From 9cc63f8bcd560c760d0b12e15bba8f81c86237cf Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 14 Aug 2026 15:43:51 -0700 Subject: Merge branches 'expcb.2026.07.24a', 'misc.2026.07.30a', 'rcu-tasks.2026.07.30a', 'srcu.2026.08.11a' and 'torture.2026.08.14a' into HEAD Changes: Make expedited grace periods expedite normal RCU callbacks Miscellaneous fixes: * Improve diagnostic output with character task states. * Mark accesses to inform KCSAN of concurrency design. * Move from kmalloc() to kmalloc_obj(). * Documentation updates. * Improve handling of RCU deferred quiescent states. * Clean up unused function arguments and structure fields. * Reduce show_rcu_gp_kthreads() stack space. Tasks RCU updates: * Clean up after SRCU re-implementation of Tasks Trace RCU. * Mark accesses to inform KCSAN of concurrency design. * Add ->lazy_timer status to diagnostic output. * Remove an unnecessary memory barrier. * Fix a data race, courtesy of KCSAN. * Documentation updates. * Convert cond_resched_tasks_rcu_qs() from macro to static inline function. SRCU updates: * Add Rust helpers for SRCU. * Avoid losing queued work at cleanup_srcu_struct() time. Torture-test updates: * Preparation work for immediate RCU priority deboosting. * Test RCU readers from real interrupt handlers (as opposed to softirq). * Simplify code through use of cpumask_next_wrap(). * Improve diagnostic output with character task states. * Add rcutorture.nwriters parameter to allow lightweight stall testing, and rcutorture.stall_only to make doing so easier. * Test an RCU Tasks Trace grace period implying an RCU grace period. * Make RCU Tasks Trace torturing track reader batches. * Fix a data race, courtesy of KCSAN. * Plug a shuffle_tmp_mask memory leak on kthread spawn failure. --- lib/nmi_backtrace.c | 132 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 132 insertions(+) create mode 100644 lib/nmi_backtrace.c (limited to 'lib/nmi_backtrace.c') diff --git a/lib/nmi_backtrace.c b/lib/nmi_backtrace.c new file mode 100644 index 000000000..a3bfa9360 --- /dev/null +++ b/lib/nmi_backtrace.c @@ -0,0 +1,132 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * NMI backtrace support + * + * Gratuitously copied from arch/x86/kernel/apic/hw_nmi.c by Russell King, + * with the following header: + * + * HW NMI watchdog support + * + * started by Don Zickus, Copyright (C) 2010 Red Hat, Inc. + * + * Arch specific calls to support NMI watchdog + * + * Bits copied from original nmi.c file + */ +#include +#include +#include +#include +#include +#include +#include + +#ifdef arch_trigger_cpumask_backtrace +/* For reliability, we're prepared to waste bits here. */ +static DECLARE_BITMAP(backtrace_mask, NR_CPUS) __read_mostly; + +/* "in progress" flag of arch_trigger_cpumask_backtrace */ +static unsigned long backtrace_flag; + +#define NMI_BT_TIMEOUT_SEC 10 + +/* + * When raise() is called it will be passed a pointer to the + * backtrace_mask. Architectures that call nmi_cpu_backtrace() + * directly from their raise() functions may rely on the mask + * they are passed being updated as a side effect of this call. + */ +void nmi_trigger_cpumask_backtrace(const cpumask_t *mask, + int exclude_cpu, + void (*raise)(cpumask_t *mask)) +{ + int i, this_cpu = get_cpu(); + + if (test_and_set_bit(0, &backtrace_flag)) { + /* + * If there is already a trigger_all_cpu_backtrace() in progress + * (backtrace_flag == 1), don't output double cpu dump infos. + */ + put_cpu(); + return; + } + + cpumask_copy(to_cpumask(backtrace_mask), mask); + if (exclude_cpu != -1) + cpumask_clear_cpu(exclude_cpu, to_cpumask(backtrace_mask)); + + /* + * Don't try to send an NMI to this cpu; it may work on some + * architectures, but on others it may not, and we'll get + * information at least as useful just by doing a dump_stack() here. + * Note that nmi_cpu_backtrace(NULL) will clear the cpu bit. + */ + if (cpumask_test_cpu(this_cpu, to_cpumask(backtrace_mask))) + nmi_cpu_backtrace(NULL); + + if (!cpumask_empty(to_cpumask(backtrace_mask))) { + pr_info("Sending NMI from CPU %d to CPUs %*pbl:\n", + this_cpu, nr_cpumask_bits, to_cpumask(backtrace_mask)); + nmi_backtrace_stall_snap(to_cpumask(backtrace_mask)); + raise(to_cpumask(backtrace_mask)); + } + + /* Wait for up to NMI_BT_TIMEOUT_SEC seconds for all CPUs to do the backtrace */ + for (i = 0; i < NMI_BT_TIMEOUT_SEC * 1000; i++) { + if (cpumask_empty(to_cpumask(backtrace_mask))) + break; + mdelay(1); + touch_softlockup_watchdog(); + } + + if (!cpumask_empty(to_cpumask(backtrace_mask))) { + pr_warn("After " __stringify(NMI_BT_TIMEOUT_SEC) " seconds, these CPUS still haven't responded to the NMI: %*pbl\n", + cpumask_pr_args(to_cpumask(backtrace_mask))); + + nmi_backtrace_stall_check(to_cpumask(backtrace_mask)); + } + + /* + * Force flush any remote buffers that might be stuck in IRQ context + * and therefore could not run their irq_work. + */ + printk_trigger_flush(); + + clear_bit_unlock(0, &backtrace_flag); + put_cpu(); +} + +// Dump stacks even for idle CPUs. +static bool backtrace_idle; +module_param(backtrace_idle, bool, 0644); + +bool nmi_cpu_backtrace(struct pt_regs *regs) +{ + int cpu = smp_processor_id(); + unsigned long flags; + + if (cpumask_test_cpu(cpu, to_cpumask(backtrace_mask))) { + /* + * Allow nested NMI backtraces while serializing + * against other CPUs. + */ + printk_cpu_sync_get_irqsave(flags); + if (!READ_ONCE(backtrace_idle) && regs && cpu_in_idle(instruction_pointer(regs))) { + pr_warn("NMI backtrace for cpu %d skipped: idling at %pS\n", + cpu, (void *)instruction_pointer(regs)); + } else { + pr_warn("NMI backtrace for cpu %d\n", cpu); + if (regs) + show_regs(regs); + else + dump_stack(); + } + printk_cpu_sync_put_irqrestore(flags); + cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask)); + return true; + } + + return false; +} +NOKPROBE_SYMBOL(nmi_cpu_backtrace); +#endif -- cgit v1.3.1