7 files changed, 60 insertions, 10 deletions

diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index 930e36099015..2f68fb2ee4fc 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -813,6 +813,13 @@ kernel_dbg_exc:
 	EXCEPTION_COMMON(0x260)
 	CHECK_NAPPING()
 	addi	r3,r1,STACK_FRAME_OVERHEAD
+	/*
+	 * XXX: Returning from performance_monitor_exception taken as a
+	 * soft-NMI (Linux irqs disabled) may be risky to use interrupt_return
+	 * and could cause bugs in return or elsewhere. That case should just
+	 * restore registers and return. There is a workaround for one known
+	 * problem in interrupt_exit_kernel_prepare().
+	 */
 	bl	performance_monitor_exception
 	b	interrupt_return
 
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 5381a43e50fe..651c36b056bd 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -2357,9 +2357,21 @@ EXC_VIRT_END(performance_monitor, 0x4f00, 0x20)
 EXC_COMMON_BEGIN(performance_monitor_common)
 	GEN_COMMON performance_monitor
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	performance_monitor_exception
+	lbz	r4,PACAIRQSOFTMASK(r13)
+	cmpdi	r4,IRQS_ENABLED
+	bne	1f
+	bl	performance_monitor_exception_async
 	b	interrupt_return_srr
+1:
+	bl	performance_monitor_exception_nmi
+	/* Clear MSR_RI before setting SRR0 and SRR1. */
+	li	r9,0
+	mtmsrd	r9,1
 
+	kuap_kernel_restore r9, r10
+
+	EXCEPTION_RESTORE_REGS hsrr=0
+	RFI_TO_KERNEL
 
 /**
  * Interrupt 0xf20 - Vector Unavailable Interrupt.
diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c
index f9db0a172401..fc6631a80527 100644
--- a/arch/powerpc/kernel/interrupt.c
+++ b/arch/powerpc/kernel/interrupt.c
@@ -374,10 +374,18 @@ notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs)
 	if (regs_is_unrecoverable(regs))
 		unrecoverable_exception(regs);
 	/*
-	 * CT_WARN_ON comes here via program_check_exception,
-	 * so avoid recursion.
+	 * CT_WARN_ON comes here via program_check_exception, so avoid
+	 * recursion.
+	 *
+	 * Skip the assertion on PMIs on 64e to work around a problem caused
+	 * by NMI PMIs incorrectly taking this interrupt return path, it's
+	 * possible for this to hit after interrupt exit to user switches
+	 * context to user. See also the comment in the performance monitor
+	 * handler in exceptions-64e.S
 	 */
-	if (TRAP(regs) != INTERRUPT_PROGRAM)
+	if (!IS_ENABLED(CONFIG_PPC_BOOK3E_64) &&
+	    TRAP(regs) != INTERRUPT_PROGRAM &&
+	    TRAP(regs) != INTERRUPT_PERFMON)
 		CT_WARN_ON(ct_state() == CONTEXT_USER);
 
 	kuap = kuap_get_and_assert_locked();
diff --git a/arch/powerpc/kernel/interrupt_64.S b/arch/powerpc/kernel/interrupt_64.S
index 978a173eb339..a019ed6fc839 100644
--- a/arch/powerpc/kernel/interrupt_64.S
+++ b/arch/powerpc/kernel/interrupt_64.S
@@ -532,15 +532,24 @@ _ASM_NOKPROBE_SYMBOL(interrupt_return_\srr\()_kernel)
 	 * Returning to soft-disabled context.
 	 * Check if a MUST_HARD_MASK interrupt has become pending, in which
 	 * case we need to disable MSR[EE] in the return context.
+	 *
+	 * The MSR[EE] check catches among other things the short incoherency
+	 * in hard_irq_disable() between clearing MSR[EE] and setting
+	 * PACA_IRQ_HARD_DIS.
 	 */
 	ld	r12,_MSR(r1)
 	andi.	r10,r12,MSR_EE
 	beq	.Lfast_kernel_interrupt_return_\srr\() // EE already disabled
 	lbz	r11,PACAIRQHAPPENED(r13)
 	andi.	r10,r11,PACA_IRQ_MUST_HARD_MASK
-	beq	.Lfast_kernel_interrupt_return_\srr\() // No HARD_MASK pending
+	bne	1f // HARD_MASK is pending
+	// No HARD_MASK pending, clear possible HARD_DIS set by interrupt
+	andi.	r11,r11,(~PACA_IRQ_HARD_DIS)@l
+	stb	r11,PACAIRQHAPPENED(r13)
+	b	.Lfast_kernel_interrupt_return_\srr\()
+
 
-	/* Must clear MSR_EE from _MSR */
+1:	/* Must clear MSR_EE from _MSR */
 #ifdef CONFIG_PPC_BOOK3S
 	li	r10,0
 	/* Clear valid before changing _MSR */
diff --git a/arch/powerpc/kernel/sys_ppc32.c b/arch/powerpc/kernel/sys_ppc32.c
index 1ab4a4d95aba..d451a8229223 100644
--- a/arch/powerpc/kernel/sys_ppc32.c
+++ b/arch/powerpc/kernel/sys_ppc32.c
@@ -112,7 +112,7 @@ PPC32_SYSCALL_DEFINE6(ppc32_fadvise64,
 				 advice);
 }
 
-COMPAT_SYSCALL_DEFINE6(ppc_sync_file_range2,
+PPC32_SYSCALL_DEFINE6(ppc_sync_file_range2,
 		       int, fd, unsigned int, flags,
 		       unsigned int, offset1, unsigned int, offset2,
 		       unsigned int, nbytes1, unsigned int, nbytes2)
@@ -122,3 +122,14 @@ COMPAT_SYSCALL_DEFINE6(ppc_sync_file_range2,
 
 	return ksys_sync_file_range(fd, offset, nbytes, flags);
 }
+
+#ifdef CONFIG_PPC32
+SYSCALL_DEFINE6(ppc_fallocate,
+		int, fd, int, mode,
+		u32, offset1, u32, offset2, u32, len1, u32, len2)
+{
+	return ksys_fallocate(fd, mode,
+			      merge_64(offset1, offset2),
+			      merge_64(len1, len2));
+}
+#endif
diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl
index e9e0df4f9a61..a0be127475b1 100644
--- a/arch/powerpc/kernel/syscalls/syscall.tbl
+++ b/arch/powerpc/kernel/syscalls/syscall.tbl
@@ -394,8 +394,11 @@
 305	common	signalfd			sys_signalfd			compat_sys_signalfd
 306	common	timerfd_create			sys_timerfd_create
 307	common	eventfd				sys_eventfd
-308	common	sync_file_range2		sys_sync_file_range2		compat_sys_ppc_sync_file_range2
-309	nospu	fallocate			sys_fallocate			compat_sys_fallocate
+308	32	sync_file_range2		sys_ppc_sync_file_range2	compat_sys_ppc_sync_file_range2
+308	64	sync_file_range2		sys_sync_file_range2
+308	spu	sync_file_range2		sys_sync_file_range2
+309	32	fallocate			sys_ppc_fallocate		compat_sys_fallocate
+309	64	fallocate			sys_fallocate
 310	nospu	subpage_prot			sys_subpage_prot
 311	32	timerfd_settime			sys_timerfd_settime32
 311	64	timerfd_settime			sys_timerfd_settime
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index 7786e3ac7611..8c3862b4c259 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -142,7 +142,7 @@ SECTIONS
 #endif
 
 	.data.rel.ro : AT(ADDR(.data.rel.ro) - LOAD_OFFSET) {
-		*(.data.rel.ro*)
+		*(.data.rel.ro .data.rel.ro.*)
 	}
 
 	.branch_lt : AT(ADDR(.branch_lt) - LOAD_OFFSET) {