYPTO_LRW is not set
 CONFIG_CRYPTO_DES=y
 CONFIG_CRYPTO_BLOWFISH=m
 CONFIG_CRYPTO_TWOFISH=m
+CONFIG_CRYPTO_TWOFISH_COMMON=m
 CONFIG_CRYPTO_SERPENT=m
 CONFIG_CRYPTO_AES=m
 CONFIG_CRYPTO_CAST5=m
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index e965215..030d300 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -303,5 +303,8 @@
 	DEFINE(NSEC_PER_SEC, NSEC_PER_SEC);
 	DEFINE(CLOCK_REALTIME_RES, TICK_NSEC);
 
+#ifdef CONFIG_BUG
+	DEFINE(BUG_ENTRY_SIZE, sizeof(struct bug_entry));
+#endif
 	return 0;
 }
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 1a3d4de..2551c08 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -28,6 +28,7 @@
 #include <asm/asm-offsets.h>
 #include <asm/cputable.h>
 #include <asm/firmware.h>
+#include <asm/bug.h>
 
 /*
  * System calls.
@@ -634,19 +635,15 @@
 	li	r0,0
 	mtcr	r0
 
+#ifdef CONFIG_BUG	
 	/* There is no way it is acceptable to get here with interrupts enabled,
 	 * check it with the asm equivalent of WARN_ON
 	 */
 	lbz	r0,PACASOFTIRQEN(r13)
 1:	tdnei	r0,0
-.section __bug_table,"a"
-	.llong	1b,__LINE__ + 0x1000000, 1f, 2f
-.previous
-.section .rodata,"a"
-1:	.asciz	__FILE__
-2:	.asciz "enter_rtas"
-.previous
-
+	EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,BUGFLAG_WARNING
+#endif
+	
 	/* Hard-disable interrupts */
 	mfmsr	r6
 	rldicl	r7,r6,48,1
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 89c836d..1bb20d8 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -744,7 +744,8 @@
 	struct vm_area_struct *vma;
 
 	vma = find_vma(current->mm, addr);
-	if (!vma || ((addr + len) <= vma->vm_start))
+	if (TASK_SIZE - len >= addr &&
+	    (!vma || ((addr + len) <= vma->vm_start)))
 		return 0;
 
 	return -ENOMEM;
@@ -815,6 +816,8 @@
 		return -EINVAL;
 	if (len & ~HPAGE_MASK)
 		return -EINVAL;
+	if (len > TASK_SIZE)
+		return -ENOMEM;
 
 	if (!cpu_has_feature(CPU_FTR_16M_PAGE))
 		return -EINVAL;
@@ -823,9 +826,6 @@
 	BUG_ON((addr + len)  < addr);
 
 	if (test_thread_flag(TIF_32BIT)) {
-		/* Paranoia, caller should have dealt with this */
-		BUG_ON((addr + len) > 0x100000000UL);
-
 		curareas = current->mm->context.low_htlb_areas;
 
 		/* First see if we can use the hint address */
diff --git a/arch/powerpc/platforms/52xx/lite5200.c b/arch/powerpc/platforms/52xx/lite5200.c
index eaff71e..0f21bab 100644
--- a/arch/powerpc/platforms/52xx/lite5200.c
+++ b/arch/powerpc/platforms/52xx/lite5200.c
@@ -153,6 +153,7 @@
 	.name 		= "lite52xx",
 	.probe 		= lite52xx_probe,
 	.setup_arch 	= lite52xx_setup_arch,
+	.init		= mpc52xx_declare_of_platform_devices,
 	.init_IRQ 	= mpc52xx_init_irq,
 	.get_irq 	= mpc52xx_get_irq,
 	.show_cpuinfo	= lite52xx_show_cpuinfo,
diff --git a/arch/powerpc/platforms/52xx/mpc52xx_common.c b/arch/powerpc/platforms/52xx/mpc52xx_common.c
index 8331ff4..cc40889 100644
--- a/arch/powerpc/platforms/52xx/mpc52xx_common.c
+++ b/arch/powerpc/platforms/52xx/mpc52xx_common.c
@@ -116,11 +116,12 @@
 	if (xlb) iounmap(xlb);
 }
 
-static int __init
+void __init
 mpc52xx_declare_of_platform_devices(void)
 {
 	/* Find every child of the SOC node and add it to of_platform */
-	return of_platform_bus_probe(NULL, NULL, NULL);
+	if (of_platform_bus_probe(NULL, NULL, NULL))
+		printk(KERN_ERR __FILE__ ": "
+			"Error while probing of_platform bus\n");
 }
 
-device_initcall(mpc52xx_declare_of_platform_devices);
diff --git a/arch/powerpc/platforms/iseries/lpevents.c b/arch/powerpc/platforms/iseries/lpevents.c
index e3e929e..c1f4502 100644
--- a/arch/powerpc/platforms/iseries/lpevents.c
+++ b/arch/powerpc/platforms/iseries/lpevents.c
@@ -17,6 +17,7 @@
 
 #include <asm/system.h>
 #include <asm/paca.h>
+#include <asm/firmware.h>
 #include <asm/iseries/it_lp_queue.h>
 #include <asm/iseries/hv_lp_event.h>
 #include <asm/iseries/hv_call_event.h>
@@ -318,6 +319,9 @@
 {
 	struct proc_dir_entry *e;
 
+	if (!firmware_has_feature(FW_FEATURE_ISERIES))
+		return 0;
+
 	e = create_proc_entry("iSeries/lpevents", S_IFREG|S_IRUGO, NULL);
 	if (e)
 		e->proc_fops = &proc_lpevents_operations;
diff --git a/arch/powerpc/platforms/iseries/mf.c b/arch/powerpc/platforms/iseries/mf.c
index cff15ae..1ad0e4a 100644
--- a/arch/powerpc/platforms/iseries/mf.c
+++ b/arch/powerpc/platforms/iseries/mf.c
@@ -38,6 +38,7 @@
 #include <asm/uaccess.h>
 #include <asm/paca.h>
 #include <asm/abs_addr.h>
+#include <asm/firmware.h>
 #include <asm/iseries/vio.h>
 #include <asm/iseries/mf.h>
 #include <asm/iseries/hv_lp_config.h>
@@ -1235,6 +1236,9 @@
 	char name[2];
 	int i;
 
+	if (!firmware_has_feature(FW_FEATURE_ISERIES))
+		return 0;
+
 	mf_proc_root = proc_mkdir("iSeries/mf", NULL);
 	if (!mf_proc_root)
 		return 1;
diff --git a/arch/powerpc/platforms/iseries/proc.c b/arch/powerpc/platforms/iseries/proc.c
index c241413..b54e371 100644
--- a/arch/powerpc/platforms/iseries/proc.c
+++ b/arch/powerpc/platforms/iseries/proc.c
@@ -24,6 +24,7 @@
 #include <asm/processor.h>
 #include <asm/time.h>
 #include <asm/lppaca.h>
+#include <asm/firmware.h>
 #include <asm/iseries/hv_call_xm.h>
 
 #include "processor_vpd.h"
@@ -31,7 +32,12 @@
 
 static int __init iseries_proc_create(void)
 {
-	struct proc_dir_entry *e = proc_mkdir("iSeries", 0);
+	struct proc_dir_entry *e;
+
+	if (!firmware_has_feature(FW_FEATURE_ISERIES))
+		return 0;
+
+	e = proc_mkdir("iSeries", 0);
 	if (!e)
 		return 1;
 
@@ -106,6 +112,9 @@
 {
 	struct proc_dir_entry *e;
 
+	if (!firmware_has_feature(FW_FEATURE_ISERIES))
+		return 0;
+
 	e = create_proc_entry("iSeries/titanTod", S_IFREG|S_IRUGO, NULL);
 	if (e)
 		e->proc_fops = &proc_titantod_operations;
diff --git a/arch/powerpc/platforms/iseries/setup.c b/arch/powerpc/platforms/iseries/setup.c
index bdf2afb..cce7e30 100644
--- a/arch/powerpc/platforms/iseries/setup.c
+++ b/arch/powerpc/platforms/iseries/setup.c
@@ -527,7 +527,8 @@
 static int __init iSeries_src_init(void)
 {
         /* clear the progress line */
-        ppc_md.progress(" ", 0xffff);
+	if (firmware_has_feature(FW_FEATURE_ISERIES))
+		ppc_md.progress(" ", 0xffff);
         return 0;
 }
 
diff --git a/arch/powerpc/platforms/iseries/viopath.c b/arch/powerpc/platforms/iseries/viopath.c
index 84e7ee2..a6799ed 100644
--- a/arch/powerpc/platforms/iseries/viopath.c
+++ b/arch/powerpc/platforms/iseries/viopath.c
@@ -42,6 +42,7 @@
 #include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/prom.h>
+#include <asm/firmware.h>
 #include <asm/iseries/hv_types.h>
 #include <asm/iseries/hv_lp_event.h>
 #include <asm/iseries/hv_lp_config.h>
@@ -183,6 +184,9 @@
 {
 	struct proc_dir_entry *e;
 
+	if (!firmware_has_feature(FW_FEATURE_ISERIES))
+		return 0;
+
 	e = create_proc_entry("iSeries/config", 0, NULL);
 	if (e)
 		e->proc_fops = &proc_viopath_operations;
diff --git a/arch/powerpc/platforms/maple/setup.c b/arch/powerpc/platforms/maple/setup.c
index f12d5c6..50855d4 100644
--- a/arch/powerpc/platforms/maple/setup.c
+++ b/arch/powerpc/platforms/maple/setup.c
@@ -254,7 +254,6 @@
 		printk(KERN_DEBUG "OpenPIC addr: %lx, has ISUs: %d\n",
 		       openpic_addr, has_isus);
 	}
-	of_node_put(root);
 
 	BUG_ON(openpic_addr == 0);
 
diff --git a/arch/powerpc/platforms/pasemi/setup.c b/arch/powerpc/platforms/pasemi/setup.c
index 89d6e29..bea7d1b 100644
--- a/arch/powerpc/platforms/pasemi/setup.c
+++ b/arch/powerpc/platforms/pasemi/setup.c
@@ -129,7 +129,6 @@
 	}
 	openpic_addr = of_read_number(opprop, naddr);
 	printk(KERN_DEBUG "OpenPIC addr: %lx\n", openpic_addr);
-	of_node_put(root);
 
 	mpic = mpic_alloc(mpic_node, openpic_addr, MPIC_PRIMARY, 0, 0,
 			  " PAS-OPIC  ");
diff --git a/arch/powerpc/platforms/pseries/hvCall.S b/arch/powerpc/platforms/pseries/hvCall.S
index c00cfed..5c7e387 100644
--- a/arch/powerpc/platforms/pseries/hvCall.S
+++ b/arch/powerpc/platforms/pseries/hvCall.S
@@ -26,7 +26,7 @@
 BEGIN_FTR_SECTION;						\
 	mfspr	r0,SPRN_PURR;		/* get PURR and */	\
 	std	r0,STK_PARM(r6)(r1);	/* save for later */	\
-END_FTR_SECTION_IFCLR(CPU_FTR_PURR);
+END_FTR_SECTION_IFSET(CPU_FTR_PURR);
 	
 /*
  * postcall is performed immediately before function return which
@@ -43,7 +43,7 @@
 	mfspr	r8,SPRN_PURR;		/* PURR after */	\
 	ld	r6,STK_PARM(r6)(r1);	/* PURR before */	\
 	subf	r6,r6,r8;		/* delta */		\
-END_FTR_SECTION_IFCLR(CPU_FTR_PURR);				\
+END_FTR_SECTION_IFSET(CPU_FTR_PURR);				\
 	ld	r5,STK_PARM(r5)(r1);	/* timebase before */	\
 	subf	r5,r5,r7;		/* time delta */	\
 								\
@@ -66,7 +66,7 @@
 	ld	r7,HCALL_STAT_PURR(r4);	/* PURR */		\
 	add	r7,r7,r6;					\
 	std	r7,HCALL_STAT_PURR(r4);				\
-END_FTR_SECTION_IFCLR(CPU_FTR_PURR);				\
+END_FTR_SECTION_IFSET(CPU_FTR_PURR);				\
 1:
 #else
 #define HCALL_INST_PRECALL
@@ -145,6 +145,7 @@
 
 	HVSC				/* invoke the hypervisor */
 
+	mr	r0,r12
 	ld	r12,STK_PARM(r4)(r1)
 	std	r4,  0(r12)
 	std	r5,  8(r12)
@@ -154,7 +155,7 @@
 	std	r9, 40(r12)
 	std	r10,48(r12)
 	std	r11,56(r12)
-	std	r12,64(r12)
+	std	r0, 64(r12)
 
 	HCALL_INST_POSTCALL
 
diff --git a/arch/powerpc/platforms/pseries/hvCall_inst.c b/arch/powerpc/platforms/pseries/hvCall_inst.c
index 80181c4..3ddc049 100644
--- a/arch/powerpc/platforms/pseries/hvCall_inst.c
+++ b/arch/powerpc/platforms/pseries/hvCall_inst.c
@@ -34,7 +34,7 @@
  */
 static void *hc_start(struct seq_file *m, loff_t *pos)
 {
-	if ((int)*pos < HCALL_STAT_ARRAY_SIZE)
+	if ((int)*pos < (HCALL_STAT_ARRAY_SIZE-1))
 		return (void *)(unsigned long)(*pos + 1);
 
 	return NULL;
@@ -57,7 +57,7 @@
 	struct hcall_stats *hs = (struct hcall_stats *)m->private;
 
 	if (hs[h_num].num_calls) {
-		if (!cpu_has_feature(CPU_FTR_PURR))
+		if (cpu_has_feature(CPU_FTR_PURR))
 			seq_printf(m, "%lu %lu %lu %lu\n", h_num<<2,
 				   hs[h_num].num_calls,
 				   hs[h_num].tb_total,
diff --git a/arch/powerpc/platforms/pseries/xics.c b/arch/powerpc/platforms/pseries/xics.c
index b5b2b11..81d172d 100644
--- a/arch/powerpc/platforms/pseries/xics.c
+++ b/arch/powerpc/platforms/pseries/xics.c
@@ -224,7 +224,6 @@
 static void xics_mask_real_irq(unsigned int irq)
 {
 	int call_status;
-	unsigned int server;
 
 	if (irq == XICS_IPI)
 		return;
@@ -236,9 +235,9 @@
 		return;
 	}
 
-	server = get_irq_server(irq);
 	/* Have to set XIVE to 0xff to be able to remove a slot */
-	call_status = rtas_call(ibm_set_xive, 3, 1, NULL, irq, server, 0xff);
+	call_status = rtas_call(ibm_set_xive, 3, 1, NULL, irq,
+				default_server, 0xff);
 	if (call_status != 0) {
 		printk(KERN_ERR "xics_disable_irq: irq=%u: ibm_set_xive(0xff)"
 		       " returned %d\n", irq, call_status);
diff --git a/arch/powerpc/sysdev/Makefile b/arch/powerpc/sysdev/Makefile
index 04d4917..2621a7e 100644
--- a/arch/powerpc/sysdev/Makefile
+++ b/arch/powerpc/sysdev/Makefile
@@ -12,7 +12,6 @@
 obj-$(CONFIG_FSL_SOC)		+= fsl_soc.o
 obj-$(CONFIG_TSI108_BRIDGE)	+= tsi108_pci.o tsi108_dev.o
 obj-$(CONFIG_QUICC_ENGINE)	+= qe_lib/
-obj-$(CONFIG_MTD)		+= rom.o
 
 ifeq ($(CONFIG_PPC_MERGE),y)
 obj-$(CONFIG_PPC_I8259)		+= i8259.o
@@ -21,5 +20,6 @@
 
 # Temporary hack until we have migrated to asm-powerpc
 ifeq ($(ARCH),powerpc)
+obj-$(CONFIG_MTD)		+= rom.o
 obj-$(CONFIG_CPM2)		+= cpm2_common.o cpm2_pic.o
 endif
diff --git a/arch/s390/kernel/head31.S b/arch/s390/kernel/head31.S
index 4388b33..eca5070 100644
--- a/arch/s390/kernel/head31.S
+++ b/arch/s390/kernel/head31.S
@@ -164,11 +164,14 @@
 	srl	%r7,28
 	clr	%r6,%r7			# compare cc with last access code
 	be	.Lsame-.LPG1(%r13)
-	b	.Lchkmem-.LPG1(%r13)
+	lhi	%r8,0			# no program checks
+	b	.Lsavchk-.LPG1(%r13)
 .Lsame:
 	ar	%r5,%r1			# add 128KB to end of chunk
 	bno	.Lloop-.LPG1(%r13)	# r1 < 0x80000000 -> loop
 .Lchkmem:				# > 2GB or tprot got a program check
+	lhi	%r8,1			# set program check flag
+.Lsavchk:
 	clr	%r4,%r5			# chunk size > 0?
 	be	.Lchkloop-.LPG1(%r13)
 	st	%r4,0(%r3)		# store start address of chunk
@@ -190,8 +193,15 @@
 	je	.Ldonemem		# if not, leave
 	chi	%r10,0			# do we have chunks left?
 	je	.Ldonemem
+	chi	%r8,1			# program check ?
+	je	.Lpgmchk
+	lr	%r4,%r5			# potential new chunk
+	alr	%r5,%r1			# add 128KB to end of chunk
+	j	.Llpcnt
+.Lpgmchk:
 	alr	%r5,%r1			# add 128KB to end of chunk
 	lr	%r4,%r5			# potential new chunk
+.Llpcnt:
 	clr	%r5,%r9			# should we go on?
 	jl	.Lloop
 .Ldonemem:
diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S
index c526279e1..6ba3f45 100644
--- a/arch/s390/kernel/head64.S
+++ b/arch/s390/kernel/head64.S
@@ -172,12 +172,15 @@
 	srl	%r7,28
 	clr	%r6,%r7			# compare cc with last access code
 	je	.Lsame
-	j	.Lchkmem
+	lghi	%r8,0			# no program checks
+	j	.Lsavchk
 .Lsame:
 	algr	%r5,%r1			# add 128KB to end of chunk
 					# no need to check here,
 	brc	12,.Lloop		# this is the same chunk
 .Lchkmem:				# > 16EB or tprot got a program check
+	lghi	%r8,1			# set program check flag
+.Lsavchk:
 	clgr	%r4,%r5			# chunk size > 0?
 	je	.Lchkloop
 	stg	%r4,0(%r3)		# store start address of chunk
@@ -204,8 +207,15 @@
 	chi	%r10, 0			# do we have chunks left?
 	je	.Ldonemem
 .Lhsaskip:
+	chi	%r8,1			# program check ?
+	je	.Lpgmchk
+	lgr	%r4,%r5			# potential new chunk
+	algr	%r5,%r1			# add 128KB to end of chunk
+	j	.Llpcnt
+.Lpgmchk:
 	algr	%r5,%r1			# add 128KB to end of chunk
 	lgr	%r4,%r5			# potential new chunk
+.Llpcnt:
 	clgr	%r5,%r9			# should we go on?
 	jl	.Lloop
 .Ldonemem:
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 49ef206..5d8ee3b 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -476,7 +476,7 @@
 	int i;
 
 	memory_size = real_size = 0;
-	max_phys = VMALLOC_END - VMALLOC_MIN_SIZE;
+	max_phys = VMALLOC_END_INIT - VMALLOC_MIN_SIZE;
 	memory_end &= PAGE_MASK;
 
 	max_mem = memory_end ? min(max_phys, memory_end) : max_phys;
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 19090f7..c0cd255 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -794,7 +794,10 @@
 	int ret;
 
 	for_each_possible_cpu(cpu) {
-		ret = register_cpu(&per_cpu(cpu_devices, cpu), cpu);
+		struct cpu *c = &per_cpu(cpu_devices, cpu);
+
+		c->hotpluggable = 1;
+		ret = register_cpu(c, cpu);
 		if (ret)
 			printk(KERN_WARNING "topology_init: register_cpu %d "
 			       "failed (%d)\n", cpu, ret);
diff --git a/arch/s390/lib/uaccess_pt.c b/arch/s390/lib/uaccess_pt.c
index 633249c..49c3e46 100644
--- a/arch/s390/lib/uaccess_pt.c
+++ b/arch/s390/lib/uaccess_pt.c
@@ -8,6 +8,7 @@
  */
 
 #include <linux/errno.h>
+#include <linux/hardirq.h>
 #include <linux/mm.h>
 #include <asm/uaccess.h>
 #include <asm/futex.h>
@@ -18,6 +19,8 @@
 	struct vm_area_struct *vma;
 	int ret = -EFAULT;
 
+	if (in_atomic())
+		return ret;
 	down_read(&mm->mmap_sem);
 	vma = find_vma(mm, address);
 	if (unlikely(!vma))
diff --git a/arch/s390/lib/uaccess_std.c b/arch/s390/lib/uaccess_std.c
index bbaca66..56a0214 100644
--- a/arch/s390/lib/uaccess_std.c
+++ b/arch/s390/lib/uaccess_std.c
@@ -258,8 +258,6 @@
 {
 	int oldval = 0, newval, ret;
 
-	pagefault_disable();
-
 	switch (op) {
 	case FUTEX_OP_SET:
 		__futex_atomic_op("lr %2,%5\n",
@@ -284,7 +282,6 @@
 	default:
 		ret = -ENOSYS;
 	}
-	pagefault_enable();
 	*old = oldval;
 	return ret;
 }
diff --git a/arch/x86_64/kernel/early-quirks.c b/arch/x86_64/kernel/early-quirks.c
index 829698f..49802f1 100644
--- a/arch/x86_64/kernel/early-quirks.c
+++ b/arch/x86_64/kernel/early-quirks.c
@@ -69,6 +69,11 @@
 
 static void ati_bugs(void)
 {
+	if (timer_over_8254 == 1) {
+		timer_over_8254 = 0;
+		printk(KERN_INFO
+	 	"ATI board detected. Disabling timer routing over 8254.\n");
+	}
 }
 
 static void intel_bugs(void)
diff --git a/arch/x86_64/kernel/io_apic.c b/arch/x86_64/kernel/io_apic.c
index 2a1dcd5..d7bad90 100644
--- a/arch/x86_64/kernel/io_apic.c
+++ b/arch/x86_64/kernel/io_apic.c
@@ -55,6 +55,10 @@
 
 static int no_timer_check;
 
+static int disable_timer_pin_1 __initdata;
+
+int timer_over_8254 __initdata = 1;
+
 /* Where if anywhere is the i8259 connect in external int mode */
 static struct { int pin, apic; } ioapic_i8259 = { -1, -1 };
 
@@ -350,6 +354,29 @@
 }
 early_param("noapic", disable_ioapic_setup);
 
+/* Actually the next is obsolete, but keep it for paranoid reasons -AK */
+static int __init disable_timer_pin_setup(char *arg)
+{
+	disable_timer_pin_1 = 1;
+	return 1;
+}
+__setup("disable_timer_pin_1", disable_timer_pin_setup);
+
+static int __init setup_disable_8254_timer(char *s)
+{
+	timer_over_8254 = -1;
+	return 1;
+}
+static int __init setup_enable_8254_timer(char *s)
+{
+	timer_over_8254 = 2;
+	return 1;
+}
+
+__setup("disable_8254_timer", setup_disable_8254_timer);
+__setup("enable_8254_timer", setup_enable_8254_timer);
+
+
 /*
  * Find the IRQ entry number of a certain pin.
  */
@@ -1568,33 +1595,10 @@
  * a wide range of boards and BIOS bugs.  Fortunately only the timer IRQ
  * is so screwy.  Thanks to Brian Perkins for testing/hacking this beast
  * fanatically on his truly buggy board.
+ *
+ * FIXME: really need to revamp this for modern platforms only.
  */
-
-static int try_apic_pin(int apic, int pin, char *msg)
-{
-	apic_printk(APIC_VERBOSE, KERN_INFO
-		    "..TIMER: trying IO-APIC=%d PIN=%d %s",
-		    apic, pin, msg);
-
-	/*
-	 * Ok, does IRQ0 through the IOAPIC work?
-	 */
-	if (!no_timer_check && timer_irq_works()) {
-		nmi_watchdog_default();
-		if (nmi_watchdog == NMI_IO_APIC) {
-			disable_8259A_irq(0);
-			setup_nmi();
-			enable_8259A_irq(0);
-		}
-		return 1;
-	}
-	clear_IO_APIC_pin(apic, pin);
-	apic_printk(APIC_QUIET, KERN_ERR " .. failed\n");
-	return 0;
-}
-
-/* The function from hell */
-static void check_timer(void)
+static inline void check_timer(void)
 {
 	int apic1, pin1, apic2, pin2;
 	int vector;
@@ -1615,43 +1619,61 @@
 	 */
 	apic_write(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT);
 	init_8259A(1);
+	if (timer_over_8254 > 0)
+		enable_8259A_irq(0);
 
 	pin1  = find_isa_irq_pin(0, mp_INT);
 	apic1 = find_isa_irq_apic(0, mp_INT);
 	pin2  = ioapic_i8259.pin;
 	apic2 = ioapic_i8259.apic;
 
-	/* Do this first, otherwise we get double interrupts on ATI boards */
-	if ((pin1 != -1) && try_apic_pin(apic1, pin1,"with 8259 IRQ0 disabled"))
-		return;
+	apic_printk(APIC_VERBOSE,KERN_INFO "..TIMER: vector=0x%02X apic1=%d pin1=%d apic2=%d pin2=%d\n",
+		vector, apic1, pin1, apic2, pin2);
 
-	/* Now try again with IRQ0 8259A enabled.
-	   Assumes timer is on IO-APIC 0 ?!? */
-	enable_8259A_irq(0);
-	unmask_IO_APIC_irq(0);
-	if (try_apic_pin(apic1, pin1, "with 8259 IRQ0 enabled"))
-		return;
-	disable_8259A_irq(0);
-
-	/* Always try pin0 and pin2 on APIC 0 to handle buggy timer overrides
-	   on Nvidia boards */
-	if (!(apic1 == 0 && pin1 == 0) &&
-	    try_apic_pin(0, 0, "fallback with 8259 IRQ0 disabled"))
-		return;
-	if (!(apic1 == 0 && pin1 == 2) &&
-	    try_apic_pin(0, 2, "fallback with 8259 IRQ0 disabled"))
-		return;
-
-	/* Then try pure 8259A routing on the 8259 as reported by BIOS*/
-	enable_8259A_irq(0);
-	if (pin2 != -1) {
-		setup_ExtINT_IRQ0_pin(apic2, pin2, vector);
-		if (try_apic_pin(apic2,pin2,"8259A broadcast ExtINT from BIOS"))
+	if (pin1 != -1) {
+		/*
+		 * Ok, does IRQ0 through the IOAPIC work?
+		 */
+		unmask_IO_APIC_irq(0);
+		if (!no_timer_check && timer_irq_works()) {
+			nmi_watchdog_default();
+			if (nmi_watchdog == NMI_IO_APIC) {
+				disable_8259A_irq(0);
+				setup_nmi();
+				enable_8259A_irq(0);
+			}
+			if (disable_timer_pin_1 > 0)
+				clear_IO_APIC_pin(0, pin1);
 			return;
+		}
+		clear_IO_APIC_pin(apic1, pin1);
+		apic_printk(APIC_QUIET,KERN_ERR "..MP-BIOS bug: 8254 timer not "
+				"connected to IO-APIC\n");
 	}
 
-	/* Tried all possibilities to go through the IO-APIC. Now come the
-	   really cheesy fallbacks. */
+	apic_printk(APIC_VERBOSE,KERN_INFO "...trying to set up timer (IRQ0) "
+				"through the 8259A ... ");
+	if (pin2 != -1) {
+		apic_printk(APIC_VERBOSE,"\n..... (found apic %d pin %d) ...",
+			apic2, pin2);
+		/*
+		 * legacy devices should be connected to IO APIC #0
+		 */
+		setup_ExtINT_IRQ0_pin(apic2, pin2, vector);
+		if (timer_irq_works()) {
+			apic_printk(APIC_VERBOSE," works.\n");
+			nmi_watchdog_default();
+			if (nmi_watchdog == NMI_IO_APIC) {
+				setup_nmi();
+			}
+			return;
+		}
+		/*
+		 * Cleanup, just in case ...
+		 */
+		clear_IO_APIC_pin(apic2, pin2);
+	}
+	apic_printk(APIC_VERBOSE," failed.\n");
 
 	if (nmi_watchdog == NMI_IO_APIC) {
 		printk(KERN_WARNING "timer doesn't work through the IO-APIC - disabling NMI Watchdog!\n");
diff --git a/drivers/acpi/toshiba_acpi.c b/drivers/acpi/toshiba_acpi.c
index 88aeccb..d9b651f 100644
--- a/drivers/acpi/toshiba_acpi.c
+++ b/drivers/acpi/toshiba_acpi.c
@@ -321,13 +321,16 @@
 static unsigned long write_lcd(const char *buffer, unsigned long count)
 {
 	int value;
-	int ret = count;
+	int ret;
 
 	if (sscanf(buffer, " brightness : %i", &value) == 1 &&
-	    value >= 0 && value < HCI_LCD_BRIGHTNESS_LEVELS)
+	    value >= 0 && value < HCI_LCD_BRIGHTNESS_LEVELS) {
 		ret = set_lcd(value);
-	else
+		if (ret == 0)
+			ret = count;
+	} else {
 		ret = -EINVAL;
+	}
 	return ret;
 }
 
diff --git a/drivers/ata/Kconfig b/drivers/ata/Kconfig
index b34e0a9..da21552 100644
--- a/drivers/ata/Kconfig
+++ b/drivers/ata/Kconfig
@@ -381,7 +381,7 @@
 	  If unsure, say N.
 
 config PATA_OPTIDMA
-	tristate "OPTI FireStar PATA support (Veyr Experimental)"
+	tristate "OPTI FireStar PATA support (Very Experimental)"
 	depends on PCI && EXPERIMENTAL
 	help
 	  This option enables DMA/PIO support for the later OPTi
diff --git a/drivers/ata/pata_hpt37x.c b/drivers/ata/pata_hpt37x.c
index 47082df..dfb3060 100644
--- a/drivers/ata/pata_hpt37x.c
+++ b/drivers/ata/pata_hpt37x.c
@@ -25,7 +25,7 @@
 #include <linux/libata.h>
 
 #define DRV_NAME	"pata_hpt37x"
-#define DRV_VERSION	"0.5.1"
+#define DRV_VERSION	"0.5.2"
 
 struct hpt_clock {
 	u8	xfer_speed;
@@ -416,7 +416,7 @@
 
 static unsigned long hpt370_filter(const struct ata_port *ap, struct ata_device *adev, unsigned long mask)
 {
-	if (adev->class != ATA_DEV_ATA) {
+	if (adev->class == ATA_DEV_ATA) {
 		if (hpt_dma_blacklisted(adev, "UDMA", bad_ata33))
 			mask &= ~ATA_MASK_UDMA;
 		if (hpt_dma_blacklisted(adev, "UDMA100", bad_ata100_5))
@@ -749,7 +749,7 @@
 {
 	struct ata_port *ap = qc->ap;
 	struct pci_dev *pdev = to_pci_dev(ap->host->dev);
-	int mscreg = 0x50 + 2 * ap->port_no;
+	int mscreg = 0x50 + 4 * ap->port_no;
 	u8 bwsr_stat, msc_stat;
 
 	pci_read_config_byte(pdev, 0x6A, &bwsr_stat);
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index 7c95c76..6246219 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -765,47 +765,34 @@
  */
 static int pkt_generic_packet(struct pktcdvd_device *pd, struct packet_command *cgc)
 {
-	char sense[SCSI_SENSE_BUFFERSIZE];
-	request_queue_t *q;
+	request_queue_t *q = bdev_get_queue(pd->bdev);
 	struct request *rq;
-	DECLARE_COMPLETION_ONSTACK(wait);
-	int err = 0;
+	int ret = 0;
 
-	q = bdev_get_queue(pd->bdev);
+	rq = blk_get_request(q, (cgc->data_direction == CGC_DATA_WRITE) ?
+			     WRITE : READ, __GFP_WAIT);
 
-	rq = blk_get_request(q, (cgc->data_direction == CGC_DATA_WRITE) ? WRITE : READ,
-			     __GFP_WAIT);
-	rq->errors = 0;
-	rq->rq_disk = pd->bdev->bd_disk;
-	rq->bio = NULL;
-	rq->buffer = NULL;
+	if (cgc->buflen) {
+		if (blk_rq_map_kern(q, rq, cgc->buffer, cgc->buflen, __GFP_WAIT))
+			goto out;
+	}
+
+	rq->cmd_len = COMMAND_SIZE(rq->cmd[0]);
+	memcpy(rq->cmd, cgc->cmd, CDROM_PACKET_SIZE);
+	if (sizeof(rq->cmd) > CDROM_PACKET_SIZE)
+		memset(rq->cmd + CDROM_PACKET_SIZE, 0, sizeof(rq->cmd) - CDROM_PACKET_SIZE);
+
 	rq->timeout = 60*HZ;
-	rq->data = cgc->buffer;
-	rq->data_len = cgc->buflen;
-	rq->sense = sense;
-	memset(sense, 0, sizeof(sense));
-	rq->sense_len = 0;
 	rq->cmd_type = REQ_TYPE_BLOCK_PC;
 	rq->cmd_flags |= REQ_HARDBARRIER;
 	if (cgc->quiet)
 		rq->cmd_flags |= REQ_QUIET;
-	memcpy(rq->cmd, cgc->cmd, CDROM_PACKET_SIZE);
-	if (sizeof(rq->cmd) > CDROM_PACKET_SIZE)
-		memset(rq->cmd + CDROM_PACKET_SIZE, 0, sizeof(rq->cmd) - CDROM_PACKET_SIZE);
-	rq->cmd_len = COMMAND_SIZE(rq->cmd[0]);
 
-	rq->ref_count++;
-	rq->end_io_data = &wait;
-	rq->end_io = blk_end_sync_rq;
-	elv_add_request(q, rq, ELEVATOR_INSERT_BACK, 1);
-	generic_unplug_device(q);
-	wait_for_completion(&wait);
-
-	if (rq->errors)
-		err = -EIO;
-
+	blk_execute_rq(rq->q, pd->bdev->bd_disk, rq, 0);
+	ret = rq->errors;
+out:
 	blk_put_request(rq);
-	return err;
+	return ret;
 }
 
 /*
diff --git a/drivers/bluetooth/hci_usb.c b/drivers/bluetooth/hci_usb.c
index aeefec9..6bdf593 100644
--- a/drivers/bluetooth/hci_usb.c
+++ b/drivers/bluetooth/hci_usb.c
@@ -117,10 +117,17 @@
 
 	/* IBM/Lenovo ThinkPad with Broadcom chip */
 	{ USB_DEVICE(0x0a5c, 0x201e), .driver_info = HCI_WRONG_SCO_MTU },
+	{ USB_DEVICE(0x0a5c, 0x2110), .driver_info = HCI_WRONG_SCO_MTU },
 
 	/* ANYCOM Bluetooth USB-200 and USB-250 */
 	{ USB_DEVICE(0x0a5c, 0x2111), .driver_info = HCI_RESET },
 
+	/* HP laptop with Broadcom chip */
+	{ USB_DEVICE(0x03f0, 0x171d), .driver_info = HCI_WRONG_SCO_MTU },
+
+	/* Dell laptop with Broadcom chip */
+	{ USB_DEVICE(0x413c, 0x8126), .driver_info = HCI_WRONG_SCO_MTU },
+
 	/* Microsoft Wireless Transceiver for Bluetooth 2.0 */
 	{ USB_DEVICE(0x045e, 0x009c), .driver_info = HCI_RESET },
 
diff --git a/drivers/char/ip2/i2ellis.h b/drivers/char/ip2/i2ellis.h
index 5eabe47..4333050 100644
--- a/drivers/char/ip2/i2ellis.h
+++ b/drivers/char/ip2/i2ellis.h
@@ -606,9 +606,9 @@
 // code and returning.
 //
 #define COMPLETE(pB,code) \
-	if(1){ \
+	do { \
 		 pB->i2eError = code; \
 		 return (code == I2EE_GOOD);\
-	}
+	} while (0)
 
 #endif   // I2ELLIS_H
diff --git a/drivers/connector/cn_proc.c b/drivers/connector/cn_proc.c
index 3ece692..5c9f67f 100644
--- a/drivers/connector/cn_proc.c
+++ b/drivers/connector/cn_proc.c
@@ -28,6 +28,7 @@
 #include <linux/init.h>
 #include <linux/connector.h>
 #include <asm/atomic.h>
+#include <asm/unaligned.h>
 
 #include <linux/cn_proc.h>
 
@@ -60,7 +61,7 @@
 	ev = (struct proc_event*)msg->data;
 	get_seq(&msg->seq, &ev->cpu);
 	ktime_get_ts(&ts); /* get high res monotonic timestamp */
-	ev->timestamp_ns = timespec_to_ns(&ts);
+	put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns);
 	ev->what = PROC_EVENT_FORK;
 	ev->event_data.fork.parent_pid = task->real_parent->pid;
 	ev->event_data.fork.parent_tgid = task->real_parent->tgid;
@@ -88,7 +89,7 @@
 	ev = (struct proc_event*)msg->data;
 	get_seq(&msg->seq, &ev->cpu);
 	ktime_get_ts(&ts); /* get high res monotonic timestamp */
-	ev->timestamp_ns = timespec_to_ns(&ts);
+	put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns);
 	ev->what = PROC_EVENT_EXEC;
 	ev->event_data.exec.process_pid = task->pid;
 	ev->event_data.exec.process_tgid = task->tgid;
@@ -124,7 +125,7 @@
 	     	return;
 	get_seq(&msg->seq, &ev->cpu);
 	ktime_get_ts(&ts); /* get high res monotonic timestamp */
-	ev->timestamp_ns = timespec_to_ns(&ts);
+	put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns);
 
 	memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id));
 	msg->ack = 0; /* not used */
@@ -146,7 +147,7 @@
 	ev = (struct proc_event*)msg->data;
 	get_seq(&msg->seq, &ev->cpu);
 	ktime_get_ts(&ts); /* get high res monotonic timestamp */
-	ev->timestamp_ns = timespec_to_ns(&ts);
+	put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns);
 	ev->what = PROC_EVENT_EXIT;
 	ev->event_data.exit.process_pid = task->pid;
 	ev->event_data.exit.process_tgid = task->tgid;
@@ -181,7 +182,7 @@
 	ev = (struct proc_event*)msg->data;
 	msg->seq = rcvd_seq;
 	ktime_get_ts(&ts); /* get high res monotonic timestamp */
-	ev->timestamp_ns = timespec_to_ns(&ts);
+	put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns);
 	ev->cpu = -1;
 	ev->what = PROC_EVENT_NONE;
 	ev->event_data.ack.err = err;
diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig
index e1989f3..9367c4c 100644
--- a/drivers/i2c/busses/Kconfig
+++ b/drivers/i2c/busses/Kconfig
@@ -564,13 +564,4 @@
 	  This driver can also be built as a module.  If so, the module
 	  will be called i2c-pnx.
 
-config I2C_PNX_EARLY
-	bool "Early initialization for I2C on PNXxxxx"
-	depends on I2C_PNX=y
-	help
-	  Under certain circumstances one may need to make sure I2C on PNXxxxx
-	  is initialized earlier than some other driver that depends on it
-	  (for instance, that might be USB in case of PNX4008). With this
-	  option turned on you can guarantee that.
-
 endmenu
diff --git a/drivers/i2c/busses/i2c-mv64xxx.c b/drivers/i2c/busses/i2c-mv64xxx.c
index bbc8e3a..4901736 100644
--- a/drivers/i2c/busses/i2c-mv64xxx.c
+++ b/drivers/i2c/busses/i2c-mv64xxx.c
@@ -529,6 +529,8 @@
 	platform_set_drvdata(pd, drv_data);
 	i2c_set_adapdata(&drv_data->adapter, drv_data);
 
+	mv64xxx_i2c_hw_init(drv_data);
+
 	if (request_irq(drv_data->irq, mv64xxx_i2c_intr, 0,
 			MV64XXX_I2C_CTLR_NAME, drv_data)) {
 		dev_err(&drv_data->adapter.dev,
@@ -542,8 +544,6 @@
 		goto exit_free_irq;
 	}
 
-	mv64xxx_i2c_hw_init(drv_data);
-
 	return 0;
 
 	exit_free_irq:
diff --git a/drivers/i2c/busses/i2c-pnx.c b/drivers/i2c/busses/i2c-pnx.c
index de0bca7..17376fe 100644
--- a/drivers/i2c/busses/i2c-pnx.c
+++ b/drivers/i2c/busses/i2c-pnx.c
@@ -305,8 +305,7 @@
 	return 0;
 }
 
-static irqreturn_t
-i2c_pnx_interrupt(int irq, void *dev_id, struct pt_regs *regs)
+static irqreturn_t i2c_pnx_interrupt(int irq, void *dev_id)
 {
 	u32 stat, ctl;
 	struct i2c_adapter *adap = dev_id;
@@ -699,10 +698,6 @@
 MODULE_DESCRIPTION("I2C driver for Philips IP3204-based I2C busses");
 MODULE_LICENSE("GPL");
 
-#ifdef CONFIG_I2C_PNX_EARLY
 /* We need to make sure I2C is initialized before USB */
 subsys_initcall(i2c_adap_pnx_init);
-#else
-mudule_init(i2c_adap_pnx_init);
-#endif
 module_exit(i2c_adap_pnx_exit);
diff --git a/drivers/i2c/chips/m41t00.c b/drivers/i2c/chips/m41t00.c
index 420377c..3fcb646 100644
--- a/drivers/i2c/chips/m41t00.c
+++ b/drivers/i2c/chips/m41t00.c
@@ -209,6 +209,7 @@
 	buf[m41t00_chip->hour] = (buf[m41t00_chip->hour] & ~0x3f) | (hour& 0x3f);
 	buf[m41t00_chip->day] = (buf[m41t00_chip->day] & ~0x3f) | (day & 0x3f);
 	buf[m41t00_chip->mon] = (buf[m41t00_chip->mon] & ~0x1f) | (mon & 0x1f);
+	buf[m41t00_chip->year] = year;
 
 	if (i2c_master_send(save_client, wbuf, 9) < 0)
 		dev_err(&save_client->dev, "m41t00_set: Write error\n");
diff --git a/drivers/i2c/i2c-core.c b/drivers/i2c/i2c-core.c
index 3e31f1d..b05378a3 100644
--- a/drivers/i2c/i2c-core.c
+++ b/drivers/i2c/i2c-core.c
@@ -95,16 +95,32 @@
 	.bus = &i2c_bus_type,
 };
 
+/* ------------------------------------------------------------------------- */
+
+/* I2C bus adapters -- one roots each I2C or SMBUS segment */
+
 static void i2c_adapter_class_dev_release(struct class_device *dev)
 {
 	struct i2c_adapter *adap = class_dev_to_i2c_adapter(dev);
 	complete(&adap->class_dev_released);
 }
 
+static ssize_t i2c_adapter_show_name(struct class_device *cdev, char *buf)
+{
+	struct i2c_adapter *adap = class_dev_to_i2c_adapter(cdev);
+	return sprintf(buf, "%s\n", adap->name);
+}
+
+static struct class_device_attribute i2c_adapter_attrs[] = {
+	__ATTR(name, S_IRUGO, i2c_adapter_show_name, NULL),
+	{ },
+};
+
 struct class i2c_adapter_class = {
-	.owner =	THIS_MODULE,
-	.name =		"i2c-adapter",
-	.release =	&i2c_adapter_class_dev_release,
+	.owner			= THIS_MODULE,
+	.name			= "i2c-adapter",
+	.class_dev_attrs	= i2c_adapter_attrs,
+	.release		= &i2c_adapter_class_dev_release,
 };
 
 static ssize_t show_adapter_name(struct device *dev, struct device_attribute *attr, char *buf)
@@ -175,8 +191,12 @@
 	 * If the parent pointer is not set up,
 	 * we add this adapter to the host bus.
 	 */
-	if (adap->dev.parent == NULL)
+	if (adap->dev.parent == NULL) {
 		adap->dev.parent = &platform_bus;
+		printk(KERN_WARNING "**WARNING** I2C adapter driver [%s] "
+		       "forgot to specify physical device; fix it!\n",
+		       adap->name);
+	}
 	sprintf(adap->dev.bus_id, "i2c-%d", adap->nr);
 	adap->dev.driver = &i2c_adapter_driver;
 	adap->dev.release = &i2c_adapter_dev_release;
diff --git a/drivers/ide/pci/atiixp.c b/drivers/ide/pci/atiixp.c
index ffdffb6..524e65d 100644
--- a/drivers/ide/pci/atiixp.c
+++ b/drivers/ide/pci/atiixp.c
@@ -46,6 +46,8 @@
 
 static int save_mdma_mode[4];
 
+static DEFINE_SPINLOCK(atiixp_lock);
+
 /**
  *	atiixp_ratemask		-	compute rate mask for ATIIXP IDE
  *	@drive: IDE drive to compute for
@@ -105,7 +107,7 @@
 	unsigned long flags;
 	u16 tmp16;
 
-	spin_lock_irqsave(&ide_lock, flags);
+	spin_lock_irqsave(&atiixp_lock, flags);
 
 	pci_read_config_word(dev, ATIIXP_IDE_UDMA_CONTROL, &tmp16);
 	if (save_mdma_mode[drive->dn])
@@ -114,7 +116,7 @@
 		tmp16 |= (1 << drive->dn);
 	pci_write_config_word(dev, ATIIXP_IDE_UDMA_CONTROL, tmp16);
 
-	spin_unlock_irqrestore(&ide_lock, flags);
+	spin_unlock_irqrestore(&atiixp_lock, flags);
 
 	return __ide_dma_host_on(drive);
 }
@@ -125,13 +127,13 @@
 	unsigned long flags;
 	u16 tmp16;
 
-	spin_lock_irqsave(&ide_lock, flags);
+	spin_lock_irqsave(&atiixp_lock, flags);
 
 	pci_read_config_word(dev, ATIIXP_IDE_UDMA_CONTROL, &tmp16);
 	tmp16 &= ~(1 << drive->dn);
 	pci_write_config_word(dev, ATIIXP_IDE_UDMA_CONTROL, tmp16);
 
-	spin_unlock_irqrestore(&ide_lock, flags);
+	spin_unlock_irqrestore(&atiixp_lock, flags);
 
 	return __ide_dma_host_off(drive);
 }
@@ -152,7 +154,7 @@
 	u32 pio_timing_data;
 	u16 pio_mode_data;
 
-	spin_lock_irqsave(&ide_lock, flags);
+	spin_lock_irqsave(&atiixp_lock, flags);
 
 	pci_read_config_word(dev, ATIIXP_IDE_PIO_MODE, &pio_mode_data);
 	pio_mode_data &= ~(0x07 << (drive->dn * 4));
@@ -165,7 +167,7 @@
 		 (pio_timing[pio].command_width << (timing_shift + 4));
 	pci_write_config_dword(dev, ATIIXP_IDE_PIO_TIMING, pio_timing_data);
 
-	spin_unlock_irqrestore(&ide_lock, flags);
+	spin_unlock_irqrestore(&atiixp_lock, flags);
 }
 
 /**
@@ -189,7 +191,7 @@
 
 	speed = ide_rate_filter(atiixp_ratemask(drive), xferspeed);
 
-	spin_lock_irqsave(&ide_lock, flags);
+	spin_lock_irqsave(&atiixp_lock, flags);
 
 	save_mdma_mode[drive->dn] = 0;
 	if (speed >= XFER_UDMA_0) {
@@ -208,7 +210,7 @@
 		}
 	}
 
-	spin_unlock_irqrestore(&ide_lock, flags);
+	spin_unlock_irqrestore(&atiixp_lock, flags);
 
 	if (speed >= XFER_SW_DMA_0)
 		pio = atiixp_dma_2_pio(speed);
diff --git a/drivers/ide/pci/via82cxxx.c b/drivers/ide/pci/via82cxxx.c
index 61f1a96..381cc6f 100644
--- a/drivers/ide/pci/via82cxxx.c
+++ b/drivers/ide/pci/via82cxxx.c
@@ -123,7 +123,7 @@
 static void via_set_speed(ide_hwif_t *hwif, u8 dn, struct ide_timing *timing)
 {
 	struct pci_dev *dev = hwif->pci_dev;
-	struct via82cxxx_dev *vdev = ide_get_hwifdata(hwif);
+	struct via82cxxx_dev *vdev = pci_get_drvdata(hwif->pci_dev);
 	u8 t;
 
 	if (~vdev->via_config->flags & VIA_BAD_AST) {
@@ -162,7 +162,7 @@
 static int via_set_drive(ide_drive_t *drive, u8 speed)
 {
 	ide_drive_t *peer = HWIF(drive)->drives + (~drive->dn & 1);
-	struct via82cxxx_dev *vdev = ide_get_hwifdata(drive->hwif);
+	struct via82cxxx_dev *vdev = pci_get_drvdata(drive->hwif->pci_dev);
 	struct ide_timing t, p;
 	unsigned int T, UT;
 
@@ -225,7 +225,7 @@
 static int via82cxxx_ide_dma_check (ide_drive_t *drive)
 {
 	ide_hwif_t *hwif = HWIF(drive);
-	struct via82cxxx_dev *vdev = ide_get_hwifdata(hwif);
+	struct via82cxxx_dev *vdev = pci_get_drvdata(hwif->pci_dev);
 	u16 w80 = hwif->udma_four;
 
 	u16 speed = ide_find_best_mode(drive,
@@ -262,6 +262,53 @@
 	return via_config;
 }
 
+/*
+ * Check and handle 80-wire cable presence
+ */
+static void __devinit via_cable_detect(struct via82cxxx_dev *vdev, u32 u)
+{
+	int i;
+
+	switch (vdev->via_config->flags & VIA_UDMA) {
+		case VIA_UDMA_66:
+			for (i = 24; i >= 0; i -= 8)
+				if (((u >> (i & 16)) & 8) &&
+				    ((u >> i) & 0x20) &&
+				     (((u >> i) & 7) < 2)) {
+					/*
+					 * 2x PCI clock and
+					 * UDMA w/ < 3T/cycle
+					 */
+					vdev->via_80w |= (1 << (1 - (i >> 4)));
+				}
+			break;
+
+		case VIA_UDMA_100:
+			for (i = 24; i >= 0; i -= 8)
+				if (((u >> i) & 0x10) ||
+				    (((u >> i) & 0x20) &&
+				     (((u >> i) & 7) < 4))) {
+					/* BIOS 80-wire bit or
+					 * UDMA w/ < 60ns/cycle
+					 */
+					vdev->via_80w |= (1 << (1 - (i >> 4)));
+				}
+			break;
+
+		case VIA_UDMA_133:
+			for (i = 24; i >= 0; i -= 8)
+				if (((u >> i) & 0x10) ||
+				    (((u >> i) & 0x20) &&
+				     (((u >> i) & 7) < 6))) {
+					/* BIOS 80-wire bit or
+					 * UDMA w/ < 60ns/cycle
+					 */
+					vdev->via_80w |= (1 << (1 - (i >> 4)));
+				}
+			break;
+	}
+}
+
 /**
  *	init_chipset_via82cxxx	-	initialization handler
  *	@dev: PCI device
@@ -274,14 +321,22 @@
 static unsigned int __devinit init_chipset_via82cxxx(struct pci_dev *dev, const char *name)
 {
 	struct pci_dev *isa = NULL;
+	struct via82cxxx_dev *vdev;
 	struct via_isa_bridge *via_config;
 	u8 t, v;
-	unsigned int u;
+	u32 u;
+
+	vdev = kzalloc(sizeof(*vdev), GFP_KERNEL);
+	if (!vdev) {
+		printk(KERN_ERR "VP_IDE: out of memory :(\n");
+		return -ENOMEM;
+	}
+	pci_set_drvdata(dev, vdev);
 
 	/*
 	 * Find the ISA bridge to see how good the IDE is.
 	 */
-	via_config = via_config_find(&isa);
+	vdev->via_config = via_config = via_config_find(&isa);
 
 	/* We checked this earlier so if it fails here deeep badness
 	   is involved */
@@ -289,16 +344,17 @@
 	BUG_ON(!via_config->id);
 
 	/*
-	 * Setup or disable Clk66 if appropriate
+	 * Detect cable and configure Clk66
 	 */
+	pci_read_config_dword(dev, VIA_UDMA_TIMING, &u);
+
+	via_cable_detect(vdev, u);
 
 	if ((via_config->flags & VIA_UDMA) == VIA_UDMA_66) {
 		/* Enable Clk66 */
-		pci_read_config_dword(dev, VIA_UDMA_TIMING, &u);
 		pci_write_config_dword(dev, VIA_UDMA_TIMING, u|0x80008);
 	} else if (via_config->flags & VIA_BAD_CLK66) {
 		/* Would cause trouble on 596a and 686 */
-		pci_read_config_dword(dev, VIA_UDMA_TIMING, &u);
 		pci_write_config_dword(dev, VIA_UDMA_TIMING, u & ~0x80008);
 	}
 
@@ -367,75 +423,11 @@
 	return 0;
 }
 
-/*
- * Check and handle 80-wire cable presence
- */
-static void __devinit via_cable_detect(struct pci_dev *dev, struct via82cxxx_dev *vdev)
-{
-	unsigned int u;
-	int i;
-	pci_read_config_dword(dev, VIA_UDMA_TIMING, &u);
-
-	switch (vdev->via_config->flags & VIA_UDMA) {
-
-		case VIA_UDMA_66:
-			for (i = 24; i >= 0; i -= 8)
-				if (((u >> (i & 16)) & 8) &&
-				    ((u >> i) & 0x20) &&
-				     (((u >> i) & 7) < 2)) {
-					/*
-					 * 2x PCI clock and
-					 * UDMA w/ < 3T/cycle
-					 */
-					vdev->via_80w |= (1 << (1 - (i >> 4)));
-				}
-			break;
-
-		case VIA_UDMA_100:
-			for (i = 24; i >= 0; i -= 8)
-				if (((u >> i) & 0x10) ||
-				    (((u >> i) & 0x20) &&
-				     (((u >> i) & 7) < 4))) {
-					/* BIOS 80-wire bit or
-					 * UDMA w/ < 60ns/cycle
-					 */
-					vdev->via_80w |= (1 << (1 - (i >> 4)));
-				}
-			break;
-
-		case VIA_UDMA_133:
-			for (i = 24; i >= 0; i -= 8)
-				if (((u >> i) & 0x10) ||
-				    (((u >> i) & 0x20) &&
-				     (((u >> i) & 7) < 6))) {
-					/* BIOS 80-wire bit or
-					 * UDMA w/ < 60ns/cycle
-					 */
-					vdev->via_80w |= (1 << (1 - (i >> 4)));
-				}
-			break;
-
-	}
-}
-
 static void __devinit init_hwif_via82cxxx(ide_hwif_t *hwif)
 {
-	struct via82cxxx_dev *vdev = kmalloc(sizeof(struct via82cxxx_dev),
-		GFP_KERNEL);
-	struct pci_dev *isa = NULL;
+	struct via82cxxx_dev *vdev = pci_get_drvdata(hwif->pci_dev);
 	int i;
 
-	if (vdev == NULL) {
-		printk(KERN_ERR "VP_IDE: out of memory :(\n");
-		return;
-	}
-
-	memset(vdev, 0, sizeof(struct via82cxxx_dev));
-	ide_set_hwifdata(hwif, vdev);
-
-	vdev->via_config = via_config_find(&isa);
-	via_cable_detect(hwif->pci_dev, vdev);
-
 	hwif->autodma = 0;
 
 	hwif->tuneproc = &via82cxxx_tune_drive;
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 533193d..9e0ab04 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -1088,10 +1088,21 @@
 		*sin = iw_event->local_addr;
 		sin = (struct sockaddr_in *) &id_priv->id.route.addr.dst_addr;
 		*sin = iw_event->remote_addr;
-		if (iw_event->status)
-			event.event = RDMA_CM_EVENT_REJECTED;
-		else
+		switch (iw_event->status) {
+		case 0:
 			event.event = RDMA_CM_EVENT_ESTABLISHED;
+			break;
+		case -ECONNRESET:
+		case -ECONNREFUSED:
+			event.event = RDMA_CM_EVENT_REJECTED;
+			break;
+		case -ETIMEDOUT:
+			event.event = RDMA_CM_EVENT_UNREACHABLE;
+			break;
+		default:
+			event.event = RDMA_CM_EVENT_CONNECT_ERROR;
+			break;
+		}
 		break;
 	case IW_CM_EVENT_ESTABLISHED:
 		event.event = RDMA_CM_EVENT_ESTABLISHED;
diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c
index 81a5cdc..e2e8d32 100644
--- a/drivers/infiniband/core/ucma.c
+++ b/drivers/infiniband/core/ucma.c
@@ -209,10 +209,21 @@
 	if (event->event == RDMA_CM_EVENT_CONNECT_REQUEST) {
 		if (!ctx->backlog) {
 			ret = -EDQUOT;
+			kfree(uevent);
 			goto out;
 		}
 		ctx->backlog--;
+	} else if (!ctx->uid) {
+		/*
+		 * We ignore events for new connections until userspace has set
+		 * their context.  This can only happen if an error occurs on a
+		 * new connection before the user accepts it.  This is okay,
+		 * since the accept will just fail later.
+		 */
+		kfree(uevent);
+		goto out;
 	}
+
 	list_add_tail(&uevent->list, &ctx->file->event_list);
 	wake_up_interruptible(&ctx->file->poll_wait);
 out:
diff --git a/drivers/infiniband/hw/ehca/ehca_hca.c b/drivers/infiniband/hw/ehca/ehca_hca.c
index e1b618c..b7be950 100644
--- a/drivers/infiniband/hw/ehca/ehca_hca.c
+++ b/drivers/infiniband/hw/ehca/ehca_hca.c
@@ -50,7 +50,7 @@
 					      ib_device);
 	struct hipz_query_hca *rblock;
 
-	rblock = ehca_alloc_fw_ctrlblock();
+	rblock = ehca_alloc_fw_ctrlblock(GFP_KERNEL);
 	if (!rblock) {
 		ehca_err(&shca->ib_device, "Can't allocate rblock memory.");
 		return -ENOMEM;
@@ -110,7 +110,7 @@
 					      ib_device);
 	struct hipz_query_port *rblock;
 
-	rblock = ehca_alloc_fw_ctrlblock();
+	rblock = ehca_alloc_fw_ctrlblock(GFP_KERNEL);
 	if (!rblock) {
 		ehca_err(&shca->ib_device, "Can't allocate rblock memory.");
 		return -ENOMEM;
@@ -179,7 +179,7 @@
 		return -EINVAL;
 	}
 
-	rblock = ehca_alloc_fw_ctrlblock();
+	rblock = ehca_alloc_fw_ctrlblock(GFP_KERNEL);
 	if (!rblock) {
 		ehca_err(&shca->ib_device,  "Can't allocate rblock memory.");
 		return -ENOMEM;
@@ -212,7 +212,7 @@
 		return -EINVAL;
 	}
 
-	rblock = ehca_alloc_fw_ctrlblock();
+	rblock = ehca_alloc_fw_ctrlblock(GFP_KERNEL);
 	if (!rblock) {
 		ehca_err(&shca->ib_device, "Can't allocate rblock memory.");
 		return -ENOMEM;
diff --git a/drivers/infiniband/hw/ehca/ehca_irq.c b/drivers/infiniband/hw/ehca/ehca_irq.c
index c3ea746..e7209af 100644
--- a/drivers/infiniband/hw/ehca/ehca_irq.c
+++ b/drivers/infiniband/hw/ehca/ehca_irq.c
@@ -138,7 +138,7 @@
 	u64 *rblock;
 	unsigned long block_count;
 
-	rblock = ehca_alloc_fw_ctrlblock();
+	rblock = ehca_alloc_fw_ctrlblock(GFP_ATOMIC);
 	if (!rblock) {
 		ehca_err(&shca->ib_device, "Cannot allocate rblock memory.");
 		ret = -ENOMEM;
diff --git a/drivers/infiniband/hw/ehca/ehca_iverbs.h b/drivers/infiniband/hw/ehca/ehca_iverbs.h
index 3720e30..cd7789f 100644
--- a/drivers/infiniband/hw/ehca/ehca_iverbs.h
+++ b/drivers/infiniband/hw/ehca/ehca_iverbs.h
@@ -180,10 +180,10 @@
 int ehca_munmap(unsigned long addr, size_t len);
 
 #ifdef CONFIG_PPC_64K_PAGES
-void *ehca_alloc_fw_ctrlblock(void);
+void *ehca_alloc_fw_ctrlblock(gfp_t flags);
 void ehca_free_fw_ctrlblock(void *ptr);
 #else
-#define ehca_alloc_fw_ctrlblock() ((void *) get_zeroed_page(GFP_KERNEL))
+#define ehca_alloc_fw_ctrlblock(flags) ((void *) get_zeroed_page(flags))
 #define ehca_free_fw_ctrlblock(ptr) free_page((unsigned long)(ptr))
 #endif
 
diff --git a/drivers/infiniband/hw/ehca/ehca_main.c b/drivers/infiniband/hw/ehca/ehca_main.c
index cc47e4c..6574fbb 100644
--- a/drivers/infiniband/hw/ehca/ehca_main.c
+++ b/drivers/infiniband/hw/ehca/ehca_main.c
@@ -106,9 +106,9 @@
 #ifdef CONFIG_PPC_64K_PAGES
 static struct kmem_cache *ctblk_cache = NULL;
 
-void *ehca_alloc_fw_ctrlblock(void)
+void *ehca_alloc_fw_ctrlblock(gfp_t flags)
 {
-	void *ret = kmem_cache_zalloc(ctblk_cache, GFP_KERNEL);
+	void *ret = kmem_cache_zalloc(ctblk_cache, flags);
 	if (!ret)
 		ehca_gen_err("Out of memory for ctblk");
 	return ret;
@@ -206,7 +206,7 @@
 	u64 h_ret;
 	struct hipz_query_hca *rblock;
 
-	rblock = ehca_alloc_fw_ctrlblock();
+	rblock = ehca_alloc_fw_ctrlblock(GFP_KERNEL);
 	if (!rblock) {
 		ehca_gen_err("Cannot allocate rblock memory.");
 		return -ENOMEM;
@@ -258,7 +258,7 @@
 	int ret = 0;
 	struct hipz_query_hca *rblock;
 
-	rblock = ehca_alloc_fw_ctrlblock();
+	rblock = ehca_alloc_fw_ctrlblock(GFP_KERNEL);
 	if (!rblock) {
 		ehca_err(&shca->ib_device, "Can't allocate rblock memory.");
 		return -ENOMEM;
@@ -469,7 +469,7 @@
 									   \
 	shca = dev->driver_data;					   \
 									   \
-	rblock = ehca_alloc_fw_ctrlblock();				   \
+	rblock = ehca_alloc_fw_ctrlblock(GFP_KERNEL);			   \
 	if (!rblock) {						           \
 		dev_err(dev, "Can't allocate rblock memory.");		   \
 		return 0;						   \
diff --git a/drivers/infiniband/hw/ehca/ehca_mrmw.c b/drivers/infiniband/hw/ehca/ehca_mrmw.c
index 0a5e221..cfb362a 100644
--- a/drivers/infiniband/hw/ehca/ehca_mrmw.c
+++ b/drivers/infiniband/hw/ehca/ehca_mrmw.c
@@ -1013,7 +1013,7 @@
 	u32 i;
 	u64 *kpage;
 
-	kpage = ehca_alloc_fw_ctrlblock();
+	kpage = ehca_alloc_fw_ctrlblock(GFP_KERNEL);
 	if (!kpage) {
 		ehca_err(&shca->ib_device, "kpage alloc failed");
 		ret = -ENOMEM;
@@ -1124,7 +1124,7 @@
 	ehca_mrmw_map_acl(acl, &hipz_acl);
 	ehca_mrmw_set_pgsize_hipz_acl(&hipz_acl);
 
-	kpage = ehca_alloc_fw_ctrlblock();
+	kpage = ehca_alloc_fw_ctrlblock(GFP_KERNEL);
 	if (!kpage) {
 		ehca_err(&shca->ib_device, "kpage alloc failed");
 		ret = -ENOMEM;
diff --git a/drivers/infiniband/hw/ehca/ehca_qp.c b/drivers/infiniband/hw/ehca/ehca_qp.c
index c6c9cef..34b8555 100644
--- a/drivers/infiniband/hw/ehca/ehca_qp.c
+++ b/drivers/infiniband/hw/ehca/ehca_qp.c
@@ -807,7 +807,7 @@
 	unsigned long spl_flags = 0;
 
 	/* do query_qp to obtain current attr values */
-	mqpcb = ehca_alloc_fw_ctrlblock();
+	mqpcb = ehca_alloc_fw_ctrlblock(GFP_KERNEL);
 	if (!mqpcb) {
 		ehca_err(ibqp->device, "Could not get zeroed page for mqpcb "
 			 "ehca_qp=%p qp_num=%x ", my_qp, ibqp->qp_num);
@@ -1273,7 +1273,7 @@
 		return -EINVAL;
 	}
 
-	qpcb = ehca_alloc_fw_ctrlblock();
+	qpcb = ehca_alloc_fw_ctrlblock(GFP_KERNEL);
 	if (!qpcb) {
 		ehca_err(qp->device,"Out of memory for qpcb "
 			 "ehca_qp=%p qp_num=%x", my_qp, qp->qp_num);
diff --git a/drivers/infiniband/hw/mthca/mthca_cq.c b/drivers/infiniband/hw/mthca/mthca_cq.c
index 283d50b..1159c8a 100644
--- a/drivers/infiniband/hw/mthca/mthca_cq.c
+++ b/drivers/infiniband/hw/mthca/mthca_cq.c
@@ -54,6 +54,10 @@
 	MTHCA_CQ_ENTRY_SIZE = 0x20
 };
 
+enum {
+	MTHCA_ATOMIC_BYTE_LEN = 8
+};
+
 /*
  * Must be packed because start is 64 bits but only aligned to 32 bits.
  */
@@ -599,11 +603,11 @@
 			break;
 		case MTHCA_OPCODE_ATOMIC_CS:
 			entry->opcode    = IB_WC_COMP_SWAP;
-			entry->byte_len  = be32_to_cpu(cqe->byte_cnt);
+			entry->byte_len  = MTHCA_ATOMIC_BYTE_LEN;
 			break;
 		case MTHCA_OPCODE_ATOMIC_FA:
 			entry->opcode    = IB_WC_FETCH_ADD;
-			entry->byte_len  = be32_to_cpu(cqe->byte_cnt);
+			entry->byte_len  = MTHCA_ATOMIC_BYTE_LEN;
 			break;
 		case MTHCA_OPCODE_BIND_MW:
 			entry->opcode    = IB_WC_BIND_MW;
diff --git a/drivers/infiniband/hw/mthca/mthca_memfree.c b/drivers/infiniband/hw/mthca/mthca_memfree.c
index 15cc2f6..6b19645 100644
--- a/drivers/infiniband/hw/mthca/mthca_memfree.c
+++ b/drivers/infiniband/hw/mthca/mthca_memfree.c
@@ -232,7 +232,7 @@
 
 	list_for_each_entry(chunk, &icm->chunk_list, list) {
 		for (i = 0; i < chunk->npages; ++i) {
-			if (chunk->mem[i].length >= offset) {
+			if (chunk->mem[i].length > offset) {
 				page = chunk->mem[i].page;
 				goto out;
 			}
diff --git a/drivers/infiniband/hw/mthca/mthca_qp.c b/drivers/infiniband/hw/mthca/mthca_qp.c
index d844a25..5f5214c 100644
--- a/drivers/infiniband/hw/mthca/mthca_qp.c
+++ b/drivers/infiniband/hw/mthca/mthca_qp.c
@@ -429,13 +429,18 @@
 {
 	struct mthca_dev *dev = to_mdev(ibqp->device);
 	struct mthca_qp *qp = to_mqp(ibqp);
-	int err;
-	struct mthca_mailbox *mailbox;
+	int err = 0;
+	struct mthca_mailbox *mailbox = NULL;
 	struct mthca_qp_param *qp_param;
 	struct mthca_qp_context *context;
 	int mthca_state;
 	u8 status;
 
+	if (qp->state == IB_QPS_RESET) {
+		qp_attr->qp_state = IB_QPS_RESET;
+		goto done;
+	}
+
 	mailbox = mthca_alloc_mailbox(dev, GFP_KERNEL);
 	if (IS_ERR(mailbox))
 		return PTR_ERR(mailbox);
@@ -454,7 +459,6 @@
 	mthca_state = be32_to_cpu(context->flags) >> 28;
 
 	qp_attr->qp_state 	     = to_ib_qp_state(mthca_state);
-	qp_attr->cur_qp_state 	     = qp_attr->qp_state;
 	qp_attr->path_mtu 	     = context->mtu_msgmax >> 5;
 	qp_attr->path_mig_state      =
 		to_ib_mig_state((be32_to_cpu(context->flags) >> 11) & 0x3);
@@ -464,11 +468,6 @@
 	qp_attr->dest_qp_num 	     = be32_to_cpu(context->remote_qpn) & 0xffffff;
 	qp_attr->qp_access_flags     =
 		to_ib_qp_access_flags(be32_to_cpu(context->params2));
-	qp_attr->cap.max_send_wr     = qp->sq.max;
-	qp_attr->cap.max_recv_wr     = qp->rq.max;
-	qp_attr->cap.max_send_sge    = qp->sq.max_gs;
-	qp_attr->cap.max_recv_sge    = qp->rq.max_gs;
-	qp_attr->cap.max_inline_data = qp->max_inline_data;
 
 	if (qp->transport == RC || qp->transport == UC) {
 		to_ib_ah_attr(dev, &qp_attr->ah_attr, &context->pri_path);
@@ -495,7 +494,16 @@
 	qp_attr->retry_cnt 	    = (be32_to_cpu(context->params1) >> 16) & 0x7;
 	qp_attr->rnr_retry 	    = context->pri_path.rnr_retry >> 5;
 	qp_attr->alt_timeout 	    = context->alt_path.ackto >> 3;
-	qp_init_attr->cap 	    = qp_attr->cap;
+
+done:
+	qp_attr->cur_qp_state	     = qp_attr->qp_state;
+	qp_attr->cap.max_send_wr     = qp->sq.max;
+	qp_attr->cap.max_recv_wr     = qp->rq.max;
+	qp_attr->cap.max_send_sge    = qp->sq.max_gs;
+	qp_attr->cap.max_recv_sge    = qp->rq.max_gs;
+	qp_attr->cap.max_inline_data = qp->max_inline_data;
+
+	qp_init_attr->cap	     = qp_attr->cap;
 
 out:
 	mthca_free_mailbox(dev, mailbox);
diff --git a/drivers/infiniband/ulp/iser/iscsi_iser.c b/drivers/infiniband/ulp/iser/iscsi_iser.c
index 9b2041e..dd221ed 100644
--- a/drivers/infiniband/ulp/iser/iscsi_iser.c
+++ b/drivers/infiniband/ulp/iser/iscsi_iser.c
@@ -177,7 +177,7 @@
 	 * - if yes, the mtask is recycled at iscsi_complete_pdu
 	 * - if no,  the mtask is recycled at iser_snd_completion
 	 */
-	if (error && error != -EAGAIN)
+	if (error && error != -ENOBUFS)
 		iscsi_conn_failure(conn, ISCSI_ERR_CONN_FAILED);
 
 	return error;
@@ -241,7 +241,7 @@
 		error = iscsi_iser_ctask_xmit_unsol_data(conn, ctask);
 
  iscsi_iser_ctask_xmit_exit:
-	if (error && error != -EAGAIN)
+	if (error && error != -ENOBUFS)
 		iscsi_conn_failure(conn, ISCSI_ERR_CONN_FAILED);
 	return error;
 }
diff --git a/drivers/infiniband/ulp/iser/iser_initiator.c b/drivers/infiniband/ulp/iser/iser_initiator.c
index e73c87b..0a7d1ab 100644
--- a/drivers/infiniband/ulp/iser/iser_initiator.c
+++ b/drivers/infiniband/ulp/iser/iser_initiator.c
@@ -304,18 +304,14 @@
 static int
 iser_check_xmit(struct iscsi_conn *conn, void *task)
 {
-	int rc = 0;
 	struct iscsi_iser_conn *iser_conn = conn->dd_data;
 
-	write_lock_bh(conn->recv_lock);
 	if (atomic_read(&iser_conn->ib_conn->post_send_buf_count) ==
 	    ISER_QP_MAX_REQ_DTOS) {
-		iser_dbg("%ld can't xmit task %p, suspending tx\n",jiffies,task);
-		set_bit(ISCSI_SUSPEND_BIT, &conn->suspend_tx);
-		rc = -EAGAIN;
+		iser_dbg("%ld can't xmit task %p\n",jiffies,task);
+		return -ENOBUFS;
 	}
-	write_unlock_bh(conn->recv_lock);
-	return rc;
+	return 0;
 }
 
 
@@ -340,7 +336,7 @@
 		return -EPERM;
 	}
 	if (iser_check_xmit(conn, ctask))
-		return -EAGAIN;
+		return -ENOBUFS;
 
 	edtl = ntohl(hdr->data_length);
 
@@ -426,7 +422,7 @@
 	}
 
 	if (iser_check_xmit(conn, ctask))
-		return -EAGAIN;
+		return -ENOBUFS;
 
 	itt = ntohl(hdr->itt);
 	data_seg_len = ntoh24(hdr->dlength);
@@ -498,7 +494,7 @@
 	}
 
 	if (iser_check_xmit(conn,mtask))
-		return -EAGAIN;
+		return -ENOBUFS;
 
 	/* build the tx desc regd header and add it to the tx desc dto */
 	mdesc->type = ISCSI_TX_CONTROL;
@@ -605,6 +601,7 @@
 	struct iscsi_iser_conn *iser_conn = ib_conn->iser_conn;
 	struct iscsi_conn      *conn = iser_conn->iscsi_conn;
 	struct iscsi_mgmt_task *mtask;
+	int resume_tx = 0;
 
 	iser_dbg("Initiator, Data sent dto=0x%p\n", dto);
 
@@ -613,15 +610,16 @@
 	if (tx_desc->type == ISCSI_TX_DATAOUT)
 		kmem_cache_free(ig.desc_cache, tx_desc);
 
+	if (atomic_read(&iser_conn->ib_conn->post_send_buf_count) ==
+	    ISER_QP_MAX_REQ_DTOS)
+		resume_tx = 1;
+
 	atomic_dec(&ib_conn->post_send_buf_count);
 
-	write_lock(conn->recv_lock);
-	if (conn->suspend_tx) {
+	if (resume_tx) {
 		iser_dbg("%ld resuming tx\n",jiffies);
-		clear_bit(ISCSI_SUSPEND_BIT, &conn->suspend_tx);
 		scsi_queue_work(conn->session->host, &conn->xmitwork);
 	}
-	write_unlock(conn->recv_lock);
 
 	if (tx_desc->type == ISCSI_TX_CONTROL) {
 		/* this arithmetic is legal by libiscsi dd_data allocation */
diff --git a/drivers/kvm/kvm.h b/drivers/kvm/kvm.h
index 100df6f..91e0c75 100644
--- a/drivers/kvm/kvm.h
+++ b/drivers/kvm/kvm.h
@@ -52,6 +52,8 @@
 #define KVM_MAX_VCPUS 1
 #define KVM_MEMORY_SLOTS 4
 #define KVM_NUM_MMU_PAGES 256
+#define KVM_MIN_FREE_MMU_PAGES 5
+#define KVM_REFILL_PAGES 25
 
 #define FX_IMAGE_SIZE 512
 #define FX_IMAGE_ALIGN 16
@@ -89,14 +91,54 @@
 typedef u64            hpa_t;
 typedef unsigned long  hfn_t;
 
+#define NR_PTE_CHAIN_ENTRIES 5
+
+struct kvm_pte_chain {
+	u64 *parent_ptes[NR_PTE_CHAIN_ENTRIES];
+	struct hlist_node link;
+};
+
+/*
+ * kvm_mmu_page_role, below, is defined as:
+ *
+ *   bits 0:3 - total guest paging levels (2-4, or zero for real mode)
+ *   bits 4:7 - page table level for this shadow (1-4)
+ *   bits 8:9 - page table quadrant for 2-level guests
+ *   bit   16 - "metaphysical" - gfn is not a real page (huge page/real mode)
+ */
+union kvm_mmu_page_role {
+	unsigned word;
+	struct {
+		unsigned glevels : 4;
+		unsigned level : 4;
+		unsigned quadrant : 2;
+		unsigned pad_for_nice_hex_output : 6;
+		unsigned metaphysical : 1;
+	};
+};
+
 struct kvm_mmu_page {
 	struct list_head link;
+	struct hlist_node hash_link;
+
+	/*
+	 * The following two entries are used to key the shadow page in the
+	 * hash table.
+	 */
+	gfn_t gfn;
+	union kvm_mmu_page_role role;
+
 	hpa_t page_hpa;
 	unsigned long slot_bitmap; /* One bit set per slot which has memory
 				    * in this shadow page.
 				    */
 	int global;              /* Set if all ptes in this page are global */
-	u64 *parent_pte;
+	int multimapped;         /* More than one parent_pte? */
+	int root_count;          /* Currently serving as active root */
+	union {
+		u64 *parent_pte;               /* !multimapped */
+		struct hlist_head parent_ptes; /* multimapped, kvm_pte_chain */
+	};
 };
 
 struct vmcs {
@@ -117,14 +159,26 @@
 struct kvm_mmu {
 	void (*new_cr3)(struct kvm_vcpu *vcpu);
 	int (*page_fault)(struct kvm_vcpu *vcpu, gva_t gva, u32 err);
-	void (*inval_page)(struct kvm_vcpu *vcpu, gva_t gva);
 	void (*free)(struct kvm_vcpu *vcpu);
 	gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t gva);
 	hpa_t root_hpa;
 	int root_level;
 	int shadow_root_level;
+
+	u64 *pae_root;
 };
 
+#define KVM_NR_MEM_OBJS 20
+
+struct kvm_mmu_memory_cache {
+	int nobjs;
+	void *objects[KVM_NR_MEM_OBJS];
+};
+
+/*
+ * We don't want allocation failures within the mmu code, so we preallocate
+ * enough memory for a single page fault in a cache.
+ */
 struct kvm_guest_debug {
 	int enabled;
 	unsigned long bp[4];
@@ -173,6 +227,7 @@
 	struct mutex mutex;
 	int   cpu;
 	int   launched;
+	int interrupt_window_open;
 	unsigned long irq_summary; /* bit vector: 1 per word in irq_pending */
 #define NR_IRQ_WORDS KVM_IRQ_BITMAP_SIZE(unsigned long)
 	unsigned long irq_pending[NR_IRQ_WORDS];
@@ -184,6 +239,7 @@
 	unsigned long cr3;
 	unsigned long cr4;
 	unsigned long cr8;
+	u64 pdptrs[4]; /* pae */
 	u64 shadow_efer;
 	u64 apic_base;
 	int nmsrs;
@@ -194,6 +250,12 @@
 	struct kvm_mmu_page page_header_buf[KVM_NUM_MMU_PAGES];
 	struct kvm_mmu mmu;
 
+	struct kvm_mmu_memory_cache mmu_pte_chain_cache;
+	struct kvm_mmu_memory_cache mmu_rmap_desc_cache;
+
+	gfn_t last_pt_write_gfn;
+	int   last_pt_write_count;
+
 	struct kvm_guest_debug guest_debug;
 
 	char fx_buf[FX_BUF_SIZE];
@@ -231,10 +293,16 @@
 	spinlock_t lock; /* protects everything except vcpus */
 	int nmemslots;
 	struct kvm_memory_slot memslots[KVM_MEMORY_SLOTS];
+	/*
+	 * Hash table of struct kvm_mmu_page.
+	 */
 	struct list_head active_mmu_pages;
+	int n_free_mmu_pages;
+	struct hlist_head mmu_page_hash[KVM_NUM_MMU_PAGES];
 	struct kvm_vcpu vcpus[KVM_MAX_VCPUS];
 	int memory_config_version;
 	int busy;
+	unsigned long rmap_overflow;
 };
 
 struct kvm_stat {
@@ -247,6 +315,9 @@
 	u32 io_exits;
 	u32 mmio_exits;
 	u32 signal_exits;
+	u32 irq_window_exits;
+	u32 halt_exits;
+	u32 request_irq_exits;
 	u32 irq_exits;
 };
 
@@ -279,6 +350,7 @@
 	void (*set_segment)(struct kvm_vcpu *vcpu,
 			    struct kvm_segment *var, int seg);
 	void (*get_cs_db_l_bits)(struct kvm_vcpu *vcpu, int *db, int *l);
+	void (*decache_cr0_cr4_guest_bits)(struct kvm_vcpu *vcpu);
 	void (*set_cr0)(struct kvm_vcpu *vcpu, unsigned long cr0);
 	void (*set_cr0_no_modeswitch)(struct kvm_vcpu *vcpu,
 				      unsigned long cr0);
@@ -323,7 +395,7 @@
 int kvm_mmu_setup(struct kvm_vcpu *vcpu);
 
 int kvm_mmu_reset_context(struct kvm_vcpu *vcpu);
-void kvm_mmu_slot_remove_write_access(struct kvm *kvm, int slot);
+void kvm_mmu_slot_remove_write_access(struct kvm_vcpu *vcpu, int slot);
 
 hpa_t gpa_to_hpa(struct kvm_vcpu *vcpu, gpa_t gpa);
 #define HPA_MSB ((sizeof(hpa_t) * 8) - 1)
@@ -396,6 +468,19 @@
 
 unsigned long segment_base(u16 selector);
 
+void kvm_mmu_pre_write(struct kvm_vcpu *vcpu, gpa_t gpa, int bytes);
+void kvm_mmu_post_write(struct kvm_vcpu *vcpu, gpa_t gpa, int bytes);
+int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva);
+void kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu);
+
+static inline int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t gva,
+				     u32 error_code)
+{
+	if (unlikely(vcpu->kvm->n_free_mmu_pages < KVM_MIN_FREE_MMU_PAGES))
+		kvm_mmu_free_some_pages(vcpu);
+	return vcpu->mmu.page_fault(vcpu, gva, error_code);
+}
+
 static inline struct page *_gfn_to_page(struct kvm *kvm, gfn_t gfn)
 {
 	struct kvm_memory_slot *slot = gfn_to_memslot(kvm, gfn);
@@ -541,19 +626,4 @@
 #define TSS_REDIRECTION_SIZE (256 / 8)
 #define RMODE_TSS_SIZE (TSS_BASE_SIZE + TSS_REDIRECTION_SIZE + TSS_IOPB_SIZE + 1)
 
-#ifdef CONFIG_X86_64
-
-/*
- * When emulating 32-bit mode, cr3 is only 32 bits even on x86_64.  Therefore
- * we need to allocate shadow page tables in the first 4GB of memory, which
- * happens to fit the DMA32 zone.
- */
-#define GFP_KVM_MMU (GFP_KERNEL | __GFP_DMA32)
-
-#else
-
-#define GFP_KVM_MMU GFP_KERNEL
-
-#endif
-
 #endif
diff --git a/drivers/kvm/kvm_main.c b/drivers/kvm/kvm_main.c
index ce7fe64..67c1154 100644
--- a/drivers/kvm/kvm_main.c
+++ b/drivers/kvm/kvm_main.c
@@ -58,6 +58,9 @@
 	{ "io_exits", &kvm_stat.io_exits },
 	{ "mmio_exits", &kvm_stat.mmio_exits },
 	{ "signal_exits", &kvm_stat.signal_exits },
+	{ "irq_window", &kvm_stat.irq_window_exits },
+	{ "halt_exits", &kvm_stat.halt_exits },
+	{ "request_irq", &kvm_stat.request_irq_exits },
 	{ "irq_exits", &kvm_stat.irq_exits },
 	{ 0, 0 }
 };
@@ -227,6 +230,7 @@
 		struct kvm_vcpu *vcpu = &kvm->vcpus[i];
 
 		mutex_init(&vcpu->mutex);
+		vcpu->kvm = kvm;
 		vcpu->mmu.root_hpa = INVALID_PAGE;
 		INIT_LIST_HEAD(&vcpu->free_pages);
 	}
@@ -268,8 +272,8 @@
 
 static void kvm_free_vcpu(struct kvm_vcpu *vcpu)
 {
-	kvm_arch_ops->vcpu_free(vcpu);
 	kvm_mmu_destroy(vcpu);
+	kvm_arch_ops->vcpu_free(vcpu);
 }
 
 static void kvm_free_vcpus(struct kvm *kvm)
@@ -295,14 +299,17 @@
 	kvm_arch_ops->inject_gp(vcpu, 0);
 }
 
-static int pdptrs_have_reserved_bits_set(struct kvm_vcpu *vcpu,
-					 unsigned long cr3)
+/*
+ * Load the pae pdptrs.  Return true is they are all valid.
+ */
+static int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3)
 {
 	gfn_t pdpt_gfn = cr3 >> PAGE_SHIFT;
-	unsigned offset = (cr3 & (PAGE_SIZE-1)) >> 5;
+	unsigned offset = ((cr3 & (PAGE_SIZE-1)) >> 5) << 2;
 	int i;
 	u64 pdpte;
 	u64 *pdpt;
+	int ret;
 	struct kvm_memory_slot *memslot;
 
 	spin_lock(&vcpu->kvm->lock);
@@ -310,16 +317,23 @@
 	/* FIXME: !memslot - emulate? 0xff? */
 	pdpt = kmap_atomic(gfn_to_page(memslot, pdpt_gfn), KM_USER0);
 
+	ret = 1;
 	for (i = 0; i < 4; ++i) {
 		pdpte = pdpt[offset + i];
-		if ((pdpte & 1) && (pdpte & 0xfffffff0000001e6ull))
-			break;
+		if ((pdpte & 1) && (pdpte & 0xfffffff0000001e6ull)) {
+			ret = 0;
+			goto out;
+		}
 	}
 
+	for (i = 0; i < 4; ++i)
+		vcpu->pdptrs[i] = pdpt[offset + i];
+
+out:
 	kunmap_atomic(pdpt, KM_USER0);
 	spin_unlock(&vcpu->kvm->lock);
 
-	return i != 4;
+	return ret;
 }
 
 void set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
@@ -365,8 +379,7 @@
 			}
 		} else
 #endif
-		if (is_pae(vcpu) &&
-			    pdptrs_have_reserved_bits_set(vcpu, vcpu->cr3)) {
+		if (is_pae(vcpu) && !load_pdptrs(vcpu, vcpu->cr3)) {
 			printk(KERN_DEBUG "set_cr0: #GP, pdptrs "
 			       "reserved bits\n");
 			inject_gp(vcpu);
@@ -387,6 +400,7 @@
 
 void lmsw(struct kvm_vcpu *vcpu, unsigned long msw)
 {
+	kvm_arch_ops->decache_cr0_cr4_guest_bits(vcpu);
 	set_cr0(vcpu, (vcpu->cr0 & ~0x0ful) | (msw & 0x0f));
 }
 EXPORT_SYMBOL_GPL(lmsw);
@@ -407,7 +421,7 @@
 			return;
 		}
 	} else if (is_paging(vcpu) && !is_pae(vcpu) && (cr4 & CR4_PAE_MASK)
-		   && pdptrs_have_reserved_bits_set(vcpu, vcpu->cr3)) {
+		   && !load_pdptrs(vcpu, vcpu->cr3)) {
 		printk(KERN_DEBUG "set_cr4: #GP, pdptrs reserved bits\n");
 		inject_gp(vcpu);
 	}
@@ -439,7 +453,7 @@
 			return;
 		}
 		if (is_paging(vcpu) && is_pae(vcpu) &&
-		    pdptrs_have_reserved_bits_set(vcpu, cr3)) {
+		    !load_pdptrs(vcpu, cr3)) {
 			printk(KERN_DEBUG "set_cr3: #GP, pdptrs "
 			       "reserved bits\n");
 			inject_gp(vcpu);
@@ -449,7 +463,19 @@
 
 	vcpu->cr3 = cr3;
 	spin_lock(&vcpu->kvm->lock);
-	vcpu->mmu.new_cr3(vcpu);
+	/*
+	 * Does the new cr3 value map to physical memory? (Note, we
+	 * catch an invalid cr3 even in real-mode, because it would
+	 * cause trouble later on when we turn on paging anyway.)
+	 *
+	 * A real CPU would silently accept an invalid cr3 and would
+	 * attempt to use it - with largely undefined (and often hard
+	 * to debug) behavior on the guest side.
+	 */
+	if (unlikely(!gfn_to_memslot(vcpu->kvm, cr3 >> PAGE_SHIFT)))
+		inject_gp(vcpu);
+	else
+		vcpu->mmu.new_cr3(vcpu);
 	spin_unlock(&vcpu->kvm->lock);
 }
 EXPORT_SYMBOL_GPL(set_cr3);
@@ -517,7 +543,6 @@
 	vcpu->guest_fx_image = vcpu->host_fx_image + FX_IMAGE_SIZE;
 
 	vcpu->cpu = -1;  /* First load will set up TR */
-	vcpu->kvm = kvm;
 	r = kvm_arch_ops->vcpu_create(vcpu);
 	if (r < 0)
 		goto out_free_vcpus;
@@ -634,6 +659,7 @@
 						     | __GFP_ZERO);
 			if (!new.phys_mem[i])
 				goto out_free;
+ 			new.phys_mem[i]->private = 0;
 		}
 	}
 
@@ -688,6 +714,13 @@
 	return r;
 }
 
+static void do_remove_write_access(struct kvm_vcpu *vcpu, int slot)
+{
+	spin_lock(&vcpu->kvm->lock);
+	kvm_mmu_slot_remove_write_access(vcpu, slot);
+	spin_unlock(&vcpu->kvm->lock);
+}
+
 /*
  * Get (and clear) the dirty memory log for a memory slot.
  */
@@ -697,6 +730,7 @@
 	struct kvm_memory_slot *memslot;
 	int r, i;
 	int n;
+	int cleared;
 	unsigned long any = 0;
 
 	spin_lock(&kvm->lock);
@@ -727,15 +761,17 @@
 
 
 	if (any) {
-		spin_lock(&kvm->lock);
-		kvm_mmu_slot_remove_write_access(kvm, log->slot);
-		spin_unlock(&kvm->lock);
-		memset(memslot->dirty_bitmap, 0, n);
+		cleared = 0;
 		for (i = 0; i < KVM_MAX_VCPUS; ++i) {
 			struct kvm_vcpu *vcpu = vcpu_load(kvm, i);
 
 			if (!vcpu)
 				continue;
+			if (!cleared) {
+				do_remove_write_access(vcpu, log->slot);
+				memset(memslot->dirty_bitmap, 0, n);
+				cleared = 1;
+			}
 			kvm_arch_ops->tlb_flush(vcpu);
 			vcpu_put(vcpu);
 		}
@@ -863,6 +899,27 @@
 	}
 }
 
+static int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa,
+			       unsigned long val, int bytes)
+{
+	struct kvm_memory_slot *m;
+	struct page *page;
+	void *virt;
+
+	if (((gpa + bytes - 1) >> PAGE_SHIFT) != (gpa >> PAGE_SHIFT))
+		return 0;
+	m = gfn_to_memslot(vcpu->kvm, gpa >> PAGE_SHIFT);
+	if (!m)
+		return 0;
+	page = gfn_to_page(m, gpa >> PAGE_SHIFT);
+	kvm_mmu_pre_write(vcpu, gpa, bytes);
+	virt = kmap_atomic(page, KM_USER0);
+	memcpy(virt + offset_in_page(gpa), &val, bytes);
+	kunmap_atomic(virt, KM_USER0);
+	kvm_mmu_post_write(vcpu, gpa, bytes);
+	return 1;
+}
+
 static int emulator_write_emulated(unsigned long addr,
 				   unsigned long val,
 				   unsigned int bytes,
@@ -874,6 +931,9 @@
 	if (gpa == UNMAPPED_GVA)
 		return X86EMUL_PROPAGATE_FAULT;
 
+	if (emulator_write_phys(vcpu, gpa, val, bytes))
+		return X86EMUL_CONTINUE;
+
 	vcpu->mmio_needed = 1;
 	vcpu->mmio_phys_addr = gpa;
 	vcpu->mmio_size = bytes;
@@ -898,6 +958,30 @@
 	return emulator_write_emulated(addr, new, bytes, ctxt);
 }
 
+#ifdef CONFIG_X86_32
+
+static int emulator_cmpxchg8b_emulated(unsigned long addr,
+				       unsigned long old_lo,
+				       unsigned long old_hi,
+				       unsigned long new_lo,
+				       unsigned long new_hi,
+				       struct x86_emulate_ctxt *ctxt)
+{
+	static int reported;
+	int r;
+
+	if (!reported) {
+		reported = 1;
+		printk(KERN_WARNING "kvm: emulating exchange8b as write\n");
+	}
+	r = emulator_write_emulated(addr, new_lo, 4, ctxt);
+	if (r != X86EMUL_CONTINUE)
+		return r;
+	return emulator_write_emulated(addr+4, new_hi, 4, ctxt);
+}
+
+#endif
+
 static unsigned long get_segment_base(struct kvm_vcpu *vcpu, int seg)
 {
 	return kvm_arch_ops->get_segment_base(vcpu, seg);
@@ -905,18 +989,15 @@
 
 int emulate_invlpg(struct kvm_vcpu *vcpu, gva_t address)
 {
-	spin_lock(&vcpu->kvm->lock);
-	vcpu->mmu.inval_page(vcpu, address);
-	spin_unlock(&vcpu->kvm->lock);
-	kvm_arch_ops->invlpg(vcpu, address);
 	return X86EMUL_CONTINUE;
 }
 
 int emulate_clts(struct kvm_vcpu *vcpu)
 {
-	unsigned long cr0 = vcpu->cr0;
+	unsigned long cr0;
 
-	cr0 &= ~CR0_TS_MASK;
+	kvm_arch_ops->decache_cr0_cr4_guest_bits(vcpu);
+	cr0 = vcpu->cr0 & ~CR0_TS_MASK;
 	kvm_arch_ops->set_cr0(vcpu, cr0);
 	return X86EMUL_CONTINUE;
 }
@@ -975,6 +1056,9 @@
 	.read_emulated       = emulator_read_emulated,
 	.write_emulated      = emulator_write_emulated,
 	.cmpxchg_emulated    = emulator_cmpxchg_emulated,
+#ifdef CONFIG_X86_32
+	.cmpxchg8b_emulated  = emulator_cmpxchg8b_emulated,
+#endif
 };
 
 int emulate_instruction(struct kvm_vcpu *vcpu,
@@ -1024,6 +1108,8 @@
 	}
 
 	if (r) {
+		if (kvm_mmu_unprotect_page_virt(vcpu, cr2))
+			return EMULATE_DONE;
 		if (!vcpu->mmio_needed) {
 			report_emulation_failure(&emulate_ctxt);
 			return EMULATE_FAIL;
@@ -1069,6 +1155,7 @@
 
 unsigned long realmode_get_cr(struct kvm_vcpu *vcpu, int cr)
 {
+	kvm_arch_ops->decache_cr0_cr4_guest_bits(vcpu);
 	switch (cr) {
 	case 0:
 		return vcpu->cr0;
@@ -1403,6 +1490,7 @@
 	sregs->gdt.limit = dt.limit;
 	sregs->gdt.base = dt.base;
 
+	kvm_arch_ops->decache_cr0_cr4_guest_bits(vcpu);
 	sregs->cr0 = vcpu->cr0;
 	sregs->cr2 = vcpu->cr2;
 	sregs->cr3 = vcpu->cr3;
@@ -1467,11 +1555,15 @@
 #endif
 	vcpu->apic_base = sregs->apic_base;
 
+	kvm_arch_ops->decache_cr0_cr4_guest_bits(vcpu);
+
 	mmu_reset_needed |= vcpu->cr0 != sregs->cr0;
 	kvm_arch_ops->set_cr0_no_modeswitch(vcpu, sregs->cr0);
 
 	mmu_reset_needed |= vcpu->cr4 != sregs->cr4;
 	kvm_arch_ops->set_cr4(vcpu, sregs->cr4);
+	if (!is_long_mode(vcpu) && is_pae(vcpu))
+		load_pdptrs(vcpu, vcpu->cr3);
 
 	if (mmu_reset_needed)
 		kvm_mmu_reset_context(vcpu);
@@ -1693,12 +1785,12 @@
 		if (copy_from_user(&kvm_run, (void *)arg, sizeof kvm_run))
 			goto out;
 		r = kvm_dev_ioctl_run(kvm, &kvm_run);
-		if (r < 0)
+		if (r < 0 &&  r != -EINTR)
 			goto out;
-		r = -EFAULT;
-		if (copy_to_user((void *)arg, &kvm_run, sizeof kvm_run))
+		if (copy_to_user((void *)arg, &kvm_run, sizeof kvm_run)) {
+			r = -EFAULT;
 			goto out;
-		r = 0;
+		}
 		break;
 	}
 	case KVM_GET_REGS: {
@@ -1842,6 +1934,7 @@
 				 num_msrs_to_save * sizeof(u32)))
 			goto out;
 		r = 0;
+		break;
 	}
 	default:
 		;
@@ -1944,17 +2037,17 @@
 		return -EEXIST;
 	}
 
-	kvm_arch_ops = ops;
-
-	if (!kvm_arch_ops->cpu_has_kvm_support()) {
+	if (!ops->cpu_has_kvm_support()) {
 		printk(KERN_ERR "kvm: no hardware support\n");
 		return -EOPNOTSUPP;
 	}
-	if (kvm_arch_ops->disabled_by_bios()) {
+	if (ops->disabled_by_bios()) {
 		printk(KERN_ERR "kvm: disabled by bios\n");
 		return -EOPNOTSUPP;
 	}
 
+	kvm_arch_ops = ops;
+
 	r = kvm_arch_ops->hardware_setup();
 	if (r < 0)
 	    return r;
diff --git a/drivers/kvm/mmu.c b/drivers/kvm/mmu.c
index 790423c..c6f9729 100644
--- a/drivers/kvm/mmu.c
+++ b/drivers/kvm/mmu.c
@@ -26,7 +26,31 @@
 #include "vmx.h"
 #include "kvm.h"
 
+#undef MMU_DEBUG
+
+#undef AUDIT
+
+#ifdef AUDIT
+static void kvm_mmu_audit(struct kvm_vcpu *vcpu, const char *msg);
+#else
+static void kvm_mmu_audit(struct kvm_vcpu *vcpu, const char *msg) {}
+#endif
+
+#ifdef MMU_DEBUG
+
+#define pgprintk(x...) do { if (dbg) printk(x); } while (0)
+#define rmap_printk(x...) do { if (dbg) printk(x); } while (0)
+
+#else
+
 #define pgprintk(x...) do { } while (0)
+#define rmap_printk(x...) do { } while (0)
+
+#endif
+
+#if defined(MMU_DEBUG) || defined(AUDIT)
+static int dbg = 1;
+#endif
 
 #define ASSERT(x)							\
 	if (!(x)) {							\
@@ -34,8 +58,10 @@
 		       __FILE__, __LINE__, #x);				\
 	}
 
-#define PT64_ENT_PER_PAGE 512
-#define PT32_ENT_PER_PAGE 1024
+#define PT64_PT_BITS 9
+#define PT64_ENT_PER_PAGE (1 << PT64_PT_BITS)
+#define PT32_PT_BITS 10
+#define PT32_ENT_PER_PAGE (1 << PT32_PT_BITS)
 
 #define PT_WRITABLE_SHIFT 1
 
@@ -125,6 +151,13 @@
 #define PT_DIRECTORY_LEVEL 2
 #define PT_PAGE_TABLE_LEVEL 1
 
+#define RMAP_EXT 4
+
+struct kvm_rmap_desc {
+	u64 *shadow_ptes[RMAP_EXT];
+	struct kvm_rmap_desc *more;
+};
+
 static int is_write_protection(struct kvm_vcpu *vcpu)
 {
 	return vcpu->cr0 & CR0_WP_MASK;
@@ -150,32 +183,272 @@
 	return pte & PT_SHADOW_IO_MARK;
 }
 
-static void kvm_mmu_free_page(struct kvm_vcpu *vcpu, hpa_t page_hpa)
+static int is_rmap_pte(u64 pte)
 {
-	struct kvm_mmu_page *page_head = page_header(page_hpa);
+	return (pte & (PT_WRITABLE_MASK | PT_PRESENT_MASK))
+		== (PT_WRITABLE_MASK | PT_PRESENT_MASK);
+}
 
-	list_del(&page_head->link);
-	page_head->page_hpa = page_hpa;
-	list_add(&page_head->link, &vcpu->free_pages);
+static int mmu_topup_memory_cache(struct kvm_mmu_memory_cache *cache,
+				  size_t objsize, int min)
+{
+	void *obj;
+
+	if (cache->nobjs >= min)
+		return 0;
+	while (cache->nobjs < ARRAY_SIZE(cache->objects)) {
+		obj = kzalloc(objsize, GFP_NOWAIT);
+		if (!obj)
+			return -ENOMEM;
+		cache->objects[cache->nobjs++] = obj;
+	}
+	return 0;
+}
+
+static void mmu_free_memory_cache(struct kvm_mmu_memory_cache *mc)
+{
+	while (mc->nobjs)
+		kfree(mc->objects[--mc->nobjs]);
+}
+
+static int mmu_topup_memory_caches(struct kvm_vcpu *vcpu)
+{
+	int r;
+
+	r = mmu_topup_memory_cache(&vcpu->mmu_pte_chain_cache,
+				   sizeof(struct kvm_pte_chain), 4);
+	if (r)
+		goto out;
+	r = mmu_topup_memory_cache(&vcpu->mmu_rmap_desc_cache,
+				   sizeof(struct kvm_rmap_desc), 1);
+out:
+	return r;
+}
+
+static void mmu_free_memory_caches(struct kvm_vcpu *vcpu)
+{
+	mmu_free_memory_cache(&vcpu->mmu_pte_chain_cache);
+	mmu_free_memory_cache(&vcpu->mmu_rmap_desc_cache);
+}
+
+static void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc,
+				    size_t size)
+{
+	void *p;
+
+	BUG_ON(!mc->nobjs);
+	p = mc->objects[--mc->nobjs];
+	memset(p, 0, size);
+	return p;
+}
+
+static void mmu_memory_cache_free(struct kvm_mmu_memory_cache *mc, void *obj)
+{
+	if (mc->nobjs < KVM_NR_MEM_OBJS)
+		mc->objects[mc->nobjs++] = obj;
+	else
+		kfree(obj);
+}
+
+static struct kvm_pte_chain *mmu_alloc_pte_chain(struct kvm_vcpu *vcpu)
+{
+	return mmu_memory_cache_alloc(&vcpu->mmu_pte_chain_cache,
+				      sizeof(struct kvm_pte_chain));
+}
+
+static void mmu_free_pte_chain(struct kvm_vcpu *vcpu,
+			       struct kvm_pte_chain *pc)
+{
+	mmu_memory_cache_free(&vcpu->mmu_pte_chain_cache, pc);
+}
+
+static struct kvm_rmap_desc *mmu_alloc_rmap_desc(struct kvm_vcpu *vcpu)
+{
+	return mmu_memory_cache_alloc(&vcpu->mmu_rmap_desc_cache,
+				      sizeof(struct kvm_rmap_desc));
+}
+
+static void mmu_free_rmap_desc(struct kvm_vcpu *vcpu,
+			       struct kvm_rmap_desc *rd)
+{
+	mmu_memory_cache_free(&vcpu->mmu_rmap_desc_cache, rd);
+}
+
+/*
+ * Reverse mapping data structures:
+ *
+ * If page->private bit zero is zero, then page->private points to the
+ * shadow page table entry that points to page_address(page).
+ *
+ * If page->private bit zero is one, (then page->private & ~1) points
+ * to a struct kvm_rmap_desc containing more mappings.
+ */
+static void rmap_add(struct kvm_vcpu *vcpu, u64 *spte)
+{
+	struct page *page;
+	struct kvm_rmap_desc *desc;
+	int i;
+
+	if (!is_rmap_pte(*spte))
+		return;
+	page = pfn_to_page((*spte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT);
+	if (!page->private) {
+		rmap_printk("rmap_add: %p %llx 0->1\n", spte, *spte);
+		page->private = (unsigned long)spte;
+	} else if (!(page->private & 1)) {
+		rmap_printk("rmap_add: %p %llx 1->many\n", spte, *spte);
+		desc = mmu_alloc_rmap_desc(vcpu);
+		desc->shadow_ptes[0] = (u64 *)page->private;
+		desc->shadow_ptes[1] = spte;
+		page->private = (unsigned long)desc | 1;
+	} else {
+		rmap_printk("rmap_add: %p %llx many->many\n", spte, *spte);
+		desc = (struct kvm_rmap_desc *)(page->private & ~1ul);
+		while (desc->shadow_ptes[RMAP_EXT-1] && desc->more)
+			desc = desc->more;
+		if (desc->shadow_ptes[RMAP_EXT-1]) {
+			desc->more = mmu_alloc_rmap_desc(vcpu);
+			desc = desc->more;
+		}
+		for (i = 0; desc->shadow_ptes[i]; ++i)
+			;
+		desc->shadow_ptes[i] = spte;
+	}
+}
+
+static void rmap_desc_remove_entry(struct kvm_vcpu *vcpu,
+				   struct page *page,
+				   struct kvm_rmap_desc *desc,
+				   int i,
+				   struct kvm_rmap_desc *prev_desc)
+{
+	int j;
+
+	for (j = RMAP_EXT - 1; !desc->shadow_ptes[j] && j > i; --j)
+		;
+	desc->shadow_ptes[i] = desc->shadow_ptes[j];
+	desc->shadow_ptes[j] = 0;
+	if (j != 0)
+		return;
+	if (!prev_desc && !desc->more)
+		page->private = (unsigned long)desc->shadow_ptes[0];
+	else
+		if (prev_desc)
+			prev_desc->more = desc->more;
+		else
+			page->private = (unsigned long)desc->more | 1;
+	mmu_free_rmap_desc(vcpu, desc);
+}
+
+static void rmap_remove(struct kvm_vcpu *vcpu, u64 *spte)
+{
+	struct page *page;
+	struct kvm_rmap_desc *desc;
+	struct kvm_rmap_desc *prev_desc;
+	int i;
+
+	if (!is_rmap_pte(*spte))
+		return;
+	page = pfn_to_page((*spte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT);
+	if (!page->private) {
+		printk(KERN_ERR "rmap_remove: %p %llx 0->BUG\n", spte, *spte);
+		BUG();
+	} else if (!(page->private & 1)) {
+		rmap_printk("rmap_remove:  %p %llx 1->0\n", spte, *spte);
+		if ((u64 *)page->private != spte) {
+			printk(KERN_ERR "rmap_remove:  %p %llx 1->BUG\n",
+			       spte, *spte);
+			BUG();
+		}
+		page->private = 0;
+	} else {
+		rmap_printk("rmap_remove:  %p %llx many->many\n", spte, *spte);
+		desc = (struct kvm_rmap_desc *)(page->private & ~1ul);
+		prev_desc = NULL;
+		while (desc) {
+			for (i = 0; i < RMAP_EXT && desc->shadow_ptes[i]; ++i)
+				if (desc->shadow_ptes[i] == spte) {
+					rmap_desc_remove_entry(vcpu, page,
+							       desc, i,
+							       prev_desc);
+					return;
+				}
+			prev_desc = desc;
+			desc = desc->more;
+		}
+		BUG();
+	}
+}
+
+static void rmap_write_protect(struct kvm_vcpu *vcpu, u64 gfn)
+{
+	struct kvm *kvm = vcpu->kvm;
+	struct page *page;
+	struct kvm_memory_slot *slot;
+	struct kvm_rmap_desc *desc;
+	u64 *spte;
+
+	slot = gfn_to_memslot(kvm, gfn);
+	BUG_ON(!slot);
+	page = gfn_to_page(slot, gfn);
+
+	while (page->private) {
+		if (!(page->private & 1))
+			spte = (u64 *)page->private;
+		else {
+			desc = (struct kvm_rmap_desc *)(page->private & ~1ul);
+			spte = desc->shadow_ptes[0];
+		}
+		BUG_ON(!spte);
+		BUG_ON((*spte & PT64_BASE_ADDR_MASK) !=
+		       page_to_pfn(page) << PAGE_SHIFT);
+		BUG_ON(!(*spte & PT_PRESENT_MASK));
+		BUG_ON(!(*spte & PT_WRITABLE_MASK));
+		rmap_printk("rmap_write_protect: spte %p %llx\n", spte, *spte);
+		rmap_remove(vcpu, spte);
+		kvm_arch_ops->tlb_flush(vcpu);
+		*spte &= ~(u64)PT_WRITABLE_MASK;
+	}
 }
 
 static int is_empty_shadow_page(hpa_t page_hpa)
 {
-	u32 *pos;
-	u32 *end;
-	for (pos = __va(page_hpa), end = pos + PAGE_SIZE / sizeof(u32);
+	u64 *pos;
+	u64 *end;
+
+	for (pos = __va(page_hpa), end = pos + PAGE_SIZE / sizeof(u64);
 		      pos != end; pos++)
-		if (*pos != 0)
+		if (*pos != 0) {
+			printk(KERN_ERR "%s: %p %llx\n", __FUNCTION__,
+			       pos, *pos);
 			return 0;
+		}
 	return 1;
 }
 
-static hpa_t kvm_mmu_alloc_page(struct kvm_vcpu *vcpu, u64 *parent_pte)
+static void kvm_mmu_free_page(struct kvm_vcpu *vcpu, hpa_t page_hpa)
+{
+	struct kvm_mmu_page *page_head = page_header(page_hpa);
+
+	ASSERT(is_empty_shadow_page(page_hpa));
+	list_del(&page_head->link);
+	page_head->page_hpa = page_hpa;
+	list_add(&page_head->link, &vcpu->free_pages);
+	++vcpu->kvm->n_free_mmu_pages;
+}
+
+static unsigned kvm_page_table_hashfn(gfn_t gfn)
+{
+	return gfn;
+}
+
+static struct kvm_mmu_page *kvm_mmu_alloc_page(struct kvm_vcpu *vcpu,
+					       u64 *parent_pte)
 {
 	struct kvm_mmu_page *page;
 
 	if (list_empty(&vcpu->free_pages))
-		return INVALID_PAGE;
+		return NULL;
 
 	page = list_entry(vcpu->free_pages.next, struct kvm_mmu_page, link);
 	list_del(&page->link);
@@ -183,8 +456,239 @@
 	ASSERT(is_empty_shadow_page(page->page_hpa));
 	page->slot_bitmap = 0;
 	page->global = 1;
+	page->multimapped = 0;
 	page->parent_pte = parent_pte;
-	return page->page_hpa;
+	--vcpu->kvm->n_free_mmu_pages;
+	return page;
+}
+
+static void mmu_page_add_parent_pte(struct kvm_vcpu *vcpu,
+				    struct kvm_mmu_page *page, u64 *parent_pte)
+{
+	struct kvm_pte_chain *pte_chain;
+	struct hlist_node *node;
+	int i;
+
+	if (!parent_pte)
+		return;
+	if (!page->multimapped) {
+		u64 *old = page->parent_pte;
+
+		if (!old) {
+			page->parent_pte = parent_pte;
+			return;
+		}
+		page->multimapped = 1;
+		pte_chain = mmu_alloc_pte_chain(vcpu);
+		INIT_HLIST_HEAD(&page->parent_ptes);
+		hlist_add_head(&pte_chain->link, &page->parent_ptes);
+		pte_chain->parent_ptes[0] = old;
+	}
+	hlist_for_each_entry(pte_chain, node, &page->parent_ptes, link) {
+		if (pte_chain->parent_ptes[NR_PTE_CHAIN_ENTRIES-1])
+			continue;
+		for (i = 0; i < NR_PTE_CHAIN_ENTRIES; ++i)
+			if (!pte_chain->parent_ptes[i]) {
+				pte_chain->parent_ptes[i] = parent_pte;
+				return;
+			}
+	}
+	pte_chain = mmu_alloc_pte_chain(vcpu);
+	BUG_ON(!pte_chain);
+	hlist_add_head(&pte_chain->link, &page->parent_ptes);
+	pte_chain->parent_ptes[0] = parent_pte;
+}
+
+static void mmu_page_remove_parent_pte(struct kvm_vcpu *vcpu,
+				       struct kvm_mmu_page *page,
+				       u64 *parent_pte)
+{
+	struct kvm_pte_chain *pte_chain;
+	struct hlist_node *node;
+	int i;
+
+	if (!page->multimapped) {
+		BUG_ON(page->parent_pte != parent_pte);
+		page->parent_pte = NULL;
+		return;
+	}
+	hlist_for_each_entry(pte_chain, node, &page->parent_ptes, link)
+		for (i = 0; i < NR_PTE_CHAIN_ENTRIES; ++i) {
+			if (!pte_chain->parent_ptes[i])
+				break;
+			if (pte_chain->parent_ptes[i] != parent_pte)
+				continue;
+			while (i + 1 < NR_PTE_CHAIN_ENTRIES
+				&& pte_chain->parent_ptes[i + 1]) {
+				pte_chain->parent_ptes[i]
+					= pte_chain->parent_ptes[i + 1];
+				++i;
+			}
+			pte_chain->parent_ptes[i] = NULL;
+			if (i == 0) {
+				hlist_del(&pte_chain->link);
+				mmu_free_pte_chain(vcpu, pte_chain);
+				if (hlist_empty(&page->parent_ptes)) {
+					page->multimapped = 0;
+					page->parent_pte = NULL;
+				}
+			}
+			return;
+		}
+	BUG();
+}
+
+static struct kvm_mmu_page *kvm_mmu_lookup_page(struct kvm_vcpu *vcpu,
+						gfn_t gfn)
+{
+	unsigned index;
+	struct hlist_head *bucket;
+	struct kvm_mmu_page *page;
+	struct hlist_node *node;
+
+	pgprintk("%s: looking for gfn %lx\n", __FUNCTION__, gfn);
+	index = kvm_page_table_hashfn(gfn) % KVM_NUM_MMU_PAGES;
+	bucket = &vcpu->kvm->mmu_page_hash[index];
+	hlist_for_each_entry(page, node, bucket, hash_link)
+		if (page->gfn == gfn && !page->role.metaphysical) {
+			pgprintk("%s: found role %x\n",
+				 __FUNCTION__, page->role.word);
+			return page;
+		}
+	return NULL;
+}
+
+static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
+					     gfn_t gfn,
+					     gva_t gaddr,
+					     unsigned level,
+					     int metaphysical,
+					     u64 *parent_pte)
+{
+	union kvm_mmu_page_role role;
+	unsigned index;
+	unsigned quadrant;
+	struct hlist_head *bucket;
+	struct kvm_mmu_page *page;
+	struct hlist_node *node;
+
+	role.word = 0;
+	role.glevels = vcpu->mmu.root_level;
+	role.level = level;
+	role.metaphysical = metaphysical;
+	if (vcpu->mmu.root_level <= PT32_ROOT_LEVEL) {
+		quadrant = gaddr >> (PAGE_SHIFT + (PT64_PT_BITS * level));
+		quadrant &= (1 << ((PT32_PT_BITS - PT64_PT_BITS) * level)) - 1;
+		role.quadrant = quadrant;
+	}
+	pgprintk("%s: looking gfn %lx role %x\n", __FUNCTION__,
+		 gfn, role.word);
+	index = kvm_page_table_hashfn(gfn) % KVM_NUM_MMU_PAGES;
+	bucket = &vcpu->kvm->mmu_page_hash[index];
+	hlist_for_each_entry(page, node, bucket, hash_link)
+		if (page->gfn == gfn && page->role.word == role.word) {
+			mmu_page_add_parent_pte(vcpu, page, parent_pte);
+			pgprintk("%s: found\n", __FUNCTION__);
+			return page;
+		}
+	page = kvm_mmu_alloc_page(vcpu, parent_pte);
+	if (!page)
+		return page;
+	pgprintk("%s: adding gfn %lx role %x\n", __FUNCTION__, gfn, role.word);
+	page->gfn = gfn;
+	page->role = role;
+	hlist_add_head(&page->hash_link, bucket);
+	if (!metaphysical)
+		rmap_write_protect(vcpu, gfn);
+	return page;
+}
+
+static void kvm_mmu_page_unlink_children(struct kvm_vcpu *vcpu,
+					 struct kvm_mmu_page *page)
+{
+	unsigned i;
+	u64 *pt;
+	u64 ent;
+
+	pt = __va(page->page_hpa);
+
+	if (page->role.level == PT_PAGE_TABLE_LEVEL) {
+		for (i = 0; i < PT64_ENT_PER_PAGE; ++i) {
+			if (pt[i] & PT_PRESENT_MASK)
+				rmap_remove(vcpu, &pt[i]);
+			pt[i] = 0;
+		}
+		kvm_arch_ops->tlb_flush(vcpu);
+		return;
+	}
+
+	for (i = 0; i < PT64_ENT_PER_PAGE; ++i) {
+		ent = pt[i];
+
+		pt[i] = 0;
+		if (!(ent & PT_PRESENT_MASK))
+			continue;
+		ent &= PT64_BASE_ADDR_MASK;
+		mmu_page_remove_parent_pte(vcpu, page_header(ent), &pt[i]);
+	}
+}
+
+static void kvm_mmu_put_page(struct kvm_vcpu *vcpu,
+			     struct kvm_mmu_page *page,
+			     u64 *parent_pte)
+{
+	mmu_page_remove_parent_pte(vcpu, page, parent_pte);
+}
+
+static void kvm_mmu_zap_page(struct kvm_vcpu *vcpu,
+			     struct kvm_mmu_page *page)
+{
+	u64 *parent_pte;
+
+	while (page->multimapped || page->parent_pte) {
+		if (!page->multimapped)
+			parent_pte = page->parent_pte;
+		else {
+			struct kvm_pte_chain *chain;
+
+			chain = container_of(page->parent_ptes.first,
+					     struct kvm_pte_chain, link);
+			parent_pte = chain->parent_ptes[0];
+		}
+		BUG_ON(!parent_pte);
+		kvm_mmu_put_page(vcpu, page, parent_pte);
+		*parent_pte = 0;
+	}
+	kvm_mmu_page_unlink_children(vcpu, page);
+	if (!page->root_count) {
+		hlist_del(&page->hash_link);
+		kvm_mmu_free_page(vcpu, page->page_hpa);
+	} else {
+		list_del(&page->link);
+		list_add(&page->link, &vcpu->kvm->active_mmu_pages);
+	}
+}
+
+static int kvm_mmu_unprotect_page(struct kvm_vcpu *vcpu, gfn_t gfn)
+{
+	unsigned index;
+	struct hlist_head *bucket;
+	struct kvm_mmu_page *page;
+	struct hlist_node *node, *n;
+	int r;
+
+	pgprintk("%s: looking for gfn %lx\n", __FUNCTION__, gfn);
+	r = 0;
+	index = kvm_page_table_hashfn(gfn) % KVM_NUM_MMU_PAGES;
+	bucket = &vcpu->kvm->mmu_page_hash[index];
+	hlist_for_each_entry_safe(page, node, n, bucket, hash_link)
+		if (page->gfn == gfn && !page->role.metaphysical) {
+			pgprintk("%s: gfn %lx role %x\n", __FUNCTION__, gfn,
+				 page->role.word);
+			kvm_mmu_zap_page(vcpu, page);
+			r = 1;
+		}
+	return r;
 }
 
 static void page_header_update_slot(struct kvm *kvm, void *pte, gpa_t gpa)
@@ -225,35 +729,6 @@
 	return gpa_to_hpa(vcpu, gpa);
 }
 
-
-static void release_pt_page_64(struct kvm_vcpu *vcpu, hpa_t page_hpa,
-			       int level)
-{
-	ASSERT(vcpu);
-	ASSERT(VALID_PAGE(page_hpa));
-	ASSERT(level <= PT64_ROOT_LEVEL && level > 0);
-
-	if (level == 1)
-		memset(__va(page_hpa), 0, PAGE_SIZE);
-	else {
-		u64 *pos;
-		u64 *end;
-
-		for (pos = __va(page_hpa), end = pos + PT64_ENT_PER_PAGE;
-		     pos != end; pos++) {
-			u64 current_ent = *pos;
-
-			*pos = 0;
-			if (is_present_pte(current_ent))
-				release_pt_page_64(vcpu,
-						  current_ent &
-						  PT64_BASE_ADDR_MASK,
-						  level - 1);
-		}
-	}
-	kvm_mmu_free_page(vcpu, page_hpa);
-}
-
 static void nonpaging_new_cr3(struct kvm_vcpu *vcpu)
 {
 }
@@ -266,52 +741,109 @@
 	for (; ; level--) {
 		u32 index = PT64_INDEX(v, level);
 		u64 *table;
+		u64 pte;
 
 		ASSERT(VALID_PAGE(table_addr));
 		table = __va(table_addr);
 
 		if (level == 1) {
+			pte = table[index];
+			if (is_present_pte(pte) && is_writeble_pte(pte))
+				return 0;
 			mark_page_dirty(vcpu->kvm, v >> PAGE_SHIFT);
 			page_header_update_slot(vcpu->kvm, table, v);
 			table[index] = p | PT_PRESENT_MASK | PT_WRITABLE_MASK |
 								PT_USER_MASK;
+			rmap_add(vcpu, &table[index]);
 			return 0;
 		}
 
 		if (table[index] == 0) {
-			hpa_t new_table = kvm_mmu_alloc_page(vcpu,
-							     &table[index]);
+			struct kvm_mmu_page *new_table;
+			gfn_t pseudo_gfn;
 
-			if (!VALID_PAGE(new_table)) {
+			pseudo_gfn = (v & PT64_DIR_BASE_ADDR_MASK)
+				>> PAGE_SHIFT;
+			new_table = kvm_mmu_get_page(vcpu, pseudo_gfn,
+						     v, level - 1,
+						     1, &table[index]);
+			if (!new_table) {
 				pgprintk("nonpaging_map: ENOMEM\n");
 				return -ENOMEM;
 			}
 
-			if (level == PT32E_ROOT_LEVEL)
-				table[index] = new_table | PT_PRESENT_MASK;
-			else
-				table[index] = new_table | PT_PRESENT_MASK |
-						PT_WRITABLE_MASK | PT_USER_MASK;
+			table[index] = new_table->page_hpa | PT_PRESENT_MASK
+				| PT_WRITABLE_MASK | PT_USER_MASK;
 		}
 		table_addr = table[index] & PT64_BASE_ADDR_MASK;
 	}
 }
 
-static void nonpaging_flush(struct kvm_vcpu *vcpu)
+static void mmu_free_roots(struct kvm_vcpu *vcpu)
 {
-	hpa_t root = vcpu->mmu.root_hpa;
+	int i;
+	struct kvm_mmu_page *page;
 
-	++kvm_stat.tlb_flush;
-	pgprintk("nonpaging_flush\n");
-	ASSERT(VALID_PAGE(root));
-	release_pt_page_64(vcpu, root, vcpu->mmu.shadow_root_level);
-	root = kvm_mmu_alloc_page(vcpu, NULL);
-	ASSERT(VALID_PAGE(root));
-	vcpu->mmu.root_hpa = root;
-	if (is_paging(vcpu))
-		root |= (vcpu->cr3 & (CR3_PCD_MASK | CR3_WPT_MASK));
-	kvm_arch_ops->set_cr3(vcpu, root);
-	kvm_arch_ops->tlb_flush(vcpu);
+#ifdef CONFIG_X86_64
+	if (vcpu->mmu.shadow_root_level == PT64_ROOT_LEVEL) {
+		hpa_t root = vcpu->mmu.root_hpa;
+
+		ASSERT(VALID_PAGE(root));
+		page = page_header(root);
+		--page->root_count;
+		vcpu->mmu.root_hpa = INVALID_PAGE;
+		return;
+	}
+#endif
+	for (i = 0; i < 4; ++i) {
+		hpa_t root = vcpu->mmu.pae_root[i];
+
+		ASSERT(VALID_PAGE(root));
+		root &= PT64_BASE_ADDR_MASK;
+		page = page_header(root);
+		--page->root_count;
+		vcpu->mmu.pae_root[i] = INVALID_PAGE;
+	}
+	vcpu->mmu.root_hpa = INVALID_PAGE;
+}
+
+static void mmu_alloc_roots(struct kvm_vcpu *vcpu)
+{
+	int i;
+	gfn_t root_gfn;
+	struct kvm_mmu_page *page;
+
+	root_gfn = vcpu->cr3 >> PAGE_SHIFT;
+
+#ifdef CONFIG_X86_64
+	if (vcpu->mmu.shadow_root_level == PT64_ROOT_LEVEL) {
+		hpa_t root = vcpu->mmu.root_hpa;
+
+		ASSERT(!VALID_PAGE(root));
+		page = kvm_mmu_get_page(vcpu, root_gfn, 0,
+					PT64_ROOT_LEVEL, 0, NULL);
+		root = page->page_hpa;
+		++page->root_count;
+		vcpu->mmu.root_hpa = root;
+		return;
+	}
+#endif
+	for (i = 0; i < 4; ++i) {
+		hpa_t root = vcpu->mmu.pae_root[i];
+
+		ASSERT(!VALID_PAGE(root));
+		if (vcpu->mmu.root_level == PT32E_ROOT_LEVEL)
+			root_gfn = vcpu->pdptrs[i] >> PAGE_SHIFT;
+		else if (vcpu->mmu.root_level == 0)
+			root_gfn = 0;
+		page = kvm_mmu_get_page(vcpu, root_gfn, i << 30,
+					PT32_ROOT_LEVEL, !is_paging(vcpu),
+					NULL);
+		root = page->page_hpa;
+		++page->root_count;
+		vcpu->mmu.pae_root[i] = root | PT_PRESENT_MASK;
+	}
+	vcpu->mmu.root_hpa = __pa(vcpu->mmu.pae_root);
 }
 
 static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, gva_t vaddr)
@@ -322,43 +854,29 @@
 static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gva_t gva,
 			       u32 error_code)
 {
-	int ret;
 	gpa_t addr = gva;
+	hpa_t paddr;
+	int r;
+
+	r = mmu_topup_memory_caches(vcpu);
+	if (r)
+		return r;
 
 	ASSERT(vcpu);
 	ASSERT(VALID_PAGE(vcpu->mmu.root_hpa));
 
-	for (;;) {
-	     hpa_t paddr;
 
-	     paddr = gpa_to_hpa(vcpu , addr & PT64_BASE_ADDR_MASK);
+	paddr = gpa_to_hpa(vcpu , addr & PT64_BASE_ADDR_MASK);
 
-	     if (is_error_hpa(paddr))
-		     return 1;
+	if (is_error_hpa(paddr))
+		return 1;
 
-	     ret = nonpaging_map(vcpu, addr & PAGE_MASK, paddr);
-	     if (ret) {
-		     nonpaging_flush(vcpu);
-		     continue;
-	     }
-	     break;
-	}
-	return ret;
-}
-
-static void nonpaging_inval_page(struct kvm_vcpu *vcpu, gva_t addr)
-{
+	return nonpaging_map(vcpu, addr & PAGE_MASK, paddr);
 }
 
 static void nonpaging_free(struct kvm_vcpu *vcpu)
 {
-	hpa_t root;
-
-	ASSERT(vcpu);
-	root = vcpu->mmu.root_hpa;
-	if (VALID_PAGE(root))
-		release_pt_page_64(vcpu, root, vcpu->mmu.shadow_root_level);
-	vcpu->mmu.root_hpa = INVALID_PAGE;
+	mmu_free_roots(vcpu);
 }
 
 static int nonpaging_init_context(struct kvm_vcpu *vcpu)
@@ -367,40 +885,31 @@
 
 	context->new_cr3 = nonpaging_new_cr3;
 	context->page_fault = nonpaging_page_fault;
-	context->inval_page = nonpaging_inval_page;
 	context->gva_to_gpa = nonpaging_gva_to_gpa;
 	context->free = nonpaging_free;
-	context->root_level = PT32E_ROOT_LEVEL;
+	context->root_level = 0;
 	context->shadow_root_level = PT32E_ROOT_LEVEL;
-	context->root_hpa = kvm_mmu_alloc_page(vcpu, NULL);
+	mmu_alloc_roots(vcpu);
 	ASSERT(VALID_PAGE(context->root_hpa));
 	kvm_arch_ops->set_cr3(vcpu, context->root_hpa);
 	return 0;
 }
 
-
 static void kvm_mmu_flush_tlb(struct kvm_vcpu *vcpu)
 {
-	struct kvm_mmu_page *page, *npage;
-
-	list_for_each_entry_safe(page, npage, &vcpu->kvm->active_mmu_pages,
-				 link) {
-		if (page->global)
-			continue;
-
-		if (!page->parent_pte)
-			continue;
-
-		*page->parent_pte = 0;
-		release_pt_page_64(vcpu, page->page_hpa, 1);
-	}
 	++kvm_stat.tlb_flush;
 	kvm_arch_ops->tlb_flush(vcpu);
 }
 
 static void paging_new_cr3(struct kvm_vcpu *vcpu)
 {
+	pgprintk("%s: cr3 %lx\n", __FUNCTION__, vcpu->cr3);
+	mmu_free_roots(vcpu);
+	if (unlikely(vcpu->kvm->n_free_mmu_pages < KVM_MIN_FREE_MMU_PAGES))
+		kvm_mmu_free_some_pages(vcpu);
+	mmu_alloc_roots(vcpu);
 	kvm_mmu_flush_tlb(vcpu);
+	kvm_arch_ops->set_cr3(vcpu, vcpu->mmu.root_hpa);
 }
 
 static void mark_pagetable_nonglobal(void *shadow_pte)
@@ -412,7 +921,8 @@
 			     u64 *shadow_pte,
 			     gpa_t gaddr,
 			     int dirty,
-			     u64 access_bits)
+			     u64 access_bits,
+			     gfn_t gfn)
 {
 	hpa_t paddr;
 
@@ -420,13 +930,10 @@
 	if (!dirty)
 		access_bits &= ~PT_WRITABLE_MASK;
 
-	if (access_bits & PT_WRITABLE_MASK)
-		mark_page_dirty(vcpu->kvm, gaddr >> PAGE_SHIFT);
+	paddr = gpa_to_hpa(vcpu, gaddr & PT64_BASE_ADDR_MASK);
 
 	*shadow_pte |= access_bits;
 
-	paddr = gpa_to_hpa(vcpu, gaddr & PT64_BASE_ADDR_MASK);
-
 	if (!(*shadow_pte & PT_GLOBAL_MASK))
 		mark_pagetable_nonglobal(shadow_pte);
 
@@ -434,10 +941,31 @@
 		*shadow_pte |= gaddr;
 		*shadow_pte |= PT_SHADOW_IO_MARK;
 		*shadow_pte &= ~PT_PRESENT_MASK;
-	} else {
-		*shadow_pte |= paddr;
-		page_header_update_slot(vcpu->kvm, shadow_pte, gaddr);
+		return;
 	}
+
+	*shadow_pte |= paddr;
+
+	if (access_bits & PT_WRITABLE_MASK) {
+		struct kvm_mmu_page *shadow;
+
+		shadow = kvm_mmu_lookup_page(vcpu, gfn);
+		if (shadow) {
+			pgprintk("%s: found shadow page for %lx, marking ro\n",
+				 __FUNCTION__, gfn);
+			access_bits &= ~PT_WRITABLE_MASK;
+			if (is_writeble_pte(*shadow_pte)) {
+				    *shadow_pte &= ~PT_WRITABLE_MASK;
+				    kvm_arch_ops->tlb_flush(vcpu);
+			}
+		}
+	}
+
+	if (access_bits & PT_WRITABLE_MASK)
+		mark_page_dirty(vcpu->kvm, gaddr >> PAGE_SHIFT);
+
+	page_header_update_slot(vcpu->kvm, shadow_pte, gaddr);
+	rmap_add(vcpu, shadow_pte);
 }
 
 static void inject_page_fault(struct kvm_vcpu *vcpu,
@@ -474,41 +1002,6 @@
 	return 1;
 }
 
-/*
- * Remove a shadow pte.
- */
-static void paging_inval_page(struct kvm_vcpu *vcpu, gva_t addr)
-{
-	hpa_t page_addr = vcpu->mmu.root_hpa;
-	int level = vcpu->mmu.shadow_root_level;
-
-	++kvm_stat.invlpg;
-
-	for (; ; level--) {
-		u32 index = PT64_INDEX(addr, level);
-		u64 *table = __va(page_addr);
-
-		if (level == PT_PAGE_TABLE_LEVEL ) {
-			table[index] = 0;
-			return;
-		}
-
-		if (!is_present_pte(table[index]))
-			return;
-
-		page_addr = table[index] & PT64_BASE_ADDR_MASK;
-
-		if (level == PT_DIRECTORY_LEVEL &&
-			  (table[index] & PT_SHADOW_PS_MARK)) {
-			table[index] = 0;
-			release_pt_page_64(vcpu, page_addr, PT_PAGE_TABLE_LEVEL);
-
-			kvm_arch_ops->tlb_flush(vcpu);
-			return;
-		}
-	}
-}
-
 static void paging_free(struct kvm_vcpu *vcpu)
 {
 	nonpaging_free(vcpu);
@@ -522,37 +1015,40 @@
 #include "paging_tmpl.h"
 #undef PTTYPE
 
-static int paging64_init_context(struct kvm_vcpu *vcpu)
+static int paging64_init_context_common(struct kvm_vcpu *vcpu, int level)
 {
 	struct kvm_mmu *context = &vcpu->mmu;
 
 	ASSERT(is_pae(vcpu));
 	context->new_cr3 = paging_new_cr3;
 	context->page_fault = paging64_page_fault;
-	context->inval_page = paging_inval_page;
 	context->gva_to_gpa = paging64_gva_to_gpa;
 	context->free = paging_free;
-	context->root_level = PT64_ROOT_LEVEL;
-	context->shadow_root_level = PT64_ROOT_LEVEL;
-	context->root_hpa = kvm_mmu_alloc_page(vcpu, NULL);
+	context->root_level = level;
+	context->shadow_root_level = level;
+	mmu_alloc_roots(vcpu);
 	ASSERT(VALID_PAGE(context->root_hpa));
 	kvm_arch_ops->set_cr3(vcpu, context->root_hpa |
 		    (vcpu->cr3 & (CR3_PCD_MASK | CR3_WPT_MASK)));
 	return 0;
 }
 
+static int paging64_init_context(struct kvm_vcpu *vcpu)
+{
+	return paging64_init_context_common(vcpu, PT64_ROOT_LEVEL);
+}
+
 static int paging32_init_context(struct kvm_vcpu *vcpu)
 {
 	struct kvm_mmu *context = &vcpu->mmu;
 
 	context->new_cr3 = paging_new_cr3;
 	context->page_fault = paging32_page_fault;
-	context->inval_page = paging_inval_page;
 	context->gva_to_gpa = paging32_gva_to_gpa;
 	context->free = paging_free;
 	context->root_level = PT32_ROOT_LEVEL;
 	context->shadow_root_level = PT32E_ROOT_LEVEL;
-	context->root_hpa = kvm_mmu_alloc_page(vcpu, NULL);
+	mmu_alloc_roots(vcpu);
 	ASSERT(VALID_PAGE(context->root_hpa));
 	kvm_arch_ops->set_cr3(vcpu, context->root_hpa |
 		    (vcpu->cr3 & (CR3_PCD_MASK | CR3_WPT_MASK)));
@@ -561,14 +1057,7 @@
 
 static int paging32E_init_context(struct kvm_vcpu *vcpu)
 {
-	int ret;
-
-	if ((ret = paging64_init_context(vcpu)))
-		return ret;
-
-	vcpu->mmu.root_level = PT32E_ROOT_LEVEL;
-	vcpu->mmu.shadow_root_level = PT32E_ROOT_LEVEL;
-	return 0;
+	return paging64_init_context_common(vcpu, PT32E_ROOT_LEVEL);
 }
 
 static int init_kvm_mmu(struct kvm_vcpu *vcpu)
@@ -597,41 +1086,161 @@
 
 int kvm_mmu_reset_context(struct kvm_vcpu *vcpu)
 {
+	int r;
+
 	destroy_kvm_mmu(vcpu);
-	return init_kvm_mmu(vcpu);
+	r = init_kvm_mmu(vcpu);
+	if (r < 0)
+		goto out;
+	r = mmu_topup_memory_caches(vcpu);
+out:
+	return r;
 }
 
+void kvm_mmu_pre_write(struct kvm_vcpu *vcpu, gpa_t gpa, int bytes)
+{
+	gfn_t gfn = gpa >> PAGE_SHIFT;
+	struct kvm_mmu_page *page;
+	struct kvm_mmu_page *child;
+	struct hlist_node *node, *n;
+	struct hlist_head *bucket;
+	unsigned index;
+	u64 *spte;
+	u64 pte;
+	unsigned offset = offset_in_page(gpa);
+	unsigned pte_size;
+	unsigned page_offset;
+	unsigned misaligned;
+	int level;
+	int flooded = 0;
+
+	pgprintk("%s: gpa %llx bytes %d\n", __FUNCTION__, gpa, bytes);
+	if (gfn == vcpu->last_pt_write_gfn) {
+		++vcpu->last_pt_write_count;
+		if (vcpu->last_pt_write_count >= 3)
+			flooded = 1;
+	} else {
+		vcpu->last_pt_write_gfn = gfn;
+		vcpu->last_pt_write_count = 1;
+	}
+	index = kvm_page_table_hashfn(gfn) % KVM_NUM_MMU_PAGES;
+	bucket = &vcpu->kvm->mmu_page_hash[index];
+	hlist_for_each_entry_safe(page, node, n, bucket, hash_link) {
+		if (page->gfn != gfn || page->role.metaphysical)
+			continue;
+		pte_size = page->role.glevels == PT32_ROOT_LEVEL ? 4 : 8;
+		misaligned = (offset ^ (offset + bytes - 1)) & ~(pte_size - 1);
+		if (misaligned || flooded) {
+			/*
+			 * Misaligned accesses are too much trouble to fix
+			 * up; also, they usually indicate a page is not used
+			 * as a page table.
+			 *
+			 * If we're seeing too many writes to a page,
+			 * it may no longer be a page table, or we may be
+			 * forking, in which case it is better to unmap the
+			 * page.
+			 */
+			pgprintk("misaligned: gpa %llx bytes %d role %x\n",
+				 gpa, bytes, page->role.word);
+			kvm_mmu_zap_page(vcpu, page);
+			continue;
+		}
+		page_offset = offset;
+		level = page->role.level;
+		if (page->role.glevels == PT32_ROOT_LEVEL) {
+			page_offset <<= 1;          /* 32->64 */
+			page_offset &= ~PAGE_MASK;
+		}
+		spte = __va(page->page_hpa);
+		spte += page_offset / sizeof(*spte);
+		pte = *spte;
+		if (is_present_pte(pte)) {
+			if (level == PT_PAGE_TABLE_LEVEL)
+				rmap_remove(vcpu, spte);
+			else {
+				child = page_header(pte & PT64_BASE_ADDR_MASK);
+				mmu_page_remove_parent_pte(vcpu, child, spte);
+			}
+		}
+		*spte = 0;
+	}
+}
+
+void kvm_mmu_post_write(struct kvm_vcpu *vcpu, gpa_t gpa, int bytes)
+{
+}
+
+int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva)
+{
+	gpa_t gpa = vcpu->mmu.gva_to_gpa(vcpu, gva);
+
+	return kvm_mmu_unprotect_page(vcpu, gpa >> PAGE_SHIFT);
+}
+
+void kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu)
+{
+	while (vcpu->kvm->n_free_mmu_pages < KVM_REFILL_PAGES) {
+		struct kvm_mmu_page *page;
+
+		page = container_of(vcpu->kvm->active_mmu_pages.prev,
+				    struct kvm_mmu_page, link);
+		kvm_mmu_zap_page(vcpu, page);
+	}
+}
+EXPORT_SYMBOL_GPL(kvm_mmu_free_some_pages);
+
 static void free_mmu_pages(struct kvm_vcpu *vcpu)
 {
-	while (!list_empty(&vcpu->free_pages)) {
-		struct kvm_mmu_page *page;
+	struct kvm_mmu_page *page;
 
+	while (!list_empty(&vcpu->kvm->active_mmu_pages)) {
+		page = container_of(vcpu->kvm->active_mmu_pages.next,
+				    struct kvm_mmu_page, link);
+		kvm_mmu_zap_page(vcpu, page);
+	}
+	while (!list_empty(&vcpu->free_pages)) {
 		page = list_entry(vcpu->free_pages.next,
 				  struct kvm_mmu_page, link);
 		list_del(&page->link);
 		__free_page(pfn_to_page(page->page_hpa >> PAGE_SHIFT));
 		page->page_hpa = INVALID_PAGE;
 	}
+	free_page((unsigned long)vcpu->mmu.pae_root);
 }
 
 static int alloc_mmu_pages(struct kvm_vcpu *vcpu)
 {
+	struct page *page;
 	int i;
 
 	ASSERT(vcpu);
 
 	for (i = 0; i < KVM_NUM_MMU_PAGES; i++) {
-		struct page *page;
 		struct kvm_mmu_page *page_header = &vcpu->page_header_buf[i];
 
 		INIT_LIST_HEAD(&page_header->link);
-		if ((page = alloc_page(GFP_KVM_MMU)) == NULL)
+		if ((page = alloc_page(GFP_KERNEL)) == NULL)
 			goto error_1;
 		page->private = (unsigned long)page_header;
 		page_header->page_hpa = (hpa_t)page_to_pfn(page) << PAGE_SHIFT;
 		memset(__va(page_header->page_hpa), 0, PAGE_SIZE);
 		list_add(&page_header->link, &vcpu->free_pages);
+		++vcpu->kvm->n_free_mmu_pages;
 	}
+
+	/*
+	 * When emulating 32-bit mode, cr3 is only 32 bits even on x86_64.
+	 * Therefore we need to allocate shadow page tables in the first
+	 * 4GB of memory, which happens to fit the DMA32 zone.
+	 */
+	page = alloc_page(GFP_KERNEL | __GFP_DMA32);
+	if (!page)
+		goto error_1;
+	vcpu->mmu.pae_root = page_address(page);
+	for (i = 0; i < 4; ++i)
+		vcpu->mmu.pae_root[i] = INVALID_PAGE;
+
 	return 0;
 
 error_1:
@@ -663,10 +1272,12 @@
 
 	destroy_kvm_mmu(vcpu);
 	free_mmu_pages(vcpu);
+	mmu_free_memory_caches(vcpu);
 }
 
-void kvm_mmu_slot_remove_write_access(struct kvm *kvm, int slot)
+void kvm_mmu_slot_remove_write_access(struct kvm_vcpu *vcpu, int slot)
 {
+	struct kvm *kvm = vcpu->kvm;
 	struct kvm_mmu_page *page;
 
 	list_for_each_entry(page, &kvm->active_mmu_pages, link) {
@@ -679,8 +1290,169 @@
 		pt = __va(page->page_hpa);
 		for (i = 0; i < PT64_ENT_PER_PAGE; ++i)
 			/* avoid RMW */
-			if (pt[i] & PT_WRITABLE_MASK)
+			if (pt[i] & PT_WRITABLE_MASK) {
+				rmap_remove(vcpu, &pt[i]);
 				pt[i] &= ~PT_WRITABLE_MASK;
-
+			}
 	}
 }
+
+#ifdef AUDIT
+
+static const char *audit_msg;
+
+static gva_t canonicalize(gva_t gva)
+{
+#ifdef CONFIG_X86_64
+	gva = (long long)(gva << 16) >> 16;
+#endif
+	return gva;
+}
+
+static void audit_mappings_page(struct kvm_vcpu *vcpu, u64 page_pte,
+				gva_t va, int level)
+{
+	u64 *pt = __va(page_pte & PT64_BASE_ADDR_MASK);
+	int i;
+	gva_t va_delta = 1ul << (PAGE_SHIFT + 9 * (level - 1));
+
+	for (i = 0; i < PT64_ENT_PER_PAGE; ++i, va += va_delta) {
+		u64 ent = pt[i];
+
+		if (!ent & PT_PRESENT_MASK)
+			continue;
+
+		va = canonicalize(va);
+		if (level > 1)
+			audit_mappings_page(vcpu, ent, va, level - 1);
+		else {
+			gpa_t gpa = vcpu->mmu.gva_to_gpa(vcpu, va);
+			hpa_t hpa = gpa_to_hpa(vcpu, gpa);
+
+			if ((ent & PT_PRESENT_MASK)
+			    && (ent & PT64_BASE_ADDR_MASK) != hpa)
+				printk(KERN_ERR "audit error: (%s) levels %d"
+				       " gva %lx gpa %llx hpa %llx ent %llx\n",
+				       audit_msg, vcpu->mmu.root_level,
+				       va, gpa, hpa, ent);
+		}
+	}
+}
+
+static void audit_mappings(struct kvm_vcpu *vcpu)
+{
+	int i;
+
+	if (vcpu->mmu.root_level == 4)
+		audit_mappings_page(vcpu, vcpu->mmu.root_hpa, 0, 4);
+	else
+		for (i = 0; i < 4; ++i)
+			if (vcpu->mmu.pae_root[i] & PT_PRESENT_MASK)
+				audit_mappings_page(vcpu,
+						    vcpu->mmu.pae_root[i],
+						    i << 30,
+						    2);
+}
+
+static int count_rmaps(struct kvm_vcpu *vcpu)
+{
+	int nmaps = 0;
+	int i, j, k;
+
+	for (i = 0; i < KVM_MEMORY_SLOTS; ++i) {
+		struct kvm_memory_slot *m = &vcpu->kvm->memslots[i];
+		struct kvm_rmap_desc *d;
+
+		for (j = 0; j < m->npages; ++j) {
+			struct page *page = m->phys_mem[j];
+
+			if (!page->private)
+				continue;
+			if (!(page->private & 1)) {
+				++nmaps;
+				continue;
+			}
+			d = (struct kvm_rmap_desc *)(page->private & ~1ul);
+			while (d) {
+				for (k = 0; k < RMAP_EXT; ++k)
+					if (d->shadow_ptes[k])
+						++nmaps;
+					else
+						break;
+				d = d->more;
+			}
+		}
+	}
+	return nmaps;
+}
+
+static int count_writable_mappings(struct kvm_vcpu *vcpu)
+{
+	int nmaps = 0;
+	struct kvm_mmu_page *page;
+	int i;
+
+	list_for_each_entry(page, &vcpu->kvm->active_mmu_pages, link) {
+		u64 *pt = __va(page->page_hpa);
+
+		if (page->role.level != PT_PAGE_TABLE_LEVEL)
+			continue;
+
+		for (i = 0; i < PT64_ENT_PER_PAGE; ++i) {
+			u64 ent = pt[i];
+
+			if (!(ent & PT_PRESENT_MASK))
+				continue;
+			if (!(ent & PT_WRITABLE_MASK))
+				continue;
+			++nmaps;
+		}
+	}
+	return nmaps;
+}
+
+static void audit_rmap(struct kvm_vcpu *vcpu)
+{
+	int n_rmap = count_rmaps(vcpu);
+	int n_actual = count_writable_mappings(vcpu);
+
+	if (n_rmap != n_actual)
+		printk(KERN_ERR "%s: (%s) rmap %d actual %d\n",
+		       __FUNCTION__, audit_msg, n_rmap, n_actual);
+}
+
+static void audit_write_protection(struct kvm_vcpu *vcpu)
+{
+	struct kvm_mmu_page *page;
+
+	list_for_each_entry(page, &vcpu->kvm->active_mmu_pages, link) {
+		hfn_t hfn;
+		struct page *pg;
+
+		if (page->role.metaphysical)
+			continue;
+
+		hfn = gpa_to_hpa(vcpu, (gpa_t)page->gfn << PAGE_SHIFT)
+			>> PAGE_SHIFT;
+		pg = pfn_to_page(hfn);
+		if (pg->private)
+			printk(KERN_ERR "%s: (%s) shadow page has writable"
+			       " mappings: gfn %lx role %x\n",
+			       __FUNCTION__, audit_msg, page->gfn,
+			       page->role.word);
+	}
+}
+
+static void kvm_mmu_audit(struct kvm_vcpu *vcpu, const char *msg)
+{
+	int olddbg = dbg;
+
+	dbg = 0;
+	audit_msg = msg;
+	audit_rmap(vcpu);
+	audit_write_protection(vcpu);
+	audit_mappings(vcpu);
+	dbg = olddbg;
+}
+
+#endif
diff --git a/drivers/kvm/paging_tmpl.h b/drivers/kvm/paging_tmpl.h
index 09bb9b4..2dbf430 100644
--- a/drivers/kvm/paging_tmpl.h
+++ b/drivers/kvm/paging_tmpl.h
@@ -32,6 +32,11 @@
 	#define SHADOW_PT_INDEX(addr, level) PT64_INDEX(addr, level)
 	#define PT_LEVEL_MASK(level) PT64_LEVEL_MASK(level)
 	#define PT_PTE_COPY_MASK PT64_PTE_COPY_MASK
+	#ifdef CONFIG_X86_64
+	#define PT_MAX_FULL_LEVELS 4
+	#else
+	#define PT_MAX_FULL_LEVELS 2
+	#endif
 #elif PTTYPE == 32
 	#define pt_element_t u32
 	#define guest_walker guest_walker32
@@ -42,6 +47,7 @@
 	#define SHADOW_PT_INDEX(addr, level) PT64_INDEX(addr, level)
 	#define PT_LEVEL_MASK(level) PT32_LEVEL_MASK(level)
 	#define PT_PTE_COPY_MASK PT32_PTE_COPY_MASK
+	#define PT_MAX_FULL_LEVELS 2
 #else
 	#error Invalid PTTYPE value
 #endif
@@ -52,93 +58,126 @@
  */
 struct guest_walker {
 	int level;
+	gfn_t table_gfn[PT_MAX_FULL_LEVELS];
 	pt_element_t *table;
+	pt_element_t *ptep;
 	pt_element_t inherited_ar;
+	gfn_t gfn;
 };
 
-static void FNAME(init_walker)(struct guest_walker *walker,
-			       struct kvm_vcpu *vcpu)
+/*
+ * Fetch a guest pte for a guest virtual address
+ */
+static void FNAME(walk_addr)(struct guest_walker *walker,
+			     struct kvm_vcpu *vcpu, gva_t addr)
 {
 	hpa_t hpa;
 	struct kvm_memory_slot *slot;
+	pt_element_t *ptep;
+	pt_element_t root;
+	gfn_t table_gfn;
 
+	pgprintk("%s: addr %lx\n", __FUNCTION__, addr);
 	walker->level = vcpu->mmu.root_level;
-	slot = gfn_to_memslot(vcpu->kvm,
-			      (vcpu->cr3 & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT);
-	hpa = safe_gpa_to_hpa(vcpu, vcpu->cr3 & PT64_BASE_ADDR_MASK);
+	walker->table = NULL;
+	root = vcpu->cr3;
+#if PTTYPE == 64
+	if (!is_long_mode(vcpu)) {
+		walker->ptep = &vcpu->pdptrs[(addr >> 30) & 3];
+		root = *walker->ptep;
+		if (!(root & PT_PRESENT_MASK))
+			return;
+		--walker->level;
+	}
+#endif
+	table_gfn = (root & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT;
+	walker->table_gfn[walker->level - 1] = table_gfn;
+	pgprintk("%s: table_gfn[%d] %lx\n", __FUNCTION__,
+		 walker->level - 1, table_gfn);
+	slot = gfn_to_memslot(vcpu->kvm, table_gfn);
+	hpa = safe_gpa_to_hpa(vcpu, root & PT64_BASE_ADDR_MASK);
 	walker->table = kmap_atomic(pfn_to_page(hpa >> PAGE_SHIFT), KM_USER0);
 
 	ASSERT((!is_long_mode(vcpu) && is_pae(vcpu)) ||
 	       (vcpu->cr3 & ~(PAGE_MASK | CR3_FLAGS_MASK)) == 0);
 
-	walker->table = (pt_element_t *)( (unsigned long)walker->table |
-		(unsigned long)(vcpu->cr3 & ~(PAGE_MASK | CR3_FLAGS_MASK)) );
 	walker->inherited_ar = PT_USER_MASK | PT_WRITABLE_MASK;
-}
-
-static void FNAME(release_walker)(struct guest_walker *walker)
-{
-	kunmap_atomic(walker->table, KM_USER0);
-}
-
-static void FNAME(set_pte)(struct kvm_vcpu *vcpu, u64 guest_pte,
-			   u64 *shadow_pte, u64 access_bits)
-{
-	ASSERT(*shadow_pte == 0);
-	access_bits &= guest_pte;
-	*shadow_pte = (guest_pte & PT_PTE_COPY_MASK);
-	set_pte_common(vcpu, shadow_pte, guest_pte & PT_BASE_ADDR_MASK,
-		       guest_pte & PT_DIRTY_MASK, access_bits);
-}
-
-static void FNAME(set_pde)(struct kvm_vcpu *vcpu, u64 guest_pde,
-			   u64 *shadow_pte, u64 access_bits,
-			   int index)
-{
-	gpa_t gaddr;
-
-	ASSERT(*shadow_pte == 0);
-	access_bits &= guest_pde;
-	gaddr = (guest_pde & PT_DIR_BASE_ADDR_MASK) + PAGE_SIZE * index;
-	if (PTTYPE == 32 && is_cpuid_PSE36())
-		gaddr |= (guest_pde & PT32_DIR_PSE36_MASK) <<
-			(32 - PT32_DIR_PSE36_SHIFT);
-	*shadow_pte = guest_pde & PT_PTE_COPY_MASK;
-	set_pte_common(vcpu, shadow_pte, gaddr,
-		       guest_pde & PT_DIRTY_MASK, access_bits);
-}
-
-/*
- * Fetch a guest pte from a specific level in the paging hierarchy.
- */
-static pt_element_t *FNAME(fetch_guest)(struct kvm_vcpu *vcpu,
-					struct guest_walker *walker,
-					int level,
-					gva_t addr)
-{
-
-	ASSERT(level > 0  && level <= walker->level);
 
 	for (;;) {
 		int index = PT_INDEX(addr, walker->level);
 		hpa_t paddr;
 
+		ptep = &walker->table[index];
 		ASSERT(((unsigned long)walker->table & PAGE_MASK) ==
-		       ((unsigned long)&walker->table[index] & PAGE_MASK));
-		if (level == walker->level ||
-		    !is_present_pte(walker->table[index]) ||
-		    (walker->level == PT_DIRECTORY_LEVEL &&
-		     (walker->table[index] & PT_PAGE_SIZE_MASK) &&
-		     (PTTYPE == 64 || is_pse(vcpu))))
-			return &walker->table[index];
+		       ((unsigned long)ptep & PAGE_MASK));
+
+		if (is_present_pte(*ptep) && !(*ptep &  PT_ACCESSED_MASK))
+			*ptep |= PT_ACCESSED_MASK;
+
+		if (!is_present_pte(*ptep))
+			break;
+
+		if (walker->level == PT_PAGE_TABLE_LEVEL) {
+			walker->gfn = (*ptep & PT_BASE_ADDR_MASK)
+				>> PAGE_SHIFT;
+			break;
+		}
+
+		if (walker->level == PT_DIRECTORY_LEVEL
+		    && (*ptep & PT_PAGE_SIZE_MASK)
+		    && (PTTYPE == 64 || is_pse(vcpu))) {
+			walker->gfn = (*ptep & PT_DIR_BASE_ADDR_MASK)
+				>> PAGE_SHIFT;
+			walker->gfn += PT_INDEX(addr, PT_PAGE_TABLE_LEVEL);
+			break;
+		}
+
 		if (walker->level != 3 || is_long_mode(vcpu))
 			walker->inherited_ar &= walker->table[index];
-		paddr = safe_gpa_to_hpa(vcpu, walker->table[index] & PT_BASE_ADDR_MASK);
+		table_gfn = (*ptep & PT_BASE_ADDR_MASK) >> PAGE_SHIFT;
+		paddr = safe_gpa_to_hpa(vcpu, *ptep & PT_BASE_ADDR_MASK);
 		kunmap_atomic(walker->table, KM_USER0);
 		walker->table = kmap_atomic(pfn_to_page(paddr >> PAGE_SHIFT),
 					    KM_USER0);
 		--walker->level;
+		walker->table_gfn[walker->level - 1 ] = table_gfn;
+		pgprintk("%s: table_gfn[%d] %lx\n", __FUNCTION__,
+			 walker->level - 1, table_gfn);
 	}
+	walker->ptep = ptep;
+	pgprintk("%s: pte %llx\n", __FUNCTION__, (u64)*ptep);
+}
+
+static void FNAME(release_walker)(struct guest_walker *walker)
+{
+	if (walker->table)
+		kunmap_atomic(walker->table, KM_USER0);
+}
+
+static void FNAME(set_pte)(struct kvm_vcpu *vcpu, u64 guest_pte,
+			   u64 *shadow_pte, u64 access_bits, gfn_t gfn)
+{
+	ASSERT(*shadow_pte == 0);
+	access_bits &= guest_pte;
+	*shadow_pte = (guest_pte & PT_PTE_COPY_MASK);
+	set_pte_common(vcpu, shadow_pte, guest_pte & PT_BASE_ADDR_MASK,
+		       guest_pte & PT_DIRTY_MASK, access_bits, gfn);
+}
+
+static void FNAME(set_pde)(struct kvm_vcpu *vcpu, u64 guest_pde,
+			   u64 *shadow_pte, u64 access_bits, gfn_t gfn)
+{
+	gpa_t gaddr;
+
+	ASSERT(*shadow_pte == 0);
+	access_bits &= guest_pde;
+	gaddr = (gpa_t)gfn << PAGE_SHIFT;
+	if (PTTYPE == 32 && is_cpuid_PSE36())
+		gaddr |= (guest_pde & PT32_DIR_PSE36_MASK) <<
+			(32 - PT32_DIR_PSE36_SHIFT);
+	*shadow_pte = guest_pde & PT_PTE_COPY_MASK;
+	set_pte_common(vcpu, shadow_pte, gaddr,
+		       guest_pde & PT_DIRTY_MASK, access_bits, gfn);
 }
 
 /*
@@ -150,15 +189,26 @@
 	hpa_t shadow_addr;
 	int level;
 	u64 *prev_shadow_ent = NULL;
+	pt_element_t *guest_ent = walker->ptep;
+
+	if (!is_present_pte(*guest_ent))
+		return NULL;
 
 	shadow_addr = vcpu->mmu.root_hpa;
 	level = vcpu->mmu.shadow_root_level;
+	if (level == PT32E_ROOT_LEVEL) {
+		shadow_addr = vcpu->mmu.pae_root[(addr >> 30) & 3];
+		shadow_addr &= PT64_BASE_ADDR_MASK;
+		--level;
+	}
 
 	for (; ; level--) {
 		u32 index = SHADOW_PT_INDEX(addr, level);
 		u64 *shadow_ent = ((u64 *)__va(shadow_addr)) + index;
-		pt_element_t *guest_ent;
+		struct kvm_mmu_page *shadow_page;
 		u64 shadow_pte;
+		int metaphysical;
+		gfn_t table_gfn;
 
 		if (is_present_pte(*shadow_ent) || is_io_pte(*shadow_ent)) {
 			if (level == PT_PAGE_TABLE_LEVEL)
@@ -168,21 +218,6 @@
 			continue;
 		}
 
-		if (PTTYPE == 32 && level > PT32_ROOT_LEVEL) {
-			ASSERT(level == PT32E_ROOT_LEVEL);
-			guest_ent = FNAME(fetch_guest)(vcpu, walker,
-						       PT32_ROOT_LEVEL, addr);
-		} else
-			guest_ent = FNAME(fetch_guest)(vcpu, walker,
-						       level, addr);
-
-		if (!is_present_pte(*guest_ent))
-			return NULL;
-
-		/* Don't set accessed bit on PAE PDPTRs */
-		if (vcpu->mmu.root_level != 3 || walker->level != 3)
-			*guest_ent |= PT_ACCESSED_MASK;
-
 		if (level == PT_PAGE_TABLE_LEVEL) {
 
 			if (walker->level == PT_DIRECTORY_LEVEL) {
@@ -190,21 +225,30 @@
 					*prev_shadow_ent |= PT_SHADOW_PS_MARK;
 				FNAME(set_pde)(vcpu, *guest_ent, shadow_ent,
 					       walker->inherited_ar,
-				          PT_INDEX(addr, PT_PAGE_TABLE_LEVEL));
+					       walker->gfn);
 			} else {
 				ASSERT(walker->level == PT_PAGE_TABLE_LEVEL);
-				FNAME(set_pte)(vcpu, *guest_ent, shadow_ent, walker->inherited_ar);
+				FNAME(set_pte)(vcpu, *guest_ent, shadow_ent,
+					       walker->inherited_ar,
+					       walker->gfn);
 			}
 			return shadow_ent;
 		}
 
-		shadow_addr = kvm_mmu_alloc_page(vcpu, shadow_ent);
-		if (!VALID_PAGE(shadow_addr))
-			return ERR_PTR(-ENOMEM);
-		shadow_pte = shadow_addr | PT_PRESENT_MASK;
-		if (vcpu->mmu.root_level > 3 || level != 3)
-			shadow_pte |= PT_ACCESSED_MASK
-				| PT_WRITABLE_MASK | PT_USER_MASK;
+		if (level - 1 == PT_PAGE_TABLE_LEVEL
+		    && walker->level == PT_DIRECTORY_LEVEL) {
+			metaphysical = 1;
+			table_gfn = (*guest_ent & PT_BASE_ADDR_MASK)
+				>> PAGE_SHIFT;
+		} else {
+			metaphysical = 0;
+			table_gfn = walker->table_gfn[level - 2];
+		}
+		shadow_page = kvm_mmu_get_page(vcpu, table_gfn, addr, level-1,
+					       metaphysical, shadow_ent);
+		shadow_addr = shadow_page->page_hpa;
+		shadow_pte = shadow_addr | PT_PRESENT_MASK | PT_ACCESSED_MASK
+			| PT_WRITABLE_MASK | PT_USER_MASK;
 		*shadow_ent = shadow_pte;
 		prev_shadow_ent = shadow_ent;
 	}
@@ -221,11 +265,13 @@
 			       u64 *shadow_ent,
 			       struct guest_walker *walker,
 			       gva_t addr,
-			       int user)
+			       int user,
+			       int *write_pt)
 {
 	pt_element_t *guest_ent;
 	int writable_shadow;
 	gfn_t gfn;
+	struct kvm_mmu_page *page;
 
 	if (is_writeble_pte(*shadow_ent))
 		return 0;
@@ -250,17 +296,35 @@
 			*shadow_ent &= ~PT_USER_MASK;
 		}
 
-	guest_ent = FNAME(fetch_guest)(vcpu, walker, PT_PAGE_TABLE_LEVEL, addr);
+	guest_ent = walker->ptep;
 
 	if (!is_present_pte(*guest_ent)) {
 		*shadow_ent = 0;
 		return 0;
 	}
 
-	gfn = (*guest_ent & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT;
+	gfn = walker->gfn;
+
+	if (user) {
+		/*
+		 * Usermode page faults won't be for page table updates.
+		 */
+		while ((page = kvm_mmu_lookup_page(vcpu, gfn)) != NULL) {
+			pgprintk("%s: zap %lx %x\n",
+				 __FUNCTION__, gfn, page->role.word);
+			kvm_mmu_zap_page(vcpu, page);
+		}
+	} else if (kvm_mmu_lookup_page(vcpu, gfn)) {
+		pgprintk("%s: found shadow page for %lx, marking ro\n",
+			 __FUNCTION__, gfn);
+		*guest_ent |= PT_DIRTY_MASK;
+		*write_pt = 1;
+		return 0;
+	}
 	mark_page_dirty(vcpu->kvm, gfn);
 	*shadow_ent |= PT_WRITABLE_MASK;
 	*guest_ent |= PT_DIRTY_MASK;
+	rmap_add(vcpu, shadow_ent);
 
 	return 1;
 }
@@ -276,7 +340,8 @@
  *   - normal guest page fault due to the guest pte marked not present, not
  *     writable, or not executable
  *
- *  Returns: 1 if we need to emulate the instruction, 0 otherwise
+ *  Returns: 1 if we need to emulate the instruction, 0 otherwise, or
+ *           a negative value on error.
  */
 static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr,
 			       u32 error_code)
@@ -287,39 +352,47 @@
 	struct guest_walker walker;
 	u64 *shadow_pte;
 	int fixed;
+	int write_pt = 0;
+	int r;
+
+	pgprintk("%s: addr %lx err %x\n", __FUNCTION__, addr, error_code);
+	kvm_mmu_audit(vcpu, "pre page fault");
+
+	r = mmu_topup_memory_caches(vcpu);
+	if (r)
+		return r;
 
 	/*
 	 * Look up the shadow pte for the faulting address.
 	 */
-	for (;;) {
-		FNAME(init_walker)(&walker, vcpu);
-		shadow_pte = FNAME(fetch)(vcpu, addr, &walker);
-		if (IS_ERR(shadow_pte)) {  /* must be -ENOMEM */
-			nonpaging_flush(vcpu);
-			FNAME(release_walker)(&walker);
-			continue;
-		}
-		break;
-	}
+	FNAME(walk_addr)(&walker, vcpu, addr);
+	shadow_pte = FNAME(fetch)(vcpu, addr, &walker);
 
 	/*
 	 * The page is not mapped by the guest.  Let the guest handle it.
 	 */
 	if (!shadow_pte) {
+		pgprintk("%s: not mapped\n", __FUNCTION__);
 		inject_page_fault(vcpu, addr, error_code);
 		FNAME(release_walker)(&walker);
 		return 0;
 	}
 
+	pgprintk("%s: shadow pte %p %llx\n", __FUNCTION__,
+		 shadow_pte, *shadow_pte);
+
 	/*
 	 * Update the shadow pte.
 	 */
 	if (write_fault)
 		fixed = FNAME(fix_write_pf)(vcpu, shadow_pte, &walker, addr,
-					    user_fault);
+					    user_fault, &write_pt);
 	else
 		fixed = fix_read_pf(shadow_pte);
 
+	pgprintk("%s: updated shadow pte %p %llx\n", __FUNCTION__,
+		 shadow_pte, *shadow_pte);
+
 	FNAME(release_walker)(&walker);
 
 	/*
@@ -331,20 +404,23 @@
 		pgprintk("%s: io work, no access\n", __FUNCTION__);
 		inject_page_fault(vcpu, addr,
 				  error_code | PFERR_PRESENT_MASK);
+		kvm_mmu_audit(vcpu, "post page fault (io)");
 		return 0;
 	}
 
 	/*
 	 * pte not present, guest page fault.
 	 */
-	if (pte_present && !fixed) {
+	if (pte_present && !fixed && !write_pt) {
 		inject_page_fault(vcpu, addr, error_code);
+		kvm_mmu_audit(vcpu, "post page fault (guest)");
 		return 0;
 	}
 
 	++kvm_stat.pf_fixed;
+	kvm_mmu_audit(vcpu, "post page fault (fixed)");
 
-	return 0;
+	return write_pt;
 }
 
 static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t vaddr)
@@ -353,9 +429,8 @@
 	pt_element_t guest_pte;
 	gpa_t gpa;
 
-	FNAME(init_walker)(&walker, vcpu);
-	guest_pte = *FNAME(fetch_guest)(vcpu, &walker, PT_PAGE_TABLE_LEVEL,
-					vaddr);
+	FNAME(walk_addr)(&walker, vcpu, vaddr);
+	guest_pte = *walker.ptep;
 	FNAME(release_walker)(&walker);
 
 	if (!is_present_pte(guest_pte))
@@ -389,3 +464,4 @@
 #undef PT_PTE_COPY_MASK
 #undef PT_NON_PTE_COPY_MASK
 #undef PT_DIR_BASE_ADDR_MASK
+#undef PT_MAX_FULL_LEVELS
diff --git a/drivers/kvm/svm.c b/drivers/kvm/svm.c
index fa04287..ccc06b1 100644
--- a/drivers/kvm/svm.c
+++ b/drivers/kvm/svm.c
@@ -235,6 +235,8 @@
 
 	vcpu->rip = vcpu->svm->vmcb->save.rip = vcpu->svm->next_rip;
 	vcpu->svm->vmcb->control.int_state &= ~SVM_INTERRUPT_SHADOW_MASK;
+
+	vcpu->interrupt_window_open = 1;
 }
 
 static int has_svm(void)
@@ -495,7 +497,6 @@
 		/*              (1ULL << INTERCEPT_SELECTIVE_CR0) | */
 				(1ULL << INTERCEPT_CPUID) |
 				(1ULL << INTERCEPT_HLT) |
-				(1ULL << INTERCEPT_INVLPG) |
 				(1ULL << INTERCEPT_INVLPGA) |
 				(1ULL << INTERCEPT_IOIO_PROT) |
 				(1ULL << INTERCEPT_MSR_PROT) |
@@ -700,6 +701,10 @@
 	vcpu->svm->vmcb->save.gdtr.base = dt->base ;
 }
 
+static void svm_decache_cr0_cr4_guest_bits(struct kvm_vcpu *vcpu)
+{
+}
+
 static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 {
 #ifdef CONFIG_X86_64
@@ -847,6 +852,7 @@
 	u64 fault_address;
 	u32 error_code;
 	enum emulation_result er;
+	int r;
 
 	if (is_external_interrupt(exit_int_info))
 		push_irq(vcpu, exit_int_info & SVM_EVTINJ_VEC_MASK);
@@ -855,7 +861,12 @@
 
 	fault_address  = vcpu->svm->vmcb->control.exit_info_2;
 	error_code = vcpu->svm->vmcb->control.exit_info_1;
-	if (!vcpu->mmu.page_fault(vcpu, fault_address, error_code)) {
+	r = kvm_mmu_page_fault(vcpu, fault_address, error_code);
+	if (r < 0) {
+		spin_unlock(&vcpu->kvm->lock);
+		return r;
+	}
+	if (!r) {
 		spin_unlock(&vcpu->kvm->lock);
 		return 1;
 	}
@@ -1031,10 +1042,11 @@
 {
 	vcpu->svm->next_rip = vcpu->svm->vmcb->save.rip + 1;
 	skip_emulated_instruction(vcpu);
-	if (vcpu->irq_summary && (vcpu->svm->vmcb->save.rflags & X86_EFLAGS_IF))
+	if (vcpu->irq_summary)
 		return 1;
 
 	kvm_run->exit_reason = KVM_EXIT_HLT;
+	++kvm_stat.halt_exits;
 	return 0;
 }
 
@@ -1186,6 +1198,23 @@
 		return rdmsr_interception(vcpu, kvm_run);
 }
 
+static int interrupt_window_interception(struct kvm_vcpu *vcpu,
+				   struct kvm_run *kvm_run)
+{
+	/*
+	 * If the user space waits to inject interrupts, exit as soon as
+	 * possible
+	 */
+	if (kvm_run->request_interrupt_window &&
+	    !vcpu->irq_summary) {
+		++kvm_stat.irq_window_exits;
+		kvm_run->exit_reason = KVM_EXIT_IRQ_WINDOW_OPEN;
+		return 0;
+	}
+
+	return 1;
+}
+
 static int (*svm_exit_handlers[])(struct kvm_vcpu *vcpu,
 				      struct kvm_run *kvm_run) = {
 	[SVM_EXIT_READ_CR0]           		= emulate_on_interception,
@@ -1210,6 +1239,7 @@
 	[SVM_EXIT_NMI]				= nop_on_interception,
 	[SVM_EXIT_SMI]				= nop_on_interception,
 	[SVM_EXIT_INIT]				= nop_on_interception,
+	[SVM_EXIT_VINTR]			= interrupt_window_interception,
 	/* [SVM_EXIT_CR0_SEL_WRITE]		= emulate_on_interception, */
 	[SVM_EXIT_CPUID]			= cpuid_interception,
 	[SVM_EXIT_HLT]				= halt_interception,
@@ -1278,15 +1308,11 @@
 }
 
 
-static inline void kvm_try_inject_irq(struct kvm_vcpu *vcpu)
+static inline void kvm_do_inject_irq(struct kvm_vcpu *vcpu)
 {
 	struct vmcb_control_area *control;
 
-	if (!vcpu->irq_summary)
-		return;
-
 	control = &vcpu->svm->vmcb->control;
-
 	control->int_vector = pop_irq(vcpu);
 	control->int_ctl &= ~V_INTR_PRIO_MASK;
 	control->int_ctl |= V_IRQ_MASK |
@@ -1301,6 +1327,59 @@
 		control->int_ctl &= ~V_IRQ_MASK;
 		push_irq(vcpu, control->int_vector);
 	}
+
+	vcpu->interrupt_window_open =
+		!(control->int_state & SVM_INTERRUPT_SHADOW_MASK);
+}
+
+static void do_interrupt_requests(struct kvm_vcpu *vcpu,
+				       struct kvm_run *kvm_run)
+{
+	struct vmcb_control_area *control = &vcpu->svm->vmcb->control;
+
+	vcpu->interrupt_window_open =
+		(!(control->int_state & SVM_INTERRUPT_SHADOW_MASK) &&
+		 (vcpu->svm->vmcb->save.rflags & X86_EFLAGS_IF));
+
+	if (vcpu->interrupt_window_open && vcpu->irq_summary)
+		/*
+		 * If interrupts enabled, and not blocked by sti or mov ss. Good.
+		 */
+		kvm_do_inject_irq(vcpu);
+
+	/*
+	 * Interrupts blocked.  Wait for unblock.
+	 */
+	if (!vcpu->interrupt_window_open &&
+	    (vcpu->irq_summary || kvm_run->request_interrupt_window)) {
+		control->intercept |= 1ULL << INTERCEPT_VINTR;
+	} else
+		control->intercept &= ~(1ULL << INTERCEPT_VINTR);
+}
+
+static void post_kvm_run_save(struct kvm_vcpu *vcpu,
+			      struct kvm_run *kvm_run)
+{
+	kvm_run->ready_for_interrupt_injection = (vcpu->interrupt_window_open &&
+						  vcpu->irq_summary == 0);
+	kvm_run->if_flag = (vcpu->svm->vmcb->save.rflags & X86_EFLAGS_IF) != 0;
+	kvm_run->cr8 = vcpu->cr8;
+	kvm_run->apic_base = vcpu->apic_base;
+}
+
+/*
+ * Check if userspace requested an interrupt window, and that the
+ * interrupt window is open.
+ *
+ * No need to exit to userspace if we already have an interrupt queued.
+ */
+static int dm_request_for_irq_injection(struct kvm_vcpu *vcpu,
+					  struct kvm_run *kvm_run)
+{
+	return (!vcpu->irq_summary &&
+		kvm_run->request_interrupt_window &&
+		vcpu->interrupt_window_open &&
+		(vcpu->svm->vmcb->save.rflags & X86_EFLAGS_IF));
 }
 
 static void save_db_regs(unsigned long *db_regs)
@@ -1324,9 +1403,10 @@
 	u16 fs_selector;
 	u16 gs_selector;
 	u16 ldt_selector;
+	int r;
 
 again:
-	kvm_try_inject_irq(vcpu);
+	do_interrupt_requests(vcpu, kvm_run);
 
 	clgi();
 
@@ -1487,18 +1567,28 @@
 	if (vcpu->svm->vmcb->control.exit_code == SVM_EXIT_ERR) {
 		kvm_run->exit_type = KVM_EXIT_TYPE_FAIL_ENTRY;
 		kvm_run->exit_reason = vcpu->svm->vmcb->control.exit_code;
+		post_kvm_run_save(vcpu, kvm_run);
 		return 0;
 	}
 
-	if (handle_exit(vcpu, kvm_run)) {
+	r = handle_exit(vcpu, kvm_run);
+	if (r > 0) {
 		if (signal_pending(current)) {
 			++kvm_stat.signal_exits;
+			post_kvm_run_save(vcpu, kvm_run);
+			return -EINTR;
+		}
+
+		if (dm_request_for_irq_injection(vcpu, kvm_run)) {
+			++kvm_stat.request_irq_exits;
+			post_kvm_run_save(vcpu, kvm_run);
 			return -EINTR;
 		}
 		kvm_resched(vcpu);
 		goto again;
 	}
-	return 0;
+	post_kvm_run_save(vcpu, kvm_run);
+	return r;
 }
 
 static void svm_flush_tlb(struct kvm_vcpu *vcpu)
@@ -1565,6 +1655,7 @@
 	.get_segment = svm_get_segment,
 	.set_segment = svm_set_segment,
 	.get_cs_db_l_bits = svm_get_cs_db_l_bits,
+	.decache_cr0_cr4_guest_bits = svm_decache_cr0_cr4_guest_bits,
 	.set_cr0 = svm_set_cr0,
 	.set_cr0_no_modeswitch = svm_set_cr0,
 	.set_cr3 = svm_set_cr3,
diff --git a/drivers/kvm/vmx.c b/drivers/kvm/vmx.c
index d0a2c2d..d4701cb 100644
--- a/drivers/kvm/vmx.c
+++ b/drivers/kvm/vmx.c
@@ -116,7 +116,7 @@
 static void __vcpu_clear(void *arg)
 {
 	struct kvm_vcpu *vcpu = arg;
-	int cpu = smp_processor_id();
+	int cpu = raw_smp_processor_id();
 
 	if (vcpu->cpu == cpu)
 		vmcs_clear(vcpu->vmcs);
@@ -152,15 +152,21 @@
 #endif
 }
 
+static noinline void vmwrite_error(unsigned long field, unsigned long value)
+{
+	printk(KERN_ERR "vmwrite error: reg %lx value %lx (err %d)\n",
+	       field, value, vmcs_read32(VM_INSTRUCTION_ERROR));
+	dump_stack();
+}
+
 static void vmcs_writel(unsigned long field, unsigned long value)
 {
 	u8 error;
 
 	asm volatile (ASM_VMX_VMWRITE_RAX_RDX "; setna %0"
 		       : "=q"(error) : "a"(value), "d"(field) : "cc" );
-	if (error)
-		printk(KERN_ERR "vmwrite error: reg %lx value %lx (err %d)\n",
-		       field, value, vmcs_read32(VM_INSTRUCTION_ERROR));
+	if (unlikely(error))
+		vmwrite_error(field, value);
 }
 
 static void vmcs_write16(unsigned long field, u16 value)
@@ -263,6 +269,7 @@
 	if (interruptibility & 3)
 		vmcs_write32(GUEST_INTERRUPTIBILITY_INFO,
 			     interruptibility & ~3);
+	vcpu->interrupt_window_open = 1;
 }
 
 static void vmx_inject_gp(struct kvm_vcpu *vcpu, unsigned error_code)
@@ -541,7 +548,7 @@
 
 static struct vmcs *alloc_vmcs(void)
 {
-	return alloc_vmcs_cpu(smp_processor_id());
+	return alloc_vmcs_cpu(raw_smp_processor_id());
 }
 
 static void free_vmcs(struct vmcs *vmcs)
@@ -736,6 +743,15 @@
 
 #endif
 
+static void vmx_decache_cr0_cr4_guest_bits(struct kvm_vcpu *vcpu)
+{
+	vcpu->cr0 &= KVM_GUEST_CR0_MASK;
+	vcpu->cr0 |= vmcs_readl(GUEST_CR0) & ~KVM_GUEST_CR0_MASK;
+
+	vcpu->cr4 &= KVM_GUEST_CR4_MASK;
+	vcpu->cr4 |= vmcs_readl(GUEST_CR4) & ~KVM_GUEST_CR4_MASK;
+}
+
 static void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 {
 	if (vcpu->rmode.active && (cr0 & CR0_PE_MASK))
@@ -1011,8 +1027,6 @@
 	vmcs_writel(GUEST_RIP, 0xfff0);
 	vmcs_writel(GUEST_RSP, 0);
 
-	vmcs_writel(GUEST_CR3, 0);
-
 	//todo: dr0 = dr1 = dr2 = dr3 = 0; dr6 = 0xffff0ff0
 	vmcs_writel(GUEST_DR7, 0x400);
 
@@ -1049,7 +1063,6 @@
 			       | CPU_BASED_CR8_LOAD_EXITING    /* 20.6.2 */
 			       | CPU_BASED_CR8_STORE_EXITING   /* 20.6.2 */
 			       | CPU_BASED_UNCOND_IO_EXITING   /* 20.6.2 */
-			       | CPU_BASED_INVDPG_EXITING
 			       | CPU_BASED_MOV_DR_EXITING
 			       | CPU_BASED_USE_TSC_OFFSETING   /* 21.3 */
 			);
@@ -1094,14 +1107,6 @@
 	rdmsrl(MSR_IA32_SYSENTER_EIP, a);
 	vmcs_writel(HOST_IA32_SYSENTER_EIP, a);   /* 22.2.3 */
 
-	ret = -ENOMEM;
-	vcpu->guest_msrs = kmalloc(PAGE_SIZE, GFP_KERNEL);
-	if (!vcpu->guest_msrs)
-		goto out;
-	vcpu->host_msrs = kmalloc(PAGE_SIZE, GFP_KERNEL);
-	if (!vcpu->host_msrs)
-		goto out_free_guest_msrs;
-
 	for (i = 0; i < NR_VMX_MSR; ++i) {
 		u32 index = vmx_msr_index[i];
 		u32 data_low, data_high;
@@ -1155,8 +1160,6 @@
 
 	return 0;
 
-out_free_guest_msrs:
-	kfree(vcpu->guest_msrs);
 out:
 	return ret;
 }
@@ -1224,21 +1227,34 @@
 			irq | INTR_TYPE_EXT_INTR | INTR_INFO_VALID_MASK);
 }
 
-static void kvm_try_inject_irq(struct kvm_vcpu *vcpu)
+
+static void do_interrupt_requests(struct kvm_vcpu *vcpu,
+				       struct kvm_run *kvm_run)
 {
-	if ((vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF)
-	    && (vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & 3) == 0)
+	u32 cpu_based_vm_exec_control;
+
+	vcpu->interrupt_window_open =
+		((vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF) &&
+		 (vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & 3) == 0);
+
+	if (vcpu->interrupt_window_open &&
+	    vcpu->irq_summary &&
+	    !(vmcs_read32(VM_ENTRY_INTR_INFO_FIELD) & INTR_INFO_VALID_MASK))
 		/*
-		 * Interrupts enabled, and not blocked by sti or mov ss. Good.
+		 * If interrupts enabled, and not blocked by sti or mov ss. Good.
 		 */
 		kvm_do_inject_irq(vcpu);
-	else
+
+	cpu_based_vm_exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL);
+	if (!vcpu->interrupt_window_open &&
+	    (vcpu->irq_summary || kvm_run->request_interrupt_window))
 		/*
 		 * Interrupts blocked.  Wait for unblock.
 		 */
-		vmcs_write32(CPU_BASED_VM_EXEC_CONTROL,
-			     vmcs_read32(CPU_BASED_VM_EXEC_CONTROL)
-			     | CPU_BASED_VIRTUAL_INTR_PENDING);
+		cpu_based_vm_exec_control |= CPU_BASED_VIRTUAL_INTR_PENDING;
+	else
+		cpu_based_vm_exec_control &= ~CPU_BASED_VIRTUAL_INTR_PENDING;
+	vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control);
 }
 
 static void kvm_guest_debug_pre(struct kvm_vcpu *vcpu)
@@ -1277,6 +1293,7 @@
 	unsigned long cr2, rip;
 	u32 vect_info;
 	enum emulation_result er;
+	int r;
 
 	vect_info = vmcs_read32(IDT_VECTORING_INFO_FIELD);
 	intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
@@ -1305,7 +1322,12 @@
 		cr2 = vmcs_readl(EXIT_QUALIFICATION);
 
 		spin_lock(&vcpu->kvm->lock);
-		if (!vcpu->mmu.page_fault(vcpu, cr2, error_code)) {
+		r = kvm_mmu_page_fault(vcpu, cr2, error_code);
+		if (r < 0) {
+			spin_unlock(&vcpu->kvm->lock);
+			return r;
+		}
+		if (!r) {
 			spin_unlock(&vcpu->kvm->lock);
 			return 1;
 		}
@@ -1425,17 +1447,6 @@
 	return 0;
 }
 
-static int handle_invlpg(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
-{
-	u64 address = vmcs_read64(EXIT_QUALIFICATION);
-	int instruction_length = vmcs_read32(VM_EXIT_INSTRUCTION_LEN);
-	spin_lock(&vcpu->kvm->lock);
-	vcpu->mmu.inval_page(vcpu, address);
-	spin_unlock(&vcpu->kvm->lock);
-	vmcs_writel(GUEST_RIP, vmcs_readl(GUEST_RIP) + instruction_length);
-	return 1;
-}
-
 static int handle_cr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 {
 	u64 exit_qualification;
@@ -1575,23 +1586,40 @@
 	return 1;
 }
 
+static void post_kvm_run_save(struct kvm_vcpu *vcpu,
+			      struct kvm_run *kvm_run)
+{
+	kvm_run->if_flag = (vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF) != 0;
+	kvm_run->cr8 = vcpu->cr8;
+	kvm_run->apic_base = vcpu->apic_base;
+	kvm_run->ready_for_interrupt_injection = (vcpu->interrupt_window_open &&
+						  vcpu->irq_summary == 0);
+}
+
 static int handle_interrupt_window(struct kvm_vcpu *vcpu,
 				   struct kvm_run *kvm_run)
 {
-	/* Turn off interrupt window reporting. */
-	vmcs_write32(CPU_BASED_VM_EXEC_CONTROL,
-		     vmcs_read32(CPU_BASED_VM_EXEC_CONTROL)
-		     & ~CPU_BASED_VIRTUAL_INTR_PENDING);
+	/*
+	 * If the user space waits to inject interrupts, exit as soon as
+	 * possible
+	 */
+	if (kvm_run->request_interrupt_window &&
+	    !vcpu->irq_summary) {
+		kvm_run->exit_reason = KVM_EXIT_IRQ_WINDOW_OPEN;
+		++kvm_stat.irq_window_exits;
+		return 0;
+	}
 	return 1;
 }
 
 static int handle_halt(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 {
 	skip_emulated_instruction(vcpu);
-	if (vcpu->irq_summary && (vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF))
+	if (vcpu->irq_summary)
 		return 1;
 
 	kvm_run->exit_reason = KVM_EXIT_HLT;
+	++kvm_stat.halt_exits;
 	return 0;
 }
 
@@ -1605,7 +1633,6 @@
 	[EXIT_REASON_EXCEPTION_NMI]           = handle_exception,
 	[EXIT_REASON_EXTERNAL_INTERRUPT]      = handle_external_interrupt,
 	[EXIT_REASON_IO_INSTRUCTION]          = handle_io,
-	[EXIT_REASON_INVLPG]                  = handle_invlpg,
 	[EXIT_REASON_CR_ACCESS]               = handle_cr,
 	[EXIT_REASON_DR_ACCESS]               = handle_dr,
 	[EXIT_REASON_CPUID]                   = handle_cpuid,
@@ -1642,11 +1669,27 @@
 	return 0;
 }
 
+/*
+ * Check if userspace requested an interrupt window, and that the
+ * interrupt window is open.
+ *
+ * No need to exit to userspace if we already have an interrupt queued.
+ */
+static int dm_request_for_irq_injection(struct kvm_vcpu *vcpu,
+					  struct kvm_run *kvm_run)
+{
+	return (!vcpu->irq_summary &&
+		kvm_run->request_interrupt_window &&
+		vcpu->interrupt_window_open &&
+		(vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF));
+}
+
 static int vmx_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 {
 	u8 fail;
 	u16 fs_sel, gs_sel, ldt_sel;
 	int fs_gs_ldt_reload_needed;
+	int r;
 
 again:
 	/*
@@ -1673,9 +1716,7 @@
 	vmcs_writel(HOST_GS_BASE, segment_base(gs_sel));
 #endif
 
-	if (vcpu->irq_summary &&
-	    !(vmcs_read32(VM_ENTRY_INTR_INFO_FIELD) & INTR_INFO_VALID_MASK))
-		kvm_try_inject_irq(vcpu);
+	do_interrupt_requests(vcpu, kvm_run);
 
 	if (vcpu->guest_debug.enabled)
 		kvm_guest_debug_pre(vcpu);
@@ -1812,6 +1853,7 @@
 
 	fx_save(vcpu->guest_fx_image);
 	fx_restore(vcpu->host_fx_image);
+	vcpu->interrupt_window_open = (vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & 3) == 0;
 
 #ifndef CONFIG_X86_64
 	asm ("mov %0, %%ds; mov %0, %%es" : : "r"(__USER_DS));
@@ -1821,6 +1863,7 @@
 	if (fail) {
 		kvm_run->exit_type = KVM_EXIT_TYPE_FAIL_ENTRY;
 		kvm_run->exit_reason = vmcs_read32(VM_INSTRUCTION_ERROR);
+		r = 0;
 	} else {
 		if (fs_gs_ldt_reload_needed) {
 			load_ldt(ldt_sel);
@@ -1840,17 +1883,28 @@
 		}
 		vcpu->launched = 1;
 		kvm_run->exit_type = KVM_EXIT_TYPE_VM_EXIT;
-		if (kvm_handle_exit(kvm_run, vcpu)) {
+		r = kvm_handle_exit(kvm_run, vcpu);
+		if (r > 0) {
 			/* Give scheduler a change to reschedule. */
 			if (signal_pending(current)) {
 				++kvm_stat.signal_exits;
+				post_kvm_run_save(vcpu, kvm_run);
 				return -EINTR;
 			}
+
+			if (dm_request_for_irq_injection(vcpu, kvm_run)) {
+				++kvm_stat.request_irq_exits;
+				post_kvm_run_save(vcpu, kvm_run);
+				return -EINTR;
+			}
+
 			kvm_resched(vcpu);
 			goto again;
 		}
 	}
-	return 0;
+
+	post_kvm_run_save(vcpu, kvm_run);
+	return r;
 }
 
 static void vmx_flush_tlb(struct kvm_vcpu *vcpu)
@@ -1906,13 +1960,33 @@
 {
 	struct vmcs *vmcs;
 
+	vcpu->guest_msrs = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	if (!vcpu->guest_msrs)
+		return -ENOMEM;
+
+	vcpu->host_msrs = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	if (!vcpu->host_msrs)
+		goto out_free_guest_msrs;
+
 	vmcs = alloc_vmcs();
 	if (!vmcs)
-		return -ENOMEM;
+		goto out_free_msrs;
+
 	vmcs_clear(vmcs);
 	vcpu->vmcs = vmcs;
 	vcpu->launched = 0;
+
 	return 0;
+
+out_free_msrs:
+	kfree(vcpu->host_msrs);
+	vcpu->host_msrs = NULL;
+
+out_free_guest_msrs:
+	kfree(vcpu->guest_msrs);
+	vcpu->guest_msrs = NULL;
+
+	return -ENOMEM;
 }
 
 static struct kvm_arch_ops vmx_arch_ops = {
@@ -1936,6 +2010,7 @@
 	.get_segment = vmx_get_segment,
 	.set_segment = vmx_set_segment,
 	.get_cs_db_l_bits = vmx_get_cs_db_l_bits,
+	.decache_cr0_cr4_guest_bits = vmx_decache_cr0_cr4_guest_bits,
 	.set_cr0 = vmx_set_cr0,
 	.set_cr0_no_modeswitch = vmx_set_cr0_no_modeswitch,
 	.set_cr3 = vmx_set_cr3,
diff --git a/drivers/kvm/x86_emulate.c b/drivers/kvm/x86_emulate.c
index 1bff3e9..be70795 100644
--- a/drivers/kvm/x86_emulate.c
+++ b/drivers/kvm/x86_emulate.c
@@ -1323,7 +1323,7 @@
 							 ctxt)) != 0))
 				goto done;
 			if ((old_lo != _regs[VCPU_REGS_RAX])
-			    || (old_hi != _regs[VCPU_REGS_RDI])) {
+			    || (old_hi != _regs[VCPU_REGS_RDX])) {
 				_regs[VCPU_REGS_RAX] = old_lo;
 				_regs[VCPU_REGS_RDX] = old_hi;
 				_eflags &= ~EFLG_ZF;
diff --git a/drivers/leds/leds-s3c24xx.c b/drivers/leds/leds-s3c24xx.c
index fb1edc1..5091443 100644
--- a/drivers/leds/leds-s3c24xx.c
+++ b/drivers/leds/leds-s3c24xx.c
@@ -16,7 +16,7 @@
 #include <linux/platform_device.h>
 #include <linux/leds.h>
 
-#include <asm/arch/hardware.h>
+#include <asm/hardware.h>
 #include <asm/arch/regs-gpio.h>
 #include <asm/arch/leds-gpio.h>
 
diff --git a/drivers/macintosh/via-pmu.c b/drivers/macintosh/via-pmu.c
index c8558d4..8ca75e5 100644
--- a/drivers/macintosh/via-pmu.c
+++ b/drivers/macintosh/via-pmu.c
@@ -44,6 +44,7 @@
 #include <linux/sysdev.h>
 #include <linux/freezer.h>
 #include <linux/syscalls.h>
+#include <linux/suspend.h>
 #include <linux/cpu.h>
 #include <asm/prom.h>
 #include <asm/machdep.h>
diff --git a/drivers/mmc/mmci.c b/drivers/mmc/mmci.c
index e9b80e9..ccfe656 100644
--- a/drivers/mmc/mmci.c
+++ b/drivers/mmc/mmci.c
@@ -42,6 +42,8 @@
 {
 	writel(0, host->base + MMCICOMMAND);
 
+	BUG_ON(host->data);
+
 	host->mrq = NULL;
 	host->cmd = NULL;
 
@@ -198,6 +200,8 @@
 	}
 
 	if (!cmd->data || cmd->error != MMC_ERR_NONE) {
+		if (host->data)
+			mmci_stop_data(host);
 		mmci_request_end(host, cmd->mrq);
 	} else if (!(cmd->data->flags & MMC_DATA_READ)) {
 		mmci_start_data(host, cmd->data);
diff --git a/drivers/net/bnx2.c b/drivers/net/bnx2.c
index ada5e9b..ca5acc4 100644
--- a/drivers/net/bnx2.c
+++ b/drivers/net/bnx2.c
@@ -57,8 +57,8 @@
 
 #define DRV_MODULE_NAME		"bnx2"
 #define PFX DRV_MODULE_NAME	": "
-#define DRV_MODULE_VERSION	"1.5.2"
-#define DRV_MODULE_RELDATE	"December 13, 2006"
+#define DRV_MODULE_VERSION	"1.5.3"
+#define DRV_MODULE_RELDATE	"January 8, 2007"
 
 #define RUN_AT(x) (jiffies + (x))
 
@@ -1345,8 +1345,6 @@
 {
 	u32 val;
 
-	bp->phy_flags |= PHY_CRC_FIX_FLAG;
-
 	if (bp->phy_flags & PHY_CRC_FIX_FLAG) {
 		bnx2_write_phy(bp, 0x18, 0x0c00);
 		bnx2_write_phy(bp, 0x17, 0x000a);
@@ -3085,7 +3083,7 @@
 		int buf_size)
 {
 	u32 written, offset32, len32;
-	u8 *buf, start[4], end[4], *flash_buffer = NULL;
+	u8 *buf, start[4], end[4], *align_buf = NULL, *flash_buffer = NULL;
 	int rc = 0;
 	int align_start, align_end;
 
@@ -3113,16 +3111,17 @@
 	}
 
 	if (align_start || align_end) {
-		buf = kmalloc(len32, GFP_KERNEL);
-		if (buf == NULL)
+		align_buf = kmalloc(len32, GFP_KERNEL);
+		if (align_buf == NULL)
 			return -ENOMEM;
 		if (align_start) {
-			memcpy(buf, start, 4);
+			memcpy(align_buf, start, 4);
 		}
 		if (align_end) {
-			memcpy(buf + len32 - 4, end, 4);
+			memcpy(align_buf + len32 - 4, end, 4);
 		}
-		memcpy(buf + align_start, data_buf, buf_size);
+		memcpy(align_buf + align_start, data_buf, buf_size);
+		buf = align_buf;
 	}
 
 	if (bp->flash_info->buffered == 0) {
@@ -3256,11 +3255,8 @@
 	}
 
 nvram_write_end:
-	if (bp->flash_info->buffered == 0)
-		kfree(flash_buffer);
-
-	if (align_start || align_end)
-		kfree(buf);
+	kfree(flash_buffer);
+	kfree(align_buf);
 	return rc;
 }
 
@@ -5645,6 +5641,44 @@
 }
 #endif
 
+static void __devinit
+bnx2_get_5709_media(struct bnx2 *bp)
+{
+	u32 val = REG_RD(bp, BNX2_MISC_DUAL_MEDIA_CTRL);
+	u32 bond_id = val & BNX2_MISC_DUAL_MEDIA_CTRL_BOND_ID;
+	u32 strap;
+
+	if (bond_id == BNX2_MISC_DUAL_MEDIA_CTRL_BOND_ID_C)
+		return;
+	else if (bond_id == BNX2_MISC_DUAL_MEDIA_CTRL_BOND_ID_S) {
+		bp->phy_flags |= PHY_SERDES_FLAG;
+		return;
+	}
+
+	if (val & BNX2_MISC_DUAL_MEDIA_CTRL_STRAP_OVERRIDE)
+		strap = (val & BNX2_MISC_DUAL_MEDIA_CTRL_PHY_CTRL) >> 21;
+	else
+		strap = (val & BNX2_MISC_DUAL_MEDIA_CTRL_PHY_CTRL_STRAP) >> 8;
+
+	if (PCI_FUNC(bp->pdev->devfn) == 0) {
+		switch (strap) {
+		case 0x4:
+		case 0x5:
+		case 0x6:
+			bp->phy_flags |= PHY_SERDES_FLAG;
+			return;
+		}
+	} else {
+		switch (strap) {
+		case 0x1:
+		case 0x2:
+		case 0x4:
+			bp->phy_flags |= PHY_SERDES_FLAG;
+			return;
+		}
+	}
+}
+
 static int __devinit
 bnx2_init_board(struct pci_dev *pdev, struct net_device *dev)
 {
@@ -5865,10 +5899,9 @@
 	bp->phy_addr = 1;
 
 	/* Disable WOL support if we are running on a SERDES chip. */
-	if (CHIP_NUM(bp) == CHIP_NUM_5709) {
-		if (CHIP_BOND_ID(bp) != BNX2_MISC_DUAL_MEDIA_CTRL_BOND_ID_C)
-			bp->phy_flags |= PHY_SERDES_FLAG;
-	} else if (CHIP_BOND_ID(bp) & CHIP_BOND_ID_SERDES_BIT)
+	if (CHIP_NUM(bp) == CHIP_NUM_5709)
+		bnx2_get_5709_media(bp);
+	else if (CHIP_BOND_ID(bp) & CHIP_BOND_ID_SERDES_BIT)
 		bp->phy_flags |= PHY_SERDES_FLAG;
 
 	if (bp->phy_flags & PHY_SERDES_FLAG) {
@@ -5880,7 +5913,9 @@
 			if (reg & BNX2_SHARED_HW_CFG_PHY_2_5G)
 				bp->phy_flags |= PHY_2_5G_CAPABLE_FLAG;
 		}
-	}
+	} else if (CHIP_NUM(bp) == CHIP_NUM_5706 ||
+		   CHIP_NUM(bp) == CHIP_NUM_5708)
+		bp->phy_flags |= PHY_CRC_FIX_FLAG;
 
 	if ((CHIP_ID(bp) == CHIP_ID_5708_A0) ||
 	    (CHIP_ID(bp) == CHIP_ID_5708_B0) ||
diff --git a/drivers/net/chelsio/my3126.c b/drivers/net/chelsio/my3126.c
index c7731b6..82fed1d 100644
--- a/drivers/net/chelsio/my3126.c
+++ b/drivers/net/chelsio/my3126.c
@@ -170,9 +170,10 @@
 {
 	struct cphy *cphy = kzalloc(sizeof (*cphy), GFP_KERNEL);
 
-	if (cphy)
-		cphy_init(cphy, adapter, phy_addr, &my3126_ops, mdio_ops);
+	if (!cphy)
+		return NULL;
 
+	cphy_init(cphy, adapter, phy_addr, &my3126_ops, mdio_ops);
 	INIT_DELAYED_WORK(&cphy->phy_update, my3216_poll);
 	cphy->bmsr = 0;
 
diff --git a/drivers/net/e1000/e1000_main.c b/drivers/net/e1000/e1000_main.c
index 4c1ff75..c6259c7 100644
--- a/drivers/net/e1000/e1000_main.c
+++ b/drivers/net/e1000/e1000_main.c
@@ -995,12 +995,6 @@
 	   (adapter->hw.mac_type != e1000_82547))
 		netdev->features |= NETIF_F_TSO;
 
-#ifdef CONFIG_DEBUG_SLAB
-	/* 82544's work arounds do not play nicely with DEBUG SLAB */
-	if (adapter->hw.mac_type == e1000_82544)
-		netdev->features &= ~NETIF_F_TSO;
-#endif
-
 #ifdef NETIF_F_TSO6
 	if (adapter->hw.mac_type > e1000_82547_rev_2)
 		netdev->features |= NETIF_F_TSO6;
diff --git a/drivers/net/forcedeth.c b/drivers/net/forcedeth.c
index 2f48fe9..93f2b7a2 100644
--- a/drivers/net/forcedeth.c
+++ b/drivers/net/forcedeth.c
@@ -234,6 +234,7 @@
 #define NVREG_XMITCTL_HOST_SEMA_MASK	0x0000f000
 #define NVREG_XMITCTL_HOST_SEMA_ACQ	0x0000f000
 #define NVREG_XMITCTL_HOST_LOADED	0x00004000
+#define NVREG_XMITCTL_TX_PATH_EN	0x01000000
 	NvRegTransmitterStatus = 0x088,
 #define NVREG_XMITSTAT_BUSY	0x01
 
@@ -249,6 +250,7 @@
 #define NVREG_OFFLOAD_NORMAL	RX_NIC_BUFSIZE
 	NvRegReceiverControl = 0x094,
 #define NVREG_RCVCTL_START	0x01
+#define NVREG_RCVCTL_RX_PATH_EN	0x01000000
 	NvRegReceiverStatus = 0x98,
 #define NVREG_RCVSTAT_BUSY	0x01
 
@@ -1169,16 +1171,21 @@
 {
 	struct fe_priv *np = netdev_priv(dev);
 	u8 __iomem *base = get_hwbase(dev);
+	u32 rx_ctrl = readl(base + NvRegReceiverControl);
 
 	dprintk(KERN_DEBUG "%s: nv_start_rx\n", dev->name);
 	/* Already running? Stop it. */
-	if (readl(base + NvRegReceiverControl) & NVREG_RCVCTL_START) {
-		writel(0, base + NvRegReceiverControl);
+	if ((readl(base + NvRegReceiverControl) & NVREG_RCVCTL_START) && !np->mac_in_use) {
+		rx_ctrl &= ~NVREG_RCVCTL_START;
+		writel(rx_ctrl, base + NvRegReceiverControl);
 		pci_push(base);
 	}
 	writel(np->linkspeed, base + NvRegLinkSpeed);
 	pci_push(base);
-	writel(NVREG_RCVCTL_START, base + NvRegReceiverControl);
+        rx_ctrl |= NVREG_RCVCTL_START;
+        if (np->mac_in_use)
+		rx_ctrl &= ~NVREG_RCVCTL_RX_PATH_EN;
+	writel(rx_ctrl, base + NvRegReceiverControl);
 	dprintk(KERN_DEBUG "%s: nv_start_rx to duplex %d, speed 0x%08x.\n",
 				dev->name, np->duplex, np->linkspeed);
 	pci_push(base);
@@ -1186,39 +1193,59 @@
 
 static void nv_stop_rx(struct net_device *dev)
 {
+	struct fe_priv *np = netdev_priv(dev);
 	u8 __iomem *base = get_hwbase(dev);
+	u32 rx_ctrl = readl(base + NvRegReceiverControl);
 
 	dprintk(KERN_DEBUG "%s: nv_stop_rx\n", dev->name);
-	writel(0, base + NvRegReceiverControl);
+	if (!np->mac_in_use)
+		rx_ctrl &= ~NVREG_RCVCTL_START;
+	else
+		rx_ctrl |= NVREG_RCVCTL_RX_PATH_EN;
+	writel(rx_ctrl, base + NvRegReceiverControl);
 	reg_delay(dev, NvRegReceiverStatus, NVREG_RCVSTAT_BUSY, 0,
 			NV_RXSTOP_DELAY1, NV_RXSTOP_DELAY1MAX,
 			KERN_INFO "nv_stop_rx: ReceiverStatus remained busy");
 
 	udelay(NV_RXSTOP_DELAY2);
-	writel(0, base + NvRegLinkSpeed);
+	if (!np->mac_in_use)
+		writel(0, base + NvRegLinkSpeed);
 }
 
 static void nv_start_tx(struct net_device *dev)
 {
+	struct fe_priv *np = netdev_priv(dev);
 	u8 __iomem *base = get_hwbase(dev);
+	u32 tx_ctrl = readl(base + NvRegTransmitterControl);
 
 	dprintk(KERN_DEBUG "%s: nv_start_tx\n", dev->name);
-	writel(NVREG_XMITCTL_START, base + NvRegTransmitterControl);
+	tx_ctrl |= NVREG_XMITCTL_START;
+	if (np->mac_in_use)
+		tx_ctrl &= ~NVREG_XMITCTL_TX_PATH_EN;
+	writel(tx_ctrl, base + NvRegTransmitterControl);
 	pci_push(base);
 }
 
 static void nv_stop_tx(struct net_device *dev)
 {
+	struct fe_priv *np = netdev_priv(dev);
 	u8 __iomem *base = get_hwbase(dev);
+	u32 tx_ctrl = readl(base + NvRegTransmitterControl);
 
 	dprintk(KERN_DEBUG "%s: nv_stop_tx\n", dev->name);
-	writel(0, base + NvRegTransmitterControl);
+	if (!np->mac_in_use)
+		tx_ctrl &= ~NVREG_XMITCTL_START;
+	else
+		tx_ctrl |= NVREG_XMITCTL_TX_PATH_EN;
+	writel(tx_ctrl, base + NvRegTransmitterControl);
 	reg_delay(dev, NvRegTransmitterStatus, NVREG_XMITSTAT_BUSY, 0,
 			NV_TXSTOP_DELAY1, NV_TXSTOP_DELAY1MAX,
 			KERN_INFO "nv_stop_tx: TransmitterStatus remained busy");
 
 	udelay(NV_TXSTOP_DELAY2);
-	writel(readl(base + NvRegTransmitPoll) & NVREG_TRANSMITPOLL_MAC_ADDR_REV, base + NvRegTransmitPoll);
+	if (!np->mac_in_use)
+		writel(readl(base + NvRegTransmitPoll) & NVREG_TRANSMITPOLL_MAC_ADDR_REV,
+		       base + NvRegTransmitPoll);
 }
 
 static void nv_txrx_reset(struct net_device *dev)
@@ -4148,20 +4175,6 @@
 	return 0;
 }
 
-/* Indicate to mgmt unit whether driver is loaded or not */
-static void nv_mgmt_driver_loaded(struct net_device *dev, int loaded)
-{
-	u8 __iomem *base = get_hwbase(dev);
-	u32 tx_ctrl;
-
-	tx_ctrl = readl(base + NvRegTransmitterControl);
-	if (loaded)
-		tx_ctrl |= NVREG_XMITCTL_HOST_LOADED;
-	else
-		tx_ctrl &= ~NVREG_XMITCTL_HOST_LOADED;
-	writel(tx_ctrl, base + NvRegTransmitterControl);
-}
-
 static int nv_open(struct net_device *dev)
 {
 	struct fe_priv *np = netdev_priv(dev);
@@ -4659,33 +4672,24 @@
 	writel(NVREG_MIISTAT_MASK, base + NvRegMIIStatus);
 
 	if (id->driver_data & DEV_HAS_MGMT_UNIT) {
-		writel(0x1, base + 0x204); pci_push(base);
-		msleep(500);
 		/* management unit running on the mac? */
-		np->mac_in_use = readl(base + NvRegTransmitterControl) & NVREG_XMITCTL_MGMT_ST;
-		if (np->mac_in_use) {
-			u32 mgmt_sync;
-			/* management unit setup the phy already? */
-			mgmt_sync = readl(base + NvRegTransmitterControl) & NVREG_XMITCTL_SYNC_MASK;
-			if (mgmt_sync == NVREG_XMITCTL_SYNC_NOT_READY) {
-				if (!nv_mgmt_acquire_sema(dev)) {
-					for (i = 0; i < 5000; i++) {
-						msleep(1);
-						mgmt_sync = readl(base + NvRegTransmitterControl) & NVREG_XMITCTL_SYNC_MASK;
-						if (mgmt_sync == NVREG_XMITCTL_SYNC_NOT_READY)
-							continue;
-						if (mgmt_sync == NVREG_XMITCTL_SYNC_PHY_INIT)
-							phyinitialized = 1;
-						break;
+		if (readl(base + NvRegTransmitterControl) & NVREG_XMITCTL_SYNC_PHY_INIT) {
+			np->mac_in_use = readl(base + NvRegTransmitterControl) & NVREG_XMITCTL_MGMT_ST;
+			dprintk(KERN_INFO "%s: mgmt unit is running. mac in use %x.\n", pci_name(pci_dev), np->mac_in_use);
+			for (i = 0; i < 5000; i++) {
+				msleep(1);
+				if (nv_mgmt_acquire_sema(dev)) {
+					/* management unit setup the phy already? */
+					if ((readl(base + NvRegTransmitterControl) & NVREG_XMITCTL_SYNC_MASK) ==
+					    NVREG_XMITCTL_SYNC_PHY_INIT) {
+						/* phy is inited by mgmt unit */
+						phyinitialized = 1;
+						dprintk(KERN_INFO "%s: Phy already initialized by mgmt unit.\n", pci_name(pci_dev));
+					} else {
+						/* we need to init the phy */
 					}
-				} else {
-					/* we need to init the phy */
+					break;
 				}
-			} else if (mgmt_sync == NVREG_XMITCTL_SYNC_PHY_INIT) {
-				/* phy is inited by SMU */
-				phyinitialized = 1;
-			} else {
-				/* we need to init the phy */
 			}
 		}
 	}
@@ -4724,10 +4728,12 @@
 	if (!phyinitialized) {
 		/* reset it */
 		phy_init(dev);
-	}
-
-	if (id->driver_data & DEV_HAS_MGMT_UNIT) {
-		nv_mgmt_driver_loaded(dev, 1);
+	} else {
+		/* see if it is a gigabit phy */
+		u32 mii_status = mii_rw(dev, np->phyaddr, MII_BMSR, MII_READ);
+		if (mii_status & PHY_GIGABIT) {
+			np->gigabit = PHY_GIGABIT;
+		}
 	}
 
 	/* set default link speed settings */
@@ -4749,8 +4755,6 @@
 out_error:
 	if (phystate_orig)
 		writel(phystate|NVREG_ADAPTCTL_RUNNING, base + NvRegAdapterControl);
-	if (np->mac_in_use)
-		nv_mgmt_driver_loaded(dev, 0);
 	pci_set_drvdata(pci_dev, NULL);
 out_freering:
 	free_rings(dev);
@@ -4780,9 +4784,6 @@
 	writel(np->orig_mac[0], base + NvRegMacAddrA);
 	writel(np->orig_mac[1], base + NvRegMacAddrB);
 
-	if (np->mac_in_use)
-		nv_mgmt_driver_loaded(dev, 0);
-
 	/* free all structures */
 	free_rings(dev);
 	iounmap(get_hwbase(dev));
diff --git a/drivers/net/ixgb/ixgb.h b/drivers/net/ixgb/ixgb.h
index 50ffe90..f4aba43 100644
--- a/drivers/net/ixgb/ixgb.h
+++ b/drivers/net/ixgb/ixgb.h
@@ -171,6 +171,7 @@
 
 	/* TX */
 	struct ixgb_desc_ring tx_ring ____cacheline_aligned_in_smp;
+	unsigned int restart_queue;
 	unsigned long timeo_start;
 	uint32_t tx_cmd_type;
 	uint64_t hw_csum_tx_good;
diff --git a/drivers/net/ixgb/ixgb_ethtool.c b/drivers/net/ixgb/ixgb_ethtool.c
index cd22523..82c044d 100644
--- a/drivers/net/ixgb/ixgb_ethtool.c
+++ b/drivers/net/ixgb/ixgb_ethtool.c
@@ -79,6 +79,7 @@
 	{"tx_window_errors", IXGB_STAT(net_stats.tx_window_errors)},
 	{"tx_deferred_ok", IXGB_STAT(stats.dc)},
 	{"tx_timeout_count", IXGB_STAT(tx_timeout_count) },
+	{"tx_restart_queue", IXGB_STAT(restart_queue) },
 	{"rx_long_length_errors", IXGB_STAT(stats.roc)},
 	{"rx_short_length_errors", IXGB_STAT(stats.ruc)},
 #ifdef NETIF_F_TSO
diff --git a/drivers/net/ixgb/ixgb_hw.c b/drivers/net/ixgb/ixgb_hw.c
index 02089b6..ecbf458 100644
--- a/drivers/net/ixgb/ixgb_hw.c
+++ b/drivers/net/ixgb/ixgb_hw.c
@@ -399,8 +399,9 @@
 	/* Zero out the other 15 receive addresses. */
 	DEBUGOUT("Clearing RAR[1-15]\n");
 	for(i = 1; i < IXGB_RAR_ENTRIES; i++) {
-		IXGB_WRITE_REG_ARRAY(hw, RA, (i << 1), 0);
+		/* Write high reg first to disable the AV bit first */
 		IXGB_WRITE_REG_ARRAY(hw, RA, ((i << 1) + 1), 0);
+		IXGB_WRITE_REG_ARRAY(hw, RA, (i << 1), 0);
 	}
 
 	return;
diff --git a/drivers/net/ixgb/ixgb_main.c b/drivers/net/ixgb/ixgb_main.c
index e628126..a083a91 100644
--- a/drivers/net/ixgb/ixgb_main.c
+++ b/drivers/net/ixgb/ixgb_main.c
@@ -36,7 +36,7 @@
 #else
 #define DRIVERNAPI "-NAPI"
 #endif
-#define DRV_VERSION		"1.0.117-k2"DRIVERNAPI
+#define DRV_VERSION		"1.0.126-k2"DRIVERNAPI
 char ixgb_driver_version[] = DRV_VERSION;
 static char ixgb_copyright[] = "Copyright (c) 1999-2006 Intel Corporation.";
 
@@ -1287,6 +1287,7 @@
 	struct ixgb_buffer *buffer_info;
 	int len = skb->len;
 	unsigned int offset = 0, size, count = 0, i;
+	unsigned int mss = skb_shinfo(skb)->gso_size;
 
 	unsigned int nr_frags = skb_shinfo(skb)->nr_frags;
 	unsigned int f;
@@ -1298,6 +1299,11 @@
 	while(len) {
 		buffer_info = &tx_ring->buffer_info[i];
 		size = min(len, IXGB_MAX_DATA_PER_TXD);
+		/* Workaround for premature desc write-backs
+		 * in TSO mode.  Append 4-byte sentinel desc */
+		if (unlikely(mss && !nr_frags && size == len && size > 8))
+			size -= 4;
+
 		buffer_info->length = size;
 		WARN_ON(buffer_info->dma != 0);
 		buffer_info->dma =
@@ -1324,6 +1330,13 @@
 		while(len) {
 			buffer_info = &tx_ring->buffer_info[i];
 			size = min(len, IXGB_MAX_DATA_PER_TXD);
+
+			/* Workaround for premature desc write-backs
+			 * in TSO mode.  Append 4-byte sentinel desc */
+			if (unlikely(mss && !nr_frags && size == len
+			             && size > 8))
+				size -= 4;
+
 			buffer_info->length = size;
 			buffer_info->dma =
 				pci_map_page(adapter->pdev,
@@ -1398,11 +1411,43 @@
 	IXGB_WRITE_REG(&adapter->hw, TDT, i);
 }
 
+static int __ixgb_maybe_stop_tx(struct net_device *netdev, int size)
+{
+	struct ixgb_adapter *adapter = netdev_priv(netdev);
+	struct ixgb_desc_ring *tx_ring = &adapter->tx_ring;
+
+	netif_stop_queue(netdev);
+	/* Herbert's original patch had:
+	 *  smp_mb__after_netif_stop_queue();
+	 * but since that doesn't exist yet, just open code it. */
+	smp_mb();
+
+	/* We need to check again in a case another CPU has just
+	 * made room available. */
+	if (likely(IXGB_DESC_UNUSED(tx_ring) < size))
+		return -EBUSY;
+
+	/* A reprieve! */
+	netif_start_queue(netdev);
+	++adapter->restart_queue;
+	return 0;
+}
+
+static int ixgb_maybe_stop_tx(struct net_device *netdev,
+                              struct ixgb_desc_ring *tx_ring, int size)
+{
+	if (likely(IXGB_DESC_UNUSED(tx_ring) >= size))
+		return 0;
+	return __ixgb_maybe_stop_tx(netdev, size);
+}
+
+
 /* Tx Descriptors needed, worst case */
 #define TXD_USE_COUNT(S) (((S) >> IXGB_MAX_TXD_PWR) + \
 			 (((S) & (IXGB_MAX_DATA_PER_TXD - 1)) ? 1 : 0))
-#define DESC_NEEDED TXD_USE_COUNT(IXGB_MAX_DATA_PER_TXD) + \
-	MAX_SKB_FRAGS * TXD_USE_COUNT(PAGE_SIZE) + 1
+#define DESC_NEEDED TXD_USE_COUNT(IXGB_MAX_DATA_PER_TXD) /* skb->date */ + \
+	MAX_SKB_FRAGS * TXD_USE_COUNT(PAGE_SIZE) + 1 /* for context */ \
+	+ 1 /* one more needed for sentinel TSO workaround */
 
 static int
 ixgb_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
@@ -1430,7 +1475,8 @@
 	spin_lock_irqsave(&adapter->tx_lock, flags);
 #endif
 
-	if(unlikely(IXGB_DESC_UNUSED(&adapter->tx_ring) < DESC_NEEDED)) {
+	if (unlikely(ixgb_maybe_stop_tx(netdev, &adapter->tx_ring,
+                     DESC_NEEDED))) {
 		netif_stop_queue(netdev);
 		spin_unlock_irqrestore(&adapter->tx_lock, flags);
 		return NETDEV_TX_BUSY;
@@ -1468,8 +1514,7 @@
 
 #ifdef NETIF_F_LLTX
 	/* Make sure there is space in the ring for the next send. */
-	if(unlikely(IXGB_DESC_UNUSED(&adapter->tx_ring) < DESC_NEEDED))
-		netif_stop_queue(netdev);
+	ixgb_maybe_stop_tx(netdev, &adapter->tx_ring, DESC_NEEDED);
 
 	spin_unlock_irqrestore(&adapter->tx_lock, flags);
 
diff --git a/drivers/net/pcmcia/pcnet_cs.c b/drivers/net/pcmcia/pcnet_cs.c
index 2b1238e..d88e9b2 100644
--- a/drivers/net/pcmcia/pcnet_cs.c
+++ b/drivers/net/pcmcia/pcnet_cs.c
@@ -1617,6 +1617,7 @@
 	PCMCIA_DEVICE_PROD_ID12("corega K.K.", "corega FastEther PCC-TX", 0x5261440f, 0x485e85d9),
 	PCMCIA_DEVICE_PROD_ID12("Corega,K.K.", "Ethernet LAN Card", 0x110d26d9, 0x9fd2f0a2),
 	PCMCIA_DEVICE_PROD_ID12("corega,K.K.", "Ethernet LAN Card", 0x9791a90e, 0x9fd2f0a2),
+	PCMCIA_DEVICE_PROD_ID12("corega K.K.", "(CG-LAPCCTXD)", 0x5261440f, 0x73ec0d88),
 	PCMCIA_DEVICE_PROD_ID12("CouplerlessPCMCIA", "100BASE", 0xee5af0ad, 0x7c2add04),
 	PCMCIA_DEVICE_PROD_ID12("CyQ've", "ELA-010", 0x77008979, 0x9d8d445d),
 	PCMCIA_DEVICE_PROD_ID12("CyQ've", "ELA-110E 10/100M LAN Card", 0x77008979, 0xfd184814),
@@ -1667,6 +1668,7 @@
 	PCMCIA_DEVICE_PROD_ID12("Logitec", "LPM-LN100TX", 0x88fcdeda, 0x6d772737),
 	PCMCIA_DEVICE_PROD_ID12("Logitec", "LPM-LN100TE", 0x88fcdeda, 0x0e714bee),
 	PCMCIA_DEVICE_PROD_ID12("Logitec", "LPM-LN20T", 0x88fcdeda, 0x81090922),
+	PCMCIA_DEVICE_PROD_ID12("Logitec", "LPM-LN10TE", 0x88fcdeda, 0xc1e2521c),
 	PCMCIA_DEVICE_PROD_ID12("LONGSHINE", "PCMCIA Ethernet Card", 0xf866b0b0, 0x6f6652e0),
 	PCMCIA_DEVICE_PROD_ID12("MACNICA", "ME1-JEIDA", 0x20841b68, 0xaf8a3578),
 	PCMCIA_DEVICE_PROD_ID12("Macsense", "MPC-10", 0xd830297f, 0xd265c307),
diff --git a/drivers/net/qla3xxx.c b/drivers/net/qla3xxx.c
index d79d141..8844c20 100644
--- a/drivers/net/qla3xxx.c
+++ b/drivers/net/qla3xxx.c
@@ -208,6 +208,15 @@
 	return;
 }
 
+static void ql_write_nvram_reg(struct ql3_adapter *qdev,
+				u32 __iomem *reg, u32 value)
+{
+	writel(value, reg);
+	readl(reg);
+	udelay(1);
+	return;
+}
+
 static void ql_write_page0_reg(struct ql3_adapter *qdev,
 			       u32 __iomem *reg, u32 value)
 {
@@ -336,9 +345,9 @@
 	    		qdev->mem_map_registers;
 
 	qdev->eeprom_cmd_data = AUBURN_EEPROM_CS_1;
-	ql_write_common_reg(qdev, &port_regs->CommonRegs.serialPortInterfaceReg,
+	ql_write_nvram_reg(qdev, &port_regs->CommonRegs.serialPortInterfaceReg,
 			    ISP_NVRAM_MASK | qdev->eeprom_cmd_data);
-	ql_write_common_reg(qdev, &port_regs->CommonRegs.serialPortInterfaceReg,
+	ql_write_nvram_reg(qdev, &port_regs->CommonRegs.serialPortInterfaceReg,
 			    ((ISP_NVRAM_MASK << 16) | qdev->eeprom_cmd_data));
 }
 
@@ -355,14 +364,14 @@
 	    		qdev->mem_map_registers;
 
 	/* Clock in a zero, then do the start bit */
-	ql_write_common_reg(qdev, &port_regs->CommonRegs.serialPortInterfaceReg,
+	ql_write_nvram_reg(qdev, &port_regs->CommonRegs.serialPortInterfaceReg,
 			    ISP_NVRAM_MASK | qdev->eeprom_cmd_data |
 			    AUBURN_EEPROM_DO_1);
-	ql_write_common_reg(qdev, &port_regs->CommonRegs.serialPortInterfaceReg,
+	ql_write_nvram_reg(qdev, &port_regs->CommonRegs.serialPortInterfaceReg,
 			    ISP_NVRAM_MASK | qdev->
 			    eeprom_cmd_data | AUBURN_EEPROM_DO_1 |
 			    AUBURN_EEPROM_CLK_RISE);
-	ql_write_common_reg(qdev, &port_regs->CommonRegs.serialPortInterfaceReg,
+	ql_write_nvram_reg(qdev, &port_regs->CommonRegs.serialPortInterfaceReg,
 			    ISP_NVRAM_MASK | qdev->
 			    eeprom_cmd_data | AUBURN_EEPROM_DO_1 |
 			    AUBURN_EEPROM_CLK_FALL);
@@ -378,20 +387,20 @@
 			 * If the bit changed, then change the DO state to
 			 * match
 			 */
-			ql_write_common_reg(qdev,
+			ql_write_nvram_reg(qdev,
 					    &port_regs->CommonRegs.
 					    serialPortInterfaceReg,
 					    ISP_NVRAM_MASK | qdev->
 					    eeprom_cmd_data | dataBit);
 			previousBit = dataBit;
 		}
-		ql_write_common_reg(qdev,
+		ql_write_nvram_reg(qdev,
 				    &port_regs->CommonRegs.
 				    serialPortInterfaceReg,
 				    ISP_NVRAM_MASK | qdev->
 				    eeprom_cmd_data | dataBit |
 				    AUBURN_EEPROM_CLK_RISE);
-		ql_write_common_reg(qdev,
+		ql_write_nvram_reg(qdev,
 				    &port_regs->CommonRegs.
 				    serialPortInterfaceReg,
 				    ISP_NVRAM_MASK | qdev->
@@ -412,20 +421,20 @@
 			 * If the bit changed, then change the DO state to
 			 * match
 			 */
-			ql_write_common_reg(qdev,
+			ql_write_nvram_reg(qdev,
 					    &port_regs->CommonRegs.
 					    serialPortInterfaceReg,
 					    ISP_NVRAM_MASK | qdev->
 					    eeprom_cmd_data | dataBit);
 			previousBit = dataBit;
 		}
-		ql_write_common_reg(qdev,
+		ql_write_nvram_reg(qdev,
 				    &port_regs->CommonRegs.
 				    serialPortInterfaceReg,
 				    ISP_NVRAM_MASK | qdev->
 				    eeprom_cmd_data | dataBit |
 				    AUBURN_EEPROM_CLK_RISE);
-		ql_write_common_reg(qdev,
+		ql_write_nvram_reg(qdev,
 				    &port_regs->CommonRegs.
 				    serialPortInterfaceReg,
 				    ISP_NVRAM_MASK | qdev->
@@ -443,7 +452,7 @@
 	struct ql3xxx_port_registers __iomem *port_regs =
 	    		qdev->mem_map_registers;
 	qdev->eeprom_cmd_data = AUBURN_EEPROM_CS_0;
-	ql_write_common_reg(qdev, &port_regs->CommonRegs.serialPortInterfaceReg,
+	ql_write_nvram_reg(qdev, &port_regs->CommonRegs.serialPortInterfaceReg,
 			    ISP_NVRAM_MASK | qdev->eeprom_cmd_data);
 }
 
@@ -461,12 +470,12 @@
 	/* Read the data bits */
 	/* The first bit is a dummy.  Clock right over it. */
 	for (i = 0; i < dataBits; i++) {
-		ql_write_common_reg(qdev,
+		ql_write_nvram_reg(qdev,
 				    &port_regs->CommonRegs.
 				    serialPortInterfaceReg,
 				    ISP_NVRAM_MASK | qdev->eeprom_cmd_data |
 				    AUBURN_EEPROM_CLK_RISE);
-		ql_write_common_reg(qdev,
+		ql_write_nvram_reg(qdev,
 				    &port_regs->CommonRegs.
 				    serialPortInterfaceReg,
 				    ISP_NVRAM_MASK | qdev->eeprom_cmd_data |
@@ -3370,7 +3379,6 @@
 	SET_MODULE_OWNER(ndev);
 	SET_NETDEV_DEV(ndev, &pdev->dev);
 
-	ndev->features = NETIF_F_LLTX;
 	if (pci_using_dac)
 		ndev->features |= NETIF_F_HIGHDMA;
 
diff --git a/drivers/net/tg3.c b/drivers/net/tg3.c
index 4056ba1..f4bf62c 100644
--- a/drivers/net/tg3.c
+++ b/drivers/net/tg3.c
@@ -68,8 +68,8 @@
 
 #define DRV_MODULE_NAME		"tg3"
 #define PFX DRV_MODULE_NAME	": "
-#define DRV_MODULE_VERSION	"3.71"
-#define DRV_MODULE_RELDATE	"December 15, 2006"
+#define DRV_MODULE_VERSION	"3.72"
+#define DRV_MODULE_RELDATE	"January 8, 2007"
 
 #define TG3_DEF_MAC_MODE	0
 #define TG3_DEF_RX_MODE		0
@@ -1015,7 +1015,12 @@
 	else if (tp->tg3_flags2 & TG3_FLG2_PHY_JITTER_BUG) {
 		tg3_writephy(tp, MII_TG3_AUX_CTRL, 0x0c00);
 		tg3_writephy(tp, MII_TG3_DSP_ADDRESS, 0x000a);
-		tg3_writephy(tp, MII_TG3_DSP_RW_PORT, 0x010b);
+		if (tp->tg3_flags2 & TG3_FLG2_PHY_ADJUST_TRIM) {
+			tg3_writephy(tp, MII_TG3_DSP_RW_PORT, 0x110b);
+			tg3_writephy(tp, MII_TG3_TEST1,
+				     MII_TG3_TEST1_TRIM_EN | 0x4);
+		} else
+			tg3_writephy(tp, MII_TG3_DSP_RW_PORT, 0x010b);
 		tg3_writephy(tp, MII_TG3_AUX_CTRL, 0x0400);
 	}
 	/* Set Extended packet length bit (bit 14) on all chips that */
@@ -10803,9 +10808,11 @@
 
 	if (tp->tg3_flags2 & TG3_FLG2_5705_PLUS) {
 		if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5755 ||
-		    GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5787)
+		    GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5787) {
 			tp->tg3_flags2 |= TG3_FLG2_PHY_JITTER_BUG;
-		else if (GET_ASIC_REV(tp->pci_chip_rev_id) != ASIC_REV_5906)
+			if (tp->pdev->device == PCI_DEVICE_ID_TIGON3_5755M)
+				tp->tg3_flags2 |= TG3_FLG2_PHY_ADJUST_TRIM;
+		} else if (GET_ASIC_REV(tp->pci_chip_rev_id) != ASIC_REV_5906)
 			tp->tg3_flags2 |= TG3_FLG2_PHY_BER_BUG;
 	}
 
diff --git a/drivers/net/tg3.h b/drivers/net/tg3.h
index cf78a7e..80f59ac 100644
--- a/drivers/net/tg3.h
+++ b/drivers/net/tg3.h
@@ -1658,6 +1658,9 @@
 #define MII_TG3_EPHY_TEST		0x1f /* 5906 PHY register */
 #define MII_TG3_EPHY_SHADOW_EN		0x80
 
+#define MII_TG3_TEST1			0x1e
+#define MII_TG3_TEST1_TRIM_EN		0x0010
+
 /* There are two ways to manage the TX descriptors on the tigon3.
  * Either the descriptors are in host DMA'able memory, or they
  * exist only in the cards on-chip SRAM.  All 16 send bds are under
@@ -2256,6 +2259,7 @@
 #define TG3_FLG2_1SHOT_MSI		0x10000000
 #define TG3_FLG2_PHY_JITTER_BUG		0x20000000
 #define TG3_FLG2_NO_FWARE_REPORTED	0x40000000
+#define TG3_FLG2_PHY_ADJUST_TRIM	0x80000000
 
 	u32				split_mode_max_reqs;
 #define SPLIT_MODE_5704_MAX_REQ		3
diff --git a/drivers/net/wireless/ipw2100.c b/drivers/net/wireless/ipw2100.c
index 0e94fbb..b85857a 100644
--- a/drivers/net/wireless/ipw2100.c
+++ b/drivers/net/wireless/ipw2100.c
@@ -2664,7 +2664,7 @@
 				break;
 			}
 #endif
-			if (stats.len < sizeof(u->rx_data.header))
+			if (stats.len < sizeof(struct ieee80211_hdr_3addr))
 				break;
 			switch (WLAN_FC_GET_TYPE(u->rx_data.header.frame_ctl)) {
 			case IEEE80211_FTYPE_MGMT:
diff --git a/drivers/pci/Kconfig b/drivers/pci/Kconfig
index f1dd81a..3cfb0a3 100644
--- a/drivers/pci/Kconfig
+++ b/drivers/pci/Kconfig
@@ -19,7 +19,7 @@
 
 config PCI_MULTITHREAD_PROBE
 	bool "PCI Multi-threaded probe (EXPERIMENTAL)"
-	depends on PCI && EXPERIMENTAL
+	depends on PCI && EXPERIMENTAL && BROKEN
 	help
 	  Say Y here if you want the PCI core to spawn a new thread for
 	  every PCI device that is probed.  This can cause a huge
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index 8f0322d..0535efc 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -1117,10 +1117,11 @@
 static void quirk_sis_96x_smbus(struct pci_dev *dev)
 {
 	u8 val = 0;
-	printk(KERN_INFO "Enabling SiS 96x SMBus.\n");
 	pci_read_config_byte(dev, 0x77, &val);
-	pci_write_config_byte(dev, 0x77, val & ~0x10);
-	pci_read_config_byte(dev, 0x77, &val);
+	if (val & 0x10) {
+		printk(KERN_INFO "Enabling SiS 96x SMBus.\n");
+		pci_write_config_byte(dev, 0x77, val & ~0x10);
+	}
 }
 
 /*
@@ -1152,11 +1153,12 @@
 	printk(KERN_WARNING "Uncovering SIS%x that hid as a SIS503 (compatible=%d)\n", devid, sis_96x_compatible);
 
 	/*
-	 * Ok, it now shows up as a 96x.. The 96x quirks are after
-	 * the 503 quirk in the quirk table, so they'll automatically
-	 * run and enable things like the SMBus device
+	 * Ok, it now shows up as a 96x.. run the 96x quirk by
+	 * hand in case it has already been processed.
+	 * (depends on link order, which is apparently not guaranteed)
 	 */
 	dev->device = devid;
+	quirk_sis_96x_smbus(dev);
 }
 
 static void __init quirk_sis_96x_compatible(struct pci_dev *dev)
diff --git a/drivers/pci/search.c b/drivers/pci/search.c
index 45f2b20..fab381e 100644
--- a/drivers/pci/search.c
+++ b/drivers/pci/search.c
@@ -193,6 +193,18 @@
 	struct pci_dev *dev;
 
 	WARN_ON(in_interrupt());
+
+	/*
+	 * pci_find_subsys() can be called on the ide_setup() path, super-early
+	 * in boot.  But the down_read() will enable local interrupts, which
+	 * can cause some machines to crash.  So here we detect and flag that
+	 * situation and bail out early.
+	 */
+	if (unlikely(list_empty(&pci_devices))) {
+		printk(KERN_INFO "pci_find_subsys() called while pci_devices "
+				"is still empty\n");
+		return NULL;
+	}
 	down_read(&pci_bus_sem);
 	n = from ? from->global_list.next : pci_devices.next;
 
@@ -259,6 +271,18 @@
 	struct pci_dev *dev;
 
 	WARN_ON(in_interrupt());
+
+	/*
+	 * pci_get_subsys() can potentially be called by drivers super-early
+	 * in boot.  But the down_read() will enable local interrupts, which
+	 * can cause some machines to crash.  So here we detect and flag that
+	 * situation and bail out early.
+	 */
+	if (unlikely(list_empty(&pci_devices))) {
+		printk(KERN_NOTICE "pci_get_subsys() called while pci_devices "
+				"is still empty\n");
+		return NULL;
+	}
 	down_read(&pci_bus_sem);
 	n = from ? from->global_list.next : pci_devices.next;
 
diff --git a/drivers/rtc/rtc-at91rm9200.c b/drivers/rtc/rtc-at91rm9200.c
index 4f654c9..a724ab4 100644
--- a/drivers/rtc/rtc-at91rm9200.c
+++ b/drivers/rtc/rtc-at91rm9200.c
@@ -33,6 +33,8 @@
 
 #include <asm/mach/time.h>
 
+#include <asm/arch/at91_rtc.h>
+
 
 #define AT91_RTC_FREQ		1
 #define AT91_RTC_EPOCH		1900UL	/* just like arch/arm/common/rtctime.c */
diff --git a/drivers/rtc/rtc-rs5c372.c b/drivers/rtc/rtc-rs5c372.c
index 1460f6b..e7851e3 100644
--- a/drivers/rtc/rtc-rs5c372.c
+++ b/drivers/rtc/rtc-rs5c372.c
@@ -1,5 +1,5 @@
 /*
- * An I2C driver for the Ricoh RS5C372 RTC
+ * An I2C driver for Ricoh RS5C372 and RV5C38[67] RTCs
  *
  * Copyright (C) 2005 Pavel Mironchik <pmironchik@optifacio.net>
  * Copyright (C) 2006 Tower Technologies
@@ -13,7 +13,7 @@
 #include <linux/rtc.h>
 #include <linux/bcd.h>
 
-#define DRV_VERSION "0.3"
+#define DRV_VERSION "0.4"
 
 /* Addresses to scan */
 static unsigned short normal_i2c[] = { /* 0x32,*/ I2C_CLIENT_END };
@@ -21,6 +21,13 @@
 /* Insmod parameters */
 I2C_CLIENT_INSMOD;
 
+
+/*
+ * Ricoh has a family of I2C based RTCs, which differ only slightly from
+ * each other.  Differences center on pinout (e.g. how many interrupts,
+ * output clock, etc) and how the control registers are used.  The '372
+ * is significant only because that's the one this driver first supported.
+ */
 #define RS5C372_REG_SECS	0
 #define RS5C372_REG_MINS	1
 #define RS5C372_REG_HOURS	2
@@ -29,59 +36,142 @@
 #define RS5C372_REG_MONTH	5
 #define RS5C372_REG_YEAR	6
 #define RS5C372_REG_TRIM	7
+#	define RS5C372_TRIM_XSL		0x80
+#	define RS5C372_TRIM_MASK	0x7F
 
-#define RS5C372_TRIM_XSL	0x80
-#define RS5C372_TRIM_MASK	0x7F
+#define RS5C_REG_ALARM_A_MIN	8			/* or ALARM_W */
+#define RS5C_REG_ALARM_A_HOURS	9
+#define RS5C_REG_ALARM_A_WDAY	10
 
-#define RS5C372_REG_BASE	0
+#define RS5C_REG_ALARM_B_MIN	11			/* or ALARM_D */
+#define RS5C_REG_ALARM_B_HOURS	12
+#define RS5C_REG_ALARM_B_WDAY	13			/* (ALARM_B only) */
 
-static int rs5c372_attach(struct i2c_adapter *adapter);
-static int rs5c372_detach(struct i2c_client *client);
-static int rs5c372_probe(struct i2c_adapter *adapter, int address, int kind);
+#define RS5C_REG_CTRL1		14
+#	define RS5C_CTRL1_AALE		(1 << 7)	/* or WALE */
+#	define RS5C_CTRL1_BALE		(1 << 6)	/* or DALE */
+#	define RV5C387_CTRL1_24		(1 << 5)
+#	define RS5C372A_CTRL1_SL1	(1 << 5)
+#	define RS5C_CTRL1_CT_MASK	(7 << 0)
+#	define RS5C_CTRL1_CT0		(0 << 0)	/* no periodic irq */
+#	define RS5C_CTRL1_CT4		(4 << 0)	/* 1 Hz level irq */
+#define RS5C_REG_CTRL2		15
+#	define RS5C372_CTRL2_24		(1 << 5)
+#	define RS5C_CTRL2_XSTP		(1 << 4)
+#	define RS5C_CTRL2_CTFG		(1 << 2)
+#	define RS5C_CTRL2_AAFG		(1 << 1)	/* or WAFG */
+#	define RS5C_CTRL2_BAFG		(1 << 0)	/* or DAFG */
 
+
+/* to read (style 1) or write registers starting at R */
+#define RS5C_ADDR(R)		(((R) << 4) | 0)
+
+
+enum rtc_type {
+	rtc_undef = 0,
+	rtc_rs5c372a,
+	rtc_rs5c372b,
+	rtc_rv5c386,
+	rtc_rv5c387a,
+};
+
+/* REVISIT:  this assumes that:
+ *  - we're in the 21st century, so it's safe to ignore the century
+ *    bit for rv5c38[67] (REG_MONTH bit 7);
+ *  - we should use ALARM_A not ALARM_B (may be wrong on some boards)
+ */
 struct rs5c372 {
-	u8 reg_addr;
-	u8 regs[17];
-	struct i2c_msg msg[1];
-	struct i2c_client client;
-	struct rtc_device *rtc;
+	struct i2c_client	*client;
+	struct rtc_device	*rtc;
+	enum rtc_type		type;
+	unsigned		time24:1;
+	unsigned		has_irq:1;
+	char			buf[17];
+	char			*regs;
+
+	/* on conversion to a "new style" i2c driver, this vanishes */
+	struct i2c_client	dev;
 };
 
-static struct i2c_driver rs5c372_driver = {
-	.driver		= {
-		.name	= "rs5c372",
-	},
-	.attach_adapter	= &rs5c372_attach,
-	.detach_client	= &rs5c372_detach,
-};
-
-static int rs5c372_get_datetime(struct i2c_client *client, struct rtc_time *tm)
+static int rs5c_get_regs(struct rs5c372 *rs5c)
 {
+	struct i2c_client	*client = rs5c->client;
+	struct i2c_msg		msgs[] = {
+		{ client->addr, I2C_M_RD, sizeof rs5c->buf, rs5c->buf },
+	};
 
-	struct rs5c372 *rs5c372 = i2c_get_clientdata(client);
-	u8 *buf = &(rs5c372->regs[1]);
-
-	/* this implements the 3rd reading method, according
-	 * to the datasheet. rs5c372 defaults to internal
-	 * address 0xF, so 0x0 is in regs[1]
+	/* This implements the third reading method from the datasheet, using
+	 * an internal address that's reset after each transaction (by STOP)
+	 * to 0x0f ... so we read extra registers, and skip the first one.
+	 *
+	 * The first method doesn't work with the iop3xx adapter driver, on at
+	 * least 80219 chips; this works around that bug.
 	 */
-
-	if ((i2c_transfer(client->adapter, rs5c372->msg, 1)) != 1) {
-		dev_err(&client->dev, "%s: read error\n", __FUNCTION__);
+	if ((i2c_transfer(client->adapter, msgs, 1)) != 1) {
+		pr_debug("%s: can't read registers\n", rs5c->rtc->name);
 		return -EIO;
 	}
 
-	tm->tm_sec = BCD2BIN(buf[RS5C372_REG_SECS] & 0x7f);
-	tm->tm_min = BCD2BIN(buf[RS5C372_REG_MINS] & 0x7f);
-	tm->tm_hour = BCD2BIN(buf[RS5C372_REG_HOURS] & 0x3f);
-	tm->tm_wday = BCD2BIN(buf[RS5C372_REG_WDAY] & 0x07);
-	tm->tm_mday = BCD2BIN(buf[RS5C372_REG_DAY] & 0x3f);
+	dev_dbg(&client->dev,
+		"%02x %02x %02x (%02x) %02x %02x %02x (%02x), "
+		"%02x %02x %02x, %02x %02x %02x; %02x %02x\n",
+		rs5c->regs[0],  rs5c->regs[1],  rs5c->regs[2],  rs5c->regs[3],
+		rs5c->regs[4],  rs5c->regs[5],  rs5c->regs[6],  rs5c->regs[7],
+		rs5c->regs[8],  rs5c->regs[9],  rs5c->regs[10], rs5c->regs[11],
+		rs5c->regs[12], rs5c->regs[13], rs5c->regs[14], rs5c->regs[15]);
+
+	return 0;
+}
+
+static unsigned rs5c_reg2hr(struct rs5c372 *rs5c, unsigned reg)
+{
+	unsigned	hour;
+
+	if (rs5c->time24)
+		return BCD2BIN(reg & 0x3f);
+
+	hour = BCD2BIN(reg & 0x1f);
+	if (hour == 12)
+		hour = 0;
+	if (reg & 0x20)
+		hour += 12;
+	return hour;
+}
+
+static unsigned rs5c_hr2reg(struct rs5c372 *rs5c, unsigned hour)
+{
+	if (rs5c->time24)
+		return BIN2BCD(hour);
+
+	if (hour > 12)
+		return 0x20 | BIN2BCD(hour - 12);
+	if (hour == 12)
+		return 0x20 | BIN2BCD(12);
+	if (hour == 0)
+		return BIN2BCD(12);
+	return BIN2BCD(hour);
+}
+
+static int rs5c372_get_datetime(struct i2c_client *client, struct rtc_time *tm)
+{
+	struct rs5c372	*rs5c = i2c_get_clientdata(client);
+	int		status = rs5c_get_regs(rs5c);
+
+	if (status < 0)
+		return status;
+
+	tm->tm_sec = BCD2BIN(rs5c->regs[RS5C372_REG_SECS] & 0x7f);
+	tm->tm_min = BCD2BIN(rs5c->regs[RS5C372_REG_MINS] & 0x7f);
+	tm->tm_hour = rs5c_reg2hr(rs5c, rs5c->regs[RS5C372_REG_HOURS]);
+
+	tm->tm_wday = BCD2BIN(rs5c->regs[RS5C372_REG_WDAY] & 0x07);
+	tm->tm_mday = BCD2BIN(rs5c->regs[RS5C372_REG_DAY] & 0x3f);
 
 	/* tm->tm_mon is zero-based */
-	tm->tm_mon = BCD2BIN(buf[RS5C372_REG_MONTH] & 0x1f) - 1;
+	tm->tm_mon = BCD2BIN(rs5c->regs[RS5C372_REG_MONTH] & 0x1f) - 1;
 
 	/* year is 1900 + tm->tm_year */
-	tm->tm_year = BCD2BIN(buf[RS5C372_REG_YEAR]) + 100;
+	tm->tm_year = BCD2BIN(rs5c->regs[RS5C372_REG_YEAR]) + 100;
 
 	dev_dbg(&client->dev, "%s: tm is secs=%d, mins=%d, hours=%d, "
 		"mday=%d, mon=%d, year=%d, wday=%d\n",
@@ -89,22 +179,25 @@
 		tm->tm_sec, tm->tm_min, tm->tm_hour,
 		tm->tm_mday, tm->tm_mon, tm->tm_year, tm->tm_wday);
 
-	return 0;
+	/* rtc might need initialization */
+	return rtc_valid_tm(tm);
 }
 
 static int rs5c372_set_datetime(struct i2c_client *client, struct rtc_time *tm)
 {
-	unsigned char buf[8] = { RS5C372_REG_BASE };
+	struct rs5c372	*rs5c = i2c_get_clientdata(client);
+	unsigned char	buf[8];
 
-	dev_dbg(&client->dev,
-		"%s: secs=%d, mins=%d, hours=%d "
+	dev_dbg(&client->dev, "%s: tm is secs=%d, mins=%d, hours=%d "
 		"mday=%d, mon=%d, year=%d, wday=%d\n",
-		__FUNCTION__, tm->tm_sec, tm->tm_min, tm->tm_hour,
+		__FUNCTION__,
+		tm->tm_sec, tm->tm_min, tm->tm_hour,
 		tm->tm_mday, tm->tm_mon, tm->tm_year, tm->tm_wday);
 
+	buf[0] = RS5C_ADDR(RS5C372_REG_SECS);
 	buf[1] = BIN2BCD(tm->tm_sec);
 	buf[2] = BIN2BCD(tm->tm_min);
-	buf[3] = BIN2BCD(tm->tm_hour);
+	buf[3] = rs5c_hr2reg(rs5c, tm->tm_hour);
 	buf[4] = BIN2BCD(tm->tm_wday);
 	buf[5] = BIN2BCD(tm->tm_mday);
 	buf[6] = BIN2BCD(tm->tm_mon + 1);
@@ -118,21 +211,43 @@
 	return 0;
 }
 
+#if defined(CONFIG_RTC_INTF_PROC) || defined(CONFIG_RTC_INTF_PROC_MODULE)
+#define	NEED_TRIM
+#endif
+
+#if defined(CONFIG_RTC_INTF_SYSFS) || defined(CONFIG_RTC_INTF_SYSFS_MODULE)
+#define	NEED_TRIM
+#endif
+
+#ifdef	NEED_TRIM
 static int rs5c372_get_trim(struct i2c_client *client, int *osc, int *trim)
 {
 	struct rs5c372 *rs5c372 = i2c_get_clientdata(client);
-	u8 tmp = rs5c372->regs[RS5C372_REG_TRIM + 1];
+	u8 tmp = rs5c372->regs[RS5C372_REG_TRIM];
 
 	if (osc)
 		*osc = (tmp & RS5C372_TRIM_XSL) ? 32000 : 32768;
 
 	if (trim) {
-		*trim = tmp & RS5C372_TRIM_MASK;
-		dev_dbg(&client->dev, "%s: raw trim=%x\n", __FUNCTION__, *trim);
+		dev_dbg(&client->dev, "%s: raw trim=%x\n", __FUNCTION__, tmp);
+		tmp &= RS5C372_TRIM_MASK;
+		if (tmp & 0x3e) {
+			int t = tmp & 0x3f;
+
+			if (tmp & 0x40)
+				t = (~t | (s8)0xc0) + 1;
+			else
+				t = t - 1;
+
+			tmp = t * 2;
+		} else
+			tmp = 0;
+		*trim = tmp;
 	}
 
 	return 0;
 }
+#endif
 
 static int rs5c372_rtc_read_time(struct device *dev, struct rtc_time *tm)
 {
@@ -144,25 +259,190 @@
 	return rs5c372_set_datetime(to_i2c_client(dev), tm);
 }
 
+#if defined(CONFIG_RTC_INTF_DEV) || defined(CONFIG_RTC_INTF_DEV_MODULE)
+
+static int
+rs5c_rtc_ioctl(struct device *dev, unsigned int cmd, unsigned long arg)
+{
+	struct i2c_client	*client = to_i2c_client(dev);
+	struct rs5c372		*rs5c = i2c_get_clientdata(client);
+	unsigned char		buf[2];
+	int			status;
+
+	buf[1] = rs5c->regs[RS5C_REG_CTRL1];
+	switch (cmd) {
+	case RTC_UIE_OFF:
+	case RTC_UIE_ON:
+		/* some 327a modes use a different IRQ pin for 1Hz irqs */
+		if (rs5c->type == rtc_rs5c372a
+				&& (buf[1] & RS5C372A_CTRL1_SL1))
+			return -ENOIOCTLCMD;
+	case RTC_AIE_OFF:
+	case RTC_AIE_ON:
+		/* these irq management calls only make sense for chips
+		 * which are wired up to an IRQ.
+		 */
+		if (!rs5c->has_irq)
+			return -ENOIOCTLCMD;
+		break;
+	default:
+		return -ENOIOCTLCMD;
+	}
+
+	status = rs5c_get_regs(rs5c);
+	if (status < 0)
+		return status;
+
+	buf[0] = RS5C_ADDR(RS5C_REG_CTRL1);
+	switch (cmd) {
+	case RTC_AIE_OFF:	/* alarm off */
+		buf[1] &= ~RS5C_CTRL1_AALE;
+		break;
+	case RTC_AIE_ON:	/* alarm on */
+		buf[1] |= RS5C_CTRL1_AALE;
+		break;
+	case RTC_UIE_OFF:	/* update off */
+		buf[1] &= ~RS5C_CTRL1_CT_MASK;
+		break;
+	case RTC_UIE_ON:	/* update on */
+		buf[1] &= ~RS5C_CTRL1_CT_MASK;
+		buf[1] |= RS5C_CTRL1_CT4;
+		break;
+	}
+	if ((i2c_master_send(client, buf, 2)) != 2) {
+		printk(KERN_WARNING "%s: can't update alarm\n",
+			rs5c->rtc->name);
+		status = -EIO;
+	} else
+		rs5c->regs[RS5C_REG_CTRL1] = buf[1];
+	return status;
+}
+
+#else
+#define	rs5c_rtc_ioctl	NULL
+#endif
+
+
+/* NOTE:  Since RTC_WKALM_{RD,SET} were originally defined for EFI,
+ * which only exposes a polled programming interface; and since
+ * these calls map directly to those EFI requests; we don't demand
+ * we have an IRQ for this chip when we go through this API.
+ *
+ * The older x86_pc derived RTC_ALM_{READ,SET} calls require irqs
+ * though, managed through RTC_AIE_{ON,OFF} requests.
+ */
+
+static int rs5c_read_alarm(struct device *dev, struct rtc_wkalrm *t)
+{
+	struct i2c_client	*client = to_i2c_client(dev);
+	struct rs5c372		*rs5c = i2c_get_clientdata(client);
+	int			status;
+
+	status = rs5c_get_regs(rs5c);
+	if (status < 0)
+		return status;
+
+	/* report alarm time */
+	t->time.tm_sec = 0;
+	t->time.tm_min = BCD2BIN(rs5c->regs[RS5C_REG_ALARM_A_MIN] & 0x7f);
+	t->time.tm_hour = rs5c_reg2hr(rs5c, rs5c->regs[RS5C_REG_ALARM_A_HOURS]);
+	t->time.tm_mday = -1;
+	t->time.tm_mon = -1;
+	t->time.tm_year = -1;
+	t->time.tm_wday = -1;
+	t->time.tm_yday = -1;
+	t->time.tm_isdst = -1;
+
+	/* ... and status */
+	t->enabled = !!(rs5c->regs[RS5C_REG_CTRL1] & RS5C_CTRL1_AALE);
+	t->pending = !!(rs5c->regs[RS5C_REG_CTRL2] & RS5C_CTRL2_AAFG);
+
+	return 0;
+}
+
+static int rs5c_set_alarm(struct device *dev, struct rtc_wkalrm *t)
+{
+	struct i2c_client	*client = to_i2c_client(dev);
+	struct rs5c372		*rs5c = i2c_get_clientdata(client);
+	int			status;
+	unsigned char		buf[4];
+
+	/* only handle up to 24 hours in the future, like RTC_ALM_SET */
+	if (t->time.tm_mday != -1
+			|| t->time.tm_mon != -1
+			|| t->time.tm_year != -1)
+		return -EINVAL;
+
+	/* REVISIT: round up tm_sec */
+
+	/* if needed, disable irq (clears pending status) */
+	status = rs5c_get_regs(rs5c);
+	if (status < 0)
+		return status;
+	if (rs5c->regs[RS5C_REG_CTRL1] & RS5C_CTRL1_AALE) {
+		buf[0] = RS5C_ADDR(RS5C_REG_CTRL1);
+		buf[1] = rs5c->regs[RS5C_REG_CTRL1] & ~RS5C_CTRL1_AALE;
+		if (i2c_master_send(client, buf, 2) != 2) {
+			pr_debug("%s: can't disable alarm\n", rs5c->rtc->name);
+			return -EIO;
+		}
+		rs5c->regs[RS5C_REG_CTRL1] = buf[1];
+	}
+
+	/* set alarm */
+	buf[0] = RS5C_ADDR(RS5C_REG_ALARM_A_MIN);
+	buf[1] = BIN2BCD(t->time.tm_min);
+	buf[2] = rs5c_hr2reg(rs5c, t->time.tm_hour);
+	buf[3] = 0x7f;	/* any/all days */
+	if ((i2c_master_send(client, buf, 4)) != 4) {
+		pr_debug("%s: can't set alarm time\n", rs5c->rtc->name);
+		return -EIO;
+	}
+
+	/* ... and maybe enable its irq */
+	if (t->enabled) {
+		buf[0] = RS5C_ADDR(RS5C_REG_CTRL1);
+		buf[1] = rs5c->regs[RS5C_REG_CTRL1] | RS5C_CTRL1_AALE;
+		if ((i2c_master_send(client, buf, 2)) != 2)
+			printk(KERN_WARNING "%s: can't enable alarm\n",
+				rs5c->rtc->name);
+		rs5c->regs[RS5C_REG_CTRL1] = buf[1];
+	}
+
+	return 0;
+}
+
+#if defined(CONFIG_RTC_INTF_PROC) || defined(CONFIG_RTC_INTF_PROC_MODULE)
+
 static int rs5c372_rtc_proc(struct device *dev, struct seq_file *seq)
 {
 	int err, osc, trim;
 
 	err = rs5c372_get_trim(to_i2c_client(dev), &osc, &trim);
 	if (err == 0) {
-		seq_printf(seq, "%d.%03d KHz\n", osc / 1000, osc % 1000);
-		seq_printf(seq, "trim\t: %d\n", trim);
+		seq_printf(seq, "crystal\t\t: %d.%03d KHz\n",
+				osc / 1000, osc % 1000);
+		seq_printf(seq, "trim\t\t: %d\n", trim);
 	}
 
 	return 0;
 }
 
+#else
+#define	rs5c372_rtc_proc	NULL
+#endif
+
 static const struct rtc_class_ops rs5c372_rtc_ops = {
 	.proc		= rs5c372_rtc_proc,
+	.ioctl		= rs5c_rtc_ioctl,
 	.read_time	= rs5c372_rtc_read_time,
 	.set_time	= rs5c372_rtc_set_time,
+	.read_alarm	= rs5c_read_alarm,
+	.set_alarm	= rs5c_set_alarm,
 };
 
+#if defined(CONFIG_RTC_INTF_SYSFS) || defined(CONFIG_RTC_INTF_SYSFS_MODULE)
+
 static ssize_t rs5c372_sysfs_show_trim(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
@@ -172,7 +452,7 @@
 	if (err)
 		return err;
 
-	return sprintf(buf, "0x%2x\n", trim);
+	return sprintf(buf, "%d\n", trim);
 }
 static DEVICE_ATTR(trim, S_IRUGO, rs5c372_sysfs_show_trim, NULL);
 
@@ -189,16 +469,35 @@
 }
 static DEVICE_ATTR(osc, S_IRUGO, rs5c372_sysfs_show_osc, NULL);
 
-static int rs5c372_attach(struct i2c_adapter *adapter)
+static int rs5c_sysfs_register(struct device *dev)
 {
-	return i2c_probe(adapter, &addr_data, rs5c372_probe);
+	int err;
+
+	err = device_create_file(dev, &dev_attr_trim);
+	if (err)
+		return err;
+	err = device_create_file(dev, &dev_attr_osc);
+	if (err)
+		device_remove_file(dev, &dev_attr_trim);
+
+	return err;
 }
 
+#else
+static int rs5c_sysfs_register(struct device *dev)
+{
+	return 0;
+}
+#endif	/* SYSFS */
+
+static struct i2c_driver rs5c372_driver;
+
 static int rs5c372_probe(struct i2c_adapter *adapter, int address, int kind)
 {
 	int err = 0;
 	struct i2c_client *client;
 	struct rs5c372 *rs5c372;
+	struct rtc_time tm;
 
 	dev_dbg(adapter->class_dev.dev, "%s\n", __FUNCTION__);
 
@@ -211,7 +510,15 @@
 		err = -ENOMEM;
 		goto exit;
 	}
-	client = &rs5c372->client;
+
+	/* we read registers 0x0f then 0x00-0x0f; skip the first one */
+	rs5c372->regs=&rs5c372->buf[1];
+
+	/* On conversion to a "new style" i2c driver, we'll be handed
+	 * the i2c_client (we won't create it)
+	 */
+	client = &rs5c372->dev;
+	rs5c372->client = client;
 
 	/* I2C client */
 	client->addr = address;
@@ -222,16 +529,99 @@
 
 	i2c_set_clientdata(client, rs5c372);
 
-	rs5c372->msg[0].addr = address;
-	rs5c372->msg[0].flags = I2C_M_RD;
-	rs5c372->msg[0].len = sizeof(rs5c372->regs);
-	rs5c372->msg[0].buf = rs5c372->regs;
-
 	/* Inform the i2c layer */
 	if ((err = i2c_attach_client(client)))
 		goto exit_kfree;
 
-	dev_info(&client->dev, "chip found, driver version " DRV_VERSION "\n");
+	err = rs5c_get_regs(rs5c372);
+	if (err < 0)
+		goto exit_detach;
+
+	/* For "new style" drivers, irq is in i2c_client and chip type
+	 * info comes from i2c_client.dev.platform_data.  Meanwhile:
+	 *
+	 * STICK BOARD-SPECIFIC SETUP CODE RIGHT HERE
+	 */
+	if (rs5c372->type == rtc_undef) {
+		rs5c372->type = rtc_rs5c372b;
+		dev_warn(&client->dev, "assuming rs5c372b\n");
+	}
+
+	/* clock may be set for am/pm or 24 hr time */
+	switch (rs5c372->type) {
+	case rtc_rs5c372a:
+	case rtc_rs5c372b:
+		/* alarm uses ALARM_A; and nINTRA on 372a, nINTR on 372b.
+		 * so does periodic irq, except some 327a modes.
+		 */
+		if (rs5c372->regs[RS5C_REG_CTRL2] & RS5C372_CTRL2_24)
+			rs5c372->time24 = 1;
+		break;
+	case rtc_rv5c386:
+	case rtc_rv5c387a:
+		if (rs5c372->regs[RS5C_REG_CTRL1] & RV5C387_CTRL1_24)
+			rs5c372->time24 = 1;
+		/* alarm uses ALARM_W; and nINTRB for alarm and periodic
+		 * irq, on both 386 and 387
+		 */
+		break;
+	default:
+		dev_err(&client->dev, "unknown RTC type\n");
+		goto exit_detach;
+	}
+
+	/* if the oscillator lost power and no other software (like
+	 * the bootloader) set it up, do it here.
+	 */
+	if (rs5c372->regs[RS5C_REG_CTRL2] & RS5C_CTRL2_XSTP) {
+		unsigned char buf[3];
+
+		rs5c372->regs[RS5C_REG_CTRL2] &= ~RS5C_CTRL2_XSTP;
+
+		buf[0] = RS5C_ADDR(RS5C_REG_CTRL1);
+		buf[1] = rs5c372->regs[RS5C_REG_CTRL1];
+		buf[2] = rs5c372->regs[RS5C_REG_CTRL2];
+
+		/* use 24hr mode */
+		switch (rs5c372->type) {
+		case rtc_rs5c372a:
+		case rtc_rs5c372b:
+			buf[2] |= RS5C372_CTRL2_24;
+			rs5c372->time24 = 1;
+			break;
+		case rtc_rv5c386:
+		case rtc_rv5c387a:
+			buf[1] |= RV5C387_CTRL1_24;
+			rs5c372->time24 = 1;
+			break;
+		default:
+			/* impossible */
+			break;
+		}
+
+		if ((i2c_master_send(client, buf, 3)) != 3) {
+			dev_err(&client->dev, "setup error\n");
+			goto exit_detach;
+		}
+		rs5c372->regs[RS5C_REG_CTRL1] = buf[1];
+		rs5c372->regs[RS5C_REG_CTRL2] = buf[2];
+	}
+
+	if (rs5c372_get_datetime(client, &tm) < 0)
+		dev_warn(&client->dev, "clock needs to be set\n");
+
+	dev_info(&client->dev, "%s found, %s, driver version " DRV_VERSION "\n",
+			({ char *s; switch (rs5c372->type) {
+			case rtc_rs5c372a:	s = "rs5c372a"; break;
+			case rtc_rs5c372b:	s = "rs5c372b"; break;
+			case rtc_rv5c386:	s = "rv5c386"; break;
+			case rtc_rv5c387a:	s = "rv5c387a"; break;
+			default:		s = "chip"; break;
+			}; s;}),
+			rs5c372->time24 ? "24hr" : "am/pm"
+			);
+
+	/* FIXME when client->irq exists, use it to register alarm irq */
 
 	rs5c372->rtc = rtc_device_register(rs5c372_driver.driver.name,
 				&client->dev, &rs5c372_rtc_ops, THIS_MODULE);
@@ -241,18 +631,12 @@
 		goto exit_detach;
 	}
 
-	err = device_create_file(&client->dev, &dev_attr_trim);
+	err = rs5c_sysfs_register(&client->dev);
 	if (err)
 		goto exit_devreg;
-	err = device_create_file(&client->dev, &dev_attr_osc);
-	if (err)
-		goto exit_trim;
 
 	return 0;
 
-exit_trim:
-	device_remove_file(&client->dev, &dev_attr_trim);
-
 exit_devreg:
 	rtc_device_unregister(rs5c372->rtc);
 
@@ -266,6 +650,11 @@
 	return err;
 }
 
+static int rs5c372_attach(struct i2c_adapter *adapter)
+{
+	return i2c_probe(adapter, &addr_data, rs5c372_probe);
+}
+
 static int rs5c372_detach(struct i2c_client *client)
 {
 	int err;
@@ -274,6 +663,8 @@
 	if (rs5c372->rtc)
 		rtc_device_unregister(rs5c372->rtc);
 
+	/* REVISIT properly destroy the sysfs files ... */
+
 	if ((err = i2c_detach_client(client)))
 		return err;
 
@@ -281,6 +672,14 @@
 	return 0;
 }
 
+static struct i2c_driver rs5c372_driver = {
+	.driver		= {
+		.name	= "rtc-rs5c372",
+	},
+	.attach_adapter	= &rs5c372_attach,
+	.detach_client	= &rs5c372_detach,
+};
+
 static __init int rs5c372_init(void)
 {
 	return i2c_add_driver(&rs5c372_driver);
diff --git a/drivers/s390/char/vmcp.c b/drivers/s390/char/vmcp.c
index 1678b6c..a420cd0 100644
--- a/drivers/s390/char/vmcp.c
+++ b/drivers/s390/char/vmcp.c
@@ -117,7 +117,7 @@
 		return -ENOMEM;
 	}
 	debug_text_event(vmcp_debug, 1, cmd);
-	session->resp_size = __cpcmd(cmd, session->response,
+	session->resp_size = cpcmd(cmd, session->response,
 				     session->bufsize,
 				     &session->resp_code);
 	up(&session->mutex);
diff --git a/drivers/s390/cio/cio.c b/drivers/s390/cio/cio.c
index b471ac4..ae1bf23 100644
--- a/drivers/s390/cio/cio.c
+++ b/drivers/s390/cio/cio.c
@@ -880,19 +880,15 @@
 static int stsch_reset(struct subchannel_id schid, volatile struct schib *addr)
 {
 	int rc;
-	register struct subchannel_id reg1 asm ("1") = schid;
 
 	pgm_check_occured = 0;
 	s390_reset_pgm_handler = cio_reset_pgm_check_handler;
-
-	asm volatile(
-		"       stsch   0(%2)\n"
-		"       ipm     %0\n"
-		"       srl     %0,28"
-		: "=d" (rc)
-		: "d" (reg1), "a" (addr), "m" (*addr) : "memory", "cc");
-
+	rc = stsch(schid, addr);
 	s390_reset_pgm_handler = NULL;
+
+	/* The program check handler could have changed pgm_check_occured */
+	barrier();
+
 	if (pgm_check_occured)
 		return -EIO;
 	else
diff --git a/drivers/s390/net/Kconfig b/drivers/s390/net/Kconfig
index 1a93fa6..5262515 100644
--- a/drivers/s390/net/Kconfig
+++ b/drivers/s390/net/Kconfig
@@ -27,10 +27,7 @@
 	help
 	  Select this option if you want to use inter-user communication
 	  under VM or VIF. If unsure, say "Y" to enable a fast communication
-	  link between VM guests. At boot time the user ID of the guest needs
-	  to be passed to the kernel. Note that both kernels need to be
-	  compiled with this option and both need to be booted with the user ID
-	  of the other VM guest.
+	  link between VM guests.
 
 config NETIUCV
 	tristate "IUCV network device support (VM only)"
diff --git a/drivers/s390/net/qeth.h b/drivers/s390/net/qeth.h
index 53c358c..e95c281 100644
--- a/drivers/s390/net/qeth.h
+++ b/drivers/s390/net/qeth.h
@@ -710,7 +710,7 @@
 	int (*callback)(struct qeth_card *,struct qeth_reply *,unsigned long);
  	u32 seqno;
 	unsigned long offset;
-	int received;
+	atomic_t received;
 	int rc;
 	void *param;
 	struct qeth_card *card;
diff --git a/drivers/s390/net/qeth_main.c b/drivers/s390/net/qeth_main.c
index 2bde4f1..d2efa5f 100644
--- a/drivers/s390/net/qeth_main.c
+++ b/drivers/s390/net/qeth_main.c
@@ -471,7 +471,7 @@
 	    channel->state == CH_STATE_UP)
 		qeth_issue_next_read(card);
 
-	tasklet_schedule(&channel->irq_tasklet);
+	qeth_irq_tasklet((unsigned long)channel);
 	return;
 out:
 	wake_up(&card->wait_q);
@@ -951,40 +951,6 @@
 }
 
 static int
-qeth_register_ip_addresses(void *ptr)
-{
-	struct qeth_card *card;
-
-	card = (struct qeth_card *) ptr;
-	daemonize("qeth_reg_ip");
-	QETH_DBF_TEXT(trace,4,"regipth1");
-	if (!qeth_do_run_thread(card, QETH_SET_IP_THREAD))
-		return 0;
-	QETH_DBF_TEXT(trace,4,"regipth2");
-	qeth_set_ip_addr_list(card);
-	qeth_clear_thread_running_bit(card, QETH_SET_IP_THREAD);
-	return 0;
-}
-
-/*
- * Drive the SET_PROMISC_MODE thread
- */
-static int
-qeth_set_promisc_mode(void *ptr)
-{
-	struct qeth_card *card = (struct qeth_card *) ptr;
-
-	daemonize("qeth_setprm");
-	QETH_DBF_TEXT(trace,4,"setprm1");
-	if (!qeth_do_run_thread(card, QETH_SET_PROMISC_MODE_THREAD))
-		return 0;
-	QETH_DBF_TEXT(trace,4,"setprm2");
-	qeth_setadp_promisc_mode(card);
-	qeth_clear_thread_running_bit(card, QETH_SET_PROMISC_MODE_THREAD);
-	return 0;
-}
-
-static int
 qeth_recover(void *ptr)
 {
 	struct qeth_card *card;
@@ -1047,11 +1013,6 @@
 	if (card->read.state != CH_STATE_UP &&
 	    card->write.state != CH_STATE_UP)
 		return;
-
-	if (qeth_do_start_thread(card, QETH_SET_IP_THREAD))
-		kernel_thread(qeth_register_ip_addresses, (void *)card,SIGCHLD);
-	if (qeth_do_start_thread(card, QETH_SET_PROMISC_MODE_THREAD))
-		kernel_thread(qeth_set_promisc_mode, (void *)card, SIGCHLD);
 	if (qeth_do_start_thread(card, QETH_RECOVER_THREAD))
 		kernel_thread(qeth_recover, (void *) card, SIGCHLD);
 }
@@ -1074,7 +1035,7 @@
 		card->options.layer2 = 1;
 	else
 		card->options.layer2 = 0;
-	card->options.performance_stats = 1;
+	card->options.performance_stats = 0;
 }
 
 /**
@@ -1613,8 +1574,6 @@
 		return -ENOMEM;
 	}
 	qeth_setup_ccw(&card->read, iob->data, QETH_BUFSIZE);
-	wait_event(card->wait_q,
-		   atomic_cmpxchg(&card->read.irq_pending, 0, 1) == 0);
 	QETH_DBF_TEXT(trace, 6, "noirqpnd");
 	rc = ccw_device_start(card->read.ccwdev, &card->read.ccw,
 			      (addr_t) iob, 0, 0);
@@ -1635,6 +1594,7 @@
 	reply = kzalloc(sizeof(struct qeth_reply), GFP_ATOMIC);
 	if (reply){
 		atomic_set(&reply->refcnt, 1);
+		atomic_set(&reply->received, 0);
 		reply->card = card;
 	};
 	return reply;
@@ -1655,31 +1615,6 @@
 		kfree(reply);
 }
 
-static void
-qeth_cmd_timeout(unsigned long data)
-{
-	struct qeth_reply *reply, *list_reply, *r;
-	unsigned long flags;
-
-	reply = (struct qeth_reply *) data;
-	spin_lock_irqsave(&reply->card->lock, flags);
-	list_for_each_entry_safe(list_reply, r,
-				 &reply->card->cmd_waiter_list, list) {
-		if (reply == list_reply){
-			qeth_get_reply(reply);
-			list_del_init(&reply->list);
-			spin_unlock_irqrestore(&reply->card->lock, flags);
-			reply->rc = -ETIME;
-			reply->received = 1;
-			wake_up(&reply->wait_q);
-			qeth_put_reply(reply);
-			return;
-		}
-	}
-	spin_unlock_irqrestore(&reply->card->lock, flags);
-}
-
-
 static struct qeth_ipa_cmd *
 qeth_check_ipa_data(struct qeth_card *card, struct qeth_cmd_buffer *iob)
 {
@@ -1745,7 +1680,7 @@
 	list_for_each_entry_safe(reply, r, &card->cmd_waiter_list, list) {
 		qeth_get_reply(reply);
 		reply->rc = -EIO;
-		reply->received = 1;
+		atomic_inc(&reply->received);
 		list_del_init(&reply->list);
 		wake_up(&reply->wait_q);
 		qeth_put_reply(reply);
@@ -1814,7 +1749,7 @@
 					      &card->cmd_waiter_list);
 				spin_unlock_irqrestore(&card->lock, flags);
 			} else {
-				reply->received = 1;
+				atomic_inc(&reply->received);
 				wake_up(&reply->wait_q);
 			}
 			qeth_put_reply(reply);
@@ -1858,7 +1793,7 @@
 	int rc;
 	unsigned long flags;
 	struct qeth_reply *reply = NULL;
-	struct timer_list timer;
+	unsigned long timeout;
 
 	QETH_DBF_TEXT(trace, 2, "sendctl");
 
@@ -1873,21 +1808,20 @@
 		reply->seqno = QETH_IDX_COMMAND_SEQNO;
 	else
 		reply->seqno = card->seqno.ipa++;
-	init_timer(&timer);
-	timer.function = qeth_cmd_timeout;
-	timer.data = (unsigned long) reply;
 	init_waitqueue_head(&reply->wait_q);
 	spin_lock_irqsave(&card->lock, flags);
 	list_add_tail(&reply->list, &card->cmd_waiter_list);
 	spin_unlock_irqrestore(&card->lock, flags);
 	QETH_DBF_HEX(control, 2, iob->data, QETH_DBF_CONTROL_LEN);
-	wait_event(card->wait_q,
-		   atomic_cmpxchg(&card->write.irq_pending, 0, 1) == 0);
+
+	while (atomic_cmpxchg(&card->write.irq_pending, 0, 1)) ;
 	qeth_prepare_control_data(card, len, iob);
+
 	if (IS_IPA(iob->data))
-		timer.expires = jiffies + QETH_IPA_TIMEOUT;
+		timeout = jiffies + QETH_IPA_TIMEOUT;
 	else
-		timer.expires = jiffies + QETH_TIMEOUT;
+		timeout = jiffies + QETH_TIMEOUT;
+
 	QETH_DBF_TEXT(trace, 6, "noirqpnd");
 	spin_lock_irqsave(get_ccwdev_lock(card->write.ccwdev), flags);
 	rc = ccw_device_start(card->write.ccwdev, &card->write.ccw,
@@ -1906,9 +1840,16 @@
 		wake_up(&card->wait_q);
 		return rc;
 	}
-	add_timer(&timer);
-	wait_event(reply->wait_q, reply->received);
-	del_timer_sync(&timer);
+	while (!atomic_read(&reply->received)) {
+		if (time_after(jiffies, timeout)) {
+			spin_lock_irqsave(&reply->card->lock, flags);
+			list_del_init(&reply->list);
+			spin_unlock_irqrestore(&reply->card->lock, flags);
+			reply->rc = -ETIME;
+			atomic_inc(&reply->received);
+			wake_up(&reply->wait_q);
+		}
+	};
 	rc = reply->rc;
 	qeth_put_reply(reply);
 	return rc;
@@ -2466,32 +2407,17 @@
 		qeth_rebuild_skb_fake_ll_eth(card, skb, hdr);
 }
 
-static inline __u16
+static inline void
 qeth_layer2_rebuild_skb(struct qeth_card *card, struct sk_buff *skb,
 			struct qeth_hdr *hdr)
 {
-	unsigned short vlan_id = 0;
-#ifdef CONFIG_QETH_VLAN
-	struct vlan_hdr *vhdr;
-#endif
-
 	skb->pkt_type = PACKET_HOST;
 	skb->protocol = qeth_type_trans(skb, skb->dev);
 	if (card->options.checksum_type == NO_CHECKSUMMING)
 		skb->ip_summed = CHECKSUM_UNNECESSARY;
 	else
 		skb->ip_summed = CHECKSUM_NONE;
-#ifdef CONFIG_QETH_VLAN
-	if (hdr->hdr.l2.flags[2] & (QETH_LAYER2_FLAG_VLAN)) {
-		vhdr = (struct vlan_hdr *) skb->data;
-		skb->protocol =
-			__constant_htons(vhdr->h_vlan_encapsulated_proto);
-		vlan_id = hdr->hdr.l2.vlan_id;
-		skb_pull(skb, VLAN_HLEN);
-	}
-#endif
 	*((__u32 *)skb->cb) = ++card->seqno.pkt_seqno;
-	return vlan_id;
 }
 
 static inline __u16
@@ -2560,7 +2486,6 @@
 	int offset;
 	int rxrc;
 	__u16 vlan_tag = 0;
-	__u16 *vlan_addr;
 
 	/* get first element of current buffer */
 	element = (struct qdio_buffer_element *)&buf->buffer->element[0];
@@ -2571,7 +2496,7 @@
 				       &offset, &hdr))) {
 		skb->dev = card->dev;
 		if (hdr->hdr.l2.id == QETH_HEADER_TYPE_LAYER2)
-			vlan_tag = qeth_layer2_rebuild_skb(card, skb, hdr);
+			qeth_layer2_rebuild_skb(card, skb, hdr);
 		else if (hdr->hdr.l3.id == QETH_HEADER_TYPE_LAYER3)
 			vlan_tag = qeth_rebuild_skb(card, skb, hdr);
 		else { /*in case of OSN*/
@@ -3968,13 +3893,22 @@
 qeth_prepare_skb(struct qeth_card *card, struct sk_buff *skb,
 		 struct qeth_hdr **hdr, int ipv)
 {
-	struct sk_buff *new_skb;
+	struct sk_buff *new_skb, *new_skb2;
 	
 	QETH_DBF_TEXT(trace, 6, "prepskb");
-
-        new_skb = qeth_realloc_headroom(card, skb, sizeof(struct qeth_hdr));
-       	if (new_skb == NULL)
+	new_skb = skb;
+	new_skb = qeth_pskb_unshare(skb, GFP_ATOMIC);
+	if (!new_skb)
 		return NULL;
+	new_skb2 = qeth_realloc_headroom(card, new_skb,
+					 sizeof(struct qeth_hdr));
+	if (!new_skb2) {
+		__qeth_free_new_skb(skb, new_skb);
+		return NULL;
+	}
+	if (new_skb != skb)
+		__qeth_free_new_skb(new_skb2, new_skb);
+	new_skb = new_skb2;
 	*hdr = __qeth_prepare_skb(card, new_skb, ipv);
 	if (*hdr == NULL) {
 		__qeth_free_new_skb(skb, new_skb);
@@ -4844,9 +4778,11 @@
 			   "(0x%x/%d)\n",
 			   QETH_CARD_IFNAME(card), qeth_arp_get_error_cause(&rc),
 			   tmp, tmp);
-		copy_to_user(udata, qinfo.udata, 4);
+		if (copy_to_user(udata, qinfo.udata, 4))
+			rc = -EFAULT;
 	} else {
-		copy_to_user(udata, qinfo.udata, qinfo.udata_len);
+		if (copy_to_user(udata, qinfo.udata, qinfo.udata_len))
+			rc = -EFAULT;
 	}
 	kfree(qinfo.udata);
 	return rc;
@@ -4992,8 +4928,10 @@
 	if (rc)
 		PRINT_WARN("SNMP command failed on %s: (0x%x)\n",
 			   QETH_CARD_IFNAME(card), rc);
-	 else
-		copy_to_user(udata, qinfo.udata, qinfo.udata_len);
+	else {
+		if (copy_to_user(udata, qinfo.udata, qinfo.udata_len))
+			rc = -EFAULT;
+	}
 
 	kfree(ureq);
 	kfree(qinfo.udata);
@@ -5544,12 +5482,10 @@
 	qeth_add_multicast_ipv6(card);
 #endif
 out:
- 	if (qeth_set_thread_start_bit(card, QETH_SET_IP_THREAD) == 0)
-		schedule_work(&card->kernel_thread_starter);
+	qeth_set_ip_addr_list(card);
 	if (!qeth_adp_supported(card, IPA_SETADP_SET_PROMISC_MODE))
 		return;
-	if (qeth_set_thread_start_bit(card, QETH_SET_PROMISC_MODE_THREAD)==0)
-		schedule_work(&card->kernel_thread_starter);
+	qeth_setadp_promisc_mode(card);
 }
 
 static int
@@ -6351,6 +6287,42 @@
 };
 
 static int
+qeth_hard_header_parse(struct sk_buff *skb, unsigned char *haddr)
+{
+	struct qeth_card *card;
+	struct ethhdr *eth;
+
+	card = qeth_get_card_from_dev(skb->dev);
+	if (card->options.layer2)
+		goto haveheader;
+#ifdef CONFIG_QETH_IPV6
+	/* cause of the manipulated arp constructor and the ARP
+	   flag for OSAE devices we have some nasty exceptions */
+	if (card->info.type == QETH_CARD_TYPE_OSAE) {
+		if (!card->options.fake_ll) {
+			if ((skb->pkt_type==PACKET_OUTGOING) &&
+			    (skb->protocol==ETH_P_IPV6))
+				goto haveheader;
+			else
+				return 0;
+		} else {
+			if ((skb->pkt_type==PACKET_OUTGOING) &&
+			    (skb->protocol==ETH_P_IP))
+				return 0;
+			else
+				goto haveheader;
+		}
+	}
+#endif
+	if (!card->options.fake_ll)
+		return 0;
+haveheader:
+	eth = eth_hdr(skb);
+	memcpy(haddr, eth->h_source, ETH_ALEN);
+	return ETH_ALEN;
+}
+
+static int
 qeth_netdev_init(struct net_device *dev)
 {
 	struct qeth_card *card;
@@ -6388,7 +6360,10 @@
 	if (card->options.fake_ll &&
 		(qeth_get_netdev_flags(card) & IFF_NOARP))
 			dev->hard_header = qeth_fake_header;
-	dev->hard_header_parse = NULL;
+	if (dev->type == ARPHRD_IEEE802_TR)
+		dev->hard_header_parse = NULL;
+	else
+		dev->hard_header_parse = qeth_hard_header_parse;
 	dev->set_mac_address = qeth_layer2_set_mac_address;
 	dev->flags |= qeth_get_netdev_flags(card);
 	if ((card->options.fake_broadcast) ||
@@ -8235,8 +8210,7 @@
 	}
 	if (!qeth_add_ip(card, ipaddr))
 		kfree(ipaddr);
- 	if (qeth_set_thread_start_bit(card, QETH_SET_IP_THREAD) == 0)
-		schedule_work(&card->kernel_thread_starter);
+	qeth_set_ip_addr_list(card);
 	return rc;
 }
 
@@ -8264,8 +8238,7 @@
 		return;
 	if (!qeth_delete_ip(card, ipaddr))
 		kfree(ipaddr);
- 	if (qeth_set_thread_start_bit(card, QETH_SET_IP_THREAD) == 0)
-		schedule_work(&card->kernel_thread_starter);
+	qeth_set_ip_addr_list(card);
 }
 
 /*
@@ -8308,8 +8281,7 @@
 	}
 	if (!qeth_add_ip(card, ipaddr))
 		kfree(ipaddr);
- 	if (qeth_set_thread_start_bit(card, QETH_SET_IP_THREAD) == 0)
-		schedule_work(&card->kernel_thread_starter);
+	qeth_set_ip_addr_list(card);
 	return 0;
 }
 
@@ -8337,8 +8309,7 @@
 		return;
 	if (!qeth_delete_ip(card, ipaddr))
 		kfree(ipaddr);
- 	if (qeth_set_thread_start_bit(card, QETH_SET_IP_THREAD) == 0)
-		schedule_work(&card->kernel_thread_starter);
+	qeth_set_ip_addr_list(card);
 }
 
 /**
@@ -8380,8 +8351,7 @@
 	default:
 		break;
 	}
- 	if (qeth_set_thread_start_bit(card, QETH_SET_IP_THREAD) == 0)
-		schedule_work(&card->kernel_thread_starter);
+	qeth_set_ip_addr_list(card);
 out:
 	return NOTIFY_DONE;
 }
@@ -8433,8 +8403,7 @@
 	default:
 		break;
 	}
- 	if (qeth_set_thread_start_bit(card, QETH_SET_IP_THREAD) == 0)
-		schedule_work(&card->kernel_thread_starter);
+	qeth_set_ip_addr_list(card);
 out:
 	return NOTIFY_DONE;
 }
diff --git a/drivers/serial/mpc52xx_uart.c b/drivers/serial/mpc52xx_uart.c
index 9d11a75..3c4b6c2 100644
--- a/drivers/serial/mpc52xx_uart.c
+++ b/drivers/serial/mpc52xx_uart.c
@@ -789,7 +789,9 @@
 static int __init
 mpc52xx_console_init(void)
 {
+#if defined(CONFIG_PPC_MERGE)
 	mpc52xx_uart_of_enumerate();
+#endif
 	register_console(&mpc52xx_console);
 	return 0;
 }
diff --git a/drivers/usb/class/usblp.c b/drivers/usb/class/usblp.c
index 24ee8be..6377db1 100644
--- a/drivers/usb/class/usblp.c
+++ b/drivers/usb/class/usblp.c
@@ -217,6 +217,7 @@
 	{ 0x0409, 0xbef4, USBLP_QUIRK_BIDIR }, /* NEC Picty760 (HP OEM) */
 	{ 0x0409, 0xf0be, USBLP_QUIRK_BIDIR }, /* NEC Picty920 (HP OEM) */
 	{ 0x0409, 0xf1be, USBLP_QUIRK_BIDIR }, /* NEC Picty800 (HP OEM) */
+	{ 0x0482, 0x0010, USBLP_QUIRK_BIDIR }, /* Kyocera Mita FS 820, by zut <kernel@zut.de> */
 	{ 0, 0 }
 };
 
diff --git a/drivers/usb/core/endpoint.c b/drivers/usb/core/endpoint.c
index c505b76..5e628ae 100644
--- a/drivers/usb/core/endpoint.c
+++ b/drivers/usb/core/endpoint.c
@@ -268,6 +268,7 @@
 	struct ep_device *ep_dev = to_ep_device(dev);
 
 	dev_dbg(dev, "%s called for %s\n", __FUNCTION__, dev->bus_id);
+	endpoint_free_minor(ep_dev);
 	kfree(ep_dev);
 }
 
@@ -349,7 +350,6 @@
 		sprintf(name, "ep_%02x", endpoint->desc.bEndpointAddress);
 		sysfs_remove_link(&ep_dev->dev.parent->kobj, name);
 		sysfs_remove_group(&ep_dev->dev.kobj, &ep_dev_attr_grp);
-		endpoint_free_minor(ep_dev);
 		device_unregister(&ep_dev->dev);
 		endpoint->ep_dev = NULL;
 		destroy_endpoint_class();
diff --git a/drivers/usb/gadget/omap_udc.c b/drivers/usb/gadget/omap_udc.c
index 15d77c3..cdcfd42 100644
--- a/drivers/usb/gadget/omap_udc.c
+++ b/drivers/usb/gadget/omap_udc.c
@@ -42,6 +42,7 @@
 #include <linux/usb_gadget.h>
 #include <linux/usb/otg.h>
 #include <linux/dma-mapping.h>
+#include <linux/clk.h>
 
 #include <asm/byteorder.h>
 #include <asm/io.h>
@@ -60,6 +61,11 @@
 /* bulk DMA seems to be behaving for both IN and OUT */
 #define	USE_DMA
 
+/* FIXME: OMAP2 currently has some problem in DMA mode */
+#ifdef CONFIG_ARCH_OMAP2
+#undef USE_DMA
+#endif
+
 /* ISO too */
 #define	USE_ISO
 
@@ -99,7 +105,7 @@
  * boot parameter "omap_udc:fifo_mode=42"
  */
 module_param (fifo_mode, uint, 0);
-MODULE_PARM_DESC (fifo_mode, "endpoint setup (0 == default)");
+MODULE_PARM_DESC (fifo_mode, "endpoint configuration");
 
 #ifdef	USE_DMA
 static unsigned use_dma = 1;
@@ -122,7 +128,7 @@
 /*-------------------------------------------------------------------------*/
 
 /* there's a notion of "current endpoint" for modifying endpoint
- * state, and PIO access to its FIFO.  
+ * state, and PIO access to its FIFO.
  */
 
 static void use_ep(struct omap_ep *ep, u16 select)
@@ -391,7 +397,7 @@
 #define FIFO_EMPTY	(UDC_NON_ISO_FIFO_EMPTY | UDC_ISO_FIFO_EMPTY)
 #define FIFO_UNREADABLE (UDC_EP_HALTED | FIFO_EMPTY)
 
-static inline int 
+static inline int
 write_packet(u8 *buf, struct omap_req *req, unsigned max)
 {
 	unsigned	len;
@@ -456,7 +462,7 @@
 	return is_last;
 }
 
-static inline int 
+static inline int
 read_packet(u8 *buf, struct omap_req *req, unsigned avail)
 {
 	unsigned	len;
@@ -542,9 +548,9 @@
 	/* omap 3.2/3.3 erratum: sometimes 0 is returned if CSAC/CDAC is
 	 * read before the DMA controller finished disabling the channel.
 	 */
-	csac = omap_readw(OMAP_DMA_CSAC(lch));
+	csac = OMAP_DMA_CSAC_REG(lch);
 	if (csac == 0)
-		csac = omap_readw(OMAP_DMA_CSAC(lch));
+		csac = OMAP_DMA_CSAC_REG(lch);
 	return csac;
 }
 
@@ -555,9 +561,9 @@
 	/* omap 3.2/3.3 erratum: sometimes 0 is returned if CSAC/CDAC is
 	 * read before the DMA controller finished disabling the channel.
 	 */
-	cdac = omap_readw(OMAP_DMA_CDAC(lch));
+	cdac = OMAP_DMA_CDAC_REG(lch);
 	if (cdac == 0)
-		cdac = omap_readw(OMAP_DMA_CDAC(lch));
+		cdac = OMAP_DMA_CDAC_REG(lch);
 	return cdac;
 }
 
@@ -582,7 +588,7 @@
 }
 
 #define DMA_DEST_LAST(x) (cpu_is_omap15xx() \
-		? omap_readw(OMAP_DMA_CSAC(x)) /* really: CPC */ \
+		? OMAP_DMA_CSAC_REG(x) /* really: CPC */ \
 		: dma_cdac(x))
 
 static u16 dma_dest_len(struct omap_ep *ep, dma_addr_t start)
@@ -620,17 +626,19 @@
 			|| (cpu_is_omap15xx() && length < ep->maxpacket)) {
 		txdma_ctrl = UDC_TXN_EOT | length;
 		omap_set_dma_transfer_params(ep->lch, OMAP_DMA_DATA_TYPE_S8,
-				length, 1, sync_mode);
+				length, 1, sync_mode, 0, 0);
 	} else {
 		length = min(length / ep->maxpacket,
 				(unsigned) UDC_TXN_TSC + 1);
- 		txdma_ctrl = length;
+		txdma_ctrl = length;
 		omap_set_dma_transfer_params(ep->lch, OMAP_DMA_DATA_TYPE_S16,
-				ep->ep.maxpacket >> 1, length, sync_mode);
+				ep->ep.maxpacket >> 1, length, sync_mode,
+				0, 0);
 		length *= ep->maxpacket;
 	}
 	omap_set_dma_src_params(ep->lch, OMAP_DMA_PORT_EMIFF,
-		OMAP_DMA_AMODE_POST_INC, req->req.dma + req->req.actual);
+		OMAP_DMA_AMODE_POST_INC, req->req.dma + req->req.actual,
+		0, 0);
 
 	omap_start_dma(ep->lch);
 	ep->dma_counter = dma_csac(ep->lch);
@@ -675,9 +683,11 @@
 	req->dma_bytes = packets * ep->ep.maxpacket;
 	omap_set_dma_transfer_params(ep->lch, OMAP_DMA_DATA_TYPE_S16,
 			ep->ep.maxpacket >> 1, packets,
-			OMAP_DMA_SYNC_ELEMENT);
+			OMAP_DMA_SYNC_ELEMENT,
+			0, 0);
 	omap_set_dma_dest_params(ep->lch, OMAP_DMA_PORT_EMIFF,
-		OMAP_DMA_AMODE_POST_INC, req->req.dma + req->req.actual);
+		OMAP_DMA_AMODE_POST_INC, req->req.dma + req->req.actual,
+		0, 0);
 	ep->dma_counter = DMA_DEST_LAST(ep->lch);
 
 	UDC_RXDMA_REG(ep->dma_channel) = UDC_RXN_STOP | (packets - 1);
@@ -820,7 +830,8 @@
 			omap_set_dma_dest_params(ep->lch,
 				OMAP_DMA_PORT_TIPB,
 				OMAP_DMA_AMODE_CONSTANT,
-				(unsigned long) io_v2p((u32)&UDC_DATA_DMA_REG));
+				(unsigned long) io_v2p((u32)&UDC_DATA_DMA_REG),
+				0, 0);
 		}
 	} else {
 		status = omap_request_dma(OMAP_DMA_USB_W2FC_RX0 - 1 + channel,
@@ -831,7 +842,8 @@
 			omap_set_dma_src_params(ep->lch,
 				OMAP_DMA_PORT_TIPB,
 				OMAP_DMA_AMODE_CONSTANT,
-				(unsigned long) io_v2p((u32)&UDC_DATA_DMA_REG));
+				(unsigned long) io_v2p((u32)&UDC_DATA_DMA_REG),
+				0, 0);
 			/* EMIFF */
 			omap_set_dma_dest_burst_mode(ep->lch,
 						OMAP_DMA_DATA_BURST_4);
@@ -846,7 +858,7 @@
 
 		/* channel type P: hw synch (fifo) */
 		if (!cpu_is_omap15xx())
-			omap_writew(2, OMAP_DMA_LCH_CTRL(ep->lch));
+			OMAP1_DMA_LCH_CTRL_REG(ep->lch) = 2;
 	}
 
 just_restart:
@@ -893,7 +905,7 @@
 	else
 		req = NULL;
 
-	active = ((1 << 7) & omap_readl(OMAP_DMA_CCR(ep->lch))) != 0;
+	active = ((1 << 7) & OMAP_DMA_CCR_REG(ep->lch)) != 0;
 
 	DBG("%s release %s %cxdma%d %p\n", ep->ep.name,
 			active ? "active" : "idle",
@@ -1117,7 +1129,7 @@
 		 */
 		dma_channel_release(ep);
 		dma_channel_claim(ep, channel);
-	} else 
+	} else
 		done(ep, req, -ECONNRESET);
 	spin_unlock_irqrestore(&ep->udc->lock, flags);
 	return 0;
@@ -1153,7 +1165,7 @@
 
 		/* IN endpoints must already be idle */
 		if ((ep->bEndpointAddress & USB_DIR_IN)
-				&& !list_empty(&ep->queue)) { 
+				&& !list_empty(&ep->queue)) {
 			status = -EAGAIN;
 			goto done;
 		}
@@ -1298,6 +1310,23 @@
 	UDC_SYSCON1_REG &= ~UDC_PULLUP_EN;
 }
 
+static struct omap_udc *udc;
+
+static void omap_udc_enable_clock(int enable)
+{
+	if (udc == NULL || udc->dc_clk == NULL || udc->hhc_clk == NULL)
+		return;
+
+	if (enable) {
+		clk_enable(udc->dc_clk);
+		clk_enable(udc->hhc_clk);
+		udelay(100);
+	} else {
+		clk_disable(udc->hhc_clk);
+		clk_disable(udc->dc_clk);
+	}
+}
+
 /*
  * Called by whatever detects VBUS sessions:  external transceiver
  * driver, or maybe GPIO0 VBUS IRQ.  May request 48 MHz clock.
@@ -1318,10 +1347,22 @@
 		else
 			FUNC_MUX_CTRL_0_REG &= ~VBUS_CTRL_1510;
 	}
+	if (udc->dc_clk != NULL && is_active) {
+		if (!udc->clk_requested) {
+			omap_udc_enable_clock(1);
+			udc->clk_requested = 1;
+		}
+	}
 	if (can_pullup(udc))
 		pullup_enable(udc);
 	else
 		pullup_disable(udc);
+	if (udc->dc_clk != NULL && !is_active) {
+		if (udc->clk_requested) {
+			omap_udc_enable_clock(0);
+			udc->clk_requested = 0;
+		}
+	}
 	spin_unlock_irqrestore(&udc->lock, flags);
 	return 0;
 }
@@ -1441,7 +1482,7 @@
 		}
 	}
 
-	/* IN/OUT packets mean we're in the DATA or STATUS stage.  
+	/* IN/OUT packets mean we're in the DATA or STATUS stage.
 	 * This driver uses only uses protocol stalls (ep0 never halts),
 	 * and if we got this far the gadget driver already had a
 	 * chance to stall.  Tries to be forgiving of host oddities.
@@ -1509,7 +1550,7 @@
 				} else if (stat == 0)
 					UDC_CTRL_REG = UDC_SET_FIFO_EN;
 				UDC_EP_NUM_REG = 0;
-				
+
 				/* activate status stage */
 				if (stat == 1) {
 					done(ep0, req, 0);
@@ -1866,7 +1907,7 @@
 
 	spin_lock_irqsave(&ep->udc->lock, flags);
 	if (!list_empty(&ep->queue) && ep->ackwait) {
-		use_ep(ep, 0);
+		use_ep(ep, UDC_EP_SEL);
 		stat_flg = UDC_STAT_FLG_REG;
 
 		if ((stat_flg & UDC_ACK) && (!(stat_flg & UDC_FIFO_EN)
@@ -1876,12 +1917,12 @@
 			VDBG("%s: lose, %04x\n", ep->ep.name, stat_flg);
 			req = container_of(ep->queue.next,
 					struct omap_req, queue);
-			UDC_EP_NUM_REG = ep->bEndpointAddress | UDC_EP_SEL;
 			(void) read_fifo(ep, req);
 			UDC_EP_NUM_REG = ep->bEndpointAddress;
 			UDC_CTRL_REG = UDC_SET_FIFO_EN;
 			ep->ackwait = 1 + ep->double_buf;
-		}
+		} else
+			deselect_ep();
 	}
 	mod_timer(&ep->timer, PIO_OUT_TIMEOUT);
 	spin_unlock_irqrestore(&ep->udc->lock, flags);
@@ -2028,7 +2069,17 @@
 
 /*-------------------------------------------------------------------------*/
 
-static struct omap_udc *udc;
+static inline int machine_needs_vbus_session(void)
+{
+	return (machine_is_omap_innovator()
+		|| machine_is_omap_osk()
+		|| machine_is_omap_apollon()
+#ifndef CONFIG_MACH_OMAP_H4_OTG
+		|| machine_is_omap_h4()
+#endif
+		|| machine_is_sx1()
+		);
+}
 
 int usb_gadget_register_driver (struct usb_gadget_driver *driver)
 {
@@ -2070,6 +2121,9 @@
 	udc->gadget.dev.driver = &driver->driver;
 	spin_unlock_irqrestore(&udc->lock, flags);
 
+	if (udc->dc_clk != NULL)
+		omap_udc_enable_clock(1);
+
 	status = driver->bind (&udc->gadget);
 	if (status) {
 		DBG("bind to %s --> %d\n", driver->driver.name, status);
@@ -2103,10 +2157,12 @@
 	/* boards that don't have VBUS sensing can't autogate 48MHz;
 	 * can't enter deep sleep while a gadget driver is active.
 	 */
-	if (machine_is_omap_innovator() || machine_is_omap_osk())
+	if (machine_needs_vbus_session())
 		omap_vbus_session(&udc->gadget, 1);
 
 done:
+	if (udc->dc_clk != NULL)
+		omap_udc_enable_clock(0);
 	return status;
 }
 EXPORT_SYMBOL(usb_gadget_register_driver);
@@ -2121,7 +2177,10 @@
 	if (!driver || driver != udc->driver || !driver->unbind)
 		return -EINVAL;
 
-	if (machine_is_omap_innovator() || machine_is_omap_osk())
+	if (udc->dc_clk != NULL)
+		omap_udc_enable_clock(1);
+
+	if (machine_needs_vbus_session())
 		omap_vbus_session(&udc->gadget, 0);
 
 	if (udc->transceiver)
@@ -2137,6 +2196,8 @@
 	udc->gadget.dev.driver = NULL;
 	udc->driver = NULL;
 
+	if (udc->dc_clk != NULL)
+		omap_udc_enable_clock(0);
 	DBG("unregistered driver '%s'\n", driver->driver.name);
 	return status;
 }
@@ -2219,7 +2280,7 @@
 	case 0:		return enabled ? "*6wire" : "unused";
 	case 1:		return "4wire";
 	case 2:		return "3wire";
-	case 3: 	return "6wire";
+	case 3:		return "6wire";
 	default:	return "unknown";
 	}
 }
@@ -2228,11 +2289,18 @@
 {
 	u32		tmp;
 	u32		trans;
+	char		*ctrl_name;
 
 	tmp = OTG_REV_REG;
-	trans = USB_TRANSCEIVER_CTRL_REG;
-	seq_printf(s, "\nOTG rev %d.%d, transceiver_ctrl %05x\n",
-		tmp >> 4, tmp & 0xf, trans);
+	if (cpu_is_omap24xx()) {
+		ctrl_name = "control_devconf";
+		trans = CONTROL_DEVCONF_REG;
+	} else {
+		ctrl_name = "tranceiver_ctrl";
+		trans = USB_TRANSCEIVER_CTRL_REG;
+	}
+	seq_printf(s, "\nOTG rev %d.%d, %s %05x\n",
+		tmp >> 4, tmp & 0xf, ctrl_name, trans);
 	tmp = OTG_SYSCON_1_REG;
 	seq_printf(s, "otg_syscon1 %08x usb2 %s, usb1 %s, usb0 %s,"
 			FOURBITS "\n", tmp,
@@ -2307,7 +2375,7 @@
 		driver_desc,
 		use_dma ?  " (dma)" : "");
 
-	tmp = UDC_REV_REG & 0xff; 
+	tmp = UDC_REV_REG & 0xff;
 	seq_printf(s,
 		"UDC rev %d.%d, fifo mode %d, gadget %s\n"
 		"hmc %d, transceiver %s\n",
@@ -2315,11 +2383,16 @@
 		fifo_mode,
 		udc->driver ? udc->driver->driver.name : "(none)",
 		HMC,
-		udc->transceiver ? udc->transceiver->label : "(none)");
-	seq_printf(s, "ULPD control %04x req %04x status %04x\n",
-		__REG16(ULPD_CLOCK_CTRL),
-		__REG16(ULPD_SOFT_REQ),
-		__REG16(ULPD_STATUS_REQ));
+		udc->transceiver
+			? udc->transceiver->label
+			: ((cpu_is_omap1710() || cpu_is_omap24xx())
+				? "external" : "(none)"));
+	if (cpu_class_is_omap1()) {
+		seq_printf(s, "ULPD control %04x req %04x status %04x\n",
+			__REG16(ULPD_CLOCK_CTRL),
+			__REG16(ULPD_SOFT_REQ),
+			__REG16(ULPD_STATUS_REQ));
+	}
 
 	/* OTG controller registers */
 	if (!cpu_is_omap15xx())
@@ -2504,9 +2577,10 @@
 		dbuf = 1;
 	} else {
 		/* double-buffering "not supported" on 15xx,
-		 * and ignored for PIO-IN on 16xx
+		 * and ignored for PIO-IN on newer chips
+		 * (for more reliable behavior)
 		 */
-		if (!use_dma || cpu_is_omap15xx())
+		if (!use_dma || cpu_is_omap15xx() || cpu_is_omap24xx())
 			dbuf = 0;
 
 		switch (maxp) {
@@ -2549,7 +2623,7 @@
 	ep->bEndpointAddress = addr;
 	ep->bmAttributes = type;
 	ep->double_buf = dbuf;
-	ep->udc = udc; 
+	ep->udc = udc;
 
 	ep->ep.name = ep->name;
 	ep->ep.ops = &omap_ep_ops;
@@ -2709,15 +2783,37 @@
 	struct otg_transceiver	*xceiv = NULL;
 	const char		*type = NULL;
 	struct omap_usb_config	*config = pdev->dev.platform_data;
+	struct clk		*dc_clk;
+	struct clk		*hhc_clk;
 
 	/* NOTE:  "knows" the order of the resources! */
-	if (!request_mem_region(pdev->resource[0].start, 
+	if (!request_mem_region(pdev->resource[0].start,
 			pdev->resource[0].end - pdev->resource[0].start + 1,
 			driver_name)) {
 		DBG("request_mem_region failed\n");
 		return -EBUSY;
 	}
 
+	if (cpu_is_omap16xx()) {
+		dc_clk = clk_get(&pdev->dev, "usb_dc_ck");
+		hhc_clk = clk_get(&pdev->dev, "usb_hhc_ck");
+		BUG_ON(IS_ERR(dc_clk) || IS_ERR(hhc_clk));
+		/* can't use omap_udc_enable_clock yet */
+		clk_enable(dc_clk);
+		clk_enable(hhc_clk);
+		udelay(100);
+	}
+
+	if (cpu_is_omap24xx()) {
+		dc_clk = clk_get(&pdev->dev, "usb_fck");
+		hhc_clk = clk_get(&pdev->dev, "usb_l4_ick");
+		BUG_ON(IS_ERR(dc_clk) || IS_ERR(hhc_clk));
+		/* can't use omap_udc_enable_clock yet */
+		clk_enable(dc_clk);
+		clk_enable(hhc_clk);
+		udelay(100);
+	}
+
 	INFO("OMAP UDC rev %d.%d%s\n",
 		UDC_REV_REG >> 4, UDC_REV_REG & 0xf,
 		config->otg ? ", Mini-AB" : "");
@@ -2727,7 +2823,7 @@
 		hmc = HMC_1510;
 		type = "(unknown)";
 
-		if (machine_is_omap_innovator()) {
+		if (machine_is_omap_innovator() || machine_is_sx1()) {
 			/* just set up software VBUS detect, and then
 			 * later rig it so we always report VBUS.
 			 * FIXME without really sensing VBUS, we can't
@@ -2756,6 +2852,15 @@
 		}
 
 		hmc = HMC_1610;
+
+		if (cpu_is_omap24xx()) {
+			/* this could be transceiverless in one of the
+			 * "we don't need to know" modes.
+			 */
+			type = "external";
+			goto known;
+		}
+
 		switch (hmc) {
 		case 0:			/* POWERUP DEFAULT == 0 */
 		case 4:
@@ -2794,6 +2899,7 @@
 			goto cleanup0;
 		}
 	}
+known:
 	INFO("hmc mode %d, %s transceiver\n", hmc, type);
 
 	/* a "gadget" abstracts/virtualizes the controller */
@@ -2818,8 +2924,8 @@
 	status = request_irq(pdev->resource[1].start, omap_udc_irq,
 			IRQF_SAMPLE_RANDOM, driver_name, udc);
 	if (status != 0) {
-		ERR( "can't get irq %ld, err %d\n",
-			pdev->resource[1].start, status);
+		ERR("can't get irq %d, err %d\n",
+			(int) pdev->resource[1].start, status);
 		goto cleanup1;
 	}
 
@@ -2827,24 +2933,41 @@
 	status = request_irq(pdev->resource[2].start, omap_udc_pio_irq,
 			IRQF_SAMPLE_RANDOM, "omap_udc pio", udc);
 	if (status != 0) {
-		ERR( "can't get irq %ld, err %d\n",
-			pdev->resource[2].start, status);
+		ERR("can't get irq %d, err %d\n",
+			(int) pdev->resource[2].start, status);
 		goto cleanup2;
 	}
 #ifdef	USE_ISO
 	status = request_irq(pdev->resource[3].start, omap_udc_iso_irq,
 			IRQF_DISABLED, "omap_udc iso", udc);
 	if (status != 0) {
-		ERR("can't get irq %ld, err %d\n",
-			pdev->resource[3].start, status);
+		ERR("can't get irq %d, err %d\n",
+			(int) pdev->resource[3].start, status);
 		goto cleanup3;
 	}
 #endif
+	if (cpu_is_omap16xx()) {
+		udc->dc_clk = dc_clk;
+		udc->hhc_clk = hhc_clk;
+		clk_disable(hhc_clk);
+		clk_disable(dc_clk);
+	}
+
+	if (cpu_is_omap24xx()) {
+		udc->dc_clk = dc_clk;
+		udc->hhc_clk = hhc_clk;
+		/* FIXME OMAP2 don't release hhc & dc clock */
+#if 0
+		clk_disable(hhc_clk);
+		clk_disable(dc_clk);
+#endif
+	}
 
 	create_proc_file();
-	device_add(&udc->gadget.dev);
-	return 0;
-
+	status = device_add(&udc->gadget.dev);
+	if (!status)
+		return status;
+	/* If fail, fall through */
 #ifdef	USE_ISO
 cleanup3:
 	free_irq(pdev->resource[2].start, udc);
@@ -2860,8 +2983,17 @@
 cleanup0:
 	if (xceiv)
 		put_device(xceiv->dev);
+
+	if (cpu_is_omap16xx() || cpu_is_omap24xx()) {
+		clk_disable(hhc_clk);
+		clk_disable(dc_clk);
+		clk_put(hhc_clk);
+		clk_put(dc_clk);
+	}
+
 	release_mem_region(pdev->resource[0].start,
 			pdev->resource[0].end - pdev->resource[0].start + 1);
+
 	return status;
 }
 
@@ -2891,6 +3023,13 @@
 	free_irq(pdev->resource[2].start, udc);
 	free_irq(pdev->resource[1].start, udc);
 
+	if (udc->dc_clk) {
+		if (udc->clk_requested)
+			omap_udc_enable_clock(0);
+		clk_put(udc->hhc_clk);
+		clk_put(udc->dc_clk);
+	}
+
 	release_mem_region(pdev->resource[0].start,
 			pdev->resource[0].end - pdev->resource[0].start + 1);
 
diff --git a/drivers/usb/gadget/omap_udc.h b/drivers/usb/gadget/omap_udc.h
index 652ee46..1dc398b 100644
--- a/drivers/usb/gadget/omap_udc.h
+++ b/drivers/usb/gadget/omap_udc.h
@@ -175,6 +175,9 @@
 	unsigned			ep0_reset_config:1;
 	unsigned			ep0_setup:1;
 	struct completion		*done;
+	struct clk			*dc_clk;
+	struct clk			*hhc_clk;
+	unsigned			clk_requested:1;
 };
 
 /*-------------------------------------------------------------------------*/
diff --git a/drivers/usb/host/uhci-hcd.c b/drivers/usb/host/uhci-hcd.c
index acd101c..e0d4c23 100644
--- a/drivers/usb/host/uhci-hcd.c
+++ b/drivers/usb/host/uhci-hcd.c
@@ -209,24 +209,16 @@
 
 static int remote_wakeup_is_broken(struct uhci_hcd *uhci)
 {
-	static struct dmi_system_id broken_wakeup_table[] = {
-		{
-			.ident = "Asus A7V8X",
-			.matches = {
-				DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK"),
-				DMI_MATCH(DMI_BOARD_NAME, "A7V8X"),
-				DMI_MATCH(DMI_BOARD_VERSION, "REV 1.xx"),
-			}
-		},
-		{ }
-	};
 	int port;
+	char *sys_info;
+	static char bad_Asus_board[] = "A7V8X";
 
 	/* One of Asus's motherboards has a bug which causes it to
 	 * wake up immediately from suspend-to-RAM if any of the ports
 	 * are connected.  In such cases we will not set EGSM.
 	 */
-	if (dmi_check_system(broken_wakeup_table)) {
+	sys_info = dmi_get_system_info(DMI_BOARD_NAME);
+	if (sys_info && !strcmp(sys_info, bad_Asus_board)) {
 		for (port = 0; port < uhci->rh_numports; ++port) {
 			if (inw(uhci->io_addr + USBPORTSC1 + port * 2) &
 					USBPORTSC_CCS)
@@ -265,7 +257,9 @@
 	int_enable = USBINTR_RESUME;
 	if (remote_wakeup_is_broken(uhci))
 		egsm_enable = 0;
-	if (resume_detect_interrupts_are_broken(uhci) || !egsm_enable)
+	if (resume_detect_interrupts_are_broken(uhci) || !egsm_enable ||
+			!device_may_wakeup(
+				&uhci_to_hcd(uhci)->self.root_hub->dev))
 		uhci->working_RD = int_enable = 0;
 
 	outw(int_enable, uhci->io_addr + USBINTR);
diff --git a/drivers/usb/misc/sisusbvga/sisusb_con.c b/drivers/usb/misc/sisusbvga/sisusb_con.c
index bf26c3c..9148694 100644
--- a/drivers/usb/misc/sisusbvga/sisusb_con.c
+++ b/drivers/usb/misc/sisusbvga/sisusb_con.c
@@ -403,7 +403,7 @@
 
 
 	sisusb_copy_memory(sisusb, (char *)SISUSB_VADDR(x, y),
-				(u32)SISUSB_HADDR(x, y), 2, &written);
+				(long)SISUSB_HADDR(x, y), 2, &written);
 
 	mutex_unlock(&sisusb->lock);
 }
@@ -438,7 +438,7 @@
 	}
 
 	sisusb_copy_memory(sisusb, (char *)SISUSB_VADDR(x, y),
-				(u32)SISUSB_HADDR(x, y), count * 2, &written);
+				(long)SISUSB_HADDR(x, y), count * 2, &written);
 
 	mutex_unlock(&sisusb->lock);
 }
@@ -492,7 +492,7 @@
 
 
 	sisusb_copy_memory(sisusb, (unsigned char *)SISUSB_VADDR(x, y),
-				(u32)SISUSB_HADDR(x, y), length, &written);
+				(long)SISUSB_HADDR(x, y), length, &written);
 
 	mutex_unlock(&sisusb->lock);
 }
@@ -564,7 +564,7 @@
 
 
 	sisusb_copy_memory(sisusb, (unsigned char *)SISUSB_VADDR(dx, dy),
-				(u32)SISUSB_HADDR(dx, dy), length, &written);
+				(long)SISUSB_HADDR(dx, dy), length, &written);
 
 	mutex_unlock(&sisusb->lock);
 }
@@ -612,7 +612,7 @@
 								length);
 
 	sisusb_copy_memory(sisusb, (unsigned char *)c->vc_origin,
-				(u32)SISUSB_HADDR(0, 0),
+				(long)SISUSB_HADDR(0, 0),
 				length, &written);
 
 	mutex_unlock(&sisusb->lock);
@@ -939,7 +939,7 @@
 	}
 
 	sisusb_copy_memory(sisusb, (char *)SISUSB_VADDR(0, t),
-				(u32)SISUSB_HADDR(0, t), length, &written);
+				(long)SISUSB_HADDR(0, t), length, &written);
 
 	mutex_unlock(&sisusb->lock);
 
diff --git a/drivers/usb/net/asix.c b/drivers/usb/net/asix.c
index 95e682e..f538013 100644
--- a/drivers/usb/net/asix.c
+++ b/drivers/usb/net/asix.c
@@ -920,7 +920,7 @@
 		goto out2;
 
 	if ((ret = asix_write_cmd(dev, AX_CMD_SW_PHY_SELECT,
-				0x0000, 0, 0, buf)) < 0) {
+				1, 0, 0, buf)) < 0) {
 		dbg("Select PHY #1 failed: %d", ret);
 		goto out2;
 	}
diff --git a/drivers/usb/serial/Kconfig b/drivers/usb/serial/Kconfig
index 2f4d303..c8999ae 100644
--- a/drivers/usb/serial/Kconfig
+++ b/drivers/usb/serial/Kconfig
@@ -170,7 +170,7 @@
 
 config USB_SERIAL_FUNSOFT
 	tristate "USB Fundamental Software Dongle Driver"
-	depends on USB_SERIAL
+	depends on USB_SERIAL && !(SPARC || SPARC64)
 	---help---
 	  Say Y here if you want to use the Fundamental Software dongle.
 
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index 819266b..5ca04e8 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -625,6 +625,9 @@
 
 	dbg("%s", __FUNCTION__);
 
+	if (port->number != 0)
+		return 0;
+
 	portdata = usb_get_serial_port_data(port);
 
 	if (port->tty) {
diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h
index 5fe7ff4..cddef3e 100644
--- a/drivers/usb/storage/unusual_devs.h
+++ b/drivers/usb/storage/unusual_devs.h
@@ -728,7 +728,7 @@
 		"Apple",
 		"iPod",
 		US_SC_DEVICE, US_PR_DEVICE, NULL,
-		US_FL_FIX_CAPACITY ),
+		US_FL_FIX_CAPACITY | US_FL_NOT_LOCKABLE ),
 
 UNUSUAL_DEV( 0x05ac, 0x1205, 0x0000, 0x9999,
 		"Apple",
@@ -1358,6 +1358,21 @@
 		US_SC_DEVICE, US_PR_DEVICE, NULL,
 		US_FL_IGNORE_RESIDUE ),
 
+/* Reported by Francesco Foresti <frafore@tiscali.it> */
+UNUSUAL_DEV(  0x14cd, 0x6600, 0x0201, 0x0201,
+		"Super Top",
+		"IDE DEVICE",
+		US_SC_DEVICE, US_PR_DEVICE, NULL,
+		US_FL_IGNORE_RESIDUE ),
+
+/* Reported by Robert Schedel <r.schedel@yahoo.de>
+ * Note: this is a 'super top' device like the above 14cd/6600 device */
+UNUSUAL_DEV(  0x1652, 0x6600, 0x0201, 0x0201,
+		"Teac",
+		"HD-35PUK-B",
+		US_SC_DEVICE, US_PR_DEVICE, NULL,
+		US_FL_IGNORE_RESIDUE ),
+
 /* patch submitted by Davide Perini <perini.davide@dpsoftware.org>
  * and Renato Perini <rperini@email.it>
  */
diff --git a/fs/adfs/dir_f.c b/fs/adfs/dir_f.c
index bbfc862..b9b2b27 100644
--- a/fs/adfs/dir_f.c
+++ b/fs/adfs/dir_f.c
@@ -53,7 +53,7 @@
 {
 	char *old_buf = buf;
 
-	while (*ptr >= ' ' && maxlen--) {
+	while ((unsigned char)*ptr >= ' ' && maxlen--) {
 		if (*ptr == '/')
 			*buf++ = '.';
 		else
diff --git a/fs/bad_inode.c b/fs/bad_inode.c
index 34e6d7b..869f519 100644
--- a/fs/bad_inode.c
+++ b/fs/bad_inode.c
@@ -14,59 +14,307 @@
 #include <linux/time.h>
 #include <linux/smp_lock.h>
 #include <linux/namei.h>
+#include <linux/poll.h>
 
-static int return_EIO(void)
+
+static loff_t bad_file_llseek(struct file *file, loff_t offset, int origin)
 {
 	return -EIO;
 }
 
-#define EIO_ERROR ((void *) (return_EIO))
+static ssize_t bad_file_read(struct file *filp, char __user *buf,
+			size_t size, loff_t *ppos)
+{
+        return -EIO;
+}
+
+static ssize_t bad_file_write(struct file *filp, const char __user *buf,
+			size_t siz, loff_t *ppos)
+{
+        return -EIO;
+}
+
+static ssize_t bad_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
+			unsigned long nr_segs, loff_t pos)
+{
+	return -EIO;
+}
+
+static ssize_t bad_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
+			unsigned long nr_segs, loff_t pos)
+{
+	return -EIO;
+}
+
+static int bad_file_readdir(struct file *filp, void *dirent, filldir_t filldir)
+{
+	return -EIO;
+}
+
+static unsigned int bad_file_poll(struct file *filp, poll_table *wait)
+{
+	return POLLERR;
+}
+
+static int bad_file_ioctl (struct inode *inode, struct file *filp,
+			unsigned int cmd, unsigned long arg)
+{
+	return -EIO;
+}
+
+static long bad_file_unlocked_ioctl(struct file *file, unsigned cmd,
+			unsigned long arg)
+{
+	return -EIO;
+}
+
+static long bad_file_compat_ioctl(struct file *file, unsigned int cmd,
+			unsigned long arg)
+{
+	return -EIO;
+}
+
+static int bad_file_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	return -EIO;
+}
+
+static int bad_file_open(struct inode *inode, struct file *filp)
+{
+	return -EIO;
+}
+
+static int bad_file_flush(struct file *file, fl_owner_t id)
+{
+	return -EIO;
+}
+
+static int bad_file_release(struct inode *inode, struct file *filp)
+{
+	return -EIO;
+}
+
+static int bad_file_fsync(struct file *file, struct dentry *dentry,
+			int datasync)
+{
+	return -EIO;
+}
+
+static int bad_file_aio_fsync(struct kiocb *iocb, int datasync)
+{
+	return -EIO;
+}
+
+static int bad_file_fasync(int fd, struct file *filp, int on)
+{
+	return -EIO;
+}
+
+static int bad_file_lock(struct file *file, int cmd, struct file_lock *fl)
+{
+	return -EIO;
+}
+
+static ssize_t bad_file_sendfile(struct file *in_file, loff_t *ppos,
+			size_t count, read_actor_t actor, void *target)
+{
+	return -EIO;
+}
+
+static ssize_t bad_file_sendpage(struct file *file, struct page *page,
+			int off, size_t len, loff_t *pos, int more)
+{
+	return -EIO;
+}
+
+static unsigned long bad_file_get_unmapped_area(struct file *file,
+				unsigned long addr, unsigned long len,
+				unsigned long pgoff, unsigned long flags)
+{
+	return -EIO;
+}
+
+static int bad_file_check_flags(int flags)
+{
+	return -EIO;
+}
+
+static int bad_file_dir_notify(struct file *file, unsigned long arg)
+{
+	return -EIO;
+}
+
+static int bad_file_flock(struct file *filp, int cmd, struct file_lock *fl)
+{
+	return -EIO;
+}
+
+static ssize_t bad_file_splice_write(struct pipe_inode_info *pipe,
+			struct file *out, loff_t *ppos, size_t len,
+			unsigned int flags)
+{
+	return -EIO;
+}
+
+static ssize_t bad_file_splice_read(struct file *in, loff_t *ppos,
+			struct pipe_inode_info *pipe, size_t len,
+			unsigned int flags)
+{
+	return -EIO;
+}
 
 static const struct file_operations bad_file_ops =
 {
-	.llseek		= EIO_ERROR,
-	.aio_read	= EIO_ERROR,
-	.read		= EIO_ERROR,
-	.write		= EIO_ERROR,
-	.aio_write	= EIO_ERROR,
-	.readdir	= EIO_ERROR,
-	.poll		= EIO_ERROR,
-	.ioctl		= EIO_ERROR,
-	.mmap		= EIO_ERROR,
-	.open		= EIO_ERROR,
-	.flush		= EIO_ERROR,
-	.release	= EIO_ERROR,
-	.fsync		= EIO_ERROR,
-	.aio_fsync	= EIO_ERROR,
-	.fasync		= EIO_ERROR,
-	.lock		= EIO_ERROR,
-	.sendfile	= EIO_ERROR,
-	.sendpage	= EIO_ERROR,
-	.get_unmapped_area = EIO_ERROR,
+	.llseek		= bad_file_llseek,
+	.read		= bad_file_read,
+	.write		= bad_file_write,
+	.aio_read	= bad_file_aio_read,
+	.aio_write	= bad_file_aio_write,
+	.readdir	= bad_file_readdir,
+	.poll		= bad_file_poll,
+	.ioctl		= bad_file_ioctl,
+	.unlocked_ioctl	= bad_file_unlocked_ioctl,
+	.compat_ioctl	= bad_file_compat_ioctl,
+	.mmap		= bad_file_mmap,
+	.open		= bad_file_open,
+	.flush		= bad_file_flush,
+	.release	= bad_file_release,
+	.fsync		= bad_file_fsync,
+	.aio_fsync	= bad_file_aio_fsync,
+	.fasync		= bad_file_fasync,
+	.lock		= bad_file_lock,
+	.sendfile	= bad_file_sendfile,
+	.sendpage	= bad_file_sendpage,
+	.get_unmapped_area = bad_file_get_unmapped_area,
+	.check_flags	= bad_file_check_flags,
+	.dir_notify	= bad_file_dir_notify,
+	.flock		= bad_file_flock,
+	.splice_write	= bad_file_splice_write,
+	.splice_read	= bad_file_splice_read,
 };
 
+static int bad_inode_create (struct inode *dir, struct dentry *dentry,
+		int mode, struct nameidata *nd)
+{
+	return -EIO;
+}
+
+static struct dentry *bad_inode_lookup(struct inode *dir,
+			struct dentry *dentry, struct nameidata *nd)
+{
+	return ERR_PTR(-EIO);
+}
+
+static int bad_inode_link (struct dentry *old_dentry, struct inode *dir,
+		struct dentry *dentry)
+{
+	return -EIO;
+}
+
+static int bad_inode_unlink(struct inode *dir, struct dentry *dentry)
+{
+	return -EIO;
+}
+
+static int bad_inode_symlink (struct inode *dir, struct dentry *dentry,
+		const char *symname)
+{
+	return -EIO;
+}
+
+static int bad_inode_mkdir(struct inode *dir, struct dentry *dentry,
+			int mode)
+{
+	return -EIO;
+}
+
+static int bad_inode_rmdir (struct inode *dir, struct dentry *dentry)
+{
+	return -EIO;
+}
+
+static int bad_inode_mknod (struct inode *dir, struct dentry *dentry,
+			int mode, dev_t rdev)
+{
+	return -EIO;
+}
+
+static int bad_inode_rename (struct inode *old_dir, struct dentry *old_dentry,
+		struct inode *new_dir, struct dentry *new_dentry)
+{
+	return -EIO;
+}
+
+static int bad_inode_readlink(struct dentry *dentry, char __user *buffer,
+		int buflen)
+{
+	return -EIO;
+}
+
+static int bad_inode_permission(struct inode *inode, int mask,
+			struct nameidata *nd)
+{
+	return -EIO;
+}
+
+static int bad_inode_getattr(struct vfsmount *mnt, struct dentry *dentry,
+			struct kstat *stat)
+{
+	return -EIO;
+}
+
+static int bad_inode_setattr(struct dentry *direntry, struct iattr *attrs)
+{
+	return -EIO;
+}
+
+static int bad_inode_setxattr(struct dentry *dentry, const char *name,
+		const void *value, size_t size, int flags)
+{
+	return -EIO;
+}
+
+static ssize_t bad_inode_getxattr(struct dentry *dentry, const char *name,
+			void *buffer, size_t size)
+{
+	return -EIO;
+}
+
+static ssize_t bad_inode_listxattr(struct dentry *dentry, char *buffer,
+			size_t buffer_size)
+{
+	return -EIO;
+}
+
+static int bad_inode_removexattr(struct dentry *dentry, const char *name)
+{
+	return -EIO;
+}
+
 static struct inode_operations bad_inode_ops =
 {
-	.create		= EIO_ERROR,
-	.lookup		= EIO_ERROR,
-	.link		= EIO_ERROR,
-	.unlink		= EIO_ERROR,
-	.symlink	= EIO_ERROR,
-	.mkdir		= EIO_ERROR,
-	.rmdir		= EIO_ERROR,
-	.mknod		= EIO_ERROR,
-	.rename		= EIO_ERROR,
-	.readlink	= EIO_ERROR,
+	.create		= bad_inode_create,
+	.lookup		= bad_inode_lookup,
+	.link		= bad_inode_link,
+	.unlink		= bad_inode_unlink,
+	.symlink	= bad_inode_symlink,
+	.mkdir		= bad_inode_mkdir,
+	.rmdir		= bad_inode_rmdir,
+	.mknod		= bad_inode_mknod,
+	.rename		= bad_inode_rename,
+	.readlink	= bad_inode_readlink,
 	/* follow_link must be no-op, otherwise unmounting this inode
 	   won't work */
-	.truncate	= EIO_ERROR,
-	.permission	= EIO_ERROR,
-	.getattr	= EIO_ERROR,
-	.setattr	= EIO_ERROR,
-	.setxattr	= EIO_ERROR,
-	.getxattr	= EIO_ERROR,
-	.listxattr	= EIO_ERROR,
-	.removexattr	= EIO_ERROR,
+	/* put_link returns void */
+	/* truncate returns void */
+	.permission	= bad_inode_permission,
+	.getattr	= bad_inode_getattr,
+	.setattr	= bad_inode_setattr,
+	.setxattr	= bad_inode_setxattr,
+	.getxattr	= bad_inode_getxattr,
+	.listxattr	= bad_inode_listxattr,
+	.removexattr	= bad_inode_removexattr,
+	/* truncate_range returns void */
 };
 
 
@@ -88,7 +336,7 @@
  *	on it to fail from this point on.
  */
  
-void make_bad_inode(struct inode * inode) 
+void make_bad_inode(struct inode *inode)
 {
 	remove_inode_hash(inode);
 
@@ -113,7 +361,7 @@
  *	Returns true if the inode in question has been marked as bad.
  */
  
-int is_bad_inode(struct inode * inode) 
+int is_bad_inode(struct inode *inode)
 {
 	return (inode->i_op == &bad_inode_ops);	
 }
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index d3adfd3..7cb2872 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -854,13 +854,7 @@
 			 * default mmap base, as well as whatever program they
 			 * might try to exec.  This is because the brk will
 			 * follow the loader, and is not movable.  */
-			if (current->flags & PF_RANDOMIZE)
-				load_bias = randomize_range(0x10000,
-							    ELF_ET_DYN_BASE,
-							    0);
-			else
-				load_bias = ELF_ET_DYN_BASE;
-			load_bias = ELF_PAGESTART(load_bias - vaddr);
+			load_bias = ELF_PAGESTART(ELF_ET_DYN_BASE - vaddr);
 		}
 
 		error = elf_map(bprm->file, load_bias + vaddr, elf_ppnt,
diff --git a/fs/ufs/balloc.c b/fs/ufs/balloc.c
index b823814..2e0021e 100644
--- a/fs/ufs/balloc.c
+++ b/fs/ufs/balloc.c
@@ -275,6 +275,25 @@
 	UFSD("EXIT\n");
 }
 
+static void ufs_clear_frags(struct inode *inode, sector_t beg, unsigned int n,
+			    int sync)
+{
+	struct buffer_head *bh;
+	sector_t end = beg + n;
+
+	for (; beg < end; ++beg) {
+		bh = sb_getblk(inode->i_sb, beg);
+		lock_buffer(bh);
+		memset(bh->b_data, 0, inode->i_sb->s_blocksize);
+		set_buffer_uptodate(bh);
+		mark_buffer_dirty(bh);
+		unlock_buffer(bh);
+		if (IS_SYNC(inode) || sync)
+			sync_dirty_buffer(bh);
+		brelse(bh);
+	}
+}
+
 unsigned ufs_new_fragments(struct inode * inode, __fs32 * p, unsigned fragment,
 			   unsigned goal, unsigned count, int * err, struct page *locked_page)
 {
@@ -350,6 +369,8 @@
 			*p = cpu_to_fs32(sb, result);
 			*err = 0;
 			UFS_I(inode)->i_lastfrag = max_t(u32, UFS_I(inode)->i_lastfrag, fragment + count);
+			ufs_clear_frags(inode, result + oldcount, newcount - oldcount,
+					locked_page != NULL);
 		}
 		unlock_super(sb);
 		UFSD("EXIT, result %u\n", result);
@@ -363,6 +384,8 @@
 	if (result) {
 		*err = 0;
 		UFS_I(inode)->i_lastfrag = max_t(u32, UFS_I(inode)->i_lastfrag, fragment + count);
+		ufs_clear_frags(inode, result + oldcount, newcount - oldcount,
+				locked_page != NULL);
 		unlock_super(sb);
 		UFSD("EXIT, result %u\n", result);
 		return result;
@@ -398,6 +421,8 @@
 		*p = cpu_to_fs32(sb, result);
 		*err = 0;
 		UFS_I(inode)->i_lastfrag = max_t(u32, UFS_I(inode)->i_lastfrag, fragment + count);
+		ufs_clear_frags(inode, result + oldcount, newcount - oldcount,
+				locked_page != NULL);
 		unlock_super(sb);
 		if (newcount < request)
 			ufs_free_fragments (inode, result + newcount, request - newcount);
diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c
index ee1eaa6..2fbab0a 100644
--- a/fs/ufs/inode.c
+++ b/fs/ufs/inode.c
@@ -156,36 +156,6 @@
 	return ret;
 }
 
-static void ufs_clear_frag(struct inode *inode, struct buffer_head *bh)
-{
-	lock_buffer(bh);
-	memset(bh->b_data, 0, inode->i_sb->s_blocksize);
-	set_buffer_uptodate(bh);
-	mark_buffer_dirty(bh);
-	unlock_buffer(bh);
-	if (IS_SYNC(inode))
-		sync_dirty_buffer(bh);
-}
-
-static struct buffer_head *
-ufs_clear_frags(struct inode *inode, sector_t beg,
-		unsigned int n, sector_t want)
-{
-	struct buffer_head *res = NULL, *bh;
-	sector_t end = beg + n;
-
-	for (; beg < end; ++beg) {
-		bh = sb_getblk(inode->i_sb, beg);
-		ufs_clear_frag(inode, bh);
-		if (want != beg)
-			brelse(bh);
-		else
-			res = bh;
-	}
-	BUG_ON(!res);
-	return res;
-}
-
 /**
  * ufs_inode_getfrag() - allocate new fragment(s)
  * @inode - pointer to inode
@@ -302,7 +272,7 @@
 	}
 
 	if (!phys) {
-		result = ufs_clear_frags(inode, tmp, required, tmp + blockoff);
+		result = sb_getblk(sb, tmp + blockoff);
 	} else {
 		*phys = tmp + blockoff;
 		result = NULL;
@@ -403,8 +373,7 @@
 
 
 	if (!phys) {
-		result = ufs_clear_frags(inode, tmp, uspi->s_fpb,
-					 tmp + blockoff);
+		result = sb_getblk(sb, tmp + blockoff);
 	} else {
 		*phys = tmp + blockoff;
 		*new = 1;
@@ -471,13 +440,13 @@
 #define GET_INODE_DATABLOCK(x) \
 	ufs_inode_getfrag(inode, x, fragment, 1, &err, &phys, &new, bh_result->b_page)
 #define GET_INODE_PTR(x) \
-	ufs_inode_getfrag(inode, x, fragment, uspi->s_fpb, &err, NULL, NULL, bh_result->b_page)
+	ufs_inode_getfrag(inode, x, fragment, uspi->s_fpb, &err, NULL, NULL, NULL)
 #define GET_INDIRECT_DATABLOCK(x) \
 	ufs_inode_getblock(inode, bh, x, fragment,	\
-			  &err, &phys, &new, bh_result->b_page);
+			  &err, &phys, &new, bh_result->b_page)
 #define GET_INDIRECT_PTR(x) \
 	ufs_inode_getblock(inode, bh, x, fragment,	\
-			  &err, NULL, NULL, bh_result->b_page);
+			  &err, NULL, NULL, NULL)
 
 	if (ptr < UFS_NDIR_FRAGMENT) {
 		bh = GET_INODE_DATABLOCK(ptr);
diff --git a/include/asm-arm/arch-iop32x/iop32x.h b/include/asm-arm/arch-iop32x/iop32x.h
index 4bbd85f..2e94690 100644
--- a/include/asm-arm/arch-iop32x/iop32x.h
+++ b/include/asm-arm/arch-iop32x/iop32x.h
@@ -19,7 +19,7 @@
  * Peripherals that are shared between the iop32x and iop33x but
  * located at different addresses.
  */
-#define IOP3XX_GPIO_REG(reg)	(IOP3XX_PERIPHERAL_VIRT_BASE + 0x07c0 + (reg))
+#define IOP3XX_GPIO_REG(reg)	(IOP3XX_PERIPHERAL_VIRT_BASE + 0x07c4 + (reg))
 #define IOP3XX_TIMER_REG(reg)	(IOP3XX_PERIPHERAL_VIRT_BASE + 0x07e0 + (reg))
 
 #include <asm/hardware/iop3xx.h>
diff --git a/include/asm-arm/cacheflush.h b/include/asm-arm/cacheflush.h
index d510495..5f531ea 100644
--- a/include/asm-arm/cacheflush.h
+++ b/include/asm-arm/cacheflush.h
@@ -357,6 +357,16 @@
 
 extern void __flush_dcache_page(struct address_space *mapping, struct page *page);
 
+#define ARCH_HAS_FLUSH_ANON_PAGE
+static inline void flush_anon_page(struct vm_area_struct *vma,
+			 struct page *page, unsigned long vmaddr)
+{
+	extern void __flush_anon_page(struct vm_area_struct *vma,
+				struct page *, unsigned long);
+	if (PageAnon(page))
+		__flush_anon_page(vma, page, vmaddr);
+}
+
 #define flush_dcache_mmap_lock(mapping) \
 	write_lock_irq(&(mapping)->tree_lock)
 #define flush_dcache_mmap_unlock(mapping) \
diff --git a/include/asm-arm/hardware/iop3xx.h b/include/asm-arm/hardware/iop3xx.h
index 1018a74..13ac8a4 100644
--- a/include/asm-arm/hardware/iop3xx.h
+++ b/include/asm-arm/hardware/iop3xx.h
@@ -168,9 +168,9 @@
 #define IOP3XX_PERCR0		(volatile u32 *)IOP3XX_REG_ADDR(0x0710)
 
 /* General Purpose I/O  */
-#define IOP3XX_GPOE		(volatile u32 *)IOP3XX_GPIO_REG(0x0004)
-#define IOP3XX_GPID		(volatile u32 *)IOP3XX_GPIO_REG(0x0008)
-#define IOP3XX_GPOD		(volatile u32 *)IOP3XX_GPIO_REG(0x000c)
+#define IOP3XX_GPOE		(volatile u32 *)IOP3XX_GPIO_REG(0x0000)
+#define IOP3XX_GPID		(volatile u32 *)IOP3XX_GPIO_REG(0x0004)
+#define IOP3XX_GPOD		(volatile u32 *)IOP3XX_GPIO_REG(0x0008)
 
 /* Timers  */
 #define IOP3XX_TU_TMR0		(volatile u32 *)IOP3XX_TIMER_REG(0x0000)
diff --git a/include/asm-i386/boot.h b/include/asm-i386/boot.h
index 8ce79a6..e7686d0 100644
--- a/include/asm-i386/boot.h
+++ b/include/asm-i386/boot.h
@@ -13,7 +13,8 @@
 #define ASK_VGA		0xfffd		/* ask for it at bootup */
 
 /* Physical address where kenrel should be loaded. */
-#define LOAD_PHYSICAL_ADDR ((0x100000 + CONFIG_PHYSICAL_ALIGN - 1) \
+#define LOAD_PHYSICAL_ADDR ((CONFIG_PHYSICAL_START \
+				+ (CONFIG_PHYSICAL_ALIGN - 1)) \
 				& ~(CONFIG_PHYSICAL_ALIGN - 1))
 
 #endif /* _LINUX_BOOT_H */
diff --git a/include/asm-mips/checksum.h b/include/asm-mips/checksum.h
index 9b768c3..24cdcc6 100644
--- a/include/asm-mips/checksum.h
+++ b/include/asm-mips/checksum.h
@@ -29,31 +29,38 @@
  */
 __wsum csum_partial(const void *buff, int len, __wsum sum);
 
+__wsum __csum_partial_copy_user(const void *src, void *dst,
+				int len, __wsum sum, int *err_ptr);
+
 /*
  * this is a new version of the above that records errors it finds in *errp,
  * but continues and zeros the rest of the buffer.
  */
-__wsum csum_partial_copy_from_user(const void __user *src,
-					 void *dst, int len,
-					 __wsum sum, int *errp);
+static inline
+__wsum csum_partial_copy_from_user(const void __user *src, void *dst, int len,
+				   __wsum sum, int *err_ptr)
+{
+	might_sleep();
+	return __csum_partial_copy_user((__force void *)src, dst,
+					len, sum, err_ptr);
+}
 
 /*
  * Copy and checksum to user
  */
 #define HAVE_CSUM_COPY_USER
-static inline __wsum csum_and_copy_to_user (const void *src, void __user *dst,
-						  int len, __wsum sum,
-						  int *err_ptr)
+static inline
+__wsum csum_and_copy_to_user(const void *src, void __user *dst, int len,
+			     __wsum sum, int *err_ptr)
 {
 	might_sleep();
-	sum = csum_partial(src, len, sum);
-
-	if (copy_to_user(dst, src, len)) {
+	if (access_ok(VERIFY_WRITE, dst, len))
+		return __csum_partial_copy_user(src, (__force void *)dst,
+						len, sum, err_ptr);
+	if (len)
 		*err_ptr = -EFAULT;
-		return (__force __wsum)-1;
-	}
 
-	return sum;
+	return (__force __wsum)-1; /* invalid checksum */
 }
 
 /*
diff --git a/include/asm-mips/irq.h b/include/asm-mips/irq.h
index 6765708..386da82 100644
--- a/include/asm-mips/irq.h
+++ b/include/asm-mips/irq.h
@@ -31,14 +31,14 @@
  * functions will take over re-enabling the low-level mask.
  * Otherwise it will be done on return from exception.
  */
-#define __DO_IRQ_SMTC_HOOK()						\
+#define __DO_IRQ_SMTC_HOOK(irq)						\
 do {									\
 	if (irq_hwmask[irq] & 0x0000ff00)				\
 		write_c0_tccontext(read_c0_tccontext() &		\
 		                   ~(irq_hwmask[irq] & 0x0000ff00));	\
 } while (0)
 #else
-#define __DO_IRQ_SMTC_HOOK() do { } while (0)
+#define __DO_IRQ_SMTC_HOOK(irq) do { } while (0)
 #endif
 
 /*
@@ -52,7 +52,7 @@
 #define do_IRQ(irq)							\
 do {									\
 	irq_enter();							\
-	__DO_IRQ_SMTC_HOOK();						\
+	__DO_IRQ_SMTC_HOOK(irq);					\
 	generic_handle_irq(irq);					\
 	irq_exit();							\
 } while (0)
diff --git a/include/asm-parisc/cacheflush.h b/include/asm-parisc/cacheflush.h
index aedb051..a799dd8 100644
--- a/include/asm-parisc/cacheflush.h
+++ b/include/asm-parisc/cacheflush.h
@@ -186,7 +186,7 @@
 }
 
 static inline void
-flush_anon_page(struct page *page, unsigned long vmaddr)
+flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned long vmaddr)
 {
 	if (PageAnon(page))
 		flush_user_dcache_page(vmaddr);
diff --git a/include/asm-powerpc/bug.h b/include/asm-powerpc/bug.h
index 7095688..f6fa394 100644
--- a/include/asm-powerpc/bug.h
+++ b/include/asm-powerpc/bug.h
@@ -11,10 +11,31 @@
 #define BUG_OPCODE .long 0x00b00b00  /* For asm */
 #define BUG_ILLEGAL_INSTR "0x00b00b00" /* For BUG macro */
 
-#ifndef __ASSEMBLY__
-
 #ifdef CONFIG_BUG
 
+#ifdef __ASSEMBLY__
+#ifdef CONFIG_DEBUG_BUGVERBOSE
+.macro EMIT_BUG_ENTRY addr,file,line,flags
+	 .section __bug_table,"a"
+5001:	 PPC_LONG \addr, 5002f
+	 .short \line, \flags
+	 .org 5001b+BUG_ENTRY_SIZE
+	 .previous
+	 .section .rodata,"a"
+5002:	 .asciz "\file"
+	 .previous
+.endm
+#else
+ .macro EMIT_BUG_ENTRY addr,file,line,flags
+	 .section __bug_table,"a"
+5001:	 PPC_LONG \addr
+	 .short \flags
+	 .org 5001b+BUG_ENTRY_SIZE
+	 .previous
+.endm
+#endif /* verbose */
+
+#else /* !__ASSEMBLY__ */
 /* _EMIT_BUG_ENTRY expects args %0,%1,%2,%3 to be FILE, LINE, flags and
    sizeof(struct bug_entry), respectively */
 #ifdef CONFIG_DEBUG_BUGVERBOSE
@@ -91,8 +112,8 @@
 #define HAVE_ARCH_BUG
 #define HAVE_ARCH_BUG_ON
 #define HAVE_ARCH_WARN_ON
-#endif /* CONFIG_BUG */
 #endif /* __ASSEMBLY __ */
+#endif /* CONFIG_BUG */
 
 #include <asm-generic/bug.h>
 
diff --git a/include/asm-powerpc/hvcall.h b/include/asm-powerpc/hvcall.h
index 257d1ce..7a50073 100644
--- a/include/asm-powerpc/hvcall.h
+++ b/include/asm-powerpc/hvcall.h
@@ -252,8 +252,6 @@
 	unsigned long	tb_total;	/* total wall time (mftb) of calls. */
 	unsigned long	purr_total;	/* total cpu time (PURR) of calls. */
 };
-void update_hcall_stats(unsigned long opcode, unsigned long tb_delta,
-			unsigned long purr_delta);
 #define HCALL_STAT_ARRAY_SIZE	((MAX_HCALL_OPCODE >> 2) + 1)
 
 #endif /* __ASSEMBLY__ */
diff --git a/include/asm-powerpc/mpc52xx.h b/include/asm-powerpc/mpc52xx.h
index 4a28a85..4560d72 100644
--- a/include/asm-powerpc/mpc52xx.h
+++ b/include/asm-powerpc/mpc52xx.h
@@ -244,6 +244,7 @@
 extern void __iomem * mpc52xx_find_and_map(const char *);
 extern unsigned int mpc52xx_find_ipb_freq(struct device_node *node);
 extern void mpc52xx_setup_cpu(void);
+extern void mpc52xx_declare_of_platform_devices(void);
 
 extern void mpc52xx_init_irq(void);
 extern unsigned int mpc52xx_get_irq(void);
diff --git a/include/asm-s390/futex.h b/include/asm-s390/futex.h
index 5e261e1..5c5d02d 100644
--- a/include/asm-s390/futex.h
+++ b/include/asm-s390/futex.h
@@ -4,8 +4,8 @@
 #ifdef __KERNEL__
 
 #include <linux/futex.h>
+#include <linux/uaccess.h>
 #include <asm/errno.h>
-#include <asm/uaccess.h>
 
 static inline int futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
 {
@@ -21,7 +21,9 @@
 	if (! access_ok (VERIFY_WRITE, uaddr, sizeof(int)))
 		return -EFAULT;
 
+	pagefault_disable();
 	ret = uaccess.futex_atomic_op(op, uaddr, oparg, &oldval);
+	pagefault_enable();
 
 	if (!ret) {
 		switch (cmp) {
diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index ca9a602..645d440 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -8,7 +8,7 @@
 #include <asm/cacheflush.h>
 
 #ifndef ARCH_HAS_FLUSH_ANON_PAGE
-static inline void flush_anon_page(struct page *page, unsigned long vmaddr)
+static inline void flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned long vmaddr)
 {
 }
 #endif
diff --git a/include/linux/kvm.h b/include/linux/kvm.h
index 28fdce1..bc8b461 100644
--- a/include/linux/kvm.h
+++ b/include/linux/kvm.h
@@ -11,7 +11,7 @@
 #include <asm/types.h>
 #include <linux/ioctl.h>
 
-#define KVM_API_VERSION 1
+#define KVM_API_VERSION 2
 
 /*
  * Architectural interrupt line count, and the size of the bitmap needed
@@ -45,6 +45,7 @@
 	KVM_EXIT_DEBUG            = 4,
 	KVM_EXIT_HLT              = 5,
 	KVM_EXIT_MMIO             = 6,
+	KVM_EXIT_IRQ_WINDOW_OPEN  = 7,
 };
 
 /* for KVM_RUN */
@@ -53,11 +54,19 @@
 	__u32 vcpu;
 	__u32 emulated;  /* skip current instruction */
 	__u32 mmio_completed; /* mmio request completed */
+	__u8 request_interrupt_window;
+	__u8 padding1[3];
 
 	/* out */
 	__u32 exit_type;
 	__u32 exit_reason;
 	__u32 instruction_length;
+	__u8 ready_for_interrupt_injection;
+	__u8 if_flag;
+	__u16 padding2;
+	__u64 cr8;
+	__u64 apic_base;
+
 	union {
 		/* KVM_EXIT_UNKNOWN */
 		struct {
diff --git a/include/linux/magic.h b/include/linux/magic.h
index 156c40f..b78bbf4 100644
--- a/include/linux/magic.h
+++ b/include/linux/magic.h
@@ -3,6 +3,7 @@
 
 #define ADFS_SUPER_MAGIC	0xadf5
 #define AFFS_SUPER_MAGIC	0xadff
+#define AFS_SUPER_MAGIC                0x5346414F
 #define AUTOFS_SUPER_MAGIC	0x0187
 #define CODA_SUPER_MAGIC	0x73757245
 #define EFS_SUPER_MAGIC		0x414A53
diff --git a/include/linux/swap.h b/include/linux/swap.h
index add51ce..5423559 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -245,7 +245,7 @@
 extern int valid_swaphandles(swp_entry_t, unsigned long *);
 extern void swap_free(swp_entry_t);
 extern void free_swap_and_cache(swp_entry_t);
-extern int swap_type_of(dev_t, sector_t);
+extern int swap_type_of(dev_t, sector_t, struct block_device **);
 extern unsigned int count_swap_pages(int, int);
 extern sector_t map_swap_page(struct swap_info_struct *, pgoff_t);
 extern sector_t swapdev_block(int, pgoff_t);
diff --git a/include/net/ieee80211.h b/include/net/ieee80211.h
index e6af381..e02d85f 100644
--- a/include/net/ieee80211.h
+++ b/include/net/ieee80211.h
@@ -218,7 +218,7 @@
 #define WLAN_FC_GET_STYPE(fc) ((fc) & IEEE80211_FCTL_STYPE)
 
 #define WLAN_GET_SEQ_FRAG(seq) ((seq) & IEEE80211_SCTL_FRAG)
-#define WLAN_GET_SEQ_SEQ(seq)  ((seq) & IEEE80211_SCTL_SEQ)
+#define WLAN_GET_SEQ_SEQ(seq)  (((seq) & IEEE80211_SCTL_SEQ) >> 4)
 
 /* Authentication algorithms */
 #define WLAN_AUTH_OPEN 0
diff --git a/include/sound/version.h b/include/sound/version.h
index 2949b9b..20f7bab 100644
--- a/include/sound/version.h
+++ b/include/sound/version.h
@@ -1,3 +1,3 @@
 /* include/version.h.  Generated by alsa/ksync script.  */
 #define CONFIG_SND_VERSION "1.0.14rc1"
-#define CONFIG_SND_DATE " (Wed Dec 20 08:11:48 2006 UTC)"
+#define CONFIG_SND_DATE " (Tue Jan 09 09:56:17 2007 UTC)"
diff --git a/init/main.c b/init/main.c
index 2b1cdaa..bc27d72 100644
--- a/init/main.c
+++ b/init/main.c
@@ -538,6 +538,11 @@
 	parse_args("Booting kernel", command_line, __start___param,
 		   __stop___param - __start___param,
 		   &unknown_bootoption);
+	if (!irqs_disabled()) {
+		printk(KERN_WARNING "start_kernel(): bug: interrupts were "
+				"enabled *very* early, fixing it\n");
+		local_irq_disable();
+	}
 	sort_main_extable();
 	trap_init();
 	rcu_init();
diff --git a/kernel/module.c b/kernel/module.c
index dbce132..d0f2260 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -1148,10 +1148,10 @@
 	kobject_uevent(&mod->mkobj.kobj, KOBJ_ADD);
 	return 0;
 
-out_unreg_drivers:
-	kobject_unregister(mod->drivers_dir);
 out_unreg_param:
 	module_param_sysfs_remove(mod);
+out_unreg_drivers:
+	kobject_unregister(mod->drivers_dir);
 out_unreg:
 	kobject_del(&mod->mkobj.kobj);
 	kobject_put(&mod->mkobj.kobj);
@@ -2327,8 +2327,22 @@
 	printk("\n");
 }
 
+static char *make_driver_name(struct device_driver *drv)
+{
+	char *driver_name;
+
+	driver_name = kmalloc(strlen(drv->name) + strlen(drv->bus->name) + 2,
+			      GFP_KERNEL);
+	if (!driver_name)
+		return NULL;
+
+	sprintf(driver_name, "%s:%s", drv->bus->name, drv->name);
+	return driver_name;
+}
+
 void module_add_driver(struct module *mod, struct device_driver *drv)
 {
+	char *driver_name;
 	int no_warn;
 
 	if (!mod || !drv)
@@ -2336,17 +2350,31 @@
 
 	/* Don't check return codes; these calls are idempotent */
 	no_warn = sysfs_create_link(&drv->kobj, &mod->mkobj.kobj, "module");
-	no_warn = sysfs_create_link(mod->drivers_dir, &drv->kobj, drv->name);
+	driver_name = make_driver_name(drv);
+	if (driver_name) {
+		no_warn = sysfs_create_link(mod->drivers_dir, &drv->kobj,
+					    driver_name);
+		kfree(driver_name);
+	}
 }
 EXPORT_SYMBOL(module_add_driver);
 
 void module_remove_driver(struct device_driver *drv)
 {
+	char *driver_name;
+
 	if (!drv)
 		return;
+
 	sysfs_remove_link(&drv->kobj, "module");
-	if (drv->owner && drv->owner->drivers_dir)
-		sysfs_remove_link(drv->owner->drivers_dir, drv->name);
+	if (drv->owner && drv->owner->drivers_dir) {
+		driver_name = make_driver_name(drv);
+		if (driver_name) {
+			sysfs_remove_link(drv->owner->drivers_dir,
+					  driver_name);
+			kfree(driver_name);
+		}
+	}
 }
 EXPORT_SYMBOL(module_remove_driver);
 
diff --git a/kernel/params.c b/kernel/params.c
index f406655..718945d 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -143,9 +143,15 @@
 
 	while (*args) {
 		int ret;
+		int irq_was_disabled;
 
 		args = next_arg(args, &param, &val);
+		irq_was_disabled = irqs_disabled();
 		ret = parse_one(param, val, params, num, unknown);
+		if (irq_was_disabled && !irqs_disabled()) {
+			printk(KERN_WARNING "parse_args(): option '%s' enabled "
+					"irq's!\n", param);
+		}
 		switch (ret) {
 		case -ENOENT:
 			printk(KERN_ERR "%s: Unknown parameter `%s'\n",
diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index f133d4a..3581f8f 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -165,14 +165,15 @@
 {
 	int res;
 
-	res = swap_type_of(swsusp_resume_device, swsusp_resume_block);
+	res = swap_type_of(swsusp_resume_device, swsusp_resume_block,
+			&resume_bdev);
 	if (res < 0)
 		return res;
 
 	root_swap = res;
-	resume_bdev = open_by_devnum(swsusp_resume_device, FMODE_WRITE);
-	if (IS_ERR(resume_bdev))
-		return PTR_ERR(resume_bdev);
+	res = blkdev_get(resume_bdev, FMODE_WRITE, O_RDWR);
+	if (res)
+		return res;
 
 	res = set_blocksize(resume_bdev, PAGE_SIZE);
 	if (res < 0)
diff --git a/kernel/power/user.c b/kernel/power/user.c
index 89443b8..f7b7a78 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -57,7 +57,7 @@
 	memset(&data->handle, 0, sizeof(struct snapshot_handle));
 	if ((filp->f_flags & O_ACCMODE) == O_RDONLY) {
 		data->swap = swsusp_resume_device ?
-				swap_type_of(swsusp_resume_device, 0) : -1;
+			swap_type_of(swsusp_resume_device, 0, NULL) : -1;
 		data->mode = O_RDONLY;
 	} else {
 		data->swap = -1;
@@ -268,7 +268,8 @@
 			 * so we need to recode them
 			 */
 			if (old_decode_dev(arg)) {
-				data->swap = swap_type_of(old_decode_dev(arg), 0);
+				data->swap = swap_type_of(old_decode_dev(arg),
+							0, NULL);
 				if (data->swap < 0)
 					error = -ENODEV;
 			} else {
@@ -365,7 +366,7 @@
 			swdev = old_decode_dev(swap_area.dev);
 			if (swdev) {
 				offset = swap_area.offset;
-				data->swap = swap_type_of(swdev, offset);
+				data->swap = swap_type_of(swdev, offset, NULL);
 				if (data->swap < 0)
 					error = -ENODEV;
 			} else {
diff --git a/kernel/profile.c b/kernel/profile.c
index fb5e03d..11550b2 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -63,7 +63,7 @@
 		printk(KERN_INFO
 			"kernel sleep profiling enabled (shift: %ld)\n",
 			prof_shift);
-	} else if (!strncmp(str, sleepstr, strlen(sleepstr))) {
+	} else if (!strncmp(str, schedstr, strlen(schedstr))) {
 		prof_on = SCHED_PROFILING;
 		if (str[strlen(schedstr)] == ',')
 			str += strlen(schedstr) + 1;
diff --git a/mm/memory.c b/mm/memory.c
index 563792f..af227d2 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1091,7 +1091,7 @@
 			if (pages) {
 				pages[i] = page;
 
-				flush_anon_page(page, start);
+				flush_anon_page(vma, page, start);
 				flush_dcache_page(page);
 			}
 			if (vmas)
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 6969cfb..b278b8d 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -61,12 +61,6 @@
 	}
 
 	/*
-	 * swapoff can easily use up all memory, so kill those first.
-	 */
-	if (p->flags & PF_SWAPOFF)
-		return ULONG_MAX;
-
-	/*
 	 * The memory size of the process is the basis for the badness.
 	 */
 	points = mm->total_vm;
@@ -77,6 +71,12 @@
 	task_unlock(p);
 
 	/*
+	 * swapoff can easily use up all memory, so kill those first.
+	 */
+	if (p->flags & PF_SWAPOFF)
+		return ULONG_MAX;
+
+	/*
 	 * Processes which fork a lot of child processes are likely
 	 * a good choice. We add half the vmsize of the children if they
 	 * have an own mm. This prevents forking servers to flood the
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 8c1a116..a49f96b 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -711,6 +711,9 @@
 	for_each_zone(zone) {
 		struct per_cpu_pageset *pset;
 
+		if (!populated_zone(zone))
+			continue;
+
 		pset = zone_pcp(zone, cpu);
 		for (i = 0; i < ARRAY_SIZE(pset->pcp); i++) {
 			struct per_cpu_pages *pcp;
@@ -3321,6 +3324,10 @@
 			numentries >>= (scale - PAGE_SHIFT);
 		else
 			numentries <<= (PAGE_SHIFT - scale);
+
+		/* Make sure we've got at least a 0-order allocation.. */
+		if (unlikely((numentries * bucketsize) < PAGE_SIZE))
+			numentries = PAGE_SIZE / bucketsize;
 	}
 	numentries = roundup_pow_of_two(numentries);
 
diff --git a/mm/slab.c b/mm/slab.c
index 0d4e574..c610062 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -3281,7 +3281,7 @@
 					flags | GFP_THISNODE, nid);
 	}
 
-	if (!obj) {
+	if (!obj && !(flags & __GFP_NO_GROW)) {
 		/*
 		 * This allocation will be performed within the constraints
 		 * of the current cpuset / memory policy requirements.
@@ -3310,7 +3310,7 @@
 					 */
 					goto retry;
 			} else {
-				kmem_freepages(cache, obj);
+				/* cache_grow already freed obj */
 				obj = NULL;
 			}
 		}
diff --git a/mm/swapfile.c b/mm/swapfile.c
index b9fc0e5d..a2d9bb4 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -434,7 +434,7 @@
  *
  * This is needed for the suspend to disk (aka swsusp).
  */
-int swap_type_of(dev_t device, sector_t offset)
+int swap_type_of(dev_t device, sector_t offset, struct block_device **bdev_p)
 {
 	struct block_device *bdev = NULL;
 	int i;
@@ -450,6 +450,9 @@
 			continue;
 
 		if (!bdev) {
+			if (bdev_p)
+				*bdev_p = sis->bdev;
+
 			spin_unlock(&swap_lock);
 			return i;
 		}
@@ -459,6 +462,9 @@
 			se = list_entry(sis->extent_list.next,
 					struct swap_extent, list);
 			if (se->start_block == offset) {
+				if (bdev_p)
+					*bdev_p = sis->bdev;
+
 				spin_unlock(&swap_lock);
 				bdput(bdev);
 				return i;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 40fea49..7430df6 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1406,6 +1406,16 @@
 	return ret;
 }
 
+static unsigned long count_lru_pages(void)
+{
+	struct zone *zone;
+	unsigned long ret = 0;
+
+	for_each_zone(zone)
+		ret += zone->nr_active + zone->nr_inactive;
+	return ret;
+}
+
 /*
  * Try to free `nr_pages' of memory, system-wide, and return the number of
  * freed pages.
@@ -1420,7 +1430,6 @@
 	unsigned long ret = 0;
 	int pass;
 	struct reclaim_state reclaim_state;
-	struct zone *zone;
 	struct scan_control sc = {
 		.gfp_mask = GFP_KERNEL,
 		.may_swap = 0,
@@ -1431,10 +1440,7 @@
 
 	current->reclaim_state = &reclaim_state;
 
-	lru_pages = 0;
-	for_each_zone(zone)
-		lru_pages += zone->nr_active + zone->nr_inactive;
-
+	lru_pages = count_lru_pages();
 	nr_slab = global_page_state(NR_SLAB_RECLAIMABLE);
 	/* If slab caches are huge, it's better to hit them first */
 	while (nr_slab >= lru_pages) {
@@ -1461,13 +1467,6 @@
 	for (pass = 0; pass < 5; pass++) {
 		int prio;
 
-		/* Needed for shrinking slab caches later on */
-		if (!lru_pages)
-			for_each_zone(zone) {
-				lru_pages += zone->nr_active;
-				lru_pages += zone->nr_inactive;
-			}
-
 		/* Force reclaiming mapped pages in the passes #3 and #4 */
 		if (pass > 2) {
 			sc.may_swap = 1;
@@ -1483,7 +1482,8 @@
 				goto out;
 
 			reclaim_state.reclaimed_slab = 0;
-			shrink_slab(sc.nr_scanned, sc.gfp_mask, lru_pages);
+			shrink_slab(sc.nr_scanned, sc.gfp_mask,
+					count_lru_pages());
 			ret += reclaim_state.reclaimed_slab;
 			if (ret >= nr_pages)
 				goto out;
@@ -1491,20 +1491,19 @@
 			if (sc.nr_scanned && prio < DEF_PRIORITY - 2)
 				congestion_wait(WRITE, HZ / 10);
 		}
-
-		lru_pages = 0;
 	}
 
 	/*
 	 * If ret = 0, we could not shrink LRUs, but there may be something
 	 * in slab caches
 	 */
-	if (!ret)
+	if (!ret) {
 		do {
 			reclaim_state.reclaimed_slab = 0;
-			shrink_slab(nr_pages, sc.gfp_mask, lru_pages);
+			shrink_slab(nr_pages, sc.gfp_mask, count_lru_pages());
 			ret += reclaim_state.reclaimed_slab;
 		} while (ret < nr_pages && reclaim_state.reclaimed_slab > 0);
+	}
 
 out:
 	current->reclaim_state = NULL;
diff --git a/net/bluetooth/cmtp/capi.c b/net/bluetooth/cmtp/capi.c
index be04e9f..ab166b4 100644
--- a/net/bluetooth/cmtp/capi.c
+++ b/net/bluetooth/cmtp/capi.c
@@ -196,6 +196,9 @@
 
 	switch (CAPIMSG_SUBCOMMAND(skb->data)) {
 	case CAPI_CONF:
+		if (skb->len < CAPI_MSG_BASELEN + 10)
+			break;
+
 		func = CAPIMSG_U16(skb->data, CAPI_MSG_BASELEN + 5);
 		info = CAPIMSG_U16(skb->data, CAPI_MSG_BASELEN + 8);
 
@@ -226,6 +229,9 @@
 			break;
 
 		case CAPI_FUNCTION_GET_PROFILE:
+			if (skb->len < CAPI_MSG_BASELEN + 11 + sizeof(capi_profile))
+				break;
+
 			controller = CAPIMSG_U16(skb->data, CAPI_MSG_BASELEN + 11);
 			msgnum = CAPIMSG_MSGID(skb->data);
 
@@ -246,17 +252,26 @@
 			break;
 
 		case CAPI_FUNCTION_GET_MANUFACTURER:
+			if (skb->len < CAPI_MSG_BASELEN + 15)
+				break;
+
 			controller = CAPIMSG_U32(skb->data, CAPI_MSG_BASELEN + 10);
 
 			if (!info && ctrl) {
+				int len = min_t(uint, CAPI_MANUFACTURER_LEN,
+						skb->data[CAPI_MSG_BASELEN + 14]);
+
+				memset(ctrl->manu, 0, CAPI_MANUFACTURER_LEN);
 				strncpy(ctrl->manu,
-					skb->data + CAPI_MSG_BASELEN + 15,
-					skb->data[CAPI_MSG_BASELEN + 14]);
+					skb->data + CAPI_MSG_BASELEN + 15, len);
 			}
 
 			break;
 
 		case CAPI_FUNCTION_GET_VERSION:
+			if (skb->len < CAPI_MSG_BASELEN + 32)
+				break;
+
 			controller = CAPIMSG_U32(skb->data, CAPI_MSG_BASELEN + 12);
 
 			if (!info && ctrl) {
@@ -269,13 +284,18 @@
 			break;
 
 		case CAPI_FUNCTION_GET_SERIAL_NUMBER:
+			if (skb->len < CAPI_MSG_BASELEN + 17)
+				break;
+
 			controller = CAPIMSG_U32(skb->data, CAPI_MSG_BASELEN + 12);
 
 			if (!info && ctrl) {
+				int len = min_t(uint, CAPI_SERIAL_LEN,
+						skb->data[CAPI_MSG_BASELEN + 16]);
+
 				memset(ctrl->serial, 0, CAPI_SERIAL_LEN);
 				strncpy(ctrl->serial,
-					skb->data + CAPI_MSG_BASELEN + 17,
-					skb->data[CAPI_MSG_BASELEN + 16]);
+					skb->data + CAPI_MSG_BASELEN + 17, len);
 			}
 
 			break;
@@ -284,14 +304,18 @@
 		break;
 
 	case CAPI_IND:
+		if (skb->len < CAPI_MSG_BASELEN + 6)
+			break;
+
 		func = CAPIMSG_U16(skb->data, CAPI_MSG_BASELEN + 3);
 
 		if (func == CAPI_FUNCTION_LOOPBACK) {
+			int len = min_t(uint, skb->len - CAPI_MSG_BASELEN - 6,
+						skb->data[CAPI_MSG_BASELEN + 5]);
 			appl = CAPIMSG_APPID(skb->data);
 			msgnum = CAPIMSG_MSGID(skb->data);
 			cmtp_send_interopmsg(session, CAPI_RESP, appl, msgnum, func,
-						skb->data + CAPI_MSG_BASELEN + 6,
-						skb->data[CAPI_MSG_BASELEN + 5]);
+						skb->data + CAPI_MSG_BASELEN + 6, len);
 		}
 
 		break;
@@ -309,6 +333,9 @@
 
 	BT_DBG("session %p skb %p len %d", session, skb, skb->len);
 
+	if (skb->len < CAPI_MSG_BASELEN)
+		return;
+
 	if (CAPIMSG_COMMAND(skb->data) == CAPI_INTEROPERABILITY) {
 		cmtp_recv_interopmsg(session, skb);
 		return;
diff --git a/net/bluetooth/hci_sysfs.c b/net/bluetooth/hci_sysfs.c
index d4c9356..801d687 100644
--- a/net/bluetooth/hci_sysfs.c
+++ b/net/bluetooth/hci_sysfs.c
@@ -242,7 +242,7 @@
 	struct hci_conn *conn = container_of(work, struct hci_conn, work);
 	int i;
 
-	if (device_register(&conn->dev) < 0) {
+	if (device_add(&conn->dev) < 0) {
 		BT_ERR("Failed to register connection device");
 		return;
 	}
@@ -272,6 +272,8 @@
 
 	dev_set_drvdata(&conn->dev, conn);
 
+	device_initialize(&conn->dev);
+
 	INIT_WORK(&conn->work, add_conn);
 
 	schedule_work(&conn->work);
@@ -287,6 +289,9 @@
 {
 	BT_DBG("conn %p", conn);
 
+	if (!device_is_registered(&conn->dev))
+		return;
+
 	INIT_WORK(&conn->work, del_conn);
 
 	schedule_work(&conn->work);
diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c
index 544d65b..cb7e855 100644
--- a/net/bluetooth/rfcomm/sock.c
+++ b/net/bluetooth/rfcomm/sock.c
@@ -557,7 +557,6 @@
 	struct sock *sk = sock->sk;
 	struct rfcomm_dlc *d = rfcomm_pi(sk)->dlc;
 	struct sk_buff *skb;
-	int err;
 	int sent = 0;
 
 	if (msg->msg_flags & MSG_OOB)
@@ -572,6 +571,7 @@
 
 	while (len) {
 		size_t size = min_t(size_t, len, d->mtu);
+		int err;
 		
 		skb = sock_alloc_send_skb(sk, size + RFCOMM_SKB_RESERVE,
 				msg->msg_flags & MSG_DONTWAIT, &err);
@@ -582,13 +582,16 @@
 		err = memcpy_fromiovec(skb_put(skb, size), msg->msg_iov, size);
 		if (err) {
 			kfree_skb(skb);
-			sent = err;
+			if (sent == 0)
+				sent = err;
 			break;
 		}
 
 		err = rfcomm_dlc_send(d, skb);
 		if (err < 0) {
 			kfree_skb(skb);
+			if (sent == 0)
+				sent = err;
 			break;
 		}
 
@@ -598,7 +601,7 @@
 
 	release_sock(sk);
 
-	return sent ? sent : err;
+	return sent;
 }
 
 static long rfcomm_sock_data_wait(struct sock *sk, long timeo)
diff --git a/net/bluetooth/rfcomm/tty.c b/net/bluetooth/rfcomm/tty.c
index e0e0d09..eb2b524 100644
--- a/net/bluetooth/rfcomm/tty.c
+++ b/net/bluetooth/rfcomm/tty.c
@@ -697,9 +697,13 @@
 
 	BT_DBG("tty %p", tty);
 
+	if (!dev || !dev->dlc)
+		return 0;
+
 	room = rfcomm_room(dev->dlc) - atomic_read(&dev->wmem_alloc);
 	if (room < 0)
 		room = 0;
+
 	return room;
 }
 
@@ -915,12 +919,14 @@
 static int rfcomm_tty_chars_in_buffer(struct tty_struct *tty)
 {
 	struct rfcomm_dev *dev = (struct rfcomm_dev *) tty->driver_data;
-	struct rfcomm_dlc *dlc = dev->dlc;
 
 	BT_DBG("tty %p dev %p", tty, dev);
 
-	if (!skb_queue_empty(&dlc->tx_queue))
-		return dlc->mtu;
+	if (!dev || !dev->dlc)
+		return 0;
+
+	if (!skb_queue_empty(&dev->dlc->tx_queue))
+		return dev->dlc->mtu;
 
 	return 0;
 }
@@ -928,11 +934,12 @@
 static void rfcomm_tty_flush_buffer(struct tty_struct *tty)
 {
 	struct rfcomm_dev *dev = (struct rfcomm_dev *) tty->driver_data;
-	if (!dev)
-		return;
 
 	BT_DBG("tty %p dev %p", tty, dev);
 
+	if (!dev || !dev->dlc)
+		return;
+
 	skb_queue_purge(&dev->dlc->tx_queue);
 
 	if (test_bit(TTY_DO_WRITE_WAKEUP, &tty->flags) && tty->ldisc.write_wakeup)
@@ -952,11 +959,12 @@
 static void rfcomm_tty_hangup(struct tty_struct *tty)
 {
 	struct rfcomm_dev *dev = (struct rfcomm_dev *) tty->driver_data;
-	if (!dev)
-		return;
 
 	BT_DBG("tty %p dev %p", tty, dev);
 
+	if (!dev)
+		return;
+
 	rfcomm_tty_flush_buffer(tty);
 
 	if (test_bit(RFCOMM_RELEASE_ONHUP, &dev->flags))
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 1144900..d60fd73 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -305,7 +305,7 @@
 		sk->sk_reuse = 1;
 
 	inet = inet_sk(sk);
-	inet->is_icsk = INET_PROTOSW_ICSK & answer_flags;
+	inet->is_icsk = (INET_PROTOSW_ICSK & answer_flags) == INET_PROTOSW_ICSK;
 
 	if (SOCK_RAW == sock->type) {
 		inet->num = protocol;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index bf7a224..12de90a 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -648,7 +648,7 @@
 				   TCPOLEN_TIMESTAMP);
 		rep.opt[1] = htonl(tcp_time_stamp);
 		rep.opt[2] = htonl(ts);
-		arg.iov[0].iov_len = TCPOLEN_TSTAMP_ALIGNED;
+		arg.iov[0].iov_len += TCPOLEN_TSTAMP_ALIGNED;
 	}
 
 	/* Swap the send and the receive. */
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index e5cd83b..832a5e6 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -171,7 +171,7 @@
 		sk->sk_reuse = 1;
 
 	inet = inet_sk(sk);
-	inet->is_icsk = INET_PROTOSW_ICSK & answer_flags;
+	inet->is_icsk = (INET_PROTOSW_ICSK & answer_flags) == INET_PROTOSW_ICSK;
 
 	if (SOCK_RAW == sock->type) {
 		inet->num = protocol;
diff --git a/net/netfilter/nf_conntrack_netbios_ns.c b/net/netfilter/nf_conntrack_netbios_ns.c
index a5b234e..2a48efd 100644
--- a/net/netfilter/nf_conntrack_netbios_ns.c
+++ b/net/netfilter/nf_conntrack_netbios_ns.c
@@ -89,6 +89,7 @@
 
 	exp->expectfn             = NULL;
 	exp->flags                = NF_CT_EXPECT_PERMANENT;
+	exp->helper               = NULL;
 
 	nf_conntrack_expect_related(exp);
 	nf_conntrack_expect_put(exp);
diff --git a/net/netlabel/netlabel_cipso_v4.c b/net/netlabel/netlabel_cipso_v4.c
index 4afc75f..73e0ff4 100644
--- a/net/netlabel/netlabel_cipso_v4.c
+++ b/net/netlabel/netlabel_cipso_v4.c
@@ -130,12 +130,12 @@
 
 	nla_for_each_nested(nla, info->attrs[NLBL_CIPSOV4_A_TAGLST], nla_rem)
 		if (nla->nla_type == NLBL_CIPSOV4_A_TAG) {
-			if (iter > CIPSO_V4_TAG_MAXCNT)
+			if (iter >= CIPSO_V4_TAG_MAXCNT)
 				return -EINVAL;
 			doi_def->tags[iter++] = nla_get_u8(nla);
 		}
-	if (iter < CIPSO_V4_TAG_MAXCNT)
-		doi_def->tags[iter] = CIPSO_V4_TAG_INVALID;
+	while (iter < CIPSO_V4_TAG_MAXCNT)
+		doi_def->tags[iter++] = CIPSO_V4_TAG_INVALID;
 
 	return 0;
 }
diff --git a/net/x25/x25_facilities.c b/net/x25/x25_facilities.c
index 9f42b9c9..27f5cc7 100644
--- a/net/x25/x25_facilities.c
+++ b/net/x25/x25_facilities.c
@@ -254,7 +254,7 @@
 	 *	They want reverse charging, we won't accept it.
 	 */
 	if ((theirs.reverse & 0x01 ) && (ours->reverse & 0x01)) {
-		SOCK_DEBUG(sk, "X.25: rejecting reverse charging request");
+		SOCK_DEBUG(sk, "X.25: rejecting reverse charging request\n");
 		return -1;
 	}
 
@@ -262,29 +262,29 @@
 
 	if (theirs.throughput) {
 		if (theirs.throughput < ours->throughput) {
-			SOCK_DEBUG(sk, "X.25: throughput negotiated down");
+			SOCK_DEBUG(sk, "X.25: throughput negotiated down\n");
 			new->throughput = theirs.throughput;
 		}
 	}
 
 	if (theirs.pacsize_in && theirs.pacsize_out) {
 		if (theirs.pacsize_in < ours->pacsize_in) {
-			SOCK_DEBUG(sk, "X.25: packet size inwards negotiated down");
+			SOCK_DEBUG(sk, "X.25: packet size inwards negotiated down\n");
 			new->pacsize_in = theirs.pacsize_in;
 		}
 		if (theirs.pacsize_out < ours->pacsize_out) {
-			SOCK_DEBUG(sk, "X.25: packet size outwards negotiated down");
+			SOCK_DEBUG(sk, "X.25: packet size outwards negotiated down\n");
 			new->pacsize_out = theirs.pacsize_out;
 		}
 	}
 
 	if (theirs.winsize_in && theirs.winsize_out) {
 		if (theirs.winsize_in < ours->winsize_in) {
-			SOCK_DEBUG(sk, "X.25: window size inwards negotiated down");
+			SOCK_DEBUG(sk, "X.25: window size inwards negotiated down\n");
 			new->winsize_in = theirs.winsize_in;
 		}
 		if (theirs.winsize_out < ours->winsize_out) {
-			SOCK_DEBUG(sk, "X.25: window size outwards negotiated down");
+			SOCK_DEBUG(sk, "X.25: window size outwards negotiated down\n");
 			new->winsize_out = theirs.winsize_out;
 		}
 	}
diff --git a/scripts/kconfig/qconf.cc b/scripts/kconfig/qconf.cc
index 0b2fcc4..a8ffc32 100644
--- a/scripts/kconfig/qconf.cc
+++ b/scripts/kconfig/qconf.cc
@@ -925,6 +925,8 @@
 		configSettings->endGroup();
 		connect(configApp, SIGNAL(aboutToQuit()), SLOT(saveSettings()));
 	}
+
+	has_dbg_info = 0;
 }
 
 void ConfigInfoView::saveSettings(void)
@@ -953,10 +955,13 @@
 	if (menu == m)
 		return;
 	menu = m;
-	if (!menu)
+	if (!menu) {
+		has_dbg_info = 0;
 		clear();
-	else
+	} else {
+		has_dbg_info = 1;
 		menuInfo();
+       }
 }
 
 void ConfigInfoView::setSource(const QString& name)
@@ -991,6 +996,9 @@
 {
 	QString str;
 
+	if (!has_dbg_info)
+		return;
+
 	str += "<big>Symbol: <b>";
 	str += print_filter(sym->name);
 	str += "</b></big><br><br>value: ";
diff --git a/scripts/kconfig/qconf.h b/scripts/kconfig/qconf.h
index 6fc1c5f..a397edb 100644
--- a/scripts/kconfig/qconf.h
+++ b/scripts/kconfig/qconf.h
@@ -273,6 +273,8 @@
 	struct symbol *sym;
 	struct menu *menu;
 	bool _showDebug;
+
+	int has_dbg_info;
 };
 
 class ConfigSearchWindow : public QDialog {
diff --git a/security/selinux/ss/context.h b/security/selinux/ss/context.h
index 0562bac..2eee0da 100644
--- a/security/selinux/ss/context.h
+++ b/security/selinux/ss/context.h
@@ -55,6 +55,29 @@
 	return rc;
 }
 
+/*
+ * Sets both levels in the MLS range of 'dst' to the low level of 'src'.
+ */
+static inline int mls_context_cpy_low(struct context *dst, struct context *src)
+{
+	int rc;
+
+	if (!selinux_mls_enabled)
+		return 0;
+
+	dst->range.level[0].sens = src->range.level[0].sens;
+	rc = ebitmap_cpy(&dst->range.level[0].cat, &src->range.level[0].cat);
+	if (rc)
+		goto out;
+
+	dst->range.level[1].sens = src->range.level[0].sens;
+	rc = ebitmap_cpy(&dst->range.level[1].cat, &src->range.level[0].cat);
+	if (rc)
+		ebitmap_destroy(&dst->range.level[0].cat);
+out:
+	return rc;
+}
+
 static inline int mls_context_cmp(struct context *c1, struct context *c2)
 {
 	if (!selinux_mls_enabled)
diff --git a/security/selinux/ss/mls.c b/security/selinux/ss/mls.c
index b4f682d..4a8bab2 100644
--- a/security/selinux/ss/mls.c
+++ b/security/selinux/ss/mls.c
@@ -270,7 +270,7 @@
 		if (!defcon)
 			goto out;
 
-		rc = mls_copy_context(context, defcon);
+		rc = mls_context_cpy(context, defcon);
 		goto out;
 	}
 
@@ -401,26 +401,6 @@
 }
 
 /*
- * Copies the effective MLS range from `src' into `dst'.
- */
-static inline int mls_scopy_context(struct context *dst,
-                                    struct context *src)
-{
-	int l, rc = 0;
-
-	/* Copy the MLS range from the source context */
-	for (l = 0; l < 2; l++) {
-		dst->range.level[l].sens = src->range.level[0].sens;
-		rc = ebitmap_cpy(&dst->range.level[l].cat,
-				 &src->range.level[0].cat);
-		if (rc)
-			break;
-	}
-
-	return rc;
-}
-
-/*
  * Copies the MLS range `range' into `context'.
  */
 static inline int mls_range_set(struct context *context,
@@ -552,19 +532,19 @@
 	case AVTAB_CHANGE:
 		if (tclass == SECCLASS_PROCESS)
 			/* Use the process MLS attributes. */
-			return mls_copy_context(newcontext, scontext);
+			return mls_context_cpy(newcontext, scontext);
 		else
 			/* Use the process effective MLS attributes. */
-			return mls_scopy_context(newcontext, scontext);
+			return mls_context_cpy_low(newcontext, scontext);
 	case AVTAB_MEMBER:
 		/* Only polyinstantiate the MLS attributes if
 		   the type is being polyinstantiated */
 		if (newcontext->type != tcontext->type) {
 			/* Use the process effective MLS attributes. */
-			return mls_scopy_context(newcontext, scontext);
+			return mls_context_cpy_low(newcontext, scontext);
 		} else {
 			/* Use the related object MLS attributes. */
-			return mls_copy_context(newcontext, tcontext);
+			return mls_context_cpy(newcontext, tcontext);
 		}
 	default:
 		return -EINVAL;
diff --git a/security/selinux/ss/mls.h b/security/selinux/ss/mls.h
index 661d6fc..096d1b4 100644
--- a/security/selinux/ss/mls.h
+++ b/security/selinux/ss/mls.h
@@ -24,26 +24,6 @@
 #include "context.h"
 #include "policydb.h"
 
-/*
- * Copies the MLS range from `src' into `dst'.
- */
-static inline int mls_copy_context(struct context *dst,
-				   struct context *src)
-{
-	int l, rc = 0;
-
-	/* Copy the MLS range from the source context */
-	for (l = 0; l < 2; l++) {
-		dst->range.level[l].sens = src->range.level[l].sens;
-		rc = ebitmap_cpy(&dst->range.level[l].cat,
-				 &src->range.level[l].cat);
-		if (rc)
-			break;
-	}
-
-	return rc;
-}
-
 int mls_compute_context_len(struct context *context);
 void mls_sid_to_context(struct context *context, char **scontext);
 int mls_context_isvalid(struct policydb *p, struct context *c);
diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c
index ee05815..3eb1fa9 100644
--- a/security/selinux/ss/services.c
+++ b/security/selinux/ss/services.c
@@ -1916,11 +1916,10 @@
 	newcon.user = context1->user;
 	newcon.role = context1->role;
 	newcon.type = context1->type;
-	rc = mls_copy_context(&newcon, context2);
+	rc = mls_context_cpy(&newcon, context2);
 	if (rc)
 		goto out_unlock;
 
-
 	/* Check the validity of the new context. */
 	if (!policydb_context_isvalid(&policydb, &newcon)) {
 		rc = convert_context_handle_invalid_context(&newcon);
@@ -2492,9 +2491,9 @@
 
 	rc = netlbl_socket_setattr(sock, &secattr);
 	if (rc == 0) {
-		spin_lock(&sksec->nlbl_lock);
+		spin_lock_bh(&sksec->nlbl_lock);
 		sksec->nlbl_state = NLBL_LABELED;
-		spin_unlock(&sksec->nlbl_lock);
+		spin_unlock_bh(&sksec->nlbl_lock);
 	}
 
 netlbl_socket_setsid_return:
diff --git a/sound/pci/cmipci.c b/sound/pci/cmipci.c
index 71c58df..70face7 100644
--- a/sound/pci/cmipci.c
+++ b/sound/pci/cmipci.c
@@ -2198,7 +2198,8 @@
 		val = inb(cm->iobase + args->reg);
 	else
 		val = snd_cmipci_read(cm, args->reg);
-	change = (val & args->mask) != (ucontrol->value.integer.value[0] ? args->mask : 0);
+	change = (val & args->mask) != (ucontrol->value.integer.value[0] ? 
+			args->mask_on : (args->mask & ~args->mask_on));
 	if (change) {
 		val &= ~args->mask;
 		if (ucontrol->value.integer.value[0])
diff --git a/sound/pci/echoaudio/midi.c b/sound/pci/echoaudio/midi.c
index e31f0f1..91f5bff 100644
--- a/sound/pci/echoaudio/midi.c
+++ b/sound/pci/echoaudio/midi.c
@@ -213,7 +213,7 @@
 	sent = bytes = 0;
 	spin_lock_irqsave(&chip->lock, flags);
 	chip->midi_full = 0;
-	if (chip->midi_out && !snd_rawmidi_transmit_empty(chip->midi_out)) {
+	if (!snd_rawmidi_transmit_empty(chip->midi_out)) {
 		bytes = snd_rawmidi_transmit_peek(chip->midi_out, buf,
 						  MIDI_OUT_BUFFER_SIZE - 1);
 		DE_MID(("Try to send %d bytes...\n", bytes));
@@ -264,9 +264,11 @@
 		}
 	} else {
 		if (chip->tinuse) {
-			del_timer(&chip->timer);
 			chip->tinuse = 0;
+			spin_unlock_irq(&chip->lock);
+			del_timer_sync(&chip->timer);
 			DE_MID(("Timer removed\n"));
+			return;
 		}
 	}
 	spin_unlock_irq(&chip->lock);
diff --git a/sound/pci/hda/hda_generic.c b/sound/pci/hda/hda_generic.c
index 97e9af1..1589d2f 100644
--- a/sound/pci/hda/hda_generic.c
+++ b/sound/pci/hda/hda_generic.c
@@ -485,8 +485,9 @@
 			return "Front Aux";
 		return "Aux";
 	case AC_JACK_MIC_IN:
-		if (node->pin_caps &
-		    (AC_PINCAP_VREF_80 << AC_PINCAP_VREF_SHIFT))
+		if (pinctl &&
+		    (node->pin_caps &
+		     (AC_PINCAP_VREF_80 << AC_PINCAP_VREF_SHIFT)))
 			*pinctl |= AC_PINCTL_VREF_80;
 		if ((location & 0x0f) == AC_JACK_LOC_FRONT)
 			return "Front Mic";
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index 9fd34f8..1a7e821 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -83,6 +83,7 @@
 			 "{Intel, ICH7},"
 			 "{Intel, ESB2},"
 			 "{Intel, ICH8},"
+			 "{Intel, ICH9},"
 			 "{ATI, SB450},"
 			 "{ATI, SB600},"
 			 "{ATI, RS600},"
@@ -1711,6 +1712,8 @@
 	{ 0x8086, 0x27d8, PCI_ANY_ID, PCI_ANY_ID, 0, 0, AZX_DRIVER_ICH }, /* ICH7 */
 	{ 0x8086, 0x269a, PCI_ANY_ID, PCI_ANY_ID, 0, 0, AZX_DRIVER_ICH }, /* ESB2 */
 	{ 0x8086, 0x284b, PCI_ANY_ID, PCI_ANY_ID, 0, 0, AZX_DRIVER_ICH }, /* ICH8 */
+	{ 0x8086, 0x293e, PCI_ANY_ID, PCI_ANY_ID, 0, 0, AZX_DRIVER_ICH }, /* ICH9 */
+	{ 0x8086, 0x293f, PCI_ANY_ID, PCI_ANY_ID, 0, 0, AZX_DRIVER_ICH }, /* ICH9 */
 	{ 0x1002, 0x437b, PCI_ANY_ID, PCI_ANY_ID, 0, 0, AZX_DRIVER_ATI }, /* ATI SB450 */
 	{ 0x1002, 0x4383, PCI_ANY_ID, PCI_ANY_ID, 0, 0, AZX_DRIVER_ATI }, /* ATI SB600 */
 	{ 0x1002, 0x793b, PCI_ANY_ID, PCI_ANY_ID, 0, 0, AZX_DRIVER_ATIHDMI }, /* ATI RS600 HDMI */
@@ -1718,9 +1721,14 @@
 	{ 0x1106, 0x3288, PCI_ANY_ID, PCI_ANY_ID, 0, 0, AZX_DRIVER_VIA }, /* VIA VT8251/VT8237A */
 	{ 0x1039, 0x7502, PCI_ANY_ID, PCI_ANY_ID, 0, 0, AZX_DRIVER_SIS }, /* SIS966 */
 	{ 0x10b9, 0x5461, PCI_ANY_ID, PCI_ANY_ID, 0, 0, AZX_DRIVER_ULI }, /* ULI M5461 */
-	{ 0x10de, 0x026c, PCI_ANY_ID, PCI_ANY_ID, 0, 0, AZX_DRIVER_NVIDIA }, /* NVIDIA 026c */
-	{ 0x10de, 0x0371, PCI_ANY_ID, PCI_ANY_ID, 0, 0, AZX_DRIVER_NVIDIA }, /* NVIDIA 0371 */
-	{ 0x10de, 0x03f0, PCI_ANY_ID, PCI_ANY_ID, 0, 0, AZX_DRIVER_NVIDIA }, /* NVIDIA 03f0 */
+	{ 0x10de, 0x026c, PCI_ANY_ID, PCI_ANY_ID, 0, 0, AZX_DRIVER_NVIDIA }, /* NVIDIA MCP51 */
+	{ 0x10de, 0x0371, PCI_ANY_ID, PCI_ANY_ID, 0, 0, AZX_DRIVER_NVIDIA }, /* NVIDIA MCP55 */
+	{ 0x10de, 0x03e4, PCI_ANY_ID, PCI_ANY_ID, 0, 0, AZX_DRIVER_NVIDIA }, /* NVIDIA MCP61 */
+	{ 0x10de, 0x03f0, PCI_ANY_ID, PCI_ANY_ID, 0, 0, AZX_DRIVER_NVIDIA }, /* NVIDIA MCP61 */
+	{ 0x10de, 0x044a, PCI_ANY_ID, PCI_ANY_ID, 0, 0, AZX_DRIVER_NVIDIA }, /* NVIDIA MCP65 */
+	{ 0x10de, 0x044b, PCI_ANY_ID, PCI_ANY_ID, 0, 0, AZX_DRIVER_NVIDIA }, /* NVIDIA MCP65 */
+	{ 0x10de, 0x055c, PCI_ANY_ID, PCI_ANY_ID, 0, 0, AZX_DRIVER_NVIDIA }, /* NVIDIA MCP67 */
+	{ 0x10de, 0x055d, PCI_ANY_ID, PCI_ANY_ID, 0, 0, AZX_DRIVER_NVIDIA }, /* NVIDIA MCP67 */
 	{ 0, }
 };
 MODULE_DEVICE_TABLE(pci, azx_ids);
diff --git a/sound/usb/usbaudio.c b/sound/usb/usbaudio.c
index 3d7f36f..19bdcc7 100644
--- a/sound/usb/usbaudio.c
+++ b/sound/usb/usbaudio.c
@@ -2471,7 +2471,13 @@
 		fp->nr_rates = nr_rates;
 		fp->rate_min = fp->rate_max = combine_triple(&fmt[8]);
 		for (r = 0, idx = offset + 1; r < nr_rates; r++, idx += 3) {
-			unsigned int rate = fp->rate_table[r] = combine_triple(&fmt[idx]);
+			unsigned int rate = combine_triple(&fmt[idx]);
+			/* C-Media CM6501 mislabels its 96 kHz altsetting */
+			if (rate == 48000 && nr_rates == 1 &&
+			    chip->usb_id == USB_ID(0x0d8c, 0x0201) &&
+			    fp->altsetting == 5 && fp->maxpacksize == 392)
+				rate = 96000;
+			fp->rate_table[r] = rate;
 			if (rate < fp->rate_min)
 				fp->rate_min = rate;
 			else if (rate > fp->rate_max)
@@ -3280,6 +3286,7 @@
 
 static int snd_usb_audio_free(struct snd_usb_audio *chip)
 {
+	usb_chip[chip->index] = NULL;
 	kfree(chip);
 	return 0;
 }
@@ -3541,7 +3548,6 @@
 		list_for_each(p, &chip->mixer_list) {
 			snd_usb_mixer_disconnect(p);
 		}
-		usb_chip[chip->index] = NULL;
 		mutex_unlock(&register_mutex);
 		snd_card_free_when_closed(card);
 	} else {
diff --git a/sound/usb/usbmixer.c b/sound/usb/usbmixer.c
index e74eb1b..7b3bf35 100644
--- a/sound/usb/usbmixer.c
+++ b/sound/usb/usbmixer.c
@@ -1526,7 +1526,7 @@
 		namelist[i] = kmalloc(MAX_ITEM_NAME_LEN, GFP_KERNEL);
 		if (! namelist[i]) {
 			snd_printk(KERN_ERR "cannot malloc\n");
-			while (--i > 0)
+			while (i--)
 				kfree(namelist[i]);
 			kfree(namelist);
 			kfree(cval);