Merge branch 'bpf-map-prealloc'

Alexei Starovoitov says:

====================
bpf: map pre-alloc

v1->v2:
. fix few issues spotted by Daniel
. converted stackmap into pre-allocation as well
. added a workaround for lockdep false positive
. added pcpu_freelist_populate to be used by hashmap and stackmap

this path set switches bpf hash map to use pre-allocation by default
and introduces BPF_F_NO_PREALLOC flag to keep old behavior for cases
where full map pre-allocation is too memory expensive.

Some time back Daniel Wagner reported crashes when bpf hash map is
used to compute time intervals between preempt_disable->preempt_enable
and recently Tom Zanussi reported a dead lock in iovisor/bcc/funccount
tool if it's used to count the number of invocations of kernel
'*spin*' functions. Both problems are due to the recursive use of
slub and can only be solved by pre-allocating all map elements.

A lot of different solutions were considered. Many implemented,
but at the end pre-allocation seems to be the only feasible answer.
As far as pre-allocation goes it also was implemented 4 different ways:
- simple free-list with single lock
- percpu_ida with optimizations
- blk-mq-tag variant customized for bpf use case
- percpu_freelist
For bpf style of alloc/free patterns percpu_freelist is the best
and implemented in this patch set.
Detailed performance numbers in patch 3.
Patch 2 introduces percpu_freelist
Patch 1 fixes simple deadlocks due to missing recursion checks
Patch 5: converts stackmap to pre-allocation
Patches 6-9: prepare test infra
Patch 10: stress test for hash map infra. It attaches to spin_lock
functions and bpf_map_update/delete are called from different contexts
Patch 11: stress for bpf_get_stackid
Patch 12: map performance test
Reported-by: Daniel Wagner <daniel.wagner@bmw-carit.de>
Reported-by: Tom Zanussi <tom.zanussi@linux.intel.com>
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

include/linux/bpf.h

@@ -10,6 +10,7 @@
 #include <uapi/linux/bpf.h>
 #include <linux/workqueue.h>
 #include <linux/file.h>
+#include <linux/percpu.h>
 
 struct bpf_map;
 
@@ -36,6 +37,7 @@ struct bpf_map {
 	u32 key_size;
 	u32 value_size;
 	u32 max_entries;
+	u32 map_flags;
 	u32 pages;
 	struct user_struct *user;
 	const struct bpf_map_ops *ops;
@@ -163,6 +165,8 @@ bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *f
 const struct bpf_func_proto *bpf_get_trace_printk_proto(void);
 
 #ifdef CONFIG_BPF_SYSCALL
+DECLARE_PER_CPU(int, bpf_prog_active);
+
 void bpf_register_prog_type(struct bpf_prog_type_list *tl);
 void bpf_register_map_type(struct bpf_map_type_list *tl);
 
@@ -175,6 +179,7 @@ struct bpf_map *__bpf_map_get(struct fd f);
 void bpf_map_inc(struct bpf_map *map, bool uref);
 void bpf_map_put_with_uref(struct bpf_map *map);
 void bpf_map_put(struct bpf_map *map);
+int bpf_map_precharge_memlock(u32 pages);
 
 extern int sysctl_unprivileged_bpf_disabled;
 
@@ -190,6 +195,7 @@ int bpf_percpu_hash_update(struct bpf_map *map, void *key, void *value,
 			   u64 flags);
 int bpf_percpu_array_update(struct bpf_map *map, void *key, void *value,
 			    u64 flags);
+int bpf_stackmap_copy(struct bpf_map *map, void *key, void *value);
 
 /* memcpy that is used with 8-byte aligned pointers, power-of-8 size and
  * forced to use 'long' read/writes to try to atomically copy long counters.

include/uapi/linux/bpf.h

@@ -101,12 +101,15 @@ enum bpf_prog_type {
 #define BPF_NOEXIST	1 /* create new element if it didn't exist */
 #define BPF_EXIST	2 /* update existing element */
 
+#define BPF_F_NO_PREALLOC	(1U << 0)
+
 union bpf_attr {
 	struct { /* anonymous struct used by BPF_MAP_CREATE command */
 		__u32	map_type;	/* one of enum bpf_map_type */
 		__u32	key_size;	/* size of key in bytes */
 		__u32	value_size;	/* size of value in bytes */
 		__u32	max_entries;	/* max number of entries in a map */
+		__u32	map_flags;	/* prealloc or not */
 	};
 
 	struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */

kernel/bpf/Makefile

 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

kernel/bpf/arraymap.c

@@ -53,7 +53,7 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
 
 	/* check sanity of attributes */
 	if (attr->max_entries == 0 || attr->key_size != 4 ||
-	    attr->value_size == 0)
+	    attr->value_size == 0 || attr->map_flags)
 		return ERR_PTR(-EINVAL);
 
 	if (attr->value_size >= 1 << (KMALLOC_SHIFT_MAX - 1))

kernel/bpf/percpu_freelist.c

+/* 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;
+	}
+}

kernel/bpf/percpu_freelist.h

+/* 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

kernel/bpf/stackmap.c

@@ -10,9 +10,10 @@
 #include <linux/vmalloc.h>
 #include <linux/stacktrace.h>
 #include <linux/perf_event.h>
+#include "percpu_freelist.h"
 
 struct stack_map_bucket {
-	struct rcu_head rcu;
+	struct pcpu_freelist_node fnode;
 	u32 hash;
 	u32 nr;
 	u64 ip[];
@@ -20,10 +21,34 @@ struct stack_map_bucket {
 
 struct bpf_stack_map {
 	struct bpf_map map;
+	void *elems;
+	struct pcpu_freelist freelist;
 	u32 n_buckets;
-	struct stack_map_bucket __rcu *buckets[];
+	struct stack_map_bucket *buckets[];
 };
 
+static int prealloc_elems_and_freelist(struct bpf_stack_map *smap)
+{
+	u32 elem_size = sizeof(struct stack_map_bucket) + smap->map.value_size;
+	int err;
+
+	smap->elems = vzalloc(elem_size * smap->map.max_entries);
+	if (!smap->elems)
+		return -ENOMEM;
+
+	err = pcpu_freelist_init(&smap->freelist);
+	if (err)
+		goto free_elems;
+
+	pcpu_freelist_populate(&smap->freelist, smap->elems, elem_size,
+			       smap->map.max_entries);
+	return 0;
+
+free_elems:
+	vfree(smap->elems);
+	return err;
+}
+
 /* Called from syscall */
 static struct bpf_map *stack_map_alloc(union bpf_attr *attr)
 {
@@ -35,6 +60,9 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr)
 	if (!capable(CAP_SYS_ADMIN))
 		return ERR_PTR(-EPERM);
 
+	if (attr->map_flags)
+		return ERR_PTR(-EINVAL);
+
 	/* check sanity of attributes */
 	if (attr->max_entries == 0 || attr->key_size != 4 ||
 	    value_size < 8 || value_size % 8 ||
@@ -67,12 +95,22 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr)
 	smap->n_buckets = n_buckets;
 	smap->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT;
 
+	err = bpf_map_precharge_memlock(smap->map.pages);
+	if (err)
+		goto free_smap;
+
 	err = get_callchain_buffers();
 	if (err)
 		goto free_smap;
 
+	err = prealloc_elems_and_freelist(smap);
+	if (err)
+		goto put_buffers;
+
 	return &smap->map;
 
+put_buffers:
+	put_callchain_buffers();
 free_smap:
 	kvfree(smap);
 	return ERR_PTR(err);
@@ -118,7 +156,7 @@ static u64 bpf_get_stackid(u64 r1, u64 r2, u64 flags, u64 r4, u64 r5)
 	ips = trace->ip + skip + init_nr;
 	hash = jhash2((u32 *)ips, trace_len / sizeof(u32), 0);
 	id = hash & (smap->n_buckets - 1);
-	bucket = rcu_dereference(smap->buckets[id]);
+	bucket = READ_ONCE(smap->buckets[id]);
 
 	if (bucket && bucket->hash == hash) {
 		if (flags & BPF_F_FAST_STACK_CMP)
@@ -132,19 +170,18 @@ static u64 bpf_get_stackid(u64 r1, u64 r2, u64 flags, u64 r4, u64 r5)
 	if (bucket && !(flags & BPF_F_REUSE_STACKID))
 		return -EEXIST;
 
-	new_bucket = kmalloc(sizeof(struct stack_map_bucket) + map->value_size,
-			     GFP_ATOMIC | __GFP_NOWARN);
+	new_bucket = (struct stack_map_bucket *)
+		pcpu_freelist_pop(&smap->freelist);
 	if (unlikely(!new_bucket))
 		return -ENOMEM;
 
 	memcpy(new_bucket->ip, ips, trace_len);
-	memset(new_bucket->ip + trace_len / 8, 0, map->value_size - trace_len);
 	new_bucket->hash = hash;
 	new_bucket->nr = trace_nr;
 
 	old_bucket = xchg(&smap->buckets[id], new_bucket);
 	if (old_bucket)
-		kfree_rcu(old_bucket, rcu);
+		pcpu_freelist_push(&smap->freelist, &old_bucket->fnode);
 	return id;
 }
 
@@ -157,17 +194,34 @@ const struct bpf_func_proto bpf_get_stackid_proto = {
 	.arg3_type	= ARG_ANYTHING,
 };
 
-/* Called from syscall or from eBPF program */
+/* Called from eBPF program */
 static void *stack_map_lookup_elem(struct bpf_map *map, void *key)
+{
+	return NULL;
+}
+
+/* Called from syscall */
+int bpf_stackmap_copy(struct bpf_map *map, void *key, void *value)
 {
 	struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map);
-	struct stack_map_bucket *bucket;
-	u32 id = *(u32 *)key;
+	struct stack_map_bucket *bucket, *old_bucket;
+	u32 id = *(u32 *)key, trace_len;
 
 	if (unlikely(id >= smap->n_buckets))
-		return NULL;
-	bucket = rcu_dereference(smap->buckets[id]);
-	return bucket ? bucket->ip : NULL;
+		return -ENOENT;
+
+	bucket = xchg(&smap->buckets[id], NULL);
+	if (!bucket)
+		return -ENOENT;
+
+	trace_len = bucket->nr * sizeof(u64);
+	memcpy(value, bucket->ip, trace_len);
+	memset(value + trace_len, 0, map->value_size - trace_len);
+
+	old_bucket = xchg(&smap->buckets[id], bucket);
+	if (old_bucket)
+		pcpu_freelist_push(&smap->freelist, &old_bucket->fnode);
+	return 0;
 }
 
 static int stack_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
@@ -193,7 +247,7 @@ static int stack_map_delete_elem(struct bpf_map *map, void *key)
 
 	old_bucket = xchg(&smap->buckets[id], NULL);
 	if (old_bucket) {
-		kfree_rcu(old_bucket, rcu);
+		pcpu_freelist_push(&smap->freelist, &old_bucket->fnode);
 		return 0;
 	} else {
 		return -ENOENT;
@@ -204,13 +258,12 @@ static int stack_map_delete_elem(struct bpf_map *map, void *key)
 static void stack_map_free(struct bpf_map *map)
 {
 	struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map);
-	int i;
 
+	/* wait for bpf programs to complete before freeing stack map */
 	synchronize_rcu();
 
-	for (i = 0; i < smap->n_buckets; i++)
-		if (smap->buckets[i])
-			kfree_rcu(smap->buckets[i], rcu);
+	vfree(smap->elems);
+	pcpu_freelist_destroy(&smap->freelist);
 	kvfree(smap);
 	put_callchain_buffers();
 }

kernel/bpf/syscall.c

@@ -18,6 +18,8 @@
 #include <linux/filter.h>
 #include <linux/version.h>
 
+DEFINE_PER_CPU(int, bpf_prog_active);
+
 int sysctl_unprivileged_bpf_disabled __read_mostly;
 
 static LIST_HEAD(bpf_map_types);
@@ -46,6 +48,19 @@ void bpf_register_map_type(struct bpf_map_type_list *tl)
 	list_add(&tl->list_node, &bpf_map_types);
 }
 
+int bpf_map_precharge_memlock(u32 pages)
+{
+	struct user_struct *user = get_current_user();
+	unsigned long memlock_limit, cur;
+
+	memlock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
+	cur = atomic_long_read(&user->locked_vm);
+	free_uid(user);
+	if (cur + pages > memlock_limit)
+		return -EPERM;
+	return 0;
+}
+
 static int bpf_map_charge_memlock(struct bpf_map *map)
 {
 	struct user_struct *user = get_current_user();
@@ -151,7 +166,7 @@ int bpf_map_new_fd(struct bpf_map *map)
 		   offsetof(union bpf_attr, CMD##_LAST_FIELD) - \
 		   sizeof(attr->CMD##_LAST_FIELD)) != NULL
 
-#define BPF_MAP_CREATE_LAST_FIELD max_entries
+#define BPF_MAP_CREATE_LAST_FIELD map_flags
 /* called via syscall */
 static int map_create(union bpf_attr *attr)
 {
@@ -275,6 +290,8 @@ static int map_lookup_elem(union bpf_attr *attr)
 		err = bpf_percpu_hash_copy(map, key, value);
 	} else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) {
 		err = bpf_percpu_array_copy(map, key, value);
+	} else if (map->map_type == BPF_MAP_TYPE_STACK_TRACE) {
+		err = bpf_stackmap_copy(map, key, value);
 	} else {
 		rcu_read_lock();
 		ptr = map->ops->map_lookup_elem(map, key);
@@ -347,6 +364,11 @@ static int map_update_elem(union bpf_attr *attr)
 	if (copy_from_user(value, uvalue, value_size) != 0)
 		goto free_value;
 
+	/* must increment bpf_prog_active to avoid kprobe+bpf triggering from
+	 * inside bpf map update or delete otherwise deadlocks are possible
+	 */
+	preempt_disable();
+	__this_cpu_inc(bpf_prog_active);
 	if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH) {
 		err = bpf_percpu_hash_update(map, key, value, attr->flags);
 	} else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) {
@@ -356,6 +378,8 @@ static int map_update_elem(union bpf_attr *attr)
 		err = map->ops->map_update_elem(map, key, value, attr->flags);
 		rcu_read_unlock();
 	}
+	__this_cpu_dec(bpf_prog_active);
+	preempt_enable();
 
 free_value:
 	kfree(value);
@@ -394,9 +418,13 @@ static int map_delete_elem(union bpf_attr *attr)
 	if (copy_from_user(key, ukey, map->key_size) != 0)
 		goto free_key;
 
+	preempt_disable();
+	__this_cpu_inc(bpf_prog_active);
 	rcu_read_lock();
 	err = map->ops->map_delete_elem(map, key);
 	rcu_read_unlock();
+	__this_cpu_dec(bpf_prog_active);
+	preempt_enable();
 
 free_key:
 	kfree(key);

kernel/trace/bpf_trace.c

@@ -13,8 +13,6 @@
 #include <linux/ctype.h>
 #include "trace.h"
 
-static DEFINE_PER_CPU(int, bpf_prog_active);
-
 /**
  * trace_call_bpf - invoke BPF program
  * @prog: BPF program

samples/bpf/bpf_helpers.h

@@ -61,6 +61,7 @@ struct bpf_map_def {
 	unsigned int key_size;
 	unsigned int value_size;
 	unsigned int max_entries;
+	unsigned int map_flags;
 };
 
 static int (*bpf_skb_store_bytes)(void *ctx, int off, void *from, int len, int flags) =

samples/bpf/bpf_load.c

@@ -157,9 +157,13 @@ static int load_maps(struct bpf_map_def *maps, int len)
 		map_fd[i] = bpf_create_map(maps[i].type,
 					   maps[i].key_size,
 					   maps[i].value_size,
-					   maps[i].max_entries);
-		if (map_fd[i] < 0)
+					   maps[i].max_entries,
+					   maps[i].map_flags);
+		if (map_fd[i] < 0) {
+			printf("failed to create a map: %d %s\n",
+			       errno, strerror(errno));
 			return 1;
+		}
 
 		if (maps[i].type == BPF_MAP_TYPE_PROG_ARRAY)
 			prog_array_fd = map_fd[i];
@@ -343,3 +347,65 @@ void read_trace_pipe(void)
 		}
 	}
 }
+
+#define MAX_SYMS 300000
+static struct ksym syms[MAX_SYMS];
+static int sym_cnt;
+
+static int ksym_cmp(const void *p1, const void *p2)
+{
+	return ((struct ksym *)p1)->addr - ((struct ksym *)p2)->addr;
+}
+
+int load_kallsyms(void)
+{
+	FILE *f = fopen("/proc/kallsyms", "r");
+	char func[256], buf[256];
+	char symbol;
+	void *addr;
+	int i = 0;
+
+	if (!f)
+		return -ENOENT;
+
+	while (!feof(f)) {
+		if (!fgets(buf, sizeof(buf), f))
+			break;
+		if (sscanf(buf, "%p %c %s", &addr, &symbol, func) != 3)
+			break;
+		if (!addr)
+			continue;
+		syms[i].addr = (long) addr;
+		syms[i].name = strdup(func);
+		i++;
+	}
+	sym_cnt = i;
+	qsort(syms, sym_cnt, sizeof(struct ksym), ksym_cmp);
+	return 0;
+}
+
+struct ksym *ksym_search(long key)
+{
+	int start = 0, end = sym_cnt;
+	int result;
+
+	while (start < end) {
+		size_t mid = start + (end - start) / 2;
+
+		result = key - syms[mid].addr;
+		if (result < 0)
+			end = mid;
+		else if (result > 0)
+			start = mid + 1;
+		else
+			return &syms[mid];
+	}
+
+	if (start >= 1 && syms[start - 1].addr < key &&
+	    key < syms[start].addr)
+		/* valid ksym */
+		return &syms[start - 1];
+
+	/* out of range. return _stext */
+	return &syms[0];
+}

samples/bpf/bpf_load.h

@@ -23,5 +23,11 @@ extern int event_fd[MAX_PROGS];
 int load_bpf_file(char *path);
 
 void read_trace_pipe(void);
+struct ksym {
+	long addr;
+	char *name;
+};
 
+int load_kallsyms(void);
+struct ksym *ksym_search(long key);
 #endif

samples/bpf/fds_example.c

@@ -44,7 +44,7 @@ static void usage(void)
 static int bpf_map_create(void)
 {
 	return bpf_create_map(BPF_MAP_TYPE_ARRAY, sizeof(uint32_t),
-			      sizeof(uint32_t), 1024);
+			      sizeof(uint32_t), 1024, 0);
 }
 
 static int bpf_prog_create(const char *object)

samples/bpf/libbpf.c

@@ -19,13 +19,14 @@ static __u64 ptr_to_u64(void *ptr)
 }
 
 int bpf_create_map(enum bpf_map_type map_type, int key_size, int value_size,
-		   int max_entries)
+		   int max_entries, int map_flags)
 {
 	union bpf_attr attr = {
 		.map_type = map_type,
 		.key_size = key_size,
 		.value_size = value_size,
-		.max_entries = max_entries
+		.max_entries = max_entries,
+		.map_flags = map_flags,
 	};
 
 	return syscall(__NR_bpf, BPF_MAP_CREATE, &attr, sizeof(attr));

samples/bpf/libbpf.h

@@ -5,7 +5,7 @@
 struct bpf_insn;
 
 int bpf_create_map(enum bpf_map_type map_type, int key_size, int value_size,
-		   int max_entries);
+		   int max_entries, int map_flags);
 int bpf_update_elem(int fd, void *key, void *value, unsigned long long flags);
 int bpf_lookup_elem(int fd, void *key, void *value);
 int bpf_delete_elem(int fd, void *key);

samples/bpf/offwaketime_user.c

@@ -18,80 +18,15 @@
 #include "libbpf.h"
 #include "bpf_load.h"
 
-#define MAX_SYMS 300000
 #define PRINT_RAW_ADDR 0
 
-static struct ksym {
-	long addr;
-	char *name;
-} syms[MAX_SYMS];
-static int sym_cnt;
-
-static int ksym_cmp(const void *p1, const void *p2)
-{
-	return ((struct ksym *)p1)->addr - ((struct ksym *)p2)->addr;
-}
-
-static int load_kallsyms(void)
-{
-	FILE *f = fopen("/proc/kallsyms", "r");
-	char func[256], buf[256];
-	char symbol;
-	void *addr;
-	int i = 0;
-
-	if (!f)
-		return -ENOENT;
-
-	while (!feof(f)) {
-		if (!fgets(buf, sizeof(buf), f))
-			break;
-		if (sscanf(buf, "%p %c %s", &addr, &symbol, func) != 3)
-			break;
-		if (!addr)
-			continue;
-		syms[i].addr = (long) addr;
-		syms[i].name = strdup(func);
-		i++;
-	}
-	sym_cnt = i;
-	qsort(syms, sym_cnt, sizeof(struct ksym), ksym_cmp);
-	return 0;
-}
-
-static void *search(long key)
-{
-	int start = 0, end = sym_cnt;
-	int result;
-
-	while (start < end) {
-		size_t mid = start + (end - start) / 2;
-
-		result = key - syms[mid].addr;
-		if (result < 0)
-			end = mid;
-		else if (result > 0)
-			start = mid + 1;
-		else
-			return &syms[mid];
-	}
-
-	if (start >= 1 && syms[start - 1].addr < key &&
-	    key < syms[start].addr)
-		/* valid ksym */
-		return &syms[start - 1];
-
-	/* out of range. return _stext */
-	return &syms[0];
-}
-
 static void print_ksym(__u64 addr)
 {
 	struct ksym *sym;
 
 	if (!addr)
 		return;
-	sym = search(addr);
+	sym = ksym_search(addr);
 	if (PRINT_RAW_ADDR)
 		printf("%s/%llx;", sym->name, addr);
 	else

samples/bpf/sock_example.c

@@ -34,7 +34,7 @@ static int test_sock(void)
 	long long value = 0, tcp_cnt, udp_cnt, icmp_cnt;
 
 	map_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, sizeof(key), sizeof(value),
-				256);
+				256, 0);
 	if (map_fd < 0) {
 		printf("failed to create map '%s'\n", strerror(errno));
 		goto cleanup;

samples/bpf/test_maps.c

@@ -2,6 +2,7 @@
  * Testsuite for eBPF maps
  *
  * Copyright (c) 2014 PLUMgrid, http://plumgrid.com
+ * 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
@@ -17,13 +18,16 @@
 #include <stdlib.h>
 #include "libbpf.h"
 
+static int map_flags;
+
 /* sanity tests for map API */
 static void test_hashmap_sanity(int i, void *data)
 {
 	long long key, next_key, value;
 	int map_fd;
 
-	map_fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value), 2);
+	map_fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value),
+				2, map_flags);
 	if (map_fd < 0) {
 		printf("failed to create hashmap '%s'\n", strerror(errno));
 		exit(1);
@@ -99,7 +103,7 @@ static void test_percpu_hashmap_sanity(int task, void *data)
 	int map_fd, i;
 
 	map_fd = bpf_create_map(BPF_MAP_TYPE_PERCPU_HASH, sizeof(key),
-				sizeof(value[0]), 2);
+				sizeof(value[0]), 2, map_flags);
 	if (map_fd < 0) {
 		printf("failed to create hashmap '%s'\n", strerror(errno));
 		exit(1);
@@ -188,7 +192,8 @@ static void test_arraymap_sanity(int i, void *data)
 	int key, next_key, map_fd;
 	long long value;
 
-	map_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, sizeof(key), sizeof(value), 2);
+	map_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, sizeof(key), sizeof(value),
+				2, 0);
 	if (map_fd < 0) {
 		printf("failed to create arraymap '%s'\n", strerror(errno));
 		exit(1);
@@ -244,7 +249,7 @@ static void test_percpu_arraymap_many_keys(void)
 	int key, map_fd, i;
 
 	map_fd = bpf_create_map(BPF_MAP_TYPE_PERCPU_ARRAY, sizeof(key),
-				sizeof(values[0]), nr_keys);
+				sizeof(values[0]), nr_keys, 0);
 	if (map_fd < 0) {
 		printf("failed to create per-cpu arraymap '%s'\n",
 		       strerror(errno));
@@ -275,7 +280,7 @@ static void test_percpu_arraymap_sanity(int i, void *data)
 	int key, next_key, map_fd;
 
 	map_fd = bpf_create_map(BPF_MAP_TYPE_PERCPU_ARRAY, sizeof(key),
-				sizeof(values[0]), 2);
+				sizeof(values[0]), 2, 0);
 	if (map_fd < 0) {
 		printf("failed to create arraymap '%s'\n", strerror(errno));
 		exit(1);
@@ -336,7 +341,7 @@ static void test_map_large(void)
 
 	/* allocate 4Mbyte of memory */
 	map_fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value),
-				MAP_SIZE);
+				MAP_SIZE, map_flags);
 	if (map_fd < 0) {
 		printf("failed to create large map '%s'\n", strerror(errno));
 		exit(1);
@@ -421,7 +426,7 @@ static void test_map_parallel(void)
 	int data[2];
 
 	map_fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value),
-				MAP_SIZE);
+				MAP_SIZE, map_flags);
 	if (map_fd < 0) {
 		printf("failed to create map for parallel test '%s'\n",
 		       strerror(errno));
@@ -463,7 +468,7 @@ static void test_map_parallel(void)
 	assert(bpf_get_next_key(map_fd, &key, &key) == -1 && errno == ENOENT);
 }
 
-int main(void)
+static void run_all_tests(void)
 {
 	test_hashmap_sanity(0, NULL);
 	test_percpu_hashmap_sanity(0, NULL);
@@ -474,6 +479,14 @@ int main(void)
 	test_map_large();
 	test_map_parallel();
 	test_map_stress();
+}
+
+int main(void)
+{
+	map_flags = 0;
+	run_all_tests();
+	map_flags = BPF_F_NO_PREALLOC;
+	run_all_tests();
 	printf("test_maps: OK\n");
 	return 0;
 }

samples/bpf/test_verifier.c

@@ -1198,7 +1198,7 @@ static int create_map(void)
 	int map_fd;
 
 	map_fd = bpf_create_map(BPF_MAP_TYPE_HASH,
-				sizeof(long long), sizeof(long long), 1024);
+				sizeof(long long), sizeof(long long), 1024, 0);
 	if (map_fd < 0)
 		printf("failed to create map '%s'\n", strerror(errno));
 
@@ -1210,7 +1210,7 @@ static int create_prog_array(void)
 	int map_fd;
 
 	map_fd = bpf_create_map(BPF_MAP_TYPE_PROG_ARRAY,
-				sizeof(int), sizeof(int), 4);
+				sizeof(int), sizeof(int), 4, 0);
 	if (map_fd < 0)
 		printf("failed to create prog_array '%s'\n", strerror(errno));