linux-kernel - [PATCH v5 2/2] x86, mwaitt: introduce mwaix delay with a configurable timer

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <1434365284-1495-3-git-send-email-ray.huang@amd.com>
Date:	Mon, 15 Jun 2015 18:48:04 +0800
From:	Huang Rui <ray.huang@....com>
To:	Borislav Petkov <bp@...e.de>,
	Andy Lutomirski <luto@...capital.net>,
	Thomas Gleixner <tglx@...utronix.de>,
	Peter Zijlstra <peterz@...radead.org>,
	Ingo Molnar <mingo@...nel.org>,
	"Rafael J. Wysocki" <rjw@...ysocki.net>,
	"Len Brown" <lenb@...nel.org>,
	John Stultz <john.stultz@...aro.org>,
	Frédéric Weisbecker <fweisbec@...il.com>
CC:	<linux-kernel@...r.kernel.org>, <x86@...nel.org>,
	Fengguang Wu <fengguang.wu@...el.com>,
	Aaron Lu <aaron.lu@...el.com>,
	Suravee Suthikulanit <suravee.suthikulpanit@....com>,
	Tony Li <tony.li@....com>, Ken Xue <ken.xue@....com>,
	Huang Rui <ray.huang@....com>
Subject: [PATCH v5 2/2] x86, mwaitt: introduce mwaix delay with a configurable timer

MWAITX can enable a timer and a corresponding timer value specified in SW
P0 clocks. The SW P0 frequency is the same with TSC. The timer provides an
upper bound on how long the instruction waits before exiting.

The implementation of delay function in kernel can lerverage the timer of
MWAITX. This patch provides a new method (delay_mwaitx) to measure delay
time.

Suggested-by: Andy Lutomirski <luto@...capital.net>
Suggested-by: Borislav Petkov <bp@...e.de>
Suggested-by: Peter Zijlstra <peterz@...radead.org>
Signed-off-by: Huang Rui <ray.huang@....com>
---
 arch/x86/include/asm/delay.h |  1 +
 arch/x86/include/asm/mwait.h |  3 +++
 arch/x86/kernel/cpu/amd.c    |  4 ++++
 arch/x86/lib/delay.c         | 45 ++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 53 insertions(+)

diff --git a/arch/x86/include/asm/delay.h b/arch/x86/include/asm/delay.h
index 9b3b4f2..36a760b 100644
--- a/arch/x86/include/asm/delay.h
+++ b/arch/x86/include/asm/delay.h
@@ -4,5 +4,6 @@
 #include <asm-generic/delay.h>
 
 void use_tsc_delay(void);
+void use_mwaitx_delay(void);
 
 #endif /* _ASM_X86_DELAY_H */
diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h
index 1fbc89d..47f3540 100644
--- a/arch/x86/include/asm/mwait.h
+++ b/arch/x86/include/asm/mwait.h
@@ -14,6 +14,9 @@
 #define CPUID5_ECX_INTERRUPT_BREAK	0x2
 
 #define MWAIT_ECX_INTERRUPT_BREAK	0x1
+#define MWAITX_ECX_TIMER_ENABLE		BIT(1)
+#define MWAITX_MAX_LOOPS		((u32)-1)
+#define MWAITX_DISABLE_CSTATES		0xf
 
 static inline void __monitor(const void *eax, unsigned long ecx,
 			     unsigned long edx)
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 5bd3a99..1f0a8e2 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -11,6 +11,7 @@
 #include <asm/cpu.h>
 #include <asm/smp.h>
 #include <asm/pci-direct.h>
+#include <asm/delay.h>
 
 #ifdef CONFIG_X86_64
 # include <asm/mmconfig.h>
@@ -661,6 +662,9 @@ static void init_amd(struct cpuinfo_x86 *c)
 
 	early_init_amd(c);
 
+	if (static_cpu_has_safe(X86_FEATURE_MWAITT))
+		use_mwaitx_delay();
+
 	/*
 	 * Bit 31 in normal CPUID used for nonstandard 3DNow ID;
 	 * 3DNow is IDd by bit 31 in extended CPUID (1*32+31) anyway
diff --git a/arch/x86/lib/delay.c b/arch/x86/lib/delay.c
index 39d6a3d..035b6f6 100644
--- a/arch/x86/lib/delay.c
+++ b/arch/x86/lib/delay.c
@@ -20,6 +20,7 @@
 #include <asm/processor.h>
 #include <asm/delay.h>
 #include <asm/timer.h>
+#include <asm/mwait.h>
 
 #ifdef CONFIG_SMP
 # include <asm/smp.h>
@@ -87,6 +88,45 @@ static void delay_tsc(unsigned long __loops)
 }
 
 /*
+ * On AMD platforms mwaitx has a configurable 32-bit timer, that counts
+ * with TSC frequency. And the input value is the loop of the counter, it
+ * will exit with the timer expired.
+ */
+static void delay_mwaitx(unsigned long __loops)
+{
+	u32 end, start, delay, loops = __loops;
+
+	rdtsc_barrier();
+	rdtscl(start);
+
+	for (;;) {
+		delay = min(MWAITX_MAX_LOOPS, loops);
+
+		/*
+		 * Use cpu_tss as a cacheline-aligned, seldomly
+		 * accessed per-cpu variable as the monitor target.
+		 */
+		__monitorx(this_cpu_ptr(&cpu_tss), 0, 0);
+		/*
+		 * AMD, like Intel, supports the EAX hint and EAX=0xf
+		 * means, do not enter any deep C-state and we use it
+		 * here in delay() to minimize wakeup latency.
+		 */
+		__mwaitx(MWAITX_DISABLE_CSTATES, delay, MWAITX_ECX_TIMER_ENABLE);
+
+		rdtsc_barrier();
+		rdtscl(end);
+
+		if (loops <= end - start)
+			break;
+
+		loops -= end - start;
+
+		start = end;
+	}
+}
+
+/*
  * Since we calibrate only once at boot, this
  * function should be set once at boot and not changed
  */
@@ -97,6 +137,11 @@ void use_tsc_delay(void)
 	delay_fn = delay_tsc;
 }
 
+void use_mwaitx_delay(void)
+{
+	delay_fn = delay_mwaitx;
+}
+
 int read_current_timer(unsigned long *timer_val)
 {
 	if (delay_fn == delay_tsc) {
-- 
1.9.1

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/