summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2016-03-19 10:05:34 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2016-03-19 10:05:34 -0700
commit1200b6809dfd9d73bc4c7db76d288c35fa4b2ebe (patch)
tree552e03de245cdbd0780ca1215914edc4a26540f7 /kernel
parent6b5f04b6cf8ebab9a65d9c0026c650bb2538fd0f (diff)
parentfe30937b65354c7fec244caebbdaae68e28ca797 (diff)
downloadlinux-1200b6809dfd9d73bc4c7db76d288c35fa4b2ebe.tar.bz2
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller: "Highlights: 1) Support more Realtek wireless chips, from Jes Sorenson. 2) New BPF types for per-cpu hash and arrap maps, from Alexei Starovoitov. 3) Make several TCP sysctls per-namespace, from Nikolay Borisov. 4) Allow the use of SO_REUSEPORT in order to do per-thread processing of incoming TCP/UDP connections. The muxing can be done using a BPF program which hashes the incoming packet. From Craig Gallek. 5) Add a multiplexer for TCP streams, to provide a messaged based interface. BPF programs can be used to determine the message boundaries. From Tom Herbert. 6) Add 802.1AE MACSEC support, from Sabrina Dubroca. 7) Avoid factorial complexity when taking down an inetdev interface with lots of configured addresses. We were doing things like traversing the entire address less for each address removed, and flushing the entire netfilter conntrack table for every address as well. 8) Add and use SKB bulk free infrastructure, from Jesper Brouer. 9) Allow offloading u32 classifiers to hardware, and implement for ixgbe, from John Fastabend. 10) Allow configuring IRQ coalescing parameters on a per-queue basis, from Kan Liang. 11) Extend ethtool so that larger link mode masks can be supported. From David Decotigny. 12) Introduce devlink, which can be used to configure port link types (ethernet vs Infiniband, etc.), port splitting, and switch device level attributes as a whole. From Jiri Pirko. 13) Hardware offload support for flower classifiers, from Amir Vadai. 14) Add "Local Checksum Offload". Basically, for a tunneled packet the checksum of the outer header is 'constant' (because with the checksum field filled into the inner protocol header, the payload of the outer frame checksums to 'zero'), and we can take advantage of that in various ways. From Edward Cree" * git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1548 commits) bonding: fix bond_get_stats() net: bcmgenet: fix dma api length mismatch net/mlx4_core: Fix backward compatibility on VFs phy: mdio-thunder: Fix some Kconfig typos lan78xx: add ndo_get_stats64 lan78xx: handle statistics counter rollover RDS: TCP: Remove unused constant RDS: TCP: Add sysctl tunables for sndbuf/rcvbuf on rds-tcp socket net: smc911x: convert pxa dma to dmaengine team: remove duplicate set of flag IFF_MULTICAST bonding: remove duplicate set of flag IFF_MULTICAST net: fix a comment typo ethernet: micrel: fix some error codes ip_tunnels, bpf: define IP_TUNNEL_OPTS_MAX and use it bpf, dst: add and use dst_tclassid helper bpf: make skb->tc_classid also readable net: mvneta: bm: clarify dependencies cls_bpf: reset class and reuse major in da ldmvsw: Checkpatch sunvnet.c and sunvnet_common.c ldmvsw: Add ldmvsw.c driver code ...
Diffstat (limited to 'kernel')
-rw-r--r--kernel/bpf/Makefile5
-rw-r--r--kernel/bpf/arraymap.c168
-rw-r--r--kernel/bpf/hashtab.c458
-rw-r--r--kernel/bpf/helpers.c2
-rw-r--r--kernel/bpf/percpu_freelist.c100
-rw-r--r--kernel/bpf/percpu_freelist.h31
-rw-r--r--kernel/bpf/stackmap.c290
-rw-r--r--kernel/bpf/syscall.c90
-rw-r--r--kernel/bpf/verifier.c48
-rw-r--r--kernel/events/callchain.c32
-rw-r--r--kernel/events/internal.h2
-rw-r--r--kernel/trace/bpf_trace.c4
12 files changed, 1116 insertions, 114 deletions
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index 13272582eee0..eed911d091da 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -1,4 +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/arraymap.c b/kernel/bpf/arraymap.c
index 89ebbc4d1164..76d5a794e426 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -17,15 +17,43 @@
#include <linux/filter.h>
#include <linux/perf_event.h>
+static void bpf_array_free_percpu(struct bpf_array *array)
+{
+ int i;
+
+ for (i = 0; i < array->map.max_entries; i++)
+ free_percpu(array->pptrs[i]);
+}
+
+static int bpf_array_alloc_percpu(struct bpf_array *array)
+{
+ void __percpu *ptr;
+ int i;
+
+ for (i = 0; i < array->map.max_entries; i++) {
+ ptr = __alloc_percpu_gfp(array->elem_size, 8,
+ GFP_USER | __GFP_NOWARN);
+ if (!ptr) {
+ bpf_array_free_percpu(array);
+ return -ENOMEM;
+ }
+ array->pptrs[i] = ptr;
+ }
+
+ return 0;
+}
+
/* Called from syscall */
static struct bpf_map *array_map_alloc(union bpf_attr *attr)
{
+ bool percpu = attr->map_type == BPF_MAP_TYPE_PERCPU_ARRAY;
struct bpf_array *array;
- u32 elem_size, array_size;
+ u64 array_size;
+ u32 elem_size;
/* 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))
@@ -36,12 +64,16 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
elem_size = round_up(attr->value_size, 8);
- /* check round_up into zero and u32 overflow */
- if (elem_size == 0 ||
- attr->max_entries > (U32_MAX - PAGE_SIZE - sizeof(*array)) / elem_size)
+ array_size = sizeof(*array);
+ if (percpu)
+ array_size += (u64) attr->max_entries * sizeof(void *);
+ else
+ array_size += (u64) attr->max_entries * elem_size;
+
+ /* make sure there is no u32 overflow later in round_up() */
+ if (array_size >= U32_MAX - PAGE_SIZE)
return ERR_PTR(-ENOMEM);
- array_size = sizeof(*array) + attr->max_entries * elem_size;
/* allocate all map elements and zero-initialize them */
array = kzalloc(array_size, GFP_USER | __GFP_NOWARN);
@@ -52,12 +84,25 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
}
/* copy mandatory map attributes */
+ array->map.map_type = attr->map_type;
array->map.key_size = attr->key_size;
array->map.value_size = attr->value_size;
array->map.max_entries = attr->max_entries;
- array->map.pages = round_up(array_size, PAGE_SIZE) >> PAGE_SHIFT;
array->elem_size = elem_size;
+ if (!percpu)
+ goto out;
+
+ array_size += (u64) attr->max_entries * elem_size * num_possible_cpus();
+
+ if (array_size >= U32_MAX - PAGE_SIZE ||
+ elem_size > PCPU_MIN_UNIT_SIZE || bpf_array_alloc_percpu(array)) {
+ kvfree(array);
+ return ERR_PTR(-ENOMEM);
+ }
+out:
+ array->map.pages = round_up(array_size, PAGE_SIZE) >> PAGE_SHIFT;
+
return &array->map;
}
@@ -67,12 +112,50 @@ static void *array_map_lookup_elem(struct bpf_map *map, void *key)
struct bpf_array *array = container_of(map, struct bpf_array, map);
u32 index = *(u32 *)key;
- if (index >= array->map.max_entries)
+ if (unlikely(index >= array->map.max_entries))
return NULL;
return array->value + array->elem_size * index;
}
+/* Called from eBPF program */
+static void *percpu_array_map_lookup_elem(struct bpf_map *map, void *key)
+{
+ struct bpf_array *array = container_of(map, struct bpf_array, map);
+ u32 index = *(u32 *)key;
+
+ if (unlikely(index >= array->map.max_entries))
+ return NULL;
+
+ return this_cpu_ptr(array->pptrs[index]);
+}
+
+int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value)
+{
+ struct bpf_array *array = container_of(map, struct bpf_array, map);
+ u32 index = *(u32 *)key;
+ void __percpu *pptr;
+ int cpu, off = 0;
+ u32 size;
+
+ if (unlikely(index >= array->map.max_entries))
+ return -ENOENT;
+
+ /* 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();
+ pptr = array->pptrs[index];
+ for_each_possible_cpu(cpu) {
+ bpf_long_memcpy(value + off, per_cpu_ptr(pptr, cpu), size);
+ off += size;
+ }
+ rcu_read_unlock();
+ return 0;
+}
+
/* Called from syscall */
static int array_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
{
@@ -99,19 +182,62 @@ static int array_map_update_elem(struct bpf_map *map, void *key, void *value,
struct bpf_array *array = container_of(map, struct bpf_array, map);
u32 index = *(u32 *)key;
- if (map_flags > BPF_EXIST)
+ if (unlikely(map_flags > BPF_EXIST))
/* unknown flags */
return -EINVAL;
- if (index >= array->map.max_entries)
+ if (unlikely(index >= array->map.max_entries))
/* all elements were pre-allocated, cannot insert a new one */
return -E2BIG;
- if (map_flags == BPF_NOEXIST)
+ if (unlikely(map_flags == BPF_NOEXIST))
/* all elements already exist */
return -EEXIST;
- memcpy(array->value + array->elem_size * index, value, map->value_size);
+ if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY)
+ memcpy(this_cpu_ptr(array->pptrs[index]),
+ value, map->value_size);
+ else
+ memcpy(array->value + array->elem_size * index,
+ value, map->value_size);
+ return 0;
+}
+
+int bpf_percpu_array_update(struct bpf_map *map, void *key, void *value,
+ u64 map_flags)
+{
+ struct bpf_array *array = container_of(map, struct bpf_array, map);
+ u32 index = *(u32 *)key;
+ void __percpu *pptr;
+ int cpu, off = 0;
+ u32 size;
+
+ if (unlikely(map_flags > BPF_EXIST))
+ /* unknown flags */
+ return -EINVAL;
+
+ if (unlikely(index >= array->map.max_entries))
+ /* all elements were pre-allocated, cannot insert a new one */
+ return -E2BIG;
+
+ if (unlikely(map_flags == BPF_NOEXIST))
+ /* all elements already exist */
+ return -EEXIST;
+
+ /* the user space will provide round_up(value_size, 8) bytes that
+ * will be copied into per-cpu area. bpf programs can only access
+ * value_size of it. During lookup the same extra bytes will be
+ * returned or zeros which were zero-filled by percpu_alloc,
+ * so no kernel data leaks possible
+ */
+ size = round_up(map->value_size, 8);
+ rcu_read_lock();
+ pptr = array->pptrs[index];
+ for_each_possible_cpu(cpu) {
+ bpf_long_memcpy(per_cpu_ptr(pptr, cpu), value + off, size);
+ off += size;
+ }
+ rcu_read_unlock();
return 0;
}
@@ -133,6 +259,9 @@ static void array_map_free(struct bpf_map *map)
*/
synchronize_rcu();
+ if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY)
+ bpf_array_free_percpu(array);
+
kvfree(array);
}
@@ -150,9 +279,24 @@ static struct bpf_map_type_list array_type __read_mostly = {
.type = BPF_MAP_TYPE_ARRAY,
};
+static const struct bpf_map_ops percpu_array_ops = {
+ .map_alloc = array_map_alloc,
+ .map_free = array_map_free,
+ .map_get_next_key = array_map_get_next_key,
+ .map_lookup_elem = percpu_array_map_lookup_elem,
+ .map_update_elem = array_map_update_elem,
+ .map_delete_elem = array_map_delete_elem,
+};
+
+static struct bpf_map_type_list percpu_array_type __read_mostly = {
+ .ops = &percpu_array_ops,
+ .type = BPF_MAP_TYPE_PERCPU_ARRAY,
+};
+
static int __init register_array_map(void)
{
bpf_register_map_type(&array_type);
+ bpf_register_map_type(&percpu_array_type);
return 0;
}
late_initcall(register_array_map);
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index c5b30fd8a315..fff3650d52fc 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);
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 4504ca66118d..50da680c479f 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -166,7 +166,7 @@ static u64 bpf_get_current_comm(u64 r1, u64 size, u64 r3, u64 r4, u64 r5)
if (!task)
return -EINVAL;
- memcpy(buf, task->comm, min_t(size_t, size, sizeof(task->comm)));
+ strlcpy(buf, task->comm, min_t(size_t, size, sizeof(task->comm)));
return 0;
}
diff --git a/kernel/bpf/percpu_freelist.c b/kernel/bpf/percpu_freelist.c
new file mode 100644
index 000000000000..5c51d1985b51
--- /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
index 000000000000..3049aae8ea1e
--- /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
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
new file mode 100644
index 000000000000..499d9e933f8e
--- /dev/null
+++ b/kernel/bpf/stackmap.c
@@ -0,0 +1,290 @@
+/* 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 <linux/bpf.h>
+#include <linux/jhash.h>
+#include <linux/filter.h>
+#include <linux/vmalloc.h>
+#include <linux/stacktrace.h>
+#include <linux/perf_event.h>
+#include "percpu_freelist.h"
+
+struct stack_map_bucket {
+ struct pcpu_freelist_node fnode;
+ u32 hash;
+ u32 nr;
+ u64 ip[];
+};
+
+struct bpf_stack_map {
+ struct bpf_map map;
+ void *elems;
+ struct pcpu_freelist freelist;
+ u32 n_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)
+{
+ u32 value_size = attr->value_size;
+ struct bpf_stack_map *smap;
+ u64 cost, n_buckets;
+ int err;
+
+ 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 ||
+ value_size / 8 > PERF_MAX_STACK_DEPTH)
+ return ERR_PTR(-EINVAL);
+
+ /* hash table size must be power of 2 */
+ n_buckets = roundup_pow_of_two(attr->max_entries);
+
+ cost = n_buckets * sizeof(struct stack_map_bucket *) + sizeof(*smap);
+ if (cost >= U32_MAX - PAGE_SIZE)
+ return ERR_PTR(-E2BIG);
+
+ smap = kzalloc(cost, GFP_USER | __GFP_NOWARN);
+ if (!smap) {
+ smap = vzalloc(cost);
+ if (!smap)
+ return ERR_PTR(-ENOMEM);
+ }
+
+ err = -E2BIG;
+ cost += n_buckets * (value_size + sizeof(struct stack_map_bucket));
+ if (cost >= U32_MAX - PAGE_SIZE)
+ goto free_smap;
+
+ smap->map.map_type = attr->map_type;
+ smap->map.key_size = attr->key_size;
+ smap->map.value_size = value_size;
+ smap->map.max_entries = attr->max_entries;
+ 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);
+}
+
+static u64 bpf_get_stackid(u64 r1, u64 r2, u64 flags, u64 r4, u64 r5)
+{
+ struct pt_regs *regs = (struct pt_regs *) (long) r1;
+ struct bpf_map *map = (struct bpf_map *) (long) r2;
+ struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map);
+ struct perf_callchain_entry *trace;
+ struct stack_map_bucket *bucket, *new_bucket, *old_bucket;
+ u32 max_depth = map->value_size / 8;
+ /* stack_map_alloc() checks that max_depth <= PERF_MAX_STACK_DEPTH */
+ u32 init_nr = PERF_MAX_STACK_DEPTH - max_depth;
+ u32 skip = flags & BPF_F_SKIP_FIELD_MASK;
+ u32 hash, id, trace_nr, trace_len;
+ bool user = flags & BPF_F_USER_STACK;
+ bool kernel = !user;
+ u64 *ips;
+
+ if (unlikely(flags & ~(BPF_F_SKIP_FIELD_MASK | BPF_F_USER_STACK |
+ BPF_F_FAST_STACK_CMP | BPF_F_REUSE_STACKID)))
+ return -EINVAL;
+
+ trace = get_perf_callchain(regs, init_nr, kernel, user, false, false);
+
+ if (unlikely(!trace))
+ /* couldn't fetch the stack trace */
+ return -EFAULT;
+
+ /* get_perf_callchain() guarantees that trace->nr >= init_nr
+ * and trace-nr <= PERF_MAX_STACK_DEPTH, so trace_nr <= max_depth
+ */
+ trace_nr = trace->nr - init_nr;
+
+ if (trace_nr <= skip)
+ /* skipping more than usable stack trace */
+ return -EFAULT;
+
+ trace_nr -= skip;
+ trace_len = trace_nr * sizeof(u64);
+ ips = trace->ip + skip + init_nr;
+ hash = jhash2((u32 *)ips, trace_len / sizeof(u32), 0);
+ id = hash & (smap->n_buckets - 1);
+ bucket = READ_ONCE(smap->buckets[id]);
+
+ if (bucket && bucket->hash == hash) {
+ if (flags & BPF_F_FAST_STACK_CMP)
+ return id;
+ if (bucket->nr == trace_nr &&
+ memcmp(bucket->ip, ips, trace_len) == 0)
+ return id;
+ }
+
+ /* this call stack is not in the map, try to add it */
+ if (bucket && !(flags & BPF_F_REUSE_STACKID))
+ return -EEXIST;
+
+ new_bucket = (struct stack_map_bucket *)
+ pcpu_freelist_pop(&smap->freelist);
+ if (unlikely(!new_bucket))
+ return -ENOMEM;
+
+ memcpy(new_bucket->ip, ips, trace_len);
+ new_bucket->hash = hash;
+ new_bucket->nr = trace_nr;
+
+ old_bucket = xchg(&smap->buckets[id], new_bucket);
+ if (old_bucket)
+ pcpu_freelist_push(&smap->freelist, &old_bucket->fnode);
+ return id;
+}
+
+const struct bpf_func_proto bpf_get_stackid_proto = {
+ .func = bpf_get_stackid,
+ .gpl_only = true,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_CONST_MAP_PTR,
+ .arg3_type = ARG_ANYTHING,
+};
+
+/* 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, *old_bucket;
+ u32 id = *(u32 *)key, trace_len;
+
+ if (unlikely(id >= smap->n_buckets))
+ 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)
+{
+ return -EINVAL;
+}
+
+static int stack_map_update_elem(struct bpf_map *map, void *key, void *value,
+ u64 map_flags)
+{
+ return -EINVAL;
+}
+
+/* Called from syscall or from eBPF program */
+static int stack_map_delete_elem(struct bpf_map *map, void *key)
+{
+ struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map);
+ struct stack_map_bucket *old_bucket;
+ u32 id = *(u32 *)key;
+
+ if (unlikely(id >= smap->n_buckets))
+ return -E2BIG;
+
+ old_bucket = xchg(&smap->buckets[id], NULL);
+ if (old_bucket) {
+ pcpu_freelist_push(&smap->freelist, &old_bucket->fnode);
+ return 0;
+ } else {
+ return -ENOENT;
+ }
+}
+
+/* Called when map->refcnt goes to zero, either from workqueue or from syscall */
+static void stack_map_free(struct bpf_map *map)
+{
+ struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map);
+
+ /* wait for bpf programs to complete before freeing stack map */
+ synchronize_rcu();
+
+ vfree(smap->elems);
+ pcpu_freelist_destroy(&smap->freelist);
+ kvfree(smap);
+ put_callchain_buffers();
+}
+
+static const struct bpf_map_ops stack_map_ops = {
+ .map_alloc = stack_map_alloc,
+ .map_free = stack_map_free,
+ .map_get_next_key = stack_map_get_next_key,
+ .map_lookup_elem = stack_map_lookup_elem,
+ .map_update_elem = stack_map_update_elem,
+ .map_delete_elem = stack_map_delete_elem,
+};
+
+static struct bpf_map_type_list stack_map_type __read_mostly = {
+ .ops = &stack_map_ops,
+ .type = BPF_MAP_TYPE_STACK_TRACE,
+};
+
+static int __init register_stack_map(void)
+{
+ bpf_register_map_type(&stack_map_type);
+ return 0;
+}
+late_initcall(register_stack_map);
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 637397059f76..2a2efe1bc76c 100644
--- a/kernel/bpf/syscall.c
+++ b/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)
{
@@ -229,6 +244,11 @@ static void __user *u64_to_ptr(__u64 val)
return (void __user *) (unsigned long) val;
}
+int __weak bpf_stackmap_copy(struct bpf_map *map, void *key, void *value)
+{
+ return -ENOTSUPP;
+}
+
/* last field in 'union bpf_attr' used by this command */
#define BPF_MAP_LOOKUP_ELEM_LAST_FIELD value
@@ -239,6 +259,7 @@ static int map_lookup_elem(union bpf_attr *attr)
int ufd = attr->map_fd;
struct bpf_map *map;
void *key, *value, *ptr;
+ u32 value_size;
struct fd f;
int err;
@@ -259,23 +280,37 @@ static int map_lookup_elem(union bpf_attr *attr)
if (copy_from_user(key, ukey, map->key_size) != 0)
goto free_key;
+ if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
+ map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY)
+ value_size = round_up(map->value_size, 8) * num_possible_cpus();
+ else
+ value_size = map->value_size;
+
err = -ENOMEM;
- value = kmalloc(map->value_size, GFP_USER | __GFP_NOWARN);
+ value = kmalloc(value_size, GFP_USER | __GFP_NOWARN);
if (!value)
goto free_key;
- rcu_read_lock();
- ptr = map->ops->map_lookup_elem(map, key);
- if (ptr)
- memcpy(value, ptr, map->value_size);
- rcu_read_unlock();
+ if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH) {
+ 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);
+ if (ptr)
+ memcpy(value, ptr, value_size);
+ rcu_read_unlock();
+ err = ptr ? 0 : -ENOENT;
+ }
- err = -ENOENT;
- if (!ptr)
+ if (err)
goto free_value;
err = -EFAULT;
- if (copy_to_user(uvalue, value, map->value_size) != 0)
+ if (copy_to_user(uvalue, value, value_size) != 0)
goto free_value;
err = 0;
@@ -298,6 +333,7 @@ static int map_update_elem(union bpf_attr *attr)
int ufd = attr->map_fd;
struct bpf_map *map;
void *key, *value;
+ u32 value_size;
struct fd f;
int err;
@@ -318,21 +354,37 @@ static int map_update_elem(union bpf_attr *attr)
if (copy_from_user(key, ukey, map->key_size) != 0)
goto free_key;
+ if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
+ map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY)
+ value_size = round_up(map->value_size, 8) * num_possible_cpus();
+ else
+ value_size = map->value_size;
+
err = -ENOMEM;
- value = kmalloc(map->value_size, GFP_USER | __GFP_NOWARN);
+ value = kmalloc(value_size, GFP_USER | __GFP_NOWARN);
if (!value)
goto free_key;
err = -EFAULT;
- if (copy_from_user(value, uvalue, map->value_size) != 0)
+ if (copy_from_user(value, uvalue, value_size) != 0)
goto free_value;
- /* eBPF program that use maps are running under rcu_read_lock(),
- * therefore all map accessors rely on this fact, so do the same here
+ /* must increment bpf_prog_active to avoid kprobe+bpf triggering from
+ * inside bpf map update or delete otherwise deadlocks are possible
*/
- rcu_read_lock();
- err = map->ops->map_update_elem(map, key, value, attr->flags);
- rcu_read_unlock();
+ 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) {
+ err = bpf_percpu_array_update(map, key, value, attr->flags);
+ } else {
+ rcu_read_lock();
+ 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);
@@ -371,9 +423,13 @@ 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);
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 2e7f7ab739e4..2e08f8e9b771 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -246,6 +246,7 @@ static const struct {
{BPF_MAP_TYPE_PROG_ARRAY, BPF_FUNC_tail_call},
{BPF_MAP_TYPE_PERF_EVENT_ARRAY, BPF_FUNC_perf_event_read},
{BPF_MAP_TYPE_PERF_EVENT_ARRAY, BPF_FUNC_perf_event_output},
+ {BPF_MAP_TYPE_STACK_TRACE, BPF_FUNC_get_stackid},
};
static void print_verifier_state(struct verifier_env *env)
@@ -778,15 +779,24 @@ static int check_xadd(struct verifier_env *env, struct bpf_insn *insn)
* bytes from that pointer, make sure that it's within stack boundary
* and all elements of stack are initialized
*/
-static int check_stack_boundary(struct verifier_env *env,
- int regno, int access_size)
+static int check_stack_boundary(struct verifier_env *env, int regno,
+ int access_size, bool zero_size_allowed)
{
struct verifier_state *state = &env->cur_state;
struct reg_state *regs = state->regs;
int off, i;
- if (regs[regno].type != PTR_TO_STACK)
+ if (regs[regno].type != PTR_TO_STACK) {
+ if (zero_size_allowed && access_size == 0 &&
+ regs[regno].type == CONST_IMM &&
+ regs[regno].imm == 0)
+ return 0;
+
+ verbose("R%d type=%s expected=%s\n", regno,
+ reg_type_str[regs[regno].type],
+ reg_type_str[PTR_TO_STACK]);
return -EACCES;
+ }
off = regs[regno].imm;
if (off >= 0 || off < -MAX_BPF_STACK || off + access_size > 0 ||
@@ -829,15 +839,24 @@ static int check_func_arg(struct verifier_env *env, u32 regno,
return 0;
}
- if (arg_type == ARG_PTR_TO_STACK || arg_type == ARG_PTR_TO_MAP_KEY ||
+ if (arg_type == ARG_PTR_TO_MAP_KEY ||
arg_type == ARG_PTR_TO_MAP_VALUE) {
expected_type = PTR_TO_STACK;
- } else if (arg_type == ARG_CONST_STACK_SIZE) {
+ } else if (arg_type == ARG_CONST_STACK_SIZE ||
+ arg_type == ARG_CONST_STACK_SIZE_OR_ZERO) {
expected_type = CONST_IMM;
} else if (arg_type == ARG_CONST_MAP_PTR) {
expected_type = CONST_PTR_TO_MAP;
} else if (arg_type == ARG_PTR_TO_CTX) {
expected_type = PTR_TO_CTX;
+ } else if (arg_type == ARG_PTR_TO_STACK) {
+ expected_type = PTR_TO_STACK;
+ /* One exception here. In case function allows for NULL to be
+ * passed in as argument, it's a CONST_IMM type. Final test
+ * happens during stack boundary checking.
+ */
+ if (reg->type == CONST_IMM && reg->imm == 0)
+ expected_type = CONST_IMM;
} else {
verbose("unsupported arg_type %d\n", arg_type);
return -EFAULT;
@@ -867,8 +886,8 @@ static int check_func_arg(struct verifier_env *env, u32 regno,
verbose("invalid map_ptr to access map->key\n");
return -EACCES;
}
- err = check_stack_boundary(env, regno, (*mapp)->key_size);
-
+ err = check_stack_boundary(env, regno, (*mapp)->key_size,
+ false);
} else if (arg_type == ARG_PTR_TO_MAP_VALUE) {
/* bpf_map_xxx(..., map_ptr, ..., value) call:
* check [value, value + map->value_size) validity
@@ -878,9 +897,12 @@ static int check_func_arg(struct verifier_env *env, u32 regno,
verbose("invalid map_ptr to access map->value\n");
return -EACCES;
}
- err = check_stack_boundary(env, regno, (*mapp)->value_size);
+ err = check_stack_boundary(env, regno, (*mapp)->value_size,
+ false);
+ } else if (arg_type == ARG_CONST_STACK_SIZE ||
+ arg_type == ARG_CONST_STACK_SIZE_OR_ZERO) {
+ bool zero_size_allowed = (arg_type == ARG_CONST_STACK_SIZE_OR_ZERO);
- } else if (arg_type == ARG_CONST_STACK_SIZE) {
/* bpf_xxx(..., buf, len) call will access 'len' bytes
* from stack pointer 'buf'. Check it
* note: regno == len, regno - 1 == buf
@@ -890,7 +912,8 @@ static int check_func_arg(struct verifier_env *env, u32 regno,
verbose("ARG_CONST_STACK_SIZE cannot be first argument\n");
return -EACCES;
}
- err = check_stack_boundary(env, regno - 1, reg->imm);
+ err = check_stack_boundary(env, regno - 1, reg->imm,
+ zero_size_allowed);
}
return err;
@@ -911,8 +934,11 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id)
* don't allow any other map type to be passed into
* the special func;
*/
- if (bool_func && bool_map != bool_func)
+ if (bool_func && bool_map != bool_func) {
+ verbose("cannot pass map_type %d into func %d\n",
+ map->map_type, func_id);
return -EINVAL;
+ }
}
return 0;
diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c
index 9c418002b8c1..343c22f5e867 100644
--- a/kernel/events/callchain.c
+++ b/kernel/events/callchain.c
@@ -159,15 +159,24 @@ put_callchain_entry(int rctx)
struct perf_callchain_entry *
perf_callchain(struct perf_event *event, struct pt_regs *regs)
{
- int rctx;
- struct perf_callchain_entry *entry;
-
- int kernel = !event->attr.exclude_callchain_kernel;
- int user = !event->attr.exclude_callchain_user;
+ bool kernel = !event->attr.exclude_callchain_kernel;
+ bool user = !event->attr.exclude_callchain_user;
+ /* Disallow cross-task user callchains. */
+ bool crosstask = event->ctx->task && event->ctx->task != current;
if (!kernel && !user)
return NULL;
+ return get_perf_callchain(regs, 0, kernel, user, crosstask, true);
+}
+
+struct perf_callchain_entry *
+get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
+ bool crosstask, bool add_mark)
+{
+ struct perf_callchain_entry *entry;
+ int rctx;
+
entry = get_callchain_entry(&rctx);
if (rctx == -1)
return NULL;
@@ -175,10 +184,11 @@ perf_callchain(struct perf_event *event, struct pt_regs *regs)
if (!entry)
goto exit_put;
- entry->nr = 0;
+ entry->nr = init_nr;
if (kernel && !user_mode(regs)) {
- perf_callchain_store(entry, PERF_CONTEXT_KERNEL);
+ if (add_mark)
+ perf_callchain_store(entry, PERF_CONTEXT_KERNEL);
perf_callchain_kernel(entry, regs);
}
@@ -191,13 +201,11 @@ perf_callchain(struct perf_event *event, struct pt_regs *regs)
}
if (regs) {
- /*
- * Disallow cross-task user callchains.
- */
- if (event->ctx->task && event->ctx->task != current)
+ if (crosstask)
goto exit_put;
- perf_callchain_store(entry, PERF_CONTEXT_USER);
+ if (add_mark)
+ perf_callchain_store(entry, PERF_CONTEXT_USER);
perf_callchain_user(entry, regs);
}
}
diff --git a/kernel/events/internal.h b/kernel/events/internal.h
index 2bbad9c1274c..4199b6d193f5 100644
--- a/kernel/events/internal.h
+++ b/kernel/events/internal.h
@@ -182,8 +182,6 @@ DEFINE_OUTPUT_COPY(__output_copy_user, arch_perf_out_copy_user)
/* Callchain handling */
extern struct perf_callchain_entry *
perf_callchain(struct perf_event *event, struct pt_regs *regs);
-extern int get_callchain_buffers(void);
-extern void put_callchain_buffers(void);
static inline int get_recursion_context(int *recursion)
{
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 326a75e884db..3e4ffb3ace5f 100644
--- a/kernel/trace/bpf_trace.c
+++ b/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
@@ -299,6 +297,8 @@ static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func
return &bpf_perf_event_read_proto;
case BPF_FUNC_perf_event_output:
return &bpf_perf_event_output_proto;
+ case BPF_FUNC_get_stackid:
+ return &bpf_get_stackid_proto;
default:
return NULL;
}