[tip:x86/hyperv] x86/hyperv: Reenlightenment notifications support

From: tip-bot for Vitaly Kuznetsov
Date: Tue Jan 30 2018 - 18:03:09 EST

Next message: tip-bot for Vitaly Kuznetsov: "[tip:x86/hyperv] x86/hyperv: Redirect reenlightment notifications on CPU offlining"
Previous message: Eric Biggers: "Re: general protection fault in sctp_stream_free"
In reply to: Vitaly Kuznetsov: "[PATCH v4 3/7] x86/hyper-v: reenlightenment notifications support"
Next in thread: Vitaly Kuznetsov: "[PATCH v4 4/7] x86/hyper-v: redirect reenlightment notifications on CPU offlining"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

Commit-ID: 93286261de1b46339aa27cd4c639b21778f6cade
Gitweb: https://git.kernel.org/tip/93286261de1b46339aa27cd4c639b21778f6cade
Author: Vitaly Kuznetsov <vkuznets@xxxxxxxxxx>
AuthorDate: Wed, 24 Jan 2018 14:23:33 +0100
Committer: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
CommitDate: Tue, 30 Jan 2018 23:55:32 +0100

x86/hyperv: Reenlightenment notifications support

Hyper-V supports Live Migration notification. This is supposed to be used
in conjunction with TSC emulation: when a VM is migrated to a host with
different TSC frequency for some short period the host emulates the
accesses to TSC and sends an interrupt to notify about the event. When the
guest is done updating everything it can disable TSC emulation and
everything will start working fast again.

These notifications weren't required until now as Hyper-V guests are not
supposed to use TSC as a clocksource: in Linux the TSC is even marked as
unstable on boot. Guests normally use 'tsc page' clocksource and host
updates its values on migrations automatically.

Things change when with nested virtualization: even when the PV
clocksources (kvm-clock or tsc page) are passed through to the nested
guests the TSC frequency and frequency changes need to be know..

Hyper-V Top Level Functional Specification (as of v5.0b) wrongly specifies
EAX:BIT(12) of CPUID:0x40000009 as the feature identification bit. The
right one to check is EAX:BIT(13) of CPUID:0x40000003. I was assured that
the fix in on the way.

Signed-off-by: Vitaly Kuznetsov <vkuznets@xxxxxxxxxx>
Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Reviewed-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Stephen Hemminger <sthemmin@xxxxxxxxxxxxx>
Cc: kvm@xxxxxxxxxxxxxxx
Cc: Radim KrÄmÃÅ <rkrcmar@xxxxxxxxxx>
Cc: Haiyang Zhang <haiyangz@xxxxxxxxxxxxx>
Cc: "Michael Kelley (EOSG)" <Michael.H.Kelley@xxxxxxxxxxxxx>
Cc: Roman Kagan <rkagan@xxxxxxxxxxxxx>
Cc: Andy Lutomirski <luto@xxxxxxxxxx>
Cc: devel@xxxxxxxxxxxxxxxxxxxxxx
Cc: Paolo Bonzini <pbonzini@xxxxxxxxxx>
Cc: "K. Y. Srinivasan" <kys@xxxxxxxxxxxxx>
Cc: Cathy Avery <cavery@xxxxxxxxxx>
Cc: Mohammed Gamal <mmorsy@xxxxxxxxxx>
Link: https://lkml.kernel.org/r/20180124132337.30138-4-vkuznets@xxxxxxxxxx

---
arch/x86/entry/entry_32.S | 3 ++
arch/x86/entry/entry_64.S | 3 ++
arch/x86/hyperv/hv_init.c | 89 ++++++++++++++++++++++++++++++++++++++
arch/x86/include/asm/irq_vectors.h | 7 ++-
arch/x86/include/asm/mshyperv.h | 9 ++++
arch/x86/include/uapi/asm/hyperv.h | 27 ++++++++++++
arch/x86/kernel/cpu/mshyperv.c | 6 +++
7 files changed, 143 insertions(+), 1 deletion(-)

diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index 2a35b1e..7a796eed 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -895,6 +895,9 @@ BUILD_INTERRUPT3(xen_hvm_callback_vector, HYPERVISOR_CALLBACK_VECTOR,
BUILD_INTERRUPT3(hyperv_callback_vector, HYPERVISOR_CALLBACK_VECTOR,
hyperv_vector_handler)

+BUILD_INTERRUPT3(hyperv_reenlightenment_vector, HYPERV_REENLIGHTENMENT_VECTOR,
+ hyperv_reenlightenment_intr)
+
#endif /* CONFIG_HYPERV */

ENTRY(page_fault)
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index a835704..553aa49 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -1245,6 +1245,9 @@ apicinterrupt3 HYPERVISOR_CALLBACK_VECTOR \
#if IS_ENABLED(CONFIG_HYPERV)
apicinterrupt3 HYPERVISOR_CALLBACK_VECTOR \
hyperv_callback_vector hyperv_vector_handler
+
+apicinterrupt3 HYPERV_REENLIGHTENMENT_VECTOR \
+ hyperv_reenlightenment_vector hyperv_reenlightenment_intr
#endif /* CONFIG_HYPERV */

idtentry debug do_debug has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK
diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index 1a6c63f..712ac40 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -18,6 +18,8 @@
*/

#include <linux/types.h>
+#include <asm/apic.h>
+#include <asm/desc.h>
#include <asm/hypervisor.h>
#include <asm/hyperv.h>
#include <asm/mshyperv.h>
@@ -102,6 +104,93 @@ static int hv_cpu_init(unsigned int cpu)
return 0;
}

+static void (*hv_reenlightenment_cb)(void);
+
+static void hv_reenlightenment_notify(struct work_struct *dummy)
+{
+ struct hv_tsc_emulation_status emu_status;
+
+ rdmsrl(HV_X64_MSR_TSC_EMULATION_STATUS, *(u64 *)&emu_status);
+
+ /* Don't issue the callback if TSC accesses are not emulated */
+ if (hv_reenlightenment_cb && emu_status.inprogress)
+ hv_reenlightenment_cb();
+}
+static DECLARE_DELAYED_WORK(hv_reenlightenment_work, hv_reenlightenment_notify);
+
+void hyperv_stop_tsc_emulation(void)
+{
+ u64 freq;
+ struct hv_tsc_emulation_status emu_status;
+
+ rdmsrl(HV_X64_MSR_TSC_EMULATION_STATUS, *(u64 *)&emu_status);
+ emu_status.inprogress = 0;
+ wrmsrl(HV_X64_MSR_TSC_EMULATION_STATUS, *(u64 *)&emu_status);
+
+ rdmsrl(HV_X64_MSR_TSC_FREQUENCY, freq);
+ tsc_khz = div64_u64(freq, 1000);
+}
+EXPORT_SYMBOL_GPL(hyperv_stop_tsc_emulation);
+
+static inline bool hv_reenlightenment_available(void)
+{
+ /*
+ * Check for required features and priviliges to make TSC frequency
+ * change notifications work.
+ */
+ return ms_hyperv.features & HV_X64_ACCESS_FREQUENCY_MSRS &&
+ ms_hyperv.misc_features & HV_FEATURE_FREQUENCY_MSRS_AVAILABLE &&
+ ms_hyperv.features & HV_X64_ACCESS_REENLIGHTENMENT;
+}
+
+__visible void __irq_entry hyperv_reenlightenment_intr(struct pt_regs *regs)
+{
+ entering_ack_irq();
+
+ schedule_delayed_work(&hv_reenlightenment_work, HZ/10);
+
+ exiting_irq();
+}
+
+void set_hv_tscchange_cb(void (*cb)(void))
+{
+ struct hv_reenlightenment_control re_ctrl = {
+ .vector = HYPERV_REENLIGHTENMENT_VECTOR,
+ .enabled = 1,
+ .target_vp = hv_vp_index[smp_processor_id()]
+ };
+ struct hv_tsc_emulation_control emu_ctrl = {.enabled = 1};
+
+ if (!hv_reenlightenment_available()) {
+ pr_warn("Hyper-V: reenlightenment support is unavailable\n");
+ return;
+ }
+
+ hv_reenlightenment_cb = cb;
+
+ /* Make sure callback is registered before we write to MSRs */
+ wmb();
+
+ wrmsrl(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *((u64 *)&re_ctrl));
+ wrmsrl(HV_X64_MSR_TSC_EMULATION_CONTROL, *((u64 *)&emu_ctrl));
+}
+EXPORT_SYMBOL_GPL(set_hv_tscchange_cb);
+
+void clear_hv_tscchange_cb(void)
+{
+ struct hv_reenlightenment_control re_ctrl;
+
+ if (!hv_reenlightenment_available())
+ return;
+
+ rdmsrl(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *(u64 *)&re_ctrl);
+ re_ctrl.enabled = 0;
+ wrmsrl(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *(u64 *)&re_ctrl);
+
+ hv_reenlightenment_cb = NULL;
+}
+EXPORT_SYMBOL_GPL(clear_hv_tscchange_cb);
+
/*
* This function is to be invoked early in the boot sequence after the
* hypervisor has been detected.
diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h
index 67421f6..e71c112 100644
--- a/arch/x86/include/asm/irq_vectors.h
+++ b/arch/x86/include/asm/irq_vectors.h
@@ -103,7 +103,12 @@
#endif

#define MANAGED_IRQ_SHUTDOWN_VECTOR 0xef
-#define LOCAL_TIMER_VECTOR 0xee
+
+#if IS_ENABLED(CONFIG_HYPERV)
+#define HYPERV_REENLIGHTENMENT_VECTOR 0xee
+#endif
+
+#define LOCAL_TIMER_VECTOR 0xed

#define NR_VECTORS 256

diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index 6b1d4ea..1790002a 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -160,6 +160,7 @@ static inline void vmbus_signal_eom(struct hv_message *msg, u32 old_msg_type)
#define hv_set_synint_state(int_num, val) wrmsrl(int_num, val)

void hyperv_callback_vector(void);
+void hyperv_reenlightenment_vector(void);
#ifdef CONFIG_TRACING
#define trace_hyperv_callback_vector hyperv_callback_vector
#endif
@@ -316,11 +317,19 @@ void hyper_alloc_mmu(void);
void hyperv_report_panic(struct pt_regs *regs, long err);
bool hv_is_hypercall_page_setup(void);
void hyperv_cleanup(void);
+
+void hyperv_reenlightenment_intr(struct pt_regs *regs);
+void set_hv_tscchange_cb(void (*cb)(void));
+void clear_hv_tscchange_cb(void);
+void hyperv_stop_tsc_emulation(void);
#else /* CONFIG_HYPERV */
static inline void hyperv_init(void) {}
static inline bool hv_is_hypercall_page_setup(void) { return false; }
static inline void hyperv_cleanup(void) {}
static inline void hyperv_setup_mmu_ops(void) {}
+static inline void set_hv_tscchange_cb(void (*cb)(void)) {}
+static inline void clear_hv_tscchange_cb(void) {}
+static inline void hyperv_stop_tsc_emulation(void) {};
#endif /* CONFIG_HYPERV */

#ifdef CONFIG_HYPERV_TSCPAGE
diff --git a/arch/x86/include/uapi/asm/hyperv.h b/arch/x86/include/uapi/asm/hyperv.h
index 1a5bfea..197c2e6 100644
--- a/arch/x86/include/uapi/asm/hyperv.h
+++ b/arch/x86/include/uapi/asm/hyperv.h
@@ -40,6 +40,9 @@
*/
#define HV_X64_ACCESS_FREQUENCY_MSRS (1 << 11)

+/* AccessReenlightenmentControls privilege */
+#define HV_X64_ACCESS_REENLIGHTENMENT BIT(13)
+
/*
* Basic SynIC MSRs (HV_X64_MSR_SCONTROL through HV_X64_MSR_EOM
* and HV_X64_MSR_SINT0 through HV_X64_MSR_SINT15) available
@@ -234,6 +237,30 @@
#define HV_X64_MSR_CRASH_PARAMS \
(1 + (HV_X64_MSR_CRASH_P4 - HV_X64_MSR_CRASH_P0))

+/* TSC emulation after migration */
+#define HV_X64_MSR_REENLIGHTENMENT_CONTROL 0x40000106
+
+struct hv_reenlightenment_control {
+ u64 vector:8;
+ u64 reserved1:8;
+ u64 enabled:1;
+ u64 reserved2:15;
+ u64 target_vp:32;
+};
+
+#define HV_X64_MSR_TSC_EMULATION_CONTROL 0x40000107
+#define HV_X64_MSR_TSC_EMULATION_STATUS 0x40000108
+
+struct hv_tsc_emulation_control {
+ u64 enabled:1;
+ u64 reserved:63;
+};
+
+struct hv_tsc_emulation_status {
+ u64 inprogress:1;
+ u64 reserved:63;
+};
+
#define HV_X64_MSR_HYPERCALL_ENABLE 0x00000001
#define HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT 12
#define HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_MASK \
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 85eb5fc..9340f41 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -251,6 +251,12 @@ static void __init ms_hyperv_init_platform(void)
hyperv_setup_mmu_ops();
/* Setup the IDT for hypervisor callback */
alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, hyperv_callback_vector);
+
+ /* Setup the IDT for reenlightenment notifications */
+ if (ms_hyperv.features & HV_X64_ACCESS_REENLIGHTENMENT)
+ alloc_intr_gate(HYPERV_REENLIGHTENMENT_VECTOR,
+ hyperv_reenlightenment_vector);
+
#endif
}

Next message: tip-bot for Vitaly Kuznetsov: "[tip:x86/hyperv] x86/hyperv: Redirect reenlightment notifications on CPU offlining"
Previous message: Eric Biggers: "Re: general protection fault in sctp_stream_free"
In reply to: Vitaly Kuznetsov: "[PATCH v4 3/7] x86/hyper-v: reenlightenment notifications support"
Next in thread: Vitaly Kuznetsov: "[PATCH v4 4/7] x86/hyper-v: redirect reenlightment notifications on CPU offlining"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]