Merge tag 'mvebu-fixes-4.12-1' of git://git.infradead.org/linux-mvebu into fixes

mvebu fixes for 4.12

Fix the interrupt description of the crypto node for device tree of
the Armada 7K/8K SoCs

* tag 'mvebu-fixes-4.12-1' of git://git.infradead.org/linux-mvebu: (316 commits)
  arm64: marvell: dts: fix interrupts in 7k/8k crypto nodes
  + Linux 4.12-rc2

Signed-off-by: Olof Johansson <olof@lixom.net>

55 files changed, 449 insertions, 237 deletions

diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c
index 9ec56dc97374..ce93124a850b 100644
--- a/arch/alpha/kernel/osf_sys.c
+++ b/arch/alpha/kernel/osf_sys.c
@@ -1201,8 +1201,10 @@ SYSCALL_DEFINE4(osf_wait4, pid_t, pid, int __user *, ustatus, int, options,
 	if (!access_ok(VERIFY_WRITE, ur, sizeof(*ur)))
 		return -EFAULT;
 
-	err = 0;
-	err |= put_user(status, ustatus);
+	err = put_user(status, ustatus);
+	if (ret < 0)
+		return err ? err : ret;
+
 	err |= __put_user(r.ru_utime.tv_sec, &ur->ru_utime.tv_sec);
 	err |= __put_user(r.ru_utime.tv_usec, &ur->ru_utime.tv_usec);
 	err |= __put_user(r.ru_stime.tv_sec, &ur->ru_stime.tv_sec);
diff --git a/arch/arm/include/asm/kvm_coproc.h b/arch/arm/include/asm/kvm_coproc.h
index 4917c2f7e459..e74ab0fbab79 100644
--- a/arch/arm/include/asm/kvm_coproc.h
+++ b/arch/arm/include/asm/kvm_coproc.h
@@ -31,7 +31,8 @@ void kvm_register_target_coproc_table(struct kvm_coproc_target_table *table);
 int kvm_handle_cp10_id(struct kvm_vcpu *vcpu, struct kvm_run *run);
 int kvm_handle_cp_0_13_access(struct kvm_vcpu *vcpu, struct kvm_run *run);
 int kvm_handle_cp14_load_store(struct kvm_vcpu *vcpu, struct kvm_run *run);
-int kvm_handle_cp14_access(struct kvm_vcpu *vcpu, struct kvm_run *run);
+int kvm_handle_cp14_32(struct kvm_vcpu *vcpu, struct kvm_run *run);
+int kvm_handle_cp14_64(struct kvm_vcpu *vcpu, struct kvm_run *run);
 int kvm_handle_cp15_32(struct kvm_vcpu *vcpu, struct kvm_run *run);
 int kvm_handle_cp15_64(struct kvm_vcpu *vcpu, struct kvm_run *run);
 
diff --git a/arch/arm/kvm/coproc.c b/arch/arm/kvm/coproc.c
index 2c14b69511e9..6d1d2e26dfe5 100644
--- a/arch/arm/kvm/coproc.c
+++ b/arch/arm/kvm/coproc.c
@@ -32,6 +32,7 @@
 #include <asm/vfp.h>
 #include "../vfp/vfpinstr.h"
 
+#define CREATE_TRACE_POINTS
 #include "trace.h"
 #include "coproc.h"
 
@@ -111,12 +112,6 @@ int kvm_handle_cp14_load_store(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	return 1;
 }
 
-int kvm_handle_cp14_access(struct kvm_vcpu *vcpu, struct kvm_run *run)
-{
-	kvm_inject_undefined(vcpu);
-	return 1;
-}
-
 static void reset_mpidr(struct kvm_vcpu *vcpu, const struct coproc_reg *r)
 {
 	/*
@@ -284,7 +279,7 @@ static bool access_gic_sre(struct kvm_vcpu *vcpu,
  * must always support PMCCNTR (the cycle counter): we just RAZ/WI for
  * all PM registers, which doesn't crash the guest kernel at least.
  */
-static bool pm_fake(struct kvm_vcpu *vcpu,
+static bool trap_raz_wi(struct kvm_vcpu *vcpu,
 		    const struct coproc_params *p,
 		    const struct coproc_reg *r)
 {
@@ -294,19 +289,19 @@ static bool pm_fake(struct kvm_vcpu *vcpu,
 		return read_zero(vcpu, p);
 }
 
-#define access_pmcr pm_fake
-#define access_pmcntenset pm_fake
-#define access_pmcntenclr pm_fake
-#define access_pmovsr pm_fake
-#define access_pmselr pm_fake
-#define access_pmceid0 pm_fake
-#define access_pmceid1 pm_fake
-#define access_pmccntr pm_fake
-#define access_pmxevtyper pm_fake
-#define access_pmxevcntr pm_fake
-#define access_pmuserenr pm_fake
-#define access_pmintenset pm_fake
-#define access_pmintenclr pm_fake
+#define access_pmcr trap_raz_wi
+#define access_pmcntenset trap_raz_wi
+#define access_pmcntenclr trap_raz_wi
+#define access_pmovsr trap_raz_wi
+#define access_pmselr trap_raz_wi
+#define access_pmceid0 trap_raz_wi
+#define access_pmceid1 trap_raz_wi
+#define access_pmccntr trap_raz_wi
+#define access_pmxevtyper trap_raz_wi
+#define access_pmxevcntr trap_raz_wi
+#define access_pmuserenr trap_raz_wi
+#define access_pmintenset trap_raz_wi
+#define access_pmintenclr trap_raz_wi
 
 /* Architected CP15 registers.
  * CRn denotes the primary register number, but is copied to the CRm in the
@@ -532,12 +527,7 @@ static int emulate_cp15(struct kvm_vcpu *vcpu,
 	return 1;
 }
 
-/**
- * kvm_handle_cp15_64 -- handles a mrrc/mcrr trap on a guest CP15 access
- * @vcpu: The VCPU pointer
- * @run:  The kvm_run struct
- */
-int kvm_handle_cp15_64(struct kvm_vcpu *vcpu, struct kvm_run *run)
+static struct coproc_params decode_64bit_hsr(struct kvm_vcpu *vcpu)
 {
 	struct coproc_params params;
 
@@ -551,9 +541,38 @@ int kvm_handle_cp15_64(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	params.Rt2 = (kvm_vcpu_get_hsr(vcpu) >> 10) & 0xf;
 	params.CRm = 0;
 
+	return params;
+}
+
+/**
+ * kvm_handle_cp15_64 -- handles a mrrc/mcrr trap on a guest CP15 access
+ * @vcpu: The VCPU pointer
+ * @run:  The kvm_run struct
+ */
+int kvm_handle_cp15_64(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	struct coproc_params params = decode_64bit_hsr(vcpu);
+
 	return emulate_cp15(vcpu, &params);
 }
 
+/**
+ * kvm_handle_cp14_64 -- handles a mrrc/mcrr trap on a guest CP14 access
+ * @vcpu: The VCPU pointer
+ * @run:  The kvm_run struct
+ */
+int kvm_handle_cp14_64(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	struct coproc_params params = decode_64bit_hsr(vcpu);
+
+	/* raz_wi cp14 */
+	trap_raz_wi(vcpu, &params, NULL);
+
+	/* handled */
+	kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
+	return 1;
+}
+
 static void reset_coproc_regs(struct kvm_vcpu *vcpu,
 			      const struct coproc_reg *table, size_t num)
 {
@@ -564,12 +583,7 @@ static void reset_coproc_regs(struct kvm_vcpu *vcpu,
 			table[i].reset(vcpu, &table[i]);
 }
 
-/**
- * kvm_handle_cp15_32 -- handles a mrc/mcr trap on a guest CP15 access
- * @vcpu: The VCPU pointer
- * @run:  The kvm_run struct
- */
-int kvm_handle_cp15_32(struct kvm_vcpu *vcpu, struct kvm_run *run)
+static struct coproc_params decode_32bit_hsr(struct kvm_vcpu *vcpu)
 {
 	struct coproc_params params;
 
@@ -583,9 +597,37 @@ int kvm_handle_cp15_32(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	params.Op2 = (kvm_vcpu_get_hsr(vcpu) >> 17) & 0x7;
 	params.Rt2 = 0;
 
+	return params;
+}
+
+/**
+ * kvm_handle_cp15_32 -- handles a mrc/mcr trap on a guest CP15 access
+ * @vcpu: The VCPU pointer
+ * @run:  The kvm_run struct
+ */
+int kvm_handle_cp15_32(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	struct coproc_params params = decode_32bit_hsr(vcpu);
 	return emulate_cp15(vcpu, &params);
 }
 
+/**
+ * kvm_handle_cp14_32 -- handles a mrc/mcr trap on a guest CP14 access
+ * @vcpu: The VCPU pointer
+ * @run:  The kvm_run struct
+ */
+int kvm_handle_cp14_32(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	struct coproc_params params = decode_32bit_hsr(vcpu);
+
+	/* raz_wi cp14 */
+	trap_raz_wi(vcpu, &params, NULL);
+
+	/* handled */
+	kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
+	return 1;
+}
+
 /******************************************************************************
  * Userspace API
  *****************************************************************************/
diff --git a/arch/arm/kvm/handle_exit.c b/arch/arm/kvm/handle_exit.c
index 5fd7968cdae9..f86a9aaef462 100644
--- a/arch/arm/kvm/handle_exit.c
+++ b/arch/arm/kvm/handle_exit.c
@@ -95,9 +95,9 @@ static exit_handle_fn arm_exit_handlers[] = {
 	[HSR_EC_WFI]		= kvm_handle_wfx,
 	[HSR_EC_CP15_32]	= kvm_handle_cp15_32,
 	[HSR_EC_CP15_64]	= kvm_handle_cp15_64,
-	[HSR_EC_CP14_MR]	= kvm_handle_cp14_access,
+	[HSR_EC_CP14_MR]	= kvm_handle_cp14_32,
 	[HSR_EC_CP14_LS]	= kvm_handle_cp14_load_store,
-	[HSR_EC_CP14_64]	= kvm_handle_cp14_access,
+	[HSR_EC_CP14_64]	= kvm_handle_cp14_64,
 	[HSR_EC_CP_0_13]	= kvm_handle_cp_0_13_access,
 	[HSR_EC_CP10_ID]	= kvm_handle_cp10_id,
 	[HSR_EC_HVC]		= handle_hvc,
diff --git a/arch/arm/kvm/hyp/Makefile b/arch/arm/kvm/hyp/Makefile
index 3023bb530edf..8679405b0b2b 100644
--- a/arch/arm/kvm/hyp/Makefile
+++ b/arch/arm/kvm/hyp/Makefile
@@ -2,6 +2,8 @@
 # Makefile for Kernel-based Virtual Machine module, HYP part
 #
 
+ccflags-y += -fno-stack-protector
+
 KVM=../../../../virt/kvm
 
 obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/vgic-v2-sr.o
diff --git a/arch/arm/kvm/hyp/switch.c b/arch/arm/kvm/hyp/switch.c
index 92678b7bd046..624a510d31df 100644
--- a/arch/arm/kvm/hyp/switch.c
+++ b/arch/arm/kvm/hyp/switch.c
@@ -48,7 +48,9 @@ static void __hyp_text __activate_traps(struct kvm_vcpu *vcpu, u32 *fpexc_host)
 	write_sysreg(HSTR_T(15), HSTR);
 	write_sysreg(HCPTR_TTA | HCPTR_TCP(10) | HCPTR_TCP(11), HCPTR);
 	val = read_sysreg(HDCR);
-	write_sysreg(val | HDCR_TPM | HDCR_TPMCR, HDCR);
+	val |= HDCR_TPM | HDCR_TPMCR; /* trap performance monitors */
+	val |= HDCR_TDRA | HDCR_TDOSA | HDCR_TDA; /* trap debug regs */
+	write_sysreg(val, HDCR);
 }
 
 static void __hyp_text __deactivate_traps(struct kvm_vcpu *vcpu)
diff --git a/arch/arm/kvm/trace.h b/arch/arm/kvm/trace.h
index fc0943776db2..b0d10648c486 100644
--- a/arch/arm/kvm/trace.h
+++ b/arch/arm/kvm/trace.h
@@ -1,5 +1,5 @@
-#if !defined(_TRACE_KVM_H) || defined(TRACE_HEADER_MULTI_READ)
-#define _TRACE_KVM_H
+#if !defined(_TRACE_ARM_KVM_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_ARM_KVM_H
 
 #include <linux/tracepoint.h>
 
@@ -74,10 +74,10 @@ TRACE_EVENT(kvm_hvc,
 		  __entry->vcpu_pc, __entry->r0, __entry->imm)
 );
 
-#endif /* _TRACE_KVM_H */
+#endif /* _TRACE_ARM_KVM_H */
 
 #undef TRACE_INCLUDE_PATH
-#define TRACE_INCLUDE_PATH arch/arm/kvm
+#define TRACE_INCLUDE_PATH .
 #undef TRACE_INCLUDE_FILE
 #define TRACE_INCLUDE_FILE trace
 
diff --git a/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi b/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi
index ac8df5201cd6..b4bc42ece754 100644
--- a/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi
@@ -231,8 +231,7 @@
 			cpm_crypto: crypto@800000 {
 				compatible = "inside-secure,safexcel-eip197";
 				reg = <0x800000 0x200000>;
-				interrupts = <GIC_SPI 34 (IRQ_TYPE_EDGE_RISING
-				| IRQ_TYPE_LEVEL_HIGH)>,
+				interrupts = <GIC_SPI 34 IRQ_TYPE_LEVEL_HIGH>,
 					     <GIC_SPI 54 IRQ_TYPE_LEVEL_HIGH>,
 					     <GIC_SPI 55 IRQ_TYPE_LEVEL_HIGH>,
 					     <GIC_SPI 56 IRQ_TYPE_LEVEL_HIGH>,
diff --git a/arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi b/arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi
index 7740a75a8230..6e2058847ddc 100644
--- a/arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi
@@ -221,8 +221,7 @@
 			cps_crypto: crypto@800000 {
 				compatible = "inside-secure,safexcel-eip197";
 				reg = <0x800000 0x200000>;
-				interrupts = <GIC_SPI 34 (IRQ_TYPE_EDGE_RISING
-				| IRQ_TYPE_LEVEL_HIGH)>,
+				interrupts = <GIC_SPI 34 IRQ_TYPE_LEVEL_HIGH>,
 					     <GIC_SPI 278 IRQ_TYPE_LEVEL_HIGH>,
 					     <GIC_SPI 279 IRQ_TYPE_LEVEL_HIGH>,
 					     <GIC_SPI 280 IRQ_TYPE_LEVEL_HIGH>,
diff --git a/arch/arm64/include/asm/atomic_ll_sc.h b/arch/arm64/include/asm/atomic_ll_sc.h
index f819fdcff1ac..f5a2d09afb38 100644
--- a/arch/arm64/include/asm/atomic_ll_sc.h
+++ b/arch/arm64/include/asm/atomic_ll_sc.h
@@ -264,7 +264,6 @@ __LL_SC_PREFIX(__cmpxchg_case_##name(volatile void *ptr,		\
 	"	st" #rel "xr" #sz "\t%w[tmp], %" #w "[new], %[v]\n"	\
 	"	cbnz	%w[tmp], 1b\n"					\
 	"	" #mb "\n"						\
-	"	mov	%" #w "[oldval], %" #w "[old]\n"		\
 	"2:"								\
 	: [tmp] "=&r" (tmp), [oldval] "=&r" (oldval),			\
 	  [v] "+Q" (*(unsigned long *)ptr)				\
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index e7f84a7b4465..428ee1f2468c 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -115,6 +115,7 @@ struct arm64_cpu_capabilities {
 
 extern DECLARE_BITMAP(cpu_hwcaps, ARM64_NCAPS);
 extern struct static_key_false cpu_hwcap_keys[ARM64_NCAPS];
+extern struct static_key_false arm64_const_caps_ready;
 
 bool this_cpu_has_cap(unsigned int cap);
 
@@ -124,7 +125,7 @@ static inline bool cpu_have_feature(unsigned int num)
 }
 
 /* System capability check for constant caps */
-static inline bool cpus_have_const_cap(int num)
+static inline bool __cpus_have_const_cap(int num)
 {
 	if (num >= ARM64_NCAPS)
 		return false;
@@ -138,6 +139,14 @@ static inline bool cpus_have_cap(unsigned int num)
 	return test_bit(num, cpu_hwcaps);
 }
 
+static inline bool cpus_have_const_cap(int num)
+{
+	if (static_branch_likely(&arm64_const_caps_ready))
+		return __cpus_have_const_cap(num);
+	else
+		return cpus_have_cap(num);
+}
+
 static inline void cpus_set_cap(unsigned int num)
 {
 	if (num >= ARM64_NCAPS) {
@@ -145,7 +154,6 @@ static inline void cpus_set_cap(unsigned int num)
 			num, ARM64_NCAPS);
 	} else {
 		__set_bit(num, cpu_hwcaps);
-		static_branch_enable(&cpu_hwcap_keys[num]);
 	}
 }
 
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 5e19165c5fa8..1f252a95bc02 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -24,6 +24,7 @@
 
 #include <linux/types.h>
 #include <linux/kvm_types.h>
+#include <asm/cpufeature.h>
 #include <asm/kvm.h>
 #include <asm/kvm_asm.h>
 #include <asm/kvm_mmio.h>
@@ -355,9 +356,12 @@ static inline void __cpu_init_hyp_mode(phys_addr_t pgd_ptr,
 				       unsigned long vector_ptr)
 {
 	/*
-	 * Call initialization code, and switch to the full blown
-	 * HYP code.
+	 * Call initialization code, and switch to the full blown HYP code.
+	 * If the cpucaps haven't been finalized yet, something has gone very
+	 * wrong, and hyp will crash and burn when it uses any
+	 * cpus_have_const_cap() wrapper.
 	 */
+	BUG_ON(!static_branch_likely(&arm64_const_caps_ready));
 	__kvm_call_hyp((void *)pgd_ptr, hyp_stack_ptr, vector_ptr);
 }
 
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 94b8f7fc3310..817ce3365e20 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -985,8 +985,16 @@ void update_cpu_capabilities(const struct arm64_cpu_capabilities *caps,
  */
 void __init enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps)
 {
-	for (; caps->matches; caps++)
-		if (caps->enable && cpus_have_cap(caps->capability))
+	for (; caps->matches; caps++) {
+		unsigned int num = caps->capability;
+
+		if (!cpus_have_cap(num))
+			continue;
+
+		/* Ensure cpus_have_const_cap(num) works */
+		static_branch_enable(&cpu_hwcap_keys[num]);
+
+		if (caps->enable) {
 			/*
 			 * Use stop_machine() as it schedules the work allowing
 			 * us to modify PSTATE, instead of on_each_cpu() which
@@ -994,6 +1002,8 @@ void __init enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps)
 			 * we return.
 			 */
 			stop_machine(caps->enable, NULL, cpu_online_mask);
+		}
+	}
 }
 
 /*
@@ -1096,6 +1106,14 @@ static void __init setup_feature_capabilities(void)
 	enable_cpu_capabilities(arm64_features);
 }
 
+DEFINE_STATIC_KEY_FALSE(arm64_const_caps_ready);
+EXPORT_SYMBOL(arm64_const_caps_ready);
+
+static void __init mark_const_caps_ready(void)
+{
+	static_branch_enable(&arm64_const_caps_ready);
+}
+
 /*
  * Check if the current CPU has a given feature capability.
  * Should be called from non-preemptible context.
@@ -1131,6 +1149,7 @@ void __init setup_cpu_features(void)
 	/* Set the CPU feature capabilies */
 	setup_feature_capabilities();
 	enable_errata_workarounds();
+	mark_const_caps_ready();
 	setup_elf_hwcaps(arm64_elf_hwcaps);
 
 	if (system_supports_32bit_el0())
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index bcc79471b38e..83a1b1ad189f 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -877,15 +877,24 @@ static int armv8pmu_set_event_filter(struct hw_perf_event *event,
 
 	if (attr->exclude_idle)
 		return -EPERM;
-	if (is_kernel_in_hyp_mode() &&
-	    attr->exclude_kernel != attr->exclude_hv)
-		return -EINVAL;
+
+	/*
+	 * If we're running in hyp mode, then we *are* the hypervisor.
+	 * Therefore we ignore exclude_hv in this configuration, since
+	 * there's no hypervisor to sample anyway. This is consistent
+	 * with other architectures (x86 and Power).
+	 */
+	if (is_kernel_in_hyp_mode()) {
+		if (!attr->exclude_kernel)
+			config_base |= ARMV8_PMU_INCLUDE_EL2;
+	} else {
+		if (attr->exclude_kernel)
+			config_base |= ARMV8_PMU_EXCLUDE_EL1;
+		if (!attr->exclude_hv)
+			config_base |= ARMV8_PMU_INCLUDE_EL2;
+	}
 	if (attr->exclude_user)
 		config_base |= ARMV8_PMU_EXCLUDE_EL0;
-	if (!is_kernel_in_hyp_mode() && attr->exclude_kernel)
-		config_base |= ARMV8_PMU_EXCLUDE_EL1;
-	if (!attr->exclude_hv)
-		config_base |= ARMV8_PMU_INCLUDE_EL2;
 
 	/*
 	 * Install the filter into config_base as this is used to
diff --git a/arch/arm64/kvm/hyp/Makefile b/arch/arm64/kvm/hyp/Makefile
index aaf42ae8d8c3..14c4e3b14bcb 100644
--- a/arch/arm64/kvm/hyp/Makefile
+++ b/arch/arm64/kvm/hyp/Makefile
@@ -2,6 +2,8 @@
 # Makefile for Kernel-based Virtual Machine module, HYP part
 #
 
+ccflags-y += -fno-stack-protector
+
 KVM=../../../../virt/kvm
 
 obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/vgic-v2-sr.o
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index c6e53580aefe..71f930501ade 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -253,8 +253,9 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx)
 	 */
 	off = offsetof(struct bpf_array, ptrs);
 	emit_a64_mov_i64(tmp, off, ctx);
-	emit(A64_LDR64(tmp, r2, tmp), ctx);
-	emit(A64_LDR64(prg, tmp, r3), ctx);
+	emit(A64_ADD(1, tmp, r2, tmp), ctx);
+	emit(A64_LSL(1, prg, r3, 3), ctx);
+	emit(A64_LDR64(prg, tmp, prg), ctx);
 	emit(A64_CBZ(1, prg, jmp_offset), ctx);
 
 	/* goto *(prog->bpf_func + prologue_size); */
diff --git a/arch/powerpc/include/asm/module.h b/arch/powerpc/include/asm/module.h
index 53885512b8d3..6c0132c7212f 100644
--- a/arch/powerpc/include/asm/module.h
+++ b/arch/powerpc/include/asm/module.h
@@ -14,6 +14,10 @@
 #include <asm-generic/module.h>
 
 
+#ifdef CC_USING_MPROFILE_KERNEL
+#define MODULE_ARCH_VERMAGIC	"mprofile-kernel"
+#endif
+
 #ifndef __powerpc64__
 /*
  * Thanks to Paul M for explaining this.
diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h
index 2a32483c7b6c..8da5d4c1cab2 100644
--- a/arch/powerpc/include/asm/page.h
+++ b/arch/powerpc/include/asm/page.h
@@ -132,7 +132,19 @@ extern long long virt_phys_offset;
 #define virt_to_pfn(kaddr)	(__pa(kaddr) >> PAGE_SHIFT)
 #define virt_to_page(kaddr)	pfn_to_page(virt_to_pfn(kaddr))
 #define pfn_to_kaddr(pfn)	__va((pfn) << PAGE_SHIFT)
+
+#ifdef CONFIG_PPC_BOOK3S_64
+/*
+ * On hash the vmalloc and other regions alias to the kernel region when passed
+ * through __pa(), which virt_to_pfn() uses. That means virt_addr_valid() can
+ * return true for some vmalloc addresses, which is incorrect. So explicitly
+ * check that the address is in the kernel region.
+ */
+#define virt_addr_valid(kaddr) (REGION_ID(kaddr) == KERNEL_REGION_ID && \
+				pfn_valid(virt_to_pfn(kaddr)))
+#else
 #define virt_addr_valid(kaddr)	pfn_valid(virt_to_pfn(kaddr))
+#endif
 
 /*
  * On Book-E parts we need __va to parse the device tree and we can't
diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S
index 07d4e0ad60db..4898d676dcae 100644
--- a/arch/powerpc/kernel/idle_book3s.S
+++ b/arch/powerpc/kernel/idle_book3s.S
@@ -416,7 +416,7 @@ power9_dd1_recover_paca:
 	 * which needs to be restored from the stack.
 	 */
 	li	r3, 1
-	stb	r0,PACA_NAPSTATELOST(r13)
+	stb	r3,PACA_NAPSTATELOST(r13)
 	blr
 
 /*
diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c
index 160ae0fa7d0d..fc4343514bed 100644
--- a/arch/powerpc/kernel/kprobes.c
+++ b/arch/powerpc/kernel/kprobes.c
@@ -305,16 +305,17 @@ int kprobe_handler(struct pt_regs *regs)
 			save_previous_kprobe(kcb);
 			set_current_kprobe(p, regs, kcb);
 			kprobes_inc_nmissed_count(p);
-			prepare_singlestep(p, regs);
 			kcb->kprobe_status = KPROBE_REENTER;
 			if (p->ainsn.boostable >= 0) {
 				ret = try_to_emulate(p, regs);
 
 				if (ret > 0) {
 					restore_previous_kprobe(kcb);
+					preempt_enable_no_resched();
 					return 1;
 				}
 			}
+			prepare_singlestep(p, regs);
 			return 1;
 		} else {
 			if (*addr != BREAKPOINT_INSTRUCTION) {
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index d645da302bf2..baae104b16c7 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -864,6 +864,25 @@ static void tm_reclaim_thread(struct thread_struct *thr,
 	if (!MSR_TM_SUSPENDED(mfmsr()))
 		return;
 
+	/*
+	 * If we are in a transaction and FP is off then we can't have
+	 * used FP inside that transaction. Hence the checkpointed
+	 * state is the same as the live state. We need to copy the
+	 * live state to the checkpointed state so that when the
+	 * transaction is restored, the checkpointed state is correct
+	 * and the aborted transaction sees the correct state. We use
+	 * ckpt_regs.msr here as that's what tm_reclaim will use to
+	 * determine if it's going to write the checkpointed state or
+	 * not. So either this will write the checkpointed registers,
+	 * or reclaim will. Similarly for VMX.
+	 */
+	if ((thr->ckpt_regs.msr & MSR_FP) == 0)
+		memcpy(&thr->ckfp_state, &thr->fp_state,
+		       sizeof(struct thread_fp_state));
+	if ((thr->ckpt_regs.msr & MSR_VEC) == 0)
+		memcpy(&thr->ckvr_state, &thr->vr_state,
+		       sizeof(struct thread_vr_state));
+
 	giveup_all(container_of(thr, struct task_struct, thread));
 
 	tm_reclaim(thr, thr->ckpt_regs.msr, cause);
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index 24de532c1736..0c52cb5d43f5 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -67,7 +67,7 @@ config KVM_BOOK3S_64
 	select KVM_BOOK3S_64_HANDLER
 	select KVM
 	select KVM_BOOK3S_PR_POSSIBLE if !KVM_BOOK3S_HV_POSSIBLE
-	select SPAPR_TCE_IOMMU if IOMMU_SUPPORT
+	select SPAPR_TCE_IOMMU if IOMMU_SUPPORT && (PPC_SERIES || PPC_POWERNV)
 	---help---
 	  Support running unmodified book3s_64 and book3s_32 guest kernels
 	  in virtual machines on book3s_64 host processors.
diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile
index d91a2604c496..381a6ec0ff3b 100644
--- a/arch/powerpc/kvm/Makefile
+++ b/arch/powerpc/kvm/Makefile
@@ -46,7 +46,7 @@ kvm-e500mc-objs := \
 	e500_emulate.o
 kvm-objs-$(CONFIG_KVM_E500MC) := $(kvm-e500mc-objs)
 
-kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HANDLER) := \
+kvm-book3s_64-builtin-objs-$(CONFIG_SPAPR_TCE_IOMMU) := \
 	book3s_64_vio_hv.o
 
 kvm-pr-y := \
@@ -90,11 +90,11 @@ kvm-book3s_64-objs-$(CONFIG_KVM_XICS) += \
 	book3s_xics.o
 
 kvm-book3s_64-objs-$(CONFIG_KVM_XIVE) += book3s_xive.o
+kvm-book3s_64-objs-$(CONFIG_SPAPR_TCE_IOMMU) += book3s_64_vio.o
 
 kvm-book3s_64-module-objs := \
 	$(common-objs-y) \
 	book3s.o \
-	book3s_64_vio.o \
 	book3s_rtas.o \
 	$(kvm-book3s_64-objs-y)
 
diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c
index eda0a8f6fae8..3adfd2f5301c 100644
--- a/arch/powerpc/kvm/book3s_64_vio_hv.c
+++ b/arch/powerpc/kvm/book3s_64_vio_hv.c
@@ -301,6 +301,10 @@ long kvmppc_rm_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 	/* udbg_printf("H_PUT_TCE(): liobn=0x%lx ioba=0x%lx, tce=0x%lx\n", */
 	/* 	    liobn, ioba, tce); */
 
+	/* For radix, we might be in virtual mode, so punt */
+	if (kvm_is_radix(vcpu->kvm))
+		return H_TOO_HARD;
+
 	stt = kvmppc_find_table(vcpu->kvm, liobn);
 	if (!stt)
 		return H_TOO_HARD;
@@ -381,6 +385,10 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 	bool prereg = false;
 	struct kvmppc_spapr_tce_iommu_table *stit;
 
+	/* For radix, we might be in virtual mode, so punt */
+	if (kvm_is_radix(vcpu->kvm))
+		return H_TOO_HARD;
+
 	stt = kvmppc_find_table(vcpu->kvm, liobn);
 	if (!stt)
 		return H_TOO_HARD;
@@ -491,6 +499,10 @@ long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu,
 	long i, ret;
 	struct kvmppc_spapr_tce_iommu_table *stit;
 
+	/* For radix, we might be in virtual mode, so punt */
+	if (kvm_is_radix(vcpu->kvm))
+		return H_TOO_HARD;
+
 	stt = kvmppc_find_table(vcpu->kvm, liobn);
 	if (!stt)
 		return H_TOO_HARD;
@@ -527,6 +539,7 @@ long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu,
 	return H_SUCCESS;
 }
 
+/* This can be called in either virtual mode or real mode */
 long kvmppc_h_get_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 		      unsigned long ioba)
 {
diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
index 88a65923c649..ee4c2558c305 100644
--- a/arch/powerpc/kvm/book3s_hv_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -207,7 +207,14 @@ EXPORT_SYMBOL_GPL(kvmppc_hwrng_present);
 
 long kvmppc_h_random(struct kvm_vcpu *vcpu)
 {
-	if (powernv_get_random_real_mode(&vcpu->arch.gpr[4]))
+	int r;
+
+	/* Only need to do the expensive mfmsr() on radix */
+	if (kvm_is_radix(vcpu->kvm) && (mfmsr() & MSR_IR))
+		r = powernv_get_random_long(&vcpu->arch.gpr[4]);
+	else
+		r = powernv_get_random_real_mode(&vcpu->arch.gpr[4]);
+	if (r)
 		return H_SUCCESS;
 
 	return H_HARDWARE;
diff --git a/arch/powerpc/kvm/book3s_pr_papr.c b/arch/powerpc/kvm/book3s_pr_papr.c
index bcbeeb62dd13..8a4205fa774f 100644
--- a/arch/powerpc/kvm/book3s_pr_papr.c
+++ b/arch/powerpc/kvm/book3s_pr_papr.c
@@ -50,7 +50,9 @@ static int kvmppc_h_pr_enter(struct kvm_vcpu *vcpu)
 	pteg_addr = get_pteg_addr(vcpu, pte_index);
 
 	mutex_lock(&vcpu->kvm->arch.hpt_mutex);
-	copy_from_user(pteg, (void __user *)pteg_addr, sizeof(pteg));
+	ret = H_FUNCTION;
+	if (copy_from_user(pteg, (void __user *)pteg_addr, sizeof(pteg)))
+		goto done;
 	hpte = pteg;
 
 	ret = H_PTEG_FULL;
@@ -71,7 +73,9 @@ static int kvmppc_h_pr_enter(struct kvm_vcpu *vcpu)
 	hpte[0] = cpu_to_be64(kvmppc_get_gpr(vcpu, 6));
 	hpte[1] = cpu_to_be64(kvmppc_get_gpr(vcpu, 7));
 	pteg_addr += i * HPTE_SIZE;
-	copy_to_user((void __user *)pteg_addr, hpte, HPTE_SIZE);
+	ret = H_FUNCTION;
+	if (copy_to_user((void __user *)pteg_addr, hpte, HPTE_SIZE))
+		goto done;
 	kvmppc_set_gpr(vcpu, 4, pte_index | i);
 	ret = H_SUCCESS;
 
@@ -93,7 +97,9 @@ static int kvmppc_h_pr_remove(struct kvm_vcpu *vcpu)
 
 	pteg = get_pteg_addr(vcpu, pte_index);
 	mutex_lock(&vcpu->kvm->arch.hpt_mutex);
-	copy_from_user(pte, (void __user *)pteg, sizeof(pte));
+	ret = H_FUNCTION;
+	if (copy_from_user(pte, (void __user *)pteg, sizeof(pte)))
+		goto done;
 	pte[0] = be64_to_cpu((__force __be64)pte[0]);
 	pte[1] = be64_to_cpu((__force __be64)pte[1]);
 
@@ -103,7 +109,9 @@ static int kvmppc_h_pr_remove(struct kvm_vcpu *vcpu)
 	    ((flags & H_ANDCOND) && (pte[0] & avpn) != 0))
 		goto done;
 
-	copy_to_user((void __user *)pteg, &v, sizeof(v));
+	ret = H_FUNCTION;
+	if (copy_to_user((void __user *)pteg, &v, sizeof(v)))
+		goto done;
 
 	rb = compute_tlbie_rb(pte[0], pte[1], pte_index);
 	vcpu->arch.mmu.tlbie(vcpu, rb, rb & 1 ? true : false);
@@ -171,7 +179,10 @@ static int kvmppc_h_pr_bulk_remove(struct kvm_vcpu *vcpu)
 		}
 
 		pteg = get_pteg_addr(vcpu, tsh & H_BULK_REMOVE_PTEX);
-		copy_from_user(pte, (void __user *)pteg, sizeof(pte));
+		if (copy_from_user(pte, (void __user *)pteg, sizeof(pte))) {
+			ret = H_FUNCTION;
+			break;
+		}
 		pte[0] = be64_to_cpu((__force __be64)pte[0]);
 		pte[1] = be64_to_cpu((__force __be64)pte[1]);
 
@@ -184,7 +195,10 @@ static int kvmppc_h_pr_bulk_remove(struct kvm_vcpu *vcpu)
 			tsh |= H_BULK_REMOVE_NOT_FOUND;
 		} else {
 			/* Splat the pteg in (userland) hpt */
-			copy_to_user((void __user *)pteg, &v, sizeof(v));
+			if (copy_to_user((void __user *)pteg, &v, sizeof(v))) {
+				ret = H_FUNCTION;
+				break;
+			}
 
 			rb = compute_tlbie_rb(pte[0], pte[1],
 					      tsh & H_BULK_REMOVE_PTEX);
@@ -211,7 +225,9 @@ static int kvmppc_h_pr_protect(struct kvm_vcpu *vcpu)
 
 	pteg = get_pteg_addr(vcpu, pte_index);
 	mutex_lock(&vcpu->kvm->arch.hpt_mutex);
-	copy_from_user(pte, (void __user *)pteg, sizeof(pte));
+	ret = H_FUNCTION;
+	if (copy_from_user(pte, (void __user *)pteg, sizeof(pte)))
+		goto done;
 	pte[0] = be64_to_cpu((__force __be64)pte[0]);
 	pte[1] = be64_to_cpu((__force __be64)pte[1]);
 
@@ -234,7 +250,9 @@ static int kvmppc_h_pr_protect(struct kvm_vcpu *vcpu)
 	vcpu->arch.mmu.tlbie(vcpu, rb, rb & 1 ? true : false);
 	pte[0] = (__force u64)cpu_to_be64(pte[0]);
 	pte[1] = (__force u64)cpu_to_be64(pte[1]);
-	copy_to_user((void __user *)pteg, pte, sizeof(pte));
+	ret = H_FUNCTION;
+	if (copy_to_user((void __user *)pteg, pte, sizeof(pte)))
+		goto done;
 	ret = H_SUCCESS;
 
  done:
@@ -244,36 +262,37 @@ static int kvmppc_h_pr_protect(struct kvm_vcpu *vcpu)
 	return EMULATE_DONE;
 }
 
-static int kvmppc_h_pr_put_tce(struct kvm_vcpu *vcpu)
+static int kvmppc_h_pr_logical_ci_load(struct kvm_vcpu *vcpu)
 {
-	unsigned long liobn = kvmppc_get_gpr(vcpu, 4);
-	unsigned long ioba = kvmppc_get_gpr(vcpu, 5);
-	unsigned long tce = kvmppc_get_gpr(vcpu, 6);
 	long rc;
 
-	rc = kvmppc_h_put_tce(vcpu, liobn, ioba, tce);
+	rc = kvmppc_h_logical_ci_load(vcpu);
 	if (rc == H_TOO_HARD)
 		return EMULATE_FAIL;
 	kvmppc_set_gpr(vcpu, 3, rc);
 	return EMULATE_DONE;
 }
 
-static int kvmppc_h_pr_logical_ci_load(struct kvm_vcpu *vcpu)
+static int kvmppc_h_pr_logical_ci_store(struct kvm_vcpu *vcpu)
 {
 	long rc;
 
-	rc = kvmppc_h_logical_ci_load(vcpu);
+	rc = kvmppc_h_logical_ci_store(vcpu);
 	if (rc == H_TOO_HARD)
 		return EMULATE_FAIL;
 	kvmppc_set_gpr(vcpu, 3, rc);
 	return EMULATE_DONE;
 }
 
-static int kvmppc_h_pr_logical_ci_store(struct kvm_vcpu *vcpu)
+#ifdef CONFIG_SPAPR_TCE_IOMMU
+static int kvmppc_h_pr_put_tce(struct kvm_vcpu *vcpu)
 {
+	unsigned long liobn = kvmppc_get_gpr(vcpu, 4);
+	unsigned long ioba = kvmppc_get_gpr(vcpu, 5);
+	unsigned long tce = kvmppc_get_gpr(vcpu, 6);
 	long rc;
 
-	rc = kvmppc_h_logical_ci_store(vcpu);
+	rc = kvmppc_h_put_tce(vcpu, liobn, ioba, tce);
 	if (rc == H_TOO_HARD)
 		return EMULATE_FAIL;
 	kvmppc_set_gpr(vcpu, 3, rc);
@@ -311,6 +330,23 @@ static int kvmppc_h_pr_stuff_tce(struct kvm_vcpu *vcpu)
 	return EMULATE_DONE;
 }
 
+#else /* CONFIG_SPAPR_TCE_IOMMU */
+static int kvmppc_h_pr_put_tce(struct kvm_vcpu *vcpu)
+{
+	return EMULATE_FAIL;
+}
+
+static int kvmppc_h_pr_put_tce_indirect(struct kvm_vcpu *vcpu)
+{
+	return EMULATE_FAIL;
+}
+
+static int kvmppc_h_pr_stuff_tce(struct kvm_vcpu *vcpu)
+{
+	return EMULATE_FAIL;
+}
+#endif /* CONFIG_SPAPR_TCE_IOMMU */
+
 static int kvmppc_h_pr_xics_hcall(struct kvm_vcpu *vcpu, u32 cmd)
 {
 	long rc = kvmppc_xics_hcall(vcpu, cmd);
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index f7cf2cd564ef..7f71ab5fcad1 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -1749,7 +1749,7 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		r = kvm_vm_ioctl_enable_cap(kvm, &cap);
 		break;
 	}
-#ifdef CONFIG_PPC_BOOK3S_64
+#ifdef CONFIG_SPAPR_TCE_IOMMU
 	case KVM_CREATE_SPAPR_TCE_64: {
 		struct kvm_create_spapr_tce_64 create_tce_64;
 
@@ -1780,6 +1780,8 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		r = kvm_vm_ioctl_create_spapr_tce(kvm, &create_tce_64);
 		goto out;
 	}
+#endif
+#ifdef CONFIG_PPC_BOOK3S_64
 	case KVM_PPC_GET_SMMU_INFO: {
 		struct kvm_ppc_smmu_info info;
 		struct kvm *kvm = filp->private_data;
diff --git a/arch/powerpc/mm/dump_linuxpagetables.c b/arch/powerpc/mm/dump_linuxpagetables.c
index d659345a98d6..44fe4833910f 100644
--- a/arch/powerpc/mm/dump_linuxpagetables.c
+++ b/arch/powerpc/mm/dump_linuxpagetables.c
@@ -16,6 +16,7 @@
  */
 #include <linux/debugfs.h>
 #include <linux/fs.h>
+#include <linux/hugetlb.h>
 #include <linux/io.h>
 #include <linux/mm.h>
 #include <linux/sched.h>
@@ -391,7 +392,7 @@ static void walk_pmd(struct pg_state *st, pud_t *pud, unsigned long start)
 
 	for (i = 0; i < PTRS_PER_PMD; i++, pmd++) {
 		addr = start + i * PMD_SIZE;
-		if (!pmd_none(*pmd))
+		if (!pmd_none(*pmd) && !pmd_huge(*pmd))
 			/* pmd exists */
 			walk_pte(st, pmd, addr);
 		else
@@ -407,7 +408,7 @@ static void walk_pud(struct pg_state *st, pgd_t *pgd, unsigned long start)
 
 	for (i = 0; i < PTRS_PER_PUD; i++, pud++) {
 		addr = start + i * PUD_SIZE;
-		if (!pud_none(*pud))
+		if (!pud_none(*pud) && !pud_huge(*pud))
 			/* pud exists */
 			walk_pmd(st, pud, addr);
 		else
@@ -427,7 +428,7 @@ static void walk_pagetables(struct pg_state *st)
 	 */
 	for (i = 0; i < PTRS_PER_PGD; i++, pgd++) {
 		addr = KERN_VIRT_START + i * PGDIR_SIZE;
-		if (!pgd_none(*pgd))
+		if (!pgd_none(*pgd) && !pgd_huge(*pgd))
 			/* pgd exists */
 			walk_pud(st, pgd, addr);
 		else
diff --git a/arch/s390/include/asm/debug.h b/arch/s390/include/asm/debug.h
index 0206c8052328..df7b54ea956d 100644
--- a/arch/s390/include/asm/debug.h
+++ b/arch/s390/include/asm/debug.h
@@ -10,6 +10,7 @@
 #include <linux/spinlock.h>
 #include <linux/kernel.h>
 #include <linux/time.h>
+#include <linux/refcount.h>
 #include <uapi/asm/debug.h>
 
 #define DEBUG_MAX_LEVEL            6  /* debug levels range from 0 to 6 */
@@ -31,7 +32,7 @@ struct debug_view;
 typedef struct debug_info {	
 	struct debug_info* next;
 	struct debug_info* prev;
-	atomic_t ref_count;
+	refcount_t ref_count;
 	spinlock_t lock;			
 	int level;
 	int nr_areas;
diff --git a/arch/s390/include/asm/dis.h b/arch/s390/include/asm/dis.h
index 60323c21938b..37f617dfbede 100644
--- a/arch/s390/include/asm/dis.h
+++ b/arch/s390/include/asm/dis.h
@@ -40,6 +40,8 @@ static inline int insn_length(unsigned char code)
 	return ((((int) code + 64) >> 7) + 1) << 1;
 }
 
+struct pt_regs;
+
 void show_code(struct pt_regs *regs);
 void print_fn_code(unsigned char *code, unsigned long len);
 int insn_to_mnemonic(unsigned char *instruction, char *buf, unsigned int len);
diff --git a/arch/s390/include/asm/kprobes.h b/arch/s390/include/asm/kprobes.h
index 1293c4066cfc..28792ef82c83 100644
--- a/arch/s390/include/asm/kprobes.h
+++ b/arch/s390/include/asm/kprobes.h
@@ -27,12 +27,21 @@
  * 2005-Dec	Used as a template for s390 by Mike Grundy
  *		<grundym@us.ibm.com>
  */
+#include <linux/types.h>
 #include <asm-generic/kprobes.h>
 
 #define BREAKPOINT_INSTRUCTION	0x0002
 
+#define FIXUP_PSW_NORMAL	0x08
+#define FIXUP_BRANCH_NOT_TAKEN	0x04
+#define FIXUP_RETURN_REGISTER	0x02
+#define FIXUP_NOT_REQUIRED	0x01
+
+int probe_is_prohibited_opcode(u16 *insn);
+int probe_get_fixup_type(u16 *insn);
+int probe_is_insn_relative_long(u16 *insn);
+
 #ifdef CONFIG_KPROBES
-#include <linux/types.h>
 #include <linux/ptrace.h>
 #include <linux/percpu.h>
 #include <linux/sched/task_stack.h>
@@ -56,11 +65,6 @@ typedef u16 kprobe_opcode_t;
 
 #define KPROBE_SWAP_INST	0x10
 
-#define FIXUP_PSW_NORMAL	0x08
-#define FIXUP_BRANCH_NOT_TAKEN	0x04
-#define FIXUP_RETURN_REGISTER	0x02
-#define FIXUP_NOT_REQUIRED	0x01
-
 /* Architecture specific copy of original instruction */
 struct arch_specific_insn {
 	/* copy of original instruction */
@@ -90,10 +94,6 @@ int kprobe_fault_handler(struct pt_regs *regs, int trapnr);
 int kprobe_exceptions_notify(struct notifier_block *self,
 	unsigned long val, void *data);
 
-int probe_is_prohibited_opcode(u16 *insn);
-int probe_get_fixup_type(u16 *insn);
-int probe_is_insn_relative_long(u16 *insn);
-
 #define flush_insn_slot(p)	do { } while (0)
 
 #endif /* CONFIG_KPROBES */
diff --git a/arch/s390/include/asm/sysinfo.h b/arch/s390/include/asm/sysinfo.h
index 73bff45ced55..e784bed6ed7f 100644
--- a/arch/s390/include/asm/sysinfo.h
+++ b/arch/s390/include/asm/sysinfo.h
@@ -146,7 +146,7 @@ extern int topology_max_mnest;
  * Returns the maximum nesting level supported by the cpu topology code.
  * The current maximum level is 4 which is the drawer level.
  */
-static inline int topology_mnest_limit(void)
+static inline unsigned char topology_mnest_limit(void)
 {
 	return min(topology_max_mnest, 4);
 }
diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c
index 530226b6cb19..86b3e74f569e 100644
--- a/arch/s390/kernel/debug.c
+++ b/arch/s390/kernel/debug.c
@@ -277,7 +277,7 @@ debug_info_alloc(const char *name, int pages_per_area, int nr_areas,
 	memset(rc->views, 0, DEBUG_MAX_VIEWS * sizeof(struct debug_view *));
 	memset(rc->debugfs_entries, 0 ,DEBUG_MAX_VIEWS *
 		sizeof(struct dentry*));
-	atomic_set(&(rc->ref_count), 0);
+	refcount_set(&(rc->ref_count), 0);
 
 	return rc;
 
@@ -361,7 +361,7 @@ debug_info_create(const char *name, int pages_per_area, int nr_areas,
         debug_area_last = rc;
         rc->next = NULL;
 
-	debug_info_get(rc);
+	refcount_set(&rc->ref_count, 1);
 out:
 	return rc;
 }
@@ -416,7 +416,7 @@ static void
 debug_info_get(debug_info_t * db_info)
 {
 	if (db_info)
-		atomic_inc(&db_info->ref_count);
+		refcount_inc(&db_info->ref_count);
 }
 
 /*
@@ -431,7 +431,7 @@ debug_info_put(debug_info_t *db_info)
 
 	if (!db_info)
 		return;
-	if (atomic_dec_and_test(&db_info->ref_count)) {
+	if (refcount_dec_and_test(&db_info->ref_count)) {
 		for (i = 0; i < DEBUG_MAX_VIEWS; i++) {
 			if (!db_info->views[i])
 				continue;
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index a5f5d3bb3dbc..e408d9cc5b96 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -312,6 +312,7 @@ ENTRY(system_call)
 	lg	%r14,__LC_VDSO_PER_CPU
 	lmg	%r0,%r10,__PT_R0(%r11)
 	mvc	__LC_RETURN_PSW(16),__PT_PSW(%r11)
+.Lsysc_exit_timer:
 	stpt	__LC_EXIT_TIMER
 	mvc	__VDSO_ECTG_BASE(16,%r14),__LC_EXIT_TIMER
 	lmg	%r11,%r15,__PT_R11(%r11)
@@ -623,6 +624,7 @@ ENTRY(io_int_handler)
 	lg	%r14,__LC_VDSO_PER_CPU
 	lmg	%r0,%r10,__PT_R0(%r11)
 	mvc	__LC_RETURN_PSW(16),__PT_PSW(%r11)
+.Lio_exit_timer:
 	stpt	__LC_EXIT_TIMER
 	mvc	__VDSO_ECTG_BASE(16,%r14),__LC_EXIT_TIMER
 	lmg	%r11,%r15,__PT_R11(%r11)
@@ -1174,15 +1176,23 @@ cleanup_critical:
 	br	%r14
 
 .Lcleanup_sysc_restore:
+	# check if stpt has been executed
 	clg	%r9,BASED(.Lcleanup_sysc_restore_insn)
+	jh	0f
+	mvc	__LC_EXIT_TIMER(8),__LC_ASYNC_ENTER_TIMER
+	cghi	%r11,__LC_SAVE_AREA_ASYNC
 	je	0f
+	mvc	__LC_EXIT_TIMER(8),__LC_MCCK_ENTER_TIMER
+0:	clg	%r9,BASED(.Lcleanup_sysc_restore_insn+8)
+	je	1f
 	lg	%r9,24(%r11)		# get saved pointer to pt_regs
 	mvc	__LC_RETURN_PSW(16),__PT_PSW(%r9)
 	mvc	0(64,%r11),__PT_R8(%r9)
 	lmg	%r0,%r7,__PT_R0(%r9)
-0:	lmg	%r8,%r9,__LC_RETURN_PSW
+1:	lmg	%r8,%r9,__LC_RETURN_PSW
 	br	%r14
 .Lcleanup_sysc_restore_insn:
+	.quad	.Lsysc_exit_timer
 	.quad	.Lsysc_done - 4
 
 .Lcleanup_io_tif:
@@ -1190,15 +1200,20 @@ cleanup_critical:
 	br	%r14
 
 .Lcleanup_io_restore:
+	# check if stpt has been executed
 	clg	%r9,BASED(.Lcleanup_io_restore_insn)
-	je	0f
+	jh	0f
+	mvc	__LC_EXIT_TIMER(8),__LC_MCCK_ENTER_TIMER
+0:	clg	%r9,BASED(.Lcleanup_io_restore_insn+8)
+	je	1f
 	lg	%r9,24(%r11)		# get saved r11 pointer to pt_regs
 	mvc	__LC_RETURN_PSW(16),__PT_PSW(%r9)
 	mvc	0(64,%r11),__PT_R8(%r9)
 	lmg	%r0,%r7,__PT_R0(%r9)
-0:	lmg	%r8,%r9,__LC_RETURN_PSW
+1:	lmg	%r8,%r9,__LC_RETURN_PSW
 	br	%r14
 .Lcleanup_io_restore_insn:
+	.quad	.Lio_exit_timer
 	.quad	.Lio_done - 4
 
 .Lcleanup_idle:
diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c
index 27477f34cc0a..d03a6d12c4bd 100644
--- a/arch/s390/kernel/ftrace.c
+++ b/arch/s390/kernel/ftrace.c
@@ -173,6 +173,8 @@ int __init ftrace_dyn_arch_init(void)
 	return 0;
 }
 
+#ifdef CONFIG_MODULES
+
 static int __init ftrace_plt_init(void)
 {
 	unsigned int *ip;
@@ -191,6 +193,8 @@ static int __init ftrace_plt_init(void)
 }
 device_initcall(ftrace_plt_init);
 
+#endif /* CONFIG_MODULES */
+
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 /*
  * Hook the return address and push it in the stack of return addresses
diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S
index 72307f108c40..6e2c42bd1c3b 100644
--- a/arch/s390/kernel/vmlinux.lds.S
+++ b/arch/s390/kernel/vmlinux.lds.S
@@ -31,8 +31,14 @@ SECTIONS
 {
 	. = 0x00000000;
 	.text : {
-	_text = .;		/* Text and read-only data */
+		/* Text and read-only data */
 		HEAD_TEXT
+		/*
+		 * E.g. perf doesn't like symbols starting at address zero,
+		 * therefore skip the initial PSW and channel program located
+		 * at address zero and let _text start at 0x200.
+		 */
+	_text = 0x200;
 		TEXT_TEXT
 		SCHED_TEXT
 		CPUIDLE_TEXT
diff --git a/arch/s390/lib/probes.c b/arch/s390/lib/probes.c
index ae90e1ae3607..1963ddbf4ab3 100644
--- a/arch/s390/lib/probes.c
+++ b/arch/s390/lib/probes.c
@@ -4,6 +4,7 @@
  *    Copyright IBM Corp. 2014
  */
 
+#include <linux/errno.h>
 #include <asm/kprobes.h>
 #include <asm/dis.h>
 
diff --git a/arch/s390/lib/uaccess.c b/arch/s390/lib/uaccess.c
index 1e5bb2b86c42..b3bd3f23b8e8 100644
--- a/arch/s390/lib/uaccess.c
+++ b/arch/s390/lib/uaccess.c
@@ -337,8 +337,8 @@ long __strncpy_from_user(char *dst, const char __user *src, long size)
 		return 0;
 	done = 0;
 	do {
-		offset = (size_t)src & ~PAGE_MASK;
-		len = min(size - done, PAGE_SIZE - offset);
+		offset = (size_t)src & (L1_CACHE_BYTES - 1);
+		len = min(size - done, L1_CACHE_BYTES - offset);
 		if (copy_from_user(dst, src, len))
 			return -EFAULT;
 		len_str = strnlen(dst, len);
diff --git a/arch/sparc/include/asm/hugetlb.h b/arch/sparc/include/asm/hugetlb.h
index dcbf985ab243..d1f837dc77a4 100644
--- a/arch/sparc/include/asm/hugetlb.h
+++ b/arch/sparc/include/asm/hugetlb.h
@@ -24,9 +24,11 @@ static inline int is_hugepage_only_range(struct mm_struct *mm,
 static inline int prepare_hugepage_range(struct file *file,
 			unsigned long addr, unsigned long len)
 {
-	if (len & ~HPAGE_MASK)
+	struct hstate *h = hstate_file(file);
+
+	if (len & ~huge_page_mask(h))
 		return -EINVAL;
-	if (addr & ~HPAGE_MASK)
+	if (addr & ~huge_page_mask(h))
 		return -EINVAL;
 	return 0;
 }
diff --git a/arch/sparc/include/asm/pgtable_32.h b/arch/sparc/include/asm/pgtable_32.h
index ce6f56980aef..cf190728360b 100644
--- a/arch/sparc/include/asm/pgtable_32.h
+++ b/arch/sparc/include/asm/pgtable_32.h
@@ -91,9 +91,9 @@ extern unsigned long pfn_base;
  * ZERO_PAGE is a global shared page that is always zero: used
  * for zero-mapped memory areas etc..
  */
-extern unsigned long empty_zero_page;
+extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
 
-#define ZERO_PAGE(vaddr) (virt_to_page(&empty_zero_page))
+#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page))
 
 /*
  * In general all page table modifications should use the V8 atomic
diff --git a/arch/sparc/include/asm/setup.h b/arch/sparc/include/asm/setup.h
index 478bf6bb4598..3fae200dd251 100644
--- a/arch/sparc/include/asm/setup.h
+++ b/arch/sparc/include/asm/setup.h
@@ -16,7 +16,7 @@ extern char reboot_command[];
  */
 extern unsigned char boot_cpu_id;
 
-extern unsigned long empty_zero_page;
+extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
 
 extern int serial_console;
 static inline int con_is_present(void)
diff --git a/arch/sparc/kernel/ftrace.c b/arch/sparc/kernel/ftrace.c
index 6bcff698069b..cec54dc4ab81 100644
--- a/arch/sparc/kernel/ftrace.c
+++ b/arch/sparc/kernel/ftrace.c
@@ -130,17 +130,16 @@ unsigned long prepare_ftrace_return(unsigned long parent,
 	if (unlikely(atomic_read(&current->tracing_graph_pause)))
 		return parent + 8UL;
 
-	if (ftrace_push_return_trace(parent, self_addr, &trace.depth,
-				     frame_pointer, NULL) == -EBUSY)
-		return parent + 8UL;
-
 	trace.func = self_addr;
+	trace.depth = current->curr_ret_stack + 1;
 
 	/* Only trace if the calling function expects to */
-	if (!ftrace_graph_entry(&trace)) {
-		current->curr_ret_stack--;
+	if (!ftrace_graph_entry(&trace))
+		return parent + 8UL;
+
+	if (ftrace_push_return_trace(parent, self_addr, &trace.depth,
+				     frame_pointer, NULL) == -EBUSY)
 		return parent + 8UL;
-	}
 
 	return return_hooker;
 }
diff --git a/arch/sparc/mm/init_32.c b/arch/sparc/mm/init_32.c
index c6afe98de4d9..3bd0d513bddb 100644
--- a/arch/sparc/mm/init_32.c
+++ b/arch/sparc/mm/init_32.c
@@ -290,7 +290,7 @@ void __init mem_init(void)
 
 
 	/* Saves us work later. */
-	memset((void *)&empty_zero_page, 0, PAGE_SIZE);
+	memset((void *)empty_zero_page, 0, PAGE_SIZE);
 
 	i = last_valid_pfn >> ((20 - PAGE_SHIFT) + 5);
 	i += 1;
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 9c761fea0c98..695605eb1dfb 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -43,7 +43,7 @@
 #define KVM_PRIVATE_MEM_SLOTS 3
 #define KVM_MEM_SLOTS_NUM (KVM_USER_MEM_SLOTS + KVM_PRIVATE_MEM_SLOTS)
 
-#define KVM_HALT_POLL_NS_DEFAULT 400000
+#define KVM_HALT_POLL_NS_DEFAULT 200000
 
 #define KVM_IRQCHIP_NUM_PINS  KVM_IOAPIC_NUM_PINS
 
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 68766b276d9e..a059aac9e937 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -319,10 +319,10 @@ do {									\
 #define __get_user_asm_u64(x, ptr, retval, errret)			\
 ({									\
 	__typeof__(ptr) __ptr = (ptr);					\
-	asm volatile(ASM_STAC "\n"					\
+	asm volatile("\n"					\
 		     "1:	movl %2,%%eax\n"			\
 		     "2:	movl %3,%%edx\n"			\
-		     "3: " ASM_CLAC "\n"				\
+		     "3:\n"				\
 		     ".section .fixup,\"ax\"\n"				\
 		     "4:	mov %4,%0\n"				\
 		     "	xorl %%eax,%%eax\n"				\
@@ -331,7 +331,7 @@ do {									\
 		     ".previous\n"					\
 		     _ASM_EXTABLE(1b, 4b)				\
 		     _ASM_EXTABLE(2b, 4b)				\
-		     : "=r" (retval), "=A"(x)				\
+		     : "=r" (retval), "=&A"(x)				\
 		     : "m" (__m(__ptr)), "m" __m(((u32 *)(__ptr)) + 1),	\
 		       "i" (errret), "0" (retval));			\
 })
@@ -703,14 +703,15 @@ extern struct movsl_mask {
 #define unsafe_put_user(x, ptr, err_label)					\
 do {										\
 	int __pu_err;								\
-	__put_user_size((x), (ptr), sizeof(*(ptr)), __pu_err, -EFAULT);		\
+	__typeof__(*(ptr)) __pu_val = (x);					\
+	__put_user_size(__pu_val, (ptr), sizeof(*(ptr)), __pu_err, -EFAULT);	\
 	if (unlikely(__pu_err)) goto err_label;					\
 } while (0)
 
 #define unsafe_get_user(x, ptr, err_label)					\
 do {										\
 	int __gu_err;								\
-	unsigned long __gu_val;							\
+	__inttype(*(ptr)) __gu_val;						\
 	__get_user_size(__gu_val, (ptr), sizeof(*(ptr)), __gu_err, -EFAULT);	\
 	(x) = (__force __typeof__(*(ptr)))__gu_val;				\
 	if (unlikely(__gu_err)) goto err_label;					\
diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c
index c2f8dde3255c..d5d44c452624 100644
--- a/arch/x86/kernel/fpu/init.c
+++ b/arch/x86/kernel/fpu/init.c
@@ -90,6 +90,7 @@ static void fpu__init_system_early_generic(struct cpuinfo_x86 *c)
  * Boot time FPU feature detection code:
  */
 unsigned int mxcsr_feature_mask __read_mostly = 0xffffffffu;
+EXPORT_SYMBOL_GPL(mxcsr_feature_mask);
 
 static void __init fpu__init_system_mxcsr(void)
 {
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index c25cfaf584e7..0816ab2e8adc 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -4173,7 +4173,7 @@ static int check_dr_write(struct x86_emulate_ctxt *ctxt)
 
 static int check_svme(struct x86_emulate_ctxt *ctxt)
 {
-	u64 efer;
+	u64 efer = 0;
 
 	ctxt->ops->get_msr(ctxt, MSR_EFER, &efer);
 
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 56241746abbd..b0454c7e4cff 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -283,11 +283,13 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker,
 	pt_element_t pte;
 	pt_element_t __user *uninitialized_var(ptep_user);
 	gfn_t table_gfn;
-	unsigned index, pt_access, pte_access, accessed_dirty, pte_pkey;
+	u64 pt_access, pte_access;
+	unsigned index, accessed_dirty, pte_pkey;
 	unsigned nested_access;
 	gpa_t pte_gpa;
 	bool have_ad;
 	int offset;
+	u64 walk_nx_mask = 0;
 	const int write_fault = access & PFERR_WRITE_MASK;
 	const int user_fault  = access & PFERR_USER_MASK;
 	const int fetch_fault = access & PFERR_FETCH_MASK;
@@ -302,6 +304,7 @@ retry_walk:
 	have_ad       = PT_HAVE_ACCESSED_DIRTY(mmu);
 
 #if PTTYPE == 64
+	walk_nx_mask = 1ULL << PT64_NX_SHIFT;
 	if (walker->level == PT32E_ROOT_LEVEL) {
 		pte = mmu->get_pdptr(vcpu, (addr >> 30) & 3);
 		trace_kvm_mmu_paging_element(pte, walker->level);
@@ -313,8 +316,6 @@ retry_walk:
 	walker->max_level = walker->level;
 	ASSERT(!(is_long_mode(vcpu) && !is_pae(vcpu)));
 
-	accessed_dirty = have_ad ? PT_GUEST_ACCESSED_MASK : 0;
-
 	/*
 	 * FIXME: on Intel processors, loads of the PDPTE registers for PAE paging
 	 * by the MOV to CR instruction are treated as reads and do not cause the
@@ -322,14 +323,14 @@ retry_walk:
 	 */
 	nested_access = (have_ad ? PFERR_WRITE_MASK : 0) | PFERR_USER_MASK;
 
-	pt_access = pte_access = ACC_ALL;
+	pte_access = ~0;
 	++walker->level;
 
 	do {
 		gfn_t real_gfn;
 		unsigned long host_addr;
 
-		pt_access &= pte_access;
+		pt_access = pte_access;
 		--walker->level;
 
 		index = PT_INDEX(addr, walker->level);
@@ -371,6 +372,12 @@ retry_walk:
 
 		trace_kvm_mmu_paging_element(pte, walker->level);
 
+		/*
+		 * Inverting the NX it lets us AND it like other
+		 * permission bits.
+		 */
+		pte_access = pt_access & (pte ^ walk_nx_mask);
+
 		if (unlikely(!FNAME(is_present_gpte)(pte)))
 			goto error;
 
@@ -379,14 +386,16 @@ retry_walk:
 			goto error;
 		}
 
-		accessed_dirty &= pte;
-		pte_access = pt_access & FNAME(gpte_access)(vcpu, pte);
-
 		walker->ptes[walker->level - 1] = pte;
 	} while (!is_last_gpte(mmu, walker->level, pte));
 
 	pte_pkey = FNAME(gpte_pkeys)(vcpu, pte);
-	errcode = permission_fault(vcpu, mmu, pte_access, pte_pkey, access);
+	accessed_dirty = have_ad ? pte_access & PT_GUEST_ACCESSED_MASK : 0;
+
+	/* Convert to ACC_*_MASK flags for struct guest_walker.  */
+	walker->pt_access = FNAME(gpte_access)(vcpu, pt_access ^ walk_nx_mask);
+	walker->pte_access = FNAME(gpte_access)(vcpu, pte_access ^ walk_nx_mask);
+	errcode = permission_fault(vcpu, mmu, walker->pte_access, pte_pkey, access);
 	if (unlikely(errcode))
 		goto error;
 
@@ -403,7 +412,7 @@ retry_walk:
 	walker->gfn = real_gpa >> PAGE_SHIFT;
 
 	if (!write_fault)
-		FNAME(protect_clean_gpte)(mmu, &pte_access, pte);
+		FNAME(protect_clean_gpte)(mmu, &walker->pte_access, pte);
 	else
 		/*
 		 * On a write fault, fold the dirty bit into accessed_dirty.
@@ -421,10 +430,8 @@ retry_walk:
 			goto retry_walk;
 	}
 
-	walker->pt_access = pt_access;
-	walker->pte_access = pte_access;
 	pgprintk("%s: pte %llx pte_access %x pt_access %x\n",
-		 __func__, (u64)pte, pte_access, pt_access);
+		 __func__, (u64)pte, walker->pte_access, walker->pt_access);
 	return 1;
 
 error:
@@ -452,7 +459,7 @@ error:
 	 */
 	if (!(errcode & PFERR_RSVD_MASK)) {
 		vcpu->arch.exit_qualification &= 0x187;
-		vcpu->arch.exit_qualification |= ((pt_access & pte) & 0x7) << 3;
+		vcpu->arch.exit_qualification |= (pte_access & 0x7) << 3;
 	}
 #endif
 	walker->fault.address = addr;
diff --git a/arch/x86/kvm/pmu_intel.c b/arch/x86/kvm/pmu_intel.c
index 9d4a8504a95a..5ab4a364348e 100644
--- a/arch/x86/kvm/pmu_intel.c
+++ b/arch/x86/kvm/pmu_intel.c
@@ -294,7 +294,7 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
 			((u64)1 << edx.split.bit_width_fixed) - 1;
 	}
 
-	pmu->global_ctrl = ((1 << pmu->nr_arch_gp_counters) - 1) |
+	pmu->global_ctrl = ((1ull << pmu->nr_arch_gp_counters) - 1) |
 		(((1ull << pmu->nr_arch_fixed_counters) - 1) << INTEL_PMC_IDX_FIXED);
 	pmu->global_ctrl_mask = ~pmu->global_ctrl;
 
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index c27ac6923a18..183ddb235fb4 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -1272,7 +1272,8 @@ static void init_vmcb(struct vcpu_svm *svm)
 
 }
 
-static u64 *avic_get_physical_id_entry(struct kvm_vcpu *vcpu, int index)
+static u64 *avic_get_physical_id_entry(struct kvm_vcpu *vcpu,
+				       unsigned int index)
 {
 	u64 *avic_physical_id_table;
 	struct kvm_arch *vm_data = &vcpu->kvm->arch;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index c6f4ad44aa95..72f78396bc09 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -6504,7 +6504,7 @@ static __init int hardware_setup(void)
 		enable_ept_ad_bits = 0;
 	}
 
-	if (!cpu_has_vmx_ept_ad_bits())
+	if (!cpu_has_vmx_ept_ad_bits() || !enable_ept)
 		enable_ept_ad_bits = 0;
 
 	if (!cpu_has_vmx_unrestricted_guest())
@@ -11213,7 +11213,7 @@ static int vmx_write_pml_buffer(struct kvm_vcpu *vcpu)
 		if (!nested_cpu_has_pml(vmcs12))
 			return 0;
 
-		if (vmcs12->guest_pml_index > PML_ENTITY_NUM) {
+		if (vmcs12->guest_pml_index >= PML_ENTITY_NUM) {
 			vmx->nested.pml_full = true;
 			return 1;
 		}
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 464da936c53d..02363e37d4a6 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1763,6 +1763,7 @@ u64 get_kvmclock_ns(struct kvm *kvm)
 {
 	struct kvm_arch *ka = &kvm->arch;
 	struct pvclock_vcpu_time_info hv_clock;
+	u64 ret;
 
 	spin_lock(&ka->pvclock_gtod_sync_lock);
 	if (!ka->use_master_clock) {
@@ -1774,10 +1775,17 @@ u64 get_kvmclock_ns(struct kvm *kvm)
 	hv_clock.system_time = ka->master_kernel_ns + ka->kvmclock_offset;
 	spin_unlock(&ka->pvclock_gtod_sync_lock);
 
+	/* both __this_cpu_read() and rdtsc() should be on the same cpu */
+	get_cpu();
+
 	kvm_get_time_scale(NSEC_PER_SEC, __this_cpu_read(cpu_tsc_khz) * 1000LL,
 			   &hv_clock.tsc_shift,
 			   &hv_clock.tsc_to_system_mul);
-	return __pvclock_read_cycles(&hv_clock, rdtsc());
+	ret = __pvclock_read_cycles(&hv_clock, rdtsc());
+
+	put_cpu();
+
+	return ret;
 }
 
 static void kvm_setup_pvclock_page(struct kvm_vcpu *v)
@@ -3288,11 +3296,14 @@ static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu,
 	}
 }
 
+#define XSAVE_MXCSR_OFFSET 24
+
 static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu,
 					struct kvm_xsave *guest_xsave)
 {
 	u64 xstate_bv =
 		*(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)];
+	u32 mxcsr = *(u32 *)&guest_xsave->region[XSAVE_MXCSR_OFFSET / sizeof(u32)];
 
 	if (boot_cpu_has(X86_FEATURE_XSAVE)) {
 		/*
@@ -3300,11 +3311,13 @@ static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu,
 		 * CPUID leaf 0xD, index 0, EDX:EAX.  This is for compatibility
 		 * with old userspace.
 		 */
-		if (xstate_bv & ~kvm_supported_xcr0())
+		if (xstate_bv & ~kvm_supported_xcr0() ||
+			mxcsr & ~mxcsr_feature_mask)
 			return -EINVAL;
 		load_xsave(vcpu, (u8 *)guest_xsave->region);
 	} else {
-		if (xstate_bv & ~XFEATURE_MASK_FPSSE)
+		if (xstate_bv & ~XFEATURE_MASK_FPSSE ||
+			mxcsr & ~mxcsr_feature_mask)
 			return -EINVAL;
 		memcpy(&vcpu->arch.guest_fpu.state.fxsave,
 			guest_xsave->region, sizeof(struct fxregs_state));
@@ -4818,16 +4831,20 @@ emul_write:
 
 static int kernel_pio(struct kvm_vcpu *vcpu, void *pd)
 {
-	/* TODO: String I/O for in kernel device */
-	int r;
+	int r = 0, i;
 
-	if (vcpu->arch.pio.in)
-		r = kvm_io_bus_read(vcpu, KVM_PIO_BUS, vcpu->arch.pio.port,
-				    vcpu->arch.pio.size, pd);
-	else
-		r = kvm_io_bus_write(vcpu, KVM_PIO_BUS,
-				     vcpu->arch.pio.port, vcpu->arch.pio.size,
-				     pd);
+	for (i = 0; i < vcpu->arch.pio.count; i++) {
+		if (vcpu->arch.pio.in)
+			r = kvm_io_bus_read(vcpu, KVM_PIO_BUS, vcpu->arch.pio.port,
+					    vcpu->arch.pio.size, pd);
+		else
+			r = kvm_io_bus_write(vcpu, KVM_PIO_BUS,
+					     vcpu->arch.pio.port, vcpu->arch.pio.size,
+					     pd);
+		if (r)
+			break;
+		pd += vcpu->arch.pio.size;
+	}
 	return r;
 }
 
@@ -4865,6 +4882,8 @@ static int emulator_pio_in_emulated(struct x86_emulate_ctxt *ctxt,
 	if (vcpu->arch.pio.count)
 		goto data_avail;
 
+	memset(vcpu->arch.pio_data, 0, size * count);
+
 	ret = emulator_pio_in_out(vcpu, size, port, val, count, true);
 	if (ret) {
 data_avail:
@@ -5048,6 +5067,8 @@ static bool emulator_get_segment(struct x86_emulate_ctxt *ctxt, u16 *selector,
 
 	if (var.unusable) {
 		memset(desc, 0, sizeof(*desc));
+		if (base3)
+			*base3 = 0;
 		return false;
 	}
 
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index 7cd442690f9d..f33eef4ebd12 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -142,9 +142,7 @@ static void __init xen_banner(void)
 	struct xen_extraversion extra;
 	HYPERVISOR_xen_version(XENVER_extraversion, &extra);
 
-	pr_info("Booting paravirtualized kernel %son %s\n",
-		xen_feature(XENFEAT_auto_translated_physmap) ?
-			"with PVH extensions " : "", pv_info.name);
+	pr_info("Booting paravirtualized kernel on %s\n", pv_info.name);
 	printk(KERN_INFO "Xen version: %d.%d%s%s\n",
 	       version >> 16, version & 0xffff, extra.extraversion,
 	       xen_feature(XENFEAT_mmu_pt_update_preserve_ad) ? " (preserve-AD)" : "");
@@ -957,15 +955,10 @@ static void xen_write_msr(unsigned int msr, unsigned low, unsigned high)
 
 void xen_setup_shared_info(void)
 {
-	if (!xen_feature(XENFEAT_auto_translated_physmap)) {
-		set_fixmap(FIX_PARAVIRT_BOOTMAP,
-			   xen_start_info->shared_info);
+	set_fixmap(FIX_PARAVIRT_BOOTMAP, xen_start_info->shared_info);
 
-		HYPERVISOR_shared_info =
-			(struct shared_info *)fix_to_virt(FIX_PARAVIRT_BOOTMAP);
-	} else
-		HYPERVISOR_shared_info =
-			(struct shared_info *)__va(xen_start_info->shared_info);
+	HYPERVISOR_shared_info =
+		(struct shared_info *)fix_to_virt(FIX_PARAVIRT_BOOTMAP);
 
 #ifndef CONFIG_SMP
 	/* In UP this is as good a place as any to set up shared info */
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 5e375a5e815f..3be06f3caf3c 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -42,7 +42,7 @@ xmaddr_t arbitrary_virt_to_machine(void *vaddr)
 }
 EXPORT_SYMBOL_GPL(arbitrary_virt_to_machine);
 
-void xen_flush_tlb_all(void)
+static void xen_flush_tlb_all(void)
 {
 	struct mmuext_op *op;
 	struct multicall_space mcs;
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index 7397d8b8459d..1f386d7fdf70 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -355,10 +355,8 @@ static pteval_t pte_pfn_to_mfn(pteval_t val)
 		pteval_t flags = val & PTE_FLAGS_MASK;
 		unsigned long mfn;
 
-		if (!xen_feature(XENFEAT_auto_translated_physmap))
-			mfn = __pfn_to_mfn(pfn);
-		else
-			mfn = pfn;
+		mfn = __pfn_to_mfn(pfn);
+
 		/*
 		 * If there's no mfn for the pfn, then just create an
 		 * empty non-present pte.  Unfortunately this loses
@@ -647,9 +645,6 @@ static int __xen_pgd_walk(struct mm_struct *mm, pgd_t *pgd,
 	limit--;
 	BUG_ON(limit >= FIXADDR_TOP);
 
-	if (xen_feature(XENFEAT_auto_translated_physmap))
-		return 0;
-
 	/*
 	 * 64-bit has a great big hole in the middle of the address
 	 * space, which contains the Xen mappings.  On 32-bit these
@@ -1289,9 +1284,6 @@ static void __init xen_pagetable_cleanhighmap(void)
 
 static void __init xen_pagetable_p2m_setup(void)
 {
-	if (xen_feature(XENFEAT_auto_translated_physmap))
-		return;
-
 	xen_vmalloc_p2m_tree();
 
 #ifdef CONFIG_X86_64
@@ -1314,8 +1306,7 @@ static void __init xen_pagetable_init(void)
 	xen_build_mfn_list_list();
 
 	/* Remap memory freed due to conflicts with E820 map */
-	if (!xen_feature(XENFEAT_auto_translated_physmap))
-		xen_remap_memory();
+	xen_remap_memory();
 
 	xen_setup_shared_info();
 }
@@ -1925,21 +1916,20 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
 	/* Zap identity mapping */
 	init_level4_pgt[0] = __pgd(0);
 
-	if (!xen_feature(XENFEAT_auto_translated_physmap)) {
-		/* Pre-constructed entries are in pfn, so convert to mfn */
-		/* L4[272] -> level3_ident_pgt
-		 * L4[511] -> level3_kernel_pgt */
-		convert_pfn_mfn(init_level4_pgt);
+	/* Pre-constructed entries are in pfn, so convert to mfn */
+	/* L4[272] -> level3_ident_pgt  */
+	/* L4[511] -> level3_kernel_pgt */
+	convert_pfn_mfn(init_level4_pgt);
 
-		/* L3_i[0] -> level2_ident_pgt */
-		convert_pfn_mfn(level3_ident_pgt);
-		/* L3_k[510] -> level2_kernel_pgt
-		 * L3_k[511] -> level2_fixmap_pgt */
-		convert_pfn_mfn(level3_kernel_pgt);
+	/* L3_i[0] -> level2_ident_pgt */
+	convert_pfn_mfn(level3_ident_pgt);
+	/* L3_k[510] -> level2_kernel_pgt */
+	/* L3_k[511] -> level2_fixmap_pgt */
+	convert_pfn_mfn(level3_kernel_pgt);
+
+	/* L3_k[511][506] -> level1_fixmap_pgt */
+	convert_pfn_mfn(level2_fixmap_pgt);
 
-		/* L3_k[511][506] -> level1_fixmap_pgt */
-		convert_pfn_mfn(level2_fixmap_pgt);
-	}
 	/* We get [511][511] and have Xen's version of level2_kernel_pgt */
 	l3 = m2v(pgd[pgd_index(__START_KERNEL_map)].pgd);
 	l2 = m2v(l3[pud_index(__START_KERNEL_map)].pud);
@@ -1962,34 +1952,30 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
 	if (i && i < pgd_index(__START_KERNEL_map))
 		init_level4_pgt[i] = ((pgd_t *)xen_start_info->pt_base)[i];
 
-	if (!xen_feature(XENFEAT_auto_translated_physmap)) {
-		/* Make pagetable pieces RO */
-		set_page_prot(init_level4_pgt, PAGE_KERNEL_RO);
-		set_page_prot(level3_ident_pgt, PAGE_KERNEL_RO);
-		set_page_prot(level3_kernel_pgt, PAGE_KERNEL_RO);
-		set_page_prot(level3_user_vsyscall, PAGE_KERNEL_RO);
-		set_page_prot(level2_ident_pgt, PAGE_KERNEL_RO);
-		set_page_prot(level2_kernel_pgt, PAGE_KERNEL_RO);
-		set_page_prot(level2_fixmap_pgt, PAGE_KERNEL_RO);
-		set_page_prot(level1_fixmap_pgt, PAGE_KERNEL_RO);
-
-		/* Pin down new L4 */
-		pin_pagetable_pfn(MMUEXT_PIN_L4_TABLE,
-				  PFN_DOWN(__pa_symbol(init_level4_pgt)));
-
-		/* Unpin Xen-provided one */
-		pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd)));
+	/* Make pagetable pieces RO */
+	set_page_prot(init_level4_pgt, PAGE_KERNEL_RO);
+	set_page_prot(level3_ident_pgt, PAGE_KERNEL_RO);
+	set_page_prot(level3_kernel_pgt, PAGE_KERNEL_RO);
+	set_page_prot(level3_user_vsyscall, PAGE_KERNEL_RO);
+	set_page_prot(level2_ident_pgt, PAGE_KERNEL_RO);
+	set_page_prot(level2_kernel_pgt, PAGE_KERNEL_RO);
+	set_page_prot(level2_fixmap_pgt, PAGE_KERNEL_RO);
+	set_page_prot(level1_fixmap_pgt, PAGE_KERNEL_RO);
+
+	/* Pin down new L4 */
+	pin_pagetable_pfn(MMUEXT_PIN_L4_TABLE,
+			  PFN_DOWN(__pa_symbol(init_level4_pgt)));
+
+	/* Unpin Xen-provided one */
+	pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd)));
 
-		/*
-		 * At this stage there can be no user pgd, and no page
-		 * structure to attach it to, so make sure we just set kernel
-		 * pgd.
-		 */
-		xen_mc_batch();
-		__xen_write_cr3(true, __pa(init_level4_pgt));
-		xen_mc_issue(PARAVIRT_LAZY_CPU);
-	} else
-		native_write_cr3(__pa(init_level4_pgt));
+	/*
+	 * At this stage there can be no user pgd, and no page structure to
+	 * attach it to, so make sure we just set kernel pgd.
+	 */
+	xen_mc_batch();
+	__xen_write_cr3(true, __pa(init_level4_pgt));
+	xen_mc_issue(PARAVIRT_LAZY_CPU);
 
 	/* We can't that easily rip out L3 and L2, as the Xen pagetables are
 	 * set out this way: [L4], [L1], [L2], [L3], [L1], [L1] ...  for
@@ -2403,9 +2389,6 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
 
 static void __init xen_post_allocator_init(void)
 {
-	if (xen_feature(XENFEAT_auto_translated_physmap))
-		return;
-
 	pv_mmu_ops.set_pte = xen_set_pte;
 	pv_mmu_ops.set_pmd = xen_set_pmd;
 	pv_mmu_ops.set_pud = xen_set_pud;
@@ -2511,9 +2494,6 @@ void __init xen_init_mmu_ops(void)
 {
 	x86_init.paging.pagetable_init = xen_pagetable_init;
 
-	if (xen_feature(XENFEAT_auto_translated_physmap))
-		return;
-
 	pv_mmu_ops = xen_mmu_ops;
 
 	memset(dummy_mapping, 0xff, PAGE_SIZE);
@@ -2650,9 +2630,6 @@ int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order,
 	 * this function are redundant and can be ignored.
 	 */
 
-	if (xen_feature(XENFEAT_auto_translated_physmap))
-		return 0;
-
 	if (unlikely(order > MAX_CONTIG_ORDER))
 		return -ENOMEM;
 
@@ -2689,9 +2666,6 @@ void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order)
 	int success;
 	unsigned long vstart;
 
-	if (xen_feature(XENFEAT_auto_translated_physmap))
-		return;
-
 	if (unlikely(order > MAX_CONTIG_ORDER))
 		return;