18 files changed, 125 insertions, 81 deletions

diff --git a/arch/powerpc/include/asm/book3s/32/kup.h b/arch/powerpc/include/asm/book3s/32/kup.h
index 64201125a287..d4b145b279f6 100644
--- a/arch/powerpc/include/asm/book3s/32/kup.h
+++ b/arch/powerpc/include/asm/book3s/32/kup.h
@@ -4,6 +4,8 @@
 
 #include <asm/bug.h>
 #include <asm/book3s/32/mmu-hash.h>
+#include <asm/mmu.h>
+#include <asm/synch.h>
 
 #ifndef __ASSEMBLY__
 
@@ -28,6 +30,15 @@ static inline void kuep_lock(void)
 		return;
 
 	update_user_segments(mfsr(0) | SR_NX);
+	/*
+	 * This isync() shouldn't be necessary as the kernel is not excepted to
+	 * run any instruction in userspace soon after the update of segments,
+	 * but hash based cores (at least G3) seem to exhibit a random
+	 * behaviour when the 'isync' is not there. 603 cores don't have this
+	 * behaviour so don't do the 'isync' as it saves several CPU cycles.
+	 */
+	if (mmu_has_feature(MMU_FTR_HPTE_TABLE))
+		isync();	/* Context sync required after mtsr() */
 }
 
 static inline void kuep_unlock(void)
@@ -36,6 +47,15 @@ static inline void kuep_unlock(void)
 		return;
 
 	update_user_segments(mfsr(0) & ~SR_NX);
+	/*
+	 * This isync() shouldn't be necessary as a 'rfi' will soon be executed
+	 * to return to userspace, but hash based cores (at least G3) seem to
+	 * exhibit a random behaviour when the 'isync' is not there. 603 cores
+	 * don't have this behaviour so don't do the 'isync' as it saves several
+	 * CPU cycles.
+	 */
+	if (mmu_has_feature(MMU_FTR_HPTE_TABLE))
+		isync();	/* Context sync required after mtsr() */
 }
 
 #ifdef CONFIG_PPC_KUAP
diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h
index d4bdf7d274ac..6b800d3e2681 100644
--- a/arch/powerpc/include/asm/interrupt.h
+++ b/arch/powerpc/include/asm/interrupt.h
@@ -583,6 +583,9 @@ DECLARE_INTERRUPT_HANDLER_NMI(hmi_exception_realmode);
 
 DECLARE_INTERRUPT_HANDLER_ASYNC(TAUException);
 
+/* irq.c */
+DECLARE_INTERRUPT_HANDLER_ASYNC(do_IRQ);
+
 void __noreturn unrecoverable_exception(struct pt_regs *regs);
 
 void replay_system_reset(void);
diff --git a/arch/powerpc/include/asm/irq.h b/arch/powerpc/include/asm/irq.h
index 4982f3711fc3..2b3278534bc1 100644
--- a/arch/powerpc/include/asm/irq.h
+++ b/arch/powerpc/include/asm/irq.h
@@ -52,7 +52,7 @@ extern void *mcheckirq_ctx[NR_CPUS];
 extern void *hardirq_ctx[NR_CPUS];
 extern void *softirq_ctx[NR_CPUS];
 
-extern void do_IRQ(struct pt_regs *regs);
+void __do_IRQ(struct pt_regs *regs);
 extern void __init init_IRQ(void);
 extern void __do_irq(struct pt_regs *regs);
 
diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h
index f9c235c1d6ce..6e560f035614 100644
--- a/arch/powerpc/include/asm/ptrace.h
+++ b/arch/powerpc/include/asm/ptrace.h
@@ -77,6 +77,22 @@ struct pt_regs
 		unsigned long __pad[4];	/* Maintain 16 byte interrupt stack alignment */
 	};
 #endif
+#if defined(CONFIG_PPC32) && defined(CONFIG_BOOKE)
+	struct { /* Must be a multiple of 16 bytes */
+		unsigned long mas0;
+		unsigned long mas1;
+		unsigned long mas2;
+		unsigned long mas3;
+		unsigned long mas6;
+		unsigned long mas7;
+		unsigned long srr0;
+		unsigned long srr1;
+		unsigned long csrr0;
+		unsigned long csrr1;
+		unsigned long dsrr0;
+		unsigned long dsrr1;
+	};
+#endif
 };
 #endif
 
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 8357d5fcd09e..e563d3222d69 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -302,24 +302,21 @@ int main(void)
 	STACK_PT_REGS_OFFSET(STACK_REGS_IAMR, iamr);
 #endif
 
-#if defined(CONFIG_PPC32)
-#if defined(CONFIG_BOOKE) || defined(CONFIG_40x)
-	DEFINE(EXC_LVL_SIZE, STACK_EXC_LVL_FRAME_SIZE);
-	DEFINE(MAS0, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, mas0));
+#if defined(CONFIG_PPC32) && defined(CONFIG_BOOKE)
+	STACK_PT_REGS_OFFSET(MAS0, mas0);
 	/* we overload MMUCR for 44x on MAS0 since they are mutually exclusive */
-	DEFINE(MMUCR, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, mas0));
-	DEFINE(MAS1, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, mas1));
-	DEFINE(MAS2, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, mas2));
-	DEFINE(MAS3, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, mas3));
-	DEFINE(MAS6, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, mas6));
-	DEFINE(MAS7, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, mas7));
-	DEFINE(_SRR0, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, srr0));
-	DEFINE(_SRR1, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, srr1));
-	DEFINE(_CSRR0, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, csrr0));
-	DEFINE(_CSRR1, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, csrr1));
-	DEFINE(_DSRR0, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, dsrr0));
-	DEFINE(_DSRR1, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, dsrr1));
-#endif
+	STACK_PT_REGS_OFFSET(MMUCR, mas0);
+	STACK_PT_REGS_OFFSET(MAS1, mas1);
+	STACK_PT_REGS_OFFSET(MAS2, mas2);
+	STACK_PT_REGS_OFFSET(MAS3, mas3);
+	STACK_PT_REGS_OFFSET(MAS6, mas6);
+	STACK_PT_REGS_OFFSET(MAS7, mas7);
+	STACK_PT_REGS_OFFSET(_SRR0, srr0);
+	STACK_PT_REGS_OFFSET(_SRR1, srr1);
+	STACK_PT_REGS_OFFSET(_CSRR0, csrr0);
+	STACK_PT_REGS_OFFSET(_CSRR1, csrr1);
+	STACK_PT_REGS_OFFSET(_DSRR0, dsrr0);
+	STACK_PT_REGS_OFFSET(_DSRR1, dsrr1);
 #endif
 
 	/* About the CPU features table */
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 4aec59a77d4c..37859e62a8dc 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -812,7 +812,6 @@ __start_interrupts:
  * syscall register convention is in Documentation/powerpc/syscall64-abi.rst
  */
 EXC_VIRT_BEGIN(system_call_vectored, 0x3000, 0x1000)
-1:
 	/* SCV 0 */
 	mr	r9,r13
 	GET_PACA(r13)
@@ -842,10 +841,12 @@ EXC_VIRT_BEGIN(system_call_vectored, 0x3000, 0x1000)
 	b	system_call_vectored_sigill
 #endif
 	.endr
-2:
 EXC_VIRT_END(system_call_vectored, 0x3000, 0x1000)
 
-SOFT_MASK_TABLE(1b, 2b) // Treat scv vectors as soft-masked, see comment above.
+// Treat scv vectors as soft-masked, see comment above.
+// Use absolute values rather than labels here, so they don't get relocated,
+// because this code runs unrelocated.
+SOFT_MASK_TABLE(0xc000000000003000, 0xc000000000004000)
 
 #ifdef CONFIG_RELOCATABLE
 TRAMP_VIRT_BEGIN(system_call_vectored_tramp)
diff --git a/arch/powerpc/kernel/head_book3s_32.S b/arch/powerpc/kernel/head_book3s_32.S
index 764edd860ed4..68e5c0a7e99d 100644
--- a/arch/powerpc/kernel/head_book3s_32.S
+++ b/arch/powerpc/kernel/head_book3s_32.S
@@ -300,7 +300,7 @@ ALT_MMU_FTR_SECTION_END_IFSET(MMU_FTR_HPTE_TABLE)
 	EXCEPTION_PROLOG_1
 	EXCEPTION_PROLOG_2 INTERRUPT_DATA_STORAGE DataAccess handle_dar_dsisr=1
 	prepare_transfer_to_handler
-	lwz	r5, _DSISR(r11)
+	lwz	r5, _DSISR(r1)
 	andis.	r0, r5, DSISR_DABRMATCH@h
 	bne-	1f
 	bl	do_page_fault
diff --git a/arch/powerpc/kernel/head_booke.h b/arch/powerpc/kernel/head_booke.h
index 87b806e8eded..e5503420b6c6 100644
--- a/arch/powerpc/kernel/head_booke.h
+++ b/arch/powerpc/kernel/head_booke.h
@@ -168,20 +168,18 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_EMB_HV)
 /* only on e500mc */
 #define DBG_STACK_BASE		dbgirq_ctx
 
-#define EXC_LVL_FRAME_OVERHEAD	(THREAD_SIZE - INT_FRAME_SIZE - EXC_LVL_SIZE)
-
 #ifdef CONFIG_SMP
 #define BOOKE_LOAD_EXC_LEVEL_STACK(level)		\
 	mfspr	r8,SPRN_PIR;				\
 	slwi	r8,r8,2;				\
 	addis	r8,r8,level##_STACK_BASE@ha;		\
 	lwz	r8,level##_STACK_BASE@l(r8);		\
-	addi	r8,r8,EXC_LVL_FRAME_OVERHEAD;
+	addi	r8,r8,THREAD_SIZE - INT_FRAME_SIZE;
 #else
 #define BOOKE_LOAD_EXC_LEVEL_STACK(level)		\
 	lis	r8,level##_STACK_BASE@ha;		\
 	lwz	r8,level##_STACK_BASE@l(r8);		\
-	addi	r8,r8,EXC_LVL_FRAME_OVERHEAD;
+	addi	r8,r8,THREAD_SIZE - INT_FRAME_SIZE;
 #endif
 
 /*
@@ -208,7 +206,7 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_EMB_HV)
 	mtmsr	r11;							\
 	mfspr	r11,SPRN_SPRG_THREAD;	/* if from user, start at top of   */\
 	lwz	r11, TASK_STACK - THREAD(r11); /* this thread's kernel stack */\
-	addi	r11,r11,EXC_LVL_FRAME_OVERHEAD;	/* allocate stack frame    */\
+	addi	r11,r11,THREAD_SIZE - INT_FRAME_SIZE;	/* allocate stack frame    */\
 	beq	1f;							     \
 	/* COMING FROM USER MODE */					     \
 	stw	r9,_CCR(r11);		/* save CR			   */\
@@ -516,24 +514,5 @@ label:
 	bl	kernel_fp_unavailable_exception;			      \
 	b	interrupt_return
 
-#else /* __ASSEMBLY__ */
-struct exception_regs {
-	unsigned long mas0;
-	unsigned long mas1;
-	unsigned long mas2;
-	unsigned long mas3;
-	unsigned long mas6;
-	unsigned long mas7;
-	unsigned long srr0;
-	unsigned long srr1;
-	unsigned long csrr0;
-	unsigned long csrr1;
-	unsigned long dsrr0;
-	unsigned long dsrr1;
-};
-
-/* ensure this structure is always sized to a multiple of the stack alignment */
-#define STACK_EXC_LVL_FRAME_SIZE	ALIGN(sizeof (struct exception_regs), 16)
-
 #endif /* __ASSEMBLY__ */
 #endif /* __HEAD_BOOKE_H__ */
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 91e63eac4e8f..551b653228c4 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -750,7 +750,7 @@ void __do_irq(struct pt_regs *regs)
 	trace_irq_exit(regs);
 }
 
-DEFINE_INTERRUPT_HANDLER_ASYNC(do_IRQ)
+void __do_IRQ(struct pt_regs *regs)
 {
 	struct pt_regs *old_regs = set_irq_regs(regs);
 	void *cursp, *irqsp, *sirqsp;
@@ -774,6 +774,11 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(do_IRQ)
 	set_irq_regs(old_regs);
 }
 
+DEFINE_INTERRUPT_HANDLER_ASYNC(do_IRQ)
+{
+	__do_IRQ(regs);
+}
+
 static void *__init alloc_vm_stack(void)
 {
 	return __vmalloc_node(THREAD_SIZE, THREAD_ALIGN, THREADINFO_GFP,
diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c
index cbc28d1a2e1b..7a7cd6bda53e 100644
--- a/arch/powerpc/kernel/kprobes.c
+++ b/arch/powerpc/kernel/kprobes.c
@@ -292,7 +292,8 @@ int kprobe_handler(struct pt_regs *regs)
 	if (user_mode(regs))
 		return 0;
 
-	if (!(regs->msr & MSR_IR) || !(regs->msr & MSR_DR))
+	if (!IS_ENABLED(CONFIG_BOOKE) &&
+	    (!(regs->msr & MSR_IR) || !(regs->msr & MSR_DR)))
 		return 0;
 
 	/*
diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c
index 5ff0e55d0db1..defecb3b1b15 100644
--- a/arch/powerpc/kernel/sysfs.c
+++ b/arch/powerpc/kernel/sysfs.c
@@ -1167,7 +1167,7 @@ static int __init topology_init(void)
 		 * CPU.  For instance, the boot cpu might never be valid
 		 * for hotplugging.
 		 */
-		if (smp_ops->cpu_offline_self)
+		if (smp_ops && smp_ops->cpu_offline_self)
 			c->hotpluggable = 1;
 #endif
 
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 77bae85e2fae..934d8ae66cc6 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -585,7 +585,7 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(timer_interrupt)
 
 #if defined(CONFIG_PPC32) && defined(CONFIG_PPC_PMAC)
 	if (atomic_read(&ppc_n_lost_interrupts) != 0)
-		do_IRQ(regs);
+		__do_IRQ(regs);
 #endif
 
 	old_regs = set_irq_regs(regs);
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 3a344f5265c2..96bec6349876 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -1104,7 +1104,7 @@ DEFINE_INTERRUPT_HANDLER(RunModeException)
 	_exception(SIGTRAP, regs, TRAP_UNK, 0);
 }
 
-DEFINE_INTERRUPT_HANDLER(single_step_exception)
+static void __single_step_exception(struct pt_regs *regs)
 {
 	clear_single_step(regs);
 	clear_br_trace(regs);
@@ -1121,6 +1121,11 @@ DEFINE_INTERRUPT_HANDLER(single_step_exception)
 	_exception(SIGTRAP, regs, TRAP_TRACE, regs->nip);
 }
 
+DEFINE_INTERRUPT_HANDLER(single_step_exception)
+{
+	__single_step_exception(regs);
+}
+
 /*
  * After we have successfully emulated an instruction, we have to
  * check if the instruction was being single-stepped, and if so,
@@ -1130,7 +1135,7 @@ DEFINE_INTERRUPT_HANDLER(single_step_exception)
 static void emulate_single_step(struct pt_regs *regs)
 {
 	if (single_stepping(regs))
-		single_step_exception(regs);
+		__single_step_exception(regs);
 }
 
 static inline int __parse_fpscr(unsigned long fpscr)
diff --git a/arch/powerpc/kernel/vdso64/Makefile b/arch/powerpc/kernel/vdso64/Makefile
index 2813e3f98db6..3c5baaa6f1e7 100644
--- a/arch/powerpc/kernel/vdso64/Makefile
+++ b/arch/powerpc/kernel/vdso64/Makefile
@@ -27,6 +27,13 @@ KASAN_SANITIZE := n
 
 ccflags-y := -shared -fno-common -fno-builtin -nostdlib \
 	-Wl,-soname=linux-vdso64.so.1 -Wl,--hash-style=both
+
+# Go prior to 1.16.x assumes r30 is not clobbered by any VDSO code. That used to be true
+# by accident when the VDSO was hand-written asm code, but may not be now that the VDSO is
+# compiler generated. To avoid breaking Go tell GCC not to use r30. Impact on code
+# generation is minimal, it will just use r29 instead.
+ccflags-y += $(call cc-option, -ffixed-r30)
+
 asflags-y := -D__VDSO64__ -s
 
 targets += vdso64.lds
diff --git a/arch/powerpc/mm/pageattr.c b/arch/powerpc/mm/pageattr.c
index 0876216ceee6..edea388e9d3f 100644
--- a/arch/powerpc/mm/pageattr.c
+++ b/arch/powerpc/mm/pageattr.c
@@ -18,16 +18,12 @@
 /*
  * Updates the attributes of a page in three steps:
  *
- * 1. invalidate the page table entry
- * 2. flush the TLB
- * 3. install the new entry with the updated attributes
- *
- * Invalidating the pte means there are situations where this will not work
- * when in theory it should.
- * For example:
- * - removing write from page whilst it is being executed
- * - setting a page read-only whilst it is being read by another CPU
+ * 1. take the page_table_lock
+ * 2. install the new entry with the updated attributes
+ * 3. flush the TLB
  *
+ * This sequence is safe against concurrent updates, and also allows updating the
+ * attributes of a page currently being executed or accessed.
  */
 static int change_page_attr(pte_t *ptep, unsigned long addr, void *data)
 {
@@ -36,9 +32,7 @@ static int change_page_attr(pte_t *ptep, unsigned long addr, void *data)
 
 	spin_lock(&init_mm.page_table_lock);
 
-	/* invalidate the PTE so it's safe to modify */
-	pte = ptep_get_and_clear(&init_mm, addr, ptep);
-	flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
+	pte = ptep_get(ptep);
 
 	/* modify the PTE bits as desired, then apply */
 	switch (action) {
@@ -59,11 +53,14 @@ static int change_page_attr(pte_t *ptep, unsigned long addr, void *data)
 		break;
 	}
 
-	set_pte_at(&init_mm, addr, ptep, pte);
+	pte_update(&init_mm, addr, ptep, ~0UL, pte_val(pte), 0);
 
 	/* See ptesync comment in radix__set_pte_at() */
 	if (radix_enabled())
 		asm volatile("ptesync": : :"memory");
+
+	flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
+
 	spin_unlock(&init_mm.page_table_lock);
 
 	return 0;
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index 6794145603de..a208997ade88 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -98,7 +98,7 @@ config PPC_BOOK3S_64
 	select PPC_HAVE_PMU_SUPPORT
 	select HAVE_ARCH_TRANSPARENT_HUGEPAGE
 	select ARCH_ENABLE_HUGEPAGE_MIGRATION if HUGETLB_PAGE && MIGRATION
-	select ARCH_ENABLE_PMD_SPLIT_PTLOCK
+	select ARCH_ENABLE_SPLIT_PMD_PTLOCK
 	select ARCH_ENABLE_THP_MIGRATION if TRANSPARENT_HUGEPAGE
 	select ARCH_SUPPORTS_HUGETLBFS
 	select ARCH_SUPPORTS_NUMA_BALANCING
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index 35724caf8a83..f79126f16258 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -77,7 +77,7 @@
 #include "../../../../drivers/pci/pci.h"
 
 DEFINE_STATIC_KEY_FALSE(shared_processor);
-EXPORT_SYMBOL_GPL(shared_processor);
+EXPORT_SYMBOL(shared_processor);
 
 int CMO_PrPSP = -1;
 int CMO_SecPSP = -1;
@@ -541,9 +541,10 @@ static void init_cpu_char_feature_flags(struct h_cpu_char_result *result)
 	 * H_CPU_BEHAV_FAVOUR_SECURITY_H could be set only if
 	 * H_CPU_BEHAV_FAVOUR_SECURITY is.
 	 */
-	if (!(result->behaviour & H_CPU_BEHAV_FAVOUR_SECURITY))
+	if (!(result->behaviour & H_CPU_BEHAV_FAVOUR_SECURITY)) {
 		security_ftr_clear(SEC_FTR_FAVOUR_SECURITY);
-	else if (result->behaviour & H_CPU_BEHAV_FAVOUR_SECURITY_H)
+		pseries_security_flavor = 0;
+	} else if (result->behaviour & H_CPU_BEHAV_FAVOUR_SECURITY_H)
 		pseries_security_flavor = 1;
 	else
 		pseries_security_flavor = 2;
diff --git a/arch/powerpc/sysdev/xive/common.c b/arch/powerpc/sysdev/xive/common.c
index 458645c7a72b..c732ce5a3e1a 100644
--- a/arch/powerpc/sysdev/xive/common.c
+++ b/arch/powerpc/sysdev/xive/common.c
@@ -66,6 +66,7 @@ static struct irq_domain *xive_irq_domain;
 static struct xive_ipi_desc {
 	unsigned int irq;
 	char name[16];
+	atomic_t started;
 } *xive_ipis;
 
 /*
@@ -1107,7 +1108,7 @@ static const struct irq_domain_ops xive_ipi_irq_domain_ops = {
 	.alloc  = xive_ipi_irq_domain_alloc,
 };
 
-static int __init xive_request_ipi(void)
+static int __init xive_init_ipis(void)
 {
 	struct fwnode_handle *fwnode;
 	struct irq_domain *ipi_domain;
@@ -1131,10 +1132,6 @@ static int __init xive_request_ipi(void)
 		struct xive_ipi_desc *xid = &xive_ipis[node];
 		struct xive_ipi_alloc_info info = { node };
 
-		/* Skip nodes without CPUs */
-		if (cpumask_empty(cpumask_of_node(node)))
-			continue;
-
 		/*
 		 * Map one IPI interrupt per node for all cpus of that node.
 		 * Since the HW interrupt number doesn't have any meaning,
@@ -1146,12 +1143,6 @@ static int __init xive_request_ipi(void)
 		xid->irq = ret;
 
 		snprintf(xid->name, sizeof(xid->name), "IPI-%d", node);
-
-		ret = request_irq(xid->irq, xive_muxed_ipi_action,
-				  IRQF_NO_DEBUG | IRQF_PERCPU | IRQF_NO_THREAD,
-				  xid->name, NULL);
-
-		WARN(ret < 0, "Failed to request IPI %d: %d\n", xid->irq, ret);
 	}
 
 	return ret;
@@ -1166,6 +1157,22 @@ out:
 	return ret;
 }
 
+static int xive_request_ipi(unsigned int cpu)
+{
+	struct xive_ipi_desc *xid = &xive_ipis[early_cpu_to_node(cpu)];
+	int ret;
+
+	if (atomic_inc_return(&xid->started) > 1)
+		return 0;
+
+	ret = request_irq(xid->irq, xive_muxed_ipi_action,
+			  IRQF_NO_DEBUG | IRQF_PERCPU | IRQF_NO_THREAD,
+			  xid->name, NULL);
+
+	WARN(ret < 0, "Failed to request IPI %d: %d\n", xid->irq, ret);
+	return ret;
+}
+
 static int xive_setup_cpu_ipi(unsigned int cpu)
 {
 	unsigned int xive_ipi_irq = xive_ipi_cpu_to_irq(cpu);
@@ -1180,6 +1187,9 @@ static int xive_setup_cpu_ipi(unsigned int cpu)
 	if (xc->hw_ipi != XIVE_BAD_IRQ)
 		return 0;
 
+	/* Register the IPI */
+	xive_request_ipi(cpu);
+
 	/* Grab an IPI from the backend, this will populate xc->hw_ipi */
 	if (xive_ops->get_ipi(cpu, xc))
 		return -EIO;
@@ -1219,6 +1229,8 @@ static void xive_cleanup_cpu_ipi(unsigned int cpu, struct xive_cpu *xc)
 	if (xc->hw_ipi == XIVE_BAD_IRQ)
 		return;
 
+	/* TODO: clear IPI mapping */
+
 	/* Mask the IPI */
 	xive_do_source_set_mask(&xc->ipi_data, true);
 
@@ -1241,7 +1253,7 @@ void __init xive_smp_probe(void)
 	smp_ops->cause_ipi = xive_cause_ipi;
 
 	/* Register the IPI */
-	xive_request_ipi();
+	xive_init_ipis();
 
 	/* Allocate and setup IPI for the boot CPU */
 	xive_setup_cpu_ipi(smp_processor_id());