[PATCH v4 08/47] x86/tsc: Add dedicated hypervisor hooks for getting known TSC/CPU frequencies

[Sean Christopherson <seanjc@xxxxxxxxxx>]

Add dedicated hypervisor hooks for getting known TSC/CPU frequencies
instead of overriding seemingly generic platform hooks, and explicitly
priotize hypervisor-provided frequencies over native methods, but do NOT
clobber the frequency obtained from trusted firmware.  While shuffling the
hooks around is arguably "six of one, half dozen of the other", scoping
them to x86_hyper_init makes their purpose more obvious, and allows for
explicitly defining the priority of sources (as is done here).

Cc: David Woodhouse <dwmw2@xxxxxxxxxxxxx>
Signed-off-by: Sean Christopherson <seanjc@xxxxxxxxxx>
---
 arch/x86/include/asm/acrn.h     |  5 -----
 arch/x86/include/asm/x86_init.h |  4 ++++
 arch/x86/kernel/cpu/acrn.c      | 10 +++++++---
 arch/x86/kernel/cpu/mshyperv.c  |  6 +++---
 arch/x86/kernel/cpu/vmware.c    |  8 ++++----
 arch/x86/kernel/jailhouse.c     |  6 +++---
 arch/x86/kernel/kvmclock.c      |  6 +++---
 arch/x86/kernel/tsc.c           | 23 +++++++++++++++++++----
 arch/x86/xen/time.c             |  4 ++--
 9 files changed, 45 insertions(+), 27 deletions(-)

diff --git a/arch/x86/include/asm/acrn.h b/arch/x86/include/asm/acrn.h
index db42b477c41d..a892179c61c6 100644
--- a/arch/x86/include/asm/acrn.h
+++ b/arch/x86/include/asm/acrn.h
@@ -32,11 +32,6 @@ static inline u32 acrn_cpuid_base(void)
        return 0;
 }
 
-static inline unsigned long acrn_get_tsc_khz(void)
-{
-       return cpuid_eax(ACRN_CPUID_TIMING_INFO);
-}
-
 /*
  * Hypercalls for ACRN
  *
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index 6c8a6ead84f6..a4f8a4aa601d 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -120,6 +120,8 @@ struct x86_init_pci {
  * @msi_ext_dest_id:           MSI supports 15-bit APIC IDs
  * @init_mem_mapping:          setup early mappings during init_mem_mapping()
  * @init_after_bootmem:                guest init after boot allocator is 
finished
+ * @get_tsc_khz:               get the TSC frequency (returns 0 if frequency 
is unknown)
+ * @get_cpu_khz:               get the CPU frequency (returns 0 if frequency 
is unknown)
  */
 struct x86_hyper_init {
        void (*init_platform)(void);
@@ -128,6 +130,8 @@ struct x86_hyper_init {
        bool (*msi_ext_dest_id)(void);
        void (*init_mem_mapping)(void);
        void (*init_after_bootmem)(void);
+       unsigned int (*get_tsc_khz)(void);
+       unsigned int (*get_cpu_khz)(void);
 };
 
 /**
diff --git a/arch/x86/kernel/cpu/acrn.c b/arch/x86/kernel/cpu/acrn.c
index dc119af83524..ad8f2da8003b 100644
--- a/arch/x86/kernel/cpu/acrn.c
+++ b/arch/x86/kernel/cpu/acrn.c
@@ -24,13 +24,15 @@ static u32 __init acrn_detect(void)
        return acrn_cpuid_base();
 }
 
+static unsigned int __init acrn_get_tsc_khz(void)
+{
+       return cpuid_eax(ACRN_CPUID_TIMING_INFO);
+}
+
 static void __init acrn_init_platform(void)
 {
        /* Install system interrupt handler for ACRN hypervisor callback */
        sysvec_install(HYPERVISOR_CALLBACK_VECTOR, sysvec_acrn_hv_callback);
-
-       x86_platform.calibrate_tsc = acrn_get_tsc_khz;
-       x86_platform.calibrate_cpu = acrn_get_tsc_khz;
 }
 
 static bool acrn_x2apic_available(void)
@@ -78,4 +80,6 @@ const __initconst struct hypervisor_x86 x86_hyper_acrn = {
        .type                   = X86_HYPER_ACRN,
        .init.init_platform     = acrn_init_platform,
        .init.x2apic_available  = acrn_x2apic_available,
+       .init.get_tsc_khz       = acrn_get_tsc_khz,
+       .init.get_cpu_khz       = acrn_get_tsc_khz,
 };
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 185d4f677ec0..733e12d5a7dd 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -395,7 +395,7 @@ static int hv_nmi_unknown(unsigned int val, struct pt_regs 
*regs)
 }
 #endif
 
-static unsigned long hv_get_tsc_khz(void)
+static unsigned int __init hv_get_tsc_khz(void)
 {
        unsigned long freq;
 
@@ -573,8 +573,8 @@ static void __init ms_hyperv_init_platform(void)
 
        if (ms_hyperv.features & HV_ACCESS_FREQUENCY_MSRS &&
            ms_hyperv.misc_features & HV_FEATURE_FREQUENCY_MSRS_AVAILABLE) {
-               x86_platform.calibrate_tsc = hv_get_tsc_khz;
-               x86_platform.calibrate_cpu = hv_get_tsc_khz;
+               x86_init.hyper.get_tsc_khz = hv_get_tsc_khz;
+               x86_init.hyper.get_cpu_khz = hv_get_tsc_khz;
                setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ);
        }
 
diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c
index 34b73573b108..7c8cf4885e82 100644
--- a/arch/x86/kernel/cpu/vmware.c
+++ b/arch/x86/kernel/cpu/vmware.c
@@ -64,7 +64,7 @@ struct vmware_steal_time {
        u64 reserved[7];
 };
 
-static unsigned long vmware_tsc_khz __ro_after_init;
+static unsigned long vmware_tsc_khz __initdata;
 static u8 vmware_hypercall_mode     __ro_after_init;
 
 unsigned long vmware_hypercall_slow(unsigned long cmd,
@@ -137,7 +137,7 @@ static inline int __vmware_platform(void)
        return eax != UINT_MAX && ebx == VMWARE_HYPERVISOR_MAGIC;
 }
 
-static unsigned long vmware_get_tsc_khz(void)
+static unsigned int __init vmware_get_tsc_khz(void)
 {
        return vmware_tsc_khz;
 }
@@ -419,8 +419,8 @@ static void __init vmware_platform_setup(void)
                }
 
                vmware_tsc_khz = tsc_khz;
-               x86_platform.calibrate_tsc = vmware_get_tsc_khz;
-               x86_platform.calibrate_cpu = vmware_get_tsc_khz;
+               x86_init.hyper.get_tsc_khz = vmware_get_tsc_khz;
+               x86_init.hyper.get_cpu_khz = vmware_get_tsc_khz;
 
 #ifdef CONFIG_X86_LOCAL_APIC
                /* Skip lapic calibration since we know the bus frequency. */
diff --git a/arch/x86/kernel/jailhouse.c b/arch/x86/kernel/jailhouse.c
index f58ce9220e0f..4034e08c5f11 100644
--- a/arch/x86/kernel/jailhouse.c
+++ b/arch/x86/kernel/jailhouse.c
@@ -68,7 +68,7 @@ static void __init jailhouse_timer_init(void)
        lapic_timer_period = setup_data.v1.apic_khz * (1000 / HZ);
 }
 
-static unsigned long jailhouse_get_tsc(void)
+static unsigned int __init jailhouse_get_tsc(void)
 {
        return precalibrated_tsc_khz;
 }
@@ -210,8 +210,6 @@ static void __init jailhouse_init_platform(void)
        x86_init.mpparse.parse_smp_cfg          = jailhouse_parse_smp_config;
        x86_init.pci.arch_init                  = jailhouse_pci_arch_init;
 
-       x86_platform.calibrate_cpu              = jailhouse_get_tsc;
-       x86_platform.calibrate_tsc              = jailhouse_get_tsc;
        x86_platform.get_wallclock              = jailhouse_get_wallclock;
        x86_platform.legacy.rtc                 = 0;
        x86_platform.legacy.warm_reset          = 0;
@@ -293,5 +291,7 @@ const struct hypervisor_x86 x86_hyper_jailhouse __refconst 
= {
        .detect                 = jailhouse_detect,
        .init.init_platform     = jailhouse_init_platform,
        .init.x2apic_available  = jailhouse_x2apic_available,
+       .init.get_tsc_khz       = jailhouse_get_tsc,
+       .init.get_cpu_khz       = jailhouse_get_tsc,
        .ignore_nopv            = true,
 };
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index b5991d53fc0e..ec888eef74aa 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -115,7 +115,7 @@ static inline void kvm_sched_clock_init(bool stable)
  * poll of guests can be running and trouble each other. So we preset
  * lpj here
  */
-static unsigned long kvm_get_tsc_khz(void)
+static unsigned int __init kvm_get_tsc_khz(void)
 {
        setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ);
        return pvclock_tsc_khz(this_cpu_pvti());
@@ -321,8 +321,8 @@ void __init kvmclock_init(void)
        flags = pvclock_read_flags(&hv_clock_boot[0].pvti);
        kvm_sched_clock_init(flags & PVCLOCK_TSC_STABLE_BIT);
 
-       x86_platform.calibrate_tsc = kvm_get_tsc_khz;
-       x86_platform.calibrate_cpu = kvm_get_tsc_khz;
+       x86_init.hyper.get_tsc_khz = kvm_get_tsc_khz;
+       x86_init.hyper.get_cpu_khz = kvm_get_tsc_khz;
        x86_platform.get_wallclock = kvm_get_wallclock;
        x86_platform.set_wallclock = kvm_set_wallclock;
 #ifdef CONFIG_X86_LOCAL_APIC
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 2603f136e29b..362596612442 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -1476,13 +1476,17 @@ static int __init init_tsc_clocksource(void)
 device_initcall(init_tsc_clocksource);
 
 static bool __init determine_cpu_tsc_frequencies(bool early,
+                                                unsigned int known_cpu_khz,
                                                 unsigned int known_tsc_khz)
 {
        /* Make sure that cpu and tsc are not already calibrated */
        WARN_ON(cpu_khz || tsc_khz);
 
        if (early) {
-               cpu_khz = x86_platform.calibrate_cpu();
+               if (known_cpu_khz)
+                       cpu_khz = known_cpu_khz;
+               else
+                       cpu_khz = x86_platform.calibrate_cpu();
                if (known_tsc_khz)
                        tsc_khz = known_tsc_khz;
                else
@@ -1539,7 +1543,7 @@ static void __init tsc_enable_sched_clock(void)
 
 void __init tsc_early_init(void)
 {
-       unsigned int known_tsc_khz = 0;
+       unsigned int known_cpu_khz = 0, known_tsc_khz = 0;
 
        if (!boot_cpu_has(X86_FEATURE_TSC))
                return;
@@ -1547,6 +1551,9 @@ void __init tsc_early_init(void)
        if (is_early_uv_system())
                return;
 
+       if (x86_init.hyper.get_cpu_khz)
+               known_cpu_khz = x86_init.hyper.get_cpu_khz();
+
        if (tsc_early_khz)
                known_tsc_khz = tsc_early_khz;
        else if (cc_platform_has(CC_ATTR_GUEST_SNP_SECURE_TSC))
@@ -1554,7 +1561,15 @@ void __init tsc_early_init(void)
        else if (boot_cpu_has(X86_FEATURE_TDX_GUEST))
                known_tsc_khz = tdx_tsc_init();
 
-       if (!determine_cpu_tsc_frequencies(true, known_tsc_khz))
+       /*
+        * If the TSC frequency is still unknown, i.e. not provided by the user
+        * or by trusted firmware, try to get it from the hypervisor (which is
+        * untrusted when running as a CoCo guest).
+        */
+       if (!known_tsc_khz && x86_init.hyper.get_tsc_khz)
+               known_tsc_khz = x86_init.hyper.get_tsc_khz();
+
+       if (!determine_cpu_tsc_frequencies(true, known_cpu_khz, known_tsc_khz))
                return;
        tsc_enable_sched_clock();
 }
@@ -1575,7 +1590,7 @@ void __init tsc_init(void)
 
        if (!tsc_khz) {
                /* We failed to determine frequencies earlier, try again */
-               if (!determine_cpu_tsc_frequencies(false, 0)) {
+               if (!determine_cpu_tsc_frequencies(false, 0, 0)) {
                        mark_tsc_unstable("could not calculate TSC khz");
                        setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER);
                        return;
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index d62c14334b35..1adb44fdddb2 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -38,7 +38,7 @@
 static u64 xen_sched_clock_offset __read_mostly;
 
 /* Get the TSC speed from Xen */
-static unsigned long xen_tsc_khz(void)
+static unsigned int __init xen_tsc_khz(void)
 {
        struct pvclock_vcpu_time_info *info =
                &HYPERVISOR_shared_info->vcpu_info[0].time;
@@ -569,7 +569,7 @@ static void __init xen_init_time_common(void)
        static_call_update(pv_steal_clock, xen_steal_clock);
        paravirt_set_sched_clock(xen_sched_clock);
 
-       x86_platform.calibrate_tsc = xen_tsc_khz;
+       x86_init.hyper.get_tsc_khz = xen_tsc_khz;
        x86_platform.get_wallclock = xen_get_wallclock;
 }
 
-- 
2.54.0.823.g6e5bcc1fc9-goog