[PATCH v4 08/18] x86/intel_rdt: Pick up L3/L2 RDT parameters from CPUID

From: Fenghua Yu
Date: Fri Oct 14 2016 - 19:13:24 EST


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 | 62 ++++++++++++++++++++++++++++++++++
arch/x86/kernel/cpu/intel_rdt.c | 72 +++++++++++++++++++++++++++++++++++++---
2 files changed, 130 insertions(+), 4 deletions(-)

diff --git a/arch/x86/include/asm/intel_rdt.h b/arch/x86/include/asm/intel_rdt.h
index 3aca86d..8c61d83 100644
--- a/arch/x86/include/asm/intel_rdt.h
+++ b/arch/x86/include/asm/intel_rdt.h
@@ -2,5 +2,67 @@
#define _ASM_X86_INTEL_RDT_H

#define IA32_L3_CBM_BASE 0xc90
+#define IA32_L2_CBM_BASE 0xd10

+/**
+ * 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,
+ RDT_RESOURCE_L2,
+};
+
+/* 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 9d55942..87f9650 100644
--- a/arch/x86/kernel/cpu/intel_rdt.c
+++ b/arch/x86/kernel/cpu/intel_rdt.c
@@ -31,6 +31,28 @@
#include <asm/intel-family.h>
#include <asm/intel_rdt.h>

+#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
+ },
+ {
+ .name = "L2",
+ .domains = domain_init(RDT_RESOURCE_L2),
+ .msr_base = IA32_L2_CBM_BASE,
+ .min_cbm_bits = 1,
+ .cache_level = 2
+ },
+ {
+ /* NULL terminated */
+ }
+};
+
/*
* cache_alloc_hsw_probe() - Have to probe for Intel haswell server CPUs
* as they do not have CPUID enumeration support for Cache allocation.
@@ -53,6 +75,7 @@ static inline bool cache_alloc_hsw_probe(void)
{
u32 l, h;
u32 max_cbm = BIT_MASK(20) - 1;
+ struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3];

if (wrmsr_safe(IA32_L3_CBM_BASE, max_cbm, 0))
return false;
@@ -60,11 +83,19 @@ static inline bool cache_alloc_hsw_probe(void)
if (l != max_cbm)
return false;

+ r->max_closid = 4;
+ r->num_closid = r->max_closid;
+ r->cbm_len = 20;
+ r->max_cbm = max_cbm;
+ r->min_cbm_bits = 2;
+ r->enabled = true;
+
return true;
}

static inline bool get_rdt_resources(void)
{
+ struct rdt_resource *r;
bool ret = false;

if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL &&
@@ -74,20 +105,53 @@ static inline bool get_rdt_resources(void)

if (!boot_cpu_has(X86_FEATURE_RDT_A))
return false;
- if (boot_cpu_has(X86_FEATURE_CAT_L3))
+ if (boot_cpu_has(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 (boot_cpu_has(X86_FEATURE_CDP_L3))
+ r->cdp_capable = true;
+ r->enabled = true;
+
ret = true;
+ }
+ if (boot_cpu_has(X86_FEATURE_CAT_L2)) {
+ union cpuid_0x10_1_eax eax;
+ union cpuid_0x10_1_edx edx;
+ u32 ebx, ecx;
+
+ /* CPUID 0x10.2 fields are same format at 0x10.1 */
+ r = &rdt_resources_all[RDT_RESOURCE_L2];
+ cpuid_count(0x00000010, 2, &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;
+ r->enabled = true;
+
+ ret = true;
+ }

return ret;
}

static int __init intel_rdt_late_init(void)
{
+ struct rdt_resource *r;
+
if (!get_rdt_resources())
return -ENODEV;

- pr_info("Intel RDT cache allocation detected\n");
- if (boot_cpu_has(X86_FEATURE_CDP_L3))
- pr_info("Intel RDT code data prioritization detected\n");
+ for_each_rdt_resource(r)
+ pr_info("Intel RDT %s allocation %s detected\n", r->name,
+ r->cdp_capable ? " (with CDP)" : "");

return 0;
}
--
2.5.0