[PATCH v4 11/18] x86/intel_rdt: Add basic resctrl filesystem support

[Fenghua Yu]

From: Fenghua Yu <fenghua.yu@xxxxxxxxx>

Use kernfs as basis for our user interface filesystem. This patch
supports mount/umount, and one mount parameter "cdp" to enable code/data
prioritization (though all we do at this point is ensure that the system
can support CDP).  The file system is not populated yet in this patch.

Signed-off-by: Fenghua Yu <fenghua.yu@xxxxxxxxx>
Signed-off-by: Tony Luck <tony.luck@xxxxxxxxx>
---
 arch/x86/include/asm/intel_rdt.h         |  22 +++
 arch/x86/kernel/cpu/Makefile             |   2 +-
 arch/x86/kernel/cpu/intel_rdt.c          |   8 +-
 arch/x86/kernel/cpu/intel_rdt_rdtgroup.c | 235 +++++++++++++++++++++++++++++++
 include/uapi/linux/magic.h               |   1 +
 5 files changed, 266 insertions(+), 2 deletions(-)
 create mode 100644 arch/x86/kernel/cpu/intel_rdt_rdtgroup.c

diff --git a/arch/x86/include/asm/intel_rdt.h b/arch/x86/include/asm/intel_rdt.h
index b3df691..f7acae2 100644
--- a/arch/x86/include/asm/intel_rdt.h
+++ b/arch/x86/include/asm/intel_rdt.h
@@ -5,6 +5,23 @@
 #define IA32_L2_CBM_BASE	0xd10
 
 /**
+ * struct rdtgroup - store rdtgroup's data in resctrl file system.
+ * @kn:				kernfs node
+ * @rdtgroup_list:		linked list for all rdtgroups
+ * @closid:			closid for this rdtgroup
+ */
+struct rdtgroup {
+	struct kernfs_node	*kn;
+	struct list_head	rdtgroup_list;
+	int			closid;
+};
+
+/* List of all resource groups */
+extern struct list_head rdt_all_groups;
+
+int __init rdtgroup_init(void);
+
+/**
  * struct rdt_resource - attributes of an RDT resource
  * @enabled:			Is this feature enabled on this machine
  * @name:			Name to use in "schemata" file
@@ -42,6 +59,7 @@ struct rdt_resource {
 	for (r = rdt_resources_all; r->name; r++) \
 		if (r->enabled)
 
+#define IA32_L3_QOS_CFG		0xc81
 #define IA32_L3_CBM_BASE	0xc90
 
 /**
@@ -73,6 +91,10 @@ struct msr_param {
 extern struct mutex rdtgroup_mutex;
 
 extern struct rdt_resource rdt_resources_all[];
+extern struct rdtgroup rdtgroup_default;
+extern struct static_key_false rdt_enable_key;
+
+int __init rdtgroup_init(void);
 
 enum {
 	RDT_RESOURCE_L3,
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index cf4bfd0..b4334e8 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -34,7 +34,7 @@ obj-$(CONFIG_CPU_SUP_CENTAUR)		+= centaur.o
 obj-$(CONFIG_CPU_SUP_TRANSMETA_32)	+= transmeta.o
 obj-$(CONFIG_CPU_SUP_UMC_32)		+= umc.o
 
-obj-$(CONFIG_INTEL_RDT_A)	+= intel_rdt.o
+obj-$(CONFIG_INTEL_RDT_A)	+= intel_rdt.o intel_rdt_rdtgroup.o
 
 obj-$(CONFIG_X86_MCE)			+= mcheck/
 obj-$(CONFIG_MTRR)			+= mtrr/
diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c
index 0b47ea9..3d4a125 100644
--- a/arch/x86/kernel/cpu/intel_rdt.c
+++ b/arch/x86/kernel/cpu/intel_rdt.c
@@ -266,7 +266,7 @@ static int intel_rdt_offline_cpu(unsigned int cpu)
 static int __init intel_rdt_late_init(void)
 {
 	struct rdt_resource *r;
-	int state;
+	int state, ret;
 
 	if (!get_rdt_resources())
 		return -ENODEV;
@@ -277,6 +277,12 @@ static int __init intel_rdt_late_init(void)
 	if (state < 0)
 		return state;
 
+	ret = rdtgroup_init();
+	if (ret) {
+		cpuhp_remove_state(state);
+		return ret;
+	}
+
 	for_each_rdt_resource(r)
 		pr_info("Intel RDT %s allocation %s detected\n", r->name,
 			r->cdp_capable ? " (with CDP)" : "");
diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
new file mode 100644
index 0000000..b2bbd04
--- /dev/null
+++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
@@ -0,0 +1,235 @@
+/*
+ * User interface for Resource Alloction in Resource Director Technology(RDT)
+ *
+ * Copyright (C) 2016 Intel Corporation
+ *
+ * Author: Fenghua Yu <fenghua.yu@xxxxxxxxx>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * More information about RDT be found in the Intel (R) x86 Architecture
+ * Software Developer Manual.
+ */
+
+#define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
+
+#include <linux/fs.h>
+#include <linux/sysfs.h>
+#include <linux/kernfs.h>
+#include <linux/slab.h>
+
+#include <uapi/linux/magic.h>
+
+#include <asm/intel_rdt.h>
+
+DEFINE_STATIC_KEY_FALSE(rdt_enable_key);
+struct kernfs_root *rdt_root;
+struct rdtgroup rdtgroup_default;
+LIST_HEAD(rdt_all_groups);
+
+static void l3_qos_cfg_update(void *arg)
+{
+	struct rdt_resource *r = arg;
+
+	wrmsrl(IA32_L3_QOS_CFG, r->cdp_enabled);
+}
+
+static void set_l3_qos_cfg(struct rdt_resource *r)
+{
+	struct list_head *l;
+	struct rdt_domain *d;
+	struct cpumask cpu_mask;
+	int cpu;
+
+	cpumask_clear(&cpu_mask);
+	list_for_each(l, &r->domains) {
+		d = list_entry(l, struct rdt_domain, list);
+		cpumask_set_cpu(cpumask_any(&d->cpu_mask), &cpu_mask);
+	}
+	cpu = get_cpu();
+	/* Update QOS_CFG MSR on this cpu if it's in cpu_mask. */
+	if (cpumask_test_cpu(cpu, &cpu_mask))
+		l3_qos_cfg_update(r);
+	/* Update QOS_CFG MSR on all other cpus in cpu_mask. */
+	smp_call_function_many(&cpu_mask, l3_qos_cfg_update, r, 1);
+	put_cpu();
+}
+
+static int parse_rdtgroupfs_options(char *data)
+{
+	char *token, *o = data;
+	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3];
+
+	r->cdp_enabled = false;
+	while ((token = strsep(&o, ",")) != NULL) {
+		if (!*token)
+			return -EINVAL;
+
+		if (!strcmp(token, "cdp"))
+			if (r->enabled && r->cdp_capable)
+				r->cdp_enabled = true;
+	}
+
+	return 0;
+}
+
+static struct dentry *rdt_mount(struct file_system_type *fs_type,
+				int flags, const char *unused_dev_name,
+				void *data)
+{
+	struct dentry *dentry;
+	int ret;
+	bool new_sb;
+
+	mutex_lock(&rdtgroup_mutex);
+	/*
+	 * resctrl file system can only be mounted once.
+	 */
+	if (static_branch_unlikely(&rdt_enable_key)) {
+		dentry = ERR_PTR(-EBUSY);
+		goto out;
+	}
+
+	ret = parse_rdtgroupfs_options(data);
+	if (ret) {
+		dentry = ERR_PTR(ret);
+		goto out;
+	}
+
+	dentry = kernfs_mount(fs_type, flags, rdt_root,
+			      RDTGROUP_SUPER_MAGIC, &new_sb);
+	if (IS_ERR(dentry))
+		goto out;
+	if (!new_sb) {
+		dentry = ERR_PTR(-EINVAL);
+		goto out;
+	}
+	if (rdt_resources_all[RDT_RESOURCE_L3].cdp_capable)
+		set_l3_qos_cfg(&rdt_resources_all[RDT_RESOURCE_L3]);
+	static_branch_enable(&rdt_enable_key);
+
+out:
+	mutex_unlock(&rdtgroup_mutex);
+
+	return dentry;
+}
+
+static void reset_all_cbms(struct rdt_resource *r)
+{
+	struct list_head *l;
+	struct rdt_domain *d;
+	struct msr_param msr_param;
+	struct cpumask cpu_mask;
+	int i, cpu;
+
+	cpumask_clear(&cpu_mask);
+	msr_param.res = r;
+	msr_param.low = 0;
+	msr_param.high = r->max_closid;
+
+	list_for_each(l, &r->domains) {
+		d = list_entry(l, struct rdt_domain, list);
+		cpumask_set_cpu(cpumask_any(&d->cpu_mask), &cpu_mask);
+
+		for (i = 0; i < r->max_closid; i++)
+			d->cbm[i] = r->max_cbm;
+	}
+	cpu = get_cpu();
+	/* Update CBM on this cpu if it's in cpu_mask. */
+	if (cpumask_test_cpu(cpu, &cpu_mask))
+		rdt_cbm_update(&msr_param);
+	/* Updte CBM on all other cpus in cpu_mask. */
+	smp_call_function_many(&cpu_mask, rdt_cbm_update, &msr_param, 1);
+	put_cpu();
+}
+
+static void rdt_kill_sb(struct super_block *sb)
+{
+	struct rdt_resource *r;
+
+	mutex_lock(&rdtgroup_mutex);
+
+	/*Put everything back to default values. */
+	for_each_rdt_resource(r)
+		reset_all_cbms(r);
+	r = &rdt_resources_all[RDT_RESOURCE_L3];
+	if (r->cdp_capable) {
+		r->cdp_enabled = 0;
+		set_l3_qos_cfg(r);
+	}
+
+	static_branch_disable(&rdt_enable_key);
+	kernfs_kill_sb(sb);
+	mutex_unlock(&rdtgroup_mutex);
+}
+
+static struct file_system_type rdt_fs_type = {
+	.name    = "resctrl",
+	.mount   = rdt_mount,
+	.kill_sb = rdt_kill_sb,
+};
+
+static struct kernfs_syscall_ops rdtgroup_kf_syscall_ops = {
+};
+
+static int __init rdtgroup_setup_root(void)
+{
+	rdt_root = kernfs_create_root(&rdtgroup_kf_syscall_ops,
+				      KERNFS_ROOT_CREATE_DEACTIVATED,
+				      &rdtgroup_default);
+	if (IS_ERR(rdt_root))
+		return PTR_ERR(rdt_root);
+
+	mutex_lock(&rdtgroup_mutex);
+
+	rdtgroup_default.closid = 0;
+	list_add(&rdtgroup_default.rdtgroup_list, &rdt_all_groups);
+
+	rdtgroup_default.kn = rdt_root->kn;
+	kernfs_activate(rdtgroup_default.kn);
+
+	mutex_unlock(&rdtgroup_mutex);
+
+	return 0;
+}
+
+/*
+ * rdtgroup_init - rdtgroup initialization
+ *
+ * Setup resctrl file system including set up root, create mount point,
+ * register rdtgroup filesystem, and initialize files under root directory.
+ *
+ * Return: 0 on success or -errno
+ */
+int __init rdtgroup_init(void)
+{
+	int ret = 0;
+
+	ret = rdtgroup_setup_root();
+	if (ret)
+		return ret;
+
+	ret = sysfs_create_mount_point(fs_kobj, "resctrl");
+	if (ret)
+		goto cleanup_root;
+
+	ret = register_filesystem(&rdt_fs_type);
+	if (ret)
+		goto cleanup_mountpoint;
+
+	return 0;
+
+cleanup_mountpoint:
+	sysfs_remove_mount_point(fs_kobj, "resctrl");
+cleanup_root:
+	kernfs_destroy_root(rdt_root);
+
+	return ret;
+}
diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h
index e398bea..27ef03d 100644
--- a/include/uapi/linux/magic.h
+++ b/include/uapi/linux/magic.h
@@ -57,6 +57,7 @@
 #define CGROUP_SUPER_MAGIC	0x27e0eb
 #define CGROUP2_SUPER_MAGIC	0x63677270
 
+#define RDTGROUP_SUPER_MAGIC	0x7655821
 
 #define STACK_END_MAGIC		0x57AC6E9D
 
-- 
2.5.0