Linux 3.6-rc3

Pull drm fixes from Dave Airlie:
 "Intel: edid fixes, power consumption fix, s/r fix, haswell fix

  Radeon: BIOS loading fixes for UEFI and Thunderbolt machines, better
  MSAA validation, lockup timeout fixes, modesetting fixes

  One udl dpms fix, one vmwgfx fix, a couple of trivial core changes.

  There is an export added to ACPI as part of the radeon bios fixes.

  I've also included the fbcon flashing cursor vs deinit race fix, that
  seems the simplest place to start"

Trivial conflict in drivers/video/console/fbcon.c due to me having
already applied the fbcon flashing cursor vs deinit race fix, and Dave
had added a comment in there too.

* 'drm-fixes' of git://people.freedesktop.org/~airlied/linux: (22 commits)
  fbcon: fix race condition between console lock and cursor timer (v1.1)
  drm: Add missing static storage class specifiers in drm_proc.c file
  drm/udl: dpms off the crtc when disabled.
  drm: Remove two unused fields from struct drm_display_mode
  drm: stop vmgfx driver explosion
  drm/radeon/ss: use num_crtc rather than hardcoded 6
  Revert "drm/radeon: fix bo creation retry path"
  drm/i915: use hsw rps tuning values everywhere on gen6+
  drm/radeon: split ATRM support out from the ATPX handler (v3)
  drm/radeon: convert radeon vfct code to use acpi_get_table_with_size
  ACPI: export symbol acpi_get_table_with_size
  drm/radeon: implement ACPI VFCT vbios fetch (v3)
  drm/radeon/kms: extend the Fujitsu D3003-S2 board connector quirk to cover later silicon stepping
  drm/radeon: fix checking of MSAA renderbuffers on r600-r700
  drm/radeon: allow CMASK and FMASK in the CS checker on r600-r700
  drm/radeon: init lockup timeout on ring init
  drm/radeon: avoid turning off spread spectrum for used pll
  drm/i915: fall back to bit-banging if GMBUS fails in CRT EDID reads
  drm/i915: extract connector update from intel_ddc_get_modes() for reuse
  drm/i915: fix hsw uncached pte
  ...

Documentation/ABI/testing/sysfs-platform-ideapad-laptop

@@ -5,4 +5,15 @@ Contact:	"Ike Panhc <ike.pan@canonical.com>"
 Description:
 		Control the power of camera module. 1 means on, 0 means off.
 
+What:		/sys/devices/platform/ideapad/fan_mode
+Date:		June 2012
+KernelVersion:	3.6
+Contact:	"Maxim Mikityanskiy <maxtram95@gmail.com>"
+Description:
+		Change fan mode
+		There are four available modes:
+			* 0 -> Super Silent Mode
+			* 1 -> Standard Mode
+			* 2 -> Dust Cleaning
+			* 4 -> Efficient Thermal Dissipation Mode
 

Documentation/DocBook/media/v4l/vidioc-g-tuner.xml

@@ -125,7 +125,7 @@ the structure refers to a radio tuner the
 <constant>V4L2_TUNER_CAP_NORM</constant> flags can't be used.</para>
 <para>If multiple frequency bands are supported, then
 <structfield>capability</structfield> is the union of all
-<structfield>capability></structfield> fields of each &v4l2-frequency-band;.
+<structfield>capability</structfield> fields of each &v4l2-frequency-band;.
 </para></entry>
 	  </row>
 	  <row>

Documentation/devicetree/bindings/regulator/tps6586x.txt

@@ -9,9 +9,9 @@ Required properties:
 - regulators: list of regulators provided by this controller, must have
   property "regulator-compatible" to match their hardware counterparts:
   sm[0-2], ldo[0-9] and ldo_rtc
-- sm0-supply: The input supply for the SM0.
-- sm1-supply: The input supply for the SM1.
-- sm2-supply: The input supply for the SM2.
+- vin-sm0-supply: The input supply for the SM0.
+- vin-sm1-supply: The input supply for the SM1.
+- vin-sm2-supply: The input supply for the SM2.
 - vinldo01-supply: The input supply for the LDO1 and LDO2
 - vinldo23-supply: The input supply for the LDO2 and LDO3
 - vinldo4-supply: The input supply for the LDO4
@@ -30,9 +30,9 @@ Example:
 		#gpio-cells = <2>;
 		gpio-controller;
 
-		sm0-supply = <&some_reg>;
-		sm1-supply = <&some_reg>;
-		sm2-supply = <&some_reg>;
+		vin-sm0-supply = <&some_reg>;
+		vin-sm1-supply = <&some_reg>;
+		vin-sm2-supply = <&some_reg>;
 		vinldo01-supply = <...>;
 		vinldo23-supply = <...>;
 		vinldo4-supply = <...>;

Documentation/filesystems/vfat.txt

@@ -137,6 +137,17 @@ errors=panic|continue|remount-ro
 		 without doing anything or remount the partition in
 		 read-only mode (default behavior).
 
+discard       -- If set, issues discard/TRIM commands to the block
+		 device when blocks are freed. This is useful for SSD devices
+		 and sparse/thinly-provisoned LUNs.
+
+nfs           -- This option maintains an index (cache) of directory
+		 inodes by i_logstart which is used by the nfs-related code to
+		 improve look-ups.
+
+		 Enable this only if you want to export the FAT filesystem
+		 over NFS
+
 <bool>: 0,1,yes,no,true,false
 
 TODO

Documentation/networking/netconsole.txt

@@ -51,8 +51,23 @@ Built-in netconsole starts immediately after the TCP stack is
 initialized and attempts to bring up the supplied dev at the supplied
 address.
 
-The remote host can run either 'netcat -u -l -p <port>',
-'nc -l -u <port>' or syslogd.
+The remote host has several options to receive the kernel messages,
+for example:
+
+1) syslogd
+
+2) netcat
+
+   On distributions using a BSD-based netcat version (e.g. Fedora,
+   openSUSE and Ubuntu) the listening port must be specified without
+   the -p switch:
+
+   'nc -u -l -p <port>' / 'nc -u -l <port>' or
+   'netcat -u -l -p <port>' / 'netcat -u -l <port>'
+
+3) socat
+
+   'socat udp-recv:<port> -'
 
 Dynamic reconfiguration:
 ========================

Documentation/pinctrl.txt

@@ -840,9 +840,9 @@ static unsigned long i2c_pin_configs[] = {
 
 static struct pinctrl_map __initdata mapping[] = {
 	PIN_MAP_MUX_GROUP("foo-i2c.0", PINCTRL_STATE_DEFAULT, "pinctrl-foo", "i2c0", "i2c0"),
-	PIN_MAP_MUX_CONFIGS_GROUP("foo-i2c.0", PINCTRL_STATE_DEFAULT, "pinctrl-foo", "i2c0", i2c_grp_configs),
-	PIN_MAP_MUX_CONFIGS_PIN("foo-i2c.0", PINCTRL_STATE_DEFAULT, "pinctrl-foo", "i2c0scl", i2c_pin_configs),
-	PIN_MAP_MUX_CONFIGS_PIN("foo-i2c.0", PINCTRL_STATE_DEFAULT, "pinctrl-foo", "i2c0sda", i2c_pin_configs),
+	PIN_MAP_CONFIGS_GROUP("foo-i2c.0", PINCTRL_STATE_DEFAULT, "pinctrl-foo", "i2c0", i2c_grp_configs),
+	PIN_MAP_CONFIGS_PIN("foo-i2c.0", PINCTRL_STATE_DEFAULT, "pinctrl-foo", "i2c0scl", i2c_pin_configs),
+	PIN_MAP_CONFIGS_PIN("foo-i2c.0", PINCTRL_STATE_DEFAULT, "pinctrl-foo", "i2c0sda", i2c_pin_configs),
 };
 
 Finally, some devices expect the mapping table to contain certain specific

Documentation/vm/hugetlbpage.txt

@@ -299,11 +299,17 @@ map_hugetlb.c.
 *******************************************************************
 
 /*
- * hugepage-shm:  see Documentation/vm/hugepage-shm.c
+ * map_hugetlb: see tools/testing/selftests/vm/map_hugetlb.c
  */
 
 *******************************************************************
 
 /*
- * hugepage-mmap:  see Documentation/vm/hugepage-mmap.c
+ * hugepage-shm:  see tools/testing/selftests/vm/hugepage-shm.c
+ */
+
+*******************************************************************
+
+/*
+ * hugepage-mmap:  see tools/testing/selftests/vm/hugepage-mmap.c
  */

Documentation/w1/slaves/w1_therm

@@ -3,6 +3,7 @@ Kernel driver w1_therm
 
 Supported chips:
   * Maxim ds18*20 based temperature sensors.
+  * Maxim ds1825 based temperature sensors.
 
 Author: Evgeniy Polyakov <johnpol@2ka.mipt.ru>
 
@@ -15,6 +16,7 @@ supported family codes:
 W1_THERM_DS18S20	0x10
 W1_THERM_DS1822		0x22
 W1_THERM_DS18B20	0x28
+W1_THERM_DS1825		0x3B
 
 Support is provided through the sysfs w1_slave file.  Each open and
 read sequence will initiate a temperature conversion then provide two

MAINTAINERS

@@ -2217,7 +2217,7 @@ S:	Maintained
 F:	drivers/scsi/tmscsim.*
 
 DC395x SCSI driver
-M:	Oliver Neukum <oliver@neukum.name>
+M:	Oliver Neukum <oliver@neukum.org>
 M:	Ali Akcaagac <aliakc@web.de>
 M:	Jamie Lenehan <lenehan@twibble.org>
 W:	http://twibble.org/dist/dc395x/
@@ -4537,7 +4537,7 @@ S:	Supported
 F:	arch/microblaze/
 
 MICROTEK X6 SCANNER
-M:	Oliver Neukum <oliver@neukum.name>
+M:	Oliver Neukum <oliver@neukum.org>
 S:	Maintained
 F:	drivers/usb/image/microtek.*
 
@@ -7076,7 +7076,7 @@ F:	include/linux/mtd/ubi.h
 F:	include/mtd/ubi-user.h
 
 USB ACM DRIVER
-M:	Oliver Neukum <oliver@neukum.name>
+M:	Oliver Neukum <oliver@neukum.org>
 L:	linux-usb@vger.kernel.org
 S:	Maintained
 F:	Documentation/usb/acm.txt
@@ -7097,7 +7097,7 @@ S:	Supported
 F:	drivers/block/ub.c
 
 USB CDC ETHERNET DRIVER
-M:	Oliver Neukum <oliver@neukum.name>
+M:	Oliver Neukum <oliver@neukum.org>
 L:	linux-usb@vger.kernel.org
 S:	Maintained
 F:	drivers/net/usb/cdc_*.c
@@ -7170,7 +7170,7 @@ F:	drivers/usb/host/isp116x*
 F:	include/linux/usb/isp116x.h
 
 USB KAWASAKI LSI DRIVER
-M:	Oliver Neukum <oliver@neukum.name>
+M:	Oliver Neukum <oliver@neukum.org>
 L:	linux-usb@vger.kernel.org
 S:	Maintained
 F:	drivers/usb/serial/kl5kusb105.*
@@ -7288,6 +7288,12 @@ W:	http://www.connecttech.com
 S:	Supported
 F:	drivers/usb/serial/whiteheat*
 
+USB SMSC75XX ETHERNET DRIVER
+M:	Steve Glendinning <steve.glendinning@shawell.net>
+L:	netdev@vger.kernel.org
+S:	Maintained
+F:	drivers/net/usb/smsc75xx.*
+
 USB SMSC95XX ETHERNET DRIVER
 M:	Steve Glendinning <steve.glendinning@shawell.net>
 L:	netdev@vger.kernel.org
@@ -7670,23 +7676,28 @@ S:	Supported
 F:	Documentation/hwmon/wm83??
 F:	arch/arm/mach-s3c64xx/mach-crag6410*
 F:	drivers/clk/clk-wm83*.c
+F:	drivers/extcon/extcon-arizona.c
 F:	drivers/leds/leds-wm83*.c
 F:	drivers/gpio/gpio-*wm*.c
+F:	drivers/gpio/gpio-arizona.c
 F:	drivers/hwmon/wm83??-hwmon.c
 F:	drivers/input/misc/wm831x-on.c
 F:	drivers/input/touchscreen/wm831x-ts.c
 F:	drivers/input/touchscreen/wm97*.c
-F:	drivers/mfd/wm8*.c
+F:	drivers/mfd/arizona*
+F:	drivers/mfd/wm*.c
 F:	drivers/power/wm83*.c
 F:	drivers/rtc/rtc-wm83*.c
 F:	drivers/regulator/wm8*.c
 F:	drivers/video/backlight/wm83*_bl.c
 F:	drivers/watchdog/wm83*_wdt.c
+F:	include/linux/mfd/arizona/
 F:	include/linux/mfd/wm831x/
 F:	include/linux/mfd/wm8350/
 F:	include/linux/mfd/wm8400*
 F:	include/linux/wm97xx.h
 F:	include/sound/wm????.h
+F:	sound/soc/codecs/arizona.?
 F:	sound/soc/codecs/wm*
 
 WORKQUEUE

Makefile

@@ -1,7 +1,7 @@
 VERSION = 3
 PATCHLEVEL = 6
 SUBLEVEL = 0
-EXTRAVERSION = -rc2
+EXTRAVERSION = -rc3
 NAME = Saber-toothed Squirrel
 
 # *DOCUMENTATION*

arch/alpha/Kconfig

@@ -18,6 +18,8 @@ config ALPHA
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select GENERIC_SMP_IDLE_THREAD
 	select GENERIC_CMOS_UPDATE
+	select GENERIC_STRNCPY_FROM_USER
+	select GENERIC_STRNLEN_USER
 	help
 	  The Alpha is a 64-bit general-purpose processor designed and
 	  marketed by the Digital Equipment Corporation of blessed memory,

arch/alpha/include/asm/atomic.h

@@ -14,8 +14,8 @@
  */
 
 
-#define ATOMIC_INIT(i)		( (atomic_t) { (i) } )
-#define ATOMIC64_INIT(i)	( (atomic64_t) { (i) } )
+#define ATOMIC_INIT(i)		{ (i) }
+#define ATOMIC64_INIT(i)	{ (i) }
 
 #define atomic_read(v)		(*(volatile int *)&(v)->counter)
 #define atomic64_read(v)	(*(volatile long *)&(v)->counter)

arch/alpha/include/asm/fpu.h

@@ -1,7 +1,9 @@
 #ifndef __ASM_ALPHA_FPU_H
 #define __ASM_ALPHA_FPU_H
 
+#ifdef __KERNEL__
 #include <asm/special_insns.h>
+#endif
 
 /*
  * Alpha floating-point control register defines:

arch/alpha/include/asm/ptrace.h

@@ -76,7 +76,10 @@ struct switch_stack {
 #define task_pt_regs(task) \
   ((struct pt_regs *) (task_stack_page(task) + 2*PAGE_SIZE) - 1)
 
-#define force_successful_syscall_return() (task_pt_regs(current)->r0 = 0)
+#define current_pt_regs() \
+  ((struct pt_regs *) ((char *)current_thread_info() + 2*PAGE_SIZE) - 1)
+
+#define force_successful_syscall_return() (current_pt_regs()->r0 = 0)
 
 #endif
 

arch/alpha/include/asm/socket.h

@@ -76,9 +76,11 @@
 /* Instruct lower device to use last 4-bytes of skb data as FCS */
 #define SO_NOFCS		43
 
+#ifdef __KERNEL__
 /* O_NONBLOCK clashes with the bits used for socket types.  Therefore we
  * have to define SOCK_NONBLOCK to a different value here.
  */
 #define SOCK_NONBLOCK	0x40000000
+#endif /* __KERNEL__ */
 
 #endif /* _ASM_SOCKET_H */

arch/alpha/include/asm/uaccess.h

@@ -433,36 +433,12 @@ clear_user(void __user *to, long len)
 #undef __module_address
 #undef __module_call
 
-/* Returns: -EFAULT if exception before terminator, N if the entire
-   buffer filled, else strlen.  */
+#define user_addr_max() \
+        (segment_eq(get_fs(), USER_DS) ? TASK_SIZE : ~0UL)
 
-extern long __strncpy_from_user(char *__to, const char __user *__from, long __to_len);
-
-extern inline long
-strncpy_from_user(char *to, const char __user *from, long n)
-{
-	long ret = -EFAULT;
-	if (__access_ok((unsigned long)from, 0, get_fs()))
-		ret = __strncpy_from_user(to, from, n);
-	return ret;
-}
-
-/* Returns: 0 if bad, string length+1 (memory size) of string if ok */
-extern long __strlen_user(const char __user *);
-
-extern inline long strlen_user(const char __user *str)
-{
-	return access_ok(VERIFY_READ,str,0) ? __strlen_user(str) : 0;
-}
-
-/* Returns: 0 if exception before NUL or reaching the supplied limit (N),
- * a value greater than N if the limit would be exceeded, else strlen.  */
-extern long __strnlen_user(const char __user *, long);
-
-extern inline long strnlen_user(const char __user *str, long n)
-{
-	return access_ok(VERIFY_READ,str,0) ? __strnlen_user(str, n) : 0;
-}
+extern long strncpy_from_user(char *dest, const char __user *src, long count);
+extern __must_check long strlen_user(const char __user *str);
+extern __must_check long strnlen_user(const char __user *str, long n);
 
 /*
  * About the exception table:

arch/alpha/include/asm/unistd.h

@@ -465,10 +465,12 @@
 #define __NR_setns			501
 #define __NR_accept4			502
 #define __NR_sendmmsg			503
+#define __NR_process_vm_readv		504
+#define __NR_process_vm_writev		505
 
 #ifdef __KERNEL__
 
-#define NR_SYSCALLS			504
+#define NR_SYSCALLS			506
 
 #define __ARCH_WANT_OLD_READDIR
 #define __ARCH_WANT_STAT64

arch/alpha/include/asm/word-at-a-time.h

@@ -0,0 +1,55 @@
+#ifndef _ASM_WORD_AT_A_TIME_H
+#define _ASM_WORD_AT_A_TIME_H
+
+#include <asm/compiler.h>
+
+/*
+ * word-at-a-time interface for Alpha.
+ */
+
+/*
+ * We do not use the word_at_a_time struct on Alpha, but it needs to be
+ * implemented to humour the generic code.
+ */
+struct word_at_a_time {
+	const unsigned long unused;
+};
+
+#define WORD_AT_A_TIME_CONSTANTS { 0 }
+
+/* Return nonzero if val has a zero */
+static inline unsigned long has_zero(unsigned long val, unsigned long *bits, const struct word_at_a_time *c)
+{
+	unsigned long zero_locations = __kernel_cmpbge(0, val);
+	*bits = zero_locations;
+	return zero_locations;
+}
+
+static inline unsigned long prep_zero_mask(unsigned long val, unsigned long bits, const struct word_at_a_time *c)
+{
+	return bits;
+}
+
+#define create_zero_mask(bits) (bits)
+
+static inline unsigned long find_zero(unsigned long bits)
+{
+#if defined(CONFIG_ALPHA_EV6) && defined(CONFIG_ALPHA_EV67)
+	/* Simple if have CIX instructions */
+	return __kernel_cttz(bits);
+#else
+	unsigned long t1, t2, t3;
+	/* Retain lowest set bit only */
+	bits &= -bits;
+	/* Binary search for lowest set bit */
+	t1 = bits & 0xf0;
+	t2 = bits & 0xcc;
+	t3 = bits & 0xaa;
+	if (t1) t1 = 4;
+	if (t2) t2 = 2;
+	if (t3) t3 = 1;
+	return t1 + t2 + t3;
+#endif
+}
+
+#endif /* _ASM_WORD_AT_A_TIME_H */

arch/alpha/kernel/alpha_ksyms.c

@@ -52,7 +52,6 @@ EXPORT_SYMBOL(alpha_write_fp_reg_s);
 
 /* entry.S */
 EXPORT_SYMBOL(kernel_thread);
-EXPORT_SYMBOL(kernel_execve);
 
 /* Networking helper routines. */
 EXPORT_SYMBOL(csum_tcpudp_magic);
@@ -74,8 +73,6 @@ EXPORT_SYMBOL(alpha_fp_emul);
  */
 EXPORT_SYMBOL(__copy_user);
 EXPORT_SYMBOL(__do_clear_user);
-EXPORT_SYMBOL(__strncpy_from_user);
-EXPORT_SYMBOL(__strnlen_user);
 
 /* 
  * SMP-specific symbols.

arch/alpha/kernel/entry.S

@@ -663,58 +663,6 @@ kernel_thread:
 	br	ret_to_kernel
 .end kernel_thread
 
-/*
- * kernel_execve(path, argv, envp)
- */
-	.align	4
-	.globl	kernel_execve
-	.ent	kernel_execve
-kernel_execve:
-	/* We can be called from a module.  */
-	ldgp	$gp, 0($27)
-	lda	$sp, -(32+SIZEOF_PT_REGS+8)($sp)
-	.frame	$sp, 32+SIZEOF_PT_REGS+8, $26, 0
-	stq	$26, 0($sp)
-	stq	$16, 8($sp)
-	stq	$17, 16($sp)
-	stq	$18, 24($sp)
-	.prologue 1
-
-	lda	$16, 32($sp)
-	lda	$17, 0
-	lda	$18, SIZEOF_PT_REGS
-	bsr	$26, memset		!samegp
-
-	/* Avoid the HAE being gratuitously wrong, which would cause us
-	   to do the whole turn off interrupts thing and restore it.  */
-	ldq	$2, alpha_mv+HAE_CACHE
-	stq	$2, 152+32($sp)
-
-	ldq	$16, 8($sp)
-	ldq	$17, 16($sp)
-	ldq	$18, 24($sp)
-	lda	$19, 32($sp)
-	bsr	$26, do_execve		!samegp
-
-	ldq	$26, 0($sp)
-	bne	$0, 1f			/* error! */
-
-	/* Move the temporary pt_regs struct from its current location
-	   to the top of the kernel stack frame.  See copy_thread for
-	   details for a normal process.  */
-	lda	$16, 0x4000 - SIZEOF_PT_REGS($8)
-	lda	$17, 32($sp)
-	lda	$18, SIZEOF_PT_REGS
-	bsr	$26, memmove		!samegp
-
-	/* Take that over as our new stack frame and visit userland!  */
-	lda	$sp, 0x4000 - SIZEOF_PT_REGS($8)
-	br	$31, ret_from_sys_call
-
-1:	lda	$sp, 32+SIZEOF_PT_REGS+8($sp)
-	ret
-.end kernel_execve
-
 
 /*
  * Special system calls.  Most of these are special in that they either
@@ -796,115 +744,6 @@ sys_rt_sigreturn:
 	br	ret_from_sys_call
 .end sys_rt_sigreturn
 
-	.align	4
-	.globl	sys_sethae
-	.ent	sys_sethae
-sys_sethae:
-	.prologue 0
-	stq	$16, 152($sp)
-	ret
-.end sys_sethae
-
-	.align	4
-	.globl	osf_getpriority
-	.ent	osf_getpriority
-osf_getpriority:
-	lda	$sp, -16($sp)
-	stq	$26, 0($sp)
-	.prologue 0
-
-	jsr	$26, sys_getpriority
-
-	ldq	$26, 0($sp)
-	blt	$0, 1f
-
-	/* Return value is the unbiased priority, i.e. 20 - prio.
-	   This does result in negative return values, so signal
-	   no error by writing into the R0 slot.  */
-	lda	$1, 20
-	stq	$31, 16($sp)
-	subl	$1, $0, $0
-	unop
-
-1:	lda	$sp, 16($sp)
-	ret
-.end osf_getpriority
-
-	.align	4
-	.globl	sys_getxuid
-	.ent	sys_getxuid
-sys_getxuid:
-	.prologue 0
-	ldq	$2, TI_TASK($8)
-	ldq	$3, TASK_CRED($2)
-	ldl	$0, CRED_UID($3)
-	ldl	$1, CRED_EUID($3)
-	stq	$1, 80($sp)
-	ret
-.end sys_getxuid
-
-	.align	4
-	.globl	sys_getxgid
-	.ent	sys_getxgid
-sys_getxgid:
-	.prologue 0
-	ldq	$2, TI_TASK($8)
-	ldq	$3, TASK_CRED($2)
-	ldl	$0, CRED_GID($3)
-	ldl	$1, CRED_EGID($3)
-	stq	$1, 80($sp)
-	ret
-.end sys_getxgid
-
-	.align	4
-	.globl	sys_getxpid
-	.ent	sys_getxpid
-sys_getxpid:
-	.prologue 0
-	ldq	$2, TI_TASK($8)
-
-	/* See linux/kernel/timer.c sys_getppid for discussion
-	   about this loop.  */
-	ldq	$3, TASK_GROUP_LEADER($2)
-	ldq	$4, TASK_REAL_PARENT($3)
-	ldl	$0, TASK_TGID($2)
-1:	ldl	$1, TASK_TGID($4)
-#ifdef CONFIG_SMP
-	mov	$4, $5
-	mb
-	ldq	$3, TASK_GROUP_LEADER($2)
-	ldq	$4, TASK_REAL_PARENT($3)
-	cmpeq	$4, $5, $5
-	beq	$5, 1b
-#endif
-	stq	$1, 80($sp)
-	ret
-.end sys_getxpid
-
-	.align	4
-	.globl	sys_alpha_pipe
-	.ent	sys_alpha_pipe
-sys_alpha_pipe:
-	lda	$sp, -16($sp)
-	stq	$26, 0($sp)
-	.prologue 0
-
-	mov	$31, $17
-	lda	$16, 8($sp)
-	jsr	$26, do_pipe_flags
-
-	ldq	$26, 0($sp)
-	bne	$0, 1f
-
-	/* The return values are in $0 and $20.  */
-	ldl	$1, 12($sp)
-	ldl	$0, 8($sp)
-
-	stq	$1, 80+16($sp)
-1:	lda	$sp, 16($sp)
-	ret
-.end sys_alpha_pipe
-
 	.align	4
 	.globl	sys_execve
 	.ent	sys_execve

arch/alpha/kernel/osf_sys.c

@@ -1404,3 +1404,52 @@ SYSCALL_DEFINE3(osf_writev, unsigned long, fd,
 }
 
 #endif
+
+SYSCALL_DEFINE2(osf_getpriority, int, which, int, who)
+{
+	int prio = sys_getpriority(which, who);
+	if (prio >= 0) {
+		/* Return value is the unbiased priority, i.e. 20 - prio.
+		   This does result in negative return values, so signal
+		   no error */
+		force_successful_syscall_return();
+		prio = 20 - prio;
+	}
+	return prio;
+}
+
+SYSCALL_DEFINE0(getxuid)
+{
+	current_pt_regs()->r20 = sys_geteuid();
+	return sys_getuid();
+}
+
+SYSCALL_DEFINE0(getxgid)
+{
+	current_pt_regs()->r20 = sys_getegid();
+	return sys_getgid();
+}
+
+SYSCALL_DEFINE0(getxpid)
+{
+	current_pt_regs()->r20 = sys_getppid();
+	return sys_getpid();
+}
+
+SYSCALL_DEFINE0(alpha_pipe)
+{
+	int fd[2];
+	int res = do_pipe_flags(fd, 0);
+	if (!res) {
+		/* The return values are in $0 and $20.  */
+		current_pt_regs()->r20 = fd[1];
+		res = fd[0];
+	}
+	return res;
+}
+
+SYSCALL_DEFINE1(sethae, unsigned long, val)
+{
+	current_pt_regs()->hae = val;
+	return 0;
+}

arch/alpha/kernel/process.c

@@ -455,3 +455,22 @@ get_wchan(struct task_struct *p)
 	}
 	return pc;
 }
+
+int kernel_execve(const char *path, const char *const argv[], const char *const envp[])
+{
+	/* Avoid the HAE being gratuitously wrong, which would cause us
+	   to do the whole turn off interrupts thing and restore it.  */
+	struct pt_regs regs = {.hae = alpha_mv.hae_cache};
+	int err = do_execve(path, argv, envp, &regs);
+	if (!err) {
+		struct pt_regs *p = current_pt_regs();
+		/* copy regs to normal position and off to userland we go... */
+		*p = regs;
+		__asm__ __volatile__ (
+			"mov	%0, $sp;"
+			"br	$31, ret_from_sys_call"
+			: : "r"(p));
+	}
+	return err;
+}
+EXPORT_SYMBOL(kernel_execve);

arch/alpha/kernel/systbls.S

@@ -111,7 +111,7 @@ sys_call_table:
 	.quad sys_socket
 	.quad sys_connect
 	.quad sys_accept
-	.quad osf_getpriority			/* 100 */
+	.quad sys_osf_getpriority			/* 100 */
 	.quad sys_send
 	.quad sys_recv
 	.quad sys_sigreturn
@@ -522,6 +522,8 @@ sys_call_table:
 	.quad sys_setns
 	.quad sys_accept4
 	.quad sys_sendmmsg
+	.quad sys_process_vm_readv
+	.quad sys_process_vm_writev		/* 505 */
 
 	.size sys_call_table, . - sys_call_table
 	.type sys_call_table, @object

arch/alpha/lib/Makefile

@@ -31,8 +31,6 @@ lib-y =	__divqu.o __remqu.o __divlu.o __remlu.o \
 	$(ev6-y)memchr.o \
 	$(ev6-y)copy_user.o \
 	$(ev6-y)clear_user.o \
-	$(ev6-y)strncpy_from_user.o \
-	$(ev67-y)strlen_user.o \
 	$(ev6-y)csum_ipv6_magic.o \
 	$(ev6-y)clear_page.o \
 	$(ev6-y)copy_page.o \

arch/alpha/lib/ev6-strncpy_from_user.S

@@ -1,424 +0,0 @@
-/*
- * arch/alpha/lib/ev6-strncpy_from_user.S
- * 21264 version contributed by Rick Gorton <rick.gorton@alpha-processor.com>
- *
- * Just like strncpy except in the return value:
- *
- * -EFAULT       if an exception occurs before the terminator is copied.
- * N             if the buffer filled.
- *
- * Otherwise the length of the string is returned.
- *
- * Much of the information about 21264 scheduling/coding comes from:
- *	Compiler Writer's Guide for the Alpha 21264
- *	abbreviated as 'CWG' in other comments here
- *	ftp.digital.com/pub/Digital/info/semiconductor/literature/dsc-library.html
- * Scheduling notation:
- *	E	- either cluster
- *	U	- upper subcluster; U0 - subcluster U0; U1 - subcluster U1
- *	L	- lower subcluster; L0 - subcluster L0; L1 - subcluster L1
- * A bunch of instructions got moved and temp registers were changed
- * to aid in scheduling.  Control flow was also re-arranged to eliminate
- * branches, and to provide longer code sequences to enable better scheduling.
- * A total rewrite (using byte load/stores for start & tail sequences)
- * is desirable, but very difficult to do without a from-scratch rewrite.
- * Save that for the future.
- */
-
-
-#include <asm/errno.h>
-#include <asm/regdef.h>
-
-
-/* Allow an exception for an insn; exit if we get one.  */
-#define EX(x,y...)			\
-	99: x,##y;			\
-	.section __ex_table,"a";	\
-	.long 99b - .;			\
-	lda $31, $exception-99b($0); 	\
-	.previous
-
-
-	.set noat
-	.set noreorder
-	.text
-
-	.globl __strncpy_from_user
-	.ent __strncpy_from_user
-	.frame $30, 0, $26
-	.prologue 0
-
-	.align 4
-__strncpy_from_user:
-	and	a0, 7, t3	# E : find dest misalignment
-	beq	a2, $zerolength	# U :
-
-	/* Are source and destination co-aligned?  */
-	mov	a0, v0		# E : save the string start
-	xor	a0, a1, t4	# E :
-	EX( ldq_u t1, 0(a1) )	# L : Latency=3 load first quadword
-	ldq_u	t0, 0(a0)	# L : load first (partial) aligned dest quadword
-
-	addq	a2, t3, a2	# E : bias count by dest misalignment
-	subq	a2, 1, a3	# E :
-	addq	zero, 1, t10	# E :
-	and	t4, 7, t4	# E : misalignment between the two
-
-	and	a3, 7, t6	# E : number of tail bytes
-	sll	t10, t6, t10	# E : t10 = bitmask of last count byte
-	bne	t4, $unaligned	# U :
-	lda	t2, -1		# E : build a mask against false zero
-
-	/*
-	 * We are co-aligned; take care of a partial first word.
-	 * On entry to this basic block:
-	 * t0 == the first destination word for masking back in
-	 * t1 == the first source word.
-	 */
-
-	srl	a3, 3, a2	# E : a2 = loop counter = (count - 1)/8
-	addq	a1, 8, a1	# E :
-	mskqh	t2, a1, t2	# U :   detection in the src word
-	nop
-
-	/* Create the 1st output word and detect 0's in the 1st input word.  */
-	mskqh	t1, a1, t3	# U :
-	mskql	t0, a1, t0	# U : assemble the first output word
-	ornot	t1, t2, t2	# E :
-	nop
-
-	cmpbge	zero, t2, t8	# E : bits set iff null found
-	or	t0, t3, t0	# E :
-	beq	a2, $a_eoc	# U :
-	bne	t8, $a_eos	# U : 2nd branch in a quad.  Bad.
-
-	/* On entry to this basic block:
-	 * t0 == a source quad not containing a null.
-	 * a0 - current aligned destination address
-	 * a1 - current aligned source address
-	 * a2 - count of quadwords to move.
-	 * NOTE: Loop improvement - unrolling this is going to be
-	 *	a huge win, since we're going to stall otherwise.
-	 *	Fix this later.  For _really_ large copies, look
-	 *	at using wh64 on a look-ahead basis.  See the code
-	 *	in clear_user.S and copy_user.S.
-	 * Presumably, since (a0) and (a1) do not overlap (by C definition)
-	 * Lots of nops here:
-	 *	- Separate loads from stores
-	 *	- Keep it to 1 branch/quadpack so the branch predictor
-	 *	  can train.
-	 */
-$a_loop:
-	stq_u	t0, 0(a0)	# L :
-	addq	a0, 8, a0	# E :
-	nop
-	subq	a2, 1, a2	# E :
-
-	EX( ldq_u t0, 0(a1) )	# L :
-	addq	a1, 8, a1	# E :
-	cmpbge	zero, t0, t8	# E : Stall 2 cycles on t0
-	beq	a2, $a_eoc      # U :
-
-	beq	t8, $a_loop	# U :
-	nop
-	nop
-	nop
-
-	/* Take care of the final (partial) word store.  At this point
-	 * the end-of-count bit is set in t8 iff it applies.
-	 *
-	 * On entry to this basic block we have:
-	 * t0 == the source word containing the null
-	 * t8 == the cmpbge mask that found it.
-	 */
-$a_eos:
-	negq	t8, t12		# E : find low bit set
-	and	t8, t12, t12	# E : 
-
-	/* We're doing a partial word store and so need to combine
-	   our source and original destination words.  */
-	ldq_u	t1, 0(a0)	# L :
-	subq	t12, 1, t6	# E :
-
-	or	t12, t6, t8	# E :
-	zapnot	t0, t8, t0	# U : clear src bytes > null
-	zap	t1, t8, t1	# U : clear dst bytes <= null
-	or	t0, t1, t0	# E :
-
-	stq_u	t0, 0(a0)	# L :
-	br	$finish_up	# L0 :
-	nop
-	nop
-
-	/* Add the end-of-count bit to the eos detection bitmask.  */
-	.align 4
-$a_eoc:
-	or	t10, t8, t8
-	br	$a_eos
-	nop
-	nop
-
-
-/* The source and destination are not co-aligned.  Align the destination
-   and cope.  We have to be very careful about not reading too much and
-   causing a SEGV.  */
-
-	.align 4
-$u_head:
-	/* We know just enough now to be able to assemble the first
-	   full source word.  We can still find a zero at the end of it
-	   that prevents us from outputting the whole thing.
-
-	   On entry to this basic block:
-	   t0 == the first dest word, unmasked
-	   t1 == the shifted low bits of the first source word
-	   t6 == bytemask that is -1 in dest word bytes */
-
-	EX( ldq_u t2, 8(a1) )	# L : load second src word
-	addq	a1, 8, a1	# E :
-	mskql	t0, a0, t0	# U : mask trailing garbage in dst
-	extqh	t2, a1, t4	# U :
-
-	or	t1, t4, t1	# E : first aligned src word complete
-	mskqh	t1, a0, t1	# U : mask leading garbage in src
-	or	t0, t1, t0	# E : first output word complete
-	or	t0, t6, t6	# E : mask original data for zero test
-
-	cmpbge	zero, t6, t8	# E :
-	beq	a2, $u_eocfin	# U :
-	bne	t8, $u_final	# U : bad news - 2nd branch in a quad
-	lda	t6, -1		# E : mask out the bits we have
-
-	mskql	t6, a1, t6	# U :   already seen
-	stq_u	t0, 0(a0)	# L : store first output word
-	or      t6, t2, t2	# E :
-	cmpbge	zero, t2, t8	# E : find nulls in second partial
-
-	addq	a0, 8, a0		# E :
-	subq	a2, 1, a2		# E :
-	bne	t8, $u_late_head_exit	# U :
-	nop
-
-	/* Finally, we've got all the stupid leading edge cases taken care
-	   of and we can set up to enter the main loop.  */
-
-	extql	t2, a1, t1	# U : position hi-bits of lo word
-	EX( ldq_u t2, 8(a1) )	# L : read next high-order source word
-	addq	a1, 8, a1	# E :
-	cmpbge	zero, t2, t8	# E :
-
-	beq	a2, $u_eoc	# U :
-	bne	t8, $u_eos	# U :
-	nop
-	nop
-
-	/* Unaligned copy main loop.  In order to avoid reading too much,
-	   the loop is structured to detect zeros in aligned source words.
-	   This has, unfortunately, effectively pulled half of a loop
-	   iteration out into the head and half into the tail, but it does
-	   prevent nastiness from accumulating in the very thing we want
-	   to run as fast as possible.
-
-	   On entry to this basic block:
-	   t1 == the shifted high-order bits from the previous source word
-	   t2 == the unshifted current source word
-
-	   We further know that t2 does not contain a null terminator.  */
-
-	/*
-	 * Extra nops here:
-	 *	separate load quads from store quads
-	 *	only one branch/quad to permit predictor training
-	 */
-
-	.align 4
-$u_loop:
-	extqh	t2, a1, t0	# U : extract high bits for current word
-	addq	a1, 8, a1	# E :
-	extql	t2, a1, t3	# U : extract low bits for next time
-	addq	a0, 8, a0	# E :
-
-	or	t0, t1, t0	# E : current dst word now complete
-	EX( ldq_u t2, 0(a1) )	# L : load high word for next time
-	subq	a2, 1, a2	# E :
-	nop
-
-	stq_u	t0, -8(a0)	# L : save the current word
-	mov	t3, t1		# E :
-	cmpbge	zero, t2, t8	# E : test new word for eos
-	beq	a2, $u_eoc	# U :
-
-	beq	t8, $u_loop	# U :
-	nop
-	nop
-	nop
-
-	/* We've found a zero somewhere in the source word we just read.
-	   If it resides in the lower half, we have one (probably partial)
-	   word to write out, and if it resides in the upper half, we
-	   have one full and one partial word left to write out.
-
-	   On entry to this basic block:
-	   t1 == the shifted high-order bits from the previous source word
-	   t2 == the unshifted current source word.  */
-	.align 4
-$u_eos:
-	extqh	t2, a1, t0	# U :
-	or	t0, t1, t0	# E : first (partial) source word complete
-	cmpbge	zero, t0, t8	# E : is the null in this first bit?
-	nop
-
-	bne	t8, $u_final	# U :
-	stq_u	t0, 0(a0)	# L : the null was in the high-order bits
-	addq	a0, 8, a0	# E :
-	subq	a2, 1, a2	# E :
-
-	.align 4
-$u_late_head_exit:
-	extql	t2, a1, t0	# U :
-	cmpbge	zero, t0, t8	# E :
-	or	t8, t10, t6	# E :
-	cmoveq	a2, t6, t8	# E :
-
-	/* Take care of a final (probably partial) result word.
-	   On entry to this basic block:
-	   t0 == assembled source word
-	   t8 == cmpbge mask that found the null.  */
-	.align 4
-$u_final:
-	negq	t8, t6		# E : isolate low bit set
-	and	t6, t8, t12	# E :
-	ldq_u	t1, 0(a0)	# L :
-	subq	t12, 1, t6	# E :
-
-	or	t6, t12, t8	# E :
-	zapnot	t0, t8, t0	# U : kill source bytes > null
-	zap	t1, t8, t1	# U : kill dest bytes <= null
-	or	t0, t1, t0	# E :
-
-	stq_u	t0, 0(a0)	# E :
-	br	$finish_up	# U :
-	nop
-	nop
-
-	.align 4
-$u_eoc:				# end-of-count
-	extqh	t2, a1, t0	# U :
-	or	t0, t1, t0	# E :
-	cmpbge	zero, t0, t8	# E :
-	nop
-
-	.align 4
-$u_eocfin:			# end-of-count, final word
-	or	t10, t8, t8	# E :
-	br	$u_final	# U :
-	nop
-	nop
-
-	/* Unaligned copy entry point.  */
-	.align 4
-$unaligned:
-
-	srl	a3, 3, a2	# U : a2 = loop counter = (count - 1)/8
-	and	a0, 7, t4	# E : find dest misalignment
-	and	a1, 7, t5	# E : find src misalignment
-	mov	zero, t0	# E :
-
-	/* Conditionally load the first destination word and a bytemask
-	   with 0xff indicating that the destination byte is sacrosanct.  */
-
-	mov	zero, t6	# E :
-	beq	t4, 1f		# U :
-	ldq_u	t0, 0(a0)	# L :
-	lda	t6, -1		# E :
-
-	mskql	t6, a0, t6	# E :
-	nop
-	nop
-	nop
-
-	.align 4
-1:
-	subq	a1, t4, a1	# E : sub dest misalignment from src addr
-	/* If source misalignment is larger than dest misalignment, we need
-	   extra startup checks to avoid SEGV.  */
-	cmplt	t4, t5, t12	# E :
-	extql	t1, a1, t1	# U : shift src into place
-	lda	t2, -1		# E : for creating masks later
-
-	beq	t12, $u_head	# U :
-	mskqh	t2, t5, t2	# U : begin src byte validity mask
-	cmpbge	zero, t1, t8	# E : is there a zero?
-	nop
-
-	extql	t2, a1, t2	# U :
-	or	t8, t10, t5	# E : test for end-of-count too
-	cmpbge	zero, t2, t3	# E :
-	cmoveq	a2, t5, t8	# E : Latency=2, extra map slot
-
-	nop			# E : goes with cmov
-	andnot	t8, t3, t8	# E :
-	beq	t8, $u_head	# U :
-	nop
-
-	/* At this point we've found a zero in the first partial word of
-	   the source.  We need to isolate the valid source data and mask
-	   it into the original destination data.  (Incidentally, we know
-	   that we'll need at least one byte of that original dest word.) */
-
-	ldq_u	t0, 0(a0)	# L :
-	negq	t8, t6		# E : build bitmask of bytes <= zero
-	mskqh	t1, t4, t1	# U :
-	and	t6, t8, t12	# E :
-
-	subq	t12, 1, t6	# E :
-	or	t6, t12, t8	# E :
-	zapnot	t2, t8, t2	# U : prepare source word; mirror changes
-	zapnot	t1, t8, t1	# U : to source validity mask
-
-	andnot	t0, t2, t0	# E : zero place for source to reside
-	or	t0, t1, t0	# E : and put it there
-	stq_u	t0, 0(a0)	# L :
-	nop
-
-	.align 4
-$finish_up:
-	zapnot	t0, t12, t4	# U : was last byte written null?
-	and	t12, 0xf0, t3	# E : binary search for the address of the
-	cmovne	t4, 1, t4	# E : Latency=2, extra map slot
-	nop			# E : with cmovne
-
-	and	t12, 0xcc, t2	# E : last byte written
-	and	t12, 0xaa, t1	# E :
-	cmovne	t3, 4, t3	# E : Latency=2, extra map slot
-	nop			# E : with cmovne
-
-	bic	a0, 7, t0
-	cmovne	t2, 2, t2	# E : Latency=2, extra map slot
-	nop			# E : with cmovne
-	nop
-
-	cmovne	t1, 1, t1	# E : Latency=2, extra map slot
-	nop			# E : with cmovne
-	addq	t0, t3, t0	# E :
-	addq	t1, t2, t1	# E :
-
-	addq	t0, t1, t0	# E :
-	addq	t0, t4, t0	# add one if we filled the buffer
-	subq	t0, v0, v0	# find string length
-	ret			# L0 :
-
-	.align 4
-$zerolength:
-	nop
-	nop
-	nop
-	clr	v0
-
-$exception:
-	nop
-	nop
-	nop
-	ret
-
-	.end __strncpy_from_user

arch/alpha/lib/ev67-strlen_user.S

@@ -1,107 +0,0 @@
-/*
- * arch/alpha/lib/ev67-strlen_user.S
- * 21264 version contributed by Rick Gorton <rick.gorton@api-networks.com>
- *
- * Return the length of the string including the NULL terminator
- * (strlen+1) or zero if an error occurred.
- *
- * In places where it is critical to limit the processing time,
- * and the data is not trusted, strnlen_user() should be used.
- * It will return a value greater than its second argument if
- * that limit would be exceeded. This implementation is allowed
- * to access memory beyond the limit, but will not cross a page
- * boundary when doing so.
- *
- * Much of the information about 21264 scheduling/coding comes from:
- *      Compiler Writer's Guide for the Alpha 21264
- *      abbreviated as 'CWG' in other comments here
- *      ftp.digital.com/pub/Digital/info/semiconductor/literature/dsc-library.html
- * Scheduling notation:
- *      E       - either cluster
- *      U       - upper subcluster; U0 - subcluster U0; U1 - subcluster U1
- *      L       - lower subcluster; L0 - subcluster L0; L1 - subcluster L1
- * Try not to change the actual algorithm if possible for consistency.
- */
-
-#include <asm/regdef.h>
-
-
-/* Allow an exception for an insn; exit if we get one.  */
-#define EX(x,y...)			\
-	99: x,##y;			\
-	.section __ex_table,"a";	\
-	.long 99b - .;			\
-	lda v0, $exception-99b(zero);	\
-	.previous
-
-
-	.set noreorder
-	.set noat
-	.text
-
-	.globl __strlen_user
-	.ent __strlen_user
-	.frame sp, 0, ra
-
-	.align 4
-__strlen_user:
-	ldah	a1, 32767(zero)	# do not use plain strlen_user() for strings
-				# that might be almost 2 GB long; you should
-				# be using strnlen_user() instead
-	nop
-	nop
-	nop
-
-	.globl __strnlen_user
-
-	.align 4
-__strnlen_user:
-	.prologue 0
-	EX( ldq_u t0, 0(a0) )	# L : load first quadword (a0 may be misaligned)
-	lda     t1, -1(zero)	# E :
-
-	insqh   t1, a0, t1	# U :
-	andnot  a0, 7, v0	# E :
-	or      t1, t0, t0	# E :
-	subq	a0, 1, a0	# E : get our +1 for the return 
-
-	cmpbge  zero, t0, t1	# E : t1 <- bitmask: bit i == 1 <==> i-th byte == 0
-	subq	a1, 7, t2	# E :
-	subq	a0, v0, t0	# E :
-	bne     t1, $found	# U :
-
-	addq	t2, t0, t2	# E :
-	addq	a1, 1, a1	# E :
-	nop			# E :
-	nop			# E :
-
-	.align 4
-$loop:	ble	t2, $limit	# U :
-	EX( ldq t0, 8(v0) )	# L :
-	nop			# E :
-	nop			# E :
-
-	cmpbge  zero, t0, t1	# E :
-	subq	t2, 8, t2	# E :
-	addq    v0, 8, v0	# E : addr += 8
-	beq     t1, $loop	# U :
-
-$found: cttz	t1, t2		# U0 :
-	addq	v0, t2, v0	# E :
-	subq    v0, a0, v0	# E :
-	ret			# L0 :
-
-$exception:
-	nop
-	nop
-	nop
-	ret
-
-	.align 4		# currently redundant
-$limit:
-	nop
-	nop
-	subq	a1, t2, v0
-	ret
-
-	.end __strlen_user

arch/alpha/lib/strlen_user.S

@@ -1,91 +0,0 @@
-/*
- * arch/alpha/lib/strlen_user.S
- *
- * Return the length of the string including the NUL terminator
- * (strlen+1) or zero if an error occurred.
- *
- * In places where it is critical to limit the processing time,
- * and the data is not trusted, strnlen_user() should be used.
- * It will return a value greater than its second argument if
- * that limit would be exceeded. This implementation is allowed
- * to access memory beyond the limit, but will not cross a page
- * boundary when doing so.
- */
-
-#include <asm/regdef.h>
-
-
-/* Allow an exception for an insn; exit if we get one.  */
-#define EX(x,y...)			\
-	99: x,##y;			\
-	.section __ex_table,"a";	\
-	.long 99b - .;			\
-	lda v0, $exception-99b(zero);	\
-	.previous
-
-
-	.set noreorder
-	.set noat
-	.text
-
-	.globl __strlen_user
-	.ent __strlen_user
-	.frame sp, 0, ra
-
-	.align 3
-__strlen_user:
-	ldah	a1, 32767(zero)	# do not use plain strlen_user() for strings
-				# that might be almost 2 GB long; you should
-				# be using strnlen_user() instead
-
-	.globl __strnlen_user
-
-	.align 3
-__strnlen_user:
-	.prologue 0
-
-	EX( ldq_u t0, 0(a0) )	# load first quadword (a0 may be misaligned)
-	lda     t1, -1(zero)
-	insqh   t1, a0, t1
-	andnot  a0, 7, v0
-	or      t1, t0, t0
-	subq	a0, 1, a0	# get our +1 for the return 
-	cmpbge  zero, t0, t1	# t1 <- bitmask: bit i == 1 <==> i-th byte == 0
-	subq	a1, 7, t2
-	subq	a0, v0, t0
-	bne     t1, $found
-
-	addq	t2, t0, t2
-	addq	a1, 1, a1
-
-	.align 3
-$loop:	ble	t2, $limit
-	EX( ldq t0, 8(v0) )
-	subq	t2, 8, t2
-	addq    v0, 8, v0	# addr += 8
-	cmpbge  zero, t0, t1
-	beq     t1, $loop
-
-$found:	negq    t1, t2		# clear all but least set bit
-	and     t1, t2, t1
-
-	and     t1, 0xf0, t2	# binary search for that set bit
-	and	t1, 0xcc, t3
-	and	t1, 0xaa, t4
-	cmovne	t2, 4, t2
-	cmovne	t3, 2, t3
-	cmovne	t4, 1, t4
-	addq	t2, t3, t2
-	addq	v0, t4, v0
-	addq	v0, t2, v0
-	nop			# dual issue next two on ev4 and ev5
-	subq    v0, a0, v0
-$exception:
-	ret
-
-	.align 3		# currently redundant
-$limit:
-	subq	a1, t2, v0
-	ret
-
-	.end __strlen_user

arch/alpha/lib/strncpy_from_user.S

@@ -1,339 +0,0 @@
-/*
- * arch/alpha/lib/strncpy_from_user.S
- * Contributed by Richard Henderson (rth@tamu.edu)
- *
- * Just like strncpy except in the return value:
- *
- * -EFAULT       if an exception occurs before the terminator is copied.
- * N             if the buffer filled.
- *
- * Otherwise the length of the string is returned.
- */
-
-
-#include <asm/errno.h>
-#include <asm/regdef.h>
-
-
-/* Allow an exception for an insn; exit if we get one.  */
-#define EX(x,y...)			\
-	99: x,##y;			\
-	.section __ex_table,"a";	\
-	.long 99b - .;			\
-	lda $31, $exception-99b($0); 	\
-	.previous
-
-
-	.set noat
-	.set noreorder
-	.text
-
-	.globl __strncpy_from_user
-	.ent __strncpy_from_user
-	.frame $30, 0, $26
-	.prologue 0
-
-	.align 3
-$aligned:
-	/* On entry to this basic block:
-	   t0 == the first destination word for masking back in
-	   t1 == the first source word.  */
-
-	/* Create the 1st output word and detect 0's in the 1st input word.  */
-	lda	t2, -1		# e1    : build a mask against false zero
-	mskqh	t2, a1, t2	# e0    :   detection in the src word
-	mskqh	t1, a1, t3	# e0    :
-	ornot	t1, t2, t2	# .. e1 :
-	mskql	t0, a1, t0	# e0    : assemble the first output word
-	cmpbge	zero, t2, t8	# .. e1 : bits set iff null found
-	or	t0, t3, t0	# e0    :
-	beq	a2, $a_eoc	# .. e1 :
-	bne	t8, $a_eos	# .. e1 :
-
-	/* On entry to this basic block:
-	   t0 == a source word not containing a null.  */
-
-$a_loop:
-	stq_u	t0, 0(a0)	# e0    :
-	addq	a0, 8, a0	# .. e1 :
-	EX( ldq_u t0, 0(a1) )	# e0    :
-	addq	a1, 8, a1	# .. e1 :
-	subq	a2, 1, a2	# e0    :
-	cmpbge	zero, t0, t8	# .. e1 (stall)
-	beq	a2, $a_eoc      # e1    :
-	beq	t8, $a_loop	# e1    :
-
-	/* Take care of the final (partial) word store.  At this point
-	   the end-of-count bit is set in t8 iff it applies.
-
-	   On entry to this basic block we have:
-	   t0 == the source word containing the null
-	   t8 == the cmpbge mask that found it.  */
-
-$a_eos:
-	negq	t8, t12		# e0    : find low bit set
-	and	t8, t12, t12	# e1 (stall)
-
-	/* For the sake of the cache, don't read a destination word
-	   if we're not going to need it.  */
-	and	t12, 0x80, t6	# e0    :
-	bne	t6, 1f		# .. e1 (zdb)
-
-	/* We're doing a partial word store and so need to combine
-	   our source and original destination words.  */
-	ldq_u	t1, 0(a0)	# e0    :
-	subq	t12, 1, t6	# .. e1 :
-	or	t12, t6, t8	# e0    :
-	unop			#
-	zapnot	t0, t8, t0	# e0    : clear src bytes > null
-	zap	t1, t8, t1	# .. e1 : clear dst bytes <= null
-	or	t0, t1, t0	# e1    :
-
-1:	stq_u	t0, 0(a0)
-	br	$finish_up
-
-	/* Add the end-of-count bit to the eos detection bitmask.  */
-$a_eoc:
-	or	t10, t8, t8
-	br	$a_eos
-
-	/*** The Function Entry Point ***/
-	.align 3
-__strncpy_from_user:
-	mov	a0, v0		# save the string start
-	beq	a2, $zerolength
-
-	/* Are source and destination co-aligned?  */
-	xor	a0, a1, t1	# e0    :
-	and	a0, 7, t0	# .. e1 : find dest misalignment
-	and	t1, 7, t1	# e0    :
-	addq	a2, t0, a2	# .. e1 : bias count by dest misalignment
-	subq	a2, 1, a2	# e0    :
-	and	a2, 7, t2	# e1    :
-	srl	a2, 3, a2	# e0    : a2 = loop counter = (count - 1)/8
-	addq	zero, 1, t10	# .. e1 :
-	sll	t10, t2, t10	# e0    : t10 = bitmask of last count byte
-	bne	t1, $unaligned	# .. e1 :
-
-	/* We are co-aligned; take care of a partial first word.  */
-
-	EX( ldq_u t1, 0(a1) )	# e0    : load first src word
-	addq	a1, 8, a1	# .. e1 :
-
-	beq	t0, $aligned	# avoid loading dest word if not needed
-	ldq_u	t0, 0(a0)	# e0    :
-	br	$aligned	# .. e1 :
-
-
-/* The source and destination are not co-aligned.  Align the destination
-   and cope.  We have to be very careful about not reading too much and
-   causing a SEGV.  */
-
-	.align 3
-$u_head:
-	/* We know just enough now to be able to assemble the first
-	   full source word.  We can still find a zero at the end of it
-	   that prevents us from outputting the whole thing.
-
-	   On entry to this basic block:
-	   t0 == the first dest word, unmasked
-	   t1 == the shifted low bits of the first source word
-	   t6 == bytemask that is -1 in dest word bytes */
-
-	EX( ldq_u t2, 8(a1) )	# e0    : load second src word
-	addq	a1, 8, a1	# .. e1 :
-	mskql	t0, a0, t0	# e0    : mask trailing garbage in dst
-	extqh	t2, a1, t4	# e0    :
-	or	t1, t4, t1	# e1    : first aligned src word complete
-	mskqh	t1, a0, t1	# e0    : mask leading garbage in src
-	or	t0, t1, t0	# e0    : first output word complete
-	or	t0, t6, t6	# e1    : mask original data for zero test
-	cmpbge	zero, t6, t8	# e0    :
-	beq	a2, $u_eocfin	# .. e1 :
-	bne	t8, $u_final	# e1    :
-
-	lda	t6, -1			# e1    : mask out the bits we have
-	mskql	t6, a1, t6		# e0    :   already seen
-	stq_u	t0, 0(a0)		# e0    : store first output word
-	or      t6, t2, t2		# .. e1 :
-	cmpbge	zero, t2, t8		# e0    : find nulls in second partial
-	addq	a0, 8, a0		# .. e1 :
-	subq	a2, 1, a2		# e0    :
-	bne	t8, $u_late_head_exit	# .. e1 :
-
-	/* Finally, we've got all the stupid leading edge cases taken care
-	   of and we can set up to enter the main loop.  */
-
-	extql	t2, a1, t1	# e0    : position hi-bits of lo word
-	EX( ldq_u t2, 8(a1) )	# .. e1 : read next high-order source word
-	addq	a1, 8, a1	# e0    :
-	cmpbge	zero, t2, t8	# e1 (stall)
-	beq	a2, $u_eoc	# e1    :
-	bne	t8, $u_eos	# e1    :
-
-	/* Unaligned copy main loop.  In order to avoid reading too much,
-	   the loop is structured to detect zeros in aligned source words.
-	   This has, unfortunately, effectively pulled half of a loop
-	   iteration out into the head and half into the tail, but it does
-	   prevent nastiness from accumulating in the very thing we want
-	   to run as fast as possible.
-
-	   On entry to this basic block:
-	   t1 == the shifted high-order bits from the previous source word
-	   t2 == the unshifted current source word
-
-	   We further know that t2 does not contain a null terminator.  */
-
-	.align 3
-$u_loop:
-	extqh	t2, a1, t0	# e0    : extract high bits for current word
-	addq	a1, 8, a1	# .. e1 :
-	extql	t2, a1, t3	# e0    : extract low bits for next time
-	addq	a0, 8, a0	# .. e1 :
-	or	t0, t1, t0	# e0    : current dst word now complete
-	EX( ldq_u t2, 0(a1) )	# .. e1 : load high word for next time
-	stq_u	t0, -8(a0)	# e0    : save the current word
-	mov	t3, t1		# .. e1 :
-	subq	a2, 1, a2	# e0    :
-	cmpbge	zero, t2, t8	# .. e1 : test new word for eos
-	beq	a2, $u_eoc	# e1    :
-	beq	t8, $u_loop	# e1    :
-
-	/* We've found a zero somewhere in the source word we just read.
-	   If it resides in the lower half, we have one (probably partial)
-	   word to write out, and if it resides in the upper half, we
-	   have one full and one partial word left to write out.
-
-	   On entry to this basic block:
-	   t1 == the shifted high-order bits from the previous source word
-	   t2 == the unshifted current source word.  */
-$u_eos:
-	extqh	t2, a1, t0	# e0    :
-	or	t0, t1, t0	# e1    : first (partial) source word complete
-
-	cmpbge	zero, t0, t8	# e0    : is the null in this first bit?
-	bne	t8, $u_final	# .. e1 (zdb)
-
-	stq_u	t0, 0(a0)	# e0    : the null was in the high-order bits
-	addq	a0, 8, a0	# .. e1 :
-	subq	a2, 1, a2	# e1    :
-
-$u_late_head_exit:
-	extql	t2, a1, t0	# .. e0 :
-	cmpbge	zero, t0, t8	# e0    :
-	or	t8, t10, t6	# e1    :
-	cmoveq	a2, t6, t8	# e0    :
-	nop			# .. e1 :
-
-	/* Take care of a final (probably partial) result word.
-	   On entry to this basic block:
-	   t0 == assembled source word
-	   t8 == cmpbge mask that found the null.  */
-$u_final:
-	negq	t8, t6		# e0    : isolate low bit set
-	and	t6, t8, t12	# e1    :
-
-	and	t12, 0x80, t6	# e0    : avoid dest word load if we can
-	bne	t6, 1f		# .. e1 (zdb)
-
-	ldq_u	t1, 0(a0)	# e0    :
-	subq	t12, 1, t6	# .. e1 :
-	or	t6, t12, t8	# e0    :
-	zapnot	t0, t8, t0	# .. e1 : kill source bytes > null
-	zap	t1, t8, t1	# e0    : kill dest bytes <= null
-	or	t0, t1, t0	# e1    :
-
-1:	stq_u	t0, 0(a0)	# e0    :
-	br	$finish_up
-
-$u_eoc:				# end-of-count
-	extqh	t2, a1, t0
-	or	t0, t1, t0
-	cmpbge	zero, t0, t8
-
-$u_eocfin:			# end-of-count, final word
-	or	t10, t8, t8
-	br	$u_final
-
-	/* Unaligned copy entry point.  */
-	.align 3
-$unaligned:
-
-	EX( ldq_u t1, 0(a1) )	# e0    : load first source word
-
-	and	a0, 7, t4	# .. e1 : find dest misalignment
-	and	a1, 7, t5	# e0    : find src misalignment
-
-	/* Conditionally load the first destination word and a bytemask
-	   with 0xff indicating that the destination byte is sacrosanct.  */
-
-	mov	zero, t0	# .. e1 :
-	mov	zero, t6	# e0    :
-	beq	t4, 1f		# .. e1 :
-	ldq_u	t0, 0(a0)	# e0    :
-	lda	t6, -1		# .. e1 :
-	mskql	t6, a0, t6	# e0    :
-1:
-	subq	a1, t4, a1	# .. e1 : sub dest misalignment from src addr
-
-	/* If source misalignment is larger than dest misalignment, we need
-	   extra startup checks to avoid SEGV.  */
-
-	cmplt	t4, t5, t12	# e1    :
-	extql	t1, a1, t1	# .. e0 : shift src into place
-	lda	t2, -1		# e0    : for creating masks later
-	beq	t12, $u_head	# e1    :
-
-	mskqh	t2, t5, t2	# e0    : begin src byte validity mask
-	cmpbge	zero, t1, t8	# .. e1 : is there a zero?
-	extql	t2, a1, t2	# e0    :
-	or	t8, t10, t5	# .. e1 : test for end-of-count too
-	cmpbge	zero, t2, t3	# e0    :
-	cmoveq	a2, t5, t8	# .. e1 :
-	andnot	t8, t3, t8	# e0    :
-	beq	t8, $u_head	# .. e1 (zdb)
-
-	/* At this point we've found a zero in the first partial word of
-	   the source.  We need to isolate the valid source data and mask
-	   it into the original destination data.  (Incidentally, we know
-	   that we'll need at least one byte of that original dest word.) */
-
-	ldq_u	t0, 0(a0)	# e0    :
-	negq	t8, t6		# .. e1 : build bitmask of bytes <= zero
-	mskqh	t1, t4, t1	# e0    :
-	and	t6, t8, t12	# .. e1 :
-	subq	t12, 1, t6	# e0    :
-	or	t6, t12, t8	# e1    :
-
-	zapnot	t2, t8, t2	# e0    : prepare source word; mirror changes
-	zapnot	t1, t8, t1	# .. e1 : to source validity mask
-
-	andnot	t0, t2, t0	# e0    : zero place for source to reside
-	or	t0, t1, t0	# e1    : and put it there
-	stq_u	t0, 0(a0)	# e0    :
-
-$finish_up:
-	zapnot	t0, t12, t4	# was last byte written null?
-	cmovne	t4, 1, t4
-
-	and	t12, 0xf0, t3	# binary search for the address of the
-	and	t12, 0xcc, t2	# last byte written
-	and	t12, 0xaa, t1
-	bic	a0, 7, t0
-	cmovne	t3, 4, t3
-	cmovne	t2, 2, t2
-	cmovne	t1, 1, t1
-	addq	t0, t3, t0
-	addq	t1, t2, t1
-	addq	t0, t1, t0
-	addq	t0, t4, t0	# add one if we filled the buffer
-
-	subq	t0, v0, v0	# find string length
-	ret
-
-$zerolength:
-	clr	v0
-$exception:
-	ret
-
-	.end __strncpy_from_user

arch/alpha/mm/fault.c

@@ -89,6 +89,8 @@ do_page_fault(unsigned long address, unsigned long mmcsr,
 	const struct exception_table_entry *fixup;
 	int fault, si_code = SEGV_MAPERR;
 	siginfo_t info;
+	unsigned int flags = (FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
+			      (cause > 0 ? FAULT_FLAG_WRITE : 0));
 
 	/* As of EV6, a load into $31/$f31 is a prefetch, and never faults
 	   (or is suppressed by the PALcode).  Support that for older CPUs
@@ -114,6 +116,7 @@ do_page_fault(unsigned long address, unsigned long mmcsr,
 		goto vmalloc_fault;
 #endif
 
+retry:
 	down_read(&mm->mmap_sem);
 	vma = find_vma(mm, address);
 	if (!vma)
@@ -144,8 +147,11 @@ do_page_fault(unsigned long address, unsigned long mmcsr,
 	/* If for any reason at all we couldn't handle the fault,
 	   make sure we exit gracefully rather than endlessly redo
 	   the fault.  */
-	fault = handle_mm_fault(mm, vma, address, cause > 0 ? FAULT_FLAG_WRITE : 0);
-	up_read(&mm->mmap_sem);
+	fault = handle_mm_fault(mm, vma, address, flags);
+
+	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
+		return;
+
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
@@ -153,10 +159,26 @@ do_page_fault(unsigned long address, unsigned long mmcsr,
 			goto do_sigbus;
 		BUG();
 	}
-	if (fault & VM_FAULT_MAJOR)
-		current->maj_flt++;
-	else
-		current->min_flt++;
+
+	if (flags & FAULT_FLAG_ALLOW_RETRY) {
+		if (fault & VM_FAULT_MAJOR)
+			current->maj_flt++;
+		else
+			current->min_flt++;
+		if (fault & VM_FAULT_RETRY) {
+			flags &= ~FAULT_FLAG_ALLOW_RETRY;
+
+			 /* No need to up_read(&mm->mmap_sem) as we would
+			 * have already released it in __lock_page_or_retry
+			 * in mm/filemap.c.
+			 */
+
+			goto retry;
+		}
+	}
+
+	up_read(&mm->mmap_sem);
+
 	return;
 
 	/* Something tried to access memory that isn't in our memory map.
@@ -186,12 +208,14 @@ do_page_fault(unsigned long address, unsigned long mmcsr,
 	/* We ran out of memory, or some other thing happened to us that
 	   made us unable to handle the page fault gracefully.  */
  out_of_memory:
+	up_read(&mm->mmap_sem);
 	if (!user_mode(regs))
 		goto no_context;
 	pagefault_out_of_memory();
 	return;
 
  do_sigbus:
+	up_read(&mm->mmap_sem);
 	/* Send a sigbus, regardless of whether we were in kernel
 	   or user mode.  */
 	info.si_signo = SIGBUS;

arch/alpha/oprofile/common.c

@@ -12,6 +12,7 @@
 #include <linux/smp.h>
 #include <linux/errno.h>
 #include <asm/ptrace.h>
+#include <asm/special_insns.h>
 
 #include "op_impl.h"
 

arch/arm/Kconfig

@@ -38,7 +38,6 @@ config ARM
 	select HARDIRQS_SW_RESEND
 	select GENERIC_IRQ_PROBE
 	select GENERIC_IRQ_SHOW
-	select GENERIC_IRQ_PROBE
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select HARDIRQS_SW_RESEND
 	select CPU_PM if (SUSPEND || CPU_IDLE)
@@ -126,11 +125,6 @@ config TRACE_IRQFLAGS_SUPPORT
 	bool
 	default y
 
-config GENERIC_LOCKBREAK
-	bool
-	default y
-	depends on SMP && PREEMPT
-
 config RWSEM_GENERIC_SPINLOCK
 	bool
 	default y

arch/arm/include/asm/pgtable.h

@@ -195,25 +195,6 @@ static inline pte_t *pmd_page_vaddr(pmd_t pmd)
 
 #define pte_clear(mm,addr,ptep)	set_pte_ext(ptep, __pte(0), 0)
 
-#if __LINUX_ARM_ARCH__ < 6
-static inline void __sync_icache_dcache(pte_t pteval)
-{
-}
-#else
-extern void __sync_icache_dcache(pte_t pteval);
-#endif
-
-static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
-			      pte_t *ptep, pte_t pteval)
-{
-	if (addr >= TASK_SIZE)
-		set_pte_ext(ptep, pteval, 0);
-	else {
-		__sync_icache_dcache(pteval);
-		set_pte_ext(ptep, pteval, PTE_EXT_NG);
-	}
-}
-
 #define pte_none(pte)		(!pte_val(pte))
 #define pte_present(pte)	(pte_val(pte) & L_PTE_PRESENT)
 #define pte_write(pte)		(!(pte_val(pte) & L_PTE_RDONLY))
@@ -226,6 +207,27 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 	((pte_val(pte) & (L_PTE_PRESENT | L_PTE_USER)) == \
 	 (L_PTE_PRESENT | L_PTE_USER))
 
+#if __LINUX_ARM_ARCH__ < 6
+static inline void __sync_icache_dcache(pte_t pteval)
+{
+}
+#else
+extern void __sync_icache_dcache(pte_t pteval);
+#endif
+
+static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
+			      pte_t *ptep, pte_t pteval)
+{
+	unsigned long ext = 0;
+
+	if (addr < TASK_SIZE && pte_present_user(pteval)) {
+		__sync_icache_dcache(pteval);
+		ext |= PTE_EXT_NG;
+	}
+
+	set_pte_ext(ptep, pteval, ext);
+}
+
 #define PTE_BIT_FUNC(fn,op) \
 static inline pte_t pte_##fn(pte_t pte) { pte_val(pte) op; return pte; }
 
@@ -251,13 +253,13 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
  *
  *   3 3 2 2 2 2 2 2 2 2 2 2 1 1 1 1 1 1 1 1 1 1
  *   1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0
- *   <--------------- offset --------------------> <- type --> 0 0 0
+ *   <--------------- offset ----------------------> < type -> 0 0 0
  *
- * This gives us up to 63 swap files and 32GB per swap file.  Note that
+ * This gives us up to 31 swap files and 64GB per swap file.  Note that
  * the offset field is always non-zero.
  */
 #define __SWP_TYPE_SHIFT	3
-#define __SWP_TYPE_BITS		6
+#define __SWP_TYPE_BITS		5
 #define __SWP_TYPE_MASK		((1 << __SWP_TYPE_BITS) - 1)
 #define __SWP_OFFSET_SHIFT	(__SWP_TYPE_BITS + __SWP_TYPE_SHIFT)
 

arch/arm/include/asm/sched_clock.h

@@ -10,5 +10,7 @@
 
 extern void sched_clock_postinit(void);
 extern void setup_sched_clock(u32 (*read)(void), int bits, unsigned long rate);
+extern void setup_sched_clock_needs_suspend(u32 (*read)(void), int bits,
+		unsigned long rate);
 
 #endif

arch/arm/kernel/sched_clock.c

@@ -21,6 +21,8 @@ struct clock_data {
 	u32 epoch_cyc_copy;
 	u32 mult;
 	u32 shift;
+	bool suspended;
+	bool needs_suspend;
 };
 
 static void sched_clock_poll(unsigned long wrap_ticks);
@@ -49,6 +51,9 @@ static unsigned long long cyc_to_sched_clock(u32 cyc, u32 mask)
 	u64 epoch_ns;
 	u32 epoch_cyc;
 
+	if (cd.suspended)
+		return cd.epoch_ns;
+
 	/*
 	 * Load the epoch_cyc and epoch_ns atomically.  We do this by
 	 * ensuring that we always write epoch_cyc, epoch_ns and
@@ -98,6 +103,13 @@ static void sched_clock_poll(unsigned long wrap_ticks)
 	update_sched_clock();
 }
 
+void __init setup_sched_clock_needs_suspend(u32 (*read)(void), int bits,
+		unsigned long rate)
+{
+	setup_sched_clock(read, bits, rate);
+	cd.needs_suspend = true;
+}
+
 void __init setup_sched_clock(u32 (*read)(void), int bits, unsigned long rate)
 {
 	unsigned long r, w;
@@ -169,11 +181,23 @@ void __init sched_clock_postinit(void)
 static int sched_clock_suspend(void)
 {
 	sched_clock_poll(sched_clock_timer.data);
+	if (cd.needs_suspend)
+		cd.suspended = true;
 	return 0;
 }
 
+static void sched_clock_resume(void)
+{
+	if (cd.needs_suspend) {
+		cd.epoch_cyc = read_sched_clock();
+		cd.epoch_cyc_copy = cd.epoch_cyc;
+		cd.suspended = false;
+	}
+}
+
 static struct syscore_ops sched_clock_ops = {
 	.suspend = sched_clock_suspend,
+	.resume = sched_clock_resume,
 };
 
 static int __init sched_clock_syscore_init(void)

arch/arm/kernel/topology.c

@@ -321,7 +321,7 @@ void store_cpu_topology(unsigned int cpuid)
  * init_cpu_topology is called at boot when only one cpu is running
  * which prevent simultaneous write access to cpu_topology array
  */
-void init_cpu_topology(void)
+void __init init_cpu_topology(void)
 {
 	unsigned int cpu;
 

arch/arm/lib/Makefile

@@ -16,13 +16,30 @@ lib-y		:= backtrace.o changebit.o csumipv6.o csumpartial.o   \
 		   call_with_stack.o
 
 mmu-y	:= clear_user.o copy_page.o getuser.o putuser.o
-mmu-y	+= copy_from_user.o copy_to_user.o
+
+# the code in uaccess.S is not preemption safe and
+# probably faster on ARMv3 only
+ifeq ($(CONFIG_PREEMPT),y)
+  mmu-y	+= copy_from_user.o copy_to_user.o
+else
+ifneq ($(CONFIG_CPU_32v3),y)
+  mmu-y	+= copy_from_user.o copy_to_user.o
+else
+  mmu-y	+= uaccess.o
+endif
+endif
 
 # using lib_ here won't override already available weak symbols
 obj-$(CONFIG_UACCESS_WITH_MEMCPY) += uaccess_with_memcpy.o
 
-lib-$(CONFIG_MMU)		+= $(mmu-y)
-lib-y				+= io-readsw-armv4.o io-writesw-armv4.o
+lib-$(CONFIG_MMU) += $(mmu-y)
+
+ifeq ($(CONFIG_CPU_32v3),y)
+  lib-y	+= io-readsw-armv3.o io-writesw-armv3.o
+else
+  lib-y	+= io-readsw-armv4.o io-writesw-armv4.o
+endif
+
 lib-$(CONFIG_ARCH_RPC)		+= ecard.o io-acorn.o floppydma.o
 lib-$(CONFIG_ARCH_SHARK)	+= io-shark.o
 

arch/arm/lib/io-readsw-armv3.S

@@ -0,0 +1,106 @@
+/*
+ *  linux/arch/arm/lib/io-readsw-armv3.S
+ *
+ *  Copyright (C) 1995-2000 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+.Linsw_bad_alignment:
+		adr	r0, .Linsw_bad_align_msg
+		mov	r2, lr
+		b	panic
+.Linsw_bad_align_msg:
+		.asciz	"insw: bad buffer alignment (0x%p, lr=0x%08lX)\n"
+		.align
+
+.Linsw_align:	tst	r1, #1
+		bne	.Linsw_bad_alignment
+
+		ldr	r3, [r0]
+		strb	r3, [r1], #1
+		mov	r3, r3, lsr #8
+		strb	r3, [r1], #1
+
+		subs	r2, r2, #1
+		moveq	pc, lr
+
+ENTRY(__raw_readsw)
+		teq	r2, #0		@ do we have to check for the zero len?
+		moveq	pc, lr
+		tst	r1, #3
+		bne	.Linsw_align
+
+.Linsw_aligned:	mov	ip, #0xff
+		orr	ip, ip, ip, lsl #8
+		stmfd	sp!, {r4, r5, r6, lr}
+
+		subs	r2, r2, #8
+		bmi	.Lno_insw_8
+
+.Linsw_8_lp:	ldr	r3, [r0]
+		and	r3, r3, ip
+		ldr	r4, [r0]
+		orr	r3, r3, r4, lsl #16
+
+		ldr	r4, [r0]
+		and	r4, r4, ip
+		ldr	r5, [r0]
+		orr	r4, r4, r5, lsl #16
+
+		ldr	r5, [r0]
+		and	r5, r5, ip
+		ldr	r6, [r0]
+		orr	r5, r5, r6, lsl #16
+
+		ldr	r6, [r0]
+		and	r6, r6, ip
+		ldr	lr, [r0]
+		orr	r6, r6, lr, lsl #16
+
+		stmia	r1!, {r3 - r6}
+
+		subs	r2, r2, #8
+		bpl	.Linsw_8_lp
+
+		tst	r2, #7
+		ldmeqfd	sp!, {r4, r5, r6, pc}
+
+.Lno_insw_8:	tst	r2, #4
+		beq	.Lno_insw_4
+
+		ldr	r3, [r0]
+		and	r3, r3, ip
+		ldr	r4, [r0]
+		orr	r3, r3, r4, lsl #16
+
+		ldr	r4, [r0]
+		and	r4, r4, ip
+		ldr	r5, [r0]
+		orr	r4, r4, r5, lsl #16
+
+		stmia	r1!, {r3, r4}
+
+.Lno_insw_4:	tst	r2, #2
+		beq	.Lno_insw_2
+
+		ldr	r3, [r0]
+		and	r3, r3, ip
+		ldr	r4, [r0]
+		orr	r3, r3, r4, lsl #16
+
+		str	r3, [r1], #4
+
+.Lno_insw_2:	tst	r2, #1
+		ldrne	r3, [r0]
+		strneb	r3, [r1], #1
+		movne	r3, r3, lsr #8
+		strneb	r3, [r1]
+
+		ldmfd	sp!, {r4, r5, r6, pc}
+
+

arch/arm/lib/io-writesw-armv3.S

@@ -0,0 +1,126 @@
+/*
+ *  linux/arch/arm/lib/io-writesw-armv3.S
+ *
+ *  Copyright (C) 1995-2000 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+.Loutsw_bad_alignment:
+		adr	r0, .Loutsw_bad_align_msg
+		mov	r2, lr
+		b	panic
+.Loutsw_bad_align_msg:
+		.asciz	"outsw: bad buffer alignment (0x%p, lr=0x%08lX)\n"
+		.align
+
+.Loutsw_align:	tst	r1, #1
+		bne	.Loutsw_bad_alignment
+
+		add	r1, r1, #2
+
+		ldr	r3, [r1, #-4]
+		mov	r3, r3, lsr #16
+		orr	r3, r3, r3, lsl #16
+		str	r3, [r0]
+		subs	r2, r2, #1
+		moveq	pc, lr
+
+ENTRY(__raw_writesw)
+		teq	r2, #0		@ do we have to check for the zero len?
+		moveq	pc, lr
+		tst	r1, #3
+		bne	.Loutsw_align
+
+		stmfd	sp!, {r4, r5, r6, lr}
+
+		subs	r2, r2, #8
+		bmi	.Lno_outsw_8
+
+.Loutsw_8_lp:	ldmia	r1!, {r3, r4, r5, r6}
+
+		mov	ip, r3, lsl #16
+		orr	ip, ip, ip, lsr #16
+		str	ip, [r0]
+
+		mov	ip, r3, lsr #16
+		orr	ip, ip, ip, lsl #16
+		str	ip, [r0]
+
+		mov	ip, r4, lsl #16
+		orr	ip, ip, ip, lsr #16
+		str	ip, [r0]
+
+		mov	ip, r4, lsr #16
+		orr	ip, ip, ip, lsl #16
+		str	ip, [r0]
+
+		mov	ip, r5, lsl #16
+		orr	ip, ip, ip, lsr #16
+		str	ip, [r0]
+
+		mov	ip, r5, lsr #16
+		orr	ip, ip, ip, lsl #16
+		str	ip, [r0]
+
+		mov	ip, r6, lsl #16
+		orr	ip, ip, ip, lsr #16
+		str	ip, [r0]
+
+		mov	ip, r6, lsr #16
+		orr	ip, ip, ip, lsl #16
+		str	ip, [r0]
+
+		subs	r2, r2, #8
+		bpl	.Loutsw_8_lp
+
+		tst	r2, #7
+		ldmeqfd	sp!, {r4, r5, r6, pc}
+
+.Lno_outsw_8:	tst	r2, #4
+		beq	.Lno_outsw_4
+
+		ldmia	r1!, {r3, r4}
+
+		mov	ip, r3, lsl #16
+		orr	ip, ip, ip, lsr #16
+		str	ip, [r0]
+
+		mov	ip, r3, lsr #16
+		orr	ip, ip, ip, lsl #16
+		str	ip, [r0]
+
+		mov	ip, r4, lsl #16
+		orr	ip, ip, ip, lsr #16
+		str	ip, [r0]
+
+		mov	ip, r4, lsr #16
+		orr	ip, ip, ip, lsl #16
+		str	ip, [r0]
+
+.Lno_outsw_4:	tst	r2, #2
+		beq	.Lno_outsw_2
+
+		ldr	r3, [r1], #4
+
+		mov	ip, r3, lsl #16
+		orr	ip, ip, ip, lsr #16
+		str	ip, [r0]
+
+		mov	ip, r3, lsr #16
+		orr	ip, ip, ip, lsl #16
+		str	ip, [r0]
+
+.Lno_outsw_2:	tst	r2, #1
+
+		ldrne	r3, [r1]
+
+		movne	ip, r3, lsl #16
+		orrne	ip, ip, ip, lsr #16
+		strne	ip, [r0]
+
+		ldmfd	sp!, {r4, r5, r6, pc}

arch/arm/lib/uaccess.S

@@ -0,0 +1,564 @@
+/*
+ *  linux/arch/arm/lib/uaccess.S
+ *
+ *  Copyright (C) 1995, 1996,1997,1998 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ *  Routines to block copy data to/from user memory
+ *   These are highly optimised both for the 4k page size
+ *   and for various alignments.
+ */
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+#include <asm/errno.h>
+#include <asm/domain.h>
+
+		.text
+
+#define PAGE_SHIFT 12
+
+/* Prototype: int __copy_to_user(void *to, const char *from, size_t n)
+ * Purpose  : copy a block to user memory from kernel memory
+ * Params   : to   - user memory
+ *          : from - kernel memory
+ *          : n    - number of bytes to copy
+ * Returns  : Number of bytes NOT copied.
+ */
+
+.Lc2u_dest_not_aligned:
+		rsb	ip, ip, #4
+		cmp	ip, #2
+		ldrb	r3, [r1], #1
+USER(	TUSER(	strb)	r3, [r0], #1)			@ May fault
+		ldrgeb	r3, [r1], #1
+USER(	TUSER(	strgeb) r3, [r0], #1)			@ May fault
+		ldrgtb	r3, [r1], #1
+USER(	TUSER(	strgtb) r3, [r0], #1)			@ May fault
+		sub	r2, r2, ip
+		b	.Lc2u_dest_aligned
+
+ENTRY(__copy_to_user)
+		stmfd	sp!, {r2, r4 - r7, lr}
+		cmp	r2, #4
+		blt	.Lc2u_not_enough
+		ands	ip, r0, #3
+		bne	.Lc2u_dest_not_aligned
+.Lc2u_dest_aligned:
+
+		ands	ip, r1, #3
+		bne	.Lc2u_src_not_aligned
+/*
+ * Seeing as there has to be at least 8 bytes to copy, we can
+ * copy one word, and force a user-mode page fault...
+ */
+
+.Lc2u_0fupi:	subs	r2, r2, #4
+		addmi	ip, r2, #4
+		bmi	.Lc2u_0nowords
+		ldr	r3, [r1], #4
+USER(	TUSER(	str)	r3, [r0], #4)			@ May fault
+		mov	ip, r0, lsl #32 - PAGE_SHIFT	@ On each page, use a ld/st??t instruction
+		rsb	ip, ip, #0
+		movs	ip, ip, lsr #32 - PAGE_SHIFT
+		beq	.Lc2u_0fupi
+/*
+ * ip = max no. of bytes to copy before needing another "strt" insn
+ */
+		cmp	r2, ip
+		movlt	ip, r2
+		sub	r2, r2, ip
+		subs	ip, ip, #32
+		blt	.Lc2u_0rem8lp
+
+.Lc2u_0cpy8lp:	ldmia	r1!, {r3 - r6}
+		stmia	r0!, {r3 - r6}			@ Shouldnt fault
+		ldmia	r1!, {r3 - r6}
+		subs	ip, ip, #32
+		stmia	r0!, {r3 - r6}			@ Shouldnt fault
+		bpl	.Lc2u_0cpy8lp
+
+.Lc2u_0rem8lp:	cmn	ip, #16
+		ldmgeia	r1!, {r3 - r6}
+		stmgeia	r0!, {r3 - r6}			@ Shouldnt fault
+		tst	ip, #8
+		ldmneia	r1!, {r3 - r4}
+		stmneia	r0!, {r3 - r4}			@ Shouldnt fault
+		tst	ip, #4
+		ldrne	r3, [r1], #4
+	TUSER(	strne) r3, [r0], #4			@ Shouldnt fault
+		ands	ip, ip, #3
+		beq	.Lc2u_0fupi
+.Lc2u_0nowords:	teq	ip, #0
+		beq	.Lc2u_finished
+.Lc2u_nowords:	cmp	ip, #2
+		ldrb	r3, [r1], #1
+USER(	TUSER(	strb)	r3, [r0], #1)			@ May fault
+		ldrgeb	r3, [r1], #1
+USER(	TUSER(	strgeb) r3, [r0], #1)			@ May fault
+		ldrgtb	r3, [r1], #1
+USER(	TUSER(	strgtb) r3, [r0], #1)			@ May fault
+		b	.Lc2u_finished
+
+.Lc2u_not_enough:
+		movs	ip, r2
+		bne	.Lc2u_nowords
+.Lc2u_finished:	mov	r0, #0
+		ldmfd	sp!, {r2, r4 - r7, pc}
+
+.Lc2u_src_not_aligned:
+		bic	r1, r1, #3
+		ldr	r7, [r1], #4
+		cmp	ip, #2
+		bgt	.Lc2u_3fupi
+		beq	.Lc2u_2fupi
+.Lc2u_1fupi:	subs	r2, r2, #4
+		addmi	ip, r2, #4
+		bmi	.Lc2u_1nowords
+		mov	r3, r7, pull #8
+		ldr	r7, [r1], #4
+		orr	r3, r3, r7, push #24
+USER(	TUSER(	str)	r3, [r0], #4)			@ May fault
+		mov	ip, r0, lsl #32 - PAGE_SHIFT
+		rsb	ip, ip, #0
+		movs	ip, ip, lsr #32 - PAGE_SHIFT
+		beq	.Lc2u_1fupi
+		cmp	r2, ip
+		movlt	ip, r2
+		sub	r2, r2, ip
+		subs	ip, ip, #16
+		blt	.Lc2u_1rem8lp
+
+.Lc2u_1cpy8lp:	mov	r3, r7, pull #8
+		ldmia	r1!, {r4 - r7}
+		subs	ip, ip, #16
+		orr	r3, r3, r4, push #24
+		mov	r4, r4, pull #8
+		orr	r4, r4, r5, push #24
+		mov	r5, r5, pull #8
+		orr	r5, r5, r6, push #24
+		mov	r6, r6, pull #8
+		orr	r6, r6, r7, push #24
+		stmia	r0!, {r3 - r6}			@ Shouldnt fault
+		bpl	.Lc2u_1cpy8lp
+
+.Lc2u_1rem8lp:	tst	ip, #8
+		movne	r3, r7, pull #8
+		ldmneia	r1!, {r4, r7}
+		orrne	r3, r3, r4, push #24
+		movne	r4, r4, pull #8
+		orrne	r4, r4, r7, push #24
+		stmneia	r0!, {r3 - r4}			@ Shouldnt fault
+		tst	ip, #4
+		movne	r3, r7, pull #8
+		ldrne	r7, [r1], #4
+		orrne	r3, r3, r7, push #24
+	TUSER(	strne) r3, [r0], #4			@ Shouldnt fault
+		ands	ip, ip, #3
+		beq	.Lc2u_1fupi
+.Lc2u_1nowords:	mov	r3, r7, get_byte_1
+		teq	ip, #0
+		beq	.Lc2u_finished
+		cmp	ip, #2
+USER(	TUSER(	strb)	r3, [r0], #1)			@ May fault
+		movge	r3, r7, get_byte_2
+USER(	TUSER(	strgeb) r3, [r0], #1)			@ May fault
+		movgt	r3, r7, get_byte_3
+USER(	TUSER(	strgtb) r3, [r0], #1)			@ May fault
+		b	.Lc2u_finished
+
+.Lc2u_2fupi:	subs	r2, r2, #4
+		addmi	ip, r2, #4
+		bmi	.Lc2u_2nowords
+		mov	r3, r7, pull #16
+		ldr	r7, [r1], #4
+		orr	r3, r3, r7, push #16
+USER(	TUSER(	str)	r3, [r0], #4)			@ May fault
+		mov	ip, r0, lsl #32 - PAGE_SHIFT
+		rsb	ip, ip, #0
+		movs	ip, ip, lsr #32 - PAGE_SHIFT
+		beq	.Lc2u_2fupi
+		cmp	r2, ip
+		movlt	ip, r2
+		sub	r2, r2, ip
+		subs	ip, ip, #16
+		blt	.Lc2u_2rem8lp
+
+.Lc2u_2cpy8lp:	mov	r3, r7, pull #16
+		ldmia	r1!, {r4 - r7}
+		subs	ip, ip, #16
+		orr	r3, r3, r4, push #16
+		mov	r4, r4, pull #16
+		orr	r4, r4, r5, push #16
+		mov	r5, r5, pull #16
+		orr	r5, r5, r6, push #16
+		mov	r6, r6, pull #16
+		orr	r6, r6, r7, push #16
+		stmia	r0!, {r3 - r6}			@ Shouldnt fault
+		bpl	.Lc2u_2cpy8lp
+
+.Lc2u_2rem8lp:	tst	ip, #8
+		movne	r3, r7, pull #16
+		ldmneia	r1!, {r4, r7}
+		orrne	r3, r3, r4, push #16
+		movne	r4, r4, pull #16
+		orrne	r4, r4, r7, push #16
+		stmneia	r0!, {r3 - r4}			@ Shouldnt fault
+		tst	ip, #4
+		movne	r3, r7, pull #16
+		ldrne	r7, [r1], #4
+		orrne	r3, r3, r7, push #16
+	TUSER(	strne) r3, [r0], #4			@ Shouldnt fault
+		ands	ip, ip, #3
+		beq	.Lc2u_2fupi
+.Lc2u_2nowords:	mov	r3, r7, get_byte_2
+		teq	ip, #0
+		beq	.Lc2u_finished
+		cmp	ip, #2
+USER(	TUSER(	strb)	r3, [r0], #1)			@ May fault
+		movge	r3, r7, get_byte_3
+USER(	TUSER(	strgeb) r3, [r0], #1)			@ May fault
+		ldrgtb	r3, [r1], #0
+USER(	TUSER(	strgtb) r3, [r0], #1)			@ May fault
+		b	.Lc2u_finished
+
+.Lc2u_3fupi:	subs	r2, r2, #4
+		addmi	ip, r2, #4
+		bmi	.Lc2u_3nowords
+		mov	r3, r7, pull #24
+		ldr	r7, [r1], #4
+		orr	r3, r3, r7, push #8
+USER(	TUSER(	str)	r3, [r0], #4)			@ May fault
+		mov	ip, r0, lsl #32 - PAGE_SHIFT
+		rsb	ip, ip, #0
+		movs	ip, ip, lsr #32 - PAGE_SHIFT
+		beq	.Lc2u_3fupi
+		cmp	r2, ip
+		movlt	ip, r2
+		sub	r2, r2, ip
+		subs	ip, ip, #16
+		blt	.Lc2u_3rem8lp
+
+.Lc2u_3cpy8lp:	mov	r3, r7, pull #24
+		ldmia	r1!, {r4 - r7}
+		subs	ip, ip, #16
+		orr	r3, r3, r4, push #8
+		mov	r4, r4, pull #24
+		orr	r4, r4, r5, push #8
+		mov	r5, r5, pull #24
+		orr	r5, r5, r6, push #8
+		mov	r6, r6, pull #24
+		orr	r6, r6, r7, push #8
+		stmia	r0!, {r3 - r6}			@ Shouldnt fault
+		bpl	.Lc2u_3cpy8lp
+
+.Lc2u_3rem8lp:	tst	ip, #8
+		movne	r3, r7, pull #24
+		ldmneia	r1!, {r4, r7}
+		orrne	r3, r3, r4, push #8
+		movne	r4, r4, pull #24
+		orrne	r4, r4, r7, push #8
+		stmneia	r0!, {r3 - r4}			@ Shouldnt fault
+		tst	ip, #4
+		movne	r3, r7, pull #24
+		ldrne	r7, [r1], #4
+		orrne	r3, r3, r7, push #8
+	TUSER(	strne) r3, [r0], #4			@ Shouldnt fault
+		ands	ip, ip, #3
+		beq	.Lc2u_3fupi
+.Lc2u_3nowords:	mov	r3, r7, get_byte_3
+		teq	ip, #0
+		beq	.Lc2u_finished
+		cmp	ip, #2
+USER(	TUSER(	strb)	r3, [r0], #1)			@ May fault
+		ldrgeb	r3, [r1], #1
+USER(	TUSER(	strgeb) r3, [r0], #1)			@ May fault
+		ldrgtb	r3, [r1], #0
+USER(	TUSER(	strgtb) r3, [r0], #1)			@ May fault
+		b	.Lc2u_finished
+ENDPROC(__copy_to_user)
+
+		.pushsection .fixup,"ax"
+		.align	0
+9001:		ldmfd	sp!, {r0, r4 - r7, pc}
+		.popsection
+
+/* Prototype: unsigned long __copy_from_user(void *to,const void *from,unsigned long n);
+ * Purpose  : copy a block from user memory to kernel memory
+ * Params   : to   - kernel memory
+ *          : from - user memory
+ *          : n    - number of bytes to copy
+ * Returns  : Number of bytes NOT copied.
+ */
+.Lcfu_dest_not_aligned:
+		rsb	ip, ip, #4
+		cmp	ip, #2
+USER(	TUSER(	ldrb)	r3, [r1], #1)			@ May fault
+		strb	r3, [r0], #1
+USER(	TUSER(	ldrgeb) r3, [r1], #1)			@ May fault
+		strgeb	r3, [r0], #1
+USER(	TUSER(	ldrgtb) r3, [r1], #1)			@ May fault
+		strgtb	r3, [r0], #1
+		sub	r2, r2, ip
+		b	.Lcfu_dest_aligned
+
+ENTRY(__copy_from_user)
+		stmfd	sp!, {r0, r2, r4 - r7, lr}
+		cmp	r2, #4
+		blt	.Lcfu_not_enough
+		ands	ip, r0, #3
+		bne	.Lcfu_dest_not_aligned
+.Lcfu_dest_aligned:
+		ands	ip, r1, #3
+		bne	.Lcfu_src_not_aligned
+
+/*
+ * Seeing as there has to be at least 8 bytes to copy, we can
+ * copy one word, and force a user-mode page fault...
+ */
+
+.Lcfu_0fupi:	subs	r2, r2, #4
+		addmi	ip, r2, #4
+		bmi	.Lcfu_0nowords
+USER(	TUSER(	ldr)	r3, [r1], #4)
+		str	r3, [r0], #4
+		mov	ip, r1, lsl #32 - PAGE_SHIFT	@ On each page, use a ld/st??t instruction
+		rsb	ip, ip, #0
+		movs	ip, ip, lsr #32 - PAGE_SHIFT
+		beq	.Lcfu_0fupi
+/*
+ * ip = max no. of bytes to copy before needing another "strt" insn
+ */
+		cmp	r2, ip
+		movlt	ip, r2
+		sub	r2, r2, ip
+		subs	ip, ip, #32
+		blt	.Lcfu_0rem8lp
+
+.Lcfu_0cpy8lp:	ldmia	r1!, {r3 - r6}			@ Shouldnt fault
+		stmia	r0!, {r3 - r6}
+		ldmia	r1!, {r3 - r6}			@ Shouldnt fault
+		subs	ip, ip, #32
+		stmia	r0!, {r3 - r6}
+		bpl	.Lcfu_0cpy8lp
+
+.Lcfu_0rem8lp:	cmn	ip, #16
+		ldmgeia	r1!, {r3 - r6}			@ Shouldnt fault
+		stmgeia	r0!, {r3 - r6}
+		tst	ip, #8
+		ldmneia	r1!, {r3 - r4}			@ Shouldnt fault
+		stmneia	r0!, {r3 - r4}
+		tst	ip, #4
+	TUSER(	ldrne) r3, [r1], #4			@ Shouldnt fault
+		strne	r3, [r0], #4
+		ands	ip, ip, #3
+		beq	.Lcfu_0fupi
+.Lcfu_0nowords:	teq	ip, #0
+		beq	.Lcfu_finished
+.Lcfu_nowords:	cmp	ip, #2
+USER(	TUSER(	ldrb)	r3, [r1], #1)			@ May fault
+		strb	r3, [r0], #1
+USER(	TUSER(	ldrgeb) r3, [r1], #1)			@ May fault
+		strgeb	r3, [r0], #1
+USER(	TUSER(	ldrgtb) r3, [r1], #1)			@ May fault
+		strgtb	r3, [r0], #1
+		b	.Lcfu_finished
+
+.Lcfu_not_enough:
+		movs	ip, r2
+		bne	.Lcfu_nowords
+.Lcfu_finished:	mov	r0, #0
+		add	sp, sp, #8
+		ldmfd	sp!, {r4 - r7, pc}
+
+.Lcfu_src_not_aligned:
+		bic	r1, r1, #3
+USER(	TUSER(	ldr)	r7, [r1], #4)			@ May fault
+		cmp	ip, #2
+		bgt	.Lcfu_3fupi
+		beq	.Lcfu_2fupi
+.Lcfu_1fupi:	subs	r2, r2, #4
+		addmi	ip, r2, #4
+		bmi	.Lcfu_1nowords
+		mov	r3, r7, pull #8
+USER(	TUSER(	ldr)	r7, [r1], #4)			@ May fault
+		orr	r3, r3, r7, push #24
+		str	r3, [r0], #4
+		mov	ip, r1, lsl #32 - PAGE_SHIFT
+		rsb	ip, ip, #0
+		movs	ip, ip, lsr #32 - PAGE_SHIFT
+		beq	.Lcfu_1fupi
+		cmp	r2, ip
+		movlt	ip, r2
+		sub	r2, r2, ip
+		subs	ip, ip, #16
+		blt	.Lcfu_1rem8lp
+
+.Lcfu_1cpy8lp:	mov	r3, r7, pull #8
+		ldmia	r1!, {r4 - r7}			@ Shouldnt fault
+		subs	ip, ip, #16
+		orr	r3, r3, r4, push #24
+		mov	r4, r4, pull #8
+		orr	r4, r4, r5, push #24
+		mov	r5, r5, pull #8
+		orr	r5, r5, r6, push #24
+		mov	r6, r6, pull #8
+		orr	r6, r6, r7, push #24
+		stmia	r0!, {r3 - r6}
+		bpl	.Lcfu_1cpy8lp
+
+.Lcfu_1rem8lp:	tst	ip, #8
+		movne	r3, r7, pull #8
+		ldmneia	r1!, {r4, r7}			@ Shouldnt fault
+		orrne	r3, r3, r4, push #24
+		movne	r4, r4, pull #8
+		orrne	r4, r4, r7, push #24
+		stmneia	r0!, {r3 - r4}
+		tst	ip, #4
+		movne	r3, r7, pull #8
+USER(	TUSER(	ldrne) r7, [r1], #4)			@ May fault
+		orrne	r3, r3, r7, push #24
+		strne	r3, [r0], #4
+		ands	ip, ip, #3
+		beq	.Lcfu_1fupi
+.Lcfu_1nowords:	mov	r3, r7, get_byte_1
+		teq	ip, #0
+		beq	.Lcfu_finished
+		cmp	ip, #2
+		strb	r3, [r0], #1
+		movge	r3, r7, get_byte_2
+		strgeb	r3, [r0], #1
+		movgt	r3, r7, get_byte_3
+		strgtb	r3, [r0], #1
+		b	.Lcfu_finished
+
+.Lcfu_2fupi:	subs	r2, r2, #4
+		addmi	ip, r2, #4
+		bmi	.Lcfu_2nowords
+		mov	r3, r7, pull #16
+USER(	TUSER(	ldr)	r7, [r1], #4)			@ May fault
+		orr	r3, r3, r7, push #16
+		str	r3, [r0], #4
+		mov	ip, r1, lsl #32 - PAGE_SHIFT
+		rsb	ip, ip, #0
+		movs	ip, ip, lsr #32 - PAGE_SHIFT
+		beq	.Lcfu_2fupi
+		cmp	r2, ip
+		movlt	ip, r2
+		sub	r2, r2, ip
+		subs	ip, ip, #16
+		blt	.Lcfu_2rem8lp
+
+
+.Lcfu_2cpy8lp:	mov	r3, r7, pull #16
+		ldmia	r1!, {r4 - r7}			@ Shouldnt fault
+		subs	ip, ip, #16
+		orr	r3, r3, r4, push #16
+		mov	r4, r4, pull #16
+		orr	r4, r4, r5, push #16
+		mov	r5, r5, pull #16
+		orr	r5, r5, r6, push #16
+		mov	r6, r6, pull #16
+		orr	r6, r6, r7, push #16
+		stmia	r0!, {r3 - r6}
+		bpl	.Lcfu_2cpy8lp
+
+.Lcfu_2rem8lp:	tst	ip, #8
+		movne	r3, r7, pull #16
+		ldmneia	r1!, {r4, r7}			@ Shouldnt fault
+		orrne	r3, r3, r4, push #16
+		movne	r4, r4, pull #16
+		orrne	r4, r4, r7, push #16
+		stmneia	r0!, {r3 - r4}
+		tst	ip, #4
+		movne	r3, r7, pull #16
+USER(	TUSER(	ldrne) r7, [r1], #4)			@ May fault
+		orrne	r3, r3, r7, push #16
+		strne	r3, [r0], #4
+		ands	ip, ip, #3
+		beq	.Lcfu_2fupi
+.Lcfu_2nowords:	mov	r3, r7, get_byte_2
+		teq	ip, #0
+		beq	.Lcfu_finished
+		cmp	ip, #2
+		strb	r3, [r0], #1
+		movge	r3, r7, get_byte_3
+		strgeb	r3, [r0], #1
+USER(	TUSER(	ldrgtb) r3, [r1], #0)			@ May fault
+		strgtb	r3, [r0], #1
+		b	.Lcfu_finished
+
+.Lcfu_3fupi:	subs	r2, r2, #4
+		addmi	ip, r2, #4
+		bmi	.Lcfu_3nowords
+		mov	r3, r7, pull #24
+USER(	TUSER(	ldr)	r7, [r1], #4)			@ May fault
+		orr	r3, r3, r7, push #8
+		str	r3, [r0], #4
+		mov	ip, r1, lsl #32 - PAGE_SHIFT
+		rsb	ip, ip, #0
+		movs	ip, ip, lsr #32 - PAGE_SHIFT
+		beq	.Lcfu_3fupi
+		cmp	r2, ip
+		movlt	ip, r2
+		sub	r2, r2, ip
+		subs	ip, ip, #16
+		blt	.Lcfu_3rem8lp
+
+.Lcfu_3cpy8lp:	mov	r3, r7, pull #24
+		ldmia	r1!, {r4 - r7}			@ Shouldnt fault
+		orr	r3, r3, r4, push #8
+		mov	r4, r4, pull #24
+		orr	r4, r4, r5, push #8
+		mov	r5, r5, pull #24
+		orr	r5, r5, r6, push #8
+		mov	r6, r6, pull #24
+		orr	r6, r6, r7, push #8
+		stmia	r0!, {r3 - r6}
+		subs	ip, ip, #16
+		bpl	.Lcfu_3cpy8lp
+
+.Lcfu_3rem8lp:	tst	ip, #8
+		movne	r3, r7, pull #24
+		ldmneia	r1!, {r4, r7}			@ Shouldnt fault
+		orrne	r3, r3, r4, push #8
+		movne	r4, r4, pull #24
+		orrne	r4, r4, r7, push #8
+		stmneia	r0!, {r3 - r4}
+		tst	ip, #4
+		movne	r3, r7, pull #24
+USER(	TUSER(	ldrne) r7, [r1], #4)			@ May fault
+		orrne	r3, r3, r7, push #8
+		strne	r3, [r0], #4
+		ands	ip, ip, #3
+		beq	.Lcfu_3fupi
+.Lcfu_3nowords:	mov	r3, r7, get_byte_3
+		teq	ip, #0
+		beq	.Lcfu_finished
+		cmp	ip, #2
+		strb	r3, [r0], #1
+USER(	TUSER(	ldrgeb) r3, [r1], #1)			@ May fault
+		strgeb	r3, [r0], #1
+USER(	TUSER(	ldrgtb) r3, [r1], #1)			@ May fault
+		strgtb	r3, [r0], #1
+		b	.Lcfu_finished
+ENDPROC(__copy_from_user)
+
+		.pushsection .fixup,"ax"
+		.align	0
+		/*
+		 * We took an exception.  r0 contains a pointer to
+		 * the byte not copied.
+		 */
+9001:		ldr	r2, [sp], #4			@ void *to
+		sub	r2, r0, r2			@ bytes copied
+		ldr	r1, [sp], #4			@ unsigned long count
+		subs	r4, r1, r2			@ bytes left to copy
+		movne	r1, r4
+		blne	__memzero
+		mov	r0, r4
+		ldmfd	sp!, {r4 - r7, pc}
+		.popsection
+

arch/arm/mm/flush.c

@@ -231,8 +231,6 @@ void __sync_icache_dcache(pte_t pteval)
 	struct page *page;
 	struct address_space *mapping;
 
-	if (!pte_present_user(pteval))
-		return;
 	if (cache_is_vipt_nonaliasing() && !pte_exec(pteval))
 		/* only flush non-aliasing VIPT caches for exec mappings */
 		return;

arch/arm/mm/tlb-v7.S

@@ -38,10 +38,10 @@ ENTRY(v7wbi_flush_user_tlb_range)
 	dsb
 	mov	r0, r0, lsr #PAGE_SHIFT		@ align address
 	mov	r1, r1, lsr #PAGE_SHIFT
-#ifdef CONFIG_ARM_ERRATA_720789
-	mov	r3, #0
-#else
 	asid	r3, r3				@ mask ASID
+#ifdef CONFIG_ARM_ERRATA_720789
+	ALT_SMP(W(mov)	r3, #0	)
+	ALT_UP(W(nop)		)
 #endif
 	orr	r0, r3, r0, lsl #PAGE_SHIFT	@ Create initial MVA
 	mov	r1, r1, lsl #PAGE_SHIFT

arch/arm/vfp/vfpmodule.c

@@ -719,8 +719,10 @@ static int __init vfp_init(void)
 			if ((fmrx(MVFR1) & 0x000fff00) == 0x00011100)
 				elf_hwcap |= HWCAP_NEON;
 #endif
+#ifdef CONFIG_VFPv3
 			if ((fmrx(MVFR1) & 0xf0000000) == 0x10000000)
 				elf_hwcap |= HWCAP_VFPv4;
+#endif
 		}
 	}
 	return 0;

arch/c6x/Kconfig

@@ -6,6 +6,7 @@
 config C6X
 	def_bool y
 	select CLKDEV_LOOKUP
+	select GENERIC_ATOMIC64
 	select GENERIC_IRQ_SHOW
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_DMA_API_DEBUG

arch/c6x/include/asm/cache.h

@@ -1,7 +1,7 @@
 /*
  *  Port on Texas Instruments TMS320C6x architecture
  *
- *  Copyright (C) 2005, 2006, 2009, 2010 Texas Instruments Incorporated
+ *  Copyright (C) 2005, 2006, 2009, 2010, 2012 Texas Instruments Incorporated
  *  Author: Aurelien Jacquiot (aurelien.jacquiot@jaluna.com)
  *
  *  This program is free software; you can redistribute it and/or modify
@@ -16,9 +16,14 @@
 /*
  * Cache line size
  */
-#define L1D_CACHE_BYTES   64
-#define L1P_CACHE_BYTES   32
-#define L2_CACHE_BYTES	  128
+#define L1D_CACHE_SHIFT   6
+#define L1D_CACHE_BYTES   (1 << L1D_CACHE_SHIFT)
+
+#define L1P_CACHE_SHIFT   5
+#define L1P_CACHE_BYTES   (1 << L1P_CACHE_SHIFT)
+
+#define L2_CACHE_SHIFT    7
+#define L2_CACHE_BYTES    (1 << L2_CACHE_SHIFT)
 
 /*
  * L2 used as cache
@@ -29,7 +34,8 @@
  * For practical reasons the L1_CACHE_BYTES defines should not be smaller than
  * the L2 line size
  */
-#define L1_CACHE_BYTES        L2_CACHE_BYTES
+#define L1_CACHE_SHIFT        L2_CACHE_SHIFT
+#define L1_CACHE_BYTES        (1 << L1_CACHE_SHIFT)
 
 #define L2_CACHE_ALIGN_LOW(x) \
 	(((x) & ~(L2_CACHE_BYTES - 1)))

arch/ia64/configs/generic_defconfig

@@ -234,5 +234,4 @@ CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_MD5=y
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
 CONFIG_CRC_T10DIF=y
-CONFIG_MISC_DEVICES=y
 CONFIG_INTEL_IOMMU=y

arch/ia64/configs/gensparse_defconfig

@@ -209,4 +209,3 @@ CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_KERNEL=y
 CONFIG_DEBUG_MUTEXES=y
 CONFIG_CRYPTO_MD5=y
-CONFIG_MISC_DEVICES=y

arch/m68k/Kconfig

@@ -5,6 +5,7 @@ config M68K
 	select HAVE_AOUT if MMU
 	select HAVE_GENERIC_HARDIRQS
 	select GENERIC_IRQ_SHOW
+	select GENERIC_ATOMIC64
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG if RMW_INSNS
 	select GENERIC_CPU_DEVICES
 	select GENERIC_STRNCPY_FROM_USER if MMU

arch/m68k/Kconfig.cpu

@@ -28,6 +28,7 @@ config COLDFIRE
 	select CPU_HAS_NO_BITFIELDS
 	select CPU_HAS_NO_MULDIV64
 	select GENERIC_CSUM
+	select HAVE_CLK
 
 endchoice
 
@@ -58,7 +59,6 @@ config MCPU32
 config M68020
 	bool "68020 support"
 	depends on MMU
-	select GENERIC_ATOMIC64
 	select CPU_HAS_ADDRESS_SPACES
 	help
 	  If you anticipate running this kernel on a computer with a MC68020
@@ -69,7 +69,6 @@ config M68020
 config M68030
 	bool "68030 support"
 	depends on MMU && !MMU_SUN3
-	select GENERIC_ATOMIC64
 	select CPU_HAS_ADDRESS_SPACES
 	help
 	  If you anticipate running this kernel on a computer with a MC68030
@@ -79,7 +78,6 @@ config M68030
 config M68040
 	bool "68040 support"
 	depends on MMU && !MMU_SUN3
-	select GENERIC_ATOMIC64
 	select CPU_HAS_ADDRESS_SPACES
 	help
 	  If you anticipate running this kernel on a computer with a MC68LC040
@@ -90,7 +88,6 @@ config M68040
 config M68060
 	bool "68060 support"
 	depends on MMU && !MMU_SUN3
-	select GENERIC_ATOMIC64
 	select CPU_HAS_ADDRESS_SPACES
 	help
 	  If you anticipate running this kernel on a computer with a MC68060

arch/x86/Makefile

@@ -27,6 +27,10 @@ ifeq ($(CONFIG_X86_32),y)
 
         KBUILD_CFLAGS += -msoft-float -mregparm=3 -freg-struct-return
 
+        # Never want PIC in a 32-bit kernel, prevent breakage with GCC built
+        # with nonstandard options
+        KBUILD_CFLAGS += -fno-pic
+
         # prevent gcc from keeping the stack 16 byte aligned
         KBUILD_CFLAGS += $(call cc-option,-mpreferred-stack-boundary=2)
 

arch/x86/boot/Makefile

@@ -57,7 +57,7 @@ KBUILD_CFLAGS	:= $(LINUXINCLUDE) -g -Os -D_SETUP -D__KERNEL__ \
 		   -Wall -Wstrict-prototypes \
 		   -march=i386 -mregparm=3 \
 		   -include $(srctree)/$(src)/code16gcc.h \
-		   -fno-strict-aliasing -fomit-frame-pointer \
+		   -fno-strict-aliasing -fomit-frame-pointer -fno-pic \
 		   $(call cc-option, -ffreestanding) \
 		   $(call cc-option, -fno-toplevel-reorder,\
 			$(call cc-option, -fno-unit-at-a-time)) \

arch/x86/kernel/apic/io_apic.c

@@ -1356,6 +1356,16 @@ static void setup_ioapic_irq(unsigned int irq, struct irq_cfg *cfg,
 	if (!IO_APIC_IRQ(irq))
 		return;
 
+	/*
+	 * For legacy irqs, cfg->domain starts with cpu 0. Now that IO-APIC
+	 * can handle this irq and the apic driver is finialized at this point,
+	 * update the cfg->domain.
+	 */
+	if (irq < legacy_pic->nr_legacy_irqs &&
+	    cpumask_equal(cfg->domain, cpumask_of(0)))
+		apic->vector_allocation_domain(0, cfg->domain,
+					       apic->target_cpus());
+
 	if (assign_irq_vector(irq, cfg, apic->target_cpus()))
 		return;
 

arch/x86/kernel/cpu/common.c

@@ -144,6 +144,8 @@ static int __init x86_xsave_setup(char *s)
 {
 	setup_clear_cpu_cap(X86_FEATURE_XSAVE);
 	setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
+	setup_clear_cpu_cap(X86_FEATURE_AVX);
+	setup_clear_cpu_cap(X86_FEATURE_AVX2);
 	return 1;
 }
 __setup("noxsave", x86_xsave_setup);

arch/x86/kernel/cpu/perf_event_intel.c

@@ -1522,8 +1522,16 @@ static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr)
 	arr[0].msr = MSR_CORE_PERF_GLOBAL_CTRL;
 	arr[0].host = x86_pmu.intel_ctrl & ~cpuc->intel_ctrl_guest_mask;
 	arr[0].guest = x86_pmu.intel_ctrl & ~cpuc->intel_ctrl_host_mask;
+	/*
+	 * If PMU counter has PEBS enabled it is not enough to disable counter
+	 * on a guest entry since PEBS memory write can overshoot guest entry
+	 * and corrupt guest memory. Disabling PEBS solves the problem.
+	 */
+	arr[1].msr = MSR_IA32_PEBS_ENABLE;
+	arr[1].host = cpuc->pebs_enabled;
+	arr[1].guest = 0;
 
-	*nr = 1;
+	*nr = 2;
 	return arr;
 }
 

arch/x86/kernel/cpu/perf_event_intel_uncore.c

@@ -796,7 +796,6 @@ static struct intel_uncore_type *nhm_msr_uncores[] = {
 
 DEFINE_UNCORE_FORMAT_ATTR(event5, event, "config:1-5");
 DEFINE_UNCORE_FORMAT_ATTR(counter, counter, "config:6-7");
-DEFINE_UNCORE_FORMAT_ATTR(mm_cfg, mm_cfg, "config:63");
 DEFINE_UNCORE_FORMAT_ATTR(match, match, "config1:0-63");
 DEFINE_UNCORE_FORMAT_ATTR(mask, mask, "config2:0-63");
 
@@ -902,16 +901,21 @@ static struct attribute_group nhmex_uncore_cbox_format_group = {
 	.attrs = nhmex_uncore_cbox_formats_attr,
 };
 
+/* msr offset for each instance of cbox */
+static unsigned nhmex_cbox_msr_offsets[] = {
+	0x0, 0x80, 0x40, 0xc0, 0x20, 0xa0, 0x60, 0xe0, 0x240, 0x2c0,
+};
+
 static struct intel_uncore_type nhmex_uncore_cbox = {
 	.name			= "cbox",
 	.num_counters		= 6,
-	.num_boxes		= 8,
+	.num_boxes		= 10,
 	.perf_ctr_bits		= 48,
 	.event_ctl		= NHMEX_C0_MSR_PMON_EV_SEL0,
 	.perf_ctr		= NHMEX_C0_MSR_PMON_CTR0,
 	.event_mask		= NHMEX_PMON_RAW_EVENT_MASK,
 	.box_ctl		= NHMEX_C0_MSR_PMON_GLOBAL_CTL,
-	.msr_offset		= NHMEX_C_MSR_OFFSET,
+	.msr_offsets		= nhmex_cbox_msr_offsets,
 	.pair_ctr_ctl		= 1,
 	.ops			= &nhmex_uncore_ops,
 	.format_group		= &nhmex_uncore_cbox_format_group
@@ -1032,24 +1036,22 @@ static struct intel_uncore_type nhmex_uncore_bbox = {
 
 static int nhmex_sbox_hw_config(struct intel_uncore_box *box, struct perf_event *event)
 {
-	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
-	struct hw_perf_event_extra *reg2 = &event->hw.branch_reg;
+	struct hw_perf_event *hwc = &event->hw;
+	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+	struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
 
-	if (event->attr.config & NHMEX_S_PMON_MM_CFG_EN) {
-		reg1->config = event->attr.config1;
-		reg2->config = event->attr.config2;
-	} else {
-		reg1->config = ~0ULL;
-		reg2->config = ~0ULL;
-	}
+	/* only TO_R_PROG_EV event uses the match/mask register */
+	if ((hwc->config & NHMEX_PMON_CTL_EV_SEL_MASK) !=
+	    NHMEX_S_EVENT_TO_R_PROG_EV)
+		return 0;
 
 	if (box->pmu->pmu_idx == 0)
 		reg1->reg = NHMEX_S0_MSR_MM_CFG;
 	else
 		reg1->reg = NHMEX_S1_MSR_MM_CFG;
-
 	reg1->idx = 0;
-
+	reg1->config = event->attr.config1;
+	reg2->config = event->attr.config2;
 	return 0;
 }
 
@@ -1059,8 +1061,8 @@ static void nhmex_sbox_msr_enable_event(struct intel_uncore_box *box, struct per
 	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
 	struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
 
-	wrmsrl(reg1->reg, 0);
-	if (reg1->config != ~0ULL || reg2->config != ~0ULL) {
+	if (reg1->idx != EXTRA_REG_NONE) {
+		wrmsrl(reg1->reg, 0);
 		wrmsrl(reg1->reg + 1, reg1->config);
 		wrmsrl(reg1->reg + 2, reg2->config);
 		wrmsrl(reg1->reg, NHMEX_S_PMON_MM_CFG_EN);
@@ -1074,7 +1076,6 @@ static struct attribute *nhmex_uncore_sbox_formats_attr[] = {
 	&format_attr_edge.attr,
 	&format_attr_inv.attr,
 	&format_attr_thresh8.attr,
-	&format_attr_mm_cfg.attr,
 	&format_attr_match.attr,
 	&format_attr_mask.attr,
 	NULL,
@@ -1142,6 +1143,9 @@ static struct extra_reg nhmex_uncore_mbox_extra_regs[] = {
 	EVENT_EXTRA_END
 };
 
+/* Nehalem-EX or Westmere-EX ? */
+bool uncore_nhmex;
+
 static bool nhmex_mbox_get_shared_reg(struct intel_uncore_box *box, int idx, u64 config)
 {
 	struct intel_uncore_extra_reg *er;
@@ -1171,18 +1175,29 @@ static bool nhmex_mbox_get_shared_reg(struct intel_uncore_box *box, int idx, u64
 		return false;
 
 	/* mask of the shared fields */
-	mask = NHMEX_M_PMON_ZDP_CTL_FVC_MASK;
+	if (uncore_nhmex)
+		mask = NHMEX_M_PMON_ZDP_CTL_FVC_MASK;
+	else
+		mask = WSMEX_M_PMON_ZDP_CTL_FVC_MASK;
 	er = &box->shared_regs[EXTRA_REG_NHMEX_M_ZDP_CTL_FVC];
 
 	raw_spin_lock_irqsave(&er->lock, flags);
 	/* add mask of the non-shared field if it's in use */
-	if (__BITS_VALUE(atomic_read(&er->ref), idx, 8))
-		mask |= NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
+	if (__BITS_VALUE(atomic_read(&er->ref), idx, 8)) {
+		if (uncore_nhmex)
+			mask |= NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
+		else
+			mask |= WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
+	}
 
 	if (!atomic_read(&er->ref) || !((er->config ^ config) & mask)) {
 		atomic_add(1 << (idx * 8), &er->ref);
-		mask = NHMEX_M_PMON_ZDP_CTL_FVC_MASK |
-			NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
+		if (uncore_nhmex)
+			mask = NHMEX_M_PMON_ZDP_CTL_FVC_MASK |
+				NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
+		else
+			mask = WSMEX_M_PMON_ZDP_CTL_FVC_MASK |
+				WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
 		er->config &= ~mask;
 		er->config |= (config & mask);
 		ret = true;
@@ -1216,7 +1231,10 @@ u64 nhmex_mbox_alter_er(struct perf_event *event, int new_idx, bool modify)
 
 	/* get the non-shared control bits and shift them */
 	idx = orig_idx - EXTRA_REG_NHMEX_M_ZDP_CTL_FVC;
-	config &= NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
+	if (uncore_nhmex)
+		config &= NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
+	else
+		config &= WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
 	if (new_idx > orig_idx) {
 		idx = new_idx - orig_idx;
 		config <<= 3 * idx;
@@ -1226,6 +1244,10 @@ u64 nhmex_mbox_alter_er(struct perf_event *event, int new_idx, bool modify)
 	}
 
 	/* add the shared control bits back */
+	if (uncore_nhmex)
+		config |= NHMEX_M_PMON_ZDP_CTL_FVC_MASK & reg1->config;
+	else
+		config |= WSMEX_M_PMON_ZDP_CTL_FVC_MASK & reg1->config;
 	config |= NHMEX_M_PMON_ZDP_CTL_FVC_MASK & reg1->config;
 	if (modify) {
 		/* adjust the main event selector */
@@ -1264,7 +1286,8 @@ again:
 	}
 
 	/* for the match/mask registers */
-	if ((uncore_box_is_fake(box) || !reg2->alloc) &&
+	if (reg2->idx != EXTRA_REG_NONE &&
+	    (uncore_box_is_fake(box) || !reg2->alloc) &&
 	    !nhmex_mbox_get_shared_reg(box, reg2->idx, reg2->config))
 		goto fail;
 
@@ -1278,7 +1301,8 @@ again:
 		if (idx[0] != 0xff && idx[0] != __BITS_VALUE(reg1->idx, 0, 8))
 			nhmex_mbox_alter_er(event, idx[0], true);
 		reg1->alloc |= alloc;
-		reg2->alloc = 1;
+		if (reg2->idx != EXTRA_REG_NONE)
+			reg2->alloc = 1;
 	}
 	return NULL;
 fail:
@@ -1342,9 +1366,6 @@ static int nhmex_mbox_hw_config(struct intel_uncore_box *box, struct perf_event
 	struct extra_reg *er;
 	unsigned msr;
 	int reg_idx = 0;
-
-	if (WARN_ON_ONCE(reg1->idx != -1))
-		return -EINVAL;
 	/*
 	 * The mbox events may require 2 extra MSRs at the most. But only
 	 * the lower 32 bits in these MSRs are significant, so we can use
@@ -1355,11 +1376,6 @@ static int nhmex_mbox_hw_config(struct intel_uncore_box *box, struct perf_event
 			continue;
 		if (event->attr.config1 & ~er->valid_mask)
 			return -EINVAL;
-		if (er->idx == __BITS_VALUE(reg1->idx, 0, 8) ||
-		    er->idx == __BITS_VALUE(reg1->idx, 1, 8))
-			continue;
-		if (WARN_ON_ONCE(reg_idx >= 2))
-			return -EINVAL;
 
 		msr = er->msr + type->msr_offset * box->pmu->pmu_idx;
 		if (WARN_ON_ONCE(msr >= 0xffff || er->idx >= 0xff))
@@ -1368,6 +1384,8 @@ static int nhmex_mbox_hw_config(struct intel_uncore_box *box, struct perf_event
 		/* always use the 32~63 bits to pass the PLD config */
 		if (er->idx == EXTRA_REG_NHMEX_M_PLD)
 			reg_idx = 1;
+		else if (WARN_ON_ONCE(reg_idx > 0))
+			return -EINVAL;
 
 		reg1->idx &= ~(0xff << (reg_idx * 8));
 		reg1->reg &= ~(0xffff << (reg_idx * 16));
@@ -1376,17 +1394,21 @@ static int nhmex_mbox_hw_config(struct intel_uncore_box *box, struct perf_event
 		reg1->config = event->attr.config1;
 		reg_idx++;
 	}
-	/* use config2 to pass the filter config */
-	reg2->idx = EXTRA_REG_NHMEX_M_FILTER;
-	if (event->attr.config2 & NHMEX_M_PMON_MM_CFG_EN)
-		reg2->config = event->attr.config2;
-	else
-		reg2->config = ~0ULL;
-	if (box->pmu->pmu_idx == 0)
-		reg2->reg = NHMEX_M0_MSR_PMU_MM_CFG;
-	else
-		reg2->reg = NHMEX_M1_MSR_PMU_MM_CFG;
-
+	/*
+	 * The mbox only provides ability to perform address matching
+	 * for the PLD events.
+	 */
+	if (reg_idx == 2) {
+		reg2->idx = EXTRA_REG_NHMEX_M_FILTER;
+		if (event->attr.config2 & NHMEX_M_PMON_MM_CFG_EN)
+			reg2->config = event->attr.config2;
+		else
+			reg2->config = ~0ULL;
+		if (box->pmu->pmu_idx == 0)
+			reg2->reg = NHMEX_M0_MSR_PMU_MM_CFG;
+		else
+			reg2->reg = NHMEX_M1_MSR_PMU_MM_CFG;
+	}
 	return 0;
 }
 
@@ -1422,34 +1444,36 @@ static void nhmex_mbox_msr_enable_event(struct intel_uncore_box *box, struct per
 		wrmsrl(__BITS_VALUE(reg1->reg, 1, 16),
 			nhmex_mbox_shared_reg_config(box, idx));
 
-	wrmsrl(reg2->reg, 0);
-	if (reg2->config != ~0ULL) {
-		wrmsrl(reg2->reg + 1,
-			reg2->config & NHMEX_M_PMON_ADDR_MATCH_MASK);
-		wrmsrl(reg2->reg + 2, NHMEX_M_PMON_ADDR_MASK_MASK &
-			(reg2->config >> NHMEX_M_PMON_ADDR_MASK_SHIFT));
-		wrmsrl(reg2->reg, NHMEX_M_PMON_MM_CFG_EN);
+	if (reg2->idx != EXTRA_REG_NONE) {
+		wrmsrl(reg2->reg, 0);
+		if (reg2->config != ~0ULL) {
+			wrmsrl(reg2->reg + 1,
+				reg2->config & NHMEX_M_PMON_ADDR_MATCH_MASK);
+			wrmsrl(reg2->reg + 2, NHMEX_M_PMON_ADDR_MASK_MASK &
+				(reg2->config >> NHMEX_M_PMON_ADDR_MASK_SHIFT));
+			wrmsrl(reg2->reg, NHMEX_M_PMON_MM_CFG_EN);
+		}
 	}
 
 	wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT0);
 }
 
-DEFINE_UNCORE_FORMAT_ATTR(count_mode,	count_mode,	"config:2-3");
-DEFINE_UNCORE_FORMAT_ATTR(storage_mode, storage_mode,	"config:4-5");
-DEFINE_UNCORE_FORMAT_ATTR(wrap_mode,	wrap_mode,	"config:6");
-DEFINE_UNCORE_FORMAT_ATTR(flag_mode,	flag_mode,	"config:7");
-DEFINE_UNCORE_FORMAT_ATTR(inc_sel,	inc_sel,	"config:9-13");
-DEFINE_UNCORE_FORMAT_ATTR(set_flag_sel,	set_flag_sel,	"config:19-21");
-DEFINE_UNCORE_FORMAT_ATTR(filter_cfg,	filter_cfg,	"config2:63");
-DEFINE_UNCORE_FORMAT_ATTR(filter_match,	filter_match,	"config2:0-33");
-DEFINE_UNCORE_FORMAT_ATTR(filter_mask,	filter_mask,	"config2:34-61");
-DEFINE_UNCORE_FORMAT_ATTR(dsp,		dsp,		"config1:0-31");
-DEFINE_UNCORE_FORMAT_ATTR(thr,		thr,		"config1:0-31");
-DEFINE_UNCORE_FORMAT_ATTR(fvc,		fvc,		"config1:0-31");
-DEFINE_UNCORE_FORMAT_ATTR(pgt,		pgt,		"config1:0-31");
-DEFINE_UNCORE_FORMAT_ATTR(map,		map,		"config1:0-31");
-DEFINE_UNCORE_FORMAT_ATTR(iss,		iss,		"config1:0-31");
-DEFINE_UNCORE_FORMAT_ATTR(pld,		pld,		"config1:32-63");
+DEFINE_UNCORE_FORMAT_ATTR(count_mode,		count_mode,	"config:2-3");
+DEFINE_UNCORE_FORMAT_ATTR(storage_mode,		storage_mode,	"config:4-5");
+DEFINE_UNCORE_FORMAT_ATTR(wrap_mode,		wrap_mode,	"config:6");
+DEFINE_UNCORE_FORMAT_ATTR(flag_mode,		flag_mode,	"config:7");
+DEFINE_UNCORE_FORMAT_ATTR(inc_sel,		inc_sel,	"config:9-13");
+DEFINE_UNCORE_FORMAT_ATTR(set_flag_sel,		set_flag_sel,	"config:19-21");
+DEFINE_UNCORE_FORMAT_ATTR(filter_cfg_en,	filter_cfg_en,	"config2:63");
+DEFINE_UNCORE_FORMAT_ATTR(filter_match,		filter_match,	"config2:0-33");
+DEFINE_UNCORE_FORMAT_ATTR(filter_mask,		filter_mask,	"config2:34-61");
+DEFINE_UNCORE_FORMAT_ATTR(dsp,			dsp,		"config1:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(thr,			thr,		"config1:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(fvc,			fvc,		"config1:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(pgt,			pgt,		"config1:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(map,			map,		"config1:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(iss,			iss,		"config1:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(pld,			pld,		"config1:32-63");
 
 static struct attribute *nhmex_uncore_mbox_formats_attr[] = {
 	&format_attr_count_mode.attr,
@@ -1458,7 +1482,7 @@ static struct attribute *nhmex_uncore_mbox_formats_attr[] = {
 	&format_attr_flag_mode.attr,
 	&format_attr_inc_sel.attr,
 	&format_attr_set_flag_sel.attr,
-	&format_attr_filter_cfg.attr,
+	&format_attr_filter_cfg_en.attr,
 	&format_attr_filter_match.attr,
 	&format_attr_filter_mask.attr,
 	&format_attr_dsp.attr,
@@ -1482,6 +1506,12 @@ static struct uncore_event_desc nhmex_uncore_mbox_events[] = {
 	{ /* end: all zeroes */ },
 };
 
+static struct uncore_event_desc wsmex_uncore_mbox_events[] = {
+	INTEL_UNCORE_EVENT_DESC(bbox_cmds_read, "inc_sel=0xd,fvc=0x5000"),
+	INTEL_UNCORE_EVENT_DESC(bbox_cmds_write, "inc_sel=0xd,fvc=0x5040"),
+	{ /* end: all zeroes */ },
+};
+
 static struct intel_uncore_ops nhmex_uncore_mbox_ops = {
 	NHMEX_UNCORE_OPS_COMMON_INIT(),
 	.enable_event	= nhmex_mbox_msr_enable_event,
@@ -1513,7 +1543,7 @@ void nhmex_rbox_alter_er(struct intel_uncore_box *box, struct perf_event *event)
 	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
 	int port;
 
-	/* adjust the main event selector */
+	/* adjust the main event selector and extra register index */
 	if (reg1->idx % 2) {
 		reg1->idx--;
 		hwc->config -= 1 << NHMEX_R_PMON_CTL_EV_SEL_SHIFT;
@@ -1522,29 +1552,17 @@ void nhmex_rbox_alter_er(struct intel_uncore_box *box, struct perf_event *event)
 		hwc->config += 1 << NHMEX_R_PMON_CTL_EV_SEL_SHIFT;
 	}
 
-	/* adjust address or config of extra register */
+	/* adjust extra register config */
 	port = reg1->idx / 6 + box->pmu->pmu_idx * 4;
 	switch (reg1->idx % 6) {
-	case 0:
-		reg1->reg = NHMEX_R_MSR_PORTN_IPERF_CFG0(port);
-		break;
-	case 1:
-		reg1->reg = NHMEX_R_MSR_PORTN_IPERF_CFG1(port);
-		break;
 	case 2:
-		/* the 8~15 bits to the 0~7 bits */
+		/* shift the 8~15 bits to the 0~7 bits */
 		reg1->config >>= 8;
 		break;
 	case 3:
-		/* the 0~7 bits to the 8~15 bits */
+		/* shift the 0~7 bits to the 8~15 bits */
 		reg1->config <<= 8;
 		break;
-	case 4:
-		reg1->reg = NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(port);
-		break;
-	case 5:
-		reg1->reg = NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(port);
-		break;
 	};
 }
 
@@ -1671,7 +1689,7 @@ static int nhmex_rbox_hw_config(struct intel_uncore_box *box, struct perf_event
 	struct hw_perf_event *hwc = &event->hw;
 	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
 	struct hw_perf_event_extra *reg2 = &event->hw.branch_reg;
-	int port, idx;
+	int idx;
 
 	idx = (event->hw.config & NHMEX_R_PMON_CTL_EV_SEL_MASK) >>
 		NHMEX_R_PMON_CTL_EV_SEL_SHIFT;
@@ -1681,27 +1699,11 @@ static int nhmex_rbox_hw_config(struct intel_uncore_box *box, struct perf_event
 	reg1->idx = idx;
 	reg1->config = event->attr.config1;
 
-	port = idx / 6 + box->pmu->pmu_idx * 4;
-	idx %= 6;
-	switch (idx) {
-	case 0:
-		reg1->reg = NHMEX_R_MSR_PORTN_IPERF_CFG0(port);
-		break;
-	case 1:
-		reg1->reg = NHMEX_R_MSR_PORTN_IPERF_CFG1(port);
-		break;
-	case 2:
-	case 3:
-		reg1->reg = NHMEX_R_MSR_PORTN_QLX_CFG(port);
-		break;
+	switch (idx % 6) {
 	case 4:
 	case 5:
-		if (idx == 4)
-			reg1->reg = NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(port);
-		else
-			reg1->reg = NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(port);
-		reg2->config = event->attr.config2;
 		hwc->config |= event->attr.config & (~0ULL << 32);
+		reg2->config = event->attr.config2;
 		break;
 	};
 	return 0;
@@ -1727,28 +1729,34 @@ static void nhmex_rbox_msr_enable_event(struct intel_uncore_box *box, struct per
 	struct hw_perf_event *hwc = &event->hw;
 	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
 	struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
-	int idx, er_idx;
+	int idx, port;
 
-	idx = reg1->idx % 6;
-	er_idx = idx;
-	if (er_idx > 2)
-		er_idx--;
-	er_idx += (reg1->idx / 6) * 5;
+	idx = reg1->idx;
+	port = idx / 6 + box->pmu->pmu_idx * 4;
 
-	switch (idx) {
+	switch (idx % 6) {
 	case 0:
+		wrmsrl(NHMEX_R_MSR_PORTN_IPERF_CFG0(port), reg1->config);
+		break;
 	case 1:
-		wrmsrl(reg1->reg, reg1->config);
+		wrmsrl(NHMEX_R_MSR_PORTN_IPERF_CFG1(port), reg1->config);
 		break;
 	case 2:
 	case 3:
-		wrmsrl(reg1->reg, nhmex_rbox_shared_reg_config(box, er_idx));
+		wrmsrl(NHMEX_R_MSR_PORTN_QLX_CFG(port),
+			nhmex_rbox_shared_reg_config(box, 2 + (idx / 6) * 5));
 		break;
 	case 4:
+		wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(port),
+			hwc->config >> 32);
+		wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET1_MATCH(port), reg1->config);
+		wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET1_MASK(port), reg2->config);
+		break;
 	case 5:
-		wrmsrl(reg1->reg, reg1->config);
-		wrmsrl(reg1->reg + 1, hwc->config >> 32);
-		wrmsrl(reg1->reg + 2, reg2->config);
+		wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(port),
+			hwc->config >> 32);
+		wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET2_MATCH(port), reg1->config);
+		wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET2_MASK(port), reg2->config);
 		break;
 	};
 
@@ -1756,8 +1764,8 @@ static void nhmex_rbox_msr_enable_event(struct intel_uncore_box *box, struct per
 		(hwc->config & NHMEX_R_PMON_CTL_EV_SEL_MASK));
 }
 
-DEFINE_UNCORE_FORMAT_ATTR(xbr_match, xbr_match, "config:32-63");
-DEFINE_UNCORE_FORMAT_ATTR(xbr_mm_cfg, xbr_mm_cfg, "config1:0-63");
+DEFINE_UNCORE_FORMAT_ATTR(xbr_mm_cfg, xbr_mm_cfg, "config:32-63");
+DEFINE_UNCORE_FORMAT_ATTR(xbr_match, xbr_match, "config1:0-63");
 DEFINE_UNCORE_FORMAT_ATTR(xbr_mask, xbr_mask, "config2:0-63");
 DEFINE_UNCORE_FORMAT_ATTR(qlx_cfg, qlx_cfg, "config1:0-15");
 DEFINE_UNCORE_FORMAT_ATTR(iperf_cfg, iperf_cfg, "config1:0-31");
@@ -2303,6 +2311,7 @@ int uncore_pmu_event_init(struct perf_event *event)
 	event->hw.idx = -1;
 	event->hw.last_tag = ~0ULL;
 	event->hw.extra_reg.idx = EXTRA_REG_NONE;
+	event->hw.branch_reg.idx = EXTRA_REG_NONE;
 
 	if (event->attr.config == UNCORE_FIXED_EVENT) {
 		/* no fixed counter */
@@ -2373,7 +2382,7 @@ static void __init uncore_type_exit(struct intel_uncore_type *type)
 	type->attr_groups[1] = NULL;
 }
 
-static void uncore_types_exit(struct intel_uncore_type **types)
+static void __init uncore_types_exit(struct intel_uncore_type **types)
 {
 	int i;
 	for (i = 0; types[i]; i++)
@@ -2814,7 +2823,13 @@ static int __init uncore_cpu_init(void)
 			snbep_uncore_cbox.num_boxes = max_cores;
 		msr_uncores = snbep_msr_uncores;
 		break;
-	case 46:
+	case 46: /* Nehalem-EX */
+		uncore_nhmex = true;
+	case 47: /* Westmere-EX aka. Xeon E7 */
+		if (!uncore_nhmex)
+			nhmex_uncore_mbox.event_descs = wsmex_uncore_mbox_events;
+		if (nhmex_uncore_cbox.num_boxes > max_cores)
+			nhmex_uncore_cbox.num_boxes = max_cores;
 		msr_uncores = nhmex_msr_uncores;
 		break;
 	default:

arch/x86/kernel/cpu/perf_event_intel_uncore.h

@@ -230,6 +230,7 @@
 #define NHMEX_S1_MSR_MASK			0xe5a
 
 #define NHMEX_S_PMON_MM_CFG_EN			(0x1ULL << 63)
+#define NHMEX_S_EVENT_TO_R_PROG_EV		0
 
 /* NHM-EX Mbox */
 #define NHMEX_M0_MSR_GLOBAL_CTL			0xca0
@@ -275,18 +276,12 @@
 		 NHMEX_M_PMON_CTL_INC_SEL_MASK |	\
 		 NHMEX_M_PMON_CTL_SET_FLAG_SEL_MASK)
 
-
-#define NHMEX_M_PMON_ZDP_CTL_FVC_FVID_MASK	0x1f
-#define NHMEX_M_PMON_ZDP_CTL_FVC_BCMD_MASK	(0x7 << 5)
-#define NHMEX_M_PMON_ZDP_CTL_FVC_RSP_MASK	(0x7 << 8)
-#define NHMEX_M_PMON_ZDP_CTL_FVC_PBOX_INIT_ERR	(1 << 23)
-#define NHMEX_M_PMON_ZDP_CTL_FVC_MASK			\
-		(NHMEX_M_PMON_ZDP_CTL_FVC_FVID_MASK |	\
-		 NHMEX_M_PMON_ZDP_CTL_FVC_BCMD_MASK |	\
-		 NHMEX_M_PMON_ZDP_CTL_FVC_RSP_MASK  |	\
-		 NHMEX_M_PMON_ZDP_CTL_FVC_PBOX_INIT_ERR)
+#define NHMEX_M_PMON_ZDP_CTL_FVC_MASK		(((1 << 11) - 1) | (1 << 23))
 #define NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(n)	(0x7 << (11 + 3 * (n)))
 
+#define WSMEX_M_PMON_ZDP_CTL_FVC_MASK		(((1 << 12) - 1) | (1 << 24))
+#define WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(n)	(0x7 << (12 + 3 * (n)))
+
 /*
  * use the 9~13 bits to select event If the 7th bit is not set,
  * otherwise use the 19~21 bits to select event.
@@ -368,6 +363,7 @@ struct intel_uncore_type {
 	unsigned num_shared_regs:8;
 	unsigned single_fixed:1;
 	unsigned pair_ctr_ctl:1;
+	unsigned *msr_offsets;
 	struct event_constraint unconstrainted;
 	struct event_constraint *constraints;
 	struct intel_uncore_pmu *pmus;
@@ -485,29 +481,31 @@ unsigned uncore_pci_perf_ctr(struct intel_uncore_box *box, int idx)
 	return idx * 8 + box->pmu->type->perf_ctr;
 }
 
-static inline
-unsigned uncore_msr_box_ctl(struct intel_uncore_box *box)
+static inline unsigned uncore_msr_box_offset(struct intel_uncore_box *box)
+{
+	struct intel_uncore_pmu *pmu = box->pmu;
+	return pmu->type->msr_offsets ?
+		pmu->type->msr_offsets[pmu->pmu_idx] :
+		pmu->type->msr_offset * pmu->pmu_idx;
+}
+
+static inline unsigned uncore_msr_box_ctl(struct intel_uncore_box *box)
 {
 	if (!box->pmu->type->box_ctl)
 		return 0;
-	return box->pmu->type->box_ctl +
-		box->pmu->type->msr_offset * box->pmu->pmu_idx;
+	return box->pmu->type->box_ctl + uncore_msr_box_offset(box);
 }
 
-static inline
-unsigned uncore_msr_fixed_ctl(struct intel_uncore_box *box)
+static inline unsigned uncore_msr_fixed_ctl(struct intel_uncore_box *box)
 {
 	if (!box->pmu->type->fixed_ctl)
 		return 0;
-	return box->pmu->type->fixed_ctl +
-		box->pmu->type->msr_offset * box->pmu->pmu_idx;
+	return box->pmu->type->fixed_ctl + uncore_msr_box_offset(box);
 }
 
-static inline
-unsigned uncore_msr_fixed_ctr(struct intel_uncore_box *box)
+static inline unsigned uncore_msr_fixed_ctr(struct intel_uncore_box *box)
 {
-	return box->pmu->type->fixed_ctr +
-		box->pmu->type->msr_offset * box->pmu->pmu_idx;
+	return box->pmu->type->fixed_ctr + uncore_msr_box_offset(box);
 }
 
 static inline
@@ -515,7 +513,7 @@ unsigned uncore_msr_event_ctl(struct intel_uncore_box *box, int idx)
 {
 	return box->pmu->type->event_ctl +
 		(box->pmu->type->pair_ctr_ctl ? 2 * idx : idx) +
-		box->pmu->type->msr_offset * box->pmu->pmu_idx;
+		uncore_msr_box_offset(box);
 }
 
 static inline
@@ -523,7 +521,7 @@ unsigned uncore_msr_perf_ctr(struct intel_uncore_box *box, int idx)
 {
 	return box->pmu->type->perf_ctr +
 		(box->pmu->type->pair_ctr_ctl ? 2 * idx : idx) +
-		box->pmu->type->msr_offset * box->pmu->pmu_idx;
+		uncore_msr_box_offset(box);
 }
 
 static inline

arch/x86/mm/hugetlbpage.c

@@ -56,9 +56,16 @@ static int vma_shareable(struct vm_area_struct *vma, unsigned long addr)
 }
 
 /*
- * search for a shareable pmd page for hugetlb.
+ * Search for a shareable pmd page for hugetlb. In any case calls pmd_alloc()
+ * and returns the corresponding pte. While this is not necessary for the
+ * !shared pmd case because we can allocate the pmd later as well, it makes the
+ * code much cleaner. pmd allocation is essential for the shared case because
+ * pud has to be populated inside the same i_mmap_mutex section - otherwise
+ * racing tasks could either miss the sharing (see huge_pte_offset) or select a
+ * bad pmd for sharing.
  */
-static void huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
+static pte_t *
+huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
 {
 	struct vm_area_struct *vma = find_vma(mm, addr);
 	struct address_space *mapping = vma->vm_file->f_mapping;
@@ -68,9 +75,10 @@ static void huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
 	struct vm_area_struct *svma;
 	unsigned long saddr;
 	pte_t *spte = NULL;
+	pte_t *pte;
 
 	if (!vma_shareable(vma, addr))
-		return;
+		return (pte_t *)pmd_alloc(mm, pud, addr);
 
 	mutex_lock(&mapping->i_mmap_mutex);
 	vma_prio_tree_foreach(svma, &iter, &mapping->i_mmap, idx, idx) {
@@ -97,7 +105,9 @@ static void huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
 		put_page(virt_to_page(spte));
 	spin_unlock(&mm->page_table_lock);
 out:
+	pte = (pte_t *)pmd_alloc(mm, pud, addr);
 	mutex_unlock(&mapping->i_mmap_mutex);
+	return pte;
 }
 
 /*
@@ -142,8 +152,9 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
 		} else {
 			BUG_ON(sz != PMD_SIZE);
 			if (pud_none(*pud))
-				huge_pmd_share(mm, addr, pud);
-			pte = (pte_t *) pmd_alloc(mm, pud, addr);
+				pte = huge_pmd_share(mm, addr, pud);
+			else
+				pte = (pte_t *)pmd_alloc(mm, pud, addr);
 		}
 	}
 	BUG_ON(pte && !pte_none(*pte) && !pte_huge(*pte));

arch/x86/mm/pageattr.c

@@ -919,13 +919,11 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages,
 
 	/*
 	 * On success we use clflush, when the CPU supports it to
-	 * avoid the wbindv. If the CPU does not support it, in the
-	 * error case, and during early boot (for EFI) we fall back
-	 * to cpa_flush_all (which uses wbinvd):
+	 * avoid the wbindv. If the CPU does not support it and in the
+	 * error case we fall back to cpa_flush_all (which uses
+	 * wbindv):
 	 */
-	if (early_boot_irqs_disabled)
-		__cpa_flush_all((void *)(long)cache);
-	else if (!ret && cpu_has_clflush) {
+	if (!ret && cpu_has_clflush) {
 		if (cpa.flags & (CPA_PAGES_ARRAY | CPA_ARRAY)) {
 			cpa_flush_array(addr, numpages, cache,
 					cpa.flags, pages);

arch/x86/platform/efi/efi.c

@@ -234,7 +234,22 @@ static efi_status_t __init phys_efi_set_virtual_address_map(
 	return status;
 }
 
-static int efi_set_rtc_mmss(unsigned long nowtime)
+static efi_status_t __init phys_efi_get_time(efi_time_t *tm,
+					     efi_time_cap_t *tc)
+{
+	unsigned long flags;
+	efi_status_t status;
+
+	spin_lock_irqsave(&rtc_lock, flags);
+	efi_call_phys_prelog();
+	status = efi_call_phys2(efi_phys.get_time, virt_to_phys(tm),
+				virt_to_phys(tc));
+	efi_call_phys_epilog();
+	spin_unlock_irqrestore(&rtc_lock, flags);
+	return status;
+}
+
+int efi_set_rtc_mmss(unsigned long nowtime)
 {
 	int real_seconds, real_minutes;
 	efi_status_t 	status;
@@ -263,7 +278,7 @@ static int efi_set_rtc_mmss(unsigned long nowtime)
 	return 0;
 }
 
-static unsigned long efi_get_time(void)
+unsigned long efi_get_time(void)
 {
 	efi_status_t status;
 	efi_time_t eft;
@@ -606,13 +621,18 @@ static int __init efi_runtime_init(void)
 	}
 	/*
 	 * We will only need *early* access to the following
-	 * EFI runtime service before set_virtual_address_map
+	 * two EFI runtime services before set_virtual_address_map
 	 * is invoked.
 	 */
+	efi_phys.get_time = (efi_get_time_t *)runtime->get_time;
 	efi_phys.set_virtual_address_map =
 		(efi_set_virtual_address_map_t *)
 		runtime->set_virtual_address_map;
-
+	/*
+	 * Make efi_get_time can be called before entering
+	 * virtual mode.
+	 */
+	efi.get_time = phys_efi_get_time;
 	early_iounmap(runtime, sizeof(efi_runtime_services_t));
 
 	return 0;
@@ -700,10 +720,12 @@ void __init efi_init(void)
 		efi_enabled = 0;
 		return;
 	}
+#ifdef CONFIG_X86_32
 	if (efi_native) {
 		x86_platform.get_wallclock = efi_get_time;
 		x86_platform.set_wallclock = efi_set_rtc_mmss;
 	}
+#endif
 
 #if EFI_DEBUG
 	print_efi_memmap();

arch/x86/realmode/rm/Makefile

@@ -72,7 +72,7 @@ KBUILD_CFLAGS	:= $(LINUXINCLUDE) -m32 -g -Os -D_SETUP -D__KERNEL__ -D_WAKEUP \
 		   -Wall -Wstrict-prototypes \
 		   -march=i386 -mregparm=3 \
 		   -include $(srctree)/$(src)/../../boot/code16gcc.h \
-		   -fno-strict-aliasing -fomit-frame-pointer \
+		   -fno-strict-aliasing -fomit-frame-pointer -fno-pic \
 		   $(call cc-option, -ffreestanding) \
 		   $(call cc-option, -fno-toplevel-reorder,\
 			$(call cc-option, -fno-unit-at-a-time)) \

arch/x86/syscalls/syscall_64.tbl

@@ -60,8 +60,8 @@
 51	common	getsockname		sys_getsockname
 52	common	getpeername		sys_getpeername
 53	common	socketpair		sys_socketpair
-54	common	setsockopt		sys_setsockopt
-55	common	getsockopt		sys_getsockopt
+54	64	setsockopt		sys_setsockopt
+55	64	getsockopt		sys_getsockopt
 56	common	clone			stub_clone
 57	common	fork			stub_fork
 58	common	vfork			stub_vfork
@@ -353,3 +353,5 @@
 538	x32	sendmmsg		compat_sys_sendmmsg
 539	x32	process_vm_readv	compat_sys_process_vm_readv
 540	x32	process_vm_writev	compat_sys_process_vm_writev
+541	x32	setsockopt		compat_sys_setsockopt
+542	x32	getsockopt		compat_sys_getsockopt

drivers/acpi/acpica/tbxface.c

@@ -387,6 +387,7 @@ acpi_get_table_with_size(char *signature,
 
 	return (AE_NOT_FOUND);
 }
+ACPI_EXPORT_SYMBOL(acpi_get_table_with_size)
 
 acpi_status
 acpi_get_table(char *signature,

drivers/base/core.c

@@ -1865,6 +1865,7 @@ int __dev_printk(const char *level, const struct device *dev,
 		 struct va_format *vaf)
 {
 	char dict[128];
+	const char *level_extra = "";
 	size_t dictlen = 0;
 	const char *subsys;
 
@@ -1911,10 +1912,14 @@ int __dev_printk(const char *level, const struct device *dev,
 				    "DEVICE=+%s:%s", subsys, dev_name(dev));
 	}
 skip:
+	if (level[2])
+		level_extra = &level[2]; /* skip past KERN_SOH "L" */
+
 	return printk_emit(0, level[1] - '0',
 			   dictlen ? dict : NULL, dictlen,
-			   "%s %s: %pV",
-			   dev_driver_string(dev), dev_name(dev), vaf);
+			   "%s %s: %s%pV",
+			   dev_driver_string(dev), dev_name(dev),
+			   level_extra, vaf);
 }
 EXPORT_SYMBOL(__dev_printk);
 

drivers/base/power/runtime.c

@@ -147,6 +147,8 @@ static int rpm_check_suspend_allowed(struct device *dev)
 	    || (dev->power.request_pending
 			&& dev->power.request == RPM_REQ_RESUME))
 		retval = -EAGAIN;
+	else if (__dev_pm_qos_read_value(dev) < 0)
+		retval = -EPERM;
 	else if (dev->power.runtime_status == RPM_SUSPENDED)
 		retval = 1;
 
@@ -388,7 +390,6 @@ static int rpm_suspend(struct device *dev, int rpmflags)
 		goto repeat;
 	}
 
-	dev->power.deferred_resume = false;
 	if (dev->power.no_callbacks)
 		goto no_callback;	/* Assume success. */
 
@@ -403,12 +404,6 @@ static int rpm_suspend(struct device *dev, int rpmflags)
 		goto out;
 	}
 
-	if (__dev_pm_qos_read_value(dev) < 0) {
-		/* Negative PM QoS constraint means "never suspend". */
-		retval = -EPERM;
-		goto out;
-	}
-
 	__update_runtime_status(dev, RPM_SUSPENDING);
 
 	if (dev->pm_domain)
@@ -440,6 +435,7 @@ static int rpm_suspend(struct device *dev, int rpmflags)
 	wake_up_all(&dev->power.wait_queue);
 
 	if (dev->power.deferred_resume) {
+		dev->power.deferred_resume = false;
 		rpm_resume(dev, 0);
 		retval = -EAGAIN;
 		goto out;
@@ -584,6 +580,7 @@ static int rpm_resume(struct device *dev, int rpmflags)
 		    || dev->parent->power.runtime_status == RPM_ACTIVE) {
 			atomic_inc(&dev->parent->power.child_count);
 			spin_unlock(&dev->parent->power.lock);
+			retval = 1;
 			goto no_callback;	/* Assume success. */
 		}
 		spin_unlock(&dev->parent->power.lock);
@@ -664,7 +661,7 @@ static int rpm_resume(struct device *dev, int rpmflags)
 	}
 	wake_up_all(&dev->power.wait_queue);
 
-	if (!retval)
+	if (retval >= 0)
 		rpm_idle(dev, RPM_ASYNC);
 
  out:

drivers/block/cciss_scsi.c

@@ -763,16 +763,7 @@ static void complete_scsi_command(CommandList_struct *c, int timeout,
 		{
 			case CMD_TARGET_STATUS:
 				/* Pass it up to the upper layers... */
-				if( ei->ScsiStatus)
-                		{
-#if 0
-                    			printk(KERN_WARNING "cciss: cmd %p "
-						"has SCSI Status = %x\n",
-						c, ei->ScsiStatus);
-#endif
-					cmd->result |= (ei->ScsiStatus << 1);
-                		}
-				else {  /* scsi status is zero??? How??? */
+				if (!ei->ScsiStatus) {
 					
 	/* Ordinarily, this case should never happen, but there is a bug
 	   in some released firmware revisions that allows it to happen

drivers/bluetooth/ath3k.c

@@ -79,6 +79,7 @@ static struct usb_device_id ath3k_table[] = {
 	{ USB_DEVICE(0x13d3, 0x3362) },
 	{ USB_DEVICE(0x0CF3, 0xE004) },
 	{ USB_DEVICE(0x0930, 0x0219) },
+	{ USB_DEVICE(0x0489, 0xe057) },
 
 	/* Atheros AR5BBU12 with sflash firmware */
 	{ USB_DEVICE(0x0489, 0xE02C) },
@@ -104,6 +105,7 @@ static struct usb_device_id ath3k_blist_tbl[] = {
 	{ USB_DEVICE(0x13d3, 0x3362), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0cf3, 0xe004), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0930, 0x0219), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x0489, 0xe057), .driver_info = BTUSB_ATH3012 },
 
 	/* Atheros AR5BBU22 with sflash firmware */
 	{ USB_DEVICE(0x0489, 0xE03C), .driver_info = BTUSB_ATH3012 },

drivers/bluetooth/btusb.c

@@ -98,6 +98,7 @@ static struct usb_device_id btusb_table[] = {
 	{ USB_DEVICE(0x0a5c, 0x21e6) },
 	{ USB_DEVICE(0x0a5c, 0x21e8) },
 	{ USB_DEVICE(0x0a5c, 0x21f3) },
+	{ USB_DEVICE(0x0a5c, 0x21f4) },
 	{ USB_DEVICE(0x413c, 0x8197) },
 
 	/* Foxconn - Hon Hai */
@@ -133,6 +134,7 @@ static struct usb_device_id blacklist_table[] = {
 	{ USB_DEVICE(0x13d3, 0x3362), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0cf3, 0xe004), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0930, 0x0219), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x0489, 0xe057), .driver_info = BTUSB_ATH3012 },
 
 	/* Atheros AR5BBU12 with sflash firmware */
 	{ USB_DEVICE(0x0489, 0xe02c), .driver_info = BTUSB_IGNORE },

drivers/char/agp/intel-agp.h

@@ -64,6 +64,7 @@
 #define I830_PTE_SYSTEM_CACHED  0x00000006
 /* GT PTE cache control fields */
 #define GEN6_PTE_UNCACHED	0x00000002
+#define HSW_PTE_UNCACHED	0x00000000
 #define GEN6_PTE_LLC		0x00000004
 #define GEN6_PTE_LLC_MLC	0x00000006
 #define GEN6_PTE_GFDT		0x00000008

drivers/char/agp/intel-gtt.c

@@ -1156,6 +1156,30 @@ static bool gen6_check_flags(unsigned int flags)
 	return true;
 }
 
+static void haswell_write_entry(dma_addr_t addr, unsigned int entry,
+				unsigned int flags)
+{
+	unsigned int type_mask = flags & ~AGP_USER_CACHED_MEMORY_GFDT;
+	unsigned int gfdt = flags & AGP_USER_CACHED_MEMORY_GFDT;
+	u32 pte_flags;
+
+	if (type_mask == AGP_USER_MEMORY)
+		pte_flags = HSW_PTE_UNCACHED | I810_PTE_VALID;
+	else if (type_mask == AGP_USER_CACHED_MEMORY_LLC_MLC) {
+		pte_flags = GEN6_PTE_LLC_MLC | I810_PTE_VALID;
+		if (gfdt)
+			pte_flags |= GEN6_PTE_GFDT;
+	} else { /* set 'normal'/'cached' to LLC by default */
+		pte_flags = GEN6_PTE_LLC | I810_PTE_VALID;
+		if (gfdt)
+			pte_flags |= GEN6_PTE_GFDT;
+	}
+
+	/* gen6 has bit11-4 for physical addr bit39-32 */
+	addr |= (addr >> 28) & 0xff0;
+	writel(addr | pte_flags, intel_private.gtt + entry);
+}
+
 static void gen6_write_entry(dma_addr_t addr, unsigned int entry,
 			     unsigned int flags)
 {
@@ -1382,6 +1406,15 @@ static const struct intel_gtt_driver sandybridge_gtt_driver = {
 	.check_flags = gen6_check_flags,
 	.chipset_flush = i9xx_chipset_flush,
 };
+static const struct intel_gtt_driver haswell_gtt_driver = {
+	.gen = 6,
+	.setup = i9xx_setup,
+	.cleanup = gen6_cleanup,
+	.write_entry = haswell_write_entry,
+	.dma_mask_size = 40,
+	.check_flags = gen6_check_flags,
+	.chipset_flush = i9xx_chipset_flush,
+};
 static const struct intel_gtt_driver valleyview_gtt_driver = {
 	.gen = 7,
 	.setup = i9xx_setup,
@@ -1499,77 +1532,77 @@ static const struct intel_gtt_driver_description {
 	{ PCI_DEVICE_ID_INTEL_VALLEYVIEW_IG,
 	    "ValleyView", &valleyview_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_D_GT1_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_D_GT2_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_D_GT2_PLUS_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_M_GT1_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_M_GT2_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_M_GT2_PLUS_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_S_GT1_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_S_GT2_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_S_GT2_PLUS_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_SDV_D_GT1_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_SDV_D_GT2_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_SDV_D_GT2_PLUS_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_SDV_M_GT1_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_SDV_M_GT2_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_SDV_M_GT2_PLUS_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_SDV_S_GT1_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_SDV_S_GT2_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_SDV_S_GT2_PLUS_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_ULT_D_GT1_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_ULT_D_GT2_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_ULT_D_GT2_PLUS_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_ULT_M_GT1_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_ULT_M_GT2_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_ULT_M_GT2_PLUS_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_ULT_S_GT1_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_ULT_S_GT2_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_ULT_S_GT2_PLUS_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_CRW_D_GT1_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_CRW_D_GT2_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_CRW_D_GT2_PLUS_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_CRW_M_GT1_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_CRW_M_GT2_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_CRW_M_GT2_PLUS_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_CRW_S_GT1_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_CRW_S_GT2_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_CRW_S_GT2_PLUS_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ 0, NULL, NULL }
 };
 

drivers/clocksource/cs5535-clockevt.c

@@ -53,7 +53,7 @@ static struct cs5535_mfgpt_timer *cs5535_event_clock;
 #define MFGPT_PERIODIC (MFGPT_HZ / HZ)
 
 /*
- * The MFPGT timers on the CS5536 provide us with suitable timers to use
+ * The MFGPT timers on the CS5536 provide us with suitable timers to use
  * as clock event sources - not as good as a HPET or APIC, but certainly
  * better than the PIT.  This isn't a general purpose MFGPT driver, but
  * a simplified one designed specifically to act as a clock event source.
@@ -144,7 +144,7 @@ static int __init cs5535_mfgpt_init(void)
 
 	timer = cs5535_mfgpt_alloc_timer(MFGPT_TIMER_ANY, MFGPT_DOMAIN_WORKING);
 	if (!timer) {
-		printk(KERN_ERR DRV_NAME ": Could not allocate MFPGT timer\n");
+		printk(KERN_ERR DRV_NAME ": Could not allocate MFGPT timer\n");
 		return -ENODEV;
 	}
 	cs5535_event_clock = timer;

drivers/cpuidle/coupled.c

@@ -678,10 +678,22 @@ static int cpuidle_coupled_cpu_notify(struct notifier_block *nb,
 	int cpu = (unsigned long)hcpu;
 	struct cpuidle_device *dev;
 
+	switch (action & ~CPU_TASKS_FROZEN) {
+	case CPU_UP_PREPARE:
+	case CPU_DOWN_PREPARE:
+	case CPU_ONLINE:
+	case CPU_DEAD:
+	case CPU_UP_CANCELED:
+	case CPU_DOWN_FAILED:
+		break;
+	default:
+		return NOTIFY_OK;
+	}
+
 	mutex_lock(&cpuidle_lock);
 
 	dev = per_cpu(cpuidle_devices, cpu);
-	if (!dev->coupled)
+	if (!dev || !dev->coupled)
 		goto out;
 
 	switch (action & ~CPU_TASKS_FROZEN) {

drivers/extcon/extcon_gpio.c

@@ -107,7 +107,8 @@ static int __devinit gpio_extcon_probe(struct platform_device *pdev)
 	if (ret < 0)
 		return ret;
 
-	ret = gpio_request_one(extcon_data->gpio, GPIOF_DIR_IN, pdev->name);
+	ret = devm_gpio_request_one(&pdev->dev, extcon_data->gpio, GPIOF_DIR_IN,
+				    pdev->name);
 	if (ret < 0)
 		goto err;
 

drivers/gpu/drm/Kconfig

@@ -22,6 +22,7 @@ menuconfig DRM
 config DRM_USB
 	tristate
 	depends on DRM
+	depends on USB_ARCH_HAS_HCD
 	select USB
 
 config DRM_KMS_HELPER

drivers/gpu/drm/drm_modes.c

@@ -706,9 +706,6 @@ void drm_mode_set_crtcinfo(struct drm_display_mode *p, int adjust_flags)
 	p->crtc_vblank_end = max(p->crtc_vsync_end, p->crtc_vtotal);
 	p->crtc_hblank_start = min(p->crtc_hsync_start, p->crtc_hdisplay);
 	p->crtc_hblank_end = max(p->crtc_hsync_end, p->crtc_htotal);
-
-	p->crtc_hadjusted = false;
-	p->crtc_vadjusted = false;
 }
 EXPORT_SYMBOL(drm_mode_set_crtcinfo);
 

drivers/gpu/drm/drm_proc.c

@@ -89,7 +89,7 @@ static const struct file_operations drm_proc_fops = {
  * Create a given set of proc files represented by an array of
  * gdm_proc_lists in the given root directory.
  */
-int drm_proc_create_files(struct drm_info_list *files, int count,
+static int drm_proc_create_files(struct drm_info_list *files, int count,
 			  struct proc_dir_entry *root, struct drm_minor *minor)
 {
 	struct drm_device *dev = minor->dev;
@@ -172,7 +172,7 @@ int drm_proc_init(struct drm_minor *minor, int minor_id,
 	return 0;
 }
 
-int drm_proc_remove_files(struct drm_info_list *files, int count,
+static int drm_proc_remove_files(struct drm_info_list *files, int count,
 			  struct drm_minor *minor)
 {
 	struct list_head *pos, *q;

drivers/gpu/drm/i915/i915_gem.c

@@ -2365,6 +2365,10 @@ int i915_gpu_idle(struct drm_device *dev)
 
 	/* Flush everything onto the inactive list. */
 	for_each_ring(ring, dev_priv, i) {
+		ret = i915_switch_context(ring, NULL, DEFAULT_CONTEXT_ID);
+		if (ret)
+			return ret;
+
 		ret = i915_ring_idle(ring);
 		if (ret)
 			return ret;
@@ -2372,10 +2376,6 @@ int i915_gpu_idle(struct drm_device *dev)
 		/* Is the device fubar? */
 		if (WARN_ON(!list_empty(&ring->gpu_write_list)))
 			return -EBUSY;
-
-		ret = i915_switch_context(ring, NULL, DEFAULT_CONTEXT_ID);
-		if (ret)
-			return ret;
 	}
 
 	return 0;

drivers/gpu/drm/i915/i915_gem_gtt.c

@@ -261,7 +261,10 @@ void i915_ppgtt_bind_object(struct i915_hw_ppgtt *ppgtt,
 		pte_flags |= GEN6_PTE_CACHE_LLC;
 		break;
 	case I915_CACHE_NONE:
-		pte_flags |= GEN6_PTE_UNCACHED;
+		if (IS_HASWELL(dev))
+			pte_flags |= HSW_PTE_UNCACHED;
+		else
+			pte_flags |= GEN6_PTE_UNCACHED;
 		break;
 	default:
 		BUG();

drivers/gpu/drm/i915/i915_reg.h

@@ -115,6 +115,7 @@
 
 #define GEN6_PTE_VALID			(1 << 0)
 #define GEN6_PTE_UNCACHED		(1 << 1)
+#define HSW_PTE_UNCACHED		(0)
 #define GEN6_PTE_CACHE_LLC		(2 << 1)
 #define GEN6_PTE_CACHE_LLC_MLC		(3 << 1)
 #define GEN6_PTE_CACHE_BITS		(3 << 1)

drivers/gpu/drm/i915/intel_crt.c

@@ -326,6 +326,36 @@ static bool intel_crt_detect_hotplug(struct drm_connector *connector)
 	return ret;
 }
 
+static struct edid *intel_crt_get_edid(struct drm_connector *connector,
+				struct i2c_adapter *i2c)
+{
+	struct edid *edid;
+
+	edid = drm_get_edid(connector, i2c);
+
+	if (!edid && !intel_gmbus_is_forced_bit(i2c)) {
+		DRM_DEBUG_KMS("CRT GMBUS EDID read failed, retry using GPIO bit-banging\n");
+		intel_gmbus_force_bit(i2c, true);
+		edid = drm_get_edid(connector, i2c);
+		intel_gmbus_force_bit(i2c, false);
+	}
+
+	return edid;
+}
+
+/* local version of intel_ddc_get_modes() to use intel_crt_get_edid() */
+static int intel_crt_ddc_get_modes(struct drm_connector *connector,
+				struct i2c_adapter *adapter)
+{
+	struct edid *edid;
+
+	edid = intel_crt_get_edid(connector, adapter);
+	if (!edid)
+		return 0;
+
+	return intel_connector_update_modes(connector, edid);
+}
+
 static bool intel_crt_detect_ddc(struct drm_connector *connector)
 {
 	struct intel_crt *crt = intel_attached_crt(connector);
@@ -336,7 +366,7 @@ static bool intel_crt_detect_ddc(struct drm_connector *connector)
 	BUG_ON(crt->base.type != INTEL_OUTPUT_ANALOG);
 
 	i2c = intel_gmbus_get_adapter(dev_priv, dev_priv->crt_ddc_pin);
-	edid = drm_get_edid(connector, i2c);
+	edid = intel_crt_get_edid(connector, i2c);
 
 	if (edid) {
 		bool is_digital = edid->input & DRM_EDID_INPUT_DIGITAL;
@@ -544,13 +574,13 @@ static int intel_crt_get_modes(struct drm_connector *connector)
 	struct i2c_adapter *i2c;
 
 	i2c = intel_gmbus_get_adapter(dev_priv, dev_priv->crt_ddc_pin);
-	ret = intel_ddc_get_modes(connector, i2c);
+	ret = intel_crt_ddc_get_modes(connector, i2c);
 	if (ret || !IS_G4X(dev))
 		return ret;
 
 	/* Try to probe digital port for output in DVI-I -> VGA mode. */
 	i2c = intel_gmbus_get_adapter(dev_priv, GMBUS_PORT_DPB);
-	return intel_ddc_get_modes(connector, i2c);
+	return intel_crt_ddc_get_modes(connector, i2c);
 }
 
 static int intel_crt_set_property(struct drm_connector *connector,

drivers/gpu/drm/i915/intel_drv.h

@@ -342,6 +342,8 @@ struct intel_fbc_work {
 	int interval;
 };
 
+int intel_connector_update_modes(struct drm_connector *connector,
+				struct edid *edid);
 int intel_ddc_get_modes(struct drm_connector *c, struct i2c_adapter *adapter);
 
 extern void intel_attach_force_audio_property(struct drm_connector *connector);

drivers/gpu/drm/i915/intel_modes.c

@@ -32,6 +32,25 @@
 #include "intel_drv.h"
 #include "i915_drv.h"
 
+/**
+ * intel_connector_update_modes - update connector from edid
+ * @connector: DRM connector device to use
+ * @edid: previously read EDID information
+ */
+int intel_connector_update_modes(struct drm_connector *connector,
+				struct edid *edid)
+{
+	int ret;
+
+	drm_mode_connector_update_edid_property(connector, edid);
+	ret = drm_add_edid_modes(connector, edid);
+	drm_edid_to_eld(connector, edid);
+	connector->display_info.raw_edid = NULL;
+	kfree(edid);
+
+	return ret;
+}
+
 /**
  * intel_ddc_get_modes - get modelist from monitor
  * @connector: DRM connector device to use
@@ -43,18 +62,12 @@ int intel_ddc_get_modes(struct drm_connector *connector,
 			struct i2c_adapter *adapter)
 {
 	struct edid *edid;
-	int ret = 0;
 
 	edid = drm_get_edid(connector, adapter);
-	if (edid) {
-		drm_mode_connector_update_edid_property(connector, edid);
-		ret = drm_add_edid_modes(connector, edid);
-		drm_edid_to_eld(connector, edid);
-		connector->display_info.raw_edid = NULL;
-		kfree(edid);
-	}
+	if (!edid)
+		return 0;
 
-	return ret;
+	return intel_connector_update_modes(connector, edid);
 }
 
 static const struct drm_prop_enum_list force_audio_names[] = {

drivers/gpu/drm/i915/intel_pm.c

@@ -2441,17 +2441,10 @@ static void gen6_enable_rps(struct drm_device *dev)
 		   dev_priv->max_delay << 24 |
 		   dev_priv->min_delay << 16);
 
-	if (IS_HASWELL(dev)) {
-		I915_WRITE(GEN6_RP_UP_THRESHOLD, 59400);
-		I915_WRITE(GEN6_RP_DOWN_THRESHOLD, 245000);
-		I915_WRITE(GEN6_RP_UP_EI, 66000);
-		I915_WRITE(GEN6_RP_DOWN_EI, 350000);
-	} else {
-		I915_WRITE(GEN6_RP_UP_THRESHOLD, 10000);
-		I915_WRITE(GEN6_RP_DOWN_THRESHOLD, 1000000);
-		I915_WRITE(GEN6_RP_UP_EI, 100000);
-		I915_WRITE(GEN6_RP_DOWN_EI, 5000000);
-	}
+	I915_WRITE(GEN6_RP_UP_THRESHOLD, 59400);
+	I915_WRITE(GEN6_RP_DOWN_THRESHOLD, 245000);
+	I915_WRITE(GEN6_RP_UP_EI, 66000);
+	I915_WRITE(GEN6_RP_DOWN_EI, 350000);
 
 	I915_WRITE(GEN6_RP_IDLE_HYSTERSIS, 10);
 	I915_WRITE(GEN6_RP_CONTROL,

drivers/gpu/drm/i915/intel_sdvo.c

@@ -1692,6 +1692,7 @@ static bool intel_sdvo_detect_hdmi_audio(struct drm_connector *connector)
 	edid = intel_sdvo_get_edid(connector);
 	if (edid != NULL && edid->input & DRM_EDID_INPUT_DIGITAL)
 		has_audio = drm_detect_monitor_audio(edid);
+	kfree(edid);
 
 	return has_audio;
 }

drivers/gpu/drm/nouveau/nouveau_acpi.c

@@ -211,11 +211,6 @@ static int nouveau_dsm_power_state(enum vga_switcheroo_client_id id,
 	return nouveau_dsm_set_discrete_state(nouveau_dsm_priv.dhandle, state);
 }
 
-static int nouveau_dsm_init(void)
-{
-	return 0;
-}
-
 static int nouveau_dsm_get_client_id(struct pci_dev *pdev)
 {
 	/* easy option one - intel vendor ID means Integrated */
@@ -232,7 +227,6 @@ static int nouveau_dsm_get_client_id(struct pci_dev *pdev)
 static struct vga_switcheroo_handler nouveau_dsm_handler = {
 	.switchto = nouveau_dsm_switchto,
 	.power_state = nouveau_dsm_power_state,
-	.init = nouveau_dsm_init,
 	.get_client_id = nouveau_dsm_get_client_id,
 };
 

drivers/gpu/drm/radeon/atombios_crtc.c

@@ -444,11 +444,28 @@ union atom_enable_ss {
 static void atombios_crtc_program_ss(struct radeon_device *rdev,
 				     int enable,
 				     int pll_id,
+				     int crtc_id,
 				     struct radeon_atom_ss *ss)
 {
+	unsigned i;
 	int index = GetIndexIntoMasterTable(COMMAND, EnableSpreadSpectrumOnPPLL);
 	union atom_enable_ss args;
 
+	if (!enable) {
+		for (i = 0; i < rdev->num_crtc; i++) {
+			if (rdev->mode_info.crtcs[i] &&
+			    rdev->mode_info.crtcs[i]->enabled &&
+			    i != crtc_id &&
+			    pll_id == rdev->mode_info.crtcs[i]->pll_id) {
+				/* one other crtc is using this pll don't turn
+				 * off spread spectrum as it might turn off
+				 * display on active crtc
+				 */
+				return;
+			}
+		}
+	}
+
 	memset(&args, 0, sizeof(args));
 
 	if (ASIC_IS_DCE5(rdev)) {
@@ -1028,7 +1045,7 @@ static void atombios_crtc_set_pll(struct drm_crtc *crtc, struct drm_display_mode
 		radeon_compute_pll_legacy(pll, adjusted_clock, &pll_clock, &fb_div, &frac_fb_div,
 					  &ref_div, &post_div);
 
-	atombios_crtc_program_ss(rdev, ATOM_DISABLE, radeon_crtc->pll_id, &ss);
+	atombios_crtc_program_ss(rdev, ATOM_DISABLE, radeon_crtc->pll_id, radeon_crtc->crtc_id, &ss);
 
 	atombios_crtc_program_pll(crtc, radeon_crtc->crtc_id, radeon_crtc->pll_id,
 				  encoder_mode, radeon_encoder->encoder_id, mode->clock,
@@ -1051,7 +1068,7 @@ static void atombios_crtc_set_pll(struct drm_crtc *crtc, struct drm_display_mode
 			ss.step = step_size;
 		}
 
-		atombios_crtc_program_ss(rdev, ATOM_ENABLE, radeon_crtc->pll_id, &ss);
+		atombios_crtc_program_ss(rdev, ATOM_ENABLE, radeon_crtc->pll_id, radeon_crtc->crtc_id, &ss);
 	}
 }
 
@@ -1572,11 +1589,11 @@ void radeon_atom_disp_eng_pll_init(struct radeon_device *rdev)
 								   ASIC_INTERNAL_SS_ON_DCPLL,
 								   rdev->clock.default_dispclk);
 		if (ss_enabled)
-			atombios_crtc_program_ss(rdev, ATOM_DISABLE, ATOM_DCPLL, &ss);
+			atombios_crtc_program_ss(rdev, ATOM_DISABLE, ATOM_DCPLL, -1, &ss);
 		/* XXX: DCE5, make sure voltage, dispclk is high enough */
 		atombios_crtc_set_disp_eng_pll(rdev, rdev->clock.default_dispclk);
 		if (ss_enabled)
-			atombios_crtc_program_ss(rdev, ATOM_ENABLE, ATOM_DCPLL, &ss);
+			atombios_crtc_program_ss(rdev, ATOM_ENABLE, ATOM_DCPLL, -1, &ss);
 	}
 
 }

drivers/gpu/drm/radeon/r600_cs.c

@@ -47,13 +47,17 @@ struct r600_cs_track {
 	u32			npipes;
 	/* value we track */
 	u32			sq_config;
+	u32			log_nsamples;
 	u32			nsamples;
 	u32			cb_color_base_last[8];
 	struct radeon_bo	*cb_color_bo[8];
 	u64			cb_color_bo_mc[8];
-	u32			cb_color_bo_offset[8];
-	struct radeon_bo	*cb_color_frag_bo[8]; /* unused */
-	struct radeon_bo	*cb_color_tile_bo[8]; /* unused */
+	u64			cb_color_bo_offset[8];
+	struct radeon_bo	*cb_color_frag_bo[8];
+	u64			cb_color_frag_offset[8];
+	struct radeon_bo	*cb_color_tile_bo[8];
+	u64			cb_color_tile_offset[8];
+	u32			cb_color_mask[8];
 	u32			cb_color_info[8];
 	u32			cb_color_view[8];
 	u32			cb_color_size_idx[8]; /* unused */
@@ -349,10 +353,6 @@ static int r600_cs_track_validate_cb(struct radeon_cs_parser *p, int i)
 	unsigned array_mode;
 	u32 format;
 
-	if (G_0280A0_TILE_MODE(track->cb_color_info[i])) {
-		dev_warn(p->dev, "FMASK or CMASK buffer are not supported by this kernel\n");
-		return -EINVAL;
-	}
 	size = radeon_bo_size(track->cb_color_bo[i]) - track->cb_color_bo_offset[i];
 	format = G_0280A0_FORMAT(track->cb_color_info[i]);
 	if (!r600_fmt_is_valid_color(format)) {
@@ -420,7 +420,8 @@ static int r600_cs_track_validate_cb(struct radeon_cs_parser *p, int i)
 	}
 
 	/* check offset */
-	tmp = r600_fmt_get_nblocksy(format, height) * r600_fmt_get_nblocksx(format, pitch) * r600_fmt_get_blocksize(format);
+	tmp = r600_fmt_get_nblocksy(format, height) * r600_fmt_get_nblocksx(format, pitch) *
+	      r600_fmt_get_blocksize(format) * track->nsamples;
 	switch (array_mode) {
 	default:
 	case V_0280A0_ARRAY_LINEAR_GENERAL:
@@ -441,7 +442,7 @@ static int r600_cs_track_validate_cb(struct radeon_cs_parser *p, int i)
 			 * broken userspace.
 			 */
 		} else {
-			dev_warn(p->dev, "%s offset[%d] %d %d %d %lu too big (%d %d) (%d %d %d)\n",
+			dev_warn(p->dev, "%s offset[%d] %d %llu %d %lu too big (%d %d) (%d %d %d)\n",
 				 __func__, i, array_mode,
 				 track->cb_color_bo_offset[i], tmp,
 				 radeon_bo_size(track->cb_color_bo[i]),
@@ -458,6 +459,51 @@ static int r600_cs_track_validate_cb(struct radeon_cs_parser *p, int i)
 	tmp = S_028060_PITCH_TILE_MAX((pitch / 8) - 1) |
 		S_028060_SLICE_TILE_MAX(slice_tile_max - 1);
 	ib[track->cb_color_size_idx[i]] = tmp;
+
+	/* FMASK/CMASK */
+	switch (G_0280A0_TILE_MODE(track->cb_color_info[i])) {
+	case V_0280A0_TILE_DISABLE:
+		break;
+	case V_0280A0_FRAG_ENABLE:
+		if (track->nsamples > 1) {
+			uint32_t tile_max = G_028100_FMASK_TILE_MAX(track->cb_color_mask[i]);
+			/* the tile size is 8x8, but the size is in units of bits.
+			 * for bytes, do just * 8. */
+			uint32_t bytes = track->nsamples * track->log_nsamples * 8 * (tile_max + 1);
+
+			if (bytes + track->cb_color_frag_offset[i] >
+			    radeon_bo_size(track->cb_color_frag_bo[i])) {
+				dev_warn(p->dev, "%s FMASK_TILE_MAX too large "
+					 "(tile_max=%u, bytes=%u, offset=%llu, bo_size=%lu)\n",
+					 __func__, tile_max, bytes,
+					 track->cb_color_frag_offset[i],
+					 radeon_bo_size(track->cb_color_frag_bo[i]));
+				return -EINVAL;
+			}
+		}
+		/* fall through */
+	case V_0280A0_CLEAR_ENABLE:
+	{
+		uint32_t block_max = G_028100_CMASK_BLOCK_MAX(track->cb_color_mask[i]);
+		/* One block = 128x128 pixels, one 8x8 tile has 4 bits..
+		 * (128*128) / (8*8) / 2 = 128 bytes per block. */
+		uint32_t bytes = (block_max + 1) * 128;
+
+		if (bytes + track->cb_color_tile_offset[i] >
+		    radeon_bo_size(track->cb_color_tile_bo[i])) {
+			dev_warn(p->dev, "%s CMASK_BLOCK_MAX too large "
+				 "(block_max=%u, bytes=%u, offset=%llu, bo_size=%lu)\n",
+				 __func__, block_max, bytes,
+				 track->cb_color_tile_offset[i],
+				 radeon_bo_size(track->cb_color_tile_bo[i]));
+			return -EINVAL;
+		}
+		break;
+	}
+	default:
+		dev_warn(p->dev, "%s invalid tile mode\n", __func__);
+		return -EINVAL;
+	}
 	return 0;
 }
 
@@ -566,7 +612,7 @@ static int r600_cs_track_validate_db(struct radeon_cs_parser *p)
 
 		ntiles = G_028000_SLICE_TILE_MAX(track->db_depth_size) + 1;
 		nviews = G_028004_SLICE_MAX(track->db_depth_view) + 1;
-		tmp = ntiles * bpe * 64 * nviews;
+		tmp = ntiles * bpe * 64 * nviews * track->nsamples;
 		if ((tmp + track->db_offset) > radeon_bo_size(track->db_bo)) {
 			dev_warn(p->dev, "z/stencil buffer (%d) too small (0x%08X %d %d %d -> %u have %lu)\n",
 					array_mode,
@@ -1231,6 +1277,7 @@ static int r600_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 		break;
 	case R_028C04_PA_SC_AA_CONFIG:
 		tmp = G_028C04_MSAA_NUM_SAMPLES(radeon_get_ib_value(p, idx));
+		track->log_nsamples = tmp;
 		track->nsamples = 1 << tmp;
 		track->cb_dirty = true;
 		break;
@@ -1312,16 +1359,21 @@ static int r600_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 				dev_err(p->dev, "Broken old userspace ? no cb_color0_base supplied before trying to write 0x%08X\n", reg);
 				return -EINVAL;
 			}
-			ib[idx] = track->cb_color_base_last[tmp];
 			track->cb_color_frag_bo[tmp] = track->cb_color_bo[tmp];
+			track->cb_color_frag_offset[tmp] = track->cb_color_bo_offset[tmp];
+			ib[idx] = track->cb_color_base_last[tmp];
 		} else {
 			r = r600_cs_packet_next_reloc(p, &reloc);
 			if (r) {
 				dev_err(p->dev, "bad SET_CONTEXT_REG 0x%04X\n", reg);
 				return -EINVAL;
 			}
-			ib[idx] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
 			track->cb_color_frag_bo[tmp] = reloc->robj;
+			track->cb_color_frag_offset[tmp] = (u64)ib[idx] << 8;
+			ib[idx] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
+		}
+		if (G_0280A0_TILE_MODE(track->cb_color_info[tmp])) {
+			track->cb_dirty = true;
 		}
 		break;
 	case R_0280C0_CB_COLOR0_TILE:
@@ -1338,16 +1390,35 @@ static int r600_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 				dev_err(p->dev, "Broken old userspace ? no cb_color0_base supplied before trying to write 0x%08X\n", reg);
 				return -EINVAL;
 			}
-			ib[idx] = track->cb_color_base_last[tmp];
 			track->cb_color_tile_bo[tmp] = track->cb_color_bo[tmp];
+			track->cb_color_tile_offset[tmp] = track->cb_color_bo_offset[tmp];
+			ib[idx] = track->cb_color_base_last[tmp];
 		} else {
 			r = r600_cs_packet_next_reloc(p, &reloc);
 			if (r) {
 				dev_err(p->dev, "bad SET_CONTEXT_REG 0x%04X\n", reg);
 				return -EINVAL;
 			}
-			ib[idx] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
 			track->cb_color_tile_bo[tmp] = reloc->robj;
+			track->cb_color_tile_offset[tmp] = (u64)ib[idx] << 8;
+			ib[idx] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
+		}
+		if (G_0280A0_TILE_MODE(track->cb_color_info[tmp])) {
+			track->cb_dirty = true;
+		}
+		break;
+	case R_028100_CB_COLOR0_MASK:
+	case R_028104_CB_COLOR1_MASK:
+	case R_028108_CB_COLOR2_MASK:
+	case R_02810C_CB_COLOR3_MASK:
+	case R_028110_CB_COLOR4_MASK:
+	case R_028114_CB_COLOR5_MASK:
+	case R_028118_CB_COLOR6_MASK:
+	case R_02811C_CB_COLOR7_MASK:
+		tmp = (reg - R_028100_CB_COLOR0_MASK) / 4;
+		track->cb_color_mask[tmp] = ib[idx];
+		if (G_0280A0_TILE_MODE(track->cb_color_info[tmp])) {
+			track->cb_dirty = true;
 		}
 		break;
 	case CB_COLOR0_BASE:
@@ -1492,7 +1563,7 @@ unsigned r600_mip_minify(unsigned size, unsigned level)
 }
 
 static void r600_texture_size(unsigned nfaces, unsigned blevel, unsigned llevel,
-			      unsigned w0, unsigned h0, unsigned d0, unsigned format,
+			      unsigned w0, unsigned h0, unsigned d0, unsigned nsamples, unsigned format,
 			      unsigned block_align, unsigned height_align, unsigned base_align,
 			      unsigned *l0_size, unsigned *mipmap_size)
 {
@@ -1520,7 +1591,7 @@ static void r600_texture_size(unsigned nfaces, unsigned blevel, unsigned llevel,
 
 		depth = r600_mip_minify(d0, i);
 
-		size = nbx * nby * blocksize;
+		size = nbx * nby * blocksize * nsamples;
 		if (nfaces)
 			size *= nfaces;
 		else
@@ -1672,7 +1743,7 @@ static int r600_check_texture_resource(struct radeon_cs_parser *p,  u32 idx,
 
 		nfaces = larray - barray + 1;
 	}
-	r600_texture_size(nfaces, blevel, llevel, w0, h0, d0, format,
+	r600_texture_size(nfaces, blevel, llevel, w0, h0, d0, array_check.nsamples, format,
 			  pitch_align, height_align, base_align,
 			  &l0_size, &mipmap_size);
 	/* using get ib will give us the offset into the texture bo */

drivers/gpu/drm/radeon/r600d.h

@@ -92,6 +92,20 @@
 #define R_028094_CB_COLOR5_VIEW                      0x028094
 #define R_028098_CB_COLOR6_VIEW                      0x028098
 #define R_02809C_CB_COLOR7_VIEW                      0x02809C
+#define R_028100_CB_COLOR0_MASK                      0x028100
+#define   S_028100_CMASK_BLOCK_MAX(x)                  (((x) & 0xFFF) << 0)
+#define   G_028100_CMASK_BLOCK_MAX(x)                  (((x) >> 0) & 0xFFF)
+#define   C_028100_CMASK_BLOCK_MAX                     0xFFFFF000
+#define   S_028100_FMASK_TILE_MAX(x)                   (((x) & 0xFFFFF) << 12)
+#define   G_028100_FMASK_TILE_MAX(x)                   (((x) >> 12) & 0xFFFFF)
+#define   C_028100_FMASK_TILE_MAX                      0x00000FFF
+#define R_028104_CB_COLOR1_MASK                      0x028104
+#define R_028108_CB_COLOR2_MASK                      0x028108
+#define R_02810C_CB_COLOR3_MASK                      0x02810C
+#define R_028110_CB_COLOR4_MASK                      0x028110
+#define R_028114_CB_COLOR5_MASK                      0x028114
+#define R_028118_CB_COLOR6_MASK                      0x028118
+#define R_02811C_CB_COLOR7_MASK                      0x02811C
 #define CB_COLOR0_INFO                                  0x280a0
 #	define CB_FORMAT(x)				((x) << 2)
 #       define CB_ARRAY_MODE(x)                         ((x) << 8)
@@ -1400,6 +1414,9 @@
 #define   S_0280A0_TILE_MODE(x)                        (((x) & 0x3) << 18)
 #define   G_0280A0_TILE_MODE(x)                        (((x) >> 18) & 0x3)
 #define   C_0280A0_TILE_MODE                           0xFFF3FFFF
+#define     V_0280A0_TILE_DISABLE			0
+#define     V_0280A0_CLEAR_ENABLE			1
+#define     V_0280A0_FRAG_ENABLE			2
 #define   S_0280A0_BLEND_CLAMP(x)                      (((x) & 0x1) << 20)
 #define   G_0280A0_BLEND_CLAMP(x)                      (((x) >> 20) & 0x1)
 #define   C_0280A0_BLEND_CLAMP                         0xFFEFFFFF

drivers/gpu/drm/radeon/radeon.h

@@ -142,21 +142,6 @@ struct radeon_device;
 /*
  * BIOS.
  */
-#define ATRM_BIOS_PAGE 4096
-
-#if defined(CONFIG_VGA_SWITCHEROO)
-bool radeon_atrm_supported(struct pci_dev *pdev);
-int radeon_atrm_get_bios_chunk(uint8_t *bios, int offset, int len);
-#else
-static inline bool radeon_atrm_supported(struct pci_dev *pdev)
-{
-	return false;
-}
-
-static inline int radeon_atrm_get_bios_chunk(uint8_t *bios, int offset, int len){
-	return -EINVAL;
-}
-#endif
 bool radeon_get_bios(struct radeon_device *rdev);
 
 /*

drivers/gpu/drm/radeon/radeon_atombios.c

@@ -452,7 +452,7 @@ static bool radeon_atom_apply_quirks(struct drm_device *dev,
 	}
 
 	/* Fujitsu D3003-S2 board lists DVI-I as DVI-D and VGA */
-	if ((dev->pdev->device == 0x9802) &&
+	if (((dev->pdev->device == 0x9802) || (dev->pdev->device == 0x9806)) &&
 	    (dev->pdev->subsystem_vendor == 0x1734) &&
 	    (dev->pdev->subsystem_device == 0x11bd)) {
 		if (*connector_type == DRM_MODE_CONNECTOR_VGA) {

drivers/gpu/drm/radeon/radeon_atpx_handler.c

@@ -30,57 +30,8 @@ static struct radeon_atpx_priv {
 	/* handle for device - and atpx */
 	acpi_handle dhandle;
 	acpi_handle atpx_handle;
-	acpi_handle atrm_handle;
 } radeon_atpx_priv;
 
-/* retrieve the ROM in 4k blocks */
-static int radeon_atrm_call(acpi_handle atrm_handle, uint8_t *bios,
-			    int offset, int len)
-{
-	acpi_status status;
-	union acpi_object atrm_arg_elements[2], *obj;
-	struct acpi_object_list atrm_arg;
-	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL};
-
-	atrm_arg.count = 2;
-	atrm_arg.pointer = &atrm_arg_elements[0];
-
-	atrm_arg_elements[0].type = ACPI_TYPE_INTEGER;
-	atrm_arg_elements[0].integer.value = offset;
-
-	atrm_arg_elements[1].type = ACPI_TYPE_INTEGER;
-	atrm_arg_elements[1].integer.value = len;
-
-	status = acpi_evaluate_object(atrm_handle, NULL, &atrm_arg, &buffer);
-	if (ACPI_FAILURE(status)) {
-		printk("failed to evaluate ATRM got %s\n", acpi_format_exception(status));
-		return -ENODEV;
-	}
-
-	obj = (union acpi_object *)buffer.pointer;
-	memcpy(bios+offset, obj->buffer.pointer, obj->buffer.length);
-	len = obj->buffer.length;
-	kfree(buffer.pointer);
-	return len;
-}
-
-bool radeon_atrm_supported(struct pci_dev *pdev)
-{
-	/* get the discrete ROM only via ATRM */
-	if (!radeon_atpx_priv.atpx_detected)
-		return false;
-
-	if (radeon_atpx_priv.dhandle == DEVICE_ACPI_HANDLE(&pdev->dev))
-		return false;
-	return true;
-}
-
-
-int radeon_atrm_get_bios_chunk(uint8_t *bios, int offset, int len)
-{
-	return radeon_atrm_call(radeon_atpx_priv.atrm_handle, bios, offset, len);
-}
-
 static int radeon_atpx_get_version(acpi_handle handle)
 {
 	acpi_status status;
@@ -198,7 +149,7 @@ static int radeon_atpx_power_state(enum vga_switcheroo_client_id id,
 
 static bool radeon_atpx_pci_probe_handle(struct pci_dev *pdev)
 {
-	acpi_handle dhandle, atpx_handle, atrm_handle;
+	acpi_handle dhandle, atpx_handle;
 	acpi_status status;
 
 	dhandle = DEVICE_ACPI_HANDLE(&pdev->dev);
@@ -209,13 +160,8 @@ static bool radeon_atpx_pci_probe_handle(struct pci_dev *pdev)
 	if (ACPI_FAILURE(status))
 		return false;
 
-	status = acpi_get_handle(dhandle, "ATRM", &atrm_handle);
-	if (ACPI_FAILURE(status))
-		return false;
-
 	radeon_atpx_priv.dhandle = dhandle;
 	radeon_atpx_priv.atpx_handle = atpx_handle;
-	radeon_atpx_priv.atrm_handle = atrm_handle;
 	return true;
 }
 

drivers/gpu/drm/radeon/radeon_bios.c

@@ -32,6 +32,7 @@
 
 #include <linux/vga_switcheroo.h>
 #include <linux/slab.h>
+#include <linux/acpi.h>
 /*
  * BIOS.
  */
@@ -98,16 +99,81 @@ static bool radeon_read_bios(struct radeon_device *rdev)
 	return true;
 }
 
+#ifdef CONFIG_ACPI
 /* ATRM is used to get the BIOS on the discrete cards in
  * dual-gpu systems.
  */
+/* retrieve the ROM in 4k blocks */
+#define ATRM_BIOS_PAGE 4096
+/**
+ * radeon_atrm_call - fetch a chunk of the vbios
+ *
+ * @atrm_handle: acpi ATRM handle
+ * @bios: vbios image pointer
+ * @offset: offset of vbios image data to fetch
+ * @len: length of vbios image data to fetch
+ *
+ * Executes ATRM to fetch a chunk of the discrete
+ * vbios image on PX systems (all asics).
+ * Returns the length of the buffer fetched.
+ */
+static int radeon_atrm_call(acpi_handle atrm_handle, uint8_t *bios,
+			    int offset, int len)
+{
+	acpi_status status;
+	union acpi_object atrm_arg_elements[2], *obj;
+	struct acpi_object_list atrm_arg;
+	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL};
+
+	atrm_arg.count = 2;
+	atrm_arg.pointer = &atrm_arg_elements[0];
+
+	atrm_arg_elements[0].type = ACPI_TYPE_INTEGER;
+	atrm_arg_elements[0].integer.value = offset;
+
+	atrm_arg_elements[1].type = ACPI_TYPE_INTEGER;
+	atrm_arg_elements[1].integer.value = len;
+
+	status = acpi_evaluate_object(atrm_handle, NULL, &atrm_arg, &buffer);
+	if (ACPI_FAILURE(status)) {
+		printk("failed to evaluate ATRM got %s\n", acpi_format_exception(status));
+		return -ENODEV;
+	}
+
+	obj = (union acpi_object *)buffer.pointer;
+	memcpy(bios+offset, obj->buffer.pointer, obj->buffer.length);
+	len = obj->buffer.length;
+	kfree(buffer.pointer);
+	return len;
+}
+
 static bool radeon_atrm_get_bios(struct radeon_device *rdev)
 {
 	int ret;
 	int size = 256 * 1024;
 	int i;
+	struct pci_dev *pdev = NULL;
+	acpi_handle dhandle, atrm_handle;
+	acpi_status status;
+	bool found = false;
 
-	if (!radeon_atrm_supported(rdev->pdev))
+	/* ATRM is for the discrete card only */
+	if (rdev->flags & RADEON_IS_IGP)
+		return false;
+
+	while ((pdev = pci_get_class(PCI_CLASS_DISPLAY_VGA << 8, pdev)) != NULL) {
+		dhandle = DEVICE_ACPI_HANDLE(&pdev->dev);
+		if (!dhandle)
+			continue;
+
+		status = acpi_get_handle(dhandle, "ATRM", &atrm_handle);
+		if (!ACPI_FAILURE(status)) {
+			found = true;
+			break;
+		}
+	}
+
+	if (!found)
 		return false;
 
 	rdev->bios = kmalloc(size, GFP_KERNEL);
@@ -117,9 +183,10 @@ static bool radeon_atrm_get_bios(struct radeon_device *rdev)
 	}
 
 	for (i = 0; i < size / ATRM_BIOS_PAGE; i++) {
-		ret = radeon_atrm_get_bios_chunk(rdev->bios,
-						 (i * ATRM_BIOS_PAGE),
-						 ATRM_BIOS_PAGE);
+		ret = radeon_atrm_call(atrm_handle,
+				       rdev->bios,
+				       (i * ATRM_BIOS_PAGE),
+				       ATRM_BIOS_PAGE);
 		if (ret < ATRM_BIOS_PAGE)
 			break;
 	}
@@ -130,6 +197,12 @@ static bool radeon_atrm_get_bios(struct radeon_device *rdev)
 	}
 	return true;
 }
+#else
+static inline bool radeon_atrm_get_bios(struct radeon_device *rdev)
+{
+	return false;
+}
+#endif
 
 static bool ni_read_disabled_bios(struct radeon_device *rdev)
 {
@@ -476,6 +549,61 @@ static bool radeon_read_disabled_bios(struct radeon_device *rdev)
 		return legacy_read_disabled_bios(rdev);
 }
 
+#ifdef CONFIG_ACPI
+static bool radeon_acpi_vfct_bios(struct radeon_device *rdev)
+{
+	bool ret = false;
+	struct acpi_table_header *hdr;
+	acpi_size tbl_size;
+	UEFI_ACPI_VFCT *vfct;
+	GOP_VBIOS_CONTENT *vbios;
+	VFCT_IMAGE_HEADER *vhdr;
+
+	if (!ACPI_SUCCESS(acpi_get_table_with_size("VFCT", 1, &hdr, &tbl_size)))
+		return false;
+	if (tbl_size < sizeof(UEFI_ACPI_VFCT)) {
+		DRM_ERROR("ACPI VFCT table present but broken (too short #1)\n");
+		goto out_unmap;
+	}
+
+	vfct = (UEFI_ACPI_VFCT *)hdr;
+	if (vfct->VBIOSImageOffset + sizeof(VFCT_IMAGE_HEADER) > tbl_size) {
+		DRM_ERROR("ACPI VFCT table present but broken (too short #2)\n");
+		goto out_unmap;
+	}
+
+	vbios = (GOP_VBIOS_CONTENT *)((char *)hdr + vfct->VBIOSImageOffset);
+	vhdr = &vbios->VbiosHeader;
+	DRM_INFO("ACPI VFCT contains a BIOS for %02x:%02x.%d %04x:%04x, size %d\n",
+			vhdr->PCIBus, vhdr->PCIDevice, vhdr->PCIFunction,
+			vhdr->VendorID, vhdr->DeviceID, vhdr->ImageLength);
+
+	if (vhdr->PCIBus != rdev->pdev->bus->number ||
+	    vhdr->PCIDevice != PCI_SLOT(rdev->pdev->devfn) ||
+	    vhdr->PCIFunction != PCI_FUNC(rdev->pdev->devfn) ||
+	    vhdr->VendorID != rdev->pdev->vendor ||
+	    vhdr->DeviceID != rdev->pdev->device) {
+		DRM_INFO("ACPI VFCT table is not for this card\n");
+		goto out_unmap;
+	};
+
+	if (vfct->VBIOSImageOffset + sizeof(VFCT_IMAGE_HEADER) + vhdr->ImageLength > tbl_size) {
+		DRM_ERROR("ACPI VFCT image truncated\n");
+		goto out_unmap;
+	}
+
+	rdev->bios = kmemdup(&vbios->VbiosContent, vhdr->ImageLength, GFP_KERNEL);
+	ret = !!rdev->bios;
+
+out_unmap:
+	return ret;
+}
+#else
+static inline bool radeon_acpi_vfct_bios(struct radeon_device *rdev)
+{
+	return false;
+}
+#endif
 
 bool radeon_get_bios(struct radeon_device *rdev)
 {
@@ -483,6 +611,8 @@ bool radeon_get_bios(struct radeon_device *rdev)
 	uint16_t tmp;
 
 	r = radeon_atrm_get_bios(rdev);
+	if (r == false)
+		r = radeon_acpi_vfct_bios(rdev);
 	if (r == false)
 		r = igp_read_bios_from_vram(rdev);
 	if (r == false)

drivers/gpu/drm/radeon/radeon_drv.c

@@ -62,9 +62,10 @@
  *   2.18.0 - r600-eg: allow "invalid" DB formats
  *   2.19.0 - r600-eg: MSAA textures
  *   2.20.0 - r600-si: RADEON_INFO_TIMESTAMP query
+ *   2.21.0 - r600-r700: FMASK and CMASK
  */
 #define KMS_DRIVER_MAJOR	2
-#define KMS_DRIVER_MINOR	20
+#define KMS_DRIVER_MINOR	21
 #define KMS_DRIVER_PATCHLEVEL	0
 int radeon_driver_load_kms(struct drm_device *dev, unsigned long flags);
 int radeon_driver_unload_kms(struct drm_device *dev);

drivers/gpu/drm/radeon/radeon_object.c

@@ -132,6 +132,7 @@ int radeon_bo_create(struct radeon_device *rdev,
 	acc_size = ttm_bo_dma_acc_size(&rdev->mman.bdev, size,
 				       sizeof(struct radeon_bo));
 
+retry:
 	bo = kzalloc(sizeof(struct radeon_bo), GFP_KERNEL);
 	if (bo == NULL)
 		return -ENOMEM;
@@ -145,8 +146,6 @@ int radeon_bo_create(struct radeon_device *rdev,
 	bo->surface_reg = -1;
 	INIT_LIST_HEAD(&bo->list);
 	INIT_LIST_HEAD(&bo->va);
-
-retry:
 	radeon_ttm_placement_from_domain(bo, domain);
 	/* Kernel allocation are uninterruptible */
 	down_read(&rdev->pm.mclk_lock);

drivers/gpu/drm/radeon/radeon_ring.c

@@ -706,6 +706,7 @@ int radeon_ring_init(struct radeon_device *rdev, struct radeon_ring *ring, unsig
 	if (radeon_debugfs_ring_init(rdev, ring)) {
 		DRM_ERROR("Failed to register debugfs file for rings !\n");
 	}
+	radeon_ring_lockup_update(ring);
 	return 0;
 }
 

drivers/gpu/drm/radeon/reg_srcs/r600

@@ -744,14 +744,6 @@ r600 0x9400
 0x00028C38 CB_CLRCMP_DST
 0x00028C3C CB_CLRCMP_MSK
 0x00028C34 CB_CLRCMP_SRC
-0x00028100 CB_COLOR0_MASK
-0x00028104 CB_COLOR1_MASK
-0x00028108 CB_COLOR2_MASK
-0x0002810C CB_COLOR3_MASK
-0x00028110 CB_COLOR4_MASK
-0x00028114 CB_COLOR5_MASK
-0x00028118 CB_COLOR6_MASK
-0x0002811C CB_COLOR7_MASK
 0x00028808 CB_COLOR_CONTROL
 0x0002842C CB_FOG_BLUE
 0x00028428 CB_FOG_GREEN

drivers/gpu/drm/udl/Kconfig

@@ -1,6 +1,7 @@
 config DRM_UDL
 	tristate "DisplayLink"
 	depends on DRM && EXPERIMENTAL
+	depends on USB_ARCH_HAS_HCD
 	select DRM_USB
 	select FB_SYS_FILLRECT
 	select FB_SYS_COPYAREA

drivers/gpu/drm/udl/udl_modeset.c

@@ -354,8 +354,7 @@ static int udl_crtc_mode_set(struct drm_crtc *crtc,
 
 static void udl_crtc_disable(struct drm_crtc *crtc)
 {
-
-
+	udl_crtc_dpms(crtc, DRM_MODE_DPMS_OFF);
 }
 
 static void udl_crtc_destroy(struct drm_crtc *crtc)

drivers/gpu/drm/vmwgfx/vmwgfx_kms.c

@@ -1688,15 +1688,19 @@ int vmw_du_page_flip(struct drm_crtc *crtc,
 	struct vmw_private *dev_priv = vmw_priv(crtc->dev);
 	struct drm_framebuffer *old_fb = crtc->fb;
 	struct vmw_framebuffer *vfb = vmw_framebuffer_to_vfb(fb);
-	struct drm_file *file_priv = event->base.file_priv;
+	struct drm_file *file_priv ;
 	struct vmw_fence_obj *fence = NULL;
 	struct drm_clip_rect clips;
 	int ret;
 
+	if (event == NULL)
+		return -EINVAL;
+
 	/* require ScreenObject support for page flipping */
 	if (!dev_priv->sou_priv)
 		return -ENOSYS;
 
+	file_priv = event->base.file_priv;
 	if (!vmw_kms_screen_object_flippable(dev_priv, crtc))
 		return -EINVAL;
 

drivers/gpu/vga/vga_switcheroo.c

@@ -70,27 +70,12 @@ static struct vgasr_priv vgasr_priv = {
 	.clients = LIST_HEAD_INIT(vgasr_priv.clients),
 };
 
-int vga_switcheroo_register_handler(struct vga_switcheroo_handler *handler)
+static bool vga_switcheroo_ready(void)
 {
-	mutex_lock(&vgasr_mutex);
-	if (vgasr_priv.handler) {
-		mutex_unlock(&vgasr_mutex);
-		return -EINVAL;
-	}
-
-	vgasr_priv.handler = handler;
-	mutex_unlock(&vgasr_mutex);
-	return 0;
+	/* we're ready if we get two clients + handler */
+	return !vgasr_priv.active &&
+	       vgasr_priv.registered_clients == 2 && vgasr_priv.handler;
 }
-EXPORT_SYMBOL(vga_switcheroo_register_handler);
-
-void vga_switcheroo_unregister_handler(void)
-{
-	mutex_lock(&vgasr_mutex);
-	vgasr_priv.handler = NULL;
-	mutex_unlock(&vgasr_mutex);
-}
-EXPORT_SYMBOL(vga_switcheroo_unregister_handler);
 
 static void vga_switcheroo_enable(void)
 {
@@ -98,7 +83,8 @@ static void vga_switcheroo_enable(void)
 	struct vga_switcheroo_client *client;
 
 	/* call the handler to init */
-	vgasr_priv.handler->init();
+	if (vgasr_priv.handler->init)
+		vgasr_priv.handler->init();
 
 	list_for_each_entry(client, &vgasr_priv.clients, list) {
 		if (client->id != -1)
@@ -113,6 +99,37 @@ static void vga_switcheroo_enable(void)
 	vgasr_priv.active = true;
 }
 
+int vga_switcheroo_register_handler(struct vga_switcheroo_handler *handler)
+{
+	mutex_lock(&vgasr_mutex);
+	if (vgasr_priv.handler) {
+		mutex_unlock(&vgasr_mutex);
+		return -EINVAL;
+	}
+
+	vgasr_priv.handler = handler;
+	if (vga_switcheroo_ready()) {
+		printk(KERN_INFO "vga_switcheroo: enabled\n");
+		vga_switcheroo_enable();
+	}
+	mutex_unlock(&vgasr_mutex);
+	return 0;
+}
+EXPORT_SYMBOL(vga_switcheroo_register_handler);
+
+void vga_switcheroo_unregister_handler(void)
+{
+	mutex_lock(&vgasr_mutex);
+	vgasr_priv.handler = NULL;
+	if (vgasr_priv.active) {
+		pr_info("vga_switcheroo: disabled\n");
+		vga_switcheroo_debugfs_fini(&vgasr_priv);
+		vgasr_priv.active = false;
+	}
+	mutex_unlock(&vgasr_mutex);
+}
+EXPORT_SYMBOL(vga_switcheroo_unregister_handler);
+
 static int register_client(struct pci_dev *pdev,
 			   const struct vga_switcheroo_client_ops *ops,
 			   int id, bool active)
@@ -134,9 +151,7 @@ static int register_client(struct pci_dev *pdev,
 	if (client_is_vga(client))
 		vgasr_priv.registered_clients++;
 
-	/* if we get two clients + handler */
-	if (!vgasr_priv.active &&
-	    vgasr_priv.registered_clients == 2 && vgasr_priv.handler) {
+	if (vga_switcheroo_ready()) {
 		printk(KERN_INFO "vga_switcheroo: enabled\n");
 		vga_switcheroo_enable();
 	}

drivers/hwmon/coretemp.c

@@ -196,7 +196,7 @@ struct tjmax {
 	int tjmax;
 };
 
-static struct tjmax __cpuinitconst tjmax_table[] = {
+static const struct tjmax __cpuinitconst tjmax_table[] = {
 	{ "CPU D410", 100000 },
 	{ "CPU D425", 100000 },
 	{ "CPU D510", 100000 },

drivers/hwmon/w83627hf.c

@@ -1206,7 +1206,7 @@ static int __init w83627hf_find(int sioaddr, unsigned short *addr,
 	int err = -ENODEV;
 	u16 val;
 
-	static const __initdata char *names[] = {
+	static __initconst char *const names[] = {
 		"W83627HF",
 		"W83627THF",
 		"W83697HF",