Merge tag 'powerpc-5.17-3' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc fixes from Michael Ellerman:

 - Fix VM debug warnings on boot triggered via __set_fixmap().

 - Fix a debug warning in the 64-bit Book3S PMU handling code.

 - Fix nested guest HFSCR handling with multiple vCPUs on Power9 or
   later.

 - Fix decrementer storm caused by a recent change, seen with some
   configs.

Thanks to Alexey Kardashevskiy, Athira Rajeev, Christophe Leroy,
Fabiano Rosas, Maxime Bizon, Nicholas Piggin, and Sachin Sant.

* tag 'powerpc-5.17-3' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux:
  powerpc/64s/interrupt: Fix decrementer storm
  KVM: PPC: Book3S HV Nested: Fix nested HFSCR being clobbered with multiple vCPUs
  powerpc/perf: Fix power_pmu_disable to call clear_pmi_irq_pending only if PMI is pending
  powerpc/fixmap: Fix VM debug warning on unmap

arch/powerpc/include/asm/book3s/32/pgtable.h

@@ -178,6 +178,7 @@ static inline bool pte_user(pte_t pte)
 #ifndef __ASSEMBLY__
 
 int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot);
+void unmap_kernel_page(unsigned long va);
 
 #endif /* !__ASSEMBLY__ */
 

arch/powerpc/include/asm/book3s/64/pgtable.h

@@ -1082,6 +1082,8 @@ static inline int map_kernel_page(unsigned long ea, unsigned long pa, pgprot_t p
 	return hash__map_kernel_page(ea, pa, prot);
 }
 
+void unmap_kernel_page(unsigned long va);
+
 static inline int __meminit vmemmap_create_mapping(unsigned long start,
 						   unsigned long page_size,
 						   unsigned long phys)

arch/powerpc/include/asm/fixmap.h

@@ -111,8 +111,10 @@ static inline void __set_fixmap(enum fixed_addresses idx,
 		BUILD_BUG_ON(idx >= __end_of_fixed_addresses);
 	else if (WARN_ON(idx >= __end_of_fixed_addresses))
 		return;
-
-	map_kernel_page(__fix_to_virt(idx), phys, flags);
+	if (pgprot_val(flags))
+		map_kernel_page(__fix_to_virt(idx), phys, flags);
+	else
+		unmap_kernel_page(__fix_to_virt(idx));
 }
 
 #define __early_set_fixmap	__set_fixmap

arch/powerpc/include/asm/kvm_book3s_64.h

@@ -39,7 +39,6 @@ struct kvm_nested_guest {
 	pgd_t *shadow_pgtable;		/* our page table for this guest */
 	u64 l1_gr_to_hr;		/* L1's addr of part'n-scoped table */
 	u64 process_table;		/* process table entry for this guest */
-	u64 hfscr;			/* HFSCR that the L1 requested for this nested guest */
 	long refcnt;			/* number of pointers to this struct */
 	struct mutex tlb_lock;		/* serialize page faults and tlbies */
 	struct kvm_nested_guest *next;

arch/powerpc/include/asm/kvm_host.h

@@ -818,6 +818,7 @@ struct kvm_vcpu_arch {
 
 	/* For support of nested guests */
 	struct kvm_nested_guest *nested;
+	u64 nested_hfscr;	/* HFSCR that the L1 requested for the nested guest */
 	u32 nested_vcpu_id;
 	gpa_t nested_io_gpr;
 #endif

arch/powerpc/include/asm/nohash/32/pgtable.h

@@ -64,6 +64,7 @@ extern int icache_44x_need_flush;
 #ifndef __ASSEMBLY__
 
 int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot);
+void unmap_kernel_page(unsigned long va);
 
 #endif /* !__ASSEMBLY__ */
 

arch/powerpc/include/asm/nohash/64/pgtable.h

@@ -308,6 +308,7 @@ static inline void __ptep_set_access_flags(struct vm_area_struct *vma,
 #define __swp_entry_to_pte(x)		__pte((x).val)
 
 int map_kernel_page(unsigned long ea, unsigned long pa, pgprot_t prot);
+void unmap_kernel_page(unsigned long va);
 extern int __meminit vmemmap_create_mapping(unsigned long start,
 					    unsigned long page_size,
 					    unsigned long phys);

arch/powerpc/kernel/time.c

@@ -649,8 +649,9 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(timer_interrupt)
 		__this_cpu_inc(irq_stat.timer_irqs_event);
 	} else {
 		now = *next_tb - now;
-		if (now <= decrementer_max)
-			set_dec_or_work(now);
+		if (now > decrementer_max)
+			now = decrementer_max;
+		set_dec_or_work(now);
 		__this_cpu_inc(irq_stat.timer_irqs_others);
 	}
 

arch/powerpc/kvm/book3s_hv.c

@@ -1816,7 +1816,6 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu,
 
 static int kvmppc_handle_nested_exit(struct kvm_vcpu *vcpu)
 {
-	struct kvm_nested_guest *nested = vcpu->arch.nested;
 	int r;
 	int srcu_idx;
 
@@ -1922,7 +1921,7 @@ static int kvmppc_handle_nested_exit(struct kvm_vcpu *vcpu)
 		 * it into a HEAI.
 		 */
 		if (!(vcpu->arch.hfscr_permitted & (1UL << cause)) ||
-					(nested->hfscr & (1UL << cause))) {
+				(vcpu->arch.nested_hfscr & (1UL << cause))) {
 			vcpu->arch.trap = BOOK3S_INTERRUPT_H_EMUL_ASSIST;
 
 			/*

arch/powerpc/kvm/book3s_hv_nested.c

@@ -363,7 +363,7 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu)
 	/* set L1 state to L2 state */
 	vcpu->arch.nested = l2;
 	vcpu->arch.nested_vcpu_id = l2_hv.vcpu_token;
-	l2->hfscr = l2_hv.hfscr;
+	vcpu->arch.nested_hfscr = l2_hv.hfscr;
 	vcpu->arch.regs = l2_regs;
 
 	/* Guest must always run with ME enabled, HV disabled. */

arch/powerpc/mm/pgtable.c

@@ -206,6 +206,15 @@ void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
 	__set_pte_at(mm, addr, ptep, pte, 0);
 }
 
+void unmap_kernel_page(unsigned long va)
+{
+	pmd_t *pmdp = pmd_off_k(va);
+	pte_t *ptep = pte_offset_kernel(pmdp, va);
+
+	pte_clear(&init_mm, va, ptep);
+	flush_tlb_kernel_range(va, va + PAGE_SIZE);
+}
+
 /*
  * This is called when relaxing access to a PTE. It's also called in the page
  * fault path when we don't hit any of the major fault cases, ie, a minor

arch/powerpc/perf/core-book3s.c

@@ -1355,9 +1355,20 @@ static void power_pmu_disable(struct pmu *pmu)
 		 * Otherwise provide a warning if there is PMI pending, but
 		 * no counter is found overflown.
 		 */
-		if (any_pmc_overflown(cpuhw))
-			clear_pmi_irq_pending();
-		else
+		if (any_pmc_overflown(cpuhw)) {
+			/*
+			 * Since power_pmu_disable runs under local_irq_save, it
+			 * could happen that code hits a PMC overflow without PMI
+			 * pending in paca. Hence only clear PMI pending if it was
+			 * set.
+			 *
+			 * If a PMI is pending, then MSR[EE] must be disabled (because
+			 * the masked PMI handler disabling EE). So it is safe to
+			 * call clear_pmi_irq_pending().
+			 */
+			if (pmi_irq_pending())
+				clear_pmi_irq_pending();
+		} else
 			WARN_ON(pmi_irq_pending());
 
 		val = mmcra = cpuhw->mmcr.mmcra;