diff options
author | Linus Torvalds | 2020-06-01 12:56:29 -0700 |
---|---|---|
committer | Linus Torvalds | 2020-06-01 12:56:29 -0700 |
commit | 2227e5b21aec6c5f7f6491352f0c19fd02d19418 (patch) | |
tree | 098e17fe2c1ec5fc753c9ae7983d2f8466914c0e /arch/x86/kernel/cpu | |
parent | 0bd957eb11cfeef23fcc240edde6dfe431731e69 (diff) | |
parent | cb3cb6733fbd8fd8d2c716095fdca42dadba2063 (diff) |
Merge tag 'core-rcu-2020-06-01' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull RCU updates from Ingo Molnar:
"The RCU updates for this cycle were:
- RCU-tasks update, including addition of RCU Tasks Trace for BPF use
and TASKS_RUDE_RCU
- kfree_rcu() updates.
- Remove scheduler locking restriction
- RCU CPU stall warning updates.
- Torture-test updates.
- Miscellaneous fixes and other updates"
* tag 'core-rcu-2020-06-01' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (103 commits)
rcu: Allow for smp_call_function() running callbacks from idle
rcu: Provide rcu_irq_exit_check_preempt()
rcu: Abstract out rcu_irq_enter_check_tick() from rcu_nmi_enter()
rcu: Provide __rcu_is_watching()
rcu: Provide rcu_irq_exit_preempt()
rcu: Make RCU IRQ enter/exit functions rely on in_nmi()
rcu/tree: Mark the idle relevant functions noinstr
x86: Replace ist_enter() with nmi_enter()
x86/mce: Send #MC singal from task work
x86/entry: Get rid of ist_begin/end_non_atomic()
sched,rcu,tracing: Avoid tracing before in_nmi() is correct
sh/ftrace: Move arch_ftrace_nmi_{enter,exit} into nmi exception
lockdep: Always inline lockdep_{off,on}()
hardirq/nmi: Allow nested nmi_enter()
arm64: Prepare arch_nmi_enter() for recursion
printk: Disallow instrumenting print_nmi_enter()
printk: Prepare for nested printk_nmi_enter()
rcutorture: Convert ULONG_CMP_LT() to time_before()
torture: Add a --kasan argument
torture: Save a few lines by using config_override_param initially
...
Diffstat (limited to 'arch/x86/kernel/cpu')
-rw-r--r-- | arch/x86/kernel/cpu/mce/core.c | 65 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/mce/p5.c | 5 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/mce/winchip.c | 5 |
3 files changed, 43 insertions, 32 deletions
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 54165f3569e8..e9265e2f28c9 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -42,6 +42,8 @@ #include <linux/export.h> #include <linux/jump_label.h> #include <linux/set_memory.h> +#include <linux/task_work.h> +#include <linux/hardirq.h> #include <asm/intel-family.h> #include <asm/processor.h> @@ -1086,23 +1088,6 @@ static void mce_clear_state(unsigned long *toclear) } } -static int do_memory_failure(struct mce *m) -{ - int flags = MF_ACTION_REQUIRED; - int ret; - - pr_err("Uncorrected hardware memory error in user-access at %llx", m->addr); - if (!(m->mcgstatus & MCG_STATUS_RIPV)) - flags |= MF_MUST_KILL; - ret = memory_failure(m->addr >> PAGE_SHIFT, flags); - if (ret) - pr_err("Memory error not recovered"); - else - set_mce_nospec(m->addr >> PAGE_SHIFT); - return ret; -} - - /* * Cases where we avoid rendezvous handler timeout: * 1) If this CPU is offline. @@ -1204,6 +1189,29 @@ static void __mc_scan_banks(struct mce *m, struct mce *final, *m = *final; } +static void kill_me_now(struct callback_head *ch) +{ + force_sig(SIGBUS); +} + +static void kill_me_maybe(struct callback_head *cb) +{ + struct task_struct *p = container_of(cb, struct task_struct, mce_kill_me); + int flags = MF_ACTION_REQUIRED; + + pr_err("Uncorrected hardware memory error in user-access at %llx", p->mce_addr); + if (!(p->mce_status & MCG_STATUS_RIPV)) + flags |= MF_MUST_KILL; + + if (!memory_failure(p->mce_addr >> PAGE_SHIFT, flags)) { + set_mce_nospec(p->mce_addr >> PAGE_SHIFT); + return; + } + + pr_err("Memory error not recovered"); + kill_me_now(cb); +} + /* * The actual machine check handler. This only handles real * exceptions when something got corrupted coming in through int 18. @@ -1222,7 +1230,7 @@ static void __mc_scan_banks(struct mce *m, struct mce *final, * backing the user stack, tracing that reads the user stack will cause * potentially infinite recursion. */ -void notrace do_machine_check(struct pt_regs *regs, long error_code) +void noinstr do_machine_check(struct pt_regs *regs, long error_code) { DECLARE_BITMAP(valid_banks, MAX_NR_BANKS); DECLARE_BITMAP(toclear, MAX_NR_BANKS); @@ -1259,7 +1267,7 @@ void notrace do_machine_check(struct pt_regs *regs, long error_code) if (__mc_check_crashing_cpu(cpu)) return; - ist_enter(regs); + nmi_enter(); this_cpu_inc(mce_exception_count); @@ -1352,23 +1360,24 @@ void notrace do_machine_check(struct pt_regs *regs, long error_code) /* Fault was in user mode and we need to take some action */ if ((m.cs & 3) == 3) { - ist_begin_non_atomic(regs); - local_irq_enable(); - - if (kill_it || do_memory_failure(&m)) - force_sig(SIGBUS); - local_irq_disable(); - ist_end_non_atomic(); + /* If this triggers there is no way to recover. Die hard. */ + BUG_ON(!on_thread_stack() || !user_mode(regs)); + + current->mce_addr = m.addr; + current->mce_status = m.mcgstatus; + current->mce_kill_me.func = kill_me_maybe; + if (kill_it) + current->mce_kill_me.func = kill_me_now; + task_work_add(current, ¤t->mce_kill_me, true); } else { if (!fixup_exception(regs, X86_TRAP_MC, error_code, 0)) mce_panic("Failed kernel mode recovery", &m, msg); } out_ist: - ist_exit(regs); + nmi_exit(); } EXPORT_SYMBOL_GPL(do_machine_check); -NOKPROBE_SYMBOL(do_machine_check); #ifndef CONFIG_MEMORY_FAILURE int memory_failure(unsigned long pfn, int flags) diff --git a/arch/x86/kernel/cpu/mce/p5.c b/arch/x86/kernel/cpu/mce/p5.c index 4ae6df556526..5ee94aa1b766 100644 --- a/arch/x86/kernel/cpu/mce/p5.c +++ b/arch/x86/kernel/cpu/mce/p5.c @@ -7,6 +7,7 @@ #include <linux/kernel.h> #include <linux/types.h> #include <linux/smp.h> +#include <linux/hardirq.h> #include <asm/processor.h> #include <asm/traps.h> @@ -24,7 +25,7 @@ static void pentium_machine_check(struct pt_regs *regs, long error_code) { u32 loaddr, hi, lotype; - ist_enter(regs); + nmi_enter(); rdmsr(MSR_IA32_P5_MC_ADDR, loaddr, hi); rdmsr(MSR_IA32_P5_MC_TYPE, lotype, hi); @@ -39,7 +40,7 @@ static void pentium_machine_check(struct pt_regs *regs, long error_code) add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE); - ist_exit(regs); + nmi_exit(); } /* Set up machine check reporting for processors with Intel style MCE: */ diff --git a/arch/x86/kernel/cpu/mce/winchip.c b/arch/x86/kernel/cpu/mce/winchip.c index a30ea13cccc2..b3938c195365 100644 --- a/arch/x86/kernel/cpu/mce/winchip.c +++ b/arch/x86/kernel/cpu/mce/winchip.c @@ -6,6 +6,7 @@ #include <linux/interrupt.h> #include <linux/kernel.h> #include <linux/types.h> +#include <linux/hardirq.h> #include <asm/processor.h> #include <asm/traps.h> @@ -18,12 +19,12 @@ /* Machine check handler for WinChip C6: */ static void winchip_machine_check(struct pt_regs *regs, long error_code) { - ist_enter(regs); + nmi_enter(); pr_emerg("CPU0: Machine Check Exception.\n"); add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE); - ist_exit(regs); + nmi_exit(); } /* Set up machine check reporting on the Winchip C6 series */ |