arm64: entry: always set GIC_PRIO_PSR_I_SET during entry

Zenghui reports that booting a kernel with "irqchip.gicv3_pseudo_nmi=1"
on the command line hits a warning during kernel entry, due to the way
we manipulate the PMR.

Early in the entry sequence, we call lockdep_hardirqs_off() to inform
lockdep that interrupts have been masked (as the HW sets DAIF wqhen
entering an exception). Architecturally PMR_EL1 is not affected by
exception entry, and we don't set GIC_PRIO_PSR_I_SET in the PMR early in
the exception entry sequence, so early in exception entry the PMR can
indicate that interrupts are unmasked even though they are masked by
DAIF.

If DEBUG_LOCKDEP is selected, lockdep_hardirqs_off() will check that
interrupts are masked, before we set GIC_PRIO_PSR_I_SET in any of the
exception entry paths, and hence lockdep_hardirqs_off() will WARN() that
something is amiss.

We can avoid this by consistently setting GIC_PRIO_PSR_I_SET during
exception entry so that kernel code sees a consistent environment. We
must also update local_daif_inherit() to undo this, as currently only
touches DAIF. For other paths, local_daif_restore() will update both
DAIF and the PMR. With this done, we can remove the existing special
cases which set this later in the entry code.

We always use (GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET) for consistency with
local_daif_save(), as this will warn if it ever encounters
(GIC_PRIO_IRQOFF | GIC_PRIO_PSR_I_SET), and never sets this itself. This
matches the gic_prio_kentry_setup that we have to retain for
ret_to_user.

The original splat from Zenghui's report was:

| DEBUG_LOCKS_WARN_ON(!irqs_disabled())
| WARNING: CPU: 3 PID: 125 at kernel/locking/lockdep.c:4258 lockdep_hardirqs_off+0xd4/0xe8
| Modules linked in:
| CPU: 3 PID: 125 Comm: modprobe Tainted: G        W         5.12.0-rc8+ #463
| Hardware name: QEMU KVM Virtual Machine, BIOS 0.0.0 02/06/2015
| pstate: 604003c5 (nZCv DAIF +PAN -UAO -TCO BTYPE=--)
| pc : lockdep_hardirqs_off+0xd4/0xe8
| lr : lockdep_hardirqs_off+0xd4/0xe8
| sp : ffff80002a39bad0
| pmr_save: 000000e0
| x29: ffff80002a39bad0 x28: ffff0000de214bc0
| x27: ffff0000de1c0400 x26: 000000000049b328
| x25: 0000000000406f30 x24: ffff0000de1c00a0
| x23: 0000000020400005 x22: ffff8000105f747c
| x21: 0000000096000044 x20: 0000000000498ef9
| x19: ffff80002a39bc88 x18: ffffffffffffffff
| x17: 0000000000000000 x16: ffff800011c61eb0
| x15: ffff800011700a88 x14: 0720072007200720
| x13: 0720072007200720 x12: 0720072007200720
| x11: 0720072007200720 x10: 0720072007200720
| x9 : ffff80002a39bad0 x8 : ffff80002a39bad0
| x7 : ffff8000119f0800 x6 : c0000000ffff7fff
| x5 : ffff8000119f07a8 x4 : 0000000000000001
| x3 : 9bcdab23f2432800 x2 : ffff800011730538
| x1 : 9bcdab23f2432800 x0 : 0000000000000000
| Call trace:
|  lockdep_hardirqs_off+0xd4/0xe8
|  enter_from_kernel_mode.isra.5+0x7c/0xa8
|  el1_abort+0x24/0x100
|  el1_sync_handler+0x80/0xd0
|  el1_sync+0x6c/0x100
|  __arch_clear_user+0xc/0x90
|  load_elf_binary+0x9fc/0x1450
|  bprm_execve+0x404/0x880
|  kernel_execve+0x180/0x188
|  call_usermodehelper_exec_async+0xdc/0x158
|  ret_from_fork+0x10/0x18

Fixes: 23529049c684 ("arm64: entry: fix non-NMI user<->kernel transitions")
Fixes: 7cd1ea1010ac ("arm64: entry: fix non-NMI kernel<->kernel transitions")
Fixes: f0cd5ac1e4c5 ("arm64: entry: fix NMI {user, kernel}->kernel transitions")
Fixes: 2a9b3e6ac69a ("arm64: entry: fix EL1 debug transitions")
Link: https://lore.kernel.org/r/f4012761-026f-4e51-3a0c-7524e434e8b3@huawei.com
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Reported-by: Zenghui Yu <yuzenghui@huawei.com>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Will Deacon <will@kernel.org>
Acked-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20210428111555.50880-1-mark.rutland@arm.com
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>

1 files changed, 0 insertions, 17 deletions

diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c
index a1ec351c36bd..340d04e13617 100644
--- a/arch/arm64/kernel/entry-common.c
+++ b/arch/arm64/kernel/entry-common.c
@@ -230,14 +230,6 @@ static void noinstr el1_dbg(struct pt_regs *regs, unsigned long esr)
 {
 	unsigned long far = read_sysreg(far_el1);
 
-	/*
-	 * The CPU masked interrupts, and we are leaving them masked during
-	 * do_debug_exception(). Update PMR as if we had called
-	 * local_daif_mask().
-	 */
-	if (system_uses_irq_prio_masking())
-		gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET);
-
 	arm64_enter_el1_dbg(regs);
 	if (!cortex_a76_erratum_1463225_debug_handler(regs))
 		do_debug_exception(far, esr, regs);
@@ -404,9 +396,6 @@ static void noinstr el0_dbg(struct pt_regs *regs, unsigned long esr)
 	/* Only watchpoints write FAR_EL1, otherwise its UNKNOWN */
 	unsigned long far = read_sysreg(far_el1);
 
-	if (system_uses_irq_prio_masking())
-		gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET);
-
 	enter_from_user_mode();
 	do_debug_exception(far, esr, regs);
 	local_daif_restore(DAIF_PROCCTX_NOIRQ);
@@ -414,9 +403,6 @@ static void noinstr el0_dbg(struct pt_regs *regs, unsigned long esr)
 
 static void noinstr el0_svc(struct pt_regs *regs)
 {
-	if (system_uses_irq_prio_masking())
-		gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET);
-
 	enter_from_user_mode();
 	cortex_a76_erratum_1463225_svc_handler();
 	do_el0_svc(regs);
@@ -492,9 +478,6 @@ static void noinstr el0_cp15(struct pt_regs *regs, unsigned long esr)
 
 static void noinstr el0_svc_compat(struct pt_regs *regs)
 {
-	if (system_uses_irq_prio_masking())
-		gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET);
-
 	enter_from_user_mode();
 	cortex_a76_erratum_1463225_svc_handler();
 	do_el0_svc_compat(regs);