[PATCH 4/8] x86/intel_rct/mba: Add MBA structures and initialize MBA

[Vikas Shivappa]

The MBA feature details like minimum bandwidth supported, b/w
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.

Signed-off-by: Vikas Shivappa <vikas.shivappa@xxxxxxxxxxxxxxx>
---
 arch/x86/include/asm/intel_rdt.h |  92 +++++++++++++++---------
 arch/x86/kernel/cpu/intel_rdt.c  | 151 ++++++++++++++++++++++++++++++++++++---
 2 files changed, 199 insertions(+), 44 deletions(-)

diff --git a/arch/x86/include/asm/intel_rdt.h b/arch/x86/include/asm/intel_rdt.h
index 4c94f18..097134b 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
 
@@ -69,39 +70,6 @@ struct rftype {
 };
 
 /**
- * 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
- * @default_ctrl:		Specifies default cache cbm or mem b/w percent.
- * @data_width:		Character width of data when displaying
- * @min_cbm_bits:		Minimum number of consecutive bits to be set
- *				in a cache bit mask
- * @domains:			All domains for this resource
- * @msr_base:			Base MSR address for CBMs
- * @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			default_ctrl;
-	int			data_width;
-	struct list_head	domains;
-	int			msr_base;
-	int			cache_level;
-	int			cbm_idx_multi;
-	int			cbm_idx_offset;
-};
-
-/**
  * struct rdt_domain - group of cpus sharing an RDT resource
  * @list:	all instances of this resource
  * @id:		unique id for this instance
@@ -131,6 +99,63 @@ struct msr_param {
 	int			high;
 };
 
+/**
+ * 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
+ * @default_ctrl:		Specifies default cache cbm or mem b/w percent.
+ * @data_width:		Character width of data when displaying
+ * @msr_update:		Function pointer to update QOS MSRs
+ * @domains:			All domains for this resource
+ * @msr_base:			Base MSR address for CBMs
+ * @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
+ * @cbm_len			Number of cbm bits
+ * @min_cbm_bits:		Minimum number of consecutive bits to be set
+ *				in a cache bit mask
+ * @max_delay:			Max throttle delay. Delay is the hardware
+ *				understandable value 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 values
+ */
+struct rdt_resource {
+	bool			enabled;
+	bool			capable;
+	char			*name;
+	int			num_closid;
+	u32			default_ctrl;
+	int			data_width;
+	void (*msr_update)	(struct rdt_domain *d, struct msr_param *m,
+				 struct rdt_resource *r);
+	struct list_head	domains;
+	int			msr_base;
+	int			cache_level;
+	int			cbm_idx_multi;
+	int			cbm_idx_offset;
+	union {
+		struct { /*cache ctrls*/
+			int	cbm_len;
+			int	min_cbm_bits;
+		};
+		struct { /*mem ctrls*/
+			u32	max_delay;
+			u32	min_bw;
+			u32	bw_gran;
+			u32	delay_linear;
+			u32	*mb_map;
+		};
+	};
+};
+
 extern struct mutex rdtgroup_mutex;
 
 extern struct rdt_resource rdt_resources_all[];
@@ -144,6 +169,7 @@ 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 c4cf2e8..b9f1cfc 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);
 
@@ -45,11 +48,17 @@
  */
 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);
+
 struct rdt_resource rdt_resources_all[] = {
 	{
 		.name		= "L3",
 		.domains	= domain_init(RDT_RESOURCE_L3),
 		.msr_base	= IA32_L3_CBM_BASE,
+		.msr_update	= cat_wrmsr,
 		.min_cbm_bits	= 1,
 		.cache_level	= 3,
 		.cbm_idx_multi	= 1,
@@ -59,6 +68,7 @@ struct rdt_resource rdt_resources_all[] = {
 		.name		= "L3DATA",
 		.domains	= domain_init(RDT_RESOURCE_L3DATA),
 		.msr_base	= IA32_L3_CBM_BASE,
+		.msr_update	= cat_wrmsr,
 		.min_cbm_bits	= 1,
 		.cache_level	= 3,
 		.cbm_idx_multi	= 2,
@@ -68,6 +78,7 @@ struct rdt_resource rdt_resources_all[] = {
 		.name		= "L3CODE",
 		.domains	= domain_init(RDT_RESOURCE_L3CODE),
 		.msr_base	= IA32_L3_CBM_BASE,
+		.msr_update	= cat_wrmsr,
 		.min_cbm_bits	= 1,
 		.cache_level	= 3,
 		.cbm_idx_multi	= 2,
@@ -77,11 +88,21 @@ struct rdt_resource rdt_resources_all[] = {
 		.name		= "L2",
 		.domains	= domain_init(RDT_RESOURCE_L2),
 		.msr_base	= IA32_L2_CBM_BASE,
+		.msr_update	= cat_wrmsr,
 		.min_cbm_bits	= 1,
 		.cache_level	= 2,
 		.cbm_idx_multi	= 1,
 		.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,
+		.cbm_idx_multi	= 1,
+		.cbm_idx_offset = 0
+	},
 };
 
 static int cbm_idx(struct rdt_resource *r, int closid)
@@ -136,6 +157,53 @@ 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->max_delay = eax.split.max_delay + 1;
+	r->default_ctrl = MAX_MBA_BW;
+	if (ecx & MBA_IS_LINEAR) {
+		r->delay_linear = true;
+		r->min_bw = MAX_MBA_BW - r->max_delay;
+		r->bw_gran = MAX_MBA_BW - r->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;
@@ -212,7 +280,8 @@ static inline bool get_rdt_resources(void)
 		ret = true;
 	}
 
-	if (boot_cpu_has(X86_FEATURE_MBA))
+	if (boot_cpu_has(X86_FEATURE_MBA) &&
+	     rdt_get_mem_config(&rdt_resources_all[RDT_RESOURCE_MBA]))
 		ret = true;
 
 	rdt_init_padding();
@@ -233,6 +302,47 @@ 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->delay_linear)
+		return MAX_MBA_BW - bw;
+
+	WARN_ONCE(1, "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)
+{
+	int i;
+
+	for (i = m->low; i < m->high; i++) {
+		int idx = cbm_idx(r, i);
+
+		/*
+		 * Write the delay value for mba.
+		 */
+		wrmsrl(r->msr_base + idx, delay_bw_map(d->ctrl_val[i], r));
+	}
+}
+
+static void
+cat_wrmsr(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r)
+{
+	int i;
+
+	for (i = m->low; i < m->high; i++) {
+		int idx = cbm_idx(r, i);
+
+		wrmsrl(r->msr_base + idx, d->ctrl_val[i]);
+	}
+}
+
 void rdt_ctrl_update(void *arg)
 {
 	struct msr_param *m = (struct msr_param *)arg;
@@ -291,6 +401,33 @@ static struct rdt_domain *rdt_find_domain(struct rdt_resource *r, int id,
 	return NULL;
 }
 
+static int domain_setup_ctrlval(struct rdt_resource *r, struct rdt_domain *d)
+{
+	struct msr_param m;
+	u32 *dc;
+	int i;
+
+	dc = kmalloc_array(r->num_closid, sizeof(*d->ctrl_val), GFP_KERNEL);
+	if (!dc)
+		return -ENOMEM;
+
+	d->ctrl_val = dc;
+
+	/*
+	 * Initialize the Control MSRs to having no control.
+	 * For Cache Allocation: Set all bits in cbm
+	 * For Memory Allocation: Set b/w requested to 100
+	 */
+	for (i = 0; i < r->num_closid; i++, dc++)
+		*dc = r->default_ctrl;
+
+	m.low = 0;
+	m.high = r->num_closid;
+	r->msr_update(d, &m, r);
+
+	return 0;
+}
+
 /*
  * domain_add_cpu - Add a cpu to a resource's domain list.
  *
@@ -306,7 +443,7 @@ static struct rdt_domain *rdt_find_domain(struct rdt_resource *r, int id,
  */
 static void domain_add_cpu(int cpu, struct rdt_resource *r)
 {
-	int i, id = get_cache_id(cpu, r->cache_level);
+	int id = get_cache_id(cpu, r->cache_level);
 	struct list_head *add_pos = NULL;
 	struct rdt_domain *d;
 
@@ -327,19 +464,11 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r)
 
 	d->id = id;
 
-	d->ctrl_val = kmalloc_array(r->num_closid, sizeof(*d->ctrl_val), GFP_KERNEL);
-	if (!d->ctrl_val) {
+	if (domain_setup_ctrlval(r, d)) {
 		kfree(d);
 		return;
 	}
 
-	for (i = 0; i < r->num_closid; i++) {
-		int idx = cbm_idx(r, i);
-
-		d->ctrl_val[i] = r->default_ctrl;
-		wrmsrl(r->msr_base + idx, d->ctrl_val[i]);
-	}
-
 	cpumask_set_cpu(cpu, &d->cpu_mask);
 	list_add_tail(&d->list, add_pos);
 }
-- 
1.9.1