1 files changed, 402 insertions, 56 deletions

diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index c5b30fd8a..fff3650d5 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -1,4 +1,5 @@
 /* Copyright (c) 2011-2014 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
@@ -13,6 +14,7 @@
 #include <linux/jhash.h>
 #include <linux/filter.h>
 #include <linux/vmalloc.h>
+#include "percpu_freelist.h"
 
 struct bucket {
 	struct hlist_head head;
@@ -22,6 +24,8 @@ struct bucket {
 struct bpf_htab {
 	struct bpf_map map;
 	struct bucket *buckets;
+	void *elems;
+	struct pcpu_freelist freelist;
 	atomic_t count;	/* number of elements in this hashtable */
 	u32 n_buckets;	/* number of hash buckets */
 	u32 elem_size;	/* size of each element in bytes */
@@ -29,26 +33,108 @@ struct bpf_htab {
 
 /* each htab element is struct htab_elem + key + value */
 struct htab_elem {
-	struct hlist_node hash_node;
+	union {
+		struct hlist_node hash_node;
+		struct bpf_htab *htab;
+		struct pcpu_freelist_node fnode;
+	};
 	struct rcu_head rcu;
 	u32 hash;
 	char key[0] __aligned(8);
 };
 
+static inline void htab_elem_set_ptr(struct htab_elem *l, u32 key_size,
+				     void __percpu *pptr)
+{
+	*(void __percpu **)(l->key + key_size) = pptr;
+}
+
+static inline void __percpu *htab_elem_get_ptr(struct htab_elem *l, u32 key_size)
+{
+	return *(void __percpu **)(l->key + key_size);
+}
+
+static struct htab_elem *get_htab_elem(struct bpf_htab *htab, int i)
+{
+	return (struct htab_elem *) (htab->elems + i * htab->elem_size);
+}
+
+static void htab_free_elems(struct bpf_htab *htab)
+{
+	int i;
+
+	if (htab->map.map_type != BPF_MAP_TYPE_PERCPU_HASH)
+		goto free_elems;
+
+	for (i = 0; i < htab->map.max_entries; i++) {
+		void __percpu *pptr;
+
+		pptr = htab_elem_get_ptr(get_htab_elem(htab, i),
+					 htab->map.key_size);
+		free_percpu(pptr);
+	}
+free_elems:
+	vfree(htab->elems);
+}
+
+static int prealloc_elems_and_freelist(struct bpf_htab *htab)
+{
+	int err = -ENOMEM, i;
+
+	htab->elems = vzalloc(htab->elem_size * htab->map.max_entries);
+	if (!htab->elems)
+		return -ENOMEM;
+
+	if (htab->map.map_type != BPF_MAP_TYPE_PERCPU_HASH)
+		goto skip_percpu_elems;
+
+	for (i = 0; i < htab->map.max_entries; i++) {
+		u32 size = round_up(htab->map.value_size, 8);
+		void __percpu *pptr;
+
+		pptr = __alloc_percpu_gfp(size, 8, GFP_USER | __GFP_NOWARN);
+		if (!pptr)
+			goto free_elems;
+		htab_elem_set_ptr(get_htab_elem(htab, i), htab->map.key_size,
+				  pptr);
+	}
+
+skip_percpu_elems:
+	err = pcpu_freelist_init(&htab->freelist);
+	if (err)
+		goto free_elems;
+
+	pcpu_freelist_populate(&htab->freelist, htab->elems, htab->elem_size,
+			       htab->map.max_entries);
+	return 0;
+
+free_elems:
+	htab_free_elems(htab);
+	return err;
+}
+
 /* Called from syscall */
 static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
 {
+	bool percpu = attr->map_type == BPF_MAP_TYPE_PERCPU_HASH;
 	struct bpf_htab *htab;
 	int err, i;
+	u64 cost;
+
+	if (attr->map_flags & ~BPF_F_NO_PREALLOC)
+		/* reserved bits should not be used */
+		return ERR_PTR(-EINVAL);
 
 	htab = kzalloc(sizeof(*htab), GFP_USER);
 	if (!htab)
 		return ERR_PTR(-ENOMEM);
 
 	/* mandatory map attributes */
+	htab->map.map_type = attr->map_type;
 	htab->map.key_size = attr->key_size;
 	htab->map.value_size = attr->value_size;
 	htab->map.max_entries = attr->max_entries;
+	htab->map.map_flags = attr->map_flags;
 
 	/* check sanity of attributes.
 	 * value_size == 0 may be allowed in the future to use map as a set
@@ -77,24 +163,39 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
 		 */
 		goto free_htab;
 
+	if (percpu && round_up(htab->map.value_size, 8) > PCPU_MIN_UNIT_SIZE)
+		/* make sure the size for pcpu_alloc() is reasonable */
+		goto free_htab;
+
 	htab->elem_size = sizeof(struct htab_elem) +
-			  round_up(htab->map.key_size, 8) +
-			  htab->map.value_size;
+			  round_up(htab->map.key_size, 8);
+	if (percpu)
+		htab->elem_size += sizeof(void *);
+	else
+		htab->elem_size += round_up(htab->map.value_size, 8);
 
 	/* prevent zero size kmalloc and check for u32 overflow */
 	if (htab->n_buckets == 0 ||
 	    htab->n_buckets > U32_MAX / sizeof(struct bucket))
 		goto free_htab;
 
-	if ((u64) htab->n_buckets * sizeof(struct bucket) +
-	    (u64) htab->elem_size * htab->map.max_entries >=
-	    U32_MAX - PAGE_SIZE)
+	cost = (u64) htab->n_buckets * sizeof(struct bucket) +
+	       (u64) htab->elem_size * htab->map.max_entries;
+
+	if (percpu)
+		cost += (u64) round_up(htab->map.value_size, 8) *
+			num_possible_cpus() * htab->map.max_entries;
+
+	if (cost >= U32_MAX - PAGE_SIZE)
 		/* make sure page count doesn't overflow */
 		goto free_htab;
 
-	htab->map.pages = round_up(htab->n_buckets * sizeof(struct bucket) +
-				   htab->elem_size * htab->map.max_entries,
-				   PAGE_SIZE) >> PAGE_SHIFT;
+	htab->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT;
+
+	/* if map size is larger than memlock limit, reject it early */
+	err = bpf_map_precharge_memlock(htab->map.pages);
+	if (err)
+		goto free_htab;
 
 	err = -ENOMEM;
 	htab->buckets = kmalloc_array(htab->n_buckets, sizeof(struct bucket),
@@ -111,10 +212,16 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
 		raw_spin_lock_init(&htab->buckets[i].lock);
 	}
 
-	atomic_set(&htab->count, 0);
+	if (!(attr->map_flags & BPF_F_NO_PREALLOC)) {
+		err = prealloc_elems_and_freelist(htab);
+		if (err)
+			goto free_buckets;
+	}
 
 	return &htab->map;
 
+free_buckets:
+	kvfree(htab->buckets);
 free_htab:
 	kfree(htab);
 	return ERR_PTR(err);
@@ -148,7 +255,7 @@ static struct htab_elem *lookup_elem_raw(struct hlist_head *head, u32 hash,
 }
 
 /* Called from syscall or from eBPF program */
-static void *htab_map_lookup_elem(struct bpf_map *map, void *key)
+static void *__htab_map_lookup_elem(struct bpf_map *map, void *key)
 {
 	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
 	struct hlist_head *head;
@@ -166,6 +273,13 @@ static void *htab_map_lookup_elem(struct bpf_map *map, void *key)
 
 	l = lookup_elem_raw(head, hash, key, key_size);
 
+	return l;
+}
+
+static void *htab_map_lookup_elem(struct bpf_map *map, void *key)
+{
+	struct htab_elem *l = __htab_map_lookup_elem(map, key);
+
 	if (l)
 		return l->key + round_up(map->key_size, 8);
 
@@ -226,86 +340,248 @@ find_first_elem:
 		}
 	}
 
-	/* itereated over all buckets and all elements */
+	/* iterated over all buckets and all elements */
 	return -ENOENT;
 }
 
+static void htab_elem_free(struct bpf_htab *htab, struct htab_elem *l)
+{
+	if (htab->map.map_type == BPF_MAP_TYPE_PERCPU_HASH)
+		free_percpu(htab_elem_get_ptr(l, htab->map.key_size));
+	kfree(l);
+
+}
+
+static void htab_elem_free_rcu(struct rcu_head *head)
+{
+	struct htab_elem *l = container_of(head, struct htab_elem, rcu);
+	struct bpf_htab *htab = l->htab;
+
+	/* must increment bpf_prog_active to avoid kprobe+bpf triggering while
+	 * we're calling kfree, otherwise deadlock is possible if kprobes
+	 * are placed somewhere inside of slub
+	 */
+	preempt_disable();
+	__this_cpu_inc(bpf_prog_active);
+	htab_elem_free(htab, l);
+	__this_cpu_dec(bpf_prog_active);
+	preempt_enable();
+}
+
+static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l)
+{
+	if (!(htab->map.map_flags & BPF_F_NO_PREALLOC)) {
+		pcpu_freelist_push(&htab->freelist, &l->fnode);
+	} else {
+		atomic_dec(&htab->count);
+		l->htab = htab;
+		call_rcu(&l->rcu, htab_elem_free_rcu);
+	}
+}
+
+static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
+					 void *value, u32 key_size, u32 hash,
+					 bool percpu, bool onallcpus)
+{
+	u32 size = htab->map.value_size;
+	bool prealloc = !(htab->map.map_flags & BPF_F_NO_PREALLOC);
+	struct htab_elem *l_new;
+	void __percpu *pptr;
+
+	if (prealloc) {
+		l_new = (struct htab_elem *)pcpu_freelist_pop(&htab->freelist);
+		if (!l_new)
+			return ERR_PTR(-E2BIG);
+	} else {
+		if (atomic_inc_return(&htab->count) > htab->map.max_entries) {
+			atomic_dec(&htab->count);
+			return ERR_PTR(-E2BIG);
+		}
+		l_new = kmalloc(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN);
+		if (!l_new)
+			return ERR_PTR(-ENOMEM);
+	}
+
+	memcpy(l_new->key, key, key_size);
+	if (percpu) {
+		/* round up value_size to 8 bytes */
+		size = round_up(size, 8);
+
+		if (prealloc) {
+			pptr = htab_elem_get_ptr(l_new, key_size);
+		} else {
+			/* alloc_percpu zero-fills */
+			pptr = __alloc_percpu_gfp(size, 8,
+						  GFP_ATOMIC | __GFP_NOWARN);
+			if (!pptr) {
+				kfree(l_new);
+				return ERR_PTR(-ENOMEM);
+			}
+		}
+
+		if (!onallcpus) {
+			/* copy true value_size bytes */
+			memcpy(this_cpu_ptr(pptr), value, htab->map.value_size);
+		} else {
+			int off = 0, cpu;
+
+			for_each_possible_cpu(cpu) {
+				bpf_long_memcpy(per_cpu_ptr(pptr, cpu),
+						value + off, size);
+				off += size;
+			}
+		}
+		if (!prealloc)
+			htab_elem_set_ptr(l_new, key_size, pptr);
+	} else {
+		memcpy(l_new->key + round_up(key_size, 8), value, size);
+	}
+
+	l_new->hash = hash;
+	return l_new;
+}
+
+static int check_flags(struct bpf_htab *htab, struct htab_elem *l_old,
+		       u64 map_flags)
+{
+	if (l_old && map_flags == BPF_NOEXIST)
+		/* elem already exists */
+		return -EEXIST;
+
+	if (!l_old && map_flags == BPF_EXIST)
+		/* elem doesn't exist, cannot update it */
+		return -ENOENT;
+
+	return 0;
+}
+
 /* Called from syscall or from eBPF program */
 static int htab_map_update_elem(struct bpf_map *map, void *key, void *value,
 				u64 map_flags)
 {
 	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
-	struct htab_elem *l_new, *l_old;
+	struct htab_elem *l_new = NULL, *l_old;
 	struct hlist_head *head;
-	struct bucket *b;
 	unsigned long flags;
-	u32 key_size;
+	struct bucket *b;
+	u32 key_size, hash;
 	int ret;
 
-	if (map_flags > BPF_EXIST)
+	if (unlikely(map_flags > BPF_EXIST))
 		/* unknown flags */
 		return -EINVAL;
 
 	WARN_ON_ONCE(!rcu_read_lock_held());
 
-	/* allocate new element outside of lock */
-	l_new = kmalloc(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN);
-	if (!l_new)
-		return -ENOMEM;
-
 	key_size = map->key_size;
 
-	memcpy(l_new->key, key, key_size);
-	memcpy(l_new->key + round_up(key_size, 8), value, map->value_size);
+	hash = htab_map_hash(key, key_size);
 
-	l_new->hash = htab_map_hash(l_new->key, key_size);
-	b = __select_bucket(htab, l_new->hash);
+	b = __select_bucket(htab, hash);
 	head = &b->head;
 
 	/* bpf_map_update_elem() can be called in_irq() */
 	raw_spin_lock_irqsave(&b->lock, flags);
 
-	l_old = lookup_elem_raw(head, l_new->hash, key, key_size);
+	l_old = lookup_elem_raw(head, hash, key, key_size);
 
-	if (!l_old && unlikely(atomic_read(&htab->count) >= map->max_entries)) {
-		/* if elem with this 'key' doesn't exist and we've reached
-		 * max_entries limit, fail insertion of new elem
-		 */
-		ret = -E2BIG;
+	ret = check_flags(htab, l_old, map_flags);
+	if (ret)
 		goto err;
-	}
 
-	if (l_old && map_flags == BPF_NOEXIST) {
-		/* elem already exists */
-		ret = -EEXIST;
+	l_new = alloc_htab_elem(htab, key, value, key_size, hash, false, false);
+	if (IS_ERR(l_new)) {
+		/* all pre-allocated elements are in use or memory exhausted */
+		ret = PTR_ERR(l_new);
 		goto err;
 	}
 
-	if (!l_old && map_flags == BPF_EXIST) {
-		/* elem doesn't exist, cannot update it */
-		ret = -ENOENT;
-		goto err;
-	}
-
-	/* add new element to the head of the list, so that concurrent
-	 * search will find it before old elem
+	/* add new element to the head of the list, so that
+	 * concurrent search will find it before old elem
 	 */
 	hlist_add_head_rcu(&l_new->hash_node, head);
 	if (l_old) {
 		hlist_del_rcu(&l_old->hash_node);
-		kfree_rcu(l_old, rcu);
-	} else {
-		atomic_inc(&htab->count);
+		free_htab_elem(htab, l_old);
 	}
+	ret = 0;
+err:
 	raw_spin_unlock_irqrestore(&b->lock, flags);
+	return ret;
+}
 
-	return 0;
+static int __htab_percpu_map_update_elem(struct bpf_map *map, void *key,
+					 void *value, u64 map_flags,
+					 bool onallcpus)
+{
+	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+	struct htab_elem *l_new = NULL, *l_old;
+	struct hlist_head *head;
+	unsigned long flags;
+	struct bucket *b;
+	u32 key_size, hash;
+	int ret;
+
+	if (unlikely(map_flags > BPF_EXIST))
+		/* unknown flags */
+		return -EINVAL;
+
+	WARN_ON_ONCE(!rcu_read_lock_held());
+
+	key_size = map->key_size;
+
+	hash = htab_map_hash(key, key_size);
+
+	b = __select_bucket(htab, hash);
+	head = &b->head;
+
+	/* bpf_map_update_elem() can be called in_irq() */
+	raw_spin_lock_irqsave(&b->lock, flags);
+
+	l_old = lookup_elem_raw(head, hash, key, key_size);
+
+	ret = check_flags(htab, l_old, map_flags);
+	if (ret)
+		goto err;
+
+	if (l_old) {
+		void __percpu *pptr = htab_elem_get_ptr(l_old, key_size);
+		u32 size = htab->map.value_size;
+
+		/* per-cpu hash map can update value in-place */
+		if (!onallcpus) {
+			memcpy(this_cpu_ptr(pptr), value, size);
+		} else {
+			int off = 0, cpu;
+
+			size = round_up(size, 8);
+			for_each_possible_cpu(cpu) {
+				bpf_long_memcpy(per_cpu_ptr(pptr, cpu),
+						value + off, size);
+				off += size;
+			}
+		}
+	} else {
+		l_new = alloc_htab_elem(htab, key, value, key_size,
+					hash, true, onallcpus);
+		if (IS_ERR(l_new)) {
+			ret = PTR_ERR(l_new);
+			goto err;
+		}
+		hlist_add_head_rcu(&l_new->hash_node, head);
+	}
+	ret = 0;
 err:
 	raw_spin_unlock_irqrestore(&b->lock, flags);
-	kfree(l_new);
 	return ret;
 }
 
+static int htab_percpu_map_update_elem(struct bpf_map *map, void *key,
+				       void *value, u64 map_flags)
+{
+	return __htab_percpu_map_update_elem(map, key, value, map_flags, false);
+}
+
 /* Called from syscall or from eBPF program */
 static int htab_map_delete_elem(struct bpf_map *map, void *key)
 {
@@ -331,8 +607,7 @@ static int htab_map_delete_elem(struct bpf_map *map, void *key)
 
 	if (l) {
 		hlist_del_rcu(&l->hash_node);
-		atomic_dec(&htab->count);
-		kfree_rcu(l, rcu);
+		free_htab_elem(htab, l);
 		ret = 0;
 	}
 
@@ -351,12 +626,10 @@ static void delete_all_elements(struct bpf_htab *htab)
 
 		hlist_for_each_entry_safe(l, n, head, hash_node) {
 			hlist_del_rcu(&l->hash_node);
-			atomic_dec(&htab->count);
-			kfree(l);
+			htab_elem_free(htab, l);
 		}
 	}
 }
-
 /* Called when map->refcnt goes to zero, either from workqueue or from syscall */
 static void htab_map_free(struct bpf_map *map)
 {
@@ -369,10 +642,16 @@ static void htab_map_free(struct bpf_map *map)
 	 */
 	synchronize_rcu();
 
-	/* some of kfree_rcu() callbacks for elements of this map may not have
-	 * executed. It's ok. Proceed to free residual elements and map itself
+	/* some of free_htab_elem() callbacks for elements of this map may
+	 * not have executed. Wait for them.
 	 */
-	delete_all_elements(htab);
+	rcu_barrier();
+	if (htab->map.map_flags & BPF_F_NO_PREALLOC) {
+		delete_all_elements(htab);
+	} else {
+		htab_free_elems(htab);
+		pcpu_freelist_destroy(&htab->freelist);
+	}
 	kvfree(htab->buckets);
 	kfree(htab);
 }
@@ -391,9 +670,76 @@ static struct bpf_map_type_list htab_type __read_mostly = {
 	.type = BPF_MAP_TYPE_HASH,
 };
 
+/* Called from eBPF program */
+static void *htab_percpu_map_lookup_elem(struct bpf_map *map, void *key)
+{
+	struct htab_elem *l = __htab_map_lookup_elem(map, key);
+
+	if (l)
+		return this_cpu_ptr(htab_elem_get_ptr(l, map->key_size));
+	else
+		return NULL;
+}
+
+int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value)
+{
+	struct htab_elem *l;
+	void __percpu *pptr;
+	int ret = -ENOENT;
+	int cpu, off = 0;
+	u32 size;
+
+	/* per_cpu areas are zero-filled and bpf programs can only
+	 * access 'value_size' of them, so copying rounded areas
+	 * will not leak any kernel data
+	 */
+	size = round_up(map->value_size, 8);
+	rcu_read_lock();
+	l = __htab_map_lookup_elem(map, key);
+	if (!l)
+		goto out;
+	pptr = htab_elem_get_ptr(l, map->key_size);
+	for_each_possible_cpu(cpu) {
+		bpf_long_memcpy(value + off,
+				per_cpu_ptr(pptr, cpu), size);
+		off += size;
+	}
+	ret = 0;
+out:
+	rcu_read_unlock();
+	return ret;
+}
+
+int bpf_percpu_hash_update(struct bpf_map *map, void *key, void *value,
+			   u64 map_flags)
+{
+	int ret;
+
+	rcu_read_lock();
+	ret = __htab_percpu_map_update_elem(map, key, value, map_flags, true);
+	rcu_read_unlock();
+
+	return ret;
+}
+
+static const struct bpf_map_ops htab_percpu_ops = {
+	.map_alloc = htab_map_alloc,
+	.map_free = htab_map_free,
+	.map_get_next_key = htab_map_get_next_key,
+	.map_lookup_elem = htab_percpu_map_lookup_elem,
+	.map_update_elem = htab_percpu_map_update_elem,
+	.map_delete_elem = htab_map_delete_elem,
+};
+
+static struct bpf_map_type_list htab_percpu_type __read_mostly = {
+	.ops = &htab_percpu_ops,
+	.type = BPF_MAP_TYPE_PERCPU_HASH,
+};
+
 static int __init register_htab_map(void)
 {
 	bpf_register_map_type(&htab_type);
+	bpf_register_map_type(&htab_percpu_type);
 	return 0;
 }
 late_initcall(register_htab_map);