[tip:x86/cpu] x86/intel_rdt/mba: Add primary support for Memory Bandwidth Allocation (MBA)

[tip-bot for Vikas Shivappa <tipbot@zytor.com>]

Commit-ID:  05b93417ce5b924c6652de19fdcc27439ab37c90
Gitweb:     http://git.kernel.org/tip/05b93417ce5b924c6652de19fdcc27439ab37c90
Author:     Vikas Shivappa <vikas.shivappa@linux.intel.com>
AuthorDate: Fri, 7 Apr 2017 17:33:53 -0700
Committer:  Thomas Gleixner <tglx@linutronix.de>
CommitDate: Fri, 14 Apr 2017 16:10:08 +0200

x86/intel_rdt/mba: Add primary support for Memory Bandwidth Allocation (MBA)

The MBA feature details like minimum bandwidth supported, bandwidth
granularity etc are obtained via executing CPUID with EAX=10H ,ECX=3.

Setup and initialize the MBA specific extensions to data structures like
global list of RDT resources, RDT resource structure and RDT domain
structure.

[ tglx: Split out the seperate structure and the CBM related parts ]

Signed-off-by: Vikas Shivappa <vikas.shivappa@linux.intel.com>
Cc: ravi.v.shankar@intel.com
Cc: tony.luck@intel.com
Cc: fenghua.yu@intel.com
Cc: vikas.shivappa@intel.com
Link: http://lkml.kernel.org/r/1491611637-20417-5-git-send-email-vikas.shivappa@linux.intel.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

---
 arch/x86/include/asm/intel_rdt.h | 24 ++++++++++-
 arch/x86/kernel/cpu/intel_rdt.c  | 89 +++++++++++++++++++++++++++++++++++++++-
 2 files changed, 110 insertions(+), 3 deletions(-)

diff --git a/arch/x86/include/asm/intel_rdt.h b/arch/x86/include/asm/intel_rdt.h
index 6295594..0620fc9 100644
--- a/arch/x86/include/asm/intel_rdt.h
+++ b/arch/x86/include/asm/intel_rdt.h
@@ -12,6 +12,7 @@
 #define IA32_L3_QOS_CFG		0xc81
 #define IA32_L3_CBM_BASE	0xc90
 #define IA32_L2_CBM_BASE	0xd10
+#define IA32_MBA_THRTL_BASE	0xd50
 
 #define L3_QOS_CDP_ENABLE	0x01ULL
 
@@ -120,6 +121,23 @@ struct rdt_cache {
 };
 
 /**
+ * struct rdt_membw - Memory bandwidth allocation related data
+ * @max_delay:		Max throttle delay. Delay is the hardware
+ *			representation for memory bandwidth.
+ * @min_bw:		Minimum memory bandwidth percentage user can request
+ * @bw_gran:		Granularity at which the memory bandwidth is allocated
+ * @delay_linear:	True if memory B/W delay is in linear scale
+ * @mb_map:		Mapping of memory B/W percentage to memory B/W delay
+ */
+struct rdt_membw {
+	u32		max_delay;
+	u32		min_bw;
+	u32		bw_gran;
+	u32		delay_linear;
+	u32		*mb_map;
+};
+
+/**
  * struct rdt_resource - attributes of an RDT resource
  * @enabled:		Is this feature enabled on this machine
  * @capable:		Is this feature available on this machine
@@ -145,7 +163,10 @@ struct rdt_resource {
 				 struct rdt_resource *r);
 	int			data_width;
 	struct list_head	domains;
-	struct rdt_cache	cache;
+	union {
+		struct rdt_cache	cache;
+		struct rdt_membw	membw;
+	};
 };
 
 extern struct mutex rdtgroup_mutex;
@@ -161,6 +182,7 @@ enum {
 	RDT_RESOURCE_L3DATA,
 	RDT_RESOURCE_L3CODE,
 	RDT_RESOURCE_L2,
+	RDT_RESOURCE_MBA,
 
 	/* Must be the last */
 	RDT_NUM_RESOURCES,
diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c
index 82eafd6..ae1aec1 100644
--- a/arch/x86/kernel/cpu/intel_rdt.c
+++ b/arch/x86/kernel/cpu/intel_rdt.c
@@ -32,6 +32,9 @@
 #include <asm/intel-family.h>
 #include <asm/intel_rdt.h>
 
+#define MAX_MBA_BW	100u
+#define MBA_IS_LINEAR	0x4
+
 /* Mutex to protect rdtgroup access. */
 DEFINE_MUTEX(rdtgroup_mutex);
 
@@ -44,6 +47,8 @@ DEFINE_PER_CPU_READ_MOSTLY(int, cpu_closid);
 int max_name_width, max_data_width;
 
 static void
+mba_wrmsr(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r);
+static void
 cat_wrmsr(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r);
 
 #define domain_init(id) LIST_HEAD_INIT(rdt_resources_all[id].domains)
@@ -97,6 +102,13 @@ struct rdt_resource rdt_resources_all[] = {
 			.cbm_idx_offset	= 0,
 		},
 	},
+	{
+		.name			= "MB",
+		.domains		= domain_init(RDT_RESOURCE_MBA),
+		.msr_base		= IA32_MBA_THRTL_BASE,
+		.msr_update		= mba_wrmsr,
+		.cache_level		= 3,
+	},
 };
 
 static unsigned int cbm_idx(struct rdt_resource *r, unsigned int closid)
@@ -151,6 +163,53 @@ static inline bool cache_alloc_hsw_probe(void)
 	return false;
 }
 
+/*
+ * rdt_get_mb_table() - get a mapping of bandwidth(b/w) percentage values
+ * exposed to user interface and the h/w understandable delay values.
+ *
+ * The non-linear delay values have the granularity of power of two
+ * and also the h/w does not guarantee a curve for configured delay
+ * values vs. actual b/w enforced.
+ * Hence we need a mapping that is pre calibrated so the user can
+ * express the memory b/w as a percentage value.
+ */
+static inline bool rdt_get_mb_table(struct rdt_resource *r)
+{
+	/*
+	 * There are no Intel SKUs as of now to support non-linear delay.
+	 */
+	pr_info("MBA b/w map not implemented for cpu:%d, model:%d",
+		boot_cpu_data.x86, boot_cpu_data.x86_model);
+
+	return false;
+}
+
+static bool rdt_get_mem_config(struct rdt_resource *r)
+{
+	union cpuid_0x10_3_eax eax;
+	union cpuid_0x10_x_edx edx;
+	u32 ebx, ecx;
+
+	cpuid_count(0x00000010, 3, &eax.full, &ebx, &ecx, &edx.full);
+	r->num_closid = edx.split.cos_max + 1;
+	r->membw.max_delay = eax.split.max_delay + 1;
+	r->default_ctrl = MAX_MBA_BW;
+	if (ecx & MBA_IS_LINEAR) {
+		r->membw.delay_linear = true;
+		r->membw.min_bw = MAX_MBA_BW - r->membw.max_delay;
+		r->membw.bw_gran = MAX_MBA_BW - r->membw.max_delay;
+	} else {
+		if (!rdt_get_mb_table(r))
+			return false;
+	}
+	r->data_width = 3;
+
+	r->capable = true;
+	r->enabled = true;
+
+	return true;
+}
+
 static void rdt_get_cache_config(int idx, struct rdt_resource *r)
 {
 	union cpuid_0x10_1_eax eax;
@@ -196,6 +255,30 @@ static int get_cache_id(int cpu, int level)
 	return -1;
 }
 
+/*
+ * Map the memory b/w percentage value to delay values
+ * that can be written to QOS_MSRs.
+ * There are currently no SKUs which support non linear delay values.
+ */
+static u32 delay_bw_map(unsigned long bw, struct rdt_resource *r)
+{
+	if (r->membw.delay_linear)
+		return MAX_MBA_BW - bw;
+
+	pr_warn_once("Non Linear delay-bw map not supported but queried\n");
+	return r->default_ctrl;
+}
+
+static void
+mba_wrmsr(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r)
+{
+	unsigned int i;
+
+	/*  Write the delay values for mba. */
+	for (i = m->low; i < m->high; i++)
+		wrmsrl(r->msr_base + i, delay_bw_map(d->ctrl_val[i], r));
+}
+
 static void
 cat_wrmsr(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r)
 {
@@ -431,8 +514,10 @@ static __init bool get_rdt_resources(void)
 		ret = true;
 	}
 
-	if (boot_cpu_has(X86_FEATURE_MBA))
-		ret = true;
+	if (boot_cpu_has(X86_FEATURE_MBA)) {
+		if (rdt_get_mem_config(&rdt_resources_all[RDT_RESOURCE_MBA]))
+			ret = true;
+	}
 
 	return ret;
 }