This patch adds the necessary KVM specific code to allow KVM to
support the CPU halting and kicking operations needed by the queue
spinlock PV code.
Two KVM guests of 20 CPU cores (2 nodes) were created for performance
testing in one of the following three configurations:
1) Only 1 VM is active
2) Both VMs are active and they share the same 20 physical CPUs
(200% overcommit)
The tests run included the disk workload of the AIM7 benchmark on
both ext4 and xfs RAM disks at 3000 users on a 3.17 based kernel. The
"ebizzy -m" test and futextest was was also run and its performance
data were recorded. With two VMs running, the "idle=poll" kernel
option was added to simulate a busy guest. If PV qspinlock is not
enabled, unfairlock will be used automically in a guest.
AIM7 XFS Disk Test (no overcommit)
kernel JPM Real Time Sys Time Usr Time
----- --- --------- -------- --------
PV ticketlock 2542373 7.08 98.95 5.44
PV qspinlock 2549575 7.06 98.63 5.40
unfairlock 2616279 6.91 97.05 5.42
AIM7 XFS Disk Test (200% overcommit)
kernel JPM Real Time Sys Time Usr Time
----- --- --------- -------- --------
PV ticketlock 644468 27.93 415.22 6.33
PV qspinlock 645624 27.88 419.84 0.39
unfairlock 695518 25.88 377.40 4.09
AIM7 EXT4 Disk Test (no overcommit)
kernel JPM Real Time Sys Time Usr Time
----- --- --------- -------- --------
PV ticketlock 1995565 9.02 103.67 5.76
PV qspinlock 2011173 8.95 102.15 5.40
unfairlock 2066590 8.71 98.13 5.46
AIM7 EXT4 Disk Test (200% overcommit)
kernel JPM Real Time Sys Time Usr Time
----- --- --------- -------- --------
PV ticketlock 478341 37.63 495.81 30.78
PV qspinlock 474058 37.97 475.74 30.95
unfairlock 560224 32.13 398.43 26.27
For the AIM7 disk workload, both PV ticketlock and qspinlock have
about the same performance. The unfairlock performs slightly better
than the PV lock.
EBIZZY-m Test (no overcommit)
kernel Rec/s Real Time Sys Time Usr Time
----- ----- --------- -------- --------
PV ticketlock 3255 10.00 60.65 3.62
PV qspinlock 3318 10.00 54.27 3.60
unfairlock 2833 10.00 26.66 3.09
EBIZZY-m Test (200% overcommit)
kernel Rec/s Real Time Sys Time Usr Time
----- ----- --------- -------- --------
PV ticketlock 841 10.00 71.03 2.37
PV qspinlock 834 10.00 68.27 2.39
unfairlock 865 10.00 27.08 1.51
futextest (no overcommit)
kernel kops/s
----- ------
PV ticketlock 11523
PV qspinlock 12328
unfairlock 9478
futextest (200% overcommit)
kernel kops/s
----- ------
PV ticketlock 7276
PV qspinlock 7095
unfairlock 5614
The ebizzy and futextest have much higher spinlock contention than
Additional kernel build tests had been done on an 8-socket 32-core
Westmere-EX system (HT off) with an overcommitted KVM PV guest of 60
vCPUs with no NUMA awareness. The kernels is 3.18-2 based. The build
times of a 3.17 kernel with "make -j 60" are shown in the table below:
kernel Elapsed time User time Sys time
------ ------------ --------- --------
PV ticketlock 16m57s 219m17s 189m30s
PV qspinlock 14m47s 188m50s 177m14s
There is a 13% reduction in build time. This is probably caused
by the fact that contended qspinlock produces much less cacheline
contention than contended ticket spinlock and the test system is an
8-socket server.
Signed-off-by: Waiman Long <Waiman.Long@xxxxxx>
---
arch/x86/kernel/kvm.c | 143 ++++++++++++++++++++++++++++++++++++++++++++++++-
kernel/Kconfig.locks | 2 +-
2 files changed, 143 insertions(+), 2 deletions(-)
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 2f1bcc9..29a312d 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -575,7 +575,7 @@ arch_initcall(activate_jump_labels);
#ifdef CONFIG_PARAVIRT_SPINLOCKS
/* Kick a cpu by its apicid. Used to wake up a halted vcpu */
-static void kvm_kick_cpu(int cpu)
+void kvm_kick_cpu(int cpu)
{
int apicid;
unsigned long flags = 0;
@@ -583,7 +583,9 @@ static void kvm_kick_cpu(int cpu)
apicid = per_cpu(x86_cpu_to_apicid, cpu);
kvm_hypercall2(KVM_HC_KICK_CPU, flags, apicid);
}
+PV_CALLEE_SAVE_REGS_THUNK(kvm_kick_cpu);
+#ifndef CONFIG_QUEUE_SPINLOCK
enum kvm_contention_stat {
TAKEN_SLOW,
TAKEN_SLOW_PICKUP,
@@ -811,6 +813,137 @@ static void kvm_unlock_kick(struct arch_spinlock *lock, __ticket_t ticket)
}
}
}
+#else /* !CONFIG_QUEUE_SPINLOCK */
+
+#ifdef CONFIG_KVM_DEBUG_FS
+static struct dentry *d_spin_debug;
+static struct dentry *d_kvm_debug;
+static u32 kick_nohlt_stats; /* Kick but not halt count */
+static u32 halt_qhead_stats; /* Queue head halting count */
+static u32 halt_qnode_stats; /* Queue node halting count */
+static u32 halt_abort_stats; /* Halting abort count */
+static u32 wake_kick_stats; /* Wakeup by kicking count */
+static u32 wake_spur_stats; /* Spurious wakeup count */
+static u64 time_blocked; /* Total blocking time */
+
+static int __init kvm_spinlock_debugfs(void)
+{
+ d_kvm_debug = debugfs_create_dir("kvm-guest", NULL);
+ if (!d_kvm_debug) {
+ printk(KERN_WARNING
+ "Could not create 'kvm' debugfs directory\n");
+ return -ENOMEM;
+ }
+ d_spin_debug = debugfs_create_dir("spinlocks", d_kvm_debug);
+
+ debugfs_create_u32("kick_nohlt_stats",
+ 0644, d_spin_debug, &kick_nohlt_stats);
+ debugfs_create_u32("halt_qhead_stats",
+ 0644, d_spin_debug, &halt_qhead_stats);
+ debugfs_create_u32("halt_qnode_stats",
+ 0644, d_spin_debug, &halt_qnode_stats);
+ debugfs_create_u32("halt_abort_stats",
+ 0644, d_spin_debug, &halt_abort_stats);
+ debugfs_create_u32("wake_kick_stats",
+ 0644, d_spin_debug, &wake_kick_stats);
+ debugfs_create_u32("wake_spur_stats",
+ 0644, d_spin_debug, &wake_spur_stats);
+ debugfs_create_u64("time_blocked",
+ 0644, d_spin_debug, &time_blocked);
+ return 0;
+}
+
+void kvm_lock_stats(int stat_types)
+{
+ if (stat_types & PV_LOCKSTAT_WAKE_KICKED)
+ add_smp(&wake_kick_stats, 1);
+ if (stat_types & PV_LOCKSTAT_WAKE_SPURIOUS)
+ add_smp(&wake_spur_stats, 1);
+ if (stat_types & PV_LOCKSTAT_KICK_NOHALT)
+ add_smp(&kick_nohlt_stats, 1);
+ if (stat_types & PV_LOCKSTAT_HALT_QHEAD)
+ add_smp(&halt_qhead_stats, 1);
+ if (stat_types & PV_LOCKSTAT_HALT_QNODE)
+ add_smp(&halt_qnode_stats, 1);
+ if (stat_types & PV_LOCKSTAT_HALT_ABORT)
+ add_smp(&halt_abort_stats, 1);
+}
+PV_CALLEE_SAVE_REGS_THUNK(kvm_lock_stats);
+
+static inline u64 spin_time_start(void)
+{
+ return sched_clock();
+}
+
+static inline void spin_time_accum_blocked(u64 start)
+{
+ u64 delta;
+
+ delta = sched_clock() - start;
+ add_smp(&time_blocked, delta);
+}
+
+fs_initcall(kvm_spinlock_debugfs);
+
+#else /* CONFIG_KVM_DEBUG_FS */
+static inline void kvm_lock_stats(int stat_types)
+{
+}
+
+static inline u64 spin_time_start(void)
+{
+ return 0;
+}
+
+static inline void spin_time_accum_blocked(u64 start)
+{
+}
+#endif /* CONFIG_KVM_DEBUG_FS */
+
+/*
+ * Halt the current CPU & release it back to the host unless the given
+ * byte pointer has value different from the given one.
+ *
+ * Return 0 if halted, -1 otherwise.
+ */
+int kvm_halt_cpu(u8 *byte, u8 val)
+{
+ unsigned long flags;
+ int ret = -1;
+ u64 start = (u64)-1;
+
+ if (in_nmi())
+ return ret;
+
+ /*
+ * Make sure an interrupt handler can't upset things in a
+ * partially setup state.
+ */
+ local_irq_save(flags);
+ /*
+ * Don't halt if the content of the given byte address differs from
+ * the expected value. A read memory barrier is added to make sure that
+ * the latest value of the byte address is fetched.
+ */
+ smp_rmb();
+ if (*byte != val) {
+ kvm_lock_stats(PV_LOCKSTAT_HALT_ABORT);
+ goto out;
+ }
+ start = spin_time_start();
+ if (arch_irqs_disabled_flags(flags))
+ halt();
+ else
+ safe_halt();
+ ret = 0;
+out:
+ local_irq_restore(flags);
+ if (start != (u64)-1)
+ spin_time_accum_blocked(start);
+ return ret;
+}
+PV_CALLEE_SAVE_REGS_THUNK(kvm_halt_cpu);
+#endif /* !CONFIG_QUEUE_SPINLOCK */
/*
* Setup pv_lock_ops to exploit KVM_FEATURE_PV_UNHALT if present.
@@ -823,8 +956,16 @@ void __init kvm_spinlock_init(void)
if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT))
return;
+#ifdef CONFIG_QUEUE_SPINLOCK
+ pv_lock_ops.kick_cpu = kvm_kick_cpu;
+ pv_lock_ops.lockwait = PV_CALLEE_SAVE(kvm_halt_cpu);
+#ifdef CONFIG_KVM_DEBUG_FS
+ pv_lock_ops.lockstat = PV_CALLEE_SAVE(kvm_lock_stats);
+#endif
+#else
pv_lock_ops.lock_spinning = PV_CALLEE_SAVE(kvm_lock_spinning);
pv_lock_ops.unlock_kick = kvm_unlock_kick;
+#endif
}
static __init int kvm_spinlock_init_jump(void)
diff --git a/kernel/Kconfig.locks b/kernel/Kconfig.locks
index 9215fab..57301de 100644
--- a/kernel/Kconfig.locks
+++ b/kernel/Kconfig.locks
@@ -236,7 +236,7 @@ config ARCH_USE_QUEUE_SPINLOCK
config QUEUE_SPINLOCK
def_bool y if ARCH_USE_QUEUE_SPINLOCK
- depends on SMP && !PARAVIRT_SPINLOCKS
+ depends on SMP && (!PARAVIRT_SPINLOCKS || !XEN)
config ARCH_USE_QUEUE_RWLOCK
bool
--
1.7.1
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
