| 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
| ||
|
Date: Wed, 6 Apr 2016 17:00:47 -0400
From: Len Brown <lenb@...nel.org>
To: linux-pm@...r.kernel.org
Cc: linux-kernel@...r.kernel.org, Len Brown <len.brown@...el.com>
Subject: [PATCH 01/13] intel_idle: add BXT support
From: Len Brown <len.brown@...el.com>
Broxton has all the HSW C-states, except C3.
BXT C-state timing is slightly different.
Here we trust the IRTL MSRs as authority
on maximum C-state latency, and override the driver's tables
with the values found in the associated IRTL MSRs.
Further we set the target_residency to 1x maximum latency,
trusting the hardware demotion logic.
Signed-off-by: Len Brown <len.brown@...el.com>
---
arch/x86/include/asm/msr-index.h | 8 +++
drivers/idle/intel_idle.c | 137 +++++++++++++++++++++++++++++++++++++++
2 files changed, 145 insertions(+)
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 2da46ac..1e81927 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -167,6 +167,14 @@
#define MSR_PKG_C9_RESIDENCY 0x00000631
#define MSR_PKG_C10_RESIDENCY 0x00000632
+/* Interrupt Response Limit */
+#define MSR_PKGC3_IRTL 0x0000060a
+#define MSR_PKGC6_IRTL 0x0000060b
+#define MSR_PKGC7_IRTL 0x0000060c
+#define MSR_PKGC8_IRTL 0x00000633
+#define MSR_PKGC9_IRTL 0x00000634
+#define MSR_PKGC10_IRTL 0x00000635
+
/* Run Time Average Power Limiting (RAPL) Interface */
#define MSR_RAPL_POWER_UNIT 0x00000606
diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index ba947df..012980a 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -737,6 +737,67 @@ static struct cpuidle_state knl_cstates[] = {
.enter = NULL }
};
+static struct cpuidle_state bxt_cstates[] = {
+ {
+ .name = "C1-BXT",
+ .desc = "MWAIT 0x00",
+ .flags = MWAIT2flg(0x00),
+ .exit_latency = 2,
+ .target_residency = 2,
+ .enter = &intel_idle,
+ .enter_freeze = intel_idle_freeze, },
+ {
+ .name = "C1E-BXT",
+ .desc = "MWAIT 0x01",
+ .flags = MWAIT2flg(0x01),
+ .exit_latency = 10,
+ .target_residency = 20,
+ .enter = &intel_idle,
+ .enter_freeze = intel_idle_freeze, },
+ {
+ .name = "C6-BXT",
+ .desc = "MWAIT 0x20",
+ .flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED,
+ .exit_latency = 133,
+ .target_residency = 133,
+ .enter = &intel_idle,
+ .enter_freeze = intel_idle_freeze, },
+ {
+ .name = "C7s-BXT",
+ .desc = "MWAIT 0x31",
+ .flags = MWAIT2flg(0x31) | CPUIDLE_FLAG_TLB_FLUSHED,
+ .exit_latency = 155,
+ .target_residency = 155,
+ .enter = &intel_idle,
+ .enter_freeze = intel_idle_freeze, },
+ {
+ .name = "C8-BXT",
+ .desc = "MWAIT 0x40",
+ .flags = MWAIT2flg(0x40) | CPUIDLE_FLAG_TLB_FLUSHED,
+ .exit_latency = 1000,
+ .target_residency = 1000,
+ .enter = &intel_idle,
+ .enter_freeze = intel_idle_freeze, },
+ {
+ .name = "C9-BXT",
+ .desc = "MWAIT 0x50",
+ .flags = MWAIT2flg(0x50) | CPUIDLE_FLAG_TLB_FLUSHED,
+ .exit_latency = 2000,
+ .target_residency = 2000,
+ .enter = &intel_idle,
+ .enter_freeze = intel_idle_freeze, },
+ {
+ .name = "C10-BXT",
+ .desc = "MWAIT 0x60",
+ .flags = MWAIT2flg(0x60) | CPUIDLE_FLAG_TLB_FLUSHED,
+ .exit_latency = 10000,
+ .target_residency = 10000,
+ .enter = &intel_idle,
+ .enter_freeze = intel_idle_freeze, },
+ {
+ .enter = NULL }
+};
+
/**
* intel_idle
* @dev: cpuidle_device
@@ -914,6 +975,11 @@ static const struct idle_cpu idle_cpu_knl = {
.state_table = knl_cstates,
};
+static const struct idle_cpu idle_cpu_bxt = {
+ .state_table = bxt_cstates,
+ .disable_promotion_to_c1e = true,
+};
+
#define ICPU(model, cpu) \
{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_MWAIT, (unsigned long)&cpu }
@@ -946,6 +1012,7 @@ static const struct x86_cpu_id intel_idle_ids[] __initconst = {
ICPU(0x4e, idle_cpu_skl),
ICPU(0x5e, idle_cpu_skl),
ICPU(0x57, idle_cpu_knl),
+ ICPU(0x5c, idle_cpu_bxt),
{}
};
MODULE_DEVICE_TABLE(x86cpu, intel_idle_ids);
@@ -1046,6 +1113,73 @@ static void ivt_idle_state_table_update(void)
/* else, 1 and 2 socket systems use default ivt_cstates */
}
+
+/*
+ * Translate IRTL (Interrupt Response Time Limit) MSR to usec
+ */
+
+static unsigned int irtl_ns_units[] = {
+ 1, 32, 1024, 32768, 1048576, 33554432, 0, 0 };
+
+static unsigned long long irtl_2_usec(unsigned long long irtl)
+{
+ unsigned long long ns;
+
+ ns = irtl_ns_units[(irtl >> 10) & 0x3];
+
+ return div64_u64((irtl & 0x3FF) * ns, 1000);
+}
+/*
+ * bxt_idle_state_table_update(void)
+ *
+ * On BXT, we trust the IRTL to show the definitive maximum latency
+ * We use the same value for target_residency.
+ */
+static void bxt_idle_state_table_update(void)
+{
+ unsigned long long msr;
+
+ rdmsrl(MSR_PKGC6_IRTL, msr);
+ if (msr) {
+ unsigned int usec = irtl_2_usec(msr);
+
+ bxt_cstates[2].exit_latency = usec;
+ bxt_cstates[2].target_residency = usec;
+ }
+
+ rdmsrl(MSR_PKGC7_IRTL, msr);
+ if (msr) {
+ unsigned int usec = irtl_2_usec(msr);
+
+ bxt_cstates[3].exit_latency = usec;
+ bxt_cstates[3].target_residency = usec;
+ }
+
+ rdmsrl(MSR_PKGC8_IRTL, msr);
+ if (msr) {
+ unsigned int usec = irtl_2_usec(msr);
+
+ bxt_cstates[4].exit_latency = usec;
+ bxt_cstates[4].target_residency = usec;
+ }
+
+ rdmsrl(MSR_PKGC9_IRTL, msr);
+ if (msr) {
+ unsigned int usec = irtl_2_usec(msr);
+
+ bxt_cstates[5].exit_latency = usec;
+ bxt_cstates[5].target_residency = usec;
+ }
+
+ rdmsrl(MSR_PKGC10_IRTL, msr);
+ if (msr) {
+ unsigned int usec = irtl_2_usec(msr);
+
+ bxt_cstates[6].exit_latency = usec;
+ bxt_cstates[6].target_residency = usec;
+ }
+
+}
/*
* sklh_idle_state_table_update(void)
*
@@ -1101,6 +1235,9 @@ static void intel_idle_state_table_update(void)
case 0x3e: /* IVT */
ivt_idle_state_table_update();
break;
+ case 0x5c: /* BXT */
+ bxt_idle_state_table_update();
+ break;
case 0x5e: /* SKL-H */
sklh_idle_state_table_update();
break;
--
2.8.0.rc4.16.g56331f8
Powered by blists - more mailing lists