Merging upstream version 6.9.9.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

21 files changed, 122 insertions, 53 deletions

diff --git a/arch/arm64/boot/dts/rockchip/rk3566-quartz64-b.dts b/arch/arm64/boot/dts/rockchip/rk3566-quartz64-b.dts
index 2d92713be2..6195937aa6 100644
--- a/arch/arm64/boot/dts/rockchip/rk3566-quartz64-b.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3566-quartz64-b.dts
@@ -289,7 +289,7 @@
 				regulator-name = "vdd_gpu";
 				regulator-always-on;
 				regulator-boot-on;
-				regulator-min-microvolt = <900000>;
+				regulator-min-microvolt = <500000>;
 				regulator-max-microvolt = <1350000>;
 				regulator-ramp-delay = <6001>;
 
diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h
index 7b610864b3..2d6c886b40 100644
--- a/arch/powerpc/include/asm/interrupt.h
+++ b/arch/powerpc/include/asm/interrupt.h
@@ -336,6 +336,14 @@ static inline void interrupt_nmi_enter_prepare(struct pt_regs *regs, struct inte
 	if (IS_ENABLED(CONFIG_KASAN))
 		return;
 
+	/*
+	 * Likewise, do not use it in real mode if percpu first chunk is not
+	 * embedded. With CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK enabled there
+	 * are chances where percpu allocation can come from vmalloc area.
+	 */
+	if (percpu_first_chunk_is_paged)
+		return;
+
 	/* Otherwise, it should be safe to call it */
 	nmi_enter();
 }
@@ -351,6 +359,8 @@ static inline void interrupt_nmi_exit_prepare(struct pt_regs *regs, struct inter
 		// no nmi_exit for a pseries hash guest taking a real mode exception
 	} else if (IS_ENABLED(CONFIG_KASAN)) {
 		// no nmi_exit for KASAN in real mode
+	} else if (percpu_first_chunk_is_paged) {
+		// no nmi_exit if percpu first chunk is not embedded
 	} else {
 		nmi_exit();
 	}
diff --git a/arch/powerpc/include/asm/io.h b/arch/powerpc/include/asm/io.h
index ba2e13bb87..048e3705af 100644
--- a/arch/powerpc/include/asm/io.h
+++ b/arch/powerpc/include/asm/io.h
@@ -37,7 +37,7 @@ extern struct pci_dev *isa_bridge_pcidev;
  * define properly based on the platform
  */
 #ifndef CONFIG_PCI
-#define _IO_BASE	0
+#define _IO_BASE	POISON_POINTER_DELTA
 #define _ISA_MEM_BASE	0
 #define PCI_DRAM_OFFSET 0
 #elif defined(CONFIG_PPC32)
diff --git a/arch/powerpc/include/asm/percpu.h b/arch/powerpc/include/asm/percpu.h
index 8e5b7d0b85..634970ce13 100644
--- a/arch/powerpc/include/asm/percpu.h
+++ b/arch/powerpc/include/asm/percpu.h
@@ -15,6 +15,16 @@
 #endif /* CONFIG_SMP */
 #endif /* __powerpc64__ */
 
+#if defined(CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK) && defined(CONFIG_SMP)
+#include <linux/jump_label.h>
+DECLARE_STATIC_KEY_FALSE(__percpu_first_chunk_is_paged);
+
+#define percpu_first_chunk_is_paged	\
+		(static_key_enabled(&__percpu_first_chunk_is_paged.key))
+#else
+#define percpu_first_chunk_is_paged	false
+#endif /* CONFIG_PPC64 && CONFIG_SMP */
+
 #include <asm-generic/percpu.h>
 
 #include <asm/paca.h>
diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
index 4690c219bf..63432a33ec 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -647,8 +647,9 @@ __after_prom_start:
  * Note: This process overwrites the OF exception vectors.
  */
 	LOAD_REG_IMMEDIATE(r3, PAGE_OFFSET)
-	mr.	r4,r26			/* In some cases the loader may  */
-	beq	9f			/* have already put us at zero */
+	mr	r4,r26			/* Load the virtual source address into r4 */
+	cmpld	r3,r4			/* Check if source == dest */
+	beq	9f			/* If so skip the copy  */
 	li	r6,0x100		/* Start offset, the first 0x100 */
 					/* bytes were copied earlier.	 */
 
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 2f19d5e944..ae36a12978 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -834,6 +834,7 @@ static __init int pcpu_cpu_to_node(int cpu)
 
 unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
 EXPORT_SYMBOL(__per_cpu_offset);
+DEFINE_STATIC_KEY_FALSE(__percpu_first_chunk_is_paged);
 
 void __init setup_per_cpu_areas(void)
 {
@@ -876,6 +877,7 @@ void __init setup_per_cpu_areas(void)
 	if (rc < 0)
 		panic("cannot initialize percpu area (err=%d)", rc);
 
+	static_key_enable(&__percpu_first_chunk_is_paged.key);
 	delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start;
 	for_each_possible_cpu(cpu) {
                 __per_cpu_offset[cpu] = delta + pcpu_unit_offsets[cpu];
diff --git a/arch/powerpc/kexec/core_64.c b/arch/powerpc/kexec/core_64.c
index 762e4d09aa..27254624f6 100644
--- a/arch/powerpc/kexec/core_64.c
+++ b/arch/powerpc/kexec/core_64.c
@@ -26,6 +26,7 @@
 #include <asm/paca.h>
 #include <asm/mmu.h>
 #include <asm/sections.h>	/* _end */
+#include <asm/setup.h>
 #include <asm/smp.h>
 #include <asm/hw_breakpoint.h>
 #include <asm/svm.h>
@@ -315,6 +316,16 @@ void default_machine_kexec(struct kimage *image)
 	if (!kdump_in_progress())
 		kexec_prepare_cpus();
 
+#ifdef CONFIG_PPC_PSERIES
+	/*
+	 * This must be done after other CPUs have shut down, otherwise they
+	 * could execute the 'scv' instruction, which is not supported with
+	 * reloc disabled (see configure_exceptions()).
+	 */
+	if (firmware_has_feature(FW_FEATURE_SET_MODE))
+		pseries_disable_reloc_on_exc();
+#endif
+
 	printk("kexec: Starting switchover sequence.\n");
 
 	/* switch to a staticly allocated stack.  Based on irq stack code.
diff --git a/arch/powerpc/platforms/pseries/kexec.c b/arch/powerpc/platforms/pseries/kexec.c
index 096d09ed89..431be156ca 100644
--- a/arch/powerpc/platforms/pseries/kexec.c
+++ b/arch/powerpc/platforms/pseries/kexec.c
@@ -61,11 +61,3 @@ void pseries_kexec_cpu_down(int crash_shutdown, int secondary)
 	} else
 		xics_kexec_teardown_cpu(secondary);
 }
-
-void pseries_machine_kexec(struct kimage *image)
-{
-	if (firmware_has_feature(FW_FEATURE_SET_MODE))
-		pseries_disable_reloc_on_exc();
-
-	default_machine_kexec(image);
-}
diff --git a/arch/powerpc/platforms/pseries/pseries.h b/arch/powerpc/platforms/pseries/pseries.h
index bba4ad192b..3968a6970f 100644
--- a/arch/powerpc/platforms/pseries/pseries.h
+++ b/arch/powerpc/platforms/pseries/pseries.h
@@ -38,7 +38,6 @@ static inline void smp_init_pseries(void) { }
 #endif
 
 extern void pseries_kexec_cpu_down(int crash_shutdown, int secondary);
-void pseries_machine_kexec(struct kimage *image);
 
 extern void pSeries_final_fixup(void);
 
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index 284a6fa04b..b44de0f082 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -1159,7 +1159,6 @@ define_machine(pseries) {
 	.machine_check_exception = pSeries_machine_check_exception,
 	.machine_check_log_err	= pSeries_machine_check_log_err,
 #ifdef CONFIG_KEXEC_CORE
-	.machine_kexec          = pseries_machine_kexec,
 	.kexec_cpu_down         = pseries_kexec_cpu_down,
 #endif
 #ifdef CONFIG_MEMORY_HOTPLUG
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index d79d6633f3..bd4813bad3 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -1350,7 +1350,7 @@ static int cpu_cmd(void)
 	}
 	termch = cpu;
 
-	if (!scanhex(&cpu)) {
+	if (!scanhex(&cpu) || cpu >= num_possible_cpus()) {
 		/* print cpus waiting or in xmon */
 		printf("cpus stopped:");
 		last_cpu = first_cpu = NR_CPUS;
@@ -2772,7 +2772,7 @@ static void dump_pacas(void)
 
 	termch = c;	/* Put c back, it wasn't 'a' */
 
-	if (scanhex(&num))
+	if (scanhex(&num) && num < num_possible_cpus())
 		dump_one_paca(num);
 	else
 		dump_one_paca(xmon_owner);
@@ -2845,7 +2845,7 @@ static void dump_xives(void)
 
 	termch = c;	/* Put c back, it wasn't 'a' */
 
-	if (scanhex(&num))
+	if (scanhex(&num) && num < num_possible_cpus())
 		dump_one_xive(num);
 	else
 		dump_one_xive(xmon_owner);
diff --git a/arch/riscv/include/asm/errata_list.h b/arch/riscv/include/asm/errata_list.h
index efd851e1b4..7c8a71a526 100644
--- a/arch/riscv/include/asm/errata_list.h
+++ b/arch/riscv/include/asm/errata_list.h
@@ -43,11 +43,21 @@ ALTERNATIVE(__stringify(RISCV_PTR do_page_fault),			\
 	    CONFIG_ERRATA_SIFIVE_CIP_453)
 #else /* !__ASSEMBLY__ */
 
-#define ALT_FLUSH_TLB_PAGE(x)						\
+#define ALT_SFENCE_VMA_ASID(asid)					\
+asm(ALTERNATIVE("sfence.vma x0, %0", "sfence.vma", SIFIVE_VENDOR_ID,	\
+		ERRATA_SIFIVE_CIP_1200, CONFIG_ERRATA_SIFIVE_CIP_1200)	\
+		: : "r" (asid) : "memory")
+
+#define ALT_SFENCE_VMA_ADDR(addr)					\
 asm(ALTERNATIVE("sfence.vma %0", "sfence.vma", SIFIVE_VENDOR_ID,	\
 		ERRATA_SIFIVE_CIP_1200, CONFIG_ERRATA_SIFIVE_CIP_1200)	\
 		: : "r" (addr) : "memory")
 
+#define ALT_SFENCE_VMA_ADDR_ASID(addr, asid)				\
+asm(ALTERNATIVE("sfence.vma %0, %1", "sfence.vma", SIFIVE_VENDOR_ID,	\
+		ERRATA_SIFIVE_CIP_1200, CONFIG_ERRATA_SIFIVE_CIP_1200)	\
+		: : "r" (addr), "r" (asid) : "memory")
+
 /*
  * _val is marked as "will be overwritten", so need to set it to 0
  * in the default case.
diff --git a/arch/riscv/include/asm/tlbflush.h b/arch/riscv/include/asm/tlbflush.h
index 4112cc8d1d..79dada53d7 100644
--- a/arch/riscv/include/asm/tlbflush.h
+++ b/arch/riscv/include/asm/tlbflush.h
@@ -22,10 +22,27 @@ static inline void local_flush_tlb_all(void)
 	__asm__ __volatile__ ("sfence.vma" : : : "memory");
 }
 
+static inline void local_flush_tlb_all_asid(unsigned long asid)
+{
+	if (asid != FLUSH_TLB_NO_ASID)
+		ALT_SFENCE_VMA_ASID(asid);
+	else
+		local_flush_tlb_all();
+}
+
 /* Flush one page from local TLB */
 static inline void local_flush_tlb_page(unsigned long addr)
 {
-	ALT_FLUSH_TLB_PAGE(__asm__ __volatile__ ("sfence.vma %0" : : "r" (addr) : "memory"));
+	ALT_SFENCE_VMA_ADDR(addr);
+}
+
+static inline void local_flush_tlb_page_asid(unsigned long addr,
+					     unsigned long asid)
+{
+	if (asid != FLUSH_TLB_NO_ASID)
+		ALT_SFENCE_VMA_ADDR_ASID(addr, asid);
+	else
+		local_flush_tlb_page(addr);
 }
 #else /* CONFIG_MMU */
 #define local_flush_tlb_all()			do { } while (0)
diff --git a/arch/riscv/kernel/machine_kexec.c b/arch/riscv/kernel/machine_kexec.c
index ed9cad20c0..3c830a6f7e 100644
--- a/arch/riscv/kernel/machine_kexec.c
+++ b/arch/riscv/kernel/machine_kexec.c
@@ -121,20 +121,12 @@ static void machine_kexec_mask_interrupts(void)
 
 	for_each_irq_desc(i, desc) {
 		struct irq_chip *chip;
-		int ret;
 
 		chip = irq_desc_get_chip(desc);
 		if (!chip)
 			continue;
 
-		/*
-		 * First try to remove the active state. If this
-		 * fails, try to EOI the interrupt.
-		 */
-		ret = irq_set_irqchip_state(i, IRQCHIP_STATE_ACTIVE, false);
-
-		if (ret && irqd_irq_inprogress(&desc->irq_data) &&
-		    chip->irq_eoi)
+		if (chip->irq_eoi && irqd_irq_inprogress(&desc->irq_data))
 			chip->irq_eoi(&desc->irq_data);
 
 		if (chip->irq_mask)
diff --git a/arch/riscv/kvm/vcpu_pmu.c b/arch/riscv/kvm/vcpu_pmu.c
index 86391a5061..cee1b9ca4e 100644
--- a/arch/riscv/kvm/vcpu_pmu.c
+++ b/arch/riscv/kvm/vcpu_pmu.c
@@ -39,7 +39,7 @@ static u64 kvm_pmu_get_sample_period(struct kvm_pmc *pmc)
 	u64 sample_period;
 
 	if (!pmc->counter_val)
-		sample_period = counter_val_mask + 1;
+		sample_period = counter_val_mask;
 	else
 		sample_period = (-pmc->counter_val) & counter_val_mask;
 
diff --git a/arch/riscv/mm/tlbflush.c b/arch/riscv/mm/tlbflush.c
index 07d743f87b..a6f7887748 100644
--- a/arch/riscv/mm/tlbflush.c
+++ b/arch/riscv/mm/tlbflush.c
@@ -7,29 +7,6 @@
 #include <asm/sbi.h>
 #include <asm/mmu_context.h>
 
-static inline void local_flush_tlb_all_asid(unsigned long asid)
-{
-	if (asid != FLUSH_TLB_NO_ASID)
-		__asm__ __volatile__ ("sfence.vma x0, %0"
-				:
-				: "r" (asid)
-				: "memory");
-	else
-		local_flush_tlb_all();
-}
-
-static inline void local_flush_tlb_page_asid(unsigned long addr,
-		unsigned long asid)
-{
-	if (asid != FLUSH_TLB_NO_ASID)
-		__asm__ __volatile__ ("sfence.vma %0, %1"
-				:
-				: "r" (addr), "r" (asid)
-				: "memory");
-	else
-		local_flush_tlb_page(addr);
-}
-
 /*
  * Flush entire TLB if number of entries to be flushed is greater
  * than the threshold below.
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index 9599046188..9281063636 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -427,6 +427,7 @@ struct kvm_vcpu_stat {
 	u64 instruction_io_other;
 	u64 instruction_lpsw;
 	u64 instruction_lpswe;
+	u64 instruction_lpswey;
 	u64 instruction_pfmf;
 	u64 instruction_ptff;
 	u64 instruction_sck;
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index bbbdc5abe2..a589547ee0 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -305,8 +305,8 @@ static inline void __load_psw(psw_t psw)
  */
 static __always_inline void __load_psw_mask(unsigned long mask)
 {
+	psw_t psw __uninitialized;
 	unsigned long addr;
-	psw_t psw;
 
 	psw.mask = mask;
 
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 82e9631cd9..54b5b2565d 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -132,6 +132,7 @@ const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = {
 	STATS_DESC_COUNTER(VCPU, instruction_io_other),
 	STATS_DESC_COUNTER(VCPU, instruction_lpsw),
 	STATS_DESC_COUNTER(VCPU, instruction_lpswe),
+	STATS_DESC_COUNTER(VCPU, instruction_lpswey),
 	STATS_DESC_COUNTER(VCPU, instruction_pfmf),
 	STATS_DESC_COUNTER(VCPU, instruction_ptff),
 	STATS_DESC_COUNTER(VCPU, instruction_sck),
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index 111eb5c747..bf8534218a 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -138,6 +138,21 @@ static inline u64 kvm_s390_get_base_disp_s(struct kvm_vcpu *vcpu, u8 *ar)
 	return (base2 ? vcpu->run->s.regs.gprs[base2] : 0) + disp2;
 }
 
+static inline u64 kvm_s390_get_base_disp_siy(struct kvm_vcpu *vcpu, u8 *ar)
+{
+	u32 base1 = vcpu->arch.sie_block->ipb >> 28;
+	s64 disp1;
+
+	/* The displacement is a 20bit _SIGNED_ value */
+	disp1 = sign_extend64(((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16) +
+			      ((vcpu->arch.sie_block->ipb & 0xff00) << 4), 19);
+
+	if (ar)
+		*ar = base1;
+
+	return (base1 ? vcpu->run->s.regs.gprs[base1] : 0) + disp1;
+}
+
 static inline void kvm_s390_get_base_disp_sse(struct kvm_vcpu *vcpu,
 					      u64 *address1, u64 *address2,
 					      u8 *ar_b1, u8 *ar_b2)
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index 1be19cc9d7..1a49b89706 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -797,6 +797,36 @@ static int handle_lpswe(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
+static int handle_lpswey(struct kvm_vcpu *vcpu)
+{
+	psw_t new_psw;
+	u64 addr;
+	int rc;
+	u8 ar;
+
+	vcpu->stat.instruction_lpswey++;
+
+	if (!test_kvm_facility(vcpu->kvm, 193))
+		return kvm_s390_inject_program_int(vcpu, PGM_OPERATION);
+
+	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
+		return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
+
+	addr = kvm_s390_get_base_disp_siy(vcpu, &ar);
+	if (addr & 7)
+		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+
+	rc = read_guest(vcpu, addr, ar, &new_psw, sizeof(new_psw));
+	if (rc)
+		return kvm_s390_inject_prog_cond(vcpu, rc);
+
+	vcpu->arch.sie_block->gpsw = new_psw;
+	if (!is_valid_psw(&vcpu->arch.sie_block->gpsw))
+		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+
+	return 0;
+}
+
 static int handle_stidp(struct kvm_vcpu *vcpu)
 {
 	u64 stidp_data = vcpu->kvm->arch.model.cpuid;
@@ -1462,6 +1492,8 @@ int kvm_s390_handle_eb(struct kvm_vcpu *vcpu)
 	case 0x61:
 	case 0x62:
 		return handle_ri(vcpu);
+	case 0x71:
+		return handle_lpswey(vcpu);
 	default:
 		return -EOPNOTSUPP;
 	}