Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf before 7.0-rc2

Cross-merge BPF and other fixes after downstream PR.

No conflicts.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>

25 files changed, 179 insertions, 133 deletions

diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h
index 83e03abbb2ca..8cbd1e96fd50 100644
--- a/arch/arm64/include/asm/io.h
+++ b/arch/arm64/include/asm/io.h
@@ -264,19 +264,33 @@ __iowrite64_copy(void __iomem *to, const void *from, size_t count)
 typedef int (*ioremap_prot_hook_t)(phys_addr_t phys_addr, size_t size,
 				   pgprot_t *prot);
 int arm64_ioremap_prot_hook_register(const ioremap_prot_hook_t hook);
+void __iomem *__ioremap_prot(phys_addr_t phys, size_t size, pgprot_t prot);
 
-#define ioremap_prot ioremap_prot
+static inline void __iomem *ioremap_prot(phys_addr_t phys, size_t size,
+					 pgprot_t user_prot)
+{
+	pgprot_t prot;
+	ptdesc_t user_prot_val = pgprot_val(user_prot);
+
+	if (WARN_ON_ONCE(!(user_prot_val & PTE_USER)))
+		return NULL;
 
-#define _PAGE_IOREMAP PROT_DEVICE_nGnRE
+	prot = __pgprot_modify(PAGE_KERNEL, PTE_ATTRINDX_MASK,
+			       user_prot_val & PTE_ATTRINDX_MASK);
+	return __ioremap_prot(phys, size, prot);
+}
+#define ioremap_prot ioremap_prot
 
+#define ioremap(addr, size)	\
+	__ioremap_prot((addr), (size), __pgprot(PROT_DEVICE_nGnRE))
 #define ioremap_wc(addr, size)	\
-	ioremap_prot((addr), (size), __pgprot(PROT_NORMAL_NC))
+	__ioremap_prot((addr), (size), __pgprot(PROT_NORMAL_NC))
 #define ioremap_np(addr, size)	\
-	ioremap_prot((addr), (size), __pgprot(PROT_DEVICE_nGnRnE))
+	__ioremap_prot((addr), (size), __pgprot(PROT_DEVICE_nGnRnE))
 
 
 #define ioremap_encrypted(addr, size)	\
-	ioremap_prot((addr), (size), PAGE_KERNEL)
+	__ioremap_prot((addr), (size), PAGE_KERNEL)
 
 /*
  * io{read,write}{16,32,64}be() macros
@@ -297,7 +311,7 @@ static inline void __iomem *ioremap_cache(phys_addr_t addr, size_t size)
 	if (pfn_is_map_memory(__phys_to_pfn(addr)))
 		return (void __iomem *)__phys_to_virt(addr);
 
-	return ioremap_prot(addr, size, __pgprot(PROT_NORMAL));
+	return __ioremap_prot(addr, size, __pgprot(PROT_NORMAL));
 }
 
 /*
diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h
index d27e8872fe3c..2b32639160de 100644
--- a/arch/arm64/include/asm/pgtable-prot.h
+++ b/arch/arm64/include/asm/pgtable-prot.h
@@ -164,9 +164,6 @@ static inline bool __pure lpa2_is_enabled(void)
 #define _PAGE_GCS	(_PAGE_DEFAULT | PTE_NG | PTE_UXN | PTE_WRITE | PTE_USER)
 #define _PAGE_GCS_RO	(_PAGE_DEFAULT | PTE_NG | PTE_UXN | PTE_USER)
 
-#define PAGE_GCS	__pgprot(_PAGE_GCS)
-#define PAGE_GCS_RO	__pgprot(_PAGE_GCS_RO)
-
 #define PIE_E0	( \
 	PIRx_ELx_PERM_PREP(pte_pi_index(_PAGE_GCS),           PIE_GCS)  | \
 	PIRx_ELx_PERM_PREP(pte_pi_index(_PAGE_GCS_RO),        PIE_R)   | \
diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h
index a2d65d7d6aae..1416e652612b 100644
--- a/arch/arm64/include/asm/tlbflush.h
+++ b/arch/arm64/include/asm/tlbflush.h
@@ -31,19 +31,11 @@
  */
 #define __TLBI_0(op, arg) asm (ARM64_ASM_PREAMBLE			       \
 			       "tlbi " #op "\n"				       \
-		   ALTERNATIVE("nop\n			nop",		       \
-			       "dsb ish\n		tlbi " #op,	       \
-			       ARM64_WORKAROUND_REPEAT_TLBI,		       \
-			       CONFIG_ARM64_WORKAROUND_REPEAT_TLBI)	       \
 			    : : )
 
 #define __TLBI_1(op, arg) asm (ARM64_ASM_PREAMBLE			       \
-			       "tlbi " #op ", %0\n"			       \
-		   ALTERNATIVE("nop\n			nop",		       \
-			       "dsb ish\n		tlbi " #op ", %0",     \
-			       ARM64_WORKAROUND_REPEAT_TLBI,		       \
-			       CONFIG_ARM64_WORKAROUND_REPEAT_TLBI)	       \
-			    : : "r" (arg))
+			       "tlbi " #op ", %x0\n"			       \
+			    : : "rZ" (arg))
 
 #define __TLBI_N(op, arg, n, ...) __TLBI_##n(op, arg)
 
@@ -181,6 +173,34 @@ static inline unsigned long get_trans_granule(void)
 		(__pages >> (5 * (scale) + 1)) - 1;			\
 	})
 
+#define __repeat_tlbi_sync(op, arg...)						\
+do {										\
+	if (!alternative_has_cap_unlikely(ARM64_WORKAROUND_REPEAT_TLBI))	\
+		break;								\
+	__tlbi(op, ##arg);							\
+	dsb(ish);								\
+} while (0)
+
+/*
+ * Complete broadcast TLB maintenance issued by the host which invalidates
+ * stage 1 information in the host's own translation regime.
+ */
+static inline void __tlbi_sync_s1ish(void)
+{
+	dsb(ish);
+	__repeat_tlbi_sync(vale1is, 0);
+}
+
+/*
+ * Complete broadcast TLB maintenance issued by hyp code which invalidates
+ * stage 1 translation information in any translation regime.
+ */
+static inline void __tlbi_sync_s1ish_hyp(void)
+{
+	dsb(ish);
+	__repeat_tlbi_sync(vale2is, 0);
+}
+
 /*
  *	TLB Invalidation
  *	================
@@ -279,7 +299,7 @@ static inline void flush_tlb_all(void)
 {
 	dsb(ishst);
 	__tlbi(vmalle1is);
-	dsb(ish);
+	__tlbi_sync_s1ish();
 	isb();
 }
 
@@ -291,7 +311,7 @@ static inline void flush_tlb_mm(struct mm_struct *mm)
 	asid = __TLBI_VADDR(0, ASID(mm));
 	__tlbi(aside1is, asid);
 	__tlbi_user(aside1is, asid);
-	dsb(ish);
+	__tlbi_sync_s1ish();
 	mmu_notifier_arch_invalidate_secondary_tlbs(mm, 0, -1UL);
 }
 
@@ -345,20 +365,11 @@ static inline void flush_tlb_page(struct vm_area_struct *vma,
 				  unsigned long uaddr)
 {
 	flush_tlb_page_nosync(vma, uaddr);
-	dsb(ish);
+	__tlbi_sync_s1ish();
 }
 
 static inline bool arch_tlbbatch_should_defer(struct mm_struct *mm)
 {
-	/*
-	 * TLB flush deferral is not required on systems which are affected by
-	 * ARM64_WORKAROUND_REPEAT_TLBI, as __tlbi()/__tlbi_user() implementation
-	 * will have two consecutive TLBI instructions with a dsb(ish) in between
-	 * defeating the purpose (i.e save overall 'dsb ish' cost).
-	 */
-	if (alternative_has_cap_unlikely(ARM64_WORKAROUND_REPEAT_TLBI))
-		return false;
-
 	return true;
 }
 
@@ -374,7 +385,7 @@ static inline bool arch_tlbbatch_should_defer(struct mm_struct *mm)
  */
 static inline void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch)
 {
-	dsb(ish);
+	__tlbi_sync_s1ish();
 }
 
 /*
@@ -509,7 +520,7 @@ static inline void __flush_tlb_range(struct vm_area_struct *vma,
 {
 	__flush_tlb_range_nosync(vma->vm_mm, start, end, stride,
 				 last_level, tlb_level);
-	dsb(ish);
+	__tlbi_sync_s1ish();
 }
 
 static inline void local_flush_tlb_contpte(struct vm_area_struct *vma,
@@ -557,7 +568,7 @@ static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end
 	dsb(ishst);
 	__flush_tlb_range_op(vaale1is, start, pages, stride, 0,
 			     TLBI_TTL_UNKNOWN, false, lpa2_is_enabled());
-	dsb(ish);
+	__tlbi_sync_s1ish();
 	isb();
 }
 
@@ -571,7 +582,7 @@ static inline void __flush_tlb_kernel_pgtable(unsigned long kaddr)
 
 	dsb(ishst);
 	__tlbi(vaae1is, addr);
-	dsb(ish);
+	__tlbi_sync_s1ish();
 	isb();
 }
 
diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c
index af90128cfed5..a9d884fd1d00 100644
--- a/arch/arm64/kernel/acpi.c
+++ b/arch/arm64/kernel/acpi.c
@@ -377,7 +377,7 @@ void __iomem *acpi_os_ioremap(acpi_physical_address phys, acpi_size size)
 				prot = __acpi_get_writethrough_mem_attribute();
 		}
 	}
-	return ioremap_prot(phys, size, prot);
+	return __ioremap_prot(phys, size, prot);
 }
 
 /*
diff --git a/arch/arm64/kernel/sys_compat.c b/arch/arm64/kernel/sys_compat.c
index 4a609e9b65de..b9d4998c97ef 100644
--- a/arch/arm64/kernel/sys_compat.c
+++ b/arch/arm64/kernel/sys_compat.c
@@ -37,7 +37,7 @@ __do_compat_cache_op(unsigned long start, unsigned long end)
 			 * We pick the reserved-ASID to minimise the impact.
 			 */
 			__tlbi(aside1is, __TLBI_VADDR(0, 0));
-			dsb(ish);
+			__tlbi_sync_s1ish();
 		}
 
 		ret = caches_clean_inval_user_pou(start, start + chunk);
diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
index 3fe1faab0362..b32f13358fbb 100644
--- a/arch/arm64/kernel/topology.c
+++ b/arch/arm64/kernel/topology.c
@@ -400,16 +400,25 @@ static inline
 int counters_read_on_cpu(int cpu, smp_call_func_t func, u64 *val)
 {
 	/*
-	 * Abort call on counterless CPU or when interrupts are
-	 * disabled - can lead to deadlock in smp sync call.
+	 * Abort call on counterless CPU.
 	 */
 	if (!cpu_has_amu_feat(cpu))
 		return -EOPNOTSUPP;
 
-	if (WARN_ON_ONCE(irqs_disabled()))
-		return -EPERM;
-
-	smp_call_function_single(cpu, func, val, 1);
+	if (irqs_disabled()) {
+		/*
+		 * When IRQs are disabled (tick path: sched_tick ->
+		 * topology_scale_freq_tick or cppc_scale_freq_tick), only local
+		 * CPU counter reads are allowed. Remote CPU counter read would
+		 * require smp_call_function_single() which is unsafe with IRQs
+		 * disabled.
+		 */
+		if (WARN_ON_ONCE(cpu != smp_processor_id()))
+			return -EPERM;
+		func(val);
+	} else {
+		smp_call_function_single(cpu, func, val, 1);
+	}
 
 	return 0;
 }
diff --git a/arch/arm64/kvm/hyp/nvhe/mm.c b/arch/arm64/kvm/hyp/nvhe/mm.c
index ae8391baebc3..218976287d3f 100644
--- a/arch/arm64/kvm/hyp/nvhe/mm.c
+++ b/arch/arm64/kvm/hyp/nvhe/mm.c
@@ -271,7 +271,7 @@ static void fixmap_clear_slot(struct hyp_fixmap_slot *slot)
 	 */
 	dsb(ishst);
 	__tlbi_level(vale2is, __TLBI_VADDR(addr, 0), level);
-	dsb(ish);
+	__tlbi_sync_s1ish_hyp();
 	isb();
 }
 
diff --git a/arch/arm64/kvm/hyp/nvhe/tlb.c b/arch/arm64/kvm/hyp/nvhe/tlb.c
index 48da9ca9763f..3dc1ce0d27fe 100644
--- a/arch/arm64/kvm/hyp/nvhe/tlb.c
+++ b/arch/arm64/kvm/hyp/nvhe/tlb.c
@@ -169,7 +169,7 @@ void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu,
 	 */
 	dsb(ish);
 	__tlbi(vmalle1is);
-	dsb(ish);
+	__tlbi_sync_s1ish_hyp();
 	isb();
 
 	exit_vmid_context(&cxt);
@@ -226,7 +226,7 @@ void __kvm_tlb_flush_vmid_range(struct kvm_s2_mmu *mmu,
 
 	dsb(ish);
 	__tlbi(vmalle1is);
-	dsb(ish);
+	__tlbi_sync_s1ish_hyp();
 	isb();
 
 	exit_vmid_context(&cxt);
@@ -240,7 +240,7 @@ void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu)
 	enter_vmid_context(mmu, &cxt, false);
 
 	__tlbi(vmalls12e1is);
-	dsb(ish);
+	__tlbi_sync_s1ish_hyp();
 	isb();
 
 	exit_vmid_context(&cxt);
@@ -266,5 +266,5 @@ void __kvm_flush_vm_context(void)
 	/* Same remark as in enter_vmid_context() */
 	dsb(ish);
 	__tlbi(alle1is);
-	dsb(ish);
+	__tlbi_sync_s1ish_hyp();
 }
diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
index 0e4ddd28ef5d..9b480f947da2 100644
--- a/arch/arm64/kvm/hyp/pgtable.c
+++ b/arch/arm64/kvm/hyp/pgtable.c
@@ -501,7 +501,7 @@ static int hyp_unmap_walker(const struct kvm_pgtable_visit_ctx *ctx,
 		*unmapped += granule;
 	}
 
-	dsb(ish);
+	__tlbi_sync_s1ish_hyp();
 	isb();
 	mm_ops->put_page(ctx->ptep);
 
diff --git a/arch/arm64/kvm/hyp/vhe/tlb.c b/arch/arm64/kvm/hyp/vhe/tlb.c
index ec2569818629..35855dadfb1b 100644
--- a/arch/arm64/kvm/hyp/vhe/tlb.c
+++ b/arch/arm64/kvm/hyp/vhe/tlb.c
@@ -115,7 +115,7 @@ void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu,
 	 */
 	dsb(ish);
 	__tlbi(vmalle1is);
-	dsb(ish);
+	__tlbi_sync_s1ish_hyp();
 	isb();
 
 	exit_vmid_context(&cxt);
@@ -176,7 +176,7 @@ void __kvm_tlb_flush_vmid_range(struct kvm_s2_mmu *mmu,
 
 	dsb(ish);
 	__tlbi(vmalle1is);
-	dsb(ish);
+	__tlbi_sync_s1ish_hyp();
 	isb();
 
 	exit_vmid_context(&cxt);
@@ -192,7 +192,7 @@ void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu)
 	enter_vmid_context(mmu, &cxt);
 
 	__tlbi(vmalls12e1is);
-	dsb(ish);
+	__tlbi_sync_s1ish_hyp();
 	isb();
 
 	exit_vmid_context(&cxt);
@@ -217,7 +217,7 @@ void __kvm_flush_vm_context(void)
 {
 	dsb(ishst);
 	__tlbi(alle1is);
-	dsb(ish);
+	__tlbi_sync_s1ish_hyp();
 }
 
 /*
@@ -358,7 +358,7 @@ int __kvm_tlbi_s1e2(struct kvm_s2_mmu *mmu, u64 va, u64 sys_encoding)
 	default:
 		ret = -EINVAL;
 	}
-	dsb(ish);
+	__tlbi_sync_s1ish_hyp();
 	isb();
 
 	if (mmu)
diff --git a/arch/arm64/lib/delay.c b/arch/arm64/lib/delay.c
index d02341303899..e278e060e78a 100644
--- a/arch/arm64/lib/delay.c
+++ b/arch/arm64/lib/delay.c
@@ -32,7 +32,11 @@ static inline unsigned long xloops_to_cycles(unsigned long xloops)
  * Note that userspace cannot change the offset behind our back either,
  * as the vcpu mutex is held as long as KVM_RUN is in progress.
  */
-#define __delay_cycles()	__arch_counter_get_cntvct_stable()
+static cycles_t notrace __delay_cycles(void)
+{
+	guard(preempt_notrace)();
+	return __arch_counter_get_cntvct_stable();
+}
 
 void __delay(unsigned long cycles)
 {
diff --git a/arch/arm64/mm/ioremap.c b/arch/arm64/mm/ioremap.c
index b12cbed9b5ad..6eef48ef6278 100644
--- a/arch/arm64/mm/ioremap.c
+++ b/arch/arm64/mm/ioremap.c
@@ -14,8 +14,8 @@ int arm64_ioremap_prot_hook_register(ioremap_prot_hook_t hook)
 	return 0;
 }
 
-void __iomem *ioremap_prot(phys_addr_t phys_addr, size_t size,
-			   pgprot_t pgprot)
+void __iomem *__ioremap_prot(phys_addr_t phys_addr, size_t size,
+			     pgprot_t pgprot)
 {
 	unsigned long last_addr = phys_addr + size - 1;
 
@@ -39,7 +39,7 @@ void __iomem *ioremap_prot(phys_addr_t phys_addr, size_t size,
 
 	return generic_ioremap_prot(phys_addr, size, pgprot);
 }
-EXPORT_SYMBOL(ioremap_prot);
+EXPORT_SYMBOL(__ioremap_prot);
 
 /*
  * Must be called after early_fixmap_init
diff --git a/arch/arm64/mm/mmap.c b/arch/arm64/mm/mmap.c
index 08ee177432c2..92b2f5097a96 100644
--- a/arch/arm64/mm/mmap.c
+++ b/arch/arm64/mm/mmap.c
@@ -34,6 +34,8 @@ static pgprot_t protection_map[16] __ro_after_init = {
 	[VM_SHARED | VM_EXEC | VM_WRITE | VM_READ]	= PAGE_SHARED_EXEC
 };
 
+static ptdesc_t gcs_page_prot __ro_after_init = _PAGE_GCS_RO;
+
 /*
  * You really shouldn't be using read() or write() on /dev/mem.  This might go
  * away in the future.
@@ -73,9 +75,11 @@ static int __init adjust_protection_map(void)
 		protection_map[VM_EXEC | VM_SHARED] = PAGE_EXECONLY;
 	}
 
-	if (lpa2_is_enabled())
+	if (lpa2_is_enabled()) {
 		for (int i = 0; i < ARRAY_SIZE(protection_map); i++)
 			pgprot_val(protection_map[i]) &= ~PTE_SHARED;
+		gcs_page_prot &= ~PTE_SHARED;
+	}
 
 	return 0;
 }
@@ -87,7 +91,11 @@ pgprot_t vm_get_page_prot(vm_flags_t vm_flags)
 
 	/* Short circuit GCS to avoid bloating the table. */
 	if (system_supports_gcs() && (vm_flags & VM_SHADOW_STACK)) {
-		prot = _PAGE_GCS_RO;
+		/* Honour mprotect(PROT_NONE) on shadow stack mappings */
+		if (vm_flags & VM_ACCESS_FLAGS)
+			prot = gcs_page_prot;
+		else
+			prot = pgprot_val(protection_map[VM_NONE]);
 	} else {
 		prot = pgprot_val(protection_map[vm_flags &
 				   (VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)]);
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index 356d33c7a4ae..adf84962d579 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -2119,7 +2119,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	extable_offset = round_up(prog_size + PLT_TARGET_SIZE, extable_align);
 	image_size = extable_offset + extable_size;
 	ro_header = bpf_jit_binary_pack_alloc(image_size, &ro_image_ptr,
-					      sizeof(u32), &header, &image_ptr,
+					      sizeof(u64), &header, &image_ptr,
 					      jit_fill_hole);
 	if (!ro_header) {
 		prog = orig_prog;
diff --git a/arch/s390/include/asm/idle.h b/arch/s390/include/asm/idle.h
index 09f763b9eb40..32536ee34aa0 100644
--- a/arch/s390/include/asm/idle.h
+++ b/arch/s390/include/asm/idle.h
@@ -19,9 +19,9 @@ struct s390_idle_data {
 	unsigned long mt_cycles_enter[8];
 };
 
+DECLARE_PER_CPU(struct s390_idle_data, s390_idle);
+
 extern struct device_attribute dev_attr_idle_count;
 extern struct device_attribute dev_attr_idle_time_us;
 
-void psw_idle(struct s390_idle_data *data, unsigned long psw_mask);
-
 #endif /* _S390_IDLE_H */
diff --git a/arch/s390/include/asm/vtime.h b/arch/s390/include/asm/vtime.h
index 9d25fb35a042..b1db75d14e9d 100644
--- a/arch/s390/include/asm/vtime.h
+++ b/arch/s390/include/asm/vtime.h
@@ -2,6 +2,12 @@
 #ifndef _S390_VTIME_H
 #define _S390_VTIME_H
 
+#include <asm/lowcore.h>
+#include <asm/cpu_mf.h>
+#include <asm/idle.h>
+
+DECLARE_PER_CPU(u64, mt_cycles[8]);
+
 static inline void update_timer_sys(void)
 {
 	struct lowcore *lc = get_lowcore();
@@ -20,4 +26,32 @@ static inline void update_timer_mcck(void)
 	lc->last_update_timer = lc->mcck_enter_timer;
 }
 
+static inline void update_timer_idle(void)
+{
+	struct s390_idle_data *idle = this_cpu_ptr(&s390_idle);
+	struct lowcore *lc = get_lowcore();
+	u64 cycles_new[8];
+	int i, mtid;
+
+	mtid = smp_cpu_mtid;
+	if (mtid) {
+		stcctm(MT_DIAG, mtid, cycles_new);
+		for (i = 0; i < mtid; i++)
+			__this_cpu_add(mt_cycles[i], cycles_new[i] - idle->mt_cycles_enter[i]);
+	}
+	/*
+	 * This is a bit subtle: Forward last_update_clock so it excludes idle
+	 * time. For correct steal time calculation in do_account_vtime() add
+	 * passed wall time before idle_enter to steal_timer:
+	 * During the passed wall time before idle_enter CPU time may have
+	 * been accounted to system, hardirq, softirq, etc. lowcore fields.
+	 * The accounted CPU times will be subtracted again from steal_timer
+	 * when accumulated steal time is calculated in do_account_vtime().
+	 */
+	lc->steal_timer += idle->clock_idle_enter - lc->last_update_clock;
+	lc->last_update_clock = lc->int_clock;
+	lc->system_timer += lc->last_update_timer - idle->timer_idle_enter;
+	lc->last_update_timer = lc->sys_enter_timer;
+}
+
 #endif /* _S390_VTIME_H */
diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h
index dd55cc6bbc28..fb67b4abe68c 100644
--- a/arch/s390/kernel/entry.h
+++ b/arch/s390/kernel/entry.h
@@ -56,8 +56,6 @@ long sys_s390_pci_mmio_write(unsigned long, const void __user *, size_t);
 long sys_s390_pci_mmio_read(unsigned long, void __user *, size_t);
 long sys_s390_sthyi(unsigned long function_code, void __user *buffer, u64 __user *return_code, unsigned long flags);
 
-DECLARE_PER_CPU(u64, mt_cycles[8]);
-
 unsigned long stack_alloc(void);
 void stack_free(unsigned long stack);
 
diff --git a/arch/s390/kernel/idle.c b/arch/s390/kernel/idle.c
index 39cb8d0ae348..1f1b06b6b4ef 100644
--- a/arch/s390/kernel/idle.c
+++ b/arch/s390/kernel/idle.c
@@ -15,37 +15,22 @@
 #include <trace/events/power.h>
 #include <asm/cpu_mf.h>
 #include <asm/cputime.h>
+#include <asm/idle.h>
 #include <asm/nmi.h>
 #include <asm/smp.h>
-#include "entry.h"
 
-static DEFINE_PER_CPU(struct s390_idle_data, s390_idle);
+DEFINE_PER_CPU(struct s390_idle_data, s390_idle);
 
 void account_idle_time_irq(void)
 {
 	struct s390_idle_data *idle = this_cpu_ptr(&s390_idle);
-	struct lowcore *lc = get_lowcore();
 	unsigned long idle_time;
-	u64 cycles_new[8];
-	int i;
 
-	if (smp_cpu_mtid) {
-		stcctm(MT_DIAG, smp_cpu_mtid, cycles_new);
-		for (i = 0; i < smp_cpu_mtid; i++)
-			this_cpu_add(mt_cycles[i], cycles_new[i] - idle->mt_cycles_enter[i]);
-	}
-
-	idle_time = lc->int_clock - idle->clock_idle_enter;
-
-	lc->steal_timer += idle->clock_idle_enter - lc->last_update_clock;
-	lc->last_update_clock = lc->int_clock;
-
-	lc->system_timer += lc->last_update_timer - idle->timer_idle_enter;
-	lc->last_update_timer = lc->sys_enter_timer;
+	idle_time = get_lowcore()->int_clock - idle->clock_idle_enter;
 
 	/* Account time spent with enabled wait psw loaded as idle time. */
-	WRITE_ONCE(idle->idle_time, READ_ONCE(idle->idle_time) + idle_time);
-	WRITE_ONCE(idle->idle_count, READ_ONCE(idle->idle_count) + 1);
+	__atomic64_add(idle_time, &idle->idle_time);
+	__atomic64_add_const(1, &idle->idle_count);
 	account_idle_time(cputime_to_nsecs(idle_time));
 }
 
diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c
index dcdc7e274848..049c557c452f 100644
--- a/arch/s390/kernel/ipl.c
+++ b/arch/s390/kernel/ipl.c
@@ -2377,7 +2377,7 @@ void __init setup_ipl(void)
 	atomic_notifier_chain_register(&panic_notifier_list, &on_panic_nb);
 }
 
-void s390_reset_system(void)
+void __no_stack_protector s390_reset_system(void)
 {
 	/* Disable prefixing */
 	set_prefix(0);
diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c
index f81723bc8856..7fdf960191d3 100644
--- a/arch/s390/kernel/irq.c
+++ b/arch/s390/kernel/irq.c
@@ -146,6 +146,12 @@ void noinstr do_io_irq(struct pt_regs *regs)
 	struct pt_regs *old_regs = set_irq_regs(regs);
 	bool from_idle;
 
+	from_idle = test_and_clear_cpu_flag(CIF_ENABLED_WAIT);
+	if (from_idle) {
+		update_timer_idle();
+		regs->psw.mask &= ~(PSW_MASK_EXT | PSW_MASK_IO | PSW_MASK_WAIT);
+	}
+
 	irq_enter_rcu();
 
 	if (user_mode(regs)) {
@@ -154,7 +160,6 @@ void noinstr do_io_irq(struct pt_regs *regs)
 			current->thread.last_break = regs->last_break;
 	}
 
-	from_idle = test_and_clear_cpu_flag(CIF_ENABLED_WAIT);
 	if (from_idle)
 		account_idle_time_irq();
 
@@ -171,9 +176,6 @@ void noinstr do_io_irq(struct pt_regs *regs)
 
 	set_irq_regs(old_regs);
 	irqentry_exit(regs, state);
-
-	if (from_idle)
-		regs->psw.mask &= ~(PSW_MASK_EXT | PSW_MASK_IO | PSW_MASK_WAIT);
 }
 
 void noinstr do_ext_irq(struct pt_regs *regs)
@@ -182,6 +184,12 @@ void noinstr do_ext_irq(struct pt_regs *regs)
 	struct pt_regs *old_regs = set_irq_regs(regs);
 	bool from_idle;
 
+	from_idle = test_and_clear_cpu_flag(CIF_ENABLED_WAIT);
+	if (from_idle) {
+		update_timer_idle();
+		regs->psw.mask &= ~(PSW_MASK_EXT | PSW_MASK_IO | PSW_MASK_WAIT);
+	}
+
 	irq_enter_rcu();
 
 	if (user_mode(regs)) {
@@ -194,7 +202,6 @@ void noinstr do_ext_irq(struct pt_regs *regs)
 	regs->int_parm = get_lowcore()->ext_params;
 	regs->int_parm_long = get_lowcore()->ext_params2;
 
-	from_idle = test_and_clear_cpu_flag(CIF_ENABLED_WAIT);
 	if (from_idle)
 		account_idle_time_irq();
 
@@ -203,9 +210,6 @@ void noinstr do_ext_irq(struct pt_regs *regs)
 	irq_exit_rcu();
 	set_irq_regs(old_regs);
 	irqentry_exit(regs, state);
-
-	if (from_idle)
-		regs->psw.mask &= ~(PSW_MASK_EXT | PSW_MASK_IO | PSW_MASK_WAIT);
 }
 
 static void show_msi_interrupt(struct seq_file *p, int irq)
diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c
index 234a0ba30510..bf48744d0912 100644
--- a/arch/s390/kernel/vtime.c
+++ b/arch/s390/kernel/vtime.c
@@ -48,8 +48,7 @@ static inline void set_vtimer(u64 expires)
 
 static inline int virt_timer_forward(u64 elapsed)
 {
-	BUG_ON(!irqs_disabled());
-
+	lockdep_assert_irqs_disabled();
 	if (list_empty(&virt_timer_list))
 		return 0;
 	elapsed = atomic64_add_return(elapsed, &virt_timer_elapsed);
@@ -137,23 +136,16 @@ static int do_account_vtime(struct task_struct *tsk)
 		lc->system_timer += timer;
 
 	/* Update MT utilization calculation */
-	if (smp_cpu_mtid &&
-	    time_after64(jiffies_64, this_cpu_read(mt_scaling_jiffies)))
+	if (smp_cpu_mtid && time_after64(jiffies_64, __this_cpu_read(mt_scaling_jiffies)))
 		update_mt_scaling();
 
 	/* Calculate cputime delta */
-	user = update_tsk_timer(&tsk->thread.user_timer,
-				READ_ONCE(lc->user_timer));
-	guest = update_tsk_timer(&tsk->thread.guest_timer,
-				 READ_ONCE(lc->guest_timer));
-	system = update_tsk_timer(&tsk->thread.system_timer,
-				  READ_ONCE(lc->system_timer));
-	hardirq = update_tsk_timer(&tsk->thread.hardirq_timer,
-				   READ_ONCE(lc->hardirq_timer));
-	softirq = update_tsk_timer(&tsk->thread.softirq_timer,
-				   READ_ONCE(lc->softirq_timer));
-	lc->steal_timer +=
-		clock - user - guest - system - hardirq - softirq;
+	user = update_tsk_timer(&tsk->thread.user_timer, lc->user_timer);
+	guest = update_tsk_timer(&tsk->thread.guest_timer, lc->guest_timer);
+	system = update_tsk_timer(&tsk->thread.system_timer, lc->system_timer);
+	hardirq = update_tsk_timer(&tsk->thread.hardirq_timer, lc->hardirq_timer);
+	softirq = update_tsk_timer(&tsk->thread.softirq_timer, lc->softirq_timer);
+	lc->steal_timer += clock - user - guest - system - hardirq - softirq;
 
 	/* Push account value */
 	if (user) {
@@ -225,10 +217,6 @@ static u64 vtime_delta(void)
 	return timer - lc->last_update_timer;
 }
 
-/*
- * Update process times based on virtual cpu times stored by entry.S
- * to the lowcore fields user_timer, system_timer & steal_clock.
- */
 void vtime_account_kernel(struct task_struct *tsk)
 {
 	struct lowcore *lc = get_lowcore();
@@ -238,27 +226,17 @@ void vtime_account_kernel(struct task_struct *tsk)
 		lc->guest_timer += delta;
 	else
 		lc->system_timer += delta;
-
-	virt_timer_forward(delta);
 }
 EXPORT_SYMBOL_GPL(vtime_account_kernel);
 
 void vtime_account_softirq(struct task_struct *tsk)
 {
-	u64 delta = vtime_delta();
-
-	get_lowcore()->softirq_timer += delta;
-
-	virt_timer_forward(delta);
+	get_lowcore()->softirq_timer += vtime_delta();
 }
 
 void vtime_account_hardirq(struct task_struct *tsk)
 {
-	u64 delta = vtime_delta();
-
-	get_lowcore()->hardirq_timer += delta;
-
-	virt_timer_forward(delta);
+	get_lowcore()->hardirq_timer += vtime_delta();
 }
 
 /*
diff --git a/arch/s390/mm/pfault.c b/arch/s390/mm/pfault.c
index 2f829448c719..6ecd6b0a22a8 100644
--- a/arch/s390/mm/pfault.c
+++ b/arch/s390/mm/pfault.c
@@ -62,7 +62,7 @@ int __pfault_init(void)
 		"0:	nopr	%%r7\n"
 		EX_TABLE(0b, 0b)
 		: [rc] "+d" (rc)
-		: [refbk] "a" (&pfault_init_refbk), "m" (pfault_init_refbk)
+		: [refbk] "a" (virt_to_phys(&pfault_init_refbk)), "m" (pfault_init_refbk)
 		: "cc");
 	return rc;
 }
@@ -84,7 +84,7 @@ void __pfault_fini(void)
 		"0:	nopr	%%r7\n"
 		EX_TABLE(0b, 0b)
 		:
-		: [refbk] "a" (&pfault_fini_refbk), "m" (pfault_fini_refbk)
+		: [refbk] "a" (virt_to_phys(&pfault_fini_refbk)), "m" (pfault_fini_refbk)
 		: "cc");
 }
 
diff --git a/arch/sparc/kernel/iommu.c b/arch/sparc/kernel/iommu.c
index 46ef88bc9c26..7613ab0ffb89 100644
--- a/arch/sparc/kernel/iommu.c
+++ b/arch/sparc/kernel/iommu.c
@@ -312,6 +312,8 @@ static dma_addr_t dma_4u_map_phys(struct device *dev, phys_addr_t phys,
 	if (direction != DMA_TO_DEVICE)
 		iopte_protection |= IOPTE_WRITE;
 
+	phys &= IO_PAGE_MASK;
+
 	for (i = 0; i < npages; i++, base++, phys += IO_PAGE_SIZE)
 		iopte_val(*base) = iopte_protection | phys;
 
diff --git a/arch/sparc/kernel/pci_sun4v.c b/arch/sparc/kernel/pci_sun4v.c
index 440284cc804e..61f14b4c8f90 100644
--- a/arch/sparc/kernel/pci_sun4v.c
+++ b/arch/sparc/kernel/pci_sun4v.c
@@ -410,6 +410,8 @@ static dma_addr_t dma_4v_map_phys(struct device *dev, phys_addr_t phys,
 
 	iommu_batch_start(dev, prot, entry);
 
+	phys &= IO_PAGE_MASK;
+
 	for (i = 0; i < npages; i++, phys += IO_PAGE_SIZE) {
 		long err = iommu_batch_add(phys, mask);
 		if (unlikely(err < 0L))
diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c
index 012b2bcaa8a0..20fc33300a95 100644
--- a/arch/um/drivers/ubd_kern.c
+++ b/arch/um/drivers/ubd_kern.c
@@ -69,11 +69,11 @@ struct io_thread_req {
 };
 
 
-static struct io_thread_req * (*irq_req_buffer)[];
+static struct io_thread_req **irq_req_buffer;
 static struct io_thread_req *irq_remainder;
 static int irq_remainder_size;
 
-static struct io_thread_req * (*io_req_buffer)[];
+static struct io_thread_req **io_req_buffer;
 static struct io_thread_req *io_remainder;
 static int io_remainder_size;
 
@@ -398,7 +398,7 @@ static int thread_fd = -1;
 
 static int bulk_req_safe_read(
 	int fd,
-	struct io_thread_req * (*request_buffer)[],
+	struct io_thread_req **request_buffer,
 	struct io_thread_req **remainder,
 	int *remainder_size,
 	int max_recs
@@ -465,7 +465,7 @@ static irqreturn_t ubd_intr(int irq, void *dev)
 			&irq_remainder, &irq_remainder_size,
 			UBD_REQ_BUFFER_SIZE)) >= 0) {
 		for (i = 0; i < len / sizeof(struct io_thread_req *); i++)
-			ubd_end_request((*irq_req_buffer)[i]);
+			ubd_end_request(irq_req_buffer[i]);
 	}
 
 	if (len < 0 && len != -EAGAIN)
@@ -1512,7 +1512,7 @@ void *io_thread(void *arg)
 		}
 
 		for (count = 0; count < n/sizeof(struct io_thread_req *); count++) {
-			struct io_thread_req *req = (*io_req_buffer)[count];
+			struct io_thread_req *req = io_req_buffer[count];
 			int i;
 
 			io_count++;