25 files changed, 211 insertions, 75 deletions

diff --git a/arch/arm/boot/dts/bcm2835-rpi.dtsi b/arch/arm/boot/dts/bcm2835-rpi.dtsi
index f7ae5a4530b8..d94357b21f7e 100644
--- a/arch/arm/boot/dts/bcm2835-rpi.dtsi
+++ b/arch/arm/boot/dts/bcm2835-rpi.dtsi
@@ -13,7 +13,7 @@
 
 	soc {
 		firmware: firmware {
-			compatible = "raspberrypi,bcm2835-firmware", "simple-bus";
+			compatible = "raspberrypi,bcm2835-firmware", "simple-mfd";
 			#address-cells = <1>;
 			#size-cells = <1>;
 
diff --git a/arch/arm/mach-imx/cpuidle-imx6q.c b/arch/arm/mach-imx/cpuidle-imx6q.c
index 24dd5bbe60e4..094337dc1bc7 100644
--- a/arch/arm/mach-imx/cpuidle-imx6q.c
+++ b/arch/arm/mach-imx/cpuidle-imx6q.c
@@ -24,7 +24,9 @@ static int imx6q_enter_wait(struct cpuidle_device *dev,
 		imx6_set_lpm(WAIT_UNCLOCKED);
 	raw_spin_unlock(&cpuidle_lock);
 
+	rcu_idle_enter();
 	cpu_do_idle();
+	rcu_idle_exit();
 
 	raw_spin_lock(&cpuidle_lock);
 	if (num_idle_cpus-- == num_online_cpus())
@@ -44,7 +46,7 @@ static struct cpuidle_driver imx6q_cpuidle_driver = {
 		{
 			.exit_latency = 50,
 			.target_residency = 75,
-			.flags = CPUIDLE_FLAG_TIMER_STOP,
+			.flags = CPUIDLE_FLAG_TIMER_STOP | CPUIDLE_FLAG_RCU_IDLE,
 			.enter = imx6q_enter_wait,
 			.name = "WAIT",
 			.desc = "Clock off",
diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c
index a85174d05473..cada0b816c8a 100644
--- a/arch/arm64/kernel/acpi.c
+++ b/arch/arm64/kernel/acpi.c
@@ -298,8 +298,21 @@ void __iomem *acpi_os_ioremap(acpi_physical_address phys, acpi_size size)
 		case EFI_BOOT_SERVICES_DATA:
 		case EFI_CONVENTIONAL_MEMORY:
 		case EFI_PERSISTENT_MEMORY:
-			pr_warn(FW_BUG "requested region covers kernel memory @ %pa\n", &phys);
-			return NULL;
+			if (memblock_is_map_memory(phys) ||
+			    !memblock_is_region_memory(phys, size)) {
+				pr_warn(FW_BUG "requested region covers kernel memory @ %pa\n", &phys);
+				return NULL;
+			}
+			/*
+			 * Mapping kernel memory is permitted if the region in
+			 * question is covered by a single memblock with the
+			 * NOMAP attribute set: this enables the use of ACPI
+			 * table overrides passed via initramfs, which are
+			 * reserved in memory using arch_reserve_mem_area()
+			 * below. As this particular use case only requires
+			 * read access, fall through to the R/O mapping case.
+			 */
+			fallthrough;
 
 		case EFI_RUNTIME_SERVICES_CODE:
 			/*
@@ -388,3 +401,8 @@ int apei_claim_sea(struct pt_regs *regs)
 
 	return err;
 }
+
+void arch_reserve_mem_area(acpi_physical_address addr, size_t size)
+{
+	memblock_mark_nomap(addr, size);
+}
diff --git a/arch/arm64/kvm/hyp/nvhe/tlb.c b/arch/arm64/kvm/hyp/nvhe/tlb.c
index 69eae608d670..b15d65a42042 100644
--- a/arch/arm64/kvm/hyp/nvhe/tlb.c
+++ b/arch/arm64/kvm/hyp/nvhe/tlb.c
@@ -31,7 +31,14 @@ static void __tlb_switch_to_guest(struct kvm_s2_mmu *mmu,
 		isb();
 	}
 
+	/*
+	 * __load_guest_stage2() includes an ISB only when the AT
+	 * workaround is applied. Take care of the opposite condition,
+	 * ensuring that we always have an ISB, but not two ISBs back
+	 * to back.
+	 */
 	__load_guest_stage2(mmu);
+	asm(ALTERNATIVE("isb", "nop", ARM64_WORKAROUND_SPECULATIVE_AT));
 }
 
 static void __tlb_switch_to_host(struct tlb_inv_context *cxt)
diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c
index 0b3fb4c7af29..8e7b8c6c576e 100644
--- a/arch/ia64/mm/init.c
+++ b/arch/ia64/mm/init.c
@@ -538,7 +538,7 @@ virtual_memmap_init(u64 start, u64 end, void *arg)
 	if (map_start < map_end)
 		memmap_init_zone((unsigned long)(map_end - map_start),
 				 args->nid, args->zone, page_to_pfn(map_start),
-				 MEMMAP_EARLY, NULL);
+				 MEMINIT_EARLY, NULL);
 	return 0;
 }
 
@@ -547,8 +547,8 @@ memmap_init (unsigned long size, int nid, unsigned long zone,
 	     unsigned long start_pfn)
 {
 	if (!vmem_map) {
-		memmap_init_zone(size, nid, zone, start_pfn, MEMMAP_EARLY,
-				NULL);
+		memmap_init_zone(size, nid, zone, start_pfn,
+				 MEMINIT_EARLY, NULL);
 	} else {
 		struct page *start;
 		struct memmap_init_callback_data args;
diff --git a/arch/mips/bcm47xx/setup.c b/arch/mips/bcm47xx/setup.c
index 82627c264964..01427bde2397 100644
--- a/arch/mips/bcm47xx/setup.c
+++ b/arch/mips/bcm47xx/setup.c
@@ -148,7 +148,7 @@ void __init plat_mem_setup(void)
 {
 	struct cpuinfo_mips *c = &current_cpu_data;
 
-	if ((c->cputype == CPU_74K) || (c->cputype == CPU_1074K)) {
+	if (c->cputype == CPU_74K) {
 		pr_info("Using bcma bus\n");
 #ifdef CONFIG_BCM47XX_BCMA
 		bcm47xx_bus_type = BCM47XX_BUS_TYPE_BCMA;
diff --git a/arch/mips/include/asm/cpu-type.h b/arch/mips/include/asm/cpu-type.h
index 75a7a382da09..3288cef4b168 100644
--- a/arch/mips/include/asm/cpu-type.h
+++ b/arch/mips/include/asm/cpu-type.h
@@ -47,6 +47,7 @@ static inline int __pure __get_cpu_type(const int cpu_type)
 	case CPU_34K:
 	case CPU_1004K:
 	case CPU_74K:
+	case CPU_1074K:
 	case CPU_M14KC:
 	case CPU_M14KEC:
 	case CPU_INTERAPTIV:
diff --git a/arch/mips/loongson2ef/Platform b/arch/mips/loongson2ef/Platform
index 4ab55f1123a0..ae023b9a1c51 100644
--- a/arch/mips/loongson2ef/Platform
+++ b/arch/mips/loongson2ef/Platform
@@ -44,6 +44,10 @@ ifdef CONFIG_CPU_LOONGSON2F_WORKAROUNDS
   endif
 endif
 
+# Some -march= flags enable MMI instructions, and GCC complains about that
+# support being enabled alongside -msoft-float. Thus explicitly disable MMI.
+cflags-y += $(call cc-option,-mno-loongson-mmi)
+
 #
 # Loongson Machines' Support
 #
diff --git a/arch/mips/loongson64/cop2-ex.c b/arch/mips/loongson64/cop2-ex.c
index f130f62129b8..00055d4b6042 100644
--- a/arch/mips/loongson64/cop2-ex.c
+++ b/arch/mips/loongson64/cop2-ex.c
@@ -95,10 +95,8 @@ static int loongson_cu2_call(struct notifier_block *nfb, unsigned long action,
 			if (res)
 				goto fault;
 
-			set_fpr64(current->thread.fpu.fpr,
-				insn.loongson3_lswc2_format.rt, value);
-			set_fpr64(current->thread.fpu.fpr,
-				insn.loongson3_lswc2_format.rq, value_next);
+			set_fpr64(&current->thread.fpu.fpr[insn.loongson3_lswc2_format.rt], 0, value);
+			set_fpr64(&current->thread.fpu.fpr[insn.loongson3_lswc2_format.rq], 0, value_next);
 			compute_return_epc(regs);
 			own_fpu(1);
 		}
@@ -130,15 +128,13 @@ static int loongson_cu2_call(struct notifier_block *nfb, unsigned long action,
 				goto sigbus;
 
 			lose_fpu(1);
-			value_next = get_fpr64(current->thread.fpu.fpr,
-					insn.loongson3_lswc2_format.rq);
+			value_next = get_fpr64(&current->thread.fpu.fpr[insn.loongson3_lswc2_format.rq], 0);
 
 			StoreDW(addr + 8, value_next, res);
 			if (res)
 				goto fault;
 
-			value = get_fpr64(current->thread.fpu.fpr,
-					insn.loongson3_lswc2_format.rt);
+			value = get_fpr64(&current->thread.fpu.fpr[insn.loongson3_lswc2_format.rt], 0);
 
 			StoreDW(addr, value, res);
 			if (res)
@@ -204,8 +200,7 @@ static int loongson_cu2_call(struct notifier_block *nfb, unsigned long action,
 			if (res)
 				goto fault;
 
-			set_fpr64(current->thread.fpu.fpr,
-					insn.loongson3_lsdc2_format.rt, value);
+			set_fpr64(&current->thread.fpu.fpr[insn.loongson3_lsdc2_format.rt], 0, value);
 			compute_return_epc(regs);
 			own_fpu(1);
 
@@ -221,8 +216,7 @@ static int loongson_cu2_call(struct notifier_block *nfb, unsigned long action,
 			if (res)
 				goto fault;
 
-			set_fpr64(current->thread.fpu.fpr,
-					insn.loongson3_lsdc2_format.rt, value);
+			set_fpr64(&current->thread.fpu.fpr[insn.loongson3_lsdc2_format.rt], 0, value);
 			compute_return_epc(regs);
 			own_fpu(1);
 			break;
@@ -286,8 +280,7 @@ static int loongson_cu2_call(struct notifier_block *nfb, unsigned long action,
 				goto sigbus;
 
 			lose_fpu(1);
-			value = get_fpr64(current->thread.fpu.fpr,
-					insn.loongson3_lsdc2_format.rt);
+			value = get_fpr64(&current->thread.fpu.fpr[insn.loongson3_lsdc2_format.rt], 0);
 
 			StoreW(addr, value, res);
 			if (res)
@@ -305,8 +298,7 @@ static int loongson_cu2_call(struct notifier_block *nfb, unsigned long action,
 				goto sigbus;
 
 			lose_fpu(1);
-			value = get_fpr64(current->thread.fpu.fpr,
-					insn.loongson3_lsdc2_format.rt);
+			value = get_fpr64(&current->thread.fpu.fpr[insn.loongson3_lsdc2_format.rt], 0);
 
 			StoreDW(addr, value, res);
 			if (res)
diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index 78d61f97371e..e809cb5a1631 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -475,7 +475,6 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
 		case BPF_JMP | BPF_JSET | BPF_K:
 		case BPF_JMP | BPF_JSET | BPF_X:
 			true_cond = COND_NE;
-			fallthrough;
 		cond_branch:
 			/* same targets, can avoid doing the test :) */
 			if (filter[i].jt == filter[i].jf) {
diff --git a/arch/riscv/include/asm/stackprotector.h b/arch/riscv/include/asm/stackprotector.h
index d95f7b2a7f37..5962f8891f06 100644
--- a/arch/riscv/include/asm/stackprotector.h
+++ b/arch/riscv/include/asm/stackprotector.h
@@ -5,7 +5,6 @@
 
 #include <linux/random.h>
 #include <linux/version.h>
-#include <asm/timex.h>
 
 extern unsigned long __stack_chk_guard;
 
@@ -18,12 +17,9 @@ extern unsigned long __stack_chk_guard;
 static __always_inline void boot_init_stack_canary(void)
 {
 	unsigned long canary;
-	unsigned long tsc;
 
 	/* Try to get a semi random initial value. */
 	get_random_bytes(&canary, sizeof(canary));
-	tsc = get_cycles();
-	canary += tsc + (tsc << BITS_PER_LONG/2);
 	canary ^= LINUX_VERSION_CODE;
 	canary &= CANARY_MASK;
 
diff --git a/arch/riscv/include/asm/timex.h b/arch/riscv/include/asm/timex.h
index 7f659dda0032..ab104905d4db 100644
--- a/arch/riscv/include/asm/timex.h
+++ b/arch/riscv/include/asm/timex.h
@@ -33,6 +33,19 @@ static inline u32 get_cycles_hi(void)
 #define get_cycles_hi get_cycles_hi
 #endif /* CONFIG_64BIT */
 
+/*
+ * Much like MIPS, we may not have a viable counter to use at an early point
+ * in the boot process. Unfortunately we don't have a fallback, so instead
+ * we just return 0.
+ */
+static inline unsigned long random_get_entropy(void)
+{
+	if (unlikely(clint_time_val == NULL))
+		return 0;
+	return get_cycles();
+}
+#define random_get_entropy()	random_get_entropy()
+
 #else /* CONFIG_RISCV_M_MODE */
 
 static inline cycles_t get_cycles(void)
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 7eb01a5459cd..b55561cc8786 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -1260,26 +1260,44 @@ static inline pgd_t *pgd_offset_raw(pgd_t *pgd, unsigned long address)
 
 #define pgd_offset(mm, address) pgd_offset_raw(READ_ONCE((mm)->pgd), address)
 
-static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address)
+static inline p4d_t *p4d_offset_lockless(pgd_t *pgdp, pgd_t pgd, unsigned long address)
 {
-	if ((pgd_val(*pgd) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R1)
-		return (p4d_t *) pgd_deref(*pgd) + p4d_index(address);
-	return (p4d_t *) pgd;
+	if ((pgd_val(pgd) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R1)
+		return (p4d_t *) pgd_deref(pgd) + p4d_index(address);
+	return (p4d_t *) pgdp;
 }
+#define p4d_offset_lockless p4d_offset_lockless
 
-static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address)
+static inline p4d_t *p4d_offset(pgd_t *pgdp, unsigned long address)
 {
-	if ((p4d_val(*p4d) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R2)
-		return (pud_t *) p4d_deref(*p4d) + pud_index(address);
-	return (pud_t *) p4d;
+	return p4d_offset_lockless(pgdp, *pgdp, address);
+}
+
+static inline pud_t *pud_offset_lockless(p4d_t *p4dp, p4d_t p4d, unsigned long address)
+{
+	if ((p4d_val(p4d) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R2)
+		return (pud_t *) p4d_deref(p4d) + pud_index(address);
+	return (pud_t *) p4dp;
+}
+#define pud_offset_lockless pud_offset_lockless
+
+static inline pud_t *pud_offset(p4d_t *p4dp, unsigned long address)
+{
+	return pud_offset_lockless(p4dp, *p4dp, address);
 }
 #define pud_offset pud_offset
 
-static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address)
+static inline pmd_t *pmd_offset_lockless(pud_t *pudp, pud_t pud, unsigned long address)
+{
+	if ((pud_val(pud) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R3)
+		return (pmd_t *) pud_deref(pud) + pmd_index(address);
+	return (pmd_t *) pudp;
+}
+#define pmd_offset_lockless pmd_offset_lockless
+
+static inline pmd_t *pmd_offset(pud_t *pudp, unsigned long address)
 {
-	if ((pud_val(*pud) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R3)
-		return (pmd_t *) pud_deref(*pud) + pmd_index(address);
-	return (pmd_t *) pud;
+	return pmd_offset_lockless(pudp, *pudp, address);
 }
 #define pmd_offset pmd_offset
 
diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index 2f84c7ca74ea..870efeec8bda 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -299,7 +299,7 @@ __visible noinstr void xen_pv_evtchn_do_upcall(struct pt_regs *regs)
 	old_regs = set_irq_regs(regs);
 
 	instrumentation_begin();
-	run_on_irqstack_cond(__xen_pv_evtchn_do_upcall, NULL, regs);
+	run_on_irqstack_cond(__xen_pv_evtchn_do_upcall, regs);
 	instrumentation_begin();
 
 	set_irq_regs(old_regs);
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 70dea9337816..d977079a7d02 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -682,6 +682,8 @@ SYM_CODE_END(.Lbad_gs)
  * rdx: Function argument (can be NULL if none)
  */
 SYM_FUNC_START(asm_call_on_stack)
+SYM_INNER_LABEL(asm_call_sysvec_on_stack, SYM_L_GLOBAL)
+SYM_INNER_LABEL(asm_call_irq_on_stack, SYM_L_GLOBAL)
 	/*
 	 * Save the frame pointer unconditionally. This allows the ORC
 	 * unwinder to handle the stack switch.
diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h
index a43366191212..a0638640f1ed 100644
--- a/arch/x86/include/asm/idtentry.h
+++ b/arch/x86/include/asm/idtentry.h
@@ -242,7 +242,7 @@ __visible noinstr void func(struct pt_regs *regs)			\
 	instrumentation_begin();					\
 	irq_enter_rcu();						\
 	kvm_set_cpu_l1tf_flush_l1d();					\
-	run_on_irqstack_cond(__##func, regs, regs);			\
+	run_sysvec_on_irqstack_cond(__##func, regs);			\
 	irq_exit_rcu();							\
 	instrumentation_end();						\
 	irqentry_exit(regs, state);					\
diff --git a/arch/x86/include/asm/irq_stack.h b/arch/x86/include/asm/irq_stack.h
index 4ae66f097101..775816965c6a 100644
--- a/arch/x86/include/asm/irq_stack.h
+++ b/arch/x86/include/asm/irq_stack.h
@@ -12,20 +12,50 @@ static __always_inline bool irqstack_active(void)
 	return __this_cpu_read(irq_count) != -1;
 }
 
-void asm_call_on_stack(void *sp, void *func, void *arg);
+void asm_call_on_stack(void *sp, void (*func)(void), void *arg);
+void asm_call_sysvec_on_stack(void *sp, void (*func)(struct pt_regs *regs),
+			      struct pt_regs *regs);
+void asm_call_irq_on_stack(void *sp, void (*func)(struct irq_desc *desc),
+			   struct irq_desc *desc);
 
-static __always_inline void __run_on_irqstack(void *func, void *arg)
+static __always_inline void __run_on_irqstack(void (*func)(void))
 {
 	void *tos = __this_cpu_read(hardirq_stack_ptr);
 
 	__this_cpu_add(irq_count, 1);
-	asm_call_on_stack(tos - 8, func, arg);
+	asm_call_on_stack(tos - 8, func, NULL);
+	__this_cpu_sub(irq_count, 1);
+}
+
+static __always_inline void
+__run_sysvec_on_irqstack(void (*func)(struct pt_regs *regs),
+			 struct pt_regs *regs)
+{
+	void *tos = __this_cpu_read(hardirq_stack_ptr);
+
+	__this_cpu_add(irq_count, 1);
+	asm_call_sysvec_on_stack(tos - 8, func, regs);
+	__this_cpu_sub(irq_count, 1);
+}
+
+static __always_inline void
+__run_irq_on_irqstack(void (*func)(struct irq_desc *desc),
+		      struct irq_desc *desc)
+{
+	void *tos = __this_cpu_read(hardirq_stack_ptr);
+
+	__this_cpu_add(irq_count, 1);
+	asm_call_irq_on_stack(tos - 8, func, desc);
 	__this_cpu_sub(irq_count, 1);
 }
 
 #else /* CONFIG_X86_64 */
 static inline bool irqstack_active(void) { return false; }
-static inline void __run_on_irqstack(void *func, void *arg) { }
+static inline void __run_on_irqstack(void (*func)(void)) { }
+static inline void __run_sysvec_on_irqstack(void (*func)(struct pt_regs *regs),
+					    struct pt_regs *regs) { }
+static inline void __run_irq_on_irqstack(void (*func)(struct irq_desc *desc),
+					 struct irq_desc *desc) { }
 #endif /* !CONFIG_X86_64 */
 
 static __always_inline bool irq_needs_irq_stack(struct pt_regs *regs)
@@ -37,17 +67,40 @@ static __always_inline bool irq_needs_irq_stack(struct pt_regs *regs)
 	return !user_mode(regs) && !irqstack_active();
 }
 
-static __always_inline void run_on_irqstack_cond(void *func, void *arg,
+
+static __always_inline void run_on_irqstack_cond(void (*func)(void),
 						 struct pt_regs *regs)
 {
-	void (*__func)(void *arg) = func;
+	lockdep_assert_irqs_disabled();
+
+	if (irq_needs_irq_stack(regs))
+		__run_on_irqstack(func);
+	else
+		func();
+}
+
+static __always_inline void
+run_sysvec_on_irqstack_cond(void (*func)(struct pt_regs *regs),
+			    struct pt_regs *regs)
+{
+	lockdep_assert_irqs_disabled();
 
+	if (irq_needs_irq_stack(regs))
+		__run_sysvec_on_irqstack(func, regs);
+	else
+		func(regs);
+}
+
+static __always_inline void
+run_irq_on_irqstack_cond(void (*func)(struct irq_desc *desc), struct irq_desc *desc,
+			 struct pt_regs *regs)
+{
 	lockdep_assert_irqs_disabled();
 
 	if (irq_needs_irq_stack(regs))
-		__run_on_irqstack(__func, arg);
+		__run_irq_on_irqstack(func, desc);
 	else
-		__func(arg);
+		func(desc);
 }
 
 #endif
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 779a89e31c4c..21f9c7f11779 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -2243,6 +2243,7 @@ static inline void __init check_timer(void)
 	legacy_pic->init(0);
 	legacy_pic->make_irq(0);
 	apic_write(APIC_LVT0, APIC_DM_EXTINT);
+	legacy_pic->unmask(0);
 
 	unlock_ExtINT_logic();
 
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 181060247e3c..c5dd50369e2f 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -227,7 +227,7 @@ static __always_inline void handle_irq(struct irq_desc *desc,
 				       struct pt_regs *regs)
 {
 	if (IS_ENABLED(CONFIG_X86_64))
-		run_on_irqstack_cond(desc->handle_irq, desc, regs);
+		run_irq_on_irqstack_cond(desc->handle_irq, desc, regs);
 	else
 		__handle_irq(desc, regs);
 }
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index 1b4fe93a86c5..440eed558558 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -74,5 +74,5 @@ int irq_init_percpu_irqstack(unsigned int cpu)
 
 void do_softirq_own_stack(void)
 {
-	run_on_irqstack_cond(__do_softirq, NULL, NULL);
+	run_on_irqstack_cond(__do_softirq, NULL);
 }
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index c44f3e9140d5..91ea74ae71b8 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -2183,6 +2183,12 @@ static int iret_interception(struct vcpu_svm *svm)
 	return 1;
 }
 
+static int invd_interception(struct vcpu_svm *svm)
+{
+	/* Treat an INVD instruction as a NOP and just skip it. */
+	return kvm_skip_emulated_instruction(&svm->vcpu);
+}
+
 static int invlpg_interception(struct vcpu_svm *svm)
 {
 	if (!static_cpu_has(X86_FEATURE_DECODEASSISTS))
@@ -2774,7 +2780,7 @@ static int (*const svm_exit_handlers[])(struct vcpu_svm *svm) = {
 	[SVM_EXIT_RDPMC]			= rdpmc_interception,
 	[SVM_EXIT_CPUID]			= cpuid_interception,
 	[SVM_EXIT_IRET]                         = iret_interception,
-	[SVM_EXIT_INVD]                         = emulate_on_interception,
+	[SVM_EXIT_INVD]                         = invd_interception,
 	[SVM_EXIT_PAUSE]			= pause_interception,
 	[SVM_EXIT_HLT]				= halt_interception,
 	[SVM_EXIT_INVLPG]			= invlpg_interception,
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 8646a797b7a8..96979c09ebd1 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -129,6 +129,9 @@ static bool __read_mostly enable_preemption_timer = 1;
 module_param_named(preemption_timer, enable_preemption_timer, bool, S_IRUGO);
 #endif
 
+extern bool __read_mostly allow_smaller_maxphyaddr;
+module_param(allow_smaller_maxphyaddr, bool, S_IRUGO);
+
 #define KVM_VM_CR0_ALWAYS_OFF (X86_CR0_NW | X86_CR0_CD)
 #define KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST X86_CR0_NE
 #define KVM_VM_CR0_ALWAYS_ON				\
@@ -791,6 +794,18 @@ void update_exception_bitmap(struct kvm_vcpu *vcpu)
 	 */
 	if (is_guest_mode(vcpu))
 		eb |= get_vmcs12(vcpu)->exception_bitmap;
+        else {
+		/*
+		 * If EPT is enabled, #PF is only trapped if MAXPHYADDR is mismatched
+		 * between guest and host.  In that case we only care about present
+		 * faults.  For vmcs02, however, PFEC_MASK and PFEC_MATCH are set in
+		 * prepare_vmcs02_rare.
+		 */
+		bool selective_pf_trap = enable_ept && (eb & (1u << PF_VECTOR));
+		int mask = selective_pf_trap ? PFERR_PRESENT_MASK : 0;
+		vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK, mask);
+		vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH, mask);
+	}
 
 	vmcs_write32(EXCEPTION_BITMAP, eb);
 }
@@ -4352,16 +4367,6 @@ static void init_vmcs(struct vcpu_vmx *vmx)
 		vmx->pt_desc.guest.output_mask = 0x7F;
 		vmcs_write64(GUEST_IA32_RTIT_CTL, 0);
 	}
-
-	/*
-	 * If EPT is enabled, #PF is only trapped if MAXPHYADDR is mismatched
-	 * between guest and host.  In that case we only care about present
-	 * faults.
-	 */
-	if (enable_ept) {
-		vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK, PFERR_PRESENT_MASK);
-		vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH, PFERR_PRESENT_MASK);
-	}
 }
 
 static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
@@ -4803,6 +4808,7 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu)
 			 * EPT will cause page fault only if we need to
 			 * detect illegal GPAs.
 			 */
+			WARN_ON_ONCE(!allow_smaller_maxphyaddr);
 			kvm_fixup_and_inject_pf_error(vcpu, cr2, error_code);
 			return 1;
 		} else
@@ -5331,7 +5337,7 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu)
 	 * would also use advanced VM-exit information for EPT violations to
 	 * reconstruct the page fault error code.
 	 */
-	if (unlikely(kvm_mmu_is_illegal_gpa(vcpu, gpa)))
+	if (unlikely(allow_smaller_maxphyaddr && kvm_mmu_is_illegal_gpa(vcpu, gpa)))
 		return kvm_emulate_instruction(vcpu, 0);
 
 	return kvm_mmu_page_fault(vcpu, gpa, error_code, NULL, 0);
@@ -8305,11 +8311,12 @@ static int __init vmx_init(void)
 	vmx_check_vmcs12_offsets();
 
 	/*
-	 * Intel processors don't have problems with
-	 * GUEST_MAXPHYADDR < HOST_MAXPHYADDR so enable
-	 * it for VMX by default
+	 * Shadow paging doesn't have a (further) performance penalty
+	 * from GUEST_MAXPHYADDR < HOST_MAXPHYADDR so enable it
+	 * by default
 	 */
-	allow_smaller_maxphyaddr = true;
+	if (!enable_ept)
+		allow_smaller_maxphyaddr = true;
 
 	return 0;
 }
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index a2f82127c170..a0e47720f60c 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -552,7 +552,10 @@ static inline bool vmx_has_waitpkg(struct vcpu_vmx *vmx)
 
 static inline bool vmx_need_pf_intercept(struct kvm_vcpu *vcpu)
 {
-	return !enable_ept || cpuid_maxphyaddr(vcpu) < boot_cpu_data.x86_phys_bits;
+	if (!enable_ept)
+		return true;
+
+	return allow_smaller_maxphyaddr && cpuid_maxphyaddr(vcpu) < boot_cpu_data.x86_phys_bits;
 }
 
 void dump_vmcs(void);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 1994602a0851..ce856e0ece84 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -188,7 +188,7 @@ static struct kvm_shared_msrs __percpu *shared_msrs;
 u64 __read_mostly host_efer;
 EXPORT_SYMBOL_GPL(host_efer);
 
-bool __read_mostly allow_smaller_maxphyaddr;
+bool __read_mostly allow_smaller_maxphyaddr = 0;
 EXPORT_SYMBOL_GPL(allow_smaller_maxphyaddr);
 
 static u64 __read_mostly host_xss;
@@ -976,6 +976,7 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 	unsigned long old_cr4 = kvm_read_cr4(vcpu);
 	unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE |
 				   X86_CR4_SMEP;
+	unsigned long mmu_role_bits = pdptr_bits | X86_CR4_SMAP | X86_CR4_PKE;
 
 	if (kvm_valid_cr4(vcpu, cr4))
 		return 1;
@@ -1003,7 +1004,7 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 	if (kvm_x86_ops.set_cr4(vcpu, cr4))
 		return 1;
 
-	if (((cr4 ^ old_cr4) & pdptr_bits) ||
+	if (((cr4 ^ old_cr4) & mmu_role_bits) ||
 	    (!(cr4 & X86_CR4_PCIDE) && (old_cr4 & X86_CR4_PCIDE)))
 		kvm_mmu_reset_context(vcpu);
 
@@ -3221,9 +3222,22 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_IA32_POWER_CTL:
 		msr_info->data = vcpu->arch.msr_ia32_power_ctl;
 		break;
-	case MSR_IA32_TSC:
-		msr_info->data = kvm_scale_tsc(vcpu, rdtsc()) + vcpu->arch.tsc_offset;
+	case MSR_IA32_TSC: {
+		/*
+		 * Intel SDM states that MSR_IA32_TSC read adds the TSC offset
+		 * even when not intercepted. AMD manual doesn't explicitly
+		 * state this but appears to behave the same.
+		 *
+		 * On userspace reads and writes, however, we unconditionally
+		 * operate L1's TSC value to ensure backwards-compatible
+		 * behavior for migration.
+		 */
+		u64 tsc_offset = msr_info->host_initiated ? vcpu->arch.l1_tsc_offset :
+							    vcpu->arch.tsc_offset;
+
+		msr_info->data = kvm_scale_tsc(vcpu, rdtsc()) + tsc_offset;
 		break;
+	}
 	case MSR_MTRRcap:
 	case 0x200 ... 0x2ff:
 		return kvm_mtrr_get_msr(vcpu, msr_info->index, &msr_info->data);
diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c
index b0dfac3d3df7..1847e993ac63 100644
--- a/arch/x86/lib/usercopy_64.c
+++ b/arch/x86/lib/usercopy_64.c
@@ -120,7 +120,7 @@ long __copy_user_flushcache(void *dst, const void __user *src, unsigned size)
 	 */
 	if (size < 8) {
 		if (!IS_ALIGNED(dest, 4) || size != 4)
-			clean_cache_range(dst, 1);
+			clean_cache_range(dst, size);
 	} else {
 		if (!IS_ALIGNED(dest, 8)) {
 			dest = ALIGN(dest, boot_cpu_data.x86_clflush_size);