linux-kernel - Re: Unfair qspinlocks on ARM64 without LSE atomics => 3ms delay in interrupt handling

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [thread-next>] [day] [month] [year] [list]

Message-ID: <AS1PR10MB567534190B05A4493674173BEB659@AS1PR10MB5675.EURPRD10.PROD.OUTLOOK.COM>
Date:   Wed, 26 Apr 2023 12:03:58 +0000
From:   "Bouska, Zdenek" <zdenek.bouska@...mens.com>
To:     Will Deacon <will@...nel.org>,
        Catalin Marinas <catalin.marinas@....com>
CC:     Thomas Gleixner <tglx@...utronix.de>,
        "linux-arm-kernel@...ts.infradead.org" 
        <linux-arm-kernel@...ts.infradead.org>,
        "linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
        "Kiszka, Jan" <jan.kiszka@...mens.com>,
        "linux-rt-users@...r.kernel.org" <linux-rt-users@...r.kernel.org>,
        Nishanth Menon <nm@...com>, Puranjay Mohan <p-mohan@...com>
Subject: Re: Unfair qspinlocks on ARM64 without LSE atomics => 3ms delay in
 interrupt handling

Hello,

following patch is my current approach for fixing this issue. I introduced
big_cpu_relax(), which uses Will's implementation [1] on ARM64 without
LSE atomics and original cpu_relax() on any other CPU.

Anyone has a better idea how to solve this issue properly?

[1] https://lore.kernel.org/lkml/20170728092831.GA24839@arm.com/

Zdenek Bouska

--
Siemens, s.r.o
Siemens Advanta Development

diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 3918f2a67970..f3861ab9f541 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -367,6 +367,23 @@ static inline void spin_lock_prefetch(const void *ptr)
 		     "nop") : : "p" (ptr));
 }
 
+void armv8_big_cpu_relax(unsigned long pc);
+
+static inline void _big_cpu_relax(void)
+{
+	armv8_big_cpu_relax(_THIS_IP_);
+}
+
+#define ARCH_HAS_BIG_CPU_RELAX
+static inline void big_cpu_relax(void)
+{
+	if (system_uses_lse_atomics()) {
+		cpu_relax();
+	} else {
+		_big_cpu_relax();
+	}
+}
+
 extern unsigned long __ro_after_init signal_minsigstksz; /* sigframe size */
 extern void __init minsigstksz_setup(void);
 
diff --git a/arch/arm64/lib/delay.c b/arch/arm64/lib/delay.c
index 5b7890139bc2..3f4fd24bd4b2 100644
--- a/arch/arm64/lib/delay.c
+++ b/arch/arm64/lib/delay.c
@@ -67,3 +67,29 @@ void __ndelay(unsigned long nsecs)
 	__const_udelay(nsecs * 0x5UL); /* 2**32 / 1000000000 (rounded up) */
 }
 EXPORT_SYMBOL(__ndelay);
+
+static DEFINE_PER_CPU(u64, __cpu_relax_data);
+
+#define CPU_RELAX_WFE_THRESHOLD	10000
+void armv8_big_cpu_relax(unsigned long pc)
+{
+	u64 new, old = raw_cpu_read(__cpu_relax_data);
+	u32 old_pc, new_pc;
+	bool wfe = false;
+
+	old_pc = (u32)old;
+	new = new_pc = (u32)pc;
+
+	if (old_pc == new_pc) {
+		if ((old >> 32) > CPU_RELAX_WFE_THRESHOLD) {
+			asm volatile("sevl; wfe; wfe\n" ::: "memory");
+			wfe = true;
+		} else {
+			new = old + (1UL << 32);
+		}
+	}
+
+	if (this_cpu_cmpxchg(__cpu_relax_data, old, new) == old && !wfe)
+		asm volatile("yield" ::: "memory");
+}
+EXPORT_SYMBOL(armv8_big_cpu_relax);
diff --git a/include/linux/processor.h b/include/linux/processor.h
index dc78bdc7079a..3dc5e3fcb400 100644
--- a/include/linux/processor.h
+++ b/include/linux/processor.h
@@ -59,4 +59,8 @@ do {								\
 
 #endif
 
+#ifndef ARCH_HAS_BIG_CPU_RELAX
+#define big_cpu_relax() cpu_relax()
+#endif
+
 #endif /* _LINUX_PROCESSOR_H */
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 8ce75495e04f..cc8445de1006 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -21,6 +21,7 @@
 #include <linux/sched/isolation.h>
 #include <uapi/linux/sched/types.h>
 #include <linux/task_work.h>
+#include <linux/processor.h>
 
 #include "internals.h"
 
@@ -1101,7 +1102,7 @@ static void irq_finalize_oneshot(struct irq_desc *desc,
 	if (unlikely(irqd_irq_inprogress(&desc->irq_data))) {
 		raw_spin_unlock_irq(&desc->lock);
 		chip_bus_sync_unlock(desc);
-		cpu_relax();
+		big_cpu_relax();
 		goto again;
 	}