22 files changed, 180 insertions, 71 deletions

diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c
index 94a666dd1443..2642e9ce2819 100644
--- a/arch/arm64/kvm/vgic/vgic-its.c
+++ b/arch/arm64/kvm/vgic/vgic-its.c
@@ -2187,7 +2187,7 @@ static int vgic_its_save_ite(struct vgic_its *its, struct its_device *dev,
 	       ((u64)ite->irq->intid << KVM_ITS_ITE_PINTID_SHIFT) |
 		ite->collection->collection_id;
 	val = cpu_to_le64(val);
-	return kvm_write_guest_lock(kvm, gpa, &val, ite_esz);
+	return vgic_write_guest_lock(kvm, gpa, &val, ite_esz);
 }
 
 /**
@@ -2339,7 +2339,7 @@ static int vgic_its_save_dte(struct vgic_its *its, struct its_device *dev,
 	       (itt_addr_field << KVM_ITS_DTE_ITTADDR_SHIFT) |
 		(dev->num_eventid_bits - 1));
 	val = cpu_to_le64(val);
-	return kvm_write_guest_lock(kvm, ptr, &val, dte_esz);
+	return vgic_write_guest_lock(kvm, ptr, &val, dte_esz);
 }
 
 /**
@@ -2526,7 +2526,7 @@ static int vgic_its_save_cte(struct vgic_its *its,
 	       ((u64)collection->target_addr << KVM_ITS_CTE_RDBASE_SHIFT) |
 	       collection->collection_id);
 	val = cpu_to_le64(val);
-	return kvm_write_guest_lock(its->dev->kvm, gpa, &val, esz);
+	return vgic_write_guest_lock(its->dev->kvm, gpa, &val, esz);
 }
 
 /*
@@ -2607,7 +2607,7 @@ static int vgic_its_save_collection_table(struct vgic_its *its)
 	 */
 	val = 0;
 	BUG_ON(cte_esz > sizeof(val));
-	ret = kvm_write_guest_lock(its->dev->kvm, gpa, &val, cte_esz);
+	ret = vgic_write_guest_lock(its->dev->kvm, gpa, &val, cte_esz);
 	return ret;
 }
 
@@ -2743,7 +2743,6 @@ static int vgic_its_has_attr(struct kvm_device *dev,
 static int vgic_its_ctrl(struct kvm *kvm, struct vgic_its *its, u64 attr)
 {
 	const struct vgic_its_abi *abi = vgic_its_get_abi(its);
-	struct vgic_dist *dist = &kvm->arch.vgic;
 	int ret = 0;
 
 	if (attr == KVM_DEV_ARM_VGIC_CTRL_INIT) /* Nothing to do */
@@ -2763,9 +2762,7 @@ static int vgic_its_ctrl(struct kvm *kvm, struct vgic_its *its, u64 attr)
 		vgic_its_reset(kvm, its);
 		break;
 	case KVM_DEV_ARM_ITS_SAVE_TABLES:
-		dist->save_its_tables_in_progress = true;
 		ret = abi->save_tables(its);
-		dist->save_its_tables_in_progress = false;
 		break;
 	case KVM_DEV_ARM_ITS_RESTORE_TABLES:
 		ret = abi->restore_tables(its);
@@ -2792,7 +2789,7 @@ bool kvm_arch_allow_write_without_running_vcpu(struct kvm *kvm)
 {
 	struct vgic_dist *dist = &kvm->arch.vgic;
 
-	return dist->save_its_tables_in_progress;
+	return dist->table_write_in_progress;
 }
 
 static int vgic_its_set_attr(struct kvm_device *dev,
diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c
index 2624963cb95b..684bdfaad4a9 100644
--- a/arch/arm64/kvm/vgic/vgic-v3.c
+++ b/arch/arm64/kvm/vgic/vgic-v3.c
@@ -339,7 +339,7 @@ retry:
 	if (status) {
 		/* clear consumed data */
 		val &= ~(1 << bit_nr);
-		ret = kvm_write_guest_lock(kvm, ptr, &val, 1);
+		ret = vgic_write_guest_lock(kvm, ptr, &val, 1);
 		if (ret)
 			return ret;
 	}
@@ -434,7 +434,7 @@ int vgic_v3_save_pending_tables(struct kvm *kvm)
 		else
 			val &= ~(1 << bit_nr);
 
-		ret = kvm_write_guest_lock(kvm, ptr, &val, 1);
+		ret = vgic_write_guest_lock(kvm, ptr, &val, 1);
 		if (ret)
 			goto out;
 	}
diff --git a/arch/arm64/kvm/vgic/vgic.h b/arch/arm64/kvm/vgic/vgic.h
index 23e280fa0a16..7f7f3c5ed85a 100644
--- a/arch/arm64/kvm/vgic/vgic.h
+++ b/arch/arm64/kvm/vgic/vgic.h
@@ -6,6 +6,7 @@
 #define __KVM_ARM_VGIC_NEW_H__
 
 #include <linux/irqchip/arm-gic-common.h>
+#include <asm/kvm_mmu.h>
 
 #define PRODUCT_ID_KVM		0x4b	/* ASCII code K */
 #define IMPLEMENTER_ARM		0x43b
@@ -131,6 +132,19 @@ static inline bool vgic_irq_is_multi_sgi(struct vgic_irq *irq)
 	return vgic_irq_get_lr_count(irq) > 1;
 }
 
+static inline int vgic_write_guest_lock(struct kvm *kvm, gpa_t gpa,
+					const void *data, unsigned long len)
+{
+	struct vgic_dist *dist = &kvm->arch.vgic;
+	int ret;
+
+	dist->table_write_in_progress = true;
+	ret = kvm_write_guest_lock(kvm, gpa, data, len);
+	dist->table_write_in_progress = false;
+
+	return ret;
+}
+
 /*
  * This struct provides an intermediate representation of the fields contained
  * in the GICH_VMCR and ICH_VMCR registers, such that code exporting the GIC
diff --git a/arch/ia64/kernel/sys_ia64.c b/arch/ia64/kernel/sys_ia64.c
index f6a502e8f02c..6e948d015332 100644
--- a/arch/ia64/kernel/sys_ia64.c
+++ b/arch/ia64/kernel/sys_ia64.c
@@ -170,6 +170,9 @@ ia64_mremap (unsigned long addr, unsigned long old_len, unsigned long new_len, u
 asmlinkage long
 ia64_clock_getres(const clockid_t which_clock, struct __kernel_timespec __user *tp)
 {
+	struct timespec64 rtn_tp;
+	s64 tick_ns;
+
 	/*
 	 * ia64's clock_gettime() syscall is implemented as a vdso call
 	 * fsys_clock_gettime(). Currently it handles only
@@ -185,8 +188,8 @@ ia64_clock_getres(const clockid_t which_clock, struct __kernel_timespec __user *
 	switch (which_clock) {
 	case CLOCK_REALTIME:
 	case CLOCK_MONOTONIC:
-		s64 tick_ns = DIV_ROUND_UP(NSEC_PER_SEC, local_cpu_data->itc_freq);
-		struct timespec64 rtn_tp = ns_to_timespec64(tick_ns);
+		tick_ns = DIV_ROUND_UP(NSEC_PER_SEC, local_cpu_data->itc_freq);
+		rtn_tp = ns_to_timespec64(tick_ns);
 		return put_timespec64(&rtn_tp, tp);
 	}
 
diff --git a/arch/parisc/kernel/firmware.c b/arch/parisc/kernel/firmware.c
index 4dfe1f49c5c8..6817892a2c58 100644
--- a/arch/parisc/kernel/firmware.c
+++ b/arch/parisc/kernel/firmware.c
@@ -1303,7 +1303,7 @@ static char iodc_dbuf[4096] __page_aligned_bss;
  */
 int pdc_iodc_print(const unsigned char *str, unsigned count)
 {
-	unsigned int i;
+	unsigned int i, found = 0;
 	unsigned long flags;
 
 	count = min_t(unsigned int, count, sizeof(iodc_dbuf));
@@ -1315,6 +1315,7 @@ int pdc_iodc_print(const unsigned char *str, unsigned count)
 			iodc_dbuf[i+0] = '\r';
 			iodc_dbuf[i+1] = '\n';
 			i += 2;
+			found = 1;
 			goto print;
 		default:
 			iodc_dbuf[i] = str[i];
@@ -1330,7 +1331,7 @@ print:
 		__pa(pdc_result), 0, __pa(iodc_dbuf), i, 0);
 	spin_unlock_irqrestore(&pdc_lock, flags);
 
-	return i;
+	return i - found;
 }
 
 #if !defined(BOOTLOADER)
diff --git a/arch/parisc/kernel/ptrace.c b/arch/parisc/kernel/ptrace.c
index 69c62933e952..ceb45f51d52e 100644
--- a/arch/parisc/kernel/ptrace.c
+++ b/arch/parisc/kernel/ptrace.c
@@ -126,6 +126,12 @@ long arch_ptrace(struct task_struct *child, long request,
 	unsigned long tmp;
 	long ret = -EIO;
 
+	unsigned long user_regs_struct_size = sizeof(struct user_regs_struct);
+#ifdef CONFIG_64BIT
+	if (is_compat_task())
+		user_regs_struct_size /= 2;
+#endif
+
 	switch (request) {
 
 	/* Read the word at location addr in the USER area.  For ptraced
@@ -166,7 +172,7 @@ long arch_ptrace(struct task_struct *child, long request,
 		     addr >= sizeof(struct pt_regs))
 			break;
 		if (addr == PT_IAOQ0 || addr == PT_IAOQ1) {
-			data |= 3; /* ensure userspace privilege */
+			data |= PRIV_USER; /* ensure userspace privilege */
 		}
 		if ((addr >= PT_GR1 && addr <= PT_GR31) ||
 				addr == PT_IAOQ0 || addr == PT_IAOQ1 ||
@@ -181,14 +187,14 @@ long arch_ptrace(struct task_struct *child, long request,
 		return copy_regset_to_user(child,
 					   task_user_regset_view(current),
 					   REGSET_GENERAL,
-					   0, sizeof(struct user_regs_struct),
+					   0, user_regs_struct_size,
 					   datap);
 
 	case PTRACE_SETREGS:	/* Set all gp regs in the child. */
 		return copy_regset_from_user(child,
 					     task_user_regset_view(current),
 					     REGSET_GENERAL,
-					     0, sizeof(struct user_regs_struct),
+					     0, user_regs_struct_size,
 					     datap);
 
 	case PTRACE_GETFPREGS:	/* Get the child FPU state. */
@@ -285,7 +291,7 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
 			if (addr >= sizeof(struct pt_regs))
 				break;
 			if (addr == PT_IAOQ0+4 || addr == PT_IAOQ1+4) {
-				data |= 3; /* ensure userspace privilege */
+				data |= PRIV_USER; /* ensure userspace privilege */
 			}
 			if (addr >= PT_FR0 && addr <= PT_FR31 + 4) {
 				/* Special case, fp regs are 64 bits anyway */
@@ -302,6 +308,11 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
 			}
 		}
 		break;
+	case PTRACE_GETREGS:
+	case PTRACE_SETREGS:
+	case PTRACE_GETFPREGS:
+	case PTRACE_SETFPREGS:
+		return arch_ptrace(child, request, addr, data);
 
 	default:
 		ret = compat_ptrace_request(child, request, addr, data);
@@ -484,7 +495,7 @@ static void set_reg(struct pt_regs *regs, int num, unsigned long val)
 	case RI(iaoq[0]):
 	case RI(iaoq[1]):
 			/* set 2 lowest bits to ensure userspace privilege: */
-			regs->iaoq[num - RI(iaoq[0])] = val | 3;
+			regs->iaoq[num - RI(iaoq[0])] = val | PRIV_USER;
 			return;
 	case RI(sar):	regs->sar = val;
 			return;
diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush.h b/arch/powerpc/include/asm/book3s/64/tlbflush.h
index dd39313242b4..d5cd16270c5d 100644
--- a/arch/powerpc/include/asm/book3s/64/tlbflush.h
+++ b/arch/powerpc/include/asm/book3s/64/tlbflush.h
@@ -97,6 +97,8 @@ static inline void tlb_flush(struct mmu_gather *tlb)
 {
 	if (radix_enabled())
 		radix__tlb_flush(tlb);
+
+	return hash__tlb_flush(tlb);
 }
 
 #ifdef CONFIG_SMP
diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h
index 77fa88c2aed0..eb6d094083fd 100644
--- a/arch/powerpc/include/asm/hw_irq.h
+++ b/arch/powerpc/include/asm/hw_irq.h
@@ -173,6 +173,15 @@ static inline notrace unsigned long irq_soft_mask_or_return(unsigned long mask)
 	return flags;
 }
 
+static inline notrace unsigned long irq_soft_mask_andc_return(unsigned long mask)
+{
+	unsigned long flags = irq_soft_mask_return();
+
+	irq_soft_mask_set(flags & ~mask);
+
+	return flags;
+}
+
 static inline unsigned long arch_local_save_flags(void)
 {
 	return irq_soft_mask_return();
@@ -192,7 +201,7 @@ static inline void arch_local_irq_enable(void)
 
 static inline unsigned long arch_local_irq_save(void)
 {
-	return irq_soft_mask_set_return(IRQS_DISABLED);
+	return irq_soft_mask_or_return(IRQS_DISABLED);
 }
 
 static inline bool arch_irqs_disabled_flags(unsigned long flags)
@@ -331,10 +340,11 @@ bool power_pmu_wants_prompt_pmi(void);
  * is a different soft-masked interrupt pending that requires hard
  * masking.
  */
-static inline bool should_hard_irq_enable(void)
+static inline bool should_hard_irq_enable(struct pt_regs *regs)
 {
 	if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) {
-		WARN_ON(irq_soft_mask_return() == IRQS_ENABLED);
+		WARN_ON(irq_soft_mask_return() != IRQS_ALL_DISABLED);
+		WARN_ON(!(get_paca()->irq_happened & PACA_IRQ_HARD_DIS));
 		WARN_ON(mfmsr() & MSR_EE);
 	}
 
@@ -347,8 +357,17 @@ static inline bool should_hard_irq_enable(void)
 	 *
 	 * TODO: Add test for 64e
 	 */
-	if (IS_ENABLED(CONFIG_PPC_BOOK3S_64) && !power_pmu_wants_prompt_pmi())
-		return false;
+	if (IS_ENABLED(CONFIG_PPC_BOOK3S_64)) {
+		if (!power_pmu_wants_prompt_pmi())
+			return false;
+		/*
+		 * If PMIs are disabled then IRQs should be disabled as well,
+		 * so we shouldn't see this condition, check for it just in
+		 * case because we are about to enable PMIs.
+		 */
+		if (WARN_ON_ONCE(regs->softe & IRQS_PMI_DISABLED))
+			return false;
+	}
 
 	if (get_paca()->irq_happened & PACA_IRQ_MUST_HARD_MASK)
 		return false;
@@ -358,18 +377,16 @@ static inline bool should_hard_irq_enable(void)
 
 /*
  * Do the hard enabling, only call this if should_hard_irq_enable is true.
+ * This allows PMI interrupts to profile irq handlers.
  */
 static inline void do_hard_irq_enable(void)
 {
-	if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) {
-		WARN_ON(irq_soft_mask_return() == IRQS_ENABLED);
-		WARN_ON(get_paca()->irq_happened & PACA_IRQ_MUST_HARD_MASK);
-		WARN_ON(mfmsr() & MSR_EE);
-	}
 	/*
-	 * This allows PMI interrupts (and watchdog soft-NMIs) through.
-	 * There is no other reason to enable this way.
+	 * Asynch interrupts come in with IRQS_ALL_DISABLED,
+	 * PACA_IRQ_HARD_DIS, and MSR[EE]=0.
 	 */
+	if (IS_ENABLED(CONFIG_PPC_BOOK3S_64))
+		irq_soft_mask_andc_return(IRQS_PMI_DISABLED);
 	get_paca()->irq_happened &= ~PACA_IRQ_HARD_DIS;
 	__hard_irq_enable();
 }
@@ -452,7 +469,7 @@ static inline bool arch_irq_disabled_regs(struct pt_regs *regs)
 	return !(regs->msr & MSR_EE);
 }
 
-static __always_inline bool should_hard_irq_enable(void)
+static __always_inline bool should_hard_irq_enable(struct pt_regs *regs)
 {
 	return false;
 }
diff --git a/arch/powerpc/kernel/dbell.c b/arch/powerpc/kernel/dbell.c
index f55c6fb34a3a..5712dd846263 100644
--- a/arch/powerpc/kernel/dbell.c
+++ b/arch/powerpc/kernel/dbell.c
@@ -27,7 +27,7 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(doorbell_exception)
 
 	ppc_msgsync();
 
-	if (should_hard_irq_enable())
+	if (should_hard_irq_enable(regs))
 		do_hard_irq_enable();
 
 	kvmppc_clear_host_ipi(smp_processor_id());
diff --git a/arch/powerpc/kernel/head_85xx.S b/arch/powerpc/kernel/head_85xx.S
index d438ca74e96c..fdbee1093e2b 100644
--- a/arch/powerpc/kernel/head_85xx.S
+++ b/arch/powerpc/kernel/head_85xx.S
@@ -864,7 +864,7 @@ _GLOBAL(load_up_spe)
  * SPE unavailable trap from kernel - print a message, but let
  * the task use SPE in the kernel until it returns to user mode.
  */
-KernelSPE:
+SYM_FUNC_START_LOCAL(KernelSPE)
 	lwz	r3,_MSR(r1)
 	oris	r3,r3,MSR_SPE@h
 	stw	r3,_MSR(r1)	/* enable use of SPE after return */
@@ -881,6 +881,7 @@ KernelSPE:
 #endif
 	.align	4,0
 
+SYM_FUNC_END(KernelSPE)
 #endif /* CONFIG_SPE */
 
 /*
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index c5b9ce887483..c9535f2760b5 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -238,7 +238,7 @@ static void __do_irq(struct pt_regs *regs, unsigned long oldsp)
 	irq = static_call(ppc_get_irq)();
 
 	/* We can hard enable interrupts now to allow perf interrupts */
-	if (should_hard_irq_enable())
+	if (should_hard_irq_enable(regs))
 		do_hard_irq_enable();
 
 	/* And finally process it */
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index d68de3618741..e26eb6618ae5 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -515,7 +515,7 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(timer_interrupt)
 	}
 
 	/* Conditionally hard-enable interrupts. */
-	if (should_hard_irq_enable()) {
+	if (should_hard_irq_enable(regs)) {
 		/*
 		 * Ensure a positive value is written to the decrementer, or
 		 * else some CPUs will continue to take decrementer exceptions.
diff --git a/arch/powerpc/kexec/file_load_64.c b/arch/powerpc/kexec/file_load_64.c
index af8854f9eae3..52085751f5f4 100644
--- a/arch/powerpc/kexec/file_load_64.c
+++ b/arch/powerpc/kexec/file_load_64.c
@@ -989,10 +989,13 @@ unsigned int kexec_extra_fdt_size_ppc64(struct kimage *image)
 	 * linux,drconf-usable-memory properties. Get an approximate on the
 	 * number of usable memory entries and use for FDT size estimation.
 	 */
-	usm_entries = ((memblock_end_of_DRAM() / drmem_lmb_size()) +
-		       (2 * (resource_size(&crashk_res) / drmem_lmb_size())));
-
-	extra_size = (unsigned int)(usm_entries * sizeof(u64));
+	if (drmem_lmb_size()) {
+		usm_entries = ((memory_hotplug_max() / drmem_lmb_size()) +
+			       (2 * (resource_size(&crashk_res) / drmem_lmb_size())));
+		extra_size = (unsigned int)(usm_entries * sizeof(u64));
+	} else {
+		extra_size = 0;
+	}
 
 	/*
 	 * Get the number of CPU nodes in the current DT. This allows to
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 0dce93ccaadf..e89281d3ba28 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -912,16 +912,15 @@ static int kvmppc_handle_debug(struct kvm_vcpu *vcpu)
 
 static void kvmppc_fill_pt_regs(struct pt_regs *regs)
 {
-	ulong r1, ip, msr, lr;
+	ulong r1, msr, lr;
 
 	asm("mr %0, 1" : "=r"(r1));
 	asm("mflr %0" : "=r"(lr));
 	asm("mfmsr %0" : "=r"(msr));
-	asm("bl 1f; 1: mflr %0" : "=r"(ip));
 
 	memset(regs, 0, sizeof(*regs));
 	regs->gpr[1] = r1;
-	regs->nip = ip;
+	regs->nip = _THIS_IP_;
 	regs->msr = msr;
 	regs->link = lr;
 }
diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c
index cac727b01799..26245aaf12b8 100644
--- a/arch/powerpc/mm/book3s64/radix_pgtable.c
+++ b/arch/powerpc/mm/book3s64/radix_pgtable.c
@@ -234,6 +234,14 @@ void radix__mark_rodata_ro(void)
 	end = (unsigned long)__end_rodata;
 
 	radix__change_memory_range(start, end, _PAGE_WRITE);
+
+	for (start = PAGE_OFFSET; start < (unsigned long)_stext; start += PAGE_SIZE) {
+		end = start + PAGE_SIZE;
+		if (overlaps_interrupt_vector_text(start, end))
+			radix__change_memory_range(start, end, _PAGE_WRITE);
+		else
+			break;
+	}
 }
 
 void radix__mark_initmem_nx(void)
@@ -262,6 +270,22 @@ print_mapping(unsigned long start, unsigned long end, unsigned long size, bool e
 static unsigned long next_boundary(unsigned long addr, unsigned long end)
 {
 #ifdef CONFIG_STRICT_KERNEL_RWX
+	unsigned long stext_phys;
+
+	stext_phys = __pa_symbol(_stext);
+
+	// Relocatable kernel running at non-zero real address
+	if (stext_phys != 0) {
+		// The end of interrupts code at zero is a rodata boundary
+		unsigned long end_intr = __pa_symbol(__end_interrupts) - stext_phys;
+		if (addr < end_intr)
+			return end_intr;
+
+		// Start of relocated kernel text is a rodata boundary
+		if (addr < stext_phys)
+			return stext_phys;
+	}
+
 	if (addr < __pa_symbol(__srwx_boundary))
 		return __pa_symbol(__srwx_boundary);
 #endif
diff --git a/arch/powerpc/perf/imc-pmu.c b/arch/powerpc/perf/imc-pmu.c
index 100e97daf76b..9d229ef7f86e 100644
--- a/arch/powerpc/perf/imc-pmu.c
+++ b/arch/powerpc/perf/imc-pmu.c
@@ -22,7 +22,7 @@
  * Used to avoid races in counting the nest-pmu units during hotplug
  * register and unregister
  */
-static DEFINE_SPINLOCK(nest_init_lock);
+static DEFINE_MUTEX(nest_init_lock);
 static DEFINE_PER_CPU(struct imc_pmu_ref *, local_nest_imc_refc);
 static struct imc_pmu **per_nest_pmu_arr;
 static cpumask_t nest_imc_cpumask;
@@ -1629,7 +1629,7 @@ static void imc_common_mem_free(struct imc_pmu *pmu_ptr)
 static void imc_common_cpuhp_mem_free(struct imc_pmu *pmu_ptr)
 {
 	if (pmu_ptr->domain == IMC_DOMAIN_NEST) {
-		spin_lock(&nest_init_lock);
+		mutex_lock(&nest_init_lock);
 		if (nest_pmus == 1) {
 			cpuhp_remove_state(CPUHP_AP_PERF_POWERPC_NEST_IMC_ONLINE);
 			kfree(nest_imc_refc);
@@ -1639,7 +1639,7 @@ static void imc_common_cpuhp_mem_free(struct imc_pmu *pmu_ptr)
 
 		if (nest_pmus > 0)
 			nest_pmus--;
-		spin_unlock(&nest_init_lock);
+		mutex_unlock(&nest_init_lock);
 	}
 
 	/* Free core_imc memory */
@@ -1796,11 +1796,11 @@ int init_imc_pmu(struct device_node *parent, struct imc_pmu *pmu_ptr, int pmu_id
 		* rest. To handle the cpuhotplug callback unregister, we track
 		* the number of nest pmus in "nest_pmus".
 		*/
-		spin_lock(&nest_init_lock);
+		mutex_lock(&nest_init_lock);
 		if (nest_pmus == 0) {
 			ret = init_nest_pmu_ref();
 			if (ret) {
-				spin_unlock(&nest_init_lock);
+				mutex_unlock(&nest_init_lock);
 				kfree(per_nest_pmu_arr);
 				per_nest_pmu_arr = NULL;
 				goto err_free_mem;
@@ -1808,7 +1808,7 @@ int init_imc_pmu(struct device_node *parent, struct imc_pmu *pmu_ptr, int pmu_id
 			/* Register for cpu hotplug notification. */
 			ret = nest_pmu_cpumask_init();
 			if (ret) {
-				spin_unlock(&nest_init_lock);
+				mutex_unlock(&nest_init_lock);
 				kfree(nest_imc_refc);
 				kfree(per_nest_pmu_arr);
 				per_nest_pmu_arr = NULL;
@@ -1816,7 +1816,7 @@ int init_imc_pmu(struct device_node *parent, struct imc_pmu *pmu_ptr, int pmu_id
 			}
 		}
 		nest_pmus++;
-		spin_unlock(&nest_init_lock);
+		mutex_unlock(&nest_init_lock);
 		break;
 	case IMC_DOMAIN_CORE:
 		ret = core_imc_pmu_cpumask_init();
diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile
index faf2c2177094..82153960ac00 100644
--- a/arch/riscv/Makefile
+++ b/arch/riscv/Makefile
@@ -80,6 +80,9 @@ ifeq ($(CONFIG_PERF_EVENTS),y)
         KBUILD_CFLAGS += -fno-omit-frame-pointer
 endif
 
+# Avoid generating .eh_frame sections.
+KBUILD_CFLAGS += -fno-asynchronous-unwind-tables -fno-unwind-tables
+
 KBUILD_CFLAGS_MODULE += $(call cc-option,-mno-relax)
 KBUILD_AFLAGS_MODULE += $(call as-option,-Wa$(comma)-mno-relax)
 
diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h
index 86328e3acb02..64ad1937e714 100644
--- a/arch/riscv/include/asm/hwcap.h
+++ b/arch/riscv/include/asm/hwcap.h
@@ -70,7 +70,6 @@ static_assert(RISCV_ISA_EXT_ID_MAX <= RISCV_ISA_EXT_MAX);
  */
 enum riscv_isa_ext_key {
 	RISCV_ISA_EXT_KEY_FPU,		/* For 'F' and 'D' */
-	RISCV_ISA_EXT_KEY_ZIHINTPAUSE,
 	RISCV_ISA_EXT_KEY_SVINVAL,
 	RISCV_ISA_EXT_KEY_MAX,
 };
@@ -91,8 +90,6 @@ static __always_inline int riscv_isa_ext2key(int num)
 		return RISCV_ISA_EXT_KEY_FPU;
 	case RISCV_ISA_EXT_d:
 		return RISCV_ISA_EXT_KEY_FPU;
-	case RISCV_ISA_EXT_ZIHINTPAUSE:
-		return RISCV_ISA_EXT_KEY_ZIHINTPAUSE;
 	case RISCV_ISA_EXT_SVINVAL:
 		return RISCV_ISA_EXT_KEY_SVINVAL;
 	default:
diff --git a/arch/riscv/include/asm/vdso/processor.h b/arch/riscv/include/asm/vdso/processor.h
index fa70cfe507aa..14f5d27783b8 100644
--- a/arch/riscv/include/asm/vdso/processor.h
+++ b/arch/riscv/include/asm/vdso/processor.h
@@ -4,30 +4,26 @@
 
 #ifndef __ASSEMBLY__
 
-#include <linux/jump_label.h>
 #include <asm/barrier.h>
-#include <asm/hwcap.h>
 
 static inline void cpu_relax(void)
 {
-	if (!static_branch_likely(&riscv_isa_ext_keys[RISCV_ISA_EXT_KEY_ZIHINTPAUSE])) {
 #ifdef __riscv_muldiv
-		int dummy;
-		/* In lieu of a halt instruction, induce a long-latency stall. */
-		__asm__ __volatile__ ("div %0, %0, zero" : "=r" (dummy));
+	int dummy;
+	/* In lieu of a halt instruction, induce a long-latency stall. */
+	__asm__ __volatile__ ("div %0, %0, zero" : "=r" (dummy));
 #endif
-	} else {
-		/*
-		 * Reduce instruction retirement.
-		 * This assumes the PC changes.
-		 */
-#ifdef CONFIG_TOOLCHAIN_HAS_ZIHINTPAUSE
-		__asm__ __volatile__ ("pause");
+
+#ifdef __riscv_zihintpause
+	/*
+	 * Reduce instruction retirement.
+	 * This assumes the PC changes.
+	 */
+	__asm__ __volatile__ ("pause");
 #else
-		/* Encoding of the pause instruction */
-		__asm__ __volatile__ (".4byte 0x100000F");
+	/* Encoding of the pause instruction */
+	__asm__ __volatile__ (".4byte 0x100000F");
 #endif
-	}
 	barrier();
 }
 
diff --git a/arch/riscv/kernel/probes/kprobes.c b/arch/riscv/kernel/probes/kprobes.c
index f21592d20306..41c7481afde3 100644
--- a/arch/riscv/kernel/probes/kprobes.c
+++ b/arch/riscv/kernel/probes/kprobes.c
@@ -48,6 +48,21 @@ static void __kprobes arch_simulate_insn(struct kprobe *p, struct pt_regs *regs)
 	post_kprobe_handler(p, kcb, regs);
 }
 
+static bool __kprobes arch_check_kprobe(struct kprobe *p)
+{
+	unsigned long tmp  = (unsigned long)p->addr - p->offset;
+	unsigned long addr = (unsigned long)p->addr;
+
+	while (tmp <= addr) {
+		if (tmp == addr)
+			return true;
+
+		tmp += GET_INSN_LENGTH(*(u16 *)tmp);
+	}
+
+	return false;
+}
+
 int __kprobes arch_prepare_kprobe(struct kprobe *p)
 {
 	unsigned long probe_addr = (unsigned long)p->addr;
@@ -55,6 +70,9 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p)
 	if (probe_addr & 0x1)
 		return -EILSEQ;
 
+	if (!arch_check_kprobe(p))
+		return -EILSEQ;
+
 	/* copy instruction */
 	p->opcode = *p->addr;
 
diff --git a/arch/sh/kernel/vmlinux.lds.S b/arch/sh/kernel/vmlinux.lds.S
index 3161b9ccd2a5..b6276a3521d7 100644
--- a/arch/sh/kernel/vmlinux.lds.S
+++ b/arch/sh/kernel/vmlinux.lds.S
@@ -4,6 +4,7 @@
  * Written by Niibe Yutaka and Paul Mundt
  */
 OUTPUT_ARCH(sh)
+#define RUNTIME_DISCARD_EXIT
 #include <asm/thread_info.h>
 #include <asm/cache.h>
 #include <asm/vmlinux.lds.h>
diff --git a/arch/x86/include/asm/debugreg.h b/arch/x86/include/asm/debugreg.h
index b049d950612f..ca97442e8d49 100644
--- a/arch/x86/include/asm/debugreg.h
+++ b/arch/x86/include/asm/debugreg.h
@@ -39,7 +39,20 @@ static __always_inline unsigned long native_get_debugreg(int regno)
 		asm("mov %%db6, %0" :"=r" (val));
 		break;
 	case 7:
-		asm("mov %%db7, %0" :"=r" (val));
+		/*
+		 * Apply __FORCE_ORDER to DR7 reads to forbid re-ordering them
+		 * with other code.
+		 *
+		 * This is needed because a DR7 access can cause a #VC exception
+		 * when running under SEV-ES. Taking a #VC exception is not a
+		 * safe thing to do just anywhere in the entry code and
+		 * re-ordering might place the access into an unsafe location.
+		 *
+		 * This happened in the NMI handler, where the DR7 read was
+		 * re-ordered to happen before the call to sev_es_ist_enter(),
+		 * causing stack recursion.
+		 */
+		asm volatile("mov %%db7, %0" : "=r" (val) : __FORCE_ORDER);
 		break;
 	default:
 		BUG();
@@ -66,7 +79,16 @@ static __always_inline void native_set_debugreg(int regno, unsigned long value)
 		asm("mov %0, %%db6"	::"r" (value));
 		break;
 	case 7:
-		asm("mov %0, %%db7"	::"r" (value));
+		/*
+		 * Apply __FORCE_ORDER to DR7 writes to forbid re-ordering them
+		 * with other code.
+		 *
+		 * While is didn't happen with a DR7 write (see the DR7 read
+		 * comment above which explains where it happened), add the
+		 * __FORCE_ORDER here too to avoid similar problems in the
+		 * future.
+		 */
+		asm volatile("mov %0, %%db7"	::"r" (value), __FORCE_ORDER);
 		break;
 	default:
 		BUG();