[PATCH v2 2/2] irqchip/riscv-aplic: Register syscore operations only once

[liu.xuemei1 at zte.com.cn]

From: Jessica Liu <liu.xuemei1 at zte.com.cn>

Since commit 95a8ddde3660 ("irqchip/riscv-aplic: Preserve APLIC
states across suspend/resume"), when multiple NUMA nodes exist
and AIA is not configured as "none", aplic_probe() is called
multiple times. This leads to register_syscore(&aplic_syscore)
being invoked repeatedly, causing the following Oops:

[    1.188071] list_add double add: new=ffffffffb91461f0, prev=ffffffffb91461f0, next=ffffffffb915c408.
[    1.189839] ------------[ cut here ]------------
[    1.190080] kernel BUG at lib/list_debug.c:35!
[    1.190403] Kernel BUG [#1]
[    1.190438] Modules linked in:
[    1.191173] CPU: 1 UID: 0 PID: 1 Comm: swapper/0 Not tainted 7.0.0-rc2+ #1 PREEMPT(full)
[    1.191363] Hardware name: QEMU QEMU Virtual Machine, BIOS edk2-202402-20.an23 02/14/2024
[    1.191495] epc : __list_add_valid_or_report+0x60/0xc0
[    1.192103]  ra : __list_add_valid_or_report+0x60/0xc0
[    1.192143] epc : ffffffffb7b5c8ca ra : ffffffffb7b5c8ca sp : ffffffc600103ad0
[    1.192166]  gp : ffffffffb91feb60 tp : ffffffd680a1eac0 t0 : 2000000000000000
[    1.192188]  t1 : 000000000000006c t2 : 206464615f747369 s0 : ffffffc600103b00
[    1.192209]  s1 : ffffffffb915c408 a0 : 0000000000000058 a1 : ffffffe23ef7b0c0
[    1.192229]  a2 : 0000000000000010 a3 : 0000000000000000 a4 : 0000000000000000
[    1.192249]  a5 : 0000000000000000 a6 : c0000000ffffdfff a7 : ffffffffb93da948
[    1.192271]  s2 : ffffffffb91461f0 s3 : ffffffffb91461f0 s4 : ffffffffb915c408
[    1.192292]  s5 : ffffffd681254890 s6 : ffffffffb8c40410 s7 : ffffffffb84361c8
[    1.192313]  s8 : 0000000000000000 s9 : 0000000000000000 s10: 0000000000000000
[    1.192333]  s11: 0000000000000000 t3 : ffffffffb93da9e7 t4 : ffffffffb93da9e7
[    1.192352]  t5 : ffffffffb93da9e8 t6 : ffffffc6001038d8 ssp : 0000000000000000
[    1.192373] status: 0000000200000120 badaddr: ffffffffb7b5c8ca cause: 0000000000000003
[    1.192508] [<ffffffffb7b5c8ca>] __list_add_valid_or_report+0x60/0xc0
[    1.192606] [<ffffffffb7cc3236>] register_syscore+0x3e/0x70
[    1.192630] [<ffffffffb7b8d61c>] aplic_probe+0xc6/0x112
[    1.192649] [<ffffffffb7cc5014>] platform_probe+0x46/0x76
[    1.192669] [<ffffffffb7cc19c6>] call_driver_probe+0x1a/0x108
[    1.192687] [<ffffffffb7cc23e2>] really_probe+0x82/0x288
[    1.192707] [<ffffffffb7cc2654>] __driver_probe_device+0x6c/0x11e
[    1.192727] [<ffffffffb7cc27c8>] driver_probe_device+0x2c/0xa0
[    1.192746] [<ffffffffb7cc2a08>] __driver_attach+0xce/0x1ee
[    1.192763] [<ffffffffb7cc00e6>] bus_for_each_dev+0x5a/0xa6
[    1.192781] [<ffffffffb7cc1cf4>] driver_attach+0x1a/0x22
[    1.192798] [<ffffffffb7cc148a>] bus_add_driver+0x10e/0x1fc
[    1.192817] [<ffffffffb7cc3ab2>] driver_register+0x3e/0xd8
[    1.192837] [<ffffffffb7cc4c7c>] __platform_driver_register+0x1c/0x24
[    1.192887] [<ffffffffb8236e4c>] aplic_driver_init+0x1a/0x22
[    1.192909] [<ffffffffb76179a6>] do_one_initcall+0x36/0x2b4
[    1.192935] [<ffffffffb82013b2>] do_initcalls+0xfe/0x12c
[    1.192958] [<ffffffffb82015a4>] kernel_init_freeable+0x15c/0x1c8
[    1.192979] [<ffffffffb80894ea>] kernel_init+0x20/0x152
[    1.193001] [<ffffffffb76194c6>] ret_from_fork_kernel+0x12/0x1f6
[    1.193020] [<ffffffffb80943e6>] ret_from_fork_kernel_asm+0x16/0x18
[    1.193190] Code: 86a6 85aa 4517 00fc 0513 7765 8097 ffaa 80e7 9940 (9002) 854a
[    1.193665] ---[ end trace 0000000000000000 ]---
[    1.194254] Kernel panic - not syncing: Fatal exception in interrupt
[    1.194627] SMP: stopping secondary CPUs
[    1.195436] Kernel Offset: 0x37600000 from 0xffffffff80000000

Fix by registering syscore operations only once, using a static
variable aplic_syscore_registered to track registration.

Fixes: 95a8ddde3660 ("irqchip/riscv-aplic: Preserve APLIC states across suspend/resume")
Signed-off-by: Jessica Liu <liu.xuemei1 at zte.com.cn>
---
 drivers/irqchip/irq-riscv-aplic-main.c | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/drivers/irqchip/irq-riscv-aplic-main.c b/drivers/irqchip/irq-riscv-aplic-main.c
index 8775f188ea4f..9f53979b6962 100644
--- a/drivers/irqchip/irq-riscv-aplic-main.c
+++ b/drivers/irqchip/irq-riscv-aplic-main.c
@@ -116,6 +116,16 @@ static struct syscore aplic_syscore = {
 	.ops = &aplic_syscore_ops,
 };

+static bool aplic_syscore_registered __ro_after_init;
+
+static void aplic_syscore_init(void)
+{
+	if (!aplic_syscore_registered) {
+		register_syscore(&aplic_syscore);
+		aplic_syscore_registered = true;
+	}
+}
+
 static int aplic_pm_notifier(struct notifier_block *nb, unsigned long action, void *data)
 {
 	struct aplic_priv *priv = container_of(nb, struct aplic_priv, genpd_nb);
@@ -379,7 +389,7 @@ static int aplic_probe(struct platform_device *pdev)
 		return rc;
 	}

-	register_syscore(&aplic_syscore);
+	aplic_syscore_init();

 #ifdef CONFIG_ACPI
 	if (!acpi_disabled)
-- 
2.27.0