summaryrefslogtreecommitdiffstats
path: root/arch/x86/power
diff options
context:
space:
mode:
authorJiri Kosina <jkosina@suse.cz>2019-05-30 00:09:39 +0200
committerRafael J. Wysocki <rafael.j.wysocki@intel.com>2019-06-03 12:02:03 +0200
commitec527c318036a65a083ef68d8ba95789d2212246 (patch)
tree175e0ca9ba0d214c469b7f03aa2baa567d99be7b /arch/x86/power
parentbe1fcde604e429691771ce70230668af8097e29b (diff)
downloadlinux-ec527c318036a65a083ef68d8ba95789d2212246.tar.bz2
x86/power: Fix 'nosmt' vs hibernation triple fault during resume
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that is being resumed, which in turn means that all the HT siblings are all of a sudden mwaiting on address which is no longer valid.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+ <stable@vger.kernel.org> # v4.19+ Debugged-by: Thomas Gleixner <tglx@linutronix.de> Fixes: 0cc3cd21657b ("cpu/hotplug: Boot HT siblings at least once") Signed-off-by: Jiri Kosina <jkosina@suse.cz> Acked-by: Pavel Machek <pavel@ucw.cz> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Diffstat (limited to 'arch/x86/power')
-rw-r--r--arch/x86/power/cpu.c10
-rw-r--r--arch/x86/power/hibernate.c33
2 files changed, 43 insertions, 0 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.c b/arch/x86/power/hibernate.c
index 4845b8c7be7f..fc413717a45f 100644
--- a/arch/x86/power/hibernate.c
+++ b/arch/x86/power/hibernate.c
@@ -11,6 +11,7 @@
#include <linux/suspend.h>
#include <linux/scatterlist.h>
#include <linux/kdebug.h>
+#include <linux/cpu.h>
#include <crypto/hash.h>
@@ -245,3 +246,35 @@ out:
__flush_tlb_all();
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;
+}