Message-Id: <20220701144013.1085272-3-sebastianene@google.com>
Date:   Fri,  1 Jul 2022 14:40:14 +0000
From:   Sebastian Ene <sebastianene@...gle.com>
To:     Rob Herring <robh+dt@...nel.org>,
        Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
        Arnd Bergmann <arnd@...db.de>,
        Dragan Cvetic <dragan.cvetic@...inx.com>
Cc:     linux-kernel@...r.kernel.org, devicetree@...r.kernel.org,
        maz@...nel.org, will@...nel.org, vdonnefort@...gle.com,
        Guenter Roeck <linux@...ck-us.net>,
        Sebastian Ene <sebastianene@...gle.com>
Subject: [PATCH v9 2/2] misc: Add a mechanism to detect stalls on guest vCPUs

This driver creates per-cpu hrtimers which are required to do the
periodic 'pet' operation. On a conventional watchdog-core driver, the
userspace is responsible for delivering the 'pet' events by writing to
the particular /dev/watchdogN node. In this case we require a strong
thread affinity to be able to account for lost time on a per vCPU.

This part of the driver is the 'frontend' which is reponsible for
delivering the periodic 'pet' events, configuring the virtual peripheral
and listening for cpu hotplug events. The other part of the driver is
an emulated MMIO device which is part of the KVM virtual machine
monitor and this part accounts for lost time by looking at the
/proc/{}/task/{}/stat entries.

Signed-off-by: Sebastian Ene <sebastianene@...gle.com>
---
 drivers/misc/Kconfig               |  13 ++
 drivers/misc/Makefile              |   1 +
 drivers/misc/vcpu_stall_detector.c | 212 +++++++++++++++++++++++++++++
 3 files changed, 226 insertions(+)
 create mode 100644 drivers/misc/vcpu_stall_detector.c

diff --git a/drivers/misc/Kconfig b/drivers/misc/Kconfig
index 41d2bb0ae23a..83afb41a85cf 100644
--- a/drivers/misc/Kconfig
+++ b/drivers/misc/Kconfig
@@ -483,6 +483,19 @@ config OPEN_DICE
 
 	  If unsure, say N.
 
+config VCPU_STALL_DETECTOR
+	tristate "VCPU stall detector"
+	select LOCKUP_DETECTOR
+	depends on OF
+	help
+	  Detect CPU locks on a kvm virtual machine. This driver relies on
+	  the hrtimers which are CPU-binded to do the 'pet' operation. When a
+	  vCPU has to do a 'pet', it exits the guest through MMIO write and
+	  the backend driver takes into account the lost ticks for this
+	  particular CPU.
+	  To compile this driver as a module, choose M here: the
+	  module will be called vcpu_stall_detector.
+
 source "drivers/misc/c2port/Kconfig"
 source "drivers/misc/eeprom/Kconfig"
 source "drivers/misc/cb710/Kconfig"
diff --git a/drivers/misc/Makefile b/drivers/misc/Makefile
index 70e800e9127f..2be8542616dd 100644
--- a/drivers/misc/Makefile
+++ b/drivers/misc/Makefile
@@ -60,3 +60,4 @@ obj-$(CONFIG_XILINX_SDFEC)	+= xilinx_sdfec.o
 obj-$(CONFIG_HISI_HIKEY_USB)	+= hisi_hikey_usb.o
 obj-$(CONFIG_HI6421V600_IRQ)	+= hi6421v600-irq.o
 obj-$(CONFIG_OPEN_DICE)		+= open-dice.o
+obj-$(CONFIG_VCPU_STALL_DETECTOR)	+= vcpu_stall_detector.o
\ No newline at end of file
diff --git a/drivers/misc/vcpu_stall_detector.c b/drivers/misc/vcpu_stall_detector.c
new file mode 100644
index 000000000000..039ac54564c1
--- /dev/null
+++ b/drivers/misc/vcpu_stall_detector.c
@@ -0,0 +1,212 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// VCPU stall detector.
+//  Copyright (C) Google, 2022
+
+#include <linux/cpu.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+
+#include <linux/device.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/nmi.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/param.h>
+#include <linux/percpu.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+
+#define REG_STATUS		(0x00)
+#define REG_LOAD_CNT		(0x04)
+#define REG_CURRENT_CNT		(0x08)
+#define REG_CLOCK_FREQ_HZ	(0x0C)
+#define REG_LEN			(0x10)
+
+#define DEFAULT_CLOCK_HZ	(10)
+#define DEFAULT_TIMEOT_SEC	(8)
+
+struct vm_stall_detect_s {
+	void __iomem *membase;
+	u32 clock_freq;
+	u32 expiration_sec;
+	u32 ping_timeout_ms;
+	struct hrtimer per_cpu_hrtimer;
+	struct platform_device *dev;
+};
+
+#define vcpu_stall_detect_reg_write(stall_detect, reg, value)	\
+	iowrite32((value), (stall_detect)->membase + (reg))
+#define vcpu_stall_detect_reg_read(stall_detect, reg)		\
+	io32read((stall_detect)->membase + (reg))
+
+static struct vm_stall_detect_s __percpu *vm_stall_detect;
+
+static enum hrtimer_restart
+vcpu_stall_detect_timer_fn(struct hrtimer *hrtimer)
+{
+	struct vm_stall_detect_s *cpu_stall_detect;
+	u32 ticks;
+
+	cpu_stall_detect = container_of(hrtimer, struct vm_stall_detect_s,
+					per_cpu_hrtimer);
+	ticks = cpu_stall_detect->clock_freq * cpu_stall_detect->expiration_sec;
+	vcpu_stall_detect_reg_write(cpu_stall_detect, REG_LOAD_CNT, ticks);
+	hrtimer_forward_now(hrtimer,
+			    ms_to_ktime(cpu_stall_detect->ping_timeout_ms));
+
+	return HRTIMER_RESTART;
+}
+
+static void vcpu_stall_detect_start(void *arg)
+{
+	u32 ticks;
+	struct vm_stall_detect_s *cpu_stall_detect = arg;
+	struct hrtimer *hrtimer = &cpu_stall_detect->per_cpu_hrtimer;
+
+	vcpu_stall_detect_reg_write(cpu_stall_detect, REG_CLOCK_FREQ_HZ,
+				    cpu_stall_detect->clock_freq);
+
+	/* Compute the number of ticks required for the stall detector counter
+	 * register based on the internal clock frequency and the timeout
+	 * value given from the device tree.
+	 */
+	ticks = cpu_stall_detect->clock_freq *
+		cpu_stall_detect->expiration_sec;
+	vcpu_stall_detect_reg_write(cpu_stall_detect, REG_LOAD_CNT, ticks);
+
+	/* Enable the internal clock and start the stall detector */
+	vcpu_stall_detect_reg_write(cpu_stall_detect, REG_STATUS, 1);
+
+	hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	hrtimer->function = vcpu_stall_detect_timer_fn;
+	hrtimer_start(hrtimer, ms_to_ktime(cpu_stall_detect->ping_timeout_ms),
+		      HRTIMER_MODE_REL_PINNED);
+}
+
+static void vcpu_stall_detect_stop(void *arg)
+{
+	struct vm_stall_detect_s *cpu_stall_detect = arg;
+	struct hrtimer *hrtimer = &cpu_stall_detect->per_cpu_hrtimer;
+
+	hrtimer_cancel(hrtimer);
+
+	/* Disable the stall detector */
+	vcpu_stall_detect_reg_write(cpu_stall_detect, REG_STATUS, 0);
+}
+
+static int start_stall_detector_on_cpu(unsigned int cpu)
+{
+	vcpu_stall_detect_start(this_cpu_ptr(vm_stall_detect));
+	return 0;
+}
+
+static int stop_stall_detector_on_cpu(unsigned int cpu)
+{
+	vcpu_stall_detect_stop(this_cpu_ptr(vm_stall_detect));
+	return 0;
+}
+
+static int vcpu_stall_detect_probe(struct platform_device *dev)
+{
+	int cpu, ret, err;
+	void __iomem *membase;
+	struct resource *r;
+	u32 stall_detect_clock, stall_detect_timeout_sec = 0;
+
+	r = platform_get_resource(dev, IORESOURCE_MEM, 0);
+	if (r == NULL)
+		return -ENODEV;
+
+	vm_stall_detect = alloc_percpu(typeof(struct vm_stall_detect_s));
+	if (!vm_stall_detect)
+		return -ENOMEM;
+
+	membase = ioremap(r->start, resource_size(r));
+	if (!membase) {
+		ret = -ENOMEM;
+		goto err_withmem;
+	}
+
+	if (of_property_read_u32(dev->dev.of_node, "clock-frequency",
+				 &stall_detect_clock))
+		stall_detect_clock = DEFAULT_CLOCK_HZ;
+
+	if (of_property_read_u32(dev->dev.of_node, "timeout-sec",
+				 &stall_detect_timeout_sec))
+		stall_detect_timeout_sec = DEFAULT_TIMEOT_SEC;
+
+	for_each_cpu_and(cpu, cpu_online_mask, &watchdog_cpumask) {
+		struct vm_stall_detect_s *cpu_stall_detect;
+
+		cpu_stall_detect = per_cpu_ptr(vm_stall_detect, cpu);
+		cpu_stall_detect->membase = membase + cpu * REG_LEN;
+		cpu_stall_detect->clock_freq = stall_detect_clock;
+		cpu_stall_detect->expiration_sec = stall_detect_timeout_sec;
+
+		/* Pet the stall detector at half of its expiration timeout
+		 * to prevent spurios resets.
+		 */
+		cpu_stall_detect->ping_timeout_ms = stall_detect_timeout_sec *
+			MSEC_PER_SEC / 2;
+		smp_call_function_single(cpu, vcpu_stall_detect_start,
+					 cpu_stall_detect, true);
+	}
+
+	err = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
+					"virt/vcpu_stall_detector:online",
+					start_stall_detector_on_cpu,
+					stop_stall_detector_on_cpu);
+	if (err < 0) {
+		dev_err(&dev->dev, "failed to install cpu hotplug");
+		ret = err;
+		goto err_withmem;
+	}
+
+	return 0;
+
+err_withmem:
+	free_percpu(vm_stall_detect);
+	return ret;
+}
+
+static int vcpu_stall_detect_remove(struct platform_device *dev)
+{
+	int cpu;
+
+	for_each_cpu_and(cpu, cpu_online_mask, &watchdog_cpumask) {
+		struct vm_stall_detect_s *cpu_stall_detect;
+
+		cpu_stall_detect = per_cpu_ptr(vm_stall_detect, cpu);
+		smp_call_function_single(cpu, vcpu_stall_detect_stop,
+					 cpu_stall_detect, true);
+	}
+
+	free_percpu(vm_stall_detect);
+	vm_stall_detect = NULL;
+	return 0;
+}
+
+static const struct of_device_id vcpu_stall_detect_of_match[] = {
+	{ .compatible = "qemu,vcpu-stall-detector", },
+	{}
+};
+
+MODULE_DEVICE_TABLE(of, vcpu_stall_detect_of_match);
+
+static struct platform_driver vcpu_stall_detect_driver = {
+	.probe  = vcpu_stall_detect_probe,
+	.remove = vcpu_stall_detect_remove,
+	.driver = {
+		.name           = KBUILD_MODNAME,
+		.of_match_table = vcpu_stall_detect_of_match,
+	},
+};
+
+module_platform_driver(vcpu_stall_detect_driver);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Sebastian Ene <sebastianene@...gle.com>");
+MODULE_DESCRIPTION("VCPU stall detector");
-- 
2.37.0.rc0.161.g10f37bed90-goog

Powered by blists - more mailing lists