[PATCH v5 2/2] x86/time: avoid early uses of NOW() to return zero

Waiting loops like the one in flush_command_buffer() will degenerate to
infinite ones when used early enough for NOW() to still return constant
zero. Make sure the returned value at least monotonically increases. When
available, use nominal frequency values as initial approximation.

Do this only in get_s_time(), as producing a sane value in
get_s_time_fixed() for non-zero inputs won't be reasonably possible.
Put an assertion there.

Reported-by: Roger Pau Monné <[email protected]>
Signed-off-by: Jan Beulich <[email protected]>
---
RFC: While generally the mentioned waiting loops will take longer to time
     out, on a very fast CPU tight loops may time out too early.

With "x86/time: set AP's TSC scale estimate earlier" the counter update
may not need to be atomic anymore, as then only the BSP can reasonably hit
that path.

I don't think Fixes: tags should be put here. If we did, we'd have to
enumerate all introductions of early uses of NOW() (or get_s_time()), with
the exception of those dealing with getting back 0 (which I expect is only
printk_start_of_line()). Will want backporting nevertheless (unless deemed
too risky).
---
v5: Move addition to early_cpu_init() down. Adjust commentary there.
v3: Use "high" / "max" freq if "nominal" isn't available. Set NOW_good.
v2: Add assertion to get_s_time_fixed(). Use nominal frequencies for very
    early setting, if available.

--- a/xen/arch/x86/cpu/common.c
+++ b/xen/arch/x86/cpu/common.c
@@ -19,6 +19,7 @@
 #include <asm/random.h>
 #include <asm/setup.h>
 #include <asm/shstk.h>
+#include <asm/time.h>
 #include <asm/xstate.h>
 
 #include <public/sysctl.h>
@@ -444,6 +445,39 @@ void __init early_cpu_init(bool verbose)
 
 	if (!(c->vendor & (X86_VENDOR_AMD | X86_VENDOR_HYGON)))
 		park_offline_cpus = opt_mce;
+
+	/*
+	 * If nominal freq isn't available, use highest, thus causing NOW()
+	 * output to move more slowly.  See preset_tsc_scale().
+	 */
+	if (c->cpuid_level >= 0x15) {
+		cpuid(0x15, &eax, &ebx, &ecx, &edx);
+
+		if (ecx && ebx && eax)
+			preset_tsc_scale(DIV_ROUND_UP(ecx * 1UL * ebx, eax));
+		else if (c->cpuid_level >= 0x16) {
+			/* Assume CPU base freq ≈ TSC freq. */
+			cpuid(0x16, &eax, &ebx, &ecx, &edx);
+			if (eax)
+				preset_tsc_scale(eax * 1000000UL);
+			else if (ebx)
+				preset_tsc_scale(ebx * 1000000UL);
+		}
+	} else if (c->vendor & (X86_VENDOR_AMD | X86_VENDOR_HYGON)) {
+		unsigned int nom_mhz = 0, hi_mhz = 0;
+
+		amd_process_freq(c, NULL, &nom_mhz, &hi_mhz);
+		if (nom_mhz)
+			preset_tsc_scale(nom_mhz * 1000000UL);
+		else if (hi_mhz)
+			preset_tsc_scale(hi_mhz * 1000000UL);
+	} else if (c->vendor & X86_VENDOR_INTEL) {
+		unsigned int hi_mhz = 0;
+
+		intel_process_freq(c, NULL, &hi_mhz);
+		if (hi_mhz)
+			preset_tsc_scale(hi_mhz * 1000000UL);
+	}
 }
 
 void reset_cpuinfo(struct cpuinfo_x86 *c, bool keep_basic)
--- a/xen/arch/x86/include/asm/time.h
+++ b/xen/arch/x86/include/asm/time.h
@@ -23,6 +23,7 @@ mktime (unsigned int year, unsigned int
 int time_suspend(void);
 int time_resume(void);
 
+void preset_tsc_scale(unsigned long freq);
 void init_percpu_time(void);
 void time_latch_stamps(void);
 
--- a/xen/arch/x86/cpu/intel.c
+++ b/xen/arch/x86/cpu/intel.c
@@ -476,8 +476,8 @@ static int num_cpu_cores(struct cpuinfo_
 		return 1;
 }
 
-static void intel_process_freq(const struct cpuinfo_x86 *c,
-                               unsigned int *min_mhz, unsigned int *max_mhz)
+void intel_process_freq(const struct cpuinfo_x86 *c,
+                        unsigned int *min_mhz, unsigned int *max_mhz)
 {
     uint64_t msrval;
     uint8_t max_ratio, min_ratio;
--- a/xen/arch/x86/include/asm/processor.h
+++ b/xen/arch/x86/include/asm/processor.h
@@ -417,6 +417,9 @@ static inline uint8_t get_cpu_family(uin
     return fam;
 }
 
+void intel_process_freq(const struct cpuinfo_x86 *c,
+                        unsigned int *min_mhz, unsigned int *max_mhz);
+
 #ifdef CONFIG_INTEL
 extern int8_t opt_tsx;
 extern bool rtm_disabled;
--- a/xen/arch/x86/time.c
+++ b/xen/arch/x86/time.c
@@ -1664,6 +1664,9 @@ s_time_t get_s_time_fixed(uint64_t at_ts
     const struct cpu_time *t = &this_cpu(cpu_time);
     uint64_t tsc, delta;
 
+    /* scale_delta() degenerates when the scale wasn't set yet. */
+    ASSERT(t->tsc_scale.mul_frac);
+
     if ( at_tsc )
         tsc = at_tsc;
     else
@@ -1679,6 +1682,20 @@ s_time_t get_s_time_fixed(uint64_t at_ts
 
 s_time_t get_s_time(void)
 {
+    /*
+     * Before the TSC scale is set, avoid returning constant 0 (or whatever
+     * this_cpu(cpu_time).stamp.local_stime is set to).  While the returned
+     * value is in no way representing time, it at least increases
+     * monotonically, thus avoiding e.g. waiting loops to degenerate to
+     * entirely infinite ones.
+     */
+    if ( unlikely(!this_cpu(cpu_time).tsc_scale.mul_frac) )
+    {
+        static s_time_t counter;
+
+        return arch_fetch_and_add(&counter, 1);
+    }
+
     return get_s_time_fixed(0);
 }
 
@@ -2632,6 +2649,22 @@ int __init init_xen_time(void)
     return 0;
 }
 
+/* BSP-only function to pre-set an approximate TSC scale. */
+void __init preset_tsc_scale(unsigned long freq)
+{
+    struct cpu_time *t = &this_cpu(cpu_time);
+
+    /*
+     * The incoming frequency is only approximate (nominal).  Increase it by
+     * 1% to make NOW() output rather a little too slow than too fast, thus
+     * avoiding a possible backwards jump once the final scale is set.
+     */
+    freq += DIV_ROUND_UP(freq, 100);
+
+    set_time_scale(&t->tsc_scale, freq);
+    t->stamp.local_tsc = boot_tsc_stamp;
+    NOW_good = true;
+}
 
 /* Early init function. */
 void __init early_time_init(void)
@@ -2649,6 +2682,9 @@ void __init early_time_init(void)
                    "TSC ADJUST set to %lx on boot CPU - clearing\n", tmp);
             wrmsrl(MSR_IA32_TSC_ADJUST, 0);
             boot_tsc_stamp -= tmp;
+
+            if ( t->stamp.local_tsc )
+                t->stamp.local_tsc -= tmp;
         }
     }