Linux 3.0.80

commit e1d45ae10a upstream.

If we set mantis->fe to NULL on an error its not a good idea to then try
passing NULL to the unregister paths and oopsing really.

Resolves-bug: https://bugzilla.kernel.org/show_bug.cgi?id=16473

Signed-off-by: Alan Cox <alan@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
Cc: Bjørn Mork <bjorn@mork.no>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

Documentation/kernel-parameters.txt

@@ -531,6 +531,8 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			UART at the specified I/O port or MMIO address,
 			switching to the matching ttyS device later.  The
 			options are the same as for ttyS, above.
+		hvc<n>	Use the hypervisor console device <n>. This is for
+			both Xen and PowerPC hypervisors.
 
                 If the device connected to the port is not a TTY but a braille
                 device, prepend "brl," before the device type, for instance
@@ -679,6 +681,7 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 
 	earlyprintk=	[X86,SH,BLACKFIN]
 			earlyprintk=vga
+			earlyprintk=xen
 			earlyprintk=serial[,ttySn[,baudrate]]
 			earlyprintk=ttySn[,baudrate]
 			earlyprintk=dbgp[debugController#]
@@ -696,6 +699,8 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			The VGA output is eventually overwritten by the real
 			console.
 
+			The xen output can only be used by Xen PV guests.
+
 	ekgdboc=	[X86,KGDB] Allow early kernel console debugging
 			ekgdboc=kbd
 

Documentation/networking/ip-sysctl.txt

@@ -534,6 +534,11 @@ tcp_thin_dupack - BOOLEAN
 	Documentation/networking/tcp-thin.txt
 	Default: 0
 
+tcp_challenge_ack_limit - INTEGER
+	Limits number of Challenge ACK sent per second, as recommended
+	in RFC 5961 (Improving TCP's Robustness to Blind In-Window Attacks)
+	Default: 100
+
 UDP variables:
 
 udp_mem - vector of 3 INTEGERs: min, pressure, max

MAINTAINERS

@@ -2491,7 +2491,7 @@ S:	Maintained
 F:	drivers/net/eexpress.*
 
 ETHERNET BRIDGE
-M:	Stephen Hemminger <shemminger@linux-foundation.org>
+M:	Stephen Hemminger <stephen@networkplumber.org>
 L:	bridge@lists.linux-foundation.org
 L:	netdev@vger.kernel.org
 W:	http://www.linuxfoundation.org/en/Net:Bridge
@@ -4327,7 +4327,7 @@ S:	Supported
 F:	drivers/infiniband/hw/nes/
 
 NETEM NETWORK EMULATOR
-M:	Stephen Hemminger <shemminger@linux-foundation.org>
+M:	Stephen Hemminger <stephen@networkplumber.org>
 L:	netem@lists.linux-foundation.org
 S:	Maintained
 F:	net/sched/sch_netem.c
@@ -5779,7 +5779,7 @@ S:	Maintained
 F:	drivers/usb/misc/sisusbvga/
 
 SKGE, SKY2 10/100/1000 GIGABIT ETHERNET DRIVERS
-M:	Stephen Hemminger <shemminger@linux-foundation.org>
+M:	Stephen Hemminger <stephen@networkplumber.org>
 L:	netdev@vger.kernel.org
 S:	Maintained
 F:	drivers/net/skge.*

Makefile

@@ -1,6 +1,6 @@
 VERSION = 3
 PATCHLEVEL = 0
-SUBLEVEL = 55
+SUBLEVEL = 80
 EXTRAVERSION =
 NAME = Sneaky Weasel
 

arch/alpha/kernel/sys_nautilus.c

@@ -189,6 +189,10 @@ nautilus_machine_check(unsigned long vector, unsigned long la_ptr)
 extern void free_reserved_mem(void *, void *);
 extern void pcibios_claim_one_bus(struct pci_bus *);
 
+static struct resource irongate_io = {
+	.name	= "Irongate PCI IO",
+	.flags	= IORESOURCE_IO,
+};
 static struct resource irongate_mem = {
 	.name	= "Irongate PCI MEM",
 	.flags	= IORESOURCE_MEM,
@@ -210,6 +214,7 @@ nautilus_init_pci(void)
 
 	irongate = pci_get_bus_and_slot(0, 0);
 	bus->self = irongate;
+	bus->resource[0] = &irongate_io;
 	bus->resource[1] = &irongate_mem;
 
 	pci_bus_size_bridges(bus);

arch/arm/include/asm/hwcap.h

@@ -18,8 +18,9 @@
 #define HWCAP_THUMBEE	2048
 #define HWCAP_NEON	4096
 #define HWCAP_VFPv3	8192
-#define HWCAP_VFPv3D16	16384
+#define HWCAP_VFPv3D16	(1 << 14)	/* also set for VFPv4-D16 */
 #define HWCAP_TLS	32768
+#define HWCAP_VFPD32	(1 << 19)	/* set if VFP has 32 regs (not 16) */
 
 #if defined(__KERNEL__) && !defined(__ASSEMBLY__)
 /*

arch/arm/include/asm/signal.h

@@ -127,6 +127,7 @@ struct sigaction {
 	__sigrestore_t sa_restorer;
 	sigset_t sa_mask;		/* mask last for extensibility */
 };
+#define __ARCH_HAS_SA_RESTORER
 
 struct k_sigaction {
 	struct sigaction sa;

arch/arm/include/asm/vfpmacros.h

@@ -27,9 +27,9 @@
 #if __LINUX_ARM_ARCH__ <= 6
 	ldr	\tmp, =elf_hwcap		    @ may not have MVFR regs
 	ldr	\tmp, [\tmp, #0]
-	tst	\tmp, #HWCAP_VFPv3D16
-	ldceql	p11, cr0, [\base],#32*4		    @ FLDMIAD \base!, {d16-d31}
-	addne	\base, \base, #32*4		    @ step over unused register space
+	tst	\tmp, #HWCAP_VFPD32
+	ldcnel	p11, cr0, [\base],#32*4		    @ FLDMIAD \base!, {d16-d31}
+	addeq	\base, \base, #32*4		    @ step over unused register space
 #else
 	VFPFMRX	\tmp, MVFR0			    @ Media and VFP Feature Register 0
 	and	\tmp, \tmp, #MVFR0_A_SIMD_MASK	    @ A_SIMD field
@@ -51,9 +51,9 @@
 #if __LINUX_ARM_ARCH__ <= 6
 	ldr	\tmp, =elf_hwcap		    @ may not have MVFR regs
 	ldr	\tmp, [\tmp, #0]
-	tst	\tmp, #HWCAP_VFPv3D16
-	stceql	p11, cr0, [\base],#32*4		    @ FSTMIAD \base!, {d16-d31}
-	addne	\base, \base, #32*4		    @ step over unused register space
+	tst	\tmp, #HWCAP_VFPD32
+	stcnel	p11, cr0, [\base],#32*4		    @ FSTMIAD \base!, {d16-d31}
+	addeq	\base, \base, #32*4		    @ step over unused register space
 #else
 	VFPFMRX	\tmp, MVFR0			    @ Media and VFP Feature Register 0
 	and	\tmp, \tmp, #MVFR0_A_SIMD_MASK	    @ A_SIMD field

arch/arm/kernel/swp_emulate.c

@@ -108,10 +108,12 @@ static void set_segfault(struct pt_regs *regs, unsigned long addr)
 {
 	siginfo_t info;
 
+	down_read(&current->mm->mmap_sem);
 	if (find_vma(current->mm, addr) == NULL)
 		info.si_code = SEGV_MAPERR;
 	else
 		info.si_code = SEGV_ACCERR;
+	up_read(&current->mm->mmap_sem);
 
 	info.si_signo = SIGSEGV;
 	info.si_errno = 0;

arch/arm/mach-dove/include/mach/pm.h

@@ -45,7 +45,7 @@ static inline int pmu_to_irq(int pin)
 
 static inline int irq_to_pmu(int irq)
 {
-	if (IRQ_DOVE_PMU_START < irq && irq < NR_IRQS)
+	if (IRQ_DOVE_PMU_START <= irq && irq < NR_IRQS)
 		return irq - IRQ_DOVE_PMU_START;
 
 	return -EINVAL;

arch/arm/mach-dove/irq.c

@@ -61,8 +61,20 @@ static void pmu_irq_ack(struct irq_data *d)
 	int pin = irq_to_pmu(d->irq);
 	u32 u;
 
+	/*
+	 * The PMU mask register is not RW0C: it is RW.  This means that
+	 * the bits take whatever value is written to them; if you write
+	 * a '1', you will set the interrupt.
+	 *
+	 * Unfortunately this means there is NO race free way to clear
+	 * these interrupts.
+	 *
+	 * So, let's structure the code so that the window is as small as
+	 * possible.
+	 */
 	u = ~(1 << (pin & 31));
-	writel(u, PMU_INTERRUPT_CAUSE);
+	u &= readl_relaxed(PMU_INTERRUPT_CAUSE);
+	writel_relaxed(u, PMU_INTERRUPT_CAUSE);
 }
 
 static struct irq_chip pmu_irq_chip = {

arch/arm/mach-omap2/board-rx51-peripherals.c

@@ -56,11 +56,11 @@
 
 #define RX51_USB_TRANSCEIVER_RST_GPIO	67
 
-/* list all spi devices here */
+/* List all SPI devices here. Note that the list/probe order seems to matter! */
 enum {
 	RX51_SPI_WL1251,
-	RX51_SPI_MIPID,		/* LCD panel */
 	RX51_SPI_TSC2005,	/* Touch Controller */
+	RX51_SPI_MIPID,		/* LCD panel */
 };
 
 static struct wl12xx_platform_data wl1251_pdata;

arch/arm/mach-pxa/include/mach/smemc.h

@@ -37,6 +37,7 @@
 #define CSADRCFG1	(SMEMC_VIRT + 0x84)  /* Address Configuration Register for CS1 */
 #define CSADRCFG2	(SMEMC_VIRT + 0x88)  /* Address Configuration Register for CS2 */
 #define CSADRCFG3	(SMEMC_VIRT + 0x8C)  /* Address Configuration Register for CS3 */
+#define CSMSADRCFG	(SMEMC_VIRT + 0xA0)  /* Chip Select Configuration Register */
 
 /*
  * More handy macros for PCMCIA

arch/arm/mach-pxa/smemc.c

@@ -40,6 +40,8 @@ static void pxa3xx_smemc_resume(void)
 	__raw_writel(csadrcfg[1], CSADRCFG1);
 	__raw_writel(csadrcfg[2], CSADRCFG2);
 	__raw_writel(csadrcfg[3], CSADRCFG3);
+	/* CSMSADRCFG wakes up in its default state (0), so we need to set it */
+	__raw_writel(0x2, CSMSADRCFG);
 }
 
 static struct syscore_ops smemc_syscore_ops = {
@@ -49,8 +51,19 @@ static struct syscore_ops smemc_syscore_ops = {
 
 static int __init smemc_init(void)
 {
-	if (cpu_is_pxa3xx())
+	if (cpu_is_pxa3xx()) {
+		/*
+		 * The only documentation we have on the
+		 * Chip Select Configuration Register (CSMSADRCFG) is that
+		 * it must be programmed to 0x2.
+		 * Moreover, in the bit definitions, the second bit
+		 * (CSMSADRCFG[1]) is called "SETALWAYS".
+		 * Other bits are reserved in this register.
+		 */
+		__raw_writel(0x2, CSMSADRCFG);
+
 		register_syscore_ops(&smemc_syscore_ops);
+	}
 
 	return 0;
 }

arch/arm/mm/alignment.c

@@ -721,7 +721,6 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 	unsigned long instr = 0, instrptr;
 	int (*handler)(unsigned long addr, unsigned long instr, struct pt_regs *regs);
 	unsigned int type;
-	mm_segment_t fs;
 	unsigned int fault;
 	u16 tinstr = 0;
 	int isize = 4;
@@ -729,16 +728,15 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 
 	instrptr = instruction_pointer(regs);
 
-	fs = get_fs();
-	set_fs(KERNEL_DS);
 	if (thumb_mode(regs)) {
-		fault = __get_user(tinstr, (u16 *)(instrptr & ~1));
+		u16 *ptr = (u16 *)(instrptr & ~1);
+		fault = probe_kernel_address(ptr, tinstr);
 		if (!fault) {
 			if (cpu_architecture() >= CPU_ARCH_ARMv7 &&
 			    IS_T32(tinstr)) {
 				/* Thumb-2 32-bit */
 				u16 tinst2 = 0;
-				fault = __get_user(tinst2, (u16 *)(instrptr+2));
+				fault = probe_kernel_address(ptr + 1, tinst2);
 				instr = (tinstr << 16) | tinst2;
 				thumb2_32b = 1;
 			} else {
@@ -747,8 +745,7 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 			}
 		}
 	} else
-		fault = __get_user(instr, (u32 *)instrptr);
-	set_fs(fs);
+		fault = probe_kernel_address(instrptr, instr);
 
 	if (fault) {
 		type = TYPE_FAULT;

arch/arm/mm/cache-feroceon-l2.c

@@ -342,6 +342,7 @@ void __init feroceon_l2_init(int __l2_wt_override)
 	outer_cache.inv_range = feroceon_l2_inv_range;
 	outer_cache.clean_range = feroceon_l2_clean_range;
 	outer_cache.flush_range = feroceon_l2_flush_range;
+	outer_cache.inv_all = l2_inv_all;
 
 	enable_l2();
 

arch/arm/mm/dma-mapping.c

@@ -467,25 +467,27 @@ static void dma_cache_maint_page(struct page *page, unsigned long offset,
 	size_t size, enum dma_data_direction dir,
 	void (*op)(const void *, size_t, int))
 {
+	unsigned long pfn;
+	size_t left = size;
+
+	pfn = page_to_pfn(page) + offset / PAGE_SIZE;
+	offset %= PAGE_SIZE;
+
 	/*
 	 * A single sg entry may refer to multiple physically contiguous
 	 * pages.  But we still need to process highmem pages individually.
 	 * If highmem is not configured then the bulk of this loop gets
 	 * optimized out.
 	 */
-	size_t left = size;
 	do {
 		size_t len = left;
 		void *vaddr;
 
+		page = pfn_to_page(pfn);
+
 		if (PageHighMem(page)) {
-			if (len + offset > PAGE_SIZE) {
-				if (offset >= PAGE_SIZE) {
-					page += offset / PAGE_SIZE;
-					offset %= PAGE_SIZE;
-				}
+			if (len + offset > PAGE_SIZE)
 				len = PAGE_SIZE - offset;
-			}
 			vaddr = kmap_high_get(page);
 			if (vaddr) {
 				vaddr += offset;
@@ -502,7 +504,7 @@ static void dma_cache_maint_page(struct page *page, unsigned long offset,
 			op(vaddr, len, dir);
 		}
 		offset = 0;
-		page++;
+		pfn++;
 		left -= len;
 	} while (left);
 }

arch/arm/mm/mmu.c

@@ -467,7 +467,7 @@ static void __init build_mem_type_table(void)
 	}
 
 	for (i = 0; i < 16; i++) {
-		unsigned long v = pgprot_val(protection_map[i]);
+		pteval_t v = pgprot_val(protection_map[i]);
 		protection_map[i] = __pgprot(v | user_pgprot);
 	}
 

arch/arm/vfp/vfpmodule.c

@@ -369,7 +369,7 @@ void VFP_bounce(u32 trigger, u32 fpexc, struct pt_regs *regs)
 	 * If there isn't a second FP instruction, exit now. Note that
 	 * the FPEXC.FP2V bit is valid only if FPEXC.EX is 1.
 	 */
-	if (fpexc ^ (FPEXC_EX | FPEXC_FP2V))
+	if ((fpexc & (FPEXC_EX | FPEXC_FP2V)) != (FPEXC_EX | FPEXC_FP2V))
 		goto exit;
 
 	/*
@@ -575,11 +575,14 @@ static int __init vfp_init(void)
 			elf_hwcap |= HWCAP_VFPv3;
 
 			/*
-			 * Check for VFPv3 D16. CPUs in this configuration
-			 * only have 16 x 64bit registers.
+			 * Check for VFPv3 D16 and VFPv4 D16.  CPUs in
+			 * this configuration only have 16 x 64bit
+			 * registers.
 			 */
 			if (((fmrx(MVFR0) & MVFR0_A_SIMD_MASK)) == 1)
-				elf_hwcap |= HWCAP_VFPv3D16;
+				elf_hwcap |= HWCAP_VFPv3D16; /* also v4-D16 */
+			else
+				elf_hwcap |= HWCAP_VFPD32;
 		}
 #endif
 #ifdef CONFIG_NEON

arch/avr32/include/asm/signal.h

@@ -128,6 +128,7 @@ struct sigaction {
 	__sigrestore_t sa_restorer;
 	sigset_t sa_mask;		/* mask last for extensibility */
 };
+#define __ARCH_HAS_SA_RESTORER
 
 struct k_sigaction {
 	struct sigaction sa;

arch/cris/include/asm/io.h

@@ -133,12 +133,39 @@ static inline void writel(unsigned int b, volatile void __iomem *addr)
 #define insb(port,addr,count) (cris_iops ? cris_iops->read_io(port,addr,1,count) : 0)
 #define insw(port,addr,count) (cris_iops ? cris_iops->read_io(port,addr,2,count) : 0)
 #define insl(port,addr,count) (cris_iops ? cris_iops->read_io(port,addr,4,count) : 0)
-#define outb(data,port) if (cris_iops) cris_iops->write_io(port,(void*)(unsigned)data,1,1)
-#define outw(data,port) if (cris_iops) cris_iops->write_io(port,(void*)(unsigned)data,2,1)
-#define outl(data,port) if (cris_iops) cris_iops->write_io(port,(void*)(unsigned)data,4,1)
-#define outsb(port,addr,count) if(cris_iops) cris_iops->write_io(port,(void*)addr,1,count)
-#define outsw(port,addr,count) if(cris_iops) cris_iops->write_io(port,(void*)addr,2,count)
-#define outsl(port,addr,count) if(cris_iops) cris_iops->write_io(port,(void*)addr,3,count)
+static inline void outb(unsigned char data, unsigned int port)
+{
+	if (cris_iops)
+		cris_iops->write_io(port, (void *) &data, 1, 1);
+}
+static inline void outw(unsigned short data, unsigned int port)
+{
+	if (cris_iops)
+		cris_iops->write_io(port, (void *) &data, 2, 1);
+}
+static inline void outl(unsigned int data, unsigned int port)
+{
+	if (cris_iops)
+		cris_iops->write_io(port, (void *) &data, 4, 1);
+}
+static inline void outsb(unsigned int port, const void *addr,
+			 unsigned long count)
+{
+	if (cris_iops)
+		cris_iops->write_io(port, (void *)addr, 1, count);
+}
+static inline void outsw(unsigned int port, const void *addr,
+			 unsigned long count)
+{
+	if (cris_iops)
+		cris_iops->write_io(port, (void *)addr, 2, count);
+}
+static inline void outsl(unsigned int port, const void *addr,
+			 unsigned long count)
+{
+	if (cris_iops)
+		cris_iops->write_io(port, (void *)addr, 4, count);
+}
 
 /*
  * Convert a physical pointer to a virtual kernel pointer for /dev/mem

arch/cris/include/asm/signal.h

@@ -122,6 +122,7 @@ struct sigaction {
 	void (*sa_restorer)(void);
 	sigset_t sa_mask;		/* mask last for extensibility */
 };
+#define __ARCH_HAS_SA_RESTORER
 
 struct k_sigaction {
 	struct sigaction sa;

arch/h8300/include/asm/signal.h

@@ -121,6 +121,7 @@ struct sigaction {
 	void (*sa_restorer)(void);
 	sigset_t sa_mask;		/* mask last for extensibility */
 };
+#define __ARCH_HAS_SA_RESTORER
 
 struct k_sigaction {
 	struct sigaction sa;

arch/ia64/include/asm/futex.h

@@ -107,16 +107,15 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 		return -EFAULT;
 
 	{
-		register unsigned long r8 __asm ("r8");
+		register unsigned long r8 __asm ("r8") = 0;
 		unsigned long prev;
 		__asm__ __volatile__(
 			"	mf;;					\n"
-			"	mov %0=r0				\n"
 			"	mov ar.ccv=%4;;				\n"
 			"[1:]	cmpxchg4.acq %1=[%2],%3,ar.ccv		\n"
 			"	.xdata4 \"__ex_table\", 1b-., 2f-.	\n"
 			"[2:]"
-			: "=r" (r8), "=r" (prev)
+			: "+r" (r8), "=&r" (prev)
 			: "r" (uaddr), "r" (newval),
 			  "rO" ((long) (unsigned) oldval)
 			: "memory");

arch/ia64/include/asm/mca.h

@@ -143,6 +143,7 @@ extern unsigned long __per_cpu_mca[NR_CPUS];
 extern int cpe_vector;
 extern int ia64_cpe_irq;
 extern void ia64_mca_init(void);
+extern void ia64_mca_irq_init(void);
 extern void ia64_mca_cpu_init(void *);
 extern void ia64_os_mca_dispatch(void);
 extern void ia64_os_mca_dispatch_end(void);

arch/ia64/kernel/irq.c

@@ -23,6 +23,8 @@
 #include <linux/interrupt.h>
 #include <linux/kernel_stat.h>
 
+#include <asm/mca.h>
+
 /*
  * 'what should we do if we get a hw irq event on an illegal vector'.
  * each architecture has to answer this themselves.
@@ -83,6 +85,12 @@ bool is_affinity_mask_valid(const struct cpumask *cpumask)
 
 #endif /* CONFIG_SMP */
 
+int __init arch_early_irq_init(void)
+{
+	ia64_mca_irq_init();
+	return 0;
+}
+
 #ifdef CONFIG_HOTPLUG_CPU
 unsigned int vectors_in_migration[NR_IRQS];
 

arch/ia64/kernel/mca.c

@@ -2071,22 +2071,16 @@ ia64_mca_init(void)
 	printk(KERN_INFO "MCA related initialization done\n");
 }
 
-/*
- * ia64_mca_late_init
- *
- *	Opportunity to setup things that require initialization later
- *	than ia64_mca_init.  Setup a timer to poll for CPEs if the
- *	platform doesn't support an interrupt driven mechanism.
- *
- *  Inputs  :   None
- *  Outputs :   Status
- */
-static int __init
-ia64_mca_late_init(void)
-{
-	if (!mca_init)
-		return 0;
 
+/*
+ * These pieces cannot be done in ia64_mca_init() because it is called before
+ * early_irq_init() which would wipe out our percpu irq registrations. But we
+ * cannot leave them until ia64_mca_late_init() because by then all the other
+ * processors have been brought online and have set their own CMC vectors to
+ * point at a non-existant action. Called from arch_early_irq_init().
+ */
+void __init ia64_mca_irq_init(void)
+{
 	/*
 	 *  Configure the CMCI/P vector and handler. Interrupts for CMC are
 	 *  per-processor, so AP CMC interrupts are setup in smp_callin() (smpboot.c).
@@ -2105,6 +2099,23 @@ ia64_mca_late_init(void)
 	/* Setup the CPEI/P handler */
 	register_percpu_irq(IA64_CPEP_VECTOR, &mca_cpep_irqaction);
 #endif
+}
+
+/*
+ * ia64_mca_late_init
+ *
+ *	Opportunity to setup things that require initialization later
+ *	than ia64_mca_init.  Setup a timer to poll for CPEs if the
+ *	platform doesn't support an interrupt driven mechanism.
+ *
+ *  Inputs  :   None
+ *  Outputs :   Status
+ */
+static int __init
+ia64_mca_late_init(void)
+{
+	if (!mca_init)
+		return 0;
 
 	register_hotcpu_notifier(&mca_cpu_notifier);
 

arch/ia64/kvm/kvm-ia64.c

@@ -1168,6 +1168,11 @@ out:
 
 #define PALE_RESET_ENTRY    0x80000000ffffffb0UL
 
+bool kvm_vcpu_compatible(struct kvm_vcpu *vcpu)
+{
+	return irqchip_in_kernel(vcpu->kcm) == (vcpu->arch.apic != NULL);
+}
+
 int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 {
 	struct kvm_vcpu *v;

arch/ia64/kvm/vtlb.c

@@ -256,7 +256,7 @@ u64 guest_vhpt_lookup(u64 iha, u64 *pte)
 			"srlz.d;;"
 			"ssm psr.i;;"
 			"srlz.d;;"
-			: "=r"(ret) : "r"(iha), "r"(pte):"memory");
+			: "=&r"(ret) : "r"(iha), "r"(pte) : "memory");
 
 	return ret;
 }

arch/m32r/include/asm/signal.h

@@ -123,6 +123,7 @@ struct sigaction {
 	__sigrestore_t sa_restorer;
 	sigset_t sa_mask;		/* mask last for extensibility */
 };
+#define __ARCH_HAS_SA_RESTORER
 
 struct k_sigaction {
 	struct sigaction sa;

arch/m68k/include/asm/signal.h

@@ -119,6 +119,7 @@ struct sigaction {
 	__sigrestore_t sa_restorer;
 	sigset_t sa_mask;		/* mask last for extensibility */
 };
+#define __ARCH_HAS_SA_RESTORER
 
 struct k_sigaction {
 	struct sigaction sa;

arch/mn10300/include/asm/signal.h

@@ -131,6 +131,7 @@ struct sigaction {
 	__sigrestore_t sa_restorer;
 	sigset_t sa_mask;		/* mask last for extensibility */
 };
+#define __ARCH_HAS_SA_RESTORER
 
 struct k_sigaction {
 	struct sigaction sa;

arch/parisc/include/asm/pgtable.h

@@ -12,11 +12,10 @@
 
 #include <linux/bitops.h>
 #include <linux/spinlock.h>
+#include <linux/mm_types.h>
 #include <asm/processor.h>
 #include <asm/cache.h>
 
-struct vm_area_struct;
-
 /*
  * kern_addr_valid(ADDR) tests if ADDR is pointing to valid kernel
  * memory.  For the return value to be meaningful, ADDR must be >=
@@ -40,7 +39,14 @@ struct vm_area_struct;
         do{                                                     \
                 *(pteptr) = (pteval);                           \
         } while(0)
-#define set_pte_at(mm,addr,ptep,pteval) set_pte(ptep,pteval)
+
+extern void purge_tlb_entries(struct mm_struct *, unsigned long);
+
+#define set_pte_at(mm, addr, ptep, pteval)                      \
+	do {                                                    \
+		set_pte(ptep, pteval);                          \
+		purge_tlb_entries(mm, addr);                    \
+	} while (0)
 
 #endif /* !__ASSEMBLY__ */
 
@@ -464,6 +470,7 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr,
 		old = pte_val(*ptep);
 		new = pte_val(pte_wrprotect(__pte (old)));
 	} while (cmpxchg((unsigned long *) ptep, old, new) != old);
+	purge_tlb_entries(mm, addr);
 #else
 	pte_t old_pte = *ptep;
 	set_pte_at(mm, addr, ptep, pte_wrprotect(old_pte));

arch/parisc/kernel/cache.c

@@ -421,6 +421,24 @@ void kunmap_parisc(void *addr)
 EXPORT_SYMBOL(kunmap_parisc);
 #endif
 
+void purge_tlb_entries(struct mm_struct *mm, unsigned long addr)
+{
+	unsigned long flags;
+
+	/* Note: purge_tlb_entries can be called at startup with
+	   no context.  */
+
+	/* Disable preemption while we play with %sr1.  */
+	preempt_disable();
+	mtsp(mm->context, 1);
+	purge_tlb_start(flags);
+	pdtlb(addr);
+	pitlb(addr);
+	purge_tlb_end(flags);
+	preempt_enable();
+}
+EXPORT_SYMBOL(purge_tlb_entries);
+
 void __flush_tlb_range(unsigned long sid, unsigned long start,
 		       unsigned long end)
 {

arch/powerpc/include/asm/signal.h

@@ -109,6 +109,7 @@ struct sigaction {
 	__sigrestore_t sa_restorer;
 	sigset_t sa_mask;		/* mask last for extensibility */
 };
+#define __ARCH_HAS_SA_RESTORER
 
 struct k_sigaction {
 	struct sigaction sa;

arch/powerpc/kernel/cputable.c

@@ -268,7 +268,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_features		= CPU_FTRS_PPC970,
 		.cpu_user_features	= COMMON_USER_POWER4 |
 			PPC_FEATURE_HAS_ALTIVEC_COMP,
-		.mmu_features		= MMU_FTR_HPTE_TABLE,
+		.mmu_features		= MMU_FTRS_PPC970,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.num_pmcs		= 8,

arch/powerpc/kernel/head_64.S

@@ -425,7 +425,7 @@ _STATIC(__after_prom_start)
 	tovirt(r6,r6)			/* on booke, we already run at PAGE_OFFSET */
 #endif
 
-#ifdef CONFIG_CRASH_DUMP
+#ifdef CONFIG_RELOCATABLE
 /*
  * Check if the kernel has to be running as relocatable kernel based on the
  * variable __run_at_load, if it is set the kernel is treated as relocatable
@@ -492,6 +492,7 @@ _GLOBAL(copy_and_flush)
 	sync
 	addi	r5,r5,8
 	addi	r6,r6,8
+	isync
 	blr
 
 .align 8

arch/powerpc/kernel/machine_kexec_64.c

@@ -163,6 +163,8 @@ static int kexec_all_irq_disabled = 0;
 static void kexec_smp_down(void *arg)
 {
 	local_irq_disable();
+	hard_irq_disable();
+
 	mb(); /* make sure our irqs are disabled before we say they are */
 	get_paca()->kexec_state = KEXEC_STATE_IRQS_OFF;
 	while(kexec_all_irq_disabled == 0)
@@ -245,6 +247,8 @@ static void kexec_prepare_cpus(void)
 	wake_offline_cpus();
 	smp_call_function(kexec_smp_down, NULL, /* wait */0);
 	local_irq_disable();
+	hard_irq_disable();
+
 	mb(); /* make sure IRQs are disabled before we say they are */
 	get_paca()->kexec_state = KEXEC_STATE_IRQS_OFF;
 
@@ -282,6 +286,7 @@ static void kexec_prepare_cpus(void)
 	if (ppc_md.kexec_cpu_down)
 		ppc_md.kexec_cpu_down(0, 0);
 	local_irq_disable();
+	hard_irq_disable();
 }
 
 #endif /* SMP */

arch/powerpc/kernel/ptrace.c

@@ -1497,9 +1497,14 @@ long arch_ptrace(struct task_struct *child, long request,
 		if (index < PT_FPR0) {
 			tmp = ptrace_get_reg(child, (int) index);
 		} else {
+			unsigned int fpidx = index - PT_FPR0;
+
 			flush_fp_to_thread(child);
-			tmp = ((unsigned long *)child->thread.fpr)
-				[TS_FPRWIDTH * (index - PT_FPR0)];
+			if (fpidx < (PT_FPSCR - PT_FPR0))
+				tmp = ((unsigned long *)child->thread.fpr)
+					[fpidx * TS_FPRWIDTH];
+			else
+				tmp = child->thread.fpscr.val;
 		}
 		ret = put_user(tmp, datalp);
 		break;
@@ -1525,9 +1530,14 @@ long arch_ptrace(struct task_struct *child, long request,
 		if (index < PT_FPR0) {
 			ret = ptrace_put_reg(child, index, data);
 		} else {
+			unsigned int fpidx = index - PT_FPR0;
+
 			flush_fp_to_thread(child);
-			((unsigned long *)child->thread.fpr)
-				[TS_FPRWIDTH * (index - PT_FPR0)] = data;
+			if (fpidx < (PT_FPSCR - PT_FPR0))
+				((unsigned long *)child->thread.fpr)
+					[fpidx * TS_FPRWIDTH] = data;
+			else
+				child->thread.fpscr.val = data;
 			ret = 0;
 		}
 		break;

arch/powerpc/kernel/sysfs.c

@@ -192,6 +192,14 @@ static ssize_t show_dscr_default(struct sysdev_class *class,
 	return sprintf(buf, "%lx\n", dscr_default);
 }
 
+static void update_dscr(void *dummy)
+{
+	if (!current->thread.dscr_inherit) {
+		current->thread.dscr = dscr_default;
+		mtspr(SPRN_DSCR, dscr_default);
+	}
+}
+
 static ssize_t __used store_dscr_default(struct sysdev_class *class,
 		struct sysdev_class_attribute *attr, const char *buf,
 		size_t count)
@@ -204,6 +212,8 @@ static ssize_t __used store_dscr_default(struct sysdev_class *class,
 		return -EINVAL;
 	dscr_default = val;
 
+	on_each_cpu(update_dscr, NULL, 1);
+
 	return count;
 }
 

arch/powerpc/kernel/time.c

@@ -859,13 +859,8 @@ void update_vsyscall(struct timespec *wall_time, struct timespec *wtm,
 
 void update_vsyscall_tz(void)
 {
-	/* Make userspace gettimeofday spin until we're done. */
-	++vdso_data->tb_update_count;
-	smp_mb();
 	vdso_data->tz_minuteswest = sys_tz.tz_minuteswest;
 	vdso_data->tz_dsttime = sys_tz.tz_dsttime;
-	smp_mb();
-	++vdso_data->tb_update_count;
 }
 
 static void __init clocksource_init(void)

arch/powerpc/kernel/traps.c

@@ -935,8 +935,9 @@ static int emulate_instruction(struct pt_regs *regs)
 			cpu_has_feature(CPU_FTR_DSCR)) {
 		PPC_WARN_EMULATED(mtdscr, regs);
 		rd = (instword >> 21) & 0x1f;
-		mtspr(SPRN_DSCR, regs->gpr[rd]);
+		current->thread.dscr = regs->gpr[rd];
 		current->thread.dscr_inherit = 1;
+		mtspr(SPRN_DSCR, current->thread.dscr);
 		return 0;
 	}
 #endif

arch/powerpc/kvm/44x_emulate.c

@@ -79,6 +79,7 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 				run->dcr.dcrn = dcrn;
 				run->dcr.data =  0;
 				run->dcr.is_write = 0;
+				vcpu->arch.dcr_is_write = 0;
 				vcpu->arch.io_gpr = rt;
 				vcpu->arch.dcr_needed = 1;
 				kvmppc_account_exit(vcpu, DCR_EXITS);
@@ -100,6 +101,7 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 				run->dcr.dcrn = dcrn;
 				run->dcr.data = kvmppc_get_gpr(vcpu, rs);
 				run->dcr.is_write = 1;
+				vcpu->arch.dcr_is_write = 1;
 				vcpu->arch.dcr_needed = 1;
 				kvmppc_account_exit(vcpu, DCR_EXITS);
 				emulated = EMULATE_DO_DCR;

arch/powerpc/mm/numa.c

@@ -221,7 +221,7 @@ int __node_distance(int a, int b)
 	int distance = LOCAL_DISTANCE;
 
 	if (!form1_affinity)
-		return distance;
+		return ((a == b) ? LOCAL_DISTANCE : REMOTE_DISTANCE);
 
 	for (i = 0; i < distance_ref_points_depth; i++) {
 		if (distance_lookup_table[a][i] == distance_lookup_table[b][i])

arch/powerpc/platforms/cell/spufs/inode.c

@@ -100,6 +100,7 @@ spufs_new_inode(struct super_block *sb, int mode)
 	if (!inode)
 		goto out;
 
+	inode->i_ino = get_next_ino();
 	inode->i_mode = mode;
 	inode->i_uid = current_fsuid();
 	inode->i_gid = current_fsgid();

arch/powerpc/platforms/embedded6xx/wii.c

@@ -85,9 +85,11 @@ void __init wii_memory_fixups(void)
 	wii_hole_start = p[0].base + p[0].size;
 	wii_hole_size = p[1].base - wii_hole_start;
 
-	pr_info("MEM1: <%08llx %08llx>\n", p[0].base, p[0].size);
+	pr_info("MEM1: <%08llx %08llx>\n",
+		(unsigned long long) p[0].base, (unsigned long long) p[0].size);
 	pr_info("HOLE: <%08lx %08lx>\n", wii_hole_start, wii_hole_size);
-	pr_info("MEM2: <%08llx %08llx>\n", p[1].base, p[1].size);
+	pr_info("MEM2: <%08llx %08llx>\n",
+		(unsigned long long) p[1].base, (unsigned long long) p[1].size);
 
 	p[0].size += wii_hole_size + p[1].size;
 

arch/powerpc/platforms/pseries/lpar.c

@@ -377,7 +377,13 @@ static long pSeries_lpar_hpte_remove(unsigned long hpte_group)
 					   (0x1UL << 4), &dummy1, &dummy2);
 		if (lpar_rc == H_SUCCESS)
 			return i;
-		BUG_ON(lpar_rc != H_NOT_FOUND);
+
+		/*
+		 * The test for adjunct partition is performed before the
+		 * ANDCOND test.  H_RESOURCE may be returned, so we need to
+		 * check for that as well.
+		 */
+		BUG_ON(lpar_rc != H_NOT_FOUND && lpar_rc != H_RESOURCE);
 
 		slot_offset++;
 		slot_offset &= 0x7;

arch/s390/include/asm/pgtable.h

@@ -67,6 +67,10 @@ static inline int is_zero_pfn(unsigned long pfn)
 
 #define my_zero_pfn(addr)	page_to_pfn(ZERO_PAGE(addr))
 
+/* TODO: s390 cannot support io_remap_pfn_range... */
+#define io_remap_pfn_range(vma, vaddr, pfn, size, prot) 	       \
+	remap_pfn_range(vma, vaddr, pfn, size, prot)
+
 #endif /* !__ASSEMBLY__ */
 
 /*

arch/s390/include/asm/signal.h

@@ -131,6 +131,7 @@ struct sigaction {
         void (*sa_restorer)(void);
         sigset_t sa_mask;               /* mask last for extensibility */
 };
+#define __ARCH_HAS_SA_RESTORER
 
 struct k_sigaction {
         struct sigaction sa;

arch/s390/include/asm/timex.h

@@ -126,4 +126,32 @@ static inline unsigned long long get_clock_monotonic(void)
 	return get_clock_xt() - sched_clock_base_cc;
 }
 
+/**
+ * tod_to_ns - convert a TOD format value to nanoseconds
+ * @todval: to be converted TOD format value
+ * Returns: number of nanoseconds that correspond to the TOD format value
+ *
+ * Converting a 64 Bit TOD format value to nanoseconds means that the value
+ * must be divided by 4.096. In order to achieve that we multiply with 125
+ * and divide by 512:
+ *
+ *    ns = (todval * 125) >> 9;
+ *
+ * In order to avoid an overflow with the multiplication we can rewrite this.
+ * With a split todval == 2^32 * th + tl (th upper 32 bits, tl lower 32 bits)
+ * we end up with
+ *
+ *    ns = ((2^32 * th + tl) * 125 ) >> 9;
+ * -> ns = (2^23 * th * 125) + ((tl * 125) >> 9);
+ *
+ */
+static inline unsigned long long tod_to_ns(unsigned long long todval)
+{
+	unsigned long long ns;
+
+	ns = ((todval >> 32) << 23) * 125;
+	ns += ((todval & 0xffffffff) * 125) >> 9;
+	return ns;
+}
+
 #endif

arch/s390/include/asm/tlbflush.h

@@ -73,8 +73,6 @@ static inline void __tlb_flush_idte(unsigned long asce)
 
 static inline void __tlb_flush_mm(struct mm_struct * mm)
 {
-	if (unlikely(cpumask_empty(mm_cpumask(mm))))
-		return;
 	/*
 	 * If the machine has IDTE we prefer to do a per mm flush
 	 * on all cpus instead of doing a local flush if the mm

arch/s390/kernel/time.c

@@ -63,7 +63,7 @@ static DEFINE_PER_CPU(struct clock_event_device, comparators);
  */
 unsigned long long notrace __kprobes sched_clock(void)
 {
-	return (get_clock_monotonic() * 125) >> 9;
+	return tod_to_ns(get_clock_monotonic());
 }
 
 /*

arch/s390/kvm/interrupt.c

@@ -358,7 +358,7 @@ int kvm_s390_handle_wait(struct kvm_vcpu *vcpu)
 		return 0;
 	}
 
-	sltime = ((vcpu->arch.sie_block->ckc - now)*125)>>9;
+	sltime = tod_to_ns(vcpu->arch.sie_block->ckc - now);
 
 	hrtimer_start(&vcpu->arch.ckc_timer, ktime_set (0, sltime) , HRTIMER_MODE_REL);
 	VCPU_EVENT(vcpu, 5, "enabled wait via clock comparator: %llx ns", sltime);

arch/s390/kvm/kvm-s390.c

@@ -584,6 +584,14 @@ int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr)
 	} else
 		prefix = 0;
 
+	/*
+	 * The guest FPRS and ACRS are in the host FPRS/ACRS due to the lazy
+	 * copying in vcpu load/put. Lets update our copies before we save
+	 * it into the save area
+	 */
+	save_fp_regs(&vcpu->arch.guest_fpregs);
+	save_access_regs(vcpu->arch.guest_acrs);
+
 	if (__guestcopy(vcpu, addr + offsetof(struct save_area, fp_regs),
 			vcpu->arch.guest_fpregs.fprs, 128, prefix))
 		return -EFAULT;

arch/sh/include/asm/elf.h

@@ -202,9 +202,9 @@ extern void __kernel_vsyscall;
 	if (vdso_enabled)					\
 		NEW_AUX_ENT(AT_SYSINFO_EHDR, VDSO_BASE);	\
 	else							\
-		NEW_AUX_ENT(AT_IGNORE, 0);
+		NEW_AUX_ENT(AT_IGNORE, 0)
 #else
-#define VSYSCALL_AUX_ENT
+#define VSYSCALL_AUX_ENT	NEW_AUX_ENT(AT_IGNORE, 0)
 #endif /* CONFIG_VSYSCALL */
 
 #ifdef CONFIG_SH_FPU

arch/sparc/Kconfig

@@ -31,6 +31,7 @@ config SPARC
 
 config SPARC32
 	def_bool !64BIT
+	select GENERIC_ATOMIC64
 
 config SPARC64
 	def_bool 64BIT

arch/sparc/include/asm/atomic_32.h

@@ -15,6 +15,8 @@
 
 #ifdef __KERNEL__
 
+#include <asm-generic/atomic64.h>
+
 #include <asm/system.h>
 
 #define ATOMIC_INIT(i)  { (i) }

arch/sparc/include/asm/hugetlb.h

@@ -58,14 +58,20 @@ static inline pte_t huge_pte_wrprotect(pte_t pte)
 static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
 					   unsigned long addr, pte_t *ptep)
 {
-	ptep_set_wrprotect(mm, addr, ptep);
+	pte_t old_pte = *ptep;
+	set_huge_pte_at(mm, addr, ptep, pte_wrprotect(old_pte));
 }
 
 static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 					     unsigned long addr, pte_t *ptep,
 					     pte_t pte, int dirty)
 {
-	return ptep_set_access_flags(vma, addr, ptep, pte, dirty);
+	int changed = !pte_same(*ptep, pte);
+	if (changed) {
+		set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
+		flush_tlb_page(vma, addr);
+	}
+	return changed;
 }
 
 static inline pte_t huge_ptep_get(pte_t *ptep)

arch/sparc/include/asm/pgtable_64.h

@@ -774,6 +774,7 @@ static inline int io_remap_pfn_range(struct vm_area_struct *vma,
 	return remap_pfn_range(vma, from, phys_base >> PAGE_SHIFT, size, prot);
 }
 
+#include <asm/tlbflush.h>
 #include <asm-generic/pgtable.h>
 
 /* We provide our own get_unmapped_area to cope with VA holes and

arch/sparc/include/asm/signal.h

@@ -191,6 +191,7 @@ struct __old_sigaction {
 	unsigned long		sa_flags;
 	void			(*sa_restorer)(void);  /* not used by Linux/SPARC yet */
 };
+#define __ARCH_HAS_SA_RESTORER
 
 typedef struct sigaltstack {
 	void			__user *ss_sp;

arch/sparc/include/asm/system_64.h

@@ -140,8 +140,7 @@ do {						\
 	 * and 2 stores in this critical code path.  -DaveM
 	 */
 #define switch_to(prev, next, last)					\
-do {	flush_tlb_pending();						\
-	save_and_clear_fpu();						\
+do {	save_and_clear_fpu();						\
 	/* If you are tempted to conditionalize the following */	\
 	/* so that ASI is only written if it changes, think again. */	\
 	__asm__ __volatile__("wr %%g0, %0, %%asi"			\

arch/sparc/include/asm/tlbflush_64.h

@@ -11,24 +11,40 @@
 struct tlb_batch {
 	struct mm_struct *mm;
 	unsigned long tlb_nr;
+	unsigned long active;
 	unsigned long vaddrs[TLB_BATCH_NR];
 };
 
 extern void flush_tsb_kernel_range(unsigned long start, unsigned long end);
 extern void flush_tsb_user(struct tlb_batch *tb);
+extern void flush_tsb_user_page(struct mm_struct *mm, unsigned long vaddr);
 
 /* TLB flush operations. */
 
-extern void flush_tlb_pending(void);
+static inline void flush_tlb_mm(struct mm_struct *mm)
+{
+}
 
-#define flush_tlb_range(vma,start,end)	\
-	do { (void)(start); flush_tlb_pending(); } while (0)
-#define flush_tlb_page(vma,addr)	flush_tlb_pending()
-#define flush_tlb_mm(mm)		flush_tlb_pending()
+static inline void flush_tlb_page(struct vm_area_struct *vma,
+				  unsigned long vmaddr)
+{
+}
+
+static inline void flush_tlb_range(struct vm_area_struct *vma,
+				   unsigned long start, unsigned long end)
+{
+}
+
+#define __HAVE_ARCH_ENTER_LAZY_MMU_MODE
+
+extern void flush_tlb_pending(void);
+extern void arch_enter_lazy_mmu_mode(void);
+extern void arch_leave_lazy_mmu_mode(void);
+#define arch_flush_lazy_mmu_mode()      do {} while (0)
 
 /* Local cpu only.  */
 extern void __flush_tlb_all(void);
-
+extern void __flush_tlb_page(unsigned long context, unsigned long vaddr);
 extern void __flush_tlb_kernel_range(unsigned long start, unsigned long end);
 
 #ifndef CONFIG_SMP
@@ -38,15 +54,24 @@ do {	flush_tsb_kernel_range(start,end); \
 	__flush_tlb_kernel_range(start,end); \
 } while (0)
 
+static inline void global_flush_tlb_page(struct mm_struct *mm, unsigned long vaddr)
+{
+	__flush_tlb_page(CTX_HWBITS(mm->context), vaddr);
+}
+
 #else /* CONFIG_SMP */
 
 extern void smp_flush_tlb_kernel_range(unsigned long start, unsigned long end);
+extern void smp_flush_tlb_page(struct mm_struct *mm, unsigned long vaddr);
 
 #define flush_tlb_kernel_range(start, end) \
 do {	flush_tsb_kernel_range(start,end); \
 	smp_flush_tlb_kernel_range(start, end); \
 } while (0)
 
+#define global_flush_tlb_page(mm, vaddr) \
+	smp_flush_tlb_page(mm, vaddr)
+
 #endif /* ! CONFIG_SMP */
 
 #endif /* _SPARC64_TLBFLUSH_H */

arch/sparc/kernel/smp_64.c

@@ -856,7 +856,7 @@ void smp_tsb_sync(struct mm_struct *mm)
 }
 
 extern unsigned long xcall_flush_tlb_mm;
-extern unsigned long xcall_flush_tlb_pending;
+extern unsigned long xcall_flush_tlb_page;
 extern unsigned long xcall_flush_tlb_kernel_range;
 extern unsigned long xcall_fetch_glob_regs;
 extern unsigned long xcall_receive_signal;
@@ -1070,19 +1070,52 @@ local_flush_and_out:
 	put_cpu();
 }
 
+struct tlb_pending_info {
+	unsigned long ctx;
+	unsigned long nr;
+	unsigned long *vaddrs;
+};
+
+static void tlb_pending_func(void *info)
+{
+	struct tlb_pending_info *t = info;
+
+	__flush_tlb_pending(t->ctx, t->nr, t->vaddrs);
+}
+
 void smp_flush_tlb_pending(struct mm_struct *mm, unsigned long nr, unsigned long *vaddrs)
 {
 	u32 ctx = CTX_HWBITS(mm->context);
+	struct tlb_pending_info info;
+	int cpu = get_cpu();
+
+	info.ctx = ctx;
+	info.nr = nr;
+	info.vaddrs = vaddrs;
+
+	if (mm == current->mm && atomic_read(&mm->mm_users) == 1)
+		cpumask_copy(mm_cpumask(mm), cpumask_of(cpu));
+	else
+		smp_call_function_many(mm_cpumask(mm), tlb_pending_func,
+				       &info, 1);
+
+	__flush_tlb_pending(ctx, nr, vaddrs);
+
+	put_cpu();
+}
+
+void smp_flush_tlb_page(struct mm_struct *mm, unsigned long vaddr)
+{
+	unsigned long context = CTX_HWBITS(mm->context);
 	int cpu = get_cpu();
 
 	if (mm == current->mm && atomic_read(&mm->mm_users) == 1)
 		cpumask_copy(mm_cpumask(mm), cpumask_of(cpu));
 	else
-		smp_cross_call_masked(&xcall_flush_tlb_pending,
-				      ctx, nr, (unsigned long) vaddrs,
+		smp_cross_call_masked(&xcall_flush_tlb_page,
+				      context, vaddr, 0,
 				      mm_cpumask(mm));
-
-	__flush_tlb_pending(ctx, nr, vaddrs);
+	__flush_tlb_page(context, vaddr);
 
 	put_cpu();
 }

arch/sparc/mm/tlb.c

@@ -24,11 +24,17 @@ static DEFINE_PER_CPU(struct tlb_batch, tlb_batch);
 void flush_tlb_pending(void)
 {
 	struct tlb_batch *tb = &get_cpu_var(tlb_batch);
+	struct mm_struct *mm = tb->mm;
 
-	if (tb->tlb_nr) {
-		flush_tsb_user(tb);
+	if (!tb->tlb_nr)
+		goto out;
 
-		if (CTX_VALID(tb->mm->context)) {
+	flush_tsb_user(tb);
+
+	if (CTX_VALID(mm->context)) {
+		if (tb->tlb_nr == 1) {
+			global_flush_tlb_page(mm, tb->vaddrs[0]);
+		} else {
 #ifdef CONFIG_SMP
 			smp_flush_tlb_pending(tb->mm, tb->tlb_nr,
 					      &tb->vaddrs[0]);
@@ -37,12 +43,30 @@ void flush_tlb_pending(void)
 					    tb->tlb_nr, &tb->vaddrs[0]);
 #endif
 		}
-		tb->tlb_nr = 0;
 	}
 
+	tb->tlb_nr = 0;
+
+out:
 	put_cpu_var(tlb_batch);
 }
 
+void arch_enter_lazy_mmu_mode(void)
+{
+	struct tlb_batch *tb = &__get_cpu_var(tlb_batch);
+
+	tb->active = 1;
+}
+
+void arch_leave_lazy_mmu_mode(void)
+{
+	struct tlb_batch *tb = &__get_cpu_var(tlb_batch);
+
+	if (tb->tlb_nr)
+		flush_tlb_pending();
+	tb->active = 0;
+}
+
 void tlb_batch_add(struct mm_struct *mm, unsigned long vaddr,
 		   pte_t *ptep, pte_t orig, int fullmm)
 {
@@ -90,6 +114,12 @@ no_cache_flush:
 		nr = 0;
 	}
 
+	if (!tb->active) {
+		global_flush_tlb_page(mm, vaddr);
+		flush_tsb_user_page(mm, vaddr);
+		goto out;
+	}
+
 	if (nr == 0)
 		tb->mm = mm;
 
@@ -98,5 +128,6 @@ no_cache_flush:
 	if (nr >= TLB_BATCH_NR)
 		flush_tlb_pending();
 
+out:
 	put_cpu_var(tlb_batch);
 }

arch/sparc/mm/tsb.c

@@ -8,11 +8,10 @@
 #include <linux/slab.h>
 #include <asm/system.h>
 #include <asm/page.h>
-#include <asm/tlbflush.h>
-#include <asm/tlb.h>
-#include <asm/mmu_context.h>
 #include <asm/pgtable.h>
+#include <asm/mmu_context.h>
 #include <asm/tsb.h>
+#include <asm/tlb.h>
 #include <asm/oplib.h>
 
 extern struct tsb swapper_tsb[KERNEL_TSB_NENTRIES];
@@ -47,23 +46,27 @@ void flush_tsb_kernel_range(unsigned long start, unsigned long end)
 	}
 }
 
+static void __flush_tsb_one_entry(unsigned long tsb, unsigned long v,
+				  unsigned long hash_shift,
+				  unsigned long nentries)
+{
+	unsigned long tag, ent, hash;
+
+	v &= ~0x1UL;
+	hash = tsb_hash(v, hash_shift, nentries);
+	ent = tsb + (hash * sizeof(struct tsb));
+	tag = (v >> 22UL);
+
+	tsb_flush(ent, tag);
+}
+
 static void __flush_tsb_one(struct tlb_batch *tb, unsigned long hash_shift,
 			    unsigned long tsb, unsigned long nentries)
 {
 	unsigned long i;
 
-	for (i = 0; i < tb->tlb_nr; i++) {
-		unsigned long v = tb->vaddrs[i];
-		unsigned long tag, ent, hash;
-
-		v &= ~0x1UL;
-
-		hash = tsb_hash(v, hash_shift, nentries);
-		ent = tsb + (hash * sizeof(struct tsb));
-		tag = (v >> 22UL);
-
-		tsb_flush(ent, tag);
-	}
+	for (i = 0; i < tb->tlb_nr; i++)
+		__flush_tsb_one_entry(tsb, tb->vaddrs[i], hash_shift, nentries);
 }
 
 void flush_tsb_user(struct tlb_batch *tb)
@@ -91,6 +94,30 @@ void flush_tsb_user(struct tlb_batch *tb)
 	spin_unlock_irqrestore(&mm->context.lock, flags);
 }
 
+void flush_tsb_user_page(struct mm_struct *mm, unsigned long vaddr)
+{
+	unsigned long nentries, base, flags;
+
+	spin_lock_irqsave(&mm->context.lock, flags);
+
+	base = (unsigned long) mm->context.tsb_block[MM_TSB_BASE].tsb;
+	nentries = mm->context.tsb_block[MM_TSB_BASE].tsb_nentries;
+	if (tlb_type == cheetah_plus || tlb_type == hypervisor)
+		base = __pa(base);
+	__flush_tsb_one_entry(base, vaddr, PAGE_SHIFT, nentries);
+
+#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
+	if (mm->context.tsb_block[MM_TSB_HUGE].tsb) {
+		base = (unsigned long) mm->context.tsb_block[MM_TSB_HUGE].tsb;
+		nentries = mm->context.tsb_block[MM_TSB_HUGE].tsb_nentries;
+		if (tlb_type == cheetah_plus || tlb_type == hypervisor)
+			base = __pa(base);
+		__flush_tsb_one_entry(base, vaddr, HPAGE_SHIFT, nentries);
+	}
+#endif
+	spin_unlock_irqrestore(&mm->context.lock, flags);
+}
+
 #if defined(CONFIG_SPARC64_PAGE_SIZE_8KB)
 #define HV_PGSZ_IDX_BASE	HV_PGSZ_IDX_8K
 #define HV_PGSZ_MASK_BASE	HV_PGSZ_MASK_8K

arch/sparc/mm/ultra.S

@@ -52,6 +52,33 @@ __flush_tlb_mm:		/* 18 insns */
 	nop
 	nop
 
+	.align		32
+	.globl		__flush_tlb_page
+__flush_tlb_page:	/* 22 insns */
+	/* %o0 = context, %o1 = vaddr */
+	rdpr		%pstate, %g7
+	andn		%g7, PSTATE_IE, %g2
+	wrpr		%g2, %pstate
+	mov		SECONDARY_CONTEXT, %o4
+	ldxa		[%o4] ASI_DMMU, %g2
+	stxa		%o0, [%o4] ASI_DMMU
+	andcc		%o1, 1, %g0
+	andn		%o1, 1, %o3
+	be,pn		%icc, 1f
+	 or		%o3, 0x10, %o3
+	stxa		%g0, [%o3] ASI_IMMU_DEMAP
+1:	stxa		%g0, [%o3] ASI_DMMU_DEMAP
+	membar		#Sync
+	stxa		%g2, [%o4] ASI_DMMU
+	sethi		%hi(KERNBASE), %o4
+	flush		%o4
+	retl
+	 wrpr		%g7, 0x0, %pstate
+	nop
+	nop
+	nop
+	nop
+
 	.align		32
 	.globl		__flush_tlb_pending
 __flush_tlb_pending:	/* 26 insns */
@@ -203,6 +230,31 @@ __cheetah_flush_tlb_mm: /* 19 insns */
 	retl
 	 wrpr		%g7, 0x0, %pstate
 
+__cheetah_flush_tlb_page:	/* 22 insns */
+	/* %o0 = context, %o1 = vaddr */
+	rdpr		%pstate, %g7
+	andn		%g7, PSTATE_IE, %g2
+	wrpr		%g2, 0x0, %pstate
+	wrpr		%g0, 1, %tl
+	mov		PRIMARY_CONTEXT, %o4
+	ldxa		[%o4] ASI_DMMU, %g2
+	srlx		%g2, CTX_PGSZ1_NUC_SHIFT, %o3
+	sllx		%o3, CTX_PGSZ1_NUC_SHIFT, %o3
+	or		%o0, %o3, %o0	/* Preserve nucleus page size fields */
+	stxa		%o0, [%o4] ASI_DMMU
+	andcc		%o1, 1, %g0
+	be,pn		%icc, 1f
+	 andn		%o1, 1, %o3
+	stxa		%g0, [%o3] ASI_IMMU_DEMAP
+1:	stxa		%g0, [%o3] ASI_DMMU_DEMAP
+	membar		#Sync
+	stxa		%g2, [%o4] ASI_DMMU
+	sethi		%hi(KERNBASE), %o4
+	flush		%o4
+	wrpr		%g0, 0, %tl
+	retl
+	 wrpr		%g7, 0x0, %pstate
+
 __cheetah_flush_tlb_pending:	/* 27 insns */
 	/* %o0 = context, %o1 = nr, %o2 = vaddrs[] */
 	rdpr		%pstate, %g7
@@ -269,6 +321,20 @@ __hypervisor_flush_tlb_mm: /* 10 insns */
 	retl
 	 nop
 
+__hypervisor_flush_tlb_page: /* 11 insns */
+	/* %o0 = context, %o1 = vaddr */
+	mov		%o0, %g2
+	mov		%o1, %o0              /* ARG0: vaddr + IMMU-bit */
+	mov		%g2, %o1	      /* ARG1: mmu context */
+	mov		HV_MMU_ALL, %o2	      /* ARG2: flags */
+	srlx		%o0, PAGE_SHIFT, %o0
+	sllx		%o0, PAGE_SHIFT, %o0
+	ta		HV_MMU_UNMAP_ADDR_TRAP
+	brnz,pn		%o0, __hypervisor_tlb_tl0_error
+	 mov		HV_MMU_UNMAP_ADDR_TRAP, %o1
+	retl
+	 nop
+
 __hypervisor_flush_tlb_pending: /* 16 insns */
 	/* %o0 = context, %o1 = nr, %o2 = vaddrs[] */
 	sllx		%o1, 3, %g1
@@ -339,6 +405,13 @@ cheetah_patch_cachetlbops:
 	call		tlb_patch_one
 	 mov		19, %o2
 
+	sethi		%hi(__flush_tlb_page), %o0
+	or		%o0, %lo(__flush_tlb_page), %o0
+	sethi		%hi(__cheetah_flush_tlb_page), %o1
+	or		%o1, %lo(__cheetah_flush_tlb_page), %o1
+	call		tlb_patch_one
+	 mov		22, %o2
+
 	sethi		%hi(__flush_tlb_pending), %o0
 	or		%o0, %lo(__flush_tlb_pending), %o0
 	sethi		%hi(__cheetah_flush_tlb_pending), %o1
@@ -397,10 +470,9 @@ xcall_flush_tlb_mm:	/* 21 insns */
 	nop
 	nop
 
-	.globl		xcall_flush_tlb_pending
-xcall_flush_tlb_pending:	/* 21 insns */
-	/* %g5=context, %g1=nr, %g7=vaddrs[] */
-	sllx		%g1, 3, %g1
+	.globl		xcall_flush_tlb_page
+xcall_flush_tlb_page:	/* 17 insns */
+	/* %g5=context, %g1=vaddr */
 	mov		PRIMARY_CONTEXT, %g4
 	ldxa		[%g4] ASI_DMMU, %g2
 	srlx		%g2, CTX_PGSZ1_NUC_SHIFT, %g4
@@ -408,20 +480,16 @@ xcall_flush_tlb_pending:	/* 21 insns */
 	or		%g5, %g4, %g5
 	mov		PRIMARY_CONTEXT, %g4
 	stxa		%g5, [%g4] ASI_DMMU
-1:	sub		%g1, (1 << 3), %g1
-	ldx		[%g7 + %g1], %g5
-	andcc		%g5, 0x1, %g0
+	andcc		%g1, 0x1, %g0
 	be,pn		%icc, 2f
-
-	 andn		%g5, 0x1, %g5
+	 andn		%g1, 0x1, %g5
 	stxa		%g0, [%g5] ASI_IMMU_DEMAP
 2:	stxa		%g0, [%g5] ASI_DMMU_DEMAP
 	membar		#Sync
-	brnz,pt		%g1, 1b
-	 nop
 	stxa		%g2, [%g4] ASI_DMMU
 	retry
 	nop
+	nop
 
 	.globl		xcall_flush_tlb_kernel_range
 xcall_flush_tlb_kernel_range:	/* 25 insns */
@@ -596,15 +664,13 @@ __hypervisor_xcall_flush_tlb_mm: /* 21 insns */
 	membar		#Sync
 	retry
 
-	.globl		__hypervisor_xcall_flush_tlb_pending
-__hypervisor_xcall_flush_tlb_pending: /* 21 insns */
-	/* %g5=ctx, %g1=nr, %g7=vaddrs[], %g2,%g3,%g4,g6=scratch */
-	sllx		%g1, 3, %g1
+	.globl		__hypervisor_xcall_flush_tlb_page
+__hypervisor_xcall_flush_tlb_page: /* 17 insns */
+	/* %g5=ctx, %g1=vaddr */
 	mov		%o0, %g2
 	mov		%o1, %g3
 	mov		%o2, %g4
-1:	sub		%g1, (1 << 3), %g1
-	ldx		[%g7 + %g1], %o0	/* ARG0: virtual address */
+	mov		%g1, %o0	        /* ARG0: virtual address */
 	mov		%g5, %o1		/* ARG1: mmu context */
 	mov		HV_MMU_ALL, %o2		/* ARG2: flags */
 	srlx		%o0, PAGE_SHIFT, %o0
@@ -613,8 +679,6 @@ __hypervisor_xcall_flush_tlb_pending: /* 21 insns */
 	mov		HV_MMU_UNMAP_ADDR_TRAP, %g6
 	brnz,a,pn	%o0, __hypervisor_tlb_xcall_error
 	 mov		%o0, %g5
-	brnz,pt		%g1, 1b
-	 nop
 	mov		%g2, %o0
 	mov		%g3, %o1
 	mov		%g4, %o2
@@ -697,6 +761,13 @@ hypervisor_patch_cachetlbops:
 	call		tlb_patch_one
 	 mov		10, %o2
 
+	sethi		%hi(__flush_tlb_page), %o0
+	or		%o0, %lo(__flush_tlb_page), %o0
+	sethi		%hi(__hypervisor_flush_tlb_page), %o1
+	or		%o1, %lo(__hypervisor_flush_tlb_page), %o1
+	call		tlb_patch_one
+	 mov		11, %o2
+
 	sethi		%hi(__flush_tlb_pending), %o0
 	or		%o0, %lo(__flush_tlb_pending), %o0
 	sethi		%hi(__hypervisor_flush_tlb_pending), %o1
@@ -728,12 +799,12 @@ hypervisor_patch_cachetlbops:
 	call		tlb_patch_one
 	 mov		21, %o2
 
-	sethi		%hi(xcall_flush_tlb_pending), %o0
-	or		%o0, %lo(xcall_flush_tlb_pending), %o0
-	sethi		%hi(__hypervisor_xcall_flush_tlb_pending), %o1
-	or		%o1, %lo(__hypervisor_xcall_flush_tlb_pending), %o1
+	sethi		%hi(xcall_flush_tlb_page), %o0
+	or		%o0, %lo(xcall_flush_tlb_page), %o0
+	sethi		%hi(__hypervisor_xcall_flush_tlb_page), %o1
+	or		%o1, %lo(__hypervisor_xcall_flush_tlb_page), %o1
 	call		tlb_patch_one
-	 mov		21, %o2
+	 mov		17, %o2
 
 	sethi		%hi(xcall_flush_tlb_kernel_range), %o0
 	or		%o0, %lo(xcall_flush_tlb_kernel_range), %o0

arch/x86/Kconfig

@@ -1219,10 +1219,6 @@ config HAVE_ARCH_BOOTMEM
 	def_bool y
 	depends on X86_32 && NUMA
 
-config HAVE_ARCH_ALLOC_REMAP
-	def_bool y
-	depends on X86_32 && NUMA
-
 config ARCH_HAVE_MEMORY_PRESENT
 	def_bool y
 	depends on X86_32 && DISCONTIGMEM

arch/x86/ia32/ia32entry.S

@@ -208,7 +208,7 @@ sysexit_from_sys_call:
 	testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT),TI_flags(%r10)
 	jnz ia32_ret_from_sys_call
 	TRACE_IRQS_ON
-	sti
+	ENABLE_INTERRUPTS(CLBR_NONE)
 	movl %eax,%esi		/* second arg, syscall return value */
 	cmpl $0,%eax		/* is it < 0? */
 	setl %al		/* 1 if so, 0 if not */
@@ -218,7 +218,7 @@ sysexit_from_sys_call:
 	GET_THREAD_INFO(%r10)
 	movl RAX-ARGOFFSET(%rsp),%eax	/* reload syscall return value */
 	movl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT),%edi
-	cli
+	DISABLE_INTERRUPTS(CLBR_NONE)
 	TRACE_IRQS_OFF
 	testl %edi,TI_flags(%r10)
 	jz \exit

arch/x86/include/asm/kvm_host.h

@@ -391,8 +391,8 @@ struct kvm_vcpu_arch {
 	gpa_t time;
 	struct pvclock_vcpu_time_info hv_clock;
 	unsigned int hw_tsc_khz;
-	unsigned int time_offset;
-	struct page *time_page;
+	struct gfn_to_hva_cache pv_time;
+	bool pv_time_enabled;
 	u64 last_guest_tsc;
 	u64 last_kernel_ns;
 	u64 last_tsc_nsec;

arch/x86/include/asm/mmzone_32.h

@@ -14,12 +14,6 @@ extern struct pglist_data *node_data[];
 
 #include <asm/numaq.h>
 
-extern void resume_map_numa_kva(pgd_t *pgd);
-
-#else /* !CONFIG_NUMA */
-
-static inline void resume_map_numa_kva(pgd_t *pgd) {}
-
 #endif /* CONFIG_NUMA */
 
 #ifdef CONFIG_DISCONTIGMEM

arch/x86/include/asm/paravirt.h

@@ -731,7 +731,10 @@ static inline void arch_leave_lazy_mmu_mode(void)
 	PVOP_VCALL0(pv_mmu_ops.lazy_mode.leave);
 }
 
-void arch_flush_lazy_mmu_mode(void);
+static inline void arch_flush_lazy_mmu_mode(void)
+{
+	PVOP_VCALL0(pv_mmu_ops.lazy_mode.flush);
+}
 
 static inline void __set_fixmap(unsigned /* enum fixed_addresses */ idx,
 				phys_addr_t phys, pgprot_t flags)

arch/x86/include/asm/paravirt_types.h

@@ -85,6 +85,7 @@ struct pv_lazy_ops {
 	/* Set deferred update mode, used for batching operations. */
 	void (*enter)(void);
 	void (*leave)(void);
+	void (*flush)(void);
 };
 
 struct pv_time_ops {
@@ -673,6 +674,7 @@ void paravirt_end_context_switch(struct task_struct *next);
 
 void paravirt_enter_lazy_mmu(void);
 void paravirt_leave_lazy_mmu(void);
+void paravirt_flush_lazy_mmu(void);
 
 void _paravirt_nop(void);
 u32 _paravirt_ident_32(u32);

arch/x86/include/asm/pgtable.h

@@ -142,6 +142,11 @@ static inline unsigned long pmd_pfn(pmd_t pmd)
 	return (pmd_val(pmd) & PTE_PFN_MASK) >> PAGE_SHIFT;
 }
 
+static inline unsigned long pud_pfn(pud_t pud)
+{
+	return (pud_val(pud) & PTE_PFN_MASK) >> PAGE_SHIFT;
+}
+
 #define pte_page(pte)	pfn_to_page(pte_pfn(pte))
 
 static inline int pmd_large(pmd_t pte)

arch/x86/include/asm/signal.h

@@ -125,6 +125,8 @@ typedef unsigned long sigset_t;
 extern void do_notify_resume(struct pt_regs *, void *, __u32);
 # endif /* __KERNEL__ */
 
+#define __ARCH_HAS_SA_RESTORER
+
 #ifdef __i386__
 # ifdef __KERNEL__
 struct old_sigaction {

arch/x86/include/asm/traps.h

@@ -1,6 +1,7 @@
 #ifndef _ASM_X86_TRAPS_H
 #define _ASM_X86_TRAPS_H
 
+#include <linux/kprobes.h>
 #include <asm/debugreg.h>
 #include <asm/siginfo.h>			/* TRAP_TRACE, ... */
 
@@ -87,4 +88,29 @@ asmlinkage void smp_thermal_interrupt(void);
 asmlinkage void mce_threshold_interrupt(void);
 #endif
 
+/* Interrupts/Exceptions */
+enum {
+	X86_TRAP_DE = 0,	/*  0, Divide-by-zero */
+	X86_TRAP_DB,		/*  1, Debug */
+	X86_TRAP_NMI,		/*  2, Non-maskable Interrupt */
+	X86_TRAP_BP,		/*  3, Breakpoint */
+	X86_TRAP_OF,		/*  4, Overflow */
+	X86_TRAP_BR,		/*  5, Bound Range Exceeded */
+	X86_TRAP_UD,		/*  6, Invalid Opcode */
+	X86_TRAP_NM,		/*  7, Device Not Available */
+	X86_TRAP_DF,		/*  8, Double Fault */
+	X86_TRAP_OLD_MF,	/*  9, Coprocessor Segment Overrun */
+	X86_TRAP_TS,		/* 10, Invalid TSS */
+	X86_TRAP_NP,		/* 11, Segment Not Present */
+	X86_TRAP_SS,		/* 12, Stack Segment Fault */
+	X86_TRAP_GP,		/* 13, General Protection Fault */
+	X86_TRAP_PF,		/* 14, Page Fault */
+	X86_TRAP_SPURIOUS,	/* 15, Spurious Interrupt */
+	X86_TRAP_MF,		/* 16, x87 Floating-Point Exception */
+	X86_TRAP_AC,		/* 17, Alignment Check */
+	X86_TRAP_MC,		/* 18, Machine Check */
+	X86_TRAP_XF,		/* 19, SIMD Floating-Point Exception */
+	X86_TRAP_IRET = 32,	/* 32, IRET Exception */
+};
+
 #endif /* _ASM_X86_TRAPS_H */

arch/x86/kernel/amd_iommu.c

@@ -53,6 +53,8 @@ static struct protection_domain *pt_domain;
 
 static struct iommu_ops amd_iommu_ops;
 
+static struct dma_map_ops amd_iommu_dma_ops;
+
 /*
  * general struct to manage commands send to an IOMMU
  */
@@ -1778,18 +1780,20 @@ static int device_change_notifier(struct notifier_block *nb,
 
 		domain = domain_for_device(dev);
 
-		/* allocate a protection domain if a device is added */
 		dma_domain = find_protection_domain(devid);
-		if (dma_domain)
-			goto out;
-		dma_domain = dma_ops_domain_alloc();
-		if (!dma_domain)
-			goto out;
-		dma_domain->target_dev = devid;
+		if (!dma_domain) {
+			/* allocate a protection domain if a device is added */
+			dma_domain = dma_ops_domain_alloc();
+			if (!dma_domain)
+				goto out;
+			dma_domain->target_dev = devid;
 
-		spin_lock_irqsave(&iommu_pd_list_lock, flags);
-		list_add_tail(&dma_domain->list, &iommu_pd_list);
-		spin_unlock_irqrestore(&iommu_pd_list_lock, flags);
+			spin_lock_irqsave(&iommu_pd_list_lock, flags);
+			list_add_tail(&dma_domain->list, &iommu_pd_list);
+			spin_unlock_irqrestore(&iommu_pd_list_lock, flags);
+		}
+
+		dev->archdata.dma_ops = &amd_iommu_dma_ops;
 
 		break;
 	case BUS_NOTIFY_DEL_DEVICE:

arch/x86/kernel/amd_iommu_init.c

@@ -1363,6 +1363,7 @@ static struct syscore_ops amd_iommu_syscore_ops = {
  */
 static int __init amd_iommu_init(void)
 {
+	struct amd_iommu *iommu;
 	int i, ret = 0;
 
 	/*
@@ -1411,9 +1412,6 @@ static int __init amd_iommu_init(void)
 	if (amd_iommu_pd_alloc_bitmap == NULL)
 		goto free;
 
-	/* init the device table */
-	init_device_table();
-
 	/*
 	 * let all alias entries point to itself
 	 */
@@ -1463,6 +1461,12 @@ static int __init amd_iommu_init(void)
 	if (ret)
 		goto free_disable;
 
+	/* init the device table */
+	init_device_table();
+
+	for_each_iommu(iommu)
+		iommu_flush_all_caches(iommu);
+
 	amd_iommu_init_api();
 
 	amd_iommu_init_notifier();

arch/x86/kernel/apic/x2apic_phys.c

@@ -20,12 +20,19 @@ static int set_x2apic_phys_mode(char *arg)
 }
 early_param("x2apic_phys", set_x2apic_phys_mode);
 
+static bool x2apic_fadt_phys(void)
+{
+	if ((acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID) &&
+		(acpi_gbl_FADT.flags & ACPI_FADT_APIC_PHYSICAL)) {
+		printk(KERN_DEBUG "System requires x2apic physical mode\n");
+		return true;
+	}
+	return false;
+}
+
 static int x2apic_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
 {
-	if (x2apic_phys)
-		return x2apic_enabled();
-	else
-		return 0;
+	return x2apic_enabled() && (x2apic_phys || x2apic_fadt_phys());
 }
 
 static void
@@ -108,7 +115,7 @@ static void init_x2apic_ldr(void)
 
 static int x2apic_phys_probe(void)
 {
-	if (x2apic_mode && x2apic_phys)
+	if (x2apic_mode && (x2apic_phys || x2apic_fadt_phys()))
 		return 1;
 
 	return apic == &apic_x2apic_phys;

arch/x86/kernel/cpu/amd.c

@@ -554,6 +554,20 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
 		}
 	}
 
+	/*
+	 * The way access filter has a performance penalty on some workloads.
+	 * Disable it on the affected CPUs.
+	 */
+	if ((c->x86 == 0x15) &&
+	    (c->x86_model >= 0x02) && (c->x86_model < 0x20)) {
+		u64 val;
+
+		if (!rdmsrl_safe(0xc0011021, &val) && !(val & 0x1E)) {
+			val |= 0x1E;
+			checking_wrmsrl(0xc0011021, val);
+		}
+	}
+
 	cpu_detect_cache_sizes(c);
 
 	/* Multi core CPU? */

arch/x86/kernel/cpu/perf_event_intel_ds.c

@@ -754,6 +754,16 @@ static void intel_ds_init(void)
 	}
 }
 
+void perf_restore_debug_store(void)
+{
+	struct debug_store *ds = __this_cpu_read(cpu_hw_events.ds);
+
+	if (!x86_pmu.bts && !x86_pmu.pebs)
+		return;
+
+	wrmsrl(MSR_IA32_DS_AREA, (unsigned long)ds);
+}
+
 #else /* CONFIG_CPU_SUP_INTEL */
 
 static void reserve_ds_buffers(void)

arch/x86/kernel/entry_32.S

@@ -1078,7 +1078,6 @@ ENTRY(xen_failsafe_callback)
 	lea 16(%esp),%esp
 	CFI_ADJUST_CFA_OFFSET -16
 	jz 5f
-	addl $16,%esp
 	jmp iret_exc
 5:	pushl_cfi $-1 /* orig_ax = -1 => not a system call */
 	SAVE_ALL

arch/x86/kernel/head.c

@@ -5,8 +5,6 @@
 #include <asm/setup.h>
 #include <asm/bios_ebda.h>
 
-#define BIOS_LOWMEM_KILOBYTES 0x413
-
 /*
  * The BIOS places the EBDA/XBDA at the top of conventional
  * memory, and usually decreases the reported amount of
@@ -16,17 +14,30 @@
  * chipset: reserve a page before VGA to prevent PCI prefetch
  * into it (errata #56). Usually the page is reserved anyways,
  * unless you have no PS/2 mouse plugged in.
+ *
+ * This functions is deliberately very conservative.  Losing
+ * memory in the bottom megabyte is rarely a problem, as long
+ * as we have enough memory to install the trampoline.  Using
+ * memory that is in use by the BIOS or by some DMA device
+ * the BIOS didn't shut down *is* a big problem.
  */
+
+#define BIOS_LOWMEM_KILOBYTES	0x413
+#define LOWMEM_CAP		0x9f000U	/* Absolute maximum */
+#define INSANE_CUTOFF		0x20000U	/* Less than this = insane */
+
 void __init reserve_ebda_region(void)
 {
 	unsigned int lowmem, ebda_addr;
 
-	/* To determine the position of the EBDA and the */
-	/* end of conventional memory, we need to look at */
-	/* the BIOS data area. In a paravirtual environment */
-	/* that area is absent. We'll just have to assume */
-	/* that the paravirt case can handle memory setup */
-	/* correctly, without our help. */
+	/*
+	 * To determine the position of the EBDA and the
+	 * end of conventional memory, we need to look at
+	 * the BIOS data area. In a paravirtual environment
+	 * that area is absent. We'll just have to assume
+	 * that the paravirt case can handle memory setup
+	 * correctly, without our help.
+	 */
 	if (paravirt_enabled())
 		return;
 
@@ -37,19 +48,23 @@ void __init reserve_ebda_region(void)
 	/* start of EBDA area */
 	ebda_addr = get_bios_ebda();
 
-	/* Fixup: bios puts an EBDA in the top 64K segment */
-	/* of conventional memory, but does not adjust lowmem. */
-	if ((lowmem - ebda_addr) <= 0x10000)
-		lowmem = ebda_addr;
+	/*
+	 * Note: some old Dells seem to need 4k EBDA without
+	 * reporting so, so just consider the memory above 0x9f000
+	 * to be off limits (bugzilla 2990).
+	 */
 
-	/* Fixup: bios does not report an EBDA at all. */
-	/* Some old Dells seem to need 4k anyhow (bugzilla 2990) */
-	if ((ebda_addr == 0) && (lowmem >= 0x9f000))
-		lowmem = 0x9f000;
+	/* If the EBDA address is below 128K, assume it is bogus */
+	if (ebda_addr < INSANE_CUTOFF)
+		ebda_addr = LOWMEM_CAP;
 
-	/* Paranoia: should never happen, but... */
-	if ((lowmem == 0) || (lowmem >= 0x100000))
-		lowmem = 0x9f000;
+	/* If lowmem is less than 128K, assume it is bogus */
+	if (lowmem < INSANE_CUTOFF)
+		lowmem = LOWMEM_CAP;
+
+	/* Use the lower of the lowmem and EBDA markers as the cutoff */
+	lowmem = min(lowmem, ebda_addr);
+	lowmem = min(lowmem, LOWMEM_CAP); /* Absolute cap */
 
 	/* reserve all memory between lowmem and the 1MB mark */
 	memblock_x86_reserve_range(lowmem, 0x100000, "* BIOS reserved");

arch/x86/kernel/hpet.c

@@ -427,7 +427,7 @@ void hpet_msi_unmask(struct irq_data *data)
 
 	/* unmask it */
 	cfg = hpet_readl(HPET_Tn_CFG(hdev->num));
-	cfg |= HPET_TN_FSB;
+	cfg |= HPET_TN_ENABLE | HPET_TN_FSB;
 	hpet_writel(cfg, HPET_Tn_CFG(hdev->num));
 }
 
@@ -438,7 +438,7 @@ void hpet_msi_mask(struct irq_data *data)
 
 	/* mask it */
 	cfg = hpet_readl(HPET_Tn_CFG(hdev->num));
-	cfg &= ~HPET_TN_FSB;
+	cfg &= ~(HPET_TN_ENABLE | HPET_TN_FSB);
 	hpet_writel(cfg, HPET_Tn_CFG(hdev->num));
 }
 

arch/x86/kernel/irq.c

@@ -159,10 +159,6 @@ u64 arch_irq_stat_cpu(unsigned int cpu)
 u64 arch_irq_stat(void)
 {
 	u64 sum = atomic_read(&irq_err_count);
-
-#ifdef CONFIG_X86_IO_APIC
-	sum += atomic_read(&irq_mis_count);
-#endif
 	return sum;
 }
 

arch/x86/kernel/msr.c

@@ -175,6 +175,9 @@ static int msr_open(struct inode *inode, struct file *file)
 	unsigned int cpu;
 	struct cpuinfo_x86 *c;
 
+	if (!capable(CAP_SYS_RAWIO))
+		return -EPERM;
+
 	cpu = iminor(file->f_path.dentry->d_inode);
 	if (cpu >= nr_cpu_ids || !cpu_online(cpu))
 		return -ENXIO;	/* No such CPU */

arch/x86/kernel/paravirt.c

@@ -253,6 +253,18 @@ void paravirt_leave_lazy_mmu(void)
 	leave_lazy(PARAVIRT_LAZY_MMU);
 }
 
+void paravirt_flush_lazy_mmu(void)
+{
+	preempt_disable();
+
+	if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU) {
+		arch_leave_lazy_mmu_mode();
+		arch_enter_lazy_mmu_mode();
+	}
+
+	preempt_enable();
+}
+
 void paravirt_start_context_switch(struct task_struct *prev)
 {
 	BUG_ON(preemptible());
@@ -282,18 +294,6 @@ enum paravirt_lazy_mode paravirt_get_lazy_mode(void)
 	return percpu_read(paravirt_lazy_mode);
 }
 
-void arch_flush_lazy_mmu_mode(void)
-{
-	preempt_disable();
-
-	if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU) {
-		arch_leave_lazy_mmu_mode();
-		arch_enter_lazy_mmu_mode();
-	}
-
-	preempt_enable();
-}
-
 struct pv_info pv_info = {
 	.name = "bare hardware",
 	.paravirt_enabled = 0,
@@ -462,6 +462,7 @@ struct pv_mmu_ops pv_mmu_ops = {
 	.lazy_mode = {
 		.enter = paravirt_nop,
 		.leave = paravirt_nop,
+		.flush = paravirt_nop,
 	},
 
 	.set_fixmap = native_set_fixmap,

arch/x86/kernel/setup.c

@@ -631,6 +631,83 @@ static __init void reserve_ibft_region(void)
 
 static unsigned reserve_low = CONFIG_X86_RESERVE_LOW << 10;
 
+static bool __init snb_gfx_workaround_needed(void)
+{
+#ifdef CONFIG_PCI
+	int i;
+	u16 vendor, devid;
+	static const u16 snb_ids[] = {
+		0x0102,
+		0x0112,
+		0x0122,
+		0x0106,
+		0x0116,
+		0x0126,
+		0x010a,
+	};
+
+	/* Assume no if something weird is going on with PCI */
+	if (!early_pci_allowed())
+		return false;
+
+	vendor = read_pci_config_16(0, 2, 0, PCI_VENDOR_ID);
+	if (vendor != 0x8086)
+		return false;
+
+	devid = read_pci_config_16(0, 2, 0, PCI_DEVICE_ID);
+	for (i = 0; i < ARRAY_SIZE(snb_ids); i++)
+		if (devid == snb_ids[i])
+			return true;
+#endif
+
+	return false;
+}
+
+/*
+ * Sandy Bridge graphics has trouble with certain ranges, exclude
+ * them from allocation.
+ */
+static void __init trim_snb_memory(void)
+{
+	static const unsigned long bad_pages[] = {
+		0x20050000,
+		0x20110000,
+		0x20130000,
+		0x20138000,
+		0x40004000,
+	};
+	int i;
+
+	if (!snb_gfx_workaround_needed())
+		return;
+
+	printk(KERN_DEBUG "reserving inaccessible SNB gfx pages\n");
+
+	/*
+	 * Reserve all memory below the 1 MB mark that has not
+	 * already been reserved.
+	 */
+	memblock_reserve(0, 1<<20);
+
+	for (i = 0; i < ARRAY_SIZE(bad_pages); i++) {
+		if (memblock_reserve(bad_pages[i], PAGE_SIZE))
+			printk(KERN_WARNING "failed to reserve 0x%08lx\n",
+			       bad_pages[i]);
+	}
+}
+
+/*
+ * Here we put platform-specific memory range workarounds, i.e.
+ * memory known to be corrupt or otherwise in need to be reserved on
+ * specific platforms.
+ *
+ * If this gets used more widely it could use a real dispatch mechanism.
+ */
+static void __init trim_platform_memory_ranges(void)
+{
+	trim_snb_memory();
+}
+
 static void __init trim_bios_range(void)
 {
 	/*
@@ -651,6 +728,7 @@ static void __init trim_bios_range(void)
 	 * take them out.
 	 */
 	e820_remove_range(BIOS_BEGIN, BIOS_END - BIOS_BEGIN, E820_RAM, 1);
+
 	sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
 }
 
@@ -929,6 +1007,8 @@ void __init setup_arch(char **cmdline_p)
 
 	setup_trampolines();
 
+	trim_platform_memory_ranges();
+
 	init_gbpages();
 
 	/* max_pfn_mapped is updated here */

arch/x86/kvm/i8254.c

@@ -338,11 +338,15 @@ static enum hrtimer_restart pit_timer_fn(struct hrtimer *data)
 		return HRTIMER_NORESTART;
 }
 
-static void create_pit_timer(struct kvm_kpit_state *ps, u32 val, int is_period)
+static void create_pit_timer(struct kvm *kvm, u32 val, int is_period)
 {
+	struct kvm_kpit_state *ps = &kvm->arch.vpit->pit_state;
 	struct kvm_timer *pt = &ps->pit_timer;
 	s64 interval;
 
+	if (!irqchip_in_kernel(kvm))
+		return;
+
 	interval = muldiv64(val, NSEC_PER_SEC, KVM_PIT_FREQ);
 
 	pr_debug("create pit timer, interval is %llu nsec\n", interval);
@@ -394,13 +398,13 @@ static void pit_load_count(struct kvm *kvm, int channel, u32 val)
         /* FIXME: enhance mode 4 precision */
 	case 4:
 		if (!(ps->flags & KVM_PIT_FLAGS_HPET_LEGACY)) {
-			create_pit_timer(ps, val, 0);
+			create_pit_timer(kvm, val, 0);
 		}
 		break;
 	case 2:
 	case 3:
 		if (!(ps->flags & KVM_PIT_FLAGS_HPET_LEGACY)){
-			create_pit_timer(ps, val, 1);
+			create_pit_timer(kvm, val, 1);
 		}
 		break;
 	default:

arch/x86/kvm/vmx.c

@@ -3836,6 +3836,12 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu)
 		if (err != EMULATE_DONE)
 			return 0;
 
+		if (vcpu->arch.halt_request) {
+			vcpu->arch.halt_request = 0;
+			ret = kvm_emulate_halt(vcpu);
+			goto out;
+		}
+
 		if (signal_pending(current))
 			goto out;
 		if (need_resched())

arch/x86/kvm/x86.c

@@ -575,6 +575,9 @@ static bool guest_cpuid_has_xsave(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpuid_entry2 *best;
 
+	if (!cpu_has_xsave)
+		return 0;
+
 	best = kvm_find_cpuid_entry(vcpu, 1, 0);
 	return best && (best->ecx & bit(X86_FEATURE_XSAVE));
 }
@@ -1070,7 +1073,6 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 {
 	unsigned long flags;
 	struct kvm_vcpu_arch *vcpu = &v->arch;
-	void *shared_kaddr;
 	unsigned long this_tsc_khz;
 	s64 kernel_ns, max_kernel_ns;
 	u64 tsc_timestamp;
@@ -1106,7 +1108,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 
 	local_irq_restore(flags);
 
-	if (!vcpu->time_page)
+	if (!vcpu->pv_time_enabled)
 		return 0;
 
 	/*
@@ -1164,14 +1166,9 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 	 */
 	vcpu->hv_clock.version += 2;
 
-	shared_kaddr = kmap_atomic(vcpu->time_page, KM_USER0);
-
-	memcpy(shared_kaddr + vcpu->time_offset, &vcpu->hv_clock,
-	       sizeof(vcpu->hv_clock));
-
-	kunmap_atomic(shared_kaddr, KM_USER0);
-
-	mark_page_dirty(v->kvm, vcpu->time >> PAGE_SHIFT);
+	kvm_write_guest_cached(v->kvm, &vcpu->pv_time,
+				&vcpu->hv_clock,
+				sizeof(vcpu->hv_clock));
 	return 0;
 }
 
@@ -1451,7 +1448,8 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data)
 		return 0;
 	}
 
-	if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.apf.data, gpa))
+	if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.apf.data, gpa,
+					sizeof(u32)))
 		return 1;
 
 	vcpu->arch.apf.send_user_only = !(data & KVM_ASYNC_PF_SEND_ALWAYS);
@@ -1461,10 +1459,7 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data)
 
 static void kvmclock_reset(struct kvm_vcpu *vcpu)
 {
-	if (vcpu->arch.time_page) {
-		kvm_release_page_dirty(vcpu->arch.time_page);
-		vcpu->arch.time_page = NULL;
-	}
+	vcpu->arch.pv_time_enabled = false;
 }
 
 int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
@@ -1524,6 +1519,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 		break;
 	case MSR_KVM_SYSTEM_TIME_NEW:
 	case MSR_KVM_SYSTEM_TIME: {
+		u64 gpa_offset;
 		kvmclock_reset(vcpu);
 
 		vcpu->arch.time = data;
@@ -1533,16 +1529,14 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 		if (!(data & 1))
 			break;
 
-		/* ...but clean it before doing the actual write */
-		vcpu->arch.time_offset = data & ~(PAGE_MASK | 1);
+		gpa_offset = data & ~(PAGE_MASK | 1);
 
-		vcpu->arch.time_page =
-				gfn_to_page(vcpu->kvm, data >> PAGE_SHIFT);
-
-		if (is_error_page(vcpu->arch.time_page)) {
-			kvm_release_page_clean(vcpu->arch.time_page);
-			vcpu->arch.time_page = NULL;
-		}
+		if (kvm_gfn_to_hva_cache_init(vcpu->kvm,
+		     &vcpu->arch.pv_time, data & ~1ULL,
+		     sizeof(struct pvclock_vcpu_time_info)))
+			vcpu->arch.pv_time_enabled = false;
+		else
+			vcpu->arch.pv_time_enabled = true;
 		break;
 	}
 	case MSR_KVM_ASYNC_PF_EN:
@@ -3410,6 +3404,9 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		r = -EEXIST;
 		if (kvm->arch.vpic)
 			goto create_irqchip_unlock;
+		r = -EINVAL;
+		if (atomic_read(&kvm->online_vcpus))
+			goto create_irqchip_unlock;
 		r = -ENOMEM;
 		vpic = kvm_create_pic(kvm);
 		if (vpic) {
@@ -5851,6 +5848,9 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 	int pending_vec, max_bits, idx;
 	struct desc_ptr dt;
 
+	if (!guest_cpuid_has_xsave(vcpu) && (sregs->cr4 & X86_CR4_OSXSAVE))
+		return -EINVAL;
+
 	dt.size = sregs->idt.limit;
 	dt.address = sregs->idt.base;
 	kvm_x86_ops->set_idt(vcpu, &dt);
@@ -6116,12 +6116,7 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 	if (r == 0)
 		r = kvm_mmu_setup(vcpu);
 	vcpu_put(vcpu);
-	if (r < 0)
-		goto free_vcpu;
 
-	return 0;
-free_vcpu:
-	kvm_x86_ops->vcpu_free(vcpu);
 	return r;
 }
 
@@ -6194,6 +6189,11 @@ void kvm_arch_check_processor_compat(void *rtn)
 	kvm_x86_ops->check_processor_compatibility(rtn);
 }
 
+bool kvm_vcpu_compatible(struct kvm_vcpu *vcpu)
+{
+	return irqchip_in_kernel(vcpu->kvm) == (vcpu->arch.apic != NULL);
+}
+
 int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 {
 	struct page *page;
@@ -6243,6 +6243,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 	if (!zalloc_cpumask_var(&vcpu->arch.wbinvd_dirty_mask, GFP_KERNEL))
 		goto fail_free_mce_banks;
 
+	vcpu->arch.pv_time_enabled = false;
 	kvm_async_pf_hash_reset(vcpu);
 
 	return 0;

arch/x86/lguest/boot.c

@@ -1309,6 +1309,7 @@ __init void lguest_init(void)
 	pv_mmu_ops.read_cr3 = lguest_read_cr3;
 	pv_mmu_ops.lazy_mode.enter = paravirt_enter_lazy_mmu;
 	pv_mmu_ops.lazy_mode.leave = lguest_leave_lazy_mmu_mode;
+	pv_mmu_ops.lazy_mode.flush = paravirt_flush_lazy_mmu;
 	pv_mmu_ops.pte_update = lguest_pte_update;
 	pv_mmu_ops.pte_update_defer = lguest_pte_update;
 

arch/x86/lib/usercopy_64.c

@@ -169,10 +169,10 @@ copy_user_handle_tail(char *to, char *from, unsigned len, unsigned zerorest)
 	char c;
 	unsigned zero_len;
 
-	for (; len; --len) {
+	for (; len; --len, to++) {
 		if (__get_user_nocheck(c, from++, sizeof(char)))
 			break;
-		if (__put_user_nocheck(c, to++, sizeof(char)))
+		if (__put_user_nocheck(c, to, sizeof(char)))
 			break;
 	}
 

arch/x86/mm/fault.c

@@ -376,10 +376,12 @@ static noinline __kprobes int vmalloc_fault(unsigned long address)
 	if (pgd_none(*pgd_ref))
 		return -1;
 
-	if (pgd_none(*pgd))
+	if (pgd_none(*pgd)) {
 		set_pgd(pgd, *pgd_ref);
-	else
+		arch_flush_lazy_mmu_mode();
+	} else {
 		BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*pgd_ref));
+	}
 
 	/*
 	 * Below here mismatches are bugs because these lower tables
@@ -720,12 +722,15 @@ __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
 		if (is_errata100(regs, address))
 			return;
 
-		if (unlikely(show_unhandled_signals))
+		/* Kernel addresses are always protection faults: */
+		if (address >= TASK_SIZE)
+			error_code |= PF_PROT;
+
+		if (likely(show_unhandled_signals))
 			show_signal_msg(regs, error_code, address, tsk);
 
-		/* Kernel addresses are always protection faults: */
 		tsk->thread.cr2		= address;
-		tsk->thread.error_code	= error_code | (address >= TASK_SIZE);
+		tsk->thread.error_code	= error_code;
 		tsk->thread.trap_no	= 14;
 
 		force_sig_info_fault(SIGSEGV, si_code, address, tsk, 0);

arch/x86/mm/init.c

@@ -44,11 +44,15 @@ static void __init find_early_table_space(struct map_range *mr, int nr_range)
 	int i;
 	unsigned long puds = 0, pmds = 0, ptes = 0, tables;
 	unsigned long start = 0, good_end;
+	unsigned long pgd_extra = 0;
 	phys_addr_t base;
 
 	for (i = 0; i < nr_range; i++) {
 		unsigned long range, extra;
 
+		if ((mr[i].end >> PGDIR_SHIFT) - (mr[i].start >> PGDIR_SHIFT))
+			pgd_extra++;
+
 		range = mr[i].end - mr[i].start;
 		puds += (range + PUD_SIZE - 1) >> PUD_SHIFT;
 
@@ -73,6 +77,7 @@ static void __init find_early_table_space(struct map_range *mr, int nr_range)
 	tables = roundup(puds * sizeof(pud_t), PAGE_SIZE);
 	tables += roundup(pmds * sizeof(pmd_t), PAGE_SIZE);
 	tables += roundup(ptes * sizeof(pte_t), PAGE_SIZE);
+	tables += (pgd_extra * PAGE_SIZE);
 
 #ifdef CONFIG_X86_32
 	/* for fixmap */

arch/x86/mm/init_64.c

@@ -831,6 +831,9 @@ int kern_addr_valid(unsigned long addr)
 	if (pud_none(*pud))
 		return 0;
 
+	if (pud_large(*pud))
+		return pfn_valid(pud_pfn(*pud));
+
 	pmd = pmd_offset(pud, addr);
 	if (pmd_none(*pmd))
 		return 0;

arch/x86/mm/numa.c

@@ -207,9 +207,6 @@ static void __init setup_node_data(int nid, u64 start, u64 end)
 	if (end && (end - start) < NODE_MIN_SIZE)
 		return;
 
-	/* initialize remap allocator before aligning to ZONE_ALIGN */
-	init_alloc_remap(nid, start, end);
-
 	start = roundup(start, ZONE_ALIGN);
 
 	printk(KERN_INFO "Initmem setup node %d %016Lx-%016Lx\n",

arch/x86/mm/numa_32.c

@@ -73,167 +73,6 @@ unsigned long node_memmap_size_bytes(int nid, unsigned long start_pfn,
 
 extern unsigned long highend_pfn, highstart_pfn;
 
-#define LARGE_PAGE_BYTES (PTRS_PER_PTE * PAGE_SIZE)
-
-static void *node_remap_start_vaddr[MAX_NUMNODES];
-void set_pmd_pfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags);
-
-/*
- * Remap memory allocator
- */
-static unsigned long node_remap_start_pfn[MAX_NUMNODES];
-static void *node_remap_end_vaddr[MAX_NUMNODES];
-static void *node_remap_alloc_vaddr[MAX_NUMNODES];
-
-/**
- * alloc_remap - Allocate remapped memory
- * @nid: NUMA node to allocate memory from
- * @size: The size of allocation
- *
- * Allocate @size bytes from the remap area of NUMA node @nid.  The
- * size of the remap area is predetermined by init_alloc_remap() and
- * only the callers considered there should call this function.  For
- * more info, please read the comment on top of init_alloc_remap().
- *
- * The caller must be ready to handle allocation failure from this
- * function and fall back to regular memory allocator in such cases.
- *
- * CONTEXT:
- * Single CPU early boot context.
- *
- * RETURNS:
- * Pointer to the allocated memory on success, %NULL on failure.
- */
-void *alloc_remap(int nid, unsigned long size)
-{
-	void *allocation = node_remap_alloc_vaddr[nid];
-
-	size = ALIGN(size, L1_CACHE_BYTES);
-
-	if (!allocation || (allocation + size) > node_remap_end_vaddr[nid])
-		return NULL;
-
-	node_remap_alloc_vaddr[nid] += size;
-	memset(allocation, 0, size);
-
-	return allocation;
-}
-
-#ifdef CONFIG_HIBERNATION
-/**
- * resume_map_numa_kva - add KVA mapping to the temporary page tables created
- *                       during resume from hibernation
- * @pgd_base - temporary resume page directory
- */
-void resume_map_numa_kva(pgd_t *pgd_base)
-{
-	int node;
-
-	for_each_online_node(node) {
-		unsigned long start_va, start_pfn, nr_pages, pfn;
-
-		start_va = (unsigned long)node_remap_start_vaddr[node];
-		start_pfn = node_remap_start_pfn[node];
-		nr_pages = (node_remap_end_vaddr[node] -
-			    node_remap_start_vaddr[node]) >> PAGE_SHIFT;
-
-		printk(KERN_DEBUG "%s: node %d\n", __func__, node);
-
-		for (pfn = 0; pfn < nr_pages; pfn += PTRS_PER_PTE) {
-			unsigned long vaddr = start_va + (pfn << PAGE_SHIFT);
-			pgd_t *pgd = pgd_base + pgd_index(vaddr);
-			pud_t *pud = pud_offset(pgd, vaddr);
-			pmd_t *pmd = pmd_offset(pud, vaddr);
-
-			set_pmd(pmd, pfn_pmd(start_pfn + pfn,
-						PAGE_KERNEL_LARGE_EXEC));
-
-			printk(KERN_DEBUG "%s: %08lx -> pfn %08lx\n",
-				__func__, vaddr, start_pfn + pfn);
-		}
-	}
-}
-#endif
-
-/**
- * init_alloc_remap - Initialize remap allocator for a NUMA node
- * @nid: NUMA node to initizlie remap allocator for
- *
- * NUMA nodes may end up without any lowmem.  As allocating pgdat and
- * memmap on a different node with lowmem is inefficient, a special
- * remap allocator is implemented which can be used by alloc_remap().
- *
- * For each node, the amount of memory which will be necessary for
- * pgdat and memmap is calculated and two memory areas of the size are
- * allocated - one in the node and the other in lowmem; then, the area
- * in the node is remapped to the lowmem area.
- *
- * As pgdat and memmap must be allocated in lowmem anyway, this
- * doesn't waste lowmem address space; however, the actual lowmem
- * which gets remapped over is wasted.  The amount shouldn't be
- * problematic on machines this feature will be used.
- *
- * Initialization failure isn't fatal.  alloc_remap() is used
- * opportunistically and the callers will fall back to other memory
- * allocation mechanisms on failure.
- */
-void __init init_alloc_remap(int nid, u64 start, u64 end)
-{
-	unsigned long start_pfn = start >> PAGE_SHIFT;
-	unsigned long end_pfn = end >> PAGE_SHIFT;
-	unsigned long size, pfn;
-	u64 node_pa, remap_pa;
-	void *remap_va;
-
-	/*
-	 * The acpi/srat node info can show hot-add memroy zones where
-	 * memory could be added but not currently present.
-	 */
-	printk(KERN_DEBUG "node %d pfn: [%lx - %lx]\n",
-	       nid, start_pfn, end_pfn);
-
-	/* calculate the necessary space aligned to large page size */
-	size = node_memmap_size_bytes(nid, start_pfn, end_pfn);
-	size += ALIGN(sizeof(pg_data_t), PAGE_SIZE);
-	size = ALIGN(size, LARGE_PAGE_BYTES);
-
-	/* allocate node memory and the lowmem remap area */
-	node_pa = memblock_find_in_range(start, end, size, LARGE_PAGE_BYTES);
-	if (node_pa == MEMBLOCK_ERROR) {
-		pr_warning("remap_alloc: failed to allocate %lu bytes for node %d\n",
-			   size, nid);
-		return;
-	}
-	memblock_x86_reserve_range(node_pa, node_pa + size, "KVA RAM");
-
-	remap_pa = memblock_find_in_range(min_low_pfn << PAGE_SHIFT,
-					  max_low_pfn << PAGE_SHIFT,
-					  size, LARGE_PAGE_BYTES);
-	if (remap_pa == MEMBLOCK_ERROR) {
-		pr_warning("remap_alloc: failed to allocate %lu bytes remap area for node %d\n",
-			   size, nid);
-		memblock_x86_free_range(node_pa, node_pa + size);
-		return;
-	}
-	memblock_x86_reserve_range(remap_pa, remap_pa + size, "KVA PG");
-	remap_va = phys_to_virt(remap_pa);
-
-	/* perform actual remap */
-	for (pfn = 0; pfn < size >> PAGE_SHIFT; pfn += PTRS_PER_PTE)
-		set_pmd_pfn((unsigned long)remap_va + (pfn << PAGE_SHIFT),
-			    (node_pa >> PAGE_SHIFT) + pfn,
-			    PAGE_KERNEL_LARGE);
-
-	/* initialize remap allocator parameters */
-	node_remap_start_pfn[nid] = node_pa >> PAGE_SHIFT;
-	node_remap_start_vaddr[nid] = remap_va;
-	node_remap_end_vaddr[nid] = remap_va + size;
-	node_remap_alloc_vaddr[nid] = remap_va;
-
-	printk(KERN_DEBUG "remap_alloc: node %d [%08llx-%08llx) -> [%p-%p)\n",
-	       nid, node_pa, node_pa + size, remap_va, remap_va + size);
-}
-
 void __init initmem_init(void)
 {
 	x86_numa_init();

arch/x86/mm/numa_internal.h

@@ -21,12 +21,6 @@ void __init numa_reset_distance(void);
 
 void __init x86_numa_init(void);
 
-#ifdef CONFIG_X86_64
-static inline void init_alloc_remap(int nid, u64 start, u64 end)	{ }
-#else
-void __init init_alloc_remap(int nid, u64 start, u64 end);
-#endif
-
 #ifdef CONFIG_NUMA_EMU
 void __init numa_emulation(struct numa_meminfo *numa_meminfo,
 			   int numa_dist_cnt);

arch/x86/platform/efi/efi_64.c

@@ -38,7 +38,7 @@
 #include <asm/cacheflush.h>
 #include <asm/fixmap.h>
 
-static pgd_t save_pgd __initdata;
+static pgd_t *save_pgd __initdata;
 static unsigned long efi_flags __initdata;
 
 static void __init early_code_mapping_set_exec(int executable)
@@ -61,12 +61,20 @@ static void __init early_code_mapping_set_exec(int executable)
 void __init efi_call_phys_prelog(void)
 {
 	unsigned long vaddress;
+	int pgd;
+	int n_pgds;
 
 	early_code_mapping_set_exec(1);
 	local_irq_save(efi_flags);
-	vaddress = (unsigned long)__va(0x0UL);
-	save_pgd = *pgd_offset_k(0x0UL);
-	set_pgd(pgd_offset_k(0x0UL), *pgd_offset_k(vaddress));
+
+	n_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT), PGDIR_SIZE);
+	save_pgd = kmalloc(n_pgds * sizeof(pgd_t), GFP_KERNEL);
+
+	for (pgd = 0; pgd < n_pgds; pgd++) {
+		save_pgd[pgd] = *pgd_offset_k(pgd * PGDIR_SIZE);
+		vaddress = (unsigned long)__va(pgd * PGDIR_SIZE);
+		set_pgd(pgd_offset_k(pgd * PGDIR_SIZE), *pgd_offset_k(vaddress));
+	}
 	__flush_tlb_all();
 }
 
@@ -75,7 +83,11 @@ void __init efi_call_phys_epilog(void)
 	/*
 	 * After the lock is released, the original page table is restored.
 	 */
-	set_pgd(pgd_offset_k(0x0UL), save_pgd);
+	int pgd;
+	int n_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT) , PGDIR_SIZE);
+	for (pgd = 0; pgd < n_pgds; pgd++)
+		set_pgd(pgd_offset_k(pgd * PGDIR_SIZE), save_pgd[pgd]);
+	kfree(save_pgd);
 	__flush_tlb_all();
 	local_irq_restore(efi_flags);
 	early_code_mapping_set_exec(0);

arch/x86/power/cpu.c

@@ -10,6 +10,7 @@
 
 #include <linux/suspend.h>
 #include <linux/smp.h>
+#include <linux/perf_event.h>
 
 #include <asm/pgtable.h>
 #include <asm/proto.h>
@@ -224,6 +225,7 @@ static void __restore_processor_state(struct saved_context *ctxt)
 
 	do_fpu_end();
 	mtrr_bp_restore();
+	perf_restore_debug_store();
 }
 
 /* Needed by apm.c */