Merge branch 'linus' into timers/urgent

Merge in Linus's branch which already has timers/core merged.

Signed-off-by: Ingo Molnar <mingo@kernel.org>

Documentation/RCU/checklist.txt

@@ -162,9 +162,9 @@ over a rather long period of time, but improvements are always welcome!
 		when publicizing a pointer to a structure that can
 		be traversed by an RCU read-side critical section.
 
-5.	If call_rcu(), or a related primitive such as call_rcu_bh() or
-	call_rcu_sched(), is used, the callback function must be
-	written to be called from softirq context.  In particular,
+5.	If call_rcu(), or a related primitive such as call_rcu_bh(),
+	call_rcu_sched(), or call_srcu() is used, the callback function
+	must be written to be called from softirq context.  In particular,
 	it cannot block.
 
 6.	Since synchronize_rcu() can block, it cannot be called from
@@ -202,11 +202,12 @@ over a rather long period of time, but improvements are always welcome!
 	updater uses call_rcu_sched() or synchronize_sched(), then
 	the corresponding readers must disable preemption, possibly
 	by calling rcu_read_lock_sched() and rcu_read_unlock_sched().
-	If the updater uses synchronize_srcu(), the the corresponding
-	readers must use srcu_read_lock() and srcu_read_unlock(),
-	and with the same srcu_struct.	The rules for the expedited
-	primitives are the same as for their non-expedited counterparts.
-	Mixing things up will result in confusion and broken kernels.
+	If the updater uses synchronize_srcu() or call_srcu(),
+	the the corresponding readers must use srcu_read_lock() and
+	srcu_read_unlock(), and with the same srcu_struct.  The rules for
+	the expedited primitives are the same as for their non-expedited
+	counterparts.  Mixing things up will result in confusion and
+	broken kernels.
 
 	One exception to this rule: rcu_read_lock() and rcu_read_unlock()
 	may be substituted for rcu_read_lock_bh() and rcu_read_unlock_bh()
@@ -333,14 +334,14 @@ over a rather long period of time, but improvements are always welcome!
 	victim CPU from ever going offline.)
 
 14.	SRCU (srcu_read_lock(), srcu_read_unlock(), srcu_dereference(),
-	synchronize_srcu(), and synchronize_srcu_expedited()) may only
-	be invoked from process context.  Unlike other forms of RCU, it
-	-is- permissible to block in an SRCU read-side critical section
-	(demarked by srcu_read_lock() and srcu_read_unlock()), hence the
-	"SRCU": "sleepable RCU".  Please note that if you don't need
-	to sleep in read-side critical sections, you should be using
-	RCU rather than SRCU, because RCU is almost always faster and
-	easier to use than is SRCU.
+	synchronize_srcu(), synchronize_srcu_expedited(), and call_srcu())
+	may only be invoked from process context.  Unlike other forms of
+	RCU, it -is- permissible to block in an SRCU read-side critical
+	section (demarked by srcu_read_lock() and srcu_read_unlock()),
+	hence the "SRCU": "sleepable RCU".  Please note that if you
+	don't need to sleep in read-side critical sections, you should be
+	using RCU rather than SRCU, because RCU is almost always faster
+	and easier to use than is SRCU.
 
 	If you need to enter your read-side critical section in a
 	hardirq or exception handler, and then exit that same read-side
@@ -353,8 +354,8 @@ over a rather long period of time, but improvements are always welcome!
 	cleanup_srcu_struct().	These are passed a "struct srcu_struct"
 	that defines the scope of a given SRCU domain.	Once initialized,
 	the srcu_struct is passed to srcu_read_lock(), srcu_read_unlock()
-	synchronize_srcu(), and synchronize_srcu_expedited().  A given
-	synchronize_srcu() waits only for SRCU read-side critical
+	synchronize_srcu(), synchronize_srcu_expedited(), and call_srcu().
+	A given synchronize_srcu() waits only for SRCU read-side critical
 	sections governed by srcu_read_lock() and srcu_read_unlock()
 	calls that have been passed the same srcu_struct.  This property
 	is what makes sleeping read-side critical sections tolerable --
@@ -374,7 +375,7 @@ over a rather long period of time, but improvements are always welcome!
 	requiring SRCU's read-side deadlock immunity or low read-side
 	realtime latency.
 
-	Note that, rcu_assign_pointer() relates to SRCU just as they do
+	Note that, rcu_assign_pointer() relates to SRCU just as it does
 	to other forms of RCU.
 
 15.	The whole point of call_rcu(), synchronize_rcu(), and friends

Documentation/RCU/rcubarrier.txt

@@ -79,8 +79,6 @@ complete. Pseudo-code using rcu_barrier() is as follows:
    2. Execute rcu_barrier().
    3. Allow the module to be unloaded.
 
-Quick Quiz #1: Why is there no srcu_barrier()?
-
 The rcutorture module makes use of rcu_barrier in its exit function
 as follows:
 
@@ -162,7 +160,7 @@ for any pre-existing callbacks to complete.
 Then lines 55-62 print status and do operation-specific cleanup, and
 then return, permitting the module-unload operation to be completed.
 
-Quick Quiz #2: Is there any other situation where rcu_barrier() might
+Quick Quiz #1: Is there any other situation where rcu_barrier() might
 	be required?
 
 Your module might have additional complications. For example, if your
@@ -242,7 +240,7 @@ reaches zero, as follows:
  4 complete(&rcu_barrier_completion);
  5 }
 
-Quick Quiz #3: What happens if CPU 0's rcu_barrier_func() executes
+Quick Quiz #2: What happens if CPU 0's rcu_barrier_func() executes
 	immediately (thus incrementing rcu_barrier_cpu_count to the
 	value one), but the other CPU's rcu_barrier_func() invocations
 	are delayed for a full grace period? Couldn't this result in
@@ -259,12 +257,7 @@ so that your module may be safely unloaded.
 
 Answers to Quick Quizzes
 
-Quick Quiz #1: Why is there no srcu_barrier()?
-
-Answer: Since there is no call_srcu(), there can be no outstanding SRCU
-	callbacks. Therefore, there is no need to wait for them.
-
-Quick Quiz #2: Is there any other situation where rcu_barrier() might
+Quick Quiz #1: Is there any other situation where rcu_barrier() might
 	be required?
 
 Answer: Interestingly enough, rcu_barrier() was not originally
@@ -278,7 +271,7 @@ Answer: Interestingly enough, rcu_barrier() was not originally
 	implementing rcutorture, and found that rcu_barrier() solves
 	this problem as well.
 
-Quick Quiz #3: What happens if CPU 0's rcu_barrier_func() executes
+Quick Quiz #2: What happens if CPU 0's rcu_barrier_func() executes
 	immediately (thus incrementing rcu_barrier_cpu_count to the
 	value one), but the other CPU's rcu_barrier_func() invocations
 	are delayed for a full grace period? Couldn't this result in

Documentation/RCU/torture.txt

@@ -174,11 +174,20 @@ torture_type	The type of RCU to test, with string values as follows:
 			and synchronize_rcu_bh_expedited().
 
 		"srcu": srcu_read_lock(), srcu_read_unlock() and
+			call_srcu().
+
+		"srcu_sync": srcu_read_lock(), srcu_read_unlock() and
 			synchronize_srcu().
 
 		"srcu_expedited": srcu_read_lock(), srcu_read_unlock() and
 			synchronize_srcu_expedited().
 
+		"srcu_raw": srcu_read_lock_raw(), srcu_read_unlock_raw(),
+			and call_srcu().
+
+		"srcu_raw_sync": srcu_read_lock_raw(), srcu_read_unlock_raw(),
+			and synchronize_srcu().
+
 		"sched": preempt_disable(), preempt_enable(), and
 			call_rcu_sched().
 

Documentation/RCU/whatisRCU.txt

@@ -833,9 +833,9 @@ sched:	Critical sections	Grace period		Barrier
 
 SRCU:	Critical sections	Grace period		Barrier
 
-	srcu_read_lock		synchronize_srcu	N/A
-	srcu_read_unlock	synchronize_srcu_expedited
-	srcu_read_lock_raw
+	srcu_read_lock		synchronize_srcu	srcu_barrier
+	srcu_read_unlock	call_srcu
+	srcu_read_lock_raw	synchronize_srcu_expedited
 	srcu_read_unlock_raw
 	srcu_dereference
 

Documentation/devicetree/bindings/pinctrl/fsl,imx6q-pinctrl.txt

@@ -1626,3 +1626,5 @@ MX6Q_PAD_SD2_DAT3__PCIE_CTRL_MUX_11		1587
 MX6Q_PAD_SD2_DAT3__GPIO_1_12			1588
 MX6Q_PAD_SD2_DAT3__SJC_DONE			1589
 MX6Q_PAD_SD2_DAT3__ANATOP_TESTO_3		1590
+MX6Q_PAD_ENET_RX_ER__ANATOP_USBOTG_ID		1591
+MX6Q_PAD_GPIO_1__ANATOP_USBOTG_ID		1592

Documentation/kdump/kdump.txt

@@ -86,7 +86,7 @@ There is also a gitweb interface available at
 http://www.kernel.org/git/?p=utils/kernel/kexec/kexec-tools.git
 
 More information about kexec-tools can be found at
-http://www.kernel.org/pub/linux/utils/kernel/kexec/README.html
+http://horms.net/projects/kexec/
 
 3) Unpack the tarball with the tar command, as follows:
 

Documentation/kernel-parameters.txt

@@ -2367,6 +2367,11 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			Set maximum number of finished RCU callbacks to process
 			in one batch.
 
+	rcutree.fanout_leaf=	[KNL,BOOT]
+			Increase the number of CPUs assigned to each
+			leaf rcu_node structure.  Useful for very large
+			systems.
+
 	rcutree.qhimark=	[KNL,BOOT]
 			Set threshold of queued
 			RCU callbacks over which batch limiting is disabled.

MAINTAINERS

@@ -3433,13 +3433,14 @@ S:	Supported
 F:	drivers/idle/i7300_idle.c
 
 IEEE 802.15.4 SUBSYSTEM
+M:	Alexander Smirnov <alex.bluesman.smirnov@gmail.com>
 M:	Dmitry Eremin-Solenikov <dbaryshkov@gmail.com>
-M:	Sergey Lapin <slapin@ossfans.org>
 L:	linux-zigbee-devel@lists.sourceforge.net (moderated for non-subscribers)
 W:	http://apps.sourceforge.net/trac/linux-zigbee
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/lowpan/lowpan.git
 S:	Maintained
 F:	net/ieee802154/
+F:	net/mac802154/
 F:	drivers/ieee802154/
 
 IIO SUBSYSTEM AND DRIVERS
@@ -5564,7 +5565,7 @@ F:	Documentation/networking/LICENSE.qla3xxx
 F:	drivers/net/ethernet/qlogic/qla3xxx.*
 
 QLOGIC QLCNIC (1/10)Gb ETHERNET DRIVER
-M:	Anirban Chakraborty <anirban.chakraborty@qlogic.com>
+M:	Jitendra Kalsaria <jitendra.kalsaria@qlogic.com>
 M:	Sony Chacko <sony.chacko@qlogic.com>
 M:	linux-driver@qlogic.com
 L:	netdev@vger.kernel.org
@@ -5572,7 +5573,6 @@ S:	Supported
 F:	drivers/net/ethernet/qlogic/qlcnic/
 
 QLOGIC QLGE 10Gb ETHERNET DRIVER
-M:	Anirban Chakraborty <anirban.chakraborty@qlogic.com>
 M:	Jitendra Kalsaria <jitendra.kalsaria@qlogic.com>
 M:	Ron Mercer <ron.mercer@qlogic.com>
 M:	linux-driver@qlogic.com

Makefile

@@ -1,7 +1,7 @@
 VERSION = 3
 PATCHLEVEL = 5
 SUBLEVEL = 0
-EXTRAVERSION = -rc7
+EXTRAVERSION =
 NAME = Saber-toothed Squirrel
 
 # *DOCUMENTATION*

arch/arm/boot/dts/spear13xx.dtsi

@@ -43,8 +43,8 @@
 
 	pmu {
 		compatible = "arm,cortex-a9-pmu";
-		interrupts = <0 8 0x04
-			      0 9 0x04>;
+		interrupts = <0 6 0x04
+			      0 7 0x04>;
 	};
 
 	L2: l2-cache {
@@ -119,8 +119,8 @@
 		gmac0: eth@e2000000 {
 			compatible = "st,spear600-gmac";
 			reg = <0xe2000000 0x8000>;
-			interrupts = <0 23 0x4
-				      0 24 0x4>;
+			interrupts = <0 33 0x4
+				      0 34 0x4>;
 			interrupt-names = "macirq", "eth_wake_irq";
 			status = "disabled";
 		};
@@ -202,6 +202,7 @@
 			kbd@e0300000 {
 				compatible = "st,spear300-kbd";
 				reg = <0xe0300000 0x1000>;
+				interrupts = <0 52 0x4>;
 				status = "disabled";
 			};
 
@@ -224,7 +225,7 @@
 			serial@e0000000 {
 				compatible = "arm,pl011", "arm,primecell";
 				reg = <0xe0000000 0x1000>;
-				interrupts = <0 36 0x4>;
+				interrupts = <0 35 0x4>;
 				status = "disabled";
 			};
 

arch/arm/boot/dts/spear320-evb.dts

@@ -15,8 +15,8 @@
 /include/ "spear320.dtsi"
 
 / {
-	model = "ST SPEAr300 Evaluation Board";
-	compatible = "st,spear300-evb", "st,spear300";
+	model = "ST SPEAr320 Evaluation Board";
+	compatible = "st,spear320-evb", "st,spear320";
 	#address-cells = <1>;
 	#size-cells = <1>;
 
@@ -26,7 +26,7 @@
 
 	ahb {
 		pinmux@b3000000 {
-			st,pinmux-mode = <3>;
+			st,pinmux-mode = <4>;
 			pinctrl-names = "default";
 			pinctrl-0 = <&state_default>;
 

arch/arm/boot/dts/spear600.dtsi

@@ -181,6 +181,7 @@
 			timer@f0000000 {
 				compatible = "st,spear-timer";
 				reg = <0xf0000000 0x400>;
+				interrupt-parent = <&vic0>;
 				interrupts = <16>;
 			};
 		};

arch/arm/mach-spear3xx/spear3xx.c

@@ -87,7 +87,7 @@ void __init spear3xx_map_io(void)
 
 static void __init spear3xx_timer_init(void)
 {
-	char pclk_name[] = "pll3_48m_clk";
+	char pclk_name[] = "pll3_clk";
 	struct clk *gpt_clk, *pclk;
 
 	spear3xx_clk_init();

arch/arm/mach-spear6xx/spear6xx.c

@@ -423,7 +423,7 @@ void __init spear6xx_map_io(void)
 
 static void __init spear6xx_timer_init(void)
 {
-	char pclk_name[] = "pll3_48m_clk";
+	char pclk_name[] = "pll3_clk";
 	struct clk *gpt_clk, *pclk;
 
 	spear6xx_clk_init();

arch/arm/mm/dma-mapping.c

@@ -1091,7 +1091,7 @@ error:
 	while (--i)
 		if (pages[i])
 			__free_pages(pages[i], 0);
-	if (array_size < PAGE_SIZE)
+	if (array_size <= PAGE_SIZE)
 		kfree(pages);
 	else
 		vfree(pages);
@@ -1106,7 +1106,7 @@ static int __iommu_free_buffer(struct device *dev, struct page **pages, size_t s
 	for (i = 0; i < count; i++)
 		if (pages[i])
 			__free_pages(pages[i], 0);
-	if (array_size < PAGE_SIZE)
+	if (array_size <= PAGE_SIZE)
 		kfree(pages);
 	else
 		vfree(pages);

arch/hexagon/kernel/smp.c

@@ -180,9 +180,7 @@ void __cpuinit start_secondary(void)
 
 	notify_cpu_starting(cpu);
 
-	ipi_call_lock();
 	set_cpu_online(cpu, true);
-	ipi_call_unlock();
 
 	local_irq_enable();
 

arch/ia64/kernel/smpboot.c

@@ -382,7 +382,6 @@ smp_callin (void)
 	set_numa_node(cpu_to_node_map[cpuid]);
 	set_numa_mem(local_memory_node(cpu_to_node_map[cpuid]));
 
-	ipi_call_lock_irq();
 	spin_lock(&vector_lock);
 	/* Setup the per cpu irq handling data structures */
 	__setup_vector_irq(cpuid);
@@ -390,7 +389,6 @@ smp_callin (void)
 	set_cpu_online(cpuid, true);
 	per_cpu(cpu_state, cpuid) = CPU_ONLINE;
 	spin_unlock(&vector_lock);
-	ipi_call_unlock_irq();
 
 	smp_setup_percpu_timer();
 

arch/m32r/boot/compressed/Makefile

@@ -43,9 +43,9 @@ endif
 
 OBJCOPYFLAGS += -R .empty_zero_page
 
-suffix_$(CONFIG_KERNEL_GZIP)	= gz
-suffix_$(CONFIG_KERNEL_BZIP2)	= bz2
-suffix_$(CONFIG_KERNEL_LZMA)	= lzma
+suffix-$(CONFIG_KERNEL_GZIP)	= gz
+suffix-$(CONFIG_KERNEL_BZIP2)	= bz2
+suffix-$(CONFIG_KERNEL_LZMA)	= lzma
 
 $(obj)/piggy.o: $(obj)/vmlinux.scr $(obj)/vmlinux.bin.$(suffix-y) FORCE
 	$(call if_changed,ld)

arch/m32r/boot/compressed/misc.c

@@ -28,7 +28,7 @@ static unsigned long free_mem_ptr;
 static unsigned long free_mem_end_ptr;
 
 #ifdef CONFIG_KERNEL_BZIP2
-static void *memset(void *s, int c, size_t n)
+void *memset(void *s, int c, size_t n)
 {
 	char *ss = s;
 
@@ -39,6 +39,16 @@ static void *memset(void *s, int c, size_t n)
 #endif
 
 #ifdef CONFIG_KERNEL_GZIP
+void *memcpy(void *dest, const void *src, size_t n)
+{
+	char *d = dest;
+	const char *s = src;
+	while (n--)
+		*d++ = *s++;
+
+	return dest;
+}
+
 #define BOOT_HEAP_SIZE             0x10000
 #include "../../../../lib/decompress_inflate.c"
 #endif

arch/m32r/include/asm/ptrace.h

@@ -113,9 +113,6 @@ struct pt_regs {
 
 #define PTRACE_OLDSETOPTIONS	21
 
-/* options set using PTRACE_SETOPTIONS */
-#define PTRACE_O_TRACESYSGOOD	0x00000001
-
 #ifdef __KERNEL__
 
 #include <asm/m32r.h>		/* M32R_PSW_BSM, M32R_PSW_BPM */

arch/m32r/include/asm/smp.h

@@ -79,11 +79,6 @@ static __inline__ int cpu_number_map(int cpu)
 	return cpu;
 }
 
-static __inline__ unsigned int num_booting_cpus(void)
-{
-	return cpumask_weight(&cpu_callout_map);
-}
-
 extern void smp_send_timer(void);
 extern unsigned long send_IPI_mask_phys(const cpumask_t*, int, int);
 

arch/m32r/kernel/ptrace.c

@@ -591,17 +591,16 @@ void user_enable_single_step(struct task_struct *child)
 
 	if (access_process_vm(child, pc&~3, &insn, sizeof(insn), 0)
 	    != sizeof(insn))
-		return -EIO;
+		return;
 
 	compute_next_pc(insn, pc, &next_pc, child);
 	if (next_pc & 0x80000000)
-		return -EIO;
+		return;
 
 	if (embed_debug_trap(child, next_pc))
-		return -EIO;
+		return;
 
 	invalidate_cache();
-	return 0;
 }
 
 void user_disable_single_step(struct task_struct *child)

arch/m32r/kernel/signal.c

@@ -286,7 +286,7 @@ handle_signal(unsigned long sig, struct k_sigaction *ka, siginfo_t *info,
 			case -ERESTARTNOINTR:
 				regs->r0 = regs->orig_r0;
 				if (prev_insn(regs) < 0)
-					return -EFAULT;
+					return;
 		}
 	}
 

arch/mips/Kconfig

@@ -288,6 +288,7 @@ config MIPS_MALTA
 	select SYS_HAS_CPU_MIPS32_R1
 	select SYS_HAS_CPU_MIPS32_R2
 	select SYS_HAS_CPU_MIPS64_R1
+	select SYS_HAS_CPU_MIPS64_R2
 	select SYS_HAS_CPU_NEVADA
 	select SYS_HAS_CPU_RM7000
 	select SYS_HAS_EARLY_PRINTK
@@ -1423,6 +1424,7 @@ config CPU_SB1
 config CPU_CAVIUM_OCTEON
 	bool "Cavium Octeon processor"
 	depends on SYS_HAS_CPU_CAVIUM_OCTEON
+	select ARCH_SPARSEMEM_ENABLE
 	select CPU_HAS_PREFETCH
 	select CPU_SUPPORTS_64BIT_KERNEL
 	select SYS_SUPPORTS_SMP

arch/mips/bcm47xx/Kconfig

@@ -21,6 +21,7 @@ config BCM47XX_BCMA
 	select BCMA
 	select BCMA_HOST_SOC
 	select BCMA_DRIVER_MIPS
+	select BCMA_HOST_PCI if PCI
 	select BCMA_DRIVER_PCI_HOSTMODE if PCI
 	default y
 	help

arch/mips/bcm63xx/dev-pcmcia.c

@@ -79,11 +79,11 @@ static int __init config_pcmcia_cs(unsigned int cs,
 	return ret;
 }
 
-static const __initdata struct {
+static const struct {
 	unsigned int	cs;
 	unsigned int	base;
 	unsigned int	size;
-} pcmcia_cs[3] = {
+} pcmcia_cs[3] __initconst = {
 	{
 		.cs	= MPI_CS_PCMCIA_COMMON,
 		.base	= BCM_PCMCIA_COMMON_BASE_PA,

arch/mips/cavium-octeon/Kconfig

@@ -82,10 +82,6 @@ config CAVIUM_OCTEON_LOCK_L2_MEMCPY
 	help
 	  Lock the kernel's implementation of memcpy() into L2.
 
-config ARCH_SPARSEMEM_ENABLE
-	def_bool y
-	select SPARSEMEM_STATIC
-
 config IOMMU_HELPER
 	bool
 

arch/mips/cavium-octeon/smp.c

@@ -185,7 +185,6 @@ static void __cpuinit octeon_init_secondary(void)
 	octeon_init_cvmcount();
 
 	octeon_irq_setup_secondary();
-	raw_local_irq_enable();
 }
 
 /**
@@ -233,6 +232,7 @@ static void octeon_smp_finish(void)
 
 	/* to generate the first CPU timer interrupt */
 	write_c0_compare(read_c0_count() + mips_hpt_frequency / HZ);
+	local_irq_enable();
 }
 
 /**

arch/mips/include/asm/bitops.h

@@ -17,7 +17,6 @@
 #include <linux/irqflags.h>
 #include <linux/types.h>
 #include <asm/barrier.h>
-#include <asm/bug.h>
 #include <asm/byteorder.h>		/* sigh ... */
 #include <asm/cpu-features.h>
 #include <asm/sgidefs.h>

arch/mips/include/asm/cmpxchg.h

@@ -8,6 +8,7 @@
 #ifndef __ASM_CMPXCHG_H
 #define __ASM_CMPXCHG_H
 
+#include <linux/bug.h>
 #include <linux/irqflags.h>
 #include <asm/war.h>
 

arch/mips/include/asm/cpu.h

@@ -94,6 +94,7 @@
 #define PRID_IMP_24KE		0x9600
 #define PRID_IMP_74K		0x9700
 #define PRID_IMP_1004K		0x9900
+#define PRID_IMP_M14KC		0x9c00
 
 /*
  * These are the PRID's for when 23:16 == PRID_COMP_SIBYTE
@@ -260,12 +261,12 @@ enum cpu_type_enum {
 	 */
 	CPU_4KC, CPU_4KEC, CPU_4KSC, CPU_24K, CPU_34K, CPU_1004K, CPU_74K,
 	CPU_ALCHEMY, CPU_PR4450, CPU_BMIPS32, CPU_BMIPS3300, CPU_BMIPS4350,
-	CPU_BMIPS4380, CPU_BMIPS5000, CPU_JZRISC,
+	CPU_BMIPS4380, CPU_BMIPS5000, CPU_JZRISC, CPU_M14KC,
 
 	/*
 	 * MIPS64 class processors
 	 */
-	CPU_5KC, CPU_20KC, CPU_25KF, CPU_SB1, CPU_SB1A, CPU_LOONGSON2,
+	CPU_5KC, CPU_5KE, CPU_20KC, CPU_25KF, CPU_SB1, CPU_SB1A, CPU_LOONGSON2,
 	CPU_CAVIUM_OCTEON, CPU_CAVIUM_OCTEON_PLUS, CPU_CAVIUM_OCTEON2,
 	CPU_XLR, CPU_XLP,
 
@@ -288,7 +289,7 @@ enum cpu_type_enum {
 #define MIPS_CPU_ISA_M64R2	0x00000100
 
 #define MIPS_CPU_ISA_32BIT (MIPS_CPU_ISA_I | MIPS_CPU_ISA_II | \
-	MIPS_CPU_ISA_M32R1 | MIPS_CPU_ISA_M32R2 )
+	MIPS_CPU_ISA_M32R1 | MIPS_CPU_ISA_M32R2)
 #define MIPS_CPU_ISA_64BIT (MIPS_CPU_ISA_III | MIPS_CPU_ISA_IV | \
 	MIPS_CPU_ISA_V | MIPS_CPU_ISA_M64R1 | MIPS_CPU_ISA_M64R2)
 

arch/mips/include/asm/gic.h

@@ -206,7 +206,7 @@
 
 #define GIC_VPE_EIC_SHADOW_SET_BASE	0x0100
 #define GIC_VPE_EIC_SS(intr) \
-	(GIC_EIC_SHADOW_SET_BASE + (4 * intr))
+	(GIC_VPE_EIC_SHADOW_SET_BASE + (4 * intr))
 
 #define GIC_VPE_EIC_VEC_BASE		0x0800
 #define GIC_VPE_EIC_VEC(intr) \
@@ -330,6 +330,17 @@ struct gic_intr_map {
 #define GIC_FLAG_TRANSPARENT   0x02
 };
 
+/*
+ * This is only used in EIC mode. This helps to figure out which
+ * shared interrupts we need to process when we get a vector interrupt.
+ */
+#define GIC_MAX_SHARED_INTR  0x5
+struct gic_shared_intr_map {
+	unsigned int num_shared_intr;
+	unsigned int intr_list[GIC_MAX_SHARED_INTR];
+	unsigned int local_intr_mask;
+};
+
 extern void gic_init(unsigned long gic_base_addr,
 	unsigned long gic_addrspace_size, struct gic_intr_map *intrmap,
 	unsigned int intrmap_size, unsigned int irqbase);
@@ -338,5 +349,7 @@ extern unsigned int gic_get_int(void);
 extern void gic_send_ipi(unsigned int intr);
 extern unsigned int plat_ipi_call_int_xlate(unsigned int);
 extern unsigned int plat_ipi_resched_int_xlate(unsigned int);
+extern void gic_bind_eic_interrupt(int irq, int set);
+extern unsigned int gic_get_timer_pending(void);
 
 #endif /* _ASM_GICREGS_H */

arch/mips/include/asm/inst.h

@@ -251,7 +251,7 @@ struct f_format {	/* FPU register format */
 	unsigned int func : 6;
 };
 
-struct ma_format {	/* FPU multipy and add format (MIPS IV) */
+struct ma_format {	/* FPU multiply and add format (MIPS IV) */
 	unsigned int opcode : 6;
 	unsigned int fr : 5;
 	unsigned int ft : 5;
@@ -324,7 +324,7 @@ struct f_format {	/* FPU register format */
 	unsigned int opcode : 6;
 };
 
-struct ma_format {	/* FPU multipy and add format (MIPS IV) */
+struct ma_format {	/* FPU multiply and add format (MIPS IV) */
 	unsigned int fmt : 2;
 	unsigned int func : 4;
 	unsigned int fd : 5;

arch/mips/include/asm/io.h

@@ -17,6 +17,7 @@
 #include <linux/types.h>
 
 #include <asm/addrspace.h>
+#include <asm/bug.h>
 #include <asm/byteorder.h>
 #include <asm/cpu.h>
 #include <asm/cpu-features.h>

arch/mips/include/asm/irq.h

@@ -136,6 +136,7 @@ extern void free_irqno(unsigned int irq);
  * IE7.  Since R2 their number has to be read from the c0_intctl register.
  */
 #define CP0_LEGACY_COMPARE_IRQ 7
+#define CP0_LEGACY_PERFCNT_IRQ 7
 
 extern int cp0_compare_irq;
 extern int cp0_compare_irq_shift;

arch/mips/include/asm/mach-bcm63xx/bcm63xx_regs.h

@@ -99,7 +99,7 @@
 #define CKCTL_6368_USBH_CLK_EN		(1 << 15)
 #define CKCTL_6368_DISABLE_GLESS_EN	(1 << 16)
 #define CKCTL_6368_NAND_CLK_EN		(1 << 17)
-#define CKCTL_6368_IPSEC_CLK_EN		(1 << 17)
+#define CKCTL_6368_IPSEC_CLK_EN		(1 << 18)
 
 #define CKCTL_6368_ALL_SAFE_EN		(CKCTL_6368_SWPKT_USB_EN |	\
 					CKCTL_6368_SWPKT_SAR_EN |	\

arch/mips/include/asm/mips-boards/maltaint.h

@@ -86,6 +86,16 @@
 #define GIC_CPU_INT4		4 /* .			*/
 #define GIC_CPU_INT5		5 /* Core Interrupt 5   */
 
+/* MALTA GIC local interrupts */
+#define GIC_INT_TMR             (GIC_CPU_INT5)
+#define GIC_INT_PERFCTR         (GIC_CPU_INT5)
+
+/* GIC constants */
+/* Add 2 to convert non-eic hw int # to eic vector # */
+#define GIC_CPU_TO_VEC_OFFSET   (2)
+/* If we map an intr to pin X, GIC will actually generate vector X+1 */
+#define GIC_PIN_TO_VEC_OFFSET   (1)
+
 #define GIC_EXT_INTR(x)		x
 
 /* External Interrupts used for IPI */

arch/mips/include/asm/mipsmtregs.h

@@ -48,7 +48,7 @@
 #define CP0_VPECONF0		$1, 2
 #define CP0_VPECONF1		$1, 3
 #define CP0_YQMASK		$1, 4
-#define CP0_VPESCHEDULE	$1, 5
+#define CP0_VPESCHEDULE		$1, 5
 #define CP0_VPESCHEFBK		$1, 6
 #define CP0_TCSTATUS		$2, 1
 #define CP0_TCBIND		$2, 2

arch/mips/include/asm/switch_to.h

@@ -22,7 +22,7 @@ struct task_struct;
  * switch_to(n) should switch tasks to task nr n, first
  * checking that n isn't the current task, in which case it does nothing.
  */
-extern asmlinkage void *resume(void *last, void *next, void *next_ti);
+extern asmlinkage void *resume(void *last, void *next, void *next_ti, u32 __usedfpu);
 
 extern unsigned int ll_bit;
 extern struct task_struct *ll_task;
@@ -66,11 +66,13 @@ do {									\
 
 #define switch_to(prev, next, last)					\
 do {									\
+	u32 __usedfpu;							\
 	__mips_mt_fpaff_switch_to(prev);				\
 	if (cpu_has_dsp)						\
 		__save_dsp(prev);					\
 	__clear_software_ll_bit();					\
-	(last) = resume(prev, next, task_thread_info(next));		\
+	__usedfpu = test_and_clear_tsk_thread_flag(prev, TIF_USEDFPU);	\
+	(last) = resume(prev, next, task_thread_info(next), __usedfpu);	\
 } while (0)
 
 #define finish_arch_switch(prev)					\

arch/mips/include/asm/thread_info.h

@@ -60,6 +60,8 @@ struct thread_info {
 register struct thread_info *__current_thread_info __asm__("$28");
 #define current_thread_info()  __current_thread_info
 
+#endif /* !__ASSEMBLY__ */
+
 /* thread information allocation */
 #if defined(CONFIG_PAGE_SIZE_4KB) && defined(CONFIG_32BIT)
 #define THREAD_SIZE_ORDER (1)
@@ -85,8 +87,6 @@ register struct thread_info *__current_thread_info __asm__("$28");
 
 #define STACK_WARN	(THREAD_SIZE / 8)
 
-#endif /* !__ASSEMBLY__ */
-
 #define PREEMPT_ACTIVE		0x10000000
 
 /*

arch/mips/kernel/cpu-probe.c

@@ -4,7 +4,7 @@
  * Copyright (C) xxxx  the Anonymous
  * Copyright (C) 1994 - 2006 Ralf Baechle
  * Copyright (C) 2003, 2004  Maciej W. Rozycki
- * Copyright (C) 2001, 2004  MIPS Inc.
+ * Copyright (C) 2001, 2004, 2011, 2012  MIPS Technologies, Inc.
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License
@@ -199,6 +199,7 @@ void __init check_wait(void)
 		cpu_wait = rm7k_wait_irqoff;
 		break;
 
+	case CPU_M14KC:
 	case CPU_24K:
 	case CPU_34K:
 	case CPU_1004K:
@@ -810,6 +811,10 @@ static inline void cpu_probe_mips(struct cpuinfo_mips *c, unsigned int cpu)
 		c->cputype = CPU_5KC;
 		__cpu_name[cpu] = "MIPS 5Kc";
 		break;
+	case PRID_IMP_5KE:
+		c->cputype = CPU_5KE;
+		__cpu_name[cpu] = "MIPS 5KE";
+		break;
 	case PRID_IMP_20KC:
 		c->cputype = CPU_20KC;
 		__cpu_name[cpu] = "MIPS 20Kc";
@@ -831,6 +836,10 @@ static inline void cpu_probe_mips(struct cpuinfo_mips *c, unsigned int cpu)
 		c->cputype = CPU_74K;
 		__cpu_name[cpu] = "MIPS 74Kc";
 		break;
+	case PRID_IMP_M14KC:
+		c->cputype = CPU_M14KC;
+		__cpu_name[cpu] = "MIPS M14Kc";
+		break;
 	case PRID_IMP_1004K:
 		c->cputype = CPU_1004K;
 		__cpu_name[cpu] = "MIPS 1004Kc";

arch/mips/kernel/mips_ksyms.c

@@ -5,7 +5,7 @@
  * License.  See the file "COPYING" in the main directory of this archive
  * for more details.
  *
- * Copyright (C) 1996, 97, 98, 99, 2000, 01, 03, 04, 05 by Ralf Baechle
+ * Copyright (C) 1996, 97, 98, 99, 2000, 01, 03, 04, 05, 12 by Ralf Baechle
  * Copyright (C) 1999, 2000, 01 Silicon Graphics, Inc.
  */
 #include <linux/interrupt.h>
@@ -34,6 +34,12 @@ EXPORT_SYMBOL(memmove);
 
 EXPORT_SYMBOL(kernel_thread);
 
+/*
+ * Functions that operate on entire pages.  Mostly used by memory management.
+ */
+EXPORT_SYMBOL(clear_page);
+EXPORT_SYMBOL(copy_page);
+
 /*
  * Userspace access stuff.
  */

arch/mips/kernel/octeon_switch.S

@@ -31,7 +31,7 @@
 
 /*
  * task_struct *resume(task_struct *prev, task_struct *next,
- *                     struct thread_info *next_ti)
+ *                     struct thread_info *next_ti, int usedfpu)
  */
 	.align	7
 	LEAF(resume)

arch/mips/kernel/perf_event_mipsxx.c

@@ -162,11 +162,6 @@ static unsigned int counters_total_to_per_cpu(unsigned int counters)
 	return counters >> vpe_shift();
 }
 
-static unsigned int counters_per_cpu_to_total(unsigned int counters)
-{
-	return counters << vpe_shift();
-}
-
 #else /* !CONFIG_MIPS_MT_SMP */
 #define vpe_id()	0
 

arch/mips/kernel/r2300_switch.S

@@ -43,7 +43,7 @@
 
 /*
  * task_struct *resume(task_struct *prev, task_struct *next,
- *                     struct thread_info *next_ti) )
+ *                     struct thread_info *next_ti, int usedfpu)
  */
 LEAF(resume)
 	mfc0	t1, CP0_STATUS
@@ -51,18 +51,9 @@ LEAF(resume)
 	cpu_save_nonscratch a0
 	sw	ra, THREAD_REG31(a0)
 
-	/*
-	 * check if we need to save FPU registers
-	 */
-	lw	t3, TASK_THREAD_INFO(a0)
-	lw	t0, TI_FLAGS(t3)
-	li	t1, _TIF_USEDFPU
-	and	t2, t0, t1
-	beqz	t2, 1f
-	nor	t1, zero, t1
+	beqz	a3, 1f
 
-	and	t0, t0, t1
-	sw	t0, TI_FLAGS(t3)
+	PTR_L	t3, TASK_THREAD_INFO(a0)
 
 	/*
 	 * clear saved user stack CU1 bit

arch/mips/kernel/r4k_switch.S

@@ -41,7 +41,7 @@
 
 /*
  * task_struct *resume(task_struct *prev, task_struct *next,
- *                     struct thread_info *next_ti)
+ *                     struct thread_info *next_ti, int usedfpu)
  */
 	.align	5
 	LEAF(resume)
@@ -53,16 +53,10 @@
 	/*
 	 * check if we need to save FPU registers
 	 */
-	PTR_L	t3, TASK_THREAD_INFO(a0)
-	LONG_L	t0, TI_FLAGS(t3)
-	li	t1, _TIF_USEDFPU
-	and	t2, t0, t1
-	beqz	t2, 1f
-	nor	t1, zero, t1
 
-	and	t0, t0, t1
-	LONG_S	t0, TI_FLAGS(t3)
+	beqz    a3, 1f
 
+	PTR_L	t3, TASK_THREAD_INFO(a0)
 	/*
 	 * clear saved user stack CU1 bit
 	 */

arch/mips/kernel/smp-bmips.c

@@ -15,7 +15,6 @@
 #include <linux/smp.h>
 #include <linux/interrupt.h>
 #include <linux/spinlock.h>
-#include <linux/init.h>
 #include <linux/cpu.h>
 #include <linux/cpumask.h>
 #include <linux/reboot.h>
@@ -197,13 +196,6 @@ static void bmips_init_secondary(void)
 
 	write_c0_brcm_action(ACTION_CLR_IPI(smp_processor_id(), 0));
 #endif
-
-	/* make sure there won't be a timer interrupt for a little while */
-	write_c0_compare(read_c0_count() + mips_hpt_frequency / HZ);
-
-	irq_enable_hazard();
-	set_c0_status(IE_SW0 | IE_SW1 | IE_IRQ1 | IE_IRQ5 | ST0_IE);
-	irq_enable_hazard();
 }
 
 /*
@@ -212,6 +204,13 @@ static void bmips_init_secondary(void)
 static void bmips_smp_finish(void)
 {
 	pr_info("SMP: CPU%d is running\n", smp_processor_id());
+
+	/* make sure there won't be a timer interrupt for a little while */
+	write_c0_compare(read_c0_count() + mips_hpt_frequency / HZ);
+
+	irq_enable_hazard();
+	set_c0_status(IE_SW0 | IE_SW1 | IE_IRQ1 | IE_IRQ5 | ST0_IE);
+	irq_enable_hazard();
 }
 
 /*

arch/mips/kernel/smp.c

@@ -122,13 +122,21 @@ asmlinkage __cpuinit void start_secondary(void)
 
 	notify_cpu_starting(cpu);
 
-	mp_ops->smp_finish();
+	set_cpu_online(cpu, true);
+
 	set_cpu_sibling_map(cpu);
 
 	cpu_set(cpu, cpu_callin_map);
 
 	synchronise_count_slave();
 
+	/*
+	 * irq will be enabled in ->smp_finish(), enabling it too early
+	 * is dangerous.
+	 */
+	WARN_ON_ONCE(!irqs_disabled());
+	mp_ops->smp_finish();
+
 	cpu_idle();
 }
 
@@ -196,8 +204,6 @@ int __cpuinit __cpu_up(unsigned int cpu, struct task_struct *tidle)
 	while (!cpu_isset(cpu, cpu_callin_map))
 		udelay(100);
 
-	set_cpu_online(cpu, true);
-
 	return 0;
 }
 

arch/mips/kernel/smtc.c

@@ -322,7 +322,7 @@ int __init smtc_build_cpu_map(int start_cpu_slot)
 
 /*
  * Common setup before any secondaries are started
- * Make sure all CPU's are in a sensible state before we boot any of the
+ * Make sure all CPUs are in a sensible state before we boot any of the
  * secondaries.
  *
  * For MIPS MT "SMTC" operation, we set up all TCs, spread as evenly
@@ -340,12 +340,12 @@ static void smtc_tc_setup(int vpe, int tc, int cpu)
 	/*
 	 * TCContext gets an offset from the base of the IPIQ array
 	 * to be used in low-level code to detect the presence of
-	 * an active IPI queue
+	 * an active IPI queue.
 	 */
 	write_tc_c0_tccontext((sizeof(struct smtc_ipi_q) * cpu) << 16);
 	/* Bind tc to vpe */
 	write_tc_c0_tcbind(vpe);
-	/* In general, all TCs should have the same cpu_data indications */
+	/* In general, all TCs should have the same cpu_data indications. */
 	memcpy(&cpu_data[cpu], &cpu_data[0], sizeof(struct cpuinfo_mips));
 	/* For 34Kf, start with TC/CPU 0 as sole owner of single FPU context */
 	if (cpu_data[0].cputype == CPU_34K ||
@@ -358,8 +358,8 @@ static void smtc_tc_setup(int vpe, int tc, int cpu)
 }
 
 /*
- * Tweak to get Count registes in as close a sync as possible.
- * Value seems good for 34K-class cores.
+ * Tweak to get Count registes in as close a sync as possible.  The
+ * value seems good for 34K-class cores.
  */
 
 #define CP0_SKEW 8
@@ -615,7 +615,6 @@ void __cpuinit smtc_boot_secondary(int cpu, struct task_struct *idle)
 
 void smtc_init_secondary(void)
 {
-	local_irq_enable();
 }
 
 void smtc_smp_finish(void)
@@ -631,6 +630,8 @@ void smtc_smp_finish(void)
 	if (cpu > 0 && (cpu_data[cpu].vpe_id != cpu_data[cpu - 1].vpe_id))
 		write_c0_compare(read_c0_count() + mips_hpt_frequency/HZ);
 
+	local_irq_enable();
+
 	printk("TC %d going on-line as CPU %d\n",
 		cpu_data[smp_processor_id()].tc_id, smp_processor_id());
 }

arch/mips/kernel/sync-r4k.c

@@ -111,7 +111,6 @@ void __cpuinit synchronise_count_master(void)
 void __cpuinit synchronise_count_slave(void)
 {
 	int i;
-	unsigned long flags;
 	unsigned int initcount;
 	int ncpus;
 
@@ -123,8 +122,6 @@ void __cpuinit synchronise_count_slave(void)
 	return;
 #endif
 
-	local_irq_save(flags);
-
 	/*
 	 * Not every cpu is online at the time this gets called,
 	 * so we first wait for the master to say everyone is ready
@@ -154,7 +151,5 @@ void __cpuinit synchronise_count_slave(void)
 	}
 	/* Arrange for an interrupt in a short while */
 	write_c0_compare(read_c0_count() + COUNTON);
-
-	local_irq_restore(flags);
 }
 #undef NR_LOOPS

arch/mips/kernel/traps.c

@@ -132,6 +132,9 @@ static void show_backtrace(struct task_struct *task, const struct pt_regs *regs)
 	unsigned long ra = regs->regs[31];
 	unsigned long pc = regs->cp0_epc;
 
+	if (!task)
+		task = current;
+
 	if (raw_show_trace || !__kernel_text_address(pc)) {
 		show_raw_backtrace(sp);
 		return;
@@ -1249,6 +1252,7 @@ static inline void parity_protection_init(void)
 		break;
 
 	case CPU_5KC:
+	case CPU_5KE:
 		write_c0_ecc(0x80000000);
 		back_to_back_c0_hazard();
 		/* Set the PE bit (bit 31) in the c0_errctl register. */
@@ -1498,6 +1502,7 @@ extern void flush_tlb_handlers(void);
  * Timer interrupt
  */
 int cp0_compare_irq;
+EXPORT_SYMBOL_GPL(cp0_compare_irq);
 int cp0_compare_irq_shift;
 
 /*
@@ -1597,7 +1602,7 @@ void __cpuinit per_cpu_trap_init(bool is_boot_cpu)
 			cp0_perfcount_irq = -1;
 	} else {
 		cp0_compare_irq = CP0_LEGACY_COMPARE_IRQ;
-		cp0_compare_irq_shift = cp0_compare_irq;
+		cp0_compare_irq_shift = CP0_LEGACY_PERFCNT_IRQ;
 		cp0_perfcount_irq = -1;
 	}
 

arch/mips/kernel/vmlinux.lds.S

@@ -1,5 +1,6 @@
 #include <asm/asm-offsets.h>
 #include <asm/page.h>
+#include <asm/thread_info.h>
 #include <asm-generic/vmlinux.lds.h>
 
 #undef mips
@@ -72,7 +73,7 @@ SECTIONS
 	.data : {	/* Data */
 		. = . + DATAOFFSET;		/* for CONFIG_MAPPED_KERNEL */
 
-		INIT_TASK_DATA(PAGE_SIZE)
+		INIT_TASK_DATA(THREAD_SIZE)
 		NOSAVE_DATA
 		CACHELINE_ALIGNED_DATA(1 << CONFIG_MIPS_L1_CACHE_SHIFT)
 		READ_MOSTLY_DATA(1 << CONFIG_MIPS_L1_CACHE_SHIFT)

arch/mips/mm/Makefile

@@ -3,8 +3,8 @@
 #
 
 obj-y				+= cache.o dma-default.o extable.o fault.o \
-				   gup.o init.o mmap.o page.o tlbex.o \
-				   tlbex-fault.o uasm.o
+				   gup.o init.o mmap.o page.o page-funcs.o \
+				   tlbex.o tlbex-fault.o uasm.o
 
 obj-$(CONFIG_32BIT)		+= ioremap.o pgtable-32.o
 obj-$(CONFIG_64BIT)		+= pgtable-64.o

arch/mips/mm/c-r4k.c

@@ -977,7 +977,7 @@ static void __cpuinit probe_pcache(void)
 			c->icache.linesz = 2 << lsize;
 		else
 			c->icache.linesz = lsize;
-		c->icache.sets = 64 << ((config1 >> 22) & 7);
+		c->icache.sets = 32 << (((config1 >> 22) + 1) & 7);
 		c->icache.ways = 1 + ((config1 >> 16) & 7);
 
 		icache_size = c->icache.sets *
@@ -997,7 +997,7 @@ static void __cpuinit probe_pcache(void)
 			c->dcache.linesz = 2 << lsize;
 		else
 			c->dcache.linesz= lsize;
-		c->dcache.sets = 64 << ((config1 >> 13) & 7);
+		c->dcache.sets = 32 << (((config1 >> 13) + 1) & 7);
 		c->dcache.ways = 1 + ((config1 >> 7) & 7);
 
 		dcache_size = c->dcache.sets *
@@ -1051,6 +1051,7 @@ static void __cpuinit probe_pcache(void)
 	case CPU_R14000:
 		break;
 
+	case CPU_M14KC:
 	case CPU_24K:
 	case CPU_34K:
 	case CPU_74K:

arch/mips/mm/page-funcs.S

@@ -0,0 +1,50 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Micro-assembler generated clear_page/copy_page functions.
+ *
+ * Copyright (C) 2012  MIPS Technologies, Inc.
+ * Copyright (C) 2012  Ralf Baechle <ralf@linux-mips.org>
+ */
+#include <asm/asm.h>
+#include <asm/regdef.h>
+
+#ifdef CONFIG_SIBYTE_DMA_PAGEOPS
+#define cpu_clear_page_function_name	clear_page_cpu
+#define cpu_copy_page_function_name	copy_page_cpu
+#else
+#define cpu_clear_page_function_name	clear_page
+#define cpu_copy_page_function_name	copy_page
+#endif
+
+/*
+ * Maximum sizes:
+ *
+ * R4000 128 bytes S-cache:		0x058 bytes
+ * R4600 v1.7:				0x05c bytes
+ * R4600 v2.0:				0x060 bytes
+ * With prefetching, 16 word strides	0x120 bytes
+ */
+EXPORT(__clear_page_start)
+LEAF(cpu_clear_page_function_name)
+1:	j	1b		/* Dummy, will be replaced. */
+	.space 288
+END(cpu_clear_page_function_name)
+EXPORT(__clear_page_end)
+
+/*
+ * Maximum sizes:
+ *
+ * R4000 128 bytes S-cache:		0x11c bytes
+ * R4600 v1.7:				0x080 bytes
+ * R4600 v2.0:				0x07c bytes
+ * With prefetching, 16 word strides	0x540 bytes
+ */
+EXPORT(__copy_page_start)
+LEAF(cpu_copy_page_function_name)
+1:	j	1b		/* Dummy, will be replaced. */
+	.space 1344
+END(cpu_copy_page_function_name)
+EXPORT(__copy_page_end)

arch/mips/mm/page.c

@@ -6,6 +6,7 @@
  * Copyright (C) 2003, 04, 05 Ralf Baechle (ralf@linux-mips.org)
  * Copyright (C) 2007  Maciej W. Rozycki
  * Copyright (C) 2008  Thiemo Seufer
+ * Copyright (C) 2012  MIPS Technologies, Inc.
  */
 #include <linux/init.h>
 #include <linux/kernel.h>
@@ -71,45 +72,6 @@ static struct uasm_reloc __cpuinitdata relocs[5];
 #define cpu_is_r4600_v1_x()	((read_c0_prid() & 0xfffffff0) == 0x00002010)
 #define cpu_is_r4600_v2_x()	((read_c0_prid() & 0xfffffff0) == 0x00002020)
 
-/*
- * Maximum sizes:
- *
- * R4000 128 bytes S-cache:		0x058 bytes
- * R4600 v1.7:				0x05c bytes
- * R4600 v2.0:				0x060 bytes
- * With prefetching, 16 word strides	0x120 bytes
- */
-
-static u32 clear_page_array[0x120 / 4];
-
-#ifdef CONFIG_SIBYTE_DMA_PAGEOPS
-void clear_page_cpu(void *page) __attribute__((alias("clear_page_array")));
-#else
-void clear_page(void *page) __attribute__((alias("clear_page_array")));
-#endif
-
-EXPORT_SYMBOL(clear_page);
-
-/*
- * Maximum sizes:
- *
- * R4000 128 bytes S-cache:		0x11c bytes
- * R4600 v1.7:				0x080 bytes
- * R4600 v2.0:				0x07c bytes
- * With prefetching, 16 word strides	0x540 bytes
- */
-static u32 copy_page_array[0x540 / 4];
-
-#ifdef CONFIG_SIBYTE_DMA_PAGEOPS
-void
-copy_page_cpu(void *to, void *from) __attribute__((alias("copy_page_array")));
-#else
-void copy_page(void *to, void *from) __attribute__((alias("copy_page_array")));
-#endif
-
-EXPORT_SYMBOL(copy_page);
-
-
 static int pref_bias_clear_store __cpuinitdata;
 static int pref_bias_copy_load __cpuinitdata;
 static int pref_bias_copy_store __cpuinitdata;
@@ -282,10 +244,15 @@ static inline void __cpuinit build_clear_pref(u32 **buf, int off)
 		}
 }
 
+extern u32 __clear_page_start;
+extern u32 __clear_page_end;
+extern u32 __copy_page_start;
+extern u32 __copy_page_end;
+
 void __cpuinit build_clear_page(void)
 {
 	int off;
-	u32 *buf = (u32 *)&clear_page_array;
+	u32 *buf = &__clear_page_start;
 	struct uasm_label *l = labels;
 	struct uasm_reloc *r = relocs;
 	int i;
@@ -356,17 +323,17 @@ void __cpuinit build_clear_page(void)
 	uasm_i_jr(&buf, RA);
 	uasm_i_nop(&buf);
 
-	BUG_ON(buf > clear_page_array + ARRAY_SIZE(clear_page_array));
+	BUG_ON(buf > &__clear_page_end);
 
 	uasm_resolve_relocs(relocs, labels);
 
 	pr_debug("Synthesized clear page handler (%u instructions).\n",
-		 (u32)(buf - clear_page_array));
+		 (u32)(buf - &__clear_page_start));
 
 	pr_debug("\t.set push\n");
 	pr_debug("\t.set noreorder\n");
-	for (i = 0; i < (buf - clear_page_array); i++)
-		pr_debug("\t.word 0x%08x\n", clear_page_array[i]);
+	for (i = 0; i < (buf - &__clear_page_start); i++)
+		pr_debug("\t.word 0x%08x\n", (&__clear_page_start)[i]);
 	pr_debug("\t.set pop\n");
 }
 
@@ -427,7 +394,7 @@ static inline void build_copy_store_pref(u32 **buf, int off)
 void __cpuinit build_copy_page(void)
 {
 	int off;
-	u32 *buf = (u32 *)&copy_page_array;
+	u32 *buf = &__copy_page_start;
 	struct uasm_label *l = labels;
 	struct uasm_reloc *r = relocs;
 	int i;
@@ -595,21 +562,23 @@ void __cpuinit build_copy_page(void)
 	uasm_i_jr(&buf, RA);
 	uasm_i_nop(&buf);
 
-	BUG_ON(buf > copy_page_array + ARRAY_SIZE(copy_page_array));
+	BUG_ON(buf > &__copy_page_end);
 
 	uasm_resolve_relocs(relocs, labels);
 
 	pr_debug("Synthesized copy page handler (%u instructions).\n",
-		 (u32)(buf - copy_page_array));
+		 (u32)(buf - &__copy_page_start));
 
 	pr_debug("\t.set push\n");
 	pr_debug("\t.set noreorder\n");
-	for (i = 0; i < (buf - copy_page_array); i++)
-		pr_debug("\t.word 0x%08x\n", copy_page_array[i]);
+	for (i = 0; i < (buf - &__copy_page_start); i++)
+		pr_debug("\t.word 0x%08x\n", (&__copy_page_start)[i]);
 	pr_debug("\t.set pop\n");
 }
 
 #ifdef CONFIG_SIBYTE_DMA_PAGEOPS
+extern void clear_page_cpu(void *page);
+extern void copy_page_cpu(void *to, void *from);
 
 /*
  * Pad descriptors to cacheline, since each is exclusively owned by a

arch/mips/mm/tlbex.c

@@ -9,6 +9,7 @@
  * Copyright (C) 2005, 2007, 2008, 2009  Maciej W. Rozycki
  * Copyright (C) 2006  Ralf Baechle (ralf@linux-mips.org)
  * Copyright (C) 2008, 2009 Cavium Networks, Inc.
+ * Copyright (C) 2011  MIPS Technologies, Inc.
  *
  * ... and the days got worse and worse and now you see
  * I've gone completly out of my mind.
@@ -494,6 +495,7 @@ static void __cpuinit build_tlb_write_entry(u32 **p, struct uasm_label **l,
 	case CPU_R14000:
 	case CPU_4KC:
 	case CPU_4KEC:
+	case CPU_M14KC:
 	case CPU_SB1:
 	case CPU_SB1A:
 	case CPU_4KSC:

arch/mips/mti-malta/malta-pci.c

@@ -241,8 +241,9 @@ void __init mips_pcibios_init(void)
 		return;
 	}
 
-	if (controller->io_resource->start < 0x00001000UL)	/* FIXME */
-		controller->io_resource->start = 0x00001000UL;
+	/* Change start address to avoid conflicts with ACPI and SMB devices */
+	if (controller->io_resource->start < 0x00002000UL)
+		controller->io_resource->start = 0x00002000UL;
 
 	iomem_resource.end &= 0xfffffffffULL;			/* 64 GB */
 	ioport_resource.end = controller->io_resource->end;
@@ -253,7 +254,7 @@ void __init mips_pcibios_init(void)
 }
 
 /* Enable PCI 2.1 compatibility in PIIX4 */
-static void __init quirk_dlcsetup(struct pci_dev *dev)
+static void __devinit quirk_dlcsetup(struct pci_dev *dev)
 {
 	u8 odlc, ndlc;
 	(void) pci_read_config_byte(dev, 0x82, &odlc);

arch/mips/mti-malta/malta-setup.c

@@ -111,7 +111,7 @@ static void __init pci_clock_check(void)
 	unsigned int __iomem *jmpr_p =
 		(unsigned int *) ioremap(MALTA_JMPRS_REG, sizeof(unsigned int));
 	int jmpr = (__raw_readl(jmpr_p) >> 2) & 0x07;
-	static const int pciclocks[] __initdata = {
+	static const int pciclocks[] __initconst = {
 		33, 20, 25, 30, 12, 16, 37, 10
 	};
 	int pciclock = pciclocks[jmpr];

arch/mips/netlogic/xlp/setup.c

@@ -82,8 +82,10 @@ void __init prom_free_prom_memory(void)
 
 void xlp_mmu_init(void)
 {
+	/* enable extended TLB and Large Fixed TLB */
 	write_c0_config6(read_c0_config6() | 0x24);
-	current_cpu_data.tlbsize = ((read_c0_config6() >> 16) & 0xffff) + 1;
+
+	/* set page mask of Fixed TLB in config7 */
 	write_c0_config7(PM_DEFAULT_MASK >>
 		(13 + (ffz(PM_DEFAULT_MASK >> 13) / 2)));
 }
@@ -100,6 +102,10 @@ void __init prom_init(void)
 	nlm_common_ebase = read_c0_ebase() & (~((1 << 12) - 1));
 #ifdef CONFIG_SMP
 	nlm_wakeup_secondary_cpus(0xffffffff);
+
+	/* update TLB size after waking up threads */
+	current_cpu_data.tlbsize = ((read_c0_config6() >> 16) & 0xffff) + 1;
+
 	register_smp_ops(&nlm_smp_ops);
 #endif
 }

arch/mips/oprofile/common.c

@@ -78,6 +78,7 @@ int __init oprofile_arch_init(struct oprofile_operations *ops)
 
 	switch (current_cpu_type()) {
 	case CPU_5KC:
+	case CPU_M14KC:
 	case CPU_20KC:
 	case CPU_24K:
 	case CPU_25KF:

arch/mips/oprofile/op_model_mipsxx.c

@@ -322,6 +322,10 @@ static int __init mipsxx_init(void)
 
 	op_model_mipsxx_ops.num_counters = counters;
 	switch (current_cpu_type()) {
+	case CPU_M14KC:
+		op_model_mipsxx_ops.cpu_type = "mips/M14Kc";
+		break;
+
 	case CPU_20KC:
 		op_model_mipsxx_ops.cpu_type = "mips/20K";
 		break;

arch/mips/pci/fixup-fuloong2e.c

@@ -48,7 +48,7 @@ int pcibios_plat_dev_init(struct pci_dev *dev)
 	return 0;
 }
 
-static void __init loongson2e_nec_fixup(struct pci_dev *pdev)
+static void __devinit loongson2e_nec_fixup(struct pci_dev *pdev)
 {
 	unsigned int val;
 
@@ -60,7 +60,7 @@ static void __init loongson2e_nec_fixup(struct pci_dev *pdev)
 	pci_write_config_dword(pdev, 0xe4, 1 << 5);
 }
 
-static void __init loongson2e_686b_func0_fixup(struct pci_dev *pdev)
+static void __devinit loongson2e_686b_func0_fixup(struct pci_dev *pdev)
 {
 	unsigned char c;
 
@@ -135,7 +135,7 @@ static void __init loongson2e_686b_func0_fixup(struct pci_dev *pdev)
 	printk(KERN_INFO"via686b fix: ISA bridge done\n");
 }
 
-static void __init loongson2e_686b_func1_fixup(struct pci_dev *pdev)
+static void __devinit loongson2e_686b_func1_fixup(struct pci_dev *pdev)
 {
 	printk(KERN_INFO"via686b fix: IDE\n");
 
@@ -168,19 +168,19 @@ static void __init loongson2e_686b_func1_fixup(struct pci_dev *pdev)
 	printk(KERN_INFO"via686b fix: IDE done\n");
 }
 
-static void __init loongson2e_686b_func2_fixup(struct pci_dev *pdev)
+static void __devinit loongson2e_686b_func2_fixup(struct pci_dev *pdev)
 {
 	/* irq routing */
 	pci_write_config_byte(pdev, PCI_INTERRUPT_LINE, 10);
 }
 
-static void __init loongson2e_686b_func3_fixup(struct pci_dev *pdev)
+static void __devinit loongson2e_686b_func3_fixup(struct pci_dev *pdev)
 {
 	/* irq routing */
 	pci_write_config_byte(pdev, PCI_INTERRUPT_LINE, 11);
 }
 
-static void __init loongson2e_686b_func5_fixup(struct pci_dev *pdev)
+static void __devinit loongson2e_686b_func5_fixup(struct pci_dev *pdev)
 {
 	unsigned int val;
 	unsigned char c;

arch/mips/pci/fixup-lemote2f.c

@@ -96,21 +96,21 @@ int pcibios_plat_dev_init(struct pci_dev *dev)
 }
 
 /* CS5536 SPEC. fixup */
-static void __init loongson_cs5536_isa_fixup(struct pci_dev *pdev)
+static void __devinit loongson_cs5536_isa_fixup(struct pci_dev *pdev)
 {
 	/* the uart1 and uart2 interrupt in PIC is enabled as default */
 	pci_write_config_dword(pdev, PCI_UART1_INT_REG, 1);
 	pci_write_config_dword(pdev, PCI_UART2_INT_REG, 1);
 }
 
-static void __init loongson_cs5536_ide_fixup(struct pci_dev *pdev)
+static void __devinit loongson_cs5536_ide_fixup(struct pci_dev *pdev)
 {
 	/* setting the mutex pin as IDE function */
 	pci_write_config_dword(pdev, PCI_IDE_CFG_REG,
 			       CS5536_IDE_FLASH_SIGNATURE);
 }
 
-static void __init loongson_cs5536_acc_fixup(struct pci_dev *pdev)
+static void __devinit loongson_cs5536_acc_fixup(struct pci_dev *pdev)
 {
 	/* enable the AUDIO interrupt in PIC  */
 	pci_write_config_dword(pdev, PCI_ACC_INT_REG, 1);
@@ -118,14 +118,14 @@ static void __init loongson_cs5536_acc_fixup(struct pci_dev *pdev)
 	pci_write_config_byte(pdev, PCI_LATENCY_TIMER, 0xc0);
 }
 
-static void __init loongson_cs5536_ohci_fixup(struct pci_dev *pdev)
+static void __devinit loongson_cs5536_ohci_fixup(struct pci_dev *pdev)
 {
 	/* enable the OHCI interrupt in PIC */
 	/* THE OHCI, EHCI, UDC, OTG are shared with interrupt in PIC */
 	pci_write_config_dword(pdev, PCI_OHCI_INT_REG, 1);
 }
 
-static void __init loongson_cs5536_ehci_fixup(struct pci_dev *pdev)
+static void __devinit loongson_cs5536_ehci_fixup(struct pci_dev *pdev)
 {
 	u32 hi, lo;
 
@@ -137,7 +137,7 @@ static void __init loongson_cs5536_ehci_fixup(struct pci_dev *pdev)
 	pci_write_config_dword(pdev, PCI_EHCI_FLADJ_REG, 0x2000);
 }
 
-static void __init loongson_nec_fixup(struct pci_dev *pdev)
+static void __devinit loongson_nec_fixup(struct pci_dev *pdev)
 {
 	unsigned int val;
 

arch/mips/pci/fixup-malta.c

@@ -49,10 +49,10 @@ int pcibios_plat_dev_init(struct pci_dev *dev)
 	return 0;
 }
 
-static void __init malta_piix_func0_fixup(struct pci_dev *pdev)
+static void __devinit malta_piix_func0_fixup(struct pci_dev *pdev)
 {
 	unsigned char reg_val;
-	static int piixirqmap[16] __initdata = {  /* PIIX PIRQC[A:D] irq mappings */
+	static int piixirqmap[16] __devinitdata = {  /* PIIX PIRQC[A:D] irq mappings */
 		0,  0, 	0,  3,
 		4,  5,  6,  7,
 		0,  9, 10, 11,
@@ -83,7 +83,7 @@ static void __init malta_piix_func0_fixup(struct pci_dev *pdev)
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82371AB_0,
 	 malta_piix_func0_fixup);
 
-static void __init malta_piix_func1_fixup(struct pci_dev *pdev)
+static void __devinit malta_piix_func1_fixup(struct pci_dev *pdev)
 {
 	unsigned char reg_val;
 

arch/mips/pci/fixup-mpc30x.c

@@ -22,13 +22,13 @@
 
 #include <asm/vr41xx/mpc30x.h>
 
-static const int internal_func_irqs[] __initdata = {
+static const int internal_func_irqs[] __initconst = {
 	VRC4173_CASCADE_IRQ,
 	VRC4173_AC97_IRQ,
 	VRC4173_USB_IRQ,
 };
 
-static const int irq_tab_mpc30x[] __initdata = {
+static const int irq_tab_mpc30x[] __initconst = {
  [12] = VRC4173_PCMCIA1_IRQ,
  [13] = VRC4173_PCMCIA2_IRQ,
  [29] = MQ200_IRQ,

arch/mips/pci/fixup-sb1250.c

@@ -15,7 +15,7 @@
  * Set the BCM1250, etc. PCI host bridge's TRDY timeout
  * to the finite max.
  */
-static void __init quirk_sb1250_pci(struct pci_dev *dev)
+static void __devinit quirk_sb1250_pci(struct pci_dev *dev)
 {
 	pci_write_config_byte(dev, 0x40, 0xff);
 }
@@ -25,7 +25,7 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SIBYTE, PCI_DEVICE_ID_BCM1250_PCI,
 /*
  * The BCM1250, etc. PCI/HT bridge reports as a host bridge.
  */
-static void __init quirk_sb1250_ht(struct pci_dev *dev)
+static void __devinit quirk_sb1250_ht(struct pci_dev *dev)
 {
 	dev->class = PCI_CLASS_BRIDGE_PCI << 8;
 }
@@ -35,7 +35,7 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SIBYTE, PCI_DEVICE_ID_BCM1250_HT,
 /*
  * Set the SP1011 HT/PCI bridge's TRDY timeout to the finite max.
  */
-static void __init quirk_sp1011(struct pci_dev *dev)
+static void __devinit quirk_sp1011(struct pci_dev *dev)
 {
 	pci_write_config_byte(dev, 0x64, 0xff);
 }

arch/mips/pci/ops-tx4927.c

@@ -495,7 +495,7 @@ irqreturn_t tx4927_pcierr_interrupt(int irq, void *dev_id)
 }
 
 #ifdef CONFIG_TOSHIBA_FPCIB0
-static void __init tx4927_quirk_slc90e66_bridge(struct pci_dev *dev)
+static void __devinit tx4927_quirk_slc90e66_bridge(struct pci_dev *dev)
 {
 	struct tx4927_pcic_reg __iomem *pcicptr = pci_bus_to_pcicptr(dev->bus);
 

arch/mips/pci/pci-ip27.c

@@ -212,7 +212,7 @@ static inline void pci_enable_swapping(struct pci_dev *dev)
 	bridge->b_widget.w_tflush;	/* Flush */
 }
 
-static void __init pci_fixup_ioc3(struct pci_dev *d)
+static void __devinit pci_fixup_ioc3(struct pci_dev *d)
 {
 	pci_disable_swapping(d);
 }

arch/mips/pci/pci-xlr.c

@@ -41,6 +41,7 @@
 #include <linux/irq.h>
 #include <linux/irqdesc.h>
 #include <linux/console.h>
+#include <linux/pci_regs.h>
 
 #include <asm/io.h>
 
@@ -156,35 +157,55 @@ struct pci_controller nlm_pci_controller = {
 	.io_offset      = 0x00000000UL,
 };
 
+/*
+ * The top level PCIe links on the XLS PCIe controller appear as
+ * bridges. Given a device, this function finds which link it is
+ * on.
+ */
+static struct pci_dev *xls_get_pcie_link(const struct pci_dev *dev)
+{
+	struct pci_bus *bus, *p;
+
+	/* Find the bridge on bus 0 */
+	bus = dev->bus;
+	for (p = bus->parent; p && p->number != 0; p = p->parent)
+		bus = p;
+
+	return p ? bus->self : NULL;
+}
+
 static int get_irq_vector(const struct pci_dev *dev)
 {
+	struct pci_dev *lnk;
+
 	if (!nlm_chip_is_xls())
-		return	PIC_PCIX_IRQ;	/* for XLR just one IRQ*/
+		return	PIC_PCIX_IRQ;	/* for XLR just one IRQ */
 
 	/*
 	 * For XLS PCIe, there is an IRQ per Link, find out which
 	 * link the device is on to assign interrupts
-	*/
-	if (dev->bus->self == NULL)
+	 */
+	lnk = xls_get_pcie_link(dev);
+	if (lnk == NULL)
 		return 0;
 
-	switch	(dev->bus->self->devfn) {
-	case 0x0:
+	switch	(PCI_SLOT(lnk->devfn)) {
+	case 0:
 		return PIC_PCIE_LINK0_IRQ;
-	case 0x8:
+	case 1:
 		return PIC_PCIE_LINK1_IRQ;
-	case 0x10:
+	case 2:
 		if (nlm_chip_is_xls_b())
 			return PIC_PCIE_XLSB0_LINK2_IRQ;
 		else
 			return PIC_PCIE_LINK2_IRQ;
-	case 0x18:
+	case 3:
 		if (nlm_chip_is_xls_b())
 			return PIC_PCIE_XLSB0_LINK3_IRQ;
 		else
 			return PIC_PCIE_LINK3_IRQ;
 	}
-	WARN(1, "Unexpected devfn %d\n", dev->bus->self->devfn);
+	WARN(1, "Unexpected devfn %d\n", lnk->devfn);
 	return 0;
 }
 
@@ -202,7 +223,27 @@ void arch_teardown_msi_irq(unsigned int irq)
 int arch_setup_msi_irq(struct pci_dev *dev, struct msi_desc *desc)
 {
 	struct msi_msg msg;
+	struct pci_dev *lnk;
 	int irq, ret;
+	u16 val;
+
+	/* MSI not supported on XLR */
+	if (!nlm_chip_is_xls())
+		return 1;
+
+	/*
+	 * Enable MSI on the XLS PCIe controller bridge which was disabled
+	 * at enumeration, the bridge MSI capability is at 0x50
+	 */
+	lnk = xls_get_pcie_link(dev);
+	if (lnk == NULL)
+		return 1;
+
+	pci_read_config_word(lnk, 0x50 + PCI_MSI_FLAGS, &val);
+	if ((val & PCI_MSI_FLAGS_ENABLE) == 0) {
+		val |= PCI_MSI_FLAGS_ENABLE;
+		pci_write_config_word(lnk, 0x50 + PCI_MSI_FLAGS, val);
+	}
 
 	irq = get_irq_vector(dev);
 	if (irq <= 0)
@@ -327,7 +368,7 @@ static int __init pcibios_init(void)
 		}
 	} else {
 		/* XLR PCI controller ACK */
-		irq_set_handler_data(PIC_PCIE_XLSB0_LINK3_IRQ, xlr_pci_ack);
+		irq_set_handler_data(PIC_PCIX_IRQ, xlr_pci_ack);
 	}
 
 	return 0;

arch/mips/pmc-sierra/yosemite/smp.c

@@ -115,11 +115,11 @@ static void yos_send_ipi_mask(const struct cpumask *mask, unsigned int action)
  */
 static void __cpuinit yos_init_secondary(void)
 {
-	set_c0_status(ST0_CO | ST0_IE | ST0_IM);
 }
 
 static void __cpuinit yos_smp_finish(void)
 {
+	set_c0_status(ST0_CO | ST0_IM | ST0_IE);
 }
 
 /* Hook for after all CPUs are online */

arch/mips/powertv/asic/asic-calliope.c

@@ -28,7 +28,7 @@
 
 #define CALLIOPE_ADDR(x)	(CALLIOPE_IO_BASE + (x))
 
-const struct register_map calliope_register_map __initdata = {
+const struct register_map calliope_register_map __initconst = {
 	.eic_slow0_strt_add = {.phys = CALLIOPE_ADDR(0x800000)},
 	.eic_cfg_bits = {.phys = CALLIOPE_ADDR(0x800038)},
 	.eic_ready_status = {.phys = CALLIOPE_ADDR(0x80004c)},

arch/mips/powertv/asic/asic-cronus.c

@@ -28,7 +28,7 @@
 
 #define CRONUS_ADDR(x)	(CRONUS_IO_BASE + (x))
 
-const struct register_map cronus_register_map __initdata = {
+const struct register_map cronus_register_map __initconst = {
 	.eic_slow0_strt_add = {.phys = CRONUS_ADDR(0x000000)},
 	.eic_cfg_bits = {.phys = CRONUS_ADDR(0x000038)},
 	.eic_ready_status = {.phys = CRONUS_ADDR(0x00004C)},

arch/mips/powertv/asic/asic-gaia.c

@@ -23,7 +23,7 @@
 #include <linux/init.h>
 #include <asm/mach-powertv/asic.h>
 
-const struct register_map gaia_register_map __initdata = {
+const struct register_map gaia_register_map __initconst = {
 	.eic_slow0_strt_add = {.phys = GAIA_IO_BASE + 0x000000},
 	.eic_cfg_bits = {.phys = GAIA_IO_BASE + 0x000038},
 	.eic_ready_status = {.phys = GAIA_IO_BASE + 0x00004C},

arch/mips/powertv/asic/asic-zeus.c

@@ -28,7 +28,7 @@
 
 #define ZEUS_ADDR(x)	(ZEUS_IO_BASE + (x))
 
-const struct register_map zeus_register_map __initdata = {
+const struct register_map zeus_register_map __initconst = {
 	.eic_slow0_strt_add = {.phys = ZEUS_ADDR(0x000000)},
 	.eic_cfg_bits = {.phys = ZEUS_ADDR(0x000038)},
 	.eic_ready_status = {.phys = ZEUS_ADDR(0x00004c)},

arch/mips/txx9/generic/pci.c

@@ -269,7 +269,7 @@ txx9_i8259_irq_setup(int irq)
 	return err;
 }
 
-static void __init quirk_slc90e66_bridge(struct pci_dev *dev)
+static void __devinit quirk_slc90e66_bridge(struct pci_dev *dev)
 {
 	int irq;	/* PCI/ISA Bridge interrupt */
 	u8 reg_64;

arch/mn10300/kernel/signal.c

@@ -459,10 +459,11 @@ static int handle_signal(int sig,
 	else
 		ret = setup_frame(sig, ka, oldset, regs);
 	if (ret)
-		return;
+		return ret;
 
 	signal_delivered(sig, info, ka, regs,
-				 test_thread_flag(TIF_SINGLESTEP));
+			 test_thread_flag(TIF_SINGLESTEP));
+	return 0;
 }
 
 /*

arch/mn10300/kernel/smp.c

@@ -876,9 +876,7 @@ static void __init smp_online(void)
 
 	notify_cpu_starting(cpu);
 
-	ipi_call_lock();
 	set_cpu_online(cpu, true);
-	ipi_call_unlock();
 
 	local_irq_enable();
 }

arch/parisc/kernel/smp.c

@@ -300,9 +300,7 @@ smp_cpu_init(int cpunum)
 
 	notify_cpu_starting(cpunum);
 
-	ipi_call_lock();
 	set_cpu_online(cpunum, true);
-	ipi_call_unlock();
 
 	/* Initialise the idle task for this CPU */
 	atomic_inc(&init_mm.mm_count);

arch/powerpc/kernel/smp.c

@@ -571,7 +571,6 @@ void __devinit start_secondary(void *unused)
 	if (system_state == SYSTEM_RUNNING)
 		vdso_data->processorCount++;
 #endif
-	ipi_call_lock();
 	notify_cpu_starting(cpu);
 	set_cpu_online(cpu, true);
 	/* Update sibling maps */
@@ -601,7 +600,6 @@ void __devinit start_secondary(void *unused)
 		of_node_put(np);
 	}
 	of_node_put(l2_cache);
-	ipi_call_unlock();
 
 	local_irq_enable();
 

arch/s390/kernel/smp.c

@@ -717,9 +717,7 @@ static void __cpuinit smp_start_secondary(void *cpuvoid)
 	init_cpu_vtimer();
 	pfault_init();
 	notify_cpu_starting(smp_processor_id());
-	ipi_call_lock();
 	set_cpu_online(smp_processor_id(), true);
-	ipi_call_unlock();
 	local_irq_enable();
 	/* cpu_idle will call schedule for us */
 	cpu_idle();

arch/sparc/kernel/smp_64.c

@@ -103,8 +103,6 @@ void __cpuinit smp_callin(void)
 	if (cheetah_pcache_forced_on)
 		cheetah_enable_pcache();
 
-	local_irq_enable();
-
 	callin_flag = 1;
 	__asm__ __volatile__("membar #Sync\n\t"
 			     "flush  %%g6" : : : "memory");
@@ -124,9 +122,8 @@ void __cpuinit smp_callin(void)
 	while (!cpumask_test_cpu(cpuid, &smp_commenced_mask))
 		rmb();
 
-	ipi_call_lock_irq();
 	set_cpu_online(cpuid, true);
-	ipi_call_unlock_irq();
+	local_irq_enable();
 
 	/* idle thread is expected to have preempt disabled */
 	preempt_disable();
@@ -1308,9 +1305,7 @@ int __cpu_disable(void)
 	mdelay(1);
 	local_irq_disable();
 
-	ipi_call_lock();
 	set_cpu_online(cpu, false);
-	ipi_call_unlock();
 
 	cpu_map_rebuild();
 

arch/tile/kernel/smpboot.c

@@ -198,17 +198,7 @@ void __cpuinit online_secondary(void)
 
 	notify_cpu_starting(smp_processor_id());
 
-	/*
-	 * We need to hold call_lock, so there is no inconsistency
-	 * between the time smp_call_function() determines number of
-	 * IPI recipients, and the time when the determination is made
-	 * for which cpus receive the IPI. Holding this
-	 * lock helps us to not include this cpu in a currently in progress
-	 * smp_call_function().
-	 */
-	ipi_call_lock();
 	set_cpu_online(smp_processor_id(), 1);
-	ipi_call_unlock();
 	__get_cpu_var(cpu_state) = CPU_ONLINE;
 
 	/* Set up tile-specific state for this cpu. */

arch/x86/Makefile

@@ -49,6 +49,9 @@ else
         KBUILD_AFLAGS += -m64
         KBUILD_CFLAGS += -m64
 
+	# Use -mpreferred-stack-boundary=3 if supported.
+	KBUILD_CFLAGS += $(call cc-option,-mno-sse -mpreferred-stack-boundary=3)
+
         # FIXME - should be integrated in Makefile.cpu (Makefile_32.cpu)
         cflags-$(CONFIG_MK8) += $(call cc-option,-march=k8)
         cflags-$(CONFIG_MPSC) += $(call cc-option,-march=nocona)

arch/x86/include/asm/alternative.h

@@ -75,23 +75,54 @@ static inline int alternatives_text_reserved(void *start, void *end)
 }
 #endif	/* CONFIG_SMP */
 
+#define OLDINSTR(oldinstr)	"661:\n\t" oldinstr "\n662:\n"
+
+#define b_replacement(number)	"663"#number
+#define e_replacement(number)	"664"#number
+
+#define alt_slen "662b-661b"
+#define alt_rlen(number) e_replacement(number)"f-"b_replacement(number)"f"
+
+#define ALTINSTR_ENTRY(feature, number)					      \
+	" .long 661b - .\n"				/* label           */ \
+	" .long " b_replacement(number)"f - .\n"	/* new instruction */ \
+	" .word " __stringify(feature) "\n"		/* feature bit     */ \
+	" .byte " alt_slen "\n"				/* source len      */ \
+	" .byte " alt_rlen(number) "\n"			/* replacement len */
+
+#define DISCARD_ENTRY(number)				/* rlen <= slen */    \
+	" .byte 0xff + (" alt_rlen(number) ") - (" alt_slen ")\n"
+
+#define ALTINSTR_REPLACEMENT(newinstr, feature, number)	/* replacement */     \
+	b_replacement(number)":\n\t" newinstr "\n" e_replacement(number) ":\n\t"
+
 /* alternative assembly primitive: */
 #define ALTERNATIVE(oldinstr, newinstr, feature)			\
-									\
-      "661:\n\t" oldinstr "\n662:\n"					\
-      ".section .altinstructions,\"a\"\n"				\
-      "	 .long 661b - .\n"			/* label           */	\
-      "	 .long 663f - .\n"			/* new instruction */	\
-      "	 .word " __stringify(feature) "\n"	/* feature bit     */	\
-      "	 .byte 662b-661b\n"			/* sourcelen       */	\
-      "	 .byte 664f-663f\n"			/* replacementlen  */	\
-      ".previous\n"							\
-      ".section .discard,\"aw\",@progbits\n"				\
-      "	 .byte 0xff + (664f-663f) - (662b-661b)\n" /* rlen <= slen */	\
-      ".previous\n"							\
-      ".section .altinstr_replacement, \"ax\"\n"			\
-      "663:\n\t" newinstr "\n664:\n"		/* replacement     */	\
-      ".previous"
+	OLDINSTR(oldinstr)						\
+	".section .altinstructions,\"a\"\n"				\
+	ALTINSTR_ENTRY(feature, 1)					\
+	".previous\n"							\
+	".section .discard,\"aw\",@progbits\n"				\
+	DISCARD_ENTRY(1)						\
+	".previous\n"							\
+	".section .altinstr_replacement, \"ax\"\n"			\
+	ALTINSTR_REPLACEMENT(newinstr, feature, 1)			\
+	".previous"
+
+#define ALTERNATIVE_2(oldinstr, newinstr1, feature1, newinstr2, feature2)\
+	OLDINSTR(oldinstr)						\
+	".section .altinstructions,\"a\"\n"				\
+	ALTINSTR_ENTRY(feature1, 1)					\
+	ALTINSTR_ENTRY(feature2, 2)					\
+	".previous\n"							\
+	".section .discard,\"aw\",@progbits\n"				\
+	DISCARD_ENTRY(1)						\
+	DISCARD_ENTRY(2)						\
+	".previous\n"							\
+	".section .altinstr_replacement, \"ax\"\n"			\
+	ALTINSTR_REPLACEMENT(newinstr1, feature1, 1)			\
+	ALTINSTR_REPLACEMENT(newinstr2, feature2, 2)			\
+	".previous"
 
 /*
  * This must be included *after* the definition of ALTERNATIVE due to
@@ -139,6 +170,19 @@ static inline int alternatives_text_reserved(void *start, void *end)
 	asm volatile (ALTERNATIVE("call %P[old]", "call %P[new]", feature) \
 		: output : [old] "i" (oldfunc), [new] "i" (newfunc), ## input)
 
+/*
+ * Like alternative_call, but there are two features and respective functions.
+ * If CPU has feature2, function2 is used.
+ * Otherwise, if CPU has feature1, function1 is used.
+ * Otherwise, old function is used.
+ */
+#define alternative_call_2(oldfunc, newfunc1, feature1, newfunc2, feature2,   \
+			   output, input...)				      \
+	asm volatile (ALTERNATIVE_2("call %P[old]", "call %P[new1]", feature1,\
+		"call %P[new2]", feature2)				      \
+		: output : [old] "i" (oldfunc), [new1] "i" (newfunc1),	      \
+		[new2] "i" (newfunc2), ## input)
+
 /*
  * use this macro(s) if you need more than one output parameter
  * in alternative_io

arch/x86/include/asm/apic.h

@@ -306,7 +306,8 @@ struct apic {
 	unsigned long (*check_apicid_used)(physid_mask_t *map, int apicid);
 	unsigned long (*check_apicid_present)(int apicid);
 
-	void (*vector_allocation_domain)(int cpu, struct cpumask *retmask);
+	void (*vector_allocation_domain)(int cpu, struct cpumask *retmask,
+					 const struct cpumask *mask);
 	void (*init_apic_ldr)(void);
 
 	void (*ioapic_phys_id_map)(physid_mask_t *phys_map, physid_mask_t *retmap);
@@ -331,9 +332,9 @@ struct apic {
 	unsigned long (*set_apic_id)(unsigned int id);
 	unsigned long apic_id_mask;
 
-	unsigned int (*cpu_mask_to_apicid)(const struct cpumask *cpumask);
-	unsigned int (*cpu_mask_to_apicid_and)(const struct cpumask *cpumask,
-					       const struct cpumask *andmask);
+	int (*cpu_mask_to_apicid_and)(const struct cpumask *cpumask,
+				      const struct cpumask *andmask,
+				      unsigned int *apicid);
 
 	/* ipi */
 	void (*send_IPI_mask)(const struct cpumask *mask, int vector);
@@ -537,6 +538,11 @@ static inline const struct cpumask *default_target_cpus(void)
 #endif
 }
 
+static inline const struct cpumask *online_target_cpus(void)
+{
+	return cpu_online_mask;
+}
+
 DECLARE_EARLY_PER_CPU(u16, x86_bios_cpu_apicid);
 
 
@@ -586,21 +592,50 @@ static inline int default_phys_pkg_id(int cpuid_apic, int index_msb)
 
 #endif
 
-static inline unsigned int
-default_cpu_mask_to_apicid(const struct cpumask *cpumask)
+static inline int
+flat_cpu_mask_to_apicid_and(const struct cpumask *cpumask,
+			    const struct cpumask *andmask,
+			    unsigned int *apicid)
 {
-	return cpumask_bits(cpumask)[0] & APIC_ALL_CPUS;
+	unsigned long cpu_mask = cpumask_bits(cpumask)[0] &
+				 cpumask_bits(andmask)[0] &
+				 cpumask_bits(cpu_online_mask)[0] &
+				 APIC_ALL_CPUS;
+
+	if (likely(cpu_mask)) {
+		*apicid = (unsigned int)cpu_mask;
+		return 0;
+	} else {
+		return -EINVAL;
+	}
 }
 
-static inline unsigned int
+extern int
 default_cpu_mask_to_apicid_and(const struct cpumask *cpumask,
-			       const struct cpumask *andmask)
+			       const struct cpumask *andmask,
+			       unsigned int *apicid);
+
+static inline void
+flat_vector_allocation_domain(int cpu, struct cpumask *retmask,
+			      const struct cpumask *mask)
 {
-	unsigned long mask1 = cpumask_bits(cpumask)[0];
-	unsigned long mask2 = cpumask_bits(andmask)[0];
-	unsigned long mask3 = cpumask_bits(cpu_online_mask)[0];
+	/* Careful. Some cpus do not strictly honor the set of cpus
+	 * specified in the interrupt destination when using lowest
+	 * priority interrupt delivery mode.
+	 *
+	 * In particular there was a hyperthreading cpu observed to
+	 * deliver interrupts to the wrong hyperthread when only one
+	 * hyperthread was specified in the interrupt desitination.
+	 */
+	cpumask_clear(retmask);
+	cpumask_bits(retmask)[0] = APIC_ALL_CPUS;
+}
 
-	return (unsigned int)(mask1 & mask2 & mask3);
+static inline void
+default_vector_allocation_domain(int cpu, struct cpumask *retmask,
+				 const struct cpumask *mask)
+{
+	cpumask_copy(retmask, cpumask_of(cpu));
 }
 
 static inline unsigned long default_check_apicid_used(physid_mask_t *map, int apicid)

arch/x86/include/asm/emergency-restart.h

@@ -4,9 +4,7 @@
 enum reboot_type {
 	BOOT_TRIPLE = 't',
 	BOOT_KBD = 'k',
-#ifdef CONFIG_X86_32
 	BOOT_BIOS = 'b',
-#endif
 	BOOT_ACPI = 'a',
 	BOOT_EFI = 'e',
 	BOOT_CF9 = 'p',

arch/x86/include/asm/floppy.h

@@ -99,7 +99,7 @@ static irqreturn_t floppy_hardint(int irq, void *dev_id)
 		virtual_dma_residue += virtual_dma_count;
 		virtual_dma_count = 0;
 #ifdef TRACE_FLPY_INT
-		printk("count=%x, residue=%x calls=%d bytes=%d dma_wait=%d\n",
+		printk(KERN_DEBUG "count=%x, residue=%x calls=%d bytes=%d dma_wait=%d\n",
 		       virtual_dma_count, virtual_dma_residue, calls, bytes,
 		       dma_wait);
 		calls = 0;

arch/x86/include/asm/kvm_host.h

@@ -313,8 +313,8 @@ struct kvm_pmu {
 	u64 counter_bitmask[2];
 	u64 global_ctrl_mask;
 	u8 version;
-	struct kvm_pmc gp_counters[X86_PMC_MAX_GENERIC];
-	struct kvm_pmc fixed_counters[X86_PMC_MAX_FIXED];
+	struct kvm_pmc gp_counters[INTEL_PMC_MAX_GENERIC];
+	struct kvm_pmc fixed_counters[INTEL_PMC_MAX_FIXED];
 	struct irq_work irq_work;
 	u64 reprogram_pmi;
 };

arch/x86/include/asm/msr.h

@@ -115,8 +115,8 @@ notrace static inline int native_write_msr_safe(unsigned int msr,
 
 extern unsigned long long native_read_tsc(void);
 
-extern int native_rdmsr_safe_regs(u32 regs[8]);
-extern int native_wrmsr_safe_regs(u32 regs[8]);
+extern int rdmsr_safe_regs(u32 regs[8]);
+extern int wrmsr_safe_regs(u32 regs[8]);
 
 static __always_inline unsigned long long __native_read_tsc(void)
 {
@@ -187,43 +187,6 @@ static inline int rdmsrl_safe(unsigned msr, unsigned long long *p)
 	return err;
 }
 
-static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p)
-{
-	u32 gprs[8] = { 0 };
-	int err;
-
-	gprs[1] = msr;
-	gprs[7] = 0x9c5a203a;
-
-	err = native_rdmsr_safe_regs(gprs);
-
-	*p = gprs[0] | ((u64)gprs[2] << 32);
-
-	return err;
-}
-
-static inline int wrmsrl_amd_safe(unsigned msr, unsigned long long val)
-{
-	u32 gprs[8] = { 0 };
-
-	gprs[0] = (u32)val;
-	gprs[1] = msr;
-	gprs[2] = val >> 32;
-	gprs[7] = 0x9c5a203a;
-
-	return native_wrmsr_safe_regs(gprs);
-}
-
-static inline int rdmsr_safe_regs(u32 regs[8])
-{
-	return native_rdmsr_safe_regs(regs);
-}
-
-static inline int wrmsr_safe_regs(u32 regs[8])
-{
-	return native_wrmsr_safe_regs(regs);
-}
-
 #define rdtscl(low)						\
 	((low) = (u32)__native_read_tsc())
 
@@ -237,6 +200,8 @@ do {							\
 	(high) = (u32)(_l >> 32);			\
 } while (0)
 
+#define rdpmcl(counter, val) ((val) = native_read_pmc(counter))
+
 #define rdtscp(low, high, aux)					\
 do {                                                            \
 	unsigned long long _val = native_read_tscp(&(aux));     \
@@ -248,8 +213,7 @@ do {                                                            \
 
 #endif	/* !CONFIG_PARAVIRT */
 
-
-#define checking_wrmsrl(msr, val) wrmsr_safe((msr), (u32)(val),		\
+#define wrmsrl_safe(msr, val) wrmsr_safe((msr), (u32)(val),		\
 					     (u32)((val) >> 32))
 
 #define write_tsc(val1, val2) wrmsr(MSR_IA32_TSC, (val1), (val2))

arch/x86/include/asm/nmi.h

@@ -44,28 +44,14 @@ struct nmiaction {
 	const char		*name;
 };
 
-#define register_nmi_handler(t, fn, fg, n)		\
+#define register_nmi_handler(t, fn, fg, n, init...)	\
 ({							\
-	static struct nmiaction fn##_na = {		\
+	static struct nmiaction init fn##_na = {	\
 		.handler = (fn),			\
 		.name = (n),				\
 		.flags = (fg),				\
 	};						\
-	__register_nmi_handler((t), &fn##_na);	\
-})
-
-/*
- * For special handlers that register/unregister in the
- * init section only.  This should be considered rare.
- */
-#define register_nmi_handler_initonly(t, fn, fg, n)		\
-({							\
-	static struct nmiaction fn##_na __initdata = {		\
-		.handler = (fn),			\
-		.name = (n),				\
-		.flags = (fg),				\
-	};						\
-	__register_nmi_handler((t), &fn##_na);	\
+	__register_nmi_handler((t), &fn##_na);		\
 })
 
 int __register_nmi_handler(unsigned int, struct nmiaction *);

arch/x86/include/asm/paravirt.h

@@ -128,21 +128,11 @@ static inline u64 paravirt_read_msr(unsigned msr, int *err)
 	return PVOP_CALL2(u64, pv_cpu_ops.read_msr, msr, err);
 }
 
-static inline int paravirt_rdmsr_regs(u32 *regs)
-{
-	return PVOP_CALL1(int, pv_cpu_ops.rdmsr_regs, regs);
-}
-
 static inline int paravirt_write_msr(unsigned msr, unsigned low, unsigned high)
 {
 	return PVOP_CALL3(int, pv_cpu_ops.write_msr, msr, low, high);
 }
 
-static inline int paravirt_wrmsr_regs(u32 *regs)
-{
-	return PVOP_CALL1(int, pv_cpu_ops.wrmsr_regs, regs);
-}
-
 /* These should all do BUG_ON(_err), but our headers are too tangled. */
 #define rdmsr(msr, val1, val2)			\
 do {						\
@@ -176,9 +166,6 @@ do {						\
 	_err;					\
 })
 
-#define rdmsr_safe_regs(regs)	paravirt_rdmsr_regs(regs)
-#define wrmsr_safe_regs(regs)	paravirt_wrmsr_regs(regs)
-
 static inline int rdmsrl_safe(unsigned msr, unsigned long long *p)
 {
 	int err;
@@ -186,32 +173,6 @@ static inline int rdmsrl_safe(unsigned msr, unsigned long long *p)
 	*p = paravirt_read_msr(msr, &err);
 	return err;
 }
-static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p)
-{
-	u32 gprs[8] = { 0 };
-	int err;
-
-	gprs[1] = msr;
-	gprs[7] = 0x9c5a203a;
-
-	err = paravirt_rdmsr_regs(gprs);
-
-	*p = gprs[0] | ((u64)gprs[2] << 32);
-
-	return err;
-}
-
-static inline int wrmsrl_amd_safe(unsigned msr, unsigned long long val)
-{
-	u32 gprs[8] = { 0 };
-
-	gprs[0] = (u32)val;
-	gprs[1] = msr;
-	gprs[2] = val >> 32;
-	gprs[7] = 0x9c5a203a;
-
-	return paravirt_wrmsr_regs(gprs);
-}
 
 static inline u64 paravirt_read_tsc(void)
 {
@@ -252,6 +213,8 @@ do {						\
 	high = _l >> 32;			\
 } while (0)
 
+#define rdpmcl(counter, val) ((val) = paravirt_read_pmc(counter))
+
 static inline unsigned long long paravirt_rdtscp(unsigned int *aux)
 {
 	return PVOP_CALL1(u64, pv_cpu_ops.read_tscp, aux);

arch/x86/include/asm/paravirt_types.h

@@ -153,9 +153,7 @@ struct pv_cpu_ops {
 	/* MSR, PMC and TSR operations.
 	   err = 0/-EFAULT.  wrmsr returns 0/-EFAULT. */
 	u64 (*read_msr)(unsigned int msr, int *err);
-	int (*rdmsr_regs)(u32 *regs);
 	int (*write_msr)(unsigned int msr, unsigned low, unsigned high);
-	int (*wrmsr_regs)(u32 *regs);
 
 	u64 (*read_tsc)(void);
 	u64 (*read_pmc)(int counter);

arch/x86/include/asm/pci_x86.h

@@ -7,9 +7,13 @@
 #undef DEBUG
 
 #ifdef DEBUG
-#define DBG(x...) printk(x)
+#define DBG(fmt, ...) printk(fmt, ##__VA_ARGS__)
 #else
-#define DBG(x...)
+#define DBG(fmt, ...)				\
+do {						\
+	if (0)					\
+		printk(fmt, ##__VA_ARGS__);	\
+} while (0)
 #endif
 
 #define PCI_PROBE_BIOS		0x0001

arch/x86/include/asm/perf_event.h

@@ -5,11 +5,10 @@
  * Performance event hw details:
  */
 
-#define X86_PMC_MAX_GENERIC				       32
-#define X86_PMC_MAX_FIXED					3
+#define INTEL_PMC_MAX_GENERIC				       32
+#define INTEL_PMC_MAX_FIXED					3
+#define INTEL_PMC_IDX_FIXED				       32
 
-#define X86_PMC_IDX_GENERIC				        0
-#define X86_PMC_IDX_FIXED				       32
 #define X86_PMC_IDX_MAX					       64
 
 #define MSR_ARCH_PERFMON_PERFCTR0			      0xc1
@@ -48,8 +47,7 @@
 	(X86_RAW_EVENT_MASK          |  \
 	 AMD64_EVENTSEL_EVENT)
 #define AMD64_NUM_COUNTERS				4
-#define AMD64_NUM_COUNTERS_F15H				6
-#define AMD64_NUM_COUNTERS_MAX				AMD64_NUM_COUNTERS_F15H
+#define AMD64_NUM_COUNTERS_CORE				6
 
 #define ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL		0x3c
 #define ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK		(0x00 << 8)
@@ -121,16 +119,16 @@ struct x86_pmu_capability {
 
 /* Instr_Retired.Any: */
 #define MSR_ARCH_PERFMON_FIXED_CTR0	0x309
-#define X86_PMC_IDX_FIXED_INSTRUCTIONS	(X86_PMC_IDX_FIXED + 0)
+#define INTEL_PMC_IDX_FIXED_INSTRUCTIONS	(INTEL_PMC_IDX_FIXED + 0)
 
 /* CPU_CLK_Unhalted.Core: */
 #define MSR_ARCH_PERFMON_FIXED_CTR1	0x30a
-#define X86_PMC_IDX_FIXED_CPU_CYCLES	(X86_PMC_IDX_FIXED + 1)
+#define INTEL_PMC_IDX_FIXED_CPU_CYCLES	(INTEL_PMC_IDX_FIXED + 1)
 
 /* CPU_CLK_Unhalted.Ref: */
 #define MSR_ARCH_PERFMON_FIXED_CTR2	0x30b
-#define X86_PMC_IDX_FIXED_REF_CYCLES	(X86_PMC_IDX_FIXED + 2)
-#define X86_PMC_MSK_FIXED_REF_CYCLES	(1ULL << X86_PMC_IDX_FIXED_REF_CYCLES)
+#define INTEL_PMC_IDX_FIXED_REF_CYCLES	(INTEL_PMC_IDX_FIXED + 2)
+#define INTEL_PMC_MSK_FIXED_REF_CYCLES	(1ULL << INTEL_PMC_IDX_FIXED_REF_CYCLES)
 
 /*
  * We model BTS tracing as another fixed-mode PMC.
@@ -139,7 +137,7 @@ struct x86_pmu_capability {
  * values are used by actual fixed events and higher values are used
  * to indicate other overflow conditions in the PERF_GLOBAL_STATUS msr.
  */
-#define X86_PMC_IDX_FIXED_BTS				(X86_PMC_IDX_FIXED + 16)
+#define INTEL_PMC_IDX_FIXED_BTS				(INTEL_PMC_IDX_FIXED + 16)
 
 /*
  * IBS cpuid feature detection
@@ -234,6 +232,7 @@ struct perf_guest_switch_msr {
 
 extern struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr);
 extern void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap);
+extern void perf_check_microcode(void);
 #else
 static inline perf_guest_switch_msr *perf_guest_get_msrs(int *nr)
 {
@@ -247,6 +246,7 @@ static inline void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap)
 }
 
 static inline void perf_events_lapic_init(void)	{ }
+static inline void perf_check_microcode(void) { }
 #endif
 
 #if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_AMD)

arch/x86/include/asm/pgtable-2level.h

@@ -2,9 +2,9 @@
 #define _ASM_X86_PGTABLE_2LEVEL_H
 
 #define pte_ERROR(e) \
-	printk("%s:%d: bad pte %08lx.\n", __FILE__, __LINE__, (e).pte_low)
+	pr_err("%s:%d: bad pte %08lx\n", __FILE__, __LINE__, (e).pte_low)
 #define pgd_ERROR(e) \
-	printk("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e))
+	pr_err("%s:%d: bad pgd %08lx\n", __FILE__, __LINE__, pgd_val(e))
 
 /*
  * Certain architectures need to do special things when PTEs

arch/x86/include/asm/pgtable-3level.h

@@ -9,13 +9,13 @@
  */
 
 #define pte_ERROR(e)							\
-	printk("%s:%d: bad pte %p(%08lx%08lx).\n",			\
+	pr_err("%s:%d: bad pte %p(%08lx%08lx)\n",			\
 	       __FILE__, __LINE__, &(e), (e).pte_high, (e).pte_low)
 #define pmd_ERROR(e)							\
-	printk("%s:%d: bad pmd %p(%016Lx).\n",				\
+	pr_err("%s:%d: bad pmd %p(%016Lx)\n",				\
 	       __FILE__, __LINE__, &(e), pmd_val(e))
 #define pgd_ERROR(e)							\
-	printk("%s:%d: bad pgd %p(%016Lx).\n",				\
+	pr_err("%s:%d: bad pgd %p(%016Lx)\n",				\
 	       __FILE__, __LINE__, &(e), pgd_val(e))
 
 /* Rules for using set_pte: the pte being assigned *must* be

arch/x86/include/asm/pgtable_64.h

@@ -26,16 +26,16 @@ extern pgd_t init_level4_pgt[];
 extern void paging_init(void);
 
 #define pte_ERROR(e)					\
-	printk("%s:%d: bad pte %p(%016lx).\n",		\
+	pr_err("%s:%d: bad pte %p(%016lx)\n",		\
 	       __FILE__, __LINE__, &(e), pte_val(e))
 #define pmd_ERROR(e)					\
-	printk("%s:%d: bad pmd %p(%016lx).\n",		\
+	pr_err("%s:%d: bad pmd %p(%016lx)\n",		\
 	       __FILE__, __LINE__, &(e), pmd_val(e))
 #define pud_ERROR(e)					\
-	printk("%s:%d: bad pud %p(%016lx).\n",		\
+	pr_err("%s:%d: bad pud %p(%016lx)\n",		\
 	       __FILE__, __LINE__, &(e), pud_val(e))
 #define pgd_ERROR(e)					\
-	printk("%s:%d: bad pgd %p(%016lx).\n",		\
+	pr_err("%s:%d: bad pgd %p(%016lx)\n",		\
 	       __FILE__, __LINE__, &(e), pgd_val(e))
 
 struct mm_struct;

arch/x86/include/asm/realmode.h

@@ -21,8 +21,9 @@ struct real_mode_header {
 	u32	wakeup_header;
 #endif
 	/* APM/BIOS reboot */
-#ifdef CONFIG_X86_32
 	u32	machine_real_restart_asm;
+#ifdef CONFIG_X86_64
+	u32	machine_real_restart_seg;
 #endif
 };
 

arch/x86/include/asm/reboot.h

@@ -18,8 +18,8 @@ extern struct machine_ops machine_ops;
 
 void native_machine_crash_shutdown(struct pt_regs *regs);
 void native_machine_shutdown(void);
-void machine_real_restart(unsigned int type);
-/* These must match dispatch_table in reboot_32.S */
+void __noreturn machine_real_restart(unsigned int type);
+/* These must match dispatch in arch/x86/realmore/rm/reboot.S */
 #define MRR_BIOS	0
 #define MRR_APM		1