[PATCH v3 07/18] x86/intel_rdt: Add Haswell feature discovery

[Fenghua Yu]

From: Fenghua Yu <fenghua.yu@xxxxxxxxx>

Some Haswell generation CPUs support RDT, but they don't enumerate this
using CPUID.  Use rdmsr_safe() and wrmsr_safe() to probe the MSRs on
cpu model 63 (INTEL_FAM6_HASWELL_X)

Signed-off-by: Fenghua Yu <fenghua.yu@xxxxxxxxx>
Signed-off-by: Tony Luck <tony.luck@xxxxxxxxx>
---
 arch/x86/events/intel/cqm.c             |  2 +-
 arch/x86/include/asm/intel_rdt_common.h |  6 ++++++
 arch/x86/kernel/cpu/intel_rdt.c         | 38 +++++++++++++++++++++++++++++++++
 3 files changed, 45 insertions(+), 1 deletion(-)
 create mode 100644 arch/x86/include/asm/intel_rdt_common.h

diff --git a/arch/x86/events/intel/cqm.c b/arch/x86/events/intel/cqm.c
index 8f82b02..df86874 100644
--- a/arch/x86/events/intel/cqm.c
+++ b/arch/x86/events/intel/cqm.c
@@ -7,9 +7,9 @@
 #include <linux/perf_event.h>
 #include <linux/slab.h>
 #include <asm/cpu_device_id.h>
+#include <asm/intel_rdt_common.h>
 #include "../perf_event.h"
 
-#define MSR_IA32_PQR_ASSOC	0x0c8f
 #define MSR_IA32_QM_CTR		0x0c8e
 #define MSR_IA32_QM_EVTSEL	0x0c8d
 
diff --git a/arch/x86/include/asm/intel_rdt_common.h b/arch/x86/include/asm/intel_rdt_common.h
new file mode 100644
index 0000000..e6e15cf
--- /dev/null
+++ b/arch/x86/include/asm/intel_rdt_common.h
@@ -0,0 +1,6 @@
+#ifndef _ASM_X86_INTEL_RDT_COMMON_H
+#define _ASM_X86_INTEL_RDT_COMMON_H
+
+#define MSR_IA32_PQR_ASSOC	0x0c8f
+
+#endif /* _ASM_X86_INTEL_RDT_COMMON_H */
diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c
index ebe8dae..bc7f10b 100644
--- a/arch/x86/kernel/cpu/intel_rdt.c
+++ b/arch/x86/kernel/cpu/intel_rdt.c
@@ -26,11 +26,49 @@
 
 #include <linux/slab.h>
 #include <linux/err.h>
+#include <asm/intel_rdt_common.h>
+#include <asm/intel-family.h>
+
+/*
+ * cache_alloc_hsw_probe() - Have to probe for Intel haswell server CPUs
+ * as it does not have CPUID enumeration support for Cache allocation.
+ *
+ * Probes by writing to the high 32 bits(CLOSid) of the IA32_PQR_MSR and
+ * testing if the bits stick. Max CLOSids is always 4 and max cbm length
+ * is always 20 on hsw server parts. The minimum cache bitmask length
+ * allowed for HSW server is always 2 bits. Hardcode all of them.
+ */
+static inline bool cache_alloc_hsw_probe(void)
+{
+	u32 l, h_old, h_new, h_tmp;
+
+	if (rdmsr_safe(MSR_IA32_PQR_ASSOC, &l, &h_old))
+		return false;
+
+	/*
+	 * Default value is always 0 if feature is present.
+	 */
+	h_tmp = h_old ^ 0x1U;
+	if (wrmsr_safe(MSR_IA32_PQR_ASSOC, l, h_tmp))
+		return false;
+	rdmsr(MSR_IA32_PQR_ASSOC, l, h_new);
+
+	if (h_tmp != h_new)
+		return false;
+
+	wrmsr(MSR_IA32_PQR_ASSOC, l, h_old);
+
+	return true;
+}
 
 static inline bool get_rdt_resources(struct cpuinfo_x86 *c)
 {
 	bool ret = false;
 
+	if (c->x86_vendor == X86_VENDOR_INTEL && c->x86 == 6 &&
+	    c->x86_model == INTEL_FAM6_HASWELL_X)
+		return cache_alloc_hsw_probe();
+
 	if (!cpu_has(c, X86_FEATURE_RDT_A))
 		return false;
 	if (cpu_has(c, X86_FEATURE_CAT_L3))
-- 
2.5.0