x86/intel_rdt: Add cpus file

Now we populate each directory with a read/write (mode 0644) file
named "cpus". This is used to over-ride the resources available
to processes in the default resource group when running on specific
CPUs.  Each "cpus" file reads as a cpumask showing which CPUs belong
to this resource group. Initially all online CPUs are assigned to
the default group. They can be added to other groups by writing a
cpumask to the "cpus" file in the directory for the resource group
(which will remove them from the previous group to which they were
assigned). CPU online/offline operations will delete CPUs that go
offline from whatever group they are in and add new CPUs to the
default group.

If there are CPUs assigned to a group when the directory is removed,
they are returned to the default group.

Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Fenghua Yu <fenghua.yu@intel.com>
Cc: "Ravi V Shankar" <ravi.v.shankar@intel.com>
Cc: "Shaohua Li" <shli@fb.com>
Cc: "Sai Prakhya" <sai.praneeth.prakhya@intel.com>
Cc: "Peter Zijlstra" <peterz@infradead.org>
Cc: "Stephane Eranian" <eranian@google.com>
Cc: "Dave Hansen" <dave.hansen@intel.com>
Cc: "David Carrillo-Cisneros" <davidcc@google.com>
Cc: "Nilay Vaish" <nilayvaish@gmail.com>
Cc: "Vikas Shivappa" <vikas.shivappa@linux.intel.com>
Cc: "Ingo Molnar" <mingo@elte.hu>
Cc: "Borislav Petkov" <bp@suse.de>
Cc: "H. Peter Anvin" <h.peter.anvin@intel.com>
Link: http://lkml.kernel.org/r/1477692289-37412-7-git-send-email-fenghua.yu@intel.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

arch/x86/include/asm/intel_rdt.h

@@ -14,13 +14,16 @@
  * @kn:				kernfs node
  * @rdtgroup_list:		linked list for all rdtgroups
  * @closid:			closid for this rdtgroup
+ * @cpu_mask:			CPUs assigned to this rdtgroup
  * @flags:			status bits
  * @waitcount:			how many cpus expect to find this
+ *				group when they acquire rdtgroup_mutex
  */
 struct rdtgroup {
 	struct kernfs_node	*kn;
 	struct list_head	rdtgroup_list;
 	int			closid;
+	struct cpumask		cpu_mask;
 	int			flags;
 	atomic_t		waitcount;
 };
@@ -162,6 +165,8 @@ union cpuid_0x10_1_edx {
 	unsigned int full;
 };
 
+DECLARE_PER_CPU_READ_MOSTLY(int, cpu_closid);
+
 void rdt_cbm_update(void *arg);
 struct rdtgroup *rdtgroup_kn_lock_live(struct kernfs_node *kn);
 void rdtgroup_kn_unlock(struct kernfs_node *kn);

arch/x86/kernel/cpu/intel_rdt.c

@@ -36,6 +36,8 @@
 /* Mutex to protect rdtgroup access. */
 DEFINE_MUTEX(rdtgroup_mutex);
 
+DEFINE_PER_CPU_READ_MOSTLY(int, cpu_closid);
+
 #define domain_init(id) LIST_HEAD_INIT(rdt_resources_all[id].domains)
 
 struct rdt_resource rdt_resources_all[] = {
@@ -331,16 +333,25 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r)
 	}
 }
 
-static int intel_rdt_online_cpu(unsigned int cpu)
+static void clear_closid(int cpu)
 {
 	struct intel_pqr_state *state = this_cpu_ptr(&pqr_state);
+
+	per_cpu(cpu_closid, cpu) = 0;
+	state->closid = 0;
+	wrmsr(MSR_IA32_PQR_ASSOC, state->rmid, 0);
+}
+
+static int intel_rdt_online_cpu(unsigned int cpu)
+{
 	struct rdt_resource *r;
 
 	mutex_lock(&rdtgroup_mutex);
 	for_each_capable_rdt_resource(r)
 		domain_add_cpu(cpu, r);
-	state->closid = 0;
-	wrmsr(MSR_IA32_PQR_ASSOC, state->rmid, 0);
+	/* The cpu is set in default rdtgroup after online. */
+	cpumask_set_cpu(cpu, &rdtgroup_default.cpu_mask);
+	clear_closid(cpu);
 	mutex_unlock(&rdtgroup_mutex);
 
 	return 0;
@@ -348,11 +359,17 @@ static int intel_rdt_online_cpu(unsigned int cpu)
 
 static int intel_rdt_offline_cpu(unsigned int cpu)
 {
+	struct rdtgroup *rdtgrp;
 	struct rdt_resource *r;
 
 	mutex_lock(&rdtgroup_mutex);
 	for_each_capable_rdt_resource(r)
 		domain_remove_cpu(cpu, r);
+	list_for_each_entry(rdtgrp, &rdt_all_groups, rdtgroup_list) {
+		if (cpumask_test_and_clear_cpu(cpu, &rdtgrp->cpu_mask))
+			break;
+	}
+	clear_closid(cpu);
 	mutex_unlock(&rdtgroup_mutex);
 
 	return 0;

arch/x86/kernel/cpu/intel_rdt_rdtgroup.c

@@ -20,6 +20,7 @@
 
 #define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
 
+#include <linux/cpu.h>
 #include <linux/fs.h>
 #include <linux/sysfs.h>
 #include <linux/kernfs.h>
@@ -172,6 +173,111 @@ static struct kernfs_ops rdtgroup_kf_single_ops = {
 	.seq_show		= rdtgroup_seqfile_show,
 };
 
+static int rdtgroup_cpus_show(struct kernfs_open_file *of,
+			      struct seq_file *s, void *v)
+{
+	struct rdtgroup *rdtgrp;
+	int ret = 0;
+
+	rdtgrp = rdtgroup_kn_lock_live(of->kn);
+
+	if (rdtgrp)
+		seq_printf(s, "%*pb\n", cpumask_pr_args(&rdtgrp->cpu_mask));
+	else
+		ret = -ENOENT;
+	rdtgroup_kn_unlock(of->kn);
+
+	return ret;
+}
+
+static ssize_t rdtgroup_cpus_write(struct kernfs_open_file *of,
+				   char *buf, size_t nbytes, loff_t off)
+{
+	cpumask_var_t tmpmask, newmask;
+	struct rdtgroup *rdtgrp, *r;
+	int ret, cpu;
+
+	if (!buf)
+		return -EINVAL;
+
+	if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL))
+		return -ENOMEM;
+	if (!zalloc_cpumask_var(&newmask, GFP_KERNEL)) {
+		free_cpumask_var(tmpmask);
+		return -ENOMEM;
+	}
+	rdtgrp = rdtgroup_kn_lock_live(of->kn);
+	if (!rdtgrp) {
+		ret = -ENOENT;
+		goto unlock;
+	}
+
+	ret = cpumask_parse(buf, newmask);
+	if (ret)
+		goto unlock;
+
+	get_online_cpus();
+	/* check that user didn't specify any offline cpus */
+	cpumask_andnot(tmpmask, newmask, cpu_online_mask);
+	if (cpumask_weight(tmpmask)) {
+		ret = -EINVAL;
+		goto end;
+	}
+
+	/* Check whether cpus are dropped from this group */
+	cpumask_andnot(tmpmask, &rdtgrp->cpu_mask, newmask);
+	if (cpumask_weight(tmpmask)) {
+		/* Can't drop from default group */
+		if (rdtgrp == &rdtgroup_default) {
+			ret = -EINVAL;
+			goto end;
+		}
+		/* Give any dropped cpus to rdtgroup_default */
+		cpumask_or(&rdtgroup_default.cpu_mask,
+			   &rdtgroup_default.cpu_mask, tmpmask);
+		for_each_cpu(cpu, tmpmask)
+			per_cpu(cpu_closid, cpu) = 0;
+	}
+
+	/*
+	 * If we added cpus, remove them from previous group that owned them
+	 * and update per-cpu closid
+	 */
+	cpumask_andnot(tmpmask, newmask, &rdtgrp->cpu_mask);
+	if (cpumask_weight(tmpmask)) {
+		list_for_each_entry(r, &rdt_all_groups, rdtgroup_list) {
+			if (r == rdtgrp)
+				continue;
+			cpumask_andnot(&r->cpu_mask, &r->cpu_mask, tmpmask);
+		}
+		for_each_cpu(cpu, tmpmask)
+			per_cpu(cpu_closid, cpu) = rdtgrp->closid;
+	}
+
+	/* Done pushing/pulling - update this group with new mask */
+	cpumask_copy(&rdtgrp->cpu_mask, newmask);
+
+end:
+	put_online_cpus();
+unlock:
+	rdtgroup_kn_unlock(of->kn);
+	free_cpumask_var(tmpmask);
+	free_cpumask_var(newmask);
+
+	return ret ?: nbytes;
+}
+
+/* Files in each rdtgroup */
+static struct rftype rdtgroup_base_files[] = {
+	{
+		.name		= "cpus",
+		.mode		= 0644,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.write		= rdtgroup_cpus_write,
+		.seq_show	= rdtgroup_cpus_show,
+	},
+};
+
 static int rdt_num_closids_show(struct kernfs_open_file *of,
 				struct seq_file *seq, void *v)
 {
@@ -582,6 +688,11 @@ static int rdtgroup_mkdir(struct kernfs_node *parent_kn, const char *name,
 	if (ret)
 		goto out_destroy;
 
+	ret = rdtgroup_add_files(kn, rdtgroup_base_files,
+				 ARRAY_SIZE(rdtgroup_base_files));
+	if (ret)
+		goto out_destroy;
+
 	kernfs_activate(kn);
 
 	ret = 0;
@@ -602,7 +713,7 @@ out_unlock:
 static int rdtgroup_rmdir(struct kernfs_node *kn)
 {
 	struct rdtgroup *rdtgrp;
-	int ret = 0;
+	int cpu, ret = 0;
 
 	rdtgrp = rdtgroup_kn_lock_live(kn);
 	if (!rdtgrp) {
@@ -610,6 +721,12 @@ static int rdtgroup_rmdir(struct kernfs_node *kn)
 		return -ENOENT;
 	}
 
+	/* Give any CPUs back to the default group */
+	cpumask_or(&rdtgroup_default.cpu_mask,
+		   &rdtgroup_default.cpu_mask, &rdtgrp->cpu_mask);
+	for_each_cpu(cpu, &rdtgrp->cpu_mask)
+		per_cpu(cpu_closid, cpu) = 0;
+
 	rdtgrp->flags = RDT_DELETED;
 	closid_free(rdtgrp->closid);
 	list_del(&rdtgrp->rdtgroup_list);
@@ -633,6 +750,8 @@ static struct kernfs_syscall_ops rdtgroup_kf_syscall_ops = {
 
 static int __init rdtgroup_setup_root(void)
 {
+	int ret;
+
 	rdt_root = kernfs_create_root(&rdtgroup_kf_syscall_ops,
 				      KERNFS_ROOT_CREATE_DEACTIVATED,
 				      &rdtgroup_default);
@@ -644,12 +763,20 @@ static int __init rdtgroup_setup_root(void)
 	rdtgroup_default.closid = 0;
 	list_add(&rdtgroup_default.rdtgroup_list, &rdt_all_groups);
 
+	ret = rdtgroup_add_files(rdt_root->kn, rdtgroup_base_files,
+				 ARRAY_SIZE(rdtgroup_base_files));
+	if (ret) {
+		kernfs_destroy_root(rdt_root);
+		goto out;
+	}
+
 	rdtgroup_default.kn = rdt_root->kn;
 	kernfs_activate(rdtgroup_default.kn);
 
+out:
 	mutex_unlock(&rdtgroup_mutex);
 
-	return 0;
+	return ret;
 }
 
 /*