[RFC PATCH 02/12] lockdep: Use raw access for pinned hardirq state

[Karl Mehltretter <kmehltretter@gmail.com>]

irqentry_nmi_enter() reads lockdep's hardirq state before __nmi_enter()
establishes NMI context. Arm64 does the same for its NMI-like EL1 debug
entry. Both paths run with interrupts disabled and cannot migrate.

lockdep_hardirqs_enabled() uses this_cpu_read(), whose preemption checks
are unnecessary for these callers. Add a raw accessor and use it in the
two entry paths and in lockdep_hardirqs_off(). Keep the existing accessor
for callers which are not already pinned.

Check the interrupt state before accessing per-CPU state in
lockdep_hardirqs_off(), independently of warning suppression.

On arm64, this change does not by itself make the call chain noinstr-safe:
__kern_my_cpu_offset() must also be forced inline. That prerequisite is
listed in the cover letter.

Assisted-by: LLM
---
 arch/arm64/kernel/entry-common.c | 2 +-
 include/linux/irqflags.h         | 3 +++
 kernel/entry/common.c            | 2 +-
 kernel/locking/lockdep.c         | 6 ++++--
 4 files changed, 9 insertions(+), 4 deletions(-)

diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c
index 72c03ccea59fe..93056a766fb20 100644
--- a/arch/arm64/kernel/entry-common.c
+++ b/arch/arm64/kernel/entry-common.c
@@ -141,7 +141,7 @@ static noinstr irqentry_state_t arm64_enter_el1_dbg(struct pt_regs *regs)
 {
 	irqentry_state_t state;
 
-	state.lockdep = lockdep_hardirqs_enabled();
+	state.lockdep = lockdep_hardirqs_enabled_raw();
 
 	lockdep_hardirqs_off(CALLER_ADDR0);
 	ct_nmi_enter();
diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h
index 57b074e0cfbbb..5bc179a88e513 100644
--- a/include/linux/irqflags.h
+++ b/include/linux/irqflags.h
@@ -52,6 +52,8 @@ extern void trace_hardirqs_off(void);
 # define lockdep_hardirq_context()	(raw_cpu_read(hardirq_context))
 # define lockdep_softirq_context(p)	((p)->softirq_context)
 # define lockdep_hardirqs_enabled()	(this_cpu_read(hardirqs_enabled))
+/* The caller must already be pinned to the current CPU. */
+# define lockdep_hardirqs_enabled_raw()	(raw_cpu_read(hardirqs_enabled))
 # define lockdep_softirqs_enabled(p)	((p)->softirqs_enabled)
 # define lockdep_hardirq_enter()			\
 do {							\
@@ -113,6 +115,7 @@ do {						\
 # define lockdep_hardirq_context()		0
 # define lockdep_softirq_context(p)		0
 # define lockdep_hardirqs_enabled()		0
+# define lockdep_hardirqs_enabled_raw()		0
 # define lockdep_softirqs_enabled(p)		0
 # define lockdep_hardirq_enter()		do { } while (0)
 # define lockdep_hardirq_threaded()		do { } while (0)
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index e3d381fd3d251..28399c41ebfb1 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -171,7 +171,7 @@ irqentry_state_t noinstr irqentry_nmi_enter(struct pt_regs *regs)
 {
 	irqentry_state_t irq_state;
 
-	irq_state.lockdep = lockdep_hardirqs_enabled();
+	irq_state.lockdep = lockdep_hardirqs_enabled_raw();
 
 	__nmi_enter();
 	lockdep_hardirqs_off(CALLER_ADDR0);
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index c3dc84a7cef26..01dba8fb32a90 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -4543,10 +4543,12 @@ void noinstr lockdep_hardirqs_off(unsigned long ip)
 	 * So we're supposed to get called after you mask local IRQs, but for
 	 * some reason the hardware doesn't quite think you did a proper job.
 	 */
-	if (DEBUG_LOCKS_WARN_ON(!irqs_disabled()))
+	if (unlikely(!irqs_disabled())) {
+		DEBUG_LOCKS_WARN_ON(1);
 		return;
+	}
 
-	if (lockdep_hardirqs_enabled()) {
+	if (lockdep_hardirqs_enabled_raw()) {
 		struct irqtrace_events *trace = &current->irqtrace;
 
 		/*
-- 
2.39.5 (Apple Git-154)