16 files changed, 88 insertions, 68 deletions

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index b8c4ac56bddc..7a5f8dbfbdd0 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -163,7 +163,6 @@ config PPC
 	select ARCH_WANT_IRQS_OFF_ACTIVATE_MM
 	select ARCH_WANT_LD_ORPHAN_WARN
 	select ARCH_WANTS_MODULES_DATA_IN_VMALLOC	if PPC_BOOK3S_32 || PPC_8xx
-	select ARCH_WANTS_NO_INSTR
 	select ARCH_WEAK_RELEASE_ACQUIRE
 	select BINFMT_ELF
 	select BUILDTIME_TABLE_SORT
diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile
index dc4cbf0a5ca9..533457466ce2 100644
--- a/arch/powerpc/Makefile
+++ b/arch/powerpc/Makefile
@@ -253,17 +253,7 @@ PHONY += bootwrapper_install
 bootwrapper_install:
 	$(Q)$(MAKE) $(build)=$(boot) $(patsubst %,$(boot)/%,$@)
 
-# Used to create 'merged defconfigs'
-# To use it $(call) it with the first argument as the base defconfig
-# and the second argument as a space separated list of .config files to merge,
-# without the .config suffix.
-define merge_into_defconfig
-	$(Q)$(CONFIG_SHELL) $(srctree)/scripts/kconfig/merge_config.sh \
-		-m -O $(objtree) $(srctree)/arch/$(ARCH)/configs/$(1) \
-		$(foreach config,$(2),$(srctree)/arch/$(ARCH)/configs/$(config).config)
-	+$(Q)$(MAKE) -f $(srctree)/Makefile olddefconfig
-endef
-
+include $(srctree)/scripts/Makefile.defconf
 PHONY += pseries_le_defconfig
 pseries_le_defconfig:
 	$(call merge_into_defconfig,pseries_defconfig,le)
diff --git a/arch/powerpc/include/asm/Kbuild b/arch/powerpc/include/asm/Kbuild
index bcf95ce0964f..419319c4963c 100644
--- a/arch/powerpc/include/asm/Kbuild
+++ b/arch/powerpc/include/asm/Kbuild
@@ -2,6 +2,7 @@
 generated-y += syscall_table_32.h
 generated-y += syscall_table_64.h
 generated-y += syscall_table_spu.h
+generic-y += agp.h
 generic-y += export.h
 generic-y += kvm_types.h
 generic-y += mcs_spinlock.h
diff --git a/arch/powerpc/include/asm/agp.h b/arch/powerpc/include/asm/agp.h
deleted file mode 100644
index 6b6485c988dd..000000000000
--- a/arch/powerpc/include/asm/agp.h
+++ /dev/null
@@ -1,19 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_POWERPC_AGP_H
-#define _ASM_POWERPC_AGP_H
-#ifdef __KERNEL__
-
-#include <asm/io.h>
-
-#define map_page_into_agp(page) do {} while (0)
-#define unmap_page_from_agp(page) do {} while (0)
-#define flush_agp_cache() mb()
-
-/* GATT allocation. Returns/accepts GATT kernel virtual address. */
-#define alloc_gatt_pages(order)		\
-	((char *)__get_free_pages(GFP_KERNEL, (order)))
-#define free_gatt_pages(table, order)	\
-	free_pages((unsigned long)(table), (order))
-
-#endif /* __KERNEL__ */
-#endif	/* _ASM_POWERPC_AGP_H */
diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush.h b/arch/powerpc/include/asm/book3s/64/tlbflush.h
index dd39313242b4..2bbc0fcce04a 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);
+	else
+		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/interrupt.c b/arch/powerpc/kernel/interrupt.c
index fc6631a80527..0ec1581619db 100644
--- a/arch/powerpc/kernel/interrupt.c
+++ b/arch/powerpc/kernel/interrupt.c
@@ -50,16 +50,18 @@ static inline bool exit_must_hard_disable(void)
  */
 static notrace __always_inline bool prep_irq_for_enabled_exit(bool restartable)
 {
+	bool must_hard_disable = (exit_must_hard_disable() || !restartable);
+
 	/* This must be done with RI=1 because tracing may touch vmaps */
 	trace_hardirqs_on();
 
-	if (exit_must_hard_disable() || !restartable)
+	if (must_hard_disable)
 		__hard_EE_RI_disable();
 
 #ifdef CONFIG_PPC64
 	/* This pattern matches prep_irq_for_idle */
 	if (unlikely(lazy_irq_pending_nocheck())) {
-		if (exit_must_hard_disable() || !restartable) {
+		if (must_hard_disable) {
 			local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
 			__hard_RI_enable();
 		}
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..9be3e818a240 100644
--- a/arch/powerpc/kexec/file_load_64.c
+++ b/arch/powerpc/kexec/file_load_64.c
@@ -26,6 +26,7 @@
 #include <asm/firmware.h>
 #include <asm/kexec_ranges.h>
 #include <asm/crashdump-ppc64.h>
+#include <asm/mmzone.h>
 #include <asm/prom.h>
 
 struct umem_info {
@@ -989,10 +990,13 @@ 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/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c
index dbcfe361831a..ea807aa0c31a 100644
--- a/arch/powerpc/platforms/cell/spufs/inode.c
+++ b/arch/powerpc/platforms/cell/spufs/inode.c
@@ -92,7 +92,7 @@ out:
 }
 
 static int
-spufs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
+spufs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 	      struct iattr *attr)
 {
 	struct inode *inode = d_inode(dentry);
@@ -100,7 +100,7 @@ spufs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
 	if ((attr->ia_valid & ATTR_SIZE) &&
 	    (attr->ia_size != inode->i_size))
 		return -EINVAL;
-	setattr_copy(&init_user_ns, inode, attr);
+	setattr_copy(&nop_mnt_idmap, inode, attr);
 	mark_inode_dirty(inode);
 	return 0;
 }
@@ -237,7 +237,7 @@ spufs_mkdir(struct inode *dir, struct dentry *dentry, unsigned int flags,
 	if (!inode)
 		return -ENOSPC;
 
-	inode_init_owner(&init_user_ns, inode, dir, mode | S_IFDIR);
+	inode_init_owner(&nop_mnt_idmap, inode, dir, mode | S_IFDIR);
 	ctx = alloc_spu_context(SPUFS_I(dir)->i_gang); /* XXX gang */
 	SPUFS_I(inode)->i_ctx = ctx;
 	if (!ctx) {
@@ -468,7 +468,7 @@ spufs_mkgang(struct inode *dir, struct dentry *dentry, umode_t mode)
 		goto out;
 
 	ret = 0;
-	inode_init_owner(&init_user_ns, inode, dir, mode | S_IFDIR);
+	inode_init_owner(&nop_mnt_idmap, inode, dir, mode | S_IFDIR);
 	gang = alloc_spu_gang();
 	SPUFS_I(inode)->i_ctx = NULL;
 	SPUFS_I(inode)->i_gang = gang;