Re: [PATCH v2 2/2] misc: Add a mechanism to detect stalls on guest vCPUs

[Greg Kroah-Hartman <gregkh@linuxfoundation.org>]

On Fri, Apr 22, 2022 at 02:19:50PM +0000, Sebastian Ene wrote:
> This patch adds support for a virtual watchdog which relies on the
> per-cpu hrtimers to pet at regular intervals.
> 
> Signed-off-by: Sebastian Ene <sebastianene@google.com>
> ---
>  drivers/misc/Kconfig  |   8 ++
>  drivers/misc/Makefile |   1 +
>  drivers/misc/vm-wdt.c | 215 ++++++++++++++++++++++++++++++++++++++++++
>  3 files changed, 224 insertions(+)
>  create mode 100644 drivers/misc/vm-wdt.c
> 
> diff --git a/drivers/misc/Kconfig b/drivers/misc/Kconfig
> index 2b9572a6d114..0e710149ff95 100644
> --- a/drivers/misc/Kconfig
> +++ b/drivers/misc/Kconfig
> @@ -493,6 +493,14 @@ config OPEN_DICE
>  
>  	  If unsure, say N.
>  
> +config VM_WATCHDOG
> +	tristate "Virtual Machine Watchdog"
> +	select LOCKUP_DETECTOR
> +	help
> +	  Detect CPU locks on the virtual machine.
> +	  To compile this driver as a module, choose M here: the
> +	  module will be called vm-wdt.
> +
>  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 2ec634354cf5..868e28d01b75 100644
> --- a/drivers/misc/Makefile
> +++ b/drivers/misc/Makefile
> @@ -59,3 +59,4 @@ obj-$(CONFIG_XILINX_SDFEC)	+= xilinx_sdfec.o
>  obj-$(CONFIG_HISI_HIKEY_USB)	+= hisi_hikey_usb.o
>  obj-$(CONFIG_UID_SYS_STATS)	+= uid_sys_stats.o
>  obj-$(CONFIG_OPEN_DICE)		+= open-dice.o
> +obj-$(CONFIG_VM_WATCHDOG) += vm-wdt.o

No tab?

> \ No newline at end of file
> diff --git a/drivers/misc/vm-wdt.c b/drivers/misc/vm-wdt.c
> new file mode 100644
> index 000000000000..ea4351754645
> --- /dev/null
> +++ b/drivers/misc/vm-wdt.c
> @@ -0,0 +1,215 @@
> +// SPDX-License-Identifier: GPL-2.0+

I have to ask, do you really mean "+" here as this is not the overall
license of the kernel.  It's not a normal license for your employer to
pick, so as long as you have legal approval, it's fine, but if not, you
need to get that.

> +//
> +// Virtual watchdog driver.
> +//  Copyright (C) Google, 2022
> +
> +#define pr_fmt(fmt) "vm-watchdog: " fmt

It's a driver, you shouldn't need any pr_* calls.

> +
> +#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 DRV_NAME			"vm_wdt"

KBUILD_MODNAME?

> +#define DRV_VERSION			"1.0"

"versions" mean nothing once the code is in the kernel, please drop
this.

But why isn't this in the normal watchdog subdirectory?  Why is this a
special driver?

> +
> +#define VMWDT_REG_STATUS		(0x00)
> +#define VMWDT_REG_LOAD_CNT		(0x04)
> +#define VMWDT_REG_CURRENT_CNT		(0x08)
> +#define VMWDT_REG_CLOCK_FREQ_HZ		(0x0C)
> +#define VMWDT_REG_LEN			(0x10)
> +
> +#define VMWDT_DEFAULT_CLOCK_HZ		(10)
> +#define VMWDT_DEFAULT_TIMEOT_SEC	(8)
> +
> +struct vm_wdt_s {
> +	void __iomem *membase;
> +	u32 clock_freq;
> +	u32 expiration_sec;
> +	u32 ping_timeout_ms;
> +	struct hrtimer per_cpu_hrtimer;
> +	struct platform_device *dev;
> +};
> +
> +#define vmwdt_reg_write(wdt, reg, value)	\
> +	iowrite32((value), (wdt)->membase + (reg))
> +#define vmwdt_reg_read(wdt, reg)		\
> +	io32read((wdt)->membase + (reg))
> +
> +static struct platform_device *virt_dev;
> +
> +static enum hrtimer_restart vmwdt_timer_fn(struct hrtimer *hrtimer)
> +{
> +	struct vm_wdt_s *cpu_wdt;
> +	u32 ticks;
> +
> +	cpu_wdt = container_of(hrtimer, struct vm_wdt_s, per_cpu_hrtimer);
> +	ticks = cpu_wdt->clock_freq * cpu_wdt->expiration_sec;
> +	vmwdt_reg_write(cpu_wdt, VMWDT_REG_LOAD_CNT, ticks);
> +	hrtimer_forward_now(hrtimer, ms_to_ktime(cpu_wdt->ping_timeout_ms));
> +
> +	return HRTIMER_RESTART;
> +}
> +
> +static void vmwdt_start(void *arg)
> +{
> +	u32 ticks;
> +	int cpu = smp_processor_id();
> +	struct vm_wdt_s *cpu_wdt = arg;
> +	struct hrtimer *hrtimer = &cpu_wdt->per_cpu_hrtimer;
> +
> +	pr_info("cpu %u vmwdt start\n", cpu);

When drivers work properly, they are quiet.

Again, why not have this in drivers/watchdog/ and use the apis there
instead of creating a custom one for no reason?

thanks,

greg k-h