arm64: Fix incorrect irqflag restore for priority masking

When using IRQ priority masking to disable interrupts, in order to deal
with the PSR.I state, local_irq_save() would convert the I bit into a
PMR value (GIC_PRIO_IRQOFF). This resulted in local_irq_restore()
potentially modifying the value of PMR in undesired location due to the
state of PSR.I upon flag saving [1].

In an attempt to solve this issue in a less hackish manner, introduce
a bit (GIC_PRIO_IGNORE_PMR) for the PMR values that can represent
whether PSR.I is being used to disable interrupts, in which case it
takes precedence of the status of interrupt masking via PMR.

GIC_PRIO_PSR_I_SET is chosen such that (<pmr_value> |
GIC_PRIO_PSR_I_SET) does not mask more interrupts than <pmr_value> as
some sections (e.g. arch_cpu_idle(), interrupt acknowledge path)
requires PMR not to mask interrupts that could be signaled to the
CPU when using only PSR.I.

[1] https://www.spinics.net/lists/arm-kernel/msg716956.html

Fixes: 4a503217ce37 ("arm64: irqflags: Use ICC_PMR_EL1 for interrupt masking")
Cc: <stable@vger.kernel.org> # 5.1.x-
Reported-by: Zenghui Yu <yuzenghui@huawei.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Wei Li <liwei391@huawei.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Christoffer Dall <christoffer.dall@arm.com>
Cc: James Morse <james.morse@arm.com>
Cc: Suzuki K Pouloze <suzuki.poulose@arm.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Reviewed-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Julien Thierry <julien.thierry@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>

3 files changed, 39 insertions, 9 deletions

diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 6d5966346710..165da78815c5 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -258,6 +258,7 @@ alternative_else_nop_endif
 	/*
 	 * Registers that may be useful after this macro is invoked:
 	 *
+	 * x20 - ICC_PMR_EL1
 	 * x21 - aborted SP
 	 * x22 - aborted PC
 	 * x23 - aborted PSTATE
@@ -449,6 +450,24 @@ alternative_endif
 	.endm
 #endif
 
+	.macro	gic_prio_kentry_setup, tmp:req
+#ifdef CONFIG_ARM64_PSEUDO_NMI
+	alternative_if ARM64_HAS_IRQ_PRIO_MASKING
+	mov	\tmp, #(GIC_PRIO_PSR_I_SET | GIC_PRIO_IRQON)
+	msr_s	SYS_ICC_PMR_EL1, \tmp
+	alternative_else_nop_endif
+#endif
+	.endm
+
+	.macro	gic_prio_irq_setup, pmr:req, tmp:req
+#ifdef CONFIG_ARM64_PSEUDO_NMI
+	alternative_if ARM64_HAS_IRQ_PRIO_MASKING
+	orr	\tmp, \pmr, #GIC_PRIO_PSR_I_SET
+	msr_s	SYS_ICC_PMR_EL1, \tmp
+	alternative_else_nop_endif
+#endif
+	.endm
+
 	.text
 
 /*
@@ -627,6 +646,7 @@ el1_dbg:
 	cmp	x24, #ESR_ELx_EC_BRK64		// if BRK64
 	cinc	x24, x24, eq			// set bit '0'
 	tbz	x24, #0, el1_inv		// EL1 only
+	gic_prio_kentry_setup tmp=x3
 	mrs	x0, far_el1
 	mov	x2, sp				// struct pt_regs
 	bl	do_debug_exception
@@ -644,12 +664,10 @@ ENDPROC(el1_sync)
 	.align	6
 el1_irq:
 	kernel_entry 1
+	gic_prio_irq_setup pmr=x20, tmp=x1
 	enable_da_f
 
 #ifdef CONFIG_ARM64_PSEUDO_NMI
-alternative_if ARM64_HAS_IRQ_PRIO_MASKING
-	ldr	x20, [sp, #S_PMR_SAVE]
-alternative_else_nop_endif
 	test_irqs_unmasked	res=x0, pmr=x20
 	cbz	x0, 1f
 	bl	asm_nmi_enter
@@ -679,8 +697,9 @@ alternative_else_nop_endif
 
 #ifdef CONFIG_ARM64_PSEUDO_NMI
 	/*
-	 * if IRQs were disabled when we received the interrupt, we have an NMI
-	 * and we are not re-enabling interrupt upon eret. Skip tracing.
+	 * When using IRQ priority masking, we can get spurious interrupts while
+	 * PMR is set to GIC_PRIO_IRQOFF. An NMI might also have occurred in a
+	 * section with interrupts disabled. Skip tracing in those cases.
 	 */
 	test_irqs_unmasked	res=x0, pmr=x20
 	cbz	x0, 1f
@@ -809,6 +828,7 @@ el0_ia:
 	 * Instruction abort handling
 	 */
 	mrs	x26, far_el1
+	gic_prio_kentry_setup tmp=x0
 	enable_da_f
 #ifdef CONFIG_TRACE_IRQFLAGS
 	bl	trace_hardirqs_off
@@ -854,6 +874,7 @@ el0_sp_pc:
 	 * Stack or PC alignment exception handling
 	 */
 	mrs	x26, far_el1
+	gic_prio_kentry_setup tmp=x0
 	enable_da_f
 #ifdef CONFIG_TRACE_IRQFLAGS
 	bl	trace_hardirqs_off
@@ -888,6 +909,7 @@ el0_dbg:
 	 * Debug exception handling
 	 */
 	tbnz	x24, #0, el0_inv		// EL0 only
+	gic_prio_kentry_setup tmp=x3
 	mrs	x0, far_el1
 	mov	x1, x25
 	mov	x2, sp
@@ -909,7 +931,9 @@ ENDPROC(el0_sync)
 el0_irq:
 	kernel_entry 0
 el0_irq_naked:
+	gic_prio_irq_setup pmr=x20, tmp=x0
 	enable_da_f
+
 #ifdef CONFIG_TRACE_IRQFLAGS
 	bl	trace_hardirqs_off
 #endif
@@ -931,6 +955,7 @@ ENDPROC(el0_irq)
 el1_error:
 	kernel_entry 1
 	mrs	x1, esr_el1
+	gic_prio_kentry_setup tmp=x2
 	enable_dbg
 	mov	x0, sp
 	bl	do_serror
@@ -941,6 +966,7 @@ el0_error:
 	kernel_entry 0
 el0_error_naked:
 	mrs	x1, esr_el1
+	gic_prio_kentry_setup tmp=x2
 	enable_dbg
 	mov	x0, sp
 	bl	do_serror
@@ -965,6 +991,7 @@ work_pending:
  */
 ret_to_user:
 	disable_daif
+	gic_prio_kentry_setup tmp=x3
 	ldr	x1, [tsk, #TSK_TI_FLAGS]
 	and	x2, x1, #_TIF_WORK_MASK
 	cbnz	x2, work_pending
@@ -981,6 +1008,7 @@ ENDPROC(ret_to_user)
  */
 	.align	6
 el0_svc:
+	gic_prio_kentry_setup tmp=x1
 	mov	x0, sp
 	bl	el0_svc_handler
 	b	ret_to_user
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 3767fb21a5b8..58efc3727778 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -94,7 +94,7 @@ static void __cpu_do_idle_irqprio(void)
 	 * be raised.
 	 */
 	pmr = gic_read_pmr();
-	gic_write_pmr(GIC_PRIO_IRQON);
+	gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET);
 
 	__cpu_do_idle();
 
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index bb4b3f07761a..4deaee3c2a33 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -192,11 +192,13 @@ static void init_gic_priority_masking(void)
 
 	WARN_ON(!(cpuflags & PSR_I_BIT));
 
-	gic_write_pmr(GIC_PRIO_IRQOFF);
-
 	/* We can only unmask PSR.I if we can take aborts */
-	if (!(cpuflags & PSR_A_BIT))
+	if (!(cpuflags & PSR_A_BIT)) {
+		gic_write_pmr(GIC_PRIO_IRQOFF);
 		write_sysreg(cpuflags & ~PSR_I_BIT, daif);
+	} else {
+		gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET);
+	}
 }
 
 /*