Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
From:   Vitaly Kuznetsov <vkuznets@redhat.com>
To:     kvm@vger.kernel.org, x86@kernel.org
Cc:     Paolo Bonzini <pbonzini@redhat.com>,
        =?UTF-8?q?Radim=20Kr=C4=8Dm=C3=A1=C5=99?= <rkrcmar@redhat.com>,
        Thomas Gleixner <tglx@linutronix.de>,
        Ingo Molnar <mingo@redhat.com>,
        "H. Peter Anvin" <hpa@zytor.com>,
        "K. Y. Srinivasan" <kys@microsoft.com>,
        Haiyang Zhang <haiyangz@microsoft.com>,
        Stephen Hemminger <sthemmin@microsoft.com>,
        "Michael Kelley (EOSG)" <Michael.H.Kelley@microsoft.com>,
        Andy Lutomirski <luto@kernel.org>,
        Mohammed Gamal <mmorsy@redhat.com>,
        Cathy Avery <cavery@redhat.com>,
        Roman Kagan <rkagan@virtuozzo.com>,
        linux-kernel@vger.kernel.org, devel@linuxdriverproject.org
Subject: [PATCH v4 3/7] x86/hyper-v: reenlightenment notifications support
Date:   Wed, 24 Jan 2018 14:23:33 +0100
Message-Id: <20180124132337.30138-4-vkuznets@redhat.com>
In-Reply-To: <20180124132337.30138-1-vkuznets@redhat.com>
References: <20180124132337.30138-1-vkuznets@redhat.com>
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

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

We didn't need these notifications before as Hyper-V guests are not
supposed to use TSC as a clocksource: in Linux we even mark it as unstable
on boot. Guests normally use 'tsc page' clocksouce and host updates its
values on migrations automatically.

Things change when we want to run nested virtualization: even when we pass
through PV clocksources (kvm-clock or tsc page) to our guests we need to
know TSC frequency and when it changes.

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@redhat.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
---
v3 -> v4:
- drop 'include <linux/interrupt.h>' (and __visible/_irq_entry from
  hyperv_reenlightenment_intr declaration) from mshyperv.h
  [kbuild robot]
---
 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 60c4c342316c..2938cf89d473 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -894,6 +894,9 @@ 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 ff6f8022612c..b04cfd7f6e4c 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -1244,6 +1244,9 @@ 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 1a6c63f721bc..712ac40081f7 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 67421f649cfa..e71c1120426b 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 6b1d4ea78270..1790002a2052 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 1a5bfead93b4..197c2e6c7376 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 85eb5fc180c8..9340f41ce8d3 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
 }
 
-- 
2.14.3