[PATCH V2 1/1] Drivers: hv: vmbus: Implement a clockevent device

[PATCH V2 1/1] Drivers: hv: vmbus: Implement a clockevent device

[K. Y. Srinivasan]

Implement a clockevent device based on the timer support
available on Hyper-V.

Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
---
 arch/x86/include/uapi/asm/hyperv.h |   11 +++++
 drivers/hv/hv.c                    |   78 ++++++++++++++++++++++++++++++++++++
 drivers/hv/hyperv_vmbus.h          |   21 ++++++++++
 drivers/hv/vmbus_drv.c             |   40 +++++++++++++++++-
 4 files changed, 148 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/uapi/asm/hyperv.h b/arch/x86/include/uapi/asm/hyperv.h
index 462efe7..90c458e 100644
--- a/arch/x86/include/uapi/asm/hyperv.h
+++ b/arch/x86/include/uapi/asm/hyperv.h
@@ -187,6 +187,17 @@
 #define HV_X64_MSR_SINT14			0x4000009E
 #define HV_X64_MSR_SINT15			0x4000009F
 
+/*
+ * Synthetic Timer MSRs. Four timers per vcpu.
+ */
+#define HV_X64_MSR_STIMER0_CONFIG		0x400000B0
+#define HV_X64_MSR_STIMER0_COUNT		0x400000B1
+#define HV_X64_MSR_STIMER1_CONFIG		0x400000B2
+#define HV_X64_MSR_STIMER1_COUNT		0x400000B3
+#define HV_X64_MSR_STIMER2_CONFIG		0x400000B4
+#define HV_X64_MSR_STIMER2_COUNT		0x400000B5
+#define HV_X64_MSR_STIMER3_CONFIG		0x400000B6
+#define HV_X64_MSR_STIMER3_COUNT		0x400000B7
 
 #define HV_X64_MSR_HYPERCALL_ENABLE		0x00000001
 #define HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT	12
diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c
index 3e4235c..e2749c0 100644
--- a/drivers/hv/hv.c
+++ b/drivers/hv/hv.c
@@ -28,7 +28,9 @@
 #include <linux/hyperv.h>
 #include <linux/version.h>
 #include <linux/interrupt.h>
+#include <linux/clockchips.h>
 #include <asm/hyperv.h>
+#include <asm/mshyperv.h>
 #include "hyperv_vmbus.h"
 
 /* The one and only */
@@ -37,6 +39,10 @@ struct hv_context hv_context = {
 	.hypercall_page		= NULL,
 };
 
+#define HV_TIMER_FREQUENCY (10 * 1000 * 1000) /* 100ns period */
+#define HV_MAX_MAX_DELTA_TICKS 0xffffffff
+#define HV_MIN_DELTA_TICKS 1
+
 /*
  * query_hypervisor_info - Get version info of the windows hypervisor
  */
@@ -144,6 +150,8 @@ int hv_init(void)
 	       sizeof(int) * NR_CPUS);
 	memset(hv_context.event_dpc, 0,
 	       sizeof(void *) * NR_CPUS);
+	memset(hv_context.clk_evt, 0,
+	       sizeof(void *) * NR_CPUS);
 
 	max_leaf = query_hypervisor_info();
 
@@ -258,10 +266,63 @@ u16 hv_signal_event(void *con_id)
 	return status;
 }
 
+static int hv_ce_set_next_event(unsigned long delta,
+				struct clock_event_device *evt)
+{
+	cycle_t current_tick;
+
+	WARN_ON(evt->mode != CLOCK_EVT_MODE_ONESHOT);
+
+	rdmsrl(HV_X64_MSR_TIME_REF_COUNT, current_tick);
+	current_tick += delta;
+	wrmsrl(HV_X64_MSR_STIMER0_COUNT, current_tick);
+	return 0;
+}
+
+static void hv_ce_setmode(enum clock_event_mode mode,
+			  struct clock_event_device *evt)
+{
+	union hv_timer_config timer_cfg;
+
+	switch (mode) {
+	case CLOCK_EVT_MODE_PERIODIC:
+		/* unsupported */
+		break;
+
+	case CLOCK_EVT_MODE_ONESHOT:
+		timer_cfg.enable = 1;
+		timer_cfg.auto_enable = 1;
+		timer_cfg.sintx = VMBUS_MESSAGE_SINT;
+		wrmsrl(HV_X64_MSR_STIMER0_CONFIG, timer_cfg.as_uint64);
+		break;
+
+	case CLOCK_EVT_MODE_UNUSED:
+	case CLOCK_EVT_MODE_SHUTDOWN:
+		wrmsrl(HV_X64_MSR_STIMER0_COUNT, 0);
+		wrmsrl(HV_X64_MSR_STIMER0_CONFIG, 0);
+		break;
+	case CLOCK_EVT_MODE_RESUME:
+		break;
+	}
+}
+
+static void hv_init_clockevent_device(struct clock_event_device *dev, int cpu)
+{
+	dev->name = "Hyper-V clockevent";
+	dev->features = CLOCK_EVT_FEAT_ONESHOT;
+	dev->cpumask = cpumask_of(cpu);
+	dev->rating = 1000,
+	dev->owner = THIS_MODULE,
+
+	dev->set_mode = hv_ce_setmode;
+	dev->set_next_event = hv_ce_set_next_event;
+}
+
 
 int hv_synic_alloc(void)
 {
 	size_t size = sizeof(struct tasklet_struct);
+	size_t ced_size = sizeof(struct clock_event_device);
 	int cpu;
 
 	for_each_online_cpu(cpu) {
@@ -272,6 +333,13 @@ int hv_synic_alloc(void)
 		}
 		tasklet_init(hv_context.event_dpc[cpu], vmbus_on_event, cpu);
 
+		hv_context.clk_evt[cpu] = kzalloc(ced_size, GFP_ATOMIC);
+		if (hv_context.clk_evt[cpu] == NULL) {
+			pr_err("Unable to allocate clock event device\n");
+			goto err;
+		}
+		hv_init_clockevent_device(hv_context.clk_evt[cpu], cpu);
+
 		hv_context.synic_message_page[cpu] =
 			(void *)get_zeroed_page(GFP_ATOMIC);
 
@@ -305,6 +373,7 @@ err:
 static void hv_synic_free_cpu(int cpu)
 {
 	kfree(hv_context.event_dpc[cpu]);
+	kfree(hv_context.clk_evt[cpu]);
 	if (hv_context.synic_event_page[cpu])
 		free_page((unsigned long)hv_context.synic_event_page[cpu]);
 	if (hv_context.synic_message_page[cpu])
@@ -388,6 +457,15 @@ void hv_synic_init(void *arg)
 	hv_context.vp_index[cpu] = (u32)vp_index;
 
 	INIT_LIST_HEAD(&hv_context.percpu_list[cpu]);
+
+	/*
+	 * Register the per-cpu clockevent source.
+	 */
+	if (ms_hyperv.features & HV_X64_MSR_SYNTIMER_AVAILABLE)
+		clockevents_config_and_register(hv_context.clk_evt[cpu],
+						HV_TIMER_FREQUENCY,
+						HV_MIN_DELTA_TICKS,
+						HV_MAX_MAX_DELTA_TICKS);
 	return;
 }
 
diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h
index c386d8d..44b1c94 100644
--- a/drivers/hv/hyperv_vmbus.h
+++ b/drivers/hv/hyperv_vmbus.h
@@ -178,6 +178,23 @@ struct hv_message_header {
 	};
 };
 
+/*
+ * Timer configuration register.
+ */
+union hv_timer_config {
+	u64 as_uint64;
+	struct {
+		u64 enable:1;
+		u64 periodic:1;
+		u64 lazy:1;
+		u64 auto_enable:1;
+		u64 reserved_z0:12;
+		u64 sintx:4;
+		u64 reserved_z1:44;
+	};
+};
+
+
 /* Define timer message payload structure. */
 struct hv_timer_message_payload {
 	u32 timer_index;
@@ -519,6 +536,10 @@ struct hv_context {
 	 * buffer to post messages to the host.
 	 */
 	void *post_msg_page[NR_CPUS];
+	/*
+	 * Support PV clockevent device.
+	 */
+	struct clock_event_device *clk_evt[NR_CPUS];
 };
 
 extern struct hv_context hv_context;
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 4d6b269..9e57c07 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -32,6 +32,7 @@
 #include <linux/completion.h>
 #include <linux/hyperv.h>
 #include <linux/kernel_stat.h>
+#include <linux/clockchips.h>
 #include <asm/hyperv.h>
 #include <asm/hypervisor.h>
 #include <asm/mshyperv.h>
@@ -578,6 +579,37 @@ static void vmbus_onmessage_work(struct work_struct *work)
 	kfree(ctx);
 }
 
+void hv_process_timer_expiration(struct hv_message *msg, int cpu)
+{
+	struct clock_event_device *dev = hv_context.clk_evt[cpu];
+
+	if (msg->header.message_type == HVMSG_NONE)
+		return;
+
+	if (dev->event_handler)
+		dev->event_handler(dev);
+
+	msg->header.message_type = HVMSG_NONE;
+
+	/*
+	 * Make sure the write to MessageType (ie set to
+	 * HVMSG_NONE) happens before we read the
+	 * MessagePending and EOMing. Otherwise, the EOMing
+	 * will not deliver any more messages since there is
+	 * no empty slot
+	 */
+	mb();
+
+	if (msg->header.message_flags.msg_pending) {
+		/*
+		 * This will cause message queue rescan to
+		 * possibly deliver another msg from the
+		 * hypervisor
+		 */
+		wrmsrl(HV_X64_MSR_EOM, 0);
+	}
+}
+
 static void vmbus_on_msg_dpc(unsigned long data)
 {
 	int cpu = smp_processor_id();
@@ -667,8 +699,12 @@ static void vmbus_isr(void)
 	msg = (struct hv_message *)page_addr + VMBUS_MESSAGE_SINT;
 
 	/* Check if there are actual msgs to be processed */
-	if (msg->header.message_type != HVMSG_NONE)
-		tasklet_schedule(&msg_dpc);
+	if (msg->header.message_type != HVMSG_NONE) {
+		if (msg->header.message_type == HVMSG_TIMER_EXPIRED)
+			hv_process_timer_expiration(msg, cpu);
+		else
+			tasklet_schedule(&msg_dpc);
+	}
 }
 
 /*
-- 
1.7.4.1

Re: [PATCH V2 1/1] Drivers: hv: vmbus: Implement a clockevent device

[Jason Wang]

On Fri, Dec 5, 2014 at 10:18 AM, K. Y. Srinivasan <kys@microsoft.com> 
wrote:
> Implement a clockevent device based on the timer support
> available on Hyper-V.
> 
> Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
> ---
>  arch/x86/include/uapi/asm/hyperv.h |   11 +++++
>  drivers/hv/hv.c                    |   78 
> ++++++++++++++++++++++++++++++++++++
>  drivers/hv/hyperv_vmbus.h          |   21 ++++++++++
>  drivers/hv/vmbus_drv.c             |   40 +++++++++++++++++-
>  4 files changed, 148 insertions(+), 2 deletions(-)
> 
> diff --git a/arch/x86/include/uapi/asm/hyperv.h 
> b/arch/x86/include/uapi/asm/hyperv.h
> index 462efe7..90c458e 100644
> --- a/arch/x86/include/uapi/asm/hyperv.h
> +++ b/arch/x86/include/uapi/asm/hyperv.h
> @@ -187,6 +187,17 @@
>  #define HV_X64_MSR_SINT14			0x4000009E
>  #define HV_X64_MSR_SINT15			0x4000009F
>  
> +/*
> + * Synthetic Timer MSRs. Four timers per vcpu.
> + */
> +#define HV_X64_MSR_STIMER0_CONFIG		0x400000B0
> +#define HV_X64_MSR_STIMER0_COUNT		0x400000B1
> +#define HV_X64_MSR_STIMER1_CONFIG		0x400000B2
> +#define HV_X64_MSR_STIMER1_COUNT		0x400000B3
> +#define HV_X64_MSR_STIMER2_CONFIG		0x400000B4
> +#define HV_X64_MSR_STIMER2_COUNT		0x400000B5
> +#define HV_X64_MSR_STIMER3_CONFIG		0x400000B6
> +#define HV_X64_MSR_STIMER3_COUNT		0x400000B7
>  
>  #define HV_X64_MSR_HYPERCALL_ENABLE		0x00000001
>  #define HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT	12
> diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c
> index 3e4235c..e2749c0 100644
> --- a/drivers/hv/hv.c
> +++ b/drivers/hv/hv.c
> @@ -28,7 +28,9 @@
>  #include <linux/hyperv.h>
>  #include <linux/version.h>
>  #include <linux/interrupt.h>
> +#include <linux/clockchips.h>
>  #include <asm/hyperv.h>
> +#include <asm/mshyperv.h>
>  #include "hyperv_vmbus.h"
>  
>  /* The one and only */
> @@ -37,6 +39,10 @@ struct hv_context hv_context = {
>  	.hypercall_page		= NULL,
>  };
>  
> +#define HV_TIMER_FREQUENCY (10 * 1000 * 1000) /* 100ns period */
> +#define HV_MAX_MAX_DELTA_TICKS 0xffffffff
> +#define HV_MIN_DELTA_TICKS 1
> +
>  /*
>   * query_hypervisor_info - Get version info of the windows hypervisor
>   */
> @@ -144,6 +150,8 @@ int hv_init(void)
>  	       sizeof(int) * NR_CPUS);
>  	memset(hv_context.event_dpc, 0,
>  	       sizeof(void *) * NR_CPUS);
> +	memset(hv_context.clk_evt, 0,
> +	       sizeof(void *) * NR_CPUS);
>  
>  	max_leaf = query_hypervisor_info();
>  
> @@ -258,10 +266,63 @@ u16 hv_signal_event(void *con_id)
>  	return status;
>  }
>  
> +static int hv_ce_set_next_event(unsigned long delta,
> +				struct clock_event_device *evt)
> +{
> +	cycle_t current_tick;
> +
> +	WARN_ON(evt->mode != CLOCK_EVT_MODE_ONESHOT);
> +
> +	rdmsrl(HV_X64_MSR_TIME_REF_COUNT, current_tick);
> +	current_tick += delta;
> +	wrmsrl(HV_X64_MSR_STIMER0_COUNT, current_tick);
> +	return 0;
> +}
> +
> +static void hv_ce_setmode(enum clock_event_mode mode,
> +			  struct clock_event_device *evt)
> +{
> +	union hv_timer_config timer_cfg;
> +
> +	switch (mode) {
> +	case CLOCK_EVT_MODE_PERIODIC:
> +		/* unsupported */
> +		break;
> +
> +	case CLOCK_EVT_MODE_ONESHOT:
> +		timer_cfg.enable = 1;
> +		timer_cfg.auto_enable = 1;
> +		timer_cfg.sintx = VMBUS_MESSAGE_SINT;
> +		wrmsrl(HV_X64_MSR_STIMER0_CONFIG, timer_cfg.as_uint64);
> +		break;
> +
> +	case CLOCK_EVT_MODE_UNUSED:
> +	case CLOCK_EVT_MODE_SHUTDOWN:
> +		wrmsrl(HV_X64_MSR_STIMER0_COUNT, 0);
> +		wrmsrl(HV_X64_MSR_STIMER0_CONFIG, 0);
> +		break;
> +	case CLOCK_EVT_MODE_RESUME:
> +		break;
> +	}
> +}
> +
> +static void hv_init_clockevent_device(struct clock_event_device 
> *dev, int cpu)
> +{
> +	dev->name = "Hyper-V clockevent";
> +	dev->features = CLOCK_EVT_FEAT_ONESHOT;
> +	dev->cpumask = cpumask_of(cpu);
> +	dev->rating = 1000,
> +	dev->owner = THIS_MODULE,
> +
> +	dev->set_mode = hv_ce_setmode;
> +	dev->set_next_event = hv_ce_set_next_event;
> +}
> +
>  
>  int hv_synic_alloc(void)
>  {
>  	size_t size = sizeof(struct tasklet_struct);
> +	size_t ced_size = sizeof(struct clock_event_device);
>  	int cpu;
>  
>  	for_each_online_cpu(cpu) {
> @@ -272,6 +333,13 @@ int hv_synic_alloc(void)
>  		}
>  		tasklet_init(hv_context.event_dpc[cpu], vmbus_on_event, cpu);
>  
> +		hv_context.clk_evt[cpu] = kzalloc(ced_size, GFP_ATOMIC);
> +		if (hv_context.clk_evt[cpu] == NULL) {
> +			pr_err("Unable to allocate clock event device\n");
> +			goto err;
> +		}
> +		hv_init_clockevent_device(hv_context.clk_evt[cpu], cpu);
> +
>  		hv_context.synic_message_page[cpu] =
>  			(void *)get_zeroed_page(GFP_ATOMIC);
>  
> @@ -305,6 +373,7 @@ err:
>  static void hv_synic_free_cpu(int cpu)
>  {
>  	kfree(hv_context.event_dpc[cpu]);
> +	kfree(hv_context.clk_evt[cpu]);
>  	if (hv_context.synic_event_page[cpu])
>  		free_page((unsigned long)hv_context.synic_event_page[cpu]);
>  	if (hv_context.synic_message_page[cpu])
> @@ -388,6 +457,15 @@ void hv_synic_init(void *arg)
>  	hv_context.vp_index[cpu] = (u32)vp_index;
>  
>  	INIT_LIST_HEAD(&hv_context.percpu_list[cpu]);
> +
> +	/*
> +	 * Register the per-cpu clockevent source.
> +	 */
> +	if (ms_hyperv.features & HV_X64_MSR_SYNTIMER_AVAILABLE)
> +		clockevents_config_and_register(hv_context.clk_evt[cpu],
> +						HV_TIMER_FREQUENCY,
> +						HV_MIN_DELTA_TICKS,
> +						HV_MAX_MAX_DELTA_TICKS);
>  	return;
>  }
>  
> diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h
> index c386d8d..44b1c94 100644
> --- a/drivers/hv/hyperv_vmbus.h
> +++ b/drivers/hv/hyperv_vmbus.h
> @@ -178,6 +178,23 @@ struct hv_message_header {
>  	};
>  };
>  
> +/*
> + * Timer configuration register.
> + */
> +union hv_timer_config {
> +	u64 as_uint64;
> +	struct {
> +		u64 enable:1;
> +		u64 periodic:1;
> +		u64 lazy:1;
> +		u64 auto_enable:1;
> +		u64 reserved_z0:12;
> +		u64 sintx:4;
> +		u64 reserved_z1:44;
> +	};
> +};
> +
> +
>  /* Define timer message payload structure. */
>  struct hv_timer_message_payload {
>  	u32 timer_index;
> @@ -519,6 +536,10 @@ struct hv_context {
>  	 * buffer to post messages to the host.
>  	 */
>  	void *post_msg_page[NR_CPUS];
> +	/*
> +	 * Support PV clockevent device.
> +	 */
> +	struct clock_event_device *clk_evt[NR_CPUS];
>  };
>  
>  extern struct hv_context hv_context;
> diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
> index 4d6b269..9e57c07 100644
> --- a/drivers/hv/vmbus_drv.c
> +++ b/drivers/hv/vmbus_drv.c
> @@ -32,6 +32,7 @@
>  #include <linux/completion.h>
>  #include <linux/hyperv.h>
>  #include <linux/kernel_stat.h>
> +#include <linux/clockchips.h>
>  #include <asm/hyperv.h>
>  #include <asm/hypervisor.h>
>  #include <asm/mshyperv.h>
> @@ -578,6 +579,37 @@ static void vmbus_onmessage_work(struct 
> work_struct *work)
>  	kfree(ctx);
>  }
>  
> +void hv_process_timer_expiration(struct hv_message *msg, int cpu)
> +{
> +	struct clock_event_device *dev = hv_context.clk_evt[cpu];
> +
> +	if (msg->header.message_type == HVMSG_NONE)
> +		return;

Nitpick: caller has checked this.
> 
> +
> +	if (dev->event_handler)
> +		dev->event_handler(dev);
> +
> +	msg->header.message_type = HVMSG_NONE;
> +
> +	/*
> +	 * Make sure the write to MessageType (ie set to
> +	 * HVMSG_NONE) happens before we read the
> +	 * MessagePending and EOMing. Otherwise, the EOMing
> +	 * will not deliver any more messages since there is
> +	 * no empty slot
> +	 */
> +	mb();
> +
> +	if (msg->header.message_flags.msg_pending) {
> +		/*
> +		 * This will cause message queue rescan to
> +		 * possibly deliver another msg from the
> +		 * hypervisor
> +		 */
> +		wrmsrl(HV_X64_MSR_EOM, 0);
> +	}
> +}
> +
>  static void vmbus_on_msg_dpc(unsigned long data)
>  {
>  	int cpu = smp_processor_id();
> @@ -667,8 +699,12 @@ static void vmbus_isr(void)
>  	msg = (struct hv_message *)page_addr + VMBUS_MESSAGE_SINT;
>  
>  	/* Check if there are actual msgs to be processed */
> -	if (msg->header.message_type != HVMSG_NONE)
> -		tasklet_schedule(&msg_dpc);
> +	if (msg->header.message_type != HVMSG_NONE) {
> +		if (msg->header.message_type == HVMSG_TIMER_EXPIRED)
> +			hv_process_timer_expiration(msg, cpu);
> +		else
> +			tasklet_schedule(&msg_dpc);
> +	}
>  }
>  
>  /*
> -- 
> 1.7.4.1

Reviewed-by: Jason Wang <jasowang@redhat.com>

RE: [PATCH V2 1/1] Drivers: hv: vmbus: Implement a clockevent device

[KY Srinivasan]

[-- Warning: decoded text below may be mangled, UTF-8 assumed --]
[-- Attachment #1: Type: text/plain; charset="utf-8", Size: 9253 bytes --]



> -----Original Message-----
> From: Jason Wang [mailto:jasowang@redhat.com]
> Sent: Thursday, December 4, 2014 10:52 PM
> To: KY Srinivasan
> Cc: gregkh@linuxfoundation.org; linux-kernel@vger.kernel.org;
> devel@linuxdriverproject.org; olaf@aepfle.de; apw@canonical.com; KY
> Srinivasan
> Subject: Re: [PATCH V2 1/1] Drivers: hv: vmbus: Implement a clockevent
> device
> 
> 
> 
> On Fri, Dec 5, 2014 at 10:18 AM, K. Y. Srinivasan <kys@microsoft.com>
> wrote:
> > Implement a clockevent device based on the timer support available on
> > Hyper-V.
> >
> > Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
> > ---
> >  arch/x86/include/uapi/asm/hyperv.h |   11 +++++
> >  drivers/hv/hv.c                    |   78
> > ++++++++++++++++++++++++++++++++++++
> >  drivers/hv/hyperv_vmbus.h          |   21 ++++++++++
> >  drivers/hv/vmbus_drv.c             |   40 +++++++++++++++++-
> >  4 files changed, 148 insertions(+), 2 deletions(-)
> >
> > diff --git a/arch/x86/include/uapi/asm/hyperv.h
> > b/arch/x86/include/uapi/asm/hyperv.h
> > index 462efe7..90c458e 100644
> > --- a/arch/x86/include/uapi/asm/hyperv.h
> > +++ b/arch/x86/include/uapi/asm/hyperv.h
> > @@ -187,6 +187,17 @@
> >  #define HV_X64_MSR_SINT14			0x4000009E
> >  #define HV_X64_MSR_SINT15			0x4000009F
> >
> > +/*
> > + * Synthetic Timer MSRs. Four timers per vcpu.
> > + */
> > +#define HV_X64_MSR_STIMER0_CONFIG		0x400000B0
> > +#define HV_X64_MSR_STIMER0_COUNT		0x400000B1
> > +#define HV_X64_MSR_STIMER1_CONFIG		0x400000B2
> > +#define HV_X64_MSR_STIMER1_COUNT		0x400000B3
> > +#define HV_X64_MSR_STIMER2_CONFIG		0x400000B4
> > +#define HV_X64_MSR_STIMER2_COUNT		0x400000B5
> > +#define HV_X64_MSR_STIMER3_CONFIG		0x400000B6
> > +#define HV_X64_MSR_STIMER3_COUNT		0x400000B7
> >
> >  #define HV_X64_MSR_HYPERCALL_ENABLE		0x00000001
> >  #define HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT	12
> > diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c index 3e4235c..e2749c0
> > 100644
> > --- a/drivers/hv/hv.c
> > +++ b/drivers/hv/hv.c
> > @@ -28,7 +28,9 @@
> >  #include <linux/hyperv.h>
> >  #include <linux/version.h>
> >  #include <linux/interrupt.h>
> > +#include <linux/clockchips.h>
> >  #include <asm/hyperv.h>
> > +#include <asm/mshyperv.h>
> >  #include "hyperv_vmbus.h"
> >
> >  /* The one and only */
> > @@ -37,6 +39,10 @@ struct hv_context hv_context = {
> >  	.hypercall_page		= NULL,
> >  };
> >
> > +#define HV_TIMER_FREQUENCY (10 * 1000 * 1000) /* 100ns period */
> > +#define HV_MAX_MAX_DELTA_TICKS 0xffffffff #define
> HV_MIN_DELTA_TICKS
> > +1
> > +
> >  /*
> >   * query_hypervisor_info - Get version info of the windows hypervisor
> >   */
> > @@ -144,6 +150,8 @@ int hv_init(void)
> >  	       sizeof(int) * NR_CPUS);
> >  	memset(hv_context.event_dpc, 0,
> >  	       sizeof(void *) * NR_CPUS);
> > +	memset(hv_context.clk_evt, 0,
> > +	       sizeof(void *) * NR_CPUS);
> >
> >  	max_leaf = query_hypervisor_info();
> >
> > @@ -258,10 +266,63 @@ u16 hv_signal_event(void *con_id)
> >  	return status;
> >  }
> >
> > +static int hv_ce_set_next_event(unsigned long delta,
> > +				struct clock_event_device *evt)
> > +{
> > +	cycle_t current_tick;
> > +
> > +	WARN_ON(evt->mode != CLOCK_EVT_MODE_ONESHOT);
> > +
> > +	rdmsrl(HV_X64_MSR_TIME_REF_COUNT, current_tick);
> > +	current_tick += delta;
> > +	wrmsrl(HV_X64_MSR_STIMER0_COUNT, current_tick);
> > +	return 0;
> > +}
> > +
> > +static void hv_ce_setmode(enum clock_event_mode mode,
> > +			  struct clock_event_device *evt)
> > +{
> > +	union hv_timer_config timer_cfg;
> > +
> > +	switch (mode) {
> > +	case CLOCK_EVT_MODE_PERIODIC:
> > +		/* unsupported */
> > +		break;
> > +
> > +	case CLOCK_EVT_MODE_ONESHOT:
> > +		timer_cfg.enable = 1;
> > +		timer_cfg.auto_enable = 1;
> > +		timer_cfg.sintx = VMBUS_MESSAGE_SINT;
> > +		wrmsrl(HV_X64_MSR_STIMER0_CONFIG,
> timer_cfg.as_uint64);
> > +		break;
> > +
> > +	case CLOCK_EVT_MODE_UNUSED:
> > +	case CLOCK_EVT_MODE_SHUTDOWN:
> > +		wrmsrl(HV_X64_MSR_STIMER0_COUNT, 0);
> > +		wrmsrl(HV_X64_MSR_STIMER0_CONFIG, 0);
> > +		break;
> > +	case CLOCK_EVT_MODE_RESUME:
> > +		break;
> > +	}
> > +}
> > +
> > +static void hv_init_clockevent_device(struct clock_event_device
> > *dev, int cpu)
> > +{
> > +	dev->name = "Hyper-V clockevent";
> > +	dev->features = CLOCK_EVT_FEAT_ONESHOT;
> > +	dev->cpumask = cpumask_of(cpu);
> > +	dev->rating = 1000,
> > +	dev->owner = THIS_MODULE,
> > +
> > +	dev->set_mode = hv_ce_setmode;
> > +	dev->set_next_event = hv_ce_set_next_event; }
> > +
> >
> >  int hv_synic_alloc(void)
> >  {
> >  	size_t size = sizeof(struct tasklet_struct);
> > +	size_t ced_size = sizeof(struct clock_event_device);
> >  	int cpu;
> >
> >  	for_each_online_cpu(cpu) {
> > @@ -272,6 +333,13 @@ int hv_synic_alloc(void)
> >  		}
> >  		tasklet_init(hv_context.event_dpc[cpu], vmbus_on_event,
> cpu);
> >
> > +		hv_context.clk_evt[cpu] = kzalloc(ced_size, GFP_ATOMIC);
> > +		if (hv_context.clk_evt[cpu] == NULL) {
> > +			pr_err("Unable to allocate clock event device\n");
> > +			goto err;
> > +		}
> > +		hv_init_clockevent_device(hv_context.clk_evt[cpu], cpu);
> > +
> >  		hv_context.synic_message_page[cpu] =
> >  			(void *)get_zeroed_page(GFP_ATOMIC);
> >
> > @@ -305,6 +373,7 @@ err:
> >  static void hv_synic_free_cpu(int cpu)  {
> >  	kfree(hv_context.event_dpc[cpu]);
> > +	kfree(hv_context.clk_evt[cpu]);
> >  	if (hv_context.synic_event_page[cpu])
> >  		free_page((unsigned
> long)hv_context.synic_event_page[cpu]);
> >  	if (hv_context.synic_message_page[cpu])
> > @@ -388,6 +457,15 @@ void hv_synic_init(void *arg)
> >  	hv_context.vp_index[cpu] = (u32)vp_index;
> >
> >  	INIT_LIST_HEAD(&hv_context.percpu_list[cpu]);
> > +
> > +	/*
> > +	 * Register the per-cpu clockevent source.
> > +	 */
> > +	if (ms_hyperv.features & HV_X64_MSR_SYNTIMER_AVAILABLE)
> > +		clockevents_config_and_register(hv_context.clk_evt[cpu],
> > +						HV_TIMER_FREQUENCY,
> > +						HV_MIN_DELTA_TICKS,
> > +
> 	HV_MAX_MAX_DELTA_TICKS);
> >  	return;
> >  }
> >
> > diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h
> > index c386d8d..44b1c94 100644
> > --- a/drivers/hv/hyperv_vmbus.h
> > +++ b/drivers/hv/hyperv_vmbus.h
> > @@ -178,6 +178,23 @@ struct hv_message_header {
> >  	};
> >  };
> >
> > +/*
> > + * Timer configuration register.
> > + */
> > +union hv_timer_config {
> > +	u64 as_uint64;
> > +	struct {
> > +		u64 enable:1;
> > +		u64 periodic:1;
> > +		u64 lazy:1;
> > +		u64 auto_enable:1;
> > +		u64 reserved_z0:12;
> > +		u64 sintx:4;
> > +		u64 reserved_z1:44;
> > +	};
> > +};
> > +
> > +
> >  /* Define timer message payload structure. */  struct
> > hv_timer_message_payload {
> >  	u32 timer_index;
> > @@ -519,6 +536,10 @@ struct hv_context {
> >  	 * buffer to post messages to the host.
> >  	 */
> >  	void *post_msg_page[NR_CPUS];
> > +	/*
> > +	 * Support PV clockevent device.
> > +	 */
> > +	struct clock_event_device *clk_evt[NR_CPUS];
> >  };
> >
> >  extern struct hv_context hv_context;
> > diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index
> > 4d6b269..9e57c07 100644
> > --- a/drivers/hv/vmbus_drv.c
> > +++ b/drivers/hv/vmbus_drv.c
> > @@ -32,6 +32,7 @@
> >  #include <linux/completion.h>
> >  #include <linux/hyperv.h>
> >  #include <linux/kernel_stat.h>
> > +#include <linux/clockchips.h>
> >  #include <asm/hyperv.h>
> >  #include <asm/hypervisor.h>
> >  #include <asm/mshyperv.h>
> > @@ -578,6 +579,37 @@ static void vmbus_onmessage_work(struct
> > work_struct *work)
> >  	kfree(ctx);
> >  }
> >
> > +void hv_process_timer_expiration(struct hv_message *msg, int cpu) {
> > +	struct clock_event_device *dev = hv_context.clk_evt[cpu];
> > +
> > +	if (msg->header.message_type == HVMSG_NONE)
> > +		return;
> 
> Nitpick: caller has checked this.

Yes indeed; I will fix it and resend.
> >
> > +
> > +	if (dev->event_handler)
> > +		dev->event_handler(dev);
> > +
> > +	msg->header.message_type = HVMSG_NONE;
> > +
> > +	/*
> > +	 * Make sure the write to MessageType (ie set to
> > +	 * HVMSG_NONE) happens before we read the
> > +	 * MessagePending and EOMing. Otherwise, the EOMing
> > +	 * will not deliver any more messages since there is
> > +	 * no empty slot
> > +	 */
> > +	mb();
> > +
> > +	if (msg->header.message_flags.msg_pending) {
> > +		/*
> > +		 * This will cause message queue rescan to
> > +		 * possibly deliver another msg from the
> > +		 * hypervisor
> > +		 */
> > +		wrmsrl(HV_X64_MSR_EOM, 0);
> > +	}
> > +}
> > +
> >  static void vmbus_on_msg_dpc(unsigned long data)  {
> >  	int cpu = smp_processor_id();
> > @@ -667,8 +699,12 @@ static void vmbus_isr(void)
> >  	msg = (struct hv_message *)page_addr + VMBUS_MESSAGE_SINT;
> >
> >  	/* Check if there are actual msgs to be processed */
> > -	if (msg->header.message_type != HVMSG_NONE)
> > -		tasklet_schedule(&msg_dpc);
> > +	if (msg->header.message_type != HVMSG_NONE) {
> > +		if (msg->header.message_type == HVMSG_TIMER_EXPIRED)
> > +			hv_process_timer_expiration(msg, cpu);
> > +		else
> > +			tasklet_schedule(&msg_dpc);
> > +	}
> >  }
> >
> >  /*
> > --
> > 1.7.4.1
> 
> Reviewed-by: Jason Wang <jasowang@redhat.com>

Thanks Jason.

K. Y
ÿôèº{.nÇ+‰·Ÿ®‰­†+%ŠËÿ±éݶ\x17¥Šwÿº{.nÇ+‰·¥Š{±þG«éÿŠ{ayº\x1dʇڙë,j\a­¢f£¢·hšïêÿ‘êçz_è®\x03(­éšŽŠÝ¢j"ú\x1a¶^[m§ÿÿ¾\a«þG«éÿ¢¸?™¨è­Ú&£ø§~á¶iO•æ¬z·švØ^\x14\x04\x1a¶^[m§ÿÿÃ\fÿ¶ìÿ¢¸?–I¥