diff --git a/arch/powerpc/include/asm/kprobes.h b/arch/powerpc/include/asm/kprobes.h
index a83821f33ea3..8814a7249ceb 100644
--- a/arch/powerpc/include/asm/kprobes.h
+++ b/arch/powerpc/include/asm/kprobes.h
@@ -103,6 +103,7 @@ extern int kprobe_exceptions_notify(struct notifier_block *self,
 extern int kprobe_fault_handler(struct pt_regs *regs, int trapnr);
 extern int kprobe_handler(struct pt_regs *regs);
 extern int kprobe_post_handler(struct pt_regs *regs);
+extern int is_current_kprobe_addr(unsigned long addr);
 #ifdef CONFIG_KPROBES_ON_FTRACE
 extern int skip_singlestep(struct kprobe *p, struct pt_regs *regs,
 			   struct kprobe_ctlblk *kcb);
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index ae418b85c17c..b886795060fd 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -1411,10 +1411,8 @@ USE_TEXT_SECTION()
 	.balign	IFETCH_ALIGN_BYTES
 do_hash_page:
 #ifdef CONFIG_PPC_STD_MMU_64
-	andis.	r0,r4,0xa410		/* weird error? */
+	andis.	r0,r4,0xa450		/* weird error? */
 	bne-	handle_page_fault	/* if not, try to insert a HPTE */
-	andis.  r0,r4,DSISR_DABRMATCH@h
-	bne-    handle_dabr_fault
 	CURRENT_THREAD_INFO(r11, r1)
 	lwz	r0,TI_PREEMPT(r11)	/* If we're in an "NMI" */
 	andis.	r0,r0,NMI_MASK@h	/* (i.e. an irq when soft-disabled) */
@@ -1438,11 +1436,16 @@ do_hash_page:
 
 	/* Error */
 	blt-	13f
+
+	/* Reload DSISR into r4 for the DABR check below */
+	ld      r4,_DSISR(r1)
 #endif /* CONFIG_PPC_STD_MMU_64 */
 
 /* Here we have a page fault that hash_page can't handle. */
 handle_page_fault:
-11:	ld	r4,_DAR(r1)
+11:	andis.  r0,r4,DSISR_DABRMATCH@h
+	bne-    handle_dabr_fault
+	ld	r4,_DAR(r1)
 	ld	r5,_DSISR(r1)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	do_page_fault
diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c
index fc4343514bed..01addfb0ed0a 100644
--- a/arch/powerpc/kernel/kprobes.c
+++ b/arch/powerpc/kernel/kprobes.c
@@ -43,6 +43,12 @@ DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
 
 struct kretprobe_blackpoint kretprobe_blacklist[] = {{NULL, NULL}};
 
+int is_current_kprobe_addr(unsigned long addr)
+{
+	struct kprobe *p = kprobe_running();
+	return (p && (unsigned long)p->addr == addr) ? 1 : 0;
+}
+
 bool arch_within_kprobe_blacklist(unsigned long addr)
 {
 	return  (addr >= (unsigned long)__kprobes_text_start &&
@@ -617,6 +623,15 @@ int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
 	regs->gpr[2] = (unsigned long)(((func_descr_t *)jp->entry)->toc);
 #endif
 
+	/*
+	 * jprobes use jprobe_return() which skips the normal return
+	 * path of the function, and this messes up the accounting of the
+	 * function graph tracer.
+	 *
+	 * Pause function graph tracing while performing the jprobe function.
+	 */
+	pause_graph_tracing();
+
 	return 1;
 }
 NOKPROBE_SYMBOL(setjmp_pre_handler);
@@ -642,6 +657,8 @@ int longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
 	 * saved regs...
 	 */
 	memcpy(regs, &kcb->jprobe_saved_regs, sizeof(struct pt_regs));
+	/* It's OK to start function graph tracing again */
+	unpause_graph_tracing();
 	preempt_enable_no_resched();
 	return 1;
 }
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index a8c1f99e9607..4640f6d64f8b 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -615,6 +615,24 @@ void __init exc_lvl_early_init(void)
 }
 #endif
 
+/*
+ * Emergency stacks are used for a range of things, from asynchronous
+ * NMIs (system reset, machine check) to synchronous, process context.
+ * We set preempt_count to zero, even though that isn't necessarily correct. To
+ * get the right value we'd need to copy it from the previous thread_info, but
+ * doing that might fault causing more problems.
+ * TODO: what to do with accounting?
+ */
+static void emerg_stack_init_thread_info(struct thread_info *ti, int cpu)
+{
+	ti->task = NULL;
+	ti->cpu = cpu;
+	ti->preempt_count = 0;
+	ti->local_flags = 0;
+	ti->flags = 0;
+	klp_init_thread_info(ti);
+}
+
 /*
  * Stack space used when we detect a bad kernel stack pointer, and
  * early in SMP boots before relocation is enabled. Exclusive emergency
@@ -633,24 +651,31 @@ void __init emergency_stack_init(void)
 	 * Since we use these as temporary stacks during secondary CPU
 	 * bringup, we need to get at them in real mode. This means they
 	 * must also be within the RMO region.
+	 *
+	 * The IRQ stacks allocated elsewhere in this file are zeroed and
+	 * initialized in kernel/irq.c. These are initialized here in order
+	 * to have emergency stacks available as early as possible.
 	 */
 	limit = min(safe_stack_limit(), ppc64_rma_size);
 
 	for_each_possible_cpu(i) {
 		struct thread_info *ti;
 		ti = __va(memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit));
-		klp_init_thread_info(ti);
+		memset(ti, 0, THREAD_SIZE);
+		emerg_stack_init_thread_info(ti, i);
 		paca[i].emergency_sp = (void *)ti + THREAD_SIZE;
 
 #ifdef CONFIG_PPC_BOOK3S_64
 		/* emergency stack for NMI exception handling. */
 		ti = __va(memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit));
-		klp_init_thread_info(ti);
+		memset(ti, 0, THREAD_SIZE);
+		emerg_stack_init_thread_info(ti, i);
 		paca[i].nmi_emergency_sp = (void *)ti + THREAD_SIZE;
 
 		/* emergency stack for machine check exception handling. */
 		ti = __va(memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit));
-		klp_init_thread_info(ti);
+		memset(ti, 0, THREAD_SIZE);
+		emerg_stack_init_thread_info(ti, i);
 		paca[i].mc_emergency_sp = (void *)ti + THREAD_SIZE;
 #endif
 	}
diff --git a/arch/powerpc/kernel/trace/ftrace_64_mprofile.S b/arch/powerpc/kernel/trace/ftrace_64_mprofile.S
index 7c933a99f5d5..c98e90b4ea7b 100644
--- a/arch/powerpc/kernel/trace/ftrace_64_mprofile.S
+++ b/arch/powerpc/kernel/trace/ftrace_64_mprofile.S
@@ -45,10 +45,14 @@ _GLOBAL(ftrace_caller)
 	stdu	r1,-SWITCH_FRAME_SIZE(r1)
 
 	/* Save all gprs to pt_regs */
-	SAVE_8GPRS(0,r1)
-	SAVE_8GPRS(8,r1)
-	SAVE_8GPRS(16,r1)
-	SAVE_8GPRS(24,r1)
+	SAVE_GPR(0, r1)
+	SAVE_10GPRS(2, r1)
+	SAVE_10GPRS(12, r1)
+	SAVE_10GPRS(22, r1)
+
+	/* Save previous stack pointer (r1) */
+	addi	r8, r1, SWITCH_FRAME_SIZE
+	std	r8, GPR1(r1)
 
 	/* Load special regs for save below */
 	mfmsr   r8
@@ -95,18 +99,44 @@ ftrace_call:
 	bl	ftrace_stub
 	nop
 
-	/* Load ctr with the possibly modified NIP */
-	ld	r3, _NIP(r1)
-	mtctr	r3
+	/* Load the possibly modified NIP */
+	ld	r15, _NIP(r1)
+
 #ifdef CONFIG_LIVEPATCH
-	cmpd	r14,r3		/* has NIP been altered? */
+	cmpd	r14, r15	/* has NIP been altered? */
 #endif
 
+#if defined(CONFIG_LIVEPATCH) && defined(CONFIG_KPROBES_ON_FTRACE)
+	/* NIP has not been altered, skip over further checks */
+	beq	1f
+
+	/* Check if there is an active kprobe on us */
+	subi	r3, r14, 4
+	bl	is_current_kprobe_addr
+	nop
+
+	/*
+	 * If r3 == 1, then this is a kprobe/jprobe.
+	 * else, this is livepatched function.
+	 *
+	 * The conditional branch for livepatch_handler below will use the
+	 * result of this comparison. For kprobe/jprobe, we just need to branch to
+	 * the new NIP, not call livepatch_handler. The branch below is bne, so we
+	 * want CR0[EQ] to be true if this is a kprobe/jprobe. Which means we want
+	 * CR0[EQ] = (r3 == 1).
+	 */
+	cmpdi	r3, 1
+1:
+#endif
+
+	/* Load CTR with the possibly modified NIP */
+	mtctr	r15
+
 	/* Restore gprs */
-	REST_8GPRS(0,r1)
-	REST_8GPRS(8,r1)
-	REST_8GPRS(16,r1)
-	REST_8GPRS(24,r1)
+	REST_GPR(0,r1)
+	REST_10GPRS(2,r1)
+	REST_10GPRS(12,r1)
+	REST_10GPRS(22,r1)
 
 	/* Restore possibly modified LR */
 	ld	r0, _LINK(r1)
@@ -119,7 +149,10 @@ ftrace_call:
 	addi r1, r1, SWITCH_FRAME_SIZE
 
 #ifdef CONFIG_LIVEPATCH
-        /* Based on the cmpd above, if the NIP was altered handle livepatch */
+        /*
+	 * Based on the cmpd or cmpdi above, if the NIP was altered and we're
+	 * not on a kprobe/jprobe, then handle livepatch.
+	 */
 	bne-	livepatch_handler
 #endif
 
diff --git a/arch/powerpc/perf/perf_regs.c b/arch/powerpc/perf/perf_regs.c
index cbd82fde5770..09ceea6175ba 100644
--- a/arch/powerpc/perf/perf_regs.c
+++ b/arch/powerpc/perf/perf_regs.c
@@ -101,5 +101,6 @@ void perf_get_regs_user(struct perf_regs *regs_user,
 			struct pt_regs *regs_user_copy)
 {
 	regs_user->regs = task_pt_regs(current);
-	regs_user->abi  = perf_reg_abi(current);
+	regs_user->abi = (regs_user->regs) ? perf_reg_abi(current) :
+			 PERF_SAMPLE_REGS_ABI_NONE;
 }
diff --git a/arch/powerpc/platforms/powernv/npu-dma.c b/arch/powerpc/platforms/powernv/npu-dma.c
index e6f444b46207..b5d960d6db3d 100644
--- a/arch/powerpc/platforms/powernv/npu-dma.c
+++ b/arch/powerpc/platforms/powernv/npu-dma.c
@@ -449,7 +449,7 @@ static int mmio_launch_invalidate(struct npu *npu, unsigned long launch,
 	return mmio_atsd_reg;
 }
 
-static int mmio_invalidate_pid(struct npu *npu, unsigned long pid)
+static int mmio_invalidate_pid(struct npu *npu, unsigned long pid, bool flush)
 {
 	unsigned long launch;
 
@@ -465,12 +465,15 @@ static int mmio_invalidate_pid(struct npu *npu, unsigned long pid)
 	/* PID */
 	launch |= pid << PPC_BITLSHIFT(38);
 
+	/* No flush */
+	launch |= !flush << PPC_BITLSHIFT(39);
+
 	/* Invalidating the entire process doesn't use a va */
 	return mmio_launch_invalidate(npu, launch, 0);
 }
 
 static int mmio_invalidate_va(struct npu *npu, unsigned long va,
-			unsigned long pid)
+			unsigned long pid, bool flush)
 {
 	unsigned long launch;
 
@@ -486,26 +489,60 @@ static int mmio_invalidate_va(struct npu *npu, unsigned long va,
 	/* PID */
 	launch |= pid << PPC_BITLSHIFT(38);
 
+	/* No flush */
+	launch |= !flush << PPC_BITLSHIFT(39);
+
 	return mmio_launch_invalidate(npu, launch, va);
 }
 
 #define mn_to_npu_context(x) container_of(x, struct npu_context, mn)
 
+struct mmio_atsd_reg {
+	struct npu *npu;
+	int reg;
+};
+
+static void mmio_invalidate_wait(
+	struct mmio_atsd_reg mmio_atsd_reg[NV_MAX_NPUS], bool flush)
+{
+	struct npu *npu;
+	int i, reg;
+
+	/* Wait for all invalidations to complete */
+	for (i = 0; i <= max_npu2_index; i++) {
+		if (mmio_atsd_reg[i].reg < 0)
+			continue;
+
+		/* Wait for completion */
+		npu = mmio_atsd_reg[i].npu;
+		reg = mmio_atsd_reg[i].reg;
+		while (__raw_readq(npu->mmio_atsd_regs[reg] + XTS_ATSD_STAT))
+			cpu_relax();
+
+		put_mmio_atsd_reg(npu, reg);
+
+		/*
+		 * The GPU requires two flush ATSDs to ensure all entries have
+		 * been flushed. We use PID 0 as it will never be used for a
+		 * process on the GPU.
+		 */
+		if (flush)
+			mmio_invalidate_pid(npu, 0, true);
+	}
+}
+
 /*
  * Invalidate either a single address or an entire PID depending on
  * the value of va.
  */
 static void mmio_invalidate(struct npu_context *npu_context, int va,
-			unsigned long address)
+			unsigned long address, bool flush)
 {
-	int i, j, reg;
+	int i, j;
 	struct npu *npu;
 	struct pnv_phb *nphb;
 	struct pci_dev *npdev;
-	struct {
-		struct npu *npu;
-		int reg;
-	} mmio_atsd_reg[NV_MAX_NPUS];
+	struct mmio_atsd_reg mmio_atsd_reg[NV_MAX_NPUS];
 	unsigned long pid = npu_context->mm->context.id;
 
 	/*
@@ -525,10 +562,11 @@ static void mmio_invalidate(struct npu_context *npu_context, int va,
 
 			if (va)
 				mmio_atsd_reg[i].reg =
-					mmio_invalidate_va(npu, address, pid);
+					mmio_invalidate_va(npu, address, pid,
+							flush);
 			else
 				mmio_atsd_reg[i].reg =
-					mmio_invalidate_pid(npu, pid);
+					mmio_invalidate_pid(npu, pid, flush);
 
 			/*
 			 * The NPU hardware forwards the shootdown to all GPUs
@@ -544,18 +582,10 @@ static void mmio_invalidate(struct npu_context *npu_context, int va,
 	 */
 	flush_tlb_mm(npu_context->mm);
 
-	/* Wait for all invalidations to complete */
-	for (i = 0; i <= max_npu2_index; i++) {
-		if (mmio_atsd_reg[i].reg < 0)
-			continue;
-
-		/* Wait for completion */
-		npu = mmio_atsd_reg[i].npu;
-		reg = mmio_atsd_reg[i].reg;
-		while (__raw_readq(npu->mmio_atsd_regs[reg] + XTS_ATSD_STAT))
-			cpu_relax();
-		put_mmio_atsd_reg(npu, reg);
-	}
+	mmio_invalidate_wait(mmio_atsd_reg, flush);
+	if (flush)
+		/* Wait for the flush to complete */
+		mmio_invalidate_wait(mmio_atsd_reg, false);
 }
 
 static void pnv_npu2_mn_release(struct mmu_notifier *mn,
@@ -571,7 +601,7 @@ static void pnv_npu2_mn_release(struct mmu_notifier *mn,
 	 * There should be no more translation requests for this PID, but we
 	 * need to ensure any entries for it are removed from the TLB.
 	 */
-	mmio_invalidate(npu_context, 0, 0);
+	mmio_invalidate(npu_context, 0, 0, true);
 }
 
 static void pnv_npu2_mn_change_pte(struct mmu_notifier *mn,
@@ -581,7 +611,7 @@ static void pnv_npu2_mn_change_pte(struct mmu_notifier *mn,
 {
 	struct npu_context *npu_context = mn_to_npu_context(mn);
 
-	mmio_invalidate(npu_context, 1, address);
+	mmio_invalidate(npu_context, 1, address, true);
 }
 
 static void pnv_npu2_mn_invalidate_page(struct mmu_notifier *mn,
@@ -590,7 +620,7 @@ static void pnv_npu2_mn_invalidate_page(struct mmu_notifier *mn,
 {
 	struct npu_context *npu_context = mn_to_npu_context(mn);
 
-	mmio_invalidate(npu_context, 1, address);
+	mmio_invalidate(npu_context, 1, address, true);
 }
 
 static void pnv_npu2_mn_invalidate_range(struct mmu_notifier *mn,
@@ -600,8 +630,11 @@ static void pnv_npu2_mn_invalidate_range(struct mmu_notifier *mn,
 	struct npu_context *npu_context = mn_to_npu_context(mn);
 	unsigned long address;
 
-	for (address = start; address <= end; address += PAGE_SIZE)
-		mmio_invalidate(npu_context, 1, address);
+	for (address = start; address < end; address += PAGE_SIZE)
+		mmio_invalidate(npu_context, 1, address, false);
+
+	/* Do the flush only on the final addess == end */
+	mmio_invalidate(npu_context, 1, address, true);
 }
 
 static const struct mmu_notifier_ops nv_nmmu_notifier_ops = {
@@ -651,8 +684,11 @@ struct npu_context *pnv_npu2_init_context(struct pci_dev *gpdev,
 		/* No nvlink associated with this GPU device */
 		return ERR_PTR(-ENODEV);
 
-	if (!mm) {
-		/* kernel thread contexts are not supported */
+	if (!mm || mm->context.id == 0) {
+		/*
+		 * Kernel thread contexts are not supported and context id 0 is
+		 * reserved on the GPU.
+		 */
 		return ERR_PTR(-EINVAL);
 	}