Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

11 files changed, 113 insertions, 76 deletions

diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h
index 548da3aa0a3..d58fc4e4149 100644
--- a/arch/powerpc/include/asm/exception-64s.h
+++ b/arch/powerpc/include/asm/exception-64s.h
@@ -288,13 +288,6 @@ 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
 
diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index aa795ccef29..fd07f43d662 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -81,12 +81,13 @@ struct kvmppc_vcpu_book3s {
 	u64 sdr1;
 	u64 hior;
 	u64 msr_mask;
-	u64 vsid_next;
 #ifdef CONFIG_PPC_BOOK3S_32
 	u32 vsid_pool[VSID_POOL_SIZE];
+	u32 vsid_next;
 #else
-	u64 vsid_first;
-	u64 vsid_max;
+	u64 proto_vsid_first;
+	u64 proto_vsid_max;
+	u64 proto_vsid_next;
 #endif
 	int context_id[SID_CONTEXTS];
 
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index f8a7a1a1a9f..ef2074c3e90 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -588,23 +588,19 @@ _GLOBAL(ret_from_except_lite)
 fast_exc_return_irq:
 restore:
 	/*
-	 * This is the main kernel exit path, we first check if we
-	 * have to change our interrupt state.
+	 * This is the main kernel exit path. First we check if we
+	 * are about to re-enable interrupts
 	 */
 	ld	r5,SOFTE(r1)
 	lbz	r6,PACASOFTIRQEN(r13)
-	cmpwi	cr1,r5,0
-	cmpw	cr0,r5,r6
-	beq	cr0,4f
+	cmpwi	cr0,r5,0
+	beq	restore_irq_off
 
-	/* We do, handle disable first, which is easy */
-	bne	cr1,3f;
- 	li	r0,0
-	stb	r0,PACASOFTIRQEN(r13);
-	TRACE_DISABLE_INTS
-	b	4f
+	/* We are enabling, were we already enabled ? Yes, just return */
+	cmpwi	cr0,r6,1
+	beq	cr0,do_restore
 
-3:	/*
+	/*
 	 * We are about to soft-enable interrupts (we are hard disabled
 	 * at this point). We check if there's anything that needs to
 	 * be replayed first.
@@ -626,7 +622,7 @@ restore_no_replay:
 	/*
 	 * Final return path. BookE is handled in a different file
 	 */
-4:
+do_restore:
 #ifdef CONFIG_PPC_BOOK3E
 	b	.exception_return_book3e
 #else
@@ -700,6 +696,25 @@ fast_exception_return:
 #endif /* CONFIG_PPC_BOOK3E */
 
 	/*
+	 * We are returning to a context with interrupts soft disabled.
+	 *
+	 * However, we may also about to hard enable, so we need to
+	 * make sure that in this case, we also clear PACA_IRQ_HARD_DIS
+	 * or that bit can get out of sync and bad things will happen
+	 */
+restore_irq_off:
+	ld	r3,_MSR(r1)
+	lbz	r7,PACAIRQHAPPENED(r13)
+	andi.	r0,r3,MSR_EE
+	beq	1f
+	rlwinm	r7,r7,0,~PACA_IRQ_HARD_DIS
+	stb	r7,PACAIRQHAPPENED(r13)
+1:	li	r0,0
+	stb	r0,PACASOFTIRQEN(r13);
+	TRACE_DISABLE_INTS
+	b	do_restore
+
+	/*
 	 * Something did happen, check if a re-emit is needed
 	 * (this also clears paca->irq_happened)
 	 */
@@ -748,6 +763,9 @@ restore_check_irq_replay:
 #endif /* CONFIG_PPC_BOOK3E */
 1:	b	.ret_from_except /* What else to do here ? */
  
+
+
+3:
 do_work:
 #ifdef CONFIG_PREEMPT
 	andi.	r0,r3,MSR_PR	/* Returning to user mode? */
@@ -767,16 +785,6 @@ 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)
@@ -787,14 +795,6 @@ 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
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index cb705fdbb45..8f880bc77c5 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/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
 
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 43eb74fcedd..641da9e868c 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -229,6 +229,19 @@ notrace void arch_local_irq_restore(unsigned long en)
 	 */
 	if (unlikely(irq_happened != PACA_IRQ_HARD_DIS))
 		__hard_irq_disable();
+#ifdef CONFIG_TRACE_IRQFLAG
+	else {
+		/*
+		 * We should already be hard disabled here. We had bugs
+		 * where that wasn't the case so let's dbl check it and
+		 * warn if we are wrong. Only do that when IRQ tracing
+		 * is enabled as mfmsr() can be costly.
+		 */
+		if (WARN_ON(mfmsr() & MSR_EE))
+			__hard_irq_disable();
+	}
+#endif /* CONFIG_TRACE_IRQFLAG */
+
 	set_soft_enabled(0);
 
 	/*
@@ -260,11 +273,17 @@ 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())
+	if (irqs_disabled()) {
+		local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
 		local_irq_enable();
+	} else
+		__hard_irq_enable();
 }
 
 #endif /* CONFIG_PPC64 */
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 6aa0c663e24..158972341a2 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/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_irq_disabled_regs(regs))
+	if (arch_irqs_disabled() && !arch_irq_disabled_regs(regs))
 		local_irq_enable();
 
 	memset(&info, 0, sizeof(info));
@@ -1019,7 +1019,9 @@ void __kprobes program_check_exception(struct pt_regs *regs)
 		return;
 	}
 
-	local_irq_enable();
+	/* We restore the interrupt state now */
+	if (!arch_irq_disabled_regs(regs))
+		local_irq_enable();
 
 #ifdef CONFIG_MATH_EMULATION
 	/* (reason & REASON_ILLEGAL) would be the obvious thing here,
@@ -1069,6 +1071,10 @@ 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);
diff --git a/arch/powerpc/kvm/book3s_64_mmu_host.c b/arch/powerpc/kvm/book3s_64_mmu_host.c
index 6f87f39a1ac..10fc8ec9d2a 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_host.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_host.c
@@ -194,14 +194,14 @@ static struct kvmppc_sid_map *create_sid_map(struct kvm_vcpu *vcpu, u64 gvsid)
 	backwards_map = !backwards_map;
 
 	/* Uh-oh ... out of mappings. Let's flush! */
-	if (vcpu_book3s->vsid_next == vcpu_book3s->vsid_max) {
-		vcpu_book3s->vsid_next = vcpu_book3s->vsid_first;
+	if (vcpu_book3s->proto_vsid_next == vcpu_book3s->proto_vsid_max) {
+		vcpu_book3s->proto_vsid_next = vcpu_book3s->proto_vsid_first;
 		memset(vcpu_book3s->sid_map, 0,
 		       sizeof(struct kvmppc_sid_map) * SID_MAP_NUM);
 		kvmppc_mmu_pte_flush(vcpu, 0, 0);
 		kvmppc_mmu_flush_segments(vcpu);
 	}
-	map->host_vsid = vcpu_book3s->vsid_next++;
+	map->host_vsid = vsid_scramble(vcpu_book3s->proto_vsid_next++, 256M);
 
 	map->guest_vsid = gvsid;
 	map->valid = true;
@@ -319,9 +319,10 @@ int kvmppc_mmu_init(struct kvm_vcpu *vcpu)
 		return -1;
 	vcpu3s->context_id[0] = err;
 
-	vcpu3s->vsid_max = ((vcpu3s->context_id[0] + 1) << USER_ESID_BITS) - 1;
-	vcpu3s->vsid_first = vcpu3s->context_id[0] << USER_ESID_BITS;
-	vcpu3s->vsid_next = vcpu3s->vsid_first;
+	vcpu3s->proto_vsid_max = ((vcpu3s->context_id[0] + 1)
+				  << USER_ESID_BITS) - 1;
+	vcpu3s->proto_vsid_first = vcpu3s->context_id[0] << USER_ESID_BITS;
+	vcpu3s->proto_vsid_next = vcpu3s->proto_vsid_first;
 
 	kvmppc_mmu_hpte_init(vcpu);
 
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index ddc485a529f..c3beaeef3f6 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -258,6 +258,8 @@ 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;
 			}
 		}
@@ -281,11 +283,8 @@ static long kvmppc_get_guest_page(struct kvm *kvm, unsigned long gfn,
 	err = 0;
 
  out:
-	if (got) {
-		if (PageHuge(page))
-			page = compound_head(page);
+	if (got)
 		put_page(page);
-	}
 	return err;
 
  up_err:
@@ -678,8 +677,15 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		SetPageDirty(page);
 
  out_put:
-	if (page)
-		put_page(page);
+	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]);
+	}
 	return ret;
 
  out_unlock:
@@ -979,6 +985,7 @@ 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);
@@ -991,8 +998,6 @@ 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;
@@ -1003,7 +1008,6 @@ void kvmppc_unpin_guest_page(struct kvm *kvm, void *va)
 {
 	struct page *page = virt_to_page(va);
 
-	page = compound_head(page);
 	put_page(page);
 }
 
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 01294a5099d..108d1f58017 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1192,8 +1192,6 @@ 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);
 		}
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index def880aea63..cec4daddbf3 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -463,6 +463,7 @@ long kvmppc_h_bulk_remove(struct kvm_vcpu *vcpu)
 				/* insert R and C bits from PTE */
 				rcbits = rev->guest_rpte & (HPTE_R_R|HPTE_R_C);
 				args[j] |= rcbits << (56 - 5);
+				hp[0] = 0;
 				continue;
 			}
 
diff --git a/arch/powerpc/kvm/book3s_segment.S b/arch/powerpc/kvm/book3s_segment.S
index 0676ae249b9..6e6e9cef34a 100644
--- a/arch/powerpc/kvm/book3s_segment.S
+++ b/arch/powerpc/kvm/book3s_segment.S
@@ -197,7 +197,8 @@ kvmppc_interrupt:
 	/* Save guest PC and MSR */
 #ifdef CONFIG_PPC64
 BEGIN_FTR_SECTION
-	andi.	r0,r12,0x2
+	andi.	r0, r12, 0x2
+	cmpwi	cr1, r0, 0
 	beq	1f
 	mfspr	r3,SPRN_HSRR0
 	mfspr	r4,SPRN_HSRR1
@@ -250,6 +251,12 @@ END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
 	beq	ld_last_prev_inst
 	cmpwi	r12, BOOK3S_INTERRUPT_ALIGNMENT
 	beq-	ld_last_inst
+#ifdef CONFIG_PPC64
+BEGIN_FTR_SECTION
+	cmpwi	r12, BOOK3S_INTERRUPT_H_EMUL_ASSIST
+	beq-	ld_last_inst
+END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
+#endif
 
 	b	no_ld_last_inst
 
@@ -316,23 +323,17 @@ no_dcbz32_off:
 	 * Having set up SRR0/1 with the address where we want
 	 * to continue with relocation on (potentially in module
 	 * space), we either just go straight there with rfi[d],
-	 * or we jump to an interrupt handler with bctr if there
-	 * is an interrupt to be handled first.  In the latter
-	 * case, the rfi[d] at the end of the interrupt handler
-	 * will get us back to where we want to continue.
+	 * or we jump to an interrupt handler if there is an
+	 * interrupt to be handled first.  In the latter case,
+	 * the rfi[d] at the end of the interrupt handler will
+	 * get us back to where we want to continue.
 	 */
 
-	cmpwi	r12, BOOK3S_INTERRUPT_EXTERNAL
-	beq	1f
-	cmpwi	r12, BOOK3S_INTERRUPT_DECREMENTER
-	beq	1f
-	cmpwi	r12, BOOK3S_INTERRUPT_PERFMON
-1:	mtctr	r12
-
 	/* Register usage at this point:
 	 *
 	 * R1       = host R1
 	 * R2       = host R2
+	 * R10      = raw exit handler id
 	 * R12      = exit handler id
 	 * R13      = shadow vcpu (32-bit) or PACA (64-bit)
 	 * SVCPU.*  = guest *
@@ -342,12 +343,25 @@ no_dcbz32_off:
 	PPC_LL	r6, HSTATE_HOST_MSR(r13)
 	PPC_LL	r8, HSTATE_VMHANDLER(r13)
 
-	/* Restore host msr -> SRR1 */
+#ifdef CONFIG_PPC64
+BEGIN_FTR_SECTION
+	beq	cr1, 1f
+	mtspr	SPRN_HSRR1, r6
+	mtspr	SPRN_HSRR0, r8
+END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
+#endif
+1:	/* Restore host msr -> SRR1 */
 	mtsrr1	r6
 	/* Load highmem handler address */
 	mtsrr0	r8
 
 	/* RFI into the highmem handler, or jump to interrupt handler */
-	beqctr
+	cmpwi	r12, BOOK3S_INTERRUPT_EXTERNAL
+	beqa	BOOK3S_INTERRUPT_EXTERNAL
+	cmpwi	r12, BOOK3S_INTERRUPT_DECREMENTER
+	beqa	BOOK3S_INTERRUPT_DECREMENTER
+	cmpwi	r12, BOOK3S_INTERRUPT_PERFMON
+	beqa	BOOK3S_INTERRUPT_PERFMON
+
 	RFI
 kvmppc_handler_trampoline_exit_end: