@@ -7159,6 +7159,7 @@ F: arch/x86/include/asm/trace/hyperv.h
F: arch/x86/include/asm/hyperv-tlfs.h
F: arch/x86/kernel/cpu/mshyperv.c
F: arch/x86/hyperv
+F: drivers/clocksource/hyperv_timer.c
F: drivers/hid/hid-hyperv.c
F: drivers/hv/
F: drivers/input/serio/hyperv-keyboard.c
@@ -7168,6 +7169,7 @@ F: drivers/scsi/storvsc_drv.c
F: drivers/uio/uio_hv_generic.c
F: drivers/video/fbdev/hyperv_fb.c
F: net/vmw_vsock/hyperv_transport.c
+F: include/clocksource/hyperv_timer.h
F: include/linux/hyperv.h
F: include/uapi/linux/hyperv.h
F: tools/hv/
@@ -401,6 +401,12 @@ enum HV_GENERIC_SET_FORMAT {
#define HV_STATUS_INVALID_CONNECTION_ID 18
#define HV_STATUS_INSUFFICIENT_BUFFERS 19
+/*
+ * The Hyper-V TimeRefCount register and the TSC
+ * page provide a guest VM clock with 100ns tick rate
+ */
+#define HV_CLOCK_HZ (NSEC_PER_SEC/100)
+
typedef struct _HV_REFERENCE_TSC_PAGE {
__u32 tsc_sequence;
__u32 res1;
@@ -21,6 +21,7 @@
#include <linux/irq.h>
#include <linux/kexec.h>
#include <linux/i8253.h>
+#include <linux/random.h>
#include <asm/processor.h>
#include <asm/hypervisor.h>
#include <asm/hyperv-tlfs.h>
@@ -84,6 +85,7 @@ __visible void __irq_entry hv_stimer0_vector_handler(struct pt_regs *regs)
inc_irq_stat(hyperv_stimer0_count);
if (hv_stimer0_handler)
hv_stimer0_handler();
+ add_interrupt_randomness(HYPERV_STIMER0_VECTOR, 0);
ack_APIC_irq();
exiting_irq();
@@ -83,3 +83,4 @@ obj-$(CONFIG_ATCPIT100_TIMER) += timer-atcpit100.o
obj-$(CONFIG_RISCV_TIMER) += timer-riscv.o
obj-$(CONFIG_CSKY_MP_TIMER) += timer-mp-csky.o
obj-$(CONFIG_GX6605S_TIMER) += timer-gx6605s.o
+obj-$(CONFIG_HYPERV_TIMER) += hyperv_timer.o
new file mode 100644
@@ -0,0 +1,206 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Clocksource driver for the synthetic counter and timers
+ * provided by the Hyper-V hypervisor to guest VMs, as described
+ * in the Hyper-V Top Level Functional Spec (TLFS). This driver
+ * is instruction set architecture independent.
+ *
+ * Copyright (C) 2019, Microsoft, Inc.
+ *
+ * Author: Michael Kelley <mikelley@microsoft.com>
+ */
+
+#include <linux/percpu.h>
+#include <linux/cpumask.h>
+#include <linux/clockchips.h>
+#include <linux/cpuhotplug.h>
+#include <linux/mm.h>
+#include <clocksource/hyperv_timer.h>
+#include <asm/hyperv-tlfs.h>
+#include <asm/mshyperv.h>
+
+static struct clock_event_device __percpu *hv_clock_event;
+
+/*
+ * If false, we're using the old mechanism for stimer0 interrupts
+ * where it sends a VMbus message when it expires. The old
+ * mechanism is used when running on older versions of Hyper-V
+ * that don't support Direct Mode. While Hyper-V provides
+ * four stimer's per CPU, Linux uses only stimer0.
+ */
+static bool direct_mode_enabled;
+
+static int stimer0_irq;
+static int stimer0_vector;
+static int stimer0_message_sint;
+static int stimer0_cpuhp_online;
+
+/*
+ * ISR for when stimer0 is operating in Direct Mode. Direct Mode
+ * does not use VMbus or any VMbus messages, so process here and not
+ * in the VMbus driver code.
+ */
+void hv_stimer0_isr(void)
+{
+ struct clock_event_device *ce;
+
+ ce = this_cpu_ptr(hv_clock_event);
+ ce->event_handler(ce);
+}
+EXPORT_SYMBOL_GPL(hv_stimer0_isr);
+
+static int hv_ce_set_next_event(unsigned long delta,
+ struct clock_event_device *evt)
+{
+ u64 current_tick;
+
+ WARN_ON(!clockevent_state_oneshot(evt));
+
+ current_tick = hyperv_cs->read(NULL);
+ current_tick += delta;
+ hv_init_timer(0, current_tick);
+ return 0;
+}
+
+static int hv_ce_shutdown(struct clock_event_device *evt)
+{
+ hv_init_timer(0, 0);
+ hv_init_timer_config(0, 0);
+ if (direct_mode_enabled)
+ hv_disable_stimer0_percpu_irq(stimer0_irq);
+
+ return 0;
+}
+
+static int hv_ce_set_oneshot(struct clock_event_device *evt)
+{
+ union hv_stimer_config timer_cfg;
+
+ timer_cfg.as_uint64 = 0;
+ timer_cfg.enable = 1;
+ timer_cfg.auto_enable = 1;
+ if (direct_mode_enabled) {
+ /*
+ * When it expires, the timer will directly interrupt
+ * on the specified hardware vector/IRQ.
+ */
+ timer_cfg.direct_mode = 1;
+ timer_cfg.apic_vector = stimer0_vector;
+ hv_enable_stimer0_percpu_irq(stimer0_irq);
+ } else {
+ /*
+ * When it expires, the timer will generate a VMbus message,
+ * to be handled by the normal VMbus interrupt handler.
+ */
+ timer_cfg.direct_mode = 0;
+ timer_cfg.sintx = stimer0_message_sint;
+ }
+ hv_init_timer_config(0, timer_cfg.as_uint64);
+ return 0;
+}
+
+/*
+ * hv_stimer_init - Per-cpu initialization of the clockevent
+ */
+static int hv_stimer_init(unsigned int cpu)
+{
+ struct clock_event_device *ce;
+
+ if (ms_hyperv.features & HV_MSR_SYNTIMER_AVAILABLE) {
+ ce = per_cpu_ptr(hv_clock_event, cpu);
+ ce->name = "Hyper-V clockevent";
+ ce->features = CLOCK_EVT_FEAT_ONESHOT;
+ ce->cpumask = cpumask_of(cpu);
+ ce->rating = 1000;
+ ce->set_state_shutdown = hv_ce_shutdown;
+ ce->set_state_oneshot = hv_ce_set_oneshot;
+ ce->set_next_event = hv_ce_set_next_event;
+
+ clockevents_config_and_register(ce,
+ HV_CLOCK_HZ,
+ HV_MIN_DELTA_TICKS,
+ HV_MAX_MAX_DELTA_TICKS);
+ }
+ return 0;
+}
+
+/*
+ * hv_stimer_cleanup - Per-cpu cleanup of the clockevent
+ */
+int hv_stimer_cleanup(unsigned int cpu)
+{
+ struct clock_event_device *ce;
+
+ /* Turn off clockevent device */
+ if (ms_hyperv.features & HV_MSR_SYNTIMER_AVAILABLE) {
+ ce = per_cpu_ptr(hv_clock_event, cpu);
+ clockevents_unbind_device(ce, cpu);
+ hv_ce_shutdown(ce);
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(hv_stimer_cleanup);
+
+/* hv_stimer_alloc - Global initialization of the clockevent and stimer0 */
+int hv_stimer_alloc(int sint)
+{
+ int ret;
+
+ hv_clock_event = alloc_percpu(struct clock_event_device);
+ if (!hv_clock_event)
+ return -ENOMEM;
+
+ direct_mode_enabled = ms_hyperv.misc_features &
+ HV_STIMER_DIRECT_MODE_AVAILABLE;
+ if (direct_mode_enabled &&
+ hv_setup_stimer0_irq(&stimer0_irq, &stimer0_vector,
+ hv_stimer0_isr))
+ goto err_irq;
+
+ stimer0_message_sint = sint;
+
+ ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "hyperv/stimer0:online",
+ hv_stimer_init, hv_stimer_cleanup);
+ if (ret < 0)
+ goto err_cpuhp;
+ stimer0_cpuhp_online = ret;
+ return 0;
+
+err_cpuhp:
+ if (direct_mode_enabled)
+ hv_remove_stimer0_irq(stimer0_irq);
+err_irq:
+ free_percpu(hv_clock_event);
+ return -EINVAL;
+}
+EXPORT_SYMBOL_GPL(hv_stimer_alloc);
+
+/* hv_stimer_free - Free global resources allocated by hv_stimer_alloc() */
+void hv_stimer_free(void)
+{
+ cpuhp_remove_state(stimer0_cpuhp_online);
+ if (direct_mode_enabled)
+ hv_remove_stimer0_irq(stimer0_irq);
+ free_percpu(hv_clock_event);
+}
+EXPORT_SYMBOL_GPL(hv_stimer_free);
+
+/*
+ * Do a global cleanup of clockevents for the cases of kexec and
+ * vmbus exit
+ */
+void hv_stimer_global_cleanup(void)
+{
+ int cpu;
+ struct clock_event_device *ce;
+
+ if (ms_hyperv.features & HV_MSR_SYNTIMER_AVAILABLE)
+ for_each_present_cpu(cpu) {
+ ce = per_cpu_ptr(hv_clock_event, cpu);
+ clockevents_unbind_device(ce, cpu);
+ }
+ hv_stimer_free();
+}
+EXPORT_SYMBOL_GPL(hv_stimer_global_cleanup);
@@ -10,6 +10,9 @@ config HYPERV
Select this option to run Linux as a Hyper-V client operating
system.
+config HYPERV_TIMER
+ def_bool HYPERV
+
config HYPERV_TSCPAGE
def_bool HYPERV && X86_64
@@ -36,21 +36,6 @@
struct hv_context hv_context;
/*
- * If false, we're using the old mechanism for stimer0 interrupts
- * where it sends a VMbus message when it expires. The old
- * mechanism is used when running on older versions of Hyper-V
- * that don't support Direct Mode. While Hyper-V provides
- * four stimer's per CPU, Linux uses only stimer0.
- */
-static bool direct_mode_enabled;
-static int stimer0_irq;
-static int stimer0_vector;
-
-#define HV_TIMER_FREQUENCY (10 * 1000 * 1000) /* 100ns period */
-#define HV_MAX_MAX_DELTA_TICKS 0xffffffff
-#define HV_MIN_DELTA_TICKS 1
-
-/*
* hv_init - Main initialization routine.
*
* This routine must be called before any other routines in here are called
@@ -60,9 +45,6 @@ int hv_init(void)
hv_context.cpu_context = alloc_percpu(struct hv_per_cpu_context);
if (!hv_context.cpu_context)
return -ENOMEM;
-
- direct_mode_enabled = ms_hyperv.misc_features &
- HV_STIMER_DIRECT_MODE_AVAILABLE;
return 0;
}
@@ -101,89 +83,6 @@ int hv_post_message(union hv_connection_id connection_id,
return status & 0xFFFF;
}
-/*
- * ISR for when stimer0 is operating in Direct Mode. Direct Mode
- * does not use VMbus or any VMbus messages, so process here and not
- * in the VMbus driver code.
- */
-
-static void hv_stimer0_isr(void)
-{
- struct hv_per_cpu_context *hv_cpu;
-
- hv_cpu = this_cpu_ptr(hv_context.cpu_context);
- hv_cpu->clk_evt->event_handler(hv_cpu->clk_evt);
- add_interrupt_randomness(stimer0_vector, 0);
-}
-
-static int hv_ce_set_next_event(unsigned long delta,
- struct clock_event_device *evt)
-{
- u64 current_tick;
-
- WARN_ON(!clockevent_state_oneshot(evt));
-
- current_tick = hyperv_cs->read(NULL);
- current_tick += delta;
- hv_init_timer(0, current_tick);
- return 0;
-}
-
-static int hv_ce_shutdown(struct clock_event_device *evt)
-{
- hv_init_timer(0, 0);
- hv_init_timer_config(0, 0);
- if (direct_mode_enabled)
- hv_disable_stimer0_percpu_irq(stimer0_irq);
-
- return 0;
-}
-
-static int hv_ce_set_oneshot(struct clock_event_device *evt)
-{
- union hv_stimer_config timer_cfg;
-
- timer_cfg.as_uint64 = 0;
- timer_cfg.enable = 1;
- timer_cfg.auto_enable = 1;
- if (direct_mode_enabled) {
- /*
- * When it expires, the timer will directly interrupt
- * on the specified hardware vector/IRQ.
- */
- timer_cfg.direct_mode = 1;
- timer_cfg.apic_vector = stimer0_vector;
- hv_enable_stimer0_percpu_irq(stimer0_irq);
- } else {
- /*
- * When it expires, the timer will generate a VMbus message,
- * to be handled by the normal VMbus interrupt handler.
- */
- timer_cfg.direct_mode = 0;
- timer_cfg.sintx = VMBUS_MESSAGE_SINT;
- }
- hv_init_timer_config(0, timer_cfg.as_uint64);
- return 0;
-}
-
-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;
- /*
- * Avoid settint dev->owner = THIS_MODULE deliberately as doing so will
- * result in clockevents_config_and_register() taking additional
- * references to the hv_vmbus module making it impossible to unload.
- */
-
- dev->set_state_shutdown = hv_ce_shutdown;
- dev->set_state_oneshot = hv_ce_set_oneshot;
- dev->set_next_event = hv_ce_set_next_event;
-}
-
-
int hv_synic_alloc(void)
{
int cpu;
@@ -212,14 +111,6 @@ int hv_synic_alloc(void)
tasklet_init(&hv_cpu->msg_dpc,
vmbus_on_msg_dpc, (unsigned long) hv_cpu);
- hv_cpu->clk_evt = kzalloc(sizeof(struct clock_event_device),
- GFP_KERNEL);
- if (hv_cpu->clk_evt == NULL) {
- pr_err("Unable to allocate clock event device\n");
- goto err;
- }
- hv_init_clockevent_device(hv_cpu->clk_evt, cpu);
-
hv_cpu->synic_message_page =
(void *)get_zeroed_page(GFP_ATOMIC);
if (hv_cpu->synic_message_page == NULL) {
@@ -242,11 +133,6 @@ int hv_synic_alloc(void)
INIT_LIST_HEAD(&hv_cpu->chan_list);
}
- if (direct_mode_enabled &&
- hv_setup_stimer0_irq(&stimer0_irq, &stimer0_vector,
- hv_stimer0_isr))
- goto err;
-
return 0;
err:
/*
@@ -265,7 +151,6 @@ void hv_synic_free(void)
struct hv_per_cpu_context *hv_cpu
= per_cpu_ptr(hv_context.cpu_context, cpu);
- kfree(hv_cpu->clk_evt);
free_page((unsigned long)hv_cpu->synic_event_page);
free_page((unsigned long)hv_cpu->synic_message_page);
free_page((unsigned long)hv_cpu->post_msg_page);
@@ -324,39 +209,10 @@ int hv_synic_init(unsigned int cpu)
hv_set_synic_state(sctrl.as_uint64);
- /*
- * Register the per-cpu clockevent source.
- */
- if (ms_hyperv.features & HV_MSR_SYNTIMER_AVAILABLE)
- clockevents_config_and_register(hv_cpu->clk_evt,
- HV_TIMER_FREQUENCY,
- HV_MIN_DELTA_TICKS,
- HV_MAX_MAX_DELTA_TICKS);
return 0;
}
/*
- * hv_synic_clockevents_cleanup - Cleanup clockevent devices
- */
-void hv_synic_clockevents_cleanup(void)
-{
- int cpu;
-
- if (!(ms_hyperv.features & HV_MSR_SYNTIMER_AVAILABLE))
- return;
-
- if (direct_mode_enabled)
- hv_remove_stimer0_irq(stimer0_irq);
-
- for_each_present_cpu(cpu) {
- struct hv_per_cpu_context *hv_cpu
- = per_cpu_ptr(hv_context.cpu_context, cpu);
-
- clockevents_unbind_device(hv_cpu->clk_evt, cpu);
- }
-}
-
-/*
* hv_synic_cleanup - Cleanup routine for hv_synic_init().
*/
int hv_synic_cleanup(unsigned int cpu)
@@ -401,16 +257,6 @@ int hv_synic_cleanup(unsigned int cpu)
if (channel_found && vmbus_connection.conn_state == CONNECTED)
return -EBUSY;
- /* Turn off clockevent device */
- if (ms_hyperv.features & HV_MSR_SYNTIMER_AVAILABLE) {
- struct hv_per_cpu_context *hv_cpu
- = this_cpu_ptr(hv_context.cpu_context);
-
- clockevents_unbind_device(hv_cpu->clk_evt, cpu);
- hv_ce_shutdown(hv_cpu->clk_evt);
- put_cpu_ptr(hv_cpu);
- }
-
hv_get_synint_state(VMBUS_MESSAGE_SINT, shared_sint.as_uint64);
shared_sint.masked = 1;
@@ -151,7 +151,6 @@ struct hv_per_cpu_context {
* per-cpu list of the channels based on their CPU affinity.
*/
struct list_head chan_list;
- struct clock_event_device *clk_evt;
};
struct hv_context {
@@ -189,8 +188,6 @@ extern int hv_post_message(union hv_connection_id connection_id,
extern int hv_synic_cleanup(unsigned int cpu);
-extern void hv_synic_clockevents_cleanup(void);
-
/* Interface */
@@ -43,6 +43,7 @@
#include <linux/kdebug.h>
#include <linux/efi.h>
#include <linux/random.h>
+#include <clocksource/hyperv_timer.h>
#include "hyperv_vmbus.h"
struct vmbus_dynid {
@@ -939,17 +940,6 @@ static void vmbus_onmessage_work(struct work_struct *work)
kfree(ctx);
}
-static void hv_process_timer_expiration(struct hv_message *msg,
- struct hv_per_cpu_context *hv_cpu)
-{
- struct clock_event_device *dev = hv_cpu->clk_evt;
-
- if (dev->event_handler)
- dev->event_handler(dev);
-
- vmbus_signal_eom(msg, HVMSG_TIMER_EXPIRED);
-}
-
void vmbus_on_msg_dpc(unsigned long data)
{
struct hv_per_cpu_context *hv_cpu = (void *)data;
@@ -1143,9 +1133,10 @@ static void vmbus_isr(void)
/* Check if there are actual msgs to be processed */
if (msg->header.message_type != HVMSG_NONE) {
- if (msg->header.message_type == HVMSG_TIMER_EXPIRED)
- hv_process_timer_expiration(msg, hv_cpu);
- else
+ if (msg->header.message_type == HVMSG_TIMER_EXPIRED) {
+ hv_stimer0_isr();
+ vmbus_signal_eom(msg, HVMSG_TIMER_EXPIRED);
+ } else
tasklet_schedule(&hv_cpu->msg_dpc);
}
@@ -1248,8 +1239,8 @@ static int vmbus_bus_init(void)
if (ret)
goto err_alloc;
/*
- * Initialize the per-cpu interrupt state and
- * connect to the host.
+ * Initialize the per-cpu interrupt state and stimer state.
+ * Then connect to the host.
*/
ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "hyperv/vmbus:online",
hv_synic_init, hv_synic_cleanup);
@@ -1257,6 +1248,10 @@ static int vmbus_bus_init(void)
goto err_alloc;
hyperv_cpuhp_online = ret;
+ ret = hv_stimer_alloc(VMBUS_MESSAGE_SINT);
+ if (ret < 0)
+ goto err_stimer_alloc;
+
ret = vmbus_connect();
if (ret)
goto err_connect;
@@ -1301,6 +1296,8 @@ static int vmbus_bus_init(void)
return 0;
err_connect:
+ hv_stimer_free();
+err_stimer_alloc:
cpuhp_remove_state(hyperv_cpuhp_online);
err_alloc:
hv_synic_free();
@@ -1971,7 +1968,7 @@ static int vmbus_acpi_add(struct acpi_device *device)
static void hv_kexec_handler(void)
{
- hv_synic_clockevents_cleanup();
+ hv_stimer_global_cleanup();
vmbus_initiate_unload(false);
vmbus_connection.conn_state = DISCONNECTED;
/* Make sure conn_state is set as hv_synic_cleanup checks for it */
@@ -1982,6 +1979,8 @@ static void hv_kexec_handler(void)
static void hv_crash_handler(struct pt_regs *regs)
{
+ int cpu;
+
vmbus_initiate_unload(true);
/*
* In crash handler we can't schedule synic cleanup for all CPUs,
@@ -1989,7 +1988,9 @@ static void hv_crash_handler(struct pt_regs *regs)
* for kdump.
*/
vmbus_connection.conn_state = DISCONNECTED;
- hv_synic_cleanup(smp_processor_id());
+ cpu = smp_processor_id();
+ hv_stimer_cleanup(cpu);
+ hv_synic_cleanup(cpu);
hyperv_cleanup();
};
@@ -2038,7 +2039,7 @@ static void __exit vmbus_exit(void)
hv_remove_kexec_handler();
hv_remove_crash_handler();
vmbus_connection.conn_state = DISCONNECTED;
- hv_synic_clockevents_cleanup();
+ hv_stimer_global_cleanup();
vmbus_disconnect();
hv_remove_vmbus_irq();
for_each_online_cpu(cpu) {
new file mode 100644
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * Definitions for the clocksource provided by the Hyper-V
+ * hypervisor to guest VMs, as described in the Hyper-V Top
+ * Level Functional Spec (TLFS).
+ *
+ * Copyright (C) 2019, Microsoft, Inc.
+ *
+ * Author: Michael Kelley <mikelley@microsoft.com>
+ */
+
+#ifndef __CLKSOURCE_HYPERV_TIMER_H
+#define __CLKSOURCE_HYPERV_TIMER_H
+
+#define HV_MAX_MAX_DELTA_TICKS 0xffffffff
+#define HV_MIN_DELTA_TICKS 1
+
+/* Routines called by the VMbus driver */
+extern int hv_stimer_alloc(int sint);
+extern void hv_stimer_free(void);
+extern int hv_stimer_cleanup(unsigned int cpu);
+extern void hv_stimer_global_cleanup(void);
+extern void hv_stimer0_isr(void);
+
+#endif
Clockevents code for Hyper-V synthetic timers is currently mixed in with other Hyper-V code. Move the code to a Hyper-V specific driver in the "clocksource" directory. Update the VMbus driver to call initialization and cleanup routines since the Hyper-V synthetic timers are not independently enumerated in ACPI. No behavior is changed and no new functionality is added. Suggested-by: Marc Zyngier <marc.zyngier@arm.com> Signed-off-by: Michael Kelley <mikelley@microsoft.com> --- MAINTAINERS | 2 + arch/x86/include/asm/hyperv-tlfs.h | 6 ++ arch/x86/kernel/cpu/mshyperv.c | 2 + drivers/clocksource/Makefile | 1 + drivers/clocksource/hyperv_timer.c | 206 +++++++++++++++++++++++++++++++++++++ drivers/hv/Kconfig | 3 + drivers/hv/hv.c | 154 --------------------------- drivers/hv/hyperv_vmbus.h | 3 - drivers/hv/vmbus_drv.c | 39 +++---- include/clocksource/hyperv_timer.h | 26 +++++ 10 files changed, 266 insertions(+), 176 deletions(-) create mode 100644 drivers/clocksource/hyperv_timer.c create mode 100644 include/clocksource/hyperv_timer.h