From b9284404b140ebd93ee732ab562bb5a8a7e322be Mon Sep 17 00:00:00 2001 From: Jiri Kosina Date: Thu, 30 May 2019 00:09:39 +0200 Subject: [PATCH] x86/power: Fix 'nosmt' vs hibernation triple fault during resume commit ec527c318036a65a083ef68d8ba95789d2212246 upstream. As explained in 0cc3cd21657b ("cpu/hotplug: Boot HT siblings at least once") we always, no matter what, have to bring up x86 HT siblings during boot at least once in order to avoid first MCE bringing the system to its knees. That means that whenever 'nosmt' is supplied on the kernel command-line, all the HT siblings are as a result sitting in mwait or cpudile after going through the online-offline cycle at least once. This causes a serious issue though when a kernel, which saw 'nosmt' on its commandline, is going to perform resume from hibernation: if the resume from the hibernated image is successful, cr3 is flipped in order to point to the address space of the kernel that is being resumed, which in turn means that all the HT siblings are all of a sudden mwaiting on address which is no longer valid. That results in triple fault shortly after cr3 is switched, and machine reboots. Fix this by always waking up all the SMT siblings before initiating the 'restore from hibernation' process; this guarantees that all the HT siblings will be properly carried over to the resumed kernel waiting in resume_play_dead(), and acted upon accordingly afterwards, based on the target kernel configuration. Symmetricaly, the resumed kernel has to push the SMT siblings to mwait again in case it has SMT disabled; this means it has to online all the siblings when resuming (so that they come out of hlt) and offline them again to let them reach mwait. Cc: 4.19+ # v4.19+ Debugged-by: Thomas Gleixner Fixes: 0cc3cd21657b ("cpu/hotplug: Boot HT siblings at least once") Signed-off-by: Jiri Kosina Acked-by: Pavel Machek Reviewed-by: Thomas Gleixner Reviewed-by: Josh Poimboeuf Signed-off-by: Rafael J. Wysocki Signed-off-by: Greg Kroah-Hartman --- arch/x86/power/cpu.c | 10 ++++++++++ arch/x86/power/hibernate_64.c | 33 +++++++++++++++++++++++++++++++++ include/linux/cpu.h | 4 ++++ kernel/cpu.c | 4 ++-- kernel/power/hibernate.c | 9 +++++++++ 5 files changed, 58 insertions(+), 2 deletions(-) diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index a7d966964c6f..513ce09e9950 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -299,7 +299,17 @@ int hibernate_resume_nonboot_cpu_disable(void) * address in its instruction pointer may not be possible to resolve * any more at that point (the page tables used by it previously may * have been overwritten by hibernate image data). + * + * First, make sure that we wake up all the potentially disabled SMT + * threads which have been initially brought up and then put into + * mwait/cpuidle sleep. + * Those will be put to proper (not interfering with hibernation + * resume) sleep afterwards, and the resumed kernel will decide itself + * what to do with them. */ + ret = cpuhp_smt_enable(); + if (ret) + return ret; smp_ops.play_dead = resume_play_dead; ret = disable_nonboot_cpus(); smp_ops.play_dead = play_dead; diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c index 0ef5e5204968..9c80966c80ba 100644 --- a/arch/x86/power/hibernate_64.c +++ b/arch/x86/power/hibernate_64.c @@ -13,6 +13,7 @@ #include #include #include +#include #include @@ -347,3 +348,35 @@ int arch_hibernation_header_restore(void *addr) return 0; } + +int arch_resume_nosmt(void) +{ + int ret = 0; + /* + * We reached this while coming out of hibernation. This means + * that SMT siblings are sleeping in hlt, as mwait is not safe + * against control transition during resume (see comment in + * hibernate_resume_nonboot_cpu_disable()). + * + * If the resumed kernel has SMT disabled, we have to take all the + * SMT siblings out of hlt, and offline them again so that they + * end up in mwait proper. + * + * Called with hotplug disabled. + */ + cpu_hotplug_enable(); + if (cpu_smt_control == CPU_SMT_DISABLED || + cpu_smt_control == CPU_SMT_FORCE_DISABLED) { + enum cpuhp_smt_control old = cpu_smt_control; + + ret = cpuhp_smt_enable(); + if (ret) + goto out; + ret = cpuhp_smt_disable(old); + if (ret) + goto out; + } +out: + cpu_hotplug_disable(); + return ret; +} diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 9573b5b0fc6f..efc48efb0ec6 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -191,10 +191,14 @@ enum cpuhp_smt_control { extern enum cpuhp_smt_control cpu_smt_control; extern void cpu_smt_disable(bool force); extern void cpu_smt_check_topology(void); +extern int cpuhp_smt_enable(void); +extern int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval); #else # define cpu_smt_control (CPU_SMT_ENABLED) static inline void cpu_smt_disable(bool force) { } static inline void cpu_smt_check_topology(void) { } +static inline int cpuhp_smt_enable(void) { return 0; } +static inline int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval) { return 0; } #endif /* diff --git a/kernel/cpu.c b/kernel/cpu.c index 6503ca8d59a7..127a69b8b192 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -2054,7 +2054,7 @@ static void cpuhp_online_cpu_device(unsigned int cpu) kobject_uevent(&dev->kobj, KOBJ_ONLINE); } -static int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval) +int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval) { int cpu, ret = 0; @@ -2088,7 +2088,7 @@ static int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval) return ret; } -static int cpuhp_smt_enable(void) +int cpuhp_smt_enable(void) { int cpu, ret = 0; diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index a5c36e9c56a6..2d6d14ad7b4f 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -258,6 +258,11 @@ void swsusp_show_speed(ktime_t start, ktime_t stop, (kps % 1000) / 10); } +__weak int arch_resume_nosmt(void) +{ + return 0; +} + /** * create_image - Create a hibernation image. * @platform_mode: Whether or not to use the platform driver. @@ -322,6 +327,10 @@ static int create_image(int platform_mode) Enable_cpus: enable_nonboot_cpus(); + /* Allow architectures to do nosmt-specific post-resume dances */ + if (!in_suspend) + error = arch_resume_nosmt(); + Platform_finish: platform_finish(platform_mode); -- 2.20.1