[PATCH v1 2/3] x86/xen/time: setup vcpu 0 time info page

[Joao Martins]

In order to support pvclock vdso on xen we need to setup the time
info page for vcpu 0 and register the page with Xen using the
VCPUOP_register_vcpu_time_memory_area hypercall. This hypercall
will also forcefully update the pvti which will set some of the
necessary flags for vdso. Afterwards we check if it supports the
PVCLOCK_TSC_STABLE_BIT flag which is mandatory for having
vdso/vsyscall support. And if so, it will set the cpu 0 pvti that
will be later on used when mapping the vdso image.

The xen headers are also updated to include the new hypercall for
registering the secondary vcpu_time_info struct.

Signed-off-by: Joao Martins <joao.m.martins@xxxxxxxxxx>
---
Changes since RFC:
 (Comments from Boris and David)
 * Remove Kconfig option
 * Use get_zeroed_page/free/page
 * Remove the hypercall availability check
 * Unregister pvti with arg.addr.v = NULL if stable bit isn't supported.
 (New)
 * Set secondary copy on restore such that it works on migration.
 * Drop global xen_clock variable and stash it locally on
 xen_setup_vsyscall_time_info.
 * WARN_ON(ret) if we fail to unregister the pvti.
---
 arch/x86/xen/enlighten.c     |  2 ++
 arch/x86/xen/time.c          | 51 ++++++++++++++++++++++++++++++++++++++++++++
 arch/x86/xen/xen-ops.h       |  1 +
 include/xen/interface/vcpu.h | 28 ++++++++++++++++++++++++
 4 files changed, 82 insertions(+)

diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 51ef952..15d271d 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -270,6 +270,8 @@ void xen_vcpu_restore(void)
 		    HYPERVISOR_vcpu_op(VCPUOP_up, xen_vcpu_nr(cpu), NULL))
 			BUG();
 	}
+
+	xen_setup_vsyscall_time_info(0);
 }
 
 static void __init xen_banner(void)
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index 1e69956..e90f703 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -367,6 +367,56 @@ static const struct pv_time_ops xen_time_ops __initconst = {
 	.steal_clock = xen_steal_clock,
 };
 
+int xen_setup_vsyscall_time_info(int cpu)
+{
+	struct pvclock_vsyscall_time_info *xen_clock;
+	struct vcpu_register_time_memory_area t;
+	struct pvclock_vcpu_time_info *pvti;
+	unsigned long addr;
+	u8 flags;
+	int ret;
+
+	addr = get_zeroed_page(GFP_KERNEL);
+	if (!addr)
+		return -ENOMEM;
+
+	xen_clock = (struct pvclock_vsyscall_time_info *) addr;
+	memset(xen_clock, 0, PAGE_SIZE);
+
+	t.addr.v = &xen_clock->pvti;
+
+	ret = HYPERVISOR_vcpu_op(VCPUOP_register_vcpu_time_memory_area,
+				 cpu, &t);
+
+	if (ret) {
+		pr_debug("xen: cannot register vcpu_time_info err %d\n", ret);
+		free_page(addr);
+		return ret;
+	}
+
+	pvti = &xen_clock->pvti;
+	flags = pvti->flags;
+
+	if (!(flags & PVCLOCK_TSC_STABLE_BIT)) {
+		t.addr.v = NULL;
+		ret = HYPERVISOR_vcpu_op(VCPUOP_register_vcpu_time_memory_area,
+					 cpu, &t);
+		if (!ret)
+			free_page(addr);
+
+		WARN_ON(ret);
+		pr_debug("xen: VCLOCK_PVCLOCK not supported\n");
+		return -ENOTSUPP;
+	}
+
+	pvclock_set_flags(PVCLOCK_TSC_STABLE_BIT);
+	pvclock_set_pvti_cpu0_va(xen_clock);
+
+	xen_clocksource.archdata.vclock_mode = VCLOCK_PVCLOCK;
+
+	return 0;
+}
+
 static void __init xen_time_init(void)
 {
 	int cpu = smp_processor_id();
@@ -393,6 +443,7 @@ static void __init xen_time_init(void)
 	setup_force_cpu_cap(X86_FEATURE_TSC);
 
 	xen_setup_runstate_info(cpu);
+	xen_setup_vsyscall_time_info(cpu);
 	xen_setup_timer(cpu);
 	xen_setup_cpu_clockevents();
 
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index ac0a2b0..4036d15 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -66,6 +66,7 @@ void __init xen_vmalloc_p2m_tree(void);
 void xen_init_irq_ops(void);
 void xen_setup_timer(int cpu);
 void xen_setup_runstate_info(int cpu);
+int xen_setup_vsyscall_time_info(int cpu);
 void xen_teardown_timer(int cpu);
 u64 xen_clocksource_read(void);
 void xen_setup_cpu_clockevents(void);
diff --git a/include/xen/interface/vcpu.h b/include/xen/interface/vcpu.h
index 98188c8..8da788c 100644
--- a/include/xen/interface/vcpu.h
+++ b/include/xen/interface/vcpu.h
@@ -178,4 +178,32 @@ DEFINE_GUEST_HANDLE_STRUCT(vcpu_register_vcpu_info);
 
 /* Send an NMI to the specified VCPU. @extra_arg == NULL. */
 #define VCPUOP_send_nmi             11
+
+/*
+ * Register a memory location to get a secondary copy of the vcpu time
+ * parameters.  The master copy still exists as part of the vcpu shared
+ * memory area, and this secondary copy is updated whenever the master copy
+ * is updated (and using the same versioning scheme for synchronisation).
+ *
+ * The intent is that this copy may be mapped (RO) into userspace so
+ * that usermode can compute system time using the time info and the
+ * tsc.  Usermode will see an array of vcpu_time_info structures, one
+ * for each vcpu, and choose the right one by an existing mechanism
+ * which allows it to get the current vcpu number (such as via a
+ * segment limit).  It can then apply the normal algorithm to compute
+ * system time from the tsc.
+ *
+ * @extra_arg == pointer to vcpu_register_time_info_memory_area structure.
+ */
+#define VCPUOP_register_vcpu_time_memory_area   13
+DEFINE_GUEST_HANDLE_STRUCT(vcpu_time_info_t);
+struct vcpu_register_time_memory_area {
+	union {
+		GUEST_HANDLE(vcpu_time_info_t) h;
+		struct pvclock_vcpu_time_info *v;
+		uint64_t p;
+	} addr;
+};
+DEFINE_GUEST_HANDLE_STRUCT(vcpu_register_time_memory_area_t);
+
 #endif /* __XEN_PUBLIC_VCPU_H__ */
-- 
2.1.4