common: measure the TSC only on CPUs without CPUID leaf 0x15 (#373)

The fallback that measures the TSC rate when the CPU reports none was
meant for AMD, which has no leaf 0x15 at all. It also caught Intel CPUs
that have the leaf but report a crystal frequency of 0 (Coffee Lake,
e.g. the i5-9400F) and moved them from the OS clock to the measured
RDTSC clock. With the same fallback in another Eden-based build, an
i5-9400F crashed about 3.5 s after launch; limiting the fallback to
CPUs without the leaf fixed it for that tester.

Those Intel CPUs now keep the OS clock, as before the fallback. AMD
CPUs still get the measured RDTSC clock (a Ryzen 7 9800X3D reports
max leaf 0xd, so nothing changes there).

Assisted-by: Claude Opus 5.5 (debugging, porting and drafting)

Signed-off-by: Duck912 <350528965+Duck912@users.noreply.github.com>

1 files changed, 4 insertions, 2 deletions

diff --git a/src/common/cpu_features.cpp b/src/common/cpu_features.cpp
index 93eecb1dc5..c7f6e6f036 100644
--- a/src/common/cpu_features.cpp
+++ b/src/common/cpu_features.cpp
@@ -227,8 +227,10 @@ const CPUCaps g_cpu_caps = [] {
 
     // AMD CPUs have no leaf 0x15 (Zen 4 stops at 0x10): measure their invariant TSC too, or every
     // guest clock read (CNTPCT, which games read thousands of times a frame) goes through the
-    // host's much slower QueryPerformanceCounter.
-    if (caps.invariant_tsc && caps.tsc_frequency == 0) {
+    // host's much slower QueryPerformanceCounter. Intel CPUs that have the leaf but report no
+    // crystal frequency (e.g. Coffee Lake) keep the OS clock: an i5-9400F crashed at launch on the
+    // measured RDTSC clock.
+    if (max_std_fn < 0x15 && caps.invariant_tsc && caps.tsc_frequency == 0) {
         caps.tsc_frequency = X64::EstimateRDTSCFrequency();
     }