Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Daniel Borkmann says:

====================
pull-request: bpf-next 2018-10-21

The following pull-request contains BPF updates for your *net-next* tree.

The main changes are:

1) Implement two new kind of BPF maps, that is, queue and stack
   map along with new peek, push and pop operations, from Mauricio.

2) Add support for MSG_PEEK flag when redirecting into an ingress
   psock sk_msg queue, and add a new helper bpf_msg_push_data() for
   insert data into the message, from John.

3) Allow for BPF programs of type BPF_PROG_TYPE_CGROUP_SKB to use
   direct packet access for __skb_buff, from Song.

4) Use more lightweight barriers for walking perf ring buffer for
   libbpf and perf tool as well. Also, various fixes and improvements
   from verifier side, from Daniel.

5) Add per-symbol visibility for DSO in libbpf and hide by default
   global symbols such as netlink related functions, from Andrey.

6) Two improvements to nfp's BPF offload to check vNIC capabilities
   in case prog is shared with multiple vNICs and to protect against
   mis-initializing atomic counters, from Jakub.

7) Fix for bpftool to use 4 context mode for the nfp disassembler,
   also from Jakub.

8) Fix a return value comparison in test_libbpf.sh and add several
   bpftool improvements in bash completion, documentation of bpf fs
   restrictions and batch mode summary print, from Quentin.

9) Fix a file resource leak in BPF selftest's load_kallsyms()
   helper, from Peng.

10) Fix an unused variable warning in map_lookup_and_delete_elem(),
    from Alexei.

11) Fix bpf_skb_adjust_room() signature in BPF UAPI helper doc,
    from Nicolas.

12) Add missing executables to .gitignore in BPF selftests, from Anders.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/netronome/nfp/bpf/main.h

@@ -189,6 +189,11 @@ enum nfp_bpf_map_use {
 	NFP_MAP_USE_ATOMIC_CNT,
 };
 
+struct nfp_bpf_map_word {
+	unsigned char type		:4;
+	unsigned char non_zero_update	:1;
+};
+
 /**
  * struct nfp_bpf_map - private per-map data attached to BPF maps for offload
  * @offmap:	pointer to the offloaded BPF map
@@ -202,7 +207,7 @@ struct nfp_bpf_map {
 	struct nfp_app_bpf *bpf;
 	u32 tid;
 	struct list_head l;
-	enum nfp_bpf_map_use use_map[];
+	struct nfp_bpf_map_word use_map[];
 };
 
 struct nfp_bpf_neutral_map {
@@ -436,6 +441,7 @@ struct nfp_bpf_subprog_info {
  * @prog: machine code
  * @prog_len: number of valid instructions in @prog array
  * @__prog_alloc_len: alloc size of @prog array
+ * @stack_size: total amount of stack used
  * @verifier_meta: temporary storage for verifier's insn meta
  * @type: BPF program type
  * @last_bpf_off: address of the last instruction translated from BPF
@@ -460,6 +466,8 @@ struct nfp_prog {
 	unsigned int prog_len;
 	unsigned int __prog_alloc_len;
 
+	unsigned int stack_size;
+
 	struct nfp_insn_meta *verifier_meta;
 
 	enum bpf_prog_type type;

drivers/net/ethernet/netronome/nfp/bpf/offload.c

@@ -262,10 +262,25 @@ static void nfp_map_bpf_byte_swap(struct nfp_bpf_map *nfp_map, void *value)
 	unsigned int i;
 
 	for (i = 0; i < DIV_ROUND_UP(nfp_map->offmap->map.value_size, 4); i++)
-		if (nfp_map->use_map[i] == NFP_MAP_USE_ATOMIC_CNT)
+		if (nfp_map->use_map[i].type == NFP_MAP_USE_ATOMIC_CNT)
 			word[i] = (__force u32)cpu_to_be32(word[i]);
 }
 
+/* Mark value as unsafely initialized in case it becomes atomic later
+ * and we didn't byte swap something non-byte swap neutral.
+ */
+static void
+nfp_map_bpf_byte_swap_record(struct nfp_bpf_map *nfp_map, void *value)
+{
+	u32 *word = value;
+	unsigned int i;
+
+	for (i = 0; i < DIV_ROUND_UP(nfp_map->offmap->map.value_size, 4); i++)
+		if (nfp_map->use_map[i].type == NFP_MAP_UNUSED &&
+		    word[i] != (__force u32)cpu_to_be32(word[i]))
+			nfp_map->use_map[i].non_zero_update = 1;
+}
+
 static int
 nfp_bpf_map_lookup_entry(struct bpf_offloaded_map *offmap,
 			 void *key, void *value)
@@ -285,6 +300,7 @@ nfp_bpf_map_update_entry(struct bpf_offloaded_map *offmap,
 			 void *key, void *value, u64 flags)
 {
 	nfp_map_bpf_byte_swap(offmap->dev_priv, value);
+	nfp_map_bpf_byte_swap_record(offmap->dev_priv, value);
 	return nfp_bpf_ctrl_update_entry(offmap, key, value, flags);
 }
 
@@ -473,7 +489,7 @@ nfp_net_bpf_load(struct nfp_net *nn, struct bpf_prog *prog,
 		 struct netlink_ext_ack *extack)
 {
 	struct nfp_prog *nfp_prog = prog->aux->offload->dev_priv;
-	unsigned int max_mtu;
+	unsigned int max_mtu, max_stack, max_prog_len;
 	dma_addr_t dma_addr;
 	void *img;
 	int err;
@@ -484,6 +500,18 @@ nfp_net_bpf_load(struct nfp_net *nn, struct bpf_prog *prog,
 		return -EOPNOTSUPP;
 	}
 
+	max_stack = nn_readb(nn, NFP_NET_CFG_BPF_STACK_SZ) * 64;
+	if (nfp_prog->stack_size > max_stack) {
+		NL_SET_ERR_MSG_MOD(extack, "stack too large");
+		return -EOPNOTSUPP;
+	}
+
+	max_prog_len = nn_readw(nn, NFP_NET_CFG_BPF_MAX_LEN);
+	if (nfp_prog->prog_len > max_prog_len) {
+		NL_SET_ERR_MSG_MOD(extack, "program too long");
+		return -EOPNOTSUPP;
+	}
+
 	img = nfp_bpf_relo_for_vnic(nfp_prog, nn->app_priv);
 	if (IS_ERR(img))
 		return PTR_ERR(img);

drivers/net/ethernet/netronome/nfp/bpf/verifier.c

@@ -80,6 +80,46 @@ exit_set_location:
 	nfp_prog->adjust_head_location = location;
 }
 
+static bool nfp_bpf_map_update_value_ok(struct bpf_verifier_env *env)
+{
+	const struct bpf_reg_state *reg1 = cur_regs(env) + BPF_REG_1;
+	const struct bpf_reg_state *reg3 = cur_regs(env) + BPF_REG_3;
+	struct bpf_offloaded_map *offmap;
+	struct bpf_func_state *state;
+	struct nfp_bpf_map *nfp_map;
+	int off, i;
+
+	state = env->cur_state->frame[reg3->frameno];
+
+	/* We need to record each time update happens with non-zero words,
+	 * in case such word is used in atomic operations.
+	 * Implicitly depend on nfp_bpf_stack_arg_ok(reg3) being run before.
+	 */
+
+	offmap = map_to_offmap(reg1->map_ptr);
+	nfp_map = offmap->dev_priv;
+	off = reg3->off + reg3->var_off.value;
+
+	for (i = 0; i < offmap->map.value_size; i++) {
+		struct bpf_stack_state *stack_entry;
+		unsigned int soff;
+
+		soff = -(off + i) - 1;
+		stack_entry = &state->stack[soff / BPF_REG_SIZE];
+		if (stack_entry->slot_type[soff % BPF_REG_SIZE] == STACK_ZERO)
+			continue;
+
+		if (nfp_map->use_map[i / 4].type == NFP_MAP_USE_ATOMIC_CNT) {
+			pr_vlog(env, "value at offset %d/%d may be non-zero, bpf_map_update_elem() is required to initialize atomic counters to zero to avoid offload endian issues\n",
+				i, soff);
+			return false;
+		}
+		nfp_map->use_map[i / 4].non_zero_update = 1;
+	}
+
+	return true;
+}
+
 static int
 nfp_bpf_stack_arg_ok(const char *fname, struct bpf_verifier_env *env,
 		     const struct bpf_reg_state *reg,
@@ -171,7 +211,8 @@ nfp_bpf_check_helper_call(struct nfp_prog *nfp_prog,
 					 bpf->helpers.map_update, reg1) ||
 		    !nfp_bpf_stack_arg_ok("map_update", env, reg2,
 					  meta->func_id ? &meta->arg2 : NULL) ||
-		    !nfp_bpf_stack_arg_ok("map_update", env, reg3, NULL))
+		    !nfp_bpf_stack_arg_ok("map_update", env, reg3, NULL) ||
+		    !nfp_bpf_map_update_value_ok(env))
 			return -EOPNOTSUPP;
 		break;
 
@@ -352,15 +393,22 @@ nfp_bpf_map_mark_used_one(struct bpf_verifier_env *env,
 			  struct nfp_bpf_map *nfp_map,
 			  unsigned int off, enum nfp_bpf_map_use use)
 {
-	if (nfp_map->use_map[off / 4] != NFP_MAP_UNUSED &&
-	    nfp_map->use_map[off / 4] != use) {
+	if (nfp_map->use_map[off / 4].type != NFP_MAP_UNUSED &&
+	    nfp_map->use_map[off / 4].type != use) {
 		pr_vlog(env, "map value use type conflict %s vs %s off: %u\n",
-			nfp_bpf_map_use_name(nfp_map->use_map[off / 4]),
+			nfp_bpf_map_use_name(nfp_map->use_map[off / 4].type),
 			nfp_bpf_map_use_name(use), off);
 		return -EOPNOTSUPP;
 	}
 
-	nfp_map->use_map[off / 4] = use;
+	if (nfp_map->use_map[off / 4].non_zero_update &&
+	    use == NFP_MAP_USE_ATOMIC_CNT) {
+		pr_vlog(env, "atomic counter in map value may already be initialized to non-zero value off: %u\n",
+			off);
+		return -EOPNOTSUPP;
+	}
+
+	nfp_map->use_map[off / 4].type = use;
 
 	return 0;
 }
@@ -699,9 +747,9 @@ continue_subprog:
 
 static int nfp_bpf_finalize(struct bpf_verifier_env *env)
 {
-	unsigned int stack_size, stack_needed;
 	struct bpf_subprog_info *info;
 	struct nfp_prog *nfp_prog;
+	unsigned int max_stack;
 	struct nfp_net *nn;
 	int i;
 
@@ -729,11 +777,12 @@ static int nfp_bpf_finalize(struct bpf_verifier_env *env)
 	}
 
 	nn = netdev_priv(env->prog->aux->offload->netdev);
-	stack_size = nn_readb(nn, NFP_NET_CFG_BPF_STACK_SZ) * 64;
-	stack_needed = nfp_bpf_get_stack_usage(nfp_prog, env->prog->len);
-	if (stack_needed > stack_size) {
+	max_stack = nn_readb(nn, NFP_NET_CFG_BPF_STACK_SZ) * 64;
+	nfp_prog->stack_size = nfp_bpf_get_stack_usage(nfp_prog,
+						       env->prog->len);
+	if (nfp_prog->stack_size > max_stack) {
 		pr_vlog(env, "stack too large: program %dB > FW stack %dB\n",
-			stack_needed, stack_size);
+			nfp_prog->stack_size, max_stack);
 		return -EOPNOTSUPP;
 	}
 

include/linux/bpf.h

@@ -39,6 +39,9 @@ struct bpf_map_ops {
 	void *(*map_lookup_elem)(struct bpf_map *map, void *key);
 	int (*map_update_elem)(struct bpf_map *map, void *key, void *value, u64 flags);
 	int (*map_delete_elem)(struct bpf_map *map, void *key);
+	int (*map_push_elem)(struct bpf_map *map, void *value, u64 flags);
+	int (*map_pop_elem)(struct bpf_map *map, void *value);
+	int (*map_peek_elem)(struct bpf_map *map, void *value);
 
 	/* funcs called by prog_array and perf_event_array map */
 	void *(*map_fd_get_ptr)(struct bpf_map *map, struct file *map_file,
@@ -138,6 +141,7 @@ enum bpf_arg_type {
 	ARG_CONST_MAP_PTR,	/* const argument used as pointer to bpf_map */
 	ARG_PTR_TO_MAP_KEY,	/* pointer to stack used as map key */
 	ARG_PTR_TO_MAP_VALUE,	/* pointer to stack used as map value */
+	ARG_PTR_TO_UNINIT_MAP_VALUE,	/* pointer to valid memory used to store a map value */
 
 	/* the following constraints used to prototype bpf_memcmp() and other
 	 * functions that access data on eBPF program stack
@@ -810,6 +814,9 @@ static inline int bpf_fd_reuseport_array_update_elem(struct bpf_map *map,
 extern const struct bpf_func_proto bpf_map_lookup_elem_proto;
 extern const struct bpf_func_proto bpf_map_update_elem_proto;
 extern const struct bpf_func_proto bpf_map_delete_elem_proto;
+extern const struct bpf_func_proto bpf_map_push_elem_proto;
+extern const struct bpf_func_proto bpf_map_pop_elem_proto;
+extern const struct bpf_func_proto bpf_map_peek_elem_proto;
 
 extern const struct bpf_func_proto bpf_get_prandom_u32_proto;
 extern const struct bpf_func_proto bpf_get_smp_processor_id_proto;

include/linux/bpf_types.h

@@ -51,7 +51,7 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_LRU_HASH, htab_lru_map_ops)
 BPF_MAP_TYPE(BPF_MAP_TYPE_LRU_PERCPU_HASH, htab_lru_percpu_map_ops)
 BPF_MAP_TYPE(BPF_MAP_TYPE_LPM_TRIE, trie_map_ops)
 #ifdef CONFIG_PERF_EVENTS
-BPF_MAP_TYPE(BPF_MAP_TYPE_STACK_TRACE, stack_map_ops)
+BPF_MAP_TYPE(BPF_MAP_TYPE_STACK_TRACE, stack_trace_map_ops)
 #endif
 BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY_OF_MAPS, array_of_maps_map_ops)
 BPF_MAP_TYPE(BPF_MAP_TYPE_HASH_OF_MAPS, htab_of_maps_map_ops)
@@ -69,3 +69,5 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_XSKMAP, xsk_map_ops)
 BPF_MAP_TYPE(BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, reuseport_array_ops)
 #endif
 #endif
+BPF_MAP_TYPE(BPF_MAP_TYPE_QUEUE, queue_map_ops)
+BPF_MAP_TYPE(BPF_MAP_TYPE_STACK, stack_map_ops)

include/linux/filter.h

@@ -548,6 +548,27 @@ static inline void bpf_compute_data_pointers(struct sk_buff *skb)
 	cb->data_end  = skb->data + skb_headlen(skb);
 }
 
+/* Similar to bpf_compute_data_pointers(), except that save orginal
+ * data in cb->data and cb->meta_data for restore.
+ */
+static inline void bpf_compute_and_save_data_end(
+	struct sk_buff *skb, void **saved_data_end)
+{
+	struct bpf_skb_data_end *cb = (struct bpf_skb_data_end *)skb->cb;
+
+	*saved_data_end = cb->data_end;
+	cb->data_end  = skb->data + skb_headlen(skb);
+}
+
+/* Restore data saved by bpf_compute_data_pointers(). */
+static inline void bpf_restore_data_end(
+	struct sk_buff *skb, void *saved_data_end)
+{
+	struct bpf_skb_data_end *cb = (struct bpf_skb_data_end *)skb->cb;
+
+	cb->data_end = saved_data_end;
+}
+
 static inline u8 *bpf_skb_cb(struct sk_buff *skb)
 {
 	/* eBPF programs may read/write skb->cb[] area to transfer meta

include/linux/skmsg.h

@@ -176,6 +176,7 @@ static inline void sk_msg_xfer(struct sk_msg *dst, struct sk_msg *src,
 {
 	dst->sg.data[which] = src->sg.data[which];
 	dst->sg.data[which].length  = size;
+	dst->sg.size		   += size;
 	src->sg.data[which].length -= size;
 	src->sg.data[which].offset += size;
 }
@@ -186,21 +187,29 @@ static inline void sk_msg_xfer_full(struct sk_msg *dst, struct sk_msg *src)
 	sk_msg_init(src);
 }
 
+static inline bool sk_msg_full(const struct sk_msg *msg)
+{
+	return (msg->sg.end == msg->sg.start) && msg->sg.size;
+}
+
 static inline u32 sk_msg_elem_used(const struct sk_msg *msg)
 {
+	if (sk_msg_full(msg))
+		return MAX_MSG_FRAGS;
+
 	return msg->sg.end >= msg->sg.start ?
 		msg->sg.end - msg->sg.start :
 		msg->sg.end + (MAX_MSG_FRAGS - msg->sg.start);
 }
 
-static inline bool sk_msg_full(const struct sk_msg *msg)
+static inline struct scatterlist *sk_msg_elem(struct sk_msg *msg, int which)
 {
-	return (msg->sg.end == msg->sg.start) && msg->sg.size;
+	return &msg->sg.data[which];
 }
 
-static inline struct scatterlist *sk_msg_elem(struct sk_msg *msg, int which)
+static inline struct scatterlist sk_msg_elem_cpy(struct sk_msg *msg, int which)
 {
-	return &msg->sg.data[which];
+	return msg->sg.data[which];
 }
 
 static inline struct page *sk_msg_page(struct sk_msg *msg, int which)
@@ -266,11 +275,6 @@ static inline struct sk_psock *sk_psock(const struct sock *sk)
 	return rcu_dereference_sk_user_data(sk);
 }
 
-static inline bool sk_has_psock(struct sock *sk)
-{
-	return sk_psock(sk) != NULL && sk->sk_prot->recvmsg == tcp_bpf_recvmsg;
-}
-
 static inline void sk_psock_queue_msg(struct sk_psock *psock,
 				      struct sk_msg *msg)
 {
@@ -370,6 +374,26 @@ static inline bool sk_psock_test_state(const struct sk_psock *psock,
 	return test_bit(bit, &psock->state);
 }
 
+static inline struct sk_psock *sk_psock_get_checked(struct sock *sk)
+{
+	struct sk_psock *psock;
+
+	rcu_read_lock();
+	psock = sk_psock(sk);
+	if (psock) {
+		if (sk->sk_prot->recvmsg != tcp_bpf_recvmsg) {
+			psock = ERR_PTR(-EBUSY);
+			goto out;
+		}
+
+		if (!refcount_inc_not_zero(&psock->refcnt))
+			psock = ERR_PTR(-EBUSY);
+	}
+out:
+	rcu_read_unlock();
+	return psock;
+}
+
 static inline struct sk_psock *sk_psock_get(struct sock *sk)
 {
 	struct sk_psock *psock;

include/net/tcp.h

@@ -2051,11 +2051,6 @@ enum hrtimer_restart tcp_pace_kick(struct hrtimer *timer);
 #define TCP_ULP_MAX		128
 #define TCP_ULP_BUF_MAX		(TCP_ULP_NAME_MAX*TCP_ULP_MAX)
 
-enum {
-	TCP_ULP_TLS,
-	TCP_ULP_BPF,
-};
-
 struct tcp_ulp_ops {
 	struct list_head	list;
 
@@ -2064,9 +2059,7 @@ struct tcp_ulp_ops {
 	/* cleanup ulp */
 	void (*release)(struct sock *sk);
 
-	int		uid;
 	char		name[TCP_ULP_NAME_MAX];
-	bool		user_visible;
 	struct module	*owner;
 };
 int tcp_register_ulp(struct tcp_ulp_ops *type);
@@ -2089,7 +2082,7 @@ int tcp_bpf_sendmsg_redir(struct sock *sk, struct sk_msg *msg, u32 bytes,
 int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		    int nonblock, int flags, int *addr_len);
 int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock,
-		      struct msghdr *msg, int len);
+		      struct msghdr *msg, int len, int flags);
 
 /* Call BPF_SOCK_OPS program that returns an int. If the return value
  * is < 0, then the BPF op failed (for example if the loaded BPF

include/uapi/linux/bpf.h

@@ -103,6 +103,7 @@ enum bpf_cmd {
 	BPF_BTF_LOAD,
 	BPF_BTF_GET_FD_BY_ID,
 	BPF_TASK_FD_QUERY,
+	BPF_MAP_LOOKUP_AND_DELETE_ELEM,
 };
 
 enum bpf_map_type {
@@ -128,6 +129,8 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_CGROUP_STORAGE,
 	BPF_MAP_TYPE_REUSEPORT_SOCKARRAY,
 	BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE,
+	BPF_MAP_TYPE_QUEUE,
+	BPF_MAP_TYPE_STACK,
 };
 
 enum bpf_prog_type {
@@ -462,6 +465,28 @@ union bpf_attr {
  * 	Return
  * 		0 on success, or a negative error in case of failure.
  *
+ * int bpf_map_push_elem(struct bpf_map *map, const void *value, u64 flags)
+ * 	Description
+ * 		Push an element *value* in *map*. *flags* is one of:
+ *
+ * 		**BPF_EXIST**
+ * 		If the queue/stack is full, the oldest element is removed to
+ * 		make room for this.
+ * 	Return
+ * 		0 on success, or a negative error in case of failure.
+ *
+ * int bpf_map_pop_elem(struct bpf_map *map, void *value)
+ * 	Description
+ * 		Pop an element from *map*.
+ * Return
+ * 		0 on success, or a negative error in case of failure.
+ *
+ * int bpf_map_peek_elem(struct bpf_map *map, void *value)
+ * 	Description
+ * 		Get an element from *map* without removing it.
+ * Return
+ * 		0 on success, or a negative error in case of failure.
+ *
  * int bpf_probe_read(void *dst, u32 size, const void *src)
  * 	Description
  * 		For tracing programs, safely attempt to read *size* bytes from
@@ -1433,7 +1458,7 @@ union bpf_attr {
  * 	Return
  * 		0 on success, or a negative error in case of failure.
  *
- * int bpf_skb_adjust_room(struct sk_buff *skb, u32 len_diff, u32 mode, u64 flags)
+ * int bpf_skb_adjust_room(struct sk_buff *skb, s32 len_diff, u32 mode, u64 flags)
  * 	Description
  * 		Grow or shrink the room for data in the packet associated to
  * 		*skb* by *len_diff*, and according to the selected *mode*.
@@ -2215,6 +2240,23 @@ union bpf_attr {
  *		pointer that was returned from bpf_sk_lookup_xxx\ ().
  *	Return
  *		0 on success, or a negative error in case of failure.
+ *
+ * int bpf_msg_push_data(struct sk_buff *skb, u32 start, u32 len, u64 flags)
+ *	Description
+ *		For socket policies, insert *len* bytes into msg at offset
+ *		*start*.
+ *
+ *		If a program of type **BPF_PROG_TYPE_SK_MSG** is run on a
+ *		*msg* it may want to insert metadata or options into the msg.
+ *		This can later be read and used by any of the lower layer BPF
+ *		hooks.
+ *
+ *		This helper may fail if under memory pressure (a malloc
+ *		fails) in these cases BPF programs will get an appropriate
+ *		error and BPF programs will need to handle them.
+ *
+ *	Return
+ *		0 on success, or a negative error in case of failure.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -2303,7 +2345,11 @@ union bpf_attr {
 	FN(skb_ancestor_cgroup_id),	\
 	FN(sk_lookup_tcp),		\
 	FN(sk_lookup_udp),		\
-	FN(sk_release),
+	FN(sk_release),			\
+	FN(map_push_elem),		\
+	FN(map_pop_elem),		\
+	FN(map_peek_elem),		\
+	FN(msg_push_data),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call

kernel/bpf/Makefile

@@ -3,7 +3,7 @@ obj-y := core.o
 
 obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o
 obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o
-obj-$(CONFIG_BPF_SYSCALL) += local_storage.o
+obj-$(CONFIG_BPF_SYSCALL) += local_storage.o queue_stack_maps.o
 obj-$(CONFIG_BPF_SYSCALL) += disasm.o
 obj-$(CONFIG_BPF_SYSCALL) += btf.o
 ifeq ($(CONFIG_NET),y)

kernel/bpf/cgroup.c

@@ -553,6 +553,7 @@ int __cgroup_bpf_run_filter_skb(struct sock *sk,
 {
 	unsigned int offset = skb->data - skb_network_header(skb);
 	struct sock *save_sk;
+	void *saved_data_end;
 	struct cgroup *cgrp;
 	int ret;
 
@@ -566,8 +567,13 @@ int __cgroup_bpf_run_filter_skb(struct sock *sk,
 	save_sk = skb->sk;
 	skb->sk = sk;
 	__skb_push(skb, offset);
+
+	/* compute pointers for the bpf prog */
+	bpf_compute_and_save_data_end(skb, &saved_data_end);
+
 	ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], skb,
 				 bpf_prog_run_save_cb);
+	bpf_restore_data_end(skb, saved_data_end);
 	__skb_pull(skb, offset);
 	skb->sk = save_sk;
 	return ret == 1 ? 0 : -EPERM;

kernel/bpf/core.c

@@ -1783,6 +1783,9 @@ BPF_CALL_0(bpf_user_rnd_u32)
 const struct bpf_func_proto bpf_map_lookup_elem_proto __weak;
 const struct bpf_func_proto bpf_map_update_elem_proto __weak;
 const struct bpf_func_proto bpf_map_delete_elem_proto __weak;
+const struct bpf_func_proto bpf_map_push_elem_proto __weak;
+const struct bpf_func_proto bpf_map_pop_elem_proto __weak;
+const struct bpf_func_proto bpf_map_peek_elem_proto __weak;
 
 const struct bpf_func_proto bpf_get_prandom_u32_proto __weak;
 const struct bpf_func_proto bpf_get_smp_processor_id_proto __weak;

kernel/bpf/helpers.c

@@ -76,6 +76,49 @@ const struct bpf_func_proto bpf_map_delete_elem_proto = {
 	.arg2_type	= ARG_PTR_TO_MAP_KEY,
 };
 
+BPF_CALL_3(bpf_map_push_elem, struct bpf_map *, map, void *, value, u64, flags)
+{
+	return map->ops->map_push_elem(map, value, flags);
+}
+
+const struct bpf_func_proto bpf_map_push_elem_proto = {
+	.func		= bpf_map_push_elem,
+	.gpl_only	= false,
+	.pkt_access	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_CONST_MAP_PTR,
+	.arg2_type	= ARG_PTR_TO_MAP_VALUE,
+	.arg3_type	= ARG_ANYTHING,
+};
+
+BPF_CALL_2(bpf_map_pop_elem, struct bpf_map *, map, void *, value)
+{
+	return map->ops->map_pop_elem(map, value);
+}
+
+const struct bpf_func_proto bpf_map_pop_elem_proto = {
+	.func		= bpf_map_pop_elem,
+	.gpl_only	= false,
+	.pkt_access	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_CONST_MAP_PTR,
+	.arg2_type	= ARG_PTR_TO_UNINIT_MAP_VALUE,
+};
+
+BPF_CALL_2(bpf_map_peek_elem, struct bpf_map *, map, void *, value)
+{
+	return map->ops->map_peek_elem(map, value);
+}
+
+const struct bpf_func_proto bpf_map_peek_elem_proto = {
+	.func		= bpf_map_pop_elem,
+	.gpl_only	= false,
+	.pkt_access	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_CONST_MAP_PTR,
+	.arg2_type	= ARG_PTR_TO_UNINIT_MAP_VALUE,
+};
+
 const struct bpf_func_proto bpf_get_prandom_u32_proto = {
 	.func		= bpf_user_rnd_u32,
 	.gpl_only	= false,

kernel/bpf/queue_stack_maps.c

@@ -0,0 +1,288 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * queue_stack_maps.c: BPF queue and stack maps
+ *
+ * Copyright (c) 2018 Politecnico di Torino
+ */
+#include <linux/bpf.h>
+#include <linux/list.h>
+#include <linux/slab.h>
+#include "percpu_freelist.h"
+
+#define QUEUE_STACK_CREATE_FLAG_MASK \
+	(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)
+
+
+struct bpf_queue_stack {
+	struct bpf_map map;
+	raw_spinlock_t lock;
+	u32 head, tail;
+	u32 size; /* max_entries + 1 */
+
+	char elements[0] __aligned(8);
+};
+
+static struct bpf_queue_stack *bpf_queue_stack(struct bpf_map *map)
+{
+	return container_of(map, struct bpf_queue_stack, map);
+}
+
+static bool queue_stack_map_is_empty(struct bpf_queue_stack *qs)
+{
+	return qs->head == qs->tail;
+}
+
+static bool queue_stack_map_is_full(struct bpf_queue_stack *qs)
+{
+	u32 head = qs->head + 1;
+
+	if (unlikely(head >= qs->size))
+		head = 0;
+
+	return head == qs->tail;
+}
+
+/* Called from syscall */
+static int queue_stack_map_alloc_check(union bpf_attr *attr)
+{
+	/* check sanity of attributes */
+	if (attr->max_entries == 0 || attr->key_size != 0 ||
+	    attr->map_flags & ~QUEUE_STACK_CREATE_FLAG_MASK)
+		return -EINVAL;
+
+	if (attr->value_size > KMALLOC_MAX_SIZE)
+		/* if value_size is bigger, the user space won't be able to
+		 * access the elements.
+		 */
+		return -E2BIG;
+
+	return 0;
+}
+
+static struct bpf_map *queue_stack_map_alloc(union bpf_attr *attr)
+{
+	int ret, numa_node = bpf_map_attr_numa_node(attr);
+	struct bpf_queue_stack *qs;
+	u32 size, value_size;
+	u64 queue_size, cost;
+
+	size = attr->max_entries + 1;
+	value_size = attr->value_size;
+
+	queue_size = sizeof(*qs) + (u64) value_size * size;
+
+	cost = queue_size;
+	if (cost >= U32_MAX - PAGE_SIZE)
+		return ERR_PTR(-E2BIG);
+
+	cost = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT;
+
+	ret = bpf_map_precharge_memlock(cost);
+	if (ret < 0)
+		return ERR_PTR(ret);
+
+	qs = bpf_map_area_alloc(queue_size, numa_node);
+	if (!qs)
+		return ERR_PTR(-ENOMEM);
+
+	memset(qs, 0, sizeof(*qs));
+
+	bpf_map_init_from_attr(&qs->map, attr);
+
+	qs->map.pages = cost;
+	qs->size = size;
+
+	raw_spin_lock_init(&qs->lock);
+
+	return &qs->map;
+}
+
+/* Called when map->refcnt goes to zero, either from workqueue or from syscall */
+static void queue_stack_map_free(struct bpf_map *map)
+{
+	struct bpf_queue_stack *qs = bpf_queue_stack(map);
+
+	/* at this point bpf_prog->aux->refcnt == 0 and this map->refcnt == 0,
+	 * so the programs (can be more than one that used this map) were
+	 * disconnected from events. Wait for outstanding critical sections in
+	 * these programs to complete
+	 */
+	synchronize_rcu();
+
+	bpf_map_area_free(qs);
+}
+
+static int __queue_map_get(struct bpf_map *map, void *value, bool delete)
+{
+	struct bpf_queue_stack *qs = bpf_queue_stack(map);
+	unsigned long flags;
+	int err = 0;
+	void *ptr;
+
+	raw_spin_lock_irqsave(&qs->lock, flags);
+
+	if (queue_stack_map_is_empty(qs)) {
+		err = -ENOENT;
+		goto out;
+	}
+
+	ptr = &qs->elements[qs->tail * qs->map.value_size];
+	memcpy(value, ptr, qs->map.value_size);
+
+	if (delete) {
+		if (unlikely(++qs->tail >= qs->size))
+			qs->tail = 0;
+	}
+
+out:
+	raw_spin_unlock_irqrestore(&qs->lock, flags);
+	return err;
+}
+
+
+static int __stack_map_get(struct bpf_map *map, void *value, bool delete)
+{
+	struct bpf_queue_stack *qs = bpf_queue_stack(map);
+	unsigned long flags;
+	int err = 0;
+	void *ptr;
+	u32 index;
+
+	raw_spin_lock_irqsave(&qs->lock, flags);
+
+	if (queue_stack_map_is_empty(qs)) {
+		err = -ENOENT;
+		goto out;
+	}
+
+	index = qs->head - 1;
+	if (unlikely(index >= qs->size))
+		index = qs->size - 1;
+
+	ptr = &qs->elements[index * qs->map.value_size];
+	memcpy(value, ptr, qs->map.value_size);
+
+	if (delete)
+		qs->head = index;
+
+out:
+	raw_spin_unlock_irqrestore(&qs->lock, flags);
+	return err;
+}
+
+/* Called from syscall or from eBPF program */
+static int queue_map_peek_elem(struct bpf_map *map, void *value)
+{
+	return __queue_map_get(map, value, false);
+}
+
+/* Called from syscall or from eBPF program */
+static int stack_map_peek_elem(struct bpf_map *map, void *value)
+{
+	return __stack_map_get(map, value, false);
+}
+
+/* Called from syscall or from eBPF program */
+static int queue_map_pop_elem(struct bpf_map *map, void *value)
+{
+	return __queue_map_get(map, value, true);
+}
+
+/* Called from syscall or from eBPF program */
+static int stack_map_pop_elem(struct bpf_map *map, void *value)
+{
+	return __stack_map_get(map, value, true);
+}
+
+/* Called from syscall or from eBPF program */
+static int queue_stack_map_push_elem(struct bpf_map *map, void *value,
+				     u64 flags)
+{
+	struct bpf_queue_stack *qs = bpf_queue_stack(map);
+	unsigned long irq_flags;
+	int err = 0;
+	void *dst;
+
+	/* BPF_EXIST is used to force making room for a new element in case the
+	 * map is full
+	 */
+	bool replace = (flags & BPF_EXIST);
+
+	/* Check supported flags for queue and stack maps */
+	if (flags & BPF_NOEXIST || flags > BPF_EXIST)
+		return -EINVAL;
+
+	raw_spin_lock_irqsave(&qs->lock, irq_flags);
+
+	if (queue_stack_map_is_full(qs)) {
+		if (!replace) {
+			err = -E2BIG;
+			goto out;
+		}
+		/* advance tail pointer to overwrite oldest element */
+		if (unlikely(++qs->tail >= qs->size))
+			qs->tail = 0;
+	}
+
+	dst = &qs->elements[qs->head * qs->map.value_size];
+	memcpy(dst, value, qs->map.value_size);
+
+	if (unlikely(++qs->head >= qs->size))
+		qs->head = 0;
+
+out:
+	raw_spin_unlock_irqrestore(&qs->lock, irq_flags);
+	return err;
+}
+
+/* Called from syscall or from eBPF program */
+static void *queue_stack_map_lookup_elem(struct bpf_map *map, void *key)
+{
+	return NULL;
+}
+
+/* Called from syscall or from eBPF program */
+static int queue_stack_map_update_elem(struct bpf_map *map, void *key,
+				       void *value, u64 flags)
+{
+	return -EINVAL;
+}
+
+/* Called from syscall or from eBPF program */
+static int queue_stack_map_delete_elem(struct bpf_map *map, void *key)
+{
+	return -EINVAL;
+}
+
+/* Called from syscall */
+static int queue_stack_map_get_next_key(struct bpf_map *map, void *key,
+					void *next_key)
+{
+	return -EINVAL;
+}
+
+const struct bpf_map_ops queue_map_ops = {
+	.map_alloc_check = queue_stack_map_alloc_check,
+	.map_alloc = queue_stack_map_alloc,
+	.map_free = queue_stack_map_free,
+	.map_lookup_elem = queue_stack_map_lookup_elem,
+	.map_update_elem = queue_stack_map_update_elem,
+	.map_delete_elem = queue_stack_map_delete_elem,
+	.map_push_elem = queue_stack_map_push_elem,
+	.map_pop_elem = queue_map_pop_elem,
+	.map_peek_elem = queue_map_peek_elem,
+	.map_get_next_key = queue_stack_map_get_next_key,
+};
+
+const struct bpf_map_ops stack_map_ops = {
+	.map_alloc_check = queue_stack_map_alloc_check,
+	.map_alloc = queue_stack_map_alloc,
+	.map_free = queue_stack_map_free,
+	.map_lookup_elem = queue_stack_map_lookup_elem,
+	.map_update_elem = queue_stack_map_update_elem,
+	.map_delete_elem = queue_stack_map_delete_elem,
+	.map_push_elem = queue_stack_map_push_elem,
+	.map_pop_elem = stack_map_pop_elem,
+	.map_peek_elem = stack_map_peek_elem,
+	.map_get_next_key = queue_stack_map_get_next_key,
+};

kernel/bpf/stackmap.c

@@ -600,7 +600,7 @@ static void stack_map_free(struct bpf_map *map)
 	put_callchain_buffers();
 }
 
-const struct bpf_map_ops stack_map_ops = {
+const struct bpf_map_ops stack_trace_map_ops = {
 	.map_alloc = stack_map_alloc,
 	.map_free = stack_map_free,
 	.map_get_next_key = stack_map_get_next_key,

kernel/bpf/syscall.c

@@ -651,6 +651,17 @@ int __weak bpf_stackmap_copy(struct bpf_map *map, void *key, void *value)
 	return -ENOTSUPP;
 }
 
+static void *__bpf_copy_key(void __user *ukey, u64 key_size)
+{
+	if (key_size)
+		return memdup_user(ukey, key_size);
+
+	if (ukey)
+		return ERR_PTR(-EINVAL);
+
+	return NULL;
+}
+
 /* last field in 'union bpf_attr' used by this command */
 #define BPF_MAP_LOOKUP_ELEM_LAST_FIELD value
 
@@ -678,7 +689,7 @@ static int map_lookup_elem(union bpf_attr *attr)
 		goto err_put;
 	}
 
-	key = memdup_user(ukey, map->key_size);
+	key = __bpf_copy_key(ukey, map->key_size);
 	if (IS_ERR(key)) {
 		err = PTR_ERR(key);
 		goto err_put;
@@ -716,6 +727,9 @@ static int map_lookup_elem(union bpf_attr *attr)
 		err = bpf_fd_htab_map_lookup_elem(map, key, value);
 	} else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) {
 		err = bpf_fd_reuseport_array_lookup_elem(map, key, value);
+	} else if (map->map_type == BPF_MAP_TYPE_QUEUE ||
+		   map->map_type == BPF_MAP_TYPE_STACK) {
+		err = map->ops->map_peek_elem(map, value);
 	} else {
 		rcu_read_lock();
 		ptr = map->ops->map_lookup_elem(map, key);
@@ -785,7 +799,7 @@ static int map_update_elem(union bpf_attr *attr)
 		goto err_put;
 	}
 
-	key = memdup_user(ukey, map->key_size);
+	key = __bpf_copy_key(ukey, map->key_size);
 	if (IS_ERR(key)) {
 		err = PTR_ERR(key);
 		goto err_put;
@@ -846,6 +860,9 @@ static int map_update_elem(union bpf_attr *attr)
 		/* rcu_read_lock() is not needed */
 		err = bpf_fd_reuseport_array_update_elem(map, key, value,
 							 attr->flags);
+	} else if (map->map_type == BPF_MAP_TYPE_QUEUE ||
+		   map->map_type == BPF_MAP_TYPE_STACK) {
+		err = map->ops->map_push_elem(map, value, attr->flags);
 	} else {
 		rcu_read_lock();
 		err = map->ops->map_update_elem(map, key, value, attr->flags);
@@ -888,7 +905,7 @@ static int map_delete_elem(union bpf_attr *attr)
 		goto err_put;
 	}
 
-	key = memdup_user(ukey, map->key_size);
+	key = __bpf_copy_key(ukey, map->key_size);
 	if (IS_ERR(key)) {
 		err = PTR_ERR(key);
 		goto err_put;
@@ -941,7 +958,7 @@ static int map_get_next_key(union bpf_attr *attr)
 	}
 
 	if (ukey) {
-		key = memdup_user(ukey, map->key_size);
+		key = __bpf_copy_key(ukey, map->key_size);
 		if (IS_ERR(key)) {
 			err = PTR_ERR(key);
 			goto err_put;
@@ -982,6 +999,69 @@ err_put:
 	return err;
 }
 
+#define BPF_MAP_LOOKUP_AND_DELETE_ELEM_LAST_FIELD value
+
+static int map_lookup_and_delete_elem(union bpf_attr *attr)
+{
+	void __user *ukey = u64_to_user_ptr(attr->key);
+	void __user *uvalue = u64_to_user_ptr(attr->value);
+	int ufd = attr->map_fd;
+	struct bpf_map *map;
+	void *key, *value;
+	u32 value_size;
+	struct fd f;
+	int err;
+
+	if (CHECK_ATTR(BPF_MAP_LOOKUP_AND_DELETE_ELEM))
+		return -EINVAL;
+
+	f = fdget(ufd);
+	map = __bpf_map_get(f);
+	if (IS_ERR(map))
+		return PTR_ERR(map);
+
+	if (!(f.file->f_mode & FMODE_CAN_WRITE)) {
+		err = -EPERM;
+		goto err_put;
+	}
+
+	key = __bpf_copy_key(ukey, map->key_size);
+	if (IS_ERR(key)) {
+		err = PTR_ERR(key);
+		goto err_put;
+	}
+
+	value_size = map->value_size;
+
+	err = -ENOMEM;
+	value = kmalloc(value_size, GFP_USER | __GFP_NOWARN);
+	if (!value)
+		goto free_key;
+
+	if (map->map_type == BPF_MAP_TYPE_QUEUE ||
+	    map->map_type == BPF_MAP_TYPE_STACK) {
+		err = map->ops->map_pop_elem(map, value);
+	} else {
+		err = -ENOTSUPP;
+	}
+
+	if (err)
+		goto free_value;
+
+	if (copy_to_user(uvalue, value, value_size) != 0)
+		goto free_value;
+
+	err = 0;
+
+free_value:
+	kfree(value);
+free_key:
+	kfree(key);
+err_put:
+	fdput(f);
+	return err;
+}
+
 static const struct bpf_prog_ops * const bpf_prog_types[] = {
 #define BPF_PROG_TYPE(_id, _name) \
 	[_id] = & _name ## _prog_ops,
@@ -2455,6 +2535,9 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
 	case BPF_TASK_FD_QUERY:
 		err = bpf_task_fd_query(&attr, uattr);
 		break;
+	case BPF_MAP_LOOKUP_AND_DELETE_ELEM:
+		err = map_lookup_and_delete_elem(&attr);
+		break;
 	default:
 		err = -EINVAL;
 		break;

kernel/bpf/verifier.c

@@ -1528,14 +1528,19 @@ static bool __is_pointer_value(bool allow_ptr_leaks,
 	return reg->type != SCALAR_VALUE;
 }
 
+static struct bpf_reg_state *reg_state(struct bpf_verifier_env *env, int regno)
+{
+	return cur_regs(env) + regno;
+}
+
 static bool is_pointer_value(struct bpf_verifier_env *env, int regno)
 {
-	return __is_pointer_value(env->allow_ptr_leaks, cur_regs(env) + regno);
+	return __is_pointer_value(env->allow_ptr_leaks, reg_state(env, regno));
 }
 
 static bool is_ctx_reg(struct bpf_verifier_env *env, int regno)
 {
-	const struct bpf_reg_state *reg = cur_regs(env) + regno;
+	const struct bpf_reg_state *reg = reg_state(env, regno);
 
 	return reg->type == PTR_TO_CTX ||
 	       reg->type == PTR_TO_SOCKET;
@@ -1543,11 +1548,19 @@ static bool is_ctx_reg(struct bpf_verifier_env *env, int regno)
 
 static bool is_pkt_reg(struct bpf_verifier_env *env, int regno)
 {
-	const struct bpf_reg_state *reg = cur_regs(env) + regno;
+	const struct bpf_reg_state *reg = reg_state(env, regno);
 
 	return type_is_pkt_pointer(reg->type);
 }
 
+static bool is_flow_key_reg(struct bpf_verifier_env *env, int regno)
+{
+	const struct bpf_reg_state *reg = reg_state(env, regno);
+
+	/* Separate to is_ctx_reg() since we still want to allow BPF_ST here. */
+	return reg->type == PTR_TO_FLOW_KEYS;
+}
+
 static int check_pkt_ptr_alignment(struct bpf_verifier_env *env,
 				   const struct bpf_reg_state *reg,
 				   int off, int size, bool strict)
@@ -1956,9 +1969,11 @@ static int check_xadd(struct bpf_verifier_env *env, int insn_idx, struct bpf_ins
 	}
 
 	if (is_ctx_reg(env, insn->dst_reg) ||
-	    is_pkt_reg(env, insn->dst_reg)) {
+	    is_pkt_reg(env, insn->dst_reg) ||
+	    is_flow_key_reg(env, insn->dst_reg)) {
 		verbose(env, "BPF_XADD stores into R%d %s is not allowed\n",
-			insn->dst_reg, reg_type_str[insn->dst_reg]);
+			insn->dst_reg,
+			reg_type_str[reg_state(env, insn->dst_reg)->type]);
 		return -EACCES;
 	}
 
@@ -1983,7 +1998,7 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno,
 				int access_size, bool zero_size_allowed,
 				struct bpf_call_arg_meta *meta)
 {
-	struct bpf_reg_state *reg = cur_regs(env) + regno;
+	struct bpf_reg_state *reg = reg_state(env, regno);
 	struct bpf_func_state *state = func(env, reg);
 	int off, i, slot, spi;
 
@@ -2062,8 +2077,6 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno,
 	case PTR_TO_PACKET_META:
 		return check_packet_access(env, regno, reg->off, access_size,
 					   zero_size_allowed);
-	case PTR_TO_FLOW_KEYS:
-		return check_flow_keys_access(env, reg->off, access_size);
 	case PTR_TO_MAP_VALUE:
 		return check_map_access(env, regno, reg->off, access_size,
 					zero_size_allowed);
@@ -2117,7 +2130,8 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
 	}
 
 	if (arg_type == ARG_PTR_TO_MAP_KEY ||
-	    arg_type == ARG_PTR_TO_MAP_VALUE) {
+	    arg_type == ARG_PTR_TO_MAP_VALUE ||
+	    arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE) {
 		expected_type = PTR_TO_STACK;
 		if (!type_is_pkt_pointer(type) && type != PTR_TO_MAP_VALUE &&
 		    type != expected_type)
@@ -2187,7 +2201,8 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
 		err = check_helper_mem_access(env, regno,
 					      meta->map_ptr->key_size, false,
 					      NULL);
-	} else if (arg_type == ARG_PTR_TO_MAP_VALUE) {
+	} else if (arg_type == ARG_PTR_TO_MAP_VALUE ||
+		   arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE) {
 		/* bpf_map_xxx(..., map_ptr, ..., value) call:
 		 * check [value, value + map->value_size) validity
 		 */
@@ -2196,9 +2211,10 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
 			verbose(env, "invalid map_ptr to access map->value\n");
 			return -EACCES;
 		}
+		meta->raw_mode = (arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE);
 		err = check_helper_mem_access(env, regno,
 					      meta->map_ptr->value_size, false,
-					      NULL);
+					      meta);
 	} else if (arg_type_is_mem_size(arg_type)) {
 		bool zero_size_allowed = (arg_type == ARG_CONST_SIZE_OR_ZERO);
 
@@ -2321,6 +2337,13 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
 		if (func_id != BPF_FUNC_sk_select_reuseport)
 			goto error;
 		break;
+	case BPF_MAP_TYPE_QUEUE:
+	case BPF_MAP_TYPE_STACK:
+		if (func_id != BPF_FUNC_map_peek_elem &&
+		    func_id != BPF_FUNC_map_pop_elem &&
+		    func_id != BPF_FUNC_map_push_elem)
+			goto error;
+		break;
 	default:
 		break;
 	}
@@ -2377,6 +2400,13 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
 		if (map->map_type != BPF_MAP_TYPE_REUSEPORT_SOCKARRAY)
 			goto error;
 		break;
+	case BPF_FUNC_map_peek_elem:
+	case BPF_FUNC_map_pop_elem:
+	case BPF_FUNC_map_push_elem:
+		if (map->map_type != BPF_MAP_TYPE_QUEUE &&
+		    map->map_type != BPF_MAP_TYPE_STACK)
+			goto error;
+		break;
 	default:
 		break;
 	}
@@ -2672,7 +2702,10 @@ record_func_map(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta,
 	if (func_id != BPF_FUNC_tail_call &&
 	    func_id != BPF_FUNC_map_lookup_elem &&
 	    func_id != BPF_FUNC_map_update_elem &&
-	    func_id != BPF_FUNC_map_delete_elem)
+	    func_id != BPF_FUNC_map_delete_elem &&
+	    func_id != BPF_FUNC_map_push_elem &&
+	    func_id != BPF_FUNC_map_pop_elem &&
+	    func_id != BPF_FUNC_map_peek_elem)
 		return 0;
 
 	if (meta->map_ptr == NULL) {
@@ -5244,7 +5277,8 @@ static int do_check(struct bpf_verifier_env *env)
 
 			if (is_ctx_reg(env, insn->dst_reg)) {
 				verbose(env, "BPF_ST stores into R%d %s is not allowed\n",
-					insn->dst_reg, reg_type_str[insn->dst_reg]);
+					insn->dst_reg,
+					reg_type_str[reg_state(env, insn->dst_reg)->type]);
 				return -EACCES;
 			}
 
@@ -6144,7 +6178,10 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env)
 		if (prog->jit_requested && BITS_PER_LONG == 64 &&
 		    (insn->imm == BPF_FUNC_map_lookup_elem ||
 		     insn->imm == BPF_FUNC_map_update_elem ||
-		     insn->imm == BPF_FUNC_map_delete_elem)) {
+		     insn->imm == BPF_FUNC_map_delete_elem ||
+		     insn->imm == BPF_FUNC_map_push_elem   ||
+		     insn->imm == BPF_FUNC_map_pop_elem    ||
+		     insn->imm == BPF_FUNC_map_peek_elem)) {
 			aux = &env->insn_aux_data[i + delta];
 			if (bpf_map_ptr_poisoned(aux))
 				goto patch_call_imm;
@@ -6177,6 +6214,14 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env)
 			BUILD_BUG_ON(!__same_type(ops->map_update_elem,
 				     (int (*)(struct bpf_map *map, void *key, void *value,
 					      u64 flags))NULL));
+			BUILD_BUG_ON(!__same_type(ops->map_push_elem,
+				     (int (*)(struct bpf_map *map, void *value,
+					      u64 flags))NULL));
+			BUILD_BUG_ON(!__same_type(ops->map_pop_elem,
+				     (int (*)(struct bpf_map *map, void *value))NULL));
+			BUILD_BUG_ON(!__same_type(ops->map_peek_elem,
+				     (int (*)(struct bpf_map *map, void *value))NULL));
+
 			switch (insn->imm) {
 			case BPF_FUNC_map_lookup_elem:
 				insn->imm = BPF_CAST_CALL(ops->map_lookup_elem) -
@@ -6190,6 +6235,18 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env)
 				insn->imm = BPF_CAST_CALL(ops->map_delete_elem) -
 					    __bpf_call_base;
 				continue;
+			case BPF_FUNC_map_push_elem:
+				insn->imm = BPF_CAST_CALL(ops->map_push_elem) -
+					    __bpf_call_base;
+				continue;
+			case BPF_FUNC_map_pop_elem:
+				insn->imm = BPF_CAST_CALL(ops->map_pop_elem) -
+					    __bpf_call_base;
+				continue;
+			case BPF_FUNC_map_peek_elem:
+				insn->imm = BPF_CAST_CALL(ops->map_peek_elem) -
+					    __bpf_call_base;
+				continue;
 			}
 
 			goto patch_call_imm;

net/bpf/test_run.c

@@ -10,6 +10,8 @@
 #include <linux/etherdevice.h>
 #include <linux/filter.h>
 #include <linux/sched/signal.h>
+#include <net/sock.h>
+#include <net/tcp.h>
 
 static __always_inline u32 bpf_test_run_one(struct bpf_prog *prog, void *ctx,
 		struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE])
@@ -115,6 +117,7 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
 	u32 retval, duration;
 	int hh_len = ETH_HLEN;
 	struct sk_buff *skb;
+	struct sock *sk;
 	void *data;
 	int ret;
 
@@ -137,11 +140,21 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
 		break;
 	}
 
+	sk = kzalloc(sizeof(struct sock), GFP_USER);
+	if (!sk) {
+		kfree(data);
+		return -ENOMEM;
+	}
+	sock_net_set(sk, current->nsproxy->net_ns);
+	sock_init_data(NULL, sk);
+
 	skb = build_skb(data, 0);
 	if (!skb) {
 		kfree(data);
+		kfree(sk);
 		return -ENOMEM;
 	}
+	skb->sk = sk;
 
 	skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN);
 	__skb_put(skb, size);
@@ -159,6 +172,7 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
 
 			if (pskb_expand_head(skb, nhead, 0, GFP_USER)) {
 				kfree_skb(skb);
+				kfree(sk);
 				return -ENOMEM;
 			}
 		}
@@ -171,6 +185,7 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
 		size = skb_headlen(skb);
 	ret = bpf_test_finish(kattr, uattr, skb->data, size, retval, duration);
 	kfree_skb(skb);
+	kfree(sk);
 	return ret;
 }
 

net/core/filter.c

@@ -2297,6 +2297,137 @@ static const struct bpf_func_proto bpf_msg_pull_data_proto = {
 	.arg4_type	= ARG_ANYTHING,
 };
 
+BPF_CALL_4(bpf_msg_push_data, struct sk_msg *, msg, u32, start,
+	   u32, len, u64, flags)
+{
+	struct scatterlist sge, nsge, nnsge, rsge = {0}, *psge;
+	u32 new, i = 0, l, space, copy = 0, offset = 0;
+	u8 *raw, *to, *from;
+	struct page *page;
+
+	if (unlikely(flags))
+		return -EINVAL;
+
+	/* First find the starting scatterlist element */
+	i = msg->sg.start;
+	do {
+		l = sk_msg_elem(msg, i)->length;
+
+		if (start < offset + l)
+			break;
+		offset += l;
+		sk_msg_iter_var_next(i);
+	} while (i != msg->sg.end);
+
+	if (start >= offset + l)
+		return -EINVAL;
+
+	space = MAX_MSG_FRAGS - sk_msg_elem_used(msg);
+
+	/* If no space available will fallback to copy, we need at
+	 * least one scatterlist elem available to push data into
+	 * when start aligns to the beginning of an element or two
+	 * when it falls inside an element. We handle the start equals
+	 * offset case because its the common case for inserting a
+	 * header.
+	 */
+	if (!space || (space == 1 && start != offset))
+		copy = msg->sg.data[i].length;
+
+	page = alloc_pages(__GFP_NOWARN | GFP_ATOMIC | __GFP_COMP,
+			   get_order(copy + len));
+	if (unlikely(!page))
+		return -ENOMEM;
+
+	if (copy) {
+		int front, back;
+
+		raw = page_address(page);
+
+		psge = sk_msg_elem(msg, i);
+		front = start - offset;
+		back = psge->length - front;
+		from = sg_virt(psge);
+
+		if (front)
+			memcpy(raw, from, front);
+
+		if (back) {
+			from += front;
+			to = raw + front + len;
+
+			memcpy(to, from, back);
+		}
+
+		put_page(sg_page(psge));
+	} else if (start - offset) {
+		psge = sk_msg_elem(msg, i);
+		rsge = sk_msg_elem_cpy(msg, i);
+
+		psge->length = start - offset;
+		rsge.length -= psge->length;
+		rsge.offset += start;
+
+		sk_msg_iter_var_next(i);
+		sg_unmark_end(psge);
+		sk_msg_iter_next(msg, end);
+	}
+
+	/* Slot(s) to place newly allocated data */
+	new = i;
+
+	/* Shift one or two slots as needed */
+	if (!copy) {
+		sge = sk_msg_elem_cpy(msg, i);
+
+		sk_msg_iter_var_next(i);
+		sg_unmark_end(&sge);
+		sk_msg_iter_next(msg, end);
+
+		nsge = sk_msg_elem_cpy(msg, i);
+		if (rsge.length) {
+			sk_msg_iter_var_next(i);
+			nnsge = sk_msg_elem_cpy(msg, i);
+		}
+
+		while (i != msg->sg.end) {
+			msg->sg.data[i] = sge;
+			sge = nsge;
+			sk_msg_iter_var_next(i);
+			if (rsge.length) {
+				nsge = nnsge;
+				nnsge = sk_msg_elem_cpy(msg, i);
+			} else {
+				nsge = sk_msg_elem_cpy(msg, i);
+			}
+		}
+	}
+
+	/* Place newly allocated data buffer */
+	sk_mem_charge(msg->sk, len);
+	msg->sg.size += len;
+	msg->sg.copy[new] = false;
+	sg_set_page(&msg->sg.data[new], page, len + copy, 0);
+	if (rsge.length) {
+		get_page(sg_page(&rsge));
+		sk_msg_iter_var_next(new);
+		msg->sg.data[new] = rsge;
+	}
+
+	sk_msg_compute_data_pointers(msg);
+	return 0;
+}
+
+static const struct bpf_func_proto bpf_msg_push_data_proto = {
+	.func		= bpf_msg_push_data,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_ANYTHING,
+	.arg3_type	= ARG_ANYTHING,
+	.arg4_type	= ARG_ANYTHING,
+};
+
 BPF_CALL_1(bpf_get_cgroup_classid, const struct sk_buff *, skb)
 {
 	return task_get_classid(skb);
@@ -4854,6 +4985,7 @@ bool bpf_helper_changes_pkt_data(void *func)
 	    func == bpf_xdp_adjust_head ||
 	    func == bpf_xdp_adjust_meta ||
 	    func == bpf_msg_pull_data ||
+	    func == bpf_msg_push_data ||
 	    func == bpf_xdp_adjust_tail ||
 #if IS_ENABLED(CONFIG_IPV6_SEG6_BPF)
 	    func == bpf_lwt_seg6_store_bytes ||
@@ -4876,6 +5008,12 @@ bpf_base_func_proto(enum bpf_func_id func_id)
 		return &bpf_map_update_elem_proto;
 	case BPF_FUNC_map_delete_elem:
 		return &bpf_map_delete_elem_proto;
+	case BPF_FUNC_map_push_elem:
+		return &bpf_map_push_elem_proto;
+	case BPF_FUNC_map_pop_elem:
+		return &bpf_map_pop_elem_proto;
+	case BPF_FUNC_map_peek_elem:
+		return &bpf_map_peek_elem_proto;
 	case BPF_FUNC_get_prandom_u32:
 		return &bpf_get_prandom_u32_proto;
 	case BPF_FUNC_get_smp_processor_id:
@@ -5124,6 +5262,8 @@ sk_msg_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_msg_cork_bytes_proto;
 	case BPF_FUNC_msg_pull_data:
 		return &bpf_msg_pull_data_proto;
+	case BPF_FUNC_msg_push_data:
+		return &bpf_msg_push_data_proto;
 	case BPF_FUNC_get_local_storage:
 		return &bpf_get_local_storage_proto;
 	default:
@@ -5346,6 +5486,40 @@ static bool sk_filter_is_valid_access(int off, int size,
 	return bpf_skb_is_valid_access(off, size, type, prog, info);
 }
 
+static bool cg_skb_is_valid_access(int off, int size,
+				   enum bpf_access_type type,
+				   const struct bpf_prog *prog,
+				   struct bpf_insn_access_aux *info)
+{
+	switch (off) {
+	case bpf_ctx_range(struct __sk_buff, tc_classid):
+	case bpf_ctx_range(struct __sk_buff, data_meta):
+	case bpf_ctx_range(struct __sk_buff, flow_keys):
+		return false;
+	}
+	if (type == BPF_WRITE) {
+		switch (off) {
+		case bpf_ctx_range(struct __sk_buff, mark):
+		case bpf_ctx_range(struct __sk_buff, priority):
+		case bpf_ctx_range_till(struct __sk_buff, cb[0], cb[4]):
+			break;
+		default:
+			return false;
+		}
+	}
+
+	switch (off) {
+	case bpf_ctx_range(struct __sk_buff, data):
+		info->reg_type = PTR_TO_PACKET;
+		break;
+	case bpf_ctx_range(struct __sk_buff, data_end):
+		info->reg_type = PTR_TO_PACKET_END;
+		break;
+	}
+
+	return bpf_skb_is_valid_access(off, size, type, prog, info);
+}
+
 static bool lwt_is_valid_access(int off, int size,
 				enum bpf_access_type type,
 				const struct bpf_prog *prog,
@@ -7038,7 +7212,7 @@ const struct bpf_prog_ops xdp_prog_ops = {
 
 const struct bpf_verifier_ops cg_skb_verifier_ops = {
 	.get_func_proto		= cg_skb_func_proto,
-	.is_valid_access	= sk_filter_is_valid_access,
+	.is_valid_access	= cg_skb_is_valid_access,
 	.convert_ctx_access	= bpf_convert_ctx_access,
 };
 

net/core/sock_map.c

@@ -175,12 +175,13 @@ static int sock_map_link(struct bpf_map *map, struct sk_psock_progs *progs,
 		}
 	}
 
-	psock = sk_psock_get(sk);
+	psock = sk_psock_get_checked(sk);
+	if (IS_ERR(psock)) {
+		ret = PTR_ERR(psock);
+		goto out_progs;
+	}
+
 	if (psock) {
-		if (!sk_has_psock(sk)) {
-			ret = -EBUSY;
-			goto out_progs;
-		}
 		if ((msg_parser && READ_ONCE(psock->progs.msg_parser)) ||
 		    (skb_progs  && READ_ONCE(psock->progs.skb_parser))) {
 			sk_psock_put(sk, psock);

net/ipv4/tcp_bpf.c

@@ -39,17 +39,19 @@ static int tcp_bpf_wait_data(struct sock *sk, struct sk_psock *psock,
 }
 
 int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock,
-		      struct msghdr *msg, int len)
+		      struct msghdr *msg, int len, int flags)
 {
 	struct iov_iter *iter = &msg->msg_iter;
+	int peek = flags & MSG_PEEK;
 	int i, ret, copied = 0;
+	struct sk_msg *msg_rx;
+
+	msg_rx = list_first_entry_or_null(&psock->ingress_msg,
+					  struct sk_msg, list);
 
 	while (copied != len) {
 		struct scatterlist *sge;
-		struct sk_msg *msg_rx;
 
-		msg_rx = list_first_entry_or_null(&psock->ingress_msg,
-						  struct sk_msg, list);
 		if (unlikely(!msg_rx))
 			break;
 
@@ -70,21 +72,30 @@ int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock,
 			}
 
 			copied += copy;
-			sge->offset += copy;
-			sge->length -= copy;
-			sk_mem_uncharge(sk, copy);
-			if (!sge->length) {
-				i++;
-				if (i == MAX_SKB_FRAGS)
-					i = 0;
-				if (!msg_rx->skb)
-					put_page(page);
+			if (likely(!peek)) {
+				sge->offset += copy;
+				sge->length -= copy;
+				sk_mem_uncharge(sk, copy);
+				msg_rx->sg.size -= copy;
+
+				if (!sge->length) {
+					sk_msg_iter_var_next(i);
+					if (!msg_rx->skb)
+						put_page(page);
+				}
+			} else {
+				sk_msg_iter_var_next(i);
 			}
 
 			if (copied == len)
 				break;
 		} while (i != msg_rx->sg.end);
 
+		if (unlikely(peek)) {
+			msg_rx = list_next_entry(msg_rx, list);
+			continue;
+		}
+
 		msg_rx->sg.start = i;
 		if (!sge->length && msg_rx->sg.start == msg_rx->sg.end) {
 			list_del(&msg_rx->list);
@@ -92,6 +103,8 @@ int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock,
 				consume_skb(msg_rx->skb);
 			kfree(msg_rx);
 		}
+		msg_rx = list_first_entry_or_null(&psock->ingress_msg,
+						  struct sk_msg, list);
 	}
 
 	return copied;
@@ -114,7 +127,7 @@ int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
 	lock_sock(sk);
 msg_bytes_ready:
-	copied = __tcp_bpf_recvmsg(sk, psock, msg, len);
+	copied = __tcp_bpf_recvmsg(sk, psock, msg, len, flags);
 	if (!copied) {
 		int data, err = 0;
 		long timeo;

net/tls/tls_main.c

@@ -715,8 +715,6 @@ EXPORT_SYMBOL(tls_unregister_device);
 
 static struct tcp_ulp_ops tcp_tls_ulp_ops __read_mostly = {
 	.name			= "tls",
-	.uid			= TCP_ULP_TLS,
-	.user_visible		= true,
 	.owner			= THIS_MODULE,
 	.init			= tls_init,
 };

net/tls/tls_sw.c

@@ -1478,7 +1478,8 @@ int tls_sw_recvmsg(struct sock *sk,
 		skb = tls_wait_data(sk, psock, flags, timeo, &err);
 		if (!skb) {
 			if (psock) {
-				int ret = __tcp_bpf_recvmsg(sk, psock, msg, len);
+				int ret = __tcp_bpf_recvmsg(sk, psock,
+							    msg, len, flags);
 
 				if (ret > 0) {
 					copied += ret;

tools/arch/arm64/include/asm/barrier.h

@@ -14,4 +14,74 @@
 #define wmb()		asm volatile("dmb ishst" ::: "memory")
 #define rmb()		asm volatile("dmb ishld" ::: "memory")
 
+#define smp_store_release(p, v)					\
+do {								\
+	union { typeof(*p) __val; char __c[1]; } __u =		\
+		{ .__val = (__force typeof(*p)) (v) }; 		\
+								\
+	switch (sizeof(*p)) {					\
+	case 1:							\
+		asm volatile ("stlrb %w1, %0"			\
+				: "=Q" (*p)			\
+				: "r" (*(__u8 *)__u.__c)	\
+				: "memory");			\
+		break;						\
+	case 2:							\
+		asm volatile ("stlrh %w1, %0"			\
+				: "=Q" (*p)			\
+				: "r" (*(__u16 *)__u.__c)	\
+				: "memory");			\
+		break;						\
+	case 4:							\
+		asm volatile ("stlr %w1, %0"			\
+				: "=Q" (*p)			\
+				: "r" (*(__u32 *)__u.__c)	\
+				: "memory");			\
+		break;						\
+	case 8:							\
+		asm volatile ("stlr %1, %0"			\
+				: "=Q" (*p)			\
+				: "r" (*(__u64 *)__u.__c)	\
+				: "memory");			\
+		break;						\
+	default:						\
+		/* Only to shut up gcc ... */			\
+		mb();						\
+		break;						\
+	}							\
+} while (0)
+
+#define smp_load_acquire(p)					\
+({								\
+	union { typeof(*p) __val; char __c[1]; } __u;		\
+								\
+	switch (sizeof(*p)) {					\
+	case 1:							\
+		asm volatile ("ldarb %w0, %1"			\
+			: "=r" (*(__u8 *)__u.__c)		\
+			: "Q" (*p) : "memory");			\
+		break;						\
+	case 2:							\
+		asm volatile ("ldarh %w0, %1"			\
+			: "=r" (*(__u16 *)__u.__c)		\
+			: "Q" (*p) : "memory");			\
+		break;						\
+	case 4:							\
+		asm volatile ("ldar %w0, %1"			\
+			: "=r" (*(__u32 *)__u.__c)		\
+			: "Q" (*p) : "memory");			\
+		break;						\
+	case 8:							\
+		asm volatile ("ldar %0, %1"			\
+			: "=r" (*(__u64 *)__u.__c)		\
+			: "Q" (*p) : "memory");			\
+		break;						\
+	default:						\
+		/* Only to shut up gcc ... */			\
+		mb();						\
+		break;						\
+	}							\
+	__u.__val;						\
+})
+
 #endif /* _TOOLS_LINUX_ASM_AARCH64_BARRIER_H */

tools/arch/ia64/include/asm/barrier.h

@@ -46,4 +46,17 @@
 #define rmb()		mb()
 #define wmb()		mb()
 
+#define smp_store_release(p, v)			\
+do {						\
+	barrier();				\
+	WRITE_ONCE(*p, v);			\
+} while (0)
+
+#define smp_load_acquire(p)			\
+({						\
+	typeof(*p) ___p1 = READ_ONCE(*p);	\
+	barrier();				\
+	___p1;					\
+})
+
 #endif /* _TOOLS_LINUX_ASM_IA64_BARRIER_H */

tools/arch/powerpc/include/asm/barrier.h

@@ -27,4 +27,20 @@
 #define rmb()  __asm__ __volatile__ ("sync" : : : "memory")
 #define wmb()  __asm__ __volatile__ ("sync" : : : "memory")
 
+#if defined(__powerpc64__)
+#define smp_lwsync()	__asm__ __volatile__ ("lwsync" : : : "memory")
+
+#define smp_store_release(p, v)			\
+do {						\
+	smp_lwsync();				\
+	WRITE_ONCE(*p, v);			\
+} while (0)
+
+#define smp_load_acquire(p)			\
+({						\
+	typeof(*p) ___p1 = READ_ONCE(*p);	\
+	smp_lwsync();				\
+	___p1;					\
+})
+#endif /* defined(__powerpc64__) */
 #endif /* _TOOLS_LINUX_ASM_POWERPC_BARRIER_H */

tools/arch/s390/include/asm/barrier.h

@@ -28,4 +28,17 @@
 #define rmb()				mb()
 #define wmb()				mb()
 
+#define smp_store_release(p, v)			\
+do {						\
+	barrier();				\
+	WRITE_ONCE(*p, v);			\
+} while (0)
+
+#define smp_load_acquire(p)			\
+({						\
+	typeof(*p) ___p1 = READ_ONCE(*p);	\
+	barrier();				\
+	___p1;					\
+})
+
 #endif /* __TOOLS_LIB_ASM_BARRIER_H */

tools/arch/sparc/include/asm/barrier_64.h

@@ -40,4 +40,17 @@ do {	__asm__ __volatile__("ba,pt	%%xcc, 1f\n\t" \
 #define rmb()	__asm__ __volatile__("":::"memory")
 #define wmb()	__asm__ __volatile__("":::"memory")
 
+#define smp_store_release(p, v)			\
+do {						\
+	barrier();				\
+	WRITE_ONCE(*p, v);			\
+} while (0)
+
+#define smp_load_acquire(p)			\
+({						\
+	typeof(*p) ___p1 = READ_ONCE(*p);	\
+	barrier();				\
+	___p1;					\
+})
+
 #endif /* !(__TOOLS_LINUX_SPARC64_BARRIER_H) */

tools/arch/x86/include/asm/barrier.h

@@ -26,4 +26,18 @@
 #define wmb()	asm volatile("sfence" ::: "memory")
 #endif
 
+#if defined(__x86_64__)
+#define smp_store_release(p, v)			\
+do {						\
+	barrier();				\
+	WRITE_ONCE(*p, v);			\
+} while (0)
+
+#define smp_load_acquire(p)			\
+({						\
+	typeof(*p) ___p1 = READ_ONCE(*p);	\
+	barrier();				\
+	___p1;					\
+})
+#endif /* defined(__x86_64__) */
 #endif /* _TOOLS_LINUX_ASM_X86_BARRIER_H */

tools/bpf/bpftool/Documentation/bpftool-map.rst

@@ -86,7 +86,9 @@ DESCRIPTION
 	**bpftool map pin**     *MAP*  *FILE*
 		  Pin map *MAP* as *FILE*.
 
-		  Note: *FILE* must be located in *bpffs* mount.
+		  Note: *FILE* must be located in *bpffs* mount. It must not
+		  contain a dot character ('.'), which is reserved for future
+		  extensions of *bpffs*.
 
 	**bpftool** **map event_pipe** *MAP* [**cpu** *N* **index** *M*]
 		  Read events from a BPF_MAP_TYPE_PERF_EVENT_ARRAY map.

tools/bpf/bpftool/Documentation/bpftool-prog.rst

@@ -75,7 +75,9 @@ DESCRIPTION
 	**bpftool prog pin** *PROG* *FILE*
 		  Pin program *PROG* as *FILE*.
 
-		  Note: *FILE* must be located in *bpffs* mount.
+		  Note: *FILE* must be located in *bpffs* mount. It must not
+		  contain a dot character ('.'), which is reserved for future
+		  extensions of *bpffs*.
 
 	**bpftool prog load** *OBJ* *FILE* [**type** *TYPE*] [**map** {**idx** *IDX* | **name** *NAME*} *MAP*] [**dev** *NAME*]
 		  Load bpf program from binary *OBJ* and pin as *FILE*.
@@ -91,7 +93,9 @@ DESCRIPTION
 		  If **dev** *NAME* is specified program will be loaded onto
 		  given networking device (offload).
 
-		  Note: *FILE* must be located in *bpffs* mount.
+		  Note: *FILE* must be located in *bpffs* mount. It must not
+		  contain a dot character ('.'), which is reserved for future
+		  extensions of *bpffs*.
 
         **bpftool prog attach** *PROG* *ATTACH_TYPE* *MAP*
                   Attach bpf program *PROG* (with type specified by *ATTACH_TYPE*)

tools/bpf/bpftool/bash-completion/bpftool

@@ -143,7 +143,7 @@ _bpftool_map_update_map_type()
     local type
     type=$(bpftool -jp map show $keyword $ref | \
         command sed -n 's/.*"type": "\(.*\)",$/\1/p')
-    printf $type
+    [[ -n $type ]] && printf $type
 }
 
 _bpftool_map_update_get_id()

tools/bpf/bpftool/common.c

@@ -554,7 +554,9 @@ static int read_sysfs_netdev_hex_int(char *devname, const char *entry_name)
 	return read_sysfs_hex_int(full_path);
 }
 
-const char *ifindex_to_bfd_name_ns(__u32 ifindex, __u64 ns_dev, __u64 ns_ino)
+const char *
+ifindex_to_bfd_params(__u32 ifindex, __u64 ns_dev, __u64 ns_ino,
+		      const char **opt)
 {
 	char devname[IF_NAMESIZE];
 	int vendor_id;
@@ -579,6 +581,7 @@ const char *ifindex_to_bfd_name_ns(__u32 ifindex, __u64 ns_dev, __u64 ns_ino)
 		    device_id != 0x6000 &&
 		    device_id != 0x6003)
 			p_info("Unknown NFP device ID, assuming it is NFP-6xxx arch");
+		*opt = "ctx4";
 		return "NFP-6xxx";
 	default:
 		p_err("Can't get bfd arch name for device vendor id 0x%04x",

tools/bpf/bpftool/jit_disasm.c

@@ -77,7 +77,7 @@ static int fprintf_json(void *out, const char *fmt, ...)
 }
 
 void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes,
-		       const char *arch)
+		       const char *arch, const char *disassembler_options)
 {
 	disassembler_ftype disassemble;
 	struct disassemble_info info;
@@ -116,6 +116,8 @@ void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes,
 
 	info.arch = bfd_get_arch(bfdf);
 	info.mach = bfd_get_mach(bfdf);
+	if (disassembler_options)
+		info.disassembler_options = disassembler_options;
 	info.buffer = image;
 	info.buffer_length = len;
 

tools/bpf/bpftool/main.c

@@ -321,7 +321,8 @@ static int do_batch(int argc, char **argv)
 		p_err("reading batch file failed: %s", strerror(errno));
 		err = -1;
 	} else {
-		p_info("processed %d commands", lines);
+		if (!json_output)
+			printf("processed %d commands\n", lines);
 		err = 0;
 	}
 err_close:

tools/bpf/bpftool/main.h

@@ -145,13 +145,15 @@ int map_parse_fd(int *argc, char ***argv);
 int map_parse_fd_and_info(int *argc, char ***argv, void *info, __u32 *info_len);
 
 void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes,
-		       const char *arch);
+		       const char *arch, const char *disassembler_options);
 void print_data_json(uint8_t *data, size_t len);
 void print_hex_data_json(uint8_t *data, size_t len);
 
 unsigned int get_page_size(void);
 unsigned int get_possible_cpus(void);
-const char *ifindex_to_bfd_name_ns(__u32 ifindex, __u64 ns_dev, __u64 ns_ino);
+const char *
+ifindex_to_bfd_params(__u32 ifindex, __u64 ns_dev, __u64 ns_ino,
+		      const char **opt);
 
 struct btf_dumper {
 	const struct btf *btf;

tools/bpf/bpftool/map_perf_ring.c

@@ -50,15 +50,17 @@ static void int_exit(int signo)
 	stop = true;
 }
 
-static enum bpf_perf_event_ret print_bpf_output(void *event, void *priv)
+static enum bpf_perf_event_ret
+print_bpf_output(struct perf_event_header *event, void *private_data)
 {
-	struct event_ring_info *ring = priv;
-	struct perf_event_sample *e = event;
+	struct perf_event_sample *e = container_of(event, struct perf_event_sample,
+						   header);
+	struct event_ring_info *ring = private_data;
 	struct {
 		struct perf_event_header header;
 		__u64 id;
 		__u64 lost;
-	} *lost = event;
+	} *lost = (typeof(lost))event;
 
 	if (json_output) {
 		jsonw_start_object(json_wtr);

tools/bpf/bpftool/prog.c

@@ -449,6 +449,7 @@ static int do_dump(int argc, char **argv)
 	unsigned long *func_ksyms = NULL;
 	struct bpf_prog_info info = {};
 	unsigned int *func_lens = NULL;
+	const char *disasm_opt = NULL;
 	unsigned int nr_func_ksyms;
 	unsigned int nr_func_lens;
 	struct dump_data dd = {};
@@ -607,9 +608,10 @@ static int do_dump(int argc, char **argv)
 		const char *name = NULL;
 
 		if (info.ifindex) {
-			name = ifindex_to_bfd_name_ns(info.ifindex,
-						      info.netns_dev,
-						      info.netns_ino);
+			name = ifindex_to_bfd_params(info.ifindex,
+						     info.netns_dev,
+						     info.netns_ino,
+						     &disasm_opt);
 			if (!name)
 				goto err_free;
 		}
@@ -651,7 +653,8 @@ static int do_dump(int argc, char **argv)
 					printf("%s:\n", sym_name);
 				}
 
-				disasm_print_insn(img, lens[i], opcodes, name);
+				disasm_print_insn(img, lens[i], opcodes, name,
+						  disasm_opt);
 				img += lens[i];
 
 				if (json_output)
@@ -663,7 +666,8 @@ static int do_dump(int argc, char **argv)
 			if (json_output)
 				jsonw_end_array(json_wtr);
 		} else {
-			disasm_print_insn(buf, *member_len, opcodes, name);
+			disasm_print_insn(buf, *member_len, opcodes, name,
+					  disasm_opt);
 		}
 	} else if (visual) {
 		if (json_output)

tools/include/asm/barrier.h

@@ -1,4 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/compiler.h>
 #if defined(__i386__) || defined(__x86_64__)
 #include "../../arch/x86/include/asm/barrier.h"
 #elif defined(__arm__)
@@ -26,3 +27,37 @@
 #else
 #include <asm-generic/barrier.h>
 #endif
+
+/*
+ * Generic fallback smp_*() definitions for archs that haven't
+ * been updated yet.
+ */
+
+#ifndef smp_rmb
+# define smp_rmb()	rmb()
+#endif
+
+#ifndef smp_wmb
+# define smp_wmb()	wmb()
+#endif
+
+#ifndef smp_mb
+# define smp_mb()	mb()
+#endif
+
+#ifndef smp_store_release
+# define smp_store_release(p, v)		\
+do {						\
+	smp_mb();				\
+	WRITE_ONCE(*p, v);			\
+} while (0)
+#endif
+
+#ifndef smp_load_acquire
+# define smp_load_acquire(p)			\
+({						\
+	typeof(*p) ___p1 = READ_ONCE(*p);	\
+	smp_mb();				\
+	___p1;					\
+})
+#endif

tools/include/linux/ring_buffer.h

@@ -0,0 +1,73 @@
+#ifndef _TOOLS_LINUX_RING_BUFFER_H_
+#define _TOOLS_LINUX_RING_BUFFER_H_
+
+#include <asm/barrier.h>
+
+/*
+ * Contract with kernel for walking the perf ring buffer from
+ * user space requires the following barrier pairing (quote
+ * from kernel/events/ring_buffer.c):
+ *
+ *   Since the mmap() consumer (userspace) can run on a
+ *   different CPU:
+ *
+ *   kernel                             user
+ *
+ *   if (LOAD ->data_tail) {            LOAD ->data_head
+ *                      (A)             smp_rmb()       (C)
+ *      STORE $data                     LOAD $data
+ *      smp_wmb()       (B)             smp_mb()        (D)
+ *      STORE ->data_head               STORE ->data_tail
+ *   }
+ *
+ *   Where A pairs with D, and B pairs with C.
+ *
+ *   In our case A is a control dependency that separates the
+ *   load of the ->data_tail and the stores of $data. In case
+ *   ->data_tail indicates there is no room in the buffer to
+ *   store $data we do not.
+ *
+ *   D needs to be a full barrier since it separates the data
+ *   READ from the tail WRITE.
+ *
+ *   For B a WMB is sufficient since it separates two WRITEs,
+ *   and for C an RMB is sufficient since it separates two READs.
+ *
+ * Note, instead of B, C, D we could also use smp_store_release()
+ * in B and D as well as smp_load_acquire() in C.
+ *
+ * However, this optimization does not make sense for all kernel
+ * supported architectures since for a fair number it would
+ * resolve into READ_ONCE() + smp_mb() pair for smp_load_acquire(),
+ * and smp_mb() + WRITE_ONCE() pair for smp_store_release().
+ *
+ * Thus for those smp_wmb() in B and smp_rmb() in C would still
+ * be less expensive. For the case of D this has either the same
+ * cost or is less expensive, for example, due to TSO x86 can
+ * avoid the CPU barrier entirely.
+ */
+
+static inline u64 ring_buffer_read_head(struct perf_event_mmap_page *base)
+{
+/*
+ * Architectures where smp_load_acquire() does not fallback to
+ * READ_ONCE() + smp_mb() pair.
+ */
+#if defined(__x86_64__) || defined(__aarch64__) || defined(__powerpc64__) || \
+    defined(__ia64__) || defined(__sparc__) && defined(__arch64__)
+	return smp_load_acquire(&base->data_head);
+#else
+	u64 head = READ_ONCE(base->data_head);
+
+	smp_rmb();
+	return head;
+#endif
+}
+
+static inline void ring_buffer_write_tail(struct perf_event_mmap_page *base,
+					  u64 tail)
+{
+	smp_store_release(&base->data_tail, tail);
+}
+
+#endif /* _TOOLS_LINUX_RING_BUFFER_H_ */

tools/include/uapi/linux/bpf.h

@@ -103,6 +103,7 @@ enum bpf_cmd {
 	BPF_BTF_LOAD,
 	BPF_BTF_GET_FD_BY_ID,
 	BPF_TASK_FD_QUERY,
+	BPF_MAP_LOOKUP_AND_DELETE_ELEM,
 };
 
 enum bpf_map_type {
@@ -128,6 +129,8 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_CGROUP_STORAGE,
 	BPF_MAP_TYPE_REUSEPORT_SOCKARRAY,
 	BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE,
+	BPF_MAP_TYPE_QUEUE,
+	BPF_MAP_TYPE_STACK,
 };
 
 enum bpf_prog_type {
@@ -462,6 +465,28 @@ union bpf_attr {
  * 	Return
  * 		0 on success, or a negative error in case of failure.
  *
+ * int bpf_map_push_elem(struct bpf_map *map, const void *value, u64 flags)
+ * 	Description
+ * 		Push an element *value* in *map*. *flags* is one of:
+ *
+ * 		**BPF_EXIST**
+ * 		If the queue/stack is full, the oldest element is removed to
+ * 		make room for this.
+ * 	Return
+ * 		0 on success, or a negative error in case of failure.
+ *
+ * int bpf_map_pop_elem(struct bpf_map *map, void *value)
+ * 	Description
+ * 		Pop an element from *map*.
+ * Return
+ * 		0 on success, or a negative error in case of failure.
+ *
+ * int bpf_map_peek_elem(struct bpf_map *map, void *value)
+ * 	Description
+ * 		Get an element from *map* without removing it.
+ * Return
+ * 		0 on success, or a negative error in case of failure.
+ *
  * int bpf_probe_read(void *dst, u32 size, const void *src)
  * 	Description
  * 		For tracing programs, safely attempt to read *size* bytes from
@@ -1433,7 +1458,7 @@ union bpf_attr {
  * 	Return
  * 		0 on success, or a negative error in case of failure.
  *
- * int bpf_skb_adjust_room(struct sk_buff *skb, u32 len_diff, u32 mode, u64 flags)
+ * int bpf_skb_adjust_room(struct sk_buff *skb, s32 len_diff, u32 mode, u64 flags)
  * 	Description
  * 		Grow or shrink the room for data in the packet associated to
  * 		*skb* by *len_diff*, and according to the selected *mode*.
@@ -2215,6 +2240,23 @@ union bpf_attr {
  *		pointer that was returned from bpf_sk_lookup_xxx\ ().
  *	Return
  *		0 on success, or a negative error in case of failure.
+ *
+ * int bpf_msg_push_data(struct sk_buff *skb, u32 start, u32 len, u64 flags)
+ *	Description
+ *		For socket policies, insert *len* bytes into msg at offset
+ *		*start*.
+ *
+ *		If a program of type **BPF_PROG_TYPE_SK_MSG** is run on a
+ *		*msg* it may want to insert metadata or options into the msg.
+ *		This can later be read and used by any of the lower layer BPF
+ *		hooks.
+ *
+ *		This helper may fail if under memory pressure (a malloc
+ *		fails) in these cases BPF programs will get an appropriate
+ *		error and BPF programs will need to handle them.
+ *
+ *	Return
+ *		0 on success, or a negative error in case of failure.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -2303,7 +2345,11 @@ union bpf_attr {
 	FN(skb_ancestor_cgroup_id),	\
 	FN(sk_lookup_tcp),		\
 	FN(sk_lookup_udp),		\
-	FN(sk_release),
+	FN(sk_release),			\
+	FN(map_push_elem),		\
+	FN(map_pop_elem),		\
+	FN(map_peek_elem),		\
+	FN(msg_push_data),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call

tools/include/uapi/linux/tls.h

@@ -0,0 +1,78 @@
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
+/*
+ * Copyright (c) 2016-2017, Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#ifndef _UAPI_LINUX_TLS_H
+#define _UAPI_LINUX_TLS_H
+
+#include <linux/types.h>
+
+/* TLS socket options */
+#define TLS_TX			1	/* Set transmit parameters */
+#define TLS_RX			2	/* Set receive parameters */
+
+/* Supported versions */
+#define TLS_VERSION_MINOR(ver)	((ver) & 0xFF)
+#define TLS_VERSION_MAJOR(ver)	(((ver) >> 8) & 0xFF)
+
+#define TLS_VERSION_NUMBER(id)	((((id##_VERSION_MAJOR) & 0xFF) << 8) |	\
+				 ((id##_VERSION_MINOR) & 0xFF))
+
+#define TLS_1_2_VERSION_MAJOR	0x3
+#define TLS_1_2_VERSION_MINOR	0x3
+#define TLS_1_2_VERSION		TLS_VERSION_NUMBER(TLS_1_2)
+
+/* Supported ciphers */
+#define TLS_CIPHER_AES_GCM_128				51
+#define TLS_CIPHER_AES_GCM_128_IV_SIZE			8
+#define TLS_CIPHER_AES_GCM_128_KEY_SIZE		16
+#define TLS_CIPHER_AES_GCM_128_SALT_SIZE		4
+#define TLS_CIPHER_AES_GCM_128_TAG_SIZE		16
+#define TLS_CIPHER_AES_GCM_128_REC_SEQ_SIZE		8
+
+#define TLS_SET_RECORD_TYPE	1
+#define TLS_GET_RECORD_TYPE	2
+
+struct tls_crypto_info {
+	__u16 version;
+	__u16 cipher_type;
+};
+
+struct tls12_crypto_info_aes_gcm_128 {
+	struct tls_crypto_info info;
+	unsigned char iv[TLS_CIPHER_AES_GCM_128_IV_SIZE];
+	unsigned char key[TLS_CIPHER_AES_GCM_128_KEY_SIZE];
+	unsigned char salt[TLS_CIPHER_AES_GCM_128_SALT_SIZE];
+	unsigned char rec_seq[TLS_CIPHER_AES_GCM_128_REC_SEQ_SIZE];
+};
+
+#endif /* _UAPI_LINUX_TLS_H */

tools/lib/bpf/Makefile

@@ -125,6 +125,7 @@ override CFLAGS += $(EXTRA_WARNINGS)
 override CFLAGS += -Werror -Wall
 override CFLAGS += -fPIC
 override CFLAGS += $(INCLUDES)
+override CFLAGS += -fvisibility=hidden
 
 ifeq ($(VERBOSE),1)
   Q =

tools/lib/bpf/bpf.c

@@ -278,6 +278,18 @@ int bpf_map_lookup_elem(int fd, const void *key, void *value)
 	return sys_bpf(BPF_MAP_LOOKUP_ELEM, &attr, sizeof(attr));
 }
 
+int bpf_map_lookup_and_delete_elem(int fd, const void *key, void *value)
+{
+	union bpf_attr attr;
+
+	bzero(&attr, sizeof(attr));
+	attr.map_fd = fd;
+	attr.key = ptr_to_u64(key);
+	attr.value = ptr_to_u64(value);
+
+	return sys_bpf(BPF_MAP_LOOKUP_AND_DELETE_ELEM, &attr, sizeof(attr));
+}
+
 int bpf_map_delete_elem(int fd, const void *key)
 {
 	union bpf_attr attr;

tools/lib/bpf/bpf.h

@@ -27,6 +27,10 @@
 #include <stdbool.h>
 #include <stddef.h>
 
+#ifndef LIBBPF_API
+#define LIBBPF_API __attribute__((visibility("default")))
+#endif
+
 struct bpf_create_map_attr {
 	const char *name;
 	enum bpf_map_type map_type;
@@ -42,21 +46,24 @@ struct bpf_create_map_attr {
 	__u32 inner_map_fd;
 };
 
-int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr);
-int bpf_create_map_node(enum bpf_map_type map_type, const char *name,
-			int key_size, int value_size, int max_entries,
-			__u32 map_flags, int node);
-int bpf_create_map_name(enum bpf_map_type map_type, const char *name,
-			int key_size, int value_size, int max_entries,
-			__u32 map_flags);
-int bpf_create_map(enum bpf_map_type map_type, int key_size, int value_size,
-		   int max_entries, __u32 map_flags);
-int bpf_create_map_in_map_node(enum bpf_map_type map_type, const char *name,
-			       int key_size, int inner_map_fd, int max_entries,
-			       __u32 map_flags, int node);
-int bpf_create_map_in_map(enum bpf_map_type map_type, const char *name,
-			  int key_size, int inner_map_fd, int max_entries,
-			  __u32 map_flags);
+LIBBPF_API int
+bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr);
+LIBBPF_API int bpf_create_map_node(enum bpf_map_type map_type, const char *name,
+				   int key_size, int value_size,
+				   int max_entries, __u32 map_flags, int node);
+LIBBPF_API int bpf_create_map_name(enum bpf_map_type map_type, const char *name,
+				   int key_size, int value_size,
+				   int max_entries, __u32 map_flags);
+LIBBPF_API int bpf_create_map(enum bpf_map_type map_type, int key_size,
+			      int value_size, int max_entries, __u32 map_flags);
+LIBBPF_API int bpf_create_map_in_map_node(enum bpf_map_type map_type,
+					  const char *name, int key_size,
+					  int inner_map_fd, int max_entries,
+					  __u32 map_flags, int node);
+LIBBPF_API int bpf_create_map_in_map(enum bpf_map_type map_type,
+				     const char *name, int key_size,
+				     int inner_map_fd, int max_entries,
+				     __u32 map_flags);
 
 struct bpf_load_program_attr {
 	enum bpf_prog_type prog_type;
@@ -74,44 +81,51 @@ struct bpf_load_program_attr {
 
 /* Recommend log buffer size */
 #define BPF_LOG_BUF_SIZE (256 * 1024)
-int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
-			   char *log_buf, size_t log_buf_sz);
-int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns,
-		     size_t insns_cnt, const char *license,
-		     __u32 kern_version, char *log_buf,
-		     size_t log_buf_sz);
-int bpf_verify_program(enum bpf_prog_type type, const struct bpf_insn *insns,
-		       size_t insns_cnt, int strict_alignment,
-		       const char *license, __u32 kern_version,
-		       char *log_buf, size_t log_buf_sz, int log_level);
+LIBBPF_API int
+bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
+		       char *log_buf, size_t log_buf_sz);
+LIBBPF_API int bpf_load_program(enum bpf_prog_type type,
+				const struct bpf_insn *insns, size_t insns_cnt,
+				const char *license, __u32 kern_version,
+				char *log_buf, size_t log_buf_sz);
+LIBBPF_API int bpf_verify_program(enum bpf_prog_type type,
+				  const struct bpf_insn *insns,
+				  size_t insns_cnt, int strict_alignment,
+				  const char *license, __u32 kern_version,
+				  char *log_buf, size_t log_buf_sz,
+				  int log_level);
 
-int bpf_map_update_elem(int fd, const void *key, const void *value,
-			__u64 flags);
+LIBBPF_API int bpf_map_update_elem(int fd, const void *key, const void *value,
+				   __u64 flags);
 
-int bpf_map_lookup_elem(int fd, const void *key, void *value);
-int bpf_map_delete_elem(int fd, const void *key);
-int bpf_map_get_next_key(int fd, const void *key, void *next_key);
-int bpf_obj_pin(int fd, const char *pathname);
-int bpf_obj_get(const char *pathname);
-int bpf_prog_attach(int prog_fd, int attachable_fd, enum bpf_attach_type type,
-		    unsigned int flags);
-int bpf_prog_detach(int attachable_fd, enum bpf_attach_type type);
-int bpf_prog_detach2(int prog_fd, int attachable_fd, enum bpf_attach_type type);
-int bpf_prog_test_run(int prog_fd, int repeat, void *data, __u32 size,
-		      void *data_out, __u32 *size_out, __u32 *retval,
-		      __u32 *duration);
-int bpf_prog_get_next_id(__u32 start_id, __u32 *next_id);
-int bpf_map_get_next_id(__u32 start_id, __u32 *next_id);
-int bpf_prog_get_fd_by_id(__u32 id);
-int bpf_map_get_fd_by_id(__u32 id);
-int bpf_btf_get_fd_by_id(__u32 id);
-int bpf_obj_get_info_by_fd(int prog_fd, void *info, __u32 *info_len);
-int bpf_prog_query(int target_fd, enum bpf_attach_type type, __u32 query_flags,
-		   __u32 *attach_flags, __u32 *prog_ids, __u32 *prog_cnt);
-int bpf_raw_tracepoint_open(const char *name, int prog_fd);
-int bpf_load_btf(void *btf, __u32 btf_size, char *log_buf, __u32 log_buf_size,
-		 bool do_log);
-int bpf_task_fd_query(int pid, int fd, __u32 flags, char *buf, __u32 *buf_len,
-		      __u32 *prog_id, __u32 *fd_type, __u64 *probe_offset,
-		      __u64 *probe_addr);
+LIBBPF_API int bpf_map_lookup_elem(int fd, const void *key, void *value);
+LIBBPF_API int bpf_map_lookup_and_delete_elem(int fd, const void *key,
+					      void *value);
+LIBBPF_API int bpf_map_delete_elem(int fd, const void *key);
+LIBBPF_API int bpf_map_get_next_key(int fd, const void *key, void *next_key);
+LIBBPF_API int bpf_obj_pin(int fd, const char *pathname);
+LIBBPF_API int bpf_obj_get(const char *pathname);
+LIBBPF_API int bpf_prog_attach(int prog_fd, int attachable_fd,
+			       enum bpf_attach_type type, unsigned int flags);
+LIBBPF_API int bpf_prog_detach(int attachable_fd, enum bpf_attach_type type);
+LIBBPF_API int bpf_prog_detach2(int prog_fd, int attachable_fd,
+				enum bpf_attach_type type);
+LIBBPF_API int bpf_prog_test_run(int prog_fd, int repeat, void *data,
+				 __u32 size, void *data_out, __u32 *size_out,
+				 __u32 *retval, __u32 *duration);
+LIBBPF_API int bpf_prog_get_next_id(__u32 start_id, __u32 *next_id);
+LIBBPF_API int bpf_map_get_next_id(__u32 start_id, __u32 *next_id);
+LIBBPF_API int bpf_prog_get_fd_by_id(__u32 id);
+LIBBPF_API int bpf_map_get_fd_by_id(__u32 id);
+LIBBPF_API int bpf_btf_get_fd_by_id(__u32 id);
+LIBBPF_API int bpf_obj_get_info_by_fd(int prog_fd, void *info, __u32 *info_len);
+LIBBPF_API int bpf_prog_query(int target_fd, enum bpf_attach_type type,
+			      __u32 query_flags, __u32 *attach_flags,
+			      __u32 *prog_ids, __u32 *prog_cnt);
+LIBBPF_API int bpf_raw_tracepoint_open(const char *name, int prog_fd);
+LIBBPF_API int bpf_load_btf(void *btf, __u32 btf_size, char *log_buf,
+			    __u32 log_buf_size, bool do_log);
+LIBBPF_API int bpf_task_fd_query(int pid, int fd, __u32 flags, char *buf,
+				 __u32 *buf_len, __u32 *prog_id, __u32 *fd_type,
+				 __u64 *probe_offset, __u64 *probe_addr);
 #endif /* __LIBBPF_BPF_H */

tools/lib/bpf/btf.h

@@ -6,6 +6,10 @@
 
 #include <linux/types.h>
 
+#ifndef LIBBPF_API
+#define LIBBPF_API __attribute__((visibility("default")))
+#endif
+
 #define BTF_ELF_SEC ".BTF"
 
 struct btf;
@@ -14,13 +18,15 @@ struct btf_type;
 typedef int (*btf_print_fn_t)(const char *, ...)
 	__attribute__((format(printf, 1, 2)));
 
-void btf__free(struct btf *btf);
-struct btf *btf__new(__u8 *data, __u32 size, btf_print_fn_t err_log);
-__s32 btf__find_by_name(const struct btf *btf, const char *type_name);
-const struct btf_type *btf__type_by_id(const struct btf *btf, __u32 id);
-__s64 btf__resolve_size(const struct btf *btf, __u32 type_id);
-int btf__resolve_type(const struct btf *btf, __u32 type_id);
-int btf__fd(const struct btf *btf);
-const char *btf__name_by_offset(const struct btf *btf, __u32 offset);
+LIBBPF_API void btf__free(struct btf *btf);
+LIBBPF_API struct btf *btf__new(__u8 *data, __u32 size, btf_print_fn_t err_log);
+LIBBPF_API __s32 btf__find_by_name(const struct btf *btf,
+				   const char *type_name);
+LIBBPF_API const struct btf_type *btf__type_by_id(const struct btf *btf,
+						  __u32 id);
+LIBBPF_API __s64 btf__resolve_size(const struct btf *btf, __u32 type_id);
+LIBBPF_API int btf__resolve_type(const struct btf *btf, __u32 type_id);
+LIBBPF_API int btf__fd(const struct btf *btf);
+LIBBPF_API const char *btf__name_by_offset(const struct btf *btf, __u32 offset);
 
 #endif /* __LIBBPF_BTF_H */

tools/lib/bpf/libbpf.c

@@ -27,6 +27,7 @@
 #include <linux/list.h>
 #include <linux/limits.h>
 #include <linux/perf_event.h>
+#include <linux/ring_buffer.h>
 #include <sys/stat.h>
 #include <sys/types.h>
 #include <sys/vfs.h>
@@ -2414,61 +2415,49 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
 }
 
 enum bpf_perf_event_ret
-bpf_perf_event_read_simple(void *mem, unsigned long size,
-			   unsigned long page_size, void **buf, size_t *buf_len,
-			   bpf_perf_event_print_t fn, void *priv)
+bpf_perf_event_read_simple(void *mmap_mem, size_t mmap_size, size_t page_size,
+			   void **copy_mem, size_t *copy_size,
+			   bpf_perf_event_print_t fn, void *private_data)
 {
-	volatile struct perf_event_mmap_page *header = mem;
+	struct perf_event_mmap_page *header = mmap_mem;
+	__u64 data_head = ring_buffer_read_head(header);
 	__u64 data_tail = header->data_tail;
-	__u64 data_head = header->data_head;
-	int ret = LIBBPF_PERF_EVENT_ERROR;
-	void *base, *begin, *end;
-
-	asm volatile("" ::: "memory"); /* in real code it should be smp_rmb() */
-	if (data_head == data_tail)
-		return LIBBPF_PERF_EVENT_CONT;
-
-	base = ((char *)header) + page_size;
-
-	begin = base + data_tail % size;
-	end = base + data_head % size;
-
-	while (begin != end) {
-		struct perf_event_header *ehdr;
-
-		ehdr = begin;
-		if (begin + ehdr->size > base + size) {
-			long len = base + size - begin;
-
-			if (*buf_len < ehdr->size) {
-				free(*buf);
-				*buf = malloc(ehdr->size);
-				if (!*buf) {
+	void *base = ((__u8 *)header) + page_size;
+	int ret = LIBBPF_PERF_EVENT_CONT;
+	struct perf_event_header *ehdr;
+	size_t ehdr_size;
+
+	while (data_head != data_tail) {
+		ehdr = base + (data_tail & (mmap_size - 1));
+		ehdr_size = ehdr->size;
+
+		if (((void *)ehdr) + ehdr_size > base + mmap_size) {
+			void *copy_start = ehdr;
+			size_t len_first = base + mmap_size - copy_start;
+			size_t len_secnd = ehdr_size - len_first;
+
+			if (*copy_size < ehdr_size) {
+				free(*copy_mem);
+				*copy_mem = malloc(ehdr_size);
+				if (!*copy_mem) {
+					*copy_size = 0;
 					ret = LIBBPF_PERF_EVENT_ERROR;
 					break;
 				}
-				*buf_len = ehdr->size;
+				*copy_size = ehdr_size;
 			}
 
-			memcpy(*buf, begin, len);
-			memcpy(*buf + len, base, ehdr->size - len);
-			ehdr = (void *)*buf;
-			begin = base + ehdr->size - len;
-		} else if (begin + ehdr->size == base + size) {
-			begin = base;
-		} else {
-			begin += ehdr->size;
+			memcpy(*copy_mem, copy_start, len_first);
+			memcpy(*copy_mem + len_first, base, len_secnd);
+			ehdr = *copy_mem;
 		}
 
-		ret = fn(ehdr, priv);
+		ret = fn(ehdr, private_data);
+		data_tail += ehdr_size;
 		if (ret != LIBBPF_PERF_EVENT_CONT)
 			break;
-
-		data_tail += ehdr->size;
 	}
 
-	__sync_synchronize(); /* smp_mb() */
-	header->data_tail = data_tail;
-
+	ring_buffer_write_tail(header, data_tail);
 	return ret;
 }

tools/lib/bpf/libbpf.h

@@ -16,6 +16,10 @@
 #include <sys/types.h>  // for size_t
 #include <linux/bpf.h>
 
+#ifndef LIBBPF_API
+#define LIBBPF_API __attribute__((visibility("default")))
+#endif
+
 enum libbpf_errno {
 	__LIBBPF_ERRNO__START = 4000,
 
@@ -37,7 +41,7 @@ enum libbpf_errno {
 	__LIBBPF_ERRNO__END,
 };
 
-int libbpf_strerror(int err, char *buf, size_t size);
+LIBBPF_API int libbpf_strerror(int err, char *buf, size_t size);
 
 /*
  * __printf is defined in include/linux/compiler-gcc.h. However,
@@ -47,9 +51,9 @@ int libbpf_strerror(int err, char *buf, size_t size);
 typedef int (*libbpf_print_fn_t)(const char *, ...)
 	__attribute__((format(printf, 1, 2)));
 
-void libbpf_set_print(libbpf_print_fn_t warn,
-		      libbpf_print_fn_t info,
-		      libbpf_print_fn_t debug);
+LIBBPF_API void libbpf_set_print(libbpf_print_fn_t warn,
+				 libbpf_print_fn_t info,
+				 libbpf_print_fn_t debug);
 
 /* Hide internal to user */
 struct bpf_object;
@@ -59,27 +63,28 @@ struct bpf_object_open_attr {
 	enum bpf_prog_type prog_type;
 };
 
-struct bpf_object *bpf_object__open(const char *path);
-struct bpf_object *bpf_object__open_xattr(struct bpf_object_open_attr *attr);
+LIBBPF_API struct bpf_object *bpf_object__open(const char *path);
+LIBBPF_API struct bpf_object *
+bpf_object__open_xattr(struct bpf_object_open_attr *attr);
 struct bpf_object *__bpf_object__open_xattr(struct bpf_object_open_attr *attr,
 					    int flags);
-struct bpf_object *bpf_object__open_buffer(void *obj_buf,
-					   size_t obj_buf_sz,
-					   const char *name);
-int bpf_object__pin(struct bpf_object *object, const char *path);
-void bpf_object__close(struct bpf_object *object);
+LIBBPF_API struct bpf_object *bpf_object__open_buffer(void *obj_buf,
+						      size_t obj_buf_sz,
+						      const char *name);
+LIBBPF_API int bpf_object__pin(struct bpf_object *object, const char *path);
+LIBBPF_API void bpf_object__close(struct bpf_object *object);
 
 /* Load/unload object into/from kernel */
-int bpf_object__load(struct bpf_object *obj);
-int bpf_object__unload(struct bpf_object *obj);
-const char *bpf_object__name(struct bpf_object *obj);
-unsigned int bpf_object__kversion(struct bpf_object *obj);
-int bpf_object__btf_fd(const struct bpf_object *obj);
+LIBBPF_API int bpf_object__load(struct bpf_object *obj);
+LIBBPF_API int bpf_object__unload(struct bpf_object *obj);
+LIBBPF_API const char *bpf_object__name(struct bpf_object *obj);
+LIBBPF_API unsigned int bpf_object__kversion(struct bpf_object *obj);
+LIBBPF_API int bpf_object__btf_fd(const struct bpf_object *obj);
 
-struct bpf_program *
+LIBBPF_API struct bpf_program *
 bpf_object__find_program_by_title(struct bpf_object *obj, const char *title);
 
-struct bpf_object *bpf_object__next(struct bpf_object *prev);
+LIBBPF_API struct bpf_object *bpf_object__next(struct bpf_object *prev);
 #define bpf_object__for_each_safe(pos, tmp)			\
 	for ((pos) = bpf_object__next(NULL),		\
 		(tmp) = bpf_object__next(pos);		\
@@ -87,19 +92,20 @@ struct bpf_object *bpf_object__next(struct bpf_object *prev);
 	     (pos) = (tmp), (tmp) = bpf_object__next(tmp))
 
 typedef void (*bpf_object_clear_priv_t)(struct bpf_object *, void *);
-int bpf_object__set_priv(struct bpf_object *obj, void *priv,
-			 bpf_object_clear_priv_t clear_priv);
-void *bpf_object__priv(struct bpf_object *prog);
+LIBBPF_API int bpf_object__set_priv(struct bpf_object *obj, void *priv,
+				    bpf_object_clear_priv_t clear_priv);
+LIBBPF_API void *bpf_object__priv(struct bpf_object *prog);
 
-int libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type,
-			     enum bpf_attach_type *expected_attach_type);
-int libbpf_attach_type_by_name(const char *name,
-			       enum bpf_attach_type *attach_type);
+LIBBPF_API int
+libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type,
+			 enum bpf_attach_type *expected_attach_type);
+LIBBPF_API int libbpf_attach_type_by_name(const char *name,
+					  enum bpf_attach_type *attach_type);
 
 /* Accessors of bpf_program */
 struct bpf_program;
-struct bpf_program *bpf_program__next(struct bpf_program *prog,
-				      struct bpf_object *obj);
+LIBBPF_API struct bpf_program *bpf_program__next(struct bpf_program *prog,
+						 struct bpf_object *obj);
 
 #define bpf_object__for_each_program(pos, obj)		\
 	for ((pos) = bpf_program__next(NULL, (obj));	\
@@ -109,21 +115,24 @@ struct bpf_program *bpf_program__next(struct bpf_program *prog,
 typedef void (*bpf_program_clear_priv_t)(struct bpf_program *,
 					 void *);
 
-int bpf_program__set_priv(struct bpf_program *prog, void *priv,
-			  bpf_program_clear_priv_t clear_priv);
+LIBBPF_API int bpf_program__set_priv(struct bpf_program *prog, void *priv,
+				     bpf_program_clear_priv_t clear_priv);
 
-void *bpf_program__priv(struct bpf_program *prog);
-void bpf_program__set_ifindex(struct bpf_program *prog, __u32 ifindex);
+LIBBPF_API void *bpf_program__priv(struct bpf_program *prog);
+LIBBPF_API void bpf_program__set_ifindex(struct bpf_program *prog,
+					 __u32 ifindex);
 
-const char *bpf_program__title(struct bpf_program *prog, bool needs_copy);
+LIBBPF_API const char *bpf_program__title(struct bpf_program *prog,
+					  bool needs_copy);
 
-int bpf_program__load(struct bpf_program *prog, char *license,
-		      __u32 kern_version);
-int bpf_program__fd(struct bpf_program *prog);
-int bpf_program__pin_instance(struct bpf_program *prog, const char *path,
-			      int instance);
-int bpf_program__pin(struct bpf_program *prog, const char *path);
-void bpf_program__unload(struct bpf_program *prog);
+LIBBPF_API int bpf_program__load(struct bpf_program *prog, char *license,
+				 __u32 kern_version);
+LIBBPF_API int bpf_program__fd(struct bpf_program *prog);
+LIBBPF_API int bpf_program__pin_instance(struct bpf_program *prog,
+					 const char *path,
+					 int instance);
+LIBBPF_API int bpf_program__pin(struct bpf_program *prog, const char *path);
+LIBBPF_API void bpf_program__unload(struct bpf_program *prog);
 
 struct bpf_insn;
 
@@ -184,34 +193,36 @@ typedef int (*bpf_program_prep_t)(struct bpf_program *prog, int n,
 				  struct bpf_insn *insns, int insns_cnt,
 				  struct bpf_prog_prep_result *res);
 
-int bpf_program__set_prep(struct bpf_program *prog, int nr_instance,
-			  bpf_program_prep_t prep);
+LIBBPF_API int bpf_program__set_prep(struct bpf_program *prog, int nr_instance,
+				     bpf_program_prep_t prep);
 
-int bpf_program__nth_fd(struct bpf_program *prog, int n);
+LIBBPF_API int bpf_program__nth_fd(struct bpf_program *prog, int n);
 
 /*
  * Adjust type of BPF program. Default is kprobe.
  */
-int bpf_program__set_socket_filter(struct bpf_program *prog);
-int bpf_program__set_tracepoint(struct bpf_program *prog);
-int bpf_program__set_raw_tracepoint(struct bpf_program *prog);
-int bpf_program__set_kprobe(struct bpf_program *prog);
-int bpf_program__set_sched_cls(struct bpf_program *prog);
-int bpf_program__set_sched_act(struct bpf_program *prog);
-int bpf_program__set_xdp(struct bpf_program *prog);
-int bpf_program__set_perf_event(struct bpf_program *prog);
-void bpf_program__set_type(struct bpf_program *prog, enum bpf_prog_type type);
-void bpf_program__set_expected_attach_type(struct bpf_program *prog,
-					   enum bpf_attach_type type);
-
-bool bpf_program__is_socket_filter(struct bpf_program *prog);
-bool bpf_program__is_tracepoint(struct bpf_program *prog);
-bool bpf_program__is_raw_tracepoint(struct bpf_program *prog);
-bool bpf_program__is_kprobe(struct bpf_program *prog);
-bool bpf_program__is_sched_cls(struct bpf_program *prog);
-bool bpf_program__is_sched_act(struct bpf_program *prog);
-bool bpf_program__is_xdp(struct bpf_program *prog);
-bool bpf_program__is_perf_event(struct bpf_program *prog);
+LIBBPF_API int bpf_program__set_socket_filter(struct bpf_program *prog);
+LIBBPF_API int bpf_program__set_tracepoint(struct bpf_program *prog);
+LIBBPF_API int bpf_program__set_raw_tracepoint(struct bpf_program *prog);
+LIBBPF_API int bpf_program__set_kprobe(struct bpf_program *prog);
+LIBBPF_API int bpf_program__set_sched_cls(struct bpf_program *prog);
+LIBBPF_API int bpf_program__set_sched_act(struct bpf_program *prog);
+LIBBPF_API int bpf_program__set_xdp(struct bpf_program *prog);
+LIBBPF_API int bpf_program__set_perf_event(struct bpf_program *prog);
+LIBBPF_API void bpf_program__set_type(struct bpf_program *prog,
+				      enum bpf_prog_type type);
+LIBBPF_API void
+bpf_program__set_expected_attach_type(struct bpf_program *prog,
+				      enum bpf_attach_type type);
+
+LIBBPF_API bool bpf_program__is_socket_filter(struct bpf_program *prog);
+LIBBPF_API bool bpf_program__is_tracepoint(struct bpf_program *prog);
+LIBBPF_API bool bpf_program__is_raw_tracepoint(struct bpf_program *prog);
+LIBBPF_API bool bpf_program__is_kprobe(struct bpf_program *prog);
+LIBBPF_API bool bpf_program__is_sched_cls(struct bpf_program *prog);
+LIBBPF_API bool bpf_program__is_sched_act(struct bpf_program *prog);
+LIBBPF_API bool bpf_program__is_xdp(struct bpf_program *prog);
+LIBBPF_API bool bpf_program__is_perf_event(struct bpf_program *prog);
 
 /*
  * No need for __attribute__((packed)), all members of 'bpf_map_def'
@@ -232,39 +243,39 @@ struct bpf_map_def {
  * so no need to worry about a name clash.
  */
 struct bpf_map;
-struct bpf_map *
+LIBBPF_API struct bpf_map *
 bpf_object__find_map_by_name(struct bpf_object *obj, const char *name);
 
 /*
  * Get bpf_map through the offset of corresponding struct bpf_map_def
  * in the BPF object file.
  */
-struct bpf_map *
+LIBBPF_API struct bpf_map *
 bpf_object__find_map_by_offset(struct bpf_object *obj, size_t offset);
 
-struct bpf_map *
+LIBBPF_API struct bpf_map *
 bpf_map__next(struct bpf_map *map, struct bpf_object *obj);
 #define bpf_map__for_each(pos, obj)		\
 	for ((pos) = bpf_map__next(NULL, (obj));	\
 	     (pos) != NULL;				\
 	     (pos) = bpf_map__next((pos), (obj)))
 
-int bpf_map__fd(struct bpf_map *map);
-const struct bpf_map_def *bpf_map__def(struct bpf_map *map);
-const char *bpf_map__name(struct bpf_map *map);
-__u32 bpf_map__btf_key_type_id(const struct bpf_map *map);
-__u32 bpf_map__btf_value_type_id(const struct bpf_map *map);
+LIBBPF_API int bpf_map__fd(struct bpf_map *map);
+LIBBPF_API const struct bpf_map_def *bpf_map__def(struct bpf_map *map);
+LIBBPF_API const char *bpf_map__name(struct bpf_map *map);
+LIBBPF_API __u32 bpf_map__btf_key_type_id(const struct bpf_map *map);
+LIBBPF_API __u32 bpf_map__btf_value_type_id(const struct bpf_map *map);
 
 typedef void (*bpf_map_clear_priv_t)(struct bpf_map *, void *);
-int bpf_map__set_priv(struct bpf_map *map, void *priv,
-		      bpf_map_clear_priv_t clear_priv);
-void *bpf_map__priv(struct bpf_map *map);
-int bpf_map__reuse_fd(struct bpf_map *map, int fd);
-bool bpf_map__is_offload_neutral(struct bpf_map *map);
-void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex);
-int bpf_map__pin(struct bpf_map *map, const char *path);
+LIBBPF_API int bpf_map__set_priv(struct bpf_map *map, void *priv,
+				 bpf_map_clear_priv_t clear_priv);
+LIBBPF_API void *bpf_map__priv(struct bpf_map *map);
+LIBBPF_API int bpf_map__reuse_fd(struct bpf_map *map, int fd);
+LIBBPF_API bool bpf_map__is_offload_neutral(struct bpf_map *map);
+LIBBPF_API void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex);
+LIBBPF_API int bpf_map__pin(struct bpf_map *map, const char *path);
 
-long libbpf_get_error(const void *ptr);
+LIBBPF_API long libbpf_get_error(const void *ptr);
 
 struct bpf_prog_load_attr {
 	const char *file;
@@ -273,12 +284,12 @@ struct bpf_prog_load_attr {
 	int ifindex;
 };
 
-int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
-			struct bpf_object **pobj, int *prog_fd);
-int bpf_prog_load(const char *file, enum bpf_prog_type type,
-		  struct bpf_object **pobj, int *prog_fd);
+LIBBPF_API int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
+				   struct bpf_object **pobj, int *prog_fd);
+LIBBPF_API int bpf_prog_load(const char *file, enum bpf_prog_type type,
+			     struct bpf_object **pobj, int *prog_fd);
 
-int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags);
+LIBBPF_API int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags);
 
 enum bpf_perf_event_ret {
 	LIBBPF_PERF_EVENT_DONE	= 0,
@@ -286,12 +297,14 @@ enum bpf_perf_event_ret {
 	LIBBPF_PERF_EVENT_CONT	= -2,
 };
 
-typedef enum bpf_perf_event_ret (*bpf_perf_event_print_t)(void *event,
-							  void *priv);
-int bpf_perf_event_read_simple(void *mem, unsigned long size,
-			       unsigned long page_size,
-			       void **buf, size_t *buf_len,
-			       bpf_perf_event_print_t fn, void *priv);
+struct perf_event_header;
+typedef enum bpf_perf_event_ret
+	(*bpf_perf_event_print_t)(struct perf_event_header *hdr,
+				  void *private_data);
+LIBBPF_API enum bpf_perf_event_ret
+bpf_perf_event_read_simple(void *mmap_mem, size_t mmap_size, size_t page_size,
+			   void **copy_mem, size_t *copy_size,
+			   bpf_perf_event_print_t fn, void *private_data);
 
 struct nlattr;
 typedef int (*libbpf_dump_nlmsg_t)(void *cookie, void *msg, struct nlattr **tb);

tools/perf/util/mmap.h

@@ -4,7 +4,7 @@
 #include <linux/compiler.h>
 #include <linux/refcount.h>
 #include <linux/types.h>
-#include <asm/barrier.h>
+#include <linux/ring_buffer.h>
 #include <stdbool.h>
 #include "auxtrace.h"
 #include "event.h"
@@ -71,21 +71,12 @@ void perf_mmap__consume(struct perf_mmap *map);
 
 static inline u64 perf_mmap__read_head(struct perf_mmap *mm)
 {
-	struct perf_event_mmap_page *pc = mm->base;
-	u64 head = READ_ONCE(pc->data_head);
-	rmb();
-	return head;
+	return ring_buffer_read_head(mm->base);
 }
 
 static inline void perf_mmap__write_tail(struct perf_mmap *md, u64 tail)
 {
-	struct perf_event_mmap_page *pc = md->base;
-
-	/*
-	 * ensure all reads are done before we write the tail out.
-	 */
-	mb();
-	pc->data_tail = tail;
+	ring_buffer_write_tail(md->base, tail);
 }
 
 union perf_event *perf_mmap__read_forward(struct perf_mmap *map);

tools/testing/selftests/bpf/.gitignore

@@ -25,3 +25,5 @@ test_cgroup_storage
 test_select_reuseport
 test_flow_dissector
 flow_dissector_load
+test_netcnt
+test_section_names

tools/testing/selftests/bpf/Makefile

@@ -37,7 +37,7 @@ TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test
 	test_lwt_seg6local.o sendmsg4_prog.o sendmsg6_prog.o test_lirc_mode2_kern.o \
 	get_cgroup_id_kern.o socket_cookie_prog.o test_select_reuseport_kern.o \
 	test_skb_cgroup_id_kern.o bpf_flow.o netcnt_prog.o \
-	test_sk_lookup_kern.o test_xdp_vlan.o
+	test_sk_lookup_kern.o test_xdp_vlan.o test_queue_map.o test_stack_map.o
 
 # Order correspond to 'make run_tests' order
 TEST_PROGS := test_kmod.sh \
@@ -118,6 +118,9 @@ CLANG_FLAGS = -I. -I./include/uapi -I../../../include/uapi \
 $(OUTPUT)/test_l4lb_noinline.o: CLANG_FLAGS += -fno-inline
 $(OUTPUT)/test_xdp_noinline.o: CLANG_FLAGS += -fno-inline
 
+$(OUTPUT)/test_queue_map.o: test_queue_stack_map.h
+$(OUTPUT)/test_stack_map.o: test_queue_stack_map.h
+
 BTF_LLC_PROBE := $(shell $(LLC) -march=bpf -mattr=help 2>&1 | grep dwarfris)
 BTF_PAHOLE_PROBE := $(shell $(BTF_PAHOLE) --help 2>&1 | grep BTF)
 BTF_OBJCOPY_PROBE := $(shell $(LLVM_OBJCOPY) --help 2>&1 | grep -i 'usage.*llvm')

tools/testing/selftests/bpf/bpf_helpers.h

@@ -16,6 +16,13 @@ static int (*bpf_map_update_elem)(void *map, void *key, void *value,
 	(void *) BPF_FUNC_map_update_elem;
 static int (*bpf_map_delete_elem)(void *map, void *key) =
 	(void *) BPF_FUNC_map_delete_elem;
+static int (*bpf_map_push_elem)(void *map, void *value,
+				unsigned long long flags) =
+	(void *) BPF_FUNC_map_push_elem;
+static int (*bpf_map_pop_elem)(void *map, void *value) =
+	(void *) BPF_FUNC_map_pop_elem;
+static int (*bpf_map_peek_elem)(void *map, void *value) =
+	(void *) BPF_FUNC_map_peek_elem;
 static int (*bpf_probe_read)(void *dst, int size, void *unsafe_ptr) =
 	(void *) BPF_FUNC_probe_read;
 static unsigned long long (*bpf_ktime_get_ns)(void) =
@@ -104,6 +111,8 @@ static int (*bpf_msg_cork_bytes)(void *ctx, int len) =
 	(void *) BPF_FUNC_msg_cork_bytes;
 static int (*bpf_msg_pull_data)(void *ctx, int start, int end, int flags) =
 	(void *) BPF_FUNC_msg_pull_data;
+static int (*bpf_msg_push_data)(void *ctx, int start, int end, int flags) =
+	(void *) BPF_FUNC_msg_push_data;
 static int (*bpf_bind)(void *ctx, void *addr, int addr_len) =
 	(void *) BPF_FUNC_bind;
 static int (*bpf_xdp_adjust_tail)(void *ctx, int offset) =

tools/testing/selftests/bpf/test_libbpf.sh

@@ -6,7 +6,7 @@ export TESTNAME=test_libbpf
 # Determine selftest success via shell exit code
 exit_handler()
 {
-	if (( $? == 0 )); then
+	if [ $? -eq 0 ]; then
 		echo "selftests: $TESTNAME [PASS]";
 	else
 		echo "$TESTNAME: failed at file $LAST_LOADED" 1>&2

tools/testing/selftests/bpf/test_maps.c

@@ -15,6 +15,7 @@
 #include <string.h>
 #include <assert.h>
 #include <stdlib.h>
+#include <time.h>
 
 #include <sys/wait.h>
 #include <sys/socket.h>
@@ -471,6 +472,122 @@ static void test_devmap(int task, void *data)
 	close(fd);
 }
 
+static void test_queuemap(int task, void *data)
+{
+	const int MAP_SIZE = 32;
+	__u32 vals[MAP_SIZE + MAP_SIZE/2], val;
+	int fd, i;
+
+	/* Fill test values to be used */
+	for (i = 0; i < MAP_SIZE + MAP_SIZE/2; i++)
+		vals[i] = rand();
+
+	/* Invalid key size */
+	fd = bpf_create_map(BPF_MAP_TYPE_QUEUE, 4, sizeof(val), MAP_SIZE,
+			    map_flags);
+	assert(fd < 0 && errno == EINVAL);
+
+	fd = bpf_create_map(BPF_MAP_TYPE_QUEUE, 0, sizeof(val), MAP_SIZE,
+			    map_flags);
+	/* Queue map does not support BPF_F_NO_PREALLOC */
+	if (map_flags & BPF_F_NO_PREALLOC) {
+		assert(fd < 0 && errno == EINVAL);
+		return;
+	}
+	if (fd < 0) {
+		printf("Failed to create queuemap '%s'!\n", strerror(errno));
+		exit(1);
+	}
+
+	/* Push MAP_SIZE elements */
+	for (i = 0; i < MAP_SIZE; i++)
+		assert(bpf_map_update_elem(fd, NULL, &vals[i], 0) == 0);
+
+	/* Check that element cannot be pushed due to max_entries limit */
+	assert(bpf_map_update_elem(fd, NULL, &val, 0) == -1 &&
+	       errno == E2BIG);
+
+	/* Peek element */
+	assert(bpf_map_lookup_elem(fd, NULL, &val) == 0 && val == vals[0]);
+
+	/* Replace half elements */
+	for (i = MAP_SIZE; i < MAP_SIZE + MAP_SIZE/2; i++)
+		assert(bpf_map_update_elem(fd, NULL, &vals[i], BPF_EXIST) == 0);
+
+	/* Pop all elements */
+	for (i = MAP_SIZE/2; i < MAP_SIZE + MAP_SIZE/2; i++)
+		assert(bpf_map_lookup_and_delete_elem(fd, NULL, &val) == 0 &&
+		       val == vals[i]);
+
+	/* Check that there are not elements left */
+	assert(bpf_map_lookup_and_delete_elem(fd, NULL, &val) == -1 &&
+	       errno == ENOENT);
+
+	/* Check that non supported functions set errno to EINVAL */
+	assert(bpf_map_delete_elem(fd, NULL) == -1 && errno == EINVAL);
+	assert(bpf_map_get_next_key(fd, NULL, NULL) == -1 && errno == EINVAL);
+
+	close(fd);
+}
+
+static void test_stackmap(int task, void *data)
+{
+	const int MAP_SIZE = 32;
+	__u32 vals[MAP_SIZE + MAP_SIZE/2], val;
+	int fd, i;
+
+	/* Fill test values to be used */
+	for (i = 0; i < MAP_SIZE + MAP_SIZE/2; i++)
+		vals[i] = rand();
+
+	/* Invalid key size */
+	fd = bpf_create_map(BPF_MAP_TYPE_STACK, 4, sizeof(val), MAP_SIZE,
+			    map_flags);
+	assert(fd < 0 && errno == EINVAL);
+
+	fd = bpf_create_map(BPF_MAP_TYPE_STACK, 0, sizeof(val), MAP_SIZE,
+			    map_flags);
+	/* Stack map does not support BPF_F_NO_PREALLOC */
+	if (map_flags & BPF_F_NO_PREALLOC) {
+		assert(fd < 0 && errno == EINVAL);
+		return;
+	}
+	if (fd < 0) {
+		printf("Failed to create stackmap '%s'!\n", strerror(errno));
+		exit(1);
+	}
+
+	/* Push MAP_SIZE elements */
+	for (i = 0; i < MAP_SIZE; i++)
+		assert(bpf_map_update_elem(fd, NULL, &vals[i], 0) == 0);
+
+	/* Check that element cannot be pushed due to max_entries limit */
+	assert(bpf_map_update_elem(fd, NULL, &val, 0) == -1 &&
+	       errno == E2BIG);
+
+	/* Peek element */
+	assert(bpf_map_lookup_elem(fd, NULL, &val) == 0 && val == vals[i - 1]);
+
+	/* Replace half elements */
+	for (i = MAP_SIZE; i < MAP_SIZE + MAP_SIZE/2; i++)
+		assert(bpf_map_update_elem(fd, NULL, &vals[i], BPF_EXIST) == 0);
+
+	/* Pop all elements */
+	for (i = MAP_SIZE + MAP_SIZE/2 - 1; i >= MAP_SIZE/2; i--)
+		assert(bpf_map_lookup_and_delete_elem(fd, NULL, &val) == 0 &&
+		       val == vals[i]);
+
+	/* Check that there are not elements left */
+	assert(bpf_map_lookup_and_delete_elem(fd, NULL, &val) == -1 &&
+	       errno == ENOENT);
+
+	/* Check that non supported functions set errno to EINVAL */
+	assert(bpf_map_delete_elem(fd, NULL) == -1 && errno == EINVAL);
+	assert(bpf_map_get_next_key(fd, NULL, NULL) == -1 && errno == EINVAL);
+
+	close(fd);
+}
+
 #include <sys/socket.h>
 #include <sys/ioctl.h>
 #include <arpa/inet.h>
@@ -1434,10 +1551,15 @@ static void run_all_tests(void)
 	test_map_wronly();
 
 	test_reuseport_array();
+
+	test_queuemap(0, NULL);
+	test_stackmap(0, NULL);
 }
 
 int main(void)
 {
+	srand(time(NULL));
+
 	map_flags = 0;
 	run_all_tests();
 

tools/testing/selftests/bpf/test_progs.c

@@ -1735,8 +1735,105 @@ static void test_reference_tracking()
 	bpf_object__close(obj);
 }
 
+enum {
+	QUEUE,
+	STACK,
+};
+
+static void test_queue_stack_map(int type)
+{
+	const int MAP_SIZE = 32;
+	__u32 vals[MAP_SIZE], duration, retval, size, val;
+	int i, err, prog_fd, map_in_fd, map_out_fd;
+	char file[32], buf[128];
+	struct bpf_object *obj;
+	struct iphdr *iph = (void *)buf + sizeof(struct ethhdr);
+
+	/* Fill test values to be used */
+	for (i = 0; i < MAP_SIZE; i++)
+		vals[i] = rand();
+
+	if (type == QUEUE)
+		strncpy(file, "./test_queue_map.o", sizeof(file));
+	else if (type == STACK)
+		strncpy(file, "./test_stack_map.o", sizeof(file));
+	else
+		return;
+
+	err = bpf_prog_load(file, BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd);
+	if (err) {
+		error_cnt++;
+		return;
+	}
+
+	map_in_fd = bpf_find_map(__func__, obj, "map_in");
+	if (map_in_fd < 0)
+		goto out;
+
+	map_out_fd = bpf_find_map(__func__, obj, "map_out");
+	if (map_out_fd < 0)
+		goto out;
+
+	/* Push 32 elements to the input map */
+	for (i = 0; i < MAP_SIZE; i++) {
+		err = bpf_map_update_elem(map_in_fd, NULL, &vals[i], 0);
+		if (err) {
+			error_cnt++;
+			goto out;
+		}
+	}
+
+	/* The eBPF program pushes iph.saddr in the output map,
+	 * pops the input map and saves this value in iph.daddr
+	 */
+	for (i = 0; i < MAP_SIZE; i++) {
+		if (type == QUEUE) {
+			val = vals[i];
+			pkt_v4.iph.saddr = vals[i] * 5;
+		} else if (type == STACK) {
+			val = vals[MAP_SIZE - 1 - i];
+			pkt_v4.iph.saddr = vals[MAP_SIZE - 1 - i] * 5;
+		}
+
+		err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4),
+					buf, &size, &retval, &duration);
+		if (err || retval || size != sizeof(pkt_v4) ||
+		    iph->daddr != val)
+			break;
+	}
+
+	CHECK(err || retval || size != sizeof(pkt_v4) || iph->daddr != val,
+	      "bpf_map_pop_elem",
+	      "err %d errno %d retval %d size %d iph->daddr %u\n",
+	      err, errno, retval, size, iph->daddr);
+
+	/* Queue is empty, program should return TC_ACT_SHOT */
+	err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4),
+				buf, &size, &retval, &duration);
+	CHECK(err || retval != 2 /* TC_ACT_SHOT */|| size != sizeof(pkt_v4),
+	      "check-queue-stack-map-empty",
+	      "err %d errno %d retval %d size %d\n",
+	      err, errno, retval, size);
+
+	/* Check that the program pushed elements correctly */
+	for (i = 0; i < MAP_SIZE; i++) {
+		err = bpf_map_lookup_and_delete_elem(map_out_fd, NULL, &val);
+		if (err || val != vals[i] * 5)
+			break;
+	}
+
+	CHECK(i != MAP_SIZE && (err || val != vals[i] * 5),
+	      "bpf_map_push_elem", "err %d value %u\n", err, val);
+
+out:
+	pkt_v4.iph.saddr = 0;
+	bpf_object__close(obj);
+}
+
 int main(void)
 {
+	srand(time(NULL));
+
 	jit_enabled = is_jit_enabled();
 
 	test_pkt_access();
@@ -1757,6 +1854,8 @@ int main(void)
 	test_task_fd_query_rawtp();
 	test_task_fd_query_tp();
 	test_reference_tracking();
+	test_queue_stack_map(QUEUE);
+	test_queue_stack_map(STACK);
 
 	printf("Summary: %d PASSED, %d FAILED\n", pass_cnt, error_cnt);
 	return error_cnt ? EXIT_FAILURE : EXIT_SUCCESS;

tools/testing/selftests/bpf/test_queue_map.c

@@ -0,0 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2018 Politecnico di Torino
+#define MAP_TYPE BPF_MAP_TYPE_QUEUE
+#include "test_queue_stack_map.h"

tools/testing/selftests/bpf/test_queue_stack_map.h

@@ -0,0 +1,59 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+// Copyright (c) 2018 Politecnico di Torino
+#include <stddef.h>
+#include <string.h>
+#include <linux/bpf.h>
+#include <linux/if_ether.h>
+#include <linux/ip.h>
+#include <linux/pkt_cls.h>
+#include "bpf_helpers.h"
+
+int _version SEC("version") = 1;
+
+struct bpf_map_def __attribute__ ((section("maps"), used)) map_in = {
+	.type = MAP_TYPE,
+	.key_size = 0,
+	.value_size = sizeof(__u32),
+	.max_entries = 32,
+	.map_flags = 0,
+};
+
+struct bpf_map_def __attribute__ ((section("maps"), used)) map_out = {
+	.type = MAP_TYPE,
+	.key_size = 0,
+	.value_size = sizeof(__u32),
+	.max_entries = 32,
+	.map_flags = 0,
+};
+
+SEC("test")
+int _test(struct __sk_buff *skb)
+{
+	void *data_end = (void *)(long)skb->data_end;
+	void *data = (void *)(long)skb->data;
+	struct ethhdr *eth = (struct ethhdr *)(data);
+	__u32 value;
+	int err;
+
+	if (eth + 1 > data_end)
+		return TC_ACT_SHOT;
+
+	struct iphdr *iph = (struct iphdr *)(eth + 1);
+
+	if (iph + 1 > data_end)
+		return TC_ACT_SHOT;
+
+	err = bpf_map_pop_elem(&map_in, &value);
+	if (err)
+		return TC_ACT_SHOT;
+
+	iph->daddr = value;
+
+	err = bpf_map_push_elem(&map_out, &iph->saddr, 0);
+	if (err)
+		return TC_ACT_SHOT;
+
+	return TC_ACT_OK;
+}
+
+char _license[] SEC("license") = "GPL";

tools/testing/selftests/bpf/test_sockmap.c

@@ -28,6 +28,7 @@
 #include <linux/sock_diag.h>
 #include <linux/bpf.h>
 #include <linux/if_link.h>
+#include <linux/tls.h>
 #include <assert.h>
 #include <libgen.h>
 
@@ -43,6 +44,13 @@
 int running;
 static void running_handler(int a);
 
+#ifndef TCP_ULP
+# define TCP_ULP 31
+#endif
+#ifndef SOL_TLS
+# define SOL_TLS 282
+#endif
+
 /* randomly selected ports for testing on lo */
 #define S1_PORT 10000
 #define S2_PORT 10001
@@ -69,9 +77,12 @@ int txmsg_apply;
 int txmsg_cork;
 int txmsg_start;
 int txmsg_end;
+int txmsg_start_push;
+int txmsg_end_push;
 int txmsg_ingress;
 int txmsg_skb;
 int ktls;
+int peek_flag;
 
 static const struct option long_options[] = {
 	{"help",	no_argument,		NULL, 'h' },
@@ -91,9 +102,12 @@ static const struct option long_options[] = {
 	{"txmsg_cork",	required_argument,	NULL, 'k'},
 	{"txmsg_start", required_argument,	NULL, 's'},
 	{"txmsg_end",	required_argument,	NULL, 'e'},
+	{"txmsg_start_push", required_argument,	NULL, 'p'},
+	{"txmsg_end_push",   required_argument,	NULL, 'q'},
 	{"txmsg_ingress", no_argument,		&txmsg_ingress, 1 },
 	{"txmsg_skb", no_argument,		&txmsg_skb, 1 },
 	{"ktls", no_argument,			&ktls, 1 },
+	{"peek", no_argument,			&peek_flag, 1 },
 	{0, 0, NULL, 0 }
 };
 
@@ -114,11 +128,6 @@ static void usage(char *argv[])
 	printf("\n");
 }
 
-#define TCP_ULP 31
-#define TLS_TX 1
-#define TLS_RX 2
-#include <linux/tls.h>
-
 char *sock_to_string(int s)
 {
 	if (s == c1)
@@ -349,33 +358,40 @@ static int msg_loop_sendpage(int fd, int iov_length, int cnt,
 	return 0;
 }
 
-static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
-		    struct msg_stats *s, bool tx,
-		    struct sockmap_options *opt)
+static void msg_free_iov(struct msghdr *msg)
 {
-	struct msghdr msg = {0};
-	int err, i, flags = MSG_NOSIGNAL;
+	int i;
+
+	for (i = 0; i < msg->msg_iovlen; i++)
+		free(msg->msg_iov[i].iov_base);
+	free(msg->msg_iov);
+	msg->msg_iov = NULL;
+	msg->msg_iovlen = 0;
+}
+
+static int msg_alloc_iov(struct msghdr *msg,
+			 int iov_count, int iov_length,
+			 bool data, bool xmit)
+{
+	unsigned char k = 0;
 	struct iovec *iov;
-	unsigned char k;
-	bool data_test = opt->data_test;
-	bool drop = opt->drop_expected;
+	int i;
 
 	iov = calloc(iov_count, sizeof(struct iovec));
 	if (!iov)
 		return errno;
 
-	k = 0;
 	for (i = 0; i < iov_count; i++) {
 		unsigned char *d = calloc(iov_length, sizeof(char));
 
 		if (!d) {
 			fprintf(stderr, "iov_count %i/%i OOM\n", i, iov_count);
-			goto out_errno;
+			goto unwind_iov;
 		}
 		iov[i].iov_base = d;
 		iov[i].iov_len = iov_length;
 
-		if (data_test && tx) {
+		if (data && xmit) {
 			int j;
 
 			for (j = 0; j < iov_length; j++)
@@ -383,9 +399,60 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
 		}
 	}
 
-	msg.msg_iov = iov;
-	msg.msg_iovlen = iov_count;
-	k = 0;
+	msg->msg_iov = iov;
+	msg->msg_iovlen = iov_count;
+
+	return 0;
+unwind_iov:
+	for (i--; i >= 0 ; i--)
+		free(msg->msg_iov[i].iov_base);
+	return -ENOMEM;
+}
+
+static int msg_verify_data(struct msghdr *msg, int size, int chunk_sz)
+{
+	int i, j, bytes_cnt = 0;
+	unsigned char k = 0;
+
+	for (i = 0; i < msg->msg_iovlen; i++) {
+		unsigned char *d = msg->msg_iov[i].iov_base;
+
+		for (j = 0;
+		     j < msg->msg_iov[i].iov_len && size; j++) {
+			if (d[j] != k++) {
+				fprintf(stderr,
+					"detected data corruption @iov[%i]:%i %02x != %02x, %02x ?= %02x\n",
+					i, j, d[j], k - 1, d[j+1], k);
+				return -EIO;
+			}
+			bytes_cnt++;
+			if (bytes_cnt == chunk_sz) {
+				k = 0;
+				bytes_cnt = 0;
+			}
+			size--;
+		}
+	}
+	return 0;
+}
+
+static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
+		    struct msg_stats *s, bool tx,
+		    struct sockmap_options *opt)
+{
+	struct msghdr msg = {0}, msg_peek = {0};
+	int err, i, flags = MSG_NOSIGNAL;
+	bool drop = opt->drop_expected;
+	bool data = opt->data_test;
+
+	err = msg_alloc_iov(&msg, iov_count, iov_length, data, tx);
+	if (err)
+		goto out_errno;
+	if (peek_flag) {
+		err = msg_alloc_iov(&msg_peek, iov_count, iov_length, data, tx);
+		if (err)
+			goto out_errno;
+	}
 
 	if (tx) {
 		clock_gettime(CLOCK_MONOTONIC, &s->start);
@@ -405,19 +472,12 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
 		}
 		clock_gettime(CLOCK_MONOTONIC, &s->end);
 	} else {
-		int slct, recv, max_fd = fd;
+		int slct, recvp = 0, recv, max_fd = fd;
 		int fd_flags = O_NONBLOCK;
 		struct timeval timeout;
 		float total_bytes;
-		int bytes_cnt = 0;
-		int chunk_sz;
 		fd_set w;
 
-		if (opt->sendpage)
-			chunk_sz = iov_length * cnt;
-		else
-			chunk_sz = iov_length * iov_count;
-
 		fcntl(fd, fd_flags);
 		total_bytes = (float)iov_count * (float)iov_length * (float)cnt;
 		err = clock_gettime(CLOCK_MONOTONIC, &s->start);
@@ -449,6 +509,19 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
 				goto out_errno;
 			}
 
+			errno = 0;
+			if (peek_flag) {
+				flags |= MSG_PEEK;
+				recvp = recvmsg(fd, &msg_peek, flags);
+				if (recvp < 0) {
+					if (errno != EWOULDBLOCK) {
+						clock_gettime(CLOCK_MONOTONIC, &s->end);
+						goto out_errno;
+					}
+				}
+				flags = 0;
+			}
+
 			recv = recvmsg(fd, &msg, flags);
 			if (recv < 0) {
 				if (errno != EWOULDBLOCK) {
@@ -460,27 +533,23 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
 
 			s->bytes_recvd += recv;
 
-			if (data_test) {
-				int j;
-
-				for (i = 0; i < msg.msg_iovlen; i++) {
-					unsigned char *d = iov[i].iov_base;
-
-					for (j = 0;
-					     j < iov[i].iov_len && recv; j++) {
-						if (d[j] != k++) {
-							errno = -EIO;
-							fprintf(stderr,
-								"detected data corruption @iov[%i]:%i %02x != %02x, %02x ?= %02x\n",
-								i, j, d[j], k - 1, d[j+1], k);
-							goto out_errno;
-						}
-						bytes_cnt++;
-						if (bytes_cnt == chunk_sz) {
-							k = 0;
-							bytes_cnt = 0;
-						}
-						recv--;
+			if (data) {
+				int chunk_sz = opt->sendpage ?
+						iov_length * cnt :
+						iov_length * iov_count;
+
+				errno = msg_verify_data(&msg, recv, chunk_sz);
+				if (errno) {
+					perror("data verify msg failed\n");
+					goto out_errno;
+				}
+				if (recvp) {
+					errno = msg_verify_data(&msg_peek,
+								recvp,
+								chunk_sz);
+					if (errno) {
+						perror("data verify msg_peek failed\n");
+						goto out_errno;
 					}
 				}
 			}
@@ -488,14 +557,12 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
 		clock_gettime(CLOCK_MONOTONIC, &s->end);
 	}
 
-	for (i = 0; i < iov_count; i++)
-		free(iov[i].iov_base);
-	free(iov);
-	return 0;
+	msg_free_iov(&msg);
+	msg_free_iov(&msg_peek);
+	return err;
 out_errno:
-	for (i = 0; i < iov_count; i++)
-		free(iov[i].iov_base);
-	free(iov);
+	msg_free_iov(&msg);
+	msg_free_iov(&msg_peek);
 	return errno;
 }
 
@@ -562,9 +629,10 @@ static int sendmsg_test(struct sockmap_options *opt)
 		}
 		if (opt->verbose)
 			fprintf(stdout,
-				"rx_sendmsg: TX: %zuB %fB/s %fGB/s RX: %zuB %fB/s %fGB/s\n",
+				"rx_sendmsg: TX: %zuB %fB/s %fGB/s RX: %zuB %fB/s %fGB/s %s\n",
 				s.bytes_sent, sent_Bps, sent_Bps/giga,
-				s.bytes_recvd, recvd_Bps, recvd_Bps/giga);
+				s.bytes_recvd, recvd_Bps, recvd_Bps/giga,
+				peek_flag ? "(peek_msg)" : "");
 		if (err && txmsg_cork)
 			err = 0;
 		exit(err ? 1 : 0);
@@ -839,6 +907,30 @@ run:
 			}
 		}
 
+		if (txmsg_start_push) {
+			i = 2;
+			err = bpf_map_update_elem(map_fd[5],
+						  &i, &txmsg_start_push, BPF_ANY);
+			if (err) {
+				fprintf(stderr,
+					"ERROR: bpf_map_update_elem (txmsg_start_push):  %d (%s)\n",
+					err, strerror(errno));
+				goto out;
+			}
+		}
+
+		if (txmsg_end_push) {
+			i = 3;
+			err = bpf_map_update_elem(map_fd[5],
+						  &i, &txmsg_end_push, BPF_ANY);
+			if (err) {
+				fprintf(stderr,
+					"ERROR: bpf_map_update_elem %i@%i (txmsg_end_push):  %d (%s)\n",
+					txmsg_end_push, i, err, strerror(errno));
+				goto out;
+			}
+		}
+
 		if (txmsg_ingress) {
 			int in = BPF_F_INGRESS;
 
@@ -996,6 +1088,8 @@ static void test_options(char *options)
 		strncat(options, "skb,", OPTSTRING);
 	if (ktls)
 		strncat(options, "ktls,", OPTSTRING);
+	if (peek_flag)
+		strncat(options, "peek,", OPTSTRING);
 }
 
 static int __test_exec(int cgrp, int test, struct sockmap_options *opt)
@@ -1169,6 +1263,8 @@ static int test_mixed(int cgrp)
 	txmsg_pass = txmsg_noisy = txmsg_redir_noisy = txmsg_drop = 0;
 	txmsg_apply = txmsg_cork = 0;
 	txmsg_start = txmsg_end = 0;
+	txmsg_start_push = txmsg_end_push = 0;
+
 	/* Test small and large iov_count values with pass/redir/apply/cork */
 	txmsg_pass = 1;
 	txmsg_redir = 0;
@@ -1285,6 +1381,8 @@ static int test_start_end(int cgrp)
 	/* Test basic start/end with lots of iov_count and iov_lengths */
 	txmsg_start = 1;
 	txmsg_end = 2;
+	txmsg_start_push = 1;
+	txmsg_end_push = 2;
 	err = test_txmsg(cgrp);
 	if (err)
 		goto out;
@@ -1298,6 +1396,8 @@ static int test_start_end(int cgrp)
 	for (i = 99; i <= 1600; i += 500) {
 		txmsg_start = 0;
 		txmsg_end = i;
+		txmsg_start_push = 0;
+		txmsg_end_push = i;
 		err = test_exec(cgrp, &opt);
 		if (err)
 			goto out;
@@ -1307,6 +1407,8 @@ static int test_start_end(int cgrp)
 	for (i = 199; i <= 1600; i += 500) {
 		txmsg_start = 100;
 		txmsg_end = i;
+		txmsg_start_push = 100;
+		txmsg_end_push = i;
 		err = test_exec(cgrp, &opt);
 		if (err)
 			goto out;
@@ -1315,6 +1417,8 @@ static int test_start_end(int cgrp)
 	/* Test start/end with cork pulling last sg entry */
 	txmsg_start = 1500;
 	txmsg_end = 1600;
+	txmsg_start_push = 1500;
+	txmsg_end_push = 1600;
 	err = test_exec(cgrp, &opt);
 	if (err)
 		goto out;
@@ -1322,6 +1426,8 @@ static int test_start_end(int cgrp)
 	/* Test start/end pull of single byte in last page */
 	txmsg_start = 1111;
 	txmsg_end = 1112;
+	txmsg_start_push = 1111;
+	txmsg_end_push = 1112;
 	err = test_exec(cgrp, &opt);
 	if (err)
 		goto out;
@@ -1329,6 +1435,8 @@ static int test_start_end(int cgrp)
 	/* Test start/end with end < start */
 	txmsg_start = 1111;
 	txmsg_end = 0;
+	txmsg_start_push = 1111;
+	txmsg_end_push = 0;
 	err = test_exec(cgrp, &opt);
 	if (err)
 		goto out;
@@ -1336,6 +1444,8 @@ static int test_start_end(int cgrp)
 	/* Test start/end with end > data */
 	txmsg_start = 0;
 	txmsg_end = 1601;
+	txmsg_start_push = 0;
+	txmsg_end_push = 1601;
 	err = test_exec(cgrp, &opt);
 	if (err)
 		goto out;
@@ -1343,6 +1453,8 @@ static int test_start_end(int cgrp)
 	/* Test start/end with start > data */
 	txmsg_start = 1601;
 	txmsg_end = 1600;
+	txmsg_start_push = 1601;
+	txmsg_end_push = 1600;
 	err = test_exec(cgrp, &opt);
 
 out:
@@ -1358,7 +1470,7 @@ char *map_names[] = {
 	"sock_map_redir",
 	"sock_apply_bytes",
 	"sock_cork_bytes",
-	"sock_pull_bytes",
+	"sock_bytes",
 	"sock_redir_flags",
 	"sock_skb_opts",
 };
@@ -1465,7 +1577,7 @@ static int __test_suite(int cg_fd, char *bpf_file)
 	}
 
 	/* Tests basic commands and APIs with range of iov values */
-	txmsg_start = txmsg_end = 0;
+	txmsg_start = txmsg_end = txmsg_start_push = txmsg_end_push = 0;
 	err = test_txmsg(cg_fd);
 	if (err)
 		goto out;
@@ -1514,7 +1626,7 @@ int main(int argc, char **argv)
 	if (argc < 2)
 		return test_suite(-1);
 
-	while ((opt = getopt_long(argc, argv, ":dhvc:r:i:l:t:",
+	while ((opt = getopt_long(argc, argv, ":dhvc:r:i:l:t:p:q:",
 				  long_options, &longindex)) != -1) {
 		switch (opt) {
 		case 's':
@@ -1523,6 +1635,12 @@ int main(int argc, char **argv)
 		case 'e':
 			txmsg_end = atoi(optarg);
 			break;
+		case 'p':
+			txmsg_start_push = atoi(optarg);
+			break;
+		case 'q':
+			txmsg_end_push = atoi(optarg);
+			break;
 		case 'a':
 			txmsg_apply = atoi(optarg);
 			break;

tools/testing/selftests/bpf/test_sockmap_kern.h

@@ -70,11 +70,11 @@ struct bpf_map_def SEC("maps") sock_cork_bytes = {
 	.max_entries = 1
 };
 
-struct bpf_map_def SEC("maps") sock_pull_bytes = {
+struct bpf_map_def SEC("maps") sock_bytes = {
 	.type = BPF_MAP_TYPE_ARRAY,
 	.key_size = sizeof(int),
 	.value_size = sizeof(int),
-	.max_entries = 2
+	.max_entries = 4
 };
 
 struct bpf_map_def SEC("maps") sock_redir_flags = {
@@ -181,8 +181,8 @@ int bpf_sockmap(struct bpf_sock_ops *skops)
 SEC("sk_msg1")
 int bpf_prog4(struct sk_msg_md *msg)
 {
-	int *bytes, zero = 0, one = 1;
-	int *start, *end;
+	int *bytes, zero = 0, one = 1, two = 2, three = 3;
+	int *start, *end, *start_push, *end_push;
 
 	bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
 	if (bytes)
@@ -190,18 +190,24 @@ int bpf_prog4(struct sk_msg_md *msg)
 	bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero);
 	if (bytes)
 		bpf_msg_cork_bytes(msg, *bytes);
-	start = bpf_map_lookup_elem(&sock_pull_bytes, &zero);
-	end = bpf_map_lookup_elem(&sock_pull_bytes, &one);
+	start = bpf_map_lookup_elem(&sock_bytes, &zero);
+	end = bpf_map_lookup_elem(&sock_bytes, &one);
 	if (start && end)
 		bpf_msg_pull_data(msg, *start, *end, 0);
+	start_push = bpf_map_lookup_elem(&sock_bytes, &two);
+	end_push = bpf_map_lookup_elem(&sock_bytes, &three);
+	if (start_push && end_push)
+		bpf_msg_push_data(msg, *start_push, *end_push, 0);
 	return SK_PASS;
 }
 
 SEC("sk_msg2")
 int bpf_prog5(struct sk_msg_md *msg)
 {
-	int err1 = -1, err2 = -1, zero = 0, one = 1;
-	int *bytes, *start, *end, len1, len2;
+	int zero = 0, one = 1, two = 2, three = 3;
+	int *start, *end, *start_push, *end_push;
+	int *bytes, len1, len2 = 0, len3;
+	int err1 = -1, err2 = -1;
 
 	bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
 	if (bytes)
@@ -210,8 +216,8 @@ int bpf_prog5(struct sk_msg_md *msg)
 	if (bytes)
 		err2 = bpf_msg_cork_bytes(msg, *bytes);
 	len1 = (__u64)msg->data_end - (__u64)msg->data;
-	start = bpf_map_lookup_elem(&sock_pull_bytes, &zero);
-	end = bpf_map_lookup_elem(&sock_pull_bytes, &one);
+	start = bpf_map_lookup_elem(&sock_bytes, &zero);
+	end = bpf_map_lookup_elem(&sock_bytes, &one);
 	if (start && end) {
 		int err;
 
@@ -225,6 +231,23 @@ int bpf_prog5(struct sk_msg_md *msg)
 		bpf_printk("sk_msg2: length update %i->%i\n",
 			   len1, len2);
 	}
+
+	start_push = bpf_map_lookup_elem(&sock_bytes, &two);
+	end_push = bpf_map_lookup_elem(&sock_bytes, &three);
+	if (start_push && end_push) {
+		int err;
+
+		bpf_printk("sk_msg2: push(%i:%i)\n",
+			   start_push ? *start_push : 0,
+			   end_push ? *end_push : 0);
+		err = bpf_msg_push_data(msg, *start_push, *end_push, 0);
+		if (err)
+			bpf_printk("sk_msg2: push_data err %i\n", err);
+		len3 = (__u64)msg->data_end - (__u64)msg->data;
+		bpf_printk("sk_msg2: length push_update %i->%i\n",
+			   len2 ? len2 : len1, len3);
+	}
+
 	bpf_printk("sk_msg2: data length %i err1 %i err2 %i\n",
 		   len1, err1, err2);
 	return SK_PASS;
@@ -233,8 +256,8 @@ int bpf_prog5(struct sk_msg_md *msg)
 SEC("sk_msg3")
 int bpf_prog6(struct sk_msg_md *msg)
 {
-	int *bytes, zero = 0, one = 1, key = 0;
-	int *start, *end, *f;
+	int *bytes, *start, *end, *start_push, *end_push, *f;
+	int zero = 0, one = 1, two = 2, three = 3, key = 0;
 	__u64 flags = 0;
 
 	bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
@@ -243,10 +266,17 @@ int bpf_prog6(struct sk_msg_md *msg)
 	bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero);
 	if (bytes)
 		bpf_msg_cork_bytes(msg, *bytes);
-	start = bpf_map_lookup_elem(&sock_pull_bytes, &zero);
-	end = bpf_map_lookup_elem(&sock_pull_bytes, &one);
+
+	start = bpf_map_lookup_elem(&sock_bytes, &zero);
+	end = bpf_map_lookup_elem(&sock_bytes, &one);
 	if (start && end)
 		bpf_msg_pull_data(msg, *start, *end, 0);
+
+	start_push = bpf_map_lookup_elem(&sock_bytes, &two);
+	end_push = bpf_map_lookup_elem(&sock_bytes, &three);
+	if (start_push && end_push)
+		bpf_msg_push_data(msg, *start_push, *end_push, 0);
+
 	f = bpf_map_lookup_elem(&sock_redir_flags, &zero);
 	if (f && *f) {
 		key = 2;
@@ -262,8 +292,9 @@ int bpf_prog6(struct sk_msg_md *msg)
 SEC("sk_msg4")
 int bpf_prog7(struct sk_msg_md *msg)
 {
-	int err1 = 0, err2 = 0, zero = 0, one = 1, key = 0;
-	int *f, *bytes, *start, *end, len1, len2;
+	int zero = 0, one = 1, two = 2, three = 3, len1, len2 = 0, len3;
+	int *bytes, *start, *end, *start_push, *end_push, *f;
+	int err1 = 0, err2 = 0, key = 0;
 	__u64 flags = 0;
 
 		int err;
@@ -274,10 +305,10 @@ int bpf_prog7(struct sk_msg_md *msg)
 	if (bytes)
 		err2 = bpf_msg_cork_bytes(msg, *bytes);
 	len1 = (__u64)msg->data_end - (__u64)msg->data;
-	start = bpf_map_lookup_elem(&sock_pull_bytes, &zero);
-	end = bpf_map_lookup_elem(&sock_pull_bytes, &one);
-	if (start && end) {
 
+	start = bpf_map_lookup_elem(&sock_bytes, &zero);
+	end = bpf_map_lookup_elem(&sock_bytes, &one);
+	if (start && end) {
 		bpf_printk("sk_msg2: pull(%i:%i)\n",
 			   start ? *start : 0, end ? *end : 0);
 		err = bpf_msg_pull_data(msg, *start, *end, 0);
@@ -288,6 +319,22 @@ int bpf_prog7(struct sk_msg_md *msg)
 		bpf_printk("sk_msg2: length update %i->%i\n",
 			   len1, len2);
 	}
+
+	start_push = bpf_map_lookup_elem(&sock_bytes, &two);
+	end_push = bpf_map_lookup_elem(&sock_bytes, &three);
+	if (start_push && end_push) {
+		bpf_printk("sk_msg4: push(%i:%i)\n",
+			   start_push ? *start_push : 0,
+			   end_push ? *end_push : 0);
+		err = bpf_msg_push_data(msg, *start_push, *end_push, 0);
+		if (err)
+			bpf_printk("sk_msg4: push_data err %i\n",
+				   err);
+		len3 = (__u64)msg->data_end - (__u64)msg->data;
+		bpf_printk("sk_msg4: length push_update %i->%i\n",
+			   len2 ? len2 : len1, len3);
+	}
+
 	f = bpf_map_lookup_elem(&sock_redir_flags, &zero);
 	if (f && *f) {
 		key = 2;
@@ -342,8 +389,8 @@ int bpf_prog9(struct sk_msg_md *msg)
 SEC("sk_msg7")
 int bpf_prog10(struct sk_msg_md *msg)
 {
-	int *bytes, zero = 0, one = 1;
-	int *start, *end;
+	int *bytes, *start, *end, *start_push, *end_push;
+	int zero = 0, one = 1, two = 2, three = 3;
 
 	bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
 	if (bytes)
@@ -351,10 +398,14 @@ int bpf_prog10(struct sk_msg_md *msg)
 	bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero);
 	if (bytes)
 		bpf_msg_cork_bytes(msg, *bytes);
-	start = bpf_map_lookup_elem(&sock_pull_bytes, &zero);
-	end = bpf_map_lookup_elem(&sock_pull_bytes, &one);
+	start = bpf_map_lookup_elem(&sock_bytes, &zero);
+	end = bpf_map_lookup_elem(&sock_bytes, &one);
 	if (start && end)
 		bpf_msg_pull_data(msg, *start, *end, 0);
+	start_push = bpf_map_lookup_elem(&sock_bytes, &two);
+	end_push = bpf_map_lookup_elem(&sock_bytes, &three);
+	if (start_push && end_push)
+		bpf_msg_push_data(msg, *start_push, *end_push, 0);
 
 	return SK_DROP;
 }

tools/testing/selftests/bpf/test_stack_map.c

@@ -0,0 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2018 Politecnico di Torino
+#define MAP_TYPE BPF_MAP_TYPE_STACK
+#include "test_queue_stack_map.h"

tools/testing/selftests/bpf/test_verifier.c

@@ -3430,7 +3430,7 @@ static struct bpf_test tests[] = {
 			BPF_ST_MEM(BPF_DW, BPF_REG_1, offsetof(struct __sk_buff, mark), 0),
 			BPF_EXIT_INSN(),
 		},
-		.errstr = "BPF_ST stores into R1 inv is not allowed",
+		.errstr = "BPF_ST stores into R1 ctx is not allowed",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	},
@@ -3442,7 +3442,7 @@ static struct bpf_test tests[] = {
 				     BPF_REG_0, offsetof(struct __sk_buff, mark), 0),
 			BPF_EXIT_INSN(),
 		},
-		.errstr = "BPF_XADD stores into R1 inv is not allowed",
+		.errstr = "BPF_XADD stores into R1 ctx is not allowed",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	},
@@ -4862,6 +4862,177 @@ static struct bpf_test tests[] = {
 		.result = REJECT,
 		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
+	{
+		"direct packet read test#1 for CGROUP_SKB",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct __sk_buff, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct __sk_buff, data_end)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_1,
+				    offsetof(struct __sk_buff, len)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_5, BPF_REG_1,
+				    offsetof(struct __sk_buff, pkt_type)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
+				    offsetof(struct __sk_buff, mark)),
+			BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_6,
+				    offsetof(struct __sk_buff, mark)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1,
+				    offsetof(struct __sk_buff, queue_mapping)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_8, BPF_REG_1,
+				    offsetof(struct __sk_buff, protocol)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_9, BPF_REG_1,
+				    offsetof(struct __sk_buff, vlan_present)),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1),
+			BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	},
+	{
+		"direct packet read test#2 for CGROUP_SKB",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_1,
+				    offsetof(struct __sk_buff, vlan_tci)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_5, BPF_REG_1,
+				    offsetof(struct __sk_buff, vlan_proto)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
+				    offsetof(struct __sk_buff, priority)),
+			BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_6,
+				    offsetof(struct __sk_buff, priority)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1,
+				    offsetof(struct __sk_buff,
+					     ingress_ifindex)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_8, BPF_REG_1,
+				    offsetof(struct __sk_buff, tc_index)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_9, BPF_REG_1,
+				    offsetof(struct __sk_buff, hash)),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	},
+	{
+		"direct packet read test#3 for CGROUP_SKB",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_1,
+				    offsetof(struct __sk_buff, cb[0])),
+			BPF_LDX_MEM(BPF_W, BPF_REG_5, BPF_REG_1,
+				    offsetof(struct __sk_buff, cb[1])),
+			BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
+				    offsetof(struct __sk_buff, cb[2])),
+			BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1,
+				    offsetof(struct __sk_buff, cb[3])),
+			BPF_LDX_MEM(BPF_W, BPF_REG_8, BPF_REG_1,
+				    offsetof(struct __sk_buff, cb[4])),
+			BPF_LDX_MEM(BPF_W, BPF_REG_9, BPF_REG_1,
+				    offsetof(struct __sk_buff, napi_id)),
+			BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_4,
+				    offsetof(struct __sk_buff, cb[0])),
+			BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_5,
+				    offsetof(struct __sk_buff, cb[1])),
+			BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_6,
+				    offsetof(struct __sk_buff, cb[2])),
+			BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_7,
+				    offsetof(struct __sk_buff, cb[3])),
+			BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_8,
+				    offsetof(struct __sk_buff, cb[4])),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	},
+	{
+		"direct packet read test#4 for CGROUP_SKB",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct __sk_buff, family)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct __sk_buff, remote_ip4)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_1,
+				    offsetof(struct __sk_buff, local_ip4)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_5, BPF_REG_1,
+				    offsetof(struct __sk_buff, remote_ip6[0])),
+			BPF_LDX_MEM(BPF_W, BPF_REG_5, BPF_REG_1,
+				    offsetof(struct __sk_buff, remote_ip6[1])),
+			BPF_LDX_MEM(BPF_W, BPF_REG_5, BPF_REG_1,
+				    offsetof(struct __sk_buff, remote_ip6[2])),
+			BPF_LDX_MEM(BPF_W, BPF_REG_5, BPF_REG_1,
+				    offsetof(struct __sk_buff, remote_ip6[3])),
+			BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
+				    offsetof(struct __sk_buff, local_ip6[0])),
+			BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
+				    offsetof(struct __sk_buff, local_ip6[1])),
+			BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
+				    offsetof(struct __sk_buff, local_ip6[2])),
+			BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
+				    offsetof(struct __sk_buff, local_ip6[3])),
+			BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1,
+				    offsetof(struct __sk_buff, remote_port)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_8, BPF_REG_1,
+				    offsetof(struct __sk_buff, local_port)),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	},
+	{
+		"invalid access of tc_classid for CGROUP_SKB",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+				    offsetof(struct __sk_buff, tc_classid)),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = REJECT,
+		.errstr = "invalid bpf_context access",
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	},
+	{
+		"invalid access of data_meta for CGROUP_SKB",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+				    offsetof(struct __sk_buff, data_meta)),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = REJECT,
+		.errstr = "invalid bpf_context access",
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	},
+	{
+		"invalid access of flow_keys for CGROUP_SKB",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+				    offsetof(struct __sk_buff, flow_keys)),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = REJECT,
+		.errstr = "invalid bpf_context access",
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	},
+	{
+		"invalid write access to napi_id for CGROUP_SKB",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_9, BPF_REG_1,
+				    offsetof(struct __sk_buff, napi_id)),
+			BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_9,
+				    offsetof(struct __sk_buff, napi_id)),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = REJECT,
+		.errstr = "invalid bpf_context access",
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	},
 	{
 		"valid cgroup storage access",
 		.insns = {
@@ -5499,7 +5670,7 @@ static struct bpf_test tests[] = {
 		.errstr_unpriv = "R2 leaks addr into mem",
 		.result_unpriv = REJECT,
 		.result = REJECT,
-		.errstr = "BPF_XADD stores into R1 inv is not allowed",
+		.errstr = "BPF_XADD stores into R1 ctx is not allowed",
 	},
 	{
 		"leak pointer into ctx 2",
@@ -5514,7 +5685,7 @@ static struct bpf_test tests[] = {
 		.errstr_unpriv = "R10 leaks addr into mem",
 		.result_unpriv = REJECT,
 		.result = REJECT,
-		.errstr = "BPF_XADD stores into R1 inv is not allowed",
+		.errstr = "BPF_XADD stores into R1 ctx is not allowed",
 	},
 	{
 		"leak pointer into ctx 3",
@@ -12463,7 +12634,7 @@ static struct bpf_test tests[] = {
 			BPF_EXIT_INSN(),
 		},
 		.result = REJECT,
-		.errstr = "BPF_XADD stores into R2 ctx",
+		.errstr = "BPF_XADD stores into R2 pkt is not allowed",
 		.prog_type = BPF_PROG_TYPE_XDP,
 	},
 	{

tools/testing/selftests/bpf/trace_helpers.c

@@ -41,6 +41,7 @@ int load_kallsyms(void)
 		syms[i].name = strdup(func);
 		i++;
 	}
+	fclose(f);
 	sym_cnt = i;
 	qsort(syms, sym_cnt, sizeof(struct ksym), ksym_cmp);
 	return 0;
@@ -124,10 +125,11 @@ struct perf_event_sample {
 	char data[];
 };
 
-static enum bpf_perf_event_ret bpf_perf_event_print(void *event, void *priv)
+static enum bpf_perf_event_ret
+bpf_perf_event_print(struct perf_event_header *hdr, void *private_data)
 {
-	struct perf_event_sample *e = event;
-	perf_event_print_fn fn = priv;
+	struct perf_event_sample *e = (struct perf_event_sample *)hdr;
+	perf_event_print_fn fn = private_data;
 	int ret;
 
 	if (e->header.type == PERF_RECORD_SAMPLE) {