bpf: introduce percpu_freelist

Introduce simple percpu_freelist to keep single list of elements
spread across per-cpu singly linked lists.

/* push element into the list */
void pcpu_freelist_push(struct pcpu_freelist *, struct pcpu_freelist_node *);

/* pop element from the list */
struct pcpu_freelist_node *pcpu_freelist_pop(struct pcpu_freelist *);

The object is pushed to the current cpu list.
Pop first trying to get the object from the current cpu list,
if it's empty goes to the neigbour cpu list.

For bpf program usage pattern the collision rate is very low,
since programs push and pop the objects typically on the same cpu.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index 8a932d079c24dbdccb87022fa3976d32dd505130..eed911d091dacebc429393e80120721fc6a8f110 100644 (file)
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -1,7 +1,7 @@
 obj-y := core.o
 
 obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o
-obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o
+obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o
 ifeq ($(CONFIG_PERF_EVENTS),y)
 obj-$(CONFIG_BPF_SYSCALL) += stackmap.o
 endif

diff --git a/kernel/bpf/percpu_freelist.c b/kernel/bpf/percpu_freelist.c
new file mode 100644 (file)
index 0000000..5c51d19
--- /dev/null
+++ b/kernel/bpf/percpu_freelist.c
@@ -0,0 +1,100 @@
+/* Copyright (c) 2016 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#include "percpu_freelist.h"
+
+int pcpu_freelist_init(struct pcpu_freelist *s)
+{
+       int cpu;
+
+       s->freelist = alloc_percpu(struct pcpu_freelist_head);
+       if (!s->freelist)
+               return -ENOMEM;
+
+       for_each_possible_cpu(cpu) {
+               struct pcpu_freelist_head *head = per_cpu_ptr(s->freelist, cpu);
+
+               raw_spin_lock_init(&head->lock);
+               head->first = NULL;
+       }
+       return 0;
+}
+
+void pcpu_freelist_destroy(struct pcpu_freelist *s)
+{
+       free_percpu(s->freelist);
+}
+
+static inline void __pcpu_freelist_push(struct pcpu_freelist_head *head,
+                                       struct pcpu_freelist_node *node)
+{
+       raw_spin_lock(&head->lock);
+       node->next = head->first;
+       head->first = node;
+       raw_spin_unlock(&head->lock);
+}
+
+void pcpu_freelist_push(struct pcpu_freelist *s,
+                       struct pcpu_freelist_node *node)
+{
+       struct pcpu_freelist_head *head = this_cpu_ptr(s->freelist);
+
+       __pcpu_freelist_push(head, node);
+}
+
+void pcpu_freelist_populate(struct pcpu_freelist *s, void *buf, u32 elem_size,
+                           u32 nr_elems)
+{
+       struct pcpu_freelist_head *head;
+       unsigned long flags;
+       int i, cpu, pcpu_entries;
+
+       pcpu_entries = nr_elems / num_possible_cpus() + 1;
+       i = 0;
+
+       /* disable irq to workaround lockdep false positive
+        * in bpf usage pcpu_freelist_populate() will never race
+        * with pcpu_freelist_push()
+        */
+       local_irq_save(flags);
+       for_each_possible_cpu(cpu) {
+again:
+               head = per_cpu_ptr(s->freelist, cpu);
+               __pcpu_freelist_push(head, buf);
+               i++;
+               buf += elem_size;
+               if (i == nr_elems)
+                       break;
+               if (i % pcpu_entries)
+                       goto again;
+       }
+       local_irq_restore(flags);
+}
+
+struct pcpu_freelist_node *pcpu_freelist_pop(struct pcpu_freelist *s)
+{
+       struct pcpu_freelist_head *head;
+       struct pcpu_freelist_node *node;
+       int orig_cpu, cpu;
+
+       orig_cpu = cpu = raw_smp_processor_id();
+       while (1) {
+               head = per_cpu_ptr(s->freelist, cpu);
+               raw_spin_lock(&head->lock);
+               node = head->first;
+               if (node) {
+                       head->first = node->next;
+                       raw_spin_unlock(&head->lock);
+                       return node;
+               }
+               raw_spin_unlock(&head->lock);
+               cpu = cpumask_next(cpu, cpu_possible_mask);
+               if (cpu >= nr_cpu_ids)
+                       cpu = 0;
+               if (cpu == orig_cpu)
+                       return NULL;
+       }
+}

diff --git a/kernel/bpf/percpu_freelist.h b/kernel/bpf/percpu_freelist.h
new file mode 100644 (file)
index 0000000..3049aae
--- /dev/null
+++ b/kernel/bpf/percpu_freelist.h
@@ -0,0 +1,31 @@
+/* Copyright (c) 2016 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#ifndef __PERCPU_FREELIST_H__
+#define __PERCPU_FREELIST_H__
+#include <linux/spinlock.h>
+#include <linux/percpu.h>
+
+struct pcpu_freelist_head {
+       struct pcpu_freelist_node *first;
+       raw_spinlock_t lock;
+};
+
+struct pcpu_freelist {
+       struct pcpu_freelist_head __percpu *freelist;
+};
+
+struct pcpu_freelist_node {
+       struct pcpu_freelist_node *next;
+};
+
+void pcpu_freelist_push(struct pcpu_freelist *, struct pcpu_freelist_node *);
+struct pcpu_freelist_node *pcpu_freelist_pop(struct pcpu_freelist *);
+void pcpu_freelist_populate(struct pcpu_freelist *s, void *buf, u32 elem_size,
+                           u32 nr_elems);
+int pcpu_freelist_init(struct pcpu_freelist *);
+void pcpu_freelist_destroy(struct pcpu_freelist *s);
+#endif