[tip:x86/cache] x86/intel_rdt: Pick up L3/L2 RDT parameters from CPUID

From: tip-bot for Fenghua Yu
Date: Wed Oct 26 2016 - 17:33:03 EST


Commit-ID: c1c7c3f9d6bb6999a45f66ea4c6bfbcab87ff34b
Gitweb: http://git.kernel.org/tip/c1c7c3f9d6bb6999a45f66ea4c6bfbcab87ff34b
Author: Fenghua Yu <fenghua.yu@xxxxxxxxx>
AuthorDate: Sat, 22 Oct 2016 06:19:55 -0700
Committer: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
CommitDate: Wed, 26 Oct 2016 23:12:39 +0200

x86/intel_rdt: Pick up L3/L2 RDT parameters from CPUID

Define struct rdt_resource to hold all the parameterized values for an RDT
resource and fill in the CPUID enumerated values from leaf 0x10 if
available. Hard code them for the MSR detected Haswells.

Signed-off-by: Fenghua Yu <fenghua.yu@xxxxxxxxx>
Cc: "Ravi V Shankar" <ravi.v.shankar@xxxxxxxxx>
Cc: "Tony Luck" <tony.luck@xxxxxxxxx>
Cc: "David Carrillo-Cisneros" <davidcc@xxxxxxxxxx>
Cc: "Sai Prakhya" <sai.praneeth.prakhya@xxxxxxxxx>
Cc: "Peter Zijlstra" <peterz@xxxxxxxxxxxxx>
Cc: "Stephane Eranian" <eranian@xxxxxxxxxx>
Cc: "Dave Hansen" <dave.hansen@xxxxxxxxx>
Cc: "Shaohua Li" <shli@xxxxxx>
Cc: "Nilay Vaish" <nilayvaish@xxxxxxxxx>
Cc: "Vikas Shivappa" <vikas.shivappa@xxxxxxxxxxxxxxx>
Cc: "Ingo Molnar" <mingo@xxxxxxx>
Cc: "Borislav Petkov" <bp@xxxxxxx>
Cc: "H. Peter Anvin" <h.peter.anvin@xxxxxxxxx>
Link: http://lkml.kernel.org/r/1477142405-32078-9-git-send-email-fenghua.yu@xxxxxxxxx
Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>

---
arch/x86/include/asm/intel_rdt.h | 68 ++++++++++++++++++++++++
arch/x86/kernel/cpu/intel_rdt.c | 111 ++++++++++++++++++++++++++++++++++++---
2 files changed, 172 insertions(+), 7 deletions(-)

diff --git a/arch/x86/include/asm/intel_rdt.h b/arch/x86/include/asm/intel_rdt.h
index 3aca86d..9780409 100644
--- a/arch/x86/include/asm/intel_rdt.h
+++ b/arch/x86/include/asm/intel_rdt.h
@@ -2,5 +2,73 @@
#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
+ * @capable: Is this feature available on this machine
+ * @name: Name to use in "schemata" file
+ * @num_closid: Number of CLOSIDs available
+ * @max_cbm: Largest Cache Bit Mask allowed
+ * @min_cbm_bits: Minimum number of consecutive 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
+ * @tmp_cbms: Scratch space when updating schemata
+ * @cache_level: Which cache level defines scope of this domain
+ * @cbm_idx_multi: Multiplier of CBM index
+ * @cbm_idx_offset: Offset of CBM index. CBM index is computed by:
+ * closid * cbm_idx_multi + cbm_idx_offset
+ */
+struct rdt_resource {
+ bool enabled;
+ bool capable;
+ char *name;
+ int num_closid;
+ int cbm_len;
+ int min_cbm_bits;
+ u32 max_cbm;
+ struct list_head domains;
+ int num_domains;
+ int msr_base;
+ u32 *tmp_cbms;
+ int cache_level;
+ int cbm_idx_multi;
+ int cbm_idx_offset;
+};
+
+extern struct rdt_resource rdt_resources_all[];
+
+enum {
+ RDT_RESOURCE_L3,
+ RDT_RESOURCE_L3DATA,
+ RDT_RESOURCE_L3CODE,
+ RDT_RESOURCE_L2,
+
+ /* Must be the last */
+ RDT_NUM_RESOURCES,
+};
+
+#define for_each_capable_rdt_resource(r) \
+ for (r = rdt_resources_all; r < rdt_resources_all + RDT_NUM_RESOURCES;\
+ r++) \
+ if (r->capable)
+
+/* 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 f8e35cf..157dc8d0 100644
--- a/arch/x86/kernel/cpu/intel_rdt.c
+++ b/arch/x86/kernel/cpu/intel_rdt.c
@@ -31,6 +31,47 @@
#include <asm/intel-family.h>
#include <asm/intel_rdt.h>

+#define domain_init(id) LIST_HEAD_INIT(rdt_resources_all[id].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,
+ .cbm_idx_multi = 1,
+ .cbm_idx_offset = 0
+ },
+ {
+ .name = "L3DATA",
+ .domains = domain_init(RDT_RESOURCE_L3DATA),
+ .msr_base = IA32_L3_CBM_BASE,
+ .min_cbm_bits = 1,
+ .cache_level = 3,
+ .cbm_idx_multi = 2,
+ .cbm_idx_offset = 0
+ },
+ {
+ .name = "L3CODE",
+ .domains = domain_init(RDT_RESOURCE_L3CODE),
+ .msr_base = IA32_L3_CBM_BASE,
+ .min_cbm_bits = 1,
+ .cache_level = 3,
+ .cbm_idx_multi = 2,
+ .cbm_idx_offset = 1
+ },
+ {
+ .name = "L2",
+ .domains = domain_init(RDT_RESOURCE_L2),
+ .msr_base = IA32_L2_CBM_BASE,
+ .min_cbm_bits = 1,
+ .cache_level = 2,
+ .cbm_idx_multi = 1,
+ .cbm_idx_offset = 0
+ },
+};
+
/*
* cache_alloc_hsw_probe() - Have to probe for Intel haswell server CPUs
* as they do not have CPUID enumeration support for Cache allocation.
@@ -54,6 +95,7 @@ static inline bool cache_alloc_hsw_probe(void)
if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL &&
boot_cpu_data.x86 == 6 &&
boot_cpu_data.x86_model == INTEL_FAM6_HASWELL_X) {
+ struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3];
u32 l, h, max_cbm = BIT_MASK(20) - 1;

if (wrmsr_safe(IA32_L3_CBM_BASE, max_cbm, 0))
@@ -61,33 +103,88 @@ static inline bool cache_alloc_hsw_probe(void)
rdmsr(IA32_L3_CBM_BASE, l, h);

/* If all the bits were set in MSR, return success */
- return l == max_cbm;
+ if (l != max_cbm)
+ return false;
+
+ r->num_closid = 4;
+ r->cbm_len = 20;
+ r->max_cbm = max_cbm;
+ r->min_cbm_bits = 2;
+ r->capable = true;
+ r->enabled = true;
+
+ return true;
}

return false;
}

+static void rdt_get_config(int idx, struct rdt_resource *r)
+{
+ union cpuid_0x10_1_eax eax;
+ union cpuid_0x10_1_edx edx;
+ u32 ebx, ecx;
+
+ cpuid_count(0x00000010, idx, &eax.full, &ebx, &ecx, &edx.full);
+ r->num_closid = edx.split.cos_max + 1;
+ r->cbm_len = eax.split.cbm_len + 1;
+ r->max_cbm = BIT_MASK(eax.split.cbm_len + 1) - 1;
+ r->capable = true;
+ r->enabled = true;
+}
+
+static void rdt_get_cdp_l3_config(int type)
+{
+ struct rdt_resource *r_l3 = &rdt_resources_all[RDT_RESOURCE_L3];
+ struct rdt_resource *r = &rdt_resources_all[type];
+
+ r->num_closid = r_l3->num_closid / 2;
+ r->cbm_len = r_l3->cbm_len;
+ r->max_cbm = r_l3->max_cbm;
+ r->capable = true;
+ /*
+ * By default, CDP is disabled. CDP can be enabled by mount parameter
+ * "cdp" during resctrl file system mount time.
+ */
+ r->enabled = false;
+}
+
static inline bool get_rdt_resources(void)
{
+ bool ret = false;
+
if (cache_alloc_hsw_probe())
return true;

if (!boot_cpu_has(X86_FEATURE_RDT_A))
return false;
- if (!boot_cpu_has(X86_FEATURE_CAT_L3))
- return false;

- return true;
+ if (boot_cpu_has(X86_FEATURE_CAT_L3)) {
+ rdt_get_config(1, &rdt_resources_all[RDT_RESOURCE_L3]);
+ if (boot_cpu_has(X86_FEATURE_CDP_L3)) {
+ rdt_get_cdp_l3_config(RDT_RESOURCE_L3DATA);
+ rdt_get_cdp_l3_config(RDT_RESOURCE_L3CODE);
+ }
+ ret = true;
+ }
+ if (boot_cpu_has(X86_FEATURE_CAT_L2)) {
+ /* CPUID 0x10.2 fields are same format at 0x10.1 */
+ rdt_get_config(2, &rdt_resources_all[RDT_RESOURCE_L2]);
+ 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_capable_rdt_resource(r)
+ pr_info("Intel RDT %s allocation detected\n", r->name);

return 0;
}