summaryrefslogtreecommitdiff
path: root/kernel/bpf
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/bpf')
-rw-r--r--kernel/bpf/arraymap.c2
-rw-r--r--kernel/bpf/btf.c60
-rw-r--r--kernel/bpf/cgroup.c54
-rw-r--r--kernel/bpf/core.c39
-rw-r--r--kernel/bpf/cpumap.c15
-rw-r--r--kernel/bpf/devmap.c33
-rw-r--r--kernel/bpf/hashtab.c16
-rw-r--r--kernel/bpf/sockmap.c306
-rw-r--r--kernel/bpf/syscall.c119
-rw-r--r--kernel/bpf/verifier.c11
10 files changed, 427 insertions, 228 deletions
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 544e58f5f642..2aa55d030c77 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -378,7 +378,7 @@ static int array_map_check_btf(const struct bpf_map *map, const struct btf *btf,
return -EINVAL;
value_type = btf_type_id_size(btf, &btf_value_id, &value_size);
- if (!value_type || value_size > map->value_size)
+ if (!value_type || value_size != map->value_size)
return -EINVAL;
return 0;
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 2d49d18b793a..2590700237c1 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -450,7 +450,7 @@ static const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id)
*/
static bool btf_type_int_is_regular(const struct btf_type *t)
{
- u16 nr_bits, nr_bytes;
+ u8 nr_bits, nr_bytes;
u32 int_data;
int_data = btf_type_int(t);
@@ -991,38 +991,38 @@ static void btf_int_bits_seq_show(const struct btf *btf,
void *data, u8 bits_offset,
struct seq_file *m)
{
+ u16 left_shift_bits, right_shift_bits;
u32 int_data = btf_type_int(t);
- u16 nr_bits = BTF_INT_BITS(int_data);
- u16 total_bits_offset;
- u16 nr_copy_bytes;
- u16 nr_copy_bits;
- u8 nr_upper_bits;
- union {
- u64 u64_num;
- u8 u8_nums[8];
- } print_num;
+ u8 nr_bits = BTF_INT_BITS(int_data);
+ u8 total_bits_offset;
+ u8 nr_copy_bytes;
+ u8 nr_copy_bits;
+ u64 print_num;
+ /*
+ * bits_offset is at most 7.
+ * BTF_INT_OFFSET() cannot exceed 64 bits.
+ */
total_bits_offset = bits_offset + BTF_INT_OFFSET(int_data);
data += BITS_ROUNDDOWN_BYTES(total_bits_offset);
bits_offset = BITS_PER_BYTE_MASKED(total_bits_offset);
nr_copy_bits = nr_bits + bits_offset;
nr_copy_bytes = BITS_ROUNDUP_BYTES(nr_copy_bits);
- print_num.u64_num = 0;
- memcpy(&print_num.u64_num, data, nr_copy_bytes);
-
- /* Ditch the higher order bits */
- nr_upper_bits = BITS_PER_BYTE_MASKED(nr_copy_bits);
- if (nr_upper_bits) {
- /* We need to mask out some bits of the upper byte. */
- u8 mask = (1 << nr_upper_bits) - 1;
+ print_num = 0;
+ memcpy(&print_num, data, nr_copy_bytes);
- print_num.u8_nums[nr_copy_bytes - 1] &= mask;
- }
+#ifdef __BIG_ENDIAN_BITFIELD
+ left_shift_bits = bits_offset;
+#else
+ left_shift_bits = BITS_PER_U64 - nr_copy_bits;
+#endif
+ right_shift_bits = BITS_PER_U64 - nr_bits;
- print_num.u64_num >>= bits_offset;
+ print_num <<= left_shift_bits;
+ print_num >>= right_shift_bits;
- seq_printf(m, "0x%llx", print_num.u64_num);
+ seq_printf(m, "0x%llx", print_num);
}
static void btf_int_seq_show(const struct btf *btf, const struct btf_type *t,
@@ -1032,7 +1032,7 @@ static void btf_int_seq_show(const struct btf *btf, const struct btf_type *t,
u32 int_data = btf_type_int(t);
u8 encoding = BTF_INT_ENCODING(int_data);
bool sign = encoding & BTF_INT_SIGNED;
- u32 nr_bits = BTF_INT_BITS(int_data);
+ u8 nr_bits = BTF_INT_BITS(int_data);
if (bits_offset || BTF_INT_OFFSET(int_data) ||
BITS_PER_BYTE_MASKED(nr_bits)) {
@@ -1519,9 +1519,9 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env,
{
bool is_union = BTF_INFO_KIND(t->info) == BTF_KIND_UNION;
const struct btf_member *member;
+ u32 meta_needed, last_offset;
struct btf *btf = env->btf;
u32 struct_size = t->size;
- u32 meta_needed;
u16 i;
meta_needed = btf_type_vlen(t) * sizeof(*member);
@@ -1534,6 +1534,7 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env,
btf_verifier_log_type(env, t, NULL);
+ last_offset = 0;
for_each_member(i, t, member) {
if (!btf_name_offset_valid(btf, member->name_off)) {
btf_verifier_log_member(env, t, member,
@@ -1555,6 +1556,16 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env,
return -EINVAL;
}
+ /*
+ * ">" instead of ">=" because the last member could be
+ * "char a[0];"
+ */
+ if (last_offset > member->offset) {
+ btf_verifier_log_member(env, t, member,
+ "Invalid member bits_offset");
+ return -EINVAL;
+ }
+
if (BITS_ROUNDUP_BYTES(member->offset) > struct_size) {
btf_verifier_log_member(env, t, member,
"Memmber bits_offset exceeds its struct size");
@@ -1562,6 +1573,7 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env,
}
btf_verifier_log_member(env, t, member, NULL);
+ last_offset = member->offset;
}
return meta_needed;
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index f7c00bd6f8e4..3d83ee7df381 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -428,6 +428,60 @@ int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,
return ret;
}
+int cgroup_bpf_prog_attach(const union bpf_attr *attr,
+ enum bpf_prog_type ptype, struct bpf_prog *prog)
+{
+ struct cgroup *cgrp;
+ int ret;
+
+ cgrp = cgroup_get_from_fd(attr->target_fd);
+ if (IS_ERR(cgrp))
+ return PTR_ERR(cgrp);
+
+ ret = cgroup_bpf_attach(cgrp, prog, attr->attach_type,
+ attr->attach_flags);
+ cgroup_put(cgrp);
+ return ret;
+}
+
+int cgroup_bpf_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype)
+{
+ struct bpf_prog *prog;
+ struct cgroup *cgrp;
+ int ret;
+
+ cgrp = cgroup_get_from_fd(attr->target_fd);
+ if (IS_ERR(cgrp))
+ return PTR_ERR(cgrp);
+
+ prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype);
+ if (IS_ERR(prog))
+ prog = NULL;
+
+ ret = cgroup_bpf_detach(cgrp, prog, attr->attach_type, 0);
+ if (prog)
+ bpf_prog_put(prog);
+
+ cgroup_put(cgrp);
+ return ret;
+}
+
+int cgroup_bpf_prog_query(const union bpf_attr *attr,
+ union bpf_attr __user *uattr)
+{
+ struct cgroup *cgrp;
+ int ret;
+
+ cgrp = cgroup_get_from_fd(attr->query.target_fd);
+ if (IS_ERR(cgrp))
+ return PTR_ERR(cgrp);
+
+ ret = cgroup_bpf_query(cgrp, attr, uattr);
+
+ cgroup_put(cgrp);
+ return ret;
+}
+
/**
* __cgroup_bpf_run_filter_skb() - Run a program for packet filtering
* @sk: The socket sending or receiving traffic
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 9f1493705f40..1e5625d46414 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -350,6 +350,20 @@ struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off,
return prog_adj;
}
+void bpf_prog_kallsyms_del_subprogs(struct bpf_prog *fp)
+{
+ int i;
+
+ for (i = 0; i < fp->aux->func_cnt; i++)
+ bpf_prog_kallsyms_del(fp->aux->func[i]);
+}
+
+void bpf_prog_kallsyms_del_all(struct bpf_prog *fp)
+{
+ bpf_prog_kallsyms_del_subprogs(fp);
+ bpf_prog_kallsyms_del(fp);
+}
+
#ifdef CONFIG_BPF_JIT
/* All BPF JIT sysctl knobs here. */
int bpf_jit_enable __read_mostly = IS_BUILTIN(CONFIG_BPF_JIT_ALWAYS_ON);
@@ -1434,6 +1448,17 @@ static int bpf_check_tail_call(const struct bpf_prog *fp)
return 0;
}
+static void bpf_prog_select_func(struct bpf_prog *fp)
+{
+#ifndef CONFIG_BPF_JIT_ALWAYS_ON
+ u32 stack_depth = max_t(u32, fp->aux->stack_depth, 1);
+
+ fp->bpf_func = interpreters[(round_up(stack_depth, 32) / 32) - 1];
+#else
+ fp->bpf_func = __bpf_prog_ret0_warn;
+#endif
+}
+
/**
* bpf_prog_select_runtime - select exec runtime for BPF program
* @fp: bpf_prog populated with internal BPF program
@@ -1444,13 +1469,13 @@ static int bpf_check_tail_call(const struct bpf_prog *fp)
*/
struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err)
{
-#ifndef CONFIG_BPF_JIT_ALWAYS_ON
- u32 stack_depth = max_t(u32, fp->aux->stack_depth, 1);
+ /* In case of BPF to BPF calls, verifier did all the prep
+ * work with regards to JITing, etc.
+ */
+ if (fp->bpf_func)
+ goto finalize;
- fp->bpf_func = interpreters[(round_up(stack_depth, 32) / 32) - 1];
-#else
- fp->bpf_func = __bpf_prog_ret0_warn;
-#endif
+ bpf_prog_select_func(fp);
/* eBPF JITs can rewrite the program in case constant
* blinding is active. However, in case of error during
@@ -1471,6 +1496,8 @@ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err)
if (*err)
return fp;
}
+
+finalize:
bpf_prog_lock_ro(fp);
/* The tail call compatibility check can only be done at
diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index e0918d180f08..46f5f29605d4 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -69,7 +69,7 @@ struct bpf_cpu_map {
};
static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu,
- struct xdp_bulk_queue *bq);
+ struct xdp_bulk_queue *bq, bool in_napi_ctx);
static u64 cpu_map_bitmap_size(const union bpf_attr *attr)
{
@@ -375,7 +375,7 @@ static void __cpu_map_entry_free(struct rcu_head *rcu)
struct xdp_bulk_queue *bq = per_cpu_ptr(rcpu->bulkq, cpu);
/* No concurrent bq_enqueue can run at this point */
- bq_flush_to_queue(rcpu, bq);
+ bq_flush_to_queue(rcpu, bq, false);
}
free_percpu(rcpu->bulkq);
/* Cannot kthread_stop() here, last put free rcpu resources */
@@ -558,7 +558,7 @@ const struct bpf_map_ops cpu_map_ops = {
};
static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu,
- struct xdp_bulk_queue *bq)
+ struct xdp_bulk_queue *bq, bool in_napi_ctx)
{
unsigned int processed = 0, drops = 0;
const int to_cpu = rcpu->cpu;
@@ -578,7 +578,10 @@ static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu,
err = __ptr_ring_produce(q, xdpf);
if (err) {
drops++;
- xdp_return_frame_rx_napi(xdpf);
+ if (likely(in_napi_ctx))
+ xdp_return_frame_rx_napi(xdpf);
+ else
+ xdp_return_frame(xdpf);
}
processed++;
}
@@ -598,7 +601,7 @@ static int bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf)
struct xdp_bulk_queue *bq = this_cpu_ptr(rcpu->bulkq);
if (unlikely(bq->count == CPU_MAP_BULK_SIZE))
- bq_flush_to_queue(rcpu, bq);
+ bq_flush_to_queue(rcpu, bq, true);
/* Notice, xdp_buff/page MUST be queued here, long enough for
* driver to code invoking us to finished, due to driver
@@ -661,7 +664,7 @@ void __cpu_map_flush(struct bpf_map *map)
/* Flush all frames in bulkq to real queue */
bq = this_cpu_ptr(rcpu->bulkq);
- bq_flush_to_queue(rcpu, bq);
+ bq_flush_to_queue(rcpu, bq, true);
/* If already running, costs spin_lock_irqsave + smb_mb */
wake_up_process(rcpu->kthread);
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index a7cc7b3494a9..750d45edae79 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -217,7 +217,8 @@ void __dev_map_insert_ctx(struct bpf_map *map, u32 bit)
}
static int bq_xmit_all(struct bpf_dtab_netdev *obj,
- struct xdp_bulk_queue *bq, u32 flags)
+ struct xdp_bulk_queue *bq, u32 flags,
+ bool in_napi_ctx)
{
struct net_device *dev = obj->dev;
int sent = 0, drops = 0, err = 0;
@@ -254,7 +255,10 @@ error:
struct xdp_frame *xdpf = bq->q[i];
/* RX path under NAPI protection, can return frames faster */
- xdp_return_frame_rx_napi(xdpf);
+ if (likely(in_napi_ctx))
+ xdp_return_frame_rx_napi(xdpf);
+ else
+ xdp_return_frame(xdpf);
drops++;
}
goto out;
@@ -286,7 +290,7 @@ void __dev_map_flush(struct bpf_map *map)
__clear_bit(bit, bitmap);
bq = this_cpu_ptr(dev->bulkq);
- bq_xmit_all(dev, bq, XDP_XMIT_FLUSH);
+ bq_xmit_all(dev, bq, XDP_XMIT_FLUSH, true);
}
}
@@ -316,7 +320,7 @@ static int bq_enqueue(struct bpf_dtab_netdev *obj, struct xdp_frame *xdpf,
struct xdp_bulk_queue *bq = this_cpu_ptr(obj->bulkq);
if (unlikely(bq->count == DEV_MAP_BULK_SIZE))
- bq_xmit_all(obj, bq, 0);
+ bq_xmit_all(obj, bq, 0, true);
/* Ingress dev_rx will be the same for all xdp_frame's in
* bulk_queue, because bq stored per-CPU and must be flushed
@@ -334,10 +338,15 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
{
struct net_device *dev = dst->dev;
struct xdp_frame *xdpf;
+ int err;
if (!dev->netdev_ops->ndo_xdp_xmit)
return -EOPNOTSUPP;
+ err = xdp_ok_fwd_dev(dev, xdp->data_end - xdp->data);
+ if (unlikely(err))
+ return err;
+
xdpf = convert_to_xdp_frame(xdp);
if (unlikely(!xdpf))
return -EOVERFLOW;
@@ -345,6 +354,20 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
return bq_enqueue(dst, xdpf, dev_rx);
}
+int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb,
+ struct bpf_prog *xdp_prog)
+{
+ int err;
+
+ err = xdp_ok_fwd_dev(dst->dev, skb->len);
+ if (unlikely(err))
+ return err;
+ skb->dev = dst->dev;
+ generic_xdp_tx(skb, xdp_prog);
+
+ return 0;
+}
+
static void *dev_map_lookup_elem(struct bpf_map *map, void *key)
{
struct bpf_dtab_netdev *obj = __dev_map_lookup_elem(map, *(u32 *)key);
@@ -366,7 +389,7 @@ static void dev_map_flush_old(struct bpf_dtab_netdev *dev)
__clear_bit(dev->bit, bitmap);
bq = per_cpu_ptr(dev->bulkq, cpu);
- bq_xmit_all(dev, bq, XDP_XMIT_FLUSH);
+ bq_xmit_all(dev, bq, XDP_XMIT_FLUSH, false);
}
}
}
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 3ca2198a6d22..513d9dfcf4ee 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -747,13 +747,15 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
* old element will be freed immediately.
* Otherwise return an error
*/
- atomic_dec(&htab->count);
- return ERR_PTR(-E2BIG);
+ l_new = ERR_PTR(-E2BIG);
+ goto dec_count;
}
l_new = kmalloc_node(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN,
htab->map.numa_node);
- if (!l_new)
- return ERR_PTR(-ENOMEM);
+ if (!l_new) {
+ l_new = ERR_PTR(-ENOMEM);
+ goto dec_count;
+ }
}
memcpy(l_new->key, key, key_size);
@@ -766,7 +768,8 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
GFP_ATOMIC | __GFP_NOWARN);
if (!pptr) {
kfree(l_new);
- return ERR_PTR(-ENOMEM);
+ l_new = ERR_PTR(-ENOMEM);
+ goto dec_count;
}
}
@@ -780,6 +783,9 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
l_new->hash = hash;
return l_new;
+dec_count:
+ atomic_dec(&htab->count);
+ return l_new;
}
static int check_flags(struct bpf_htab *htab, struct htab_elem *l_old,
diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c
index 52a91d816c0e..c4d75c52b4fc 100644
--- a/kernel/bpf/sockmap.c
+++ b/kernel/bpf/sockmap.c
@@ -72,6 +72,7 @@ struct bpf_htab {
u32 n_buckets;
u32 elem_size;
struct bpf_sock_progs progs;
+ struct rcu_head rcu;
};
struct htab_elem {
@@ -89,8 +90,8 @@ enum smap_psock_state {
struct smap_psock_map_entry {
struct list_head list;
struct sock **entry;
- struct htab_elem *hash_link;
- struct bpf_htab *htab;
+ struct htab_elem __rcu *hash_link;
+ struct bpf_htab __rcu *htab;
};
struct smap_psock {
@@ -120,6 +121,7 @@ struct smap_psock {
struct bpf_prog *bpf_parse;
struct bpf_prog *bpf_verdict;
struct list_head maps;
+ spinlock_t maps_lock;
/* Back reference used when sock callback trigger sockmap operations */
struct sock *sock;
@@ -140,6 +142,7 @@ static int bpf_tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
static int bpf_tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size);
static int bpf_tcp_sendpage(struct sock *sk, struct page *page,
int offset, size_t size, int flags);
+static void bpf_tcp_close(struct sock *sk, long timeout);
static inline struct smap_psock *smap_psock_sk(const struct sock *sk)
{
@@ -161,7 +164,42 @@ out:
return !empty;
}
-static struct proto tcp_bpf_proto;
+enum {
+ SOCKMAP_IPV4,
+ SOCKMAP_IPV6,
+ SOCKMAP_NUM_PROTS,
+};
+
+enum {
+ SOCKMAP_BASE,
+ SOCKMAP_TX,
+ SOCKMAP_NUM_CONFIGS,
+};
+
+static struct proto *saved_tcpv6_prot __read_mostly;
+static DEFINE_SPINLOCK(tcpv6_prot_lock);
+static struct proto bpf_tcp_prots[SOCKMAP_NUM_PROTS][SOCKMAP_NUM_CONFIGS];
+static void build_protos(struct proto prot[SOCKMAP_NUM_CONFIGS],
+ struct proto *base)
+{
+ prot[SOCKMAP_BASE] = *base;
+ prot[SOCKMAP_BASE].close = bpf_tcp_close;
+ prot[SOCKMAP_BASE].recvmsg = bpf_tcp_recvmsg;
+ prot[SOCKMAP_BASE].stream_memory_read = bpf_tcp_stream_read;
+
+ prot[SOCKMAP_TX] = prot[SOCKMAP_BASE];
+ prot[SOCKMAP_TX].sendmsg = bpf_tcp_sendmsg;
+ prot[SOCKMAP_TX].sendpage = bpf_tcp_sendpage;
+}
+
+static void update_sk_prot(struct sock *sk, struct smap_psock *psock)
+{
+ int family = sk->sk_family == AF_INET6 ? SOCKMAP_IPV6 : SOCKMAP_IPV4;
+ int conf = psock->bpf_tx_msg ? SOCKMAP_TX : SOCKMAP_BASE;
+
+ sk->sk_prot = &bpf_tcp_prots[family][conf];
+}
+
static int bpf_tcp_init(struct sock *sk)
{
struct smap_psock *psock;
@@ -181,14 +219,17 @@ static int bpf_tcp_init(struct sock *sk)
psock->save_close = sk->sk_prot->close;
psock->sk_proto = sk->sk_prot;
- if (psock->bpf_tx_msg) {
- tcp_bpf_proto.sendmsg = bpf_tcp_sendmsg;
- tcp_bpf_proto.sendpage = bpf_tcp_sendpage;
- tcp_bpf_proto.recvmsg = bpf_tcp_recvmsg;
- tcp_bpf_proto.stream_memory_read = bpf_tcp_stream_read;
+ /* Build IPv6 sockmap whenever the address of tcpv6_prot changes */
+ if (sk->sk_family == AF_INET6 &&
+ unlikely(sk->sk_prot != smp_load_acquire(&saved_tcpv6_prot))) {
+ spin_lock_bh(&tcpv6_prot_lock);
+ if (likely(sk->sk_prot != saved_tcpv6_prot)) {
+ build_protos(bpf_tcp_prots[SOCKMAP_IPV6], sk->sk_prot);
+ smp_store_release(&saved_tcpv6_prot, sk->sk_prot);
+ }
+ spin_unlock_bh(&tcpv6_prot_lock);
}
-
- sk->sk_prot = &tcp_bpf_proto;
+ update_sk_prot(sk, psock);
rcu_read_unlock();
return 0;
}
@@ -219,24 +260,64 @@ out:
rcu_read_unlock();
}
+static struct htab_elem *lookup_elem_raw(struct hlist_head *head,
+ u32 hash, void *key, u32 key_size)
+{
+ struct htab_elem *l;
+
+ hlist_for_each_entry_rcu(l, head, hash_node) {
+ if (l->hash == hash && !memcmp(&l->key, key, key_size))
+ return l;
+ }
+
+ return NULL;
+}
+
+static inline struct bucket *__select_bucket(struct bpf_htab *htab, u32 hash)
+{
+ return &htab->buckets[hash & (htab->n_buckets - 1)];
+}
+
+static inline struct hlist_head *select_bucket(struct bpf_htab *htab, u32 hash)
+{
+ return &__select_bucket(htab, hash)->head;
+}
+
static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l)
{
atomic_dec(&htab->count);
kfree_rcu(l, rcu);
}
+static struct smap_psock_map_entry *psock_map_pop(struct sock *sk,
+ struct smap_psock *psock)
+{
+ struct smap_psock_map_entry *e;
+
+ spin_lock_bh(&psock->maps_lock);
+ e = list_first_entry_or_null(&psock->maps,
+ struct smap_psock_map_entry,
+ list);
+ if (e)
+ list_del(&e->list);
+ spin_unlock_bh(&psock->maps_lock);
+ return e;
+}
+
static void bpf_tcp_close(struct sock *sk, long timeout)
{
void (*close_fun)(struct sock *sk, long timeout);
- struct smap_psock_map_entry *e, *tmp;
+ struct smap_psock_map_entry *e;
struct sk_msg_buff *md, *mtmp;
struct smap_psock *psock;
struct sock *osk;
+ lock_sock(sk);
rcu_read_lock();
psock = smap_psock_sk(sk);
if (unlikely(!psock)) {
rcu_read_unlock();
+ release_sock(sk);
return sk->sk_prot->close(sk, timeout);
}
@@ -247,7 +328,6 @@ static void bpf_tcp_close(struct sock *sk, long timeout)
*/
close_fun = psock->save_close;
- write_lock_bh(&sk->sk_callback_lock);
if (psock->cork) {
free_start_sg(psock->sock, psock->cork);
kfree(psock->cork);
@@ -260,21 +340,40 @@ static void bpf_tcp_close(struct sock *sk, long timeout)
kfree(md);
}
- list_for_each_entry_safe(e, tmp, &psock->maps, list) {
+ e = psock_map_pop(sk, psock);
+ while (e) {
if (e->entry) {
osk = cmpxchg(e->entry, sk, NULL);
if (osk == sk) {
- list_del(&e->list);
smap_release_sock(psock, sk);
}
} else {
- hlist_del_rcu(&e->hash_link->hash_node);
- smap_release_sock(psock, e->hash_link->sk);
- free_htab_elem(e->htab, e->hash_link);
+ struct htab_elem *link = rcu_dereference(e->hash_link);
+ struct bpf_htab *htab = rcu_dereference(e->htab);
+ struct hlist_head *head;
+ struct htab_elem *l;
+ struct bucket *b;
+
+ b = __select_bucket(htab, link->hash);
+ head = &b->head;
+ raw_spin_lock_bh(&b->lock);
+ l = lookup_elem_raw(head,
+ link->hash, link->key,
+ htab->map.key_size);
+ /* If another thread deleted this object skip deletion.
+ * The refcnt on psock may or may not be zero.
+ */
+ if (l) {
+ hlist_del_rcu(&link->hash_node);
+ smap_release_sock(psock, link->sk);
+ free_htab_elem(htab, link);
+ }
+ raw_spin_unlock_bh(&b->lock);
}
+ e = psock_map_pop(sk, psock);
}
- write_unlock_bh(&sk->sk_callback_lock);
rcu_read_unlock();
+ release_sock(sk);
close_fun(sk, timeout);
}
@@ -472,7 +571,8 @@ static int free_sg(struct sock *sk, int start, struct sk_msg_buff *md)
while (sg[i].length) {
free += sg[i].length;
sk_mem_uncharge(sk, sg[i].length);
- put_page(sg_page(&sg[i]));
+ if (!md->skb)
+ put_page(sg_page(&sg[i]));
sg[i].length = 0;
sg[i].page_link = 0;
sg[i].offset = 0;
@@ -481,6 +581,8 @@ static int free_sg(struct sock *sk, int start, struct sk_msg_buff *md)
if (i == MAX_SKB_FRAGS)
i = 0;
}
+ if (md->skb)
+ consume_skb(md->skb);
return free;
}
@@ -946,12 +1048,12 @@ static int bpf_tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
while (msg_data_left(msg)) {
- struct sk_msg_buff *m;
+ struct sk_msg_buff *m = NULL;
bool enospc = false;
int copy;
if (sk->sk_err) {
- err = sk->sk_err;
+ err = -sk->sk_err;
goto out_err;
}
@@ -1014,8 +1116,11 @@ wait_for_sndbuf:
set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
wait_for_memory:
err = sk_stream_wait_memory(sk, &timeo);
- if (err)
+ if (err) {
+ if (m && m != psock->cork)
+ free_start_sg(sk, m);
goto out_err;
+ }
}
out_err:
if (err < 0)
@@ -1111,8 +1216,7 @@ static void bpf_tcp_msg_add(struct smap_psock *psock,
static int bpf_tcp_ulp_register(void)
{
- tcp_bpf_proto = tcp_prot;
- tcp_bpf_proto.close = bpf_tcp_close;
+ build_protos(bpf_tcp_prots[SOCKMAP_IPV4], &tcp_prot);
/* Once BPF TX ULP is registered it is never unregistered. It
* will be in the ULP list for the lifetime of the system. Doing
* duplicate registers is not a problem.
@@ -1135,7 +1239,7 @@ static int smap_verdict_func(struct smap_psock *psock, struct sk_buff *skb)
*/
TCP_SKB_CB(skb)->bpf.sk_redir = NULL;
skb->sk = psock->sock;
- bpf_compute_data_pointers(skb);
+ bpf_compute_data_end_sk_skb(skb);
preempt_disable();
rc = (*prog->bpf_func)(skb, prog->insnsi);
preempt_enable();
@@ -1357,7 +1461,9 @@ static void smap_release_sock(struct smap_psock *psock, struct sock *sock)
{
if (refcount_dec_and_test(&psock->refcnt)) {
tcp_cleanup_ulp(sock);
+ write_lock_bh(&sock->sk_callback_lock);
smap_stop_sock(psock, sock);
+ write_unlock_bh(&sock->sk_callback_lock);
clear_bit(SMAP_TX_RUNNING, &psock->state);
rcu_assign_sk_user_data(sock, NULL);
call_rcu_sched(&psock->rcu, smap_destroy_psock);
@@ -1388,7 +1494,7 @@ static int smap_parse_func_strparser(struct strparser *strp,
* any socket yet.
*/
skb->sk = psock->sock;
- bpf_compute_data_pointers(skb);
+ bpf_compute_data_end_sk_skb(skb);
rc = (*prog->bpf_func)(skb, prog->insnsi);
skb->sk = NULL;
rcu_read_unlock();
@@ -1508,6 +1614,7 @@ static struct smap_psock *smap_init_psock(struct sock *sock, int node)
INIT_LIST_HEAD(&psock->maps);
INIT_LIST_HEAD(&psock->ingress);
refcount_set(&psock->refcnt, 1);
+ spin_lock_init(&psock->maps_lock);
rcu_assign_sk_user_data(sock, psock);
sock_hold(sock);
@@ -1564,18 +1671,32 @@ free_stab:
return ERR_PTR(err);
}
-static void smap_list_remove(struct smap_psock *psock,
- struct sock **entry,
- struct htab_elem *hash_link)
+static void smap_list_map_remove(struct smap_psock *psock,
+ struct sock **entry)
{
struct smap_psock_map_entry *e, *tmp;
+ spin_lock_bh(&psock->maps_lock);
list_for_each_entry_safe(e, tmp, &psock->maps, list) {
- if (e->entry == entry || e->hash_link == hash_link) {
+ if (e->entry == entry)
list_del(&e->list);
- break;
- }
}
+ spin_unlock_bh(&psock->maps_lock);
+}
+
+static void smap_list_hash_remove(struct smap_psock *psock,
+ struct htab_elem *hash_link)
+{
+ struct smap_psock_map_entry *e, *tmp;
+
+ spin_lock_bh(&psock->maps_lock);
+ list_for_each_entry_safe(e, tmp, &psock->maps, list) {
+ struct htab_elem *c = rcu_dereference(e->hash_link);
+
+ if (c == hash_link)
+ list_del(&e->list);
+ }
+ spin_unlock_bh(&psock->maps_lock);
}
static void sock_map_free(struct bpf_map *map)
@@ -1601,7 +1722,6 @@ static void sock_map_free(struct bpf_map *map)
if (!sock)
continue;
- write_lock_bh(&sock->sk_callback_lock);
psock = smap_psock_sk(sock);
/* This check handles a racing sock event that can get the
* sk_callback_lock before this case but after xchg happens
@@ -1609,10 +1729,9 @@ static void sock_map_free(struct bpf_map *map)
* to be null and queued for garbage collection.
*/
if (likely(psock)) {
- smap_list_remove(psock, &stab->sock_map[i], NULL);
+ smap_list_map_remove(psock, &stab->sock_map[i]);
smap_release_sock(psock, sock);
}
- write_unlock_bh(&sock->sk_callback_lock);
}
rcu_read_unlock();
@@ -1661,17 +1780,15 @@ static int sock_map_delete_elem(struct bpf_map *map, void *key)
if (!sock)
return -EINVAL;
- write_lock_bh(&sock->sk_callback_lock);
psock = smap_psock_sk(sock);
if (!psock)
goto out;
if (psock->bpf_parse)
smap_stop_sock(psock, sock);
- smap_list_remove(psock, &stab->sock_map[k], NULL);
+ smap_list_map_remove(psock, &stab->sock_map[k]);
smap_release_sock(psock, sock);
out:
- write_unlock_bh(&sock->sk_callback_lock);
return 0;
}
@@ -1752,7 +1869,6 @@ static int __sock_map_ctx_update_elem(struct bpf_map *map,
}
}
- write_lock_bh(&sock->sk_callback_lock);
psock = smap_psock_sk(sock);
/* 2. Do not allow inheriting programs if psock exists and has
@@ -1789,7 +1905,7 @@ static int __sock_map_ctx_update_elem(struct bpf_map *map,
e = kzalloc(sizeof(*e), GFP_ATOMIC | __GFP_NOWARN);
if (!e) {
err = -ENOMEM;
- goto out_progs;
+ goto out_free;
}
}
@@ -1809,7 +1925,9 @@ static int __sock_map_ctx_update_elem(struct bpf_map *map,
if (err)
goto out_free;
smap_init_progs(psock, verdict, parse);
+ write_lock_bh(&sock->sk_callback_lock);
smap_start_sock(psock, sock);
+ write_unlock_bh(&sock->sk_callback_lock);
}
/* 4. Place psock in sockmap for use and stop any programs on
@@ -1819,9 +1937,10 @@ static int __sock_map_ctx_update_elem(struct bpf_map *map,
*/
if (map_link) {
e->entry = map_link;
+ spin_lock_bh(&psock->maps_lock);
list_add_tail(&e->list, &psock->maps);
+ spin_unlock_bh(&psock->maps_lock);
}
- write_unlock_bh(&sock->sk_callback_lock);
return err;
out_free:
smap_release_sock(psock, sock);
@@ -1832,7 +1951,6 @@ out_progs:
}
if (tx_msg)
bpf_prog_put(tx_msg);
- write_unlock_bh(&sock->sk_callback_lock);
kfree(e);
return err;
}
@@ -1869,10 +1987,8 @@ static int sock_map_ctx_update_elem(struct bpf_sock_ops_kern *skops,
if (osock) {
struct smap_psock *opsock = smap_psock_sk(osock);
- write_lock_bh(&osock->sk_callback_lock);
- smap_list_remove(opsock, &stab->sock_map[i], NULL);
+ smap_list_map_remove(opsock, &stab->sock_map[i]);
smap_release_sock(opsock, osock);
- write_unlock_bh(&osock->sk_callback_lock);
}
out:
return err;
@@ -1915,6 +2031,24 @@ int sock_map_prog(struct bpf_map *map, struct bpf_prog *prog, u32 type)
return 0;
}
+int sockmap_get_from_fd(const union bpf_attr *attr, int type,
+ struct bpf_prog *prog)
+{
+ int ufd = attr->target_fd;
+ struct bpf_map *map;
+ struct fd f;
+ int err;
+
+ f = fdget(ufd);
+ map = __bpf_map_get(f);
+ if (IS_ERR(map))
+ return PTR_ERR(map);
+
+ err = sock_map_prog(map, prog, attr->attach_type);
+ fdput(f);
+ return err;
+}
+
static void *sock_map_lookup(struct bpf_map *map, void *key)
{
return NULL;
@@ -1944,7 +2078,13 @@ static int sock_map_update_elem(struct bpf_map *map,
return -EOPNOTSUPP;
}
+ lock_sock(skops.sk);
+ preempt_disable();
+ rcu_read_lock();
err = sock_map_ctx_update_elem(&skops, map, key, flags);
+ rcu_read_unlock();
+ preempt_enable();
+ release_sock(skops.sk);
fput(socket->file);
return err;
}
@@ -2043,14 +2183,13 @@ free_htab:
return ERR_PTR(err);
}
-static inline struct bucket *__select_bucket(struct bpf_htab *htab, u32 hash)
+static void __bpf_htab_free(struct rcu_head *rcu)
{
- return &htab->buckets[hash & (htab->n_buckets - 1)];
-}
+ struct bpf_htab *htab;
-static inline struct hlist_head *select_bucket(struct bpf_htab *htab, u32 hash)
-{
- return &__select_bucket(htab, hash)->head;
+ htab = container_of(rcu, struct bpf_htab, rcu);
+ bpf_map_area_free(htab->buckets);
+ kfree(htab);
}
static void sock_hash_free(struct bpf_map *map)
@@ -2069,16 +2208,18 @@ static void sock_hash_free(struct bpf_map *map)
*/
rcu_read_lock();
for (i = 0; i < htab->n_buckets; i++) {
- struct hlist_head *head = select_bucket(htab, i);
+ struct bucket *b = __select_bucket(htab, i);
+ struct hlist_head *head;
struct hlist_node *n;
struct htab_elem *l;
+ raw_spin_lock_bh(&b->lock);
+ head = &b->head;
hlist_for_each_entry_safe(l, n, head, hash_node) {
struct sock *sock = l->sk;
struct smap_psock *psock;
hlist_del_rcu(&l->hash_node);
- write_lock_bh(&sock->sk_callback_lock);
psock = smap_psock_sk(sock);
/* This check handles a racing sock event that can get
* the sk_callback_lock before this case but after xchg
@@ -2086,16 +2227,15 @@ static void sock_hash_free(struct bpf_map *map)
* (psock) to be null and queued for garbage collection.
*/
if (likely(psock)) {
- smap_list_remove(psock, NULL, l);
+ smap_list_hash_remove(psock, l);
smap_release_sock(psock, sock);
}
- write_unlock_bh(&sock->sk_callback_lock);
- kfree(l);
+ free_htab_elem(htab, l);
}
+ raw_spin_unlock_bh(&b->lock);
}
rcu_read_unlock();
- bpf_map_area_free(htab->buckets);
- kfree(htab);
+ call_rcu(&htab->rcu, __bpf_htab_free);
}
static struct htab_elem *alloc_sock_hash_elem(struct bpf_htab *htab,
@@ -2122,19 +2262,6 @@ static struct htab_elem *alloc_sock_hash_elem(struct bpf_htab *htab,
return l_new;
}
-static struct htab_elem *lookup_elem_raw(struct hlist_head *head,
- u32 hash, void *key, u32 key_size)
-{
- struct htab_elem *l;
-
- hlist_for_each_entry_rcu(l, head, hash_node) {
- if (l->hash == hash && !memcmp(&l->key, key, key_size))
- return l;
- }
-
- return NULL;
-}
-
static inline u32 htab_map_hash(const void *key, u32 key_len)
{
return jhash(key, key_len, 0);
@@ -2230,7 +2357,10 @@ static int sock_hash_ctx_update_elem(struct bpf_sock_ops_kern *skops,
if (err)
goto err;
- /* bpf_map_update_elem() can be called in_irq() */
+ /* psock is valid here because otherwise above *ctx_update_elem would
+ * have thrown an error. It is safe to skip error check.
+ */
+ psock = smap_psock_sk(sock);
raw_spin_lock_bh(&b->lock);
l_old = lookup_elem_raw(head, hash, key, key_size);
if (l_old && map_flags == BPF_NOEXIST) {
@@ -2248,15 +2378,12 @@ static int sock_hash_ctx_update_elem(struct bpf_sock_ops_kern *skops,
goto bucket_err;
}
- psock = smap_psock_sk(sock);
- if (unlikely(!psock)) {
- err = -EINVAL;
- goto bucket_err;
- }
-
- e->hash_link = l_new;
- e->htab = container_of(map, struct bpf_htab, map);
+ rcu_assign_pointer(e->hash_link, l_new);
+ rcu_assign_pointer(e->htab,
+ container_of(map, struct bpf_htab, map));
+ spin_lock_bh(&psock->maps_lock);
list_add_tail(&e->list, &psock->maps);
+ spin_unlock_bh(&psock->maps_lock);
/* add new element to the head of the list, so that
* concurrent search will find it before old elem
@@ -2266,19 +2393,17 @@ static int sock_hash_ctx_update_elem(struct bpf_sock_ops_kern *skops,
psock = smap_psock_sk(l_old->sk);
hlist_del_rcu(&l_old->hash_node);
- smap_list_remove(psock, NULL, l_old);
+ smap_list_hash_remove(psock, l_old);
smap_release_sock(psock, l_old->sk);
free_htab_elem(htab, l_old);
}
raw_spin_unlock_bh(&b->lock);
return 0;
bucket_err:
+ smap_release_sock(psock, sock);
raw_spin_unlock_bh(&b->lock);
err:
kfree(e);
- psock = smap_psock_sk(sock);
- if (psock)
- smap_release_sock(psock, sock);
return err;
}
@@ -2300,7 +2425,13 @@ static int sock_hash_update_elem(struct bpf_map *map,
return -EINVAL;
}
+ lock_sock(skops.sk);
+ preempt_disable();
+ rcu_read_lock();
err = sock_hash_ctx_update_elem(&skops, map, key, flags);
+ rcu_read_unlock();
+ preempt_enable();
+ release_sock(skops.sk);
fput(socket->file);
return err;
}
@@ -2326,7 +2457,6 @@ static int sock_hash_delete_elem(struct bpf_map *map, void *key)
struct smap_psock *psock;
hlist_del_rcu(&l->hash_node);
- write_lock_bh(&sock->sk_callback_lock);
psock = smap_psock_sk(sock);
/* This check handles a racing sock event that can get the
* sk_callback_lock before this case but after xchg happens
@@ -2334,10 +2464,9 @@ static int sock_hash_delete_elem(struct bpf_map *map, void *key)
* to be null and queued for garbage collection.
*/
if (likely(psock)) {
- smap_list_remove(psock, NULL, l);
+ smap_list_hash_remove(psock, l);
smap_release_sock(psock, sock);
}
- write_unlock_bh(&sock->sk_callback_lock);
free_htab_elem(htab, l);
ret = 0;
}
@@ -2359,10 +2488,8 @@ struct sock *__sock_hash_lookup_elem(struct bpf_map *map, void *key)
b = __select_bucket(htab, hash);
head = &b->head;
- raw_spin_lock_bh(&b->lock);
l = lookup_elem_raw(head, hash, key, key_size);
sk = l ? l->sk : NULL;
- raw_spin_unlock_bh(&b->lock);
return sk;
}
@@ -2383,6 +2510,7 @@ const struct bpf_map_ops sock_hash_ops = {
.map_get_next_key = sock_hash_get_next_key,
.map_update_elem = sock_hash_update_elem,
.map_delete_elem = sock_hash_delete_elem,
+ .map_release_uref = sock_map_release,
};
BPF_CALL_4(bpf_sock_map_update, struct bpf_sock_ops_kern *, bpf_sock,
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 0fa20624707f..b41c6cf2eb88 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -575,7 +575,7 @@ static struct bpf_map *bpf_map_inc_not_zero(struct bpf_map *map,
{
int refold;
- refold = __atomic_add_unless(&map->refcnt, 1, 0);
+ refold = atomic_fetch_add_unless(&map->refcnt, 1, 0);
if (refold >= BPF_MAX_REFCNT) {
__bpf_map_put(map, false);
@@ -735,7 +735,9 @@ static int map_update_elem(union bpf_attr *attr)
if (bpf_map_is_dev_bound(map)) {
err = bpf_map_offload_update_elem(map, key, value, attr->flags);
goto out;
- } else if (map->map_type == BPF_MAP_TYPE_CPUMAP) {
+ } else if (map->map_type == BPF_MAP_TYPE_CPUMAP ||
+ map->map_type == BPF_MAP_TYPE_SOCKHASH ||
+ map->map_type == BPF_MAP_TYPE_SOCKMAP) {
err = map->ops->map_update_elem(map, key, value, attr->flags);
goto out;
}
@@ -1034,14 +1036,9 @@ static void __bpf_prog_put_rcu(struct rcu_head *rcu)
static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock)
{
if (atomic_dec_and_test(&prog->aux->refcnt)) {
- int i;
-
/* bpf_prog_free_id() must be called first */
bpf_prog_free_id(prog, do_idr_lock);
-
- for (i = 0; i < prog->aux->func_cnt; i++)
- bpf_prog_kallsyms_del(prog->aux->func[i]);
- bpf_prog_kallsyms_del(prog);
+ bpf_prog_kallsyms_del_all(prog);
call_rcu(&prog->aux->rcu, __bpf_prog_put_rcu);
}
@@ -1147,7 +1144,7 @@ struct bpf_prog *bpf_prog_inc_not_zero(struct bpf_prog *prog)
{
int refold;
- refold = __atomic_add_unless(&prog->aux->refcnt, 1, 0);
+ refold = atomic_fetch_add_unless(&prog->aux->refcnt, 1, 0);
if (refold >= BPF_MAX_REFCNT) {
__bpf_prog_put(prog, false);
@@ -1358,9 +1355,7 @@ static int bpf_prog_load(union bpf_attr *attr)
if (err < 0)
goto free_used_maps;
- /* eBPF program is ready to be JITed */
- if (!prog->bpf_func)
- prog = bpf_prog_select_runtime(prog, &err);
+ prog = bpf_prog_select_runtime(prog, &err);
if (err < 0)
goto free_used_maps;
@@ -1384,6 +1379,7 @@ static int bpf_prog_load(union bpf_attr *attr)
return err;
free_used_maps:
+ bpf_prog_kallsyms_del_subprogs(prog);
free_used_maps(prog->aux);
free_prog:
bpf_prog_uncharge_memlock(prog);
@@ -1489,8 +1485,6 @@ out_free_tp:
return err;
}
-#ifdef CONFIG_CGROUP_BPF
-
static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog,
enum bpf_attach_type attach_type)
{
@@ -1505,40 +1499,6 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog,
#define BPF_PROG_ATTACH_LAST_FIELD attach_flags
-static int sockmap_get_from_fd(const union bpf_attr *attr,
- int type, bool attach)
-{
- struct bpf_prog *prog = NULL;
- int ufd = attr->target_fd;
- struct bpf_map *map;
- struct fd f;
- int err;
-
- f = fdget(ufd);
- map = __bpf_map_get(f);
- if (IS_ERR(map))
- return PTR_ERR(map);
-
- if (attach) {
- prog = bpf_prog_get_type(attr->attach_bpf_fd, type);
- if (IS_ERR(prog)) {
- fdput(f);
- return PTR_ERR(prog);
- }
- }
-
- err = sock_map_prog(map, prog, attr->attach_type);
- if (err) {
- fdput(f);
- if (prog)
- bpf_prog_put(prog);
- return err;
- }
-
- fdput(f);
- return 0;
-}
-
#define BPF_F_ATTACH_MASK \
(BPF_F_ALLOW_OVERRIDE | BPF_F_ALLOW_MULTI)
@@ -1546,7 +1506,6 @@ static int bpf_prog_attach(const union bpf_attr *attr)
{
enum bpf_prog_type ptype;
struct bpf_prog *prog;
- struct cgroup *cgrp;
int ret;
if (!capable(CAP_NET_ADMIN))
@@ -1583,12 +1542,15 @@ static int bpf_prog_attach(const union bpf_attr *attr)
ptype = BPF_PROG_TYPE_CGROUP_DEVICE;
break;
case BPF_SK_MSG_VERDICT:
- return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_MSG, true);
+ ptype = BPF_PROG_TYPE_SK_MSG;
+ break;
case BPF_SK_SKB_STREAM_PARSER:
case BPF_SK_SKB_STREAM_VERDICT:
- return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_SKB, true);
+ ptype = BPF_PROG_TYPE_SK_SKB;
+ break;
case BPF_LIRC_MODE2:
- return lirc_prog_attach(attr);
+ ptype = BPF_PROG_TYPE_LIRC_MODE2;
+ break;
default:
return -EINVAL;
}
@@ -1602,18 +1564,20 @@ static int bpf_prog_attach(const union bpf_attr *attr)
return -EINVAL;
}
- cgrp = cgroup_get_from_fd(attr->target_fd);
- if (IS_ERR(cgrp)) {
- bpf_prog_put(prog);
- return PTR_ERR(cgrp);
+ switch (ptype) {
+ case BPF_PROG_TYPE_SK_SKB:
+ case BPF_PROG_TYPE_SK_MSG:
+ ret = sockmap_get_from_fd(attr, ptype, prog);
+ break;
+ case BPF_PROG_TYPE_LIRC_MODE2:
+ ret = lirc_prog_attach(attr, prog);
+ break;
+ default:
+ ret = cgroup_bpf_prog_attach(attr, ptype, prog);
}
- ret = cgroup_bpf_attach(cgrp, prog, attr->attach_type,
- attr->attach_flags);
if (ret)
bpf_prog_put(prog);
- cgroup_put(cgrp);
-
return ret;
}
@@ -1622,9 +1586,6 @@ static int bpf_prog_attach(const union bpf_attr *attr)
static int bpf_prog_detach(const union bpf_attr *attr)
{
enum bpf_prog_type ptype;
- struct bpf_prog *prog;
- struct cgroup *cgrp;
- int ret;
if (!capable(CAP_NET_ADMIN))
return -EPERM;
@@ -1657,29 +1618,17 @@ static int bpf_prog_detach(const union bpf_attr *attr)
ptype = BPF_PROG_TYPE_CGROUP_DEVICE;
break;
case BPF_SK_MSG_VERDICT:
- return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_MSG, false);
+ return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_MSG, NULL);
case BPF_SK_SKB_STREAM_PARSER:
case BPF_SK_SKB_STREAM_VERDICT:
- return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_SKB, false);
+ return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_SKB, NULL);
case BPF_LIRC_MODE2:
return lirc_prog_detach(attr);
default:
return -EINVAL;
}
- cgrp = cgroup_get_from_fd(attr->target_fd);
- if (IS_ERR(cgrp))
- return PTR_ERR(cgrp);
-
- prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype);
- if (IS_ERR(prog))
- prog = NULL;
-
- ret = cgroup_bpf_detach(cgrp, prog, attr->attach_type, 0);
- if (prog)
- bpf_prog_put(prog);
- cgroup_put(cgrp);
- return ret;
+ return cgroup_bpf_prog_detach(attr, ptype);
}
#define BPF_PROG_QUERY_LAST_FIELD query.prog_cnt
@@ -1687,9 +1636,6 @@ static int bpf_prog_detach(const union bpf_attr *attr)
static int bpf_prog_query(const union bpf_attr *attr,
union bpf_attr __user *uattr)
{
- struct cgroup *cgrp;
- int ret;
-
if (!capable(CAP_NET_ADMIN))
return -EPERM;
if (CHECK_ATTR(BPF_PROG_QUERY))
@@ -1717,14 +1663,9 @@ static int bpf_prog_query(const union bpf_attr *attr,
default:
return -EINVAL;
}
- cgrp = cgroup_get_from_fd(attr->query.target_fd);
- if (IS_ERR(cgrp))
- return PTR_ERR(cgrp);
- ret = cgroup_bpf_query(cgrp, attr, uattr);
- cgroup_put(cgrp);
- return ret;
+
+ return cgroup_bpf_prog_query(attr, uattr);
}
-#endif /* CONFIG_CGROUP_BPF */
#define BPF_PROG_TEST_RUN_LAST_FIELD test.duration
@@ -2371,7 +2312,6 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
case BPF_OBJ_GET:
err = bpf_obj_get(&attr);
break;
-#ifdef CONFIG_CGROUP_BPF
case BPF_PROG_ATTACH:
err = bpf_prog_attach(&attr);
break;
@@ -2381,7 +2321,6 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
case BPF_PROG_QUERY:
err = bpf_prog_query(&attr, uattr);
break;
-#endif
case BPF_PROG_TEST_RUN:
err = bpf_prog_test_run(&attr, uattr);
break;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 9e2bf834f13a..63aaac52a265 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5430,6 +5430,10 @@ static int jit_subprogs(struct bpf_verifier_env *env)
if (insn->code != (BPF_JMP | BPF_CALL) ||
insn->src_reg != BPF_PSEUDO_CALL)
continue;
+ /* Upon error here we cannot fall back to interpreter but
+ * need a hard reject of the program. Thus -EFAULT is
+ * propagated in any case.
+ */
subprog = find_subprog(env, i + insn->imm + 1);
if (subprog < 0) {
WARN_ONCE(1, "verifier bug. No program starts at insn %d\n",
@@ -5450,7 +5454,7 @@ static int jit_subprogs(struct bpf_verifier_env *env)
func = kcalloc(env->subprog_cnt, sizeof(prog), GFP_KERNEL);
if (!func)
- return -ENOMEM;
+ goto out_undo_insn;
for (i = 0; i < env->subprog_cnt; i++) {
subprog_start = subprog_end;
@@ -5515,7 +5519,7 @@ static int jit_subprogs(struct bpf_verifier_env *env)
tmp = bpf_int_jit_compile(func[i]);
if (tmp != func[i] || func[i]->bpf_func != old_bpf_func) {
verbose(env, "JIT doesn't support bpf-to-bpf calls\n");
- err = -EFAULT;
+ err = -ENOTSUPP;
goto out_free;
}
cond_resched();
@@ -5552,6 +5556,7 @@ out_free:
if (func[i])
bpf_jit_free(func[i]);
kfree(func);
+out_undo_insn:
/* cleanup main prog to be interpreted */
prog->jit_requested = 0;
for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) {
@@ -5578,6 +5583,8 @@ static int fixup_call_args(struct bpf_verifier_env *env)
err = jit_subprogs(env);
if (err == 0)
return 0;
+ if (err == -EFAULT)
+ return err;
}
#ifndef CONFIG_BPF_JIT_ALWAYS_ON
for (i = 0; i < prog->len; i++, insn++) {
generated by cgit v1.2.3 (git 2.39.0) at 2024-11-27 09:46:57 +0300