x86/delay: Introduce TPAUSE delay

TPAUSE instructs the processor to enter an implementation-dependent
optimized state. The instruction execution wakes up when the time-stamp
counter reaches or exceeds the implicit EDX:EAX 64-bit input value.
The instruction execution also wakes up due to the expiration of
the operating system time-limit or by an external interrupt
or exceptions such as a debug exception or a machine check exception.

TPAUSE offers a choice of two lower power states:
 1. Light-weight power/performance optimized state C0.1
 2. Improved power/performance optimized state C0.2

This way, it can save power with low wake-up latency in comparison to
spinloop based delay. The selection between the two is governed by the
input register.

TPAUSE is available on processors with X86_FEATURE_WAITPKG.
Co-developed-by: Fenghua Yu <fenghua.yu@intel.com>
Signed-off-by: Fenghua Yu <fenghua.yu@intel.com>
Signed-off-by: Kyung Min Park <kyung.min.park@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Link: https://lkml.kernel.org/r/1587757076-30337-4-git-send-email-kyung.min.park@intel.com

arch/x86/Kconfig.assembler

@@ -15,3 +15,7 @@ config AS_SHA256_NI
 	def_bool $(as-instr,sha256msg1 %xmm0$(comma)%xmm1)
 	help
 	  Supported by binutils >= 2.24 and LLVM integrated assembler
+config AS_TPAUSE
+	def_bool $(as-instr,tpause %ecx)
+	help
+	  Supported by binutils >= 2.31.1 and LLVM integrated assembler >= V7

arch/x86/include/asm/delay.h

@@ -6,6 +6,7 @@
 #include <linux/init.h>
 
 void __init use_tsc_delay(void);
+void __init use_tpause_delay(void);
 void use_mwaitx_delay(void);
 
 #endif /* _ASM_X86_DELAY_H */

arch/x86/include/asm/mwait.h

@@ -22,6 +22,8 @@
 #define MWAITX_ECX_TIMER_ENABLE		BIT(1)
 #define MWAITX_MAX_WAIT_CYCLES		UINT_MAX
 #define MWAITX_DISABLE_CSTATES		0xf0
+#define TPAUSE_C01_STATE		1
+#define TPAUSE_C02_STATE		0
 
 u32 get_umwait_control_msr(void);
 
@@ -122,4 +124,24 @@ static inline void mwait_idle_with_hints(unsigned long eax, unsigned long ecx)
 	current_clr_polling();
 }
 
+/*
+ * Caller can specify whether to enter C0.1 (low latency, less
+ * power saving) or C0.2 state (saves more power, but longer wakeup
+ * latency). This may be overridden by the IA32_UMWAIT_CONTROL MSR
+ * which can force requests for C0.2 to be downgraded to C0.1.
+ */
+static inline void __tpause(u32 ecx, u32 edx, u32 eax)
+{
+	/* "tpause %ecx, %edx, %eax;" */
+	#ifdef CONFIG_AS_TPAUSE
+	asm volatile("tpause %%ecx\n"
+		     :
+		     : "c"(ecx), "d"(edx), "a"(eax));
+	#else
+	asm volatile(".byte 0x66, 0x0f, 0xae, 0xf1\t\n"
+		     :
+		     : "c"(ecx), "d"(edx), "a"(eax));
+	#endif
+}
+
 #endif /* _ASM_X86_MWAIT_H */

arch/x86/kernel/time.c

@@ -103,6 +103,9 @@ static __init void x86_late_time_init(void)
 	 */
 	x86_init.irqs.intr_mode_init();
 	tsc_init();
+
+	if (static_cpu_has(X86_FEATURE_WAITPKG))
+		use_tpause_delay();
 }
 
 /*

arch/x86/lib/delay.c

@@ -96,6 +96,27 @@ static void delay_tsc(u64 cycles)
 	preempt_enable();
 }
 
+/*
+ * On Intel the TPAUSE instruction waits until any of:
+ * 1) the TSC counter exceeds the value provided in EDX:EAX
+ * 2) global timeout in IA32_UMWAIT_CONTROL is exceeded
+ * 3) an external interrupt occurs
+ */
+static void delay_halt_tpause(u64 start, u64 cycles)
+{
+	u64 until = start + cycles;
+	u32 eax, edx;
+
+	eax = lower_32_bits(until);
+	edx = upper_32_bits(until);
+
+	/*
+	 * Hard code the deeper (C0.2) sleep state because exit latency is
+	 * small compared to the "microseconds" that usleep() will delay.
+	 */
+	__tpause(TPAUSE_C02_STATE, edx, eax);
+}
+
 /*
  * On some AMD platforms, MWAITX has a configurable 32-bit timer, that
  * counts with TSC frequency. The input value is the number of TSC cycles
@@ -156,6 +177,12 @@ void __init use_tsc_delay(void)
 		delay_fn = delay_tsc;
 }
 
+void __init use_tpause_delay(void)
+{
+	delay_halt_fn = delay_halt_tpause;
+	delay_fn = delay_halt;
+}
+
 void use_mwaitx_delay(void)
 {
 	delay_halt_fn = delay_halt_mwaitx;