x86/idle: Sanitize X86_BUG_AMD_E400 handling

amd_e400_idle(), the idle routine for AMD CPUs which are affected by
erratum 400 violates the RCU constraints by invoking tick_broadcast_enter()
and tick_broadcast_exit() after the core code has marked RCU non-idle.  The
functions can end up in lockdep or tracing, which rightfully triggers a
RCU warning.

The core code provides now a static branch conditional invocation of the
broadcast functions.

Remove amd_e400_idle(), enforce default_idle() and enable the static branch
on affected CPUs to cure this.

  [ bp: Fold in a fix for a IS_ENABLED() check fail missing a "CONFIG_"
    prefix which tglx spotted. ]

Reported-by: Borislav Petkov <bp@alien8.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://lore.kernel.org/r/877cim6sis.ffs@tglx

1 files changed, 9 insertions, 33 deletions

diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 45a9d496fe2a..b86ff0ffe59a 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -846,31 +846,6 @@ void __noreturn stop_this_cpu(void *dummy)
 }
 
 /*
- * AMD Erratum 400 aware idle routine. We handle it the same way as C3 power
- * states (local apic timer and TSC stop).
- *
- * XXX this function is completely buggered vs RCU and tracing.
- */
-static void amd_e400_idle(void)
-{
-	/*
-	 * We cannot use static_cpu_has_bug() here because X86_BUG_AMD_APIC_C1E
-	 * gets set after static_cpu_has() places have been converted via
-	 * alternatives.
-	 */
-	if (!boot_cpu_has_bug(X86_BUG_AMD_APIC_C1E)) {
-		default_idle();
-		return;
-	}
-
-	tick_broadcast_enter();
-
-	default_idle();
-
-	tick_broadcast_exit();
-}
-
-/*
  * Prefer MWAIT over HALT if MWAIT is supported, MWAIT_CPUID leaf
  * exists and whenever MONITOR/MWAIT extensions are present there is at
  * least one C1 substate.
@@ -890,8 +865,8 @@ static int prefer_mwait_c1_over_halt(const struct cpuinfo_x86 *c)
 	if (!cpu_has(c, X86_FEATURE_MWAIT))
 		return 0;
 
-	/* Monitor has a bug. Fallback to HALT */
-	if (boot_cpu_has_bug(X86_BUG_MONITOR))
+	/* Monitor has a bug or APIC stops in C1E. Fallback to HALT */
+	if (boot_cpu_has_bug(X86_BUG_MONITOR) || boot_cpu_has_bug(X86_BUG_AMD_APIC_C1E))
 		return 0;
 
 	cpuid(CPUID_MWAIT_LEAF, &eax, &ebx, &ecx, &edx);
@@ -942,17 +917,15 @@ void select_idle_routine(const struct cpuinfo_x86 *c)
 	if (x86_idle_set() || boot_option_idle_override == IDLE_POLL)
 		return;
 
-	if (boot_cpu_has_bug(X86_BUG_AMD_E400)) {
-		pr_info("using AMD E400 aware idle routine\n");
-		static_call_update(x86_idle, amd_e400_idle);
-	} else if (prefer_mwait_c1_over_halt(c)) {
+	if (prefer_mwait_c1_over_halt(c)) {
 		pr_info("using mwait in idle threads\n");
 		static_call_update(x86_idle, mwait_idle);
 	} else if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) {
 		pr_info("using TDX aware idle routine\n");
 		static_call_update(x86_idle, tdx_safe_halt);
-	} else
+	} else {
 		static_call_update(x86_idle, default_idle);
+	}
 }
 
 void amd_e400_c1e_apic_setup(void)
@@ -985,7 +958,10 @@ void __init arch_post_acpi_subsys_init(void)
 
 	if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC))
 		mark_tsc_unstable("TSC halt in AMD C1E");
-	pr_info("System has AMD C1E enabled\n");
+
+	if (IS_ENABLED(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST_IDLE))
+		static_branch_enable(&arch_needs_tick_broadcast);
+	pr_info("System has AMD C1E erratum E400. Workaround enabled.\n");
 }
 
 static int __init idle_setup(char *str)