13 files changed, 143 insertions, 78 deletions

diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index 4550d247e308..c011e2296cb1 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -74,32 +74,52 @@ struct jit_ctx {
 
 int bpf_jit_enable __read_mostly;
 
-static u64 jit_get_skb_b(struct sk_buff *skb, unsigned offset)
+static inline int call_neg_helper(struct sk_buff *skb, int offset, void *ret,
+		      unsigned int size)
+{
+	void *ptr = bpf_internal_load_pointer_neg_helper(skb, offset, size);
+
+	if (!ptr)
+		return -EFAULT;
+	memcpy(ret, ptr, size);
+	return 0;
+}
+
+static u64 jit_get_skb_b(struct sk_buff *skb, int offset)
 {
 	u8 ret;
 	int err;
 
-	err = skb_copy_bits(skb, offset, &ret, 1);
+	if (offset < 0)
+		err = call_neg_helper(skb, offset, &ret, 1);
+	else
+		err = skb_copy_bits(skb, offset, &ret, 1);
 
 	return (u64)err << 32 | ret;
 }
 
-static u64 jit_get_skb_h(struct sk_buff *skb, unsigned offset)
+static u64 jit_get_skb_h(struct sk_buff *skb, int offset)
 {
 	u16 ret;
 	int err;
 
-	err = skb_copy_bits(skb, offset, &ret, 2);
+	if (offset < 0)
+		err = call_neg_helper(skb, offset, &ret, 2);
+	else
+		err = skb_copy_bits(skb, offset, &ret, 2);
 
 	return (u64)err << 32 | ntohs(ret);
 }
 
-static u64 jit_get_skb_w(struct sk_buff *skb, unsigned offset)
+static u64 jit_get_skb_w(struct sk_buff *skb, int offset)
 {
 	u32 ret;
 	int err;
 
-	err = skb_copy_bits(skb, offset, &ret, 4);
+	if (offset < 0)
+		err = call_neg_helper(skb, offset, &ret, 4);
+	else
+		err = skb_copy_bits(skb, offset, &ret, 4);
 
 	return (u64)err << 32 | ntohl(ret);
 }
@@ -536,9 +556,6 @@ static int build_body(struct jit_ctx *ctx)
 		case BPF_LD | BPF_B | BPF_ABS:
 			load_order = 0;
 load:
-			/* the interpreter will deal with the negative K */
-			if ((int)k < 0)
-				return -ENOTSUPP;
 			emit_mov_i(r_off, k, ctx);
 load_common:
 			ctx->seen |= SEEN_DATA | SEEN_CALL;
@@ -547,12 +564,24 @@ load_common:
 				emit(ARM_SUB_I(r_scratch, r_skb_hl,
 					       1 << load_order), ctx);
 				emit(ARM_CMP_R(r_scratch, r_off), ctx);
-				condt = ARM_COND_HS;
+				condt = ARM_COND_GE;
 			} else {
 				emit(ARM_CMP_R(r_skb_hl, r_off), ctx);
 				condt = ARM_COND_HI;
 			}
 
+			/*
+			 * test for negative offset, only if we are
+			 * currently scheduled to take the fast
+			 * path. this will update the flags so that
+			 * the slowpath instruction are ignored if the
+			 * offset is negative.
+			 *
+			 * for loard_order == 0 the HI condition will
+			 * make loads at offset 0 take the slow path too.
+			 */
+			_emit(condt, ARM_CMP_I(r_off, 0), ctx);
+
 			_emit(condt, ARM_ADD_R(r_scratch, r_off, r_skb_data),
 			      ctx);
 
@@ -860,9 +889,11 @@ b_epilogue:
 			off = offsetof(struct sk_buff, vlan_tci);
 			emit(ARM_LDRH_I(r_A, r_skb, off), ctx);
 			if (code == (BPF_ANC | SKF_AD_VLAN_TAG))
-				OP_IMM3(ARM_AND, r_A, r_A, VLAN_VID_MASK, ctx);
-			else
-				OP_IMM3(ARM_AND, r_A, r_A, VLAN_TAG_PRESENT, ctx);
+				OP_IMM3(ARM_AND, r_A, r_A, ~VLAN_TAG_PRESENT, ctx);
+			else {
+				OP_IMM3(ARM_LSR, r_A, r_A, 12, ctx);
+				OP_IMM3(ARM_AND, r_A, r_A, 0x1, ctx);
+			}
 			break;
 		case BPF_ANC | SKF_AD_QUEUE:
 			ctx->seen |= SEEN_SKB;
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index f860bfda454a..e16351819fed 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -585,7 +585,8 @@ ENDPROC(el0_irq)
  *
  */
 ENTRY(cpu_switch_to)
-	add	x8, x0, #THREAD_CPU_CONTEXT
+	mov	x10, #THREAD_CPU_CONTEXT
+	add	x8, x0, x10
 	mov	x9, sp
 	stp	x19, x20, [x8], #16		// store callee-saved registers
 	stp	x21, x22, [x8], #16
@@ -594,7 +595,7 @@ ENTRY(cpu_switch_to)
 	stp	x27, x28, [x8], #16
 	stp	x29, x9, [x8], #16
 	str	lr, [x8]
-	add	x8, x1, #THREAD_CPU_CONTEXT
+	add	x8, x1, x10
 	ldp	x19, x20, [x8], #16		// restore callee-saved registers
 	ldp	x21, x22, [x8], #16
 	ldp	x23, x24, [x8], #16
diff --git a/arch/arm64/kernel/irq.c b/arch/arm64/kernel/irq.c
index 240b75c0e94f..463fa2e7e34c 100644
--- a/arch/arm64/kernel/irq.c
+++ b/arch/arm64/kernel/irq.c
@@ -61,7 +61,7 @@ void __init init_IRQ(void)
 static bool migrate_one_irq(struct irq_desc *desc)
 {
 	struct irq_data *d = irq_desc_get_irq_data(desc);
-	const struct cpumask *affinity = d->affinity;
+	const struct cpumask *affinity = irq_data_get_affinity_mask(d);
 	struct irq_chip *c;
 	bool ret = false;
 
@@ -81,7 +81,7 @@ static bool migrate_one_irq(struct irq_desc *desc)
 	if (!c->irq_set_affinity)
 		pr_debug("IRQ%u: unable to set affinity\n", d->irq);
 	else if (c->irq_set_affinity(d, affinity, false) == IRQ_SET_MASK_OK && ret)
-		cpumask_copy(d->affinity, affinity);
+		cpumask_copy(irq_data_get_affinity_mask(d), affinity);
 
 	return ret;
 }
diff --git a/arch/avr32/kernel/time.c b/arch/avr32/kernel/time.c
index d0f771be9e96..a124c55733db 100644
--- a/arch/avr32/kernel/time.c
+++ b/arch/avr32/kernel/time.c
@@ -18,6 +18,7 @@
 
 #include <mach/pm.h>
 
+static bool disable_cpu_idle_poll;
 
 static cycle_t read_cycle_count(struct clocksource *cs)
 {
@@ -80,45 +81,45 @@ static int comparator_next_event(unsigned long delta,
 	return 0;
 }
 
-static void comparator_mode(enum clock_event_mode mode,
-		struct clock_event_device *evdev)
+static int comparator_shutdown(struct clock_event_device *evdev)
 {
-	switch (mode) {
-	case CLOCK_EVT_MODE_ONESHOT:
-		pr_debug("%s: start\n", evdev->name);
-		/* FALLTHROUGH */
-	case CLOCK_EVT_MODE_RESUME:
+	pr_debug("%s: %s\n", __func__, evdev->name);
+	sysreg_write(COMPARE, 0);
+
+	if (disable_cpu_idle_poll) {
+		disable_cpu_idle_poll = false;
 		/*
-		 * If we're using the COUNT and COMPARE registers we
-		 * need to force idle poll.
+		 * Only disable idle poll if we have forced that
+		 * in a previous call.
 		 */
-		cpu_idle_poll_ctrl(true);
-		break;
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_SHUTDOWN:
-		sysreg_write(COMPARE, 0);
-		pr_debug("%s: stop\n", evdev->name);
-		if (evdev->mode == CLOCK_EVT_MODE_ONESHOT ||
-		    evdev->mode == CLOCK_EVT_MODE_RESUME) {
-			/*
-			 * Only disable idle poll if we have forced that
-			 * in a previous call.
-			 */
-			cpu_idle_poll_ctrl(false);
-		}
-		break;
-	default:
-		BUG();
+		cpu_idle_poll_ctrl(false);
 	}
+	return 0;
+}
+
+static int comparator_set_oneshot(struct clock_event_device *evdev)
+{
+	pr_debug("%s: %s\n", __func__, evdev->name);
+
+	disable_cpu_idle_poll = true;
+	/*
+	 * If we're using the COUNT and COMPARE registers we
+	 * need to force idle poll.
+	 */
+	cpu_idle_poll_ctrl(true);
+
+	return 0;
 }
 
 static struct clock_event_device comparator = {
-	.name		= "avr32_comparator",
-	.features	= CLOCK_EVT_FEAT_ONESHOT,
-	.shift		= 16,
-	.rating		= 50,
-	.set_next_event	= comparator_next_event,
-	.set_mode	= comparator_mode,
+	.name			= "avr32_comparator",
+	.features		= CLOCK_EVT_FEAT_ONESHOT,
+	.shift			= 16,
+	.rating			= 50,
+	.set_next_event		= comparator_next_event,
+	.set_state_shutdown	= comparator_shutdown,
+	.set_state_oneshot	= comparator_set_oneshot,
+	.tick_resume		= comparator_set_oneshot,
 };
 
 void read_persistent_clock(struct timespec *ts)
diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c
index c7d1b9d09011..a2da259d9327 100644
--- a/arch/s390/kernel/asm-offsets.c
+++ b/arch/s390/kernel/asm-offsets.c
@@ -23,15 +23,15 @@
 
 int main(void)
 {
-	DEFINE(__THREAD_info, offsetof(struct task_struct, stack));
-	DEFINE(__THREAD_ksp, offsetof(struct task_struct, thread.ksp));
-	DEFINE(__THREAD_mm_segment, offsetof(struct task_struct, thread.mm_segment));
-	BLANK();
+	DEFINE(__TASK_thread_info, offsetof(struct task_struct, stack));
+	DEFINE(__TASK_thread, offsetof(struct task_struct, thread));
 	DEFINE(__TASK_pid, offsetof(struct task_struct, pid));
 	BLANK();
-	DEFINE(__THREAD_per_cause, offsetof(struct task_struct, thread.per_event.cause));
-	DEFINE(__THREAD_per_address, offsetof(struct task_struct, thread.per_event.address));
-	DEFINE(__THREAD_per_paid, offsetof(struct task_struct, thread.per_event.paid));
+	DEFINE(__THREAD_ksp, offsetof(struct thread_struct, ksp));
+	DEFINE(__THREAD_per_cause, offsetof(struct thread_struct, per_event.cause));
+	DEFINE(__THREAD_per_address, offsetof(struct thread_struct, per_event.address));
+	DEFINE(__THREAD_per_paid, offsetof(struct thread_struct, per_event.paid));
+	DEFINE(__THREAD_trap_tdb, offsetof(struct thread_struct, trap_tdb));
 	BLANK();
 	DEFINE(__TI_task, offsetof(struct thread_info, task));
 	DEFINE(__TI_flags, offsetof(struct thread_info, flags));
@@ -176,7 +176,6 @@ int main(void)
 	DEFINE(__LC_VDSO_PER_CPU, offsetof(struct _lowcore, vdso_per_cpu_data));
 	DEFINE(__LC_GMAP, offsetof(struct _lowcore, gmap));
 	DEFINE(__LC_PGM_TDB, offsetof(struct _lowcore, pgm_tdb));
-	DEFINE(__THREAD_trap_tdb, offsetof(struct task_struct, thread.trap_tdb));
 	DEFINE(__GMAP_ASCE, offsetof(struct gmap, asce));
 	DEFINE(__SIE_PROG0C, offsetof(struct kvm_s390_sie_block, prog0c));
 	DEFINE(__SIE_PROG20, offsetof(struct kvm_s390_sie_block, prog20));
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index 3238893c9d4f..84062e7a77da 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -178,17 +178,21 @@ _PIF_WORK	= (_PIF_PER_TRAP)
  */
 ENTRY(__switch_to)
 	stmg	%r6,%r15,__SF_GPRS(%r15)	# store gprs of prev task
-	stg	%r15,__THREAD_ksp(%r2)		# store kernel stack of prev
-	lg	%r4,__THREAD_info(%r2)		# get thread_info of prev
-	lg	%r5,__THREAD_info(%r3)		# get thread_info of next
+	lgr	%r1,%r2
+	aghi	%r1,__TASK_thread		# thread_struct of prev task
+	lg	%r4,__TASK_thread_info(%r2)	# get thread_info of prev
+	lg	%r5,__TASK_thread_info(%r3)	# get thread_info of next
+	stg	%r15,__THREAD_ksp(%r1)		# store kernel stack of prev
+	lgr	%r1,%r3
+	aghi	%r1,__TASK_thread		# thread_struct of next task
 	lgr	%r15,%r5
 	aghi	%r15,STACK_INIT			# end of kernel stack of next
 	stg	%r3,__LC_CURRENT		# store task struct of next
 	stg	%r5,__LC_THREAD_INFO		# store thread info of next
 	stg	%r15,__LC_KERNEL_STACK		# store end of kernel stack
+	lg	%r15,__THREAD_ksp(%r1)		# load kernel stack of next
 	lctl	%c4,%c4,__TASK_pid(%r3)		# load pid to control reg. 4
 	mvc	__LC_CURRENT_PID+4(4,%r0),__TASK_pid(%r3) # store pid of next
-	lg	%r15,__THREAD_ksp(%r3)		# load kernel stack of next
 	lmg	%r6,%r15,__SF_GPRS(%r15)	# load gprs of next task
 	br	%r14
 
@@ -417,6 +421,7 @@ ENTRY(pgm_check_handler)
 	LAST_BREAK %r14
 	lg	%r15,__LC_KERNEL_STACK
 	lg	%r14,__TI_task(%r12)
+	aghi	%r14,__TASK_thread	# pointer to thread_struct
 	lghi	%r13,__LC_PGM_TDB
 	tm	__LC_PGM_ILC+2,0x02	# check for transaction abort
 	jz	2f
diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c
index 4d96c9f53455..7bea81d8a363 100644
--- a/arch/s390/kernel/traps.c
+++ b/arch/s390/kernel/traps.c
@@ -259,7 +259,7 @@ void vector_exception(struct pt_regs *regs)
 	}
 
 	/* get vector interrupt code from fpc */
-	asm volatile("stfpc %0" : "=m" (current->thread.fp_regs.fpc));
+	asm volatile("stfpc %0" : "=Q" (current->thread.fp_regs.fpc));
 	vic = (current->thread.fp_regs.fpc & 0xf00) >> 8;
 	switch (vic) {
 	case 1: /* invalid vector operation */
@@ -297,7 +297,7 @@ void data_exception(struct pt_regs *regs)
 
 	location = get_trap_ip(regs);
 
-	asm volatile("stfpc %0" : "=m" (current->thread.fp_regs.fpc));
+	asm volatile("stfpc %0" : "=Q" (current->thread.fp_regs.fpc));
 	/* Check for vector register enablement */
 	if (MACHINE_HAS_VX && !current->thread.vxrs &&
 	    (current->thread.fp_regs.fpc & FPC_DXC_MASK) == 0xfe00) {
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index a4ae82eb82aa..cd54147cb365 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -354,7 +354,7 @@ struct kvm_xcrs {
 struct kvm_sync_regs {
 };
 
-#define KVM_QUIRK_LINT0_REENABLED	(1 << 0)
-#define KVM_QUIRK_CD_NW_CLEARED		(1 << 1)
+#define KVM_X86_QUIRK_LINT0_REENABLED	(1 << 0)
+#define KVM_X86_QUIRK_CD_NW_CLEARED	(1 << 1)
 
 #endif /* _ASM_X86_KVM_H */
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 954e98a8c2e3..2a5ca97c263b 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1595,7 +1595,7 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event)
 	for (i = 0; i < APIC_LVT_NUM; i++)
 		apic_set_reg(apic, APIC_LVTT + 0x10 * i, APIC_LVT_MASKED);
 	apic_update_lvtt(apic);
-	if (!(vcpu->kvm->arch.disabled_quirks & KVM_QUIRK_LINT0_REENABLED))
+	if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_LINT0_REENABLED))
 		apic_set_reg(apic, APIC_LVT0,
 			     SET_APIC_DELIVERY_MODE(0, APIC_MODE_EXTINT));
 	apic_manage_nmi_watchdog(apic, kvm_apic_get_reg(apic, APIC_LVT0));
diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c
index de1d2d8062e2..dc0a84a6f309 100644
--- a/arch/x86/kvm/mtrr.c
+++ b/arch/x86/kvm/mtrr.c
@@ -120,6 +120,16 @@ static u8 mtrr_default_type(struct kvm_mtrr *mtrr_state)
 	return mtrr_state->deftype & IA32_MTRR_DEF_TYPE_TYPE_MASK;
 }
 
+static u8 mtrr_disabled_type(void)
+{
+	/*
+	 * Intel SDM 11.11.2.2: all MTRRs are disabled when
+	 * IA32_MTRR_DEF_TYPE.E bit is cleared, and the UC
+	 * memory type is applied to all of physical memory.
+	 */
+	return MTRR_TYPE_UNCACHABLE;
+}
+
 /*
 * Three terms are used in the following code:
 * - segment, it indicates the address segments covered by fixed MTRRs.
@@ -434,6 +444,8 @@ struct mtrr_iter {
 
 	/* output fields. */
 	int mem_type;
+	/* mtrr is completely disabled? */
+	bool mtrr_disabled;
 	/* [start, end) is not fully covered in MTRRs? */
 	bool partial_map;
 
@@ -549,7 +561,7 @@ static void mtrr_lookup_var_next(struct mtrr_iter *iter)
 static void mtrr_lookup_start(struct mtrr_iter *iter)
 {
 	if (!mtrr_is_enabled(iter->mtrr_state)) {
-		iter->partial_map = true;
+		iter->mtrr_disabled = true;
 		return;
 	}
 
@@ -563,6 +575,7 @@ static void mtrr_lookup_init(struct mtrr_iter *iter,
 	iter->mtrr_state = mtrr_state;
 	iter->start = start;
 	iter->end = end;
+	iter->mtrr_disabled = false;
 	iter->partial_map = false;
 	iter->fixed = false;
 	iter->range = NULL;
@@ -656,15 +669,19 @@ u8 kvm_mtrr_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn)
 		return MTRR_TYPE_WRBACK;
 	}
 
-	/* It is not covered by MTRRs. */
-	if (iter.partial_map) {
-		/*
-		 * We just check one page, partially covered by MTRRs is
-		 * impossible.
-		 */
-		WARN_ON(type != -1);
-		type = mtrr_default_type(mtrr_state);
-	}
+	if (iter.mtrr_disabled)
+		return mtrr_disabled_type();
+
+	/*
+	 * We just check one page, partially covered by MTRRs is
+	 * impossible.
+	 */
+	WARN_ON(iter.partial_map);
+
+	/* not contained in any MTRRs. */
+	if (type == -1)
+		return mtrr_default_type(mtrr_state);
+
 	return type;
 }
 EXPORT_SYMBOL_GPL(kvm_mtrr_get_guest_memory_type);
@@ -689,6 +706,9 @@ bool kvm_mtrr_check_gfn_range_consistency(struct kvm_vcpu *vcpu, gfn_t gfn,
 			return false;
 	}
 
+	if (iter.mtrr_disabled)
+		return true;
+
 	if (!iter.partial_map)
 		return true;
 
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index bbc678a66b18..8e0c0844c6b9 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -1672,7 +1672,7 @@ static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 	 * does not do it - this results in some delay at
 	 * reboot
 	 */
-	if (!(vcpu->kvm->arch.disabled_quirks & KVM_QUIRK_CD_NW_CLEARED))
+	if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED))
 		cr0 &= ~(X86_CR0_CD | X86_CR0_NW);
 	svm->vmcb->save.cr0 = cr0;
 	mark_dirty(svm->vmcb, VMCB_CR);
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 5b4e9384717a..83b7b5cd75d5 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -8650,7 +8650,10 @@ static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
 
 	if (kvm_read_cr0(vcpu) & X86_CR0_CD) {
 		ipat = VMX_EPT_IPAT_BIT;
-		cache = MTRR_TYPE_UNCACHABLE;
+		if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED))
+			cache = MTRR_TYPE_WRBACK;
+		else
+			cache = MTRR_TYPE_UNCACHABLE;
 		goto exit;
 	}
 
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index edc8cdcd786b..0ca2f3e4803c 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -147,6 +147,11 @@ static inline void kvm_register_writel(struct kvm_vcpu *vcpu,
 	return kvm_register_write(vcpu, reg, val);
 }
 
+static inline bool kvm_check_has_quirk(struct kvm *kvm, u64 quirk)
+{
+	return !(kvm->arch.disabled_quirks & quirk);
+}
+
 void kvm_before_handle_nmi(struct kvm_vcpu *vcpu);
 void kvm_after_handle_nmi(struct kvm_vcpu *vcpu);
 void kvm_set_pending_timer(struct kvm_vcpu *vcpu);