[PATCH 1/8] Revert "arm64: Kconfig: Enable HOTPLUG_SMT"
driver inclusion category: cleanup bugzilla: https://gitee.com/openeuler/kernel/issues/IBZQQR ---------------------------------------------------------------------- This reverts commit 4ee778a80dd45dbf3fa7c0b527271ec8babeae35. This reverts commit d31fbcb824a33a9035401a17bd995106a948b8c9. This reverts commit a09d9ba1682c68ae8a6986d4cd7c18caffb8cc53. This reverts commit b19938a0f75e2844e4c5093237f380e5ae23b361. This reverts commit 1243a42766a6352b4fdccde2caa5ef3ec41c49e1. Signed-off-by: Qi Xi <xiqi2@huawei.com> --- arch/arm64/Kconfig | 1 - arch/arm64/configs/defconfig | 1 - arch/arm64/kernel/topology.c | 23 ------------------ drivers/base/arch_topology.c | 45 ----------------------------------- include/linux/arch_topology.h | 13 ---------- 5 files changed, 83 deletions(-) diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 6e3047a1e993..580cbe2f8ec6 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -235,7 +235,6 @@ config ARM64 select HAVE_KRETPROBES select HAVE_GENERIC_VDSO select HOTPLUG_CORE_SYNC_DEAD if HOTPLUG_CPU - select HOTPLUG_SMT if (SMP && HOTPLUG_CPU) select IRQ_DOMAIN select IRQ_FORCED_THREADING select KASAN_VMALLOC if KASAN diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig index 2df5c1e3d42f..c6f35d0ce475 100644 --- a/arch/arm64/configs/defconfig +++ b/arch/arm64/configs/defconfig @@ -1593,7 +1593,6 @@ CONFIG_HISILICON_ERRATUM_162102203=y CONFIG_CPU_INSPECT=m CONFIG_CPU_INSPECTOR_ATF=m # end of CPU Inspect -CONFIG_HOTPLUG_SMT=y CONFIG_NUMA_AWARE_SPINLOCKS=y CONFIG_HISI_SOC_CACHE=m CONFIG_HISI_SOC_HHA=m diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c index 6d0d54de7349..45143dfd1402 100644 --- a/arch/arm64/kernel/topology.c +++ b/arch/arm64/kernel/topology.c @@ -16,7 +16,6 @@ #include <linux/cacheinfo.h> #include <linux/init.h> #include <linux/percpu.h> -#include <linux/xarray.h> #include <asm/cpu.h> #include <asm/cputype.h> @@ -43,16 +42,11 @@ static bool __init acpi_cpu_is_threaded(int cpu) */ int __init parse_acpi_topology(void) { - int thread_num, max_smt_thread_num = 1; - struct xarray core_threads; int cpu, topology_id; - void *entry; if (acpi_disabled) return 0; - xa_init(&core_threads); - for_each_possible_cpu(cpu) { topology_id = find_acpi_cpu_topology(cpu, 0); if (topology_id < 0) @@ -62,20 +56,6 @@ int __init parse_acpi_topology(void) cpu_topology[cpu].thread_id = topology_id; topology_id = find_acpi_cpu_topology(cpu, 1); cpu_topology[cpu].core_id = topology_id; - - entry = xa_load(&core_threads, topology_id); - if (!entry) { - xa_store(&core_threads, topology_id, - xa_mk_value(1), GFP_KERNEL); - } else { - thread_num = xa_to_value(entry); - thread_num++; - xa_store(&core_threads, topology_id, - xa_mk_value(thread_num), GFP_KERNEL); - - if (thread_num > max_smt_thread_num) - max_smt_thread_num = thread_num; - } } else { cpu_topology[cpu].thread_id = -1; cpu_topology[cpu].core_id = topology_id; @@ -86,9 +66,6 @@ int __init parse_acpi_topology(void) cpu_topology[cpu].package_id = topology_id; } - topology_smt_set_num_threads(max_smt_thread_num); - - xa_destroy(&core_threads); return 0; } #endif diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c index 630c59d97aef..2aa0c6425290 100644 --- a/drivers/base/arch_topology.c +++ b/drivers/base/arch_topology.c @@ -547,13 +547,6 @@ static int __init parse_core(struct device_node *core, int package_id, i++; } while (t); - /* - * We've already gotten threads number in this core, update the SMT - * threads number when necessary. - */ - if (i > topology_smt_get_num_threads()) - topology_smt_set_num_threads(i); - cpu = get_cpu_for_node(core); if (cpu >= 0) { if (!leaf) { @@ -757,36 +750,6 @@ const struct cpumask *cpu_clustergroup_mask(int cpu) return &cpu_topology[cpu].cluster_sibling; } -#ifdef CONFIG_HOTPLUG_SMT - -/* Maximum threads number per-Core */ -static unsigned int topology_smt_num_threads = 1; - -void __init topology_smt_set_num_threads(unsigned int num_threads) -{ - topology_smt_num_threads = num_threads; -} - -unsigned int __init topology_smt_get_num_threads(void) -{ - return topology_smt_num_threads; -} - -/* - * On SMT Hotplug the primary thread of the SMT won't be disabled. For x86 they - * seem to have a primary thread for special purpose. For other arthitectures - * like arm64 there's no such restriction for a primary thread, so make the - * first thread in the SMT as the primary thread. - */ -bool topology_is_primary_thread(unsigned int cpu) -{ - if (cpu == cpumask_first(topology_sibling_cpumask(cpu))) - return true; - - return false; -} -#endif - void update_siblings_masks(unsigned int cpuid) { struct cpu_topology *cpu_topo, *cpuid_topo = &cpu_topology[cpuid]; @@ -899,14 +862,6 @@ void __init init_cpu_topology(void) reset_cpu_topology(); } - /* - * By this stage we get to know whether we support SMT or not, update - * the information for the core. We don't support - * CONFIG_SMT_NUM_THREADS_DYNAMIC so make the max_threads == num_threads. - */ - cpu_smt_set_num_threads(topology_smt_get_num_threads(), - topology_smt_get_num_threads()); - for_each_possible_cpu(cpu) { ret = fetch_cache_info(cpu); if (!ret) diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h index 14cdf5df760c..949ecdb6e956 100644 --- a/include/linux/arch_topology.h +++ b/include/linux/arch_topology.h @@ -100,19 +100,6 @@ void remove_cpu_topology(unsigned int cpuid); void reset_cpu_topology(void); int parse_acpi_topology(void); -#ifdef CONFIG_HOTPLUG_SMT -bool topology_is_primary_thread(unsigned int cpu); -void topology_smt_set_num_threads(unsigned int num_threads); -unsigned int topology_smt_get_num_threads(void); -#else -static inline bool topology_is_primary_thread(unsigned int cpu) { return false; } -static inline void topology_smt_set_num_threads(unsigned int num_threads) { } -static inline unsigned int topology_smt_get_num_threads(void) -{ - return 1; -} -#endif - void freq_inv_set_max_ratio(int cpu, u64 max_rate); #endif -- 2.33.0
From: Yicong Yang <yangyicong@hisilicon.com> driver inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/IBZQQR ---------------------------------------------------------------------- Currently if architectures want to support HOTPLUG_SMT they need to provide a topology_is_primary_thread() telling the framework which thread in the SMT cannot offline. However arm64 doesn't have a restriction on which thread in the SMT cannot offline, a simplest choice is that just make 1st thread as the "primary" thread. So just make this as the default implementation in the framework and let architectures like x86 that have special primary thread to override this function (which they've already done). There's no need to provide a stub function if !CONFIG_SMP or !CONFIG_HOTPLUG_SMT. In such case the testing CPU is already the 1st CPU in the SMT so it's always the primary thread. Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com> Reviewed-by: Pierre Gondois <pierre.gondois@arm.com> Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com> Reviewed-by: Yicong Yang <yangyicong@hisilicon.com> Signed-off-by: Yicong Yang <yangyicong@hisilicon.com> Signed-off-by: Hongye Lin <linhongye@h-partners.com> Signed-off-by: Qi Xi <xiqi2@huawei.com> --- arch/powerpc/include/asm/topology.h | 1 + arch/x86/include/asm/topology.h | 3 ++- include/linux/topology.h | 24 ++++++++++++++++++++++++ 3 files changed, 27 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h index 16bacfe8c7a2..da15b5efe807 100644 --- a/arch/powerpc/include/asm/topology.h +++ b/arch/powerpc/include/asm/topology.h @@ -152,6 +152,7 @@ static inline bool topology_is_primary_thread(unsigned int cpu) { return cpu == cpu_first_thread_sibling(cpu); } +#define topology_is_primary_thread topology_is_primary_thread static inline bool topology_smt_thread_allowed(unsigned int cpu) { diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h index 3235ba1e5b06..61f6350b4ed1 100644 --- a/arch/x86/include/asm/topology.h +++ b/arch/x86/include/asm/topology.h @@ -153,6 +153,8 @@ static inline bool topology_is_primary_thread(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_primary_thread_mask); } +#define topology_is_primary_thread topology_is_primary_thread + #else /* CONFIG_SMP */ #define topology_max_packages() (1) static inline int @@ -162,7 +164,6 @@ topology_update_die_map(unsigned int dieid, unsigned int cpu) { return 0; } static inline int topology_phys_to_logical_pkg(unsigned int pkg) { return 0; } static inline int topology_max_die_per_package(void) { return 1; } static inline int topology_max_smt_threads(void) { return 1; } -static inline bool topology_is_primary_thread(unsigned int cpu) { return true; } #endif /* !CONFIG_SMP */ static inline void arch_fix_phys_package_id(int num, u32 slot) diff --git a/include/linux/topology.h b/include/linux/topology.h index 52f5850730b3..6ae995e18ff5 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -240,6 +240,30 @@ static inline const struct cpumask *cpu_smt_mask(int cpu) } #endif +#ifndef topology_is_primary_thread + +#define topology_is_primary_thread topology_is_primary_thread + +static inline bool topology_is_primary_thread(unsigned int cpu) +{ + /* + * When disabling SMT the primary thread of the SMT will remain + * enabled/active. Architectures do have a special primary thread + * (e.g. x86) needs to override this function. Otherwise can make + * the first thread in the SMT as the primary thread. + * + * The sibling cpumask of an offline CPU contains always the CPU + * itself for architectures using the implementation of + * CONFIG_GENERIC_ARCH_TOPOLOGY for building their topology. + * Other architectures not using CONFIG_GENERIC_ARCH_TOPOLOGY for + * building their topology have to check whether to use this default + * implementation or to override it. + */ + return cpu == cpumask_first(topology_sibling_cpumask(cpu)); +} + +#endif + static inline const struct cpumask *cpu_cpu_mask(int cpu) { return cpumask_of_node(cpu_to_node(cpu)); -- 2.33.0
From: Yicong Yang <yangyicong@hisilicon.com> driver inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/IBZQQR ---------------------------------------------------------------------- On building the topology from the devicetree, we've already gotten the SMT thread number of each core. Update the largest SMT thread number and enable the SMT control by the end of topology parsing. The framework's SMT control provides two interface to the users [1] through /sys/devices/system/cpu/smt/control: 1) enable SMT by writing "on" and disable by "off" 2) enable SMT by writing max_thread_number or disable by writing 1 Both method support to completely disable/enable the SMT cores so both work correctly for symmetric SMT platform and asymmetric platform with non-SMT and one type SMT cores like: core A: 1 thread core B: X (X!=1) threads Note that for a theoretically possible multiple SMT-X (X>1) core platform the SMT control is also supported as expected but only by writing the "on/off" method. [1] https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/Docu... Reviewed-by: Pierre Gondois <pierre.gondois@arm.com> Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com> Reviewed-by: Yicong Yang <yangyicong@hisilicon.com> Signed-off-by: Yicong Yang <yangyicong@hisilicon.com> Signed-off-by: Hongye Lin <linhongye@h-partners.com> Signed-off-by: Qi Xi <xiqi2@huawei.com> --- drivers/base/arch_topology.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c index 2aa0c6425290..3fe31e2b0372 100644 --- a/drivers/base/arch_topology.c +++ b/drivers/base/arch_topology.c @@ -10,6 +10,7 @@ #include <linux/cacheinfo.h> #include <linux/cpu.h> #include <linux/cpufreq.h> +#include <linux/cpu_smt.h> #include <linux/device.h> #include <linux/of.h> #include <linux/slab.h> @@ -487,6 +488,10 @@ core_initcall(free_raw_capacity); #endif #if defined(CONFIG_ARM64) || defined(CONFIG_RISCV) + +/* Used to enable the SMT control */ +static unsigned int max_smt_thread_num = 1; + /* * This function returns the logic cpu number of the node. * There are basically three kinds of return values: @@ -547,6 +552,8 @@ static int __init parse_core(struct device_node *core, int package_id, i++; } while (t); + max_smt_thread_num = max_t(unsigned int, max_smt_thread_num, i); + cpu = get_cpu_for_node(core); if (cpu >= 0) { if (!leaf) { @@ -657,6 +664,17 @@ static int __init parse_socket(struct device_node *socket) if (!has_socket) ret = parse_cluster(socket, 0, -1, 0); + /* + * Reset the max_smt_thread_num to 1 on failure. Since on failure + * we need to notify the framework the SMT is not supported, but + * max_smt_thread_num can be initialized to the SMT thread number + * of the cores which are successfully parsed. + */ + if (ret) + max_smt_thread_num = 1; + + cpu_smt_set_num_threads(max_smt_thread_num, max_smt_thread_num); + return ret; } -- 2.33.0
From: Yicong Yang <yangyicong@hisilicon.com> driver inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/IBZQQR ---------------------------------------------------------------------- For ACPI we'll build the topology from PPTT and we cannot directly get the SMT number of each core. Instead using a temporary xarray to record the heterogeneous information (from ACPI_PPTT_ACPI_IDENTICAL) and SMT information of the first core in its heterogeneous CPU cluster when building the topology. Then we can know the largest SMT number in the system. If a homogeneous system's using ACPI 6.2 or later, all the CPUs should be under the root node of PPTT. There'll be only one entry in the xarray and all the CPUs in the system will be assumed identical. The framework's SMT control provides two interface to the users [1] through /sys/devices/system/cpu/smt/control: 1) enable SMT by writing "on" and disable by "off" 2) enable SMT by writing max_thread_number or disable by writing 1 Both method support to completely disable/enable the SMT cores so both work correctly for symmetric SMT platform and asymmetric platform with non-SMT and one type SMT cores like: core A: 1 thread core B: X (X!=1) threads Note that for a theoretically possible multiple SMT-X (X>1) core platform the SMT control is also supported as expected but only by writing the "on/off" method. [1] https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/Docu... Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com> Reviewed-by: Hanjun Guo <guohanjun@huawei.com> Reviewed-by: Pierre Gondois <pierre.gondois@arm.com> Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com> Reviewed-by: Yicong Yang <yangyicong@hisilicon.com> Signed-off-by: Yicong Yang <yangyicong@hisilicon.com> Signed-off-by: Hongye Lin <linhongye@h-partners.com> Signed-off-by: Qi Xi <xiqi2@huawei.com> --- arch/arm64/kernel/topology.c | 52 ++++++++++++++++++++++++++++++++++++ drivers/base/arch_topology.c | 2 ++ 2 files changed, 54 insertions(+) diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c index 45143dfd1402..0c78f399fcae 100644 --- a/arch/arm64/kernel/topology.c +++ b/arch/arm64/kernel/topology.c @@ -36,17 +36,28 @@ static bool __init acpi_cpu_is_threaded(int cpu) return !!is_threaded; } +struct cpu_smt_info { + unsigned int thread_num; + int core_id; +}; + /* * Propagate the topology information of the processor_topology_node tree to the * cpu_topology array. */ int __init parse_acpi_topology(void) { + unsigned int max_smt_thread_num = 1; + struct cpu_smt_info *entry; + struct xarray hetero_cpu; + unsigned long hetero_id; int cpu, topology_id; if (acpi_disabled) return 0; + xa_init(&hetero_cpu); + for_each_possible_cpu(cpu) { topology_id = find_acpi_cpu_topology(cpu, 0); if (topology_id < 0) @@ -56,6 +67,34 @@ int __init parse_acpi_topology(void) cpu_topology[cpu].thread_id = topology_id; topology_id = find_acpi_cpu_topology(cpu, 1); cpu_topology[cpu].core_id = topology_id; + + /* + * In the PPTT, CPUs below a node with the 'identical + * implementation' flag have the same number of threads. + * Count the number of threads for only one CPU (i.e. + * one core_id) among those with the same hetero_id. + * See the comment of find_acpi_cpu_topology_hetero_id() + * for more details. + * + * One entry is created for each node having: + * - the 'identical implementation' flag + * - its parent not having the flag + */ + hetero_id = find_acpi_cpu_topology_hetero_id(cpu); + entry = xa_load(&hetero_cpu, hetero_id); + if (!entry) { + entry = kzalloc(sizeof(*entry), GFP_KERNEL); + WARN_ON_ONCE(!entry); + + if (entry) { + entry->core_id = topology_id; + entry->thread_num = 1; + xa_store(&hetero_cpu, hetero_id, + entry, GFP_KERNEL); + } + } else if (entry->core_id == topology_id) { + entry->thread_num++; + } } else { cpu_topology[cpu].thread_id = -1; cpu_topology[cpu].core_id = topology_id; @@ -66,6 +105,19 @@ int __init parse_acpi_topology(void) cpu_topology[cpu].package_id = topology_id; } + /* + * This is a short loop since the number of XArray elements is the + * number of heterogeneous CPU clusters. On a homogeneous system + * there's only one entry in the XArray. + */ + xa_for_each(&hetero_cpu, hetero_id, entry) { + max_smt_thread_num = max(max_smt_thread_num, entry->thread_num); + xa_erase(&hetero_cpu, hetero_id); + kfree(entry); + } + + cpu_smt_set_num_threads(max_smt_thread_num, max_smt_thread_num); + xa_destroy(&hetero_cpu); return 0; } #endif diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c index 3fe31e2b0372..1b816703c2a0 100644 --- a/drivers/base/arch_topology.c +++ b/drivers/base/arch_topology.c @@ -11,6 +11,7 @@ #include <linux/cpu.h> #include <linux/cpufreq.h> #include <linux/cpu_smt.h> +#include <linux/cpu_smt.h> #include <linux/device.h> #include <linux/of.h> #include <linux/slab.h> @@ -21,6 +22,7 @@ #include <linux/rcupdate.h> #include <linux/sched.h> #include <linux/units.h> +#include <linux/xarray.h> #define CREATE_TRACE_POINTS #include <trace/events/thermal_pressure.h> -- 2.33.0
From: Yicong Yang <yangyicong@hisilicon.com> driver inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/IBZQQR ---------------------------------------------------------------------- Enable HOTPLUG_SMT for SMT control. Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com> Reviewed-by: Pierre Gondois <pierre.gondois@arm.com> Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com> Reviewed-by: Yicong Yang <yangyicong@hisilicon.com> Signed-off-by: Yicong Yang <yangyicong@hisilicon.com> Signed-off-by: Hongye Lin <linhongye@h-partners.com> Signed-off-by: Qi Xi <xiqi2@huawei.com> --- arch/arm64/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 580cbe2f8ec6..3829167e97fc 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -235,6 +235,7 @@ config ARM64 select HAVE_KRETPROBES select HAVE_GENERIC_VDSO select HOTPLUG_CORE_SYNC_DEAD if HOTPLUG_CPU + select HOTPLUG_SMT if HOTPLUG_CPU select IRQ_DOMAIN select IRQ_FORCED_THREADING select KASAN_VMALLOC if KASAN -- 2.33.0
From: Yicong Yang <yangyicong@hisilicon.com> kunpeng inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I90N2C CVE: NA ---------------------------------------------------------------------- Currently we cannot use watchdog_{perf, buddy} if CONFIG_SDEI_WATCHDOG=y. Not all the platforms has watchdog_sdei so this patch tries to make watchdog_sdei coexist with other watchdogs. Only one watchdog will finally works. By default watchdog_sdei will be used. If boot with "disable_sdei_nmi_watchdog", other watchdogs will be used if probed. Signed-off-by: Yicong Yang <yangyicong@hisilicon.com> Signed-off-by: Jie Liu <liujie375@h-partners.com> Signed-off-by: Qi Xi <xiqi2@huawei.com> --- arch/arm64/kernel/watchdog_sdei.c | 6 +++--- include/linux/nmi.h | 6 ++++++ kernel/watchdog.c | 16 ++++++++++++---- lib/Kconfig.debug | 2 -- 4 files changed, 21 insertions(+), 9 deletions(-) diff --git a/arch/arm64/kernel/watchdog_sdei.c b/arch/arm64/kernel/watchdog_sdei.c index 6f43496de56e..c7b12806364e 100644 --- a/arch/arm64/kernel/watchdog_sdei.c +++ b/arch/arm64/kernel/watchdog_sdei.c @@ -25,7 +25,7 @@ bool disable_sdei_nmi_watchdog; static bool sdei_watchdog_registered; static DEFINE_PER_CPU(ktime_t, last_check_time); -void watchdog_hardlockup_enable(unsigned int cpu) +void sdei_watchdog_hardlockup_enable(unsigned int cpu) { int ret; @@ -45,7 +45,7 @@ void watchdog_hardlockup_enable(unsigned int cpu) } } -void watchdog_hardlockup_disable(unsigned int cpu) +void sdei_watchdog_hardlockup_disable(unsigned int cpu) { int ret; @@ -106,7 +106,7 @@ void sdei_watchdog_clear_eoi(void) sdei_api_clear_eoi(SDEI_NMI_WATCHDOG_HWIRQ); } -int __init watchdog_hardlockup_probe(void) +int __init sdei_watchdog_hardlockup_probe(void) { int ret; diff --git a/include/linux/nmi.h b/include/linux/nmi.h index 7bd446acad24..43dd3a79fdf2 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -236,10 +236,16 @@ static inline void nmi_backtrace_stall_check(const struct cpumask *btp) {} #endif #ifdef CONFIG_SDEI_WATCHDOG +void sdei_watchdog_hardlockup_enable(unsigned int cpu); +void sdei_watchdog_hardlockup_disable(unsigned int cpu); void sdei_watchdog_clear_eoi(void); +int sdei_watchdog_hardlockup_probe(void); extern bool disable_sdei_nmi_watchdog; #else +static inline void sdei_watchdog_hardlockup_enable(unsigned int cpu) { } +static inline void sdei_watchdog_hardlockup_disable(unsigned int cpu) { } static inline void sdei_watchdog_clear_eoi(void) { } +static inline int sdei_watchdog_hardlockup_probe(void) { return -ENODEV; } #define disable_sdei_nmi_watchdog 1 #endif diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 9e349a943cdd..11102420a2c7 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -562,8 +562,12 @@ static void watchdog_enable(unsigned int cpu) /* Initialize timestamp */ update_touch_ts(); /* Enable the hardlockup detector */ - if (watchdog_enabled & WATCHDOG_HARDLOCKUP_ENABLED) - watchdog_hardlockup_enable(cpu); + if (watchdog_enabled & WATCHDOG_HARDLOCKUP_ENABLED) { + if (disable_sdei_nmi_watchdog) + watchdog_hardlockup_enable(cpu); + else + sdei_watchdog_hardlockup_enable(cpu); + } } static void watchdog_disable(unsigned int cpu) @@ -577,7 +581,10 @@ static void watchdog_disable(unsigned int cpu) * delay between disabling the timer and disabling the hardlockup * detector causes a false positive. */ - watchdog_hardlockup_disable(cpu); + if (disable_sdei_nmi_watchdog) + watchdog_hardlockup_disable(cpu); + else + sdei_watchdog_hardlockup_disable(cpu); hrtimer_cancel(hrtimer); wait_for_completion(this_cpu_ptr(&softlockup_completion)); } @@ -1022,7 +1029,8 @@ void __init lockup_detector_init(void) cpumask_copy(&watchdog_cpumask, housekeeping_cpumask(HK_TYPE_TIMER)); - if (!watchdog_hardlockup_probe()) + if ((!disable_sdei_nmi_watchdog && !sdei_watchdog_hardlockup_probe()) || + !watchdog_hardlockup_probe()) watchdog_hardlockup_available = true; else allow_lockup_detector_init_retry = true; diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index d064a93515e1..a674fb8b2e9e 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1105,7 +1105,6 @@ config HARDLOCKUP_DETECTOR_PERF depends on HARDLOCKUP_DETECTOR depends on HAVE_HARDLOCKUP_DETECTOR_PERF && !HARDLOCKUP_DETECTOR_PREFER_BUDDY depends on !HAVE_HARDLOCKUP_DETECTOR_ARCH - depends on !SDEI_WATCHDOG select HARDLOCKUP_DETECTOR_COUNTS_HRTIMER config HARDLOCKUP_DETECTOR_BUDDY @@ -1114,7 +1113,6 @@ config HARDLOCKUP_DETECTOR_BUDDY depends on HAVE_HARDLOCKUP_DETECTOR_BUDDY depends on !HAVE_HARDLOCKUP_DETECTOR_PERF || HARDLOCKUP_DETECTOR_PREFER_BUDDY depends on !HAVE_HARDLOCKUP_DETECTOR_ARCH - depends on !SDEI_WATCHDOG select HARDLOCKUP_DETECTOR_COUNTS_HRTIMER config HARDLOCKUP_DETECTOR_ARCH -- 2.33.0
From: Yicong Yang <yangyicong@hisilicon.com> kunpeng inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I9KE9N CVE: NA ---------------------------------------------------------------------- 1509d06c9c41 ("init: only move down lockup_detector_init() when sdei_watchdog is enabled") In the above commit, sdei_watchdog needs to move down lockup_detector_init (), while nmi_watchdog does not. So when sdei_watchdog fails to be initialized, nmi_watchdog should not be initialized. [ 0.706631][ T1] SDEI NMI watchdog: Disable SDEI NMI Watchdog in VM [ 0.707405][ T1] ------------[ cut here ]------------ [ 0.708020][ T1] WARNING: CPU: 0 PID: 1 at kernel/watchdog_perf.c:117 hardlockup_detector_event_create+0x24/0x108 [ 0.709230][ T1] Modules linked in: [ 0.709665][ T1] CPU: 0 PID: 1 Comm: swapper/0 Not tainted 6.6.0 #1 [ 0.710700][ T1] Hardware name: QEMU KVM Virtual Machine, BIOS 0.0.0 02/06/2015 [ 0.711625][ T1] pstate: 00400005 (nzcv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) [ 0.712547][ T1] pc : hardlockup_detector_event_create+0x24/0x108 [ 0.713316][ T1] lr : watchdog_hardlockup_probe+0x28/0xa8 [ 0.714010][ T1] sp : ffff8000831cbdc0 [ 0.714501][ T1] pmr_save: 000000e0 [ 0.714957][ T1] x29: ffff8000831cbdc0 x28: 0000000000000000 x27: 0000000000000000 [ 0.715899][ T1] x26: 0000000000000000 x25: 0000000000000000 x24: 0000000000000000 [ 0.716839][ T1] x23: 0000000000000000 x22: 0000000000000000 x21: ffff80008218fab0 [ 0.717775][ T1] x20: ffff8000821af000 x19: ffff0000c0261900 x18: 0000000000000020 [ 0.718713][ T1] x17: 00000000cb551c45 x16: ffff800082625e48 x15: ffffffffffffffff [ 0.719663][ T1] x14: 0000000000000000 x13: 205d315420202020 x12: 5b5d313336363037 [ 0.720607][ T1] x11: 00000000ffff7fff x10: 00000000ffff7fff x9 : ffff800081b5f630 [ 0.721590][ T1] x8 : 00000000000bffe8 x7 : c0000000ffff7fff x6 : 000000000005fff4 [ 0.722528][ T1] x5 : 00000000002bffa8 x4 : 0000000000000000 x3 : 0000000000000000 [ 0.723482][ T1] x2 : 0000000000000000 x1 : 0000000000000140 x0 : ffff0000c02c0000 [ 0.724426][ T1] Call trace: [ 0.724808][ T1] hardlockup_detector_event_create+0x24/0x108 [ 0.725535][ T1] watchdog_hardlockup_probe+0x28/0xa8 [ 0.726174][ T1] lockup_detector_init+0x110/0x158 [ 0.726776][ T1] kernel_init_freeable+0x208/0x288 [ 0.727387][ T1] kernel_init+0x2c/0x200 [ 0.727902][ T1] ret_from_fork+0x10/0x20 [ 0.728420][ T1] ---[ end trace 0000000000000000 ]--- Fixes: f61b11535a0b ("watchdog: Support watchdog_sdei coexist with existing watchdogs") Signed-off-by: Yicong Yang <yangyicong@hisilicon.com> Signed-off-by: Jie Liu <liujie375@h-partners.com> Signed-off-by: Qi Xi <xiqi2@huawei.com> --- kernel/watchdog.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 11102420a2c7..68c0b1d8e467 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -1030,7 +1030,7 @@ void __init lockup_detector_init(void) housekeeping_cpumask(HK_TYPE_TIMER)); if ((!disable_sdei_nmi_watchdog && !sdei_watchdog_hardlockup_probe()) || - !watchdog_hardlockup_probe()) + (disable_sdei_nmi_watchdog && !watchdog_hardlockup_probe())) watchdog_hardlockup_available = true; else allow_lockup_detector_init_retry = true; -- 2.33.0
From: Jinjie Ruan <ruanjinjie@huawei.com> hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I9CHAE -------------------------------- A system stall occurrs when using pseudo NMI with CONFIG_ARM64_NMI closed. If the hardware supports FEAT_NMI, the ALLINT bit in pstate may set or clear on exception trap whether the software enables it or not, so it is not safe to use it to check interrupts_enabled() or fast_interrupts_enabled() when FEAT_NMI not enabled in kernel, so recover it. After applying this patch, the system stall not happen again on hardware with FEAT_NMI feature. Fixes: eefea6156921 ("irqchip/gic-v3: Fix hard LOCKUP caused by NMI being masked") Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com> --- arch/arm64/include/asm/ptrace.h | 5 ++--- arch/arm64/include/uapi/asm/ptrace.h | 1 - 2 files changed, 2 insertions(+), 4 deletions(-) diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h index 81bb2cb17d85..a90ae87ebec5 100644 --- a/arch/arm64/include/asm/ptrace.h +++ b/arch/arm64/include/asm/ptrace.h @@ -240,11 +240,10 @@ static inline void forget_syscall(struct pt_regs *regs) true) #define interrupts_enabled(regs) \ - (!((regs)->pstate & PSR_ALLINT_BIT) && !((regs)->pstate & PSR_I_BIT) && \ - irqs_priority_unmasked(regs)) + (!((regs)->pstate & PSR_I_BIT) && irqs_priority_unmasked(regs)) #define fast_interrupts_enabled(regs) \ - (!((regs)->pstate & PSR_ALLINT_BIT) && !(regs)->pstate & PSR_F_BIT) + (!(regs)->pstate & PSR_F_BIT) static inline unsigned long user_stack_pointer(struct pt_regs *regs) { diff --git a/arch/arm64/include/uapi/asm/ptrace.h b/arch/arm64/include/uapi/asm/ptrace.h index 8a125a1986be..7fa2f7036aa7 100644 --- a/arch/arm64/include/uapi/asm/ptrace.h +++ b/arch/arm64/include/uapi/asm/ptrace.h @@ -48,7 +48,6 @@ #define PSR_D_BIT 0x00000200 #define PSR_BTYPE_MASK 0x00000c00 #define PSR_SSBS_BIT 0x00001000 -#define PSR_ALLINT_BIT 0x00002000 #define PSR_PAN_BIT 0x00400000 #define PSR_UAO_BIT 0x00800000 #define PSR_DIT_BIT 0x01000000 -- 2.33.0
participants (1)
-
Qi Xi