[PATCH v5 11/18] x86/intel_rdt: Add basic resctrl filesystem support

["Fenghua Yu" <fenghua.yu@intel.com>]

From: Fenghua Yu <fenghua.yu@intel.com>

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@intel.com>
---
 arch/x86/include/asm/intel_rdt.h         |  24 +++
 arch/x86/kernel/cpu/Makefile             |   2 +-
 arch/x86/kernel/cpu/intel_rdt.c          |   8 +-
 arch/x86/kernel/cpu/intel_rdt_rdtgroup.c | 264 +++++++++++++++++++++++++++++++
 include/uapi/linux/magic.h               |   1 +
 5 files changed, 297 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 c0d0a6e..8e1d002 100644
--- a/arch/x86/include/asm/intel_rdt.h
+++ b/arch/x86/include/asm/intel_rdt.h
@@ -1,10 +1,30 @@
 #ifndef _ASM_X86_INTEL_RDT_H
 #define _ASM_X86_INTEL_RDT_H
 
+#include <linux/jump_label.h>
+
+#define IA32_L3_QOS_CFG		0xc81
 #define IA32_L3_CBM_BASE	0xc90
 #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
  * @capable:			Is this feature available on this machine
@@ -68,6 +88,10 @@ struct msr_param {
 extern struct mutex rdtgroup_mutex;
 
 extern struct rdt_resource rdt_resources_all[];
+extern struct rdtgroup rdtgroup_default;
+DECLARE_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 4ca9718..c07e03a 100644
--- a/arch/x86/kernel/cpu/intel_rdt.c
+++ b/arch/x86/kernel/cpu/intel_rdt.c
@@ -347,7 +347,7 @@ 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;
@@ -358,6 +358,12 @@ 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_capable_rdt_resource(r)
 		pr_info("Intel RDT %s allocation detected\n", r->name);
 
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..6c9061d
--- /dev/null
+++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
@@ -0,0 +1,264 @@
+/*
+ * User interface for Resource Alloction in Resource Director Technology(RDT)
+ *
+ * Copyright (C) 2016 Intel Corporation
+ *
+ * Author: Fenghua Yu <fenghua.yu@intel.com>
+ *
+ * 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)
+{
+	bool enable = *(bool *)arg;
+
+	wrmsrl(IA32_L3_QOS_CFG, enable);
+}
+
+static int set_l3_qos_cfg(struct rdt_resource *r, bool enable)
+{
+	struct rdt_domain *d;
+	cpumask_var_t cpu_mask;
+	int cpu;
+
+	if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL))
+		return -ENOMEM;
+
+	list_for_each_entry(d, &r->domains, list) {
+		/* Pick one CPU from each domain instance to update MSR */
+		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, &enable, 1);
+	put_cpu();
+
+	free_cpumask_var(cpu_mask);
+
+	return 0;
+}
+
+static int enable_cdp(void)
+{
+	struct rdt_resource *r_l3 = &rdt_resources_all[RDT_RESOURCE_L3];
+	struct rdt_resource *r_l3data = &rdt_resources_all[RDT_RESOURCE_L3DATA];
+	struct rdt_resource *r_l3code = &rdt_resources_all[RDT_RESOURCE_L3CODE];
+
+	if (!r_l3->capable || !r_l3data->capable || !r_l3code->capable)
+		return -EINVAL;
+
+	r_l3->enabled = false;
+	r_l3data->enabled = true;
+	r_l3code->enabled = true;
+
+	return 0;
+}
+
+static int parse_rdtgroupfs_options(char *data)
+{
+	char *token, *o = data;
+	int ret = 0;
+
+	while ((token = strsep(&o, ",")) != NULL) {
+		if (!*token)
+			return -EINVAL;
+
+		if (!strcmp(token, "cdp"))
+			ret = enable_cdp();
+	}
+
+	return ret;
+}
+
+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;
+
+	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, NULL);
+	if (IS_ERR(dentry))
+		goto out;
+
+	if (rdt_resources_all[RDT_RESOURCE_L3DATA].enabled &&
+	    rdt_resources_all[RDT_RESOURCE_L3CODE].enabled) {
+		ret = set_l3_qos_cfg(&rdt_resources_all[RDT_RESOURCE_L3], true);
+		if (ret)
+			goto out;
+	}
+	static_branch_enable(&rdt_enable_key);
+
+out:
+	mutex_unlock(&rdtgroup_mutex);
+
+	return dentry;
+}
+
+static int reset_all_cbms(struct rdt_resource *r)
+{
+	struct rdt_domain *d;
+	struct msr_param msr_param;
+	cpumask_var_t cpu_mask;
+	int i, cpu;
+
+	if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL))
+		return -ENOMEM;
+
+	msr_param.res = r;
+	msr_param.low = 0;
+	msr_param.high = r->num_closid;
+
+	/*
+	 * Reset each domain's all CBMs to max value and copy the domain's
+	 * cpus to cpu_mask.
+	 */
+	list_for_each_entry(d, &r->domains, list) {
+		cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask);
+
+		for (i = 0; i < r->num_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);
+	/* Update CBM on all other cpus in cpu_mask. */
+	smp_call_function_many(cpu_mask, rdt_cbm_update, &msr_param, 1);
+	put_cpu();
+
+	free_cpumask_var(cpu_mask);
+
+	return 0;
+}
+
+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_enabled_rdt_resource(r)
+		reset_all_cbms(r);
+	r = &rdt_resources_all[RDT_RESOURCE_L3];
+	r->enabled = r->capable;
+	if (boot_cpu_has(X86_FEATURE_CDP_L3)) {
+		rdt_resources_all[RDT_RESOURCE_L3DATA].enabled = false;
+		rdt_resources_all[RDT_RESOURCE_L3CODE].enabled = false;
+		set_l3_qos_cfg(r, false);
+	}
+
+	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 9bd5594..e230af2 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