[PATCH v3 08/18] x86/intel_rdt: Pick up L3 RDT parameters from CPUID

[Fenghua Yu]

From: Fenghua Yu <fenghua.yu@xxxxxxxxx>

Define struct rdt_resource to hold all the parameterized
values for an RDT resource. Fill in some of those values
from CPUID leaf 0x10 (on Haswell we hard code them).

Signed-off-by: Fenghua Yu <fenghua.yu@xxxxxxxxx>
Signed-off-by: Tony Luck <tony.luck@xxxxxxxxx>
---
 arch/x86/include/asm/intel_rdt.h | 67 ++++++++++++++++++++++++++++++++++++++++
 arch/x86/kernel/cpu/intel_rdt.c  | 54 +++++++++++++++++++++++++++++---
 2 files changed, 117 insertions(+), 4 deletions(-)
 create mode 100644 arch/x86/include/asm/intel_rdt.h

diff --git a/arch/x86/include/asm/intel_rdt.h b/arch/x86/include/asm/intel_rdt.h
new file mode 100644
index 0000000..251ac2a
--- /dev/null
+++ b/arch/x86/include/asm/intel_rdt.h
@@ -0,0 +1,67 @@
+#ifndef _ASM_X86_INTEL_RDT_H
+#define _ASM_X86_INTEL_RDT_H
+
+/**
+ * struct rdt_resource - attributes of an RDT resource
+ * @enabled:			Is this feature enabled on this machine
+ * @name:			Name to use in "schemata" file
+ * @max_closid:			Maximum number of CLOSIDs supported
+ * @num_closid:			Current number of CLOSIDs available
+ * @max_cbm:			Largest Cache Bit Mask allowed
+ * @min_cbm_bits:		Minimum number of bits to be set in a cache
+ *				bit mask
+ * @domains:			All domains for this resource
+ * @num_domains:		Number of domains active
+ * @msr_base:			Base MSR address for CBMs
+ * @cdp_capable:		Code/Data Prioritization available
+ * @cdp_enabled:		Code/Data Prioritization enabled
+ * @tmp_cbms:			Scratch space when updating schemata
+ * @cache_level:		Which cache level defines scope of this domain
+ */
+struct rdt_resource {
+	bool			enabled;
+	char			*name;
+	int			max_closid;
+	int			num_closid;
+	int			cbm_len;
+	int			min_cbm_bits;
+	u32			max_cbm;
+	struct list_head	domains;
+	int			num_domains;
+	int			msr_base;
+	bool			cdp_capable;
+	bool			cdp_enabled;
+	u32			*tmp_cbms;
+	int			cache_level;
+};
+
+#define for_each_rdt_resource(r)	\
+	for (r = rdt_resources_all; r->name; r++) \
+		if (r->enabled)
+
+#define IA32_L3_CBM_BASE	0xc90
+extern struct rdt_resource rdt_resources_all[];
+
+enum {
+	RDT_RESOURCE_L3,
+};
+
+/* Maximum CLOSID allowed across all enabled resoources */
+extern int rdt_max_closid;
+
+/* CPUID.(EAX=10H, ECX=ResID=1).EAX */
+union cpuid_0x10_1_eax {
+	struct {
+		unsigned int cbm_len:5;
+	} split;
+	unsigned int full;
+};
+
+/* CPUID.(EAX=10H, ECX=ResID=1).EDX */
+union cpuid_0x10_1_edx {
+	struct {
+		unsigned int cos_max:16;
+	} split;
+	unsigned int full;
+};
+#endif /* _ASM_X86_INTEL_RDT_H */
diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c
index bc7f10b..b9b1e9e 100644
--- a/arch/x86/kernel/cpu/intel_rdt.c
+++ b/arch/x86/kernel/cpu/intel_rdt.c
@@ -28,6 +28,24 @@
 #include <linux/err.h>
 #include <asm/intel_rdt_common.h>
 #include <asm/intel-family.h>
+#include <asm/intel_rdt.h>
+
+int rdt_max_closid;
+
+#define domain_init(name) LIST_HEAD_INIT(rdt_resources_all[name].domains)
+
+struct rdt_resource rdt_resources_all[] = {
+	{
+		.name		= "L3",
+		.domains	= domain_init(RDT_RESOURCE_L3),
+		.msr_base	= IA32_L3_CBM_BASE,
+		.min_cbm_bits	= 1,
+		.cache_level	= 3
+	},
+	{
+		/* NULL terminated */
+	}
+};
 
 /*
  * cache_alloc_hsw_probe() - Have to probe for Intel haswell server CPUs
@@ -41,6 +59,7 @@
 static inline bool cache_alloc_hsw_probe(void)
 {
 	u32 l, h_old, h_new, h_tmp;
+	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3];
 
 	if (rdmsr_safe(MSR_IA32_PQR_ASSOC, &l, &h_old))
 		return false;
@@ -58,11 +77,19 @@ static inline bool cache_alloc_hsw_probe(void)
 
 	wrmsr(MSR_IA32_PQR_ASSOC, l, h_old);
 
+	r->max_closid = 4;
+	r->num_closid = r->max_closid;
+	r->cbm_len = 20;
+	r->max_cbm = BIT_MASK(20) - 1;
+	r->min_cbm_bits = 2;
+	r->enabled = true;
+
 	return true;
 }
 
 static inline bool get_rdt_resources(struct cpuinfo_x86 *c)
 {
+	struct rdt_resource *r;
 	bool ret = false;
 
 	if (c->x86_vendor == X86_VENDOR_INTEL && c->x86 == 6 &&
@@ -71,8 +98,23 @@ static inline bool get_rdt_resources(struct cpuinfo_x86 *c)
 
 	if (!cpu_has(c, X86_FEATURE_RDT_A))
 		return false;
-	if (cpu_has(c, X86_FEATURE_CAT_L3))
+	if (cpu_has(c, X86_FEATURE_CAT_L3)) {
+		union cpuid_0x10_1_eax eax;
+		union cpuid_0x10_1_edx edx;
+		u32 ebx, ecx;
+
+		r = &rdt_resources_all[RDT_RESOURCE_L3];
+		cpuid_count(0x00000010, 1, &eax.full, &ebx, &ecx, &edx.full);
+		r->max_closid = edx.split.cos_max + 1;
+		r->num_closid = r->max_closid;
+		r->cbm_len = eax.split.cbm_len + 1;
+		r->max_cbm = BIT_MASK(eax.split.cbm_len + 1) - 1;
+		if (cpu_has(c, X86_FEATURE_CDP_L3))
+			r->cdp_capable = true;
+		r->enabled = true;
+
 		ret = true;
+	}
 
 	return ret;
 }
@@ -80,13 +122,17 @@ static inline bool get_rdt_resources(struct cpuinfo_x86 *c)
 static int __init intel_rdt_late_init(void)
 {
 	struct cpuinfo_x86 *c = &boot_cpu_data;
+	struct rdt_resource *r;
 
 	if (!get_rdt_resources(c))
 		return -ENODEV;
 
-	pr_info("Intel cache allocation detected\n");
-	if (cpu_has(c, X86_FEATURE_CDP_L3))
-		pr_info("Intel code data prioritization detected\n");
+	for_each_rdt_resource(r)
+		rdt_max_closid = max(rdt_max_closid, r->max_closid);
+
+	for_each_rdt_resource(r)
+		pr_info("Intel %s allocation %s detected\n", r->name,
+			r->cdp_capable ? " (with CDP)" : "");
 
 	return 0;
 }
-- 
2.5.0