[PATCH 2/7] x86/intel_rdt: Adds support for Class of service management

[Vikas Shivappa <vikas.shivappa@linux.intel.com>]

This patch adds a cgroup subsystem to support Intel Resource Director
Technology(RDT) or Platform Shared resources Control. The resources that
are currently supported for sharing is Last level cache
(Cache Allocation Technology or CAT).
When a RDT cgroup is created it has a CLOSid and CBM associated with it
which are inherited from its parent. A Class of service(CLOS) in Cache
Allocation is represented by a CLOSid. CLOSid is internal to the kernel
and not exposed to user. Cache bitmask(CBM) represents one cache
'subset'. Root cgroup would have all available bits set for its CBM and
would be assigned the CLOSid 0.

CLOSid allocation is tracked using a separate bitmap. The maximum number
of CLOSids is specified by the h/w during CPUID enumeration and the
kernel simply throws an -ENOSPC when it runs out of CLOSids.

Each CBM has an associated CLOSid. If multiple cgroups have the same CBM
they would also have the same CLOSid. The reference count parameter in
CLOSid-CBM map keeps track of how many cgroups are using each
CLOSid<->CBM mapping.

Signed-off-by: Vikas Shivappa <vikas.shivappa@linux.intel.com>
---
 arch/x86/include/asm/intel_rdt.h |  38 +++++++++++++++
 arch/x86/kernel/cpu/intel_rdt.c  | 101 ++++++++++++++++++++++++++++++++++++---
 include/linux/cgroup_subsys.h    |   4 ++
 3 files changed, 137 insertions(+), 6 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..87af1a5
--- /dev/null
+++ b/arch/x86/include/asm/intel_rdt.h
@@ -0,0 +1,38 @@
+#ifndef _RDT_H_
+#define _RDT_H_
+
+#ifdef CONFIG_CGROUP_RDT
+
+#include <linux/cgroup.h>
+
+struct rdt_subsys_info {
+	/* Clos Bitmap to keep track of available CLOSids.*/
+	unsigned long *closmap;
+};
+
+struct intel_rdt {
+	struct cgroup_subsys_state css;
+	/* Class of service for the cgroup.*/
+	unsigned int clos;
+};
+
+struct clos_cbm_map {
+	unsigned long cbm;
+	unsigned int cgrp_count;
+};
+
+/*
+ * Return rdt group corresponding to this container.
+ */
+static inline struct intel_rdt *css_rdt(struct cgroup_subsys_state *css)
+{
+	return css ? container_of(css, struct intel_rdt, css) : NULL;
+}
+
+static inline struct intel_rdt *parent_rdt(struct intel_rdt *ir)
+{
+	return css_rdt(ir->css.parent);
+}
+
+#endif
+#endif
diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c
index 46ce449..3726f41 100644
--- a/arch/x86/kernel/cpu/intel_rdt.c
+++ b/arch/x86/kernel/cpu/intel_rdt.c
@@ -23,10 +23,19 @@
 #include <linux/slab.h>
 #include <linux/err.h>
 #include <linux/spinlock.h>
+#include <asm/intel_rdt.h>
 
-static inline bool rdt_supported(struct cpuinfo_x86 *c)
+/*
+ * ccmap maintains 1:1 mapping between CLOSid and cbm.
+ */
+static struct clos_cbm_map *ccmap;
+static struct rdt_subsys_info rdtss_info;
+static DEFINE_MUTEX(rdt_group_mutex);
+struct intel_rdt rdt_root_group;
+
+static inline bool cat_supported(struct cpuinfo_x86 *c)
 {
-	if (cpu_has(c, X86_FEATURE_RDT))
+	if (cpu_has(c, X86_FEATURE_CAT_L3))
 		return true;
 
 	return false;
@@ -35,17 +44,97 @@ static inline bool rdt_supported(struct cpuinfo_x86 *c)
 static int __init rdt_late_init(void)
 {
 	struct cpuinfo_x86 *c = &boot_cpu_data;
+	static struct clos_cbm_map *ccm;
+	size_t sizeb;
 	int maxid, cbm_len;
 
-	if (!rdt_supported(c))
+	if (!cat_supported(c)) {
+		rdt_root_group.css.ss->disabled = 1;
 		return -ENODEV;
+	} else {
+		maxid = c->x86_cat_closs;
+		cbm_len = c->x86_cat_cbmlength;
+		sizeb = BITS_TO_LONGS(maxid) * sizeof(long);
+
+		rdtss_info.closmap = kzalloc(sizeb, GFP_KERNEL);
+		if (!rdtss_info.closmap)
+			return -ENOMEM;
 
-	maxid = c->x86_cat_closs;
-	cbm_len = c->x86_cat_cbmlength;
+		sizeb = maxid * sizeof(struct clos_cbm_map);
+		ccmap = kzalloc(sizeb, GFP_KERNEL);
+		if (!ccmap) {
+			kfree(rdtss_info.closmap);
+			return -ENOMEM;
+		}
 
-	pr_info("cbmlength:%u,Closs: %u\n", cbm_len, maxid);
+		set_bit(0, rdtss_info.closmap);
+		rdt_root_group.clos = 0;
+
+		ccm = &ccmap[0];
+		ccm->cbm = (u32)((u64)(1 << cbm_len) - 1);
+		ccm->cgrp_count++;
+
+		pr_info("cbmlength:%u,Closs: %u\n", cbm_len, maxid);
+	}
 
 	return 0;
 }
 
 late_initcall(rdt_late_init);
+
+/*
+* Called with the rdt_group_mutex held.
+*/
+static int rdt_free_closid(struct intel_rdt *ir)
+{
+
+	lockdep_assert_held(&rdt_group_mutex);
+
+	WARN_ON(!ccmap[ir->clos].cgrp_count);
+	ccmap[ir->clos].cgrp_count--;
+	if (!ccmap[ir->clos].cgrp_count)
+		clear_bit(ir->clos, rdtss_info.closmap);
+
+	return 0;
+}
+
+static struct cgroup_subsys_state *
+rdt_css_alloc(struct cgroup_subsys_state *parent_css)
+{
+	struct intel_rdt *parent = css_rdt(parent_css);
+	struct intel_rdt *ir;
+
+	/*
+	 * Cannot return failure on systems with no Cache Allocation
+	 * as the cgroup_init does not handle failures gracefully.
+	 */
+	if (!parent)
+		return &rdt_root_group.css;
+
+	ir = kzalloc(sizeof(struct intel_rdt), GFP_KERNEL);
+	if (!ir)
+		return ERR_PTR(-ENOMEM);
+
+	mutex_lock(&rdt_group_mutex);
+	ir->clos = parent->clos;
+	ccmap[parent->clos].cgrp_count++;
+	mutex_unlock(&rdt_group_mutex);
+
+	return &ir->css;
+}
+
+static void rdt_css_free(struct cgroup_subsys_state *css)
+{
+	struct intel_rdt *ir = css_rdt(css);
+
+	mutex_lock(&rdt_group_mutex);
+	rdt_free_closid(ir);
+	kfree(ir);
+	mutex_unlock(&rdt_group_mutex);
+}
+
+struct cgroup_subsys rdt_cgrp_subsys = {
+	.css_alloc			= rdt_css_alloc,
+	.css_free			= rdt_css_free,
+	.early_init			= 0,
+};
diff --git a/include/linux/cgroup_subsys.h b/include/linux/cgroup_subsys.h
index e4a96fb..81c803d 100644
--- a/include/linux/cgroup_subsys.h
+++ b/include/linux/cgroup_subsys.h
@@ -47,6 +47,10 @@ SUBSYS(net_prio)
 SUBSYS(hugetlb)
 #endif
 
+#if IS_ENABLED(CONFIG_CGROUP_RDT)
+SUBSYS(rdt)
+#endif
+
 /*
  * The following subsystems are not supported on the default hierarchy.
  */
-- 
1.9.1