linux-kernel - [PATCH] loongson: Fix idle VS timer enqueue

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

Message-ID: <20250206162922.3028861-2-marco.crivellari@suse.com>
Date: Thu,  6 Feb 2025 17:29:22 +0100
From: Marco Crivellari <marco.crivellari@...e.com>
To: loongarch@...ts.linux.dev,
	linux-kernel@...r.kernel.org
Cc: bibo mao <maobibo@...ngson.cn>,
	Huacai Chen <chenhuacai@...nel.org>,
	WANG Xuerui <kernel@...0n.name>,
	Tiezhu Yang <yangtiezhu@...ngson.cn>,
	Frederic Weisbecker <frederic@...nel.org>,
	Marco Crivellari <marco.crivellari@...e.com>,
	Youling Tang <tangyouling@...ngson.cn>,
	Peter Zijlstra <peterz@...radead.org>,
	Jiaxun Yang <jiaxun.yang@...goat.com>
Subject: [PATCH] loongson: Fix idle VS timer enqueue

From: Peter Zijlstra <peterz@...radead.org>

Loongson re-enables interrupts on its idle routine and performs a
TIF_NEED_RESCHED check afterwards before putting the CPU to sleep.

The IRQs firing between the check and the idling instruction may set the
TIF_NEED_RESCHED flag. In order to deal with the such a race, IRQs
interrupting __arch_cpu_idle() rollback their return address to the
beginning of __arch_cpu_idle() so that TIF_NEED_RESCHED is checked
again before going back to sleep.

However idle IRQs can also queue timers that may require a tick
reprogramming through a new generic idle loop iteration but those timers
would go unnoticed here because __arch_cpu_idle() only checks
TIF_NEED_RESCHED. It doesn't check for pending timers.

Fix this with fast-forwarding idle IRQs return value to the end of the
idle routine instead of the beginning, so that the generic idle loop
handles both TIF_NEED_RESCHED and pending timers.

Fixes: 0603839b18f4 ("LoongArch: Add exception/interrupt handling")
Not-yet-signed-off-by: Peter Zijlstra <peterz@...radead.org>
Cc: WANG Xuerui <kernel@...0n.name>
Signed-off-by: Frederic Weisbecker <frederic@...nel.org>
Signed-off-by: Marco Crivellari <marco.crivellari@...e.com>
---
 arch/loongarch/kernel/genex.S | 33 +++++++++++++++++++--------------
 arch/loongarch/kernel/idle.c  |  3 +--
 arch/loongarch/kernel/reset.c | 23 ++++++++++++++---------
 3 files changed, 34 insertions(+), 25 deletions(-)

diff --git a/arch/loongarch/kernel/genex.S b/arch/loongarch/kernel/genex.S
index 86d5d90ebefe..ab2e9a262ee2 100644
--- a/arch/loongarch/kernel/genex.S
+++ b/arch/loongarch/kernel/genex.S
@@ -18,28 +18,33 @@
 
 	.align	5
 SYM_FUNC_START(__arch_cpu_idle)
-	/* start of rollback region */
-	LONG_L	t0, tp, TI_FLAGS
-	nop
-	andi	t0, t0, _TIF_NEED_RESCHED
-	bnez	t0, 1f
-	nop
-	nop
-	nop
+	/* start of idle interrupt region */
+	li.w	t0, CSR_CRMD_IE
+	/* idle instruction needs irq enabled */
+	csrxchg	t0, t0, LOONGARCH_CSR_CRMD
+	/*
+	 * If an interrupt lands here; between enabling interrupts above and
+	 * going idle on the next instruction, we must *NOT* go idle since the
+	 * interrupt could have set TIF_NEED_RESCHED or caused an timer to need
+	 * reprogramming. Fall through -- see handle_vint() below -- and have
+	 * the idle loop take care of things.
+	 */
 	idle	0
-	/* end of rollback region */
-1:	jr	ra
+	nop
+	/* end of idle interrupt region */
+SYM_INNER_LABEL(__arch_cpu_idle_exit, SYM_L_LOCAL)
+	jr	ra
 SYM_FUNC_END(__arch_cpu_idle)
 
 SYM_CODE_START(handle_vint)
 	UNWIND_HINT_UNDEFINED
 	BACKUP_T0T1
 	SAVE_ALL
-	la_abs	t1, __arch_cpu_idle
+	la_abs	t1, __arch_cpu_idle_exit
 	LONG_L	t0, sp, PT_ERA
-	/* 32 byte rollback region */
-	ori	t0, t0, 0x1f
-	xori	t0, t0, 0x1f
+	/* 16 byte idle interrupt region */
+	ori	t0, t0, 0x0f
+	addi.d	t0, t0, 1
 	bne	t0, t1, 1f
 	LONG_S	t0, sp, PT_ERA
 1:	move	a0, sp
diff --git a/arch/loongarch/kernel/idle.c b/arch/loongarch/kernel/idle.c
index 0b5dd2faeb90..54b247d8cdb6 100644
--- a/arch/loongarch/kernel/idle.c
+++ b/arch/loongarch/kernel/idle.c
@@ -11,7 +11,6 @@
 
 void __cpuidle arch_cpu_idle(void)
 {
-	raw_local_irq_enable();
-	__arch_cpu_idle(); /* idle instruction needs irq enabled */
+	__arch_cpu_idle();
 	raw_local_irq_disable();
 }
diff --git a/arch/loongarch/kernel/reset.c b/arch/loongarch/kernel/reset.c
index 1ef8c6383535..d78e8a1064a1 100644
--- a/arch/loongarch/kernel/reset.c
+++ b/arch/loongarch/kernel/reset.c
@@ -20,6 +20,11 @@
 void (*pm_power_off)(void);
 EXPORT_SYMBOL(pm_power_off);
 
+static __always_inline void native_halt(void)
+{
+	asm volatile("idle 0" : : : "memory");
+}
+
 void machine_halt(void)
 {
 #ifdef CONFIG_SMP
@@ -32,9 +37,9 @@ void machine_halt(void)
 	pr_notice("\n\n** You can safely turn off the power now **\n\n");
 	console_flush_on_panic(CONSOLE_FLUSH_PENDING);
 
-	while (true) {
-		__arch_cpu_idle();
-	}
+	while (1) {
+		native_halt();
+	};
 }
 
 void machine_power_off(void)
@@ -52,9 +57,9 @@ void machine_power_off(void)
 	efi.reset_system(EFI_RESET_SHUTDOWN, EFI_SUCCESS, 0, NULL);
 #endif
 
-	while (true) {
-		__arch_cpu_idle();
-	}
+	while (1) {
+		native_halt();
+	};
 }
 
 void machine_restart(char *command)
@@ -73,7 +78,7 @@ void machine_restart(char *command)
 	if (!acpi_disabled)
 		acpi_reboot();
 
-	while (true) {
-		__arch_cpu_idle();
-	}
+	while (1) {
+		native_halt();
+	};
 }
-- 
2.48.1