LoongArch: Change acpi_core_pic[NR_CPUS] to acpi_core_pic[MAX_CORE_PIC]

chenhuacai · chenhuacai · commit 4551b30525cf · 2024-02-06T12:32:05.000+08:00
With default config, the value of NR_CPUS is 64. When HW platform has more then 64 cpus, system will crash on these platforms. MAX_CORE_PIC is the maximum cpu number in MADT table (max physical number) which can exceed the supported maximum cpu number (NR_CPUS, max logical number), but kernel should not crash. Kernel should boot cpus with NR_CPUS, let the remainder cpus stay in BIOS. The potential crash reason is that the array acpi_core_pic[NR_CPUS] can be overflowed when parsing MADT table, and it is obvious that CORE_PIC should be corresponding to physical core rather than logical core, so it is better to define the array as acpi_core_pic[MAX_CORE_PIC]. With the patch, system can boot up 64 vcpus with qemu parameter -smp 128, otherwise system will crash with the following message. [ 0.000000] CPU 0 Unable to handle kernel paging request at virtual address 0000420000004259, era == 90000000037a5f0c, ra == 90000000037a46ec [ 0.000000] Oops[#1]: [ 0.000000] CPU: 0 PID: 0 Comm: swapper Not tainted 6.8.0-rc2+ #192 [ 0.000000] Hardware name: QEMU QEMU Virtual Machine, BIOS unknown 2/2/2022 [ 0.000000] pc 90000000037a5f0c ra 90000000037a46ec tp 9000000003c90000 sp 9000000003c93d60 [ 0.000000] a0 0000000000000019 a1 9000000003d93bc0 a2 0000000000000000 a3 9000000003c93bd8 [ 0.000000] a4 9000000003c93a74 a5 9000000083c93a67 a6 9000000003c938f0 a7 0000000000000005 [ 0.000000] t0 0000420000004201 t1 0000000000000000 t2 0000000000000001 t3 0000000000000001 [ 0.000000] t4 0000000000000003 t5 0000000000000000 t6 0000000000000030 t7 0000000000000063 [ 0.000000] t8 0000000000000014 u0 ffffffffffffffff s9 0000000000000000 s0 9000000003caee98 [ 0.000000] s1 90000000041b0480 s2 9000000003c93da0 s3 9000000003c93d98 s4 9000000003c93d90 [ 0.000000] s5 9000000003caa000 s6 000000000a7fd000 s7 000000000f556b60 s8 000000000e0a4330 [ 0.000000] ra: 90000000037a46ec platform_init+0x214/0x250 [ 0.000000] ERA: 90000000037a5f0c efi_runtime_init+0x30/0x94 [ 0.000000] CRMD: 000000b0 (PLV0 -IE -DA +PG DACF=CC DACM=CC -WE) [ 0.000000] PRMD: 00000000 (PPLV0 -PIE -PWE) [ 0.000000] EUEN: 00000000 (-FPE -SXE -ASXE -BTE) [ 0.000000] ECFG: 0007080 (LIE=11 VS=7) [ 0.000000] ESTAT: 00010000 [PIL] (IS= ECode=1 EsubCode=0) [ 0.000000] BADV: 0000420000004259 [ 0.000000] PRID: 0014c010 (Loongson-64bit, Loongson-3A5000) [ 0.000000] Modules linked in: [ 0.000000] Process swapper (pid: 0, threadinfo=(____ptrval____), task=(____ptrval____)) [ 0.000000] Stack : 9000000003c93a14 9000000003800898 90000000041844f8 90000000037a46ec [ 0.000000] 000000000a7fd000 0000000008290000 0000000000000000 0000000000000000 [ 0.000000] 0000000000000000 0000000000000000 00000000019d8000 000000000f556b60 [ 0.000000] 000000000a7fd000 000000000f556b08 9000000003ca7700 9000000003800000 [ 0.000000] 9000000003c93e50 9000000003800898 9000000003800108 90000000037a484c [ 0.000000] 000000000e0a4330 000000000f556b60 000000000a7fd000 000000000f556b08 [ 0.000000] 9000000003ca7700 9000000004184000 0000000000200000 000000000e02b018 [ 0.000000] 000000000a7fd000 90000000037a0790 9000000003800108 0000000000000000 [ 0.000000] 0000000000000000 000000000e0a4330 000000000f556b60 000000000a7fd000 [ 0.000000] 000000000f556b08 000000000eaae298 000000000eaa5040 0000000000200000 [ 0.000000] ... [ 0.000000] Call Trace: [ 0.000000] [<90000000037a5f0c>] efi_runtime_init+0x30/0x94 [ 0.000000] [<90000000037a46ec>] platform_init+0x214/0x250 [ 0.000000] [<90000000037a484c>] setup_arch+0x124/0x45c [ 0.000000] [<90000000037a0790>] start_kernel+0x90/0x670 [ 0.000000] [<900000000378b0d8>] kernel_entry+0xd8/0xdc Signed-off-by: Bibo Mao <maobibo@loongson.cn> Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
diff --git a/arch/loongarch/include/asm/acpi.h b/arch/loongarch/include/asm/acpi.h
@@ -32,8 +32,10 @@ static inline bool acpi_has_cpu_in_madt(void)
 	return true;
 }
 
+#define MAX_CORE_PIC 256
+
 extern struct list_head acpi_wakeup_device_list;
-extern struct acpi_madt_core_pic acpi_core_pic[NR_CPUS];
+extern struct acpi_madt_core_pic acpi_core_pic[MAX_CORE_PIC];
 
 extern int __init parse_acpi_topology(void);
 
diff --git a/arch/loongarch/kernel/acpi.c b/arch/loongarch/kernel/acpi.c
@@ -29,11 +29,9 @@ int disabled_cpus;
 
 u64 acpi_saved_sp;
 
-#define MAX_CORE_PIC 256
-
 #define PREFIX			"ACPI: "
 
-struct acpi_madt_core_pic acpi_core_pic[NR_CPUS];
+struct acpi_madt_core_pic acpi_core_pic[MAX_CORE_PIC];
 
 void __init __iomem * __acpi_map_table(unsigned long phys, unsigned long size)
 {

Original file line number	Diff line number	Diff line change
`@@ -32,8 +32,10 @@ static inline bool acpi_has_cpu_in_madt(void)`
`32`	`32`	`return true;`
`33`	`33`	`}`
`34`	`34`
	`35`	`+#define MAX_CORE_PIC 256`
	`36`	`+`
`35`	`37`	`extern struct list_head acpi_wakeup_device_list;`
`36`		`-extern struct acpi_madt_core_pic acpi_core_pic[NR_CPUS];`
	`38`	`+extern struct acpi_madt_core_pic acpi_core_pic[MAX_CORE_PIC];`
`37`	`39`
`38`	`40`	`extern int __init parse_acpi_topology(void);`
`39`	`41`
Original file line number	Diff line number	Diff line change
`@@ -29,11 +29,9 @@ int disabled_cpus;`
`29`	`29`
`30`	`30`	`u64 acpi_saved_sp;`
`31`	`31`
`32`		`-#define MAX_CORE_PIC 256`
`33`		`-`
`34`	`32`	`#define PREFIX "ACPI: "`
`35`	`33`
`36`		`-struct acpi_madt_core_pic acpi_core_pic[NR_CPUS];`
	`34`	`+struct acpi_madt_core_pic acpi_core_pic[MAX_CORE_PIC];`
`37`	`35`
`38`	`36`	`void __init __iomem * __acpi_map_table(unsigned long phys, unsigned long size)`
`39`	`37`	`{`