---

yaml
---
r: 300123
b: refs/heads/master
c: a7ac56d
h: refs/heads/master
i:
  300121: d8fa28e
  300119: ecf0436
v: v3

[refs]

@@ -1,2 +1,2 @@
 ---
-refs/heads/master: 22b6dd78aec32abf38d9b187dea2e0a8b28aa186
+refs/heads/master: a7ac56de8316c0eb1111824c9add045cac2bd7a2

trunk/arch/arm/kernel/ptrace.c

@@ -906,14 +906,27 @@ long arch_ptrace(struct task_struct *child, long request,
 	return ret;
 }
 
+#ifdef __ARMEB__
+#define AUDIT_ARCH_NR AUDIT_ARCH_ARMEB
+#else
+#define AUDIT_ARCH_NR AUDIT_ARCH_ARM
+#endif
+
 asmlinkage int syscall_trace(int why, struct pt_regs *regs, int scno)
 {
 	unsigned long ip;
 
-	if (why)
+	/*
+	 * Save IP.  IP is used to denote syscall entry/exit:
+	 *  IP = 0 -> entry, = 1 -> exit
+	 */
+	ip = regs->ARM_ip;
+	regs->ARM_ip = why;
+
+	if (!ip)
 		audit_syscall_exit(regs);
 	else
-		audit_syscall_entry(AUDIT_ARCH_ARM, scno, regs->ARM_r0,
+		audit_syscall_entry(AUDIT_ARCH_NR, scno, regs->ARM_r0,
 				    regs->ARM_r1, regs->ARM_r2, regs->ARM_r3);
 
 	if (!test_thread_flag(TIF_SYSCALL_TRACE))
@@ -923,13 +936,6 @@ asmlinkage int syscall_trace(int why, struct pt_regs *regs, int scno)
 
 	current_thread_info()->syscall = scno;
 
-	/*
-	 * IP is used to denote syscall entry/exit:
-	 * IP = 0 -> entry, =1 -> exit
-	 */
-	ip = regs->ARM_ip;
-	regs->ARM_ip = why;
-
 	/* the 0x80 provides a way for the tracing parent to distinguish
 	   between a syscall stop and SIGTRAP delivery */
 	ptrace_notify(SIGTRAP | ((current->ptrace & PT_TRACESYSGOOD)

trunk/arch/arm/kernel/smp.c

@@ -251,6 +251,8 @@ asmlinkage void __cpuinit secondary_start_kernel(void)
 	struct mm_struct *mm = &init_mm;
 	unsigned int cpu = smp_processor_id();
 
+	printk("CPU%u: Booted secondary processor\n", cpu);
+
 	/*
 	 * All kernel threads share the same mm context; grab a
 	 * reference and switch to it.
@@ -262,8 +264,6 @@ asmlinkage void __cpuinit secondary_start_kernel(void)
 	enter_lazy_tlb(mm, current);
 	local_flush_tlb_all();
 
-	printk("CPU%u: Booted secondary processor\n", cpu);
-
 	cpu_init();
 	preempt_disable();
 	trace_hardirqs_off();

trunk/arch/arm/kernel/sys_arm.c

@@ -115,7 +115,7 @@ int kernel_execve(const char *filename,
 		  "Ir" (THREAD_START_SP - sizeof(regs)),
 		  "r" (&regs),
 		  "Ir" (sizeof(regs))
-		: "r0", "r1", "r2", "r3", "r8", "r9", "ip", "lr", "memory");
+		: "r0", "r1", "r2", "r3", "ip", "lr", "memory");
 
  out:
 	return ret;

trunk/arch/arm/mach-kirkwood/board-dt.c

@@ -14,6 +14,7 @@
 #include <linux/init.h>
 #include <linux/of.h>
 #include <linux/of_platform.h>
+#include <linux/kexec.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
 #include <mach/bridge-regs.h>

trunk/arch/ia64/kvm/kvm-ia64.c

@@ -1174,7 +1174,7 @@ static enum hrtimer_restart hlt_timer_fn(struct hrtimer *data)
 
 bool kvm_vcpu_compatible(struct kvm_vcpu *vcpu)
 {
-	return irqchip_in_kernel(vcpu->kvm) == (vcpu->arch.apic != NULL);
+	return irqchip_in_kernel(vcpu->kcm) == (vcpu->arch.apic != NULL);
 }
 
 int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)

trunk/arch/powerpc/include/asm/exception-64s.h

@@ -288,6 +288,13 @@ label##_hv:								\
 /* Exception addition: Hard disable interrupts */
 #define DISABLE_INTS	SOFT_DISABLE_INTS(r10,r11)
 
+/* Exception addition: Keep interrupt state */
+#define ENABLE_INTS				\
+	ld	r11,PACAKMSR(r13);		\
+	ld	r12,_MSR(r1);			\
+	rlwimi	r11,r12,0,MSR_EE;		\
+	mtmsrd	r11,1
+
 #define ADD_NVGPRS				\
 	bl	.save_nvgprs
 

trunk/arch/powerpc/kernel/entry_64.S

@@ -767,6 +767,16 @@ do_work:
 	SOFT_DISABLE_INTS(r3,r4)
 1:	bl	.preempt_schedule_irq
 
+	/* Hard-disable interrupts again (and update PACA) */
+#ifdef CONFIG_PPC_BOOK3E
+	wrteei	0
+#else
+	ld	r10,PACAKMSR(r13) /* Get kernel MSR without EE */
+	mtmsrd	r10,1
+#endif /* CONFIG_PPC_BOOK3E */
+	li	r0,PACA_IRQ_HARD_DIS
+	stb	r0,PACAIRQHAPPENED(r13)
+
 	/* Re-test flags and eventually loop */
 	clrrdi	r9,r1,THREAD_SHIFT
 	ld	r4,TI_FLAGS(r9)
@@ -777,6 +787,14 @@ do_work:
 user_work:
 #endif /* CONFIG_PREEMPT */
 
+	/* Enable interrupts */
+#ifdef CONFIG_PPC_BOOK3E
+	wrteei	1
+#else
+	ori	r10,r10,MSR_EE
+	mtmsrd	r10,1
+#endif /* CONFIG_PPC_BOOK3E */
+
 	andi.	r0,r4,_TIF_NEED_RESCHED
 	beq	1f
 	bl	.restore_interrupts

trunk/arch/powerpc/kernel/exceptions-64s.S

@@ -768,8 +768,8 @@ alignment_common:
 	std	r3,_DAR(r1)
 	std	r4,_DSISR(r1)
 	bl	.save_nvgprs
-	DISABLE_INTS
 	addi	r3,r1,STACK_FRAME_OVERHEAD
+	ENABLE_INTS
 	bl	.alignment_exception
 	b	.ret_from_except
 

trunk/arch/powerpc/kernel/irq.c

@@ -260,17 +260,11 @@ EXPORT_SYMBOL(arch_local_irq_restore);
  * if they are currently disabled. This is typically called before
  * schedule() or do_signal() when returning to userspace. We do it
  * in C to avoid the burden of dealing with lockdep etc...
- *
- * NOTE: This is called with interrupts hard disabled but not marked
- * as such in paca->irq_happened, so we need to resync this.
  */
 void restore_interrupts(void)
 {
-	if (irqs_disabled()) {
-		local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
+	if (irqs_disabled())
 		local_irq_enable();
-	} else
-		__hard_irq_enable();
 }
 
 #endif /* CONFIG_PPC64 */

trunk/arch/powerpc/kernel/traps.c

@@ -248,7 +248,7 @@ void _exception(int signr, struct pt_regs *regs, int code, unsigned long addr)
 				   addr, regs->nip, regs->link, code);
 	}
 
-	if (arch_irqs_disabled() && !arch_irq_disabled_regs(regs))
+	if (!arch_irq_disabled_regs(regs))
 		local_irq_enable();
 
 	memset(&info, 0, sizeof(info));
@@ -1019,9 +1019,7 @@ void __kprobes program_check_exception(struct pt_regs *regs)
 		return;
 	}
 
-	/* We restore the interrupt state now */
-	if (!arch_irq_disabled_regs(regs))
-		local_irq_enable();
+	local_irq_enable();
 
 #ifdef CONFIG_MATH_EMULATION
 	/* (reason & REASON_ILLEGAL) would be the obvious thing here,
@@ -1071,10 +1069,6 @@ void alignment_exception(struct pt_regs *regs)
 {
 	int sig, code, fixed = 0;
 
-	/* We restore the interrupt state now */
-	if (!arch_irq_disabled_regs(regs))
-		local_irq_enable();
-
 	/* we don't implement logging of alignment exceptions */
 	if (!(current->thread.align_ctl & PR_UNALIGN_SIGBUS))
 		fixed = fix_alignment(regs);

trunk/arch/powerpc/kvm/book3s_64_mmu_hv.c

@@ -258,8 +258,6 @@ static long kvmppc_get_guest_page(struct kvm *kvm, unsigned long gfn,
 			    !(memslot->userspace_addr & (s - 1))) {
 				start &= ~(s - 1);
 				pgsize = s;
-				get_page(hpage);
-				put_page(page);
 				page = hpage;
 			}
 		}
@@ -283,8 +281,11 @@ static long kvmppc_get_guest_page(struct kvm *kvm, unsigned long gfn,
 	err = 0;
 
  out:
-	if (got)
+	if (got) {
+		if (PageHuge(page))
+			page = compound_head(page);
 		put_page(page);
+	}
 	return err;
 
  up_err:
@@ -677,15 +678,8 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		SetPageDirty(page);
 
  out_put:
-	if (page) {
-		/*
-		 * We drop pages[0] here, not page because page might
-		 * have been set to the head page of a compound, but
-		 * we have to drop the reference on the correct tail
-		 * page to match the get inside gup()
-		 */
-		put_page(pages[0]);
-	}
+	if (page)
+		put_page(page);
 	return ret;
 
  out_unlock:
@@ -985,7 +979,6 @@ void *kvmppc_pin_guest_page(struct kvm *kvm, unsigned long gpa,
 			pa = *physp;
 		}
 		page = pfn_to_page(pa >> PAGE_SHIFT);
-		get_page(page);
 	} else {
 		hva = gfn_to_hva_memslot(memslot, gfn);
 		npages = get_user_pages_fast(hva, 1, 1, pages);
@@ -998,6 +991,8 @@ void *kvmppc_pin_guest_page(struct kvm *kvm, unsigned long gpa,
 		page = compound_head(page);
 		psize <<= compound_order(page);
 	}
+	if (!kvm->arch.using_mmu_notifiers)
+		get_page(page);
 	offset = gpa & (psize - 1);
 	if (nb_ret)
 		*nb_ret = psize - offset;
@@ -1008,6 +1003,7 @@ void kvmppc_unpin_guest_page(struct kvm *kvm, void *va)
 {
 	struct page *page = virt_to_page(va);
 
+	page = compound_head(page);
 	put_page(page);
 }
 

trunk/arch/powerpc/kvm/book3s_hv.c

@@ -1192,6 +1192,8 @@ static void unpin_slot(struct kvm *kvm, int slot_id)
 				continue;
 			pfn = physp[j] >> PAGE_SHIFT;
 			page = pfn_to_page(pfn);
+			if (PageHuge(page))
+				page = compound_head(page);
 			SetPageDirty(page);
 			put_page(page);
 		}

trunk/arch/x86/kernel/kvm.c

@@ -79,6 +79,7 @@ struct kvm_task_sleep_node {
 	u32 token;
 	int cpu;
 	bool halted;
+	struct mm_struct *mm;
 };
 
 static struct kvm_task_sleep_head {
@@ -125,7 +126,9 @@ void kvm_async_pf_task_wait(u32 token)
 
 	n.token = token;
 	n.cpu = smp_processor_id();
+	n.mm = current->active_mm;
 	n.halted = idle || preempt_count() > 1;
+	atomic_inc(&n.mm->mm_count);
 	init_waitqueue_head(&n.wq);
 	hlist_add_head(&n.link, &b->list);
 	spin_unlock(&b->lock);
@@ -158,6 +161,9 @@ EXPORT_SYMBOL_GPL(kvm_async_pf_task_wait);
 static void apf_task_wake_one(struct kvm_task_sleep_node *n)
 {
 	hlist_del_init(&n->link);
+	if (!n->mm)
+		return;
+	mmdrop(n->mm);
 	if (n->halted)
 		smp_send_reschedule(n->cpu);
 	else if (waitqueue_active(&n->wq))
@@ -201,7 +207,7 @@ void kvm_async_pf_task_wake(u32 token)
 		 * async PF was not yet handled.
 		 * Add dummy entry for the token.
 		 */
-		n = kzalloc(sizeof(*n), GFP_ATOMIC);
+		n = kmalloc(sizeof(*n), GFP_ATOMIC);
 		if (!n) {
 			/*
 			 * Allocation failed! Busy wait while other cpu
@@ -213,6 +219,7 @@ void kvm_async_pf_task_wake(u32 token)
 		}
 		n->token = token;
 		n->cpu = smp_processor_id();
+		n->mm = NULL;
 		init_waitqueue_head(&n->wq);
 		hlist_add_head(&n->link, &b->list);
 	} else

trunk/arch/x86/kernel/process_64.c

@@ -423,7 +423,6 @@ void set_personality_ia32(bool x32)
 		current_thread_info()->status |= TS_COMPAT;
 	}
 }
-EXPORT_SYMBOL_GPL(set_personality_ia32);
 
 unsigned long get_wchan(struct task_struct *p)
 {

trunk/arch/x86/kernel/setup_percpu.c

@@ -185,22 +185,10 @@ void __init setup_per_cpu_areas(void)
 #endif
 	rc = -EINVAL;
 	if (pcpu_chosen_fc != PCPU_FC_PAGE) {
+		const size_t atom_size = cpu_has_pse ? PMD_SIZE : PAGE_SIZE;
 		const size_t dyn_size = PERCPU_MODULE_RESERVE +
 			PERCPU_DYNAMIC_RESERVE - PERCPU_FIRST_CHUNK_RESERVE;
-		size_t atom_size;
 
-		/*
-		 * On 64bit, use PMD_SIZE for atom_size so that embedded
-		 * percpu areas are aligned to PMD.  This, in the future,
-		 * can also allow using PMD mappings in vmalloc area.  Use
-		 * PAGE_SIZE on 32bit as vmalloc space is highly contended
-		 * and large vmalloc area allocs can easily fail.
-		 */
-#ifdef CONFIG_X86_64
-		atom_size = PMD_SIZE;
-#else
-		atom_size = PAGE_SIZE;
-#endif
 		rc = pcpu_embed_first_chunk(PERCPU_FIRST_CHUNK_RESERVE,
 					    dyn_size, atom_size,
 					    pcpu_cpu_distance,

trunk/arch/x86/kvm/x86.c

@@ -6581,7 +6581,6 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
 		kvm_inject_page_fault(vcpu, &fault);
 	}
 	vcpu->arch.apf.halted = false;
-	vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
 }
 
 bool kvm_arch_can_inject_async_page_present(struct kvm_vcpu *vcpu)