x86: kvm: Revert "remove sched notifier for cross-cpu migrations"

The following point:

    2. per-CPU pvclock time info is updated if the
       underlying CPU changes.

Is not true anymore since "KVM: x86: update pvclock area conditionally,
on cpu migration".

Add task migration notification back.

Problem noticed by Andy Lutomirski.

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
CC: stable@kernel.org # 3.11+

3 files changed, 53 insertions, 8 deletions

diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h
index d6b078e9fa28..25b1cc07d496 100644
--- a/arch/x86/include/asm/pvclock.h
+++ b/arch/x86/include/asm/pvclock.h
@@ -95,6 +95,7 @@ unsigned __pvclock_read_cycles(const struct pvclock_vcpu_time_info *src,
 
 struct pvclock_vsyscall_time_info {
         struct pvclock_vcpu_time_info pvti;
+        u32 migrate_count;
 } __attribute__((__aligned__(SMP_CACHE_BYTES)));
 
 #define PVTI_SIZE sizeof(struct pvclock_vsyscall_time_info)
diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c
index 2f355d229a58..e5ecd20e72dd 100644
--- a/arch/x86/kernel/pvclock.c
+++ b/arch/x86/kernel/pvclock.c
@@ -141,7 +141,46 @@ void pvclock_read_wallclock(struct pvclock_wall_clock *wall_clock,
         set_normalized_timespec(ts, now.tv_sec, now.tv_nsec);
 }
 
+static struct pvclock_vsyscall_time_info *pvclock_vdso_info;
+
+static struct pvclock_vsyscall_time_info *
+pvclock_get_vsyscall_user_time_info(int cpu)
+{
+        if (!pvclock_vdso_info) {
+                BUG();
+                return NULL;
+        }
+
+        return &pvclock_vdso_info[cpu];
+}
+
+struct pvclock_vcpu_time_info *pvclock_get_vsyscall_time_info(int cpu)
+{
+        return &pvclock_get_vsyscall_user_time_info(cpu)->pvti;
+}
+
 #ifdef CONFIG_X86_64
+static int pvclock_task_migrate(struct notifier_block *nb, unsigned long l,
+                                void *v)
+{
+        struct task_migration_notifier *mn = v;
+        struct pvclock_vsyscall_time_info *pvti;
+
+        pvti = pvclock_get_vsyscall_user_time_info(mn->from_cpu);
+
+        /* this is NULL when pvclock vsyscall is not initialized */
+        if (unlikely(pvti == NULL))
+                return NOTIFY_DONE;
+
+        pvti->migrate_count++;
+
+        return NOTIFY_DONE;
+}
+
+static struct notifier_block pvclock_migrate = {
+        .notifier_call = pvclock_task_migrate,
+};
+
 /*
  * Initialize the generic pvclock vsyscall state.  This will allocate
  * a/some page(s) for the per-vcpu pvclock information, set up a
@@ -155,12 +194,17 @@ int __init pvclock_init_vsyscall(struct pvclock_vsyscall_time_info *i,
 
         WARN_ON (size != PVCLOCK_VSYSCALL_NR_PAGES*PAGE_SIZE);
 
+        pvclock_vdso_info = i;
+
         for (idx = 0; idx <= (PVCLOCK_FIXMAP_END-PVCLOCK_FIXMAP_BEGIN); idx++) {
                 __set_fixmap(PVCLOCK_FIXMAP_BEGIN + idx,
                              __pa(i) + (idx*PAGE_SIZE),
                              PAGE_KERNEL_VVAR);
         }
 
+
+        register_task_migration_notifier(&pvclock_migrate);
+
         return 0;
 }
 #endif
diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c
index 9793322751e0..30933760ee5f 100644
--- a/arch/x86/vdso/vclock_gettime.c
+++ b/arch/x86/vdso/vclock_gettime.c
@@ -82,18 +82,15 @@ static notrace cycle_t vread_pvclock(int *mode)
         cycle_t ret;
         u64 last;
         u32 version;
+        u32 migrate_count;
         u8 flags;
         unsigned cpu, cpu1;
 
 
         /*
-         * Note: hypervisor must guarantee that:
-         * 1. cpu ID number maps 1:1 to per-CPU pvclock time info.
-         * 2. that per-CPU pvclock time info is updated if the
-         *    underlying CPU changes.
-         * 3. that version is increased whenever underlying CPU
-         *    changes.
-         *
+         * When looping to get a consistent (time-info, tsc) pair, we
+         * also need to deal with the possibility we can switch vcpus,
+         * so make sure we always re-fetch time-info for the current vcpu.
          */
         do {
                 cpu = __getcpu() & VGETCPU_CPU_MASK;
@@ -104,6 +101,8 @@ static notrace cycle_t vread_pvclock(int *mode)
 
                 pvti = get_pvti(cpu);
 
+                migrate_count = pvti->migrate_count;
+
                 version = __pvclock_read_cycles(&pvti->pvti, &ret, &flags);
 
                 /*
@@ -115,7 +114,8 @@ static notrace cycle_t vread_pvclock(int *mode)
                 cpu1 = __getcpu() & VGETCPU_CPU_MASK;
         } while (unlikely(cpu != cpu1 ||
                           (pvti->pvti.version & 1) ||
-                          pvti->pvti.version != version));
+                          pvti->pvti.version != version ||
+                          pvti->migrate_count != migrate_count));
 
         if (unlikely(!(flags & PVCLOCK_TSC_STABLE_BIT)))
                 *mode = VCLOCK_NONE;