From 5c5682b9f87a3b7bd4833884f300ec673685f6a6 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 13 Feb 2024 22:05:54 +0100 Subject: [PATCH] x86/cpu: Detect real BSP on crash kernels When a kdump kernel is started from a crashing CPU then there is no guarantee that this CPU is the real boot CPU (BSP). If the kdump kernel tries to online the BSP then the INIT sequence will reset the machine. There is a command line option to prevent this, but in case of nested kdump kernels this is wrong. But that command line option is not required at all because the real BSP is enumerated as the first CPU by firmware. Support for the only known system which was different (Voyager) got removed long ago. Detect whether the boot CPU APIC ID is the first APIC ID enumerated by the firmware. If the first APIC ID enumerated is not matching the boot CPU APIC ID then skip registering it. Signed-off-by: Thomas Gleixner Tested-by: Michael Kelley Tested-by: Sohil Mehta Link: https://lore.kernel.org/r/20240213210252.348542071@linutronix.de --- Documentation/admin-guide/kdump/kdump.rst | 7 +- .../admin-guide/kernel-parameters.txt | 9 -- arch/x86/kernel/cpu/topology.c | 107 +++++++++++------- 3 files changed, 66 insertions(+), 57 deletions(-) diff --git a/Documentation/admin-guide/kdump/kdump.rst b/Documentation/admin-guide/kdump/kdump.rst index 5762e7477a0c..0302a93b1d40 100644 --- a/Documentation/admin-guide/kdump/kdump.rst +++ b/Documentation/admin-guide/kdump/kdump.rst @@ -191,9 +191,7 @@ Dump-capture kernel config options (Arch Dependent, i386 and x86_64) CPU is enough for kdump kernel to dump vmcore on most of systems. However, you can also specify nr_cpus=X to enable multiple processors - in kdump kernel. In this case, "disable_cpu_apicid=" is needed to - tell kdump kernel which cpu is 1st kernel's BSP. Please refer to - admin-guide/kernel-parameters.txt for more details. + in kdump kernel. With CONFIG_SMP=n, the above things are not related. @@ -454,8 +452,7 @@ Notes on loading the dump-capture kernel: to use multi-thread programs with it, such as parallel dump feature of makedumpfile. Otherwise, the multi-thread program may have a great performance degradation. To enable multi-cpu support, you should bring up an - SMP dump-capture kernel and specify maxcpus/nr_cpus, disable_cpu_apicid=[X] - options while loading it. + SMP dump-capture kernel and specify maxcpus/nr_cpus options while loading it. * For s390x there are two kdump modes: If a ELF header is specified with the elfcorehdr= kernel parameter, it is used by the kdump kernel as it diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 31b3a25680d0..4b9b4d662e31 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -1100,15 +1100,6 @@ Disable TLBIE instruction. Currently does not work with KVM, with HASH MMU, or with coherent accelerators. - disable_cpu_apicid= [X86,APIC,SMP] - Format: - The number of initial APIC ID for the - corresponding CPU to be disabled at boot, - mostly used for the kdump 2nd kernel to - disable BSP to wake up multiple CPUs without - causing system reset or hang due to sending - INIT from AP to BSP. - disable_ddw [PPC/PSERIES] Disable Dynamic DMA Window support. Use this to workaround buggy firmware. diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c index fc47f5216f9a..d55533170ba0 100644 --- a/arch/x86/kernel/cpu/topology.c +++ b/arch/x86/kernel/cpu/topology.c @@ -32,18 +32,13 @@ static struct { unsigned int nr_disabled_cpus; unsigned int nr_rejected_cpus; u32 boot_cpu_apic_id; + u32 real_bsp_apic_id; } topo_info __read_mostly = { .nr_assigned_cpus = 1, .boot_cpu_apic_id = BAD_APICID, + .real_bsp_apic_id = BAD_APICID, }; -/* - * Processor to be disabled specified by kernel parameter - * disable_cpu_apicid=, mostly used for the kdump 2nd kernel to - * avoid undefined behaviour caused by sending INIT from AP to BSP. - */ -static u32 disabled_cpu_apicid __ro_after_init = BAD_APICID; - bool arch_match_cpu_phys_id(int cpu, u64 phys_id) { return phys_id == (u64)cpuid_to_apicid[cpu]; @@ -123,35 +118,41 @@ static void topo_set_cpuids(unsigned int cpu, u32 apic_id, u32 acpi_id) cpu_mark_primary_thread(cpu, apic_id); } -/** - * topology_register_apic - Register an APIC in early topology maps - * @apic_id: The APIC ID to set up - * @acpi_id: The ACPI ID associated to the APIC - * @present: True if the corresponding CPU is present - */ -void __init topology_register_apic(u32 apic_id, u32 acpi_id, bool present) +static __init bool check_for_real_bsp(u32 apic_id) +{ + /* + * There is no real good way to detect whether this a kdump() + * kernel, but except on the Voyager SMP monstrosity which is not + * longer supported, the real BSP APIC ID is the first one which is + * enumerated by firmware. That allows to detect whether the boot + * CPU is the real BSP. If it is not, then do not register the APIC + * because sending INIT to the real BSP would reset the whole + * system. + * + * The first APIC ID which is enumerated by firmware is detectable + * because the boot CPU APIC ID is registered before that without + * invoking this code. + */ + if (topo_info.real_bsp_apic_id != BAD_APICID) + return false; + + if (apic_id == topo_info.boot_cpu_apic_id) { + topo_info.real_bsp_apic_id = apic_id; + return false; + } + + pr_warn("Boot CPU APIC ID not the first enumerated APIC ID: %x > %x\n", + topo_info.boot_cpu_apic_id, apic_id); + pr_warn("Crash kernel detected. Disabling real BSP to prevent machine INIT\n"); + + topo_info.real_bsp_apic_id = apic_id; + return true; +} + +static __init void topo_register_apic(u32 apic_id, u32 acpi_id, bool present) { int cpu; - if (apic_id >= MAX_LOCAL_APIC) { - pr_err_once("APIC ID %x exceeds kernel limit of: %x\n", apic_id, MAX_LOCAL_APIC - 1); - topo_info.nr_rejected_cpus++; - return; - } - - if (disabled_cpu_apicid == apic_id) { - pr_info("Disabling CPU as requested via 'disable_cpu_apicid=0x%x'.\n", apic_id); - topo_info.nr_rejected_cpus++; - return; - } - - /* CPU numbers exhausted? */ - if (apic_id != topo_info.boot_cpu_apic_id && topo_info.nr_assigned_cpus >= nr_cpu_ids) { - pr_warn_once("CPU limit of %d reached. Ignoring further CPUs\n", nr_cpu_ids); - topo_info.nr_rejected_cpus++; - return; - } - if (present) { set_bit(apic_id, phys_cpu_present_map); @@ -171,6 +172,35 @@ void __init topology_register_apic(u32 apic_id, u32 acpi_id, bool present) } } +/** + * topology_register_apic - Register an APIC in early topology maps + * @apic_id: The APIC ID to set up + * @acpi_id: The ACPI ID associated to the APIC + * @present: True if the corresponding CPU is present + */ +void __init topology_register_apic(u32 apic_id, u32 acpi_id, bool present) +{ + if (apic_id >= MAX_LOCAL_APIC) { + pr_err_once("APIC ID %x exceeds kernel limit of: %x\n", apic_id, MAX_LOCAL_APIC - 1); + topo_info.nr_rejected_cpus++; + return; + } + + if (check_for_real_bsp(apic_id)) { + topo_info.nr_rejected_cpus++; + return; + } + + /* CPU numbers exhausted? */ + if (apic_id != topo_info.boot_cpu_apic_id && topo_info.nr_assigned_cpus >= nr_cpu_ids) { + pr_warn_once("CPU limit of %d reached. Ignoring further CPUs\n", nr_cpu_ids); + topo_info.nr_rejected_cpus++; + return; + } + + topo_register_apic(apic_id, acpi_id, present); +} + /** * topology_register_boot_apic - Register the boot CPU APIC * @apic_id: The APIC ID to set up @@ -182,7 +212,7 @@ void __init topology_register_boot_apic(u32 apic_id) WARN_ON_ONCE(topo_info.boot_cpu_apic_id != BAD_APICID); topo_info.boot_cpu_apic_id = apic_id; - topology_register_apic(apic_id, CPU_ACPIID_INVALID, true); + topo_register_apic(apic_id, CPU_ACPIID_INVALID, true); } #ifdef CONFIG_ACPI_HOTPLUG_CPU @@ -335,12 +365,3 @@ static int __init setup_possible_cpus(char *str) } early_param("possible_cpus", setup_possible_cpus); #endif - -static int __init apic_set_disabled_cpu_apicid(char *arg) -{ - if (!arg || !get_option(&arg, &disabled_cpu_apicid)) - return -EINVAL; - - return 0; -} -early_param("disable_cpu_apicid", apic_set_disabled_cpu_apicid);