From acb04058de49458010c44bb35b849d45113fd668 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 19 Jan 2017 14:36:33 +0100 Subject: sched/clock: Fix hotplug crash Mike reported that he could trigger the WARN_ON_ONCE() in set_sched_clock_stable() using hotplug. This exposed a fundamental problem with the interface, we should never mark the TSC stable if we ever find it to be unstable. Therefore set_sched_clock_stable() is a broken interface. The reason it existed is that not having it is a pain, it means all relevant architecture code needs to call clear_sched_clock_stable() where appropriate. Of the three architectures that select HAVE_UNSTABLE_SCHED_CLOCK ia64 and parisc are trivial in that they never called set_sched_clock_stable(), so add an unconditional call to clear_sched_clock_stable() to them. For x86 the story is a lot more involved, and what this patch tries to do is ensure we preserve the status quo. So even is Cyrix or Transmeta have usable TSC they never called set_sched_clock_stable() so they now get an explicit mark unstable. Reported-by: Mike Galbraith Signed-off-by: Peter Zijlstra (Intel) Cc: Borislav Petkov Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Fixes: 9881b024b7d7 ("sched/clock: Delay switching sched_clock to stable") Link: http://lkml.kernel.org/r/20170119133633.GB6536@twins.programming.kicks-ass.net Signed-off-by: Ingo Molnar --- arch/ia64/kernel/setup.c | 2 ++ arch/parisc/kernel/setup.c | 2 ++ arch/x86/kernel/cpu/amd.c | 6 ++++-- arch/x86/kernel/cpu/centaur.c | 6 ++++-- arch/x86/kernel/cpu/common.c | 3 +++ arch/x86/kernel/cpu/cyrix.c | 2 ++ arch/x86/kernel/cpu/intel.c | 6 ++++-- arch/x86/kernel/cpu/transmeta.c | 3 +++ arch/x86/kernel/kvmclock.c | 2 +- 9 files changed, 25 insertions(+), 7 deletions(-) (limited to 'arch') diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c index 7ec7acc844c2..c483ece3eb84 100644 --- a/arch/ia64/kernel/setup.c +++ b/arch/ia64/kernel/setup.c @@ -619,6 +619,8 @@ setup_arch (char **cmdline_p) check_sal_cache_flush(); #endif paging_init(); + + clear_sched_clock_stable(); } /* diff --git a/arch/parisc/kernel/setup.c b/arch/parisc/kernel/setup.c index 2e66a887788e..068ed3607bac 100644 --- a/arch/parisc/kernel/setup.c +++ b/arch/parisc/kernel/setup.c @@ -36,6 +36,7 @@ #undef PCI_DEBUG #include #include +#include #include #include @@ -176,6 +177,7 @@ void __init setup_arch(char **cmdline_p) conswitchp = &dummy_con; /* we use do_take_over_console() later ! */ #endif + clear_sched_clock_stable(); } /* diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 71cae73a5076..1bb253a6ee4d 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -548,8 +548,10 @@ static void early_init_amd(struct cpuinfo_x86 *c) if (c->x86_power & (1 << 8)) { set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC); set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC); - if (!check_tsc_unstable()) - set_sched_clock_stable(); + if (check_tsc_unstable()) + clear_sched_clock_stable(); + } else { + clear_sched_clock_stable(); } /* Bit 12 of 8000_0007 edx is accumulated power mechanism. */ diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c index 1661d8ec9280..2c234a6d94c4 100644 --- a/arch/x86/kernel/cpu/centaur.c +++ b/arch/x86/kernel/cpu/centaur.c @@ -1,5 +1,5 @@ -#include -#include + +#include #include #include @@ -104,6 +104,8 @@ static void early_init_centaur(struct cpuinfo_x86 *c) #ifdef CONFIG_X86_64 set_cpu_cap(c, X86_FEATURE_SYSENTER32); #endif + + clear_sched_clock_stable(); } static void init_centaur(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index dc1697ca5191..3457186275a0 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -83,6 +83,7 @@ static void default_init(struct cpuinfo_x86 *c) strcpy(c->x86_model_id, "386"); } #endif + clear_sched_clock_stable(); } static const struct cpu_dev default_cpu = { @@ -1055,6 +1056,8 @@ static void identify_cpu(struct cpuinfo_x86 *c) */ if (this_cpu->c_init) this_cpu->c_init(c); + else + clear_sched_clock_stable(); /* Disable the PN if appropriate */ squash_the_stupid_serial_number(c); diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c index bd9dcd6b712d..47416f959a48 100644 --- a/arch/x86/kernel/cpu/cyrix.c +++ b/arch/x86/kernel/cpu/cyrix.c @@ -9,6 +9,7 @@ #include #include #include +#include #include "cpu.h" @@ -183,6 +184,7 @@ static void early_init_cyrix(struct cpuinfo_x86 *c) set_cpu_cap(c, X86_FEATURE_CYRIX_ARR); break; } + clear_sched_clock_stable(); } static void init_cyrix(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index fcd484d2bb03..26eaff4907b2 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -124,8 +124,10 @@ static void early_init_intel(struct cpuinfo_x86 *c) if (c->x86_power & (1 << 8)) { set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC); set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC); - if (!check_tsc_unstable()) - set_sched_clock_stable(); + if (check_tsc_unstable()) + clear_sched_clock_stable(); + } else { + clear_sched_clock_stable(); } /* Penwell and Cloverview have the TSC which doesn't sleep on S3 */ diff --git a/arch/x86/kernel/cpu/transmeta.c b/arch/x86/kernel/cpu/transmeta.c index 34178564be2a..c1ea5b999839 100644 --- a/arch/x86/kernel/cpu/transmeta.c +++ b/arch/x86/kernel/cpu/transmeta.c @@ -1,4 +1,5 @@ #include +#include #include #include #include @@ -14,6 +15,8 @@ static void early_init_transmeta(struct cpuinfo_x86 *c) if (xlvl >= 0x80860001) c->x86_capability[CPUID_8086_0001_EDX] = cpuid_edx(0x80860001); } + + clear_sched_clock_stable(); } static void init_transmeta(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index 2a5cafdf8808..542710b99f52 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -107,12 +107,12 @@ static inline void kvm_sched_clock_init(bool stable) { if (!stable) { pv_time_ops.sched_clock = kvm_clock_read; + clear_sched_clock_stable(); return; } kvm_sched_clock_offset = kvm_clock_read(); pv_time_ops.sched_clock = kvm_sched_clock_read; - set_sched_clock_stable(); printk(KERN_INFO "kvm-clock: using sched offset of %llu cycles\n", kvm_sched_clock_offset); -- cgit v1.2.3