17 files changed, 215 insertions, 96 deletions

diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 85b05c463fa..e8995727b1c 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -76,6 +76,7 @@ int main(void)
 	DEFINE(SIGSEGV, SIGSEGV);
 	DEFINE(NMI_MASK, NMI_MASK);
 	DEFINE(THREAD_DSCR, offsetof(struct thread_struct, dscr));
+	DEFINE(THREAD_DSCR_INHERIT, offsetof(struct thread_struct, dscr_inherit));
 #else
 	DEFINE(THREAD_INFO, offsetof(struct task_struct, stack));
 #endif /* CONFIG_PPC64 */
diff --git a/arch/powerpc/kernel/dbell.c b/arch/powerpc/kernel/dbell.c
index 5b25c8060fd..a892680668d 100644
--- a/arch/powerpc/kernel/dbell.c
+++ b/arch/powerpc/kernel/dbell.c
@@ -28,6 +28,8 @@ void doorbell_setup_this_cpu(void)
 
 void doorbell_cause_ipi(int cpu, unsigned long data)
 {
+	/* Order previous accesses vs. msgsnd, which is treated as a store */
+	mb();
 	ppc_msgsnd(PPC_DBELL, 0, data);
 }
 
diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c
index 2d7bb8ced13..e4897523de4 100644
--- a/arch/powerpc/kernel/dma-iommu.c
+++ b/arch/powerpc/kernel/dma-iommu.c
@@ -83,11 +83,10 @@ static int dma_iommu_dma_supported(struct device *dev, u64 mask)
 		return 0;
 	}
 
-	if ((tbl->it_offset + tbl->it_size) > (mask >> IOMMU_PAGE_SHIFT)) {
-		dev_info(dev, "Warning: IOMMU window too big for device mask\n");
-		dev_info(dev, "mask: 0x%08llx, table end: 0x%08lx\n",
-				mask, (tbl->it_offset + tbl->it_size) <<
-				IOMMU_PAGE_SHIFT);
+	if (tbl->it_offset > (mask >> IOMMU_PAGE_SHIFT)) {
+		dev_info(dev, "Warning: IOMMU offset too big for device mask\n");
+		dev_info(dev, "mask: 0x%08llx, table offset: 0x%08lx\n",
+				mask, tbl->it_offset << IOMMU_PAGE_SHIFT);
 		return 0;
 	} else
 		return 1;
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 4b01a25e29e..b40e0b4815b 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -370,6 +370,12 @@ _GLOBAL(ret_from_fork)
 	li	r3,0
 	b	syscall_exit
 
+	.section	".toc","aw"
+DSCR_DEFAULT:
+	.tc dscr_default[TC],dscr_default
+
+	.section	".text"
+
 /*
  * This routine switches between two different tasks.  The process
  * state of one is saved on its kernel stack.  Then the state
@@ -509,9 +515,6 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
 	mr	r1,r8		/* start using new stack pointer */
 	std	r7,PACAKSAVE(r13)
 
-	ld	r6,_CCR(r1)
-	mtcrf	0xFF,r6
-
 #ifdef CONFIG_ALTIVEC
 BEGIN_FTR_SECTION
 	ld	r0,THREAD_VRSAVE(r4)
@@ -520,14 +523,22 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 #endif /* CONFIG_ALTIVEC */
 #ifdef CONFIG_PPC64
 BEGIN_FTR_SECTION
+	lwz	r6,THREAD_DSCR_INHERIT(r4)
+	ld	r7,DSCR_DEFAULT@toc(2)
 	ld	r0,THREAD_DSCR(r4)
-	cmpd	r0,r25
-	beq	1f
+	cmpwi	r6,0
+	bne	1f
+	ld	r0,0(r7)
+1:	cmpd	r0,r25
+	beq	2f
 	mtspr	SPRN_DSCR,r0
-1:	
+2:
 END_FTR_SECTION_IFSET(CPU_FTR_DSCR)
 #endif
 
+	ld	r6,_CCR(r1)
+	mtcrf	0xFF,r6
+
 	/* r3-r13 are destroyed -- Cort */
 	REST_8GPRS(14, r1)
 	REST_10GPRS(22, r1)
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index e894515e77b..39aa97d3ff8 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -186,7 +186,7 @@ hardware_interrupt_hv:
 	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0x800)
 
 	MASKABLE_EXCEPTION_PSERIES(0x900, 0x900, decrementer)
-	MASKABLE_EXCEPTION_HV(0x980, 0x982, decrementer)
+	STD_EXCEPTION_HV(0x980, 0x982, hdecrementer)
 
 	STD_EXCEPTION_PSERIES(0xa00, 0xa00, trap_0a)
 	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xa00)
@@ -486,6 +486,7 @@ machine_check_common:
 
 	STD_EXCEPTION_COMMON_ASYNC(0x500, hardware_interrupt, do_IRQ)
 	STD_EXCEPTION_COMMON_ASYNC(0x900, decrementer, .timer_interrupt)
+	STD_EXCEPTION_COMMON(0x980, hdecrementer, .hdec_interrupt)
 	STD_EXCEPTION_COMMON(0xa00, trap_0a, .unknown_exception)
 	STD_EXCEPTION_COMMON(0xb00, trap_0b, .unknown_exception)
 	STD_EXCEPTION_COMMON(0xd00, single_step, .single_step_exception)
diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c
index f3a82dde61d..956a4c496de 100644
--- a/arch/powerpc/kernel/hw_breakpoint.c
+++ b/arch/powerpc/kernel/hw_breakpoint.c
@@ -253,7 +253,7 @@ int __kprobes hw_breakpoint_handler(struct die_args *args)
 
 	/* Do not emulate user-space instructions, instead single-step them */
 	if (user_mode(regs)) {
-		bp->ctx->task->thread.last_hit_ubp = bp;
+		current->thread.last_hit_ubp = bp;
 		regs->msr |= MSR_SE;
 		goto out;
 	}
diff --git a/arch/powerpc/kernel/idle_power7.S b/arch/powerpc/kernel/idle_power7.S
index 7140d838339..e11863f4e59 100644
--- a/arch/powerpc/kernel/idle_power7.S
+++ b/arch/powerpc/kernel/idle_power7.S
@@ -28,7 +28,9 @@ _GLOBAL(power7_idle)
 	lwz	r4,ADDROFF(powersave_nap)(r3)
 	cmpwi	0,r4,0
 	beqlr
+	/* fall through */
 
+_GLOBAL(power7_nap)
 	/* NAP is a state loss, we create a regs frame on the
 	 * stack, fill it up with the state we care about and
 	 * stick a pointer to it in PACAR1. We really only
diff --git a/arch/powerpc/kernel/kgdb.c b/arch/powerpc/kernel/kgdb.c
index 782bd0a3c2f..c470a40b29f 100644
--- a/arch/powerpc/kernel/kgdb.c
+++ b/arch/powerpc/kernel/kgdb.c
@@ -25,6 +25,7 @@
 #include <asm/processor.h>
 #include <asm/machdep.h>
 #include <asm/debug.h>
+#include <linux/slab.h>
 
 /*
  * This table contains the mapping between PowerPC hardware trap types, and
@@ -101,6 +102,21 @@ static int computeSignal(unsigned int tt)
 	return SIGHUP;		/* default for things we don't know about */
 }
 
+/**
+ *
+ *	kgdb_skipexception - Bail out of KGDB when we've been triggered.
+ *	@exception: Exception vector number
+ *	@regs: Current &struct pt_regs.
+ *
+ *	On some architectures we need to skip a breakpoint exception when
+ *	it occurs after a breakpoint has been removed.
+ *
+ */
+int kgdb_skipexception(int exception, struct pt_regs *regs)
+{
+	return kgdb_isremovedbreak(regs->nip);
+}
+
 static int kgdb_call_nmi_hook(struct pt_regs *regs)
 {
 	kgdb_nmicallback(raw_smp_processor_id(), regs);
@@ -138,6 +154,8 @@ static int kgdb_handle_breakpoint(struct pt_regs *regs)
 static int kgdb_singlestep(struct pt_regs *regs)
 {
 	struct thread_info *thread_info, *exception_thread_info;
+	struct thread_info *backup_current_thread_info = \
+		(struct thread_info *)kmalloc(sizeof(struct thread_info), GFP_KERNEL);
 
 	if (user_mode(regs))
 		return 0;
@@ -155,13 +173,17 @@ static int kgdb_singlestep(struct pt_regs *regs)
 	thread_info = (struct thread_info *)(regs->gpr[1] & ~(THREAD_SIZE-1));
 	exception_thread_info = current_thread_info();
 
-	if (thread_info != exception_thread_info)
+	if (thread_info != exception_thread_info) {
+		/* Save the original current_thread_info. */
+		memcpy(backup_current_thread_info, exception_thread_info, sizeof *thread_info);
 		memcpy(exception_thread_info, thread_info, sizeof *thread_info);
+	}
 
 	kgdb_handle_exception(0, SIGTRAP, 0, regs);
 
 	if (thread_info != exception_thread_info)
-		memcpy(thread_info, exception_thread_info, sizeof *thread_info);
+		/* Restore current_thread_info lastly. */
+		memcpy(exception_thread_info, backup_current_thread_info, sizeof *thread_info);
 
 	return 1;
 }
@@ -410,7 +432,6 @@ int kgdb_arch_handle_exception(int vector, int signo, int err_code,
 #else
 			linux_regs->msr |= MSR_SE;
 #endif
-			kgdb_single_step = 1;
 			atomic_set(&kgdb_cpu_doing_single_step,
 				   raw_smp_processor_id());
 		}
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index 2aa04f29e1d..43fea543d68 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -99,6 +99,26 @@ void pcibios_free_controller(struct pci_controller *phb)
 		kfree(phb);
 }
 
+/*
+ * The function is used to return the minimal alignment
+ * for memory or I/O windows of the associated P2P bridge.
+ * By default, 4KiB alignment for I/O windows and 1MiB for
+ * memory windows.
+ */
+resource_size_t pcibios_window_alignment(struct pci_bus *bus,
+					 unsigned long type)
+{
+	if (ppc_md.pcibios_window_alignment)
+		return ppc_md.pcibios_window_alignment(bus, type);
+
+	/*
+	 * PCI core will figure out the default
+	 * alignment: 4KiB for I/O and 1MiB for
+	 * memory window.
+	 */
+	return 1;
+}
+
 static resource_size_t pcibios_io_size(const struct pci_controller *hose)
 {
 #ifdef CONFIG_PPC64
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 710f400476d..e9cb51f5f80 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -514,9 +514,6 @@ struct task_struct *__switch_to(struct task_struct *prev,
 
 	local_irq_save(flags);
 
-	account_system_vtime(current);
-	account_process_vtime(current);
-
 	/*
 	 * We can't take a PMU exception inside _switch() since there is a
 	 * window where the kernel stack SLB and the kernel stack are out
@@ -802,16 +799,8 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
 #endif /* CONFIG_PPC_STD_MMU_64 */
 #ifdef CONFIG_PPC64 
 	if (cpu_has_feature(CPU_FTR_DSCR)) {
-		if (current->thread.dscr_inherit) {
-			p->thread.dscr_inherit = 1;
-			p->thread.dscr = current->thread.dscr;
-		} else if (0 != dscr_default) {
-			p->thread.dscr_inherit = 1;
-			p->thread.dscr = dscr_default;
-		} else {
-			p->thread.dscr_inherit = 0;
-			p->thread.dscr = 0;
-		}
+		p->thread.dscr_inherit = current->thread.dscr_inherit;
+		p->thread.dscr = current->thread.dscr;
 	}
 #endif
 
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index 0794a3017b1..47834a3f493 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -705,6 +705,7 @@ static void __init early_cmdline_parse(void)
 #endif
 #define OV5_TYPE1_AFFINITY	0x80	/* Type 1 NUMA affinity */
 #define OV5_PFO_HW_RNG		0x80	/* PFO Random Number Generator */
+#define OV5_PFO_HW_842		0x40	/* PFO Compression Accelerator */
 #define OV5_PFO_HW_ENCR		0x20	/* PFO Encryption Accelerator */
 
 /* Option Vector 6: IBM PAPR hints */
@@ -774,8 +775,7 @@ static unsigned char ibm_architecture_vec[] = {
 	0,
 	0,
 	0,
-	OV5_PFO_HW_RNG | OV5_PFO_HW_ENCR,
-
+	OV5_PFO_HW_RNG | OV5_PFO_HW_ENCR | OV5_PFO_HW_842,
 	/* option vector 6: IBM PAPR hints */
 	4 - 2,				/* length */
 	0,
@@ -1624,6 +1624,63 @@ static void __init prom_instantiate_rtas(void)
 
 #ifdef CONFIG_PPC64
 /*
+ * Allocate room for and instantiate Stored Measurement Log (SML)
+ */
+static void __init prom_instantiate_sml(void)
+{
+	phandle ibmvtpm_node;
+	ihandle ibmvtpm_inst;
+	u32 entry = 0, size = 0;
+	u64 base;
+
+	prom_debug("prom_instantiate_sml: start...\n");
+
+	ibmvtpm_node = call_prom("finddevice", 1, 1, ADDR("/ibm,vtpm"));
+	prom_debug("ibmvtpm_node: %x\n", ibmvtpm_node);
+	if (!PHANDLE_VALID(ibmvtpm_node))
+		return;
+
+	ibmvtpm_inst = call_prom("open", 1, 1, ADDR("/ibm,vtpm"));
+	if (!IHANDLE_VALID(ibmvtpm_inst)) {
+		prom_printf("opening vtpm package failed (%x)\n", ibmvtpm_inst);
+		return;
+	}
+
+	if (call_prom_ret("call-method", 2, 2, &size,
+			  ADDR("sml-get-handover-size"),
+			  ibmvtpm_inst) != 0 || size == 0) {
+		prom_printf("SML get handover size failed\n");
+		return;
+	}
+
+	base = alloc_down(size, PAGE_SIZE, 0);
+	if (base == 0)
+		prom_panic("Could not allocate memory for sml\n");
+
+	prom_printf("instantiating sml at 0x%x...", base);
+
+	if (call_prom_ret("call-method", 4, 2, &entry,
+			  ADDR("sml-handover"),
+			  ibmvtpm_inst, size, base) != 0 || entry == 0) {
+		prom_printf("SML handover failed\n");
+		return;
+	}
+	prom_printf(" done\n");
+
+	reserve_mem(base, size);
+
+	prom_setprop(ibmvtpm_node, "/ibm,vtpm", "linux,sml-base",
+		     &base, sizeof(base));
+	prom_setprop(ibmvtpm_node, "/ibm,vtpm", "linux,sml-size",
+		     &size, sizeof(size));
+
+	prom_debug("sml base     = 0x%x\n", base);
+	prom_debug("sml size     = 0x%x\n", (long)size);
+
+	prom_debug("prom_instantiate_sml: end...\n");
+}
+
+/*
  * Allocate room for and initialize TCE tables
  */
 static void __init prom_initialize_tce_table(void)
@@ -2916,6 +2973,11 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4,
 		prom_instantiate_opal();
 #endif
 
+#ifdef CONFIG_PPC64
+	/* instantiate sml */
+	prom_instantiate_sml();
+#endif
+
 	/*
 	 * On non-powermacs, put all CPUs in spin-loops.
 	 *
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 0321007086f..8d4214afc21 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -198,8 +198,15 @@ void smp_muxed_ipi_message_pass(int cpu, int msg)
 	struct cpu_messages *info = &per_cpu(ipi_message, cpu);
 	char *message = (char *)&info->messages;
 
+	/*
+	 * Order previous accesses before accesses in the IPI handler.
+	 */
+	smp_mb();
 	message[msg] = 1;
-	mb();
+	/*
+	 * cause_ipi functions are required to include a full barrier
+	 * before doing whatever causes the IPI.
+	 */
 	smp_ops->cause_ipi(cpu, info->data);
 }
 
@@ -211,7 +218,7 @@ irqreturn_t smp_ipi_demux(void)
 	mb();	/* order any irq clear */
 
 	do {
-		all = xchg_local(&info->messages, 0);
+		all = xchg(&info->messages, 0);
 
 #ifdef __BIG_ENDIAN
 		if (all & (1 << (24 - 8 * PPC_MSG_CALL_FUNCTION)))
diff --git a/arch/powerpc/kernel/sys_ppc32.c b/arch/powerpc/kernel/sys_ppc32.c
index 81c570633ea..abd1112da54 100644
--- a/arch/powerpc/kernel/sys_ppc32.c
+++ b/arch/powerpc/kernel/sys_ppc32.c
@@ -143,48 +143,17 @@ long compat_sys_ipc(u32 call, u32 first, u32 second, u32 third, compat_uptr_t pt
  * proper conversion (sign extension) between the register representation of a signed int (msr in 32-bit mode)
  * and the register representation of a signed int (msr in 64-bit mode) is performed.
  */
-asmlinkage long compat_sys_sendfile(u32 out_fd, u32 in_fd, compat_off_t __user * offset, u32 count)
+asmlinkage long compat_sys_sendfile_wrapper(u32 out_fd, u32 in_fd,
+					    compat_off_t __user *offset, u32 count)
 {
-	mm_segment_t old_fs = get_fs();
-	int ret;
-	off_t of;
-	off_t __user *up;
-
-	if (offset && get_user(of, offset))
-		return -EFAULT;
-
-	/* The __user pointer cast is valid because of the set_fs() */		
-	set_fs(KERNEL_DS);
-	up = offset ? (off_t __user *) &of : NULL;
-	ret = sys_sendfile((int)out_fd, (int)in_fd, up, count);
-	set_fs(old_fs);
-	
-	if (offset && put_user(of, offset))
-		return -EFAULT;
-		
-	return ret;
+	return compat_sys_sendfile((int)out_fd, (int)in_fd, offset, count);
 }
 
-asmlinkage int compat_sys_sendfile64(int out_fd, int in_fd, compat_loff_t __user *offset, s32 count)
+asmlinkage long compat_sys_sendfile64_wrapper(u32 out_fd, u32 in_fd,
+					      compat_loff_t __user *offset, u32 count)
 {
-	mm_segment_t old_fs = get_fs();
-	int ret;
-	loff_t lof;
-	loff_t __user *up;
-	
-	if (offset && get_user(lof, offset))
-		return -EFAULT;
-		
-	/* The __user pointer cast is valid because of the set_fs() */		
-	set_fs(KERNEL_DS);
-	up = offset ? (loff_t __user *) &lof : NULL;
-	ret = sys_sendfile64(out_fd, in_fd, up, count);
-	set_fs(old_fs);
-	
-	if (offset && put_user(lof, offset))
-		return -EFAULT;
-		
-	return ret;
+	return sys_sendfile((int)out_fd, (int)in_fd,
+			    (off_t __user *)offset, count);
 }
 
 long compat_sys_execve(unsigned long a0, unsigned long a1, unsigned long a2,
diff --git a/arch/powerpc/kernel/syscalls.c b/arch/powerpc/kernel/syscalls.c
index f2496f2faec..4e3cc47f26b 100644
--- a/arch/powerpc/kernel/syscalls.c
+++ b/arch/powerpc/kernel/syscalls.c
@@ -107,11 +107,11 @@ long ppc64_personality(unsigned long personality)
 	long ret;
 
 	if (personality(current->personality) == PER_LINUX32
-	    && personality == PER_LINUX)
-		personality = PER_LINUX32;
+	    && personality(personality) == PER_LINUX)
+		personality = (personality & ~PER_MASK) | PER_LINUX32;
 	ret = sys_personality(personality);
-	if (ret == PER_LINUX32)
-		ret = PER_LINUX;
+	if (personality(ret) == PER_LINUX32)
+		ret = (ret & ~PER_MASK) | PER_LINUX;
 	return ret;
 }
 #endif
diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c
index 3529446c2ab..8302af64921 100644
--- a/arch/powerpc/kernel/sysfs.c
+++ b/arch/powerpc/kernel/sysfs.c
@@ -194,6 +194,14 @@ static ssize_t show_dscr_default(struct device *dev,
 	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 device *dev,
 		struct device_attribute *attr, const char *buf,
 		size_t count)
@@ -206,6 +214,8 @@ static ssize_t __used store_dscr_default(struct device *dev,
 		return -EINVAL;
 	dscr_default = val;
 
+	on_each_cpu(update_dscr, NULL, 1);
+
 	return count;
 }
 
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index be171ee73bf..eaa9d0e6abc 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -291,13 +291,12 @@ static inline u64 calculate_stolen_time(u64 stop_tb)
  * Account time for a transition between system, hard irq
  * or soft irq state.
  */
-void account_system_vtime(struct task_struct *tsk)
+static u64 vtime_delta(struct task_struct *tsk,
+			u64 *sys_scaled, u64 *stolen)
 {
-	u64 now, nowscaled, delta, deltascaled;
-	unsigned long flags;
-	u64 stolen, udelta, sys_scaled, user_scaled;
+	u64 now, nowscaled, deltascaled;
+	u64 udelta, delta, user_scaled;
 
-	local_irq_save(flags);
 	now = mftb();
 	nowscaled = read_spurr(now);
 	get_paca()->system_time += now - get_paca()->starttime;
@@ -305,7 +304,7 @@ void account_system_vtime(struct task_struct *tsk)
 	deltascaled = nowscaled - get_paca()->startspurr;
 	get_paca()->startspurr = nowscaled;
 
-	stolen = calculate_stolen_time(now);
+	*stolen = calculate_stolen_time(now);
 
 	delta = get_paca()->system_time;
 	get_paca()->system_time = 0;
@@ -322,35 +321,45 @@ void account_system_vtime(struct task_struct *tsk)
 	 * the user ticks get saved up in paca->user_time_scaled to be
 	 * used by account_process_tick.
 	 */
-	sys_scaled = delta;
+	*sys_scaled = delta;
 	user_scaled = udelta;
 	if (deltascaled != delta + udelta) {
 		if (udelta) {
-			sys_scaled = deltascaled * delta / (delta + udelta);
-			user_scaled = deltascaled - sys_scaled;
+			*sys_scaled = deltascaled * delta / (delta + udelta);
+			user_scaled = deltascaled - *sys_scaled;
 		} else {
-			sys_scaled = deltascaled;
+			*sys_scaled = deltascaled;
 		}
 	}
 	get_paca()->user_time_scaled += user_scaled;
 
-	if (in_interrupt() || idle_task(smp_processor_id()) != tsk) {
-		account_system_time(tsk, 0, delta, sys_scaled);
-		if (stolen)
-			account_steal_time(stolen);
-	} else {
-		account_idle_time(delta + stolen);
-	}
-	local_irq_restore(flags);
+	return delta;
+}
+
+void vtime_account_system(struct task_struct *tsk)
+{
+	u64 delta, sys_scaled, stolen;
+
+	delta = vtime_delta(tsk, &sys_scaled, &stolen);
+	account_system_time(tsk, 0, delta, sys_scaled);
+	if (stolen)
+		account_steal_time(stolen);
+}
+
+void vtime_account_idle(struct task_struct *tsk)
+{
+	u64 delta, sys_scaled, stolen;
+
+	delta = vtime_delta(tsk, &sys_scaled, &stolen);
+	account_idle_time(delta + stolen);
 }
-EXPORT_SYMBOL_GPL(account_system_vtime);
 
 /*
  * Transfer the user and system times accumulated in the paca
  * by the exception entry and exit code to the generic process
  * user and system time records.
  * Must be called with interrupts disabled.
- * Assumes that account_system_vtime() has been called recently
+ * Assumes that vtime_account() has been called recently
  * (i.e. since the last entry from usermode) so that
  * get_paca()->user_time_scaled is up to date.
  */
@@ -366,6 +375,12 @@ void account_process_tick(struct task_struct *tsk, int user_tick)
 	account_user_time(tsk, utime, utimescaled);
 }
 
+void vtime_task_switch(struct task_struct *prev)
+{
+	vtime_account(prev);
+	account_process_tick(prev, 0);
+}
+
 #else /* ! CONFIG_VIRT_CPU_ACCOUNTING */
 #define calc_cputime_factors()
 #endif
@@ -535,6 +550,15 @@ void timer_interrupt(struct pt_regs * regs)
 	trace_timer_interrupt_exit(regs);
 }
 
+/*
+ * Hypervisor decrementer interrupts shouldn't occur but are sometimes
+ * left pending on exit from a KVM guest.  We don't need to do anything
+ * to clear them, as they are edge-triggered.
+ */
+void hdec_interrupt(struct pt_regs *regs)
+{
+}
+
 #ifdef CONFIG_SUSPEND
 static void generic_suspend_disable_irqs(void)
 {
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 158972341a2..ae0843fa7a6 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -972,8 +972,9 @@ 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