summaryrefslogtreecommitdiff
path: root/drivers
diff options
context:
space:
mode:
authorMarcelo Tosatti <mtosatti@redhat.com>2019-07-03 20:51:28 -0300
committerRafael J. Wysocki <rafael.j.wysocki@intel.com>2019-07-30 17:27:37 +0200
commit2cffe9f6b96fece065ee8522673c90e92ef2085d (patch)
tree9d8f97f6710e7abfd7698705ba75bad51401be6f /drivers
parent7d4daeedd575bbc3c40c87fc6708a8b88c50fe7e (diff)
cpuidle: add haltpoll governor
The cpuidle_haltpoll governor, in conjunction with the haltpoll cpuidle driver, allows guest vcpus to poll for a specified amount of time before halting. This provides the following benefits to host side polling: 1) The POLL flag is set while polling is performed, which allows a remote vCPU to avoid sending an IPI (and the associated cost of handling the IPI) when performing a wakeup. 2) The VM-exit cost can be avoided. The downside of guest side polling is that polling is performed even with other runnable tasks in the host. Results comparing halt_poll_ns and server/client application where a small packet is ping-ponged: host --> 31.33 halt_poll_ns=300000 / no guest busy spin --> 33.40 (93.8%) halt_poll_ns=0 / guest_halt_poll_ns=300000 --> 32.73 (95.7%) For the SAP HANA benchmarks (where idle_spin is a parameter of the previous version of the patch, results should be the same): hpns == halt_poll_ns idle_spin=0/ idle_spin=800/ idle_spin=0/ hpns=200000 hpns=0 hpns=800000 DeleteC06T03 (100 thread) 1.76 1.71 (-3%) 1.78 (+1%) InsertC16T02 (100 thread) 2.14 2.07 (-3%) 2.18 (+1.8%) DeleteC00T01 (1 thread) 1.34 1.28 (-4.5%) 1.29 (-3.7%) UpdateC00T03 (1 thread) 4.72 4.18 (-12%) 4.53 (-5%) Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Diffstat (limited to 'drivers')
-rw-r--r--drivers/cpuidle/Kconfig11
-rw-r--r--drivers/cpuidle/governors/Makefile1
-rw-r--r--drivers/cpuidle/governors/haltpoll.c150
3 files changed, 162 insertions, 0 deletions
diff --git a/drivers/cpuidle/Kconfig b/drivers/cpuidle/Kconfig
index cc8efc56be7d..88727b7c0d59 100644
--- a/drivers/cpuidle/Kconfig
+++ b/drivers/cpuidle/Kconfig
@@ -33,6 +33,17 @@ config CPU_IDLE_GOV_TEO
Some workloads benefit from using it and it generally should be safe
to use. Say Y here if you are not happy with the alternatives.
+config CPU_IDLE_GOV_HALTPOLL
+ bool "Haltpoll governor (for virtualized systems)"
+ depends on KVM_GUEST
+ help
+ This governor implements haltpoll idle state selection, to be
+ used in conjunction with the haltpoll cpuidle driver, allowing
+ for polling for a certain amount of time before entering idle
+ state.
+
+ Some virtualized workloads benefit from using it.
+
config DT_IDLE_STATES
bool
diff --git a/drivers/cpuidle/governors/Makefile b/drivers/cpuidle/governors/Makefile
index 42f44cc610dd..63abb5393a4d 100644
--- a/drivers/cpuidle/governors/Makefile
+++ b/drivers/cpuidle/governors/Makefile
@@ -6,3 +6,4 @@
obj-$(CONFIG_CPU_IDLE_GOV_LADDER) += ladder.o
obj-$(CONFIG_CPU_IDLE_GOV_MENU) += menu.o
obj-$(CONFIG_CPU_IDLE_GOV_TEO) += teo.o
+obj-$(CONFIG_CPU_IDLE_GOV_HALTPOLL) += haltpoll.o
diff --git a/drivers/cpuidle/governors/haltpoll.c b/drivers/cpuidle/governors/haltpoll.c
new file mode 100644
index 000000000000..797477bda486
--- /dev/null
+++ b/drivers/cpuidle/governors/haltpoll.c
@@ -0,0 +1,150 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * haltpoll.c - haltpoll idle governor
+ *
+ * Copyright 2019 Red Hat, Inc. and/or its affiliates.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2. See
+ * the COPYING file in the top-level directory.
+ *
+ * Authors: Marcelo Tosatti <mtosatti@redhat.com>
+ */
+
+#include <linux/kernel.h>
+#include <linux/cpuidle.h>
+#include <linux/time.h>
+#include <linux/ktime.h>
+#include <linux/hrtimer.h>
+#include <linux/tick.h>
+#include <linux/sched.h>
+#include <linux/module.h>
+#include <linux/kvm_para.h>
+
+static unsigned int guest_halt_poll_ns __read_mostly = 200000;
+module_param(guest_halt_poll_ns, uint, 0644);
+
+/* division factor to shrink halt_poll_ns */
+static unsigned int guest_halt_poll_shrink __read_mostly = 2;
+module_param(guest_halt_poll_shrink, uint, 0644);
+
+/* multiplication factor to grow per-cpu poll_limit_ns */
+static unsigned int guest_halt_poll_grow __read_mostly = 2;
+module_param(guest_halt_poll_grow, uint, 0644);
+
+/* value in us to start growing per-cpu halt_poll_ns */
+static unsigned int guest_halt_poll_grow_start __read_mostly = 50000;
+module_param(guest_halt_poll_grow_start, uint, 0644);
+
+/* allow shrinking guest halt poll */
+static bool guest_halt_poll_allow_shrink __read_mostly = true;
+module_param(guest_halt_poll_allow_shrink, bool, 0644);
+
+/**
+ * haltpoll_select - selects the next idle state to enter
+ * @drv: cpuidle driver containing state data
+ * @dev: the CPU
+ * @stop_tick: indication on whether or not to stop the tick
+ */
+static int haltpoll_select(struct cpuidle_driver *drv,
+ struct cpuidle_device *dev,
+ bool *stop_tick)
+{
+ int latency_req = cpuidle_governor_latency_req(dev->cpu);
+
+ if (!drv->state_count || latency_req == 0) {
+ *stop_tick = false;
+ return 0;
+ }
+
+ if (dev->poll_limit_ns == 0)
+ return 1;
+
+ /* Last state was poll? */
+ if (dev->last_state_idx == 0) {
+ /* Halt if no event occurred on poll window */
+ if (dev->poll_time_limit == true)
+ return 1;
+
+ *stop_tick = false;
+ /* Otherwise, poll again */
+ return 0;
+ }
+
+ *stop_tick = false;
+ /* Last state was halt: poll */
+ return 0;
+}
+
+static void adjust_poll_limit(struct cpuidle_device *dev, unsigned int block_us)
+{
+ unsigned int val;
+ u64 block_ns = block_us*NSEC_PER_USEC;
+
+ /* Grow cpu_halt_poll_us if
+ * cpu_halt_poll_us < block_ns < guest_halt_poll_us
+ */
+ if (block_ns > dev->poll_limit_ns && block_ns <= guest_halt_poll_ns) {
+ val = dev->poll_limit_ns * guest_halt_poll_grow;
+
+ if (val < guest_halt_poll_grow_start)
+ val = guest_halt_poll_grow_start;
+ if (val > guest_halt_poll_ns)
+ val = guest_halt_poll_ns;
+
+ dev->poll_limit_ns = val;
+ } else if (block_ns > guest_halt_poll_ns &&
+ guest_halt_poll_allow_shrink) {
+ unsigned int shrink = guest_halt_poll_shrink;
+
+ val = dev->poll_limit_ns;
+ if (shrink == 0)
+ val = 0;
+ else
+ val /= shrink;
+ dev->poll_limit_ns = val;
+ }
+}
+
+/**
+ * haltpoll_reflect - update variables and update poll time
+ * @dev: the CPU
+ * @index: the index of actual entered state
+ */
+static void haltpoll_reflect(struct cpuidle_device *dev, int index)
+{
+ dev->last_state_idx = index;
+
+ if (index != 0)
+ adjust_poll_limit(dev, dev->last_residency);
+}
+
+/**
+ * haltpoll_enable_device - scans a CPU's states and does setup
+ * @drv: cpuidle driver
+ * @dev: the CPU
+ */
+static int haltpoll_enable_device(struct cpuidle_driver *drv,
+ struct cpuidle_device *dev)
+{
+ dev->poll_limit_ns = 0;
+
+ return 0;
+}
+
+static struct cpuidle_governor haltpoll_governor = {
+ .name = "haltpoll",
+ .rating = 21,
+ .enable = haltpoll_enable_device,
+ .select = haltpoll_select,
+ .reflect = haltpoll_reflect,
+};
+
+static int __init init_haltpoll(void)
+{
+ if (kvm_para_available())
+ return cpuidle_register_governor(&haltpoll_governor);
+
+ return 0;
+}
+
+postcore_initcall(init_haltpoll);